diff options
1259 files changed, 25518 insertions, 20247 deletions
diff --git a/Documentation/ABI/stable/sysfs-devices-system-xen_memory b/Documentation/ABI/stable/sysfs-devices-system-xen_memory index caa311d59ac1..6d83f95a8a8e 100644 --- a/Documentation/ABI/stable/sysfs-devices-system-xen_memory +++ b/Documentation/ABI/stable/sysfs-devices-system-xen_memory @@ -75,3 +75,12 @@ Contact: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com> Description: Amount (in KiB) of low (or normal) memory in the balloon. + +What: /sys/devices/system/xen_memory/xen_memory0/scrub_pages +Date: September 2018 +KernelVersion: 4.20 +Contact: xen-devel@lists.xenproject.org +Description: + Control scrubbing pages before returning them to Xen for others domains + use. Can be set with xen_scrub_pages cmdline + parameter. Default value controlled with CONFIG_XEN_SCRUB_PAGES_DEFAULT. diff --git a/Documentation/ABI/testing/sysfs-class-net-dsa b/Documentation/ABI/testing/sysfs-class-net-dsa new file mode 100644 index 000000000000..f240221e071e --- /dev/null +++ b/Documentation/ABI/testing/sysfs-class-net-dsa @@ -0,0 +1,7 @@ +What: /sys/class/net/<iface>/tagging +Date: August 2018 +KernelVersion: 4.20 +Contact: netdev@vger.kernel.org +Description: + String indicating the type of tagging protocol used by the + DSA slave network device. diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt index 9871e649ffef..92eb1f42240d 100644 --- a/Documentation/admin-guide/kernel-parameters.txt +++ b/Documentation/admin-guide/kernel-parameters.txt @@ -3523,6 +3523,12 @@ ramdisk_size= [RAM] Sizes of RAM disks in kilobytes See Documentation/blockdev/ramdisk.txt. + random.trust_cpu={on,off} + [KNL] Enable or disable trusting the use of the + CPU's random number generator (if available) to + fully seed the kernel's CRNG. Default is controlled + by CONFIG_RANDOM_TRUST_CPU. + ras=option[,option,...] [KNL] RAS-specific options cec_disable [X86] @@ -4994,6 +5000,12 @@ Disables the PV optimizations forcing the HVM guest to run as generic HVM guest with no PV drivers. + xen_scrub_pages= [XEN] + Boolean option to control scrubbing pages before giving them back + to Xen, for use by other domains. Can be also changed at runtime + with /sys/devices/system/xen_memory/xen_memory0/scrub_pages. + Default value controlled with CONFIG_XEN_SCRUB_PAGES_DEFAULT. + xirc2ps_cs= [NET,PCMCIA] Format: <irq>,<irq_mask>,<io>,<full_duplex>,<do_sound>,<lockup_hack>[,<irq2>[,<irq3>[,<irq4>]]] diff --git a/Documentation/device-mapper/dm-raid.txt b/Documentation/device-mapper/dm-raid.txt index 390c145f01d7..52a719b49afd 100644 --- a/Documentation/device-mapper/dm-raid.txt +++ b/Documentation/device-mapper/dm-raid.txt @@ -348,3 +348,7 @@ Version History 1.13.1 Fix deadlock caused by early md_stop_writes(). Also fix size an state races. 1.13.2 Fix raid redundancy validation and avoid keeping raid set frozen +1.14.0 Fix reshape race on small devices. Fix stripe adding reshape + deadlock/potential data corruption. Update superblock when + specific devices are requested via rebuild. Fix RAID leg + rebuild errors. diff --git a/Documentation/devicetree/bindings/i2c/i2c-imx-lpi2c.txt b/Documentation/devicetree/bindings/i2c/i2c-imx-lpi2c.txt index 00e4365d7206..091c8dfd3229 100644 --- a/Documentation/devicetree/bindings/i2c/i2c-imx-lpi2c.txt +++ b/Documentation/devicetree/bindings/i2c/i2c-imx-lpi2c.txt @@ -3,7 +3,6 @@ Required properties: - compatible : - "fsl,imx7ulp-lpi2c" for LPI2C compatible with the one integrated on i.MX7ULP soc - - "fsl,imx8dv-lpi2c" for LPI2C compatible with the one integrated on i.MX8DV soc - reg : address and length of the lpi2c master registers - interrupts : lpi2c interrupt - clocks : lpi2c clock specifier @@ -11,7 +10,7 @@ Required properties: Examples: lpi2c7: lpi2c7@40a50000 { - compatible = "fsl,imx8dv-lpi2c"; + compatible = "fsl,imx7ulp-lpi2c"; reg = <0x40A50000 0x10000>; interrupt-parent = <&intc>; interrupts = <GIC_SPI 37 IRQ_TYPE_LEVEL_HIGH>; diff --git a/Documentation/devicetree/bindings/net/brcm,unimac-mdio.txt b/Documentation/devicetree/bindings/net/brcm,unimac-mdio.txt index 4648948f7c3b..e15589f47787 100644 --- a/Documentation/devicetree/bindings/net/brcm,unimac-mdio.txt +++ b/Documentation/devicetree/bindings/net/brcm,unimac-mdio.txt @@ -19,6 +19,9 @@ Optional properties: - interrupt-names: must be "mdio_done_error" when there is a share interrupt fed to this hardware block, or must be "mdio_done" for the first interrupt and "mdio_error" for the second when there are separate interrupts +- clocks: A reference to the clock supplying the MDIO bus controller +- clock-frequency: the MDIO bus clock that must be output by the MDIO bus + hardware, if absent, the default hardware values are used Child nodes of this MDIO bus controller node are standard Ethernet PHY device nodes as described in Documentation/devicetree/bindings/net/phy.txt diff --git a/Documentation/devicetree/bindings/net/dsa/lantiq-gswip.txt b/Documentation/devicetree/bindings/net/dsa/lantiq-gswip.txt new file mode 100644 index 000000000000..886cbe8ffb38 --- /dev/null +++ b/Documentation/devicetree/bindings/net/dsa/lantiq-gswip.txt @@ -0,0 +1,143 @@ +Lantiq GSWIP Ethernet switches +================================== + +Required properties for GSWIP core: + +- compatible : "lantiq,xrx200-gswip" for the embedded GSWIP in the + xRX200 SoC +- reg : memory range of the GSWIP core registers + : memory range of the GSWIP MDIO registers + : memory range of the GSWIP MII registers + +See Documentation/devicetree/bindings/net/dsa/dsa.txt for a list of +additional required and optional properties. + + +Required properties for MDIO bus: +- compatible : "lantiq,xrx200-mdio" for the MDIO bus inside the GSWIP + core of the xRX200 SoC and the PHYs connected to it. + +See Documentation/devicetree/bindings/net/mdio.txt for a list of additional +required and optional properties. + + +Required properties for GPHY firmware loading: +- compatible : "lantiq,xrx200-gphy-fw", "lantiq,gphy-fw" + "lantiq,xrx300-gphy-fw", "lantiq,gphy-fw" + "lantiq,xrx330-gphy-fw", "lantiq,gphy-fw" + for the loading of the firmware into the embedded + GPHY core of the SoC. +- lantiq,rcu : reference to the rcu syscon + +The GPHY firmware loader has a list of GPHY entries, one for each +embedded GPHY + +- reg : Offset of the GPHY firmware register in the RCU + register range +- resets : list of resets of the embedded GPHY +- reset-names : list of names of the resets + +Example: + +Ethernet switch on the VRX200 SoC: + +switch@e108000 { + #address-cells = <1>; + #size-cells = <0>; + compatible = "lantiq,xrx200-gswip"; + reg = < 0xe108000 0x3100 /* switch */ + 0xe10b100 0xd8 /* mdio */ + 0xe10b1d8 0x130 /* mii */ + >; + dsa,member = <0 0>; + + ports { + #address-cells = <1>; + #size-cells = <0>; + + port@0 { + reg = <0>; + label = "lan3"; + phy-mode = "rgmii"; + phy-handle = <&phy0>; + }; + + port@1 { + reg = <1>; + label = "lan4"; + phy-mode = "rgmii"; + phy-handle = <&phy1>; + }; + + port@2 { + reg = <2>; + label = "lan2"; + phy-mode = "internal"; + phy-handle = <&phy11>; + }; + + port@4 { + reg = <4>; + label = "lan1"; + phy-mode = "internal"; + phy-handle = <&phy13>; + }; + + port@5 { + reg = <5>; + label = "wan"; + phy-mode = "rgmii"; + phy-handle = <&phy5>; + }; + + port@6 { + reg = <0x6>; + label = "cpu"; + ethernet = <ð0>; + }; + }; + + mdio { + #address-cells = <1>; + #size-cells = <0>; + compatible = "lantiq,xrx200-mdio"; + reg = <0>; + + phy0: ethernet-phy@0 { + reg = <0x0>; + }; + phy1: ethernet-phy@1 { + reg = <0x1>; + }; + phy5: ethernet-phy@5 { + reg = <0x5>; + }; + phy11: ethernet-phy@11 { + reg = <0x11>; + }; + phy13: ethernet-phy@13 { + reg = <0x13>; + }; + }; + + gphy-fw { + compatible = "lantiq,xrx200-gphy-fw", "lantiq,gphy-fw"; + lantiq,rcu = <&rcu0>; + #address-cells = <1>; + #size-cells = <0>; + + gphy@20 { + reg = <0x20>; + + resets = <&reset0 31 30>; + reset-names = "gphy"; + }; + + gphy@68 { + reg = <0x68>; + + resets = <&reset0 29 28>; + reset-names = "gphy"; + }; + }; +}; diff --git a/Documentation/devicetree/bindings/net/lantiq,xrx200-net.txt b/Documentation/devicetree/bindings/net/lantiq,xrx200-net.txt new file mode 100644 index 000000000000..5ff5e68bbbb6 --- /dev/null +++ b/Documentation/devicetree/bindings/net/lantiq,xrx200-net.txt @@ -0,0 +1,21 @@ +Lantiq xRX200 GSWIP PMAC Ethernet driver +================================== + +Required properties: + +- compatible : "lantiq,xrx200-net" for the PMAC of the embedded + : GSWIP in the xXR200 +- reg : memory range of the PMAC core inside of the GSWIP core +- interrupts : TX and RX DMA interrupts. Use interrupt-names "tx" for + : the TX interrupt and "rx" for the RX interrupt. + +Example: + +ethernet@e10b308 { + #address-cells = <1>; + #size-cells = <0>; + compatible = "lantiq,xrx200-net"; + reg = <0xe10b308 0xcf8>; + interrupts = <73>, <72>; + interrupt-names = "tx", "rx"; +}; diff --git a/Documentation/devicetree/bindings/net/macb.txt b/Documentation/devicetree/bindings/net/macb.txt index 457d5ae16f23..3e17ac1d5d58 100644 --- a/Documentation/devicetree/bindings/net/macb.txt +++ b/Documentation/devicetree/bindings/net/macb.txt @@ -10,6 +10,7 @@ Required properties: Use "cdns,pc302-gem" for Picochip picoXcell pc302 and later devices based on the Cadence GEM, or the generic form: "cdns,gem". Use "atmel,sama5d2-gem" for the GEM IP (10/100) available on Atmel sama5d2 SoCs. + Use "atmel,sama5d3-macb" for the 10/100Mbit IP available on Atmel sama5d3 SoCs. Use "atmel,sama5d3-gem" for the Gigabit IP available on Atmel sama5d3 SoCs. Use "atmel,sama5d4-gem" for the GEM IP (10/100) available on Atmel sama5d4 SoCs. Use "cdns,zynq-gem" Xilinx Zynq-7xxx SoC. diff --git a/Documentation/devicetree/bindings/net/marvell-pp2.txt b/Documentation/devicetree/bindings/net/marvell-pp2.txt index fc019df0d863..b78397669320 100644 --- a/Documentation/devicetree/bindings/net/marvell-pp2.txt +++ b/Documentation/devicetree/bindings/net/marvell-pp2.txt @@ -31,7 +31,7 @@ required. Required properties (port): -- interrupts: interrupt for the port +- interrupts: interrupt(s) for the port - port-id: ID of the port from the MAC point of view - gop-port-id: only for marvell,armada-7k-pp2, ID of the port from the GOP (Group Of Ports) point of view. This ID is used to index the @@ -43,10 +43,12 @@ Optional properties (port): - marvell,loopback: port is loopback mode - phy: a phandle to a phy node defining the PHY address (as the reg property, a single integer). -- interrupt-names: if more than a single interrupt for rx is given, must - be the name associated to the interrupts listed. Valid - names are: "tx-cpu0", "tx-cpu1", "tx-cpu2", "tx-cpu3", - "rx-shared", "link". +- interrupt-names: if more than a single interrupt for is given, must be the + name associated to the interrupts listed. Valid names are: + "hifX", with X in [0..8], and "link". The names "tx-cpu0", + "tx-cpu1", "tx-cpu2", "tx-cpu3" and "rx-shared" are supported + for backward compatibility but shouldn't be used for new + additions. - marvell,system-controller: a phandle to the system controller. Example for marvell,armada-375-pp2: @@ -89,9 +91,14 @@ cpm_ethernet: ethernet@0 { <ICU_GRP_NSR 43 IRQ_TYPE_LEVEL_HIGH>, <ICU_GRP_NSR 47 IRQ_TYPE_LEVEL_HIGH>, <ICU_GRP_NSR 51 IRQ_TYPE_LEVEL_HIGH>, - <ICU_GRP_NSR 55 IRQ_TYPE_LEVEL_HIGH>; - interrupt-names = "tx-cpu0", "tx-cpu1", "tx-cpu2", - "tx-cpu3", "rx-shared"; + <ICU_GRP_NSR 55 IRQ_TYPE_LEVEL_HIGH>, + <ICU_GRP_NSR 59 IRQ_TYPE_LEVEL_HIGH>, + <ICU_GRP_NSR 63 IRQ_TYPE_LEVEL_HIGH>, + <ICU_GRP_NSR 67 IRQ_TYPE_LEVEL_HIGH>, + <ICU_GRP_NSR 71 IRQ_TYPE_LEVEL_HIGH>, + <ICU_GRP_NSR 129 IRQ_TYPE_LEVEL_HIGH>; + interrupt-names = "hif0", "hif1", "hif2", "hif3", "hif4", + "hif5", "hif6", "hif7", "hif8", "link"; port-id = <0>; gop-port-id = <0>; }; @@ -101,9 +108,14 @@ cpm_ethernet: ethernet@0 { <ICU_GRP_NSR 44 IRQ_TYPE_LEVEL_HIGH>, <ICU_GRP_NSR 48 IRQ_TYPE_LEVEL_HIGH>, <ICU_GRP_NSR 52 IRQ_TYPE_LEVEL_HIGH>, - <ICU_GRP_NSR 56 IRQ_TYPE_LEVEL_HIGH>; - interrupt-names = "tx-cpu0", "tx-cpu1", "tx-cpu2", - "tx-cpu3", "rx-shared"; + <ICU_GRP_NSR 56 IRQ_TYPE_LEVEL_HIGH>, + <ICU_GRP_NSR 60 IRQ_TYPE_LEVEL_HIGH>, + <ICU_GRP_NSR 64 IRQ_TYPE_LEVEL_HIGH>, + <ICU_GRP_NSR 68 IRQ_TYPE_LEVEL_HIGH>, + <ICU_GRP_NSR 72 IRQ_TYPE_LEVEL_HIGH>, + <ICU_GRP_NSR 128 IRQ_TYPE_LEVEL_HIGH>; + interrupt-names = "hif0", "hif1", "hif2", "hif3", "hif4", + "hif5", "hif6", "hif7", "hif8", "link"; port-id = <1>; gop-port-id = <2>; }; @@ -113,9 +125,14 @@ cpm_ethernet: ethernet@0 { <ICU_GRP_NSR 45 IRQ_TYPE_LEVEL_HIGH>, <ICU_GRP_NSR 49 IRQ_TYPE_LEVEL_HIGH>, <ICU_GRP_NSR 53 IRQ_TYPE_LEVEL_HIGH>, - <ICU_GRP_NSR 57 IRQ_TYPE_LEVEL_HIGH>; - interrupt-names = "tx-cpu0", "tx-cpu1", "tx-cpu2", - "tx-cpu3", "rx-shared"; + <ICU_GRP_NSR 57 IRQ_TYPE_LEVEL_HIGH>, + <ICU_GRP_NSR 61 IRQ_TYPE_LEVEL_HIGH>, + <ICU_GRP_NSR 65 IRQ_TYPE_LEVEL_HIGH>, + <ICU_GRP_NSR 69 IRQ_TYPE_LEVEL_HIGH>, + <ICU_GRP_NSR 73 IRQ_TYPE_LEVEL_HIGH>, + <ICU_GRP_NSR 127 IRQ_TYPE_LEVEL_HIGH>; + interrupt-names = "hif0", "hif1", "hif2", "hif3", "hif4", + "hif5", "hif6", "hif7", "hif8", "link"; port-id = <2>; gop-port-id = <3>; }; diff --git a/Documentation/devicetree/bindings/net/renesas,ravb.txt b/Documentation/devicetree/bindings/net/renesas,ravb.txt index da249b7c406c..3530256a879c 100644 --- a/Documentation/devicetree/bindings/net/renesas,ravb.txt +++ b/Documentation/devicetree/bindings/net/renesas,ravb.txt @@ -6,6 +6,7 @@ interface contains. Required properties: - compatible: Must contain one or more of the following: - "renesas,etheravb-r8a7743" for the R8A7743 SoC. + - "renesas,etheravb-r8a7744" for the R8A7744 SoC. - "renesas,etheravb-r8a7745" for the R8A7745 SoC. - "renesas,etheravb-r8a77470" for the R8A77470 SoC. - "renesas,etheravb-r8a7790" for the R8A7790 SoC. diff --git a/Documentation/filesystems/vfs.txt b/Documentation/filesystems/vfs.txt index 4b2084d0f1fb..a6c6a8af48a2 100644 --- a/Documentation/filesystems/vfs.txt +++ b/Documentation/filesystems/vfs.txt @@ -848,7 +848,7 @@ struct file_operations ---------------------- This describes how the VFS can manipulate an open file. As of kernel -4.1, the following members are defined: +4.18, the following members are defined: struct file_operations { struct module *owner; @@ -858,11 +858,11 @@ struct file_operations { ssize_t (*read_iter) (struct kiocb *, struct iov_iter *); ssize_t (*write_iter) (struct kiocb *, struct iov_iter *); int (*iterate) (struct file *, struct dir_context *); + int (*iterate_shared) (struct file *, struct dir_context *); __poll_t (*poll) (struct file *, struct poll_table_struct *); long (*unlocked_ioctl) (struct file *, unsigned int, unsigned long); long (*compat_ioctl) (struct file *, unsigned int, unsigned long); int (*mmap) (struct file *, struct vm_area_struct *); - int (*mremap)(struct file *, struct vm_area_struct *); int (*open) (struct inode *, struct file *); int (*flush) (struct file *, fl_owner_t id); int (*release) (struct inode *, struct file *); @@ -882,6 +882,10 @@ struct file_operations { #ifndef CONFIG_MMU unsigned (*mmap_capabilities)(struct file *); #endif + ssize_t (*copy_file_range)(struct file *, loff_t, struct file *, loff_t, size_t, unsigned int); + int (*clone_file_range)(struct file *, loff_t, struct file *, loff_t, u64); + int (*dedupe_file_range)(struct file *, loff_t, struct file *, loff_t, u64); + int (*fadvise)(struct file *, loff_t, loff_t, int); }; Again, all methods are called without any locks being held, unless @@ -899,6 +903,9 @@ otherwise noted. iterate: called when the VFS needs to read the directory contents + iterate_shared: called when the VFS needs to read the directory contents + when filesystem supports concurrent dir iterators + poll: called by the VFS when a process wants to check if there is activity on this file and (optionally) go to sleep until there is activity. Called by the select(2) and poll(2) system calls @@ -951,6 +958,16 @@ otherwise noted. fallocate: called by the VFS to preallocate blocks or punch a hole. + copy_file_range: called by the copy_file_range(2) system call. + + clone_file_range: called by the ioctl(2) system call for FICLONERANGE and + FICLONE commands. + + dedupe_file_range: called by the ioctl(2) system call for FIDEDUPERANGE + command. + + fadvise: possibly called by the fadvise64() system call. + Note that the file operations are implemented by the specific filesystem in which the inode resides. When opening a device node (character or block special) most filesystems will call special diff --git a/Documentation/media/uapi/dvb/video_function_calls.rst b/Documentation/media/uapi/dvb/video_function_calls.rst index 3f4f6c9ffad7..a4222b6cd2d3 100644 --- a/Documentation/media/uapi/dvb/video_function_calls.rst +++ b/Documentation/media/uapi/dvb/video_function_calls.rst @@ -33,4 +33,3 @@ Video Function Calls video-clear-buffer video-set-streamtype video-set-format - video-set-attributes diff --git a/Documentation/networking/00-INDEX b/Documentation/networking/00-INDEX index 02a323c43261..f4f2b5d6c8d8 100644 --- a/Documentation/networking/00-INDEX +++ b/Documentation/networking/00-INDEX @@ -94,8 +94,8 @@ gianfar.txt - Gianfar Ethernet Driver. i40e.txt - README for the Intel Ethernet Controller XL710 Driver (i40e). -i40evf.txt - - Short note on the Driver for the Intel(R) XL710 X710 Virtual Function +iavf.txt + - README for the Intel Ethernet Adaptive Virtual Function Driver (iavf). ieee802154.txt - Linux IEEE 802.15.4 implementation, API and drivers igb.txt @@ -198,8 +198,6 @@ tc-actions-env-rules.txt - rules for traffic control (tc) actions. timestamping.txt - overview of network packet timestamping variants. -tcp.txt - - short blurb on how TCP output takes place. tcp-thin.txt - kernel tuning options for low rate 'thin' TCP streams. team.txt diff --git a/Documentation/networking/i40evf.txt b/Documentation/networking/iavf.txt index e9b3035b95d0..cc902a2369d6 100644 --- a/Documentation/networking/i40evf.txt +++ b/Documentation/networking/iavf.txt @@ -2,7 +2,7 @@ Linux* Base Driver for Intel(R) Network Connection ================================================== Intel Ethernet Adaptive Virtual Function Linux driver. -Copyright(c) 2013-2017 Intel Corporation. +Copyright(c) 2013-2018 Intel Corporation. Contents ======== @@ -11,20 +11,21 @@ Contents - Known Issues/Troubleshooting - Support -This file describes the i40evf Linux* Base Driver. +This file describes the iavf Linux* Base Driver. This driver +was formerly called i40evf. -The i40evf driver supports the below mentioned virtual function +The iavf driver supports the below mentioned virtual function devices and can only be activated on kernels running the i40e or newer Physical Function (PF) driver compiled with CONFIG_PCI_IOV. -The i40evf driver requires CONFIG_PCI_MSI to be enabled. +The iavf driver requires CONFIG_PCI_MSI to be enabled. -The guest OS loading the i40evf driver must support MSI-X interrupts. +The guest OS loading the iavf driver must support MSI-X interrupts. Supported Hardware ================== Intel XL710 X710 Virtual Function -Intel Ethernet Adaptive Virtual Function Intel X722 Virtual Function +Intel Ethernet Adaptive Virtual Function Identifying Your Adapter ======================== @@ -32,7 +33,8 @@ Identifying Your Adapter For more information on how to identify your adapter, go to the Adapter & Driver ID Guide at: - http://support.intel.com/support/go/network/adapter/idguide.htm + https://www.intel.com/content/www/us/en/support/articles/000005584/network-and-i-o/ethernet-products.html + Known Issues/Troubleshooting ============================ diff --git a/Documentation/networking/netvsc.txt b/Documentation/networking/netvsc.txt index 92f5b31392fa..3bfa635bbbd5 100644 --- a/Documentation/networking/netvsc.txt +++ b/Documentation/networking/netvsc.txt @@ -45,6 +45,15 @@ Features like packets and significantly reduces CPU usage under heavy Rx load. + Large Receive Offload (LRO), or Receive Side Coalescing (RSC) + ------------------------------------------------------------- + The driver supports LRO/RSC in the vSwitch feature. It reduces the per packet + processing overhead by coalescing multiple TCP segments when possible. The + feature is enabled by default on VMs running on Windows Server 2019 and + later. It may be changed by ethtool command: + ethtool -K eth0 lro on + ethtool -K eth0 lro off + SR-IOV support -------------- Hyper-V supports SR-IOV as a hardware acceleration option. If SR-IOV diff --git a/Documentation/networking/tcp.txt b/Documentation/networking/tcp.txt deleted file mode 100644 index 9c7139d57e57..000000000000 --- a/Documentation/networking/tcp.txt +++ /dev/null @@ -1,101 +0,0 @@ -TCP protocol -============ - -Last updated: 3 June 2017 - -Contents -======== - -- Congestion control -- How the new TCP output machine [nyi] works - -Congestion control -================== - -The following variables are used in the tcp_sock for congestion control: -snd_cwnd The size of the congestion window -snd_ssthresh Slow start threshold. We are in slow start if - snd_cwnd is less than this. -snd_cwnd_cnt A counter used to slow down the rate of increase - once we exceed slow start threshold. -snd_cwnd_clamp This is the maximum size that snd_cwnd can grow to. -snd_cwnd_stamp Timestamp for when congestion window last validated. -snd_cwnd_used Used as a highwater mark for how much of the - congestion window is in use. It is used to adjust - snd_cwnd down when the link is limited by the - application rather than the network. - -As of 2.6.13, Linux supports pluggable congestion control algorithms. -A congestion control mechanism can be registered through functions in -tcp_cong.c. The functions used by the congestion control mechanism are -registered via passing a tcp_congestion_ops struct to -tcp_register_congestion_control. As a minimum, the congestion control -mechanism must provide a valid name and must implement either ssthresh, -cong_avoid and undo_cwnd hooks or the "omnipotent" cong_control hook. - -Private data for a congestion control mechanism is stored in tp->ca_priv. -tcp_ca(tp) returns a pointer to this space. This is preallocated space - it -is important to check the size of your private data will fit this space, or -alternatively, space could be allocated elsewhere and a pointer to it could -be stored here. - -There are three kinds of congestion control algorithms currently: The -simplest ones are derived from TCP reno (highspeed, scalable) and just -provide an alternative congestion window calculation. More complex -ones like BIC try to look at other events to provide better -heuristics. There are also round trip time based algorithms like -Vegas and Westwood+. - -Good TCP congestion control is a complex problem because the algorithm -needs to maintain fairness and performance. Please review current -research and RFC's before developing new modules. - -The default congestion control mechanism is chosen based on the -DEFAULT_TCP_CONG Kconfig parameter. If you really want a particular default -value then you can set it using sysctl net.ipv4.tcp_congestion_control. The -module will be autoloaded if needed and you will get the expected protocol. If -you ask for an unknown congestion method, then the sysctl attempt will fail. - -If you remove a TCP congestion control module, then you will get the next -available one. Since reno cannot be built as a module, and cannot be -removed, it will always be available. - -How the new TCP output machine [nyi] works. -=========================================== - -Data is kept on a single queue. The skb->users flag tells us if the frame is -one that has been queued already. To add a frame we throw it on the end. Ack -walks down the list from the start. - -We keep a set of control flags - - - sk->tcp_pend_event - - TCP_PEND_ACK Ack needed - TCP_ACK_NOW Needed now - TCP_WINDOW Window update check - TCP_WINZERO Zero probing - - - sk->transmit_queue The transmission frame begin - sk->transmit_new First new frame pointer - sk->transmit_end Where to add frames - - sk->tcp_last_tx_ack Last ack seen - sk->tcp_dup_ack Dup ack count for fast retransmit - - -Frames are queued for output by tcp_write. We do our best to send the frames -off immediately if possible, but otherwise queue and compute the body -checksum in the copy. - -When a write is done we try to clear any pending events and piggy back them. -If the window is full we queue full sized frames. On the first timeout in -zero window we split this. - -On a timer we walk the retransmit list to send any retransmits, update the -backoff timers etc. A change of route table stamp causes a change of header -and recompute. We add any new tcp level headers and refinish the checksum -before sending. - diff --git a/Documentation/process/changes.rst b/Documentation/process/changes.rst index 61f918b10a0c..d1bf143b446f 100644 --- a/Documentation/process/changes.rst +++ b/Documentation/process/changes.rst @@ -86,7 +86,7 @@ pkg-config The build system, as of 4.18, requires pkg-config to check for installed kconfig tools and to determine flags settings for use in -'make {menu,n,g,x}config'. Previously pkg-config was being used but not +'make {g,x}config'. Previously pkg-config was being used but not verified or documented. Flex diff --git a/Documentation/process/code-of-conduct.rst b/Documentation/process/code-of-conduct.rst new file mode 100644 index 000000000000..ab7c24b5478c --- /dev/null +++ b/Documentation/process/code-of-conduct.rst @@ -0,0 +1,81 @@ +Contributor Covenant Code of Conduct +++++++++++++++++++++++++++++++++++++ + +Our Pledge +========== + +In the interest of fostering an open and welcoming environment, we as +contributors and maintainers pledge to making participation in our project and +our community a harassment-free experience for everyone, regardless of age, body +size, disability, ethnicity, sex characteristics, gender identity and +expression, level of experience, education, socio-economic status, nationality, +personal appearance, race, religion, or sexual identity and orientation. + +Our Standards +============= + +Examples of behavior that contributes to creating a positive environment +include: + +* Using welcoming and inclusive language +* Being respectful of differing viewpoints and experiences +* Gracefully accepting constructive criticism +* Focusing on what is best for the community +* Showing empathy towards other community members + + +Examples of unacceptable behavior by participants include: + +* The use of sexualized language or imagery and unwelcome sexual attention or + advances +* Trolling, insulting/derogatory comments, and personal or political attacks +* Public or private harassment +* Publishing others’ private information, such as a physical or electronic + address, without explicit permission +* Other conduct which could reasonably be considered inappropriate in a + professional setting + + +Our Responsibilities +==================== + +Maintainers are responsible for clarifying the standards of acceptable behavior +and are expected to take appropriate and fair corrective action in response to +any instances of unacceptable behavior. + +Maintainers have the right and responsibility to remove, edit, or reject +comments, commits, code, wiki edits, issues, and other contributions that are +not aligned to this Code of Conduct, or to ban temporarily or permanently any +contributor for other behaviors that they deem inappropriate, threatening, +offensive, or harmful. + +Scope +===== + +This Code of Conduct applies both within project spaces and in public spaces +when an individual is representing the project or its community. Examples of +representing a project or community include using an official project e-mail +address, posting via an official social media account, or acting as an appointed +representative at an online or offline event. Representation of a project may be +further defined and clarified by project maintainers. + +Enforcement +=========== + +Instances of abusive, harassing, or otherwise unacceptable behavior may be +reported by contacting the Technical Advisory Board (TAB) at +<tab@lists.linux-foundation.org>. All complaints will be reviewed and +investigated and will result in a response that is deemed necessary and +appropriate to the circumstances. The TAB is obligated to maintain +confidentiality with regard to the reporter of an incident. Further details of +specific enforcement policies may be posted separately. + +Maintainers who do not follow or enforce the Code of Conduct in good faith may +face temporary or permanent repercussions as determined by other members of the +project’s leadership. + +Attribution +=========== + +This Code of Conduct is adapted from the Contributor Covenant, version 1.4, +available at https://www.contributor-covenant.org/version/1/4/code-of-conduct.html diff --git a/Documentation/process/code-of-conflict.rst b/Documentation/process/code-of-conflict.rst deleted file mode 100644 index 47b6de763203..000000000000 --- a/Documentation/process/code-of-conflict.rst +++ /dev/null @@ -1,28 +0,0 @@ -Code of Conflict ----------------- - -The Linux kernel development effort is a very personal process compared -to "traditional" ways of developing software. Your code and ideas -behind it will be carefully reviewed, often resulting in critique and -criticism. The review will almost always require improvements to the -code before it can be included in the kernel. Know that this happens -because everyone involved wants to see the best possible solution for -the overall success of Linux. This development process has been proven -to create the most robust operating system kernel ever, and we do not -want to do anything to cause the quality of submission and eventual -result to ever decrease. - -If however, anyone feels personally abused, threatened, or otherwise -uncomfortable due to this process, that is not acceptable. If so, -please contact the Linux Foundation's Technical Advisory Board at -<tab@lists.linux-foundation.org>, or the individual members, and they -will work to resolve the issue to the best of their ability. For more -information on who is on the Technical Advisory Board and what their -role is, please see: - - - http://www.linuxfoundation.org/projects/linux/tab - -As a reviewer of code, please strive to keep things civil and focused on -the technical issues involved. We are all humans, and frustrations can -be high on both sides of the process. Try to keep in mind the immortal -words of Bill and Ted, "Be excellent to each other." diff --git a/Documentation/process/index.rst b/Documentation/process/index.rst index 37bd0628b6ee..9ae3e317bddf 100644 --- a/Documentation/process/index.rst +++ b/Documentation/process/index.rst @@ -20,7 +20,7 @@ Below are the essential guides that every developer should read. :maxdepth: 1 howto - code-of-conflict + code-of-conduct development-process submitting-patches coding-style diff --git a/Documentation/scsi/scsi-parameters.txt b/Documentation/scsi/scsi-parameters.txt index 25a4b4cf04a6..92999d4e0cb8 100644 --- a/Documentation/scsi/scsi-parameters.txt +++ b/Documentation/scsi/scsi-parameters.txt @@ -97,6 +97,11 @@ parameters may be changed at runtime by the command allowing boot to proceed. none ignores them, expecting user space to do the scan. + scsi_mod.use_blk_mq= + [SCSI] use blk-mq I/O path by default + See SCSI_MQ_DEFAULT in drivers/scsi/Kconfig. + Format: <y/n> + sim710= [SCSI,HW] See header of drivers/scsi/sim710.c. diff --git a/Documentation/virtual/kvm/api.txt b/Documentation/virtual/kvm/api.txt index c664064f76fb..647f94128a85 100644 --- a/Documentation/virtual/kvm/api.txt +++ b/Documentation/virtual/kvm/api.txt @@ -4510,7 +4510,8 @@ Do not enable KVM_FEATURE_PV_UNHALT if you disable HLT exits. Architectures: s390 Parameters: none Returns: 0 on success, -EINVAL if hpage module parameter was not set - or cmma is enabled + or cmma is enabled, or the VM has the KVM_VM_S390_UCONTROL + flag set With this capability the KVM support for memory backing with 1m pages through hugetlbfs can be enabled for a VM. After the capability is @@ -4521,6 +4522,15 @@ hpage module parameter is not set to 1, -EINVAL is returned. While it is generally possible to create a huge page backed VM without this capability, the VM will not be able to run. +7.14 KVM_CAP_MSR_PLATFORM_INFO + +Architectures: x86 +Parameters: args[0] whether feature should be enabled or not + +With this capability, a guest may read the MSR_PLATFORM_INFO MSR. Otherwise, +a #GP would be raised when the guest tries to access. Currently, this +capability does not enable write permissions of this MSR for the guest. + 8. Other capabilities. ---------------------- diff --git a/Documentation/x86/earlyprintk.txt b/Documentation/x86/earlyprintk.txt index 688e3eeed21d..46933e06c972 100644 --- a/Documentation/x86/earlyprintk.txt +++ b/Documentation/x86/earlyprintk.txt @@ -35,25 +35,25 @@ and two USB cables, connected like this: ( If your system does not list a debug port capability then you probably won't be able to use the USB debug key. ) - b.) You also need a Netchip USB debug cable/key: + b.) You also need a NetChip USB debug cable/key: http://www.plxtech.com/products/NET2000/NET20DC/default.asp - This is a small blue plastic connector with two USB connections, + This is a small blue plastic connector with two USB connections; it draws power from its USB connections. c.) You need a second client/console system with a high speed USB 2.0 port. - d.) The Netchip device must be plugged directly into the physical + d.) The NetChip device must be plugged directly into the physical debug port on the "host/target" system. You cannot use a USB hub in between the physical debug port and the "host/target" system. The EHCI debug controller is bound to a specific physical USB - port and the Netchip device will only work as an early printk + port and the NetChip device will only work as an early printk device in this port. The EHCI host controllers are electrically wired such that the EHCI debug controller is hooked up to the - first physical and there is no way to change this via software. + first physical port and there is no way to change this via software. You can find the physical port through experimentation by trying each physical port on the system and rebooting. Or you can try and use lsusb or look at the kernel info messages emitted by the @@ -65,9 +65,9 @@ and two USB cables, connected like this: to the hardware vendor, because there is no reason not to wire this port into one of the physically accessible ports. - e.) It is also important to note, that many versions of the Netchip + e.) It is also important to note, that many versions of the NetChip device require the "client/console" system to be plugged into the - right and side of the device (with the product logo facing up and + right hand side of the device (with the product logo facing up and readable left to right). The reason being is that the 5 volt power supply is taken from only one side of the device and it must be the side that does not get rebooted. @@ -81,13 +81,18 @@ and two USB cables, connected like this: CONFIG_EARLY_PRINTK_DBGP=y And you need to add the boot command line: "earlyprintk=dbgp". + (If you are using Grub, append it to the 'kernel' line in - /etc/grub.conf) + /etc/grub.conf. If you are using Grub2 on a BIOS firmware system, + append it to the 'linux' line in /boot/grub2/grub.cfg. If you are + using Grub2 on an EFI firmware system, append it to the 'linux' + or 'linuxefi' line in /boot/grub2/grub.cfg or + /boot/efi/EFI/<distro>/grub.cfg.) On systems with more than one EHCI debug controller you must specify the correct EHCI debug controller number. The ordering comes from the PCI bus enumeration of the EHCI controllers. The - default with no number argument is "0" the first EHCI debug + default with no number argument is "0" or the first EHCI debug controller. To use the second EHCI debug controller, you would use the command line: "earlyprintk=dbgp1" @@ -111,7 +116,7 @@ and two USB cables, connected like this: see the raw output. c.) On Nvidia Southbridge based systems: the kernel will try to probe - and find out which port has debug device connected. + and find out which port has a debug device connected. 3. Testing that it works fine: diff --git a/MAINTAINERS b/MAINTAINERS index 2ef884b883c3..15565de091af 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -2311,6 +2311,7 @@ F: drivers/clocksource/cadence_ttc_timer.c F: drivers/i2c/busses/i2c-cadence.c F: drivers/mmc/host/sdhci-of-arasan.c F: drivers/edac/synopsys_edac.c +F: drivers/i2c/busses/i2c-xiic.c ARM64 PORT (AARCH64 ARCHITECTURE) M: Catalin Marinas <catalin.marinas@arm.com> @@ -5624,6 +5625,8 @@ F: lib/fault-inject.c FBTFT Framebuffer drivers M: Thomas Petazzoni <thomas.petazzoni@free-electrons.com> +L: dri-devel@lists.freedesktop.org +L: linux-fbdev@vger.kernel.org S: Maintained F: drivers/staging/fbtft/ @@ -6059,7 +6062,7 @@ F: Documentation/gcc-plugins.txt GASKET DRIVER FRAMEWORK M: Rob Springer <rspringer@google.com> -M: John Joseph <jnjoseph@google.com> +M: Todd Poynor <toddpoynor@google.com> M: Ben Chan <benchan@chromium.org> S: Maintained F: drivers/staging/gasket/ @@ -7015,6 +7018,20 @@ F: drivers/crypto/vmx/aes* F: drivers/crypto/vmx/ghash* F: drivers/crypto/vmx/ppc-xlate.pl +IBM Power PCI Hotplug Driver for RPA-compliant PPC64 platform +M: Tyrel Datwyler <tyreld@linux.vnet.ibm.com> +L: linux-pci@vger.kernel.org +L: linuxppc-dev@lists.ozlabs.org +S: Supported +F: drivers/pci/hotplug/rpaphp* + +IBM Power IO DLPAR Driver for RPA-compliant PPC64 platform +M: Tyrel Datwyler <tyreld@linux.vnet.ibm.com> +L: linux-pci@vger.kernel.org +L: linuxppc-dev@lists.ozlabs.org +S: Supported +F: drivers/pci/hotplug/rpadlpar* + IBM ServeRAID RAID DRIVER S: Orphan F: drivers/scsi/ips.* @@ -7331,7 +7348,7 @@ F: Documentation/networking/ixgb.txt F: Documentation/networking/ixgbe.txt F: Documentation/networking/ixgbevf.txt F: Documentation/networking/i40e.txt -F: Documentation/networking/i40evf.txt +F: Documentation/networking/iavf.txt F: Documentation/networking/ice.txt F: drivers/net/ethernet/intel/ F: drivers/net/ethernet/intel/*/ @@ -8166,6 +8183,15 @@ S: Maintained F: net/l3mdev F: include/net/l3mdev.h +LANTIQ / INTEL Ethernet drivers +M: Hauke Mehrtens <hauke@hauke-m.de> +L: netdev@vger.kernel.org +S: Maintained +F: net/dsa/tag_gswip.c +F: drivers/net/ethernet/lantiq_xrx200.c +F: drivers/net/dsa/lantiq_pce.h +F: drivers/net/dsa/intel_gswip.c + LANTIQ MIPS ARCHITECTURE M: John Crispin <john@phrozen.org> L: linux-mips@linux-mips.org @@ -8299,7 +8325,7 @@ F: include/linux/libata.h F: Documentation/devicetree/bindings/ata/ LIBLOCKDEP -M: Sasha Levin <alexander.levin@verizon.com> +M: Sasha Levin <alexander.levin@microsoft.com> S: Maintained F: tools/lib/lockdep/ @@ -11153,7 +11179,7 @@ F: drivers/pci/controller/dwc/pci-exynos.c PCI DRIVER FOR SYNOPSYS DESIGNWARE M: Jingoo Han <jingoohan1@gmail.com> -M: Joao Pinto <Joao.Pinto@synopsys.com> +M: Gustavo Pimentel <gustavo.pimentel@synopsys.com> L: linux-pci@vger.kernel.org S: Maintained F: Documentation/devicetree/bindings/pci/designware-pcie.txt @@ -11345,10 +11371,10 @@ S: Maintained F: drivers/platform/x86/peaq-wmi.c PER-CPU MEMORY ALLOCATOR +M: Dennis Zhou <dennis@kernel.org> M: Tejun Heo <tj@kernel.org> M: Christoph Lameter <cl@linux.com> -M: Dennis Zhou <dennisszhou@gmail.com> -T: git git://git.kernel.org/pub/scm/linux/kernel/git/tj/percpu.git +T: git git://git.kernel.org/pub/scm/linux/kernel/git/dennis/percpu.git S: Maintained F: include/linux/percpu*.h F: mm/percpu*.c @@ -12243,6 +12269,7 @@ F: Documentation/networking/rds.txt RDT - RESOURCE ALLOCATION M: Fenghua Yu <fenghua.yu@intel.com> +M: Reinette Chatre <reinette.chatre@intel.com> L: linux-kernel@vger.kernel.org S: Supported F: arch/x86/kernel/cpu/intel_rdt* @@ -13432,9 +13459,8 @@ F: drivers/i2c/busses/i2c-synquacer.c F: Documentation/devicetree/bindings/i2c/i2c-synquacer.txt SOCIONEXT UNIPHIER SOUND DRIVER -M: Katsuhiro Suzuki <suzuki.katsuhiro@socionext.com> L: alsa-devel@alsa-project.org (moderated for non-subscribers) -S: Maintained +S: Orphan F: sound/soc/uniphier/ SOEKRIS NET48XX LED SUPPORT @@ -15896,6 +15922,7 @@ F: net/x25/ X86 ARCHITECTURE (32-BIT AND 64-BIT) M: Thomas Gleixner <tglx@linutronix.de> M: Ingo Molnar <mingo@redhat.com> +M: Borislav Petkov <bp@alien8.de> R: "H. Peter Anvin" <hpa@zytor.com> M: x86@kernel.org L: linux-kernel@vger.kernel.org @@ -15924,6 +15951,15 @@ M: Borislav Petkov <bp@alien8.de> S: Maintained F: arch/x86/kernel/cpu/microcode/* +X86 MM +M: Dave Hansen <dave.hansen@linux.intel.com> +M: Andy Lutomirski <luto@kernel.org> +M: Peter Zijlstra <peterz@infradead.org> +L: linux-kernel@vger.kernel.org +T: git git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git x86/mm +S: Maintained +F: arch/x86/mm/ + X86 PLATFORM DRIVERS M: Darren Hart <dvhart@infradead.org> M: Andy Shevchenko <andy@infradead.org> @@ -2,7 +2,7 @@ VERSION = 4 PATCHLEVEL = 19 SUBLEVEL = 0 -EXTRAVERSION = -rc2 +EXTRAVERSION = -rc5 NAME = Merciless Moray # *DOCUMENTATION* @@ -299,19 +299,7 @@ KERNELRELEASE = $(shell cat include/config/kernel.release 2> /dev/null) KERNELVERSION = $(VERSION)$(if $(PATCHLEVEL),.$(PATCHLEVEL)$(if $(SUBLEVEL),.$(SUBLEVEL)))$(EXTRAVERSION) export VERSION PATCHLEVEL SUBLEVEL KERNELRELEASE KERNELVERSION -# SUBARCH tells the usermode build what the underlying arch is. That is set -# first, and if a usermode build is happening, the "ARCH=um" on the command -# line overrides the setting of ARCH below. If a native build is happening, -# then ARCH is assigned, getting whatever value it gets normally, and -# SUBARCH is subsequently ignored. - -SUBARCH := $(shell uname -m | sed -e s/i.86/x86/ -e s/x86_64/x86/ \ - -e s/sun4u/sparc64/ \ - -e s/arm.*/arm/ -e s/sa110/arm/ \ - -e s/s390x/s390/ -e s/parisc64/parisc/ \ - -e s/ppc.*/powerpc/ -e s/mips.*/mips/ \ - -e s/sh[234].*/sh/ -e s/aarch64.*/arm64/ \ - -e s/riscv.*/riscv/) +include scripts/subarch.include # Cross compiling and selecting different set of gcc/bin-utils # --------------------------------------------------------------------------- @@ -616,6 +604,11 @@ CFLAGS_GCOV := -fprofile-arcs -ftest-coverage \ $(call cc-disable-warning,maybe-uninitialized,) export CFLAGS_GCOV +# The arch Makefiles can override CC_FLAGS_FTRACE. We may also append it later. +ifdef CONFIG_FUNCTION_TRACER + CC_FLAGS_FTRACE := -pg +endif + # The arch Makefile can set ARCH_{CPP,A,C}FLAGS to override the default # values of the respective KBUILD_* variables ARCH_CPPFLAGS := @@ -755,9 +748,6 @@ KBUILD_CFLAGS += $(call cc-option, -femit-struct-debug-baseonly) \ endif ifdef CONFIG_FUNCTION_TRACER -ifndef CC_FLAGS_FTRACE -CC_FLAGS_FTRACE := -pg -endif ifdef CONFIG_FTRACE_MCOUNT_RECORD # gcc 5 supports generating the mcount tables directly ifeq ($(call cc-option-yn,-mrecord-mcount),y) diff --git a/arch/arc/Kconfig b/arch/arc/Kconfig index 6d5eb8267e42..b4441b0764d7 100644 --- a/arch/arc/Kconfig +++ b/arch/arc/Kconfig @@ -9,6 +9,7 @@ config ARC def_bool y select ARC_TIMERS + select ARCH_HAS_PTE_SPECIAL select ARCH_HAS_SYNC_DMA_FOR_CPU select ARCH_HAS_SYNC_DMA_FOR_DEVICE select ARCH_HAS_SG_CHAIN @@ -28,8 +29,12 @@ config ARC select GENERIC_SMP_IDLE_THREAD select HAVE_ARCH_KGDB select HAVE_ARCH_TRACEHOOK + select HAVE_DEBUG_STACKOVERFLOW select HAVE_FUTEX_CMPXCHG if FUTEX + select HAVE_GENERIC_DMA_COHERENT select HAVE_IOREMAP_PROT + select HAVE_KERNEL_GZIP + select HAVE_KERNEL_LZMA select HAVE_KPROBES select HAVE_KRETPROBES select HAVE_MEMBLOCK @@ -44,11 +49,6 @@ config ARC select OF_EARLY_FLATTREE select OF_RESERVED_MEM select PERF_USE_VMALLOC if ARC_CACHE_VIPT_ALIASING - select HAVE_DEBUG_STACKOVERFLOW - select HAVE_GENERIC_DMA_COHERENT - select HAVE_KERNEL_GZIP - select HAVE_KERNEL_LZMA - select ARCH_HAS_PTE_SPECIAL config ARCH_HAS_CACHE_LINE_SIZE def_bool y diff --git a/arch/arc/Makefile b/arch/arc/Makefile index fb026196aaab..99cce77ab98f 100644 --- a/arch/arc/Makefile +++ b/arch/arc/Makefile @@ -43,10 +43,7 @@ ifdef CONFIG_ARC_CURR_IN_REG LINUXINCLUDE += -include ${src}/arch/arc/include/asm/current.h endif -upto_gcc44 := $(call cc-ifversion, -le, 0404, y) -atleast_gcc44 := $(call cc-ifversion, -ge, 0404, y) - -cflags-$(atleast_gcc44) += -fsection-anchors +cflags-y += -fsection-anchors cflags-$(CONFIG_ARC_HAS_LLSC) += -mlock cflags-$(CONFIG_ARC_HAS_SWAPE) += -mswape @@ -82,11 +79,6 @@ cflags-$(disable_small_data) += -mno-sdata -fcall-used-gp cflags-$(CONFIG_CPU_BIG_ENDIAN) += -mbig-endian ldflags-$(CONFIG_CPU_BIG_ENDIAN) += -EB -# STAR 9000518362: (fixed with binutils shipping with gcc 4.8) -# arc-linux-uclibc-ld (buildroot) or arceb-elf32-ld (EZChip) don't accept -# --build-id w/o "-marclinux". Default arc-elf32-ld is OK -ldflags-$(upto_gcc44) += -marclinux - LIBGCC := $(shell $(CC) $(cflags-y) --print-libgcc-file-name) # Modules with short calls might break for calls into builtin-kernel diff --git a/arch/arc/boot/dts/axc003.dtsi b/arch/arc/boot/dts/axc003.dtsi index dc91c663bcc0..d75d65ddf8e3 100644 --- a/arch/arc/boot/dts/axc003.dtsi +++ b/arch/arc/boot/dts/axc003.dtsi @@ -94,6 +94,32 @@ }; /* + * Mark DMA peripherals connected via IOC port as dma-coherent. We do + * it via overlay because peripherals defined in axs10x_mb.dtsi are + * used for both AXS101 and AXS103 boards and only AXS103 has IOC (so + * only AXS103 board has HW-coherent DMA peripherals) + * We don't need to mark pgu@17000 as dma-coherent because it uses + * external DMA buffer located outside of IOC aperture. + */ + axs10x_mb { + ethernet@0x18000 { + dma-coherent; + }; + + ehci@0x40000 { + dma-coherent; + }; + + ohci@0x60000 { + dma-coherent; + }; + + mmc@0x15000 { + dma-coherent; + }; + }; + + /* * The DW APB ICTL intc on MB is connected to CPU intc via a * DT "invisible" DW APB GPIO block, configured to simply pass thru * interrupts - setup accordinly in platform init (plat-axs10x/ax10x.c) diff --git a/arch/arc/boot/dts/axc003_idu.dtsi b/arch/arc/boot/dts/axc003_idu.dtsi index 69ff4895f2ba..a05bb737ea63 100644 --- a/arch/arc/boot/dts/axc003_idu.dtsi +++ b/arch/arc/boot/dts/axc003_idu.dtsi @@ -101,6 +101,32 @@ }; /* + * Mark DMA peripherals connected via IOC port as dma-coherent. We do + * it via overlay because peripherals defined in axs10x_mb.dtsi are + * used for both AXS101 and AXS103 boards and only AXS103 has IOC (so + * only AXS103 board has HW-coherent DMA peripherals) + * We don't need to mark pgu@17000 as dma-coherent because it uses + * external DMA buffer located outside of IOC aperture. + */ + axs10x_mb { + ethernet@0x18000 { + dma-coherent; + }; + + ehci@0x40000 { + dma-coherent; + }; + + ohci@0x60000 { + dma-coherent; + }; + + mmc@0x15000 { + dma-coherent; + }; + }; + + /* * This INTC is actually connected to DW APB GPIO * which acts as a wire between MB INTC and CPU INTC. * GPIO INTC is configured in platform init code diff --git a/arch/arc/boot/dts/axs10x_mb.dtsi b/arch/arc/boot/dts/axs10x_mb.dtsi index 47b74fbc403c..37bafd44e36d 100644 --- a/arch/arc/boot/dts/axs10x_mb.dtsi +++ b/arch/arc/boot/dts/axs10x_mb.dtsi @@ -9,6 +9,10 @@ */ / { + aliases { + ethernet = &gmac; + }; + axs10x_mb { compatible = "simple-bus"; #address-cells = <1>; @@ -68,7 +72,7 @@ }; }; - ethernet@0x18000 { + gmac: ethernet@0x18000 { #interrupt-cells = <1>; compatible = "snps,dwmac"; reg = < 0x18000 0x2000 >; @@ -81,6 +85,7 @@ max-speed = <100>; resets = <&creg_rst 5>; reset-names = "stmmaceth"; + mac-address = [00 00 00 00 00 00]; /* Filled in by U-Boot */ }; ehci@0x40000 { diff --git a/arch/arc/boot/dts/hsdk.dts b/arch/arc/boot/dts/hsdk.dts index 006aa3de5348..ef149f59929a 100644 --- a/arch/arc/boot/dts/hsdk.dts +++ b/arch/arc/boot/dts/hsdk.dts @@ -25,6 +25,10 @@ bootargs = "earlycon=uart8250,mmio32,0xf0005000,115200n8 console=ttyS0,115200n8 debug print-fatal-signals=1"; }; + aliases { + ethernet = &gmac; + }; + cpus { #address-cells = <1>; #size-cells = <0>; @@ -163,7 +167,7 @@ #clock-cells = <0>; }; - ethernet@8000 { + gmac: ethernet@8000 { #interrupt-cells = <1>; compatible = "snps,dwmac"; reg = <0x8000 0x2000>; @@ -176,6 +180,8 @@ phy-handle = <&phy0>; resets = <&cgu_rst HSDK_ETH_RESET>; reset-names = "stmmaceth"; + mac-address = [00 00 00 00 00 00]; /* Filled in by U-Boot */ + dma-coherent; mdio { #address-cells = <1>; @@ -194,12 +200,14 @@ compatible = "snps,hsdk-v1.0-ohci", "generic-ohci"; reg = <0x60000 0x100>; interrupts = <15>; + dma-coherent; }; ehci@40000 { compatible = "snps,hsdk-v1.0-ehci", "generic-ehci"; reg = <0x40000 0x100>; interrupts = <15>; + dma-coherent; }; mmc@a000 { @@ -212,6 +220,7 @@ clock-names = "biu", "ciu"; interrupts = <12>; bus-width = <4>; + dma-coherent; }; }; diff --git a/arch/arc/configs/axs101_defconfig b/arch/arc/configs/axs101_defconfig index a635ea972304..41bc08be6a3b 100644 --- a/arch/arc/configs/axs101_defconfig +++ b/arch/arc/configs/axs101_defconfig @@ -1,5 +1,3 @@ -CONFIG_DEFAULT_HOSTNAME="ARCLinux" -# CONFIG_SWAP is not set CONFIG_SYSVIPC=y CONFIG_POSIX_MQUEUE=y # CONFIG_CROSS_MEMORY_ATTACH is not set @@ -63,7 +61,6 @@ CONFIG_MOUSE_PS2_TOUCHKIT=y CONFIG_MOUSE_SERIAL=y CONFIG_MOUSE_SYNAPTICS_USB=y # CONFIG_LEGACY_PTYS is not set -# CONFIG_DEVKMEM is not set CONFIG_SERIAL_8250=y CONFIG_SERIAL_8250_CONSOLE=y CONFIG_SERIAL_8250_DW=y diff --git a/arch/arc/configs/axs103_defconfig b/arch/arc/configs/axs103_defconfig index aa507e423075..1e1c4a8011b5 100644 --- a/arch/arc/configs/axs103_defconfig +++ b/arch/arc/configs/axs103_defconfig @@ -1,5 +1,3 @@ -CONFIG_DEFAULT_HOSTNAME="ARCLinux" -# CONFIG_SWAP is not set CONFIG_SYSVIPC=y CONFIG_POSIX_MQUEUE=y # CONFIG_CROSS_MEMORY_ATTACH is not set @@ -64,7 +62,6 @@ CONFIG_MOUSE_PS2_TOUCHKIT=y CONFIG_MOUSE_SERIAL=y CONFIG_MOUSE_SYNAPTICS_USB=y # CONFIG_LEGACY_PTYS is not set -# CONFIG_DEVKMEM is not set CONFIG_SERIAL_8250=y CONFIG_SERIAL_8250_CONSOLE=y CONFIG_SERIAL_8250_DW=y diff --git a/arch/arc/configs/axs103_smp_defconfig b/arch/arc/configs/axs103_smp_defconfig index eba07f468654..6b0c0cfd5c30 100644 --- a/arch/arc/configs/axs103_smp_defconfig +++ b/arch/arc/configs/axs103_smp_defconfig @@ -1,5 +1,3 @@ -CONFIG_DEFAULT_HOSTNAME="ARCLinux" -# CONFIG_SWAP is not set CONFIG_SYSVIPC=y CONFIG_POSIX_MQUEUE=y # CONFIG_CROSS_MEMORY_ATTACH is not set @@ -65,7 +63,6 @@ CONFIG_MOUSE_PS2_TOUCHKIT=y CONFIG_MOUSE_SERIAL=y CONFIG_MOUSE_SYNAPTICS_USB=y # CONFIG_LEGACY_PTYS is not set -# CONFIG_DEVKMEM is not set CONFIG_SERIAL_8250=y CONFIG_SERIAL_8250_CONSOLE=y CONFIG_SERIAL_8250_DW=y diff --git a/arch/arc/configs/haps_hs_defconfig b/arch/arc/configs/haps_hs_defconfig index 098b19fbaa51..240dd2cd5148 100644 --- a/arch/arc/configs/haps_hs_defconfig +++ b/arch/arc/configs/haps_hs_defconfig @@ -1,4 +1,3 @@ -CONFIG_DEFAULT_HOSTNAME="ARCLinux" # CONFIG_SWAP is not set CONFIG_SYSVIPC=y CONFIG_POSIX_MQUEUE=y @@ -57,7 +56,6 @@ CONFIG_MOUSE_PS2_TOUCHKIT=y # CONFIG_SERIO_SERPORT is not set CONFIG_SERIO_ARC_PS2=y # CONFIG_LEGACY_PTYS is not set -# CONFIG_DEVKMEM is not set CONFIG_SERIAL_8250=y CONFIG_SERIAL_8250_CONSOLE=y CONFIG_SERIAL_8250_NR_UARTS=1 diff --git a/arch/arc/configs/haps_hs_smp_defconfig b/arch/arc/configs/haps_hs_smp_defconfig index 0104c404d897..14ae7e5acc7c 100644 --- a/arch/arc/configs/haps_hs_smp_defconfig +++ b/arch/arc/configs/haps_hs_smp_defconfig @@ -1,4 +1,3 @@ -CONFIG_DEFAULT_HOSTNAME="ARCLinux" # CONFIG_SWAP is not set CONFIG_SYSVIPC=y CONFIG_POSIX_MQUEUE=y @@ -60,7 +59,6 @@ CONFIG_MOUSE_PS2_TOUCHKIT=y # CONFIG_SERIO_SERPORT is not set CONFIG_SERIO_ARC_PS2=y # CONFIG_LEGACY_PTYS is not set -# CONFIG_DEVKMEM is not set CONFIG_SERIAL_8250=y CONFIG_SERIAL_8250_CONSOLE=y CONFIG_SERIAL_8250_NR_UARTS=1 diff --git a/arch/arc/configs/hsdk_defconfig b/arch/arc/configs/hsdk_defconfig index 6491be0ddbc9..1dec2b4bc5e6 100644 --- a/arch/arc/configs/hsdk_defconfig +++ b/arch/arc/configs/hsdk_defconfig @@ -1,4 +1,3 @@ -CONFIG_DEFAULT_HOSTNAME="ARCLinux" CONFIG_SYSVIPC=y # CONFIG_CROSS_MEMORY_ATTACH is not set CONFIG_NO_HZ_IDLE=y diff --git a/arch/arc/configs/nps_defconfig b/arch/arc/configs/nps_defconfig index 7c9c706ae7f6..31ba224bbfb4 100644 --- a/arch/arc/configs/nps_defconfig +++ b/arch/arc/configs/nps_defconfig @@ -59,7 +59,6 @@ CONFIG_NETCONSOLE=y # CONFIG_INPUT_MOUSE is not set # CONFIG_SERIO is not set # CONFIG_LEGACY_PTYS is not set -# CONFIG_DEVKMEM is not set CONFIG_SERIAL_8250=y CONFIG_SERIAL_8250_CONSOLE=y CONFIG_SERIAL_8250_NR_UARTS=1 diff --git a/arch/arc/configs/nsim_700_defconfig b/arch/arc/configs/nsim_700_defconfig index 99e05cf63fca..8e0b8b134cd9 100644 --- a/arch/arc/configs/nsim_700_defconfig +++ b/arch/arc/configs/nsim_700_defconfig @@ -1,5 +1,4 @@ # CONFIG_LOCALVERSION_AUTO is not set -CONFIG_DEFAULT_HOSTNAME="ARCLinux" # CONFIG_SWAP is not set CONFIG_SYSVIPC=y CONFIG_POSIX_MQUEUE=y @@ -44,7 +43,6 @@ CONFIG_LXT_PHY=y # CONFIG_INPUT_MOUSE is not set # CONFIG_SERIO is not set # CONFIG_LEGACY_PTYS is not set -# CONFIG_DEVKMEM is not set CONFIG_SERIAL_ARC=y CONFIG_SERIAL_ARC_CONSOLE=y # CONFIG_HW_RANDOM is not set diff --git a/arch/arc/configs/nsim_hs_defconfig b/arch/arc/configs/nsim_hs_defconfig index 0dc4f9b737e7..739b90e5e893 100644 --- a/arch/arc/configs/nsim_hs_defconfig +++ b/arch/arc/configs/nsim_hs_defconfig @@ -1,5 +1,4 @@ # CONFIG_LOCALVERSION_AUTO is not set -CONFIG_DEFAULT_HOSTNAME="ARCLinux" # CONFIG_SWAP is not set CONFIG_SYSVIPC=y CONFIG_POSIX_MQUEUE=y @@ -45,7 +44,6 @@ CONFIG_DEVTMPFS=y # CONFIG_INPUT_MOUSE is not set # CONFIG_SERIO is not set # CONFIG_LEGACY_PTYS is not set -# CONFIG_DEVKMEM is not set CONFIG_SERIAL_ARC=y CONFIG_SERIAL_ARC_CONSOLE=y # CONFIG_HW_RANDOM is not set diff --git a/arch/arc/configs/nsim_hs_smp_defconfig b/arch/arc/configs/nsim_hs_smp_defconfig index be3c30a15e54..b5895bdf3a93 100644 --- a/arch/arc/configs/nsim_hs_smp_defconfig +++ b/arch/arc/configs/nsim_hs_smp_defconfig @@ -1,5 +1,4 @@ # CONFIG_LOCALVERSION_AUTO is not set -CONFIG_DEFAULT_HOSTNAME="ARCLinux" # CONFIG_SWAP is not set # CONFIG_CROSS_MEMORY_ATTACH is not set CONFIG_HIGH_RES_TIMERS=y @@ -44,7 +43,6 @@ CONFIG_DEVTMPFS=y # CONFIG_INPUT_MOUSE is not set # CONFIG_SERIO is not set # CONFIG_LEGACY_PTYS is not set -# CONFIG_DEVKMEM is not set CONFIG_SERIAL_ARC=y CONFIG_SERIAL_ARC_CONSOLE=y # CONFIG_HW_RANDOM is not set diff --git a/arch/arc/configs/nsimosci_defconfig b/arch/arc/configs/nsimosci_defconfig index 3a74b9b21772..f14eeff7d308 100644 --- a/arch/arc/configs/nsimosci_defconfig +++ b/arch/arc/configs/nsimosci_defconfig @@ -1,5 +1,4 @@ # CONFIG_LOCALVERSION_AUTO is not set -CONFIG_DEFAULT_HOSTNAME="ARCLinux" # CONFIG_SWAP is not set CONFIG_SYSVIPC=y # CONFIG_CROSS_MEMORY_ATTACH is not set @@ -48,7 +47,6 @@ CONFIG_MOUSE_PS2_TOUCHKIT=y # CONFIG_SERIO_SERPORT is not set CONFIG_SERIO_ARC_PS2=y # CONFIG_LEGACY_PTYS is not set -# CONFIG_DEVKMEM is not set CONFIG_SERIAL_8250=y CONFIG_SERIAL_8250_CONSOLE=y CONFIG_SERIAL_8250_NR_UARTS=1 diff --git a/arch/arc/configs/nsimosci_hs_defconfig b/arch/arc/configs/nsimosci_hs_defconfig index ea2834b4dc1d..025298a48305 100644 --- a/arch/arc/configs/nsimosci_hs_defconfig +++ b/arch/arc/configs/nsimosci_hs_defconfig @@ -1,5 +1,4 @@ # CONFIG_LOCALVERSION_AUTO is not set -CONFIG_DEFAULT_HOSTNAME="ARCLinux" # CONFIG_SWAP is not set CONFIG_SYSVIPC=y # CONFIG_CROSS_MEMORY_ATTACH is not set @@ -47,7 +46,6 @@ CONFIG_MOUSE_PS2_TOUCHKIT=y # CONFIG_SERIO_SERPORT is not set CONFIG_SERIO_ARC_PS2=y # CONFIG_LEGACY_PTYS is not set -# CONFIG_DEVKMEM is not set CONFIG_SERIAL_8250=y CONFIG_SERIAL_8250_CONSOLE=y CONFIG_SERIAL_8250_NR_UARTS=1 diff --git a/arch/arc/configs/nsimosci_hs_smp_defconfig b/arch/arc/configs/nsimosci_hs_smp_defconfig index 80a5a1b4924b..df7b77b13b82 100644 --- a/arch/arc/configs/nsimosci_hs_smp_defconfig +++ b/arch/arc/configs/nsimosci_hs_smp_defconfig @@ -1,4 +1,3 @@ -CONFIG_DEFAULT_HOSTNAME="ARCLinux" # CONFIG_SWAP is not set CONFIG_SYSVIPC=y # CONFIG_CROSS_MEMORY_ATTACH is not set @@ -58,7 +57,6 @@ CONFIG_MOUSE_PS2_TOUCHKIT=y # CONFIG_SERIO_SERPORT is not set CONFIG_SERIO_ARC_PS2=y # CONFIG_LEGACY_PTYS is not set -# CONFIG_DEVKMEM is not set CONFIG_SERIAL_8250=y CONFIG_SERIAL_8250_CONSOLE=y CONFIG_SERIAL_8250_NR_UARTS=1 diff --git a/arch/arc/configs/tb10x_defconfig b/arch/arc/configs/tb10x_defconfig index 2cc87f909747..a7f65313f84a 100644 --- a/arch/arc/configs/tb10x_defconfig +++ b/arch/arc/configs/tb10x_defconfig @@ -57,7 +57,6 @@ CONFIG_STMMAC_ETH=y # CONFIG_SERIO is not set # CONFIG_VT is not set # CONFIG_LEGACY_PTYS is not set -# CONFIG_DEVKMEM is not set CONFIG_SERIAL_8250=y CONFIG_SERIAL_8250_CONSOLE=y CONFIG_SERIAL_8250_NR_UARTS=1 diff --git a/arch/arc/configs/vdk_hs38_defconfig b/arch/arc/configs/vdk_hs38_defconfig index f629493929ea..db47c3541f15 100644 --- a/arch/arc/configs/vdk_hs38_defconfig +++ b/arch/arc/configs/vdk_hs38_defconfig @@ -1,5 +1,4 @@ # CONFIG_LOCALVERSION_AUTO is not set -CONFIG_DEFAULT_HOSTNAME="ARCLinux" # CONFIG_CROSS_MEMORY_ATTACH is not set CONFIG_HIGH_RES_TIMERS=y CONFIG_IKCONFIG=y @@ -53,7 +52,6 @@ CONFIG_NATIONAL_PHY=y CONFIG_MOUSE_PS2_TOUCHKIT=y CONFIG_SERIO_ARC_PS2=y # CONFIG_LEGACY_PTYS is not set -# CONFIG_DEVKMEM is not set CONFIG_SERIAL_8250=y CONFIG_SERIAL_8250_CONSOLE=y CONFIG_SERIAL_8250_DW=y diff --git a/arch/arc/configs/vdk_hs38_smp_defconfig b/arch/arc/configs/vdk_hs38_smp_defconfig index 21f0ca26a05d..a8ac5e917d9a 100644 --- a/arch/arc/configs/vdk_hs38_smp_defconfig +++ b/arch/arc/configs/vdk_hs38_smp_defconfig @@ -1,5 +1,4 @@ # CONFIG_LOCALVERSION_AUTO is not set -CONFIG_DEFAULT_HOSTNAME="ARCLinux" # CONFIG_CROSS_MEMORY_ATTACH is not set CONFIG_HIGH_RES_TIMERS=y CONFIG_IKCONFIG=y diff --git a/arch/arc/include/asm/atomic.h b/arch/arc/include/asm/atomic.h index 4e0072730241..158af079838d 100644 --- a/arch/arc/include/asm/atomic.h +++ b/arch/arc/include/asm/atomic.h @@ -84,7 +84,7 @@ static inline int atomic_fetch_##op(int i, atomic_t *v) \ "1: llock %[orig], [%[ctr]] \n" \ " " #asm_op " %[val], %[orig], %[i] \n" \ " scond %[val], [%[ctr]] \n" \ - " \n" \ + " bnz 1b \n" \ : [val] "=&r" (val), \ [orig] "=&r" (orig) \ : [ctr] "r" (&v->counter), \ diff --git a/arch/arc/include/asm/dma-mapping.h b/arch/arc/include/asm/dma-mapping.h new file mode 100644 index 000000000000..c946c0a83e76 --- /dev/null +++ b/arch/arc/include/asm/dma-mapping.h @@ -0,0 +1,13 @@ +// SPDX-License-Identifier: GPL-2.0 +// (C) 2018 Synopsys, Inc. (www.synopsys.com) + +#ifndef ASM_ARC_DMA_MAPPING_H +#define ASM_ARC_DMA_MAPPING_H + +#include <asm-generic/dma-mapping.h> + +void arch_setup_dma_ops(struct device *dev, u64 dma_base, u64 size, + const struct iommu_ops *iommu, bool coherent); +#define arch_setup_dma_ops arch_setup_dma_ops + +#endif diff --git a/arch/arc/kernel/troubleshoot.c b/arch/arc/kernel/troubleshoot.c index 783b20354f8b..e8d9fb452346 100644 --- a/arch/arc/kernel/troubleshoot.c +++ b/arch/arc/kernel/troubleshoot.c @@ -83,9 +83,6 @@ done: static void show_faulting_vma(unsigned long address, char *buf) { struct vm_area_struct *vma; - struct inode *inode; - unsigned long ino = 0; - dev_t dev = 0; char *nm = buf; struct mm_struct *active_mm = current->active_mm; @@ -99,12 +96,10 @@ static void show_faulting_vma(unsigned long address, char *buf) * if the container VMA is not found */ if (vma && (vma->vm_start <= address)) { - struct file *file = vma->vm_file; - if (file) { - nm = file_path(file, buf, PAGE_SIZE - 1); - inode = file_inode(vma->vm_file); - dev = inode->i_sb->s_dev; - ino = inode->i_ino; + if (vma->vm_file) { + nm = file_path(vma->vm_file, buf, PAGE_SIZE - 1); + if (IS_ERR(nm)) + nm = "?"; } pr_info(" @off 0x%lx in [%s]\n" " VMA: 0x%08lx to 0x%08lx\n", diff --git a/arch/arc/mm/cache.c b/arch/arc/mm/cache.c index 25c631942500..f2701c13a66b 100644 --- a/arch/arc/mm/cache.c +++ b/arch/arc/mm/cache.c @@ -65,7 +65,7 @@ char *arc_cache_mumbojumbo(int c, char *buf, int len) n += scnprintf(buf + n, len - n, "Peripherals\t: %#lx%s%s\n", perip_base, - IS_AVAIL3(ioc_exists, ioc_enable, ", IO-Coherency ")); + IS_AVAIL3(ioc_exists, ioc_enable, ", IO-Coherency (per-device) ")); return buf; } @@ -897,15 +897,6 @@ static void __dma_cache_wback_slc(phys_addr_t start, unsigned long sz) } /* - * DMA ops for systems with IOC - * IOC hardware snoops all DMA traffic keeping the caches consistent with - * memory - eliding need for any explicit cache maintenance of DMA buffers - */ -static void __dma_cache_wback_inv_ioc(phys_addr_t start, unsigned long sz) {} -static void __dma_cache_inv_ioc(phys_addr_t start, unsigned long sz) {} -static void __dma_cache_wback_ioc(phys_addr_t start, unsigned long sz) {} - -/* * Exported DMA API */ void dma_cache_wback_inv(phys_addr_t start, unsigned long sz) @@ -1153,6 +1144,19 @@ noinline void __init arc_ioc_setup(void) { unsigned int ioc_base, mem_sz; + /* + * As for today we don't support both IOC and ZONE_HIGHMEM enabled + * simultaneously. This happens because as of today IOC aperture covers + * only ZONE_NORMAL (low mem) and any dma transactions outside this + * region won't be HW coherent. + * If we want to use both IOC and ZONE_HIGHMEM we can use + * bounce_buffer to handle dma transactions to HIGHMEM. + * Also it is possible to modify dma_direct cache ops or increase IOC + * aperture size if we are planning to use HIGHMEM without PAE. + */ + if (IS_ENABLED(CONFIG_HIGHMEM)) + panic("IOC and HIGHMEM can't be used simultaneously"); + /* Flush + invalidate + disable L1 dcache */ __dc_disable(); @@ -1264,11 +1268,7 @@ void __init arc_cache_init_master(void) if (is_isa_arcv2() && ioc_enable) arc_ioc_setup(); - if (is_isa_arcv2() && ioc_enable) { - __dma_cache_wback_inv = __dma_cache_wback_inv_ioc; - __dma_cache_inv = __dma_cache_inv_ioc; - __dma_cache_wback = __dma_cache_wback_ioc; - } else if (is_isa_arcv2() && l2_line_sz && slc_enable) { + if (is_isa_arcv2() && l2_line_sz && slc_enable) { __dma_cache_wback_inv = __dma_cache_wback_inv_slc; __dma_cache_inv = __dma_cache_inv_slc; __dma_cache_wback = __dma_cache_wback_slc; @@ -1277,6 +1277,12 @@ void __init arc_cache_init_master(void) __dma_cache_inv = __dma_cache_inv_l1; __dma_cache_wback = __dma_cache_wback_l1; } + /* + * In case of IOC (say IOC+SLC case), pointers above could still be set + * but end up not being relevant as the first function in chain is not + * called at all for @dma_direct_ops + * arch_sync_dma_for_cpu() -> dma_cache_*() -> __dma_cache_*() + */ } void __ref arc_cache_init(void) diff --git a/arch/arc/mm/dma.c b/arch/arc/mm/dma.c index ec47e6079f5d..c75d5c3470e3 100644 --- a/arch/arc/mm/dma.c +++ b/arch/arc/mm/dma.c @@ -6,20 +6,17 @@ * published by the Free Software Foundation. */ -/* - * DMA Coherent API Notes - * - * I/O is inherently non-coherent on ARC. So a coherent DMA buffer is - * implemented by accessing it using a kernel virtual address, with - * Cache bit off in the TLB entry. - * - * The default DMA address == Phy address which is 0x8000_0000 based. - */ - #include <linux/dma-noncoherent.h> #include <asm/cache.h> #include <asm/cacheflush.h> +/* + * ARCH specific callbacks for generic noncoherent DMA ops (dma/noncoherent.c) + * - hardware IOC not available (or "dma-coherent" not set for device in DT) + * - But still handle both coherent and non-coherent requests from caller + * + * For DMA coherent hardware (IOC) generic code suffices + */ void *arch_dma_alloc(struct device *dev, size_t size, dma_addr_t *dma_handle, gfp_t gfp, unsigned long attrs) { @@ -27,42 +24,29 @@ void *arch_dma_alloc(struct device *dev, size_t size, dma_addr_t *dma_handle, struct page *page; phys_addr_t paddr; void *kvaddr; - int need_coh = 1, need_kvaddr = 0; - - page = alloc_pages(gfp, order); - if (!page) - return NULL; + bool need_coh = !(attrs & DMA_ATTR_NON_CONSISTENT); /* - * IOC relies on all data (even coherent DMA data) being in cache - * Thus allocate normal cached memory - * - * The gains with IOC are two pronged: - * -For streaming data, elides need for cache maintenance, saving - * cycles in flush code, and bus bandwidth as all the lines of a - * buffer need to be flushed out to memory - * -For coherent data, Read/Write to buffers terminate early in cache - * (vs. always going to memory - thus are faster) + * __GFP_HIGHMEM flag is cleared by upper layer functions + * (in include/linux/dma-mapping.h) so we should never get a + * __GFP_HIGHMEM here. */ - if ((is_isa_arcv2() && ioc_enable) || - (attrs & DMA_ATTR_NON_CONSISTENT)) - need_coh = 0; + BUG_ON(gfp & __GFP_HIGHMEM); - /* - * - A coherent buffer needs MMU mapping to enforce non-cachability - * - A highmem page needs a virtual handle (hence MMU mapping) - * independent of cachability - */ - if (PageHighMem(page) || need_coh) - need_kvaddr = 1; + page = alloc_pages(gfp, order); + if (!page) + return NULL; /* This is linear addr (0x8000_0000 based) */ paddr = page_to_phys(page); *dma_handle = paddr; - /* This is kernel Virtual address (0x7000_0000 based) */ - if (need_kvaddr) { + /* + * A coherent buffer needs MMU mapping to enforce non-cachability. + * kvaddr is kernel Virtual address (0x7000_0000 based). + */ + if (need_coh) { kvaddr = ioremap_nocache(paddr, size); if (kvaddr == NULL) { __free_pages(page, order); @@ -93,12 +77,8 @@ void arch_dma_free(struct device *dev, size_t size, void *vaddr, { phys_addr_t paddr = dma_handle; struct page *page = virt_to_page(paddr); - int is_non_coh = 1; - - is_non_coh = (attrs & DMA_ATTR_NON_CONSISTENT) || - (is_isa_arcv2() && ioc_enable); - if (PageHighMem(page) || !is_non_coh) + if (!(attrs & DMA_ATTR_NON_CONSISTENT)) iounmap((void __force __iomem *)vaddr); __free_pages(page, get_order(size)); @@ -185,3 +165,23 @@ void arch_sync_dma_for_cpu(struct device *dev, phys_addr_t paddr, break; } } + +/* + * Plug in coherent or noncoherent dma ops + */ +void arch_setup_dma_ops(struct device *dev, u64 dma_base, u64 size, + const struct iommu_ops *iommu, bool coherent) +{ + /* + * IOC hardware snoops all DMA traffic keeping the caches consistent + * with memory - eliding need for any explicit cache maintenance of + * DMA buffers - so we can use dma_direct cache ops. + */ + if (is_isa_arcv2() && ioc_enable && coherent) { + set_dma_ops(dev, &dma_direct_ops); + dev_info(dev, "use dma_direct_ops cache ops\n"); + } else { + set_dma_ops(dev, &dma_noncoherent_ops); + dev_info(dev, "use dma_noncoherent_ops cache ops\n"); + } +} diff --git a/arch/arm/boot/dts/sama5d3_emac.dtsi b/arch/arm/boot/dts/sama5d3_emac.dtsi index 7cb235ef0fb6..6e9e1c2f9def 100644 --- a/arch/arm/boot/dts/sama5d3_emac.dtsi +++ b/arch/arm/boot/dts/sama5d3_emac.dtsi @@ -41,7 +41,7 @@ }; macb1: ethernet@f802c000 { - compatible = "cdns,at91sam9260-macb", "cdns,macb"; + compatible = "atmel,sama5d3-macb", "cdns,at91sam9260-macb", "cdns,macb"; reg = <0xf802c000 0x100>; interrupts = <35 IRQ_TYPE_LEVEL_HIGH 3>; pinctrl-names = "default"; diff --git a/arch/arm/include/asm/kvm_host.h b/arch/arm/include/asm/kvm_host.h index 79906cecb091..3ad482d2f1eb 100644 --- a/arch/arm/include/asm/kvm_host.h +++ b/arch/arm/include/asm/kvm_host.h @@ -223,7 +223,6 @@ int __kvm_arm_vcpu_set_events(struct kvm_vcpu *vcpu, struct kvm_vcpu_events *events); #define KVM_ARCH_WANT_MMU_NOTIFIER -int kvm_unmap_hva(struct kvm *kvm, unsigned long hva); int kvm_unmap_hva_range(struct kvm *kvm, unsigned long start, unsigned long end); void kvm_set_spte_hva(struct kvm *kvm, unsigned long hva, pte_t pte); diff --git a/arch/arm64/boot/dts/allwinner/sun50i-h6-pine-h64.dts b/arch/arm64/boot/dts/allwinner/sun50i-h6-pine-h64.dts index ceffc40810ee..48daec7f78ba 100644 --- a/arch/arm64/boot/dts/allwinner/sun50i-h6-pine-h64.dts +++ b/arch/arm64/boot/dts/allwinner/sun50i-h6-pine-h64.dts @@ -46,6 +46,7 @@ pinctrl-0 = <&mmc0_pins>; vmmc-supply = <®_cldo1>; cd-gpios = <&pio 5 6 GPIO_ACTIVE_LOW>; + bus-width = <4>; status = "okay"; }; @@ -56,6 +57,7 @@ vqmmc-supply = <®_bldo2>; non-removable; cap-mmc-hw-reset; + bus-width = <8>; status = "okay"; }; diff --git a/arch/arm64/include/asm/jump_label.h b/arch/arm64/include/asm/jump_label.h index 1b5e0e843c3a..7e2b3e360086 100644 --- a/arch/arm64/include/asm/jump_label.h +++ b/arch/arm64/include/asm/jump_label.h @@ -28,7 +28,7 @@ static __always_inline bool arch_static_branch(struct static_key *key, bool branch) { - asm goto("1: nop\n\t" + asm_volatile_goto("1: nop\n\t" ".pushsection __jump_table, \"aw\"\n\t" ".align 3\n\t" ".quad 1b, %l[l_yes], %c0\n\t" @@ -42,7 +42,7 @@ l_yes: static __always_inline bool arch_static_branch_jump(struct static_key *key, bool branch) { - asm goto("1: b %l[l_yes]\n\t" + asm_volatile_goto("1: b %l[l_yes]\n\t" ".pushsection __jump_table, \"aw\"\n\t" ".align 3\n\t" ".quad 1b, %l[l_yes], %c0\n\t" diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h index f26055f2306e..3d6d7336f871 100644 --- a/arch/arm64/include/asm/kvm_host.h +++ b/arch/arm64/include/asm/kvm_host.h @@ -61,8 +61,7 @@ struct kvm_arch { u64 vmid_gen; u32 vmid; - /* 1-level 2nd stage table and lock */ - spinlock_t pgd_lock; + /* 1-level 2nd stage table, protected by kvm->mmu_lock */ pgd_t *pgd; /* VTTBR value associated with above pgd and vmid */ @@ -357,7 +356,6 @@ int __kvm_arm_vcpu_set_events(struct kvm_vcpu *vcpu, struct kvm_vcpu_events *events); #define KVM_ARCH_WANT_MMU_NOTIFIER -int kvm_unmap_hva(struct kvm *kvm, unsigned long hva); int kvm_unmap_hva_range(struct kvm *kvm, unsigned long start, unsigned long end); void kvm_set_spte_hva(struct kvm *kvm, unsigned long hva, pte_t pte); diff --git a/arch/arm64/kernel/Makefile b/arch/arm64/kernel/Makefile index 95ac7374d723..4c8b13bede80 100644 --- a/arch/arm64/kernel/Makefile +++ b/arch/arm64/kernel/Makefile @@ -54,6 +54,7 @@ arm64-obj-$(CONFIG_KEXEC) += machine_kexec.o relocate_kernel.o \ arm64-obj-$(CONFIG_ARM64_RELOC_TEST) += arm64-reloc-test.o arm64-reloc-test-y := reloc_test_core.o reloc_test_syms.o arm64-obj-$(CONFIG_CRASH_DUMP) += crash_dump.o +arm64-obj-$(CONFIG_CRASH_CORE) += crash_core.o arm64-obj-$(CONFIG_ARM_SDE_INTERFACE) += sdei.o arm64-obj-$(CONFIG_ARM64_SSBD) += ssbd.o diff --git a/arch/arm64/kernel/crash_core.c b/arch/arm64/kernel/crash_core.c new file mode 100644 index 000000000000..ca4c3e12d8c5 --- /dev/null +++ b/arch/arm64/kernel/crash_core.c @@ -0,0 +1,19 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) Linaro. + * Copyright (C) Huawei Futurewei Technologies. + */ + +#include <linux/crash_core.h> +#include <asm/memory.h> + +void arch_crash_save_vmcoreinfo(void) +{ + VMCOREINFO_NUMBER(VA_BITS); + /* Please note VMCOREINFO_NUMBER() uses "%d", not "%x" */ + vmcoreinfo_append_str("NUMBER(kimage_voffset)=0x%llx\n", + kimage_voffset); + vmcoreinfo_append_str("NUMBER(PHYS_OFFSET)=0x%llx\n", + PHYS_OFFSET); + vmcoreinfo_append_str("KERNELOFFSET=%lx\n", kaslr_offset()); +} diff --git a/arch/arm64/kernel/machine_kexec.c b/arch/arm64/kernel/machine_kexec.c index f6a5c6bc1434..922add8adb74 100644 --- a/arch/arm64/kernel/machine_kexec.c +++ b/arch/arm64/kernel/machine_kexec.c @@ -358,14 +358,3 @@ void crash_free_reserved_phys_range(unsigned long begin, unsigned long end) } } #endif /* CONFIG_HIBERNATION */ - -void arch_crash_save_vmcoreinfo(void) -{ - VMCOREINFO_NUMBER(VA_BITS); - /* Please note VMCOREINFO_NUMBER() uses "%d", not "%x" */ - vmcoreinfo_append_str("NUMBER(kimage_voffset)=0x%llx\n", - kimage_voffset); - vmcoreinfo_append_str("NUMBER(PHYS_OFFSET)=0x%llx\n", - PHYS_OFFSET); - vmcoreinfo_append_str("KERNELOFFSET=%lx\n", kaslr_offset()); -} diff --git a/arch/arm64/kvm/hyp/switch.c b/arch/arm64/kvm/hyp/switch.c index d496ef579859..ca46153d7915 100644 --- a/arch/arm64/kvm/hyp/switch.c +++ b/arch/arm64/kvm/hyp/switch.c @@ -98,8 +98,10 @@ static void activate_traps_vhe(struct kvm_vcpu *vcpu) val = read_sysreg(cpacr_el1); val |= CPACR_EL1_TTA; val &= ~CPACR_EL1_ZEN; - if (!update_fp_enabled(vcpu)) + if (!update_fp_enabled(vcpu)) { val &= ~CPACR_EL1_FPEN; + __activate_traps_fpsimd32(vcpu); + } write_sysreg(val, cpacr_el1); @@ -114,8 +116,10 @@ static void __hyp_text __activate_traps_nvhe(struct kvm_vcpu *vcpu) val = CPTR_EL2_DEFAULT; val |= CPTR_EL2_TTA | CPTR_EL2_TZ; - if (!update_fp_enabled(vcpu)) + if (!update_fp_enabled(vcpu)) { val |= CPTR_EL2_TFP; + __activate_traps_fpsimd32(vcpu); + } write_sysreg(val, cptr_el2); } @@ -129,7 +133,6 @@ static void __hyp_text __activate_traps(struct kvm_vcpu *vcpu) if (cpus_have_const_cap(ARM64_HAS_RAS_EXTN) && (hcr & HCR_VSE)) write_sysreg_s(vcpu->arch.vsesr_el2, SYS_VSESR_EL2); - __activate_traps_fpsimd32(vcpu); if (has_vhe()) activate_traps_vhe(vcpu); else diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c index 65f86271f02b..8080c9f489c3 100644 --- a/arch/arm64/mm/mmu.c +++ b/arch/arm64/mm/mmu.c @@ -985,8 +985,9 @@ int pmd_free_pte_page(pmd_t *pmdp, unsigned long addr) pmd = READ_ONCE(*pmdp); - /* No-op for empty entry and WARN_ON for valid entry */ - if (!pmd_present(pmd) || !pmd_table(pmd)) { + if (!pmd_present(pmd)) + return 1; + if (!pmd_table(pmd)) { VM_WARN_ON(!pmd_table(pmd)); return 1; } @@ -1007,8 +1008,9 @@ int pud_free_pmd_page(pud_t *pudp, unsigned long addr) pud = READ_ONCE(*pudp); - /* No-op for empty entry and WARN_ON for valid entry */ - if (!pud_present(pud) || !pud_table(pud)) { + if (!pud_present(pud)) + return 1; + if (!pud_table(pud)) { VM_WARN_ON(!pud_table(pud)); return 1; } diff --git a/arch/hexagon/include/asm/bitops.h b/arch/hexagon/include/asm/bitops.h index 5e4a59b3ec1b..2691a1857d20 100644 --- a/arch/hexagon/include/asm/bitops.h +++ b/arch/hexagon/include/asm/bitops.h @@ -211,7 +211,7 @@ static inline long ffz(int x) * This is defined the same way as ffs. * Note fls(0) = 0, fls(1) = 1, fls(0x80000000) = 32. */ -static inline long fls(int x) +static inline int fls(int x) { int r; @@ -232,7 +232,7 @@ static inline long fls(int x) * the libc and compiler builtin ffs routines, therefore * differs in spirit from the above ffz (man ffs). */ -static inline long ffs(int x) +static inline int ffs(int x) { int r; diff --git a/arch/hexagon/kernel/dma.c b/arch/hexagon/kernel/dma.c index 77459df34e2e..7ebe7ad19d15 100644 --- a/arch/hexagon/kernel/dma.c +++ b/arch/hexagon/kernel/dma.c @@ -60,7 +60,7 @@ static void *hexagon_dma_alloc_coherent(struct device *dev, size_t size, panic("Can't create %s() memory pool!", __func__); else gen_pool_add(coherent_pool, - pfn_to_virt(max_low_pfn), + (unsigned long)pfn_to_virt(max_low_pfn), hexagon_coherent_pool_size, -1); } diff --git a/arch/m68k/mm/mcfmmu.c b/arch/m68k/mm/mcfmmu.c index 70dde040779b..f5453d944ff5 100644 --- a/arch/m68k/mm/mcfmmu.c +++ b/arch/m68k/mm/mcfmmu.c @@ -172,7 +172,7 @@ void __init cf_bootmem_alloc(void) high_memory = (void *)_ramend; /* Reserve kernel text/data/bss */ - memblock_reserve(memstart, memstart - _rambase); + memblock_reserve(_rambase, memstart - _rambase); m68k_virt_to_node_shift = fls(_ramend - 1) - 6; module_fixup(NULL, __start_fixup, __stop_fixup); diff --git a/arch/mips/include/asm/kvm_host.h b/arch/mips/include/asm/kvm_host.h index a9af1d2dcd69..2c1c53d12179 100644 --- a/arch/mips/include/asm/kvm_host.h +++ b/arch/mips/include/asm/kvm_host.h @@ -931,7 +931,6 @@ enum kvm_mips_fault_result kvm_trap_emul_gva_fault(struct kvm_vcpu *vcpu, bool write); #define KVM_ARCH_WANT_MMU_NOTIFIER -int kvm_unmap_hva(struct kvm *kvm, unsigned long hva); int kvm_unmap_hva_range(struct kvm *kvm, unsigned long start, unsigned long end); void kvm_set_spte_hva(struct kvm *kvm, unsigned long hva, pte_t pte); diff --git a/arch/mips/include/asm/mach-lantiq/xway/xway_dma.h b/arch/mips/include/asm/mach-lantiq/xway/xway_dma.h index 4901833498f7..8441b2698e64 100644 --- a/arch/mips/include/asm/mach-lantiq/xway/xway_dma.h +++ b/arch/mips/include/asm/mach-lantiq/xway/xway_dma.h @@ -40,6 +40,7 @@ struct ltq_dma_channel { int desc; /* the current descriptor */ struct ltq_dma_desc *desc_base; /* the descriptor base */ int phys; /* physical addr */ + struct device *dev; }; enum { diff --git a/arch/mips/kernel/vdso.c b/arch/mips/kernel/vdso.c index 019035d7225c..8f845f6e5f42 100644 --- a/arch/mips/kernel/vdso.c +++ b/arch/mips/kernel/vdso.c @@ -13,6 +13,7 @@ #include <linux/err.h> #include <linux/init.h> #include <linux/ioport.h> +#include <linux/kernel.h> #include <linux/mm.h> #include <linux/sched.h> #include <linux/slab.h> @@ -20,6 +21,7 @@ #include <asm/abi.h> #include <asm/mips-cps.h> +#include <asm/page.h> #include <asm/vdso.h> /* Kernel-provided data used by the VDSO. */ @@ -128,12 +130,30 @@ int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp) vvar_size = gic_size + PAGE_SIZE; size = vvar_size + image->size; + /* + * Find a region that's large enough for us to perform the + * colour-matching alignment below. + */ + if (cpu_has_dc_aliases) + size += shm_align_mask + 1; + base = get_unmapped_area(NULL, 0, size, 0, 0); if (IS_ERR_VALUE(base)) { ret = base; goto out; } + /* + * If we suffer from dcache aliasing, ensure that the VDSO data page + * mapping is coloured the same as the kernel's mapping of that memory. + * This ensures that when the kernel updates the VDSO data userland + * will observe it without requiring cache invalidations. + */ + if (cpu_has_dc_aliases) { + base = __ALIGN_MASK(base, shm_align_mask); + base += ((unsigned long)&vdso_data - gic_size) & shm_align_mask; + } + data_addr = base + gic_size; vdso_addr = data_addr + PAGE_SIZE; diff --git a/arch/mips/kvm/mmu.c b/arch/mips/kvm/mmu.c index ee64db032793..d8dcdb350405 100644 --- a/arch/mips/kvm/mmu.c +++ b/arch/mips/kvm/mmu.c @@ -512,16 +512,6 @@ static int kvm_unmap_hva_handler(struct kvm *kvm, gfn_t gfn, gfn_t gfn_end, return 1; } -int kvm_unmap_hva(struct kvm *kvm, unsigned long hva) -{ - unsigned long end = hva + PAGE_SIZE; - - handle_hva_to_gpa(kvm, hva, end, &kvm_unmap_hva_handler, NULL); - - kvm_mips_callbacks->flush_shadow_all(kvm); - return 0; -} - int kvm_unmap_hva_range(struct kvm *kvm, unsigned long start, unsigned long end) { handle_hva_to_gpa(kvm, start, end, &kvm_unmap_hva_handler, NULL); diff --git a/arch/mips/lantiq/xway/dma.c b/arch/mips/lantiq/xway/dma.c index 4b9fbb6744ad..982859f2b2a3 100644 --- a/arch/mips/lantiq/xway/dma.c +++ b/arch/mips/lantiq/xway/dma.c @@ -106,7 +106,6 @@ ltq_dma_open(struct ltq_dma_channel *ch) spin_lock_irqsave(<q_dma_lock, flag); ltq_dma_w32(ch->nr, LTQ_DMA_CS); ltq_dma_w32_mask(0, DMA_CHAN_ON, LTQ_DMA_CCTRL); - ltq_dma_w32_mask(0, 1 << ch->nr, LTQ_DMA_IRNEN); spin_unlock_irqrestore(<q_dma_lock, flag); } EXPORT_SYMBOL_GPL(ltq_dma_open); @@ -130,7 +129,7 @@ ltq_dma_alloc(struct ltq_dma_channel *ch) unsigned long flags; ch->desc = 0; - ch->desc_base = dma_zalloc_coherent(NULL, + ch->desc_base = dma_zalloc_coherent(ch->dev, LTQ_DESC_NUM * LTQ_DESC_SIZE, &ch->phys, GFP_ATOMIC); @@ -182,7 +181,7 @@ ltq_dma_free(struct ltq_dma_channel *ch) if (!ch->desc_base) return; ltq_dma_close(ch); - dma_free_coherent(NULL, LTQ_DESC_NUM * LTQ_DESC_SIZE, + dma_free_coherent(ch->dev, LTQ_DESC_NUM * LTQ_DESC_SIZE, ch->desc_base, ch->phys); } EXPORT_SYMBOL_GPL(ltq_dma_free); diff --git a/arch/mips/lantiq/xway/sysctrl.c b/arch/mips/lantiq/xway/sysctrl.c index e0af39b33e28..fe25c99089b7 100644 --- a/arch/mips/lantiq/xway/sysctrl.c +++ b/arch/mips/lantiq/xway/sysctrl.c @@ -505,7 +505,7 @@ void __init ltq_soc_init(void) clkdev_add_pmu("1a800000.pcie", "msi", 1, 1, PMU1_PCIE2_MSI); clkdev_add_pmu("1a800000.pcie", "pdi", 1, 1, PMU1_PCIE2_PDI); clkdev_add_pmu("1a800000.pcie", "ctl", 1, 1, PMU1_PCIE2_CTL); - clkdev_add_pmu("1e108000.eth", NULL, 0, 0, PMU_SWITCH | PMU_PPE_DP); + clkdev_add_pmu("1e10b308.eth", NULL, 0, 0, PMU_SWITCH | PMU_PPE_DP); clkdev_add_pmu("1da00000.usif", "NULL", 1, 0, PMU_USIF); clkdev_add_pmu("1e103100.deu", NULL, 1, 0, PMU_DEU); } else if (of_machine_is_compatible("lantiq,ar10")) { @@ -513,11 +513,11 @@ void __init ltq_soc_init(void) ltq_ar10_fpi_hz(), ltq_ar10_pp32_hz()); clkdev_add_pmu("1e101000.usb", "otg", 1, 0, PMU_USB0); clkdev_add_pmu("1e106000.usb", "otg", 1, 0, PMU_USB1); - clkdev_add_pmu("1e108000.eth", NULL, 0, 0, PMU_SWITCH | + clkdev_add_pmu("1e10b308.eth", NULL, 0, 0, PMU_SWITCH | PMU_PPE_DP | PMU_PPE_TC); clkdev_add_pmu("1da00000.usif", "NULL", 1, 0, PMU_USIF); - clkdev_add_pmu("1f203020.gphy", NULL, 1, 0, PMU_GPHY); - clkdev_add_pmu("1f203068.gphy", NULL, 1, 0, PMU_GPHY); + clkdev_add_pmu("1e108000.gswip", "gphy0", 0, 0, PMU_GPHY); + clkdev_add_pmu("1e108000.gswip", "gphy1", 0, 0, PMU_GPHY); clkdev_add_pmu("1e103100.deu", NULL, 1, 0, PMU_DEU); clkdev_add_pmu("1e116000.mei", "afe", 1, 2, PMU_ANALOG_DSL_AFE); clkdev_add_pmu("1e116000.mei", "dfe", 1, 0, PMU_DFE); @@ -536,12 +536,12 @@ void __init ltq_soc_init(void) clkdev_add_pmu(NULL, "ahb", 1, 0, PMU_AHBM | PMU_AHBS); clkdev_add_pmu("1da00000.usif", "NULL", 1, 0, PMU_USIF); - clkdev_add_pmu("1e108000.eth", NULL, 0, 0, + clkdev_add_pmu("1e10b308.eth", NULL, 0, 0, PMU_SWITCH | PMU_PPE_DPLUS | PMU_PPE_DPLUM | PMU_PPE_EMA | PMU_PPE_TC | PMU_PPE_SLL01 | PMU_PPE_QSB | PMU_PPE_TOP); - clkdev_add_pmu("1f203020.gphy", NULL, 0, 0, PMU_GPHY); - clkdev_add_pmu("1f203068.gphy", NULL, 0, 0, PMU_GPHY); + clkdev_add_pmu("1e108000.gswip", "gphy0", 0, 0, PMU_GPHY); + clkdev_add_pmu("1e108000.gswip", "gphy1", 0, 0, PMU_GPHY); clkdev_add_pmu("1e103000.sdio", NULL, 1, 0, PMU_SDIO); clkdev_add_pmu("1e103100.deu", NULL, 1, 0, PMU_DEU); clkdev_add_pmu("1e116000.mei", "dfe", 1, 0, PMU_DFE); diff --git a/arch/nds32/Kconfig b/arch/nds32/Kconfig index 1d4248fa55e9..7068f341133d 100644 --- a/arch/nds32/Kconfig +++ b/arch/nds32/Kconfig @@ -40,6 +40,10 @@ config NDS32 select NO_IOPORT_MAP select RTC_LIB select THREAD_INFO_IN_TASK + select HAVE_FUNCTION_TRACER + select HAVE_FUNCTION_GRAPH_TRACER + select HAVE_FTRACE_MCOUNT_RECORD + select HAVE_DYNAMIC_FTRACE help Andes(nds32) Linux support. diff --git a/arch/nds32/Makefile b/arch/nds32/Makefile index 63f4f173e5f4..3509fac10491 100644 --- a/arch/nds32/Makefile +++ b/arch/nds32/Makefile @@ -5,6 +5,10 @@ KBUILD_DEFCONFIG := defconfig comma = , +ifdef CONFIG_FUNCTION_TRACER +arch-y += -malways-save-lp -mno-relax +endif + KBUILD_CFLAGS += $(call cc-option, -mno-sched-prolog-epilog) KBUILD_CFLAGS += -mcmodel=large diff --git a/arch/nds32/include/asm/elf.h b/arch/nds32/include/asm/elf.h index 56c479058802..f5f9cf7e0544 100644 --- a/arch/nds32/include/asm/elf.h +++ b/arch/nds32/include/asm/elf.h @@ -121,9 +121,9 @@ struct elf32_hdr; */ #define ELF_CLASS ELFCLASS32 #ifdef __NDS32_EB__ -#define ELF_DATA ELFDATA2MSB; +#define ELF_DATA ELFDATA2MSB #else -#define ELF_DATA ELFDATA2LSB; +#define ELF_DATA ELFDATA2LSB #endif #define ELF_ARCH EM_NDS32 #define USE_ELF_CORE_DUMP diff --git a/arch/nds32/include/asm/ftrace.h b/arch/nds32/include/asm/ftrace.h new file mode 100644 index 000000000000..2f96cc96aa35 --- /dev/null +++ b/arch/nds32/include/asm/ftrace.h @@ -0,0 +1,46 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +#ifndef __ASM_NDS32_FTRACE_H +#define __ASM_NDS32_FTRACE_H + +#ifdef CONFIG_FUNCTION_TRACER + +#define HAVE_FUNCTION_GRAPH_FP_TEST + +#define MCOUNT_ADDR ((unsigned long)(_mcount)) +/* mcount call is composed of three instructions: + * sethi + ori + jral + */ +#define MCOUNT_INSN_SIZE 12 + +extern void _mcount(unsigned long parent_ip); + +#ifdef CONFIG_DYNAMIC_FTRACE + +#define FTRACE_ADDR ((unsigned long)_ftrace_caller) + +#ifdef __NDS32_EL__ +#define INSN_NOP 0x09000040 +#define INSN_SIZE(insn) (((insn & 0x00000080) == 0) ? 4 : 2) +#define IS_SETHI(insn) ((insn & 0x000000fe) == 0x00000046) +#define ENDIAN_CONVERT(insn) be32_to_cpu(insn) +#else /* __NDS32_EB__ */ +#define INSN_NOP 0x40000009 +#define INSN_SIZE(insn) (((insn & 0x80000000) == 0) ? 4 : 2) +#define IS_SETHI(insn) ((insn & 0xfe000000) == 0x46000000) +#define ENDIAN_CONVERT(insn) (insn) +#endif + +extern void _ftrace_caller(unsigned long parent_ip); +static inline unsigned long ftrace_call_adjust(unsigned long addr) +{ + return addr; +} +struct dyn_arch_ftrace { +}; + +#endif /* CONFIG_DYNAMIC_FTRACE */ + +#endif /* CONFIG_FUNCTION_TRACER */ + +#endif /* __ASM_NDS32_FTRACE_H */ diff --git a/arch/nds32/include/asm/nds32.h b/arch/nds32/include/asm/nds32.h index 19b19394a936..68c38151c3e4 100644 --- a/arch/nds32/include/asm/nds32.h +++ b/arch/nds32/include/asm/nds32.h @@ -17,6 +17,7 @@ #else #define FP_OFFSET (-2) #endif +#define LP_OFFSET (-1) extern void __init early_trap_init(void); static inline void GIE_ENABLE(void) diff --git a/arch/nds32/include/asm/uaccess.h b/arch/nds32/include/asm/uaccess.h index 18a009f3804d..362a32d9bd16 100644 --- a/arch/nds32/include/asm/uaccess.h +++ b/arch/nds32/include/asm/uaccess.h @@ -38,7 +38,7 @@ struct exception_table_entry { extern int fixup_exception(struct pt_regs *regs); #define KERNEL_DS ((mm_segment_t) { ~0UL }) -#define USER_DS ((mm_segment_t) {TASK_SIZE - 1}) +#define USER_DS ((mm_segment_t) {TASK_SIZE - 1}) #define get_ds() (KERNEL_DS) #define get_fs() (current_thread_info()->addr_limit) @@ -49,11 +49,11 @@ static inline void set_fs(mm_segment_t fs) current_thread_info()->addr_limit = fs; } -#define segment_eq(a, b) ((a) == (b)) +#define segment_eq(a, b) ((a) == (b)) #define __range_ok(addr, size) (size <= get_fs() && addr <= (get_fs() -size)) -#define access_ok(type, addr, size) \ +#define access_ok(type, addr, size) \ __range_ok((unsigned long)addr, (unsigned long)size) /* * Single-value transfer routines. They automatically use the right @@ -75,70 +75,73 @@ static inline void set_fs(mm_segment_t fs) * versions are void (ie, don't return a value as such). */ -#define get_user(x,p) \ -({ \ - long __e = -EFAULT; \ - if(likely(access_ok(VERIFY_READ, p, sizeof(*p)))) { \ - __e = __get_user(x,p); \ - } else \ - x = 0; \ - __e; \ -}) -#define __get_user(x,ptr) \ +#define get_user __get_user \ + +#define __get_user(x, ptr) \ ({ \ long __gu_err = 0; \ - __get_user_err((x),(ptr),__gu_err); \ + __get_user_check((x), (ptr), __gu_err); \ __gu_err; \ }) -#define __get_user_error(x,ptr,err) \ +#define __get_user_error(x, ptr, err) \ ({ \ - __get_user_err((x),(ptr),err); \ - (void) 0; \ + __get_user_check((x), (ptr), (err)); \ + (void)0; \ }) -#define __get_user_err(x,ptr,err) \ +#define __get_user_check(x, ptr, err) \ +({ \ + const __typeof__(*(ptr)) __user *__p = (ptr); \ + might_fault(); \ + if (access_ok(VERIFY_READ, __p, sizeof(*__p))) { \ + __get_user_err((x), __p, (err)); \ + } else { \ + (x) = 0; (err) = -EFAULT; \ + } \ +}) + +#define __get_user_err(x, ptr, err) \ do { \ - unsigned long __gu_addr = (unsigned long)(ptr); \ unsigned long __gu_val; \ __chk_user_ptr(ptr); \ switch (sizeof(*(ptr))) { \ case 1: \ - __get_user_asm("lbi",__gu_val,__gu_addr,err); \ + __get_user_asm("lbi", __gu_val, (ptr), (err)); \ break; \ case 2: \ - __get_user_asm("lhi",__gu_val,__gu_addr,err); \ + __get_user_asm("lhi", __gu_val, (ptr), (err)); \ break; \ case 4: \ - __get_user_asm("lwi",__gu_val,__gu_addr,err); \ + __get_user_asm("lwi", __gu_val, (ptr), (err)); \ break; \ case 8: \ - __get_user_asm_dword(__gu_val,__gu_addr,err); \ + __get_user_asm_dword(__gu_val, (ptr), (err)); \ break; \ default: \ BUILD_BUG(); \ break; \ } \ - (x) = (__typeof__(*(ptr)))__gu_val; \ + (x) = (__force __typeof__(*(ptr)))__gu_val; \ } while (0) -#define __get_user_asm(inst,x,addr,err) \ - asm volatile( \ - "1: "inst" %1,[%2]\n" \ - "2:\n" \ - " .section .fixup,\"ax\"\n" \ - " .align 2\n" \ - "3: move %0, %3\n" \ - " move %1, #0\n" \ - " b 2b\n" \ - " .previous\n" \ - " .section __ex_table,\"a\"\n" \ - " .align 3\n" \ - " .long 1b, 3b\n" \ - " .previous" \ - : "+r" (err), "=&r" (x) \ - : "r" (addr), "i" (-EFAULT) \ - : "cc") +#define __get_user_asm(inst, x, addr, err) \ + __asm__ __volatile__ ( \ + "1: "inst" %1,[%2]\n" \ + "2:\n" \ + " .section .fixup,\"ax\"\n" \ + " .align 2\n" \ + "3: move %0, %3\n" \ + " move %1, #0\n" \ + " b 2b\n" \ + " .previous\n" \ + " .section __ex_table,\"a\"\n" \ + " .align 3\n" \ + " .long 1b, 3b\n" \ + " .previous" \ + : "+r" (err), "=&r" (x) \ + : "r" (addr), "i" (-EFAULT) \ + : "cc") #ifdef __NDS32_EB__ #define __gu_reg_oper0 "%H1" @@ -149,61 +152,66 @@ do { \ #endif #define __get_user_asm_dword(x, addr, err) \ - asm volatile( \ - "\n1:\tlwi " __gu_reg_oper0 ",[%2]\n" \ - "\n2:\tlwi " __gu_reg_oper1 ",[%2+4]\n" \ - "3:\n" \ - " .section .fixup,\"ax\"\n" \ - " .align 2\n" \ - "4: move %0, %3\n" \ - " b 3b\n" \ - " .previous\n" \ - " .section __ex_table,\"a\"\n" \ - " .align 3\n" \ - " .long 1b, 4b\n" \ - " .long 2b, 4b\n" \ - " .previous" \ - : "+r"(err), "=&r"(x) \ - : "r"(addr), "i"(-EFAULT) \ - : "cc") -#define put_user(x,p) \ -({ \ - long __e = -EFAULT; \ - if(likely(access_ok(VERIFY_WRITE, p, sizeof(*p)))) { \ - __e = __put_user(x,p); \ - } \ - __e; \ -}) -#define __put_user(x,ptr) \ + __asm__ __volatile__ ( \ + "\n1:\tlwi " __gu_reg_oper0 ",[%2]\n" \ + "\n2:\tlwi " __gu_reg_oper1 ",[%2+4]\n" \ + "3:\n" \ + " .section .fixup,\"ax\"\n" \ + " .align 2\n" \ + "4: move %0, %3\n" \ + " b 3b\n" \ + " .previous\n" \ + " .section __ex_table,\"a\"\n" \ + " .align 3\n" \ + " .long 1b, 4b\n" \ + " .long 2b, 4b\n" \ + " .previous" \ + : "+r"(err), "=&r"(x) \ + : "r"(addr), "i"(-EFAULT) \ + : "cc") + +#define put_user __put_user \ + +#define __put_user(x, ptr) \ ({ \ long __pu_err = 0; \ - __put_user_err((x),(ptr),__pu_err); \ + __put_user_err((x), (ptr), __pu_err); \ __pu_err; \ }) -#define __put_user_error(x,ptr,err) \ +#define __put_user_error(x, ptr, err) \ +({ \ + __put_user_err((x), (ptr), (err)); \ + (void)0; \ +}) + +#define __put_user_check(x, ptr, err) \ ({ \ - __put_user_err((x),(ptr),err); \ - (void) 0; \ + __typeof__(*(ptr)) __user *__p = (ptr); \ + might_fault(); \ + if (access_ok(VERIFY_WRITE, __p, sizeof(*__p))) { \ + __put_user_err((x), __p, (err)); \ + } else { \ + (err) = -EFAULT; \ + } \ }) -#define __put_user_err(x,ptr,err) \ +#define __put_user_err(x, ptr, err) \ do { \ - unsigned long __pu_addr = (unsigned long)(ptr); \ __typeof__(*(ptr)) __pu_val = (x); \ __chk_user_ptr(ptr); \ switch (sizeof(*(ptr))) { \ case 1: \ - __put_user_asm("sbi",__pu_val,__pu_addr,err); \ + __put_user_asm("sbi", __pu_val, (ptr), (err)); \ break; \ case 2: \ - __put_user_asm("shi",__pu_val,__pu_addr,err); \ + __put_user_asm("shi", __pu_val, (ptr), (err)); \ break; \ case 4: \ - __put_user_asm("swi",__pu_val,__pu_addr,err); \ + __put_user_asm("swi", __pu_val, (ptr), (err)); \ break; \ case 8: \ - __put_user_asm_dword(__pu_val,__pu_addr,err); \ + __put_user_asm_dword(__pu_val, (ptr), (err)); \ break; \ default: \ BUILD_BUG(); \ @@ -211,22 +219,22 @@ do { \ } \ } while (0) -#define __put_user_asm(inst,x,addr,err) \ - asm volatile( \ - "1: "inst" %1,[%2]\n" \ - "2:\n" \ - " .section .fixup,\"ax\"\n" \ - " .align 2\n" \ - "3: move %0, %3\n" \ - " b 2b\n" \ - " .previous\n" \ - " .section __ex_table,\"a\"\n" \ - " .align 3\n" \ - " .long 1b, 3b\n" \ - " .previous" \ - : "+r" (err) \ - : "r" (x), "r" (addr), "i" (-EFAULT) \ - : "cc") +#define __put_user_asm(inst, x, addr, err) \ + __asm__ __volatile__ ( \ + "1: "inst" %1,[%2]\n" \ + "2:\n" \ + " .section .fixup,\"ax\"\n" \ + " .align 2\n" \ + "3: move %0, %3\n" \ + " b 2b\n" \ + " .previous\n" \ + " .section __ex_table,\"a\"\n" \ + " .align 3\n" \ + " .long 1b, 3b\n" \ + " .previous" \ + : "+r" (err) \ + : "r" (x), "r" (addr), "i" (-EFAULT) \ + : "cc") #ifdef __NDS32_EB__ #define __pu_reg_oper0 "%H2" @@ -237,23 +245,24 @@ do { \ #endif #define __put_user_asm_dword(x, addr, err) \ - asm volatile( \ - "\n1:\tswi " __pu_reg_oper0 ",[%1]\n" \ - "\n2:\tswi " __pu_reg_oper1 ",[%1+4]\n" \ - "3:\n" \ - " .section .fixup,\"ax\"\n" \ - " .align 2\n" \ - "4: move %0, %3\n" \ - " b 3b\n" \ - " .previous\n" \ - " .section __ex_table,\"a\"\n" \ - " .align 3\n" \ - " .long 1b, 4b\n" \ - " .long 2b, 4b\n" \ - " .previous" \ - : "+r"(err) \ - : "r"(addr), "r"(x), "i"(-EFAULT) \ - : "cc") + __asm__ __volatile__ ( \ + "\n1:\tswi " __pu_reg_oper0 ",[%1]\n" \ + "\n2:\tswi " __pu_reg_oper1 ",[%1+4]\n" \ + "3:\n" \ + " .section .fixup,\"ax\"\n" \ + " .align 2\n" \ + "4: move %0, %3\n" \ + " b 3b\n" \ + " .previous\n" \ + " .section __ex_table,\"a\"\n" \ + " .align 3\n" \ + " .long 1b, 4b\n" \ + " .long 2b, 4b\n" \ + " .previous" \ + : "+r"(err) \ + : "r"(addr), "r"(x), "i"(-EFAULT) \ + : "cc") + extern unsigned long __arch_clear_user(void __user * addr, unsigned long n); extern long strncpy_from_user(char *dest, const char __user * src, long count); extern __must_check long strlen_user(const char __user * str); diff --git a/arch/nds32/kernel/Makefile b/arch/nds32/kernel/Makefile index 42792743e8b9..27cded39fa66 100644 --- a/arch/nds32/kernel/Makefile +++ b/arch/nds32/kernel/Makefile @@ -21,3 +21,9 @@ extra-y := head.o vmlinux.lds obj-y += vdso/ + +obj-$(CONFIG_FUNCTION_TRACER) += ftrace.o + +ifdef CONFIG_FUNCTION_TRACER +CFLAGS_REMOVE_ftrace.o = $(CC_FLAGS_FTRACE) +endif diff --git a/arch/nds32/kernel/atl2c.c b/arch/nds32/kernel/atl2c.c index 0c6d031a1c4a..0c5386e72098 100644 --- a/arch/nds32/kernel/atl2c.c +++ b/arch/nds32/kernel/atl2c.c @@ -9,7 +9,8 @@ void __iomem *atl2c_base; static const struct of_device_id atl2c_ids[] __initconst = { - {.compatible = "andestech,atl2c",} + {.compatible = "andestech,atl2c",}, + {} }; static int __init atl2c_of_init(void) diff --git a/arch/nds32/kernel/ex-entry.S b/arch/nds32/kernel/ex-entry.S index b8ae4e9a6b93..21a144071566 100644 --- a/arch/nds32/kernel/ex-entry.S +++ b/arch/nds32/kernel/ex-entry.S @@ -118,7 +118,7 @@ common_exception_handler: /* interrupt */ 2: #ifdef CONFIG_TRACE_IRQFLAGS - jal trace_hardirqs_off + jal __trace_hardirqs_off #endif move $r0, $sp sethi $lp, hi20(ret_from_intr) diff --git a/arch/nds32/kernel/ex-exit.S b/arch/nds32/kernel/ex-exit.S index 03e4f7788a18..f00af92f7e22 100644 --- a/arch/nds32/kernel/ex-exit.S +++ b/arch/nds32/kernel/ex-exit.S @@ -138,8 +138,8 @@ no_work_pending: #ifdef CONFIG_TRACE_IRQFLAGS lwi $p0, [$sp+(#IPSW_OFFSET)] andi $p0, $p0, #0x1 - la $r10, trace_hardirqs_off - la $r9, trace_hardirqs_on + la $r10, __trace_hardirqs_off + la $r9, __trace_hardirqs_on cmovz $r9, $p0, $r10 jral $r9 #endif diff --git a/arch/nds32/kernel/ftrace.c b/arch/nds32/kernel/ftrace.c new file mode 100644 index 000000000000..a0a9679ad5de --- /dev/null +++ b/arch/nds32/kernel/ftrace.c @@ -0,0 +1,309 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <linux/ftrace.h> +#include <linux/uaccess.h> +#include <asm/cacheflush.h> + +#ifndef CONFIG_DYNAMIC_FTRACE +extern void (*ftrace_trace_function)(unsigned long, unsigned long, + struct ftrace_ops*, struct pt_regs*); +extern int ftrace_graph_entry_stub(struct ftrace_graph_ent *trace); +extern void ftrace_graph_caller(void); + +noinline void __naked ftrace_stub(unsigned long ip, unsigned long parent_ip, + struct ftrace_ops *op, struct pt_regs *regs) +{ + __asm__ (""); /* avoid to optimize as pure function */ +} + +noinline void _mcount(unsigned long parent_ip) +{ + /* save all state by the compiler prologue */ + + unsigned long ip = (unsigned long)__builtin_return_address(0); + + if (ftrace_trace_function != ftrace_stub) + ftrace_trace_function(ip - MCOUNT_INSN_SIZE, parent_ip, + NULL, NULL); + +#ifdef CONFIG_FUNCTION_GRAPH_TRACER + if (ftrace_graph_return != (trace_func_graph_ret_t)ftrace_stub + || ftrace_graph_entry != ftrace_graph_entry_stub) + ftrace_graph_caller(); +#endif + + /* restore all state by the compiler epilogue */ +} +EXPORT_SYMBOL(_mcount); + +#else /* CONFIG_DYNAMIC_FTRACE */ + +noinline void __naked ftrace_stub(unsigned long ip, unsigned long parent_ip, + struct ftrace_ops *op, struct pt_regs *regs) +{ + __asm__ (""); /* avoid to optimize as pure function */ +} + +noinline void __naked _mcount(unsigned long parent_ip) +{ + __asm__ (""); /* avoid to optimize as pure function */ +} +EXPORT_SYMBOL(_mcount); + +#define XSTR(s) STR(s) +#define STR(s) #s +void _ftrace_caller(unsigned long parent_ip) +{ + /* save all state needed by the compiler prologue */ + + /* + * prepare arguments for real tracing function + * first arg : __builtin_return_address(0) - MCOUNT_INSN_SIZE + * second arg : parent_ip + */ + __asm__ __volatile__ ( + "move $r1, %0 \n\t" + "addi $r0, %1, #-" XSTR(MCOUNT_INSN_SIZE) "\n\t" + : + : "r" (parent_ip), "r" (__builtin_return_address(0))); + + /* a placeholder for the call to a real tracing function */ + __asm__ __volatile__ ( + "ftrace_call: \n\t" + "nop \n\t" + "nop \n\t" + "nop \n\t"); + +#ifdef CONFIG_FUNCTION_GRAPH_TRACER + /* a placeholder for the call to ftrace_graph_caller */ + __asm__ __volatile__ ( + "ftrace_graph_call: \n\t" + "nop \n\t" + "nop \n\t" + "nop \n\t"); +#endif + /* restore all state needed by the compiler epilogue */ +} + +int __init ftrace_dyn_arch_init(void) +{ + return 0; +} + +int ftrace_arch_code_modify_prepare(void) +{ + set_all_modules_text_rw(); + return 0; +} + +int ftrace_arch_code_modify_post_process(void) +{ + set_all_modules_text_ro(); + return 0; +} + +static unsigned long gen_sethi_insn(unsigned long addr) +{ + unsigned long opcode = 0x46000000; + unsigned long imm = addr >> 12; + unsigned long rt_num = 0xf << 20; + + return ENDIAN_CONVERT(opcode | rt_num | imm); +} + +static unsigned long gen_ori_insn(unsigned long addr) +{ + unsigned long opcode = 0x58000000; + unsigned long imm = addr & 0x0000fff; + unsigned long rt_num = 0xf << 20; + unsigned long ra_num = 0xf << 15; + + return ENDIAN_CONVERT(opcode | rt_num | ra_num | imm); +} + +static unsigned long gen_jral_insn(unsigned long addr) +{ + unsigned long opcode = 0x4a000001; + unsigned long rt_num = 0x1e << 20; + unsigned long rb_num = 0xf << 10; + + return ENDIAN_CONVERT(opcode | rt_num | rb_num); +} + +static void ftrace_gen_call_insn(unsigned long *call_insns, + unsigned long addr) +{ + call_insns[0] = gen_sethi_insn(addr); /* sethi $r15, imm20u */ + call_insns[1] = gen_ori_insn(addr); /* ori $r15, $r15, imm15u */ + call_insns[2] = gen_jral_insn(addr); /* jral $lp, $r15 */ +} + +static int __ftrace_modify_code(unsigned long pc, unsigned long *old_insn, + unsigned long *new_insn, bool validate) +{ + unsigned long orig_insn[3]; + + if (validate) { + if (probe_kernel_read(orig_insn, (void *)pc, MCOUNT_INSN_SIZE)) + return -EFAULT; + if (memcmp(orig_insn, old_insn, MCOUNT_INSN_SIZE)) + return -EINVAL; + } + + if (probe_kernel_write((void *)pc, new_insn, MCOUNT_INSN_SIZE)) + return -EPERM; + + return 0; +} + +static int ftrace_modify_code(unsigned long pc, unsigned long *old_insn, + unsigned long *new_insn, bool validate) +{ + int ret; + + ret = __ftrace_modify_code(pc, old_insn, new_insn, validate); + if (ret) + return ret; + + flush_icache_range(pc, pc + MCOUNT_INSN_SIZE); + + return ret; +} + +int ftrace_update_ftrace_func(ftrace_func_t func) +{ + unsigned long pc = (unsigned long)&ftrace_call; + unsigned long old_insn[3] = {INSN_NOP, INSN_NOP, INSN_NOP}; + unsigned long new_insn[3] = {INSN_NOP, INSN_NOP, INSN_NOP}; + + if (func != ftrace_stub) + ftrace_gen_call_insn(new_insn, (unsigned long)func); + + return ftrace_modify_code(pc, old_insn, new_insn, false); +} + +int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr) +{ + unsigned long pc = rec->ip; + unsigned long nop_insn[3] = {INSN_NOP, INSN_NOP, INSN_NOP}; + unsigned long call_insn[3] = {INSN_NOP, INSN_NOP, INSN_NOP}; + + ftrace_gen_call_insn(call_insn, addr); + + return ftrace_modify_code(pc, nop_insn, call_insn, true); +} + +int ftrace_make_nop(struct module *mod, struct dyn_ftrace *rec, + unsigned long addr) +{ + unsigned long pc = rec->ip; + unsigned long nop_insn[3] = {INSN_NOP, INSN_NOP, INSN_NOP}; + unsigned long call_insn[3] = {INSN_NOP, INSN_NOP, INSN_NOP}; + + ftrace_gen_call_insn(call_insn, addr); + + return ftrace_modify_code(pc, call_insn, nop_insn, true); +} +#endif /* CONFIG_DYNAMIC_FTRACE */ + +#ifdef CONFIG_FUNCTION_GRAPH_TRACER +void prepare_ftrace_return(unsigned long *parent, unsigned long self_addr, + unsigned long frame_pointer) +{ + unsigned long return_hooker = (unsigned long)&return_to_handler; + struct ftrace_graph_ent trace; + unsigned long old; + int err; + + if (unlikely(atomic_read(¤t->tracing_graph_pause))) + return; + + old = *parent; + + trace.func = self_addr; + trace.depth = current->curr_ret_stack + 1; + + /* Only trace if the calling function expects to */ + if (!ftrace_graph_entry(&trace)) + return; + + err = ftrace_push_return_trace(old, self_addr, &trace.depth, + frame_pointer, NULL); + + if (err == -EBUSY) + return; + + *parent = return_hooker; +} + +noinline void ftrace_graph_caller(void) +{ + unsigned long *parent_ip = + (unsigned long *)(__builtin_frame_address(2) - 4); + + unsigned long selfpc = + (unsigned long)(__builtin_return_address(1) - MCOUNT_INSN_SIZE); + + unsigned long frame_pointer = + (unsigned long)__builtin_frame_address(3); + + prepare_ftrace_return(parent_ip, selfpc, frame_pointer); +} + +extern unsigned long ftrace_return_to_handler(unsigned long frame_pointer); +void __naked return_to_handler(void) +{ + __asm__ __volatile__ ( + /* save state needed by the ABI */ + "smw.adm $r0,[$sp],$r1,#0x0 \n\t" + + /* get original return address */ + "move $r0, $fp \n\t" + "bal ftrace_return_to_handler\n\t" + "move $lp, $r0 \n\t" + + /* restore state nedded by the ABI */ + "lmw.bim $r0,[$sp],$r1,#0x0 \n\t"); +} + +#ifdef CONFIG_DYNAMIC_FTRACE +extern unsigned long ftrace_graph_call; + +static int ftrace_modify_graph_caller(bool enable) +{ + unsigned long pc = (unsigned long)&ftrace_graph_call; + unsigned long nop_insn[3] = {INSN_NOP, INSN_NOP, INSN_NOP}; + unsigned long call_insn[3] = {INSN_NOP, INSN_NOP, INSN_NOP}; + + ftrace_gen_call_insn(call_insn, (unsigned long)ftrace_graph_caller); + + if (enable) + return ftrace_modify_code(pc, nop_insn, call_insn, true); + else + return ftrace_modify_code(pc, call_insn, nop_insn, true); +} + +int ftrace_enable_ftrace_graph_caller(void) +{ + return ftrace_modify_graph_caller(true); +} + +int ftrace_disable_ftrace_graph_caller(void) +{ + return ftrace_modify_graph_caller(false); +} +#endif /* CONFIG_DYNAMIC_FTRACE */ + +#endif /* CONFIG_FUNCTION_GRAPH_TRACER */ + + +#ifdef CONFIG_TRACE_IRQFLAGS +noinline void __trace_hardirqs_off(void) +{ + trace_hardirqs_off(); +} +noinline void __trace_hardirqs_on(void) +{ + trace_hardirqs_on(); +} +#endif /* CONFIG_TRACE_IRQFLAGS */ diff --git a/arch/nds32/kernel/module.c b/arch/nds32/kernel/module.c index 4167283d8293..1e31829cbc2a 100644 --- a/arch/nds32/kernel/module.c +++ b/arch/nds32/kernel/module.c @@ -40,7 +40,7 @@ void do_reloc16(unsigned int val, unsigned int *loc, unsigned int val_mask, tmp2 = tmp & loc_mask; if (partial_in_place) { - tmp &= (!loc_mask); + tmp &= (~loc_mask); tmp = tmp2 | ((tmp + ((val & val_mask) >> val_shift)) & val_mask); } else { @@ -70,7 +70,7 @@ void do_reloc32(unsigned int val, unsigned int *loc, unsigned int val_mask, tmp2 = tmp & loc_mask; if (partial_in_place) { - tmp &= (!loc_mask); + tmp &= (~loc_mask); tmp = tmp2 | ((tmp + ((val & val_mask) >> val_shift)) & val_mask); } else { diff --git a/arch/nds32/kernel/stacktrace.c b/arch/nds32/kernel/stacktrace.c index 8b231e910ea6..d974c0c1c65f 100644 --- a/arch/nds32/kernel/stacktrace.c +++ b/arch/nds32/kernel/stacktrace.c @@ -4,6 +4,7 @@ #include <linux/sched/debug.h> #include <linux/sched/task_stack.h> #include <linux/stacktrace.h> +#include <linux/ftrace.h> void save_stack_trace(struct stack_trace *trace) { @@ -16,6 +17,7 @@ void save_stack_trace_tsk(struct task_struct *tsk, struct stack_trace *trace) unsigned long *fpn; int skip = trace->skip; int savesched; + int graph_idx = 0; if (tsk == current) { __asm__ __volatile__("\tori\t%0, $fp, #0\n":"=r"(fpn)); @@ -29,10 +31,12 @@ void save_stack_trace_tsk(struct task_struct *tsk, struct stack_trace *trace) && (fpn >= (unsigned long *)TASK_SIZE)) { unsigned long lpp, fpp; - lpp = fpn[-1]; + lpp = fpn[LP_OFFSET]; fpp = fpn[FP_OFFSET]; if (!__kernel_text_address(lpp)) break; + else + lpp = ftrace_graph_ret_addr(tsk, &graph_idx, lpp, NULL); if (savesched || !in_sched_functions(lpp)) { if (skip) { diff --git a/arch/nds32/kernel/traps.c b/arch/nds32/kernel/traps.c index a6205fd4db52..1496aab48998 100644 --- a/arch/nds32/kernel/traps.c +++ b/arch/nds32/kernel/traps.c @@ -8,6 +8,7 @@ #include <linux/kdebug.h> #include <linux/sched/task_stack.h> #include <linux/uaccess.h> +#include <linux/ftrace.h> #include <asm/proc-fns.h> #include <asm/unistd.h> @@ -94,28 +95,6 @@ static void dump_instr(struct pt_regs *regs) set_fs(fs); } -#ifdef CONFIG_FUNCTION_GRAPH_TRACER -#include <linux/ftrace.h> -static void -get_real_ret_addr(unsigned long *addr, struct task_struct *tsk, int *graph) -{ - if (*addr == (unsigned long)return_to_handler) { - int index = tsk->curr_ret_stack; - - if (tsk->ret_stack && index >= *graph) { - index -= *graph; - *addr = tsk->ret_stack[index].ret; - (*graph)++; - } - } -} -#else -static inline void -get_real_ret_addr(unsigned long *addr, struct task_struct *tsk, int *graph) -{ -} -#endif - #define LOOP_TIMES (100) static void __dump(struct task_struct *tsk, unsigned long *base_reg) { @@ -126,7 +105,8 @@ static void __dump(struct task_struct *tsk, unsigned long *base_reg) while (!kstack_end(base_reg)) { ret_addr = *base_reg++; if (__kernel_text_address(ret_addr)) { - get_real_ret_addr(&ret_addr, tsk, &graph); + ret_addr = ftrace_graph_ret_addr( + tsk, &graph, ret_addr, NULL); print_ip_sym(ret_addr); } if (--cnt < 0) @@ -137,15 +117,12 @@ static void __dump(struct task_struct *tsk, unsigned long *base_reg) !((unsigned long)base_reg & 0x3) && ((unsigned long)base_reg >= TASK_SIZE)) { unsigned long next_fp; -#if !defined(NDS32_ABI_2) - ret_addr = base_reg[0]; - next_fp = base_reg[1]; -#else - ret_addr = base_reg[-1]; + ret_addr = base_reg[LP_OFFSET]; next_fp = base_reg[FP_OFFSET]; -#endif if (__kernel_text_address(ret_addr)) { - get_real_ret_addr(&ret_addr, tsk, &graph); + + ret_addr = ftrace_graph_ret_addr( + tsk, &graph, ret_addr, NULL); print_ip_sym(ret_addr); } if (--cnt < 0) @@ -196,11 +173,10 @@ void die(const char *str, struct pt_regs *regs, int err) pr_emerg("CPU: %i\n", smp_processor_id()); show_regs(regs); pr_emerg("Process %s (pid: %d, stack limit = 0x%p)\n", - tsk->comm, tsk->pid, task_thread_info(tsk) + 1); + tsk->comm, tsk->pid, end_of_stack(tsk)); if (!user_mode(regs) || in_interrupt()) { - dump_mem("Stack: ", regs->sp, - THREAD_SIZE + (unsigned long)task_thread_info(tsk)); + dump_mem("Stack: ", regs->sp, (regs->sp + PAGE_SIZE) & PAGE_MASK); dump_instr(regs); dump_stack(); } diff --git a/arch/nds32/kernel/vmlinux.lds.S b/arch/nds32/kernel/vmlinux.lds.S index 288313b886ef..9e90f30a181d 100644 --- a/arch/nds32/kernel/vmlinux.lds.S +++ b/arch/nds32/kernel/vmlinux.lds.S @@ -13,14 +13,26 @@ OUTPUT_ARCH(nds32) ENTRY(_stext_lma) jiffies = jiffies_64; +#if defined(CONFIG_GCOV_KERNEL) +#define NDS32_EXIT_KEEP(x) x +#else +#define NDS32_EXIT_KEEP(x) +#endif + SECTIONS { _stext_lma = TEXTADDR - LOAD_OFFSET; . = TEXTADDR; __init_begin = .; HEAD_TEXT_SECTION + .exit.text : { + NDS32_EXIT_KEEP(EXIT_TEXT) + } INIT_TEXT_SECTION(PAGE_SIZE) INIT_DATA_SECTION(16) + .exit.data : { + NDS32_EXIT_KEEP(EXIT_DATA) + } PERCPU_SECTION(L1_CACHE_BYTES) __init_end = .; diff --git a/arch/powerpc/include/asm/book3s/64/pgtable.h b/arch/powerpc/include/asm/book3s/64/pgtable.h index 13a688fc8cd0..2fdc865ca374 100644 --- a/arch/powerpc/include/asm/book3s/64/pgtable.h +++ b/arch/powerpc/include/asm/book3s/64/pgtable.h @@ -1051,7 +1051,6 @@ static inline void vmemmap_remove_mapping(unsigned long start, return hash__vmemmap_remove_mapping(start, page_size); } #endif -struct page *realmode_pfn_to_page(unsigned long pfn); static inline pte_t pmd_pte(pmd_t pmd) { diff --git a/arch/powerpc/include/asm/iommu.h b/arch/powerpc/include/asm/iommu.h index ab3a4fba38e3..3d4b88cb8599 100644 --- a/arch/powerpc/include/asm/iommu.h +++ b/arch/powerpc/include/asm/iommu.h @@ -220,8 +220,6 @@ extern void iommu_del_device(struct device *dev); extern int __init tce_iommu_bus_notifier_init(void); extern long iommu_tce_xchg(struct iommu_table *tbl, unsigned long entry, unsigned long *hpa, enum dma_data_direction *direction); -extern long iommu_tce_xchg_rm(struct iommu_table *tbl, unsigned long entry, - unsigned long *hpa, enum dma_data_direction *direction); #else static inline void iommu_register_group(struct iommu_table_group *table_group, int pci_domain_number, diff --git a/arch/powerpc/include/asm/mmu_context.h b/arch/powerpc/include/asm/mmu_context.h index b2f89b621b15..b694d6af1150 100644 --- a/arch/powerpc/include/asm/mmu_context.h +++ b/arch/powerpc/include/asm/mmu_context.h @@ -38,6 +38,7 @@ extern long mm_iommu_ua_to_hpa(struct mm_iommu_table_group_mem_t *mem, unsigned long ua, unsigned int pageshift, unsigned long *hpa); extern long mm_iommu_ua_to_hpa_rm(struct mm_iommu_table_group_mem_t *mem, unsigned long ua, unsigned int pageshift, unsigned long *hpa); +extern void mm_iommu_ua_mark_dirty_rm(struct mm_struct *mm, unsigned long ua); extern long mm_iommu_mapped_inc(struct mm_iommu_table_group_mem_t *mem); extern void mm_iommu_mapped_dec(struct mm_iommu_table_group_mem_t *mem); #endif diff --git a/arch/powerpc/kernel/iommu.c b/arch/powerpc/kernel/iommu.c index af7a20dc6e09..19b4c628f3be 100644 --- a/arch/powerpc/kernel/iommu.c +++ b/arch/powerpc/kernel/iommu.c @@ -1013,31 +1013,6 @@ long iommu_tce_xchg(struct iommu_table *tbl, unsigned long entry, } EXPORT_SYMBOL_GPL(iommu_tce_xchg); -#ifdef CONFIG_PPC_BOOK3S_64 -long iommu_tce_xchg_rm(struct iommu_table *tbl, unsigned long entry, - unsigned long *hpa, enum dma_data_direction *direction) -{ - long ret; - - ret = tbl->it_ops->exchange_rm(tbl, entry, hpa, direction); - - if (!ret && ((*direction == DMA_FROM_DEVICE) || - (*direction == DMA_BIDIRECTIONAL))) { - struct page *pg = realmode_pfn_to_page(*hpa >> PAGE_SHIFT); - - if (likely(pg)) { - SetPageDirty(pg); - } else { - tbl->it_ops->exchange_rm(tbl, entry, hpa, direction); - ret = -EFAULT; - } - } - - return ret; -} -EXPORT_SYMBOL_GPL(iommu_tce_xchg_rm); -#endif - int iommu_take_ownership(struct iommu_table *tbl) { unsigned long flags, i, sz = (tbl->it_size + 7) >> 3; diff --git a/arch/powerpc/kvm/book3s_64_mmu_hv.c b/arch/powerpc/kvm/book3s_64_mmu_hv.c index 3c0e8fb2b773..68e14afecac8 100644 --- a/arch/powerpc/kvm/book3s_64_mmu_hv.c +++ b/arch/powerpc/kvm/book3s_64_mmu_hv.c @@ -358,7 +358,7 @@ static int kvmppc_mmu_book3s_64_hv_xlate(struct kvm_vcpu *vcpu, gva_t eaddr, unsigned long pp, key; unsigned long v, orig_v, gr; __be64 *hptep; - int index; + long int index; int virtmode = vcpu->arch.shregs.msr & (data ? MSR_DR : MSR_IR); if (kvm_is_radix(vcpu->kvm)) diff --git a/arch/powerpc/kvm/book3s_64_mmu_radix.c b/arch/powerpc/kvm/book3s_64_mmu_radix.c index 0af1c0aea1fe..933c574e1cf7 100644 --- a/arch/powerpc/kvm/book3s_64_mmu_radix.c +++ b/arch/powerpc/kvm/book3s_64_mmu_radix.c @@ -525,8 +525,8 @@ int kvmppc_book3s_radix_page_fault(struct kvm_run *run, struct kvm_vcpu *vcpu, unsigned long ea, unsigned long dsisr) { struct kvm *kvm = vcpu->kvm; - unsigned long mmu_seq, pte_size; - unsigned long gpa, gfn, hva, pfn; + unsigned long mmu_seq; + unsigned long gpa, gfn, hva; struct kvm_memory_slot *memslot; struct page *page = NULL; long ret; @@ -623,9 +623,10 @@ int kvmppc_book3s_radix_page_fault(struct kvm_run *run, struct kvm_vcpu *vcpu, */ hva = gfn_to_hva_memslot(memslot, gfn); if (upgrade_p && __get_user_pages_fast(hva, 1, 1, &page) == 1) { - pfn = page_to_pfn(page); upgrade_write = true; } else { + unsigned long pfn; + /* Call KVM generic code to do the slow-path check */ pfn = __gfn_to_pfn_memslot(memslot, gfn, false, NULL, writing, upgrade_p); @@ -639,63 +640,45 @@ int kvmppc_book3s_radix_page_fault(struct kvm_run *run, struct kvm_vcpu *vcpu, } } - /* See if we can insert a 1GB or 2MB large PTE here */ - level = 0; - if (page && PageCompound(page)) { - pte_size = PAGE_SIZE << compound_order(compound_head(page)); - if (pte_size >= PUD_SIZE && - (gpa & (PUD_SIZE - PAGE_SIZE)) == - (hva & (PUD_SIZE - PAGE_SIZE))) { - level = 2; - pfn &= ~((PUD_SIZE >> PAGE_SHIFT) - 1); - } else if (pte_size >= PMD_SIZE && - (gpa & (PMD_SIZE - PAGE_SIZE)) == - (hva & (PMD_SIZE - PAGE_SIZE))) { - level = 1; - pfn &= ~((PMD_SIZE >> PAGE_SHIFT) - 1); - } - } - /* - * Compute the PTE value that we need to insert. + * Read the PTE from the process' radix tree and use that + * so we get the shift and attribute bits. */ - if (page) { - pgflags = _PAGE_READ | _PAGE_EXEC | _PAGE_PRESENT | _PAGE_PTE | - _PAGE_ACCESSED; - if (writing || upgrade_write) - pgflags |= _PAGE_WRITE | _PAGE_DIRTY; - pte = pfn_pte(pfn, __pgprot(pgflags)); + local_irq_disable(); + ptep = __find_linux_pte(vcpu->arch.pgdir, hva, NULL, &shift); + pte = *ptep; + local_irq_enable(); + + /* Get pte level from shift/size */ + if (shift == PUD_SHIFT && + (gpa & (PUD_SIZE - PAGE_SIZE)) == + (hva & (PUD_SIZE - PAGE_SIZE))) { + level = 2; + } else if (shift == PMD_SHIFT && + (gpa & (PMD_SIZE - PAGE_SIZE)) == + (hva & (PMD_SIZE - PAGE_SIZE))) { + level = 1; } else { - /* - * Read the PTE from the process' radix tree and use that - * so we get the attribute bits. - */ - local_irq_disable(); - ptep = __find_linux_pte(vcpu->arch.pgdir, hva, NULL, &shift); - pte = *ptep; - local_irq_enable(); - if (shift == PUD_SHIFT && - (gpa & (PUD_SIZE - PAGE_SIZE)) == - (hva & (PUD_SIZE - PAGE_SIZE))) { - level = 2; - } else if (shift == PMD_SHIFT && - (gpa & (PMD_SIZE - PAGE_SIZE)) == - (hva & (PMD_SIZE - PAGE_SIZE))) { - level = 1; - } else if (shift && shift != PAGE_SHIFT) { - /* Adjust PFN */ - unsigned long mask = (1ul << shift) - PAGE_SIZE; - pte = __pte(pte_val(pte) | (hva & mask)); - } - pte = __pte(pte_val(pte) | _PAGE_EXEC | _PAGE_ACCESSED); - if (writing || upgrade_write) { - if (pte_val(pte) & _PAGE_WRITE) - pte = __pte(pte_val(pte) | _PAGE_DIRTY); - } else { - pte = __pte(pte_val(pte) & ~(_PAGE_WRITE | _PAGE_DIRTY)); + level = 0; + if (shift > PAGE_SHIFT) { + /* + * If the pte maps more than one page, bring over + * bits from the virtual address to get the real + * address of the specific single page we want. + */ + unsigned long rpnmask = (1ul << shift) - PAGE_SIZE; + pte = __pte(pte_val(pte) | (hva & rpnmask)); } } + pte = __pte(pte_val(pte) | _PAGE_EXEC | _PAGE_ACCESSED); + if (writing || upgrade_write) { + if (pte_val(pte) & _PAGE_WRITE) + pte = __pte(pte_val(pte) | _PAGE_DIRTY); + } else { + pte = __pte(pte_val(pte) & ~(_PAGE_WRITE | _PAGE_DIRTY)); + } + /* Allocate space in the tree and write the PTE */ ret = kvmppc_create_pte(kvm, pte, gpa, level, mmu_seq); @@ -725,10 +708,10 @@ int kvm_unmap_radix(struct kvm *kvm, struct kvm_memory_slot *memslot, gpa, shift); kvmppc_radix_tlbie_page(kvm, gpa, shift); if ((old & _PAGE_DIRTY) && memslot->dirty_bitmap) { - unsigned long npages = 1; + unsigned long psize = PAGE_SIZE; if (shift) - npages = 1ul << (shift - PAGE_SHIFT); - kvmppc_update_dirty_map(memslot, gfn, npages); + psize = 1ul << shift; + kvmppc_update_dirty_map(memslot, gfn, psize); } } return 0; diff --git a/arch/powerpc/kvm/book3s_64_vio_hv.c b/arch/powerpc/kvm/book3s_64_vio_hv.c index 506a4d400458..6821ead4b4eb 100644 --- a/arch/powerpc/kvm/book3s_64_vio_hv.c +++ b/arch/powerpc/kvm/book3s_64_vio_hv.c @@ -187,12 +187,35 @@ long kvmppc_gpa_to_ua(struct kvm *kvm, unsigned long gpa, EXPORT_SYMBOL_GPL(kvmppc_gpa_to_ua); #ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE -static void kvmppc_rm_clear_tce(struct iommu_table *tbl, unsigned long entry) +static long iommu_tce_xchg_rm(struct mm_struct *mm, struct iommu_table *tbl, + unsigned long entry, unsigned long *hpa, + enum dma_data_direction *direction) +{ + long ret; + + ret = tbl->it_ops->exchange_rm(tbl, entry, hpa, direction); + + if (!ret && ((*direction == DMA_FROM_DEVICE) || + (*direction == DMA_BIDIRECTIONAL))) { + __be64 *pua = IOMMU_TABLE_USERSPACE_ENTRY_RM(tbl, entry); + /* + * kvmppc_rm_tce_iommu_do_map() updates the UA cache after + * calling this so we still get here a valid UA. + */ + if (pua && *pua) + mm_iommu_ua_mark_dirty_rm(mm, be64_to_cpu(*pua)); + } + + return ret; +} + +static void kvmppc_rm_clear_tce(struct kvm *kvm, struct iommu_table *tbl, + unsigned long entry) { unsigned long hpa = 0; enum dma_data_direction dir = DMA_NONE; - iommu_tce_xchg_rm(tbl, entry, &hpa, &dir); + iommu_tce_xchg_rm(kvm->mm, tbl, entry, &hpa, &dir); } static long kvmppc_rm_tce_iommu_mapped_dec(struct kvm *kvm, @@ -224,7 +247,7 @@ static long kvmppc_rm_tce_iommu_do_unmap(struct kvm *kvm, unsigned long hpa = 0; long ret; - if (iommu_tce_xchg_rm(tbl, entry, &hpa, &dir)) + if (iommu_tce_xchg_rm(kvm->mm, tbl, entry, &hpa, &dir)) /* * real mode xchg can fail if struct page crosses * a page boundary @@ -236,7 +259,7 @@ static long kvmppc_rm_tce_iommu_do_unmap(struct kvm *kvm, ret = kvmppc_rm_tce_iommu_mapped_dec(kvm, tbl, entry); if (ret) - iommu_tce_xchg_rm(tbl, entry, &hpa, &dir); + iommu_tce_xchg_rm(kvm->mm, tbl, entry, &hpa, &dir); return ret; } @@ -282,7 +305,7 @@ static long kvmppc_rm_tce_iommu_do_map(struct kvm *kvm, struct iommu_table *tbl, if (WARN_ON_ONCE_RM(mm_iommu_mapped_inc(mem))) return H_CLOSED; - ret = iommu_tce_xchg_rm(tbl, entry, &hpa, &dir); + ret = iommu_tce_xchg_rm(kvm->mm, tbl, entry, &hpa, &dir); if (ret) { mm_iommu_mapped_dec(mem); /* @@ -371,7 +394,7 @@ long kvmppc_rm_h_put_tce(struct kvm_vcpu *vcpu, unsigned long liobn, return ret; WARN_ON_ONCE_RM(1); - kvmppc_rm_clear_tce(stit->tbl, entry); + kvmppc_rm_clear_tce(vcpu->kvm, stit->tbl, entry); } kvmppc_tce_put(stt, entry, tce); @@ -520,7 +543,7 @@ long kvmppc_rm_h_put_tce_indirect(struct kvm_vcpu *vcpu, goto unlock_exit; WARN_ON_ONCE_RM(1); - kvmppc_rm_clear_tce(stit->tbl, entry); + kvmppc_rm_clear_tce(vcpu->kvm, stit->tbl, entry); } kvmppc_tce_put(stt, entry + i, tce); @@ -571,7 +594,7 @@ long kvmppc_rm_h_stuff_tce(struct kvm_vcpu *vcpu, return ret; WARN_ON_ONCE_RM(1); - kvmppc_rm_clear_tce(stit->tbl, entry); + kvmppc_rm_clear_tce(vcpu->kvm, stit->tbl, entry); } } diff --git a/arch/powerpc/mm/init_64.c b/arch/powerpc/mm/init_64.c index 51ce091914f9..7a9886f98b0c 100644 --- a/arch/powerpc/mm/init_64.c +++ b/arch/powerpc/mm/init_64.c @@ -308,55 +308,6 @@ void register_page_bootmem_memmap(unsigned long section_nr, { } -/* - * We do not have access to the sparsemem vmemmap, so we fallback to - * walking the list of sparsemem blocks which we already maintain for - * the sake of crashdump. In the long run, we might want to maintain - * a tree if performance of that linear walk becomes a problem. - * - * realmode_pfn_to_page functions can fail due to: - * 1) As real sparsemem blocks do not lay in RAM continously (they - * are in virtual address space which is not available in the real mode), - * the requested page struct can be split between blocks so get_page/put_page - * may fail. - * 2) When huge pages are used, the get_page/put_page API will fail - * in real mode as the linked addresses in the page struct are virtual - * too. - */ -struct page *realmode_pfn_to_page(unsigned long pfn) -{ - struct vmemmap_backing *vmem_back; - struct page *page; - unsigned long page_size = 1 << mmu_psize_defs[mmu_vmemmap_psize].shift; - unsigned long pg_va = (unsigned long) pfn_to_page(pfn); - - for (vmem_back = vmemmap_list; vmem_back; vmem_back = vmem_back->list) { - if (pg_va < vmem_back->virt_addr) - continue; - - /* After vmemmap_list entry free is possible, need check all */ - if ((pg_va + sizeof(struct page)) <= - (vmem_back->virt_addr + page_size)) { - page = (struct page *) (vmem_back->phys + pg_va - - vmem_back->virt_addr); - return page; - } - } - - /* Probably that page struct is split between real pages */ - return NULL; -} -EXPORT_SYMBOL_GPL(realmode_pfn_to_page); - -#else - -struct page *realmode_pfn_to_page(unsigned long pfn) -{ - struct page *page = pfn_to_page(pfn); - return page; -} -EXPORT_SYMBOL_GPL(realmode_pfn_to_page); - #endif /* CONFIG_SPARSEMEM_VMEMMAP */ #ifdef CONFIG_PPC_BOOK3S_64 diff --git a/arch/powerpc/mm/mmu_context_iommu.c b/arch/powerpc/mm/mmu_context_iommu.c index c9ee9e23845f..56c2234cc6ae 100644 --- a/arch/powerpc/mm/mmu_context_iommu.c +++ b/arch/powerpc/mm/mmu_context_iommu.c @@ -18,11 +18,15 @@ #include <linux/migrate.h> #include <linux/hugetlb.h> #include <linux/swap.h> +#include <linux/sizes.h> #include <asm/mmu_context.h> #include <asm/pte-walk.h> static DEFINE_MUTEX(mem_list_mutex); +#define MM_IOMMU_TABLE_GROUP_PAGE_DIRTY 0x1 +#define MM_IOMMU_TABLE_GROUP_PAGE_MASK ~(SZ_4K - 1) + struct mm_iommu_table_group_mem_t { struct list_head next; struct rcu_head rcu; @@ -263,6 +267,9 @@ static void mm_iommu_unpin(struct mm_iommu_table_group_mem_t *mem) if (!page) continue; + if (mem->hpas[i] & MM_IOMMU_TABLE_GROUP_PAGE_DIRTY) + SetPageDirty(page); + put_page(page); mem->hpas[i] = 0; } @@ -360,7 +367,6 @@ struct mm_iommu_table_group_mem_t *mm_iommu_lookup_rm(struct mm_struct *mm, return ret; } -EXPORT_SYMBOL_GPL(mm_iommu_lookup_rm); struct mm_iommu_table_group_mem_t *mm_iommu_find(struct mm_struct *mm, unsigned long ua, unsigned long entries) @@ -390,7 +396,7 @@ long mm_iommu_ua_to_hpa(struct mm_iommu_table_group_mem_t *mem, if (pageshift > mem->pageshift) return -EFAULT; - *hpa = *va | (ua & ~PAGE_MASK); + *hpa = (*va & MM_IOMMU_TABLE_GROUP_PAGE_MASK) | (ua & ~PAGE_MASK); return 0; } @@ -413,11 +419,31 @@ long mm_iommu_ua_to_hpa_rm(struct mm_iommu_table_group_mem_t *mem, if (!pa) return -EFAULT; - *hpa = *pa | (ua & ~PAGE_MASK); + *hpa = (*pa & MM_IOMMU_TABLE_GROUP_PAGE_MASK) | (ua & ~PAGE_MASK); return 0; } -EXPORT_SYMBOL_GPL(mm_iommu_ua_to_hpa_rm); + +extern void mm_iommu_ua_mark_dirty_rm(struct mm_struct *mm, unsigned long ua) +{ + struct mm_iommu_table_group_mem_t *mem; + long entry; + void *va; + unsigned long *pa; + + mem = mm_iommu_lookup_rm(mm, ua, PAGE_SIZE); + if (!mem) + return; + + entry = (ua - mem->ua) >> PAGE_SHIFT; + va = &mem->hpas[entry]; + + pa = (void *) vmalloc_to_phys(va); + if (!pa) + return; + + *pa |= MM_IOMMU_TABLE_GROUP_PAGE_DIRTY; +} long mm_iommu_mapped_inc(struct mm_iommu_table_group_mem_t *mem) { diff --git a/arch/riscv/kernel/setup.c b/arch/riscv/kernel/setup.c index db20dc630e7e..aee603123030 100644 --- a/arch/riscv/kernel/setup.c +++ b/arch/riscv/kernel/setup.c @@ -85,15 +85,8 @@ atomic_t hart_lottery; #ifdef CONFIG_BLK_DEV_INITRD static void __init setup_initrd(void) { - extern char __initramfs_start[]; - extern unsigned long __initramfs_size; unsigned long size; - if (__initramfs_size > 0) { - initrd_start = (unsigned long)(&__initramfs_start); - initrd_end = initrd_start + __initramfs_size; - } - if (initrd_start >= initrd_end) { printk(KERN_INFO "initrd not found or empty"); goto disable; diff --git a/arch/s390/crypto/paes_s390.c b/arch/s390/crypto/paes_s390.c index 80b27294c1de..ab9a0ebecc19 100644 --- a/arch/s390/crypto/paes_s390.c +++ b/arch/s390/crypto/paes_s390.c @@ -208,7 +208,7 @@ static int cbc_paes_crypt(struct blkcipher_desc *desc, unsigned long modifier, walk->dst.virt.addr, walk->src.virt.addr, n); if (k) ret = blkcipher_walk_done(desc, walk, nbytes - k); - if (n < k) { + if (k < n) { if (__cbc_paes_set_key(ctx) != 0) return blkcipher_walk_done(desc, walk, -EIO); memcpy(param.key, ctx->pk.protkey, MAXPROTKEYSIZE); diff --git a/arch/s390/include/asm/mmu.h b/arch/s390/include/asm/mmu.h index f31a15044c24..a8418e1379eb 100644 --- a/arch/s390/include/asm/mmu.h +++ b/arch/s390/include/asm/mmu.h @@ -16,7 +16,13 @@ typedef struct { unsigned long asce; unsigned long asce_limit; unsigned long vdso_base; - /* The mmu context allocates 4K page tables. */ + /* + * The following bitfields need a down_write on the mm + * semaphore when they are written to. As they are only + * written once, they can be read without a lock. + * + * The mmu context allocates 4K page tables. + */ unsigned int alloc_pgste:1; /* The mmu context uses extended page tables. */ unsigned int has_pgste:1; diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index 91ad4a9425c0..ac5da6b0b862 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -481,7 +481,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) break; case KVM_CAP_S390_HPAGE_1M: r = 0; - if (hpage) + if (hpage && !kvm_is_ucontrol(kvm)) r = 1; break; case KVM_CAP_S390_MEM_OP: @@ -691,11 +691,13 @@ static int kvm_vm_ioctl_enable_cap(struct kvm *kvm, struct kvm_enable_cap *cap) mutex_lock(&kvm->lock); if (kvm->created_vcpus) r = -EBUSY; - else if (!hpage || kvm->arch.use_cmma) + else if (!hpage || kvm->arch.use_cmma || kvm_is_ucontrol(kvm)) r = -EINVAL; else { r = 0; + down_write(&kvm->mm->mmap_sem); kvm->mm->context.allow_gmap_hpage_1m = 1; + up_write(&kvm->mm->mmap_sem); /* * We might have to create fake 4k page * tables. To avoid that the hardware works on diff --git a/arch/s390/kvm/priv.c b/arch/s390/kvm/priv.c index d68f10441a16..8679bd74d337 100644 --- a/arch/s390/kvm/priv.c +++ b/arch/s390/kvm/priv.c @@ -280,9 +280,11 @@ retry: goto retry; } } - if (rc) - return kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING); up_read(¤t->mm->mmap_sem); + if (rc == -EFAULT) + return kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING); + if (rc < 0) + return rc; vcpu->run->s.regs.gprs[reg1] &= ~0xff; vcpu->run->s.regs.gprs[reg1] |= key; return 0; @@ -324,9 +326,11 @@ retry: goto retry; } } - if (rc < 0) - return kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING); up_read(¤t->mm->mmap_sem); + if (rc == -EFAULT) + return kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING); + if (rc < 0) + return rc; kvm_s390_set_psw_cc(vcpu, rc); return 0; } @@ -390,12 +394,12 @@ static int handle_sske(struct kvm_vcpu *vcpu) FAULT_FLAG_WRITE, &unlocked); rc = !rc ? -EAGAIN : rc; } + up_read(¤t->mm->mmap_sem); if (rc == -EFAULT) return kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING); - - up_read(¤t->mm->mmap_sem); - if (rc >= 0) - start += PAGE_SIZE; + if (rc < 0) + return rc; + start += PAGE_SIZE; } if (m3 & (SSKE_MC | SSKE_MR)) { @@ -1002,13 +1006,15 @@ static int handle_pfmf(struct kvm_vcpu *vcpu) FAULT_FLAG_WRITE, &unlocked); rc = !rc ? -EAGAIN : rc; } + up_read(¤t->mm->mmap_sem); if (rc == -EFAULT) return kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING); - - up_read(¤t->mm->mmap_sem); - if (rc >= 0) - start += PAGE_SIZE; + if (rc == -EAGAIN) + continue; + if (rc < 0) + return rc; } + start += PAGE_SIZE; } if (vcpu->run->s.regs.gprs[reg1] & PFMF_FSC) { if (psw_bits(vcpu->arch.sie_block->gpsw).eaba == PSW_BITS_AMODE_64BIT) { diff --git a/arch/s390/kvm/vsie.c b/arch/s390/kvm/vsie.c index 63844b95c22c..a2b28cd1e3fe 100644 --- a/arch/s390/kvm/vsie.c +++ b/arch/s390/kvm/vsie.c @@ -173,7 +173,8 @@ static int shadow_crycb(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page) return set_validity_icpt(scb_s, 0x0039U); /* copy only the wrapping keys */ - if (read_guest_real(vcpu, crycb_addr + 72, &vsie_page->crycb, 56)) + if (read_guest_real(vcpu, crycb_addr + 72, + vsie_page->crycb.dea_wrapping_key_mask, 56)) return set_validity_icpt(scb_s, 0x0035U); scb_s->ecb3 |= ecb3_flags; diff --git a/arch/s390/mm/gmap.c b/arch/s390/mm/gmap.c index bb44990c8212..911c7ded35f1 100644 --- a/arch/s390/mm/gmap.c +++ b/arch/s390/mm/gmap.c @@ -708,11 +708,13 @@ void gmap_discard(struct gmap *gmap, unsigned long from, unsigned long to) vmaddr |= gaddr & ~PMD_MASK; /* Find vma in the parent mm */ vma = find_vma(gmap->mm, vmaddr); + if (!vma) + continue; /* * We do not discard pages that are backed by * hugetlbfs, so we don't have to refault them. */ - if (vma && is_vm_hugetlb_page(vma)) + if (is_vm_hugetlb_page(vma)) continue; size = min(to - gaddr, PMD_SIZE - (gaddr & ~PMD_MASK)); zap_page_range(vma, vmaddr, size); diff --git a/arch/x86/crypto/aegis128-aesni-glue.c b/arch/x86/crypto/aegis128-aesni-glue.c index acd11b3bf639..2a356b948720 100644 --- a/arch/x86/crypto/aegis128-aesni-glue.c +++ b/arch/x86/crypto/aegis128-aesni-glue.c @@ -379,7 +379,6 @@ static int __init crypto_aegis128_aesni_module_init(void) { if (!boot_cpu_has(X86_FEATURE_XMM2) || !boot_cpu_has(X86_FEATURE_AES) || - !boot_cpu_has(X86_FEATURE_OSXSAVE) || !cpu_has_xfeatures(XFEATURE_MASK_SSE, NULL)) return -ENODEV; diff --git a/arch/x86/crypto/aegis128l-aesni-glue.c b/arch/x86/crypto/aegis128l-aesni-glue.c index 2071c3d1ae07..dbe8bb980da1 100644 --- a/arch/x86/crypto/aegis128l-aesni-glue.c +++ b/arch/x86/crypto/aegis128l-aesni-glue.c @@ -379,7 +379,6 @@ static int __init crypto_aegis128l_aesni_module_init(void) { if (!boot_cpu_has(X86_FEATURE_XMM2) || !boot_cpu_has(X86_FEATURE_AES) || - !boot_cpu_has(X86_FEATURE_OSXSAVE) || !cpu_has_xfeatures(XFEATURE_MASK_SSE, NULL)) return -ENODEV; diff --git a/arch/x86/crypto/aegis256-aesni-glue.c b/arch/x86/crypto/aegis256-aesni-glue.c index b5f2a8fd5a71..8bebda2de92f 100644 --- a/arch/x86/crypto/aegis256-aesni-glue.c +++ b/arch/x86/crypto/aegis256-aesni-glue.c @@ -379,7 +379,6 @@ static int __init crypto_aegis256_aesni_module_init(void) { if (!boot_cpu_has(X86_FEATURE_XMM2) || !boot_cpu_has(X86_FEATURE_AES) || - !boot_cpu_has(X86_FEATURE_OSXSAVE) || !cpu_has_xfeatures(XFEATURE_MASK_SSE, NULL)) return -ENODEV; diff --git a/arch/x86/crypto/morus1280-sse2-glue.c b/arch/x86/crypto/morus1280-sse2-glue.c index 95cf857d2cbb..f40244eaf14d 100644 --- a/arch/x86/crypto/morus1280-sse2-glue.c +++ b/arch/x86/crypto/morus1280-sse2-glue.c @@ -40,7 +40,6 @@ MORUS1280_DECLARE_ALGS(sse2, "morus1280-sse2", 350); static int __init crypto_morus1280_sse2_module_init(void) { if (!boot_cpu_has(X86_FEATURE_XMM2) || - !boot_cpu_has(X86_FEATURE_OSXSAVE) || !cpu_has_xfeatures(XFEATURE_MASK_SSE, NULL)) return -ENODEV; diff --git a/arch/x86/crypto/morus640-sse2-glue.c b/arch/x86/crypto/morus640-sse2-glue.c index 615fb7bc9a32..9afaf8f8565a 100644 --- a/arch/x86/crypto/morus640-sse2-glue.c +++ b/arch/x86/crypto/morus640-sse2-glue.c @@ -40,7 +40,6 @@ MORUS640_DECLARE_ALGS(sse2, "morus640-sse2", 400); static int __init crypto_morus640_sse2_module_init(void) { if (!boot_cpu_has(X86_FEATURE_XMM2) || - !boot_cpu_has(X86_FEATURE_OSXSAVE) || !cpu_has_xfeatures(XFEATURE_MASK_SSE, NULL)) return -ENODEV; diff --git a/arch/x86/events/intel/lbr.c b/arch/x86/events/intel/lbr.c index f3e006bed9a7..c88ed39582a1 100644 --- a/arch/x86/events/intel/lbr.c +++ b/arch/x86/events/intel/lbr.c @@ -1272,4 +1272,8 @@ void intel_pmu_lbr_init_knl(void) x86_pmu.lbr_sel_mask = LBR_SEL_MASK; x86_pmu.lbr_sel_map = snb_lbr_sel_map; + + /* Knights Landing does have MISPREDICT bit */ + if (x86_pmu.intel_cap.lbr_format == LBR_FORMAT_LIP) + x86_pmu.intel_cap.lbr_format = LBR_FORMAT_EIP_FLAGS; } diff --git a/arch/x86/hyperv/hv_apic.c b/arch/x86/hyperv/hv_apic.c index 5b0f613428c2..2c43e3055948 100644 --- a/arch/x86/hyperv/hv_apic.c +++ b/arch/x86/hyperv/hv_apic.c @@ -95,8 +95,8 @@ static void hv_apic_eoi_write(u32 reg, u32 val) */ static bool __send_ipi_mask_ex(const struct cpumask *mask, int vector) { - struct ipi_arg_ex **arg; - struct ipi_arg_ex *ipi_arg; + struct hv_send_ipi_ex **arg; + struct hv_send_ipi_ex *ipi_arg; unsigned long flags; int nr_bank = 0; int ret = 1; @@ -105,7 +105,7 @@ static bool __send_ipi_mask_ex(const struct cpumask *mask, int vector) return false; local_irq_save(flags); - arg = (struct ipi_arg_ex **)this_cpu_ptr(hyperv_pcpu_input_arg); + arg = (struct hv_send_ipi_ex **)this_cpu_ptr(hyperv_pcpu_input_arg); ipi_arg = *arg; if (unlikely(!ipi_arg)) @@ -135,7 +135,7 @@ ipi_mask_ex_done: static bool __send_ipi_mask(const struct cpumask *mask, int vector) { int cur_cpu, vcpu; - struct ipi_arg_non_ex ipi_arg; + struct hv_send_ipi ipi_arg; int ret = 1; trace_hyperv_send_ipi_mask(mask, vector); diff --git a/arch/x86/include/asm/atomic.h b/arch/x86/include/asm/atomic.h index b143717b92b3..ce84388e540c 100644 --- a/arch/x86/include/asm/atomic.h +++ b/arch/x86/include/asm/atomic.h @@ -80,11 +80,11 @@ static __always_inline void arch_atomic_sub(int i, atomic_t *v) * true if the result is zero, or false for all * other cases. */ -#define arch_atomic_sub_and_test arch_atomic_sub_and_test static __always_inline bool arch_atomic_sub_and_test(int i, atomic_t *v) { GEN_BINARY_RMWcc(LOCK_PREFIX "subl", v->counter, "er", i, "%0", e); } +#define arch_atomic_sub_and_test arch_atomic_sub_and_test /** * arch_atomic_inc - increment atomic variable @@ -92,12 +92,12 @@ static __always_inline bool arch_atomic_sub_and_test(int i, atomic_t *v) * * Atomically increments @v by 1. */ -#define arch_atomic_inc arch_atomic_inc static __always_inline void arch_atomic_inc(atomic_t *v) { asm volatile(LOCK_PREFIX "incl %0" : "+m" (v->counter)); } +#define arch_atomic_inc arch_atomic_inc /** * arch_atomic_dec - decrement atomic variable @@ -105,12 +105,12 @@ static __always_inline void arch_atomic_inc(atomic_t *v) * * Atomically decrements @v by 1. */ -#define arch_atomic_dec arch_atomic_dec static __always_inline void arch_atomic_dec(atomic_t *v) { asm volatile(LOCK_PREFIX "decl %0" : "+m" (v->counter)); } +#define arch_atomic_dec arch_atomic_dec /** * arch_atomic_dec_and_test - decrement and test @@ -120,11 +120,11 @@ static __always_inline void arch_atomic_dec(atomic_t *v) * returns true if the result is 0, or false for all other * cases. */ -#define arch_atomic_dec_and_test arch_atomic_dec_and_test static __always_inline bool arch_atomic_dec_and_test(atomic_t *v) { GEN_UNARY_RMWcc(LOCK_PREFIX "decl", v->counter, "%0", e); } +#define arch_atomic_dec_and_test arch_atomic_dec_and_test /** * arch_atomic_inc_and_test - increment and test @@ -134,11 +134,11 @@ static __always_inline bool arch_atomic_dec_and_test(atomic_t *v) * and returns true if the result is zero, or false for all * other cases. */ -#define arch_atomic_inc_and_test arch_atomic_inc_and_test static __always_inline bool arch_atomic_inc_and_test(atomic_t *v) { GEN_UNARY_RMWcc(LOCK_PREFIX "incl", v->counter, "%0", e); } +#define arch_atomic_inc_and_test arch_atomic_inc_and_test /** * arch_atomic_add_negative - add and test if negative @@ -149,11 +149,11 @@ static __always_inline bool arch_atomic_inc_and_test(atomic_t *v) * if the result is negative, or false when * result is greater than or equal to zero. */ -#define arch_atomic_add_negative arch_atomic_add_negative static __always_inline bool arch_atomic_add_negative(int i, atomic_t *v) { GEN_BINARY_RMWcc(LOCK_PREFIX "addl", v->counter, "er", i, "%0", s); } +#define arch_atomic_add_negative arch_atomic_add_negative /** * arch_atomic_add_return - add integer and return diff --git a/arch/x86/include/asm/atomic64_32.h b/arch/x86/include/asm/atomic64_32.h index ef959f02d070..6a5b0ec460da 100644 --- a/arch/x86/include/asm/atomic64_32.h +++ b/arch/x86/include/asm/atomic64_32.h @@ -205,12 +205,12 @@ static inline long long arch_atomic64_sub(long long i, atomic64_t *v) * * Atomically increments @v by 1. */ -#define arch_atomic64_inc arch_atomic64_inc static inline void arch_atomic64_inc(atomic64_t *v) { __alternative_atomic64(inc, inc_return, /* no output */, "S" (v) : "memory", "eax", "ecx", "edx"); } +#define arch_atomic64_inc arch_atomic64_inc /** * arch_atomic64_dec - decrement atomic64 variable @@ -218,12 +218,12 @@ static inline void arch_atomic64_inc(atomic64_t *v) * * Atomically decrements @v by 1. */ -#define arch_atomic64_dec arch_atomic64_dec static inline void arch_atomic64_dec(atomic64_t *v) { __alternative_atomic64(dec, dec_return, /* no output */, "S" (v) : "memory", "eax", "ecx", "edx"); } +#define arch_atomic64_dec arch_atomic64_dec /** * arch_atomic64_add_unless - add unless the number is a given value @@ -245,7 +245,6 @@ static inline int arch_atomic64_add_unless(atomic64_t *v, long long a, return (int)a; } -#define arch_atomic64_inc_not_zero arch_atomic64_inc_not_zero static inline int arch_atomic64_inc_not_zero(atomic64_t *v) { int r; @@ -253,8 +252,8 @@ static inline int arch_atomic64_inc_not_zero(atomic64_t *v) "S" (v) : "ecx", "edx", "memory"); return r; } +#define arch_atomic64_inc_not_zero arch_atomic64_inc_not_zero -#define arch_atomic64_dec_if_positive arch_atomic64_dec_if_positive static inline long long arch_atomic64_dec_if_positive(atomic64_t *v) { long long r; @@ -262,6 +261,7 @@ static inline long long arch_atomic64_dec_if_positive(atomic64_t *v) "S" (v) : "ecx", "memory"); return r; } +#define arch_atomic64_dec_if_positive arch_atomic64_dec_if_positive #undef alternative_atomic64 #undef __alternative_atomic64 diff --git a/arch/x86/include/asm/atomic64_64.h b/arch/x86/include/asm/atomic64_64.h index 4343d9b4f30e..5f851d92eecd 100644 --- a/arch/x86/include/asm/atomic64_64.h +++ b/arch/x86/include/asm/atomic64_64.h @@ -71,11 +71,11 @@ static inline void arch_atomic64_sub(long i, atomic64_t *v) * true if the result is zero, or false for all * other cases. */ -#define arch_atomic64_sub_and_test arch_atomic64_sub_and_test static inline bool arch_atomic64_sub_and_test(long i, atomic64_t *v) { GEN_BINARY_RMWcc(LOCK_PREFIX "subq", v->counter, "er", i, "%0", e); } +#define arch_atomic64_sub_and_test arch_atomic64_sub_and_test /** * arch_atomic64_inc - increment atomic64 variable @@ -83,13 +83,13 @@ static inline bool arch_atomic64_sub_and_test(long i, atomic64_t *v) * * Atomically increments @v by 1. */ -#define arch_atomic64_inc arch_atomic64_inc static __always_inline void arch_atomic64_inc(atomic64_t *v) { asm volatile(LOCK_PREFIX "incq %0" : "=m" (v->counter) : "m" (v->counter)); } +#define arch_atomic64_inc arch_atomic64_inc /** * arch_atomic64_dec - decrement atomic64 variable @@ -97,13 +97,13 @@ static __always_inline void arch_atomic64_inc(atomic64_t *v) * * Atomically decrements @v by 1. */ -#define arch_atomic64_dec arch_atomic64_dec static __always_inline void arch_atomic64_dec(atomic64_t *v) { asm volatile(LOCK_PREFIX "decq %0" : "=m" (v->counter) : "m" (v->counter)); } +#define arch_atomic64_dec arch_atomic64_dec /** * arch_atomic64_dec_and_test - decrement and test @@ -113,11 +113,11 @@ static __always_inline void arch_atomic64_dec(atomic64_t *v) * returns true if the result is 0, or false for all other * cases. */ -#define arch_atomic64_dec_and_test arch_atomic64_dec_and_test static inline bool arch_atomic64_dec_and_test(atomic64_t *v) { GEN_UNARY_RMWcc(LOCK_PREFIX "decq", v->counter, "%0", e); } +#define arch_atomic64_dec_and_test arch_atomic64_dec_and_test /** * arch_atomic64_inc_and_test - increment and test @@ -127,11 +127,11 @@ static inline bool arch_atomic64_dec_and_test(atomic64_t *v) * and returns true if the result is zero, or false for all * other cases. */ -#define arch_atomic64_inc_and_test arch_atomic64_inc_and_test static inline bool arch_atomic64_inc_and_test(atomic64_t *v) { GEN_UNARY_RMWcc(LOCK_PREFIX "incq", v->counter, "%0", e); } +#define arch_atomic64_inc_and_test arch_atomic64_inc_and_test /** * arch_atomic64_add_negative - add and test if negative @@ -142,11 +142,11 @@ static inline bool arch_atomic64_inc_and_test(atomic64_t *v) * if the result is negative, or false when * result is greater than or equal to zero. */ -#define arch_atomic64_add_negative arch_atomic64_add_negative static inline bool arch_atomic64_add_negative(long i, atomic64_t *v) { GEN_BINARY_RMWcc(LOCK_PREFIX "addq", v->counter, "er", i, "%0", s); } +#define arch_atomic64_add_negative arch_atomic64_add_negative /** * arch_atomic64_add_return - add and return diff --git a/arch/x86/include/asm/fixmap.h b/arch/x86/include/asm/fixmap.h index e203169931c7..6390bd8c141b 100644 --- a/arch/x86/include/asm/fixmap.h +++ b/arch/x86/include/asm/fixmap.h @@ -14,6 +14,16 @@ #ifndef _ASM_X86_FIXMAP_H #define _ASM_X86_FIXMAP_H +/* + * Exposed to assembly code for setting up initial page tables. Cannot be + * calculated in assembly code (fixmap entries are an enum), but is sanity + * checked in the actual fixmap C code to make sure that the fixmap is + * covered fully. + */ +#define FIXMAP_PMD_NUM 2 +/* fixmap starts downwards from the 507th entry in level2_fixmap_pgt */ +#define FIXMAP_PMD_TOP 507 + #ifndef __ASSEMBLY__ #include <linux/kernel.h> #include <asm/acpi.h> diff --git a/arch/x86/include/asm/hyperv-tlfs.h b/arch/x86/include/asm/hyperv-tlfs.h index e977b6b3a538..00e01d215f74 100644 --- a/arch/x86/include/asm/hyperv-tlfs.h +++ b/arch/x86/include/asm/hyperv-tlfs.h @@ -726,19 +726,21 @@ struct hv_enlightened_vmcs { #define HV_STIMER_AUTOENABLE (1ULL << 3) #define HV_STIMER_SINT(config) (__u8)(((config) >> 16) & 0x0F) -struct ipi_arg_non_ex { - u32 vector; - u32 reserved; - u64 cpu_mask; -}; - struct hv_vpset { u64 format; u64 valid_bank_mask; u64 bank_contents[]; }; -struct ipi_arg_ex { +/* HvCallSendSyntheticClusterIpi hypercall */ +struct hv_send_ipi { + u32 vector; + u32 reserved; + u64 cpu_mask; +}; + +/* HvCallSendSyntheticClusterIpiEx hypercall */ +struct hv_send_ipi_ex { u32 vector; u32 reserved; struct hv_vpset vp_set; diff --git a/arch/x86/include/asm/kdebug.h b/arch/x86/include/asm/kdebug.h index 395c9631e000..75f1e35e7c15 100644 --- a/arch/x86/include/asm/kdebug.h +++ b/arch/x86/include/asm/kdebug.h @@ -22,10 +22,20 @@ enum die_val { DIE_NMIUNKNOWN, }; +enum show_regs_mode { + SHOW_REGS_SHORT, + /* + * For when userspace crashed, but we don't think it's our fault, and + * therefore don't print kernel registers. + */ + SHOW_REGS_USER, + SHOW_REGS_ALL +}; + extern void die(const char *, struct pt_regs *,long); extern int __must_check __die(const char *, struct pt_regs *, long); extern void show_stack_regs(struct pt_regs *regs); -extern void __show_regs(struct pt_regs *regs, int all); +extern void __show_regs(struct pt_regs *regs, enum show_regs_mode); extern void show_iret_regs(struct pt_regs *regs); extern unsigned long oops_begin(void); extern void oops_end(unsigned long, struct pt_regs *, int signr); diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 00ddb0c9e612..09b2e3e2cf1b 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -869,6 +869,8 @@ struct kvm_arch { bool x2apic_format; bool x2apic_broadcast_quirk_disabled; + + bool guest_can_read_msr_platform_info; }; struct kvm_vm_stat { @@ -1022,6 +1024,7 @@ struct kvm_x86_ops { void (*refresh_apicv_exec_ctrl)(struct kvm_vcpu *vcpu); void (*hwapic_irr_update)(struct kvm_vcpu *vcpu, int max_irr); void (*hwapic_isr_update)(struct kvm_vcpu *vcpu, int isr); + bool (*guest_apic_has_interrupt)(struct kvm_vcpu *vcpu); void (*load_eoi_exitmap)(struct kvm_vcpu *vcpu, u64 *eoi_exit_bitmap); void (*set_virtual_apic_mode)(struct kvm_vcpu *vcpu); void (*set_apic_access_page_addr)(struct kvm_vcpu *vcpu, hpa_t hpa); @@ -1055,6 +1058,7 @@ struct kvm_x86_ops { bool (*umip_emulated)(void); int (*check_nested_events)(struct kvm_vcpu *vcpu, bool external_intr); + void (*request_immediate_exit)(struct kvm_vcpu *vcpu); void (*sched_in)(struct kvm_vcpu *kvm, int cpu); @@ -1237,19 +1241,12 @@ enum emulation_result { #define EMULTYPE_NO_DECODE (1 << 0) #define EMULTYPE_TRAP_UD (1 << 1) #define EMULTYPE_SKIP (1 << 2) -#define EMULTYPE_RETRY (1 << 3) -#define EMULTYPE_NO_REEXECUTE (1 << 4) -#define EMULTYPE_NO_UD_ON_FAIL (1 << 5) -#define EMULTYPE_VMWARE (1 << 6) -int x86_emulate_instruction(struct kvm_vcpu *vcpu, unsigned long cr2, - int emulation_type, void *insn, int insn_len); - -static inline int emulate_instruction(struct kvm_vcpu *vcpu, - int emulation_type) -{ - return x86_emulate_instruction(vcpu, 0, - emulation_type | EMULTYPE_NO_REEXECUTE, NULL, 0); -} +#define EMULTYPE_ALLOW_RETRY (1 << 3) +#define EMULTYPE_NO_UD_ON_FAIL (1 << 4) +#define EMULTYPE_VMWARE (1 << 5) +int kvm_emulate_instruction(struct kvm_vcpu *vcpu, int emulation_type); +int kvm_emulate_instruction_from_buffer(struct kvm_vcpu *vcpu, + void *insn, int insn_len); void kvm_enable_efer_bits(u64); bool kvm_valid_efer(struct kvm_vcpu *vcpu, u64 efer); @@ -1450,7 +1447,6 @@ asmlinkage void kvm_spurious_fault(void); ____kvm_handle_fault_on_reboot(insn, "") #define KVM_ARCH_WANT_MMU_NOTIFIER -int kvm_unmap_hva(struct kvm *kvm, unsigned long hva); int kvm_unmap_hva_range(struct kvm *kvm, unsigned long start, unsigned long end); int kvm_age_hva(struct kvm *kvm, unsigned long start, unsigned long end); int kvm_test_age_hva(struct kvm *kvm, unsigned long hva); @@ -1463,7 +1459,7 @@ void kvm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event); void kvm_vcpu_reload_apic_access_page(struct kvm_vcpu *vcpu); int kvm_pv_send_ipi(struct kvm *kvm, unsigned long ipi_bitmap_low, - unsigned long ipi_bitmap_high, int min, + unsigned long ipi_bitmap_high, u32 min, unsigned long icr, int op_64_bit); u64 kvm_get_arch_capabilities(void); @@ -1490,6 +1486,7 @@ extern bool kvm_find_async_pf_gfn(struct kvm_vcpu *vcpu, gfn_t gfn); int kvm_skip_emulated_instruction(struct kvm_vcpu *vcpu); int kvm_complete_insn_gp(struct kvm_vcpu *vcpu, int err); +void __kvm_request_immediate_exit(struct kvm_vcpu *vcpu); int kvm_is_in_guest(void); diff --git a/arch/x86/include/asm/mem_encrypt.h b/arch/x86/include/asm/mem_encrypt.h index c0643831706e..616f8e637bc3 100644 --- a/arch/x86/include/asm/mem_encrypt.h +++ b/arch/x86/include/asm/mem_encrypt.h @@ -48,10 +48,13 @@ int __init early_set_memory_encrypted(unsigned long vaddr, unsigned long size); /* Architecture __weak replacement functions */ void __init mem_encrypt_init(void); +void __init mem_encrypt_free_decrypted_mem(void); bool sme_active(void); bool sev_active(void); +#define __bss_decrypted __attribute__((__section__(".bss..decrypted"))) + #else /* !CONFIG_AMD_MEM_ENCRYPT */ #define sme_me_mask 0ULL @@ -77,6 +80,8 @@ early_set_memory_decrypted(unsigned long vaddr, unsigned long size) { return 0; static inline int __init early_set_memory_encrypted(unsigned long vaddr, unsigned long size) { return 0; } +#define __bss_decrypted + #endif /* CONFIG_AMD_MEM_ENCRYPT */ /* @@ -88,6 +93,8 @@ early_set_memory_encrypted(unsigned long vaddr, unsigned long size) { return 0; #define __sme_pa(x) (__pa(x) | sme_me_mask) #define __sme_pa_nodebug(x) (__pa_nodebug(x) | sme_me_mask) +extern char __start_bss_decrypted[], __end_bss_decrypted[], __start_bss_decrypted_unused[]; + #endif /* __ASSEMBLY__ */ #endif /* __X86_MEM_ENCRYPT_H__ */ diff --git a/arch/x86/include/asm/pgtable-2level.h b/arch/x86/include/asm/pgtable-2level.h index 24c6cf5f16b7..60d0f9015317 100644 --- a/arch/x86/include/asm/pgtable-2level.h +++ b/arch/x86/include/asm/pgtable-2level.h @@ -19,9 +19,6 @@ static inline void native_set_pte(pte_t *ptep , pte_t pte) static inline void native_set_pmd(pmd_t *pmdp, pmd_t pmd) { -#ifdef CONFIG_PAGE_TABLE_ISOLATION - pmd.pud.p4d.pgd = pti_set_user_pgtbl(&pmdp->pud.p4d.pgd, pmd.pud.p4d.pgd); -#endif *pmdp = pmd; } @@ -61,9 +58,6 @@ static inline pte_t native_ptep_get_and_clear(pte_t *xp) #ifdef CONFIG_SMP static inline pmd_t native_pmdp_get_and_clear(pmd_t *xp) { -#ifdef CONFIG_PAGE_TABLE_ISOLATION - pti_set_user_pgtbl(&xp->pud.p4d.pgd, __pgd(0)); -#endif return __pmd(xchg((pmdval_t *)xp, 0)); } #else @@ -73,9 +67,6 @@ static inline pmd_t native_pmdp_get_and_clear(pmd_t *xp) #ifdef CONFIG_SMP static inline pud_t native_pudp_get_and_clear(pud_t *xp) { -#ifdef CONFIG_PAGE_TABLE_ISOLATION - pti_set_user_pgtbl(&xp->p4d.pgd, __pgd(0)); -#endif return __pud(xchg((pudval_t *)xp, 0)); } #else diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h index e4ffa565a69f..690c0307afed 100644 --- a/arch/x86/include/asm/pgtable.h +++ b/arch/x86/include/asm/pgtable.h @@ -1195,7 +1195,7 @@ static inline pmd_t pmdp_establish(struct vm_area_struct *vma, return xchg(pmdp, pmd); } else { pmd_t old = *pmdp; - *pmdp = pmd; + WRITE_ONCE(*pmdp, pmd); return old; } } diff --git a/arch/x86/include/asm/pgtable_64.h b/arch/x86/include/asm/pgtable_64.h index f773d5e6c8cc..9c85b54bf03c 100644 --- a/arch/x86/include/asm/pgtable_64.h +++ b/arch/x86/include/asm/pgtable_64.h @@ -14,6 +14,7 @@ #include <asm/processor.h> #include <linux/bitops.h> #include <linux/threads.h> +#include <asm/fixmap.h> extern p4d_t level4_kernel_pgt[512]; extern p4d_t level4_ident_pgt[512]; @@ -22,7 +23,7 @@ extern pud_t level3_ident_pgt[512]; extern pmd_t level2_kernel_pgt[512]; extern pmd_t level2_fixmap_pgt[512]; extern pmd_t level2_ident_pgt[512]; -extern pte_t level1_fixmap_pgt[512]; +extern pte_t level1_fixmap_pgt[512 * FIXMAP_PMD_NUM]; extern pgd_t init_top_pgt[]; #define swapper_pg_dir init_top_pgt @@ -55,15 +56,15 @@ struct mm_struct; void set_pte_vaddr_p4d(p4d_t *p4d_page, unsigned long vaddr, pte_t new_pte); void set_pte_vaddr_pud(pud_t *pud_page, unsigned long vaddr, pte_t new_pte); -static inline void native_pte_clear(struct mm_struct *mm, unsigned long addr, - pte_t *ptep) +static inline void native_set_pte(pte_t *ptep, pte_t pte) { - *ptep = native_make_pte(0); + WRITE_ONCE(*ptep, pte); } -static inline void native_set_pte(pte_t *ptep, pte_t pte) +static inline void native_pte_clear(struct mm_struct *mm, unsigned long addr, + pte_t *ptep) { - *ptep = pte; + native_set_pte(ptep, native_make_pte(0)); } static inline void native_set_pte_atomic(pte_t *ptep, pte_t pte) @@ -73,7 +74,7 @@ static inline void native_set_pte_atomic(pte_t *ptep, pte_t pte) static inline void native_set_pmd(pmd_t *pmdp, pmd_t pmd) { - *pmdp = pmd; + WRITE_ONCE(*pmdp, pmd); } static inline void native_pmd_clear(pmd_t *pmd) @@ -109,7 +110,7 @@ static inline pmd_t native_pmdp_get_and_clear(pmd_t *xp) static inline void native_set_pud(pud_t *pudp, pud_t pud) { - *pudp = pud; + WRITE_ONCE(*pudp, pud); } static inline void native_pud_clear(pud_t *pud) @@ -137,13 +138,13 @@ static inline void native_set_p4d(p4d_t *p4dp, p4d_t p4d) pgd_t pgd; if (pgtable_l5_enabled() || !IS_ENABLED(CONFIG_PAGE_TABLE_ISOLATION)) { - *p4dp = p4d; + WRITE_ONCE(*p4dp, p4d); return; } pgd = native_make_pgd(native_p4d_val(p4d)); pgd = pti_set_user_pgtbl((pgd_t *)p4dp, pgd); - *p4dp = native_make_p4d(native_pgd_val(pgd)); + WRITE_ONCE(*p4dp, native_make_p4d(native_pgd_val(pgd))); } static inline void native_p4d_clear(p4d_t *p4d) @@ -153,7 +154,7 @@ static inline void native_p4d_clear(p4d_t *p4d) static inline void native_set_pgd(pgd_t *pgdp, pgd_t pgd) { - *pgdp = pti_set_user_pgtbl(pgdp, pgd); + WRITE_ONCE(*pgdp, pti_set_user_pgtbl(pgdp, pgd)); } static inline void native_pgd_clear(pgd_t *pgd) diff --git a/arch/x86/include/uapi/asm/kvm.h b/arch/x86/include/uapi/asm/kvm.h index 86299efa804a..fd23d5778ea1 100644 --- a/arch/x86/include/uapi/asm/kvm.h +++ b/arch/x86/include/uapi/asm/kvm.h @@ -377,6 +377,7 @@ struct kvm_sync_regs { #define KVM_X86_QUIRK_LINT0_REENABLED (1 << 0) #define KVM_X86_QUIRK_CD_NW_CLEARED (1 << 1) +#define KVM_X86_QUIRK_LAPIC_MMIO_HOLE (1 << 2) #define KVM_STATE_NESTED_GUEST_MODE 0x00000001 #define KVM_STATE_NESTED_RUN_PENDING 0x00000002 diff --git a/arch/x86/kernel/apic/vector.c b/arch/x86/kernel/apic/vector.c index 9f148e3d45b4..7654febd5102 100644 --- a/arch/x86/kernel/apic/vector.c +++ b/arch/x86/kernel/apic/vector.c @@ -413,7 +413,7 @@ static int activate_managed(struct irq_data *irqd) if (WARN_ON_ONCE(cpumask_empty(vector_searchmask))) { /* Something in the core code broke! Survive gracefully */ pr_err("Managed startup for irq %u, but no CPU\n", irqd->irq); - return EINVAL; + return -EINVAL; } ret = assign_managed_vector(irqd, vector_searchmask); diff --git a/arch/x86/kernel/apm_32.c b/arch/x86/kernel/apm_32.c index ec00d1ff5098..f7151cd03cb0 100644 --- a/arch/x86/kernel/apm_32.c +++ b/arch/x86/kernel/apm_32.c @@ -1640,6 +1640,7 @@ static int do_open(struct inode *inode, struct file *filp) return 0; } +#ifdef CONFIG_PROC_FS static int proc_apm_show(struct seq_file *m, void *v) { unsigned short bx; @@ -1719,6 +1720,7 @@ static int proc_apm_show(struct seq_file *m, void *v) units); return 0; } +#endif static int apm(void *unused) { diff --git a/arch/x86/kernel/cpu/intel_rdt.h b/arch/x86/kernel/cpu/intel_rdt.h index 4e588f36228f..285eb3ec4200 100644 --- a/arch/x86/kernel/cpu/intel_rdt.h +++ b/arch/x86/kernel/cpu/intel_rdt.h @@ -382,6 +382,11 @@ static inline bool is_mbm_event(int e) e <= QOS_L3_MBM_LOCAL_EVENT_ID); } +struct rdt_parse_data { + struct rdtgroup *rdtgrp; + char *buf; +}; + /** * struct rdt_resource - attributes of an RDT resource * @rid: The index of the resource @@ -423,16 +428,19 @@ struct rdt_resource { struct rdt_cache cache; struct rdt_membw membw; const char *format_str; - int (*parse_ctrlval) (void *data, struct rdt_resource *r, - struct rdt_domain *d); + int (*parse_ctrlval)(struct rdt_parse_data *data, + struct rdt_resource *r, + struct rdt_domain *d); struct list_head evt_list; int num_rmid; unsigned int mon_scale; unsigned long fflags; }; -int parse_cbm(void *_data, struct rdt_resource *r, struct rdt_domain *d); -int parse_bw(void *_buf, struct rdt_resource *r, struct rdt_domain *d); +int parse_cbm(struct rdt_parse_data *data, struct rdt_resource *r, + struct rdt_domain *d); +int parse_bw(struct rdt_parse_data *data, struct rdt_resource *r, + struct rdt_domain *d); extern struct mutex rdtgroup_mutex; @@ -536,6 +544,7 @@ int rdtgroup_pseudo_lock_create(struct rdtgroup *rdtgrp); void rdtgroup_pseudo_lock_remove(struct rdtgroup *rdtgrp); struct rdt_domain *get_domain_from_cpu(int cpu, struct rdt_resource *r); int update_domains(struct rdt_resource *r, int closid); +int closids_supported(void); void closid_free(int closid); int alloc_rmid(void); void free_rmid(u32 rmid); diff --git a/arch/x86/kernel/cpu/intel_rdt_ctrlmondata.c b/arch/x86/kernel/cpu/intel_rdt_ctrlmondata.c index af358ca05160..0f53049719cd 100644 --- a/arch/x86/kernel/cpu/intel_rdt_ctrlmondata.c +++ b/arch/x86/kernel/cpu/intel_rdt_ctrlmondata.c @@ -64,19 +64,19 @@ static bool bw_validate(char *buf, unsigned long *data, struct rdt_resource *r) return true; } -int parse_bw(void *_buf, struct rdt_resource *r, struct rdt_domain *d) +int parse_bw(struct rdt_parse_data *data, struct rdt_resource *r, + struct rdt_domain *d) { - unsigned long data; - char *buf = _buf; + unsigned long bw_val; if (d->have_new_ctrl) { rdt_last_cmd_printf("duplicate domain %d\n", d->id); return -EINVAL; } - if (!bw_validate(buf, &data, r)) + if (!bw_validate(data->buf, &bw_val, r)) return -EINVAL; - d->new_ctrl = data; + d->new_ctrl = bw_val; d->have_new_ctrl = true; return 0; @@ -123,18 +123,13 @@ static bool cbm_validate(char *buf, u32 *data, struct rdt_resource *r) return true; } -struct rdt_cbm_parse_data { - struct rdtgroup *rdtgrp; - char *buf; -}; - /* * Read one cache bit mask (hex). Check that it is valid for the current * resource type. */ -int parse_cbm(void *_data, struct rdt_resource *r, struct rdt_domain *d) +int parse_cbm(struct rdt_parse_data *data, struct rdt_resource *r, + struct rdt_domain *d) { - struct rdt_cbm_parse_data *data = _data; struct rdtgroup *rdtgrp = data->rdtgrp; u32 cbm_val; @@ -195,11 +190,17 @@ int parse_cbm(void *_data, struct rdt_resource *r, struct rdt_domain *d) static int parse_line(char *line, struct rdt_resource *r, struct rdtgroup *rdtgrp) { - struct rdt_cbm_parse_data data; + struct rdt_parse_data data; char *dom = NULL, *id; struct rdt_domain *d; unsigned long dom_id; + if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP && + r->rid == RDT_RESOURCE_MBA) { + rdt_last_cmd_puts("Cannot pseudo-lock MBA resource\n"); + return -EINVAL; + } + next: if (!line || line[0] == '\0') return 0; diff --git a/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c b/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c index b799c00bef09..1b8e86a5d5e1 100644 --- a/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c +++ b/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c @@ -97,6 +97,12 @@ void rdt_last_cmd_printf(const char *fmt, ...) * limited as the number of resources grows. */ static int closid_free_map; +static int closid_free_map_len; + +int closids_supported(void) +{ + return closid_free_map_len; +} static void closid_init(void) { @@ -111,6 +117,7 @@ static void closid_init(void) /* CLOSID 0 is always reserved for the default group */ closid_free_map &= ~1; + closid_free_map_len = rdt_min_closid; } static int closid_alloc(void) @@ -802,7 +809,7 @@ static int rdt_bit_usage_show(struct kernfs_open_file *of, sw_shareable = 0; exclusive = 0; seq_printf(seq, "%d=", dom->id); - for (i = 0; i < r->num_closid; i++, ctrl++) { + for (i = 0; i < closids_supported(); i++, ctrl++) { if (!closid_allocated(i)) continue; mode = rdtgroup_mode_by_closid(i); @@ -989,7 +996,7 @@ bool rdtgroup_cbm_overlaps(struct rdt_resource *r, struct rdt_domain *d, /* Check for overlap with other resource groups */ ctrl = d->ctrl_val; - for (i = 0; i < r->num_closid; i++, ctrl++) { + for (i = 0; i < closids_supported(); i++, ctrl++) { ctrl_b = (unsigned long *)ctrl; mode = rdtgroup_mode_by_closid(i); if (closid_allocated(i) && i != closid && @@ -1024,16 +1031,27 @@ static bool rdtgroup_mode_test_exclusive(struct rdtgroup *rdtgrp) { int closid = rdtgrp->closid; struct rdt_resource *r; + bool has_cache = false; struct rdt_domain *d; for_each_alloc_enabled_rdt_resource(r) { + if (r->rid == RDT_RESOURCE_MBA) + continue; + has_cache = true; list_for_each_entry(d, &r->domains, list) { if (rdtgroup_cbm_overlaps(r, d, d->ctrl_val[closid], - rdtgrp->closid, false)) + rdtgrp->closid, false)) { + rdt_last_cmd_puts("schemata overlaps\n"); return false; + } } } + if (!has_cache) { + rdt_last_cmd_puts("cannot be exclusive without CAT/CDP\n"); + return false; + } + return true; } @@ -1085,7 +1103,6 @@ static ssize_t rdtgroup_mode_write(struct kernfs_open_file *of, rdtgrp->mode = RDT_MODE_SHAREABLE; } else if (!strcmp(buf, "exclusive")) { if (!rdtgroup_mode_test_exclusive(rdtgrp)) { - rdt_last_cmd_printf("schemata overlaps\n"); ret = -EINVAL; goto out; } @@ -1155,8 +1172,8 @@ static int rdtgroup_size_show(struct kernfs_open_file *of, struct rdt_resource *r; struct rdt_domain *d; unsigned int size; - bool sep = false; - u32 cbm; + bool sep; + u32 ctrl; rdtgrp = rdtgroup_kn_lock_live(of->kn); if (!rdtgrp) { @@ -1174,6 +1191,7 @@ static int rdtgroup_size_show(struct kernfs_open_file *of, } for_each_alloc_enabled_rdt_resource(r) { + sep = false; seq_printf(s, "%*s:", max_name_width, r->name); list_for_each_entry(d, &r->domains, list) { if (sep) @@ -1181,8 +1199,13 @@ static int rdtgroup_size_show(struct kernfs_open_file *of, if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP) { size = 0; } else { - cbm = d->ctrl_val[rdtgrp->closid]; - size = rdtgroup_cbm_to_size(r, d, cbm); + ctrl = (!is_mba_sc(r) ? + d->ctrl_val[rdtgrp->closid] : + d->mbps_val[rdtgrp->closid]); + if (r->rid == RDT_RESOURCE_MBA) + size = ctrl; + else + size = rdtgroup_cbm_to_size(r, d, ctrl); } seq_printf(s, "%d=%u", d->id, size); sep = true; @@ -2336,12 +2359,18 @@ static int rdtgroup_init_alloc(struct rdtgroup *rdtgrp) u32 *ctrl; for_each_alloc_enabled_rdt_resource(r) { + /* + * Only initialize default allocations for CBM cache + * resources + */ + if (r->rid == RDT_RESOURCE_MBA) + continue; list_for_each_entry(d, &r->domains, list) { d->have_new_ctrl = false; d->new_ctrl = r->cache.shareable_bits; used_b = r->cache.shareable_bits; ctrl = d->ctrl_val; - for (i = 0; i < r->num_closid; i++, ctrl++) { + for (i = 0; i < closids_supported(); i++, ctrl++) { if (closid_allocated(i) && i != closid) { mode = rdtgroup_mode_by_closid(i); if (mode == RDT_MODE_PSEUDO_LOCKSETUP) @@ -2373,6 +2402,12 @@ static int rdtgroup_init_alloc(struct rdtgroup *rdtgrp) } for_each_alloc_enabled_rdt_resource(r) { + /* + * Only initialize default allocations for CBM cache + * resources + */ + if (r->rid == RDT_RESOURCE_MBA) + continue; ret = update_domains(r, rdtgrp->closid); if (ret < 0) { rdt_last_cmd_puts("failed to initialize allocations\n"); diff --git a/arch/x86/kernel/cpu/microcode/amd.c b/arch/x86/kernel/cpu/microcode/amd.c index 0624957aa068..07b5fc00b188 100644 --- a/arch/x86/kernel/cpu/microcode/amd.c +++ b/arch/x86/kernel/cpu/microcode/amd.c @@ -504,6 +504,7 @@ static enum ucode_state apply_microcode_amd(int cpu) struct microcode_amd *mc_amd; struct ucode_cpu_info *uci; struct ucode_patch *p; + enum ucode_state ret; u32 rev, dummy; BUG_ON(raw_smp_processor_id() != cpu); @@ -521,9 +522,8 @@ static enum ucode_state apply_microcode_amd(int cpu) /* need to apply patch? */ if (rev >= mc_amd->hdr.patch_id) { - c->microcode = rev; - uci->cpu_sig.rev = rev; - return UCODE_OK; + ret = UCODE_OK; + goto out; } if (__apply_microcode_amd(mc_amd)) { @@ -531,13 +531,21 @@ static enum ucode_state apply_microcode_amd(int cpu) cpu, mc_amd->hdr.patch_id); return UCODE_ERROR; } - pr_info("CPU%d: new patch_level=0x%08x\n", cpu, - mc_amd->hdr.patch_id); - uci->cpu_sig.rev = mc_amd->hdr.patch_id; - c->microcode = mc_amd->hdr.patch_id; + rev = mc_amd->hdr.patch_id; + ret = UCODE_UPDATED; + + pr_info("CPU%d: new patch_level=0x%08x\n", cpu, rev); - return UCODE_UPDATED; +out: + uci->cpu_sig.rev = rev; + c->microcode = rev; + + /* Update boot_cpu_data's revision too, if we're on the BSP: */ + if (c->cpu_index == boot_cpu_data.cpu_index) + boot_cpu_data.microcode = rev; + + return ret; } static int install_equiv_cpu_table(const u8 *buf) diff --git a/arch/x86/kernel/cpu/microcode/intel.c b/arch/x86/kernel/cpu/microcode/intel.c index 97ccf4c3b45b..16936a24795c 100644 --- a/arch/x86/kernel/cpu/microcode/intel.c +++ b/arch/x86/kernel/cpu/microcode/intel.c @@ -795,6 +795,7 @@ static enum ucode_state apply_microcode_intel(int cpu) struct ucode_cpu_info *uci = ucode_cpu_info + cpu; struct cpuinfo_x86 *c = &cpu_data(cpu); struct microcode_intel *mc; + enum ucode_state ret; static int prev_rev; u32 rev; @@ -817,9 +818,8 @@ static enum ucode_state apply_microcode_intel(int cpu) */ rev = intel_get_microcode_revision(); if (rev >= mc->hdr.rev) { - uci->cpu_sig.rev = rev; - c->microcode = rev; - return UCODE_OK; + ret = UCODE_OK; + goto out; } /* @@ -848,10 +848,17 @@ static enum ucode_state apply_microcode_intel(int cpu) prev_rev = rev; } + ret = UCODE_UPDATED; + +out: uci->cpu_sig.rev = rev; - c->microcode = rev; + c->microcode = rev; + + /* Update boot_cpu_data's revision too, if we're on the BSP: */ + if (c->cpu_index == boot_cpu_data.cpu_index) + boot_cpu_data.microcode = rev; - return UCODE_UPDATED; + return ret; } static enum ucode_state generic_load_microcode(int cpu, void *data, size_t size, diff --git a/arch/x86/kernel/dumpstack.c b/arch/x86/kernel/dumpstack.c index f56895106ccf..2b5886401e5f 100644 --- a/arch/x86/kernel/dumpstack.c +++ b/arch/x86/kernel/dumpstack.c @@ -146,7 +146,7 @@ static void show_regs_if_on_stack(struct stack_info *info, struct pt_regs *regs, * they can be printed in the right context. */ if (!partial && on_stack(info, regs, sizeof(*regs))) { - __show_regs(regs, 0); + __show_regs(regs, SHOW_REGS_SHORT); } else if (partial && on_stack(info, (void *)regs + IRET_FRAME_OFFSET, IRET_FRAME_SIZE)) { @@ -344,7 +344,7 @@ void oops_end(unsigned long flags, struct pt_regs *regs, int signr) oops_exit(); /* Executive summary in case the oops scrolled away */ - __show_regs(&exec_summary_regs, true); + __show_regs(&exec_summary_regs, SHOW_REGS_ALL); if (!signr) return; @@ -407,14 +407,9 @@ void die(const char *str, struct pt_regs *regs, long err) void show_regs(struct pt_regs *regs) { - bool all = true; - show_regs_print_info(KERN_DEFAULT); - if (IS_ENABLED(CONFIG_X86_32)) - all = !user_mode(regs); - - __show_regs(regs, all); + __show_regs(regs, user_mode(regs) ? SHOW_REGS_USER : SHOW_REGS_ALL); /* * When in-kernel, we also print out the stack at the time of the fault.. diff --git a/arch/x86/kernel/eisa.c b/arch/x86/kernel/eisa.c index f260e452e4f8..e8c8c5d78dbd 100644 --- a/arch/x86/kernel/eisa.c +++ b/arch/x86/kernel/eisa.c @@ -7,11 +7,17 @@ #include <linux/eisa.h> #include <linux/io.h> +#include <xen/xen.h> + static __init int eisa_bus_probe(void) { - void __iomem *p = ioremap(0x0FFFD9, 4); + void __iomem *p; + + if (xen_pv_domain() && !xen_initial_domain()) + return 0; - if (readl(p) == 'E' + ('I'<<8) + ('S'<<16) + ('A'<<24)) + p = ioremap(0x0FFFD9, 4); + if (p && readl(p) == 'E' + ('I' << 8) + ('S' << 16) + ('A' << 24)) EISA_bus = 1; iounmap(p); return 0; diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c index 8047379e575a..ddee1f0870c4 100644 --- a/arch/x86/kernel/head64.c +++ b/arch/x86/kernel/head64.c @@ -35,6 +35,7 @@ #include <asm/bootparam_utils.h> #include <asm/microcode.h> #include <asm/kasan.h> +#include <asm/fixmap.h> /* * Manage page tables very early on. @@ -112,6 +113,7 @@ static bool __head check_la57_support(unsigned long physaddr) unsigned long __head __startup_64(unsigned long physaddr, struct boot_params *bp) { + unsigned long vaddr, vaddr_end; unsigned long load_delta, *p; unsigned long pgtable_flags; pgdval_t *pgd; @@ -165,7 +167,8 @@ unsigned long __head __startup_64(unsigned long physaddr, pud[511] += load_delta; pmd = fixup_pointer(level2_fixmap_pgt, physaddr); - pmd[506] += load_delta; + for (i = FIXMAP_PMD_TOP; i > FIXMAP_PMD_TOP - FIXMAP_PMD_NUM; i--) + pmd[i] += load_delta; /* * Set up the identity mapping for the switchover. These @@ -235,6 +238,21 @@ unsigned long __head __startup_64(unsigned long physaddr, sme_encrypt_kernel(bp); /* + * Clear the memory encryption mask from the .bss..decrypted section. + * The bss section will be memset to zero later in the initialization so + * there is no need to zero it after changing the memory encryption + * attribute. + */ + if (mem_encrypt_active()) { + vaddr = (unsigned long)__start_bss_decrypted; + vaddr_end = (unsigned long)__end_bss_decrypted; + for (; vaddr < vaddr_end; vaddr += PMD_SIZE) { + i = pmd_index(vaddr); + pmd[i] -= sme_get_me_mask(); + } + } + + /* * Return the SME encryption mask (if SME is active) to be used as a * modifier for the initial pgdir entry programmed into CR3. */ diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S index 15ebc2fc166e..a3618cf04cf6 100644 --- a/arch/x86/kernel/head_64.S +++ b/arch/x86/kernel/head_64.S @@ -24,6 +24,7 @@ #include "../entry/calling.h" #include <asm/export.h> #include <asm/nospec-branch.h> +#include <asm/fixmap.h> #ifdef CONFIG_PARAVIRT #include <asm/asm-offsets.h> @@ -445,13 +446,20 @@ NEXT_PAGE(level2_kernel_pgt) KERNEL_IMAGE_SIZE/PMD_SIZE) NEXT_PAGE(level2_fixmap_pgt) - .fill 506,8,0 - .quad level1_fixmap_pgt - __START_KERNEL_map + _PAGE_TABLE_NOENC - /* 8MB reserved for vsyscalls + a 2MB hole = 4 + 1 entries */ - .fill 5,8,0 + .fill (512 - 4 - FIXMAP_PMD_NUM),8,0 + pgtno = 0 + .rept (FIXMAP_PMD_NUM) + .quad level1_fixmap_pgt + (pgtno << PAGE_SHIFT) - __START_KERNEL_map \ + + _PAGE_TABLE_NOENC; + pgtno = pgtno + 1 + .endr + /* 6 MB reserved space + a 2MB hole */ + .fill 4,8,0 NEXT_PAGE(level1_fixmap_pgt) + .rept (FIXMAP_PMD_NUM) .fill 512,8,0 + .endr #undef PMDS diff --git a/arch/x86/kernel/kvmclock.c b/arch/x86/kernel/kvmclock.c index 1e6764648af3..013fe3d21dbb 100644 --- a/arch/x86/kernel/kvmclock.c +++ b/arch/x86/kernel/kvmclock.c @@ -28,6 +28,7 @@ #include <linux/sched/clock.h> #include <linux/mm.h> #include <linux/slab.h> +#include <linux/set_memory.h> #include <asm/hypervisor.h> #include <asm/mem_encrypt.h> @@ -61,9 +62,10 @@ early_param("no-kvmclock-vsyscall", parse_no_kvmclock_vsyscall); (PAGE_SIZE / sizeof(struct pvclock_vsyscall_time_info)) static struct pvclock_vsyscall_time_info - hv_clock_boot[HVC_BOOT_ARRAY_SIZE] __aligned(PAGE_SIZE); -static struct pvclock_wall_clock wall_clock; + hv_clock_boot[HVC_BOOT_ARRAY_SIZE] __bss_decrypted __aligned(PAGE_SIZE); +static struct pvclock_wall_clock wall_clock __bss_decrypted; static DEFINE_PER_CPU(struct pvclock_vsyscall_time_info *, hv_clock_per_cpu); +static struct pvclock_vsyscall_time_info *hvclock_mem; static inline struct pvclock_vcpu_time_info *this_cpu_pvti(void) { @@ -236,6 +238,45 @@ static void kvm_shutdown(void) native_machine_shutdown(); } +static void __init kvmclock_init_mem(void) +{ + unsigned long ncpus; + unsigned int order; + struct page *p; + int r; + + if (HVC_BOOT_ARRAY_SIZE >= num_possible_cpus()) + return; + + ncpus = num_possible_cpus() - HVC_BOOT_ARRAY_SIZE; + order = get_order(ncpus * sizeof(*hvclock_mem)); + + p = alloc_pages(GFP_KERNEL, order); + if (!p) { + pr_warn("%s: failed to alloc %d pages", __func__, (1U << order)); + return; + } + + hvclock_mem = page_address(p); + + /* + * hvclock is shared between the guest and the hypervisor, must + * be mapped decrypted. + */ + if (sev_active()) { + r = set_memory_decrypted((unsigned long) hvclock_mem, + 1UL << order); + if (r) { + __free_pages(p, order); + hvclock_mem = NULL; + pr_warn("kvmclock: set_memory_decrypted() failed. Disabling\n"); + return; + } + } + + memset(hvclock_mem, 0, PAGE_SIZE << order); +} + static int __init kvm_setup_vsyscall_timeinfo(void) { #ifdef CONFIG_X86_64 @@ -250,6 +291,9 @@ static int __init kvm_setup_vsyscall_timeinfo(void) kvm_clock.archdata.vclock_mode = VCLOCK_PVCLOCK; #endif + + kvmclock_init_mem(); + return 0; } early_initcall(kvm_setup_vsyscall_timeinfo); @@ -269,8 +313,10 @@ static int kvmclock_setup_percpu(unsigned int cpu) /* Use the static page for the first CPUs, allocate otherwise */ if (cpu < HVC_BOOT_ARRAY_SIZE) p = &hv_clock_boot[cpu]; + else if (hvclock_mem) + p = hvclock_mem + cpu - HVC_BOOT_ARRAY_SIZE; else - p = kzalloc(sizeof(*p), GFP_KERNEL); + return -ENOMEM; per_cpu(hv_clock_per_cpu, cpu) = p; return p ? 0 : -ENOMEM; diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c index afdb303285f8..8dc69d82567e 100644 --- a/arch/x86/kernel/paravirt.c +++ b/arch/x86/kernel/paravirt.c @@ -91,7 +91,7 @@ unsigned paravirt_patch_call(void *insnbuf, if (len < 5) { #ifdef CONFIG_RETPOLINE - WARN_ONCE("Failing to patch indirect CALL in %ps\n", (void *)addr); + WARN_ONCE(1, "Failing to patch indirect CALL in %ps\n", (void *)addr); #endif return len; /* call too long for patch site */ } @@ -111,7 +111,7 @@ unsigned paravirt_patch_jmp(void *insnbuf, const void *target, if (len < 5) { #ifdef CONFIG_RETPOLINE - WARN_ONCE("Failing to patch indirect JMP in %ps\n", (void *)addr); + WARN_ONCE(1, "Failing to patch indirect JMP in %ps\n", (void *)addr); #endif return len; /* call too long for patch site */ } diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c index 2924fd447e61..5046a3c9dec2 100644 --- a/arch/x86/kernel/process_32.c +++ b/arch/x86/kernel/process_32.c @@ -59,7 +59,7 @@ #include <asm/intel_rdt_sched.h> #include <asm/proto.h> -void __show_regs(struct pt_regs *regs, int all) +void __show_regs(struct pt_regs *regs, enum show_regs_mode mode) { unsigned long cr0 = 0L, cr2 = 0L, cr3 = 0L, cr4 = 0L; unsigned long d0, d1, d2, d3, d6, d7; @@ -85,7 +85,7 @@ void __show_regs(struct pt_regs *regs, int all) printk(KERN_DEFAULT "DS: %04x ES: %04x FS: %04x GS: %04x SS: %04x EFLAGS: %08lx\n", (u16)regs->ds, (u16)regs->es, (u16)regs->fs, gs, ss, regs->flags); - if (!all) + if (mode != SHOW_REGS_ALL) return; cr0 = read_cr0(); diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c index a451bc374b9b..ea5ea850348d 100644 --- a/arch/x86/kernel/process_64.c +++ b/arch/x86/kernel/process_64.c @@ -62,7 +62,7 @@ __visible DEFINE_PER_CPU(unsigned long, rsp_scratch); /* Prints also some state that isn't saved in the pt_regs */ -void __show_regs(struct pt_regs *regs, int all) +void __show_regs(struct pt_regs *regs, enum show_regs_mode mode) { unsigned long cr0 = 0L, cr2 = 0L, cr3 = 0L, cr4 = 0L, fs, gs, shadowgs; unsigned long d0, d1, d2, d3, d6, d7; @@ -87,9 +87,17 @@ void __show_regs(struct pt_regs *regs, int all) printk(KERN_DEFAULT "R13: %016lx R14: %016lx R15: %016lx\n", regs->r13, regs->r14, regs->r15); - if (!all) + if (mode == SHOW_REGS_SHORT) return; + if (mode == SHOW_REGS_USER) { + rdmsrl(MSR_FS_BASE, fs); + rdmsrl(MSR_KERNEL_GS_BASE, shadowgs); + printk(KERN_DEFAULT "FS: %016lx GS: %016lx\n", + fs, shadowgs); + return; + } + asm("movl %%ds,%0" : "=r" (ds)); asm("movl %%cs,%0" : "=r" (cs)); asm("movl %%es,%0" : "=r" (es)); diff --git a/arch/x86/kernel/topology.c b/arch/x86/kernel/topology.c index 12cbe2b88c0f..738bf42b0218 100644 --- a/arch/x86/kernel/topology.c +++ b/arch/x86/kernel/topology.c @@ -111,8 +111,10 @@ int arch_register_cpu(int num) /* * Currently CPU0 is only hotpluggable on Intel platforms. Other * vendors can add hotplug support later. + * Xen PV guests don't support CPU0 hotplug at all. */ - if (c->x86_vendor != X86_VENDOR_INTEL) + if (c->x86_vendor != X86_VENDOR_INTEL || + boot_cpu_has(X86_FEATURE_XENPV)) cpu0_hotpluggable = 0; /* diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c index 1463468ba9a0..6490f618e096 100644 --- a/arch/x86/kernel/tsc.c +++ b/arch/x86/kernel/tsc.c @@ -1415,7 +1415,7 @@ static bool __init determine_cpu_tsc_frequencies(bool early) static unsigned long __init get_loops_per_jiffy(void) { - unsigned long lpj = tsc_khz * KHZ; + u64 lpj = (u64)tsc_khz * KHZ; do_div(lpj, HZ); return lpj; diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S index 8bde0a419f86..5dd3317d761f 100644 --- a/arch/x86/kernel/vmlinux.lds.S +++ b/arch/x86/kernel/vmlinux.lds.S @@ -65,6 +65,23 @@ jiffies_64 = jiffies; #define ALIGN_ENTRY_TEXT_BEGIN . = ALIGN(PMD_SIZE); #define ALIGN_ENTRY_TEXT_END . = ALIGN(PMD_SIZE); +/* + * This section contains data which will be mapped as decrypted. Memory + * encryption operates on a page basis. Make this section PMD-aligned + * to avoid splitting the pages while mapping the section early. + * + * Note: We use a separate section so that only this section gets + * decrypted to avoid exposing more than we wish. + */ +#define BSS_DECRYPTED \ + . = ALIGN(PMD_SIZE); \ + __start_bss_decrypted = .; \ + *(.bss..decrypted); \ + . = ALIGN(PAGE_SIZE); \ + __start_bss_decrypted_unused = .; \ + . = ALIGN(PMD_SIZE); \ + __end_bss_decrypted = .; \ + #else #define X86_ALIGN_RODATA_BEGIN @@ -74,6 +91,7 @@ jiffies_64 = jiffies; #define ALIGN_ENTRY_TEXT_BEGIN #define ALIGN_ENTRY_TEXT_END +#define BSS_DECRYPTED #endif @@ -355,6 +373,7 @@ SECTIONS __bss_start = .; *(.bss..page_aligned) *(.bss) + BSS_DECRYPTED . = ALIGN(PAGE_SIZE); __bss_stop = .; } diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index 0cefba28c864..fbb0e6df121b 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -548,7 +548,7 @@ int kvm_apic_set_irq(struct kvm_vcpu *vcpu, struct kvm_lapic_irq *irq, } int kvm_pv_send_ipi(struct kvm *kvm, unsigned long ipi_bitmap_low, - unsigned long ipi_bitmap_high, int min, + unsigned long ipi_bitmap_high, u32 min, unsigned long icr, int op_64_bit) { int i; @@ -571,18 +571,31 @@ int kvm_pv_send_ipi(struct kvm *kvm, unsigned long ipi_bitmap_low, rcu_read_lock(); map = rcu_dereference(kvm->arch.apic_map); + if (min > map->max_apic_id) + goto out; /* Bits above cluster_size are masked in the caller. */ - for_each_set_bit(i, &ipi_bitmap_low, BITS_PER_LONG) { - vcpu = map->phys_map[min + i]->vcpu; - count += kvm_apic_set_irq(vcpu, &irq, NULL); + for_each_set_bit(i, &ipi_bitmap_low, + min((u32)BITS_PER_LONG, (map->max_apic_id - min + 1))) { + if (map->phys_map[min + i]) { + vcpu = map->phys_map[min + i]->vcpu; + count += kvm_apic_set_irq(vcpu, &irq, NULL); + } } min += cluster_size; - for_each_set_bit(i, &ipi_bitmap_high, BITS_PER_LONG) { - vcpu = map->phys_map[min + i]->vcpu; - count += kvm_apic_set_irq(vcpu, &irq, NULL); + + if (min > map->max_apic_id) + goto out; + + for_each_set_bit(i, &ipi_bitmap_high, + min((u32)BITS_PER_LONG, (map->max_apic_id - min + 1))) { + if (map->phys_map[min + i]) { + vcpu = map->phys_map[min + i]->vcpu; + count += kvm_apic_set_irq(vcpu, &irq, NULL); + } } +out: rcu_read_unlock(); return count; } @@ -1331,9 +1344,8 @@ EXPORT_SYMBOL_GPL(kvm_lapic_reg_read); static int apic_mmio_in_range(struct kvm_lapic *apic, gpa_t addr) { - return kvm_apic_hw_enabled(apic) && - addr >= apic->base_address && - addr < apic->base_address + LAPIC_MMIO_LENGTH; + return addr >= apic->base_address && + addr < apic->base_address + LAPIC_MMIO_LENGTH; } static int apic_mmio_read(struct kvm_vcpu *vcpu, struct kvm_io_device *this, @@ -1345,6 +1357,15 @@ static int apic_mmio_read(struct kvm_vcpu *vcpu, struct kvm_io_device *this, if (!apic_mmio_in_range(apic, address)) return -EOPNOTSUPP; + if (!kvm_apic_hw_enabled(apic) || apic_x2apic_mode(apic)) { + if (!kvm_check_has_quirk(vcpu->kvm, + KVM_X86_QUIRK_LAPIC_MMIO_HOLE)) + return -EOPNOTSUPP; + + memset(data, 0xff, len); + return 0; + } + kvm_lapic_reg_read(apic, offset, len, data); return 0; @@ -1904,6 +1925,14 @@ static int apic_mmio_write(struct kvm_vcpu *vcpu, struct kvm_io_device *this, if (!apic_mmio_in_range(apic, address)) return -EOPNOTSUPP; + if (!kvm_apic_hw_enabled(apic) || apic_x2apic_mode(apic)) { + if (!kvm_check_has_quirk(vcpu->kvm, + KVM_X86_QUIRK_LAPIC_MMIO_HOLE)) + return -EOPNOTSUPP; + + return 0; + } + /* * APIC register must be aligned on 128-bits boundary. * 32/64/128 bits registers must be accessed thru 32 bits. diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index a282321329b5..d7e9bce6ff61 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -899,7 +899,7 @@ static void walk_shadow_page_lockless_end(struct kvm_vcpu *vcpu) { /* * Make sure the write to vcpu->mode is not reordered in front of - * reads to sptes. If it does, kvm_commit_zap_page() can see us + * reads to sptes. If it does, kvm_mmu_commit_zap_page() can see us * OUTSIDE_GUEST_MODE and proceed to free the shadow page table. */ smp_store_release(&vcpu->mode, OUTSIDE_GUEST_MODE); @@ -1853,11 +1853,6 @@ static int kvm_handle_hva(struct kvm *kvm, unsigned long hva, return kvm_handle_hva_range(kvm, hva, hva + 1, data, handler); } -int kvm_unmap_hva(struct kvm *kvm, unsigned long hva) -{ - return kvm_handle_hva(kvm, hva, 0, kvm_unmap_rmapp); -} - int kvm_unmap_hva_range(struct kvm *kvm, unsigned long start, unsigned long end) { return kvm_handle_hva_range(kvm, start, end, 0, kvm_unmap_rmapp); @@ -5217,7 +5212,7 @@ static int make_mmu_pages_available(struct kvm_vcpu *vcpu) int kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gva_t cr2, u64 error_code, void *insn, int insn_len) { - int r, emulation_type = EMULTYPE_RETRY; + int r, emulation_type = 0; enum emulation_result er; bool direct = vcpu->arch.mmu.direct_map; @@ -5230,10 +5225,8 @@ int kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gva_t cr2, u64 error_code, r = RET_PF_INVALID; if (unlikely(error_code & PFERR_RSVD_MASK)) { r = handle_mmio_page_fault(vcpu, cr2, direct); - if (r == RET_PF_EMULATE) { - emulation_type = 0; + if (r == RET_PF_EMULATE) goto emulate; - } } if (r == RET_PF_INVALID) { @@ -5260,8 +5253,19 @@ int kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gva_t cr2, u64 error_code, return 1; } - if (mmio_info_in_cache(vcpu, cr2, direct)) - emulation_type = 0; + /* + * vcpu->arch.mmu.page_fault returned RET_PF_EMULATE, but we can still + * optimistically try to just unprotect the page and let the processor + * re-execute the instruction that caused the page fault. Do not allow + * retrying MMIO emulation, as it's not only pointless but could also + * cause us to enter an infinite loop because the processor will keep + * faulting on the non-existent MMIO address. Retrying an instruction + * from a nested guest is also pointless and dangerous as we are only + * explicitly shadowing L1's page tables, i.e. unprotecting something + * for L1 isn't going to magically fix whatever issue cause L2 to fail. + */ + if (!mmio_info_in_cache(vcpu, cr2, direct) && !is_guest_mode(vcpu)) + emulation_type = EMULTYPE_ALLOW_RETRY; emulate: /* * On AMD platforms, under certain conditions insn_len may be zero on #NPF. @@ -5413,7 +5417,12 @@ void kvm_mmu_setup(struct kvm_vcpu *vcpu) { MMU_WARN_ON(VALID_PAGE(vcpu->arch.mmu.root_hpa)); - kvm_init_mmu(vcpu, true); + /* + * kvm_mmu_setup() is called only on vCPU initialization. + * Therefore, no need to reset mmu roots as they are not yet + * initialized. + */ + kvm_init_mmu(vcpu, false); } static void kvm_mmu_invalidate_zap_pages_in_memslot(struct kvm *kvm, diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c index 6276140044d0..d96092b35936 100644 --- a/arch/x86/kvm/svm.c +++ b/arch/x86/kvm/svm.c @@ -776,7 +776,7 @@ static void skip_emulated_instruction(struct kvm_vcpu *vcpu) } if (!svm->next_rip) { - if (emulate_instruction(vcpu, EMULTYPE_SKIP) != + if (kvm_emulate_instruction(vcpu, EMULTYPE_SKIP) != EMULATE_DONE) printk(KERN_DEBUG "%s: NOP\n", __func__); return; @@ -1226,8 +1226,7 @@ static __init int sev_hardware_setup(void) min_sev_asid = cpuid_edx(0x8000001F); /* Initialize SEV ASID bitmap */ - sev_asid_bitmap = kcalloc(BITS_TO_LONGS(max_sev_asid), - sizeof(unsigned long), GFP_KERNEL); + sev_asid_bitmap = bitmap_zalloc(max_sev_asid, GFP_KERNEL); if (!sev_asid_bitmap) return 1; @@ -1405,7 +1404,7 @@ static __exit void svm_hardware_unsetup(void) int cpu; if (svm_sev_enabled()) - kfree(sev_asid_bitmap); + bitmap_free(sev_asid_bitmap); for_each_possible_cpu(cpu) svm_cpu_uninit(cpu); @@ -2715,7 +2714,7 @@ static int gp_interception(struct vcpu_svm *svm) WARN_ON_ONCE(!enable_vmware_backdoor); - er = emulate_instruction(vcpu, + er = kvm_emulate_instruction(vcpu, EMULTYPE_VMWARE | EMULTYPE_NO_UD_ON_FAIL); if (er == EMULATE_USER_EXIT) return 0; @@ -2819,7 +2818,7 @@ static int io_interception(struct vcpu_svm *svm) string = (io_info & SVM_IOIO_STR_MASK) != 0; in = (io_info & SVM_IOIO_TYPE_MASK) != 0; if (string) - return emulate_instruction(vcpu, 0) == EMULATE_DONE; + return kvm_emulate_instruction(vcpu, 0) == EMULATE_DONE; port = io_info >> 16; size = (io_info & SVM_IOIO_SIZE_MASK) >> SVM_IOIO_SIZE_SHIFT; @@ -3861,7 +3860,7 @@ static int iret_interception(struct vcpu_svm *svm) static int invlpg_interception(struct vcpu_svm *svm) { if (!static_cpu_has(X86_FEATURE_DECODEASSISTS)) - return emulate_instruction(&svm->vcpu, 0) == EMULATE_DONE; + return kvm_emulate_instruction(&svm->vcpu, 0) == EMULATE_DONE; kvm_mmu_invlpg(&svm->vcpu, svm->vmcb->control.exit_info_1); return kvm_skip_emulated_instruction(&svm->vcpu); @@ -3869,13 +3868,13 @@ static int invlpg_interception(struct vcpu_svm *svm) static int emulate_on_interception(struct vcpu_svm *svm) { - return emulate_instruction(&svm->vcpu, 0) == EMULATE_DONE; + return kvm_emulate_instruction(&svm->vcpu, 0) == EMULATE_DONE; } static int rsm_interception(struct vcpu_svm *svm) { - return x86_emulate_instruction(&svm->vcpu, 0, 0, - rsm_ins_bytes, 2) == EMULATE_DONE; + return kvm_emulate_instruction_from_buffer(&svm->vcpu, + rsm_ins_bytes, 2) == EMULATE_DONE; } static int rdpmc_interception(struct vcpu_svm *svm) @@ -4700,7 +4699,7 @@ static int avic_unaccelerated_access_interception(struct vcpu_svm *svm) ret = avic_unaccel_trap_write(svm); } else { /* Handling Fault */ - ret = (emulate_instruction(&svm->vcpu, 0) == EMULATE_DONE); + ret = (kvm_emulate_instruction(&svm->vcpu, 0) == EMULATE_DONE); } return ret; @@ -6747,7 +6746,7 @@ e_free: static int sev_dbg_crypt(struct kvm *kvm, struct kvm_sev_cmd *argp, bool dec) { unsigned long vaddr, vaddr_end, next_vaddr; - unsigned long dst_vaddr, dst_vaddr_end; + unsigned long dst_vaddr; struct page **src_p, **dst_p; struct kvm_sev_dbg debug; unsigned long n; @@ -6763,7 +6762,6 @@ static int sev_dbg_crypt(struct kvm *kvm, struct kvm_sev_cmd *argp, bool dec) size = debug.len; vaddr_end = vaddr + size; dst_vaddr = debug.dst_uaddr; - dst_vaddr_end = dst_vaddr + size; for (; vaddr < vaddr_end; vaddr = next_vaddr) { int len, s_off, d_off; @@ -7150,6 +7148,8 @@ static struct kvm_x86_ops svm_x86_ops __ro_after_init = { .check_intercept = svm_check_intercept, .handle_external_intr = svm_handle_external_intr, + .request_immediate_exit = __kvm_request_immediate_exit, + .sched_in = svm_sched_in, .pmu_ops = &amd_pmu_ops, diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index 1d26f3c4985b..06412ba46aa3 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -397,6 +397,7 @@ struct loaded_vmcs { int cpu; bool launched; bool nmi_known_unmasked; + bool hv_timer_armed; /* Support for vnmi-less CPUs */ int soft_vnmi_blocked; ktime_t entry_time; @@ -1019,6 +1020,8 @@ struct vcpu_vmx { int ple_window; bool ple_window_dirty; + bool req_immediate_exit; + /* Support for PML */ #define PML_ENTITY_NUM 512 struct page *pml_pg; @@ -2864,6 +2867,8 @@ static void vmx_prepare_switch_to_guest(struct kvm_vcpu *vcpu) u16 fs_sel, gs_sel; int i; + vmx->req_immediate_exit = false; + if (vmx->loaded_cpu_state) return; @@ -5393,9 +5398,10 @@ static int vmx_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4) * To use VMXON (and later other VMX instructions), a guest * must first be able to turn on cr4.VMXE (see handle_vmon()). * So basically the check on whether to allow nested VMX - * is here. + * is here. We operate under the default treatment of SMM, + * so VMX cannot be enabled under SMM. */ - if (!nested_vmx_allowed(vcpu)) + if (!nested_vmx_allowed(vcpu) || is_smm(vcpu)) return 1; } @@ -6183,6 +6189,27 @@ static void vmx_complete_nested_posted_interrupt(struct kvm_vcpu *vcpu) nested_mark_vmcs12_pages_dirty(vcpu); } +static bool vmx_guest_apic_has_interrupt(struct kvm_vcpu *vcpu) +{ + struct vcpu_vmx *vmx = to_vmx(vcpu); + void *vapic_page; + u32 vppr; + int rvi; + + if (WARN_ON_ONCE(!is_guest_mode(vcpu)) || + !nested_cpu_has_vid(get_vmcs12(vcpu)) || + WARN_ON_ONCE(!vmx->nested.virtual_apic_page)) + return false; + + rvi = vmcs_read16(GUEST_INTR_STATUS) & 0xff; + + vapic_page = kmap(vmx->nested.virtual_apic_page); + vppr = *((u32 *)(vapic_page + APIC_PROCPRI)); + kunmap(vmx->nested.virtual_apic_page); + + return ((rvi & 0xf0) > (vppr & 0xf0)); +} + static inline bool kvm_vcpu_trigger_posted_interrupt(struct kvm_vcpu *vcpu, bool nested) { @@ -6983,7 +7010,7 @@ static int handle_rmode_exception(struct kvm_vcpu *vcpu, * Cause the #SS fault with 0 error code in VM86 mode. */ if (((vec == GP_VECTOR) || (vec == SS_VECTOR)) && err_code == 0) { - if (emulate_instruction(vcpu, 0) == EMULATE_DONE) { + if (kvm_emulate_instruction(vcpu, 0) == EMULATE_DONE) { if (vcpu->arch.halt_request) { vcpu->arch.halt_request = 0; return kvm_vcpu_halt(vcpu); @@ -7054,7 +7081,7 @@ static int handle_exception(struct kvm_vcpu *vcpu) if (!vmx->rmode.vm86_active && is_gp_fault(intr_info)) { WARN_ON_ONCE(!enable_vmware_backdoor); - er = emulate_instruction(vcpu, + er = kvm_emulate_instruction(vcpu, EMULTYPE_VMWARE | EMULTYPE_NO_UD_ON_FAIL); if (er == EMULATE_USER_EXIT) return 0; @@ -7157,7 +7184,7 @@ static int handle_io(struct kvm_vcpu *vcpu) ++vcpu->stat.io_exits; if (string) - return emulate_instruction(vcpu, 0) == EMULATE_DONE; + return kvm_emulate_instruction(vcpu, 0) == EMULATE_DONE; port = exit_qualification >> 16; size = (exit_qualification & 7) + 1; @@ -7231,7 +7258,7 @@ static int handle_set_cr4(struct kvm_vcpu *vcpu, unsigned long val) static int handle_desc(struct kvm_vcpu *vcpu) { WARN_ON(!(vcpu->arch.cr4 & X86_CR4_UMIP)); - return emulate_instruction(vcpu, 0) == EMULATE_DONE; + return kvm_emulate_instruction(vcpu, 0) == EMULATE_DONE; } static int handle_cr(struct kvm_vcpu *vcpu) @@ -7480,7 +7507,7 @@ static int handle_vmcall(struct kvm_vcpu *vcpu) static int handle_invd(struct kvm_vcpu *vcpu) { - return emulate_instruction(vcpu, 0) == EMULATE_DONE; + return kvm_emulate_instruction(vcpu, 0) == EMULATE_DONE; } static int handle_invlpg(struct kvm_vcpu *vcpu) @@ -7547,7 +7574,7 @@ static int handle_apic_access(struct kvm_vcpu *vcpu) return kvm_skip_emulated_instruction(vcpu); } } - return emulate_instruction(vcpu, 0) == EMULATE_DONE; + return kvm_emulate_instruction(vcpu, 0) == EMULATE_DONE; } static int handle_apic_eoi_induced(struct kvm_vcpu *vcpu) @@ -7704,8 +7731,8 @@ static int handle_ept_misconfig(struct kvm_vcpu *vcpu) if (!static_cpu_has(X86_FEATURE_HYPERVISOR)) return kvm_skip_emulated_instruction(vcpu); else - return x86_emulate_instruction(vcpu, gpa, EMULTYPE_SKIP, - NULL, 0) == EMULATE_DONE; + return kvm_emulate_instruction(vcpu, EMULTYPE_SKIP) == + EMULATE_DONE; } return kvm_mmu_page_fault(vcpu, gpa, PFERR_RSVD_MASK, NULL, 0); @@ -7748,7 +7775,7 @@ static int handle_invalid_guest_state(struct kvm_vcpu *vcpu) if (kvm_test_request(KVM_REQ_EVENT, vcpu)) return 1; - err = emulate_instruction(vcpu, 0); + err = kvm_emulate_instruction(vcpu, 0); if (err == EMULATE_USER_EXIT) { ++vcpu->stat.mmio_exits; @@ -7966,6 +7993,9 @@ static __init int hardware_setup(void) kvm_x86_ops->enable_log_dirty_pt_masked = NULL; } + if (!cpu_has_vmx_preemption_timer()) + kvm_x86_ops->request_immediate_exit = __kvm_request_immediate_exit; + if (cpu_has_vmx_preemption_timer() && enable_preemption_timer) { u64 vmx_msr; @@ -9208,7 +9238,8 @@ static int handle_pml_full(struct kvm_vcpu *vcpu) static int handle_preemption_timer(struct kvm_vcpu *vcpu) { - kvm_lapic_expired_hv_timer(vcpu); + if (!to_vmx(vcpu)->req_immediate_exit) + kvm_lapic_expired_hv_timer(vcpu); return 1; } @@ -10595,24 +10626,43 @@ static void atomic_switch_perf_msrs(struct vcpu_vmx *vmx) msrs[i].host, false); } -static void vmx_arm_hv_timer(struct kvm_vcpu *vcpu) +static void vmx_arm_hv_timer(struct vcpu_vmx *vmx, u32 val) +{ + vmcs_write32(VMX_PREEMPTION_TIMER_VALUE, val); + if (!vmx->loaded_vmcs->hv_timer_armed) + vmcs_set_bits(PIN_BASED_VM_EXEC_CONTROL, + PIN_BASED_VMX_PREEMPTION_TIMER); + vmx->loaded_vmcs->hv_timer_armed = true; +} + +static void vmx_update_hv_timer(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); u64 tscl; u32 delta_tsc; - if (vmx->hv_deadline_tsc == -1) + if (vmx->req_immediate_exit) { + vmx_arm_hv_timer(vmx, 0); return; + } - tscl = rdtsc(); - if (vmx->hv_deadline_tsc > tscl) - /* sure to be 32 bit only because checked on set_hv_timer */ - delta_tsc = (u32)((vmx->hv_deadline_tsc - tscl) >> - cpu_preemption_timer_multi); - else - delta_tsc = 0; + if (vmx->hv_deadline_tsc != -1) { + tscl = rdtsc(); + if (vmx->hv_deadline_tsc > tscl) + /* set_hv_timer ensures the delta fits in 32-bits */ + delta_tsc = (u32)((vmx->hv_deadline_tsc - tscl) >> + cpu_preemption_timer_multi); + else + delta_tsc = 0; + + vmx_arm_hv_timer(vmx, delta_tsc); + return; + } - vmcs_write32(VMX_PREEMPTION_TIMER_VALUE, delta_tsc); + if (vmx->loaded_vmcs->hv_timer_armed) + vmcs_clear_bits(PIN_BASED_VM_EXEC_CONTROL, + PIN_BASED_VMX_PREEMPTION_TIMER); + vmx->loaded_vmcs->hv_timer_armed = false; } static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu) @@ -10672,7 +10722,7 @@ static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu) atomic_switch_perf_msrs(vmx); - vmx_arm_hv_timer(vcpu); + vmx_update_hv_timer(vcpu); /* * If this vCPU has touched SPEC_CTRL, restore the guest's value if @@ -11427,16 +11477,18 @@ static void vmx_start_preemption_timer(struct kvm_vcpu *vcpu) u64 preemption_timeout = get_vmcs12(vcpu)->vmx_preemption_timer_value; struct vcpu_vmx *vmx = to_vmx(vcpu); - if (vcpu->arch.virtual_tsc_khz == 0) - return; - - /* Make sure short timeouts reliably trigger an immediate vmexit. - * hrtimer_start does not guarantee this. */ - if (preemption_timeout <= 1) { + /* + * A timer value of zero is architecturally guaranteed to cause + * a VMExit prior to executing any instructions in the guest. + */ + if (preemption_timeout == 0) { vmx_preemption_timer_fn(&vmx->nested.preemption_timer); return; } + if (vcpu->arch.virtual_tsc_khz == 0) + return; + preemption_timeout <<= VMX_MISC_EMULATED_PREEMPTION_TIMER_RATE; preemption_timeout *= 1000000; do_div(preemption_timeout, vcpu->arch.virtual_tsc_khz); @@ -11646,11 +11698,15 @@ static int nested_vmx_check_apicv_controls(struct kvm_vcpu *vcpu, * bits 15:8 should be zero in posted_intr_nv, * the descriptor address has been already checked * in nested_get_vmcs12_pages. + * + * bits 5:0 of posted_intr_desc_addr should be zero. */ if (nested_cpu_has_posted_intr(vmcs12) && (!nested_cpu_has_vid(vmcs12) || !nested_exit_intr_ack_set(vcpu) || - vmcs12->posted_intr_nv & 0xff00)) + (vmcs12->posted_intr_nv & 0xff00) || + (vmcs12->posted_intr_desc_addr & 0x3f) || + (!page_address_valid(vcpu, vmcs12->posted_intr_desc_addr)))) return -EINVAL; /* tpr shadow is needed by all apicv features. */ @@ -12076,11 +12132,10 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12, exec_control = vmcs12->pin_based_vm_exec_control; - /* Preemption timer setting is only taken from vmcs01. */ - exec_control &= ~PIN_BASED_VMX_PREEMPTION_TIMER; + /* Preemption timer setting is computed directly in vmx_vcpu_run. */ exec_control |= vmcs_config.pin_based_exec_ctrl; - if (vmx->hv_deadline_tsc == -1) - exec_control &= ~PIN_BASED_VMX_PREEMPTION_TIMER; + exec_control &= ~PIN_BASED_VMX_PREEMPTION_TIMER; + vmx->loaded_vmcs->hv_timer_armed = false; /* Posted interrupts setting is only taken from vmcs12. */ if (nested_cpu_has_posted_intr(vmcs12)) { @@ -12318,6 +12373,9 @@ static int check_vmentry_prereqs(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12) vmcs12->guest_activity_state != GUEST_ACTIVITY_HLT) return VMXERR_ENTRY_INVALID_CONTROL_FIELD; + if (nested_cpu_has_vpid(vmcs12) && !vmcs12->virtual_processor_id) + return VMXERR_ENTRY_INVALID_CONTROL_FIELD; + if (nested_vmx_check_io_bitmap_controls(vcpu, vmcs12)) return VMXERR_ENTRY_INVALID_CONTROL_FIELD; @@ -12537,8 +12595,11 @@ static int enter_vmx_non_root_mode(struct kvm_vcpu *vcpu, u32 *exit_qual) struct vmcs12 *vmcs12 = get_vmcs12(vcpu); bool from_vmentry = !!exit_qual; u32 dummy_exit_qual; + u32 vmcs01_cpu_exec_ctrl; int r = 0; + vmcs01_cpu_exec_ctrl = vmcs_read32(CPU_BASED_VM_EXEC_CONTROL); + enter_guest_mode(vcpu); if (!(vmcs12->vm_entry_controls & VM_ENTRY_LOAD_DEBUG_CONTROLS)) @@ -12575,6 +12636,25 @@ static int enter_vmx_non_root_mode(struct kvm_vcpu *vcpu, u32 *exit_qual) } /* + * If L1 had a pending IRQ/NMI until it executed + * VMLAUNCH/VMRESUME which wasn't delivered because it was + * disallowed (e.g. interrupts disabled), L0 needs to + * evaluate if this pending event should cause an exit from L2 + * to L1 or delivered directly to L2 (e.g. In case L1 don't + * intercept EXTERNAL_INTERRUPT). + * + * Usually this would be handled by L0 requesting a + * IRQ/NMI window by setting VMCS accordingly. However, + * this setting was done on VMCS01 and now VMCS02 is active + * instead. Thus, we force L0 to perform pending event + * evaluation by requesting a KVM_REQ_EVENT. + */ + if (vmcs01_cpu_exec_ctrl & + (CPU_BASED_VIRTUAL_INTR_PENDING | CPU_BASED_VIRTUAL_NMI_PENDING)) { + kvm_make_request(KVM_REQ_EVENT, vcpu); + } + + /* * Note no nested_vmx_succeed or nested_vmx_fail here. At this point * we are no longer running L1, and VMLAUNCH/VMRESUME has not yet * returned as far as L1 is concerned. It will only return (and set @@ -12841,6 +12921,11 @@ static int vmx_check_nested_events(struct kvm_vcpu *vcpu, bool external_intr) return 0; } +static void vmx_request_immediate_exit(struct kvm_vcpu *vcpu) +{ + to_vmx(vcpu)->req_immediate_exit = true; +} + static u32 vmx_get_preemption_timer_value(struct kvm_vcpu *vcpu) { ktime_t remaining = @@ -13231,12 +13316,7 @@ static void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 exit_reason, vmcs_write32(VM_EXIT_MSR_LOAD_COUNT, vmx->msr_autoload.host.nr); vmcs_write32(VM_ENTRY_MSR_LOAD_COUNT, vmx->msr_autoload.guest.nr); vmcs_write64(TSC_OFFSET, vcpu->arch.tsc_offset); - if (vmx->hv_deadline_tsc == -1) - vmcs_clear_bits(PIN_BASED_VM_EXEC_CONTROL, - PIN_BASED_VMX_PREEMPTION_TIMER); - else - vmcs_set_bits(PIN_BASED_VM_EXEC_CONTROL, - PIN_BASED_VMX_PREEMPTION_TIMER); + if (kvm_has_tsc_control) decache_tsc_multiplier(vmx); @@ -13440,18 +13520,12 @@ static int vmx_set_hv_timer(struct kvm_vcpu *vcpu, u64 guest_deadline_tsc) return -ERANGE; vmx->hv_deadline_tsc = tscl + delta_tsc; - vmcs_set_bits(PIN_BASED_VM_EXEC_CONTROL, - PIN_BASED_VMX_PREEMPTION_TIMER); - return delta_tsc == 0; } static void vmx_cancel_hv_timer(struct kvm_vcpu *vcpu) { - struct vcpu_vmx *vmx = to_vmx(vcpu); - vmx->hv_deadline_tsc = -1; - vmcs_clear_bits(PIN_BASED_VM_EXEC_CONTROL, - PIN_BASED_VMX_PREEMPTION_TIMER); + to_vmx(vcpu)->hv_deadline_tsc = -1; } #endif @@ -13932,6 +14006,14 @@ static int vmx_set_nested_state(struct kvm_vcpu *vcpu, ~(KVM_STATE_NESTED_SMM_GUEST_MODE | KVM_STATE_NESTED_SMM_VMXON)) return -EINVAL; + /* + * SMM temporarily disables VMX, so we cannot be in guest mode, + * nor can VMLAUNCH/VMRESUME be pending. Outside SMM, SMM flags + * must be zero. + */ + if (is_smm(vcpu) ? kvm_state->flags : kvm_state->vmx.smm.flags) + return -EINVAL; + if ((kvm_state->vmx.smm.flags & KVM_STATE_NESTED_SMM_GUEST_MODE) && !(kvm_state->vmx.smm.flags & KVM_STATE_NESTED_SMM_VMXON)) return -EINVAL; @@ -13988,9 +14070,6 @@ static int vmx_set_nested_state(struct kvm_vcpu *vcpu, check_vmentry_postreqs(vcpu, vmcs12, &exit_qual)) return -EINVAL; - if (kvm_state->flags & KVM_STATE_NESTED_RUN_PENDING) - vmx->nested.nested_run_pending = 1; - vmx->nested.dirty_vmcs12 = true; ret = enter_vmx_non_root_mode(vcpu, NULL); if (ret) @@ -14078,6 +14157,7 @@ static struct kvm_x86_ops vmx_x86_ops __ro_after_init = { .apicv_post_state_restore = vmx_apicv_post_state_restore, .hwapic_irr_update = vmx_hwapic_irr_update, .hwapic_isr_update = vmx_hwapic_isr_update, + .guest_apic_has_interrupt = vmx_guest_apic_has_interrupt, .sync_pir_to_irr = vmx_sync_pir_to_irr, .deliver_posted_interrupt = vmx_deliver_posted_interrupt, @@ -14111,6 +14191,7 @@ static struct kvm_x86_ops vmx_x86_ops __ro_after_init = { .umip_emulated = vmx_umip_emulated, .check_nested_events = vmx_check_nested_events, + .request_immediate_exit = vmx_request_immediate_exit, .sched_in = vmx_sched_in, diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 506bd2b4b8bb..edbf00ec56b3 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -628,7 +628,7 @@ bool pdptrs_changed(struct kvm_vcpu *vcpu) gfn_t gfn; int r; - if (is_long_mode(vcpu) || !is_pae(vcpu)) + if (is_long_mode(vcpu) || !is_pae(vcpu) || !is_paging(vcpu)) return false; if (!test_bit(VCPU_EXREG_PDPTR, @@ -2537,7 +2537,6 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) break; case MSR_PLATFORM_INFO: if (!msr_info->host_initiated || - data & ~MSR_PLATFORM_INFO_CPUID_FAULT || (!(data & MSR_PLATFORM_INFO_CPUID_FAULT) && cpuid_fault_enabled(vcpu))) return 1; @@ -2780,6 +2779,9 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) msr_info->data = vcpu->arch.osvw.status; break; case MSR_PLATFORM_INFO: + if (!msr_info->host_initiated && + !vcpu->kvm->arch.guest_can_read_msr_platform_info) + return 1; msr_info->data = vcpu->arch.msr_platform_info; break; case MSR_MISC_FEATURES_ENABLES: @@ -2927,6 +2929,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) case KVM_CAP_SPLIT_IRQCHIP: case KVM_CAP_IMMEDIATE_EXIT: case KVM_CAP_GET_MSR_FEATURES: + case KVM_CAP_MSR_PLATFORM_INFO: r = 1; break; case KVM_CAP_SYNC_REGS: @@ -4007,19 +4010,23 @@ long kvm_arch_vcpu_ioctl(struct file *filp, break; BUILD_BUG_ON(sizeof(user_data_size) != sizeof(user_kvm_nested_state->size)); + r = -EFAULT; if (get_user(user_data_size, &user_kvm_nested_state->size)) - return -EFAULT; + break; r = kvm_x86_ops->get_nested_state(vcpu, user_kvm_nested_state, user_data_size); if (r < 0) - return r; + break; if (r > user_data_size) { if (put_user(r, &user_kvm_nested_state->size)) - return -EFAULT; - return -E2BIG; + r = -EFAULT; + else + r = -E2BIG; + break; } + r = 0; break; } @@ -4031,19 +4038,21 @@ long kvm_arch_vcpu_ioctl(struct file *filp, if (!kvm_x86_ops->set_nested_state) break; + r = -EFAULT; if (copy_from_user(&kvm_state, user_kvm_nested_state, sizeof(kvm_state))) - return -EFAULT; + break; + r = -EINVAL; if (kvm_state.size < sizeof(kvm_state)) - return -EINVAL; + break; if (kvm_state.flags & ~(KVM_STATE_NESTED_RUN_PENDING | KVM_STATE_NESTED_GUEST_MODE)) - return -EINVAL; + break; /* nested_run_pending implies guest_mode. */ if (kvm_state.flags == KVM_STATE_NESTED_RUN_PENDING) - return -EINVAL; + break; r = kvm_x86_ops->set_nested_state(vcpu, user_kvm_nested_state, &kvm_state); break; @@ -4350,6 +4359,10 @@ split_irqchip_unlock: kvm->arch.pause_in_guest = true; r = 0; break; + case KVM_CAP_MSR_PLATFORM_INFO: + kvm->arch.guest_can_read_msr_platform_info = cap->args[0]; + r = 0; + break; default: r = -EINVAL; break; @@ -4987,7 +5000,7 @@ int handle_ud(struct kvm_vcpu *vcpu) emul_type = 0; } - er = emulate_instruction(vcpu, emul_type); + er = kvm_emulate_instruction(vcpu, emul_type); if (er == EMULATE_USER_EXIT) return 0; if (er != EMULATE_DONE) @@ -5870,7 +5883,10 @@ static bool reexecute_instruction(struct kvm_vcpu *vcpu, gva_t cr2, gpa_t gpa = cr2; kvm_pfn_t pfn; - if (emulation_type & EMULTYPE_NO_REEXECUTE) + if (!(emulation_type & EMULTYPE_ALLOW_RETRY)) + return false; + + if (WARN_ON_ONCE(is_guest_mode(vcpu))) return false; if (!vcpu->arch.mmu.direct_map) { @@ -5958,7 +5974,10 @@ static bool retry_instruction(struct x86_emulate_ctxt *ctxt, */ vcpu->arch.last_retry_eip = vcpu->arch.last_retry_addr = 0; - if (!(emulation_type & EMULTYPE_RETRY)) + if (!(emulation_type & EMULTYPE_ALLOW_RETRY)) + return false; + + if (WARN_ON_ONCE(is_guest_mode(vcpu))) return false; if (x86_page_table_writing_insn(ctxt)) @@ -6276,7 +6295,19 @@ restart: return r; } -EXPORT_SYMBOL_GPL(x86_emulate_instruction); + +int kvm_emulate_instruction(struct kvm_vcpu *vcpu, int emulation_type) +{ + return x86_emulate_instruction(vcpu, 0, emulation_type, NULL, 0); +} +EXPORT_SYMBOL_GPL(kvm_emulate_instruction); + +int kvm_emulate_instruction_from_buffer(struct kvm_vcpu *vcpu, + void *insn, int insn_len) +{ + return x86_emulate_instruction(vcpu, 0, 0, insn, insn_len); +} +EXPORT_SYMBOL_GPL(kvm_emulate_instruction_from_buffer); static int kvm_fast_pio_out(struct kvm_vcpu *vcpu, int size, unsigned short port) @@ -7343,6 +7374,12 @@ void kvm_vcpu_reload_apic_access_page(struct kvm_vcpu *vcpu) } EXPORT_SYMBOL_GPL(kvm_vcpu_reload_apic_access_page); +void __kvm_request_immediate_exit(struct kvm_vcpu *vcpu) +{ + smp_send_reschedule(vcpu->cpu); +} +EXPORT_SYMBOL_GPL(__kvm_request_immediate_exit); + /* * Returns 1 to let vcpu_run() continue the guest execution loop without * exiting to the userspace. Otherwise, the value will be returned to the @@ -7547,7 +7584,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) if (req_immediate_exit) { kvm_make_request(KVM_REQ_EVENT, vcpu); - smp_send_reschedule(vcpu->cpu); + kvm_x86_ops->request_immediate_exit(vcpu); } trace_kvm_entry(vcpu->vcpu_id); @@ -7734,7 +7771,7 @@ static inline int complete_emulated_io(struct kvm_vcpu *vcpu) { int r; vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu); - r = emulate_instruction(vcpu, EMULTYPE_NO_DECODE); + r = kvm_emulate_instruction(vcpu, EMULTYPE_NO_DECODE); srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx); if (r != EMULATE_DONE) return 0; @@ -7811,6 +7848,29 @@ static int complete_emulated_mmio(struct kvm_vcpu *vcpu) return 0; } +/* Swap (qemu) user FPU context for the guest FPU context. */ +static void kvm_load_guest_fpu(struct kvm_vcpu *vcpu) +{ + preempt_disable(); + copy_fpregs_to_fpstate(&vcpu->arch.user_fpu); + /* PKRU is separately restored in kvm_x86_ops->run. */ + __copy_kernel_to_fpregs(&vcpu->arch.guest_fpu.state, + ~XFEATURE_MASK_PKRU); + preempt_enable(); + trace_kvm_fpu(1); +} + +/* When vcpu_run ends, restore user space FPU context. */ +static void kvm_put_guest_fpu(struct kvm_vcpu *vcpu) +{ + preempt_disable(); + copy_fpregs_to_fpstate(&vcpu->arch.guest_fpu); + copy_kernel_to_fpregs(&vcpu->arch.user_fpu.state); + preempt_enable(); + ++vcpu->stat.fpu_reload; + trace_kvm_fpu(0); +} + int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) { int r; @@ -8159,7 +8219,7 @@ static int __set_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs) kvm_update_cpuid(vcpu); idx = srcu_read_lock(&vcpu->kvm->srcu); - if (!is_long_mode(vcpu) && is_pae(vcpu)) { + if (!is_long_mode(vcpu) && is_pae(vcpu) && is_paging(vcpu)) { load_pdptrs(vcpu, vcpu->arch.walk_mmu, kvm_read_cr3(vcpu)); mmu_reset_needed = 1; } @@ -8388,29 +8448,6 @@ static void fx_init(struct kvm_vcpu *vcpu) vcpu->arch.cr0 |= X86_CR0_ET; } -/* Swap (qemu) user FPU context for the guest FPU context. */ -void kvm_load_guest_fpu(struct kvm_vcpu *vcpu) -{ - preempt_disable(); - copy_fpregs_to_fpstate(&vcpu->arch.user_fpu); - /* PKRU is separately restored in kvm_x86_ops->run. */ - __copy_kernel_to_fpregs(&vcpu->arch.guest_fpu.state, - ~XFEATURE_MASK_PKRU); - preempt_enable(); - trace_kvm_fpu(1); -} - -/* When vcpu_run ends, restore user space FPU context. */ -void kvm_put_guest_fpu(struct kvm_vcpu *vcpu) -{ - preempt_disable(); - copy_fpregs_to_fpstate(&vcpu->arch.guest_fpu); - copy_kernel_to_fpregs(&vcpu->arch.user_fpu.state); - preempt_enable(); - ++vcpu->stat.fpu_reload; - trace_kvm_fpu(0); -} - void kvm_arch_vcpu_free(struct kvm_vcpu *vcpu) { void *wbinvd_dirty_mask = vcpu->arch.wbinvd_dirty_mask; @@ -8834,6 +8871,8 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type) kvm->arch.kvmclock_offset = -ktime_get_boot_ns(); pvclock_update_vm_gtod_copy(kvm); + kvm->arch.guest_can_read_msr_platform_info = true; + INIT_DELAYED_WORK(&kvm->arch.kvmclock_update_work, kvmclock_update_fn); INIT_DELAYED_WORK(&kvm->arch.kvmclock_sync_work, kvmclock_sync_fn); @@ -9182,6 +9221,13 @@ void kvm_arch_flush_shadow_memslot(struct kvm *kvm, kvm_page_track_flush_slot(kvm, slot); } +static inline bool kvm_guest_apic_has_interrupt(struct kvm_vcpu *vcpu) +{ + return (is_guest_mode(vcpu) && + kvm_x86_ops->guest_apic_has_interrupt && + kvm_x86_ops->guest_apic_has_interrupt(vcpu)); +} + static inline bool kvm_vcpu_has_events(struct kvm_vcpu *vcpu) { if (!list_empty_careful(&vcpu->async_pf.done)) @@ -9206,7 +9252,8 @@ static inline bool kvm_vcpu_has_events(struct kvm_vcpu *vcpu) return true; if (kvm_arch_interrupt_allowed(vcpu) && - kvm_cpu_has_interrupt(vcpu)) + (kvm_cpu_has_interrupt(vcpu) || + kvm_guest_apic_has_interrupt(vcpu))) return true; if (kvm_hv_has_stimer_pending(vcpu)) diff --git a/arch/x86/kvm/x86.h b/arch/x86/kvm/x86.h index 257f27620bc2..67b9568613f3 100644 --- a/arch/x86/kvm/x86.h +++ b/arch/x86/kvm/x86.h @@ -274,6 +274,8 @@ int kvm_mtrr_get_msr(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata); bool kvm_mtrr_check_gfn_range_consistency(struct kvm_vcpu *vcpu, gfn_t gfn, int page_num); bool kvm_vector_hashing_enabled(void); +int x86_emulate_instruction(struct kvm_vcpu *vcpu, unsigned long cr2, + int emulation_type, void *insn, int insn_len); #define KVM_SUPPORTED_XCR0 (XFEATURE_MASK_FP | XFEATURE_MASK_SSE \ | XFEATURE_MASK_YMM | XFEATURE_MASK_BNDREGS \ diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c index 7a8fc26c1115..faca978ebf9d 100644 --- a/arch/x86/mm/init.c +++ b/arch/x86/mm/init.c @@ -815,10 +815,14 @@ void free_kernel_image_pages(void *begin, void *end) set_memory_np_noalias(begin_ul, len_pages); } +void __weak mem_encrypt_free_decrypted_mem(void) { } + void __ref free_initmem(void) { e820__reallocate_tables(); + mem_encrypt_free_decrypted_mem(); + free_kernel_image_pages(&__init_begin, &__init_end); } diff --git a/arch/x86/mm/mem_encrypt.c b/arch/x86/mm/mem_encrypt.c index b2de398d1fd3..006f373f54ab 100644 --- a/arch/x86/mm/mem_encrypt.c +++ b/arch/x86/mm/mem_encrypt.c @@ -348,6 +348,30 @@ bool sev_active(void) EXPORT_SYMBOL(sev_active); /* Architecture __weak replacement functions */ +void __init mem_encrypt_free_decrypted_mem(void) +{ + unsigned long vaddr, vaddr_end, npages; + int r; + + vaddr = (unsigned long)__start_bss_decrypted_unused; + vaddr_end = (unsigned long)__end_bss_decrypted; + npages = (vaddr_end - vaddr) >> PAGE_SHIFT; + + /* + * The unused memory range was mapped decrypted, change the encryption + * attribute from decrypted to encrypted before freeing it. + */ + if (mem_encrypt_active()) { + r = set_memory_encrypted(vaddr, npages); + if (r) { + pr_warn("failed to free unused decrypted pages\n"); + return; + } + } + + free_init_pages("unused decrypted", vaddr, vaddr_end); +} + void __init mem_encrypt_init(void) { if (!sme_me_mask) diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c index e848a4811785..089e78c4effd 100644 --- a/arch/x86/mm/pgtable.c +++ b/arch/x86/mm/pgtable.c @@ -269,7 +269,7 @@ static void mop_up_one_pmd(struct mm_struct *mm, pgd_t *pgdp) if (pgd_val(pgd) != 0) { pmd_t *pmd = (pmd_t *)pgd_page_vaddr(pgd); - *pgdp = native_make_pgd(0); + pgd_clear(pgdp); paravirt_release_pmd(pgd_val(pgd) >> PAGE_SHIFT); pmd_free(mm, pmd); @@ -494,7 +494,7 @@ int ptep_set_access_flags(struct vm_area_struct *vma, int changed = !pte_same(*ptep, entry); if (changed && dirty) - *ptep = entry; + set_pte(ptep, entry); return changed; } @@ -509,7 +509,7 @@ int pmdp_set_access_flags(struct vm_area_struct *vma, VM_BUG_ON(address & ~HPAGE_PMD_MASK); if (changed && dirty) { - *pmdp = entry; + set_pmd(pmdp, entry); /* * We had a write-protection fault here and changed the pmd * to to more permissive. No need to flush the TLB for that, @@ -529,7 +529,7 @@ int pudp_set_access_flags(struct vm_area_struct *vma, unsigned long address, VM_BUG_ON(address & ~HPAGE_PUD_MASK); if (changed && dirty) { - *pudp = entry; + set_pud(pudp, entry); /* * We had a write-protection fault here and changed the pud * to to more permissive. No need to flush the TLB for that, @@ -637,6 +637,15 @@ void __native_set_fixmap(enum fixed_addresses idx, pte_t pte) { unsigned long address = __fix_to_virt(idx); +#ifdef CONFIG_X86_64 + /* + * Ensure that the static initial page tables are covering the + * fixmap completely. + */ + BUILD_BUG_ON(__end_of_permanent_fixed_addresses > + (FIXMAP_PMD_NUM * PTRS_PER_PTE)); +#endif + if (idx >= __end_of_fixed_addresses) { BUG(); return; diff --git a/arch/x86/platform/efi/efi_32.c b/arch/x86/platform/efi/efi_32.c index 05ca14222463..9959657127f4 100644 --- a/arch/x86/platform/efi/efi_32.c +++ b/arch/x86/platform/efi/efi_32.c @@ -85,10 +85,9 @@ pgd_t * __init efi_call_phys_prolog(void) void __init efi_call_phys_epilog(pgd_t *save_pgd) { + load_fixmap_gdt(0); load_cr3(save_pgd); __flush_tlb_all(); - - load_fixmap_gdt(0); } void __init efi_runtime_update_mappings(void) diff --git a/arch/x86/xen/mmu_pv.c b/arch/x86/xen/mmu_pv.c index 2fe5c9b1816b..dd461c0167ef 100644 --- a/arch/x86/xen/mmu_pv.c +++ b/arch/x86/xen/mmu_pv.c @@ -1907,7 +1907,7 @@ void __init xen_setup_kernel_pagetable(pgd_t *pgd, unsigned long max_pfn) /* L3_k[511] -> level2_fixmap_pgt */ convert_pfn_mfn(level3_kernel_pgt); - /* L3_k[511][506] -> level1_fixmap_pgt */ + /* L3_k[511][508-FIXMAP_PMD_NUM ... 507] -> level1_fixmap_pgt */ convert_pfn_mfn(level2_fixmap_pgt); /* We get [511][511] and have Xen's version of level2_kernel_pgt */ @@ -1952,7 +1952,11 @@ void __init xen_setup_kernel_pagetable(pgd_t *pgd, unsigned long max_pfn) set_page_prot(level2_ident_pgt, PAGE_KERNEL_RO); set_page_prot(level2_kernel_pgt, PAGE_KERNEL_RO); set_page_prot(level2_fixmap_pgt, PAGE_KERNEL_RO); - set_page_prot(level1_fixmap_pgt, PAGE_KERNEL_RO); + + for (i = 0; i < FIXMAP_PMD_NUM; i++) { + set_page_prot(level1_fixmap_pgt + i * PTRS_PER_PTE, + PAGE_KERNEL_RO); + } /* Pin down new L4 */ pin_pagetable_pfn(MMUEXT_PIN_L4_TABLE, diff --git a/arch/x86/xen/pmu.c b/arch/x86/xen/pmu.c index 7d00d4ad44d4..95997e6c0696 100644 --- a/arch/x86/xen/pmu.c +++ b/arch/x86/xen/pmu.c @@ -478,7 +478,7 @@ static void xen_convert_regs(const struct xen_pmu_regs *xen_regs, irqreturn_t xen_pmu_irq_handler(int irq, void *dev_id) { int err, ret = IRQ_NONE; - struct pt_regs regs; + struct pt_regs regs = {0}; const struct xen_pmu_data *xenpmu_data = get_xenpmu_data(); uint8_t xenpmu_flags = get_xenpmu_flags(); diff --git a/arch/xtensa/Kconfig b/arch/xtensa/Kconfig index 04d038f3b6fa..b9ad83a0ee5d 100644 --- a/arch/xtensa/Kconfig +++ b/arch/xtensa/Kconfig @@ -4,6 +4,7 @@ config ZONE_DMA config XTENSA def_bool y + select ARCH_HAS_SG_CHAIN select ARCH_HAS_SYNC_DMA_FOR_CPU select ARCH_HAS_SYNC_DMA_FOR_DEVICE select ARCH_NO_COHERENT_DMA_MMAP if !MMU diff --git a/arch/xtensa/Makefile b/arch/xtensa/Makefile index 295c120ed099..d67e30faff9c 100644 --- a/arch/xtensa/Makefile +++ b/arch/xtensa/Makefile @@ -64,11 +64,7 @@ endif vardirs := $(patsubst %,arch/xtensa/variants/%/,$(variant-y)) plfdirs := $(patsubst %,arch/xtensa/platforms/%/,$(platform-y)) -ifeq ($(KBUILD_SRC),) -KBUILD_CPPFLAGS += $(patsubst %,-I%include,$(vardirs) $(plfdirs)) -else KBUILD_CPPFLAGS += $(patsubst %,-I$(srctree)/%include,$(vardirs) $(plfdirs)) -endif KBUILD_DEFCONFIG := iss_defconfig diff --git a/arch/xtensa/platforms/iss/setup.c b/arch/xtensa/platforms/iss/setup.c index f4bbb28026f8..58709e89a8ed 100644 --- a/arch/xtensa/platforms/iss/setup.c +++ b/arch/xtensa/platforms/iss/setup.c @@ -78,23 +78,28 @@ static struct notifier_block iss_panic_block = { void __init platform_setup(char **p_cmdline) { + static void *argv[COMMAND_LINE_SIZE / sizeof(void *)] __initdata; + static char cmdline[COMMAND_LINE_SIZE] __initdata; int argc = simc_argc(); int argv_size = simc_argv_size(); if (argc > 1) { - void **argv = alloc_bootmem(argv_size); - char *cmdline = alloc_bootmem(argv_size); - int i; + if (argv_size > sizeof(argv)) { + pr_err("%s: command line too long: argv_size = %d\n", + __func__, argv_size); + } else { + int i; - cmdline[0] = 0; - simc_argv((void *)argv); + cmdline[0] = 0; + simc_argv((void *)argv); - for (i = 1; i < argc; ++i) { - if (i > 1) - strcat(cmdline, " "); - strcat(cmdline, argv[i]); + for (i = 1; i < argc; ++i) { + if (i > 1) + strcat(cmdline, " "); + strcat(cmdline, argv[i]); + } + *p_cmdline = cmdline; } - *p_cmdline = cmdline; } atomic_notifier_chain_register(&panic_notifier_list, &iss_panic_block); diff --git a/block/bfq-cgroup.c b/block/bfq-cgroup.c index 58c6efa9f9a9..9fe5952d117d 100644 --- a/block/bfq-cgroup.c +++ b/block/bfq-cgroup.c @@ -275,9 +275,9 @@ static void bfqg_and_blkg_get(struct bfq_group *bfqg) void bfqg_and_blkg_put(struct bfq_group *bfqg) { - bfqg_put(bfqg); - blkg_put(bfqg_to_blkg(bfqg)); + + bfqg_put(bfqg); } /* @stats = 0 */ diff --git a/block/bio.c b/block/bio.c index b12966e415d3..0093bed81c0e 100644 --- a/block/bio.c +++ b/block/bio.c @@ -1684,7 +1684,7 @@ void generic_end_io_acct(struct request_queue *q, int req_op, const int sgrp = op_stat_group(req_op); int cpu = part_stat_lock(); - part_stat_add(cpu, part, ticks[sgrp], duration); + part_stat_add(cpu, part, nsecs[sgrp], jiffies_to_nsecs(duration)); part_round_stats(q, cpu, part); part_dec_in_flight(q, part, op_is_write(req_op)); @@ -2015,7 +2015,8 @@ int bio_associate_blkg(struct bio *bio, struct blkcg_gq *blkg) { if (unlikely(bio->bi_blkg)) return -EBUSY; - blkg_get(blkg); + if (!blkg_try_get(blkg)) + return -ENODEV; bio->bi_blkg = blkg; return 0; } diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c index 694595b29b8f..c630e02836a8 100644 --- a/block/blk-cgroup.c +++ b/block/blk-cgroup.c @@ -310,28 +310,11 @@ struct blkcg_gq *blkg_lookup_create(struct blkcg *blkcg, } } -static void blkg_pd_offline(struct blkcg_gq *blkg) -{ - int i; - - lockdep_assert_held(blkg->q->queue_lock); - lockdep_assert_held(&blkg->blkcg->lock); - - for (i = 0; i < BLKCG_MAX_POLS; i++) { - struct blkcg_policy *pol = blkcg_policy[i]; - - if (blkg->pd[i] && !blkg->pd[i]->offline && - pol->pd_offline_fn) { - pol->pd_offline_fn(blkg->pd[i]); - blkg->pd[i]->offline = true; - } - } -} - static void blkg_destroy(struct blkcg_gq *blkg) { struct blkcg *blkcg = blkg->blkcg; struct blkcg_gq *parent = blkg->parent; + int i; lockdep_assert_held(blkg->q->queue_lock); lockdep_assert_held(&blkcg->lock); @@ -340,6 +323,13 @@ static void blkg_destroy(struct blkcg_gq *blkg) WARN_ON_ONCE(list_empty(&blkg->q_node)); WARN_ON_ONCE(hlist_unhashed(&blkg->blkcg_node)); + for (i = 0; i < BLKCG_MAX_POLS; i++) { + struct blkcg_policy *pol = blkcg_policy[i]; + + if (blkg->pd[i] && pol->pd_offline_fn) + pol->pd_offline_fn(blkg->pd[i]); + } + if (parent) { blkg_rwstat_add_aux(&parent->stat_bytes, &blkg->stat_bytes); blkg_rwstat_add_aux(&parent->stat_ios, &blkg->stat_ios); @@ -382,7 +372,6 @@ static void blkg_destroy_all(struct request_queue *q) struct blkcg *blkcg = blkg->blkcg; spin_lock(&blkcg->lock); - blkg_pd_offline(blkg); blkg_destroy(blkg); spin_unlock(&blkcg->lock); } @@ -1053,59 +1042,64 @@ static struct cftype blkcg_legacy_files[] = { { } /* terminate */ }; +/* + * blkcg destruction is a three-stage process. + * + * 1. Destruction starts. The blkcg_css_offline() callback is invoked + * which offlines writeback. Here we tie the next stage of blkg destruction + * to the completion of writeback associated with the blkcg. This lets us + * avoid punting potentially large amounts of outstanding writeback to root + * while maintaining any ongoing policies. The next stage is triggered when + * the nr_cgwbs count goes to zero. + * + * 2. When the nr_cgwbs count goes to zero, blkcg_destroy_blkgs() is called + * and handles the destruction of blkgs. Here the css reference held by + * the blkg is put back eventually allowing blkcg_css_free() to be called. + * This work may occur in cgwb_release_workfn() on the cgwb_release + * workqueue. Any submitted ios that fail to get the blkg ref will be + * punted to the root_blkg. + * + * 3. Once the blkcg ref count goes to zero, blkcg_css_free() is called. + * This finally frees the blkcg. + */ + /** * blkcg_css_offline - cgroup css_offline callback * @css: css of interest * - * This function is called when @css is about to go away and responsible - * for offlining all blkgs pd and killing all wbs associated with @css. - * blkgs pd offline should be done while holding both q and blkcg locks. - * As blkcg lock is nested inside q lock, this function performs reverse - * double lock dancing. - * - * This is the blkcg counterpart of ioc_release_fn(). + * This function is called when @css is about to go away. Here the cgwbs are + * offlined first and only once writeback associated with the blkcg has + * finished do we start step 2 (see above). */ static void blkcg_css_offline(struct cgroup_subsys_state *css) { struct blkcg *blkcg = css_to_blkcg(css); - struct blkcg_gq *blkg; - - spin_lock_irq(&blkcg->lock); - - hlist_for_each_entry(blkg, &blkcg->blkg_list, blkcg_node) { - struct request_queue *q = blkg->q; - - if (spin_trylock(q->queue_lock)) { - blkg_pd_offline(blkg); - spin_unlock(q->queue_lock); - } else { - spin_unlock_irq(&blkcg->lock); - cpu_relax(); - spin_lock_irq(&blkcg->lock); - } - } - - spin_unlock_irq(&blkcg->lock); + /* this prevents anyone from attaching or migrating to this blkcg */ wb_blkcg_offline(blkcg); + + /* put the base cgwb reference allowing step 2 to be triggered */ + blkcg_cgwb_put(blkcg); } /** - * blkcg_destroy_all_blkgs - destroy all blkgs associated with a blkcg + * blkcg_destroy_blkgs - responsible for shooting down blkgs * @blkcg: blkcg of interest * - * This function is called when blkcg css is about to free and responsible for - * destroying all blkgs associated with @blkcg. - * blkgs should be removed while holding both q and blkcg locks. As blkcg lock + * blkgs should be removed while holding both q and blkcg locks. As blkcg lock * is nested inside q lock, this function performs reverse double lock dancing. + * Destroying the blkgs releases the reference held on the blkcg's css allowing + * blkcg_css_free to eventually be called. + * + * This is the blkcg counterpart of ioc_release_fn(). */ -static void blkcg_destroy_all_blkgs(struct blkcg *blkcg) +void blkcg_destroy_blkgs(struct blkcg *blkcg) { spin_lock_irq(&blkcg->lock); + while (!hlist_empty(&blkcg->blkg_list)) { struct blkcg_gq *blkg = hlist_entry(blkcg->blkg_list.first, - struct blkcg_gq, - blkcg_node); + struct blkcg_gq, blkcg_node); struct request_queue *q = blkg->q; if (spin_trylock(q->queue_lock)) { @@ -1117,6 +1111,7 @@ static void blkcg_destroy_all_blkgs(struct blkcg *blkcg) spin_lock_irq(&blkcg->lock); } } + spin_unlock_irq(&blkcg->lock); } @@ -1125,8 +1120,6 @@ static void blkcg_css_free(struct cgroup_subsys_state *css) struct blkcg *blkcg = css_to_blkcg(css); int i; - blkcg_destroy_all_blkgs(blkcg); - mutex_lock(&blkcg_pol_mutex); list_del(&blkcg->all_blkcgs_node); @@ -1189,6 +1182,7 @@ blkcg_css_alloc(struct cgroup_subsys_state *parent_css) INIT_HLIST_HEAD(&blkcg->blkg_list); #ifdef CONFIG_CGROUP_WRITEBACK INIT_LIST_HEAD(&blkcg->cgwb_list); + refcount_set(&blkcg->cgwb_refcnt, 1); #endif list_add_tail(&blkcg->all_blkcgs_node, &all_blkcgs); @@ -1480,11 +1474,8 @@ void blkcg_deactivate_policy(struct request_queue *q, list_for_each_entry(blkg, &q->blkg_list, q_node) { if (blkg->pd[pol->plid]) { - if (!blkg->pd[pol->plid]->offline && - pol->pd_offline_fn) { + if (pol->pd_offline_fn) pol->pd_offline_fn(blkg->pd[pol->plid]); - blkg->pd[pol->plid]->offline = true; - } pol->pd_free_fn(blkg->pd[pol->plid]); blkg->pd[pol->plid] = NULL; } @@ -1519,8 +1510,10 @@ int blkcg_policy_register(struct blkcg_policy *pol) for (i = 0; i < BLKCG_MAX_POLS; i++) if (!blkcg_policy[i]) break; - if (i >= BLKCG_MAX_POLS) + if (i >= BLKCG_MAX_POLS) { + pr_warn("blkcg_policy_register: BLKCG_MAX_POLS too small\n"); goto err_unlock; + } /* Make sure cpd/pd_alloc_fn and cpd/pd_free_fn in pairs */ if ((!pol->cpd_alloc_fn ^ !pol->cpd_free_fn) || diff --git a/block/blk-core.c b/block/blk-core.c index dee56c282efb..cff0a60ee200 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -2163,9 +2163,12 @@ static inline bool bio_check_ro(struct bio *bio, struct hd_struct *part) { const int op = bio_op(bio); - if (part->policy && (op_is_write(op) && !op_is_flush(op))) { + if (part->policy && op_is_write(op)) { char b[BDEVNAME_SIZE]; + if (op_is_flush(bio->bi_opf) && !bio_sectors(bio)) + return false; + WARN_ONCE(1, "generic_make_request: Trying to write " "to read-only block-device %s (partno %d)\n", @@ -2730,17 +2733,15 @@ void blk_account_io_done(struct request *req, u64 now) * containing request is enough. */ if (blk_do_io_stat(req) && !(req->rq_flags & RQF_FLUSH_SEQ)) { - unsigned long duration; const int sgrp = op_stat_group(req_op(req)); struct hd_struct *part; int cpu; - duration = nsecs_to_jiffies(now - req->start_time_ns); cpu = part_stat_lock(); part = req->part; part_stat_inc(cpu, part, ios[sgrp]); - part_stat_add(cpu, part, ticks[sgrp], duration); + part_stat_add(cpu, part, nsecs[sgrp], now - req->start_time_ns); part_round_stats(req->q, cpu, part); part_dec_in_flight(req->q, part, rq_data_dir(req)); diff --git a/block/blk-throttle.c b/block/blk-throttle.c index a3eede00d302..01d0620a4e4a 100644 --- a/block/blk-throttle.c +++ b/block/blk-throttle.c @@ -2129,8 +2129,9 @@ static inline void throtl_update_latency_buckets(struct throtl_data *td) static void blk_throtl_assoc_bio(struct throtl_grp *tg, struct bio *bio) { #ifdef CONFIG_BLK_DEV_THROTTLING_LOW - if (bio->bi_css) - bio_associate_blkg(bio, tg_to_blkg(tg)); + /* fallback to root_blkg if we fail to get a blkg ref */ + if (bio->bi_css && (bio_associate_blkg(bio, tg_to_blkg(tg)) == -ENODEV)) + bio_associate_blkg(bio, bio->bi_disk->queue->root_blkg); bio_issue_init(&bio->bi_issue, bio_sectors(bio)); #endif } diff --git a/block/genhd.c b/block/genhd.c index 8cc719a37b32..be5bab20b2ab 100644 --- a/block/genhd.c +++ b/block/genhd.c @@ -1343,18 +1343,18 @@ static int diskstats_show(struct seq_file *seqf, void *v) part_stat_read(hd, ios[STAT_READ]), part_stat_read(hd, merges[STAT_READ]), part_stat_read(hd, sectors[STAT_READ]), - jiffies_to_msecs(part_stat_read(hd, ticks[STAT_READ])), + (unsigned int)part_stat_read_msecs(hd, STAT_READ), part_stat_read(hd, ios[STAT_WRITE]), part_stat_read(hd, merges[STAT_WRITE]), part_stat_read(hd, sectors[STAT_WRITE]), - jiffies_to_msecs(part_stat_read(hd, ticks[STAT_WRITE])), + (unsigned int)part_stat_read_msecs(hd, STAT_WRITE), inflight[0], jiffies_to_msecs(part_stat_read(hd, io_ticks)), jiffies_to_msecs(part_stat_read(hd, time_in_queue)), part_stat_read(hd, ios[STAT_DISCARD]), part_stat_read(hd, merges[STAT_DISCARD]), part_stat_read(hd, sectors[STAT_DISCARD]), - jiffies_to_msecs(part_stat_read(hd, ticks[STAT_DISCARD])) + (unsigned int)part_stat_read_msecs(hd, STAT_DISCARD) ); } disk_part_iter_exit(&piter); diff --git a/block/partition-generic.c b/block/partition-generic.c index 5a8975a1201c..d3d14e81fb12 100644 --- a/block/partition-generic.c +++ b/block/partition-generic.c @@ -136,18 +136,18 @@ ssize_t part_stat_show(struct device *dev, part_stat_read(p, ios[STAT_READ]), part_stat_read(p, merges[STAT_READ]), (unsigned long long)part_stat_read(p, sectors[STAT_READ]), - jiffies_to_msecs(part_stat_read(p, ticks[STAT_READ])), + (unsigned int)part_stat_read_msecs(p, STAT_READ), part_stat_read(p, ios[STAT_WRITE]), part_stat_read(p, merges[STAT_WRITE]), (unsigned long long)part_stat_read(p, sectors[STAT_WRITE]), - jiffies_to_msecs(part_stat_read(p, ticks[STAT_WRITE])), + (unsigned int)part_stat_read_msecs(p, STAT_WRITE), inflight[0], jiffies_to_msecs(part_stat_read(p, io_ticks)), jiffies_to_msecs(part_stat_read(p, time_in_queue)), part_stat_read(p, ios[STAT_DISCARD]), part_stat_read(p, merges[STAT_DISCARD]), (unsigned long long)part_stat_read(p, sectors[STAT_DISCARD]), - jiffies_to_msecs(part_stat_read(p, ticks[STAT_DISCARD]))); + (unsigned int)part_stat_read_msecs(p, STAT_DISCARD)); } ssize_t part_inflight_show(struct device *dev, struct device_attribute *attr, diff --git a/drivers/acpi/acpi_lpss.c b/drivers/acpi/acpi_lpss.c index 9706613eecf9..bf64cfa30feb 100644 --- a/drivers/acpi/acpi_lpss.c +++ b/drivers/acpi/acpi_lpss.c @@ -879,7 +879,7 @@ static void acpi_lpss_dismiss(struct device *dev) #define LPSS_GPIODEF0_DMA_LLP BIT(13) static DEFINE_MUTEX(lpss_iosf_mutex); -static bool lpss_iosf_d3_entered; +static bool lpss_iosf_d3_entered = true; static void lpss_iosf_enter_d3_state(void) { diff --git a/drivers/acpi/bus.c b/drivers/acpi/bus.c index 292088fcc624..d2e29a19890d 100644 --- a/drivers/acpi/bus.c +++ b/drivers/acpi/bus.c @@ -35,11 +35,11 @@ #include <linux/delay.h> #ifdef CONFIG_X86 #include <asm/mpspec.h> +#include <linux/dmi.h> #endif #include <linux/acpi_iort.h> #include <linux/pci.h> #include <acpi/apei.h> -#include <linux/dmi.h> #include <linux/suspend.h> #include "internal.h" @@ -82,10 +82,6 @@ static const struct dmi_system_id dsdt_dmi_table[] __initconst = { }, {} }; -#else -static const struct dmi_system_id dsdt_dmi_table[] __initconst = { - {} -}; #endif /* -------------------------------------------------------------------------- @@ -1033,11 +1029,16 @@ void __init acpi_early_init(void) acpi_permanent_mmap = true; +#ifdef CONFIG_X86 /* * If the machine falls into the DMI check table, - * DSDT will be copied to memory + * DSDT will be copied to memory. + * Note that calling dmi_check_system() here on other architectures + * would not be OK because only x86 initializes dmi early enough. + * Thankfully only x86 systems need such quirks for now. */ dmi_check_system(dsdt_dmi_table); +#endif status = acpi_reallocate_root_table(); if (ACPI_FAILURE(status)) { diff --git a/drivers/android/binder_alloc.c b/drivers/android/binder_alloc.c index 3f3b7b253445..64fd96eada31 100644 --- a/drivers/android/binder_alloc.c +++ b/drivers/android/binder_alloc.c @@ -332,6 +332,35 @@ err_no_vma: return vma ? -ENOMEM : -ESRCH; } + +static inline void binder_alloc_set_vma(struct binder_alloc *alloc, + struct vm_area_struct *vma) +{ + if (vma) + alloc->vma_vm_mm = vma->vm_mm; + /* + * If we see alloc->vma is not NULL, buffer data structures set up + * completely. Look at smp_rmb side binder_alloc_get_vma. + * We also want to guarantee new alloc->vma_vm_mm is always visible + * if alloc->vma is set. + */ + smp_wmb(); + alloc->vma = vma; +} + +static inline struct vm_area_struct *binder_alloc_get_vma( + struct binder_alloc *alloc) +{ + struct vm_area_struct *vma = NULL; + + if (alloc->vma) { + /* Look at description in binder_alloc_set_vma */ + smp_rmb(); + vma = alloc->vma; + } + return vma; +} + static struct binder_buffer *binder_alloc_new_buf_locked( struct binder_alloc *alloc, size_t data_size, @@ -348,7 +377,7 @@ static struct binder_buffer *binder_alloc_new_buf_locked( size_t size, data_offsets_size; int ret; - if (alloc->vma == NULL) { + if (!binder_alloc_get_vma(alloc)) { binder_alloc_debug(BINDER_DEBUG_USER_ERROR, "%d: binder_alloc_buf, no vma\n", alloc->pid); @@ -723,9 +752,7 @@ int binder_alloc_mmap_handler(struct binder_alloc *alloc, buffer->free = 1; binder_insert_free_buffer(alloc, buffer); alloc->free_async_space = alloc->buffer_size / 2; - barrier(); - alloc->vma = vma; - alloc->vma_vm_mm = vma->vm_mm; + binder_alloc_set_vma(alloc, vma); mmgrab(alloc->vma_vm_mm); return 0; @@ -754,10 +781,10 @@ void binder_alloc_deferred_release(struct binder_alloc *alloc) int buffers, page_count; struct binder_buffer *buffer; - BUG_ON(alloc->vma); - buffers = 0; mutex_lock(&alloc->mutex); + BUG_ON(alloc->vma); + while ((n = rb_first(&alloc->allocated_buffers))) { buffer = rb_entry(n, struct binder_buffer, rb_node); @@ -900,7 +927,7 @@ int binder_alloc_get_allocated_count(struct binder_alloc *alloc) */ void binder_alloc_vma_close(struct binder_alloc *alloc) { - WRITE_ONCE(alloc->vma, NULL); + binder_alloc_set_vma(alloc, NULL); } /** @@ -935,7 +962,7 @@ enum lru_status binder_alloc_free_page(struct list_head *item, index = page - alloc->pages; page_addr = (uintptr_t)alloc->buffer + index * PAGE_SIZE; - vma = alloc->vma; + vma = binder_alloc_get_vma(alloc); if (vma) { if (!mmget_not_zero(alloc->vma_vm_mm)) goto err_mmget; diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c index 172e32840256..a9dd4ea7467d 100644 --- a/drivers/ata/libata-core.c +++ b/drivers/ata/libata-core.c @@ -5359,10 +5359,20 @@ void ata_qc_complete(struct ata_queued_cmd *qc) */ int ata_qc_complete_multiple(struct ata_port *ap, u64 qc_active) { + u64 done_mask, ap_qc_active = ap->qc_active; int nr_done = 0; - u64 done_mask; - done_mask = ap->qc_active ^ qc_active; + /* + * If the internal tag is set on ap->qc_active, then we care about + * bit0 on the passed in qc_active mask. Move that bit up to match + * the internal tag. + */ + if (ap_qc_active & (1ULL << ATA_TAG_INTERNAL)) { + qc_active |= (qc_active & 0x01) << ATA_TAG_INTERNAL; + qc_active ^= qc_active & 0x01; + } + + done_mask = ap_qc_active ^ qc_active; if (unlikely(done_mask & qc_active)) { ata_port_err(ap, "illegal qc_active transition (%08llx->%08llx)\n", @@ -7394,4 +7404,4 @@ EXPORT_SYMBOL_GPL(ata_cable_unknown); EXPORT_SYMBOL_GPL(ata_cable_ignore); EXPORT_SYMBOL_GPL(ata_cable_sata); EXPORT_SYMBOL_GPL(ata_host_get); -EXPORT_SYMBOL_GPL(ata_host_put);
\ No newline at end of file +EXPORT_SYMBOL_GPL(ata_host_put); diff --git a/drivers/base/firmware_loader/main.c b/drivers/base/firmware_loader/main.c index 0943e7065e0e..b3c0498ee433 100644 --- a/drivers/base/firmware_loader/main.c +++ b/drivers/base/firmware_loader/main.c @@ -209,21 +209,24 @@ static struct fw_priv *__lookup_fw_priv(const char *fw_name) static int alloc_lookup_fw_priv(const char *fw_name, struct firmware_cache *fwc, struct fw_priv **fw_priv, void *dbuf, - size_t size) + size_t size, enum fw_opt opt_flags) { struct fw_priv *tmp; spin_lock(&fwc->lock); - tmp = __lookup_fw_priv(fw_name); - if (tmp) { - kref_get(&tmp->ref); - spin_unlock(&fwc->lock); - *fw_priv = tmp; - pr_debug("batched request - sharing the same struct fw_priv and lookup for multiple requests\n"); - return 1; + if (!(opt_flags & FW_OPT_NOCACHE)) { + tmp = __lookup_fw_priv(fw_name); + if (tmp) { + kref_get(&tmp->ref); + spin_unlock(&fwc->lock); + *fw_priv = tmp; + pr_debug("batched request - sharing the same struct fw_priv and lookup for multiple requests\n"); + return 1; + } } + tmp = __allocate_fw_priv(fw_name, fwc, dbuf, size); - if (tmp) + if (tmp && !(opt_flags & FW_OPT_NOCACHE)) list_add(&tmp->list, &fwc->head); spin_unlock(&fwc->lock); @@ -493,7 +496,8 @@ int assign_fw(struct firmware *fw, struct device *device, */ static int _request_firmware_prepare(struct firmware **firmware_p, const char *name, - struct device *device, void *dbuf, size_t size) + struct device *device, void *dbuf, size_t size, + enum fw_opt opt_flags) { struct firmware *firmware; struct fw_priv *fw_priv; @@ -511,7 +515,8 @@ _request_firmware_prepare(struct firmware **firmware_p, const char *name, return 0; /* assigned */ } - ret = alloc_lookup_fw_priv(name, &fw_cache, &fw_priv, dbuf, size); + ret = alloc_lookup_fw_priv(name, &fw_cache, &fw_priv, dbuf, size, + opt_flags); /* * bind with 'priv' now to avoid warning in failure path @@ -571,7 +576,8 @@ _request_firmware(const struct firmware **firmware_p, const char *name, goto out; } - ret = _request_firmware_prepare(&fw, name, device, buf, size); + ret = _request_firmware_prepare(&fw, name, device, buf, size, + opt_flags); if (ret <= 0) /* error or already assigned */ goto out; diff --git a/drivers/base/memory.c b/drivers/base/memory.c index c8a1cb0b6136..817320c7c4c1 100644 --- a/drivers/base/memory.c +++ b/drivers/base/memory.c @@ -417,25 +417,23 @@ static ssize_t show_valid_zones(struct device *dev, int nid; /* - * The block contains more than one zone can not be offlined. - * This can happen e.g. for ZONE_DMA and ZONE_DMA32 - */ - if (!test_pages_in_a_zone(start_pfn, start_pfn + nr_pages, &valid_start_pfn, &valid_end_pfn)) - return sprintf(buf, "none\n"); - - start_pfn = valid_start_pfn; - nr_pages = valid_end_pfn - start_pfn; - - /* * Check the existing zone. Make sure that we do that only on the * online nodes otherwise the page_zone is not reliable */ if (mem->state == MEM_ONLINE) { + /* + * The block contains more than one zone can not be offlined. + * This can happen e.g. for ZONE_DMA and ZONE_DMA32 + */ + if (!test_pages_in_a_zone(start_pfn, start_pfn + nr_pages, + &valid_start_pfn, &valid_end_pfn)) + return sprintf(buf, "none\n"); + start_pfn = valid_start_pfn; strcat(buf, page_zone(pfn_to_page(start_pfn))->name); goto out; } - nid = pfn_to_nid(start_pfn); + nid = mem->nid; default_zone = zone_for_pfn_range(MMOP_ONLINE_KEEP, nid, start_pfn, nr_pages); strcat(buf, default_zone->name); diff --git a/drivers/block/floppy.c b/drivers/block/floppy.c index 48f622728ce6..f2b6f4da1034 100644 --- a/drivers/block/floppy.c +++ b/drivers/block/floppy.c @@ -3467,6 +3467,9 @@ static int fd_locked_ioctl(struct block_device *bdev, fmode_t mode, unsigned int (struct floppy_struct **)&outparam); if (ret) return ret; + memcpy(&inparam.g, outparam, + offsetof(struct floppy_struct, name)); + outparam = &inparam.g; break; case FDMSGON: UDP->flags |= FTD_MSG; diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c index 3863c00372bb..14a51254c3db 100644 --- a/drivers/block/nbd.c +++ b/drivers/block/nbd.c @@ -1239,6 +1239,9 @@ static int __nbd_ioctl(struct block_device *bdev, struct nbd_device *nbd, case NBD_SET_SOCK: return nbd_add_socket(nbd, arg, false); case NBD_SET_BLKSIZE: + if (!arg || !is_power_of_2(arg) || arg < 512 || + arg > PAGE_SIZE) + return -EINVAL; nbd_size_set(nbd, arg, div_s64(config->bytesize, arg)); return 0; diff --git a/drivers/block/null_blk.h b/drivers/block/null_blk.h index d81781f22dba..34e0030f0592 100644 --- a/drivers/block/null_blk.h +++ b/drivers/block/null_blk.h @@ -87,10 +87,10 @@ struct nullb { #ifdef CONFIG_BLK_DEV_ZONED int null_zone_init(struct nullb_device *dev); void null_zone_exit(struct nullb_device *dev); -blk_status_t null_zone_report(struct nullb *nullb, - struct nullb_cmd *cmd); -void null_zone_write(struct nullb_cmd *cmd); -void null_zone_reset(struct nullb_cmd *cmd); +blk_status_t null_zone_report(struct nullb *nullb, struct bio *bio); +void null_zone_write(struct nullb_cmd *cmd, sector_t sector, + unsigned int nr_sectors); +void null_zone_reset(struct nullb_cmd *cmd, sector_t sector); #else static inline int null_zone_init(struct nullb_device *dev) { @@ -98,11 +98,14 @@ static inline int null_zone_init(struct nullb_device *dev) } static inline void null_zone_exit(struct nullb_device *dev) {} static inline blk_status_t null_zone_report(struct nullb *nullb, - struct nullb_cmd *cmd) + struct bio *bio) { return BLK_STS_NOTSUPP; } -static inline void null_zone_write(struct nullb_cmd *cmd) {} -static inline void null_zone_reset(struct nullb_cmd *cmd) {} +static inline void null_zone_write(struct nullb_cmd *cmd, sector_t sector, + unsigned int nr_sectors) +{ +} +static inline void null_zone_reset(struct nullb_cmd *cmd, sector_t sector) {} #endif /* CONFIG_BLK_DEV_ZONED */ #endif /* __NULL_BLK_H */ diff --git a/drivers/block/null_blk_main.c b/drivers/block/null_blk_main.c index 6127e3ff7b4b..093b614d6524 100644 --- a/drivers/block/null_blk_main.c +++ b/drivers/block/null_blk_main.c @@ -1157,16 +1157,33 @@ static void null_restart_queue_async(struct nullb *nullb) } } +static bool cmd_report_zone(struct nullb *nullb, struct nullb_cmd *cmd) +{ + struct nullb_device *dev = cmd->nq->dev; + + if (dev->queue_mode == NULL_Q_BIO) { + if (bio_op(cmd->bio) == REQ_OP_ZONE_REPORT) { + cmd->error = null_zone_report(nullb, cmd->bio); + return true; + } + } else { + if (req_op(cmd->rq) == REQ_OP_ZONE_REPORT) { + cmd->error = null_zone_report(nullb, cmd->rq->bio); + return true; + } + } + + return false; +} + static blk_status_t null_handle_cmd(struct nullb_cmd *cmd) { struct nullb_device *dev = cmd->nq->dev; struct nullb *nullb = dev->nullb; int err = 0; - if (req_op(cmd->rq) == REQ_OP_ZONE_REPORT) { - cmd->error = null_zone_report(nullb, cmd); + if (cmd_report_zone(nullb, cmd)) goto out; - } if (test_bit(NULLB_DEV_FL_THROTTLED, &dev->flags)) { struct request *rq = cmd->rq; @@ -1234,10 +1251,24 @@ static blk_status_t null_handle_cmd(struct nullb_cmd *cmd) cmd->error = errno_to_blk_status(err); if (!cmd->error && dev->zoned) { - if (req_op(cmd->rq) == REQ_OP_WRITE) - null_zone_write(cmd); - else if (req_op(cmd->rq) == REQ_OP_ZONE_RESET) - null_zone_reset(cmd); + sector_t sector; + unsigned int nr_sectors; + int op; + + if (dev->queue_mode == NULL_Q_BIO) { + op = bio_op(cmd->bio); + sector = cmd->bio->bi_iter.bi_sector; + nr_sectors = cmd->bio->bi_iter.bi_size >> 9; + } else { + op = req_op(cmd->rq); + sector = blk_rq_pos(cmd->rq); + nr_sectors = blk_rq_sectors(cmd->rq); + } + + if (op == REQ_OP_WRITE) + null_zone_write(cmd, sector, nr_sectors); + else if (op == REQ_OP_ZONE_RESET) + null_zone_reset(cmd, sector); } out: /* Complete IO by inline, softirq or timer */ diff --git a/drivers/block/null_blk_zoned.c b/drivers/block/null_blk_zoned.c index a979ca00d7be..7c6b86d98700 100644 --- a/drivers/block/null_blk_zoned.c +++ b/drivers/block/null_blk_zoned.c @@ -48,8 +48,8 @@ void null_zone_exit(struct nullb_device *dev) kvfree(dev->zones); } -static void null_zone_fill_rq(struct nullb_device *dev, struct request *rq, - unsigned int zno, unsigned int nr_zones) +static void null_zone_fill_bio(struct nullb_device *dev, struct bio *bio, + unsigned int zno, unsigned int nr_zones) { struct blk_zone_report_hdr *hdr = NULL; struct bio_vec bvec; @@ -57,7 +57,7 @@ static void null_zone_fill_rq(struct nullb_device *dev, struct request *rq, void *addr; unsigned int zones_to_cpy; - bio_for_each_segment(bvec, rq->bio, iter) { + bio_for_each_segment(bvec, bio, iter) { addr = kmap_atomic(bvec.bv_page); zones_to_cpy = bvec.bv_len / sizeof(struct blk_zone); @@ -84,29 +84,24 @@ static void null_zone_fill_rq(struct nullb_device *dev, struct request *rq, } } -blk_status_t null_zone_report(struct nullb *nullb, - struct nullb_cmd *cmd) +blk_status_t null_zone_report(struct nullb *nullb, struct bio *bio) { struct nullb_device *dev = nullb->dev; - struct request *rq = cmd->rq; - unsigned int zno = null_zone_no(dev, blk_rq_pos(rq)); + unsigned int zno = null_zone_no(dev, bio->bi_iter.bi_sector); unsigned int nr_zones = dev->nr_zones - zno; - unsigned int max_zones = (blk_rq_bytes(rq) / - sizeof(struct blk_zone)) - 1; + unsigned int max_zones; + max_zones = (bio->bi_iter.bi_size / sizeof(struct blk_zone)) - 1; nr_zones = min_t(unsigned int, nr_zones, max_zones); - - null_zone_fill_rq(nullb->dev, rq, zno, nr_zones); + null_zone_fill_bio(nullb->dev, bio, zno, nr_zones); return BLK_STS_OK; } -void null_zone_write(struct nullb_cmd *cmd) +void null_zone_write(struct nullb_cmd *cmd, sector_t sector, + unsigned int nr_sectors) { struct nullb_device *dev = cmd->nq->dev; - struct request *rq = cmd->rq; - sector_t sector = blk_rq_pos(rq); - unsigned int rq_sectors = blk_rq_sectors(rq); unsigned int zno = null_zone_no(dev, sector); struct blk_zone *zone = &dev->zones[zno]; @@ -118,7 +113,7 @@ void null_zone_write(struct nullb_cmd *cmd) case BLK_ZONE_COND_EMPTY: case BLK_ZONE_COND_IMP_OPEN: /* Writes must be at the write pointer position */ - if (blk_rq_pos(rq) != zone->wp) { + if (sector != zone->wp) { cmd->error = BLK_STS_IOERR; break; } @@ -126,7 +121,7 @@ void null_zone_write(struct nullb_cmd *cmd) if (zone->cond == BLK_ZONE_COND_EMPTY) zone->cond = BLK_ZONE_COND_IMP_OPEN; - zone->wp += rq_sectors; + zone->wp += nr_sectors; if (zone->wp == zone->start + zone->len) zone->cond = BLK_ZONE_COND_FULL; break; @@ -137,11 +132,10 @@ void null_zone_write(struct nullb_cmd *cmd) } } -void null_zone_reset(struct nullb_cmd *cmd) +void null_zone_reset(struct nullb_cmd *cmd, sector_t sector) { struct nullb_device *dev = cmd->nq->dev; - struct request *rq = cmd->rq; - unsigned int zno = null_zone_no(dev, blk_rq_pos(rq)); + unsigned int zno = null_zone_no(dev, sector); struct blk_zone *zone = &dev->zones[zno]; zone->cond = BLK_ZONE_COND_EMPTY; diff --git a/drivers/block/rbd.c b/drivers/block/rbd.c index 7915f3b03736..73ed5f3a862d 100644 --- a/drivers/block/rbd.c +++ b/drivers/block/rbd.c @@ -4207,11 +4207,13 @@ static ssize_t rbd_parent_show(struct device *dev, count += sprintf(&buf[count], "%s" "pool_id %llu\npool_name %s\n" + "pool_ns %s\n" "image_id %s\nimage_name %s\n" "snap_id %llu\nsnap_name %s\n" "overlap %llu\n", !count ? "" : "\n", /* first? */ spec->pool_id, spec->pool_name, + spec->pool_ns ?: "", spec->image_id, spec->image_name ?: "(unknown)", spec->snap_id, spec->snap_name, rbd_dev->parent_overlap); @@ -4584,47 +4586,177 @@ static int rbd_dev_v2_features(struct rbd_device *rbd_dev) &rbd_dev->header.features); } +struct parent_image_info { + u64 pool_id; + const char *pool_ns; + const char *image_id; + u64 snap_id; + + bool has_overlap; + u64 overlap; +}; + +/* + * The caller is responsible for @pii. + */ +static int decode_parent_image_spec(void **p, void *end, + struct parent_image_info *pii) +{ + u8 struct_v; + u32 struct_len; + int ret; + + ret = ceph_start_decoding(p, end, 1, "ParentImageSpec", + &struct_v, &struct_len); + if (ret) + return ret; + + ceph_decode_64_safe(p, end, pii->pool_id, e_inval); + pii->pool_ns = ceph_extract_encoded_string(p, end, NULL, GFP_KERNEL); + if (IS_ERR(pii->pool_ns)) { + ret = PTR_ERR(pii->pool_ns); + pii->pool_ns = NULL; + return ret; + } + pii->image_id = ceph_extract_encoded_string(p, end, NULL, GFP_KERNEL); + if (IS_ERR(pii->image_id)) { + ret = PTR_ERR(pii->image_id); + pii->image_id = NULL; + return ret; + } + ceph_decode_64_safe(p, end, pii->snap_id, e_inval); + return 0; + +e_inval: + return -EINVAL; +} + +static int __get_parent_info(struct rbd_device *rbd_dev, + struct page *req_page, + struct page *reply_page, + struct parent_image_info *pii) +{ + struct ceph_osd_client *osdc = &rbd_dev->rbd_client->client->osdc; + size_t reply_len = PAGE_SIZE; + void *p, *end; + int ret; + + ret = ceph_osdc_call(osdc, &rbd_dev->header_oid, &rbd_dev->header_oloc, + "rbd", "parent_get", CEPH_OSD_FLAG_READ, + req_page, sizeof(u64), reply_page, &reply_len); + if (ret) + return ret == -EOPNOTSUPP ? 1 : ret; + + p = page_address(reply_page); + end = p + reply_len; + ret = decode_parent_image_spec(&p, end, pii); + if (ret) + return ret; + + ret = ceph_osdc_call(osdc, &rbd_dev->header_oid, &rbd_dev->header_oloc, + "rbd", "parent_overlap_get", CEPH_OSD_FLAG_READ, + req_page, sizeof(u64), reply_page, &reply_len); + if (ret) + return ret; + + p = page_address(reply_page); + end = p + reply_len; + ceph_decode_8_safe(&p, end, pii->has_overlap, e_inval); + if (pii->has_overlap) + ceph_decode_64_safe(&p, end, pii->overlap, e_inval); + + return 0; + +e_inval: + return -EINVAL; +} + +/* + * The caller is responsible for @pii. + */ +static int __get_parent_info_legacy(struct rbd_device *rbd_dev, + struct page *req_page, + struct page *reply_page, + struct parent_image_info *pii) +{ + struct ceph_osd_client *osdc = &rbd_dev->rbd_client->client->osdc; + size_t reply_len = PAGE_SIZE; + void *p, *end; + int ret; + + ret = ceph_osdc_call(osdc, &rbd_dev->header_oid, &rbd_dev->header_oloc, + "rbd", "get_parent", CEPH_OSD_FLAG_READ, + req_page, sizeof(u64), reply_page, &reply_len); + if (ret) + return ret; + + p = page_address(reply_page); + end = p + reply_len; + ceph_decode_64_safe(&p, end, pii->pool_id, e_inval); + pii->image_id = ceph_extract_encoded_string(&p, end, NULL, GFP_KERNEL); + if (IS_ERR(pii->image_id)) { + ret = PTR_ERR(pii->image_id); + pii->image_id = NULL; + return ret; + } + ceph_decode_64_safe(&p, end, pii->snap_id, e_inval); + pii->has_overlap = true; + ceph_decode_64_safe(&p, end, pii->overlap, e_inval); + + return 0; + +e_inval: + return -EINVAL; +} + +static int get_parent_info(struct rbd_device *rbd_dev, + struct parent_image_info *pii) +{ + struct page *req_page, *reply_page; + void *p; + int ret; + + req_page = alloc_page(GFP_KERNEL); + if (!req_page) + return -ENOMEM; + + reply_page = alloc_page(GFP_KERNEL); + if (!reply_page) { + __free_page(req_page); + return -ENOMEM; + } + + p = page_address(req_page); + ceph_encode_64(&p, rbd_dev->spec->snap_id); + ret = __get_parent_info(rbd_dev, req_page, reply_page, pii); + if (ret > 0) + ret = __get_parent_info_legacy(rbd_dev, req_page, reply_page, + pii); + + __free_page(req_page); + __free_page(reply_page); + return ret; +} + static int rbd_dev_v2_parent_info(struct rbd_device *rbd_dev) { struct rbd_spec *parent_spec; - size_t size; - void *reply_buf = NULL; - __le64 snapid; - void *p; - void *end; - u64 pool_id; - char *image_id; - u64 snap_id; - u64 overlap; + struct parent_image_info pii = { 0 }; int ret; parent_spec = rbd_spec_alloc(); if (!parent_spec) return -ENOMEM; - size = sizeof (__le64) + /* pool_id */ - sizeof (__le32) + RBD_IMAGE_ID_LEN_MAX + /* image_id */ - sizeof (__le64) + /* snap_id */ - sizeof (__le64); /* overlap */ - reply_buf = kmalloc(size, GFP_KERNEL); - if (!reply_buf) { - ret = -ENOMEM; + ret = get_parent_info(rbd_dev, &pii); + if (ret) goto out_err; - } - snapid = cpu_to_le64(rbd_dev->spec->snap_id); - ret = rbd_obj_method_sync(rbd_dev, &rbd_dev->header_oid, - &rbd_dev->header_oloc, "get_parent", - &snapid, sizeof(snapid), reply_buf, size); - dout("%s: rbd_obj_method_sync returned %d\n", __func__, ret); - if (ret < 0) - goto out_err; + dout("%s pool_id %llu pool_ns %s image_id %s snap_id %llu has_overlap %d overlap %llu\n", + __func__, pii.pool_id, pii.pool_ns, pii.image_id, pii.snap_id, + pii.has_overlap, pii.overlap); - p = reply_buf; - end = reply_buf + ret; - ret = -ERANGE; - ceph_decode_64_safe(&p, end, pool_id, out_err); - if (pool_id == CEPH_NOPOOL) { + if (pii.pool_id == CEPH_NOPOOL || !pii.has_overlap) { /* * Either the parent never existed, or we have * record of it but the image got flattened so it no @@ -4633,6 +4765,10 @@ static int rbd_dev_v2_parent_info(struct rbd_device *rbd_dev) * overlap to 0. The effect of this is that all new * requests will be treated as if the image had no * parent. + * + * If !pii.has_overlap, the parent image spec is not + * applicable. It's there to avoid duplication in each + * snapshot record. */ if (rbd_dev->parent_overlap) { rbd_dev->parent_overlap = 0; @@ -4647,51 +4783,36 @@ static int rbd_dev_v2_parent_info(struct rbd_device *rbd_dev) /* The ceph file layout needs to fit pool id in 32 bits */ ret = -EIO; - if (pool_id > (u64)U32_MAX) { + if (pii.pool_id > (u64)U32_MAX) { rbd_warn(NULL, "parent pool id too large (%llu > %u)", - (unsigned long long)pool_id, U32_MAX); + (unsigned long long)pii.pool_id, U32_MAX); goto out_err; } - image_id = ceph_extract_encoded_string(&p, end, NULL, GFP_KERNEL); - if (IS_ERR(image_id)) { - ret = PTR_ERR(image_id); - goto out_err; - } - ceph_decode_64_safe(&p, end, snap_id, out_err); - ceph_decode_64_safe(&p, end, overlap, out_err); - /* * The parent won't change (except when the clone is * flattened, already handled that). So we only need to * record the parent spec we have not already done so. */ if (!rbd_dev->parent_spec) { - parent_spec->pool_id = pool_id; - parent_spec->image_id = image_id; - parent_spec->snap_id = snap_id; - - /* TODO: support cloning across namespaces */ - if (rbd_dev->spec->pool_ns) { - parent_spec->pool_ns = kstrdup(rbd_dev->spec->pool_ns, - GFP_KERNEL); - if (!parent_spec->pool_ns) { - ret = -ENOMEM; - goto out_err; - } + parent_spec->pool_id = pii.pool_id; + if (pii.pool_ns && *pii.pool_ns) { + parent_spec->pool_ns = pii.pool_ns; + pii.pool_ns = NULL; } + parent_spec->image_id = pii.image_id; + pii.image_id = NULL; + parent_spec->snap_id = pii.snap_id; rbd_dev->parent_spec = parent_spec; parent_spec = NULL; /* rbd_dev now owns this */ - } else { - kfree(image_id); } /* * We always update the parent overlap. If it's zero we issue * a warning, as we will proceed as if there was no parent. */ - if (!overlap) { + if (!pii.overlap) { if (parent_spec) { /* refresh, careful to warn just once */ if (rbd_dev->parent_overlap) @@ -4702,14 +4823,14 @@ static int rbd_dev_v2_parent_info(struct rbd_device *rbd_dev) rbd_warn(rbd_dev, "clone is standalone (overlap 0)"); } } - rbd_dev->parent_overlap = overlap; + rbd_dev->parent_overlap = pii.overlap; out: ret = 0; out_err: - kfree(reply_buf); + kfree(pii.pool_ns); + kfree(pii.image_id); rbd_spec_put(parent_spec); - return ret; } diff --git a/drivers/bluetooth/hci_ldisc.c b/drivers/bluetooth/hci_ldisc.c index 963bb0309e25..ea6238ed5c0e 100644 --- a/drivers/bluetooth/hci_ldisc.c +++ b/drivers/bluetooth/hci_ldisc.c @@ -543,6 +543,8 @@ static void hci_uart_tty_close(struct tty_struct *tty) } clear_bit(HCI_UART_PROTO_SET, &hu->flags); + percpu_free_rwsem(&hu->proto_lock); + kfree(hu); } diff --git a/drivers/char/Kconfig b/drivers/char/Kconfig index ce277ee0a28a..40728491f37b 100644 --- a/drivers/char/Kconfig +++ b/drivers/char/Kconfig @@ -566,5 +566,5 @@ config RANDOM_TRUST_CPU that CPU manufacturer (perhaps with the insistence or mandate of a Nation State's intelligence or law enforcement agencies) has not installed a hidden back door to compromise the CPU's - random number generation facilities. - + random number generation facilities. This can also be configured + at boot with "random.trust_cpu=on/off". diff --git a/drivers/char/ipmi/ipmi_bt_sm.c b/drivers/char/ipmi/ipmi_bt_sm.c index a3397664f800..97d6856c9c0f 100644 --- a/drivers/char/ipmi/ipmi_bt_sm.c +++ b/drivers/char/ipmi/ipmi_bt_sm.c @@ -59,8 +59,6 @@ enum bt_states { BT_STATE_RESET3, BT_STATE_RESTART, BT_STATE_PRINTME, - BT_STATE_CAPABILITIES_BEGIN, - BT_STATE_CAPABILITIES_END, BT_STATE_LONG_BUSY /* BT doesn't get hosed :-) */ }; @@ -86,7 +84,6 @@ struct si_sm_data { int error_retries; /* end of "common" fields */ int nonzero_status; /* hung BMCs stay all 0 */ enum bt_states complete; /* to divert the state machine */ - int BT_CAP_outreqs; long BT_CAP_req2rsp; int BT_CAP_retries; /* Recommended retries */ }; @@ -137,8 +134,6 @@ static char *state2txt(unsigned char state) case BT_STATE_RESET3: return("RESET3"); case BT_STATE_RESTART: return("RESTART"); case BT_STATE_LONG_BUSY: return("LONG_BUSY"); - case BT_STATE_CAPABILITIES_BEGIN: return("CAP_BEGIN"); - case BT_STATE_CAPABILITIES_END: return("CAP_END"); } return("BAD STATE"); } @@ -185,7 +180,6 @@ static unsigned int bt_init_data(struct si_sm_data *bt, struct si_sm_io *io) bt->complete = BT_STATE_IDLE; /* end here */ bt->BT_CAP_req2rsp = BT_NORMAL_TIMEOUT * USEC_PER_SEC; bt->BT_CAP_retries = BT_NORMAL_RETRY_LIMIT; - /* BT_CAP_outreqs == zero is a flag to read BT Capabilities */ return 3; /* We claim 3 bytes of space; ought to check SPMI table */ } @@ -451,7 +445,7 @@ static enum si_sm_result error_recovery(struct si_sm_data *bt, static enum si_sm_result bt_event(struct si_sm_data *bt, long time) { - unsigned char status, BT_CAP[8]; + unsigned char status; static enum bt_states last_printed = BT_STATE_PRINTME; int i; @@ -504,12 +498,6 @@ static enum si_sm_result bt_event(struct si_sm_data *bt, long time) if (status & BT_H_BUSY) /* clear a leftover H_BUSY */ BT_CONTROL(BT_H_BUSY); - bt->timeout = bt->BT_CAP_req2rsp; - - /* Read BT capabilities if it hasn't been done yet */ - if (!bt->BT_CAP_outreqs) - BT_STATE_CHANGE(BT_STATE_CAPABILITIES_BEGIN, - SI_SM_CALL_WITHOUT_DELAY); BT_SI_SM_RETURN(SI_SM_IDLE); case BT_STATE_XACTION_START: @@ -614,37 +602,6 @@ static enum si_sm_result bt_event(struct si_sm_data *bt, long time) BT_STATE_CHANGE(BT_STATE_XACTION_START, SI_SM_CALL_WITH_DELAY); - /* - * Get BT Capabilities, using timing of upper level state machine. - * Set outreqs to prevent infinite loop on timeout. - */ - case BT_STATE_CAPABILITIES_BEGIN: - bt->BT_CAP_outreqs = 1; - { - unsigned char GetBT_CAP[] = { 0x18, 0x36 }; - bt->state = BT_STATE_IDLE; - bt_start_transaction(bt, GetBT_CAP, sizeof(GetBT_CAP)); - } - bt->complete = BT_STATE_CAPABILITIES_END; - BT_STATE_CHANGE(BT_STATE_XACTION_START, - SI_SM_CALL_WITH_DELAY); - - case BT_STATE_CAPABILITIES_END: - i = bt_get_result(bt, BT_CAP, sizeof(BT_CAP)); - bt_init_data(bt, bt->io); - if ((i == 8) && !BT_CAP[2]) { - bt->BT_CAP_outreqs = BT_CAP[3]; - bt->BT_CAP_req2rsp = BT_CAP[6] * USEC_PER_SEC; - bt->BT_CAP_retries = BT_CAP[7]; - } else - printk(KERN_WARNING "IPMI BT: using default values\n"); - if (!bt->BT_CAP_outreqs) - bt->BT_CAP_outreqs = 1; - printk(KERN_WARNING "IPMI BT: req2rsp=%ld secs retries=%d\n", - bt->BT_CAP_req2rsp / USEC_PER_SEC, bt->BT_CAP_retries); - bt->timeout = bt->BT_CAP_req2rsp; - return SI_SM_CALL_WITHOUT_DELAY; - default: /* should never occur */ return error_recovery(bt, status, @@ -655,6 +612,11 @@ static enum si_sm_result bt_event(struct si_sm_data *bt, long time) static int bt_detect(struct si_sm_data *bt) { + unsigned char GetBT_CAP[] = { 0x18, 0x36 }; + unsigned char BT_CAP[8]; + enum si_sm_result smi_result; + int rv; + /* * It's impossible for the BT status and interrupt registers to be * all 1's, (assuming a properly functioning, self-initialized BMC) @@ -665,6 +627,48 @@ static int bt_detect(struct si_sm_data *bt) if ((BT_STATUS == 0xFF) && (BT_INTMASK_R == 0xFF)) return 1; reset_flags(bt); + + /* + * Try getting the BT capabilities here. + */ + rv = bt_start_transaction(bt, GetBT_CAP, sizeof(GetBT_CAP)); + if (rv) { + dev_warn(bt->io->dev, + "Can't start capabilities transaction: %d\n", rv); + goto out_no_bt_cap; + } + + smi_result = SI_SM_CALL_WITHOUT_DELAY; + for (;;) { + if (smi_result == SI_SM_CALL_WITH_DELAY || + smi_result == SI_SM_CALL_WITH_TICK_DELAY) { + schedule_timeout_uninterruptible(1); + smi_result = bt_event(bt, jiffies_to_usecs(1)); + } else if (smi_result == SI_SM_CALL_WITHOUT_DELAY) { + smi_result = bt_event(bt, 0); + } else + break; + } + + rv = bt_get_result(bt, BT_CAP, sizeof(BT_CAP)); + bt_init_data(bt, bt->io); + if (rv < 8) { + dev_warn(bt->io->dev, "bt cap response too short: %d\n", rv); + goto out_no_bt_cap; + } + + if (BT_CAP[2]) { + dev_warn(bt->io->dev, "Error fetching bt cap: %x\n", BT_CAP[2]); +out_no_bt_cap: + dev_warn(bt->io->dev, "using default values\n"); + } else { + bt->BT_CAP_req2rsp = BT_CAP[6] * USEC_PER_SEC; + bt->BT_CAP_retries = BT_CAP[7]; + } + + dev_info(bt->io->dev, "req2rsp=%ld secs retries=%d\n", + bt->BT_CAP_req2rsp / USEC_PER_SEC, bt->BT_CAP_retries); + return 0; } diff --git a/drivers/char/ipmi/ipmi_msghandler.c b/drivers/char/ipmi/ipmi_msghandler.c index 51832b8a2c62..7fc9612070a1 100644 --- a/drivers/char/ipmi/ipmi_msghandler.c +++ b/drivers/char/ipmi/ipmi_msghandler.c @@ -3381,39 +3381,45 @@ int ipmi_register_smi(const struct ipmi_smi_handlers *handlers, rv = handlers->start_processing(send_info, intf); if (rv) - goto out; + goto out_err; rv = __bmc_get_device_id(intf, NULL, &id, NULL, NULL, i); if (rv) { dev_err(si_dev, "Unable to get the device id: %d\n", rv); - goto out; + goto out_err_started; } mutex_lock(&intf->bmc_reg_mutex); rv = __scan_channels(intf, &id); mutex_unlock(&intf->bmc_reg_mutex); + if (rv) + goto out_err_bmc_reg; - out: - if (rv) { - ipmi_bmc_unregister(intf); - list_del_rcu(&intf->link); - mutex_unlock(&ipmi_interfaces_mutex); - synchronize_srcu(&ipmi_interfaces_srcu); - cleanup_srcu_struct(&intf->users_srcu); - kref_put(&intf->refcount, intf_free); - } else { - /* - * Keep memory order straight for RCU readers. Make - * sure everything else is committed to memory before - * setting intf_num to mark the interface valid. - */ - smp_wmb(); - intf->intf_num = i; - mutex_unlock(&ipmi_interfaces_mutex); + /* + * Keep memory order straight for RCU readers. Make + * sure everything else is committed to memory before + * setting intf_num to mark the interface valid. + */ + smp_wmb(); + intf->intf_num = i; + mutex_unlock(&ipmi_interfaces_mutex); - /* After this point the interface is legal to use. */ - call_smi_watchers(i, intf->si_dev); - } + /* After this point the interface is legal to use. */ + call_smi_watchers(i, intf->si_dev); + + return 0; + + out_err_bmc_reg: + ipmi_bmc_unregister(intf); + out_err_started: + if (intf->handlers->shutdown) + intf->handlers->shutdown(intf->send_info); + out_err: + list_del_rcu(&intf->link); + mutex_unlock(&ipmi_interfaces_mutex); + synchronize_srcu(&ipmi_interfaces_srcu); + cleanup_srcu_struct(&intf->users_srcu); + kref_put(&intf->refcount, intf_free); return rv; } @@ -3504,7 +3510,8 @@ void ipmi_unregister_smi(struct ipmi_smi *intf) } srcu_read_unlock(&intf->users_srcu, index); - intf->handlers->shutdown(intf->send_info); + if (intf->handlers->shutdown) + intf->handlers->shutdown(intf->send_info); cleanup_smi_msgs(intf); diff --git a/drivers/char/ipmi/ipmi_si_intf.c b/drivers/char/ipmi/ipmi_si_intf.c index 90ec010bffbd..5faa917df1b6 100644 --- a/drivers/char/ipmi/ipmi_si_intf.c +++ b/drivers/char/ipmi/ipmi_si_intf.c @@ -2083,18 +2083,9 @@ static int try_smi_init(struct smi_info *new_smi) si_to_str[new_smi->io.si_type]); WARN_ON(new_smi->io.dev->init_name != NULL); - kfree(init_name); - - return 0; - -out_err: - if (new_smi->intf) { - ipmi_unregister_smi(new_smi->intf); - new_smi->intf = NULL; - } + out_err: kfree(init_name); - return rv; } @@ -2227,6 +2218,8 @@ static void shutdown_smi(void *send_info) kfree(smi_info->si_sm); smi_info->si_sm = NULL; + + smi_info->intf = NULL; } /* @@ -2240,10 +2233,8 @@ static void cleanup_one_si(struct smi_info *smi_info) list_del(&smi_info->link); - if (smi_info->intf) { + if (smi_info->intf) ipmi_unregister_smi(smi_info->intf); - smi_info->intf = NULL; - } if (smi_info->pdev) { if (smi_info->pdev_registered) diff --git a/drivers/char/ipmi/ipmi_ssif.c b/drivers/char/ipmi/ipmi_ssif.c index 18e4650c233b..29e67a80fb20 100644 --- a/drivers/char/ipmi/ipmi_ssif.c +++ b/drivers/char/ipmi/ipmi_ssif.c @@ -181,6 +181,8 @@ struct ssif_addr_info { struct device *dev; struct i2c_client *client; + struct i2c_client *added_client; + struct mutex clients_mutex; struct list_head clients; @@ -1214,18 +1216,11 @@ static void shutdown_ssif(void *send_info) complete(&ssif_info->wake_thread); kthread_stop(ssif_info->thread); } - - /* - * No message can be outstanding now, we have removed the - * upper layer and it permitted us to do so. - */ - kfree(ssif_info); } static int ssif_remove(struct i2c_client *client) { struct ssif_info *ssif_info = i2c_get_clientdata(client); - struct ipmi_smi *intf; struct ssif_addr_info *addr_info; if (!ssif_info) @@ -1235,9 +1230,7 @@ static int ssif_remove(struct i2c_client *client) * After this point, we won't deliver anything asychronously * to the message handler. We can unregister ourself. */ - intf = ssif_info->intf; - ssif_info->intf = NULL; - ipmi_unregister_smi(intf); + ipmi_unregister_smi(ssif_info->intf); list_for_each_entry(addr_info, &ssif_infos, link) { if (addr_info->client == client) { @@ -1246,6 +1239,8 @@ static int ssif_remove(struct i2c_client *client) } } + kfree(ssif_info); + return 0; } @@ -1648,15 +1643,9 @@ static int ssif_probe(struct i2c_client *client, const struct i2c_device_id *id) out: if (rv) { - /* - * Note that if addr_info->client is assigned, we - * leave it. The i2c client hangs around even if we - * return a failure here, and the failure here is not - * propagated back to the i2c code. This seems to be - * design intent, strange as it may be. But if we - * don't leave it, ssif_platform_remove will not remove - * the client like it should. - */ + if (addr_info) + addr_info->client = NULL; + dev_err(&client->dev, "Unable to start IPMI SSIF: %d\n", rv); kfree(ssif_info); } @@ -1676,7 +1665,8 @@ static int ssif_adapter_handler(struct device *adev, void *opaque) if (adev->type != &i2c_adapter_type) return 0; - i2c_new_device(to_i2c_adapter(adev), &addr_info->binfo); + addr_info->added_client = i2c_new_device(to_i2c_adapter(adev), + &addr_info->binfo); if (!addr_info->adapter_name) return 1; /* Only try the first I2C adapter by default. */ @@ -1849,7 +1839,7 @@ static int ssif_platform_remove(struct platform_device *dev) return 0; mutex_lock(&ssif_infos_mutex); - i2c_unregister_device(addr_info->client); + i2c_unregister_device(addr_info->added_client); list_del(&addr_info->link); kfree(addr_info); diff --git a/drivers/char/ipmi/kcs_bmc.c b/drivers/char/ipmi/kcs_bmc.c index bb882ab161fe..e6124bd548df 100644 --- a/drivers/char/ipmi/kcs_bmc.c +++ b/drivers/char/ipmi/kcs_bmc.c @@ -16,6 +16,8 @@ #include "kcs_bmc.h" +#define DEVICE_NAME "ipmi-kcs" + #define KCS_MSG_BUFSIZ 1000 #define KCS_ZERO_DATA 0 @@ -429,8 +431,6 @@ struct kcs_bmc *kcs_bmc_alloc(struct device *dev, int sizeof_priv, u32 channel) if (!kcs_bmc) return NULL; - dev_set_name(dev, "ipmi-kcs%u", channel); - spin_lock_init(&kcs_bmc->lock); kcs_bmc->channel = channel; @@ -444,7 +444,8 @@ struct kcs_bmc *kcs_bmc_alloc(struct device *dev, int sizeof_priv, u32 channel) return NULL; kcs_bmc->miscdev.minor = MISC_DYNAMIC_MINOR; - kcs_bmc->miscdev.name = dev_name(dev); + kcs_bmc->miscdev.name = devm_kasprintf(dev, GFP_KERNEL, "%s%u", + DEVICE_NAME, channel); kcs_bmc->miscdev.fops = &kcs_bmc_fops; return kcs_bmc; diff --git a/drivers/char/random.c b/drivers/char/random.c index bf5f99fc36f1..c75b6cdf0053 100644 --- a/drivers/char/random.c +++ b/drivers/char/random.c @@ -779,6 +779,13 @@ static struct crng_state **crng_node_pool __read_mostly; static void invalidate_batched_entropy(void); +static bool trust_cpu __ro_after_init = IS_ENABLED(CONFIG_RANDOM_TRUST_CPU); +static int __init parse_trust_cpu(char *arg) +{ + return kstrtobool(arg, &trust_cpu); +} +early_param("random.trust_cpu", parse_trust_cpu); + static void crng_initialize(struct crng_state *crng) { int i; @@ -799,12 +806,10 @@ static void crng_initialize(struct crng_state *crng) } crng->state[i] ^= rv; } -#ifdef CONFIG_RANDOM_TRUST_CPU - if (arch_init) { + if (trust_cpu && arch_init) { crng_init = 2; pr_notice("random: crng done (trusting CPU's manufacturer)\n"); } -#endif crng->init_time = jiffies - CRNG_RESEED_INTERVAL - 1; } diff --git a/drivers/clk/x86/clk-pmc-atom.c b/drivers/clk/x86/clk-pmc-atom.c index 08ef69945ffb..d977193842df 100644 --- a/drivers/clk/x86/clk-pmc-atom.c +++ b/drivers/clk/x86/clk-pmc-atom.c @@ -55,6 +55,7 @@ struct clk_plt_data { u8 nparents; struct clk_plt *clks[PMC_CLK_NUM]; struct clk_lookup *mclk_lookup; + struct clk_lookup *ether_clk_lookup; }; /* Return an index in parent table */ @@ -186,13 +187,6 @@ static struct clk_plt *plt_clk_register(struct platform_device *pdev, int id, pclk->reg = base + PMC_CLK_CTL_OFFSET + id * PMC_CLK_CTL_SIZE; spin_lock_init(&pclk->lock); - /* - * If the clock was already enabled by the firmware mark it as critical - * to avoid it being gated by the clock framework if no driver owns it. - */ - if (plt_clk_is_enabled(&pclk->hw)) - init.flags |= CLK_IS_CRITICAL; - ret = devm_clk_hw_register(&pdev->dev, &pclk->hw); if (ret) { pclk = ERR_PTR(ret); @@ -351,11 +345,20 @@ static int plt_clk_probe(struct platform_device *pdev) goto err_unreg_clk_plt; } + data->ether_clk_lookup = clkdev_hw_create(&data->clks[4]->hw, + "ether_clk", NULL); + if (!data->ether_clk_lookup) { + err = -ENOMEM; + goto err_drop_mclk; + } + plt_clk_free_parent_names_loop(parent_names, data->nparents); platform_set_drvdata(pdev, data); return 0; +err_drop_mclk: + clkdev_drop(data->mclk_lookup); err_unreg_clk_plt: plt_clk_unregister_loop(data, i); plt_clk_unregister_parents(data); @@ -369,6 +372,7 @@ static int plt_clk_remove(struct platform_device *pdev) data = platform_get_drvdata(pdev); + clkdev_drop(data->ether_clk_lookup); clkdev_drop(data->mclk_lookup); plt_clk_unregister_loop(data, PMC_CLK_NUM); plt_clk_unregister_parents(data); diff --git a/drivers/crypto/ccp/psp-dev.c b/drivers/crypto/ccp/psp-dev.c index 218739b961fe..72790d88236d 100644 --- a/drivers/crypto/ccp/psp-dev.c +++ b/drivers/crypto/ccp/psp-dev.c @@ -38,6 +38,17 @@ static DEFINE_MUTEX(sev_cmd_mutex); static struct sev_misc_dev *misc_dev; static struct psp_device *psp_master; +static int psp_cmd_timeout = 100; +module_param(psp_cmd_timeout, int, 0644); +MODULE_PARM_DESC(psp_cmd_timeout, " default timeout value, in seconds, for PSP commands"); + +static int psp_probe_timeout = 5; +module_param(psp_probe_timeout, int, 0644); +MODULE_PARM_DESC(psp_probe_timeout, " default timeout value, in seconds, during PSP device probe"); + +static bool psp_dead; +static int psp_timeout; + static struct psp_device *psp_alloc_struct(struct sp_device *sp) { struct device *dev = sp->dev; @@ -82,10 +93,19 @@ done: return IRQ_HANDLED; } -static void sev_wait_cmd_ioc(struct psp_device *psp, unsigned int *reg) +static int sev_wait_cmd_ioc(struct psp_device *psp, + unsigned int *reg, unsigned int timeout) { - wait_event(psp->sev_int_queue, psp->sev_int_rcvd); + int ret; + + ret = wait_event_timeout(psp->sev_int_queue, + psp->sev_int_rcvd, timeout * HZ); + if (!ret) + return -ETIMEDOUT; + *reg = ioread32(psp->io_regs + psp->vdata->cmdresp_reg); + + return 0; } static int sev_cmd_buffer_len(int cmd) @@ -133,12 +153,15 @@ static int __sev_do_cmd_locked(int cmd, void *data, int *psp_ret) if (!psp) return -ENODEV; + if (psp_dead) + return -EBUSY; + /* Get the physical address of the command buffer */ phys_lsb = data ? lower_32_bits(__psp_pa(data)) : 0; phys_msb = data ? upper_32_bits(__psp_pa(data)) : 0; - dev_dbg(psp->dev, "sev command id %#x buffer 0x%08x%08x\n", - cmd, phys_msb, phys_lsb); + dev_dbg(psp->dev, "sev command id %#x buffer 0x%08x%08x timeout %us\n", + cmd, phys_msb, phys_lsb, psp_timeout); print_hex_dump_debug("(in): ", DUMP_PREFIX_OFFSET, 16, 2, data, sev_cmd_buffer_len(cmd), false); @@ -154,7 +177,18 @@ static int __sev_do_cmd_locked(int cmd, void *data, int *psp_ret) iowrite32(reg, psp->io_regs + psp->vdata->cmdresp_reg); /* wait for command completion */ - sev_wait_cmd_ioc(psp, ®); + ret = sev_wait_cmd_ioc(psp, ®, psp_timeout); + if (ret) { + if (psp_ret) + *psp_ret = 0; + + dev_err(psp->dev, "sev command %#x timed out, disabling PSP \n", cmd); + psp_dead = true; + + return ret; + } + + psp_timeout = psp_cmd_timeout; if (psp_ret) *psp_ret = reg & PSP_CMDRESP_ERR_MASK; @@ -888,6 +922,8 @@ void psp_pci_init(void) psp_master = sp->psp_data; + psp_timeout = psp_probe_timeout; + if (sev_get_api_version()) goto err; diff --git a/drivers/dax/device.c b/drivers/dax/device.c index 6fd46083e629..bbe4d72ca105 100644 --- a/drivers/dax/device.c +++ b/drivers/dax/device.c @@ -392,7 +392,8 @@ static vm_fault_t dev_dax_huge_fault(struct vm_fault *vmf, { struct file *filp = vmf->vma->vm_file; unsigned long fault_size; - int rc, id; + vm_fault_t rc = VM_FAULT_SIGBUS; + int id; pfn_t pfn; struct dev_dax *dev_dax = filp->private_data; diff --git a/drivers/dma/mic_x100_dma.c b/drivers/dma/mic_x100_dma.c index b76cb17d879c..adfd316db1a8 100644 --- a/drivers/dma/mic_x100_dma.c +++ b/drivers/dma/mic_x100_dma.c @@ -639,7 +639,7 @@ static struct mic_dma_device *mic_dma_dev_reg(struct mbus_device *mbdev, int ret; struct device *dev = &mbdev->dev; - mic_dma_dev = kzalloc(sizeof(*mic_dma_dev), GFP_KERNEL); + mic_dma_dev = devm_kzalloc(dev, sizeof(*mic_dma_dev), GFP_KERNEL); if (!mic_dma_dev) { ret = -ENOMEM; goto alloc_error; @@ -664,7 +664,6 @@ static struct mic_dma_device *mic_dma_dev_reg(struct mbus_device *mbdev, reg_error: mic_dma_uninit(mic_dma_dev); init_error: - kfree(mic_dma_dev); mic_dma_dev = NULL; alloc_error: dev_err(dev, "Error at %s %d ret=%d\n", __func__, __LINE__, ret); @@ -674,7 +673,6 @@ alloc_error: static void mic_dma_dev_unreg(struct mic_dma_device *mic_dma_dev) { mic_dma_uninit(mic_dma_dev); - kfree(mic_dma_dev); } /* DEBUGFS CODE */ diff --git a/drivers/firmware/arm_scmi/perf.c b/drivers/firmware/arm_scmi/perf.c index 721e6c57beae..64342944d917 100644 --- a/drivers/firmware/arm_scmi/perf.c +++ b/drivers/firmware/arm_scmi/perf.c @@ -166,7 +166,13 @@ scmi_perf_domain_attributes_get(const struct scmi_handle *handle, u32 domain, le32_to_cpu(attr->sustained_freq_khz); dom_info->sustained_perf_level = le32_to_cpu(attr->sustained_perf_level); - dom_info->mult_factor = (dom_info->sustained_freq_khz * 1000) / + if (!dom_info->sustained_freq_khz || + !dom_info->sustained_perf_level) + /* CPUFreq converts to kHz, hence default 1000 */ + dom_info->mult_factor = 1000; + else + dom_info->mult_factor = + (dom_info->sustained_freq_khz * 1000) / dom_info->sustained_perf_level; memcpy(dom_info->name, attr->name, SCMI_MAX_STR_SIZE); } diff --git a/drivers/firmware/efi/Kconfig b/drivers/firmware/efi/Kconfig index d8e159feb573..89110dfc7127 100644 --- a/drivers/firmware/efi/Kconfig +++ b/drivers/firmware/efi/Kconfig @@ -90,14 +90,17 @@ config EFI_ARMSTUB config EFI_ARMSTUB_DTB_LOADER bool "Enable the DTB loader" depends on EFI_ARMSTUB + default y help Select this config option to add support for the dtb= command line parameter, allowing a device tree blob to be loaded into memory from the EFI System Partition by the stub. - The device tree is typically provided by the platform or by - the bootloader, so this option is mostly for development - purposes only. + If the device tree is provided by the platform or by + the bootloader this option may not be needed. + But, for various development reasons and to maintain existing + functionality for bootloaders that do not have such support + this option is necessary. config EFI_BOOTLOADER_CONTROL tristate "EFI Bootloader Control" diff --git a/drivers/fpga/dfl-fme-pr.c b/drivers/fpga/dfl-fme-pr.c index fc9fd2d0482f..0b840531ef33 100644 --- a/drivers/fpga/dfl-fme-pr.c +++ b/drivers/fpga/dfl-fme-pr.c @@ -420,7 +420,7 @@ static int pr_mgmt_init(struct platform_device *pdev, /* Create region for each port */ fme_region = dfl_fme_create_region(pdata, mgr, fme_br->br, i); - if (!fme_region) { + if (IS_ERR(fme_region)) { ret = PTR_ERR(fme_region); goto destroy_region; } diff --git a/drivers/gpio/gpio-adp5588.c b/drivers/gpio/gpio-adp5588.c index 3530ccd17e04..da9781a2ef4a 100644 --- a/drivers/gpio/gpio-adp5588.c +++ b/drivers/gpio/gpio-adp5588.c @@ -41,6 +41,8 @@ struct adp5588_gpio { uint8_t int_en[3]; uint8_t irq_mask[3]; uint8_t irq_stat[3]; + uint8_t int_input_en[3]; + uint8_t int_lvl_cached[3]; }; static int adp5588_gpio_read(struct i2c_client *client, u8 reg) @@ -173,12 +175,28 @@ static void adp5588_irq_bus_sync_unlock(struct irq_data *d) struct adp5588_gpio *dev = irq_data_get_irq_chip_data(d); int i; - for (i = 0; i <= ADP5588_BANK(ADP5588_MAXGPIO); i++) + for (i = 0; i <= ADP5588_BANK(ADP5588_MAXGPIO); i++) { + if (dev->int_input_en[i]) { + mutex_lock(&dev->lock); + dev->dir[i] &= ~dev->int_input_en[i]; + dev->int_input_en[i] = 0; + adp5588_gpio_write(dev->client, GPIO_DIR1 + i, + dev->dir[i]); + mutex_unlock(&dev->lock); + } + + if (dev->int_lvl_cached[i] != dev->int_lvl[i]) { + dev->int_lvl_cached[i] = dev->int_lvl[i]; + adp5588_gpio_write(dev->client, GPIO_INT_LVL1 + i, + dev->int_lvl[i]); + } + if (dev->int_en[i] ^ dev->irq_mask[i]) { dev->int_en[i] = dev->irq_mask[i]; adp5588_gpio_write(dev->client, GPIO_INT_EN1 + i, dev->int_en[i]); } + } mutex_unlock(&dev->irq_lock); } @@ -221,9 +239,7 @@ static int adp5588_irq_set_type(struct irq_data *d, unsigned int type) else return -EINVAL; - adp5588_gpio_direction_input(&dev->gpio_chip, gpio); - adp5588_gpio_write(dev->client, GPIO_INT_LVL1 + bank, - dev->int_lvl[bank]); + dev->int_input_en[bank] |= bit; return 0; } diff --git a/drivers/gpio/gpio-dwapb.c b/drivers/gpio/gpio-dwapb.c index 28da700f5f52..044888fd96a1 100644 --- a/drivers/gpio/gpio-dwapb.c +++ b/drivers/gpio/gpio-dwapb.c @@ -728,6 +728,7 @@ static int dwapb_gpio_probe(struct platform_device *pdev) out_unregister: dwapb_gpio_unregister(gpio); dwapb_irq_teardown(gpio); + clk_disable_unprepare(gpio->clk); return err; } diff --git a/drivers/gpio/gpiolib-acpi.c b/drivers/gpio/gpiolib-acpi.c index c48ed9d89ff5..8b9d7e42c600 100644 --- a/drivers/gpio/gpiolib-acpi.c +++ b/drivers/gpio/gpiolib-acpi.c @@ -25,7 +25,6 @@ struct acpi_gpio_event { struct list_head node; - struct list_head initial_sync_list; acpi_handle handle; unsigned int pin; unsigned int irq; @@ -49,10 +48,19 @@ struct acpi_gpio_chip { struct mutex conn_lock; struct gpio_chip *chip; struct list_head events; + struct list_head deferred_req_irqs_list_entry; }; -static LIST_HEAD(acpi_gpio_initial_sync_list); -static DEFINE_MUTEX(acpi_gpio_initial_sync_list_lock); +/* + * For gpiochips which call acpi_gpiochip_request_interrupts() before late_init + * (so builtin drivers) we register the ACPI GpioInt event handlers from a + * late_initcall_sync handler, so that other builtin drivers can register their + * OpRegions before the event handlers can run. This list contains gpiochips + * for which the acpi_gpiochip_request_interrupts() has been deferred. + */ +static DEFINE_MUTEX(acpi_gpio_deferred_req_irqs_lock); +static LIST_HEAD(acpi_gpio_deferred_req_irqs_list); +static bool acpi_gpio_deferred_req_irqs_done; static int acpi_gpiochip_find(struct gpio_chip *gc, void *data) { @@ -89,21 +97,6 @@ static struct gpio_desc *acpi_get_gpiod(char *path, int pin) return gpiochip_get_desc(chip, pin); } -static void acpi_gpio_add_to_initial_sync_list(struct acpi_gpio_event *event) -{ - mutex_lock(&acpi_gpio_initial_sync_list_lock); - list_add(&event->initial_sync_list, &acpi_gpio_initial_sync_list); - mutex_unlock(&acpi_gpio_initial_sync_list_lock); -} - -static void acpi_gpio_del_from_initial_sync_list(struct acpi_gpio_event *event) -{ - mutex_lock(&acpi_gpio_initial_sync_list_lock); - if (!list_empty(&event->initial_sync_list)) - list_del_init(&event->initial_sync_list); - mutex_unlock(&acpi_gpio_initial_sync_list_lock); -} - static irqreturn_t acpi_gpio_irq_handler(int irq, void *data) { struct acpi_gpio_event *event = data; @@ -186,7 +179,7 @@ static acpi_status acpi_gpiochip_request_interrupt(struct acpi_resource *ares, gpiod_direction_input(desc); - value = gpiod_get_value(desc); + value = gpiod_get_value_cansleep(desc); ret = gpiochip_lock_as_irq(chip, pin); if (ret) { @@ -229,7 +222,6 @@ static acpi_status acpi_gpiochip_request_interrupt(struct acpi_resource *ares, event->irq = irq; event->pin = pin; event->desc = desc; - INIT_LIST_HEAD(&event->initial_sync_list); ret = request_threaded_irq(event->irq, NULL, handler, irqflags, "ACPI:Event", event); @@ -251,10 +243,9 @@ static acpi_status acpi_gpiochip_request_interrupt(struct acpi_resource *ares, * may refer to OperationRegions from other (builtin) drivers which * may be probed after us. */ - if (handler == acpi_gpio_irq_handler && - (((irqflags & IRQF_TRIGGER_RISING) && value == 1) || - ((irqflags & IRQF_TRIGGER_FALLING) && value == 0))) - acpi_gpio_add_to_initial_sync_list(event); + if (((irqflags & IRQF_TRIGGER_RISING) && value == 1) || + ((irqflags & IRQF_TRIGGER_FALLING) && value == 0)) + handler(event->irq, event); return AE_OK; @@ -283,6 +274,7 @@ void acpi_gpiochip_request_interrupts(struct gpio_chip *chip) struct acpi_gpio_chip *acpi_gpio; acpi_handle handle; acpi_status status; + bool defer; if (!chip->parent || !chip->to_irq) return; @@ -295,6 +287,16 @@ void acpi_gpiochip_request_interrupts(struct gpio_chip *chip) if (ACPI_FAILURE(status)) return; + mutex_lock(&acpi_gpio_deferred_req_irqs_lock); + defer = !acpi_gpio_deferred_req_irqs_done; + if (defer) + list_add(&acpi_gpio->deferred_req_irqs_list_entry, + &acpi_gpio_deferred_req_irqs_list); + mutex_unlock(&acpi_gpio_deferred_req_irqs_lock); + + if (defer) + return; + acpi_walk_resources(handle, "_AEI", acpi_gpiochip_request_interrupt, acpi_gpio); } @@ -325,11 +327,14 @@ void acpi_gpiochip_free_interrupts(struct gpio_chip *chip) if (ACPI_FAILURE(status)) return; + mutex_lock(&acpi_gpio_deferred_req_irqs_lock); + if (!list_empty(&acpi_gpio->deferred_req_irqs_list_entry)) + list_del_init(&acpi_gpio->deferred_req_irqs_list_entry); + mutex_unlock(&acpi_gpio_deferred_req_irqs_lock); + list_for_each_entry_safe_reverse(event, ep, &acpi_gpio->events, node) { struct gpio_desc *desc; - acpi_gpio_del_from_initial_sync_list(event); - if (irqd_is_wakeup_set(irq_get_irq_data(event->irq))) disable_irq_wake(event->irq); @@ -1052,6 +1057,7 @@ void acpi_gpiochip_add(struct gpio_chip *chip) acpi_gpio->chip = chip; INIT_LIST_HEAD(&acpi_gpio->events); + INIT_LIST_HEAD(&acpi_gpio->deferred_req_irqs_list_entry); status = acpi_attach_data(handle, acpi_gpio_chip_dh, acpi_gpio); if (ACPI_FAILURE(status)) { @@ -1198,20 +1204,28 @@ bool acpi_can_fallback_to_crs(struct acpi_device *adev, const char *con_id) return con_id == NULL; } -/* Sync the initial state of handlers after all builtin drivers have probed */ -static int acpi_gpio_initial_sync(void) +/* Run deferred acpi_gpiochip_request_interrupts() */ +static int acpi_gpio_handle_deferred_request_interrupts(void) { - struct acpi_gpio_event *event, *ep; + struct acpi_gpio_chip *acpi_gpio, *tmp; + + mutex_lock(&acpi_gpio_deferred_req_irqs_lock); + list_for_each_entry_safe(acpi_gpio, tmp, + &acpi_gpio_deferred_req_irqs_list, + deferred_req_irqs_list_entry) { + acpi_handle handle; - mutex_lock(&acpi_gpio_initial_sync_list_lock); - list_for_each_entry_safe(event, ep, &acpi_gpio_initial_sync_list, - initial_sync_list) { - acpi_evaluate_object(event->handle, NULL, NULL, NULL); - list_del_init(&event->initial_sync_list); + handle = ACPI_HANDLE(acpi_gpio->chip->parent); + acpi_walk_resources(handle, "_AEI", + acpi_gpiochip_request_interrupt, acpi_gpio); + + list_del_init(&acpi_gpio->deferred_req_irqs_list_entry); } - mutex_unlock(&acpi_gpio_initial_sync_list_lock); + + acpi_gpio_deferred_req_irqs_done = true; + mutex_unlock(&acpi_gpio_deferred_req_irqs_lock); return 0; } /* We must use _sync so that this runs after the first deferred_probe run */ -late_initcall_sync(acpi_gpio_initial_sync); +late_initcall_sync(acpi_gpio_handle_deferred_request_interrupts); diff --git a/drivers/gpio/gpiolib-of.c b/drivers/gpio/gpiolib-of.c index a4f1157d6aa0..d4e7a09598fa 100644 --- a/drivers/gpio/gpiolib-of.c +++ b/drivers/gpio/gpiolib-of.c @@ -31,6 +31,7 @@ static int of_gpiochip_match_node_and_xlate(struct gpio_chip *chip, void *data) struct of_phandle_args *gpiospec = data; return chip->gpiodev->dev.of_node == gpiospec->np && + chip->of_xlate && chip->of_xlate(chip, gpiospec, NULL) >= 0; } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c index f8bbbb3a9504..0c791e35acf0 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c @@ -272,7 +272,7 @@ void amdgpu_amdkfd_gpu_reset(struct kgd_dev *kgd) int alloc_gtt_mem(struct kgd_dev *kgd, size_t size, void **mem_obj, uint64_t *gpu_addr, - void **cpu_ptr) + void **cpu_ptr, bool mqd_gfx9) { struct amdgpu_device *adev = (struct amdgpu_device *)kgd; struct amdgpu_bo *bo = NULL; @@ -287,6 +287,10 @@ int alloc_gtt_mem(struct kgd_dev *kgd, size_t size, bp.flags = AMDGPU_GEM_CREATE_CPU_GTT_USWC; bp.type = ttm_bo_type_kernel; bp.resv = NULL; + + if (mqd_gfx9) + bp.flags |= AMDGPU_GEM_CREATE_MQD_GFX9; + r = amdgpu_bo_create(adev, &bp, &bo); if (r) { dev_err(adev->dev, diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h index 2f379c183ed2..cc9aeab5468c 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h @@ -136,7 +136,7 @@ void amdgpu_amdkfd_gpu_reset(struct kgd_dev *kgd); /* Shared API */ int alloc_gtt_mem(struct kgd_dev *kgd, size_t size, void **mem_obj, uint64_t *gpu_addr, - void **cpu_ptr); + void **cpu_ptr, bool mqd_gfx9); void free_gtt_mem(struct kgd_dev *kgd, void *mem_obj); void get_local_mem_info(struct kgd_dev *kgd, struct kfd_local_mem_info *mem_info); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v7.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v7.c index ea3f698aef5e..9803b91f3e77 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v7.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v7.c @@ -685,7 +685,7 @@ static int kgd_hqd_sdma_destroy(struct kgd_dev *kgd, void *mqd, while (true) { temp = RREG32(sdma_base_addr + mmSDMA0_RLC0_CONTEXT_STATUS); - if (temp & SDMA0_STATUS_REG__RB_CMD_IDLE__SHIFT) + if (temp & SDMA0_RLC0_CONTEXT_STATUS__IDLE_MASK) break; if (time_after(jiffies, end_jiffies)) return -ETIME; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cgs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cgs.c index 693ec5ea4950..8816c697b205 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cgs.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cgs.c @@ -367,12 +367,14 @@ static int amdgpu_cgs_get_firmware_info(struct cgs_device *cgs_device, break; case CHIP_POLARIS10: if (type == CGS_UCODE_ID_SMU) { - if ((adev->pdev->device == 0x67df) && - ((adev->pdev->revision == 0xe0) || - (adev->pdev->revision == 0xe3) || - (adev->pdev->revision == 0xe4) || - (adev->pdev->revision == 0xe5) || - (adev->pdev->revision == 0xe7) || + if (((adev->pdev->device == 0x67df) && + ((adev->pdev->revision == 0xe0) || + (adev->pdev->revision == 0xe3) || + (adev->pdev->revision == 0xe4) || + (adev->pdev->revision == 0xe5) || + (adev->pdev->revision == 0xe7) || + (adev->pdev->revision == 0xef))) || + ((adev->pdev->device == 0x6fdf) && (adev->pdev->revision == 0xef))) { info->is_kicker = true; strcpy(fw_name, "amdgpu/polaris10_k_smc.bin"); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c index b6e9df11115d..b31d121a876b 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c @@ -39,6 +39,7 @@ static int amdgpu_cs_user_fence_chunk(struct amdgpu_cs_parser *p, { struct drm_gem_object *gobj; unsigned long size; + int r; gobj = drm_gem_object_lookup(p->filp, data->handle); if (gobj == NULL) @@ -50,20 +51,26 @@ static int amdgpu_cs_user_fence_chunk(struct amdgpu_cs_parser *p, p->uf_entry.tv.shared = true; p->uf_entry.user_pages = NULL; - size = amdgpu_bo_size(p->uf_entry.robj); - if (size != PAGE_SIZE || (data->offset + 8) > size) - return -EINVAL; - - *offset = data->offset; - drm_gem_object_put_unlocked(gobj); + size = amdgpu_bo_size(p->uf_entry.robj); + if (size != PAGE_SIZE || (data->offset + 8) > size) { + r = -EINVAL; + goto error_unref; + } + if (amdgpu_ttm_tt_get_usermm(p->uf_entry.robj->tbo.ttm)) { - amdgpu_bo_unref(&p->uf_entry.robj); - return -EINVAL; + r = -EINVAL; + goto error_unref; } + *offset = data->offset; + return 0; + +error_unref: + amdgpu_bo_unref(&p->uf_entry.robj); + return r; } static int amdgpu_cs_bo_handles_chunk(struct amdgpu_cs_parser *p, @@ -1262,10 +1269,10 @@ static int amdgpu_cs_submit(struct amdgpu_cs_parser *p, error_abort: dma_fence_put(&job->base.s_fence->finished); job->base.s_fence = NULL; + amdgpu_mn_unlock(p->mn); error_unlock: amdgpu_job_free(job); - amdgpu_mn_unlock(p->mn); return r; } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c index 8ab5ccbc14ac..39bf2ce548c6 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c @@ -2063,6 +2063,7 @@ static int amdgpu_device_ip_reinit_early_sriov(struct amdgpu_device *adev) static enum amd_ip_block_type ip_order[] = { AMD_IP_BLOCK_TYPE_GMC, AMD_IP_BLOCK_TYPE_COMMON, + AMD_IP_BLOCK_TYPE_PSP, AMD_IP_BLOCK_TYPE_IH, }; @@ -2093,7 +2094,6 @@ static int amdgpu_device_ip_reinit_late_sriov(struct amdgpu_device *adev) static enum amd_ip_block_type ip_order[] = { AMD_IP_BLOCK_TYPE_SMC, - AMD_IP_BLOCK_TYPE_PSP, AMD_IP_BLOCK_TYPE_DCE, AMD_IP_BLOCK_TYPE_GFX, AMD_IP_BLOCK_TYPE_SDMA, diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c index 8843a06360fa..0f41d8647376 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c @@ -740,6 +740,7 @@ static const struct pci_device_id pciidlist[] = { {0x1002, 0x67CA, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_POLARIS10}, {0x1002, 0x67CC, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_POLARIS10}, {0x1002, 0x67CF, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_POLARIS10}, + {0x1002, 0x6FDF, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_POLARIS10}, /* Polaris12 */ {0x1002, 0x6980, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_POLARIS12}, {0x1002, 0x6981, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_POLARIS12}, diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c b/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c index e7ca4623cfb9..7c3b634d8d5f 100644 --- a/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c +++ b/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c @@ -70,6 +70,7 @@ static const struct soc15_reg_golden golden_settings_sdma_4[] = { SOC15_REG_GOLDEN_VALUE(SDMA0, 0, mmSDMA0_RLC1_IB_CNTL, 0x800f0100, 0x00000100), SOC15_REG_GOLDEN_VALUE(SDMA0, 0, mmSDMA0_RLC1_RB_WPTR_POLL_CNTL, 0x0000fff0, 0x00403000), SOC15_REG_GOLDEN_VALUE(SDMA0, 0, mmSDMA0_UTCL1_PAGE, 0x000003ff, 0x000003c0), + SOC15_REG_GOLDEN_VALUE(SDMA0, 0, mmSDMA0_UTCL1_WATERMK, 0xfc000000, 0x00000000), SOC15_REG_GOLDEN_VALUE(SDMA1, 0, mmSDMA1_CHICKEN_BITS, 0xfe931f07, 0x02831f07), SOC15_REG_GOLDEN_VALUE(SDMA1, 0, mmSDMA1_CLK_CTRL, 0xffffffff, 0x3f000100), SOC15_REG_GOLDEN_VALUE(SDMA1, 0, mmSDMA1_GFX_IB_CNTL, 0x800f0100, 0x00000100), @@ -81,7 +82,8 @@ static const struct soc15_reg_golden golden_settings_sdma_4[] = { SOC15_REG_GOLDEN_VALUE(SDMA1, 0, mmSDMA1_RLC0_RB_WPTR_POLL_CNTL, 0x0000fff0, 0x00403000), SOC15_REG_GOLDEN_VALUE(SDMA1, 0, mmSDMA1_RLC1_IB_CNTL, 0x800f0100, 0x00000100), SOC15_REG_GOLDEN_VALUE(SDMA1, 0, mmSDMA1_RLC1_RB_WPTR_POLL_CNTL, 0x0000fff0, 0x00403000), - SOC15_REG_GOLDEN_VALUE(SDMA1, 0, mmSDMA1_UTCL1_PAGE, 0x000003ff, 0x000003c0) + SOC15_REG_GOLDEN_VALUE(SDMA1, 0, mmSDMA1_UTCL1_PAGE, 0x000003ff, 0x000003c0), + SOC15_REG_GOLDEN_VALUE(SDMA1, 0, mmSDMA1_UTCL1_WATERMK, 0xfc000000, 0x00000000) }; static const struct soc15_reg_golden golden_settings_sdma_vg10[] = { @@ -109,7 +111,8 @@ static const struct soc15_reg_golden golden_settings_sdma_4_1[] = SOC15_REG_GOLDEN_VALUE(SDMA0, 0, mmSDMA0_RLC0_RB_WPTR_POLL_CNTL, 0xfffffff7, 0x00403000), SOC15_REG_GOLDEN_VALUE(SDMA0, 0, mmSDMA0_RLC1_IB_CNTL, 0x800f0111, 0x00000100), SOC15_REG_GOLDEN_VALUE(SDMA0, 0, mmSDMA0_RLC1_RB_WPTR_POLL_CNTL, 0xfffffff7, 0x00403000), - SOC15_REG_GOLDEN_VALUE(SDMA0, 0, mmSDMA0_UTCL1_PAGE, 0x000003ff, 0x000003c0) + SOC15_REG_GOLDEN_VALUE(SDMA0, 0, mmSDMA0_UTCL1_PAGE, 0x000003ff, 0x000003c0), + SOC15_REG_GOLDEN_VALUE(SDMA0, 0, mmSDMA0_UTCL1_WATERMK, 0xfc000000, 0x00000000) }; static const struct soc15_reg_golden golden_settings_sdma_4_2[] = diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device.c b/drivers/gpu/drm/amd/amdkfd/kfd_device.c index 1b048715ab8a..29ac74f40dce 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_device.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_device.c @@ -457,7 +457,8 @@ bool kgd2kfd_device_init(struct kfd_dev *kfd, if (kfd->kfd2kgd->init_gtt_mem_allocation( kfd->kgd, size, &kfd->gtt_mem, - &kfd->gtt_start_gpu_addr, &kfd->gtt_start_cpu_ptr)){ + &kfd->gtt_start_gpu_addr, &kfd->gtt_start_cpu_ptr, + false)) { dev_err(kfd_device, "Could not allocate %d bytes\n", size); goto out; } diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_iommu.c b/drivers/gpu/drm/amd/amdkfd/kfd_iommu.c index 7a61f38c09e6..01494752c36a 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_iommu.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_iommu.c @@ -62,9 +62,20 @@ int kfd_iommu_device_init(struct kfd_dev *kfd) struct amd_iommu_device_info iommu_info; unsigned int pasid_limit; int err; + struct kfd_topology_device *top_dev; - if (!kfd->device_info->needs_iommu_device) + top_dev = kfd_topology_device_by_id(kfd->id); + + /* + * Overwrite ATS capability according to needs_iommu_device to fix + * potential missing corresponding bit in CRAT of BIOS. + */ + if (!kfd->device_info->needs_iommu_device) { + top_dev->node_props.capability &= ~HSA_CAP_ATS_PRESENT; return 0; + } + + top_dev->node_props.capability |= HSA_CAP_ATS_PRESENT; iommu_info.flags = 0; err = amd_iommu_device_info(kfd->pdev, &iommu_info); diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v9.c b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v9.c index f5fc3675f21e..0cedb37cf513 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v9.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v9.c @@ -88,7 +88,7 @@ static int init_mqd(struct mqd_manager *mm, void **mqd, ALIGN(sizeof(struct v9_mqd), PAGE_SIZE), &((*mqd_mem_obj)->gtt_mem), &((*mqd_mem_obj)->gpu_addr), - (void *)&((*mqd_mem_obj)->cpu_ptr)); + (void *)&((*mqd_mem_obj)->cpu_ptr), true); } else retval = kfd_gtt_sa_allocate(mm->dev, sizeof(struct v9_mqd), mqd_mem_obj); diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h index f971710f1c91..92b285ca73aa 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h +++ b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h @@ -806,6 +806,7 @@ int kfd_topology_add_device(struct kfd_dev *gpu); int kfd_topology_remove_device(struct kfd_dev *gpu); struct kfd_topology_device *kfd_topology_device_by_proximity_domain( uint32_t proximity_domain); +struct kfd_topology_device *kfd_topology_device_by_id(uint32_t gpu_id); struct kfd_dev *kfd_device_by_id(uint32_t gpu_id); struct kfd_dev *kfd_device_by_pci_dev(const struct pci_dev *pdev); int kfd_topology_enum_kfd_devices(uint8_t idx, struct kfd_dev **kdev); diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_topology.c b/drivers/gpu/drm/amd/amdkfd/kfd_topology.c index bc95d4dfee2e..80f5db4ef75f 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_topology.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_topology.c @@ -63,22 +63,33 @@ struct kfd_topology_device *kfd_topology_device_by_proximity_domain( return device; } -struct kfd_dev *kfd_device_by_id(uint32_t gpu_id) +struct kfd_topology_device *kfd_topology_device_by_id(uint32_t gpu_id) { - struct kfd_topology_device *top_dev; - struct kfd_dev *device = NULL; + struct kfd_topology_device *top_dev = NULL; + struct kfd_topology_device *ret = NULL; down_read(&topology_lock); list_for_each_entry(top_dev, &topology_device_list, list) if (top_dev->gpu_id == gpu_id) { - device = top_dev->gpu; + ret = top_dev; break; } up_read(&topology_lock); - return device; + return ret; +} + +struct kfd_dev *kfd_device_by_id(uint32_t gpu_id) +{ + struct kfd_topology_device *top_dev; + + top_dev = kfd_topology_device_by_id(gpu_id); + if (!top_dev) + return NULL; + + return top_dev->gpu; } struct kfd_dev *kfd_device_by_pci_dev(const struct pci_dev *pdev) diff --git a/drivers/gpu/drm/amd/include/kgd_kfd_interface.h b/drivers/gpu/drm/amd/include/kgd_kfd_interface.h index 14391b06080c..43b82e14007e 100644 --- a/drivers/gpu/drm/amd/include/kgd_kfd_interface.h +++ b/drivers/gpu/drm/amd/include/kgd_kfd_interface.h @@ -292,7 +292,7 @@ struct tile_config { struct kfd2kgd_calls { int (*init_gtt_mem_allocation)(struct kgd_dev *kgd, size_t size, void **mem_obj, uint64_t *gpu_addr, - void **cpu_ptr); + void **cpu_ptr, bool mqd_gfx9); void (*free_gtt_mem)(struct kgd_dev *kgd, void *mem_obj); diff --git a/drivers/gpu/drm/drm_atomic.c b/drivers/gpu/drm/drm_atomic.c index 3eb061e11e2e..018fcdb353d2 100644 --- a/drivers/gpu/drm/drm_atomic.c +++ b/drivers/gpu/drm/drm_atomic.c @@ -2067,7 +2067,7 @@ static void __drm_state_dump(struct drm_device *dev, struct drm_printer *p, struct drm_connector *connector; struct drm_connector_list_iter conn_iter; - if (!drm_core_check_feature(dev, DRIVER_ATOMIC)) + if (!drm_drv_uses_atomic_modeset(dev)) return; list_for_each_entry(plane, &config->plane_list, head) { diff --git a/drivers/gpu/drm/drm_debugfs.c b/drivers/gpu/drm/drm_debugfs.c index 6f28fe58f169..373bd4c2b698 100644 --- a/drivers/gpu/drm/drm_debugfs.c +++ b/drivers/gpu/drm/drm_debugfs.c @@ -151,7 +151,7 @@ int drm_debugfs_init(struct drm_minor *minor, int minor_id, return ret; } - if (drm_core_check_feature(dev, DRIVER_ATOMIC)) { + if (drm_drv_uses_atomic_modeset(dev)) { ret = drm_atomic_debugfs_init(minor); if (ret) { DRM_ERROR("Failed to create atomic debugfs files\n"); diff --git a/drivers/gpu/drm/drm_fb_helper.c b/drivers/gpu/drm/drm_fb_helper.c index 4b0dd20bccb8..16ec93b75dbf 100644 --- a/drivers/gpu/drm/drm_fb_helper.c +++ b/drivers/gpu/drm/drm_fb_helper.c @@ -2370,7 +2370,6 @@ static int drm_pick_crtcs(struct drm_fb_helper *fb_helper, { int c, o; struct drm_connector *connector; - const struct drm_connector_helper_funcs *connector_funcs; int my_score, best_score, score; struct drm_fb_helper_crtc **crtcs, *crtc; struct drm_fb_helper_connector *fb_helper_conn; @@ -2399,8 +2398,6 @@ static int drm_pick_crtcs(struct drm_fb_helper *fb_helper, if (drm_has_preferred_mode(fb_helper_conn, width, height)) my_score++; - connector_funcs = connector->helper_private; - /* * select a crtc for this connector and then attempt to configure * remaining connectors diff --git a/drivers/gpu/drm/i915/gvt/dmabuf.c b/drivers/gpu/drm/i915/gvt/dmabuf.c index 6e3f56684f4e..51ed99a37803 100644 --- a/drivers/gpu/drm/i915/gvt/dmabuf.c +++ b/drivers/gpu/drm/i915/gvt/dmabuf.c @@ -170,20 +170,22 @@ static struct drm_i915_gem_object *vgpu_create_gem(struct drm_device *dev, unsigned int tiling_mode = 0; unsigned int stride = 0; - switch (info->drm_format_mod << 10) { - case PLANE_CTL_TILED_LINEAR: + switch (info->drm_format_mod) { + case DRM_FORMAT_MOD_LINEAR: tiling_mode = I915_TILING_NONE; break; - case PLANE_CTL_TILED_X: + case I915_FORMAT_MOD_X_TILED: tiling_mode = I915_TILING_X; stride = info->stride; break; - case PLANE_CTL_TILED_Y: + case I915_FORMAT_MOD_Y_TILED: + case I915_FORMAT_MOD_Yf_TILED: tiling_mode = I915_TILING_Y; stride = info->stride; break; default: - gvt_dbg_core("not supported tiling mode\n"); + gvt_dbg_core("invalid drm_format_mod %llx for tiling\n", + info->drm_format_mod); } obj->tiling_and_stride = tiling_mode | stride; } else { @@ -222,9 +224,26 @@ static int vgpu_get_plane_info(struct drm_device *dev, info->height = p.height; info->stride = p.stride; info->drm_format = p.drm_format; - info->drm_format_mod = p.tiled; + + switch (p.tiled) { + case PLANE_CTL_TILED_LINEAR: + info->drm_format_mod = DRM_FORMAT_MOD_LINEAR; + break; + case PLANE_CTL_TILED_X: + info->drm_format_mod = I915_FORMAT_MOD_X_TILED; + break; + case PLANE_CTL_TILED_Y: + info->drm_format_mod = I915_FORMAT_MOD_Y_TILED; + break; + case PLANE_CTL_TILED_YF: + info->drm_format_mod = I915_FORMAT_MOD_Yf_TILED; + break; + default: + gvt_vgpu_err("invalid tiling mode: %x\n", p.tiled); + } + info->size = (((p.stride * p.height * p.bpp) / 8) + - (PAGE_SIZE - 1)) >> PAGE_SHIFT; + (PAGE_SIZE - 1)) >> PAGE_SHIFT; } else if (plane_id == DRM_PLANE_TYPE_CURSOR) { ret = intel_vgpu_decode_cursor_plane(vgpu, &c); if (ret) diff --git a/drivers/gpu/drm/i915/gvt/fb_decoder.c b/drivers/gpu/drm/i915/gvt/fb_decoder.c index face664be3e8..481896fb712a 100644 --- a/drivers/gpu/drm/i915/gvt/fb_decoder.c +++ b/drivers/gpu/drm/i915/gvt/fb_decoder.c @@ -220,8 +220,7 @@ int intel_vgpu_decode_primary_plane(struct intel_vgpu *vgpu, if (IS_SKYLAKE(dev_priv) || IS_KABYLAKE(dev_priv) || IS_BROXTON(dev_priv)) { - plane->tiled = (val & PLANE_CTL_TILED_MASK) >> - _PLANE_CTL_TILED_SHIFT; + plane->tiled = val & PLANE_CTL_TILED_MASK; fmt = skl_format_to_drm( val & PLANE_CTL_FORMAT_MASK, val & PLANE_CTL_ORDER_RGBX, @@ -260,7 +259,7 @@ int intel_vgpu_decode_primary_plane(struct intel_vgpu *vgpu, return -EINVAL; } - plane->stride = intel_vgpu_get_stride(vgpu, pipe, (plane->tiled << 10), + plane->stride = intel_vgpu_get_stride(vgpu, pipe, plane->tiled, (IS_SKYLAKE(dev_priv) || IS_KABYLAKE(dev_priv) || IS_BROXTON(dev_priv)) ? diff --git a/drivers/gpu/drm/i915/gvt/fb_decoder.h b/drivers/gpu/drm/i915/gvt/fb_decoder.h index cb055f3c81a2..60c155085029 100644 --- a/drivers/gpu/drm/i915/gvt/fb_decoder.h +++ b/drivers/gpu/drm/i915/gvt/fb_decoder.h @@ -101,7 +101,7 @@ struct intel_gvt; /* color space conversion and gamma correction are not included */ struct intel_vgpu_primary_plane_format { u8 enabled; /* plane is enabled */ - u8 tiled; /* X-tiled */ + u32 tiled; /* tiling mode: linear, X-tiled, Y tiled, etc */ u8 bpp; /* bits per pixel */ u32 hw_format; /* format field in the PRI_CTL register */ u32 drm_format; /* format in DRM definition */ diff --git a/drivers/gpu/drm/i915/gvt/handlers.c b/drivers/gpu/drm/i915/gvt/handlers.c index 7a58ca555197..94c1089ecf59 100644 --- a/drivers/gpu/drm/i915/gvt/handlers.c +++ b/drivers/gpu/drm/i915/gvt/handlers.c @@ -1296,6 +1296,19 @@ static int power_well_ctl_mmio_write(struct intel_vgpu *vgpu, return 0; } +static int gen9_dbuf_ctl_mmio_write(struct intel_vgpu *vgpu, + unsigned int offset, void *p_data, unsigned int bytes) +{ + write_vreg(vgpu, offset, p_data, bytes); + + if (vgpu_vreg(vgpu, offset) & DBUF_POWER_REQUEST) + vgpu_vreg(vgpu, offset) |= DBUF_POWER_STATE; + else + vgpu_vreg(vgpu, offset) &= ~DBUF_POWER_STATE; + + return 0; +} + static int fpga_dbg_mmio_write(struct intel_vgpu *vgpu, unsigned int offset, void *p_data, unsigned int bytes) { @@ -1525,9 +1538,15 @@ static int bxt_phy_ctl_family_write(struct intel_vgpu *vgpu, u32 v = *(u32 *)p_data; u32 data = v & COMMON_RESET_DIS ? BXT_PHY_LANE_ENABLED : 0; - vgpu_vreg(vgpu, _BXT_PHY_CTL_DDI_A) = data; - vgpu_vreg(vgpu, _BXT_PHY_CTL_DDI_B) = data; - vgpu_vreg(vgpu, _BXT_PHY_CTL_DDI_C) = data; + switch (offset) { + case _PHY_CTL_FAMILY_EDP: + vgpu_vreg(vgpu, _BXT_PHY_CTL_DDI_A) = data; + break; + case _PHY_CTL_FAMILY_DDI: + vgpu_vreg(vgpu, _BXT_PHY_CTL_DDI_B) = data; + vgpu_vreg(vgpu, _BXT_PHY_CTL_DDI_C) = data; + break; + } vgpu_vreg(vgpu, offset) = v; @@ -2812,6 +2831,8 @@ static int init_skl_mmio_info(struct intel_gvt *gvt) MMIO_DH(HSW_PWR_WELL_CTL_DRIVER(SKL_DISP_PW_MISC_IO), D_SKL_PLUS, NULL, skl_power_well_ctl_write); + MMIO_DH(DBUF_CTL, D_SKL_PLUS, NULL, gen9_dbuf_ctl_mmio_write); + MMIO_D(_MMIO(0xa210), D_SKL_PLUS); MMIO_D(GEN9_MEDIA_PG_IDLE_HYSTERESIS, D_SKL_PLUS); MMIO_D(GEN9_RENDER_PG_IDLE_HYSTERESIS, D_SKL_PLUS); @@ -2987,8 +3008,6 @@ static int init_skl_mmio_info(struct intel_gvt *gvt) NULL, gen9_trtte_write); MMIO_DH(_MMIO(0x4dfc), D_SKL_PLUS, NULL, gen9_trtt_chicken_write); - MMIO_D(_MMIO(0x45008), D_SKL_PLUS); - MMIO_D(_MMIO(0x46430), D_SKL_PLUS); MMIO_D(_MMIO(0x46520), D_SKL_PLUS); @@ -3025,7 +3044,9 @@ static int init_skl_mmio_info(struct intel_gvt *gvt) MMIO_D(_MMIO(0x44500), D_SKL_PLUS); MMIO_DFH(GEN9_CSFE_CHICKEN1_RCS, D_SKL_PLUS, F_CMD_ACCESS, NULL, NULL); MMIO_DFH(GEN8_HDC_CHICKEN1, D_SKL_PLUS, F_MODE_MASK | F_CMD_ACCESS, - NULL, NULL); + NULL, NULL); + MMIO_DFH(GEN9_WM_CHICKEN3, D_SKL_PLUS, F_MODE_MASK | F_CMD_ACCESS, + NULL, NULL); MMIO_D(_MMIO(0x4ab8), D_KBL); MMIO_D(_MMIO(0x2248), D_KBL | D_SKL); @@ -3189,6 +3210,7 @@ static int init_bxt_mmio_info(struct intel_gvt *gvt) MMIO_D(BXT_DSI_PLL_ENABLE, D_BXT); MMIO_D(GEN9_CLKGATE_DIS_0, D_BXT); + MMIO_D(GEN9_CLKGATE_DIS_4, D_BXT); MMIO_D(HSW_TVIDEO_DIP_GCP(TRANSCODER_A), D_BXT); MMIO_D(HSW_TVIDEO_DIP_GCP(TRANSCODER_B), D_BXT); diff --git a/drivers/gpu/drm/i915/gvt/kvmgt.c b/drivers/gpu/drm/i915/gvt/kvmgt.c index a45f46d8537f..9ad89e38f6c0 100644 --- a/drivers/gpu/drm/i915/gvt/kvmgt.c +++ b/drivers/gpu/drm/i915/gvt/kvmgt.c @@ -32,6 +32,7 @@ #include <linux/device.h> #include <linux/mm.h> #include <linux/mmu_context.h> +#include <linux/sched/mm.h> #include <linux/types.h> #include <linux/list.h> #include <linux/rbtree.h> @@ -1792,16 +1793,21 @@ static int kvmgt_rw_gpa(unsigned long handle, unsigned long gpa, info = (struct kvmgt_guest_info *)handle; kvm = info->kvm; - if (kthread) + if (kthread) { + if (!mmget_not_zero(kvm->mm)) + return -EFAULT; use_mm(kvm->mm); + } idx = srcu_read_lock(&kvm->srcu); ret = write ? kvm_write_guest(kvm, gpa, buf, len) : kvm_read_guest(kvm, gpa, buf, len); srcu_read_unlock(&kvm->srcu, idx); - if (kthread) + if (kthread) { unuse_mm(kvm->mm); + mmput(kvm->mm); + } return ret; } @@ -1827,6 +1833,8 @@ static bool kvmgt_is_valid_gfn(unsigned long handle, unsigned long gfn) { struct kvmgt_guest_info *info; struct kvm *kvm; + int idx; + bool ret; if (!handle_valid(handle)) return false; @@ -1834,8 +1842,11 @@ static bool kvmgt_is_valid_gfn(unsigned long handle, unsigned long gfn) info = (struct kvmgt_guest_info *)handle; kvm = info->kvm; - return kvm_is_visible_gfn(kvm, gfn); + idx = srcu_read_lock(&kvm->srcu); + ret = kvm_is_visible_gfn(kvm, gfn); + srcu_read_unlock(&kvm->srcu, idx); + return ret; } struct intel_gvt_mpt kvmgt_mpt = { diff --git a/drivers/gpu/drm/i915/gvt/mmio.c b/drivers/gpu/drm/i915/gvt/mmio.c index 994366035364..9bb9a85c992c 100644 --- a/drivers/gpu/drm/i915/gvt/mmio.c +++ b/drivers/gpu/drm/i915/gvt/mmio.c @@ -244,6 +244,34 @@ void intel_vgpu_reset_mmio(struct intel_vgpu *vgpu, bool dmlr) /* set the bit 0:2(Core C-State ) to C0 */ vgpu_vreg_t(vgpu, GEN6_GT_CORE_STATUS) = 0; + + if (IS_BROXTON(vgpu->gvt->dev_priv)) { + vgpu_vreg_t(vgpu, BXT_P_CR_GT_DISP_PWRON) &= + ~(BIT(0) | BIT(1)); + vgpu_vreg_t(vgpu, BXT_PORT_CL1CM_DW0(DPIO_PHY0)) &= + ~PHY_POWER_GOOD; + vgpu_vreg_t(vgpu, BXT_PORT_CL1CM_DW0(DPIO_PHY1)) &= + ~PHY_POWER_GOOD; + vgpu_vreg_t(vgpu, BXT_PHY_CTL_FAMILY(DPIO_PHY0)) &= + ~BIT(30); + vgpu_vreg_t(vgpu, BXT_PHY_CTL_FAMILY(DPIO_PHY1)) &= + ~BIT(30); + vgpu_vreg_t(vgpu, BXT_PHY_CTL(PORT_A)) &= + ~BXT_PHY_LANE_ENABLED; + vgpu_vreg_t(vgpu, BXT_PHY_CTL(PORT_A)) |= + BXT_PHY_CMNLANE_POWERDOWN_ACK | + BXT_PHY_LANE_POWERDOWN_ACK; + vgpu_vreg_t(vgpu, BXT_PHY_CTL(PORT_B)) &= + ~BXT_PHY_LANE_ENABLED; + vgpu_vreg_t(vgpu, BXT_PHY_CTL(PORT_B)) |= + BXT_PHY_CMNLANE_POWERDOWN_ACK | + BXT_PHY_LANE_POWERDOWN_ACK; + vgpu_vreg_t(vgpu, BXT_PHY_CTL(PORT_C)) &= + ~BXT_PHY_LANE_ENABLED; + vgpu_vreg_t(vgpu, BXT_PHY_CTL(PORT_C)) |= + BXT_PHY_CMNLANE_POWERDOWN_ACK | + BXT_PHY_LANE_POWERDOWN_ACK; + } } else { #define GVT_GEN8_MMIO_RESET_OFFSET (0x44200) /* only reset the engine related, so starting with 0x44200 diff --git a/drivers/gpu/drm/i915/gvt/mmio_context.c b/drivers/gpu/drm/i915/gvt/mmio_context.c index 42e1e6bdcc2c..e872f4847fbe 100644 --- a/drivers/gpu/drm/i915/gvt/mmio_context.c +++ b/drivers/gpu/drm/i915/gvt/mmio_context.c @@ -562,11 +562,9 @@ void intel_gvt_switch_mmio(struct intel_vgpu *pre, * performace for batch mmio read/write, so we need * handle forcewake mannually. */ - intel_runtime_pm_get(dev_priv); intel_uncore_forcewake_get(dev_priv, FORCEWAKE_ALL); switch_mmio(pre, next, ring_id); intel_uncore_forcewake_put(dev_priv, FORCEWAKE_ALL); - intel_runtime_pm_put(dev_priv); } /** diff --git a/drivers/gpu/drm/i915/gvt/opregion.c b/drivers/gpu/drm/i915/gvt/opregion.c index fa75a2eead90..b0d3a43ccd03 100644 --- a/drivers/gpu/drm/i915/gvt/opregion.c +++ b/drivers/gpu/drm/i915/gvt/opregion.c @@ -42,8 +42,6 @@ #define DEVICE_TYPE_EFP3 0x20 #define DEVICE_TYPE_EFP4 0x10 -#define DEV_SIZE 38 - struct opregion_header { u8 signature[16]; u32 size; @@ -63,6 +61,10 @@ struct bdb_data_header { u16 size; /* data size */ } __packed; +/* For supporting windows guest with opregion, here hardcode the emulated + * bdb header version as '186', and the corresponding child_device_config + * length should be '33' but not '38'. + */ struct efp_child_device_config { u16 handle; u16 device_type; @@ -109,12 +111,6 @@ struct efp_child_device_config { u8 mipi_bridge_type; /* 171 */ u16 device_class_ext; u8 dvo_function; - u8 dp_usb_type_c:1; /* 195 */ - u8 skip6:7; - u8 dp_usb_type_c_2x_gpio_index; /* 195 */ - u16 dp_usb_type_c_2x_gpio_pin; /* 195 */ - u8 iboost_dp:4; /* 196 */ - u8 iboost_hdmi:4; /* 196 */ } __packed; struct vbt { @@ -155,7 +151,7 @@ static void virt_vbt_generation(struct vbt *v) v->header.bdb_offset = offsetof(struct vbt, bdb_header); strcpy(&v->bdb_header.signature[0], "BIOS_DATA_BLOCK"); - v->bdb_header.version = 186; /* child_dev_size = 38 */ + v->bdb_header.version = 186; /* child_dev_size = 33 */ v->bdb_header.header_size = sizeof(v->bdb_header); v->bdb_header.bdb_size = sizeof(struct vbt) - sizeof(struct vbt_header) @@ -169,11 +165,13 @@ static void virt_vbt_generation(struct vbt *v) /* child device */ num_child = 4; /* each port has one child */ + v->general_definitions.child_dev_size = + sizeof(struct efp_child_device_config); v->general_definitions_header.id = BDB_GENERAL_DEFINITIONS; /* size will include child devices */ v->general_definitions_header.size = - sizeof(struct bdb_general_definitions) + num_child * DEV_SIZE; - v->general_definitions.child_dev_size = DEV_SIZE; + sizeof(struct bdb_general_definitions) + + num_child * v->general_definitions.child_dev_size; /* portA */ v->child0.handle = DEVICE_TYPE_EFP1; diff --git a/drivers/gpu/drm/i915/gvt/sched_policy.c b/drivers/gpu/drm/i915/gvt/sched_policy.c index 09d7bb72b4ff..c32e7d5e8629 100644 --- a/drivers/gpu/drm/i915/gvt/sched_policy.c +++ b/drivers/gpu/drm/i915/gvt/sched_policy.c @@ -47,11 +47,15 @@ static bool vgpu_has_pending_workload(struct intel_vgpu *vgpu) return false; } +/* We give 2 seconds higher prio for vGPU during start */ +#define GVT_SCHED_VGPU_PRI_TIME 2 + struct vgpu_sched_data { struct list_head lru_list; struct intel_vgpu *vgpu; bool active; - + bool pri_sched; + ktime_t pri_time; ktime_t sched_in_time; ktime_t sched_time; ktime_t left_ts; @@ -183,6 +187,14 @@ static struct intel_vgpu *find_busy_vgpu(struct gvt_sched_data *sched_data) if (!vgpu_has_pending_workload(vgpu_data->vgpu)) continue; + if (vgpu_data->pri_sched) { + if (ktime_before(ktime_get(), vgpu_data->pri_time)) { + vgpu = vgpu_data->vgpu; + break; + } else + vgpu_data->pri_sched = false; + } + /* Return the vGPU only if it has time slice left */ if (vgpu_data->left_ts > 0) { vgpu = vgpu_data->vgpu; @@ -202,6 +214,7 @@ static void tbs_sched_func(struct gvt_sched_data *sched_data) struct intel_gvt_workload_scheduler *scheduler = &gvt->scheduler; struct vgpu_sched_data *vgpu_data; struct intel_vgpu *vgpu = NULL; + /* no active vgpu or has already had a target */ if (list_empty(&sched_data->lru_runq_head) || scheduler->next_vgpu) goto out; @@ -209,12 +222,13 @@ static void tbs_sched_func(struct gvt_sched_data *sched_data) vgpu = find_busy_vgpu(sched_data); if (vgpu) { scheduler->next_vgpu = vgpu; - - /* Move the last used vGPU to the tail of lru_list */ vgpu_data = vgpu->sched_data; - list_del_init(&vgpu_data->lru_list); - list_add_tail(&vgpu_data->lru_list, - &sched_data->lru_runq_head); + if (!vgpu_data->pri_sched) { + /* Move the last used vGPU to the tail of lru_list */ + list_del_init(&vgpu_data->lru_list); + list_add_tail(&vgpu_data->lru_list, + &sched_data->lru_runq_head); + } } else { scheduler->next_vgpu = gvt->idle_vgpu; } @@ -328,11 +342,17 @@ static void tbs_sched_start_schedule(struct intel_vgpu *vgpu) { struct gvt_sched_data *sched_data = vgpu->gvt->scheduler.sched_data; struct vgpu_sched_data *vgpu_data = vgpu->sched_data; + ktime_t now; if (!list_empty(&vgpu_data->lru_list)) return; - list_add_tail(&vgpu_data->lru_list, &sched_data->lru_runq_head); + now = ktime_get(); + vgpu_data->pri_time = ktime_add(now, + ktime_set(GVT_SCHED_VGPU_PRI_TIME, 0)); + vgpu_data->pri_sched = true; + + list_add(&vgpu_data->lru_list, &sched_data->lru_runq_head); if (!hrtimer_active(&sched_data->timer)) hrtimer_start(&sched_data->timer, ktime_add_ns(ktime_get(), @@ -426,6 +446,7 @@ void intel_vgpu_stop_schedule(struct intel_vgpu *vgpu) &vgpu->gvt->scheduler; int ring_id; struct vgpu_sched_data *vgpu_data = vgpu->sched_data; + struct drm_i915_private *dev_priv = vgpu->gvt->dev_priv; if (!vgpu_data->active) return; @@ -444,6 +465,7 @@ void intel_vgpu_stop_schedule(struct intel_vgpu *vgpu) scheduler->current_vgpu = NULL; } + intel_runtime_pm_get(dev_priv); spin_lock_bh(&scheduler->mmio_context_lock); for (ring_id = 0; ring_id < I915_NUM_ENGINES; ring_id++) { if (scheduler->engine_owner[ring_id] == vgpu) { @@ -452,5 +474,6 @@ void intel_vgpu_stop_schedule(struct intel_vgpu *vgpu) } } spin_unlock_bh(&scheduler->mmio_context_lock); + intel_runtime_pm_put(dev_priv); mutex_unlock(&vgpu->gvt->sched_lock); } diff --git a/drivers/gpu/drm/i915/gvt/vgpu.c b/drivers/gpu/drm/i915/gvt/vgpu.c index a4e8e3cf74fd..c628be05fbfe 100644 --- a/drivers/gpu/drm/i915/gvt/vgpu.c +++ b/drivers/gpu/drm/i915/gvt/vgpu.c @@ -281,6 +281,7 @@ void intel_gvt_destroy_vgpu(struct intel_vgpu *vgpu) intel_vgpu_clean_submission(vgpu); intel_vgpu_clean_display(vgpu); intel_vgpu_clean_opregion(vgpu); + intel_vgpu_reset_ggtt(vgpu, true); intel_vgpu_clean_gtt(vgpu); intel_gvt_hypervisor_detach_vgpu(vgpu); intel_vgpu_free_resource(vgpu); diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h index 08ec7446282e..9e63cd47b60f 100644 --- a/drivers/gpu/drm/i915/i915_reg.h +++ b/drivers/gpu/drm/i915/i915_reg.h @@ -10422,7 +10422,7 @@ enum skl_power_gate { _ICL_DSC0_PICTURE_PARAMETER_SET_4_PB, \ _ICL_DSC0_PICTURE_PARAMETER_SET_4_PC) #define ICL_DSC1_PICTURE_PARAMETER_SET_4(pipe) _MMIO_PIPE((pipe) - PIPE_B, \ - _ICL_DSC0_PICTURE_PARAMETER_SET_4_PB, \ + _ICL_DSC1_PICTURE_PARAMETER_SET_4_PB, \ _ICL_DSC1_PICTURE_PARAMETER_SET_4_PC) #define DSC_INITIAL_DEC_DELAY(dec_delay) ((dec_delay) << 16) #define DSC_INITIAL_XMIT_DELAY(xmit_delay) ((xmit_delay) << 0) @@ -10437,7 +10437,7 @@ enum skl_power_gate { _ICL_DSC0_PICTURE_PARAMETER_SET_5_PB, \ _ICL_DSC0_PICTURE_PARAMETER_SET_5_PC) #define ICL_DSC1_PICTURE_PARAMETER_SET_5(pipe) _MMIO_PIPE((pipe) - PIPE_B, \ - _ICL_DSC1_PICTURE_PARAMETER_SET_5_PC, \ + _ICL_DSC1_PICTURE_PARAMETER_SET_5_PB, \ _ICL_DSC1_PICTURE_PARAMETER_SET_5_PC) #define DSC_SCALE_DEC_INTINT(scale_dec) ((scale_dec) << 16) #define DSC_SCALE_INC_INT(scale_inc) ((scale_inc) << 0) diff --git a/drivers/gpu/drm/i915/intel_ddi.c b/drivers/gpu/drm/i915/intel_ddi.c index 8761513f3532..c9af34861d9e 100644 --- a/drivers/gpu/drm/i915/intel_ddi.c +++ b/drivers/gpu/drm/i915/intel_ddi.c @@ -2708,7 +2708,8 @@ static void intel_ddi_pre_enable_dp(struct intel_encoder *encoder, if (port != PORT_A || INTEL_GEN(dev_priv) >= 9) intel_dp_stop_link_train(intel_dp); - intel_ddi_enable_pipe_clock(crtc_state); + if (!is_mst) + intel_ddi_enable_pipe_clock(crtc_state); } static void intel_ddi_pre_enable_hdmi(struct intel_encoder *encoder, @@ -2810,14 +2811,14 @@ static void intel_ddi_post_disable_dp(struct intel_encoder *encoder, bool is_mst = intel_crtc_has_type(old_crtc_state, INTEL_OUTPUT_DP_MST); - intel_ddi_disable_pipe_clock(old_crtc_state); - - /* - * Power down sink before disabling the port, otherwise we end - * up getting interrupts from the sink on detecting link loss. - */ - if (!is_mst) + if (!is_mst) { + intel_ddi_disable_pipe_clock(old_crtc_state); + /* + * Power down sink before disabling the port, otherwise we end + * up getting interrupts from the sink on detecting link loss. + */ intel_dp_sink_dpms(intel_dp, DRM_MODE_DPMS_OFF); + } intel_disable_ddi_buf(encoder); diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c index 4a3c8ee9a973..d2951096bca0 100644 --- a/drivers/gpu/drm/i915/intel_display.c +++ b/drivers/gpu/drm/i915/intel_display.c @@ -5079,10 +5079,14 @@ void hsw_disable_ips(const struct intel_crtc_state *crtc_state) mutex_lock(&dev_priv->pcu_lock); WARN_ON(sandybridge_pcode_write(dev_priv, DISPLAY_IPS_CONTROL, 0)); mutex_unlock(&dev_priv->pcu_lock); - /* wait for pcode to finish disabling IPS, which may take up to 42ms */ + /* + * Wait for PCODE to finish disabling IPS. The BSpec specified + * 42ms timeout value leads to occasional timeouts so use 100ms + * instead. + */ if (intel_wait_for_register(dev_priv, IPS_CTL, IPS_ENABLE, 0, - 42)) + 100)) DRM_ERROR("Timed out waiting for IPS disable\n"); } else { I915_WRITE(IPS_CTL, 0); diff --git a/drivers/gpu/drm/i915/intel_dp.c b/drivers/gpu/drm/i915/intel_dp.c index cd0f649b57a5..1193202766a2 100644 --- a/drivers/gpu/drm/i915/intel_dp.c +++ b/drivers/gpu/drm/i915/intel_dp.c @@ -4160,18 +4160,6 @@ intel_dp_needs_link_retrain(struct intel_dp *intel_dp) return !drm_dp_channel_eq_ok(link_status, intel_dp->lane_count); } -/* - * If display is now connected check links status, - * there has been known issues of link loss triggering - * long pulse. - * - * Some sinks (eg. ASUS PB287Q) seem to perform some - * weird HPD ping pong during modesets. So we can apparently - * end up with HPD going low during a modeset, and then - * going back up soon after. And once that happens we must - * retrain the link to get a picture. That's in case no - * userspace component reacted to intermittent HPD dip. - */ int intel_dp_retrain_link(struct intel_encoder *encoder, struct drm_modeset_acquire_ctx *ctx) { @@ -4661,7 +4649,8 @@ intel_dp_unset_edid(struct intel_dp *intel_dp) } static int -intel_dp_long_pulse(struct intel_connector *connector) +intel_dp_long_pulse(struct intel_connector *connector, + struct drm_modeset_acquire_ctx *ctx) { struct drm_i915_private *dev_priv = to_i915(connector->base.dev); struct intel_dp *intel_dp = intel_attached_dp(&connector->base); @@ -4720,6 +4709,22 @@ intel_dp_long_pulse(struct intel_connector *connector) */ status = connector_status_disconnected; goto out; + } else { + /* + * If display is now connected check links status, + * there has been known issues of link loss triggering + * long pulse. + * + * Some sinks (eg. ASUS PB287Q) seem to perform some + * weird HPD ping pong during modesets. So we can apparently + * end up with HPD going low during a modeset, and then + * going back up soon after. And once that happens we must + * retrain the link to get a picture. That's in case no + * userspace component reacted to intermittent HPD dip. + */ + struct intel_encoder *encoder = &dp_to_dig_port(intel_dp)->base; + + intel_dp_retrain_link(encoder, ctx); } /* @@ -4781,7 +4786,7 @@ intel_dp_detect(struct drm_connector *connector, return ret; } - status = intel_dp_long_pulse(intel_dp->attached_connector); + status = intel_dp_long_pulse(intel_dp->attached_connector, ctx); } intel_dp->detect_done = false; diff --git a/drivers/gpu/drm/i915/intel_dp_mst.c b/drivers/gpu/drm/i915/intel_dp_mst.c index 7e3e01607643..4ecd65375603 100644 --- a/drivers/gpu/drm/i915/intel_dp_mst.c +++ b/drivers/gpu/drm/i915/intel_dp_mst.c @@ -166,6 +166,8 @@ static void intel_mst_post_disable_dp(struct intel_encoder *encoder, struct intel_connector *connector = to_intel_connector(old_conn_state->connector); + intel_ddi_disable_pipe_clock(old_crtc_state); + /* this can fail */ drm_dp_check_act_status(&intel_dp->mst_mgr); /* and this can also fail */ @@ -252,6 +254,8 @@ static void intel_mst_pre_enable_dp(struct intel_encoder *encoder, I915_WRITE(DP_TP_STATUS(port), temp); ret = drm_dp_update_payload_part1(&intel_dp->mst_mgr); + + intel_ddi_enable_pipe_clock(pipe_config); } static void intel_mst_enable_dp(struct intel_encoder *encoder, diff --git a/drivers/gpu/drm/i915/intel_overlay.c b/drivers/gpu/drm/i915/intel_overlay.c index c2f10d899329..443dfaefd7a6 100644 --- a/drivers/gpu/drm/i915/intel_overlay.c +++ b/drivers/gpu/drm/i915/intel_overlay.c @@ -181,8 +181,9 @@ struct intel_overlay { u32 brightness, contrast, saturation; u32 old_xscale, old_yscale; /* register access */ - u32 flip_addr; struct drm_i915_gem_object *reg_bo; + struct overlay_registers __iomem *regs; + u32 flip_addr; /* flip handling */ struct i915_gem_active last_flip; }; @@ -210,29 +211,6 @@ static void i830_overlay_clock_gating(struct drm_i915_private *dev_priv, PCI_DEVFN(0, 0), I830_CLOCK_GATE, val); } -static struct overlay_registers __iomem * -intel_overlay_map_regs(struct intel_overlay *overlay) -{ - struct drm_i915_private *dev_priv = overlay->i915; - struct overlay_registers __iomem *regs; - - if (OVERLAY_NEEDS_PHYSICAL(dev_priv)) - regs = (struct overlay_registers __iomem *)overlay->reg_bo->phys_handle->vaddr; - else - regs = io_mapping_map_wc(&dev_priv->ggtt.iomap, - overlay->flip_addr, - PAGE_SIZE); - - return regs; -} - -static void intel_overlay_unmap_regs(struct intel_overlay *overlay, - struct overlay_registers __iomem *regs) -{ - if (!OVERLAY_NEEDS_PHYSICAL(overlay->i915)) - io_mapping_unmap(regs); -} - static void intel_overlay_submit_request(struct intel_overlay *overlay, struct i915_request *rq, i915_gem_retire_fn retire) @@ -784,13 +762,13 @@ static int intel_overlay_do_put_image(struct intel_overlay *overlay, struct drm_i915_gem_object *new_bo, struct put_image_params *params) { - int ret, tmp_width; - struct overlay_registers __iomem *regs; - bool scale_changed = false; + struct overlay_registers __iomem *regs = overlay->regs; struct drm_i915_private *dev_priv = overlay->i915; u32 swidth, swidthsw, sheight, ostride; enum pipe pipe = overlay->crtc->pipe; + bool scale_changed = false; struct i915_vma *vma; + int ret, tmp_width; lockdep_assert_held(&dev_priv->drm.struct_mutex); WARN_ON(!drm_modeset_is_locked(&dev_priv->drm.mode_config.connection_mutex)); @@ -815,30 +793,19 @@ static int intel_overlay_do_put_image(struct intel_overlay *overlay, if (!overlay->active) { u32 oconfig; - regs = intel_overlay_map_regs(overlay); - if (!regs) { - ret = -ENOMEM; - goto out_unpin; - } + oconfig = OCONF_CC_OUT_8BIT; if (IS_GEN4(dev_priv)) oconfig |= OCONF_CSC_MODE_BT709; oconfig |= pipe == 0 ? OCONF_PIPE_A : OCONF_PIPE_B; iowrite32(oconfig, ®s->OCONFIG); - intel_overlay_unmap_regs(overlay, regs); ret = intel_overlay_on(overlay); if (ret != 0) goto out_unpin; } - regs = intel_overlay_map_regs(overlay); - if (!regs) { - ret = -ENOMEM; - goto out_unpin; - } - iowrite32((params->dst_y << 16) | params->dst_x, ®s->DWINPOS); iowrite32((params->dst_h << 16) | params->dst_w, ®s->DWINSZ); @@ -882,8 +849,6 @@ static int intel_overlay_do_put_image(struct intel_overlay *overlay, iowrite32(overlay_cmd_reg(params), ®s->OCMD); - intel_overlay_unmap_regs(overlay, regs); - ret = intel_overlay_continue(overlay, vma, scale_changed); if (ret) goto out_unpin; @@ -901,7 +866,6 @@ out_pin_section: int intel_overlay_switch_off(struct intel_overlay *overlay) { struct drm_i915_private *dev_priv = overlay->i915; - struct overlay_registers __iomem *regs; int ret; lockdep_assert_held(&dev_priv->drm.struct_mutex); @@ -918,9 +882,7 @@ int intel_overlay_switch_off(struct intel_overlay *overlay) if (ret != 0) return ret; - regs = intel_overlay_map_regs(overlay); - iowrite32(0, ®s->OCMD); - intel_overlay_unmap_regs(overlay, regs); + iowrite32(0, &overlay->regs->OCMD); return intel_overlay_off(overlay); } @@ -1305,7 +1267,6 @@ int intel_overlay_attrs_ioctl(struct drm_device *dev, void *data, struct drm_intel_overlay_attrs *attrs = data; struct drm_i915_private *dev_priv = to_i915(dev); struct intel_overlay *overlay; - struct overlay_registers __iomem *regs; int ret; overlay = dev_priv->overlay; @@ -1345,15 +1306,7 @@ int intel_overlay_attrs_ioctl(struct drm_device *dev, void *data, overlay->contrast = attrs->contrast; overlay->saturation = attrs->saturation; - regs = intel_overlay_map_regs(overlay); - if (!regs) { - ret = -ENOMEM; - goto out_unlock; - } - - update_reg_attrs(overlay, regs); - - intel_overlay_unmap_regs(overlay, regs); + update_reg_attrs(overlay, overlay->regs); if (attrs->flags & I915_OVERLAY_UPDATE_GAMMA) { if (IS_GEN2(dev_priv)) @@ -1386,12 +1339,47 @@ out_unlock: return ret; } +static int get_registers(struct intel_overlay *overlay, bool use_phys) +{ + struct drm_i915_gem_object *obj; + struct i915_vma *vma; + int err; + + obj = i915_gem_object_create_stolen(overlay->i915, PAGE_SIZE); + if (obj == NULL) + obj = i915_gem_object_create_internal(overlay->i915, PAGE_SIZE); + if (IS_ERR(obj)) + return PTR_ERR(obj); + + vma = i915_gem_object_ggtt_pin(obj, NULL, 0, 0, PIN_MAPPABLE); + if (IS_ERR(vma)) { + err = PTR_ERR(vma); + goto err_put_bo; + } + + if (use_phys) + overlay->flip_addr = sg_dma_address(obj->mm.pages->sgl); + else + overlay->flip_addr = i915_ggtt_offset(vma); + overlay->regs = i915_vma_pin_iomap(vma); + i915_vma_unpin(vma); + + if (IS_ERR(overlay->regs)) { + err = PTR_ERR(overlay->regs); + goto err_put_bo; + } + + overlay->reg_bo = obj; + return 0; + +err_put_bo: + i915_gem_object_put(obj); + return err; +} + void intel_setup_overlay(struct drm_i915_private *dev_priv) { struct intel_overlay *overlay; - struct drm_i915_gem_object *reg_bo; - struct overlay_registers __iomem *regs; - struct i915_vma *vma = NULL; int ret; if (!HAS_OVERLAY(dev_priv)) @@ -1401,46 +1389,8 @@ void intel_setup_overlay(struct drm_i915_private *dev_priv) if (!overlay) return; - mutex_lock(&dev_priv->drm.struct_mutex); - if (WARN_ON(dev_priv->overlay)) - goto out_free; - overlay->i915 = dev_priv; - reg_bo = NULL; - if (!OVERLAY_NEEDS_PHYSICAL(dev_priv)) - reg_bo = i915_gem_object_create_stolen(dev_priv, PAGE_SIZE); - if (reg_bo == NULL) - reg_bo = i915_gem_object_create(dev_priv, PAGE_SIZE); - if (IS_ERR(reg_bo)) - goto out_free; - overlay->reg_bo = reg_bo; - - if (OVERLAY_NEEDS_PHYSICAL(dev_priv)) { - ret = i915_gem_object_attach_phys(reg_bo, PAGE_SIZE); - if (ret) { - DRM_ERROR("failed to attach phys overlay regs\n"); - goto out_free_bo; - } - overlay->flip_addr = reg_bo->phys_handle->busaddr; - } else { - vma = i915_gem_object_ggtt_pin(reg_bo, NULL, - 0, PAGE_SIZE, PIN_MAPPABLE); - if (IS_ERR(vma)) { - DRM_ERROR("failed to pin overlay register bo\n"); - ret = PTR_ERR(vma); - goto out_free_bo; - } - overlay->flip_addr = i915_ggtt_offset(vma); - - ret = i915_gem_object_set_to_gtt_domain(reg_bo, true); - if (ret) { - DRM_ERROR("failed to move overlay register bo into the GTT\n"); - goto out_unpin_bo; - } - } - - /* init all values */ overlay->color_key = 0x0101fe; overlay->color_key_enabled = true; overlay->brightness = -19; @@ -1449,44 +1399,51 @@ void intel_setup_overlay(struct drm_i915_private *dev_priv) init_request_active(&overlay->last_flip, NULL); - regs = intel_overlay_map_regs(overlay); - if (!regs) - goto out_unpin_bo; + mutex_lock(&dev_priv->drm.struct_mutex); + + ret = get_registers(overlay, OVERLAY_NEEDS_PHYSICAL(dev_priv)); + if (ret) + goto out_free; + + ret = i915_gem_object_set_to_gtt_domain(overlay->reg_bo, true); + if (ret) + goto out_reg_bo; - memset_io(regs, 0, sizeof(struct overlay_registers)); - update_polyphase_filter(regs); - update_reg_attrs(overlay, regs); + mutex_unlock(&dev_priv->drm.struct_mutex); - intel_overlay_unmap_regs(overlay, regs); + memset_io(overlay->regs, 0, sizeof(struct overlay_registers)); + update_polyphase_filter(overlay->regs); + update_reg_attrs(overlay, overlay->regs); dev_priv->overlay = overlay; - mutex_unlock(&dev_priv->drm.struct_mutex); - DRM_INFO("initialized overlay support\n"); + DRM_INFO("Initialized overlay support.\n"); return; -out_unpin_bo: - if (vma) - i915_vma_unpin(vma); -out_free_bo: - i915_gem_object_put(reg_bo); +out_reg_bo: + i915_gem_object_put(overlay->reg_bo); out_free: mutex_unlock(&dev_priv->drm.struct_mutex); kfree(overlay); - return; } void intel_cleanup_overlay(struct drm_i915_private *dev_priv) { - if (!dev_priv->overlay) + struct intel_overlay *overlay; + + overlay = fetch_and_zero(&dev_priv->overlay); + if (!overlay) return; - /* The bo's should be free'd by the generic code already. + /* + * The bo's should be free'd by the generic code already. * Furthermore modesetting teardown happens beforehand so the - * hardware should be off already */ - WARN_ON(dev_priv->overlay->active); + * hardware should be off already. + */ + WARN_ON(overlay->active); + + i915_gem_object_put(overlay->reg_bo); - i915_gem_object_put(dev_priv->overlay->reg_bo); - kfree(dev_priv->overlay); + kfree(overlay); } #if IS_ENABLED(CONFIG_DRM_I915_CAPTURE_ERROR) @@ -1498,37 +1455,11 @@ struct intel_overlay_error_state { u32 isr; }; -static struct overlay_registers __iomem * -intel_overlay_map_regs_atomic(struct intel_overlay *overlay) -{ - struct drm_i915_private *dev_priv = overlay->i915; - struct overlay_registers __iomem *regs; - - if (OVERLAY_NEEDS_PHYSICAL(dev_priv)) - /* Cast to make sparse happy, but it's wc memory anyway, so - * equivalent to the wc io mapping on X86. */ - regs = (struct overlay_registers __iomem *) - overlay->reg_bo->phys_handle->vaddr; - else - regs = io_mapping_map_atomic_wc(&dev_priv->ggtt.iomap, - overlay->flip_addr); - - return regs; -} - -static void intel_overlay_unmap_regs_atomic(struct intel_overlay *overlay, - struct overlay_registers __iomem *regs) -{ - if (!OVERLAY_NEEDS_PHYSICAL(overlay->i915)) - io_mapping_unmap_atomic(regs); -} - struct intel_overlay_error_state * intel_overlay_capture_error_state(struct drm_i915_private *dev_priv) { struct intel_overlay *overlay = dev_priv->overlay; struct intel_overlay_error_state *error; - struct overlay_registers __iomem *regs; if (!overlay || !overlay->active) return NULL; @@ -1541,18 +1472,9 @@ intel_overlay_capture_error_state(struct drm_i915_private *dev_priv) error->isr = I915_READ(ISR); error->base = overlay->flip_addr; - regs = intel_overlay_map_regs_atomic(overlay); - if (!regs) - goto err; - - memcpy_fromio(&error->regs, regs, sizeof(struct overlay_registers)); - intel_overlay_unmap_regs_atomic(overlay, regs); + memcpy_fromio(&error->regs, overlay->regs, sizeof(error->regs)); return error; - -err: - kfree(error); - return NULL; } void diff --git a/drivers/gpu/drm/nouveau/dispnv50/disp.c b/drivers/gpu/drm/nouveau/dispnv50/disp.c index 8412119bd940..5691dfa1db6f 100644 --- a/drivers/gpu/drm/nouveau/dispnv50/disp.c +++ b/drivers/gpu/drm/nouveau/dispnv50/disp.c @@ -1123,17 +1123,21 @@ nv50_mstm_enable(struct nv50_mstm *mstm, u8 dpcd, int state) int ret; if (dpcd >= 0x12) { - ret = drm_dp_dpcd_readb(mstm->mgr.aux, DP_MSTM_CTRL, &dpcd); + /* Even if we're enabling MST, start with disabling the + * branching unit to clear any sink-side MST topology state + * that wasn't set by us + */ + ret = drm_dp_dpcd_writeb(mstm->mgr.aux, DP_MSTM_CTRL, 0); if (ret < 0) return ret; - dpcd &= ~DP_MST_EN; - if (state) - dpcd |= DP_MST_EN; - - ret = drm_dp_dpcd_writeb(mstm->mgr.aux, DP_MSTM_CTRL, dpcd); - if (ret < 0) - return ret; + if (state) { + /* Now, start initializing */ + ret = drm_dp_dpcd_writeb(mstm->mgr.aux, DP_MSTM_CTRL, + DP_MST_EN); + if (ret < 0) + return ret; + } } return nvif_mthd(disp, 0, &args, sizeof(args)); @@ -1142,31 +1146,58 @@ nv50_mstm_enable(struct nv50_mstm *mstm, u8 dpcd, int state) int nv50_mstm_detect(struct nv50_mstm *mstm, u8 dpcd[8], int allow) { - int ret, state = 0; + struct drm_dp_aux *aux; + int ret; + bool old_state, new_state; + u8 mstm_ctrl; if (!mstm) return 0; - if (dpcd[0] >= 0x12) { - ret = drm_dp_dpcd_readb(mstm->mgr.aux, DP_MSTM_CAP, &dpcd[1]); + mutex_lock(&mstm->mgr.lock); + + old_state = mstm->mgr.mst_state; + new_state = old_state; + aux = mstm->mgr.aux; + + if (old_state) { + /* Just check that the MST hub is still as we expect it */ + ret = drm_dp_dpcd_readb(aux, DP_MSTM_CTRL, &mstm_ctrl); + if (ret < 0 || !(mstm_ctrl & DP_MST_EN)) { + DRM_DEBUG_KMS("Hub gone, disabling MST topology\n"); + new_state = false; + } + } else if (dpcd[0] >= 0x12) { + ret = drm_dp_dpcd_readb(aux, DP_MSTM_CAP, &dpcd[1]); if (ret < 0) - return ret; + goto probe_error; if (!(dpcd[1] & DP_MST_CAP)) dpcd[0] = 0x11; else - state = allow; + new_state = allow; + } + + if (new_state == old_state) { + mutex_unlock(&mstm->mgr.lock); + return new_state; } - ret = nv50_mstm_enable(mstm, dpcd[0], state); + ret = nv50_mstm_enable(mstm, dpcd[0], new_state); if (ret) - return ret; + goto probe_error; + + mutex_unlock(&mstm->mgr.lock); - ret = drm_dp_mst_topology_mgr_set_mst(&mstm->mgr, state); + ret = drm_dp_mst_topology_mgr_set_mst(&mstm->mgr, new_state); if (ret) return nv50_mstm_enable(mstm, dpcd[0], 0); - return mstm->mgr.mst_state; + return new_state; + +probe_error: + mutex_unlock(&mstm->mgr.lock); + return ret; } static void @@ -2074,7 +2105,7 @@ nv50_disp_atomic_state_alloc(struct drm_device *dev) static const struct drm_mode_config_funcs nv50_disp_func = { .fb_create = nouveau_user_framebuffer_create, - .output_poll_changed = drm_fb_helper_output_poll_changed, + .output_poll_changed = nouveau_fbcon_output_poll_changed, .atomic_check = nv50_disp_atomic_check, .atomic_commit = nv50_disp_atomic_commit, .atomic_state_alloc = nv50_disp_atomic_state_alloc, diff --git a/drivers/gpu/drm/nouveau/nouveau_connector.c b/drivers/gpu/drm/nouveau/nouveau_connector.c index 51932c72334e..247f72cc4d10 100644 --- a/drivers/gpu/drm/nouveau/nouveau_connector.c +++ b/drivers/gpu/drm/nouveau/nouveau_connector.c @@ -409,59 +409,45 @@ static struct nouveau_encoder * nouveau_connector_ddc_detect(struct drm_connector *connector) { struct drm_device *dev = connector->dev; - struct nouveau_connector *nv_connector = nouveau_connector(connector); - struct nouveau_drm *drm = nouveau_drm(dev); - struct nvkm_gpio *gpio = nvxx_gpio(&drm->client.device); - struct nouveau_encoder *nv_encoder = NULL; + struct nouveau_encoder *nv_encoder = NULL, *found = NULL; struct drm_encoder *encoder; - int i, panel = -ENODEV; - - /* eDP panels need powering on by us (if the VBIOS doesn't default it - * to on) before doing any AUX channel transactions. LVDS panel power - * is handled by the SOR itself, and not required for LVDS DDC. - */ - if (nv_connector->type == DCB_CONNECTOR_eDP) { - panel = nvkm_gpio_get(gpio, 0, DCB_GPIO_PANEL_POWER, 0xff); - if (panel == 0) { - nvkm_gpio_set(gpio, 0, DCB_GPIO_PANEL_POWER, 0xff, 1); - msleep(300); - } - } + int i, ret; + bool switcheroo_ddc = false; drm_connector_for_each_possible_encoder(connector, encoder, i) { nv_encoder = nouveau_encoder(encoder); - if (nv_encoder->dcb->type == DCB_OUTPUT_DP) { - int ret = nouveau_dp_detect(nv_encoder); + switch (nv_encoder->dcb->type) { + case DCB_OUTPUT_DP: + ret = nouveau_dp_detect(nv_encoder); if (ret == NOUVEAU_DP_MST) return NULL; - if (ret == NOUVEAU_DP_SST) - break; - } else - if ((vga_switcheroo_handler_flags() & - VGA_SWITCHEROO_CAN_SWITCH_DDC) && - nv_encoder->dcb->type == DCB_OUTPUT_LVDS && - nv_encoder->i2c) { - int ret; - vga_switcheroo_lock_ddc(dev->pdev); - ret = nvkm_probe_i2c(nv_encoder->i2c, 0x50); - vga_switcheroo_unlock_ddc(dev->pdev); - if (ret) + else if (ret == NOUVEAU_DP_SST) + found = nv_encoder; + + break; + case DCB_OUTPUT_LVDS: + switcheroo_ddc = !!(vga_switcheroo_handler_flags() & + VGA_SWITCHEROO_CAN_SWITCH_DDC); + /* fall-through */ + default: + if (!nv_encoder->i2c) break; - } else - if (nv_encoder->i2c) { + + if (switcheroo_ddc) + vga_switcheroo_lock_ddc(dev->pdev); if (nvkm_probe_i2c(nv_encoder->i2c, 0x50)) - break; + found = nv_encoder; + if (switcheroo_ddc) + vga_switcheroo_unlock_ddc(dev->pdev); + + break; } + if (found) + break; } - /* eDP panel not detected, restore panel power GPIO to previous - * state to avoid confusing the SOR for other output types. - */ - if (!nv_encoder && panel == 0) - nvkm_gpio_set(gpio, 0, DCB_GPIO_PANEL_POWER, 0xff, panel); - - return nv_encoder; + return found; } static struct nouveau_encoder * @@ -555,12 +541,16 @@ nouveau_connector_detect(struct drm_connector *connector, bool force) nv_connector->edid = NULL; } - /* Outputs are only polled while runtime active, so acquiring a - * runtime PM ref here is unnecessary (and would deadlock upon - * runtime suspend because it waits for polling to finish). + /* Outputs are only polled while runtime active, so resuming the + * device here is unnecessary (and would deadlock upon runtime suspend + * because it waits for polling to finish). We do however, want to + * prevent the autosuspend timer from elapsing during this operation + * if possible. */ - if (!drm_kms_helper_is_poll_worker()) { - ret = pm_runtime_get_sync(connector->dev->dev); + if (drm_kms_helper_is_poll_worker()) { + pm_runtime_get_noresume(dev->dev); + } else { + ret = pm_runtime_get_sync(dev->dev); if (ret < 0 && ret != -EACCES) return conn_status; } @@ -638,10 +628,8 @@ detect_analog: out: - if (!drm_kms_helper_is_poll_worker()) { - pm_runtime_mark_last_busy(connector->dev->dev); - pm_runtime_put_autosuspend(connector->dev->dev); - } + pm_runtime_mark_last_busy(dev->dev); + pm_runtime_put_autosuspend(dev->dev); return conn_status; } @@ -1105,6 +1093,26 @@ nouveau_connector_hotplug(struct nvif_notify *notify) const struct nvif_notify_conn_rep_v0 *rep = notify->data; const char *name = connector->name; struct nouveau_encoder *nv_encoder; + int ret; + + ret = pm_runtime_get(drm->dev->dev); + if (ret == 0) { + /* We can't block here if there's a pending PM request + * running, as we'll deadlock nouveau_display_fini() when it + * calls nvif_put() on our nvif_notify struct. So, simply + * defer the hotplug event until the device finishes resuming + */ + NV_DEBUG(drm, "Deferring HPD on %s until runtime resume\n", + name); + schedule_work(&drm->hpd_work); + + pm_runtime_put_noidle(drm->dev->dev); + return NVIF_NOTIFY_KEEP; + } else if (ret != 1 && ret != -EACCES) { + NV_WARN(drm, "HPD on %s dropped due to RPM failure: %d\n", + name, ret); + return NVIF_NOTIFY_DROP; + } if (rep->mask & NVIF_NOTIFY_CONN_V0_IRQ) { NV_DEBUG(drm, "service %s\n", name); @@ -1122,6 +1130,8 @@ nouveau_connector_hotplug(struct nvif_notify *notify) drm_helper_hpd_irq_event(connector->dev); } + pm_runtime_mark_last_busy(drm->dev->dev); + pm_runtime_put_autosuspend(drm->dev->dev); return NVIF_NOTIFY_KEEP; } diff --git a/drivers/gpu/drm/nouveau/nouveau_display.c b/drivers/gpu/drm/nouveau/nouveau_display.c index 139368b31916..540c0cbbfcee 100644 --- a/drivers/gpu/drm/nouveau/nouveau_display.c +++ b/drivers/gpu/drm/nouveau/nouveau_display.c @@ -293,7 +293,7 @@ nouveau_user_framebuffer_create(struct drm_device *dev, static const struct drm_mode_config_funcs nouveau_mode_config_funcs = { .fb_create = nouveau_user_framebuffer_create, - .output_poll_changed = drm_fb_helper_output_poll_changed, + .output_poll_changed = nouveau_fbcon_output_poll_changed, }; @@ -355,8 +355,6 @@ nouveau_display_hpd_work(struct work_struct *work) pm_runtime_get_sync(drm->dev->dev); drm_helper_hpd_irq_event(drm->dev); - /* enable polling for external displays */ - drm_kms_helper_poll_enable(drm->dev); pm_runtime_mark_last_busy(drm->dev->dev); pm_runtime_put_sync(drm->dev->dev); @@ -379,15 +377,29 @@ nouveau_display_acpi_ntfy(struct notifier_block *nb, unsigned long val, { struct nouveau_drm *drm = container_of(nb, typeof(*drm), acpi_nb); struct acpi_bus_event *info = data; + int ret; if (!strcmp(info->device_class, ACPI_VIDEO_CLASS)) { if (info->type == ACPI_VIDEO_NOTIFY_PROBE) { - /* - * This may be the only indication we receive of a - * connector hotplug on a runtime suspended GPU, - * schedule hpd_work to check. - */ - schedule_work(&drm->hpd_work); + ret = pm_runtime_get(drm->dev->dev); + if (ret == 1 || ret == -EACCES) { + /* If the GPU is already awake, or in a state + * where we can't wake it up, it can handle + * it's own hotplug events. + */ + pm_runtime_put_autosuspend(drm->dev->dev); + } else if (ret == 0) { + /* This may be the only indication we receive + * of a connector hotplug on a runtime + * suspended GPU, schedule hpd_work to check. + */ + NV_DEBUG(drm, "ACPI requested connector reprobe\n"); + schedule_work(&drm->hpd_work); + pm_runtime_put_noidle(drm->dev->dev); + } else { + NV_WARN(drm, "Dropped ACPI reprobe event due to RPM error: %d\n", + ret); + } /* acpi-video should not generate keypresses for this */ return NOTIFY_BAD; @@ -411,6 +423,11 @@ nouveau_display_init(struct drm_device *dev) if (ret) return ret; + /* enable connector detection and polling for connectors without HPD + * support + */ + drm_kms_helper_poll_enable(dev); + /* enable hotplug interrupts */ drm_connector_list_iter_begin(dev, &conn_iter); nouveau_for_each_non_mst_connector_iter(connector, &conn_iter) { @@ -425,7 +442,7 @@ nouveau_display_init(struct drm_device *dev) } void -nouveau_display_fini(struct drm_device *dev, bool suspend) +nouveau_display_fini(struct drm_device *dev, bool suspend, bool runtime) { struct nouveau_display *disp = nouveau_display(dev); struct nouveau_drm *drm = nouveau_drm(dev); @@ -450,6 +467,9 @@ nouveau_display_fini(struct drm_device *dev, bool suspend) } drm_connector_list_iter_end(&conn_iter); + if (!runtime) + cancel_work_sync(&drm->hpd_work); + drm_kms_helper_poll_disable(dev); disp->fini(dev); } @@ -618,11 +638,11 @@ nouveau_display_suspend(struct drm_device *dev, bool runtime) } } - nouveau_display_fini(dev, true); + nouveau_display_fini(dev, true, runtime); return 0; } - nouveau_display_fini(dev, true); + nouveau_display_fini(dev, true, runtime); list_for_each_entry(crtc, &dev->mode_config.crtc_list, head) { struct nouveau_framebuffer *nouveau_fb; diff --git a/drivers/gpu/drm/nouveau/nouveau_display.h b/drivers/gpu/drm/nouveau/nouveau_display.h index 54aa7c3fa42d..ff92b54ce448 100644 --- a/drivers/gpu/drm/nouveau/nouveau_display.h +++ b/drivers/gpu/drm/nouveau/nouveau_display.h @@ -62,7 +62,7 @@ nouveau_display(struct drm_device *dev) int nouveau_display_create(struct drm_device *dev); void nouveau_display_destroy(struct drm_device *dev); int nouveau_display_init(struct drm_device *dev); -void nouveau_display_fini(struct drm_device *dev, bool suspend); +void nouveau_display_fini(struct drm_device *dev, bool suspend, bool runtime); int nouveau_display_suspend(struct drm_device *dev, bool runtime); void nouveau_display_resume(struct drm_device *dev, bool runtime); int nouveau_display_vblank_enable(struct drm_device *, unsigned int); diff --git a/drivers/gpu/drm/nouveau/nouveau_drm.c b/drivers/gpu/drm/nouveau/nouveau_drm.c index c7ec86d6c3c9..74d2283f2c28 100644 --- a/drivers/gpu/drm/nouveau/nouveau_drm.c +++ b/drivers/gpu/drm/nouveau/nouveau_drm.c @@ -230,7 +230,7 @@ nouveau_cli_init(struct nouveau_drm *drm, const char *sname, mutex_unlock(&drm->master.lock); } if (ret) { - NV_ERROR(drm, "Client allocation failed: %d\n", ret); + NV_PRINTK(err, cli, "Client allocation failed: %d\n", ret); goto done; } @@ -240,37 +240,37 @@ nouveau_cli_init(struct nouveau_drm *drm, const char *sname, }, sizeof(struct nv_device_v0), &cli->device); if (ret) { - NV_ERROR(drm, "Device allocation failed: %d\n", ret); + NV_PRINTK(err, cli, "Device allocation failed: %d\n", ret); goto done; } ret = nvif_mclass(&cli->device.object, mmus); if (ret < 0) { - NV_ERROR(drm, "No supported MMU class\n"); + NV_PRINTK(err, cli, "No supported MMU class\n"); goto done; } ret = nvif_mmu_init(&cli->device.object, mmus[ret].oclass, &cli->mmu); if (ret) { - NV_ERROR(drm, "MMU allocation failed: %d\n", ret); + NV_PRINTK(err, cli, "MMU allocation failed: %d\n", ret); goto done; } ret = nvif_mclass(&cli->mmu.object, vmms); if (ret < 0) { - NV_ERROR(drm, "No supported VMM class\n"); + NV_PRINTK(err, cli, "No supported VMM class\n"); goto done; } ret = nouveau_vmm_init(cli, vmms[ret].oclass, &cli->vmm); if (ret) { - NV_ERROR(drm, "VMM allocation failed: %d\n", ret); + NV_PRINTK(err, cli, "VMM allocation failed: %d\n", ret); goto done; } ret = nvif_mclass(&cli->mmu.object, mems); if (ret < 0) { - NV_ERROR(drm, "No supported MEM class\n"); + NV_PRINTK(err, cli, "No supported MEM class\n"); goto done; } @@ -592,10 +592,8 @@ nouveau_drm_load(struct drm_device *dev, unsigned long flags) pm_runtime_allow(dev->dev); pm_runtime_mark_last_busy(dev->dev); pm_runtime_put(dev->dev); - } else { - /* enable polling for external displays */ - drm_kms_helper_poll_enable(dev); } + return 0; fail_dispinit: @@ -629,7 +627,7 @@ nouveau_drm_unload(struct drm_device *dev) nouveau_debugfs_fini(drm); if (dev->mode_config.num_crtc) - nouveau_display_fini(dev, false); + nouveau_display_fini(dev, false, false); nouveau_display_destroy(dev); nouveau_bios_takedown(dev); @@ -835,7 +833,6 @@ nouveau_pmops_runtime_suspend(struct device *dev) return -EBUSY; } - drm_kms_helper_poll_disable(drm_dev); nouveau_switcheroo_optimus_dsm(); ret = nouveau_do_suspend(drm_dev, true); pci_save_state(pdev); diff --git a/drivers/gpu/drm/nouveau/nouveau_fbcon.c b/drivers/gpu/drm/nouveau/nouveau_fbcon.c index 844498c4267c..0f64c0a1d4b3 100644 --- a/drivers/gpu/drm/nouveau/nouveau_fbcon.c +++ b/drivers/gpu/drm/nouveau/nouveau_fbcon.c @@ -466,6 +466,7 @@ nouveau_fbcon_set_suspend_work(struct work_struct *work) console_unlock(); if (state == FBINFO_STATE_RUNNING) { + nouveau_fbcon_hotplug_resume(drm->fbcon); pm_runtime_mark_last_busy(drm->dev->dev); pm_runtime_put_sync(drm->dev->dev); } @@ -487,6 +488,61 @@ nouveau_fbcon_set_suspend(struct drm_device *dev, int state) schedule_work(&drm->fbcon_work); } +void +nouveau_fbcon_output_poll_changed(struct drm_device *dev) +{ + struct nouveau_drm *drm = nouveau_drm(dev); + struct nouveau_fbdev *fbcon = drm->fbcon; + int ret; + + if (!fbcon) + return; + + mutex_lock(&fbcon->hotplug_lock); + + ret = pm_runtime_get(dev->dev); + if (ret == 1 || ret == -EACCES) { + drm_fb_helper_hotplug_event(&fbcon->helper); + + pm_runtime_mark_last_busy(dev->dev); + pm_runtime_put_autosuspend(dev->dev); + } else if (ret == 0) { + /* If the GPU was already in the process of suspending before + * this event happened, then we can't block here as we'll + * deadlock the runtime pmops since they wait for us to + * finish. So, just defer this event for when we runtime + * resume again. It will be handled by fbcon_work. + */ + NV_DEBUG(drm, "fbcon HPD event deferred until runtime resume\n"); + fbcon->hotplug_waiting = true; + pm_runtime_put_noidle(drm->dev->dev); + } else { + DRM_WARN("fbcon HPD event lost due to RPM failure: %d\n", + ret); + } + + mutex_unlock(&fbcon->hotplug_lock); +} + +void +nouveau_fbcon_hotplug_resume(struct nouveau_fbdev *fbcon) +{ + struct nouveau_drm *drm; + + if (!fbcon) + return; + drm = nouveau_drm(fbcon->helper.dev); + + mutex_lock(&fbcon->hotplug_lock); + if (fbcon->hotplug_waiting) { + fbcon->hotplug_waiting = false; + + NV_DEBUG(drm, "Handling deferred fbcon HPD events\n"); + drm_fb_helper_hotplug_event(&fbcon->helper); + } + mutex_unlock(&fbcon->hotplug_lock); +} + int nouveau_fbcon_init(struct drm_device *dev) { @@ -505,6 +561,7 @@ nouveau_fbcon_init(struct drm_device *dev) drm->fbcon = fbcon; INIT_WORK(&drm->fbcon_work, nouveau_fbcon_set_suspend_work); + mutex_init(&fbcon->hotplug_lock); drm_fb_helper_prepare(dev, &fbcon->helper, &nouveau_fbcon_helper_funcs); diff --git a/drivers/gpu/drm/nouveau/nouveau_fbcon.h b/drivers/gpu/drm/nouveau/nouveau_fbcon.h index a6f192ea3fa6..db9d52047ef8 100644 --- a/drivers/gpu/drm/nouveau/nouveau_fbcon.h +++ b/drivers/gpu/drm/nouveau/nouveau_fbcon.h @@ -41,6 +41,9 @@ struct nouveau_fbdev { struct nvif_object gdi; struct nvif_object blit; struct nvif_object twod; + + struct mutex hotplug_lock; + bool hotplug_waiting; }; void nouveau_fbcon_restore(void); @@ -68,6 +71,8 @@ void nouveau_fbcon_set_suspend(struct drm_device *dev, int state); void nouveau_fbcon_accel_save_disable(struct drm_device *dev); void nouveau_fbcon_accel_restore(struct drm_device *dev); +void nouveau_fbcon_output_poll_changed(struct drm_device *dev); +void nouveau_fbcon_hotplug_resume(struct nouveau_fbdev *fbcon); extern int nouveau_nofbaccel; #endif /* __NV50_FBCON_H__ */ diff --git a/drivers/gpu/drm/nouveau/nouveau_vga.c b/drivers/gpu/drm/nouveau/nouveau_vga.c index 3da5a4305aa4..8f1ce4833230 100644 --- a/drivers/gpu/drm/nouveau/nouveau_vga.c +++ b/drivers/gpu/drm/nouveau/nouveau_vga.c @@ -46,12 +46,10 @@ nouveau_switcheroo_set_state(struct pci_dev *pdev, pr_err("VGA switcheroo: switched nouveau on\n"); dev->switch_power_state = DRM_SWITCH_POWER_CHANGING; nouveau_pmops_resume(&pdev->dev); - drm_kms_helper_poll_enable(dev); dev->switch_power_state = DRM_SWITCH_POWER_ON; } else { pr_err("VGA switcheroo: switched nouveau off\n"); dev->switch_power_state = DRM_SWITCH_POWER_CHANGING; - drm_kms_helper_poll_disable(dev); nouveau_switcheroo_optimus_dsm(); nouveau_pmops_suspend(&pdev->dev); dev->switch_power_state = DRM_SWITCH_POWER_OFF; diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/base.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/base.c index 32fa94a9773f..cbd33e87b799 100644 --- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/base.c +++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/base.c @@ -275,6 +275,7 @@ nvkm_disp_oneinit(struct nvkm_engine *engine) struct nvkm_outp *outp, *outt, *pair; struct nvkm_conn *conn; struct nvkm_head *head; + struct nvkm_ior *ior; struct nvbios_connE connE; struct dcb_output dcbE; u8 hpd = 0, ver, hdr; @@ -399,6 +400,19 @@ nvkm_disp_oneinit(struct nvkm_engine *engine) return ret; } + /* Enforce identity-mapped SOR assignment for panels, which have + * certain bits (ie. backlight controls) wired to a specific SOR. + */ + list_for_each_entry(outp, &disp->outp, head) { + if (outp->conn->info.type == DCB_CONNECTOR_LVDS || + outp->conn->info.type == DCB_CONNECTOR_eDP) { + ior = nvkm_ior_find(disp, SOR, ffs(outp->info.or) - 1); + if (!WARN_ON(!ior)) + ior->identity = true; + outp->identity = true; + } + } + i = 0; list_for_each_entry(head, &disp->head, head) i = max(i, head->id + 1); diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/dp.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/dp.c index 7c5bed29ffef..5f301e632599 100644 --- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/dp.c +++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/dp.c @@ -28,6 +28,7 @@ #include <subdev/bios.h> #include <subdev/bios/init.h> +#include <subdev/gpio.h> #include <subdev/i2c.h> #include <nvif/event.h> @@ -412,14 +413,10 @@ nvkm_dp_train(struct nvkm_dp *dp, u32 dataKBps) } static void -nvkm_dp_release(struct nvkm_outp *outp, struct nvkm_ior *ior) +nvkm_dp_disable(struct nvkm_outp *outp, struct nvkm_ior *ior) { struct nvkm_dp *dp = nvkm_dp(outp); - /* Prevent link from being retrained if sink sends an IRQ. */ - atomic_set(&dp->lt.done, 0); - ior->dp.nr = 0; - /* Execute DisableLT script from DP Info Table. */ nvbios_init(&ior->disp->engine.subdev, dp->info.script[4], init.outp = &dp->outp.info; @@ -428,6 +425,16 @@ nvkm_dp_release(struct nvkm_outp *outp, struct nvkm_ior *ior) ); } +static void +nvkm_dp_release(struct nvkm_outp *outp) +{ + struct nvkm_dp *dp = nvkm_dp(outp); + + /* Prevent link from being retrained if sink sends an IRQ. */ + atomic_set(&dp->lt.done, 0); + dp->outp.ior->dp.nr = 0; +} + static int nvkm_dp_acquire(struct nvkm_outp *outp) { @@ -491,7 +498,7 @@ done: return ret; } -static void +static bool nvkm_dp_enable(struct nvkm_dp *dp, bool enable) { struct nvkm_i2c_aux *aux = dp->aux; @@ -505,7 +512,7 @@ nvkm_dp_enable(struct nvkm_dp *dp, bool enable) if (!nvkm_rdaux(aux, DPCD_RC00_DPCD_REV, dp->dpcd, sizeof(dp->dpcd))) - return; + return true; } if (dp->present) { @@ -515,6 +522,7 @@ nvkm_dp_enable(struct nvkm_dp *dp, bool enable) } atomic_set(&dp->lt.done, 0); + return false; } static int @@ -555,9 +563,38 @@ nvkm_dp_fini(struct nvkm_outp *outp) static void nvkm_dp_init(struct nvkm_outp *outp) { + struct nvkm_gpio *gpio = outp->disp->engine.subdev.device->gpio; struct nvkm_dp *dp = nvkm_dp(outp); + nvkm_notify_put(&dp->outp.conn->hpd); - nvkm_dp_enable(dp, true); + + /* eDP panels need powering on by us (if the VBIOS doesn't default it + * to on) before doing any AUX channel transactions. LVDS panel power + * is handled by the SOR itself, and not required for LVDS DDC. + */ + if (dp->outp.conn->info.type == DCB_CONNECTOR_eDP) { + int power = nvkm_gpio_get(gpio, 0, DCB_GPIO_PANEL_POWER, 0xff); + if (power == 0) + nvkm_gpio_set(gpio, 0, DCB_GPIO_PANEL_POWER, 0xff, 1); + + /* We delay here unconditionally, even if already powered, + * because some laptop panels having a significant resume + * delay before the panel begins responding. + * + * This is likely a bit of a hack, but no better idea for + * handling this at the moment. + */ + msleep(300); + + /* If the eDP panel can't be detected, we need to restore + * the panel power GPIO to avoid breaking another output. + */ + if (!nvkm_dp_enable(dp, true) && power == 0) + nvkm_gpio_set(gpio, 0, DCB_GPIO_PANEL_POWER, 0xff, 0); + } else { + nvkm_dp_enable(dp, true); + } + nvkm_notify_get(&dp->hpd); } @@ -576,6 +613,7 @@ nvkm_dp_func = { .fini = nvkm_dp_fini, .acquire = nvkm_dp_acquire, .release = nvkm_dp_release, + .disable = nvkm_dp_disable, }; static int diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/ior.h b/drivers/gpu/drm/nouveau/nvkm/engine/disp/ior.h index e0b4e0c5704e..19911211a12a 100644 --- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/ior.h +++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/ior.h @@ -16,6 +16,7 @@ struct nvkm_ior { char name[8]; struct list_head head; + bool identity; struct nvkm_ior_state { struct nvkm_outp *outp; diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/nv50.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/nv50.c index f89c7b977aa5..def005dd5fda 100644 --- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/nv50.c +++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/nv50.c @@ -501,11 +501,11 @@ nv50_disp_super_2_0(struct nv50_disp *disp, struct nvkm_head *head) nv50_disp_super_ied_off(head, ior, 2); /* If we're shutting down the OR's only active head, execute - * the output path's release function. + * the output path's disable function. */ if (ior->arm.head == (1 << head->id)) { - if ((outp = ior->arm.outp) && outp->func->release) - outp->func->release(outp, ior); + if ((outp = ior->arm.outp) && outp->func->disable) + outp->func->disable(outp, ior); } } diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/outp.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/outp.c index be9e7f8c3b23..c62030c96fba 100644 --- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/outp.c +++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/outp.c @@ -93,6 +93,8 @@ nvkm_outp_release(struct nvkm_outp *outp, u8 user) if (ior) { outp->acquired &= ~user; if (!outp->acquired) { + if (outp->func->release && outp->ior) + outp->func->release(outp); outp->ior->asy.outp = NULL; outp->ior = NULL; } @@ -127,17 +129,26 @@ nvkm_outp_acquire(struct nvkm_outp *outp, u8 user) if (proto == UNKNOWN) return -ENOSYS; + /* Deal with panels requiring identity-mapped SOR assignment. */ + if (outp->identity) { + ior = nvkm_ior_find(outp->disp, SOR, ffs(outp->info.or) - 1); + if (WARN_ON(!ior)) + return -ENOSPC; + return nvkm_outp_acquire_ior(outp, user, ior); + } + /* First preference is to reuse the OR that is currently armed * on HW, if any, in order to prevent unnecessary switching. */ list_for_each_entry(ior, &outp->disp->ior, head) { - if (!ior->asy.outp && ior->arm.outp == outp) + if (!ior->identity && !ior->asy.outp && ior->arm.outp == outp) return nvkm_outp_acquire_ior(outp, user, ior); } /* Failing that, a completely unused OR is the next best thing. */ list_for_each_entry(ior, &outp->disp->ior, head) { - if (!ior->asy.outp && ior->type == type && !ior->arm.outp && + if (!ior->identity && + !ior->asy.outp && ior->type == type && !ior->arm.outp && (ior->func->route.set || ior->id == __ffs(outp->info.or))) return nvkm_outp_acquire_ior(outp, user, ior); } @@ -146,7 +157,7 @@ nvkm_outp_acquire(struct nvkm_outp *outp, u8 user) * but will be released during the next modeset. */ list_for_each_entry(ior, &outp->disp->ior, head) { - if (!ior->asy.outp && ior->type == type && + if (!ior->identity && !ior->asy.outp && ior->type == type && (ior->func->route.set || ior->id == __ffs(outp->info.or))) return nvkm_outp_acquire_ior(outp, user, ior); } @@ -245,7 +256,6 @@ nvkm_outp_ctor(const struct nvkm_outp_func *func, struct nvkm_disp *disp, outp->index = index; outp->info = *dcbE; outp->i2c = nvkm_i2c_bus_find(i2c, dcbE->i2c_index); - outp->or = ffs(outp->info.or) - 1; OUTP_DBG(outp, "type %02x loc %d or %d link %d con %x " "edid %x bus %d head %x", diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/outp.h b/drivers/gpu/drm/nouveau/nvkm/engine/disp/outp.h index ea84d7d5741a..6c8aa5cfed9d 100644 --- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/outp.h +++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/outp.h @@ -13,10 +13,10 @@ struct nvkm_outp { struct dcb_output info; struct nvkm_i2c_bus *i2c; - int or; struct list_head head; struct nvkm_conn *conn; + bool identity; /* Assembly state. */ #define NVKM_OUTP_PRIV 1 @@ -41,7 +41,8 @@ struct nvkm_outp_func { void (*init)(struct nvkm_outp *); void (*fini)(struct nvkm_outp *); int (*acquire)(struct nvkm_outp *); - void (*release)(struct nvkm_outp *, struct nvkm_ior *); + void (*release)(struct nvkm_outp *); + void (*disable)(struct nvkm_outp *, struct nvkm_ior *); }; #define OUTP_MSG(o,l,f,a...) do { \ diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/devinit/gm200.c b/drivers/gpu/drm/nouveau/nvkm/subdev/devinit/gm200.c index b80618e35491..17235e940ca9 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/devinit/gm200.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/devinit/gm200.c @@ -86,10 +86,8 @@ pmu_load(struct nv50_devinit *init, u8 type, bool post, struct nvkm_bios *bios = subdev->device->bios; struct nvbios_pmuR pmu; - if (!nvbios_pmuRm(bios, type, &pmu)) { - nvkm_error(subdev, "VBIOS PMU fuc %02x not found\n", type); + if (!nvbios_pmuRm(bios, type, &pmu)) return -EINVAL; - } if (!post) return 0; @@ -124,29 +122,30 @@ gm200_devinit_post(struct nvkm_devinit *base, bool post) return -EINVAL; } + /* Upload DEVINIT application from VBIOS onto PMU. */ ret = pmu_load(init, 0x04, post, &exec, &args); - if (ret) + if (ret) { + nvkm_error(subdev, "VBIOS PMU/DEVINIT not found\n"); return ret; + } - /* upload first chunk of init data */ + /* Upload tables required by opcodes in boot scripts. */ if (post) { - // devinit tables u32 pmu = pmu_args(init, args + 0x08, 0x08); u32 img = nvbios_rd16(bios, bit_I.offset + 0x14); u32 len = nvbios_rd16(bios, bit_I.offset + 0x16); pmu_data(init, pmu, img, len); } - /* upload second chunk of init data */ + /* Upload boot scripts. */ if (post) { - // devinit boot scripts u32 pmu = pmu_args(init, args + 0x08, 0x10); u32 img = nvbios_rd16(bios, bit_I.offset + 0x18); u32 len = nvbios_rd16(bios, bit_I.offset + 0x1a); pmu_data(init, pmu, img, len); } - /* execute init tables */ + /* Execute DEVINIT. */ if (post) { nvkm_wr32(device, 0x10a040, 0x00005000); pmu_exec(init, exec); @@ -157,8 +156,11 @@ gm200_devinit_post(struct nvkm_devinit *base, bool post) return -ETIMEDOUT; } - /* load and execute some other ucode image (bios therm?) */ - return pmu_load(init, 0x01, post, NULL, NULL); + /* Optional: Execute PRE_OS application on PMU, which should at + * least take care of fans until a full PMU has been loaded. + */ + pmu_load(init, 0x01, post, NULL, NULL); + return 0; } static const struct nvkm_devinit_func diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/mmu/vmm.c b/drivers/gpu/drm/nouveau/nvkm/subdev/mmu/vmm.c index de269eb482dd..7459def78d50 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/mmu/vmm.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/mmu/vmm.c @@ -1423,7 +1423,7 @@ nvkm_vmm_get(struct nvkm_vmm *vmm, u8 page, u64 size, struct nvkm_vma **pvma) void nvkm_vmm_part(struct nvkm_vmm *vmm, struct nvkm_memory *inst) { - if (vmm->func->part && inst) { + if (inst && vmm->func->part) { mutex_lock(&vmm->mutex); vmm->func->part(vmm, inst); mutex_unlock(&vmm->mutex); diff --git a/drivers/gpu/drm/pl111/pl111_vexpress.c b/drivers/gpu/drm/pl111/pl111_vexpress.c index a534b225e31b..5fa0441bb6df 100644 --- a/drivers/gpu/drm/pl111/pl111_vexpress.c +++ b/drivers/gpu/drm/pl111/pl111_vexpress.c @@ -111,7 +111,8 @@ static int vexpress_muxfpga_probe(struct platform_device *pdev) } static const struct of_device_id vexpress_muxfpga_match[] = { - { .compatible = "arm,vexpress-muxfpga", } + { .compatible = "arm,vexpress-muxfpga", }, + {} }; static struct platform_driver vexpress_muxfpga_driver = { diff --git a/drivers/gpu/drm/sun4i/sun4i_drv.c b/drivers/gpu/drm/sun4i/sun4i_drv.c index dd19d674055c..8b0cd08034e0 100644 --- a/drivers/gpu/drm/sun4i/sun4i_drv.c +++ b/drivers/gpu/drm/sun4i/sun4i_drv.c @@ -418,7 +418,6 @@ static const struct of_device_id sun4i_drv_of_table[] = { { .compatible = "allwinner,sun8i-a33-display-engine" }, { .compatible = "allwinner,sun8i-a83t-display-engine" }, { .compatible = "allwinner,sun8i-h3-display-engine" }, - { .compatible = "allwinner,sun8i-r40-display-engine" }, { .compatible = "allwinner,sun8i-v3s-display-engine" }, { .compatible = "allwinner,sun9i-a80-display-engine" }, { } diff --git a/drivers/gpu/drm/sun4i/sun8i_hdmi_phy.c b/drivers/gpu/drm/sun4i/sun8i_hdmi_phy.c index 82502b351aec..a564b5dfe082 100644 --- a/drivers/gpu/drm/sun4i/sun8i_hdmi_phy.c +++ b/drivers/gpu/drm/sun4i/sun8i_hdmi_phy.c @@ -398,7 +398,6 @@ static struct regmap_config sun8i_hdmi_phy_regmap_config = { static const struct sun8i_hdmi_phy_variant sun50i_a64_hdmi_phy = { .has_phy_clk = true, - .has_second_pll = true, .phy_init = &sun8i_hdmi_phy_init_h3, .phy_disable = &sun8i_hdmi_phy_disable_h3, .phy_config = &sun8i_hdmi_phy_config_h3, diff --git a/drivers/gpu/drm/sun4i/sun8i_mixer.c b/drivers/gpu/drm/sun4i/sun8i_mixer.c index fc3713608f78..cb65b0ed53fd 100644 --- a/drivers/gpu/drm/sun4i/sun8i_mixer.c +++ b/drivers/gpu/drm/sun4i/sun8i_mixer.c @@ -545,22 +545,6 @@ static const struct sun8i_mixer_cfg sun8i_h3_mixer0_cfg = { .vi_num = 1, }; -static const struct sun8i_mixer_cfg sun8i_r40_mixer0_cfg = { - .ccsc = 0, - .mod_rate = 297000000, - .scaler_mask = 0xf, - .ui_num = 3, - .vi_num = 1, -}; - -static const struct sun8i_mixer_cfg sun8i_r40_mixer1_cfg = { - .ccsc = 1, - .mod_rate = 297000000, - .scaler_mask = 0x3, - .ui_num = 1, - .vi_num = 1, -}; - static const struct sun8i_mixer_cfg sun8i_v3s_mixer_cfg = { .vi_num = 2, .ui_num = 1, @@ -583,14 +567,6 @@ static const struct of_device_id sun8i_mixer_of_table[] = { .data = &sun8i_h3_mixer0_cfg, }, { - .compatible = "allwinner,sun8i-r40-de2-mixer-0", - .data = &sun8i_r40_mixer0_cfg, - }, - { - .compatible = "allwinner,sun8i-r40-de2-mixer-1", - .data = &sun8i_r40_mixer1_cfg, - }, - { .compatible = "allwinner,sun8i-v3s-de2-mixer", .data = &sun8i_v3s_mixer_cfg, }, diff --git a/drivers/gpu/drm/sun4i/sun8i_tcon_top.c b/drivers/gpu/drm/sun4i/sun8i_tcon_top.c index 55fe398d8290..d5240b777a8f 100644 --- a/drivers/gpu/drm/sun4i/sun8i_tcon_top.c +++ b/drivers/gpu/drm/sun4i/sun8i_tcon_top.c @@ -253,7 +253,6 @@ static int sun8i_tcon_top_remove(struct platform_device *pdev) /* sun4i_drv uses this list to check if a device node is a TCON TOP */ const struct of_device_id sun8i_tcon_top_of_table[] = { - { .compatible = "allwinner,sun8i-r40-tcon-top" }, { /* sentinel */ } }; MODULE_DEVICE_TABLE(of, sun8i_tcon_top_of_table); diff --git a/drivers/gpu/drm/udl/udl_fb.c b/drivers/gpu/drm/udl/udl_fb.c index dbb62f6eb48a..dd9ffded223b 100644 --- a/drivers/gpu/drm/udl/udl_fb.c +++ b/drivers/gpu/drm/udl/udl_fb.c @@ -432,9 +432,11 @@ static void udl_fbdev_destroy(struct drm_device *dev, { drm_fb_helper_unregister_fbi(&ufbdev->helper); drm_fb_helper_fini(&ufbdev->helper); - drm_framebuffer_unregister_private(&ufbdev->ufb.base); - drm_framebuffer_cleanup(&ufbdev->ufb.base); - drm_gem_object_put_unlocked(&ufbdev->ufb.obj->base); + if (ufbdev->ufb.obj) { + drm_framebuffer_unregister_private(&ufbdev->ufb.base); + drm_framebuffer_cleanup(&ufbdev->ufb.base); + drm_gem_object_put_unlocked(&ufbdev->ufb.obj->base); + } } int udl_fbdev_init(struct drm_device *dev) diff --git a/drivers/gpu/drm/vc4/vc4_plane.c b/drivers/gpu/drm/vc4/vc4_plane.c index cfb50fedfa2b..a3275fa66b7b 100644 --- a/drivers/gpu/drm/vc4/vc4_plane.c +++ b/drivers/gpu/drm/vc4/vc4_plane.c @@ -297,6 +297,9 @@ static int vc4_plane_setup_clipping_and_scaling(struct drm_plane_state *state) vc4_state->y_scaling[0] = vc4_get_scaling_mode(vc4_state->src_h[0], vc4_state->crtc_h); + vc4_state->is_unity = (vc4_state->x_scaling[0] == VC4_SCALING_NONE && + vc4_state->y_scaling[0] == VC4_SCALING_NONE); + if (num_planes > 1) { vc4_state->is_yuv = true; @@ -312,24 +315,17 @@ static int vc4_plane_setup_clipping_and_scaling(struct drm_plane_state *state) vc4_get_scaling_mode(vc4_state->src_h[1], vc4_state->crtc_h); - /* YUV conversion requires that scaling be enabled, - * even on a plane that's otherwise 1:1. Choose TPZ - * for simplicity. + /* YUV conversion requires that horizontal scaling be enabled, + * even on a plane that's otherwise 1:1. Looks like only PPF + * works in that case, so let's pick that one. */ - if (vc4_state->x_scaling[0] == VC4_SCALING_NONE) - vc4_state->x_scaling[0] = VC4_SCALING_TPZ; - if (vc4_state->y_scaling[0] == VC4_SCALING_NONE) - vc4_state->y_scaling[0] = VC4_SCALING_TPZ; + if (vc4_state->is_unity) + vc4_state->x_scaling[0] = VC4_SCALING_PPF; } else { vc4_state->x_scaling[1] = VC4_SCALING_NONE; vc4_state->y_scaling[1] = VC4_SCALING_NONE; } - vc4_state->is_unity = (vc4_state->x_scaling[0] == VC4_SCALING_NONE && - vc4_state->y_scaling[0] == VC4_SCALING_NONE && - vc4_state->x_scaling[1] == VC4_SCALING_NONE && - vc4_state->y_scaling[1] == VC4_SCALING_NONE); - /* No configuring scaling on the cursor plane, since it gets non-vblank-synced updates, and scaling requires requires LBM changes which have to be vblank-synced. @@ -672,7 +668,10 @@ static int vc4_plane_mode_set(struct drm_plane *plane, vc4_dlist_write(vc4_state, SCALER_CSC2_ITR_R_601_5); } - if (!vc4_state->is_unity) { + if (vc4_state->x_scaling[0] != VC4_SCALING_NONE || + vc4_state->x_scaling[1] != VC4_SCALING_NONE || + vc4_state->y_scaling[0] != VC4_SCALING_NONE || + vc4_state->y_scaling[1] != VC4_SCALING_NONE) { /* LBM Base Address. */ if (vc4_state->y_scaling[0] != VC4_SCALING_NONE || vc4_state->y_scaling[1] != VC4_SCALING_NONE) { diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c b/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c index 1f134570b759..f0ab6b2313bb 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c @@ -3729,7 +3729,7 @@ int vmw_validate_single_buffer(struct vmw_private *dev_priv, { struct vmw_buffer_object *vbo = container_of(bo, struct vmw_buffer_object, base); - struct ttm_operation_ctx ctx = { interruptible, true }; + struct ttm_operation_ctx ctx = { interruptible, false }; int ret; if (vbo->pin_count > 0) diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c index 23beff5d8e3c..6a712a8d59e9 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c @@ -1512,21 +1512,19 @@ static int vmw_kms_check_display_memory(struct drm_device *dev, struct drm_rect *rects) { struct vmw_private *dev_priv = vmw_priv(dev); - struct drm_mode_config *mode_config = &dev->mode_config; struct drm_rect bounding_box = {0}; u64 total_pixels = 0, pixel_mem, bb_mem; int i; for (i = 0; i < num_rects; i++) { /* - * Currently this check is limiting the topology within max - * texture/screentarget size. This should change in future when - * user-space support multiple fb with topology. + * For STDU only individual screen (screen target) is limited by + * SCREENTARGET_MAX_WIDTH/HEIGHT registers. */ - if (rects[i].x1 < 0 || rects[i].y1 < 0 || - rects[i].x2 > mode_config->max_width || - rects[i].y2 > mode_config->max_height) { - DRM_ERROR("Invalid GUI layout.\n"); + if (dev_priv->active_display_unit == vmw_du_screen_target && + (drm_rect_width(&rects[i]) > dev_priv->stdu_max_width || + drm_rect_height(&rects[i]) > dev_priv->stdu_max_height)) { + DRM_ERROR("Screen size not supported.\n"); return -EINVAL; } @@ -1615,7 +1613,7 @@ static int vmw_kms_check_topology(struct drm_device *dev, struct drm_connector_state *conn_state; struct vmw_connector_state *vmw_conn_state; - if (!new_crtc_state->enable && old_crtc_state->enable) { + if (!new_crtc_state->enable) { rects[i].x1 = 0; rects[i].y1 = 0; rects[i].x2 = 0; @@ -2216,12 +2214,16 @@ int vmw_du_connector_fill_modes(struct drm_connector *connector, if (dev_priv->assume_16bpp) assumed_bpp = 2; + max_width = min(max_width, dev_priv->texture_max_width); + max_height = min(max_height, dev_priv->texture_max_height); + + /* + * For STDU extra limit for a mode on SVGA_REG_SCREENTARGET_MAX_WIDTH/ + * HEIGHT registers. + */ if (dev_priv->active_display_unit == vmw_du_screen_target) { max_width = min(max_width, dev_priv->stdu_max_width); - max_width = min(max_width, dev_priv->texture_max_width); - max_height = min(max_height, dev_priv->stdu_max_height); - max_height = min(max_height, dev_priv->texture_max_height); } /* Add preferred mode */ @@ -2376,6 +2378,7 @@ int vmw_kms_update_layout_ioctl(struct drm_device *dev, void *data, struct drm_file *file_priv) { struct vmw_private *dev_priv = vmw_priv(dev); + struct drm_mode_config *mode_config = &dev->mode_config; struct drm_vmw_update_layout_arg *arg = (struct drm_vmw_update_layout_arg *)data; void __user *user_rects; @@ -2421,6 +2424,21 @@ int vmw_kms_update_layout_ioctl(struct drm_device *dev, void *data, drm_rects[i].y1 = curr_rect.y; drm_rects[i].x2 = curr_rect.x + curr_rect.w; drm_rects[i].y2 = curr_rect.y + curr_rect.h; + + /* + * Currently this check is limiting the topology within + * mode_config->max (which actually is max texture size + * supported by virtual device). This limit is here to address + * window managers that create a big framebuffer for whole + * topology. + */ + if (drm_rects[i].x1 < 0 || drm_rects[i].y1 < 0 || + drm_rects[i].x2 > mode_config->max_width || + drm_rects[i].y2 > mode_config->max_height) { + DRM_ERROR("Invalid GUI layout.\n"); + ret = -EINVAL; + goto out_free; + } } ret = vmw_kms_check_display_memory(dev, arg->num_outputs, drm_rects); diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_stdu.c b/drivers/gpu/drm/vmwgfx/vmwgfx_stdu.c index 93f6b96ca7bb..f30e839f7bfd 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_stdu.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_stdu.c @@ -1600,31 +1600,6 @@ int vmw_kms_stdu_init_display(struct vmw_private *dev_priv) dev_priv->active_display_unit = vmw_du_screen_target; - if (dev_priv->capabilities & SVGA_CAP_3D) { - /* - * For 3D VMs, display (scanout) buffer size is the smaller of - * max texture and max STDU - */ - uint32_t max_width, max_height; - - max_width = min(dev_priv->texture_max_width, - dev_priv->stdu_max_width); - max_height = min(dev_priv->texture_max_height, - dev_priv->stdu_max_height); - - dev->mode_config.max_width = max_width; - dev->mode_config.max_height = max_height; - } else { - /* - * Given various display aspect ratios, there's no way to - * estimate these using prim_bb_mem. So just set these to - * something arbitrarily large and we will reject any layout - * that doesn't fit prim_bb_mem later - */ - dev->mode_config.max_width = 8192; - dev->mode_config.max_height = 8192; - } - vmw_kms_create_implicit_placement_property(dev_priv, false); for (i = 0; i < VMWGFX_NUM_DISPLAY_UNITS; ++i) { diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_surface.c b/drivers/gpu/drm/vmwgfx/vmwgfx_surface.c index e125233e074b..80a01cd4c051 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_surface.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_surface.c @@ -1404,22 +1404,17 @@ int vmw_surface_gb_priv_define(struct drm_device *dev, *srf_out = NULL; if (for_scanout) { - uint32_t max_width, max_height; - if (!svga3dsurface_is_screen_target_format(format)) { DRM_ERROR("Invalid Screen Target surface format."); return -EINVAL; } - max_width = min(dev_priv->texture_max_width, - dev_priv->stdu_max_width); - max_height = min(dev_priv->texture_max_height, - dev_priv->stdu_max_height); - - if (size.width > max_width || size.height > max_height) { + if (size.width > dev_priv->texture_max_width || + size.height > dev_priv->texture_max_height) { DRM_ERROR("%ux%u\n, exceeds max surface size %ux%u", size.width, size.height, - max_width, max_height); + dev_priv->texture_max_width, + dev_priv->texture_max_height); return -EINVAL; } } else { @@ -1495,8 +1490,17 @@ int vmw_surface_gb_priv_define(struct drm_device *dev, if (srf->flags & SVGA3D_SURFACE_BIND_STREAM_OUTPUT) srf->res.backup_size += sizeof(SVGA3dDXSOState); + /* + * Don't set SVGA3D_SURFACE_SCREENTARGET flag for a scanout surface with + * size greater than STDU max width/height. This is really a workaround + * to support creation of big framebuffer requested by some user-space + * for whole topology. That big framebuffer won't really be used for + * binding with screen target as during prepare_fb a separate surface is + * created so it's safe to ignore SVGA3D_SURFACE_SCREENTARGET flag. + */ if (dev_priv->active_display_unit == vmw_du_screen_target && - for_scanout) + for_scanout && size.width <= dev_priv->stdu_max_width && + size.height <= dev_priv->stdu_max_height) srf->flags |= SVGA3D_SURFACE_SCREENTARGET; /* diff --git a/drivers/gpu/vga/vga_switcheroo.c b/drivers/gpu/vga/vga_switcheroo.c index a96bf46bc483..cf2a18571d48 100644 --- a/drivers/gpu/vga/vga_switcheroo.c +++ b/drivers/gpu/vga/vga_switcheroo.c @@ -215,6 +215,8 @@ static void vga_switcheroo_enable(void) return; client->id = ret | ID_BIT_AUDIO; + if (client->ops->gpu_bound) + client->ops->gpu_bound(client->pdev, ret); } vga_switcheroo_debugfs_init(&vgasr_priv); diff --git a/drivers/hid/hid-apple.c b/drivers/hid/hid-apple.c index 25b7bd56ae11..1cb41992aaa1 100644 --- a/drivers/hid/hid-apple.c +++ b/drivers/hid/hid-apple.c @@ -335,7 +335,8 @@ static int apple_input_mapping(struct hid_device *hdev, struct hid_input *hi, struct hid_field *field, struct hid_usage *usage, unsigned long **bit, int *max) { - if (usage->hid == (HID_UP_CUSTOM | 0x0003)) { + if (usage->hid == (HID_UP_CUSTOM | 0x0003) || + usage->hid == (HID_UP_MSVENDOR | 0x0003)) { /* The fn key on Apple USB keyboards */ set_bit(EV_REP, hi->input->evbit); hid_map_usage_clear(hi, usage, bit, max, EV_KEY, KEY_FN); @@ -472,6 +473,12 @@ static const struct hid_device_id apple_devices[] = { .driver_data = APPLE_NUMLOCK_EMULATION | APPLE_HAS_FN }, { HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_MAGIC_KEYBOARD_ANSI), .driver_data = APPLE_HAS_FN }, + { HID_BLUETOOTH_DEVICE(BT_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_MAGIC_KEYBOARD_ANSI), + .driver_data = APPLE_HAS_FN }, + { HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_MAGIC_KEYBOARD_NUMPAD_ANSI), + .driver_data = APPLE_HAS_FN }, + { HID_BLUETOOTH_DEVICE(BT_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_MAGIC_KEYBOARD_NUMPAD_ANSI), + .driver_data = APPLE_HAS_FN }, { HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_WELLSPRING_ANSI), .driver_data = APPLE_HAS_FN }, { HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_WELLSPRING_ISO), diff --git a/drivers/hid/hid-core.c b/drivers/hid/hid-core.c index 3da354af7a0a..44564f61e9cc 100644 --- a/drivers/hid/hid-core.c +++ b/drivers/hid/hid-core.c @@ -1000,7 +1000,7 @@ int hid_open_report(struct hid_device *device) parser = vzalloc(sizeof(struct hid_parser)); if (!parser) { ret = -ENOMEM; - goto err; + goto alloc_err; } parser->device = device; @@ -1039,6 +1039,7 @@ int hid_open_report(struct hid_device *device) hid_err(device, "unbalanced delimiter at end of report description\n"); goto err; } + kfree(parser->collection_stack); vfree(parser); device->status |= HID_STAT_PARSED; return 0; @@ -1047,6 +1048,8 @@ int hid_open_report(struct hid_device *device) hid_err(device, "item fetching failed at offset %d\n", (int)(end - start)); err: + kfree(parser->collection_stack); +alloc_err: vfree(parser); hid_close_report(device); return ret; diff --git a/drivers/hid/hid-ids.h b/drivers/hid/hid-ids.h index 79bdf0c7e351..5146ee029db4 100644 --- a/drivers/hid/hid-ids.h +++ b/drivers/hid/hid-ids.h @@ -88,6 +88,7 @@ #define USB_DEVICE_ID_ANTON_TOUCH_PAD 0x3101 #define USB_VENDOR_ID_APPLE 0x05ac +#define BT_VENDOR_ID_APPLE 0x004c #define USB_DEVICE_ID_APPLE_MIGHTYMOUSE 0x0304 #define USB_DEVICE_ID_APPLE_MAGICMOUSE 0x030d #define USB_DEVICE_ID_APPLE_MAGICTRACKPAD 0x030e @@ -157,6 +158,7 @@ #define USB_DEVICE_ID_APPLE_ALU_WIRELESS_2011_ISO 0x0256 #define USB_DEVICE_ID_APPLE_ALU_WIRELESS_2011_JIS 0x0257 #define USB_DEVICE_ID_APPLE_MAGIC_KEYBOARD_ANSI 0x0267 +#define USB_DEVICE_ID_APPLE_MAGIC_KEYBOARD_NUMPAD_ANSI 0x026c #define USB_DEVICE_ID_APPLE_WELLSPRING8_ANSI 0x0290 #define USB_DEVICE_ID_APPLE_WELLSPRING8_ISO 0x0291 #define USB_DEVICE_ID_APPLE_WELLSPRING8_JIS 0x0292 @@ -528,9 +530,6 @@ #define I2C_VENDOR_ID_HANTICK 0x0911 #define I2C_PRODUCT_ID_HANTICK_5288 0x5288 -#define I2C_VENDOR_ID_RAYD 0x2386 -#define I2C_PRODUCT_ID_RAYD_3118 0x3118 - #define USB_VENDOR_ID_HANWANG 0x0b57 #define USB_DEVICE_ID_HANWANG_TABLET_FIRST 0x5000 #define USB_DEVICE_ID_HANWANG_TABLET_LAST 0x8fff @@ -950,6 +949,7 @@ #define USB_DEVICE_ID_SAITEK_RUMBLEPAD 0xff17 #define USB_DEVICE_ID_SAITEK_PS1000 0x0621 #define USB_DEVICE_ID_SAITEK_RAT7_OLD 0x0ccb +#define USB_DEVICE_ID_SAITEK_RAT7_CONTAGION 0x0ccd #define USB_DEVICE_ID_SAITEK_RAT7 0x0cd7 #define USB_DEVICE_ID_SAITEK_RAT9 0x0cfa #define USB_DEVICE_ID_SAITEK_MMO7 0x0cd0 diff --git a/drivers/hid/hid-input.c b/drivers/hid/hid-input.c index 4e94ea3e280a..a481eaf39e88 100644 --- a/drivers/hid/hid-input.c +++ b/drivers/hid/hid-input.c @@ -1582,6 +1582,7 @@ static struct hid_input *hidinput_allocate(struct hid_device *hid, input_dev->dev.parent = &hid->dev; hidinput->input = input_dev; + hidinput->application = application; list_add_tail(&hidinput->list, &hid->inputs); INIT_LIST_HEAD(&hidinput->reports); @@ -1677,8 +1678,7 @@ static struct hid_input *hidinput_match_application(struct hid_report *report) struct hid_input *hidinput; list_for_each_entry(hidinput, &hid->inputs, list) { - if (hidinput->report && - hidinput->report->application == report->application) + if (hidinput->application == report->application) return hidinput; } @@ -1815,6 +1815,7 @@ void hidinput_disconnect(struct hid_device *hid) input_unregister_device(hidinput->input); else input_free_device(hidinput->input); + kfree(hidinput->name); kfree(hidinput); } diff --git a/drivers/hid/hid-multitouch.c b/drivers/hid/hid-multitouch.c index 40fbb7c52723..da954f3f4da7 100644 --- a/drivers/hid/hid-multitouch.c +++ b/drivers/hid/hid-multitouch.c @@ -1375,7 +1375,8 @@ static bool mt_need_to_apply_feature(struct hid_device *hdev, struct hid_usage *usage, enum latency_mode latency, bool surface_switch, - bool button_switch) + bool button_switch, + bool *inputmode_found) { struct mt_device *td = hid_get_drvdata(hdev); struct mt_class *cls = &td->mtclass; @@ -1387,6 +1388,14 @@ static bool mt_need_to_apply_feature(struct hid_device *hdev, switch (usage->hid) { case HID_DG_INPUTMODE: + /* + * Some elan panels wrongly declare 2 input mode features, + * and silently ignore when we set the value in the second + * field. Skip the second feature and hope for the best. + */ + if (*inputmode_found) + return false; + if (cls->quirks & MT_QUIRK_FORCE_GET_FEATURE) { report_len = hid_report_len(report); buf = hid_alloc_report_buf(report, GFP_KERNEL); @@ -1402,6 +1411,7 @@ static bool mt_need_to_apply_feature(struct hid_device *hdev, } field->value[index] = td->inputmode_value; + *inputmode_found = true; return true; case HID_DG_CONTACTMAX: @@ -1439,6 +1449,7 @@ static void mt_set_modes(struct hid_device *hdev, enum latency_mode latency, struct hid_usage *usage; int i, j; bool update_report; + bool inputmode_found = false; rep_enum = &hdev->report_enum[HID_FEATURE_REPORT]; list_for_each_entry(rep, &rep_enum->report_list, list) { @@ -1457,7 +1468,8 @@ static void mt_set_modes(struct hid_device *hdev, enum latency_mode latency, usage, latency, surface_switch, - button_switch)) + button_switch, + &inputmode_found)) update_report = true; } } @@ -1685,6 +1697,9 @@ static int mt_probe(struct hid_device *hdev, const struct hid_device_id *id) */ hdev->quirks |= HID_QUIRK_INPUT_PER_APP; + if (id->group != HID_GROUP_MULTITOUCH_WIN_8) + hdev->quirks |= HID_QUIRK_MULTI_INPUT; + timer_setup(&td->release_timer, mt_expired_timeout, 0); ret = hid_parse(hdev); diff --git a/drivers/hid/hid-saitek.c b/drivers/hid/hid-saitek.c index 39e642686ff0..683861f324e3 100644 --- a/drivers/hid/hid-saitek.c +++ b/drivers/hid/hid-saitek.c @@ -183,6 +183,8 @@ static const struct hid_device_id saitek_devices[] = { .driver_data = SAITEK_RELEASE_MODE_RAT7 }, { HID_USB_DEVICE(USB_VENDOR_ID_SAITEK, USB_DEVICE_ID_SAITEK_RAT7), .driver_data = SAITEK_RELEASE_MODE_RAT7 }, + { HID_USB_DEVICE(USB_VENDOR_ID_SAITEK, USB_DEVICE_ID_SAITEK_RAT7_CONTAGION), + .driver_data = SAITEK_RELEASE_MODE_RAT7 }, { HID_USB_DEVICE(USB_VENDOR_ID_SAITEK, USB_DEVICE_ID_SAITEK_RAT9), .driver_data = SAITEK_RELEASE_MODE_RAT7 }, { HID_USB_DEVICE(USB_VENDOR_ID_MADCATZ, USB_DEVICE_ID_MADCATZ_RAT9), diff --git a/drivers/hid/hid-sensor-hub.c b/drivers/hid/hid-sensor-hub.c index 50af72baa5ca..2b63487057c2 100644 --- a/drivers/hid/hid-sensor-hub.c +++ b/drivers/hid/hid-sensor-hub.c @@ -579,6 +579,28 @@ void sensor_hub_device_close(struct hid_sensor_hub_device *hsdev) } EXPORT_SYMBOL_GPL(sensor_hub_device_close); +static __u8 *sensor_hub_report_fixup(struct hid_device *hdev, __u8 *rdesc, + unsigned int *rsize) +{ + /* + * Checks if the report descriptor of Thinkpad Helix 2 has a logical + * minimum for magnetic flux axis greater than the maximum. + */ + if (hdev->product == USB_DEVICE_ID_TEXAS_INSTRUMENTS_LENOVO_YOGA && + *rsize == 2558 && rdesc[913] == 0x17 && rdesc[914] == 0x40 && + rdesc[915] == 0x81 && rdesc[916] == 0x08 && + rdesc[917] == 0x00 && rdesc[918] == 0x27 && + rdesc[921] == 0x07 && rdesc[922] == 0x00) { + /* Sets negative logical minimum for mag x, y and z */ + rdesc[914] = rdesc[935] = rdesc[956] = 0xc0; + rdesc[915] = rdesc[936] = rdesc[957] = 0x7e; + rdesc[916] = rdesc[937] = rdesc[958] = 0xf7; + rdesc[917] = rdesc[938] = rdesc[959] = 0xff; + } + + return rdesc; +} + static int sensor_hub_probe(struct hid_device *hdev, const struct hid_device_id *id) { @@ -743,6 +765,7 @@ static struct hid_driver sensor_hub_driver = { .probe = sensor_hub_probe, .remove = sensor_hub_remove, .raw_event = sensor_hub_raw_event, + .report_fixup = sensor_hub_report_fixup, #ifdef CONFIG_PM .suspend = sensor_hub_suspend, .resume = sensor_hub_resume, diff --git a/drivers/hid/i2c-hid/i2c-hid.c b/drivers/hid/i2c-hid/i2c-hid.c index 2ce194a84868..f3076659361a 100644 --- a/drivers/hid/i2c-hid/i2c-hid.c +++ b/drivers/hid/i2c-hid/i2c-hid.c @@ -170,8 +170,6 @@ static const struct i2c_hid_quirks { I2C_HID_QUIRK_SET_PWR_WAKEUP_DEV }, { I2C_VENDOR_ID_HANTICK, I2C_PRODUCT_ID_HANTICK_5288, I2C_HID_QUIRK_NO_IRQ_AFTER_RESET }, - { I2C_VENDOR_ID_RAYD, I2C_PRODUCT_ID_RAYD_3118, - I2C_HID_QUIRK_RESEND_REPORT_DESCR }, { USB_VENDOR_ID_SIS_TOUCH, USB_DEVICE_ID_SIS10FB_TOUCH, I2C_HID_QUIRK_RESEND_REPORT_DESCR }, { 0, 0 } @@ -1235,11 +1233,16 @@ static int i2c_hid_resume(struct device *dev) pm_runtime_enable(dev); enable_irq(client->irq); - ret = i2c_hid_hwreset(client); + + /* Instead of resetting device, simply powers the device on. This + * solves "incomplete reports" on Raydium devices 2386:3118 and + * 2386:4B33 + */ + ret = i2c_hid_set_power(client, I2C_HID_PWR_ON); if (ret) return ret; - /* RAYDIUM device (2386:3118) need to re-send report descr cmd + /* Some devices need to re-send report descr cmd * after resume, after this it will be back normal. * otherwise it issues too many incomplete reports. */ diff --git a/drivers/hid/intel-ish-hid/ipc/hw-ish.h b/drivers/hid/intel-ish-hid/ipc/hw-ish.h index 97869b7410eb..da133716bed0 100644 --- a/drivers/hid/intel-ish-hid/ipc/hw-ish.h +++ b/drivers/hid/intel-ish-hid/ipc/hw-ish.h @@ -29,6 +29,7 @@ #define CNL_Ax_DEVICE_ID 0x9DFC #define GLK_Ax_DEVICE_ID 0x31A2 #define CNL_H_DEVICE_ID 0xA37C +#define SPT_H_DEVICE_ID 0xA135 #define REVISION_ID_CHT_A0 0x6 #define REVISION_ID_CHT_Ax_SI 0x0 diff --git a/drivers/hid/intel-ish-hid/ipc/pci-ish.c b/drivers/hid/intel-ish-hid/ipc/pci-ish.c index 050f9872f5c0..a1125a5c7965 100644 --- a/drivers/hid/intel-ish-hid/ipc/pci-ish.c +++ b/drivers/hid/intel-ish-hid/ipc/pci-ish.c @@ -38,6 +38,7 @@ static const struct pci_device_id ish_pci_tbl[] = { {PCI_DEVICE(PCI_VENDOR_ID_INTEL, CNL_Ax_DEVICE_ID)}, {PCI_DEVICE(PCI_VENDOR_ID_INTEL, GLK_Ax_DEVICE_ID)}, {PCI_DEVICE(PCI_VENDOR_ID_INTEL, CNL_H_DEVICE_ID)}, + {PCI_DEVICE(PCI_VENDOR_ID_INTEL, SPT_H_DEVICE_ID)}, {0, } }; MODULE_DEVICE_TABLE(pci, ish_pci_tbl); diff --git a/drivers/hv/vmbus_drv.c b/drivers/hv/vmbus_drv.c index b1b548a21f91..c71cc857b649 100644 --- a/drivers/hv/vmbus_drv.c +++ b/drivers/hv/vmbus_drv.c @@ -1291,6 +1291,9 @@ static ssize_t vmbus_chan_attr_show(struct kobject *kobj, if (!attribute->show) return -EIO; + if (chan->state != CHANNEL_OPENED_STATE) + return -EINVAL; + return attribute->show(chan, buf); } diff --git a/drivers/hwmon/nct6775.c b/drivers/hwmon/nct6775.c index 944f5b63aecd..78603b78cf41 100644 --- a/drivers/hwmon/nct6775.c +++ b/drivers/hwmon/nct6775.c @@ -207,8 +207,6 @@ superio_exit(int ioreg) #define NUM_FAN 7 -#define TEMP_SOURCE_VIRTUAL 0x1f - /* Common and NCT6775 specific data */ /* Voltage min/max registers for nr=7..14 are in bank 5 */ @@ -299,8 +297,9 @@ static const u16 NCT6775_REG_PWM_READ[] = { static const u16 NCT6775_REG_FAN[] = { 0x630, 0x632, 0x634, 0x636, 0x638 }; static const u16 NCT6775_REG_FAN_MIN[] = { 0x3b, 0x3c, 0x3d }; -static const u16 NCT6775_REG_FAN_PULSES[] = { 0x641, 0x642, 0x643, 0x644, 0 }; -static const u16 NCT6775_FAN_PULSE_SHIFT[] = { 0, 0, 0, 0, 0, 0 }; +static const u16 NCT6775_REG_FAN_PULSES[NUM_FAN] = { + 0x641, 0x642, 0x643, 0x644 }; +static const u16 NCT6775_FAN_PULSE_SHIFT[NUM_FAN] = { }; static const u16 NCT6775_REG_TEMP[] = { 0x27, 0x150, 0x250, 0x62b, 0x62c, 0x62d }; @@ -373,6 +372,7 @@ static const char *const nct6775_temp_label[] = { }; #define NCT6775_TEMP_MASK 0x001ffffe +#define NCT6775_VIRT_TEMP_MASK 0x00000000 static const u16 NCT6775_REG_TEMP_ALTERNATE[32] = { [13] = 0x661, @@ -425,8 +425,8 @@ static const u8 NCT6776_PWM_MODE_MASK[] = { 0x01, 0, 0, 0, 0, 0 }; static const u16 NCT6776_REG_FAN_MIN[] = { 0x63a, 0x63c, 0x63e, 0x640, 0x642, 0x64a, 0x64c }; -static const u16 NCT6776_REG_FAN_PULSES[] = { - 0x644, 0x645, 0x646, 0x647, 0x648, 0x649, 0 }; +static const u16 NCT6776_REG_FAN_PULSES[NUM_FAN] = { + 0x644, 0x645, 0x646, 0x647, 0x648, 0x649 }; static const u16 NCT6776_REG_WEIGHT_DUTY_BASE[] = { 0x13e, 0x23e, 0x33e, 0x83e, 0x93e, 0xa3e }; @@ -461,6 +461,7 @@ static const char *const nct6776_temp_label[] = { }; #define NCT6776_TEMP_MASK 0x007ffffe +#define NCT6776_VIRT_TEMP_MASK 0x00000000 static const u16 NCT6776_REG_TEMP_ALTERNATE[32] = { [14] = 0x401, @@ -501,9 +502,9 @@ static const s8 NCT6779_BEEP_BITS[] = { 30, 31 }; /* intrusion0, intrusion1 */ static const u16 NCT6779_REG_FAN[] = { - 0x4b0, 0x4b2, 0x4b4, 0x4b6, 0x4b8, 0x4ba, 0x660 }; -static const u16 NCT6779_REG_FAN_PULSES[] = { - 0x644, 0x645, 0x646, 0x647, 0x648, 0x649, 0 }; + 0x4c0, 0x4c2, 0x4c4, 0x4c6, 0x4c8, 0x4ca, 0x4ce }; +static const u16 NCT6779_REG_FAN_PULSES[NUM_FAN] = { + 0x644, 0x645, 0x646, 0x647, 0x648, 0x649 }; static const u16 NCT6779_REG_CRITICAL_PWM_ENABLE[] = { 0x136, 0x236, 0x336, 0x836, 0x936, 0xa36, 0xb36 }; @@ -559,7 +560,9 @@ static const char *const nct6779_temp_label[] = { }; #define NCT6779_TEMP_MASK 0x07ffff7e +#define NCT6779_VIRT_TEMP_MASK 0x00000000 #define NCT6791_TEMP_MASK 0x87ffff7e +#define NCT6791_VIRT_TEMP_MASK 0x80000000 static const u16 NCT6779_REG_TEMP_ALTERNATE[32] = { 0x490, 0x491, 0x492, 0x493, 0x494, 0x495, 0, 0, @@ -638,6 +641,7 @@ static const char *const nct6792_temp_label[] = { }; #define NCT6792_TEMP_MASK 0x9fffff7e +#define NCT6792_VIRT_TEMP_MASK 0x80000000 static const char *const nct6793_temp_label[] = { "", @@ -675,6 +679,7 @@ static const char *const nct6793_temp_label[] = { }; #define NCT6793_TEMP_MASK 0xbfff037e +#define NCT6793_VIRT_TEMP_MASK 0x80000000 static const char *const nct6795_temp_label[] = { "", @@ -712,6 +717,7 @@ static const char *const nct6795_temp_label[] = { }; #define NCT6795_TEMP_MASK 0xbfffff7e +#define NCT6795_VIRT_TEMP_MASK 0x80000000 static const char *const nct6796_temp_label[] = { "", @@ -724,8 +730,8 @@ static const char *const nct6796_temp_label[] = { "AUXTIN4", "SMBUSMASTER 0", "SMBUSMASTER 1", - "", - "", + "Virtual_TEMP", + "Virtual_TEMP", "", "", "", @@ -748,7 +754,8 @@ static const char *const nct6796_temp_label[] = { "Virtual_TEMP" }; -#define NCT6796_TEMP_MASK 0xbfff03fe +#define NCT6796_TEMP_MASK 0xbfff0ffe +#define NCT6796_VIRT_TEMP_MASK 0x80000c00 /* NCT6102D/NCT6106D specific data */ @@ -779,8 +786,8 @@ static const u16 NCT6106_REG_TEMP_CONFIG[] = { static const u16 NCT6106_REG_FAN[] = { 0x20, 0x22, 0x24 }; static const u16 NCT6106_REG_FAN_MIN[] = { 0xe0, 0xe2, 0xe4 }; -static const u16 NCT6106_REG_FAN_PULSES[] = { 0xf6, 0xf6, 0xf6, 0, 0 }; -static const u16 NCT6106_FAN_PULSE_SHIFT[] = { 0, 2, 4, 0, 0 }; +static const u16 NCT6106_REG_FAN_PULSES[] = { 0xf6, 0xf6, 0xf6 }; +static const u16 NCT6106_FAN_PULSE_SHIFT[] = { 0, 2, 4 }; static const u8 NCT6106_REG_PWM_MODE[] = { 0xf3, 0xf3, 0xf3 }; static const u8 NCT6106_PWM_MODE_MASK[] = { 0x01, 0x02, 0x04 }; @@ -917,6 +924,11 @@ static unsigned int fan_from_reg16(u16 reg, unsigned int divreg) return 1350000U / (reg << divreg); } +static unsigned int fan_from_reg_rpm(u16 reg, unsigned int divreg) +{ + return reg; +} + static u16 fan_to_reg(u32 fan, unsigned int divreg) { if (!fan) @@ -969,6 +981,7 @@ struct nct6775_data { u16 reg_temp_config[NUM_TEMP]; const char * const *temp_label; u32 temp_mask; + u32 virt_temp_mask; u16 REG_CONFIG; u16 REG_VBAT; @@ -1276,11 +1289,11 @@ static bool is_word_sized(struct nct6775_data *data, u16 reg) case nct6795: case nct6796: return reg == 0x150 || reg == 0x153 || reg == 0x155 || - ((reg & 0xfff0) == 0x4b0 && (reg & 0x000f) < 0x0b) || + (reg & 0xfff0) == 0x4c0 || reg == 0x402 || reg == 0x63a || reg == 0x63c || reg == 0x63e || reg == 0x640 || reg == 0x642 || reg == 0x64a || - reg == 0x64c || reg == 0x660 || + reg == 0x64c || reg == 0x73 || reg == 0x75 || reg == 0x77 || reg == 0x79 || reg == 0x7b || reg == 0x7d; } @@ -1558,7 +1571,7 @@ static void nct6775_update_pwm(struct device *dev) reg = nct6775_read_value(data, data->REG_WEIGHT_TEMP_SEL[i]); data->pwm_weight_temp_sel[i] = reg & 0x1f; /* If weight is disabled, report weight source as 0 */ - if (j == 1 && !(reg & 0x80)) + if (!(reg & 0x80)) data->pwm_weight_temp_sel[i] = 0; /* Weight temp data */ @@ -1682,9 +1695,13 @@ static struct nct6775_data *nct6775_update_device(struct device *dev) if (data->has_fan_min & BIT(i)) data->fan_min[i] = nct6775_read_value(data, data->REG_FAN_MIN[i]); - data->fan_pulses[i] = - (nct6775_read_value(data, data->REG_FAN_PULSES[i]) - >> data->FAN_PULSE_SHIFT[i]) & 0x03; + + if (data->REG_FAN_PULSES[i]) { + data->fan_pulses[i] = + (nct6775_read_value(data, + data->REG_FAN_PULSES[i]) + >> data->FAN_PULSE_SHIFT[i]) & 0x03; + } nct6775_select_fan_div(dev, data, i, reg); } @@ -3639,6 +3656,7 @@ static int nct6775_probe(struct platform_device *pdev) data->temp_label = nct6776_temp_label; data->temp_mask = NCT6776_TEMP_MASK; + data->virt_temp_mask = NCT6776_VIRT_TEMP_MASK; data->REG_VBAT = NCT6106_REG_VBAT; data->REG_DIODE = NCT6106_REG_DIODE; @@ -3717,6 +3735,7 @@ static int nct6775_probe(struct platform_device *pdev) data->temp_label = nct6775_temp_label; data->temp_mask = NCT6775_TEMP_MASK; + data->virt_temp_mask = NCT6775_VIRT_TEMP_MASK; data->REG_CONFIG = NCT6775_REG_CONFIG; data->REG_VBAT = NCT6775_REG_VBAT; @@ -3789,6 +3808,7 @@ static int nct6775_probe(struct platform_device *pdev) data->temp_label = nct6776_temp_label; data->temp_mask = NCT6776_TEMP_MASK; + data->virt_temp_mask = NCT6776_VIRT_TEMP_MASK; data->REG_CONFIG = NCT6775_REG_CONFIG; data->REG_VBAT = NCT6775_REG_VBAT; @@ -3853,7 +3873,7 @@ static int nct6775_probe(struct platform_device *pdev) data->ALARM_BITS = NCT6779_ALARM_BITS; data->BEEP_BITS = NCT6779_BEEP_BITS; - data->fan_from_reg = fan_from_reg13; + data->fan_from_reg = fan_from_reg_rpm; data->fan_from_reg_min = fan_from_reg13; data->target_temp_mask = 0xff; data->tolerance_mask = 0x07; @@ -3861,6 +3881,7 @@ static int nct6775_probe(struct platform_device *pdev) data->temp_label = nct6779_temp_label; data->temp_mask = NCT6779_TEMP_MASK; + data->virt_temp_mask = NCT6779_VIRT_TEMP_MASK; data->REG_CONFIG = NCT6775_REG_CONFIG; data->REG_VBAT = NCT6775_REG_VBAT; @@ -3933,7 +3954,7 @@ static int nct6775_probe(struct platform_device *pdev) data->ALARM_BITS = NCT6791_ALARM_BITS; data->BEEP_BITS = NCT6779_BEEP_BITS; - data->fan_from_reg = fan_from_reg13; + data->fan_from_reg = fan_from_reg_rpm; data->fan_from_reg_min = fan_from_reg13; data->target_temp_mask = 0xff; data->tolerance_mask = 0x07; @@ -3944,22 +3965,27 @@ static int nct6775_probe(struct platform_device *pdev) case nct6791: data->temp_label = nct6779_temp_label; data->temp_mask = NCT6791_TEMP_MASK; + data->virt_temp_mask = NCT6791_VIRT_TEMP_MASK; break; case nct6792: data->temp_label = nct6792_temp_label; data->temp_mask = NCT6792_TEMP_MASK; + data->virt_temp_mask = NCT6792_VIRT_TEMP_MASK; break; case nct6793: data->temp_label = nct6793_temp_label; data->temp_mask = NCT6793_TEMP_MASK; + data->virt_temp_mask = NCT6793_VIRT_TEMP_MASK; break; case nct6795: data->temp_label = nct6795_temp_label; data->temp_mask = NCT6795_TEMP_MASK; + data->virt_temp_mask = NCT6795_VIRT_TEMP_MASK; break; case nct6796: data->temp_label = nct6796_temp_label; data->temp_mask = NCT6796_TEMP_MASK; + data->virt_temp_mask = NCT6796_VIRT_TEMP_MASK; break; } @@ -4143,7 +4169,7 @@ static int nct6775_probe(struct platform_device *pdev) * for each fan reflects a different temperature, and there * are no duplicates. */ - if (src != TEMP_SOURCE_VIRTUAL) { + if (!(data->virt_temp_mask & BIT(src))) { if (mask & BIT(src)) continue; mask |= BIT(src); diff --git a/drivers/hwmon/raspberrypi-hwmon.c b/drivers/hwmon/raspberrypi-hwmon.c index fb4e4a6bb1f6..be5ba4690895 100644 --- a/drivers/hwmon/raspberrypi-hwmon.c +++ b/drivers/hwmon/raspberrypi-hwmon.c @@ -164,3 +164,4 @@ module_platform_driver(rpi_hwmon_driver); MODULE_AUTHOR("Stefan Wahren <stefan.wahren@i2se.com>"); MODULE_DESCRIPTION("Raspberry Pi voltage sensor driver"); MODULE_LICENSE("GPL v2"); +MODULE_ALIAS("platform:raspberrypi-hwmon"); diff --git a/drivers/hwtracing/intel_th/core.c b/drivers/hwtracing/intel_th/core.c index da962aa2cef5..fc6b7f8b62fb 100644 --- a/drivers/hwtracing/intel_th/core.c +++ b/drivers/hwtracing/intel_th/core.c @@ -139,7 +139,8 @@ static int intel_th_remove(struct device *dev) th->thdev[i] = NULL; } - th->num_thdevs = lowest; + if (lowest >= 0) + th->num_thdevs = lowest; } if (thdrv->attr_group) @@ -487,7 +488,7 @@ static const struct intel_th_subdevice { .flags = IORESOURCE_MEM, }, { - .start = TH_MMIO_SW, + .start = 1, /* use resource[1] */ .end = 0, .flags = IORESOURCE_MEM, }, @@ -580,6 +581,7 @@ intel_th_subdevice_alloc(struct intel_th *th, struct intel_th_device *thdev; struct resource res[3]; unsigned int req = 0; + bool is64bit = false; int r, err; thdev = intel_th_device_alloc(th, subdev->type, subdev->name, @@ -589,12 +591,18 @@ intel_th_subdevice_alloc(struct intel_th *th, thdev->drvdata = th->drvdata; + for (r = 0; r < th->num_resources; r++) + if (th->resource[r].flags & IORESOURCE_MEM_64) { + is64bit = true; + break; + } + memcpy(res, subdev->res, sizeof(struct resource) * subdev->nres); for (r = 0; r < subdev->nres; r++) { struct resource *devres = th->resource; - int bar = TH_MMIO_CONFIG; + int bar = 0; /* cut subdevices' MMIO from resource[0] */ /* * Take .end == 0 to mean 'take the whole bar', @@ -603,6 +611,8 @@ intel_th_subdevice_alloc(struct intel_th *th, */ if (!res[r].end && res[r].flags == IORESOURCE_MEM) { bar = res[r].start; + if (is64bit) + bar *= 2; res[r].start = 0; res[r].end = resource_size(&devres[bar]) - 1; } diff --git a/drivers/hwtracing/intel_th/pci.c b/drivers/hwtracing/intel_th/pci.c index c2e55e5d97f6..1cf6290d6435 100644 --- a/drivers/hwtracing/intel_th/pci.c +++ b/drivers/hwtracing/intel_th/pci.c @@ -160,6 +160,11 @@ static const struct pci_device_id intel_th_pci_id_table[] = { PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x18e1), .driver_data = (kernel_ulong_t)&intel_th_2x, }, + { + /* Ice Lake PCH */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x34a6), + .driver_data = (kernel_ulong_t)&intel_th_2x, + }, { 0 }, }; diff --git a/drivers/i2c/busses/i2c-i801.c b/drivers/i2c/busses/i2c-i801.c index 04b60a349d7e..c91e145ef5a5 100644 --- a/drivers/i2c/busses/i2c-i801.c +++ b/drivers/i2c/busses/i2c-i801.c @@ -140,6 +140,7 @@ #define SBREG_BAR 0x10 #define SBREG_SMBCTRL 0xc6000c +#define SBREG_SMBCTRL_DNV 0xcf000c /* Host status bits for SMBPCISTS */ #define SMBPCISTS_INTS BIT(3) @@ -1399,7 +1400,11 @@ static void i801_add_tco(struct i801_priv *priv) spin_unlock(&p2sb_spinlock); res = &tco_res[ICH_RES_MEM_OFF]; - res->start = (resource_size_t)base64_addr + SBREG_SMBCTRL; + if (pci_dev->device == PCI_DEVICE_ID_INTEL_DNV_SMBUS) + res->start = (resource_size_t)base64_addr + SBREG_SMBCTRL_DNV; + else + res->start = (resource_size_t)base64_addr + SBREG_SMBCTRL; + res->end = res->start + 3; res->flags = IORESOURCE_MEM; diff --git a/drivers/i2c/busses/i2c-imx-lpi2c.c b/drivers/i2c/busses/i2c-imx-lpi2c.c index 6d975f5221ca..06c4c767af32 100644 --- a/drivers/i2c/busses/i2c-imx-lpi2c.c +++ b/drivers/i2c/busses/i2c-imx-lpi2c.c @@ -538,7 +538,6 @@ static const struct i2c_algorithm lpi2c_imx_algo = { static const struct of_device_id lpi2c_imx_of_match[] = { { .compatible = "fsl,imx7ulp-lpi2c" }, - { .compatible = "fsl,imx8dv-lpi2c" }, { }, }; MODULE_DEVICE_TABLE(of, lpi2c_imx_of_match); diff --git a/drivers/i2c/busses/i2c-uniphier-f.c b/drivers/i2c/busses/i2c-uniphier-f.c index 9918bdd81619..a403e8579b65 100644 --- a/drivers/i2c/busses/i2c-uniphier-f.c +++ b/drivers/i2c/busses/i2c-uniphier-f.c @@ -401,11 +401,8 @@ static int uniphier_fi2c_master_xfer(struct i2c_adapter *adap, return ret; for (msg = msgs; msg < emsg; msg++) { - /* If next message is read, skip the stop condition */ - bool stop = !(msg + 1 < emsg && msg[1].flags & I2C_M_RD); - /* but, force it if I2C_M_STOP is set */ - if (msg->flags & I2C_M_STOP) - stop = true; + /* Emit STOP if it is the last message or I2C_M_STOP is set. */ + bool stop = (msg + 1 == emsg) || (msg->flags & I2C_M_STOP); ret = uniphier_fi2c_master_xfer_one(adap, msg, stop); if (ret) diff --git a/drivers/i2c/busses/i2c-uniphier.c b/drivers/i2c/busses/i2c-uniphier.c index bb181b088291..454f914ae66d 100644 --- a/drivers/i2c/busses/i2c-uniphier.c +++ b/drivers/i2c/busses/i2c-uniphier.c @@ -248,11 +248,8 @@ static int uniphier_i2c_master_xfer(struct i2c_adapter *adap, return ret; for (msg = msgs; msg < emsg; msg++) { - /* If next message is read, skip the stop condition */ - bool stop = !(msg + 1 < emsg && msg[1].flags & I2C_M_RD); - /* but, force it if I2C_M_STOP is set */ - if (msg->flags & I2C_M_STOP) - stop = true; + /* Emit STOP if it is the last message or I2C_M_STOP is set. */ + bool stop = (msg + 1 == emsg) || (msg->flags & I2C_M_STOP); ret = uniphier_i2c_master_xfer_one(adap, msg, stop); if (ret) diff --git a/drivers/i2c/busses/i2c-xiic.c b/drivers/i2c/busses/i2c-xiic.c index 9a71e50d21f1..0c51c0ffdda9 100644 --- a/drivers/i2c/busses/i2c-xiic.c +++ b/drivers/i2c/busses/i2c-xiic.c @@ -532,6 +532,7 @@ static void xiic_start_recv(struct xiic_i2c *i2c) { u8 rx_watermark; struct i2c_msg *msg = i2c->rx_msg = i2c->tx_msg; + unsigned long flags; /* Clear and enable Rx full interrupt. */ xiic_irq_clr_en(i2c, XIIC_INTR_RX_FULL_MASK | XIIC_INTR_TX_ERROR_MASK); @@ -547,6 +548,7 @@ static void xiic_start_recv(struct xiic_i2c *i2c) rx_watermark = IIC_RX_FIFO_DEPTH; xiic_setreg8(i2c, XIIC_RFD_REG_OFFSET, rx_watermark - 1); + local_irq_save(flags); if (!(msg->flags & I2C_M_NOSTART)) /* write the address */ xiic_setreg16(i2c, XIIC_DTR_REG_OFFSET, @@ -556,6 +558,8 @@ static void xiic_start_recv(struct xiic_i2c *i2c) xiic_setreg16(i2c, XIIC_DTR_REG_OFFSET, msg->len | ((i2c->nmsgs == 1) ? XIIC_TX_DYN_STOP_MASK : 0)); + local_irq_restore(flags); + if (i2c->nmsgs == 1) /* very last, enable bus not busy as well */ xiic_irq_clr_en(i2c, XIIC_INTR_BNB_MASK); diff --git a/drivers/iio/imu/st_lsm6dsx/st_lsm6dsx_buffer.c b/drivers/iio/imu/st_lsm6dsx/st_lsm6dsx_buffer.c index 7589f2ad1dae..631360b14ca7 100644 --- a/drivers/iio/imu/st_lsm6dsx/st_lsm6dsx_buffer.c +++ b/drivers/iio/imu/st_lsm6dsx/st_lsm6dsx_buffer.c @@ -187,12 +187,15 @@ static int st_lsm6dsx_set_fifo_odr(struct st_lsm6dsx_sensor *sensor, int st_lsm6dsx_update_watermark(struct st_lsm6dsx_sensor *sensor, u16 watermark) { - u16 fifo_watermark = ~0, cur_watermark, sip = 0, fifo_th_mask; + u16 fifo_watermark = ~0, cur_watermark, fifo_th_mask; struct st_lsm6dsx_hw *hw = sensor->hw; struct st_lsm6dsx_sensor *cur_sensor; int i, err, data; __le16 wdata; + if (!hw->sip) + return 0; + for (i = 0; i < ST_LSM6DSX_ID_MAX; i++) { cur_sensor = iio_priv(hw->iio_devs[i]); @@ -203,14 +206,10 @@ int st_lsm6dsx_update_watermark(struct st_lsm6dsx_sensor *sensor, u16 watermark) : cur_sensor->watermark; fifo_watermark = min_t(u16, fifo_watermark, cur_watermark); - sip += cur_sensor->sip; } - if (!sip) - return 0; - - fifo_watermark = max_t(u16, fifo_watermark, sip); - fifo_watermark = (fifo_watermark / sip) * sip; + fifo_watermark = max_t(u16, fifo_watermark, hw->sip); + fifo_watermark = (fifo_watermark / hw->sip) * hw->sip; fifo_watermark = fifo_watermark * hw->settings->fifo_ops.th_wl; err = regmap_read(hw->regmap, hw->settings->fifo_ops.fifo_th.addr + 1, diff --git a/drivers/iio/temperature/maxim_thermocouple.c b/drivers/iio/temperature/maxim_thermocouple.c index 54e383231d1e..c31b9633f32d 100644 --- a/drivers/iio/temperature/maxim_thermocouple.c +++ b/drivers/iio/temperature/maxim_thermocouple.c @@ -258,7 +258,6 @@ static int maxim_thermocouple_remove(struct spi_device *spi) static const struct spi_device_id maxim_thermocouple_id[] = { {"max6675", MAX6675}, {"max31855", MAX31855}, - {"max31856", MAX31855}, {}, }; MODULE_DEVICE_TABLE(spi, maxim_thermocouple_id); diff --git a/drivers/infiniband/core/cma.c b/drivers/infiniband/core/cma.c index f72677291b69..a36c94930c31 100644 --- a/drivers/infiniband/core/cma.c +++ b/drivers/infiniband/core/cma.c @@ -724,6 +724,7 @@ static int cma_resolve_ib_dev(struct rdma_id_private *id_priv) dgid = (union ib_gid *) &addr->sib_addr; pkey = ntohs(addr->sib_pkey); + mutex_lock(&lock); list_for_each_entry(cur_dev, &dev_list, list) { for (p = 1; p <= cur_dev->device->phys_port_cnt; ++p) { if (!rdma_cap_af_ib(cur_dev->device, p)) @@ -750,18 +751,19 @@ static int cma_resolve_ib_dev(struct rdma_id_private *id_priv) cma_dev = cur_dev; sgid = gid; id_priv->id.port_num = p; + goto found; } } } } - - if (!cma_dev) - return -ENODEV; + mutex_unlock(&lock); + return -ENODEV; found: cma_attach_to_dev(id_priv, cma_dev); - addr = (struct sockaddr_ib *) cma_src_addr(id_priv); - memcpy(&addr->sib_addr, &sgid, sizeof sgid); + mutex_unlock(&lock); + addr = (struct sockaddr_ib *)cma_src_addr(id_priv); + memcpy(&addr->sib_addr, &sgid, sizeof(sgid)); cma_translate_ib(addr, &id_priv->id.route.addr.dev_addr); return 0; } diff --git a/drivers/infiniband/core/rdma_core.c b/drivers/infiniband/core/rdma_core.c index 6eb64c6f0802..c4118bcd5103 100644 --- a/drivers/infiniband/core/rdma_core.c +++ b/drivers/infiniband/core/rdma_core.c @@ -882,6 +882,8 @@ static int __uverbs_cleanup_ufile(struct ib_uverbs_file *ufile, WARN_ON(uverbs_try_lock_object(obj, UVERBS_LOOKUP_WRITE)); if (!uverbs_destroy_uobject(obj, reason)) ret = 0; + else + atomic_set(&obj->usecnt, 0); } return ret; } diff --git a/drivers/infiniband/core/ucma.c b/drivers/infiniband/core/ucma.c index ec8fb289621f..5f437d1570fb 100644 --- a/drivers/infiniband/core/ucma.c +++ b/drivers/infiniband/core/ucma.c @@ -124,6 +124,8 @@ static DEFINE_MUTEX(mut); static DEFINE_IDR(ctx_idr); static DEFINE_IDR(multicast_idr); +static const struct file_operations ucma_fops; + static inline struct ucma_context *_ucma_find_context(int id, struct ucma_file *file) { @@ -1581,6 +1583,10 @@ static ssize_t ucma_migrate_id(struct ucma_file *new_file, f = fdget(cmd.fd); if (!f.file) return -ENOENT; + if (f.file->f_op != &ucma_fops) { + ret = -EINVAL; + goto file_put; + } /* Validate current fd and prevent destruction of id. */ ctx = ucma_get_ctx(f.file->private_data, cmd.id); diff --git a/drivers/infiniband/core/uverbs_main.c b/drivers/infiniband/core/uverbs_main.c index 823beca448e1..6d974e2363df 100644 --- a/drivers/infiniband/core/uverbs_main.c +++ b/drivers/infiniband/core/uverbs_main.c @@ -1050,7 +1050,7 @@ static void ib_uverbs_add_one(struct ib_device *device) uverbs_dev->num_comp_vectors = device->num_comp_vectors; if (ib_uverbs_create_uapi(device, uverbs_dev)) - goto err; + goto err_uapi; cdev_init(&uverbs_dev->cdev, NULL); uverbs_dev->cdev.owner = THIS_MODULE; @@ -1077,11 +1077,10 @@ static void ib_uverbs_add_one(struct ib_device *device) err_class: device_destroy(uverbs_class, uverbs_dev->cdev.dev); - err_cdev: cdev_del(&uverbs_dev->cdev); +err_uapi: clear_bit(devnum, dev_map); - err: if (atomic_dec_and_test(&uverbs_dev->refcount)) ib_uverbs_comp_dev(uverbs_dev); diff --git a/drivers/infiniband/hw/bnxt_re/ib_verbs.c b/drivers/infiniband/hw/bnxt_re/ib_verbs.c index bbfb86eb2d24..bc2b9e038439 100644 --- a/drivers/infiniband/hw/bnxt_re/ib_verbs.c +++ b/drivers/infiniband/hw/bnxt_re/ib_verbs.c @@ -833,6 +833,8 @@ int bnxt_re_destroy_qp(struct ib_qp *ib_qp) "Failed to destroy Shadow QP"); return rc; } + bnxt_qplib_free_qp_res(&rdev->qplib_res, + &rdev->qp1_sqp->qplib_qp); mutex_lock(&rdev->qp_lock); list_del(&rdev->qp1_sqp->list); atomic_dec(&rdev->qp_count); diff --git a/drivers/infiniband/hw/bnxt_re/qplib_fp.c b/drivers/infiniband/hw/bnxt_re/qplib_fp.c index e426b990c1dd..6ad0d46ab879 100644 --- a/drivers/infiniband/hw/bnxt_re/qplib_fp.c +++ b/drivers/infiniband/hw/bnxt_re/qplib_fp.c @@ -196,7 +196,7 @@ static int bnxt_qplib_alloc_qp_hdr_buf(struct bnxt_qplib_res *res, struct bnxt_qplib_qp *qp) { struct bnxt_qplib_q *rq = &qp->rq; - struct bnxt_qplib_q *sq = &qp->rq; + struct bnxt_qplib_q *sq = &qp->sq; int rc = 0; if (qp->sq_hdr_buf_size && sq->hwq.max_elements) { diff --git a/drivers/infiniband/hw/cxgb4/qp.c b/drivers/infiniband/hw/cxgb4/qp.c index b3203afa3b1d..347fe18b1a41 100644 --- a/drivers/infiniband/hw/cxgb4/qp.c +++ b/drivers/infiniband/hw/cxgb4/qp.c @@ -1685,6 +1685,12 @@ static void flush_qp(struct c4iw_qp *qhp) schp = to_c4iw_cq(qhp->ibqp.send_cq); if (qhp->ibqp.uobject) { + + /* for user qps, qhp->wq.flushed is protected by qhp->mutex */ + if (qhp->wq.flushed) + return; + + qhp->wq.flushed = 1; t4_set_wq_in_error(&qhp->wq, 0); t4_set_cq_in_error(&rchp->cq); spin_lock_irqsave(&rchp->comp_handler_lock, flag); diff --git a/drivers/infiniband/hw/hfi1/pcie.c b/drivers/infiniband/hw/hfi1/pcie.c index eec83757d55f..6c967dde58e7 100644 --- a/drivers/infiniband/hw/hfi1/pcie.c +++ b/drivers/infiniband/hw/hfi1/pcie.c @@ -893,14 +893,11 @@ static int trigger_sbr(struct hfi1_devdata *dd) } /* - * A secondary bus reset (SBR) issues a hot reset to our device. - * The following routine does a 1s wait after the reset is dropped - * per PCI Trhfa (recovery time). PCIe 3.0 section 6.6.1 - - * Conventional Reset, paragraph 3, line 35 also says that a 1s - * delay after a reset is required. Per spec requirements, - * the link is either working or not after that point. + * This is an end around to do an SBR during probe time. A new API needs + * to be implemented to have cleaner interface but this fixes the + * current brokenness */ - return pci_reset_bus(dev); + return pci_bridge_secondary_bus_reset(dev->bus->self); } /* diff --git a/drivers/infiniband/hw/mlx4/main.c b/drivers/infiniband/hw/mlx4/main.c index ca0f1ee26091..0bbeaaae47e0 100644 --- a/drivers/infiniband/hw/mlx4/main.c +++ b/drivers/infiniband/hw/mlx4/main.c @@ -517,9 +517,11 @@ static int mlx4_ib_query_device(struct ib_device *ibdev, props->page_size_cap = dev->dev->caps.page_size_cap; props->max_qp = dev->dev->quotas.qp; props->max_qp_wr = dev->dev->caps.max_wqes - MLX4_IB_SQ_MAX_SPARE; - props->max_send_sge = dev->dev->caps.max_sq_sg; - props->max_recv_sge = dev->dev->caps.max_rq_sg; - props->max_sge_rd = MLX4_MAX_SGE_RD; + props->max_send_sge = + min(dev->dev->caps.max_sq_sg, dev->dev->caps.max_rq_sg); + props->max_recv_sge = + min(dev->dev->caps.max_sq_sg, dev->dev->caps.max_rq_sg); + props->max_sge_rd = MLX4_MAX_SGE_RD; props->max_cq = dev->dev->quotas.cq; props->max_cqe = dev->dev->caps.max_cqes; props->max_mr = dev->dev->quotas.mpt; diff --git a/drivers/infiniband/hw/nes/nes_mgt.c b/drivers/infiniband/hw/nes/nes_mgt.c index 9bdb84dc225c..e96ffff61c3a 100644 --- a/drivers/infiniband/hw/nes/nes_mgt.c +++ b/drivers/infiniband/hw/nes/nes_mgt.c @@ -198,9 +198,9 @@ static struct sk_buff *nes_get_next_skb(struct nes_device *nesdev, struct nes_qp if (skb) { /* Continue processing fpdu */ - if (skb->next == (struct sk_buff *)&nesqp->pau_list) + skb = skb_peek_next(skb, &nesqp->pau_list); + if (!skb) goto out; - skb = skb->next; processacks = false; } else { /* Starting a new one */ @@ -553,12 +553,10 @@ static void queue_fpdus(struct sk_buff *skb, struct nes_vnic *nesvnic, struct ne if (skb_queue_len(&nesqp->pau_list) == 0) { skb_queue_head(&nesqp->pau_list, skb); } else { - tmpskb = nesqp->pau_list.next; - while (tmpskb != (struct sk_buff *)&nesqp->pau_list) { + skb_queue_walk(&nesqp->pau_list, tmpskb) { cb = (struct nes_rskb_cb *)&tmpskb->cb[0]; if (before(seqnum, cb->seqnum)) break; - tmpskb = tmpskb->next; } skb_insert(tmpskb, skb, &nesqp->pau_list); } diff --git a/drivers/infiniband/ulp/ipoib/ipoib_cm.c b/drivers/infiniband/ulp/ipoib/ipoib_cm.c index ea01b8dd2be6..3d5424f335cb 100644 --- a/drivers/infiniband/ulp/ipoib/ipoib_cm.c +++ b/drivers/infiniband/ulp/ipoib/ipoib_cm.c @@ -1027,12 +1027,14 @@ static int ipoib_cm_rep_handler(struct ib_cm_id *cm_id, skb_queue_head_init(&skqueue); + netif_tx_lock_bh(p->dev); spin_lock_irq(&priv->lock); set_bit(IPOIB_FLAG_OPER_UP, &p->flags); if (p->neigh) while ((skb = __skb_dequeue(&p->neigh->queue))) __skb_queue_tail(&skqueue, skb); spin_unlock_irq(&priv->lock); + netif_tx_unlock_bh(p->dev); while ((skb = __skb_dequeue(&skqueue))) { skb->dev = p->dev; diff --git a/drivers/irqchip/irq-gic-v3-its.c b/drivers/irqchip/irq-gic-v3-its.c index 316a57530f6d..c2df341ff6fa 100644 --- a/drivers/irqchip/irq-gic-v3-its.c +++ b/drivers/irqchip/irq-gic-v3-its.c @@ -1439,6 +1439,7 @@ static struct irq_chip its_irq_chip = { * The consequence of the above is that allocation is cost is low, but * freeing is expensive. We assumes that freeing rarely occurs. */ +#define ITS_MAX_LPI_NRBITS 16 /* 64K LPIs */ static DEFINE_MUTEX(lpi_range_lock); static LIST_HEAD(lpi_range_list); @@ -1625,7 +1626,8 @@ static int __init its_alloc_lpi_tables(void) { phys_addr_t paddr; - lpi_id_bits = GICD_TYPER_ID_BITS(gic_rdists->gicd_typer); + lpi_id_bits = min_t(u32, GICD_TYPER_ID_BITS(gic_rdists->gicd_typer), + ITS_MAX_LPI_NRBITS); gic_rdists->prop_page = its_allocate_prop_table(GFP_NOWAIT); if (!gic_rdists->prop_page) { pr_err("Failed to allocate PROPBASE\n"); diff --git a/drivers/isdn/hisax/w6692.c b/drivers/isdn/hisax/w6692.c index c4be1644f5bb..bb8e4b7e34ea 100644 --- a/drivers/isdn/hisax/w6692.c +++ b/drivers/isdn/hisax/w6692.c @@ -624,7 +624,7 @@ W6692_l1hw(struct PStack *st, int pr, void *arg) break; case (HW_RESET | REQUEST): spin_lock_irqsave(&cs->lock, flags); - if ((cs->dc.w6692.ph_state == W_L1IND_DRD)) { + if (cs->dc.w6692.ph_state == W_L1IND_DRD) { ph_command(cs, W_L1CMD_ECK); spin_unlock_irqrestore(&cs->lock, flags); } else { diff --git a/drivers/isdn/mISDN/socket.c b/drivers/isdn/mISDN/socket.c index 18c0a1281914..15d3ca37669a 100644 --- a/drivers/isdn/mISDN/socket.c +++ b/drivers/isdn/mISDN/socket.c @@ -236,8 +236,7 @@ mISDN_sock_sendmsg(struct socket *sock, struct msghdr *msg, size_t len) } done: - if (skb) - kfree_skb(skb); + kfree_skb(skb); release_sock(sk); return err; } diff --git a/drivers/md/dm-crypt.c b/drivers/md/dm-crypt.c index f266c81f396f..0481223b1deb 100644 --- a/drivers/md/dm-crypt.c +++ b/drivers/md/dm-crypt.c @@ -332,7 +332,7 @@ static int crypt_iv_essiv_init(struct crypt_config *cc) int err; desc->tfm = essiv->hash_tfm; - desc->flags = CRYPTO_TFM_REQ_MAY_SLEEP; + desc->flags = 0; err = crypto_shash_digest(desc, cc->key, cc->key_size, essiv->salt); shash_desc_zero(desc); @@ -606,7 +606,7 @@ static int crypt_iv_lmk_one(struct crypt_config *cc, u8 *iv, int i, r; desc->tfm = lmk->hash_tfm; - desc->flags = CRYPTO_TFM_REQ_MAY_SLEEP; + desc->flags = 0; r = crypto_shash_init(desc); if (r) @@ -768,7 +768,7 @@ static int crypt_iv_tcw_whitening(struct crypt_config *cc, /* calculate crc32 for every 32bit part and xor it */ desc->tfm = tcw->crc32_tfm; - desc->flags = CRYPTO_TFM_REQ_MAY_SLEEP; + desc->flags = 0; for (i = 0; i < 4; i++) { r = crypto_shash_init(desc); if (r) @@ -1251,7 +1251,7 @@ static void crypt_alloc_req_skcipher(struct crypt_config *cc, * requests if driver request queue is full. */ skcipher_request_set_callback(ctx->r.req, - CRYPTO_TFM_REQ_MAY_BACKLOG | CRYPTO_TFM_REQ_MAY_SLEEP, + CRYPTO_TFM_REQ_MAY_BACKLOG, kcryptd_async_done, dmreq_of_req(cc, ctx->r.req)); } @@ -1268,7 +1268,7 @@ static void crypt_alloc_req_aead(struct crypt_config *cc, * requests if driver request queue is full. */ aead_request_set_callback(ctx->r.req_aead, - CRYPTO_TFM_REQ_MAY_BACKLOG | CRYPTO_TFM_REQ_MAY_SLEEP, + CRYPTO_TFM_REQ_MAY_BACKLOG, kcryptd_async_done, dmreq_of_req(cc, ctx->r.req_aead)); } diff --git a/drivers/md/dm-integrity.c b/drivers/md/dm-integrity.c index 378878599466..89ccb64342de 100644 --- a/drivers/md/dm-integrity.c +++ b/drivers/md/dm-integrity.c @@ -532,7 +532,7 @@ static void section_mac(struct dm_integrity_c *ic, unsigned section, __u8 result unsigned j, size; desc->tfm = ic->journal_mac; - desc->flags = CRYPTO_TFM_REQ_MAY_SLEEP; + desc->flags = 0; r = crypto_shash_init(desc); if (unlikely(r)) { @@ -676,7 +676,7 @@ static void complete_journal_encrypt(struct crypto_async_request *req, int err) static bool do_crypt(bool encrypt, struct skcipher_request *req, struct journal_completion *comp) { int r; - skcipher_request_set_callback(req, CRYPTO_TFM_REQ_MAY_BACKLOG | CRYPTO_TFM_REQ_MAY_SLEEP, + skcipher_request_set_callback(req, CRYPTO_TFM_REQ_MAY_BACKLOG, complete_journal_encrypt, comp); if (likely(encrypt)) r = crypto_skcipher_encrypt(req); diff --git a/drivers/md/dm-raid.c b/drivers/md/dm-raid.c index cae689de75fd..5ba067fa0c72 100644 --- a/drivers/md/dm-raid.c +++ b/drivers/md/dm-raid.c @@ -1,6 +1,6 @@ /* * Copyright (C) 2010-2011 Neil Brown - * Copyright (C) 2010-2017 Red Hat, Inc. All rights reserved. + * Copyright (C) 2010-2018 Red Hat, Inc. All rights reserved. * * This file is released under the GPL. */ @@ -29,9 +29,6 @@ */ #define MIN_RAID456_JOURNAL_SPACE (4*2048) -/* Global list of all raid sets */ -static LIST_HEAD(raid_sets); - static bool devices_handle_discard_safely = false; /* @@ -227,7 +224,6 @@ struct rs_layout { struct raid_set { struct dm_target *ti; - struct list_head list; uint32_t stripe_cache_entries; unsigned long ctr_flags; @@ -273,19 +269,6 @@ static void rs_config_restore(struct raid_set *rs, struct rs_layout *l) mddev->new_chunk_sectors = l->new_chunk_sectors; } -/* Find any raid_set in active slot for @rs on global list */ -static struct raid_set *rs_find_active(struct raid_set *rs) -{ - struct raid_set *r; - struct mapped_device *md = dm_table_get_md(rs->ti->table); - - list_for_each_entry(r, &raid_sets, list) - if (r != rs && dm_table_get_md(r->ti->table) == md) - return r; - - return NULL; -} - /* raid10 algorithms (i.e. formats) */ #define ALGORITHM_RAID10_DEFAULT 0 #define ALGORITHM_RAID10_NEAR 1 @@ -764,7 +747,6 @@ static struct raid_set *raid_set_alloc(struct dm_target *ti, struct raid_type *r mddev_init(&rs->md); - INIT_LIST_HEAD(&rs->list); rs->raid_disks = raid_devs; rs->delta_disks = 0; @@ -782,9 +764,6 @@ static struct raid_set *raid_set_alloc(struct dm_target *ti, struct raid_type *r for (i = 0; i < raid_devs; i++) md_rdev_init(&rs->dev[i].rdev); - /* Add @rs to global list. */ - list_add(&rs->list, &raid_sets); - /* * Remaining items to be initialized by further RAID params: * rs->md.persistent @@ -797,7 +776,7 @@ static struct raid_set *raid_set_alloc(struct dm_target *ti, struct raid_type *r return rs; } -/* Free all @rs allocations and remove it from global list. */ +/* Free all @rs allocations */ static void raid_set_free(struct raid_set *rs) { int i; @@ -815,8 +794,6 @@ static void raid_set_free(struct raid_set *rs) dm_put_device(rs->ti, rs->dev[i].data_dev); } - list_del(&rs->list); - kfree(rs); } @@ -2649,7 +2626,7 @@ static int rs_adjust_data_offsets(struct raid_set *rs) return 0; } - /* HM FIXME: get InSync raid_dev? */ + /* HM FIXME: get In_Sync raid_dev? */ rdev = &rs->dev[0].rdev; if (rs->delta_disks < 0) { @@ -3149,6 +3126,11 @@ static int raid_ctr(struct dm_target *ti, unsigned int argc, char **argv) set_bit(RT_FLAG_UPDATE_SBS, &rs->runtime_flags); rs_set_new(rs); } else if (rs_is_recovering(rs)) { + /* Rebuild particular devices */ + if (test_bit(__CTR_FLAG_REBUILD, &rs->ctr_flags)) { + set_bit(RT_FLAG_UPDATE_SBS, &rs->runtime_flags); + rs_setup_recovery(rs, MaxSector); + } /* A recovering raid set may be resized */ ; /* skip setup rs */ } else if (rs_is_reshaping(rs)) { @@ -3242,6 +3224,8 @@ static int raid_ctr(struct dm_target *ti, unsigned int argc, char **argv) /* Start raid set read-only and assumed clean to change in raid_resume() */ rs->md.ro = 1; rs->md.in_sync = 1; + + /* Keep array frozen */ set_bit(MD_RECOVERY_FROZEN, &rs->md.recovery); /* Has to be held on running the array */ @@ -3265,7 +3249,7 @@ static int raid_ctr(struct dm_target *ti, unsigned int argc, char **argv) rs->callbacks.congested_fn = raid_is_congested; dm_table_add_target_callbacks(ti->table, &rs->callbacks); - /* If raid4/5/6 journal mode explictely requested (only possible with journal dev) -> set it */ + /* If raid4/5/6 journal mode explicitly requested (only possible with journal dev) -> set it */ if (test_bit(__CTR_FLAG_JOURNAL_MODE, &rs->ctr_flags)) { r = r5c_journal_mode_set(&rs->md, rs->journal_dev.mode); if (r) { @@ -3350,32 +3334,53 @@ static int raid_map(struct dm_target *ti, struct bio *bio) return DM_MAPIO_SUBMITTED; } -/* Return string describing the current sync action of @mddev */ -static const char *decipher_sync_action(struct mddev *mddev, unsigned long recovery) +/* Return sync state string for @state */ +enum sync_state { st_frozen, st_reshape, st_resync, st_check, st_repair, st_recover, st_idle }; +static const char *sync_str(enum sync_state state) +{ + /* Has to be in above sync_state order! */ + static const char *sync_strs[] = { + "frozen", + "reshape", + "resync", + "check", + "repair", + "recover", + "idle" + }; + + return __within_range(state, 0, ARRAY_SIZE(sync_strs) - 1) ? sync_strs[state] : "undef"; +}; + +/* Return enum sync_state for @mddev derived from @recovery flags */ +static const enum sync_state decipher_sync_action(struct mddev *mddev, unsigned long recovery) { if (test_bit(MD_RECOVERY_FROZEN, &recovery)) - return "frozen"; + return st_frozen; - /* The MD sync thread can be done with io but still be running */ + /* The MD sync thread can be done with io or be interrupted but still be running */ if (!test_bit(MD_RECOVERY_DONE, &recovery) && (test_bit(MD_RECOVERY_RUNNING, &recovery) || (!mddev->ro && test_bit(MD_RECOVERY_NEEDED, &recovery)))) { if (test_bit(MD_RECOVERY_RESHAPE, &recovery)) - return "reshape"; + return st_reshape; if (test_bit(MD_RECOVERY_SYNC, &recovery)) { if (!test_bit(MD_RECOVERY_REQUESTED, &recovery)) - return "resync"; - else if (test_bit(MD_RECOVERY_CHECK, &recovery)) - return "check"; - return "repair"; + return st_resync; + if (test_bit(MD_RECOVERY_CHECK, &recovery)) + return st_check; + return st_repair; } if (test_bit(MD_RECOVERY_RECOVER, &recovery)) - return "recover"; + return st_recover; + + if (mddev->reshape_position != MaxSector) + return st_reshape; } - return "idle"; + return st_idle; } /* @@ -3409,6 +3414,7 @@ static sector_t rs_get_progress(struct raid_set *rs, unsigned long recovery, sector_t resync_max_sectors) { sector_t r; + enum sync_state state; struct mddev *mddev = &rs->md; clear_bit(RT_FLAG_RS_IN_SYNC, &rs->runtime_flags); @@ -3419,20 +3425,14 @@ static sector_t rs_get_progress(struct raid_set *rs, unsigned long recovery, set_bit(RT_FLAG_RS_IN_SYNC, &rs->runtime_flags); } else { - if (!test_bit(__CTR_FLAG_NOSYNC, &rs->ctr_flags) && - !test_bit(MD_RECOVERY_INTR, &recovery) && - (test_bit(MD_RECOVERY_NEEDED, &recovery) || - test_bit(MD_RECOVERY_RESHAPE, &recovery) || - test_bit(MD_RECOVERY_RUNNING, &recovery))) - r = mddev->curr_resync_completed; - else + state = decipher_sync_action(mddev, recovery); + + if (state == st_idle && !test_bit(MD_RECOVERY_INTR, &recovery)) r = mddev->recovery_cp; + else + r = mddev->curr_resync_completed; - if (r >= resync_max_sectors && - (!test_bit(MD_RECOVERY_REQUESTED, &recovery) || - (!test_bit(MD_RECOVERY_FROZEN, &recovery) && - !test_bit(MD_RECOVERY_NEEDED, &recovery) && - !test_bit(MD_RECOVERY_RUNNING, &recovery)))) { + if (state == st_idle && r >= resync_max_sectors) { /* * Sync complete. */ @@ -3440,24 +3440,20 @@ static sector_t rs_get_progress(struct raid_set *rs, unsigned long recovery, if (test_bit(MD_RECOVERY_RECOVER, &recovery)) set_bit(RT_FLAG_RS_IN_SYNC, &rs->runtime_flags); - } else if (test_bit(MD_RECOVERY_RECOVER, &recovery)) { + } else if (state == st_recover) /* * In case we are recovering, the array is not in sync * and health chars should show the recovering legs. */ ; - - } else if (test_bit(MD_RECOVERY_SYNC, &recovery) && - !test_bit(MD_RECOVERY_REQUESTED, &recovery)) { + else if (state == st_resync) /* * If "resync" is occurring, the raid set * is or may be out of sync hence the health * characters shall be 'a'. */ set_bit(RT_FLAG_RS_RESYNCING, &rs->runtime_flags); - - } else if (test_bit(MD_RECOVERY_RESHAPE, &recovery) && - !test_bit(MD_RECOVERY_REQUESTED, &recovery)) { + else if (state == st_reshape) /* * If "reshape" is occurring, the raid set * is or may be out of sync hence the health @@ -3465,7 +3461,7 @@ static sector_t rs_get_progress(struct raid_set *rs, unsigned long recovery, */ set_bit(RT_FLAG_RS_RESYNCING, &rs->runtime_flags); - } else if (test_bit(MD_RECOVERY_REQUESTED, &recovery)) { + else if (state == st_check || state == st_repair) /* * If "check" or "repair" is occurring, the raid set has * undergone an initial sync and the health characters @@ -3473,12 +3469,12 @@ static sector_t rs_get_progress(struct raid_set *rs, unsigned long recovery, */ set_bit(RT_FLAG_RS_IN_SYNC, &rs->runtime_flags); - } else { + else { struct md_rdev *rdev; /* * We are idle and recovery is needed, prevent 'A' chars race - * caused by components still set to in-sync by constrcuctor. + * caused by components still set to in-sync by constructor. */ if (test_bit(MD_RECOVERY_NEEDED, &recovery)) set_bit(RT_FLAG_RS_RESYNCING, &rs->runtime_flags); @@ -3542,7 +3538,7 @@ static void raid_status(struct dm_target *ti, status_type_t type, progress = rs_get_progress(rs, recovery, resync_max_sectors); resync_mismatches = (mddev->last_sync_action && !strcasecmp(mddev->last_sync_action, "check")) ? atomic64_read(&mddev->resync_mismatches) : 0; - sync_action = decipher_sync_action(&rs->md, recovery); + sync_action = sync_str(decipher_sync_action(&rs->md, recovery)); /* HM FIXME: do we want another state char for raid0? It shows 'D'/'A'/'-' now */ for (i = 0; i < rs->raid_disks; i++) @@ -3892,14 +3888,13 @@ static int rs_start_reshape(struct raid_set *rs) struct mddev *mddev = &rs->md; struct md_personality *pers = mddev->pers; + /* Don't allow the sync thread to work until the table gets reloaded. */ + set_bit(MD_RECOVERY_WAIT, &mddev->recovery); + r = rs_setup_reshape(rs); if (r) return r; - /* Need to be resumed to be able to start reshape, recovery is frozen until raid_resume() though */ - if (test_and_clear_bit(RT_FLAG_RS_SUSPENDED, &rs->runtime_flags)) - mddev_resume(mddev); - /* * Check any reshape constraints enforced by the personalility * @@ -3923,10 +3918,6 @@ static int rs_start_reshape(struct raid_set *rs) } } - /* Suspend because a resume will happen in raid_resume() */ - set_bit(RT_FLAG_RS_SUSPENDED, &rs->runtime_flags); - mddev_suspend(mddev); - /* * Now reshape got set up, update superblocks to * reflect the fact so that a table reload will @@ -3947,29 +3938,6 @@ static int raid_preresume(struct dm_target *ti) if (test_and_set_bit(RT_FLAG_RS_PRERESUMED, &rs->runtime_flags)) return 0; - if (!test_bit(__CTR_FLAG_REBUILD, &rs->ctr_flags)) { - struct raid_set *rs_active = rs_find_active(rs); - - if (rs_active) { - /* - * In case no rebuilds have been requested - * and an active table slot exists, copy - * current resynchonization completed and - * reshape position pointers across from - * suspended raid set in the active slot. - * - * This resumes the new mapping at current - * offsets to continue recover/reshape without - * necessarily redoing a raid set partially or - * causing data corruption in case of a reshape. - */ - if (rs_active->md.curr_resync_completed != MaxSector) - mddev->curr_resync_completed = rs_active->md.curr_resync_completed; - if (rs_active->md.reshape_position != MaxSector) - mddev->reshape_position = rs_active->md.reshape_position; - } - } - /* * The superblocks need to be updated on disk if the * array is new or new devices got added (thus zeroed @@ -4046,7 +4014,7 @@ static void raid_resume(struct dm_target *ti) static struct target_type raid_target = { .name = "raid", - .version = {1, 13, 2}, + .version = {1, 14, 0}, .module = THIS_MODULE, .ctr = raid_ctr, .dtr = raid_dtr, diff --git a/drivers/md/dm-thin-metadata.c b/drivers/md/dm-thin-metadata.c index 72142021b5c9..74f6770c70b1 100644 --- a/drivers/md/dm-thin-metadata.c +++ b/drivers/md/dm-thin-metadata.c @@ -189,6 +189,12 @@ struct dm_pool_metadata { sector_t data_block_size; /* + * We reserve a section of the metadata for commit overhead. + * All reported space does *not* include this. + */ + dm_block_t metadata_reserve; + + /* * Set if a transaction has to be aborted but the attempt to roll back * to the previous (good) transaction failed. The only pool metadata * operation possible in this state is the closing of the device. @@ -816,6 +822,22 @@ static int __commit_transaction(struct dm_pool_metadata *pmd) return dm_tm_commit(pmd->tm, sblock); } +static void __set_metadata_reserve(struct dm_pool_metadata *pmd) +{ + int r; + dm_block_t total; + dm_block_t max_blocks = 4096; /* 16M */ + + r = dm_sm_get_nr_blocks(pmd->metadata_sm, &total); + if (r) { + DMERR("could not get size of metadata device"); + pmd->metadata_reserve = max_blocks; + } else { + sector_div(total, 10); + pmd->metadata_reserve = min(max_blocks, total); + } +} + struct dm_pool_metadata *dm_pool_metadata_open(struct block_device *bdev, sector_t data_block_size, bool format_device) @@ -849,6 +871,8 @@ struct dm_pool_metadata *dm_pool_metadata_open(struct block_device *bdev, return ERR_PTR(r); } + __set_metadata_reserve(pmd); + return pmd; } @@ -1820,6 +1844,13 @@ int dm_pool_get_free_metadata_block_count(struct dm_pool_metadata *pmd, down_read(&pmd->root_lock); if (!pmd->fail_io) r = dm_sm_get_nr_free(pmd->metadata_sm, result); + + if (!r) { + if (*result < pmd->metadata_reserve) + *result = 0; + else + *result -= pmd->metadata_reserve; + } up_read(&pmd->root_lock); return r; @@ -1932,8 +1963,11 @@ int dm_pool_resize_metadata_dev(struct dm_pool_metadata *pmd, dm_block_t new_cou int r = -EINVAL; down_write(&pmd->root_lock); - if (!pmd->fail_io) + if (!pmd->fail_io) { r = __resize_space_map(pmd->metadata_sm, new_count); + if (!r) + __set_metadata_reserve(pmd); + } up_write(&pmd->root_lock); return r; diff --git a/drivers/md/dm-thin.c b/drivers/md/dm-thin.c index 7bd60a150f8f..aaf1ad481ee8 100644 --- a/drivers/md/dm-thin.c +++ b/drivers/md/dm-thin.c @@ -200,7 +200,13 @@ struct dm_thin_new_mapping; enum pool_mode { PM_WRITE, /* metadata may be changed */ PM_OUT_OF_DATA_SPACE, /* metadata may be changed, though data may not be allocated */ + + /* + * Like READ_ONLY, except may switch back to WRITE on metadata resize. Reported as READ_ONLY. + */ + PM_OUT_OF_METADATA_SPACE, PM_READ_ONLY, /* metadata may not be changed */ + PM_FAIL, /* all I/O fails */ }; @@ -1371,7 +1377,35 @@ static void set_pool_mode(struct pool *pool, enum pool_mode new_mode); static void requeue_bios(struct pool *pool); -static void check_for_space(struct pool *pool) +static bool is_read_only_pool_mode(enum pool_mode mode) +{ + return (mode == PM_OUT_OF_METADATA_SPACE || mode == PM_READ_ONLY); +} + +static bool is_read_only(struct pool *pool) +{ + return is_read_only_pool_mode(get_pool_mode(pool)); +} + +static void check_for_metadata_space(struct pool *pool) +{ + int r; + const char *ooms_reason = NULL; + dm_block_t nr_free; + + r = dm_pool_get_free_metadata_block_count(pool->pmd, &nr_free); + if (r) + ooms_reason = "Could not get free metadata blocks"; + else if (!nr_free) + ooms_reason = "No free metadata blocks"; + + if (ooms_reason && !is_read_only(pool)) { + DMERR("%s", ooms_reason); + set_pool_mode(pool, PM_OUT_OF_METADATA_SPACE); + } +} + +static void check_for_data_space(struct pool *pool) { int r; dm_block_t nr_free; @@ -1397,14 +1431,16 @@ static int commit(struct pool *pool) { int r; - if (get_pool_mode(pool) >= PM_READ_ONLY) + if (get_pool_mode(pool) >= PM_OUT_OF_METADATA_SPACE) return -EINVAL; r = dm_pool_commit_metadata(pool->pmd); if (r) metadata_operation_failed(pool, "dm_pool_commit_metadata", r); - else - check_for_space(pool); + else { + check_for_metadata_space(pool); + check_for_data_space(pool); + } return r; } @@ -1470,6 +1506,19 @@ static int alloc_data_block(struct thin_c *tc, dm_block_t *result) return r; } + r = dm_pool_get_free_metadata_block_count(pool->pmd, &free_blocks); + if (r) { + metadata_operation_failed(pool, "dm_pool_get_free_metadata_block_count", r); + return r; + } + + if (!free_blocks) { + /* Let's commit before we use up the metadata reserve. */ + r = commit(pool); + if (r) + return r; + } + return 0; } @@ -1501,6 +1550,7 @@ static blk_status_t should_error_unserviceable_bio(struct pool *pool) case PM_OUT_OF_DATA_SPACE: return pool->pf.error_if_no_space ? BLK_STS_NOSPC : 0; + case PM_OUT_OF_METADATA_SPACE: case PM_READ_ONLY: case PM_FAIL: return BLK_STS_IOERR; @@ -2464,8 +2514,9 @@ static void set_pool_mode(struct pool *pool, enum pool_mode new_mode) error_retry_list(pool); break; + case PM_OUT_OF_METADATA_SPACE: case PM_READ_ONLY: - if (old_mode != new_mode) + if (!is_read_only_pool_mode(old_mode)) notify_of_pool_mode_change(pool, "read-only"); dm_pool_metadata_read_only(pool->pmd); pool->process_bio = process_bio_read_only; @@ -3403,6 +3454,10 @@ static int maybe_resize_metadata_dev(struct dm_target *ti, bool *need_commit) DMINFO("%s: growing the metadata device from %llu to %llu blocks", dm_device_name(pool->pool_md), sb_metadata_dev_size, metadata_dev_size); + + if (get_pool_mode(pool) == PM_OUT_OF_METADATA_SPACE) + set_pool_mode(pool, PM_WRITE); + r = dm_pool_resize_metadata_dev(pool->pmd, metadata_dev_size); if (r) { metadata_operation_failed(pool, "dm_pool_resize_metadata_dev", r); @@ -3707,7 +3762,7 @@ static int pool_message(struct dm_target *ti, unsigned argc, char **argv, struct pool_c *pt = ti->private; struct pool *pool = pt->pool; - if (get_pool_mode(pool) >= PM_READ_ONLY) { + if (get_pool_mode(pool) >= PM_OUT_OF_METADATA_SPACE) { DMERR("%s: unable to service pool target messages in READ_ONLY or FAIL mode", dm_device_name(pool->pool_md)); return -EOPNOTSUPP; @@ -3781,6 +3836,7 @@ static void pool_status(struct dm_target *ti, status_type_t type, dm_block_t nr_blocks_data; dm_block_t nr_blocks_metadata; dm_block_t held_root; + enum pool_mode mode; char buf[BDEVNAME_SIZE]; char buf2[BDEVNAME_SIZE]; struct pool_c *pt = ti->private; @@ -3851,9 +3907,10 @@ static void pool_status(struct dm_target *ti, status_type_t type, else DMEMIT("- "); - if (pool->pf.mode == PM_OUT_OF_DATA_SPACE) + mode = get_pool_mode(pool); + if (mode == PM_OUT_OF_DATA_SPACE) DMEMIT("out_of_data_space "); - else if (pool->pf.mode == PM_READ_ONLY) + else if (is_read_only_pool_mode(mode)) DMEMIT("ro "); else DMEMIT("rw "); diff --git a/drivers/md/dm-verity-target.c b/drivers/md/dm-verity-target.c index 12decdbd722d..fc65f0dedf7f 100644 --- a/drivers/md/dm-verity-target.c +++ b/drivers/md/dm-verity-target.c @@ -99,10 +99,26 @@ static int verity_hash_update(struct dm_verity *v, struct ahash_request *req, { struct scatterlist sg; - sg_init_one(&sg, data, len); - ahash_request_set_crypt(req, &sg, NULL, len); - - return crypto_wait_req(crypto_ahash_update(req), wait); + if (likely(!is_vmalloc_addr(data))) { + sg_init_one(&sg, data, len); + ahash_request_set_crypt(req, &sg, NULL, len); + return crypto_wait_req(crypto_ahash_update(req), wait); + } else { + do { + int r; + size_t this_step = min_t(size_t, len, PAGE_SIZE - offset_in_page(data)); + flush_kernel_vmap_range((void *)data, this_step); + sg_init_table(&sg, 1); + sg_set_page(&sg, vmalloc_to_page(data), this_step, offset_in_page(data)); + ahash_request_set_crypt(req, &sg, NULL, this_step); + r = crypto_wait_req(crypto_ahash_update(req), wait); + if (unlikely(r)) + return r; + data += this_step; + len -= this_step; + } while (len); + return 0; + } } /* diff --git a/drivers/md/md-cluster.c b/drivers/md/md-cluster.c index 94329e03001e..0b2af6e74fc3 100644 --- a/drivers/md/md-cluster.c +++ b/drivers/md/md-cluster.c @@ -1276,18 +1276,18 @@ static int resync_info_update(struct mddev *mddev, sector_t lo, sector_t hi) static int resync_finish(struct mddev *mddev) { struct md_cluster_info *cinfo = mddev->cluster_info; + int ret = 0; clear_bit(MD_RESYNCING_REMOTE, &mddev->recovery); - dlm_unlock_sync(cinfo->resync_lockres); /* * If resync thread is interrupted so we can't say resync is finished, * another node will launch resync thread to continue. */ - if (test_bit(MD_CLOSING, &mddev->flags)) - return 0; - else - return resync_info_update(mddev, 0, 0); + if (!test_bit(MD_CLOSING, &mddev->flags)) + ret = resync_info_update(mddev, 0, 0); + dlm_unlock_sync(cinfo->resync_lockres); + return ret; } static int area_resyncing(struct mddev *mddev, int direction, diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c index 981898049491..d6f7978b4449 100644 --- a/drivers/md/raid10.c +++ b/drivers/md/raid10.c @@ -4529,11 +4529,12 @@ static sector_t reshape_request(struct mddev *mddev, sector_t sector_nr, allow_barrier(conf); } + raise_barrier(conf, 0); read_more: /* Now schedule reads for blocks from sector_nr to last */ r10_bio = raid10_alloc_init_r10buf(conf); r10_bio->state = 0; - raise_barrier(conf, sectors_done != 0); + raise_barrier(conf, 1); atomic_set(&r10_bio->remaining, 0); r10_bio->mddev = mddev; r10_bio->sector = sector_nr; @@ -4629,6 +4630,8 @@ read_more: if (sector_nr <= last) goto read_more; + lower_barrier(conf); + /* Now that we have done the whole section we can * update reshape_progress */ diff --git a/drivers/md/raid5-log.h b/drivers/md/raid5-log.h index a001808a2b77..bfb811407061 100644 --- a/drivers/md/raid5-log.h +++ b/drivers/md/raid5-log.h @@ -46,6 +46,11 @@ extern int ppl_modify_log(struct r5conf *conf, struct md_rdev *rdev, bool add); extern void ppl_quiesce(struct r5conf *conf, int quiesce); extern int ppl_handle_flush_request(struct r5l_log *log, struct bio *bio); +static inline bool raid5_has_log(struct r5conf *conf) +{ + return test_bit(MD_HAS_JOURNAL, &conf->mddev->flags); +} + static inline bool raid5_has_ppl(struct r5conf *conf) { return test_bit(MD_HAS_PPL, &conf->mddev->flags); diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c index 4ce0d7502fad..e4e98f47865d 100644 --- a/drivers/md/raid5.c +++ b/drivers/md/raid5.c @@ -733,7 +733,7 @@ static bool stripe_can_batch(struct stripe_head *sh) { struct r5conf *conf = sh->raid_conf; - if (conf->log || raid5_has_ppl(conf)) + if (raid5_has_log(conf) || raid5_has_ppl(conf)) return false; return test_bit(STRIPE_BATCH_READY, &sh->state) && !test_bit(STRIPE_BITMAP_PENDING, &sh->state) && @@ -7737,7 +7737,7 @@ static int raid5_resize(struct mddev *mddev, sector_t sectors) sector_t newsize; struct r5conf *conf = mddev->private; - if (conf->log || raid5_has_ppl(conf)) + if (raid5_has_log(conf) || raid5_has_ppl(conf)) return -EINVAL; sectors &= ~((sector_t)conf->chunk_sectors - 1); newsize = raid5_size(mddev, sectors, mddev->raid_disks); @@ -7788,7 +7788,7 @@ static int check_reshape(struct mddev *mddev) { struct r5conf *conf = mddev->private; - if (conf->log || raid5_has_ppl(conf)) + if (raid5_has_log(conf) || raid5_has_ppl(conf)) return -EINVAL; if (mddev->delta_disks == 0 && mddev->new_layout == mddev->layout && diff --git a/drivers/media/i2c/mt9v111.c b/drivers/media/i2c/mt9v111.c index b5410aeb5fe2..bb41bea950ac 100644 --- a/drivers/media/i2c/mt9v111.c +++ b/drivers/media/i2c/mt9v111.c @@ -1159,41 +1159,21 @@ static int mt9v111_probe(struct i2c_client *client) V4L2_CID_AUTO_WHITE_BALANCE, 0, 1, 1, V4L2_WHITE_BALANCE_AUTO); - if (IS_ERR_OR_NULL(mt9v111->auto_awb)) { - ret = PTR_ERR(mt9v111->auto_awb); - goto error_free_ctrls; - } - mt9v111->auto_exp = v4l2_ctrl_new_std_menu(&mt9v111->ctrls, &mt9v111_ctrl_ops, V4L2_CID_EXPOSURE_AUTO, V4L2_EXPOSURE_MANUAL, 0, V4L2_EXPOSURE_AUTO); - if (IS_ERR_OR_NULL(mt9v111->auto_exp)) { - ret = PTR_ERR(mt9v111->auto_exp); - goto error_free_ctrls; - } - - /* Initialize timings */ mt9v111->hblank = v4l2_ctrl_new_std(&mt9v111->ctrls, &mt9v111_ctrl_ops, V4L2_CID_HBLANK, MT9V111_CORE_R05_MIN_HBLANK, MT9V111_CORE_R05_MAX_HBLANK, 1, MT9V111_CORE_R05_DEF_HBLANK); - if (IS_ERR_OR_NULL(mt9v111->hblank)) { - ret = PTR_ERR(mt9v111->hblank); - goto error_free_ctrls; - } - mt9v111->vblank = v4l2_ctrl_new_std(&mt9v111->ctrls, &mt9v111_ctrl_ops, V4L2_CID_VBLANK, MT9V111_CORE_R06_MIN_VBLANK, MT9V111_CORE_R06_MAX_VBLANK, 1, MT9V111_CORE_R06_DEF_VBLANK); - if (IS_ERR_OR_NULL(mt9v111->vblank)) { - ret = PTR_ERR(mt9v111->vblank); - goto error_free_ctrls; - } /* PIXEL_RATE is fixed: just expose it to user space. */ v4l2_ctrl_new_std(&mt9v111->ctrls, &mt9v111_ctrl_ops, @@ -1201,6 +1181,10 @@ static int mt9v111_probe(struct i2c_client *client) DIV_ROUND_CLOSEST(mt9v111->sysclk, 2), 1, DIV_ROUND_CLOSEST(mt9v111->sysclk, 2)); + if (mt9v111->ctrls.error) { + ret = mt9v111->ctrls.error; + goto error_free_ctrls; + } mt9v111->sd.ctrl_handler = &mt9v111->ctrls; /* Start with default configuration: 640x480 UYVY. */ @@ -1226,26 +1210,27 @@ static int mt9v111_probe(struct i2c_client *client) mt9v111->pad.flags = MEDIA_PAD_FL_SOURCE; ret = media_entity_pads_init(&mt9v111->sd.entity, 1, &mt9v111->pad); if (ret) - goto error_free_ctrls; + goto error_free_entity; #endif ret = mt9v111_chip_probe(mt9v111); if (ret) - goto error_free_ctrls; + goto error_free_entity; ret = v4l2_async_register_subdev(&mt9v111->sd); if (ret) - goto error_free_ctrls; + goto error_free_entity; return 0; -error_free_ctrls: - v4l2_ctrl_handler_free(&mt9v111->ctrls); - +error_free_entity: #if IS_ENABLED(CONFIG_MEDIA_CONTROLLER) media_entity_cleanup(&mt9v111->sd.entity); #endif +error_free_ctrls: + v4l2_ctrl_handler_free(&mt9v111->ctrls); + mutex_destroy(&mt9v111->pwr_mutex); mutex_destroy(&mt9v111->stream_mutex); @@ -1259,12 +1244,12 @@ static int mt9v111_remove(struct i2c_client *client) v4l2_async_unregister_subdev(sd); - v4l2_ctrl_handler_free(&mt9v111->ctrls); - #if IS_ENABLED(CONFIG_MEDIA_CONTROLLER) media_entity_cleanup(&sd->entity); #endif + v4l2_ctrl_handler_free(&mt9v111->ctrls); + mutex_destroy(&mt9v111->pwr_mutex); mutex_destroy(&mt9v111->stream_mutex); diff --git a/drivers/media/platform/Kconfig b/drivers/media/platform/Kconfig index 94c1fe0e9787..54fe90acb5b2 100644 --- a/drivers/media/platform/Kconfig +++ b/drivers/media/platform/Kconfig @@ -541,6 +541,8 @@ config VIDEO_CROS_EC_CEC depends on MFD_CROS_EC select CEC_CORE select CEC_NOTIFIER + select CHROME_PLATFORMS + select CROS_EC_PROTO ---help--- If you say yes here you will get support for the ChromeOS Embedded Controller's CEC. diff --git a/drivers/media/platform/qcom/camss/camss-csid.c b/drivers/media/platform/qcom/camss/camss-csid.c index 729b31891466..a5ae85674ffb 100644 --- a/drivers/media/platform/qcom/camss/camss-csid.c +++ b/drivers/media/platform/qcom/camss/camss-csid.c @@ -10,6 +10,7 @@ #include <linux/clk.h> #include <linux/completion.h> #include <linux/interrupt.h> +#include <linux/io.h> #include <linux/kernel.h> #include <linux/of.h> #include <linux/platform_device.h> diff --git a/drivers/media/platform/qcom/camss/camss-csiphy-2ph-1-0.c b/drivers/media/platform/qcom/camss/camss-csiphy-2ph-1-0.c index c832539397d7..12bce391d71f 100644 --- a/drivers/media/platform/qcom/camss/camss-csiphy-2ph-1-0.c +++ b/drivers/media/platform/qcom/camss/camss-csiphy-2ph-1-0.c @@ -12,6 +12,7 @@ #include <linux/delay.h> #include <linux/interrupt.h> +#include <linux/io.h> #define CAMSS_CSI_PHY_LNn_CFG2(n) (0x004 + 0x40 * (n)) #define CAMSS_CSI_PHY_LNn_CFG3(n) (0x008 + 0x40 * (n)) diff --git a/drivers/media/platform/qcom/camss/camss-csiphy-3ph-1-0.c b/drivers/media/platform/qcom/camss/camss-csiphy-3ph-1-0.c index bcd0dfd33618..2e65caf1ecae 100644 --- a/drivers/media/platform/qcom/camss/camss-csiphy-3ph-1-0.c +++ b/drivers/media/platform/qcom/camss/camss-csiphy-3ph-1-0.c @@ -12,6 +12,7 @@ #include <linux/delay.h> #include <linux/interrupt.h> +#include <linux/io.h> #define CSIPHY_3PH_LNn_CFG1(n) (0x000 + 0x100 * (n)) #define CSIPHY_3PH_LNn_CFG1_SWI_REC_DLY_PRG (BIT(7) | BIT(6)) diff --git a/drivers/media/platform/qcom/camss/camss-csiphy.c b/drivers/media/platform/qcom/camss/camss-csiphy.c index 4559f3b1b38c..008afb85023b 100644 --- a/drivers/media/platform/qcom/camss/camss-csiphy.c +++ b/drivers/media/platform/qcom/camss/camss-csiphy.c @@ -10,6 +10,7 @@ #include <linux/clk.h> #include <linux/delay.h> #include <linux/interrupt.h> +#include <linux/io.h> #include <linux/kernel.h> #include <linux/of.h> #include <linux/platform_device.h> diff --git a/drivers/media/platform/qcom/camss/camss-ispif.c b/drivers/media/platform/qcom/camss/camss-ispif.c index 7f269021d08c..1f33b4eb198c 100644 --- a/drivers/media/platform/qcom/camss/camss-ispif.c +++ b/drivers/media/platform/qcom/camss/camss-ispif.c @@ -10,6 +10,7 @@ #include <linux/clk.h> #include <linux/completion.h> #include <linux/interrupt.h> +#include <linux/io.h> #include <linux/iopoll.h> #include <linux/kernel.h> #include <linux/mutex.h> @@ -1076,8 +1077,8 @@ int msm_ispif_subdev_init(struct ispif_device *ispif, else return -EINVAL; - ispif->line = kcalloc(ispif->line_num, sizeof(*ispif->line), - GFP_KERNEL); + ispif->line = devm_kcalloc(dev, ispif->line_num, sizeof(*ispif->line), + GFP_KERNEL); if (!ispif->line) return -ENOMEM; diff --git a/drivers/media/platform/qcom/camss/camss-vfe-4-1.c b/drivers/media/platform/qcom/camss/camss-vfe-4-1.c index da3a9fed9f2d..174a36be6f5d 100644 --- a/drivers/media/platform/qcom/camss/camss-vfe-4-1.c +++ b/drivers/media/platform/qcom/camss/camss-vfe-4-1.c @@ -9,6 +9,7 @@ */ #include <linux/interrupt.h> +#include <linux/io.h> #include <linux/iopoll.h> #include "camss-vfe.h" diff --git a/drivers/media/platform/qcom/camss/camss-vfe-4-7.c b/drivers/media/platform/qcom/camss/camss-vfe-4-7.c index 4c584bffd179..0dca8bf9281e 100644 --- a/drivers/media/platform/qcom/camss/camss-vfe-4-7.c +++ b/drivers/media/platform/qcom/camss/camss-vfe-4-7.c @@ -9,6 +9,7 @@ */ #include <linux/interrupt.h> +#include <linux/io.h> #include <linux/iopoll.h> #include "camss-vfe.h" diff --git a/drivers/media/platform/qcom/camss/camss.c b/drivers/media/platform/qcom/camss/camss.c index dcc0c30ef1b1..669615fff6a0 100644 --- a/drivers/media/platform/qcom/camss/camss.c +++ b/drivers/media/platform/qcom/camss/camss.c @@ -848,17 +848,18 @@ static int camss_probe(struct platform_device *pdev) return -EINVAL; } - camss->csiphy = kcalloc(camss->csiphy_num, sizeof(*camss->csiphy), - GFP_KERNEL); + camss->csiphy = devm_kcalloc(dev, camss->csiphy_num, + sizeof(*camss->csiphy), GFP_KERNEL); if (!camss->csiphy) return -ENOMEM; - camss->csid = kcalloc(camss->csid_num, sizeof(*camss->csid), - GFP_KERNEL); + camss->csid = devm_kcalloc(dev, camss->csid_num, sizeof(*camss->csid), + GFP_KERNEL); if (!camss->csid) return -ENOMEM; - camss->vfe = kcalloc(camss->vfe_num, sizeof(*camss->vfe), GFP_KERNEL); + camss->vfe = devm_kcalloc(dev, camss->vfe_num, sizeof(*camss->vfe), + GFP_KERNEL); if (!camss->vfe) return -ENOMEM; @@ -993,12 +994,12 @@ static const struct of_device_id camss_dt_match[] = { MODULE_DEVICE_TABLE(of, camss_dt_match); -static int camss_runtime_suspend(struct device *dev) +static int __maybe_unused camss_runtime_suspend(struct device *dev) { return 0; } -static int camss_runtime_resume(struct device *dev) +static int __maybe_unused camss_runtime_resume(struct device *dev) { return 0; } diff --git a/drivers/media/usb/dvb-usb-v2/af9035.c b/drivers/media/usb/dvb-usb-v2/af9035.c index 666d319d3d1a..1f6c1eefe389 100644 --- a/drivers/media/usb/dvb-usb-v2/af9035.c +++ b/drivers/media/usb/dvb-usb-v2/af9035.c @@ -402,8 +402,10 @@ static int af9035_i2c_master_xfer(struct i2c_adapter *adap, if (msg[0].addr == state->af9033_i2c_addr[1]) reg |= 0x100000; - ret = af9035_wr_regs(d, reg, &msg[0].buf[3], - msg[0].len - 3); + ret = (msg[0].len >= 3) ? af9035_wr_regs(d, reg, + &msg[0].buf[3], + msg[0].len - 3) + : -EOPNOTSUPP; } else { /* I2C write */ u8 buf[MAX_XFER_SIZE]; diff --git a/drivers/memory/ti-aemif.c b/drivers/memory/ti-aemif.c index 31112f622b88..475e5b3790ed 100644 --- a/drivers/memory/ti-aemif.c +++ b/drivers/memory/ti-aemif.c @@ -411,7 +411,7 @@ static int aemif_probe(struct platform_device *pdev) if (ret < 0) goto error; } - } else { + } else if (pdata) { for (i = 0; i < pdata->num_sub_devices; i++) { pdata->sub_devices[i].dev.parent = dev; ret = platform_device_register(&pdata->sub_devices[i]); diff --git a/drivers/mfd/omap-usb-host.c b/drivers/mfd/omap-usb-host.c index e11ab12fbdf2..800986a79704 100644 --- a/drivers/mfd/omap-usb-host.c +++ b/drivers/mfd/omap-usb-host.c @@ -528,8 +528,8 @@ static int usbhs_omap_get_dt_pdata(struct device *dev, } static const struct of_device_id usbhs_child_match_table[] = { - { .compatible = "ti,omap-ehci", }, - { .compatible = "ti,omap-ohci", }, + { .compatible = "ti,ehci-omap", }, + { .compatible = "ti,ohci-omap3", }, { } }; @@ -855,6 +855,7 @@ static struct platform_driver usbhs_omap_driver = { .pm = &usbhsomap_dev_pm_ops, .of_match_table = usbhs_omap_dt_ids, }, + .probe = usbhs_omap_probe, .remove = usbhs_omap_remove, }; @@ -864,9 +865,9 @@ MODULE_ALIAS("platform:" USBHS_DRIVER_NAME); MODULE_LICENSE("GPL v2"); MODULE_DESCRIPTION("usb host common core driver for omap EHCI and OHCI"); -static int __init omap_usbhs_drvinit(void) +static int omap_usbhs_drvinit(void) { - return platform_driver_probe(&usbhs_omap_driver, usbhs_omap_probe); + return platform_driver_register(&usbhs_omap_driver); } /* @@ -878,7 +879,7 @@ static int __init omap_usbhs_drvinit(void) */ fs_initcall_sync(omap_usbhs_drvinit); -static void __exit omap_usbhs_drvexit(void) +static void omap_usbhs_drvexit(void) { platform_driver_unregister(&usbhs_omap_driver); } diff --git a/drivers/misc/hmc6352.c b/drivers/misc/hmc6352.c index eeb7eef62174..38f90e179927 100644 --- a/drivers/misc/hmc6352.c +++ b/drivers/misc/hmc6352.c @@ -27,6 +27,7 @@ #include <linux/err.h> #include <linux/delay.h> #include <linux/sysfs.h> +#include <linux/nospec.h> static DEFINE_MUTEX(compass_mutex); @@ -50,6 +51,7 @@ static int compass_store(struct device *dev, const char *buf, size_t count, return ret; if (val >= strlen(map)) return -EINVAL; + val = array_index_nospec(val, strlen(map)); mutex_lock(&compass_mutex); ret = compass_command(c, map[val]); mutex_unlock(&compass_mutex); diff --git a/drivers/misc/ibmvmc.c b/drivers/misc/ibmvmc.c index 8f82bb9d11e2..b8aaa684c397 100644 --- a/drivers/misc/ibmvmc.c +++ b/drivers/misc/ibmvmc.c @@ -2131,7 +2131,7 @@ static int ibmvmc_init_crq_queue(struct crq_server_adapter *adapter) retrc = plpar_hcall_norets(H_REG_CRQ, vdev->unit_address, queue->msg_token, PAGE_SIZE); - retrc = rc; + rc = retrc; if (rc == H_RESOURCE) rc = ibmvmc_reset_crq_queue(adapter); diff --git a/drivers/misc/mei/bus.c b/drivers/misc/mei/bus.c index 7bba62a72921..fc3872fe7b25 100644 --- a/drivers/misc/mei/bus.c +++ b/drivers/misc/mei/bus.c @@ -521,17 +521,15 @@ int mei_cldev_enable(struct mei_cl_device *cldev) cl = cldev->cl; + mutex_lock(&bus->device_lock); if (cl->state == MEI_FILE_UNINITIALIZED) { - mutex_lock(&bus->device_lock); ret = mei_cl_link(cl); - mutex_unlock(&bus->device_lock); if (ret) - return ret; + goto out; /* update pointers */ cl->cldev = cldev; } - mutex_lock(&bus->device_lock); if (mei_cl_is_connected(cl)) { ret = 0; goto out; @@ -616,9 +614,8 @@ int mei_cldev_disable(struct mei_cl_device *cldev) if (err < 0) dev_err(bus->dev, "Could not disconnect from the ME client\n"); -out: mei_cl_bus_module_put(cldev); - +out: /* Flush queues and remove any pending read */ mei_cl_flush_queues(cl, NULL); mei_cl_unlink(cl); @@ -876,12 +873,13 @@ static void mei_cl_bus_dev_release(struct device *dev) mei_me_cl_put(cldev->me_cl); mei_dev_bus_put(cldev->bus); + mei_cl_unlink(cldev->cl); kfree(cldev->cl); kfree(cldev); } static const struct device_type mei_cl_device_type = { - .release = mei_cl_bus_dev_release, + .release = mei_cl_bus_dev_release, }; /** diff --git a/drivers/misc/mei/client.c b/drivers/misc/mei/client.c index 4ab6251d418e..ebdcf0b450e2 100644 --- a/drivers/misc/mei/client.c +++ b/drivers/misc/mei/client.c @@ -1767,7 +1767,7 @@ out: } } - rets = buf->size; + rets = len; err: cl_dbg(dev, cl, "rpm: autosuspend\n"); pm_runtime_mark_last_busy(dev->dev); diff --git a/drivers/misc/mei/hbm.c b/drivers/misc/mei/hbm.c index 09e233d4c0de..e56f3e72d57a 100644 --- a/drivers/misc/mei/hbm.c +++ b/drivers/misc/mei/hbm.c @@ -1161,15 +1161,18 @@ int mei_hbm_dispatch(struct mei_device *dev, struct mei_msg_hdr *hdr) props_res = (struct hbm_props_response *)mei_msg; - if (props_res->status) { + if (props_res->status == MEI_HBMS_CLIENT_NOT_FOUND) { + dev_dbg(dev->dev, "hbm: properties response: %d CLIENT_NOT_FOUND\n", + props_res->me_addr); + } else if (props_res->status) { dev_err(dev->dev, "hbm: properties response: wrong status = %d %s\n", props_res->status, mei_hbm_status_str(props_res->status)); return -EPROTO; + } else { + mei_hbm_me_cl_add(dev, props_res); } - mei_hbm_me_cl_add(dev, props_res); - /* request property for the next client */ if (mei_hbm_prop_req(dev, props_res->me_addr + 1)) return -EIO; diff --git a/drivers/mmc/host/meson-mx-sdio.c b/drivers/mmc/host/meson-mx-sdio.c index 09cb89645d06..2cfec33178c1 100644 --- a/drivers/mmc/host/meson-mx-sdio.c +++ b/drivers/mmc/host/meson-mx-sdio.c @@ -517,19 +517,23 @@ static struct mmc_host_ops meson_mx_mmc_ops = { static struct platform_device *meson_mx_mmc_slot_pdev(struct device *parent) { struct device_node *slot_node; + struct platform_device *pdev; /* * TODO: the MMC core framework currently does not support * controllers with multiple slots properly. So we only register * the first slot for now */ - slot_node = of_find_compatible_node(parent->of_node, NULL, "mmc-slot"); + slot_node = of_get_compatible_child(parent->of_node, "mmc-slot"); if (!slot_node) { dev_warn(parent, "no 'mmc-slot' sub-node found\n"); return ERR_PTR(-ENOENT); } - return of_platform_device_create(slot_node, NULL, parent); + pdev = of_platform_device_create(slot_node, NULL, parent); + of_node_put(slot_node); + + return pdev; } static int meson_mx_mmc_add_host(struct meson_mx_mmc_host *host) diff --git a/drivers/mmc/host/omap_hsmmc.c b/drivers/mmc/host/omap_hsmmc.c index 071693ebfe18..68760d4a5d3d 100644 --- a/drivers/mmc/host/omap_hsmmc.c +++ b/drivers/mmc/host/omap_hsmmc.c @@ -2177,6 +2177,7 @@ static int omap_hsmmc_remove(struct platform_device *pdev) dma_release_channel(host->tx_chan); dma_release_channel(host->rx_chan); + dev_pm_clear_wake_irq(host->dev); pm_runtime_dont_use_autosuspend(host->dev); pm_runtime_put_sync(host->dev); pm_runtime_disable(host->dev); diff --git a/drivers/mtd/devices/m25p80.c b/drivers/mtd/devices/m25p80.c index cbfafc453274..270d3c9580c5 100644 --- a/drivers/mtd/devices/m25p80.c +++ b/drivers/mtd/devices/m25p80.c @@ -39,13 +39,23 @@ static int m25p80_read_reg(struct spi_nor *nor, u8 code, u8 *val, int len) struct spi_mem_op op = SPI_MEM_OP(SPI_MEM_OP_CMD(code, 1), SPI_MEM_OP_NO_ADDR, SPI_MEM_OP_NO_DUMMY, - SPI_MEM_OP_DATA_IN(len, val, 1)); + SPI_MEM_OP_DATA_IN(len, NULL, 1)); + void *scratchbuf; int ret; + scratchbuf = kmalloc(len, GFP_KERNEL); + if (!scratchbuf) + return -ENOMEM; + + op.data.buf.in = scratchbuf; ret = spi_mem_exec_op(flash->spimem, &op); if (ret < 0) dev_err(&flash->spimem->spi->dev, "error %d reading %x\n", ret, code); + else + memcpy(val, scratchbuf, len); + + kfree(scratchbuf); return ret; } @@ -56,9 +66,19 @@ static int m25p80_write_reg(struct spi_nor *nor, u8 opcode, u8 *buf, int len) struct spi_mem_op op = SPI_MEM_OP(SPI_MEM_OP_CMD(opcode, 1), SPI_MEM_OP_NO_ADDR, SPI_MEM_OP_NO_DUMMY, - SPI_MEM_OP_DATA_OUT(len, buf, 1)); + SPI_MEM_OP_DATA_OUT(len, NULL, 1)); + void *scratchbuf; + int ret; - return spi_mem_exec_op(flash->spimem, &op); + scratchbuf = kmemdup(buf, len, GFP_KERNEL); + if (!scratchbuf) + return -ENOMEM; + + op.data.buf.out = scratchbuf; + ret = spi_mem_exec_op(flash->spimem, &op); + kfree(scratchbuf); + + return ret; } static ssize_t m25p80_write(struct spi_nor *nor, loff_t to, size_t len, diff --git a/drivers/mtd/mtdpart.c b/drivers/mtd/mtdpart.c index 52e2cb35fc79..99c460facd5e 100644 --- a/drivers/mtd/mtdpart.c +++ b/drivers/mtd/mtdpart.c @@ -873,8 +873,11 @@ static int mtd_part_of_parse(struct mtd_info *master, int ret, err = 0; np = mtd_get_of_node(master); - if (!mtd_is_partition(master)) + if (mtd_is_partition(master)) + of_node_get(np); + else np = of_get_child_by_name(np, "partitions"); + of_property_for_each_string(np, "compatible", prop, compat) { parser = mtd_part_get_compatible_parser(compat); if (!parser) diff --git a/drivers/mtd/nand/raw/denali.c b/drivers/mtd/nand/raw/denali.c index 67b2065e7a19..b864b93dd289 100644 --- a/drivers/mtd/nand/raw/denali.c +++ b/drivers/mtd/nand/raw/denali.c @@ -596,6 +596,12 @@ static int denali_dma_xfer(struct denali_nand_info *denali, void *buf, } iowrite32(DMA_ENABLE__FLAG, denali->reg + DMA_ENABLE); + /* + * The ->setup_dma() hook kicks DMA by using the data/command + * interface, which belongs to a different AXI port from the + * register interface. Read back the register to avoid a race. + */ + ioread32(denali->reg + DMA_ENABLE); denali_reset_irq(denali); denali->setup_dma(denali, dma_addr, page, write); diff --git a/drivers/mtd/nand/raw/marvell_nand.c b/drivers/mtd/nand/raw/marvell_nand.c index 7af4d6213ee5..bc2ef5209783 100644 --- a/drivers/mtd/nand/raw/marvell_nand.c +++ b/drivers/mtd/nand/raw/marvell_nand.c @@ -1547,7 +1547,7 @@ static void marvell_nfc_parse_instructions(struct nand_chip *chip, for (op_id = 0; op_id < subop->ninstrs; op_id++) { unsigned int offset, naddrs; const u8 *addrs; - int len = nand_subop_get_data_len(subop, op_id); + int len; instr = &subop->instrs[op_id]; @@ -1593,6 +1593,7 @@ static void marvell_nfc_parse_instructions(struct nand_chip *chip, nfc_op->ndcb[0] |= NDCB0_CMD_XTYPE(XTYPE_MONOLITHIC_RW) | NDCB0_LEN_OVRD; + len = nand_subop_get_data_len(subop, op_id); nfc_op->ndcb[3] |= round_up(len, FIFO_DEPTH); } nfc_op->data_delay_ns = instr->delay_ns; @@ -1606,6 +1607,7 @@ static void marvell_nfc_parse_instructions(struct nand_chip *chip, nfc_op->ndcb[0] |= NDCB0_CMD_XTYPE(XTYPE_MONOLITHIC_RW) | NDCB0_LEN_OVRD; + len = nand_subop_get_data_len(subop, op_id); nfc_op->ndcb[3] |= round_up(len, FIFO_DEPTH); } nfc_op->data_delay_ns = instr->delay_ns; diff --git a/drivers/net/appletalk/ipddp.c b/drivers/net/appletalk/ipddp.c index 9375cef22420..3d27616d9c85 100644 --- a/drivers/net/appletalk/ipddp.c +++ b/drivers/net/appletalk/ipddp.c @@ -283,8 +283,12 @@ static int ipddp_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) case SIOCFINDIPDDPRT: spin_lock_bh(&ipddp_route_lock); rp = __ipddp_find_route(&rcp); - if (rp) - memcpy(&rcp2, rp, sizeof(rcp2)); + if (rp) { + memset(&rcp2, 0, sizeof(rcp2)); + rcp2.ip = rp->ip; + rcp2.at = rp->at; + rcp2.flags = rp->flags; + } spin_unlock_bh(&ipddp_route_lock); if (rp) { diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index a764a83f99da..0d87e11e7f1d 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -971,16 +971,13 @@ static void bond_poll_controller(struct net_device *bond_dev) struct slave *slave = NULL; struct list_head *iter; struct ad_info ad_info; - struct netpoll_info *ni; - const struct net_device_ops *ops; if (BOND_MODE(bond) == BOND_MODE_8023AD) if (bond_3ad_get_active_agg_info(bond, &ad_info)) return; bond_for_each_slave_rcu(bond, slave, iter) { - ops = slave->dev->netdev_ops; - if (!bond_slave_is_up(slave) || !ops->ndo_poll_controller) + if (!bond_slave_is_up(slave)) continue; if (BOND_MODE(bond) == BOND_MODE_8023AD) { @@ -992,11 +989,7 @@ static void bond_poll_controller(struct net_device *bond_dev) continue; } - ni = rcu_dereference_bh(slave->dev->npinfo); - if (down_trylock(&ni->dev_lock)) - continue; - ops->ndo_poll_controller(slave->dev); - up(&ni->dev_lock); + netpoll_poll_dev(slave->dev); } } diff --git a/drivers/net/can/rx-offload.c b/drivers/net/can/rx-offload.c index d94dae216820..c7d05027a7a0 100644 --- a/drivers/net/can/rx-offload.c +++ b/drivers/net/can/rx-offload.c @@ -79,7 +79,7 @@ static int can_rx_offload_napi_poll(struct napi_struct *napi, int quota) static inline void __skb_queue_add_sort(struct sk_buff_head *head, struct sk_buff *new, int (*compare)(struct sk_buff *a, struct sk_buff *b)) { - struct sk_buff *pos, *insert = (struct sk_buff *)head; + struct sk_buff *pos, *insert = NULL; skb_queue_reverse_walk(head, pos) { const struct can_rx_offload_cb *cb_pos, *cb_new; @@ -99,8 +99,10 @@ static inline void __skb_queue_add_sort(struct sk_buff_head *head, struct sk_buf insert = pos; break; } - - __skb_queue_after(head, insert, new); + if (!insert) + __skb_queue_head(head, new); + else + __skb_queue_after(head, insert, new); } static int can_rx_offload_compare(struct sk_buff *a, struct sk_buff *b) diff --git a/drivers/net/dsa/Kconfig b/drivers/net/dsa/Kconfig index d3ce1e4cb4d3..71bb3aebded4 100644 --- a/drivers/net/dsa/Kconfig +++ b/drivers/net/dsa/Kconfig @@ -23,6 +23,14 @@ config NET_DSA_LOOP This enables support for a fake mock-up switch chip which exercises the DSA APIs. +config NET_DSA_LANTIQ_GSWIP + tristate "Lantiq / Intel GSWIP" + depends on HAS_IOMEM && NET_DSA + select NET_DSA_TAG_GSWIP + ---help--- + This enables support for the Lantiq / Intel GSWIP 2.1 found in + the xrx200 / VR9 SoC. + config NET_DSA_MT7530 tristate "Mediatek MT7530 Ethernet switch support" depends on NET_DSA diff --git a/drivers/net/dsa/Makefile b/drivers/net/dsa/Makefile index 46c1cba91ffe..82e5d794c41f 100644 --- a/drivers/net/dsa/Makefile +++ b/drivers/net/dsa/Makefile @@ -5,6 +5,7 @@ obj-$(CONFIG_NET_DSA_LOOP) += dsa_loop.o ifdef CONFIG_NET_DSA_LOOP obj-$(CONFIG_FIXED_PHY) += dsa_loop_bdinfo.o endif +obj-$(CONFIG_NET_DSA_LANTIQ_GSWIP) += lantiq_gswip.o obj-$(CONFIG_NET_DSA_MT7530) += mt7530.o obj-$(CONFIG_NET_DSA_MV88E6060) += mv88e6060.o obj-$(CONFIG_NET_DSA_QCA8K) += qca8k.o diff --git a/drivers/net/dsa/b53/Kconfig b/drivers/net/dsa/b53/Kconfig index 37745f4bf4f6..e83ebfafd881 100644 --- a/drivers/net/dsa/b53/Kconfig +++ b/drivers/net/dsa/b53/Kconfig @@ -35,3 +35,10 @@ config B53_SRAB_DRIVER help Select to enable support for memory-mapped Switch Register Access Bridge Registers (SRAB) like it is found on the BCM53010 + +config B53_SERDES + tristate "B53 SerDes support" + depends on B53 + default ARCH_BCM_NSP + help + Select to enable support for SerDes on e.g: Northstar Plus SoCs. diff --git a/drivers/net/dsa/b53/Makefile b/drivers/net/dsa/b53/Makefile index 4256fb42a4dd..b1be13023ae4 100644 --- a/drivers/net/dsa/b53/Makefile +++ b/drivers/net/dsa/b53/Makefile @@ -5,3 +5,4 @@ obj-$(CONFIG_B53_SPI_DRIVER) += b53_spi.o obj-$(CONFIG_B53_MDIO_DRIVER) += b53_mdio.o obj-$(CONFIG_B53_MMAP_DRIVER) += b53_mmap.o obj-$(CONFIG_B53_SRAB_DRIVER) += b53_srab.o +obj-$(CONFIG_B53_SERDES) += b53_serdes.o diff --git a/drivers/net/dsa/b53/b53_common.c b/drivers/net/dsa/b53/b53_common.c index d93c790bfbe8..700d86dd5e13 100644 --- a/drivers/net/dsa/b53/b53_common.c +++ b/drivers/net/dsa/b53/b53_common.c @@ -26,6 +26,7 @@ #include <linux/module.h> #include <linux/platform_data/b53.h> #include <linux/phy.h> +#include <linux/phylink.h> #include <linux/etherdevice.h> #include <linux/if_bridge.h> #include <net/dsa.h> @@ -502,8 +503,14 @@ int b53_enable_port(struct dsa_switch *ds, int port, struct phy_device *phy) { struct b53_device *dev = ds->priv; unsigned int cpu_port = ds->ports[port].cpu_dp->index; + int ret = 0; u16 pvlan; + if (dev->ops->irq_enable) + ret = dev->ops->irq_enable(dev, port); + if (ret) + return ret; + /* Clear the Rx and Tx disable bits and set to no spanning tree */ b53_write8(dev, B53_CTRL_PAGE, B53_PORT_CTRL(port), 0); @@ -536,6 +543,9 @@ void b53_disable_port(struct dsa_switch *ds, int port, struct phy_device *phy) b53_read8(dev, B53_CTRL_PAGE, B53_PORT_CTRL(port), ®); reg |= PORT_CTRL_RX_DISABLE | PORT_CTRL_TX_DISABLE; b53_write8(dev, B53_CTRL_PAGE, B53_PORT_CTRL(port), reg); + + if (dev->ops->irq_disable) + dev->ops->irq_disable(dev, port); } EXPORT_SYMBOL(b53_disable_port); @@ -755,6 +765,8 @@ static int b53_reset_switch(struct b53_device *priv) memset(priv->vlans, 0, sizeof(*priv->vlans) * priv->num_vlans); memset(priv->ports, 0, sizeof(*priv->ports) * priv->num_ports); + priv->serdes_lane = B53_INVALID_LANE; + return b53_switch_reset(priv); } @@ -938,33 +950,50 @@ static int b53_setup(struct dsa_switch *ds) return ret; } -static void b53_adjust_link(struct dsa_switch *ds, int port, - struct phy_device *phydev) +static void b53_force_link(struct b53_device *dev, int port, int link) { - struct b53_device *dev = ds->priv; - struct ethtool_eee *p = &dev->ports[port].eee; - u8 rgmii_ctrl = 0, reg = 0, off; - - if (!phy_is_pseudo_fixed_link(phydev)) - return; + u8 reg, val, off; /* Override the port settings */ if (port == dev->cpu_port) { off = B53_PORT_OVERRIDE_CTRL; - reg = PORT_OVERRIDE_EN; + val = PORT_OVERRIDE_EN; } else { off = B53_GMII_PORT_OVERRIDE_CTRL(port); - reg = GMII_PO_EN; + val = GMII_PO_EN; } - /* Set the link UP */ - if (phydev->link) + b53_read8(dev, B53_CTRL_PAGE, off, ®); + reg |= val; + if (link) reg |= PORT_OVERRIDE_LINK; + else + reg &= ~PORT_OVERRIDE_LINK; + b53_write8(dev, B53_CTRL_PAGE, off, reg); +} - if (phydev->duplex == DUPLEX_FULL) +static void b53_force_port_config(struct b53_device *dev, int port, + int speed, int duplex, int pause) +{ + u8 reg, val, off; + + /* Override the port settings */ + if (port == dev->cpu_port) { + off = B53_PORT_OVERRIDE_CTRL; + val = PORT_OVERRIDE_EN; + } else { + off = B53_GMII_PORT_OVERRIDE_CTRL(port); + val = GMII_PO_EN; + } + + b53_read8(dev, B53_CTRL_PAGE, off, ®); + reg |= val; + if (duplex == DUPLEX_FULL) reg |= PORT_OVERRIDE_FULL_DUPLEX; + else + reg &= ~PORT_OVERRIDE_FULL_DUPLEX; - switch (phydev->speed) { + switch (speed) { case 2000: reg |= PORT_OVERRIDE_SPEED_2000M; /* fallthrough */ @@ -978,21 +1007,41 @@ static void b53_adjust_link(struct dsa_switch *ds, int port, reg |= PORT_OVERRIDE_SPEED_10M; break; default: - dev_err(ds->dev, "unknown speed: %d\n", phydev->speed); + dev_err(dev->dev, "unknown speed: %d\n", speed); return; } + if (pause & MLO_PAUSE_RX) + reg |= PORT_OVERRIDE_RX_FLOW; + if (pause & MLO_PAUSE_TX) + reg |= PORT_OVERRIDE_TX_FLOW; + + b53_write8(dev, B53_CTRL_PAGE, off, reg); +} + +static void b53_adjust_link(struct dsa_switch *ds, int port, + struct phy_device *phydev) +{ + struct b53_device *dev = ds->priv; + struct ethtool_eee *p = &dev->ports[port].eee; + u8 rgmii_ctrl = 0, reg = 0, off; + int pause = 0; + + if (!phy_is_pseudo_fixed_link(phydev)) + return; + /* Enable flow control on BCM5301x's CPU port */ if (is5301x(dev) && port == dev->cpu_port) - reg |= PORT_OVERRIDE_RX_FLOW | PORT_OVERRIDE_TX_FLOW; + pause = MLO_PAUSE_TXRX_MASK; if (phydev->pause) { if (phydev->asym_pause) - reg |= PORT_OVERRIDE_TX_FLOW; - reg |= PORT_OVERRIDE_RX_FLOW; + pause |= MLO_PAUSE_TX; + pause |= MLO_PAUSE_RX; } - b53_write8(dev, B53_CTRL_PAGE, off, reg); + b53_force_port_config(dev, port, phydev->speed, phydev->duplex, pause); + b53_force_link(dev, port, phydev->link); if (is531x5(dev) && phy_interface_is_rgmii(phydev)) { if (port == 8) @@ -1052,16 +1101,9 @@ static void b53_adjust_link(struct dsa_switch *ds, int port, } } else if (is5301x(dev)) { if (port != dev->cpu_port) { - u8 po_reg = B53_GMII_PORT_OVERRIDE_CTRL(dev->cpu_port); - u8 gmii_po; - - b53_read8(dev, B53_CTRL_PAGE, po_reg, &gmii_po); - gmii_po |= GMII_PO_LINK | - GMII_PO_RX_FLOW | - GMII_PO_TX_FLOW | - GMII_PO_EN | - GMII_PO_SPEED_2000M; - b53_write8(dev, B53_CTRL_PAGE, po_reg, gmii_po); + b53_force_port_config(dev, dev->cpu_port, 2000, + DUPLEX_FULL, MLO_PAUSE_TXRX_MASK); + b53_force_link(dev, dev->cpu_port, 1); } } @@ -1069,6 +1111,148 @@ static void b53_adjust_link(struct dsa_switch *ds, int port, p->eee_enabled = b53_eee_init(ds, port, phydev); } +void b53_port_event(struct dsa_switch *ds, int port) +{ + struct b53_device *dev = ds->priv; + bool link; + u16 sts; + + b53_read16(dev, B53_STAT_PAGE, B53_LINK_STAT, &sts); + link = !!(sts & BIT(port)); + dsa_port_phylink_mac_change(ds, port, link); +} +EXPORT_SYMBOL(b53_port_event); + +void b53_phylink_validate(struct dsa_switch *ds, int port, + unsigned long *supported, + struct phylink_link_state *state) +{ + struct b53_device *dev = ds->priv; + __ETHTOOL_DECLARE_LINK_MODE_MASK(mask) = { 0, }; + + if (dev->ops->serdes_phylink_validate) + dev->ops->serdes_phylink_validate(dev, port, mask, state); + + /* Allow all the expected bits */ + phylink_set(mask, Autoneg); + phylink_set_port_modes(mask); + phylink_set(mask, Pause); + phylink_set(mask, Asym_Pause); + + /* With the exclusion of 5325/5365, MII, Reverse MII and 802.3z, we + * support Gigabit, including Half duplex. + */ + if (state->interface != PHY_INTERFACE_MODE_MII && + state->interface != PHY_INTERFACE_MODE_REVMII && + !phy_interface_mode_is_8023z(state->interface) && + !(is5325(dev) || is5365(dev))) { + phylink_set(mask, 1000baseT_Full); + phylink_set(mask, 1000baseT_Half); + } + + if (!phy_interface_mode_is_8023z(state->interface)) { + phylink_set(mask, 10baseT_Half); + phylink_set(mask, 10baseT_Full); + phylink_set(mask, 100baseT_Half); + phylink_set(mask, 100baseT_Full); + } + + bitmap_and(supported, supported, mask, + __ETHTOOL_LINK_MODE_MASK_NBITS); + bitmap_and(state->advertising, state->advertising, mask, + __ETHTOOL_LINK_MODE_MASK_NBITS); + + phylink_helper_basex_speed(state); +} +EXPORT_SYMBOL(b53_phylink_validate); + +int b53_phylink_mac_link_state(struct dsa_switch *ds, int port, + struct phylink_link_state *state) +{ + struct b53_device *dev = ds->priv; + int ret = -EOPNOTSUPP; + + if ((phy_interface_mode_is_8023z(state->interface) || + state->interface == PHY_INTERFACE_MODE_SGMII) && + dev->ops->serdes_link_state) + ret = dev->ops->serdes_link_state(dev, port, state); + + return ret; +} +EXPORT_SYMBOL(b53_phylink_mac_link_state); + +void b53_phylink_mac_config(struct dsa_switch *ds, int port, + unsigned int mode, + const struct phylink_link_state *state) +{ + struct b53_device *dev = ds->priv; + + if (mode == MLO_AN_PHY) + return; + + if (mode == MLO_AN_FIXED) { + b53_force_port_config(dev, port, state->speed, + state->duplex, state->pause); + return; + } + + if ((phy_interface_mode_is_8023z(state->interface) || + state->interface == PHY_INTERFACE_MODE_SGMII) && + dev->ops->serdes_config) + dev->ops->serdes_config(dev, port, mode, state); +} +EXPORT_SYMBOL(b53_phylink_mac_config); + +void b53_phylink_mac_an_restart(struct dsa_switch *ds, int port) +{ + struct b53_device *dev = ds->priv; + + if (dev->ops->serdes_an_restart) + dev->ops->serdes_an_restart(dev, port); +} +EXPORT_SYMBOL(b53_phylink_mac_an_restart); + +void b53_phylink_mac_link_down(struct dsa_switch *ds, int port, + unsigned int mode, + phy_interface_t interface) +{ + struct b53_device *dev = ds->priv; + + if (mode == MLO_AN_PHY) + return; + + if (mode == MLO_AN_FIXED) { + b53_force_link(dev, port, false); + return; + } + + if (phy_interface_mode_is_8023z(interface) && + dev->ops->serdes_link_set) + dev->ops->serdes_link_set(dev, port, mode, interface, false); +} +EXPORT_SYMBOL(b53_phylink_mac_link_down); + +void b53_phylink_mac_link_up(struct dsa_switch *ds, int port, + unsigned int mode, + phy_interface_t interface, + struct phy_device *phydev) +{ + struct b53_device *dev = ds->priv; + + if (mode == MLO_AN_PHY) + return; + + if (mode == MLO_AN_FIXED) { + b53_force_link(dev, port, true); + return; + } + + if (phy_interface_mode_is_8023z(interface) && + dev->ops->serdes_link_set) + dev->ops->serdes_link_set(dev, port, mode, interface, true); +} +EXPORT_SYMBOL(b53_phylink_mac_link_up); + int b53_vlan_filtering(struct dsa_switch *ds, int port, bool vlan_filtering) { return 0; @@ -1710,6 +1894,12 @@ static const struct dsa_switch_ops b53_switch_ops = { .phy_read = b53_phy_read16, .phy_write = b53_phy_write16, .adjust_link = b53_adjust_link, + .phylink_validate = b53_phylink_validate, + .phylink_mac_link_state = b53_phylink_mac_link_state, + .phylink_mac_config = b53_phylink_mac_config, + .phylink_mac_an_restart = b53_phylink_mac_an_restart, + .phylink_mac_link_down = b53_phylink_mac_link_down, + .phylink_mac_link_up = b53_phylink_mac_link_up, .port_enable = b53_enable_port, .port_disable = b53_disable_port, .get_mac_eee = b53_get_mac_eee, diff --git a/drivers/net/dsa/b53/b53_priv.h b/drivers/net/dsa/b53/b53_priv.h index df149756c282..ec796482792d 100644 --- a/drivers/net/dsa/b53/b53_priv.h +++ b/drivers/net/dsa/b53/b53_priv.h @@ -29,6 +29,7 @@ struct b53_device; struct net_device; +struct phylink_link_state; struct b53_io_ops { int (*read8)(struct b53_device *dev, u8 page, u8 reg, u8 *value); @@ -43,8 +44,25 @@ struct b53_io_ops { int (*write64)(struct b53_device *dev, u8 page, u8 reg, u64 value); int (*phy_read16)(struct b53_device *dev, int addr, int reg, u16 *value); int (*phy_write16)(struct b53_device *dev, int addr, int reg, u16 value); + int (*irq_enable)(struct b53_device *dev, int port); + void (*irq_disable)(struct b53_device *dev, int port); + u8 (*serdes_map_lane)(struct b53_device *dev, int port); + int (*serdes_link_state)(struct b53_device *dev, int port, + struct phylink_link_state *state); + void (*serdes_config)(struct b53_device *dev, int port, + unsigned int mode, + const struct phylink_link_state *state); + void (*serdes_an_restart)(struct b53_device *dev, int port); + void (*serdes_link_set)(struct b53_device *dev, int port, + unsigned int mode, phy_interface_t interface, + bool link_up); + void (*serdes_phylink_validate)(struct b53_device *dev, int port, + unsigned long *supported, + struct phylink_link_state *state); }; +#define B53_INVALID_LANE 0xff + enum { BCM5325_DEVICE_ID = 0x25, BCM5365_DEVICE_ID = 0x65, @@ -107,6 +125,7 @@ struct b53_device { /* connect specific data */ u8 current_page; struct device *dev; + u8 serdes_lane; /* Master MDIO bus we got probed from */ struct mii_bus *bus; @@ -298,6 +317,23 @@ int b53_br_join(struct dsa_switch *ds, int port, struct net_device *bridge); void b53_br_leave(struct dsa_switch *ds, int port, struct net_device *bridge); void b53_br_set_stp_state(struct dsa_switch *ds, int port, u8 state); void b53_br_fast_age(struct dsa_switch *ds, int port); +void b53_port_event(struct dsa_switch *ds, int port); +void b53_phylink_validate(struct dsa_switch *ds, int port, + unsigned long *supported, + struct phylink_link_state *state); +int b53_phylink_mac_link_state(struct dsa_switch *ds, int port, + struct phylink_link_state *state); +void b53_phylink_mac_config(struct dsa_switch *ds, int port, + unsigned int mode, + const struct phylink_link_state *state); +void b53_phylink_mac_an_restart(struct dsa_switch *ds, int port); +void b53_phylink_mac_link_down(struct dsa_switch *ds, int port, + unsigned int mode, + phy_interface_t interface); +void b53_phylink_mac_link_up(struct dsa_switch *ds, int port, + unsigned int mode, + phy_interface_t interface, + struct phy_device *phydev); int b53_vlan_filtering(struct dsa_switch *ds, int port, bool vlan_filtering); int b53_vlan_prepare(struct dsa_switch *ds, int port, const struct switchdev_obj_port_vlan *vlan); diff --git a/drivers/net/dsa/b53/b53_serdes.c b/drivers/net/dsa/b53/b53_serdes.c new file mode 100644 index 000000000000..629bf14128a2 --- /dev/null +++ b/drivers/net/dsa/b53/b53_serdes.c @@ -0,0 +1,214 @@ +// SPDX-License-Identifier: GPL-2.0 or BSD-3-Clause +/* + * Northstar Plus switch SerDes/SGMII PHY main logic + * + * Copyright (C) 2018 Florian Fainelli <f.fainelli@gmail.com> + */ + +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + +#include <linux/delay.h> +#include <linux/kernel.h> +#include <linux/phy.h> +#include <linux/phylink.h> +#include <net/dsa.h> + +#include "b53_priv.h" +#include "b53_serdes.h" +#include "b53_regs.h" + +static void b53_serdes_write_blk(struct b53_device *dev, u8 offset, u16 block, + u16 value) +{ + b53_write16(dev, B53_SERDES_PAGE, B53_SERDES_BLKADDR, block); + b53_write16(dev, B53_SERDES_PAGE, offset, value); +} + +static u16 b53_serdes_read_blk(struct b53_device *dev, u8 offset, u16 block) +{ + u16 value; + + b53_write16(dev, B53_SERDES_PAGE, B53_SERDES_BLKADDR, block); + b53_read16(dev, B53_SERDES_PAGE, offset, &value); + + return value; +} + +static void b53_serdes_set_lane(struct b53_device *dev, u8 lane) +{ + if (dev->serdes_lane == lane) + return; + + WARN_ON(lane > 1); + + b53_serdes_write_blk(dev, B53_SERDES_LANE, + SERDES_XGXSBLK0_BLOCKADDRESS, lane); + dev->serdes_lane = lane; +} + +static void b53_serdes_write(struct b53_device *dev, u8 lane, + u8 offset, u16 block, u16 value) +{ + b53_serdes_set_lane(dev, lane); + b53_serdes_write_blk(dev, offset, block, value); +} + +static u16 b53_serdes_read(struct b53_device *dev, u8 lane, + u8 offset, u16 block) +{ + b53_serdes_set_lane(dev, lane); + return b53_serdes_read_blk(dev, offset, block); +} + +void b53_serdes_config(struct b53_device *dev, int port, unsigned int mode, + const struct phylink_link_state *state) +{ + u8 lane = b53_serdes_map_lane(dev, port); + u16 reg; + + if (lane == B53_INVALID_LANE) + return; + + reg = b53_serdes_read(dev, lane, B53_SERDES_DIGITAL_CONTROL(1), + SERDES_DIGITAL_BLK); + if (state->interface == PHY_INTERFACE_MODE_1000BASEX) + reg |= FIBER_MODE_1000X; + else + reg &= ~FIBER_MODE_1000X; + b53_serdes_write(dev, lane, B53_SERDES_DIGITAL_CONTROL(1), + SERDES_DIGITAL_BLK, reg); +} +EXPORT_SYMBOL(b53_serdes_config); + +void b53_serdes_an_restart(struct b53_device *dev, int port) +{ + u8 lane = b53_serdes_map_lane(dev, port); + u16 reg; + + if (lane == B53_INVALID_LANE) + return; + + reg = b53_serdes_read(dev, lane, B53_SERDES_MII_REG(MII_BMCR), + SERDES_MII_BLK); + reg |= BMCR_ANRESTART; + b53_serdes_write(dev, lane, B53_SERDES_MII_REG(MII_BMCR), + SERDES_MII_BLK, reg); +} +EXPORT_SYMBOL(b53_serdes_an_restart); + +int b53_serdes_link_state(struct b53_device *dev, int port, + struct phylink_link_state *state) +{ + u8 lane = b53_serdes_map_lane(dev, port); + u16 dig, bmsr; + + if (lane == B53_INVALID_LANE) + return 1; + + dig = b53_serdes_read(dev, lane, B53_SERDES_DIGITAL_STATUS, + SERDES_DIGITAL_BLK); + bmsr = b53_serdes_read(dev, lane, B53_SERDES_MII_REG(MII_BMSR), + SERDES_MII_BLK); + + switch ((dig >> SPEED_STATUS_SHIFT) & SPEED_STATUS_MASK) { + case SPEED_STATUS_10: + state->speed = SPEED_10; + break; + case SPEED_STATUS_100: + state->speed = SPEED_100; + break; + case SPEED_STATUS_1000: + state->speed = SPEED_1000; + break; + default: + case SPEED_STATUS_2500: + state->speed = SPEED_2500; + break; + } + + state->duplex = dig & DUPLEX_STATUS ? DUPLEX_FULL : DUPLEX_HALF; + state->an_complete = !!(bmsr & BMSR_ANEGCOMPLETE); + state->link = !!(dig & LINK_STATUS); + if (dig & PAUSE_RESOLUTION_RX_SIDE) + state->pause |= MLO_PAUSE_RX; + if (dig & PAUSE_RESOLUTION_TX_SIDE) + state->pause |= MLO_PAUSE_TX; + + return 0; +} +EXPORT_SYMBOL(b53_serdes_link_state); + +void b53_serdes_link_set(struct b53_device *dev, int port, unsigned int mode, + phy_interface_t interface, bool link_up) +{ + u8 lane = b53_serdes_map_lane(dev, port); + u16 reg; + + if (lane == B53_INVALID_LANE) + return; + + reg = b53_serdes_read(dev, lane, B53_SERDES_MII_REG(MII_BMCR), + SERDES_MII_BLK); + if (link_up) + reg &= ~BMCR_PDOWN; + else + reg |= BMCR_PDOWN; + b53_serdes_write(dev, lane, B53_SERDES_MII_REG(MII_BMCR), + SERDES_MII_BLK, reg); +} +EXPORT_SYMBOL(b53_serdes_link_set); + +void b53_serdes_phylink_validate(struct b53_device *dev, int port, + unsigned long *supported, + struct phylink_link_state *state) +{ + u8 lane = b53_serdes_map_lane(dev, port); + + if (lane == B53_INVALID_LANE) + return; + + switch (lane) { + case 0: + phylink_set(supported, 2500baseX_Full); + /* fallthrough */ + case 1: + phylink_set(supported, 1000baseX_Full); + break; + default: + break; + } +} +EXPORT_SYMBOL(b53_serdes_phylink_validate); + +int b53_serdes_init(struct b53_device *dev, int port) +{ + u8 lane = b53_serdes_map_lane(dev, port); + u16 id0, msb, lsb; + + if (lane == B53_INVALID_LANE) + return -EINVAL; + + id0 = b53_serdes_read(dev, lane, B53_SERDES_ID0, SERDES_ID0); + msb = b53_serdes_read(dev, lane, B53_SERDES_MII_REG(MII_PHYSID1), + SERDES_MII_BLK); + lsb = b53_serdes_read(dev, lane, B53_SERDES_MII_REG(MII_PHYSID2), + SERDES_MII_BLK); + if (id0 == 0 || id0 == 0xffff) { + dev_err(dev->dev, "SerDes not initialized, check settings\n"); + return -ENODEV; + } + + dev_info(dev->dev, + "SerDes lane %d, model: %d, rev %c%d (OUI: 0x%08x)\n", + lane, id0 & SERDES_ID0_MODEL_MASK, + (id0 >> SERDES_ID0_REV_LETTER_SHIFT) + 0x41, + (id0 >> SERDES_ID0_REV_NUM_SHIFT) & SERDES_ID0_REV_NUM_MASK, + (u32)msb << 16 | lsb); + + return 0; +} +EXPORT_SYMBOL(b53_serdes_init); + +MODULE_AUTHOR("Florian Fainelli <f.fainelli@gmail.com>"); +MODULE_DESCRIPTION("B53 Switch SerDes driver"); +MODULE_LICENSE("Dual BSD/GPL"); diff --git a/drivers/net/dsa/b53/b53_serdes.h b/drivers/net/dsa/b53/b53_serdes.h new file mode 100644 index 000000000000..3bb4f91aec9e --- /dev/null +++ b/drivers/net/dsa/b53/b53_serdes.h @@ -0,0 +1,128 @@ +/* SPDX-License-Identifier: GPL-2.0 or BSD-3-Clause + * + * Northstar Plus switch SerDes/SGMII PHY definitions + * + * Copyright (C) 2018 Florian Fainelli <f.fainelli@gmail.com> + */ + +#include <linux/phy.h> +#include <linux/types.h> + +/* Non-standard page used to access SerDes PHY registers on NorthStar Plus */ +#define B53_SERDES_PAGE 0x16 +#define B53_SERDES_BLKADDR 0x3e +#define B53_SERDES_LANE 0x3c + +#define B53_SERDES_ID0 0x20 +#define SERDES_ID0_MODEL_MASK 0x3f +#define SERDES_ID0_REV_NUM_SHIFT 11 +#define SERDES_ID0_REV_NUM_MASK 0x7 +#define SERDES_ID0_REV_LETTER_SHIFT 14 + +#define B53_SERDES_MII_REG(x) (0x20 + (x) * 2) +#define B53_SERDES_DIGITAL_CONTROL(x) (0x1e + (x) * 2) +#define B53_SERDES_DIGITAL_STATUS 0x28 + +/* SERDES_DIGITAL_CONTROL1 */ +#define FIBER_MODE_1000X BIT(0) +#define TBI_INTERFACE BIT(1) +#define SIGNAL_DETECT_EN BIT(2) +#define INVERT_SIGNAL_DETECT BIT(3) +#define AUTODET_EN BIT(4) +#define SGMII_MASTER_MODE BIT(5) +#define DISABLE_DLL_PWRDOWN BIT(6) +#define CRC_CHECKER_DIS BIT(7) +#define COMMA_DET_EN BIT(8) +#define ZERO_COMMA_DET_EN BIT(9) +#define REMOTE_LOOPBACK BIT(10) +#define SEL_RX_PKTS_FOR_CNTR BIT(11) +#define MASTER_MDIO_PHY_SEL BIT(13) +#define DISABLE_SIGNAL_DETECT_FLT BIT(14) + +/* SERDES_DIGITAL_CONTROL2 */ +#define EN_PARALLEL_DET BIT(0) +#define DIS_FALSE_LINK BIT(1) +#define FLT_FORCE_LINK BIT(2) +#define EN_AUTONEG_ERR_TIMER BIT(3) +#define DIS_REMOTE_FAULT_SENSING BIT(4) +#define FORCE_XMIT_DATA BIT(5) +#define AUTONEG_FAST_TIMERS BIT(6) +#define DIS_CARRIER_EXTEND BIT(7) +#define DIS_TRRR_GENERATION BIT(8) +#define BYPASS_PCS_RX BIT(9) +#define BYPASS_PCS_TX BIT(10) +#define TEST_CNTR_EN BIT(11) +#define TX_PACKET_SEQ_TEST BIT(12) +#define TX_IDLE_JAM_SEQ_TEST BIT(13) +#define CLR_BER_CNTR BIT(14) + +/* SERDES_DIGITAL_CONTROL3 */ +#define TX_FIFO_RST BIT(0) +#define FIFO_ELAST_TX_RX_SHIFT 1 +#define FIFO_ELAST_TX_RX_5K 0 +#define FIFO_ELAST_TX_RX_10K 1 +#define FIFO_ELAST_TX_RX_13_5K 2 +#define FIFO_ELAST_TX_RX_18_5K 3 +#define BLOCK_TXEN_MODE BIT(9) +#define JAM_FALSE_CARRIER_MODE BIT(10) +#define EXT_PHY_CRS_MODE BIT(11) +#define INVERT_EXT_PHY_CRS BIT(12) +#define DISABLE_TX_CRS BIT(13) + +/* SERDES_DIGITAL_STATUS */ +#define SGMII_MODE BIT(0) +#define LINK_STATUS BIT(1) +#define DUPLEX_STATUS BIT(2) +#define SPEED_STATUS_SHIFT 3 +#define SPEED_STATUS_10 0 +#define SPEED_STATUS_100 1 +#define SPEED_STATUS_1000 2 +#define SPEED_STATUS_2500 3 +#define SPEED_STATUS_MASK SPEED_STATUS_2500 +#define PAUSE_RESOLUTION_TX_SIDE BIT(5) +#define PAUSE_RESOLUTION_RX_SIDE BIT(6) +#define LINK_STATUS_CHANGE BIT(7) +#define EARLY_END_EXT_DET BIT(8) +#define CARRIER_EXT_ERR_DET BIT(9) +#define RX_ERR_DET BIT(10) +#define TX_ERR_DET BIT(11) +#define CRC_ERR_DET BIT(12) +#define FALSE_CARRIER_ERR_DET BIT(13) +#define RXFIFO_ERR_DET BIT(14) +#define TXFIFO_ERR_DET BIT(15) + +/* Block offsets */ +#define SERDES_DIGITAL_BLK 0x8300 +#define SERDES_ID0 0x8310 +#define SERDES_MII_BLK 0xffe0 +#define SERDES_XGXSBLK0_BLOCKADDRESS 0xffd0 + +struct phylink_link_state; + +static inline u8 b53_serdes_map_lane(struct b53_device *dev, int port) +{ + if (!dev->ops->serdes_map_lane) + return B53_INVALID_LANE; + + return dev->ops->serdes_map_lane(dev, port); +} + +int b53_serdes_get_link(struct b53_device *dev, int port); +int b53_serdes_link_state(struct b53_device *dev, int port, + struct phylink_link_state *state); +void b53_serdes_config(struct b53_device *dev, int port, unsigned int mode, + const struct phylink_link_state *state); +void b53_serdes_an_restart(struct b53_device *dev, int port); +void b53_serdes_link_set(struct b53_device *dev, int port, unsigned int mode, + phy_interface_t interface, bool link_up); +void b53_serdes_phylink_validate(struct b53_device *dev, int port, + unsigned long *supported, + struct phylink_link_state *state); +#if IS_ENABLED(CONFIG_B53_SERDES) +int b53_serdes_init(struct b53_device *dev, int port); +#else +static inline int b53_serdes_init(struct b53_device *dev, int port) +{ + return -ENODEV; +} +#endif diff --git a/drivers/net/dsa/b53/b53_srab.c b/drivers/net/dsa/b53/b53_srab.c index 91de2ba99ad1..90f514252987 100644 --- a/drivers/net/dsa/b53/b53_srab.c +++ b/drivers/net/dsa/b53/b53_srab.c @@ -19,11 +19,13 @@ #include <linux/kernel.h> #include <linux/module.h> #include <linux/delay.h> +#include <linux/interrupt.h> #include <linux/platform_device.h> #include <linux/platform_data/b53.h> #include <linux/of.h> #include "b53_priv.h" +#include "b53_serdes.h" /* command and status register of the SRAB */ #define B53_SRAB_CMDSTAT 0x2c @@ -47,6 +49,7 @@ /* command and status register of the SRAB */ #define B53_SRAB_CTRLS 0x40 +#define B53_SRAB_CTRLS_HOST_INTR BIT(1) #define B53_SRAB_CTRLS_RCAREQ BIT(3) #define B53_SRAB_CTRLS_RCAGNT BIT(4) #define B53_SRAB_CTRLS_SW_INIT_DONE BIT(6) @@ -60,8 +63,29 @@ #define B53_SRAB_P7_SLEEP_TIMER BIT(11) #define B53_SRAB_IMP0_SLEEP_TIMER BIT(12) +/* Port mux configuration registers */ +#define B53_MUX_CONFIG_P5 0x00 +#define MUX_CONFIG_SGMII 0 +#define MUX_CONFIG_MII_LITE 1 +#define MUX_CONFIG_RGMII 2 +#define MUX_CONFIG_GMII 3 +#define MUX_CONFIG_GPHY 4 +#define MUX_CONFIG_INTERNAL 5 +#define MUX_CONFIG_MASK 0x7 +#define B53_MUX_CONFIG_P4 0x04 + +struct b53_srab_port_priv { + int irq; + bool irq_enabled; + struct b53_device *dev; + unsigned int num; + phy_interface_t mode; +}; + struct b53_srab_priv { void __iomem *regs; + void __iomem *mux_config; + struct b53_srab_port_priv port_intrs[B53_N_PORTS]; }; static int b53_srab_request_grant(struct b53_device *dev) @@ -344,6 +368,81 @@ err: return ret; } +static irqreturn_t b53_srab_port_thread(int irq, void *dev_id) +{ + struct b53_srab_port_priv *port = dev_id; + struct b53_device *dev = port->dev; + + if (port->mode == PHY_INTERFACE_MODE_SGMII) + b53_port_event(dev->ds, port->num); + + return IRQ_HANDLED; +} + +static irqreturn_t b53_srab_port_isr(int irq, void *dev_id) +{ + struct b53_srab_port_priv *port = dev_id; + struct b53_device *dev = port->dev; + struct b53_srab_priv *priv = dev->priv; + + /* Acknowledge the interrupt */ + writel(BIT(port->num), priv->regs + B53_SRAB_INTR); + + return IRQ_WAKE_THREAD; +} + +#if IS_ENABLED(CONFIG_B53_SERDES) +static u8 b53_srab_serdes_map_lane(struct b53_device *dev, int port) +{ + struct b53_srab_priv *priv = dev->priv; + struct b53_srab_port_priv *p = &priv->port_intrs[port]; + + if (p->mode != PHY_INTERFACE_MODE_SGMII) + return B53_INVALID_LANE; + + switch (port) { + case 5: + return 0; + case 4: + return 1; + default: + return B53_INVALID_LANE; + } +} +#endif + +static int b53_srab_irq_enable(struct b53_device *dev, int port) +{ + struct b53_srab_priv *priv = dev->priv; + struct b53_srab_port_priv *p = &priv->port_intrs[port]; + int ret = 0; + + /* Interrupt is optional and was not specified, do not make + * this fatal + */ + if (p->irq == -ENXIO) + return ret; + + ret = request_threaded_irq(p->irq, b53_srab_port_isr, + b53_srab_port_thread, 0, + dev_name(dev->dev), p); + if (!ret) + p->irq_enabled = true; + + return ret; +} + +static void b53_srab_irq_disable(struct b53_device *dev, int port) +{ + struct b53_srab_priv *priv = dev->priv; + struct b53_srab_port_priv *p = &priv->port_intrs[port]; + + if (p->irq_enabled) { + free_irq(p->irq, p); + p->irq_enabled = false; + } +} + static const struct b53_io_ops b53_srab_ops = { .read8 = b53_srab_read8, .read16 = b53_srab_read16, @@ -355,6 +454,16 @@ static const struct b53_io_ops b53_srab_ops = { .write32 = b53_srab_write32, .write48 = b53_srab_write48, .write64 = b53_srab_write64, + .irq_enable = b53_srab_irq_enable, + .irq_disable = b53_srab_irq_disable, +#if IS_ENABLED(CONFIG_B53_SERDES) + .serdes_map_lane = b53_srab_serdes_map_lane, + .serdes_link_state = b53_serdes_link_state, + .serdes_config = b53_serdes_config, + .serdes_an_restart = b53_serdes_an_restart, + .serdes_link_set = b53_serdes_link_set, + .serdes_phylink_validate = b53_serdes_phylink_validate, +#endif }; static const struct of_device_id b53_srab_of_match[] = { @@ -379,6 +488,107 @@ static const struct of_device_id b53_srab_of_match[] = { }; MODULE_DEVICE_TABLE(of, b53_srab_of_match); +static void b53_srab_intr_set(struct b53_srab_priv *priv, bool set) +{ + u32 reg; + + reg = readl(priv->regs + B53_SRAB_CTRLS); + if (set) + reg |= B53_SRAB_CTRLS_HOST_INTR; + else + reg &= ~B53_SRAB_CTRLS_HOST_INTR; + writel(reg, priv->regs + B53_SRAB_CTRLS); +} + +static void b53_srab_prepare_irq(struct platform_device *pdev) +{ + struct b53_device *dev = platform_get_drvdata(pdev); + struct b53_srab_priv *priv = dev->priv; + struct b53_srab_port_priv *port; + unsigned int i; + char *name; + + /* Clear all pending interrupts */ + writel(0xffffffff, priv->regs + B53_SRAB_INTR); + + if (dev->pdata && dev->pdata->chip_id != BCM58XX_DEVICE_ID) + return; + + for (i = 0; i < B53_N_PORTS; i++) { + port = &priv->port_intrs[i]; + + /* There is no port 6 */ + if (i == 6) + continue; + + name = kasprintf(GFP_KERNEL, "link_state_p%d", i); + if (!name) + return; + + port->num = i; + port->dev = dev; + port->irq = platform_get_irq_byname(pdev, name); + kfree(name); + } + + b53_srab_intr_set(priv, true); +} + +static void b53_srab_mux_init(struct platform_device *pdev) +{ + struct b53_device *dev = platform_get_drvdata(pdev); + struct b53_srab_priv *priv = dev->priv; + struct b53_srab_port_priv *p; + struct resource *r; + unsigned int port; + u32 reg, off = 0; + int ret; + + if (dev->pdata && dev->pdata->chip_id != BCM58XX_DEVICE_ID) + return; + + r = platform_get_resource(pdev, IORESOURCE_MEM, 1); + priv->mux_config = devm_ioremap_resource(&pdev->dev, r); + if (IS_ERR(priv->mux_config)) + return; + + /* Obtain the port mux configuration so we know which lanes + * actually map to SerDes lanes + */ + for (port = 5; port > 3; port--, off += 4) { + p = &priv->port_intrs[port]; + + reg = readl(priv->mux_config + B53_MUX_CONFIG_P5 + off); + switch (reg & MUX_CONFIG_MASK) { + case MUX_CONFIG_SGMII: + p->mode = PHY_INTERFACE_MODE_SGMII; + ret = b53_serdes_init(dev, port); + if (ret) + continue; + break; + case MUX_CONFIG_MII_LITE: + p->mode = PHY_INTERFACE_MODE_MII; + break; + case MUX_CONFIG_GMII: + p->mode = PHY_INTERFACE_MODE_GMII; + break; + case MUX_CONFIG_RGMII: + p->mode = PHY_INTERFACE_MODE_RGMII; + break; + case MUX_CONFIG_INTERNAL: + p->mode = PHY_INTERFACE_MODE_INTERNAL; + break; + default: + p->mode = PHY_INTERFACE_MODE_NA; + break; + } + + if (p->mode != PHY_INTERFACE_MODE_NA) + dev_info(&pdev->dev, "Port %d mode: %s\n", + port, phy_modes(p->mode)); + } +} + static int b53_srab_probe(struct platform_device *pdev) { struct b53_platform_data *pdata = pdev->dev.platform_data; @@ -417,13 +627,18 @@ static int b53_srab_probe(struct platform_device *pdev) platform_set_drvdata(pdev, dev); + b53_srab_prepare_irq(pdev); + b53_srab_mux_init(pdev); + return b53_switch_register(dev); } static int b53_srab_remove(struct platform_device *pdev) { struct b53_device *dev = platform_get_drvdata(pdev); + struct b53_srab_priv *priv = dev->priv; + b53_srab_intr_set(priv, false); if (dev) b53_switch_remove(dev); diff --git a/drivers/net/dsa/bcm_sf2.c b/drivers/net/dsa/bcm_sf2.c index e0066adcd2f3..1fc27e149e7f 100644 --- a/drivers/net/dsa/bcm_sf2.c +++ b/drivers/net/dsa/bcm_sf2.c @@ -465,8 +465,7 @@ static int bcm_sf2_mdio_register(struct dsa_switch *ds) static void bcm_sf2_mdio_unregister(struct bcm_sf2_priv *priv) { mdiobus_unregister(priv->slave_mii_bus); - if (priv->master_mii_dn) - of_node_put(priv->master_mii_dn); + of_node_put(priv->master_mii_dn); } static u32 bcm_sf2_sw_get_phy_flags(struct dsa_switch *ds, int port) diff --git a/drivers/net/dsa/lantiq_gswip.c b/drivers/net/dsa/lantiq_gswip.c new file mode 100644 index 000000000000..693a67f45bef --- /dev/null +++ b/drivers/net/dsa/lantiq_gswip.c @@ -0,0 +1,1167 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Lantiq / Intel GSWIP switch driver for VRX200 SoCs + * + * Copyright (C) 2010 Lantiq Deutschland + * Copyright (C) 2012 John Crispin <john@phrozen.org> + * Copyright (C) 2017 - 2018 Hauke Mehrtens <hauke@hauke-m.de> + */ + +#include <linux/clk.h> +#include <linux/etherdevice.h> +#include <linux/firmware.h> +#include <linux/if_bridge.h> +#include <linux/if_vlan.h> +#include <linux/iopoll.h> +#include <linux/mfd/syscon.h> +#include <linux/module.h> +#include <linux/of_mdio.h> +#include <linux/of_net.h> +#include <linux/of_platform.h> +#include <linux/phy.h> +#include <linux/phylink.h> +#include <linux/platform_device.h> +#include <linux/regmap.h> +#include <linux/reset.h> +#include <net/dsa.h> +#include <dt-bindings/mips/lantiq_rcu_gphy.h> + +#include "lantiq_pce.h" + +/* GSWIP MDIO Registers */ +#define GSWIP_MDIO_GLOB 0x00 +#define GSWIP_MDIO_GLOB_ENABLE BIT(15) +#define GSWIP_MDIO_CTRL 0x08 +#define GSWIP_MDIO_CTRL_BUSY BIT(12) +#define GSWIP_MDIO_CTRL_RD BIT(11) +#define GSWIP_MDIO_CTRL_WR BIT(10) +#define GSWIP_MDIO_CTRL_PHYAD_MASK 0x1f +#define GSWIP_MDIO_CTRL_PHYAD_SHIFT 5 +#define GSWIP_MDIO_CTRL_REGAD_MASK 0x1f +#define GSWIP_MDIO_READ 0x09 +#define GSWIP_MDIO_WRITE 0x0A +#define GSWIP_MDIO_MDC_CFG0 0x0B +#define GSWIP_MDIO_MDC_CFG1 0x0C +#define GSWIP_MDIO_PHYp(p) (0x15 - (p)) +#define GSWIP_MDIO_PHY_LINK_MASK 0x6000 +#define GSWIP_MDIO_PHY_LINK_AUTO 0x0000 +#define GSWIP_MDIO_PHY_LINK_DOWN 0x4000 +#define GSWIP_MDIO_PHY_LINK_UP 0x2000 +#define GSWIP_MDIO_PHY_SPEED_MASK 0x1800 +#define GSWIP_MDIO_PHY_SPEED_AUTO 0x1800 +#define GSWIP_MDIO_PHY_SPEED_M10 0x0000 +#define GSWIP_MDIO_PHY_SPEED_M100 0x0800 +#define GSWIP_MDIO_PHY_SPEED_G1 0x1000 +#define GSWIP_MDIO_PHY_FDUP_MASK 0x0600 +#define GSWIP_MDIO_PHY_FDUP_AUTO 0x0000 +#define GSWIP_MDIO_PHY_FDUP_EN 0x0200 +#define GSWIP_MDIO_PHY_FDUP_DIS 0x0600 +#define GSWIP_MDIO_PHY_FCONTX_MASK 0x0180 +#define GSWIP_MDIO_PHY_FCONTX_AUTO 0x0000 +#define GSWIP_MDIO_PHY_FCONTX_EN 0x0100 +#define GSWIP_MDIO_PHY_FCONTX_DIS 0x0180 +#define GSWIP_MDIO_PHY_FCONRX_MASK 0x0060 +#define GSWIP_MDIO_PHY_FCONRX_AUTO 0x0000 +#define GSWIP_MDIO_PHY_FCONRX_EN 0x0020 +#define GSWIP_MDIO_PHY_FCONRX_DIS 0x0060 +#define GSWIP_MDIO_PHY_ADDR_MASK 0x001f +#define GSWIP_MDIO_PHY_MASK (GSWIP_MDIO_PHY_ADDR_MASK | \ + GSWIP_MDIO_PHY_FCONRX_MASK | \ + GSWIP_MDIO_PHY_FCONTX_MASK | \ + GSWIP_MDIO_PHY_LINK_MASK | \ + GSWIP_MDIO_PHY_SPEED_MASK | \ + GSWIP_MDIO_PHY_FDUP_MASK) + +/* GSWIP MII Registers */ +#define GSWIP_MII_CFG0 0x00 +#define GSWIP_MII_CFG1 0x02 +#define GSWIP_MII_CFG5 0x04 +#define GSWIP_MII_CFG_EN BIT(14) +#define GSWIP_MII_CFG_LDCLKDIS BIT(12) +#define GSWIP_MII_CFG_MODE_MIIP 0x0 +#define GSWIP_MII_CFG_MODE_MIIM 0x1 +#define GSWIP_MII_CFG_MODE_RMIIP 0x2 +#define GSWIP_MII_CFG_MODE_RMIIM 0x3 +#define GSWIP_MII_CFG_MODE_RGMII 0x4 +#define GSWIP_MII_CFG_MODE_MASK 0xf +#define GSWIP_MII_CFG_RATE_M2P5 0x00 +#define GSWIP_MII_CFG_RATE_M25 0x10 +#define GSWIP_MII_CFG_RATE_M125 0x20 +#define GSWIP_MII_CFG_RATE_M50 0x30 +#define GSWIP_MII_CFG_RATE_AUTO 0x40 +#define GSWIP_MII_CFG_RATE_MASK 0x70 +#define GSWIP_MII_PCDU0 0x01 +#define GSWIP_MII_PCDU1 0x03 +#define GSWIP_MII_PCDU5 0x05 +#define GSWIP_MII_PCDU_TXDLY_MASK GENMASK(2, 0) +#define GSWIP_MII_PCDU_RXDLY_MASK GENMASK(9, 7) + +/* GSWIP Core Registers */ +#define GSWIP_SWRES 0x000 +#define GSWIP_SWRES_R1 BIT(1) /* GSWIP Software reset */ +#define GSWIP_SWRES_R0 BIT(0) /* GSWIP Hardware reset */ +#define GSWIP_VERSION 0x013 +#define GSWIP_VERSION_REV_SHIFT 0 +#define GSWIP_VERSION_REV_MASK GENMASK(7, 0) +#define GSWIP_VERSION_MOD_SHIFT 8 +#define GSWIP_VERSION_MOD_MASK GENMASK(15, 8) +#define GSWIP_VERSION_2_0 0x100 +#define GSWIP_VERSION_2_1 0x021 +#define GSWIP_VERSION_2_2 0x122 +#define GSWIP_VERSION_2_2_ETC 0x022 + +#define GSWIP_BM_RAM_VAL(x) (0x043 - (x)) +#define GSWIP_BM_RAM_ADDR 0x044 +#define GSWIP_BM_RAM_CTRL 0x045 +#define GSWIP_BM_RAM_CTRL_BAS BIT(15) +#define GSWIP_BM_RAM_CTRL_OPMOD BIT(5) +#define GSWIP_BM_RAM_CTRL_ADDR_MASK GENMASK(4, 0) +#define GSWIP_BM_QUEUE_GCTRL 0x04A +#define GSWIP_BM_QUEUE_GCTRL_GL_MOD BIT(10) +/* buffer management Port Configuration Register */ +#define GSWIP_BM_PCFGp(p) (0x080 + ((p) * 2)) +#define GSWIP_BM_PCFG_CNTEN BIT(0) /* RMON Counter Enable */ +#define GSWIP_BM_PCFG_IGCNT BIT(1) /* Ingres Special Tag RMON count */ +/* buffer management Port Control Register */ +#define GSWIP_BM_RMON_CTRLp(p) (0x81 + ((p) * 2)) +#define GSWIP_BM_CTRL_RMON_RAM1_RES BIT(0) /* Software Reset for RMON RAM 1 */ +#define GSWIP_BM_CTRL_RMON_RAM2_RES BIT(1) /* Software Reset for RMON RAM 2 */ + +/* PCE */ +#define GSWIP_PCE_TBL_KEY(x) (0x447 - (x)) +#define GSWIP_PCE_TBL_MASK 0x448 +#define GSWIP_PCE_TBL_VAL(x) (0x44D - (x)) +#define GSWIP_PCE_TBL_ADDR 0x44E +#define GSWIP_PCE_TBL_CTRL 0x44F +#define GSWIP_PCE_TBL_CTRL_BAS BIT(15) +#define GSWIP_PCE_TBL_CTRL_TYPE BIT(13) +#define GSWIP_PCE_TBL_CTRL_VLD BIT(12) +#define GSWIP_PCE_TBL_CTRL_KEYFORM BIT(11) +#define GSWIP_PCE_TBL_CTRL_GMAP_MASK GENMASK(10, 7) +#define GSWIP_PCE_TBL_CTRL_OPMOD_MASK GENMASK(6, 5) +#define GSWIP_PCE_TBL_CTRL_OPMOD_ADRD 0x00 +#define GSWIP_PCE_TBL_CTRL_OPMOD_ADWR 0x20 +#define GSWIP_PCE_TBL_CTRL_OPMOD_KSRD 0x40 +#define GSWIP_PCE_TBL_CTRL_OPMOD_KSWR 0x60 +#define GSWIP_PCE_TBL_CTRL_ADDR_MASK GENMASK(4, 0) +#define GSWIP_PCE_PMAP1 0x453 /* Monitoring port map */ +#define GSWIP_PCE_PMAP2 0x454 /* Default Multicast port map */ +#define GSWIP_PCE_PMAP3 0x455 /* Default Unknown Unicast port map */ +#define GSWIP_PCE_GCTRL_0 0x456 +#define GSWIP_PCE_GCTRL_0_MC_VALID BIT(3) +#define GSWIP_PCE_GCTRL_0_VLAN BIT(14) /* VLAN aware Switching */ +#define GSWIP_PCE_GCTRL_1 0x457 +#define GSWIP_PCE_GCTRL_1_MAC_GLOCK BIT(2) /* MAC Address table lock */ +#define GSWIP_PCE_GCTRL_1_MAC_GLOCK_MOD BIT(3) /* Mac address table lock forwarding mode */ +#define GSWIP_PCE_PCTRL_0p(p) (0x480 + ((p) * 0xA)) +#define GSWIP_PCE_PCTRL_0_INGRESS BIT(11) +#define GSWIP_PCE_PCTRL_0_PSTATE_LISTEN 0x0 +#define GSWIP_PCE_PCTRL_0_PSTATE_RX 0x1 +#define GSWIP_PCE_PCTRL_0_PSTATE_TX 0x2 +#define GSWIP_PCE_PCTRL_0_PSTATE_LEARNING 0x3 +#define GSWIP_PCE_PCTRL_0_PSTATE_FORWARDING 0x7 +#define GSWIP_PCE_PCTRL_0_PSTATE_MASK GENMASK(2, 0) + +#define GSWIP_MAC_FLEN 0x8C5 +#define GSWIP_MAC_CTRL_2p(p) (0x905 + ((p) * 0xC)) +#define GSWIP_MAC_CTRL_2_MLEN BIT(3) /* Maximum Untagged Frame Lnegth */ + +/* Ethernet Switch Fetch DMA Port Control Register */ +#define GSWIP_FDMA_PCTRLp(p) (0xA80 + ((p) * 0x6)) +#define GSWIP_FDMA_PCTRL_EN BIT(0) /* FDMA Port Enable */ +#define GSWIP_FDMA_PCTRL_STEN BIT(1) /* Special Tag Insertion Enable */ +#define GSWIP_FDMA_PCTRL_VLANMOD_MASK GENMASK(4, 3) /* VLAN Modification Control */ +#define GSWIP_FDMA_PCTRL_VLANMOD_SHIFT 3 /* VLAN Modification Control */ +#define GSWIP_FDMA_PCTRL_VLANMOD_DIS (0x0 << GSWIP_FDMA_PCTRL_VLANMOD_SHIFT) +#define GSWIP_FDMA_PCTRL_VLANMOD_PRIO (0x1 << GSWIP_FDMA_PCTRL_VLANMOD_SHIFT) +#define GSWIP_FDMA_PCTRL_VLANMOD_ID (0x2 << GSWIP_FDMA_PCTRL_VLANMOD_SHIFT) +#define GSWIP_FDMA_PCTRL_VLANMOD_BOTH (0x3 << GSWIP_FDMA_PCTRL_VLANMOD_SHIFT) + +/* Ethernet Switch Store DMA Port Control Register */ +#define GSWIP_SDMA_PCTRLp(p) (0xBC0 + ((p) * 0x6)) +#define GSWIP_SDMA_PCTRL_EN BIT(0) /* SDMA Port Enable */ +#define GSWIP_SDMA_PCTRL_FCEN BIT(1) /* Flow Control Enable */ +#define GSWIP_SDMA_PCTRL_PAUFWD BIT(1) /* Pause Frame Forwarding */ + +#define XRX200_GPHY_FW_ALIGN (16 * 1024) + +struct gswip_hw_info { + int max_ports; + int cpu_port; +}; + +struct xway_gphy_match_data { + char *fe_firmware_name; + char *ge_firmware_name; +}; + +struct gswip_gphy_fw { + struct clk *clk_gate; + struct reset_control *reset; + u32 fw_addr_offset; + char *fw_name; +}; + +struct gswip_priv { + __iomem void *gswip; + __iomem void *mdio; + __iomem void *mii; + const struct gswip_hw_info *hw_info; + const struct xway_gphy_match_data *gphy_fw_name_cfg; + struct dsa_switch *ds; + struct device *dev; + struct regmap *rcu_regmap; + int num_gphy_fw; + struct gswip_gphy_fw *gphy_fw; +}; + +struct gswip_rmon_cnt_desc { + unsigned int size; + unsigned int offset; + const char *name; +}; + +#define MIB_DESC(_size, _offset, _name) {.size = _size, .offset = _offset, .name = _name} + +static const struct gswip_rmon_cnt_desc gswip_rmon_cnt[] = { + /** Receive Packet Count (only packets that are accepted and not discarded). */ + MIB_DESC(1, 0x1F, "RxGoodPkts"), + MIB_DESC(1, 0x23, "RxUnicastPkts"), + MIB_DESC(1, 0x22, "RxMulticastPkts"), + MIB_DESC(1, 0x21, "RxFCSErrorPkts"), + MIB_DESC(1, 0x1D, "RxUnderSizeGoodPkts"), + MIB_DESC(1, 0x1E, "RxUnderSizeErrorPkts"), + MIB_DESC(1, 0x1B, "RxOversizeGoodPkts"), + MIB_DESC(1, 0x1C, "RxOversizeErrorPkts"), + MIB_DESC(1, 0x20, "RxGoodPausePkts"), + MIB_DESC(1, 0x1A, "RxAlignErrorPkts"), + MIB_DESC(1, 0x12, "Rx64BytePkts"), + MIB_DESC(1, 0x13, "Rx127BytePkts"), + MIB_DESC(1, 0x14, "Rx255BytePkts"), + MIB_DESC(1, 0x15, "Rx511BytePkts"), + MIB_DESC(1, 0x16, "Rx1023BytePkts"), + /** Receive Size 1024-1522 (or more, if configured) Packet Count. */ + MIB_DESC(1, 0x17, "RxMaxBytePkts"), + MIB_DESC(1, 0x18, "RxDroppedPkts"), + MIB_DESC(1, 0x19, "RxFilteredPkts"), + MIB_DESC(2, 0x24, "RxGoodBytes"), + MIB_DESC(2, 0x26, "RxBadBytes"), + MIB_DESC(1, 0x11, "TxAcmDroppedPkts"), + MIB_DESC(1, 0x0C, "TxGoodPkts"), + MIB_DESC(1, 0x06, "TxUnicastPkts"), + MIB_DESC(1, 0x07, "TxMulticastPkts"), + MIB_DESC(1, 0x00, "Tx64BytePkts"), + MIB_DESC(1, 0x01, "Tx127BytePkts"), + MIB_DESC(1, 0x02, "Tx255BytePkts"), + MIB_DESC(1, 0x03, "Tx511BytePkts"), + MIB_DESC(1, 0x04, "Tx1023BytePkts"), + /** Transmit Size 1024-1522 (or more, if configured) Packet Count. */ + MIB_DESC(1, 0x05, "TxMaxBytePkts"), + MIB_DESC(1, 0x08, "TxSingleCollCount"), + MIB_DESC(1, 0x09, "TxMultCollCount"), + MIB_DESC(1, 0x0A, "TxLateCollCount"), + MIB_DESC(1, 0x0B, "TxExcessCollCount"), + MIB_DESC(1, 0x0D, "TxPauseCount"), + MIB_DESC(1, 0x10, "TxDroppedPkts"), + MIB_DESC(2, 0x0E, "TxGoodBytes"), +}; + +static u32 gswip_switch_r(struct gswip_priv *priv, u32 offset) +{ + return __raw_readl(priv->gswip + (offset * 4)); +} + +static void gswip_switch_w(struct gswip_priv *priv, u32 val, u32 offset) +{ + __raw_writel(val, priv->gswip + (offset * 4)); +} + +static void gswip_switch_mask(struct gswip_priv *priv, u32 clear, u32 set, + u32 offset) +{ + u32 val = gswip_switch_r(priv, offset); + + val &= ~(clear); + val |= set; + gswip_switch_w(priv, val, offset); +} + +static u32 gswip_switch_r_timeout(struct gswip_priv *priv, u32 offset, + u32 cleared) +{ + u32 val; + + return readx_poll_timeout(__raw_readl, priv->gswip + (offset * 4), val, + (val & cleared) == 0, 20, 50000); +} + +static u32 gswip_mdio_r(struct gswip_priv *priv, u32 offset) +{ + return __raw_readl(priv->mdio + (offset * 4)); +} + +static void gswip_mdio_w(struct gswip_priv *priv, u32 val, u32 offset) +{ + __raw_writel(val, priv->mdio + (offset * 4)); +} + +static void gswip_mdio_mask(struct gswip_priv *priv, u32 clear, u32 set, + u32 offset) +{ + u32 val = gswip_mdio_r(priv, offset); + + val &= ~(clear); + val |= set; + gswip_mdio_w(priv, val, offset); +} + +static u32 gswip_mii_r(struct gswip_priv *priv, u32 offset) +{ + return __raw_readl(priv->mii + (offset * 4)); +} + +static void gswip_mii_w(struct gswip_priv *priv, u32 val, u32 offset) +{ + __raw_writel(val, priv->mii + (offset * 4)); +} + +static void gswip_mii_mask(struct gswip_priv *priv, u32 clear, u32 set, + u32 offset) +{ + u32 val = gswip_mii_r(priv, offset); + + val &= ~(clear); + val |= set; + gswip_mii_w(priv, val, offset); +} + +static void gswip_mii_mask_cfg(struct gswip_priv *priv, u32 clear, u32 set, + int port) +{ + switch (port) { + case 0: + gswip_mii_mask(priv, clear, set, GSWIP_MII_CFG0); + break; + case 1: + gswip_mii_mask(priv, clear, set, GSWIP_MII_CFG1); + break; + case 5: + gswip_mii_mask(priv, clear, set, GSWIP_MII_CFG5); + break; + } +} + +static void gswip_mii_mask_pcdu(struct gswip_priv *priv, u32 clear, u32 set, + int port) +{ + switch (port) { + case 0: + gswip_mii_mask(priv, clear, set, GSWIP_MII_PCDU0); + break; + case 1: + gswip_mii_mask(priv, clear, set, GSWIP_MII_PCDU1); + break; + case 5: + gswip_mii_mask(priv, clear, set, GSWIP_MII_PCDU5); + break; + } +} + +static int gswip_mdio_poll(struct gswip_priv *priv) +{ + int cnt = 100; + + while (likely(cnt--)) { + u32 ctrl = gswip_mdio_r(priv, GSWIP_MDIO_CTRL); + + if ((ctrl & GSWIP_MDIO_CTRL_BUSY) == 0) + return 0; + usleep_range(20, 40); + } + + return -ETIMEDOUT; +} + +static int gswip_mdio_wr(struct mii_bus *bus, int addr, int reg, u16 val) +{ + struct gswip_priv *priv = bus->priv; + int err; + + err = gswip_mdio_poll(priv); + if (err) { + dev_err(&bus->dev, "waiting for MDIO bus busy timed out\n"); + return err; + } + + gswip_mdio_w(priv, val, GSWIP_MDIO_WRITE); + gswip_mdio_w(priv, GSWIP_MDIO_CTRL_BUSY | GSWIP_MDIO_CTRL_WR | + ((addr & GSWIP_MDIO_CTRL_PHYAD_MASK) << GSWIP_MDIO_CTRL_PHYAD_SHIFT) | + (reg & GSWIP_MDIO_CTRL_REGAD_MASK), + GSWIP_MDIO_CTRL); + + return 0; +} + +static int gswip_mdio_rd(struct mii_bus *bus, int addr, int reg) +{ + struct gswip_priv *priv = bus->priv; + int err; + + err = gswip_mdio_poll(priv); + if (err) { + dev_err(&bus->dev, "waiting for MDIO bus busy timed out\n"); + return err; + } + + gswip_mdio_w(priv, GSWIP_MDIO_CTRL_BUSY | GSWIP_MDIO_CTRL_RD | + ((addr & GSWIP_MDIO_CTRL_PHYAD_MASK) << GSWIP_MDIO_CTRL_PHYAD_SHIFT) | + (reg & GSWIP_MDIO_CTRL_REGAD_MASK), + GSWIP_MDIO_CTRL); + + err = gswip_mdio_poll(priv); + if (err) { + dev_err(&bus->dev, "waiting for MDIO bus busy timed out\n"); + return err; + } + + return gswip_mdio_r(priv, GSWIP_MDIO_READ); +} + +static int gswip_mdio(struct gswip_priv *priv, struct device_node *mdio_np) +{ + struct dsa_switch *ds = priv->ds; + + ds->slave_mii_bus = devm_mdiobus_alloc(priv->dev); + if (!ds->slave_mii_bus) + return -ENOMEM; + + ds->slave_mii_bus->priv = priv; + ds->slave_mii_bus->read = gswip_mdio_rd; + ds->slave_mii_bus->write = gswip_mdio_wr; + ds->slave_mii_bus->name = "lantiq,xrx200-mdio"; + snprintf(ds->slave_mii_bus->id, MII_BUS_ID_SIZE, "%s-mii", + dev_name(priv->dev)); + ds->slave_mii_bus->parent = priv->dev; + ds->slave_mii_bus->phy_mask = ~ds->phys_mii_mask; + + return of_mdiobus_register(ds->slave_mii_bus, mdio_np); +} + +static int gswip_port_enable(struct dsa_switch *ds, int port, + struct phy_device *phydev) +{ + struct gswip_priv *priv = ds->priv; + + /* RMON Counter Enable for port */ + gswip_switch_w(priv, GSWIP_BM_PCFG_CNTEN, GSWIP_BM_PCFGp(port)); + + /* enable port fetch/store dma & VLAN Modification */ + gswip_switch_mask(priv, 0, GSWIP_FDMA_PCTRL_EN | + GSWIP_FDMA_PCTRL_VLANMOD_BOTH, + GSWIP_FDMA_PCTRLp(port)); + gswip_switch_mask(priv, 0, GSWIP_SDMA_PCTRL_EN, + GSWIP_SDMA_PCTRLp(port)); + gswip_switch_mask(priv, 0, GSWIP_PCE_PCTRL_0_INGRESS, + GSWIP_PCE_PCTRL_0p(port)); + + if (!dsa_is_cpu_port(ds, port)) { + u32 macconf = GSWIP_MDIO_PHY_LINK_AUTO | + GSWIP_MDIO_PHY_SPEED_AUTO | + GSWIP_MDIO_PHY_FDUP_AUTO | + GSWIP_MDIO_PHY_FCONTX_AUTO | + GSWIP_MDIO_PHY_FCONRX_AUTO | + (phydev->mdio.addr & GSWIP_MDIO_PHY_ADDR_MASK); + + gswip_mdio_w(priv, macconf, GSWIP_MDIO_PHYp(port)); + /* Activate MDIO auto polling */ + gswip_mdio_mask(priv, 0, BIT(port), GSWIP_MDIO_MDC_CFG0); + } + + return 0; +} + +static void gswip_port_disable(struct dsa_switch *ds, int port, + struct phy_device *phy) +{ + struct gswip_priv *priv = ds->priv; + + if (!dsa_is_cpu_port(ds, port)) { + gswip_mdio_mask(priv, GSWIP_MDIO_PHY_LINK_DOWN, + GSWIP_MDIO_PHY_LINK_MASK, + GSWIP_MDIO_PHYp(port)); + /* Deactivate MDIO auto polling */ + gswip_mdio_mask(priv, BIT(port), 0, GSWIP_MDIO_MDC_CFG0); + } + + gswip_switch_mask(priv, GSWIP_FDMA_PCTRL_EN, 0, + GSWIP_FDMA_PCTRLp(port)); + gswip_switch_mask(priv, GSWIP_SDMA_PCTRL_EN, 0, + GSWIP_SDMA_PCTRLp(port)); +} + +static int gswip_pce_load_microcode(struct gswip_priv *priv) +{ + int i; + int err; + + gswip_switch_mask(priv, GSWIP_PCE_TBL_CTRL_ADDR_MASK | + GSWIP_PCE_TBL_CTRL_OPMOD_MASK, + GSWIP_PCE_TBL_CTRL_OPMOD_ADWR, GSWIP_PCE_TBL_CTRL); + gswip_switch_w(priv, 0, GSWIP_PCE_TBL_MASK); + + for (i = 0; i < ARRAY_SIZE(gswip_pce_microcode); i++) { + gswip_switch_w(priv, i, GSWIP_PCE_TBL_ADDR); + gswip_switch_w(priv, gswip_pce_microcode[i].val_0, + GSWIP_PCE_TBL_VAL(0)); + gswip_switch_w(priv, gswip_pce_microcode[i].val_1, + GSWIP_PCE_TBL_VAL(1)); + gswip_switch_w(priv, gswip_pce_microcode[i].val_2, + GSWIP_PCE_TBL_VAL(2)); + gswip_switch_w(priv, gswip_pce_microcode[i].val_3, + GSWIP_PCE_TBL_VAL(3)); + + /* start the table access: */ + gswip_switch_mask(priv, 0, GSWIP_PCE_TBL_CTRL_BAS, + GSWIP_PCE_TBL_CTRL); + err = gswip_switch_r_timeout(priv, GSWIP_PCE_TBL_CTRL, + GSWIP_PCE_TBL_CTRL_BAS); + if (err) + return err; + } + + /* tell the switch that the microcode is loaded */ + gswip_switch_mask(priv, 0, GSWIP_PCE_GCTRL_0_MC_VALID, + GSWIP_PCE_GCTRL_0); + + return 0; +} + +static int gswip_setup(struct dsa_switch *ds) +{ + struct gswip_priv *priv = ds->priv; + unsigned int cpu_port = priv->hw_info->cpu_port; + int i; + int err; + + gswip_switch_w(priv, GSWIP_SWRES_R0, GSWIP_SWRES); + usleep_range(5000, 10000); + gswip_switch_w(priv, 0, GSWIP_SWRES); + + /* disable port fetch/store dma on all ports */ + for (i = 0; i < priv->hw_info->max_ports; i++) + gswip_port_disable(ds, i, NULL); + + /* enable Switch */ + gswip_mdio_mask(priv, 0, GSWIP_MDIO_GLOB_ENABLE, GSWIP_MDIO_GLOB); + + err = gswip_pce_load_microcode(priv); + if (err) { + dev_err(priv->dev, "writing PCE microcode failed, %i", err); + return err; + } + + /* Default unknown Broadcast/Multicast/Unicast port maps */ + gswip_switch_w(priv, BIT(cpu_port), GSWIP_PCE_PMAP1); + gswip_switch_w(priv, BIT(cpu_port), GSWIP_PCE_PMAP2); + gswip_switch_w(priv, BIT(cpu_port), GSWIP_PCE_PMAP3); + + /* disable PHY auto polling */ + gswip_mdio_w(priv, 0x0, GSWIP_MDIO_MDC_CFG0); + /* Configure the MDIO Clock 2.5 MHz */ + gswip_mdio_mask(priv, 0xff, 0x09, GSWIP_MDIO_MDC_CFG1); + + /* Disable the xMII link */ + gswip_mii_mask_cfg(priv, GSWIP_MII_CFG_EN, 0, 0); + gswip_mii_mask_cfg(priv, GSWIP_MII_CFG_EN, 0, 1); + gswip_mii_mask_cfg(priv, GSWIP_MII_CFG_EN, 0, 5); + + /* enable special tag insertion on cpu port */ + gswip_switch_mask(priv, 0, GSWIP_FDMA_PCTRL_STEN, + GSWIP_FDMA_PCTRLp(cpu_port)); + + gswip_switch_mask(priv, 0, GSWIP_MAC_CTRL_2_MLEN, + GSWIP_MAC_CTRL_2p(cpu_port)); + gswip_switch_w(priv, VLAN_ETH_FRAME_LEN + 8, GSWIP_MAC_FLEN); + gswip_switch_mask(priv, 0, GSWIP_BM_QUEUE_GCTRL_GL_MOD, + GSWIP_BM_QUEUE_GCTRL); + + /* VLAN aware Switching */ + gswip_switch_mask(priv, 0, GSWIP_PCE_GCTRL_0_VLAN, GSWIP_PCE_GCTRL_0); + + /* Mac Address Table Lock */ + gswip_switch_mask(priv, 0, GSWIP_PCE_GCTRL_1_MAC_GLOCK | + GSWIP_PCE_GCTRL_1_MAC_GLOCK_MOD, + GSWIP_PCE_GCTRL_1); + + gswip_port_enable(ds, cpu_port, NULL); + return 0; +} + +static enum dsa_tag_protocol gswip_get_tag_protocol(struct dsa_switch *ds, + int port) +{ + return DSA_TAG_PROTO_GSWIP; +} + +static void gswip_phylink_validate(struct dsa_switch *ds, int port, + unsigned long *supported, + struct phylink_link_state *state) +{ + __ETHTOOL_DECLARE_LINK_MODE_MASK(mask) = { 0, }; + + switch (port) { + case 0: + case 1: + if (!phy_interface_mode_is_rgmii(state->interface) && + state->interface != PHY_INTERFACE_MODE_MII && + state->interface != PHY_INTERFACE_MODE_REVMII && + state->interface != PHY_INTERFACE_MODE_RMII) + goto unsupported; + break; + case 2: + case 3: + case 4: + if (state->interface != PHY_INTERFACE_MODE_INTERNAL) + goto unsupported; + break; + case 5: + if (!phy_interface_mode_is_rgmii(state->interface) && + state->interface != PHY_INTERFACE_MODE_INTERNAL) + goto unsupported; + break; + default: + bitmap_zero(supported, __ETHTOOL_LINK_MODE_MASK_NBITS); + dev_err(ds->dev, "Unsupported port: %i\n", port); + return; + } + + /* Allow all the expected bits */ + phylink_set(mask, Autoneg); + phylink_set_port_modes(mask); + phylink_set(mask, Pause); + phylink_set(mask, Asym_Pause); + + /* With the exclusion of MII and Reverse MII, we support Gigabit, + * including Half duplex + */ + if (state->interface != PHY_INTERFACE_MODE_MII && + state->interface != PHY_INTERFACE_MODE_REVMII) { + phylink_set(mask, 1000baseT_Full); + phylink_set(mask, 1000baseT_Half); + } + + phylink_set(mask, 10baseT_Half); + phylink_set(mask, 10baseT_Full); + phylink_set(mask, 100baseT_Half); + phylink_set(mask, 100baseT_Full); + + bitmap_and(supported, supported, mask, + __ETHTOOL_LINK_MODE_MASK_NBITS); + bitmap_and(state->advertising, state->advertising, mask, + __ETHTOOL_LINK_MODE_MASK_NBITS); + return; + +unsupported: + bitmap_zero(supported, __ETHTOOL_LINK_MODE_MASK_NBITS); + dev_err(ds->dev, "Unsupported interface: %d\n", state->interface); + return; +} + +static void gswip_phylink_mac_config(struct dsa_switch *ds, int port, + unsigned int mode, + const struct phylink_link_state *state) +{ + struct gswip_priv *priv = ds->priv; + u32 miicfg = 0; + + miicfg |= GSWIP_MII_CFG_LDCLKDIS; + + switch (state->interface) { + case PHY_INTERFACE_MODE_MII: + case PHY_INTERFACE_MODE_INTERNAL: + miicfg |= GSWIP_MII_CFG_MODE_MIIM; + break; + case PHY_INTERFACE_MODE_REVMII: + miicfg |= GSWIP_MII_CFG_MODE_MIIP; + break; + case PHY_INTERFACE_MODE_RMII: + miicfg |= GSWIP_MII_CFG_MODE_RMIIM; + break; + case PHY_INTERFACE_MODE_RGMII: + case PHY_INTERFACE_MODE_RGMII_ID: + case PHY_INTERFACE_MODE_RGMII_RXID: + case PHY_INTERFACE_MODE_RGMII_TXID: + miicfg |= GSWIP_MII_CFG_MODE_RGMII; + break; + default: + dev_err(ds->dev, + "Unsupported interface: %d\n", state->interface); + return; + } + gswip_mii_mask_cfg(priv, GSWIP_MII_CFG_MODE_MASK, miicfg, port); + + switch (state->interface) { + case PHY_INTERFACE_MODE_RGMII_ID: + gswip_mii_mask_pcdu(priv, GSWIP_MII_PCDU_TXDLY_MASK | + GSWIP_MII_PCDU_RXDLY_MASK, 0, port); + break; + case PHY_INTERFACE_MODE_RGMII_RXID: + gswip_mii_mask_pcdu(priv, GSWIP_MII_PCDU_RXDLY_MASK, 0, port); + break; + case PHY_INTERFACE_MODE_RGMII_TXID: + gswip_mii_mask_pcdu(priv, GSWIP_MII_PCDU_TXDLY_MASK, 0, port); + break; + default: + break; + } +} + +static void gswip_phylink_mac_link_down(struct dsa_switch *ds, int port, + unsigned int mode, + phy_interface_t interface) +{ + struct gswip_priv *priv = ds->priv; + + gswip_mii_mask_cfg(priv, GSWIP_MII_CFG_EN, 0, port); +} + +static void gswip_phylink_mac_link_up(struct dsa_switch *ds, int port, + unsigned int mode, + phy_interface_t interface, + struct phy_device *phydev) +{ + struct gswip_priv *priv = ds->priv; + + /* Enable the xMII interface only for the external PHY */ + if (interface != PHY_INTERFACE_MODE_INTERNAL) + gswip_mii_mask_cfg(priv, 0, GSWIP_MII_CFG_EN, port); +} + +static void gswip_get_strings(struct dsa_switch *ds, int port, u32 stringset, + uint8_t *data) +{ + int i; + + if (stringset != ETH_SS_STATS) + return; + + for (i = 0; i < ARRAY_SIZE(gswip_rmon_cnt); i++) + strncpy(data + i * ETH_GSTRING_LEN, gswip_rmon_cnt[i].name, + ETH_GSTRING_LEN); +} + +static u32 gswip_bcm_ram_entry_read(struct gswip_priv *priv, u32 table, + u32 index) +{ + u32 result; + int err; + + gswip_switch_w(priv, index, GSWIP_BM_RAM_ADDR); + gswip_switch_mask(priv, GSWIP_BM_RAM_CTRL_ADDR_MASK | + GSWIP_BM_RAM_CTRL_OPMOD, + table | GSWIP_BM_RAM_CTRL_BAS, + GSWIP_BM_RAM_CTRL); + + err = gswip_switch_r_timeout(priv, GSWIP_BM_RAM_CTRL, + GSWIP_BM_RAM_CTRL_BAS); + if (err) { + dev_err(priv->dev, "timeout while reading table: %u, index: %u", + table, index); + return 0; + } + + result = gswip_switch_r(priv, GSWIP_BM_RAM_VAL(0)); + result |= gswip_switch_r(priv, GSWIP_BM_RAM_VAL(1)) << 16; + + return result; +} + +static void gswip_get_ethtool_stats(struct dsa_switch *ds, int port, + uint64_t *data) +{ + struct gswip_priv *priv = ds->priv; + const struct gswip_rmon_cnt_desc *rmon_cnt; + int i; + u64 high; + + for (i = 0; i < ARRAY_SIZE(gswip_rmon_cnt); i++) { + rmon_cnt = &gswip_rmon_cnt[i]; + + data[i] = gswip_bcm_ram_entry_read(priv, port, + rmon_cnt->offset); + if (rmon_cnt->size == 2) { + high = gswip_bcm_ram_entry_read(priv, port, + rmon_cnt->offset + 1); + data[i] |= high << 32; + } + } +} + +static int gswip_get_sset_count(struct dsa_switch *ds, int port, int sset) +{ + if (sset != ETH_SS_STATS) + return 0; + + return ARRAY_SIZE(gswip_rmon_cnt); +} + +static const struct dsa_switch_ops gswip_switch_ops = { + .get_tag_protocol = gswip_get_tag_protocol, + .setup = gswip_setup, + .port_enable = gswip_port_enable, + .port_disable = gswip_port_disable, + .phylink_validate = gswip_phylink_validate, + .phylink_mac_config = gswip_phylink_mac_config, + .phylink_mac_link_down = gswip_phylink_mac_link_down, + .phylink_mac_link_up = gswip_phylink_mac_link_up, + .get_strings = gswip_get_strings, + .get_ethtool_stats = gswip_get_ethtool_stats, + .get_sset_count = gswip_get_sset_count, +}; + +static const struct xway_gphy_match_data xrx200a1x_gphy_data = { + .fe_firmware_name = "lantiq/xrx200_phy22f_a14.bin", + .ge_firmware_name = "lantiq/xrx200_phy11g_a14.bin", +}; + +static const struct xway_gphy_match_data xrx200a2x_gphy_data = { + .fe_firmware_name = "lantiq/xrx200_phy22f_a22.bin", + .ge_firmware_name = "lantiq/xrx200_phy11g_a22.bin", +}; + +static const struct xway_gphy_match_data xrx300_gphy_data = { + .fe_firmware_name = "lantiq/xrx300_phy22f_a21.bin", + .ge_firmware_name = "lantiq/xrx300_phy11g_a21.bin", +}; + +static const struct of_device_id xway_gphy_match[] = { + { .compatible = "lantiq,xrx200-gphy-fw", .data = NULL }, + { .compatible = "lantiq,xrx200a1x-gphy-fw", .data = &xrx200a1x_gphy_data }, + { .compatible = "lantiq,xrx200a2x-gphy-fw", .data = &xrx200a2x_gphy_data }, + { .compatible = "lantiq,xrx300-gphy-fw", .data = &xrx300_gphy_data }, + { .compatible = "lantiq,xrx330-gphy-fw", .data = &xrx300_gphy_data }, + {}, +}; + +static int gswip_gphy_fw_load(struct gswip_priv *priv, struct gswip_gphy_fw *gphy_fw) +{ + struct device *dev = priv->dev; + const struct firmware *fw; + void *fw_addr; + dma_addr_t dma_addr; + dma_addr_t dev_addr; + size_t size; + int ret; + + ret = clk_prepare_enable(gphy_fw->clk_gate); + if (ret) + return ret; + + reset_control_assert(gphy_fw->reset); + + ret = request_firmware(&fw, gphy_fw->fw_name, dev); + if (ret) { + dev_err(dev, "failed to load firmware: %s, error: %i\n", + gphy_fw->fw_name, ret); + return ret; + } + + /* GPHY cores need the firmware code in a persistent and contiguous + * memory area with a 16 kB boundary aligned start address. + */ + size = fw->size + XRX200_GPHY_FW_ALIGN; + + fw_addr = dmam_alloc_coherent(dev, size, &dma_addr, GFP_KERNEL); + if (fw_addr) { + fw_addr = PTR_ALIGN(fw_addr, XRX200_GPHY_FW_ALIGN); + dev_addr = ALIGN(dma_addr, XRX200_GPHY_FW_ALIGN); + memcpy(fw_addr, fw->data, fw->size); + } else { + dev_err(dev, "failed to alloc firmware memory\n"); + release_firmware(fw); + return -ENOMEM; + } + + release_firmware(fw); + + ret = regmap_write(priv->rcu_regmap, gphy_fw->fw_addr_offset, dev_addr); + if (ret) + return ret; + + reset_control_deassert(gphy_fw->reset); + + return ret; +} + +static int gswip_gphy_fw_probe(struct gswip_priv *priv, + struct gswip_gphy_fw *gphy_fw, + struct device_node *gphy_fw_np, int i) +{ + struct device *dev = priv->dev; + u32 gphy_mode; + int ret; + char gphyname[10]; + + snprintf(gphyname, sizeof(gphyname), "gphy%d", i); + + gphy_fw->clk_gate = devm_clk_get(dev, gphyname); + if (IS_ERR(gphy_fw->clk_gate)) { + dev_err(dev, "Failed to lookup gate clock\n"); + return PTR_ERR(gphy_fw->clk_gate); + } + + ret = of_property_read_u32(gphy_fw_np, "reg", &gphy_fw->fw_addr_offset); + if (ret) + return ret; + + ret = of_property_read_u32(gphy_fw_np, "lantiq,gphy-mode", &gphy_mode); + /* Default to GE mode */ + if (ret) + gphy_mode = GPHY_MODE_GE; + + switch (gphy_mode) { + case GPHY_MODE_FE: + gphy_fw->fw_name = priv->gphy_fw_name_cfg->fe_firmware_name; + break; + case GPHY_MODE_GE: + gphy_fw->fw_name = priv->gphy_fw_name_cfg->ge_firmware_name; + break; + default: + dev_err(dev, "Unknown GPHY mode %d\n", gphy_mode); + return -EINVAL; + } + + gphy_fw->reset = of_reset_control_array_get_exclusive(gphy_fw_np); + if (IS_ERR(gphy_fw->reset)) { + if (PTR_ERR(gphy_fw->reset) != -EPROBE_DEFER) + dev_err(dev, "Failed to lookup gphy reset\n"); + return PTR_ERR(gphy_fw->reset); + } + + return gswip_gphy_fw_load(priv, gphy_fw); +} + +static void gswip_gphy_fw_remove(struct gswip_priv *priv, + struct gswip_gphy_fw *gphy_fw) +{ + int ret; + + /* check if the device was fully probed */ + if (!gphy_fw->fw_name) + return; + + ret = regmap_write(priv->rcu_regmap, gphy_fw->fw_addr_offset, 0); + if (ret) + dev_err(priv->dev, "can not reset GPHY FW pointer"); + + clk_disable_unprepare(gphy_fw->clk_gate); + + reset_control_put(gphy_fw->reset); +} + +static int gswip_gphy_fw_list(struct gswip_priv *priv, + struct device_node *gphy_fw_list_np, u32 version) +{ + struct device *dev = priv->dev; + struct device_node *gphy_fw_np; + const struct of_device_id *match; + int err; + int i = 0; + + /* The VRX200 rev 1.1 uses the GSWIP 2.0 and needs the older + * GPHY firmware. The VRX200 rev 1.2 uses the GSWIP 2.1 and also + * needs a different GPHY firmware. + */ + if (of_device_is_compatible(gphy_fw_list_np, "lantiq,xrx200-gphy-fw")) { + switch (version) { + case GSWIP_VERSION_2_0: + priv->gphy_fw_name_cfg = &xrx200a1x_gphy_data; + break; + case GSWIP_VERSION_2_1: + priv->gphy_fw_name_cfg = &xrx200a2x_gphy_data; + break; + default: + dev_err(dev, "unknown GSWIP version: 0x%x", version); + return -ENOENT; + } + } + + match = of_match_node(xway_gphy_match, gphy_fw_list_np); + if (match && match->data) + priv->gphy_fw_name_cfg = match->data; + + if (!priv->gphy_fw_name_cfg) { + dev_err(dev, "GPHY compatible type not supported"); + return -ENOENT; + } + + priv->num_gphy_fw = of_get_available_child_count(gphy_fw_list_np); + if (!priv->num_gphy_fw) + return -ENOENT; + + priv->rcu_regmap = syscon_regmap_lookup_by_phandle(gphy_fw_list_np, + "lantiq,rcu"); + if (IS_ERR(priv->rcu_regmap)) + return PTR_ERR(priv->rcu_regmap); + + priv->gphy_fw = devm_kmalloc_array(dev, priv->num_gphy_fw, + sizeof(*priv->gphy_fw), + GFP_KERNEL | __GFP_ZERO); + if (!priv->gphy_fw) + return -ENOMEM; + + for_each_available_child_of_node(gphy_fw_list_np, gphy_fw_np) { + err = gswip_gphy_fw_probe(priv, &priv->gphy_fw[i], + gphy_fw_np, i); + if (err) + goto remove_gphy; + i++; + } + + return 0; + +remove_gphy: + for (i = 0; i < priv->num_gphy_fw; i++) + gswip_gphy_fw_remove(priv, &priv->gphy_fw[i]); + return err; +} + +static int gswip_probe(struct platform_device *pdev) +{ + struct gswip_priv *priv; + struct resource *gswip_res, *mdio_res, *mii_res; + struct device_node *mdio_np, *gphy_fw_np; + struct device *dev = &pdev->dev; + int err; + int i; + u32 version; + + priv = devm_kzalloc(dev, sizeof(*priv), GFP_KERNEL); + if (!priv) + return -ENOMEM; + + gswip_res = platform_get_resource(pdev, IORESOURCE_MEM, 0); + priv->gswip = devm_ioremap_resource(dev, gswip_res); + if (IS_ERR(priv->gswip)) + return PTR_ERR(priv->gswip); + + mdio_res = platform_get_resource(pdev, IORESOURCE_MEM, 1); + priv->mdio = devm_ioremap_resource(dev, mdio_res); + if (IS_ERR(priv->mdio)) + return PTR_ERR(priv->mdio); + + mii_res = platform_get_resource(pdev, IORESOURCE_MEM, 2); + priv->mii = devm_ioremap_resource(dev, mii_res); + if (IS_ERR(priv->mii)) + return PTR_ERR(priv->mii); + + priv->hw_info = of_device_get_match_data(dev); + if (!priv->hw_info) + return -EINVAL; + + priv->ds = dsa_switch_alloc(dev, priv->hw_info->max_ports); + if (!priv->ds) + return -ENOMEM; + + priv->ds->priv = priv; + priv->ds->ops = &gswip_switch_ops; + priv->dev = dev; + version = gswip_switch_r(priv, GSWIP_VERSION); + + /* bring up the mdio bus */ + gphy_fw_np = of_find_compatible_node(pdev->dev.of_node, NULL, + "lantiq,gphy-fw"); + if (gphy_fw_np) { + err = gswip_gphy_fw_list(priv, gphy_fw_np, version); + if (err) { + dev_err(dev, "gphy fw probe failed\n"); + return err; + } + } + + /* bring up the mdio bus */ + mdio_np = of_find_compatible_node(pdev->dev.of_node, NULL, + "lantiq,xrx200-mdio"); + if (mdio_np) { + err = gswip_mdio(priv, mdio_np); + if (err) { + dev_err(dev, "mdio probe failed\n"); + goto gphy_fw; + } + } + + err = dsa_register_switch(priv->ds); + if (err) { + dev_err(dev, "dsa switch register failed: %i\n", err); + goto mdio_bus; + } + if (!dsa_is_cpu_port(priv->ds, priv->hw_info->cpu_port)) { + dev_err(dev, "wrong CPU port defined, HW only supports port: %i", + priv->hw_info->cpu_port); + err = -EINVAL; + goto mdio_bus; + } + + platform_set_drvdata(pdev, priv); + + dev_info(dev, "probed GSWIP version %lx mod %lx\n", + (version & GSWIP_VERSION_REV_MASK) >> GSWIP_VERSION_REV_SHIFT, + (version & GSWIP_VERSION_MOD_MASK) >> GSWIP_VERSION_MOD_SHIFT); + return 0; + +mdio_bus: + if (mdio_np) + mdiobus_unregister(priv->ds->slave_mii_bus); +gphy_fw: + for (i = 0; i < priv->num_gphy_fw; i++) + gswip_gphy_fw_remove(priv, &priv->gphy_fw[i]); + return err; +} + +static int gswip_remove(struct platform_device *pdev) +{ + struct gswip_priv *priv = platform_get_drvdata(pdev); + int i; + + if (!priv) + return 0; + + /* disable the switch */ + gswip_mdio_mask(priv, GSWIP_MDIO_GLOB_ENABLE, 0, GSWIP_MDIO_GLOB); + + dsa_unregister_switch(priv->ds); + + if (priv->ds->slave_mii_bus) + mdiobus_unregister(priv->ds->slave_mii_bus); + + for (i = 0; i < priv->num_gphy_fw; i++) + gswip_gphy_fw_remove(priv, &priv->gphy_fw[i]); + + return 0; +} + +static const struct gswip_hw_info gswip_xrx200 = { + .max_ports = 7, + .cpu_port = 6, +}; + +static const struct of_device_id gswip_of_match[] = { + { .compatible = "lantiq,xrx200-gswip", .data = &gswip_xrx200 }, + {}, +}; +MODULE_DEVICE_TABLE(of, gswip_of_match); + +static struct platform_driver gswip_driver = { + .probe = gswip_probe, + .remove = gswip_remove, + .driver = { + .name = "gswip", + .of_match_table = gswip_of_match, + }, +}; + +module_platform_driver(gswip_driver); + +MODULE_AUTHOR("Hauke Mehrtens <hauke@hauke-m.de>"); +MODULE_DESCRIPTION("Lantiq / Intel GSWIP driver"); +MODULE_LICENSE("GPL v2"); diff --git a/drivers/net/dsa/lantiq_pce.h b/drivers/net/dsa/lantiq_pce.h new file mode 100644 index 000000000000..180663138e75 --- /dev/null +++ b/drivers/net/dsa/lantiq_pce.h @@ -0,0 +1,153 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * PCE microcode extracted from UGW 7.1.1 switch api + * + * Copyright (c) 2012, 2014, 2015 Lantiq Deutschland GmbH + * Copyright (C) 2012 John Crispin <john@phrozen.org> + * Copyright (C) 2017 - 2018 Hauke Mehrtens <hauke@hauke-m.de> + */ + +enum { + OUT_MAC0 = 0, + OUT_MAC1, + OUT_MAC2, + OUT_MAC3, + OUT_MAC4, + OUT_MAC5, + OUT_ETHTYP, + OUT_VTAG0, + OUT_VTAG1, + OUT_ITAG0, + OUT_ITAG1, /*10 */ + OUT_ITAG2, + OUT_ITAG3, + OUT_IP0, + OUT_IP1, + OUT_IP2, + OUT_IP3, + OUT_SIP0, + OUT_SIP1, + OUT_SIP2, + OUT_SIP3, /*20*/ + OUT_SIP4, + OUT_SIP5, + OUT_SIP6, + OUT_SIP7, + OUT_DIP0, + OUT_DIP1, + OUT_DIP2, + OUT_DIP3, + OUT_DIP4, + OUT_DIP5, /*30*/ + OUT_DIP6, + OUT_DIP7, + OUT_SESID, + OUT_PROT, + OUT_APP0, + OUT_APP1, + OUT_IGMP0, + OUT_IGMP1, + OUT_IPOFF, /*39*/ + OUT_NONE = 63, +}; + +/* parser's microcode length type */ +#define INSTR 0 +#define IPV6 1 +#define LENACCU 2 + +/* parser's microcode flag type */ +enum { + FLAG_ITAG = 0, + FLAG_VLAN, + FLAG_SNAP, + FLAG_PPPOE, + FLAG_IPV6, + FLAG_IPV6FL, + FLAG_IPV4, + FLAG_IGMP, + FLAG_TU, + FLAG_HOP, + FLAG_NN1, /*10 */ + FLAG_NN2, + FLAG_END, + FLAG_NO, /*13*/ +}; + +struct gswip_pce_microcode { + u16 val_3; + u16 val_2; + u16 val_1; + u16 val_0; +}; + +#define MC_ENTRY(val, msk, ns, out, len, type, flags, ipv4_len) \ + { val, msk, ((ns) << 10 | (out) << 4 | (len) >> 1),\ + ((len) & 1) << 15 | (type) << 13 | (flags) << 9 | (ipv4_len) << 8 } +static const struct gswip_pce_microcode gswip_pce_microcode[] = { + /* value mask ns fields L type flags ipv4_len */ + MC_ENTRY(0x88c3, 0xFFFF, 1, OUT_ITAG0, 4, INSTR, FLAG_ITAG, 0), + MC_ENTRY(0x8100, 0xFFFF, 2, OUT_VTAG0, 2, INSTR, FLAG_VLAN, 0), + MC_ENTRY(0x88A8, 0xFFFF, 1, OUT_VTAG0, 2, INSTR, FLAG_VLAN, 0), + MC_ENTRY(0x8100, 0xFFFF, 1, OUT_VTAG0, 2, INSTR, FLAG_VLAN, 0), + MC_ENTRY(0x8864, 0xFFFF, 17, OUT_ETHTYP, 1, INSTR, FLAG_NO, 0), + MC_ENTRY(0x0800, 0xFFFF, 21, OUT_ETHTYP, 1, INSTR, FLAG_NO, 0), + MC_ENTRY(0x86DD, 0xFFFF, 22, OUT_ETHTYP, 1, INSTR, FLAG_NO, 0), + MC_ENTRY(0x8863, 0xFFFF, 16, OUT_ETHTYP, 1, INSTR, FLAG_NO, 0), + MC_ENTRY(0x0000, 0xF800, 10, OUT_NONE, 0, INSTR, FLAG_NO, 0), + MC_ENTRY(0x0000, 0x0000, 40, OUT_ETHTYP, 1, INSTR, FLAG_NO, 0), + MC_ENTRY(0x0600, 0x0600, 40, OUT_ETHTYP, 1, INSTR, FLAG_NO, 0), + MC_ENTRY(0x0000, 0x0000, 12, OUT_NONE, 1, INSTR, FLAG_NO, 0), + MC_ENTRY(0xAAAA, 0xFFFF, 14, OUT_NONE, 1, INSTR, FLAG_NO, 0), + MC_ENTRY(0x0000, 0x0000, 41, OUT_NONE, 0, INSTR, FLAG_NO, 0), + MC_ENTRY(0x0300, 0xFF00, 41, OUT_NONE, 0, INSTR, FLAG_SNAP, 0), + MC_ENTRY(0x0000, 0x0000, 41, OUT_NONE, 0, INSTR, FLAG_NO, 0), + MC_ENTRY(0x0000, 0x0000, 41, OUT_DIP7, 3, INSTR, FLAG_NO, 0), + MC_ENTRY(0x0000, 0x0000, 18, OUT_DIP7, 3, INSTR, FLAG_PPPOE, 0), + MC_ENTRY(0x0021, 0xFFFF, 21, OUT_NONE, 1, INSTR, FLAG_NO, 0), + MC_ENTRY(0x0057, 0xFFFF, 22, OUT_NONE, 1, INSTR, FLAG_NO, 0), + MC_ENTRY(0x0000, 0x0000, 40, OUT_NONE, 0, INSTR, FLAG_NO, 0), + MC_ENTRY(0x4000, 0xF000, 24, OUT_IP0, 4, INSTR, FLAG_IPV4, 1), + MC_ENTRY(0x6000, 0xF000, 27, OUT_IP0, 3, INSTR, FLAG_IPV6, 0), + MC_ENTRY(0x0000, 0x0000, 41, OUT_NONE, 0, INSTR, FLAG_NO, 0), + MC_ENTRY(0x0000, 0x0000, 25, OUT_IP3, 2, INSTR, FLAG_NO, 0), + MC_ENTRY(0x0000, 0x0000, 26, OUT_SIP0, 4, INSTR, FLAG_NO, 0), + MC_ENTRY(0x0000, 0x0000, 40, OUT_NONE, 0, LENACCU, FLAG_NO, 0), + MC_ENTRY(0x1100, 0xFF00, 39, OUT_PROT, 1, INSTR, FLAG_NO, 0), + MC_ENTRY(0x0600, 0xFF00, 39, OUT_PROT, 1, INSTR, FLAG_NO, 0), + MC_ENTRY(0x0000, 0xFF00, 33, OUT_IP3, 17, INSTR, FLAG_HOP, 0), + MC_ENTRY(0x2B00, 0xFF00, 33, OUT_IP3, 17, INSTR, FLAG_NN1, 0), + MC_ENTRY(0x3C00, 0xFF00, 33, OUT_IP3, 17, INSTR, FLAG_NN2, 0), + MC_ENTRY(0x0000, 0x0000, 39, OUT_PROT, 1, INSTR, FLAG_NO, 0), + MC_ENTRY(0x0000, 0x00E0, 35, OUT_NONE, 0, INSTR, FLAG_NO, 0), + MC_ENTRY(0x0000, 0x0000, 40, OUT_NONE, 0, INSTR, FLAG_NO, 0), + MC_ENTRY(0x0000, 0xFF00, 33, OUT_NONE, 0, IPV6, FLAG_HOP, 0), + MC_ENTRY(0x2B00, 0xFF00, 33, OUT_NONE, 0, IPV6, FLAG_NN1, 0), + MC_ENTRY(0x3C00, 0xFF00, 33, OUT_NONE, 0, IPV6, FLAG_NN2, 0), + MC_ENTRY(0x0000, 0x0000, 40, OUT_PROT, 1, IPV6, FLAG_NO, 0), + MC_ENTRY(0x0000, 0x0000, 40, OUT_SIP0, 16, INSTR, FLAG_NO, 0), + MC_ENTRY(0x0000, 0x0000, 41, OUT_APP0, 4, INSTR, FLAG_IGMP, 0), + MC_ENTRY(0x0000, 0x0000, 41, OUT_NONE, 0, INSTR, FLAG_END, 0), + MC_ENTRY(0x0000, 0x0000, 41, OUT_NONE, 0, INSTR, FLAG_END, 0), + MC_ENTRY(0x0000, 0x0000, 41, OUT_NONE, 0, INSTR, FLAG_END, 0), + MC_ENTRY(0x0000, 0x0000, 41, OUT_NONE, 0, INSTR, FLAG_END, 0), + MC_ENTRY(0x0000, 0x0000, 41, OUT_NONE, 0, INSTR, FLAG_END, 0), + MC_ENTRY(0x0000, 0x0000, 41, OUT_NONE, 0, INSTR, FLAG_END, 0), + MC_ENTRY(0x0000, 0x0000, 41, OUT_NONE, 0, INSTR, FLAG_END, 0), + MC_ENTRY(0x0000, 0x0000, 41, OUT_NONE, 0, INSTR, FLAG_END, 0), + MC_ENTRY(0x0000, 0x0000, 41, OUT_NONE, 0, INSTR, FLAG_END, 0), + MC_ENTRY(0x0000, 0x0000, 41, OUT_NONE, 0, INSTR, FLAG_END, 0), + MC_ENTRY(0x0000, 0x0000, 41, OUT_NONE, 0, INSTR, FLAG_END, 0), + MC_ENTRY(0x0000, 0x0000, 41, OUT_NONE, 0, INSTR, FLAG_END, 0), + MC_ENTRY(0x0000, 0x0000, 41, OUT_NONE, 0, INSTR, FLAG_END, 0), + MC_ENTRY(0x0000, 0x0000, 41, OUT_NONE, 0, INSTR, FLAG_END, 0), + MC_ENTRY(0x0000, 0x0000, 41, OUT_NONE, 0, INSTR, FLAG_END, 0), + MC_ENTRY(0x0000, 0x0000, 41, OUT_NONE, 0, INSTR, FLAG_END, 0), + MC_ENTRY(0x0000, 0x0000, 41, OUT_NONE, 0, INSTR, FLAG_END, 0), + MC_ENTRY(0x0000, 0x0000, 41, OUT_NONE, 0, INSTR, FLAG_END, 0), + MC_ENTRY(0x0000, 0x0000, 41, OUT_NONE, 0, INSTR, FLAG_END, 0), + MC_ENTRY(0x0000, 0x0000, 41, OUT_NONE, 0, INSTR, FLAG_END, 0), + MC_ENTRY(0x0000, 0x0000, 41, OUT_NONE, 0, INSTR, FLAG_END, 0), + MC_ENTRY(0x0000, 0x0000, 41, OUT_NONE, 0, INSTR, FLAG_END, 0), + MC_ENTRY(0x0000, 0x0000, 41, OUT_NONE, 0, INSTR, FLAG_END, 0), +}; diff --git a/drivers/net/dsa/mv88e6xxx/chip.c b/drivers/net/dsa/mv88e6xxx/chip.c index e07838430d16..78ce820b5257 100644 --- a/drivers/net/dsa/mv88e6xxx/chip.c +++ b/drivers/net/dsa/mv88e6xxx/chip.c @@ -575,6 +575,13 @@ restore_link: return err; } +static int mv88e6xxx_phy_is_internal(struct dsa_switch *ds, int port) +{ + struct mv88e6xxx_chip *chip = ds->priv; + + return port < chip->info->num_internal_phys; +} + /* We expect the switch to perform auto negotiation if there is a real * phy. However, in the case of a fixed link phy, we force the port * settings from the fixed link settings. @@ -585,7 +592,8 @@ static void mv88e6xxx_adjust_link(struct dsa_switch *ds, int port, struct mv88e6xxx_chip *chip = ds->priv; int err; - if (!phy_is_pseudo_fixed_link(phydev)) + if (!phy_is_pseudo_fixed_link(phydev) && + mv88e6xxx_phy_is_internal(ds, port)) return; mutex_lock(&chip->reg_lock); @@ -709,13 +717,17 @@ static void mv88e6xxx_mac_config(struct dsa_switch *ds, int port, struct mv88e6xxx_chip *chip = ds->priv; int speed, duplex, link, pause, err; - if (mode == MLO_AN_PHY) + if ((mode == MLO_AN_PHY) && mv88e6xxx_phy_is_internal(ds, port)) return; if (mode == MLO_AN_FIXED) { link = LINK_FORCED_UP; speed = state->speed; duplex = state->duplex; + } else if (!mv88e6xxx_phy_is_internal(ds, port)) { + link = state->link; + speed = state->speed; + duplex = state->duplex; } else { speed = SPEED_UNFORCED; duplex = DUPLEX_UNFORCED; diff --git a/drivers/net/dsa/mv88e6xxx/global1.h b/drivers/net/dsa/mv88e6xxx/global1.h index 7c791c1da4b9..bef01331266f 100644 --- a/drivers/net/dsa/mv88e6xxx/global1.h +++ b/drivers/net/dsa/mv88e6xxx/global1.h @@ -128,7 +128,7 @@ #define MV88E6XXX_G1_ATU_OP_GET_CLR_VIOLATION 0x7000 #define MV88E6XXX_G1_ATU_OP_AGE_OUT_VIOLATION BIT(7) #define MV88E6XXX_G1_ATU_OP_MEMBER_VIOLATION BIT(6) -#define MV88E6XXX_G1_ATU_OP_MISS_VIOLTATION BIT(5) +#define MV88E6XXX_G1_ATU_OP_MISS_VIOLATION BIT(5) #define MV88E6XXX_G1_ATU_OP_FULL_VIOLATION BIT(4) /* Offset 0x0C: ATU Data Register */ diff --git a/drivers/net/dsa/mv88e6xxx/global1_atu.c b/drivers/net/dsa/mv88e6xxx/global1_atu.c index 307410898fc9..5200e4bdce93 100644 --- a/drivers/net/dsa/mv88e6xxx/global1_atu.c +++ b/drivers/net/dsa/mv88e6xxx/global1_atu.c @@ -349,7 +349,7 @@ static irqreturn_t mv88e6xxx_g1_atu_prob_irq_thread_fn(int irq, void *dev_id) chip->ports[entry.portvec].atu_member_violation++; } - if (val & MV88E6XXX_G1_ATU_OP_MEMBER_VIOLATION) { + if (val & MV88E6XXX_G1_ATU_OP_MISS_VIOLATION) { dev_err_ratelimited(chip->dev, "ATU miss violation for %pM portvec %x\n", entry.mac, entry.portvec); diff --git a/drivers/net/ethernet/8390/ax88796.c b/drivers/net/ethernet/8390/ax88796.c index 2a0ddec1dd56..3dcc61821ed5 100644 --- a/drivers/net/ethernet/8390/ax88796.c +++ b/drivers/net/ethernet/8390/ax88796.c @@ -377,9 +377,7 @@ static int ax_mii_probe(struct net_device *dev) return ret; } - /* mask with MAC supported features */ - phy_dev->supported &= PHY_BASIC_FEATURES; - phy_dev->advertising = phy_dev->supported; + phy_set_max_speed(phy_dev, SPEED_100); netdev_info(dev, "PHY driver [%s] (mii_bus:phy_addr=%s, irq=%d)\n", phy_dev->drv->name, phydev_name(phy_dev), phy_dev->irq); diff --git a/drivers/net/ethernet/Kconfig b/drivers/net/ethernet/Kconfig index 6fde68aa13a4..885e00d17807 100644 --- a/drivers/net/ethernet/Kconfig +++ b/drivers/net/ethernet/Kconfig @@ -108,6 +108,13 @@ config LANTIQ_ETOP ---help--- Support for the MII0 inside the Lantiq SoC +config LANTIQ_XRX200 + tristate "Lantiq / Intel xRX200 PMAC network driver" + depends on SOC_TYPE_XWAY + ---help--- + Support for the PMAC of the Gigabit switch (GSWIP) inside the + Lantiq / Intel VRX200 VDSL SoC + source "drivers/net/ethernet/marvell/Kconfig" source "drivers/net/ethernet/mediatek/Kconfig" source "drivers/net/ethernet/mellanox/Kconfig" diff --git a/drivers/net/ethernet/Makefile b/drivers/net/ethernet/Makefile index b45d5f626b59..7b5bf9682066 100644 --- a/drivers/net/ethernet/Makefile +++ b/drivers/net/ethernet/Makefile @@ -49,6 +49,7 @@ obj-$(CONFIG_NET_VENDOR_XSCALE) += xscale/ obj-$(CONFIG_JME) += jme.o obj-$(CONFIG_KORINA) += korina.o obj-$(CONFIG_LANTIQ_ETOP) += lantiq_etop.o +obj-$(CONFIG_LANTIQ_XRX200) += lantiq_xrx200.o obj-$(CONFIG_NET_VENDOR_MARVELL) += marvell/ obj-$(CONFIG_NET_VENDOR_MEDIATEK) += mediatek/ obj-$(CONFIG_NET_VENDOR_MELLANOX) += mellanox/ diff --git a/drivers/net/ethernet/aeroflex/greth.c b/drivers/net/ethernet/aeroflex/greth.c index 4309be3724ad..7c9348a26cbb 100644 --- a/drivers/net/ethernet/aeroflex/greth.c +++ b/drivers/net/ethernet/aeroflex/greth.c @@ -1279,9 +1279,9 @@ static int greth_mdio_probe(struct net_device *dev) } if (greth->gbit_mac) - phy->supported &= PHY_GBIT_FEATURES; + phy_set_max_speed(phy, SPEED_1000); else - phy->supported &= PHY_BASIC_FEATURES; + phy_set_max_speed(phy, SPEED_100); phy->advertising = phy->supported; diff --git a/drivers/net/ethernet/agere/et131x.c b/drivers/net/ethernet/agere/et131x.c index 48220b6c600d..ea34bcb868b5 100644 --- a/drivers/net/ethernet/agere/et131x.c +++ b/drivers/net/ethernet/agere/et131x.c @@ -3258,19 +3258,11 @@ static int et131x_mii_probe(struct net_device *netdev) return PTR_ERR(phydev); } - phydev->supported &= (SUPPORTED_10baseT_Half | - SUPPORTED_10baseT_Full | - SUPPORTED_100baseT_Half | - SUPPORTED_100baseT_Full | - SUPPORTED_Autoneg | - SUPPORTED_MII | - SUPPORTED_TP); + phy_set_max_speed(phydev, SPEED_100); if (adapter->pdev->device != ET131X_PCI_DEVICE_ID_FAST) - phydev->supported |= SUPPORTED_1000baseT_Half | - SUPPORTED_1000baseT_Full; + phy_set_max_speed(phydev, SPEED_1000); - phydev->advertising = phydev->supported; phydev->autoneg = AUTONEG_ENABLE; phy_attached_info(phydev); diff --git a/drivers/net/ethernet/alacritech/slic.h b/drivers/net/ethernet/alacritech/slic.h index d0c388cfd52f..3add305d34b4 100644 --- a/drivers/net/ethernet/alacritech/slic.h +++ b/drivers/net/ethernet/alacritech/slic.h @@ -8,7 +8,6 @@ #include <linux/spinlock_types.h> #include <linux/dma-mapping.h> #include <linux/pci.h> -#include <linux/netdevice.h> #include <linux/list.h> #include <linux/u64_stats_sync.h> diff --git a/drivers/net/ethernet/allwinner/sun4i-emac.c b/drivers/net/ethernet/allwinner/sun4i-emac.c index 3143de45baaa..e1acafa82214 100644 --- a/drivers/net/ethernet/allwinner/sun4i-emac.c +++ b/drivers/net/ethernet/allwinner/sun4i-emac.c @@ -172,8 +172,7 @@ static int emac_mdio_probe(struct net_device *dev) } /* mask with MAC supported features */ - phydev->supported &= PHY_BASIC_FEATURES; - phydev->advertising = phydev->supported; + phy_set_max_speed(phydev, SPEED_100); db->link = 0; db->speed = 0; diff --git a/drivers/net/ethernet/altera/altera_tse_main.c b/drivers/net/ethernet/altera/altera_tse_main.c index baca8f704a45..02921d877c08 100644 --- a/drivers/net/ethernet/altera/altera_tse_main.c +++ b/drivers/net/ethernet/altera/altera_tse_main.c @@ -835,13 +835,10 @@ static int init_phy(struct net_device *dev) } /* Stop Advertising 1000BASE Capability if interface is not GMII - * Note: Checkpatch throws CHECKs for the camel case defines below, - * it's ok to ignore. */ if ((priv->phy_iface == PHY_INTERFACE_MODE_MII) || (priv->phy_iface == PHY_INTERFACE_MODE_RMII)) - phydev->advertising &= ~(SUPPORTED_1000baseT_Half | - SUPPORTED_1000baseT_Full); + phy_set_max_speed(phydev, SPEED_100); /* Broken HW is sometimes missing the pull-up resistor on the * MDIO line, which results in reads to non-existent devices returning diff --git a/drivers/net/ethernet/amazon/ena/ena_com.c b/drivers/net/ethernet/amazon/ena/ena_com.c index 17f12c18d225..7635c38e77dd 100644 --- a/drivers/net/ethernet/amazon/ena/ena_com.c +++ b/drivers/net/ethernet/amazon/ena/ena_com.c @@ -459,12 +459,12 @@ static void ena_com_handle_admin_completion(struct ena_com_admin_queue *admin_qu cqe = &admin_queue->cq.entries[head_masked]; /* Go over all the completions */ - while ((cqe->acq_common_descriptor.flags & + while ((READ_ONCE(cqe->acq_common_descriptor.flags) & ENA_ADMIN_ACQ_COMMON_DESC_PHASE_MASK) == phase) { /* Do not read the rest of the completion entry before the * phase bit was validated */ - rmb(); + dma_rmb(); ena_com_handle_single_admin_completion(admin_queue, cqe); head_masked++; @@ -627,17 +627,10 @@ static u32 ena_com_reg_bar_read32(struct ena_com_dev *ena_dev, u16 offset) mmio_read_reg |= mmio_read->seq_num & ENA_REGS_MMIO_REG_READ_REQ_ID_MASK; - /* make sure read_resp->req_id get updated before the hw can write - * there - */ - wmb(); - - writel_relaxed(mmio_read_reg, - ena_dev->reg_bar + ENA_REGS_MMIO_REG_READ_OFF); + writel(mmio_read_reg, ena_dev->reg_bar + ENA_REGS_MMIO_REG_READ_OFF); - mmiowb(); for (i = 0; i < timeout; i++) { - if (read_resp->req_id == mmio_read->seq_num) + if (READ_ONCE(read_resp->req_id) == mmio_read->seq_num) break; udelay(1); @@ -1796,8 +1789,13 @@ void ena_com_aenq_intr_handler(struct ena_com_dev *dev, void *data) aenq_common = &aenq_e->aenq_common_desc; /* Go over all the events */ - while ((aenq_common->flags & ENA_ADMIN_AENQ_COMMON_DESC_PHASE_MASK) == - phase) { + while ((READ_ONCE(aenq_common->flags) & + ENA_ADMIN_AENQ_COMMON_DESC_PHASE_MASK) == phase) { + /* Make sure the phase bit (ownership) is as expected before + * reading the rest of the descriptor. + */ + dma_rmb(); + pr_debug("AENQ! Group[%x] Syndrom[%x] timestamp: [%llus]\n", aenq_common->group, aenq_common->syndrom, (u64)aenq_common->timestamp_low + diff --git a/drivers/net/ethernet/amazon/ena/ena_eth_com.c b/drivers/net/ethernet/amazon/ena/ena_eth_com.c index ea149c134e15..1c682b76190f 100644 --- a/drivers/net/ethernet/amazon/ena/ena_eth_com.c +++ b/drivers/net/ethernet/amazon/ena/ena_eth_com.c @@ -51,6 +51,11 @@ static inline struct ena_eth_io_rx_cdesc_base *ena_com_get_next_rx_cdesc( if (desc_phase != expected_phase) return NULL; + /* Make sure we read the rest of the descriptor after the phase bit + * has been read + */ + dma_rmb(); + return cdesc; } @@ -493,6 +498,7 @@ int ena_com_tx_comp_req_id_get(struct ena_com_io_cq *io_cq, u16 *req_id) if (cdesc_phase != expected_phase) return -EAGAIN; + dma_rmb(); if (unlikely(cdesc->req_id >= io_cq->q_depth)) { pr_err("Invalid req id %d\n", cdesc->req_id); return -EINVAL; diff --git a/drivers/net/ethernet/amazon/ena/ena_eth_com.h b/drivers/net/ethernet/amazon/ena/ena_eth_com.h index 6fdc753d9483..2f7657227cfe 100644 --- a/drivers/net/ethernet/amazon/ena/ena_eth_com.h +++ b/drivers/net/ethernet/amazon/ena/ena_eth_com.h @@ -107,8 +107,7 @@ static inline int ena_com_sq_empty_space(struct ena_com_io_sq *io_sq) return io_sq->q_depth - 1 - cnt; } -static inline int ena_com_write_sq_doorbell(struct ena_com_io_sq *io_sq, - bool relaxed) +static inline int ena_com_write_sq_doorbell(struct ena_com_io_sq *io_sq) { u16 tail; @@ -117,10 +116,7 @@ static inline int ena_com_write_sq_doorbell(struct ena_com_io_sq *io_sq, pr_debug("write submission queue doorbell for queue: %d tail: %d\n", io_sq->qid, tail); - if (relaxed) - writel_relaxed(tail, io_sq->db_addr); - else - writel(tail, io_sq->db_addr); + writel(tail, io_sq->db_addr); return 0; } diff --git a/drivers/net/ethernet/amazon/ena/ena_netdev.c b/drivers/net/ethernet/amazon/ena/ena_netdev.c index c673ac2df65b..b2522e84f482 100644 --- a/drivers/net/ethernet/amazon/ena/ena_netdev.c +++ b/drivers/net/ethernet/amazon/ena/ena_netdev.c @@ -39,7 +39,6 @@ #include <linux/if_vlan.h> #include <linux/kernel.h> #include <linux/module.h> -#include <linux/moduleparam.h> #include <linux/numa.h> #include <linux/pci.h> #include <linux/utsname.h> @@ -76,7 +75,7 @@ MODULE_DEVICE_TABLE(pci, ena_pci_tbl); static int ena_rss_init_default(struct ena_adapter *adapter); static void check_for_admin_com_state(struct ena_adapter *adapter); -static void ena_destroy_device(struct ena_adapter *adapter); +static void ena_destroy_device(struct ena_adapter *adapter, bool graceful); static int ena_restore_device(struct ena_adapter *adapter); static void ena_tx_timeout(struct net_device *dev) @@ -461,7 +460,7 @@ static inline int ena_alloc_rx_page(struct ena_ring *rx_ring, return -ENOMEM; } - dma = dma_map_page(rx_ring->dev, page, 0, PAGE_SIZE, + dma = dma_map_page(rx_ring->dev, page, 0, ENA_PAGE_SIZE, DMA_FROM_DEVICE); if (unlikely(dma_mapping_error(rx_ring->dev, dma))) { u64_stats_update_begin(&rx_ring->syncp); @@ -478,7 +477,7 @@ static inline int ena_alloc_rx_page(struct ena_ring *rx_ring, rx_info->page_offset = 0; ena_buf = &rx_info->ena_buf; ena_buf->paddr = dma; - ena_buf->len = PAGE_SIZE; + ena_buf->len = ENA_PAGE_SIZE; return 0; } @@ -495,7 +494,7 @@ static void ena_free_rx_page(struct ena_ring *rx_ring, return; } - dma_unmap_page(rx_ring->dev, ena_buf->paddr, PAGE_SIZE, + dma_unmap_page(rx_ring->dev, ena_buf->paddr, ENA_PAGE_SIZE, DMA_FROM_DEVICE); __free_page(page); @@ -551,14 +550,9 @@ static int ena_refill_rx_bufs(struct ena_ring *rx_ring, u32 num) rx_ring->qid, i, num); } - if (likely(i)) { - /* Add memory barrier to make sure the desc were written before - * issue a doorbell - */ - wmb(); - ena_com_write_sq_doorbell(rx_ring->ena_com_io_sq, true); - mmiowb(); - } + /* ena_com_write_sq_doorbell issues a wmb() */ + if (likely(i)) + ena_com_write_sq_doorbell(rx_ring->ena_com_io_sq); rx_ring->next_to_use = next_to_use; @@ -916,10 +910,10 @@ static struct sk_buff *ena_rx_skb(struct ena_ring *rx_ring, do { dma_unmap_page(rx_ring->dev, dma_unmap_addr(&rx_info->ena_buf, paddr), - PAGE_SIZE, DMA_FROM_DEVICE); + ENA_PAGE_SIZE, DMA_FROM_DEVICE); skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags, rx_info->page, - rx_info->page_offset, len, PAGE_SIZE); + rx_info->page_offset, len, ENA_PAGE_SIZE); netif_dbg(rx_ring->adapter, rx_status, rx_ring->netdev, "rx skb updated. len %d. data_len %d\n", @@ -1900,7 +1894,7 @@ static int ena_close(struct net_device *netdev) "Destroy failure, restarting device\n"); ena_dump_stats_to_dmesg(adapter); /* rtnl lock already obtained in dev_ioctl() layer */ - ena_destroy_device(adapter); + ena_destroy_device(adapter, false); ena_restore_device(adapter); } @@ -2112,12 +2106,6 @@ static netdev_tx_t ena_start_xmit(struct sk_buff *skb, struct net_device *dev) tx_ring->next_to_use = ENA_TX_RING_IDX_NEXT(next_to_use, tx_ring->ring_size); - /* This WMB is aimed to: - * 1 - perform smp barrier before reading next_to_completion - * 2 - make sure the desc were written before trigger DB - */ - wmb(); - /* stop the queue when no more space available, the packet can have up * to sgl_size + 2. one for the meta descriptor and one for header * (if the header is larger than tx_max_header_size). @@ -2136,10 +2124,11 @@ static netdev_tx_t ena_start_xmit(struct sk_buff *skb, struct net_device *dev) * stop the queue but meanwhile clean_tx_irq updates * next_to_completion and terminates. * The queue will remain stopped forever. - * To solve this issue this function perform rmb, check - * the wakeup condition and wake up the queue if needed. + * To solve this issue add a mb() to make sure that + * netif_tx_stop_queue() write is vissible before checking if + * there is additional space in the queue. */ - smp_rmb(); + smp_mb(); if (ena_com_sq_empty_space(tx_ring->ena_com_io_sq) > ENA_TX_WAKEUP_THRESH) { @@ -2151,8 +2140,10 @@ static netdev_tx_t ena_start_xmit(struct sk_buff *skb, struct net_device *dev) } if (netif_xmit_stopped(txq) || !skb->xmit_more) { - /* trigger the dma engine */ - ena_com_write_sq_doorbell(tx_ring->ena_com_io_sq, false); + /* trigger the dma engine. ena_com_write_sq_doorbell() + * has a mb + */ + ena_com_write_sq_doorbell(tx_ring->ena_com_io_sq); u64_stats_update_begin(&tx_ring->syncp); tx_ring->tx_stats.doorbells++; u64_stats_update_end(&tx_ring->syncp); @@ -2550,12 +2541,15 @@ err_disable_msix: return rc; } -static void ena_destroy_device(struct ena_adapter *adapter) +static void ena_destroy_device(struct ena_adapter *adapter, bool graceful) { struct net_device *netdev = adapter->netdev; struct ena_com_dev *ena_dev = adapter->ena_dev; bool dev_up; + if (!test_bit(ENA_FLAG_DEVICE_RUNNING, &adapter->flags)) + return; + netif_carrier_off(netdev); del_timer_sync(&adapter->timer_service); @@ -2563,7 +2557,8 @@ static void ena_destroy_device(struct ena_adapter *adapter) dev_up = test_bit(ENA_FLAG_DEV_UP, &adapter->flags); adapter->dev_up_before_reset = dev_up; - ena_com_set_admin_running_state(ena_dev, false); + if (!graceful) + ena_com_set_admin_running_state(ena_dev, false); if (test_bit(ENA_FLAG_DEV_UP, &adapter->flags)) ena_down(adapter); @@ -2591,6 +2586,7 @@ static void ena_destroy_device(struct ena_adapter *adapter) adapter->reset_reason = ENA_REGS_RESET_NORMAL; clear_bit(ENA_FLAG_TRIGGER_RESET, &adapter->flags); + clear_bit(ENA_FLAG_DEVICE_RUNNING, &adapter->flags); } static int ena_restore_device(struct ena_adapter *adapter) @@ -2635,6 +2631,7 @@ static int ena_restore_device(struct ena_adapter *adapter) } } + set_bit(ENA_FLAG_DEVICE_RUNNING, &adapter->flags); mod_timer(&adapter->timer_service, round_jiffies(jiffies + HZ)); dev_err(&pdev->dev, "Device reset completed successfully\n"); @@ -2665,7 +2662,7 @@ static void ena_fw_reset_device(struct work_struct *work) return; } rtnl_lock(); - ena_destroy_device(adapter); + ena_destroy_device(adapter, false); ena_restore_device(adapter); rtnl_unlock(); } @@ -3409,30 +3406,24 @@ static void ena_remove(struct pci_dev *pdev) netdev->rx_cpu_rmap = NULL; } #endif /* CONFIG_RFS_ACCEL */ - - unregister_netdev(netdev); del_timer_sync(&adapter->timer_service); cancel_work_sync(&adapter->reset_task); - /* Reset the device only if the device is running. */ - if (test_bit(ENA_FLAG_DEVICE_RUNNING, &adapter->flags)) - ena_com_dev_reset(ena_dev, adapter->reset_reason); + unregister_netdev(netdev); - ena_free_mgmnt_irq(adapter); + /* If the device is running then we want to make sure the device will be + * reset to make sure no more events will be issued by the device. + */ + if (test_bit(ENA_FLAG_DEVICE_RUNNING, &adapter->flags)) + set_bit(ENA_FLAG_TRIGGER_RESET, &adapter->flags); - ena_disable_msix(adapter); + rtnl_lock(); + ena_destroy_device(adapter, true); + rtnl_unlock(); free_netdev(netdev); - ena_com_mmio_reg_read_request_destroy(ena_dev); - - ena_com_abort_admin_commands(ena_dev); - - ena_com_wait_for_abort_completion(ena_dev); - - ena_com_admin_destroy(ena_dev); - ena_com_rss_destroy(ena_dev); ena_com_delete_debug_area(ena_dev); @@ -3467,7 +3458,7 @@ static int ena_suspend(struct pci_dev *pdev, pm_message_t state) "ignoring device reset request as the device is being suspended\n"); clear_bit(ENA_FLAG_TRIGGER_RESET, &adapter->flags); } - ena_destroy_device(adapter); + ena_destroy_device(adapter, true); rtnl_unlock(); return 0; } diff --git a/drivers/net/ethernet/amazon/ena/ena_netdev.h b/drivers/net/ethernet/amazon/ena/ena_netdev.h index f1972b5ab650..7c7ae56c52cf 100644 --- a/drivers/net/ethernet/amazon/ena/ena_netdev.h +++ b/drivers/net/ethernet/amazon/ena/ena_netdev.h @@ -355,4 +355,15 @@ void ena_dump_stats_to_buf(struct ena_adapter *adapter, u8 *buf); int ena_get_sset_count(struct net_device *netdev, int sset); +/* The ENA buffer length fields is 16 bit long. So when PAGE_SIZE == 64kB the + * driver passas 0. + * Since the max packet size the ENA handles is ~9kB limit the buffer length to + * 16kB. + */ +#if PAGE_SIZE > SZ_16K +#define ENA_PAGE_SIZE SZ_16K +#else +#define ENA_PAGE_SIZE PAGE_SIZE +#endif + #endif /* !(ENA_H) */ diff --git a/drivers/net/ethernet/amd/am79c961a.c b/drivers/net/ethernet/amd/am79c961a.c index 01d132c02ff9..265039c57023 100644 --- a/drivers/net/ethernet/amd/am79c961a.c +++ b/drivers/net/ethernet/amd/am79c961a.c @@ -440,7 +440,7 @@ static void am79c961_timeout(struct net_device *dev) /* * Transmit a packet */ -static int +static netdev_tx_t am79c961_sendpacket(struct sk_buff *skb, struct net_device *dev) { struct dev_priv *priv = netdev_priv(dev); diff --git a/drivers/net/ethernet/amd/atarilance.c b/drivers/net/ethernet/amd/atarilance.c index c5b81268c284..d3d44e07afbc 100644 --- a/drivers/net/ethernet/amd/atarilance.c +++ b/drivers/net/ethernet/amd/atarilance.c @@ -339,7 +339,8 @@ static unsigned long lance_probe1( struct net_device *dev, struct lance_addr *init_rec ); static int lance_open( struct net_device *dev ); static void lance_init_ring( struct net_device *dev ); -static int lance_start_xmit( struct sk_buff *skb, struct net_device *dev ); +static netdev_tx_t lance_start_xmit(struct sk_buff *skb, + struct net_device *dev); static irqreturn_t lance_interrupt( int irq, void *dev_id ); static int lance_rx( struct net_device *dev ); static int lance_close( struct net_device *dev ); @@ -769,7 +770,8 @@ static void lance_tx_timeout (struct net_device *dev) /* XXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXX */ -static int lance_start_xmit( struct sk_buff *skb, struct net_device *dev ) +static netdev_tx_t +lance_start_xmit(struct sk_buff *skb, struct net_device *dev) { struct lance_private *lp = netdev_priv(dev); struct lance_ioreg *IO = lp->iobase; diff --git a/drivers/net/ethernet/amd/au1000_eth.c b/drivers/net/ethernet/amd/au1000_eth.c index 73ca8879ada7..7c1eb304c27e 100644 --- a/drivers/net/ethernet/amd/au1000_eth.c +++ b/drivers/net/ethernet/amd/au1000_eth.c @@ -564,17 +564,7 @@ static int au1000_mii_probe(struct net_device *dev) return PTR_ERR(phydev); } - /* mask with MAC supported features */ - phydev->supported &= (SUPPORTED_10baseT_Half - | SUPPORTED_10baseT_Full - | SUPPORTED_100baseT_Half - | SUPPORTED_100baseT_Full - | SUPPORTED_Autoneg - /* | SUPPORTED_Pause | SUPPORTED_Asym_Pause */ - | SUPPORTED_MII - | SUPPORTED_TP); - - phydev->advertising = phydev->supported; + phy_set_max_speed(phydev, SPEED_100); aup->old_link = 0; aup->old_speed = 0; diff --git a/drivers/net/ethernet/amd/declance.c b/drivers/net/ethernet/amd/declance.c index 116997a8b593..29ebbf582010 100644 --- a/drivers/net/ethernet/amd/declance.c +++ b/drivers/net/ethernet/amd/declance.c @@ -894,7 +894,7 @@ static void lance_tx_timeout(struct net_device *dev) netif_wake_queue(dev); } -static int lance_start_xmit(struct sk_buff *skb, struct net_device *dev) +static netdev_tx_t lance_start_xmit(struct sk_buff *skb, struct net_device *dev) { struct lance_private *lp = netdev_priv(dev); volatile struct lance_regs *ll = lp->ll; diff --git a/drivers/net/ethernet/amd/ni65.c b/drivers/net/ethernet/amd/ni65.c index e248d1ab3e47..8931ce6bab7b 100644 --- a/drivers/net/ethernet/amd/ni65.c +++ b/drivers/net/ethernet/amd/ni65.c @@ -435,10 +435,8 @@ static int __init ni65_probe1(struct net_device *dev,int ioaddr) } if(cards[i].vendor_id) { for(j=0;j<3;j++) - if(inb(ioaddr+cards[i].addr_offset+j) != cards[i].vendor_id[j]) { + if(inb(ioaddr+cards[i].addr_offset+j) != cards[i].vendor_id[j]) release_region(ioaddr, cards[i].total_size); - continue; - } } break; } diff --git a/drivers/net/ethernet/amd/sun3lance.c b/drivers/net/ethernet/amd/sun3lance.c index 77b1db267730..da7e3d4f4166 100644 --- a/drivers/net/ethernet/amd/sun3lance.c +++ b/drivers/net/ethernet/amd/sun3lance.c @@ -236,7 +236,8 @@ struct lance_private { static int lance_probe( struct net_device *dev); static int lance_open( struct net_device *dev ); static void lance_init_ring( struct net_device *dev ); -static int lance_start_xmit( struct sk_buff *skb, struct net_device *dev ); +static netdev_tx_t lance_start_xmit(struct sk_buff *skb, + struct net_device *dev); static irqreturn_t lance_interrupt( int irq, void *dev_id); static int lance_rx( struct net_device *dev ); static int lance_close( struct net_device *dev ); @@ -511,7 +512,8 @@ static void lance_init_ring( struct net_device *dev ) } -static int lance_start_xmit( struct sk_buff *skb, struct net_device *dev ) +static netdev_tx_t +lance_start_xmit(struct sk_buff *skb, struct net_device *dev) { struct lance_private *lp = netdev_priv(dev); int entry, len; diff --git a/drivers/net/ethernet/amd/sunlance.c b/drivers/net/ethernet/amd/sunlance.c index cdd7a611479b..b4fc0ed5bce8 100644 --- a/drivers/net/ethernet/amd/sunlance.c +++ b/drivers/net/ethernet/amd/sunlance.c @@ -1106,7 +1106,7 @@ static void lance_tx_timeout(struct net_device *dev) netif_wake_queue(dev); } -static int lance_start_xmit(struct sk_buff *skb, struct net_device *dev) +static netdev_tx_t lance_start_xmit(struct sk_buff *skb, struct net_device *dev) { struct lance_private *lp = netdev_priv(dev); int entry, skblen, len; diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-drv.c b/drivers/net/ethernet/amd/xgbe/xgbe-drv.c index 24f1053b8785..d96a84a62d78 100644 --- a/drivers/net/ethernet/amd/xgbe/xgbe-drv.c +++ b/drivers/net/ethernet/amd/xgbe/xgbe-drv.c @@ -2009,7 +2009,7 @@ static int xgbe_close(struct net_device *netdev) return 0; } -static int xgbe_xmit(struct sk_buff *skb, struct net_device *netdev) +static netdev_tx_t xgbe_xmit(struct sk_buff *skb, struct net_device *netdev) { struct xgbe_prv_data *pdata = netdev_priv(netdev); struct xgbe_hw_if *hw_if = &pdata->hw_if; @@ -2018,7 +2018,7 @@ static int xgbe_xmit(struct sk_buff *skb, struct net_device *netdev) struct xgbe_ring *ring; struct xgbe_packet_data *packet; struct netdev_queue *txq; - int ret; + netdev_tx_t ret; DBGPR("-->xgbe_xmit: skb->len = %d\n", skb->len); diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-phy-v2.c b/drivers/net/ethernet/amd/xgbe/xgbe-phy-v2.c index 3ceb4f95ca7c..289129011b9f 100644 --- a/drivers/net/ethernet/amd/xgbe/xgbe-phy-v2.c +++ b/drivers/net/ethernet/amd/xgbe/xgbe-phy-v2.c @@ -879,8 +879,8 @@ static bool xgbe_phy_finisar_phy_quirks(struct xgbe_prv_data *pdata) phy_write(phy_data->phydev, 0x00, 0x9140); phy_data->phydev->supported = PHY_GBIT_FEATURES; - phy_data->phydev->supported |= SUPPORTED_Pause | SUPPORTED_Asym_Pause; phy_data->phydev->advertising = phy_data->phydev->supported; + phy_support_asym_pause(phy_data->phydev); netif_dbg(pdata, drv, pdata->netdev, "Finisar PHY quirk in place\n"); @@ -951,8 +951,8 @@ static bool xgbe_phy_belfuse_phy_quirks(struct xgbe_prv_data *pdata) phy_write(phy_data->phydev, 0x00, reg & ~0x00800); phy_data->phydev->supported = PHY_GBIT_FEATURES; - phy_data->phydev->supported |= SUPPORTED_Pause | SUPPORTED_Asym_Pause; phy_data->phydev->advertising = phy_data->phydev->supported; + phy_support_asym_pause(phy_data->phydev); netif_dbg(pdata, drv, pdata->netdev, "BelFuse PHY quirk in place\n"); diff --git a/drivers/net/ethernet/apm/xgene/xgene_enet_ethtool.c b/drivers/net/ethernet/apm/xgene/xgene_enet_ethtool.c index 4f50f11718f4..78dd09b5beeb 100644 --- a/drivers/net/ethernet/apm/xgene/xgene_enet_ethtool.c +++ b/drivers/net/ethernet/apm/xgene/xgene_enet_ethtool.c @@ -306,45 +306,25 @@ static int xgene_set_pauseparam(struct net_device *ndev, { struct xgene_enet_pdata *pdata = netdev_priv(ndev); struct phy_device *phydev = ndev->phydev; - u32 oldadv, newadv; if (phy_interface_mode_is_rgmii(pdata->phy_mode) || pdata->phy_mode == PHY_INTERFACE_MODE_SGMII) { if (!phydev) return -EINVAL; - if (!(phydev->supported & SUPPORTED_Pause) || - (!(phydev->supported & SUPPORTED_Asym_Pause) && - pp->rx_pause != pp->tx_pause)) + if (!phy_validate_pause(phydev, pp)) return -EINVAL; pdata->pause_autoneg = pp->autoneg; pdata->tx_pause = pp->tx_pause; pdata->rx_pause = pp->rx_pause; - oldadv = phydev->advertising; - newadv = oldadv & ~(ADVERTISED_Pause | ADVERTISED_Asym_Pause); + phy_set_asym_pause(phydev, pp->rx_pause, pp->tx_pause); - if (pp->rx_pause) - newadv |= ADVERTISED_Pause | ADVERTISED_Asym_Pause; - - if (pp->tx_pause) - newadv ^= ADVERTISED_Asym_Pause; - - if (oldadv ^ newadv) { - phydev->advertising = newadv; - - if (phydev->autoneg) - return phy_start_aneg(phydev); - - if (!pp->autoneg) { - pdata->mac_ops->flowctl_tx(pdata, - pdata->tx_pause); - pdata->mac_ops->flowctl_rx(pdata, - pdata->rx_pause); - } + if (!pp->autoneg) { + pdata->mac_ops->flowctl_tx(pdata, pdata->tx_pause); + pdata->mac_ops->flowctl_rx(pdata, pdata->rx_pause); } - } else { if (pp->autoneg) return -EINVAL; diff --git a/drivers/net/ethernet/apm/xgene/xgene_enet_hw.c b/drivers/net/ethernet/apm/xgene/xgene_enet_hw.c index 078a04dc1182..e3560311711a 100644 --- a/drivers/net/ethernet/apm/xgene/xgene_enet_hw.c +++ b/drivers/net/ethernet/apm/xgene/xgene_enet_hw.c @@ -895,12 +895,10 @@ int xgene_enet_phy_connect(struct net_device *ndev) } pdata->phy_speed = SPEED_UNKNOWN; - phy_dev->supported &= ~SUPPORTED_10baseT_Half & - ~SUPPORTED_100baseT_Half & - ~SUPPORTED_1000baseT_Half; - phy_dev->supported |= SUPPORTED_Pause | - SUPPORTED_Asym_Pause; - phy_dev->advertising = phy_dev->supported; + phy_remove_link_mode(phy_dev, ETHTOOL_LINK_MODE_10baseT_Half_BIT); + phy_remove_link_mode(phy_dev, ETHTOOL_LINK_MODE_100baseT_Half_BIT); + phy_remove_link_mode(phy_dev, ETHTOOL_LINK_MODE_1000baseT_Half_BIT); + phy_support_asym_pause(phy_dev); return 0; } diff --git a/drivers/net/ethernet/apple/bmac.c b/drivers/net/ethernet/apple/bmac.c index 024998d6d8c6..6a8e2567f2bd 100644 --- a/drivers/net/ethernet/apple/bmac.c +++ b/drivers/net/ethernet/apple/bmac.c @@ -154,7 +154,7 @@ static irqreturn_t bmac_txdma_intr(int irq, void *dev_id); static irqreturn_t bmac_rxdma_intr(int irq, void *dev_id); static void bmac_set_timeout(struct net_device *dev); static void bmac_tx_timeout(struct timer_list *t); -static int bmac_output(struct sk_buff *skb, struct net_device *dev); +static netdev_tx_t bmac_output(struct sk_buff *skb, struct net_device *dev); static void bmac_start(struct net_device *dev); #define DBDMA_SET(x) ( ((x) | (x) << 16) ) @@ -1456,7 +1456,7 @@ bmac_start(struct net_device *dev) spin_unlock_irqrestore(&bp->lock, flags); } -static int +static netdev_tx_t bmac_output(struct sk_buff *skb, struct net_device *dev) { struct bmac_data *bp = netdev_priv(dev); diff --git a/drivers/net/ethernet/apple/mace.c b/drivers/net/ethernet/apple/mace.c index 0b5429d76bcf..68b9ee489489 100644 --- a/drivers/net/ethernet/apple/mace.c +++ b/drivers/net/ethernet/apple/mace.c @@ -78,7 +78,7 @@ struct mace_data { static int mace_open(struct net_device *dev); static int mace_close(struct net_device *dev); -static int mace_xmit_start(struct sk_buff *skb, struct net_device *dev); +static netdev_tx_t mace_xmit_start(struct sk_buff *skb, struct net_device *dev); static void mace_set_multicast(struct net_device *dev); static void mace_reset(struct net_device *dev); static int mace_set_address(struct net_device *dev, void *addr); @@ -525,7 +525,7 @@ static inline void mace_set_timeout(struct net_device *dev) mp->timeout_active = 1; } -static int mace_xmit_start(struct sk_buff *skb, struct net_device *dev) +static netdev_tx_t mace_xmit_start(struct sk_buff *skb, struct net_device *dev) { struct mace_data *mp = netdev_priv(dev); volatile struct dbdma_regs __iomem *td = mp->tx_dma; diff --git a/drivers/net/ethernet/apple/macmace.c b/drivers/net/ethernet/apple/macmace.c index 137cbb470af2..376f2c2613e7 100644 --- a/drivers/net/ethernet/apple/macmace.c +++ b/drivers/net/ethernet/apple/macmace.c @@ -89,7 +89,7 @@ struct mace_frame { static int mace_open(struct net_device *dev); static int mace_close(struct net_device *dev); -static int mace_xmit_start(struct sk_buff *skb, struct net_device *dev); +static netdev_tx_t mace_xmit_start(struct sk_buff *skb, struct net_device *dev); static void mace_set_multicast(struct net_device *dev); static int mace_set_address(struct net_device *dev, void *addr); static void mace_reset(struct net_device *dev); @@ -444,7 +444,7 @@ static int mace_close(struct net_device *dev) * Transmit a frame */ -static int mace_xmit_start(struct sk_buff *skb, struct net_device *dev) +static netdev_tx_t mace_xmit_start(struct sk_buff *skb, struct net_device *dev) { struct mace_data *mp = netdev_priv(dev); unsigned long flags; diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_common.h b/drivers/net/ethernet/aquantia/atlantic/aq_common.h index d52b088ff8f0..becb578211ed 100644 --- a/drivers/net/ethernet/aquantia/atlantic/aq_common.h +++ b/drivers/net/ethernet/aquantia/atlantic/aq_common.h @@ -57,4 +57,9 @@ #define AQ_NIC_RATE_1G BIT(4) #define AQ_NIC_RATE_100M BIT(5) +#define AQ_NIC_RATE_EEE_10G BIT(6) +#define AQ_NIC_RATE_EEE_5G BIT(7) +#define AQ_NIC_RATE_EEE_2GS BIT(8) +#define AQ_NIC_RATE_EEE_1G BIT(9) + #endif /* AQ_COMMON_H */ diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_ethtool.c b/drivers/net/ethernet/aquantia/atlantic/aq_ethtool.c index 08c9fa6ca71f..6a633c70f603 100644 --- a/drivers/net/ethernet/aquantia/atlantic/aq_ethtool.c +++ b/drivers/net/ethernet/aquantia/atlantic/aq_ethtool.c @@ -98,8 +98,8 @@ static void aq_ethtool_stats(struct net_device *ndev, struct aq_nic_cfg_s *cfg = aq_nic_get_cfg(aq_nic); memset(data, 0, (ARRAY_SIZE(aq_ethtool_stat_names) + - ARRAY_SIZE(aq_ethtool_queue_stat_names) * - cfg->vecs) * sizeof(u64)); + ARRAY_SIZE(aq_ethtool_queue_stat_names) * + cfg->vecs) * sizeof(u64)); aq_nic_get_stats(aq_nic, data); } @@ -285,6 +285,111 @@ static int aq_ethtool_set_coalesce(struct net_device *ndev, return aq_nic_update_interrupt_moderation_settings(aq_nic); } +static void aq_ethtool_get_wol(struct net_device *ndev, + struct ethtool_wolinfo *wol) +{ + struct aq_nic_s *aq_nic = netdev_priv(ndev); + struct aq_nic_cfg_s *cfg = aq_nic_get_cfg(aq_nic); + + wol->supported = WAKE_MAGIC; + wol->wolopts = 0; + + if (cfg->wol) + wol->wolopts |= WAKE_MAGIC; +} + +static int aq_ethtool_set_wol(struct net_device *ndev, + struct ethtool_wolinfo *wol) +{ + struct pci_dev *pdev = to_pci_dev(ndev->dev.parent); + struct aq_nic_s *aq_nic = netdev_priv(ndev); + struct aq_nic_cfg_s *cfg = aq_nic_get_cfg(aq_nic); + int err = 0; + + if (wol->wolopts & WAKE_MAGIC) + cfg->wol |= AQ_NIC_WOL_ENABLED; + else + cfg->wol &= ~AQ_NIC_WOL_ENABLED; + err = device_set_wakeup_enable(&pdev->dev, wol->wolopts); + + return err; +} + +static enum hw_atl_fw2x_rate eee_mask_to_ethtool_mask(u32 speed) +{ + u32 rate = 0; + + if (speed & AQ_NIC_RATE_EEE_10G) + rate |= SUPPORTED_10000baseT_Full; + + if (speed & AQ_NIC_RATE_EEE_2GS) + rate |= SUPPORTED_2500baseX_Full; + + if (speed & AQ_NIC_RATE_EEE_1G) + rate |= SUPPORTED_1000baseT_Full; + + return rate; +} + +static int aq_ethtool_get_eee(struct net_device *ndev, struct ethtool_eee *eee) +{ + struct aq_nic_s *aq_nic = netdev_priv(ndev); + u32 rate, supported_rates; + int err = 0; + + if (!aq_nic->aq_fw_ops->get_eee_rate) + return -EOPNOTSUPP; + + err = aq_nic->aq_fw_ops->get_eee_rate(aq_nic->aq_hw, &rate, + &supported_rates); + if (err < 0) + return err; + + eee->supported = eee_mask_to_ethtool_mask(supported_rates); + + if (aq_nic->aq_nic_cfg.eee_speeds) + eee->advertised = eee->supported; + + eee->lp_advertised = eee_mask_to_ethtool_mask(rate); + + eee->eee_enabled = !!eee->advertised; + + eee->tx_lpi_enabled = eee->eee_enabled; + if (eee->advertised & eee->lp_advertised) + eee->eee_active = true; + + return 0; +} + +static int aq_ethtool_set_eee(struct net_device *ndev, struct ethtool_eee *eee) +{ + struct aq_nic_s *aq_nic = netdev_priv(ndev); + u32 rate, supported_rates; + struct aq_nic_cfg_s *cfg; + int err = 0; + + cfg = aq_nic_get_cfg(aq_nic); + + if (unlikely(!aq_nic->aq_fw_ops->get_eee_rate || + !aq_nic->aq_fw_ops->set_eee_rate)) + return -EOPNOTSUPP; + + err = aq_nic->aq_fw_ops->get_eee_rate(aq_nic->aq_hw, &rate, + &supported_rates); + if (err < 0) + return err; + + if (eee->eee_enabled) { + rate = supported_rates; + cfg->eee_speeds = rate; + } else { + rate = 0; + cfg->eee_speeds = 0; + } + + return aq_nic->aq_fw_ops->set_eee_rate(aq_nic->aq_hw, rate); +} + static int aq_ethtool_nway_reset(struct net_device *ndev) { struct aq_nic_s *aq_nic = netdev_priv(ndev); @@ -403,9 +508,13 @@ const struct ethtool_ops aq_ethtool_ops = { .get_drvinfo = aq_ethtool_get_drvinfo, .get_strings = aq_ethtool_get_strings, .get_rxfh_indir_size = aq_ethtool_get_rss_indir_size, + .get_wol = aq_ethtool_get_wol, + .set_wol = aq_ethtool_set_wol, .nway_reset = aq_ethtool_nway_reset, .get_ringparam = aq_get_ringparam, .set_ringparam = aq_set_ringparam, + .get_eee = aq_ethtool_get_eee, + .set_eee = aq_ethtool_set_eee, .get_pauseparam = aq_ethtool_get_pauseparam, .set_pauseparam = aq_ethtool_set_pauseparam, .get_rxfh_key_size = aq_ethtool_get_rss_key_size, diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_hw.h b/drivers/net/ethernet/aquantia/atlantic/aq_hw.h index 5c00671f248d..e8689241204e 100644 --- a/drivers/net/ethernet/aquantia/atlantic/aq_hw.h +++ b/drivers/net/ethernet/aquantia/atlantic/aq_hw.h @@ -112,7 +112,7 @@ struct aq_hw_s { const struct aq_fw_ops *aq_fw_ops; void __iomem *mmio; struct aq_hw_link_status_s aq_link_status; - struct hw_aq_atl_utils_mbox mbox; + struct hw_atl_utils_mbox mbox; struct hw_atl_stats_s last_stats; struct aq_stats_s curr_stats; u64 speed; @@ -124,7 +124,7 @@ struct aq_hw_s { u32 mbox_addr; u32 rpc_addr; u32 rpc_tid; - struct hw_aq_atl_utils_fw_rpc rpc; + struct hw_atl_utils_fw_rpc rpc; }; struct aq_ring_s; @@ -204,7 +204,6 @@ struct aq_hw_ops { int (*hw_get_fw_version)(struct aq_hw_s *self, u32 *fw_version); - int (*hw_set_power)(struct aq_hw_s *self, unsigned int power_state); }; struct aq_fw_ops { @@ -228,6 +227,14 @@ struct aq_fw_ops { int (*update_stats)(struct aq_hw_s *self); int (*set_flow_control)(struct aq_hw_s *self); + + int (*set_power)(struct aq_hw_s *self, unsigned int power_state, + u8 *mac); + + int (*set_eee_rate)(struct aq_hw_s *self, u32 speed); + + int (*get_eee_rate)(struct aq_hw_s *self, u32 *rate, + u32 *supported_rates); }; #endif /* AQ_HW_H */ diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_nic.c b/drivers/net/ethernet/aquantia/atlantic/aq_nic.c index 26dc6782b475..5fed24446687 100644 --- a/drivers/net/ethernet/aquantia/atlantic/aq_nic.c +++ b/drivers/net/ethernet/aquantia/atlantic/aq_nic.c @@ -189,7 +189,7 @@ static void aq_nic_polling_timer_cb(struct timer_list *t) aq_vec_isr(i, (void *)aq_vec); mod_timer(&self->polling_timer, jiffies + - AQ_CFG_POLLING_TIMER_INTERVAL); + AQ_CFG_POLLING_TIMER_INTERVAL); } int aq_nic_ndev_register(struct aq_nic_s *self) @@ -301,13 +301,13 @@ int aq_nic_start(struct aq_nic_s *self) unsigned int i = 0U; err = self->aq_hw_ops->hw_multicast_list_set(self->aq_hw, - self->mc_list.ar, - self->mc_list.count); + self->mc_list.ar, + self->mc_list.count); if (err < 0) goto err_exit; err = self->aq_hw_ops->hw_packet_filter_set(self->aq_hw, - self->packet_filter); + self->packet_filter); if (err < 0) goto err_exit; @@ -327,7 +327,7 @@ int aq_nic_start(struct aq_nic_s *self) goto err_exit; timer_setup(&self->service_timer, aq_nic_service_timer_cb, 0); mod_timer(&self->service_timer, jiffies + - AQ_CFG_SERVICE_TIMER_INTERVAL); + AQ_CFG_SERVICE_TIMER_INTERVAL); if (self->aq_nic_cfg.is_polling) { timer_setup(&self->polling_timer, aq_nic_polling_timer_cb, 0); @@ -344,7 +344,7 @@ int aq_nic_start(struct aq_nic_s *self) } err = self->aq_hw_ops->hw_irq_enable(self->aq_hw, - AQ_CFG_IRQ_MASK); + AQ_CFG_IRQ_MASK); if (err < 0) goto err_exit; } @@ -889,11 +889,13 @@ void aq_nic_deinit(struct aq_nic_s *self) self->aq_vecs > i; ++i, aq_vec = self->aq_vec[i]) aq_vec_deinit(aq_vec); - if (self->power_state == AQ_HW_POWER_STATE_D0) { - (void)self->aq_fw_ops->deinit(self->aq_hw); - } else { - (void)self->aq_hw_ops->hw_set_power(self->aq_hw, - self->power_state); + self->aq_fw_ops->deinit(self->aq_hw); + + if (self->power_state != AQ_HW_POWER_STATE_D0 || + self->aq_hw->aq_nic_cfg->wol) { + self->aq_fw_ops->set_power(self->aq_hw, + self->power_state, + self->ndev->dev_addr); } err_exit:; diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_nic.h b/drivers/net/ethernet/aquantia/atlantic/aq_nic.h index fecfc401f95d..c1582f4e8e1b 100644 --- a/drivers/net/ethernet/aquantia/atlantic/aq_nic.h +++ b/drivers/net/ethernet/aquantia/atlantic/aq_nic.h @@ -36,6 +36,7 @@ struct aq_nic_cfg_s { u32 flow_control; u32 link_speed_msk; u32 vlan_id; + u32 wol; u16 is_mc_list_enabled; u16 mc_list_count; bool is_autoneg; @@ -44,6 +45,7 @@ struct aq_nic_cfg_s { bool is_lro; u8 tcs; struct aq_rss_parameters aq_rss; + u32 eee_speeds; }; #define AQ_NIC_FLAG_STARTED 0x00000004U @@ -54,6 +56,8 @@ struct aq_nic_cfg_s { #define AQ_NIC_FLAG_ERR_UNPLUG 0x40000000U #define AQ_NIC_FLAG_ERR_HW 0x80000000U +#define AQ_NIC_WOL_ENABLED BIT(0) + #define AQ_NIC_TCVEC2RING(_NIC_, _TC_, _VEC_) \ ((_TC_) * AQ_CFG_TCS_MAX + (_VEC_)) diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_ring.c b/drivers/net/ethernet/aquantia/atlantic/aq_ring.c index b5f1f62e8e25..3db91446cc67 100644 --- a/drivers/net/ethernet/aquantia/atlantic/aq_ring.c +++ b/drivers/net/ethernet/aquantia/atlantic/aq_ring.c @@ -29,8 +29,8 @@ static struct aq_ring_s *aq_ring_alloc(struct aq_ring_s *self, goto err_exit; } self->dx_ring = dma_alloc_coherent(aq_nic_get_dev(aq_nic), - self->size * self->dx_size, - &self->dx_ring_pa, GFP_KERNEL); + self->size * self->dx_size, + &self->dx_ring_pa, GFP_KERNEL); if (!self->dx_ring) { err = -ENOMEM; goto err_exit; @@ -225,9 +225,10 @@ int aq_ring_rx_clean(struct aq_ring_s *self, } /* for single fragment packets use build_skb() */ - if (buff->is_eop) { + if (buff->is_eop && + buff->len <= AQ_CFG_RX_FRAME_MAX - AQ_SKB_ALIGN) { skb = build_skb(page_address(buff->page), - buff->len + AQ_SKB_ALIGN); + AQ_CFG_RX_FRAME_MAX); if (unlikely(!skb)) { err = -ENOMEM; goto err_exit; @@ -247,18 +248,21 @@ int aq_ring_rx_clean(struct aq_ring_s *self, buff->len - ETH_HLEN, SKB_TRUESIZE(buff->len - ETH_HLEN)); - for (i = 1U, next_ = buff->next, - buff_ = &self->buff_ring[next_]; true; - next_ = buff_->next, - buff_ = &self->buff_ring[next_], ++i) { - skb_add_rx_frag(skb, i, buff_->page, 0, - buff_->len, - SKB_TRUESIZE(buff->len - - ETH_HLEN)); - buff_->is_cleaned = 1; - - if (buff_->is_eop) - break; + if (!buff->is_eop) { + for (i = 1U, next_ = buff->next, + buff_ = &self->buff_ring[next_]; + true; next_ = buff_->next, + buff_ = &self->buff_ring[next_], ++i) { + skb_add_rx_frag(skb, i, + buff_->page, 0, + buff_->len, + SKB_TRUESIZE(buff->len - + ETH_HLEN)); + buff_->is_cleaned = 1; + + if (buff_->is_eop) + break; + } } } diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_a0.c b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_a0.c index 97addfa6f895..2469ed4d86b9 100644 --- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_a0.c +++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_a0.c @@ -49,37 +49,37 @@ const struct aq_hw_caps_s hw_atl_a0_caps_aqc100 = { DEFAULT_A0_BOARD_BASIC_CAPABILITIES, .media_type = AQ_HW_MEDIA_TYPE_FIBRE, - .link_speed_msk = HW_ATL_A0_RATE_5G | - HW_ATL_A0_RATE_2G5 | - HW_ATL_A0_RATE_1G | - HW_ATL_A0_RATE_100M, + .link_speed_msk = AQ_NIC_RATE_5G | + AQ_NIC_RATE_2GS | + AQ_NIC_RATE_1G | + AQ_NIC_RATE_100M, }; const struct aq_hw_caps_s hw_atl_a0_caps_aqc107 = { DEFAULT_A0_BOARD_BASIC_CAPABILITIES, .media_type = AQ_HW_MEDIA_TYPE_TP, - .link_speed_msk = HW_ATL_A0_RATE_10G | - HW_ATL_A0_RATE_5G | - HW_ATL_A0_RATE_2G5 | - HW_ATL_A0_RATE_1G | - HW_ATL_A0_RATE_100M, + .link_speed_msk = AQ_NIC_RATE_10G | + AQ_NIC_RATE_5G | + AQ_NIC_RATE_2GS | + AQ_NIC_RATE_1G | + AQ_NIC_RATE_100M, }; const struct aq_hw_caps_s hw_atl_a0_caps_aqc108 = { DEFAULT_A0_BOARD_BASIC_CAPABILITIES, .media_type = AQ_HW_MEDIA_TYPE_TP, - .link_speed_msk = HW_ATL_A0_RATE_5G | - HW_ATL_A0_RATE_2G5 | - HW_ATL_A0_RATE_1G | - HW_ATL_A0_RATE_100M, + .link_speed_msk = AQ_NIC_RATE_5G | + AQ_NIC_RATE_2GS | + AQ_NIC_RATE_1G | + AQ_NIC_RATE_100M, }; const struct aq_hw_caps_s hw_atl_a0_caps_aqc109 = { DEFAULT_A0_BOARD_BASIC_CAPABILITIES, .media_type = AQ_HW_MEDIA_TYPE_TP, - .link_speed_msk = HW_ATL_A0_RATE_2G5 | - HW_ATL_A0_RATE_1G | - HW_ATL_A0_RATE_100M, + .link_speed_msk = AQ_NIC_RATE_2GS | + AQ_NIC_RATE_1G | + AQ_NIC_RATE_100M, }; static int hw_atl_a0_hw_reset(struct aq_hw_s *self) @@ -284,7 +284,7 @@ static int hw_atl_a0_hw_init_rx_path(struct aq_hw_s *self) /* RSS Ring selection */ hw_atl_reg_rx_flr_rss_control1set(self, cfg->is_rss ? - 0xB3333333U : 0x00000000U); + 0xB3333333U : 0x00000000U); /* Multicast filters */ for (i = HW_ATL_A0_MAC_MAX; i--;) { @@ -325,7 +325,7 @@ static int hw_atl_a0_hw_mac_addr_set(struct aq_hw_s *self, u8 *mac_addr) } h = (mac_addr[0] << 8) | (mac_addr[1]); l = (mac_addr[2] << 24) | (mac_addr[3] << 16) | - (mac_addr[4] << 8) | mac_addr[5]; + (mac_addr[4] << 8) | mac_addr[5]; hw_atl_rpfl2_uc_flr_en_set(self, 0U, HW_ATL_A0_MAC); hw_atl_rpfl2unicast_dest_addresslsw_set(self, l, HW_ATL_A0_MAC); @@ -519,7 +519,7 @@ static int hw_atl_a0_hw_ring_rx_init(struct aq_hw_s *self, hw_atl_rdm_rx_desc_data_buff_size_set(self, AQ_CFG_RX_FRAME_MAX / 1024U, - aq_ring->idx); + aq_ring->idx); hw_atl_rdm_rx_desc_head_buff_size_set(self, 0U, aq_ring->idx); hw_atl_rdm_rx_desc_head_splitting_set(self, 0U, aq_ring->idx); @@ -758,7 +758,7 @@ static int hw_atl_a0_hw_packet_filter_set(struct aq_hw_s *self, hw_atl_rpfl2_uc_flr_en_set(self, (self->aq_nic_cfg->is_mc_list_enabled && (i <= self->aq_nic_cfg->mc_list_count)) ? - 1U : 0U, i); + 1U : 0U, i); return aq_hw_err_from_flags(self); } @@ -877,7 +877,6 @@ static int hw_atl_a0_hw_ring_rx_stop(struct aq_hw_s *self, const struct aq_hw_ops hw_atl_ops_a0 = { .hw_set_mac_address = hw_atl_a0_hw_mac_addr_set, .hw_init = hw_atl_a0_hw_init, - .hw_set_power = hw_atl_utils_hw_set_power, .hw_reset = hw_atl_a0_hw_reset, .hw_start = hw_atl_a0_hw_start, .hw_ring_tx_start = hw_atl_a0_hw_ring_tx_start, diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_a0_internal.h b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_a0_internal.h index 3c94cff57876..a021dc431ef7 100644 --- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_a0_internal.h +++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_a0_internal.h @@ -62,12 +62,6 @@ #define HW_ATL_A0_MPI_SPEED_MSK 0xFFFFU #define HW_ATL_A0_MPI_SPEED_SHIFT 16U -#define HW_ATL_A0_RATE_10G BIT(0) -#define HW_ATL_A0_RATE_5G BIT(1) -#define HW_ATL_A0_RATE_2G5 BIT(3) -#define HW_ATL_A0_RATE_1G BIT(4) -#define HW_ATL_A0_RATE_100M BIT(5) - #define HW_ATL_A0_TXBUF_MAX 160U #define HW_ATL_A0_RXBUF_MAX 320U diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c index 1d44a386e7d3..76d25d594a0f 100644 --- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c +++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c @@ -51,38 +51,38 @@ const struct aq_hw_caps_s hw_atl_b0_caps_aqc100 = { DEFAULT_B0_BOARD_BASIC_CAPABILITIES, .media_type = AQ_HW_MEDIA_TYPE_FIBRE, - .link_speed_msk = HW_ATL_B0_RATE_10G | - HW_ATL_B0_RATE_5G | - HW_ATL_B0_RATE_2G5 | - HW_ATL_B0_RATE_1G | - HW_ATL_B0_RATE_100M, + .link_speed_msk = AQ_NIC_RATE_10G | + AQ_NIC_RATE_5G | + AQ_NIC_RATE_2GS | + AQ_NIC_RATE_1G | + AQ_NIC_RATE_100M, }; const struct aq_hw_caps_s hw_atl_b0_caps_aqc107 = { DEFAULT_B0_BOARD_BASIC_CAPABILITIES, .media_type = AQ_HW_MEDIA_TYPE_TP, - .link_speed_msk = HW_ATL_B0_RATE_10G | - HW_ATL_B0_RATE_5G | - HW_ATL_B0_RATE_2G5 | - HW_ATL_B0_RATE_1G | - HW_ATL_B0_RATE_100M, + .link_speed_msk = AQ_NIC_RATE_10G | + AQ_NIC_RATE_5G | + AQ_NIC_RATE_2GS | + AQ_NIC_RATE_1G | + AQ_NIC_RATE_100M, }; const struct aq_hw_caps_s hw_atl_b0_caps_aqc108 = { DEFAULT_B0_BOARD_BASIC_CAPABILITIES, .media_type = AQ_HW_MEDIA_TYPE_TP, - .link_speed_msk = HW_ATL_B0_RATE_5G | - HW_ATL_B0_RATE_2G5 | - HW_ATL_B0_RATE_1G | - HW_ATL_B0_RATE_100M, + .link_speed_msk = AQ_NIC_RATE_5G | + AQ_NIC_RATE_2GS | + AQ_NIC_RATE_1G | + AQ_NIC_RATE_100M, }; const struct aq_hw_caps_s hw_atl_b0_caps_aqc109 = { DEFAULT_B0_BOARD_BASIC_CAPABILITIES, .media_type = AQ_HW_MEDIA_TYPE_TP, - .link_speed_msk = HW_ATL_B0_RATE_2G5 | - HW_ATL_B0_RATE_1G | - HW_ATL_B0_RATE_100M, + .link_speed_msk = AQ_NIC_RATE_2GS | + AQ_NIC_RATE_1G | + AQ_NIC_RATE_100M, }; static int hw_atl_b0_hw_reset(struct aq_hw_s *self) @@ -935,7 +935,6 @@ static int hw_atl_b0_hw_ring_rx_stop(struct aq_hw_s *self, const struct aq_hw_ops hw_atl_ops_b0 = { .hw_set_mac_address = hw_atl_b0_hw_mac_addr_set, .hw_init = hw_atl_b0_hw_init, - .hw_set_power = hw_atl_utils_hw_set_power, .hw_reset = hw_atl_b0_hw_reset, .hw_start = hw_atl_b0_hw_start, .hw_ring_tx_start = hw_atl_b0_hw_ring_tx_start, diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0_internal.h b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0_internal.h index 28568f5fa74b..b318eefd36ae 100644 --- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0_internal.h +++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0_internal.h @@ -67,12 +67,6 @@ #define HW_ATL_B0_MPI_SPEED_MSK 0xFFFFU #define HW_ATL_B0_MPI_SPEED_SHIFT 16U -#define HW_ATL_B0_RATE_10G BIT(0) -#define HW_ATL_B0_RATE_5G BIT(1) -#define HW_ATL_B0_RATE_2G5 BIT(3) -#define HW_ATL_B0_RATE_1G BIT(4) -#define HW_ATL_B0_RATE_100M BIT(5) - #define HW_ATL_B0_TXBUF_MAX 160U #define HW_ATL_B0_RXBUF_MAX 320U diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_llh.c b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_llh.c index 10ba035dadb1..be0a3a90dfad 100644 --- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_llh.c +++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_llh.c @@ -1460,3 +1460,11 @@ void hw_atl_reg_glb_cpu_scratch_scp_set(struct aq_hw_s *aq_hw, aq_hw_write_reg(aq_hw, HW_ATL_GLB_CPU_SCRATCH_SCP_ADR(scratch_scp), glb_cpu_scratch_scp); } + +void hw_atl_mcp_up_force_intr_set(struct aq_hw_s *aq_hw, u32 up_force_intr) +{ + aq_hw_write_reg_bit(aq_hw, HW_ATL_MCP_UP_FORCE_INTERRUPT_ADR, + HW_ATL_MCP_UP_FORCE_INTERRUPT_MSK, + HW_ATL_MCP_UP_FORCE_INTERRUPT_SHIFT, + up_force_intr); +} diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_llh.h b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_llh.h index dfb426f2dc2c..7056c7342afc 100644 --- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_llh.h +++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_llh.h @@ -698,4 +698,7 @@ void hw_atl_msm_reg_wr_strobe_set(struct aq_hw_s *aq_hw, u32 reg_wr_strobe); /* set pci register reset disable */ void hw_atl_pci_pci_reg_res_dis_set(struct aq_hw_s *aq_hw, u32 pci_reg_res_dis); +/* set uP Force Interrupt */ +void hw_atl_mcp_up_force_intr_set(struct aq_hw_s *aq_hw, u32 up_force_intr); + #endif /* HW_ATL_LLH_H */ diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_llh_internal.h b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_llh_internal.h index e0cf70120f1d..716674a9b729 100644 --- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_llh_internal.h +++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_llh_internal.h @@ -2387,4 +2387,17 @@ #define HW_ATL_GLB_CPU_SCRATCH_SCP_ADR(scratch_scp) \ (0x00000300u + (scratch_scp) * 0x4) +/* register address for bitfield uP Force Interrupt */ +#define HW_ATL_MCP_UP_FORCE_INTERRUPT_ADR 0x00000404 +/* bitmask for bitfield uP Force Interrupt */ +#define HW_ATL_MCP_UP_FORCE_INTERRUPT_MSK 0x00000002 +/* inverted bitmask for bitfield uP Force Interrupt */ +#define HW_ATL_MCP_UP_FORCE_INTERRUPT_MSKN 0xFFFFFFFD +/* lower bit position of bitfield uP Force Interrupt */ +#define HW_ATL_MCP_UP_FORCE_INTERRUPT_SHIFT 1 +/* width of bitfield uP Force Interrupt */ +#define HW_ATL_MCP_UP_FORCE_INTERRUPT_WIDTH 1 +/* default value of bitfield uP Force Interrupt */ +#define HW_ATL_MCP_UP_FORCE_INTERRUPT_DEFAULT 0x0 + #endif /* HW_ATL_LLH_INTERNAL_H */ diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.c b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.c index c965e65d07db..0dd59b09060b 100644 --- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.c +++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.c @@ -49,6 +49,7 @@ #define FORCE_FLASHLESS 0 static int hw_atl_utils_ver_match(u32 ver_expected, u32 ver_actual); + static int hw_atl_utils_mpi_set_state(struct aq_hw_s *self, enum hal_atl_utils_fw_state_e state); @@ -69,10 +70,10 @@ int hw_atl_utils_initfw(struct aq_hw_s *self, const struct aq_fw_ops **fw_ops) self->fw_ver_actual) == 0) { *fw_ops = &aq_fw_1x_ops; } else if (hw_atl_utils_ver_match(HW_ATL_FW_VER_2X, - self->fw_ver_actual) == 0) { + self->fw_ver_actual) == 0) { *fw_ops = &aq_fw_2x_ops; } else if (hw_atl_utils_ver_match(HW_ATL_FW_VER_3X, - self->fw_ver_actual) == 0) { + self->fw_ver_actual) == 0) { *fw_ops = &aq_fw_2x_ops; } else { aq_pr_err("Bad FW version detected: %x\n", @@ -260,7 +261,7 @@ int hw_atl_utils_soft_reset(struct aq_hw_s *self) hw_atl_utils_mpi_set_state(self, MPI_DEINIT); AQ_HW_WAIT_FOR((aq_hw_read_reg(self, HW_ATL_MPI_STATE_ADR) & - HW_ATL_MPI_STATE_MSK) == MPI_DEINIT, + HW_ATL_MPI_STATE_MSK) == MPI_DEINIT, 10, 1000U); } @@ -277,7 +278,7 @@ int hw_atl_utils_fw_downld_dwords(struct aq_hw_s *self, u32 a, AQ_HW_WAIT_FOR(hw_atl_reg_glb_cpu_sem_get(self, HW_ATL_FW_SM_RAM) == 1U, - 1U, 10000U); + 1U, 10000U); if (err < 0) { bool is_locked; @@ -325,17 +326,31 @@ static int hw_atl_utils_fw_upload_dwords(struct aq_hw_s *self, u32 a, u32 *p, err = -ETIME; goto err_exit; } + if (IS_CHIP_FEATURE(REVISION_B1)) { + u32 offset = 0; + + for (; offset < cnt; ++offset) { + aq_hw_write_reg(self, 0x328, p[offset]); + aq_hw_write_reg(self, 0x32C, + (0x80000000 | (0xFFFF & (offset * 4)))); + hw_atl_mcp_up_force_intr_set(self, 1); + /* 1000 times by 10us = 10ms */ + AQ_HW_WAIT_FOR((aq_hw_read_reg(self, + 0x32C) & 0xF0000000) != + 0x80000000, + 10, 1000); + } + } else { + u32 offset = 0; - aq_hw_write_reg(self, 0x00000208U, a); - - for (++cnt; --cnt;) { - u32 i = 0U; + aq_hw_write_reg(self, 0x208, a); - aq_hw_write_reg(self, 0x0000020CU, *(p++)); - aq_hw_write_reg(self, 0x00000200U, 0xC000U); + for (; offset < cnt; ++offset) { + aq_hw_write_reg(self, 0x20C, p[offset]); + aq_hw_write_reg(self, 0x200, 0xC000); - for (i = 1024U; - (0x100U & aq_hw_read_reg(self, 0x00000200U)) && --i;) { + AQ_HW_WAIT_FOR((aq_hw_read_reg(self, 0x200U) & + 0x100) == 0, 10, 1000); } } @@ -379,7 +394,7 @@ static int hw_atl_utils_init_ucp(struct aq_hw_s *self, /* check 10 times by 1ms */ AQ_HW_WAIT_FOR(0U != (self->mbox_addr = - aq_hw_read_reg(self, 0x360U)), 1000U, 10U); + aq_hw_read_reg(self, 0x360U)), 1000U, 10U); return err; } @@ -399,7 +414,7 @@ struct aq_hw_atl_utils_fw_rpc_tid_s { #define hw_atl_utils_fw_rpc_init(_H_) hw_atl_utils_fw_rpc_wait(_H_, NULL) -static int hw_atl_utils_fw_rpc_call(struct aq_hw_s *self, unsigned int rpc_size) +int hw_atl_utils_fw_rpc_call(struct aq_hw_s *self, unsigned int rpc_size) { int err = 0; struct aq_hw_atl_utils_fw_rpc_tid_s sw; @@ -411,7 +426,7 @@ static int hw_atl_utils_fw_rpc_call(struct aq_hw_s *self, unsigned int rpc_size) err = hw_atl_utils_fw_upload_dwords(self, self->rpc_addr, (u32 *)(void *)&self->rpc, (rpc_size + sizeof(u32) - - sizeof(u8)) / sizeof(u32)); + sizeof(u8)) / sizeof(u32)); if (err < 0) goto err_exit; @@ -423,8 +438,8 @@ err_exit: return err; } -static int hw_atl_utils_fw_rpc_wait(struct aq_hw_s *self, - struct hw_aq_atl_utils_fw_rpc **rpc) +int hw_atl_utils_fw_rpc_wait(struct aq_hw_s *self, + struct hw_atl_utils_fw_rpc **rpc) { int err = 0; struct aq_hw_atl_utils_fw_rpc_tid_s sw; @@ -436,7 +451,7 @@ static int hw_atl_utils_fw_rpc_wait(struct aq_hw_s *self, self->rpc_tid = sw.tid; AQ_HW_WAIT_FOR(sw.tid == - (fw.val = + (fw.val = aq_hw_read_reg(self, HW_ATL_RPC_STATE_ADR), fw.tid), 1000U, 100U); if (err < 0) @@ -459,7 +474,7 @@ static int hw_atl_utils_fw_rpc_wait(struct aq_hw_s *self, (u32 *)(void *) &self->rpc, (fw.len + sizeof(u32) - - sizeof(u8)) / + sizeof(u8)) / sizeof(u32)); if (err < 0) goto err_exit; @@ -489,16 +504,16 @@ err_exit: } int hw_atl_utils_mpi_read_mbox(struct aq_hw_s *self, - struct hw_aq_atl_utils_mbox_header *pmbox) + struct hw_atl_utils_mbox_header *pmbox) { return hw_atl_utils_fw_downld_dwords(self, - self->mbox_addr, - (u32 *)(void *)pmbox, - sizeof(*pmbox) / sizeof(u32)); + self->mbox_addr, + (u32 *)(void *)pmbox, + sizeof(*pmbox) / sizeof(u32)); } void hw_atl_utils_mpi_read_stats(struct aq_hw_s *self, - struct hw_aq_atl_utils_mbox *pmbox) + struct hw_atl_utils_mbox *pmbox) { int err = 0; @@ -538,7 +553,7 @@ static int hw_atl_utils_mpi_set_state(struct aq_hw_s *self, { int err = 0; u32 transaction_id = 0; - struct hw_aq_atl_utils_mbox_header mbox; + struct hw_atl_utils_mbox_header mbox; u32 val = aq_hw_read_reg(self, HW_ATL_MPI_CONTROL_ADR); if (state == MPI_RESET) { @@ -547,8 +562,8 @@ static int hw_atl_utils_mpi_set_state(struct aq_hw_s *self, transaction_id = mbox.transaction_id; AQ_HW_WAIT_FOR(transaction_id != - (hw_atl_utils_mpi_read_mbox(self, &mbox), - mbox.transaction_id), + (hw_atl_utils_mpi_read_mbox(self, &mbox), + mbox.transaction_id), 1000U, 100U); if (err < 0) goto err_exit; @@ -645,9 +660,9 @@ int hw_atl_utils_get_mac_permanent(struct aq_hw_s *self, if ((mac[0] & 0x01U) || ((mac[0] | mac[1] | mac[2]) == 0x00U)) { /* chip revision */ - l = 0xE3000000U - | (0xFFFFU & aq_hw_read_reg(self, HW_ATL_UCP_0X370_REG)) - | (0x00 << 16); + l = 0xE3000000U | + (0xFFFFU & aq_hw_read_reg(self, HW_ATL_UCP_0X370_REG)) | + (0x00 << 16); h = 0x8001300EU; mac[5] = (u8)(0xFFU & l); @@ -730,17 +745,9 @@ static int hw_atl_fw1x_deinit(struct aq_hw_s *self) return 0; } -int hw_atl_utils_hw_set_power(struct aq_hw_s *self, - unsigned int power_state) -{ - hw_atl_utils_mpi_set_speed(self, 0); - hw_atl_utils_mpi_set_state(self, MPI_POWER); - return 0; -} - int hw_atl_utils_update_stats(struct aq_hw_s *self) { - struct hw_aq_atl_utils_mbox mbox; + struct hw_atl_utils_mbox mbox; hw_atl_utils_mpi_read_stats(self, &mbox); @@ -825,6 +832,81 @@ int hw_atl_utils_get_fw_version(struct aq_hw_s *self, u32 *fw_version) return 0; } +static int aq_fw1x_set_wol(struct aq_hw_s *self, bool wol_enabled, u8 *mac) +{ + struct hw_atl_utils_fw_rpc *prpc = NULL; + unsigned int rpc_size = 0U; + int err = 0; + + err = hw_atl_utils_fw_rpc_wait(self, &prpc); + if (err < 0) + goto err_exit; + + memset(prpc, 0, sizeof(*prpc)); + + if (wol_enabled) { + rpc_size = sizeof(prpc->msg_id) + sizeof(prpc->msg_wol); + + prpc->msg_id = HAL_ATLANTIC_UTILS_FW_MSG_WOL_ADD; + prpc->msg_wol.priority = + HAL_ATLANTIC_UTILS_FW_MSG_WOL_PRIOR; + prpc->msg_wol.pattern_id = + HAL_ATLANTIC_UTILS_FW_MSG_WOL_PATTERN; + prpc->msg_wol.wol_packet_type = + HAL_ATLANTIC_UTILS_FW_MSG_WOL_MAG_PKT; + + ether_addr_copy((u8 *)&prpc->msg_wol.wol_pattern, mac); + } else { + rpc_size = sizeof(prpc->msg_id) + sizeof(prpc->msg_del_id); + + prpc->msg_id = HAL_ATLANTIC_UTILS_FW_MSG_WOL_DEL; + prpc->msg_wol.pattern_id = + HAL_ATLANTIC_UTILS_FW_MSG_WOL_PATTERN; + } + + err = hw_atl_utils_fw_rpc_call(self, rpc_size); + +err_exit: + return err; +} + +int aq_fw1x_set_power(struct aq_hw_s *self, unsigned int power_state, + u8 *mac) +{ + struct hw_atl_utils_fw_rpc *prpc = NULL; + unsigned int rpc_size = 0U; + int err = 0; + + if (self->aq_nic_cfg->wol & AQ_NIC_WOL_ENABLED) { + err = aq_fw1x_set_wol(self, 1, mac); + + if (err < 0) + goto err_exit; + + rpc_size = sizeof(prpc->msg_id) + + sizeof(prpc->msg_enable_wakeup); + + err = hw_atl_utils_fw_rpc_wait(self, &prpc); + + if (err < 0) + goto err_exit; + + memset(prpc, 0, rpc_size); + + prpc->msg_id = HAL_ATLANTIC_UTILS_FW_MSG_ENABLE_WAKEUP; + prpc->msg_enable_wakeup.pattern_mask = 0x00000002; + + err = hw_atl_utils_fw_rpc_call(self, rpc_size); + if (err < 0) + goto err_exit; + } + hw_atl_utils_mpi_set_speed(self, 0); + hw_atl_utils_mpi_set_state(self, MPI_POWER); + +err_exit: + return err; +} + const struct aq_fw_ops aq_fw_1x_ops = { .init = hw_atl_utils_mpi_create, .deinit = hw_atl_fw1x_deinit, @@ -834,5 +916,8 @@ const struct aq_fw_ops aq_fw_1x_ops = { .set_state = hw_atl_utils_mpi_set_state, .update_link_status = hw_atl_utils_mpi_get_link_status, .update_stats = hw_atl_utils_update_stats, + .set_power = aq_fw1x_set_power, + .set_eee_rate = NULL, + .get_eee_rate = NULL, .set_flow_control = NULL, }; diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.h b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.h index b875590efcbd..3613fca64b58 100644 --- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.h +++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.h @@ -75,7 +75,7 @@ union __packed ip_addr { } v4; }; -struct __packed hw_aq_atl_utils_fw_rpc { +struct __packed hw_atl_utils_fw_rpc { u32 msg_id; union { @@ -101,8 +101,6 @@ struct __packed hw_aq_atl_utils_fw_rpc { struct { u32 priority; u32 wol_packet_type; - u16 friendly_name_len; - u16 friendly_name[65]; u32 pattern_id; u32 next_wol_pattern_offset; @@ -134,25 +132,112 @@ struct __packed hw_aq_atl_utils_fw_rpc { u32 pattern_offset; u32 pattern_size; } wol_bit_map_pattern; + + struct { + u8 mac_addr[ETH_ALEN]; + } wol_magic_packet_patter; } wol_pattern; } msg_wol; struct { - u32 is_wake_on_link_down; - u32 is_wake_on_link_up; - } msg_wolink; + union { + u32 pattern_mask; + + struct { + u32 reason_arp_v4_pkt : 1; + u32 reason_ipv4_ping_pkt : 1; + u32 reason_ipv6_ns_pkt : 1; + u32 reason_ipv6_ping_pkt : 1; + u32 reason_link_up : 1; + u32 reason_link_down : 1; + u32 reason_maximum : 1; + }; + }; + + union { + u32 offload_mask; + }; + } msg_enable_wakeup; + + struct { + u32 id; + } msg_del_id; }; }; -struct __packed hw_aq_atl_utils_mbox_header { +struct __packed hw_atl_utils_mbox_header { u32 version; u32 transaction_id; u32 error; }; -struct __packed hw_aq_atl_utils_mbox { - struct hw_aq_atl_utils_mbox_header header; +struct __packed hw_aq_info { + u8 reserved[6]; + u16 phy_fault_code; + u16 phy_temperature; + u8 cable_len; + u8 reserved1; + u32 cable_diag_data[4]; + u8 reserved2[32]; + u32 caps_lo; + u32 caps_hi; +}; + +struct __packed hw_atl_utils_mbox { + struct hw_atl_utils_mbox_header header; struct hw_atl_stats_s stats; + struct hw_aq_info info; +}; + +/* fw2x */ +typedef u32 fw_offset_t; + +struct __packed offload_ip_info { + u8 v4_local_addr_count; + u8 v4_addr_count; + u8 v6_local_addr_count; + u8 v6_addr_count; + fw_offset_t v4_addr; + fw_offset_t v4_prefix; + fw_offset_t v6_addr; + fw_offset_t v6_prefix; +}; + +struct __packed offload_port_info { + u16 udp_port_count; + u16 tcp_port_count; + fw_offset_t udp_port; + fw_offset_t tcp_port; +}; + +struct __packed offload_ka_info { + u16 v4_ka_count; + u16 v6_ka_count; + u32 retry_count; + u32 retry_interval; + fw_offset_t v4_ka; + fw_offset_t v6_ka; +}; + +struct __packed offload_rr_info { + u32 rr_count; + u32 rr_buf_len; + fw_offset_t rr_id_x; + fw_offset_t rr_buf; +}; + +struct __packed offload_info { + u32 version; + u32 len; + u8 mac_addr[ETH_ALEN]; + + u8 reserved[2]; + + struct offload_ip_info ips; + struct offload_port_info ports; + struct offload_ka_info kas; + struct offload_rr_info rrs; + u8 buf[0]; }; #define HAL_ATLANTIC_UTILS_CHIP_MIPS 0x00000001U @@ -181,6 +266,21 @@ enum hal_atl_utils_fw_state_e { #define HAL_ATLANTIC_RATE_100M BIT(5) #define HAL_ATLANTIC_RATE_INVALID BIT(6) +#define HAL_ATLANTIC_UTILS_FW_MSG_PING 0x1U +#define HAL_ATLANTIC_UTILS_FW_MSG_ARP 0x2U +#define HAL_ATLANTIC_UTILS_FW_MSG_INJECT 0x3U +#define HAL_ATLANTIC_UTILS_FW_MSG_WOL_ADD 0x4U +#define HAL_ATLANTIC_UTILS_FW_MSG_WOL_PRIOR 0x10000000U +#define HAL_ATLANTIC_UTILS_FW_MSG_WOL_PATTERN 0x1U +#define HAL_ATLANTIC_UTILS_FW_MSG_WOL_MAG_PKT 0x2U +#define HAL_ATLANTIC_UTILS_FW_MSG_WOL_DEL 0x5U +#define HAL_ATLANTIC_UTILS_FW_MSG_ENABLE_WAKEUP 0x6U +#define HAL_ATLANTIC_UTILS_FW_MSG_MSM_PFC 0x7U +#define HAL_ATLANTIC_UTILS_FW_MSG_PROVISIONING 0x8U +#define HAL_ATLANTIC_UTILS_FW_MSG_OFFLOAD_ADD 0x9U +#define HAL_ATLANTIC_UTILS_FW_MSG_OFFLOAD_DEL 0xAU +#define HAL_ATLANTIC_UTILS_FW_MSG_CABLE_DIAG 0xDU + enum hw_atl_fw2x_rate { FW2X_RATE_100M = 0x20, FW2X_RATE_1G = 0x100, @@ -286,10 +386,10 @@ int hw_atl_utils_soft_reset(struct aq_hw_s *self); void hw_atl_utils_hw_chip_features_init(struct aq_hw_s *self, u32 *p); int hw_atl_utils_mpi_read_mbox(struct aq_hw_s *self, - struct hw_aq_atl_utils_mbox_header *pmbox); + struct hw_atl_utils_mbox_header *pmbox); void hw_atl_utils_mpi_read_stats(struct aq_hw_s *self, - struct hw_aq_atl_utils_mbox *pmbox); + struct hw_atl_utils_mbox *pmbox); void hw_atl_utils_mpi_set(struct aq_hw_s *self, enum hal_atl_utils_fw_state_e state, @@ -316,9 +416,17 @@ int hw_atl_utils_get_fw_version(struct aq_hw_s *self, u32 *fw_version); int hw_atl_utils_update_stats(struct aq_hw_s *self); struct aq_stats_s *hw_atl_utils_get_hw_stats(struct aq_hw_s *self); + int hw_atl_utils_fw_downld_dwords(struct aq_hw_s *self, u32 a, u32 *p, u32 cnt); +int hw_atl_utils_fw_set_wol(struct aq_hw_s *self, bool wol_enabled, u8 *mac); + +int hw_atl_utils_fw_rpc_call(struct aq_hw_s *self, unsigned int rpc_size); + +int hw_atl_utils_fw_rpc_wait(struct aq_hw_s *self, + struct hw_atl_utils_fw_rpc **rpc); + extern const struct aq_fw_ops aq_fw_1x_ops; extern const struct aq_fw_ops aq_fw_2x_ops; diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils_fw2x.c b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils_fw2x.c index e37943760a58..c0568465e10b 100644 --- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils_fw2x.c +++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils_fw2x.c @@ -16,11 +16,13 @@ #include "../aq_pci_func.h" #include "../aq_ring.h" #include "../aq_vec.h" +#include "../aq_nic.h" #include "hw_atl_utils.h" #include "hw_atl_llh.h" #define HW_ATL_FW2X_MPI_EFUSE_ADDR 0x364 #define HW_ATL_FW2X_MPI_MBOX_ADDR 0x360 +#define HW_ATL_FW2X_MPI_RPC_ADDR 0x334 #define HW_ATL_FW2X_MPI_CONTROL_ADDR 0x368 #define HW_ATL_FW2X_MPI_CONTROL2_ADDR 0x36C @@ -28,6 +30,42 @@ #define HW_ATL_FW2X_MPI_STATE_ADDR 0x370 #define HW_ATL_FW2X_MPI_STATE2_ADDR 0x374 +#define HW_ATL_FW2X_CAP_SLEEP_PROXY BIT(CAPS_HI_SLEEP_PROXY) +#define HW_ATL_FW2X_CAP_WOL BIT(CAPS_HI_WOL) + +#define HW_ATL_FW2X_CTRL_SLEEP_PROXY BIT(CTRL_SLEEP_PROXY) +#define HW_ATL_FW2X_CTRL_WOL BIT(CTRL_WOL) +#define HW_ATL_FW2X_CTRL_LINK_DROP BIT(CTRL_LINK_DROP) +#define HW_ATL_FW2X_CTRL_PAUSE BIT(CTRL_PAUSE) +#define HW_ATL_FW2X_CTRL_ASYMMETRIC_PAUSE BIT(CTRL_ASYMMETRIC_PAUSE) +#define HW_ATL_FW2X_CTRL_FORCE_RECONNECT BIT(CTRL_FORCE_RECONNECT) + +#define HW_ATL_FW2X_CAP_EEE_1G_MASK BIT(CAPS_HI_1000BASET_FD_EEE) +#define HW_ATL_FW2X_CAP_EEE_2G5_MASK BIT(CAPS_HI_2P5GBASET_FD_EEE) +#define HW_ATL_FW2X_CAP_EEE_5G_MASK BIT(CAPS_HI_5GBASET_FD_EEE) +#define HW_ATL_FW2X_CAP_EEE_10G_MASK BIT(CAPS_HI_10GBASET_FD_EEE) + +#define HAL_ATLANTIC_WOL_FILTERS_COUNT 8 +#define HAL_ATLANTIC_UTILS_FW2X_MSG_WOL 0x0E + +struct __packed fw2x_msg_wol_pattern { + u8 mask[16]; + u32 crc; +}; + +struct __packed fw2x_msg_wol { + u32 msg_id; + u8 hw_addr[ETH_ALEN]; + u8 magic_packet_enabled; + u8 filter_count; + struct fw2x_msg_wol_pattern filter[HAL_ATLANTIC_WOL_FILTERS_COUNT]; + u8 link_up_enabled; + u8 link_down_enabled; + u16 reserved; + u32 link_up_timeout; + u32 link_down_timeout; +}; + static int aq_fw2x_set_link_speed(struct aq_hw_s *self, u32 speed); static int aq_fw2x_set_state(struct aq_hw_s *self, enum hal_atl_utils_fw_state_e state); @@ -38,8 +76,12 @@ static int aq_fw2x_init(struct aq_hw_s *self) /* check 10 times by 1ms */ AQ_HW_WAIT_FOR(0U != (self->mbox_addr = - aq_hw_read_reg(self, HW_ATL_FW2X_MPI_MBOX_ADDR)), + aq_hw_read_reg(self, HW_ATL_FW2X_MPI_MBOX_ADDR)), 1000U, 10U); + AQ_HW_WAIT_FOR(0U != (self->rpc_addr = + aq_hw_read_reg(self, HW_ATL_FW2X_MPI_RPC_ADDR)), + 1000U, 100U); + return err; } @@ -78,6 +120,38 @@ static enum hw_atl_fw2x_rate link_speed_mask_2fw2x_ratemask(u32 speed) return rate; } +static u32 fw2x_to_eee_mask(u32 speed) +{ + u32 rate = 0; + + if (speed & HW_ATL_FW2X_CAP_EEE_10G_MASK) + rate |= AQ_NIC_RATE_EEE_10G; + if (speed & HW_ATL_FW2X_CAP_EEE_5G_MASK) + rate |= AQ_NIC_RATE_EEE_5G; + if (speed & HW_ATL_FW2X_CAP_EEE_2G5_MASK) + rate |= AQ_NIC_RATE_EEE_2GS; + if (speed & HW_ATL_FW2X_CAP_EEE_1G_MASK) + rate |= AQ_NIC_RATE_EEE_1G; + + return rate; +} + +static u32 eee_mask_to_fw2x(u32 speed) +{ + u32 rate = 0; + + if (speed & AQ_NIC_RATE_EEE_10G) + rate |= HW_ATL_FW2X_CAP_EEE_10G_MASK; + if (speed & AQ_NIC_RATE_EEE_5G) + rate |= HW_ATL_FW2X_CAP_EEE_5G_MASK; + if (speed & AQ_NIC_RATE_EEE_2GS) + rate |= HW_ATL_FW2X_CAP_EEE_2G5_MASK; + if (speed & AQ_NIC_RATE_EEE_1G) + rate |= HW_ATL_FW2X_CAP_EEE_1G_MASK; + + return rate; +} + static int aq_fw2x_set_link_speed(struct aq_hw_s *self, u32 speed) { u32 val = link_speed_mask_2fw2x_ratemask(speed); @@ -100,14 +174,27 @@ static void aq_fw2x_set_mpi_flow_control(struct aq_hw_s *self, u32 *mpi_state) *mpi_state &= ~BIT(CAPS_HI_ASYMMETRIC_PAUSE); } +static void aq_fw2x_upd_eee_rate_bits(struct aq_hw_s *self, u32 *mpi_opts, + u32 eee_speeds) +{ + *mpi_opts &= ~(HW_ATL_FW2X_CAP_EEE_1G_MASK | + HW_ATL_FW2X_CAP_EEE_2G5_MASK | + HW_ATL_FW2X_CAP_EEE_5G_MASK | + HW_ATL_FW2X_CAP_EEE_10G_MASK); + + *mpi_opts |= eee_mask_to_fw2x(eee_speeds); +} + static int aq_fw2x_set_state(struct aq_hw_s *self, enum hal_atl_utils_fw_state_e state) { u32 mpi_state = aq_hw_read_reg(self, HW_ATL_FW2X_MPI_CONTROL2_ADDR); + struct aq_nic_cfg_s *cfg = self->aq_nic_cfg; switch (state) { case MPI_INIT: mpi_state &= ~BIT(CAPS_HI_LINK_DROP); + aq_fw2x_upd_eee_rate_bits(self, &mpi_state, cfg->eee_speeds); aq_fw2x_set_mpi_flow_control(self, &mpi_state); break; case MPI_DEINIT: @@ -126,7 +213,7 @@ static int aq_fw2x_update_link_status(struct aq_hw_s *self) { u32 mpi_state = aq_hw_read_reg(self, HW_ATL_FW2X_MPI_STATE_ADDR); u32 speed = mpi_state & (FW2X_RATE_100M | FW2X_RATE_1G | - FW2X_RATE_2G5 | FW2X_RATE_5G | FW2X_RATE_10G); + FW2X_RATE_2G5 | FW2X_RATE_5G | FW2X_RATE_10G); struct aq_hw_link_status_s *link_status = &self->aq_link_status; if (speed) { @@ -175,9 +262,7 @@ static int aq_fw2x_get_mac_permanent(struct aq_hw_s *self, u8 *mac) get_random_bytes(&rnd, sizeof(unsigned int)); - l = 0xE3000000U - | (0xFFFFU & rnd) - | (0x00 << 16); + l = 0xE3000000U | (0xFFFFU & rnd) | (0x00 << 16); h = 0x8001300EU; mac[5] = (u8)(0xFFU & l); @@ -194,7 +279,7 @@ static int aq_fw2x_get_mac_permanent(struct aq_hw_s *self, u8 *mac) return err; } -static int aq_fw2x_update_stats(struct aq_hw_s *self) +int aq_fw2x_update_stats(struct aq_hw_s *self) { int err = 0; u32 mpi_opts = aq_hw_read_reg(self, HW_ATL_FW2X_MPI_CONTROL2_ADDR); @@ -207,7 +292,7 @@ static int aq_fw2x_update_stats(struct aq_hw_s *self) /* Wait FW to report back */ AQ_HW_WAIT_FOR(orig_stats_val != (aq_hw_read_reg(self, HW_ATL_FW2X_MPI_STATE2_ADDR) & - BIT(CAPS_HI_STATISTICS)), + BIT(CAPS_HI_STATISTICS)), 1U, 10000U); if (err) return err; @@ -215,6 +300,135 @@ static int aq_fw2x_update_stats(struct aq_hw_s *self) return hw_atl_utils_update_stats(self); } +static int aq_fw2x_set_sleep_proxy(struct aq_hw_s *self, u8 *mac) +{ + struct hw_atl_utils_fw_rpc *rpc = NULL; + struct offload_info *cfg = NULL; + unsigned int rpc_size = 0U; + u32 mpi_opts; + int err = 0; + + rpc_size = sizeof(rpc->msg_id) + sizeof(*cfg); + + err = hw_atl_utils_fw_rpc_wait(self, &rpc); + if (err < 0) + goto err_exit; + + memset(rpc, 0, rpc_size); + cfg = (struct offload_info *)(&rpc->msg_id + 1); + + memcpy(cfg->mac_addr, mac, ETH_ALEN); + cfg->len = sizeof(*cfg); + + /* Clear bit 0x36C.23 and 0x36C.22 */ + mpi_opts = aq_hw_read_reg(self, HW_ATL_FW2X_MPI_CONTROL2_ADDR); + mpi_opts &= ~HW_ATL_FW2X_CTRL_SLEEP_PROXY; + mpi_opts &= ~HW_ATL_FW2X_CTRL_LINK_DROP; + + aq_hw_write_reg(self, HW_ATL_FW2X_MPI_CONTROL2_ADDR, mpi_opts); + + err = hw_atl_utils_fw_rpc_call(self, rpc_size); + if (err < 0) + goto err_exit; + + /* Set bit 0x36C.23 */ + mpi_opts |= HW_ATL_FW2X_CTRL_SLEEP_PROXY; + aq_hw_write_reg(self, HW_ATL_FW2X_MPI_CONTROL2_ADDR, mpi_opts); + + AQ_HW_WAIT_FOR((aq_hw_read_reg(self, HW_ATL_FW2X_MPI_STATE2_ADDR) & + HW_ATL_FW2X_CTRL_SLEEP_PROXY), 1U, 10000U); + +err_exit: + return err; +} + +static int aq_fw2x_set_wol_params(struct aq_hw_s *self, u8 *mac) +{ + struct hw_atl_utils_fw_rpc *rpc = NULL; + struct fw2x_msg_wol *msg = NULL; + u32 mpi_opts; + int err = 0; + + err = hw_atl_utils_fw_rpc_wait(self, &rpc); + if (err < 0) + goto err_exit; + + msg = (struct fw2x_msg_wol *)rpc; + + msg->msg_id = HAL_ATLANTIC_UTILS_FW2X_MSG_WOL; + msg->magic_packet_enabled = true; + memcpy(msg->hw_addr, mac, ETH_ALEN); + + mpi_opts = aq_hw_read_reg(self, HW_ATL_FW2X_MPI_CONTROL2_ADDR); + mpi_opts &= ~(HW_ATL_FW2X_CTRL_SLEEP_PROXY | HW_ATL_FW2X_CTRL_WOL); + + aq_hw_write_reg(self, HW_ATL_FW2X_MPI_CONTROL2_ADDR, mpi_opts); + + err = hw_atl_utils_fw_rpc_call(self, sizeof(*msg)); + if (err < 0) + goto err_exit; + + /* Set bit 0x36C.24 */ + mpi_opts |= HW_ATL_FW2X_CTRL_WOL; + aq_hw_write_reg(self, HW_ATL_FW2X_MPI_CONTROL2_ADDR, mpi_opts); + + AQ_HW_WAIT_FOR((aq_hw_read_reg(self, HW_ATL_FW2X_MPI_STATE2_ADDR) & + HW_ATL_FW2X_CTRL_WOL), 1U, 10000U); + +err_exit: + return err; +} + +static int aq_fw2x_set_power(struct aq_hw_s *self, unsigned int power_state, + u8 *mac) +{ + int err = 0; + + if (self->aq_nic_cfg->wol & AQ_NIC_WOL_ENABLED) { + err = aq_fw2x_set_sleep_proxy(self, mac); + if (err < 0) + goto err_exit; + err = aq_fw2x_set_wol_params(self, mac); + } + +err_exit: + return err; +} + +static int aq_fw2x_set_eee_rate(struct aq_hw_s *self, u32 speed) +{ + u32 mpi_opts = aq_hw_read_reg(self, HW_ATL_FW2X_MPI_CONTROL2_ADDR); + + aq_fw2x_upd_eee_rate_bits(self, &mpi_opts, speed); + + aq_hw_write_reg(self, HW_ATL_FW2X_MPI_CONTROL2_ADDR, mpi_opts); + + return 0; +} + +static int aq_fw2x_get_eee_rate(struct aq_hw_s *self, u32 *rate, + u32 *supported_rates) +{ + u32 mpi_state; + u32 caps_hi; + int err = 0; + u32 addr = self->mbox_addr + offsetof(struct hw_atl_utils_mbox, info) + + offsetof(struct hw_aq_info, caps_hi); + + err = hw_atl_utils_fw_downld_dwords(self, addr, &caps_hi, + sizeof(caps_hi) / sizeof(u32)); + + if (err) + return err; + + *supported_rates = fw2x_to_eee_mask(caps_hi); + + mpi_state = aq_hw_read_reg(self, HW_ATL_FW2X_MPI_STATE2_ADDR); + *rate = fw2x_to_eee_mask(mpi_state); + + return err; +} + static int aq_fw2x_renegotiate(struct aq_hw_s *self) { u32 mpi_opts = aq_hw_read_reg(self, HW_ATL_FW2X_MPI_CONTROL2_ADDR); @@ -247,5 +461,8 @@ const struct aq_fw_ops aq_fw_2x_ops = { .set_state = aq_fw2x_set_state, .update_link_status = aq_fw2x_update_link_status, .update_stats = aq_fw2x_update_stats, - .set_flow_control = aq_fw2x_set_flow_control, + .set_power = aq_fw2x_set_power, + .set_eee_rate = aq_fw2x_set_eee_rate, + .get_eee_rate = aq_fw2x_get_eee_rate, + .set_flow_control = aq_fw2x_set_flow_control, }; diff --git a/drivers/net/ethernet/aquantia/atlantic/ver.h b/drivers/net/ethernet/aquantia/atlantic/ver.h index 94efc6477bdc..b48260114da3 100644 --- a/drivers/net/ethernet/aquantia/atlantic/ver.h +++ b/drivers/net/ethernet/aquantia/atlantic/ver.h @@ -12,7 +12,7 @@ #define NIC_MAJOR_DRIVER_VERSION 2 #define NIC_MINOR_DRIVER_VERSION 0 -#define NIC_BUILD_DRIVER_VERSION 3 +#define NIC_BUILD_DRIVER_VERSION 4 #define NIC_REVISION_DRIVER_VERSION 0 #define AQ_CFG_DRV_VERSION_SUFFIX "-kern" diff --git a/drivers/net/ethernet/atheros/atlx/atl1.c b/drivers/net/ethernet/atheros/atlx/atl1.c index b81fbf119bce..63edc5706c09 100644 --- a/drivers/net/ethernet/atheros/atlx/atl1.c +++ b/drivers/net/ethernet/atheros/atlx/atl1.c @@ -63,7 +63,6 @@ #include <linux/jiffies.h> #include <linux/mii.h> #include <linux/module.h> -#include <linux/moduleparam.h> #include <linux/net.h> #include <linux/netdevice.h> #include <linux/pci.h> @@ -3278,7 +3277,6 @@ static int atl1_set_link_ksettings(struct net_device *netdev, u16 phy_data; int ret_val = 0; u16 old_media_type = hw->media_type; - u32 advertising; if (netif_running(adapter->netdev)) { if (netif_msg_link(adapter)) @@ -3312,25 +3310,7 @@ static int atl1_set_link_ksettings(struct net_device *netdev, hw->media_type = MEDIA_TYPE_10M_HALF; } } - switch (hw->media_type) { - case MEDIA_TYPE_AUTO_SENSOR: - advertising = - ADVERTISED_10baseT_Half | - ADVERTISED_10baseT_Full | - ADVERTISED_100baseT_Half | - ADVERTISED_100baseT_Full | - ADVERTISED_1000baseT_Full | - ADVERTISED_Autoneg | ADVERTISED_TP; - break; - case MEDIA_TYPE_1000M_FULL: - advertising = - ADVERTISED_1000baseT_Full | - ADVERTISED_Autoneg | ADVERTISED_TP; - break; - default: - advertising = 0; - break; - } + if (atl1_phy_setup_autoneg_adv(hw)) { ret_val = -EINVAL; if (netif_msg_link(adapter)) diff --git a/drivers/net/ethernet/aurora/nb8800.c b/drivers/net/ethernet/aurora/nb8800.c index c8d1f8fa4713..6f56276015a4 100644 --- a/drivers/net/ethernet/aurora/nb8800.c +++ b/drivers/net/ethernet/aurora/nb8800.c @@ -935,18 +935,11 @@ static void nb8800_pause_adv(struct net_device *dev) { struct nb8800_priv *priv = netdev_priv(dev); struct phy_device *phydev = dev->phydev; - u32 adv = 0; if (!phydev) return; - if (priv->pause_rx) - adv |= ADVERTISED_Pause | ADVERTISED_Asym_Pause; - if (priv->pause_tx) - adv ^= ADVERTISED_Asym_Pause; - - phydev->supported |= adv; - phydev->advertising |= adv; + phy_set_asym_pause(phydev, priv->pause_rx, priv->pause_tx); } static int nb8800_open(struct net_device *dev) diff --git a/drivers/net/ethernet/broadcom/bcm63xx_enet.c b/drivers/net/ethernet/broadcom/bcm63xx_enet.c index 897302adc38e..6bae973d4dce 100644 --- a/drivers/net/ethernet/broadcom/bcm63xx_enet.c +++ b/drivers/net/ethernet/broadcom/bcm63xx_enet.c @@ -568,12 +568,13 @@ static irqreturn_t bcm_enet_isr_dma(int irq, void *dev_id) /* * tx request callback */ -static int bcm_enet_start_xmit(struct sk_buff *skb, struct net_device *dev) +static netdev_tx_t +bcm_enet_start_xmit(struct sk_buff *skb, struct net_device *dev) { struct bcm_enet_priv *priv; struct bcm_enet_desc *desc; u32 len_stat; - int ret; + netdev_tx_t ret; priv = netdev_priv(dev); @@ -890,19 +891,10 @@ static int bcm_enet_open(struct net_device *dev) } /* mask with MAC supported features */ - phydev->supported &= (SUPPORTED_10baseT_Half | - SUPPORTED_10baseT_Full | - SUPPORTED_100baseT_Half | - SUPPORTED_100baseT_Full | - SUPPORTED_Autoneg | - SUPPORTED_Pause | - SUPPORTED_MII); - phydev->advertising = phydev->supported; - - if (priv->pause_auto && priv->pause_rx && priv->pause_tx) - phydev->advertising |= SUPPORTED_Pause; - else - phydev->advertising &= ~SUPPORTED_Pause; + phy_support_sym_pause(phydev); + phy_set_max_speed(phydev, SPEED_100); + phy_set_sym_pause(phydev, priv->pause_rx, priv->pause_rx, + priv->pause_auto); phy_attached_info(phydev); diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h index 0e508e5defce..142bc11b9fbb 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h @@ -494,6 +494,7 @@ int bnx2x_get_vf_config(struct net_device *dev, int vf, int bnx2x_set_vf_mac(struct net_device *dev, int queue, u8 *mac); int bnx2x_set_vf_vlan(struct net_device *netdev, int vf, u16 vlan, u8 qos, __be16 vlan_proto); +int bnx2x_set_vf_spoofchk(struct net_device *dev, int idx, bool val); /* select_queue callback */ u16 bnx2x_select_queue(struct net_device *dev, struct sk_buff *skb, diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c index 71362b7f6040..40093d88353f 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c @@ -3536,6 +3536,16 @@ static void bnx2x_drv_info_iscsi_stat(struct bnx2x *bp) */ static void bnx2x_config_mf_bw(struct bnx2x *bp) { + /* Workaround for MFW bug. + * MFW is not supposed to generate BW attention in + * single function mode. + */ + if (!IS_MF(bp)) { + DP(BNX2X_MSG_MCP, + "Ignoring MF BW config in single function mode\n"); + return; + } + if (bp->link_vars.link_up) { bnx2x_cmng_fns_init(bp, true, CMNG_FNS_MINMAX); bnx2x_link_sync_notify(bp); @@ -12894,19 +12904,6 @@ static int bnx2x_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) } } -#ifdef CONFIG_NET_POLL_CONTROLLER -static void poll_bnx2x(struct net_device *dev) -{ - struct bnx2x *bp = netdev_priv(dev); - int i; - - for_each_eth_queue(bp, i) { - struct bnx2x_fastpath *fp = &bp->fp[i]; - napi_schedule(&bnx2x_fp(bp, fp->index, napi)); - } -} -#endif - static int bnx2x_validate_addr(struct net_device *dev) { struct bnx2x *bp = netdev_priv(dev); @@ -13113,14 +13110,12 @@ static const struct net_device_ops bnx2x_netdev_ops = { .ndo_tx_timeout = bnx2x_tx_timeout, .ndo_vlan_rx_add_vid = bnx2x_vlan_rx_add_vid, .ndo_vlan_rx_kill_vid = bnx2x_vlan_rx_kill_vid, -#ifdef CONFIG_NET_POLL_CONTROLLER - .ndo_poll_controller = poll_bnx2x, -#endif .ndo_setup_tc = __bnx2x_setup_tc, #ifdef CONFIG_BNX2X_SRIOV .ndo_set_vf_mac = bnx2x_set_vf_mac, .ndo_set_vf_vlan = bnx2x_set_vf_vlan, .ndo_get_vf_config = bnx2x_get_vf_config, + .ndo_set_vf_spoofchk = bnx2x_set_vf_spoofchk, #endif #ifdef NETDEV_FCOE_WWNN .ndo_fcoe_get_wwn = bnx2x_fcoe_get_wwn, diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c index 62da46537734..c835f6c7ecd0 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c @@ -209,7 +209,10 @@ void bnx2x_vfop_qctor_prep(struct bnx2x *bp, */ __set_bit(BNX2X_Q_FLG_TX_SWITCH, &setup_p->flags); __set_bit(BNX2X_Q_FLG_TX_SEC, &setup_p->flags); - __set_bit(BNX2X_Q_FLG_ANTI_SPOOF, &setup_p->flags); + if (vf->spoofchk) + __set_bit(BNX2X_Q_FLG_ANTI_SPOOF, &setup_p->flags); + else + __clear_bit(BNX2X_Q_FLG_ANTI_SPOOF, &setup_p->flags); /* Setup-op rx parameters */ if (test_bit(BNX2X_Q_TYPE_HAS_RX, &q_type)) { @@ -1269,6 +1272,8 @@ int bnx2x_iov_init_one(struct bnx2x *bp, int int_mode_param, bnx2x_vf(bp, i, state) = VF_FREE; mutex_init(&bnx2x_vf(bp, i, op_mutex)); bnx2x_vf(bp, i, op_current) = CHANNEL_TLV_NONE; + /* enable spoofchk by default */ + bnx2x_vf(bp, i, spoofchk) = 1; } /* re-read the IGU CAM for VFs - index and abs_vfid must be set */ @@ -2632,7 +2637,8 @@ int bnx2x_get_vf_config(struct net_device *dev, int vfidx, ivi->qos = 0; ivi->max_tx_rate = 10000; /* always 10G. TBA take from link struct */ ivi->min_tx_rate = 0; - ivi->spoofchk = 1; /*always enabled */ + ivi->spoofchk = vf->spoofchk ? 1 : 0; + ivi->linkstate = vf->link_cfg; if (vf->state == VF_ENABLED) { /* mac and vlan are in vlan_mac objects */ if (bnx2x_validate_vf_sp_objs(bp, vf, false)) { @@ -2950,6 +2956,77 @@ out: return rc; } +int bnx2x_set_vf_spoofchk(struct net_device *dev, int idx, bool val) +{ + struct bnx2x *bp = netdev_priv(dev); + struct bnx2x_virtf *vf; + int i, rc = 0; + + vf = BP_VF(bp, idx); + if (!vf) + return -EINVAL; + + /* nothing to do */ + if (vf->spoofchk == val) + return 0; + + vf->spoofchk = val ? 1 : 0; + + DP(BNX2X_MSG_IOV, "%s spoofchk for VF %d\n", + val ? "enabling" : "disabling", idx); + + /* is vf initialized and queue set up? */ + if (vf->state != VF_ENABLED || + bnx2x_get_q_logical_state(bp, &bnx2x_leading_vfq(vf, sp_obj)) != + BNX2X_Q_LOGICAL_STATE_ACTIVE) + return rc; + + /* User should be able to see error in system logs */ + if (!bnx2x_validate_vf_sp_objs(bp, vf, true)) + return -EINVAL; + + /* send queue update ramrods to configure spoofchk */ + for_each_vfq(vf, i) { + struct bnx2x_queue_state_params q_params = {NULL}; + struct bnx2x_queue_update_params *update_params; + + q_params.q_obj = &bnx2x_vfq(vf, i, sp_obj); + + /* validate the Q is UP */ + if (bnx2x_get_q_logical_state(bp, q_params.q_obj) != + BNX2X_Q_LOGICAL_STATE_ACTIVE) + continue; + + __set_bit(RAMROD_COMP_WAIT, &q_params.ramrod_flags); + q_params.cmd = BNX2X_Q_CMD_UPDATE; + update_params = &q_params.params.update; + __set_bit(BNX2X_Q_UPDATE_ANTI_SPOOF_CHNG, + &update_params->update_flags); + if (val) { + __set_bit(BNX2X_Q_UPDATE_ANTI_SPOOF, + &update_params->update_flags); + } else { + __clear_bit(BNX2X_Q_UPDATE_ANTI_SPOOF, + &update_params->update_flags); + } + + /* Update the Queue state */ + rc = bnx2x_queue_state_change(bp, &q_params); + if (rc) { + BNX2X_ERR("Failed to %s spoofchk on VF %d - vfq %d\n", + val ? "enable" : "disable", idx, i); + goto out; + } + } +out: + if (!rc) + DP(BNX2X_MSG_IOV, + "%s spoofchk for VF[%d]\n", val ? "Enabled" : "Disabled", + idx); + + return rc; +} + /* crc is the first field in the bulletin board. Compute the crc over the * entire bulletin board excluding the crc field itself. Use the length field * as the Bulletin Board was posted by a PF with possibly a different version diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.h index eb814c65152f..b6ebd92ec565 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.h +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.h @@ -142,6 +142,8 @@ struct bnx2x_virtf { bool flr_clnup_stage; /* true during flr cleanup */ bool malicious; /* true if FW indicated so, until FLR */ + /* 1(true) if spoof check is enabled */ + u8 spoofchk; /* dma */ dma_addr_t fw_stat_map; diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index cecbb1d1f587..61957b0bbd8c 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -7672,21 +7672,6 @@ static void bnxt_tx_timeout(struct net_device *dev) bnxt_queue_sp_work(bp); } -#ifdef CONFIG_NET_POLL_CONTROLLER -static void bnxt_poll_controller(struct net_device *dev) -{ - struct bnxt *bp = netdev_priv(dev); - int i; - - /* Only process tx rings/combined rings in netpoll mode. */ - for (i = 0; i < bp->tx_nr_rings; i++) { - struct bnxt_tx_ring_info *txr = &bp->tx_ring[i]; - - napi_schedule(&txr->bnapi->napi); - } -} -#endif - static void bnxt_timer(struct timer_list *t) { struct bnxt *bp = from_timer(bp, t, timer); @@ -8027,7 +8012,7 @@ static int bnxt_change_mac_addr(struct net_device *dev, void *p) if (ether_addr_equal(addr->sa_data, dev->dev_addr)) return 0; - rc = bnxt_approve_mac(bp, addr->sa_data); + rc = bnxt_approve_mac(bp, addr->sa_data, true); if (rc) return rc; @@ -8520,9 +8505,6 @@ static const struct net_device_ops bnxt_netdev_ops = { .ndo_set_vf_spoofchk = bnxt_set_vf_spoofchk, .ndo_set_vf_trust = bnxt_set_vf_trust, #endif -#ifdef CONFIG_NET_POLL_CONTROLLER - .ndo_poll_controller = bnxt_poll_controller, -#endif .ndo_setup_tc = bnxt_setup_tc, #ifdef CONFIG_RFS_ACCEL .ndo_rx_flow_steer = bnxt_rx_flow_steer, @@ -8827,14 +8809,19 @@ static int bnxt_init_mac_addr(struct bnxt *bp) } else { #ifdef CONFIG_BNXT_SRIOV struct bnxt_vf_info *vf = &bp->vf; + bool strict_approval = true; if (is_valid_ether_addr(vf->mac_addr)) { /* overwrite netdev dev_addr with admin VF MAC */ memcpy(bp->dev->dev_addr, vf->mac_addr, ETH_ALEN); + /* Older PF driver or firmware may not approve this + * correctly. + */ + strict_approval = false; } else { eth_hw_addr_random(bp->dev); } - rc = bnxt_approve_mac(bp, bp->dev->dev_addr); + rc = bnxt_approve_mac(bp, bp->dev->dev_addr, strict_approval); #endif } return rc; diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c index f3b9fbcc705b..790c684f08ab 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c @@ -46,6 +46,9 @@ static int bnxt_hwrm_nvm_req(struct bnxt *bp, u32 param_id, void *msg, } } + if (i == ARRAY_SIZE(nvm_params)) + return -EOPNOTSUPP; + if (nvm_param.dir_type == BNXT_NVM_PORT_CFG) idx = bp->pf.port_id; else if (nvm_param.dir_type == BNXT_NVM_FUNC_CFG) diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c index fcd085a9853a..3962f6fd543c 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c @@ -1104,7 +1104,7 @@ update_vf_mac_exit: mutex_unlock(&bp->hwrm_cmd_lock); } -int bnxt_approve_mac(struct bnxt *bp, u8 *mac) +int bnxt_approve_mac(struct bnxt *bp, u8 *mac, bool strict) { struct hwrm_func_vf_cfg_input req = {0}; int rc = 0; @@ -1122,12 +1122,13 @@ int bnxt_approve_mac(struct bnxt *bp, u8 *mac) memcpy(req.dflt_mac_addr, mac, ETH_ALEN); rc = hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT); mac_done: - if (rc) { + if (rc && strict) { rc = -EADDRNOTAVAIL; netdev_warn(bp->dev, "VF MAC address %pM not approved by the PF\n", mac); + return rc; } - return rc; + return 0; } #else @@ -1144,7 +1145,7 @@ void bnxt_update_vf_mac(struct bnxt *bp) { } -int bnxt_approve_mac(struct bnxt *bp, u8 *mac) +int bnxt_approve_mac(struct bnxt *bp, u8 *mac, bool strict) { return 0; } diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.h b/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.h index e9b20cd19881..2eed9eda1195 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.h +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.h @@ -39,5 +39,5 @@ int bnxt_sriov_configure(struct pci_dev *pdev, int num_vfs); void bnxt_sriov_disable(struct bnxt *); void bnxt_hwrm_exec_fwd_req(struct bnxt *); void bnxt_update_vf_mac(struct bnxt *); -int bnxt_approve_mac(struct bnxt *, u8 *); +int bnxt_approve_mac(struct bnxt *, u8 *, bool); #endif diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c index 092c817f8f11..749f63beddd8 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c @@ -75,17 +75,23 @@ static int bnxt_tc_parse_redir(struct bnxt *bp, return 0; } -static void bnxt_tc_parse_vlan(struct bnxt *bp, - struct bnxt_tc_actions *actions, - const struct tc_action *tc_act) +static int bnxt_tc_parse_vlan(struct bnxt *bp, + struct bnxt_tc_actions *actions, + const struct tc_action *tc_act) { - if (tcf_vlan_action(tc_act) == TCA_VLAN_ACT_POP) { + switch (tcf_vlan_action(tc_act)) { + case TCA_VLAN_ACT_POP: actions->flags |= BNXT_TC_ACTION_FLAG_POP_VLAN; - } else if (tcf_vlan_action(tc_act) == TCA_VLAN_ACT_PUSH) { + break; + case TCA_VLAN_ACT_PUSH: actions->flags |= BNXT_TC_ACTION_FLAG_PUSH_VLAN; actions->push_vlan_tci = htons(tcf_vlan_push_vid(tc_act)); actions->push_vlan_tpid = tcf_vlan_push_proto(tc_act); + break; + default: + return -EOPNOTSUPP; } + return 0; } static int bnxt_tc_parse_tunnel_set(struct bnxt *bp, @@ -134,7 +140,9 @@ static int bnxt_tc_parse_actions(struct bnxt *bp, /* Push/pop VLAN */ if (is_tcf_vlan(tc_act)) { - bnxt_tc_parse_vlan(bp, actions, tc_act); + rc = bnxt_tc_parse_vlan(bp, actions, tc_act); + if (rc) + return rc; continue; } @@ -181,7 +189,6 @@ static int bnxt_tc_parse_flow(struct bnxt *bp, struct bnxt_tc_flow *flow) { struct flow_dissector *dissector = tc_flow_cmd->dissector; - u16 addr_type = 0; /* KEY_CONTROL and KEY_BASIC are needed for forming a meaningful key */ if ((dissector->used_keys & BIT(FLOW_DISSECTOR_KEY_CONTROL)) == 0 || @@ -191,13 +198,6 @@ static int bnxt_tc_parse_flow(struct bnxt *bp, return -EOPNOTSUPP; } - if (dissector_uses_key(dissector, FLOW_DISSECTOR_KEY_CONTROL)) { - struct flow_dissector_key_control *key = - GET_KEY(tc_flow_cmd, FLOW_DISSECTOR_KEY_CONTROL); - - addr_type = key->addr_type; - } - if (dissector_uses_key(dissector, FLOW_DISSECTOR_KEY_BASIC)) { struct flow_dissector_key_basic *key = GET_KEY(tc_flow_cmd, FLOW_DISSECTOR_KEY_BASIC); @@ -293,13 +293,6 @@ static int bnxt_tc_parse_flow(struct bnxt *bp, flow->l4_mask.icmp.code = mask->code; } - if (dissector_uses_key(dissector, FLOW_DISSECTOR_KEY_ENC_CONTROL)) { - struct flow_dissector_key_control *key = - GET_KEY(tc_flow_cmd, FLOW_DISSECTOR_KEY_ENC_CONTROL); - - addr_type = key->addr_type; - } - if (dissector_uses_key(dissector, FLOW_DISSECTOR_KEY_ENC_IPV4_ADDRS)) { struct flow_dissector_key_ipv4_addrs *key = GET_KEY(tc_flow_cmd, FLOW_DISSECTOR_KEY_ENC_IPV4_ADDRS); diff --git a/drivers/net/ethernet/broadcom/genet/bcmmii.c b/drivers/net/ethernet/broadcom/genet/bcmmii.c index 4241ae928d4a..b756fc79424e 100644 --- a/drivers/net/ethernet/broadcom/genet/bcmmii.c +++ b/drivers/net/ethernet/broadcom/genet/bcmmii.c @@ -214,7 +214,7 @@ int bcmgenet_mii_config(struct net_device *dev, bool init) case PHY_INTERFACE_MODE_MII: phy_name = "external MII"; - phydev->supported &= PHY_BASIC_FEATURES; + phy_set_max_speed(phydev, SPEED_100); bcmgenet_sys_writel(priv, PORT_MODE_EXT_EPHY, SYS_PORT_CTRL); break; @@ -226,11 +226,10 @@ int bcmgenet_mii_config(struct net_device *dev, bool init) * capabilities, use that knowledge to also configure the * Reverse MII interface correctly. */ - if ((dev->phydev->supported & PHY_BASIC_FEATURES) == - PHY_BASIC_FEATURES) - port_ctrl = PORT_MODE_EXT_RVMII_25; - else + if (dev->phydev->supported & PHY_1000BT_FEATURES) port_ctrl = PORT_MODE_EXT_RVMII_50; + else + port_ctrl = PORT_MODE_EXT_RVMII_25; bcmgenet_sys_writel(priv, port_ctrl, SYS_PORT_CTRL); break; diff --git a/drivers/net/ethernet/broadcom/sb1250-mac.c b/drivers/net/ethernet/broadcom/sb1250-mac.c index ef4a0c326736..5db9f4158e62 100644 --- a/drivers/net/ethernet/broadcom/sb1250-mac.c +++ b/drivers/net/ethernet/broadcom/sb1250-mac.c @@ -156,7 +156,7 @@ enum sbmac_state { (d)->sbdma_dscrtable : (d)->f+1) -#define NUMCACHEBLKS(x) (((x)+SMP_CACHE_BYTES-1)/SMP_CACHE_BYTES) +#define NUMCACHEBLKS(x) DIV_ROUND_UP(x, SMP_CACHE_BYTES) #define SBMAC_MAX_TXDESCR 256 #define SBMAC_MAX_RXDESCR 256 @@ -299,7 +299,7 @@ static enum sbmac_state sbmac_set_channel_state(struct sbmac_softc *, static void sbmac_promiscuous_mode(struct sbmac_softc *sc, int onoff); static uint64_t sbmac_addr2reg(unsigned char *ptr); static irqreturn_t sbmac_intr(int irq, void *dev_instance); -static int sbmac_start_tx(struct sk_buff *skb, struct net_device *dev); +static netdev_tx_t sbmac_start_tx(struct sk_buff *skb, struct net_device *dev); static void sbmac_setmulti(struct sbmac_softc *sc); static int sbmac_init(struct platform_device *pldev, long long base); static int sbmac_set_speed(struct sbmac_softc *s, enum sbmac_speed speed); @@ -2028,7 +2028,7 @@ static irqreturn_t sbmac_intr(int irq,void *dev_instance) * Return value: * nothing ********************************************************************* */ -static int sbmac_start_tx(struct sk_buff *skb, struct net_device *dev) +static netdev_tx_t sbmac_start_tx(struct sk_buff *skb, struct net_device *dev) { struct sbmac_softc *sc = netdev_priv(dev); unsigned long flags; @@ -2357,21 +2357,11 @@ static int sbmac_mii_probe(struct net_device *dev) } /* Remove any features not supported by the controller */ - phy_dev->supported &= SUPPORTED_10baseT_Half | - SUPPORTED_10baseT_Full | - SUPPORTED_100baseT_Half | - SUPPORTED_100baseT_Full | - SUPPORTED_1000baseT_Half | - SUPPORTED_1000baseT_Full | - SUPPORTED_Autoneg | - SUPPORTED_MII | - SUPPORTED_Pause | - SUPPORTED_Asym_Pause; + phy_set_max_speed(phy_dev, SPEED_1000); + phy_support_asym_pause(phy_dev); phy_attached_info(phy_dev); - phy_dev->advertising = phy_dev->supported; - sc->phy_dev = phy_dev; return 0; diff --git a/drivers/net/ethernet/broadcom/tg3.c b/drivers/net/ethernet/broadcom/tg3.c index e6f28c7942ab..89295306f161 100644 --- a/drivers/net/ethernet/broadcom/tg3.c +++ b/drivers/net/ethernet/broadcom/tg3.c @@ -1598,7 +1598,7 @@ static int tg3_mdio_init(struct tg3 *tp) phydev->dev_flags |= PHY_BRCM_EXT_IBND_RX_ENABLE; if (tg3_flag(tp, RGMII_EXT_IBND_TX_EN)) phydev->dev_flags |= PHY_BRCM_EXT_IBND_TX_ENABLE; - /* fallthru */ + /* fall through */ case PHY_ID_RTL8211C: phydev->interface = PHY_INTERFACE_MODE_RGMII; break; @@ -2122,16 +2122,14 @@ static int tg3_phy_init(struct tg3 *tp) case PHY_INTERFACE_MODE_GMII: case PHY_INTERFACE_MODE_RGMII: if (!(tp->phy_flags & TG3_PHYFLG_10_100_ONLY)) { - phydev->supported &= (PHY_GBIT_FEATURES | - SUPPORTED_Pause | - SUPPORTED_Asym_Pause); + phy_set_max_speed(phydev, SPEED_1000); + phy_support_asym_pause(phydev); break; } - /* fallthru */ + /* fall through */ case PHY_INTERFACE_MODE_MII: - phydev->supported &= (PHY_BASIC_FEATURES | - SUPPORTED_Pause | - SUPPORTED_Asym_Pause); + phy_set_max_speed(phydev, SPEED_100); + phy_support_asym_pause(phydev); break; default: phy_disconnect(mdiobus_get_phy(tp->mdio_bus, tp->phy_addr)); @@ -2140,8 +2138,6 @@ static int tg3_phy_init(struct tg3 *tp) tp->phy_flags |= TG3_PHYFLG_IS_CONNECTED; - phydev->advertising = phydev->supported; - phy_attached_info(phydev); return 0; @@ -5215,7 +5211,7 @@ static int tg3_fiber_aneg_smachine(struct tg3 *tp, if (ap->flags & (MR_AN_ENABLE | MR_RESTART_AN)) ap->state = ANEG_STATE_AN_ENABLE; - /* fallthru */ + /* fall through */ case ANEG_STATE_AN_ENABLE: ap->flags &= ~(MR_AN_COMPLETE | MR_PAGE_RX); if (ap->flags & MR_AN_ENABLE) { @@ -5245,7 +5241,7 @@ static int tg3_fiber_aneg_smachine(struct tg3 *tp, ret = ANEG_TIMER_ENAB; ap->state = ANEG_STATE_RESTART; - /* fallthru */ + /* fall through */ case ANEG_STATE_RESTART: delta = ap->cur_time - ap->link_time; if (delta > ANEG_STATE_SETTLE_TIME) @@ -5288,7 +5284,7 @@ static int tg3_fiber_aneg_smachine(struct tg3 *tp, ap->state = ANEG_STATE_ACK_DETECT; - /* fallthru */ + /* fall through */ case ANEG_STATE_ACK_DETECT: if (ap->ack_match != 0) { if ((ap->rxconfig & ~ANEG_CFG_ACK) == @@ -12496,31 +12492,24 @@ static int tg3_set_pauseparam(struct net_device *dev, struct ethtool_pauseparam tg3_warn_mgmt_link_flap(tp); if (tg3_flag(tp, USE_PHYLIB)) { - u32 newadv; struct phy_device *phydev; phydev = mdiobus_get_phy(tp->mdio_bus, tp->phy_addr); - if (!(phydev->supported & SUPPORTED_Pause) || - (!(phydev->supported & SUPPORTED_Asym_Pause) && - (epause->rx_pause != epause->tx_pause))) + if (!phy_validate_pause(phydev, epause)) return -EINVAL; tp->link_config.flowctrl = 0; + phy_set_asym_pause(phydev, epause->rx_pause, epause->tx_pause); if (epause->rx_pause) { tp->link_config.flowctrl |= FLOW_CTRL_RX; if (epause->tx_pause) { tp->link_config.flowctrl |= FLOW_CTRL_TX; - newadv = ADVERTISED_Pause; - } else - newadv = ADVERTISED_Pause | - ADVERTISED_Asym_Pause; + } } else if (epause->tx_pause) { tp->link_config.flowctrl |= FLOW_CTRL_TX; - newadv = ADVERTISED_Asym_Pause; - } else - newadv = 0; + } if (epause->autoneg) tg3_flag_set(tp, PAUSE_AUTONEG); @@ -12528,33 +12517,19 @@ static int tg3_set_pauseparam(struct net_device *dev, struct ethtool_pauseparam tg3_flag_clear(tp, PAUSE_AUTONEG); if (tp->phy_flags & TG3_PHYFLG_IS_CONNECTED) { - u32 oldadv = phydev->advertising & - (ADVERTISED_Pause | ADVERTISED_Asym_Pause); - if (oldadv != newadv) { - phydev->advertising &= - ~(ADVERTISED_Pause | - ADVERTISED_Asym_Pause); - phydev->advertising |= newadv; - if (phydev->autoneg) { - /* - * Always renegotiate the link to - * inform our link partner of our - * flow control settings, even if the - * flow control is forced. Let - * tg3_adjust_link() do the final - * flow control setup. - */ - return phy_start_aneg(phydev); - } + if (phydev->autoneg) { + /* phy_set_asym_pause() will + * renegotiate the link to inform our + * link partner of our flow control + * settings, even if the flow control + * is forced. Let tg3_adjust_link() + * do the final flow control setup. + */ + return 0; } if (!epause->autoneg) tg3_setup_flow_control(tp, 0, 0); - } else { - tp->link_config.advertising &= - ~(ADVERTISED_Pause | - ADVERTISED_Asym_Pause); - tp->link_config.advertising |= newadv; } } else { int irq_sync = 0; @@ -14013,7 +13988,7 @@ static int tg3_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) case SIOCGMIIPHY: data->phy_id = tp->phy_addr; - /* fallthru */ + /* fall through */ case SIOCGMIIREG: { u32 mii_regval; diff --git a/drivers/net/ethernet/brocade/bna/bna_enet.c b/drivers/net/ethernet/brocade/bna/bna_enet.c index bba81735ce87..6d2d4527357c 100644 --- a/drivers/net/ethernet/brocade/bna/bna_enet.c +++ b/drivers/net/ethernet/brocade/bna/bna_enet.c @@ -1797,7 +1797,7 @@ bna_ucam_mod_init(struct bna_ucam_mod *ucam_mod, struct bna *bna, /* A separate queue to allow synchronous setting of a list of MACs */ INIT_LIST_HEAD(&ucam_mod->del_q); - for (i = i; i < (bna->ioceth.attr.num_ucmac * 2); i++) + for (; i < (bna->ioceth.attr.num_ucmac * 2); i++) list_add_tail(&ucam_mod->ucmac[i].qe, &ucam_mod->del_q); ucam_mod->bna = bna; @@ -1832,7 +1832,7 @@ bna_mcam_mod_init(struct bna_mcam_mod *mcam_mod, struct bna *bna, /* A separate queue to allow synchronous setting of a list of MACs */ INIT_LIST_HEAD(&mcam_mod->del_q); - for (i = i; i < (bna->ioceth.attr.num_mcmac * 2); i++) + for (; i < (bna->ioceth.attr.num_mcmac * 2); i++) list_add_tail(&mcam_mod->mcmac[i].qe, &mcam_mod->del_q); mcam_mod->bna = bna; diff --git a/drivers/net/ethernet/cadence/macb_main.c b/drivers/net/ethernet/cadence/macb_main.c index 16e4ef7d7185..0acaef3ef548 100644 --- a/drivers/net/ethernet/cadence/macb_main.c +++ b/drivers/net/ethernet/cadence/macb_main.c @@ -544,14 +544,13 @@ static int macb_mii_probe(struct net_device *dev) /* mask with MAC supported features */ if (macb_is_gem(bp) && bp->caps & MACB_CAPS_GIGABIT_MODE_AVAILABLE) - phydev->supported &= PHY_GBIT_FEATURES; + phy_set_max_speed(phydev, SPEED_1000); else - phydev->supported &= PHY_BASIC_FEATURES; + phy_set_max_speed(phydev, SPEED_100); if (bp->caps & MACB_CAPS_NO_GIGABIT_HALF) - phydev->supported &= ~SUPPORTED_1000baseT_Half; - - phydev->advertising = phydev->supported; + phy_remove_link_mode(phydev, + ETHTOOL_LINK_MODE_1000baseT_Half_BIT); bp->link = 0; bp->speed = 0; @@ -2160,6 +2159,7 @@ static void macb_configure_dma(struct macb *bp) else dmacfg &= ~GEM_BIT(TXCOEN); + dmacfg &= ~GEM_BIT(ADDR64); #ifdef CONFIG_ARCH_DMA_ADDR_T_64BIT if (bp->hw_dma_cap & HW_DMA_CAP_64B) dmacfg |= GEM_BIT(ADDR64); @@ -3837,6 +3837,13 @@ static const struct macb_config at91sam9260_config = { .init = macb_init, }; +static const struct macb_config sama5d3macb_config = { + .caps = MACB_CAPS_SG_DISABLED + | MACB_CAPS_USRIO_HAS_CLKEN | MACB_CAPS_USRIO_DEFAULT_IS_MII_GMII, + .clk_init = macb_clk_init, + .init = macb_init, +}; + static const struct macb_config pc302gem_config = { .caps = MACB_CAPS_SG_DISABLED | MACB_CAPS_GIGABIT_MODE_AVAILABLE, .dma_burst_length = 16, @@ -3904,6 +3911,7 @@ static const struct of_device_id macb_dt_ids[] = { { .compatible = "cdns,gem", .data = &pc302gem_config }, { .compatible = "atmel,sama5d2-gem", .data = &sama5d2_config }, { .compatible = "atmel,sama5d3-gem", .data = &sama5d3_config }, + { .compatible = "atmel,sama5d3-macb", .data = &sama5d3macb_config }, { .compatible = "atmel,sama5d4-gem", .data = &sama5d4_config }, { .compatible = "cdns,at91rm9200-emac", .data = &emac_config }, { .compatible = "cdns,emac", .data = &emac_config }, diff --git a/drivers/net/ethernet/cavium/liquidio/cn23xx_vf_device.c b/drivers/net/ethernet/cavium/liquidio/cn23xx_vf_device.c index 962bb62933db..fda49404968c 100644 --- a/drivers/net/ethernet/cavium/liquidio/cn23xx_vf_device.c +++ b/drivers/net/ethernet/cavium/liquidio/cn23xx_vf_device.c @@ -616,7 +616,7 @@ static void cn23xx_disable_vf_interrupt(struct octeon_device *oct, u8 intr_flag) int cn23xx_setup_octeon_vf_device(struct octeon_device *oct) { struct octeon_cn23xx_vf *cn23xx = (struct octeon_cn23xx_vf *)oct->chip; - u32 rings_per_vf, ring_flag; + u32 rings_per_vf; u64 reg_val; if (octeon_map_pci_barx(oct, 0, 0)) @@ -634,8 +634,6 @@ int cn23xx_setup_octeon_vf_device(struct octeon_device *oct) rings_per_vf = reg_val & CN23XX_PKT_INPUT_CTL_RPVF_MASK; - ring_flag = 0; - cn23xx->conf = oct_get_config_info(oct, LIO_23XX); if (!cn23xx->conf) { dev_err(&oct->pci_dev->dev, "%s No Config found for CN23XX\n", diff --git a/drivers/net/ethernet/cavium/liquidio/lio_core.c b/drivers/net/ethernet/cavium/liquidio/lio_core.c index cdc26cae5fea..eb96b0613cf6 100644 --- a/drivers/net/ethernet/cavium/liquidio/lio_core.c +++ b/drivers/net/ethernet/cavium/liquidio/lio_core.c @@ -425,56 +425,73 @@ void octeon_pf_changed_vf_macaddr(struct octeon_device *oct, u8 *mac) */ } +void octeon_schedule_rxq_oom_work(struct octeon_device *oct, + struct octeon_droq *droq) +{ + struct net_device *netdev = oct->props[0].netdev; + struct lio *lio = GET_LIO(netdev); + struct cavium_wq *wq = &lio->rxq_status_wq[droq->q_no]; + + queue_delayed_work(wq->wq, &wq->wk.work, + msecs_to_jiffies(LIO_OOM_POLL_INTERVAL_MS)); +} + static void octnet_poll_check_rxq_oom_status(struct work_struct *work) { struct cavium_wk *wk = (struct cavium_wk *)work; struct lio *lio = (struct lio *)wk->ctxptr; struct octeon_device *oct = lio->oct_dev; - struct octeon_droq *droq; - int q, q_no = 0; + int q_no = wk->ctxul; + struct octeon_droq *droq = oct->droq[q_no]; - if (ifstate_check(lio, LIO_IFSTATE_RUNNING)) { - for (q = 0; q < lio->linfo.num_rxpciq; q++) { - q_no = lio->linfo.rxpciq[q].s.q_no; - droq = oct->droq[q_no]; - if (!droq) - continue; - octeon_droq_check_oom(droq); - } - } - queue_delayed_work(lio->rxq_status_wq.wq, - &lio->rxq_status_wq.wk.work, - msecs_to_jiffies(LIO_OOM_POLL_INTERVAL_MS)); + if (!ifstate_check(lio, LIO_IFSTATE_RUNNING) || !droq) + return; + + if (octeon_retry_droq_refill(droq)) + octeon_schedule_rxq_oom_work(oct, droq); } int setup_rx_oom_poll_fn(struct net_device *netdev) { struct lio *lio = GET_LIO(netdev); struct octeon_device *oct = lio->oct_dev; + struct cavium_wq *wq; + int q, q_no; - lio->rxq_status_wq.wq = alloc_workqueue("rxq-oom-status", - WQ_MEM_RECLAIM, 0); - if (!lio->rxq_status_wq.wq) { - dev_err(&oct->pci_dev->dev, "unable to create cavium rxq oom status wq\n"); - return -ENOMEM; + for (q = 0; q < oct->num_oqs; q++) { + q_no = lio->linfo.rxpciq[q].s.q_no; + wq = &lio->rxq_status_wq[q_no]; + wq->wq = alloc_workqueue("rxq-oom-status", + WQ_MEM_RECLAIM, 0); + if (!wq->wq) { + dev_err(&oct->pci_dev->dev, "unable to create cavium rxq oom status wq\n"); + return -ENOMEM; + } + + INIT_DELAYED_WORK(&wq->wk.work, + octnet_poll_check_rxq_oom_status); + wq->wk.ctxptr = lio; + wq->wk.ctxul = q_no; } - INIT_DELAYED_WORK(&lio->rxq_status_wq.wk.work, - octnet_poll_check_rxq_oom_status); - lio->rxq_status_wq.wk.ctxptr = lio; - queue_delayed_work(lio->rxq_status_wq.wq, - &lio->rxq_status_wq.wk.work, - msecs_to_jiffies(LIO_OOM_POLL_INTERVAL_MS)); + return 0; } void cleanup_rx_oom_poll_fn(struct net_device *netdev) { struct lio *lio = GET_LIO(netdev); - - if (lio->rxq_status_wq.wq) { - cancel_delayed_work_sync(&lio->rxq_status_wq.wk.work); - flush_workqueue(lio->rxq_status_wq.wq); - destroy_workqueue(lio->rxq_status_wq.wq); + struct octeon_device *oct = lio->oct_dev; + struct cavium_wq *wq; + int q_no; + + for (q_no = 0; q_no < oct->num_oqs; q_no++) { + wq = &lio->rxq_status_wq[q_no]; + if (wq->wq) { + cancel_delayed_work_sync(&wq->wk.work); + flush_workqueue(wq->wq); + destroy_workqueue(wq->wq); + wq->wq = NULL; + } } } @@ -1357,6 +1374,69 @@ octnet_nic_stats_callback(struct octeon_device *oct_dev, } } +static int lio_fetch_vf_stats(struct lio *lio) +{ + struct octeon_device *oct_dev = lio->oct_dev; + struct octeon_soft_command *sc; + struct oct_nic_vf_stats_resp *resp; + + int retval; + + /* Alloc soft command */ + sc = (struct octeon_soft_command *) + octeon_alloc_soft_command(oct_dev, + 0, + sizeof(struct oct_nic_vf_stats_resp), + 0); + + if (!sc) { + dev_err(&oct_dev->pci_dev->dev, "Soft command allocation failed\n"); + retval = -ENOMEM; + goto lio_fetch_vf_stats_exit; + } + + resp = (struct oct_nic_vf_stats_resp *)sc->virtrptr; + memset(resp, 0, sizeof(struct oct_nic_vf_stats_resp)); + + init_completion(&sc->complete); + sc->sc_status = OCTEON_REQUEST_PENDING; + + sc->iq_no = lio->linfo.txpciq[0].s.q_no; + + octeon_prepare_soft_command(oct_dev, sc, OPCODE_NIC, + OPCODE_NIC_VF_PORT_STATS, 0, 0, 0); + + retval = octeon_send_soft_command(oct_dev, sc); + if (retval == IQ_SEND_FAILED) { + octeon_free_soft_command(oct_dev, sc); + goto lio_fetch_vf_stats_exit; + } + + retval = + wait_for_sc_completion_timeout(oct_dev, sc, + (2 * LIO_SC_MAX_TMO_MS)); + if (retval) { + dev_err(&oct_dev->pci_dev->dev, + "sc OPCODE_NIC_VF_PORT_STATS command failed\n"); + goto lio_fetch_vf_stats_exit; + } + + if (sc->sc_status != OCTEON_REQUEST_TIMEOUT && !resp->status) { + octeon_swap_8B_data((u64 *)&resp->spoofmac_cnt, + (sizeof(u64)) >> 3); + + if (resp->spoofmac_cnt != 0) { + dev_warn(&oct_dev->pci_dev->dev, + "%llu Spoofed packets detected\n", + resp->spoofmac_cnt); + } + } + WRITE_ONCE(sc->caller_is_done, 1); + +lio_fetch_vf_stats_exit: + return retval; +} + void lio_fetch_stats(struct work_struct *work) { struct cavium_wk *wk = (struct cavium_wk *)work; @@ -1367,6 +1447,17 @@ void lio_fetch_stats(struct work_struct *work) unsigned long time_in_jiffies; int retval; + if (OCTEON_CN23XX_PF(oct_dev)) { + /* report spoofchk every 2 seconds */ + if (!(oct_dev->vfstats_poll % LIO_VFSTATS_POLL) && + (oct_dev->fw_info.app_cap_flags & LIQUIDIO_SPOOFCHK_CAP) && + oct_dev->sriov_info.num_vfs_alloced) { + lio_fetch_vf_stats(lio); + } + + oct_dev->vfstats_poll++; + } + /* Alloc soft command */ sc = (struct octeon_soft_command *) octeon_alloc_soft_command(oct_dev, @@ -1563,3 +1654,151 @@ int liquidio_get_speed(struct lio *lio) return retval; } + +int liquidio_set_fec(struct lio *lio, int on_off) +{ + struct oct_nic_seapi_resp *resp; + struct octeon_soft_command *sc; + struct octeon_device *oct; + union octnet_cmd *ncmd; + int retval; + u32 var; + + oct = lio->oct_dev; + + if (oct->props[lio->ifidx].fec == on_off) + return 0; + + if (!OCTEON_CN23XX_PF(oct)) { + dev_err(&oct->pci_dev->dev, "%s: SET FEC only for PF\n", + __func__); + return -1; + } + + if (oct->speed_boot != 25) { + dev_err(&oct->pci_dev->dev, + "Set FEC only when link speed is 25G during insmod\n"); + return -1; + } + + sc = octeon_alloc_soft_command(oct, OCTNET_CMD_SIZE, + sizeof(struct oct_nic_seapi_resp), 0); + + ncmd = sc->virtdptr; + resp = sc->virtrptr; + memset(resp, 0, sizeof(struct oct_nic_seapi_resp)); + + init_completion(&sc->complete); + sc->sc_status = OCTEON_REQUEST_PENDING; + + ncmd->u64 = 0; + ncmd->s.cmd = SEAPI_CMD_FEC_SET; + ncmd->s.param1 = on_off; + /* SEAPI_CMD_FEC_DISABLE(0) or SEAPI_CMD_FEC_RS(1) */ + + octeon_swap_8B_data((u64 *)ncmd, (OCTNET_CMD_SIZE >> 3)); + + sc->iq_no = lio->linfo.txpciq[0].s.q_no; + + octeon_prepare_soft_command(oct, sc, OPCODE_NIC, + OPCODE_NIC_UBOOT_CTL, 0, 0, 0); + + retval = octeon_send_soft_command(oct, sc); + if (retval == IQ_SEND_FAILED) { + dev_info(&oct->pci_dev->dev, "Failed to send soft command\n"); + octeon_free_soft_command(oct, sc); + return -EIO; + } + + retval = wait_for_sc_completion_timeout(oct, sc, 0); + if (retval) + return (-EIO); + + var = be32_to_cpu(resp->fec_setting); + resp->fec_setting = var; + if (var != on_off) { + dev_err(&oct->pci_dev->dev, + "Setting failed fec= %x, expect %x\n", + var, on_off); + oct->props[lio->ifidx].fec = var; + if (resp->fec_setting == SEAPI_CMD_FEC_SET_RS) + oct->props[lio->ifidx].fec = 1; + else + oct->props[lio->ifidx].fec = 0; + } + + WRITE_ONCE(sc->caller_is_done, true); + + if (oct->props[lio->ifidx].fec != + oct->props[lio->ifidx].fec_boot) { + dev_dbg(&oct->pci_dev->dev, + "Reloade driver to chang fec to %s\n", + oct->props[lio->ifidx].fec ? "on" : "off"); + } + + return retval; +} + +int liquidio_get_fec(struct lio *lio) +{ + struct oct_nic_seapi_resp *resp; + struct octeon_soft_command *sc; + struct octeon_device *oct; + union octnet_cmd *ncmd; + int retval; + u32 var; + + oct = lio->oct_dev; + + sc = octeon_alloc_soft_command(oct, OCTNET_CMD_SIZE, + sizeof(struct oct_nic_seapi_resp), 0); + if (!sc) + return -ENOMEM; + + ncmd = sc->virtdptr; + resp = sc->virtrptr; + memset(resp, 0, sizeof(struct oct_nic_seapi_resp)); + + init_completion(&sc->complete); + sc->sc_status = OCTEON_REQUEST_PENDING; + + ncmd->u64 = 0; + ncmd->s.cmd = SEAPI_CMD_FEC_GET; + + octeon_swap_8B_data((u64 *)ncmd, (OCTNET_CMD_SIZE >> 3)); + + sc->iq_no = lio->linfo.txpciq[0].s.q_no; + + octeon_prepare_soft_command(oct, sc, OPCODE_NIC, + OPCODE_NIC_UBOOT_CTL, 0, 0, 0); + + retval = octeon_send_soft_command(oct, sc); + if (retval == IQ_SEND_FAILED) { + dev_info(&oct->pci_dev->dev, + "%s: Failed to send soft command\n", __func__); + octeon_free_soft_command(oct, sc); + return -EIO; + } + + retval = wait_for_sc_completion_timeout(oct, sc, 0); + if (retval) + return retval; + + var = be32_to_cpu(resp->fec_setting); + resp->fec_setting = var; + if (resp->fec_setting == SEAPI_CMD_FEC_SET_RS) + oct->props[lio->ifidx].fec = 1; + else + oct->props[lio->ifidx].fec = 0; + + WRITE_ONCE(sc->caller_is_done, true); + + if (oct->props[lio->ifidx].fec != + oct->props[lio->ifidx].fec_boot) { + dev_dbg(&oct->pci_dev->dev, + "Reloade driver to chang fec to %s\n", + oct->props[lio->ifidx].fec ? "on" : "off"); + } + + return retval; +} diff --git a/drivers/net/ethernet/cavium/liquidio/lio_ethtool.c b/drivers/net/ethernet/cavium/liquidio/lio_ethtool.c index 46d8379d8c7c..4c3925af53bc 100644 --- a/drivers/net/ethernet/cavium/liquidio/lio_ethtool.c +++ b/drivers/net/ethernet/cavium/liquidio/lio_ethtool.c @@ -244,6 +244,7 @@ static int lio_get_link_ksettings(struct net_device *netdev, linfo->link.s.if_mode == INTERFACE_MODE_XLAUI || linfo->link.s.if_mode == INTERFACE_MODE_XFI) { dev_dbg(&oct->pci_dev->dev, "ecmd->base.transceiver is XCVR_EXTERNAL\n"); + ecmd->base.transceiver = XCVR_EXTERNAL; } else { dev_err(&oct->pci_dev->dev, "Unknown link interface mode: %d\n", linfo->link.s.if_mode); @@ -277,10 +278,12 @@ static int lio_get_link_ksettings(struct net_device *netdev, 10000baseCR_Full); } - if (oct->no_speed_setting == 0) + if (oct->no_speed_setting == 0) { liquidio_get_speed(lio); - else + liquidio_get_fec(lio); + } else { oct->speed_setting = 25; + } if (oct->speed_setting == 10) { ethtool_link_ksettings_add_link_mode @@ -304,6 +307,24 @@ static int lio_get_link_ksettings(struct net_device *netdev, (ecmd, advertising, 25000baseCR_Full); } + + if (oct->no_speed_setting) + break; + + ethtool_link_ksettings_add_link_mode + (ecmd, supported, FEC_RS); + ethtool_link_ksettings_add_link_mode + (ecmd, supported, FEC_NONE); + /*FEC_OFF*/ + if (oct->props[lio->ifidx].fec == 1) { + /* ETHTOOL_FEC_RS */ + ethtool_link_ksettings_add_link_mode + (ecmd, advertising, FEC_RS); + } else { + /* ETHTOOL_FEC_OFF */ + ethtool_link_ksettings_add_link_mode + (ecmd, advertising, FEC_NONE); + } } else { /* VF */ if (linfo->link.s.speed == 10000) { ethtool_link_ksettings_add_link_mode @@ -1115,6 +1136,8 @@ static int lio_reset_queues(struct net_device *netdev, uint32_t num_qs) * steps like updating sriov_info for the octeon device need to be done. */ if (queue_count_update) { + cleanup_rx_oom_poll_fn(netdev); + lio_delete_glists(lio); /* Delete mbox for PF which is SRIOV disabled because sriov_info @@ -1214,6 +1237,11 @@ static int lio_reset_queues(struct net_device *netdev, uint32_t num_qs) return -1; } + if (setup_rx_oom_poll_fn(netdev)) { + dev_err(&oct->pci_dev->dev, "lio_setup_rx_oom_poll_fn failed\n"); + return 1; + } + /* Send firmware the information about new number of queues * if the interface is a VF or a PF that is SRIOV enabled. */ @@ -1713,7 +1741,8 @@ static void lio_vf_get_ethtool_stats(struct net_device *netdev, */ data[i++] = lstats.rx_dropped; /* sum of oct->instr_queue[iq_no]->stats.tx_dropped */ - data[i++] = lstats.tx_dropped; + data[i++] = lstats.tx_dropped + + oct_dev->link_stats.fromhost.fw_err_drop; data[i++] = oct_dev->link_stats.fromwire.fw_total_mcast; data[i++] = oct_dev->link_stats.fromhost.fw_total_mcast_sent; @@ -3021,9 +3050,60 @@ static int lio_set_priv_flags(struct net_device *netdev, u32 flags) return 0; } +static int lio_get_fecparam(struct net_device *netdev, + struct ethtool_fecparam *fec) +{ + struct lio *lio = GET_LIO(netdev); + struct octeon_device *oct = lio->oct_dev; + + fec->active_fec = ETHTOOL_FEC_NONE; + fec->fec = ETHTOOL_FEC_NONE; + + if (oct->subsystem_id == OCTEON_CN2350_25GB_SUBSYS_ID || + oct->subsystem_id == OCTEON_CN2360_25GB_SUBSYS_ID) { + if (oct->no_speed_setting == 1) + return 0; + + liquidio_get_fec(lio); + fec->fec = (ETHTOOL_FEC_RS | ETHTOOL_FEC_OFF); + if (oct->props[lio->ifidx].fec == 1) + fec->active_fec = ETHTOOL_FEC_RS; + else + fec->active_fec = ETHTOOL_FEC_OFF; + } + + return 0; +} + +static int lio_set_fecparam(struct net_device *netdev, + struct ethtool_fecparam *fec) +{ + struct lio *lio = GET_LIO(netdev); + struct octeon_device *oct = lio->oct_dev; + + if (oct->subsystem_id == OCTEON_CN2350_25GB_SUBSYS_ID || + oct->subsystem_id == OCTEON_CN2360_25GB_SUBSYS_ID) { + if (oct->no_speed_setting == 1) + return -EOPNOTSUPP; + + if (fec->fec & ETHTOOL_FEC_OFF) + liquidio_set_fec(lio, 0); + else if (fec->fec & ETHTOOL_FEC_RS) + liquidio_set_fec(lio, 1); + else + return -EOPNOTSUPP; + } else { + return -EOPNOTSUPP; + } + + return 0; +} + static const struct ethtool_ops lio_ethtool_ops = { .get_link_ksettings = lio_get_link_ksettings, .set_link_ksettings = lio_set_link_ksettings, + .get_fecparam = lio_get_fecparam, + .set_fecparam = lio_set_fecparam, .get_link = ethtool_op_get_link, .get_drvinfo = lio_get_drvinfo, .get_ringparam = lio_ethtool_get_ringparam, diff --git a/drivers/net/ethernet/cavium/liquidio/lio_main.c b/drivers/net/ethernet/cavium/liquidio/lio_main.c index e973662c18e2..9d70e5c6157f 100644 --- a/drivers/net/ethernet/cavium/liquidio/lio_main.c +++ b/drivers/net/ethernet/cavium/liquidio/lio_main.c @@ -1239,8 +1239,10 @@ static void send_rx_ctrl_cmd(struct lio *lio, int start_stop) static void liquidio_destroy_nic_device(struct octeon_device *oct, int ifidx) { struct net_device *netdev = oct->props[ifidx].netdev; - struct lio *lio; + struct octeon_device_priv *oct_priv = + (struct octeon_device_priv *)oct->priv; struct napi_struct *napi, *n; + struct lio *lio; if (!netdev) { dev_err(&oct->pci_dev->dev, "%s No netdevice ptr for index %d\n", @@ -1269,6 +1271,8 @@ static void liquidio_destroy_nic_device(struct octeon_device *oct, int ifidx) list_for_each_entry_safe(napi, n, &netdev->napi_list, dev_list) netif_napi_del(napi); + tasklet_enable(&oct_priv->droq_tasklet); + if (atomic_read(&lio->ifstate) & LIO_IFSTATE_REGISTERED) unregister_netdev(netdev); @@ -1805,9 +1809,13 @@ static int liquidio_open(struct net_device *netdev) { struct lio *lio = GET_LIO(netdev); struct octeon_device *oct = lio->oct_dev; + struct octeon_device_priv *oct_priv = + (struct octeon_device_priv *)oct->priv; struct napi_struct *napi, *n; if (oct->props[lio->ifidx].napi_enabled == 0) { + tasklet_disable(&oct_priv->droq_tasklet); + list_for_each_entry_safe(napi, n, &netdev->napi_list, dev_list) napi_enable(napi); @@ -1861,6 +1869,8 @@ static int liquidio_stop(struct net_device *netdev) { struct lio *lio = GET_LIO(netdev); struct octeon_device *oct = lio->oct_dev; + struct octeon_device_priv *oct_priv = + (struct octeon_device_priv *)oct->priv; struct napi_struct *napi, *n; ifstate_reset(lio, LIO_IFSTATE_RUNNING); @@ -1907,6 +1917,8 @@ static int liquidio_stop(struct net_device *netdev) if (OCTEON_CN23XX_PF(oct)) oct->droq[0]->ops.poll_mode = 0; + + tasklet_enable(&oct_priv->droq_tasklet); } dev_info(&oct->pci_dev->dev, "%s interface is stopped\n", netdev->name); @@ -2301,7 +2313,7 @@ static inline int send_nic_timestamp_pkt(struct octeon_device *oct, * @returns whether the packet was transmitted to the device okay or not * (NETDEV_TX_OK or NETDEV_TX_BUSY) */ -static int liquidio_xmit(struct sk_buff *skb, struct net_device *netdev) +static netdev_tx_t liquidio_xmit(struct sk_buff *skb, struct net_device *netdev) { struct lio *lio; struct octnet_buf_free_info *finfo; @@ -2858,6 +2870,62 @@ static int liquidio_set_vf_mac(struct net_device *netdev, int vfidx, u8 *mac) return retval; } +static int liquidio_set_vf_spoofchk(struct net_device *netdev, int vfidx, + bool enable) +{ + struct lio *lio = GET_LIO(netdev); + struct octeon_device *oct = lio->oct_dev; + struct octnic_ctrl_pkt nctrl; + int retval; + + if (!(oct->fw_info.app_cap_flags & LIQUIDIO_SPOOFCHK_CAP)) { + netif_info(lio, drv, lio->netdev, + "firmware does not support spoofchk\n"); + return -EOPNOTSUPP; + } + + if (vfidx < 0 || vfidx >= oct->sriov_info.num_vfs_alloced) { + netif_info(lio, drv, lio->netdev, "Invalid vfidx %d\n", vfidx); + return -EINVAL; + } + + if (enable) { + if (oct->sriov_info.vf_spoofchk[vfidx]) + return 0; + } else { + /* Clear */ + if (!oct->sriov_info.vf_spoofchk[vfidx]) + return 0; + } + + memset(&nctrl, 0, sizeof(struct octnic_ctrl_pkt)); + nctrl.ncmd.s.cmdgroup = OCTNET_CMD_GROUP1; + nctrl.ncmd.s.cmd = OCTNET_CMD_SET_VF_SPOOFCHK; + nctrl.ncmd.s.param1 = + vfidx + 1; /* vfidx is 0 based, + * but vf_num (param1) is 1 based + */ + nctrl.ncmd.s.param2 = enable; + nctrl.ncmd.s.more = 0; + nctrl.iq_no = lio->linfo.txpciq[0].s.q_no; + nctrl.cb_fn = 0; + + retval = octnet_send_nic_ctrl_pkt(oct, &nctrl); + + if (retval) { + netif_info(lio, drv, lio->netdev, + "Failed to set VF %d spoofchk %s\n", vfidx, + enable ? "on" : "off"); + return -1; + } + + oct->sriov_info.vf_spoofchk[vfidx] = enable; + netif_info(lio, drv, lio->netdev, "VF %u spoofchk is %s\n", vfidx, + enable ? "on" : "off"); + + return 0; +} + static int liquidio_set_vf_vlan(struct net_device *netdev, int vfidx, u16 vlan, u8 qos, __be16 vlan_proto) { @@ -2920,6 +2988,8 @@ static int liquidio_get_vf_config(struct net_device *netdev, int vfidx, if (vfidx < 0 || vfidx >= oct->sriov_info.num_vfs_alloced) return -EINVAL; + memset(ivi, 0, sizeof(struct ifla_vf_info)); + ivi->vf = vfidx; macaddr = 2 + (u8 *)&oct->sriov_info.vf_macaddr[vfidx]; ether_addr_copy(&ivi->mac[0], macaddr); @@ -2931,6 +3001,10 @@ static int liquidio_get_vf_config(struct net_device *netdev, int vfidx, else ivi->trusted = false; ivi->linkstate = oct->sriov_info.vf_linkstate[vfidx]; + ivi->spoofchk = oct->sriov_info.vf_spoofchk[vfidx]; + ivi->max_tx_rate = lio->linfo.link.s.speed; + ivi->min_tx_rate = 0; + return 0; } @@ -3180,6 +3254,7 @@ static const struct net_device_ops lionetdevops = { .ndo_set_vf_mac = liquidio_set_vf_mac, .ndo_set_vf_vlan = liquidio_set_vf_vlan, .ndo_get_vf_config = liquidio_get_vf_config, + .ndo_set_vf_spoofchk = liquidio_set_vf_spoofchk, .ndo_set_vf_trust = liquidio_set_vf_trust, .ndo_set_vf_link_state = liquidio_set_vf_link_state, .ndo_get_vf_stats = liquidio_get_vf_stats, @@ -3686,6 +3761,14 @@ static int setup_nic_devices(struct octeon_device *octeon_dev) octeon_dev->speed_setting = 10; } octeon_dev->speed_boot = octeon_dev->speed_setting; + + /* don't read FEC setting if unsupported by f/w (see above) */ + if (octeon_dev->speed_boot == 25 && + !octeon_dev->no_speed_setting) { + liquidio_get_fec(lio); + octeon_dev->props[lio->ifidx].fec_boot = + octeon_dev->props[lio->ifidx].fec; + } } devlink = devlink_alloc(&liquidio_devlink_ops, diff --git a/drivers/net/ethernet/cavium/liquidio/lio_vf_main.c b/drivers/net/ethernet/cavium/liquidio/lio_vf_main.c index fe3d935fa1e0..54b245797d2e 100644 --- a/drivers/net/ethernet/cavium/liquidio/lio_vf_main.c +++ b/drivers/net/ethernet/cavium/liquidio/lio_vf_main.c @@ -444,6 +444,8 @@ static void octeon_pci_flr(struct octeon_device *oct) */ static void octeon_destroy_resources(struct octeon_device *oct) { + struct octeon_device_priv *oct_priv = + (struct octeon_device_priv *)oct->priv; struct msix_entry *msix_entries; int i; @@ -587,6 +589,8 @@ static void octeon_destroy_resources(struct octeon_device *oct) /* Nothing to be done here either */ break; } + + tasklet_kill(&oct_priv->droq_tasklet); } /** @@ -652,6 +656,8 @@ static void send_rx_ctrl_cmd(struct lio *lio, int start_stop) static void liquidio_destroy_nic_device(struct octeon_device *oct, int ifidx) { struct net_device *netdev = oct->props[ifidx].netdev; + struct octeon_device_priv *oct_priv = + (struct octeon_device_priv *)oct->priv; struct napi_struct *napi, *n; struct lio *lio; @@ -681,6 +687,8 @@ static void liquidio_destroy_nic_device(struct octeon_device *oct, int ifidx) list_for_each_entry_safe(napi, n, &netdev->napi_list, dev_list) netif_napi_del(napi); + tasklet_enable(&oct_priv->droq_tasklet); + if (atomic_read(&lio->ifstate) & LIO_IFSTATE_REGISTERED) unregister_netdev(netdev); @@ -898,9 +906,13 @@ static int liquidio_open(struct net_device *netdev) { struct lio *lio = GET_LIO(netdev); struct octeon_device *oct = lio->oct_dev; + struct octeon_device_priv *oct_priv = + (struct octeon_device_priv *)oct->priv; struct napi_struct *napi, *n; if (!oct->props[lio->ifidx].napi_enabled) { + tasklet_disable(&oct_priv->droq_tasklet); + list_for_each_entry_safe(napi, n, &netdev->napi_list, dev_list) napi_enable(napi); @@ -938,6 +950,8 @@ static int liquidio_stop(struct net_device *netdev) { struct lio *lio = GET_LIO(netdev); struct octeon_device *oct = lio->oct_dev; + struct octeon_device_priv *oct_priv = + (struct octeon_device_priv *)oct->priv; struct napi_struct *napi, *n; /* tell Octeon to stop forwarding packets to host */ @@ -967,6 +981,8 @@ static int liquidio_stop(struct net_device *netdev) oct->props[lio->ifidx].napi_enabled = 0; oct->droq[0]->ops.poll_mode = 0; + + tasklet_enable(&oct_priv->droq_tasklet); } cancel_delayed_work_sync(&lio->stats_wk.work); @@ -1135,6 +1151,12 @@ static int liquidio_set_mac(struct net_device *netdev, void *p) return -ENOMEM; } + if (nctrl.sc_status == + FIRMWARE_STATUS_CODE(OCTEON_REQUEST_NO_PERMISSION)) { + dev_err(&oct->pci_dev->dev, "MAC Address change failed: no permission\n"); + return -EPERM; + } + memcpy(netdev->dev_addr, addr->sa_data, netdev->addr_len); ether_addr_copy(((u8 *)&lio->linfo.hw_addr) + 2, addr->sa_data); @@ -1379,7 +1401,7 @@ static int send_nic_timestamp_pkt(struct octeon_device *oct, * @returns whether the packet was transmitted to the device okay or not * (NETDEV_TX_OK or NETDEV_TX_BUSY) */ -static int liquidio_xmit(struct sk_buff *skb, struct net_device *netdev) +static netdev_tx_t liquidio_xmit(struct sk_buff *skb, struct net_device *netdev) { struct octnet_buf_free_info *finfo; union octnic_cmd_setup cmdsetup; @@ -2049,6 +2071,8 @@ static int setup_nic_devices(struct octeon_device *octeon_dev) lio->linfo.link.u64 = resp->cfg_info.linfo.link.u64; lio->linfo.macaddr_is_admin_asgnd = resp->cfg_info.linfo.macaddr_is_admin_asgnd; + lio->linfo.macaddr_spoofchk = + resp->cfg_info.linfo.macaddr_spoofchk; lio->msg_enable = netif_msg_init(debug, DEFAULT_MSG_ENABLE); diff --git a/drivers/net/ethernet/cavium/liquidio/lio_vf_rep.c b/drivers/net/ethernet/cavium/liquidio/lio_vf_rep.c index a9306164dbcd..ea9859e028d4 100644 --- a/drivers/net/ethernet/cavium/liquidio/lio_vf_rep.c +++ b/drivers/net/ethernet/cavium/liquidio/lio_vf_rep.c @@ -27,11 +27,11 @@ #include "octeon_network.h" #include <net/switchdev.h> #include "lio_vf_rep.h" -#include "octeon_network.h" static int lio_vf_rep_open(struct net_device *ndev); static int lio_vf_rep_stop(struct net_device *ndev); -static int lio_vf_rep_pkt_xmit(struct sk_buff *skb, struct net_device *ndev); +static netdev_tx_t lio_vf_rep_pkt_xmit(struct sk_buff *skb, + struct net_device *ndev); static void lio_vf_rep_tx_timeout(struct net_device *netdev); static int lio_vf_rep_phys_port_name(struct net_device *dev, char *buf, size_t len); @@ -362,7 +362,7 @@ lio_vf_rep_packet_sent_callback(struct octeon_device *oct, netif_wake_queue(ndev); } -static int +static netdev_tx_t lio_vf_rep_pkt_xmit(struct sk_buff *skb, struct net_device *ndev) { struct lio_vf_rep_desc *vf_rep = netdev_priv(ndev); diff --git a/drivers/net/ethernet/cavium/liquidio/liquidio_common.h b/drivers/net/ethernet/cavium/liquidio/liquidio_common.h index 0decc7294b4c..a5e0e9f17959 100644 --- a/drivers/net/ethernet/cavium/liquidio/liquidio_common.h +++ b/drivers/net/ethernet/cavium/liquidio/liquidio_common.h @@ -118,6 +118,10 @@ enum octeon_tag_type { /* App specific capabilities from firmware to pf driver */ #define LIQUIDIO_TIME_SYNC_CAP 0x1 #define LIQUIDIO_SWITCHDEV_CAP 0x2 +#define LIQUIDIO_SPOOFCHK_CAP 0x4 + +/* error status return from firmware */ +#define OCTEON_REQUEST_NO_PERMISSION 0xc static inline u32 incr_index(u32 index, u32 count, u32 max) { @@ -241,6 +245,10 @@ static inline void add_sg_size(struct octeon_sg_entry *sg_entry, #define OCTNET_CMD_QUEUE_COUNT_CTL 0x1f +#define OCTNET_CMD_GROUP1 1 +#define OCTNET_CMD_SET_VF_SPOOFCHK 0x1 +#define OCTNET_GROUP1_LAST_CMD OCTNET_CMD_SET_VF_SPOOFCHK + #define OCTNET_CMD_VXLAN_PORT_ADD 0x0 #define OCTNET_CMD_VXLAN_PORT_DEL 0x1 #define OCTNET_CMD_RXCSUM_ENABLE 0x0 @@ -252,9 +260,16 @@ static inline void add_sg_size(struct octeon_sg_entry *sg_entry, #define OCTNET_CMD_FAIL 0x1 +#define SEAPI_CMD_FEC_SET 0x0 +#define SEAPI_CMD_FEC_SET_DISABLE 0x0 +#define SEAPI_CMD_FEC_SET_RS 0x1 +#define SEAPI_CMD_FEC_GET 0x1 + #define SEAPI_CMD_SPEED_SET 0x2 #define SEAPI_CMD_SPEED_GET 0x3 +#define OPCODE_NIC_VF_PORT_STATS 0x22 + #define LIO_CMD_WAIT_TM 100 /* RX(packets coming from wire) Checksum verification flags */ @@ -303,7 +318,8 @@ union octnet_cmd { u64 more:6; /* How many udd words follow the command */ - u64 reserved:29; + u64 cmdgroup:8; + u64 reserved:21; u64 param1:16; @@ -315,7 +331,8 @@ union octnet_cmd { u64 param1:16; - u64 reserved:29; + u64 reserved:21; + u64 cmdgroup:8; u64 more:6; @@ -759,13 +776,17 @@ struct oct_link_info { #ifdef __BIG_ENDIAN_BITFIELD u64 gmxport:16; u64 macaddr_is_admin_asgnd:1; - u64 rsvd:31; + u64 rsvd:13; + u64 macaddr_spoofchk:1; + u64 rsvd1:17; u64 num_txpciq:8; u64 num_rxpciq:8; #else u64 num_rxpciq:8; u64 num_txpciq:8; - u64 rsvd:31; + u64 rsvd1:17; + u64 macaddr_spoofchk:1; + u64 rsvd:13; u64 macaddr_is_admin_asgnd:1; u64 gmxport:16; #endif diff --git a/drivers/net/ethernet/cavium/liquidio/octeon_device.c b/drivers/net/ethernet/cavium/liquidio/octeon_device.c index d0ed6c4f9e1a..0f0275cd153e 100644 --- a/drivers/net/ethernet/cavium/liquidio/octeon_device.c +++ b/drivers/net/ethernet/cavium/liquidio/octeon_device.c @@ -1440,12 +1440,8 @@ void lio_enable_irq(struct octeon_droq *droq, struct octeon_instr_queue *iq) /* the whole thing needs to be atomic, ideally */ if (droq) { pkts_pend = (u32)atomic_read(&droq->pkts_pending); - spin_lock_bh(&droq->lock); writel(droq->pkt_count - pkts_pend, droq->pkts_sent_reg); droq->pkt_count = pkts_pend; - /* this write needs to be flushed before we release the lock */ - mmiowb(); - spin_unlock_bh(&droq->lock); oct = droq->oct_dev; } if (iq) { diff --git a/drivers/net/ethernet/cavium/liquidio/octeon_device.h b/drivers/net/ethernet/cavium/liquidio/octeon_device.h index d99ca6ba23a4..3d01d3602d8f 100644 --- a/drivers/net/ethernet/cavium/liquidio/octeon_device.h +++ b/drivers/net/ethernet/cavium/liquidio/octeon_device.h @@ -316,6 +316,8 @@ struct octdev_props { * device pointer (used for OS specific calls). */ int rx_on; + int fec; + int fec_boot; int napi_enabled; int gmxport; struct net_device *netdev; @@ -397,6 +399,8 @@ struct octeon_sriov_info { int vf_linkstate[MAX_POSSIBLE_VFS]; + bool vf_spoofchk[MAX_POSSIBLE_VFS]; + u64 vf_drv_loaded_mask; }; @@ -607,6 +611,9 @@ struct octeon_device { u8 speed_boot; u8 speed_setting; u8 no_speed_setting; + + u32 vfstats_poll; +#define LIO_VFSTATS_POLL 10 }; #define OCT_DRV_ONLINE 1 diff --git a/drivers/net/ethernet/cavium/liquidio/octeon_droq.c b/drivers/net/ethernet/cavium/liquidio/octeon_droq.c index a71dbb7ab6af..a0c099f71524 100644 --- a/drivers/net/ethernet/cavium/liquidio/octeon_droq.c +++ b/drivers/net/ethernet/cavium/liquidio/octeon_droq.c @@ -301,8 +301,6 @@ int octeon_init_droq(struct octeon_device *oct, dev_dbg(&oct->pci_dev->dev, "DROQ INIT: max_empty_descs: %d\n", droq->max_empty_descs); - spin_lock_init(&droq->lock); - INIT_LIST_HEAD(&droq->dispatch_list); /* For 56xx Pass1, this function won't be called, so no checks. */ @@ -333,8 +331,6 @@ init_droq_fail: * Returns: * Success: Pointer to recv_info_t * Failure: NULL. - * Locks: - * The droq->lock is held when this routine is called. */ static inline struct octeon_recv_info *octeon_create_recv_info( struct octeon_device *octeon_dev, @@ -433,8 +429,6 @@ octeon_droq_refill_pullup_descs(struct octeon_droq *droq, * up buffers (that were not dispatched) to form a contiguous ring. * Returns: * No of descriptors refilled. - * Locks: - * This routine is called with droq->lock held. */ static u32 octeon_droq_refill(struct octeon_device *octeon_dev, struct octeon_droq *droq) @@ -449,8 +443,7 @@ octeon_droq_refill(struct octeon_device *octeon_dev, struct octeon_droq *droq) while (droq->refill_count && (desc_refilled < droq->max_count)) { /* If a valid buffer exists (happens if there is no dispatch), - * reuse - * the buffer, else allocate. + * reuse the buffer, else allocate. */ if (!droq->recv_buf_list[droq->refill_idx].buffer) { pg_info = @@ -503,34 +496,37 @@ octeon_droq_refill(struct octeon_device *octeon_dev, struct octeon_droq *droq) /** check if we can allocate packets to get out of oom. * @param droq - Droq being checked. - * @return does not return anything + * @return 1 if fails to refill minimum */ -void octeon_droq_check_oom(struct octeon_droq *droq) +int octeon_retry_droq_refill(struct octeon_droq *droq) { - int desc_refilled; struct octeon_device *oct = droq->oct_dev; + int desc_refilled, reschedule = 1; + u32 pkts_credit; + + pkts_credit = readl(droq->pkts_credit_reg); + desc_refilled = octeon_droq_refill(oct, droq); + if (desc_refilled) { + /* Flush the droq descriptor data to memory to be sure + * that when we update the credits the data in memory + * is accurate. + */ + wmb(); + writel(desc_refilled, droq->pkts_credit_reg); + /* make sure mmio write completes */ + mmiowb(); - if (readl(droq->pkts_credit_reg) <= CN23XX_SLI_DEF_BP) { - spin_lock_bh(&droq->lock); - desc_refilled = octeon_droq_refill(oct, droq); - if (desc_refilled) { - /* Flush the droq descriptor data to memory to be sure - * that when we update the credits the data in memory - * is accurate. - */ - wmb(); - writel(desc_refilled, droq->pkts_credit_reg); - /* make sure mmio write completes */ - mmiowb(); - } - spin_unlock_bh(&droq->lock); + if (pkts_credit + desc_refilled >= CN23XX_SLI_DEF_BP) + reschedule = 0; } + + return reschedule; } static inline u32 octeon_droq_get_bufcount(u32 buf_size, u32 total_len) { - return ((total_len + buf_size - 1) / buf_size); + return DIV_ROUND_UP(total_len, buf_size); } static int @@ -603,9 +599,9 @@ octeon_droq_fast_process_packets(struct octeon_device *oct, struct octeon_droq *droq, u32 pkts_to_process) { + u32 pkt, total_len = 0, pkt_count, retval; struct octeon_droq_info *info; union octeon_rh *rh; - u32 pkt, total_len = 0, pkt_count; pkt_count = pkts_to_process; @@ -709,30 +705,43 @@ octeon_droq_fast_process_packets(struct octeon_device *oct, if (droq->refill_count >= droq->refill_threshold) { int desc_refilled = octeon_droq_refill(oct, droq); - /* Flush the droq descriptor data to memory to be sure - * that when we update the credits the data in memory - * is accurate. - */ - wmb(); - writel((desc_refilled), droq->pkts_credit_reg); - /* make sure mmio write completes */ - mmiowb(); + if (desc_refilled) { + /* Flush the droq descriptor data to memory to + * be sure that when we update the credits the + * data in memory is accurate. + */ + wmb(); + writel(desc_refilled, droq->pkts_credit_reg); + /* make sure mmio write completes */ + mmiowb(); + } } - } /* for (each packet)... */ /* Increment refill_count by the number of buffers processed. */ droq->stats.pkts_received += pkt; droq->stats.bytes_received += total_len; + retval = pkt; if ((droq->ops.drop_on_max) && (pkts_to_process - pkt)) { octeon_droq_drop_packets(oct, droq, (pkts_to_process - pkt)); droq->stats.dropped_toomany += (pkts_to_process - pkt); - return pkts_to_process; + retval = pkts_to_process; + } + + atomic_sub(retval, &droq->pkts_pending); + + if (droq->refill_count >= droq->refill_threshold && + readl(droq->pkts_credit_reg) < CN23XX_SLI_DEF_BP) { + octeon_droq_check_hw_for_pkts(droq); + + /* Make sure there are no pkts_pending */ + if (!atomic_read(&droq->pkts_pending)) + octeon_schedule_rxq_oom_work(oct, droq); } - return pkt; + return retval; } int @@ -740,29 +749,19 @@ octeon_droq_process_packets(struct octeon_device *oct, struct octeon_droq *droq, u32 budget) { - u32 pkt_count = 0, pkts_processed = 0; + u32 pkt_count = 0; struct list_head *tmp, *tmp2; - /* Grab the droq lock */ - spin_lock(&droq->lock); - octeon_droq_check_hw_for_pkts(droq); pkt_count = atomic_read(&droq->pkts_pending); - if (!pkt_count) { - spin_unlock(&droq->lock); + if (!pkt_count) return 0; - } if (pkt_count > budget) pkt_count = budget; - pkts_processed = octeon_droq_fast_process_packets(oct, droq, pkt_count); - - atomic_sub(pkts_processed, &droq->pkts_pending); - - /* Release the spin lock */ - spin_unlock(&droq->lock); + octeon_droq_fast_process_packets(oct, droq, pkt_count); list_for_each_safe(tmp, tmp2, &droq->dispatch_list) { struct __dispatch *rdisp = (struct __dispatch *)tmp; @@ -798,8 +797,6 @@ octeon_droq_process_poll_pkts(struct octeon_device *oct, if (budget > droq->max_count) budget = droq->max_count; - spin_lock(&droq->lock); - while (total_pkts_processed < budget) { octeon_droq_check_hw_for_pkts(droq); @@ -813,13 +810,9 @@ octeon_droq_process_poll_pkts(struct octeon_device *oct, octeon_droq_fast_process_packets(oct, droq, pkts_available); - atomic_sub(pkts_processed, &droq->pkts_pending); - total_pkts_processed += pkts_processed; } - spin_unlock(&droq->lock); - list_for_each_safe(tmp, tmp2, &droq->dispatch_list) { struct __dispatch *rdisp = (struct __dispatch *)tmp; @@ -879,9 +872,8 @@ octeon_enable_irq(struct octeon_device *oct, u32 q_no) int octeon_register_droq_ops(struct octeon_device *oct, u32 q_no, struct octeon_droq_ops *ops) { - struct octeon_droq *droq; - unsigned long flags; struct octeon_config *oct_cfg = NULL; + struct octeon_droq *droq; oct_cfg = octeon_get_conf(oct); @@ -901,21 +893,15 @@ int octeon_register_droq_ops(struct octeon_device *oct, u32 q_no, } droq = oct->droq[q_no]; - - spin_lock_irqsave(&droq->lock, flags); - memcpy(&droq->ops, ops, sizeof(struct octeon_droq_ops)); - spin_unlock_irqrestore(&droq->lock, flags); - return 0; } int octeon_unregister_droq_ops(struct octeon_device *oct, u32 q_no) { - unsigned long flags; - struct octeon_droq *droq; struct octeon_config *oct_cfg = NULL; + struct octeon_droq *droq; oct_cfg = octeon_get_conf(oct); @@ -936,14 +922,10 @@ int octeon_unregister_droq_ops(struct octeon_device *oct, u32 q_no) return 0; } - spin_lock_irqsave(&droq->lock, flags); - droq->ops.fptr = NULL; droq->ops.farg = NULL; droq->ops.drop_on_max = 0; - spin_unlock_irqrestore(&droq->lock, flags); - return 0; } diff --git a/drivers/net/ethernet/cavium/liquidio/octeon_droq.h b/drivers/net/ethernet/cavium/liquidio/octeon_droq.h index f28f262d4ab6..c9b19e624dce 100644 --- a/drivers/net/ethernet/cavium/liquidio/octeon_droq.h +++ b/drivers/net/ethernet/cavium/liquidio/octeon_droq.h @@ -245,9 +245,6 @@ struct octeon_droq_ops { * Octeon DROQ. */ struct octeon_droq { - /** A spinlock to protect access to this ring. */ - spinlock_t lock; - u32 q_no; u32 pkt_count; @@ -414,6 +411,6 @@ int octeon_droq_process_poll_pkts(struct octeon_device *oct, int octeon_enable_irq(struct octeon_device *oct, u32 q_no); -void octeon_droq_check_oom(struct octeon_droq *droq); +int octeon_retry_droq_refill(struct octeon_droq *droq); #endif /*__OCTEON_DROQ_H__ */ diff --git a/drivers/net/ethernet/cavium/liquidio/octeon_main.h b/drivers/net/ethernet/cavium/liquidio/octeon_main.h index 38c055f3c213..073d0647b439 100644 --- a/drivers/net/ethernet/cavium/liquidio/octeon_main.h +++ b/drivers/net/ethernet/cavium/liquidio/octeon_main.h @@ -70,6 +70,10 @@ void octeon_update_tx_completion_counters(void *buf, int reqtype, void octeon_report_tx_completion_to_bql(void *txq, unsigned int pkts_compl, unsigned int bytes_compl); void octeon_pf_changed_vf_macaddr(struct octeon_device *oct, u8 *mac); + +void octeon_schedule_rxq_oom_work(struct octeon_device *oct, + struct octeon_droq *droq); + /** Swap 8B blocks */ static inline void octeon_swap_8B_data(u64 *data, u32 blocks) { diff --git a/drivers/net/ethernet/cavium/liquidio/octeon_network.h b/drivers/net/ethernet/cavium/liquidio/octeon_network.h index ecd2a26a57d1..50201fc86dcf 100644 --- a/drivers/net/ethernet/cavium/liquidio/octeon_network.h +++ b/drivers/net/ethernet/cavium/liquidio/octeon_network.h @@ -71,6 +71,12 @@ struct oct_nic_stats_resp { u64 status; }; +struct oct_nic_vf_stats_resp { + u64 rh; + u64 spoofmac_cnt; + u64 status; +}; + struct oct_nic_stats_ctrl { struct completion complete; struct net_device *netdev; @@ -78,7 +84,10 @@ struct oct_nic_stats_ctrl { struct oct_nic_seapi_resp { u64 rh; - u32 speed; + union { + u32 fec_setting; + u32 speed; + }; u64 status; }; @@ -167,7 +176,7 @@ struct lio { struct cavium_wq txq_status_wq; /* work queue for rxq oom status */ - struct cavium_wq rxq_status_wq; + struct cavium_wq rxq_status_wq[MAX_POSSIBLE_OCTEON_OUTPUT_QUEUES]; /* work queue for link status */ struct cavium_wq link_status_wq; @@ -230,6 +239,8 @@ int lio_setup_glists(struct octeon_device *oct, struct lio *lio, int num_qs); int liquidio_get_speed(struct lio *lio); int liquidio_set_speed(struct lio *lio, int speed); +int liquidio_get_fec(struct lio *lio); +int liquidio_set_fec(struct lio *lio, int on_off); /** * \brief Net device change_mtu diff --git a/drivers/net/ethernet/cavium/liquidio/octeon_nic.c b/drivers/net/ethernet/cavium/liquidio/octeon_nic.c index 676fe0b7ab8c..1a706f81bbb0 100644 --- a/drivers/net/ethernet/cavium/liquidio/octeon_nic.c +++ b/drivers/net/ethernet/cavium/liquidio/octeon_nic.c @@ -172,13 +172,15 @@ octnet_send_nic_ctrl_pkt(struct octeon_device *oct, spin_unlock_bh(&oct->cmd_resp_wqlock); - switch (nctrl->ncmd.s.cmd) { - /* caller holds lock, can not sleep */ - case OCTNET_CMD_CHANGE_DEVFLAGS: - case OCTNET_CMD_SET_MULTI_LIST: - case OCTNET_CMD_SET_UC_LIST: - WRITE_ONCE(sc->caller_is_done, true); - return retval; + if (nctrl->ncmd.s.cmdgroup == 0) { + switch (nctrl->ncmd.s.cmd) { + /* caller holds lock, can not sleep */ + case OCTNET_CMD_CHANGE_DEVFLAGS: + case OCTNET_CMD_SET_MULTI_LIST: + case OCTNET_CMD_SET_UC_LIST: + WRITE_ONCE(sc->caller_is_done, true); + return retval; + } } retval = wait_for_sc_completion_timeout(oct, sc, 0); diff --git a/drivers/net/ethernet/cavium/octeon/octeon_mgmt.c b/drivers/net/ethernet/cavium/octeon/octeon_mgmt.c index bb43ddb7539e..4b3aecf98f2a 100644 --- a/drivers/net/ethernet/cavium/octeon/octeon_mgmt.c +++ b/drivers/net/ethernet/cavium/octeon/octeon_mgmt.c @@ -1268,12 +1268,13 @@ static int octeon_mgmt_stop(struct net_device *netdev) return 0; } -static int octeon_mgmt_xmit(struct sk_buff *skb, struct net_device *netdev) +static netdev_tx_t +octeon_mgmt_xmit(struct sk_buff *skb, struct net_device *netdev) { struct octeon_mgmt *p = netdev_priv(netdev); union mgmt_port_ring_entry re; unsigned long flags; - int rv = NETDEV_TX_BUSY; + netdev_tx_t rv = NETDEV_TX_BUSY; re.d64 = 0; re.s.tstamp = ((skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP) != 0); diff --git a/drivers/net/ethernet/chelsio/cxgb3/cxgb3_main.c b/drivers/net/ethernet/chelsio/cxgb3/cxgb3_main.c index a19172dbe6be..8b0a253a18d8 100644 --- a/drivers/net/ethernet/chelsio/cxgb3/cxgb3_main.c +++ b/drivers/net/ethernet/chelsio/cxgb3/cxgb3_main.c @@ -33,7 +33,6 @@ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/module.h> -#include <linux/moduleparam.h> #include <linux/init.h> #include <linux/pci.h> #include <linux/dma-mapping.h> @@ -3423,8 +3422,7 @@ static void remove_one(struct pci_dev *pdev) free_netdev(adapter->port[i]); iounmap(adapter->regs); - if (adapter->nofail_skb) - kfree_skb(adapter->nofail_skb); + kfree_skb(adapter->nofail_skb); kfree(adapter); pci_release_regions(pdev); pci_disable_device(pdev); diff --git a/drivers/net/ethernet/chelsio/cxgb3/cxgb3_offload.c b/drivers/net/ethernet/chelsio/cxgb3/cxgb3_offload.c index 50cd660732c5..84604aff53ce 100644 --- a/drivers/net/ethernet/chelsio/cxgb3/cxgb3_offload.c +++ b/drivers/net/ethernet/chelsio/cxgb3/cxgb3_offload.c @@ -1302,8 +1302,7 @@ void cxgb3_offload_deactivate(struct adapter *adapter) rcu_read_unlock(); RCU_INIT_POINTER(tdev->l2opt, NULL); call_rcu(&d->rcu_head, clean_l2_data); - if (t->nofail_skb) - kfree_skb(t->nofail_skb); + kfree_skb(t->nofail_skb); kfree(t); } diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h b/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h index 298701edb638..b5010bd32ea3 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h @@ -692,6 +692,7 @@ struct sge_eth_stats { /* Ethernet queue statistics */ unsigned long rx_cso; /* # of Rx checksum offloads */ unsigned long vlan_ex; /* # of Rx VLAN extractions */ unsigned long rx_drops; /* # of packets dropped due to no mem */ + unsigned long bad_rx_pkts; /* # of packets with err_vec!=0 */ }; struct sge_eth_rxq { /* SW Ethernet Rx queue */ diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_dcb.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_dcb.c index b34f0f077a31..6ba3104ff7eb 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_dcb.c +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_dcb.c @@ -114,6 +114,24 @@ void cxgb4_dcb_reset(struct net_device *dev) cxgb4_dcb_state_init(dev); } +/* update the dcb port support, if version is IEEE then set it to + * FW_PORT_DCB_VER_IEEE and if DCB_CAP_DCBX_VER_CEE is already set then + * clear that. and if it is set to CEE then set dcb supported to + * DCB_CAP_DCBX_VER_CEE & if DCB_CAP_DCBX_VER_IEEE is set, clear it + */ +static inline void cxgb4_dcb_update_support(struct port_dcb_info *dcb) +{ + if (dcb->dcb_version == FW_PORT_DCB_VER_IEEE) { + if (dcb->supported & DCB_CAP_DCBX_VER_CEE) + dcb->supported &= ~DCB_CAP_DCBX_VER_CEE; + dcb->supported |= DCB_CAP_DCBX_VER_IEEE; + } else if (dcb->dcb_version == FW_PORT_DCB_VER_CEE1D01) { + if (dcb->supported & DCB_CAP_DCBX_VER_IEEE) + dcb->supported &= ~DCB_CAP_DCBX_VER_IEEE; + dcb->supported |= DCB_CAP_DCBX_VER_CEE; + } +} + /* Finite State machine for Data Center Bridging. */ void cxgb4_dcb_state_fsm(struct net_device *dev, @@ -165,6 +183,15 @@ void cxgb4_dcb_state_fsm(struct net_device *dev, } case CXGB4_DCB_STATE_FW_INCOMPLETE: { + if (transition_to != CXGB4_DCB_INPUT_FW_DISABLED) { + /* during this CXGB4_DCB_STATE_FW_INCOMPLETE state, + * check if the dcb version is changed (there can be + * mismatch in default config & the negotiated switch + * configuration at FW, so update the dcb support + * accordingly. + */ + cxgb4_dcb_update_support(dcb); + } switch (transition_to) { case CXGB4_DCB_INPUT_FW_ENABLED: { /* we're alreaady in firmware DCB mode */ diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c index 0f72f9c4ec74..cab492ec8f59 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c @@ -2784,6 +2784,7 @@ do { \ RL("LROmerged:", stats.lro_merged); RL("LROpackets:", stats.lro_pkts); RL("RxDrops:", stats.rx_drops); + RL("RxBadPkts:", stats.bad_rx_pkts); TL("TSO:", tso); TL("TxCSO:", tx_cso); TL("VLANins:", vlan_ins); diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c index 2e1e286c74ac..1a93efa60e71 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c @@ -62,7 +62,6 @@ #include <net/netevent.h> #include <net/addrconf.h> #include <net/bonding.h> -#include <net/addrconf.h> #include <linux/uaccess.h> #include <linux/crash_dump.h> #include <net/udp_tunnel.h> diff --git a/drivers/net/ethernet/chelsio/cxgb4/l2t.c b/drivers/net/ethernet/chelsio/cxgb4/l2t.c index 301c4df8a566..99022c0898b5 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/l2t.c +++ b/drivers/net/ethernet/chelsio/cxgb4/l2t.c @@ -433,10 +433,12 @@ struct l2t_entry *cxgb4_l2t_get(struct l2t_data *d, struct neighbour *neigh, else lport = netdev2pinfo(physdev)->lport; - if (is_vlan_dev(neigh->dev)) + if (is_vlan_dev(neigh->dev)) { vlan = vlan_dev_vlan_id(neigh->dev); - else + vlan |= vlan_dev_get_egress_qos_mask(neigh->dev, priority); + } else { vlan = VLAN_NONE; + } write_lock_bh(&d->lock); for (e = d->l2tab[hash].first; e; e = e->next) diff --git a/drivers/net/ethernet/chelsio/cxgb4/sge.c b/drivers/net/ethernet/chelsio/cxgb4/sge.c index 6807bc3a44fb..b90188401d4a 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/sge.c +++ b/drivers/net/ethernet/chelsio/cxgb4/sge.c @@ -2830,6 +2830,10 @@ int t4_ethrx_handler(struct sge_rspq *q, const __be64 *rsp, csum_ok = pkt->csum_calc && !err_vec && (q->netdev->features & NETIF_F_RXCSUM); + + if (err_vec) + rxq->stats.bad_rx_pkts++; + if (((pkt->l2info & htonl(RXF_TCP_F)) || tnl_hdr_len) && (q->netdev->features & NETIF_F_GRO) && csum_ok && !pkt->ip_frag) { diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c b/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c index 5fe5d16dee72..f85eab57e9e1 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c +++ b/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c @@ -3889,7 +3889,7 @@ int t4_fwcache(struct adapter *adap, enum fw_params_param_dev_fwcache op) c.param[0].mnem = cpu_to_be32(FW_PARAMS_MNEM_V(FW_PARAMS_MNEM_DEV) | FW_PARAMS_PARAM_X_V(FW_PARAMS_PARAM_DEV_FWCACHE)); - c.param[0].val = (__force __be32)op; + c.param[0].val = cpu_to_be32(op); return t4_wr_mbox(adap, adap->mbox, &c, sizeof(c), NULL); } @@ -10209,7 +10209,9 @@ int t4_set_vlan_acl(struct adapter *adap, unsigned int mbox, unsigned int vf, FW_ACL_VLAN_CMD_VFN_V(vf)); vlan_cmd.en_to_len16 = cpu_to_be32(enable | FW_LEN16(vlan_cmd)); /* Drop all packets that donot match vlan id */ - vlan_cmd.dropnovlan_fm = FW_ACL_VLAN_CMD_FM_F; + vlan_cmd.dropnovlan_fm = (enable + ? (FW_ACL_VLAN_CMD_DROPNOVLAN_F | + FW_ACL_VLAN_CMD_FM_F) : 0); if (enable != 0) { vlan_cmd.nvlan = 1; vlan_cmd.vlanid[0] = cpu_to_be16(vlan); diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4fw_api.h b/drivers/net/ethernet/chelsio/cxgb4/t4fw_api.h index 5dc6c4154af8..6d2bc8789223 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/t4fw_api.h +++ b/drivers/net/ethernet/chelsio/cxgb4/t4fw_api.h @@ -2464,6 +2464,7 @@ struct fw_acl_vlan_cmd { #define FW_ACL_VLAN_CMD_DROPNOVLAN_S 7 #define FW_ACL_VLAN_CMD_DROPNOVLAN_V(x) ((x) << FW_ACL_VLAN_CMD_DROPNOVLAN_S) +#define FW_ACL_VLAN_CMD_DROPNOVLAN_F FW_ACL_VLAN_CMD_DROPNOVLAN_V(1U) #define FW_ACL_VLAN_CMD_FM_S 6 #define FW_ACL_VLAN_CMD_FM_M 0x1 diff --git a/drivers/net/ethernet/cirrus/ep93xx_eth.c b/drivers/net/ethernet/cirrus/ep93xx_eth.c index e2a702996db4..13dfdfca49fc 100644 --- a/drivers/net/ethernet/cirrus/ep93xx_eth.c +++ b/drivers/net/ethernet/cirrus/ep93xx_eth.c @@ -332,7 +332,7 @@ static int ep93xx_poll(struct napi_struct *napi, int budget) return rx; } -static int ep93xx_xmit(struct sk_buff *skb, struct net_device *dev) +static netdev_tx_t ep93xx_xmit(struct sk_buff *skb, struct net_device *dev) { struct ep93xx_priv *ep = netdev_priv(dev); struct ep93xx_tdesc *txd; diff --git a/drivers/net/ethernet/cirrus/mac89x0.c b/drivers/net/ethernet/cirrus/mac89x0.c index 3f8fe8fd79cc..6324e80960c3 100644 --- a/drivers/net/ethernet/cirrus/mac89x0.c +++ b/drivers/net/ethernet/cirrus/mac89x0.c @@ -113,7 +113,7 @@ struct net_local { /* Index to functions, as function prototypes. */ static int net_open(struct net_device *dev); -static int net_send_packet(struct sk_buff *skb, struct net_device *dev); +static netdev_tx_t net_send_packet(struct sk_buff *skb, struct net_device *dev); static irqreturn_t net_interrupt(int irq, void *dev_id); static void set_multicast_list(struct net_device *dev); static void net_rx(struct net_device *dev); @@ -324,7 +324,7 @@ net_open(struct net_device *dev) return 0; } -static int +static netdev_tx_t net_send_packet(struct sk_buff *skb, struct net_device *dev) { struct net_local *lp = netdev_priv(dev); diff --git a/drivers/net/ethernet/cortina/gemini.c b/drivers/net/ethernet/cortina/gemini.c index 1c9ad3630c77..ceec467f590d 100644 --- a/drivers/net/ethernet/cortina/gemini.c +++ b/drivers/net/ethernet/cortina/gemini.c @@ -372,9 +372,8 @@ static int gmac_setup_phy(struct net_device *netdev) return -ENODEV; netdev->phydev = phy; - phy->supported &= PHY_GBIT_FEATURES; - phy->supported |= SUPPORTED_Asym_Pause | SUPPORTED_Pause; - phy->advertising = phy->supported; + phy_set_max_speed(phy, SPEED_1000); + phy_support_asym_pause(phy); /* set PHY interface type */ switch (phy->interface) { diff --git a/drivers/net/ethernet/dnet.c b/drivers/net/ethernet/dnet.c index 5a847941c46b..79521e27f0d1 100644 --- a/drivers/net/ethernet/dnet.c +++ b/drivers/net/ethernet/dnet.c @@ -284,13 +284,11 @@ static int dnet_mii_probe(struct net_device *dev) /* mask with MAC supported features */ if (bp->capabilities & DNET_HAS_GIGABIT) - phydev->supported &= PHY_GBIT_FEATURES; + phy_set_max_speed(phydev, SPEED_1000); else - phydev->supported &= PHY_BASIC_FEATURES; + phy_set_max_speed(phydev, SPEED_100); - phydev->supported |= SUPPORTED_Asym_Pause | SUPPORTED_Pause; - - phydev->advertising = phydev->supported; + phy_support_asym_pause(phydev); bp->link = 0; bp->speed = 0; diff --git a/drivers/net/ethernet/emulex/benet/be_cmds.c b/drivers/net/ethernet/emulex/benet/be_cmds.c index ff92ab1daeb8..1e9d882c04ef 100644 --- a/drivers/net/ethernet/emulex/benet/be_cmds.c +++ b/drivers/net/ethernet/emulex/benet/be_cmds.c @@ -4500,7 +4500,7 @@ int be_cmd_get_profile_config(struct be_adapter *adapter, port_res->max_vfs += le16_to_cpu(pcie->num_vfs); } } - return status; + goto err; } pcie = be_get_pcie_desc(resp->func_param, desc_count, diff --git a/drivers/net/ethernet/ethoc.c b/drivers/net/ethernet/ethoc.c index 60da0499ad66..0f3e7f21c6fa 100644 --- a/drivers/net/ethernet/ethoc.c +++ b/drivers/net/ethernet/ethoc.c @@ -721,10 +721,7 @@ static int ethoc_mdio_probe(struct net_device *dev) return err; } - phy->advertising &= ~(ADVERTISED_1000baseT_Full | - ADVERTISED_1000baseT_Half); - phy->supported &= ~(SUPPORTED_1000baseT_Full | - SUPPORTED_1000baseT_Half); + phy_set_max_speed(phy, SPEED_100); return 0; } diff --git a/drivers/net/ethernet/faraday/ftgmac100.c b/drivers/net/ethernet/faraday/ftgmac100.c index ed6c76d20b45..d8ead7e4177e 100644 --- a/drivers/net/ethernet/faraday/ftgmac100.c +++ b/drivers/net/ethernet/faraday/ftgmac100.c @@ -1079,8 +1079,7 @@ static int ftgmac100_mii_probe(struct ftgmac100 *priv, phy_interface_t intf) /* Indicate that we support PAUSE frames (see comment in * Documentation/networking/phy.txt) */ - phydev->supported |= SUPPORTED_Pause | SUPPORTED_Asym_Pause; - phydev->advertising = phydev->supported; + phy_support_asym_pause(phydev); /* Display what we found */ phy_attached_info(phydev); @@ -1220,22 +1219,11 @@ static int ftgmac100_set_pauseparam(struct net_device *netdev, priv->tx_pause = pause->tx_pause; priv->rx_pause = pause->rx_pause; - if (phydev) { - phydev->advertising &= ~ADVERTISED_Pause; - phydev->advertising &= ~ADVERTISED_Asym_Pause; + if (phydev) + phy_set_asym_pause(phydev, pause->rx_pause, pause->tx_pause); - if (pause->rx_pause) { - phydev->advertising |= ADVERTISED_Pause; - phydev->advertising |= ADVERTISED_Asym_Pause; - } - - if (pause->tx_pause) - phydev->advertising ^= ADVERTISED_Asym_Pause; - } if (netif_running(netdev)) { - if (phydev && priv->aneg_pause) - phy_start_aneg(phydev); - else + if (!(phydev && priv->aneg_pause)) ftgmac100_config_pause(priv); } diff --git a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c index 65a22cd9aef2..84843de25c7b 100644 --- a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c +++ b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c @@ -1280,7 +1280,7 @@ static int dpaa_bman_release(const struct dpaa_bp *dpaa_bp, err = bman_release(dpaa_bp->pool, bmb, cnt); /* Should never occur, address anyway to avoid leaking the buffers */ - if (unlikely(WARN_ON(err)) && dpaa_bp->free_buf_cb) + if (WARN_ON(err) && dpaa_bp->free_buf_cb) while (cnt-- > 0) dpaa_bp->free_buf_cb(dpaa_bp, &bmb[cnt]); @@ -1704,10 +1704,8 @@ static struct sk_buff *contig_fd_to_skb(const struct dpaa_priv *priv, skb = build_skb(vaddr, dpaa_bp->size + SKB_DATA_ALIGN(sizeof(struct skb_shared_info))); - if (unlikely(!skb)) { - WARN_ONCE(1, "Build skb failure on Rx\n"); + if (WARN_ONCE(!skb, "Build skb failure on Rx\n")) goto free_buffer; - } WARN_ON(fd_off != priv->rx_headroom); skb_reserve(skb, fd_off); skb_put(skb, qm_fd_get_length(fd)); @@ -1770,7 +1768,7 @@ static struct sk_buff *sg_fd_to_skb(const struct dpaa_priv *priv, sz = dpaa_bp->size + SKB_DATA_ALIGN(sizeof(struct skb_shared_info)); skb = build_skb(sg_vaddr, sz); - if (WARN_ON(unlikely(!skb))) + if (WARN_ON(!skb)) goto free_buffers; skb->ip_summed = rx_csum_offload(priv, fd); @@ -2046,7 +2044,8 @@ static inline int dpaa_xmit(struct dpaa_priv *priv, return 0; } -static int dpaa_start_xmit(struct sk_buff *skb, struct net_device *net_dev) +static netdev_tx_t +dpaa_start_xmit(struct sk_buff *skb, struct net_device *net_dev) { const int queue_mapping = skb_get_queue_mapping(skb); bool nonlinear = skb_is_nonlinear(skb); @@ -2493,8 +2492,7 @@ static int dpaa_phy_init(struct net_device *net_dev) /* Remove any features not supported by the controller */ phy_dev->supported &= mac_dev->if_support; - phy_dev->supported |= (SUPPORTED_Pause | SUPPORTED_Asym_Pause); - phy_dev->advertising = phy_dev->supported; + phy_support_asym_pause(phy_dev); mac_dev->phy_dev = phy_dev; net_dev->phydev = phy_dev; diff --git a/drivers/net/ethernet/freescale/dpaa/dpaa_ethtool.c b/drivers/net/ethernet/freescale/dpaa/dpaa_ethtool.c index 3184c8f7cdd0..5d0fdf667b82 100644 --- a/drivers/net/ethernet/freescale/dpaa/dpaa_ethtool.c +++ b/drivers/net/ethernet/freescale/dpaa/dpaa_ethtool.c @@ -194,9 +194,7 @@ static int dpaa_set_pauseparam(struct net_device *net_dev, return -ENODEV; } - if (!(phydev->supported & SUPPORTED_Pause) || - (!(phydev->supported & SUPPORTED_Asym_Pause) && - (epause->rx_pause != epause->tx_pause))) + if (!phy_validate_pause(phydev, epause)) return -EINVAL; /* The MAC should know how to handle PAUSE frame autonegotiation before @@ -210,29 +208,8 @@ static int dpaa_set_pauseparam(struct net_device *net_dev, /* Determine the sym/asym advertised PAUSE capabilities from the desired * rx/tx pause settings. */ - newadv = 0; - if (epause->rx_pause) - newadv = ADVERTISED_Pause | ADVERTISED_Asym_Pause; - if (epause->tx_pause) - newadv ^= ADVERTISED_Asym_Pause; - oldadv = phydev->advertising & - (ADVERTISED_Pause | ADVERTISED_Asym_Pause); - - /* If there are differences between the old and the new advertised - * values, restart PHY autonegotiation and advertise the new values. - */ - if (oldadv != newadv) { - phydev->advertising &= ~(ADVERTISED_Pause - | ADVERTISED_Asym_Pause); - phydev->advertising |= newadv; - if (phydev->autoneg) { - err = phy_start_aneg(phydev); - if (err < 0) - netdev_err(net_dev, "phy_start_aneg() = %d\n", - err); - } - } + phy_set_asym_pause(phydev, epause->rx_pause, epause->tx_pause); fman_get_pause_cfg(mac_dev, &rx_pause, &tx_pause); err = fman_set_mac_active_pause(mac_dev, rx_pause, tx_pause); diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c index 559154a5d9e9..c282d5ca06d6 100644 --- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c +++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c @@ -2003,9 +2003,21 @@ static int setup_tx_flow(struct dpaa2_eth_priv *priv, return 0; } -/* Hash key is a 5-tuple: IPsrc, IPdst, IPnextproto, L4src, L4dst */ +/* Supported header fields for Rx hash distribution key */ static const struct dpaa2_eth_hash_fields hash_fields[] = { { + /* L2 header */ + .rxnfc_field = RXH_L2DA, + .cls_prot = NET_PROT_ETH, + .cls_field = NH_FLD_ETH_DA, + .size = 6, + }, { + /* VLAN header */ + .rxnfc_field = RXH_VLAN, + .cls_prot = NET_PROT_VLAN, + .cls_field = NH_FLD_VLAN_TCI, + .size = 2, + }, { /* IP header */ .rxnfc_field = RXH_IP_SRC, .cls_prot = NET_PROT_IP, @@ -2040,19 +2052,20 @@ static const struct dpaa2_eth_hash_fields hash_fields[] = { /* Set RX hash options * flags is a combination of RXH_ bits */ -static int dpaa2_eth_set_hash(struct net_device *net_dev, u64 flags) +int dpaa2_eth_set_hash(struct net_device *net_dev, u64 flags) { struct device *dev = net_dev->dev.parent; struct dpaa2_eth_priv *priv = netdev_priv(net_dev); struct dpkg_profile_cfg cls_cfg; struct dpni_rx_tc_dist_cfg dist_cfg; + u32 rx_hash_fields = 0; u8 *dma_mem; int i; int err = 0; if (!dpaa2_eth_hash_enabled(priv)) { dev_dbg(dev, "Hashing support is not enabled\n"); - return 0; + return -EOPNOTSUPP; } memset(&cls_cfg, 0, sizeof(cls_cfg)); @@ -2075,7 +2088,7 @@ static int dpaa2_eth_set_hash(struct net_device *net_dev, u64 flags) key->extract.from_hdr.field = hash_fields[i].cls_field; cls_cfg.num_extracts++; - priv->rx_hash_fields |= hash_fields[i].rxnfc_field; + rx_hash_fields |= hash_fields[i].rxnfc_field; } dma_mem = kzalloc(DPAA2_CLASSIFIER_DMA_SIZE, GFP_KERNEL); @@ -2108,6 +2121,8 @@ static int dpaa2_eth_set_hash(struct net_device *net_dev, u64 flags) DPAA2_CLASSIFIER_DMA_SIZE, DMA_TO_DEVICE); if (err) dev_err(dev, "dpni_set_rx_tc_dist() error %d\n", err); + else + priv->rx_hash_fields = rx_hash_fields; err_dma_map: err_prep_key: @@ -2141,7 +2156,7 @@ static int bind_dpni(struct dpaa2_eth_priv *priv) * the default hash key */ err = dpaa2_eth_set_hash(net_dev, DPAA2_RXH_DEFAULT); - if (err) + if (err && err != -EOPNOTSUPP) dev_err(dev, "Failed to configure hashing\n"); /* Configure handling of error frames */ diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.h b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.h index d54cb0b99d08..93bc41265e5e 100644 --- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.h +++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.h @@ -409,4 +409,6 @@ static int dpaa2_eth_queue_count(struct dpaa2_eth_priv *priv) return priv->dpni_attrs.num_queues; } +int dpaa2_eth_set_hash(struct net_device *net_dev, u64 flags); + #endif /* __DPAA2_H */ diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-ethtool.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-ethtool.c index 8056a95e1265..ce0d94d8a7d8 100644 --- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-ethtool.c +++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-ethtool.c @@ -247,6 +247,24 @@ static int dpaa2_eth_get_rxnfc(struct net_device *net_dev, return 0; } +static int dpaa2_eth_set_rxnfc(struct net_device *net_dev, + struct ethtool_rxnfc *rxnfc) +{ + int err = 0; + + switch (rxnfc->cmd) { + case ETHTOOL_SRXFH: + if ((rxnfc->data & DPAA2_RXH_SUPPORTED) != rxnfc->data) + return -EOPNOTSUPP; + err = dpaa2_eth_set_hash(net_dev, rxnfc->data); + break; + default: + err = -EOPNOTSUPP; + } + + return err; +} + int dpaa2_phc_index = -1; EXPORT_SYMBOL(dpaa2_phc_index); @@ -276,5 +294,6 @@ const struct ethtool_ops dpaa2_ethtool_ops = { .get_ethtool_stats = dpaa2_eth_get_ethtool_stats, .get_strings = dpaa2_eth_get_strings, .get_rxnfc = dpaa2_eth_get_rxnfc, + .set_rxnfc = dpaa2_eth_set_rxnfc, .get_ts_info = dpaa2_eth_get_ts_info, }; diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c index 2708297e7795..ce74b7a46d07 100644 --- a/drivers/net/ethernet/freescale/fec_main.c +++ b/drivers/net/ethernet/freescale/fec_main.c @@ -1946,16 +1946,15 @@ static int fec_enet_mii_probe(struct net_device *ndev) /* mask with MAC supported features */ if (fep->quirks & FEC_QUIRK_HAS_GBIT) { - phy_dev->supported &= PHY_GBIT_FEATURES; - phy_dev->supported &= ~SUPPORTED_1000baseT_Half; + phy_set_max_speed(phy_dev, 1000); + phy_remove_link_mode(phy_dev, + ETHTOOL_LINK_MODE_1000baseT_Half_BIT); #if !defined(CONFIG_M5272) - phy_dev->supported |= SUPPORTED_Pause; + phy_support_sym_pause(phy_dev); #endif } else - phy_dev->supported &= PHY_BASIC_FEATURES; - - phy_dev->advertising = phy_dev->supported; + phy_set_max_speed(phy_dev, 100); fep->link = 0; fep->full_duplex = 0; @@ -2055,8 +2054,7 @@ static int fec_enet_mii_init(struct platform_device *pdev) node = of_get_child_by_name(pdev->dev.of_node, "mdio"); err = of_mdiobus_register(fep->mii_bus, node); - if (node) - of_node_put(node); + of_node_put(node); if (err) goto err_out_free_mdiobus; @@ -2230,13 +2228,8 @@ static int fec_enet_set_pauseparam(struct net_device *ndev, fep->pause_flag |= pause->rx_pause ? FEC_PAUSE_FLAG_ENABLE : 0; fep->pause_flag |= pause->autoneg ? FEC_PAUSE_FLAG_AUTONEG : 0; - if (pause->rx_pause || pause->autoneg) { - ndev->phydev->supported |= ADVERTISED_Pause; - ndev->phydev->advertising |= ADVERTISED_Pause; - } else { - ndev->phydev->supported &= ~ADVERTISED_Pause; - ndev->phydev->advertising &= ~ADVERTISED_Pause; - } + phy_set_sym_pause(ndev->phydev, pause->rx_pause, pause->tx_pause, + pause->autoneg); if (pause->autoneg) { if (netif_running(ndev)) diff --git a/drivers/net/ethernet/freescale/fec_mpc52xx.c b/drivers/net/ethernet/freescale/fec_mpc52xx.c index 6d7269d87a85..b90bab72efdb 100644 --- a/drivers/net/ethernet/freescale/fec_mpc52xx.c +++ b/drivers/net/ethernet/freescale/fec_mpc52xx.c @@ -305,7 +305,8 @@ static int mpc52xx_fec_close(struct net_device *dev) * invariant will hold if you make sure that the netif_*_queue() * calls are done at the proper times. */ -static int mpc52xx_fec_start_xmit(struct sk_buff *skb, struct net_device *dev) +static netdev_tx_t +mpc52xx_fec_start_xmit(struct sk_buff *skb, struct net_device *dev) { struct mpc52xx_fec_priv *priv = netdev_priv(dev); struct bcom_fec_bd *bd; diff --git a/drivers/net/ethernet/freescale/fs_enet/fs_enet-main.c b/drivers/net/ethernet/freescale/fs_enet/fs_enet-main.c index 2c2976a2dda6..7c548ed535da 100644 --- a/drivers/net/ethernet/freescale/fs_enet/fs_enet-main.c +++ b/drivers/net/ethernet/freescale/fs_enet/fs_enet-main.c @@ -481,7 +481,8 @@ static struct sk_buff *tx_skb_align_workaround(struct net_device *dev, } #endif -static int fs_enet_start_xmit(struct sk_buff *skb, struct net_device *dev) +static netdev_tx_t +fs_enet_start_xmit(struct sk_buff *skb, struct net_device *dev) { struct fs_enet_private *fep = netdev_priv(dev); cbd_t __iomem *bdp; diff --git a/drivers/net/ethernet/freescale/gianfar.c b/drivers/net/ethernet/freescale/gianfar.c index f27f9bae1a4a..0bd21a493016 100644 --- a/drivers/net/ethernet/freescale/gianfar.c +++ b/drivers/net/ethernet/freescale/gianfar.c @@ -102,8 +102,6 @@ #include <linux/phy_fixed.h> #include <linux/of.h> #include <linux/of_net.h> -#include <linux/of_address.h> -#include <linux/of_irq.h> #include "gianfar.h" @@ -112,7 +110,7 @@ const char gfar_driver_version[] = "2.0"; static int gfar_enet_open(struct net_device *dev); -static int gfar_start_xmit(struct sk_buff *skb, struct net_device *dev); +static netdev_tx_t gfar_start_xmit(struct sk_buff *skb, struct net_device *dev); static void gfar_reset_task(struct work_struct *work); static void gfar_timeout(struct net_device *dev); static int gfar_close(struct net_device *dev); @@ -1814,8 +1812,8 @@ static int init_phy(struct net_device *dev) phydev->supported &= (GFAR_SUPPORTED | gigabit_support); phydev->advertising = phydev->supported; - /* Add support for flow control, but don't advertise it by default */ - phydev->supported |= (SUPPORTED_Pause | SUPPORTED_Asym_Pause); + /* Add support for flow control */ + phy_support_asym_pause(phydev); /* disable EEE autoneg, EEE not supported by eTSEC */ memset(&edata, 0, sizeof(struct ethtool_eee)); @@ -2334,7 +2332,7 @@ static inline bool gfar_csum_errata_76(struct gfar_private *priv, /* This is called by the kernel when a frame is ready for transmission. * It is pointed to by the dev->hard_start_xmit function pointer */ -static int gfar_start_xmit(struct sk_buff *skb, struct net_device *dev) +static netdev_tx_t gfar_start_xmit(struct sk_buff *skb, struct net_device *dev) { struct gfar_private *priv = netdev_priv(dev); struct gfar_priv_tx_q *tx_queue = NULL; diff --git a/drivers/net/ethernet/freescale/gianfar_ethtool.c b/drivers/net/ethernet/freescale/gianfar_ethtool.c index 395a5266ea30..0d76e15cd6dd 100644 --- a/drivers/net/ethernet/freescale/gianfar_ethtool.c +++ b/drivers/net/ethernet/freescale/gianfar_ethtool.c @@ -230,7 +230,7 @@ static unsigned int gfar_usecs2ticks(struct gfar_private *priv, /* Make sure we return a number greater than 0 * if usecs > 0 */ - return (usecs * 1000 + count - 1) / count; + return DIV_ROUND_UP(usecs * 1000, count); } /* Convert ethernet clock ticks to microseconds */ @@ -503,65 +503,44 @@ static int gfar_spauseparam(struct net_device *dev, struct gfar_private *priv = netdev_priv(dev); struct phy_device *phydev = dev->phydev; struct gfar __iomem *regs = priv->gfargrp[0].regs; - u32 oldadv, newadv; if (!phydev) return -ENODEV; - if (!(phydev->supported & SUPPORTED_Pause) || - (!(phydev->supported & SUPPORTED_Asym_Pause) && - (epause->rx_pause != epause->tx_pause))) + if (!phy_validate_pause(phydev, epause)) return -EINVAL; priv->rx_pause_en = priv->tx_pause_en = 0; + phy_set_asym_pause(phydev, epause->rx_pause, epause->tx_pause); if (epause->rx_pause) { priv->rx_pause_en = 1; if (epause->tx_pause) { priv->tx_pause_en = 1; - /* FLOW_CTRL_RX & TX */ - newadv = ADVERTISED_Pause; - } else /* FLOW_CTLR_RX */ - newadv = ADVERTISED_Pause | ADVERTISED_Asym_Pause; + } } else if (epause->tx_pause) { priv->tx_pause_en = 1; - /* FLOW_CTLR_TX */ - newadv = ADVERTISED_Asym_Pause; - } else - newadv = 0; + } if (epause->autoneg) priv->pause_aneg_en = 1; else priv->pause_aneg_en = 0; - oldadv = phydev->advertising & - (ADVERTISED_Pause | ADVERTISED_Asym_Pause); - if (oldadv != newadv) { - phydev->advertising &= - ~(ADVERTISED_Pause | ADVERTISED_Asym_Pause); - phydev->advertising |= newadv; - if (phydev->autoneg) - /* inform link partner of our - * new flow ctrl settings - */ - return phy_start_aneg(phydev); - - if (!epause->autoneg) { - u32 tempval; - tempval = gfar_read(®s->maccfg1); - tempval &= ~(MACCFG1_TX_FLOW | MACCFG1_RX_FLOW); - - priv->tx_actual_en = 0; - if (priv->tx_pause_en) { - priv->tx_actual_en = 1; - tempval |= MACCFG1_TX_FLOW; - } + if (!epause->autoneg) { + u32 tempval = gfar_read(®s->maccfg1); - if (priv->rx_pause_en) - tempval |= MACCFG1_RX_FLOW; - gfar_write(®s->maccfg1, tempval); + tempval &= ~(MACCFG1_TX_FLOW | MACCFG1_RX_FLOW); + + priv->tx_actual_en = 0; + if (priv->tx_pause_en) { + priv->tx_actual_en = 1; + tempval |= MACCFG1_TX_FLOW; } + + if (priv->rx_pause_en) + tempval |= MACCFG1_RX_FLOW; + gfar_write(®s->maccfg1, tempval); } return 0; diff --git a/drivers/net/ethernet/freescale/ucc_geth.c b/drivers/net/ethernet/freescale/ucc_geth.c index 22a817da861e..32e02700feaa 100644 --- a/drivers/net/ethernet/freescale/ucc_geth.c +++ b/drivers/net/ethernet/freescale/ucc_geth.c @@ -1742,12 +1742,7 @@ static int init_phy(struct net_device *dev) if (priv->phy_interface == PHY_INTERFACE_MODE_SGMII) uec_configure_serdes(dev); - phydev->supported &= (SUPPORTED_MII | - SUPPORTED_Autoneg | - ADVERTISED_10baseT_Half | - ADVERTISED_10baseT_Full | - ADVERTISED_100baseT_Half | - ADVERTISED_100baseT_Full); + phy_set_max_speed(phydev, SPEED_100); if (priv->max_speed == SPEED_1000) phydev->supported |= ADVERTISED_1000baseT_Full; @@ -3083,7 +3078,8 @@ static int ucc_geth_startup(struct ucc_geth_private *ugeth) /* This is called by the kernel when a frame is ready for transmission. */ /* It is pointed to by the dev->hard_start_xmit function pointer */ -static int ucc_geth_start_xmit(struct sk_buff *skb, struct net_device *dev) +static netdev_tx_t +ucc_geth_start_xmit(struct sk_buff *skb, struct net_device *dev) { struct ucc_geth_private *ugeth = netdev_priv(dev); #ifdef CONFIG_UGETH_TX_ON_DEMAND diff --git a/drivers/net/ethernet/hisilicon/hip04_eth.c b/drivers/net/ethernet/hisilicon/hip04_eth.c index 14374a856d30..be268dcde8fa 100644 --- a/drivers/net/ethernet/hisilicon/hip04_eth.c +++ b/drivers/net/ethernet/hisilicon/hip04_eth.c @@ -422,7 +422,8 @@ static void hip04_start_tx_timer(struct hip04_priv *priv) ns, HRTIMER_MODE_REL); } -static int hip04_mac_start_xmit(struct sk_buff *skb, struct net_device *ndev) +static netdev_tx_t +hip04_mac_start_xmit(struct sk_buff *skb, struct net_device *ndev) { struct hip04_priv *priv = netdev_priv(ndev); struct net_device_stats *stats = &ndev->stats; diff --git a/drivers/net/ethernet/hisilicon/hix5hd2_gmac.c b/drivers/net/ethernet/hisilicon/hix5hd2_gmac.c index c5727003af8c..471805ea363b 100644 --- a/drivers/net/ethernet/hisilicon/hix5hd2_gmac.c +++ b/drivers/net/ethernet/hisilicon/hix5hd2_gmac.c @@ -736,7 +736,7 @@ static int hix5hd2_fill_sg_desc(struct hix5hd2_priv *priv, return 0; } -static int hix5hd2_net_xmit(struct sk_buff *skb, struct net_device *dev) +static netdev_tx_t hix5hd2_net_xmit(struct sk_buff *skb, struct net_device *dev) { struct hix5hd2_priv *priv = netdev_priv(dev); struct hix5hd2_desc *desc; diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_gmac.c b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_gmac.c index 09e4061d1fa6..aaf72c055711 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_gmac.c +++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_gmac.c @@ -319,7 +319,7 @@ static void hns_gmac_set_promisc(void *mac_drv, u8 en) hns_gmac_set_uc_match(mac_drv, en); } -int hns_gmac_wait_fifo_clean(void *mac_drv) +static int hns_gmac_wait_fifo_clean(void *mac_drv) { struct mac_driver *drv = (struct mac_driver *)mac_drv; int wait_cnt; diff --git a/drivers/net/ethernet/hisilicon/hns3/hnae3.c b/drivers/net/ethernet/hisilicon/hns3/hnae3.c index fff5be8078ac..781e5dee3c70 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hnae3.c +++ b/drivers/net/ethernet/hisilicon/hns3/hnae3.c @@ -29,8 +29,8 @@ static bool hnae3_client_match(enum hnae3_client_type client_type, return false; } -static void hnae3_set_client_init_flag(struct hnae3_client *client, - struct hnae3_ae_dev *ae_dev, int inited) +void hnae3_set_client_init_flag(struct hnae3_client *client, + struct hnae3_ae_dev *ae_dev, int inited) { switch (client->type) { case HNAE3_CLIENT_KNIC: @@ -46,6 +46,7 @@ static void hnae3_set_client_init_flag(struct hnae3_client *client, break; } } +EXPORT_SYMBOL(hnae3_set_client_init_flag); static int hnae3_get_client_init_flag(struct hnae3_client *client, struct hnae3_ae_dev *ae_dev) @@ -86,14 +87,11 @@ static int hnae3_match_n_instantiate(struct hnae3_client *client, /* now, (un-)instantiate client by calling lower layer */ if (is_reg) { ret = ae_dev->ops->init_client_instance(client, ae_dev); - if (ret) { + if (ret) dev_err(&ae_dev->pdev->dev, "fail to instantiate client, ret = %d\n", ret); - return ret; - } - hnae3_set_client_init_flag(client, ae_dev, 1); - return 0; + return ret; } if (hnae3_get_client_init_flag(client, ae_dev)) { diff --git a/drivers/net/ethernet/hisilicon/hns3/hnae3.h b/drivers/net/ethernet/hisilicon/hns3/hnae3.h index 67befff0bfc5..564afd4c1323 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hnae3.h +++ b/drivers/net/ethernet/hisilicon/hns3/hnae3.h @@ -107,6 +107,7 @@ enum hnae3_media_type { HNAE3_MEDIA_TYPE_FIBER, HNAE3_MEDIA_TYPE_COPPER, HNAE3_MEDIA_TYPE_BACKPLANE, + HNAE3_MEDIA_TYPE_NONE, }; enum hnae3_reset_notify_type { @@ -337,6 +338,8 @@ struct hnae3_ae_ops { void (*get_mac_addr)(struct hnae3_handle *handle, u8 *p); int (*set_mac_addr)(struct hnae3_handle *handle, void *p, bool is_first); + int (*do_ioctl)(struct hnae3_handle *handle, + struct ifreq *ifr, int cmd); int (*add_uc_addr)(struct hnae3_handle *handle, const unsigned char *addr); int (*rm_uc_addr)(struct hnae3_handle *handle, @@ -408,7 +411,6 @@ struct hnae3_ae_ops { void (*get_link_mode)(struct hnae3_handle *handle, unsigned long *supported, unsigned long *advertising); - void (*get_port_type)(struct hnae3_handle *handle, u8 *port_type); }; struct hnae3_dcb_ops { @@ -521,4 +523,7 @@ void hnae3_register_ae_algo(struct hnae3_ae_algo *ae_algo); void hnae3_unregister_client(struct hnae3_client *client); int hnae3_register_client(struct hnae3_client *client); + +void hnae3_set_client_init_flag(struct hnae3_client *client, + struct hnae3_ae_dev *ae_dev, int inited); #endif diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c index 75e8ee9d4e2e..5a4773a9b4a5 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c @@ -66,6 +66,23 @@ static irqreturn_t hns3_irq_handle(int irq, void *vector) return IRQ_HANDLED; } +/* This callback function is used to set affinity changes to the irq affinity + * masks when the irq_set_affinity_notifier function is used. + */ +static void hns3_nic_irq_affinity_notify(struct irq_affinity_notify *notify, + const cpumask_t *mask) +{ + struct hns3_enet_tqp_vector *tqp_vectors = + container_of(notify, struct hns3_enet_tqp_vector, + affinity_notify); + + tqp_vectors->affinity_mask = *mask; +} + +static void hns3_nic_irq_affinity_release(struct kref *ref) +{ +} + static void hns3_nic_uninit_irq(struct hns3_nic_priv *priv) { struct hns3_enet_tqp_vector *tqp_vectors; @@ -77,6 +94,10 @@ static void hns3_nic_uninit_irq(struct hns3_nic_priv *priv) if (tqp_vectors->irq_init_flag != HNS3_VECTOR_INITED) continue; + /* clear the affinity notifier and affinity mask */ + irq_set_affinity_notifier(tqp_vectors->vector_irq, NULL); + irq_set_affinity_hint(tqp_vectors->vector_irq, NULL); + /* release the irq resource */ free_irq(tqp_vectors->vector_irq, tqp_vectors); tqp_vectors->irq_init_flag = HNS3_VECTOR_NOT_INITED; @@ -127,6 +148,15 @@ static int hns3_nic_init_irq(struct hns3_nic_priv *priv) return ret; } + tqp_vectors->affinity_notify.notify = + hns3_nic_irq_affinity_notify; + tqp_vectors->affinity_notify.release = + hns3_nic_irq_affinity_release; + irq_set_affinity_notifier(tqp_vectors->vector_irq, + &tqp_vectors->affinity_notify); + irq_set_affinity_hint(tqp_vectors->vector_irq, + &tqp_vectors->affinity_mask); + tqp_vectors->irq_init_flag = HNS3_VECTOR_INITED; } @@ -1044,7 +1074,7 @@ static int hns3_nic_maybe_stop_tx(struct sk_buff **out_skb, int *bnum, /* No. of segments (plus a header) */ buf_num = skb_shinfo(skb)->nr_frags + 1; - if (buf_num > ring_space(ring)) + if (unlikely(ring_space(ring) < buf_num)) return -EBUSY; *bnum = buf_num; @@ -1209,6 +1239,20 @@ static int hns3_nic_net_set_mac_address(struct net_device *netdev, void *p) return 0; } +static int hns3_nic_do_ioctl(struct net_device *netdev, + struct ifreq *ifr, int cmd) +{ + struct hnae3_handle *h = hns3_get_handle(netdev); + + if (!netif_running(netdev)) + return -EINVAL; + + if (!h->ae_algo->ops->do_ioctl) + return -EOPNOTSUPP; + + return h->ae_algo->ops->do_ioctl(h, ifr, cmd); +} + static int hns3_nic_set_features(struct net_device *netdev, netdev_features_t features) { @@ -1535,6 +1579,7 @@ static const struct net_device_ops hns3_nic_netdev_ops = { .ndo_start_xmit = hns3_nic_net_xmit, .ndo_tx_timeout = hns3_nic_net_timeout, .ndo_set_mac_address = hns3_nic_net_set_mac_address, + .ndo_do_ioctl = hns3_nic_do_ioctl, .ndo_change_mtu = hns3_nic_change_mtu, .ndo_set_features = hns3_nic_set_features, .ndo_get_stats64 = hns3_nic_get_stats64, @@ -1762,7 +1807,7 @@ static int hns3_map_buffer(struct hns3_enet_ring *ring, struct hns3_desc_cb *cb) cb->dma = dma_map_page(ring_to_dev(ring), cb->priv, 0, cb->length, ring_to_dma_dir(ring)); - if (dma_mapping_error(ring_to_dev(ring), cb->dma)) + if (unlikely(dma_mapping_error(ring_to_dev(ring), cb->dma))) return -EIO; return 0; @@ -1925,9 +1970,10 @@ static int is_valid_clean_head(struct hns3_enet_ring *ring, int h) return u > c ? (h > c && h <= u) : (h > c || h <= u); } -bool hns3_clean_tx_ring(struct hns3_enet_ring *ring, int budget) +void hns3_clean_tx_ring(struct hns3_enet_ring *ring) { struct net_device *netdev = ring->tqp->handle->kinfo.netdev; + struct hns3_nic_priv *priv = netdev_priv(netdev); struct netdev_queue *dev_queue; int bytes, pkts; int head; @@ -1936,7 +1982,7 @@ bool hns3_clean_tx_ring(struct hns3_enet_ring *ring, int budget) rmb(); /* Make sure head is ready before touch any data */ if (is_ring_empty(ring) || head == ring->next_to_clean) - return true; /* no data to poll */ + return; /* no data to poll */ if (unlikely(!is_valid_clean_head(ring, head))) { netdev_err(netdev, "wrong head (%d, %d-%d)\n", head, @@ -1945,16 +1991,15 @@ bool hns3_clean_tx_ring(struct hns3_enet_ring *ring, int budget) u64_stats_update_begin(&ring->syncp); ring->stats.io_err_cnt++; u64_stats_update_end(&ring->syncp); - return true; + return; } bytes = 0; pkts = 0; - while (head != ring->next_to_clean && budget) { + while (head != ring->next_to_clean) { hns3_nic_reclaim_one_desc(ring, &bytes, &pkts); /* Issue prefetch for next Tx descriptor */ prefetch(&ring->desc_cb[ring->next_to_clean]); - budget--; } ring->tqp_vector->tx_group.total_bytes += bytes; @@ -1974,13 +2019,12 @@ bool hns3_clean_tx_ring(struct hns3_enet_ring *ring, int budget) * sees the new next_to_clean. */ smp_mb(); - if (netif_tx_queue_stopped(dev_queue)) { + if (netif_tx_queue_stopped(dev_queue) && + !test_bit(HNS3_NIC_STATE_DOWN, &priv->state)) { netif_tx_wake_queue(dev_queue); ring->stats.restart_queue++; } } - - return !!budget; } static int hns3_desc_unused(struct hns3_enet_ring *ring) @@ -2105,7 +2149,6 @@ static void hns3_rx_checksum(struct hns3_enet_ring *ring, struct sk_buff *skb, hnae3_get_bit(l234info, HNS3_RXD_L4E_B) || hnae3_get_bit(l234info, HNS3_RXD_OL3E_B) || hnae3_get_bit(l234info, HNS3_RXD_OL4E_B))) { - netdev_err(netdev, "L3/L4 error pkt\n"); u64_stats_update_begin(&ring->syncp); ring->stats.l3l4_csum_err++; u64_stats_update_end(&ring->syncp); @@ -2134,6 +2177,8 @@ static void hns3_rx_checksum(struct hns3_enet_ring *ring, struct sk_buff *skb, l4_type == HNS3_L4_TYPE_SCTP)) skb->ip_summed = CHECKSUM_UNNECESSARY; break; + default: + break; } } @@ -2282,8 +2327,6 @@ static int hns3_handle_rx_bd(struct hns3_enet_ring *ring, } if (unlikely(!hnae3_get_bit(bd_base_info, HNS3_RXD_VLD_B))) { - netdev_err(netdev, "no valid bd,%016llx,%016llx\n", - ((u64 *)desc)[0], ((u64 *)desc)[1]); u64_stats_update_begin(&ring->syncp); ring->stats.non_vld_descs++; u64_stats_update_end(&ring->syncp); @@ -2294,7 +2337,6 @@ static int hns3_handle_rx_bd(struct hns3_enet_ring *ring, if (unlikely((!desc->rx.pkt_len) || hnae3_get_bit(l234info, HNS3_RXD_TRUNCAT_B))) { - netdev_err(netdev, "truncated pkt\n"); u64_stats_update_begin(&ring->syncp); ring->stats.err_pkt_len++; u64_stats_update_end(&ring->syncp); @@ -2304,7 +2346,6 @@ static int hns3_handle_rx_bd(struct hns3_enet_ring *ring, } if (unlikely(hnae3_get_bit(l234info, HNS3_RXD_L2E_B))) { - netdev_err(netdev, "L2 error pkt\n"); u64_stats_update_begin(&ring->syncp); ring->stats.l2_err++; u64_stats_update_end(&ring->syncp); @@ -2514,10 +2555,8 @@ static int hns3_nic_common_poll(struct napi_struct *napi, int budget) /* Since the actual Tx work is minimal, we can give the Tx a larger * budget and be more aggressive about cleaning up the Tx descriptors. */ - hns3_for_each_ring(ring, tqp_vector->tx_group) { - if (!hns3_clean_tx_ring(ring, budget)) - clean_complete = false; - } + hns3_for_each_ring(ring, tqp_vector->tx_group) + hns3_clean_tx_ring(ring); /* make sure rx ring budget not smaller than 1 */ rx_budget = max(budget / tqp_vector->num_tqps, 1); @@ -2640,6 +2679,23 @@ static void hns3_add_ring_to_group(struct hns3_enet_ring_group *group, group->count++; } +static void hns3_nic_set_cpumask(struct hns3_nic_priv *priv) +{ + struct pci_dev *pdev = priv->ae_handle->pdev; + struct hns3_enet_tqp_vector *tqp_vector; + int num_vectors = priv->vector_num; + int numa_node; + int vector_i; + + numa_node = dev_to_node(&pdev->dev); + + for (vector_i = 0; vector_i < num_vectors; vector_i++) { + tqp_vector = &priv->tqp_vector[vector_i]; + cpumask_set_cpu(cpumask_local_spread(vector_i, numa_node), + &tqp_vector->affinity_mask); + } +} + static int hns3_nic_init_vector_data(struct hns3_nic_priv *priv) { struct hnae3_ring_chain_node vector_ring_chain; @@ -2648,6 +2704,8 @@ static int hns3_nic_init_vector_data(struct hns3_nic_priv *priv) int ret = 0; u16 i; + hns3_nic_set_cpumask(priv); + for (i = 0; i < priv->vector_num; i++) { tqp_vector = &priv->tqp_vector[i]; hns3_vector_gl_rl_init_hw(tqp_vector, priv); diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h index cb450d7ec8c1..4a56c3d2204f 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h +++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h @@ -491,7 +491,9 @@ struct hns3_enet_tqp_vector { struct hns3_enet_ring_group rx_group; struct hns3_enet_ring_group tx_group; + cpumask_t affinity_mask; u16 num_tqps; /* total number of tqps in TQP vector */ + struct irq_affinity_notify affinity_notify; char name[HNAE3_INT_NAME_LEN]; @@ -615,7 +617,7 @@ void hns3_ethtool_set_ops(struct net_device *netdev); int hns3_set_channels(struct net_device *netdev, struct ethtool_channels *ch); -bool hns3_clean_tx_ring(struct hns3_enet_ring *ring, int budget); +void hns3_clean_tx_ring(struct hns3_enet_ring *ring); int hns3_init_all_ring(struct hns3_nic_priv *priv); int hns3_uninit_all_ring(struct hns3_nic_priv *priv); int hns3_nic_reset_all_ring(struct hnae3_handle *h); diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c b/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c index 3019007d7ceb..8803a8721c8e 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c @@ -22,13 +22,13 @@ struct hns3_stats { static const struct hns3_stats hns3_txq_stats[] = { /* Tx per-queue statistics */ HNS3_TQP_STAT("io_err_cnt", io_err_cnt), - HNS3_TQP_STAT("tx_dropped", sw_err_cnt), + HNS3_TQP_STAT("dropped", sw_err_cnt), HNS3_TQP_STAT("seg_pkt_cnt", seg_pkt_cnt), HNS3_TQP_STAT("packets", tx_pkts), HNS3_TQP_STAT("bytes", tx_bytes), HNS3_TQP_STAT("errors", tx_err_cnt), - HNS3_TQP_STAT("tx_wake", restart_queue), - HNS3_TQP_STAT("tx_busy", tx_busy), + HNS3_TQP_STAT("wake", restart_queue), + HNS3_TQP_STAT("busy", tx_busy), }; #define HNS3_TXQ_STATS_COUNT ARRAY_SIZE(hns3_txq_stats) @@ -36,7 +36,7 @@ static const struct hns3_stats hns3_txq_stats[] = { static const struct hns3_stats hns3_rxq_stats[] = { /* Rx per-queue statistics */ HNS3_TQP_STAT("io_err_cnt", io_err_cnt), - HNS3_TQP_STAT("rx_dropped", sw_err_cnt), + HNS3_TQP_STAT("dropped", sw_err_cnt), HNS3_TQP_STAT("seg_pkt_cnt", seg_pkt_cnt), HNS3_TQP_STAT("packets", rx_pkts), HNS3_TQP_STAT("bytes", rx_bytes), @@ -200,7 +200,7 @@ static void hns3_lb_clear_tx_ring(struct hns3_nic_priv *priv, u32 start_ringid, for (i = start_ringid; i <= end_ringid; i++) { struct hns3_enet_ring *ring = priv->ring_data[i].ring; - hns3_clean_tx_ring(ring, budget); + hns3_clean_tx_ring(ring); } } @@ -351,9 +351,10 @@ static int hns3_get_sset_count(struct net_device *netdev, int stringset) case ETH_SS_TEST: return ops->get_sset_count(h, stringset); - } - return 0; + default: + return -EOPNOTSUPP; + } } static void *hns3_update_strings(u8 *data, const struct hns3_stats *stats, @@ -369,7 +370,7 @@ static void *hns3_update_strings(u8 *data, const struct hns3_stats *stats, data[ETH_GSTRING_LEN - 1] = '\0'; /* first, prepend the prefix string */ - n1 = snprintf(data, MAX_PREFIX_SIZE, "%s#%d_", + n1 = snprintf(data, MAX_PREFIX_SIZE, "%s%d_", prefix, i); n1 = min_t(uint, n1, MAX_PREFIX_SIZE - 1); size_left = (ETH_GSTRING_LEN - 1) - n1; @@ -417,6 +418,8 @@ static void hns3_get_strings(struct net_device *netdev, u32 stringset, u8 *data) case ETH_SS_TEST: ops->get_strings(h, stringset, data); break; + default: + break; } } @@ -542,55 +545,67 @@ static int hns3_set_pauseparam(struct net_device *netdev, return -EOPNOTSUPP; } +static void hns3_get_ksettings(struct hnae3_handle *h, + struct ethtool_link_ksettings *cmd) +{ + const struct hnae3_ae_ops *ops = h->ae_algo->ops; + + /* 1.auto_neg & speed & duplex from cmd */ + if (ops->get_ksettings_an_result) + ops->get_ksettings_an_result(h, + &cmd->base.autoneg, + &cmd->base.speed, + &cmd->base.duplex); + + /* 2.get link mode*/ + if (ops->get_link_mode) + ops->get_link_mode(h, + cmd->link_modes.supported, + cmd->link_modes.advertising); + + /* 3.mdix_ctrl&mdix get from phy reg */ + if (ops->get_mdix_mode) + ops->get_mdix_mode(h, &cmd->base.eth_tp_mdix_ctrl, + &cmd->base.eth_tp_mdix); +} + static int hns3_get_link_ksettings(struct net_device *netdev, struct ethtool_link_ksettings *cmd) { struct hnae3_handle *h = hns3_get_handle(netdev); const struct hnae3_ae_ops *ops; + u8 media_type; u8 link_stat; if (!h->ae_algo || !h->ae_algo->ops) return -EOPNOTSUPP; ops = h->ae_algo->ops; - if (ops->get_port_type) - ops->get_port_type(h, &cmd->base.port); + if (ops->get_media_type) + ops->get_media_type(h, &media_type); else return -EOPNOTSUPP; - switch (cmd->base.port) { - case PORT_FIBRE: - /* 1.auto_neg & speed & duplex from cmd */ - if (ops->get_ksettings_an_result) - ops->get_ksettings_an_result(h, - &cmd->base.autoneg, - &cmd->base.speed, - &cmd->base.duplex); - else - return -EOPNOTSUPP; - - /* 2.get link mode*/ - if (ops->get_link_mode) - ops->get_link_mode(h, - cmd->link_modes.supported, - cmd->link_modes.advertising); - - /* 3.mdix_ctrl&mdix get from phy reg */ - if (ops->get_mdix_mode) - ops->get_mdix_mode(h, &cmd->base.eth_tp_mdix_ctrl, - &cmd->base.eth_tp_mdix); - + switch (media_type) { + case HNAE3_MEDIA_TYPE_NONE: + cmd->base.port = PORT_NONE; + hns3_get_ksettings(h, cmd); break; - case PORT_TP: + case HNAE3_MEDIA_TYPE_FIBER: + cmd->base.port = PORT_FIBRE; + hns3_get_ksettings(h, cmd); + break; + case HNAE3_MEDIA_TYPE_COPPER: if (!netdev->phydev) return -EOPNOTSUPP; + cmd->base.port = PORT_TP; phy_ethtool_ksettings_get(netdev->phydev, cmd); break; default: - netdev_warn(netdev, - "Unknown port type, neither Fibre/Copper detected"); + + netdev_warn(netdev, "Unknown media type"); return 0; } diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_dcb.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_dcb.c index f08ebb7caaaf..92f19384e258 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_dcb.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_dcb.c @@ -73,6 +73,7 @@ static int hclge_ieee_getets(struct hnae3_handle *h, struct ieee_ets *ets) static int hclge_ets_validate(struct hclge_dev *hdev, struct ieee_ets *ets, u8 *tc, bool *changed) { + bool has_ets_tc = false; u32 total_ets_bw = 0; u8 max_tc = 0; u8 i; @@ -100,13 +101,14 @@ static int hclge_ets_validate(struct hclge_dev *hdev, struct ieee_ets *ets, *changed = true; total_ets_bw += ets->tc_tx_bw[i]; - break; + has_ets_tc = true; + break; default: return -EINVAL; } } - if (total_ets_bw != BW_PERCENT) + if (has_ets_tc && total_ets_bw != BW_PERCENT) return -EINVAL; *tc = max_tc + 1; diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c index c56db06b63e0..2de5a0061dc9 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c @@ -24,8 +24,6 @@ #define HCLGE_NAME "hclge" #define HCLGE_STATS_READ(p, offset) (*((u64 *)((u8 *)(p) + (offset)))) #define HCLGE_MAC_STATS_FIELD_OFF(f) (offsetof(struct hclge_mac_stats, f)) -#define HCLGE_64BIT_STATS_FIELD_OFF(f) (offsetof(struct hclge_64_bit_stats, f)) -#define HCLGE_32BIT_STATS_FIELD_OFF(f) (offsetof(struct hclge_32_bit_stats, f)) static int hclge_set_mta_filter_mode(struct hclge_dev *hdev, enum hclge_mta_dmac_sel_type mta_mac_sel, @@ -56,170 +54,6 @@ static const char hns3_nic_test_strs[][ETH_GSTRING_LEN] = { "Phy Loopback test" }; -static const struct hclge_comm_stats_str g_all_64bit_stats_string[] = { - {"igu_rx_oversize_pkt", - HCLGE_64BIT_STATS_FIELD_OFF(igu_rx_oversize_pkt)}, - {"igu_rx_undersize_pkt", - HCLGE_64BIT_STATS_FIELD_OFF(igu_rx_undersize_pkt)}, - {"igu_rx_out_all_pkt", - HCLGE_64BIT_STATS_FIELD_OFF(igu_rx_out_all_pkt)}, - {"igu_rx_uni_pkt", - HCLGE_64BIT_STATS_FIELD_OFF(igu_rx_uni_pkt)}, - {"igu_rx_multi_pkt", - HCLGE_64BIT_STATS_FIELD_OFF(igu_rx_multi_pkt)}, - {"igu_rx_broad_pkt", - HCLGE_64BIT_STATS_FIELD_OFF(igu_rx_broad_pkt)}, - {"egu_tx_out_all_pkt", - HCLGE_64BIT_STATS_FIELD_OFF(egu_tx_out_all_pkt)}, - {"egu_tx_uni_pkt", - HCLGE_64BIT_STATS_FIELD_OFF(egu_tx_uni_pkt)}, - {"egu_tx_multi_pkt", - HCLGE_64BIT_STATS_FIELD_OFF(egu_tx_multi_pkt)}, - {"egu_tx_broad_pkt", - HCLGE_64BIT_STATS_FIELD_OFF(egu_tx_broad_pkt)}, - {"ssu_ppp_mac_key_num", - HCLGE_64BIT_STATS_FIELD_OFF(ssu_ppp_mac_key_num)}, - {"ssu_ppp_host_key_num", - HCLGE_64BIT_STATS_FIELD_OFF(ssu_ppp_host_key_num)}, - {"ppp_ssu_mac_rlt_num", - HCLGE_64BIT_STATS_FIELD_OFF(ppp_ssu_mac_rlt_num)}, - {"ppp_ssu_host_rlt_num", - HCLGE_64BIT_STATS_FIELD_OFF(ppp_ssu_host_rlt_num)}, - {"ssu_tx_in_num", - HCLGE_64BIT_STATS_FIELD_OFF(ssu_tx_in_num)}, - {"ssu_tx_out_num", - HCLGE_64BIT_STATS_FIELD_OFF(ssu_tx_out_num)}, - {"ssu_rx_in_num", - HCLGE_64BIT_STATS_FIELD_OFF(ssu_rx_in_num)}, - {"ssu_rx_out_num", - HCLGE_64BIT_STATS_FIELD_OFF(ssu_rx_out_num)} -}; - -static const struct hclge_comm_stats_str g_all_32bit_stats_string[] = { - {"igu_rx_err_pkt", - HCLGE_32BIT_STATS_FIELD_OFF(igu_rx_err_pkt)}, - {"igu_rx_no_eof_pkt", - HCLGE_32BIT_STATS_FIELD_OFF(igu_rx_no_eof_pkt)}, - {"igu_rx_no_sof_pkt", - HCLGE_32BIT_STATS_FIELD_OFF(igu_rx_no_sof_pkt)}, - {"egu_tx_1588_pkt", - HCLGE_32BIT_STATS_FIELD_OFF(egu_tx_1588_pkt)}, - {"ssu_full_drop_num", - HCLGE_32BIT_STATS_FIELD_OFF(ssu_full_drop_num)}, - {"ssu_part_drop_num", - HCLGE_32BIT_STATS_FIELD_OFF(ssu_part_drop_num)}, - {"ppp_key_drop_num", - HCLGE_32BIT_STATS_FIELD_OFF(ppp_key_drop_num)}, - {"ppp_rlt_drop_num", - HCLGE_32BIT_STATS_FIELD_OFF(ppp_rlt_drop_num)}, - {"ssu_key_drop_num", - HCLGE_32BIT_STATS_FIELD_OFF(ssu_key_drop_num)}, - {"pkt_curr_buf_cnt", - HCLGE_32BIT_STATS_FIELD_OFF(pkt_curr_buf_cnt)}, - {"qcn_fb_rcv_cnt", - HCLGE_32BIT_STATS_FIELD_OFF(qcn_fb_rcv_cnt)}, - {"qcn_fb_drop_cnt", - HCLGE_32BIT_STATS_FIELD_OFF(qcn_fb_drop_cnt)}, - {"qcn_fb_invaild_cnt", - HCLGE_32BIT_STATS_FIELD_OFF(qcn_fb_invaild_cnt)}, - {"rx_packet_tc0_in_cnt", - HCLGE_32BIT_STATS_FIELD_OFF(rx_packet_tc0_in_cnt)}, - {"rx_packet_tc1_in_cnt", - HCLGE_32BIT_STATS_FIELD_OFF(rx_packet_tc1_in_cnt)}, - {"rx_packet_tc2_in_cnt", - HCLGE_32BIT_STATS_FIELD_OFF(rx_packet_tc2_in_cnt)}, - {"rx_packet_tc3_in_cnt", - HCLGE_32BIT_STATS_FIELD_OFF(rx_packet_tc3_in_cnt)}, - {"rx_packet_tc4_in_cnt", - HCLGE_32BIT_STATS_FIELD_OFF(rx_packet_tc4_in_cnt)}, - {"rx_packet_tc5_in_cnt", - HCLGE_32BIT_STATS_FIELD_OFF(rx_packet_tc5_in_cnt)}, - {"rx_packet_tc6_in_cnt", - HCLGE_32BIT_STATS_FIELD_OFF(rx_packet_tc6_in_cnt)}, - {"rx_packet_tc7_in_cnt", - HCLGE_32BIT_STATS_FIELD_OFF(rx_packet_tc7_in_cnt)}, - {"rx_packet_tc0_out_cnt", - HCLGE_32BIT_STATS_FIELD_OFF(rx_packet_tc0_out_cnt)}, - {"rx_packet_tc1_out_cnt", - HCLGE_32BIT_STATS_FIELD_OFF(rx_packet_tc1_out_cnt)}, - {"rx_packet_tc2_out_cnt", - HCLGE_32BIT_STATS_FIELD_OFF(rx_packet_tc2_out_cnt)}, - {"rx_packet_tc3_out_cnt", - HCLGE_32BIT_STATS_FIELD_OFF(rx_packet_tc3_out_cnt)}, - {"rx_packet_tc4_out_cnt", - HCLGE_32BIT_STATS_FIELD_OFF(rx_packet_tc4_out_cnt)}, - {"rx_packet_tc5_out_cnt", - HCLGE_32BIT_STATS_FIELD_OFF(rx_packet_tc5_out_cnt)}, - {"rx_packet_tc6_out_cnt", - HCLGE_32BIT_STATS_FIELD_OFF(rx_packet_tc6_out_cnt)}, - {"rx_packet_tc7_out_cnt", - HCLGE_32BIT_STATS_FIELD_OFF(rx_packet_tc7_out_cnt)}, - {"tx_packet_tc0_in_cnt", - HCLGE_32BIT_STATS_FIELD_OFF(tx_packet_tc0_in_cnt)}, - {"tx_packet_tc1_in_cnt", - HCLGE_32BIT_STATS_FIELD_OFF(tx_packet_tc1_in_cnt)}, - {"tx_packet_tc2_in_cnt", - HCLGE_32BIT_STATS_FIELD_OFF(tx_packet_tc2_in_cnt)}, - {"tx_packet_tc3_in_cnt", - HCLGE_32BIT_STATS_FIELD_OFF(tx_packet_tc3_in_cnt)}, - {"tx_packet_tc4_in_cnt", - HCLGE_32BIT_STATS_FIELD_OFF(tx_packet_tc4_in_cnt)}, - {"tx_packet_tc5_in_cnt", - HCLGE_32BIT_STATS_FIELD_OFF(tx_packet_tc5_in_cnt)}, - {"tx_packet_tc6_in_cnt", - HCLGE_32BIT_STATS_FIELD_OFF(tx_packet_tc6_in_cnt)}, - {"tx_packet_tc7_in_cnt", - HCLGE_32BIT_STATS_FIELD_OFF(tx_packet_tc7_in_cnt)}, - {"tx_packet_tc0_out_cnt", - HCLGE_32BIT_STATS_FIELD_OFF(tx_packet_tc0_out_cnt)}, - {"tx_packet_tc1_out_cnt", - HCLGE_32BIT_STATS_FIELD_OFF(tx_packet_tc1_out_cnt)}, - {"tx_packet_tc2_out_cnt", - HCLGE_32BIT_STATS_FIELD_OFF(tx_packet_tc2_out_cnt)}, - {"tx_packet_tc3_out_cnt", - HCLGE_32BIT_STATS_FIELD_OFF(tx_packet_tc3_out_cnt)}, - {"tx_packet_tc4_out_cnt", - HCLGE_32BIT_STATS_FIELD_OFF(tx_packet_tc4_out_cnt)}, - {"tx_packet_tc5_out_cnt", - HCLGE_32BIT_STATS_FIELD_OFF(tx_packet_tc5_out_cnt)}, - {"tx_packet_tc6_out_cnt", - HCLGE_32BIT_STATS_FIELD_OFF(tx_packet_tc6_out_cnt)}, - {"tx_packet_tc7_out_cnt", - HCLGE_32BIT_STATS_FIELD_OFF(tx_packet_tc7_out_cnt)}, - {"pkt_curr_buf_tc0_cnt", - HCLGE_32BIT_STATS_FIELD_OFF(pkt_curr_buf_tc0_cnt)}, - {"pkt_curr_buf_tc1_cnt", - HCLGE_32BIT_STATS_FIELD_OFF(pkt_curr_buf_tc1_cnt)}, - {"pkt_curr_buf_tc2_cnt", - HCLGE_32BIT_STATS_FIELD_OFF(pkt_curr_buf_tc2_cnt)}, - {"pkt_curr_buf_tc3_cnt", - HCLGE_32BIT_STATS_FIELD_OFF(pkt_curr_buf_tc3_cnt)}, - {"pkt_curr_buf_tc4_cnt", - HCLGE_32BIT_STATS_FIELD_OFF(pkt_curr_buf_tc4_cnt)}, - {"pkt_curr_buf_tc5_cnt", - HCLGE_32BIT_STATS_FIELD_OFF(pkt_curr_buf_tc5_cnt)}, - {"pkt_curr_buf_tc6_cnt", - HCLGE_32BIT_STATS_FIELD_OFF(pkt_curr_buf_tc6_cnt)}, - {"pkt_curr_buf_tc7_cnt", - HCLGE_32BIT_STATS_FIELD_OFF(pkt_curr_buf_tc7_cnt)}, - {"mb_uncopy_num", - HCLGE_32BIT_STATS_FIELD_OFF(mb_uncopy_num)}, - {"lo_pri_unicast_rlt_drop_num", - HCLGE_32BIT_STATS_FIELD_OFF(lo_pri_unicast_rlt_drop_num)}, - {"hi_pri_multicast_rlt_drop_num", - HCLGE_32BIT_STATS_FIELD_OFF(hi_pri_multicast_rlt_drop_num)}, - {"lo_pri_multicast_rlt_drop_num", - HCLGE_32BIT_STATS_FIELD_OFF(lo_pri_multicast_rlt_drop_num)}, - {"rx_oq_drop_pkt_cnt", - HCLGE_32BIT_STATS_FIELD_OFF(rx_oq_drop_pkt_cnt)}, - {"tx_oq_drop_pkt_cnt", - HCLGE_32BIT_STATS_FIELD_OFF(tx_oq_drop_pkt_cnt)}, - {"nic_l2_err_drop_pkt_cnt", - HCLGE_32BIT_STATS_FIELD_OFF(nic_l2_err_drop_pkt_cnt)}, - {"roc_l2_err_drop_pkt_cnt", - HCLGE_32BIT_STATS_FIELD_OFF(roc_l2_err_drop_pkt_cnt)} -}; - static const struct hclge_comm_stats_str g_mac_stats_string[] = { {"mac_tx_mac_pause_num", HCLGE_MAC_STATS_FIELD_OFF(mac_tx_mac_pause_num)}, @@ -394,109 +228,6 @@ static const struct hclge_mac_mgr_tbl_entry_cmd hclge_mgr_table[] = { }, }; -static int hclge_64_bit_update_stats(struct hclge_dev *hdev) -{ -#define HCLGE_64_BIT_CMD_NUM 5 -#define HCLGE_64_BIT_RTN_DATANUM 4 - u64 *data = (u64 *)(&hdev->hw_stats.all_64_bit_stats); - struct hclge_desc desc[HCLGE_64_BIT_CMD_NUM]; - __le64 *desc_data; - int i, k, n; - int ret; - - hclge_cmd_setup_basic_desc(&desc[0], HCLGE_OPC_STATS_64_BIT, true); - ret = hclge_cmd_send(&hdev->hw, desc, HCLGE_64_BIT_CMD_NUM); - if (ret) { - dev_err(&hdev->pdev->dev, - "Get 64 bit pkt stats fail, status = %d.\n", ret); - return ret; - } - - for (i = 0; i < HCLGE_64_BIT_CMD_NUM; i++) { - if (unlikely(i == 0)) { - desc_data = (__le64 *)(&desc[i].data[0]); - n = HCLGE_64_BIT_RTN_DATANUM - 1; - } else { - desc_data = (__le64 *)(&desc[i]); - n = HCLGE_64_BIT_RTN_DATANUM; - } - for (k = 0; k < n; k++) { - *data++ += le64_to_cpu(*desc_data); - desc_data++; - } - } - - return 0; -} - -static void hclge_reset_partial_32bit_counter(struct hclge_32_bit_stats *stats) -{ - stats->pkt_curr_buf_cnt = 0; - stats->pkt_curr_buf_tc0_cnt = 0; - stats->pkt_curr_buf_tc1_cnt = 0; - stats->pkt_curr_buf_tc2_cnt = 0; - stats->pkt_curr_buf_tc3_cnt = 0; - stats->pkt_curr_buf_tc4_cnt = 0; - stats->pkt_curr_buf_tc5_cnt = 0; - stats->pkt_curr_buf_tc6_cnt = 0; - stats->pkt_curr_buf_tc7_cnt = 0; -} - -static int hclge_32_bit_update_stats(struct hclge_dev *hdev) -{ -#define HCLGE_32_BIT_CMD_NUM 8 -#define HCLGE_32_BIT_RTN_DATANUM 8 - - struct hclge_desc desc[HCLGE_32_BIT_CMD_NUM]; - struct hclge_32_bit_stats *all_32_bit_stats; - __le32 *desc_data; - int i, k, n; - u64 *data; - int ret; - - all_32_bit_stats = &hdev->hw_stats.all_32_bit_stats; - data = (u64 *)(&all_32_bit_stats->egu_tx_1588_pkt); - - hclge_cmd_setup_basic_desc(&desc[0], HCLGE_OPC_STATS_32_BIT, true); - ret = hclge_cmd_send(&hdev->hw, desc, HCLGE_32_BIT_CMD_NUM); - if (ret) { - dev_err(&hdev->pdev->dev, - "Get 32 bit pkt stats fail, status = %d.\n", ret); - - return ret; - } - - hclge_reset_partial_32bit_counter(all_32_bit_stats); - for (i = 0; i < HCLGE_32_BIT_CMD_NUM; i++) { - if (unlikely(i == 0)) { - __le16 *desc_data_16bit; - - all_32_bit_stats->igu_rx_err_pkt += - le32_to_cpu(desc[i].data[0]); - - desc_data_16bit = (__le16 *)&desc[i].data[1]; - all_32_bit_stats->igu_rx_no_eof_pkt += - le16_to_cpu(*desc_data_16bit); - - desc_data_16bit++; - all_32_bit_stats->igu_rx_no_sof_pkt += - le16_to_cpu(*desc_data_16bit); - - desc_data = &desc[i].data[2]; - n = HCLGE_32_BIT_RTN_DATANUM - 4; - } else { - desc_data = (__le32 *)&desc[i]; - n = HCLGE_32_BIT_RTN_DATANUM; - } - for (k = 0; k < n; k++) { - *data++ += le32_to_cpu(*desc_data); - desc_data++; - } - } - - return 0; -} - static int hclge_mac_update_stats(struct hclge_dev *hdev) { #define HCLGE_MAC_CMD_NUM 21 @@ -623,7 +354,7 @@ static u8 *hclge_tqps_get_strings(struct hnae3_handle *handle, u8 *data) for (i = 0; i < kinfo->num_tqps; i++) { struct hclge_tqp *tqp = container_of(handle->kinfo.tqp[i], struct hclge_tqp, q); - snprintf(buff, ETH_GSTRING_LEN, "txq#%d_pktnum_rcd", + snprintf(buff, ETH_GSTRING_LEN, "txq%d_pktnum_rcd", tqp->index); buff = buff + ETH_GSTRING_LEN; } @@ -631,7 +362,7 @@ static u8 *hclge_tqps_get_strings(struct hnae3_handle *handle, u8 *data) for (i = 0; i < kinfo->num_tqps; i++) { struct hclge_tqp *tqp = container_of(kinfo->tqp[i], struct hclge_tqp, q); - snprintf(buff, ETH_GSTRING_LEN, "rxq#%d_pktnum_rcd", + snprintf(buff, ETH_GSTRING_LEN, "rxq%d_pktnum_rcd", tqp->index); buff = buff + ETH_GSTRING_LEN; } @@ -675,14 +406,8 @@ static void hclge_update_netstat(struct hclge_hw_stats *hw_stats, struct net_device_stats *net_stats) { net_stats->tx_dropped = 0; - net_stats->rx_dropped = hw_stats->all_32_bit_stats.ssu_full_drop_num; - net_stats->rx_dropped += hw_stats->all_32_bit_stats.ppp_key_drop_num; - net_stats->rx_dropped += hw_stats->all_32_bit_stats.ssu_key_drop_num; - net_stats->rx_errors = hw_stats->mac_stats.mac_rx_oversize_pkt_num; net_stats->rx_errors += hw_stats->mac_stats.mac_rx_undersize_pkt_num; - net_stats->rx_errors += hw_stats->all_32_bit_stats.igu_rx_no_eof_pkt; - net_stats->rx_errors += hw_stats->all_32_bit_stats.igu_rx_no_sof_pkt; net_stats->rx_errors += hw_stats->mac_stats.mac_rx_fcs_err_pkt_num; net_stats->multicast = hw_stats->mac_stats.mac_tx_multi_pkt_num; @@ -717,12 +442,6 @@ static void hclge_update_stats_for_all(struct hclge_dev *hdev) dev_err(&hdev->pdev->dev, "Update MAC stats fail, status = %d.\n", status); - status = hclge_32_bit_update_stats(hdev); - if (status) - dev_err(&hdev->pdev->dev, - "Update 32 bit stats fail, status = %d.\n", - status); - hclge_update_netstat(&hdev->hw_stats, &handle->kinfo.netdev->stats); } @@ -743,18 +462,6 @@ static void hclge_update_stats(struct hnae3_handle *handle, "Update MAC stats fail, status = %d.\n", status); - status = hclge_32_bit_update_stats(hdev); - if (status) - dev_err(&hdev->pdev->dev, - "Update 32 bit stats fail, status = %d.\n", - status); - - status = hclge_64_bit_update_stats(hdev); - if (status) - dev_err(&hdev->pdev->dev, - "Update 64 bit stats fail, status = %d.\n", - status); - status = hclge_tqps_update_stats(handle); if (status) dev_err(&hdev->pdev->dev, @@ -793,8 +500,6 @@ static int hclge_get_sset_count(struct hnae3_handle *handle, int stringset) handle->flags |= HNAE3_SUPPORT_SERDES_LOOPBACK; } else if (stringset == ETH_SS_STATS) { count = ARRAY_SIZE(g_mac_stats_string) + - ARRAY_SIZE(g_all_32bit_stats_string) + - ARRAY_SIZE(g_all_64bit_stats_string) + hclge_tqps_get_sset_count(handle, stringset); } @@ -814,16 +519,6 @@ static void hclge_get_strings(struct hnae3_handle *handle, g_mac_stats_string, size, p); - size = ARRAY_SIZE(g_all_32bit_stats_string); - p = hclge_comm_get_strings(stringset, - g_all_32bit_stats_string, - size, - p); - size = ARRAY_SIZE(g_all_64bit_stats_string); - p = hclge_comm_get_strings(stringset, - g_all_64bit_stats_string, - size, - p); p = hclge_tqps_get_strings(handle, p); } else if (stringset == ETH_SS_TEST) { if (handle->flags & HNAE3_SUPPORT_MAC_LOOPBACK) { @@ -857,14 +552,6 @@ static void hclge_get_stats(struct hnae3_handle *handle, u64 *data) g_mac_stats_string, ARRAY_SIZE(g_mac_stats_string), data); - p = hclge_comm_get_stats(&hdev->hw_stats.all_32_bit_stats, - g_all_32bit_stats_string, - ARRAY_SIZE(g_all_32bit_stats_string), - p); - p = hclge_comm_get_stats(&hdev->hw_stats.all_64_bit_stats, - g_all_64bit_stats_string, - ARRAY_SIZE(g_all_64bit_stats_string), - p); p = hclge_tqps_get_stats(handle, p); } @@ -2376,10 +2063,13 @@ static int hclge_get_mac_phy_link(struct hclge_dev *hdev) int mac_state; int link_stat; + if (test_bit(HCLGE_STATE_DOWN, &hdev->state)) + return 0; + mac_state = hclge_get_mac_link_status(hdev); if (hdev->hw.mac.phydev) { - if (!genphy_read_status(hdev->hw.mac.phydev)) + if (hdev->hw.mac.phydev->state == PHY_RUNNING) link_stat = mac_state & hdev->hw.mac.phydev->link; else @@ -2534,6 +2224,8 @@ static void hclge_clear_event_cause(struct hclge_dev *hdev, u32 event_type, case HCLGE_VECTOR0_EVENT_MBX: hclge_write_dev(&hdev->hw, HCLGE_VECTOR0_CMDQ_SRC_REG, regclr); break; + default: + break; } } @@ -3697,7 +3389,7 @@ static int hclge_set_serdes_loopback(struct hclge_dev *hdev, bool en) struct hclge_desc desc; int ret, i = 0; - req = (struct hclge_serdes_lb_cmd *)&desc.data[0]; + req = (struct hclge_serdes_lb_cmd *)desc.data; hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_SERDES_LOOPBACK, false); if (en) { @@ -3832,6 +3524,8 @@ static void hclge_ae_stop(struct hnae3_handle *handle) struct hclge_dev *hdev = vport->back; int i; + set_bit(HCLGE_STATE_DOWN, &hdev->state); + del_timer_sync(&hdev->service_timer); cancel_work_sync(&hdev->service_task); clear_bit(HCLGE_STATE_SERVICE_SCHED, &hdev->state); @@ -4621,6 +4315,18 @@ static int hclge_set_mac_addr(struct hnae3_handle *handle, void *p, return 0; } +static int hclge_do_ioctl(struct hnae3_handle *handle, struct ifreq *ifr, + int cmd) +{ + struct hclge_vport *vport = hclge_get_vport(handle); + struct hclge_dev *hdev = vport->back; + + if (!hdev->hw.mac.phydev) + return -EOPNOTSUPP; + + return phy_mii_ioctl(hdev->hw.mac.phydev, ifr, cmd); +} + static int hclge_set_vlan_filter_ctrl(struct hclge_dev *hdev, u8 vlan_type, bool filter_en) { @@ -4930,7 +4636,7 @@ static int hclge_set_vlan_protocol_type(struct hclge_dev *hdev) hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_MAC_VLAN_INSERT, false); - tx_req = (struct hclge_tx_vlan_type_cfg_cmd *)&desc.data; + tx_req = (struct hclge_tx_vlan_type_cfg_cmd *)desc.data; tx_req->ot_vlan_type = cpu_to_le16(hdev->vlan_type_cfg.tx_ot_vlan_type); tx_req->in_vlan_type = cpu_to_le16(hdev->vlan_type_cfg.tx_in_vlan_type); @@ -5228,13 +4934,7 @@ static void hclge_set_flowctrl_adv(struct hclge_dev *hdev, u32 rx_en, u32 tx_en) if (!phydev) return; - phydev->advertising &= ~(ADVERTISED_Pause | ADVERTISED_Asym_Pause); - - if (rx_en) - phydev->advertising |= ADVERTISED_Pause | ADVERTISED_Asym_Pause; - - if (tx_en) - phydev->advertising ^= ADVERTISED_Asym_Pause; + phy_set_asym_pause(phydev, rx_en, tx_en); } static int hclge_cfg_pauseparam(struct hclge_dev *hdev, u32 rx_en, u32 tx_en) @@ -5464,26 +5164,31 @@ static int hclge_init_client_instance(struct hnae3_client *client, vport->nic.client = client; ret = client->ops->init_instance(&vport->nic); if (ret) - return ret; + goto clear_nic; ret = hclge_init_instance_hw(hdev); if (ret) { client->ops->uninit_instance(&vport->nic, 0); - return ret; + goto clear_nic; } + hnae3_set_client_init_flag(client, ae_dev, 1); + if (hdev->roce_client && hnae3_dev_roce_supported(hdev)) { struct hnae3_client *rc = hdev->roce_client; ret = hclge_init_roce_base_info(vport); if (ret) - return ret; + goto clear_roce; ret = rc->ops->init_instance(&vport->roce); if (ret) - return ret; + goto clear_roce; + + hnae3_set_client_init_flag(hdev->roce_client, + ae_dev, 1); } break; @@ -5493,7 +5198,9 @@ static int hclge_init_client_instance(struct hnae3_client *client, ret = client->ops->init_instance(&vport->nic); if (ret) - return ret; + goto clear_nic; + + hnae3_set_client_init_flag(client, ae_dev, 1); break; case HNAE3_CLIENT_ROCE: @@ -5505,16 +5212,31 @@ static int hclge_init_client_instance(struct hnae3_client *client, if (hdev->roce_client && hdev->nic_client) { ret = hclge_init_roce_base_info(vport); if (ret) - return ret; + goto clear_roce; ret = client->ops->init_instance(&vport->roce); if (ret) - return ret; + goto clear_roce; + + hnae3_set_client_init_flag(client, ae_dev, 1); } + + break; + default: + return -EINVAL; } } return 0; + +clear_nic: + hdev->nic_client = NULL; + vport->nic.client = NULL; + return ret; +clear_roce: + hdev->roce_client = NULL; + vport->roce.client = NULL; + return ret; } static void hclge_uninit_client_instance(struct hnae3_client *client, @@ -5534,7 +5256,7 @@ static void hclge_uninit_client_instance(struct hnae3_client *client, } if (client->type == HNAE3_CLIENT_ROCE) return; - if (client->ops->uninit_instance) { + if (hdev->nic_client && client->ops->uninit_instance) { hclge_uninit_instance_hw(hdev); client->ops->uninit_instance(&vport->nic, 0); hdev->nic_client = NULL; @@ -6248,27 +5970,6 @@ static void hclge_get_link_mode(struct hnae3_handle *handle, } } -static void hclge_get_port_type(struct hnae3_handle *handle, - u8 *port_type) -{ - struct hclge_vport *vport = hclge_get_vport(handle); - struct hclge_dev *hdev = vport->back; - u8 media_type = hdev->hw.mac.media_type; - - switch (media_type) { - case HNAE3_MEDIA_TYPE_FIBER: - *port_type = PORT_FIBRE; - break; - case HNAE3_MEDIA_TYPE_COPPER: - *port_type = PORT_TP; - break; - case HNAE3_MEDIA_TYPE_UNKNOWN: - default: - *port_type = PORT_OTHER; - break; - } -} - static const struct hnae3_ae_ops hclge_ops = { .init_ae_dev = hclge_init_ae_dev, .uninit_ae_dev = hclge_uninit_ae_dev, @@ -6296,6 +5997,7 @@ static const struct hnae3_ae_ops hclge_ops = { .get_tc_size = hclge_get_tc_size, .get_mac_addr = hclge_get_mac_addr, .set_mac_addr = hclge_set_mac_addr, + .do_ioctl = hclge_do_ioctl, .add_uc_addr = hclge_add_uc_addr, .rm_uc_addr = hclge_rm_uc_addr, .add_mc_addr = hclge_add_mc_addr, @@ -6325,7 +6027,6 @@ static const struct hnae3_ae_ops hclge_ops = { .get_regs = hclge_get_regs, .set_led_id = hclge_set_led_id, .get_link_mode = hclge_get_link_mode, - .get_port_type = hclge_get_port_type, }; static struct hnae3_ae_algo ae_algo = { diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h index 1528fb3fa6be..7841b830a716 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h @@ -256,109 +256,6 @@ struct hclge_comm_stats_str { unsigned long offset; }; -/* all 64bit stats, opcode id: 0x0030 */ -struct hclge_64_bit_stats { - /* query_igu_stat */ - u64 igu_rx_oversize_pkt; - u64 igu_rx_undersize_pkt; - u64 igu_rx_out_all_pkt; - u64 igu_rx_uni_pkt; - u64 igu_rx_multi_pkt; - u64 igu_rx_broad_pkt; - u64 rsv0; - - /* query_egu_stat */ - u64 egu_tx_out_all_pkt; - u64 egu_tx_uni_pkt; - u64 egu_tx_multi_pkt; - u64 egu_tx_broad_pkt; - - /* ssu_ppp packet stats */ - u64 ssu_ppp_mac_key_num; - u64 ssu_ppp_host_key_num; - u64 ppp_ssu_mac_rlt_num; - u64 ppp_ssu_host_rlt_num; - - /* ssu_tx_in_out_dfx_stats */ - u64 ssu_tx_in_num; - u64 ssu_tx_out_num; - /* ssu_rx_in_out_dfx_stats */ - u64 ssu_rx_in_num; - u64 ssu_rx_out_num; -}; - -/* all 32bit stats, opcode id: 0x0031 */ -struct hclge_32_bit_stats { - u64 igu_rx_err_pkt; - u64 igu_rx_no_eof_pkt; - u64 igu_rx_no_sof_pkt; - u64 egu_tx_1588_pkt; - u64 egu_tx_err_pkt; - u64 ssu_full_drop_num; - u64 ssu_part_drop_num; - u64 ppp_key_drop_num; - u64 ppp_rlt_drop_num; - u64 ssu_key_drop_num; - u64 pkt_curr_buf_cnt; - u64 qcn_fb_rcv_cnt; - u64 qcn_fb_drop_cnt; - u64 qcn_fb_invaild_cnt; - u64 rsv0; - u64 rx_packet_tc0_in_cnt; - u64 rx_packet_tc1_in_cnt; - u64 rx_packet_tc2_in_cnt; - u64 rx_packet_tc3_in_cnt; - u64 rx_packet_tc4_in_cnt; - u64 rx_packet_tc5_in_cnt; - u64 rx_packet_tc6_in_cnt; - u64 rx_packet_tc7_in_cnt; - u64 rx_packet_tc0_out_cnt; - u64 rx_packet_tc1_out_cnt; - u64 rx_packet_tc2_out_cnt; - u64 rx_packet_tc3_out_cnt; - u64 rx_packet_tc4_out_cnt; - u64 rx_packet_tc5_out_cnt; - u64 rx_packet_tc6_out_cnt; - u64 rx_packet_tc7_out_cnt; - - /* Tx packet level statistics */ - u64 tx_packet_tc0_in_cnt; - u64 tx_packet_tc1_in_cnt; - u64 tx_packet_tc2_in_cnt; - u64 tx_packet_tc3_in_cnt; - u64 tx_packet_tc4_in_cnt; - u64 tx_packet_tc5_in_cnt; - u64 tx_packet_tc6_in_cnt; - u64 tx_packet_tc7_in_cnt; - u64 tx_packet_tc0_out_cnt; - u64 tx_packet_tc1_out_cnt; - u64 tx_packet_tc2_out_cnt; - u64 tx_packet_tc3_out_cnt; - u64 tx_packet_tc4_out_cnt; - u64 tx_packet_tc5_out_cnt; - u64 tx_packet_tc6_out_cnt; - u64 tx_packet_tc7_out_cnt; - - /* packet buffer statistics */ - u64 pkt_curr_buf_tc0_cnt; - u64 pkt_curr_buf_tc1_cnt; - u64 pkt_curr_buf_tc2_cnt; - u64 pkt_curr_buf_tc3_cnt; - u64 pkt_curr_buf_tc4_cnt; - u64 pkt_curr_buf_tc5_cnt; - u64 pkt_curr_buf_tc6_cnt; - u64 pkt_curr_buf_tc7_cnt; - - u64 mb_uncopy_num; - u64 lo_pri_unicast_rlt_drop_num; - u64 hi_pri_multicast_rlt_drop_num; - u64 lo_pri_multicast_rlt_drop_num; - u64 rx_oq_drop_pkt_cnt; - u64 tx_oq_drop_pkt_cnt; - u64 nic_l2_err_drop_pkt_cnt; - u64 roc_l2_err_drop_pkt_cnt; -}; - /* mac stats ,opcode id: 0x0032 */ struct hclge_mac_stats { u64 mac_tx_mac_pause_num; @@ -450,8 +347,6 @@ struct hclge_mac_stats { #define HCLGE_STATS_TIMER_INTERVAL (60 * 5) struct hclge_hw_stats { struct hclge_mac_stats mac_stats; - struct hclge_64_bit_stats all_64_bit_stats; - struct hclge_32_bit_stats all_32_bit_stats; u32 stats_timer; }; diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mdio.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mdio.c index 398971a062f4..24b1f2a0c32a 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mdio.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mdio.c @@ -10,8 +10,6 @@ #define HCLGE_PHY_SUPPORTED_FEATURES (SUPPORTED_Autoneg | \ SUPPORTED_TP | \ - SUPPORTED_Pause | \ - SUPPORTED_Asym_Pause | \ PHY_10BT_FEATURES | \ PHY_100BT_FEATURES | \ PHY_1000BT_FEATURES) @@ -213,7 +211,7 @@ int hclge_mac_connect_phy(struct hclge_dev *hdev) } phydev->supported &= HCLGE_PHY_SUPPORTED_FEATURES; - phydev->advertising = phydev->supported; + phy_support_asym_pause(phydev); return 0; } diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c index 5db70a1451c5..00bb39451bc5 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c @@ -172,7 +172,7 @@ static int hclge_pfc_pause_en_cfg(struct hclge_dev *hdev, u8 tx_rx_bitmap, u8 pfc_bitmap) { struct hclge_desc desc; - struct hclge_pfc_en_cmd *pfc = (struct hclge_pfc_en_cmd *)&desc.data; + struct hclge_pfc_en_cmd *pfc = (struct hclge_pfc_en_cmd *)desc.data; hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_CFG_PFC_PAUSE_EN, false); @@ -188,7 +188,7 @@ static int hclge_pause_param_cfg(struct hclge_dev *hdev, const u8 *addr, struct hclge_cfg_pause_param_cmd *pause_param; struct hclge_desc desc; - pause_param = (struct hclge_cfg_pause_param_cmd *)&desc.data; + pause_param = (struct hclge_cfg_pause_param_cmd *)desc.data; hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_CFG_MAC_PARA, false); @@ -207,7 +207,7 @@ int hclge_pause_addr_cfg(struct hclge_dev *hdev, const u8 *mac_addr) u8 trans_gap; int ret; - pause_param = (struct hclge_cfg_pause_param_cmd *)&desc.data; + pause_param = (struct hclge_cfg_pause_param_cmd *)desc.data; hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_CFG_MAC_PARA, true); @@ -297,7 +297,7 @@ static int hclge_tm_qs_to_pri_map_cfg(struct hclge_dev *hdev, } static int hclge_tm_q_to_qs_map_cfg(struct hclge_dev *hdev, - u8 q_id, u16 qs_id) + u16 q_id, u16 qs_id) { struct hclge_nq_to_qs_link_cmd *map; struct hclge_desc desc; diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_cmd.c b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_cmd.c index fb471fe2c494..0d3b445f6799 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_cmd.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_cmd.c @@ -132,9 +132,9 @@ static int hclgevf_init_cmd_queue(struct hclgevf_dev *hdev, reg_val |= HCLGEVF_NIC_CMQ_ENABLE; hclgevf_write_dev(hw, HCLGEVF_NIC_CSQ_DEPTH_REG, reg_val); - hclgevf_write_dev(hw, HCLGEVF_NIC_CSQ_TAIL_REG, 0); hclgevf_write_dev(hw, HCLGEVF_NIC_CSQ_HEAD_REG, 0); - break; + hclgevf_write_dev(hw, HCLGEVF_NIC_CSQ_TAIL_REG, 0); + return 0; case HCLGEVF_TYPE_CRQ: reg_val = (u32)ring->desc_dma_addr; hclgevf_write_dev(hw, HCLGEVF_NIC_CRQ_BASEADDR_L_REG, reg_val); @@ -145,12 +145,12 @@ static int hclgevf_init_cmd_queue(struct hclgevf_dev *hdev, reg_val |= HCLGEVF_NIC_CMQ_ENABLE; hclgevf_write_dev(hw, HCLGEVF_NIC_CRQ_DEPTH_REG, reg_val); - hclgevf_write_dev(hw, HCLGEVF_NIC_CRQ_TAIL_REG, 0); hclgevf_write_dev(hw, HCLGEVF_NIC_CRQ_HEAD_REG, 0); - break; + hclgevf_write_dev(hw, HCLGEVF_NIC_CRQ_TAIL_REG, 0); + return 0; + default: + return -EINVAL; } - - return 0; } void hclgevf_cmd_setup_basic_desc(struct hclgevf_desc *desc, diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c index 9c0091f2addf..978193123c71 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c @@ -31,16 +31,15 @@ static inline struct hclgevf_dev *hclgevf_ae_get_hdev( static int hclgevf_tqps_update_stats(struct hnae3_handle *handle) { + struct hnae3_knic_private_info *kinfo = &handle->kinfo; struct hclgevf_dev *hdev = hclgevf_ae_get_hdev(handle); - struct hnae3_queue *queue; struct hclgevf_desc desc; struct hclgevf_tqp *tqp; int status; int i; - for (i = 0; i < hdev->num_tqps; i++) { - queue = handle->kinfo.tqp[i]; - tqp = container_of(queue, struct hclgevf_tqp, q); + for (i = 0; i < kinfo->num_tqps; i++) { + tqp = container_of(kinfo->tqp[i], struct hclgevf_tqp, q); hclgevf_cmd_setup_basic_desc(&desc, HCLGEVF_OPC_QUERY_RX_STATUS, true); @@ -77,17 +76,16 @@ static int hclgevf_tqps_update_stats(struct hnae3_handle *handle) static u64 *hclgevf_tqps_get_stats(struct hnae3_handle *handle, u64 *data) { struct hnae3_knic_private_info *kinfo = &handle->kinfo; - struct hclgevf_dev *hdev = hclgevf_ae_get_hdev(handle); struct hclgevf_tqp *tqp; u64 *buff = data; int i; - for (i = 0; i < hdev->num_tqps; i++) { - tqp = container_of(handle->kinfo.tqp[i], struct hclgevf_tqp, q); + for (i = 0; i < kinfo->num_tqps; i++) { + tqp = container_of(kinfo->tqp[i], struct hclgevf_tqp, q); *buff++ = tqp->tqp_stats.rcb_tx_ring_pktnum_rcd; } for (i = 0; i < kinfo->num_tqps; i++) { - tqp = container_of(handle->kinfo.tqp[i], struct hclgevf_tqp, q); + tqp = container_of(kinfo->tqp[i], struct hclgevf_tqp, q); *buff++ = tqp->tqp_stats.rcb_rx_ring_pktnum_rcd; } @@ -96,29 +94,29 @@ static u64 *hclgevf_tqps_get_stats(struct hnae3_handle *handle, u64 *data) static int hclgevf_tqps_get_sset_count(struct hnae3_handle *handle, int strset) { - struct hclgevf_dev *hdev = hclgevf_ae_get_hdev(handle); + struct hnae3_knic_private_info *kinfo = &handle->kinfo; - return hdev->num_tqps * 2; + return kinfo->num_tqps * 2; } static u8 *hclgevf_tqps_get_strings(struct hnae3_handle *handle, u8 *data) { - struct hclgevf_dev *hdev = hclgevf_ae_get_hdev(handle); + struct hnae3_knic_private_info *kinfo = &handle->kinfo; u8 *buff = data; int i = 0; - for (i = 0; i < hdev->num_tqps; i++) { - struct hclgevf_tqp *tqp = container_of(handle->kinfo.tqp[i], - struct hclgevf_tqp, q); - snprintf(buff, ETH_GSTRING_LEN, "txq#%d_pktnum_rcd", + for (i = 0; i < kinfo->num_tqps; i++) { + struct hclgevf_tqp *tqp = container_of(kinfo->tqp[i], + struct hclgevf_tqp, q); + snprintf(buff, ETH_GSTRING_LEN, "txq%d_pktnum_rcd", tqp->index); buff += ETH_GSTRING_LEN; } - for (i = 0; i < hdev->num_tqps; i++) { - struct hclgevf_tqp *tqp = container_of(handle->kinfo.tqp[i], - struct hclgevf_tqp, q); - snprintf(buff, ETH_GSTRING_LEN, "rxq#%d_pktnum_rcd", + for (i = 0; i < kinfo->num_tqps; i++) { + struct hclgevf_tqp *tqp = container_of(kinfo->tqp[i], + struct hclgevf_tqp, q); + snprintf(buff, ETH_GSTRING_LEN, "rxq%d_pktnum_rcd", tqp->index); buff += ETH_GSTRING_LEN; } @@ -182,7 +180,7 @@ static int hclgevf_get_tc_info(struct hclgevf_dev *hdev) return 0; } -static int hclge_get_queue_info(struct hclgevf_dev *hdev) +static int hclgevf_get_queue_info(struct hclgevf_dev *hdev) { #define HCLGEVF_TQPS_RSS_INFO_LEN 8 u8 resp_msg[HCLGEVF_TQPS_RSS_INFO_LEN]; @@ -299,6 +297,9 @@ void hclgevf_update_link_status(struct hclgevf_dev *hdev, int link_state) client = handle->client; + link_state = + test_bit(HCLGEVF_STATE_DOWN, &hdev->state) ? 0 : link_state; + if (link_state != hdev->hw.mac.link) { client->ops->link_status_change(handle, !!link_state); hdev->hw.mac.link = link_state; @@ -735,14 +736,12 @@ static int hclgevf_get_queue_id(struct hnae3_queue *queue) static void hclgevf_reset_tqp_stats(struct hnae3_handle *handle) { - struct hclgevf_dev *hdev = hclgevf_ae_get_hdev(handle); - struct hnae3_queue *queue; + struct hnae3_knic_private_info *kinfo = &handle->kinfo; struct hclgevf_tqp *tqp; int i; - for (i = 0; i < hdev->num_tqps; i++) { - queue = handle->kinfo.tqp[i]; - tqp = container_of(queue, struct hclgevf_tqp, q); + for (i = 0; i < kinfo->num_tqps; i++) { + tqp = container_of(kinfo->tqp[i], struct hclgevf_tqp, q); memset(&tqp->tqp_stats, 0, sizeof(tqp->tqp_stats)); } } @@ -1341,8 +1340,10 @@ static int hclgevf_configure(struct hclgevf_dev *hdev) { int ret; + hdev->hw.mac.media_type = HNAE3_MEDIA_TYPE_NONE; + /* get queue configuration from PF */ - ret = hclge_get_queue_info(hdev); + ret = hclgevf_get_queue_info(hdev); if (ret) return ret; /* get tc configuration from PF */ @@ -1417,12 +1418,13 @@ static int hclgevf_init_vlan_config(struct hclgevf_dev *hdev) static int hclgevf_ae_start(struct hnae3_handle *handle) { + struct hnae3_knic_private_info *kinfo = &handle->kinfo; struct hclgevf_dev *hdev = hclgevf_ae_get_hdev(handle); int i, queue_id; - for (i = 0; i < handle->kinfo.num_tqps; i++) { + for (i = 0; i < kinfo->num_tqps; i++) { /* ring enable */ - queue_id = hclgevf_get_queue_id(handle->kinfo.tqp[i]); + queue_id = hclgevf_get_queue_id(kinfo->tqp[i]); if (queue_id < 0) { dev_warn(&hdev->pdev->dev, "Get invalid queue id, ignore it\n"); @@ -1445,12 +1447,15 @@ static int hclgevf_ae_start(struct hnae3_handle *handle) static void hclgevf_ae_stop(struct hnae3_handle *handle) { + struct hnae3_knic_private_info *kinfo = &handle->kinfo; struct hclgevf_dev *hdev = hclgevf_ae_get_hdev(handle); int i, queue_id; - for (i = 0; i < hdev->num_tqps; i++) { + set_bit(HCLGEVF_STATE_DOWN, &hdev->state); + + for (i = 0; i < kinfo->num_tqps; i++) { /* Ring disable */ - queue_id = hclgevf_get_queue_id(handle->kinfo.tqp[i]); + queue_id = hclgevf_get_queue_id(kinfo->tqp[i]); if (queue_id < 0) { dev_warn(&hdev->pdev->dev, "Get invalid queue id, ignore it\n"); @@ -1619,17 +1624,22 @@ static int hclgevf_init_client_instance(struct hnae3_client *client, ret = client->ops->init_instance(&hdev->nic); if (ret) - return ret; + goto clear_nic; + + hnae3_set_client_init_flag(client, ae_dev, 1); if (hdev->roce_client && hnae3_dev_roce_supported(hdev)) { struct hnae3_client *rc = hdev->roce_client; ret = hclgevf_init_roce_base_info(hdev); if (ret) - return ret; + goto clear_roce; ret = rc->ops->init_instance(&hdev->roce); if (ret) - return ret; + goto clear_roce; + + hnae3_set_client_init_flag(hdev->roce_client, ae_dev, + 1); } break; case HNAE3_CLIENT_UNIC: @@ -1638,7 +1648,9 @@ static int hclgevf_init_client_instance(struct hnae3_client *client, ret = client->ops->init_instance(&hdev->nic); if (ret) - return ret; + goto clear_nic; + + hnae3_set_client_init_flag(client, ae_dev, 1); break; case HNAE3_CLIENT_ROCE: if (hnae3_dev_roce_supported(hdev)) { @@ -1649,15 +1661,29 @@ static int hclgevf_init_client_instance(struct hnae3_client *client, if (hdev->roce_client && hdev->nic_client) { ret = hclgevf_init_roce_base_info(hdev); if (ret) - return ret; + goto clear_roce; ret = client->ops->init_instance(&hdev->roce); if (ret) - return ret; + goto clear_roce; } + + hnae3_set_client_init_flag(client, ae_dev, 1); + break; + default: + return -EINVAL; } return 0; + +clear_nic: + hdev->nic_client = NULL; + hdev->nic.client = NULL; + return ret; +clear_roce: + hdev->roce_client = NULL; + hdev->roce.client = NULL; + return ret; } static void hclgevf_uninit_client_instance(struct hnae3_client *client, @@ -1666,13 +1692,19 @@ static void hclgevf_uninit_client_instance(struct hnae3_client *client, struct hclgevf_dev *hdev = ae_dev->priv; /* un-init roce, if it exists */ - if (hdev->roce_client) + if (hdev->roce_client) { hdev->roce_client->ops->uninit_instance(&hdev->roce, 0); + hdev->roce_client = NULL; + hdev->roce.client = NULL; + } /* un-init nic/unic, if this was not called by roce client */ - if ((client->ops->uninit_instance) && - (client->type != HNAE3_CLIENT_ROCE)) + if (client->ops->uninit_instance && hdev->nic_client && + client->type != HNAE3_CLIENT_ROCE) { client->ops->uninit_instance(&hdev->nic, 0); + hdev->nic_client = NULL; + hdev->nic.client = NULL; + } } static int hclgevf_pci_init(struct hclgevf_dev *hdev) @@ -1979,6 +2011,14 @@ void hclgevf_update_speed_duplex(struct hclgevf_dev *hdev, u32 speed, hdev->hw.mac.duplex = duplex; } +static void hclgevf_get_media_type(struct hnae3_handle *handle, + u8 *media_type) +{ + struct hclgevf_dev *hdev = hclgevf_ae_get_hdev(handle); + if (media_type) + *media_type = hdev->hw.mac.media_type; +} + static const struct hnae3_ae_ops hclgevf_ops = { .init_ae_dev = hclgevf_init_ae_dev, .uninit_ae_dev = hclgevf_uninit_ae_dev, @@ -2016,6 +2056,7 @@ static const struct hnae3_ae_ops hclgevf_ops = { .get_tqps_and_rss_info = hclgevf_get_tqps_and_rss_info, .get_status = hclgevf_get_status, .get_ksettings_an_result = hclgevf_get_ksettings_an_result, + .get_media_type = hclgevf_get_media_type, }; static struct hnae3_ae_algo ae_algovf = { diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h index b23ba171473c..2af01f107c63 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h +++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h @@ -66,6 +66,7 @@ enum hclgevf_states { #define HCLGEVF_MPF_ENBALE 1 struct hclgevf_mac { + u8 media_type; u8 mac_addr[ETH_ALEN]; int link; u8 duplex; diff --git a/drivers/net/ethernet/hp/hp100.c b/drivers/net/ethernet/hp/hp100.c index c8c7ad2eff77..9b5a68b65432 100644 --- a/drivers/net/ethernet/hp/hp100.c +++ b/drivers/net/ethernet/hp/hp100.c @@ -2634,7 +2634,7 @@ static int hp100_login_to_vg_hub(struct net_device *dev, u_short force_relogin) /* Wait for link to drop */ time = jiffies + (HZ / 10); do { - if (~(hp100_inb(VG_LAN_CFG_1) & HP100_LINK_UP_ST)) + if (!(hp100_inb(VG_LAN_CFG_1) & HP100_LINK_UP_ST)) break; if (!in_interrupt()) schedule_timeout_interruptible(1); diff --git a/drivers/net/ethernet/i825xx/ether1.c b/drivers/net/ethernet/i825xx/ether1.c index dc983450354b..35f6291a3672 100644 --- a/drivers/net/ethernet/i825xx/ether1.c +++ b/drivers/net/ethernet/i825xx/ether1.c @@ -64,7 +64,8 @@ static unsigned int net_debug = NET_DEBUG; #define RX_AREA_END 0x0fc00 static int ether1_open(struct net_device *dev); -static int ether1_sendpacket(struct sk_buff *skb, struct net_device *dev); +static netdev_tx_t ether1_sendpacket(struct sk_buff *skb, + struct net_device *dev); static irqreturn_t ether1_interrupt(int irq, void *dev_id); static int ether1_close(struct net_device *dev); static void ether1_setmulticastlist(struct net_device *dev); @@ -667,7 +668,7 @@ ether1_timeout(struct net_device *dev) netif_wake_queue(dev); } -static int +static netdev_tx_t ether1_sendpacket (struct sk_buff *skb, struct net_device *dev) { int tmp, tst, nopaddr, txaddr, tbdaddr, dataddr; diff --git a/drivers/net/ethernet/i825xx/lib82596.c b/drivers/net/ethernet/i825xx/lib82596.c index f00a1dc2128c..2f7ae118217f 100644 --- a/drivers/net/ethernet/i825xx/lib82596.c +++ b/drivers/net/ethernet/i825xx/lib82596.c @@ -347,7 +347,7 @@ static const char init_setup[] = 0x7f /* *multi IA */ }; static int i596_open(struct net_device *dev); -static int i596_start_xmit(struct sk_buff *skb, struct net_device *dev); +static netdev_tx_t i596_start_xmit(struct sk_buff *skb, struct net_device *dev); static irqreturn_t i596_interrupt(int irq, void *dev_id); static int i596_close(struct net_device *dev); static void i596_add_cmd(struct net_device *dev, struct i596_cmd *cmd); @@ -966,7 +966,7 @@ static void i596_tx_timeout (struct net_device *dev) } -static int i596_start_xmit(struct sk_buff *skb, struct net_device *dev) +static netdev_tx_t i596_start_xmit(struct sk_buff *skb, struct net_device *dev) { struct i596_private *lp = netdev_priv(dev); struct tx_cmd *tx_cmd; diff --git a/drivers/net/ethernet/i825xx/sun3_82586.c b/drivers/net/ethernet/i825xx/sun3_82586.c index 8bb15a8c2a40..1a86184d44c0 100644 --- a/drivers/net/ethernet/i825xx/sun3_82586.c +++ b/drivers/net/ethernet/i825xx/sun3_82586.c @@ -121,7 +121,8 @@ static int sun3_82586_probe1(struct net_device *dev,int ioaddr); static irqreturn_t sun3_82586_interrupt(int irq,void *dev_id); static int sun3_82586_open(struct net_device *dev); static int sun3_82586_close(struct net_device *dev); -static int sun3_82586_send_packet(struct sk_buff *,struct net_device *); +static netdev_tx_t sun3_82586_send_packet(struct sk_buff *, + struct net_device *); static struct net_device_stats *sun3_82586_get_stats(struct net_device *dev); static void set_multicast_list(struct net_device *dev); static void sun3_82586_timeout(struct net_device *dev); @@ -1002,7 +1003,8 @@ static void sun3_82586_timeout(struct net_device *dev) * send frame */ -static int sun3_82586_send_packet(struct sk_buff *skb, struct net_device *dev) +static netdev_tx_t +sun3_82586_send_packet(struct sk_buff *skb, struct net_device *dev) { int len,i; #ifndef NO_NOPCOMMANDS diff --git a/drivers/net/ethernet/ibm/ehea/ehea_main.c b/drivers/net/ethernet/ibm/ehea/ehea_main.c index ba580bfae512..aa0b89777e74 100644 --- a/drivers/net/ethernet/ibm/ehea/ehea_main.c +++ b/drivers/net/ethernet/ibm/ehea/ehea_main.c @@ -778,12 +778,11 @@ static void check_sqs(struct ehea_port *port) { struct ehea_swqe *swqe; int swqe_index; - int i, k; + int i; for (i = 0; i < port->num_def_qps; i++) { struct ehea_port_res *pr = &port->port_res[i]; int ret; - k = 0; swqe = ehea_get_swqe(pr->qp, &swqe_index); memset(swqe, 0, SWQE_HEADER_SIZE); atomic_dec(&pr->swqe_avail); @@ -2038,7 +2037,7 @@ static void ehea_xmit3(struct sk_buff *skb, struct net_device *dev, dev_consume_skb_any(skb); } -static int ehea_start_xmit(struct sk_buff *skb, struct net_device *dev) +static netdev_tx_t ehea_start_xmit(struct sk_buff *skb, struct net_device *dev) { struct ehea_port *port = netdev_priv(dev); struct ehea_swqe *swqe; diff --git a/drivers/net/ethernet/ibm/ehea/ehea_qmr.c b/drivers/net/ethernet/ibm/ehea/ehea_qmr.c index a0820f72b25c..5e4e37132bf2 100644 --- a/drivers/net/ethernet/ibm/ehea/ehea_qmr.c +++ b/drivers/net/ethernet/ibm/ehea/ehea_qmr.c @@ -125,7 +125,7 @@ struct ehea_cq *ehea_create_cq(struct ehea_adapter *adapter, struct ehea_cq *cq; struct h_epa epa; u64 *cq_handle_ref, hret, rpage; - u32 act_nr_of_entries, act_pages, counter; + u32 counter; int ret; void *vpage; @@ -140,8 +140,6 @@ struct ehea_cq *ehea_create_cq(struct ehea_adapter *adapter, cq->adapter = adapter; cq_handle_ref = &cq->fw_handle; - act_nr_of_entries = 0; - act_pages = 0; hret = ehea_h_alloc_resource_cq(adapter->handle, &cq->attr, &cq->fw_handle, &cq->epas); diff --git a/drivers/net/ethernet/ibm/emac/core.c b/drivers/net/ethernet/ibm/emac/core.c index 372664686309..760b2ad8e295 100644 --- a/drivers/net/ethernet/ibm/emac/core.c +++ b/drivers/net/ethernet/ibm/emac/core.c @@ -423,7 +423,7 @@ static void emac_hash_mc(struct emac_instance *dev) { const int regs = EMAC_XAHT_REGS(dev); u32 *gaht_base = emac_gaht_base(dev); - u32 gaht_temp[regs]; + u32 gaht_temp[EMAC_XAHT_MAX_REGS]; struct netdev_hw_addr *ha; int i; @@ -1409,7 +1409,7 @@ static inline u16 emac_tx_csum(struct emac_instance *dev, return 0; } -static inline int emac_xmit_finish(struct emac_instance *dev, int len) +static inline netdev_tx_t emac_xmit_finish(struct emac_instance *dev, int len) { struct emac_regs __iomem *p = dev->emacp; struct net_device *ndev = dev->ndev; @@ -1436,7 +1436,7 @@ static inline int emac_xmit_finish(struct emac_instance *dev, int len) } /* Tx lock BH */ -static int emac_start_xmit(struct sk_buff *skb, struct net_device *ndev) +static netdev_tx_t emac_start_xmit(struct sk_buff *skb, struct net_device *ndev) { struct emac_instance *dev = netdev_priv(ndev); unsigned int len = skb->len; @@ -1494,7 +1494,8 @@ static inline int emac_xmit_split(struct emac_instance *dev, int slot, } /* Tx lock BH disabled (SG version for TAH equipped EMACs) */ -static int emac_start_xmit_sg(struct sk_buff *skb, struct net_device *ndev) +static netdev_tx_t +emac_start_xmit_sg(struct sk_buff *skb, struct net_device *ndev) { struct emac_instance *dev = netdev_priv(ndev); int nr_frags = skb_shinfo(skb)->nr_frags; @@ -2677,12 +2678,17 @@ static int emac_init_phy(struct emac_instance *dev) if (of_phy_is_fixed_link(np)) { int res = emac_dt_mdio_probe(dev); - if (!res) { - res = of_phy_register_fixed_link(np); - if (res) - mdiobus_unregister(dev->mii_bus); + if (res) + return res; + + res = of_phy_register_fixed_link(np); + dev->phy_dev = of_phy_find_device(np); + if (res || !dev->phy_dev) { + mdiobus_unregister(dev->mii_bus); + return res ? res : -EINVAL; } - return res; + emac_adjust_link(dev->ndev); + put_device(&dev->phy_dev->mdio.dev); } return 0; } @@ -2964,6 +2970,10 @@ static int emac_init_config(struct emac_instance *dev) dev->xaht_width_shift = EMAC4_XAHT_WIDTH_SHIFT; } + /* This should never happen */ + if (WARN_ON(EMAC_XAHT_REGS(dev) > EMAC_XAHT_MAX_REGS)) + return -ENXIO; + DBG(dev, "features : 0x%08x / 0x%08x\n", dev->features, EMAC_FTRS_POSSIBLE); DBG(dev, "tx_fifo_size : %d (%d gige)\n", dev->tx_fifo_size, dev->tx_fifo_size_gige); DBG(dev, "rx_fifo_size : %d (%d gige)\n", dev->rx_fifo_size, dev->rx_fifo_size_gige); diff --git a/drivers/net/ethernet/ibm/emac/core.h b/drivers/net/ethernet/ibm/emac/core.h index 369de2cfb15b..84caa4a3fc52 100644 --- a/drivers/net/ethernet/ibm/emac/core.h +++ b/drivers/net/ethernet/ibm/emac/core.h @@ -390,6 +390,9 @@ static inline int emac_has_feature(struct emac_instance *dev, #define EMAC4SYNC_XAHT_SLOTS_SHIFT 8 #define EMAC4SYNC_XAHT_WIDTH_SHIFT 5 +/* The largest span between slots and widths above is 3 */ +#define EMAC_XAHT_MAX_REGS (1 << 3) + #define EMAC_XAHT_SLOTS(dev) (1 << (dev)->xaht_slots_shift) #define EMAC_XAHT_WIDTH(dev) (1 << (dev)->xaht_width_shift) #define EMAC_XAHT_REGS(dev) (1 << ((dev)->xaht_slots_shift - \ diff --git a/drivers/net/ethernet/ibm/emac/mal.h b/drivers/net/ethernet/ibm/emac/mal.h index eeade2ea8334..e4c20f0024f6 100644 --- a/drivers/net/ethernet/ibm/emac/mal.h +++ b/drivers/net/ethernet/ibm/emac/mal.h @@ -136,7 +136,7 @@ static inline int mal_rx_size(int len) static inline int mal_tx_chunks(int len) { - return (len + MAL_MAX_TX_SIZE - 1) / MAL_MAX_TX_SIZE; + return DIV_ROUND_UP(len, MAL_MAX_TX_SIZE); } #define MAL_CHAN_MASK(n) (0x80000000 >> (n)) diff --git a/drivers/net/ethernet/ibm/ibmveth.c b/drivers/net/ethernet/ibm/ibmveth.c index 525d8b89187b..a4681780a55d 100644 --- a/drivers/net/ethernet/ibm/ibmveth.c +++ b/drivers/net/ethernet/ibm/ibmveth.c @@ -24,7 +24,6 @@ */ #include <linux/module.h> -#include <linux/moduleparam.h> #include <linux/types.h> #include <linux/errno.h> #include <linux/dma-mapping.h> diff --git a/drivers/net/ethernet/ibm/ibmvnic.c b/drivers/net/ethernet/ibm/ibmvnic.c index 4f0daf67b18d..a8369addfe68 100644 --- a/drivers/net/ethernet/ibm/ibmvnic.c +++ b/drivers/net/ethernet/ibm/ibmvnic.c @@ -1428,7 +1428,7 @@ static int ibmvnic_xmit_workarounds(struct sk_buff *skb, return 0; } -static int ibmvnic_xmit(struct sk_buff *skb, struct net_device *netdev) +static netdev_tx_t ibmvnic_xmit(struct sk_buff *skb, struct net_device *netdev) { struct ibmvnic_adapter *adapter = netdev_priv(netdev); int queue_num = skb_get_queue_mapping(skb); @@ -1452,7 +1452,7 @@ static int ibmvnic_xmit(struct sk_buff *skb, struct net_device *netdev) u64 *handle_array; int index = 0; u8 proto = 0; - int ret = 0; + netdev_tx_t ret = NETDEV_TX_OK; if (adapter->resetting) { if (!netif_subqueue_stopped(netdev, skb)) diff --git a/drivers/net/ethernet/intel/Kconfig b/drivers/net/ethernet/intel/Kconfig index 1ab613eb5796..b542aba6f0e8 100644 --- a/drivers/net/ethernet/intel/Kconfig +++ b/drivers/net/ethernet/intel/Kconfig @@ -235,20 +235,27 @@ config I40E_DCB If unsure, say N. +# this is here to allow seamless migration from I40EVF --> IAVF name +# so that CONFIG_IAVF symbol will always mirror the state of CONFIG_I40EVF +config IAVF + tristate config I40EVF tristate "Intel(R) Ethernet Adaptive Virtual Function support" + select IAVF depends on PCI_MSI ---help--- This driver supports virtual functions for Intel XL710, - X710, X722, and all devices advertising support for Intel - Ethernet Adaptive Virtual Function devices. For more + X710, X722, XXV710, and all devices advertising support for + Intel Ethernet Adaptive Virtual Function devices. For more information on how to identify your adapter, go to the Adapter & Driver ID Guide that can be located at: - <http://support.intel.com> + <https://support.intel.com> + + This driver was formerly named i40evf. To compile this driver as a module, choose M here. The module - will be called i40evf. MSI-X interrupt support is required + will be called iavf. MSI-X interrupt support is required for this driver to work correctly. config ICE diff --git a/drivers/net/ethernet/intel/Makefile b/drivers/net/ethernet/intel/Makefile index 807a4f8c7e4e..b91153df6ee8 100644 --- a/drivers/net/ethernet/intel/Makefile +++ b/drivers/net/ethernet/intel/Makefile @@ -12,6 +12,6 @@ obj-$(CONFIG_IXGBE) += ixgbe/ obj-$(CONFIG_IXGBEVF) += ixgbevf/ obj-$(CONFIG_I40E) += i40e/ obj-$(CONFIG_IXGB) += ixgb/ -obj-$(CONFIG_I40EVF) += i40evf/ +obj-$(CONFIG_IAVF) += iavf/ obj-$(CONFIG_FM10K) += fm10k/ obj-$(CONFIG_ICE) += ice/ diff --git a/drivers/net/ethernet/intel/e100.c b/drivers/net/ethernet/intel/e100.c index 27d5f27163d2..7c4b55482f72 100644 --- a/drivers/net/ethernet/intel/e100.c +++ b/drivers/net/ethernet/intel/e100.c @@ -164,7 +164,7 @@ MODULE_DESCRIPTION(DRV_DESCRIPTION); MODULE_AUTHOR(DRV_COPYRIGHT); -MODULE_LICENSE("GPL"); +MODULE_LICENSE("GPL v2"); MODULE_VERSION(DRV_VERSION); MODULE_FIRMWARE(FIRMWARE_D101M); MODULE_FIRMWARE(FIRMWARE_D101S); diff --git a/drivers/net/ethernet/intel/e1000/e1000_main.c b/drivers/net/ethernet/intel/e1000/e1000_main.c index 2110d5f2da19..43b6d3cec3b3 100644 --- a/drivers/net/ethernet/intel/e1000/e1000_main.c +++ b/drivers/net/ethernet/intel/e1000/e1000_main.c @@ -195,7 +195,7 @@ static struct pci_driver e1000_driver = { MODULE_AUTHOR("Intel Corporation, <linux.nics@intel.com>"); MODULE_DESCRIPTION("Intel(R) PRO/1000 Network Driver"); -MODULE_LICENSE("GPL"); +MODULE_LICENSE("GPL v2"); MODULE_VERSION(DRV_VERSION); #define DEFAULT_MSG_ENABLE (NETIF_MSG_DRV|NETIF_MSG_PROBE|NETIF_MSG_LINK) @@ -2433,7 +2433,6 @@ static void e1000_watchdog(struct work_struct *work) if (link) { if (!netif_carrier_ok(netdev)) { u32 ctrl; - bool txb2b = true; /* update snapshot of PHY registers on LSC */ e1000_get_speed_and_duplex(hw, &adapter->link_speed, @@ -2455,11 +2454,9 @@ static void e1000_watchdog(struct work_struct *work) adapter->tx_timeout_factor = 1; switch (adapter->link_speed) { case SPEED_10: - txb2b = false; adapter->tx_timeout_factor = 16; break; case SPEED_100: - txb2b = false; /* maybe add some timeout factor ? */ break; } diff --git a/drivers/net/ethernet/intel/e1000e/netdev.c b/drivers/net/ethernet/intel/e1000e/netdev.c index 3ba0c90e7055..c0f9faca70c4 100644 --- a/drivers/net/ethernet/intel/e1000e/netdev.c +++ b/drivers/net/ethernet/intel/e1000e/netdev.c @@ -7592,7 +7592,7 @@ module_exit(e1000_exit_module); MODULE_AUTHOR("Intel Corporation, <linux.nics@intel.com>"); MODULE_DESCRIPTION("Intel(R) PRO/1000 Network Driver"); -MODULE_LICENSE("GPL"); +MODULE_LICENSE("GPL v2"); MODULE_VERSION(DRV_VERSION); /* netdev.c */ diff --git a/drivers/net/ethernet/intel/fm10k/fm10k.h b/drivers/net/ethernet/intel/fm10k/fm10k.h index a903a0ba45e1..7d42582ed48d 100644 --- a/drivers/net/ethernet/intel/fm10k/fm10k.h +++ b/drivers/net/ethernet/intel/fm10k/fm10k.h @@ -504,9 +504,6 @@ void fm10k_update_stats(struct fm10k_intfc *interface); void fm10k_service_event_schedule(struct fm10k_intfc *interface); void fm10k_macvlan_schedule(struct fm10k_intfc *interface); void fm10k_update_rx_drop_en(struct fm10k_intfc *interface); -#ifdef CONFIG_NET_POLL_CONTROLLER -void fm10k_netpoll(struct net_device *netdev); -#endif /* Netdev */ struct net_device *fm10k_alloc_netdev(const struct fm10k_info *info); diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_main.c b/drivers/net/ethernet/intel/fm10k/fm10k_main.c index 3f536541f45f..503bbc017792 100644 --- a/drivers/net/ethernet/intel/fm10k/fm10k_main.c +++ b/drivers/net/ethernet/intel/fm10k/fm10k_main.c @@ -21,7 +21,7 @@ static const char fm10k_copyright[] = MODULE_AUTHOR("Intel Corporation, <linux.nics@intel.com>"); MODULE_DESCRIPTION(DRV_SUMMARY); -MODULE_LICENSE("GPL"); +MODULE_LICENSE("GPL v2"); MODULE_VERSION(DRV_VERSION); /* single workqueue for entire fm10k driver */ diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_netdev.c b/drivers/net/ethernet/intel/fm10k/fm10k_netdev.c index 929f538d28bc..538a8467f434 100644 --- a/drivers/net/ethernet/intel/fm10k/fm10k_netdev.c +++ b/drivers/net/ethernet/intel/fm10k/fm10k_netdev.c @@ -1648,9 +1648,6 @@ static const struct net_device_ops fm10k_netdev_ops = { .ndo_udp_tunnel_del = fm10k_udp_tunnel_del, .ndo_dfwd_add_station = fm10k_dfwd_add_station, .ndo_dfwd_del_station = fm10k_dfwd_del_station, -#ifdef CONFIG_NET_POLL_CONTROLLER - .ndo_poll_controller = fm10k_netpoll, -#endif .ndo_features_check = fm10k_features_check, }; diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_pci.c b/drivers/net/ethernet/intel/fm10k/fm10k_pci.c index 15071e4adb98..c859ababeed5 100644 --- a/drivers/net/ethernet/intel/fm10k/fm10k_pci.c +++ b/drivers/net/ethernet/intel/fm10k/fm10k_pci.c @@ -1210,28 +1210,6 @@ static irqreturn_t fm10k_msix_mbx_vf(int __always_unused irq, void *data) return IRQ_HANDLED; } -#ifdef CONFIG_NET_POLL_CONTROLLER -/** - * fm10k_netpoll - A Polling 'interrupt' handler - * @netdev: network interface device structure - * - * This is used by netconsole to send skbs without having to re-enable - * interrupts. It's not called while the normal interrupt routine is executing. - **/ -void fm10k_netpoll(struct net_device *netdev) -{ - struct fm10k_intfc *interface = netdev_priv(netdev); - int i; - - /* if interface is down do nothing */ - if (test_bit(__FM10K_DOWN, interface->state)) - return; - - for (i = 0; i < interface->num_q_vectors; i++) - fm10k_msix_clean_rings(0, interface->q_vector[i]); -} - -#endif #define FM10K_ERR_MSG(type) case (type): error = #type; break static void fm10k_handle_fault(struct fm10k_intfc *interface, int type, struct fm10k_fault *fault) diff --git a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c index d7d3974beca2..9f8464f80783 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c +++ b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c @@ -5,8 +5,226 @@ #include "i40e.h" #include "i40e_diag.h" +#include "i40e_txrx_common.h" -#include "i40e_ethtool_stats.h" +/* ethtool statistics helpers */ + +/** + * struct i40e_stats - definition for an ethtool statistic + * @stat_string: statistic name to display in ethtool -S output + * @sizeof_stat: the sizeof() the stat, must be no greater than sizeof(u64) + * @stat_offset: offsetof() the stat from a base pointer + * + * This structure defines a statistic to be added to the ethtool stats buffer. + * It defines a statistic as offset from a common base pointer. Stats should + * be defined in constant arrays using the I40E_STAT macro, with every element + * of the array using the same _type for calculating the sizeof_stat and + * stat_offset. + * + * The @sizeof_stat is expected to be sizeof(u8), sizeof(u16), sizeof(u32) or + * sizeof(u64). Other sizes are not expected and will produce a WARN_ONCE from + * the i40e_add_ethtool_stat() helper function. + * + * The @stat_string is interpreted as a format string, allowing formatted + * values to be inserted while looping over multiple structures for a given + * statistics array. Thus, every statistic string in an array should have the + * same type and number of format specifiers, to be formatted by variadic + * arguments to the i40e_add_stat_string() helper function. + **/ +struct i40e_stats { + char stat_string[ETH_GSTRING_LEN]; + int sizeof_stat; + int stat_offset; +}; + +/* Helper macro to define an i40e_stat structure with proper size and type. + * Use this when defining constant statistics arrays. Note that @_type expects + * only a type name and is used multiple times. + */ +#define I40E_STAT(_type, _name, _stat) { \ + .stat_string = _name, \ + .sizeof_stat = FIELD_SIZEOF(_type, _stat), \ + .stat_offset = offsetof(_type, _stat) \ +} + +/* Helper macro for defining some statistics directly copied from the netdev + * stats structure. + */ +#define I40E_NETDEV_STAT(_net_stat) \ + I40E_STAT(struct rtnl_link_stats64, #_net_stat, _net_stat) + +/* Helper macro for defining some statistics related to queues */ +#define I40E_QUEUE_STAT(_name, _stat) \ + I40E_STAT(struct i40e_ring, _name, _stat) + +/* Stats associated with a Tx or Rx ring */ +static const struct i40e_stats i40e_gstrings_queue_stats[] = { + I40E_QUEUE_STAT("%s-%u.packets", stats.packets), + I40E_QUEUE_STAT("%s-%u.bytes", stats.bytes), +}; + +/** + * i40e_add_one_ethtool_stat - copy the stat into the supplied buffer + * @data: location to store the stat value + * @pointer: basis for where to copy from + * @stat: the stat definition + * + * Copies the stat data defined by the pointer and stat structure pair into + * the memory supplied as data. Used to implement i40e_add_ethtool_stats and + * i40e_add_queue_stats. If the pointer is null, data will be zero'd. + */ +static void +i40e_add_one_ethtool_stat(u64 *data, void *pointer, + const struct i40e_stats *stat) +{ + char *p; + + if (!pointer) { + /* ensure that the ethtool data buffer is zero'd for any stats + * which don't have a valid pointer. + */ + *data = 0; + return; + } + + p = (char *)pointer + stat->stat_offset; + switch (stat->sizeof_stat) { + case sizeof(u64): + *data = *((u64 *)p); + break; + case sizeof(u32): + *data = *((u32 *)p); + break; + case sizeof(u16): + *data = *((u16 *)p); + break; + case sizeof(u8): + *data = *((u8 *)p); + break; + default: + WARN_ONCE(1, "unexpected stat size for %s", + stat->stat_string); + *data = 0; + } +} + +/** + * __i40e_add_ethtool_stats - copy stats into the ethtool supplied buffer + * @data: ethtool stats buffer + * @pointer: location to copy stats from + * @stats: array of stats to copy + * @size: the size of the stats definition + * + * Copy the stats defined by the stats array using the pointer as a base into + * the data buffer supplied by ethtool. Updates the data pointer to point to + * the next empty location for successive calls to __i40e_add_ethtool_stats. + * If pointer is null, set the data values to zero and update the pointer to + * skip these stats. + **/ +static void +__i40e_add_ethtool_stats(u64 **data, void *pointer, + const struct i40e_stats stats[], + const unsigned int size) +{ + unsigned int i; + + for (i = 0; i < size; i++) + i40e_add_one_ethtool_stat((*data)++, pointer, &stats[i]); +} + +/** + * i40e_add_ethtool_stats - copy stats into ethtool supplied buffer + * @data: ethtool stats buffer + * @pointer: location where stats are stored + * @stats: static const array of stat definitions + * + * Macro to ease the use of __i40e_add_ethtool_stats by taking a static + * constant stats array and passing the ARRAY_SIZE(). This avoids typos by + * ensuring that we pass the size associated with the given stats array. + * + * The parameter @stats is evaluated twice, so parameters with side effects + * should be avoided. + **/ +#define i40e_add_ethtool_stats(data, pointer, stats) \ + __i40e_add_ethtool_stats(data, pointer, stats, ARRAY_SIZE(stats)) + +/** + * i40e_add_queue_stats - copy queue statistics into supplied buffer + * @data: ethtool stats buffer + * @ring: the ring to copy + * + * Queue statistics must be copied while protected by + * u64_stats_fetch_begin_irq, so we can't directly use i40e_add_ethtool_stats. + * Assumes that queue stats are defined in i40e_gstrings_queue_stats. If the + * ring pointer is null, zero out the queue stat values and update the data + * pointer. Otherwise safely copy the stats from the ring into the supplied + * buffer and update the data pointer when finished. + * + * This function expects to be called while under rcu_read_lock(). + **/ +static void +i40e_add_queue_stats(u64 **data, struct i40e_ring *ring) +{ + const unsigned int size = ARRAY_SIZE(i40e_gstrings_queue_stats); + const struct i40e_stats *stats = i40e_gstrings_queue_stats; + unsigned int start; + unsigned int i; + + /* To avoid invalid statistics values, ensure that we keep retrying + * the copy until we get a consistent value according to + * u64_stats_fetch_retry_irq. But first, make sure our ring is + * non-null before attempting to access its syncp. + */ + do { + start = !ring ? 0 : u64_stats_fetch_begin_irq(&ring->syncp); + for (i = 0; i < size; i++) { + i40e_add_one_ethtool_stat(&(*data)[i], ring, + &stats[i]); + } + } while (ring && u64_stats_fetch_retry_irq(&ring->syncp, start)); + + /* Once we successfully copy the stats in, update the data pointer */ + *data += size; +} + +/** + * __i40e_add_stat_strings - copy stat strings into ethtool buffer + * @p: ethtool supplied buffer + * @stats: stat definitions array + * @size: size of the stats array + * + * Format and copy the strings described by stats into the buffer pointed at + * by p. + **/ +static void __i40e_add_stat_strings(u8 **p, const struct i40e_stats stats[], + const unsigned int size, ...) +{ + unsigned int i; + + for (i = 0; i < size; i++) { + va_list args; + + va_start(args, size); + vsnprintf(*p, ETH_GSTRING_LEN, stats[i].stat_string, args); + *p += ETH_GSTRING_LEN; + va_end(args); + } +} + +/** + * 40e_add_stat_strings - copy stat strings into ethtool buffer + * @p: ethtool supplied buffer + * @stats: stat definitions array + * + * Format and copy the strings described by the const static stats value into + * the buffer pointed at by p. + * + * The parameter @stats is evaluated twice, so parameters with side effects + * should be avoided. Additionally, stats must be an array such that + * ARRAY_SIZE can be called on it. + **/ +#define i40e_add_stat_strings(p, stats, ...) \ + __i40e_add_stat_strings(p, stats, ARRAY_SIZE(stats), ## __VA_ARGS__) #define I40E_PF_STAT(_name, _stat) \ I40E_STAT(struct i40e_pf, _name, _stat) @@ -1493,6 +1711,13 @@ static int i40e_set_ringparam(struct net_device *netdev, (new_rx_count == vsi->rx_rings[0]->count)) return 0; + /* If there is a AF_XDP UMEM attached to any of Rx rings, + * disallow changing the number of descriptors -- regardless + * if the netdev is running or not. + */ + if (i40e_xsk_any_rx_ring_enabled(vsi)) + return -EBUSY; + while (test_and_set_bit(__I40E_CONFIG_BUSY, pf->state)) { timeout--; if (!timeout) diff --git a/drivers/net/ethernet/intel/i40e/i40e_ethtool_stats.h b/drivers/net/ethernet/intel/i40e/i40e_ethtool_stats.h deleted file mode 100644 index bba1cb0b658f..000000000000 --- a/drivers/net/ethernet/intel/i40e/i40e_ethtool_stats.h +++ /dev/null @@ -1,221 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright(c) 2013 - 2018 Intel Corporation. */ - -/* ethtool statistics helpers */ - -/** - * struct i40e_stats - definition for an ethtool statistic - * @stat_string: statistic name to display in ethtool -S output - * @sizeof_stat: the sizeof() the stat, must be no greater than sizeof(u64) - * @stat_offset: offsetof() the stat from a base pointer - * - * This structure defines a statistic to be added to the ethtool stats buffer. - * It defines a statistic as offset from a common base pointer. Stats should - * be defined in constant arrays using the I40E_STAT macro, with every element - * of the array using the same _type for calculating the sizeof_stat and - * stat_offset. - * - * The @sizeof_stat is expected to be sizeof(u8), sizeof(u16), sizeof(u32) or - * sizeof(u64). Other sizes are not expected and will produce a WARN_ONCE from - * the i40e_add_ethtool_stat() helper function. - * - * The @stat_string is interpreted as a format string, allowing formatted - * values to be inserted while looping over multiple structures for a given - * statistics array. Thus, every statistic string in an array should have the - * same type and number of format specifiers, to be formatted by variadic - * arguments to the i40e_add_stat_string() helper function. - **/ -struct i40e_stats { - char stat_string[ETH_GSTRING_LEN]; - int sizeof_stat; - int stat_offset; -}; - -/* Helper macro to define an i40e_stat structure with proper size and type. - * Use this when defining constant statistics arrays. Note that @_type expects - * only a type name and is used multiple times. - */ -#define I40E_STAT(_type, _name, _stat) { \ - .stat_string = _name, \ - .sizeof_stat = FIELD_SIZEOF(_type, _stat), \ - .stat_offset = offsetof(_type, _stat) \ -} - -/* Helper macro for defining some statistics directly copied from the netdev - * stats structure. - */ -#define I40E_NETDEV_STAT(_net_stat) \ - I40E_STAT(struct rtnl_link_stats64, #_net_stat, _net_stat) - -/* Helper macro for defining some statistics related to queues */ -#define I40E_QUEUE_STAT(_name, _stat) \ - I40E_STAT(struct i40e_ring, _name, _stat) - -/* Stats associated with a Tx or Rx ring */ -static const struct i40e_stats i40e_gstrings_queue_stats[] = { - I40E_QUEUE_STAT("%s-%u.packets", stats.packets), - I40E_QUEUE_STAT("%s-%u.bytes", stats.bytes), -}; - -/** - * i40e_add_one_ethtool_stat - copy the stat into the supplied buffer - * @data: location to store the stat value - * @pointer: basis for where to copy from - * @stat: the stat definition - * - * Copies the stat data defined by the pointer and stat structure pair into - * the memory supplied as data. Used to implement i40e_add_ethtool_stats and - * i40e_add_queue_stats. If the pointer is null, data will be zero'd. - */ -static inline void -i40e_add_one_ethtool_stat(u64 *data, void *pointer, - const struct i40e_stats *stat) -{ - char *p; - - if (!pointer) { - /* ensure that the ethtool data buffer is zero'd for any stats - * which don't have a valid pointer. - */ - *data = 0; - return; - } - - p = (char *)pointer + stat->stat_offset; - switch (stat->sizeof_stat) { - case sizeof(u64): - *data = *((u64 *)p); - break; - case sizeof(u32): - *data = *((u32 *)p); - break; - case sizeof(u16): - *data = *((u16 *)p); - break; - case sizeof(u8): - *data = *((u8 *)p); - break; - default: - WARN_ONCE(1, "unexpected stat size for %s", - stat->stat_string); - *data = 0; - } -} - -/** - * __i40e_add_ethtool_stats - copy stats into the ethtool supplied buffer - * @data: ethtool stats buffer - * @pointer: location to copy stats from - * @stats: array of stats to copy - * @size: the size of the stats definition - * - * Copy the stats defined by the stats array using the pointer as a base into - * the data buffer supplied by ethtool. Updates the data pointer to point to - * the next empty location for successive calls to __i40e_add_ethtool_stats. - * If pointer is null, set the data values to zero and update the pointer to - * skip these stats. - **/ -static inline void -__i40e_add_ethtool_stats(u64 **data, void *pointer, - const struct i40e_stats stats[], - const unsigned int size) -{ - unsigned int i; - - for (i = 0; i < size; i++) - i40e_add_one_ethtool_stat((*data)++, pointer, &stats[i]); -} - -/** - * i40e_add_ethtool_stats - copy stats into ethtool supplied buffer - * @data: ethtool stats buffer - * @pointer: location where stats are stored - * @stats: static const array of stat definitions - * - * Macro to ease the use of __i40e_add_ethtool_stats by taking a static - * constant stats array and passing the ARRAY_SIZE(). This avoids typos by - * ensuring that we pass the size associated with the given stats array. - * - * The parameter @stats is evaluated twice, so parameters with side effects - * should be avoided. - **/ -#define i40e_add_ethtool_stats(data, pointer, stats) \ - __i40e_add_ethtool_stats(data, pointer, stats, ARRAY_SIZE(stats)) - -/** - * i40e_add_queue_stats - copy queue statistics into supplied buffer - * @data: ethtool stats buffer - * @ring: the ring to copy - * - * Queue statistics must be copied while protected by - * u64_stats_fetch_begin_irq, so we can't directly use i40e_add_ethtool_stats. - * Assumes that queue stats are defined in i40e_gstrings_queue_stats. If the - * ring pointer is null, zero out the queue stat values and update the data - * pointer. Otherwise safely copy the stats from the ring into the supplied - * buffer and update the data pointer when finished. - * - * This function expects to be called while under rcu_read_lock(). - **/ -static inline void -i40e_add_queue_stats(u64 **data, struct i40e_ring *ring) -{ - const unsigned int size = ARRAY_SIZE(i40e_gstrings_queue_stats); - const struct i40e_stats *stats = i40e_gstrings_queue_stats; - unsigned int start; - unsigned int i; - - /* To avoid invalid statistics values, ensure that we keep retrying - * the copy until we get a consistent value according to - * u64_stats_fetch_retry_irq. But first, make sure our ring is - * non-null before attempting to access its syncp. - */ - do { - start = !ring ? 0 : u64_stats_fetch_begin_irq(&ring->syncp); - for (i = 0; i < size; i++) { - i40e_add_one_ethtool_stat(&(*data)[i], ring, - &stats[i]); - } - } while (ring && u64_stats_fetch_retry_irq(&ring->syncp, start)); - - /* Once we successfully copy the stats in, update the data pointer */ - *data += size; -} - -/** - * __i40e_add_stat_strings - copy stat strings into ethtool buffer - * @p: ethtool supplied buffer - * @stats: stat definitions array - * @size: size of the stats array - * - * Format and copy the strings described by stats into the buffer pointed at - * by p. - **/ -static inline void __i40e_add_stat_strings(u8 **p, const struct i40e_stats stats[], - const unsigned int size, ...) -{ - unsigned int i; - - for (i = 0; i < size; i++) { - va_list args; - - va_start(args, size); - vsnprintf(*p, ETH_GSTRING_LEN, stats[i].stat_string, args); - *p += ETH_GSTRING_LEN; - va_end(args); - } -} - -/** - * 40e_add_stat_strings - copy stat strings into ethtool buffer - * @p: ethtool supplied buffer - * @stats: stat definitions array - * - * Format and copy the strings described by the const static stats value into - * the buffer pointed at by p. - * - * The parameter @stats is evaluated twice, so parameters with side effects - * should be avoided. Additionally, stats must be an array such that - * ARRAY_SIZE can be called on it. - **/ -#define i40e_add_stat_strings(p, stats, ...) \ - __i40e_add_stat_strings(p, stats, ARRAY_SIZE(stats), ## __VA_ARGS__) diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c index 5d209d8fe9b8..330bafe6a689 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_main.c +++ b/drivers/net/ethernet/intel/i40e/i40e_main.c @@ -91,7 +91,7 @@ MODULE_PARM_DESC(debug, "Debug level (0=none,...,16=all), Debug mask (0x8XXXXXXX MODULE_AUTHOR("Intel Corporation, <e1000-devel@lists.sourceforge.net>"); MODULE_DESCRIPTION("Intel(R) Ethernet Connection XL710 Network Driver"); -MODULE_LICENSE("GPL"); +MODULE_LICENSE("GPL v2"); MODULE_VERSION(DRV_VERSION); static struct workqueue_struct *i40e_wq; @@ -1532,8 +1532,8 @@ static int i40e_set_mac(struct net_device *netdev, void *p) return 0; } - if (test_bit(__I40E_VSI_DOWN, vsi->back->state) || - test_bit(__I40E_RESET_RECOVERY_PENDING, vsi->back->state)) + if (test_bit(__I40E_DOWN, pf->state) || + test_bit(__I40E_RESET_RECOVERY_PENDING, pf->state)) return -EADDRNOTAVAIL; if (ether_addr_equal(hw->mac.addr, addr->sa_data)) @@ -1557,8 +1557,7 @@ static int i40e_set_mac(struct net_device *netdev, void *p) if (vsi->type == I40E_VSI_MAIN) { i40e_status ret; - ret = i40e_aq_mac_address_write(&vsi->back->hw, - I40E_AQC_WRITE_TYPE_LAA_WOL, + ret = i40e_aq_mac_address_write(hw, I40E_AQC_WRITE_TYPE_LAA_WOL, addr->sa_data, NULL); if (ret) netdev_info(netdev, "Ignoring error from firmware on LAA update, status %s, AQ ret %s\n", @@ -1569,7 +1568,7 @@ static int i40e_set_mac(struct net_device *netdev, void *p) /* schedule our worker thread which will take care of * applying the new filter changes */ - i40e_service_event_schedule(vsi->back); + i40e_service_event_schedule(pf); return 0; } @@ -6432,7 +6431,10 @@ void i40e_print_link_message(struct i40e_vsi *vsi, bool isup) char *req_fec = ""; char *an = ""; - new_speed = pf->hw.phy.link_info.link_speed; + if (isup) + new_speed = pf->hw.phy.link_info.link_speed; + else + new_speed = I40E_LINK_SPEED_UNKNOWN; if ((vsi->current_isup == isup) && (vsi->current_speed == new_speed)) return; @@ -8509,14 +8511,9 @@ static void i40e_link_event(struct i40e_pf *pf) i40e_status status; bool new_link, old_link; - /* save off old link status information */ - pf->hw.phy.link_info_old = pf->hw.phy.link_info; - /* set this to force the get_link_status call to refresh state */ pf->hw.phy.get_link_info = true; - old_link = (pf->hw.phy.link_info_old.link_info & I40E_AQ_LINK_UP); - status = i40e_get_link_status(&pf->hw, &new_link); /* On success, disable temp link polling */ diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.c b/drivers/net/ethernet/intel/i40e/i40e_txrx.c index 37bd4e50ccde..740ea58ba938 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_txrx.c +++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.c @@ -636,13 +636,18 @@ void i40e_clean_tx_ring(struct i40e_ring *tx_ring) unsigned long bi_size; u16 i; - /* ring already cleared, nothing to do */ - if (!tx_ring->tx_bi) - return; + if (ring_is_xdp(tx_ring) && tx_ring->xsk_umem) { + i40e_xsk_clean_tx_ring(tx_ring); + } else { + /* ring already cleared, nothing to do */ + if (!tx_ring->tx_bi) + return; - /* Free all the Tx ring sk_buffs */ - for (i = 0; i < tx_ring->count; i++) - i40e_unmap_and_free_tx_resource(tx_ring, &tx_ring->tx_bi[i]); + /* Free all the Tx ring sk_buffs */ + for (i = 0; i < tx_ring->count; i++) + i40e_unmap_and_free_tx_resource(tx_ring, + &tx_ring->tx_bi[i]); + } bi_size = sizeof(struct i40e_tx_buffer) * tx_ring->count; memset(tx_ring->tx_bi, 0, bi_size); @@ -1350,8 +1355,10 @@ void i40e_clean_rx_ring(struct i40e_ring *rx_ring) rx_ring->skb = NULL; } - if (rx_ring->xsk_umem) + if (rx_ring->xsk_umem) { + i40e_xsk_clean_rx_ring(rx_ring); goto skip_free; + } /* Free all the Rx ring sk_buffs */ for (i = 0; i < rx_ring->count; i++) { diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx_common.h b/drivers/net/ethernet/intel/i40e/i40e_txrx_common.h index b5afd479a9c5..09809dffe399 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_txrx_common.h +++ b/drivers/net/ethernet/intel/i40e/i40e_txrx_common.h @@ -87,4 +87,8 @@ static inline void i40e_arm_wb(struct i40e_ring *tx_ring, } } +void i40e_xsk_clean_rx_ring(struct i40e_ring *rx_ring); +void i40e_xsk_clean_tx_ring(struct i40e_ring *tx_ring); +bool i40e_xsk_any_rx_ring_enabled(struct i40e_vsi *vsi); + #endif /* I40E_TXRX_COMMON_ */ diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c index 3e707c7e6782..f4bb2779f03a 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c +++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c @@ -1084,6 +1084,136 @@ static int i40e_quiesce_vf_pci(struct i40e_vf *vf) return -EIO; } +static inline int i40e_getnum_vf_vsi_vlan_filters(struct i40e_vsi *vsi); + +/** + * i40e_config_vf_promiscuous_mode + * @vf: pointer to the VF info + * @vsi_id: VSI id + * @allmulti: set MAC L2 layer multicast promiscuous enable/disable + * @alluni: set MAC L2 layer unicast promiscuous enable/disable + * + * Called from the VF to configure the promiscuous mode of + * VF vsis and from the VF reset path to reset promiscuous mode. + **/ +static i40e_status i40e_config_vf_promiscuous_mode(struct i40e_vf *vf, + u16 vsi_id, + bool allmulti, + bool alluni) +{ + struct i40e_pf *pf = vf->pf; + struct i40e_hw *hw = &pf->hw; + struct i40e_mac_filter *f; + i40e_status aq_ret = 0; + struct i40e_vsi *vsi; + int bkt; + + vsi = i40e_find_vsi_from_id(pf, vsi_id); + if (!i40e_vc_isvalid_vsi_id(vf, vsi_id) || !vsi) + return I40E_ERR_PARAM; + + if (!test_bit(I40E_VIRTCHNL_VF_CAP_PRIVILEGE, &vf->vf_caps)) { + dev_err(&pf->pdev->dev, + "Unprivileged VF %d is attempting to configure promiscuous mode\n", + vf->vf_id); + /* Lie to the VF on purpose. */ + return 0; + } + + if (vf->port_vlan_id) { + aq_ret = i40e_aq_set_vsi_mc_promisc_on_vlan(hw, vsi->seid, + allmulti, + vf->port_vlan_id, + NULL); + if (aq_ret) { + int aq_err = pf->hw.aq.asq_last_status; + + dev_err(&pf->pdev->dev, + "VF %d failed to set multicast promiscuous mode err %s aq_err %s\n", + vf->vf_id, + i40e_stat_str(&pf->hw, aq_ret), + i40e_aq_str(&pf->hw, aq_err)); + return aq_ret; + } + + aq_ret = i40e_aq_set_vsi_uc_promisc_on_vlan(hw, vsi->seid, + alluni, + vf->port_vlan_id, + NULL); + if (aq_ret) { + int aq_err = pf->hw.aq.asq_last_status; + + dev_err(&pf->pdev->dev, + "VF %d failed to set unicast promiscuous mode err %s aq_err %s\n", + vf->vf_id, + i40e_stat_str(&pf->hw, aq_ret), + i40e_aq_str(&pf->hw, aq_err)); + } + return aq_ret; + } else if (i40e_getnum_vf_vsi_vlan_filters(vsi)) { + hash_for_each(vsi->mac_filter_hash, bkt, f, hlist) { + if (f->vlan < 0 || f->vlan > I40E_MAX_VLANID) + continue; + aq_ret = i40e_aq_set_vsi_mc_promisc_on_vlan(hw, + vsi->seid, + allmulti, + f->vlan, + NULL); + if (aq_ret) { + int aq_err = pf->hw.aq.asq_last_status; + + dev_err(&pf->pdev->dev, + "Could not add VLAN %d to multicast promiscuous domain err %s aq_err %s\n", + f->vlan, + i40e_stat_str(&pf->hw, aq_ret), + i40e_aq_str(&pf->hw, aq_err)); + } + + aq_ret = i40e_aq_set_vsi_uc_promisc_on_vlan(hw, + vsi->seid, + alluni, + f->vlan, + NULL); + if (aq_ret) { + int aq_err = pf->hw.aq.asq_last_status; + + dev_err(&pf->pdev->dev, + "Could not add VLAN %d to Unicast promiscuous domain err %s aq_err %s\n", + f->vlan, + i40e_stat_str(&pf->hw, aq_ret), + i40e_aq_str(&pf->hw, aq_err)); + } + } + return aq_ret; + } + aq_ret = i40e_aq_set_vsi_multicast_promiscuous(hw, vsi->seid, allmulti, + NULL); + if (aq_ret) { + int aq_err = pf->hw.aq.asq_last_status; + + dev_err(&pf->pdev->dev, + "VF %d failed to set multicast promiscuous mode err %s aq_err %s\n", + vf->vf_id, + i40e_stat_str(&pf->hw, aq_ret), + i40e_aq_str(&pf->hw, aq_err)); + return aq_ret; + } + + aq_ret = i40e_aq_set_vsi_unicast_promiscuous(hw, vsi->seid, alluni, + NULL, true); + if (aq_ret) { + int aq_err = pf->hw.aq.asq_last_status; + + dev_err(&pf->pdev->dev, + "VF %d failed to set unicast promiscuous mode err %s aq_err %s\n", + vf->vf_id, + i40e_stat_str(&pf->hw, aq_ret), + i40e_aq_str(&pf->hw, aq_err)); + } + + return aq_ret; +} + /** * i40e_trigger_vf_reset * @vf: pointer to the VF structure @@ -1145,6 +1275,9 @@ static void i40e_cleanup_reset_vf(struct i40e_vf *vf) struct i40e_hw *hw = &pf->hw; u32 reg; + /* disable promisc modes in case they were enabled */ + i40e_config_vf_promiscuous_mode(vf, vf->lan_vsi_id, false, false); + /* free VF resources to begin resetting the VSI state */ i40e_free_vf_res(vf); @@ -1840,143 +1973,55 @@ static inline int i40e_getnum_vf_vsi_vlan_filters(struct i40e_vsi *vsi) * i40e_vc_config_promiscuous_mode_msg * @vf: pointer to the VF info * @msg: pointer to the msg buffer - * @msglen: msg length * * called from the VF to configure the promiscuous mode of * VF vsis **/ -static int i40e_vc_config_promiscuous_mode_msg(struct i40e_vf *vf, - u8 *msg, u16 msglen) +static int i40e_vc_config_promiscuous_mode_msg(struct i40e_vf *vf, u8 *msg) { struct virtchnl_promisc_info *info = (struct virtchnl_promisc_info *)msg; struct i40e_pf *pf = vf->pf; - struct i40e_hw *hw = &pf->hw; - struct i40e_mac_filter *f; i40e_status aq_ret = 0; bool allmulti = false; - struct i40e_vsi *vsi; bool alluni = false; - int aq_err = 0; - int bkt; - vsi = i40e_find_vsi_from_id(pf, info->vsi_id); - if (!test_bit(I40E_VF_STATE_ACTIVE, &vf->vf_states) || - !i40e_vc_isvalid_vsi_id(vf, info->vsi_id) || - !vsi) { - aq_ret = I40E_ERR_PARAM; - goto error_param; - } - if (!test_bit(I40E_VIRTCHNL_VF_CAP_PRIVILEGE, &vf->vf_caps)) { - dev_err(&pf->pdev->dev, - "Unprivileged VF %d is attempting to configure promiscuous mode\n", - vf->vf_id); - /* Lie to the VF on purpose. */ - aq_ret = 0; - goto error_param; - } + if (!test_bit(I40E_VF_STATE_ACTIVE, &vf->vf_states)) + return I40E_ERR_PARAM; + /* Multicast promiscuous handling*/ if (info->flags & FLAG_VF_MULTICAST_PROMISC) allmulti = true; - if (vf->port_vlan_id) { - aq_ret = i40e_aq_set_vsi_mc_promisc_on_vlan(hw, vsi->seid, - allmulti, - vf->port_vlan_id, - NULL); - } else if (i40e_getnum_vf_vsi_vlan_filters(vsi)) { - hash_for_each(vsi->mac_filter_hash, bkt, f, hlist) { - if (f->vlan < 0 || f->vlan > I40E_MAX_VLANID) - continue; - aq_ret = i40e_aq_set_vsi_mc_promisc_on_vlan(hw, - vsi->seid, - allmulti, - f->vlan, - NULL); - aq_err = pf->hw.aq.asq_last_status; - if (aq_ret) { - dev_err(&pf->pdev->dev, - "Could not add VLAN %d to multicast promiscuous domain err %s aq_err %s\n", - f->vlan, - i40e_stat_str(&pf->hw, aq_ret), - i40e_aq_str(&pf->hw, aq_err)); - break; - } - } - } else { - aq_ret = i40e_aq_set_vsi_multicast_promiscuous(hw, vsi->seid, - allmulti, NULL); - aq_err = pf->hw.aq.asq_last_status; - if (aq_ret) { - dev_err(&pf->pdev->dev, - "VF %d failed to set multicast promiscuous mode err %s aq_err %s\n", - vf->vf_id, - i40e_stat_str(&pf->hw, aq_ret), - i40e_aq_str(&pf->hw, aq_err)); - goto error_param; - } - } - + if (info->flags & FLAG_VF_UNICAST_PROMISC) + alluni = true; + aq_ret = i40e_config_vf_promiscuous_mode(vf, info->vsi_id, allmulti, + alluni); if (!aq_ret) { - dev_info(&pf->pdev->dev, - "VF %d successfully set multicast promiscuous mode\n", - vf->vf_id); - if (allmulti) + if (allmulti) { + dev_info(&pf->pdev->dev, + "VF %d successfully set multicast promiscuous mode\n", + vf->vf_id); set_bit(I40E_VF_STATE_MC_PROMISC, &vf->vf_states); - else + } else { + dev_info(&pf->pdev->dev, + "VF %d successfully unset multicast promiscuous mode\n", + vf->vf_id); clear_bit(I40E_VF_STATE_MC_PROMISC, &vf->vf_states); - } - - if (info->flags & FLAG_VF_UNICAST_PROMISC) - alluni = true; - if (vf->port_vlan_id) { - aq_ret = i40e_aq_set_vsi_uc_promisc_on_vlan(hw, vsi->seid, - alluni, - vf->port_vlan_id, - NULL); - } else if (i40e_getnum_vf_vsi_vlan_filters(vsi)) { - hash_for_each(vsi->mac_filter_hash, bkt, f, hlist) { - if (f->vlan < 0 || f->vlan > I40E_MAX_VLANID) - continue; - aq_ret = i40e_aq_set_vsi_uc_promisc_on_vlan(hw, - vsi->seid, - alluni, - f->vlan, - NULL); - aq_err = pf->hw.aq.asq_last_status; - if (aq_ret) - dev_err(&pf->pdev->dev, - "Could not add VLAN %d to Unicast promiscuous domain err %s aq_err %s\n", - f->vlan, - i40e_stat_str(&pf->hw, aq_ret), - i40e_aq_str(&pf->hw, aq_err)); - } - } else { - aq_ret = i40e_aq_set_vsi_unicast_promiscuous(hw, vsi->seid, - alluni, NULL, - true); - aq_err = pf->hw.aq.asq_last_status; - if (aq_ret) { - dev_err(&pf->pdev->dev, - "VF %d failed to set unicast promiscuous mode %8.8x err %s aq_err %s\n", - vf->vf_id, info->flags, - i40e_stat_str(&pf->hw, aq_ret), - i40e_aq_str(&pf->hw, aq_err)); - goto error_param; } - } - - if (!aq_ret) { - dev_info(&pf->pdev->dev, - "VF %d successfully set unicast promiscuous mode\n", - vf->vf_id); - if (alluni) + if (alluni) { + dev_info(&pf->pdev->dev, + "VF %d successfully set unicast promiscuous mode\n", + vf->vf_id); set_bit(I40E_VF_STATE_UC_PROMISC, &vf->vf_states); - else + } else { + dev_info(&pf->pdev->dev, + "VF %d successfully unset unicast promiscuous mode\n", + vf->vf_id); clear_bit(I40E_VF_STATE_UC_PROMISC, &vf->vf_states); + } } -error_param: /* send the response to the VF */ return i40e_vc_send_resp_to_vf(vf, VIRTCHNL_OP_CONFIG_PROMISCUOUS_MODE, @@ -1987,12 +2032,11 @@ error_param: * i40e_vc_config_queues_msg * @vf: pointer to the VF info * @msg: pointer to the msg buffer - * @msglen: msg length * * called from the VF to configure the rx/tx * queues **/ -static int i40e_vc_config_queues_msg(struct i40e_vf *vf, u8 *msg, u16 msglen) +static int i40e_vc_config_queues_msg(struct i40e_vf *vf, u8 *msg) { struct virtchnl_vsi_queue_config_info *qci = (struct virtchnl_vsi_queue_config_info *)msg; @@ -2105,12 +2149,11 @@ static int i40e_validate_queue_map(struct i40e_vf *vf, u16 vsi_id, * i40e_vc_config_irq_map_msg * @vf: pointer to the VF info * @msg: pointer to the msg buffer - * @msglen: msg length * * called from the VF to configure the irq to * queue map **/ -static int i40e_vc_config_irq_map_msg(struct i40e_vf *vf, u8 *msg, u16 msglen) +static int i40e_vc_config_irq_map_msg(struct i40e_vf *vf, u8 *msg) { struct virtchnl_irq_map_info *irqmap_info = (struct virtchnl_irq_map_info *)msg; @@ -2202,11 +2245,10 @@ static int i40e_ctrl_vf_rx_rings(struct i40e_vsi *vsi, unsigned long q_map, * i40e_vc_enable_queues_msg * @vf: pointer to the VF info * @msg: pointer to the msg buffer - * @msglen: msg length * * called from the VF to enable all or specific queue(s) **/ -static int i40e_vc_enable_queues_msg(struct i40e_vf *vf, u8 *msg, u16 msglen) +static int i40e_vc_enable_queues_msg(struct i40e_vf *vf, u8 *msg) { struct virtchnl_queue_select *vqs = (struct virtchnl_queue_select *)msg; @@ -2261,12 +2303,11 @@ error_param: * i40e_vc_disable_queues_msg * @vf: pointer to the VF info * @msg: pointer to the msg buffer - * @msglen: msg length * * called from the VF to disable all or specific * queue(s) **/ -static int i40e_vc_disable_queues_msg(struct i40e_vf *vf, u8 *msg, u16 msglen) +static int i40e_vc_disable_queues_msg(struct i40e_vf *vf, u8 *msg) { struct virtchnl_queue_select *vqs = (struct virtchnl_queue_select *)msg; @@ -2309,14 +2350,13 @@ error_param: * i40e_vc_request_queues_msg * @vf: pointer to the VF info * @msg: pointer to the msg buffer - * @msglen: msg length * * VFs get a default number of queues but can use this message to request a * different number. If the request is successful, PF will reset the VF and * return 0. If unsuccessful, PF will send message informing VF of number of * available queues and return result of sending VF a message. **/ -static int i40e_vc_request_queues_msg(struct i40e_vf *vf, u8 *msg, int msglen) +static int i40e_vc_request_queues_msg(struct i40e_vf *vf, u8 *msg) { struct virtchnl_vf_res_request *vfres = (struct virtchnl_vf_res_request *)msg; @@ -2360,11 +2400,10 @@ static int i40e_vc_request_queues_msg(struct i40e_vf *vf, u8 *msg, int msglen) * i40e_vc_get_stats_msg * @vf: pointer to the VF info * @msg: pointer to the msg buffer - * @msglen: msg length * * called from the VF to get vsi stats **/ -static int i40e_vc_get_stats_msg(struct i40e_vf *vf, u8 *msg, u16 msglen) +static int i40e_vc_get_stats_msg(struct i40e_vf *vf, u8 *msg) { struct virtchnl_queue_select *vqs = (struct virtchnl_queue_select *)msg; @@ -2470,11 +2509,10 @@ static inline int i40e_check_vf_permission(struct i40e_vf *vf, * i40e_vc_add_mac_addr_msg * @vf: pointer to the VF info * @msg: pointer to the msg buffer - * @msglen: msg length * * add guest mac address filter **/ -static int i40e_vc_add_mac_addr_msg(struct i40e_vf *vf, u8 *msg, u16 msglen) +static int i40e_vc_add_mac_addr_msg(struct i40e_vf *vf, u8 *msg) { struct virtchnl_ether_addr_list *al = (struct virtchnl_ether_addr_list *)msg; @@ -2541,11 +2579,10 @@ error_param: * i40e_vc_del_mac_addr_msg * @vf: pointer to the VF info * @msg: pointer to the msg buffer - * @msglen: msg length * * remove guest mac address filter **/ -static int i40e_vc_del_mac_addr_msg(struct i40e_vf *vf, u8 *msg, u16 msglen) +static int i40e_vc_del_mac_addr_msg(struct i40e_vf *vf, u8 *msg) { struct virtchnl_ether_addr_list *al = (struct virtchnl_ether_addr_list *)msg; @@ -2611,11 +2648,10 @@ error_param: * i40e_vc_add_vlan_msg * @vf: pointer to the VF info * @msg: pointer to the msg buffer - * @msglen: msg length * * program guest vlan id **/ -static int i40e_vc_add_vlan_msg(struct i40e_vf *vf, u8 *msg, u16 msglen) +static int i40e_vc_add_vlan_msg(struct i40e_vf *vf, u8 *msg) { struct virtchnl_vlan_filter_list *vfl = (struct virtchnl_vlan_filter_list *)msg; @@ -2684,11 +2720,10 @@ error_param: * i40e_vc_remove_vlan_msg * @vf: pointer to the VF info * @msg: pointer to the msg buffer - * @msglen: msg length * * remove programmed guest vlan id **/ -static int i40e_vc_remove_vlan_msg(struct i40e_vf *vf, u8 *msg, u16 msglen) +static int i40e_vc_remove_vlan_msg(struct i40e_vf *vf, u8 *msg) { struct virtchnl_vlan_filter_list *vfl = (struct virtchnl_vlan_filter_list *)msg; @@ -2771,13 +2806,11 @@ error_param: * i40e_vc_iwarp_qvmap_msg * @vf: pointer to the VF info * @msg: pointer to the msg buffer - * @msglen: msg length * @config: config qvmap or release it * * called from the VF for the iwarp msgs **/ -static int i40e_vc_iwarp_qvmap_msg(struct i40e_vf *vf, u8 *msg, u16 msglen, - bool config) +static int i40e_vc_iwarp_qvmap_msg(struct i40e_vf *vf, u8 *msg, bool config) { struct virtchnl_iwarp_qvlist_info *qvlist_info = (struct virtchnl_iwarp_qvlist_info *)msg; @@ -2808,11 +2841,10 @@ error_param: * i40e_vc_config_rss_key * @vf: pointer to the VF info * @msg: pointer to the msg buffer - * @msglen: msg length * * Configure the VF's RSS key **/ -static int i40e_vc_config_rss_key(struct i40e_vf *vf, u8 *msg, u16 msglen) +static int i40e_vc_config_rss_key(struct i40e_vf *vf, u8 *msg) { struct virtchnl_rss_key *vrk = (struct virtchnl_rss_key *)msg; @@ -2840,11 +2872,10 @@ err: * i40e_vc_config_rss_lut * @vf: pointer to the VF info * @msg: pointer to the msg buffer - * @msglen: msg length * * Configure the VF's RSS LUT **/ -static int i40e_vc_config_rss_lut(struct i40e_vf *vf, u8 *msg, u16 msglen) +static int i40e_vc_config_rss_lut(struct i40e_vf *vf, u8 *msg) { struct virtchnl_rss_lut *vrl = (struct virtchnl_rss_lut *)msg; @@ -2872,11 +2903,10 @@ err: * i40e_vc_get_rss_hena * @vf: pointer to the VF info * @msg: pointer to the msg buffer - * @msglen: msg length * * Return the RSS HENA bits allowed by the hardware **/ -static int i40e_vc_get_rss_hena(struct i40e_vf *vf, u8 *msg, u16 msglen) +static int i40e_vc_get_rss_hena(struct i40e_vf *vf, u8 *msg) { struct virtchnl_rss_hena *vrh = NULL; struct i40e_pf *pf = vf->pf; @@ -2908,11 +2938,10 @@ err: * i40e_vc_set_rss_hena * @vf: pointer to the VF info * @msg: pointer to the msg buffer - * @msglen: msg length * * Set the RSS HENA bits for the VF **/ -static int i40e_vc_set_rss_hena(struct i40e_vf *vf, u8 *msg, u16 msglen) +static int i40e_vc_set_rss_hena(struct i40e_vf *vf, u8 *msg) { struct virtchnl_rss_hena *vrh = (struct virtchnl_rss_hena *)msg; @@ -2937,12 +2966,10 @@ err: * i40e_vc_enable_vlan_stripping * @vf: pointer to the VF info * @msg: pointer to the msg buffer - * @msglen: msg length * * Enable vlan header stripping for the VF **/ -static int i40e_vc_enable_vlan_stripping(struct i40e_vf *vf, u8 *msg, - u16 msglen) +static int i40e_vc_enable_vlan_stripping(struct i40e_vf *vf, u8 *msg) { struct i40e_vsi *vsi = vf->pf->vsi[vf->lan_vsi_idx]; i40e_status aq_ret = 0; @@ -2964,12 +2991,10 @@ err: * i40e_vc_disable_vlan_stripping * @vf: pointer to the VF info * @msg: pointer to the msg buffer - * @msglen: msg length * * Disable vlan header stripping for the VF **/ -static int i40e_vc_disable_vlan_stripping(struct i40e_vf *vf, u8 *msg, - u16 msglen) +static int i40e_vc_disable_vlan_stripping(struct i40e_vf *vf, u8 *msg) { struct i40e_vsi *vsi = vf->pf->vsi[vf->lan_vsi_idx]; i40e_status aq_ret = 0; @@ -3669,65 +3694,65 @@ int i40e_vc_process_vf_msg(struct i40e_pf *pf, s16 vf_id, u32 v_opcode, ret = 0; break; case VIRTCHNL_OP_CONFIG_PROMISCUOUS_MODE: - ret = i40e_vc_config_promiscuous_mode_msg(vf, msg, msglen); + ret = i40e_vc_config_promiscuous_mode_msg(vf, msg); break; case VIRTCHNL_OP_CONFIG_VSI_QUEUES: - ret = i40e_vc_config_queues_msg(vf, msg, msglen); + ret = i40e_vc_config_queues_msg(vf, msg); break; case VIRTCHNL_OP_CONFIG_IRQ_MAP: - ret = i40e_vc_config_irq_map_msg(vf, msg, msglen); + ret = i40e_vc_config_irq_map_msg(vf, msg); break; case VIRTCHNL_OP_ENABLE_QUEUES: - ret = i40e_vc_enable_queues_msg(vf, msg, msglen); + ret = i40e_vc_enable_queues_msg(vf, msg); i40e_vc_notify_vf_link_state(vf); break; case VIRTCHNL_OP_DISABLE_QUEUES: - ret = i40e_vc_disable_queues_msg(vf, msg, msglen); + ret = i40e_vc_disable_queues_msg(vf, msg); break; case VIRTCHNL_OP_ADD_ETH_ADDR: - ret = i40e_vc_add_mac_addr_msg(vf, msg, msglen); + ret = i40e_vc_add_mac_addr_msg(vf, msg); break; case VIRTCHNL_OP_DEL_ETH_ADDR: - ret = i40e_vc_del_mac_addr_msg(vf, msg, msglen); + ret = i40e_vc_del_mac_addr_msg(vf, msg); break; case VIRTCHNL_OP_ADD_VLAN: - ret = i40e_vc_add_vlan_msg(vf, msg, msglen); + ret = i40e_vc_add_vlan_msg(vf, msg); break; case VIRTCHNL_OP_DEL_VLAN: - ret = i40e_vc_remove_vlan_msg(vf, msg, msglen); + ret = i40e_vc_remove_vlan_msg(vf, msg); break; case VIRTCHNL_OP_GET_STATS: - ret = i40e_vc_get_stats_msg(vf, msg, msglen); + ret = i40e_vc_get_stats_msg(vf, msg); break; case VIRTCHNL_OP_IWARP: ret = i40e_vc_iwarp_msg(vf, msg, msglen); break; case VIRTCHNL_OP_CONFIG_IWARP_IRQ_MAP: - ret = i40e_vc_iwarp_qvmap_msg(vf, msg, msglen, true); + ret = i40e_vc_iwarp_qvmap_msg(vf, msg, true); break; case VIRTCHNL_OP_RELEASE_IWARP_IRQ_MAP: - ret = i40e_vc_iwarp_qvmap_msg(vf, msg, msglen, false); + ret = i40e_vc_iwarp_qvmap_msg(vf, msg, false); break; case VIRTCHNL_OP_CONFIG_RSS_KEY: - ret = i40e_vc_config_rss_key(vf, msg, msglen); + ret = i40e_vc_config_rss_key(vf, msg); break; case VIRTCHNL_OP_CONFIG_RSS_LUT: - ret = i40e_vc_config_rss_lut(vf, msg, msglen); + ret = i40e_vc_config_rss_lut(vf, msg); break; case VIRTCHNL_OP_GET_RSS_HENA_CAPS: - ret = i40e_vc_get_rss_hena(vf, msg, msglen); + ret = i40e_vc_get_rss_hena(vf, msg); break; case VIRTCHNL_OP_SET_RSS_HENA: - ret = i40e_vc_set_rss_hena(vf, msg, msglen); + ret = i40e_vc_set_rss_hena(vf, msg); break; case VIRTCHNL_OP_ENABLE_VLAN_STRIPPING: - ret = i40e_vc_enable_vlan_stripping(vf, msg, msglen); + ret = i40e_vc_enable_vlan_stripping(vf, msg); break; case VIRTCHNL_OP_DISABLE_VLAN_STRIPPING: - ret = i40e_vc_disable_vlan_stripping(vf, msg, msglen); + ret = i40e_vc_disable_vlan_stripping(vf, msg); break; case VIRTCHNL_OP_REQUEST_QUEUES: - ret = i40e_vc_request_queues_msg(vf, msg, msglen); + ret = i40e_vc_request_queues_msg(vf, msg); break; case VIRTCHNL_OP_ENABLE_CHANNELS: ret = i40e_vc_add_qch_msg(vf, msg); @@ -3796,6 +3821,35 @@ int i40e_vc_process_vflr_event(struct i40e_pf *pf) } /** + * i40e_validate_vf + * @pf: the physical function + * @vf_id: VF identifier + * + * Check that the VF is enabled and the VSI exists. + * + * Returns 0 on success, negative on failure + **/ +static int i40e_validate_vf(struct i40e_pf *pf, int vf_id) +{ + struct i40e_vsi *vsi; + struct i40e_vf *vf; + int ret = 0; + + if (vf_id >= pf->num_alloc_vfs) { + dev_err(&pf->pdev->dev, + "Invalid VF Identifier %d\n", vf_id); + ret = -EINVAL; + goto err_out; + } + vf = &pf->vf[vf_id]; + vsi = i40e_find_vsi_from_id(pf, vf->lan_vsi_id); + if (!vsi) + ret = -EINVAL; +err_out: + return ret; +} + +/** * i40e_ndo_set_vf_mac * @netdev: network interface device structure * @vf_id: VF identifier @@ -3816,14 +3870,11 @@ int i40e_ndo_set_vf_mac(struct net_device *netdev, int vf_id, u8 *mac) u8 i; /* validate the request */ - if (vf_id >= pf->num_alloc_vfs) { - dev_err(&pf->pdev->dev, - "Invalid VF Identifier %d\n", vf_id); - ret = -EINVAL; + ret = i40e_validate_vf(pf, vf_id); + if (ret) goto error_param; - } - vf = &(pf->vf[vf_id]); + vf = &pf->vf[vf_id]; vsi = pf->vsi[vf->lan_vsi_idx]; /* When the VF is resetting wait until it is done. @@ -3942,11 +3993,9 @@ int i40e_ndo_set_vf_port_vlan(struct net_device *netdev, int vf_id, int ret = 0; /* validate the request */ - if (vf_id >= pf->num_alloc_vfs) { - dev_err(&pf->pdev->dev, "Invalid VF Identifier %d\n", vf_id); - ret = -EINVAL; + ret = i40e_validate_vf(pf, vf_id); + if (ret) goto error_pvid; - } if ((vlan_id > I40E_MAX_VLANID) || (qos > 7)) { dev_err(&pf->pdev->dev, "Invalid VF Parameters\n"); @@ -3960,7 +4009,7 @@ int i40e_ndo_set_vf_port_vlan(struct net_device *netdev, int vf_id, goto error_pvid; } - vf = &(pf->vf[vf_id]); + vf = &pf->vf[vf_id]; vsi = pf->vsi[vf->lan_vsi_idx]; if (!test_bit(I40E_VF_STATE_INIT, &vf->vf_states)) { dev_err(&pf->pdev->dev, "VF %d still in reset. Try again.\n", @@ -4080,11 +4129,9 @@ int i40e_ndo_set_vf_bw(struct net_device *netdev, int vf_id, int min_tx_rate, int ret = 0; /* validate the request */ - if (vf_id >= pf->num_alloc_vfs) { - dev_err(&pf->pdev->dev, "Invalid VF Identifier %d.\n", vf_id); - ret = -EINVAL; + ret = i40e_validate_vf(pf, vf_id); + if (ret) goto error; - } if (min_tx_rate) { dev_err(&pf->pdev->dev, "Invalid min tx rate (%d) (greater than 0) specified for VF %d.\n", @@ -4092,7 +4139,7 @@ int i40e_ndo_set_vf_bw(struct net_device *netdev, int vf_id, int min_tx_rate, return -EINVAL; } - vf = &(pf->vf[vf_id]); + vf = &pf->vf[vf_id]; vsi = pf->vsi[vf->lan_vsi_idx]; if (!test_bit(I40E_VF_STATE_INIT, &vf->vf_states)) { dev_err(&pf->pdev->dev, "VF %d still in reset. Try again.\n", @@ -4128,13 +4175,11 @@ int i40e_ndo_get_vf_config(struct net_device *netdev, int ret = 0; /* validate the request */ - if (vf_id >= pf->num_alloc_vfs) { - dev_err(&pf->pdev->dev, "Invalid VF Identifier %d\n", vf_id); - ret = -EINVAL; + ret = i40e_validate_vf(pf, vf_id); + if (ret) goto error_param; - } - vf = &(pf->vf[vf_id]); + vf = &pf->vf[vf_id]; /* first vsi is always the LAN vsi */ vsi = pf->vsi[vf->lan_vsi_idx]; if (!test_bit(I40E_VF_STATE_INIT, &vf->vf_states)) { diff --git a/drivers/net/ethernet/intel/i40e/i40e_xsk.c b/drivers/net/ethernet/intel/i40e/i40e_xsk.c index 2ebfc78bbd09..add1e457886d 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_xsk.c +++ b/drivers/net/ethernet/intel/i40e/i40e_xsk.c @@ -140,6 +140,7 @@ static void i40e_xsk_umem_dma_unmap(struct i40e_vsi *vsi, struct xdp_umem *umem) static int i40e_xsk_umem_enable(struct i40e_vsi *vsi, struct xdp_umem *umem, u16 qid) { + struct xdp_umem_fq_reuse *reuseq; bool if_running; int err; @@ -156,6 +157,12 @@ static int i40e_xsk_umem_enable(struct i40e_vsi *vsi, struct xdp_umem *umem, return -EBUSY; } + reuseq = xsk_reuseq_prepare(vsi->rx_rings[0]->count); + if (!reuseq) + return -ENOMEM; + + xsk_reuseq_free(xsk_reuseq_swap(umem, reuseq)); + err = i40e_xsk_umem_dma_map(vsi, umem); if (err) return err; @@ -353,16 +360,46 @@ static bool i40e_alloc_buffer_zc(struct i40e_ring *rx_ring, } /** - * i40e_alloc_rx_buffers_zc - Allocates a number of Rx buffers + * i40e_alloc_buffer_slow_zc - Allocates an i40e_rx_buffer * @rx_ring: Rx ring - * @count: The number of buffers to allocate + * @bi: Rx buffer to populate * - * This function allocates a number of Rx buffers and places them on - * the Rx ring. + * This function allocates an Rx buffer. The buffer can come from fill + * queue, or via the reuse queue. * * Returns true for a successful allocation, false otherwise **/ -bool i40e_alloc_rx_buffers_zc(struct i40e_ring *rx_ring, u16 count) +static bool i40e_alloc_buffer_slow_zc(struct i40e_ring *rx_ring, + struct i40e_rx_buffer *bi) +{ + struct xdp_umem *umem = rx_ring->xsk_umem; + u64 handle, hr; + + if (!xsk_umem_peek_addr_rq(umem, &handle)) { + rx_ring->rx_stats.alloc_page_failed++; + return false; + } + + handle &= rx_ring->xsk_umem->chunk_mask; + + hr = umem->headroom + XDP_PACKET_HEADROOM; + + bi->dma = xdp_umem_get_dma(umem, handle); + bi->dma += hr; + + bi->addr = xdp_umem_get_data(umem, handle); + bi->addr += hr; + + bi->handle = handle + umem->headroom; + + xsk_umem_discard_addr_rq(umem); + return true; +} + +static __always_inline bool +__i40e_alloc_rx_buffers_zc(struct i40e_ring *rx_ring, u16 count, + bool alloc(struct i40e_ring *rx_ring, + struct i40e_rx_buffer *bi)) { u16 ntu = rx_ring->next_to_use; union i40e_rx_desc *rx_desc; @@ -372,7 +409,7 @@ bool i40e_alloc_rx_buffers_zc(struct i40e_ring *rx_ring, u16 count) rx_desc = I40E_RX_DESC(rx_ring, ntu); bi = &rx_ring->rx_bi[ntu]; do { - if (!i40e_alloc_buffer_zc(rx_ring, bi)) { + if (!alloc(rx_ring, bi)) { ok = false; goto no_buffers; } @@ -405,6 +442,38 @@ no_buffers: } /** + * i40e_alloc_rx_buffers_zc - Allocates a number of Rx buffers + * @rx_ring: Rx ring + * @count: The number of buffers to allocate + * + * This function allocates a number of Rx buffers from the reuse queue + * or fill ring and places them on the Rx ring. + * + * Returns true for a successful allocation, false otherwise + **/ +bool i40e_alloc_rx_buffers_zc(struct i40e_ring *rx_ring, u16 count) +{ + return __i40e_alloc_rx_buffers_zc(rx_ring, count, + i40e_alloc_buffer_slow_zc); +} + +/** + * i40e_alloc_rx_buffers_fast_zc - Allocates a number of Rx buffers + * @rx_ring: Rx ring + * @count: The number of buffers to allocate + * + * This function allocates a number of Rx buffers from the fill ring + * or the internal recycle mechanism and places them on the Rx ring. + * + * Returns true for a successful allocation, false otherwise + **/ +static bool i40e_alloc_rx_buffers_fast_zc(struct i40e_ring *rx_ring, u16 count) +{ + return __i40e_alloc_rx_buffers_zc(rx_ring, count, + i40e_alloc_buffer_zc); +} + +/** * i40e_get_rx_buffer_zc - Return the current Rx buffer * @rx_ring: Rx ring * @size: The size of the rx buffer (read from descriptor) @@ -571,8 +640,8 @@ int i40e_clean_rx_irq_zc(struct i40e_ring *rx_ring, int budget) if (cleaned_count >= I40E_RX_BUFFER_WRITE) { failure = failure || - !i40e_alloc_rx_buffers_zc(rx_ring, - cleaned_count); + !i40e_alloc_rx_buffers_fast_zc(rx_ring, + cleaned_count); cleaned_count = 0; } @@ -830,3 +899,69 @@ int i40e_xsk_async_xmit(struct net_device *dev, u32 queue_id) return 0; } + +void i40e_xsk_clean_rx_ring(struct i40e_ring *rx_ring) +{ + u16 i; + + for (i = 0; i < rx_ring->count; i++) { + struct i40e_rx_buffer *rx_bi = &rx_ring->rx_bi[i]; + + if (!rx_bi->addr) + continue; + + xsk_umem_fq_reuse(rx_ring->xsk_umem, rx_bi->handle); + rx_bi->addr = NULL; + } +} + +/** + * i40e_xsk_clean_xdp_ring - Clean the XDP Tx ring on shutdown + * @xdp_ring: XDP Tx ring + **/ +void i40e_xsk_clean_tx_ring(struct i40e_ring *tx_ring) +{ + u16 ntc = tx_ring->next_to_clean, ntu = tx_ring->next_to_use; + struct xdp_umem *umem = tx_ring->xsk_umem; + struct i40e_tx_buffer *tx_bi; + u32 xsk_frames = 0; + + while (ntc != ntu) { + tx_bi = &tx_ring->tx_bi[ntc]; + + if (tx_bi->xdpf) + i40e_clean_xdp_tx_buffer(tx_ring, tx_bi); + else + xsk_frames++; + + tx_bi->xdpf = NULL; + + ntc++; + if (ntc >= tx_ring->count) + ntc = 0; + } + + if (xsk_frames) + xsk_umem_complete_tx(umem, xsk_frames); +} + +/** + * i40e_xsk_any_rx_ring_enabled - Checks if Rx rings have AF_XDP UMEM attached + * @vsi: vsi + * + * Returns true if any of the Rx rings has an AF_XDP UMEM attached + **/ +bool i40e_xsk_any_rx_ring_enabled(struct i40e_vsi *vsi) +{ + int i; + + if (!vsi->xsk_umems) + return false; + + for (i = 0; i < vsi->num_queue_pairs; i++) { + if (vsi->xsk_umems[i]) + return true; + } + + return false; +} diff --git a/drivers/net/ethernet/intel/i40evf/Makefile b/drivers/net/ethernet/intel/i40evf/Makefile deleted file mode 100644 index 3c5c6e962280..000000000000 --- a/drivers/net/ethernet/intel/i40evf/Makefile +++ /dev/null @@ -1,16 +0,0 @@ -# SPDX-License-Identifier: GPL-2.0 -# Copyright(c) 2013 - 2018 Intel Corporation. - -# -## Makefile for the Intel(R) 40GbE VF driver -# -# - -ccflags-y += -I$(src) -subdir-ccflags-y += -I$(src) - -obj-$(CONFIG_I40EVF) += i40evf.o - -i40evf-objs := i40evf_main.o i40evf_ethtool.o i40evf_virtchnl.o \ - i40e_txrx.o i40e_common.o i40e_adminq.o i40evf_client.o - diff --git a/drivers/net/ethernet/intel/i40evf/i40e_adminq_cmd.h b/drivers/net/ethernet/intel/i40evf/i40e_adminq_cmd.h deleted file mode 100644 index 5fd8529465d4..000000000000 --- a/drivers/net/ethernet/intel/i40evf/i40e_adminq_cmd.h +++ /dev/null @@ -1,2717 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright(c) 2013 - 2018 Intel Corporation. */ - -#ifndef _I40E_ADMINQ_CMD_H_ -#define _I40E_ADMINQ_CMD_H_ - -/* This header file defines the i40e Admin Queue commands and is shared between - * i40e Firmware and Software. - * - * This file needs to comply with the Linux Kernel coding style. - */ - -#define I40E_FW_API_VERSION_MAJOR 0x0001 -#define I40E_FW_API_VERSION_MINOR_X722 0x0005 -#define I40E_FW_API_VERSION_MINOR_X710 0x0007 - -#define I40E_FW_MINOR_VERSION(_h) ((_h)->mac.type == I40E_MAC_XL710 ? \ - I40E_FW_API_VERSION_MINOR_X710 : \ - I40E_FW_API_VERSION_MINOR_X722) - -/* API version 1.7 implements additional link and PHY-specific APIs */ -#define I40E_MINOR_VER_GET_LINK_INFO_XL710 0x0007 - -struct i40e_aq_desc { - __le16 flags; - __le16 opcode; - __le16 datalen; - __le16 retval; - __le32 cookie_high; - __le32 cookie_low; - union { - struct { - __le32 param0; - __le32 param1; - __le32 param2; - __le32 param3; - } internal; - struct { - __le32 param0; - __le32 param1; - __le32 addr_high; - __le32 addr_low; - } external; - u8 raw[16]; - } params; -}; - -/* Flags sub-structure - * |0 |1 |2 |3 |4 |5 |6 |7 |8 |9 |10 |11 |12 |13 |14 |15 | - * |DD |CMP|ERR|VFE| * * RESERVED * * |LB |RD |VFC|BUF|SI |EI |FE | - */ - -/* command flags and offsets*/ -#define I40E_AQ_FLAG_DD_SHIFT 0 -#define I40E_AQ_FLAG_CMP_SHIFT 1 -#define I40E_AQ_FLAG_ERR_SHIFT 2 -#define I40E_AQ_FLAG_VFE_SHIFT 3 -#define I40E_AQ_FLAG_LB_SHIFT 9 -#define I40E_AQ_FLAG_RD_SHIFT 10 -#define I40E_AQ_FLAG_VFC_SHIFT 11 -#define I40E_AQ_FLAG_BUF_SHIFT 12 -#define I40E_AQ_FLAG_SI_SHIFT 13 -#define I40E_AQ_FLAG_EI_SHIFT 14 -#define I40E_AQ_FLAG_FE_SHIFT 15 - -#define I40E_AQ_FLAG_DD BIT(I40E_AQ_FLAG_DD_SHIFT) /* 0x1 */ -#define I40E_AQ_FLAG_CMP BIT(I40E_AQ_FLAG_CMP_SHIFT) /* 0x2 */ -#define I40E_AQ_FLAG_ERR BIT(I40E_AQ_FLAG_ERR_SHIFT) /* 0x4 */ -#define I40E_AQ_FLAG_VFE BIT(I40E_AQ_FLAG_VFE_SHIFT) /* 0x8 */ -#define I40E_AQ_FLAG_LB BIT(I40E_AQ_FLAG_LB_SHIFT) /* 0x200 */ -#define I40E_AQ_FLAG_RD BIT(I40E_AQ_FLAG_RD_SHIFT) /* 0x400 */ -#define I40E_AQ_FLAG_VFC BIT(I40E_AQ_FLAG_VFC_SHIFT) /* 0x800 */ -#define I40E_AQ_FLAG_BUF BIT(I40E_AQ_FLAG_BUF_SHIFT) /* 0x1000 */ -#define I40E_AQ_FLAG_SI BIT(I40E_AQ_FLAG_SI_SHIFT) /* 0x2000 */ -#define I40E_AQ_FLAG_EI BIT(I40E_AQ_FLAG_EI_SHIFT) /* 0x4000 */ -#define I40E_AQ_FLAG_FE BIT(I40E_AQ_FLAG_FE_SHIFT) /* 0x8000 */ - -/* error codes */ -enum i40e_admin_queue_err { - I40E_AQ_RC_OK = 0, /* success */ - I40E_AQ_RC_EPERM = 1, /* Operation not permitted */ - I40E_AQ_RC_ENOENT = 2, /* No such element */ - I40E_AQ_RC_ESRCH = 3, /* Bad opcode */ - I40E_AQ_RC_EINTR = 4, /* operation interrupted */ - I40E_AQ_RC_EIO = 5, /* I/O error */ - I40E_AQ_RC_ENXIO = 6, /* No such resource */ - I40E_AQ_RC_E2BIG = 7, /* Arg too long */ - I40E_AQ_RC_EAGAIN = 8, /* Try again */ - I40E_AQ_RC_ENOMEM = 9, /* Out of memory */ - I40E_AQ_RC_EACCES = 10, /* Permission denied */ - I40E_AQ_RC_EFAULT = 11, /* Bad address */ - I40E_AQ_RC_EBUSY = 12, /* Device or resource busy */ - I40E_AQ_RC_EEXIST = 13, /* object already exists */ - I40E_AQ_RC_EINVAL = 14, /* Invalid argument */ - I40E_AQ_RC_ENOTTY = 15, /* Not a typewriter */ - I40E_AQ_RC_ENOSPC = 16, /* No space left or alloc failure */ - I40E_AQ_RC_ENOSYS = 17, /* Function not implemented */ - I40E_AQ_RC_ERANGE = 18, /* Parameter out of range */ - I40E_AQ_RC_EFLUSHED = 19, /* Cmd flushed due to prev cmd error */ - I40E_AQ_RC_BAD_ADDR = 20, /* Descriptor contains a bad pointer */ - I40E_AQ_RC_EMODE = 21, /* Op not allowed in current dev mode */ - I40E_AQ_RC_EFBIG = 22, /* File too large */ -}; - -/* Admin Queue command opcodes */ -enum i40e_admin_queue_opc { - /* aq commands */ - i40e_aqc_opc_get_version = 0x0001, - i40e_aqc_opc_driver_version = 0x0002, - i40e_aqc_opc_queue_shutdown = 0x0003, - i40e_aqc_opc_set_pf_context = 0x0004, - - /* resource ownership */ - i40e_aqc_opc_request_resource = 0x0008, - i40e_aqc_opc_release_resource = 0x0009, - - i40e_aqc_opc_list_func_capabilities = 0x000A, - i40e_aqc_opc_list_dev_capabilities = 0x000B, - - /* Proxy commands */ - i40e_aqc_opc_set_proxy_config = 0x0104, - i40e_aqc_opc_set_ns_proxy_table_entry = 0x0105, - - /* LAA */ - i40e_aqc_opc_mac_address_read = 0x0107, - i40e_aqc_opc_mac_address_write = 0x0108, - - /* PXE */ - i40e_aqc_opc_clear_pxe_mode = 0x0110, - - /* WoL commands */ - i40e_aqc_opc_set_wol_filter = 0x0120, - i40e_aqc_opc_get_wake_reason = 0x0121, - - /* internal switch commands */ - i40e_aqc_opc_get_switch_config = 0x0200, - i40e_aqc_opc_add_statistics = 0x0201, - i40e_aqc_opc_remove_statistics = 0x0202, - i40e_aqc_opc_set_port_parameters = 0x0203, - i40e_aqc_opc_get_switch_resource_alloc = 0x0204, - i40e_aqc_opc_set_switch_config = 0x0205, - i40e_aqc_opc_rx_ctl_reg_read = 0x0206, - i40e_aqc_opc_rx_ctl_reg_write = 0x0207, - - i40e_aqc_opc_add_vsi = 0x0210, - i40e_aqc_opc_update_vsi_parameters = 0x0211, - i40e_aqc_opc_get_vsi_parameters = 0x0212, - - i40e_aqc_opc_add_pv = 0x0220, - i40e_aqc_opc_update_pv_parameters = 0x0221, - i40e_aqc_opc_get_pv_parameters = 0x0222, - - i40e_aqc_opc_add_veb = 0x0230, - i40e_aqc_opc_update_veb_parameters = 0x0231, - i40e_aqc_opc_get_veb_parameters = 0x0232, - - i40e_aqc_opc_delete_element = 0x0243, - - i40e_aqc_opc_add_macvlan = 0x0250, - i40e_aqc_opc_remove_macvlan = 0x0251, - i40e_aqc_opc_add_vlan = 0x0252, - i40e_aqc_opc_remove_vlan = 0x0253, - i40e_aqc_opc_set_vsi_promiscuous_modes = 0x0254, - i40e_aqc_opc_add_tag = 0x0255, - i40e_aqc_opc_remove_tag = 0x0256, - i40e_aqc_opc_add_multicast_etag = 0x0257, - i40e_aqc_opc_remove_multicast_etag = 0x0258, - i40e_aqc_opc_update_tag = 0x0259, - i40e_aqc_opc_add_control_packet_filter = 0x025A, - i40e_aqc_opc_remove_control_packet_filter = 0x025B, - i40e_aqc_opc_add_cloud_filters = 0x025C, - i40e_aqc_opc_remove_cloud_filters = 0x025D, - i40e_aqc_opc_clear_wol_switch_filters = 0x025E, - - i40e_aqc_opc_add_mirror_rule = 0x0260, - i40e_aqc_opc_delete_mirror_rule = 0x0261, - - /* Dynamic Device Personalization */ - i40e_aqc_opc_write_personalization_profile = 0x0270, - i40e_aqc_opc_get_personalization_profile_list = 0x0271, - - /* DCB commands */ - i40e_aqc_opc_dcb_ignore_pfc = 0x0301, - i40e_aqc_opc_dcb_updated = 0x0302, - i40e_aqc_opc_set_dcb_parameters = 0x0303, - - /* TX scheduler */ - i40e_aqc_opc_configure_vsi_bw_limit = 0x0400, - i40e_aqc_opc_configure_vsi_ets_sla_bw_limit = 0x0406, - i40e_aqc_opc_configure_vsi_tc_bw = 0x0407, - i40e_aqc_opc_query_vsi_bw_config = 0x0408, - i40e_aqc_opc_query_vsi_ets_sla_config = 0x040A, - i40e_aqc_opc_configure_switching_comp_bw_limit = 0x0410, - - i40e_aqc_opc_enable_switching_comp_ets = 0x0413, - i40e_aqc_opc_modify_switching_comp_ets = 0x0414, - i40e_aqc_opc_disable_switching_comp_ets = 0x0415, - i40e_aqc_opc_configure_switching_comp_ets_bw_limit = 0x0416, - i40e_aqc_opc_configure_switching_comp_bw_config = 0x0417, - i40e_aqc_opc_query_switching_comp_ets_config = 0x0418, - i40e_aqc_opc_query_port_ets_config = 0x0419, - i40e_aqc_opc_query_switching_comp_bw_config = 0x041A, - i40e_aqc_opc_suspend_port_tx = 0x041B, - i40e_aqc_opc_resume_port_tx = 0x041C, - i40e_aqc_opc_configure_partition_bw = 0x041D, - /* hmc */ - i40e_aqc_opc_query_hmc_resource_profile = 0x0500, - i40e_aqc_opc_set_hmc_resource_profile = 0x0501, - - /* phy commands*/ - i40e_aqc_opc_get_phy_abilities = 0x0600, - i40e_aqc_opc_set_phy_config = 0x0601, - i40e_aqc_opc_set_mac_config = 0x0603, - i40e_aqc_opc_set_link_restart_an = 0x0605, - i40e_aqc_opc_get_link_status = 0x0607, - i40e_aqc_opc_set_phy_int_mask = 0x0613, - i40e_aqc_opc_get_local_advt_reg = 0x0614, - i40e_aqc_opc_set_local_advt_reg = 0x0615, - i40e_aqc_opc_get_partner_advt = 0x0616, - i40e_aqc_opc_set_lb_modes = 0x0618, - i40e_aqc_opc_get_phy_wol_caps = 0x0621, - i40e_aqc_opc_set_phy_debug = 0x0622, - i40e_aqc_opc_upload_ext_phy_fm = 0x0625, - i40e_aqc_opc_run_phy_activity = 0x0626, - i40e_aqc_opc_set_phy_register = 0x0628, - i40e_aqc_opc_get_phy_register = 0x0629, - - /* NVM commands */ - i40e_aqc_opc_nvm_read = 0x0701, - i40e_aqc_opc_nvm_erase = 0x0702, - i40e_aqc_opc_nvm_update = 0x0703, - i40e_aqc_opc_nvm_config_read = 0x0704, - i40e_aqc_opc_nvm_config_write = 0x0705, - i40e_aqc_opc_oem_post_update = 0x0720, - i40e_aqc_opc_thermal_sensor = 0x0721, - - /* virtualization commands */ - i40e_aqc_opc_send_msg_to_pf = 0x0801, - i40e_aqc_opc_send_msg_to_vf = 0x0802, - i40e_aqc_opc_send_msg_to_peer = 0x0803, - - /* alternate structure */ - i40e_aqc_opc_alternate_write = 0x0900, - i40e_aqc_opc_alternate_write_indirect = 0x0901, - i40e_aqc_opc_alternate_read = 0x0902, - i40e_aqc_opc_alternate_read_indirect = 0x0903, - i40e_aqc_opc_alternate_write_done = 0x0904, - i40e_aqc_opc_alternate_set_mode = 0x0905, - i40e_aqc_opc_alternate_clear_port = 0x0906, - - /* LLDP commands */ - i40e_aqc_opc_lldp_get_mib = 0x0A00, - i40e_aqc_opc_lldp_update_mib = 0x0A01, - i40e_aqc_opc_lldp_add_tlv = 0x0A02, - i40e_aqc_opc_lldp_update_tlv = 0x0A03, - i40e_aqc_opc_lldp_delete_tlv = 0x0A04, - i40e_aqc_opc_lldp_stop = 0x0A05, - i40e_aqc_opc_lldp_start = 0x0A06, - - /* Tunnel commands */ - i40e_aqc_opc_add_udp_tunnel = 0x0B00, - i40e_aqc_opc_del_udp_tunnel = 0x0B01, - i40e_aqc_opc_set_rss_key = 0x0B02, - i40e_aqc_opc_set_rss_lut = 0x0B03, - i40e_aqc_opc_get_rss_key = 0x0B04, - i40e_aqc_opc_get_rss_lut = 0x0B05, - - /* Async Events */ - i40e_aqc_opc_event_lan_overflow = 0x1001, - - /* OEM commands */ - i40e_aqc_opc_oem_parameter_change = 0xFE00, - i40e_aqc_opc_oem_device_status_change = 0xFE01, - i40e_aqc_opc_oem_ocsd_initialize = 0xFE02, - i40e_aqc_opc_oem_ocbb_initialize = 0xFE03, - - /* debug commands */ - i40e_aqc_opc_debug_read_reg = 0xFF03, - i40e_aqc_opc_debug_write_reg = 0xFF04, - i40e_aqc_opc_debug_modify_reg = 0xFF07, - i40e_aqc_opc_debug_dump_internals = 0xFF08, -}; - -/* command structures and indirect data structures */ - -/* Structure naming conventions: - * - no suffix for direct command descriptor structures - * - _data for indirect sent data - * - _resp for indirect return data (data which is both will use _data) - * - _completion for direct return data - * - _element_ for repeated elements (may also be _data or _resp) - * - * Command structures are expected to overlay the params.raw member of the basic - * descriptor, and as such cannot exceed 16 bytes in length. - */ - -/* This macro is used to generate a compilation error if a structure - * is not exactly the correct length. It gives a divide by zero error if the - * structure is not of the correct size, otherwise it creates an enum that is - * never used. - */ -#define I40E_CHECK_STRUCT_LEN(n, X) enum i40e_static_assert_enum_##X \ - { i40e_static_assert_##X = (n)/((sizeof(struct X) == (n)) ? 1 : 0) } - -/* This macro is used extensively to ensure that command structures are 16 - * bytes in length as they have to map to the raw array of that size. - */ -#define I40E_CHECK_CMD_LENGTH(X) I40E_CHECK_STRUCT_LEN(16, X) - -/* internal (0x00XX) commands */ - -/* Get version (direct 0x0001) */ -struct i40e_aqc_get_version { - __le32 rom_ver; - __le32 fw_build; - __le16 fw_major; - __le16 fw_minor; - __le16 api_major; - __le16 api_minor; -}; - -I40E_CHECK_CMD_LENGTH(i40e_aqc_get_version); - -/* Send driver version (indirect 0x0002) */ -struct i40e_aqc_driver_version { - u8 driver_major_ver; - u8 driver_minor_ver; - u8 driver_build_ver; - u8 driver_subbuild_ver; - u8 reserved[4]; - __le32 address_high; - __le32 address_low; -}; - -I40E_CHECK_CMD_LENGTH(i40e_aqc_driver_version); - -/* Queue Shutdown (direct 0x0003) */ -struct i40e_aqc_queue_shutdown { - __le32 driver_unloading; -#define I40E_AQ_DRIVER_UNLOADING 0x1 - u8 reserved[12]; -}; - -I40E_CHECK_CMD_LENGTH(i40e_aqc_queue_shutdown); - -/* Set PF context (0x0004, direct) */ -struct i40e_aqc_set_pf_context { - u8 pf_id; - u8 reserved[15]; -}; - -I40E_CHECK_CMD_LENGTH(i40e_aqc_set_pf_context); - -/* Request resource ownership (direct 0x0008) - * Release resource ownership (direct 0x0009) - */ -#define I40E_AQ_RESOURCE_NVM 1 -#define I40E_AQ_RESOURCE_SDP 2 -#define I40E_AQ_RESOURCE_ACCESS_READ 1 -#define I40E_AQ_RESOURCE_ACCESS_WRITE 2 -#define I40E_AQ_RESOURCE_NVM_READ_TIMEOUT 3000 -#define I40E_AQ_RESOURCE_NVM_WRITE_TIMEOUT 180000 - -struct i40e_aqc_request_resource { - __le16 resource_id; - __le16 access_type; - __le32 timeout; - __le32 resource_number; - u8 reserved[4]; -}; - -I40E_CHECK_CMD_LENGTH(i40e_aqc_request_resource); - -/* Get function capabilities (indirect 0x000A) - * Get device capabilities (indirect 0x000B) - */ -struct i40e_aqc_list_capabilites { - u8 command_flags; -#define I40E_AQ_LIST_CAP_PF_INDEX_EN 1 - u8 pf_index; - u8 reserved[2]; - __le32 count; - __le32 addr_high; - __le32 addr_low; -}; - -I40E_CHECK_CMD_LENGTH(i40e_aqc_list_capabilites); - -struct i40e_aqc_list_capabilities_element_resp { - __le16 id; - u8 major_rev; - u8 minor_rev; - __le32 number; - __le32 logical_id; - __le32 phys_id; - u8 reserved[16]; -}; - -/* list of caps */ - -#define I40E_AQ_CAP_ID_SWITCH_MODE 0x0001 -#define I40E_AQ_CAP_ID_MNG_MODE 0x0002 -#define I40E_AQ_CAP_ID_NPAR_ACTIVE 0x0003 -#define I40E_AQ_CAP_ID_OS2BMC_CAP 0x0004 -#define I40E_AQ_CAP_ID_FUNCTIONS_VALID 0x0005 -#define I40E_AQ_CAP_ID_ALTERNATE_RAM 0x0006 -#define I40E_AQ_CAP_ID_WOL_AND_PROXY 0x0008 -#define I40E_AQ_CAP_ID_SRIOV 0x0012 -#define I40E_AQ_CAP_ID_VF 0x0013 -#define I40E_AQ_CAP_ID_VMDQ 0x0014 -#define I40E_AQ_CAP_ID_8021QBG 0x0015 -#define I40E_AQ_CAP_ID_8021QBR 0x0016 -#define I40E_AQ_CAP_ID_VSI 0x0017 -#define I40E_AQ_CAP_ID_DCB 0x0018 -#define I40E_AQ_CAP_ID_FCOE 0x0021 -#define I40E_AQ_CAP_ID_ISCSI 0x0022 -#define I40E_AQ_CAP_ID_RSS 0x0040 -#define I40E_AQ_CAP_ID_RXQ 0x0041 -#define I40E_AQ_CAP_ID_TXQ 0x0042 -#define I40E_AQ_CAP_ID_MSIX 0x0043 -#define I40E_AQ_CAP_ID_VF_MSIX 0x0044 -#define I40E_AQ_CAP_ID_FLOW_DIRECTOR 0x0045 -#define I40E_AQ_CAP_ID_1588 0x0046 -#define I40E_AQ_CAP_ID_IWARP 0x0051 -#define I40E_AQ_CAP_ID_LED 0x0061 -#define I40E_AQ_CAP_ID_SDP 0x0062 -#define I40E_AQ_CAP_ID_MDIO 0x0063 -#define I40E_AQ_CAP_ID_WSR_PROT 0x0064 -#define I40E_AQ_CAP_ID_NVM_MGMT 0x0080 -#define I40E_AQ_CAP_ID_FLEX10 0x00F1 -#define I40E_AQ_CAP_ID_CEM 0x00F2 - -/* Set CPPM Configuration (direct 0x0103) */ -struct i40e_aqc_cppm_configuration { - __le16 command_flags; -#define I40E_AQ_CPPM_EN_LTRC 0x0800 -#define I40E_AQ_CPPM_EN_DMCTH 0x1000 -#define I40E_AQ_CPPM_EN_DMCTLX 0x2000 -#define I40E_AQ_CPPM_EN_HPTC 0x4000 -#define I40E_AQ_CPPM_EN_DMARC 0x8000 - __le16 ttlx; - __le32 dmacr; - __le16 dmcth; - u8 hptc; - u8 reserved; - __le32 pfltrc; -}; - -I40E_CHECK_CMD_LENGTH(i40e_aqc_cppm_configuration); - -/* Set ARP Proxy command / response (indirect 0x0104) */ -struct i40e_aqc_arp_proxy_data { - __le16 command_flags; -#define I40E_AQ_ARP_INIT_IPV4 0x0800 -#define I40E_AQ_ARP_UNSUP_CTL 0x1000 -#define I40E_AQ_ARP_ENA 0x2000 -#define I40E_AQ_ARP_ADD_IPV4 0x4000 -#define I40E_AQ_ARP_DEL_IPV4 0x8000 - __le16 table_id; - __le32 enabled_offloads; -#define I40E_AQ_ARP_DIRECTED_OFFLOAD_ENABLE 0x00000020 -#define I40E_AQ_ARP_OFFLOAD_ENABLE 0x00000800 - __le32 ip_addr; - u8 mac_addr[6]; - u8 reserved[2]; -}; - -I40E_CHECK_STRUCT_LEN(0x14, i40e_aqc_arp_proxy_data); - -/* Set NS Proxy Table Entry Command (indirect 0x0105) */ -struct i40e_aqc_ns_proxy_data { - __le16 table_idx_mac_addr_0; - __le16 table_idx_mac_addr_1; - __le16 table_idx_ipv6_0; - __le16 table_idx_ipv6_1; - __le16 control; -#define I40E_AQ_NS_PROXY_ADD_0 0x0001 -#define I40E_AQ_NS_PROXY_DEL_0 0x0002 -#define I40E_AQ_NS_PROXY_ADD_1 0x0004 -#define I40E_AQ_NS_PROXY_DEL_1 0x0008 -#define I40E_AQ_NS_PROXY_ADD_IPV6_0 0x0010 -#define I40E_AQ_NS_PROXY_DEL_IPV6_0 0x0020 -#define I40E_AQ_NS_PROXY_ADD_IPV6_1 0x0040 -#define I40E_AQ_NS_PROXY_DEL_IPV6_1 0x0080 -#define I40E_AQ_NS_PROXY_COMMAND_SEQ 0x0100 -#define I40E_AQ_NS_PROXY_INIT_IPV6_TBL 0x0200 -#define I40E_AQ_NS_PROXY_INIT_MAC_TBL 0x0400 -#define I40E_AQ_NS_PROXY_OFFLOAD_ENABLE 0x0800 -#define I40E_AQ_NS_PROXY_DIRECTED_OFFLOAD_ENABLE 0x1000 - u8 mac_addr_0[6]; - u8 mac_addr_1[6]; - u8 local_mac_addr[6]; - u8 ipv6_addr_0[16]; /* Warning! spec specifies BE byte order */ - u8 ipv6_addr_1[16]; -}; - -I40E_CHECK_STRUCT_LEN(0x3c, i40e_aqc_ns_proxy_data); - -/* Manage LAA Command (0x0106) - obsolete */ -struct i40e_aqc_mng_laa { - __le16 command_flags; -#define I40E_AQ_LAA_FLAG_WR 0x8000 - u8 reserved[2]; - __le32 sal; - __le16 sah; - u8 reserved2[6]; -}; - -I40E_CHECK_CMD_LENGTH(i40e_aqc_mng_laa); - -/* Manage MAC Address Read Command (indirect 0x0107) */ -struct i40e_aqc_mac_address_read { - __le16 command_flags; -#define I40E_AQC_LAN_ADDR_VALID 0x10 -#define I40E_AQC_SAN_ADDR_VALID 0x20 -#define I40E_AQC_PORT_ADDR_VALID 0x40 -#define I40E_AQC_WOL_ADDR_VALID 0x80 -#define I40E_AQC_MC_MAG_EN_VALID 0x100 -#define I40E_AQC_ADDR_VALID_MASK 0x3F0 - u8 reserved[6]; - __le32 addr_high; - __le32 addr_low; -}; - -I40E_CHECK_CMD_LENGTH(i40e_aqc_mac_address_read); - -struct i40e_aqc_mac_address_read_data { - u8 pf_lan_mac[6]; - u8 pf_san_mac[6]; - u8 port_mac[6]; - u8 pf_wol_mac[6]; -}; - -I40E_CHECK_STRUCT_LEN(24, i40e_aqc_mac_address_read_data); - -/* Manage MAC Address Write Command (0x0108) */ -struct i40e_aqc_mac_address_write { - __le16 command_flags; -#define I40E_AQC_WRITE_TYPE_LAA_ONLY 0x0000 -#define I40E_AQC_WRITE_TYPE_LAA_WOL 0x4000 -#define I40E_AQC_WRITE_TYPE_PORT 0x8000 -#define I40E_AQC_WRITE_TYPE_UPDATE_MC_MAG 0xC000 -#define I40E_AQC_WRITE_TYPE_MASK 0xC000 - - __le16 mac_sah; - __le32 mac_sal; - u8 reserved[8]; -}; - -I40E_CHECK_CMD_LENGTH(i40e_aqc_mac_address_write); - -/* PXE commands (0x011x) */ - -/* Clear PXE Command and response (direct 0x0110) */ -struct i40e_aqc_clear_pxe { - u8 rx_cnt; - u8 reserved[15]; -}; - -I40E_CHECK_CMD_LENGTH(i40e_aqc_clear_pxe); - -/* Set WoL Filter (0x0120) */ - -struct i40e_aqc_set_wol_filter { - __le16 filter_index; -#define I40E_AQC_MAX_NUM_WOL_FILTERS 8 -#define I40E_AQC_SET_WOL_FILTER_TYPE_MAGIC_SHIFT 15 -#define I40E_AQC_SET_WOL_FILTER_TYPE_MAGIC_MASK (0x1 << \ - I40E_AQC_SET_WOL_FILTER_TYPE_MAGIC_SHIFT) - -#define I40E_AQC_SET_WOL_FILTER_INDEX_SHIFT 0 -#define I40E_AQC_SET_WOL_FILTER_INDEX_MASK (0x7 << \ - I40E_AQC_SET_WOL_FILTER_INDEX_SHIFT) - __le16 cmd_flags; -#define I40E_AQC_SET_WOL_FILTER 0x8000 -#define I40E_AQC_SET_WOL_FILTER_NO_TCO_WOL 0x4000 -#define I40E_AQC_SET_WOL_FILTER_WOL_PRESERVE_ON_PFR 0x2000 -#define I40E_AQC_SET_WOL_FILTER_ACTION_CLEAR 0 -#define I40E_AQC_SET_WOL_FILTER_ACTION_SET 1 - __le16 valid_flags; -#define I40E_AQC_SET_WOL_FILTER_ACTION_VALID 0x8000 -#define I40E_AQC_SET_WOL_FILTER_NO_TCO_ACTION_VALID 0x4000 - u8 reserved[2]; - __le32 address_high; - __le32 address_low; -}; - -I40E_CHECK_CMD_LENGTH(i40e_aqc_set_wol_filter); - -struct i40e_aqc_set_wol_filter_data { - u8 filter[128]; - u8 mask[16]; -}; - -I40E_CHECK_STRUCT_LEN(0x90, i40e_aqc_set_wol_filter_data); - -/* Get Wake Reason (0x0121) */ - -struct i40e_aqc_get_wake_reason_completion { - u8 reserved_1[2]; - __le16 wake_reason; -#define I40E_AQC_GET_WAKE_UP_REASON_WOL_REASON_MATCHED_INDEX_SHIFT 0 -#define I40E_AQC_GET_WAKE_UP_REASON_WOL_REASON_MATCHED_INDEX_MASK (0xFF << \ - I40E_AQC_GET_WAKE_UP_REASON_WOL_REASON_MATCHED_INDEX_SHIFT) -#define I40E_AQC_GET_WAKE_UP_REASON_WOL_REASON_RESERVED_SHIFT 8 -#define I40E_AQC_GET_WAKE_UP_REASON_WOL_REASON_RESERVED_MASK (0xFF << \ - I40E_AQC_GET_WAKE_UP_REASON_WOL_REASON_RESERVED_SHIFT) - u8 reserved_2[12]; -}; - -I40E_CHECK_CMD_LENGTH(i40e_aqc_get_wake_reason_completion); - -/* Switch configuration commands (0x02xx) */ - -/* Used by many indirect commands that only pass an seid and a buffer in the - * command - */ -struct i40e_aqc_switch_seid { - __le16 seid; - u8 reserved[6]; - __le32 addr_high; - __le32 addr_low; -}; - -I40E_CHECK_CMD_LENGTH(i40e_aqc_switch_seid); - -/* Get Switch Configuration command (indirect 0x0200) - * uses i40e_aqc_switch_seid for the descriptor - */ -struct i40e_aqc_get_switch_config_header_resp { - __le16 num_reported; - __le16 num_total; - u8 reserved[12]; -}; - -I40E_CHECK_CMD_LENGTH(i40e_aqc_get_switch_config_header_resp); - -struct i40e_aqc_switch_config_element_resp { - u8 element_type; -#define I40E_AQ_SW_ELEM_TYPE_MAC 1 -#define I40E_AQ_SW_ELEM_TYPE_PF 2 -#define I40E_AQ_SW_ELEM_TYPE_VF 3 -#define I40E_AQ_SW_ELEM_TYPE_EMP 4 -#define I40E_AQ_SW_ELEM_TYPE_BMC 5 -#define I40E_AQ_SW_ELEM_TYPE_PV 16 -#define I40E_AQ_SW_ELEM_TYPE_VEB 17 -#define I40E_AQ_SW_ELEM_TYPE_PA 18 -#define I40E_AQ_SW_ELEM_TYPE_VSI 19 - u8 revision; -#define I40E_AQ_SW_ELEM_REV_1 1 - __le16 seid; - __le16 uplink_seid; - __le16 downlink_seid; - u8 reserved[3]; - u8 connection_type; -#define I40E_AQ_CONN_TYPE_REGULAR 0x1 -#define I40E_AQ_CONN_TYPE_DEFAULT 0x2 -#define I40E_AQ_CONN_TYPE_CASCADED 0x3 - __le16 scheduler_id; - __le16 element_info; -}; - -I40E_CHECK_STRUCT_LEN(0x10, i40e_aqc_switch_config_element_resp); - -/* Get Switch Configuration (indirect 0x0200) - * an array of elements are returned in the response buffer - * the first in the array is the header, remainder are elements - */ -struct i40e_aqc_get_switch_config_resp { - struct i40e_aqc_get_switch_config_header_resp header; - struct i40e_aqc_switch_config_element_resp element[1]; -}; - -I40E_CHECK_STRUCT_LEN(0x20, i40e_aqc_get_switch_config_resp); - -/* Add Statistics (direct 0x0201) - * Remove Statistics (direct 0x0202) - */ -struct i40e_aqc_add_remove_statistics { - __le16 seid; - __le16 vlan; - __le16 stat_index; - u8 reserved[10]; -}; - -I40E_CHECK_CMD_LENGTH(i40e_aqc_add_remove_statistics); - -/* Set Port Parameters command (direct 0x0203) */ -struct i40e_aqc_set_port_parameters { - __le16 command_flags; -#define I40E_AQ_SET_P_PARAMS_SAVE_BAD_PACKETS 1 -#define I40E_AQ_SET_P_PARAMS_PAD_SHORT_PACKETS 2 /* must set! */ -#define I40E_AQ_SET_P_PARAMS_DOUBLE_VLAN_ENA 4 - __le16 bad_frame_vsi; -#define I40E_AQ_SET_P_PARAMS_BFRAME_SEID_SHIFT 0x0 -#define I40E_AQ_SET_P_PARAMS_BFRAME_SEID_MASK 0x3FF - __le16 default_seid; /* reserved for command */ - u8 reserved[10]; -}; - -I40E_CHECK_CMD_LENGTH(i40e_aqc_set_port_parameters); - -/* Get Switch Resource Allocation (indirect 0x0204) */ -struct i40e_aqc_get_switch_resource_alloc { - u8 num_entries; /* reserved for command */ - u8 reserved[7]; - __le32 addr_high; - __le32 addr_low; -}; - -I40E_CHECK_CMD_LENGTH(i40e_aqc_get_switch_resource_alloc); - -/* expect an array of these structs in the response buffer */ -struct i40e_aqc_switch_resource_alloc_element_resp { - u8 resource_type; -#define I40E_AQ_RESOURCE_TYPE_VEB 0x0 -#define I40E_AQ_RESOURCE_TYPE_VSI 0x1 -#define I40E_AQ_RESOURCE_TYPE_MACADDR 0x2 -#define I40E_AQ_RESOURCE_TYPE_STAG 0x3 -#define I40E_AQ_RESOURCE_TYPE_ETAG 0x4 -#define I40E_AQ_RESOURCE_TYPE_MULTICAST_HASH 0x5 -#define I40E_AQ_RESOURCE_TYPE_UNICAST_HASH 0x6 -#define I40E_AQ_RESOURCE_TYPE_VLAN 0x7 -#define I40E_AQ_RESOURCE_TYPE_VSI_LIST_ENTRY 0x8 -#define I40E_AQ_RESOURCE_TYPE_ETAG_LIST_ENTRY 0x9 -#define I40E_AQ_RESOURCE_TYPE_VLAN_STAT_POOL 0xA -#define I40E_AQ_RESOURCE_TYPE_MIRROR_RULE 0xB -#define I40E_AQ_RESOURCE_TYPE_QUEUE_SETS 0xC -#define I40E_AQ_RESOURCE_TYPE_VLAN_FILTERS 0xD -#define I40E_AQ_RESOURCE_TYPE_INNER_MAC_FILTERS 0xF -#define I40E_AQ_RESOURCE_TYPE_IP_FILTERS 0x10 -#define I40E_AQ_RESOURCE_TYPE_GRE_VN_KEYS 0x11 -#define I40E_AQ_RESOURCE_TYPE_VN2_KEYS 0x12 -#define I40E_AQ_RESOURCE_TYPE_TUNNEL_PORTS 0x13 - u8 reserved1; - __le16 guaranteed; - __le16 total; - __le16 used; - __le16 total_unalloced; - u8 reserved2[6]; -}; - -I40E_CHECK_STRUCT_LEN(0x10, i40e_aqc_switch_resource_alloc_element_resp); - -/* Set Switch Configuration (direct 0x0205) */ -struct i40e_aqc_set_switch_config { - __le16 flags; -/* flags used for both fields below */ -#define I40E_AQ_SET_SWITCH_CFG_PROMISC 0x0001 -#define I40E_AQ_SET_SWITCH_CFG_L2_FILTER 0x0002 - __le16 valid_flags; - /* The ethertype in switch_tag is dropped on ingress and used - * internally by the switch. Set this to zero for the default - * of 0x88a8 (802.1ad). Should be zero for firmware API - * versions lower than 1.7. - */ - __le16 switch_tag; - /* The ethertypes in first_tag and second_tag are used to - * match the outer and inner VLAN tags (respectively) when HW - * double VLAN tagging is enabled via the set port parameters - * AQ command. Otherwise these are both ignored. Set them to - * zero for their defaults of 0x8100 (802.1Q). Should be zero - * for firmware API versions lower than 1.7. - */ - __le16 first_tag; - __le16 second_tag; - u8 reserved[6]; -}; - -I40E_CHECK_CMD_LENGTH(i40e_aqc_set_switch_config); - -/* Read Receive control registers (direct 0x0206) - * Write Receive control registers (direct 0x0207) - * used for accessing Rx control registers that can be - * slow and need special handling when under high Rx load - */ -struct i40e_aqc_rx_ctl_reg_read_write { - __le32 reserved1; - __le32 address; - __le32 reserved2; - __le32 value; -}; - -I40E_CHECK_CMD_LENGTH(i40e_aqc_rx_ctl_reg_read_write); - -/* Add VSI (indirect 0x0210) - * this indirect command uses struct i40e_aqc_vsi_properties_data - * as the indirect buffer (128 bytes) - * - * Update VSI (indirect 0x211) - * uses the same data structure as Add VSI - * - * Get VSI (indirect 0x0212) - * uses the same completion and data structure as Add VSI - */ -struct i40e_aqc_add_get_update_vsi { - __le16 uplink_seid; - u8 connection_type; -#define I40E_AQ_VSI_CONN_TYPE_NORMAL 0x1 -#define I40E_AQ_VSI_CONN_TYPE_DEFAULT 0x2 -#define I40E_AQ_VSI_CONN_TYPE_CASCADED 0x3 - u8 reserved1; - u8 vf_id; - u8 reserved2; - __le16 vsi_flags; -#define I40E_AQ_VSI_TYPE_SHIFT 0x0 -#define I40E_AQ_VSI_TYPE_MASK (0x3 << I40E_AQ_VSI_TYPE_SHIFT) -#define I40E_AQ_VSI_TYPE_VF 0x0 -#define I40E_AQ_VSI_TYPE_VMDQ2 0x1 -#define I40E_AQ_VSI_TYPE_PF 0x2 -#define I40E_AQ_VSI_TYPE_EMP_MNG 0x3 -#define I40E_AQ_VSI_FLAG_CASCADED_PV 0x4 - __le32 addr_high; - __le32 addr_low; -}; - -I40E_CHECK_CMD_LENGTH(i40e_aqc_add_get_update_vsi); - -struct i40e_aqc_add_get_update_vsi_completion { - __le16 seid; - __le16 vsi_number; - __le16 vsi_used; - __le16 vsi_free; - __le32 addr_high; - __le32 addr_low; -}; - -I40E_CHECK_CMD_LENGTH(i40e_aqc_add_get_update_vsi_completion); - -struct i40e_aqc_vsi_properties_data { - /* first 96 byte are written by SW */ - __le16 valid_sections; -#define I40E_AQ_VSI_PROP_SWITCH_VALID 0x0001 -#define I40E_AQ_VSI_PROP_SECURITY_VALID 0x0002 -#define I40E_AQ_VSI_PROP_VLAN_VALID 0x0004 -#define I40E_AQ_VSI_PROP_CAS_PV_VALID 0x0008 -#define I40E_AQ_VSI_PROP_INGRESS_UP_VALID 0x0010 -#define I40E_AQ_VSI_PROP_EGRESS_UP_VALID 0x0020 -#define I40E_AQ_VSI_PROP_QUEUE_MAP_VALID 0x0040 -#define I40E_AQ_VSI_PROP_QUEUE_OPT_VALID 0x0080 -#define I40E_AQ_VSI_PROP_OUTER_UP_VALID 0x0100 -#define I40E_AQ_VSI_PROP_SCHED_VALID 0x0200 - /* switch section */ - __le16 switch_id; /* 12bit id combined with flags below */ -#define I40E_AQ_VSI_SW_ID_SHIFT 0x0000 -#define I40E_AQ_VSI_SW_ID_MASK (0xFFF << I40E_AQ_VSI_SW_ID_SHIFT) -#define I40E_AQ_VSI_SW_ID_FLAG_NOT_STAG 0x1000 -#define I40E_AQ_VSI_SW_ID_FLAG_ALLOW_LB 0x2000 -#define I40E_AQ_VSI_SW_ID_FLAG_LOCAL_LB 0x4000 - u8 sw_reserved[2]; - /* security section */ - u8 sec_flags; -#define I40E_AQ_VSI_SEC_FLAG_ALLOW_DEST_OVRD 0x01 -#define I40E_AQ_VSI_SEC_FLAG_ENABLE_VLAN_CHK 0x02 -#define I40E_AQ_VSI_SEC_FLAG_ENABLE_MAC_CHK 0x04 - u8 sec_reserved; - /* VLAN section */ - __le16 pvid; /* VLANS include priority bits */ - __le16 fcoe_pvid; - u8 port_vlan_flags; -#define I40E_AQ_VSI_PVLAN_MODE_SHIFT 0x00 -#define I40E_AQ_VSI_PVLAN_MODE_MASK (0x03 << \ - I40E_AQ_VSI_PVLAN_MODE_SHIFT) -#define I40E_AQ_VSI_PVLAN_MODE_TAGGED 0x01 -#define I40E_AQ_VSI_PVLAN_MODE_UNTAGGED 0x02 -#define I40E_AQ_VSI_PVLAN_MODE_ALL 0x03 -#define I40E_AQ_VSI_PVLAN_INSERT_PVID 0x04 -#define I40E_AQ_VSI_PVLAN_EMOD_SHIFT 0x03 -#define I40E_AQ_VSI_PVLAN_EMOD_MASK (0x3 << \ - I40E_AQ_VSI_PVLAN_EMOD_SHIFT) -#define I40E_AQ_VSI_PVLAN_EMOD_STR_BOTH 0x0 -#define I40E_AQ_VSI_PVLAN_EMOD_STR_UP 0x08 -#define I40E_AQ_VSI_PVLAN_EMOD_STR 0x10 -#define I40E_AQ_VSI_PVLAN_EMOD_NOTHING 0x18 - u8 pvlan_reserved[3]; - /* ingress egress up sections */ - __le32 ingress_table; /* bitmap, 3 bits per up */ -#define I40E_AQ_VSI_UP_TABLE_UP0_SHIFT 0 -#define I40E_AQ_VSI_UP_TABLE_UP0_MASK (0x7 << \ - I40E_AQ_VSI_UP_TABLE_UP0_SHIFT) -#define I40E_AQ_VSI_UP_TABLE_UP1_SHIFT 3 -#define I40E_AQ_VSI_UP_TABLE_UP1_MASK (0x7 << \ - I40E_AQ_VSI_UP_TABLE_UP1_SHIFT) -#define I40E_AQ_VSI_UP_TABLE_UP2_SHIFT 6 -#define I40E_AQ_VSI_UP_TABLE_UP2_MASK (0x7 << \ - I40E_AQ_VSI_UP_TABLE_UP2_SHIFT) -#define I40E_AQ_VSI_UP_TABLE_UP3_SHIFT 9 -#define I40E_AQ_VSI_UP_TABLE_UP3_MASK (0x7 << \ - I40E_AQ_VSI_UP_TABLE_UP3_SHIFT) -#define I40E_AQ_VSI_UP_TABLE_UP4_SHIFT 12 -#define I40E_AQ_VSI_UP_TABLE_UP4_MASK (0x7 << \ - I40E_AQ_VSI_UP_TABLE_UP4_SHIFT) -#define I40E_AQ_VSI_UP_TABLE_UP5_SHIFT 15 -#define I40E_AQ_VSI_UP_TABLE_UP5_MASK (0x7 << \ - I40E_AQ_VSI_UP_TABLE_UP5_SHIFT) -#define I40E_AQ_VSI_UP_TABLE_UP6_SHIFT 18 -#define I40E_AQ_VSI_UP_TABLE_UP6_MASK (0x7 << \ - I40E_AQ_VSI_UP_TABLE_UP6_SHIFT) -#define I40E_AQ_VSI_UP_TABLE_UP7_SHIFT 21 -#define I40E_AQ_VSI_UP_TABLE_UP7_MASK (0x7 << \ - I40E_AQ_VSI_UP_TABLE_UP7_SHIFT) - __le32 egress_table; /* same defines as for ingress table */ - /* cascaded PV section */ - __le16 cas_pv_tag; - u8 cas_pv_flags; -#define I40E_AQ_VSI_CAS_PV_TAGX_SHIFT 0x00 -#define I40E_AQ_VSI_CAS_PV_TAGX_MASK (0x03 << \ - I40E_AQ_VSI_CAS_PV_TAGX_SHIFT) -#define I40E_AQ_VSI_CAS_PV_TAGX_LEAVE 0x00 -#define I40E_AQ_VSI_CAS_PV_TAGX_REMOVE 0x01 -#define I40E_AQ_VSI_CAS_PV_TAGX_COPY 0x02 -#define I40E_AQ_VSI_CAS_PV_INSERT_TAG 0x10 -#define I40E_AQ_VSI_CAS_PV_ETAG_PRUNE 0x20 -#define I40E_AQ_VSI_CAS_PV_ACCEPT_HOST_TAG 0x40 - u8 cas_pv_reserved; - /* queue mapping section */ - __le16 mapping_flags; -#define I40E_AQ_VSI_QUE_MAP_CONTIG 0x0 -#define I40E_AQ_VSI_QUE_MAP_NONCONTIG 0x1 - __le16 queue_mapping[16]; -#define I40E_AQ_VSI_QUEUE_SHIFT 0x0 -#define I40E_AQ_VSI_QUEUE_MASK (0x7FF << I40E_AQ_VSI_QUEUE_SHIFT) - __le16 tc_mapping[8]; -#define I40E_AQ_VSI_TC_QUE_OFFSET_SHIFT 0 -#define I40E_AQ_VSI_TC_QUE_OFFSET_MASK (0x1FF << \ - I40E_AQ_VSI_TC_QUE_OFFSET_SHIFT) -#define I40E_AQ_VSI_TC_QUE_NUMBER_SHIFT 9 -#define I40E_AQ_VSI_TC_QUE_NUMBER_MASK (0x7 << \ - I40E_AQ_VSI_TC_QUE_NUMBER_SHIFT) - /* queueing option section */ - u8 queueing_opt_flags; -#define I40E_AQ_VSI_QUE_OPT_MULTICAST_UDP_ENA 0x04 -#define I40E_AQ_VSI_QUE_OPT_UNICAST_UDP_ENA 0x08 -#define I40E_AQ_VSI_QUE_OPT_TCP_ENA 0x10 -#define I40E_AQ_VSI_QUE_OPT_FCOE_ENA 0x20 -#define I40E_AQ_VSI_QUE_OPT_RSS_LUT_PF 0x00 -#define I40E_AQ_VSI_QUE_OPT_RSS_LUT_VSI 0x40 - u8 queueing_opt_reserved[3]; - /* scheduler section */ - u8 up_enable_bits; - u8 sched_reserved; - /* outer up section */ - __le32 outer_up_table; /* same structure and defines as ingress tbl */ - u8 cmd_reserved[8]; - /* last 32 bytes are written by FW */ - __le16 qs_handle[8]; -#define I40E_AQ_VSI_QS_HANDLE_INVALID 0xFFFF - __le16 stat_counter_idx; - __le16 sched_id; - u8 resp_reserved[12]; -}; - -I40E_CHECK_STRUCT_LEN(128, i40e_aqc_vsi_properties_data); - -/* Add Port Virtualizer (direct 0x0220) - * also used for update PV (direct 0x0221) but only flags are used - * (IS_CTRL_PORT only works on add PV) - */ -struct i40e_aqc_add_update_pv { - __le16 command_flags; -#define I40E_AQC_PV_FLAG_PV_TYPE 0x1 -#define I40E_AQC_PV_FLAG_FWD_UNKNOWN_STAG_EN 0x2 -#define I40E_AQC_PV_FLAG_FWD_UNKNOWN_ETAG_EN 0x4 -#define I40E_AQC_PV_FLAG_IS_CTRL_PORT 0x8 - __le16 uplink_seid; - __le16 connected_seid; - u8 reserved[10]; -}; - -I40E_CHECK_CMD_LENGTH(i40e_aqc_add_update_pv); - -struct i40e_aqc_add_update_pv_completion { - /* reserved for update; for add also encodes error if rc == ENOSPC */ - __le16 pv_seid; -#define I40E_AQC_PV_ERR_FLAG_NO_PV 0x1 -#define I40E_AQC_PV_ERR_FLAG_NO_SCHED 0x2 -#define I40E_AQC_PV_ERR_FLAG_NO_COUNTER 0x4 -#define I40E_AQC_PV_ERR_FLAG_NO_ENTRY 0x8 - u8 reserved[14]; -}; - -I40E_CHECK_CMD_LENGTH(i40e_aqc_add_update_pv_completion); - -/* Get PV Params (direct 0x0222) - * uses i40e_aqc_switch_seid for the descriptor - */ - -struct i40e_aqc_get_pv_params_completion { - __le16 seid; - __le16 default_stag; - __le16 pv_flags; /* same flags as add_pv */ -#define I40E_AQC_GET_PV_PV_TYPE 0x1 -#define I40E_AQC_GET_PV_FRWD_UNKNOWN_STAG 0x2 -#define I40E_AQC_GET_PV_FRWD_UNKNOWN_ETAG 0x4 - u8 reserved[8]; - __le16 default_port_seid; -}; - -I40E_CHECK_CMD_LENGTH(i40e_aqc_get_pv_params_completion); - -/* Add VEB (direct 0x0230) */ -struct i40e_aqc_add_veb { - __le16 uplink_seid; - __le16 downlink_seid; - __le16 veb_flags; -#define I40E_AQC_ADD_VEB_FLOATING 0x1 -#define I40E_AQC_ADD_VEB_PORT_TYPE_SHIFT 1 -#define I40E_AQC_ADD_VEB_PORT_TYPE_MASK (0x3 << \ - I40E_AQC_ADD_VEB_PORT_TYPE_SHIFT) -#define I40E_AQC_ADD_VEB_PORT_TYPE_DEFAULT 0x2 -#define I40E_AQC_ADD_VEB_PORT_TYPE_DATA 0x4 -#define I40E_AQC_ADD_VEB_ENABLE_L2_FILTER 0x8 /* deprecated */ -#define I40E_AQC_ADD_VEB_ENABLE_DISABLE_STATS 0x10 - u8 enable_tcs; - u8 reserved[9]; -}; - -I40E_CHECK_CMD_LENGTH(i40e_aqc_add_veb); - -struct i40e_aqc_add_veb_completion { - u8 reserved[6]; - __le16 switch_seid; - /* also encodes error if rc == ENOSPC; codes are the same as add_pv */ - __le16 veb_seid; -#define I40E_AQC_VEB_ERR_FLAG_NO_VEB 0x1 -#define I40E_AQC_VEB_ERR_FLAG_NO_SCHED 0x2 -#define I40E_AQC_VEB_ERR_FLAG_NO_COUNTER 0x4 -#define I40E_AQC_VEB_ERR_FLAG_NO_ENTRY 0x8 - __le16 statistic_index; - __le16 vebs_used; - __le16 vebs_free; -}; - -I40E_CHECK_CMD_LENGTH(i40e_aqc_add_veb_completion); - -/* Get VEB Parameters (direct 0x0232) - * uses i40e_aqc_switch_seid for the descriptor - */ -struct i40e_aqc_get_veb_parameters_completion { - __le16 seid; - __le16 switch_id; - __le16 veb_flags; /* only the first/last flags from 0x0230 is valid */ - __le16 statistic_index; - __le16 vebs_used; - __le16 vebs_free; - u8 reserved[4]; -}; - -I40E_CHECK_CMD_LENGTH(i40e_aqc_get_veb_parameters_completion); - -/* Delete Element (direct 0x0243) - * uses the generic i40e_aqc_switch_seid - */ - -/* Add MAC-VLAN (indirect 0x0250) */ - -/* used for the command for most vlan commands */ -struct i40e_aqc_macvlan { - __le16 num_addresses; - __le16 seid[3]; -#define I40E_AQC_MACVLAN_CMD_SEID_NUM_SHIFT 0 -#define I40E_AQC_MACVLAN_CMD_SEID_NUM_MASK (0x3FF << \ - I40E_AQC_MACVLAN_CMD_SEID_NUM_SHIFT) -#define I40E_AQC_MACVLAN_CMD_SEID_VALID 0x8000 - __le32 addr_high; - __le32 addr_low; -}; - -I40E_CHECK_CMD_LENGTH(i40e_aqc_macvlan); - -/* indirect data for command and response */ -struct i40e_aqc_add_macvlan_element_data { - u8 mac_addr[6]; - __le16 vlan_tag; - __le16 flags; -#define I40E_AQC_MACVLAN_ADD_PERFECT_MATCH 0x0001 -#define I40E_AQC_MACVLAN_ADD_HASH_MATCH 0x0002 -#define I40E_AQC_MACVLAN_ADD_IGNORE_VLAN 0x0004 -#define I40E_AQC_MACVLAN_ADD_TO_QUEUE 0x0008 -#define I40E_AQC_MACVLAN_ADD_USE_SHARED_MAC 0x0010 - __le16 queue_number; -#define I40E_AQC_MACVLAN_CMD_QUEUE_SHIFT 0 -#define I40E_AQC_MACVLAN_CMD_QUEUE_MASK (0x7FF << \ - I40E_AQC_MACVLAN_CMD_SEID_NUM_SHIFT) - /* response section */ - u8 match_method; -#define I40E_AQC_MM_PERFECT_MATCH 0x01 -#define I40E_AQC_MM_HASH_MATCH 0x02 -#define I40E_AQC_MM_ERR_NO_RES 0xFF - u8 reserved1[3]; -}; - -struct i40e_aqc_add_remove_macvlan_completion { - __le16 perfect_mac_used; - __le16 perfect_mac_free; - __le16 unicast_hash_free; - __le16 multicast_hash_free; - __le32 addr_high; - __le32 addr_low; -}; - -I40E_CHECK_CMD_LENGTH(i40e_aqc_add_remove_macvlan_completion); - -/* Remove MAC-VLAN (indirect 0x0251) - * uses i40e_aqc_macvlan for the descriptor - * data points to an array of num_addresses of elements - */ - -struct i40e_aqc_remove_macvlan_element_data { - u8 mac_addr[6]; - __le16 vlan_tag; - u8 flags; -#define I40E_AQC_MACVLAN_DEL_PERFECT_MATCH 0x01 -#define I40E_AQC_MACVLAN_DEL_HASH_MATCH 0x02 -#define I40E_AQC_MACVLAN_DEL_IGNORE_VLAN 0x08 -#define I40E_AQC_MACVLAN_DEL_ALL_VSIS 0x10 - u8 reserved[3]; - /* reply section */ - u8 error_code; -#define I40E_AQC_REMOVE_MACVLAN_SUCCESS 0x0 -#define I40E_AQC_REMOVE_MACVLAN_FAIL 0xFF - u8 reply_reserved[3]; -}; - -/* Add VLAN (indirect 0x0252) - * Remove VLAN (indirect 0x0253) - * use the generic i40e_aqc_macvlan for the command - */ -struct i40e_aqc_add_remove_vlan_element_data { - __le16 vlan_tag; - u8 vlan_flags; -/* flags for add VLAN */ -#define I40E_AQC_ADD_VLAN_LOCAL 0x1 -#define I40E_AQC_ADD_PVLAN_TYPE_SHIFT 1 -#define I40E_AQC_ADD_PVLAN_TYPE_MASK (0x3 << I40E_AQC_ADD_PVLAN_TYPE_SHIFT) -#define I40E_AQC_ADD_PVLAN_TYPE_REGULAR 0x0 -#define I40E_AQC_ADD_PVLAN_TYPE_PRIMARY 0x2 -#define I40E_AQC_ADD_PVLAN_TYPE_SECONDARY 0x4 -#define I40E_AQC_VLAN_PTYPE_SHIFT 3 -#define I40E_AQC_VLAN_PTYPE_MASK (0x3 << I40E_AQC_VLAN_PTYPE_SHIFT) -#define I40E_AQC_VLAN_PTYPE_REGULAR_VSI 0x0 -#define I40E_AQC_VLAN_PTYPE_PROMISC_VSI 0x8 -#define I40E_AQC_VLAN_PTYPE_COMMUNITY_VSI 0x10 -#define I40E_AQC_VLAN_PTYPE_ISOLATED_VSI 0x18 -/* flags for remove VLAN */ -#define I40E_AQC_REMOVE_VLAN_ALL 0x1 - u8 reserved; - u8 result; -/* flags for add VLAN */ -#define I40E_AQC_ADD_VLAN_SUCCESS 0x0 -#define I40E_AQC_ADD_VLAN_FAIL_REQUEST 0xFE -#define I40E_AQC_ADD_VLAN_FAIL_RESOURCE 0xFF -/* flags for remove VLAN */ -#define I40E_AQC_REMOVE_VLAN_SUCCESS 0x0 -#define I40E_AQC_REMOVE_VLAN_FAIL 0xFF - u8 reserved1[3]; -}; - -struct i40e_aqc_add_remove_vlan_completion { - u8 reserved[4]; - __le16 vlans_used; - __le16 vlans_free; - __le32 addr_high; - __le32 addr_low; -}; - -/* Set VSI Promiscuous Modes (direct 0x0254) */ -struct i40e_aqc_set_vsi_promiscuous_modes { - __le16 promiscuous_flags; - __le16 valid_flags; -/* flags used for both fields above */ -#define I40E_AQC_SET_VSI_PROMISC_UNICAST 0x01 -#define I40E_AQC_SET_VSI_PROMISC_MULTICAST 0x02 -#define I40E_AQC_SET_VSI_PROMISC_BROADCAST 0x04 -#define I40E_AQC_SET_VSI_DEFAULT 0x08 -#define I40E_AQC_SET_VSI_PROMISC_VLAN 0x10 -#define I40E_AQC_SET_VSI_PROMISC_TX 0x8000 - __le16 seid; -#define I40E_AQC_VSI_PROM_CMD_SEID_MASK 0x3FF - __le16 vlan_tag; -#define I40E_AQC_SET_VSI_VLAN_MASK 0x0FFF -#define I40E_AQC_SET_VSI_VLAN_VALID 0x8000 - u8 reserved[8]; -}; - -I40E_CHECK_CMD_LENGTH(i40e_aqc_set_vsi_promiscuous_modes); - -/* Add S/E-tag command (direct 0x0255) - * Uses generic i40e_aqc_add_remove_tag_completion for completion - */ -struct i40e_aqc_add_tag { - __le16 flags; -#define I40E_AQC_ADD_TAG_FLAG_TO_QUEUE 0x0001 - __le16 seid; -#define I40E_AQC_ADD_TAG_CMD_SEID_NUM_SHIFT 0 -#define I40E_AQC_ADD_TAG_CMD_SEID_NUM_MASK (0x3FF << \ - I40E_AQC_ADD_TAG_CMD_SEID_NUM_SHIFT) - __le16 tag; - __le16 queue_number; - u8 reserved[8]; -}; - -I40E_CHECK_CMD_LENGTH(i40e_aqc_add_tag); - -struct i40e_aqc_add_remove_tag_completion { - u8 reserved[12]; - __le16 tags_used; - __le16 tags_free; -}; - -I40E_CHECK_CMD_LENGTH(i40e_aqc_add_remove_tag_completion); - -/* Remove S/E-tag command (direct 0x0256) - * Uses generic i40e_aqc_add_remove_tag_completion for completion - */ -struct i40e_aqc_remove_tag { - __le16 seid; -#define I40E_AQC_REMOVE_TAG_CMD_SEID_NUM_SHIFT 0 -#define I40E_AQC_REMOVE_TAG_CMD_SEID_NUM_MASK (0x3FF << \ - I40E_AQC_REMOVE_TAG_CMD_SEID_NUM_SHIFT) - __le16 tag; - u8 reserved[12]; -}; - -I40E_CHECK_CMD_LENGTH(i40e_aqc_remove_tag); - -/* Add multicast E-Tag (direct 0x0257) - * del multicast E-Tag (direct 0x0258) only uses pv_seid and etag fields - * and no external data - */ -struct i40e_aqc_add_remove_mcast_etag { - __le16 pv_seid; - __le16 etag; - u8 num_unicast_etags; - u8 reserved[3]; - __le32 addr_high; /* address of array of 2-byte s-tags */ - __le32 addr_low; -}; - -I40E_CHECK_CMD_LENGTH(i40e_aqc_add_remove_mcast_etag); - -struct i40e_aqc_add_remove_mcast_etag_completion { - u8 reserved[4]; - __le16 mcast_etags_used; - __le16 mcast_etags_free; - __le32 addr_high; - __le32 addr_low; - -}; - -I40E_CHECK_CMD_LENGTH(i40e_aqc_add_remove_mcast_etag_completion); - -/* Update S/E-Tag (direct 0x0259) */ -struct i40e_aqc_update_tag { - __le16 seid; -#define I40E_AQC_UPDATE_TAG_CMD_SEID_NUM_SHIFT 0 -#define I40E_AQC_UPDATE_TAG_CMD_SEID_NUM_MASK (0x3FF << \ - I40E_AQC_UPDATE_TAG_CMD_SEID_NUM_SHIFT) - __le16 old_tag; - __le16 new_tag; - u8 reserved[10]; -}; - -I40E_CHECK_CMD_LENGTH(i40e_aqc_update_tag); - -struct i40e_aqc_update_tag_completion { - u8 reserved[12]; - __le16 tags_used; - __le16 tags_free; -}; - -I40E_CHECK_CMD_LENGTH(i40e_aqc_update_tag_completion); - -/* Add Control Packet filter (direct 0x025A) - * Remove Control Packet filter (direct 0x025B) - * uses the i40e_aqc_add_oveb_cloud, - * and the generic direct completion structure - */ -struct i40e_aqc_add_remove_control_packet_filter { - u8 mac[6]; - __le16 etype; - __le16 flags; -#define I40E_AQC_ADD_CONTROL_PACKET_FLAGS_IGNORE_MAC 0x0001 -#define I40E_AQC_ADD_CONTROL_PACKET_FLAGS_DROP 0x0002 -#define I40E_AQC_ADD_CONTROL_PACKET_FLAGS_TO_QUEUE 0x0004 -#define I40E_AQC_ADD_CONTROL_PACKET_FLAGS_TX 0x0008 -#define I40E_AQC_ADD_CONTROL_PACKET_FLAGS_RX 0x0000 - __le16 seid; -#define I40E_AQC_ADD_CONTROL_PACKET_CMD_SEID_NUM_SHIFT 0 -#define I40E_AQC_ADD_CONTROL_PACKET_CMD_SEID_NUM_MASK (0x3FF << \ - I40E_AQC_ADD_CONTROL_PACKET_CMD_SEID_NUM_SHIFT) - __le16 queue; - u8 reserved[2]; -}; - -I40E_CHECK_CMD_LENGTH(i40e_aqc_add_remove_control_packet_filter); - -struct i40e_aqc_add_remove_control_packet_filter_completion { - __le16 mac_etype_used; - __le16 etype_used; - __le16 mac_etype_free; - __le16 etype_free; - u8 reserved[8]; -}; - -I40E_CHECK_CMD_LENGTH(i40e_aqc_add_remove_control_packet_filter_completion); - -/* Add Cloud filters (indirect 0x025C) - * Remove Cloud filters (indirect 0x025D) - * uses the i40e_aqc_add_remove_cloud_filters, - * and the generic indirect completion structure - */ -struct i40e_aqc_add_remove_cloud_filters { - u8 num_filters; - u8 reserved; - __le16 seid; -#define I40E_AQC_ADD_CLOUD_CMD_SEID_NUM_SHIFT 0 -#define I40E_AQC_ADD_CLOUD_CMD_SEID_NUM_MASK (0x3FF << \ - I40E_AQC_ADD_CLOUD_CMD_SEID_NUM_SHIFT) - u8 big_buffer_flag; -#define I40E_AQC_ADD_CLOUD_CMD_BB 1 - u8 reserved2[3]; - __le32 addr_high; - __le32 addr_low; -}; - -I40E_CHECK_CMD_LENGTH(i40e_aqc_add_remove_cloud_filters); - -struct i40e_aqc_cloud_filters_element_data { - u8 outer_mac[6]; - u8 inner_mac[6]; - __le16 inner_vlan; - union { - struct { - u8 reserved[12]; - u8 data[4]; - } v4; - struct { - u8 data[16]; - } v6; - struct { - __le16 data[8]; - } raw_v6; - } ipaddr; - __le16 flags; -#define I40E_AQC_ADD_CLOUD_FILTER_SHIFT 0 -#define I40E_AQC_ADD_CLOUD_FILTER_MASK (0x3F << \ - I40E_AQC_ADD_CLOUD_FILTER_SHIFT) -/* 0x0000 reserved */ -#define I40E_AQC_ADD_CLOUD_FILTER_OIP 0x0001 -/* 0x0002 reserved */ -#define I40E_AQC_ADD_CLOUD_FILTER_IMAC_IVLAN 0x0003 -#define I40E_AQC_ADD_CLOUD_FILTER_IMAC_IVLAN_TEN_ID 0x0004 -/* 0x0005 reserved */ -#define I40E_AQC_ADD_CLOUD_FILTER_IMAC_TEN_ID 0x0006 -/* 0x0007 reserved */ -/* 0x0008 reserved */ -#define I40E_AQC_ADD_CLOUD_FILTER_OMAC 0x0009 -#define I40E_AQC_ADD_CLOUD_FILTER_IMAC 0x000A -#define I40E_AQC_ADD_CLOUD_FILTER_OMAC_TEN_ID_IMAC 0x000B -#define I40E_AQC_ADD_CLOUD_FILTER_IIP 0x000C -/* 0x0010 to 0x0017 is for custom filters */ -#define I40E_AQC_ADD_CLOUD_FILTER_IP_PORT 0x0010 /* Dest IP + L4 Port */ -#define I40E_AQC_ADD_CLOUD_FILTER_MAC_PORT 0x0011 /* Dest MAC + L4 Port */ -#define I40E_AQC_ADD_CLOUD_FILTER_MAC_VLAN_PORT 0x0012 /* Dest MAC + VLAN + L4 Port */ - -#define I40E_AQC_ADD_CLOUD_FLAGS_TO_QUEUE 0x0080 -#define I40E_AQC_ADD_CLOUD_VNK_SHIFT 6 -#define I40E_AQC_ADD_CLOUD_VNK_MASK 0x00C0 -#define I40E_AQC_ADD_CLOUD_FLAGS_IPV4 0 -#define I40E_AQC_ADD_CLOUD_FLAGS_IPV6 0x0100 - -#define I40E_AQC_ADD_CLOUD_TNL_TYPE_SHIFT 9 -#define I40E_AQC_ADD_CLOUD_TNL_TYPE_MASK 0x1E00 -#define I40E_AQC_ADD_CLOUD_TNL_TYPE_VXLAN 0 -#define I40E_AQC_ADD_CLOUD_TNL_TYPE_NVGRE_OMAC 1 -#define I40E_AQC_ADD_CLOUD_TNL_TYPE_GENEVE 2 -#define I40E_AQC_ADD_CLOUD_TNL_TYPE_IP 3 -#define I40E_AQC_ADD_CLOUD_TNL_TYPE_RESERVED 4 -#define I40E_AQC_ADD_CLOUD_TNL_TYPE_VXLAN_GPE 5 - -#define I40E_AQC_ADD_CLOUD_FLAGS_SHARED_OUTER_MAC 0x2000 -#define I40E_AQC_ADD_CLOUD_FLAGS_SHARED_INNER_MAC 0x4000 -#define I40E_AQC_ADD_CLOUD_FLAGS_SHARED_OUTER_IP 0x8000 - - __le32 tenant_id; - u8 reserved[4]; - __le16 queue_number; -#define I40E_AQC_ADD_CLOUD_QUEUE_SHIFT 0 -#define I40E_AQC_ADD_CLOUD_QUEUE_MASK (0x7FF << \ - I40E_AQC_ADD_CLOUD_QUEUE_SHIFT) - u8 reserved2[14]; - /* response section */ - u8 allocation_result; -#define I40E_AQC_ADD_CLOUD_FILTER_SUCCESS 0x0 -#define I40E_AQC_ADD_CLOUD_FILTER_FAIL 0xFF - u8 response_reserved[7]; -}; - -I40E_CHECK_STRUCT_LEN(0x40, i40e_aqc_cloud_filters_element_data); - -/* i40e_aqc_cloud_filters_element_bb is used when - * I40E_AQC_ADD_CLOUD_CMD_BB flag is set. - */ -struct i40e_aqc_cloud_filters_element_bb { - struct i40e_aqc_cloud_filters_element_data element; - u16 general_fields[32]; -#define I40E_AQC_ADD_CLOUD_FV_FLU_0X10_WORD0 0 -#define I40E_AQC_ADD_CLOUD_FV_FLU_0X10_WORD1 1 -#define I40E_AQC_ADD_CLOUD_FV_FLU_0X10_WORD2 2 -#define I40E_AQC_ADD_CLOUD_FV_FLU_0X11_WORD0 3 -#define I40E_AQC_ADD_CLOUD_FV_FLU_0X11_WORD1 4 -#define I40E_AQC_ADD_CLOUD_FV_FLU_0X11_WORD2 5 -#define I40E_AQC_ADD_CLOUD_FV_FLU_0X12_WORD0 6 -#define I40E_AQC_ADD_CLOUD_FV_FLU_0X12_WORD1 7 -#define I40E_AQC_ADD_CLOUD_FV_FLU_0X12_WORD2 8 -#define I40E_AQC_ADD_CLOUD_FV_FLU_0X13_WORD0 9 -#define I40E_AQC_ADD_CLOUD_FV_FLU_0X13_WORD1 10 -#define I40E_AQC_ADD_CLOUD_FV_FLU_0X13_WORD2 11 -#define I40E_AQC_ADD_CLOUD_FV_FLU_0X14_WORD0 12 -#define I40E_AQC_ADD_CLOUD_FV_FLU_0X14_WORD1 13 -#define I40E_AQC_ADD_CLOUD_FV_FLU_0X14_WORD2 14 -#define I40E_AQC_ADD_CLOUD_FV_FLU_0X16_WORD0 15 -#define I40E_AQC_ADD_CLOUD_FV_FLU_0X16_WORD1 16 -#define I40E_AQC_ADD_CLOUD_FV_FLU_0X16_WORD2 17 -#define I40E_AQC_ADD_CLOUD_FV_FLU_0X16_WORD3 18 -#define I40E_AQC_ADD_CLOUD_FV_FLU_0X16_WORD4 19 -#define I40E_AQC_ADD_CLOUD_FV_FLU_0X16_WORD5 20 -#define I40E_AQC_ADD_CLOUD_FV_FLU_0X16_WORD6 21 -#define I40E_AQC_ADD_CLOUD_FV_FLU_0X16_WORD7 22 -#define I40E_AQC_ADD_CLOUD_FV_FLU_0X17_WORD0 23 -#define I40E_AQC_ADD_CLOUD_FV_FLU_0X17_WORD1 24 -#define I40E_AQC_ADD_CLOUD_FV_FLU_0X17_WORD2 25 -#define I40E_AQC_ADD_CLOUD_FV_FLU_0X17_WORD3 26 -#define I40E_AQC_ADD_CLOUD_FV_FLU_0X17_WORD4 27 -#define I40E_AQC_ADD_CLOUD_FV_FLU_0X17_WORD5 28 -#define I40E_AQC_ADD_CLOUD_FV_FLU_0X17_WORD6 29 -#define I40E_AQC_ADD_CLOUD_FV_FLU_0X17_WORD7 30 -}; - -I40E_CHECK_STRUCT_LEN(0x80, i40e_aqc_cloud_filters_element_bb); - -struct i40e_aqc_remove_cloud_filters_completion { - __le16 perfect_ovlan_used; - __le16 perfect_ovlan_free; - __le16 vlan_used; - __le16 vlan_free; - __le32 addr_high; - __le32 addr_low; -}; - -I40E_CHECK_CMD_LENGTH(i40e_aqc_remove_cloud_filters_completion); - -/* Replace filter Command 0x025F - * uses the i40e_aqc_replace_cloud_filters, - * and the generic indirect completion structure - */ -struct i40e_filter_data { - u8 filter_type; - u8 input[3]; -}; - -I40E_CHECK_STRUCT_LEN(4, i40e_filter_data); - -struct i40e_aqc_replace_cloud_filters_cmd { - u8 valid_flags; -#define I40E_AQC_REPLACE_L1_FILTER 0x0 -#define I40E_AQC_REPLACE_CLOUD_FILTER 0x1 -#define I40E_AQC_GET_CLOUD_FILTERS 0x2 -#define I40E_AQC_MIRROR_CLOUD_FILTER 0x4 -#define I40E_AQC_HIGH_PRIORITY_CLOUD_FILTER 0x8 - u8 old_filter_type; - u8 new_filter_type; - u8 tr_bit; - u8 reserved[4]; - __le32 addr_high; - __le32 addr_low; -}; - -I40E_CHECK_CMD_LENGTH(i40e_aqc_replace_cloud_filters_cmd); - -struct i40e_aqc_replace_cloud_filters_cmd_buf { - u8 data[32]; -/* Filter type INPUT codes*/ -#define I40E_AQC_REPLACE_CLOUD_CMD_INPUT_ENTRIES_MAX 3 -#define I40E_AQC_REPLACE_CLOUD_CMD_INPUT_VALIDATED BIT(7) - -/* Field Vector offsets */ -#define I40E_AQC_REPLACE_CLOUD_CMD_INPUT_FV_MAC_DA 0 -#define I40E_AQC_REPLACE_CLOUD_CMD_INPUT_FV_STAG_ETH 6 -#define I40E_AQC_REPLACE_CLOUD_CMD_INPUT_FV_STAG 7 -#define I40E_AQC_REPLACE_CLOUD_CMD_INPUT_FV_VLAN 8 -#define I40E_AQC_REPLACE_CLOUD_CMD_INPUT_FV_STAG_OVLAN 9 -#define I40E_AQC_REPLACE_CLOUD_CMD_INPUT_FV_STAG_IVLAN 10 -#define I40E_AQC_REPLACE_CLOUD_CMD_INPUT_FV_TUNNLE_KEY 11 -#define I40E_AQC_REPLACE_CLOUD_CMD_INPUT_FV_IMAC 12 -/* big FLU */ -#define I40E_AQC_REPLACE_CLOUD_CMD_INPUT_FV_IP_DA 14 -/* big FLU */ -#define I40E_AQC_REPLACE_CLOUD_CMD_INPUT_FV_OIP_DA 15 - -#define I40E_AQC_REPLACE_CLOUD_CMD_INPUT_FV_INNER_VLAN 37 - struct i40e_filter_data filters[8]; -}; - -I40E_CHECK_STRUCT_LEN(0x40, i40e_aqc_replace_cloud_filters_cmd_buf); - -/* Add Mirror Rule (indirect or direct 0x0260) - * Delete Mirror Rule (indirect or direct 0x0261) - * note: some rule types (4,5) do not use an external buffer. - * take care to set the flags correctly. - */ -struct i40e_aqc_add_delete_mirror_rule { - __le16 seid; - __le16 rule_type; -#define I40E_AQC_MIRROR_RULE_TYPE_SHIFT 0 -#define I40E_AQC_MIRROR_RULE_TYPE_MASK (0x7 << \ - I40E_AQC_MIRROR_RULE_TYPE_SHIFT) -#define I40E_AQC_MIRROR_RULE_TYPE_VPORT_INGRESS 1 -#define I40E_AQC_MIRROR_RULE_TYPE_VPORT_EGRESS 2 -#define I40E_AQC_MIRROR_RULE_TYPE_VLAN 3 -#define I40E_AQC_MIRROR_RULE_TYPE_ALL_INGRESS 4 -#define I40E_AQC_MIRROR_RULE_TYPE_ALL_EGRESS 5 - __le16 num_entries; - __le16 destination; /* VSI for add, rule id for delete */ - __le32 addr_high; /* address of array of 2-byte VSI or VLAN ids */ - __le32 addr_low; -}; - -I40E_CHECK_CMD_LENGTH(i40e_aqc_add_delete_mirror_rule); - -struct i40e_aqc_add_delete_mirror_rule_completion { - u8 reserved[2]; - __le16 rule_id; /* only used on add */ - __le16 mirror_rules_used; - __le16 mirror_rules_free; - __le32 addr_high; - __le32 addr_low; -}; - -I40E_CHECK_CMD_LENGTH(i40e_aqc_add_delete_mirror_rule_completion); - -/* Dynamic Device Personalization */ -struct i40e_aqc_write_personalization_profile { - u8 flags; - u8 reserved[3]; - __le32 profile_track_id; - __le32 addr_high; - __le32 addr_low; -}; - -I40E_CHECK_CMD_LENGTH(i40e_aqc_write_personalization_profile); - -struct i40e_aqc_write_ddp_resp { - __le32 error_offset; - __le32 error_info; - __le32 addr_high; - __le32 addr_low; -}; - -struct i40e_aqc_get_applied_profiles { - u8 flags; -#define I40E_AQC_GET_DDP_GET_CONF 0x1 -#define I40E_AQC_GET_DDP_GET_RDPU_CONF 0x2 - u8 rsv[3]; - __le32 reserved; - __le32 addr_high; - __le32 addr_low; -}; - -I40E_CHECK_CMD_LENGTH(i40e_aqc_get_applied_profiles); - -/* DCB 0x03xx*/ - -/* PFC Ignore (direct 0x0301) - * the command and response use the same descriptor structure - */ -struct i40e_aqc_pfc_ignore { - u8 tc_bitmap; - u8 command_flags; /* unused on response */ -#define I40E_AQC_PFC_IGNORE_SET 0x80 -#define I40E_AQC_PFC_IGNORE_CLEAR 0x0 - u8 reserved[14]; -}; - -I40E_CHECK_CMD_LENGTH(i40e_aqc_pfc_ignore); - -/* DCB Update (direct 0x0302) uses the i40e_aq_desc structure - * with no parameters - */ - -/* TX scheduler 0x04xx */ - -/* Almost all the indirect commands use - * this generic struct to pass the SEID in param0 - */ -struct i40e_aqc_tx_sched_ind { - __le16 vsi_seid; - u8 reserved[6]; - __le32 addr_high; - __le32 addr_low; -}; - -I40E_CHECK_CMD_LENGTH(i40e_aqc_tx_sched_ind); - -/* Several commands respond with a set of queue set handles */ -struct i40e_aqc_qs_handles_resp { - __le16 qs_handles[8]; -}; - -/* Configure VSI BW limits (direct 0x0400) */ -struct i40e_aqc_configure_vsi_bw_limit { - __le16 vsi_seid; - u8 reserved[2]; - __le16 credit; - u8 reserved1[2]; - u8 max_credit; /* 0-3, limit = 2^max */ - u8 reserved2[7]; -}; - -I40E_CHECK_CMD_LENGTH(i40e_aqc_configure_vsi_bw_limit); - -/* Configure VSI Bandwidth Limit per Traffic Type (indirect 0x0406) - * responds with i40e_aqc_qs_handles_resp - */ -struct i40e_aqc_configure_vsi_ets_sla_bw_data { - u8 tc_valid_bits; - u8 reserved[15]; - __le16 tc_bw_credits[8]; /* FW writesback QS handles here */ - - /* 4 bits per tc 0-7, 4th bit is reserved, limit = 2^max */ - __le16 tc_bw_max[2]; - u8 reserved1[28]; -}; - -I40E_CHECK_STRUCT_LEN(0x40, i40e_aqc_configure_vsi_ets_sla_bw_data); - -/* Configure VSI Bandwidth Allocation per Traffic Type (indirect 0x0407) - * responds with i40e_aqc_qs_handles_resp - */ -struct i40e_aqc_configure_vsi_tc_bw_data { - u8 tc_valid_bits; - u8 reserved[3]; - u8 tc_bw_credits[8]; - u8 reserved1[4]; - __le16 qs_handles[8]; -}; - -I40E_CHECK_STRUCT_LEN(0x20, i40e_aqc_configure_vsi_tc_bw_data); - -/* Query vsi bw configuration (indirect 0x0408) */ -struct i40e_aqc_query_vsi_bw_config_resp { - u8 tc_valid_bits; - u8 tc_suspended_bits; - u8 reserved[14]; - __le16 qs_handles[8]; - u8 reserved1[4]; - __le16 port_bw_limit; - u8 reserved2[2]; - u8 max_bw; /* 0-3, limit = 2^max */ - u8 reserved3[23]; -}; - -I40E_CHECK_STRUCT_LEN(0x40, i40e_aqc_query_vsi_bw_config_resp); - -/* Query VSI Bandwidth Allocation per Traffic Type (indirect 0x040A) */ -struct i40e_aqc_query_vsi_ets_sla_config_resp { - u8 tc_valid_bits; - u8 reserved[3]; - u8 share_credits[8]; - __le16 credits[8]; - - /* 4 bits per tc 0-7, 4th bit is reserved, limit = 2^max */ - __le16 tc_bw_max[2]; -}; - -I40E_CHECK_STRUCT_LEN(0x20, i40e_aqc_query_vsi_ets_sla_config_resp); - -/* Configure Switching Component Bandwidth Limit (direct 0x0410) */ -struct i40e_aqc_configure_switching_comp_bw_limit { - __le16 seid; - u8 reserved[2]; - __le16 credit; - u8 reserved1[2]; - u8 max_bw; /* 0-3, limit = 2^max */ - u8 reserved2[7]; -}; - -I40E_CHECK_CMD_LENGTH(i40e_aqc_configure_switching_comp_bw_limit); - -/* Enable Physical Port ETS (indirect 0x0413) - * Modify Physical Port ETS (indirect 0x0414) - * Disable Physical Port ETS (indirect 0x0415) - */ -struct i40e_aqc_configure_switching_comp_ets_data { - u8 reserved[4]; - u8 tc_valid_bits; - u8 seepage; -#define I40E_AQ_ETS_SEEPAGE_EN_MASK 0x1 - u8 tc_strict_priority_flags; - u8 reserved1[17]; - u8 tc_bw_share_credits[8]; - u8 reserved2[96]; -}; - -I40E_CHECK_STRUCT_LEN(0x80, i40e_aqc_configure_switching_comp_ets_data); - -/* Configure Switching Component Bandwidth Limits per Tc (indirect 0x0416) */ -struct i40e_aqc_configure_switching_comp_ets_bw_limit_data { - u8 tc_valid_bits; - u8 reserved[15]; - __le16 tc_bw_credit[8]; - - /* 4 bits per tc 0-7, 4th bit is reserved, limit = 2^max */ - __le16 tc_bw_max[2]; - u8 reserved1[28]; -}; - -I40E_CHECK_STRUCT_LEN(0x40, - i40e_aqc_configure_switching_comp_ets_bw_limit_data); - -/* Configure Switching Component Bandwidth Allocation per Tc - * (indirect 0x0417) - */ -struct i40e_aqc_configure_switching_comp_bw_config_data { - u8 tc_valid_bits; - u8 reserved[2]; - u8 absolute_credits; /* bool */ - u8 tc_bw_share_credits[8]; - u8 reserved1[20]; -}; - -I40E_CHECK_STRUCT_LEN(0x20, i40e_aqc_configure_switching_comp_bw_config_data); - -/* Query Switching Component Configuration (indirect 0x0418) */ -struct i40e_aqc_query_switching_comp_ets_config_resp { - u8 tc_valid_bits; - u8 reserved[35]; - __le16 port_bw_limit; - u8 reserved1[2]; - u8 tc_bw_max; /* 0-3, limit = 2^max */ - u8 reserved2[23]; -}; - -I40E_CHECK_STRUCT_LEN(0x40, i40e_aqc_query_switching_comp_ets_config_resp); - -/* Query PhysicalPort ETS Configuration (indirect 0x0419) */ -struct i40e_aqc_query_port_ets_config_resp { - u8 reserved[4]; - u8 tc_valid_bits; - u8 reserved1; - u8 tc_strict_priority_bits; - u8 reserved2; - u8 tc_bw_share_credits[8]; - __le16 tc_bw_limits[8]; - - /* 4 bits per tc 0-7, 4th bit reserved, limit = 2^max */ - __le16 tc_bw_max[2]; - u8 reserved3[32]; -}; - -I40E_CHECK_STRUCT_LEN(0x44, i40e_aqc_query_port_ets_config_resp); - -/* Query Switching Component Bandwidth Allocation per Traffic Type - * (indirect 0x041A) - */ -struct i40e_aqc_query_switching_comp_bw_config_resp { - u8 tc_valid_bits; - u8 reserved[2]; - u8 absolute_credits_enable; /* bool */ - u8 tc_bw_share_credits[8]; - __le16 tc_bw_limits[8]; - - /* 4 bits per tc 0-7, 4th bit is reserved, limit = 2^max */ - __le16 tc_bw_max[2]; -}; - -I40E_CHECK_STRUCT_LEN(0x20, i40e_aqc_query_switching_comp_bw_config_resp); - -/* Suspend/resume port TX traffic - * (direct 0x041B and 0x041C) uses the generic SEID struct - */ - -/* Configure partition BW - * (indirect 0x041D) - */ -struct i40e_aqc_configure_partition_bw_data { - __le16 pf_valid_bits; - u8 min_bw[16]; /* guaranteed bandwidth */ - u8 max_bw[16]; /* bandwidth limit */ -}; - -I40E_CHECK_STRUCT_LEN(0x22, i40e_aqc_configure_partition_bw_data); - -/* Get and set the active HMC resource profile and status. - * (direct 0x0500) and (direct 0x0501) - */ -struct i40e_aq_get_set_hmc_resource_profile { - u8 pm_profile; - u8 pe_vf_enabled; - u8 reserved[14]; -}; - -I40E_CHECK_CMD_LENGTH(i40e_aq_get_set_hmc_resource_profile); - -enum i40e_aq_hmc_profile { - /* I40E_HMC_PROFILE_NO_CHANGE = 0, reserved */ - I40E_HMC_PROFILE_DEFAULT = 1, - I40E_HMC_PROFILE_FAVOR_VF = 2, - I40E_HMC_PROFILE_EQUAL = 3, -}; - -/* Get PHY Abilities (indirect 0x0600) uses the generic indirect struct */ - -/* set in param0 for get phy abilities to report qualified modules */ -#define I40E_AQ_PHY_REPORT_QUALIFIED_MODULES 0x0001 -#define I40E_AQ_PHY_REPORT_INITIAL_VALUES 0x0002 - -enum i40e_aq_phy_type { - I40E_PHY_TYPE_SGMII = 0x0, - I40E_PHY_TYPE_1000BASE_KX = 0x1, - I40E_PHY_TYPE_10GBASE_KX4 = 0x2, - I40E_PHY_TYPE_10GBASE_KR = 0x3, - I40E_PHY_TYPE_40GBASE_KR4 = 0x4, - I40E_PHY_TYPE_XAUI = 0x5, - I40E_PHY_TYPE_XFI = 0x6, - I40E_PHY_TYPE_SFI = 0x7, - I40E_PHY_TYPE_XLAUI = 0x8, - I40E_PHY_TYPE_XLPPI = 0x9, - I40E_PHY_TYPE_40GBASE_CR4_CU = 0xA, - I40E_PHY_TYPE_10GBASE_CR1_CU = 0xB, - I40E_PHY_TYPE_10GBASE_AOC = 0xC, - I40E_PHY_TYPE_40GBASE_AOC = 0xD, - I40E_PHY_TYPE_UNRECOGNIZED = 0xE, - I40E_PHY_TYPE_UNSUPPORTED = 0xF, - I40E_PHY_TYPE_100BASE_TX = 0x11, - I40E_PHY_TYPE_1000BASE_T = 0x12, - I40E_PHY_TYPE_10GBASE_T = 0x13, - I40E_PHY_TYPE_10GBASE_SR = 0x14, - I40E_PHY_TYPE_10GBASE_LR = 0x15, - I40E_PHY_TYPE_10GBASE_SFPP_CU = 0x16, - I40E_PHY_TYPE_10GBASE_CR1 = 0x17, - I40E_PHY_TYPE_40GBASE_CR4 = 0x18, - I40E_PHY_TYPE_40GBASE_SR4 = 0x19, - I40E_PHY_TYPE_40GBASE_LR4 = 0x1A, - I40E_PHY_TYPE_1000BASE_SX = 0x1B, - I40E_PHY_TYPE_1000BASE_LX = 0x1C, - I40E_PHY_TYPE_1000BASE_T_OPTICAL = 0x1D, - I40E_PHY_TYPE_20GBASE_KR2 = 0x1E, - I40E_PHY_TYPE_25GBASE_KR = 0x1F, - I40E_PHY_TYPE_25GBASE_CR = 0x20, - I40E_PHY_TYPE_25GBASE_SR = 0x21, - I40E_PHY_TYPE_25GBASE_LR = 0x22, - I40E_PHY_TYPE_25GBASE_AOC = 0x23, - I40E_PHY_TYPE_25GBASE_ACC = 0x24, - I40E_PHY_TYPE_MAX, - I40E_PHY_TYPE_NOT_SUPPORTED_HIGH_TEMP = 0xFD, - I40E_PHY_TYPE_EMPTY = 0xFE, - I40E_PHY_TYPE_DEFAULT = 0xFF, -}; - -#define I40E_LINK_SPEED_100MB_SHIFT 0x1 -#define I40E_LINK_SPEED_1000MB_SHIFT 0x2 -#define I40E_LINK_SPEED_10GB_SHIFT 0x3 -#define I40E_LINK_SPEED_40GB_SHIFT 0x4 -#define I40E_LINK_SPEED_20GB_SHIFT 0x5 -#define I40E_LINK_SPEED_25GB_SHIFT 0x6 - -enum i40e_aq_link_speed { - I40E_LINK_SPEED_UNKNOWN = 0, - I40E_LINK_SPEED_100MB = BIT(I40E_LINK_SPEED_100MB_SHIFT), - I40E_LINK_SPEED_1GB = BIT(I40E_LINK_SPEED_1000MB_SHIFT), - I40E_LINK_SPEED_10GB = BIT(I40E_LINK_SPEED_10GB_SHIFT), - I40E_LINK_SPEED_40GB = BIT(I40E_LINK_SPEED_40GB_SHIFT), - I40E_LINK_SPEED_20GB = BIT(I40E_LINK_SPEED_20GB_SHIFT), - I40E_LINK_SPEED_25GB = BIT(I40E_LINK_SPEED_25GB_SHIFT), -}; - -struct i40e_aqc_module_desc { - u8 oui[3]; - u8 reserved1; - u8 part_number[16]; - u8 revision[4]; - u8 reserved2[8]; -}; - -I40E_CHECK_STRUCT_LEN(0x20, i40e_aqc_module_desc); - -struct i40e_aq_get_phy_abilities_resp { - __le32 phy_type; /* bitmap using the above enum for offsets */ - u8 link_speed; /* bitmap using the above enum bit patterns */ - u8 abilities; -#define I40E_AQ_PHY_FLAG_PAUSE_TX 0x01 -#define I40E_AQ_PHY_FLAG_PAUSE_RX 0x02 -#define I40E_AQ_PHY_FLAG_LOW_POWER 0x04 -#define I40E_AQ_PHY_LINK_ENABLED 0x08 -#define I40E_AQ_PHY_AN_ENABLED 0x10 -#define I40E_AQ_PHY_FLAG_MODULE_QUAL 0x20 -#define I40E_AQ_PHY_FEC_ABILITY_KR 0x40 -#define I40E_AQ_PHY_FEC_ABILITY_RS 0x80 - __le16 eee_capability; -#define I40E_AQ_EEE_100BASE_TX 0x0002 -#define I40E_AQ_EEE_1000BASE_T 0x0004 -#define I40E_AQ_EEE_10GBASE_T 0x0008 -#define I40E_AQ_EEE_1000BASE_KX 0x0010 -#define I40E_AQ_EEE_10GBASE_KX4 0x0020 -#define I40E_AQ_EEE_10GBASE_KR 0x0040 - __le32 eeer_val; - u8 d3_lpan; -#define I40E_AQ_SET_PHY_D3_LPAN_ENA 0x01 - u8 phy_type_ext; -#define I40E_AQ_PHY_TYPE_EXT_25G_KR 0X01 -#define I40E_AQ_PHY_TYPE_EXT_25G_CR 0X02 -#define I40E_AQ_PHY_TYPE_EXT_25G_SR 0x04 -#define I40E_AQ_PHY_TYPE_EXT_25G_LR 0x08 -#define I40E_AQ_PHY_TYPE_EXT_25G_AOC 0x10 -#define I40E_AQ_PHY_TYPE_EXT_25G_ACC 0x20 - u8 fec_cfg_curr_mod_ext_info; -#define I40E_AQ_ENABLE_FEC_KR 0x01 -#define I40E_AQ_ENABLE_FEC_RS 0x02 -#define I40E_AQ_REQUEST_FEC_KR 0x04 -#define I40E_AQ_REQUEST_FEC_RS 0x08 -#define I40E_AQ_ENABLE_FEC_AUTO 0x10 -#define I40E_AQ_FEC -#define I40E_AQ_MODULE_TYPE_EXT_MASK 0xE0 -#define I40E_AQ_MODULE_TYPE_EXT_SHIFT 5 - - u8 ext_comp_code; - u8 phy_id[4]; - u8 module_type[3]; - u8 qualified_module_count; -#define I40E_AQ_PHY_MAX_QMS 16 - struct i40e_aqc_module_desc qualified_module[I40E_AQ_PHY_MAX_QMS]; -}; - -I40E_CHECK_STRUCT_LEN(0x218, i40e_aq_get_phy_abilities_resp); - -/* Set PHY Config (direct 0x0601) */ -struct i40e_aq_set_phy_config { /* same bits as above in all */ - __le32 phy_type; - u8 link_speed; - u8 abilities; -/* bits 0-2 use the values from get_phy_abilities_resp */ -#define I40E_AQ_PHY_ENABLE_LINK 0x08 -#define I40E_AQ_PHY_ENABLE_AN 0x10 -#define I40E_AQ_PHY_ENABLE_ATOMIC_LINK 0x20 - __le16 eee_capability; - __le32 eeer; - u8 low_power_ctrl; - u8 phy_type_ext; -#define I40E_AQ_PHY_TYPE_EXT_25G_KR 0X01 -#define I40E_AQ_PHY_TYPE_EXT_25G_CR 0X02 -#define I40E_AQ_PHY_TYPE_EXT_25G_SR 0x04 -#define I40E_AQ_PHY_TYPE_EXT_25G_LR 0x08 - u8 fec_config; -#define I40E_AQ_SET_FEC_ABILITY_KR BIT(0) -#define I40E_AQ_SET_FEC_ABILITY_RS BIT(1) -#define I40E_AQ_SET_FEC_REQUEST_KR BIT(2) -#define I40E_AQ_SET_FEC_REQUEST_RS BIT(3) -#define I40E_AQ_SET_FEC_AUTO BIT(4) -#define I40E_AQ_PHY_FEC_CONFIG_SHIFT 0x0 -#define I40E_AQ_PHY_FEC_CONFIG_MASK (0x1F << I40E_AQ_PHY_FEC_CONFIG_SHIFT) - u8 reserved; -}; - -I40E_CHECK_CMD_LENGTH(i40e_aq_set_phy_config); - -/* Set MAC Config command data structure (direct 0x0603) */ -struct i40e_aq_set_mac_config { - __le16 max_frame_size; - u8 params; -#define I40E_AQ_SET_MAC_CONFIG_CRC_EN 0x04 -#define I40E_AQ_SET_MAC_CONFIG_PACING_MASK 0x78 -#define I40E_AQ_SET_MAC_CONFIG_PACING_SHIFT 3 -#define I40E_AQ_SET_MAC_CONFIG_PACING_NONE 0x0 -#define I40E_AQ_SET_MAC_CONFIG_PACING_1B_13TX 0xF -#define I40E_AQ_SET_MAC_CONFIG_PACING_1DW_9TX 0x9 -#define I40E_AQ_SET_MAC_CONFIG_PACING_1DW_4TX 0x8 -#define I40E_AQ_SET_MAC_CONFIG_PACING_3DW_7TX 0x7 -#define I40E_AQ_SET_MAC_CONFIG_PACING_2DW_3TX 0x6 -#define I40E_AQ_SET_MAC_CONFIG_PACING_1DW_1TX 0x5 -#define I40E_AQ_SET_MAC_CONFIG_PACING_3DW_2TX 0x4 -#define I40E_AQ_SET_MAC_CONFIG_PACING_7DW_3TX 0x3 -#define I40E_AQ_SET_MAC_CONFIG_PACING_4DW_1TX 0x2 -#define I40E_AQ_SET_MAC_CONFIG_PACING_9DW_1TX 0x1 - u8 tx_timer_priority; /* bitmap */ - __le16 tx_timer_value; - __le16 fc_refresh_threshold; - u8 reserved[8]; -}; - -I40E_CHECK_CMD_LENGTH(i40e_aq_set_mac_config); - -/* Restart Auto-Negotiation (direct 0x605) */ -struct i40e_aqc_set_link_restart_an { - u8 command; -#define I40E_AQ_PHY_RESTART_AN 0x02 -#define I40E_AQ_PHY_LINK_ENABLE 0x04 - u8 reserved[15]; -}; - -I40E_CHECK_CMD_LENGTH(i40e_aqc_set_link_restart_an); - -/* Get Link Status cmd & response data structure (direct 0x0607) */ -struct i40e_aqc_get_link_status { - __le16 command_flags; /* only field set on command */ -#define I40E_AQ_LSE_MASK 0x3 -#define I40E_AQ_LSE_NOP 0x0 -#define I40E_AQ_LSE_DISABLE 0x2 -#define I40E_AQ_LSE_ENABLE 0x3 -/* only response uses this flag */ -#define I40E_AQ_LSE_IS_ENABLED 0x1 - u8 phy_type; /* i40e_aq_phy_type */ - u8 link_speed; /* i40e_aq_link_speed */ - u8 link_info; -#define I40E_AQ_LINK_UP 0x01 /* obsolete */ -#define I40E_AQ_LINK_UP_FUNCTION 0x01 -#define I40E_AQ_LINK_FAULT 0x02 -#define I40E_AQ_LINK_FAULT_TX 0x04 -#define I40E_AQ_LINK_FAULT_RX 0x08 -#define I40E_AQ_LINK_FAULT_REMOTE 0x10 -#define I40E_AQ_LINK_UP_PORT 0x20 -#define I40E_AQ_MEDIA_AVAILABLE 0x40 -#define I40E_AQ_SIGNAL_DETECT 0x80 - u8 an_info; -#define I40E_AQ_AN_COMPLETED 0x01 -#define I40E_AQ_LP_AN_ABILITY 0x02 -#define I40E_AQ_PD_FAULT 0x04 -#define I40E_AQ_FEC_EN 0x08 -#define I40E_AQ_PHY_LOW_POWER 0x10 -#define I40E_AQ_LINK_PAUSE_TX 0x20 -#define I40E_AQ_LINK_PAUSE_RX 0x40 -#define I40E_AQ_QUALIFIED_MODULE 0x80 - u8 ext_info; -#define I40E_AQ_LINK_PHY_TEMP_ALARM 0x01 -#define I40E_AQ_LINK_XCESSIVE_ERRORS 0x02 -#define I40E_AQ_LINK_TX_SHIFT 0x02 -#define I40E_AQ_LINK_TX_MASK (0x03 << I40E_AQ_LINK_TX_SHIFT) -#define I40E_AQ_LINK_TX_ACTIVE 0x00 -#define I40E_AQ_LINK_TX_DRAINED 0x01 -#define I40E_AQ_LINK_TX_FLUSHED 0x03 -#define I40E_AQ_LINK_FORCED_40G 0x10 -/* 25G Error Codes */ -#define I40E_AQ_25G_NO_ERR 0X00 -#define I40E_AQ_25G_NOT_PRESENT 0X01 -#define I40E_AQ_25G_NVM_CRC_ERR 0X02 -#define I40E_AQ_25G_SBUS_UCODE_ERR 0X03 -#define I40E_AQ_25G_SERDES_UCODE_ERR 0X04 -#define I40E_AQ_25G_NIMB_UCODE_ERR 0X05 - u8 loopback; /* use defines from i40e_aqc_set_lb_mode */ -/* Since firmware API 1.7 loopback field keeps power class info as well */ -#define I40E_AQ_LOOPBACK_MASK 0x07 -#define I40E_AQ_PWR_CLASS_SHIFT_LB 6 -#define I40E_AQ_PWR_CLASS_MASK_LB (0x03 << I40E_AQ_PWR_CLASS_SHIFT_LB) - __le16 max_frame_size; - u8 config; -#define I40E_AQ_CONFIG_FEC_KR_ENA 0x01 -#define I40E_AQ_CONFIG_FEC_RS_ENA 0x02 -#define I40E_AQ_CONFIG_CRC_ENA 0x04 -#define I40E_AQ_CONFIG_PACING_MASK 0x78 - union { - struct { - u8 power_desc; -#define I40E_AQ_LINK_POWER_CLASS_1 0x00 -#define I40E_AQ_LINK_POWER_CLASS_2 0x01 -#define I40E_AQ_LINK_POWER_CLASS_3 0x02 -#define I40E_AQ_LINK_POWER_CLASS_4 0x03 -#define I40E_AQ_PWR_CLASS_MASK 0x03 - u8 reserved[4]; - }; - struct { - u8 link_type[4]; - u8 link_type_ext; - }; - }; -}; - -I40E_CHECK_CMD_LENGTH(i40e_aqc_get_link_status); - -/* Set event mask command (direct 0x613) */ -struct i40e_aqc_set_phy_int_mask { - u8 reserved[8]; - __le16 event_mask; -#define I40E_AQ_EVENT_LINK_UPDOWN 0x0002 -#define I40E_AQ_EVENT_MEDIA_NA 0x0004 -#define I40E_AQ_EVENT_LINK_FAULT 0x0008 -#define I40E_AQ_EVENT_PHY_TEMP_ALARM 0x0010 -#define I40E_AQ_EVENT_EXCESSIVE_ERRORS 0x0020 -#define I40E_AQ_EVENT_SIGNAL_DETECT 0x0040 -#define I40E_AQ_EVENT_AN_COMPLETED 0x0080 -#define I40E_AQ_EVENT_MODULE_QUAL_FAIL 0x0100 -#define I40E_AQ_EVENT_PORT_TX_SUSPENDED 0x0200 - u8 reserved1[6]; -}; - -I40E_CHECK_CMD_LENGTH(i40e_aqc_set_phy_int_mask); - -/* Get Local AN advt register (direct 0x0614) - * Set Local AN advt register (direct 0x0615) - * Get Link Partner AN advt register (direct 0x0616) - */ -struct i40e_aqc_an_advt_reg { - __le32 local_an_reg0; - __le16 local_an_reg1; - u8 reserved[10]; -}; - -I40E_CHECK_CMD_LENGTH(i40e_aqc_an_advt_reg); - -/* Set Loopback mode (0x0618) */ -struct i40e_aqc_set_lb_mode { - __le16 lb_mode; -#define I40E_AQ_LB_PHY_LOCAL 0x01 -#define I40E_AQ_LB_PHY_REMOTE 0x02 -#define I40E_AQ_LB_MAC_LOCAL 0x04 - u8 reserved[14]; -}; - -I40E_CHECK_CMD_LENGTH(i40e_aqc_set_lb_mode); - -/* Set PHY Debug command (0x0622) */ -struct i40e_aqc_set_phy_debug { - u8 command_flags; -#define I40E_AQ_PHY_DEBUG_RESET_INTERNAL 0x02 -#define I40E_AQ_PHY_DEBUG_RESET_EXTERNAL_SHIFT 2 -#define I40E_AQ_PHY_DEBUG_RESET_EXTERNAL_MASK (0x03 << \ - I40E_AQ_PHY_DEBUG_RESET_EXTERNAL_SHIFT) -#define I40E_AQ_PHY_DEBUG_RESET_EXTERNAL_NONE 0x00 -#define I40E_AQ_PHY_DEBUG_RESET_EXTERNAL_HARD 0x01 -#define I40E_AQ_PHY_DEBUG_RESET_EXTERNAL_SOFT 0x02 -#define I40E_AQ_PHY_DEBUG_DISABLE_LINK_FW 0x10 - u8 reserved[15]; -}; - -I40E_CHECK_CMD_LENGTH(i40e_aqc_set_phy_debug); - -enum i40e_aq_phy_reg_type { - I40E_AQC_PHY_REG_INTERNAL = 0x1, - I40E_AQC_PHY_REG_EXERNAL_BASET = 0x2, - I40E_AQC_PHY_REG_EXERNAL_MODULE = 0x3 -}; - -/* Run PHY Activity (0x0626) */ -struct i40e_aqc_run_phy_activity { - __le16 activity_id; - u8 flags; - u8 reserved1; - __le32 control; - __le32 data; - u8 reserved2[4]; -}; - -I40E_CHECK_CMD_LENGTH(i40e_aqc_run_phy_activity); - -/* Set PHY Register command (0x0628) */ -/* Get PHY Register command (0x0629) */ -struct i40e_aqc_phy_register_access { - u8 phy_interface; -#define I40E_AQ_PHY_REG_ACCESS_INTERNAL 0 -#define I40E_AQ_PHY_REG_ACCESS_EXTERNAL 1 -#define I40E_AQ_PHY_REG_ACCESS_EXTERNAL_MODULE 2 - u8 dev_address; - u8 reserved1[2]; - __le32 reg_address; - __le32 reg_value; - u8 reserved2[4]; -}; - -I40E_CHECK_CMD_LENGTH(i40e_aqc_phy_register_access); - -/* NVM Read command (indirect 0x0701) - * NVM Erase commands (direct 0x0702) - * NVM Update commands (indirect 0x0703) - */ -struct i40e_aqc_nvm_update { - u8 command_flags; -#define I40E_AQ_NVM_LAST_CMD 0x01 -#define I40E_AQ_NVM_REARRANGE_TO_FLAT 0x20 -#define I40E_AQ_NVM_REARRANGE_TO_STRUCT 0x40 -#define I40E_AQ_NVM_FLASH_ONLY 0x80 -#define I40E_AQ_NVM_PRESERVATION_FLAGS_SHIFT 1 -#define I40E_AQ_NVM_PRESERVATION_FLAGS_MASK 0x03 -#define I40E_AQ_NVM_PRESERVATION_FLAGS_SELECTED 0x03 -#define I40E_AQ_NVM_PRESERVATION_FLAGS_ALL 0x01 - u8 module_pointer; - __le16 length; - __le32 offset; - __le32 addr_high; - __le32 addr_low; -}; - -I40E_CHECK_CMD_LENGTH(i40e_aqc_nvm_update); - -/* NVM Config Read (indirect 0x0704) */ -struct i40e_aqc_nvm_config_read { - __le16 cmd_flags; -#define I40E_AQ_ANVM_SINGLE_OR_MULTIPLE_FEATURES_MASK 1 -#define I40E_AQ_ANVM_READ_SINGLE_FEATURE 0 -#define I40E_AQ_ANVM_READ_MULTIPLE_FEATURES 1 - __le16 element_count; - __le16 element_id; /* Feature/field ID */ - __le16 element_id_msw; /* MSWord of field ID */ - __le32 address_high; - __le32 address_low; -}; - -I40E_CHECK_CMD_LENGTH(i40e_aqc_nvm_config_read); - -/* NVM Config Write (indirect 0x0705) */ -struct i40e_aqc_nvm_config_write { - __le16 cmd_flags; - __le16 element_count; - u8 reserved[4]; - __le32 address_high; - __le32 address_low; -}; - -I40E_CHECK_CMD_LENGTH(i40e_aqc_nvm_config_write); - -/* Used for 0x0704 as well as for 0x0705 commands */ -#define I40E_AQ_ANVM_FEATURE_OR_IMMEDIATE_SHIFT 1 -#define I40E_AQ_ANVM_FEATURE_OR_IMMEDIATE_MASK \ - BIT(I40E_AQ_ANVM_FEATURE_OR_IMMEDIATE_SHIFT) -#define I40E_AQ_ANVM_FEATURE 0 -#define I40E_AQ_ANVM_IMMEDIATE_FIELD BIT(FEATURE_OR_IMMEDIATE_SHIFT) -struct i40e_aqc_nvm_config_data_feature { - __le16 feature_id; -#define I40E_AQ_ANVM_FEATURE_OPTION_OEM_ONLY 0x01 -#define I40E_AQ_ANVM_FEATURE_OPTION_DWORD_MAP 0x08 -#define I40E_AQ_ANVM_FEATURE_OPTION_POR_CSR 0x10 - __le16 feature_options; - __le16 feature_selection; -}; - -I40E_CHECK_STRUCT_LEN(0x6, i40e_aqc_nvm_config_data_feature); - -struct i40e_aqc_nvm_config_data_immediate_field { - __le32 field_id; - __le32 field_value; - __le16 field_options; - __le16 reserved; -}; - -I40E_CHECK_STRUCT_LEN(0xc, i40e_aqc_nvm_config_data_immediate_field); - -/* OEM Post Update (indirect 0x0720) - * no command data struct used - */ - struct i40e_aqc_nvm_oem_post_update { -#define I40E_AQ_NVM_OEM_POST_UPDATE_EXTERNAL_DATA 0x01 - u8 sel_data; - u8 reserved[7]; -}; - -I40E_CHECK_STRUCT_LEN(0x8, i40e_aqc_nvm_oem_post_update); - -struct i40e_aqc_nvm_oem_post_update_buffer { - u8 str_len; - u8 dev_addr; - __le16 eeprom_addr; - u8 data[36]; -}; - -I40E_CHECK_STRUCT_LEN(0x28, i40e_aqc_nvm_oem_post_update_buffer); - -/* Thermal Sensor (indirect 0x0721) - * read or set thermal sensor configs and values - * takes a sensor and command specific data buffer, not detailed here - */ -struct i40e_aqc_thermal_sensor { - u8 sensor_action; -#define I40E_AQ_THERMAL_SENSOR_READ_CONFIG 0 -#define I40E_AQ_THERMAL_SENSOR_SET_CONFIG 1 -#define I40E_AQ_THERMAL_SENSOR_READ_TEMP 2 - u8 reserved[7]; - __le32 addr_high; - __le32 addr_low; -}; - -I40E_CHECK_CMD_LENGTH(i40e_aqc_thermal_sensor); - -/* Send to PF command (indirect 0x0801) id is only used by PF - * Send to VF command (indirect 0x0802) id is only used by PF - * Send to Peer PF command (indirect 0x0803) - */ -struct i40e_aqc_pf_vf_message { - __le32 id; - u8 reserved[4]; - __le32 addr_high; - __le32 addr_low; -}; - -I40E_CHECK_CMD_LENGTH(i40e_aqc_pf_vf_message); - -/* Alternate structure */ - -/* Direct write (direct 0x0900) - * Direct read (direct 0x0902) - */ -struct i40e_aqc_alternate_write { - __le32 address0; - __le32 data0; - __le32 address1; - __le32 data1; -}; - -I40E_CHECK_CMD_LENGTH(i40e_aqc_alternate_write); - -/* Indirect write (indirect 0x0901) - * Indirect read (indirect 0x0903) - */ - -struct i40e_aqc_alternate_ind_write { - __le32 address; - __le32 length; - __le32 addr_high; - __le32 addr_low; -}; - -I40E_CHECK_CMD_LENGTH(i40e_aqc_alternate_ind_write); - -/* Done alternate write (direct 0x0904) - * uses i40e_aq_desc - */ -struct i40e_aqc_alternate_write_done { - __le16 cmd_flags; -#define I40E_AQ_ALTERNATE_MODE_BIOS_MASK 1 -#define I40E_AQ_ALTERNATE_MODE_BIOS_LEGACY 0 -#define I40E_AQ_ALTERNATE_MODE_BIOS_UEFI 1 -#define I40E_AQ_ALTERNATE_RESET_NEEDED 2 - u8 reserved[14]; -}; - -I40E_CHECK_CMD_LENGTH(i40e_aqc_alternate_write_done); - -/* Set OEM mode (direct 0x0905) */ -struct i40e_aqc_alternate_set_mode { - __le32 mode; -#define I40E_AQ_ALTERNATE_MODE_NONE 0 -#define I40E_AQ_ALTERNATE_MODE_OEM 1 - u8 reserved[12]; -}; - -I40E_CHECK_CMD_LENGTH(i40e_aqc_alternate_set_mode); - -/* Clear port Alternate RAM (direct 0x0906) uses i40e_aq_desc */ - -/* async events 0x10xx */ - -/* Lan Queue Overflow Event (direct, 0x1001) */ -struct i40e_aqc_lan_overflow { - __le32 prtdcb_rupto; - __le32 otx_ctl; - u8 reserved[8]; -}; - -I40E_CHECK_CMD_LENGTH(i40e_aqc_lan_overflow); - -/* Get LLDP MIB (indirect 0x0A00) */ -struct i40e_aqc_lldp_get_mib { - u8 type; - u8 reserved1; -#define I40E_AQ_LLDP_MIB_TYPE_MASK 0x3 -#define I40E_AQ_LLDP_MIB_LOCAL 0x0 -#define I40E_AQ_LLDP_MIB_REMOTE 0x1 -#define I40E_AQ_LLDP_MIB_LOCAL_AND_REMOTE 0x2 -#define I40E_AQ_LLDP_BRIDGE_TYPE_MASK 0xC -#define I40E_AQ_LLDP_BRIDGE_TYPE_SHIFT 0x2 -#define I40E_AQ_LLDP_BRIDGE_TYPE_NEAREST_BRIDGE 0x0 -#define I40E_AQ_LLDP_BRIDGE_TYPE_NON_TPMR 0x1 -#define I40E_AQ_LLDP_TX_SHIFT 0x4 -#define I40E_AQ_LLDP_TX_MASK (0x03 << I40E_AQ_LLDP_TX_SHIFT) -/* TX pause flags use I40E_AQ_LINK_TX_* above */ - __le16 local_len; - __le16 remote_len; - u8 reserved2[2]; - __le32 addr_high; - __le32 addr_low; -}; - -I40E_CHECK_CMD_LENGTH(i40e_aqc_lldp_get_mib); - -/* Configure LLDP MIB Change Event (direct 0x0A01) - * also used for the event (with type in the command field) - */ -struct i40e_aqc_lldp_update_mib { - u8 command; -#define I40E_AQ_LLDP_MIB_UPDATE_ENABLE 0x0 -#define I40E_AQ_LLDP_MIB_UPDATE_DISABLE 0x1 - u8 reserved[7]; - __le32 addr_high; - __le32 addr_low; -}; - -I40E_CHECK_CMD_LENGTH(i40e_aqc_lldp_update_mib); - -/* Add LLDP TLV (indirect 0x0A02) - * Delete LLDP TLV (indirect 0x0A04) - */ -struct i40e_aqc_lldp_add_tlv { - u8 type; /* only nearest bridge and non-TPMR from 0x0A00 */ - u8 reserved1[1]; - __le16 len; - u8 reserved2[4]; - __le32 addr_high; - __le32 addr_low; -}; - -I40E_CHECK_CMD_LENGTH(i40e_aqc_lldp_add_tlv); - -/* Update LLDP TLV (indirect 0x0A03) */ -struct i40e_aqc_lldp_update_tlv { - u8 type; /* only nearest bridge and non-TPMR from 0x0A00 */ - u8 reserved; - __le16 old_len; - __le16 new_offset; - __le16 new_len; - __le32 addr_high; - __le32 addr_low; -}; - -I40E_CHECK_CMD_LENGTH(i40e_aqc_lldp_update_tlv); - -/* Stop LLDP (direct 0x0A05) */ -struct i40e_aqc_lldp_stop { - u8 command; -#define I40E_AQ_LLDP_AGENT_STOP 0x0 -#define I40E_AQ_LLDP_AGENT_SHUTDOWN 0x1 - u8 reserved[15]; -}; - -I40E_CHECK_CMD_LENGTH(i40e_aqc_lldp_stop); - -/* Start LLDP (direct 0x0A06) */ - -struct i40e_aqc_lldp_start { - u8 command; -#define I40E_AQ_LLDP_AGENT_START 0x1 - u8 reserved[15]; -}; - -I40E_CHECK_CMD_LENGTH(i40e_aqc_lldp_start); - -/* Set DCB (direct 0x0303) */ -struct i40e_aqc_set_dcb_parameters { - u8 command; -#define I40E_AQ_DCB_SET_AGENT 0x1 -#define I40E_DCB_VALID 0x1 - u8 valid_flags; - u8 reserved[14]; -}; - -I40E_CHECK_CMD_LENGTH(i40e_aqc_set_dcb_parameters); - -/* Apply MIB changes (0x0A07) - * uses the generic struc as it contains no data - */ - -/* Add Udp Tunnel command and completion (direct 0x0B00) */ -struct i40e_aqc_add_udp_tunnel { - __le16 udp_port; - u8 reserved0[3]; - u8 protocol_type; -#define I40E_AQC_TUNNEL_TYPE_VXLAN 0x00 -#define I40E_AQC_TUNNEL_TYPE_NGE 0x01 -#define I40E_AQC_TUNNEL_TYPE_TEREDO 0x10 -#define I40E_AQC_TUNNEL_TYPE_VXLAN_GPE 0x11 - u8 reserved1[10]; -}; - -I40E_CHECK_CMD_LENGTH(i40e_aqc_add_udp_tunnel); - -struct i40e_aqc_add_udp_tunnel_completion { - __le16 udp_port; - u8 filter_entry_index; - u8 multiple_pfs; -#define I40E_AQC_SINGLE_PF 0x0 -#define I40E_AQC_MULTIPLE_PFS 0x1 - u8 total_filters; - u8 reserved[11]; -}; - -I40E_CHECK_CMD_LENGTH(i40e_aqc_add_udp_tunnel_completion); - -/* remove UDP Tunnel command (0x0B01) */ -struct i40e_aqc_remove_udp_tunnel { - u8 reserved[2]; - u8 index; /* 0 to 15 */ - u8 reserved2[13]; -}; - -I40E_CHECK_CMD_LENGTH(i40e_aqc_remove_udp_tunnel); - -struct i40e_aqc_del_udp_tunnel_completion { - __le16 udp_port; - u8 index; /* 0 to 15 */ - u8 multiple_pfs; - u8 total_filters_used; - u8 reserved1[11]; -}; - -I40E_CHECK_CMD_LENGTH(i40e_aqc_del_udp_tunnel_completion); - -struct i40e_aqc_get_set_rss_key { -#define I40E_AQC_SET_RSS_KEY_VSI_VALID BIT(15) -#define I40E_AQC_SET_RSS_KEY_VSI_ID_SHIFT 0 -#define I40E_AQC_SET_RSS_KEY_VSI_ID_MASK (0x3FF << \ - I40E_AQC_SET_RSS_KEY_VSI_ID_SHIFT) - __le16 vsi_id; - u8 reserved[6]; - __le32 addr_high; - __le32 addr_low; -}; - -I40E_CHECK_CMD_LENGTH(i40e_aqc_get_set_rss_key); - -struct i40e_aqc_get_set_rss_key_data { - u8 standard_rss_key[0x28]; - u8 extended_hash_key[0xc]; -}; - -I40E_CHECK_STRUCT_LEN(0x34, i40e_aqc_get_set_rss_key_data); - -struct i40e_aqc_get_set_rss_lut { -#define I40E_AQC_SET_RSS_LUT_VSI_VALID BIT(15) -#define I40E_AQC_SET_RSS_LUT_VSI_ID_SHIFT 0 -#define I40E_AQC_SET_RSS_LUT_VSI_ID_MASK (0x3FF << \ - I40E_AQC_SET_RSS_LUT_VSI_ID_SHIFT) - __le16 vsi_id; -#define I40E_AQC_SET_RSS_LUT_TABLE_TYPE_SHIFT 0 -#define I40E_AQC_SET_RSS_LUT_TABLE_TYPE_MASK \ - BIT(I40E_AQC_SET_RSS_LUT_TABLE_TYPE_SHIFT) - -#define I40E_AQC_SET_RSS_LUT_TABLE_TYPE_VSI 0 -#define I40E_AQC_SET_RSS_LUT_TABLE_TYPE_PF 1 - __le16 flags; - u8 reserved[4]; - __le32 addr_high; - __le32 addr_low; -}; - -I40E_CHECK_CMD_LENGTH(i40e_aqc_get_set_rss_lut); - -/* tunnel key structure 0x0B10 */ - -struct i40e_aqc_tunnel_key_structure_A0 { - __le16 key1_off; - __le16 key1_len; - __le16 key2_off; - __le16 key2_len; - __le16 flags; -#define I40E_AQC_TUNNEL_KEY_STRUCT_OVERRIDE 0x01 -/* response flags */ -#define I40E_AQC_TUNNEL_KEY_STRUCT_SUCCESS 0x01 -#define I40E_AQC_TUNNEL_KEY_STRUCT_MODIFIED 0x02 -#define I40E_AQC_TUNNEL_KEY_STRUCT_OVERRIDDEN 0x03 - u8 resreved[6]; -}; - -I40E_CHECK_CMD_LENGTH(i40e_aqc_tunnel_key_structure_A0); - -struct i40e_aqc_tunnel_key_structure { - u8 key1_off; - u8 key2_off; - u8 key1_len; /* 0 to 15 */ - u8 key2_len; /* 0 to 15 */ - u8 flags; -#define I40E_AQC_TUNNEL_KEY_STRUCT_OVERRIDE 0x01 -/* response flags */ -#define I40E_AQC_TUNNEL_KEY_STRUCT_SUCCESS 0x01 -#define I40E_AQC_TUNNEL_KEY_STRUCT_MODIFIED 0x02 -#define I40E_AQC_TUNNEL_KEY_STRUCT_OVERRIDDEN 0x03 - u8 network_key_index; -#define I40E_AQC_NETWORK_KEY_INDEX_VXLAN 0x0 -#define I40E_AQC_NETWORK_KEY_INDEX_NGE 0x1 -#define I40E_AQC_NETWORK_KEY_INDEX_FLEX_MAC_IN_UDP 0x2 -#define I40E_AQC_NETWORK_KEY_INDEX_GRE 0x3 - u8 reserved[10]; -}; - -I40E_CHECK_CMD_LENGTH(i40e_aqc_tunnel_key_structure); - -/* OEM mode commands (direct 0xFE0x) */ -struct i40e_aqc_oem_param_change { - __le32 param_type; -#define I40E_AQ_OEM_PARAM_TYPE_PF_CTL 0 -#define I40E_AQ_OEM_PARAM_TYPE_BW_CTL 1 -#define I40E_AQ_OEM_PARAM_MAC 2 - __le32 param_value1; - __le16 param_value2; - u8 reserved[6]; -}; - -I40E_CHECK_CMD_LENGTH(i40e_aqc_oem_param_change); - -struct i40e_aqc_oem_state_change { - __le32 state; -#define I40E_AQ_OEM_STATE_LINK_DOWN 0x0 -#define I40E_AQ_OEM_STATE_LINK_UP 0x1 - u8 reserved[12]; -}; - -I40E_CHECK_CMD_LENGTH(i40e_aqc_oem_state_change); - -/* Initialize OCSD (0xFE02, direct) */ -struct i40e_aqc_opc_oem_ocsd_initialize { - u8 type_status; - u8 reserved1[3]; - __le32 ocsd_memory_block_addr_high; - __le32 ocsd_memory_block_addr_low; - __le32 requested_update_interval; -}; - -I40E_CHECK_CMD_LENGTH(i40e_aqc_opc_oem_ocsd_initialize); - -/* Initialize OCBB (0xFE03, direct) */ -struct i40e_aqc_opc_oem_ocbb_initialize { - u8 type_status; - u8 reserved1[3]; - __le32 ocbb_memory_block_addr_high; - __le32 ocbb_memory_block_addr_low; - u8 reserved2[4]; -}; - -I40E_CHECK_CMD_LENGTH(i40e_aqc_opc_oem_ocbb_initialize); - -/* debug commands */ - -/* get device id (0xFF00) uses the generic structure */ - -/* set test more (0xFF01, internal) */ - -struct i40e_acq_set_test_mode { - u8 mode; -#define I40E_AQ_TEST_PARTIAL 0 -#define I40E_AQ_TEST_FULL 1 -#define I40E_AQ_TEST_NVM 2 - u8 reserved[3]; - u8 command; -#define I40E_AQ_TEST_OPEN 0 -#define I40E_AQ_TEST_CLOSE 1 -#define I40E_AQ_TEST_INC 2 - u8 reserved2[3]; - __le32 address_high; - __le32 address_low; -}; - -I40E_CHECK_CMD_LENGTH(i40e_acq_set_test_mode); - -/* Debug Read Register command (0xFF03) - * Debug Write Register command (0xFF04) - */ -struct i40e_aqc_debug_reg_read_write { - __le32 reserved; - __le32 address; - __le32 value_high; - __le32 value_low; -}; - -I40E_CHECK_CMD_LENGTH(i40e_aqc_debug_reg_read_write); - -/* Scatter/gather Reg Read (indirect 0xFF05) - * Scatter/gather Reg Write (indirect 0xFF06) - */ - -/* i40e_aq_desc is used for the command */ -struct i40e_aqc_debug_reg_sg_element_data { - __le32 address; - __le32 value; -}; - -/* Debug Modify register (direct 0xFF07) */ -struct i40e_aqc_debug_modify_reg { - __le32 address; - __le32 value; - __le32 clear_mask; - __le32 set_mask; -}; - -I40E_CHECK_CMD_LENGTH(i40e_aqc_debug_modify_reg); - -/* dump internal data (0xFF08, indirect) */ - -#define I40E_AQ_CLUSTER_ID_AUX 0 -#define I40E_AQ_CLUSTER_ID_SWITCH_FLU 1 -#define I40E_AQ_CLUSTER_ID_TXSCHED 2 -#define I40E_AQ_CLUSTER_ID_HMC 3 -#define I40E_AQ_CLUSTER_ID_MAC0 4 -#define I40E_AQ_CLUSTER_ID_MAC1 5 -#define I40E_AQ_CLUSTER_ID_MAC2 6 -#define I40E_AQ_CLUSTER_ID_MAC3 7 -#define I40E_AQ_CLUSTER_ID_DCB 8 -#define I40E_AQ_CLUSTER_ID_EMP_MEM 9 -#define I40E_AQ_CLUSTER_ID_PKT_BUF 10 -#define I40E_AQ_CLUSTER_ID_ALTRAM 11 - -struct i40e_aqc_debug_dump_internals { - u8 cluster_id; - u8 table_id; - __le16 data_size; - __le32 idx; - __le32 address_high; - __le32 address_low; -}; - -I40E_CHECK_CMD_LENGTH(i40e_aqc_debug_dump_internals); - -struct i40e_aqc_debug_modify_internals { - u8 cluster_id; - u8 cluster_specific_params[7]; - __le32 address_high; - __le32 address_low; -}; - -I40E_CHECK_CMD_LENGTH(i40e_aqc_debug_modify_internals); - -#endif /* _I40E_ADMINQ_CMD_H_ */ diff --git a/drivers/net/ethernet/intel/i40evf/i40e_alloc.h b/drivers/net/ethernet/intel/i40evf/i40e_alloc.h deleted file mode 100644 index cb8689222c8b..000000000000 --- a/drivers/net/ethernet/intel/i40evf/i40e_alloc.h +++ /dev/null @@ -1,35 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright(c) 2013 - 2018 Intel Corporation. */ - -#ifndef _I40E_ALLOC_H_ -#define _I40E_ALLOC_H_ - -struct i40e_hw; - -/* Memory allocation types */ -enum i40e_memory_type { - i40e_mem_arq_buf = 0, /* ARQ indirect command buffer */ - i40e_mem_asq_buf = 1, - i40e_mem_atq_buf = 2, /* ATQ indirect command buffer */ - i40e_mem_arq_ring = 3, /* ARQ descriptor ring */ - i40e_mem_atq_ring = 4, /* ATQ descriptor ring */ - i40e_mem_pd = 5, /* Page Descriptor */ - i40e_mem_bp = 6, /* Backing Page - 4KB */ - i40e_mem_bp_jumbo = 7, /* Backing Page - > 4KB */ - i40e_mem_reserved -}; - -/* prototype for functions used for dynamic memory allocation */ -i40e_status i40e_allocate_dma_mem(struct i40e_hw *hw, - struct i40e_dma_mem *mem, - enum i40e_memory_type type, - u64 size, u32 alignment); -i40e_status i40e_free_dma_mem(struct i40e_hw *hw, - struct i40e_dma_mem *mem); -i40e_status i40e_allocate_virt_mem(struct i40e_hw *hw, - struct i40e_virt_mem *mem, - u32 size); -i40e_status i40e_free_virt_mem(struct i40e_hw *hw, - struct i40e_virt_mem *mem); - -#endif /* _I40E_ALLOC_H_ */ diff --git a/drivers/net/ethernet/intel/i40evf/i40e_common.c b/drivers/net/ethernet/intel/i40evf/i40e_common.c deleted file mode 100644 index eea280ba411e..000000000000 --- a/drivers/net/ethernet/intel/i40evf/i40e_common.c +++ /dev/null @@ -1,1320 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -/* Copyright(c) 2013 - 2018 Intel Corporation. */ - -#include "i40e_type.h" -#include "i40e_adminq.h" -#include "i40e_prototype.h" -#include <linux/avf/virtchnl.h> - -/** - * i40e_set_mac_type - Sets MAC type - * @hw: pointer to the HW structure - * - * This function sets the mac type of the adapter based on the - * vendor ID and device ID stored in the hw structure. - **/ -i40e_status i40e_set_mac_type(struct i40e_hw *hw) -{ - i40e_status status = 0; - - if (hw->vendor_id == PCI_VENDOR_ID_INTEL) { - switch (hw->device_id) { - case I40E_DEV_ID_SFP_XL710: - case I40E_DEV_ID_QEMU: - case I40E_DEV_ID_KX_B: - case I40E_DEV_ID_KX_C: - case I40E_DEV_ID_QSFP_A: - case I40E_DEV_ID_QSFP_B: - case I40E_DEV_ID_QSFP_C: - case I40E_DEV_ID_10G_BASE_T: - case I40E_DEV_ID_10G_BASE_T4: - case I40E_DEV_ID_20G_KR2: - case I40E_DEV_ID_20G_KR2_A: - case I40E_DEV_ID_25G_B: - case I40E_DEV_ID_25G_SFP28: - hw->mac.type = I40E_MAC_XL710; - break; - case I40E_DEV_ID_SFP_X722: - case I40E_DEV_ID_1G_BASE_T_X722: - case I40E_DEV_ID_10G_BASE_T_X722: - case I40E_DEV_ID_SFP_I_X722: - hw->mac.type = I40E_MAC_X722; - break; - case I40E_DEV_ID_X722_VF: - hw->mac.type = I40E_MAC_X722_VF; - break; - case I40E_DEV_ID_VF: - case I40E_DEV_ID_VF_HV: - case I40E_DEV_ID_ADAPTIVE_VF: - hw->mac.type = I40E_MAC_VF; - break; - default: - hw->mac.type = I40E_MAC_GENERIC; - break; - } - } else { - status = I40E_ERR_DEVICE_NOT_SUPPORTED; - } - - hw_dbg(hw, "i40e_set_mac_type found mac: %d, returns: %d\n", - hw->mac.type, status); - return status; -} - -/** - * i40evf_aq_str - convert AQ err code to a string - * @hw: pointer to the HW structure - * @aq_err: the AQ error code to convert - **/ -const char *i40evf_aq_str(struct i40e_hw *hw, enum i40e_admin_queue_err aq_err) -{ - switch (aq_err) { - case I40E_AQ_RC_OK: - return "OK"; - case I40E_AQ_RC_EPERM: - return "I40E_AQ_RC_EPERM"; - case I40E_AQ_RC_ENOENT: - return "I40E_AQ_RC_ENOENT"; - case I40E_AQ_RC_ESRCH: - return "I40E_AQ_RC_ESRCH"; - case I40E_AQ_RC_EINTR: - return "I40E_AQ_RC_EINTR"; - case I40E_AQ_RC_EIO: - return "I40E_AQ_RC_EIO"; - case I40E_AQ_RC_ENXIO: - return "I40E_AQ_RC_ENXIO"; - case I40E_AQ_RC_E2BIG: - return "I40E_AQ_RC_E2BIG"; - case I40E_AQ_RC_EAGAIN: - return "I40E_AQ_RC_EAGAIN"; - case I40E_AQ_RC_ENOMEM: - return "I40E_AQ_RC_ENOMEM"; - case I40E_AQ_RC_EACCES: - return "I40E_AQ_RC_EACCES"; - case I40E_AQ_RC_EFAULT: - return "I40E_AQ_RC_EFAULT"; - case I40E_AQ_RC_EBUSY: - return "I40E_AQ_RC_EBUSY"; - case I40E_AQ_RC_EEXIST: - return "I40E_AQ_RC_EEXIST"; - case I40E_AQ_RC_EINVAL: - return "I40E_AQ_RC_EINVAL"; - case I40E_AQ_RC_ENOTTY: - return "I40E_AQ_RC_ENOTTY"; - case I40E_AQ_RC_ENOSPC: - return "I40E_AQ_RC_ENOSPC"; - case I40E_AQ_RC_ENOSYS: - return "I40E_AQ_RC_ENOSYS"; - case I40E_AQ_RC_ERANGE: - return "I40E_AQ_RC_ERANGE"; - case I40E_AQ_RC_EFLUSHED: - return "I40E_AQ_RC_EFLUSHED"; - case I40E_AQ_RC_BAD_ADDR: - return "I40E_AQ_RC_BAD_ADDR"; - case I40E_AQ_RC_EMODE: - return "I40E_AQ_RC_EMODE"; - case I40E_AQ_RC_EFBIG: - return "I40E_AQ_RC_EFBIG"; - } - - snprintf(hw->err_str, sizeof(hw->err_str), "%d", aq_err); - return hw->err_str; -} - -/** - * i40evf_stat_str - convert status err code to a string - * @hw: pointer to the HW structure - * @stat_err: the status error code to convert - **/ -const char *i40evf_stat_str(struct i40e_hw *hw, i40e_status stat_err) -{ - switch (stat_err) { - case 0: - return "OK"; - case I40E_ERR_NVM: - return "I40E_ERR_NVM"; - case I40E_ERR_NVM_CHECKSUM: - return "I40E_ERR_NVM_CHECKSUM"; - case I40E_ERR_PHY: - return "I40E_ERR_PHY"; - case I40E_ERR_CONFIG: - return "I40E_ERR_CONFIG"; - case I40E_ERR_PARAM: - return "I40E_ERR_PARAM"; - case I40E_ERR_MAC_TYPE: - return "I40E_ERR_MAC_TYPE"; - case I40E_ERR_UNKNOWN_PHY: - return "I40E_ERR_UNKNOWN_PHY"; - case I40E_ERR_LINK_SETUP: - return "I40E_ERR_LINK_SETUP"; - case I40E_ERR_ADAPTER_STOPPED: - return "I40E_ERR_ADAPTER_STOPPED"; - case I40E_ERR_INVALID_MAC_ADDR: - return "I40E_ERR_INVALID_MAC_ADDR"; - case I40E_ERR_DEVICE_NOT_SUPPORTED: - return "I40E_ERR_DEVICE_NOT_SUPPORTED"; - case I40E_ERR_MASTER_REQUESTS_PENDING: - return "I40E_ERR_MASTER_REQUESTS_PENDING"; - case I40E_ERR_INVALID_LINK_SETTINGS: - return "I40E_ERR_INVALID_LINK_SETTINGS"; - case I40E_ERR_AUTONEG_NOT_COMPLETE: - return "I40E_ERR_AUTONEG_NOT_COMPLETE"; - case I40E_ERR_RESET_FAILED: - return "I40E_ERR_RESET_FAILED"; - case I40E_ERR_SWFW_SYNC: - return "I40E_ERR_SWFW_SYNC"; - case I40E_ERR_NO_AVAILABLE_VSI: - return "I40E_ERR_NO_AVAILABLE_VSI"; - case I40E_ERR_NO_MEMORY: - return "I40E_ERR_NO_MEMORY"; - case I40E_ERR_BAD_PTR: - return "I40E_ERR_BAD_PTR"; - case I40E_ERR_RING_FULL: - return "I40E_ERR_RING_FULL"; - case I40E_ERR_INVALID_PD_ID: - return "I40E_ERR_INVALID_PD_ID"; - case I40E_ERR_INVALID_QP_ID: - return "I40E_ERR_INVALID_QP_ID"; - case I40E_ERR_INVALID_CQ_ID: - return "I40E_ERR_INVALID_CQ_ID"; - case I40E_ERR_INVALID_CEQ_ID: - return "I40E_ERR_INVALID_CEQ_ID"; - case I40E_ERR_INVALID_AEQ_ID: - return "I40E_ERR_INVALID_AEQ_ID"; - case I40E_ERR_INVALID_SIZE: - return "I40E_ERR_INVALID_SIZE"; - case I40E_ERR_INVALID_ARP_INDEX: - return "I40E_ERR_INVALID_ARP_INDEX"; - case I40E_ERR_INVALID_FPM_FUNC_ID: - return "I40E_ERR_INVALID_FPM_FUNC_ID"; - case I40E_ERR_QP_INVALID_MSG_SIZE: - return "I40E_ERR_QP_INVALID_MSG_SIZE"; - case I40E_ERR_QP_TOOMANY_WRS_POSTED: - return "I40E_ERR_QP_TOOMANY_WRS_POSTED"; - case I40E_ERR_INVALID_FRAG_COUNT: - return "I40E_ERR_INVALID_FRAG_COUNT"; - case I40E_ERR_QUEUE_EMPTY: - return "I40E_ERR_QUEUE_EMPTY"; - case I40E_ERR_INVALID_ALIGNMENT: - return "I40E_ERR_INVALID_ALIGNMENT"; - case I40E_ERR_FLUSHED_QUEUE: - return "I40E_ERR_FLUSHED_QUEUE"; - case I40E_ERR_INVALID_PUSH_PAGE_INDEX: - return "I40E_ERR_INVALID_PUSH_PAGE_INDEX"; - case I40E_ERR_INVALID_IMM_DATA_SIZE: - return "I40E_ERR_INVALID_IMM_DATA_SIZE"; - case I40E_ERR_TIMEOUT: - return "I40E_ERR_TIMEOUT"; - case I40E_ERR_OPCODE_MISMATCH: - return "I40E_ERR_OPCODE_MISMATCH"; - case I40E_ERR_CQP_COMPL_ERROR: - return "I40E_ERR_CQP_COMPL_ERROR"; - case I40E_ERR_INVALID_VF_ID: - return "I40E_ERR_INVALID_VF_ID"; - case I40E_ERR_INVALID_HMCFN_ID: - return "I40E_ERR_INVALID_HMCFN_ID"; - case I40E_ERR_BACKING_PAGE_ERROR: - return "I40E_ERR_BACKING_PAGE_ERROR"; - case I40E_ERR_NO_PBLCHUNKS_AVAILABLE: - return "I40E_ERR_NO_PBLCHUNKS_AVAILABLE"; - case I40E_ERR_INVALID_PBLE_INDEX: - return "I40E_ERR_INVALID_PBLE_INDEX"; - case I40E_ERR_INVALID_SD_INDEX: - return "I40E_ERR_INVALID_SD_INDEX"; - case I40E_ERR_INVALID_PAGE_DESC_INDEX: - return "I40E_ERR_INVALID_PAGE_DESC_INDEX"; - case I40E_ERR_INVALID_SD_TYPE: - return "I40E_ERR_INVALID_SD_TYPE"; - case I40E_ERR_MEMCPY_FAILED: - return "I40E_ERR_MEMCPY_FAILED"; - case I40E_ERR_INVALID_HMC_OBJ_INDEX: - return "I40E_ERR_INVALID_HMC_OBJ_INDEX"; - case I40E_ERR_INVALID_HMC_OBJ_COUNT: - return "I40E_ERR_INVALID_HMC_OBJ_COUNT"; - case I40E_ERR_INVALID_SRQ_ARM_LIMIT: - return "I40E_ERR_INVALID_SRQ_ARM_LIMIT"; - case I40E_ERR_SRQ_ENABLED: - return "I40E_ERR_SRQ_ENABLED"; - case I40E_ERR_ADMIN_QUEUE_ERROR: - return "I40E_ERR_ADMIN_QUEUE_ERROR"; - case I40E_ERR_ADMIN_QUEUE_TIMEOUT: - return "I40E_ERR_ADMIN_QUEUE_TIMEOUT"; - case I40E_ERR_BUF_TOO_SHORT: - return "I40E_ERR_BUF_TOO_SHORT"; - case I40E_ERR_ADMIN_QUEUE_FULL: - return "I40E_ERR_ADMIN_QUEUE_FULL"; - case I40E_ERR_ADMIN_QUEUE_NO_WORK: - return "I40E_ERR_ADMIN_QUEUE_NO_WORK"; - case I40E_ERR_BAD_IWARP_CQE: - return "I40E_ERR_BAD_IWARP_CQE"; - case I40E_ERR_NVM_BLANK_MODE: - return "I40E_ERR_NVM_BLANK_MODE"; - case I40E_ERR_NOT_IMPLEMENTED: - return "I40E_ERR_NOT_IMPLEMENTED"; - case I40E_ERR_PE_DOORBELL_NOT_ENABLED: - return "I40E_ERR_PE_DOORBELL_NOT_ENABLED"; - case I40E_ERR_DIAG_TEST_FAILED: - return "I40E_ERR_DIAG_TEST_FAILED"; - case I40E_ERR_NOT_READY: - return "I40E_ERR_NOT_READY"; - case I40E_NOT_SUPPORTED: - return "I40E_NOT_SUPPORTED"; - case I40E_ERR_FIRMWARE_API_VERSION: - return "I40E_ERR_FIRMWARE_API_VERSION"; - case I40E_ERR_ADMIN_QUEUE_CRITICAL_ERROR: - return "I40E_ERR_ADMIN_QUEUE_CRITICAL_ERROR"; - } - - snprintf(hw->err_str, sizeof(hw->err_str), "%d", stat_err); - return hw->err_str; -} - -/** - * i40evf_debug_aq - * @hw: debug mask related to admin queue - * @mask: debug mask - * @desc: pointer to admin queue descriptor - * @buffer: pointer to command buffer - * @buf_len: max length of buffer - * - * Dumps debug log about adminq command with descriptor contents. - **/ -void i40evf_debug_aq(struct i40e_hw *hw, enum i40e_debug_mask mask, void *desc, - void *buffer, u16 buf_len) -{ - struct i40e_aq_desc *aq_desc = (struct i40e_aq_desc *)desc; - u8 *buf = (u8 *)buffer; - - if ((!(mask & hw->debug_mask)) || (desc == NULL)) - return; - - i40e_debug(hw, mask, - "AQ CMD: opcode 0x%04X, flags 0x%04X, datalen 0x%04X, retval 0x%04X\n", - le16_to_cpu(aq_desc->opcode), - le16_to_cpu(aq_desc->flags), - le16_to_cpu(aq_desc->datalen), - le16_to_cpu(aq_desc->retval)); - i40e_debug(hw, mask, "\tcookie (h,l) 0x%08X 0x%08X\n", - le32_to_cpu(aq_desc->cookie_high), - le32_to_cpu(aq_desc->cookie_low)); - i40e_debug(hw, mask, "\tparam (0,1) 0x%08X 0x%08X\n", - le32_to_cpu(aq_desc->params.internal.param0), - le32_to_cpu(aq_desc->params.internal.param1)); - i40e_debug(hw, mask, "\taddr (h,l) 0x%08X 0x%08X\n", - le32_to_cpu(aq_desc->params.external.addr_high), - le32_to_cpu(aq_desc->params.external.addr_low)); - - if ((buffer != NULL) && (aq_desc->datalen != 0)) { - u16 len = le16_to_cpu(aq_desc->datalen); - - i40e_debug(hw, mask, "AQ CMD Buffer:\n"); - if (buf_len < len) - len = buf_len; - /* write the full 16-byte chunks */ - if (hw->debug_mask & mask) { - char prefix[27]; - - snprintf(prefix, sizeof(prefix), - "i40evf %02x:%02x.%x: \t0x", - hw->bus.bus_id, - hw->bus.device, - hw->bus.func); - - print_hex_dump(KERN_INFO, prefix, DUMP_PREFIX_OFFSET, - 16, 1, buf, len, false); - } - } -} - -/** - * i40evf_check_asq_alive - * @hw: pointer to the hw struct - * - * Returns true if Queue is enabled else false. - **/ -bool i40evf_check_asq_alive(struct i40e_hw *hw) -{ - if (hw->aq.asq.len) - return !!(rd32(hw, hw->aq.asq.len) & - I40E_VF_ATQLEN1_ATQENABLE_MASK); - else - return false; -} - -/** - * i40evf_aq_queue_shutdown - * @hw: pointer to the hw struct - * @unloading: is the driver unloading itself - * - * Tell the Firmware that we're shutting down the AdminQ and whether - * or not the driver is unloading as well. - **/ -i40e_status i40evf_aq_queue_shutdown(struct i40e_hw *hw, - bool unloading) -{ - struct i40e_aq_desc desc; - struct i40e_aqc_queue_shutdown *cmd = - (struct i40e_aqc_queue_shutdown *)&desc.params.raw; - i40e_status status; - - i40evf_fill_default_direct_cmd_desc(&desc, - i40e_aqc_opc_queue_shutdown); - - if (unloading) - cmd->driver_unloading = cpu_to_le32(I40E_AQ_DRIVER_UNLOADING); - status = i40evf_asq_send_command(hw, &desc, NULL, 0, NULL); - - return status; -} - -/** - * i40e_aq_get_set_rss_lut - * @hw: pointer to the hardware structure - * @vsi_id: vsi fw index - * @pf_lut: for PF table set true, for VSI table set false - * @lut: pointer to the lut buffer provided by the caller - * @lut_size: size of the lut buffer - * @set: set true to set the table, false to get the table - * - * Internal function to get or set RSS look up table - **/ -static i40e_status i40e_aq_get_set_rss_lut(struct i40e_hw *hw, - u16 vsi_id, bool pf_lut, - u8 *lut, u16 lut_size, - bool set) -{ - i40e_status status; - struct i40e_aq_desc desc; - struct i40e_aqc_get_set_rss_lut *cmd_resp = - (struct i40e_aqc_get_set_rss_lut *)&desc.params.raw; - - if (set) - i40evf_fill_default_direct_cmd_desc(&desc, - i40e_aqc_opc_set_rss_lut); - else - i40evf_fill_default_direct_cmd_desc(&desc, - i40e_aqc_opc_get_rss_lut); - - /* Indirect command */ - desc.flags |= cpu_to_le16((u16)I40E_AQ_FLAG_BUF); - desc.flags |= cpu_to_le16((u16)I40E_AQ_FLAG_RD); - - cmd_resp->vsi_id = - cpu_to_le16((u16)((vsi_id << - I40E_AQC_SET_RSS_LUT_VSI_ID_SHIFT) & - I40E_AQC_SET_RSS_LUT_VSI_ID_MASK)); - cmd_resp->vsi_id |= cpu_to_le16((u16)I40E_AQC_SET_RSS_LUT_VSI_VALID); - - if (pf_lut) - cmd_resp->flags |= cpu_to_le16((u16) - ((I40E_AQC_SET_RSS_LUT_TABLE_TYPE_PF << - I40E_AQC_SET_RSS_LUT_TABLE_TYPE_SHIFT) & - I40E_AQC_SET_RSS_LUT_TABLE_TYPE_MASK)); - else - cmd_resp->flags |= cpu_to_le16((u16) - ((I40E_AQC_SET_RSS_LUT_TABLE_TYPE_VSI << - I40E_AQC_SET_RSS_LUT_TABLE_TYPE_SHIFT) & - I40E_AQC_SET_RSS_LUT_TABLE_TYPE_MASK)); - - status = i40evf_asq_send_command(hw, &desc, lut, lut_size, NULL); - - return status; -} - -/** - * i40evf_aq_get_rss_lut - * @hw: pointer to the hardware structure - * @vsi_id: vsi fw index - * @pf_lut: for PF table set true, for VSI table set false - * @lut: pointer to the lut buffer provided by the caller - * @lut_size: size of the lut buffer - * - * get the RSS lookup table, PF or VSI type - **/ -i40e_status i40evf_aq_get_rss_lut(struct i40e_hw *hw, u16 vsi_id, - bool pf_lut, u8 *lut, u16 lut_size) -{ - return i40e_aq_get_set_rss_lut(hw, vsi_id, pf_lut, lut, lut_size, - false); -} - -/** - * i40evf_aq_set_rss_lut - * @hw: pointer to the hardware structure - * @vsi_id: vsi fw index - * @pf_lut: for PF table set true, for VSI table set false - * @lut: pointer to the lut buffer provided by the caller - * @lut_size: size of the lut buffer - * - * set the RSS lookup table, PF or VSI type - **/ -i40e_status i40evf_aq_set_rss_lut(struct i40e_hw *hw, u16 vsi_id, - bool pf_lut, u8 *lut, u16 lut_size) -{ - return i40e_aq_get_set_rss_lut(hw, vsi_id, pf_lut, lut, lut_size, true); -} - -/** - * i40e_aq_get_set_rss_key - * @hw: pointer to the hw struct - * @vsi_id: vsi fw index - * @key: pointer to key info struct - * @set: set true to set the key, false to get the key - * - * get the RSS key per VSI - **/ -static i40e_status i40e_aq_get_set_rss_key(struct i40e_hw *hw, - u16 vsi_id, - struct i40e_aqc_get_set_rss_key_data *key, - bool set) -{ - i40e_status status; - struct i40e_aq_desc desc; - struct i40e_aqc_get_set_rss_key *cmd_resp = - (struct i40e_aqc_get_set_rss_key *)&desc.params.raw; - u16 key_size = sizeof(struct i40e_aqc_get_set_rss_key_data); - - if (set) - i40evf_fill_default_direct_cmd_desc(&desc, - i40e_aqc_opc_set_rss_key); - else - i40evf_fill_default_direct_cmd_desc(&desc, - i40e_aqc_opc_get_rss_key); - - /* Indirect command */ - desc.flags |= cpu_to_le16((u16)I40E_AQ_FLAG_BUF); - desc.flags |= cpu_to_le16((u16)I40E_AQ_FLAG_RD); - - cmd_resp->vsi_id = - cpu_to_le16((u16)((vsi_id << - I40E_AQC_SET_RSS_KEY_VSI_ID_SHIFT) & - I40E_AQC_SET_RSS_KEY_VSI_ID_MASK)); - cmd_resp->vsi_id |= cpu_to_le16((u16)I40E_AQC_SET_RSS_KEY_VSI_VALID); - - status = i40evf_asq_send_command(hw, &desc, key, key_size, NULL); - - return status; -} - -/** - * i40evf_aq_get_rss_key - * @hw: pointer to the hw struct - * @vsi_id: vsi fw index - * @key: pointer to key info struct - * - **/ -i40e_status i40evf_aq_get_rss_key(struct i40e_hw *hw, - u16 vsi_id, - struct i40e_aqc_get_set_rss_key_data *key) -{ - return i40e_aq_get_set_rss_key(hw, vsi_id, key, false); -} - -/** - * i40evf_aq_set_rss_key - * @hw: pointer to the hw struct - * @vsi_id: vsi fw index - * @key: pointer to key info struct - * - * set the RSS key per VSI - **/ -i40e_status i40evf_aq_set_rss_key(struct i40e_hw *hw, - u16 vsi_id, - struct i40e_aqc_get_set_rss_key_data *key) -{ - return i40e_aq_get_set_rss_key(hw, vsi_id, key, true); -} - - -/* The i40evf_ptype_lookup table is used to convert from the 8-bit ptype in the - * hardware to a bit-field that can be used by SW to more easily determine the - * packet type. - * - * Macros are used to shorten the table lines and make this table human - * readable. - * - * We store the PTYPE in the top byte of the bit field - this is just so that - * we can check that the table doesn't have a row missing, as the index into - * the table should be the PTYPE. - * - * Typical work flow: - * - * IF NOT i40evf_ptype_lookup[ptype].known - * THEN - * Packet is unknown - * ELSE IF i40evf_ptype_lookup[ptype].outer_ip == I40E_RX_PTYPE_OUTER_IP - * Use the rest of the fields to look at the tunnels, inner protocols, etc - * ELSE - * Use the enum i40e_rx_l2_ptype to decode the packet type - * ENDIF - */ - -/* macro to make the table lines short */ -#define I40E_PTT(PTYPE, OUTER_IP, OUTER_IP_VER, OUTER_FRAG, T, TE, TEF, I, PL)\ - { PTYPE, \ - 1, \ - I40E_RX_PTYPE_OUTER_##OUTER_IP, \ - I40E_RX_PTYPE_OUTER_##OUTER_IP_VER, \ - I40E_RX_PTYPE_##OUTER_FRAG, \ - I40E_RX_PTYPE_TUNNEL_##T, \ - I40E_RX_PTYPE_TUNNEL_END_##TE, \ - I40E_RX_PTYPE_##TEF, \ - I40E_RX_PTYPE_INNER_PROT_##I, \ - I40E_RX_PTYPE_PAYLOAD_LAYER_##PL } - -#define I40E_PTT_UNUSED_ENTRY(PTYPE) \ - { PTYPE, 0, 0, 0, 0, 0, 0, 0, 0, 0 } - -/* shorter macros makes the table fit but are terse */ -#define I40E_RX_PTYPE_NOF I40E_RX_PTYPE_NOT_FRAG -#define I40E_RX_PTYPE_FRG I40E_RX_PTYPE_FRAG -#define I40E_RX_PTYPE_INNER_PROT_TS I40E_RX_PTYPE_INNER_PROT_TIMESYNC - -/* Lookup table mapping the HW PTYPE to the bit field for decoding */ -struct i40e_rx_ptype_decoded i40evf_ptype_lookup[] = { - /* L2 Packet types */ - I40E_PTT_UNUSED_ENTRY(0), - I40E_PTT(1, L2, NONE, NOF, NONE, NONE, NOF, NONE, PAY2), - I40E_PTT(2, L2, NONE, NOF, NONE, NONE, NOF, TS, PAY2), - I40E_PTT(3, L2, NONE, NOF, NONE, NONE, NOF, NONE, PAY2), - I40E_PTT_UNUSED_ENTRY(4), - I40E_PTT_UNUSED_ENTRY(5), - I40E_PTT(6, L2, NONE, NOF, NONE, NONE, NOF, NONE, PAY2), - I40E_PTT(7, L2, NONE, NOF, NONE, NONE, NOF, NONE, PAY2), - I40E_PTT_UNUSED_ENTRY(8), - I40E_PTT_UNUSED_ENTRY(9), - I40E_PTT(10, L2, NONE, NOF, NONE, NONE, NOF, NONE, PAY2), - I40E_PTT(11, L2, NONE, NOF, NONE, NONE, NOF, NONE, NONE), - I40E_PTT(12, L2, NONE, NOF, NONE, NONE, NOF, NONE, PAY3), - I40E_PTT(13, L2, NONE, NOF, NONE, NONE, NOF, NONE, PAY3), - I40E_PTT(14, L2, NONE, NOF, NONE, NONE, NOF, NONE, PAY3), - I40E_PTT(15, L2, NONE, NOF, NONE, NONE, NOF, NONE, PAY3), - I40E_PTT(16, L2, NONE, NOF, NONE, NONE, NOF, NONE, PAY3), - I40E_PTT(17, L2, NONE, NOF, NONE, NONE, NOF, NONE, PAY3), - I40E_PTT(18, L2, NONE, NOF, NONE, NONE, NOF, NONE, PAY3), - I40E_PTT(19, L2, NONE, NOF, NONE, NONE, NOF, NONE, PAY3), - I40E_PTT(20, L2, NONE, NOF, NONE, NONE, NOF, NONE, PAY3), - I40E_PTT(21, L2, NONE, NOF, NONE, NONE, NOF, NONE, PAY3), - - /* Non Tunneled IPv4 */ - I40E_PTT(22, IP, IPV4, FRG, NONE, NONE, NOF, NONE, PAY3), - I40E_PTT(23, IP, IPV4, NOF, NONE, NONE, NOF, NONE, PAY3), - I40E_PTT(24, IP, IPV4, NOF, NONE, NONE, NOF, UDP, PAY4), - I40E_PTT_UNUSED_ENTRY(25), - I40E_PTT(26, IP, IPV4, NOF, NONE, NONE, NOF, TCP, PAY4), - I40E_PTT(27, IP, IPV4, NOF, NONE, NONE, NOF, SCTP, PAY4), - I40E_PTT(28, IP, IPV4, NOF, NONE, NONE, NOF, ICMP, PAY4), - - /* IPv4 --> IPv4 */ - I40E_PTT(29, IP, IPV4, NOF, IP_IP, IPV4, FRG, NONE, PAY3), - I40E_PTT(30, IP, IPV4, NOF, IP_IP, IPV4, NOF, NONE, PAY3), - I40E_PTT(31, IP, IPV4, NOF, IP_IP, IPV4, NOF, UDP, PAY4), - I40E_PTT_UNUSED_ENTRY(32), - I40E_PTT(33, IP, IPV4, NOF, IP_IP, IPV4, NOF, TCP, PAY4), - I40E_PTT(34, IP, IPV4, NOF, IP_IP, IPV4, NOF, SCTP, PAY4), - I40E_PTT(35, IP, IPV4, NOF, IP_IP, IPV4, NOF, ICMP, PAY4), - - /* IPv4 --> IPv6 */ - I40E_PTT(36, IP, IPV4, NOF, IP_IP, IPV6, FRG, NONE, PAY3), - I40E_PTT(37, IP, IPV4, NOF, IP_IP, IPV6, NOF, NONE, PAY3), - I40E_PTT(38, IP, IPV4, NOF, IP_IP, IPV6, NOF, UDP, PAY4), - I40E_PTT_UNUSED_ENTRY(39), - I40E_PTT(40, IP, IPV4, NOF, IP_IP, IPV6, NOF, TCP, PAY4), - I40E_PTT(41, IP, IPV4, NOF, IP_IP, IPV6, NOF, SCTP, PAY4), - I40E_PTT(42, IP, IPV4, NOF, IP_IP, IPV6, NOF, ICMP, PAY4), - - /* IPv4 --> GRE/NAT */ - I40E_PTT(43, IP, IPV4, NOF, IP_GRENAT, NONE, NOF, NONE, PAY3), - - /* IPv4 --> GRE/NAT --> IPv4 */ - I40E_PTT(44, IP, IPV4, NOF, IP_GRENAT, IPV4, FRG, NONE, PAY3), - I40E_PTT(45, IP, IPV4, NOF, IP_GRENAT, IPV4, NOF, NONE, PAY3), - I40E_PTT(46, IP, IPV4, NOF, IP_GRENAT, IPV4, NOF, UDP, PAY4), - I40E_PTT_UNUSED_ENTRY(47), - I40E_PTT(48, IP, IPV4, NOF, IP_GRENAT, IPV4, NOF, TCP, PAY4), - I40E_PTT(49, IP, IPV4, NOF, IP_GRENAT, IPV4, NOF, SCTP, PAY4), - I40E_PTT(50, IP, IPV4, NOF, IP_GRENAT, IPV4, NOF, ICMP, PAY4), - - /* IPv4 --> GRE/NAT --> IPv6 */ - I40E_PTT(51, IP, IPV4, NOF, IP_GRENAT, IPV6, FRG, NONE, PAY3), - I40E_PTT(52, IP, IPV4, NOF, IP_GRENAT, IPV6, NOF, NONE, PAY3), - I40E_PTT(53, IP, IPV4, NOF, IP_GRENAT, IPV6, NOF, UDP, PAY4), - I40E_PTT_UNUSED_ENTRY(54), - I40E_PTT(55, IP, IPV4, NOF, IP_GRENAT, IPV6, NOF, TCP, PAY4), - I40E_PTT(56, IP, IPV4, NOF, IP_GRENAT, IPV6, NOF, SCTP, PAY4), - I40E_PTT(57, IP, IPV4, NOF, IP_GRENAT, IPV6, NOF, ICMP, PAY4), - - /* IPv4 --> GRE/NAT --> MAC */ - I40E_PTT(58, IP, IPV4, NOF, IP_GRENAT_MAC, NONE, NOF, NONE, PAY3), - - /* IPv4 --> GRE/NAT --> MAC --> IPv4 */ - I40E_PTT(59, IP, IPV4, NOF, IP_GRENAT_MAC, IPV4, FRG, NONE, PAY3), - I40E_PTT(60, IP, IPV4, NOF, IP_GRENAT_MAC, IPV4, NOF, NONE, PAY3), - I40E_PTT(61, IP, IPV4, NOF, IP_GRENAT_MAC, IPV4, NOF, UDP, PAY4), - I40E_PTT_UNUSED_ENTRY(62), - I40E_PTT(63, IP, IPV4, NOF, IP_GRENAT_MAC, IPV4, NOF, TCP, PAY4), - I40E_PTT(64, IP, IPV4, NOF, IP_GRENAT_MAC, IPV4, NOF, SCTP, PAY4), - I40E_PTT(65, IP, IPV4, NOF, IP_GRENAT_MAC, IPV4, NOF, ICMP, PAY4), - - /* IPv4 --> GRE/NAT -> MAC --> IPv6 */ - I40E_PTT(66, IP, IPV4, NOF, IP_GRENAT_MAC, IPV6, FRG, NONE, PAY3), - I40E_PTT(67, IP, IPV4, NOF, IP_GRENAT_MAC, IPV6, NOF, NONE, PAY3), - I40E_PTT(68, IP, IPV4, NOF, IP_GRENAT_MAC, IPV6, NOF, UDP, PAY4), - I40E_PTT_UNUSED_ENTRY(69), - I40E_PTT(70, IP, IPV4, NOF, IP_GRENAT_MAC, IPV6, NOF, TCP, PAY4), - I40E_PTT(71, IP, IPV4, NOF, IP_GRENAT_MAC, IPV6, NOF, SCTP, PAY4), - I40E_PTT(72, IP, IPV4, NOF, IP_GRENAT_MAC, IPV6, NOF, ICMP, PAY4), - - /* IPv4 --> GRE/NAT --> MAC/VLAN */ - I40E_PTT(73, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, NONE, NOF, NONE, PAY3), - - /* IPv4 ---> GRE/NAT -> MAC/VLAN --> IPv4 */ - I40E_PTT(74, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV4, FRG, NONE, PAY3), - I40E_PTT(75, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, NONE, PAY3), - I40E_PTT(76, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, UDP, PAY4), - I40E_PTT_UNUSED_ENTRY(77), - I40E_PTT(78, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, TCP, PAY4), - I40E_PTT(79, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, SCTP, PAY4), - I40E_PTT(80, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, ICMP, PAY4), - - /* IPv4 -> GRE/NAT -> MAC/VLAN --> IPv6 */ - I40E_PTT(81, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV6, FRG, NONE, PAY3), - I40E_PTT(82, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, NONE, PAY3), - I40E_PTT(83, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, UDP, PAY4), - I40E_PTT_UNUSED_ENTRY(84), - I40E_PTT(85, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, TCP, PAY4), - I40E_PTT(86, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, SCTP, PAY4), - I40E_PTT(87, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, ICMP, PAY4), - - /* Non Tunneled IPv6 */ - I40E_PTT(88, IP, IPV6, FRG, NONE, NONE, NOF, NONE, PAY3), - I40E_PTT(89, IP, IPV6, NOF, NONE, NONE, NOF, NONE, PAY3), - I40E_PTT(90, IP, IPV6, NOF, NONE, NONE, NOF, UDP, PAY3), - I40E_PTT_UNUSED_ENTRY(91), - I40E_PTT(92, IP, IPV6, NOF, NONE, NONE, NOF, TCP, PAY4), - I40E_PTT(93, IP, IPV6, NOF, NONE, NONE, NOF, SCTP, PAY4), - I40E_PTT(94, IP, IPV6, NOF, NONE, NONE, NOF, ICMP, PAY4), - - /* IPv6 --> IPv4 */ - I40E_PTT(95, IP, IPV6, NOF, IP_IP, IPV4, FRG, NONE, PAY3), - I40E_PTT(96, IP, IPV6, NOF, IP_IP, IPV4, NOF, NONE, PAY3), - I40E_PTT(97, IP, IPV6, NOF, IP_IP, IPV4, NOF, UDP, PAY4), - I40E_PTT_UNUSED_ENTRY(98), - I40E_PTT(99, IP, IPV6, NOF, IP_IP, IPV4, NOF, TCP, PAY4), - I40E_PTT(100, IP, IPV6, NOF, IP_IP, IPV4, NOF, SCTP, PAY4), - I40E_PTT(101, IP, IPV6, NOF, IP_IP, IPV4, NOF, ICMP, PAY4), - - /* IPv6 --> IPv6 */ - I40E_PTT(102, IP, IPV6, NOF, IP_IP, IPV6, FRG, NONE, PAY3), - I40E_PTT(103, IP, IPV6, NOF, IP_IP, IPV6, NOF, NONE, PAY3), - I40E_PTT(104, IP, IPV6, NOF, IP_IP, IPV6, NOF, UDP, PAY4), - I40E_PTT_UNUSED_ENTRY(105), - I40E_PTT(106, IP, IPV6, NOF, IP_IP, IPV6, NOF, TCP, PAY4), - I40E_PTT(107, IP, IPV6, NOF, IP_IP, IPV6, NOF, SCTP, PAY4), - I40E_PTT(108, IP, IPV6, NOF, IP_IP, IPV6, NOF, ICMP, PAY4), - - /* IPv6 --> GRE/NAT */ - I40E_PTT(109, IP, IPV6, NOF, IP_GRENAT, NONE, NOF, NONE, PAY3), - - /* IPv6 --> GRE/NAT -> IPv4 */ - I40E_PTT(110, IP, IPV6, NOF, IP_GRENAT, IPV4, FRG, NONE, PAY3), - I40E_PTT(111, IP, IPV6, NOF, IP_GRENAT, IPV4, NOF, NONE, PAY3), - I40E_PTT(112, IP, IPV6, NOF, IP_GRENAT, IPV4, NOF, UDP, PAY4), - I40E_PTT_UNUSED_ENTRY(113), - I40E_PTT(114, IP, IPV6, NOF, IP_GRENAT, IPV4, NOF, TCP, PAY4), - I40E_PTT(115, IP, IPV6, NOF, IP_GRENAT, IPV4, NOF, SCTP, PAY4), - I40E_PTT(116, IP, IPV6, NOF, IP_GRENAT, IPV4, NOF, ICMP, PAY4), - - /* IPv6 --> GRE/NAT -> IPv6 */ - I40E_PTT(117, IP, IPV6, NOF, IP_GRENAT, IPV6, FRG, NONE, PAY3), - I40E_PTT(118, IP, IPV6, NOF, IP_GRENAT, IPV6, NOF, NONE, PAY3), - I40E_PTT(119, IP, IPV6, NOF, IP_GRENAT, IPV6, NOF, UDP, PAY4), - I40E_PTT_UNUSED_ENTRY(120), - I40E_PTT(121, IP, IPV6, NOF, IP_GRENAT, IPV6, NOF, TCP, PAY4), - I40E_PTT(122, IP, IPV6, NOF, IP_GRENAT, IPV6, NOF, SCTP, PAY4), - I40E_PTT(123, IP, IPV6, NOF, IP_GRENAT, IPV6, NOF, ICMP, PAY4), - - /* IPv6 --> GRE/NAT -> MAC */ - I40E_PTT(124, IP, IPV6, NOF, IP_GRENAT_MAC, NONE, NOF, NONE, PAY3), - - /* IPv6 --> GRE/NAT -> MAC -> IPv4 */ - I40E_PTT(125, IP, IPV6, NOF, IP_GRENAT_MAC, IPV4, FRG, NONE, PAY3), - I40E_PTT(126, IP, IPV6, NOF, IP_GRENAT_MAC, IPV4, NOF, NONE, PAY3), - I40E_PTT(127, IP, IPV6, NOF, IP_GRENAT_MAC, IPV4, NOF, UDP, PAY4), - I40E_PTT_UNUSED_ENTRY(128), - I40E_PTT(129, IP, IPV6, NOF, IP_GRENAT_MAC, IPV4, NOF, TCP, PAY4), - I40E_PTT(130, IP, IPV6, NOF, IP_GRENAT_MAC, IPV4, NOF, SCTP, PAY4), - I40E_PTT(131, IP, IPV6, NOF, IP_GRENAT_MAC, IPV4, NOF, ICMP, PAY4), - - /* IPv6 --> GRE/NAT -> MAC -> IPv6 */ - I40E_PTT(132, IP, IPV6, NOF, IP_GRENAT_MAC, IPV6, FRG, NONE, PAY3), - I40E_PTT(133, IP, IPV6, NOF, IP_GRENAT_MAC, IPV6, NOF, NONE, PAY3), - I40E_PTT(134, IP, IPV6, NOF, IP_GRENAT_MAC, IPV6, NOF, UDP, PAY4), - I40E_PTT_UNUSED_ENTRY(135), - I40E_PTT(136, IP, IPV6, NOF, IP_GRENAT_MAC, IPV6, NOF, TCP, PAY4), - I40E_PTT(137, IP, IPV6, NOF, IP_GRENAT_MAC, IPV6, NOF, SCTP, PAY4), - I40E_PTT(138, IP, IPV6, NOF, IP_GRENAT_MAC, IPV6, NOF, ICMP, PAY4), - - /* IPv6 --> GRE/NAT -> MAC/VLAN */ - I40E_PTT(139, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, NONE, NOF, NONE, PAY3), - - /* IPv6 --> GRE/NAT -> MAC/VLAN --> IPv4 */ - I40E_PTT(140, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV4, FRG, NONE, PAY3), - I40E_PTT(141, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, NONE, PAY3), - I40E_PTT(142, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, UDP, PAY4), - I40E_PTT_UNUSED_ENTRY(143), - I40E_PTT(144, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, TCP, PAY4), - I40E_PTT(145, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, SCTP, PAY4), - I40E_PTT(146, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, ICMP, PAY4), - - /* IPv6 --> GRE/NAT -> MAC/VLAN --> IPv6 */ - I40E_PTT(147, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV6, FRG, NONE, PAY3), - I40E_PTT(148, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, NONE, PAY3), - I40E_PTT(149, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, UDP, PAY4), - I40E_PTT_UNUSED_ENTRY(150), - I40E_PTT(151, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, TCP, PAY4), - I40E_PTT(152, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, SCTP, PAY4), - I40E_PTT(153, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, ICMP, PAY4), - - /* unused entries */ - I40E_PTT_UNUSED_ENTRY(154), - I40E_PTT_UNUSED_ENTRY(155), - I40E_PTT_UNUSED_ENTRY(156), - I40E_PTT_UNUSED_ENTRY(157), - I40E_PTT_UNUSED_ENTRY(158), - I40E_PTT_UNUSED_ENTRY(159), - - I40E_PTT_UNUSED_ENTRY(160), - I40E_PTT_UNUSED_ENTRY(161), - I40E_PTT_UNUSED_ENTRY(162), - I40E_PTT_UNUSED_ENTRY(163), - I40E_PTT_UNUSED_ENTRY(164), - I40E_PTT_UNUSED_ENTRY(165), - I40E_PTT_UNUSED_ENTRY(166), - I40E_PTT_UNUSED_ENTRY(167), - I40E_PTT_UNUSED_ENTRY(168), - I40E_PTT_UNUSED_ENTRY(169), - - I40E_PTT_UNUSED_ENTRY(170), - I40E_PTT_UNUSED_ENTRY(171), - I40E_PTT_UNUSED_ENTRY(172), - I40E_PTT_UNUSED_ENTRY(173), - I40E_PTT_UNUSED_ENTRY(174), - I40E_PTT_UNUSED_ENTRY(175), - I40E_PTT_UNUSED_ENTRY(176), - I40E_PTT_UNUSED_ENTRY(177), - I40E_PTT_UNUSED_ENTRY(178), - I40E_PTT_UNUSED_ENTRY(179), - - I40E_PTT_UNUSED_ENTRY(180), - I40E_PTT_UNUSED_ENTRY(181), - I40E_PTT_UNUSED_ENTRY(182), - I40E_PTT_UNUSED_ENTRY(183), - I40E_PTT_UNUSED_ENTRY(184), - I40E_PTT_UNUSED_ENTRY(185), - I40E_PTT_UNUSED_ENTRY(186), - I40E_PTT_UNUSED_ENTRY(187), - I40E_PTT_UNUSED_ENTRY(188), - I40E_PTT_UNUSED_ENTRY(189), - - I40E_PTT_UNUSED_ENTRY(190), - I40E_PTT_UNUSED_ENTRY(191), - I40E_PTT_UNUSED_ENTRY(192), - I40E_PTT_UNUSED_ENTRY(193), - I40E_PTT_UNUSED_ENTRY(194), - I40E_PTT_UNUSED_ENTRY(195), - I40E_PTT_UNUSED_ENTRY(196), - I40E_PTT_UNUSED_ENTRY(197), - I40E_PTT_UNUSED_ENTRY(198), - I40E_PTT_UNUSED_ENTRY(199), - - I40E_PTT_UNUSED_ENTRY(200), - I40E_PTT_UNUSED_ENTRY(201), - I40E_PTT_UNUSED_ENTRY(202), - I40E_PTT_UNUSED_ENTRY(203), - I40E_PTT_UNUSED_ENTRY(204), - I40E_PTT_UNUSED_ENTRY(205), - I40E_PTT_UNUSED_ENTRY(206), - I40E_PTT_UNUSED_ENTRY(207), - I40E_PTT_UNUSED_ENTRY(208), - I40E_PTT_UNUSED_ENTRY(209), - - I40E_PTT_UNUSED_ENTRY(210), - I40E_PTT_UNUSED_ENTRY(211), - I40E_PTT_UNUSED_ENTRY(212), - I40E_PTT_UNUSED_ENTRY(213), - I40E_PTT_UNUSED_ENTRY(214), - I40E_PTT_UNUSED_ENTRY(215), - I40E_PTT_UNUSED_ENTRY(216), - I40E_PTT_UNUSED_ENTRY(217), - I40E_PTT_UNUSED_ENTRY(218), - I40E_PTT_UNUSED_ENTRY(219), - - I40E_PTT_UNUSED_ENTRY(220), - I40E_PTT_UNUSED_ENTRY(221), - I40E_PTT_UNUSED_ENTRY(222), - I40E_PTT_UNUSED_ENTRY(223), - I40E_PTT_UNUSED_ENTRY(224), - I40E_PTT_UNUSED_ENTRY(225), - I40E_PTT_UNUSED_ENTRY(226), - I40E_PTT_UNUSED_ENTRY(227), - I40E_PTT_UNUSED_ENTRY(228), - I40E_PTT_UNUSED_ENTRY(229), - - I40E_PTT_UNUSED_ENTRY(230), - I40E_PTT_UNUSED_ENTRY(231), - I40E_PTT_UNUSED_ENTRY(232), - I40E_PTT_UNUSED_ENTRY(233), - I40E_PTT_UNUSED_ENTRY(234), - I40E_PTT_UNUSED_ENTRY(235), - I40E_PTT_UNUSED_ENTRY(236), - I40E_PTT_UNUSED_ENTRY(237), - I40E_PTT_UNUSED_ENTRY(238), - I40E_PTT_UNUSED_ENTRY(239), - - I40E_PTT_UNUSED_ENTRY(240), - I40E_PTT_UNUSED_ENTRY(241), - I40E_PTT_UNUSED_ENTRY(242), - I40E_PTT_UNUSED_ENTRY(243), - I40E_PTT_UNUSED_ENTRY(244), - I40E_PTT_UNUSED_ENTRY(245), - I40E_PTT_UNUSED_ENTRY(246), - I40E_PTT_UNUSED_ENTRY(247), - I40E_PTT_UNUSED_ENTRY(248), - I40E_PTT_UNUSED_ENTRY(249), - - I40E_PTT_UNUSED_ENTRY(250), - I40E_PTT_UNUSED_ENTRY(251), - I40E_PTT_UNUSED_ENTRY(252), - I40E_PTT_UNUSED_ENTRY(253), - I40E_PTT_UNUSED_ENTRY(254), - I40E_PTT_UNUSED_ENTRY(255) -}; - -/** - * i40evf_aq_rx_ctl_read_register - use FW to read from an Rx control register - * @hw: pointer to the hw struct - * @reg_addr: register address - * @reg_val: ptr to register value - * @cmd_details: pointer to command details structure or NULL - * - * Use the firmware to read the Rx control register, - * especially useful if the Rx unit is under heavy pressure - **/ -i40e_status i40evf_aq_rx_ctl_read_register(struct i40e_hw *hw, - u32 reg_addr, u32 *reg_val, - struct i40e_asq_cmd_details *cmd_details) -{ - struct i40e_aq_desc desc; - struct i40e_aqc_rx_ctl_reg_read_write *cmd_resp = - (struct i40e_aqc_rx_ctl_reg_read_write *)&desc.params.raw; - i40e_status status; - - if (!reg_val) - return I40E_ERR_PARAM; - - i40evf_fill_default_direct_cmd_desc(&desc, - i40e_aqc_opc_rx_ctl_reg_read); - - cmd_resp->address = cpu_to_le32(reg_addr); - - status = i40evf_asq_send_command(hw, &desc, NULL, 0, cmd_details); - - if (status == 0) - *reg_val = le32_to_cpu(cmd_resp->value); - - return status; -} - -/** - * i40evf_read_rx_ctl - read from an Rx control register - * @hw: pointer to the hw struct - * @reg_addr: register address - **/ -u32 i40evf_read_rx_ctl(struct i40e_hw *hw, u32 reg_addr) -{ - i40e_status status = 0; - bool use_register; - int retry = 5; - u32 val = 0; - - use_register = (((hw->aq.api_maj_ver == 1) && - (hw->aq.api_min_ver < 5)) || - (hw->mac.type == I40E_MAC_X722)); - if (!use_register) { -do_retry: - status = i40evf_aq_rx_ctl_read_register(hw, reg_addr, - &val, NULL); - if (hw->aq.asq_last_status == I40E_AQ_RC_EAGAIN && retry) { - usleep_range(1000, 2000); - retry--; - goto do_retry; - } - } - - /* if the AQ access failed, try the old-fashioned way */ - if (status || use_register) - val = rd32(hw, reg_addr); - - return val; -} - -/** - * i40evf_aq_rx_ctl_write_register - * @hw: pointer to the hw struct - * @reg_addr: register address - * @reg_val: register value - * @cmd_details: pointer to command details structure or NULL - * - * Use the firmware to write to an Rx control register, - * especially useful if the Rx unit is under heavy pressure - **/ -i40e_status i40evf_aq_rx_ctl_write_register(struct i40e_hw *hw, - u32 reg_addr, u32 reg_val, - struct i40e_asq_cmd_details *cmd_details) -{ - struct i40e_aq_desc desc; - struct i40e_aqc_rx_ctl_reg_read_write *cmd = - (struct i40e_aqc_rx_ctl_reg_read_write *)&desc.params.raw; - i40e_status status; - - i40evf_fill_default_direct_cmd_desc(&desc, - i40e_aqc_opc_rx_ctl_reg_write); - - cmd->address = cpu_to_le32(reg_addr); - cmd->value = cpu_to_le32(reg_val); - - status = i40evf_asq_send_command(hw, &desc, NULL, 0, cmd_details); - - return status; -} - -/** - * i40evf_write_rx_ctl - write to an Rx control register - * @hw: pointer to the hw struct - * @reg_addr: register address - * @reg_val: register value - **/ -void i40evf_write_rx_ctl(struct i40e_hw *hw, u32 reg_addr, u32 reg_val) -{ - i40e_status status = 0; - bool use_register; - int retry = 5; - - use_register = (((hw->aq.api_maj_ver == 1) && - (hw->aq.api_min_ver < 5)) || - (hw->mac.type == I40E_MAC_X722)); - if (!use_register) { -do_retry: - status = i40evf_aq_rx_ctl_write_register(hw, reg_addr, - reg_val, NULL); - if (hw->aq.asq_last_status == I40E_AQ_RC_EAGAIN && retry) { - usleep_range(1000, 2000); - retry--; - goto do_retry; - } - } - - /* if the AQ access failed, try the old-fashioned way */ - if (status || use_register) - wr32(hw, reg_addr, reg_val); -} - -/** - * i40e_aq_send_msg_to_pf - * @hw: pointer to the hardware structure - * @v_opcode: opcodes for VF-PF communication - * @v_retval: return error code - * @msg: pointer to the msg buffer - * @msglen: msg length - * @cmd_details: pointer to command details - * - * Send message to PF driver using admin queue. By default, this message - * is sent asynchronously, i.e. i40evf_asq_send_command() does not wait for - * completion before returning. - **/ -i40e_status i40e_aq_send_msg_to_pf(struct i40e_hw *hw, - enum virtchnl_ops v_opcode, - i40e_status v_retval, - u8 *msg, u16 msglen, - struct i40e_asq_cmd_details *cmd_details) -{ - struct i40e_aq_desc desc; - struct i40e_asq_cmd_details details; - i40e_status status; - - i40evf_fill_default_direct_cmd_desc(&desc, i40e_aqc_opc_send_msg_to_pf); - desc.flags |= cpu_to_le16((u16)I40E_AQ_FLAG_SI); - desc.cookie_high = cpu_to_le32(v_opcode); - desc.cookie_low = cpu_to_le32(v_retval); - if (msglen) { - desc.flags |= cpu_to_le16((u16)(I40E_AQ_FLAG_BUF - | I40E_AQ_FLAG_RD)); - if (msglen > I40E_AQ_LARGE_BUF) - desc.flags |= cpu_to_le16((u16)I40E_AQ_FLAG_LB); - desc.datalen = cpu_to_le16(msglen); - } - if (!cmd_details) { - memset(&details, 0, sizeof(details)); - details.async = true; - cmd_details = &details; - } - status = i40evf_asq_send_command(hw, &desc, msg, msglen, cmd_details); - return status; -} - -/** - * i40e_vf_parse_hw_config - * @hw: pointer to the hardware structure - * @msg: pointer to the virtual channel VF resource structure - * - * Given a VF resource message from the PF, populate the hw struct - * with appropriate information. - **/ -void i40e_vf_parse_hw_config(struct i40e_hw *hw, - struct virtchnl_vf_resource *msg) -{ - struct virtchnl_vsi_resource *vsi_res; - int i; - - vsi_res = &msg->vsi_res[0]; - - hw->dev_caps.num_vsis = msg->num_vsis; - hw->dev_caps.num_rx_qp = msg->num_queue_pairs; - hw->dev_caps.num_tx_qp = msg->num_queue_pairs; - hw->dev_caps.num_msix_vectors_vf = msg->max_vectors; - hw->dev_caps.dcb = msg->vf_cap_flags & - VIRTCHNL_VF_OFFLOAD_L2; - hw->dev_caps.fcoe = 0; - for (i = 0; i < msg->num_vsis; i++) { - if (vsi_res->vsi_type == VIRTCHNL_VSI_SRIOV) { - ether_addr_copy(hw->mac.perm_addr, - vsi_res->default_mac_addr); - ether_addr_copy(hw->mac.addr, - vsi_res->default_mac_addr); - } - vsi_res++; - } -} - -/** - * i40e_vf_reset - * @hw: pointer to the hardware structure - * - * Send a VF_RESET message to the PF. Does not wait for response from PF - * as none will be forthcoming. Immediately after calling this function, - * the admin queue should be shut down and (optionally) reinitialized. - **/ -i40e_status i40e_vf_reset(struct i40e_hw *hw) -{ - return i40e_aq_send_msg_to_pf(hw, VIRTCHNL_OP_RESET_VF, - 0, NULL, 0, NULL); -} - -/** - * i40evf_aq_write_ddp - Write dynamic device personalization (ddp) - * @hw: pointer to the hw struct - * @buff: command buffer (size in bytes = buff_size) - * @buff_size: buffer size in bytes - * @track_id: package tracking id - * @error_offset: returns error offset - * @error_info: returns error information - * @cmd_details: pointer to command details structure or NULL - **/ -enum -i40e_status_code i40evf_aq_write_ddp(struct i40e_hw *hw, void *buff, - u16 buff_size, u32 track_id, - u32 *error_offset, u32 *error_info, - struct i40e_asq_cmd_details *cmd_details) -{ - struct i40e_aq_desc desc; - struct i40e_aqc_write_personalization_profile *cmd = - (struct i40e_aqc_write_personalization_profile *) - &desc.params.raw; - struct i40e_aqc_write_ddp_resp *resp; - i40e_status status; - - i40evf_fill_default_direct_cmd_desc(&desc, - i40e_aqc_opc_write_personalization_profile); - - desc.flags |= cpu_to_le16(I40E_AQ_FLAG_BUF | I40E_AQ_FLAG_RD); - if (buff_size > I40E_AQ_LARGE_BUF) - desc.flags |= cpu_to_le16((u16)I40E_AQ_FLAG_LB); - - desc.datalen = cpu_to_le16(buff_size); - - cmd->profile_track_id = cpu_to_le32(track_id); - - status = i40evf_asq_send_command(hw, &desc, buff, buff_size, cmd_details); - if (!status) { - resp = (struct i40e_aqc_write_ddp_resp *)&desc.params.raw; - if (error_offset) - *error_offset = le32_to_cpu(resp->error_offset); - if (error_info) - *error_info = le32_to_cpu(resp->error_info); - } - - return status; -} - -/** - * i40evf_aq_get_ddp_list - Read dynamic device personalization (ddp) - * @hw: pointer to the hw struct - * @buff: command buffer (size in bytes = buff_size) - * @buff_size: buffer size in bytes - * @flags: AdminQ command flags - * @cmd_details: pointer to command details structure or NULL - **/ -enum -i40e_status_code i40evf_aq_get_ddp_list(struct i40e_hw *hw, void *buff, - u16 buff_size, u8 flags, - struct i40e_asq_cmd_details *cmd_details) -{ - struct i40e_aq_desc desc; - struct i40e_aqc_get_applied_profiles *cmd = - (struct i40e_aqc_get_applied_profiles *)&desc.params.raw; - i40e_status status; - - i40evf_fill_default_direct_cmd_desc(&desc, - i40e_aqc_opc_get_personalization_profile_list); - - desc.flags |= cpu_to_le16((u16)I40E_AQ_FLAG_BUF); - if (buff_size > I40E_AQ_LARGE_BUF) - desc.flags |= cpu_to_le16((u16)I40E_AQ_FLAG_LB); - desc.datalen = cpu_to_le16(buff_size); - - cmd->flags = flags; - - status = i40evf_asq_send_command(hw, &desc, buff, buff_size, cmd_details); - - return status; -} - -/** - * i40evf_find_segment_in_package - * @segment_type: the segment type to search for (i.e., SEGMENT_TYPE_I40E) - * @pkg_hdr: pointer to the package header to be searched - * - * This function searches a package file for a particular segment type. On - * success it returns a pointer to the segment header, otherwise it will - * return NULL. - **/ -struct i40e_generic_seg_header * -i40evf_find_segment_in_package(u32 segment_type, - struct i40e_package_header *pkg_hdr) -{ - struct i40e_generic_seg_header *segment; - u32 i; - - /* Search all package segments for the requested segment type */ - for (i = 0; i < pkg_hdr->segment_count; i++) { - segment = - (struct i40e_generic_seg_header *)((u8 *)pkg_hdr + - pkg_hdr->segment_offset[i]); - - if (segment->type == segment_type) - return segment; - } - - return NULL; -} - -/** - * i40evf_write_profile - * @hw: pointer to the hardware structure - * @profile: pointer to the profile segment of the package to be downloaded - * @track_id: package tracking id - * - * Handles the download of a complete package. - */ -enum i40e_status_code -i40evf_write_profile(struct i40e_hw *hw, struct i40e_profile_segment *profile, - u32 track_id) -{ - i40e_status status = 0; - struct i40e_section_table *sec_tbl; - struct i40e_profile_section_header *sec = NULL; - u32 dev_cnt; - u32 vendor_dev_id; - u32 *nvm; - u32 section_size = 0; - u32 offset = 0, info = 0; - u32 i; - - dev_cnt = profile->device_table_count; - - for (i = 0; i < dev_cnt; i++) { - vendor_dev_id = profile->device_table[i].vendor_dev_id; - if ((vendor_dev_id >> 16) == PCI_VENDOR_ID_INTEL) - if (hw->device_id == (vendor_dev_id & 0xFFFF)) - break; - } - if (i == dev_cnt) { - i40e_debug(hw, I40E_DEBUG_PACKAGE, "Device doesn't support DDP"); - return I40E_ERR_DEVICE_NOT_SUPPORTED; - } - - nvm = (u32 *)&profile->device_table[dev_cnt]; - sec_tbl = (struct i40e_section_table *)&nvm[nvm[0] + 1]; - - for (i = 0; i < sec_tbl->section_count; i++) { - sec = (struct i40e_profile_section_header *)((u8 *)profile + - sec_tbl->section_offset[i]); - - /* Skip 'AQ', 'note' and 'name' sections */ - if (sec->section.type != SECTION_TYPE_MMIO) - continue; - - section_size = sec->section.size + - sizeof(struct i40e_profile_section_header); - - /* Write profile */ - status = i40evf_aq_write_ddp(hw, (void *)sec, (u16)section_size, - track_id, &offset, &info, NULL); - if (status) { - i40e_debug(hw, I40E_DEBUG_PACKAGE, - "Failed to write profile: offset %d, info %d", - offset, info); - break; - } - } - return status; -} - -/** - * i40evf_add_pinfo_to_list - * @hw: pointer to the hardware structure - * @profile: pointer to the profile segment of the package - * @profile_info_sec: buffer for information section - * @track_id: package tracking id - * - * Register a profile to the list of loaded profiles. - */ -enum i40e_status_code -i40evf_add_pinfo_to_list(struct i40e_hw *hw, - struct i40e_profile_segment *profile, - u8 *profile_info_sec, u32 track_id) -{ - i40e_status status = 0; - struct i40e_profile_section_header *sec = NULL; - struct i40e_profile_info *pinfo; - u32 offset = 0, info = 0; - - sec = (struct i40e_profile_section_header *)profile_info_sec; - sec->tbl_size = 1; - sec->data_end = sizeof(struct i40e_profile_section_header) + - sizeof(struct i40e_profile_info); - sec->section.type = SECTION_TYPE_INFO; - sec->section.offset = sizeof(struct i40e_profile_section_header); - sec->section.size = sizeof(struct i40e_profile_info); - pinfo = (struct i40e_profile_info *)(profile_info_sec + - sec->section.offset); - pinfo->track_id = track_id; - pinfo->version = profile->version; - pinfo->op = I40E_DDP_ADD_TRACKID; - memcpy(pinfo->name, profile->name, I40E_DDP_NAME_SIZE); - - status = i40evf_aq_write_ddp(hw, (void *)sec, sec->data_end, - track_id, &offset, &info, NULL); - return status; -} diff --git a/drivers/net/ethernet/intel/i40evf/i40e_devids.h b/drivers/net/ethernet/intel/i40evf/i40e_devids.h deleted file mode 100644 index f300bf271824..000000000000 --- a/drivers/net/ethernet/intel/i40evf/i40e_devids.h +++ /dev/null @@ -1,34 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright(c) 2013 - 2018 Intel Corporation. */ - -#ifndef _I40E_DEVIDS_H_ -#define _I40E_DEVIDS_H_ - -/* Device IDs */ -#define I40E_DEV_ID_SFP_XL710 0x1572 -#define I40E_DEV_ID_QEMU 0x1574 -#define I40E_DEV_ID_KX_B 0x1580 -#define I40E_DEV_ID_KX_C 0x1581 -#define I40E_DEV_ID_QSFP_A 0x1583 -#define I40E_DEV_ID_QSFP_B 0x1584 -#define I40E_DEV_ID_QSFP_C 0x1585 -#define I40E_DEV_ID_10G_BASE_T 0x1586 -#define I40E_DEV_ID_20G_KR2 0x1587 -#define I40E_DEV_ID_20G_KR2_A 0x1588 -#define I40E_DEV_ID_10G_BASE_T4 0x1589 -#define I40E_DEV_ID_25G_B 0x158A -#define I40E_DEV_ID_25G_SFP28 0x158B -#define I40E_DEV_ID_VF 0x154C -#define I40E_DEV_ID_VF_HV 0x1571 -#define I40E_DEV_ID_ADAPTIVE_VF 0x1889 -#define I40E_DEV_ID_SFP_X722 0x37D0 -#define I40E_DEV_ID_1G_BASE_T_X722 0x37D1 -#define I40E_DEV_ID_10G_BASE_T_X722 0x37D2 -#define I40E_DEV_ID_SFP_I_X722 0x37D3 -#define I40E_DEV_ID_X722_VF 0x37CD - -#define i40e_is_40G_device(d) ((d) == I40E_DEV_ID_QSFP_A || \ - (d) == I40E_DEV_ID_QSFP_B || \ - (d) == I40E_DEV_ID_QSFP_C) - -#endif /* _I40E_DEVIDS_H_ */ diff --git a/drivers/net/ethernet/intel/i40evf/i40e_ethtool_stats.h b/drivers/net/ethernet/intel/i40evf/i40e_ethtool_stats.h deleted file mode 100644 index 60b595dd8c39..000000000000 --- a/drivers/net/ethernet/intel/i40evf/i40e_ethtool_stats.h +++ /dev/null @@ -1,221 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright(c) 2013 - 2018 Intel Corporation. */ - -/* ethtool statistics helpers */ - -/** - * struct i40e_stats - definition for an ethtool statistic - * @stat_string: statistic name to display in ethtool -S output - * @sizeof_stat: the sizeof() the stat, must be no greater than sizeof(u64) - * @stat_offset: offsetof() the stat from a base pointer - * - * This structure defines a statistic to be added to the ethtool stats buffer. - * It defines a statistic as offset from a common base pointer. Stats should - * be defined in constant arrays using the I40E_STAT macro, with every element - * of the array using the same _type for calculating the sizeof_stat and - * stat_offset. - * - * The @sizeof_stat is expected to be sizeof(u8), sizeof(u16), sizeof(u32) or - * sizeof(u64). Other sizes are not expected and will produce a WARN_ONCE from - * the i40e_add_ethtool_stat() helper function. - * - * The @stat_string is interpreted as a format string, allowing formatted - * values to be inserted while looping over multiple structures for a given - * statistics array. Thus, every statistic string in an array should have the - * same type and number of format specifiers, to be formatted by variadic - * arguments to the i40e_add_stat_string() helper function. - **/ -struct i40e_stats { - char stat_string[ETH_GSTRING_LEN]; - int sizeof_stat; - int stat_offset; -}; - -/* Helper macro to define an i40e_stat structure with proper size and type. - * Use this when defining constant statistics arrays. Note that @_type expects - * only a type name and is used multiple times. - */ -#define I40E_STAT(_type, _name, _stat) { \ - .stat_string = _name, \ - .sizeof_stat = FIELD_SIZEOF(_type, _stat), \ - .stat_offset = offsetof(_type, _stat) \ -} - -/* Helper macro for defining some statistics directly copied from the netdev - * stats structure. - */ -#define I40E_NETDEV_STAT(_net_stat) \ - I40E_STAT(struct rtnl_link_stats64, #_net_stat, _net_stat) - -/* Helper macro for defining some statistics related to queues */ -#define I40E_QUEUE_STAT(_name, _stat) \ - I40E_STAT(struct i40e_ring, _name, _stat) - -/* Stats associated with a Tx or Rx ring */ -static const struct i40e_stats i40e_gstrings_queue_stats[] = { - I40E_QUEUE_STAT("%s-%u.packets", stats.packets), - I40E_QUEUE_STAT("%s-%u.bytes", stats.bytes), -}; - -/** - * i40evf_add_one_ethtool_stat - copy the stat into the supplied buffer - * @data: location to store the stat value - * @pointer: basis for where to copy from - * @stat: the stat definition - * - * Copies the stat data defined by the pointer and stat structure pair into - * the memory supplied as data. Used to implement i40e_add_ethtool_stats and - * i40evf_add_queue_stats. If the pointer is null, data will be zero'd. - */ -static inline void -i40evf_add_one_ethtool_stat(u64 *data, void *pointer, - const struct i40e_stats *stat) -{ - char *p; - - if (!pointer) { - /* ensure that the ethtool data buffer is zero'd for any stats - * which don't have a valid pointer. - */ - *data = 0; - return; - } - - p = (char *)pointer + stat->stat_offset; - switch (stat->sizeof_stat) { - case sizeof(u64): - *data = *((u64 *)p); - break; - case sizeof(u32): - *data = *((u32 *)p); - break; - case sizeof(u16): - *data = *((u16 *)p); - break; - case sizeof(u8): - *data = *((u8 *)p); - break; - default: - WARN_ONCE(1, "unexpected stat size for %s", - stat->stat_string); - *data = 0; - } -} - -/** - * __i40evf_add_ethtool_stats - copy stats into the ethtool supplied buffer - * @data: ethtool stats buffer - * @pointer: location to copy stats from - * @stats: array of stats to copy - * @size: the size of the stats definition - * - * Copy the stats defined by the stats array using the pointer as a base into - * the data buffer supplied by ethtool. Updates the data pointer to point to - * the next empty location for successive calls to __i40evf_add_ethtool_stats. - * If pointer is null, set the data values to zero and update the pointer to - * skip these stats. - **/ -static inline void -__i40evf_add_ethtool_stats(u64 **data, void *pointer, - const struct i40e_stats stats[], - const unsigned int size) -{ - unsigned int i; - - for (i = 0; i < size; i++) - i40evf_add_one_ethtool_stat((*data)++, pointer, &stats[i]); -} - -/** - * i40e_add_ethtool_stats - copy stats into ethtool supplied buffer - * @data: ethtool stats buffer - * @pointer: location where stats are stored - * @stats: static const array of stat definitions - * - * Macro to ease the use of __i40evf_add_ethtool_stats by taking a static - * constant stats array and passing the ARRAY_SIZE(). This avoids typos by - * ensuring that we pass the size associated with the given stats array. - * - * The parameter @stats is evaluated twice, so parameters with side effects - * should be avoided. - **/ -#define i40e_add_ethtool_stats(data, pointer, stats) \ - __i40evf_add_ethtool_stats(data, pointer, stats, ARRAY_SIZE(stats)) - -/** - * i40evf_add_queue_stats - copy queue statistics into supplied buffer - * @data: ethtool stats buffer - * @ring: the ring to copy - * - * Queue statistics must be copied while protected by - * u64_stats_fetch_begin_irq, so we can't directly use i40e_add_ethtool_stats. - * Assumes that queue stats are defined in i40e_gstrings_queue_stats. If the - * ring pointer is null, zero out the queue stat values and update the data - * pointer. Otherwise safely copy the stats from the ring into the supplied - * buffer and update the data pointer when finished. - * - * This function expects to be called while under rcu_read_lock(). - **/ -static inline void -i40evf_add_queue_stats(u64 **data, struct i40e_ring *ring) -{ - const unsigned int size = ARRAY_SIZE(i40e_gstrings_queue_stats); - const struct i40e_stats *stats = i40e_gstrings_queue_stats; - unsigned int start; - unsigned int i; - - /* To avoid invalid statistics values, ensure that we keep retrying - * the copy until we get a consistent value according to - * u64_stats_fetch_retry_irq. But first, make sure our ring is - * non-null before attempting to access its syncp. - */ - do { - start = !ring ? 0 : u64_stats_fetch_begin_irq(&ring->syncp); - for (i = 0; i < size; i++) { - i40evf_add_one_ethtool_stat(&(*data)[i], ring, - &stats[i]); - } - } while (ring && u64_stats_fetch_retry_irq(&ring->syncp, start)); - - /* Once we successfully copy the stats in, update the data pointer */ - *data += size; -} - -/** - * __i40e_add_stat_strings - copy stat strings into ethtool buffer - * @p: ethtool supplied buffer - * @stats: stat definitions array - * @size: size of the stats array - * - * Format and copy the strings described by stats into the buffer pointed at - * by p. - **/ -static void __i40e_add_stat_strings(u8 **p, const struct i40e_stats stats[], - const unsigned int size, ...) -{ - unsigned int i; - - for (i = 0; i < size; i++) { - va_list args; - - va_start(args, size); - vsnprintf(*p, ETH_GSTRING_LEN, stats[i].stat_string, args); - *p += ETH_GSTRING_LEN; - va_end(args); - } -} - -/** - * 40e_add_stat_strings - copy stat strings into ethtool buffer - * @p: ethtool supplied buffer - * @stats: stat definitions array - * - * Format and copy the strings described by the const static stats value into - * the buffer pointed at by p. - * - * The parameter @stats is evaluated twice, so parameters with side effects - * should be avoided. Additionally, stats must be an array such that - * ARRAY_SIZE can be called on it. - **/ -#define i40e_add_stat_strings(p, stats, ...) \ - __i40e_add_stat_strings(p, stats, ARRAY_SIZE(stats), ## __VA_ARGS__) diff --git a/drivers/net/ethernet/intel/i40evf/i40e_hmc.h b/drivers/net/ethernet/intel/i40evf/i40e_hmc.h deleted file mode 100644 index 1c78de838857..000000000000 --- a/drivers/net/ethernet/intel/i40evf/i40e_hmc.h +++ /dev/null @@ -1,215 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright(c) 2013 - 2018 Intel Corporation. */ - -#ifndef _I40E_HMC_H_ -#define _I40E_HMC_H_ - -#define I40E_HMC_MAX_BP_COUNT 512 - -/* forward-declare the HW struct for the compiler */ -struct i40e_hw; - -#define I40E_HMC_INFO_SIGNATURE 0x484D5347 /* HMSG */ -#define I40E_HMC_PD_CNT_IN_SD 512 -#define I40E_HMC_DIRECT_BP_SIZE 0x200000 /* 2M */ -#define I40E_HMC_PAGED_BP_SIZE 4096 -#define I40E_HMC_PD_BP_BUF_ALIGNMENT 4096 -#define I40E_FIRST_VF_FPM_ID 16 - -struct i40e_hmc_obj_info { - u64 base; /* base addr in FPM */ - u32 max_cnt; /* max count available for this hmc func */ - u32 cnt; /* count of objects driver actually wants to create */ - u64 size; /* size in bytes of one object */ -}; - -enum i40e_sd_entry_type { - I40E_SD_TYPE_INVALID = 0, - I40E_SD_TYPE_PAGED = 1, - I40E_SD_TYPE_DIRECT = 2 -}; - -struct i40e_hmc_bp { - enum i40e_sd_entry_type entry_type; - struct i40e_dma_mem addr; /* populate to be used by hw */ - u32 sd_pd_index; - u32 ref_cnt; -}; - -struct i40e_hmc_pd_entry { - struct i40e_hmc_bp bp; - u32 sd_index; - bool rsrc_pg; - bool valid; -}; - -struct i40e_hmc_pd_table { - struct i40e_dma_mem pd_page_addr; /* populate to be used by hw */ - struct i40e_hmc_pd_entry *pd_entry; /* [512] for sw book keeping */ - struct i40e_virt_mem pd_entry_virt_mem; /* virt mem for pd_entry */ - - u32 ref_cnt; - u32 sd_index; -}; - -struct i40e_hmc_sd_entry { - enum i40e_sd_entry_type entry_type; - bool valid; - - union { - struct i40e_hmc_pd_table pd_table; - struct i40e_hmc_bp bp; - } u; -}; - -struct i40e_hmc_sd_table { - struct i40e_virt_mem addr; /* used to track sd_entry allocations */ - u32 sd_cnt; - u32 ref_cnt; - struct i40e_hmc_sd_entry *sd_entry; /* (sd_cnt*512) entries max */ -}; - -struct i40e_hmc_info { - u32 signature; - /* equals to pci func num for PF and dynamically allocated for VFs */ - u8 hmc_fn_id; - u16 first_sd_index; /* index of the first available SD */ - - /* hmc objects */ - struct i40e_hmc_obj_info *hmc_obj; - struct i40e_virt_mem hmc_obj_virt_mem; - struct i40e_hmc_sd_table sd_table; -}; - -#define I40E_INC_SD_REFCNT(sd_table) ((sd_table)->ref_cnt++) -#define I40E_INC_PD_REFCNT(pd_table) ((pd_table)->ref_cnt++) -#define I40E_INC_BP_REFCNT(bp) ((bp)->ref_cnt++) - -#define I40E_DEC_SD_REFCNT(sd_table) ((sd_table)->ref_cnt--) -#define I40E_DEC_PD_REFCNT(pd_table) ((pd_table)->ref_cnt--) -#define I40E_DEC_BP_REFCNT(bp) ((bp)->ref_cnt--) - -/** - * I40E_SET_PF_SD_ENTRY - marks the sd entry as valid in the hardware - * @hw: pointer to our hw struct - * @pa: pointer to physical address - * @sd_index: segment descriptor index - * @type: if sd entry is direct or paged - **/ -#define I40E_SET_PF_SD_ENTRY(hw, pa, sd_index, type) \ -{ \ - u32 val1, val2, val3; \ - val1 = (u32)(upper_32_bits(pa)); \ - val2 = (u32)(pa) | (I40E_HMC_MAX_BP_COUNT << \ - I40E_PFHMC_SDDATALOW_PMSDBPCOUNT_SHIFT) | \ - ((((type) == I40E_SD_TYPE_PAGED) ? 0 : 1) << \ - I40E_PFHMC_SDDATALOW_PMSDTYPE_SHIFT) | \ - BIT(I40E_PFHMC_SDDATALOW_PMSDVALID_SHIFT); \ - val3 = (sd_index) | BIT_ULL(I40E_PFHMC_SDCMD_PMSDWR_SHIFT); \ - wr32((hw), I40E_PFHMC_SDDATAHIGH, val1); \ - wr32((hw), I40E_PFHMC_SDDATALOW, val2); \ - wr32((hw), I40E_PFHMC_SDCMD, val3); \ -} - -/** - * I40E_CLEAR_PF_SD_ENTRY - marks the sd entry as invalid in the hardware - * @hw: pointer to our hw struct - * @sd_index: segment descriptor index - * @type: if sd entry is direct or paged - **/ -#define I40E_CLEAR_PF_SD_ENTRY(hw, sd_index, type) \ -{ \ - u32 val2, val3; \ - val2 = (I40E_HMC_MAX_BP_COUNT << \ - I40E_PFHMC_SDDATALOW_PMSDBPCOUNT_SHIFT) | \ - ((((type) == I40E_SD_TYPE_PAGED) ? 0 : 1) << \ - I40E_PFHMC_SDDATALOW_PMSDTYPE_SHIFT); \ - val3 = (sd_index) | BIT_ULL(I40E_PFHMC_SDCMD_PMSDWR_SHIFT); \ - wr32((hw), I40E_PFHMC_SDDATAHIGH, 0); \ - wr32((hw), I40E_PFHMC_SDDATALOW, val2); \ - wr32((hw), I40E_PFHMC_SDCMD, val3); \ -} - -/** - * I40E_INVALIDATE_PF_HMC_PD - Invalidates the pd cache in the hardware - * @hw: pointer to our hw struct - * @sd_idx: segment descriptor index - * @pd_idx: page descriptor index - **/ -#define I40E_INVALIDATE_PF_HMC_PD(hw, sd_idx, pd_idx) \ - wr32((hw), I40E_PFHMC_PDINV, \ - (((sd_idx) << I40E_PFHMC_PDINV_PMSDIDX_SHIFT) | \ - ((pd_idx) << I40E_PFHMC_PDINV_PMPDIDX_SHIFT))) - -/** - * I40E_FIND_SD_INDEX_LIMIT - finds segment descriptor index limit - * @hmc_info: pointer to the HMC configuration information structure - * @type: type of HMC resources we're searching - * @index: starting index for the object - * @cnt: number of objects we're trying to create - * @sd_idx: pointer to return index of the segment descriptor in question - * @sd_limit: pointer to return the maximum number of segment descriptors - * - * This function calculates the segment descriptor index and index limit - * for the resource defined by i40e_hmc_rsrc_type. - **/ -#define I40E_FIND_SD_INDEX_LIMIT(hmc_info, type, index, cnt, sd_idx, sd_limit)\ -{ \ - u64 fpm_addr, fpm_limit; \ - fpm_addr = (hmc_info)->hmc_obj[(type)].base + \ - (hmc_info)->hmc_obj[(type)].size * (index); \ - fpm_limit = fpm_addr + (hmc_info)->hmc_obj[(type)].size * (cnt);\ - *(sd_idx) = (u32)(fpm_addr / I40E_HMC_DIRECT_BP_SIZE); \ - *(sd_limit) = (u32)((fpm_limit - 1) / I40E_HMC_DIRECT_BP_SIZE); \ - /* add one more to the limit to correct our range */ \ - *(sd_limit) += 1; \ -} - -/** - * I40E_FIND_PD_INDEX_LIMIT - finds page descriptor index limit - * @hmc_info: pointer to the HMC configuration information struct - * @type: HMC resource type we're examining - * @idx: starting index for the object - * @cnt: number of objects we're trying to create - * @pd_index: pointer to return page descriptor index - * @pd_limit: pointer to return page descriptor index limit - * - * Calculates the page descriptor index and index limit for the resource - * defined by i40e_hmc_rsrc_type. - **/ -#define I40E_FIND_PD_INDEX_LIMIT(hmc_info, type, idx, cnt, pd_index, pd_limit)\ -{ \ - u64 fpm_adr, fpm_limit; \ - fpm_adr = (hmc_info)->hmc_obj[(type)].base + \ - (hmc_info)->hmc_obj[(type)].size * (idx); \ - fpm_limit = fpm_adr + (hmc_info)->hmc_obj[(type)].size * (cnt); \ - *(pd_index) = (u32)(fpm_adr / I40E_HMC_PAGED_BP_SIZE); \ - *(pd_limit) = (u32)((fpm_limit - 1) / I40E_HMC_PAGED_BP_SIZE); \ - /* add one more to the limit to correct our range */ \ - *(pd_limit) += 1; \ -} -i40e_status i40e_add_sd_table_entry(struct i40e_hw *hw, - struct i40e_hmc_info *hmc_info, - u32 sd_index, - enum i40e_sd_entry_type type, - u64 direct_mode_sz); - -i40e_status i40e_add_pd_table_entry(struct i40e_hw *hw, - struct i40e_hmc_info *hmc_info, - u32 pd_index, - struct i40e_dma_mem *rsrc_pg); -i40e_status i40e_remove_pd_bp(struct i40e_hw *hw, - struct i40e_hmc_info *hmc_info, - u32 idx); -i40e_status i40e_prep_remove_sd_bp(struct i40e_hmc_info *hmc_info, - u32 idx); -i40e_status i40e_remove_sd_bp_new(struct i40e_hw *hw, - struct i40e_hmc_info *hmc_info, - u32 idx, bool is_pf); -i40e_status i40e_prep_remove_pd_page(struct i40e_hmc_info *hmc_info, - u32 idx); -i40e_status i40e_remove_pd_page_new(struct i40e_hw *hw, - struct i40e_hmc_info *hmc_info, - u32 idx, bool is_pf); - -#endif /* _I40E_HMC_H_ */ diff --git a/drivers/net/ethernet/intel/i40evf/i40e_lan_hmc.h b/drivers/net/ethernet/intel/i40evf/i40e_lan_hmc.h deleted file mode 100644 index 82b00f70a632..000000000000 --- a/drivers/net/ethernet/intel/i40evf/i40e_lan_hmc.h +++ /dev/null @@ -1,158 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright(c) 2013 - 2018 Intel Corporation. */ - -#ifndef _I40E_LAN_HMC_H_ -#define _I40E_LAN_HMC_H_ - -/* forward-declare the HW struct for the compiler */ -struct i40e_hw; - -/* HMC element context information */ - -/* Rx queue context data - * - * The sizes of the variables may be larger than needed due to crossing byte - * boundaries. If we do not have the width of the variable set to the correct - * size then we could end up shifting bits off the top of the variable when the - * variable is at the top of a byte and crosses over into the next byte. - */ -struct i40e_hmc_obj_rxq { - u16 head; - u16 cpuid; /* bigger than needed, see above for reason */ - u64 base; - u16 qlen; -#define I40E_RXQ_CTX_DBUFF_SHIFT 7 - u16 dbuff; /* bigger than needed, see above for reason */ -#define I40E_RXQ_CTX_HBUFF_SHIFT 6 - u16 hbuff; /* bigger than needed, see above for reason */ - u8 dtype; - u8 dsize; - u8 crcstrip; - u8 fc_ena; - u8 l2tsel; - u8 hsplit_0; - u8 hsplit_1; - u8 showiv; - u32 rxmax; /* bigger than needed, see above for reason */ - u8 tphrdesc_ena; - u8 tphwdesc_ena; - u8 tphdata_ena; - u8 tphhead_ena; - u16 lrxqthresh; /* bigger than needed, see above for reason */ - u8 prefena; /* NOTE: normally must be set to 1 at init */ -}; - -/* Tx queue context data -* -* The sizes of the variables may be larger than needed due to crossing byte -* boundaries. If we do not have the width of the variable set to the correct -* size then we could end up shifting bits off the top of the variable when the -* variable is at the top of a byte and crosses over into the next byte. -*/ -struct i40e_hmc_obj_txq { - u16 head; - u8 new_context; - u64 base; - u8 fc_ena; - u8 timesync_ena; - u8 fd_ena; - u8 alt_vlan_ena; - u16 thead_wb; - u8 cpuid; - u8 head_wb_ena; - u16 qlen; - u8 tphrdesc_ena; - u8 tphrpacket_ena; - u8 tphwdesc_ena; - u64 head_wb_addr; - u32 crc; - u16 rdylist; - u8 rdylist_act; -}; - -/* for hsplit_0 field of Rx HMC context */ -enum i40e_hmc_obj_rx_hsplit_0 { - I40E_HMC_OBJ_RX_HSPLIT_0_NO_SPLIT = 0, - I40E_HMC_OBJ_RX_HSPLIT_0_SPLIT_L2 = 1, - I40E_HMC_OBJ_RX_HSPLIT_0_SPLIT_IP = 2, - I40E_HMC_OBJ_RX_HSPLIT_0_SPLIT_TCP_UDP = 4, - I40E_HMC_OBJ_RX_HSPLIT_0_SPLIT_SCTP = 8, -}; - -/* fcoe_cntx and fcoe_filt are for debugging purpose only */ -struct i40e_hmc_obj_fcoe_cntx { - u32 rsv[32]; -}; - -struct i40e_hmc_obj_fcoe_filt { - u32 rsv[8]; -}; - -/* Context sizes for LAN objects */ -enum i40e_hmc_lan_object_size { - I40E_HMC_LAN_OBJ_SZ_8 = 0x3, - I40E_HMC_LAN_OBJ_SZ_16 = 0x4, - I40E_HMC_LAN_OBJ_SZ_32 = 0x5, - I40E_HMC_LAN_OBJ_SZ_64 = 0x6, - I40E_HMC_LAN_OBJ_SZ_128 = 0x7, - I40E_HMC_LAN_OBJ_SZ_256 = 0x8, - I40E_HMC_LAN_OBJ_SZ_512 = 0x9, -}; - -#define I40E_HMC_L2OBJ_BASE_ALIGNMENT 512 -#define I40E_HMC_OBJ_SIZE_TXQ 128 -#define I40E_HMC_OBJ_SIZE_RXQ 32 -#define I40E_HMC_OBJ_SIZE_FCOE_CNTX 128 -#define I40E_HMC_OBJ_SIZE_FCOE_FILT 64 - -enum i40e_hmc_lan_rsrc_type { - I40E_HMC_LAN_FULL = 0, - I40E_HMC_LAN_TX = 1, - I40E_HMC_LAN_RX = 2, - I40E_HMC_FCOE_CTX = 3, - I40E_HMC_FCOE_FILT = 4, - I40E_HMC_LAN_MAX = 5 -}; - -enum i40e_hmc_model { - I40E_HMC_MODEL_DIRECT_PREFERRED = 0, - I40E_HMC_MODEL_DIRECT_ONLY = 1, - I40E_HMC_MODEL_PAGED_ONLY = 2, - I40E_HMC_MODEL_UNKNOWN, -}; - -struct i40e_hmc_lan_create_obj_info { - struct i40e_hmc_info *hmc_info; - u32 rsrc_type; - u32 start_idx; - u32 count; - enum i40e_sd_entry_type entry_type; - u64 direct_mode_sz; -}; - -struct i40e_hmc_lan_delete_obj_info { - struct i40e_hmc_info *hmc_info; - u32 rsrc_type; - u32 start_idx; - u32 count; -}; - -i40e_status i40e_init_lan_hmc(struct i40e_hw *hw, u32 txq_num, - u32 rxq_num, u32 fcoe_cntx_num, - u32 fcoe_filt_num); -i40e_status i40e_configure_lan_hmc(struct i40e_hw *hw, - enum i40e_hmc_model model); -i40e_status i40e_shutdown_lan_hmc(struct i40e_hw *hw); - -i40e_status i40e_clear_lan_tx_queue_context(struct i40e_hw *hw, - u16 queue); -i40e_status i40e_set_lan_tx_queue_context(struct i40e_hw *hw, - u16 queue, - struct i40e_hmc_obj_txq *s); -i40e_status i40e_clear_lan_rx_queue_context(struct i40e_hw *hw, - u16 queue); -i40e_status i40e_set_lan_rx_queue_context(struct i40e_hw *hw, - u16 queue, - struct i40e_hmc_obj_rxq *s); - -#endif /* _I40E_LAN_HMC_H_ */ diff --git a/drivers/net/ethernet/intel/i40evf/i40e_prototype.h b/drivers/net/ethernet/intel/i40evf/i40e_prototype.h deleted file mode 100644 index a358f4b9d5aa..000000000000 --- a/drivers/net/ethernet/intel/i40evf/i40e_prototype.h +++ /dev/null @@ -1,130 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright(c) 2013 - 2018 Intel Corporation. */ - -#ifndef _I40E_PROTOTYPE_H_ -#define _I40E_PROTOTYPE_H_ - -#include "i40e_type.h" -#include "i40e_alloc.h" -#include <linux/avf/virtchnl.h> - -/* Prototypes for shared code functions that are not in - * the standard function pointer structures. These are - * mostly because they are needed even before the init - * has happened and will assist in the early SW and FW - * setup. - */ - -/* adminq functions */ -i40e_status i40evf_init_adminq(struct i40e_hw *hw); -i40e_status i40evf_shutdown_adminq(struct i40e_hw *hw); -void i40e_adminq_init_ring_data(struct i40e_hw *hw); -i40e_status i40evf_clean_arq_element(struct i40e_hw *hw, - struct i40e_arq_event_info *e, - u16 *events_pending); -i40e_status i40evf_asq_send_command(struct i40e_hw *hw, - struct i40e_aq_desc *desc, - void *buff, /* can be NULL */ - u16 buff_size, - struct i40e_asq_cmd_details *cmd_details); -bool i40evf_asq_done(struct i40e_hw *hw); - -/* debug function for adminq */ -void i40evf_debug_aq(struct i40e_hw *hw, enum i40e_debug_mask mask, - void *desc, void *buffer, u16 buf_len); - -void i40e_idle_aq(struct i40e_hw *hw); -void i40evf_resume_aq(struct i40e_hw *hw); -bool i40evf_check_asq_alive(struct i40e_hw *hw); -i40e_status i40evf_aq_queue_shutdown(struct i40e_hw *hw, bool unloading); -const char *i40evf_aq_str(struct i40e_hw *hw, enum i40e_admin_queue_err aq_err); -const char *i40evf_stat_str(struct i40e_hw *hw, i40e_status stat_err); - -i40e_status i40evf_aq_get_rss_lut(struct i40e_hw *hw, u16 seid, - bool pf_lut, u8 *lut, u16 lut_size); -i40e_status i40evf_aq_set_rss_lut(struct i40e_hw *hw, u16 seid, - bool pf_lut, u8 *lut, u16 lut_size); -i40e_status i40evf_aq_get_rss_key(struct i40e_hw *hw, - u16 seid, - struct i40e_aqc_get_set_rss_key_data *key); -i40e_status i40evf_aq_set_rss_key(struct i40e_hw *hw, - u16 seid, - struct i40e_aqc_get_set_rss_key_data *key); - -i40e_status i40e_set_mac_type(struct i40e_hw *hw); - -extern struct i40e_rx_ptype_decoded i40evf_ptype_lookup[]; - -static inline struct i40e_rx_ptype_decoded decode_rx_desc_ptype(u8 ptype) -{ - return i40evf_ptype_lookup[ptype]; -} - -/* prototype for functions used for SW locks */ - -/* i40e_common for VF drivers*/ -void i40e_vf_parse_hw_config(struct i40e_hw *hw, - struct virtchnl_vf_resource *msg); -i40e_status i40e_vf_reset(struct i40e_hw *hw); -i40e_status i40e_aq_send_msg_to_pf(struct i40e_hw *hw, - enum virtchnl_ops v_opcode, - i40e_status v_retval, - u8 *msg, u16 msglen, - struct i40e_asq_cmd_details *cmd_details); -i40e_status i40e_set_filter_control(struct i40e_hw *hw, - struct i40e_filter_control_settings *settings); -i40e_status i40e_aq_add_rem_control_packet_filter(struct i40e_hw *hw, - u8 *mac_addr, u16 ethtype, u16 flags, - u16 vsi_seid, u16 queue, bool is_add, - struct i40e_control_filter_stats *stats, - struct i40e_asq_cmd_details *cmd_details); -void i40e_add_filter_to_drop_tx_flow_control_frames(struct i40e_hw *hw, - u16 vsi_seid); -i40e_status i40evf_aq_rx_ctl_read_register(struct i40e_hw *hw, - u32 reg_addr, u32 *reg_val, - struct i40e_asq_cmd_details *cmd_details); -u32 i40evf_read_rx_ctl(struct i40e_hw *hw, u32 reg_addr); -i40e_status i40evf_aq_rx_ctl_write_register(struct i40e_hw *hw, - u32 reg_addr, u32 reg_val, - struct i40e_asq_cmd_details *cmd_details); -void i40evf_write_rx_ctl(struct i40e_hw *hw, u32 reg_addr, u32 reg_val); -i40e_status i40e_aq_set_phy_register(struct i40e_hw *hw, - u8 phy_select, u8 dev_addr, - u32 reg_addr, u32 reg_val, - struct i40e_asq_cmd_details *cmd_details); -i40e_status i40e_aq_get_phy_register(struct i40e_hw *hw, - u8 phy_select, u8 dev_addr, - u32 reg_addr, u32 *reg_val, - struct i40e_asq_cmd_details *cmd_details); - -i40e_status i40e_read_phy_register(struct i40e_hw *hw, u8 page, - u16 reg, u8 phy_addr, u16 *value); -i40e_status i40e_write_phy_register(struct i40e_hw *hw, u8 page, - u16 reg, u8 phy_addr, u16 value); -i40e_status i40e_read_phy_register(struct i40e_hw *hw, u8 page, u16 reg, - u8 phy_addr, u16 *value); -i40e_status i40e_write_phy_register(struct i40e_hw *hw, u8 page, u16 reg, - u8 phy_addr, u16 value); -u8 i40e_get_phy_address(struct i40e_hw *hw, u8 dev_num); -i40e_status i40e_blink_phy_link_led(struct i40e_hw *hw, - u32 time, u32 interval); -i40e_status i40evf_aq_write_ddp(struct i40e_hw *hw, void *buff, - u16 buff_size, u32 track_id, - u32 *error_offset, u32 *error_info, - struct i40e_asq_cmd_details * - cmd_details); -i40e_status i40evf_aq_get_ddp_list(struct i40e_hw *hw, void *buff, - u16 buff_size, u8 flags, - struct i40e_asq_cmd_details * - cmd_details); -struct i40e_generic_seg_header * -i40evf_find_segment_in_package(u32 segment_type, - struct i40e_package_header *pkg_header); -enum i40e_status_code -i40evf_write_profile(struct i40e_hw *hw, struct i40e_profile_segment *i40e_seg, - u32 track_id); -enum i40e_status_code -i40evf_add_pinfo_to_list(struct i40e_hw *hw, - struct i40e_profile_segment *profile, - u8 *profile_info_sec, u32 track_id); -#endif /* _I40E_PROTOTYPE_H_ */ diff --git a/drivers/net/ethernet/intel/i40evf/i40e_register.h b/drivers/net/ethernet/intel/i40evf/i40e_register.h deleted file mode 100644 index 49e1f57d99cc..000000000000 --- a/drivers/net/ethernet/intel/i40evf/i40e_register.h +++ /dev/null @@ -1,313 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright(c) 2013 - 2018 Intel Corporation. */ - -#ifndef _I40E_REGISTER_H_ -#define _I40E_REGISTER_H_ - -#define I40E_VFMSIX_PBA1(_i) (0x00002000 + ((_i) * 4)) /* _i=0...19 */ /* Reset: VFLR */ -#define I40E_VFMSIX_PBA1_MAX_INDEX 19 -#define I40E_VFMSIX_PBA1_PENBIT_SHIFT 0 -#define I40E_VFMSIX_PBA1_PENBIT_MASK I40E_MASK(0xFFFFFFFF, I40E_VFMSIX_PBA1_PENBIT_SHIFT) -#define I40E_VFMSIX_TADD1(_i) (0x00002100 + ((_i) * 16)) /* _i=0...639 */ /* Reset: VFLR */ -#define I40E_VFMSIX_TADD1_MAX_INDEX 639 -#define I40E_VFMSIX_TADD1_MSIXTADD10_SHIFT 0 -#define I40E_VFMSIX_TADD1_MSIXTADD10_MASK I40E_MASK(0x3, I40E_VFMSIX_TADD1_MSIXTADD10_SHIFT) -#define I40E_VFMSIX_TADD1_MSIXTADD_SHIFT 2 -#define I40E_VFMSIX_TADD1_MSIXTADD_MASK I40E_MASK(0x3FFFFFFF, I40E_VFMSIX_TADD1_MSIXTADD_SHIFT) -#define I40E_VFMSIX_TMSG1(_i) (0x00002108 + ((_i) * 16)) /* _i=0...639 */ /* Reset: VFLR */ -#define I40E_VFMSIX_TMSG1_MAX_INDEX 639 -#define I40E_VFMSIX_TMSG1_MSIXTMSG_SHIFT 0 -#define I40E_VFMSIX_TMSG1_MSIXTMSG_MASK I40E_MASK(0xFFFFFFFF, I40E_VFMSIX_TMSG1_MSIXTMSG_SHIFT) -#define I40E_VFMSIX_TUADD1(_i) (0x00002104 + ((_i) * 16)) /* _i=0...639 */ /* Reset: VFLR */ -#define I40E_VFMSIX_TUADD1_MAX_INDEX 639 -#define I40E_VFMSIX_TUADD1_MSIXTUADD_SHIFT 0 -#define I40E_VFMSIX_TUADD1_MSIXTUADD_MASK I40E_MASK(0xFFFFFFFF, I40E_VFMSIX_TUADD1_MSIXTUADD_SHIFT) -#define I40E_VFMSIX_TVCTRL1(_i) (0x0000210C + ((_i) * 16)) /* _i=0...639 */ /* Reset: VFLR */ -#define I40E_VFMSIX_TVCTRL1_MAX_INDEX 639 -#define I40E_VFMSIX_TVCTRL1_MASK_SHIFT 0 -#define I40E_VFMSIX_TVCTRL1_MASK_MASK I40E_MASK(0x1, I40E_VFMSIX_TVCTRL1_MASK_SHIFT) -#define I40E_VF_ARQBAH1 0x00006000 /* Reset: EMPR */ -#define I40E_VF_ARQBAH1_ARQBAH_SHIFT 0 -#define I40E_VF_ARQBAH1_ARQBAH_MASK I40E_MASK(0xFFFFFFFF, I40E_VF_ARQBAH1_ARQBAH_SHIFT) -#define I40E_VF_ARQBAL1 0x00006C00 /* Reset: EMPR */ -#define I40E_VF_ARQBAL1_ARQBAL_SHIFT 0 -#define I40E_VF_ARQBAL1_ARQBAL_MASK I40E_MASK(0xFFFFFFFF, I40E_VF_ARQBAL1_ARQBAL_SHIFT) -#define I40E_VF_ARQH1 0x00007400 /* Reset: EMPR */ -#define I40E_VF_ARQH1_ARQH_SHIFT 0 -#define I40E_VF_ARQH1_ARQH_MASK I40E_MASK(0x3FF, I40E_VF_ARQH1_ARQH_SHIFT) -#define I40E_VF_ARQLEN1 0x00008000 /* Reset: EMPR */ -#define I40E_VF_ARQLEN1_ARQLEN_SHIFT 0 -#define I40E_VF_ARQLEN1_ARQLEN_MASK I40E_MASK(0x3FF, I40E_VF_ARQLEN1_ARQLEN_SHIFT) -#define I40E_VF_ARQLEN1_ARQVFE_SHIFT 28 -#define I40E_VF_ARQLEN1_ARQVFE_MASK I40E_MASK(0x1, I40E_VF_ARQLEN1_ARQVFE_SHIFT) -#define I40E_VF_ARQLEN1_ARQOVFL_SHIFT 29 -#define I40E_VF_ARQLEN1_ARQOVFL_MASK I40E_MASK(0x1, I40E_VF_ARQLEN1_ARQOVFL_SHIFT) -#define I40E_VF_ARQLEN1_ARQCRIT_SHIFT 30 -#define I40E_VF_ARQLEN1_ARQCRIT_MASK I40E_MASK(0x1, I40E_VF_ARQLEN1_ARQCRIT_SHIFT) -#define I40E_VF_ARQLEN1_ARQENABLE_SHIFT 31 -#define I40E_VF_ARQLEN1_ARQENABLE_MASK I40E_MASK(0x1, I40E_VF_ARQLEN1_ARQENABLE_SHIFT) -#define I40E_VF_ARQT1 0x00007000 /* Reset: EMPR */ -#define I40E_VF_ARQT1_ARQT_SHIFT 0 -#define I40E_VF_ARQT1_ARQT_MASK I40E_MASK(0x3FF, I40E_VF_ARQT1_ARQT_SHIFT) -#define I40E_VF_ATQBAH1 0x00007800 /* Reset: EMPR */ -#define I40E_VF_ATQBAH1_ATQBAH_SHIFT 0 -#define I40E_VF_ATQBAH1_ATQBAH_MASK I40E_MASK(0xFFFFFFFF, I40E_VF_ATQBAH1_ATQBAH_SHIFT) -#define I40E_VF_ATQBAL1 0x00007C00 /* Reset: EMPR */ -#define I40E_VF_ATQBAL1_ATQBAL_SHIFT 0 -#define I40E_VF_ATQBAL1_ATQBAL_MASK I40E_MASK(0xFFFFFFFF, I40E_VF_ATQBAL1_ATQBAL_SHIFT) -#define I40E_VF_ATQH1 0x00006400 /* Reset: EMPR */ -#define I40E_VF_ATQH1_ATQH_SHIFT 0 -#define I40E_VF_ATQH1_ATQH_MASK I40E_MASK(0x3FF, I40E_VF_ATQH1_ATQH_SHIFT) -#define I40E_VF_ATQLEN1 0x00006800 /* Reset: EMPR */ -#define I40E_VF_ATQLEN1_ATQLEN_SHIFT 0 -#define I40E_VF_ATQLEN1_ATQLEN_MASK I40E_MASK(0x3FF, I40E_VF_ATQLEN1_ATQLEN_SHIFT) -#define I40E_VF_ATQLEN1_ATQVFE_SHIFT 28 -#define I40E_VF_ATQLEN1_ATQVFE_MASK I40E_MASK(0x1, I40E_VF_ATQLEN1_ATQVFE_SHIFT) -#define I40E_VF_ATQLEN1_ATQOVFL_SHIFT 29 -#define I40E_VF_ATQLEN1_ATQOVFL_MASK I40E_MASK(0x1, I40E_VF_ATQLEN1_ATQOVFL_SHIFT) -#define I40E_VF_ATQLEN1_ATQCRIT_SHIFT 30 -#define I40E_VF_ATQLEN1_ATQCRIT_MASK I40E_MASK(0x1, I40E_VF_ATQLEN1_ATQCRIT_SHIFT) -#define I40E_VF_ATQLEN1_ATQENABLE_SHIFT 31 -#define I40E_VF_ATQLEN1_ATQENABLE_MASK I40E_MASK(0x1, I40E_VF_ATQLEN1_ATQENABLE_SHIFT) -#define I40E_VF_ATQT1 0x00008400 /* Reset: EMPR */ -#define I40E_VF_ATQT1_ATQT_SHIFT 0 -#define I40E_VF_ATQT1_ATQT_MASK I40E_MASK(0x3FF, I40E_VF_ATQT1_ATQT_SHIFT) -#define I40E_VFGEN_RSTAT 0x00008800 /* Reset: VFR */ -#define I40E_VFGEN_RSTAT_VFR_STATE_SHIFT 0 -#define I40E_VFGEN_RSTAT_VFR_STATE_MASK I40E_MASK(0x3, I40E_VFGEN_RSTAT_VFR_STATE_SHIFT) -#define I40E_VFINT_DYN_CTL01 0x00005C00 /* Reset: VFR */ -#define I40E_VFINT_DYN_CTL01_INTENA_SHIFT 0 -#define I40E_VFINT_DYN_CTL01_INTENA_MASK I40E_MASK(0x1, I40E_VFINT_DYN_CTL01_INTENA_SHIFT) -#define I40E_VFINT_DYN_CTL01_CLEARPBA_SHIFT 1 -#define I40E_VFINT_DYN_CTL01_CLEARPBA_MASK I40E_MASK(0x1, I40E_VFINT_DYN_CTL01_CLEARPBA_SHIFT) -#define I40E_VFINT_DYN_CTL01_SWINT_TRIG_SHIFT 2 -#define I40E_VFINT_DYN_CTL01_SWINT_TRIG_MASK I40E_MASK(0x1, I40E_VFINT_DYN_CTL01_SWINT_TRIG_SHIFT) -#define I40E_VFINT_DYN_CTL01_ITR_INDX_SHIFT 3 -#define I40E_VFINT_DYN_CTL01_ITR_INDX_MASK I40E_MASK(0x3, I40E_VFINT_DYN_CTL01_ITR_INDX_SHIFT) -#define I40E_VFINT_DYN_CTL01_INTERVAL_SHIFT 5 -#define I40E_VFINT_DYN_CTL01_INTERVAL_MASK I40E_MASK(0xFFF, I40E_VFINT_DYN_CTL01_INTERVAL_SHIFT) -#define I40E_VFINT_DYN_CTL01_SW_ITR_INDX_ENA_SHIFT 24 -#define I40E_VFINT_DYN_CTL01_SW_ITR_INDX_ENA_MASK I40E_MASK(0x1, I40E_VFINT_DYN_CTL01_SW_ITR_INDX_ENA_SHIFT) -#define I40E_VFINT_DYN_CTL01_SW_ITR_INDX_SHIFT 25 -#define I40E_VFINT_DYN_CTL01_SW_ITR_INDX_MASK I40E_MASK(0x3, I40E_VFINT_DYN_CTL01_SW_ITR_INDX_SHIFT) -#define I40E_VFINT_DYN_CTL01_INTENA_MSK_SHIFT 31 -#define I40E_VFINT_DYN_CTL01_INTENA_MSK_MASK I40E_MASK(0x1, I40E_VFINT_DYN_CTL01_INTENA_MSK_SHIFT) -#define I40E_VFINT_DYN_CTLN1(_INTVF) (0x00003800 + ((_INTVF) * 4)) /* _i=0...15 */ /* Reset: VFR */ -#define I40E_VFINT_DYN_CTLN1_MAX_INDEX 15 -#define I40E_VFINT_DYN_CTLN1_INTENA_SHIFT 0 -#define I40E_VFINT_DYN_CTLN1_INTENA_MASK I40E_MASK(0x1, I40E_VFINT_DYN_CTLN1_INTENA_SHIFT) -#define I40E_VFINT_DYN_CTLN1_CLEARPBA_SHIFT 1 -#define I40E_VFINT_DYN_CTLN1_CLEARPBA_MASK I40E_MASK(0x1, I40E_VFINT_DYN_CTLN1_CLEARPBA_SHIFT) -#define I40E_VFINT_DYN_CTLN1_SWINT_TRIG_SHIFT 2 -#define I40E_VFINT_DYN_CTLN1_SWINT_TRIG_MASK I40E_MASK(0x1, I40E_VFINT_DYN_CTLN1_SWINT_TRIG_SHIFT) -#define I40E_VFINT_DYN_CTLN1_ITR_INDX_SHIFT 3 -#define I40E_VFINT_DYN_CTLN1_ITR_INDX_MASK I40E_MASK(0x3, I40E_VFINT_DYN_CTLN1_ITR_INDX_SHIFT) -#define I40E_VFINT_DYN_CTLN1_INTERVAL_SHIFT 5 -#define I40E_VFINT_DYN_CTLN1_INTERVAL_MASK I40E_MASK(0xFFF, I40E_VFINT_DYN_CTLN1_INTERVAL_SHIFT) -#define I40E_VFINT_DYN_CTLN1_SW_ITR_INDX_ENA_SHIFT 24 -#define I40E_VFINT_DYN_CTLN1_SW_ITR_INDX_ENA_MASK I40E_MASK(0x1, I40E_VFINT_DYN_CTLN1_SW_ITR_INDX_ENA_SHIFT) -#define I40E_VFINT_DYN_CTLN1_SW_ITR_INDX_SHIFT 25 -#define I40E_VFINT_DYN_CTLN1_SW_ITR_INDX_MASK I40E_MASK(0x3, I40E_VFINT_DYN_CTLN1_SW_ITR_INDX_SHIFT) -#define I40E_VFINT_DYN_CTLN1_INTENA_MSK_SHIFT 31 -#define I40E_VFINT_DYN_CTLN1_INTENA_MSK_MASK I40E_MASK(0x1, I40E_VFINT_DYN_CTLN1_INTENA_MSK_SHIFT) -#define I40E_VFINT_ICR0_ENA1 0x00005000 /* Reset: CORER */ -#define I40E_VFINT_ICR0_ENA1_LINK_STAT_CHANGE_SHIFT 25 -#define I40E_VFINT_ICR0_ENA1_LINK_STAT_CHANGE_MASK I40E_MASK(0x1, I40E_VFINT_ICR0_ENA1_LINK_STAT_CHANGE_SHIFT) -#define I40E_VFINT_ICR0_ENA1_ADMINQ_SHIFT 30 -#define I40E_VFINT_ICR0_ENA1_ADMINQ_MASK I40E_MASK(0x1, I40E_VFINT_ICR0_ENA1_ADMINQ_SHIFT) -#define I40E_VFINT_ICR0_ENA1_RSVD_SHIFT 31 -#define I40E_VFINT_ICR0_ENA1_RSVD_MASK I40E_MASK(0x1, I40E_VFINT_ICR0_ENA1_RSVD_SHIFT) -#define I40E_VFINT_ICR01 0x00004800 /* Reset: CORER */ -#define I40E_VFINT_ICR01_INTEVENT_SHIFT 0 -#define I40E_VFINT_ICR01_INTEVENT_MASK I40E_MASK(0x1, I40E_VFINT_ICR01_INTEVENT_SHIFT) -#define I40E_VFINT_ICR01_QUEUE_0_SHIFT 1 -#define I40E_VFINT_ICR01_QUEUE_0_MASK I40E_MASK(0x1, I40E_VFINT_ICR01_QUEUE_0_SHIFT) -#define I40E_VFINT_ICR01_QUEUE_1_SHIFT 2 -#define I40E_VFINT_ICR01_QUEUE_1_MASK I40E_MASK(0x1, I40E_VFINT_ICR01_QUEUE_1_SHIFT) -#define I40E_VFINT_ICR01_QUEUE_2_SHIFT 3 -#define I40E_VFINT_ICR01_QUEUE_2_MASK I40E_MASK(0x1, I40E_VFINT_ICR01_QUEUE_2_SHIFT) -#define I40E_VFINT_ICR01_QUEUE_3_SHIFT 4 -#define I40E_VFINT_ICR01_QUEUE_3_MASK I40E_MASK(0x1, I40E_VFINT_ICR01_QUEUE_3_SHIFT) -#define I40E_VFINT_ICR01_LINK_STAT_CHANGE_SHIFT 25 -#define I40E_VFINT_ICR01_LINK_STAT_CHANGE_MASK I40E_MASK(0x1, I40E_VFINT_ICR01_LINK_STAT_CHANGE_SHIFT) -#define I40E_VFINT_ICR01_ADMINQ_SHIFT 30 -#define I40E_VFINT_ICR01_ADMINQ_MASK I40E_MASK(0x1, I40E_VFINT_ICR01_ADMINQ_SHIFT) -#define I40E_VFINT_ICR01_SWINT_SHIFT 31 -#define I40E_VFINT_ICR01_SWINT_MASK I40E_MASK(0x1, I40E_VFINT_ICR01_SWINT_SHIFT) -#define I40E_VFINT_ITR01(_i) (0x00004C00 + ((_i) * 4)) /* _i=0...2 */ /* Reset: VFR */ -#define I40E_VFINT_ITR01_MAX_INDEX 2 -#define I40E_VFINT_ITR01_INTERVAL_SHIFT 0 -#define I40E_VFINT_ITR01_INTERVAL_MASK I40E_MASK(0xFFF, I40E_VFINT_ITR01_INTERVAL_SHIFT) -#define I40E_VFINT_ITRN1(_i, _INTVF) (0x00002800 + ((_i) * 64 + (_INTVF) * 4)) /* _i=0...2, _INTVF=0...15 */ /* Reset: VFR */ -#define I40E_VFINT_ITRN1_MAX_INDEX 2 -#define I40E_VFINT_ITRN1_INTERVAL_SHIFT 0 -#define I40E_VFINT_ITRN1_INTERVAL_MASK I40E_MASK(0xFFF, I40E_VFINT_ITRN1_INTERVAL_SHIFT) -#define I40E_VFINT_STAT_CTL01 0x00005400 /* Reset: CORER */ -#define I40E_VFINT_STAT_CTL01_OTHER_ITR_INDX_SHIFT 2 -#define I40E_VFINT_STAT_CTL01_OTHER_ITR_INDX_MASK I40E_MASK(0x3, I40E_VFINT_STAT_CTL01_OTHER_ITR_INDX_SHIFT) -#define I40E_QRX_TAIL1(_Q) (0x00002000 + ((_Q) * 4)) /* _i=0...15 */ /* Reset: CORER */ -#define I40E_QRX_TAIL1_MAX_INDEX 15 -#define I40E_QRX_TAIL1_TAIL_SHIFT 0 -#define I40E_QRX_TAIL1_TAIL_MASK I40E_MASK(0x1FFF, I40E_QRX_TAIL1_TAIL_SHIFT) -#define I40E_QTX_TAIL1(_Q) (0x00000000 + ((_Q) * 4)) /* _i=0...15 */ /* Reset: PFR */ -#define I40E_QTX_TAIL1_MAX_INDEX 15 -#define I40E_QTX_TAIL1_TAIL_SHIFT 0 -#define I40E_QTX_TAIL1_TAIL_MASK I40E_MASK(0x1FFF, I40E_QTX_TAIL1_TAIL_SHIFT) -#define I40E_VFMSIX_PBA 0x00002000 /* Reset: VFLR */ -#define I40E_VFMSIX_PBA_PENBIT_SHIFT 0 -#define I40E_VFMSIX_PBA_PENBIT_MASK I40E_MASK(0xFFFFFFFF, I40E_VFMSIX_PBA_PENBIT_SHIFT) -#define I40E_VFMSIX_TADD(_i) (0x00000000 + ((_i) * 16)) /* _i=0...16 */ /* Reset: VFLR */ -#define I40E_VFMSIX_TADD_MAX_INDEX 16 -#define I40E_VFMSIX_TADD_MSIXTADD10_SHIFT 0 -#define I40E_VFMSIX_TADD_MSIXTADD10_MASK I40E_MASK(0x3, I40E_VFMSIX_TADD_MSIXTADD10_SHIFT) -#define I40E_VFMSIX_TADD_MSIXTADD_SHIFT 2 -#define I40E_VFMSIX_TADD_MSIXTADD_MASK I40E_MASK(0x3FFFFFFF, I40E_VFMSIX_TADD_MSIXTADD_SHIFT) -#define I40E_VFMSIX_TMSG(_i) (0x00000008 + ((_i) * 16)) /* _i=0...16 */ /* Reset: VFLR */ -#define I40E_VFMSIX_TMSG_MAX_INDEX 16 -#define I40E_VFMSIX_TMSG_MSIXTMSG_SHIFT 0 -#define I40E_VFMSIX_TMSG_MSIXTMSG_MASK I40E_MASK(0xFFFFFFFF, I40E_VFMSIX_TMSG_MSIXTMSG_SHIFT) -#define I40E_VFMSIX_TUADD(_i) (0x00000004 + ((_i) * 16)) /* _i=0...16 */ /* Reset: VFLR */ -#define I40E_VFMSIX_TUADD_MAX_INDEX 16 -#define I40E_VFMSIX_TUADD_MSIXTUADD_SHIFT 0 -#define I40E_VFMSIX_TUADD_MSIXTUADD_MASK I40E_MASK(0xFFFFFFFF, I40E_VFMSIX_TUADD_MSIXTUADD_SHIFT) -#define I40E_VFMSIX_TVCTRL(_i) (0x0000000C + ((_i) * 16)) /* _i=0...16 */ /* Reset: VFLR */ -#define I40E_VFMSIX_TVCTRL_MAX_INDEX 16 -#define I40E_VFMSIX_TVCTRL_MASK_SHIFT 0 -#define I40E_VFMSIX_TVCTRL_MASK_MASK I40E_MASK(0x1, I40E_VFMSIX_TVCTRL_MASK_SHIFT) -#define I40E_VFCM_PE_ERRDATA 0x0000DC00 /* Reset: VFR */ -#define I40E_VFCM_PE_ERRDATA_ERROR_CODE_SHIFT 0 -#define I40E_VFCM_PE_ERRDATA_ERROR_CODE_MASK I40E_MASK(0xF, I40E_VFCM_PE_ERRDATA_ERROR_CODE_SHIFT) -#define I40E_VFCM_PE_ERRDATA_Q_TYPE_SHIFT 4 -#define I40E_VFCM_PE_ERRDATA_Q_TYPE_MASK I40E_MASK(0x7, I40E_VFCM_PE_ERRDATA_Q_TYPE_SHIFT) -#define I40E_VFCM_PE_ERRDATA_Q_NUM_SHIFT 8 -#define I40E_VFCM_PE_ERRDATA_Q_NUM_MASK I40E_MASK(0x3FFFF, I40E_VFCM_PE_ERRDATA_Q_NUM_SHIFT) -#define I40E_VFCM_PE_ERRINFO 0x0000D800 /* Reset: VFR */ -#define I40E_VFCM_PE_ERRINFO_ERROR_VALID_SHIFT 0 -#define I40E_VFCM_PE_ERRINFO_ERROR_VALID_MASK I40E_MASK(0x1, I40E_VFCM_PE_ERRINFO_ERROR_VALID_SHIFT) -#define I40E_VFCM_PE_ERRINFO_ERROR_INST_SHIFT 4 -#define I40E_VFCM_PE_ERRINFO_ERROR_INST_MASK I40E_MASK(0x7, I40E_VFCM_PE_ERRINFO_ERROR_INST_SHIFT) -#define I40E_VFCM_PE_ERRINFO_DBL_ERROR_CNT_SHIFT 8 -#define I40E_VFCM_PE_ERRINFO_DBL_ERROR_CNT_MASK I40E_MASK(0xFF, I40E_VFCM_PE_ERRINFO_DBL_ERROR_CNT_SHIFT) -#define I40E_VFCM_PE_ERRINFO_RLU_ERROR_CNT_SHIFT 16 -#define I40E_VFCM_PE_ERRINFO_RLU_ERROR_CNT_MASK I40E_MASK(0xFF, I40E_VFCM_PE_ERRINFO_RLU_ERROR_CNT_SHIFT) -#define I40E_VFCM_PE_ERRINFO_RLS_ERROR_CNT_SHIFT 24 -#define I40E_VFCM_PE_ERRINFO_RLS_ERROR_CNT_MASK I40E_MASK(0xFF, I40E_VFCM_PE_ERRINFO_RLS_ERROR_CNT_SHIFT) -#define I40E_VFQF_HENA(_i) (0x0000C400 + ((_i) * 4)) /* _i=0...1 */ /* Reset: CORER */ -#define I40E_VFQF_HENA_MAX_INDEX 1 -#define I40E_VFQF_HENA_PTYPE_ENA_SHIFT 0 -#define I40E_VFQF_HENA_PTYPE_ENA_MASK I40E_MASK(0xFFFFFFFF, I40E_VFQF_HENA_PTYPE_ENA_SHIFT) -#define I40E_VFQF_HKEY(_i) (0x0000CC00 + ((_i) * 4)) /* _i=0...12 */ /* Reset: CORER */ -#define I40E_VFQF_HKEY_MAX_INDEX 12 -#define I40E_VFQF_HKEY_KEY_0_SHIFT 0 -#define I40E_VFQF_HKEY_KEY_0_MASK I40E_MASK(0xFF, I40E_VFQF_HKEY_KEY_0_SHIFT) -#define I40E_VFQF_HKEY_KEY_1_SHIFT 8 -#define I40E_VFQF_HKEY_KEY_1_MASK I40E_MASK(0xFF, I40E_VFQF_HKEY_KEY_1_SHIFT) -#define I40E_VFQF_HKEY_KEY_2_SHIFT 16 -#define I40E_VFQF_HKEY_KEY_2_MASK I40E_MASK(0xFF, I40E_VFQF_HKEY_KEY_2_SHIFT) -#define I40E_VFQF_HKEY_KEY_3_SHIFT 24 -#define I40E_VFQF_HKEY_KEY_3_MASK I40E_MASK(0xFF, I40E_VFQF_HKEY_KEY_3_SHIFT) -#define I40E_VFQF_HLUT(_i) (0x0000D000 + ((_i) * 4)) /* _i=0...15 */ /* Reset: CORER */ -#define I40E_VFQF_HLUT_MAX_INDEX 15 -#define I40E_VFQF_HLUT_LUT0_SHIFT 0 -#define I40E_VFQF_HLUT_LUT0_MASK I40E_MASK(0xF, I40E_VFQF_HLUT_LUT0_SHIFT) -#define I40E_VFQF_HLUT_LUT1_SHIFT 8 -#define I40E_VFQF_HLUT_LUT1_MASK I40E_MASK(0xF, I40E_VFQF_HLUT_LUT1_SHIFT) -#define I40E_VFQF_HLUT_LUT2_SHIFT 16 -#define I40E_VFQF_HLUT_LUT2_MASK I40E_MASK(0xF, I40E_VFQF_HLUT_LUT2_SHIFT) -#define I40E_VFQF_HLUT_LUT3_SHIFT 24 -#define I40E_VFQF_HLUT_LUT3_MASK I40E_MASK(0xF, I40E_VFQF_HLUT_LUT3_SHIFT) -#define I40E_VFQF_HREGION(_i) (0x0000D400 + ((_i) * 4)) /* _i=0...7 */ /* Reset: CORER */ -#define I40E_VFQF_HREGION_MAX_INDEX 7 -#define I40E_VFQF_HREGION_OVERRIDE_ENA_0_SHIFT 0 -#define I40E_VFQF_HREGION_OVERRIDE_ENA_0_MASK I40E_MASK(0x1, I40E_VFQF_HREGION_OVERRIDE_ENA_0_SHIFT) -#define I40E_VFQF_HREGION_REGION_0_SHIFT 1 -#define I40E_VFQF_HREGION_REGION_0_MASK I40E_MASK(0x7, I40E_VFQF_HREGION_REGION_0_SHIFT) -#define I40E_VFQF_HREGION_OVERRIDE_ENA_1_SHIFT 4 -#define I40E_VFQF_HREGION_OVERRIDE_ENA_1_MASK I40E_MASK(0x1, I40E_VFQF_HREGION_OVERRIDE_ENA_1_SHIFT) -#define I40E_VFQF_HREGION_REGION_1_SHIFT 5 -#define I40E_VFQF_HREGION_REGION_1_MASK I40E_MASK(0x7, I40E_VFQF_HREGION_REGION_1_SHIFT) -#define I40E_VFQF_HREGION_OVERRIDE_ENA_2_SHIFT 8 -#define I40E_VFQF_HREGION_OVERRIDE_ENA_2_MASK I40E_MASK(0x1, I40E_VFQF_HREGION_OVERRIDE_ENA_2_SHIFT) -#define I40E_VFQF_HREGION_REGION_2_SHIFT 9 -#define I40E_VFQF_HREGION_REGION_2_MASK I40E_MASK(0x7, I40E_VFQF_HREGION_REGION_2_SHIFT) -#define I40E_VFQF_HREGION_OVERRIDE_ENA_3_SHIFT 12 -#define I40E_VFQF_HREGION_OVERRIDE_ENA_3_MASK I40E_MASK(0x1, I40E_VFQF_HREGION_OVERRIDE_ENA_3_SHIFT) -#define I40E_VFQF_HREGION_REGION_3_SHIFT 13 -#define I40E_VFQF_HREGION_REGION_3_MASK I40E_MASK(0x7, I40E_VFQF_HREGION_REGION_3_SHIFT) -#define I40E_VFQF_HREGION_OVERRIDE_ENA_4_SHIFT 16 -#define I40E_VFQF_HREGION_OVERRIDE_ENA_4_MASK I40E_MASK(0x1, I40E_VFQF_HREGION_OVERRIDE_ENA_4_SHIFT) -#define I40E_VFQF_HREGION_REGION_4_SHIFT 17 -#define I40E_VFQF_HREGION_REGION_4_MASK I40E_MASK(0x7, I40E_VFQF_HREGION_REGION_4_SHIFT) -#define I40E_VFQF_HREGION_OVERRIDE_ENA_5_SHIFT 20 -#define I40E_VFQF_HREGION_OVERRIDE_ENA_5_MASK I40E_MASK(0x1, I40E_VFQF_HREGION_OVERRIDE_ENA_5_SHIFT) -#define I40E_VFQF_HREGION_REGION_5_SHIFT 21 -#define I40E_VFQF_HREGION_REGION_5_MASK I40E_MASK(0x7, I40E_VFQF_HREGION_REGION_5_SHIFT) -#define I40E_VFQF_HREGION_OVERRIDE_ENA_6_SHIFT 24 -#define I40E_VFQF_HREGION_OVERRIDE_ENA_6_MASK I40E_MASK(0x1, I40E_VFQF_HREGION_OVERRIDE_ENA_6_SHIFT) -#define I40E_VFQF_HREGION_REGION_6_SHIFT 25 -#define I40E_VFQF_HREGION_REGION_6_MASK I40E_MASK(0x7, I40E_VFQF_HREGION_REGION_6_SHIFT) -#define I40E_VFQF_HREGION_OVERRIDE_ENA_7_SHIFT 28 -#define I40E_VFQF_HREGION_OVERRIDE_ENA_7_MASK I40E_MASK(0x1, I40E_VFQF_HREGION_OVERRIDE_ENA_7_SHIFT) -#define I40E_VFQF_HREGION_REGION_7_SHIFT 29 -#define I40E_VFQF_HREGION_REGION_7_MASK I40E_MASK(0x7, I40E_VFQF_HREGION_REGION_7_SHIFT) -#define I40E_VFINT_DYN_CTL01_WB_ON_ITR_SHIFT 30 -#define I40E_VFINT_DYN_CTL01_WB_ON_ITR_MASK I40E_MASK(0x1, I40E_VFINT_DYN_CTL01_WB_ON_ITR_SHIFT) -#define I40E_VFINT_DYN_CTLN1_WB_ON_ITR_SHIFT 30 -#define I40E_VFINT_DYN_CTLN1_WB_ON_ITR_MASK I40E_MASK(0x1, I40E_VFINT_DYN_CTLN1_WB_ON_ITR_SHIFT) -#define I40E_VFPE_AEQALLOC1 0x0000A400 /* Reset: VFR */ -#define I40E_VFPE_AEQALLOC1_AECOUNT_SHIFT 0 -#define I40E_VFPE_AEQALLOC1_AECOUNT_MASK I40E_MASK(0xFFFFFFFF, I40E_VFPE_AEQALLOC1_AECOUNT_SHIFT) -#define I40E_VFPE_CCQPHIGH1 0x00009800 /* Reset: VFR */ -#define I40E_VFPE_CCQPHIGH1_PECCQPHIGH_SHIFT 0 -#define I40E_VFPE_CCQPHIGH1_PECCQPHIGH_MASK I40E_MASK(0xFFFFFFFF, I40E_VFPE_CCQPHIGH1_PECCQPHIGH_SHIFT) -#define I40E_VFPE_CCQPLOW1 0x0000AC00 /* Reset: VFR */ -#define I40E_VFPE_CCQPLOW1_PECCQPLOW_SHIFT 0 -#define I40E_VFPE_CCQPLOW1_PECCQPLOW_MASK I40E_MASK(0xFFFFFFFF, I40E_VFPE_CCQPLOW1_PECCQPLOW_SHIFT) -#define I40E_VFPE_CCQPSTATUS1 0x0000B800 /* Reset: VFR */ -#define I40E_VFPE_CCQPSTATUS1_CCQP_DONE_SHIFT 0 -#define I40E_VFPE_CCQPSTATUS1_CCQP_DONE_MASK I40E_MASK(0x1, I40E_VFPE_CCQPSTATUS1_CCQP_DONE_SHIFT) -#define I40E_VFPE_CCQPSTATUS1_HMC_PROFILE_SHIFT 4 -#define I40E_VFPE_CCQPSTATUS1_HMC_PROFILE_MASK I40E_MASK(0x7, I40E_VFPE_CCQPSTATUS1_HMC_PROFILE_SHIFT) -#define I40E_VFPE_CCQPSTATUS1_RDMA_EN_VFS_SHIFT 16 -#define I40E_VFPE_CCQPSTATUS1_RDMA_EN_VFS_MASK I40E_MASK(0x3F, I40E_VFPE_CCQPSTATUS1_RDMA_EN_VFS_SHIFT) -#define I40E_VFPE_CCQPSTATUS1_CCQP_ERR_SHIFT 31 -#define I40E_VFPE_CCQPSTATUS1_CCQP_ERR_MASK I40E_MASK(0x1, I40E_VFPE_CCQPSTATUS1_CCQP_ERR_SHIFT) -#define I40E_VFPE_CQACK1 0x0000B000 /* Reset: VFR */ -#define I40E_VFPE_CQACK1_PECQID_SHIFT 0 -#define I40E_VFPE_CQACK1_PECQID_MASK I40E_MASK(0x1FFFF, I40E_VFPE_CQACK1_PECQID_SHIFT) -#define I40E_VFPE_CQARM1 0x0000B400 /* Reset: VFR */ -#define I40E_VFPE_CQARM1_PECQID_SHIFT 0 -#define I40E_VFPE_CQARM1_PECQID_MASK I40E_MASK(0x1FFFF, I40E_VFPE_CQARM1_PECQID_SHIFT) -#define I40E_VFPE_CQPDB1 0x0000BC00 /* Reset: VFR */ -#define I40E_VFPE_CQPDB1_WQHEAD_SHIFT 0 -#define I40E_VFPE_CQPDB1_WQHEAD_MASK I40E_MASK(0x7FF, I40E_VFPE_CQPDB1_WQHEAD_SHIFT) -#define I40E_VFPE_CQPERRCODES1 0x00009C00 /* Reset: VFR */ -#define I40E_VFPE_CQPERRCODES1_CQP_MINOR_CODE_SHIFT 0 -#define I40E_VFPE_CQPERRCODES1_CQP_MINOR_CODE_MASK I40E_MASK(0xFFFF, I40E_VFPE_CQPERRCODES1_CQP_MINOR_CODE_SHIFT) -#define I40E_VFPE_CQPERRCODES1_CQP_MAJOR_CODE_SHIFT 16 -#define I40E_VFPE_CQPERRCODES1_CQP_MAJOR_CODE_MASK I40E_MASK(0xFFFF, I40E_VFPE_CQPERRCODES1_CQP_MAJOR_CODE_SHIFT) -#define I40E_VFPE_CQPTAIL1 0x0000A000 /* Reset: VFR */ -#define I40E_VFPE_CQPTAIL1_WQTAIL_SHIFT 0 -#define I40E_VFPE_CQPTAIL1_WQTAIL_MASK I40E_MASK(0x7FF, I40E_VFPE_CQPTAIL1_WQTAIL_SHIFT) -#define I40E_VFPE_CQPTAIL1_CQP_OP_ERR_SHIFT 31 -#define I40E_VFPE_CQPTAIL1_CQP_OP_ERR_MASK I40E_MASK(0x1, I40E_VFPE_CQPTAIL1_CQP_OP_ERR_SHIFT) -#define I40E_VFPE_IPCONFIG01 0x00008C00 /* Reset: VFR */ -#define I40E_VFPE_IPCONFIG01_PEIPID_SHIFT 0 -#define I40E_VFPE_IPCONFIG01_PEIPID_MASK I40E_MASK(0xFFFF, I40E_VFPE_IPCONFIG01_PEIPID_SHIFT) -#define I40E_VFPE_IPCONFIG01_USEENTIREIDRANGE_SHIFT 16 -#define I40E_VFPE_IPCONFIG01_USEENTIREIDRANGE_MASK I40E_MASK(0x1, I40E_VFPE_IPCONFIG01_USEENTIREIDRANGE_SHIFT) -#define I40E_VFPE_MRTEIDXMASK1 0x00009000 /* Reset: VFR */ -#define I40E_VFPE_MRTEIDXMASK1_MRTEIDXMASKBITS_SHIFT 0 -#define I40E_VFPE_MRTEIDXMASK1_MRTEIDXMASKBITS_MASK I40E_MASK(0x1F, I40E_VFPE_MRTEIDXMASK1_MRTEIDXMASKBITS_SHIFT) -#define I40E_VFPE_RCVUNEXPECTEDERROR1 0x00009400 /* Reset: VFR */ -#define I40E_VFPE_RCVUNEXPECTEDERROR1_TCP_RX_UNEXP_ERR_SHIFT 0 -#define I40E_VFPE_RCVUNEXPECTEDERROR1_TCP_RX_UNEXP_ERR_MASK I40E_MASK(0xFFFFFF, I40E_VFPE_RCVUNEXPECTEDERROR1_TCP_RX_UNEXP_ERR_SHIFT) -#define I40E_VFPE_TCPNOWTIMER1 0x0000A800 /* Reset: VFR */ -#define I40E_VFPE_TCPNOWTIMER1_TCP_NOW_SHIFT 0 -#define I40E_VFPE_TCPNOWTIMER1_TCP_NOW_MASK I40E_MASK(0xFFFFFFFF, I40E_VFPE_TCPNOWTIMER1_TCP_NOW_SHIFT) -#define I40E_VFPE_WQEALLOC1 0x0000C000 /* Reset: VFR */ -#define I40E_VFPE_WQEALLOC1_PEQPID_SHIFT 0 -#define I40E_VFPE_WQEALLOC1_PEQPID_MASK I40E_MASK(0x3FFFF, I40E_VFPE_WQEALLOC1_PEQPID_SHIFT) -#define I40E_VFPE_WQEALLOC1_WQE_DESC_INDEX_SHIFT 20 -#define I40E_VFPE_WQEALLOC1_WQE_DESC_INDEX_MASK I40E_MASK(0xFFF, I40E_VFPE_WQEALLOC1_WQE_DESC_INDEX_SHIFT) -#endif /* _I40E_REGISTER_H_ */ diff --git a/drivers/net/ethernet/intel/i40evf/i40e_type.h b/drivers/net/ethernet/intel/i40evf/i40e_type.h deleted file mode 100644 index 094387db3c11..000000000000 --- a/drivers/net/ethernet/intel/i40evf/i40e_type.h +++ /dev/null @@ -1,1496 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright(c) 2013 - 2018 Intel Corporation. */ - -#ifndef _I40E_TYPE_H_ -#define _I40E_TYPE_H_ - -#include "i40e_status.h" -#include "i40e_osdep.h" -#include "i40e_register.h" -#include "i40e_adminq.h" -#include "i40e_hmc.h" -#include "i40e_lan_hmc.h" -#include "i40e_devids.h" - -/* I40E_MASK is a macro used on 32 bit registers */ -#define I40E_MASK(mask, shift) ((u32)(mask) << (shift)) - -#define I40E_MAX_VSI_QP 16 -#define I40E_MAX_VF_VSI 3 -#define I40E_MAX_CHAINED_RX_BUFFERS 5 -#define I40E_MAX_PF_UDP_OFFLOAD_PORTS 16 - -/* Max default timeout in ms, */ -#define I40E_MAX_NVM_TIMEOUT 18000 - -/* Max timeout in ms for the phy to respond */ -#define I40E_MAX_PHY_TIMEOUT 500 - -/* Switch from ms to the 1usec global time (this is the GTIME resolution) */ -#define I40E_MS_TO_GTIME(time) ((time) * 1000) - -/* forward declaration */ -struct i40e_hw; -typedef void (*I40E_ADMINQ_CALLBACK)(struct i40e_hw *, struct i40e_aq_desc *); - -/* Data type manipulation macros. */ - -#define I40E_DESC_UNUSED(R) \ - ((((R)->next_to_clean > (R)->next_to_use) ? 0 : (R)->count) + \ - (R)->next_to_clean - (R)->next_to_use - 1) - -/* bitfields for Tx queue mapping in QTX_CTL */ -#define I40E_QTX_CTL_VF_QUEUE 0x0 -#define I40E_QTX_CTL_VM_QUEUE 0x1 -#define I40E_QTX_CTL_PF_QUEUE 0x2 - -/* debug masks - set these bits in hw->debug_mask to control output */ -enum i40e_debug_mask { - I40E_DEBUG_INIT = 0x00000001, - I40E_DEBUG_RELEASE = 0x00000002, - - I40E_DEBUG_LINK = 0x00000010, - I40E_DEBUG_PHY = 0x00000020, - I40E_DEBUG_HMC = 0x00000040, - I40E_DEBUG_NVM = 0x00000080, - I40E_DEBUG_LAN = 0x00000100, - I40E_DEBUG_FLOW = 0x00000200, - I40E_DEBUG_DCB = 0x00000400, - I40E_DEBUG_DIAG = 0x00000800, - I40E_DEBUG_FD = 0x00001000, - I40E_DEBUG_PACKAGE = 0x00002000, - - I40E_DEBUG_AQ_MESSAGE = 0x01000000, - I40E_DEBUG_AQ_DESCRIPTOR = 0x02000000, - I40E_DEBUG_AQ_DESC_BUFFER = 0x04000000, - I40E_DEBUG_AQ_COMMAND = 0x06000000, - I40E_DEBUG_AQ = 0x0F000000, - - I40E_DEBUG_USER = 0xF0000000, - - I40E_DEBUG_ALL = 0xFFFFFFFF -}; - -/* These are structs for managing the hardware information and the operations. - * The structures of function pointers are filled out at init time when we - * know for sure exactly which hardware we're working with. This gives us the - * flexibility of using the same main driver code but adapting to slightly - * different hardware needs as new parts are developed. For this architecture, - * the Firmware and AdminQ are intended to insulate the driver from most of the - * future changes, but these structures will also do part of the job. - */ -enum i40e_mac_type { - I40E_MAC_UNKNOWN = 0, - I40E_MAC_XL710, - I40E_MAC_VF, - I40E_MAC_X722, - I40E_MAC_X722_VF, - I40E_MAC_GENERIC, -}; - -enum i40e_media_type { - I40E_MEDIA_TYPE_UNKNOWN = 0, - I40E_MEDIA_TYPE_FIBER, - I40E_MEDIA_TYPE_BASET, - I40E_MEDIA_TYPE_BACKPLANE, - I40E_MEDIA_TYPE_CX4, - I40E_MEDIA_TYPE_DA, - I40E_MEDIA_TYPE_VIRTUAL -}; - -enum i40e_fc_mode { - I40E_FC_NONE = 0, - I40E_FC_RX_PAUSE, - I40E_FC_TX_PAUSE, - I40E_FC_FULL, - I40E_FC_PFC, - I40E_FC_DEFAULT -}; - -enum i40e_set_fc_aq_failures { - I40E_SET_FC_AQ_FAIL_NONE = 0, - I40E_SET_FC_AQ_FAIL_GET = 1, - I40E_SET_FC_AQ_FAIL_SET = 2, - I40E_SET_FC_AQ_FAIL_UPDATE = 4, - I40E_SET_FC_AQ_FAIL_SET_UPDATE = 6 -}; - -enum i40e_vsi_type { - I40E_VSI_MAIN = 0, - I40E_VSI_VMDQ1 = 1, - I40E_VSI_VMDQ2 = 2, - I40E_VSI_CTRL = 3, - I40E_VSI_FCOE = 4, - I40E_VSI_MIRROR = 5, - I40E_VSI_SRIOV = 6, - I40E_VSI_FDIR = 7, - I40E_VSI_TYPE_UNKNOWN -}; - -enum i40e_queue_type { - I40E_QUEUE_TYPE_RX = 0, - I40E_QUEUE_TYPE_TX, - I40E_QUEUE_TYPE_PE_CEQ, - I40E_QUEUE_TYPE_UNKNOWN -}; - -struct i40e_link_status { - enum i40e_aq_phy_type phy_type; - enum i40e_aq_link_speed link_speed; - u8 link_info; - u8 an_info; - u8 req_fec_info; - u8 fec_info; - u8 ext_info; - u8 loopback; - /* is Link Status Event notification to SW enabled */ - bool lse_enable; - u16 max_frame_size; - bool crc_enable; - u8 pacing; - u8 requested_speeds; - u8 module_type[3]; - /* 1st byte: module identifier */ -#define I40E_MODULE_TYPE_SFP 0x03 -#define I40E_MODULE_TYPE_QSFP 0x0D - /* 2nd byte: ethernet compliance codes for 10/40G */ -#define I40E_MODULE_TYPE_40G_ACTIVE 0x01 -#define I40E_MODULE_TYPE_40G_LR4 0x02 -#define I40E_MODULE_TYPE_40G_SR4 0x04 -#define I40E_MODULE_TYPE_40G_CR4 0x08 -#define I40E_MODULE_TYPE_10G_BASE_SR 0x10 -#define I40E_MODULE_TYPE_10G_BASE_LR 0x20 -#define I40E_MODULE_TYPE_10G_BASE_LRM 0x40 -#define I40E_MODULE_TYPE_10G_BASE_ER 0x80 - /* 3rd byte: ethernet compliance codes for 1G */ -#define I40E_MODULE_TYPE_1000BASE_SX 0x01 -#define I40E_MODULE_TYPE_1000BASE_LX 0x02 -#define I40E_MODULE_TYPE_1000BASE_CX 0x04 -#define I40E_MODULE_TYPE_1000BASE_T 0x08 -}; - -struct i40e_phy_info { - struct i40e_link_status link_info; - struct i40e_link_status link_info_old; - bool get_link_info; - enum i40e_media_type media_type; - /* all the phy types the NVM is capable of */ - u64 phy_types; -}; - -#define I40E_CAP_PHY_TYPE_SGMII BIT_ULL(I40E_PHY_TYPE_SGMII) -#define I40E_CAP_PHY_TYPE_1000BASE_KX BIT_ULL(I40E_PHY_TYPE_1000BASE_KX) -#define I40E_CAP_PHY_TYPE_10GBASE_KX4 BIT_ULL(I40E_PHY_TYPE_10GBASE_KX4) -#define I40E_CAP_PHY_TYPE_10GBASE_KR BIT_ULL(I40E_PHY_TYPE_10GBASE_KR) -#define I40E_CAP_PHY_TYPE_40GBASE_KR4 BIT_ULL(I40E_PHY_TYPE_40GBASE_KR4) -#define I40E_CAP_PHY_TYPE_XAUI BIT_ULL(I40E_PHY_TYPE_XAUI) -#define I40E_CAP_PHY_TYPE_XFI BIT_ULL(I40E_PHY_TYPE_XFI) -#define I40E_CAP_PHY_TYPE_SFI BIT_ULL(I40E_PHY_TYPE_SFI) -#define I40E_CAP_PHY_TYPE_XLAUI BIT_ULL(I40E_PHY_TYPE_XLAUI) -#define I40E_CAP_PHY_TYPE_XLPPI BIT_ULL(I40E_PHY_TYPE_XLPPI) -#define I40E_CAP_PHY_TYPE_40GBASE_CR4_CU BIT_ULL(I40E_PHY_TYPE_40GBASE_CR4_CU) -#define I40E_CAP_PHY_TYPE_10GBASE_CR1_CU BIT_ULL(I40E_PHY_TYPE_10GBASE_CR1_CU) -#define I40E_CAP_PHY_TYPE_10GBASE_AOC BIT_ULL(I40E_PHY_TYPE_10GBASE_AOC) -#define I40E_CAP_PHY_TYPE_40GBASE_AOC BIT_ULL(I40E_PHY_TYPE_40GBASE_AOC) -#define I40E_CAP_PHY_TYPE_100BASE_TX BIT_ULL(I40E_PHY_TYPE_100BASE_TX) -#define I40E_CAP_PHY_TYPE_1000BASE_T BIT_ULL(I40E_PHY_TYPE_1000BASE_T) -#define I40E_CAP_PHY_TYPE_10GBASE_T BIT_ULL(I40E_PHY_TYPE_10GBASE_T) -#define I40E_CAP_PHY_TYPE_10GBASE_SR BIT_ULL(I40E_PHY_TYPE_10GBASE_SR) -#define I40E_CAP_PHY_TYPE_10GBASE_LR BIT_ULL(I40E_PHY_TYPE_10GBASE_LR) -#define I40E_CAP_PHY_TYPE_10GBASE_SFPP_CU BIT_ULL(I40E_PHY_TYPE_10GBASE_SFPP_CU) -#define I40E_CAP_PHY_TYPE_10GBASE_CR1 BIT_ULL(I40E_PHY_TYPE_10GBASE_CR1) -#define I40E_CAP_PHY_TYPE_40GBASE_CR4 BIT_ULL(I40E_PHY_TYPE_40GBASE_CR4) -#define I40E_CAP_PHY_TYPE_40GBASE_SR4 BIT_ULL(I40E_PHY_TYPE_40GBASE_SR4) -#define I40E_CAP_PHY_TYPE_40GBASE_LR4 BIT_ULL(I40E_PHY_TYPE_40GBASE_LR4) -#define I40E_CAP_PHY_TYPE_1000BASE_SX BIT_ULL(I40E_PHY_TYPE_1000BASE_SX) -#define I40E_CAP_PHY_TYPE_1000BASE_LX BIT_ULL(I40E_PHY_TYPE_1000BASE_LX) -#define I40E_CAP_PHY_TYPE_1000BASE_T_OPTICAL \ - BIT_ULL(I40E_PHY_TYPE_1000BASE_T_OPTICAL) -#define I40E_CAP_PHY_TYPE_20GBASE_KR2 BIT_ULL(I40E_PHY_TYPE_20GBASE_KR2) -/* Defining the macro I40E_TYPE_OFFSET to implement a bit shift for some - * PHY types. There is an unused bit (31) in the I40E_CAP_PHY_TYPE_* bit - * fields but no corresponding gap in the i40e_aq_phy_type enumeration. So, - * a shift is needed to adjust for this with values larger than 31. The - * only affected values are I40E_PHY_TYPE_25GBASE_*. - */ -#define I40E_PHY_TYPE_OFFSET 1 -#define I40E_CAP_PHY_TYPE_25GBASE_KR BIT_ULL(I40E_PHY_TYPE_25GBASE_KR + \ - I40E_PHY_TYPE_OFFSET) -#define I40E_CAP_PHY_TYPE_25GBASE_CR BIT_ULL(I40E_PHY_TYPE_25GBASE_CR + \ - I40E_PHY_TYPE_OFFSET) -#define I40E_CAP_PHY_TYPE_25GBASE_SR BIT_ULL(I40E_PHY_TYPE_25GBASE_SR + \ - I40E_PHY_TYPE_OFFSET) -#define I40E_CAP_PHY_TYPE_25GBASE_LR BIT_ULL(I40E_PHY_TYPE_25GBASE_LR + \ - I40E_PHY_TYPE_OFFSET) -#define I40E_HW_CAP_MAX_GPIO 30 -/* Capabilities of a PF or a VF or the whole device */ -struct i40e_hw_capabilities { - u32 switch_mode; -#define I40E_NVM_IMAGE_TYPE_EVB 0x0 -#define I40E_NVM_IMAGE_TYPE_CLOUD 0x2 -#define I40E_NVM_IMAGE_TYPE_UDP_CLOUD 0x3 - - u32 management_mode; - u32 mng_protocols_over_mctp; -#define I40E_MNG_PROTOCOL_PLDM 0x2 -#define I40E_MNG_PROTOCOL_OEM_COMMANDS 0x4 -#define I40E_MNG_PROTOCOL_NCSI 0x8 - u32 npar_enable; - u32 os2bmc; - u32 valid_functions; - bool sr_iov_1_1; - bool vmdq; - bool evb_802_1_qbg; /* Edge Virtual Bridging */ - bool evb_802_1_qbh; /* Bridge Port Extension */ - bool dcb; - bool fcoe; - bool iscsi; /* Indicates iSCSI enabled */ - bool flex10_enable; - bool flex10_capable; - u32 flex10_mode; -#define I40E_FLEX10_MODE_UNKNOWN 0x0 -#define I40E_FLEX10_MODE_DCC 0x1 -#define I40E_FLEX10_MODE_DCI 0x2 - - u32 flex10_status; -#define I40E_FLEX10_STATUS_DCC_ERROR 0x1 -#define I40E_FLEX10_STATUS_VC_MODE 0x2 - - bool sec_rev_disabled; - bool update_disabled; -#define I40E_NVM_MGMT_SEC_REV_DISABLED 0x1 -#define I40E_NVM_MGMT_UPDATE_DISABLED 0x2 - - bool mgmt_cem; - bool ieee_1588; - bool iwarp; - bool fd; - u32 fd_filters_guaranteed; - u32 fd_filters_best_effort; - bool rss; - u32 rss_table_size; - u32 rss_table_entry_width; - bool led[I40E_HW_CAP_MAX_GPIO]; - bool sdp[I40E_HW_CAP_MAX_GPIO]; - u32 nvm_image_type; - u32 num_flow_director_filters; - u32 num_vfs; - u32 vf_base_id; - u32 num_vsis; - u32 num_rx_qp; - u32 num_tx_qp; - u32 base_queue; - u32 num_msix_vectors; - u32 num_msix_vectors_vf; - u32 led_pin_num; - u32 sdp_pin_num; - u32 mdio_port_num; - u32 mdio_port_mode; - u8 rx_buf_chain_len; - u32 enabled_tcmap; - u32 maxtc; - u64 wr_csr_prot; -}; - -struct i40e_mac_info { - enum i40e_mac_type type; - u8 addr[ETH_ALEN]; - u8 perm_addr[ETH_ALEN]; - u8 san_addr[ETH_ALEN]; - u16 max_fcoeq; -}; - -enum i40e_aq_resources_ids { - I40E_NVM_RESOURCE_ID = 1 -}; - -enum i40e_aq_resource_access_type { - I40E_RESOURCE_READ = 1, - I40E_RESOURCE_WRITE -}; - -struct i40e_nvm_info { - u64 hw_semaphore_timeout; /* usec global time (GTIME resolution) */ - u32 timeout; /* [ms] */ - u16 sr_size; /* Shadow RAM size in words */ - bool blank_nvm_mode; /* is NVM empty (no FW present)*/ - u16 version; /* NVM package version */ - u32 eetrack; /* NVM data version */ - u32 oem_ver; /* OEM version info */ -}; - -/* definitions used in NVM update support */ - -enum i40e_nvmupd_cmd { - I40E_NVMUPD_INVALID, - I40E_NVMUPD_READ_CON, - I40E_NVMUPD_READ_SNT, - I40E_NVMUPD_READ_LCB, - I40E_NVMUPD_READ_SA, - I40E_NVMUPD_WRITE_ERA, - I40E_NVMUPD_WRITE_CON, - I40E_NVMUPD_WRITE_SNT, - I40E_NVMUPD_WRITE_LCB, - I40E_NVMUPD_WRITE_SA, - I40E_NVMUPD_CSUM_CON, - I40E_NVMUPD_CSUM_SA, - I40E_NVMUPD_CSUM_LCB, - I40E_NVMUPD_STATUS, - I40E_NVMUPD_EXEC_AQ, - I40E_NVMUPD_GET_AQ_RESULT, - I40E_NVMUPD_GET_AQ_EVENT, -}; - -enum i40e_nvmupd_state { - I40E_NVMUPD_STATE_INIT, - I40E_NVMUPD_STATE_READING, - I40E_NVMUPD_STATE_WRITING, - I40E_NVMUPD_STATE_INIT_WAIT, - I40E_NVMUPD_STATE_WRITE_WAIT, - I40E_NVMUPD_STATE_ERROR -}; - -/* nvm_access definition and its masks/shifts need to be accessible to - * application, core driver, and shared code. Where is the right file? - */ -#define I40E_NVM_READ 0xB -#define I40E_NVM_WRITE 0xC - -#define I40E_NVM_MOD_PNT_MASK 0xFF - -#define I40E_NVM_TRANS_SHIFT 8 -#define I40E_NVM_TRANS_MASK (0xf << I40E_NVM_TRANS_SHIFT) -#define I40E_NVM_PRESERVATION_FLAGS_SHIFT 12 -#define I40E_NVM_PRESERVATION_FLAGS_MASK \ - (0x3 << I40E_NVM_PRESERVATION_FLAGS_SHIFT) -#define I40E_NVM_PRESERVATION_FLAGS_SELECTED 0x01 -#define I40E_NVM_PRESERVATION_FLAGS_ALL 0x02 -#define I40E_NVM_CON 0x0 -#define I40E_NVM_SNT 0x1 -#define I40E_NVM_LCB 0x2 -#define I40E_NVM_SA (I40E_NVM_SNT | I40E_NVM_LCB) -#define I40E_NVM_ERA 0x4 -#define I40E_NVM_CSUM 0x8 -#define I40E_NVM_AQE 0xe -#define I40E_NVM_EXEC 0xf - -#define I40E_NVM_ADAPT_SHIFT 16 -#define I40E_NVM_ADAPT_MASK (0xffff << I40E_NVM_ADAPT_SHIFT) - -#define I40E_NVMUPD_MAX_DATA 4096 -#define I40E_NVMUPD_IFACE_TIMEOUT 2 /* seconds */ - -struct i40e_nvm_access { - u32 command; - u32 config; - u32 offset; /* in bytes */ - u32 data_size; /* in bytes */ - u8 data[1]; -}; - -/* (Q)SFP module access definitions */ -#define I40E_I2C_EEPROM_DEV_ADDR 0xA0 -#define I40E_I2C_EEPROM_DEV_ADDR2 0xA2 -#define I40E_MODULE_TYPE_ADDR 0x00 -#define I40E_MODULE_REVISION_ADDR 0x01 -#define I40E_MODULE_SFF_8472_COMP 0x5E -#define I40E_MODULE_SFF_8472_SWAP 0x5C -#define I40E_MODULE_SFF_ADDR_MODE 0x04 -#define I40E_MODULE_TYPE_QSFP_PLUS 0x0D -#define I40E_MODULE_TYPE_QSFP28 0x11 -#define I40E_MODULE_QSFP_MAX_LEN 640 - -/* PCI bus types */ -enum i40e_bus_type { - i40e_bus_type_unknown = 0, - i40e_bus_type_pci, - i40e_bus_type_pcix, - i40e_bus_type_pci_express, - i40e_bus_type_reserved -}; - -/* PCI bus speeds */ -enum i40e_bus_speed { - i40e_bus_speed_unknown = 0, - i40e_bus_speed_33 = 33, - i40e_bus_speed_66 = 66, - i40e_bus_speed_100 = 100, - i40e_bus_speed_120 = 120, - i40e_bus_speed_133 = 133, - i40e_bus_speed_2500 = 2500, - i40e_bus_speed_5000 = 5000, - i40e_bus_speed_8000 = 8000, - i40e_bus_speed_reserved -}; - -/* PCI bus widths */ -enum i40e_bus_width { - i40e_bus_width_unknown = 0, - i40e_bus_width_pcie_x1 = 1, - i40e_bus_width_pcie_x2 = 2, - i40e_bus_width_pcie_x4 = 4, - i40e_bus_width_pcie_x8 = 8, - i40e_bus_width_32 = 32, - i40e_bus_width_64 = 64, - i40e_bus_width_reserved -}; - -/* Bus parameters */ -struct i40e_bus_info { - enum i40e_bus_speed speed; - enum i40e_bus_width width; - enum i40e_bus_type type; - - u16 func; - u16 device; - u16 lan_id; - u16 bus_id; -}; - -/* Flow control (FC) parameters */ -struct i40e_fc_info { - enum i40e_fc_mode current_mode; /* FC mode in effect */ - enum i40e_fc_mode requested_mode; /* FC mode requested by caller */ -}; - -#define I40E_MAX_TRAFFIC_CLASS 8 -#define I40E_MAX_USER_PRIORITY 8 -#define I40E_DCBX_MAX_APPS 32 -#define I40E_LLDPDU_SIZE 1500 - -/* IEEE 802.1Qaz ETS Configuration data */ -struct i40e_ieee_ets_config { - u8 willing; - u8 cbs; - u8 maxtcs; - u8 prioritytable[I40E_MAX_TRAFFIC_CLASS]; - u8 tcbwtable[I40E_MAX_TRAFFIC_CLASS]; - u8 tsatable[I40E_MAX_TRAFFIC_CLASS]; -}; - -/* IEEE 802.1Qaz ETS Recommendation data */ -struct i40e_ieee_ets_recommend { - u8 prioritytable[I40E_MAX_TRAFFIC_CLASS]; - u8 tcbwtable[I40E_MAX_TRAFFIC_CLASS]; - u8 tsatable[I40E_MAX_TRAFFIC_CLASS]; -}; - -/* IEEE 802.1Qaz PFC Configuration data */ -struct i40e_ieee_pfc_config { - u8 willing; - u8 mbc; - u8 pfccap; - u8 pfcenable; -}; - -/* IEEE 802.1Qaz Application Priority data */ -struct i40e_ieee_app_priority_table { - u8 priority; - u8 selector; - u16 protocolid; -}; - -struct i40e_dcbx_config { - u32 numapps; - u32 tlv_status; /* CEE mode TLV status */ - struct i40e_ieee_ets_config etscfg; - struct i40e_ieee_ets_recommend etsrec; - struct i40e_ieee_pfc_config pfc; - struct i40e_ieee_app_priority_table app[I40E_DCBX_MAX_APPS]; -}; - -/* Port hardware description */ -struct i40e_hw { - u8 __iomem *hw_addr; - void *back; - - /* subsystem structs */ - struct i40e_phy_info phy; - struct i40e_mac_info mac; - struct i40e_bus_info bus; - struct i40e_nvm_info nvm; - struct i40e_fc_info fc; - - /* pci info */ - u16 device_id; - u16 vendor_id; - u16 subsystem_device_id; - u16 subsystem_vendor_id; - u8 revision_id; - u8 port; - bool adapter_stopped; - - /* capabilities for entire device and PCI func */ - struct i40e_hw_capabilities dev_caps; - struct i40e_hw_capabilities func_caps; - - /* Flow Director shared filter space */ - u16 fdir_shared_filter_count; - - /* device profile info */ - u8 pf_id; - u16 main_vsi_seid; - - /* for multi-function MACs */ - u16 partition_id; - u16 num_partitions; - u16 num_ports; - - /* Closest numa node to the device */ - u16 numa_node; - - /* Admin Queue info */ - struct i40e_adminq_info aq; - - /* state of nvm update process */ - enum i40e_nvmupd_state nvmupd_state; - struct i40e_aq_desc nvm_wb_desc; - struct i40e_aq_desc nvm_aq_event_desc; - struct i40e_virt_mem nvm_buff; - bool nvm_release_on_done; - u16 nvm_wait_opcode; - - /* HMC info */ - struct i40e_hmc_info hmc; /* HMC info struct */ - - /* LLDP/DCBX Status */ - u16 dcbx_status; - -#define I40E_HW_FLAG_802_1AD_CAPABLE BIT_ULL(1) -#define I40E_HW_FLAG_AQ_PHY_ACCESS_CAPABLE BIT_ULL(2) - - /* DCBX info */ - struct i40e_dcbx_config local_dcbx_config; /* Oper/Local Cfg */ - struct i40e_dcbx_config remote_dcbx_config; /* Peer Cfg */ - struct i40e_dcbx_config desired_dcbx_config; /* CEE Desired Cfg */ - - /* Used in set switch config AQ command */ - u16 switch_tag; - u16 first_tag; - u16 second_tag; - - /* debug mask */ - u32 debug_mask; - char err_str[16]; -}; - -static inline bool i40e_is_vf(struct i40e_hw *hw) -{ - return (hw->mac.type == I40E_MAC_VF || - hw->mac.type == I40E_MAC_X722_VF); -} - -struct i40e_driver_version { - u8 major_version; - u8 minor_version; - u8 build_version; - u8 subbuild_version; - u8 driver_string[32]; -}; - -/* RX Descriptors */ -union i40e_16byte_rx_desc { - struct { - __le64 pkt_addr; /* Packet buffer address */ - __le64 hdr_addr; /* Header buffer address */ - } read; - struct { - struct { - struct { - union { - __le16 mirroring_status; - __le16 fcoe_ctx_id; - } mirr_fcoe; - __le16 l2tag1; - } lo_dword; - union { - __le32 rss; /* RSS Hash */ - __le32 fd_id; /* Flow director filter id */ - __le32 fcoe_param; /* FCoE DDP Context id */ - } hi_dword; - } qword0; - struct { - /* ext status/error/pktype/length */ - __le64 status_error_len; - } qword1; - } wb; /* writeback */ -}; - -union i40e_32byte_rx_desc { - struct { - __le64 pkt_addr; /* Packet buffer address */ - __le64 hdr_addr; /* Header buffer address */ - /* bit 0 of hdr_buffer_addr is DD bit */ - __le64 rsvd1; - __le64 rsvd2; - } read; - struct { - struct { - struct { - union { - __le16 mirroring_status; - __le16 fcoe_ctx_id; - } mirr_fcoe; - __le16 l2tag1; - } lo_dword; - union { - __le32 rss; /* RSS Hash */ - __le32 fcoe_param; /* FCoE DDP Context id */ - /* Flow director filter id in case of - * Programming status desc WB - */ - __le32 fd_id; - } hi_dword; - } qword0; - struct { - /* status/error/pktype/length */ - __le64 status_error_len; - } qword1; - struct { - __le16 ext_status; /* extended status */ - __le16 rsvd; - __le16 l2tag2_1; - __le16 l2tag2_2; - } qword2; - struct { - union { - __le32 flex_bytes_lo; - __le32 pe_status; - } lo_dword; - union { - __le32 flex_bytes_hi; - __le32 fd_id; - } hi_dword; - } qword3; - } wb; /* writeback */ -}; - -enum i40e_rx_desc_status_bits { - /* Note: These are predefined bit offsets */ - I40E_RX_DESC_STATUS_DD_SHIFT = 0, - I40E_RX_DESC_STATUS_EOF_SHIFT = 1, - I40E_RX_DESC_STATUS_L2TAG1P_SHIFT = 2, - I40E_RX_DESC_STATUS_L3L4P_SHIFT = 3, - I40E_RX_DESC_STATUS_CRCP_SHIFT = 4, - I40E_RX_DESC_STATUS_TSYNINDX_SHIFT = 5, /* 2 BITS */ - I40E_RX_DESC_STATUS_TSYNVALID_SHIFT = 7, - /* Note: Bit 8 is reserved in X710 and XL710 */ - I40E_RX_DESC_STATUS_EXT_UDP_0_SHIFT = 8, - I40E_RX_DESC_STATUS_UMBCAST_SHIFT = 9, /* 2 BITS */ - I40E_RX_DESC_STATUS_FLM_SHIFT = 11, - I40E_RX_DESC_STATUS_FLTSTAT_SHIFT = 12, /* 2 BITS */ - I40E_RX_DESC_STATUS_LPBK_SHIFT = 14, - I40E_RX_DESC_STATUS_IPV6EXADD_SHIFT = 15, - I40E_RX_DESC_STATUS_RESERVED_SHIFT = 16, /* 2 BITS */ - /* Note: For non-tunnel packets INT_UDP_0 is the right status for - * UDP header - */ - I40E_RX_DESC_STATUS_INT_UDP_0_SHIFT = 18, - I40E_RX_DESC_STATUS_LAST /* this entry must be last!!! */ -}; - -#define I40E_RXD_QW1_STATUS_SHIFT 0 -#define I40E_RXD_QW1_STATUS_MASK ((BIT(I40E_RX_DESC_STATUS_LAST) - 1) \ - << I40E_RXD_QW1_STATUS_SHIFT) - -#define I40E_RXD_QW1_STATUS_TSYNINDX_SHIFT I40E_RX_DESC_STATUS_TSYNINDX_SHIFT -#define I40E_RXD_QW1_STATUS_TSYNINDX_MASK (0x3UL << \ - I40E_RXD_QW1_STATUS_TSYNINDX_SHIFT) - -#define I40E_RXD_QW1_STATUS_TSYNVALID_SHIFT I40E_RX_DESC_STATUS_TSYNVALID_SHIFT -#define I40E_RXD_QW1_STATUS_TSYNVALID_MASK \ - BIT_ULL(I40E_RXD_QW1_STATUS_TSYNVALID_SHIFT) - -enum i40e_rx_desc_fltstat_values { - I40E_RX_DESC_FLTSTAT_NO_DATA = 0, - I40E_RX_DESC_FLTSTAT_RSV_FD_ID = 1, /* 16byte desc? FD_ID : RSV */ - I40E_RX_DESC_FLTSTAT_RSV = 2, - I40E_RX_DESC_FLTSTAT_RSS_HASH = 3, -}; - -#define I40E_RXD_QW1_ERROR_SHIFT 19 -#define I40E_RXD_QW1_ERROR_MASK (0xFFUL << I40E_RXD_QW1_ERROR_SHIFT) - -enum i40e_rx_desc_error_bits { - /* Note: These are predefined bit offsets */ - I40E_RX_DESC_ERROR_RXE_SHIFT = 0, - I40E_RX_DESC_ERROR_RECIPE_SHIFT = 1, - I40E_RX_DESC_ERROR_HBO_SHIFT = 2, - I40E_RX_DESC_ERROR_L3L4E_SHIFT = 3, /* 3 BITS */ - I40E_RX_DESC_ERROR_IPE_SHIFT = 3, - I40E_RX_DESC_ERROR_L4E_SHIFT = 4, - I40E_RX_DESC_ERROR_EIPE_SHIFT = 5, - I40E_RX_DESC_ERROR_OVERSIZE_SHIFT = 6, - I40E_RX_DESC_ERROR_PPRS_SHIFT = 7 -}; - -enum i40e_rx_desc_error_l3l4e_fcoe_masks { - I40E_RX_DESC_ERROR_L3L4E_NONE = 0, - I40E_RX_DESC_ERROR_L3L4E_PROT = 1, - I40E_RX_DESC_ERROR_L3L4E_FC = 2, - I40E_RX_DESC_ERROR_L3L4E_DMAC_ERR = 3, - I40E_RX_DESC_ERROR_L3L4E_DMAC_WARN = 4 -}; - -#define I40E_RXD_QW1_PTYPE_SHIFT 30 -#define I40E_RXD_QW1_PTYPE_MASK (0xFFULL << I40E_RXD_QW1_PTYPE_SHIFT) - -/* Packet type non-ip values */ -enum i40e_rx_l2_ptype { - I40E_RX_PTYPE_L2_RESERVED = 0, - I40E_RX_PTYPE_L2_MAC_PAY2 = 1, - I40E_RX_PTYPE_L2_TIMESYNC_PAY2 = 2, - I40E_RX_PTYPE_L2_FIP_PAY2 = 3, - I40E_RX_PTYPE_L2_OUI_PAY2 = 4, - I40E_RX_PTYPE_L2_MACCNTRL_PAY2 = 5, - I40E_RX_PTYPE_L2_LLDP_PAY2 = 6, - I40E_RX_PTYPE_L2_ECP_PAY2 = 7, - I40E_RX_PTYPE_L2_EVB_PAY2 = 8, - I40E_RX_PTYPE_L2_QCN_PAY2 = 9, - I40E_RX_PTYPE_L2_EAPOL_PAY2 = 10, - I40E_RX_PTYPE_L2_ARP = 11, - I40E_RX_PTYPE_L2_FCOE_PAY3 = 12, - I40E_RX_PTYPE_L2_FCOE_FCDATA_PAY3 = 13, - I40E_RX_PTYPE_L2_FCOE_FCRDY_PAY3 = 14, - I40E_RX_PTYPE_L2_FCOE_FCRSP_PAY3 = 15, - I40E_RX_PTYPE_L2_FCOE_FCOTHER_PA = 16, - I40E_RX_PTYPE_L2_FCOE_VFT_PAY3 = 17, - I40E_RX_PTYPE_L2_FCOE_VFT_FCDATA = 18, - I40E_RX_PTYPE_L2_FCOE_VFT_FCRDY = 19, - I40E_RX_PTYPE_L2_FCOE_VFT_FCRSP = 20, - I40E_RX_PTYPE_L2_FCOE_VFT_FCOTHER = 21, - I40E_RX_PTYPE_GRENAT4_MAC_PAY3 = 58, - I40E_RX_PTYPE_GRENAT4_MACVLAN_IPV6_ICMP_PAY4 = 87, - I40E_RX_PTYPE_GRENAT6_MAC_PAY3 = 124, - I40E_RX_PTYPE_GRENAT6_MACVLAN_IPV6_ICMP_PAY4 = 153 -}; - -struct i40e_rx_ptype_decoded { - u32 ptype:8; - u32 known:1; - u32 outer_ip:1; - u32 outer_ip_ver:1; - u32 outer_frag:1; - u32 tunnel_type:3; - u32 tunnel_end_prot:2; - u32 tunnel_end_frag:1; - u32 inner_prot:4; - u32 payload_layer:3; -}; - -enum i40e_rx_ptype_outer_ip { - I40E_RX_PTYPE_OUTER_L2 = 0, - I40E_RX_PTYPE_OUTER_IP = 1 -}; - -enum i40e_rx_ptype_outer_ip_ver { - I40E_RX_PTYPE_OUTER_NONE = 0, - I40E_RX_PTYPE_OUTER_IPV4 = 0, - I40E_RX_PTYPE_OUTER_IPV6 = 1 -}; - -enum i40e_rx_ptype_outer_fragmented { - I40E_RX_PTYPE_NOT_FRAG = 0, - I40E_RX_PTYPE_FRAG = 1 -}; - -enum i40e_rx_ptype_tunnel_type { - I40E_RX_PTYPE_TUNNEL_NONE = 0, - I40E_RX_PTYPE_TUNNEL_IP_IP = 1, - I40E_RX_PTYPE_TUNNEL_IP_GRENAT = 2, - I40E_RX_PTYPE_TUNNEL_IP_GRENAT_MAC = 3, - I40E_RX_PTYPE_TUNNEL_IP_GRENAT_MAC_VLAN = 4, -}; - -enum i40e_rx_ptype_tunnel_end_prot { - I40E_RX_PTYPE_TUNNEL_END_NONE = 0, - I40E_RX_PTYPE_TUNNEL_END_IPV4 = 1, - I40E_RX_PTYPE_TUNNEL_END_IPV6 = 2, -}; - -enum i40e_rx_ptype_inner_prot { - I40E_RX_PTYPE_INNER_PROT_NONE = 0, - I40E_RX_PTYPE_INNER_PROT_UDP = 1, - I40E_RX_PTYPE_INNER_PROT_TCP = 2, - I40E_RX_PTYPE_INNER_PROT_SCTP = 3, - I40E_RX_PTYPE_INNER_PROT_ICMP = 4, - I40E_RX_PTYPE_INNER_PROT_TIMESYNC = 5 -}; - -enum i40e_rx_ptype_payload_layer { - I40E_RX_PTYPE_PAYLOAD_LAYER_NONE = 0, - I40E_RX_PTYPE_PAYLOAD_LAYER_PAY2 = 1, - I40E_RX_PTYPE_PAYLOAD_LAYER_PAY3 = 2, - I40E_RX_PTYPE_PAYLOAD_LAYER_PAY4 = 3, -}; - -#define I40E_RXD_QW1_LENGTH_PBUF_SHIFT 38 -#define I40E_RXD_QW1_LENGTH_PBUF_MASK (0x3FFFULL << \ - I40E_RXD_QW1_LENGTH_PBUF_SHIFT) - -#define I40E_RXD_QW1_LENGTH_HBUF_SHIFT 52 -#define I40E_RXD_QW1_LENGTH_HBUF_MASK (0x7FFULL << \ - I40E_RXD_QW1_LENGTH_HBUF_SHIFT) - -#define I40E_RXD_QW1_LENGTH_SPH_SHIFT 63 -#define I40E_RXD_QW1_LENGTH_SPH_MASK BIT_ULL(I40E_RXD_QW1_LENGTH_SPH_SHIFT) - -enum i40e_rx_desc_ext_status_bits { - /* Note: These are predefined bit offsets */ - I40E_RX_DESC_EXT_STATUS_L2TAG2P_SHIFT = 0, - I40E_RX_DESC_EXT_STATUS_L2TAG3P_SHIFT = 1, - I40E_RX_DESC_EXT_STATUS_FLEXBL_SHIFT = 2, /* 2 BITS */ - I40E_RX_DESC_EXT_STATUS_FLEXBH_SHIFT = 4, /* 2 BITS */ - I40E_RX_DESC_EXT_STATUS_FDLONGB_SHIFT = 9, - I40E_RX_DESC_EXT_STATUS_FCOELONGB_SHIFT = 10, - I40E_RX_DESC_EXT_STATUS_PELONGB_SHIFT = 11, -}; - -enum i40e_rx_desc_pe_status_bits { - /* Note: These are predefined bit offsets */ - I40E_RX_DESC_PE_STATUS_QPID_SHIFT = 0, /* 18 BITS */ - I40E_RX_DESC_PE_STATUS_L4PORT_SHIFT = 0, /* 16 BITS */ - I40E_RX_DESC_PE_STATUS_IPINDEX_SHIFT = 16, /* 8 BITS */ - I40E_RX_DESC_PE_STATUS_QPIDHIT_SHIFT = 24, - I40E_RX_DESC_PE_STATUS_APBVTHIT_SHIFT = 25, - I40E_RX_DESC_PE_STATUS_PORTV_SHIFT = 26, - I40E_RX_DESC_PE_STATUS_URG_SHIFT = 27, - I40E_RX_DESC_PE_STATUS_IPFRAG_SHIFT = 28, - I40E_RX_DESC_PE_STATUS_IPOPT_SHIFT = 29 -}; - -#define I40E_RX_PROG_STATUS_DESC_LENGTH_SHIFT 38 -#define I40E_RX_PROG_STATUS_DESC_LENGTH 0x2000000 - -#define I40E_RX_PROG_STATUS_DESC_QW1_PROGID_SHIFT 2 -#define I40E_RX_PROG_STATUS_DESC_QW1_PROGID_MASK (0x7UL << \ - I40E_RX_PROG_STATUS_DESC_QW1_PROGID_SHIFT) - -#define I40E_RX_PROG_STATUS_DESC_QW1_ERROR_SHIFT 19 -#define I40E_RX_PROG_STATUS_DESC_QW1_ERROR_MASK (0x3FUL << \ - I40E_RX_PROG_STATUS_DESC_QW1_ERROR_SHIFT) - -enum i40e_rx_prog_status_desc_status_bits { - /* Note: These are predefined bit offsets */ - I40E_RX_PROG_STATUS_DESC_DD_SHIFT = 0, - I40E_RX_PROG_STATUS_DESC_PROG_ID_SHIFT = 2 /* 3 BITS */ -}; - -enum i40e_rx_prog_status_desc_prog_id_masks { - I40E_RX_PROG_STATUS_DESC_FD_FILTER_STATUS = 1, - I40E_RX_PROG_STATUS_DESC_FCOE_CTXT_PROG_STATUS = 2, - I40E_RX_PROG_STATUS_DESC_FCOE_CTXT_INVL_STATUS = 4, -}; - -enum i40e_rx_prog_status_desc_error_bits { - /* Note: These are predefined bit offsets */ - I40E_RX_PROG_STATUS_DESC_FD_TBL_FULL_SHIFT = 0, - I40E_RX_PROG_STATUS_DESC_NO_FD_ENTRY_SHIFT = 1, - I40E_RX_PROG_STATUS_DESC_FCOE_TBL_FULL_SHIFT = 2, - I40E_RX_PROG_STATUS_DESC_FCOE_CONFLICT_SHIFT = 3 -}; - -/* TX Descriptor */ -struct i40e_tx_desc { - __le64 buffer_addr; /* Address of descriptor's data buf */ - __le64 cmd_type_offset_bsz; -}; - -#define I40E_TXD_QW1_DTYPE_SHIFT 0 -#define I40E_TXD_QW1_DTYPE_MASK (0xFUL << I40E_TXD_QW1_DTYPE_SHIFT) - -enum i40e_tx_desc_dtype_value { - I40E_TX_DESC_DTYPE_DATA = 0x0, - I40E_TX_DESC_DTYPE_NOP = 0x1, /* same as Context desc */ - I40E_TX_DESC_DTYPE_CONTEXT = 0x1, - I40E_TX_DESC_DTYPE_FCOE_CTX = 0x2, - I40E_TX_DESC_DTYPE_FILTER_PROG = 0x8, - I40E_TX_DESC_DTYPE_DDP_CTX = 0x9, - I40E_TX_DESC_DTYPE_FLEX_DATA = 0xB, - I40E_TX_DESC_DTYPE_FLEX_CTX_1 = 0xC, - I40E_TX_DESC_DTYPE_FLEX_CTX_2 = 0xD, - I40E_TX_DESC_DTYPE_DESC_DONE = 0xF -}; - -#define I40E_TXD_QW1_CMD_SHIFT 4 -#define I40E_TXD_QW1_CMD_MASK (0x3FFUL << I40E_TXD_QW1_CMD_SHIFT) - -enum i40e_tx_desc_cmd_bits { - I40E_TX_DESC_CMD_EOP = 0x0001, - I40E_TX_DESC_CMD_RS = 0x0002, - I40E_TX_DESC_CMD_ICRC = 0x0004, - I40E_TX_DESC_CMD_IL2TAG1 = 0x0008, - I40E_TX_DESC_CMD_DUMMY = 0x0010, - I40E_TX_DESC_CMD_IIPT_NONIP = 0x0000, /* 2 BITS */ - I40E_TX_DESC_CMD_IIPT_IPV6 = 0x0020, /* 2 BITS */ - I40E_TX_DESC_CMD_IIPT_IPV4 = 0x0040, /* 2 BITS */ - I40E_TX_DESC_CMD_IIPT_IPV4_CSUM = 0x0060, /* 2 BITS */ - I40E_TX_DESC_CMD_FCOET = 0x0080, - I40E_TX_DESC_CMD_L4T_EOFT_UNK = 0x0000, /* 2 BITS */ - I40E_TX_DESC_CMD_L4T_EOFT_TCP = 0x0100, /* 2 BITS */ - I40E_TX_DESC_CMD_L4T_EOFT_SCTP = 0x0200, /* 2 BITS */ - I40E_TX_DESC_CMD_L4T_EOFT_UDP = 0x0300, /* 2 BITS */ - I40E_TX_DESC_CMD_L4T_EOFT_EOF_N = 0x0000, /* 2 BITS */ - I40E_TX_DESC_CMD_L4T_EOFT_EOF_T = 0x0100, /* 2 BITS */ - I40E_TX_DESC_CMD_L4T_EOFT_EOF_NI = 0x0200, /* 2 BITS */ - I40E_TX_DESC_CMD_L4T_EOFT_EOF_A = 0x0300, /* 2 BITS */ -}; - -#define I40E_TXD_QW1_OFFSET_SHIFT 16 -#define I40E_TXD_QW1_OFFSET_MASK (0x3FFFFULL << \ - I40E_TXD_QW1_OFFSET_SHIFT) - -enum i40e_tx_desc_length_fields { - /* Note: These are predefined bit offsets */ - I40E_TX_DESC_LENGTH_MACLEN_SHIFT = 0, /* 7 BITS */ - I40E_TX_DESC_LENGTH_IPLEN_SHIFT = 7, /* 7 BITS */ - I40E_TX_DESC_LENGTH_L4_FC_LEN_SHIFT = 14 /* 4 BITS */ -}; - -#define I40E_TXD_QW1_TX_BUF_SZ_SHIFT 34 -#define I40E_TXD_QW1_TX_BUF_SZ_MASK (0x3FFFULL << \ - I40E_TXD_QW1_TX_BUF_SZ_SHIFT) - -#define I40E_TXD_QW1_L2TAG1_SHIFT 48 -#define I40E_TXD_QW1_L2TAG1_MASK (0xFFFFULL << I40E_TXD_QW1_L2TAG1_SHIFT) - -/* Context descriptors */ -struct i40e_tx_context_desc { - __le32 tunneling_params; - __le16 l2tag2; - __le16 rsvd; - __le64 type_cmd_tso_mss; -}; - -#define I40E_TXD_CTX_QW1_DTYPE_SHIFT 0 -#define I40E_TXD_CTX_QW1_DTYPE_MASK (0xFUL << I40E_TXD_CTX_QW1_DTYPE_SHIFT) - -#define I40E_TXD_CTX_QW1_CMD_SHIFT 4 -#define I40E_TXD_CTX_QW1_CMD_MASK (0xFFFFUL << I40E_TXD_CTX_QW1_CMD_SHIFT) - -enum i40e_tx_ctx_desc_cmd_bits { - I40E_TX_CTX_DESC_TSO = 0x01, - I40E_TX_CTX_DESC_TSYN = 0x02, - I40E_TX_CTX_DESC_IL2TAG2 = 0x04, - I40E_TX_CTX_DESC_IL2TAG2_IL2H = 0x08, - I40E_TX_CTX_DESC_SWTCH_NOTAG = 0x00, - I40E_TX_CTX_DESC_SWTCH_UPLINK = 0x10, - I40E_TX_CTX_DESC_SWTCH_LOCAL = 0x20, - I40E_TX_CTX_DESC_SWTCH_VSI = 0x30, - I40E_TX_CTX_DESC_SWPE = 0x40 -}; - -#define I40E_TXD_CTX_QW1_TSO_LEN_SHIFT 30 -#define I40E_TXD_CTX_QW1_TSO_LEN_MASK (0x3FFFFULL << \ - I40E_TXD_CTX_QW1_TSO_LEN_SHIFT) - -#define I40E_TXD_CTX_QW1_MSS_SHIFT 50 -#define I40E_TXD_CTX_QW1_MSS_MASK (0x3FFFULL << \ - I40E_TXD_CTX_QW1_MSS_SHIFT) - -#define I40E_TXD_CTX_QW1_VSI_SHIFT 50 -#define I40E_TXD_CTX_QW1_VSI_MASK (0x1FFULL << I40E_TXD_CTX_QW1_VSI_SHIFT) - -#define I40E_TXD_CTX_QW0_EXT_IP_SHIFT 0 -#define I40E_TXD_CTX_QW0_EXT_IP_MASK (0x3ULL << \ - I40E_TXD_CTX_QW0_EXT_IP_SHIFT) - -enum i40e_tx_ctx_desc_eipt_offload { - I40E_TX_CTX_EXT_IP_NONE = 0x0, - I40E_TX_CTX_EXT_IP_IPV6 = 0x1, - I40E_TX_CTX_EXT_IP_IPV4_NO_CSUM = 0x2, - I40E_TX_CTX_EXT_IP_IPV4 = 0x3 -}; - -#define I40E_TXD_CTX_QW0_EXT_IPLEN_SHIFT 2 -#define I40E_TXD_CTX_QW0_EXT_IPLEN_MASK (0x3FULL << \ - I40E_TXD_CTX_QW0_EXT_IPLEN_SHIFT) - -#define I40E_TXD_CTX_QW0_NATT_SHIFT 9 -#define I40E_TXD_CTX_QW0_NATT_MASK (0x3ULL << I40E_TXD_CTX_QW0_NATT_SHIFT) - -#define I40E_TXD_CTX_UDP_TUNNELING BIT_ULL(I40E_TXD_CTX_QW0_NATT_SHIFT) -#define I40E_TXD_CTX_GRE_TUNNELING (0x2ULL << I40E_TXD_CTX_QW0_NATT_SHIFT) - -#define I40E_TXD_CTX_QW0_EIP_NOINC_SHIFT 11 -#define I40E_TXD_CTX_QW0_EIP_NOINC_MASK \ - BIT_ULL(I40E_TXD_CTX_QW0_EIP_NOINC_SHIFT) - -#define I40E_TXD_CTX_EIP_NOINC_IPID_CONST I40E_TXD_CTX_QW0_EIP_NOINC_MASK - -#define I40E_TXD_CTX_QW0_NATLEN_SHIFT 12 -#define I40E_TXD_CTX_QW0_NATLEN_MASK (0X7FULL << \ - I40E_TXD_CTX_QW0_NATLEN_SHIFT) - -#define I40E_TXD_CTX_QW0_DECTTL_SHIFT 19 -#define I40E_TXD_CTX_QW0_DECTTL_MASK (0xFULL << \ - I40E_TXD_CTX_QW0_DECTTL_SHIFT) - -#define I40E_TXD_CTX_QW0_L4T_CS_SHIFT 23 -#define I40E_TXD_CTX_QW0_L4T_CS_MASK BIT_ULL(I40E_TXD_CTX_QW0_L4T_CS_SHIFT) -struct i40e_filter_program_desc { - __le32 qindex_flex_ptype_vsi; - __le32 rsvd; - __le32 dtype_cmd_cntindex; - __le32 fd_id; -}; -#define I40E_TXD_FLTR_QW0_QINDEX_SHIFT 0 -#define I40E_TXD_FLTR_QW0_QINDEX_MASK (0x7FFUL << \ - I40E_TXD_FLTR_QW0_QINDEX_SHIFT) -#define I40E_TXD_FLTR_QW0_FLEXOFF_SHIFT 11 -#define I40E_TXD_FLTR_QW0_FLEXOFF_MASK (0x7UL << \ - I40E_TXD_FLTR_QW0_FLEXOFF_SHIFT) -#define I40E_TXD_FLTR_QW0_PCTYPE_SHIFT 17 -#define I40E_TXD_FLTR_QW0_PCTYPE_MASK (0x3FUL << \ - I40E_TXD_FLTR_QW0_PCTYPE_SHIFT) - -/* Packet Classifier Types for filters */ -enum i40e_filter_pctype { - /* Note: Values 0-28 are reserved for future use. - * Value 29, 30, 32 are not supported on XL710 and X710. - */ - I40E_FILTER_PCTYPE_NONF_UNICAST_IPV4_UDP = 29, - I40E_FILTER_PCTYPE_NONF_MULTICAST_IPV4_UDP = 30, - I40E_FILTER_PCTYPE_NONF_IPV4_UDP = 31, - I40E_FILTER_PCTYPE_NONF_IPV4_TCP_SYN_NO_ACK = 32, - I40E_FILTER_PCTYPE_NONF_IPV4_TCP = 33, - I40E_FILTER_PCTYPE_NONF_IPV4_SCTP = 34, - I40E_FILTER_PCTYPE_NONF_IPV4_OTHER = 35, - I40E_FILTER_PCTYPE_FRAG_IPV4 = 36, - /* Note: Values 37-38 are reserved for future use. - * Value 39, 40, 42 are not supported on XL710 and X710. - */ - I40E_FILTER_PCTYPE_NONF_UNICAST_IPV6_UDP = 39, - I40E_FILTER_PCTYPE_NONF_MULTICAST_IPV6_UDP = 40, - I40E_FILTER_PCTYPE_NONF_IPV6_UDP = 41, - I40E_FILTER_PCTYPE_NONF_IPV6_TCP_SYN_NO_ACK = 42, - I40E_FILTER_PCTYPE_NONF_IPV6_TCP = 43, - I40E_FILTER_PCTYPE_NONF_IPV6_SCTP = 44, - I40E_FILTER_PCTYPE_NONF_IPV6_OTHER = 45, - I40E_FILTER_PCTYPE_FRAG_IPV6 = 46, - /* Note: Value 47 is reserved for future use */ - I40E_FILTER_PCTYPE_FCOE_OX = 48, - I40E_FILTER_PCTYPE_FCOE_RX = 49, - I40E_FILTER_PCTYPE_FCOE_OTHER = 50, - /* Note: Values 51-62 are reserved for future use */ - I40E_FILTER_PCTYPE_L2_PAYLOAD = 63, -}; - -enum i40e_filter_program_desc_dest { - I40E_FILTER_PROGRAM_DESC_DEST_DROP_PACKET = 0x0, - I40E_FILTER_PROGRAM_DESC_DEST_DIRECT_PACKET_QINDEX = 0x1, - I40E_FILTER_PROGRAM_DESC_DEST_DIRECT_PACKET_OTHER = 0x2, -}; - -enum i40e_filter_program_desc_fd_status { - I40E_FILTER_PROGRAM_DESC_FD_STATUS_NONE = 0x0, - I40E_FILTER_PROGRAM_DESC_FD_STATUS_FD_ID = 0x1, - I40E_FILTER_PROGRAM_DESC_FD_STATUS_FD_ID_4FLEX_BYTES = 0x2, - I40E_FILTER_PROGRAM_DESC_FD_STATUS_8FLEX_BYTES = 0x3, -}; - -#define I40E_TXD_FLTR_QW0_DEST_VSI_SHIFT 23 -#define I40E_TXD_FLTR_QW0_DEST_VSI_MASK (0x1FFUL << \ - I40E_TXD_FLTR_QW0_DEST_VSI_SHIFT) - -#define I40E_TXD_FLTR_QW1_CMD_SHIFT 4 -#define I40E_TXD_FLTR_QW1_CMD_MASK (0xFFFFULL << \ - I40E_TXD_FLTR_QW1_CMD_SHIFT) - -#define I40E_TXD_FLTR_QW1_PCMD_SHIFT (0x0ULL + I40E_TXD_FLTR_QW1_CMD_SHIFT) -#define I40E_TXD_FLTR_QW1_PCMD_MASK (0x7ULL << I40E_TXD_FLTR_QW1_PCMD_SHIFT) - -enum i40e_filter_program_desc_pcmd { - I40E_FILTER_PROGRAM_DESC_PCMD_ADD_UPDATE = 0x1, - I40E_FILTER_PROGRAM_DESC_PCMD_REMOVE = 0x2, -}; - -#define I40E_TXD_FLTR_QW1_DEST_SHIFT (0x3ULL + I40E_TXD_FLTR_QW1_CMD_SHIFT) -#define I40E_TXD_FLTR_QW1_DEST_MASK (0x3ULL << I40E_TXD_FLTR_QW1_DEST_SHIFT) - -#define I40E_TXD_FLTR_QW1_CNT_ENA_SHIFT (0x7ULL + I40E_TXD_FLTR_QW1_CMD_SHIFT) -#define I40E_TXD_FLTR_QW1_CNT_ENA_MASK BIT_ULL(I40E_TXD_FLTR_QW1_CNT_ENA_SHIFT) - -#define I40E_TXD_FLTR_QW1_FD_STATUS_SHIFT (0x9ULL + \ - I40E_TXD_FLTR_QW1_CMD_SHIFT) -#define I40E_TXD_FLTR_QW1_FD_STATUS_MASK (0x3ULL << \ - I40E_TXD_FLTR_QW1_FD_STATUS_SHIFT) - -#define I40E_TXD_FLTR_QW1_CNTINDEX_SHIFT 20 -#define I40E_TXD_FLTR_QW1_CNTINDEX_MASK (0x1FFUL << \ - I40E_TXD_FLTR_QW1_CNTINDEX_SHIFT) - -enum i40e_filter_type { - I40E_FLOW_DIRECTOR_FLTR = 0, - I40E_PE_QUAD_HASH_FLTR = 1, - I40E_ETHERTYPE_FLTR, - I40E_FCOE_CTX_FLTR, - I40E_MAC_VLAN_FLTR, - I40E_HASH_FLTR -}; - -struct i40e_vsi_context { - u16 seid; - u16 uplink_seid; - u16 vsi_number; - u16 vsis_allocated; - u16 vsis_unallocated; - u16 flags; - u8 pf_num; - u8 vf_num; - u8 connection_type; - struct i40e_aqc_vsi_properties_data info; -}; - -struct i40e_veb_context { - u16 seid; - u16 uplink_seid; - u16 veb_number; - u16 vebs_allocated; - u16 vebs_unallocated; - u16 flags; - struct i40e_aqc_get_veb_parameters_completion info; -}; - -/* Statistics collected by each port, VSI, VEB, and S-channel */ -struct i40e_eth_stats { - u64 rx_bytes; /* gorc */ - u64 rx_unicast; /* uprc */ - u64 rx_multicast; /* mprc */ - u64 rx_broadcast; /* bprc */ - u64 rx_discards; /* rdpc */ - u64 rx_unknown_protocol; /* rupp */ - u64 tx_bytes; /* gotc */ - u64 tx_unicast; /* uptc */ - u64 tx_multicast; /* mptc */ - u64 tx_broadcast; /* bptc */ - u64 tx_discards; /* tdpc */ - u64 tx_errors; /* tepc */ -}; - -/* Statistics collected per VEB per TC */ -struct i40e_veb_tc_stats { - u64 tc_rx_packets[I40E_MAX_TRAFFIC_CLASS]; - u64 tc_rx_bytes[I40E_MAX_TRAFFIC_CLASS]; - u64 tc_tx_packets[I40E_MAX_TRAFFIC_CLASS]; - u64 tc_tx_bytes[I40E_MAX_TRAFFIC_CLASS]; -}; - -/* Statistics collected by the MAC */ -struct i40e_hw_port_stats { - /* eth stats collected by the port */ - struct i40e_eth_stats eth; - - /* additional port specific stats */ - u64 tx_dropped_link_down; /* tdold */ - u64 crc_errors; /* crcerrs */ - u64 illegal_bytes; /* illerrc */ - u64 error_bytes; /* errbc */ - u64 mac_local_faults; /* mlfc */ - u64 mac_remote_faults; /* mrfc */ - u64 rx_length_errors; /* rlec */ - u64 link_xon_rx; /* lxonrxc */ - u64 link_xoff_rx; /* lxoffrxc */ - u64 priority_xon_rx[8]; /* pxonrxc[8] */ - u64 priority_xoff_rx[8]; /* pxoffrxc[8] */ - u64 link_xon_tx; /* lxontxc */ - u64 link_xoff_tx; /* lxofftxc */ - u64 priority_xon_tx[8]; /* pxontxc[8] */ - u64 priority_xoff_tx[8]; /* pxofftxc[8] */ - u64 priority_xon_2_xoff[8]; /* pxon2offc[8] */ - u64 rx_size_64; /* prc64 */ - u64 rx_size_127; /* prc127 */ - u64 rx_size_255; /* prc255 */ - u64 rx_size_511; /* prc511 */ - u64 rx_size_1023; /* prc1023 */ - u64 rx_size_1522; /* prc1522 */ - u64 rx_size_big; /* prc9522 */ - u64 rx_undersize; /* ruc */ - u64 rx_fragments; /* rfc */ - u64 rx_oversize; /* roc */ - u64 rx_jabber; /* rjc */ - u64 tx_size_64; /* ptc64 */ - u64 tx_size_127; /* ptc127 */ - u64 tx_size_255; /* ptc255 */ - u64 tx_size_511; /* ptc511 */ - u64 tx_size_1023; /* ptc1023 */ - u64 tx_size_1522; /* ptc1522 */ - u64 tx_size_big; /* ptc9522 */ - u64 mac_short_packet_dropped; /* mspdc */ - u64 checksum_error; /* xec */ - /* flow director stats */ - u64 fd_atr_match; - u64 fd_sb_match; - u64 fd_atr_tunnel_match; - u32 fd_atr_status; - u32 fd_sb_status; - /* EEE LPI */ - u32 tx_lpi_status; - u32 rx_lpi_status; - u64 tx_lpi_count; /* etlpic */ - u64 rx_lpi_count; /* erlpic */ -}; - -/* Checksum and Shadow RAM pointers */ -#define I40E_SR_NVM_CONTROL_WORD 0x00 -#define I40E_EMP_MODULE_PTR 0x0F -#define I40E_SR_EMP_MODULE_PTR 0x48 -#define I40E_NVM_OEM_VER_OFF 0x83 -#define I40E_SR_NVM_DEV_STARTER_VERSION 0x18 -#define I40E_SR_NVM_WAKE_ON_LAN 0x19 -#define I40E_SR_ALTERNATE_SAN_MAC_ADDRESS_PTR 0x27 -#define I40E_SR_NVM_EETRACK_LO 0x2D -#define I40E_SR_NVM_EETRACK_HI 0x2E -#define I40E_SR_VPD_PTR 0x2F -#define I40E_SR_PCIE_ALT_AUTO_LOAD_PTR 0x3E -#define I40E_SR_SW_CHECKSUM_WORD 0x3F - -/* Auxiliary field, mask and shift definition for Shadow RAM and NVM Flash */ -#define I40E_SR_VPD_MODULE_MAX_SIZE 1024 -#define I40E_SR_PCIE_ALT_MODULE_MAX_SIZE 1024 -#define I40E_SR_CONTROL_WORD_1_SHIFT 0x06 -#define I40E_SR_CONTROL_WORD_1_MASK (0x03 << I40E_SR_CONTROL_WORD_1_SHIFT) -#define I40E_SR_CONTROL_WORD_1_NVM_BANK_VALID BIT(5) -#define I40E_SR_NVM_MAP_STRUCTURE_TYPE BIT(12) -#define I40E_PTR_TYPE BIT(15) - -/* Shadow RAM related */ -#define I40E_SR_SECTOR_SIZE_IN_WORDS 0x800 -#define I40E_SR_WORDS_IN_1KB 512 -/* Checksum should be calculated such that after adding all the words, - * including the checksum word itself, the sum should be 0xBABA. - */ -#define I40E_SR_SW_CHECKSUM_BASE 0xBABA - -#define I40E_SRRD_SRCTL_ATTEMPTS 100000 - -enum i40e_switch_element_types { - I40E_SWITCH_ELEMENT_TYPE_MAC = 1, - I40E_SWITCH_ELEMENT_TYPE_PF = 2, - I40E_SWITCH_ELEMENT_TYPE_VF = 3, - I40E_SWITCH_ELEMENT_TYPE_EMP = 4, - I40E_SWITCH_ELEMENT_TYPE_BMC = 6, - I40E_SWITCH_ELEMENT_TYPE_PE = 16, - I40E_SWITCH_ELEMENT_TYPE_VEB = 17, - I40E_SWITCH_ELEMENT_TYPE_PA = 18, - I40E_SWITCH_ELEMENT_TYPE_VSI = 19, -}; - -/* Supported EtherType filters */ -enum i40e_ether_type_index { - I40E_ETHER_TYPE_1588 = 0, - I40E_ETHER_TYPE_FIP = 1, - I40E_ETHER_TYPE_OUI_EXTENDED = 2, - I40E_ETHER_TYPE_MAC_CONTROL = 3, - I40E_ETHER_TYPE_LLDP = 4, - I40E_ETHER_TYPE_EVB_PROTOCOL1 = 5, - I40E_ETHER_TYPE_EVB_PROTOCOL2 = 6, - I40E_ETHER_TYPE_QCN_CNM = 7, - I40E_ETHER_TYPE_8021X = 8, - I40E_ETHER_TYPE_ARP = 9, - I40E_ETHER_TYPE_RSV1 = 10, - I40E_ETHER_TYPE_RSV2 = 11, -}; - -/* Filter context base size is 1K */ -#define I40E_HASH_FILTER_BASE_SIZE 1024 -/* Supported Hash filter values */ -enum i40e_hash_filter_size { - I40E_HASH_FILTER_SIZE_1K = 0, - I40E_HASH_FILTER_SIZE_2K = 1, - I40E_HASH_FILTER_SIZE_4K = 2, - I40E_HASH_FILTER_SIZE_8K = 3, - I40E_HASH_FILTER_SIZE_16K = 4, - I40E_HASH_FILTER_SIZE_32K = 5, - I40E_HASH_FILTER_SIZE_64K = 6, - I40E_HASH_FILTER_SIZE_128K = 7, - I40E_HASH_FILTER_SIZE_256K = 8, - I40E_HASH_FILTER_SIZE_512K = 9, - I40E_HASH_FILTER_SIZE_1M = 10, -}; - -/* DMA context base size is 0.5K */ -#define I40E_DMA_CNTX_BASE_SIZE 512 -/* Supported DMA context values */ -enum i40e_dma_cntx_size { - I40E_DMA_CNTX_SIZE_512 = 0, - I40E_DMA_CNTX_SIZE_1K = 1, - I40E_DMA_CNTX_SIZE_2K = 2, - I40E_DMA_CNTX_SIZE_4K = 3, - I40E_DMA_CNTX_SIZE_8K = 4, - I40E_DMA_CNTX_SIZE_16K = 5, - I40E_DMA_CNTX_SIZE_32K = 6, - I40E_DMA_CNTX_SIZE_64K = 7, - I40E_DMA_CNTX_SIZE_128K = 8, - I40E_DMA_CNTX_SIZE_256K = 9, -}; - -/* Supported Hash look up table (LUT) sizes */ -enum i40e_hash_lut_size { - I40E_HASH_LUT_SIZE_128 = 0, - I40E_HASH_LUT_SIZE_512 = 1, -}; - -/* Structure to hold a per PF filter control settings */ -struct i40e_filter_control_settings { - /* number of PE Quad Hash filter buckets */ - enum i40e_hash_filter_size pe_filt_num; - /* number of PE Quad Hash contexts */ - enum i40e_dma_cntx_size pe_cntx_num; - /* number of FCoE filter buckets */ - enum i40e_hash_filter_size fcoe_filt_num; - /* number of FCoE DDP contexts */ - enum i40e_dma_cntx_size fcoe_cntx_num; - /* size of the Hash LUT */ - enum i40e_hash_lut_size hash_lut_size; - /* enable FDIR filters for PF and its VFs */ - bool enable_fdir; - /* enable Ethertype filters for PF and its VFs */ - bool enable_ethtype; - /* enable MAC/VLAN filters for PF and its VFs */ - bool enable_macvlan; -}; - -/* Structure to hold device level control filter counts */ -struct i40e_control_filter_stats { - u16 mac_etype_used; /* Used perfect match MAC/EtherType filters */ - u16 etype_used; /* Used perfect EtherType filters */ - u16 mac_etype_free; /* Un-used perfect match MAC/EtherType filters */ - u16 etype_free; /* Un-used perfect EtherType filters */ -}; - -enum i40e_reset_type { - I40E_RESET_POR = 0, - I40E_RESET_CORER = 1, - I40E_RESET_GLOBR = 2, - I40E_RESET_EMPR = 3, -}; - -/* IEEE 802.1AB LLDP Agent Variables from NVM */ -#define I40E_NVM_LLDP_CFG_PTR 0x06 -#define I40E_SR_LLDP_CFG_PTR 0x31 - -/* RSS Hash Table Size */ -#define I40E_PFQF_CTL_0_HASHLUTSIZE_512 0x00010000 - -/* INPUT SET MASK for RSS, flow director and flexible payload */ -#define I40E_FD_INSET_L3_SRC_SHIFT 47 -#define I40E_FD_INSET_L3_SRC_WORD_MASK (0x3ULL << \ - I40E_FD_INSET_L3_SRC_SHIFT) -#define I40E_FD_INSET_L3_DST_SHIFT 35 -#define I40E_FD_INSET_L3_DST_WORD_MASK (0x3ULL << \ - I40E_FD_INSET_L3_DST_SHIFT) -#define I40E_FD_INSET_L4_SRC_SHIFT 34 -#define I40E_FD_INSET_L4_SRC_WORD_MASK (0x1ULL << \ - I40E_FD_INSET_L4_SRC_SHIFT) -#define I40E_FD_INSET_L4_DST_SHIFT 33 -#define I40E_FD_INSET_L4_DST_WORD_MASK (0x1ULL << \ - I40E_FD_INSET_L4_DST_SHIFT) -#define I40E_FD_INSET_VERIFY_TAG_SHIFT 31 -#define I40E_FD_INSET_VERIFY_TAG_WORD_MASK (0x3ULL << \ - I40E_FD_INSET_VERIFY_TAG_SHIFT) - -#define I40E_FD_INSET_FLEX_WORD50_SHIFT 17 -#define I40E_FD_INSET_FLEX_WORD50_MASK (0x1ULL << \ - I40E_FD_INSET_FLEX_WORD50_SHIFT) -#define I40E_FD_INSET_FLEX_WORD51_SHIFT 16 -#define I40E_FD_INSET_FLEX_WORD51_MASK (0x1ULL << \ - I40E_FD_INSET_FLEX_WORD51_SHIFT) -#define I40E_FD_INSET_FLEX_WORD52_SHIFT 15 -#define I40E_FD_INSET_FLEX_WORD52_MASK (0x1ULL << \ - I40E_FD_INSET_FLEX_WORD52_SHIFT) -#define I40E_FD_INSET_FLEX_WORD53_SHIFT 14 -#define I40E_FD_INSET_FLEX_WORD53_MASK (0x1ULL << \ - I40E_FD_INSET_FLEX_WORD53_SHIFT) -#define I40E_FD_INSET_FLEX_WORD54_SHIFT 13 -#define I40E_FD_INSET_FLEX_WORD54_MASK (0x1ULL << \ - I40E_FD_INSET_FLEX_WORD54_SHIFT) -#define I40E_FD_INSET_FLEX_WORD55_SHIFT 12 -#define I40E_FD_INSET_FLEX_WORD55_MASK (0x1ULL << \ - I40E_FD_INSET_FLEX_WORD55_SHIFT) -#define I40E_FD_INSET_FLEX_WORD56_SHIFT 11 -#define I40E_FD_INSET_FLEX_WORD56_MASK (0x1ULL << \ - I40E_FD_INSET_FLEX_WORD56_SHIFT) -#define I40E_FD_INSET_FLEX_WORD57_SHIFT 10 -#define I40E_FD_INSET_FLEX_WORD57_MASK (0x1ULL << \ - I40E_FD_INSET_FLEX_WORD57_SHIFT) - -/* Version format for Dynamic Device Personalization(DDP) */ -struct i40e_ddp_version { - u8 major; - u8 minor; - u8 update; - u8 draft; -}; - -#define I40E_DDP_NAME_SIZE 32 - -/* Package header */ -struct i40e_package_header { - struct i40e_ddp_version version; - u32 segment_count; - u32 segment_offset[1]; -}; - -/* Generic segment header */ -struct i40e_generic_seg_header { -#define SEGMENT_TYPE_METADATA 0x00000001 -#define SEGMENT_TYPE_NOTES 0x00000002 -#define SEGMENT_TYPE_I40E 0x00000011 -#define SEGMENT_TYPE_X722 0x00000012 - u32 type; - struct i40e_ddp_version version; - u32 size; - char name[I40E_DDP_NAME_SIZE]; -}; - -struct i40e_metadata_segment { - struct i40e_generic_seg_header header; - struct i40e_ddp_version version; - u32 track_id; - char name[I40E_DDP_NAME_SIZE]; -}; - -struct i40e_device_id_entry { - u32 vendor_dev_id; - u32 sub_vendor_dev_id; -}; - -struct i40e_profile_segment { - struct i40e_generic_seg_header header; - struct i40e_ddp_version version; - char name[I40E_DDP_NAME_SIZE]; - u32 device_table_count; - struct i40e_device_id_entry device_table[1]; -}; - -struct i40e_section_table { - u32 section_count; - u32 section_offset[1]; -}; - -struct i40e_profile_section_header { - u16 tbl_size; - u16 data_end; - struct { -#define SECTION_TYPE_INFO 0x00000010 -#define SECTION_TYPE_MMIO 0x00000800 -#define SECTION_TYPE_AQ 0x00000801 -#define SECTION_TYPE_NOTE 0x80000000 -#define SECTION_TYPE_NAME 0x80000001 - u32 type; - u32 offset; - u32 size; - } section; -}; - -struct i40e_profile_info { - u32 track_id; - struct i40e_ddp_version version; - u8 op; -#define I40E_DDP_ADD_TRACKID 0x01 -#define I40E_DDP_REMOVE_TRACKID 0x02 - u8 reserved[7]; - u8 name[I40E_DDP_NAME_SIZE]; -}; -#endif /* _I40E_TYPE_H_ */ diff --git a/drivers/net/ethernet/intel/i40evf/i40evf.h b/drivers/net/ethernet/intel/i40evf/i40evf.h deleted file mode 100644 index 96e537a35000..000000000000 --- a/drivers/net/ethernet/intel/i40evf/i40evf.h +++ /dev/null @@ -1,427 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright(c) 2013 - 2018 Intel Corporation. */ - -#ifndef _I40EVF_H_ -#define _I40EVF_H_ - -#include <linux/module.h> -#include <linux/pci.h> -#include <linux/aer.h> -#include <linux/netdevice.h> -#include <linux/vmalloc.h> -#include <linux/interrupt.h> -#include <linux/ethtool.h> -#include <linux/if_vlan.h> -#include <linux/ip.h> -#include <linux/tcp.h> -#include <linux/sctp.h> -#include <linux/ipv6.h> -#include <linux/kernel.h> -#include <linux/bitops.h> -#include <linux/timer.h> -#include <linux/workqueue.h> -#include <linux/wait.h> -#include <linux/delay.h> -#include <linux/gfp.h> -#include <linux/skbuff.h> -#include <linux/dma-mapping.h> -#include <linux/etherdevice.h> -#include <linux/socket.h> -#include <linux/jiffies.h> -#include <net/ip6_checksum.h> -#include <net/pkt_cls.h> -#include <net/udp.h> -#include <net/tc_act/tc_gact.h> -#include <net/tc_act/tc_mirred.h> - -#include "i40e_type.h" -#include <linux/avf/virtchnl.h> -#include "i40e_txrx.h" - -#define DEFAULT_DEBUG_LEVEL_SHIFT 3 -#define PFX "i40evf: " - -/* VSI state flags shared with common code */ -enum i40evf_vsi_state_t { - __I40E_VSI_DOWN, - /* This must be last as it determines the size of the BITMAP */ - __I40E_VSI_STATE_SIZE__, -}; - -/* dummy struct to make common code less painful */ -struct i40e_vsi { - struct i40evf_adapter *back; - struct net_device *netdev; - unsigned long active_vlans[BITS_TO_LONGS(VLAN_N_VID)]; - u16 seid; - u16 id; - DECLARE_BITMAP(state, __I40E_VSI_STATE_SIZE__); - int base_vector; - u16 work_limit; - u16 qs_handle; - void *priv; /* client driver data reference. */ -}; - -/* How many Rx Buffers do we bundle into one write to the hardware ? */ -#define I40EVF_RX_BUFFER_WRITE 16 /* Must be power of 2 */ -#define I40EVF_DEFAULT_TXD 512 -#define I40EVF_DEFAULT_RXD 512 -#define I40EVF_MAX_TXD 4096 -#define I40EVF_MIN_TXD 64 -#define I40EVF_MAX_RXD 4096 -#define I40EVF_MIN_RXD 64 -#define I40EVF_REQ_DESCRIPTOR_MULTIPLE 32 -#define I40EVF_MAX_AQ_BUF_SIZE 4096 -#define I40EVF_AQ_LEN 32 -#define I40EVF_AQ_MAX_ERR 20 /* times to try before resetting AQ */ - -#define MAXIMUM_ETHERNET_VLAN_SIZE (VLAN_ETH_FRAME_LEN + ETH_FCS_LEN) - -#define I40E_RX_DESC(R, i) (&(((union i40e_32byte_rx_desc *)((R)->desc))[i])) -#define I40E_TX_DESC(R, i) (&(((struct i40e_tx_desc *)((R)->desc))[i])) -#define I40E_TX_CTXTDESC(R, i) \ - (&(((struct i40e_tx_context_desc *)((R)->desc))[i])) -#define I40EVF_MAX_REQ_QUEUES 4 - -#define I40EVF_HKEY_ARRAY_SIZE ((I40E_VFQF_HKEY_MAX_INDEX + 1) * 4) -#define I40EVF_HLUT_ARRAY_SIZE ((I40E_VFQF_HLUT_MAX_INDEX + 1) * 4) -#define I40EVF_MBPS_DIVISOR 125000 /* divisor to convert to Mbps */ - -/* MAX_MSIX_Q_VECTORS of these are allocated, - * but we only use one per queue-specific vector. - */ -struct i40e_q_vector { - struct i40evf_adapter *adapter; - struct i40e_vsi *vsi; - struct napi_struct napi; - struct i40e_ring_container rx; - struct i40e_ring_container tx; - u32 ring_mask; - u8 itr_countdown; /* when 0 should adjust adaptive ITR */ - u8 num_ringpairs; /* total number of ring pairs in vector */ - u16 v_idx; /* index in the vsi->q_vector array. */ - u16 reg_idx; /* register index of the interrupt */ - char name[IFNAMSIZ + 15]; - bool arm_wb_state; - cpumask_t affinity_mask; - struct irq_affinity_notify affinity_notify; -}; - -/* Helper macros to switch between ints/sec and what the register uses. - * And yes, it's the same math going both ways. The lowest value - * supported by all of the i40e hardware is 8. - */ -#define EITR_INTS_PER_SEC_TO_REG(_eitr) \ - ((_eitr) ? (1000000000 / ((_eitr) * 256)) : 8) -#define EITR_REG_TO_INTS_PER_SEC EITR_INTS_PER_SEC_TO_REG - -#define I40EVF_DESC_UNUSED(R) \ - ((((R)->next_to_clean > (R)->next_to_use) ? 0 : (R)->count) + \ - (R)->next_to_clean - (R)->next_to_use - 1) - -#define I40EVF_RX_DESC_ADV(R, i) \ - (&(((union i40e_adv_rx_desc *)((R).desc))[i])) -#define I40EVF_TX_DESC_ADV(R, i) \ - (&(((union i40e_adv_tx_desc *)((R).desc))[i])) -#define I40EVF_TX_CTXTDESC_ADV(R, i) \ - (&(((struct i40e_adv_tx_context_desc *)((R).desc))[i])) - -#define OTHER_VECTOR 1 -#define NONQ_VECS (OTHER_VECTOR) - -#define MIN_MSIX_Q_VECTORS 1 -#define MIN_MSIX_COUNT (MIN_MSIX_Q_VECTORS + NONQ_VECS) - -#define I40EVF_QUEUE_END_OF_LIST 0x7FF -#define I40EVF_FREE_VECTOR 0x7FFF -struct i40evf_mac_filter { - struct list_head list; - u8 macaddr[ETH_ALEN]; - bool remove; /* filter needs to be removed */ - bool add; /* filter needs to be added */ -}; - -struct i40evf_vlan_filter { - struct list_head list; - u16 vlan; - bool remove; /* filter needs to be removed */ - bool add; /* filter needs to be added */ -}; - -#define I40EVF_MAX_TRAFFIC_CLASS 4 -/* State of traffic class creation */ -enum i40evf_tc_state_t { - __I40EVF_TC_INVALID, /* no traffic class, default state */ - __I40EVF_TC_RUNNING, /* traffic classes have been created */ -}; - -/* channel info */ -struct i40evf_channel_config { - struct virtchnl_channel_info ch_info[I40EVF_MAX_TRAFFIC_CLASS]; - enum i40evf_tc_state_t state; - u8 total_qps; -}; - -/* State of cloud filter */ -enum i40evf_cloud_filter_state_t { - __I40EVF_CF_INVALID, /* cloud filter not added */ - __I40EVF_CF_ADD_PENDING, /* cloud filter pending add by the PF */ - __I40EVF_CF_DEL_PENDING, /* cloud filter pending del by the PF */ - __I40EVF_CF_ACTIVE, /* cloud filter is active */ -}; - -/* Driver state. The order of these is important! */ -enum i40evf_state_t { - __I40EVF_STARTUP, /* driver loaded, probe complete */ - __I40EVF_REMOVE, /* driver is being unloaded */ - __I40EVF_INIT_VERSION_CHECK, /* aq msg sent, awaiting reply */ - __I40EVF_INIT_GET_RESOURCES, /* aq msg sent, awaiting reply */ - __I40EVF_INIT_SW, /* got resources, setting up structs */ - __I40EVF_RESETTING, /* in reset */ - /* Below here, watchdog is running */ - __I40EVF_DOWN, /* ready, can be opened */ - __I40EVF_DOWN_PENDING, /* descending, waiting for watchdog */ - __I40EVF_TESTING, /* in ethtool self-test */ - __I40EVF_RUNNING, /* opened, working */ -}; - -enum i40evf_critical_section_t { - __I40EVF_IN_CRITICAL_TASK, /* cannot be interrupted */ - __I40EVF_IN_CLIENT_TASK, - __I40EVF_IN_REMOVE_TASK, /* device being removed */ -}; - -#define I40EVF_CLOUD_FIELD_OMAC 0x01 -#define I40EVF_CLOUD_FIELD_IMAC 0x02 -#define I40EVF_CLOUD_FIELD_IVLAN 0x04 -#define I40EVF_CLOUD_FIELD_TEN_ID 0x08 -#define I40EVF_CLOUD_FIELD_IIP 0x10 - -#define I40EVF_CF_FLAGS_OMAC I40EVF_CLOUD_FIELD_OMAC -#define I40EVF_CF_FLAGS_IMAC I40EVF_CLOUD_FIELD_IMAC -#define I40EVF_CF_FLAGS_IMAC_IVLAN (I40EVF_CLOUD_FIELD_IMAC |\ - I40EVF_CLOUD_FIELD_IVLAN) -#define I40EVF_CF_FLAGS_IMAC_TEN_ID (I40EVF_CLOUD_FIELD_IMAC |\ - I40EVF_CLOUD_FIELD_TEN_ID) -#define I40EVF_CF_FLAGS_OMAC_TEN_ID_IMAC (I40EVF_CLOUD_FIELD_OMAC |\ - I40EVF_CLOUD_FIELD_IMAC |\ - I40EVF_CLOUD_FIELD_TEN_ID) -#define I40EVF_CF_FLAGS_IMAC_IVLAN_TEN_ID (I40EVF_CLOUD_FIELD_IMAC |\ - I40EVF_CLOUD_FIELD_IVLAN |\ - I40EVF_CLOUD_FIELD_TEN_ID) -#define I40EVF_CF_FLAGS_IIP I40E_CLOUD_FIELD_IIP - -/* bookkeeping of cloud filters */ -struct i40evf_cloud_filter { - enum i40evf_cloud_filter_state_t state; - struct list_head list; - struct virtchnl_filter f; - unsigned long cookie; - bool del; /* filter needs to be deleted */ - bool add; /* filter needs to be added */ -}; - -/* board specific private data structure */ -struct i40evf_adapter { - struct timer_list watchdog_timer; - struct work_struct reset_task; - struct work_struct adminq_task; - struct delayed_work client_task; - struct delayed_work init_task; - wait_queue_head_t down_waitqueue; - struct i40e_q_vector *q_vectors; - struct list_head vlan_filter_list; - struct list_head mac_filter_list; - /* Lock to protect accesses to MAC and VLAN lists */ - spinlock_t mac_vlan_list_lock; - char misc_vector_name[IFNAMSIZ + 9]; - int num_active_queues; - int num_req_queues; - - /* TX */ - struct i40e_ring *tx_rings; - u32 tx_timeout_count; - u32 tx_desc_count; - - /* RX */ - struct i40e_ring *rx_rings; - u64 hw_csum_rx_error; - u32 rx_desc_count; - int num_msix_vectors; - int num_iwarp_msix; - int iwarp_base_vector; - u32 client_pending; - struct i40e_client_instance *cinst; - struct msix_entry *msix_entries; - - u32 flags; -#define I40EVF_FLAG_RX_CSUM_ENABLED BIT(0) -#define I40EVF_FLAG_PF_COMMS_FAILED BIT(3) -#define I40EVF_FLAG_RESET_PENDING BIT(4) -#define I40EVF_FLAG_RESET_NEEDED BIT(5) -#define I40EVF_FLAG_WB_ON_ITR_CAPABLE BIT(6) -#define I40EVF_FLAG_ADDR_SET_BY_PF BIT(8) -#define I40EVF_FLAG_SERVICE_CLIENT_REQUESTED BIT(9) -#define I40EVF_FLAG_CLIENT_NEEDS_OPEN BIT(10) -#define I40EVF_FLAG_CLIENT_NEEDS_CLOSE BIT(11) -#define I40EVF_FLAG_CLIENT_NEEDS_L2_PARAMS BIT(12) -#define I40EVF_FLAG_PROMISC_ON BIT(13) -#define I40EVF_FLAG_ALLMULTI_ON BIT(14) -#define I40EVF_FLAG_LEGACY_RX BIT(15) -#define I40EVF_FLAG_REINIT_ITR_NEEDED BIT(16) -#define I40EVF_FLAG_QUEUES_DISABLED BIT(17) -/* duplicates for common code */ -#define I40E_FLAG_DCB_ENABLED 0 -#define I40E_FLAG_RX_CSUM_ENABLED I40EVF_FLAG_RX_CSUM_ENABLED -#define I40E_FLAG_LEGACY_RX I40EVF_FLAG_LEGACY_RX - /* flags for admin queue service task */ - u32 aq_required; -#define I40EVF_FLAG_AQ_ENABLE_QUEUES BIT(0) -#define I40EVF_FLAG_AQ_DISABLE_QUEUES BIT(1) -#define I40EVF_FLAG_AQ_ADD_MAC_FILTER BIT(2) -#define I40EVF_FLAG_AQ_ADD_VLAN_FILTER BIT(3) -#define I40EVF_FLAG_AQ_DEL_MAC_FILTER BIT(4) -#define I40EVF_FLAG_AQ_DEL_VLAN_FILTER BIT(5) -#define I40EVF_FLAG_AQ_CONFIGURE_QUEUES BIT(6) -#define I40EVF_FLAG_AQ_MAP_VECTORS BIT(7) -#define I40EVF_FLAG_AQ_HANDLE_RESET BIT(8) -#define I40EVF_FLAG_AQ_CONFIGURE_RSS BIT(9) /* direct AQ config */ -#define I40EVF_FLAG_AQ_GET_CONFIG BIT(10) -/* Newer style, RSS done by the PF so we can ignore hardware vagaries. */ -#define I40EVF_FLAG_AQ_GET_HENA BIT(11) -#define I40EVF_FLAG_AQ_SET_HENA BIT(12) -#define I40EVF_FLAG_AQ_SET_RSS_KEY BIT(13) -#define I40EVF_FLAG_AQ_SET_RSS_LUT BIT(14) -#define I40EVF_FLAG_AQ_REQUEST_PROMISC BIT(15) -#define I40EVF_FLAG_AQ_RELEASE_PROMISC BIT(16) -#define I40EVF_FLAG_AQ_REQUEST_ALLMULTI BIT(17) -#define I40EVF_FLAG_AQ_RELEASE_ALLMULTI BIT(18) -#define I40EVF_FLAG_AQ_ENABLE_VLAN_STRIPPING BIT(19) -#define I40EVF_FLAG_AQ_DISABLE_VLAN_STRIPPING BIT(20) -#define I40EVF_FLAG_AQ_ENABLE_CHANNELS BIT(21) -#define I40EVF_FLAG_AQ_DISABLE_CHANNELS BIT(22) -#define I40EVF_FLAG_AQ_ADD_CLOUD_FILTER BIT(23) -#define I40EVF_FLAG_AQ_DEL_CLOUD_FILTER BIT(24) - - /* OS defined structs */ - struct net_device *netdev; - struct pci_dev *pdev; - - struct i40e_hw hw; /* defined in i40e_type.h */ - - enum i40evf_state_t state; - unsigned long crit_section; - - struct work_struct watchdog_task; - bool netdev_registered; - bool link_up; - enum virtchnl_link_speed link_speed; - enum virtchnl_ops current_op; -#define CLIENT_ALLOWED(_a) ((_a)->vf_res ? \ - (_a)->vf_res->vf_cap_flags & \ - VIRTCHNL_VF_OFFLOAD_IWARP : \ - 0) -#define CLIENT_ENABLED(_a) ((_a)->cinst) -/* RSS by the PF should be preferred over RSS via other methods. */ -#define RSS_PF(_a) ((_a)->vf_res->vf_cap_flags & \ - VIRTCHNL_VF_OFFLOAD_RSS_PF) -#define RSS_AQ(_a) ((_a)->vf_res->vf_cap_flags & \ - VIRTCHNL_VF_OFFLOAD_RSS_AQ) -#define RSS_REG(_a) (!((_a)->vf_res->vf_cap_flags & \ - (VIRTCHNL_VF_OFFLOAD_RSS_AQ | \ - VIRTCHNL_VF_OFFLOAD_RSS_PF))) -#define VLAN_ALLOWED(_a) ((_a)->vf_res->vf_cap_flags & \ - VIRTCHNL_VF_OFFLOAD_VLAN) - struct virtchnl_vf_resource *vf_res; /* incl. all VSIs */ - struct virtchnl_vsi_resource *vsi_res; /* our LAN VSI */ - struct virtchnl_version_info pf_version; -#define PF_IS_V11(_a) (((_a)->pf_version.major == 1) && \ - ((_a)->pf_version.minor == 1)) - u16 msg_enable; - struct i40e_eth_stats current_stats; - struct i40e_vsi vsi; - u32 aq_wait_count; - /* RSS stuff */ - u64 hena; - u16 rss_key_size; - u16 rss_lut_size; - u8 *rss_key; - u8 *rss_lut; - /* ADQ related members */ - struct i40evf_channel_config ch_config; - u8 num_tc; - struct list_head cloud_filter_list; - /* lock to protest access to the cloud filter list */ - spinlock_t cloud_filter_list_lock; - u16 num_cloud_filters; -}; - - -/* Ethtool Private Flags */ - -/* lan device */ -struct i40e_device { - struct list_head list; - struct i40evf_adapter *vf; -}; - -/* needed by i40evf_ethtool.c */ -extern char i40evf_driver_name[]; -extern const char i40evf_driver_version[]; - -int i40evf_up(struct i40evf_adapter *adapter); -void i40evf_down(struct i40evf_adapter *adapter); -int i40evf_process_config(struct i40evf_adapter *adapter); -void i40evf_schedule_reset(struct i40evf_adapter *adapter); -void i40evf_reset(struct i40evf_adapter *adapter); -void i40evf_set_ethtool_ops(struct net_device *netdev); -void i40evf_update_stats(struct i40evf_adapter *adapter); -void i40evf_reset_interrupt_capability(struct i40evf_adapter *adapter); -int i40evf_init_interrupt_scheme(struct i40evf_adapter *adapter); -void i40evf_irq_enable_queues(struct i40evf_adapter *adapter, u32 mask); -void i40evf_free_all_tx_resources(struct i40evf_adapter *adapter); -void i40evf_free_all_rx_resources(struct i40evf_adapter *adapter); - -void i40e_napi_add_all(struct i40evf_adapter *adapter); -void i40e_napi_del_all(struct i40evf_adapter *adapter); - -int i40evf_send_api_ver(struct i40evf_adapter *adapter); -int i40evf_verify_api_ver(struct i40evf_adapter *adapter); -int i40evf_send_vf_config_msg(struct i40evf_adapter *adapter); -int i40evf_get_vf_config(struct i40evf_adapter *adapter); -void i40evf_irq_enable(struct i40evf_adapter *adapter, bool flush); -void i40evf_configure_queues(struct i40evf_adapter *adapter); -void i40evf_deconfigure_queues(struct i40evf_adapter *adapter); -void i40evf_enable_queues(struct i40evf_adapter *adapter); -void i40evf_disable_queues(struct i40evf_adapter *adapter); -void i40evf_map_queues(struct i40evf_adapter *adapter); -int i40evf_request_queues(struct i40evf_adapter *adapter, int num); -void i40evf_add_ether_addrs(struct i40evf_adapter *adapter); -void i40evf_del_ether_addrs(struct i40evf_adapter *adapter); -void i40evf_add_vlans(struct i40evf_adapter *adapter); -void i40evf_del_vlans(struct i40evf_adapter *adapter); -void i40evf_set_promiscuous(struct i40evf_adapter *adapter, int flags); -void i40evf_request_stats(struct i40evf_adapter *adapter); -void i40evf_request_reset(struct i40evf_adapter *adapter); -void i40evf_get_hena(struct i40evf_adapter *adapter); -void i40evf_set_hena(struct i40evf_adapter *adapter); -void i40evf_set_rss_key(struct i40evf_adapter *adapter); -void i40evf_set_rss_lut(struct i40evf_adapter *adapter); -void i40evf_enable_vlan_stripping(struct i40evf_adapter *adapter); -void i40evf_disable_vlan_stripping(struct i40evf_adapter *adapter); -void i40evf_virtchnl_completion(struct i40evf_adapter *adapter, - enum virtchnl_ops v_opcode, - i40e_status v_retval, u8 *msg, u16 msglen); -int i40evf_config_rss(struct i40evf_adapter *adapter); -int i40evf_lan_add_device(struct i40evf_adapter *adapter); -int i40evf_lan_del_device(struct i40evf_adapter *adapter); -void i40evf_client_subtask(struct i40evf_adapter *adapter); -void i40evf_notify_client_message(struct i40e_vsi *vsi, u8 *msg, u16 len); -void i40evf_notify_client_l2_params(struct i40e_vsi *vsi); -void i40evf_notify_client_open(struct i40e_vsi *vsi); -void i40evf_notify_client_close(struct i40e_vsi *vsi, bool reset); -void i40evf_enable_channels(struct i40evf_adapter *adapter); -void i40evf_disable_channels(struct i40evf_adapter *adapter); -void i40evf_add_cloud_filter(struct i40evf_adapter *adapter); -void i40evf_del_cloud_filter(struct i40evf_adapter *adapter); -#endif /* _I40EVF_H_ */ diff --git a/drivers/net/ethernet/intel/i40evf/i40evf_ethtool.c b/drivers/net/ethernet/intel/i40evf/i40evf_ethtool.c deleted file mode 100644 index 9319971c5c92..000000000000 --- a/drivers/net/ethernet/intel/i40evf/i40evf_ethtool.c +++ /dev/null @@ -1,837 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -/* Copyright(c) 2013 - 2018 Intel Corporation. */ - -/* ethtool support for i40evf */ -#include "i40evf.h" - -#include <linux/uaccess.h> - -#include "i40e_ethtool_stats.h" - -#define I40EVF_STAT(_name, _stat) \ - I40E_STAT(struct i40evf_adapter, _name, _stat) - -static const struct i40e_stats i40evf_gstrings_stats[] = { - I40EVF_STAT("rx_bytes", current_stats.rx_bytes), - I40EVF_STAT("rx_unicast", current_stats.rx_unicast), - I40EVF_STAT("rx_multicast", current_stats.rx_multicast), - I40EVF_STAT("rx_broadcast", current_stats.rx_broadcast), - I40EVF_STAT("rx_discards", current_stats.rx_discards), - I40EVF_STAT("rx_unknown_protocol", current_stats.rx_unknown_protocol), - I40EVF_STAT("tx_bytes", current_stats.tx_bytes), - I40EVF_STAT("tx_unicast", current_stats.tx_unicast), - I40EVF_STAT("tx_multicast", current_stats.tx_multicast), - I40EVF_STAT("tx_broadcast", current_stats.tx_broadcast), - I40EVF_STAT("tx_discards", current_stats.tx_discards), - I40EVF_STAT("tx_errors", current_stats.tx_errors), -}; - -#define I40EVF_STATS_LEN ARRAY_SIZE(i40evf_gstrings_stats) - -#define I40EVF_QUEUE_STATS_LEN ARRAY_SIZE(i40e_gstrings_queue_stats) - -/* For now we have one and only one private flag and it is only defined - * when we have support for the SKIP_CPU_SYNC DMA attribute. Instead - * of leaving all this code sitting around empty we will strip it unless - * our one private flag is actually available. - */ -struct i40evf_priv_flags { - char flag_string[ETH_GSTRING_LEN]; - u32 flag; - bool read_only; -}; - -#define I40EVF_PRIV_FLAG(_name, _flag, _read_only) { \ - .flag_string = _name, \ - .flag = _flag, \ - .read_only = _read_only, \ -} - -static const struct i40evf_priv_flags i40evf_gstrings_priv_flags[] = { - I40EVF_PRIV_FLAG("legacy-rx", I40EVF_FLAG_LEGACY_RX, 0), -}; - -#define I40EVF_PRIV_FLAGS_STR_LEN ARRAY_SIZE(i40evf_gstrings_priv_flags) - -/** - * i40evf_get_link_ksettings - Get Link Speed and Duplex settings - * @netdev: network interface device structure - * @cmd: ethtool command - * - * Reports speed/duplex settings. Because this is a VF, we don't know what - * kind of link we really have, so we fake it. - **/ -static int i40evf_get_link_ksettings(struct net_device *netdev, - struct ethtool_link_ksettings *cmd) -{ - struct i40evf_adapter *adapter = netdev_priv(netdev); - - ethtool_link_ksettings_zero_link_mode(cmd, supported); - cmd->base.autoneg = AUTONEG_DISABLE; - cmd->base.port = PORT_NONE; - /* Set speed and duplex */ - switch (adapter->link_speed) { - case I40E_LINK_SPEED_40GB: - cmd->base.speed = SPEED_40000; - break; - case I40E_LINK_SPEED_25GB: -#ifdef SPEED_25000 - cmd->base.speed = SPEED_25000; -#else - netdev_info(netdev, - "Speed is 25G, display not supported by this version of ethtool.\n"); -#endif - break; - case I40E_LINK_SPEED_20GB: - cmd->base.speed = SPEED_20000; - break; - case I40E_LINK_SPEED_10GB: - cmd->base.speed = SPEED_10000; - break; - case I40E_LINK_SPEED_1GB: - cmd->base.speed = SPEED_1000; - break; - case I40E_LINK_SPEED_100MB: - cmd->base.speed = SPEED_100; - break; - default: - break; - } - cmd->base.duplex = DUPLEX_FULL; - - return 0; -} - -/** - * i40evf_get_sset_count - Get length of string set - * @netdev: network interface device structure - * @sset: id of string set - * - * Reports size of various string tables. - **/ -static int i40evf_get_sset_count(struct net_device *netdev, int sset) -{ - if (sset == ETH_SS_STATS) - return I40EVF_STATS_LEN + - (I40EVF_QUEUE_STATS_LEN * 2 * I40EVF_MAX_REQ_QUEUES); - else if (sset == ETH_SS_PRIV_FLAGS) - return I40EVF_PRIV_FLAGS_STR_LEN; - else - return -EINVAL; -} - -/** - * i40evf_get_ethtool_stats - report device statistics - * @netdev: network interface device structure - * @stats: ethtool statistics structure - * @data: pointer to data buffer - * - * All statistics are added to the data buffer as an array of u64. - **/ -static void i40evf_get_ethtool_stats(struct net_device *netdev, - struct ethtool_stats *stats, u64 *data) -{ - struct i40evf_adapter *adapter = netdev_priv(netdev); - unsigned int i; - - i40e_add_ethtool_stats(&data, adapter, i40evf_gstrings_stats); - - rcu_read_lock(); - for (i = 0; i < I40EVF_MAX_REQ_QUEUES; i++) { - struct i40e_ring *ring; - - /* Avoid accessing un-allocated queues */ - ring = (i < adapter->num_active_queues ? - &adapter->tx_rings[i] : NULL); - i40evf_add_queue_stats(&data, ring); - - /* Avoid accessing un-allocated queues */ - ring = (i < adapter->num_active_queues ? - &adapter->rx_rings[i] : NULL); - i40evf_add_queue_stats(&data, ring); - } - rcu_read_unlock(); -} - -/** - * i40evf_get_priv_flag_strings - Get private flag strings - * @netdev: network interface device structure - * @data: buffer for string data - * - * Builds the private flags string table - **/ -static void i40evf_get_priv_flag_strings(struct net_device *netdev, u8 *data) -{ - unsigned int i; - - for (i = 0; i < I40EVF_PRIV_FLAGS_STR_LEN; i++) { - snprintf(data, ETH_GSTRING_LEN, "%s", - i40evf_gstrings_priv_flags[i].flag_string); - data += ETH_GSTRING_LEN; - } -} - -/** - * i40evf_get_stat_strings - Get stat strings - * @netdev: network interface device structure - * @data: buffer for string data - * - * Builds the statistics string table - **/ -static void i40evf_get_stat_strings(struct net_device *netdev, u8 *data) -{ - unsigned int i; - - i40e_add_stat_strings(&data, i40evf_gstrings_stats); - - /* Queues are always allocated in pairs, so we just use num_tx_queues - * for both Tx and Rx queues. - */ - for (i = 0; i < netdev->num_tx_queues; i++) { - i40e_add_stat_strings(&data, i40e_gstrings_queue_stats, - "tx", i); - i40e_add_stat_strings(&data, i40e_gstrings_queue_stats, - "rx", i); - } -} - -/** - * i40evf_get_strings - Get string set - * @netdev: network interface device structure - * @sset: id of string set - * @data: buffer for string data - * - * Builds string tables for various string sets - **/ -static void i40evf_get_strings(struct net_device *netdev, u32 sset, u8 *data) -{ - switch (sset) { - case ETH_SS_STATS: - i40evf_get_stat_strings(netdev, data); - break; - case ETH_SS_PRIV_FLAGS: - i40evf_get_priv_flag_strings(netdev, data); - break; - default: - break; - } -} - -/** - * i40evf_get_priv_flags - report device private flags - * @netdev: network interface device structure - * - * The get string set count and the string set should be matched for each - * flag returned. Add new strings for each flag to the i40e_gstrings_priv_flags - * array. - * - * Returns a u32 bitmap of flags. - **/ -static u32 i40evf_get_priv_flags(struct net_device *netdev) -{ - struct i40evf_adapter *adapter = netdev_priv(netdev); - u32 i, ret_flags = 0; - - for (i = 0; i < I40EVF_PRIV_FLAGS_STR_LEN; i++) { - const struct i40evf_priv_flags *priv_flags; - - priv_flags = &i40evf_gstrings_priv_flags[i]; - - if (priv_flags->flag & adapter->flags) - ret_flags |= BIT(i); - } - - return ret_flags; -} - -/** - * i40evf_set_priv_flags - set private flags - * @netdev: network interface device structure - * @flags: bit flags to be set - **/ -static int i40evf_set_priv_flags(struct net_device *netdev, u32 flags) -{ - struct i40evf_adapter *adapter = netdev_priv(netdev); - u32 orig_flags, new_flags, changed_flags; - u32 i; - - orig_flags = READ_ONCE(adapter->flags); - new_flags = orig_flags; - - for (i = 0; i < I40EVF_PRIV_FLAGS_STR_LEN; i++) { - const struct i40evf_priv_flags *priv_flags; - - priv_flags = &i40evf_gstrings_priv_flags[i]; - - if (flags & BIT(i)) - new_flags |= priv_flags->flag; - else - new_flags &= ~(priv_flags->flag); - - if (priv_flags->read_only && - ((orig_flags ^ new_flags) & ~BIT(i))) - return -EOPNOTSUPP; - } - - /* Before we finalize any flag changes, any checks which we need to - * perform to determine if the new flags will be supported should go - * here... - */ - - /* Compare and exchange the new flags into place. If we failed, that - * is if cmpxchg returns anything but the old value, this means - * something else must have modified the flags variable since we - * copied it. We'll just punt with an error and log something in the - * message buffer. - */ - if (cmpxchg(&adapter->flags, orig_flags, new_flags) != orig_flags) { - dev_warn(&adapter->pdev->dev, - "Unable to update adapter->flags as it was modified by another thread...\n"); - return -EAGAIN; - } - - changed_flags = orig_flags ^ new_flags; - - /* Process any additional changes needed as a result of flag changes. - * The changed_flags value reflects the list of bits that were changed - * in the code above. - */ - - /* issue a reset to force legacy-rx change to take effect */ - if (changed_flags & I40EVF_FLAG_LEGACY_RX) { - if (netif_running(netdev)) { - adapter->flags |= I40EVF_FLAG_RESET_NEEDED; - schedule_work(&adapter->reset_task); - } - } - - return 0; -} - -/** - * i40evf_get_msglevel - Get debug message level - * @netdev: network interface device structure - * - * Returns current debug message level. - **/ -static u32 i40evf_get_msglevel(struct net_device *netdev) -{ - struct i40evf_adapter *adapter = netdev_priv(netdev); - - return adapter->msg_enable; -} - -/** - * i40evf_set_msglevel - Set debug message level - * @netdev: network interface device structure - * @data: message level - * - * Set current debug message level. Higher values cause the driver to - * be noisier. - **/ -static void i40evf_set_msglevel(struct net_device *netdev, u32 data) -{ - struct i40evf_adapter *adapter = netdev_priv(netdev); - - if (I40E_DEBUG_USER & data) - adapter->hw.debug_mask = data; - adapter->msg_enable = data; -} - -/** - * i40evf_get_drvinfo - Get driver info - * @netdev: network interface device structure - * @drvinfo: ethool driver info structure - * - * Returns information about the driver and device for display to the user. - **/ -static void i40evf_get_drvinfo(struct net_device *netdev, - struct ethtool_drvinfo *drvinfo) -{ - struct i40evf_adapter *adapter = netdev_priv(netdev); - - strlcpy(drvinfo->driver, i40evf_driver_name, 32); - strlcpy(drvinfo->version, i40evf_driver_version, 32); - strlcpy(drvinfo->fw_version, "N/A", 4); - strlcpy(drvinfo->bus_info, pci_name(adapter->pdev), 32); - drvinfo->n_priv_flags = I40EVF_PRIV_FLAGS_STR_LEN; -} - -/** - * i40evf_get_ringparam - Get ring parameters - * @netdev: network interface device structure - * @ring: ethtool ringparam structure - * - * Returns current ring parameters. TX and RX rings are reported separately, - * but the number of rings is not reported. - **/ -static void i40evf_get_ringparam(struct net_device *netdev, - struct ethtool_ringparam *ring) -{ - struct i40evf_adapter *adapter = netdev_priv(netdev); - - ring->rx_max_pending = I40EVF_MAX_RXD; - ring->tx_max_pending = I40EVF_MAX_TXD; - ring->rx_pending = adapter->rx_desc_count; - ring->tx_pending = adapter->tx_desc_count; -} - -/** - * i40evf_set_ringparam - Set ring parameters - * @netdev: network interface device structure - * @ring: ethtool ringparam structure - * - * Sets ring parameters. TX and RX rings are controlled separately, but the - * number of rings is not specified, so all rings get the same settings. - **/ -static int i40evf_set_ringparam(struct net_device *netdev, - struct ethtool_ringparam *ring) -{ - struct i40evf_adapter *adapter = netdev_priv(netdev); - u32 new_rx_count, new_tx_count; - - if ((ring->rx_mini_pending) || (ring->rx_jumbo_pending)) - return -EINVAL; - - new_tx_count = clamp_t(u32, ring->tx_pending, - I40EVF_MIN_TXD, - I40EVF_MAX_TXD); - new_tx_count = ALIGN(new_tx_count, I40EVF_REQ_DESCRIPTOR_MULTIPLE); - - new_rx_count = clamp_t(u32, ring->rx_pending, - I40EVF_MIN_RXD, - I40EVF_MAX_RXD); - new_rx_count = ALIGN(new_rx_count, I40EVF_REQ_DESCRIPTOR_MULTIPLE); - - /* if nothing to do return success */ - if ((new_tx_count == adapter->tx_desc_count) && - (new_rx_count == adapter->rx_desc_count)) - return 0; - - adapter->tx_desc_count = new_tx_count; - adapter->rx_desc_count = new_rx_count; - - if (netif_running(netdev)) { - adapter->flags |= I40EVF_FLAG_RESET_NEEDED; - schedule_work(&adapter->reset_task); - } - - return 0; -} - -/** - * __i40evf_get_coalesce - get per-queue coalesce settings - * @netdev: the netdev to check - * @ec: ethtool coalesce data structure - * @queue: which queue to pick - * - * Gets the per-queue settings for coalescence. Specifically Rx and Tx usecs - * are per queue. If queue is <0 then we default to queue 0 as the - * representative value. - **/ -static int __i40evf_get_coalesce(struct net_device *netdev, - struct ethtool_coalesce *ec, - int queue) -{ - struct i40evf_adapter *adapter = netdev_priv(netdev); - struct i40e_vsi *vsi = &adapter->vsi; - struct i40e_ring *rx_ring, *tx_ring; - - ec->tx_max_coalesced_frames = vsi->work_limit; - ec->rx_max_coalesced_frames = vsi->work_limit; - - /* Rx and Tx usecs per queue value. If user doesn't specify the - * queue, return queue 0's value to represent. - */ - if (queue < 0) - queue = 0; - else if (queue >= adapter->num_active_queues) - return -EINVAL; - - rx_ring = &adapter->rx_rings[queue]; - tx_ring = &adapter->tx_rings[queue]; - - if (ITR_IS_DYNAMIC(rx_ring->itr_setting)) - ec->use_adaptive_rx_coalesce = 1; - - if (ITR_IS_DYNAMIC(tx_ring->itr_setting)) - ec->use_adaptive_tx_coalesce = 1; - - ec->rx_coalesce_usecs = rx_ring->itr_setting & ~I40E_ITR_DYNAMIC; - ec->tx_coalesce_usecs = tx_ring->itr_setting & ~I40E_ITR_DYNAMIC; - - return 0; -} - -/** - * i40evf_get_coalesce - Get interrupt coalescing settings - * @netdev: network interface device structure - * @ec: ethtool coalesce structure - * - * Returns current coalescing settings. This is referred to elsewhere in the - * driver as Interrupt Throttle Rate, as this is how the hardware describes - * this functionality. Note that if per-queue settings have been modified this - * only represents the settings of queue 0. - **/ -static int i40evf_get_coalesce(struct net_device *netdev, - struct ethtool_coalesce *ec) -{ - return __i40evf_get_coalesce(netdev, ec, -1); -} - -/** - * i40evf_get_per_queue_coalesce - get coalesce values for specific queue - * @netdev: netdev to read - * @ec: coalesce settings from ethtool - * @queue: the queue to read - * - * Read specific queue's coalesce settings. - **/ -static int i40evf_get_per_queue_coalesce(struct net_device *netdev, - u32 queue, - struct ethtool_coalesce *ec) -{ - return __i40evf_get_coalesce(netdev, ec, queue); -} - -/** - * i40evf_set_itr_per_queue - set ITR values for specific queue - * @adapter: the VF adapter struct to set values for - * @ec: coalesce settings from ethtool - * @queue: the queue to modify - * - * Change the ITR settings for a specific queue. - **/ -static void i40evf_set_itr_per_queue(struct i40evf_adapter *adapter, - struct ethtool_coalesce *ec, - int queue) -{ - struct i40e_ring *rx_ring = &adapter->rx_rings[queue]; - struct i40e_ring *tx_ring = &adapter->tx_rings[queue]; - struct i40e_q_vector *q_vector; - - rx_ring->itr_setting = ITR_REG_ALIGN(ec->rx_coalesce_usecs); - tx_ring->itr_setting = ITR_REG_ALIGN(ec->tx_coalesce_usecs); - - rx_ring->itr_setting |= I40E_ITR_DYNAMIC; - if (!ec->use_adaptive_rx_coalesce) - rx_ring->itr_setting ^= I40E_ITR_DYNAMIC; - - tx_ring->itr_setting |= I40E_ITR_DYNAMIC; - if (!ec->use_adaptive_tx_coalesce) - tx_ring->itr_setting ^= I40E_ITR_DYNAMIC; - - q_vector = rx_ring->q_vector; - q_vector->rx.target_itr = ITR_TO_REG(rx_ring->itr_setting); - - q_vector = tx_ring->q_vector; - q_vector->tx.target_itr = ITR_TO_REG(tx_ring->itr_setting); - - /* The interrupt handler itself will take care of programming - * the Tx and Rx ITR values based on the values we have entered - * into the q_vector, no need to write the values now. - */ -} - -/** - * __i40evf_set_coalesce - set coalesce settings for particular queue - * @netdev: the netdev to change - * @ec: ethtool coalesce settings - * @queue: the queue to change - * - * Sets the coalesce settings for a particular queue. - **/ -static int __i40evf_set_coalesce(struct net_device *netdev, - struct ethtool_coalesce *ec, - int queue) -{ - struct i40evf_adapter *adapter = netdev_priv(netdev); - struct i40e_vsi *vsi = &adapter->vsi; - int i; - - if (ec->tx_max_coalesced_frames_irq || ec->rx_max_coalesced_frames_irq) - vsi->work_limit = ec->tx_max_coalesced_frames_irq; - - if (ec->rx_coalesce_usecs == 0) { - if (ec->use_adaptive_rx_coalesce) - netif_info(adapter, drv, netdev, "rx-usecs=0, need to disable adaptive-rx for a complete disable\n"); - } else if ((ec->rx_coalesce_usecs < I40E_MIN_ITR) || - (ec->rx_coalesce_usecs > I40E_MAX_ITR)) { - netif_info(adapter, drv, netdev, "Invalid value, rx-usecs range is 0-8160\n"); - return -EINVAL; - } - - else - if (ec->tx_coalesce_usecs == 0) { - if (ec->use_adaptive_tx_coalesce) - netif_info(adapter, drv, netdev, "tx-usecs=0, need to disable adaptive-tx for a complete disable\n"); - } else if ((ec->tx_coalesce_usecs < I40E_MIN_ITR) || - (ec->tx_coalesce_usecs > I40E_MAX_ITR)) { - netif_info(adapter, drv, netdev, "Invalid value, tx-usecs range is 0-8160\n"); - return -EINVAL; - } - - /* Rx and Tx usecs has per queue value. If user doesn't specify the - * queue, apply to all queues. - */ - if (queue < 0) { - for (i = 0; i < adapter->num_active_queues; i++) - i40evf_set_itr_per_queue(adapter, ec, i); - } else if (queue < adapter->num_active_queues) { - i40evf_set_itr_per_queue(adapter, ec, queue); - } else { - netif_info(adapter, drv, netdev, "Invalid queue value, queue range is 0 - %d\n", - adapter->num_active_queues - 1); - return -EINVAL; - } - - return 0; -} - -/** - * i40evf_set_coalesce - Set interrupt coalescing settings - * @netdev: network interface device structure - * @ec: ethtool coalesce structure - * - * Change current coalescing settings for every queue. - **/ -static int i40evf_set_coalesce(struct net_device *netdev, - struct ethtool_coalesce *ec) -{ - return __i40evf_set_coalesce(netdev, ec, -1); -} - -/** - * i40evf_set_per_queue_coalesce - set specific queue's coalesce settings - * @netdev: the netdev to change - * @ec: ethtool's coalesce settings - * @queue: the queue to modify - * - * Modifies a specific queue's coalesce settings. - */ -static int i40evf_set_per_queue_coalesce(struct net_device *netdev, - u32 queue, - struct ethtool_coalesce *ec) -{ - return __i40evf_set_coalesce(netdev, ec, queue); -} - -/** - * i40evf_get_rxnfc - command to get RX flow classification rules - * @netdev: network interface device structure - * @cmd: ethtool rxnfc command - * @rule_locs: pointer to store rule locations - * - * Returns Success if the command is supported. - **/ -static int i40evf_get_rxnfc(struct net_device *netdev, - struct ethtool_rxnfc *cmd, - u32 *rule_locs) -{ - struct i40evf_adapter *adapter = netdev_priv(netdev); - int ret = -EOPNOTSUPP; - - switch (cmd->cmd) { - case ETHTOOL_GRXRINGS: - cmd->data = adapter->num_active_queues; - ret = 0; - break; - case ETHTOOL_GRXFH: - netdev_info(netdev, - "RSS hash info is not available to vf, use pf.\n"); - break; - default: - break; - } - - return ret; -} -/** - * i40evf_get_channels: get the number of channels supported by the device - * @netdev: network interface device structure - * @ch: channel information structure - * - * For the purposes of our device, we only use combined channels, i.e. a tx/rx - * queue pair. Report one extra channel to match our "other" MSI-X vector. - **/ -static void i40evf_get_channels(struct net_device *netdev, - struct ethtool_channels *ch) -{ - struct i40evf_adapter *adapter = netdev_priv(netdev); - - /* Report maximum channels */ - ch->max_combined = I40EVF_MAX_REQ_QUEUES; - - ch->max_other = NONQ_VECS; - ch->other_count = NONQ_VECS; - - ch->combined_count = adapter->num_active_queues; -} - -/** - * i40evf_set_channels: set the new channel count - * @netdev: network interface device structure - * @ch: channel information structure - * - * Negotiate a new number of channels with the PF then do a reset. During - * reset we'll realloc queues and fix the RSS table. Returns 0 on success, - * negative on failure. - **/ -static int i40evf_set_channels(struct net_device *netdev, - struct ethtool_channels *ch) -{ - struct i40evf_adapter *adapter = netdev_priv(netdev); - int num_req = ch->combined_count; - - if (num_req != adapter->num_active_queues && - !(adapter->vf_res->vf_cap_flags & - VIRTCHNL_VF_OFFLOAD_REQ_QUEUES)) { - dev_info(&adapter->pdev->dev, "PF is not capable of queue negotiation.\n"); - return -EINVAL; - } - - if ((adapter->vf_res->vf_cap_flags & VIRTCHNL_VF_OFFLOAD_ADQ) && - adapter->num_tc) { - dev_info(&adapter->pdev->dev, "Cannot set channels since ADq is enabled.\n"); - return -EINVAL; - } - - /* All of these should have already been checked by ethtool before this - * even gets to us, but just to be sure. - */ - if (num_req <= 0 || num_req > I40EVF_MAX_REQ_QUEUES) - return -EINVAL; - - if (ch->rx_count || ch->tx_count || ch->other_count != NONQ_VECS) - return -EINVAL; - - adapter->num_req_queues = num_req; - return i40evf_request_queues(adapter, num_req); -} - -/** - * i40evf_get_rxfh_key_size - get the RSS hash key size - * @netdev: network interface device structure - * - * Returns the table size. - **/ -static u32 i40evf_get_rxfh_key_size(struct net_device *netdev) -{ - struct i40evf_adapter *adapter = netdev_priv(netdev); - - return adapter->rss_key_size; -} - -/** - * i40evf_get_rxfh_indir_size - get the rx flow hash indirection table size - * @netdev: network interface device structure - * - * Returns the table size. - **/ -static u32 i40evf_get_rxfh_indir_size(struct net_device *netdev) -{ - struct i40evf_adapter *adapter = netdev_priv(netdev); - - return adapter->rss_lut_size; -} - -/** - * i40evf_get_rxfh - get the rx flow hash indirection table - * @netdev: network interface device structure - * @indir: indirection table - * @key: hash key - * @hfunc: hash function in use - * - * Reads the indirection table directly from the hardware. Always returns 0. - **/ -static int i40evf_get_rxfh(struct net_device *netdev, u32 *indir, u8 *key, - u8 *hfunc) -{ - struct i40evf_adapter *adapter = netdev_priv(netdev); - u16 i; - - if (hfunc) - *hfunc = ETH_RSS_HASH_TOP; - if (!indir) - return 0; - - memcpy(key, adapter->rss_key, adapter->rss_key_size); - - /* Each 32 bits pointed by 'indir' is stored with a lut entry */ - for (i = 0; i < adapter->rss_lut_size; i++) - indir[i] = (u32)adapter->rss_lut[i]; - - return 0; -} - -/** - * i40evf_set_rxfh - set the rx flow hash indirection table - * @netdev: network interface device structure - * @indir: indirection table - * @key: hash key - * @hfunc: hash function to use - * - * Returns -EINVAL if the table specifies an inavlid queue id, otherwise - * returns 0 after programming the table. - **/ -static int i40evf_set_rxfh(struct net_device *netdev, const u32 *indir, - const u8 *key, const u8 hfunc) -{ - struct i40evf_adapter *adapter = netdev_priv(netdev); - u16 i; - - /* We do not allow change in unsupported parameters */ - if (key || - (hfunc != ETH_RSS_HASH_NO_CHANGE && hfunc != ETH_RSS_HASH_TOP)) - return -EOPNOTSUPP; - if (!indir) - return 0; - - if (key) { - memcpy(adapter->rss_key, key, adapter->rss_key_size); - } - - /* Each 32 bits pointed by 'indir' is stored with a lut entry */ - for (i = 0; i < adapter->rss_lut_size; i++) - adapter->rss_lut[i] = (u8)(indir[i]); - - return i40evf_config_rss(adapter); -} - -static const struct ethtool_ops i40evf_ethtool_ops = { - .get_drvinfo = i40evf_get_drvinfo, - .get_link = ethtool_op_get_link, - .get_ringparam = i40evf_get_ringparam, - .set_ringparam = i40evf_set_ringparam, - .get_strings = i40evf_get_strings, - .get_ethtool_stats = i40evf_get_ethtool_stats, - .get_sset_count = i40evf_get_sset_count, - .get_priv_flags = i40evf_get_priv_flags, - .set_priv_flags = i40evf_set_priv_flags, - .get_msglevel = i40evf_get_msglevel, - .set_msglevel = i40evf_set_msglevel, - .get_coalesce = i40evf_get_coalesce, - .set_coalesce = i40evf_set_coalesce, - .get_per_queue_coalesce = i40evf_get_per_queue_coalesce, - .set_per_queue_coalesce = i40evf_set_per_queue_coalesce, - .get_rxnfc = i40evf_get_rxnfc, - .get_rxfh_indir_size = i40evf_get_rxfh_indir_size, - .get_rxfh = i40evf_get_rxfh, - .set_rxfh = i40evf_set_rxfh, - .get_channels = i40evf_get_channels, - .set_channels = i40evf_set_channels, - .get_rxfh_key_size = i40evf_get_rxfh_key_size, - .get_link_ksettings = i40evf_get_link_ksettings, -}; - -/** - * i40evf_set_ethtool_ops - Initialize ethtool ops struct - * @netdev: network interface device structure - * - * Sets ethtool ops struct in our netdev so that ethtool can call - * our functions. - **/ -void i40evf_set_ethtool_ops(struct net_device *netdev) -{ - netdev->ethtool_ops = &i40evf_ethtool_ops; -} diff --git a/drivers/net/ethernet/intel/iavf/Makefile b/drivers/net/ethernet/intel/iavf/Makefile new file mode 100644 index 000000000000..9cbb5743ed12 --- /dev/null +++ b/drivers/net/ethernet/intel/iavf/Makefile @@ -0,0 +1,15 @@ +# SPDX-License-Identifier: GPL-2.0 +# Copyright(c) 2013 - 2018 Intel Corporation. +# +# Makefile for the Intel(R) Ethernet Adaptive Virtual Function (iavf) +# driver +# +# + +ccflags-y += -I$(src) +subdir-ccflags-y += -I$(src) + +obj-$(CONFIG_IAVF) += iavf.o + +iavf-objs := iavf_main.o iavf_ethtool.o iavf_virtchnl.o \ + iavf_txrx.o iavf_common.o i40e_adminq.o iavf_client.o diff --git a/drivers/net/ethernet/intel/i40evf/i40e_adminq.c b/drivers/net/ethernet/intel/iavf/i40e_adminq.c index 21a0dbf6ccf6..fca1ecfd9f71 100644 --- a/drivers/net/ethernet/intel/i40evf/i40e_adminq.c +++ b/drivers/net/ethernet/intel/iavf/i40e_adminq.c @@ -1,21 +1,11 @@ // SPDX-License-Identifier: GPL-2.0 /* Copyright(c) 2013 - 2018 Intel Corporation. */ -#include "i40e_status.h" -#include "i40e_type.h" -#include "i40e_register.h" +#include "iavf_status.h" +#include "iavf_type.h" +#include "iavf_register.h" #include "i40e_adminq.h" -#include "i40e_prototype.h" - -/** - * i40e_is_nvm_update_op - return true if this is an NVM update operation - * @desc: API request descriptor - **/ -static inline bool i40e_is_nvm_update_op(struct i40e_aq_desc *desc) -{ - return (desc->opcode == i40e_aqc_opc_nvm_erase) || - (desc->opcode == i40e_aqc_opc_nvm_update); -} +#include "iavf_prototype.h" /** * i40e_adminq_init_regs - Initialize AdminQ registers @@ -23,44 +13,42 @@ static inline bool i40e_is_nvm_update_op(struct i40e_aq_desc *desc) * * This assumes the alloc_asq and alloc_arq functions have already been called **/ -static void i40e_adminq_init_regs(struct i40e_hw *hw) +static void i40e_adminq_init_regs(struct iavf_hw *hw) { /* set head and tail registers in our local struct */ - if (i40e_is_vf(hw)) { - hw->aq.asq.tail = I40E_VF_ATQT1; - hw->aq.asq.head = I40E_VF_ATQH1; - hw->aq.asq.len = I40E_VF_ATQLEN1; - hw->aq.asq.bal = I40E_VF_ATQBAL1; - hw->aq.asq.bah = I40E_VF_ATQBAH1; - hw->aq.arq.tail = I40E_VF_ARQT1; - hw->aq.arq.head = I40E_VF_ARQH1; - hw->aq.arq.len = I40E_VF_ARQLEN1; - hw->aq.arq.bal = I40E_VF_ARQBAL1; - hw->aq.arq.bah = I40E_VF_ARQBAH1; - } + hw->aq.asq.tail = IAVF_VF_ATQT1; + hw->aq.asq.head = IAVF_VF_ATQH1; + hw->aq.asq.len = IAVF_VF_ATQLEN1; + hw->aq.asq.bal = IAVF_VF_ATQBAL1; + hw->aq.asq.bah = IAVF_VF_ATQBAH1; + hw->aq.arq.tail = IAVF_VF_ARQT1; + hw->aq.arq.head = IAVF_VF_ARQH1; + hw->aq.arq.len = IAVF_VF_ARQLEN1; + hw->aq.arq.bal = IAVF_VF_ARQBAL1; + hw->aq.arq.bah = IAVF_VF_ARQBAH1; } /** * i40e_alloc_adminq_asq_ring - Allocate Admin Queue send rings * @hw: pointer to the hardware structure **/ -static i40e_status i40e_alloc_adminq_asq_ring(struct i40e_hw *hw) +static iavf_status i40e_alloc_adminq_asq_ring(struct iavf_hw *hw) { - i40e_status ret_code; + iavf_status ret_code; - ret_code = i40e_allocate_dma_mem(hw, &hw->aq.asq.desc_buf, + ret_code = iavf_allocate_dma_mem(hw, &hw->aq.asq.desc_buf, i40e_mem_atq_ring, (hw->aq.num_asq_entries * sizeof(struct i40e_aq_desc)), - I40E_ADMINQ_DESC_ALIGNMENT); + IAVF_ADMINQ_DESC_ALIGNMENT); if (ret_code) return ret_code; - ret_code = i40e_allocate_virt_mem(hw, &hw->aq.asq.cmd_buf, + ret_code = iavf_allocate_virt_mem(hw, &hw->aq.asq.cmd_buf, (hw->aq.num_asq_entries * sizeof(struct i40e_asq_cmd_details))); if (ret_code) { - i40e_free_dma_mem(hw, &hw->aq.asq.desc_buf); + iavf_free_dma_mem(hw, &hw->aq.asq.desc_buf); return ret_code; } @@ -71,15 +59,15 @@ static i40e_status i40e_alloc_adminq_asq_ring(struct i40e_hw *hw) * i40e_alloc_adminq_arq_ring - Allocate Admin Queue receive rings * @hw: pointer to the hardware structure **/ -static i40e_status i40e_alloc_adminq_arq_ring(struct i40e_hw *hw) +static iavf_status i40e_alloc_adminq_arq_ring(struct iavf_hw *hw) { - i40e_status ret_code; + iavf_status ret_code; - ret_code = i40e_allocate_dma_mem(hw, &hw->aq.arq.desc_buf, + ret_code = iavf_allocate_dma_mem(hw, &hw->aq.arq.desc_buf, i40e_mem_arq_ring, (hw->aq.num_arq_entries * sizeof(struct i40e_aq_desc)), - I40E_ADMINQ_DESC_ALIGNMENT); + IAVF_ADMINQ_DESC_ALIGNMENT); return ret_code; } @@ -91,9 +79,9 @@ static i40e_status i40e_alloc_adminq_arq_ring(struct i40e_hw *hw) * This assumes the posted send buffers have already been cleaned * and de-allocated **/ -static void i40e_free_adminq_asq(struct i40e_hw *hw) +static void i40e_free_adminq_asq(struct iavf_hw *hw) { - i40e_free_dma_mem(hw, &hw->aq.asq.desc_buf); + iavf_free_dma_mem(hw, &hw->aq.asq.desc_buf); } /** @@ -103,20 +91,20 @@ static void i40e_free_adminq_asq(struct i40e_hw *hw) * This assumes the posted receive buffers have already been cleaned * and de-allocated **/ -static void i40e_free_adminq_arq(struct i40e_hw *hw) +static void i40e_free_adminq_arq(struct iavf_hw *hw) { - i40e_free_dma_mem(hw, &hw->aq.arq.desc_buf); + iavf_free_dma_mem(hw, &hw->aq.arq.desc_buf); } /** * i40e_alloc_arq_bufs - Allocate pre-posted buffers for the receive queue * @hw: pointer to the hardware structure **/ -static i40e_status i40e_alloc_arq_bufs(struct i40e_hw *hw) +static iavf_status i40e_alloc_arq_bufs(struct iavf_hw *hw) { - i40e_status ret_code; struct i40e_aq_desc *desc; - struct i40e_dma_mem *bi; + struct iavf_dma_mem *bi; + iavf_status ret_code; int i; /* We'll be allocating the buffer info memory first, then we can @@ -124,24 +112,25 @@ static i40e_status i40e_alloc_arq_bufs(struct i40e_hw *hw) */ /* buffer_info structures do not need alignment */ - ret_code = i40e_allocate_virt_mem(hw, &hw->aq.arq.dma_head, - (hw->aq.num_arq_entries * sizeof(struct i40e_dma_mem))); + ret_code = iavf_allocate_virt_mem(hw, &hw->aq.arq.dma_head, + (hw->aq.num_arq_entries * + sizeof(struct iavf_dma_mem))); if (ret_code) goto alloc_arq_bufs; - hw->aq.arq.r.arq_bi = (struct i40e_dma_mem *)hw->aq.arq.dma_head.va; + hw->aq.arq.r.arq_bi = (struct iavf_dma_mem *)hw->aq.arq.dma_head.va; /* allocate the mapped buffers */ for (i = 0; i < hw->aq.num_arq_entries; i++) { bi = &hw->aq.arq.r.arq_bi[i]; - ret_code = i40e_allocate_dma_mem(hw, bi, + ret_code = iavf_allocate_dma_mem(hw, bi, i40e_mem_arq_buf, hw->aq.arq_buf_size, - I40E_ADMINQ_DESC_ALIGNMENT); + IAVF_ADMINQ_DESC_ALIGNMENT); if (ret_code) goto unwind_alloc_arq_bufs; /* now configure the descriptors for use */ - desc = I40E_ADMINQ_DESC(hw->aq.arq, i); + desc = IAVF_ADMINQ_DESC(hw->aq.arq, i); desc->flags = cpu_to_le16(I40E_AQ_FLAG_BUF); if (hw->aq.arq_buf_size > I40E_AQ_LARGE_BUF) @@ -169,8 +158,8 @@ unwind_alloc_arq_bufs: /* don't try to free the one that failed... */ i--; for (; i >= 0; i--) - i40e_free_dma_mem(hw, &hw->aq.arq.r.arq_bi[i]); - i40e_free_virt_mem(hw, &hw->aq.arq.dma_head); + iavf_free_dma_mem(hw, &hw->aq.arq.r.arq_bi[i]); + iavf_free_virt_mem(hw, &hw->aq.arq.dma_head); return ret_code; } @@ -179,26 +168,27 @@ unwind_alloc_arq_bufs: * i40e_alloc_asq_bufs - Allocate empty buffer structs for the send queue * @hw: pointer to the hardware structure **/ -static i40e_status i40e_alloc_asq_bufs(struct i40e_hw *hw) +static iavf_status i40e_alloc_asq_bufs(struct iavf_hw *hw) { - i40e_status ret_code; - struct i40e_dma_mem *bi; + struct iavf_dma_mem *bi; + iavf_status ret_code; int i; /* No mapped memory needed yet, just the buffer info structures */ - ret_code = i40e_allocate_virt_mem(hw, &hw->aq.asq.dma_head, - (hw->aq.num_asq_entries * sizeof(struct i40e_dma_mem))); + ret_code = iavf_allocate_virt_mem(hw, &hw->aq.asq.dma_head, + (hw->aq.num_asq_entries * + sizeof(struct iavf_dma_mem))); if (ret_code) goto alloc_asq_bufs; - hw->aq.asq.r.asq_bi = (struct i40e_dma_mem *)hw->aq.asq.dma_head.va; + hw->aq.asq.r.asq_bi = (struct iavf_dma_mem *)hw->aq.asq.dma_head.va; /* allocate the mapped buffers */ for (i = 0; i < hw->aq.num_asq_entries; i++) { bi = &hw->aq.asq.r.asq_bi[i]; - ret_code = i40e_allocate_dma_mem(hw, bi, + ret_code = iavf_allocate_dma_mem(hw, bi, i40e_mem_asq_buf, hw->aq.asq_buf_size, - I40E_ADMINQ_DESC_ALIGNMENT); + IAVF_ADMINQ_DESC_ALIGNMENT); if (ret_code) goto unwind_alloc_asq_bufs; } @@ -209,8 +199,8 @@ unwind_alloc_asq_bufs: /* don't try to free the one that failed... */ i--; for (; i >= 0; i--) - i40e_free_dma_mem(hw, &hw->aq.asq.r.asq_bi[i]); - i40e_free_virt_mem(hw, &hw->aq.asq.dma_head); + iavf_free_dma_mem(hw, &hw->aq.asq.r.asq_bi[i]); + iavf_free_virt_mem(hw, &hw->aq.asq.dma_head); return ret_code; } @@ -219,42 +209,42 @@ unwind_alloc_asq_bufs: * i40e_free_arq_bufs - Free receive queue buffer info elements * @hw: pointer to the hardware structure **/ -static void i40e_free_arq_bufs(struct i40e_hw *hw) +static void i40e_free_arq_bufs(struct iavf_hw *hw) { int i; /* free descriptors */ for (i = 0; i < hw->aq.num_arq_entries; i++) - i40e_free_dma_mem(hw, &hw->aq.arq.r.arq_bi[i]); + iavf_free_dma_mem(hw, &hw->aq.arq.r.arq_bi[i]); /* free the descriptor memory */ - i40e_free_dma_mem(hw, &hw->aq.arq.desc_buf); + iavf_free_dma_mem(hw, &hw->aq.arq.desc_buf); /* free the dma header */ - i40e_free_virt_mem(hw, &hw->aq.arq.dma_head); + iavf_free_virt_mem(hw, &hw->aq.arq.dma_head); } /** * i40e_free_asq_bufs - Free send queue buffer info elements * @hw: pointer to the hardware structure **/ -static void i40e_free_asq_bufs(struct i40e_hw *hw) +static void i40e_free_asq_bufs(struct iavf_hw *hw) { int i; /* only unmap if the address is non-NULL */ for (i = 0; i < hw->aq.num_asq_entries; i++) if (hw->aq.asq.r.asq_bi[i].pa) - i40e_free_dma_mem(hw, &hw->aq.asq.r.asq_bi[i]); + iavf_free_dma_mem(hw, &hw->aq.asq.r.asq_bi[i]); /* free the buffer info list */ - i40e_free_virt_mem(hw, &hw->aq.asq.cmd_buf); + iavf_free_virt_mem(hw, &hw->aq.asq.cmd_buf); /* free the descriptor memory */ - i40e_free_dma_mem(hw, &hw->aq.asq.desc_buf); + iavf_free_dma_mem(hw, &hw->aq.asq.desc_buf); /* free the dma header */ - i40e_free_virt_mem(hw, &hw->aq.asq.dma_head); + iavf_free_virt_mem(hw, &hw->aq.asq.dma_head); } /** @@ -263,9 +253,9 @@ static void i40e_free_asq_bufs(struct i40e_hw *hw) * * Configure base address and length registers for the transmit queue **/ -static i40e_status i40e_config_asq_regs(struct i40e_hw *hw) +static iavf_status i40e_config_asq_regs(struct iavf_hw *hw) { - i40e_status ret_code = 0; + iavf_status ret_code = 0; u32 reg = 0; /* Clear Head and Tail */ @@ -274,7 +264,7 @@ static i40e_status i40e_config_asq_regs(struct i40e_hw *hw) /* set starting point */ wr32(hw, hw->aq.asq.len, (hw->aq.num_asq_entries | - I40E_VF_ATQLEN1_ATQENABLE_MASK)); + IAVF_VF_ATQLEN1_ATQENABLE_MASK)); wr32(hw, hw->aq.asq.bal, lower_32_bits(hw->aq.asq.desc_buf.pa)); wr32(hw, hw->aq.asq.bah, upper_32_bits(hw->aq.asq.desc_buf.pa)); @@ -292,9 +282,9 @@ static i40e_status i40e_config_asq_regs(struct i40e_hw *hw) * * Configure base address and length registers for the receive (event queue) **/ -static i40e_status i40e_config_arq_regs(struct i40e_hw *hw) +static iavf_status i40e_config_arq_regs(struct iavf_hw *hw) { - i40e_status ret_code = 0; + iavf_status ret_code = 0; u32 reg = 0; /* Clear Head and Tail */ @@ -303,7 +293,7 @@ static i40e_status i40e_config_arq_regs(struct i40e_hw *hw) /* set starting point */ wr32(hw, hw->aq.arq.len, (hw->aq.num_arq_entries | - I40E_VF_ARQLEN1_ARQENABLE_MASK)); + IAVF_VF_ARQLEN1_ARQENABLE_MASK)); wr32(hw, hw->aq.arq.bal, lower_32_bits(hw->aq.arq.desc_buf.pa)); wr32(hw, hw->aq.arq.bah, upper_32_bits(hw->aq.arq.desc_buf.pa)); @@ -331,9 +321,9 @@ static i40e_status i40e_config_arq_regs(struct i40e_hw *hw) * Do *NOT* hold the lock when calling this as the memory allocation routines * called are not going to be atomic context safe **/ -static i40e_status i40e_init_asq(struct i40e_hw *hw) +static iavf_status i40e_init_asq(struct iavf_hw *hw) { - i40e_status ret_code = 0; + iavf_status ret_code = 0; if (hw->aq.asq.count > 0) { /* queue already initialized */ @@ -390,9 +380,9 @@ init_adminq_exit: * Do *NOT* hold the lock when calling this as the memory allocation routines * called are not going to be atomic context safe **/ -static i40e_status i40e_init_arq(struct i40e_hw *hw) +static iavf_status i40e_init_arq(struct iavf_hw *hw) { - i40e_status ret_code = 0; + iavf_status ret_code = 0; if (hw->aq.arq.count > 0) { /* queue already initialized */ @@ -442,9 +432,9 @@ init_adminq_exit: * * The main shutdown routine for the Admin Send Queue **/ -static i40e_status i40e_shutdown_asq(struct i40e_hw *hw) +static iavf_status i40e_shutdown_asq(struct iavf_hw *hw) { - i40e_status ret_code = 0; + iavf_status ret_code = 0; mutex_lock(&hw->aq.asq_mutex); @@ -476,9 +466,9 @@ shutdown_asq_out: * * The main shutdown routine for the Admin Receive Queue **/ -static i40e_status i40e_shutdown_arq(struct i40e_hw *hw) +static iavf_status i40e_shutdown_arq(struct iavf_hw *hw) { - i40e_status ret_code = 0; + iavf_status ret_code = 0; mutex_lock(&hw->aq.arq_mutex); @@ -505,7 +495,7 @@ shutdown_arq_out: } /** - * i40evf_init_adminq - main initialization routine for Admin Queue + * iavf_init_adminq - main initialization routine for Admin Queue * @hw: pointer to the hardware structure * * Prior to calling this function, drivers *MUST* set the following fields @@ -515,9 +505,9 @@ shutdown_arq_out: * - hw->aq.arq_buf_size * - hw->aq.asq_buf_size **/ -i40e_status i40evf_init_adminq(struct i40e_hw *hw) +iavf_status iavf_init_adminq(struct iavf_hw *hw) { - i40e_status ret_code; + iavf_status ret_code; /* verify input for valid configuration */ if ((hw->aq.num_arq_entries == 0) || @@ -556,22 +546,19 @@ init_adminq_exit: } /** - * i40evf_shutdown_adminq - shutdown routine for the Admin Queue + * iavf_shutdown_adminq - shutdown routine for the Admin Queue * @hw: pointer to the hardware structure **/ -i40e_status i40evf_shutdown_adminq(struct i40e_hw *hw) +iavf_status iavf_shutdown_adminq(struct iavf_hw *hw) { - i40e_status ret_code = 0; + iavf_status ret_code = 0; - if (i40evf_check_asq_alive(hw)) - i40evf_aq_queue_shutdown(hw, true); + if (iavf_check_asq_alive(hw)) + iavf_aq_queue_shutdown(hw, true); i40e_shutdown_asq(hw); i40e_shutdown_arq(hw); - if (hw->nvm_buff.va) - i40e_free_virt_mem(hw, &hw->nvm_buff); - return ret_code; } @@ -581,18 +568,18 @@ i40e_status i40evf_shutdown_adminq(struct i40e_hw *hw) * * returns the number of free desc **/ -static u16 i40e_clean_asq(struct i40e_hw *hw) +static u16 i40e_clean_asq(struct iavf_hw *hw) { - struct i40e_adminq_ring *asq = &(hw->aq.asq); + struct iavf_adminq_ring *asq = &hw->aq.asq; struct i40e_asq_cmd_details *details; u16 ntc = asq->next_to_clean; struct i40e_aq_desc desc_cb; struct i40e_aq_desc *desc; - desc = I40E_ADMINQ_DESC(*asq, ntc); + desc = IAVF_ADMINQ_DESC(*asq, ntc); details = I40E_ADMINQ_DETAILS(*asq, ntc); while (rd32(hw, hw->aq.asq.head) != ntc) { - i40e_debug(hw, I40E_DEBUG_AQ_MESSAGE, + iavf_debug(hw, IAVF_DEBUG_AQ_MESSAGE, "ntc %d head %d.\n", ntc, rd32(hw, hw->aq.asq.head)); if (details->callback) { @@ -607,33 +594,32 @@ static u16 i40e_clean_asq(struct i40e_hw *hw) ntc++; if (ntc == asq->count) ntc = 0; - desc = I40E_ADMINQ_DESC(*asq, ntc); + desc = IAVF_ADMINQ_DESC(*asq, ntc); details = I40E_ADMINQ_DETAILS(*asq, ntc); } asq->next_to_clean = ntc; - return I40E_DESC_UNUSED(asq); + return IAVF_DESC_UNUSED(asq); } /** - * i40evf_asq_done - check if FW has processed the Admin Send Queue + * iavf_asq_done - check if FW has processed the Admin Send Queue * @hw: pointer to the hw struct * * Returns true if the firmware has processed all descriptors on the * admin send queue. Returns false if there are still requests pending. **/ -bool i40evf_asq_done(struct i40e_hw *hw) +bool iavf_asq_done(struct iavf_hw *hw) { /* AQ designers suggest use of head for better * timing reliability than DD bit */ return rd32(hw, hw->aq.asq.head) == hw->aq.asq.next_to_use; - } /** - * i40evf_asq_send_command - send command to Admin Queue + * iavf_asq_send_command - send command to Admin Queue * @hw: pointer to the hw struct * @desc: prefilled descriptor describing the command (non DMA mem) * @buff: buffer to use for indirect commands @@ -643,24 +629,23 @@ bool i40evf_asq_done(struct i40e_hw *hw) * This is the main send command driver routine for the Admin Queue send * queue. It runs the queue, cleans the queue, etc **/ -i40e_status i40evf_asq_send_command(struct i40e_hw *hw, - struct i40e_aq_desc *desc, - void *buff, /* can be NULL */ - u16 buff_size, - struct i40e_asq_cmd_details *cmd_details) +iavf_status iavf_asq_send_command(struct iavf_hw *hw, struct i40e_aq_desc *desc, + void *buff, /* can be NULL */ + u16 buff_size, + struct i40e_asq_cmd_details *cmd_details) { - i40e_status status = 0; - struct i40e_dma_mem *dma_buff = NULL; + struct iavf_dma_mem *dma_buff = NULL; struct i40e_asq_cmd_details *details; struct i40e_aq_desc *desc_on_ring; bool cmd_completed = false; + iavf_status status = 0; u16 retval = 0; u32 val = 0; mutex_lock(&hw->aq.asq_mutex); if (hw->aq.asq.count == 0) { - i40e_debug(hw, I40E_DEBUG_AQ_MESSAGE, + iavf_debug(hw, IAVF_DEBUG_AQ_MESSAGE, "AQTX: Admin queue not initialized.\n"); status = I40E_ERR_QUEUE_EMPTY; goto asq_send_command_error; @@ -670,7 +655,7 @@ i40e_status i40evf_asq_send_command(struct i40e_hw *hw, val = rd32(hw, hw->aq.asq.head); if (val >= hw->aq.num_asq_entries) { - i40e_debug(hw, I40E_DEBUG_AQ_MESSAGE, + iavf_debug(hw, IAVF_DEBUG_AQ_MESSAGE, "AQTX: head overrun at %d\n", val); status = I40E_ERR_QUEUE_EMPTY; goto asq_send_command_error; @@ -699,8 +684,8 @@ i40e_status i40evf_asq_send_command(struct i40e_hw *hw, desc->flags |= cpu_to_le16(details->flags_ena); if (buff_size > hw->aq.asq_buf_size) { - i40e_debug(hw, - I40E_DEBUG_AQ_MESSAGE, + iavf_debug(hw, + IAVF_DEBUG_AQ_MESSAGE, "AQTX: Invalid buffer size: %d.\n", buff_size); status = I40E_ERR_INVALID_SIZE; @@ -708,8 +693,8 @@ i40e_status i40evf_asq_send_command(struct i40e_hw *hw, } if (details->postpone && !details->async) { - i40e_debug(hw, - I40E_DEBUG_AQ_MESSAGE, + iavf_debug(hw, + IAVF_DEBUG_AQ_MESSAGE, "AQTX: Async flag not set along with postpone flag"); status = I40E_ERR_PARAM; goto asq_send_command_error; @@ -723,22 +708,22 @@ i40e_status i40evf_asq_send_command(struct i40e_hw *hw, * in case of asynchronous completions */ if (i40e_clean_asq(hw) == 0) { - i40e_debug(hw, - I40E_DEBUG_AQ_MESSAGE, + iavf_debug(hw, + IAVF_DEBUG_AQ_MESSAGE, "AQTX: Error queue is full.\n"); status = I40E_ERR_ADMIN_QUEUE_FULL; goto asq_send_command_error; } /* initialize the temp desc pointer with the right desc */ - desc_on_ring = I40E_ADMINQ_DESC(hw->aq.asq, hw->aq.asq.next_to_use); + desc_on_ring = IAVF_ADMINQ_DESC(hw->aq.asq, hw->aq.asq.next_to_use); /* if the desc is available copy the temp desc to the right place */ *desc_on_ring = *desc; /* if buff is not NULL assume indirect command */ - if (buff != NULL) { - dma_buff = &(hw->aq.asq.r.asq_bi[hw->aq.asq.next_to_use]); + if (buff) { + dma_buff = &hw->aq.asq.r.asq_bi[hw->aq.asq.next_to_use]; /* copy the user buff into the respective DMA buff */ memcpy(dma_buff->va, buff, buff_size); desc_on_ring->datalen = cpu_to_le16(buff_size); @@ -753,9 +738,9 @@ i40e_status i40evf_asq_send_command(struct i40e_hw *hw, } /* bump the tail */ - i40e_debug(hw, I40E_DEBUG_AQ_MESSAGE, "AQTX: desc and buffer:\n"); - i40evf_debug_aq(hw, I40E_DEBUG_AQ_COMMAND, (void *)desc_on_ring, - buff, buff_size); + iavf_debug(hw, IAVF_DEBUG_AQ_MESSAGE, "AQTX: desc and buffer:\n"); + iavf_debug_aq(hw, IAVF_DEBUG_AQ_COMMAND, (void *)desc_on_ring, + buff, buff_size); (hw->aq.asq.next_to_use)++; if (hw->aq.asq.next_to_use == hw->aq.asq.count) hw->aq.asq.next_to_use = 0; @@ -772,7 +757,7 @@ i40e_status i40evf_asq_send_command(struct i40e_hw *hw, /* AQ designers suggest use of head for better * timing reliability than DD bit */ - if (i40evf_asq_done(hw)) + if (iavf_asq_done(hw)) break; udelay(50); total_delay += 50; @@ -780,14 +765,14 @@ i40e_status i40evf_asq_send_command(struct i40e_hw *hw, } /* if ready, copy the desc back to temp */ - if (i40evf_asq_done(hw)) { + if (iavf_asq_done(hw)) { *desc = *desc_on_ring; - if (buff != NULL) + if (buff) memcpy(buff, dma_buff->va, buff_size); retval = le16_to_cpu(desc->retval); if (retval != 0) { - i40e_debug(hw, - I40E_DEBUG_AQ_MESSAGE, + iavf_debug(hw, + IAVF_DEBUG_AQ_MESSAGE, "AQTX: Command completed with error 0x%X.\n", retval); @@ -804,10 +789,9 @@ i40e_status i40evf_asq_send_command(struct i40e_hw *hw, hw->aq.asq_last_status = (enum i40e_admin_queue_err)retval; } - i40e_debug(hw, I40E_DEBUG_AQ_MESSAGE, + iavf_debug(hw, IAVF_DEBUG_AQ_MESSAGE, "AQTX: desc and buffer writeback:\n"); - i40evf_debug_aq(hw, I40E_DEBUG_AQ_COMMAND, (void *)desc, buff, - buff_size); + iavf_debug_aq(hw, IAVF_DEBUG_AQ_COMMAND, (void *)desc, buff, buff_size); /* save writeback aq if requested */ if (details->wb_desc) @@ -816,12 +800,12 @@ i40e_status i40evf_asq_send_command(struct i40e_hw *hw, /* update the error if time out occurred */ if ((!cmd_completed) && (!details->async && !details->postpone)) { - if (rd32(hw, hw->aq.asq.len) & I40E_VF_ATQLEN1_ATQCRIT_MASK) { - i40e_debug(hw, I40E_DEBUG_AQ_MESSAGE, + if (rd32(hw, hw->aq.asq.len) & IAVF_VF_ATQLEN1_ATQCRIT_MASK) { + iavf_debug(hw, IAVF_DEBUG_AQ_MESSAGE, "AQTX: AQ Critical error.\n"); status = I40E_ERR_ADMIN_QUEUE_CRITICAL_ERROR; } else { - i40e_debug(hw, I40E_DEBUG_AQ_MESSAGE, + iavf_debug(hw, IAVF_DEBUG_AQ_MESSAGE, "AQTX: Writeback timeout.\n"); status = I40E_ERR_ADMIN_QUEUE_TIMEOUT; } @@ -833,14 +817,13 @@ asq_send_command_error: } /** - * i40evf_fill_default_direct_cmd_desc - AQ descriptor helper function + * iavf_fill_default_direct_cmd_desc - AQ descriptor helper function * @desc: pointer to the temp descriptor (non DMA mem) * @opcode: the opcode can be used to decide which flags to turn off or on * * Fill the desc with default values **/ -void i40evf_fill_default_direct_cmd_desc(struct i40e_aq_desc *desc, - u16 opcode) +void iavf_fill_default_direct_cmd_desc(struct i40e_aq_desc *desc, u16 opcode) { /* zero out the desc */ memset((void *)desc, 0, sizeof(struct i40e_aq_desc)); @@ -849,7 +832,7 @@ void i40evf_fill_default_direct_cmd_desc(struct i40e_aq_desc *desc, } /** - * i40evf_clean_arq_element + * iavf_clean_arq_element * @hw: pointer to the hw struct * @e: event info from the receive descriptor, includes any buffers * @pending: number of events that could be left to process @@ -858,14 +841,14 @@ void i40evf_fill_default_direct_cmd_desc(struct i40e_aq_desc *desc, * the contents through e. It can also return how many events are * left to process through 'pending' **/ -i40e_status i40evf_clean_arq_element(struct i40e_hw *hw, - struct i40e_arq_event_info *e, - u16 *pending) +iavf_status iavf_clean_arq_element(struct iavf_hw *hw, + struct i40e_arq_event_info *e, + u16 *pending) { - i40e_status ret_code = 0; u16 ntc = hw->aq.arq.next_to_clean; struct i40e_aq_desc *desc; - struct i40e_dma_mem *bi; + iavf_status ret_code = 0; + struct iavf_dma_mem *bi; u16 desc_idx; u16 datalen; u16 flags; @@ -878,14 +861,14 @@ i40e_status i40evf_clean_arq_element(struct i40e_hw *hw, mutex_lock(&hw->aq.arq_mutex); if (hw->aq.arq.count == 0) { - i40e_debug(hw, I40E_DEBUG_AQ_MESSAGE, + iavf_debug(hw, IAVF_DEBUG_AQ_MESSAGE, "AQRX: Admin queue not initialized.\n"); ret_code = I40E_ERR_QUEUE_EMPTY; goto clean_arq_element_err; } /* set next_to_use to head */ - ntu = rd32(hw, hw->aq.arq.head) & I40E_VF_ARQH1_ARQH_MASK; + ntu = rd32(hw, hw->aq.arq.head) & IAVF_VF_ARQH1_ARQH_MASK; if (ntu == ntc) { /* nothing to do - shouldn't need to update ring's values */ ret_code = I40E_ERR_ADMIN_QUEUE_NO_WORK; @@ -893,7 +876,7 @@ i40e_status i40evf_clean_arq_element(struct i40e_hw *hw, } /* now clean the next descriptor */ - desc = I40E_ADMINQ_DESC(hw->aq.arq, ntc); + desc = IAVF_ADMINQ_DESC(hw->aq.arq, ntc); desc_idx = ntc; hw->aq.arq_last_status = @@ -901,8 +884,8 @@ i40e_status i40evf_clean_arq_element(struct i40e_hw *hw, flags = le16_to_cpu(desc->flags); if (flags & I40E_AQ_FLAG_ERR) { ret_code = I40E_ERR_ADMIN_QUEUE_ERROR; - i40e_debug(hw, - I40E_DEBUG_AQ_MESSAGE, + iavf_debug(hw, + IAVF_DEBUG_AQ_MESSAGE, "AQRX: Event received with error 0x%X.\n", hw->aq.arq_last_status); } @@ -910,13 +893,13 @@ i40e_status i40evf_clean_arq_element(struct i40e_hw *hw, e->desc = *desc; datalen = le16_to_cpu(desc->datalen); e->msg_len = min(datalen, e->buf_len); - if (e->msg_buf != NULL && (e->msg_len != 0)) + if (e->msg_buf && (e->msg_len != 0)) memcpy(e->msg_buf, hw->aq.arq.r.arq_bi[desc_idx].va, e->msg_len); - i40e_debug(hw, I40E_DEBUG_AQ_MESSAGE, "AQRX: desc and buffer:\n"); - i40evf_debug_aq(hw, I40E_DEBUG_AQ_COMMAND, (void *)desc, e->msg_buf, - hw->aq.arq_buf_size); + iavf_debug(hw, IAVF_DEBUG_AQ_MESSAGE, "AQRX: desc and buffer:\n"); + iavf_debug_aq(hw, IAVF_DEBUG_AQ_COMMAND, (void *)desc, e->msg_buf, + hw->aq.arq_buf_size); /* Restore the original datalen and buffer address in the desc, * FW updates datalen to indicate the event message @@ -943,7 +926,7 @@ i40e_status i40evf_clean_arq_element(struct i40e_hw *hw, clean_arq_element_out: /* Set pending if needed, unlock and return */ - if (pending != NULL) + if (pending) *pending = (ntc > ntu ? hw->aq.arq.count : 0) + (ntu - ntc); clean_arq_element_err: @@ -951,17 +934,3 @@ clean_arq_element_err: return ret_code; } - -void i40evf_resume_aq(struct i40e_hw *hw) -{ - /* Registers are reset after PF reset */ - hw->aq.asq.next_to_use = 0; - hw->aq.asq.next_to_clean = 0; - - i40e_config_asq_regs(hw); - - hw->aq.arq.next_to_use = 0; - hw->aq.arq.next_to_clean = 0; - - i40e_config_arq_regs(hw); -} diff --git a/drivers/net/ethernet/intel/i40evf/i40e_adminq.h b/drivers/net/ethernet/intel/iavf/i40e_adminq.h index 1f264b9b6805..ee983889eab0 100644 --- a/drivers/net/ethernet/intel/i40evf/i40e_adminq.h +++ b/drivers/net/ethernet/intel/iavf/i40e_adminq.h @@ -1,26 +1,26 @@ /* SPDX-License-Identifier: GPL-2.0 */ /* Copyright(c) 2013 - 2018 Intel Corporation. */ -#ifndef _I40E_ADMINQ_H_ -#define _I40E_ADMINQ_H_ +#ifndef _IAVF_ADMINQ_H_ +#define _IAVF_ADMINQ_H_ -#include "i40e_osdep.h" -#include "i40e_status.h" +#include "iavf_osdep.h" +#include "iavf_status.h" #include "i40e_adminq_cmd.h" -#define I40E_ADMINQ_DESC(R, i) \ +#define IAVF_ADMINQ_DESC(R, i) \ (&(((struct i40e_aq_desc *)((R).desc_buf.va))[i])) -#define I40E_ADMINQ_DESC_ALIGNMENT 4096 +#define IAVF_ADMINQ_DESC_ALIGNMENT 4096 -struct i40e_adminq_ring { - struct i40e_virt_mem dma_head; /* space for dma structures */ - struct i40e_dma_mem desc_buf; /* descriptor ring memory */ - struct i40e_virt_mem cmd_buf; /* command buffer memory */ +struct iavf_adminq_ring { + struct iavf_virt_mem dma_head; /* space for dma structures */ + struct iavf_dma_mem desc_buf; /* descriptor ring memory */ + struct iavf_virt_mem cmd_buf; /* command buffer memory */ union { - struct i40e_dma_mem *asq_bi; - struct i40e_dma_mem *arq_bi; + struct iavf_dma_mem *asq_bi; + struct iavf_dma_mem *arq_bi; } r; u16 count; /* Number of descriptors */ @@ -61,9 +61,9 @@ struct i40e_arq_event_info { }; /* Admin Queue information */ -struct i40e_adminq_info { - struct i40e_adminq_ring arq; /* receive queue */ - struct i40e_adminq_ring asq; /* send queue */ +struct iavf_adminq_info { + struct iavf_adminq_ring arq; /* receive queue */ + struct iavf_adminq_ring asq; /* send queue */ u32 asq_cmd_timeout; /* send queue cmd write back timeout*/ u16 num_arq_entries; /* receive queue depth */ u16 num_asq_entries; /* send queue depth */ @@ -130,7 +130,6 @@ static inline int i40e_aq_rc_to_posix(int aq_ret, int aq_rc) #define I40E_AQ_LARGE_BUF 512 #define I40E_ASQ_CMD_TIMEOUT 250000 /* usecs */ -void i40evf_fill_default_direct_cmd_desc(struct i40e_aq_desc *desc, - u16 opcode); +void iavf_fill_default_direct_cmd_desc(struct i40e_aq_desc *desc, u16 opcode); -#endif /* _I40E_ADMINQ_H_ */ +#endif /* _IAVF_ADMINQ_H_ */ diff --git a/drivers/net/ethernet/intel/iavf/i40e_adminq_cmd.h b/drivers/net/ethernet/intel/iavf/i40e_adminq_cmd.h new file mode 100644 index 000000000000..af4f94a6541e --- /dev/null +++ b/drivers/net/ethernet/intel/iavf/i40e_adminq_cmd.h @@ -0,0 +1,530 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright(c) 2013 - 2018 Intel Corporation. */ + +#ifndef _I40E_ADMINQ_CMD_H_ +#define _I40E_ADMINQ_CMD_H_ + +/* This header file defines the i40e Admin Queue commands and is shared between + * i40e Firmware and Software. Do not change the names in this file to IAVF + * because this file should be diff-able against the i40e version, even + * though many parts have been removed in this VF version. + * + * This file needs to comply with the Linux Kernel coding style. + */ + +#define I40E_FW_API_VERSION_MAJOR 0x0001 +#define I40E_FW_API_VERSION_MINOR_X722 0x0005 +#define I40E_FW_API_VERSION_MINOR_X710 0x0007 + +#define I40E_FW_MINOR_VERSION(_h) ((_h)->mac.type == I40E_MAC_XL710 ? \ + I40E_FW_API_VERSION_MINOR_X710 : \ + I40E_FW_API_VERSION_MINOR_X722) + +/* API version 1.7 implements additional link and PHY-specific APIs */ +#define I40E_MINOR_VER_GET_LINK_INFO_XL710 0x0007 + +struct i40e_aq_desc { + __le16 flags; + __le16 opcode; + __le16 datalen; + __le16 retval; + __le32 cookie_high; + __le32 cookie_low; + union { + struct { + __le32 param0; + __le32 param1; + __le32 param2; + __le32 param3; + } internal; + struct { + __le32 param0; + __le32 param1; + __le32 addr_high; + __le32 addr_low; + } external; + u8 raw[16]; + } params; +}; + +/* Flags sub-structure + * |0 |1 |2 |3 |4 |5 |6 |7 |8 |9 |10 |11 |12 |13 |14 |15 | + * |DD |CMP|ERR|VFE| * * RESERVED * * |LB |RD |VFC|BUF|SI |EI |FE | + */ + +/* command flags and offsets*/ +#define I40E_AQ_FLAG_DD_SHIFT 0 +#define I40E_AQ_FLAG_CMP_SHIFT 1 +#define I40E_AQ_FLAG_ERR_SHIFT 2 +#define I40E_AQ_FLAG_VFE_SHIFT 3 +#define I40E_AQ_FLAG_LB_SHIFT 9 +#define I40E_AQ_FLAG_RD_SHIFT 10 +#define I40E_AQ_FLAG_VFC_SHIFT 11 +#define I40E_AQ_FLAG_BUF_SHIFT 12 +#define I40E_AQ_FLAG_SI_SHIFT 13 +#define I40E_AQ_FLAG_EI_SHIFT 14 +#define I40E_AQ_FLAG_FE_SHIFT 15 + +#define I40E_AQ_FLAG_DD BIT(I40E_AQ_FLAG_DD_SHIFT) /* 0x1 */ +#define I40E_AQ_FLAG_CMP BIT(I40E_AQ_FLAG_CMP_SHIFT) /* 0x2 */ +#define I40E_AQ_FLAG_ERR BIT(I40E_AQ_FLAG_ERR_SHIFT) /* 0x4 */ +#define I40E_AQ_FLAG_VFE BIT(I40E_AQ_FLAG_VFE_SHIFT) /* 0x8 */ +#define I40E_AQ_FLAG_LB BIT(I40E_AQ_FLAG_LB_SHIFT) /* 0x200 */ +#define I40E_AQ_FLAG_RD BIT(I40E_AQ_FLAG_RD_SHIFT) /* 0x400 */ +#define I40E_AQ_FLAG_VFC BIT(I40E_AQ_FLAG_VFC_SHIFT) /* 0x800 */ +#define I40E_AQ_FLAG_BUF BIT(I40E_AQ_FLAG_BUF_SHIFT) /* 0x1000 */ +#define I40E_AQ_FLAG_SI BIT(I40E_AQ_FLAG_SI_SHIFT) /* 0x2000 */ +#define I40E_AQ_FLAG_EI BIT(I40E_AQ_FLAG_EI_SHIFT) /* 0x4000 */ +#define I40E_AQ_FLAG_FE BIT(I40E_AQ_FLAG_FE_SHIFT) /* 0x8000 */ + +/* error codes */ +enum i40e_admin_queue_err { + I40E_AQ_RC_OK = 0, /* success */ + I40E_AQ_RC_EPERM = 1, /* Operation not permitted */ + I40E_AQ_RC_ENOENT = 2, /* No such element */ + I40E_AQ_RC_ESRCH = 3, /* Bad opcode */ + I40E_AQ_RC_EINTR = 4, /* operation interrupted */ + I40E_AQ_RC_EIO = 5, /* I/O error */ + I40E_AQ_RC_ENXIO = 6, /* No such resource */ + I40E_AQ_RC_E2BIG = 7, /* Arg too long */ + I40E_AQ_RC_EAGAIN = 8, /* Try again */ + I40E_AQ_RC_ENOMEM = 9, /* Out of memory */ + I40E_AQ_RC_EACCES = 10, /* Permission denied */ + I40E_AQ_RC_EFAULT = 11, /* Bad address */ + I40E_AQ_RC_EBUSY = 12, /* Device or resource busy */ + I40E_AQ_RC_EEXIST = 13, /* object already exists */ + I40E_AQ_RC_EINVAL = 14, /* Invalid argument */ + I40E_AQ_RC_ENOTTY = 15, /* Not a typewriter */ + I40E_AQ_RC_ENOSPC = 16, /* No space left or alloc failure */ + I40E_AQ_RC_ENOSYS = 17, /* Function not implemented */ + I40E_AQ_RC_ERANGE = 18, /* Parameter out of range */ + I40E_AQ_RC_EFLUSHED = 19, /* Cmd flushed due to prev cmd error */ + I40E_AQ_RC_BAD_ADDR = 20, /* Descriptor contains a bad pointer */ + I40E_AQ_RC_EMODE = 21, /* Op not allowed in current dev mode */ + I40E_AQ_RC_EFBIG = 22, /* File too large */ +}; + +/* Admin Queue command opcodes */ +enum i40e_admin_queue_opc { + /* aq commands */ + i40e_aqc_opc_get_version = 0x0001, + i40e_aqc_opc_driver_version = 0x0002, + i40e_aqc_opc_queue_shutdown = 0x0003, + i40e_aqc_opc_set_pf_context = 0x0004, + + /* resource ownership */ + i40e_aqc_opc_request_resource = 0x0008, + i40e_aqc_opc_release_resource = 0x0009, + + i40e_aqc_opc_list_func_capabilities = 0x000A, + i40e_aqc_opc_list_dev_capabilities = 0x000B, + + /* Proxy commands */ + i40e_aqc_opc_set_proxy_config = 0x0104, + i40e_aqc_opc_set_ns_proxy_table_entry = 0x0105, + + /* LAA */ + i40e_aqc_opc_mac_address_read = 0x0107, + i40e_aqc_opc_mac_address_write = 0x0108, + + /* PXE */ + i40e_aqc_opc_clear_pxe_mode = 0x0110, + + /* WoL commands */ + i40e_aqc_opc_set_wol_filter = 0x0120, + i40e_aqc_opc_get_wake_reason = 0x0121, + + /* internal switch commands */ + i40e_aqc_opc_get_switch_config = 0x0200, + i40e_aqc_opc_add_statistics = 0x0201, + i40e_aqc_opc_remove_statistics = 0x0202, + i40e_aqc_opc_set_port_parameters = 0x0203, + i40e_aqc_opc_get_switch_resource_alloc = 0x0204, + i40e_aqc_opc_set_switch_config = 0x0205, + i40e_aqc_opc_rx_ctl_reg_read = 0x0206, + i40e_aqc_opc_rx_ctl_reg_write = 0x0207, + + i40e_aqc_opc_add_vsi = 0x0210, + i40e_aqc_opc_update_vsi_parameters = 0x0211, + i40e_aqc_opc_get_vsi_parameters = 0x0212, + + i40e_aqc_opc_add_pv = 0x0220, + i40e_aqc_opc_update_pv_parameters = 0x0221, + i40e_aqc_opc_get_pv_parameters = 0x0222, + + i40e_aqc_opc_add_veb = 0x0230, + i40e_aqc_opc_update_veb_parameters = 0x0231, + i40e_aqc_opc_get_veb_parameters = 0x0232, + + i40e_aqc_opc_delete_element = 0x0243, + + i40e_aqc_opc_add_macvlan = 0x0250, + i40e_aqc_opc_remove_macvlan = 0x0251, + i40e_aqc_opc_add_vlan = 0x0252, + i40e_aqc_opc_remove_vlan = 0x0253, + i40e_aqc_opc_set_vsi_promiscuous_modes = 0x0254, + i40e_aqc_opc_add_tag = 0x0255, + i40e_aqc_opc_remove_tag = 0x0256, + i40e_aqc_opc_add_multicast_etag = 0x0257, + i40e_aqc_opc_remove_multicast_etag = 0x0258, + i40e_aqc_opc_update_tag = 0x0259, + i40e_aqc_opc_add_control_packet_filter = 0x025A, + i40e_aqc_opc_remove_control_packet_filter = 0x025B, + i40e_aqc_opc_add_cloud_filters = 0x025C, + i40e_aqc_opc_remove_cloud_filters = 0x025D, + i40e_aqc_opc_clear_wol_switch_filters = 0x025E, + + i40e_aqc_opc_add_mirror_rule = 0x0260, + i40e_aqc_opc_delete_mirror_rule = 0x0261, + + /* Dynamic Device Personalization */ + i40e_aqc_opc_write_personalization_profile = 0x0270, + i40e_aqc_opc_get_personalization_profile_list = 0x0271, + + /* DCB commands */ + i40e_aqc_opc_dcb_ignore_pfc = 0x0301, + i40e_aqc_opc_dcb_updated = 0x0302, + i40e_aqc_opc_set_dcb_parameters = 0x0303, + + /* TX scheduler */ + i40e_aqc_opc_configure_vsi_bw_limit = 0x0400, + i40e_aqc_opc_configure_vsi_ets_sla_bw_limit = 0x0406, + i40e_aqc_opc_configure_vsi_tc_bw = 0x0407, + i40e_aqc_opc_query_vsi_bw_config = 0x0408, + i40e_aqc_opc_query_vsi_ets_sla_config = 0x040A, + i40e_aqc_opc_configure_switching_comp_bw_limit = 0x0410, + + i40e_aqc_opc_enable_switching_comp_ets = 0x0413, + i40e_aqc_opc_modify_switching_comp_ets = 0x0414, + i40e_aqc_opc_disable_switching_comp_ets = 0x0415, + i40e_aqc_opc_configure_switching_comp_ets_bw_limit = 0x0416, + i40e_aqc_opc_configure_switching_comp_bw_config = 0x0417, + i40e_aqc_opc_query_switching_comp_ets_config = 0x0418, + i40e_aqc_opc_query_port_ets_config = 0x0419, + i40e_aqc_opc_query_switching_comp_bw_config = 0x041A, + i40e_aqc_opc_suspend_port_tx = 0x041B, + i40e_aqc_opc_resume_port_tx = 0x041C, + i40e_aqc_opc_configure_partition_bw = 0x041D, + /* hmc */ + i40e_aqc_opc_query_hmc_resource_profile = 0x0500, + i40e_aqc_opc_set_hmc_resource_profile = 0x0501, + + /* phy commands*/ + i40e_aqc_opc_get_phy_abilities = 0x0600, + i40e_aqc_opc_set_phy_config = 0x0601, + i40e_aqc_opc_set_mac_config = 0x0603, + i40e_aqc_opc_set_link_restart_an = 0x0605, + i40e_aqc_opc_get_link_status = 0x0607, + i40e_aqc_opc_set_phy_int_mask = 0x0613, + i40e_aqc_opc_get_local_advt_reg = 0x0614, + i40e_aqc_opc_set_local_advt_reg = 0x0615, + i40e_aqc_opc_get_partner_advt = 0x0616, + i40e_aqc_opc_set_lb_modes = 0x0618, + i40e_aqc_opc_get_phy_wol_caps = 0x0621, + i40e_aqc_opc_set_phy_debug = 0x0622, + i40e_aqc_opc_upload_ext_phy_fm = 0x0625, + i40e_aqc_opc_run_phy_activity = 0x0626, + i40e_aqc_opc_set_phy_register = 0x0628, + i40e_aqc_opc_get_phy_register = 0x0629, + + /* NVM commands */ + i40e_aqc_opc_nvm_read = 0x0701, + i40e_aqc_opc_nvm_erase = 0x0702, + i40e_aqc_opc_nvm_update = 0x0703, + i40e_aqc_opc_nvm_config_read = 0x0704, + i40e_aqc_opc_nvm_config_write = 0x0705, + i40e_aqc_opc_oem_post_update = 0x0720, + i40e_aqc_opc_thermal_sensor = 0x0721, + + /* virtualization commands */ + i40e_aqc_opc_send_msg_to_pf = 0x0801, + i40e_aqc_opc_send_msg_to_vf = 0x0802, + i40e_aqc_opc_send_msg_to_peer = 0x0803, + + /* alternate structure */ + i40e_aqc_opc_alternate_write = 0x0900, + i40e_aqc_opc_alternate_write_indirect = 0x0901, + i40e_aqc_opc_alternate_read = 0x0902, + i40e_aqc_opc_alternate_read_indirect = 0x0903, + i40e_aqc_opc_alternate_write_done = 0x0904, + i40e_aqc_opc_alternate_set_mode = 0x0905, + i40e_aqc_opc_alternate_clear_port = 0x0906, + + /* LLDP commands */ + i40e_aqc_opc_lldp_get_mib = 0x0A00, + i40e_aqc_opc_lldp_update_mib = 0x0A01, + i40e_aqc_opc_lldp_add_tlv = 0x0A02, + i40e_aqc_opc_lldp_update_tlv = 0x0A03, + i40e_aqc_opc_lldp_delete_tlv = 0x0A04, + i40e_aqc_opc_lldp_stop = 0x0A05, + i40e_aqc_opc_lldp_start = 0x0A06, + + /* Tunnel commands */ + i40e_aqc_opc_add_udp_tunnel = 0x0B00, + i40e_aqc_opc_del_udp_tunnel = 0x0B01, + i40e_aqc_opc_set_rss_key = 0x0B02, + i40e_aqc_opc_set_rss_lut = 0x0B03, + i40e_aqc_opc_get_rss_key = 0x0B04, + i40e_aqc_opc_get_rss_lut = 0x0B05, + + /* Async Events */ + i40e_aqc_opc_event_lan_overflow = 0x1001, + + /* OEM commands */ + i40e_aqc_opc_oem_parameter_change = 0xFE00, + i40e_aqc_opc_oem_device_status_change = 0xFE01, + i40e_aqc_opc_oem_ocsd_initialize = 0xFE02, + i40e_aqc_opc_oem_ocbb_initialize = 0xFE03, + + /* debug commands */ + i40e_aqc_opc_debug_read_reg = 0xFF03, + i40e_aqc_opc_debug_write_reg = 0xFF04, + i40e_aqc_opc_debug_modify_reg = 0xFF07, + i40e_aqc_opc_debug_dump_internals = 0xFF08, +}; + +/* command structures and indirect data structures */ + +/* Structure naming conventions: + * - no suffix for direct command descriptor structures + * - _data for indirect sent data + * - _resp for indirect return data (data which is both will use _data) + * - _completion for direct return data + * - _element_ for repeated elements (may also be _data or _resp) + * + * Command structures are expected to overlay the params.raw member of the basic + * descriptor, and as such cannot exceed 16 bytes in length. + */ + +/* This macro is used to generate a compilation error if a structure + * is not exactly the correct length. It gives a divide by zero error if the + * structure is not of the correct size, otherwise it creates an enum that is + * never used. + */ +#define I40E_CHECK_STRUCT_LEN(n, X) enum i40e_static_assert_enum_##X \ + { i40e_static_assert_##X = (n)/((sizeof(struct X) == (n)) ? 1 : 0) } + +/* This macro is used extensively to ensure that command structures are 16 + * bytes in length as they have to map to the raw array of that size. + */ +#define I40E_CHECK_CMD_LENGTH(X) I40E_CHECK_STRUCT_LEN(16, X) + +/* Queue Shutdown (direct 0x0003) */ +struct i40e_aqc_queue_shutdown { + __le32 driver_unloading; +#define I40E_AQ_DRIVER_UNLOADING 0x1 + u8 reserved[12]; +}; + +I40E_CHECK_CMD_LENGTH(i40e_aqc_queue_shutdown); + +struct i40e_aqc_vsi_properties_data { + /* first 96 byte are written by SW */ + __le16 valid_sections; +#define I40E_AQ_VSI_PROP_SWITCH_VALID 0x0001 +#define I40E_AQ_VSI_PROP_SECURITY_VALID 0x0002 +#define I40E_AQ_VSI_PROP_VLAN_VALID 0x0004 +#define I40E_AQ_VSI_PROP_CAS_PV_VALID 0x0008 +#define I40E_AQ_VSI_PROP_INGRESS_UP_VALID 0x0010 +#define I40E_AQ_VSI_PROP_EGRESS_UP_VALID 0x0020 +#define I40E_AQ_VSI_PROP_QUEUE_MAP_VALID 0x0040 +#define I40E_AQ_VSI_PROP_QUEUE_OPT_VALID 0x0080 +#define I40E_AQ_VSI_PROP_OUTER_UP_VALID 0x0100 +#define I40E_AQ_VSI_PROP_SCHED_VALID 0x0200 + /* switch section */ + __le16 switch_id; /* 12bit id combined with flags below */ +#define I40E_AQ_VSI_SW_ID_SHIFT 0x0000 +#define I40E_AQ_VSI_SW_ID_MASK (0xFFF << I40E_AQ_VSI_SW_ID_SHIFT) +#define I40E_AQ_VSI_SW_ID_FLAG_NOT_STAG 0x1000 +#define I40E_AQ_VSI_SW_ID_FLAG_ALLOW_LB 0x2000 +#define I40E_AQ_VSI_SW_ID_FLAG_LOCAL_LB 0x4000 + u8 sw_reserved[2]; + /* security section */ + u8 sec_flags; +#define I40E_AQ_VSI_SEC_FLAG_ALLOW_DEST_OVRD 0x01 +#define I40E_AQ_VSI_SEC_FLAG_ENABLE_VLAN_CHK 0x02 +#define I40E_AQ_VSI_SEC_FLAG_ENABLE_MAC_CHK 0x04 + u8 sec_reserved; + /* VLAN section */ + __le16 pvid; /* VLANS include priority bits */ + __le16 fcoe_pvid; + u8 port_vlan_flags; +#define I40E_AQ_VSI_PVLAN_MODE_SHIFT 0x00 +#define I40E_AQ_VSI_PVLAN_MODE_MASK (0x03 << \ + I40E_AQ_VSI_PVLAN_MODE_SHIFT) +#define I40E_AQ_VSI_PVLAN_MODE_TAGGED 0x01 +#define I40E_AQ_VSI_PVLAN_MODE_UNTAGGED 0x02 +#define I40E_AQ_VSI_PVLAN_MODE_ALL 0x03 +#define I40E_AQ_VSI_PVLAN_INSERT_PVID 0x04 +#define I40E_AQ_VSI_PVLAN_EMOD_SHIFT 0x03 +#define I40E_AQ_VSI_PVLAN_EMOD_MASK (0x3 << \ + I40E_AQ_VSI_PVLAN_EMOD_SHIFT) +#define I40E_AQ_VSI_PVLAN_EMOD_STR_BOTH 0x0 +#define I40E_AQ_VSI_PVLAN_EMOD_STR_UP 0x08 +#define I40E_AQ_VSI_PVLAN_EMOD_STR 0x10 +#define I40E_AQ_VSI_PVLAN_EMOD_NOTHING 0x18 + u8 pvlan_reserved[3]; + /* ingress egress up sections */ + __le32 ingress_table; /* bitmap, 3 bits per up */ +#define I40E_AQ_VSI_UP_TABLE_UP0_SHIFT 0 +#define I40E_AQ_VSI_UP_TABLE_UP0_MASK (0x7 << \ + I40E_AQ_VSI_UP_TABLE_UP0_SHIFT) +#define I40E_AQ_VSI_UP_TABLE_UP1_SHIFT 3 +#define I40E_AQ_VSI_UP_TABLE_UP1_MASK (0x7 << \ + I40E_AQ_VSI_UP_TABLE_UP1_SHIFT) +#define I40E_AQ_VSI_UP_TABLE_UP2_SHIFT 6 +#define I40E_AQ_VSI_UP_TABLE_UP2_MASK (0x7 << \ + I40E_AQ_VSI_UP_TABLE_UP2_SHIFT) +#define I40E_AQ_VSI_UP_TABLE_UP3_SHIFT 9 +#define I40E_AQ_VSI_UP_TABLE_UP3_MASK (0x7 << \ + I40E_AQ_VSI_UP_TABLE_UP3_SHIFT) +#define I40E_AQ_VSI_UP_TABLE_UP4_SHIFT 12 +#define I40E_AQ_VSI_UP_TABLE_UP4_MASK (0x7 << \ + I40E_AQ_VSI_UP_TABLE_UP4_SHIFT) +#define I40E_AQ_VSI_UP_TABLE_UP5_SHIFT 15 +#define I40E_AQ_VSI_UP_TABLE_UP5_MASK (0x7 << \ + I40E_AQ_VSI_UP_TABLE_UP5_SHIFT) +#define I40E_AQ_VSI_UP_TABLE_UP6_SHIFT 18 +#define I40E_AQ_VSI_UP_TABLE_UP6_MASK (0x7 << \ + I40E_AQ_VSI_UP_TABLE_UP6_SHIFT) +#define I40E_AQ_VSI_UP_TABLE_UP7_SHIFT 21 +#define I40E_AQ_VSI_UP_TABLE_UP7_MASK (0x7 << \ + I40E_AQ_VSI_UP_TABLE_UP7_SHIFT) + __le32 egress_table; /* same defines as for ingress table */ + /* cascaded PV section */ + __le16 cas_pv_tag; + u8 cas_pv_flags; +#define I40E_AQ_VSI_CAS_PV_TAGX_SHIFT 0x00 +#define I40E_AQ_VSI_CAS_PV_TAGX_MASK (0x03 << \ + I40E_AQ_VSI_CAS_PV_TAGX_SHIFT) +#define I40E_AQ_VSI_CAS_PV_TAGX_LEAVE 0x00 +#define I40E_AQ_VSI_CAS_PV_TAGX_REMOVE 0x01 +#define I40E_AQ_VSI_CAS_PV_TAGX_COPY 0x02 +#define I40E_AQ_VSI_CAS_PV_INSERT_TAG 0x10 +#define I40E_AQ_VSI_CAS_PV_ETAG_PRUNE 0x20 +#define I40E_AQ_VSI_CAS_PV_ACCEPT_HOST_TAG 0x40 + u8 cas_pv_reserved; + /* queue mapping section */ + __le16 mapping_flags; +#define I40E_AQ_VSI_QUE_MAP_CONTIG 0x0 +#define I40E_AQ_VSI_QUE_MAP_NONCONTIG 0x1 + __le16 queue_mapping[16]; +#define I40E_AQ_VSI_QUEUE_SHIFT 0x0 +#define I40E_AQ_VSI_QUEUE_MASK (0x7FF << I40E_AQ_VSI_QUEUE_SHIFT) + __le16 tc_mapping[8]; +#define I40E_AQ_VSI_TC_QUE_OFFSET_SHIFT 0 +#define I40E_AQ_VSI_TC_QUE_OFFSET_MASK (0x1FF << \ + I40E_AQ_VSI_TC_QUE_OFFSET_SHIFT) +#define I40E_AQ_VSI_TC_QUE_NUMBER_SHIFT 9 +#define I40E_AQ_VSI_TC_QUE_NUMBER_MASK (0x7 << \ + I40E_AQ_VSI_TC_QUE_NUMBER_SHIFT) + /* queueing option section */ + u8 queueing_opt_flags; +#define I40E_AQ_VSI_QUE_OPT_MULTICAST_UDP_ENA 0x04 +#define I40E_AQ_VSI_QUE_OPT_UNICAST_UDP_ENA 0x08 +#define I40E_AQ_VSI_QUE_OPT_TCP_ENA 0x10 +#define I40E_AQ_VSI_QUE_OPT_FCOE_ENA 0x20 +#define I40E_AQ_VSI_QUE_OPT_RSS_LUT_PF 0x00 +#define I40E_AQ_VSI_QUE_OPT_RSS_LUT_VSI 0x40 + u8 queueing_opt_reserved[3]; + /* scheduler section */ + u8 up_enable_bits; + u8 sched_reserved; + /* outer up section */ + __le32 outer_up_table; /* same structure and defines as ingress tbl */ + u8 cmd_reserved[8]; + /* last 32 bytes are written by FW */ + __le16 qs_handle[8]; +#define I40E_AQ_VSI_QS_HANDLE_INVALID 0xFFFF + __le16 stat_counter_idx; + __le16 sched_id; + u8 resp_reserved[12]; +}; + +I40E_CHECK_STRUCT_LEN(128, i40e_aqc_vsi_properties_data); + +/* Get VEB Parameters (direct 0x0232) + * uses i40e_aqc_switch_seid for the descriptor + */ +struct i40e_aqc_get_veb_parameters_completion { + __le16 seid; + __le16 switch_id; + __le16 veb_flags; /* only the first/last flags from 0x0230 is valid */ + __le16 statistic_index; + __le16 vebs_used; + __le16 vebs_free; + u8 reserved[4]; +}; + +I40E_CHECK_CMD_LENGTH(i40e_aqc_get_veb_parameters_completion); + +#define I40E_LINK_SPEED_100MB_SHIFT 0x1 +#define I40E_LINK_SPEED_1000MB_SHIFT 0x2 +#define I40E_LINK_SPEED_10GB_SHIFT 0x3 +#define I40E_LINK_SPEED_40GB_SHIFT 0x4 +#define I40E_LINK_SPEED_20GB_SHIFT 0x5 +#define I40E_LINK_SPEED_25GB_SHIFT 0x6 + +enum i40e_aq_link_speed { + I40E_LINK_SPEED_UNKNOWN = 0, + I40E_LINK_SPEED_100MB = BIT(I40E_LINK_SPEED_100MB_SHIFT), + I40E_LINK_SPEED_1GB = BIT(I40E_LINK_SPEED_1000MB_SHIFT), + I40E_LINK_SPEED_10GB = BIT(I40E_LINK_SPEED_10GB_SHIFT), + I40E_LINK_SPEED_40GB = BIT(I40E_LINK_SPEED_40GB_SHIFT), + I40E_LINK_SPEED_20GB = BIT(I40E_LINK_SPEED_20GB_SHIFT), + I40E_LINK_SPEED_25GB = BIT(I40E_LINK_SPEED_25GB_SHIFT), +}; + +/* Send to PF command (indirect 0x0801) id is only used by PF + * Send to VF command (indirect 0x0802) id is only used by PF + * Send to Peer PF command (indirect 0x0803) + */ +struct i40e_aqc_pf_vf_message { + __le32 id; + u8 reserved[4]; + __le32 addr_high; + __le32 addr_low; +}; + +I40E_CHECK_CMD_LENGTH(i40e_aqc_pf_vf_message); + +struct i40e_aqc_get_set_rss_key { +#define I40E_AQC_SET_RSS_KEY_VSI_VALID BIT(15) +#define I40E_AQC_SET_RSS_KEY_VSI_ID_SHIFT 0 +#define I40E_AQC_SET_RSS_KEY_VSI_ID_MASK (0x3FF << \ + I40E_AQC_SET_RSS_KEY_VSI_ID_SHIFT) + __le16 vsi_id; + u8 reserved[6]; + __le32 addr_high; + __le32 addr_low; +}; + +I40E_CHECK_CMD_LENGTH(i40e_aqc_get_set_rss_key); + +struct i40e_aqc_get_set_rss_key_data { + u8 standard_rss_key[0x28]; + u8 extended_hash_key[0xc]; +}; + +I40E_CHECK_STRUCT_LEN(0x34, i40e_aqc_get_set_rss_key_data); + +struct i40e_aqc_get_set_rss_lut { +#define I40E_AQC_SET_RSS_LUT_VSI_VALID BIT(15) +#define I40E_AQC_SET_RSS_LUT_VSI_ID_SHIFT 0 +#define I40E_AQC_SET_RSS_LUT_VSI_ID_MASK (0x3FF << \ + I40E_AQC_SET_RSS_LUT_VSI_ID_SHIFT) + __le16 vsi_id; +#define I40E_AQC_SET_RSS_LUT_TABLE_TYPE_SHIFT 0 +#define I40E_AQC_SET_RSS_LUT_TABLE_TYPE_MASK \ + BIT(I40E_AQC_SET_RSS_LUT_TABLE_TYPE_SHIFT) + +#define I40E_AQC_SET_RSS_LUT_TABLE_TYPE_VSI 0 +#define I40E_AQC_SET_RSS_LUT_TABLE_TYPE_PF 1 + __le16 flags; + u8 reserved[4]; + __le32 addr_high; + __le32 addr_low; +}; + +I40E_CHECK_CMD_LENGTH(i40e_aqc_get_set_rss_lut); +#endif /* _I40E_ADMINQ_CMD_H_ */ diff --git a/drivers/net/ethernet/intel/iavf/iavf.h b/drivers/net/ethernet/intel/iavf/iavf.h new file mode 100644 index 000000000000..a512f7521841 --- /dev/null +++ b/drivers/net/ethernet/intel/iavf/iavf.h @@ -0,0 +1,418 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright(c) 2013 - 2018 Intel Corporation. */ + +#ifndef _IAVF_H_ +#define _IAVF_H_ + +#include <linux/module.h> +#include <linux/pci.h> +#include <linux/aer.h> +#include <linux/netdevice.h> +#include <linux/vmalloc.h> +#include <linux/interrupt.h> +#include <linux/ethtool.h> +#include <linux/if_vlan.h> +#include <linux/ip.h> +#include <linux/tcp.h> +#include <linux/sctp.h> +#include <linux/ipv6.h> +#include <linux/kernel.h> +#include <linux/bitops.h> +#include <linux/timer.h> +#include <linux/workqueue.h> +#include <linux/wait.h> +#include <linux/delay.h> +#include <linux/gfp.h> +#include <linux/skbuff.h> +#include <linux/dma-mapping.h> +#include <linux/etherdevice.h> +#include <linux/socket.h> +#include <linux/jiffies.h> +#include <net/ip6_checksum.h> +#include <net/pkt_cls.h> +#include <net/udp.h> +#include <net/tc_act/tc_gact.h> +#include <net/tc_act/tc_mirred.h> + +#include "iavf_type.h" +#include <linux/avf/virtchnl.h> +#include "iavf_txrx.h" + +#define DEFAULT_DEBUG_LEVEL_SHIFT 3 +#define PFX "iavf: " + +/* VSI state flags shared with common code */ +enum iavf_vsi_state_t { + __IAVF_VSI_DOWN, + /* This must be last as it determines the size of the BITMAP */ + __IAVF_VSI_STATE_SIZE__, +}; + +/* dummy struct to make common code less painful */ +struct iavf_vsi { + struct iavf_adapter *back; + struct net_device *netdev; + unsigned long active_vlans[BITS_TO_LONGS(VLAN_N_VID)]; + u16 seid; + u16 id; + DECLARE_BITMAP(state, __IAVF_VSI_STATE_SIZE__); + int base_vector; + u16 work_limit; + u16 qs_handle; + void *priv; /* client driver data reference. */ +}; + +/* How many Rx Buffers do we bundle into one write to the hardware ? */ +#define IAVF_RX_BUFFER_WRITE 16 /* Must be power of 2 */ +#define IAVF_DEFAULT_TXD 512 +#define IAVF_DEFAULT_RXD 512 +#define IAVF_MAX_TXD 4096 +#define IAVF_MIN_TXD 64 +#define IAVF_MAX_RXD 4096 +#define IAVF_MIN_RXD 64 +#define IAVF_REQ_DESCRIPTOR_MULTIPLE 32 +#define IAVF_MAX_AQ_BUF_SIZE 4096 +#define IAVF_AQ_LEN 32 +#define IAVF_AQ_MAX_ERR 20 /* times to try before resetting AQ */ + +#define MAXIMUM_ETHERNET_VLAN_SIZE (VLAN_ETH_FRAME_LEN + ETH_FCS_LEN) + +#define IAVF_RX_DESC(R, i) (&(((union iavf_32byte_rx_desc *)((R)->desc))[i])) +#define IAVF_TX_DESC(R, i) (&(((struct iavf_tx_desc *)((R)->desc))[i])) +#define IAVF_TX_CTXTDESC(R, i) \ + (&(((struct iavf_tx_context_desc *)((R)->desc))[i])) +#define IAVF_MAX_REQ_QUEUES 4 + +#define IAVF_HKEY_ARRAY_SIZE ((IAVF_VFQF_HKEY_MAX_INDEX + 1) * 4) +#define IAVF_HLUT_ARRAY_SIZE ((IAVF_VFQF_HLUT_MAX_INDEX + 1) * 4) +#define IAVF_MBPS_DIVISOR 125000 /* divisor to convert to Mbps */ + +/* MAX_MSIX_Q_VECTORS of these are allocated, + * but we only use one per queue-specific vector. + */ +struct iavf_q_vector { + struct iavf_adapter *adapter; + struct iavf_vsi *vsi; + struct napi_struct napi; + struct iavf_ring_container rx; + struct iavf_ring_container tx; + u32 ring_mask; + u8 itr_countdown; /* when 0 should adjust adaptive ITR */ + u8 num_ringpairs; /* total number of ring pairs in vector */ + u16 v_idx; /* index in the vsi->q_vector array. */ + u16 reg_idx; /* register index of the interrupt */ + char name[IFNAMSIZ + 15]; + bool arm_wb_state; + cpumask_t affinity_mask; + struct irq_affinity_notify affinity_notify; +}; + +/* Helper macros to switch between ints/sec and what the register uses. + * And yes, it's the same math going both ways. The lowest value + * supported by all of the i40e hardware is 8. + */ +#define EITR_INTS_PER_SEC_TO_REG(_eitr) \ + ((_eitr) ? (1000000000 / ((_eitr) * 256)) : 8) +#define EITR_REG_TO_INTS_PER_SEC EITR_INTS_PER_SEC_TO_REG + +#define IAVF_DESC_UNUSED(R) \ + ((((R)->next_to_clean > (R)->next_to_use) ? 0 : (R)->count) + \ + (R)->next_to_clean - (R)->next_to_use - 1) + +#define OTHER_VECTOR 1 +#define NONQ_VECS (OTHER_VECTOR) + +#define MIN_MSIX_Q_VECTORS 1 +#define MIN_MSIX_COUNT (MIN_MSIX_Q_VECTORS + NONQ_VECS) + +#define IAVF_QUEUE_END_OF_LIST 0x7FF +#define IAVF_FREE_VECTOR 0x7FFF +struct iavf_mac_filter { + struct list_head list; + u8 macaddr[ETH_ALEN]; + bool remove; /* filter needs to be removed */ + bool add; /* filter needs to be added */ +}; + +struct iavf_vlan_filter { + struct list_head list; + u16 vlan; + bool remove; /* filter needs to be removed */ + bool add; /* filter needs to be added */ +}; + +#define IAVF_MAX_TRAFFIC_CLASS 4 +/* State of traffic class creation */ +enum iavf_tc_state_t { + __IAVF_TC_INVALID, /* no traffic class, default state */ + __IAVF_TC_RUNNING, /* traffic classes have been created */ +}; + +/* channel info */ +struct iavf_channel_config { + struct virtchnl_channel_info ch_info[IAVF_MAX_TRAFFIC_CLASS]; + enum iavf_tc_state_t state; + u8 total_qps; +}; + +/* State of cloud filter */ +enum iavf_cloud_filter_state_t { + __IAVF_CF_INVALID, /* cloud filter not added */ + __IAVF_CF_ADD_PENDING, /* cloud filter pending add by the PF */ + __IAVF_CF_DEL_PENDING, /* cloud filter pending del by the PF */ + __IAVF_CF_ACTIVE, /* cloud filter is active */ +}; + +/* Driver state. The order of these is important! */ +enum iavf_state_t { + __IAVF_STARTUP, /* driver loaded, probe complete */ + __IAVF_REMOVE, /* driver is being unloaded */ + __IAVF_INIT_VERSION_CHECK, /* aq msg sent, awaiting reply */ + __IAVF_INIT_GET_RESOURCES, /* aq msg sent, awaiting reply */ + __IAVF_INIT_SW, /* got resources, setting up structs */ + __IAVF_RESETTING, /* in reset */ + /* Below here, watchdog is running */ + __IAVF_DOWN, /* ready, can be opened */ + __IAVF_DOWN_PENDING, /* descending, waiting for watchdog */ + __IAVF_TESTING, /* in ethtool self-test */ + __IAVF_RUNNING, /* opened, working */ +}; + +enum iavf_critical_section_t { + __IAVF_IN_CRITICAL_TASK, /* cannot be interrupted */ + __IAVF_IN_CLIENT_TASK, + __IAVF_IN_REMOVE_TASK, /* device being removed */ +}; + +#define IAVF_CLOUD_FIELD_OMAC 0x01 +#define IAVF_CLOUD_FIELD_IMAC 0x02 +#define IAVF_CLOUD_FIELD_IVLAN 0x04 +#define IAVF_CLOUD_FIELD_TEN_ID 0x08 +#define IAVF_CLOUD_FIELD_IIP 0x10 + +#define IAVF_CF_FLAGS_OMAC IAVF_CLOUD_FIELD_OMAC +#define IAVF_CF_FLAGS_IMAC IAVF_CLOUD_FIELD_IMAC +#define IAVF_CF_FLAGS_IMAC_IVLAN (IAVF_CLOUD_FIELD_IMAC |\ + IAVF_CLOUD_FIELD_IVLAN) +#define IAVF_CF_FLAGS_IMAC_TEN_ID (IAVF_CLOUD_FIELD_IMAC |\ + IAVF_CLOUD_FIELD_TEN_ID) +#define IAVF_CF_FLAGS_OMAC_TEN_ID_IMAC (IAVF_CLOUD_FIELD_OMAC |\ + IAVF_CLOUD_FIELD_IMAC |\ + IAVF_CLOUD_FIELD_TEN_ID) +#define IAVF_CF_FLAGS_IMAC_IVLAN_TEN_ID (IAVF_CLOUD_FIELD_IMAC |\ + IAVF_CLOUD_FIELD_IVLAN |\ + IAVF_CLOUD_FIELD_TEN_ID) +#define IAVF_CF_FLAGS_IIP IAVF_CLOUD_FIELD_IIP + +/* bookkeeping of cloud filters */ +struct iavf_cloud_filter { + enum iavf_cloud_filter_state_t state; + struct list_head list; + struct virtchnl_filter f; + unsigned long cookie; + bool del; /* filter needs to be deleted */ + bool add; /* filter needs to be added */ +}; + +/* board specific private data structure */ +struct iavf_adapter { + struct timer_list watchdog_timer; + struct work_struct reset_task; + struct work_struct adminq_task; + struct delayed_work client_task; + struct delayed_work init_task; + wait_queue_head_t down_waitqueue; + struct iavf_q_vector *q_vectors; + struct list_head vlan_filter_list; + struct list_head mac_filter_list; + /* Lock to protect accesses to MAC and VLAN lists */ + spinlock_t mac_vlan_list_lock; + char misc_vector_name[IFNAMSIZ + 9]; + int num_active_queues; + int num_req_queues; + + /* TX */ + struct iavf_ring *tx_rings; + u32 tx_timeout_count; + u32 tx_desc_count; + + /* RX */ + struct iavf_ring *rx_rings; + u64 hw_csum_rx_error; + u32 rx_desc_count; + int num_msix_vectors; + int num_iwarp_msix; + int iwarp_base_vector; + u32 client_pending; + struct i40e_client_instance *cinst; + struct msix_entry *msix_entries; + + u32 flags; +#define IAVF_FLAG_RX_CSUM_ENABLED BIT(0) +#define IAVF_FLAG_PF_COMMS_FAILED BIT(3) +#define IAVF_FLAG_RESET_PENDING BIT(4) +#define IAVF_FLAG_RESET_NEEDED BIT(5) +#define IAVF_FLAG_WB_ON_ITR_CAPABLE BIT(6) +#define IAVF_FLAG_ADDR_SET_BY_PF BIT(8) +#define IAVF_FLAG_SERVICE_CLIENT_REQUESTED BIT(9) +#define IAVF_FLAG_CLIENT_NEEDS_OPEN BIT(10) +#define IAVF_FLAG_CLIENT_NEEDS_CLOSE BIT(11) +#define IAVF_FLAG_CLIENT_NEEDS_L2_PARAMS BIT(12) +#define IAVF_FLAG_PROMISC_ON BIT(13) +#define IAVF_FLAG_ALLMULTI_ON BIT(14) +#define IAVF_FLAG_LEGACY_RX BIT(15) +#define IAVF_FLAG_REINIT_ITR_NEEDED BIT(16) +#define IAVF_FLAG_QUEUES_DISABLED BIT(17) +/* duplicates for common code */ +#define IAVF_FLAG_DCB_ENABLED 0 + /* flags for admin queue service task */ + u32 aq_required; +#define IAVF_FLAG_AQ_ENABLE_QUEUES BIT(0) +#define IAVF_FLAG_AQ_DISABLE_QUEUES BIT(1) +#define IAVF_FLAG_AQ_ADD_MAC_FILTER BIT(2) +#define IAVF_FLAG_AQ_ADD_VLAN_FILTER BIT(3) +#define IAVF_FLAG_AQ_DEL_MAC_FILTER BIT(4) +#define IAVF_FLAG_AQ_DEL_VLAN_FILTER BIT(5) +#define IAVF_FLAG_AQ_CONFIGURE_QUEUES BIT(6) +#define IAVF_FLAG_AQ_MAP_VECTORS BIT(7) +#define IAVF_FLAG_AQ_HANDLE_RESET BIT(8) +#define IAVF_FLAG_AQ_CONFIGURE_RSS BIT(9) /* direct AQ config */ +#define IAVF_FLAG_AQ_GET_CONFIG BIT(10) +/* Newer style, RSS done by the PF so we can ignore hardware vagaries. */ +#define IAVF_FLAG_AQ_GET_HENA BIT(11) +#define IAVF_FLAG_AQ_SET_HENA BIT(12) +#define IAVF_FLAG_AQ_SET_RSS_KEY BIT(13) +#define IAVF_FLAG_AQ_SET_RSS_LUT BIT(14) +#define IAVF_FLAG_AQ_REQUEST_PROMISC BIT(15) +#define IAVF_FLAG_AQ_RELEASE_PROMISC BIT(16) +#define IAVF_FLAG_AQ_REQUEST_ALLMULTI BIT(17) +#define IAVF_FLAG_AQ_RELEASE_ALLMULTI BIT(18) +#define IAVF_FLAG_AQ_ENABLE_VLAN_STRIPPING BIT(19) +#define IAVF_FLAG_AQ_DISABLE_VLAN_STRIPPING BIT(20) +#define IAVF_FLAG_AQ_ENABLE_CHANNELS BIT(21) +#define IAVF_FLAG_AQ_DISABLE_CHANNELS BIT(22) +#define IAVF_FLAG_AQ_ADD_CLOUD_FILTER BIT(23) +#define IAVF_FLAG_AQ_DEL_CLOUD_FILTER BIT(24) + + /* OS defined structs */ + struct net_device *netdev; + struct pci_dev *pdev; + + struct iavf_hw hw; /* defined in iavf_type.h */ + + enum iavf_state_t state; + unsigned long crit_section; + + struct work_struct watchdog_task; + bool netdev_registered; + bool link_up; + enum virtchnl_link_speed link_speed; + enum virtchnl_ops current_op; +#define CLIENT_ALLOWED(_a) ((_a)->vf_res ? \ + (_a)->vf_res->vf_cap_flags & \ + VIRTCHNL_VF_OFFLOAD_IWARP : \ + 0) +#define CLIENT_ENABLED(_a) ((_a)->cinst) +/* RSS by the PF should be preferred over RSS via other methods. */ +#define RSS_PF(_a) ((_a)->vf_res->vf_cap_flags & \ + VIRTCHNL_VF_OFFLOAD_RSS_PF) +#define RSS_AQ(_a) ((_a)->vf_res->vf_cap_flags & \ + VIRTCHNL_VF_OFFLOAD_RSS_AQ) +#define RSS_REG(_a) (!((_a)->vf_res->vf_cap_flags & \ + (VIRTCHNL_VF_OFFLOAD_RSS_AQ | \ + VIRTCHNL_VF_OFFLOAD_RSS_PF))) +#define VLAN_ALLOWED(_a) ((_a)->vf_res->vf_cap_flags & \ + VIRTCHNL_VF_OFFLOAD_VLAN) + struct virtchnl_vf_resource *vf_res; /* incl. all VSIs */ + struct virtchnl_vsi_resource *vsi_res; /* our LAN VSI */ + struct virtchnl_version_info pf_version; +#define PF_IS_V11(_a) (((_a)->pf_version.major == 1) && \ + ((_a)->pf_version.minor == 1)) + u16 msg_enable; + struct iavf_eth_stats current_stats; + struct iavf_vsi vsi; + u32 aq_wait_count; + /* RSS stuff */ + u64 hena; + u16 rss_key_size; + u16 rss_lut_size; + u8 *rss_key; + u8 *rss_lut; + /* ADQ related members */ + struct iavf_channel_config ch_config; + u8 num_tc; + struct list_head cloud_filter_list; + /* lock to protest access to the cloud filter list */ + spinlock_t cloud_filter_list_lock; + u16 num_cloud_filters; +}; + + +/* Ethtool Private Flags */ + +/* lan device, used by client interface */ +struct i40e_device { + struct list_head list; + struct iavf_adapter *vf; +}; + +/* needed by iavf_ethtool.c */ +extern char iavf_driver_name[]; +extern const char iavf_driver_version[]; + +int iavf_up(struct iavf_adapter *adapter); +void iavf_down(struct iavf_adapter *adapter); +int iavf_process_config(struct iavf_adapter *adapter); +void iavf_schedule_reset(struct iavf_adapter *adapter); +void iavf_reset(struct iavf_adapter *adapter); +void iavf_set_ethtool_ops(struct net_device *netdev); +void iavf_update_stats(struct iavf_adapter *adapter); +void iavf_reset_interrupt_capability(struct iavf_adapter *adapter); +int iavf_init_interrupt_scheme(struct iavf_adapter *adapter); +void iavf_irq_enable_queues(struct iavf_adapter *adapter, u32 mask); +void iavf_free_all_tx_resources(struct iavf_adapter *adapter); +void iavf_free_all_rx_resources(struct iavf_adapter *adapter); + +void iavf_napi_add_all(struct iavf_adapter *adapter); +void iavf_napi_del_all(struct iavf_adapter *adapter); + +int iavf_send_api_ver(struct iavf_adapter *adapter); +int iavf_verify_api_ver(struct iavf_adapter *adapter); +int iavf_send_vf_config_msg(struct iavf_adapter *adapter); +int iavf_get_vf_config(struct iavf_adapter *adapter); +void iavf_irq_enable(struct iavf_adapter *adapter, bool flush); +void iavf_configure_queues(struct iavf_adapter *adapter); +void iavf_deconfigure_queues(struct iavf_adapter *adapter); +void iavf_enable_queues(struct iavf_adapter *adapter); +void iavf_disable_queues(struct iavf_adapter *adapter); +void iavf_map_queues(struct iavf_adapter *adapter); +int iavf_request_queues(struct iavf_adapter *adapter, int num); +void iavf_add_ether_addrs(struct iavf_adapter *adapter); +void iavf_del_ether_addrs(struct iavf_adapter *adapter); +void iavf_add_vlans(struct iavf_adapter *adapter); +void iavf_del_vlans(struct iavf_adapter *adapter); +void iavf_set_promiscuous(struct iavf_adapter *adapter, int flags); +void iavf_request_stats(struct iavf_adapter *adapter); +void iavf_request_reset(struct iavf_adapter *adapter); +void iavf_get_hena(struct iavf_adapter *adapter); +void iavf_set_hena(struct iavf_adapter *adapter); +void iavf_set_rss_key(struct iavf_adapter *adapter); +void iavf_set_rss_lut(struct iavf_adapter *adapter); +void iavf_enable_vlan_stripping(struct iavf_adapter *adapter); +void iavf_disable_vlan_stripping(struct iavf_adapter *adapter); +void iavf_virtchnl_completion(struct iavf_adapter *adapter, + enum virtchnl_ops v_opcode, + iavf_status v_retval, u8 *msg, u16 msglen); +int iavf_config_rss(struct iavf_adapter *adapter); +int iavf_lan_add_device(struct iavf_adapter *adapter); +int iavf_lan_del_device(struct iavf_adapter *adapter); +void iavf_client_subtask(struct iavf_adapter *adapter); +void iavf_notify_client_message(struct iavf_vsi *vsi, u8 *msg, u16 len); +void iavf_notify_client_l2_params(struct iavf_vsi *vsi); +void iavf_notify_client_open(struct iavf_vsi *vsi); +void iavf_notify_client_close(struct iavf_vsi *vsi, bool reset); +void iavf_enable_channels(struct iavf_adapter *adapter); +void iavf_disable_channels(struct iavf_adapter *adapter); +void iavf_add_cloud_filter(struct iavf_adapter *adapter); +void iavf_del_cloud_filter(struct iavf_adapter *adapter); +#endif /* _IAVF_H_ */ diff --git a/drivers/net/ethernet/intel/iavf/iavf_alloc.h b/drivers/net/ethernet/intel/iavf/iavf_alloc.h new file mode 100644 index 000000000000..bf2753146f30 --- /dev/null +++ b/drivers/net/ethernet/intel/iavf/iavf_alloc.h @@ -0,0 +1,31 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright(c) 2013 - 2018 Intel Corporation. */ + +#ifndef _IAVF_ALLOC_H_ +#define _IAVF_ALLOC_H_ + +struct iavf_hw; + +/* Memory allocation types */ +enum iavf_memory_type { + iavf_mem_arq_buf = 0, /* ARQ indirect command buffer */ + iavf_mem_asq_buf = 1, + iavf_mem_atq_buf = 2, /* ATQ indirect command buffer */ + iavf_mem_arq_ring = 3, /* ARQ descriptor ring */ + iavf_mem_atq_ring = 4, /* ATQ descriptor ring */ + iavf_mem_pd = 5, /* Page Descriptor */ + iavf_mem_bp = 6, /* Backing Page - 4KB */ + iavf_mem_bp_jumbo = 7, /* Backing Page - > 4KB */ + iavf_mem_reserved +}; + +/* prototype for functions used for dynamic memory allocation */ +iavf_status iavf_allocate_dma_mem(struct iavf_hw *hw, struct iavf_dma_mem *mem, + enum iavf_memory_type type, + u64 size, u32 alignment); +iavf_status iavf_free_dma_mem(struct iavf_hw *hw, struct iavf_dma_mem *mem); +iavf_status iavf_allocate_virt_mem(struct iavf_hw *hw, + struct iavf_virt_mem *mem, u32 size); +iavf_status iavf_free_virt_mem(struct iavf_hw *hw, struct iavf_virt_mem *mem); + +#endif /* _IAVF_ALLOC_H_ */ diff --git a/drivers/net/ethernet/intel/i40evf/i40evf_client.c b/drivers/net/ethernet/intel/iavf/iavf_client.c index 3cc9d60d0d72..aea45364fd1c 100644 --- a/drivers/net/ethernet/intel/i40evf/i40evf_client.c +++ b/drivers/net/ethernet/intel/iavf/iavf_client.c @@ -4,36 +4,36 @@ #include <linux/list.h> #include <linux/errno.h> -#include "i40evf.h" -#include "i40e_prototype.h" -#include "i40evf_client.h" +#include "iavf.h" +#include "iavf_prototype.h" +#include "iavf_client.h" static -const char i40evf_client_interface_version_str[] = I40EVF_CLIENT_VERSION_STR; +const char iavf_client_interface_version_str[] = IAVF_CLIENT_VERSION_STR; static struct i40e_client *vf_registered_client; -static LIST_HEAD(i40evf_devices); -static DEFINE_MUTEX(i40evf_device_mutex); +static LIST_HEAD(i40e_devices); +static DEFINE_MUTEX(iavf_device_mutex); -static u32 i40evf_client_virtchnl_send(struct i40e_info *ldev, - struct i40e_client *client, - u8 *msg, u16 len); +static u32 iavf_client_virtchnl_send(struct i40e_info *ldev, + struct i40e_client *client, + u8 *msg, u16 len); -static int i40evf_client_setup_qvlist(struct i40e_info *ldev, - struct i40e_client *client, - struct i40e_qvlist_info *qvlist_info); +static int iavf_client_setup_qvlist(struct i40e_info *ldev, + struct i40e_client *client, + struct i40e_qvlist_info *qvlist_info); -static struct i40e_ops i40evf_lan_ops = { - .virtchnl_send = i40evf_client_virtchnl_send, - .setup_qvlist = i40evf_client_setup_qvlist, +static struct i40e_ops iavf_lan_ops = { + .virtchnl_send = iavf_client_virtchnl_send, + .setup_qvlist = iavf_client_setup_qvlist, }; /** - * i40evf_client_get_params - retrieve relevant client parameters + * iavf_client_get_params - retrieve relevant client parameters * @vsi: VSI with parameters * @params: client param struct **/ static -void i40evf_client_get_params(struct i40e_vsi *vsi, struct i40e_params *params) +void iavf_client_get_params(struct iavf_vsi *vsi, struct i40e_params *params) { int i; @@ -41,21 +41,21 @@ void i40evf_client_get_params(struct i40e_vsi *vsi, struct i40e_params *params) params->mtu = vsi->netdev->mtu; params->link_up = vsi->back->link_up; - for (i = 0; i < I40E_MAX_USER_PRIORITY; i++) { + for (i = 0; i < IAVF_MAX_USER_PRIORITY; i++) { params->qos.prio_qos[i].tc = 0; params->qos.prio_qos[i].qs_handle = vsi->qs_handle; } } /** - * i40evf_notify_client_message - call the client message receive callback + * iavf_notify_client_message - call the client message receive callback * @vsi: the VSI associated with this client * @msg: message buffer * @len: length of message * * If there is a client to this VSI, call the client **/ -void i40evf_notify_client_message(struct i40e_vsi *vsi, u8 *msg, u16 len) +void iavf_notify_client_message(struct iavf_vsi *vsi, u8 *msg, u16 len) { struct i40e_client_instance *cinst; @@ -74,12 +74,12 @@ void i40evf_notify_client_message(struct i40e_vsi *vsi, u8 *msg, u16 len) } /** - * i40evf_notify_client_l2_params - call the client notify callback + * iavf_notify_client_l2_params - call the client notify callback * @vsi: the VSI with l2 param changes * * If there is a client to this VSI, call the client **/ -void i40evf_notify_client_l2_params(struct i40e_vsi *vsi) +void iavf_notify_client_l2_params(struct iavf_vsi *vsi) { struct i40e_client_instance *cinst; struct i40e_params params; @@ -95,21 +95,21 @@ void i40evf_notify_client_l2_params(struct i40e_vsi *vsi) "Cannot locate client instance l2_param_change function\n"); return; } - i40evf_client_get_params(vsi, ¶ms); + iavf_client_get_params(vsi, ¶ms); cinst->lan_info.params = params; cinst->client->ops->l2_param_change(&cinst->lan_info, cinst->client, ¶ms); } /** - * i40evf_notify_client_open - call the client open callback + * iavf_notify_client_open - call the client open callback * @vsi: the VSI with netdev opened * * If there is a client to this netdev, call the client with open **/ -void i40evf_notify_client_open(struct i40e_vsi *vsi) +void iavf_notify_client_open(struct iavf_vsi *vsi) { - struct i40evf_adapter *adapter = vsi->back; + struct iavf_adapter *adapter = vsi->back; struct i40e_client_instance *cinst = adapter->cinst; int ret; @@ -127,22 +127,22 @@ void i40evf_notify_client_open(struct i40e_vsi *vsi) } /** - * i40evf_client_release_qvlist - send a message to the PF to release iwarp qv map + * iavf_client_release_qvlist - send a message to the PF to release iwarp qv map * @ldev: pointer to L2 context. * * Return 0 on success or < 0 on error **/ -static int i40evf_client_release_qvlist(struct i40e_info *ldev) +static int iavf_client_release_qvlist(struct i40e_info *ldev) { - struct i40evf_adapter *adapter = ldev->vf; - i40e_status err; + struct iavf_adapter *adapter = ldev->vf; + iavf_status err; if (adapter->aq_required) return -EAGAIN; - err = i40e_aq_send_msg_to_pf(&adapter->hw, - VIRTCHNL_OP_RELEASE_IWARP_IRQ_MAP, - I40E_SUCCESS, NULL, 0, NULL); + err = iavf_aq_send_msg_to_pf(&adapter->hw, + VIRTCHNL_OP_RELEASE_IWARP_IRQ_MAP, + I40E_SUCCESS, NULL, 0, NULL); if (err) dev_err(&adapter->pdev->dev, @@ -153,15 +153,15 @@ static int i40evf_client_release_qvlist(struct i40e_info *ldev) } /** - * i40evf_notify_client_close - call the client close callback + * iavf_notify_client_close - call the client close callback * @vsi: the VSI with netdev closed * @reset: true when close called due to reset pending * * If there is a client to this netdev, call the client with close **/ -void i40evf_notify_client_close(struct i40e_vsi *vsi, bool reset) +void iavf_notify_client_close(struct iavf_vsi *vsi, bool reset) { - struct i40evf_adapter *adapter = vsi->back; + struct iavf_adapter *adapter = vsi->back; struct i40e_client_instance *cinst = adapter->cinst; if (!cinst || !cinst->client || !cinst->client->ops || @@ -171,21 +171,21 @@ void i40evf_notify_client_close(struct i40e_vsi *vsi, bool reset) return; } cinst->client->ops->close(&cinst->lan_info, cinst->client, reset); - i40evf_client_release_qvlist(&cinst->lan_info); + iavf_client_release_qvlist(&cinst->lan_info); clear_bit(__I40E_CLIENT_INSTANCE_OPENED, &cinst->state); } /** - * i40evf_client_add_instance - add a client instance to the instance list + * iavf_client_add_instance - add a client instance to the instance list * @adapter: pointer to the board struct * * Returns cinst ptr on success, NULL on failure **/ static struct i40e_client_instance * -i40evf_client_add_instance(struct i40evf_adapter *adapter) +iavf_client_add_instance(struct iavf_adapter *adapter) { struct i40e_client_instance *cinst = NULL; - struct i40e_vsi *vsi = &adapter->vsi; + struct iavf_vsi *vsi = &adapter->vsi; struct netdev_hw_addr *mac = NULL; struct i40e_params params; @@ -207,11 +207,11 @@ i40evf_client_add_instance(struct i40evf_adapter *adapter) cinst->lan_info.fid = 0; cinst->lan_info.ftype = I40E_CLIENT_FTYPE_VF; cinst->lan_info.hw_addr = adapter->hw.hw_addr; - cinst->lan_info.ops = &i40evf_lan_ops; - cinst->lan_info.version.major = I40EVF_CLIENT_VERSION_MAJOR; - cinst->lan_info.version.minor = I40EVF_CLIENT_VERSION_MINOR; - cinst->lan_info.version.build = I40EVF_CLIENT_VERSION_BUILD; - i40evf_client_get_params(vsi, ¶ms); + cinst->lan_info.ops = &iavf_lan_ops; + cinst->lan_info.version.major = IAVF_CLIENT_VERSION_MAJOR; + cinst->lan_info.version.minor = IAVF_CLIENT_VERSION_MINOR; + cinst->lan_info.version.build = IAVF_CLIENT_VERSION_BUILD; + iavf_client_get_params(vsi, ¶ms); cinst->lan_info.params = params; set_bit(__I40E_CLIENT_INSTANCE_NONE, &cinst->state); @@ -233,28 +233,28 @@ out: } /** - * i40evf_client_del_instance - removes a client instance from the list + * iavf_client_del_instance - removes a client instance from the list * @adapter: pointer to the board struct * **/ static -void i40evf_client_del_instance(struct i40evf_adapter *adapter) +void iavf_client_del_instance(struct iavf_adapter *adapter) { kfree(adapter->cinst); adapter->cinst = NULL; } /** - * i40evf_client_subtask - client maintenance work + * iavf_client_subtask - client maintenance work * @adapter: board private structure **/ -void i40evf_client_subtask(struct i40evf_adapter *adapter) +void iavf_client_subtask(struct iavf_adapter *adapter) { struct i40e_client *client = vf_registered_client; struct i40e_client_instance *cinst; int ret = 0; - if (adapter->state < __I40EVF_DOWN) + if (adapter->state < __IAVF_DOWN) return; /* first check client is registered */ @@ -262,7 +262,7 @@ void i40evf_client_subtask(struct i40evf_adapter *adapter) return; /* Add the client instance to the instance list */ - cinst = i40evf_client_add_instance(adapter); + cinst = iavf_client_add_instance(adapter); if (!cinst) return; @@ -279,23 +279,23 @@ void i40evf_client_subtask(struct i40evf_adapter *adapter) &cinst->state); else /* remove client instance */ - i40evf_client_del_instance(adapter); + iavf_client_del_instance(adapter); } } /** - * i40evf_lan_add_device - add a lan device struct to the list of lan devices + * iavf_lan_add_device - add a lan device struct to the list of lan devices * @adapter: pointer to the board struct * * Returns 0 on success or none 0 on error **/ -int i40evf_lan_add_device(struct i40evf_adapter *adapter) +int iavf_lan_add_device(struct iavf_adapter *adapter) { struct i40e_device *ldev; int ret = 0; - mutex_lock(&i40evf_device_mutex); - list_for_each_entry(ldev, &i40evf_devices, list) { + mutex_lock(&iavf_device_mutex); + list_for_each_entry(ldev, &i40e_devices, list) { if (ldev->vf == adapter) { ret = -EEXIST; goto out; @@ -308,7 +308,7 @@ int i40evf_lan_add_device(struct i40evf_adapter *adapter) } ldev->vf = adapter; INIT_LIST_HEAD(&ldev->list); - list_add(&ldev->list, &i40evf_devices); + list_add(&ldev->list, &i40e_devices); dev_info(&adapter->pdev->dev, "Added LAN device bus=0x%02x dev=0x%02x func=0x%02x\n", adapter->hw.bus.bus_id, adapter->hw.bus.device, adapter->hw.bus.func); @@ -316,26 +316,26 @@ int i40evf_lan_add_device(struct i40evf_adapter *adapter) /* Since in some cases register may have happened before a device gets * added, we can schedule a subtask to go initiate the clients. */ - adapter->flags |= I40EVF_FLAG_SERVICE_CLIENT_REQUESTED; + adapter->flags |= IAVF_FLAG_SERVICE_CLIENT_REQUESTED; out: - mutex_unlock(&i40evf_device_mutex); + mutex_unlock(&iavf_device_mutex); return ret; } /** - * i40evf_lan_del_device - removes a lan device from the device list + * iavf_lan_del_device - removes a lan device from the device list * @adapter: pointer to the board struct * * Returns 0 on success or non-0 on error **/ -int i40evf_lan_del_device(struct i40evf_adapter *adapter) +int iavf_lan_del_device(struct iavf_adapter *adapter) { struct i40e_device *ldev, *tmp; int ret = -ENODEV; - mutex_lock(&i40evf_device_mutex); - list_for_each_entry_safe(ldev, tmp, &i40evf_devices, list) { + mutex_lock(&iavf_device_mutex); + list_for_each_entry_safe(ldev, tmp, &i40e_devices, list) { if (ldev->vf == adapter) { dev_info(&adapter->pdev->dev, "Deleted LAN device bus=0x%02x dev=0x%02x func=0x%02x\n", @@ -348,23 +348,23 @@ int i40evf_lan_del_device(struct i40evf_adapter *adapter) } } - mutex_unlock(&i40evf_device_mutex); + mutex_unlock(&iavf_device_mutex); return ret; } /** - * i40evf_client_release - release client specific resources + * iavf_client_release - release client specific resources * @client: pointer to the registered client * **/ -static void i40evf_client_release(struct i40e_client *client) +static void iavf_client_release(struct i40e_client *client) { struct i40e_client_instance *cinst; struct i40e_device *ldev; - struct i40evf_adapter *adapter; + struct iavf_adapter *adapter; - mutex_lock(&i40evf_device_mutex); - list_for_each_entry(ldev, &i40evf_devices, list) { + mutex_lock(&iavf_device_mutex); + list_for_each_entry(ldev, &i40e_devices, list) { adapter = ldev->vf; cinst = adapter->cinst; if (!cinst) @@ -373,41 +373,41 @@ static void i40evf_client_release(struct i40e_client *client) if (client->ops && client->ops->close) client->ops->close(&cinst->lan_info, client, false); - i40evf_client_release_qvlist(&cinst->lan_info); + iavf_client_release_qvlist(&cinst->lan_info); clear_bit(__I40E_CLIENT_INSTANCE_OPENED, &cinst->state); dev_warn(&adapter->pdev->dev, "Client %s instance closed\n", client->name); } /* delete the client instance */ - i40evf_client_del_instance(adapter); + iavf_client_del_instance(adapter); dev_info(&adapter->pdev->dev, "Deleted client instance of Client %s\n", client->name); } - mutex_unlock(&i40evf_device_mutex); + mutex_unlock(&iavf_device_mutex); } /** - * i40evf_client_prepare - prepare client specific resources + * iavf_client_prepare - prepare client specific resources * @client: pointer to the registered client * **/ -static void i40evf_client_prepare(struct i40e_client *client) +static void iavf_client_prepare(struct i40e_client *client) { struct i40e_device *ldev; - struct i40evf_adapter *adapter; + struct iavf_adapter *adapter; - mutex_lock(&i40evf_device_mutex); - list_for_each_entry(ldev, &i40evf_devices, list) { + mutex_lock(&iavf_device_mutex); + list_for_each_entry(ldev, &i40e_devices, list) { adapter = ldev->vf; /* Signal the watchdog to service the client */ - adapter->flags |= I40EVF_FLAG_SERVICE_CLIENT_REQUESTED; + adapter->flags |= IAVF_FLAG_SERVICE_CLIENT_REQUESTED; } - mutex_unlock(&i40evf_device_mutex); + mutex_unlock(&iavf_device_mutex); } /** - * i40evf_client_virtchnl_send - send a message to the PF instance + * iavf_client_virtchnl_send - send a message to the PF instance * @ldev: pointer to L2 context. * @client: Client pointer. * @msg: pointer to message buffer @@ -415,17 +415,17 @@ static void i40evf_client_prepare(struct i40e_client *client) * * Return 0 on success or < 0 on error **/ -static u32 i40evf_client_virtchnl_send(struct i40e_info *ldev, - struct i40e_client *client, - u8 *msg, u16 len) +static u32 iavf_client_virtchnl_send(struct i40e_info *ldev, + struct i40e_client *client, + u8 *msg, u16 len) { - struct i40evf_adapter *adapter = ldev->vf; - i40e_status err; + struct iavf_adapter *adapter = ldev->vf; + iavf_status err; if (adapter->aq_required) return -EAGAIN; - err = i40e_aq_send_msg_to_pf(&adapter->hw, VIRTCHNL_OP_IWARP, + err = iavf_aq_send_msg_to_pf(&adapter->hw, VIRTCHNL_OP_IWARP, I40E_SUCCESS, msg, len, NULL); if (err) dev_err(&adapter->pdev->dev, "Unable to send iWarp message to PF, error %d, aq status %d\n", @@ -435,21 +435,21 @@ static u32 i40evf_client_virtchnl_send(struct i40e_info *ldev, } /** - * i40evf_client_setup_qvlist - send a message to the PF to setup iwarp qv map + * iavf_client_setup_qvlist - send a message to the PF to setup iwarp qv map * @ldev: pointer to L2 context. * @client: Client pointer. * @qvlist_info: queue and vector list * * Return 0 on success or < 0 on error **/ -static int i40evf_client_setup_qvlist(struct i40e_info *ldev, - struct i40e_client *client, - struct i40e_qvlist_info *qvlist_info) +static int iavf_client_setup_qvlist(struct i40e_info *ldev, + struct i40e_client *client, + struct i40e_qvlist_info *qvlist_info) { struct virtchnl_iwarp_qvlist_info *v_qvlist_info; - struct i40evf_adapter *adapter = ldev->vf; + struct iavf_adapter *adapter = ldev->vf; struct i40e_qv_info *qv_info; - i40e_status err; + iavf_status err; u32 v_idx, i; u32 msg_size; @@ -474,9 +474,9 @@ static int i40evf_client_setup_qvlist(struct i40e_info *ldev, (v_qvlist_info->num_vectors - 1)); adapter->client_pending |= BIT(VIRTCHNL_OP_CONFIG_IWARP_IRQ_MAP); - err = i40e_aq_send_msg_to_pf(&adapter->hw, - VIRTCHNL_OP_CONFIG_IWARP_IRQ_MAP, - I40E_SUCCESS, (u8 *)v_qvlist_info, msg_size, NULL); + err = iavf_aq_send_msg_to_pf(&adapter->hw, + VIRTCHNL_OP_CONFIG_IWARP_IRQ_MAP, I40E_SUCCESS, + (u8 *)v_qvlist_info, msg_size, NULL); if (err) { dev_err(&adapter->pdev->dev, @@ -499,12 +499,12 @@ out: } /** - * i40evf_register_client - Register a i40e client driver with the L2 driver + * iavf_register_client - Register a i40e client driver with the L2 driver * @client: pointer to the i40e_client struct * * Returns 0 on success or non-0 on error **/ -int i40evf_register_client(struct i40e_client *client) +int iavf_register_client(struct i40e_client *client) { int ret = 0; @@ -514,48 +514,48 @@ int i40evf_register_client(struct i40e_client *client) } if (strlen(client->name) == 0) { - pr_info("i40evf: Failed to register client with no name\n"); + pr_info("iavf: Failed to register client with no name\n"); ret = -EIO; goto out; } if (vf_registered_client) { - pr_info("i40evf: Client %s has already been registered!\n", + pr_info("iavf: Client %s has already been registered!\n", client->name); ret = -EEXIST; goto out; } - if ((client->version.major != I40EVF_CLIENT_VERSION_MAJOR) || - (client->version.minor != I40EVF_CLIENT_VERSION_MINOR)) { - pr_info("i40evf: Failed to register client %s due to mismatched client interface version\n", + if ((client->version.major != IAVF_CLIENT_VERSION_MAJOR) || + (client->version.minor != IAVF_CLIENT_VERSION_MINOR)) { + pr_info("iavf: Failed to register client %s due to mismatched client interface version\n", client->name); pr_info("Client is using version: %02d.%02d.%02d while LAN driver supports %s\n", client->version.major, client->version.minor, client->version.build, - i40evf_client_interface_version_str); + iavf_client_interface_version_str); ret = -EIO; goto out; } vf_registered_client = client; - i40evf_client_prepare(client); + iavf_client_prepare(client); - pr_info("i40evf: Registered client %s with return code %d\n", + pr_info("iavf: Registered client %s with return code %d\n", client->name, ret); out: return ret; } -EXPORT_SYMBOL(i40evf_register_client); +EXPORT_SYMBOL(iavf_register_client); /** - * i40evf_unregister_client - Unregister a i40e client driver with the L2 driver + * iavf_unregister_client - Unregister a i40e client driver with the L2 driver * @client: pointer to the i40e_client struct * * Returns 0 on success or non-0 on error **/ -int i40evf_unregister_client(struct i40e_client *client) +int iavf_unregister_client(struct i40e_client *client) { int ret = 0; @@ -563,17 +563,17 @@ int i40evf_unregister_client(struct i40e_client *client) * a close for each of the client instances that were opened. * client_release function is called to handle this. */ - i40evf_client_release(client); + iavf_client_release(client); if (vf_registered_client != client) { - pr_info("i40evf: Client %s has not been registered\n", + pr_info("iavf: Client %s has not been registered\n", client->name); ret = -ENODEV; goto out; } vf_registered_client = NULL; - pr_info("i40evf: Unregistered client %s\n", client->name); + pr_info("iavf: Unregistered client %s\n", client->name); out: return ret; } -EXPORT_SYMBOL(i40evf_unregister_client); +EXPORT_SYMBOL(iavf_unregister_client); diff --git a/drivers/net/ethernet/intel/i40evf/i40evf_client.h b/drivers/net/ethernet/intel/iavf/iavf_client.h index 5585f362048a..e216fc9dfd81 100644 --- a/drivers/net/ethernet/intel/i40evf/i40evf_client.h +++ b/drivers/net/ethernet/intel/iavf/iavf_client.h @@ -1,21 +1,21 @@ /* SPDX-License-Identifier: GPL-2.0 */ /* Copyright(c) 2013 - 2018 Intel Corporation. */ -#ifndef _I40EVF_CLIENT_H_ -#define _I40EVF_CLIENT_H_ +#ifndef _IAVF_CLIENT_H_ +#define _IAVF_CLIENT_H_ -#define I40EVF_CLIENT_STR_LENGTH 10 +#define IAVF_CLIENT_STR_LENGTH 10 /* Client interface version should be updated anytime there is a change in the * existing APIs or data structures. */ -#define I40EVF_CLIENT_VERSION_MAJOR 0 -#define I40EVF_CLIENT_VERSION_MINOR 01 -#define I40EVF_CLIENT_VERSION_BUILD 00 -#define I40EVF_CLIENT_VERSION_STR \ - __stringify(I40EVF_CLIENT_VERSION_MAJOR) "." \ - __stringify(I40EVF_CLIENT_VERSION_MINOR) "." \ - __stringify(I40EVF_CLIENT_VERSION_BUILD) +#define IAVF_CLIENT_VERSION_MAJOR 0 +#define IAVF_CLIENT_VERSION_MINOR 01 +#define IAVF_CLIENT_VERSION_BUILD 00 +#define IAVF_CLIENT_VERSION_STR \ + __stringify(IAVF_CLIENT_VERSION_MAJOR) "." \ + __stringify(IAVF_CLIENT_VERSION_MINOR) "." \ + __stringify(IAVF_CLIENT_VERSION_BUILD) struct i40e_client_version { u8 major; @@ -90,7 +90,7 @@ struct i40e_info { #define I40E_CLIENT_FTYPE_PF 0 #define I40E_CLIENT_FTYPE_VF 1 u8 ftype; /* function type, PF or VF */ - void *vf; /* cast to i40evf_adapter */ + void *vf; /* cast to iavf_adapter */ /* All L2 params that could change during the life span of the device * and needs to be communicated to the client when they change @@ -151,7 +151,7 @@ struct i40e_client_instance { struct i40e_client { struct list_head list; /* list of registered clients */ - char name[I40EVF_CLIENT_STR_LENGTH]; + char name[IAVF_CLIENT_STR_LENGTH]; struct i40e_client_version version; unsigned long state; /* client state */ atomic_t ref_cnt; /* Count of all the client devices of this kind */ @@ -164,6 +164,6 @@ struct i40e_client { }; /* used by clients */ -int i40evf_register_client(struct i40e_client *client); -int i40evf_unregister_client(struct i40e_client *client); -#endif /* _I40EVF_CLIENT_H_ */ +int iavf_register_client(struct i40e_client *client); +int iavf_unregister_client(struct i40e_client *client); +#endif /* _IAVF_CLIENT_H_ */ diff --git a/drivers/net/ethernet/intel/iavf/iavf_common.c b/drivers/net/ethernet/intel/iavf/iavf_common.c new file mode 100644 index 000000000000..768369c89e77 --- /dev/null +++ b/drivers/net/ethernet/intel/iavf/iavf_common.c @@ -0,0 +1,955 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright(c) 2013 - 2018 Intel Corporation. */ + +#include "iavf_type.h" +#include "i40e_adminq.h" +#include "iavf_prototype.h" +#include <linux/avf/virtchnl.h> + +/** + * iavf_set_mac_type - Sets MAC type + * @hw: pointer to the HW structure + * + * This function sets the mac type of the adapter based on the + * vendor ID and device ID stored in the hw structure. + **/ +iavf_status iavf_set_mac_type(struct iavf_hw *hw) +{ + iavf_status status = 0; + + if (hw->vendor_id == PCI_VENDOR_ID_INTEL) { + switch (hw->device_id) { + case IAVF_DEV_ID_X722_VF: + hw->mac.type = IAVF_MAC_X722_VF; + break; + case IAVF_DEV_ID_VF: + case IAVF_DEV_ID_VF_HV: + case IAVF_DEV_ID_ADAPTIVE_VF: + hw->mac.type = IAVF_MAC_VF; + break; + default: + hw->mac.type = IAVF_MAC_GENERIC; + break; + } + } else { + status = I40E_ERR_DEVICE_NOT_SUPPORTED; + } + + hw_dbg(hw, "found mac: %d, returns: %d\n", hw->mac.type, status); + return status; +} + +/** + * iavf_aq_str - convert AQ err code to a string + * @hw: pointer to the HW structure + * @aq_err: the AQ error code to convert + **/ +const char *iavf_aq_str(struct iavf_hw *hw, enum i40e_admin_queue_err aq_err) +{ + switch (aq_err) { + case I40E_AQ_RC_OK: + return "OK"; + case I40E_AQ_RC_EPERM: + return "I40E_AQ_RC_EPERM"; + case I40E_AQ_RC_ENOENT: + return "I40E_AQ_RC_ENOENT"; + case I40E_AQ_RC_ESRCH: + return "I40E_AQ_RC_ESRCH"; + case I40E_AQ_RC_EINTR: + return "I40E_AQ_RC_EINTR"; + case I40E_AQ_RC_EIO: + return "I40E_AQ_RC_EIO"; + case I40E_AQ_RC_ENXIO: + return "I40E_AQ_RC_ENXIO"; + case I40E_AQ_RC_E2BIG: + return "I40E_AQ_RC_E2BIG"; + case I40E_AQ_RC_EAGAIN: + return "I40E_AQ_RC_EAGAIN"; + case I40E_AQ_RC_ENOMEM: + return "I40E_AQ_RC_ENOMEM"; + case I40E_AQ_RC_EACCES: + return "I40E_AQ_RC_EACCES"; + case I40E_AQ_RC_EFAULT: + return "I40E_AQ_RC_EFAULT"; + case I40E_AQ_RC_EBUSY: + return "I40E_AQ_RC_EBUSY"; + case I40E_AQ_RC_EEXIST: + return "I40E_AQ_RC_EEXIST"; + case I40E_AQ_RC_EINVAL: + return "I40E_AQ_RC_EINVAL"; + case I40E_AQ_RC_ENOTTY: + return "I40E_AQ_RC_ENOTTY"; + case I40E_AQ_RC_ENOSPC: + return "I40E_AQ_RC_ENOSPC"; + case I40E_AQ_RC_ENOSYS: + return "I40E_AQ_RC_ENOSYS"; + case I40E_AQ_RC_ERANGE: + return "I40E_AQ_RC_ERANGE"; + case I40E_AQ_RC_EFLUSHED: + return "I40E_AQ_RC_EFLUSHED"; + case I40E_AQ_RC_BAD_ADDR: + return "I40E_AQ_RC_BAD_ADDR"; + case I40E_AQ_RC_EMODE: + return "I40E_AQ_RC_EMODE"; + case I40E_AQ_RC_EFBIG: + return "I40E_AQ_RC_EFBIG"; + } + + snprintf(hw->err_str, sizeof(hw->err_str), "%d", aq_err); + return hw->err_str; +} + +/** + * iavf_stat_str - convert status err code to a string + * @hw: pointer to the HW structure + * @stat_err: the status error code to convert + **/ +const char *iavf_stat_str(struct iavf_hw *hw, iavf_status stat_err) +{ + switch (stat_err) { + case 0: + return "OK"; + case I40E_ERR_NVM: + return "I40E_ERR_NVM"; + case I40E_ERR_NVM_CHECKSUM: + return "I40E_ERR_NVM_CHECKSUM"; + case I40E_ERR_PHY: + return "I40E_ERR_PHY"; + case I40E_ERR_CONFIG: + return "I40E_ERR_CONFIG"; + case I40E_ERR_PARAM: + return "I40E_ERR_PARAM"; + case I40E_ERR_MAC_TYPE: + return "I40E_ERR_MAC_TYPE"; + case I40E_ERR_UNKNOWN_PHY: + return "I40E_ERR_UNKNOWN_PHY"; + case I40E_ERR_LINK_SETUP: + return "I40E_ERR_LINK_SETUP"; + case I40E_ERR_ADAPTER_STOPPED: + return "I40E_ERR_ADAPTER_STOPPED"; + case I40E_ERR_INVALID_MAC_ADDR: + return "I40E_ERR_INVALID_MAC_ADDR"; + case I40E_ERR_DEVICE_NOT_SUPPORTED: + return "I40E_ERR_DEVICE_NOT_SUPPORTED"; + case I40E_ERR_MASTER_REQUESTS_PENDING: + return "I40E_ERR_MASTER_REQUESTS_PENDING"; + case I40E_ERR_INVALID_LINK_SETTINGS: + return "I40E_ERR_INVALID_LINK_SETTINGS"; + case I40E_ERR_AUTONEG_NOT_COMPLETE: + return "I40E_ERR_AUTONEG_NOT_COMPLETE"; + case I40E_ERR_RESET_FAILED: + return "I40E_ERR_RESET_FAILED"; + case I40E_ERR_SWFW_SYNC: + return "I40E_ERR_SWFW_SYNC"; + case I40E_ERR_NO_AVAILABLE_VSI: + return "I40E_ERR_NO_AVAILABLE_VSI"; + case I40E_ERR_NO_MEMORY: + return "I40E_ERR_NO_MEMORY"; + case I40E_ERR_BAD_PTR: + return "I40E_ERR_BAD_PTR"; + case I40E_ERR_RING_FULL: + return "I40E_ERR_RING_FULL"; + case I40E_ERR_INVALID_PD_ID: + return "I40E_ERR_INVALID_PD_ID"; + case I40E_ERR_INVALID_QP_ID: + return "I40E_ERR_INVALID_QP_ID"; + case I40E_ERR_INVALID_CQ_ID: + return "I40E_ERR_INVALID_CQ_ID"; + case I40E_ERR_INVALID_CEQ_ID: + return "I40E_ERR_INVALID_CEQ_ID"; + case I40E_ERR_INVALID_AEQ_ID: + return "I40E_ERR_INVALID_AEQ_ID"; + case I40E_ERR_INVALID_SIZE: + return "I40E_ERR_INVALID_SIZE"; + case I40E_ERR_INVALID_ARP_INDEX: + return "I40E_ERR_INVALID_ARP_INDEX"; + case I40E_ERR_INVALID_FPM_FUNC_ID: + return "I40E_ERR_INVALID_FPM_FUNC_ID"; + case I40E_ERR_QP_INVALID_MSG_SIZE: + return "I40E_ERR_QP_INVALID_MSG_SIZE"; + case I40E_ERR_QP_TOOMANY_WRS_POSTED: + return "I40E_ERR_QP_TOOMANY_WRS_POSTED"; + case I40E_ERR_INVALID_FRAG_COUNT: + return "I40E_ERR_INVALID_FRAG_COUNT"; + case I40E_ERR_QUEUE_EMPTY: + return "I40E_ERR_QUEUE_EMPTY"; + case I40E_ERR_INVALID_ALIGNMENT: + return "I40E_ERR_INVALID_ALIGNMENT"; + case I40E_ERR_FLUSHED_QUEUE: + return "I40E_ERR_FLUSHED_QUEUE"; + case I40E_ERR_INVALID_PUSH_PAGE_INDEX: + return "I40E_ERR_INVALID_PUSH_PAGE_INDEX"; + case I40E_ERR_INVALID_IMM_DATA_SIZE: + return "I40E_ERR_INVALID_IMM_DATA_SIZE"; + case I40E_ERR_TIMEOUT: + return "I40E_ERR_TIMEOUT"; + case I40E_ERR_OPCODE_MISMATCH: + return "I40E_ERR_OPCODE_MISMATCH"; + case I40E_ERR_CQP_COMPL_ERROR: + return "I40E_ERR_CQP_COMPL_ERROR"; + case I40E_ERR_INVALID_VF_ID: + return "I40E_ERR_INVALID_VF_ID"; + case I40E_ERR_INVALID_HMCFN_ID: + return "I40E_ERR_INVALID_HMCFN_ID"; + case I40E_ERR_BACKING_PAGE_ERROR: + return "I40E_ERR_BACKING_PAGE_ERROR"; + case I40E_ERR_NO_PBLCHUNKS_AVAILABLE: + return "I40E_ERR_NO_PBLCHUNKS_AVAILABLE"; + case I40E_ERR_INVALID_PBLE_INDEX: + return "I40E_ERR_INVALID_PBLE_INDEX"; + case I40E_ERR_INVALID_SD_INDEX: + return "I40E_ERR_INVALID_SD_INDEX"; + case I40E_ERR_INVALID_PAGE_DESC_INDEX: + return "I40E_ERR_INVALID_PAGE_DESC_INDEX"; + case I40E_ERR_INVALID_SD_TYPE: + return "I40E_ERR_INVALID_SD_TYPE"; + case I40E_ERR_MEMCPY_FAILED: + return "I40E_ERR_MEMCPY_FAILED"; + case I40E_ERR_INVALID_HMC_OBJ_INDEX: + return "I40E_ERR_INVALID_HMC_OBJ_INDEX"; + case I40E_ERR_INVALID_HMC_OBJ_COUNT: + return "I40E_ERR_INVALID_HMC_OBJ_COUNT"; + case I40E_ERR_INVALID_SRQ_ARM_LIMIT: + return "I40E_ERR_INVALID_SRQ_ARM_LIMIT"; + case I40E_ERR_SRQ_ENABLED: + return "I40E_ERR_SRQ_ENABLED"; + case I40E_ERR_ADMIN_QUEUE_ERROR: + return "I40E_ERR_ADMIN_QUEUE_ERROR"; + case I40E_ERR_ADMIN_QUEUE_TIMEOUT: + return "I40E_ERR_ADMIN_QUEUE_TIMEOUT"; + case I40E_ERR_BUF_TOO_SHORT: + return "I40E_ERR_BUF_TOO_SHORT"; + case I40E_ERR_ADMIN_QUEUE_FULL: + return "I40E_ERR_ADMIN_QUEUE_FULL"; + case I40E_ERR_ADMIN_QUEUE_NO_WORK: + return "I40E_ERR_ADMIN_QUEUE_NO_WORK"; + case I40E_ERR_BAD_IWARP_CQE: + return "I40E_ERR_BAD_IWARP_CQE"; + case I40E_ERR_NVM_BLANK_MODE: + return "I40E_ERR_NVM_BLANK_MODE"; + case I40E_ERR_NOT_IMPLEMENTED: + return "I40E_ERR_NOT_IMPLEMENTED"; + case I40E_ERR_PE_DOORBELL_NOT_ENABLED: + return "I40E_ERR_PE_DOORBELL_NOT_ENABLED"; + case I40E_ERR_DIAG_TEST_FAILED: + return "I40E_ERR_DIAG_TEST_FAILED"; + case I40E_ERR_NOT_READY: + return "I40E_ERR_NOT_READY"; + case I40E_NOT_SUPPORTED: + return "I40E_NOT_SUPPORTED"; + case I40E_ERR_FIRMWARE_API_VERSION: + return "I40E_ERR_FIRMWARE_API_VERSION"; + case I40E_ERR_ADMIN_QUEUE_CRITICAL_ERROR: + return "I40E_ERR_ADMIN_QUEUE_CRITICAL_ERROR"; + } + + snprintf(hw->err_str, sizeof(hw->err_str), "%d", stat_err); + return hw->err_str; +} + +/** + * iavf_debug_aq + * @hw: debug mask related to admin queue + * @mask: debug mask + * @desc: pointer to admin queue descriptor + * @buffer: pointer to command buffer + * @buf_len: max length of buffer + * + * Dumps debug log about adminq command with descriptor contents. + **/ +void iavf_debug_aq(struct iavf_hw *hw, enum iavf_debug_mask mask, void *desc, + void *buffer, u16 buf_len) +{ + struct i40e_aq_desc *aq_desc = (struct i40e_aq_desc *)desc; + u8 *buf = (u8 *)buffer; + + if ((!(mask & hw->debug_mask)) || !desc) + return; + + iavf_debug(hw, mask, + "AQ CMD: opcode 0x%04X, flags 0x%04X, datalen 0x%04X, retval 0x%04X\n", + le16_to_cpu(aq_desc->opcode), + le16_to_cpu(aq_desc->flags), + le16_to_cpu(aq_desc->datalen), + le16_to_cpu(aq_desc->retval)); + iavf_debug(hw, mask, "\tcookie (h,l) 0x%08X 0x%08X\n", + le32_to_cpu(aq_desc->cookie_high), + le32_to_cpu(aq_desc->cookie_low)); + iavf_debug(hw, mask, "\tparam (0,1) 0x%08X 0x%08X\n", + le32_to_cpu(aq_desc->params.internal.param0), + le32_to_cpu(aq_desc->params.internal.param1)); + iavf_debug(hw, mask, "\taddr (h,l) 0x%08X 0x%08X\n", + le32_to_cpu(aq_desc->params.external.addr_high), + le32_to_cpu(aq_desc->params.external.addr_low)); + + if (buffer && aq_desc->datalen) { + u16 len = le16_to_cpu(aq_desc->datalen); + + iavf_debug(hw, mask, "AQ CMD Buffer:\n"); + if (buf_len < len) + len = buf_len; + /* write the full 16-byte chunks */ + if (hw->debug_mask & mask) { + char prefix[27]; + + snprintf(prefix, sizeof(prefix), + "iavf %02x:%02x.%x: \t0x", + hw->bus.bus_id, + hw->bus.device, + hw->bus.func); + + print_hex_dump(KERN_INFO, prefix, DUMP_PREFIX_OFFSET, + 16, 1, buf, len, false); + } + } +} + +/** + * iavf_check_asq_alive + * @hw: pointer to the hw struct + * + * Returns true if Queue is enabled else false. + **/ +bool iavf_check_asq_alive(struct iavf_hw *hw) +{ + if (hw->aq.asq.len) + return !!(rd32(hw, hw->aq.asq.len) & + IAVF_VF_ATQLEN1_ATQENABLE_MASK); + else + return false; +} + +/** + * iavf_aq_queue_shutdown + * @hw: pointer to the hw struct + * @unloading: is the driver unloading itself + * + * Tell the Firmware that we're shutting down the AdminQ and whether + * or not the driver is unloading as well. + **/ +iavf_status iavf_aq_queue_shutdown(struct iavf_hw *hw, bool unloading) +{ + struct i40e_aq_desc desc; + struct i40e_aqc_queue_shutdown *cmd = + (struct i40e_aqc_queue_shutdown *)&desc.params.raw; + iavf_status status; + + iavf_fill_default_direct_cmd_desc(&desc, i40e_aqc_opc_queue_shutdown); + + if (unloading) + cmd->driver_unloading = cpu_to_le32(I40E_AQ_DRIVER_UNLOADING); + status = iavf_asq_send_command(hw, &desc, NULL, 0, NULL); + + return status; +} + +/** + * iavf_aq_get_set_rss_lut + * @hw: pointer to the hardware structure + * @vsi_id: vsi fw index + * @pf_lut: for PF table set true, for VSI table set false + * @lut: pointer to the lut buffer provided by the caller + * @lut_size: size of the lut buffer + * @set: set true to set the table, false to get the table + * + * Internal function to get or set RSS look up table + **/ +static iavf_status iavf_aq_get_set_rss_lut(struct iavf_hw *hw, + u16 vsi_id, bool pf_lut, + u8 *lut, u16 lut_size, + bool set) +{ + iavf_status status; + struct i40e_aq_desc desc; + struct i40e_aqc_get_set_rss_lut *cmd_resp = + (struct i40e_aqc_get_set_rss_lut *)&desc.params.raw; + + if (set) + iavf_fill_default_direct_cmd_desc(&desc, + i40e_aqc_opc_set_rss_lut); + else + iavf_fill_default_direct_cmd_desc(&desc, + i40e_aqc_opc_get_rss_lut); + + /* Indirect command */ + desc.flags |= cpu_to_le16((u16)I40E_AQ_FLAG_BUF); + desc.flags |= cpu_to_le16((u16)I40E_AQ_FLAG_RD); + + cmd_resp->vsi_id = + cpu_to_le16((u16)((vsi_id << + I40E_AQC_SET_RSS_LUT_VSI_ID_SHIFT) & + I40E_AQC_SET_RSS_LUT_VSI_ID_MASK)); + cmd_resp->vsi_id |= cpu_to_le16((u16)I40E_AQC_SET_RSS_LUT_VSI_VALID); + + if (pf_lut) + cmd_resp->flags |= cpu_to_le16((u16) + ((I40E_AQC_SET_RSS_LUT_TABLE_TYPE_PF << + I40E_AQC_SET_RSS_LUT_TABLE_TYPE_SHIFT) & + I40E_AQC_SET_RSS_LUT_TABLE_TYPE_MASK)); + else + cmd_resp->flags |= cpu_to_le16((u16) + ((I40E_AQC_SET_RSS_LUT_TABLE_TYPE_VSI << + I40E_AQC_SET_RSS_LUT_TABLE_TYPE_SHIFT) & + I40E_AQC_SET_RSS_LUT_TABLE_TYPE_MASK)); + + status = iavf_asq_send_command(hw, &desc, lut, lut_size, NULL); + + return status; +} + +/** + * iavf_aq_get_rss_lut + * @hw: pointer to the hardware structure + * @vsi_id: vsi fw index + * @pf_lut: for PF table set true, for VSI table set false + * @lut: pointer to the lut buffer provided by the caller + * @lut_size: size of the lut buffer + * + * get the RSS lookup table, PF or VSI type + **/ +iavf_status iavf_aq_get_rss_lut(struct iavf_hw *hw, u16 vsi_id, + bool pf_lut, u8 *lut, u16 lut_size) +{ + return iavf_aq_get_set_rss_lut(hw, vsi_id, pf_lut, lut, lut_size, + false); +} + +/** + * iavf_aq_set_rss_lut + * @hw: pointer to the hardware structure + * @vsi_id: vsi fw index + * @pf_lut: for PF table set true, for VSI table set false + * @lut: pointer to the lut buffer provided by the caller + * @lut_size: size of the lut buffer + * + * set the RSS lookup table, PF or VSI type + **/ +iavf_status iavf_aq_set_rss_lut(struct iavf_hw *hw, u16 vsi_id, + bool pf_lut, u8 *lut, u16 lut_size) +{ + return iavf_aq_get_set_rss_lut(hw, vsi_id, pf_lut, lut, lut_size, true); +} + +/** + * iavf_aq_get_set_rss_key + * @hw: pointer to the hw struct + * @vsi_id: vsi fw index + * @key: pointer to key info struct + * @set: set true to set the key, false to get the key + * + * get the RSS key per VSI + **/ +static +iavf_status iavf_aq_get_set_rss_key(struct iavf_hw *hw, u16 vsi_id, + struct i40e_aqc_get_set_rss_key_data *key, + bool set) +{ + iavf_status status; + struct i40e_aq_desc desc; + struct i40e_aqc_get_set_rss_key *cmd_resp = + (struct i40e_aqc_get_set_rss_key *)&desc.params.raw; + u16 key_size = sizeof(struct i40e_aqc_get_set_rss_key_data); + + if (set) + iavf_fill_default_direct_cmd_desc(&desc, + i40e_aqc_opc_set_rss_key); + else + iavf_fill_default_direct_cmd_desc(&desc, + i40e_aqc_opc_get_rss_key); + + /* Indirect command */ + desc.flags |= cpu_to_le16((u16)I40E_AQ_FLAG_BUF); + desc.flags |= cpu_to_le16((u16)I40E_AQ_FLAG_RD); + + cmd_resp->vsi_id = + cpu_to_le16((u16)((vsi_id << + I40E_AQC_SET_RSS_KEY_VSI_ID_SHIFT) & + I40E_AQC_SET_RSS_KEY_VSI_ID_MASK)); + cmd_resp->vsi_id |= cpu_to_le16((u16)I40E_AQC_SET_RSS_KEY_VSI_VALID); + + status = iavf_asq_send_command(hw, &desc, key, key_size, NULL); + + return status; +} + +/** + * iavf_aq_get_rss_key + * @hw: pointer to the hw struct + * @vsi_id: vsi fw index + * @key: pointer to key info struct + * + **/ +iavf_status iavf_aq_get_rss_key(struct iavf_hw *hw, u16 vsi_id, + struct i40e_aqc_get_set_rss_key_data *key) +{ + return iavf_aq_get_set_rss_key(hw, vsi_id, key, false); +} + +/** + * iavf_aq_set_rss_key + * @hw: pointer to the hw struct + * @vsi_id: vsi fw index + * @key: pointer to key info struct + * + * set the RSS key per VSI + **/ +iavf_status iavf_aq_set_rss_key(struct iavf_hw *hw, u16 vsi_id, + struct i40e_aqc_get_set_rss_key_data *key) +{ + return iavf_aq_get_set_rss_key(hw, vsi_id, key, true); +} + +/* The iavf_ptype_lookup table is used to convert from the 8-bit ptype in the + * hardware to a bit-field that can be used by SW to more easily determine the + * packet type. + * + * Macros are used to shorten the table lines and make this table human + * readable. + * + * We store the PTYPE in the top byte of the bit field - this is just so that + * we can check that the table doesn't have a row missing, as the index into + * the table should be the PTYPE. + * + * Typical work flow: + * + * IF NOT iavf_ptype_lookup[ptype].known + * THEN + * Packet is unknown + * ELSE IF iavf_ptype_lookup[ptype].outer_ip == I40E_RX_PTYPE_OUTER_IP + * Use the rest of the fields to look at the tunnels, inner protocols, etc + * ELSE + * Use the enum iavf_rx_l2_ptype to decode the packet type + * ENDIF + */ + +/* macro to make the table lines short */ +#define IAVF_PTT(PTYPE, OUTER_IP, OUTER_IP_VER, OUTER_FRAG, T, TE, TEF, I, PL)\ + { PTYPE, \ + 1, \ + IAVF_RX_PTYPE_OUTER_##OUTER_IP, \ + IAVF_RX_PTYPE_OUTER_##OUTER_IP_VER, \ + IAVF_RX_PTYPE_##OUTER_FRAG, \ + IAVF_RX_PTYPE_TUNNEL_##T, \ + IAVF_RX_PTYPE_TUNNEL_END_##TE, \ + IAVF_RX_PTYPE_##TEF, \ + IAVF_RX_PTYPE_INNER_PROT_##I, \ + IAVF_RX_PTYPE_PAYLOAD_LAYER_##PL } + +#define IAVF_PTT_UNUSED_ENTRY(PTYPE) \ + { PTYPE, 0, 0, 0, 0, 0, 0, 0, 0, 0 } + +/* shorter macros makes the table fit but are terse */ +#define IAVF_RX_PTYPE_NOF IAVF_RX_PTYPE_NOT_FRAG +#define IAVF_RX_PTYPE_FRG IAVF_RX_PTYPE_FRAG +#define IAVF_RX_PTYPE_INNER_PROT_TS IAVF_RX_PTYPE_INNER_PROT_TIMESYNC + +/* Lookup table mapping the HW PTYPE to the bit field for decoding */ +struct iavf_rx_ptype_decoded iavf_ptype_lookup[] = { + /* L2 Packet types */ + IAVF_PTT_UNUSED_ENTRY(0), + IAVF_PTT(1, L2, NONE, NOF, NONE, NONE, NOF, NONE, PAY2), + IAVF_PTT(2, L2, NONE, NOF, NONE, NONE, NOF, TS, PAY2), + IAVF_PTT(3, L2, NONE, NOF, NONE, NONE, NOF, NONE, PAY2), + IAVF_PTT_UNUSED_ENTRY(4), + IAVF_PTT_UNUSED_ENTRY(5), + IAVF_PTT(6, L2, NONE, NOF, NONE, NONE, NOF, NONE, PAY2), + IAVF_PTT(7, L2, NONE, NOF, NONE, NONE, NOF, NONE, PAY2), + IAVF_PTT_UNUSED_ENTRY(8), + IAVF_PTT_UNUSED_ENTRY(9), + IAVF_PTT(10, L2, NONE, NOF, NONE, NONE, NOF, NONE, PAY2), + IAVF_PTT(11, L2, NONE, NOF, NONE, NONE, NOF, NONE, NONE), + IAVF_PTT(12, L2, NONE, NOF, NONE, NONE, NOF, NONE, PAY3), + IAVF_PTT(13, L2, NONE, NOF, NONE, NONE, NOF, NONE, PAY3), + IAVF_PTT(14, L2, NONE, NOF, NONE, NONE, NOF, NONE, PAY3), + IAVF_PTT(15, L2, NONE, NOF, NONE, NONE, NOF, NONE, PAY3), + IAVF_PTT(16, L2, NONE, NOF, NONE, NONE, NOF, NONE, PAY3), + IAVF_PTT(17, L2, NONE, NOF, NONE, NONE, NOF, NONE, PAY3), + IAVF_PTT(18, L2, NONE, NOF, NONE, NONE, NOF, NONE, PAY3), + IAVF_PTT(19, L2, NONE, NOF, NONE, NONE, NOF, NONE, PAY3), + IAVF_PTT(20, L2, NONE, NOF, NONE, NONE, NOF, NONE, PAY3), + IAVF_PTT(21, L2, NONE, NOF, NONE, NONE, NOF, NONE, PAY3), + + /* Non Tunneled IPv4 */ + IAVF_PTT(22, IP, IPV4, FRG, NONE, NONE, NOF, NONE, PAY3), + IAVF_PTT(23, IP, IPV4, NOF, NONE, NONE, NOF, NONE, PAY3), + IAVF_PTT(24, IP, IPV4, NOF, NONE, NONE, NOF, UDP, PAY4), + IAVF_PTT_UNUSED_ENTRY(25), + IAVF_PTT(26, IP, IPV4, NOF, NONE, NONE, NOF, TCP, PAY4), + IAVF_PTT(27, IP, IPV4, NOF, NONE, NONE, NOF, SCTP, PAY4), + IAVF_PTT(28, IP, IPV4, NOF, NONE, NONE, NOF, ICMP, PAY4), + + /* IPv4 --> IPv4 */ + IAVF_PTT(29, IP, IPV4, NOF, IP_IP, IPV4, FRG, NONE, PAY3), + IAVF_PTT(30, IP, IPV4, NOF, IP_IP, IPV4, NOF, NONE, PAY3), + IAVF_PTT(31, IP, IPV4, NOF, IP_IP, IPV4, NOF, UDP, PAY4), + IAVF_PTT_UNUSED_ENTRY(32), + IAVF_PTT(33, IP, IPV4, NOF, IP_IP, IPV4, NOF, TCP, PAY4), + IAVF_PTT(34, IP, IPV4, NOF, IP_IP, IPV4, NOF, SCTP, PAY4), + IAVF_PTT(35, IP, IPV4, NOF, IP_IP, IPV4, NOF, ICMP, PAY4), + + /* IPv4 --> IPv6 */ + IAVF_PTT(36, IP, IPV4, NOF, IP_IP, IPV6, FRG, NONE, PAY3), + IAVF_PTT(37, IP, IPV4, NOF, IP_IP, IPV6, NOF, NONE, PAY3), + IAVF_PTT(38, IP, IPV4, NOF, IP_IP, IPV6, NOF, UDP, PAY4), + IAVF_PTT_UNUSED_ENTRY(39), + IAVF_PTT(40, IP, IPV4, NOF, IP_IP, IPV6, NOF, TCP, PAY4), + IAVF_PTT(41, IP, IPV4, NOF, IP_IP, IPV6, NOF, SCTP, PAY4), + IAVF_PTT(42, IP, IPV4, NOF, IP_IP, IPV6, NOF, ICMP, PAY4), + + /* IPv4 --> GRE/NAT */ + IAVF_PTT(43, IP, IPV4, NOF, IP_GRENAT, NONE, NOF, NONE, PAY3), + + /* IPv4 --> GRE/NAT --> IPv4 */ + IAVF_PTT(44, IP, IPV4, NOF, IP_GRENAT, IPV4, FRG, NONE, PAY3), + IAVF_PTT(45, IP, IPV4, NOF, IP_GRENAT, IPV4, NOF, NONE, PAY3), + IAVF_PTT(46, IP, IPV4, NOF, IP_GRENAT, IPV4, NOF, UDP, PAY4), + IAVF_PTT_UNUSED_ENTRY(47), + IAVF_PTT(48, IP, IPV4, NOF, IP_GRENAT, IPV4, NOF, TCP, PAY4), + IAVF_PTT(49, IP, IPV4, NOF, IP_GRENAT, IPV4, NOF, SCTP, PAY4), + IAVF_PTT(50, IP, IPV4, NOF, IP_GRENAT, IPV4, NOF, ICMP, PAY4), + + /* IPv4 --> GRE/NAT --> IPv6 */ + IAVF_PTT(51, IP, IPV4, NOF, IP_GRENAT, IPV6, FRG, NONE, PAY3), + IAVF_PTT(52, IP, IPV4, NOF, IP_GRENAT, IPV6, NOF, NONE, PAY3), + IAVF_PTT(53, IP, IPV4, NOF, IP_GRENAT, IPV6, NOF, UDP, PAY4), + IAVF_PTT_UNUSED_ENTRY(54), + IAVF_PTT(55, IP, IPV4, NOF, IP_GRENAT, IPV6, NOF, TCP, PAY4), + IAVF_PTT(56, IP, IPV4, NOF, IP_GRENAT, IPV6, NOF, SCTP, PAY4), + IAVF_PTT(57, IP, IPV4, NOF, IP_GRENAT, IPV6, NOF, ICMP, PAY4), + + /* IPv4 --> GRE/NAT --> MAC */ + IAVF_PTT(58, IP, IPV4, NOF, IP_GRENAT_MAC, NONE, NOF, NONE, PAY3), + + /* IPv4 --> GRE/NAT --> MAC --> IPv4 */ + IAVF_PTT(59, IP, IPV4, NOF, IP_GRENAT_MAC, IPV4, FRG, NONE, PAY3), + IAVF_PTT(60, IP, IPV4, NOF, IP_GRENAT_MAC, IPV4, NOF, NONE, PAY3), + IAVF_PTT(61, IP, IPV4, NOF, IP_GRENAT_MAC, IPV4, NOF, UDP, PAY4), + IAVF_PTT_UNUSED_ENTRY(62), + IAVF_PTT(63, IP, IPV4, NOF, IP_GRENAT_MAC, IPV4, NOF, TCP, PAY4), + IAVF_PTT(64, IP, IPV4, NOF, IP_GRENAT_MAC, IPV4, NOF, SCTP, PAY4), + IAVF_PTT(65, IP, IPV4, NOF, IP_GRENAT_MAC, IPV4, NOF, ICMP, PAY4), + + /* IPv4 --> GRE/NAT -> MAC --> IPv6 */ + IAVF_PTT(66, IP, IPV4, NOF, IP_GRENAT_MAC, IPV6, FRG, NONE, PAY3), + IAVF_PTT(67, IP, IPV4, NOF, IP_GRENAT_MAC, IPV6, NOF, NONE, PAY3), + IAVF_PTT(68, IP, IPV4, NOF, IP_GRENAT_MAC, IPV6, NOF, UDP, PAY4), + IAVF_PTT_UNUSED_ENTRY(69), + IAVF_PTT(70, IP, IPV4, NOF, IP_GRENAT_MAC, IPV6, NOF, TCP, PAY4), + IAVF_PTT(71, IP, IPV4, NOF, IP_GRENAT_MAC, IPV6, NOF, SCTP, PAY4), + IAVF_PTT(72, IP, IPV4, NOF, IP_GRENAT_MAC, IPV6, NOF, ICMP, PAY4), + + /* IPv4 --> GRE/NAT --> MAC/VLAN */ + IAVF_PTT(73, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, NONE, NOF, NONE, PAY3), + + /* IPv4 ---> GRE/NAT -> MAC/VLAN --> IPv4 */ + IAVF_PTT(74, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV4, FRG, NONE, PAY3), + IAVF_PTT(75, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, NONE, PAY3), + IAVF_PTT(76, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, UDP, PAY4), + IAVF_PTT_UNUSED_ENTRY(77), + IAVF_PTT(78, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, TCP, PAY4), + IAVF_PTT(79, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, SCTP, PAY4), + IAVF_PTT(80, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, ICMP, PAY4), + + /* IPv4 -> GRE/NAT -> MAC/VLAN --> IPv6 */ + IAVF_PTT(81, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV6, FRG, NONE, PAY3), + IAVF_PTT(82, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, NONE, PAY3), + IAVF_PTT(83, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, UDP, PAY4), + IAVF_PTT_UNUSED_ENTRY(84), + IAVF_PTT(85, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, TCP, PAY4), + IAVF_PTT(86, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, SCTP, PAY4), + IAVF_PTT(87, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, ICMP, PAY4), + + /* Non Tunneled IPv6 */ + IAVF_PTT(88, IP, IPV6, FRG, NONE, NONE, NOF, NONE, PAY3), + IAVF_PTT(89, IP, IPV6, NOF, NONE, NONE, NOF, NONE, PAY3), + IAVF_PTT(90, IP, IPV6, NOF, NONE, NONE, NOF, UDP, PAY3), + IAVF_PTT_UNUSED_ENTRY(91), + IAVF_PTT(92, IP, IPV6, NOF, NONE, NONE, NOF, TCP, PAY4), + IAVF_PTT(93, IP, IPV6, NOF, NONE, NONE, NOF, SCTP, PAY4), + IAVF_PTT(94, IP, IPV6, NOF, NONE, NONE, NOF, ICMP, PAY4), + + /* IPv6 --> IPv4 */ + IAVF_PTT(95, IP, IPV6, NOF, IP_IP, IPV4, FRG, NONE, PAY3), + IAVF_PTT(96, IP, IPV6, NOF, IP_IP, IPV4, NOF, NONE, PAY3), + IAVF_PTT(97, IP, IPV6, NOF, IP_IP, IPV4, NOF, UDP, PAY4), + IAVF_PTT_UNUSED_ENTRY(98), + IAVF_PTT(99, IP, IPV6, NOF, IP_IP, IPV4, NOF, TCP, PAY4), + IAVF_PTT(100, IP, IPV6, NOF, IP_IP, IPV4, NOF, SCTP, PAY4), + IAVF_PTT(101, IP, IPV6, NOF, IP_IP, IPV4, NOF, ICMP, PAY4), + + /* IPv6 --> IPv6 */ + IAVF_PTT(102, IP, IPV6, NOF, IP_IP, IPV6, FRG, NONE, PAY3), + IAVF_PTT(103, IP, IPV6, NOF, IP_IP, IPV6, NOF, NONE, PAY3), + IAVF_PTT(104, IP, IPV6, NOF, IP_IP, IPV6, NOF, UDP, PAY4), + IAVF_PTT_UNUSED_ENTRY(105), + IAVF_PTT(106, IP, IPV6, NOF, IP_IP, IPV6, NOF, TCP, PAY4), + IAVF_PTT(107, IP, IPV6, NOF, IP_IP, IPV6, NOF, SCTP, PAY4), + IAVF_PTT(108, IP, IPV6, NOF, IP_IP, IPV6, NOF, ICMP, PAY4), + + /* IPv6 --> GRE/NAT */ + IAVF_PTT(109, IP, IPV6, NOF, IP_GRENAT, NONE, NOF, NONE, PAY3), + + /* IPv6 --> GRE/NAT -> IPv4 */ + IAVF_PTT(110, IP, IPV6, NOF, IP_GRENAT, IPV4, FRG, NONE, PAY3), + IAVF_PTT(111, IP, IPV6, NOF, IP_GRENAT, IPV4, NOF, NONE, PAY3), + IAVF_PTT(112, IP, IPV6, NOF, IP_GRENAT, IPV4, NOF, UDP, PAY4), + IAVF_PTT_UNUSED_ENTRY(113), + IAVF_PTT(114, IP, IPV6, NOF, IP_GRENAT, IPV4, NOF, TCP, PAY4), + IAVF_PTT(115, IP, IPV6, NOF, IP_GRENAT, IPV4, NOF, SCTP, PAY4), + IAVF_PTT(116, IP, IPV6, NOF, IP_GRENAT, IPV4, NOF, ICMP, PAY4), + + /* IPv6 --> GRE/NAT -> IPv6 */ + IAVF_PTT(117, IP, IPV6, NOF, IP_GRENAT, IPV6, FRG, NONE, PAY3), + IAVF_PTT(118, IP, IPV6, NOF, IP_GRENAT, IPV6, NOF, NONE, PAY3), + IAVF_PTT(119, IP, IPV6, NOF, IP_GRENAT, IPV6, NOF, UDP, PAY4), + IAVF_PTT_UNUSED_ENTRY(120), + IAVF_PTT(121, IP, IPV6, NOF, IP_GRENAT, IPV6, NOF, TCP, PAY4), + IAVF_PTT(122, IP, IPV6, NOF, IP_GRENAT, IPV6, NOF, SCTP, PAY4), + IAVF_PTT(123, IP, IPV6, NOF, IP_GRENAT, IPV6, NOF, ICMP, PAY4), + + /* IPv6 --> GRE/NAT -> MAC */ + IAVF_PTT(124, IP, IPV6, NOF, IP_GRENAT_MAC, NONE, NOF, NONE, PAY3), + + /* IPv6 --> GRE/NAT -> MAC -> IPv4 */ + IAVF_PTT(125, IP, IPV6, NOF, IP_GRENAT_MAC, IPV4, FRG, NONE, PAY3), + IAVF_PTT(126, IP, IPV6, NOF, IP_GRENAT_MAC, IPV4, NOF, NONE, PAY3), + IAVF_PTT(127, IP, IPV6, NOF, IP_GRENAT_MAC, IPV4, NOF, UDP, PAY4), + IAVF_PTT_UNUSED_ENTRY(128), + IAVF_PTT(129, IP, IPV6, NOF, IP_GRENAT_MAC, IPV4, NOF, TCP, PAY4), + IAVF_PTT(130, IP, IPV6, NOF, IP_GRENAT_MAC, IPV4, NOF, SCTP, PAY4), + IAVF_PTT(131, IP, IPV6, NOF, IP_GRENAT_MAC, IPV4, NOF, ICMP, PAY4), + + /* IPv6 --> GRE/NAT -> MAC -> IPv6 */ + IAVF_PTT(132, IP, IPV6, NOF, IP_GRENAT_MAC, IPV6, FRG, NONE, PAY3), + IAVF_PTT(133, IP, IPV6, NOF, IP_GRENAT_MAC, IPV6, NOF, NONE, PAY3), + IAVF_PTT(134, IP, IPV6, NOF, IP_GRENAT_MAC, IPV6, NOF, UDP, PAY4), + IAVF_PTT_UNUSED_ENTRY(135), + IAVF_PTT(136, IP, IPV6, NOF, IP_GRENAT_MAC, IPV6, NOF, TCP, PAY4), + IAVF_PTT(137, IP, IPV6, NOF, IP_GRENAT_MAC, IPV6, NOF, SCTP, PAY4), + IAVF_PTT(138, IP, IPV6, NOF, IP_GRENAT_MAC, IPV6, NOF, ICMP, PAY4), + + /* IPv6 --> GRE/NAT -> MAC/VLAN */ + IAVF_PTT(139, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, NONE, NOF, NONE, PAY3), + + /* IPv6 --> GRE/NAT -> MAC/VLAN --> IPv4 */ + IAVF_PTT(140, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV4, FRG, NONE, PAY3), + IAVF_PTT(141, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, NONE, PAY3), + IAVF_PTT(142, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, UDP, PAY4), + IAVF_PTT_UNUSED_ENTRY(143), + IAVF_PTT(144, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, TCP, PAY4), + IAVF_PTT(145, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, SCTP, PAY4), + IAVF_PTT(146, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, ICMP, PAY4), + + /* IPv6 --> GRE/NAT -> MAC/VLAN --> IPv6 */ + IAVF_PTT(147, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV6, FRG, NONE, PAY3), + IAVF_PTT(148, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, NONE, PAY3), + IAVF_PTT(149, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, UDP, PAY4), + IAVF_PTT_UNUSED_ENTRY(150), + IAVF_PTT(151, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, TCP, PAY4), + IAVF_PTT(152, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, SCTP, PAY4), + IAVF_PTT(153, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, ICMP, PAY4), + + /* unused entries */ + IAVF_PTT_UNUSED_ENTRY(154), + IAVF_PTT_UNUSED_ENTRY(155), + IAVF_PTT_UNUSED_ENTRY(156), + IAVF_PTT_UNUSED_ENTRY(157), + IAVF_PTT_UNUSED_ENTRY(158), + IAVF_PTT_UNUSED_ENTRY(159), + + IAVF_PTT_UNUSED_ENTRY(160), + IAVF_PTT_UNUSED_ENTRY(161), + IAVF_PTT_UNUSED_ENTRY(162), + IAVF_PTT_UNUSED_ENTRY(163), + IAVF_PTT_UNUSED_ENTRY(164), + IAVF_PTT_UNUSED_ENTRY(165), + IAVF_PTT_UNUSED_ENTRY(166), + IAVF_PTT_UNUSED_ENTRY(167), + IAVF_PTT_UNUSED_ENTRY(168), + IAVF_PTT_UNUSED_ENTRY(169), + + IAVF_PTT_UNUSED_ENTRY(170), + IAVF_PTT_UNUSED_ENTRY(171), + IAVF_PTT_UNUSED_ENTRY(172), + IAVF_PTT_UNUSED_ENTRY(173), + IAVF_PTT_UNUSED_ENTRY(174), + IAVF_PTT_UNUSED_ENTRY(175), + IAVF_PTT_UNUSED_ENTRY(176), + IAVF_PTT_UNUSED_ENTRY(177), + IAVF_PTT_UNUSED_ENTRY(178), + IAVF_PTT_UNUSED_ENTRY(179), + + IAVF_PTT_UNUSED_ENTRY(180), + IAVF_PTT_UNUSED_ENTRY(181), + IAVF_PTT_UNUSED_ENTRY(182), + IAVF_PTT_UNUSED_ENTRY(183), + IAVF_PTT_UNUSED_ENTRY(184), + IAVF_PTT_UNUSED_ENTRY(185), + IAVF_PTT_UNUSED_ENTRY(186), + IAVF_PTT_UNUSED_ENTRY(187), + IAVF_PTT_UNUSED_ENTRY(188), + IAVF_PTT_UNUSED_ENTRY(189), + + IAVF_PTT_UNUSED_ENTRY(190), + IAVF_PTT_UNUSED_ENTRY(191), + IAVF_PTT_UNUSED_ENTRY(192), + IAVF_PTT_UNUSED_ENTRY(193), + IAVF_PTT_UNUSED_ENTRY(194), + IAVF_PTT_UNUSED_ENTRY(195), + IAVF_PTT_UNUSED_ENTRY(196), + IAVF_PTT_UNUSED_ENTRY(197), + IAVF_PTT_UNUSED_ENTRY(198), + IAVF_PTT_UNUSED_ENTRY(199), + + IAVF_PTT_UNUSED_ENTRY(200), + IAVF_PTT_UNUSED_ENTRY(201), + IAVF_PTT_UNUSED_ENTRY(202), + IAVF_PTT_UNUSED_ENTRY(203), + IAVF_PTT_UNUSED_ENTRY(204), + IAVF_PTT_UNUSED_ENTRY(205), + IAVF_PTT_UNUSED_ENTRY(206), + IAVF_PTT_UNUSED_ENTRY(207), + IAVF_PTT_UNUSED_ENTRY(208), + IAVF_PTT_UNUSED_ENTRY(209), + + IAVF_PTT_UNUSED_ENTRY(210), + IAVF_PTT_UNUSED_ENTRY(211), + IAVF_PTT_UNUSED_ENTRY(212), + IAVF_PTT_UNUSED_ENTRY(213), + IAVF_PTT_UNUSED_ENTRY(214), + IAVF_PTT_UNUSED_ENTRY(215), + IAVF_PTT_UNUSED_ENTRY(216), + IAVF_PTT_UNUSED_ENTRY(217), + IAVF_PTT_UNUSED_ENTRY(218), + IAVF_PTT_UNUSED_ENTRY(219), + + IAVF_PTT_UNUSED_ENTRY(220), + IAVF_PTT_UNUSED_ENTRY(221), + IAVF_PTT_UNUSED_ENTRY(222), + IAVF_PTT_UNUSED_ENTRY(223), + IAVF_PTT_UNUSED_ENTRY(224), + IAVF_PTT_UNUSED_ENTRY(225), + IAVF_PTT_UNUSED_ENTRY(226), + IAVF_PTT_UNUSED_ENTRY(227), + IAVF_PTT_UNUSED_ENTRY(228), + IAVF_PTT_UNUSED_ENTRY(229), + + IAVF_PTT_UNUSED_ENTRY(230), + IAVF_PTT_UNUSED_ENTRY(231), + IAVF_PTT_UNUSED_ENTRY(232), + IAVF_PTT_UNUSED_ENTRY(233), + IAVF_PTT_UNUSED_ENTRY(234), + IAVF_PTT_UNUSED_ENTRY(235), + IAVF_PTT_UNUSED_ENTRY(236), + IAVF_PTT_UNUSED_ENTRY(237), + IAVF_PTT_UNUSED_ENTRY(238), + IAVF_PTT_UNUSED_ENTRY(239), + + IAVF_PTT_UNUSED_ENTRY(240), + IAVF_PTT_UNUSED_ENTRY(241), + IAVF_PTT_UNUSED_ENTRY(242), + IAVF_PTT_UNUSED_ENTRY(243), + IAVF_PTT_UNUSED_ENTRY(244), + IAVF_PTT_UNUSED_ENTRY(245), + IAVF_PTT_UNUSED_ENTRY(246), + IAVF_PTT_UNUSED_ENTRY(247), + IAVF_PTT_UNUSED_ENTRY(248), + IAVF_PTT_UNUSED_ENTRY(249), + + IAVF_PTT_UNUSED_ENTRY(250), + IAVF_PTT_UNUSED_ENTRY(251), + IAVF_PTT_UNUSED_ENTRY(252), + IAVF_PTT_UNUSED_ENTRY(253), + IAVF_PTT_UNUSED_ENTRY(254), + IAVF_PTT_UNUSED_ENTRY(255) +}; + +/** + * iavf_aq_send_msg_to_pf + * @hw: pointer to the hardware structure + * @v_opcode: opcodes for VF-PF communication + * @v_retval: return error code + * @msg: pointer to the msg buffer + * @msglen: msg length + * @cmd_details: pointer to command details + * + * Send message to PF driver using admin queue. By default, this message + * is sent asynchronously, i.e. iavf_asq_send_command() does not wait for + * completion before returning. + **/ +iavf_status iavf_aq_send_msg_to_pf(struct iavf_hw *hw, + enum virtchnl_ops v_opcode, + iavf_status v_retval, u8 *msg, u16 msglen, + struct i40e_asq_cmd_details *cmd_details) +{ + struct i40e_asq_cmd_details details; + struct i40e_aq_desc desc; + iavf_status status; + + iavf_fill_default_direct_cmd_desc(&desc, i40e_aqc_opc_send_msg_to_pf); + desc.flags |= cpu_to_le16((u16)I40E_AQ_FLAG_SI); + desc.cookie_high = cpu_to_le32(v_opcode); + desc.cookie_low = cpu_to_le32(v_retval); + if (msglen) { + desc.flags |= cpu_to_le16((u16)(I40E_AQ_FLAG_BUF + | I40E_AQ_FLAG_RD)); + if (msglen > I40E_AQ_LARGE_BUF) + desc.flags |= cpu_to_le16((u16)I40E_AQ_FLAG_LB); + desc.datalen = cpu_to_le16(msglen); + } + if (!cmd_details) { + memset(&details, 0, sizeof(details)); + details.async = true; + cmd_details = &details; + } + status = iavf_asq_send_command(hw, &desc, msg, msglen, cmd_details); + return status; +} + +/** + * iavf_vf_parse_hw_config + * @hw: pointer to the hardware structure + * @msg: pointer to the virtual channel VF resource structure + * + * Given a VF resource message from the PF, populate the hw struct + * with appropriate information. + **/ +void iavf_vf_parse_hw_config(struct iavf_hw *hw, + struct virtchnl_vf_resource *msg) +{ + struct virtchnl_vsi_resource *vsi_res; + int i; + + vsi_res = &msg->vsi_res[0]; + + hw->dev_caps.num_vsis = msg->num_vsis; + hw->dev_caps.num_rx_qp = msg->num_queue_pairs; + hw->dev_caps.num_tx_qp = msg->num_queue_pairs; + hw->dev_caps.num_msix_vectors_vf = msg->max_vectors; + hw->dev_caps.dcb = msg->vf_cap_flags & + VIRTCHNL_VF_OFFLOAD_L2; + hw->dev_caps.fcoe = 0; + for (i = 0; i < msg->num_vsis; i++) { + if (vsi_res->vsi_type == VIRTCHNL_VSI_SRIOV) { + ether_addr_copy(hw->mac.perm_addr, + vsi_res->default_mac_addr); + ether_addr_copy(hw->mac.addr, + vsi_res->default_mac_addr); + } + vsi_res++; + } +} + +/** + * iavf_vf_reset + * @hw: pointer to the hardware structure + * + * Send a VF_RESET message to the PF. Does not wait for response from PF + * as none will be forthcoming. Immediately after calling this function, + * the admin queue should be shut down and (optionally) reinitialized. + **/ +iavf_status iavf_vf_reset(struct iavf_hw *hw) +{ + return iavf_aq_send_msg_to_pf(hw, VIRTCHNL_OP_RESET_VF, + 0, NULL, 0, NULL); +} diff --git a/drivers/net/ethernet/intel/iavf/iavf_devids.h b/drivers/net/ethernet/intel/iavf/iavf_devids.h new file mode 100644 index 000000000000..8eb7b697e96c --- /dev/null +++ b/drivers/net/ethernet/intel/iavf/iavf_devids.h @@ -0,0 +1,12 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright(c) 2013 - 2018 Intel Corporation. */ + +#ifndef _IAVF_DEVIDS_H_ +#define _IAVF_DEVIDS_H_ + +/* Device IDs for the VF driver */ +#define IAVF_DEV_ID_VF 0x154C +#define IAVF_DEV_ID_VF_HV 0x1571 +#define IAVF_DEV_ID_ADAPTIVE_VF 0x1889 +#define IAVF_DEV_ID_X722_VF 0x37CD +#endif /* _IAVF_DEVIDS_H_ */ diff --git a/drivers/net/ethernet/intel/iavf/iavf_ethtool.c b/drivers/net/ethernet/intel/iavf/iavf_ethtool.c new file mode 100644 index 000000000000..9f87304109fe --- /dev/null +++ b/drivers/net/ethernet/intel/iavf/iavf_ethtool.c @@ -0,0 +1,1036 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright(c) 2013 - 2018 Intel Corporation. */ + +/* ethtool support for iavf */ +#include "iavf.h" + +#include <linux/uaccess.h> + +/* ethtool statistics helpers */ + +/** + * struct iavf_stats - definition for an ethtool statistic + * @stat_string: statistic name to display in ethtool -S output + * @sizeof_stat: the sizeof() the stat, must be no greater than sizeof(u64) + * @stat_offset: offsetof() the stat from a base pointer + * + * This structure defines a statistic to be added to the ethtool stats buffer. + * It defines a statistic as offset from a common base pointer. Stats should + * be defined in constant arrays using the IAVF_STAT macro, with every element + * of the array using the same _type for calculating the sizeof_stat and + * stat_offset. + * + * The @sizeof_stat is expected to be sizeof(u8), sizeof(u16), sizeof(u32) or + * sizeof(u64). Other sizes are not expected and will produce a WARN_ONCE from + * the iavf_add_ethtool_stat() helper function. + * + * The @stat_string is interpreted as a format string, allowing formatted + * values to be inserted while looping over multiple structures for a given + * statistics array. Thus, every statistic string in an array should have the + * same type and number of format specifiers, to be formatted by variadic + * arguments to the iavf_add_stat_string() helper function. + **/ +struct iavf_stats { + char stat_string[ETH_GSTRING_LEN]; + int sizeof_stat; + int stat_offset; +}; + +/* Helper macro to define an iavf_stat structure with proper size and type. + * Use this when defining constant statistics arrays. Note that @_type expects + * only a type name and is used multiple times. + */ +#define IAVF_STAT(_type, _name, _stat) { \ + .stat_string = _name, \ + .sizeof_stat = FIELD_SIZEOF(_type, _stat), \ + .stat_offset = offsetof(_type, _stat) \ +} + +/* Helper macro for defining some statistics related to queues */ +#define IAVF_QUEUE_STAT(_name, _stat) \ + IAVF_STAT(struct iavf_ring, _name, _stat) + +/* Stats associated with a Tx or Rx ring */ +static const struct iavf_stats iavf_gstrings_queue_stats[] = { + IAVF_QUEUE_STAT("%s-%u.packets", stats.packets), + IAVF_QUEUE_STAT("%s-%u.bytes", stats.bytes), +}; + +/** + * iavf_add_one_ethtool_stat - copy the stat into the supplied buffer + * @data: location to store the stat value + * @pointer: basis for where to copy from + * @stat: the stat definition + * + * Copies the stat data defined by the pointer and stat structure pair into + * the memory supplied as data. Used to implement iavf_add_ethtool_stats and + * iavf_add_queue_stats. If the pointer is null, data will be zero'd. + */ +static void +iavf_add_one_ethtool_stat(u64 *data, void *pointer, + const struct iavf_stats *stat) +{ + char *p; + + if (!pointer) { + /* ensure that the ethtool data buffer is zero'd for any stats + * which don't have a valid pointer. + */ + *data = 0; + return; + } + + p = (char *)pointer + stat->stat_offset; + switch (stat->sizeof_stat) { + case sizeof(u64): + *data = *((u64 *)p); + break; + case sizeof(u32): + *data = *((u32 *)p); + break; + case sizeof(u16): + *data = *((u16 *)p); + break; + case sizeof(u8): + *data = *((u8 *)p); + break; + default: + WARN_ONCE(1, "unexpected stat size for %s", + stat->stat_string); + *data = 0; + } +} + +/** + * __iavf_add_ethtool_stats - copy stats into the ethtool supplied buffer + * @data: ethtool stats buffer + * @pointer: location to copy stats from + * @stats: array of stats to copy + * @size: the size of the stats definition + * + * Copy the stats defined by the stats array using the pointer as a base into + * the data buffer supplied by ethtool. Updates the data pointer to point to + * the next empty location for successive calls to __iavf_add_ethtool_stats. + * If pointer is null, set the data values to zero and update the pointer to + * skip these stats. + **/ +static void +__iavf_add_ethtool_stats(u64 **data, void *pointer, + const struct iavf_stats stats[], + const unsigned int size) +{ + unsigned int i; + + for (i = 0; i < size; i++) + iavf_add_one_ethtool_stat((*data)++, pointer, &stats[i]); +} + +/** + * iavf_add_ethtool_stats - copy stats into ethtool supplied buffer + * @data: ethtool stats buffer + * @pointer: location where stats are stored + * @stats: static const array of stat definitions + * + * Macro to ease the use of __iavf_add_ethtool_stats by taking a static + * constant stats array and passing the ARRAY_SIZE(). This avoids typos by + * ensuring that we pass the size associated with the given stats array. + * + * The parameter @stats is evaluated twice, so parameters with side effects + * should be avoided. + **/ +#define iavf_add_ethtool_stats(data, pointer, stats) \ + __iavf_add_ethtool_stats(data, pointer, stats, ARRAY_SIZE(stats)) + +/** + * iavf_add_queue_stats - copy queue statistics into supplied buffer + * @data: ethtool stats buffer + * @ring: the ring to copy + * + * Queue statistics must be copied while protected by + * u64_stats_fetch_begin_irq, so we can't directly use iavf_add_ethtool_stats. + * Assumes that queue stats are defined in iavf_gstrings_queue_stats. If the + * ring pointer is null, zero out the queue stat values and update the data + * pointer. Otherwise safely copy the stats from the ring into the supplied + * buffer and update the data pointer when finished. + * + * This function expects to be called while under rcu_read_lock(). + **/ +static void +iavf_add_queue_stats(u64 **data, struct iavf_ring *ring) +{ + const unsigned int size = ARRAY_SIZE(iavf_gstrings_queue_stats); + const struct iavf_stats *stats = iavf_gstrings_queue_stats; + unsigned int start; + unsigned int i; + + /* To avoid invalid statistics values, ensure that we keep retrying + * the copy until we get a consistent value according to + * u64_stats_fetch_retry_irq. But first, make sure our ring is + * non-null before attempting to access its syncp. + */ + do { + start = !ring ? 0 : u64_stats_fetch_begin_irq(&ring->syncp); + for (i = 0; i < size; i++) + iavf_add_one_ethtool_stat(&(*data)[i], ring, &stats[i]); + } while (ring && u64_stats_fetch_retry_irq(&ring->syncp, start)); + + /* Once we successfully copy the stats in, update the data pointer */ + *data += size; +} + +/** + * __iavf_add_stat_strings - copy stat strings into ethtool buffer + * @p: ethtool supplied buffer + * @stats: stat definitions array + * @size: size of the stats array + * + * Format and copy the strings described by stats into the buffer pointed at + * by p. + **/ +static void __iavf_add_stat_strings(u8 **p, const struct iavf_stats stats[], + const unsigned int size, ...) +{ + unsigned int i; + + for (i = 0; i < size; i++) { + va_list args; + + va_start(args, size); + vsnprintf(*p, ETH_GSTRING_LEN, stats[i].stat_string, args); + *p += ETH_GSTRING_LEN; + va_end(args); + } +} + +/** + * iavf_add_stat_strings - copy stat strings into ethtool buffer + * @p: ethtool supplied buffer + * @stats: stat definitions array + * + * Format and copy the strings described by the const static stats value into + * the buffer pointed at by p. + * + * The parameter @stats is evaluated twice, so parameters with side effects + * should be avoided. Additionally, stats must be an array such that + * ARRAY_SIZE can be called on it. + **/ +#define iavf_add_stat_strings(p, stats, ...) \ + __iavf_add_stat_strings(p, stats, ARRAY_SIZE(stats), ## __VA_ARGS__) + +#define VF_STAT(_name, _stat) \ + IAVF_STAT(struct iavf_adapter, _name, _stat) + +static const struct iavf_stats iavf_gstrings_stats[] = { + VF_STAT("rx_bytes", current_stats.rx_bytes), + VF_STAT("rx_unicast", current_stats.rx_unicast), + VF_STAT("rx_multicast", current_stats.rx_multicast), + VF_STAT("rx_broadcast", current_stats.rx_broadcast), + VF_STAT("rx_discards", current_stats.rx_discards), + VF_STAT("rx_unknown_protocol", current_stats.rx_unknown_protocol), + VF_STAT("tx_bytes", current_stats.tx_bytes), + VF_STAT("tx_unicast", current_stats.tx_unicast), + VF_STAT("tx_multicast", current_stats.tx_multicast), + VF_STAT("tx_broadcast", current_stats.tx_broadcast), + VF_STAT("tx_discards", current_stats.tx_discards), + VF_STAT("tx_errors", current_stats.tx_errors), +}; + +#define IAVF_STATS_LEN ARRAY_SIZE(iavf_gstrings_stats) + +#define IAVF_QUEUE_STATS_LEN ARRAY_SIZE(iavf_gstrings_queue_stats) + +/* For now we have one and only one private flag and it is only defined + * when we have support for the SKIP_CPU_SYNC DMA attribute. Instead + * of leaving all this code sitting around empty we will strip it unless + * our one private flag is actually available. + */ +struct iavf_priv_flags { + char flag_string[ETH_GSTRING_LEN]; + u32 flag; + bool read_only; +}; + +#define IAVF_PRIV_FLAG(_name, _flag, _read_only) { \ + .flag_string = _name, \ + .flag = _flag, \ + .read_only = _read_only, \ +} + +static const struct iavf_priv_flags iavf_gstrings_priv_flags[] = { + IAVF_PRIV_FLAG("legacy-rx", IAVF_FLAG_LEGACY_RX, 0), +}; + +#define IAVF_PRIV_FLAGS_STR_LEN ARRAY_SIZE(iavf_gstrings_priv_flags) + +/** + * iavf_get_link_ksettings - Get Link Speed and Duplex settings + * @netdev: network interface device structure + * @cmd: ethtool command + * + * Reports speed/duplex settings. Because this is a VF, we don't know what + * kind of link we really have, so we fake it. + **/ +static int iavf_get_link_ksettings(struct net_device *netdev, + struct ethtool_link_ksettings *cmd) +{ + struct iavf_adapter *adapter = netdev_priv(netdev); + + ethtool_link_ksettings_zero_link_mode(cmd, supported); + cmd->base.autoneg = AUTONEG_DISABLE; + cmd->base.port = PORT_NONE; + /* Set speed and duplex */ + switch (adapter->link_speed) { + case I40E_LINK_SPEED_40GB: + cmd->base.speed = SPEED_40000; + break; + case I40E_LINK_SPEED_25GB: +#ifdef SPEED_25000 + cmd->base.speed = SPEED_25000; +#else + netdev_info(netdev, + "Speed is 25G, display not supported by this version of ethtool.\n"); +#endif + break; + case I40E_LINK_SPEED_20GB: + cmd->base.speed = SPEED_20000; + break; + case I40E_LINK_SPEED_10GB: + cmd->base.speed = SPEED_10000; + break; + case I40E_LINK_SPEED_1GB: + cmd->base.speed = SPEED_1000; + break; + case I40E_LINK_SPEED_100MB: + cmd->base.speed = SPEED_100; + break; + default: + break; + } + cmd->base.duplex = DUPLEX_FULL; + + return 0; +} + +/** + * iavf_get_sset_count - Get length of string set + * @netdev: network interface device structure + * @sset: id of string set + * + * Reports size of various string tables. + **/ +static int iavf_get_sset_count(struct net_device *netdev, int sset) +{ + if (sset == ETH_SS_STATS) + return IAVF_STATS_LEN + + (IAVF_QUEUE_STATS_LEN * 2 * IAVF_MAX_REQ_QUEUES); + else if (sset == ETH_SS_PRIV_FLAGS) + return IAVF_PRIV_FLAGS_STR_LEN; + else + return -EINVAL; +} + +/** + * iavf_get_ethtool_stats - report device statistics + * @netdev: network interface device structure + * @stats: ethtool statistics structure + * @data: pointer to data buffer + * + * All statistics are added to the data buffer as an array of u64. + **/ +static void iavf_get_ethtool_stats(struct net_device *netdev, + struct ethtool_stats *stats, u64 *data) +{ + struct iavf_adapter *adapter = netdev_priv(netdev); + unsigned int i; + + iavf_add_ethtool_stats(&data, adapter, iavf_gstrings_stats); + + rcu_read_lock(); + for (i = 0; i < IAVF_MAX_REQ_QUEUES; i++) { + struct iavf_ring *ring; + + /* Avoid accessing un-allocated queues */ + ring = (i < adapter->num_active_queues ? + &adapter->tx_rings[i] : NULL); + iavf_add_queue_stats(&data, ring); + + /* Avoid accessing un-allocated queues */ + ring = (i < adapter->num_active_queues ? + &adapter->rx_rings[i] : NULL); + iavf_add_queue_stats(&data, ring); + } + rcu_read_unlock(); +} + +/** + * iavf_get_priv_flag_strings - Get private flag strings + * @netdev: network interface device structure + * @data: buffer for string data + * + * Builds the private flags string table + **/ +static void iavf_get_priv_flag_strings(struct net_device *netdev, u8 *data) +{ + unsigned int i; + + for (i = 0; i < IAVF_PRIV_FLAGS_STR_LEN; i++) { + snprintf(data, ETH_GSTRING_LEN, "%s", + iavf_gstrings_priv_flags[i].flag_string); + data += ETH_GSTRING_LEN; + } +} + +/** + * iavf_get_stat_strings - Get stat strings + * @netdev: network interface device structure + * @data: buffer for string data + * + * Builds the statistics string table + **/ +static void iavf_get_stat_strings(struct net_device *netdev, u8 *data) +{ + unsigned int i; + + iavf_add_stat_strings(&data, iavf_gstrings_stats); + + /* Queues are always allocated in pairs, so we just use num_tx_queues + * for both Tx and Rx queues. + */ + for (i = 0; i < netdev->num_tx_queues; i++) { + iavf_add_stat_strings(&data, iavf_gstrings_queue_stats, + "tx", i); + iavf_add_stat_strings(&data, iavf_gstrings_queue_stats, + "rx", i); + } +} + +/** + * iavf_get_strings - Get string set + * @netdev: network interface device structure + * @sset: id of string set + * @data: buffer for string data + * + * Builds string tables for various string sets + **/ +static void iavf_get_strings(struct net_device *netdev, u32 sset, u8 *data) +{ + switch (sset) { + case ETH_SS_STATS: + iavf_get_stat_strings(netdev, data); + break; + case ETH_SS_PRIV_FLAGS: + iavf_get_priv_flag_strings(netdev, data); + break; + default: + break; + } +} + +/** + * iavf_get_priv_flags - report device private flags + * @netdev: network interface device structure + * + * The get string set count and the string set should be matched for each + * flag returned. Add new strings for each flag to the iavf_gstrings_priv_flags + * array. + * + * Returns a u32 bitmap of flags. + **/ +static u32 iavf_get_priv_flags(struct net_device *netdev) +{ + struct iavf_adapter *adapter = netdev_priv(netdev); + u32 i, ret_flags = 0; + + for (i = 0; i < IAVF_PRIV_FLAGS_STR_LEN; i++) { + const struct iavf_priv_flags *priv_flags; + + priv_flags = &iavf_gstrings_priv_flags[i]; + + if (priv_flags->flag & adapter->flags) + ret_flags |= BIT(i); + } + + return ret_flags; +} + +/** + * iavf_set_priv_flags - set private flags + * @netdev: network interface device structure + * @flags: bit flags to be set + **/ +static int iavf_set_priv_flags(struct net_device *netdev, u32 flags) +{ + struct iavf_adapter *adapter = netdev_priv(netdev); + u32 orig_flags, new_flags, changed_flags; + u32 i; + + orig_flags = READ_ONCE(adapter->flags); + new_flags = orig_flags; + + for (i = 0; i < IAVF_PRIV_FLAGS_STR_LEN; i++) { + const struct iavf_priv_flags *priv_flags; + + priv_flags = &iavf_gstrings_priv_flags[i]; + + if (flags & BIT(i)) + new_flags |= priv_flags->flag; + else + new_flags &= ~(priv_flags->flag); + + if (priv_flags->read_only && + ((orig_flags ^ new_flags) & ~BIT(i))) + return -EOPNOTSUPP; + } + + /* Before we finalize any flag changes, any checks which we need to + * perform to determine if the new flags will be supported should go + * here... + */ + + /* Compare and exchange the new flags into place. If we failed, that + * is if cmpxchg returns anything but the old value, this means + * something else must have modified the flags variable since we + * copied it. We'll just punt with an error and log something in the + * message buffer. + */ + if (cmpxchg(&adapter->flags, orig_flags, new_flags) != orig_flags) { + dev_warn(&adapter->pdev->dev, + "Unable to update adapter->flags as it was modified by another thread...\n"); + return -EAGAIN; + } + + changed_flags = orig_flags ^ new_flags; + + /* Process any additional changes needed as a result of flag changes. + * The changed_flags value reflects the list of bits that were changed + * in the code above. + */ + + /* issue a reset to force legacy-rx change to take effect */ + if (changed_flags & IAVF_FLAG_LEGACY_RX) { + if (netif_running(netdev)) { + adapter->flags |= IAVF_FLAG_RESET_NEEDED; + schedule_work(&adapter->reset_task); + } + } + + return 0; +} + +/** + * iavf_get_msglevel - Get debug message level + * @netdev: network interface device structure + * + * Returns current debug message level. + **/ +static u32 iavf_get_msglevel(struct net_device *netdev) +{ + struct iavf_adapter *adapter = netdev_priv(netdev); + + return adapter->msg_enable; +} + +/** + * iavf_set_msglevel - Set debug message level + * @netdev: network interface device structure + * @data: message level + * + * Set current debug message level. Higher values cause the driver to + * be noisier. + **/ +static void iavf_set_msglevel(struct net_device *netdev, u32 data) +{ + struct iavf_adapter *adapter = netdev_priv(netdev); + + if (IAVF_DEBUG_USER & data) + adapter->hw.debug_mask = data; + adapter->msg_enable = data; +} + +/** + * iavf_get_drvinfo - Get driver info + * @netdev: network interface device structure + * @drvinfo: ethool driver info structure + * + * Returns information about the driver and device for display to the user. + **/ +static void iavf_get_drvinfo(struct net_device *netdev, + struct ethtool_drvinfo *drvinfo) +{ + struct iavf_adapter *adapter = netdev_priv(netdev); + + strlcpy(drvinfo->driver, iavf_driver_name, 32); + strlcpy(drvinfo->version, iavf_driver_version, 32); + strlcpy(drvinfo->fw_version, "N/A", 4); + strlcpy(drvinfo->bus_info, pci_name(adapter->pdev), 32); + drvinfo->n_priv_flags = IAVF_PRIV_FLAGS_STR_LEN; +} + +/** + * iavf_get_ringparam - Get ring parameters + * @netdev: network interface device structure + * @ring: ethtool ringparam structure + * + * Returns current ring parameters. TX and RX rings are reported separately, + * but the number of rings is not reported. + **/ +static void iavf_get_ringparam(struct net_device *netdev, + struct ethtool_ringparam *ring) +{ + struct iavf_adapter *adapter = netdev_priv(netdev); + + ring->rx_max_pending = IAVF_MAX_RXD; + ring->tx_max_pending = IAVF_MAX_TXD; + ring->rx_pending = adapter->rx_desc_count; + ring->tx_pending = adapter->tx_desc_count; +} + +/** + * iavf_set_ringparam - Set ring parameters + * @netdev: network interface device structure + * @ring: ethtool ringparam structure + * + * Sets ring parameters. TX and RX rings are controlled separately, but the + * number of rings is not specified, so all rings get the same settings. + **/ +static int iavf_set_ringparam(struct net_device *netdev, + struct ethtool_ringparam *ring) +{ + struct iavf_adapter *adapter = netdev_priv(netdev); + u32 new_rx_count, new_tx_count; + + if ((ring->rx_mini_pending) || (ring->rx_jumbo_pending)) + return -EINVAL; + + new_tx_count = clamp_t(u32, ring->tx_pending, + IAVF_MIN_TXD, + IAVF_MAX_TXD); + new_tx_count = ALIGN(new_tx_count, IAVF_REQ_DESCRIPTOR_MULTIPLE); + + new_rx_count = clamp_t(u32, ring->rx_pending, + IAVF_MIN_RXD, + IAVF_MAX_RXD); + new_rx_count = ALIGN(new_rx_count, IAVF_REQ_DESCRIPTOR_MULTIPLE); + + /* if nothing to do return success */ + if ((new_tx_count == adapter->tx_desc_count) && + (new_rx_count == adapter->rx_desc_count)) + return 0; + + adapter->tx_desc_count = new_tx_count; + adapter->rx_desc_count = new_rx_count; + + if (netif_running(netdev)) { + adapter->flags |= IAVF_FLAG_RESET_NEEDED; + schedule_work(&adapter->reset_task); + } + + return 0; +} + +/** + * __iavf_get_coalesce - get per-queue coalesce settings + * @netdev: the netdev to check + * @ec: ethtool coalesce data structure + * @queue: which queue to pick + * + * Gets the per-queue settings for coalescence. Specifically Rx and Tx usecs + * are per queue. If queue is <0 then we default to queue 0 as the + * representative value. + **/ +static int __iavf_get_coalesce(struct net_device *netdev, + struct ethtool_coalesce *ec, int queue) +{ + struct iavf_adapter *adapter = netdev_priv(netdev); + struct iavf_vsi *vsi = &adapter->vsi; + struct iavf_ring *rx_ring, *tx_ring; + + ec->tx_max_coalesced_frames = vsi->work_limit; + ec->rx_max_coalesced_frames = vsi->work_limit; + + /* Rx and Tx usecs per queue value. If user doesn't specify the + * queue, return queue 0's value to represent. + */ + if (queue < 0) + queue = 0; + else if (queue >= adapter->num_active_queues) + return -EINVAL; + + rx_ring = &adapter->rx_rings[queue]; + tx_ring = &adapter->tx_rings[queue]; + + if (ITR_IS_DYNAMIC(rx_ring->itr_setting)) + ec->use_adaptive_rx_coalesce = 1; + + if (ITR_IS_DYNAMIC(tx_ring->itr_setting)) + ec->use_adaptive_tx_coalesce = 1; + + ec->rx_coalesce_usecs = rx_ring->itr_setting & ~IAVF_ITR_DYNAMIC; + ec->tx_coalesce_usecs = tx_ring->itr_setting & ~IAVF_ITR_DYNAMIC; + + return 0; +} + +/** + * iavf_get_coalesce - Get interrupt coalescing settings + * @netdev: network interface device structure + * @ec: ethtool coalesce structure + * + * Returns current coalescing settings. This is referred to elsewhere in the + * driver as Interrupt Throttle Rate, as this is how the hardware describes + * this functionality. Note that if per-queue settings have been modified this + * only represents the settings of queue 0. + **/ +static int iavf_get_coalesce(struct net_device *netdev, + struct ethtool_coalesce *ec) +{ + return __iavf_get_coalesce(netdev, ec, -1); +} + +/** + * iavf_get_per_queue_coalesce - get coalesce values for specific queue + * @netdev: netdev to read + * @ec: coalesce settings from ethtool + * @queue: the queue to read + * + * Read specific queue's coalesce settings. + **/ +static int iavf_get_per_queue_coalesce(struct net_device *netdev, u32 queue, + struct ethtool_coalesce *ec) +{ + return __iavf_get_coalesce(netdev, ec, queue); +} + +/** + * iavf_set_itr_per_queue - set ITR values for specific queue + * @adapter: the VF adapter struct to set values for + * @ec: coalesce settings from ethtool + * @queue: the queue to modify + * + * Change the ITR settings for a specific queue. + **/ +static void iavf_set_itr_per_queue(struct iavf_adapter *adapter, + struct ethtool_coalesce *ec, int queue) +{ + struct iavf_ring *rx_ring = &adapter->rx_rings[queue]; + struct iavf_ring *tx_ring = &adapter->tx_rings[queue]; + struct iavf_q_vector *q_vector; + + rx_ring->itr_setting = ITR_REG_ALIGN(ec->rx_coalesce_usecs); + tx_ring->itr_setting = ITR_REG_ALIGN(ec->tx_coalesce_usecs); + + rx_ring->itr_setting |= IAVF_ITR_DYNAMIC; + if (!ec->use_adaptive_rx_coalesce) + rx_ring->itr_setting ^= IAVF_ITR_DYNAMIC; + + tx_ring->itr_setting |= IAVF_ITR_DYNAMIC; + if (!ec->use_adaptive_tx_coalesce) + tx_ring->itr_setting ^= IAVF_ITR_DYNAMIC; + + q_vector = rx_ring->q_vector; + q_vector->rx.target_itr = ITR_TO_REG(rx_ring->itr_setting); + + q_vector = tx_ring->q_vector; + q_vector->tx.target_itr = ITR_TO_REG(tx_ring->itr_setting); + + /* The interrupt handler itself will take care of programming + * the Tx and Rx ITR values based on the values we have entered + * into the q_vector, no need to write the values now. + */ +} + +/** + * __iavf_set_coalesce - set coalesce settings for particular queue + * @netdev: the netdev to change + * @ec: ethtool coalesce settings + * @queue: the queue to change + * + * Sets the coalesce settings for a particular queue. + **/ +static int __iavf_set_coalesce(struct net_device *netdev, + struct ethtool_coalesce *ec, int queue) +{ + struct iavf_adapter *adapter = netdev_priv(netdev); + struct iavf_vsi *vsi = &adapter->vsi; + int i; + + if (ec->tx_max_coalesced_frames_irq || ec->rx_max_coalesced_frames_irq) + vsi->work_limit = ec->tx_max_coalesced_frames_irq; + + if (ec->rx_coalesce_usecs == 0) { + if (ec->use_adaptive_rx_coalesce) + netif_info(adapter, drv, netdev, "rx-usecs=0, need to disable adaptive-rx for a complete disable\n"); + } else if ((ec->rx_coalesce_usecs < IAVF_MIN_ITR) || + (ec->rx_coalesce_usecs > IAVF_MAX_ITR)) { + netif_info(adapter, drv, netdev, "Invalid value, rx-usecs range is 0-8160\n"); + return -EINVAL; + } else if (ec->tx_coalesce_usecs == 0) { + if (ec->use_adaptive_tx_coalesce) + netif_info(adapter, drv, netdev, "tx-usecs=0, need to disable adaptive-tx for a complete disable\n"); + } else if ((ec->tx_coalesce_usecs < IAVF_MIN_ITR) || + (ec->tx_coalesce_usecs > IAVF_MAX_ITR)) { + netif_info(adapter, drv, netdev, "Invalid value, tx-usecs range is 0-8160\n"); + return -EINVAL; + } + + /* Rx and Tx usecs has per queue value. If user doesn't specify the + * queue, apply to all queues. + */ + if (queue < 0) { + for (i = 0; i < adapter->num_active_queues; i++) + iavf_set_itr_per_queue(adapter, ec, i); + } else if (queue < adapter->num_active_queues) { + iavf_set_itr_per_queue(adapter, ec, queue); + } else { + netif_info(adapter, drv, netdev, "Invalid queue value, queue range is 0 - %d\n", + adapter->num_active_queues - 1); + return -EINVAL; + } + + return 0; +} + +/** + * iavf_set_coalesce - Set interrupt coalescing settings + * @netdev: network interface device structure + * @ec: ethtool coalesce structure + * + * Change current coalescing settings for every queue. + **/ +static int iavf_set_coalesce(struct net_device *netdev, + struct ethtool_coalesce *ec) +{ + return __iavf_set_coalesce(netdev, ec, -1); +} + +/** + * iavf_set_per_queue_coalesce - set specific queue's coalesce settings + * @netdev: the netdev to change + * @ec: ethtool's coalesce settings + * @queue: the queue to modify + * + * Modifies a specific queue's coalesce settings. + */ +static int iavf_set_per_queue_coalesce(struct net_device *netdev, u32 queue, + struct ethtool_coalesce *ec) +{ + return __iavf_set_coalesce(netdev, ec, queue); +} + +/** + * iavf_get_rxnfc - command to get RX flow classification rules + * @netdev: network interface device structure + * @cmd: ethtool rxnfc command + * @rule_locs: pointer to store rule locations + * + * Returns Success if the command is supported. + **/ +static int iavf_get_rxnfc(struct net_device *netdev, struct ethtool_rxnfc *cmd, + u32 *rule_locs) +{ + struct iavf_adapter *adapter = netdev_priv(netdev); + int ret = -EOPNOTSUPP; + + switch (cmd->cmd) { + case ETHTOOL_GRXRINGS: + cmd->data = adapter->num_active_queues; + ret = 0; + break; + case ETHTOOL_GRXFH: + netdev_info(netdev, + "RSS hash info is not available to vf, use pf.\n"); + break; + default: + break; + } + + return ret; +} +/** + * iavf_get_channels: get the number of channels supported by the device + * @netdev: network interface device structure + * @ch: channel information structure + * + * For the purposes of our device, we only use combined channels, i.e. a tx/rx + * queue pair. Report one extra channel to match our "other" MSI-X vector. + **/ +static void iavf_get_channels(struct net_device *netdev, + struct ethtool_channels *ch) +{ + struct iavf_adapter *adapter = netdev_priv(netdev); + + /* Report maximum channels */ + ch->max_combined = IAVF_MAX_REQ_QUEUES; + + ch->max_other = NONQ_VECS; + ch->other_count = NONQ_VECS; + + ch->combined_count = adapter->num_active_queues; +} + +/** + * iavf_set_channels: set the new channel count + * @netdev: network interface device structure + * @ch: channel information structure + * + * Negotiate a new number of channels with the PF then do a reset. During + * reset we'll realloc queues and fix the RSS table. Returns 0 on success, + * negative on failure. + **/ +static int iavf_set_channels(struct net_device *netdev, + struct ethtool_channels *ch) +{ + struct iavf_adapter *adapter = netdev_priv(netdev); + int num_req = ch->combined_count; + + if (num_req != adapter->num_active_queues && + !(adapter->vf_res->vf_cap_flags & + VIRTCHNL_VF_OFFLOAD_REQ_QUEUES)) { + dev_info(&adapter->pdev->dev, "PF is not capable of queue negotiation.\n"); + return -EINVAL; + } + + if ((adapter->vf_res->vf_cap_flags & VIRTCHNL_VF_OFFLOAD_ADQ) && + adapter->num_tc) { + dev_info(&adapter->pdev->dev, "Cannot set channels since ADq is enabled.\n"); + return -EINVAL; + } + + /* All of these should have already been checked by ethtool before this + * even gets to us, but just to be sure. + */ + if (num_req <= 0 || num_req > IAVF_MAX_REQ_QUEUES) + return -EINVAL; + + if (ch->rx_count || ch->tx_count || ch->other_count != NONQ_VECS) + return -EINVAL; + + adapter->num_req_queues = num_req; + return iavf_request_queues(adapter, num_req); +} + +/** + * iavf_get_rxfh_key_size - get the RSS hash key size + * @netdev: network interface device structure + * + * Returns the table size. + **/ +static u32 iavf_get_rxfh_key_size(struct net_device *netdev) +{ + struct iavf_adapter *adapter = netdev_priv(netdev); + + return adapter->rss_key_size; +} + +/** + * iavf_get_rxfh_indir_size - get the rx flow hash indirection table size + * @netdev: network interface device structure + * + * Returns the table size. + **/ +static u32 iavf_get_rxfh_indir_size(struct net_device *netdev) +{ + struct iavf_adapter *adapter = netdev_priv(netdev); + + return adapter->rss_lut_size; +} + +/** + * iavf_get_rxfh - get the rx flow hash indirection table + * @netdev: network interface device structure + * @indir: indirection table + * @key: hash key + * @hfunc: hash function in use + * + * Reads the indirection table directly from the hardware. Always returns 0. + **/ +static int iavf_get_rxfh(struct net_device *netdev, u32 *indir, u8 *key, + u8 *hfunc) +{ + struct iavf_adapter *adapter = netdev_priv(netdev); + u16 i; + + if (hfunc) + *hfunc = ETH_RSS_HASH_TOP; + if (!indir) + return 0; + + memcpy(key, adapter->rss_key, adapter->rss_key_size); + + /* Each 32 bits pointed by 'indir' is stored with a lut entry */ + for (i = 0; i < adapter->rss_lut_size; i++) + indir[i] = (u32)adapter->rss_lut[i]; + + return 0; +} + +/** + * iavf_set_rxfh - set the rx flow hash indirection table + * @netdev: network interface device structure + * @indir: indirection table + * @key: hash key + * @hfunc: hash function to use + * + * Returns -EINVAL if the table specifies an inavlid queue id, otherwise + * returns 0 after programming the table. + **/ +static int iavf_set_rxfh(struct net_device *netdev, const u32 *indir, + const u8 *key, const u8 hfunc) +{ + struct iavf_adapter *adapter = netdev_priv(netdev); + u16 i; + + /* We do not allow change in unsupported parameters */ + if (key || + (hfunc != ETH_RSS_HASH_NO_CHANGE && hfunc != ETH_RSS_HASH_TOP)) + return -EOPNOTSUPP; + if (!indir) + return 0; + + if (key) + memcpy(adapter->rss_key, key, adapter->rss_key_size); + + /* Each 32 bits pointed by 'indir' is stored with a lut entry */ + for (i = 0; i < adapter->rss_lut_size; i++) + adapter->rss_lut[i] = (u8)(indir[i]); + + return iavf_config_rss(adapter); +} + +static const struct ethtool_ops iavf_ethtool_ops = { + .get_drvinfo = iavf_get_drvinfo, + .get_link = ethtool_op_get_link, + .get_ringparam = iavf_get_ringparam, + .set_ringparam = iavf_set_ringparam, + .get_strings = iavf_get_strings, + .get_ethtool_stats = iavf_get_ethtool_stats, + .get_sset_count = iavf_get_sset_count, + .get_priv_flags = iavf_get_priv_flags, + .set_priv_flags = iavf_set_priv_flags, + .get_msglevel = iavf_get_msglevel, + .set_msglevel = iavf_set_msglevel, + .get_coalesce = iavf_get_coalesce, + .set_coalesce = iavf_set_coalesce, + .get_per_queue_coalesce = iavf_get_per_queue_coalesce, + .set_per_queue_coalesce = iavf_set_per_queue_coalesce, + .get_rxnfc = iavf_get_rxnfc, + .get_rxfh_indir_size = iavf_get_rxfh_indir_size, + .get_rxfh = iavf_get_rxfh, + .set_rxfh = iavf_set_rxfh, + .get_channels = iavf_get_channels, + .set_channels = iavf_set_channels, + .get_rxfh_key_size = iavf_get_rxfh_key_size, + .get_link_ksettings = iavf_get_link_ksettings, +}; + +/** + * iavf_set_ethtool_ops - Initialize ethtool ops struct + * @netdev: network interface device structure + * + * Sets ethtool ops struct in our netdev so that ethtool can call + * our functions. + **/ +void iavf_set_ethtool_ops(struct net_device *netdev) +{ + netdev->ethtool_ops = &iavf_ethtool_ops; +} diff --git a/drivers/net/ethernet/intel/i40evf/i40evf_main.c b/drivers/net/ethernet/intel/iavf/iavf_main.c index 174d1da2857b..9f2b7b7adf6b 100644 --- a/drivers/net/ethernet/intel/i40evf/i40evf_main.c +++ b/drivers/net/ethernet/intel/iavf/iavf_main.c @@ -1,38 +1,38 @@ // SPDX-License-Identifier: GPL-2.0 /* Copyright(c) 2013 - 2018 Intel Corporation. */ -#include "i40evf.h" -#include "i40e_prototype.h" -#include "i40evf_client.h" -/* All i40evf tracepoints are defined by the include below, which must +#include "iavf.h" +#include "iavf_prototype.h" +#include "iavf_client.h" +/* All iavf tracepoints are defined by the include below, which must * be included exactly once across the whole kernel with * CREATE_TRACE_POINTS defined */ #define CREATE_TRACE_POINTS -#include "i40e_trace.h" +#include "iavf_trace.h" -static int i40evf_setup_all_tx_resources(struct i40evf_adapter *adapter); -static int i40evf_setup_all_rx_resources(struct i40evf_adapter *adapter); -static int i40evf_close(struct net_device *netdev); +static int iavf_setup_all_tx_resources(struct iavf_adapter *adapter); +static int iavf_setup_all_rx_resources(struct iavf_adapter *adapter); +static int iavf_close(struct net_device *netdev); -char i40evf_driver_name[] = "i40evf"; -static const char i40evf_driver_string[] = - "Intel(R) 40-10 Gigabit Virtual Function Network Driver"; +char iavf_driver_name[] = "iavf"; +static const char iavf_driver_string[] = + "Intel(R) Ethernet Adaptive Virtual Function Network Driver"; #define DRV_KERN "-k" #define DRV_VERSION_MAJOR 3 #define DRV_VERSION_MINOR 2 -#define DRV_VERSION_BUILD 2 +#define DRV_VERSION_BUILD 3 #define DRV_VERSION __stringify(DRV_VERSION_MAJOR) "." \ __stringify(DRV_VERSION_MINOR) "." \ __stringify(DRV_VERSION_BUILD) \ DRV_KERN -const char i40evf_driver_version[] = DRV_VERSION; -static const char i40evf_copyright[] = - "Copyright (c) 2013 - 2015 Intel Corporation."; +const char iavf_driver_version[] = DRV_VERSION; +static const char iavf_copyright[] = + "Copyright (c) 2013 - 2018 Intel Corporation."; -/* i40evf_pci_tbl - PCI Device ID Table +/* iavf_pci_tbl - PCI Device ID Table * * Wildcard entries (PCI_ANY_ID) should come last * Last entry must be all 0s @@ -40,36 +40,37 @@ static const char i40evf_copyright[] = * { Vendor ID, Device ID, SubVendor ID, SubDevice ID, * Class, Class Mask, private data (not used) } */ -static const struct pci_device_id i40evf_pci_tbl[] = { - {PCI_VDEVICE(INTEL, I40E_DEV_ID_VF), 0}, - {PCI_VDEVICE(INTEL, I40E_DEV_ID_VF_HV), 0}, - {PCI_VDEVICE(INTEL, I40E_DEV_ID_X722_VF), 0}, - {PCI_VDEVICE(INTEL, I40E_DEV_ID_ADAPTIVE_VF), 0}, +static const struct pci_device_id iavf_pci_tbl[] = { + {PCI_VDEVICE(INTEL, IAVF_DEV_ID_VF), 0}, + {PCI_VDEVICE(INTEL, IAVF_DEV_ID_VF_HV), 0}, + {PCI_VDEVICE(INTEL, IAVF_DEV_ID_X722_VF), 0}, + {PCI_VDEVICE(INTEL, IAVF_DEV_ID_ADAPTIVE_VF), 0}, /* required last entry */ {0, } }; -MODULE_DEVICE_TABLE(pci, i40evf_pci_tbl); +MODULE_DEVICE_TABLE(pci, iavf_pci_tbl); +MODULE_ALIAS("i40evf"); MODULE_AUTHOR("Intel Corporation, <linux.nics@intel.com>"); -MODULE_DESCRIPTION("Intel(R) XL710 X710 Virtual Function Network Driver"); -MODULE_LICENSE("GPL"); +MODULE_DESCRIPTION("Intel(R) Ethernet Adaptive Virtual Function Network Driver"); +MODULE_LICENSE("GPL v2"); MODULE_VERSION(DRV_VERSION); -static struct workqueue_struct *i40evf_wq; +static struct workqueue_struct *iavf_wq; /** - * i40evf_allocate_dma_mem_d - OS specific memory alloc for shared code + * iavf_allocate_dma_mem_d - OS specific memory alloc for shared code * @hw: pointer to the HW structure * @mem: ptr to mem struct to fill out * @size: size of memory requested * @alignment: what to align the allocation to **/ -i40e_status i40evf_allocate_dma_mem_d(struct i40e_hw *hw, - struct i40e_dma_mem *mem, - u64 size, u32 alignment) +iavf_status iavf_allocate_dma_mem_d(struct iavf_hw *hw, + struct iavf_dma_mem *mem, + u64 size, u32 alignment) { - struct i40evf_adapter *adapter = (struct i40evf_adapter *)hw->back; + struct iavf_adapter *adapter = (struct iavf_adapter *)hw->back; if (!mem) return I40E_ERR_PARAM; @@ -84,13 +85,13 @@ i40e_status i40evf_allocate_dma_mem_d(struct i40e_hw *hw, } /** - * i40evf_free_dma_mem_d - OS specific memory free for shared code + * iavf_free_dma_mem_d - OS specific memory free for shared code * @hw: pointer to the HW structure * @mem: ptr to mem struct to free **/ -i40e_status i40evf_free_dma_mem_d(struct i40e_hw *hw, struct i40e_dma_mem *mem) +iavf_status iavf_free_dma_mem_d(struct iavf_hw *hw, struct iavf_dma_mem *mem) { - struct i40evf_adapter *adapter = (struct i40evf_adapter *)hw->back; + struct iavf_adapter *adapter = (struct iavf_adapter *)hw->back; if (!mem || !mem->va) return I40E_ERR_PARAM; @@ -100,13 +101,13 @@ i40e_status i40evf_free_dma_mem_d(struct i40e_hw *hw, struct i40e_dma_mem *mem) } /** - * i40evf_allocate_virt_mem_d - OS specific memory alloc for shared code + * iavf_allocate_virt_mem_d - OS specific memory alloc for shared code * @hw: pointer to the HW structure * @mem: ptr to mem struct to fill out * @size: size of memory requested **/ -i40e_status i40evf_allocate_virt_mem_d(struct i40e_hw *hw, - struct i40e_virt_mem *mem, u32 size) +iavf_status iavf_allocate_virt_mem_d(struct iavf_hw *hw, + struct iavf_virt_mem *mem, u32 size) { if (!mem) return I40E_ERR_PARAM; @@ -121,12 +122,11 @@ i40e_status i40evf_allocate_virt_mem_d(struct i40e_hw *hw, } /** - * i40evf_free_virt_mem_d - OS specific memory free for shared code + * iavf_free_virt_mem_d - OS specific memory free for shared code * @hw: pointer to the HW structure * @mem: ptr to mem struct to free **/ -i40e_status i40evf_free_virt_mem_d(struct i40e_hw *hw, - struct i40e_virt_mem *mem) +iavf_status iavf_free_virt_mem_d(struct iavf_hw *hw, struct iavf_virt_mem *mem) { if (!mem) return I40E_ERR_PARAM; @@ -138,17 +138,17 @@ i40e_status i40evf_free_virt_mem_d(struct i40e_hw *hw, } /** - * i40evf_debug_d - OS dependent version of debug printing + * iavf_debug_d - OS dependent version of debug printing * @hw: pointer to the HW structure * @mask: debug level mask * @fmt_str: printf-type format description **/ -void i40evf_debug_d(void *hw, u32 mask, char *fmt_str, ...) +void iavf_debug_d(void *hw, u32 mask, char *fmt_str, ...) { char buf[512]; va_list argptr; - if (!(mask & ((struct i40e_hw *)hw)->debug_mask)) + if (!(mask & ((struct iavf_hw *)hw)->debug_mask)) return; va_start(argptr, fmt_str); @@ -160,134 +160,131 @@ void i40evf_debug_d(void *hw, u32 mask, char *fmt_str, ...) } /** - * i40evf_schedule_reset - Set the flags and schedule a reset event + * iavf_schedule_reset - Set the flags and schedule a reset event * @adapter: board private structure **/ -void i40evf_schedule_reset(struct i40evf_adapter *adapter) +void iavf_schedule_reset(struct iavf_adapter *adapter) { if (!(adapter->flags & - (I40EVF_FLAG_RESET_PENDING | I40EVF_FLAG_RESET_NEEDED))) { - adapter->flags |= I40EVF_FLAG_RESET_NEEDED; + (IAVF_FLAG_RESET_PENDING | IAVF_FLAG_RESET_NEEDED))) { + adapter->flags |= IAVF_FLAG_RESET_NEEDED; schedule_work(&adapter->reset_task); } } /** - * i40evf_tx_timeout - Respond to a Tx Hang + * iavf_tx_timeout - Respond to a Tx Hang * @netdev: network interface device structure **/ -static void i40evf_tx_timeout(struct net_device *netdev) +static void iavf_tx_timeout(struct net_device *netdev) { - struct i40evf_adapter *adapter = netdev_priv(netdev); + struct iavf_adapter *adapter = netdev_priv(netdev); adapter->tx_timeout_count++; - i40evf_schedule_reset(adapter); + iavf_schedule_reset(adapter); } /** - * i40evf_misc_irq_disable - Mask off interrupt generation on the NIC + * iavf_misc_irq_disable - Mask off interrupt generation on the NIC * @adapter: board private structure **/ -static void i40evf_misc_irq_disable(struct i40evf_adapter *adapter) +static void iavf_misc_irq_disable(struct iavf_adapter *adapter) { - struct i40e_hw *hw = &adapter->hw; + struct iavf_hw *hw = &adapter->hw; if (!adapter->msix_entries) return; - wr32(hw, I40E_VFINT_DYN_CTL01, 0); + wr32(hw, IAVF_VFINT_DYN_CTL01, 0); - /* read flush */ - rd32(hw, I40E_VFGEN_RSTAT); + iavf_flush(hw); synchronize_irq(adapter->msix_entries[0].vector); } /** - * i40evf_misc_irq_enable - Enable default interrupt generation settings + * iavf_misc_irq_enable - Enable default interrupt generation settings * @adapter: board private structure **/ -static void i40evf_misc_irq_enable(struct i40evf_adapter *adapter) +static void iavf_misc_irq_enable(struct iavf_adapter *adapter) { - struct i40e_hw *hw = &adapter->hw; + struct iavf_hw *hw = &adapter->hw; - wr32(hw, I40E_VFINT_DYN_CTL01, I40E_VFINT_DYN_CTL01_INTENA_MASK | - I40E_VFINT_DYN_CTL01_ITR_INDX_MASK); - wr32(hw, I40E_VFINT_ICR0_ENA1, I40E_VFINT_ICR0_ENA1_ADMINQ_MASK); + wr32(hw, IAVF_VFINT_DYN_CTL01, IAVF_VFINT_DYN_CTL01_INTENA_MASK | + IAVF_VFINT_DYN_CTL01_ITR_INDX_MASK); + wr32(hw, IAVF_VFINT_ICR0_ENA1, IAVF_VFINT_ICR0_ENA1_ADMINQ_MASK); - /* read flush */ - rd32(hw, I40E_VFGEN_RSTAT); + iavf_flush(hw); } /** - * i40evf_irq_disable - Mask off interrupt generation on the NIC + * iavf_irq_disable - Mask off interrupt generation on the NIC * @adapter: board private structure **/ -static void i40evf_irq_disable(struct i40evf_adapter *adapter) +static void iavf_irq_disable(struct iavf_adapter *adapter) { int i; - struct i40e_hw *hw = &adapter->hw; + struct iavf_hw *hw = &adapter->hw; if (!adapter->msix_entries) return; for (i = 1; i < adapter->num_msix_vectors; i++) { - wr32(hw, I40E_VFINT_DYN_CTLN1(i - 1), 0); + wr32(hw, IAVF_VFINT_DYN_CTLN1(i - 1), 0); synchronize_irq(adapter->msix_entries[i].vector); } - /* read flush */ - rd32(hw, I40E_VFGEN_RSTAT); + iavf_flush(hw); } /** - * i40evf_irq_enable_queues - Enable interrupt for specified queues + * iavf_irq_enable_queues - Enable interrupt for specified queues * @adapter: board private structure * @mask: bitmap of queues to enable **/ -void i40evf_irq_enable_queues(struct i40evf_adapter *adapter, u32 mask) +void iavf_irq_enable_queues(struct iavf_adapter *adapter, u32 mask) { - struct i40e_hw *hw = &adapter->hw; + struct iavf_hw *hw = &adapter->hw; int i; for (i = 1; i < adapter->num_msix_vectors; i++) { if (mask & BIT(i - 1)) { - wr32(hw, I40E_VFINT_DYN_CTLN1(i - 1), - I40E_VFINT_DYN_CTLN1_INTENA_MASK | - I40E_VFINT_DYN_CTLN1_ITR_INDX_MASK); + wr32(hw, IAVF_VFINT_DYN_CTLN1(i - 1), + IAVF_VFINT_DYN_CTLN1_INTENA_MASK | + IAVF_VFINT_DYN_CTLN1_ITR_INDX_MASK); } } } /** - * i40evf_irq_enable - Enable default interrupt generation settings + * iavf_irq_enable - Enable default interrupt generation settings * @adapter: board private structure * @flush: boolean value whether to run rd32() **/ -void i40evf_irq_enable(struct i40evf_adapter *adapter, bool flush) +void iavf_irq_enable(struct iavf_adapter *adapter, bool flush) { - struct i40e_hw *hw = &adapter->hw; + struct iavf_hw *hw = &adapter->hw; - i40evf_misc_irq_enable(adapter); - i40evf_irq_enable_queues(adapter, ~0); + iavf_misc_irq_enable(adapter); + iavf_irq_enable_queues(adapter, ~0); if (flush) - rd32(hw, I40E_VFGEN_RSTAT); + iavf_flush(hw); } /** - * i40evf_msix_aq - Interrupt handler for vector 0 + * iavf_msix_aq - Interrupt handler for vector 0 * @irq: interrupt number * @data: pointer to netdev **/ -static irqreturn_t i40evf_msix_aq(int irq, void *data) +static irqreturn_t iavf_msix_aq(int irq, void *data) { struct net_device *netdev = data; - struct i40evf_adapter *adapter = netdev_priv(netdev); - struct i40e_hw *hw = &adapter->hw; + struct iavf_adapter *adapter = netdev_priv(netdev); + struct iavf_hw *hw = &adapter->hw; /* handle non-queue interrupts, these reads clear the registers */ - rd32(hw, I40E_VFINT_ICR01); - rd32(hw, I40E_VFINT_ICR0_ENA1); + rd32(hw, IAVF_VFINT_ICR01); + rd32(hw, IAVF_VFINT_ICR0_ENA1); /* schedule work on the private workqueue */ schedule_work(&adapter->adminq_task); @@ -296,13 +293,13 @@ static irqreturn_t i40evf_msix_aq(int irq, void *data) } /** - * i40evf_msix_clean_rings - MSIX mode Interrupt Handler + * iavf_msix_clean_rings - MSIX mode Interrupt Handler * @irq: interrupt number * @data: pointer to a q_vector **/ -static irqreturn_t i40evf_msix_clean_rings(int irq, void *data) +static irqreturn_t iavf_msix_clean_rings(int irq, void *data) { - struct i40e_q_vector *q_vector = data; + struct iavf_q_vector *q_vector = data; if (!q_vector->tx.ring && !q_vector->rx.ring) return IRQ_HANDLED; @@ -313,17 +310,17 @@ static irqreturn_t i40evf_msix_clean_rings(int irq, void *data) } /** - * i40evf_map_vector_to_rxq - associate irqs with rx queues + * iavf_map_vector_to_rxq - associate irqs with rx queues * @adapter: board private structure * @v_idx: interrupt number * @r_idx: queue number **/ static void -i40evf_map_vector_to_rxq(struct i40evf_adapter *adapter, int v_idx, int r_idx) +iavf_map_vector_to_rxq(struct iavf_adapter *adapter, int v_idx, int r_idx) { - struct i40e_q_vector *q_vector = &adapter->q_vectors[v_idx]; - struct i40e_ring *rx_ring = &adapter->rx_rings[r_idx]; - struct i40e_hw *hw = &adapter->hw; + struct iavf_q_vector *q_vector = &adapter->q_vectors[v_idx]; + struct iavf_ring *rx_ring = &adapter->rx_rings[r_idx]; + struct iavf_hw *hw = &adapter->hw; rx_ring->q_vector = q_vector; rx_ring->next = q_vector->rx.ring; @@ -333,23 +330,23 @@ i40evf_map_vector_to_rxq(struct i40evf_adapter *adapter, int v_idx, int r_idx) q_vector->rx.next_update = jiffies + 1; q_vector->rx.target_itr = ITR_TO_REG(rx_ring->itr_setting); q_vector->ring_mask |= BIT(r_idx); - wr32(hw, I40E_VFINT_ITRN1(I40E_RX_ITR, q_vector->reg_idx), + wr32(hw, IAVF_VFINT_ITRN1(IAVF_RX_ITR, q_vector->reg_idx), q_vector->rx.current_itr); q_vector->rx.current_itr = q_vector->rx.target_itr; } /** - * i40evf_map_vector_to_txq - associate irqs with tx queues + * iavf_map_vector_to_txq - associate irqs with tx queues * @adapter: board private structure * @v_idx: interrupt number * @t_idx: queue number **/ static void -i40evf_map_vector_to_txq(struct i40evf_adapter *adapter, int v_idx, int t_idx) +iavf_map_vector_to_txq(struct iavf_adapter *adapter, int v_idx, int t_idx) { - struct i40e_q_vector *q_vector = &adapter->q_vectors[v_idx]; - struct i40e_ring *tx_ring = &adapter->tx_rings[t_idx]; - struct i40e_hw *hw = &adapter->hw; + struct iavf_q_vector *q_vector = &adapter->q_vectors[v_idx]; + struct iavf_ring *tx_ring = &adapter->tx_rings[t_idx]; + struct iavf_hw *hw = &adapter->hw; tx_ring->q_vector = q_vector; tx_ring->next = q_vector->tx.ring; @@ -359,13 +356,13 @@ i40evf_map_vector_to_txq(struct i40evf_adapter *adapter, int v_idx, int t_idx) q_vector->tx.next_update = jiffies + 1; q_vector->tx.target_itr = ITR_TO_REG(tx_ring->itr_setting); q_vector->num_ringpairs++; - wr32(hw, I40E_VFINT_ITRN1(I40E_TX_ITR, q_vector->reg_idx), + wr32(hw, IAVF_VFINT_ITRN1(IAVF_TX_ITR, q_vector->reg_idx), q_vector->tx.target_itr); q_vector->tx.current_itr = q_vector->tx.target_itr; } /** - * i40evf_map_rings_to_vectors - Maps descriptor rings to vectors + * iavf_map_rings_to_vectors - Maps descriptor rings to vectors * @adapter: board private structure to initialize * * This function maps descriptor rings to the queue-specific vectors @@ -374,7 +371,7 @@ i40evf_map_vector_to_txq(struct i40evf_adapter *adapter, int v_idx, int t_idx) * group the rings as "efficiently" as possible. You would add new * mapping configurations in here. **/ -static void i40evf_map_rings_to_vectors(struct i40evf_adapter *adapter) +static void iavf_map_rings_to_vectors(struct iavf_adapter *adapter) { int rings_remaining = adapter->num_active_queues; int ridx = 0, vidx = 0; @@ -383,8 +380,8 @@ static void i40evf_map_rings_to_vectors(struct i40evf_adapter *adapter) q_vectors = adapter->num_msix_vectors - NONQ_VECS; for (; ridx < rings_remaining; ridx++) { - i40evf_map_vector_to_rxq(adapter, vidx, ridx); - i40evf_map_vector_to_txq(adapter, vidx, ridx); + iavf_map_vector_to_rxq(adapter, vidx, ridx); + iavf_map_vector_to_txq(adapter, vidx, ridx); /* In the case where we have more queues than vectors, continue * round-robin on vectors until all queues are mapped. @@ -393,61 +390,38 @@ static void i40evf_map_rings_to_vectors(struct i40evf_adapter *adapter) vidx = 0; } - adapter->aq_required |= I40EVF_FLAG_AQ_MAP_VECTORS; + adapter->aq_required |= IAVF_FLAG_AQ_MAP_VECTORS; } -#ifdef CONFIG_NET_POLL_CONTROLLER /** - * i40evf_netpoll - A Polling 'interrupt' handler - * @netdev: network interface device structure - * - * This is used by netconsole to send skbs without having to re-enable - * interrupts. It's not called while the normal interrupt routine is executing. - **/ -static void i40evf_netpoll(struct net_device *netdev) -{ - struct i40evf_adapter *adapter = netdev_priv(netdev); - int q_vectors = adapter->num_msix_vectors - NONQ_VECS; - int i; - - /* if interface is down do nothing */ - if (test_bit(__I40E_VSI_DOWN, adapter->vsi.state)) - return; - - for (i = 0; i < q_vectors; i++) - i40evf_msix_clean_rings(0, &adapter->q_vectors[i]); -} - -#endif -/** - * i40evf_irq_affinity_notify - Callback for affinity changes + * iavf_irq_affinity_notify - Callback for affinity changes * @notify: context as to what irq was changed * @mask: the new affinity mask * * This is a callback function used by the irq_set_affinity_notifier function * so that we may register to receive changes to the irq affinity masks. **/ -static void i40evf_irq_affinity_notify(struct irq_affinity_notify *notify, - const cpumask_t *mask) +static void iavf_irq_affinity_notify(struct irq_affinity_notify *notify, + const cpumask_t *mask) { - struct i40e_q_vector *q_vector = - container_of(notify, struct i40e_q_vector, affinity_notify); + struct iavf_q_vector *q_vector = + container_of(notify, struct iavf_q_vector, affinity_notify); cpumask_copy(&q_vector->affinity_mask, mask); } /** - * i40evf_irq_affinity_release - Callback for affinity notifier release + * iavf_irq_affinity_release - Callback for affinity notifier release * @ref: internal core kernel usage * * This is a callback function used by the irq_set_affinity_notifier function * to inform the current notification subscriber that they will no longer * receive notifications. **/ -static void i40evf_irq_affinity_release(struct kref *ref) {} +static void iavf_irq_affinity_release(struct kref *ref) {} /** - * i40evf_request_traffic_irqs - Initialize MSI-X interrupts + * iavf_request_traffic_irqs - Initialize MSI-X interrupts * @adapter: board private structure * @basename: device basename * @@ -455,37 +429,38 @@ static void i40evf_irq_affinity_release(struct kref *ref) {} * interrupts from the kernel. **/ static int -i40evf_request_traffic_irqs(struct i40evf_adapter *adapter, char *basename) +iavf_request_traffic_irqs(struct iavf_adapter *adapter, char *basename) { unsigned int vector, q_vectors; unsigned int rx_int_idx = 0, tx_int_idx = 0; int irq_num, err; int cpu; - i40evf_irq_disable(adapter); + iavf_irq_disable(adapter); /* Decrement for Other and TCP Timer vectors */ q_vectors = adapter->num_msix_vectors - NONQ_VECS; for (vector = 0; vector < q_vectors; vector++) { - struct i40e_q_vector *q_vector = &adapter->q_vectors[vector]; + struct iavf_q_vector *q_vector = &adapter->q_vectors[vector]; + irq_num = adapter->msix_entries[vector + NONQ_VECS].vector; if (q_vector->tx.ring && q_vector->rx.ring) { snprintf(q_vector->name, sizeof(q_vector->name), - "i40evf-%s-TxRx-%d", basename, rx_int_idx++); + "iavf-%s-TxRx-%d", basename, rx_int_idx++); tx_int_idx++; } else if (q_vector->rx.ring) { snprintf(q_vector->name, sizeof(q_vector->name), - "i40evf-%s-rx-%d", basename, rx_int_idx++); + "iavf-%s-rx-%d", basename, rx_int_idx++); } else if (q_vector->tx.ring) { snprintf(q_vector->name, sizeof(q_vector->name), - "i40evf-%s-tx-%d", basename, tx_int_idx++); + "iavf-%s-tx-%d", basename, tx_int_idx++); } else { /* skip this unused q_vector */ continue; } err = request_irq(irq_num, - i40evf_msix_clean_rings, + iavf_msix_clean_rings, 0, q_vector->name, q_vector); @@ -495,9 +470,9 @@ i40evf_request_traffic_irqs(struct i40evf_adapter *adapter, char *basename) goto free_queue_irqs; } /* register for affinity change notifications */ - q_vector->affinity_notify.notify = i40evf_irq_affinity_notify; + q_vector->affinity_notify.notify = iavf_irq_affinity_notify; q_vector->affinity_notify.release = - i40evf_irq_affinity_release; + iavf_irq_affinity_release; irq_set_affinity_notifier(irq_num, &q_vector->affinity_notify); /* Spread the IRQ affinity hints across online CPUs. Note that * get_cpu_mask returns a mask with a permanent lifetime so @@ -521,23 +496,23 @@ free_queue_irqs: } /** - * i40evf_request_misc_irq - Initialize MSI-X interrupts + * iavf_request_misc_irq - Initialize MSI-X interrupts * @adapter: board private structure * * Allocates MSI-X vector 0 and requests interrupts from the kernel. This * vector is only for the admin queue, and stays active even when the netdev * is closed. **/ -static int i40evf_request_misc_irq(struct i40evf_adapter *adapter) +static int iavf_request_misc_irq(struct iavf_adapter *adapter) { struct net_device *netdev = adapter->netdev; int err; snprintf(adapter->misc_vector_name, - sizeof(adapter->misc_vector_name) - 1, "i40evf-%s:mbx", + sizeof(adapter->misc_vector_name) - 1, "iavf-%s:mbx", dev_name(&adapter->pdev->dev)); err = request_irq(adapter->msix_entries[0].vector, - &i40evf_msix_aq, 0, + &iavf_msix_aq, 0, adapter->misc_vector_name, netdev); if (err) { dev_err(&adapter->pdev->dev, @@ -549,12 +524,12 @@ static int i40evf_request_misc_irq(struct i40evf_adapter *adapter) } /** - * i40evf_free_traffic_irqs - Free MSI-X interrupts + * iavf_free_traffic_irqs - Free MSI-X interrupts * @adapter: board private structure * * Frees all MSI-X vectors other than 0. **/ -static void i40evf_free_traffic_irqs(struct i40evf_adapter *adapter) +static void iavf_free_traffic_irqs(struct iavf_adapter *adapter) { int vector, irq_num, q_vectors; @@ -572,12 +547,12 @@ static void i40evf_free_traffic_irqs(struct i40evf_adapter *adapter) } /** - * i40evf_free_misc_irq - Free MSI-X miscellaneous vector + * iavf_free_misc_irq - Free MSI-X miscellaneous vector * @adapter: board private structure * * Frees MSI-X vector 0. **/ -static void i40evf_free_misc_irq(struct i40evf_adapter *adapter) +static void iavf_free_misc_irq(struct iavf_adapter *adapter) { struct net_device *netdev = adapter->netdev; @@ -588,58 +563,58 @@ static void i40evf_free_misc_irq(struct i40evf_adapter *adapter) } /** - * i40evf_configure_tx - Configure Transmit Unit after Reset + * iavf_configure_tx - Configure Transmit Unit after Reset * @adapter: board private structure * * Configure the Tx unit of the MAC after a reset. **/ -static void i40evf_configure_tx(struct i40evf_adapter *adapter) +static void iavf_configure_tx(struct iavf_adapter *adapter) { - struct i40e_hw *hw = &adapter->hw; + struct iavf_hw *hw = &adapter->hw; int i; for (i = 0; i < adapter->num_active_queues; i++) - adapter->tx_rings[i].tail = hw->hw_addr + I40E_QTX_TAIL1(i); + adapter->tx_rings[i].tail = hw->hw_addr + IAVF_QTX_TAIL1(i); } /** - * i40evf_configure_rx - Configure Receive Unit after Reset + * iavf_configure_rx - Configure Receive Unit after Reset * @adapter: board private structure * * Configure the Rx unit of the MAC after a reset. **/ -static void i40evf_configure_rx(struct i40evf_adapter *adapter) +static void iavf_configure_rx(struct iavf_adapter *adapter) { - unsigned int rx_buf_len = I40E_RXBUFFER_2048; - struct i40e_hw *hw = &adapter->hw; + unsigned int rx_buf_len = IAVF_RXBUFFER_2048; + struct iavf_hw *hw = &adapter->hw; int i; /* Legacy Rx will always default to a 2048 buffer size. */ #if (PAGE_SIZE < 8192) - if (!(adapter->flags & I40EVF_FLAG_LEGACY_RX)) { + if (!(adapter->flags & IAVF_FLAG_LEGACY_RX)) { struct net_device *netdev = adapter->netdev; /* For jumbo frames on systems with 4K pages we have to use * an order 1 page, so we might as well increase the size * of our Rx buffer to make better use of the available space */ - rx_buf_len = I40E_RXBUFFER_3072; + rx_buf_len = IAVF_RXBUFFER_3072; /* We use a 1536 buffer size for configurations with * standard Ethernet mtu. On x86 this gives us enough room * for shared info and 192 bytes of padding. */ - if (!I40E_2K_TOO_SMALL_WITH_PADDING && + if (!IAVF_2K_TOO_SMALL_WITH_PADDING && (netdev->mtu <= ETH_DATA_LEN)) - rx_buf_len = I40E_RXBUFFER_1536 - NET_IP_ALIGN; + rx_buf_len = IAVF_RXBUFFER_1536 - NET_IP_ALIGN; } #endif for (i = 0; i < adapter->num_active_queues; i++) { - adapter->rx_rings[i].tail = hw->hw_addr + I40E_QRX_TAIL1(i); + adapter->rx_rings[i].tail = hw->hw_addr + IAVF_QRX_TAIL1(i); adapter->rx_rings[i].rx_buf_len = rx_buf_len; - if (adapter->flags & I40EVF_FLAG_LEGACY_RX) + if (adapter->flags & IAVF_FLAG_LEGACY_RX) clear_ring_build_skb_enabled(&adapter->rx_rings[i]); else set_ring_build_skb_enabled(&adapter->rx_rings[i]); @@ -647,7 +622,7 @@ static void i40evf_configure_rx(struct i40evf_adapter *adapter) } /** - * i40evf_find_vlan - Search filter list for specific vlan filter + * iavf_find_vlan - Search filter list for specific vlan filter * @adapter: board private structure * @vlan: vlan tag * @@ -655,9 +630,9 @@ static void i40evf_configure_rx(struct i40evf_adapter *adapter) * mac_vlan_list_lock. **/ static struct -i40evf_vlan_filter *i40evf_find_vlan(struct i40evf_adapter *adapter, u16 vlan) +iavf_vlan_filter *iavf_find_vlan(struct iavf_adapter *adapter, u16 vlan) { - struct i40evf_vlan_filter *f; + struct iavf_vlan_filter *f; list_for_each_entry(f, &adapter->vlan_filter_list, list) { if (vlan == f->vlan) @@ -667,20 +642,20 @@ i40evf_vlan_filter *i40evf_find_vlan(struct i40evf_adapter *adapter, u16 vlan) } /** - * i40evf_add_vlan - Add a vlan filter to the list + * iavf_add_vlan - Add a vlan filter to the list * @adapter: board private structure * @vlan: VLAN tag * * Returns ptr to the filter object or NULL when no memory available. **/ static struct -i40evf_vlan_filter *i40evf_add_vlan(struct i40evf_adapter *adapter, u16 vlan) +iavf_vlan_filter *iavf_add_vlan(struct iavf_adapter *adapter, u16 vlan) { - struct i40evf_vlan_filter *f = NULL; + struct iavf_vlan_filter *f = NULL; spin_lock_bh(&adapter->mac_vlan_list_lock); - f = i40evf_find_vlan(adapter, vlan); + f = iavf_find_vlan(adapter, vlan); if (!f) { f = kzalloc(sizeof(*f), GFP_KERNEL); if (!f) @@ -691,7 +666,7 @@ i40evf_vlan_filter *i40evf_add_vlan(struct i40evf_adapter *adapter, u16 vlan) INIT_LIST_HEAD(&f->list); list_add(&f->list, &adapter->vlan_filter_list); f->add = true; - adapter->aq_required |= I40EVF_FLAG_AQ_ADD_VLAN_FILTER; + adapter->aq_required |= IAVF_FLAG_AQ_ADD_VLAN_FILTER; } clearout: @@ -700,63 +675,63 @@ clearout: } /** - * i40evf_del_vlan - Remove a vlan filter from the list + * iavf_del_vlan - Remove a vlan filter from the list * @adapter: board private structure * @vlan: VLAN tag **/ -static void i40evf_del_vlan(struct i40evf_adapter *adapter, u16 vlan) +static void iavf_del_vlan(struct iavf_adapter *adapter, u16 vlan) { - struct i40evf_vlan_filter *f; + struct iavf_vlan_filter *f; spin_lock_bh(&adapter->mac_vlan_list_lock); - f = i40evf_find_vlan(adapter, vlan); + f = iavf_find_vlan(adapter, vlan); if (f) { f->remove = true; - adapter->aq_required |= I40EVF_FLAG_AQ_DEL_VLAN_FILTER; + adapter->aq_required |= IAVF_FLAG_AQ_DEL_VLAN_FILTER; } spin_unlock_bh(&adapter->mac_vlan_list_lock); } /** - * i40evf_vlan_rx_add_vid - Add a VLAN filter to a device + * iavf_vlan_rx_add_vid - Add a VLAN filter to a device * @netdev: network device struct * @proto: unused protocol data * @vid: VLAN tag **/ -static int i40evf_vlan_rx_add_vid(struct net_device *netdev, - __always_unused __be16 proto, u16 vid) +static int iavf_vlan_rx_add_vid(struct net_device *netdev, + __always_unused __be16 proto, u16 vid) { - struct i40evf_adapter *adapter = netdev_priv(netdev); + struct iavf_adapter *adapter = netdev_priv(netdev); if (!VLAN_ALLOWED(adapter)) return -EIO; - if (i40evf_add_vlan(adapter, vid) == NULL) + if (iavf_add_vlan(adapter, vid) == NULL) return -ENOMEM; return 0; } /** - * i40evf_vlan_rx_kill_vid - Remove a VLAN filter from a device + * iavf_vlan_rx_kill_vid - Remove a VLAN filter from a device * @netdev: network device struct * @proto: unused protocol data * @vid: VLAN tag **/ -static int i40evf_vlan_rx_kill_vid(struct net_device *netdev, - __always_unused __be16 proto, u16 vid) +static int iavf_vlan_rx_kill_vid(struct net_device *netdev, + __always_unused __be16 proto, u16 vid) { - struct i40evf_adapter *adapter = netdev_priv(netdev); + struct iavf_adapter *adapter = netdev_priv(netdev); if (VLAN_ALLOWED(adapter)) { - i40evf_del_vlan(adapter, vid); + iavf_del_vlan(adapter, vid); return 0; } return -EIO; } /** - * i40evf_find_filter - Search filter list for specific mac filter + * iavf_find_filter - Search filter list for specific mac filter * @adapter: board private structure * @macaddr: the MAC address * @@ -764,10 +739,10 @@ static int i40evf_vlan_rx_kill_vid(struct net_device *netdev, * mac_vlan_list_lock. **/ static struct -i40evf_mac_filter *i40evf_find_filter(struct i40evf_adapter *adapter, - const u8 *macaddr) +iavf_mac_filter *iavf_find_filter(struct iavf_adapter *adapter, + const u8 *macaddr) { - struct i40evf_mac_filter *f; + struct iavf_mac_filter *f; if (!macaddr) return NULL; @@ -780,22 +755,22 @@ i40evf_mac_filter *i40evf_find_filter(struct i40evf_adapter *adapter, } /** - * i40e_add_filter - Add a mac filter to the filter list + * iavf_add_filter - Add a mac filter to the filter list * @adapter: board private structure * @macaddr: the MAC address * * Returns ptr to the filter object or NULL when no memory available. **/ static struct -i40evf_mac_filter *i40evf_add_filter(struct i40evf_adapter *adapter, - const u8 *macaddr) +iavf_mac_filter *iavf_add_filter(struct iavf_adapter *adapter, + const u8 *macaddr) { - struct i40evf_mac_filter *f; + struct iavf_mac_filter *f; if (!macaddr) return NULL; - f = i40evf_find_filter(adapter, macaddr); + f = iavf_find_filter(adapter, macaddr); if (!f) { f = kzalloc(sizeof(*f), GFP_ATOMIC); if (!f) @@ -805,7 +780,7 @@ i40evf_mac_filter *i40evf_add_filter(struct i40evf_adapter *adapter, list_add_tail(&f->list, &adapter->mac_filter_list); f->add = true; - adapter->aq_required |= I40EVF_FLAG_AQ_ADD_MAC_FILTER; + adapter->aq_required |= IAVF_FLAG_AQ_ADD_MAC_FILTER; } else { f->remove = false; } @@ -814,17 +789,17 @@ i40evf_mac_filter *i40evf_add_filter(struct i40evf_adapter *adapter, } /** - * i40evf_set_mac - NDO callback to set port mac address + * iavf_set_mac - NDO callback to set port mac address * @netdev: network interface device structure * @p: pointer to an address structure * * Returns 0 on success, negative on failure **/ -static int i40evf_set_mac(struct net_device *netdev, void *p) +static int iavf_set_mac(struct net_device *netdev, void *p) { - struct i40evf_adapter *adapter = netdev_priv(netdev); - struct i40e_hw *hw = &adapter->hw; - struct i40evf_mac_filter *f; + struct iavf_adapter *adapter = netdev_priv(netdev); + struct iavf_hw *hw = &adapter->hw; + struct iavf_mac_filter *f; struct sockaddr *addr = p; if (!is_valid_ether_addr(addr->sa_data)) @@ -833,18 +808,18 @@ static int i40evf_set_mac(struct net_device *netdev, void *p) if (ether_addr_equal(netdev->dev_addr, addr->sa_data)) return 0; - if (adapter->flags & I40EVF_FLAG_ADDR_SET_BY_PF) + if (adapter->flags & IAVF_FLAG_ADDR_SET_BY_PF) return -EPERM; spin_lock_bh(&adapter->mac_vlan_list_lock); - f = i40evf_find_filter(adapter, hw->mac.addr); + f = iavf_find_filter(adapter, hw->mac.addr); if (f) { f->remove = true; - adapter->aq_required |= I40EVF_FLAG_AQ_DEL_MAC_FILTER; + adapter->aq_required |= IAVF_FLAG_AQ_DEL_MAC_FILTER; } - f = i40evf_add_filter(adapter, addr->sa_data); + f = iavf_add_filter(adapter, addr->sa_data); spin_unlock_bh(&adapter->mac_vlan_list_lock); @@ -857,35 +832,35 @@ static int i40evf_set_mac(struct net_device *netdev, void *p) } /** - * i40evf_addr_sync - Callback for dev_(mc|uc)_sync to add address + * iavf_addr_sync - Callback for dev_(mc|uc)_sync to add address * @netdev: the netdevice * @addr: address to add * * Called by __dev_(mc|uc)_sync when an address needs to be added. We call * __dev_(uc|mc)_sync from .set_rx_mode and guarantee to hold the hash lock. */ -static int i40evf_addr_sync(struct net_device *netdev, const u8 *addr) +static int iavf_addr_sync(struct net_device *netdev, const u8 *addr) { - struct i40evf_adapter *adapter = netdev_priv(netdev); + struct iavf_adapter *adapter = netdev_priv(netdev); - if (i40evf_add_filter(adapter, addr)) + if (iavf_add_filter(adapter, addr)) return 0; else return -ENOMEM; } /** - * i40evf_addr_unsync - Callback for dev_(mc|uc)_sync to remove address + * iavf_addr_unsync - Callback for dev_(mc|uc)_sync to remove address * @netdev: the netdevice * @addr: address to add * * Called by __dev_(mc|uc)_sync when an address needs to be removed. We call * __dev_(uc|mc)_sync from .set_rx_mode and guarantee to hold the hash lock. */ -static int i40evf_addr_unsync(struct net_device *netdev, const u8 *addr) +static int iavf_addr_unsync(struct net_device *netdev, const u8 *addr) { - struct i40evf_adapter *adapter = netdev_priv(netdev); - struct i40evf_mac_filter *f; + struct iavf_adapter *adapter = netdev_priv(netdev); + struct iavf_mac_filter *f; /* Under some circumstances, we might receive a request to delete * our own device address from our uc list. Because we store the @@ -895,50 +870,50 @@ static int i40evf_addr_unsync(struct net_device *netdev, const u8 *addr) if (ether_addr_equal(addr, netdev->dev_addr)) return 0; - f = i40evf_find_filter(adapter, addr); + f = iavf_find_filter(adapter, addr); if (f) { f->remove = true; - adapter->aq_required |= I40EVF_FLAG_AQ_DEL_MAC_FILTER; + adapter->aq_required |= IAVF_FLAG_AQ_DEL_MAC_FILTER; } return 0; } /** - * i40evf_set_rx_mode - NDO callback to set the netdev filters + * iavf_set_rx_mode - NDO callback to set the netdev filters * @netdev: network interface device structure **/ -static void i40evf_set_rx_mode(struct net_device *netdev) +static void iavf_set_rx_mode(struct net_device *netdev) { - struct i40evf_adapter *adapter = netdev_priv(netdev); + struct iavf_adapter *adapter = netdev_priv(netdev); spin_lock_bh(&adapter->mac_vlan_list_lock); - __dev_uc_sync(netdev, i40evf_addr_sync, i40evf_addr_unsync); - __dev_mc_sync(netdev, i40evf_addr_sync, i40evf_addr_unsync); + __dev_uc_sync(netdev, iavf_addr_sync, iavf_addr_unsync); + __dev_mc_sync(netdev, iavf_addr_sync, iavf_addr_unsync); spin_unlock_bh(&adapter->mac_vlan_list_lock); if (netdev->flags & IFF_PROMISC && - !(adapter->flags & I40EVF_FLAG_PROMISC_ON)) - adapter->aq_required |= I40EVF_FLAG_AQ_REQUEST_PROMISC; + !(adapter->flags & IAVF_FLAG_PROMISC_ON)) + adapter->aq_required |= IAVF_FLAG_AQ_REQUEST_PROMISC; else if (!(netdev->flags & IFF_PROMISC) && - adapter->flags & I40EVF_FLAG_PROMISC_ON) - adapter->aq_required |= I40EVF_FLAG_AQ_RELEASE_PROMISC; + adapter->flags & IAVF_FLAG_PROMISC_ON) + adapter->aq_required |= IAVF_FLAG_AQ_RELEASE_PROMISC; if (netdev->flags & IFF_ALLMULTI && - !(adapter->flags & I40EVF_FLAG_ALLMULTI_ON)) - adapter->aq_required |= I40EVF_FLAG_AQ_REQUEST_ALLMULTI; + !(adapter->flags & IAVF_FLAG_ALLMULTI_ON)) + adapter->aq_required |= IAVF_FLAG_AQ_REQUEST_ALLMULTI; else if (!(netdev->flags & IFF_ALLMULTI) && - adapter->flags & I40EVF_FLAG_ALLMULTI_ON) - adapter->aq_required |= I40EVF_FLAG_AQ_RELEASE_ALLMULTI; + adapter->flags & IAVF_FLAG_ALLMULTI_ON) + adapter->aq_required |= IAVF_FLAG_AQ_RELEASE_ALLMULTI; } /** - * i40evf_napi_enable_all - enable NAPI on all queue vectors + * iavf_napi_enable_all - enable NAPI on all queue vectors * @adapter: board private structure **/ -static void i40evf_napi_enable_all(struct i40evf_adapter *adapter) +static void iavf_napi_enable_all(struct iavf_adapter *adapter) { int q_idx; - struct i40e_q_vector *q_vector; + struct iavf_q_vector *q_vector; int q_vectors = adapter->num_msix_vectors - NONQ_VECS; for (q_idx = 0; q_idx < q_vectors; q_idx++) { @@ -951,13 +926,13 @@ static void i40evf_napi_enable_all(struct i40evf_adapter *adapter) } /** - * i40evf_napi_disable_all - disable NAPI on all queue vectors + * iavf_napi_disable_all - disable NAPI on all queue vectors * @adapter: board private structure **/ -static void i40evf_napi_disable_all(struct i40evf_adapter *adapter) +static void iavf_napi_disable_all(struct iavf_adapter *adapter) { int q_idx; - struct i40e_q_vector *q_vector; + struct iavf_q_vector *q_vector; int q_vectors = adapter->num_msix_vectors - NONQ_VECS; for (q_idx = 0; q_idx < q_vectors; q_idx++) { @@ -967,67 +942,67 @@ static void i40evf_napi_disable_all(struct i40evf_adapter *adapter) } /** - * i40evf_configure - set up transmit and receive data structures + * iavf_configure - set up transmit and receive data structures * @adapter: board private structure **/ -static void i40evf_configure(struct i40evf_adapter *adapter) +static void iavf_configure(struct iavf_adapter *adapter) { struct net_device *netdev = adapter->netdev; int i; - i40evf_set_rx_mode(netdev); + iavf_set_rx_mode(netdev); - i40evf_configure_tx(adapter); - i40evf_configure_rx(adapter); - adapter->aq_required |= I40EVF_FLAG_AQ_CONFIGURE_QUEUES; + iavf_configure_tx(adapter); + iavf_configure_rx(adapter); + adapter->aq_required |= IAVF_FLAG_AQ_CONFIGURE_QUEUES; for (i = 0; i < adapter->num_active_queues; i++) { - struct i40e_ring *ring = &adapter->rx_rings[i]; + struct iavf_ring *ring = &adapter->rx_rings[i]; - i40evf_alloc_rx_buffers(ring, I40E_DESC_UNUSED(ring)); + iavf_alloc_rx_buffers(ring, IAVF_DESC_UNUSED(ring)); } } /** - * i40evf_up_complete - Finish the last steps of bringing up a connection + * iavf_up_complete - Finish the last steps of bringing up a connection * @adapter: board private structure * - * Expects to be called while holding the __I40EVF_IN_CRITICAL_TASK bit lock. + * Expects to be called while holding the __IAVF_IN_CRITICAL_TASK bit lock. **/ -static void i40evf_up_complete(struct i40evf_adapter *adapter) +static void iavf_up_complete(struct iavf_adapter *adapter) { - adapter->state = __I40EVF_RUNNING; - clear_bit(__I40E_VSI_DOWN, adapter->vsi.state); + adapter->state = __IAVF_RUNNING; + clear_bit(__IAVF_VSI_DOWN, adapter->vsi.state); - i40evf_napi_enable_all(adapter); + iavf_napi_enable_all(adapter); - adapter->aq_required |= I40EVF_FLAG_AQ_ENABLE_QUEUES; + adapter->aq_required |= IAVF_FLAG_AQ_ENABLE_QUEUES; if (CLIENT_ENABLED(adapter)) - adapter->flags |= I40EVF_FLAG_CLIENT_NEEDS_OPEN; + adapter->flags |= IAVF_FLAG_CLIENT_NEEDS_OPEN; mod_timer_pending(&adapter->watchdog_timer, jiffies + 1); } /** - * i40e_down - Shutdown the connection processing + * iavf_down - Shutdown the connection processing * @adapter: board private structure * - * Expects to be called while holding the __I40EVF_IN_CRITICAL_TASK bit lock. + * Expects to be called while holding the __IAVF_IN_CRITICAL_TASK bit lock. **/ -void i40evf_down(struct i40evf_adapter *adapter) +void iavf_down(struct iavf_adapter *adapter) { struct net_device *netdev = adapter->netdev; - struct i40evf_vlan_filter *vlf; - struct i40evf_mac_filter *f; - struct i40evf_cloud_filter *cf; + struct iavf_vlan_filter *vlf; + struct iavf_mac_filter *f; + struct iavf_cloud_filter *cf; - if (adapter->state <= __I40EVF_DOWN_PENDING) + if (adapter->state <= __IAVF_DOWN_PENDING) return; netif_carrier_off(netdev); netif_tx_disable(netdev); adapter->link_up = false; - i40evf_napi_disable_all(adapter); - i40evf_irq_disable(adapter); + iavf_napi_disable_all(adapter); + iavf_irq_disable(adapter); spin_lock_bh(&adapter->mac_vlan_list_lock); @@ -1054,25 +1029,25 @@ void i40evf_down(struct i40evf_adapter *adapter) } spin_unlock_bh(&adapter->cloud_filter_list_lock); - if (!(adapter->flags & I40EVF_FLAG_PF_COMMS_FAILED) && - adapter->state != __I40EVF_RESETTING) { + if (!(adapter->flags & IAVF_FLAG_PF_COMMS_FAILED) && + adapter->state != __IAVF_RESETTING) { /* cancel any current operation */ adapter->current_op = VIRTCHNL_OP_UNKNOWN; /* Schedule operations to close down the HW. Don't wait * here for this to complete. The watchdog is still running * and it will take care of this. */ - adapter->aq_required = I40EVF_FLAG_AQ_DEL_MAC_FILTER; - adapter->aq_required |= I40EVF_FLAG_AQ_DEL_VLAN_FILTER; - adapter->aq_required |= I40EVF_FLAG_AQ_DEL_CLOUD_FILTER; - adapter->aq_required |= I40EVF_FLAG_AQ_DISABLE_QUEUES; + adapter->aq_required = IAVF_FLAG_AQ_DEL_MAC_FILTER; + adapter->aq_required |= IAVF_FLAG_AQ_DEL_VLAN_FILTER; + adapter->aq_required |= IAVF_FLAG_AQ_DEL_CLOUD_FILTER; + adapter->aq_required |= IAVF_FLAG_AQ_DISABLE_QUEUES; } mod_timer_pending(&adapter->watchdog_timer, jiffies + 1); } /** - * i40evf_acquire_msix_vectors - Setup the MSIX capability + * iavf_acquire_msix_vectors - Setup the MSIX capability * @adapter: board private structure * @vectors: number of vectors to request * @@ -1081,7 +1056,7 @@ void i40evf_down(struct i40evf_adapter *adapter) * Returns 0 on success, negative on failure **/ static int -i40evf_acquire_msix_vectors(struct i40evf_adapter *adapter, int vectors) +iavf_acquire_msix_vectors(struct iavf_adapter *adapter, int vectors) { int err, vector_threshold; @@ -1115,12 +1090,12 @@ i40evf_acquire_msix_vectors(struct i40evf_adapter *adapter, int vectors) } /** - * i40evf_free_queues - Free memory for all rings + * iavf_free_queues - Free memory for all rings * @adapter: board private structure to initialize * * Free all of the memory associated with queue pairs. **/ -static void i40evf_free_queues(struct i40evf_adapter *adapter) +static void iavf_free_queues(struct iavf_adapter *adapter) { if (!adapter->vsi_res) return; @@ -1132,14 +1107,14 @@ static void i40evf_free_queues(struct i40evf_adapter *adapter) } /** - * i40evf_alloc_queues - Allocate memory for all rings + * iavf_alloc_queues - Allocate memory for all rings * @adapter: board private structure to initialize * * We allocate one ring per queue at run-time since we don't know the * number of queues at compile-time. The polling_netdev array is * intended for Multiqueue, but should work fine with a single queue. **/ -static int i40evf_alloc_queues(struct i40evf_adapter *adapter) +static int iavf_alloc_queues(struct iavf_adapter *adapter) { int i, num_active_queues; @@ -1160,17 +1135,17 @@ static int i40evf_alloc_queues(struct i40evf_adapter *adapter) adapter->tx_rings = kcalloc(num_active_queues, - sizeof(struct i40e_ring), GFP_KERNEL); + sizeof(struct iavf_ring), GFP_KERNEL); if (!adapter->tx_rings) goto err_out; adapter->rx_rings = kcalloc(num_active_queues, - sizeof(struct i40e_ring), GFP_KERNEL); + sizeof(struct iavf_ring), GFP_KERNEL); if (!adapter->rx_rings) goto err_out; for (i = 0; i < num_active_queues; i++) { - struct i40e_ring *tx_ring; - struct i40e_ring *rx_ring; + struct iavf_ring *tx_ring; + struct iavf_ring *rx_ring; tx_ring = &adapter->tx_rings[i]; @@ -1178,16 +1153,16 @@ static int i40evf_alloc_queues(struct i40evf_adapter *adapter) tx_ring->netdev = adapter->netdev; tx_ring->dev = &adapter->pdev->dev; tx_ring->count = adapter->tx_desc_count; - tx_ring->itr_setting = I40E_ITR_TX_DEF; - if (adapter->flags & I40EVF_FLAG_WB_ON_ITR_CAPABLE) - tx_ring->flags |= I40E_TXR_FLAGS_WB_ON_ITR; + tx_ring->itr_setting = IAVF_ITR_TX_DEF; + if (adapter->flags & IAVF_FLAG_WB_ON_ITR_CAPABLE) + tx_ring->flags |= IAVF_TXR_FLAGS_WB_ON_ITR; rx_ring = &adapter->rx_rings[i]; rx_ring->queue_index = i; rx_ring->netdev = adapter->netdev; rx_ring->dev = &adapter->pdev->dev; rx_ring->count = adapter->rx_desc_count; - rx_ring->itr_setting = I40E_ITR_RX_DEF; + rx_ring->itr_setting = IAVF_ITR_RX_DEF; } adapter->num_active_queues = num_active_queues; @@ -1195,18 +1170,18 @@ static int i40evf_alloc_queues(struct i40evf_adapter *adapter) return 0; err_out: - i40evf_free_queues(adapter); + iavf_free_queues(adapter); return -ENOMEM; } /** - * i40evf_set_interrupt_capability - set MSI-X or FAIL if not supported + * iavf_set_interrupt_capability - set MSI-X or FAIL if not supported * @adapter: board private structure to initialize * * Attempt to configure the interrupts using the best available * capabilities of the hardware and the kernel. **/ -static int i40evf_set_interrupt_capability(struct i40evf_adapter *adapter) +static int iavf_set_interrupt_capability(struct iavf_adapter *adapter) { int vector, v_budget; int pairs = 0; @@ -1236,7 +1211,7 @@ static int i40evf_set_interrupt_capability(struct i40evf_adapter *adapter) for (vector = 0; vector < v_budget; vector++) adapter->msix_entries[vector].entry = vector; - err = i40evf_acquire_msix_vectors(adapter, v_budget); + err = iavf_acquire_msix_vectors(adapter, v_budget); out: netif_set_real_num_rx_queues(adapter->netdev, pairs); @@ -1245,16 +1220,16 @@ out: } /** - * i40e_config_rss_aq - Configure RSS keys and lut by using AQ commands + * iavf_config_rss_aq - Configure RSS keys and lut by using AQ commands * @adapter: board private structure * * Return 0 on success, negative on failure **/ -static int i40evf_config_rss_aq(struct i40evf_adapter *adapter) +static int iavf_config_rss_aq(struct iavf_adapter *adapter) { struct i40e_aqc_get_set_rss_key_data *rss_key = (struct i40e_aqc_get_set_rss_key_data *)adapter->rss_key; - struct i40e_hw *hw = &adapter->hw; + struct iavf_hw *hw = &adapter->hw; int ret = 0; if (adapter->current_op != VIRTCHNL_OP_UNKNOWN) { @@ -1264,21 +1239,21 @@ static int i40evf_config_rss_aq(struct i40evf_adapter *adapter) return -EBUSY; } - ret = i40evf_aq_set_rss_key(hw, adapter->vsi.id, rss_key); + ret = iavf_aq_set_rss_key(hw, adapter->vsi.id, rss_key); if (ret) { dev_err(&adapter->pdev->dev, "Cannot set RSS key, err %s aq_err %s\n", - i40evf_stat_str(hw, ret), - i40evf_aq_str(hw, hw->aq.asq_last_status)); + iavf_stat_str(hw, ret), + iavf_aq_str(hw, hw->aq.asq_last_status)); return ret; } - ret = i40evf_aq_set_rss_lut(hw, adapter->vsi.id, false, - adapter->rss_lut, adapter->rss_lut_size); + ret = iavf_aq_set_rss_lut(hw, adapter->vsi.id, false, + adapter->rss_lut, adapter->rss_lut_size); if (ret) { dev_err(&adapter->pdev->dev, "Cannot set RSS lut, err %s aq_err %s\n", - i40evf_stat_str(hw, ret), - i40evf_aq_str(hw, hw->aq.asq_last_status)); + iavf_stat_str(hw, ret), + iavf_aq_str(hw, hw->aq.asq_last_status)); } return ret; @@ -1286,55 +1261,55 @@ static int i40evf_config_rss_aq(struct i40evf_adapter *adapter) } /** - * i40evf_config_rss_reg - Configure RSS keys and lut by writing registers + * iavf_config_rss_reg - Configure RSS keys and lut by writing registers * @adapter: board private structure * * Returns 0 on success, negative on failure **/ -static int i40evf_config_rss_reg(struct i40evf_adapter *adapter) +static int iavf_config_rss_reg(struct iavf_adapter *adapter) { - struct i40e_hw *hw = &adapter->hw; + struct iavf_hw *hw = &adapter->hw; u32 *dw; u16 i; dw = (u32 *)adapter->rss_key; for (i = 0; i <= adapter->rss_key_size / 4; i++) - wr32(hw, I40E_VFQF_HKEY(i), dw[i]); + wr32(hw, IAVF_VFQF_HKEY(i), dw[i]); dw = (u32 *)adapter->rss_lut; for (i = 0; i <= adapter->rss_lut_size / 4; i++) - wr32(hw, I40E_VFQF_HLUT(i), dw[i]); + wr32(hw, IAVF_VFQF_HLUT(i), dw[i]); - i40e_flush(hw); + iavf_flush(hw); return 0; } /** - * i40evf_config_rss - Configure RSS keys and lut + * iavf_config_rss - Configure RSS keys and lut * @adapter: board private structure * * Returns 0 on success, negative on failure **/ -int i40evf_config_rss(struct i40evf_adapter *adapter) +int iavf_config_rss(struct iavf_adapter *adapter) { if (RSS_PF(adapter)) { - adapter->aq_required |= I40EVF_FLAG_AQ_SET_RSS_LUT | - I40EVF_FLAG_AQ_SET_RSS_KEY; + adapter->aq_required |= IAVF_FLAG_AQ_SET_RSS_LUT | + IAVF_FLAG_AQ_SET_RSS_KEY; return 0; } else if (RSS_AQ(adapter)) { - return i40evf_config_rss_aq(adapter); + return iavf_config_rss_aq(adapter); } else { - return i40evf_config_rss_reg(adapter); + return iavf_config_rss_reg(adapter); } } /** - * i40evf_fill_rss_lut - Fill the lut with default values + * iavf_fill_rss_lut - Fill the lut with default values * @adapter: board private structure **/ -static void i40evf_fill_rss_lut(struct i40evf_adapter *adapter) +static void iavf_fill_rss_lut(struct iavf_adapter *adapter) { u16 i; @@ -1343,47 +1318,46 @@ static void i40evf_fill_rss_lut(struct i40evf_adapter *adapter) } /** - * i40evf_init_rss - Prepare for RSS + * iavf_init_rss - Prepare for RSS * @adapter: board private structure * * Return 0 on success, negative on failure **/ -static int i40evf_init_rss(struct i40evf_adapter *adapter) +static int iavf_init_rss(struct iavf_adapter *adapter) { - struct i40e_hw *hw = &adapter->hw; + struct iavf_hw *hw = &adapter->hw; int ret; if (!RSS_PF(adapter)) { /* Enable PCTYPES for RSS, TCP/UDP with IPv4/IPv6 */ if (adapter->vf_res->vf_cap_flags & VIRTCHNL_VF_OFFLOAD_RSS_PCTYPE_V2) - adapter->hena = I40E_DEFAULT_RSS_HENA_EXPANDED; + adapter->hena = IAVF_DEFAULT_RSS_HENA_EXPANDED; else - adapter->hena = I40E_DEFAULT_RSS_HENA; + adapter->hena = IAVF_DEFAULT_RSS_HENA; - wr32(hw, I40E_VFQF_HENA(0), (u32)adapter->hena); - wr32(hw, I40E_VFQF_HENA(1), (u32)(adapter->hena >> 32)); + wr32(hw, IAVF_VFQF_HENA(0), (u32)adapter->hena); + wr32(hw, IAVF_VFQF_HENA(1), (u32)(adapter->hena >> 32)); } - i40evf_fill_rss_lut(adapter); - + iavf_fill_rss_lut(adapter); netdev_rss_key_fill((void *)adapter->rss_key, adapter->rss_key_size); - ret = i40evf_config_rss(adapter); + ret = iavf_config_rss(adapter); return ret; } /** - * i40evf_alloc_q_vectors - Allocate memory for interrupt vectors + * iavf_alloc_q_vectors - Allocate memory for interrupt vectors * @adapter: board private structure to initialize * * We allocate one q_vector per queue interrupt. If allocation fails we * return -ENOMEM. **/ -static int i40evf_alloc_q_vectors(struct i40evf_adapter *adapter) +static int iavf_alloc_q_vectors(struct iavf_adapter *adapter) { int q_idx = 0, num_q_vectors; - struct i40e_q_vector *q_vector; + struct iavf_q_vector *q_vector; num_q_vectors = adapter->num_msix_vectors - NONQ_VECS; adapter->q_vectors = kcalloc(num_q_vectors, sizeof(*q_vector), @@ -1399,21 +1373,21 @@ static int i40evf_alloc_q_vectors(struct i40evf_adapter *adapter) q_vector->reg_idx = q_idx; cpumask_copy(&q_vector->affinity_mask, cpu_possible_mask); netif_napi_add(adapter->netdev, &q_vector->napi, - i40evf_napi_poll, NAPI_POLL_WEIGHT); + iavf_napi_poll, NAPI_POLL_WEIGHT); } return 0; } /** - * i40evf_free_q_vectors - Free memory allocated for interrupt vectors + * iavf_free_q_vectors - Free memory allocated for interrupt vectors * @adapter: board private structure to initialize * * This function frees the memory allocated to the q_vectors. In addition if * NAPI is enabled it will delete any references to the NAPI struct prior * to freeing the q_vector. **/ -static void i40evf_free_q_vectors(struct i40evf_adapter *adapter) +static void iavf_free_q_vectors(struct iavf_adapter *adapter) { int q_idx, num_q_vectors; int napi_vectors; @@ -1425,7 +1399,8 @@ static void i40evf_free_q_vectors(struct i40evf_adapter *adapter) napi_vectors = adapter->num_active_queues; for (q_idx = 0; q_idx < num_q_vectors; q_idx++) { - struct i40e_q_vector *q_vector = &adapter->q_vectors[q_idx]; + struct iavf_q_vector *q_vector = &adapter->q_vectors[q_idx]; + if (q_idx < napi_vectors) netif_napi_del(&q_vector->napi); } @@ -1434,11 +1409,11 @@ static void i40evf_free_q_vectors(struct i40evf_adapter *adapter) } /** - * i40evf_reset_interrupt_capability - Reset MSIX setup + * iavf_reset_interrupt_capability - Reset MSIX setup * @adapter: board private structure * **/ -void i40evf_reset_interrupt_capability(struct i40evf_adapter *adapter) +void iavf_reset_interrupt_capability(struct iavf_adapter *adapter) { if (!adapter->msix_entries) return; @@ -1449,15 +1424,15 @@ void i40evf_reset_interrupt_capability(struct i40evf_adapter *adapter) } /** - * i40evf_init_interrupt_scheme - Determine if MSIX is supported and init + * iavf_init_interrupt_scheme - Determine if MSIX is supported and init * @adapter: board private structure to initialize * **/ -int i40evf_init_interrupt_scheme(struct i40evf_adapter *adapter) +int iavf_init_interrupt_scheme(struct iavf_adapter *adapter) { int err; - err = i40evf_alloc_queues(adapter); + err = iavf_alloc_queues(adapter); if (err) { dev_err(&adapter->pdev->dev, "Unable to allocate memory for queues\n"); @@ -1465,7 +1440,7 @@ int i40evf_init_interrupt_scheme(struct i40evf_adapter *adapter) } rtnl_lock(); - err = i40evf_set_interrupt_capability(adapter); + err = iavf_set_interrupt_capability(adapter); rtnl_unlock(); if (err) { dev_err(&adapter->pdev->dev, @@ -1473,7 +1448,7 @@ int i40evf_init_interrupt_scheme(struct i40evf_adapter *adapter) goto err_set_interrupt; } - err = i40evf_alloc_q_vectors(adapter); + err = iavf_alloc_q_vectors(adapter); if (err) { dev_err(&adapter->pdev->dev, "Unable to allocate memory for queue vectors\n"); @@ -1496,18 +1471,18 @@ int i40evf_init_interrupt_scheme(struct i40evf_adapter *adapter) return 0; err_alloc_q_vectors: - i40evf_reset_interrupt_capability(adapter); + iavf_reset_interrupt_capability(adapter); err_set_interrupt: - i40evf_free_queues(adapter); + iavf_free_queues(adapter); err_alloc_queues: return err; } /** - * i40evf_free_rss - Free memory used by RSS structs + * iavf_free_rss - Free memory used by RSS structs * @adapter: board private structure **/ -static void i40evf_free_rss(struct i40evf_adapter *adapter) +static void iavf_free_rss(struct iavf_adapter *adapter) { kfree(adapter->rss_key); adapter->rss_key = NULL; @@ -1517,52 +1492,52 @@ static void i40evf_free_rss(struct i40evf_adapter *adapter) } /** - * i40evf_reinit_interrupt_scheme - Reallocate queues and vectors + * iavf_reinit_interrupt_scheme - Reallocate queues and vectors * @adapter: board private structure * * Returns 0 on success, negative on failure **/ -static int i40evf_reinit_interrupt_scheme(struct i40evf_adapter *adapter) +static int iavf_reinit_interrupt_scheme(struct iavf_adapter *adapter) { struct net_device *netdev = adapter->netdev; int err; if (netif_running(netdev)) - i40evf_free_traffic_irqs(adapter); - i40evf_free_misc_irq(adapter); - i40evf_reset_interrupt_capability(adapter); - i40evf_free_q_vectors(adapter); - i40evf_free_queues(adapter); + iavf_free_traffic_irqs(adapter); + iavf_free_misc_irq(adapter); + iavf_reset_interrupt_capability(adapter); + iavf_free_q_vectors(adapter); + iavf_free_queues(adapter); - err = i40evf_init_interrupt_scheme(adapter); + err = iavf_init_interrupt_scheme(adapter); if (err) goto err; netif_tx_stop_all_queues(netdev); - err = i40evf_request_misc_irq(adapter); + err = iavf_request_misc_irq(adapter); if (err) goto err; - set_bit(__I40E_VSI_DOWN, adapter->vsi.state); + set_bit(__IAVF_VSI_DOWN, adapter->vsi.state); - i40evf_map_rings_to_vectors(adapter); + iavf_map_rings_to_vectors(adapter); if (RSS_AQ(adapter)) - adapter->aq_required |= I40EVF_FLAG_AQ_CONFIGURE_RSS; + adapter->aq_required |= IAVF_FLAG_AQ_CONFIGURE_RSS; else - err = i40evf_init_rss(adapter); + err = iavf_init_rss(adapter); err: return err; } /** - * i40evf_watchdog_timer - Periodic call-back timer + * iavf_watchdog_timer - Periodic call-back timer * @data: pointer to adapter disguised as unsigned long **/ -static void i40evf_watchdog_timer(struct timer_list *t) +static void iavf_watchdog_timer(struct timer_list *t) { - struct i40evf_adapter *adapter = from_timer(adapter, t, + struct iavf_adapter *adapter = from_timer(adapter, t, watchdog_timer); schedule_work(&adapter->watchdog_task); @@ -1570,31 +1545,31 @@ static void i40evf_watchdog_timer(struct timer_list *t) } /** - * i40evf_watchdog_task - Periodic call-back task + * iavf_watchdog_task - Periodic call-back task * @work: pointer to work_struct **/ -static void i40evf_watchdog_task(struct work_struct *work) +static void iavf_watchdog_task(struct work_struct *work) { - struct i40evf_adapter *adapter = container_of(work, - struct i40evf_adapter, + struct iavf_adapter *adapter = container_of(work, + struct iavf_adapter, watchdog_task); - struct i40e_hw *hw = &adapter->hw; + struct iavf_hw *hw = &adapter->hw; u32 reg_val; - if (test_and_set_bit(__I40EVF_IN_CRITICAL_TASK, &adapter->crit_section)) + if (test_and_set_bit(__IAVF_IN_CRITICAL_TASK, &adapter->crit_section)) goto restart_watchdog; - if (adapter->flags & I40EVF_FLAG_PF_COMMS_FAILED) { - reg_val = rd32(hw, I40E_VFGEN_RSTAT) & - I40E_VFGEN_RSTAT_VFR_STATE_MASK; + if (adapter->flags & IAVF_FLAG_PF_COMMS_FAILED) { + reg_val = rd32(hw, IAVF_VFGEN_RSTAT) & + IAVF_VFGEN_RSTAT_VFR_STATE_MASK; if ((reg_val == VIRTCHNL_VFR_VFACTIVE) || (reg_val == VIRTCHNL_VFR_COMPLETED)) { /* A chance for redemption! */ dev_err(&adapter->pdev->dev, "Hardware came out of reset. Attempting reinit.\n"); - adapter->state = __I40EVF_STARTUP; - adapter->flags &= ~I40EVF_FLAG_PF_COMMS_FAILED; + adapter->state = __IAVF_STARTUP; + adapter->flags &= ~IAVF_FLAG_PF_COMMS_FAILED; schedule_delayed_work(&adapter->init_task, 10); - clear_bit(__I40EVF_IN_CRITICAL_TASK, + clear_bit(__IAVF_IN_CRITICAL_TASK, &adapter->crit_section); /* Don't reschedule the watchdog, since we've restarted * the init task. When init_task contacts the PF and @@ -1608,15 +1583,15 @@ static void i40evf_watchdog_task(struct work_struct *work) goto watchdog_done; } - if ((adapter->state < __I40EVF_DOWN) || - (adapter->flags & I40EVF_FLAG_RESET_PENDING)) + if ((adapter->state < __IAVF_DOWN) || + (adapter->flags & IAVF_FLAG_RESET_PENDING)) goto watchdog_done; /* check for reset */ - reg_val = rd32(hw, I40E_VF_ARQLEN1) & I40E_VF_ARQLEN1_ARQENABLE_MASK; - if (!(adapter->flags & I40EVF_FLAG_RESET_PENDING) && !reg_val) { - adapter->state = __I40EVF_RESETTING; - adapter->flags |= I40EVF_FLAG_RESET_PENDING; + reg_val = rd32(hw, IAVF_VF_ARQLEN1) & IAVF_VF_ARQLEN1_ARQENABLE_MASK; + if (!(adapter->flags & IAVF_FLAG_RESET_PENDING) && !reg_val) { + adapter->state = __IAVF_RESETTING; + adapter->flags |= IAVF_FLAG_RESET_PENDING; dev_err(&adapter->pdev->dev, "Hardware reset detected\n"); schedule_work(&adapter->reset_task); adapter->aq_required = 0; @@ -1628,140 +1603,140 @@ static void i40evf_watchdog_task(struct work_struct *work) * here so we don't race on the admin queue. */ if (adapter->current_op) { - if (!i40evf_asq_done(hw)) { + if (!iavf_asq_done(hw)) { dev_dbg(&adapter->pdev->dev, "Admin queue timeout\n"); - i40evf_send_api_ver(adapter); + iavf_send_api_ver(adapter); } goto watchdog_done; } - if (adapter->aq_required & I40EVF_FLAG_AQ_GET_CONFIG) { - i40evf_send_vf_config_msg(adapter); + if (adapter->aq_required & IAVF_FLAG_AQ_GET_CONFIG) { + iavf_send_vf_config_msg(adapter); goto watchdog_done; } - if (adapter->aq_required & I40EVF_FLAG_AQ_DISABLE_QUEUES) { - i40evf_disable_queues(adapter); + if (adapter->aq_required & IAVF_FLAG_AQ_DISABLE_QUEUES) { + iavf_disable_queues(adapter); goto watchdog_done; } - if (adapter->aq_required & I40EVF_FLAG_AQ_MAP_VECTORS) { - i40evf_map_queues(adapter); + if (adapter->aq_required & IAVF_FLAG_AQ_MAP_VECTORS) { + iavf_map_queues(adapter); goto watchdog_done; } - if (adapter->aq_required & I40EVF_FLAG_AQ_ADD_MAC_FILTER) { - i40evf_add_ether_addrs(adapter); + if (adapter->aq_required & IAVF_FLAG_AQ_ADD_MAC_FILTER) { + iavf_add_ether_addrs(adapter); goto watchdog_done; } - if (adapter->aq_required & I40EVF_FLAG_AQ_ADD_VLAN_FILTER) { - i40evf_add_vlans(adapter); + if (adapter->aq_required & IAVF_FLAG_AQ_ADD_VLAN_FILTER) { + iavf_add_vlans(adapter); goto watchdog_done; } - if (adapter->aq_required & I40EVF_FLAG_AQ_DEL_MAC_FILTER) { - i40evf_del_ether_addrs(adapter); + if (adapter->aq_required & IAVF_FLAG_AQ_DEL_MAC_FILTER) { + iavf_del_ether_addrs(adapter); goto watchdog_done; } - if (adapter->aq_required & I40EVF_FLAG_AQ_DEL_VLAN_FILTER) { - i40evf_del_vlans(adapter); + if (adapter->aq_required & IAVF_FLAG_AQ_DEL_VLAN_FILTER) { + iavf_del_vlans(adapter); goto watchdog_done; } - if (adapter->aq_required & I40EVF_FLAG_AQ_ENABLE_VLAN_STRIPPING) { - i40evf_enable_vlan_stripping(adapter); + if (adapter->aq_required & IAVF_FLAG_AQ_ENABLE_VLAN_STRIPPING) { + iavf_enable_vlan_stripping(adapter); goto watchdog_done; } - if (adapter->aq_required & I40EVF_FLAG_AQ_DISABLE_VLAN_STRIPPING) { - i40evf_disable_vlan_stripping(adapter); + if (adapter->aq_required & IAVF_FLAG_AQ_DISABLE_VLAN_STRIPPING) { + iavf_disable_vlan_stripping(adapter); goto watchdog_done; } - if (adapter->aq_required & I40EVF_FLAG_AQ_CONFIGURE_QUEUES) { - i40evf_configure_queues(adapter); + if (adapter->aq_required & IAVF_FLAG_AQ_CONFIGURE_QUEUES) { + iavf_configure_queues(adapter); goto watchdog_done; } - if (adapter->aq_required & I40EVF_FLAG_AQ_ENABLE_QUEUES) { - i40evf_enable_queues(adapter); + if (adapter->aq_required & IAVF_FLAG_AQ_ENABLE_QUEUES) { + iavf_enable_queues(adapter); goto watchdog_done; } - if (adapter->aq_required & I40EVF_FLAG_AQ_CONFIGURE_RSS) { + if (adapter->aq_required & IAVF_FLAG_AQ_CONFIGURE_RSS) { /* This message goes straight to the firmware, not the * PF, so we don't have to set current_op as we will * not get a response through the ARQ. */ - i40evf_init_rss(adapter); - adapter->aq_required &= ~I40EVF_FLAG_AQ_CONFIGURE_RSS; + iavf_init_rss(adapter); + adapter->aq_required &= ~IAVF_FLAG_AQ_CONFIGURE_RSS; goto watchdog_done; } - if (adapter->aq_required & I40EVF_FLAG_AQ_GET_HENA) { - i40evf_get_hena(adapter); + if (adapter->aq_required & IAVF_FLAG_AQ_GET_HENA) { + iavf_get_hena(adapter); goto watchdog_done; } - if (adapter->aq_required & I40EVF_FLAG_AQ_SET_HENA) { - i40evf_set_hena(adapter); + if (adapter->aq_required & IAVF_FLAG_AQ_SET_HENA) { + iavf_set_hena(adapter); goto watchdog_done; } - if (adapter->aq_required & I40EVF_FLAG_AQ_SET_RSS_KEY) { - i40evf_set_rss_key(adapter); + if (adapter->aq_required & IAVF_FLAG_AQ_SET_RSS_KEY) { + iavf_set_rss_key(adapter); goto watchdog_done; } - if (adapter->aq_required & I40EVF_FLAG_AQ_SET_RSS_LUT) { - i40evf_set_rss_lut(adapter); + if (adapter->aq_required & IAVF_FLAG_AQ_SET_RSS_LUT) { + iavf_set_rss_lut(adapter); goto watchdog_done; } - if (adapter->aq_required & I40EVF_FLAG_AQ_REQUEST_PROMISC) { - i40evf_set_promiscuous(adapter, FLAG_VF_UNICAST_PROMISC | + if (adapter->aq_required & IAVF_FLAG_AQ_REQUEST_PROMISC) { + iavf_set_promiscuous(adapter, FLAG_VF_UNICAST_PROMISC | FLAG_VF_MULTICAST_PROMISC); goto watchdog_done; } - if (adapter->aq_required & I40EVF_FLAG_AQ_REQUEST_ALLMULTI) { - i40evf_set_promiscuous(adapter, FLAG_VF_MULTICAST_PROMISC); + if (adapter->aq_required & IAVF_FLAG_AQ_REQUEST_ALLMULTI) { + iavf_set_promiscuous(adapter, FLAG_VF_MULTICAST_PROMISC); goto watchdog_done; } - if ((adapter->aq_required & I40EVF_FLAG_AQ_RELEASE_PROMISC) && - (adapter->aq_required & I40EVF_FLAG_AQ_RELEASE_ALLMULTI)) { - i40evf_set_promiscuous(adapter, 0); + if ((adapter->aq_required & IAVF_FLAG_AQ_RELEASE_PROMISC) && + (adapter->aq_required & IAVF_FLAG_AQ_RELEASE_ALLMULTI)) { + iavf_set_promiscuous(adapter, 0); goto watchdog_done; } - if (adapter->aq_required & I40EVF_FLAG_AQ_ENABLE_CHANNELS) { - i40evf_enable_channels(adapter); + if (adapter->aq_required & IAVF_FLAG_AQ_ENABLE_CHANNELS) { + iavf_enable_channels(adapter); goto watchdog_done; } - if (adapter->aq_required & I40EVF_FLAG_AQ_DISABLE_CHANNELS) { - i40evf_disable_channels(adapter); + if (adapter->aq_required & IAVF_FLAG_AQ_DISABLE_CHANNELS) { + iavf_disable_channels(adapter); goto watchdog_done; } - if (adapter->aq_required & I40EVF_FLAG_AQ_ADD_CLOUD_FILTER) { - i40evf_add_cloud_filter(adapter); + if (adapter->aq_required & IAVF_FLAG_AQ_ADD_CLOUD_FILTER) { + iavf_add_cloud_filter(adapter); goto watchdog_done; } - if (adapter->aq_required & I40EVF_FLAG_AQ_DEL_CLOUD_FILTER) { - i40evf_del_cloud_filter(adapter); + if (adapter->aq_required & IAVF_FLAG_AQ_DEL_CLOUD_FILTER) { + iavf_del_cloud_filter(adapter); goto watchdog_done; } schedule_delayed_work(&adapter->client_task, msecs_to_jiffies(5)); - if (adapter->state == __I40EVF_RUNNING) - i40evf_request_stats(adapter); + if (adapter->state == __IAVF_RUNNING) + iavf_request_stats(adapter); watchdog_done: - if (adapter->state == __I40EVF_RUNNING) - i40evf_detect_recover_hung(&adapter->vsi); - clear_bit(__I40EVF_IN_CRITICAL_TASK, &adapter->crit_section); + if (adapter->state == __IAVF_RUNNING) + iavf_detect_recover_hung(&adapter->vsi); + clear_bit(__IAVF_IN_CRITICAL_TASK, &adapter->crit_section); restart_watchdog: - if (adapter->state == __I40EVF_REMOVE) + if (adapter->state == __IAVF_REMOVE) return; if (adapter->aq_required) mod_timer(&adapter->watchdog_timer, @@ -1771,28 +1746,28 @@ restart_watchdog: schedule_work(&adapter->adminq_task); } -static void i40evf_disable_vf(struct i40evf_adapter *adapter) +static void iavf_disable_vf(struct iavf_adapter *adapter) { - struct i40evf_mac_filter *f, *ftmp; - struct i40evf_vlan_filter *fv, *fvtmp; - struct i40evf_cloud_filter *cf, *cftmp; + struct iavf_mac_filter *f, *ftmp; + struct iavf_vlan_filter *fv, *fvtmp; + struct iavf_cloud_filter *cf, *cftmp; - adapter->flags |= I40EVF_FLAG_PF_COMMS_FAILED; + adapter->flags |= IAVF_FLAG_PF_COMMS_FAILED; /* We don't use netif_running() because it may be true prior to * ndo_open() returning, so we can't assume it means all our open * tasks have finished, since we're not holding the rtnl_lock here. */ - if (adapter->state == __I40EVF_RUNNING) { - set_bit(__I40E_VSI_DOWN, adapter->vsi.state); + if (adapter->state == __IAVF_RUNNING) { + set_bit(__IAVF_VSI_DOWN, adapter->vsi.state); netif_carrier_off(adapter->netdev); netif_tx_disable(adapter->netdev); adapter->link_up = false; - i40evf_napi_disable_all(adapter); - i40evf_irq_disable(adapter); - i40evf_free_traffic_irqs(adapter); - i40evf_free_all_tx_resources(adapter); - i40evf_free_all_rx_resources(adapter); + iavf_napi_disable_all(adapter); + iavf_irq_disable(adapter); + iavf_free_traffic_irqs(adapter); + iavf_free_all_tx_resources(adapter); + iavf_free_all_rx_resources(adapter); } spin_lock_bh(&adapter->mac_vlan_list_lock); @@ -1818,41 +1793,41 @@ static void i40evf_disable_vf(struct i40evf_adapter *adapter) } spin_unlock_bh(&adapter->cloud_filter_list_lock); - i40evf_free_misc_irq(adapter); - i40evf_reset_interrupt_capability(adapter); - i40evf_free_queues(adapter); - i40evf_free_q_vectors(adapter); + iavf_free_misc_irq(adapter); + iavf_reset_interrupt_capability(adapter); + iavf_free_queues(adapter); + iavf_free_q_vectors(adapter); kfree(adapter->vf_res); - i40evf_shutdown_adminq(&adapter->hw); + iavf_shutdown_adminq(&adapter->hw); adapter->netdev->flags &= ~IFF_UP; - clear_bit(__I40EVF_IN_CRITICAL_TASK, &adapter->crit_section); - adapter->flags &= ~I40EVF_FLAG_RESET_PENDING; - adapter->state = __I40EVF_DOWN; + clear_bit(__IAVF_IN_CRITICAL_TASK, &adapter->crit_section); + adapter->flags &= ~IAVF_FLAG_RESET_PENDING; + adapter->state = __IAVF_DOWN; wake_up(&adapter->down_waitqueue); dev_info(&adapter->pdev->dev, "Reset task did not complete, VF disabled\n"); } -#define I40EVF_RESET_WAIT_MS 10 -#define I40EVF_RESET_WAIT_COUNT 500 +#define IAVF_RESET_WAIT_MS 10 +#define IAVF_RESET_WAIT_COUNT 500 /** - * i40evf_reset_task - Call-back task to handle hardware reset + * iavf_reset_task - Call-back task to handle hardware reset * @work: pointer to work_struct * * During reset we need to shut down and reinitialize the admin queue * before we can use it to communicate with the PF again. We also clear * and reinit the rings because that context is lost as well. **/ -static void i40evf_reset_task(struct work_struct *work) +static void iavf_reset_task(struct work_struct *work) { - struct i40evf_adapter *adapter = container_of(work, - struct i40evf_adapter, + struct iavf_adapter *adapter = container_of(work, + struct iavf_adapter, reset_task); struct virtchnl_vf_resource *vfres = adapter->vf_res; struct net_device *netdev = adapter->netdev; - struct i40e_hw *hw = &adapter->hw; - struct i40evf_vlan_filter *vlf; - struct i40evf_cloud_filter *cf; - struct i40evf_mac_filter *f; + struct iavf_hw *hw = &adapter->hw; + struct iavf_vlan_filter *vlf; + struct iavf_cloud_filter *cf; + struct iavf_mac_filter *f; u32 reg_val; int i = 0, err; bool running; @@ -1860,63 +1835,63 @@ static void i40evf_reset_task(struct work_struct *work) /* When device is being removed it doesn't make sense to run the reset * task, just return in such a case. */ - if (test_bit(__I40EVF_IN_REMOVE_TASK, &adapter->crit_section)) + if (test_bit(__IAVF_IN_REMOVE_TASK, &adapter->crit_section)) return; - while (test_and_set_bit(__I40EVF_IN_CLIENT_TASK, + while (test_and_set_bit(__IAVF_IN_CLIENT_TASK, &adapter->crit_section)) usleep_range(500, 1000); if (CLIENT_ENABLED(adapter)) { - adapter->flags &= ~(I40EVF_FLAG_CLIENT_NEEDS_OPEN | - I40EVF_FLAG_CLIENT_NEEDS_CLOSE | - I40EVF_FLAG_CLIENT_NEEDS_L2_PARAMS | - I40EVF_FLAG_SERVICE_CLIENT_REQUESTED); + adapter->flags &= ~(IAVF_FLAG_CLIENT_NEEDS_OPEN | + IAVF_FLAG_CLIENT_NEEDS_CLOSE | + IAVF_FLAG_CLIENT_NEEDS_L2_PARAMS | + IAVF_FLAG_SERVICE_CLIENT_REQUESTED); cancel_delayed_work_sync(&adapter->client_task); - i40evf_notify_client_close(&adapter->vsi, true); + iavf_notify_client_close(&adapter->vsi, true); } - i40evf_misc_irq_disable(adapter); - if (adapter->flags & I40EVF_FLAG_RESET_NEEDED) { - adapter->flags &= ~I40EVF_FLAG_RESET_NEEDED; + iavf_misc_irq_disable(adapter); + if (adapter->flags & IAVF_FLAG_RESET_NEEDED) { + adapter->flags &= ~IAVF_FLAG_RESET_NEEDED; /* Restart the AQ here. If we have been reset but didn't * detect it, or if the PF had to reinit, our AQ will be hosed. */ - i40evf_shutdown_adminq(hw); - i40evf_init_adminq(hw); - i40evf_request_reset(adapter); + iavf_shutdown_adminq(hw); + iavf_init_adminq(hw); + iavf_request_reset(adapter); } - adapter->flags |= I40EVF_FLAG_RESET_PENDING; + adapter->flags |= IAVF_FLAG_RESET_PENDING; /* poll until we see the reset actually happen */ - for (i = 0; i < I40EVF_RESET_WAIT_COUNT; i++) { - reg_val = rd32(hw, I40E_VF_ARQLEN1) & - I40E_VF_ARQLEN1_ARQENABLE_MASK; + for (i = 0; i < IAVF_RESET_WAIT_COUNT; i++) { + reg_val = rd32(hw, IAVF_VF_ARQLEN1) & + IAVF_VF_ARQLEN1_ARQENABLE_MASK; if (!reg_val) break; usleep_range(5000, 10000); } - if (i == I40EVF_RESET_WAIT_COUNT) { + if (i == IAVF_RESET_WAIT_COUNT) { dev_info(&adapter->pdev->dev, "Never saw reset\n"); goto continue_reset; /* act like the reset happened */ } /* wait until the reset is complete and the PF is responding to us */ - for (i = 0; i < I40EVF_RESET_WAIT_COUNT; i++) { + for (i = 0; i < IAVF_RESET_WAIT_COUNT; i++) { /* sleep first to make sure a minimum wait time is met */ - msleep(I40EVF_RESET_WAIT_MS); + msleep(IAVF_RESET_WAIT_MS); - reg_val = rd32(hw, I40E_VFGEN_RSTAT) & - I40E_VFGEN_RSTAT_VFR_STATE_MASK; + reg_val = rd32(hw, IAVF_VFGEN_RSTAT) & + IAVF_VFGEN_RSTAT_VFR_STATE_MASK; if (reg_val == VIRTCHNL_VFR_VFACTIVE) break; } pci_set_master(adapter->pdev); - if (i == I40EVF_RESET_WAIT_COUNT) { + if (i == IAVF_RESET_WAIT_COUNT) { dev_err(&adapter->pdev->dev, "Reset never finished (%x)\n", reg_val); - i40evf_disable_vf(adapter); - clear_bit(__I40EVF_IN_CLIENT_TASK, &adapter->crit_section); + iavf_disable_vf(adapter); + clear_bit(__IAVF_IN_CLIENT_TASK, &adapter->crit_section); return; /* Do not attempt to reinit. It's dead, Jim. */ } @@ -1925,44 +1900,44 @@ continue_reset: * ndo_open() returning, so we can't assume it means all our open * tasks have finished, since we're not holding the rtnl_lock here. */ - running = ((adapter->state == __I40EVF_RUNNING) || - (adapter->state == __I40EVF_RESETTING)); + running = ((adapter->state == __IAVF_RUNNING) || + (adapter->state == __IAVF_RESETTING)); if (running) { netif_carrier_off(netdev); netif_tx_stop_all_queues(netdev); adapter->link_up = false; - i40evf_napi_disable_all(adapter); + iavf_napi_disable_all(adapter); } - i40evf_irq_disable(adapter); + iavf_irq_disable(adapter); - adapter->state = __I40EVF_RESETTING; - adapter->flags &= ~I40EVF_FLAG_RESET_PENDING; + adapter->state = __IAVF_RESETTING; + adapter->flags &= ~IAVF_FLAG_RESET_PENDING; /* free the Tx/Rx rings and descriptors, might be better to just * re-use them sometime in the future */ - i40evf_free_all_rx_resources(adapter); - i40evf_free_all_tx_resources(adapter); + iavf_free_all_rx_resources(adapter); + iavf_free_all_tx_resources(adapter); - adapter->flags |= I40EVF_FLAG_QUEUES_DISABLED; + adapter->flags |= IAVF_FLAG_QUEUES_DISABLED; /* kill and reinit the admin queue */ - i40evf_shutdown_adminq(hw); + iavf_shutdown_adminq(hw); adapter->current_op = VIRTCHNL_OP_UNKNOWN; - err = i40evf_init_adminq(hw); + err = iavf_init_adminq(hw); if (err) dev_info(&adapter->pdev->dev, "Failed to init adminq: %d\n", err); adapter->aq_required = 0; - if (adapter->flags & I40EVF_FLAG_REINIT_ITR_NEEDED) { - err = i40evf_reinit_interrupt_scheme(adapter); + if (adapter->flags & IAVF_FLAG_REINIT_ITR_NEEDED) { + err = iavf_reinit_interrupt_scheme(adapter); if (err) goto reset_err; } - adapter->aq_required |= I40EVF_FLAG_AQ_GET_CONFIG; - adapter->aq_required |= I40EVF_FLAG_AQ_MAP_VECTORS; + adapter->aq_required |= IAVF_FLAG_AQ_GET_CONFIG; + adapter->aq_required |= IAVF_FLAG_AQ_MAP_VECTORS; spin_lock_bh(&adapter->mac_vlan_list_lock); @@ -1987,10 +1962,10 @@ continue_reset: } spin_unlock_bh(&adapter->cloud_filter_list_lock); - adapter->aq_required |= I40EVF_FLAG_AQ_ADD_MAC_FILTER; - adapter->aq_required |= I40EVF_FLAG_AQ_ADD_VLAN_FILTER; - adapter->aq_required |= I40EVF_FLAG_AQ_ADD_CLOUD_FILTER; - i40evf_misc_irq_enable(adapter); + adapter->aq_required |= IAVF_FLAG_AQ_ADD_MAC_FILTER; + adapter->aq_required |= IAVF_FLAG_AQ_ADD_VLAN_FILTER; + adapter->aq_required |= IAVF_FLAG_AQ_ADD_CLOUD_FILTER; + iavf_misc_irq_enable(adapter); mod_timer(&adapter->watchdog_timer, jiffies + 2); @@ -1999,84 +1974,83 @@ continue_reset: */ if (running) { /* allocate transmit descriptors */ - err = i40evf_setup_all_tx_resources(adapter); + err = iavf_setup_all_tx_resources(adapter); if (err) goto reset_err; /* allocate receive descriptors */ - err = i40evf_setup_all_rx_resources(adapter); + err = iavf_setup_all_rx_resources(adapter); if (err) goto reset_err; - if (adapter->flags & I40EVF_FLAG_REINIT_ITR_NEEDED) { - err = i40evf_request_traffic_irqs(adapter, - netdev->name); + if (adapter->flags & IAVF_FLAG_REINIT_ITR_NEEDED) { + err = iavf_request_traffic_irqs(adapter, netdev->name); if (err) goto reset_err; - adapter->flags &= ~I40EVF_FLAG_REINIT_ITR_NEEDED; + adapter->flags &= ~IAVF_FLAG_REINIT_ITR_NEEDED; } - i40evf_configure(adapter); + iavf_configure(adapter); - i40evf_up_complete(adapter); + iavf_up_complete(adapter); - i40evf_irq_enable(adapter, true); + iavf_irq_enable(adapter, true); } else { - adapter->state = __I40EVF_DOWN; + adapter->state = __IAVF_DOWN; wake_up(&adapter->down_waitqueue); } - clear_bit(__I40EVF_IN_CLIENT_TASK, &adapter->crit_section); - clear_bit(__I40EVF_IN_CRITICAL_TASK, &adapter->crit_section); + clear_bit(__IAVF_IN_CLIENT_TASK, &adapter->crit_section); + clear_bit(__IAVF_IN_CRITICAL_TASK, &adapter->crit_section); return; reset_err: - clear_bit(__I40EVF_IN_CLIENT_TASK, &adapter->crit_section); - clear_bit(__I40EVF_IN_CRITICAL_TASK, &adapter->crit_section); + clear_bit(__IAVF_IN_CLIENT_TASK, &adapter->crit_section); + clear_bit(__IAVF_IN_CRITICAL_TASK, &adapter->crit_section); dev_err(&adapter->pdev->dev, "failed to allocate resources during reinit\n"); - i40evf_close(netdev); + iavf_close(netdev); } /** - * i40evf_adminq_task - worker thread to clean the admin queue + * iavf_adminq_task - worker thread to clean the admin queue * @work: pointer to work_struct containing our data **/ -static void i40evf_adminq_task(struct work_struct *work) +static void iavf_adminq_task(struct work_struct *work) { - struct i40evf_adapter *adapter = - container_of(work, struct i40evf_adapter, adminq_task); - struct i40e_hw *hw = &adapter->hw; + struct iavf_adapter *adapter = + container_of(work, struct iavf_adapter, adminq_task); + struct iavf_hw *hw = &adapter->hw; struct i40e_arq_event_info event; enum virtchnl_ops v_op; - i40e_status ret, v_ret; + iavf_status ret, v_ret; u32 val, oldval; u16 pending; - if (adapter->flags & I40EVF_FLAG_PF_COMMS_FAILED) + if (adapter->flags & IAVF_FLAG_PF_COMMS_FAILED) goto out; - event.buf_len = I40EVF_MAX_AQ_BUF_SIZE; + event.buf_len = IAVF_MAX_AQ_BUF_SIZE; event.msg_buf = kzalloc(event.buf_len, GFP_KERNEL); if (!event.msg_buf) goto out; do { - ret = i40evf_clean_arq_element(hw, &event, &pending); + ret = iavf_clean_arq_element(hw, &event, &pending); v_op = (enum virtchnl_ops)le32_to_cpu(event.desc.cookie_high); - v_ret = (i40e_status)le32_to_cpu(event.desc.cookie_low); + v_ret = (iavf_status)le32_to_cpu(event.desc.cookie_low); if (ret || !v_op) break; /* No event to process or error cleaning ARQ */ - i40evf_virtchnl_completion(adapter, v_op, v_ret, event.msg_buf, - event.msg_len); + iavf_virtchnl_completion(adapter, v_op, v_ret, event.msg_buf, + event.msg_len); if (pending != 0) - memset(event.msg_buf, 0, I40EVF_MAX_AQ_BUF_SIZE); + memset(event.msg_buf, 0, IAVF_MAX_AQ_BUF_SIZE); } while (pending); if ((adapter->flags & - (I40EVF_FLAG_RESET_PENDING | I40EVF_FLAG_RESET_NEEDED)) || - adapter->state == __I40EVF_RESETTING) + (IAVF_FLAG_RESET_PENDING | IAVF_FLAG_RESET_NEEDED)) || + adapter->state == __IAVF_RESETTING) goto freedom; /* check for error indications */ @@ -2084,34 +2058,34 @@ static void i40evf_adminq_task(struct work_struct *work) if (val == 0xdeadbeef) /* indicates device in reset */ goto freedom; oldval = val; - if (val & I40E_VF_ARQLEN1_ARQVFE_MASK) { + if (val & IAVF_VF_ARQLEN1_ARQVFE_MASK) { dev_info(&adapter->pdev->dev, "ARQ VF Error detected\n"); - val &= ~I40E_VF_ARQLEN1_ARQVFE_MASK; + val &= ~IAVF_VF_ARQLEN1_ARQVFE_MASK; } - if (val & I40E_VF_ARQLEN1_ARQOVFL_MASK) { + if (val & IAVF_VF_ARQLEN1_ARQOVFL_MASK) { dev_info(&adapter->pdev->dev, "ARQ Overflow Error detected\n"); - val &= ~I40E_VF_ARQLEN1_ARQOVFL_MASK; + val &= ~IAVF_VF_ARQLEN1_ARQOVFL_MASK; } - if (val & I40E_VF_ARQLEN1_ARQCRIT_MASK) { + if (val & IAVF_VF_ARQLEN1_ARQCRIT_MASK) { dev_info(&adapter->pdev->dev, "ARQ Critical Error detected\n"); - val &= ~I40E_VF_ARQLEN1_ARQCRIT_MASK; + val &= ~IAVF_VF_ARQLEN1_ARQCRIT_MASK; } if (oldval != val) wr32(hw, hw->aq.arq.len, val); val = rd32(hw, hw->aq.asq.len); oldval = val; - if (val & I40E_VF_ATQLEN1_ATQVFE_MASK) { + if (val & IAVF_VF_ATQLEN1_ATQVFE_MASK) { dev_info(&adapter->pdev->dev, "ASQ VF Error detected\n"); - val &= ~I40E_VF_ATQLEN1_ATQVFE_MASK; + val &= ~IAVF_VF_ATQLEN1_ATQVFE_MASK; } - if (val & I40E_VF_ATQLEN1_ATQOVFL_MASK) { + if (val & IAVF_VF_ATQLEN1_ATQOVFL_MASK) { dev_info(&adapter->pdev->dev, "ASQ Overflow Error detected\n"); - val &= ~I40E_VF_ATQLEN1_ATQOVFL_MASK; + val &= ~IAVF_VF_ATQLEN1_ATQOVFL_MASK; } - if (val & I40E_VF_ATQLEN1_ATQCRIT_MASK) { + if (val & IAVF_VF_ATQLEN1_ATQCRIT_MASK) { dev_info(&adapter->pdev->dev, "ASQ Critical Error detected\n"); - val &= ~I40E_VF_ATQLEN1_ATQCRIT_MASK; + val &= ~IAVF_VF_ATQLEN1_ATQCRIT_MASK; } if (oldval != val) wr32(hw, hw->aq.asq.len, val); @@ -2120,58 +2094,58 @@ freedom: kfree(event.msg_buf); out: /* re-enable Admin queue interrupt cause */ - i40evf_misc_irq_enable(adapter); + iavf_misc_irq_enable(adapter); } /** - * i40evf_client_task - worker thread to perform client work + * iavf_client_task - worker thread to perform client work * @work: pointer to work_struct containing our data * * This task handles client interactions. Because client calls can be * reentrant, we can't handle them in the watchdog. **/ -static void i40evf_client_task(struct work_struct *work) +static void iavf_client_task(struct work_struct *work) { - struct i40evf_adapter *adapter = - container_of(work, struct i40evf_adapter, client_task.work); + struct iavf_adapter *adapter = + container_of(work, struct iavf_adapter, client_task.work); /* If we can't get the client bit, just give up. We'll be rescheduled * later. */ - if (test_and_set_bit(__I40EVF_IN_CLIENT_TASK, &adapter->crit_section)) + if (test_and_set_bit(__IAVF_IN_CLIENT_TASK, &adapter->crit_section)) return; - if (adapter->flags & I40EVF_FLAG_SERVICE_CLIENT_REQUESTED) { - i40evf_client_subtask(adapter); - adapter->flags &= ~I40EVF_FLAG_SERVICE_CLIENT_REQUESTED; + if (adapter->flags & IAVF_FLAG_SERVICE_CLIENT_REQUESTED) { + iavf_client_subtask(adapter); + adapter->flags &= ~IAVF_FLAG_SERVICE_CLIENT_REQUESTED; goto out; } - if (adapter->flags & I40EVF_FLAG_CLIENT_NEEDS_L2_PARAMS) { - i40evf_notify_client_l2_params(&adapter->vsi); - adapter->flags &= ~I40EVF_FLAG_CLIENT_NEEDS_L2_PARAMS; + if (adapter->flags & IAVF_FLAG_CLIENT_NEEDS_L2_PARAMS) { + iavf_notify_client_l2_params(&adapter->vsi); + adapter->flags &= ~IAVF_FLAG_CLIENT_NEEDS_L2_PARAMS; goto out; } - if (adapter->flags & I40EVF_FLAG_CLIENT_NEEDS_CLOSE) { - i40evf_notify_client_close(&adapter->vsi, false); - adapter->flags &= ~I40EVF_FLAG_CLIENT_NEEDS_CLOSE; + if (adapter->flags & IAVF_FLAG_CLIENT_NEEDS_CLOSE) { + iavf_notify_client_close(&adapter->vsi, false); + adapter->flags &= ~IAVF_FLAG_CLIENT_NEEDS_CLOSE; goto out; } - if (adapter->flags & I40EVF_FLAG_CLIENT_NEEDS_OPEN) { - i40evf_notify_client_open(&adapter->vsi); - adapter->flags &= ~I40EVF_FLAG_CLIENT_NEEDS_OPEN; + if (adapter->flags & IAVF_FLAG_CLIENT_NEEDS_OPEN) { + iavf_notify_client_open(&adapter->vsi); + adapter->flags &= ~IAVF_FLAG_CLIENT_NEEDS_OPEN; } out: - clear_bit(__I40EVF_IN_CLIENT_TASK, &adapter->crit_section); + clear_bit(__IAVF_IN_CLIENT_TASK, &adapter->crit_section); } /** - * i40evf_free_all_tx_resources - Free Tx Resources for All Queues + * iavf_free_all_tx_resources - Free Tx Resources for All Queues * @adapter: board private structure * * Free all transmit software resources **/ -void i40evf_free_all_tx_resources(struct i40evf_adapter *adapter) +void iavf_free_all_tx_resources(struct iavf_adapter *adapter) { int i; @@ -2180,11 +2154,11 @@ void i40evf_free_all_tx_resources(struct i40evf_adapter *adapter) for (i = 0; i < adapter->num_active_queues; i++) if (adapter->tx_rings[i].desc) - i40evf_free_tx_resources(&adapter->tx_rings[i]); + iavf_free_tx_resources(&adapter->tx_rings[i]); } /** - * i40evf_setup_all_tx_resources - allocate all queues Tx resources + * iavf_setup_all_tx_resources - allocate all queues Tx resources * @adapter: board private structure * * If this function returns with an error, then it's possible one or @@ -2193,13 +2167,13 @@ void i40evf_free_all_tx_resources(struct i40evf_adapter *adapter) * * Return 0 on success, negative on failure **/ -static int i40evf_setup_all_tx_resources(struct i40evf_adapter *adapter) +static int iavf_setup_all_tx_resources(struct iavf_adapter *adapter) { int i, err = 0; for (i = 0; i < adapter->num_active_queues; i++) { adapter->tx_rings[i].count = adapter->tx_desc_count; - err = i40evf_setup_tx_descriptors(&adapter->tx_rings[i]); + err = iavf_setup_tx_descriptors(&adapter->tx_rings[i]); if (!err) continue; dev_err(&adapter->pdev->dev, @@ -2211,7 +2185,7 @@ static int i40evf_setup_all_tx_resources(struct i40evf_adapter *adapter) } /** - * i40evf_setup_all_rx_resources - allocate all queues Rx resources + * iavf_setup_all_rx_resources - allocate all queues Rx resources * @adapter: board private structure * * If this function returns with an error, then it's possible one or @@ -2220,13 +2194,13 @@ static int i40evf_setup_all_tx_resources(struct i40evf_adapter *adapter) * * Return 0 on success, negative on failure **/ -static int i40evf_setup_all_rx_resources(struct i40evf_adapter *adapter) +static int iavf_setup_all_rx_resources(struct iavf_adapter *adapter) { int i, err = 0; for (i = 0; i < adapter->num_active_queues; i++) { adapter->rx_rings[i].count = adapter->rx_desc_count; - err = i40evf_setup_rx_descriptors(&adapter->rx_rings[i]); + err = iavf_setup_rx_descriptors(&adapter->rx_rings[i]); if (!err) continue; dev_err(&adapter->pdev->dev, @@ -2237,12 +2211,12 @@ static int i40evf_setup_all_rx_resources(struct i40evf_adapter *adapter) } /** - * i40evf_free_all_rx_resources - Free Rx Resources for All Queues + * iavf_free_all_rx_resources - Free Rx Resources for All Queues * @adapter: board private structure * * Free all receive software resources **/ -void i40evf_free_all_rx_resources(struct i40evf_adapter *adapter) +void iavf_free_all_rx_resources(struct iavf_adapter *adapter) { int i; @@ -2251,16 +2225,16 @@ void i40evf_free_all_rx_resources(struct i40evf_adapter *adapter) for (i = 0; i < adapter->num_active_queues; i++) if (adapter->rx_rings[i].desc) - i40evf_free_rx_resources(&adapter->rx_rings[i]); + iavf_free_rx_resources(&adapter->rx_rings[i]); } /** - * i40evf_validate_tx_bandwidth - validate the max Tx bandwidth + * iavf_validate_tx_bandwidth - validate the max Tx bandwidth * @adapter: board private structure * @max_tx_rate: max Tx bw for a tc **/ -static int i40evf_validate_tx_bandwidth(struct i40evf_adapter *adapter, - u64 max_tx_rate) +static int iavf_validate_tx_bandwidth(struct iavf_adapter *adapter, + u64 max_tx_rate) { int speed = 0, ret = 0; @@ -2297,7 +2271,7 @@ static int i40evf_validate_tx_bandwidth(struct i40evf_adapter *adapter, } /** - * i40evf_validate_channel_config - validate queue mapping info + * iavf_validate_channel_config - validate queue mapping info * @adapter: board private structure * @mqprio_qopt: queue parameters * @@ -2305,15 +2279,15 @@ static int i40evf_validate_tx_bandwidth(struct i40evf_adapter *adapter, * configure queue channels is valid or not. Returns 0 on a valid * config. **/ -static int i40evf_validate_ch_config(struct i40evf_adapter *adapter, - struct tc_mqprio_qopt_offload *mqprio_qopt) +static int iavf_validate_ch_config(struct iavf_adapter *adapter, + struct tc_mqprio_qopt_offload *mqprio_qopt) { u64 total_max_rate = 0; int i, num_qps = 0; u64 tx_rate = 0; int ret = 0; - if (mqprio_qopt->qopt.num_tc > I40EVF_MAX_TRAFFIC_CLASS || + if (mqprio_qopt->qopt.num_tc > IAVF_MAX_TRAFFIC_CLASS || mqprio_qopt->qopt.num_tc < 1) return -EINVAL; @@ -2328,24 +2302,24 @@ static int i40evf_validate_ch_config(struct i40evf_adapter *adapter, } /*convert to Mbps */ tx_rate = div_u64(mqprio_qopt->max_rate[i], - I40EVF_MBPS_DIVISOR); + IAVF_MBPS_DIVISOR); total_max_rate += tx_rate; num_qps += mqprio_qopt->qopt.count[i]; } - if (num_qps > I40EVF_MAX_REQ_QUEUES) + if (num_qps > IAVF_MAX_REQ_QUEUES) return -EINVAL; - ret = i40evf_validate_tx_bandwidth(adapter, total_max_rate); + ret = iavf_validate_tx_bandwidth(adapter, total_max_rate); return ret; } /** - * i40evf_del_all_cloud_filters - delete all cloud filters + * iavf_del_all_cloud_filters - delete all cloud filters * on the traffic classes **/ -static void i40evf_del_all_cloud_filters(struct i40evf_adapter *adapter) +static void iavf_del_all_cloud_filters(struct iavf_adapter *adapter) { - struct i40evf_cloud_filter *cf, *cftmp; + struct iavf_cloud_filter *cf, *cftmp; spin_lock_bh(&adapter->cloud_filter_list_lock); list_for_each_entry_safe(cf, cftmp, &adapter->cloud_filter_list, @@ -2358,7 +2332,7 @@ static void i40evf_del_all_cloud_filters(struct i40evf_adapter *adapter) } /** - * __i40evf_setup_tc - configure multiple traffic classes + * __iavf_setup_tc - configure multiple traffic classes * @netdev: network interface device structure * @type_date: tc offload data * @@ -2368,10 +2342,10 @@ static void i40evf_del_all_cloud_filters(struct i40evf_adapter *adapter) * * Returns 0 on success. **/ -static int __i40evf_setup_tc(struct net_device *netdev, void *type_data) +static int __iavf_setup_tc(struct net_device *netdev, void *type_data) { struct tc_mqprio_qopt_offload *mqprio_qopt = type_data; - struct i40evf_adapter *adapter = netdev_priv(netdev); + struct iavf_adapter *adapter = netdev_priv(netdev); struct virtchnl_vf_resource *vfres = adapter->vf_res; u8 num_tc = 0, total_qps = 0; int ret = 0, netdev_tc = 0; @@ -2384,14 +2358,14 @@ static int __i40evf_setup_tc(struct net_device *netdev, void *type_data) /* delete queue_channel */ if (!mqprio_qopt->qopt.hw) { - if (adapter->ch_config.state == __I40EVF_TC_RUNNING) { + if (adapter->ch_config.state == __IAVF_TC_RUNNING) { /* reset the tc configuration */ netdev_reset_tc(netdev); adapter->num_tc = 0; netif_tx_stop_all_queues(netdev); netif_tx_disable(netdev); - i40evf_del_all_cloud_filters(adapter); - adapter->aq_required = I40EVF_FLAG_AQ_DISABLE_CHANNELS; + iavf_del_all_cloud_filters(adapter); + adapter->aq_required = IAVF_FLAG_AQ_DISABLE_CHANNELS; goto exit; } else { return -EINVAL; @@ -2404,12 +2378,12 @@ static int __i40evf_setup_tc(struct net_device *netdev, void *type_data) dev_err(&adapter->pdev->dev, "ADq not supported\n"); return -EOPNOTSUPP; } - if (adapter->ch_config.state != __I40EVF_TC_INVALID) { + if (adapter->ch_config.state != __IAVF_TC_INVALID) { dev_err(&adapter->pdev->dev, "TC configuration already exists\n"); return -EINVAL; } - ret = i40evf_validate_ch_config(adapter, mqprio_qopt); + ret = iavf_validate_ch_config(adapter, mqprio_qopt); if (ret) return ret; /* Return if same TC config is requested */ @@ -2417,7 +2391,7 @@ static int __i40evf_setup_tc(struct net_device *netdev, void *type_data) return 0; adapter->num_tc = num_tc; - for (i = 0; i < I40EVF_MAX_TRAFFIC_CLASS; i++) { + for (i = 0; i < IAVF_MAX_TRAFFIC_CLASS; i++) { if (i < num_tc) { adapter->ch_config.ch_info[i].count = mqprio_qopt->qopt.count[i]; @@ -2427,7 +2401,7 @@ static int __i40evf_setup_tc(struct net_device *netdev, void *type_data) max_tx_rate = mqprio_qopt->max_rate[i]; /* convert to Mbps */ max_tx_rate = div_u64(max_tx_rate, - I40EVF_MBPS_DIVISOR); + IAVF_MBPS_DIVISOR); adapter->ch_config.ch_info[i].max_tx_rate = max_tx_rate; } else { @@ -2438,11 +2412,11 @@ static int __i40evf_setup_tc(struct net_device *netdev, void *type_data) adapter->ch_config.total_qps = total_qps; netif_tx_stop_all_queues(netdev); netif_tx_disable(netdev); - adapter->aq_required |= I40EVF_FLAG_AQ_ENABLE_CHANNELS; + adapter->aq_required |= IAVF_FLAG_AQ_ENABLE_CHANNELS; netdev_reset_tc(netdev); /* Report the tc mapping up the stack */ netdev_set_num_tc(adapter->netdev, num_tc); - for (i = 0; i < I40EVF_MAX_TRAFFIC_CLASS; i++) { + for (i = 0; i < IAVF_MAX_TRAFFIC_CLASS; i++) { u16 qcount = mqprio_qopt->qopt.count[i]; u16 qoffset = mqprio_qopt->qopt.offset[i]; @@ -2456,14 +2430,14 @@ exit: } /** - * i40evf_parse_cls_flower - Parse tc flower filters provided by kernel + * iavf_parse_cls_flower - Parse tc flower filters provided by kernel * @adapter: board private structure * @cls_flower: pointer to struct tc_cls_flower_offload * @filter: pointer to cloud filter structure */ -static int i40evf_parse_cls_flower(struct i40evf_adapter *adapter, - struct tc_cls_flower_offload *f, - struct i40evf_cloud_filter *filter) +static int iavf_parse_cls_flower(struct iavf_adapter *adapter, + struct tc_cls_flower_offload *f, + struct iavf_cloud_filter *filter) { u16 n_proto_mask = 0; u16 n_proto_key = 0; @@ -2494,7 +2468,7 @@ static int i40evf_parse_cls_flower(struct i40evf_adapter *adapter, f->mask); if (mask->keyid != 0) - field_flags |= I40EVF_CLOUD_FIELD_TEN_ID; + field_flags |= IAVF_CLOUD_FIELD_TEN_ID; } if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_BASIC)) { @@ -2541,7 +2515,7 @@ static int i40evf_parse_cls_flower(struct i40evf_adapter *adapter, /* use is_broadcast and is_zero to check for all 0xf or 0 */ if (!is_zero_ether_addr(mask->dst)) { if (is_broadcast_ether_addr(mask->dst)) { - field_flags |= I40EVF_CLOUD_FIELD_OMAC; + field_flags |= IAVF_CLOUD_FIELD_OMAC; } else { dev_err(&adapter->pdev->dev, "Bad ether dest mask %pM\n", mask->dst); @@ -2551,7 +2525,7 @@ static int i40evf_parse_cls_flower(struct i40evf_adapter *adapter, if (!is_zero_ether_addr(mask->src)) { if (is_broadcast_ether_addr(mask->src)) { - field_flags |= I40EVF_CLOUD_FIELD_IMAC; + field_flags |= IAVF_CLOUD_FIELD_IMAC; } else { dev_err(&adapter->pdev->dev, "Bad ether src mask %pM\n", mask->src); @@ -2592,7 +2566,7 @@ static int i40evf_parse_cls_flower(struct i40evf_adapter *adapter, if (mask->vlan_id) { if (mask->vlan_id == VLAN_VID_MASK) { - field_flags |= I40EVF_CLOUD_FIELD_IVLAN; + field_flags |= IAVF_CLOUD_FIELD_IVLAN; } else { dev_err(&adapter->pdev->dev, "Bad vlan mask %u\n", mask->vlan_id); @@ -2624,7 +2598,7 @@ static int i40evf_parse_cls_flower(struct i40evf_adapter *adapter, if (mask->dst) { if (mask->dst == cpu_to_be32(0xffffffff)) { - field_flags |= I40EVF_CLOUD_FIELD_IIP; + field_flags |= IAVF_CLOUD_FIELD_IIP; } else { dev_err(&adapter->pdev->dev, "Bad ip dst mask 0x%08x\n", be32_to_cpu(mask->dst)); @@ -2634,7 +2608,7 @@ static int i40evf_parse_cls_flower(struct i40evf_adapter *adapter, if (mask->src) { if (mask->src == cpu_to_be32(0xffffffff)) { - field_flags |= I40EVF_CLOUD_FIELD_IIP; + field_flags |= IAVF_CLOUD_FIELD_IIP; } else { dev_err(&adapter->pdev->dev, "Bad ip src mask 0x%08x\n", be32_to_cpu(mask->dst)); @@ -2642,7 +2616,7 @@ static int i40evf_parse_cls_flower(struct i40evf_adapter *adapter, } } - if (field_flags & I40EVF_CLOUD_FIELD_TEN_ID) { + if (field_flags & IAVF_CLOUD_FIELD_TEN_ID) { dev_info(&adapter->pdev->dev, "Tenant id not allowed for ip filter\n"); return I40E_ERR_CONFIG; } @@ -2683,7 +2657,7 @@ static int i40evf_parse_cls_flower(struct i40evf_adapter *adapter, return I40E_ERR_CONFIG; } if (!ipv6_addr_any(&mask->dst) || !ipv6_addr_any(&mask->src)) - field_flags |= I40EVF_CLOUD_FIELD_IIP; + field_flags |= IAVF_CLOUD_FIELD_IIP; for (i = 0; i < 4; i++) vf->mask.tcp_spec.dst_ip[i] |= cpu_to_be32(0xffffffff); @@ -2706,7 +2680,7 @@ static int i40evf_parse_cls_flower(struct i40evf_adapter *adapter, if (mask->src) { if (mask->src == cpu_to_be16(0xffff)) { - field_flags |= I40EVF_CLOUD_FIELD_IIP; + field_flags |= IAVF_CLOUD_FIELD_IIP; } else { dev_err(&adapter->pdev->dev, "Bad src port mask %u\n", be16_to_cpu(mask->src)); @@ -2716,7 +2690,7 @@ static int i40evf_parse_cls_flower(struct i40evf_adapter *adapter, if (mask->dst) { if (mask->dst == cpu_to_be16(0xffff)) { - field_flags |= I40EVF_CLOUD_FIELD_IIP; + field_flags |= IAVF_CLOUD_FIELD_IIP; } else { dev_err(&adapter->pdev->dev, "Bad dst port mask %u\n", be16_to_cpu(mask->dst)); @@ -2739,13 +2713,13 @@ static int i40evf_parse_cls_flower(struct i40evf_adapter *adapter, } /** - * i40evf_handle_tclass - Forward to a traffic class on the device + * iavf_handle_tclass - Forward to a traffic class on the device * @adapter: board private structure * @tc: traffic class index on the device * @filter: pointer to cloud filter structure */ -static int i40evf_handle_tclass(struct i40evf_adapter *adapter, u32 tc, - struct i40evf_cloud_filter *filter) +static int iavf_handle_tclass(struct iavf_adapter *adapter, u32 tc, + struct iavf_cloud_filter *filter) { if (tc == 0) return 0; @@ -2763,15 +2737,15 @@ static int i40evf_handle_tclass(struct i40evf_adapter *adapter, u32 tc, } /** - * i40evf_configure_clsflower - Add tc flower filters + * iavf_configure_clsflower - Add tc flower filters * @adapter: board private structure * @cls_flower: Pointer to struct tc_cls_flower_offload */ -static int i40evf_configure_clsflower(struct i40evf_adapter *adapter, - struct tc_cls_flower_offload *cls_flower) +static int iavf_configure_clsflower(struct iavf_adapter *adapter, + struct tc_cls_flower_offload *cls_flower) { int tc = tc_classid_to_hwtc(adapter->netdev, cls_flower->classid); - struct i40evf_cloud_filter *filter = NULL; + struct iavf_cloud_filter *filter = NULL; int err = -EINVAL, count = 50; if (tc < 0) { @@ -2783,7 +2757,7 @@ static int i40evf_configure_clsflower(struct i40evf_adapter *adapter, if (!filter) return -ENOMEM; - while (test_and_set_bit(__I40EVF_IN_CRITICAL_TASK, + while (test_and_set_bit(__IAVF_IN_CRITICAL_TASK, &adapter->crit_section)) { if (--count == 0) goto err; @@ -2796,11 +2770,11 @@ static int i40evf_configure_clsflower(struct i40evf_adapter *adapter, memset(&filter->f.mask.tcp_spec, 0, sizeof(struct virtchnl_l4_spec)); /* start out with flow type and eth type IPv4 to begin with */ filter->f.flow_type = VIRTCHNL_TCP_V4_FLOW; - err = i40evf_parse_cls_flower(adapter, cls_flower, filter); + err = iavf_parse_cls_flower(adapter, cls_flower, filter); if (err < 0) goto err; - err = i40evf_handle_tclass(adapter, tc, filter); + err = iavf_handle_tclass(adapter, tc, filter); if (err < 0) goto err; @@ -2809,27 +2783,27 @@ static int i40evf_configure_clsflower(struct i40evf_adapter *adapter, list_add_tail(&filter->list, &adapter->cloud_filter_list); adapter->num_cloud_filters++; filter->add = true; - adapter->aq_required |= I40EVF_FLAG_AQ_ADD_CLOUD_FILTER; + adapter->aq_required |= IAVF_FLAG_AQ_ADD_CLOUD_FILTER; spin_unlock_bh(&adapter->cloud_filter_list_lock); err: if (err) kfree(filter); - clear_bit(__I40EVF_IN_CRITICAL_TASK, &adapter->crit_section); + clear_bit(__IAVF_IN_CRITICAL_TASK, &adapter->crit_section); return err; } -/* i40evf_find_cf - Find the cloud filter in the list +/* iavf_find_cf - Find the cloud filter in the list * @adapter: Board private structure * @cookie: filter specific cookie * * Returns ptr to the filter object or NULL. Must be called while holding the * cloud_filter_list_lock. */ -static struct i40evf_cloud_filter *i40evf_find_cf(struct i40evf_adapter *adapter, - unsigned long *cookie) +static struct iavf_cloud_filter *iavf_find_cf(struct iavf_adapter *adapter, + unsigned long *cookie) { - struct i40evf_cloud_filter *filter = NULL; + struct iavf_cloud_filter *filter = NULL; if (!cookie) return NULL; @@ -2842,21 +2816,21 @@ static struct i40evf_cloud_filter *i40evf_find_cf(struct i40evf_adapter *adapter } /** - * i40evf_delete_clsflower - Remove tc flower filters + * iavf_delete_clsflower - Remove tc flower filters * @adapter: board private structure * @cls_flower: Pointer to struct tc_cls_flower_offload */ -static int i40evf_delete_clsflower(struct i40evf_adapter *adapter, - struct tc_cls_flower_offload *cls_flower) +static int iavf_delete_clsflower(struct iavf_adapter *adapter, + struct tc_cls_flower_offload *cls_flower) { - struct i40evf_cloud_filter *filter = NULL; + struct iavf_cloud_filter *filter = NULL; int err = 0; spin_lock_bh(&adapter->cloud_filter_list_lock); - filter = i40evf_find_cf(adapter, &cls_flower->cookie); + filter = iavf_find_cf(adapter, &cls_flower->cookie); if (filter) { filter->del = true; - adapter->aq_required |= I40EVF_FLAG_AQ_DEL_CLOUD_FILTER; + adapter->aq_required |= IAVF_FLAG_AQ_DEL_CLOUD_FILTER; } else { err = -EINVAL; } @@ -2866,21 +2840,21 @@ static int i40evf_delete_clsflower(struct i40evf_adapter *adapter, } /** - * i40evf_setup_tc_cls_flower - flower classifier offloads + * iavf_setup_tc_cls_flower - flower classifier offloads * @netdev: net device to configure * @type_data: offload data */ -static int i40evf_setup_tc_cls_flower(struct i40evf_adapter *adapter, - struct tc_cls_flower_offload *cls_flower) +static int iavf_setup_tc_cls_flower(struct iavf_adapter *adapter, + struct tc_cls_flower_offload *cls_flower) { if (cls_flower->common.chain_index) return -EOPNOTSUPP; switch (cls_flower->command) { case TC_CLSFLOWER_REPLACE: - return i40evf_configure_clsflower(adapter, cls_flower); + return iavf_configure_clsflower(adapter, cls_flower); case TC_CLSFLOWER_DESTROY: - return i40evf_delete_clsflower(adapter, cls_flower); + return iavf_delete_clsflower(adapter, cls_flower); case TC_CLSFLOWER_STATS: return -EOPNOTSUPP; default: @@ -2889,46 +2863,46 @@ static int i40evf_setup_tc_cls_flower(struct i40evf_adapter *adapter, } /** - * i40evf_setup_tc_block_cb - block callback for tc + * iavf_setup_tc_block_cb - block callback for tc * @type: type of offload * @type_data: offload data * @cb_priv: * * This function is the block callback for traffic classes **/ -static int i40evf_setup_tc_block_cb(enum tc_setup_type type, void *type_data, - void *cb_priv) +static int iavf_setup_tc_block_cb(enum tc_setup_type type, void *type_data, + void *cb_priv) { switch (type) { case TC_SETUP_CLSFLOWER: - return i40evf_setup_tc_cls_flower(cb_priv, type_data); + return iavf_setup_tc_cls_flower(cb_priv, type_data); default: return -EOPNOTSUPP; } } /** - * i40evf_setup_tc_block - register callbacks for tc + * iavf_setup_tc_block - register callbacks for tc * @netdev: network interface device structure * @f: tc offload data * * This function registers block callbacks for tc * offloads **/ -static int i40evf_setup_tc_block(struct net_device *dev, - struct tc_block_offload *f) +static int iavf_setup_tc_block(struct net_device *dev, + struct tc_block_offload *f) { - struct i40evf_adapter *adapter = netdev_priv(dev); + struct iavf_adapter *adapter = netdev_priv(dev); if (f->binder_type != TCF_BLOCK_BINDER_TYPE_CLSACT_INGRESS) return -EOPNOTSUPP; switch (f->command) { case TC_BLOCK_BIND: - return tcf_block_cb_register(f->block, i40evf_setup_tc_block_cb, + return tcf_block_cb_register(f->block, iavf_setup_tc_block_cb, adapter, adapter, f->extack); case TC_BLOCK_UNBIND: - tcf_block_cb_unregister(f->block, i40evf_setup_tc_block_cb, + tcf_block_cb_unregister(f->block, iavf_setup_tc_block_cb, adapter); return 0; default: @@ -2937,7 +2911,7 @@ static int i40evf_setup_tc_block(struct net_device *dev, } /** - * i40evf_setup_tc - configure multiple traffic classes + * iavf_setup_tc - configure multiple traffic classes * @netdev: network interface device structure * @type: type of offload * @type_date: tc offload data @@ -2947,21 +2921,21 @@ static int i40evf_setup_tc_block(struct net_device *dev, * * Returns 0 on success **/ -static int i40evf_setup_tc(struct net_device *netdev, enum tc_setup_type type, - void *type_data) +static int iavf_setup_tc(struct net_device *netdev, enum tc_setup_type type, + void *type_data) { switch (type) { case TC_SETUP_QDISC_MQPRIO: - return __i40evf_setup_tc(netdev, type_data); + return __iavf_setup_tc(netdev, type_data); case TC_SETUP_BLOCK: - return i40evf_setup_tc_block(netdev, type_data); + return iavf_setup_tc_block(netdev, type_data); default: return -EOPNOTSUPP; } } /** - * i40evf_open - Called when a network interface is made active + * iavf_open - Called when a network interface is made active * @netdev: network interface device structure * * Returns 0 on success, negative value on failure @@ -2972,71 +2946,71 @@ static int i40evf_setup_tc(struct net_device *netdev, enum tc_setup_type type, * handler is registered with the OS, the watchdog timer is started, * and the stack is notified that the interface is ready. **/ -static int i40evf_open(struct net_device *netdev) +static int iavf_open(struct net_device *netdev) { - struct i40evf_adapter *adapter = netdev_priv(netdev); + struct iavf_adapter *adapter = netdev_priv(netdev); int err; - if (adapter->flags & I40EVF_FLAG_PF_COMMS_FAILED) { + if (adapter->flags & IAVF_FLAG_PF_COMMS_FAILED) { dev_err(&adapter->pdev->dev, "Unable to open device due to PF driver failure.\n"); return -EIO; } - while (test_and_set_bit(__I40EVF_IN_CRITICAL_TASK, + while (test_and_set_bit(__IAVF_IN_CRITICAL_TASK, &adapter->crit_section)) usleep_range(500, 1000); - if (adapter->state != __I40EVF_DOWN) { + if (adapter->state != __IAVF_DOWN) { err = -EBUSY; goto err_unlock; } /* allocate transmit descriptors */ - err = i40evf_setup_all_tx_resources(adapter); + err = iavf_setup_all_tx_resources(adapter); if (err) goto err_setup_tx; /* allocate receive descriptors */ - err = i40evf_setup_all_rx_resources(adapter); + err = iavf_setup_all_rx_resources(adapter); if (err) goto err_setup_rx; /* clear any pending interrupts, may auto mask */ - err = i40evf_request_traffic_irqs(adapter, netdev->name); + err = iavf_request_traffic_irqs(adapter, netdev->name); if (err) goto err_req_irq; spin_lock_bh(&adapter->mac_vlan_list_lock); - i40evf_add_filter(adapter, adapter->hw.mac.addr); + iavf_add_filter(adapter, adapter->hw.mac.addr); spin_unlock_bh(&adapter->mac_vlan_list_lock); - i40evf_configure(adapter); + iavf_configure(adapter); - i40evf_up_complete(adapter); + iavf_up_complete(adapter); - i40evf_irq_enable(adapter, true); + iavf_irq_enable(adapter, true); - clear_bit(__I40EVF_IN_CRITICAL_TASK, &adapter->crit_section); + clear_bit(__IAVF_IN_CRITICAL_TASK, &adapter->crit_section); return 0; err_req_irq: - i40evf_down(adapter); - i40evf_free_traffic_irqs(adapter); + iavf_down(adapter); + iavf_free_traffic_irqs(adapter); err_setup_rx: - i40evf_free_all_rx_resources(adapter); + iavf_free_all_rx_resources(adapter); err_setup_tx: - i40evf_free_all_tx_resources(adapter); + iavf_free_all_tx_resources(adapter); err_unlock: - clear_bit(__I40EVF_IN_CRITICAL_TASK, &adapter->crit_section); + clear_bit(__IAVF_IN_CRITICAL_TASK, &adapter->crit_section); return err; } /** - * i40evf_close - Disables a network interface + * iavf_close - Disables a network interface * @netdev: network interface device structure * * Returns 0, this is not allowed to fail @@ -3046,41 +3020,41 @@ err_unlock: * needs to be disabled. All IRQs except vector 0 (reserved for admin queue) * are freed, along with all transmit and receive resources. **/ -static int i40evf_close(struct net_device *netdev) +static int iavf_close(struct net_device *netdev) { - struct i40evf_adapter *adapter = netdev_priv(netdev); + struct iavf_adapter *adapter = netdev_priv(netdev); int status; - if (adapter->state <= __I40EVF_DOWN_PENDING) + if (adapter->state <= __IAVF_DOWN_PENDING) return 0; - while (test_and_set_bit(__I40EVF_IN_CRITICAL_TASK, + while (test_and_set_bit(__IAVF_IN_CRITICAL_TASK, &adapter->crit_section)) usleep_range(500, 1000); - set_bit(__I40E_VSI_DOWN, adapter->vsi.state); + set_bit(__IAVF_VSI_DOWN, adapter->vsi.state); if (CLIENT_ENABLED(adapter)) - adapter->flags |= I40EVF_FLAG_CLIENT_NEEDS_CLOSE; + adapter->flags |= IAVF_FLAG_CLIENT_NEEDS_CLOSE; - i40evf_down(adapter); - adapter->state = __I40EVF_DOWN_PENDING; - i40evf_free_traffic_irqs(adapter); + iavf_down(adapter); + adapter->state = __IAVF_DOWN_PENDING; + iavf_free_traffic_irqs(adapter); - clear_bit(__I40EVF_IN_CRITICAL_TASK, &adapter->crit_section); + clear_bit(__IAVF_IN_CRITICAL_TASK, &adapter->crit_section); /* We explicitly don't free resources here because the hardware is * still active and can DMA into memory. Resources are cleared in - * i40evf_virtchnl_completion() after we get confirmation from the PF + * iavf_virtchnl_completion() after we get confirmation from the PF * driver that the rings have been stopped. * - * Also, we wait for state to transition to __I40EVF_DOWN before - * returning. State change occurs in i40evf_virtchnl_completion() after + * Also, we wait for state to transition to __IAVF_DOWN before + * returning. State change occurs in iavf_virtchnl_completion() after * VF resources are released (which occurs after PF driver processes and * responds to admin queue commands). */ status = wait_event_timeout(adapter->down_waitqueue, - adapter->state == __I40EVF_DOWN, + adapter->state == __IAVF_DOWN, msecs_to_jiffies(200)); if (!status) netdev_warn(netdev, "Device resources not yet released\n"); @@ -3088,37 +3062,37 @@ static int i40evf_close(struct net_device *netdev) } /** - * i40evf_change_mtu - Change the Maximum Transfer Unit + * iavf_change_mtu - Change the Maximum Transfer Unit * @netdev: network interface device structure * @new_mtu: new value for maximum frame size * * Returns 0 on success, negative on failure **/ -static int i40evf_change_mtu(struct net_device *netdev, int new_mtu) +static int iavf_change_mtu(struct net_device *netdev, int new_mtu) { - struct i40evf_adapter *adapter = netdev_priv(netdev); + struct iavf_adapter *adapter = netdev_priv(netdev); netdev->mtu = new_mtu; if (CLIENT_ENABLED(adapter)) { - i40evf_notify_client_l2_params(&adapter->vsi); - adapter->flags |= I40EVF_FLAG_SERVICE_CLIENT_REQUESTED; + iavf_notify_client_l2_params(&adapter->vsi); + adapter->flags |= IAVF_FLAG_SERVICE_CLIENT_REQUESTED; } - adapter->flags |= I40EVF_FLAG_RESET_NEEDED; + adapter->flags |= IAVF_FLAG_RESET_NEEDED; schedule_work(&adapter->reset_task); return 0; } /** - * i40e_set_features - set the netdev feature flags + * iavf_set_features - set the netdev feature flags * @netdev: ptr to the netdev being adjusted * @features: the feature set that the stack is suggesting * Note: expects to be called while under rtnl_lock() **/ -static int i40evf_set_features(struct net_device *netdev, - netdev_features_t features) +static int iavf_set_features(struct net_device *netdev, + netdev_features_t features) { - struct i40evf_adapter *adapter = netdev_priv(netdev); + struct iavf_adapter *adapter = netdev_priv(netdev); /* Don't allow changing VLAN_RX flag when adapter is not capable * of VLAN offload @@ -3129,24 +3103,24 @@ static int i40evf_set_features(struct net_device *netdev, } else if ((netdev->features ^ features) & NETIF_F_HW_VLAN_CTAG_RX) { if (features & NETIF_F_HW_VLAN_CTAG_RX) adapter->aq_required |= - I40EVF_FLAG_AQ_ENABLE_VLAN_STRIPPING; + IAVF_FLAG_AQ_ENABLE_VLAN_STRIPPING; else adapter->aq_required |= - I40EVF_FLAG_AQ_DISABLE_VLAN_STRIPPING; + IAVF_FLAG_AQ_DISABLE_VLAN_STRIPPING; } return 0; } /** - * i40evf_features_check - Validate encapsulated packet conforms to limits + * iavf_features_check - Validate encapsulated packet conforms to limits * @skb: skb buff * @dev: This physical port's netdev * @features: Offload features that the stack believes apply **/ -static netdev_features_t i40evf_features_check(struct sk_buff *skb, - struct net_device *dev, - netdev_features_t features) +static netdev_features_t iavf_features_check(struct sk_buff *skb, + struct net_device *dev, + netdev_features_t features) { size_t len; @@ -3197,16 +3171,16 @@ out_err: } /** - * i40evf_fix_features - fix up the netdev feature bits + * iavf_fix_features - fix up the netdev feature bits * @netdev: our net device * @features: desired feature bits * * Returns fixed-up features bits **/ -static netdev_features_t i40evf_fix_features(struct net_device *netdev, - netdev_features_t features) +static netdev_features_t iavf_fix_features(struct net_device *netdev, + netdev_features_t features) { - struct i40evf_adapter *adapter = netdev_priv(netdev); + struct iavf_adapter *adapter = netdev_priv(netdev); if (!(adapter->vf_res->vf_cap_flags & VIRTCHNL_VF_OFFLOAD_VLAN)) features &= ~(NETIF_F_HW_VLAN_CTAG_TX | @@ -3216,40 +3190,37 @@ static netdev_features_t i40evf_fix_features(struct net_device *netdev, return features; } -static const struct net_device_ops i40evf_netdev_ops = { - .ndo_open = i40evf_open, - .ndo_stop = i40evf_close, - .ndo_start_xmit = i40evf_xmit_frame, - .ndo_set_rx_mode = i40evf_set_rx_mode, +static const struct net_device_ops iavf_netdev_ops = { + .ndo_open = iavf_open, + .ndo_stop = iavf_close, + .ndo_start_xmit = iavf_xmit_frame, + .ndo_set_rx_mode = iavf_set_rx_mode, .ndo_validate_addr = eth_validate_addr, - .ndo_set_mac_address = i40evf_set_mac, - .ndo_change_mtu = i40evf_change_mtu, - .ndo_tx_timeout = i40evf_tx_timeout, - .ndo_vlan_rx_add_vid = i40evf_vlan_rx_add_vid, - .ndo_vlan_rx_kill_vid = i40evf_vlan_rx_kill_vid, - .ndo_features_check = i40evf_features_check, - .ndo_fix_features = i40evf_fix_features, - .ndo_set_features = i40evf_set_features, -#ifdef CONFIG_NET_POLL_CONTROLLER - .ndo_poll_controller = i40evf_netpoll, -#endif - .ndo_setup_tc = i40evf_setup_tc, + .ndo_set_mac_address = iavf_set_mac, + .ndo_change_mtu = iavf_change_mtu, + .ndo_tx_timeout = iavf_tx_timeout, + .ndo_vlan_rx_add_vid = iavf_vlan_rx_add_vid, + .ndo_vlan_rx_kill_vid = iavf_vlan_rx_kill_vid, + .ndo_features_check = iavf_features_check, + .ndo_fix_features = iavf_fix_features, + .ndo_set_features = iavf_set_features, + .ndo_setup_tc = iavf_setup_tc, }; /** - * i40evf_check_reset_complete - check that VF reset is complete + * iavf_check_reset_complete - check that VF reset is complete * @hw: pointer to hw struct * * Returns 0 if device is ready to use, or -EBUSY if it's in reset. **/ -static int i40evf_check_reset_complete(struct i40e_hw *hw) +static int iavf_check_reset_complete(struct iavf_hw *hw) { u32 rstat; int i; for (i = 0; i < 100; i++) { - rstat = rd32(hw, I40E_VFGEN_RSTAT) & - I40E_VFGEN_RSTAT_VFR_STATE_MASK; + rstat = rd32(hw, IAVF_VFGEN_RSTAT) & + IAVF_VFGEN_RSTAT_VFR_STATE_MASK; if ((rstat == VIRTCHNL_VFR_VFACTIVE) || (rstat == VIRTCHNL_VFR_COMPLETED)) return 0; @@ -3259,18 +3230,18 @@ static int i40evf_check_reset_complete(struct i40e_hw *hw) } /** - * i40evf_process_config - Process the config information we got from the PF + * iavf_process_config - Process the config information we got from the PF * @adapter: board private structure * * Verify that we have a valid config struct, and set up our netdev features * and our VSI struct. **/ -int i40evf_process_config(struct i40evf_adapter *adapter) +int iavf_process_config(struct iavf_adapter *adapter) { struct virtchnl_vf_resource *vfres = adapter->vf_res; int i, num_req_queues = adapter->num_req_queues; struct net_device *netdev = adapter->netdev; - struct i40e_vsi *vsi = &adapter->vsi; + struct iavf_vsi *vsi = &adapter->vsi; netdev_features_t hw_enc_features; netdev_features_t hw_features; @@ -3294,9 +3265,9 @@ int i40evf_process_config(struct i40evf_adapter *adapter) "Requested %d queues, but PF only gave us %d.\n", num_req_queues, adapter->vsi_res->num_queue_pairs); - adapter->flags |= I40EVF_FLAG_REINIT_ITR_NEEDED; + adapter->flags |= IAVF_FLAG_REINIT_ITR_NEEDED; adapter->num_req_queues = adapter->vsi_res->num_queue_pairs; - i40evf_schedule_reset(adapter); + iavf_schedule_reset(adapter); return -ENODEV; } adapter->num_req_queues = 0; @@ -3383,22 +3354,22 @@ int i40evf_process_config(struct i40evf_adapter *adapter) adapter->vsi.back = adapter; adapter->vsi.base_vector = 1; - adapter->vsi.work_limit = I40E_DEFAULT_IRQ_WORK; + adapter->vsi.work_limit = IAVF_DEFAULT_IRQ_WORK; vsi->netdev = adapter->netdev; vsi->qs_handle = adapter->vsi_res->qset_handle; if (vfres->vf_cap_flags & VIRTCHNL_VF_OFFLOAD_RSS_PF) { adapter->rss_key_size = vfres->rss_key_size; adapter->rss_lut_size = vfres->rss_lut_size; } else { - adapter->rss_key_size = I40EVF_HKEY_ARRAY_SIZE; - adapter->rss_lut_size = I40EVF_HLUT_ARRAY_SIZE; + adapter->rss_key_size = IAVF_HKEY_ARRAY_SIZE; + adapter->rss_lut_size = IAVF_HLUT_ARRAY_SIZE; } return 0; } /** - * i40evf_init_task - worker thread to perform delayed initialization + * iavf_init_task - worker thread to perform delayed initialization * @work: pointer to work_struct containing our data * * This task completes the work that was begun in probe. Due to the nature @@ -3409,65 +3380,65 @@ int i40evf_process_config(struct i40evf_adapter *adapter) * communications with the PF driver and set up our netdev, the watchdog * takes over. **/ -static void i40evf_init_task(struct work_struct *work) +static void iavf_init_task(struct work_struct *work) { - struct i40evf_adapter *adapter = container_of(work, - struct i40evf_adapter, + struct iavf_adapter *adapter = container_of(work, + struct iavf_adapter, init_task.work); struct net_device *netdev = adapter->netdev; - struct i40e_hw *hw = &adapter->hw; + struct iavf_hw *hw = &adapter->hw; struct pci_dev *pdev = adapter->pdev; int err, bufsz; switch (adapter->state) { - case __I40EVF_STARTUP: + case __IAVF_STARTUP: /* driver loaded, probe complete */ - adapter->flags &= ~I40EVF_FLAG_PF_COMMS_FAILED; - adapter->flags &= ~I40EVF_FLAG_RESET_PENDING; - err = i40e_set_mac_type(hw); + adapter->flags &= ~IAVF_FLAG_PF_COMMS_FAILED; + adapter->flags &= ~IAVF_FLAG_RESET_PENDING; + err = iavf_set_mac_type(hw); if (err) { dev_err(&pdev->dev, "Failed to set MAC type (%d)\n", err); goto err; } - err = i40evf_check_reset_complete(hw); + err = iavf_check_reset_complete(hw); if (err) { dev_info(&pdev->dev, "Device is still in reset (%d), retrying\n", err); goto err; } - hw->aq.num_arq_entries = I40EVF_AQ_LEN; - hw->aq.num_asq_entries = I40EVF_AQ_LEN; - hw->aq.arq_buf_size = I40EVF_MAX_AQ_BUF_SIZE; - hw->aq.asq_buf_size = I40EVF_MAX_AQ_BUF_SIZE; + hw->aq.num_arq_entries = IAVF_AQ_LEN; + hw->aq.num_asq_entries = IAVF_AQ_LEN; + hw->aq.arq_buf_size = IAVF_MAX_AQ_BUF_SIZE; + hw->aq.asq_buf_size = IAVF_MAX_AQ_BUF_SIZE; - err = i40evf_init_adminq(hw); + err = iavf_init_adminq(hw); if (err) { dev_err(&pdev->dev, "Failed to init Admin Queue (%d)\n", err); goto err; } - err = i40evf_send_api_ver(adapter); + err = iavf_send_api_ver(adapter); if (err) { dev_err(&pdev->dev, "Unable to send to PF (%d)\n", err); - i40evf_shutdown_adminq(hw); + iavf_shutdown_adminq(hw); goto err; } - adapter->state = __I40EVF_INIT_VERSION_CHECK; + adapter->state = __IAVF_INIT_VERSION_CHECK; goto restart; - case __I40EVF_INIT_VERSION_CHECK: - if (!i40evf_asq_done(hw)) { + case __IAVF_INIT_VERSION_CHECK: + if (!iavf_asq_done(hw)) { dev_err(&pdev->dev, "Admin queue command never completed\n"); - i40evf_shutdown_adminq(hw); - adapter->state = __I40EVF_STARTUP; + iavf_shutdown_adminq(hw); + adapter->state = __IAVF_STARTUP; goto err; } /* aq msg sent, awaiting reply */ - err = i40evf_verify_api_ver(adapter); + err = iavf_verify_api_ver(adapter); if (err) { if (err == I40E_ERR_ADMIN_QUEUE_NO_WORK) - err = i40evf_send_api_ver(adapter); + err = iavf_send_api_ver(adapter); else dev_err(&pdev->dev, "Unsupported PF API version %d.%d, expected %d.%d\n", adapter->pf_version.major, @@ -3476,34 +3447,34 @@ static void i40evf_init_task(struct work_struct *work) VIRTCHNL_VERSION_MINOR); goto err; } - err = i40evf_send_vf_config_msg(adapter); + err = iavf_send_vf_config_msg(adapter); if (err) { dev_err(&pdev->dev, "Unable to send config request (%d)\n", err); goto err; } - adapter->state = __I40EVF_INIT_GET_RESOURCES; + adapter->state = __IAVF_INIT_GET_RESOURCES; goto restart; - case __I40EVF_INIT_GET_RESOURCES: + case __IAVF_INIT_GET_RESOURCES: /* aq msg sent, awaiting reply */ if (!adapter->vf_res) { bufsz = sizeof(struct virtchnl_vf_resource) + - (I40E_MAX_VF_VSI * + (IAVF_MAX_VF_VSI * sizeof(struct virtchnl_vsi_resource)); adapter->vf_res = kzalloc(bufsz, GFP_KERNEL); if (!adapter->vf_res) goto err; } - err = i40evf_get_vf_config(adapter); + err = iavf_get_vf_config(adapter); if (err == I40E_ERR_ADMIN_QUEUE_NO_WORK) { - err = i40evf_send_vf_config_msg(adapter); + err = iavf_send_vf_config_msg(adapter); goto err; } else if (err == I40E_ERR_PARAM) { /* We only get ERR_PARAM if the device is in a very bad * state or if we've been disabled for previous bad * behavior. Either way, we're done now. */ - i40evf_shutdown_adminq(hw); + iavf_shutdown_adminq(hw); dev_err(&pdev->dev, "Unable to get VF config due to PF error condition, not retrying\n"); return; } @@ -3512,25 +3483,25 @@ static void i40evf_init_task(struct work_struct *work) err); goto err_alloc; } - adapter->state = __I40EVF_INIT_SW; + adapter->state = __IAVF_INIT_SW; break; default: goto err_alloc; } - if (i40evf_process_config(adapter)) + if (iavf_process_config(adapter)) goto err_alloc; adapter->current_op = VIRTCHNL_OP_UNKNOWN; - adapter->flags |= I40EVF_FLAG_RX_CSUM_ENABLED; + adapter->flags |= IAVF_FLAG_RX_CSUM_ENABLED; - netdev->netdev_ops = &i40evf_netdev_ops; - i40evf_set_ethtool_ops(netdev); + netdev->netdev_ops = &iavf_netdev_ops; + iavf_set_ethtool_ops(netdev); netdev->watchdog_timeo = 5 * HZ; /* MTU range: 68 - 9710 */ netdev->min_mtu = ETH_MIN_MTU; - netdev->max_mtu = I40E_MAX_RXBUFFER - I40E_PACKET_HDR_PAD; + netdev->max_mtu = IAVF_MAX_RXBUFFER - IAVF_PACKET_HDR_PAD; if (!is_valid_ether_addr(adapter->hw.mac.addr)) { dev_info(&pdev->dev, "Invalid MAC address %pM, using random\n", @@ -3538,25 +3509,25 @@ static void i40evf_init_task(struct work_struct *work) eth_hw_addr_random(netdev); ether_addr_copy(adapter->hw.mac.addr, netdev->dev_addr); } else { - adapter->flags |= I40EVF_FLAG_ADDR_SET_BY_PF; + adapter->flags |= IAVF_FLAG_ADDR_SET_BY_PF; ether_addr_copy(netdev->dev_addr, adapter->hw.mac.addr); ether_addr_copy(netdev->perm_addr, adapter->hw.mac.addr); } - timer_setup(&adapter->watchdog_timer, i40evf_watchdog_timer, 0); + timer_setup(&adapter->watchdog_timer, iavf_watchdog_timer, 0); mod_timer(&adapter->watchdog_timer, jiffies + 1); - adapter->tx_desc_count = I40EVF_DEFAULT_TXD; - adapter->rx_desc_count = I40EVF_DEFAULT_RXD; - err = i40evf_init_interrupt_scheme(adapter); + adapter->tx_desc_count = IAVF_DEFAULT_TXD; + adapter->rx_desc_count = IAVF_DEFAULT_RXD; + err = iavf_init_interrupt_scheme(adapter); if (err) goto err_sw_init; - i40evf_map_rings_to_vectors(adapter); + iavf_map_rings_to_vectors(adapter); if (adapter->vf_res->vf_cap_flags & VIRTCHNL_VF_OFFLOAD_WB_ON_ITR) - adapter->flags |= I40EVF_FLAG_WB_ON_ITR_CAPABLE; + adapter->flags |= IAVF_FLAG_WB_ON_ITR_CAPABLE; - err = i40evf_request_misc_irq(adapter); + err = iavf_request_misc_irq(adapter); if (err) goto err_sw_init; @@ -3573,7 +3544,7 @@ static void i40evf_init_task(struct work_struct *work) netif_tx_stop_all_queues(netdev); if (CLIENT_ALLOWED(adapter)) { - err = i40evf_lan_add_device(adapter); + err = iavf_lan_add_device(adapter); if (err) dev_info(&pdev->dev, "Failed to add VF to client API service list: %d\n", err); @@ -3583,9 +3554,9 @@ static void i40evf_init_task(struct work_struct *work) if (netdev->features & NETIF_F_GRO) dev_info(&pdev->dev, "GRO is enabled\n"); - adapter->state = __I40EVF_DOWN; - set_bit(__I40E_VSI_DOWN, adapter->vsi.state); - i40evf_misc_irq_enable(adapter); + adapter->state = __IAVF_DOWN; + set_bit(__IAVF_VSI_DOWN, adapter->vsi.state); + iavf_misc_irq_enable(adapter); wake_up(&adapter->down_waitqueue); adapter->rss_key = kzalloc(adapter->rss_key_size, GFP_KERNEL); @@ -3594,31 +3565,31 @@ static void i40evf_init_task(struct work_struct *work) goto err_mem; if (RSS_AQ(adapter)) { - adapter->aq_required |= I40EVF_FLAG_AQ_CONFIGURE_RSS; + adapter->aq_required |= IAVF_FLAG_AQ_CONFIGURE_RSS; mod_timer_pending(&adapter->watchdog_timer, jiffies + 1); } else { - i40evf_init_rss(adapter); + iavf_init_rss(adapter); } return; restart: schedule_delayed_work(&adapter->init_task, msecs_to_jiffies(30)); return; err_mem: - i40evf_free_rss(adapter); + iavf_free_rss(adapter); err_register: - i40evf_free_misc_irq(adapter); + iavf_free_misc_irq(adapter); err_sw_init: - i40evf_reset_interrupt_capability(adapter); + iavf_reset_interrupt_capability(adapter); err_alloc: kfree(adapter->vf_res); adapter->vf_res = NULL; err: /* Things went into the weeds, so try again later */ - if (++adapter->aq_wait_count > I40EVF_AQ_MAX_ERR) { + if (++adapter->aq_wait_count > IAVF_AQ_MAX_ERR) { dev_err(&pdev->dev, "Failed to communicate with PF; waiting before retry\n"); - adapter->flags |= I40EVF_FLAG_PF_COMMS_FAILED; - i40evf_shutdown_adminq(hw); - adapter->state = __I40EVF_STARTUP; + adapter->flags |= IAVF_FLAG_PF_COMMS_FAILED; + iavf_shutdown_adminq(hw); + adapter->state = __IAVF_STARTUP; schedule_delayed_work(&adapter->init_task, HZ * 5); return; } @@ -3626,21 +3597,21 @@ err: } /** - * i40evf_shutdown - Shutdown the device in preparation for a reboot + * iavf_shutdown - Shutdown the device in preparation for a reboot * @pdev: pci device structure **/ -static void i40evf_shutdown(struct pci_dev *pdev) +static void iavf_shutdown(struct pci_dev *pdev) { struct net_device *netdev = pci_get_drvdata(pdev); - struct i40evf_adapter *adapter = netdev_priv(netdev); + struct iavf_adapter *adapter = netdev_priv(netdev); netif_device_detach(netdev); if (netif_running(netdev)) - i40evf_close(netdev); + iavf_close(netdev); /* Prevent the watchdog from running. */ - adapter->state = __I40EVF_REMOVE; + adapter->state = __IAVF_REMOVE; adapter->aq_required = 0; #ifdef CONFIG_PM @@ -3651,21 +3622,21 @@ static void i40evf_shutdown(struct pci_dev *pdev) } /** - * i40evf_probe - Device Initialization Routine + * iavf_probe - Device Initialization Routine * @pdev: PCI device information struct - * @ent: entry in i40evf_pci_tbl + * @ent: entry in iavf_pci_tbl * * Returns 0 on success, negative on failure * - * i40evf_probe initializes an adapter identified by a pci_dev structure. + * iavf_probe initializes an adapter identified by a pci_dev structure. * The OS initialization, configuring of the adapter private structure, * and a hardware reset occur. **/ -static int i40evf_probe(struct pci_dev *pdev, const struct pci_device_id *ent) +static int iavf_probe(struct pci_dev *pdev, const struct pci_device_id *ent) { struct net_device *netdev; - struct i40evf_adapter *adapter = NULL; - struct i40e_hw *hw = NULL; + struct iavf_adapter *adapter = NULL; + struct iavf_hw *hw = NULL; int err; err = pci_enable_device(pdev); @@ -3682,7 +3653,7 @@ static int i40evf_probe(struct pci_dev *pdev, const struct pci_device_id *ent) } } - err = pci_request_regions(pdev, i40evf_driver_name); + err = pci_request_regions(pdev, iavf_driver_name); if (err) { dev_err(&pdev->dev, "pci_request_regions failed 0x%x\n", err); @@ -3693,8 +3664,8 @@ static int i40evf_probe(struct pci_dev *pdev, const struct pci_device_id *ent) pci_set_master(pdev); - netdev = alloc_etherdev_mq(sizeof(struct i40evf_adapter), - I40EVF_MAX_REQ_QUEUES); + netdev = alloc_etherdev_mq(sizeof(struct iavf_adapter), + IAVF_MAX_REQ_QUEUES); if (!netdev) { err = -ENOMEM; goto err_alloc_etherdev; @@ -3712,7 +3683,7 @@ static int i40evf_probe(struct pci_dev *pdev, const struct pci_device_id *ent) hw->back = adapter; adapter->msg_enable = BIT(DEFAULT_DEBUG_LEVEL_SHIFT) - 1; - adapter->state = __I40EVF_STARTUP; + adapter->state = __IAVF_STARTUP; /* Call save state here because it relies on the adapter struct. */ pci_save_state(pdev); @@ -3745,11 +3716,11 @@ static int i40evf_probe(struct pci_dev *pdev, const struct pci_device_id *ent) INIT_LIST_HEAD(&adapter->vlan_filter_list); INIT_LIST_HEAD(&adapter->cloud_filter_list); - INIT_WORK(&adapter->reset_task, i40evf_reset_task); - INIT_WORK(&adapter->adminq_task, i40evf_adminq_task); - INIT_WORK(&adapter->watchdog_task, i40evf_watchdog_task); - INIT_DELAYED_WORK(&adapter->client_task, i40evf_client_task); - INIT_DELAYED_WORK(&adapter->init_task, i40evf_init_task); + INIT_WORK(&adapter->reset_task, iavf_reset_task); + INIT_WORK(&adapter->adminq_task, iavf_adminq_task); + INIT_WORK(&adapter->watchdog_task, iavf_watchdog_task); + INIT_DELAYED_WORK(&adapter->client_task, iavf_client_task); + INIT_DELAYED_WORK(&adapter->init_task, iavf_init_task); schedule_delayed_work(&adapter->init_task, msecs_to_jiffies(5 * (pdev->devfn & 0x07))); @@ -3770,33 +3741,33 @@ err_dma: #ifdef CONFIG_PM /** - * i40evf_suspend - Power management suspend routine + * iavf_suspend - Power management suspend routine * @pdev: PCI device information struct * @state: unused * * Called when the system (VM) is entering sleep/suspend. **/ -static int i40evf_suspend(struct pci_dev *pdev, pm_message_t state) +static int iavf_suspend(struct pci_dev *pdev, pm_message_t state) { struct net_device *netdev = pci_get_drvdata(pdev); - struct i40evf_adapter *adapter = netdev_priv(netdev); + struct iavf_adapter *adapter = netdev_priv(netdev); int retval = 0; netif_device_detach(netdev); - while (test_and_set_bit(__I40EVF_IN_CRITICAL_TASK, + while (test_and_set_bit(__IAVF_IN_CRITICAL_TASK, &adapter->crit_section)) usleep_range(500, 1000); if (netif_running(netdev)) { rtnl_lock(); - i40evf_down(adapter); + iavf_down(adapter); rtnl_unlock(); } - i40evf_free_misc_irq(adapter); - i40evf_reset_interrupt_capability(adapter); + iavf_free_misc_irq(adapter); + iavf_reset_interrupt_capability(adapter); - clear_bit(__I40EVF_IN_CRITICAL_TASK, &adapter->crit_section); + clear_bit(__IAVF_IN_CRITICAL_TASK, &adapter->crit_section); retval = pci_save_state(pdev); if (retval) @@ -3808,14 +3779,14 @@ static int i40evf_suspend(struct pci_dev *pdev, pm_message_t state) } /** - * i40evf_resume - Power management resume routine + * iavf_resume - Power management resume routine * @pdev: PCI device information struct * * Called when the system (VM) is resumed from sleep/suspend. **/ -static int i40evf_resume(struct pci_dev *pdev) +static int iavf_resume(struct pci_dev *pdev) { - struct i40evf_adapter *adapter = pci_get_drvdata(pdev); + struct iavf_adapter *adapter = pci_get_drvdata(pdev); struct net_device *netdev = adapter->netdev; u32 err; @@ -3834,13 +3805,13 @@ static int i40evf_resume(struct pci_dev *pdev) pci_set_master(pdev); rtnl_lock(); - err = i40evf_set_interrupt_capability(adapter); + err = iavf_set_interrupt_capability(adapter); if (err) { rtnl_unlock(); dev_err(&pdev->dev, "Cannot enable MSI-X interrupts.\n"); return err; } - err = i40evf_request_misc_irq(adapter); + err = iavf_request_misc_irq(adapter); rtnl_unlock(); if (err) { dev_err(&pdev->dev, "Cannot get interrupt vector.\n"); @@ -3856,25 +3827,25 @@ static int i40evf_resume(struct pci_dev *pdev) #endif /* CONFIG_PM */ /** - * i40evf_remove - Device Removal Routine + * iavf_remove - Device Removal Routine * @pdev: PCI device information struct * - * i40evf_remove is called by the PCI subsystem to alert the driver + * iavf_remove is called by the PCI subsystem to alert the driver * that it should release a PCI device. The could be caused by a * Hot-Plug event, or because the driver is going to be removed from * memory. **/ -static void i40evf_remove(struct pci_dev *pdev) +static void iavf_remove(struct pci_dev *pdev) { struct net_device *netdev = pci_get_drvdata(pdev); - struct i40evf_adapter *adapter = netdev_priv(netdev); - struct i40evf_vlan_filter *vlf, *vlftmp; - struct i40evf_mac_filter *f, *ftmp; - struct i40evf_cloud_filter *cf, *cftmp; - struct i40e_hw *hw = &adapter->hw; + struct iavf_adapter *adapter = netdev_priv(netdev); + struct iavf_vlan_filter *vlf, *vlftmp; + struct iavf_mac_filter *f, *ftmp; + struct iavf_cloud_filter *cf, *cftmp; + struct iavf_hw *hw = &adapter->hw; int err; /* Indicate we are in remove and not to run reset_task */ - set_bit(__I40EVF_IN_REMOVE_TASK, &adapter->crit_section); + set_bit(__IAVF_IN_REMOVE_TASK, &adapter->crit_section); cancel_delayed_work_sync(&adapter->init_task); cancel_work_sync(&adapter->reset_task); cancel_delayed_work_sync(&adapter->client_task); @@ -3883,39 +3854,39 @@ static void i40evf_remove(struct pci_dev *pdev) adapter->netdev_registered = false; } if (CLIENT_ALLOWED(adapter)) { - err = i40evf_lan_del_device(adapter); + err = iavf_lan_del_device(adapter); if (err) dev_warn(&pdev->dev, "Failed to delete client device: %d\n", err); } /* Shut down all the garbage mashers on the detention level */ - adapter->state = __I40EVF_REMOVE; + adapter->state = __IAVF_REMOVE; adapter->aq_required = 0; - adapter->flags &= ~I40EVF_FLAG_REINIT_ITR_NEEDED; - i40evf_request_reset(adapter); + adapter->flags &= ~IAVF_FLAG_REINIT_ITR_NEEDED; + iavf_request_reset(adapter); msleep(50); /* If the FW isn't responding, kick it once, but only once. */ - if (!i40evf_asq_done(hw)) { - i40evf_request_reset(adapter); + if (!iavf_asq_done(hw)) { + iavf_request_reset(adapter); msleep(50); } - i40evf_free_all_tx_resources(adapter); - i40evf_free_all_rx_resources(adapter); - i40evf_misc_irq_disable(adapter); - i40evf_free_misc_irq(adapter); - i40evf_reset_interrupt_capability(adapter); - i40evf_free_q_vectors(adapter); + iavf_free_all_tx_resources(adapter); + iavf_free_all_rx_resources(adapter); + iavf_misc_irq_disable(adapter); + iavf_free_misc_irq(adapter); + iavf_reset_interrupt_capability(adapter); + iavf_free_q_vectors(adapter); if (adapter->watchdog_timer.function) del_timer_sync(&adapter->watchdog_timer); cancel_work_sync(&adapter->adminq_task); - i40evf_free_rss(adapter); + iavf_free_rss(adapter); if (hw->aq.asq.count) - i40evf_shutdown_adminq(hw); + iavf_shutdown_adminq(hw); /* destroy the locks only once, here */ mutex_destroy(&hw->aq.arq_mutex); @@ -3923,9 +3894,9 @@ static void i40evf_remove(struct pci_dev *pdev) iounmap(hw->hw_addr); pci_release_regions(pdev); - i40evf_free_all_tx_resources(adapter); - i40evf_free_all_rx_resources(adapter); - i40evf_free_queues(adapter); + iavf_free_all_tx_resources(adapter); + iavf_free_all_rx_resources(adapter); + iavf_free_queues(adapter); kfree(adapter->vf_res); spin_lock_bh(&adapter->mac_vlan_list_lock); /* If we got removed before an up/down sequence, we've got a filter @@ -3957,57 +3928,57 @@ static void i40evf_remove(struct pci_dev *pdev) pci_disable_device(pdev); } -static struct pci_driver i40evf_driver = { - .name = i40evf_driver_name, - .id_table = i40evf_pci_tbl, - .probe = i40evf_probe, - .remove = i40evf_remove, +static struct pci_driver iavf_driver = { + .name = iavf_driver_name, + .id_table = iavf_pci_tbl, + .probe = iavf_probe, + .remove = iavf_remove, #ifdef CONFIG_PM - .suspend = i40evf_suspend, - .resume = i40evf_resume, + .suspend = iavf_suspend, + .resume = iavf_resume, #endif - .shutdown = i40evf_shutdown, + .shutdown = iavf_shutdown, }; /** - * i40e_init_module - Driver Registration Routine + * iavf_init_module - Driver Registration Routine * - * i40e_init_module is the first routine called when the driver is + * iavf_init_module is the first routine called when the driver is * loaded. All it does is register with the PCI subsystem. **/ -static int __init i40evf_init_module(void) +static int __init iavf_init_module(void) { int ret; - pr_info("i40evf: %s - version %s\n", i40evf_driver_string, - i40evf_driver_version); + pr_info("iavf: %s - version %s\n", iavf_driver_string, + iavf_driver_version); - pr_info("%s\n", i40evf_copyright); + pr_info("%s\n", iavf_copyright); - i40evf_wq = alloc_workqueue("%s", WQ_UNBOUND | WQ_MEM_RECLAIM, 1, - i40evf_driver_name); - if (!i40evf_wq) { - pr_err("%s: Failed to create workqueue\n", i40evf_driver_name); + iavf_wq = alloc_workqueue("%s", WQ_UNBOUND | WQ_MEM_RECLAIM, 1, + iavf_driver_name); + if (!iavf_wq) { + pr_err("%s: Failed to create workqueue\n", iavf_driver_name); return -ENOMEM; } - ret = pci_register_driver(&i40evf_driver); + ret = pci_register_driver(&iavf_driver); return ret; } -module_init(i40evf_init_module); +module_init(iavf_init_module); /** - * i40e_exit_module - Driver Exit Cleanup Routine + * iavf_exit_module - Driver Exit Cleanup Routine * - * i40e_exit_module is called just before the driver is removed + * iavf_exit_module is called just before the driver is removed * from memory. **/ -static void __exit i40evf_exit_module(void) +static void __exit iavf_exit_module(void) { - pci_unregister_driver(&i40evf_driver); - destroy_workqueue(i40evf_wq); + pci_unregister_driver(&iavf_driver); + destroy_workqueue(iavf_wq); } -module_exit(i40evf_exit_module); +module_exit(iavf_exit_module); -/* i40evf_main.c */ +/* iavf_main.c */ diff --git a/drivers/net/ethernet/intel/i40evf/i40e_osdep.h b/drivers/net/ethernet/intel/iavf/iavf_osdep.h index 3ddddb46455b..e6e0b0328706 100644 --- a/drivers/net/ethernet/intel/i40evf/i40e_osdep.h +++ b/drivers/net/ethernet/intel/iavf/iavf_osdep.h @@ -1,8 +1,8 @@ /* SPDX-License-Identifier: GPL-2.0 */ /* Copyright(c) 2013 - 2018 Intel Corporation. */ -#ifndef _I40E_OSDEP_H_ -#define _I40E_OSDEP_H_ +#ifndef _IAVF_OSDEP_H_ +#define _IAVF_OSDEP_H_ #include <linux/types.h> #include <linux/if_ether.h> @@ -24,29 +24,29 @@ #define wr64(a, reg, value) writeq((value), ((a)->hw_addr + (reg))) #define rd64(a, reg) readq((a)->hw_addr + (reg)) -#define i40e_flush(a) readl((a)->hw_addr + I40E_VFGEN_RSTAT) +#define iavf_flush(a) readl((a)->hw_addr + IAVF_VFGEN_RSTAT) /* memory allocation tracking */ -struct i40e_dma_mem { +struct iavf_dma_mem { void *va; dma_addr_t pa; u32 size; }; -#define i40e_allocate_dma_mem(h, m, unused, s, a) \ - i40evf_allocate_dma_mem_d(h, m, s, a) -#define i40e_free_dma_mem(h, m) i40evf_free_dma_mem_d(h, m) +#define iavf_allocate_dma_mem(h, m, unused, s, a) \ + iavf_allocate_dma_mem_d(h, m, s, a) +#define iavf_free_dma_mem(h, m) iavf_free_dma_mem_d(h, m) -struct i40e_virt_mem { +struct iavf_virt_mem { void *va; u32 size; }; -#define i40e_allocate_virt_mem(h, m, s) i40evf_allocate_virt_mem_d(h, m, s) -#define i40e_free_virt_mem(h, m) i40evf_free_virt_mem_d(h, m) +#define iavf_allocate_virt_mem(h, m, s) iavf_allocate_virt_mem_d(h, m, s) +#define iavf_free_virt_mem(h, m) iavf_free_virt_mem_d(h, m) -#define i40e_debug(h, m, s, ...) i40evf_debug_d(h, m, s, ##__VA_ARGS__) -extern void i40evf_debug_d(void *hw, u32 mask, char *fmt_str, ...) +#define iavf_debug(h, m, s, ...) iavf_debug_d(h, m, s, ##__VA_ARGS__) +extern void iavf_debug_d(void *hw, u32 mask, char *fmt_str, ...) __attribute__ ((format(gnu_printf, 3, 4))); -typedef enum i40e_status_code i40e_status; -#endif /* _I40E_OSDEP_H_ */ +typedef enum iavf_status_code iavf_status; +#endif /* _IAVF_OSDEP_H_ */ diff --git a/drivers/net/ethernet/intel/iavf/iavf_prototype.h b/drivers/net/ethernet/intel/iavf/iavf_prototype.h new file mode 100644 index 000000000000..d6685103af39 --- /dev/null +++ b/drivers/net/ethernet/intel/iavf/iavf_prototype.h @@ -0,0 +1,67 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright(c) 2013 - 2018 Intel Corporation. */ + +#ifndef _IAVF_PROTOTYPE_H_ +#define _IAVF_PROTOTYPE_H_ + +#include "iavf_type.h" +#include "iavf_alloc.h" +#include <linux/avf/virtchnl.h> + +/* Prototypes for shared code functions that are not in + * the standard function pointer structures. These are + * mostly because they are needed even before the init + * has happened and will assist in the early SW and FW + * setup. + */ + +/* adminq functions */ +iavf_status iavf_init_adminq(struct iavf_hw *hw); +iavf_status iavf_shutdown_adminq(struct iavf_hw *hw); +void i40e_adminq_init_ring_data(struct iavf_hw *hw); +iavf_status iavf_clean_arq_element(struct iavf_hw *hw, + struct i40e_arq_event_info *e, + u16 *events_pending); +iavf_status iavf_asq_send_command(struct iavf_hw *hw, struct i40e_aq_desc *desc, + void *buff, /* can be NULL */ + u16 buff_size, + struct i40e_asq_cmd_details *cmd_details); +bool iavf_asq_done(struct iavf_hw *hw); + +/* debug function for adminq */ +void iavf_debug_aq(struct iavf_hw *hw, enum iavf_debug_mask mask, + void *desc, void *buffer, u16 buf_len); + +void i40e_idle_aq(struct iavf_hw *hw); +void iavf_resume_aq(struct iavf_hw *hw); +bool iavf_check_asq_alive(struct iavf_hw *hw); +iavf_status iavf_aq_queue_shutdown(struct iavf_hw *hw, bool unloading); +const char *iavf_aq_str(struct iavf_hw *hw, enum i40e_admin_queue_err aq_err); +const char *iavf_stat_str(struct iavf_hw *hw, iavf_status stat_err); + +iavf_status iavf_aq_get_rss_lut(struct iavf_hw *hw, u16 seid, + bool pf_lut, u8 *lut, u16 lut_size); +iavf_status iavf_aq_set_rss_lut(struct iavf_hw *hw, u16 seid, + bool pf_lut, u8 *lut, u16 lut_size); +iavf_status iavf_aq_get_rss_key(struct iavf_hw *hw, u16 seid, + struct i40e_aqc_get_set_rss_key_data *key); +iavf_status iavf_aq_set_rss_key(struct iavf_hw *hw, u16 seid, + struct i40e_aqc_get_set_rss_key_data *key); + +iavf_status iavf_set_mac_type(struct iavf_hw *hw); + +extern struct iavf_rx_ptype_decoded iavf_ptype_lookup[]; + +static inline struct iavf_rx_ptype_decoded decode_rx_desc_ptype(u8 ptype) +{ + return iavf_ptype_lookup[ptype]; +} + +void iavf_vf_parse_hw_config(struct iavf_hw *hw, + struct virtchnl_vf_resource *msg); +iavf_status iavf_vf_reset(struct iavf_hw *hw); +iavf_status iavf_aq_send_msg_to_pf(struct iavf_hw *hw, + enum virtchnl_ops v_opcode, + iavf_status v_retval, u8 *msg, u16 msglen, + struct i40e_asq_cmd_details *cmd_details); +#endif /* _IAVF_PROTOTYPE_H_ */ diff --git a/drivers/net/ethernet/intel/iavf/iavf_register.h b/drivers/net/ethernet/intel/iavf/iavf_register.h new file mode 100644 index 000000000000..bf793332fc9d --- /dev/null +++ b/drivers/net/ethernet/intel/iavf/iavf_register.h @@ -0,0 +1,68 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright(c) 2013 - 2018 Intel Corporation. */ + +#ifndef _IAVF_REGISTER_H_ +#define _IAVF_REGISTER_H_ + +#define IAVF_VF_ARQBAH1 0x00006000 /* Reset: EMPR */ +#define IAVF_VF_ARQBAL1 0x00006C00 /* Reset: EMPR */ +#define IAVF_VF_ARQH1 0x00007400 /* Reset: EMPR */ +#define IAVF_VF_ARQH1_ARQH_SHIFT 0 +#define IAVF_VF_ARQH1_ARQH_MASK IAVF_MASK(0x3FF, IAVF_VF_ARQH1_ARQH_SHIFT) +#define IAVF_VF_ARQLEN1 0x00008000 /* Reset: EMPR */ +#define IAVF_VF_ARQLEN1_ARQVFE_SHIFT 28 +#define IAVF_VF_ARQLEN1_ARQVFE_MASK IAVF_MASK(0x1, IAVF_VF_ARQLEN1_ARQVFE_SHIFT) +#define IAVF_VF_ARQLEN1_ARQOVFL_SHIFT 29 +#define IAVF_VF_ARQLEN1_ARQOVFL_MASK IAVF_MASK(0x1, IAVF_VF_ARQLEN1_ARQOVFL_SHIFT) +#define IAVF_VF_ARQLEN1_ARQCRIT_SHIFT 30 +#define IAVF_VF_ARQLEN1_ARQCRIT_MASK IAVF_MASK(0x1, IAVF_VF_ARQLEN1_ARQCRIT_SHIFT) +#define IAVF_VF_ARQLEN1_ARQENABLE_SHIFT 31 +#define IAVF_VF_ARQLEN1_ARQENABLE_MASK IAVF_MASK(0x1, IAVF_VF_ARQLEN1_ARQENABLE_SHIFT) +#define IAVF_VF_ARQT1 0x00007000 /* Reset: EMPR */ +#define IAVF_VF_ATQBAH1 0x00007800 /* Reset: EMPR */ +#define IAVF_VF_ATQBAL1 0x00007C00 /* Reset: EMPR */ +#define IAVF_VF_ATQH1 0x00006400 /* Reset: EMPR */ +#define IAVF_VF_ATQLEN1 0x00006800 /* Reset: EMPR */ +#define IAVF_VF_ATQLEN1_ATQVFE_SHIFT 28 +#define IAVF_VF_ATQLEN1_ATQVFE_MASK IAVF_MASK(0x1, IAVF_VF_ATQLEN1_ATQVFE_SHIFT) +#define IAVF_VF_ATQLEN1_ATQOVFL_SHIFT 29 +#define IAVF_VF_ATQLEN1_ATQOVFL_MASK IAVF_MASK(0x1, IAVF_VF_ATQLEN1_ATQOVFL_SHIFT) +#define IAVF_VF_ATQLEN1_ATQCRIT_SHIFT 30 +#define IAVF_VF_ATQLEN1_ATQCRIT_MASK IAVF_MASK(0x1, IAVF_VF_ATQLEN1_ATQCRIT_SHIFT) +#define IAVF_VF_ATQLEN1_ATQENABLE_SHIFT 31 +#define IAVF_VF_ATQLEN1_ATQENABLE_MASK IAVF_MASK(0x1, IAVF_VF_ATQLEN1_ATQENABLE_SHIFT) +#define IAVF_VF_ATQT1 0x00008400 /* Reset: EMPR */ +#define IAVF_VFGEN_RSTAT 0x00008800 /* Reset: VFR */ +#define IAVF_VFGEN_RSTAT_VFR_STATE_SHIFT 0 +#define IAVF_VFGEN_RSTAT_VFR_STATE_MASK IAVF_MASK(0x3, IAVF_VFGEN_RSTAT_VFR_STATE_SHIFT) +#define IAVF_VFINT_DYN_CTL01 0x00005C00 /* Reset: VFR */ +#define IAVF_VFINT_DYN_CTL01_INTENA_SHIFT 0 +#define IAVF_VFINT_DYN_CTL01_INTENA_MASK IAVF_MASK(0x1, IAVF_VFINT_DYN_CTL01_INTENA_SHIFT) +#define IAVF_VFINT_DYN_CTL01_ITR_INDX_SHIFT 3 +#define IAVF_VFINT_DYN_CTL01_ITR_INDX_MASK IAVF_MASK(0x3, IAVF_VFINT_DYN_CTL01_ITR_INDX_SHIFT) +#define IAVF_VFINT_DYN_CTLN1(_INTVF) (0x00003800 + ((_INTVF) * 4)) /* _i=0...15 */ /* Reset: VFR */ +#define IAVF_VFINT_DYN_CTLN1_INTENA_SHIFT 0 +#define IAVF_VFINT_DYN_CTLN1_INTENA_MASK IAVF_MASK(0x1, IAVF_VFINT_DYN_CTLN1_INTENA_SHIFT) +#define IAVF_VFINT_DYN_CTLN1_SWINT_TRIG_SHIFT 2 +#define IAVF_VFINT_DYN_CTLN1_SWINT_TRIG_MASK IAVF_MASK(0x1, IAVF_VFINT_DYN_CTLN1_SWINT_TRIG_SHIFT) +#define IAVF_VFINT_DYN_CTLN1_ITR_INDX_SHIFT 3 +#define IAVF_VFINT_DYN_CTLN1_ITR_INDX_MASK IAVF_MASK(0x3, IAVF_VFINT_DYN_CTLN1_ITR_INDX_SHIFT) +#define IAVF_VFINT_DYN_CTLN1_INTERVAL_SHIFT 5 +#define IAVF_VFINT_DYN_CTLN1_SW_ITR_INDX_ENA_SHIFT 24 +#define IAVF_VFINT_DYN_CTLN1_SW_ITR_INDX_ENA_MASK IAVF_MASK(0x1, IAVF_VFINT_DYN_CTLN1_SW_ITR_INDX_ENA_SHIFT) +#define IAVF_VFINT_ICR0_ENA1 0x00005000 /* Reset: CORER */ +#define IAVF_VFINT_ICR0_ENA1_ADMINQ_SHIFT 30 +#define IAVF_VFINT_ICR0_ENA1_ADMINQ_MASK IAVF_MASK(0x1, IAVF_VFINT_ICR0_ENA1_ADMINQ_SHIFT) +#define IAVF_VFINT_ICR0_ENA1_RSVD_SHIFT 31 +#define IAVF_VFINT_ICR01 0x00004800 /* Reset: CORER */ +#define IAVF_VFINT_ITRN1(_i, _INTVF) (0x00002800 + ((_i) * 64 + (_INTVF) * 4)) /* _i=0...2, _INTVF=0...15 */ /* Reset: VFR */ +#define IAVF_QRX_TAIL1(_Q) (0x00002000 + ((_Q) * 4)) /* _i=0...15 */ /* Reset: CORER */ +#define IAVF_QTX_TAIL1(_Q) (0x00000000 + ((_Q) * 4)) /* _i=0...15 */ /* Reset: PFR */ +#define IAVF_VFQF_HENA(_i) (0x0000C400 + ((_i) * 4)) /* _i=0...1 */ /* Reset: CORER */ +#define IAVF_VFQF_HKEY(_i) (0x0000CC00 + ((_i) * 4)) /* _i=0...12 */ /* Reset: CORER */ +#define IAVF_VFQF_HKEY_MAX_INDEX 12 +#define IAVF_VFQF_HLUT(_i) (0x0000D000 + ((_i) * 4)) /* _i=0...15 */ /* Reset: CORER */ +#define IAVF_VFQF_HLUT_MAX_INDEX 15 +#define IAVF_VFINT_DYN_CTLN1_WB_ON_ITR_SHIFT 30 +#define IAVF_VFINT_DYN_CTLN1_WB_ON_ITR_MASK IAVF_MASK(0x1, IAVF_VFINT_DYN_CTLN1_WB_ON_ITR_SHIFT) +#endif /* _IAVF_REGISTER_H_ */ diff --git a/drivers/net/ethernet/intel/i40evf/i40e_status.h b/drivers/net/ethernet/intel/iavf/iavf_status.h index 77be0702d07c..46742fab7b8c 100644 --- a/drivers/net/ethernet/intel/i40evf/i40e_status.h +++ b/drivers/net/ethernet/intel/iavf/iavf_status.h @@ -1,11 +1,11 @@ /* SPDX-License-Identifier: GPL-2.0 */ /* Copyright(c) 2013 - 2018 Intel Corporation. */ -#ifndef _I40E_STATUS_H_ -#define _I40E_STATUS_H_ +#ifndef _IAVF_STATUS_H_ +#define _IAVF_STATUS_H_ /* Error Codes */ -enum i40e_status_code { +enum iavf_status_code { I40E_SUCCESS = 0, I40E_ERR_NVM = -1, I40E_ERR_NVM_CHECKSUM = -2, @@ -75,4 +75,4 @@ enum i40e_status_code { I40E_ERR_ADMIN_QUEUE_CRITICAL_ERROR = -66, }; -#endif /* _I40E_STATUS_H_ */ +#endif /* _IAVF_STATUS_H_ */ diff --git a/drivers/net/ethernet/intel/i40evf/i40e_trace.h b/drivers/net/ethernet/intel/iavf/iavf_trace.h index d7a4e68820a8..1474f5539751 100644 --- a/drivers/net/ethernet/intel/i40evf/i40e_trace.h +++ b/drivers/net/ethernet/intel/iavf/iavf_trace.h @@ -3,16 +3,16 @@ /* Modeled on trace-events-sample.h */ -/* The trace subsystem name for i40evf will be "i40evf". +/* The trace subsystem name for iavf will be "iavf". * - * This file is named i40e_trace.h. + * This file is named iavf_trace.h. * * Since this include file's name is different from the trace * subsystem name, we'll have to define TRACE_INCLUDE_FILE at the end * of this file. */ #undef TRACE_SYSTEM -#define TRACE_SYSTEM i40evf +#define TRACE_SYSTEM iavf /* See trace-events-sample.h for a detailed description of why this * guard clause is different from most normal include files. @@ -23,14 +23,14 @@ #include <linux/tracepoint.h> /** - * i40e_trace() macro enables shared code to refer to trace points + * iavf_trace() macro enables shared code to refer to trace points * like: * - * trace_i40e{,vf}_example(args...) + * trace_iavf{,vf}_example(args...) * * ... as: * - * i40e_trace(example, args...) + * iavf_trace(example, args...) * * ... to resolve to the PF or VF version of the tracepoint without * ifdefs, and to allow tracepoints to be disabled entirely at build @@ -39,29 +39,29 @@ * Trace point should always be referred to in the driver via this * macro. * - * Similarly, i40e_trace_enabled(trace_name) wraps references to - * trace_i40e{,vf}_<trace_name>_enabled() functions. + * Similarly, iavf_trace_enabled(trace_name) wraps references to + * trace_iavf{,vf}_<trace_name>_enabled() functions. */ -#define _I40E_TRACE_NAME(trace_name) (trace_ ## i40evf ## _ ## trace_name) -#define I40E_TRACE_NAME(trace_name) _I40E_TRACE_NAME(trace_name) +#define _IAVF_TRACE_NAME(trace_name) (trace_ ## iavf ## _ ## trace_name) +#define IAVF_TRACE_NAME(trace_name) _IAVF_TRACE_NAME(trace_name) -#define i40e_trace(trace_name, args...) I40E_TRACE_NAME(trace_name)(args) +#define iavf_trace(trace_name, args...) IAVF_TRACE_NAME(trace_name)(args) -#define i40e_trace_enabled(trace_name) I40E_TRACE_NAME(trace_name##_enabled)() +#define iavf_trace_enabled(trace_name) IAVF_TRACE_NAME(trace_name##_enabled)() /* Events common to PF and VF. Corresponding versions will be defined - * for both, named trace_i40e_* and trace_i40evf_*. The i40e_trace() + * for both, named trace_iavf_* and trace_iavf_*. The iavf_trace() * macro above will select the right trace point name for the driver * being built from shared code. */ /* Events related to a vsi & ring */ DECLARE_EVENT_CLASS( - i40evf_tx_template, + iavf_tx_template, - TP_PROTO(struct i40e_ring *ring, - struct i40e_tx_desc *desc, - struct i40e_tx_buffer *buf), + TP_PROTO(struct iavf_ring *ring, + struct iavf_tx_desc *desc, + struct iavf_tx_buffer *buf), TP_ARGS(ring, desc, buf), @@ -93,26 +93,26 @@ DECLARE_EVENT_CLASS( ); DEFINE_EVENT( - i40evf_tx_template, i40evf_clean_tx_irq, - TP_PROTO(struct i40e_ring *ring, - struct i40e_tx_desc *desc, - struct i40e_tx_buffer *buf), + iavf_tx_template, iavf_clean_tx_irq, + TP_PROTO(struct iavf_ring *ring, + struct iavf_tx_desc *desc, + struct iavf_tx_buffer *buf), TP_ARGS(ring, desc, buf)); DEFINE_EVENT( - i40evf_tx_template, i40evf_clean_tx_irq_unmap, - TP_PROTO(struct i40e_ring *ring, - struct i40e_tx_desc *desc, - struct i40e_tx_buffer *buf), + iavf_tx_template, iavf_clean_tx_irq_unmap, + TP_PROTO(struct iavf_ring *ring, + struct iavf_tx_desc *desc, + struct iavf_tx_buffer *buf), TP_ARGS(ring, desc, buf)); DECLARE_EVENT_CLASS( - i40evf_rx_template, + iavf_rx_template, - TP_PROTO(struct i40e_ring *ring, - union i40e_32byte_rx_desc *desc, + TP_PROTO(struct iavf_ring *ring, + union iavf_32byte_rx_desc *desc, struct sk_buff *skb), TP_ARGS(ring, desc, skb), @@ -138,26 +138,26 @@ DECLARE_EVENT_CLASS( ); DEFINE_EVENT( - i40evf_rx_template, i40evf_clean_rx_irq, - TP_PROTO(struct i40e_ring *ring, - union i40e_32byte_rx_desc *desc, + iavf_rx_template, iavf_clean_rx_irq, + TP_PROTO(struct iavf_ring *ring, + union iavf_32byte_rx_desc *desc, struct sk_buff *skb), TP_ARGS(ring, desc, skb)); DEFINE_EVENT( - i40evf_rx_template, i40evf_clean_rx_irq_rx, - TP_PROTO(struct i40e_ring *ring, - union i40e_32byte_rx_desc *desc, + iavf_rx_template, iavf_clean_rx_irq_rx, + TP_PROTO(struct iavf_ring *ring, + union iavf_32byte_rx_desc *desc, struct sk_buff *skb), TP_ARGS(ring, desc, skb)); DECLARE_EVENT_CLASS( - i40evf_xmit_template, + iavf_xmit_template, TP_PROTO(struct sk_buff *skb, - struct i40e_ring *ring), + struct iavf_ring *ring), TP_ARGS(skb, ring), @@ -180,23 +180,23 @@ DECLARE_EVENT_CLASS( ); DEFINE_EVENT( - i40evf_xmit_template, i40evf_xmit_frame_ring, + iavf_xmit_template, iavf_xmit_frame_ring, TP_PROTO(struct sk_buff *skb, - struct i40e_ring *ring), + struct iavf_ring *ring), TP_ARGS(skb, ring)); DEFINE_EVENT( - i40evf_xmit_template, i40evf_xmit_frame_ring_drop, + iavf_xmit_template, iavf_xmit_frame_ring_drop, TP_PROTO(struct sk_buff *skb, - struct i40e_ring *ring), + struct iavf_ring *ring), TP_ARGS(skb, ring)); /* Events unique to the VF. */ -#endif /* _I40E_TRACE_H_ */ -/* This must be outside ifdef _I40E_TRACE_H */ +#endif /* _IAVF_TRACE_H_ */ +/* This must be outside ifdef _IAVF_TRACE_H */ /* This trace include file is not located in the .../include/trace * with the kernel tracepoint definitions, because we're a loadable @@ -205,5 +205,5 @@ DEFINE_EVENT( #undef TRACE_INCLUDE_PATH #define TRACE_INCLUDE_PATH . #undef TRACE_INCLUDE_FILE -#define TRACE_INCLUDE_FILE i40e_trace +#define TRACE_INCLUDE_FILE iavf_trace #include <trace/define_trace.h> diff --git a/drivers/net/ethernet/intel/i40evf/i40e_txrx.c b/drivers/net/ethernet/intel/iavf/iavf_txrx.c index a9730711e257..edc349f49748 100644 --- a/drivers/net/ethernet/intel/i40evf/i40e_txrx.c +++ b/drivers/net/ethernet/intel/iavf/iavf_txrx.c @@ -4,32 +4,32 @@ #include <linux/prefetch.h> #include <net/busy_poll.h> -#include "i40evf.h" -#include "i40e_trace.h" -#include "i40e_prototype.h" +#include "iavf.h" +#include "iavf_trace.h" +#include "iavf_prototype.h" static inline __le64 build_ctob(u32 td_cmd, u32 td_offset, unsigned int size, u32 td_tag) { - return cpu_to_le64(I40E_TX_DESC_DTYPE_DATA | - ((u64)td_cmd << I40E_TXD_QW1_CMD_SHIFT) | - ((u64)td_offset << I40E_TXD_QW1_OFFSET_SHIFT) | - ((u64)size << I40E_TXD_QW1_TX_BUF_SZ_SHIFT) | - ((u64)td_tag << I40E_TXD_QW1_L2TAG1_SHIFT)); + return cpu_to_le64(IAVF_TX_DESC_DTYPE_DATA | + ((u64)td_cmd << IAVF_TXD_QW1_CMD_SHIFT) | + ((u64)td_offset << IAVF_TXD_QW1_OFFSET_SHIFT) | + ((u64)size << IAVF_TXD_QW1_TX_BUF_SZ_SHIFT) | + ((u64)td_tag << IAVF_TXD_QW1_L2TAG1_SHIFT)); } -#define I40E_TXD_CMD (I40E_TX_DESC_CMD_EOP | I40E_TX_DESC_CMD_RS) +#define IAVF_TXD_CMD (IAVF_TX_DESC_CMD_EOP | IAVF_TX_DESC_CMD_RS) /** - * i40e_unmap_and_free_tx_resource - Release a Tx buffer + * iavf_unmap_and_free_tx_resource - Release a Tx buffer * @ring: the ring that owns the buffer * @tx_buffer: the buffer to free **/ -static void i40e_unmap_and_free_tx_resource(struct i40e_ring *ring, - struct i40e_tx_buffer *tx_buffer) +static void iavf_unmap_and_free_tx_resource(struct iavf_ring *ring, + struct iavf_tx_buffer *tx_buffer) { if (tx_buffer->skb) { - if (tx_buffer->tx_flags & I40E_TX_FLAGS_FD_SB) + if (tx_buffer->tx_flags & IAVF_TX_FLAGS_FD_SB) kfree(tx_buffer->raw_buf); else dev_kfree_skb_any(tx_buffer->skb); @@ -52,10 +52,10 @@ static void i40e_unmap_and_free_tx_resource(struct i40e_ring *ring, } /** - * i40evf_clean_tx_ring - Free any empty Tx buffers + * iavf_clean_tx_ring - Free any empty Tx buffers * @tx_ring: ring to be cleaned **/ -void i40evf_clean_tx_ring(struct i40e_ring *tx_ring) +void iavf_clean_tx_ring(struct iavf_ring *tx_ring) { unsigned long bi_size; u16 i; @@ -66,9 +66,9 @@ void i40evf_clean_tx_ring(struct i40e_ring *tx_ring) /* Free all the Tx ring sk_buffs */ for (i = 0; i < tx_ring->count; i++) - i40e_unmap_and_free_tx_resource(tx_ring, &tx_ring->tx_bi[i]); + iavf_unmap_and_free_tx_resource(tx_ring, &tx_ring->tx_bi[i]); - bi_size = sizeof(struct i40e_tx_buffer) * tx_ring->count; + bi_size = sizeof(struct iavf_tx_buffer) * tx_ring->count; memset(tx_ring->tx_bi, 0, bi_size); /* Zero out the descriptor ring */ @@ -85,14 +85,14 @@ void i40evf_clean_tx_ring(struct i40e_ring *tx_ring) } /** - * i40evf_free_tx_resources - Free Tx resources per queue + * iavf_free_tx_resources - Free Tx resources per queue * @tx_ring: Tx descriptor ring for a specific queue * * Free all transmit software resources **/ -void i40evf_free_tx_resources(struct i40e_ring *tx_ring) +void iavf_free_tx_resources(struct iavf_ring *tx_ring) { - i40evf_clean_tx_ring(tx_ring); + iavf_clean_tx_ring(tx_ring); kfree(tx_ring->tx_bi); tx_ring->tx_bi = NULL; @@ -104,14 +104,14 @@ void i40evf_free_tx_resources(struct i40e_ring *tx_ring) } /** - * i40evf_get_tx_pending - how many Tx descriptors not processed + * iavf_get_tx_pending - how many Tx descriptors not processed * @ring: the ring of descriptors * @in_sw: is tx_pending being checked in SW or HW * * Since there is no access to the ring head register * in XL710, we need to use our local copies **/ -u32 i40evf_get_tx_pending(struct i40e_ring *ring, bool in_sw) +u32 iavf_get_tx_pending(struct iavf_ring *ring, bool in_sw) { u32 head, tail; @@ -126,15 +126,15 @@ u32 i40evf_get_tx_pending(struct i40e_ring *ring, bool in_sw) } /** - * i40evf_detect_recover_hung - Function to detect and recover hung_queues + * iavf_detect_recover_hung - Function to detect and recover hung_queues * @vsi: pointer to vsi struct with tx queues * * VSI has netdev and netdev has TX queues. This function is to check each of * those TX queues if they are hung, trigger recovery by issuing SW interrupt. **/ -void i40evf_detect_recover_hung(struct i40e_vsi *vsi) +void iavf_detect_recover_hung(struct iavf_vsi *vsi) { - struct i40e_ring *tx_ring = NULL; + struct iavf_ring *tx_ring = NULL; struct net_device *netdev; unsigned int i; int packets; @@ -142,7 +142,7 @@ void i40evf_detect_recover_hung(struct i40e_vsi *vsi) if (!vsi) return; - if (test_bit(__I40E_VSI_DOWN, vsi->state)) + if (test_bit(__IAVF_VSI_DOWN, vsi->state)) return; netdev = vsi->netdev; @@ -164,16 +164,16 @@ void i40evf_detect_recover_hung(struct i40e_vsi *vsi) */ packets = tx_ring->stats.packets & INT_MAX; if (tx_ring->tx_stats.prev_pkt_ctr == packets) { - i40evf_force_wb(vsi, tx_ring->q_vector); + iavf_force_wb(vsi, tx_ring->q_vector); continue; } /* Memory barrier between read of packet count and call - * to i40evf_get_tx_pending() + * to iavf_get_tx_pending() */ smp_rmb(); tx_ring->tx_stats.prev_pkt_ctr = - i40evf_get_tx_pending(tx_ring, true) ? packets : -1; + iavf_get_tx_pending(tx_ring, true) ? packets : -1; } } } @@ -181,28 +181,28 @@ void i40evf_detect_recover_hung(struct i40e_vsi *vsi) #define WB_STRIDE 4 /** - * i40e_clean_tx_irq - Reclaim resources after transmit completes + * iavf_clean_tx_irq - Reclaim resources after transmit completes * @vsi: the VSI we care about * @tx_ring: Tx ring to clean * @napi_budget: Used to determine if we are in netpoll * * Returns true if there's any budget left (e.g. the clean is finished) **/ -static bool i40e_clean_tx_irq(struct i40e_vsi *vsi, - struct i40e_ring *tx_ring, int napi_budget) +static bool iavf_clean_tx_irq(struct iavf_vsi *vsi, + struct iavf_ring *tx_ring, int napi_budget) { u16 i = tx_ring->next_to_clean; - struct i40e_tx_buffer *tx_buf; - struct i40e_tx_desc *tx_desc; + struct iavf_tx_buffer *tx_buf; + struct iavf_tx_desc *tx_desc; unsigned int total_bytes = 0, total_packets = 0; unsigned int budget = vsi->work_limit; tx_buf = &tx_ring->tx_bi[i]; - tx_desc = I40E_TX_DESC(tx_ring, i); + tx_desc = IAVF_TX_DESC(tx_ring, i); i -= tx_ring->count; do { - struct i40e_tx_desc *eop_desc = tx_buf->next_to_watch; + struct iavf_tx_desc *eop_desc = tx_buf->next_to_watch; /* if next_to_watch is not set then there is no work pending */ if (!eop_desc) @@ -211,10 +211,10 @@ static bool i40e_clean_tx_irq(struct i40e_vsi *vsi, /* prevent any other reads prior to eop_desc */ smp_rmb(); - i40e_trace(clean_tx_irq, tx_ring, tx_desc, tx_buf); + iavf_trace(clean_tx_irq, tx_ring, tx_desc, tx_buf); /* if the descriptor isn't done, no work yet to do */ if (!(eop_desc->cmd_type_offset_bsz & - cpu_to_le64(I40E_TX_DESC_DTYPE_DESC_DONE))) + cpu_to_le64(IAVF_TX_DESC_DTYPE_DESC_DONE))) break; /* clear next_to_watch to prevent false hangs */ @@ -239,7 +239,7 @@ static bool i40e_clean_tx_irq(struct i40e_vsi *vsi, /* unmap remaining buffers */ while (tx_desc != eop_desc) { - i40e_trace(clean_tx_irq_unmap, + iavf_trace(clean_tx_irq_unmap, tx_ring, tx_desc, tx_buf); tx_buf++; @@ -248,7 +248,7 @@ static bool i40e_clean_tx_irq(struct i40e_vsi *vsi, if (unlikely(!i)) { i -= tx_ring->count; tx_buf = tx_ring->tx_bi; - tx_desc = I40E_TX_DESC(tx_ring, 0); + tx_desc = IAVF_TX_DESC(tx_ring, 0); } /* unmap any remaining paged data */ @@ -268,7 +268,7 @@ static bool i40e_clean_tx_irq(struct i40e_vsi *vsi, if (unlikely(!i)) { i -= tx_ring->count; tx_buf = tx_ring->tx_bi; - tx_desc = I40E_TX_DESC(tx_ring, 0); + tx_desc = IAVF_TX_DESC(tx_ring, 0); } prefetch(tx_desc); @@ -286,18 +286,18 @@ static bool i40e_clean_tx_irq(struct i40e_vsi *vsi, tx_ring->q_vector->tx.total_bytes += total_bytes; tx_ring->q_vector->tx.total_packets += total_packets; - if (tx_ring->flags & I40E_TXR_FLAGS_WB_ON_ITR) { + if (tx_ring->flags & IAVF_TXR_FLAGS_WB_ON_ITR) { /* check to see if there are < 4 descriptors * waiting to be written back, then kick the hardware to force * them to be written back in case we stay in NAPI. * In this mode on X722 we do not enable Interrupt. */ - unsigned int j = i40evf_get_tx_pending(tx_ring, false); + unsigned int j = iavf_get_tx_pending(tx_ring, false); if (budget && ((j / WB_STRIDE) == 0) && (j > 0) && - !test_bit(__I40E_VSI_DOWN, vsi->state) && - (I40E_DESC_UNUSED(tx_ring) != tx_ring->count)) + !test_bit(__IAVF_VSI_DOWN, vsi->state) && + (IAVF_DESC_UNUSED(tx_ring) != tx_ring->count)) tx_ring->arm_wb = true; } @@ -307,14 +307,14 @@ static bool i40e_clean_tx_irq(struct i40e_vsi *vsi, #define TX_WAKE_THRESHOLD ((s16)(DESC_NEEDED * 2)) if (unlikely(total_packets && netif_carrier_ok(tx_ring->netdev) && - (I40E_DESC_UNUSED(tx_ring) >= TX_WAKE_THRESHOLD))) { + (IAVF_DESC_UNUSED(tx_ring) >= TX_WAKE_THRESHOLD))) { /* Make sure that anybody stopping the queue after this * sees the new next_to_clean. */ smp_mb(); if (__netif_subqueue_stopped(tx_ring->netdev, tx_ring->queue_index) && - !test_bit(__I40E_VSI_DOWN, vsi->state)) { + !test_bit(__IAVF_VSI_DOWN, vsi->state)) { netif_wake_subqueue(tx_ring->netdev, tx_ring->queue_index); ++tx_ring->tx_stats.restart_queue; @@ -325,75 +325,75 @@ static bool i40e_clean_tx_irq(struct i40e_vsi *vsi, } /** - * i40evf_enable_wb_on_itr - Arm hardware to do a wb, interrupts are not enabled + * iavf_enable_wb_on_itr - Arm hardware to do a wb, interrupts are not enabled * @vsi: the VSI we care about * @q_vector: the vector on which to enable writeback * **/ -static void i40e_enable_wb_on_itr(struct i40e_vsi *vsi, - struct i40e_q_vector *q_vector) +static void iavf_enable_wb_on_itr(struct iavf_vsi *vsi, + struct iavf_q_vector *q_vector) { u16 flags = q_vector->tx.ring[0].flags; u32 val; - if (!(flags & I40E_TXR_FLAGS_WB_ON_ITR)) + if (!(flags & IAVF_TXR_FLAGS_WB_ON_ITR)) return; if (q_vector->arm_wb_state) return; - val = I40E_VFINT_DYN_CTLN1_WB_ON_ITR_MASK | - I40E_VFINT_DYN_CTLN1_ITR_INDX_MASK; /* set noitr */ + val = IAVF_VFINT_DYN_CTLN1_WB_ON_ITR_MASK | + IAVF_VFINT_DYN_CTLN1_ITR_INDX_MASK; /* set noitr */ wr32(&vsi->back->hw, - I40E_VFINT_DYN_CTLN1(q_vector->reg_idx), val); + IAVF_VFINT_DYN_CTLN1(q_vector->reg_idx), val); q_vector->arm_wb_state = true; } /** - * i40evf_force_wb - Issue SW Interrupt so HW does a wb + * iavf_force_wb - Issue SW Interrupt so HW does a wb * @vsi: the VSI we care about * @q_vector: the vector on which to force writeback * **/ -void i40evf_force_wb(struct i40e_vsi *vsi, struct i40e_q_vector *q_vector) +void iavf_force_wb(struct iavf_vsi *vsi, struct iavf_q_vector *q_vector) { - u32 val = I40E_VFINT_DYN_CTLN1_INTENA_MASK | - I40E_VFINT_DYN_CTLN1_ITR_INDX_MASK | /* set noitr */ - I40E_VFINT_DYN_CTLN1_SWINT_TRIG_MASK | - I40E_VFINT_DYN_CTLN1_SW_ITR_INDX_ENA_MASK + u32 val = IAVF_VFINT_DYN_CTLN1_INTENA_MASK | + IAVF_VFINT_DYN_CTLN1_ITR_INDX_MASK | /* set noitr */ + IAVF_VFINT_DYN_CTLN1_SWINT_TRIG_MASK | + IAVF_VFINT_DYN_CTLN1_SW_ITR_INDX_ENA_MASK /* allow 00 to be written to the index */; wr32(&vsi->back->hw, - I40E_VFINT_DYN_CTLN1(q_vector->reg_idx), + IAVF_VFINT_DYN_CTLN1(q_vector->reg_idx), val); } -static inline bool i40e_container_is_rx(struct i40e_q_vector *q_vector, - struct i40e_ring_container *rc) +static inline bool iavf_container_is_rx(struct iavf_q_vector *q_vector, + struct iavf_ring_container *rc) { return &q_vector->rx == rc; } -static inline unsigned int i40e_itr_divisor(struct i40e_q_vector *q_vector) +static inline unsigned int iavf_itr_divisor(struct iavf_q_vector *q_vector) { unsigned int divisor; switch (q_vector->adapter->link_speed) { case I40E_LINK_SPEED_40GB: - divisor = I40E_ITR_ADAPTIVE_MIN_INC * 1024; + divisor = IAVF_ITR_ADAPTIVE_MIN_INC * 1024; break; case I40E_LINK_SPEED_25GB: case I40E_LINK_SPEED_20GB: - divisor = I40E_ITR_ADAPTIVE_MIN_INC * 512; + divisor = IAVF_ITR_ADAPTIVE_MIN_INC * 512; break; default: case I40E_LINK_SPEED_10GB: - divisor = I40E_ITR_ADAPTIVE_MIN_INC * 256; + divisor = IAVF_ITR_ADAPTIVE_MIN_INC * 256; break; case I40E_LINK_SPEED_1GB: case I40E_LINK_SPEED_100MB: - divisor = I40E_ITR_ADAPTIVE_MIN_INC * 32; + divisor = IAVF_ITR_ADAPTIVE_MIN_INC * 32; break; } @@ -401,7 +401,7 @@ static inline unsigned int i40e_itr_divisor(struct i40e_q_vector *q_vector) } /** - * i40e_update_itr - update the dynamic ITR value based on statistics + * iavf_update_itr - update the dynamic ITR value based on statistics * @q_vector: structure containing interrupt and ring information * @rc: structure containing ring performance data * @@ -413,8 +413,8 @@ static inline unsigned int i40e_itr_divisor(struct i40e_q_vector *q_vector) * on testing data as well as attempting to minimize response time * while increasing bulk throughput. **/ -static void i40e_update_itr(struct i40e_q_vector *q_vector, - struct i40e_ring_container *rc) +static void iavf_update_itr(struct iavf_q_vector *q_vector, + struct iavf_ring_container *rc) { unsigned int avg_wire_size, packets, bytes, itr; unsigned long next_update = jiffies; @@ -428,9 +428,9 @@ static void i40e_update_itr(struct i40e_q_vector *q_vector, /* For Rx we want to push the delay up and default to low latency. * for Tx we want to pull the delay down and default to high latency. */ - itr = i40e_container_is_rx(q_vector, rc) ? - I40E_ITR_ADAPTIVE_MIN_USECS | I40E_ITR_ADAPTIVE_LATENCY : - I40E_ITR_ADAPTIVE_MAX_USECS | I40E_ITR_ADAPTIVE_LATENCY; + itr = iavf_container_is_rx(q_vector, rc) ? + IAVF_ITR_ADAPTIVE_MIN_USECS | IAVF_ITR_ADAPTIVE_LATENCY : + IAVF_ITR_ADAPTIVE_MAX_USECS | IAVF_ITR_ADAPTIVE_LATENCY; /* If we didn't update within up to 1 - 2 jiffies we can assume * that either packets are coming in so slow there hasn't been @@ -454,15 +454,15 @@ static void i40e_update_itr(struct i40e_q_vector *q_vector, packets = rc->total_packets; bytes = rc->total_bytes; - if (i40e_container_is_rx(q_vector, rc)) { + if (iavf_container_is_rx(q_vector, rc)) { /* If Rx there are 1 to 4 packets and bytes are less than * 9000 assume insufficient data to use bulk rate limiting * approach unless Tx is already in bulk rate limiting. We * are likely latency driven. */ if (packets && packets < 4 && bytes < 9000 && - (q_vector->tx.target_itr & I40E_ITR_ADAPTIVE_LATENCY)) { - itr = I40E_ITR_ADAPTIVE_LATENCY; + (q_vector->tx.target_itr & IAVF_ITR_ADAPTIVE_LATENCY)) { + itr = IAVF_ITR_ADAPTIVE_LATENCY; goto adjust_by_size; } } else if (packets < 4) { @@ -471,15 +471,15 @@ static void i40e_update_itr(struct i40e_q_vector *q_vector, * reset the ITR_ADAPTIVE_LATENCY bit for latency mode so * that the Rx can relax. */ - if (rc->target_itr == I40E_ITR_ADAPTIVE_MAX_USECS && - (q_vector->rx.target_itr & I40E_ITR_MASK) == - I40E_ITR_ADAPTIVE_MAX_USECS) + if (rc->target_itr == IAVF_ITR_ADAPTIVE_MAX_USECS && + (q_vector->rx.target_itr & IAVF_ITR_MASK) == + IAVF_ITR_ADAPTIVE_MAX_USECS) goto clear_counts; } else if (packets > 32) { /* If we have processed over 32 packets in a single interrupt * for Tx assume we need to switch over to "bulk" mode. */ - rc->target_itr &= ~I40E_ITR_ADAPTIVE_LATENCY; + rc->target_itr &= ~IAVF_ITR_ADAPTIVE_LATENCY; } /* We have no packets to actually measure against. This means @@ -491,17 +491,17 @@ static void i40e_update_itr(struct i40e_q_vector *q_vector, * fixed amount. */ if (packets < 56) { - itr = rc->target_itr + I40E_ITR_ADAPTIVE_MIN_INC; - if ((itr & I40E_ITR_MASK) > I40E_ITR_ADAPTIVE_MAX_USECS) { - itr &= I40E_ITR_ADAPTIVE_LATENCY; - itr += I40E_ITR_ADAPTIVE_MAX_USECS; + itr = rc->target_itr + IAVF_ITR_ADAPTIVE_MIN_INC; + if ((itr & IAVF_ITR_MASK) > IAVF_ITR_ADAPTIVE_MAX_USECS) { + itr &= IAVF_ITR_ADAPTIVE_LATENCY; + itr += IAVF_ITR_ADAPTIVE_MAX_USECS; } goto clear_counts; } if (packets <= 256) { itr = min(q_vector->tx.current_itr, q_vector->rx.current_itr); - itr &= I40E_ITR_MASK; + itr &= IAVF_ITR_MASK; /* Between 56 and 112 is our "goldilocks" zone where we are * working out "just right". Just report that our current @@ -516,9 +516,9 @@ static void i40e_update_itr(struct i40e_q_vector *q_vector, * in half per interrupt. */ itr /= 2; - itr &= I40E_ITR_MASK; - if (itr < I40E_ITR_ADAPTIVE_MIN_USECS) - itr = I40E_ITR_ADAPTIVE_MIN_USECS; + itr &= IAVF_ITR_MASK; + if (itr < IAVF_ITR_ADAPTIVE_MIN_USECS) + itr = IAVF_ITR_ADAPTIVE_MIN_USECS; goto clear_counts; } @@ -529,7 +529,7 @@ static void i40e_update_itr(struct i40e_q_vector *q_vector, * though for smaller packet sizes there isn't much we can do as * NAPI polling will likely be kicking in sooner rather than later. */ - itr = I40E_ITR_ADAPTIVE_BULK; + itr = IAVF_ITR_ADAPTIVE_BULK; adjust_by_size: /* If packet counts are 256 or greater we can assume we have a gross @@ -577,7 +577,7 @@ adjust_by_size: /* If we are in low latency mode halve our delay which doubles the * rate to somewhere between 100K to 16K ints/sec */ - if (itr & I40E_ITR_ADAPTIVE_LATENCY) + if (itr & IAVF_ITR_ADAPTIVE_LATENCY) avg_wire_size /= 2; /* Resultant value is 256 times larger than it needs to be. This @@ -587,12 +587,12 @@ adjust_by_size: * Use addition as we have already recorded the new latency flag * for the ITR value. */ - itr += DIV_ROUND_UP(avg_wire_size, i40e_itr_divisor(q_vector)) * - I40E_ITR_ADAPTIVE_MIN_INC; + itr += DIV_ROUND_UP(avg_wire_size, iavf_itr_divisor(q_vector)) * + IAVF_ITR_ADAPTIVE_MIN_INC; - if ((itr & I40E_ITR_MASK) > I40E_ITR_ADAPTIVE_MAX_USECS) { - itr &= I40E_ITR_ADAPTIVE_LATENCY; - itr += I40E_ITR_ADAPTIVE_MAX_USECS; + if ((itr & IAVF_ITR_MASK) > IAVF_ITR_ADAPTIVE_MAX_USECS) { + itr &= IAVF_ITR_ADAPTIVE_LATENCY; + itr += IAVF_ITR_ADAPTIVE_MAX_USECS; } clear_counts: @@ -607,12 +607,12 @@ clear_counts: } /** - * i40evf_setup_tx_descriptors - Allocate the Tx descriptors + * iavf_setup_tx_descriptors - Allocate the Tx descriptors * @tx_ring: the tx ring to set up * * Return 0 on success, negative on error **/ -int i40evf_setup_tx_descriptors(struct i40e_ring *tx_ring) +int iavf_setup_tx_descriptors(struct iavf_ring *tx_ring) { struct device *dev = tx_ring->dev; int bi_size; @@ -622,13 +622,13 @@ int i40evf_setup_tx_descriptors(struct i40e_ring *tx_ring) /* warn if we are about to overwrite the pointer */ WARN_ON(tx_ring->tx_bi); - bi_size = sizeof(struct i40e_tx_buffer) * tx_ring->count; + bi_size = sizeof(struct iavf_tx_buffer) * tx_ring->count; tx_ring->tx_bi = kzalloc(bi_size, GFP_KERNEL); if (!tx_ring->tx_bi) goto err; /* round up to nearest 4K */ - tx_ring->size = tx_ring->count * sizeof(struct i40e_tx_desc); + tx_ring->size = tx_ring->count * sizeof(struct iavf_tx_desc); tx_ring->size = ALIGN(tx_ring->size, 4096); tx_ring->desc = dma_alloc_coherent(dev, tx_ring->size, &tx_ring->dma, GFP_KERNEL); @@ -650,10 +650,10 @@ err: } /** - * i40evf_clean_rx_ring - Free Rx buffers + * iavf_clean_rx_ring - Free Rx buffers * @rx_ring: ring to be cleaned **/ -void i40evf_clean_rx_ring(struct i40e_ring *rx_ring) +void iavf_clean_rx_ring(struct iavf_ring *rx_ring) { unsigned long bi_size; u16 i; @@ -669,7 +669,7 @@ void i40evf_clean_rx_ring(struct i40e_ring *rx_ring) /* Free all the Rx ring sk_buffs */ for (i = 0; i < rx_ring->count; i++) { - struct i40e_rx_buffer *rx_bi = &rx_ring->rx_bi[i]; + struct iavf_rx_buffer *rx_bi = &rx_ring->rx_bi[i]; if (!rx_bi->page) continue; @@ -685,9 +685,9 @@ void i40evf_clean_rx_ring(struct i40e_ring *rx_ring) /* free resources associated with mapping */ dma_unmap_page_attrs(rx_ring->dev, rx_bi->dma, - i40e_rx_pg_size(rx_ring), + iavf_rx_pg_size(rx_ring), DMA_FROM_DEVICE, - I40E_RX_DMA_ATTR); + IAVF_RX_DMA_ATTR); __page_frag_cache_drain(rx_bi->page, rx_bi->pagecnt_bias); @@ -695,7 +695,7 @@ void i40evf_clean_rx_ring(struct i40e_ring *rx_ring) rx_bi->page_offset = 0; } - bi_size = sizeof(struct i40e_rx_buffer) * rx_ring->count; + bi_size = sizeof(struct iavf_rx_buffer) * rx_ring->count; memset(rx_ring->rx_bi, 0, bi_size); /* Zero out the descriptor ring */ @@ -707,14 +707,14 @@ void i40evf_clean_rx_ring(struct i40e_ring *rx_ring) } /** - * i40evf_free_rx_resources - Free Rx resources + * iavf_free_rx_resources - Free Rx resources * @rx_ring: ring to clean the resources from * * Free all receive software resources **/ -void i40evf_free_rx_resources(struct i40e_ring *rx_ring) +void iavf_free_rx_resources(struct iavf_ring *rx_ring) { - i40evf_clean_rx_ring(rx_ring); + iavf_clean_rx_ring(rx_ring); kfree(rx_ring->rx_bi); rx_ring->rx_bi = NULL; @@ -726,19 +726,19 @@ void i40evf_free_rx_resources(struct i40e_ring *rx_ring) } /** - * i40evf_setup_rx_descriptors - Allocate Rx descriptors + * iavf_setup_rx_descriptors - Allocate Rx descriptors * @rx_ring: Rx descriptor ring (for a specific queue) to setup * * Returns 0 on success, negative on failure **/ -int i40evf_setup_rx_descriptors(struct i40e_ring *rx_ring) +int iavf_setup_rx_descriptors(struct iavf_ring *rx_ring) { struct device *dev = rx_ring->dev; int bi_size; /* warn if we are about to overwrite the pointer */ WARN_ON(rx_ring->rx_bi); - bi_size = sizeof(struct i40e_rx_buffer) * rx_ring->count; + bi_size = sizeof(struct iavf_rx_buffer) * rx_ring->count; rx_ring->rx_bi = kzalloc(bi_size, GFP_KERNEL); if (!rx_ring->rx_bi) goto err; @@ -746,7 +746,7 @@ int i40evf_setup_rx_descriptors(struct i40e_ring *rx_ring) u64_stats_init(&rx_ring->syncp); /* Round up to nearest 4K */ - rx_ring->size = rx_ring->count * sizeof(union i40e_32byte_rx_desc); + rx_ring->size = rx_ring->count * sizeof(union iavf_32byte_rx_desc); rx_ring->size = ALIGN(rx_ring->size, 4096); rx_ring->desc = dma_alloc_coherent(dev, rx_ring->size, &rx_ring->dma, GFP_KERNEL); @@ -769,11 +769,11 @@ err: } /** - * i40e_release_rx_desc - Store the new tail and head values + * iavf_release_rx_desc - Store the new tail and head values * @rx_ring: ring to bump * @val: new head index **/ -static inline void i40e_release_rx_desc(struct i40e_ring *rx_ring, u32 val) +static inline void iavf_release_rx_desc(struct iavf_ring *rx_ring, u32 val) { rx_ring->next_to_use = val; @@ -790,26 +790,26 @@ static inline void i40e_release_rx_desc(struct i40e_ring *rx_ring, u32 val) } /** - * i40e_rx_offset - Return expected offset into page to access data + * iavf_rx_offset - Return expected offset into page to access data * @rx_ring: Ring we are requesting offset of * * Returns the offset value for ring into the data buffer. */ -static inline unsigned int i40e_rx_offset(struct i40e_ring *rx_ring) +static inline unsigned int iavf_rx_offset(struct iavf_ring *rx_ring) { - return ring_uses_build_skb(rx_ring) ? I40E_SKB_PAD : 0; + return ring_uses_build_skb(rx_ring) ? IAVF_SKB_PAD : 0; } /** - * i40e_alloc_mapped_page - recycle or make a new page + * iavf_alloc_mapped_page - recycle or make a new page * @rx_ring: ring to use * @bi: rx_buffer struct to modify * * Returns true if the page was successfully allocated or * reused. **/ -static bool i40e_alloc_mapped_page(struct i40e_ring *rx_ring, - struct i40e_rx_buffer *bi) +static bool iavf_alloc_mapped_page(struct iavf_ring *rx_ring, + struct iavf_rx_buffer *bi) { struct page *page = bi->page; dma_addr_t dma; @@ -821,7 +821,7 @@ static bool i40e_alloc_mapped_page(struct i40e_ring *rx_ring, } /* alloc new page for storage */ - page = dev_alloc_pages(i40e_rx_pg_order(rx_ring)); + page = dev_alloc_pages(iavf_rx_pg_order(rx_ring)); if (unlikely(!page)) { rx_ring->rx_stats.alloc_page_failed++; return false; @@ -829,22 +829,22 @@ static bool i40e_alloc_mapped_page(struct i40e_ring *rx_ring, /* map page for use */ dma = dma_map_page_attrs(rx_ring->dev, page, 0, - i40e_rx_pg_size(rx_ring), + iavf_rx_pg_size(rx_ring), DMA_FROM_DEVICE, - I40E_RX_DMA_ATTR); + IAVF_RX_DMA_ATTR); /* if mapping failed free memory back to system since * there isn't much point in holding memory we can't use */ if (dma_mapping_error(rx_ring->dev, dma)) { - __free_pages(page, i40e_rx_pg_order(rx_ring)); + __free_pages(page, iavf_rx_pg_order(rx_ring)); rx_ring->rx_stats.alloc_page_failed++; return false; } bi->dma = dma; bi->page = page; - bi->page_offset = i40e_rx_offset(rx_ring); + bi->page_offset = iavf_rx_offset(rx_ring); /* initialize pagecnt_bias to 1 representing we fully own page */ bi->pagecnt_bias = 1; @@ -853,15 +853,15 @@ static bool i40e_alloc_mapped_page(struct i40e_ring *rx_ring, } /** - * i40e_receive_skb - Send a completed packet up the stack + * iavf_receive_skb - Send a completed packet up the stack * @rx_ring: rx ring in play * @skb: packet to send up * @vlan_tag: vlan tag for packet **/ -static void i40e_receive_skb(struct i40e_ring *rx_ring, +static void iavf_receive_skb(struct iavf_ring *rx_ring, struct sk_buff *skb, u16 vlan_tag) { - struct i40e_q_vector *q_vector = rx_ring->q_vector; + struct iavf_q_vector *q_vector = rx_ring->q_vector; if ((rx_ring->netdev->features & NETIF_F_HW_VLAN_CTAG_RX) && (vlan_tag & VLAN_VID_MASK)) @@ -871,27 +871,27 @@ static void i40e_receive_skb(struct i40e_ring *rx_ring, } /** - * i40evf_alloc_rx_buffers - Replace used receive buffers + * iavf_alloc_rx_buffers - Replace used receive buffers * @rx_ring: ring to place buffers on * @cleaned_count: number of buffers to replace * * Returns false if all allocations were successful, true if any fail **/ -bool i40evf_alloc_rx_buffers(struct i40e_ring *rx_ring, u16 cleaned_count) +bool iavf_alloc_rx_buffers(struct iavf_ring *rx_ring, u16 cleaned_count) { u16 ntu = rx_ring->next_to_use; - union i40e_rx_desc *rx_desc; - struct i40e_rx_buffer *bi; + union iavf_rx_desc *rx_desc; + struct iavf_rx_buffer *bi; /* do nothing if no valid netdev defined */ if (!rx_ring->netdev || !cleaned_count) return false; - rx_desc = I40E_RX_DESC(rx_ring, ntu); + rx_desc = IAVF_RX_DESC(rx_ring, ntu); bi = &rx_ring->rx_bi[ntu]; do { - if (!i40e_alloc_mapped_page(rx_ring, bi)) + if (!iavf_alloc_mapped_page(rx_ring, bi)) goto no_buffers; /* sync the buffer for use by the device */ @@ -909,7 +909,7 @@ bool i40evf_alloc_rx_buffers(struct i40e_ring *rx_ring, u16 cleaned_count) bi++; ntu++; if (unlikely(ntu == rx_ring->count)) { - rx_desc = I40E_RX_DESC(rx_ring, 0); + rx_desc = IAVF_RX_DESC(rx_ring, 0); bi = rx_ring->rx_bi; ntu = 0; } @@ -921,13 +921,13 @@ bool i40evf_alloc_rx_buffers(struct i40e_ring *rx_ring, u16 cleaned_count) } while (cleaned_count); if (rx_ring->next_to_use != ntu) - i40e_release_rx_desc(rx_ring, ntu); + iavf_release_rx_desc(rx_ring, ntu); return false; no_buffers: if (rx_ring->next_to_use != ntu) - i40e_release_rx_desc(rx_ring, ntu); + iavf_release_rx_desc(rx_ring, ntu); /* make sure to come back via polling to try again after * allocation failure @@ -936,27 +936,27 @@ no_buffers: } /** - * i40e_rx_checksum - Indicate in skb if hw indicated a good cksum + * iavf_rx_checksum - Indicate in skb if hw indicated a good cksum * @vsi: the VSI we care about * @skb: skb currently being received and modified * @rx_desc: the receive descriptor **/ -static inline void i40e_rx_checksum(struct i40e_vsi *vsi, +static inline void iavf_rx_checksum(struct iavf_vsi *vsi, struct sk_buff *skb, - union i40e_rx_desc *rx_desc) + union iavf_rx_desc *rx_desc) { - struct i40e_rx_ptype_decoded decoded; + struct iavf_rx_ptype_decoded decoded; u32 rx_error, rx_status; bool ipv4, ipv6; u8 ptype; u64 qword; qword = le64_to_cpu(rx_desc->wb.qword1.status_error_len); - ptype = (qword & I40E_RXD_QW1_PTYPE_MASK) >> I40E_RXD_QW1_PTYPE_SHIFT; - rx_error = (qword & I40E_RXD_QW1_ERROR_MASK) >> - I40E_RXD_QW1_ERROR_SHIFT; - rx_status = (qword & I40E_RXD_QW1_STATUS_MASK) >> - I40E_RXD_QW1_STATUS_SHIFT; + ptype = (qword & IAVF_RXD_QW1_PTYPE_MASK) >> IAVF_RXD_QW1_PTYPE_SHIFT; + rx_error = (qword & IAVF_RXD_QW1_ERROR_MASK) >> + IAVF_RXD_QW1_ERROR_SHIFT; + rx_status = (qword & IAVF_RXD_QW1_STATUS_MASK) >> + IAVF_RXD_QW1_STATUS_SHIFT; decoded = decode_rx_desc_ptype(ptype); skb->ip_summed = CHECKSUM_NONE; @@ -968,45 +968,45 @@ static inline void i40e_rx_checksum(struct i40e_vsi *vsi, return; /* did the hardware decode the packet and checksum? */ - if (!(rx_status & BIT(I40E_RX_DESC_STATUS_L3L4P_SHIFT))) + if (!(rx_status & BIT(IAVF_RX_DESC_STATUS_L3L4P_SHIFT))) return; /* both known and outer_ip must be set for the below code to work */ if (!(decoded.known && decoded.outer_ip)) return; - ipv4 = (decoded.outer_ip == I40E_RX_PTYPE_OUTER_IP) && - (decoded.outer_ip_ver == I40E_RX_PTYPE_OUTER_IPV4); - ipv6 = (decoded.outer_ip == I40E_RX_PTYPE_OUTER_IP) && - (decoded.outer_ip_ver == I40E_RX_PTYPE_OUTER_IPV6); + ipv4 = (decoded.outer_ip == IAVF_RX_PTYPE_OUTER_IP) && + (decoded.outer_ip_ver == IAVF_RX_PTYPE_OUTER_IPV4); + ipv6 = (decoded.outer_ip == IAVF_RX_PTYPE_OUTER_IP) && + (decoded.outer_ip_ver == IAVF_RX_PTYPE_OUTER_IPV6); if (ipv4 && - (rx_error & (BIT(I40E_RX_DESC_ERROR_IPE_SHIFT) | - BIT(I40E_RX_DESC_ERROR_EIPE_SHIFT)))) + (rx_error & (BIT(IAVF_RX_DESC_ERROR_IPE_SHIFT) | + BIT(IAVF_RX_DESC_ERROR_EIPE_SHIFT)))) goto checksum_fail; /* likely incorrect csum if alternate IP extension headers found */ if (ipv6 && - rx_status & BIT(I40E_RX_DESC_STATUS_IPV6EXADD_SHIFT)) + rx_status & BIT(IAVF_RX_DESC_STATUS_IPV6EXADD_SHIFT)) /* don't increment checksum err here, non-fatal err */ return; /* there was some L4 error, count error and punt packet to the stack */ - if (rx_error & BIT(I40E_RX_DESC_ERROR_L4E_SHIFT)) + if (rx_error & BIT(IAVF_RX_DESC_ERROR_L4E_SHIFT)) goto checksum_fail; /* handle packets that were not able to be checksummed due * to arrival speed, in this case the stack can compute * the csum. */ - if (rx_error & BIT(I40E_RX_DESC_ERROR_PPRS_SHIFT)) + if (rx_error & BIT(IAVF_RX_DESC_ERROR_PPRS_SHIFT)) return; /* Only report checksum unnecessary for TCP, UDP, or SCTP */ switch (decoded.inner_prot) { - case I40E_RX_PTYPE_INNER_PROT_TCP: - case I40E_RX_PTYPE_INNER_PROT_UDP: - case I40E_RX_PTYPE_INNER_PROT_SCTP: + case IAVF_RX_PTYPE_INNER_PROT_TCP: + case IAVF_RX_PTYPE_INNER_PROT_UDP: + case IAVF_RX_PTYPE_INNER_PROT_SCTP: skb->ip_summed = CHECKSUM_UNNECESSARY; /* fall though */ default: @@ -1020,56 +1020,56 @@ checksum_fail: } /** - * i40e_ptype_to_htype - get a hash type + * iavf_ptype_to_htype - get a hash type * @ptype: the ptype value from the descriptor * * Returns a hash type to be used by skb_set_hash **/ -static inline int i40e_ptype_to_htype(u8 ptype) +static inline int iavf_ptype_to_htype(u8 ptype) { - struct i40e_rx_ptype_decoded decoded = decode_rx_desc_ptype(ptype); + struct iavf_rx_ptype_decoded decoded = decode_rx_desc_ptype(ptype); if (!decoded.known) return PKT_HASH_TYPE_NONE; - if (decoded.outer_ip == I40E_RX_PTYPE_OUTER_IP && - decoded.payload_layer == I40E_RX_PTYPE_PAYLOAD_LAYER_PAY4) + if (decoded.outer_ip == IAVF_RX_PTYPE_OUTER_IP && + decoded.payload_layer == IAVF_RX_PTYPE_PAYLOAD_LAYER_PAY4) return PKT_HASH_TYPE_L4; - else if (decoded.outer_ip == I40E_RX_PTYPE_OUTER_IP && - decoded.payload_layer == I40E_RX_PTYPE_PAYLOAD_LAYER_PAY3) + else if (decoded.outer_ip == IAVF_RX_PTYPE_OUTER_IP && + decoded.payload_layer == IAVF_RX_PTYPE_PAYLOAD_LAYER_PAY3) return PKT_HASH_TYPE_L3; else return PKT_HASH_TYPE_L2; } /** - * i40e_rx_hash - set the hash value in the skb + * iavf_rx_hash - set the hash value in the skb * @ring: descriptor ring * @rx_desc: specific descriptor * @skb: skb currently being received and modified * @rx_ptype: Rx packet type **/ -static inline void i40e_rx_hash(struct i40e_ring *ring, - union i40e_rx_desc *rx_desc, +static inline void iavf_rx_hash(struct iavf_ring *ring, + union iavf_rx_desc *rx_desc, struct sk_buff *skb, u8 rx_ptype) { u32 hash; const __le64 rss_mask = - cpu_to_le64((u64)I40E_RX_DESC_FLTSTAT_RSS_HASH << - I40E_RX_DESC_STATUS_FLTSTAT_SHIFT); + cpu_to_le64((u64)IAVF_RX_DESC_FLTSTAT_RSS_HASH << + IAVF_RX_DESC_STATUS_FLTSTAT_SHIFT); if (ring->netdev->features & NETIF_F_RXHASH) return; if ((rx_desc->wb.qword1.status_error_len & rss_mask) == rss_mask) { hash = le32_to_cpu(rx_desc->wb.qword0.hi_dword.rss); - skb_set_hash(skb, hash, i40e_ptype_to_htype(rx_ptype)); + skb_set_hash(skb, hash, iavf_ptype_to_htype(rx_ptype)); } } /** - * i40evf_process_skb_fields - Populate skb header fields from Rx descriptor + * iavf_process_skb_fields - Populate skb header fields from Rx descriptor * @rx_ring: rx descriptor ring packet is being transacted on * @rx_desc: pointer to the EOP Rx descriptor * @skb: pointer to current skb being populated @@ -1080,13 +1080,13 @@ static inline void i40e_rx_hash(struct i40e_ring *ring, * other fields within the skb. **/ static inline -void i40evf_process_skb_fields(struct i40e_ring *rx_ring, - union i40e_rx_desc *rx_desc, struct sk_buff *skb, - u8 rx_ptype) +void iavf_process_skb_fields(struct iavf_ring *rx_ring, + union iavf_rx_desc *rx_desc, struct sk_buff *skb, + u8 rx_ptype) { - i40e_rx_hash(rx_ring, rx_desc, skb, rx_ptype); + iavf_rx_hash(rx_ring, rx_desc, skb, rx_ptype); - i40e_rx_checksum(rx_ring->vsi, skb, rx_desc); + iavf_rx_checksum(rx_ring->vsi, skb, rx_desc); skb_record_rx_queue(skb, rx_ring->queue_index); @@ -1095,7 +1095,7 @@ void i40evf_process_skb_fields(struct i40e_ring *rx_ring, } /** - * i40e_cleanup_headers - Correct empty headers + * iavf_cleanup_headers - Correct empty headers * @rx_ring: rx descriptor ring packet is being transacted on * @skb: pointer to current skb being fixed * @@ -1107,7 +1107,7 @@ void i40evf_process_skb_fields(struct i40e_ring *rx_ring, * * Returns true if an error was encountered and skb was freed. **/ -static bool i40e_cleanup_headers(struct i40e_ring *rx_ring, struct sk_buff *skb) +static bool iavf_cleanup_headers(struct iavf_ring *rx_ring, struct sk_buff *skb) { /* if eth_skb_pad returns an error the skb was freed */ if (eth_skb_pad(skb)) @@ -1117,16 +1117,16 @@ static bool i40e_cleanup_headers(struct i40e_ring *rx_ring, struct sk_buff *skb) } /** - * i40e_reuse_rx_page - page flip buffer and store it back on the ring + * iavf_reuse_rx_page - page flip buffer and store it back on the ring * @rx_ring: rx descriptor ring to store buffers on * @old_buff: donor buffer to have page reused * * Synchronizes page for reuse by the adapter **/ -static void i40e_reuse_rx_page(struct i40e_ring *rx_ring, - struct i40e_rx_buffer *old_buff) +static void iavf_reuse_rx_page(struct iavf_ring *rx_ring, + struct iavf_rx_buffer *old_buff) { - struct i40e_rx_buffer *new_buff; + struct iavf_rx_buffer *new_buff; u16 nta = rx_ring->next_to_alloc; new_buff = &rx_ring->rx_bi[nta]; @@ -1143,20 +1143,20 @@ static void i40e_reuse_rx_page(struct i40e_ring *rx_ring, } /** - * i40e_page_is_reusable - check if any reuse is possible + * iavf_page_is_reusable - check if any reuse is possible * @page: page struct to check * * A page is not reusable if it was allocated under low memory * conditions, or it's not in the same NUMA node as this CPU. */ -static inline bool i40e_page_is_reusable(struct page *page) +static inline bool iavf_page_is_reusable(struct page *page) { return (page_to_nid(page) == numa_mem_id()) && !page_is_pfmemalloc(page); } /** - * i40e_can_reuse_rx_page - Determine if this page can be reused by + * iavf_can_reuse_rx_page - Determine if this page can be reused by * the adapter for another receive * * @rx_buffer: buffer containing the page @@ -1182,13 +1182,13 @@ static inline bool i40e_page_is_reusable(struct page *page) * * In either case, if the page is reusable its refcount is increased. **/ -static bool i40e_can_reuse_rx_page(struct i40e_rx_buffer *rx_buffer) +static bool iavf_can_reuse_rx_page(struct iavf_rx_buffer *rx_buffer) { unsigned int pagecnt_bias = rx_buffer->pagecnt_bias; struct page *page = rx_buffer->page; /* Is any reuse possible? */ - if (unlikely(!i40e_page_is_reusable(page))) + if (unlikely(!iavf_page_is_reusable(page))) return false; #if (PAGE_SIZE < 8192) @@ -1196,9 +1196,9 @@ static bool i40e_can_reuse_rx_page(struct i40e_rx_buffer *rx_buffer) if (unlikely((page_count(page) - pagecnt_bias) > 1)) return false; #else -#define I40E_LAST_OFFSET \ - (SKB_WITH_OVERHEAD(PAGE_SIZE) - I40E_RXBUFFER_2048) - if (rx_buffer->page_offset > I40E_LAST_OFFSET) +#define IAVF_LAST_OFFSET \ + (SKB_WITH_OVERHEAD(PAGE_SIZE) - IAVF_RXBUFFER_2048) + if (rx_buffer->page_offset > IAVF_LAST_OFFSET) return false; #endif @@ -1215,7 +1215,7 @@ static bool i40e_can_reuse_rx_page(struct i40e_rx_buffer *rx_buffer) } /** - * i40e_add_rx_frag - Add contents of Rx buffer to sk_buff + * iavf_add_rx_frag - Add contents of Rx buffer to sk_buff * @rx_ring: rx descriptor ring to transact packets on * @rx_buffer: buffer containing page to add * @skb: sk_buff to place the data into @@ -1226,15 +1226,15 @@ static bool i40e_can_reuse_rx_page(struct i40e_rx_buffer *rx_buffer) * * The function will then update the page offset. **/ -static void i40e_add_rx_frag(struct i40e_ring *rx_ring, - struct i40e_rx_buffer *rx_buffer, +static void iavf_add_rx_frag(struct iavf_ring *rx_ring, + struct iavf_rx_buffer *rx_buffer, struct sk_buff *skb, unsigned int size) { #if (PAGE_SIZE < 8192) - unsigned int truesize = i40e_rx_pg_size(rx_ring) / 2; + unsigned int truesize = iavf_rx_pg_size(rx_ring) / 2; #else - unsigned int truesize = SKB_DATA_ALIGN(size + i40e_rx_offset(rx_ring)); + unsigned int truesize = SKB_DATA_ALIGN(size + iavf_rx_offset(rx_ring)); #endif skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags, rx_buffer->page, @@ -1249,17 +1249,17 @@ static void i40e_add_rx_frag(struct i40e_ring *rx_ring, } /** - * i40e_get_rx_buffer - Fetch Rx buffer and synchronize data for use + * iavf_get_rx_buffer - Fetch Rx buffer and synchronize data for use * @rx_ring: rx descriptor ring to transact packets on * @size: size of buffer to add to skb * * This function will pull an Rx buffer from the ring and synchronize it * for use by the CPU. */ -static struct i40e_rx_buffer *i40e_get_rx_buffer(struct i40e_ring *rx_ring, +static struct iavf_rx_buffer *iavf_get_rx_buffer(struct iavf_ring *rx_ring, const unsigned int size) { - struct i40e_rx_buffer *rx_buffer; + struct iavf_rx_buffer *rx_buffer; rx_buffer = &rx_ring->rx_bi[rx_ring->next_to_clean]; prefetchw(rx_buffer->page); @@ -1278,7 +1278,7 @@ static struct i40e_rx_buffer *i40e_get_rx_buffer(struct i40e_ring *rx_ring, } /** - * i40e_construct_skb - Allocate skb and populate it + * iavf_construct_skb - Allocate skb and populate it * @rx_ring: rx descriptor ring to transact packets on * @rx_buffer: rx buffer to pull data from * @size: size of buffer to add to skb @@ -1287,13 +1287,13 @@ static struct i40e_rx_buffer *i40e_get_rx_buffer(struct i40e_ring *rx_ring, * data from the current receive descriptor, taking care to set up the * skb correctly. */ -static struct sk_buff *i40e_construct_skb(struct i40e_ring *rx_ring, - struct i40e_rx_buffer *rx_buffer, +static struct sk_buff *iavf_construct_skb(struct iavf_ring *rx_ring, + struct iavf_rx_buffer *rx_buffer, unsigned int size) { void *va = page_address(rx_buffer->page) + rx_buffer->page_offset; #if (PAGE_SIZE < 8192) - unsigned int truesize = i40e_rx_pg_size(rx_ring) / 2; + unsigned int truesize = iavf_rx_pg_size(rx_ring) / 2; #else unsigned int truesize = SKB_DATA_ALIGN(size); #endif @@ -1308,15 +1308,15 @@ static struct sk_buff *i40e_construct_skb(struct i40e_ring *rx_ring, /* allocate a skb to store the frags */ skb = __napi_alloc_skb(&rx_ring->q_vector->napi, - I40E_RX_HDR_SIZE, + IAVF_RX_HDR_SIZE, GFP_ATOMIC | __GFP_NOWARN); if (unlikely(!skb)) return NULL; /* Determine available headroom for copy */ headlen = size; - if (headlen > I40E_RX_HDR_SIZE) - headlen = eth_get_headlen(va, I40E_RX_HDR_SIZE); + if (headlen > IAVF_RX_HDR_SIZE) + headlen = eth_get_headlen(va, IAVF_RX_HDR_SIZE); /* align pull length to size of long to optimize memcpy performance */ memcpy(__skb_put(skb, headlen), va, ALIGN(headlen, sizeof(long))); @@ -1343,7 +1343,7 @@ static struct sk_buff *i40e_construct_skb(struct i40e_ring *rx_ring, } /** - * i40e_build_skb - Build skb around an existing buffer + * iavf_build_skb - Build skb around an existing buffer * @rx_ring: Rx descriptor ring to transact packets on * @rx_buffer: Rx buffer to pull data from * @size: size of buffer to add to skb @@ -1351,16 +1351,16 @@ static struct sk_buff *i40e_construct_skb(struct i40e_ring *rx_ring, * This function builds an skb around an existing Rx buffer, taking care * to set up the skb correctly and avoid any memcpy overhead. */ -static struct sk_buff *i40e_build_skb(struct i40e_ring *rx_ring, - struct i40e_rx_buffer *rx_buffer, +static struct sk_buff *iavf_build_skb(struct iavf_ring *rx_ring, + struct iavf_rx_buffer *rx_buffer, unsigned int size) { void *va = page_address(rx_buffer->page) + rx_buffer->page_offset; #if (PAGE_SIZE < 8192) - unsigned int truesize = i40e_rx_pg_size(rx_ring) / 2; + unsigned int truesize = iavf_rx_pg_size(rx_ring) / 2; #else unsigned int truesize = SKB_DATA_ALIGN(sizeof(struct skb_shared_info)) + - SKB_DATA_ALIGN(I40E_SKB_PAD + size); + SKB_DATA_ALIGN(IAVF_SKB_PAD + size); #endif struct sk_buff *skb; @@ -1370,12 +1370,12 @@ static struct sk_buff *i40e_build_skb(struct i40e_ring *rx_ring, prefetch(va + L1_CACHE_BYTES); #endif /* build an skb around the page buffer */ - skb = build_skb(va - I40E_SKB_PAD, truesize); + skb = build_skb(va - IAVF_SKB_PAD, truesize); if (unlikely(!skb)) return NULL; /* update pointers within the skb to store the data */ - skb_reserve(skb, I40E_SKB_PAD); + skb_reserve(skb, IAVF_SKB_PAD); __skb_put(skb, size); /* buffer is used by skb, update page_offset */ @@ -1389,25 +1389,25 @@ static struct sk_buff *i40e_build_skb(struct i40e_ring *rx_ring, } /** - * i40e_put_rx_buffer - Clean up used buffer and either recycle or free + * iavf_put_rx_buffer - Clean up used buffer and either recycle or free * @rx_ring: rx descriptor ring to transact packets on * @rx_buffer: rx buffer to pull data from * * This function will clean up the contents of the rx_buffer. It will * either recycle the buffer or unmap it and free the associated resources. */ -static void i40e_put_rx_buffer(struct i40e_ring *rx_ring, - struct i40e_rx_buffer *rx_buffer) +static void iavf_put_rx_buffer(struct iavf_ring *rx_ring, + struct iavf_rx_buffer *rx_buffer) { - if (i40e_can_reuse_rx_page(rx_buffer)) { + if (iavf_can_reuse_rx_page(rx_buffer)) { /* hand second half of page back to the ring */ - i40e_reuse_rx_page(rx_ring, rx_buffer); + iavf_reuse_rx_page(rx_ring, rx_buffer); rx_ring->rx_stats.page_reuse_count++; } else { /* we are not reusing the buffer so unmap it */ dma_unmap_page_attrs(rx_ring->dev, rx_buffer->dma, - i40e_rx_pg_size(rx_ring), - DMA_FROM_DEVICE, I40E_RX_DMA_ATTR); + iavf_rx_pg_size(rx_ring), + DMA_FROM_DEVICE, IAVF_RX_DMA_ATTR); __page_frag_cache_drain(rx_buffer->page, rx_buffer->pagecnt_bias); } @@ -1417,7 +1417,7 @@ static void i40e_put_rx_buffer(struct i40e_ring *rx_ring, } /** - * i40e_is_non_eop - process handling of non-EOP buffers + * iavf_is_non_eop - process handling of non-EOP buffers * @rx_ring: Rx ring being processed * @rx_desc: Rx descriptor for current buffer * @skb: Current socket buffer containing buffer in progress @@ -1427,8 +1427,8 @@ static void i40e_put_rx_buffer(struct i40e_ring *rx_ring, * sk_buff in the next buffer to be chained and return true indicating * that this is in fact a non-EOP buffer. **/ -static bool i40e_is_non_eop(struct i40e_ring *rx_ring, - union i40e_rx_desc *rx_desc, +static bool iavf_is_non_eop(struct iavf_ring *rx_ring, + union iavf_rx_desc *rx_desc, struct sk_buff *skb) { u32 ntc = rx_ring->next_to_clean + 1; @@ -1437,11 +1437,11 @@ static bool i40e_is_non_eop(struct i40e_ring *rx_ring, ntc = (ntc < rx_ring->count) ? ntc : 0; rx_ring->next_to_clean = ntc; - prefetch(I40E_RX_DESC(rx_ring, ntc)); + prefetch(IAVF_RX_DESC(rx_ring, ntc)); /* if we are the last buffer then there is nothing else to do */ -#define I40E_RXD_EOF BIT(I40E_RX_DESC_STATUS_EOF_SHIFT) - if (likely(i40e_test_staterr(rx_desc, I40E_RXD_EOF))) +#define IAVF_RXD_EOF BIT(IAVF_RX_DESC_STATUS_EOF_SHIFT) + if (likely(iavf_test_staterr(rx_desc, IAVF_RXD_EOF))) return false; rx_ring->rx_stats.non_eop_descs++; @@ -1450,7 +1450,7 @@ static bool i40e_is_non_eop(struct i40e_ring *rx_ring, } /** - * i40e_clean_rx_irq - Clean completed descriptors from Rx ring - bounce buf + * iavf_clean_rx_irq - Clean completed descriptors from Rx ring - bounce buf * @rx_ring: rx descriptor ring to transact packets on * @budget: Total limit on number of packets to process * @@ -1461,29 +1461,29 @@ static bool i40e_is_non_eop(struct i40e_ring *rx_ring, * * Returns amount of work completed **/ -static int i40e_clean_rx_irq(struct i40e_ring *rx_ring, int budget) +static int iavf_clean_rx_irq(struct iavf_ring *rx_ring, int budget) { unsigned int total_rx_bytes = 0, total_rx_packets = 0; struct sk_buff *skb = rx_ring->skb; - u16 cleaned_count = I40E_DESC_UNUSED(rx_ring); + u16 cleaned_count = IAVF_DESC_UNUSED(rx_ring); bool failure = false; while (likely(total_rx_packets < (unsigned int)budget)) { - struct i40e_rx_buffer *rx_buffer; - union i40e_rx_desc *rx_desc; + struct iavf_rx_buffer *rx_buffer; + union iavf_rx_desc *rx_desc; unsigned int size; u16 vlan_tag; u8 rx_ptype; u64 qword; /* return some buffers to hardware, one at a time is too slow */ - if (cleaned_count >= I40E_RX_BUFFER_WRITE) { + if (cleaned_count >= IAVF_RX_BUFFER_WRITE) { failure = failure || - i40evf_alloc_rx_buffers(rx_ring, cleaned_count); + iavf_alloc_rx_buffers(rx_ring, cleaned_count); cleaned_count = 0; } - rx_desc = I40E_RX_DESC(rx_ring, rx_ring->next_to_clean); + rx_desc = IAVF_RX_DESC(rx_ring, rx_ring->next_to_clean); /* status_error_len will always be zero for unused descriptors * because it's cleared in cleanup, and overlaps with hdr_addr @@ -1498,21 +1498,21 @@ static int i40e_clean_rx_irq(struct i40e_ring *rx_ring, int budget) */ dma_rmb(); - size = (qword & I40E_RXD_QW1_LENGTH_PBUF_MASK) >> - I40E_RXD_QW1_LENGTH_PBUF_SHIFT; + size = (qword & IAVF_RXD_QW1_LENGTH_PBUF_MASK) >> + IAVF_RXD_QW1_LENGTH_PBUF_SHIFT; if (!size) break; - i40e_trace(clean_rx_irq, rx_ring, rx_desc, skb); - rx_buffer = i40e_get_rx_buffer(rx_ring, size); + iavf_trace(clean_rx_irq, rx_ring, rx_desc, skb); + rx_buffer = iavf_get_rx_buffer(rx_ring, size); /* retrieve a buffer from the ring */ if (skb) - i40e_add_rx_frag(rx_ring, rx_buffer, skb, size); + iavf_add_rx_frag(rx_ring, rx_buffer, skb, size); else if (ring_uses_build_skb(rx_ring)) - skb = i40e_build_skb(rx_ring, rx_buffer, size); + skb = iavf_build_skb(rx_ring, rx_buffer, size); else - skb = i40e_construct_skb(rx_ring, rx_buffer, size); + skb = iavf_construct_skb(rx_ring, rx_buffer, size); /* exit if we failed to retrieve a buffer */ if (!skb) { @@ -1521,24 +1521,24 @@ static int i40e_clean_rx_irq(struct i40e_ring *rx_ring, int budget) break; } - i40e_put_rx_buffer(rx_ring, rx_buffer); + iavf_put_rx_buffer(rx_ring, rx_buffer); cleaned_count++; - if (i40e_is_non_eop(rx_ring, rx_desc, skb)) + if (iavf_is_non_eop(rx_ring, rx_desc, skb)) continue; /* ERR_MASK will only have valid bits if EOP set, and * what we are doing here is actually checking - * I40E_RX_DESC_ERROR_RXE_SHIFT, since it is the zeroth bit in + * IAVF_RX_DESC_ERROR_RXE_SHIFT, since it is the zeroth bit in * the error field */ - if (unlikely(i40e_test_staterr(rx_desc, BIT(I40E_RXD_QW1_ERROR_SHIFT)))) { + if (unlikely(iavf_test_staterr(rx_desc, BIT(IAVF_RXD_QW1_ERROR_SHIFT)))) { dev_kfree_skb_any(skb); skb = NULL; continue; } - if (i40e_cleanup_headers(rx_ring, skb)) { + if (iavf_cleanup_headers(rx_ring, skb)) { skb = NULL; continue; } @@ -1547,18 +1547,18 @@ static int i40e_clean_rx_irq(struct i40e_ring *rx_ring, int budget) total_rx_bytes += skb->len; qword = le64_to_cpu(rx_desc->wb.qword1.status_error_len); - rx_ptype = (qword & I40E_RXD_QW1_PTYPE_MASK) >> - I40E_RXD_QW1_PTYPE_SHIFT; + rx_ptype = (qword & IAVF_RXD_QW1_PTYPE_MASK) >> + IAVF_RXD_QW1_PTYPE_SHIFT; /* populate checksum, VLAN, and protocol */ - i40evf_process_skb_fields(rx_ring, rx_desc, skb, rx_ptype); + iavf_process_skb_fields(rx_ring, rx_desc, skb, rx_ptype); - vlan_tag = (qword & BIT(I40E_RX_DESC_STATUS_L2TAG1P_SHIFT)) ? + vlan_tag = (qword & BIT(IAVF_RX_DESC_STATUS_L2TAG1P_SHIFT)) ? le16_to_cpu(rx_desc->wb.qword0.lo_dword.l2tag1) : 0; - i40e_trace(clean_rx_irq_rx, rx_ring, rx_desc, skb); - i40e_receive_skb(rx_ring, skb, vlan_tag); + iavf_trace(clean_rx_irq_rx, rx_ring, rx_desc, skb); + iavf_receive_skb(rx_ring, skb, vlan_tag); skb = NULL; /* update budget accounting */ @@ -1578,7 +1578,7 @@ static int i40e_clean_rx_irq(struct i40e_ring *rx_ring, int budget) return failure ? budget : (int)total_rx_packets; } -static inline u32 i40e_buildreg_itr(const int type, u16 itr) +static inline u32 iavf_buildreg_itr(const int type, u16 itr) { u32 val; @@ -1597,17 +1597,17 @@ static inline u32 i40e_buildreg_itr(const int type, u16 itr) * only need to shift by the interval shift - 1 instead of the * full value. */ - itr &= I40E_ITR_MASK; + itr &= IAVF_ITR_MASK; - val = I40E_VFINT_DYN_CTLN1_INTENA_MASK | - (type << I40E_VFINT_DYN_CTLN1_ITR_INDX_SHIFT) | - (itr << (I40E_VFINT_DYN_CTLN1_INTERVAL_SHIFT - 1)); + val = IAVF_VFINT_DYN_CTLN1_INTENA_MASK | + (type << IAVF_VFINT_DYN_CTLN1_ITR_INDX_SHIFT) | + (itr << (IAVF_VFINT_DYN_CTLN1_INTERVAL_SHIFT - 1)); return val; } /* a small macro to shorten up some long lines */ -#define INTREG I40E_VFINT_DYN_CTLN1 +#define INTREG IAVF_VFINT_DYN_CTLN1 /* The act of updating the ITR will cause it to immediately trigger. In order * to prevent this from throwing off adaptive update statistics we defer the @@ -1619,20 +1619,20 @@ static inline u32 i40e_buildreg_itr(const int type, u16 itr) #define ITR_COUNTDOWN_START 3 /** - * i40e_update_enable_itr - Update itr and re-enable MSIX interrupt + * iavf_update_enable_itr - Update itr and re-enable MSIX interrupt * @vsi: the VSI we care about * @q_vector: q_vector for which itr is being updated and interrupt enabled * **/ -static inline void i40e_update_enable_itr(struct i40e_vsi *vsi, - struct i40e_q_vector *q_vector) +static inline void iavf_update_enable_itr(struct iavf_vsi *vsi, + struct iavf_q_vector *q_vector) { - struct i40e_hw *hw = &vsi->back->hw; + struct iavf_hw *hw = &vsi->back->hw; u32 intval; /* These will do nothing if dynamic updates are not enabled */ - i40e_update_itr(q_vector, &q_vector->tx); - i40e_update_itr(q_vector, &q_vector->rx); + iavf_update_itr(q_vector, &q_vector->tx); + iavf_update_itr(q_vector, &q_vector->rx); /* This block of logic allows us to get away with only updating * one ITR value with each interrupt. The idea is to perform a @@ -1644,7 +1644,7 @@ static inline void i40e_update_enable_itr(struct i40e_vsi *vsi, */ if (q_vector->rx.target_itr < q_vector->rx.current_itr) { /* Rx ITR needs to be reduced, this is highest priority */ - intval = i40e_buildreg_itr(I40E_RX_ITR, + intval = iavf_buildreg_itr(IAVF_RX_ITR, q_vector->rx.target_itr); q_vector->rx.current_itr = q_vector->rx.target_itr; q_vector->itr_countdown = ITR_COUNTDOWN_START; @@ -1654,29 +1654,29 @@ static inline void i40e_update_enable_itr(struct i40e_vsi *vsi, /* Tx ITR needs to be reduced, this is second priority * Tx ITR needs to be increased more than Rx, fourth priority */ - intval = i40e_buildreg_itr(I40E_TX_ITR, + intval = iavf_buildreg_itr(IAVF_TX_ITR, q_vector->tx.target_itr); q_vector->tx.current_itr = q_vector->tx.target_itr; q_vector->itr_countdown = ITR_COUNTDOWN_START; } else if (q_vector->rx.current_itr != q_vector->rx.target_itr) { /* Rx ITR needs to be increased, third priority */ - intval = i40e_buildreg_itr(I40E_RX_ITR, + intval = iavf_buildreg_itr(IAVF_RX_ITR, q_vector->rx.target_itr); q_vector->rx.current_itr = q_vector->rx.target_itr; q_vector->itr_countdown = ITR_COUNTDOWN_START; } else { /* No ITR update, lowest priority */ - intval = i40e_buildreg_itr(I40E_ITR_NONE, 0); + intval = iavf_buildreg_itr(IAVF_ITR_NONE, 0); if (q_vector->itr_countdown) q_vector->itr_countdown--; } - if (!test_bit(__I40E_VSI_DOWN, vsi->state)) + if (!test_bit(__IAVF_VSI_DOWN, vsi->state)) wr32(hw, INTREG(q_vector->reg_idx), intval); } /** - * i40evf_napi_poll - NAPI polling Rx/Tx cleanup routine + * iavf_napi_poll - NAPI polling Rx/Tx cleanup routine * @napi: napi struct with our devices info in it * @budget: amount of work driver is allowed to do this pass, in packets * @@ -1684,18 +1684,18 @@ static inline void i40e_update_enable_itr(struct i40e_vsi *vsi, * * Returns the amount of work done **/ -int i40evf_napi_poll(struct napi_struct *napi, int budget) +int iavf_napi_poll(struct napi_struct *napi, int budget) { - struct i40e_q_vector *q_vector = - container_of(napi, struct i40e_q_vector, napi); - struct i40e_vsi *vsi = q_vector->vsi; - struct i40e_ring *ring; + struct iavf_q_vector *q_vector = + container_of(napi, struct iavf_q_vector, napi); + struct iavf_vsi *vsi = q_vector->vsi; + struct iavf_ring *ring; bool clean_complete = true; bool arm_wb = false; int budget_per_ring; int work_done = 0; - if (test_bit(__I40E_VSI_DOWN, vsi->state)) { + if (test_bit(__IAVF_VSI_DOWN, vsi->state)) { napi_complete(napi); return 0; } @@ -1703,8 +1703,8 @@ int i40evf_napi_poll(struct napi_struct *napi, int budget) /* Since the actual Tx work is minimal, we can give the Tx a larger * budget and be more aggressive about cleaning up the Tx descriptors. */ - i40e_for_each_ring(ring, q_vector->tx) { - if (!i40e_clean_tx_irq(vsi, ring, budget)) { + iavf_for_each_ring(ring, q_vector->tx) { + if (!iavf_clean_tx_irq(vsi, ring, budget)) { clean_complete = false; continue; } @@ -1721,8 +1721,8 @@ int i40evf_napi_poll(struct napi_struct *napi, int budget) */ budget_per_ring = max(budget/q_vector->num_ringpairs, 1); - i40e_for_each_ring(ring, q_vector->rx) { - int cleaned = i40e_clean_rx_irq(ring, budget_per_ring); + iavf_for_each_ring(ring, q_vector->rx) { + int cleaned = iavf_clean_rx_irq(ring, budget_per_ring); work_done += cleaned; /* if we clean as many as budgeted, we must not be done */ @@ -1746,7 +1746,7 @@ int i40evf_napi_poll(struct napi_struct *napi, int budget) napi_complete_done(napi, work_done); /* Force an interrupt */ - i40evf_force_wb(vsi, q_vector); + iavf_force_wb(vsi, q_vector); /* Return budget-1 so that polling stops */ return budget - 1; @@ -1754,24 +1754,24 @@ int i40evf_napi_poll(struct napi_struct *napi, int budget) tx_only: if (arm_wb) { q_vector->tx.ring[0].tx_stats.tx_force_wb++; - i40e_enable_wb_on_itr(vsi, q_vector); + iavf_enable_wb_on_itr(vsi, q_vector); } return budget; } - if (vsi->back->flags & I40E_TXR_FLAGS_WB_ON_ITR) + if (vsi->back->flags & IAVF_TXR_FLAGS_WB_ON_ITR) q_vector->arm_wb_state = false; /* Work is done so exit the polling mode and re-enable the interrupt */ napi_complete_done(napi, work_done); - i40e_update_enable_itr(vsi, q_vector); + iavf_update_enable_itr(vsi, q_vector); return min(work_done, budget - 1); } /** - * i40evf_tx_prepare_vlan_flags - prepare generic TX VLAN tagging flags for HW + * iavf_tx_prepare_vlan_flags - prepare generic TX VLAN tagging flags for HW * @skb: send buffer * @tx_ring: ring to send buffer on * @flags: the tx flags to be set @@ -1782,9 +1782,9 @@ tx_only: * Returns error code indicate the frame should be dropped upon error and the * otherwise returns 0 to indicate the flags has been set properly. **/ -static inline int i40evf_tx_prepare_vlan_flags(struct sk_buff *skb, - struct i40e_ring *tx_ring, - u32 *flags) +static inline int iavf_tx_prepare_vlan_flags(struct sk_buff *skb, + struct iavf_ring *tx_ring, + u32 *flags) { __be16 protocol = skb->protocol; u32 tx_flags = 0; @@ -1804,8 +1804,8 @@ static inline int i40evf_tx_prepare_vlan_flags(struct sk_buff *skb, /* if we have a HW VLAN tag being added, default to the HW one */ if (skb_vlan_tag_present(skb)) { - tx_flags |= skb_vlan_tag_get(skb) << I40E_TX_FLAGS_VLAN_SHIFT; - tx_flags |= I40E_TX_FLAGS_HW_VLAN; + tx_flags |= skb_vlan_tag_get(skb) << IAVF_TX_FLAGS_VLAN_SHIFT; + tx_flags |= IAVF_TX_FLAGS_HW_VLAN; /* else if it is a SW VLAN, check the next protocol and store the tag */ } else if (protocol == htons(ETH_P_8021Q)) { struct vlan_hdr *vhdr, _vhdr; @@ -1815,8 +1815,8 @@ static inline int i40evf_tx_prepare_vlan_flags(struct sk_buff *skb, return -EINVAL; protocol = vhdr->h_vlan_encapsulated_proto; - tx_flags |= ntohs(vhdr->h_vlan_TCI) << I40E_TX_FLAGS_VLAN_SHIFT; - tx_flags |= I40E_TX_FLAGS_SW_VLAN; + tx_flags |= ntohs(vhdr->h_vlan_TCI) << IAVF_TX_FLAGS_VLAN_SHIFT; + tx_flags |= IAVF_TX_FLAGS_SW_VLAN; } out: @@ -1825,14 +1825,14 @@ out: } /** - * i40e_tso - set up the tso context descriptor + * iavf_tso - set up the tso context descriptor * @first: pointer to first Tx buffer for xmit * @hdr_len: ptr to the size of the packet header * @cd_type_cmd_tso_mss: Quad Word 1 * * Returns 0 if no TSO can happen, 1 if tso is going, or error **/ -static int i40e_tso(struct i40e_tx_buffer *first, u8 *hdr_len, +static int iavf_tso(struct iavf_tx_buffer *first, u8 *hdr_len, u64 *cd_type_cmd_tso_mss) { struct sk_buff *skb = first->skb; @@ -1923,17 +1923,17 @@ static int i40e_tso(struct i40e_tx_buffer *first, u8 *hdr_len, first->bytecount += (first->gso_segs - 1) * *hdr_len; /* find the field values */ - cd_cmd = I40E_TX_CTX_DESC_TSO; + cd_cmd = IAVF_TX_CTX_DESC_TSO; cd_tso_len = skb->len - *hdr_len; cd_mss = gso_size; - *cd_type_cmd_tso_mss |= (cd_cmd << I40E_TXD_CTX_QW1_CMD_SHIFT) | - (cd_tso_len << I40E_TXD_CTX_QW1_TSO_LEN_SHIFT) | - (cd_mss << I40E_TXD_CTX_QW1_MSS_SHIFT); + *cd_type_cmd_tso_mss |= (cd_cmd << IAVF_TXD_CTX_QW1_CMD_SHIFT) | + (cd_tso_len << IAVF_TXD_CTX_QW1_TSO_LEN_SHIFT) | + (cd_mss << IAVF_TXD_CTX_QW1_MSS_SHIFT); return 1; } /** - * i40e_tx_enable_csum - Enable Tx checksum offloads + * iavf_tx_enable_csum - Enable Tx checksum offloads * @skb: send buffer * @tx_flags: pointer to Tx flags currently set * @td_cmd: Tx descriptor command bits to set @@ -1941,9 +1941,9 @@ static int i40e_tso(struct i40e_tx_buffer *first, u8 *hdr_len, * @tx_ring: Tx descriptor ring * @cd_tunneling: ptr to context desc bits **/ -static int i40e_tx_enable_csum(struct sk_buff *skb, u32 *tx_flags, +static int iavf_tx_enable_csum(struct sk_buff *skb, u32 *tx_flags, u32 *td_cmd, u32 *td_offset, - struct i40e_ring *tx_ring, + struct iavf_ring *tx_ring, u32 *cd_tunneling) { union { @@ -1968,19 +1968,19 @@ static int i40e_tx_enable_csum(struct sk_buff *skb, u32 *tx_flags, l4.hdr = skb_transport_header(skb); /* compute outer L2 header size */ - offset = ((ip.hdr - skb->data) / 2) << I40E_TX_DESC_LENGTH_MACLEN_SHIFT; + offset = ((ip.hdr - skb->data) / 2) << IAVF_TX_DESC_LENGTH_MACLEN_SHIFT; if (skb->encapsulation) { u32 tunnel = 0; /* define outer network header type */ - if (*tx_flags & I40E_TX_FLAGS_IPV4) { - tunnel |= (*tx_flags & I40E_TX_FLAGS_TSO) ? - I40E_TX_CTX_EXT_IP_IPV4 : - I40E_TX_CTX_EXT_IP_IPV4_NO_CSUM; + if (*tx_flags & IAVF_TX_FLAGS_IPV4) { + tunnel |= (*tx_flags & IAVF_TX_FLAGS_TSO) ? + IAVF_TX_CTX_EXT_IP_IPV4 : + IAVF_TX_CTX_EXT_IP_IPV4_NO_CSUM; l4_proto = ip.v4->protocol; - } else if (*tx_flags & I40E_TX_FLAGS_IPV6) { - tunnel |= I40E_TX_CTX_EXT_IP_IPV6; + } else if (*tx_flags & IAVF_TX_FLAGS_IPV6) { + tunnel |= IAVF_TX_CTX_EXT_IP_IPV6; exthdr = ip.hdr + sizeof(*ip.v6); l4_proto = ip.v6->nexthdr; @@ -1992,20 +1992,20 @@ static int i40e_tx_enable_csum(struct sk_buff *skb, u32 *tx_flags, /* define outer transport */ switch (l4_proto) { case IPPROTO_UDP: - tunnel |= I40E_TXD_CTX_UDP_TUNNELING; - *tx_flags |= I40E_TX_FLAGS_VXLAN_TUNNEL; + tunnel |= IAVF_TXD_CTX_UDP_TUNNELING; + *tx_flags |= IAVF_TX_FLAGS_VXLAN_TUNNEL; break; case IPPROTO_GRE: - tunnel |= I40E_TXD_CTX_GRE_TUNNELING; - *tx_flags |= I40E_TX_FLAGS_VXLAN_TUNNEL; + tunnel |= IAVF_TXD_CTX_GRE_TUNNELING; + *tx_flags |= IAVF_TX_FLAGS_VXLAN_TUNNEL; break; case IPPROTO_IPIP: case IPPROTO_IPV6: - *tx_flags |= I40E_TX_FLAGS_VXLAN_TUNNEL; + *tx_flags |= IAVF_TX_FLAGS_VXLAN_TUNNEL; l4.hdr = skb_inner_network_header(skb); break; default: - if (*tx_flags & I40E_TX_FLAGS_TSO) + if (*tx_flags & IAVF_TX_FLAGS_TSO) return -1; skb_checksum_help(skb); @@ -2014,20 +2014,20 @@ static int i40e_tx_enable_csum(struct sk_buff *skb, u32 *tx_flags, /* compute outer L3 header size */ tunnel |= ((l4.hdr - ip.hdr) / 4) << - I40E_TXD_CTX_QW0_EXT_IPLEN_SHIFT; + IAVF_TXD_CTX_QW0_EXT_IPLEN_SHIFT; /* switch IP header pointer from outer to inner header */ ip.hdr = skb_inner_network_header(skb); /* compute tunnel header size */ tunnel |= ((ip.hdr - l4.hdr) / 2) << - I40E_TXD_CTX_QW0_NATLEN_SHIFT; + IAVF_TXD_CTX_QW0_NATLEN_SHIFT; /* indicate if we need to offload outer UDP header */ - if ((*tx_flags & I40E_TX_FLAGS_TSO) && + if ((*tx_flags & IAVF_TX_FLAGS_TSO) && !(skb_shinfo(skb)->gso_type & SKB_GSO_PARTIAL) && (skb_shinfo(skb)->gso_type & SKB_GSO_UDP_TUNNEL_CSUM)) - tunnel |= I40E_TXD_CTX_QW0_L4T_CS_MASK; + tunnel |= IAVF_TXD_CTX_QW0_L4T_CS_MASK; /* record tunnel offload values */ *cd_tunneling |= tunnel; @@ -2037,24 +2037,24 @@ static int i40e_tx_enable_csum(struct sk_buff *skb, u32 *tx_flags, l4_proto = 0; /* reset type as we transition from outer to inner headers */ - *tx_flags &= ~(I40E_TX_FLAGS_IPV4 | I40E_TX_FLAGS_IPV6); + *tx_flags &= ~(IAVF_TX_FLAGS_IPV4 | IAVF_TX_FLAGS_IPV6); if (ip.v4->version == 4) - *tx_flags |= I40E_TX_FLAGS_IPV4; + *tx_flags |= IAVF_TX_FLAGS_IPV4; if (ip.v6->version == 6) - *tx_flags |= I40E_TX_FLAGS_IPV6; + *tx_flags |= IAVF_TX_FLAGS_IPV6; } /* Enable IP checksum offloads */ - if (*tx_flags & I40E_TX_FLAGS_IPV4) { + if (*tx_flags & IAVF_TX_FLAGS_IPV4) { l4_proto = ip.v4->protocol; /* the stack computes the IP header already, the only time we * need the hardware to recompute it is in the case of TSO. */ - cmd |= (*tx_flags & I40E_TX_FLAGS_TSO) ? - I40E_TX_DESC_CMD_IIPT_IPV4_CSUM : - I40E_TX_DESC_CMD_IIPT_IPV4; - } else if (*tx_flags & I40E_TX_FLAGS_IPV6) { - cmd |= I40E_TX_DESC_CMD_IIPT_IPV6; + cmd |= (*tx_flags & IAVF_TX_FLAGS_TSO) ? + IAVF_TX_DESC_CMD_IIPT_IPV4_CSUM : + IAVF_TX_DESC_CMD_IIPT_IPV4; + } else if (*tx_flags & IAVF_TX_FLAGS_IPV6) { + cmd |= IAVF_TX_DESC_CMD_IIPT_IPV6; exthdr = ip.hdr + sizeof(*ip.v6); l4_proto = ip.v6->nexthdr; @@ -2064,29 +2064,29 @@ static int i40e_tx_enable_csum(struct sk_buff *skb, u32 *tx_flags, } /* compute inner L3 header size */ - offset |= ((l4.hdr - ip.hdr) / 4) << I40E_TX_DESC_LENGTH_IPLEN_SHIFT; + offset |= ((l4.hdr - ip.hdr) / 4) << IAVF_TX_DESC_LENGTH_IPLEN_SHIFT; /* Enable L4 checksum offloads */ switch (l4_proto) { case IPPROTO_TCP: /* enable checksum offloads */ - cmd |= I40E_TX_DESC_CMD_L4T_EOFT_TCP; - offset |= l4.tcp->doff << I40E_TX_DESC_LENGTH_L4_FC_LEN_SHIFT; + cmd |= IAVF_TX_DESC_CMD_L4T_EOFT_TCP; + offset |= l4.tcp->doff << IAVF_TX_DESC_LENGTH_L4_FC_LEN_SHIFT; break; case IPPROTO_SCTP: /* enable SCTP checksum offload */ - cmd |= I40E_TX_DESC_CMD_L4T_EOFT_SCTP; + cmd |= IAVF_TX_DESC_CMD_L4T_EOFT_SCTP; offset |= (sizeof(struct sctphdr) >> 2) << - I40E_TX_DESC_LENGTH_L4_FC_LEN_SHIFT; + IAVF_TX_DESC_LENGTH_L4_FC_LEN_SHIFT; break; case IPPROTO_UDP: /* enable UDP checksum offload */ - cmd |= I40E_TX_DESC_CMD_L4T_EOFT_UDP; + cmd |= IAVF_TX_DESC_CMD_L4T_EOFT_UDP; offset |= (sizeof(struct udphdr) >> 2) << - I40E_TX_DESC_LENGTH_L4_FC_LEN_SHIFT; + IAVF_TX_DESC_LENGTH_L4_FC_LEN_SHIFT; break; default: - if (*tx_flags & I40E_TX_FLAGS_TSO) + if (*tx_flags & IAVF_TX_FLAGS_TSO) return -1; skb_checksum_help(skb); return 0; @@ -2099,25 +2099,25 @@ static int i40e_tx_enable_csum(struct sk_buff *skb, u32 *tx_flags, } /** - * i40e_create_tx_ctx Build the Tx context descriptor + * iavf_create_tx_ctx Build the Tx context descriptor * @tx_ring: ring to create the descriptor on * @cd_type_cmd_tso_mss: Quad Word 1 * @cd_tunneling: Quad Word 0 - bits 0-31 * @cd_l2tag2: Quad Word 0 - bits 32-63 **/ -static void i40e_create_tx_ctx(struct i40e_ring *tx_ring, +static void iavf_create_tx_ctx(struct iavf_ring *tx_ring, const u64 cd_type_cmd_tso_mss, const u32 cd_tunneling, const u32 cd_l2tag2) { - struct i40e_tx_context_desc *context_desc; + struct iavf_tx_context_desc *context_desc; int i = tx_ring->next_to_use; - if ((cd_type_cmd_tso_mss == I40E_TX_DESC_DTYPE_CONTEXT) && + if ((cd_type_cmd_tso_mss == IAVF_TX_DESC_DTYPE_CONTEXT) && !cd_tunneling && !cd_l2tag2) return; /* grab the next descriptor */ - context_desc = I40E_TX_CTXTDESC(tx_ring, i); + context_desc = IAVF_TX_CTXTDESC(tx_ring, i); i++; tx_ring->next_to_use = (i < tx_ring->count) ? i : 0; @@ -2130,7 +2130,7 @@ static void i40e_create_tx_ctx(struct i40e_ring *tx_ring, } /** - * __i40evf_chk_linearize - Check if there are more than 8 buffers per packet + * __iavf_chk_linearize - Check if there are more than 8 buffers per packet * @skb: send buffer * * Note: Our HW can't DMA more than 8 buffers to build a packet on the wire @@ -2142,20 +2142,20 @@ static void i40e_create_tx_ctx(struct i40e_ring *tx_ring, * the segment payload in the first descriptor, and another 7 for the * fragments. **/ -bool __i40evf_chk_linearize(struct sk_buff *skb) +bool __iavf_chk_linearize(struct sk_buff *skb) { const struct skb_frag_struct *frag, *stale; int nr_frags, sum; /* no need to check if number of frags is less than 7 */ nr_frags = skb_shinfo(skb)->nr_frags; - if (nr_frags < (I40E_MAX_BUFFER_TXD - 1)) + if (nr_frags < (IAVF_MAX_BUFFER_TXD - 1)) return false; /* We need to walk through the list and validate that each group * of 6 fragments totals at least gso_size. */ - nr_frags -= I40E_MAX_BUFFER_TXD - 2; + nr_frags -= IAVF_MAX_BUFFER_TXD - 2; frag = &skb_shinfo(skb)->frags[0]; /* Initialize size to the negative value of gso_size minus 1. We @@ -2187,17 +2187,17 @@ bool __i40evf_chk_linearize(struct sk_buff *skb) * figure out what the remainder would be in the last * descriptor associated with the fragment. */ - if (stale_size > I40E_MAX_DATA_PER_TXD) { + if (stale_size > IAVF_MAX_DATA_PER_TXD) { int align_pad = -(stale->page_offset) & - (I40E_MAX_READ_REQ_SIZE - 1); + (IAVF_MAX_READ_REQ_SIZE - 1); sum -= align_pad; stale_size -= align_pad; do { - sum -= I40E_MAX_DATA_PER_TXD_ALIGNED; - stale_size -= I40E_MAX_DATA_PER_TXD_ALIGNED; - } while (stale_size > I40E_MAX_DATA_PER_TXD); + sum -= IAVF_MAX_DATA_PER_TXD_ALIGNED; + stale_size -= IAVF_MAX_DATA_PER_TXD_ALIGNED; + } while (stale_size > IAVF_MAX_DATA_PER_TXD); } /* if sum is negative we failed to make sufficient progress */ @@ -2214,20 +2214,20 @@ bool __i40evf_chk_linearize(struct sk_buff *skb) } /** - * __i40evf_maybe_stop_tx - 2nd level check for tx stop conditions + * __iavf_maybe_stop_tx - 2nd level check for tx stop conditions * @tx_ring: the ring to be checked * @size: the size buffer we want to assure is available * * Returns -EBUSY if a stop is needed, else 0 **/ -int __i40evf_maybe_stop_tx(struct i40e_ring *tx_ring, int size) +int __iavf_maybe_stop_tx(struct iavf_ring *tx_ring, int size) { netif_stop_subqueue(tx_ring->netdev, tx_ring->queue_index); /* Memory barrier before checking head and tail */ smp_mb(); /* Check again in a case another CPU has just made room available. */ - if (likely(I40E_DESC_UNUSED(tx_ring) < size)) + if (likely(IAVF_DESC_UNUSED(tx_ring) < size)) return -EBUSY; /* A reprieve! - use start_queue because it doesn't call schedule */ @@ -2237,7 +2237,7 @@ int __i40evf_maybe_stop_tx(struct i40e_ring *tx_ring, int size) } /** - * i40evf_tx_map - Build the Tx descriptor + * iavf_tx_map - Build the Tx descriptor * @tx_ring: ring to send buffer on * @skb: send buffer * @first: first buffer info buffer to use @@ -2246,34 +2246,34 @@ int __i40evf_maybe_stop_tx(struct i40e_ring *tx_ring, int size) * @td_cmd: the command field in the descriptor * @td_offset: offset for checksum or crc **/ -static inline void i40evf_tx_map(struct i40e_ring *tx_ring, struct sk_buff *skb, - struct i40e_tx_buffer *first, u32 tx_flags, - const u8 hdr_len, u32 td_cmd, u32 td_offset) +static inline void iavf_tx_map(struct iavf_ring *tx_ring, struct sk_buff *skb, + struct iavf_tx_buffer *first, u32 tx_flags, + const u8 hdr_len, u32 td_cmd, u32 td_offset) { unsigned int data_len = skb->data_len; unsigned int size = skb_headlen(skb); struct skb_frag_struct *frag; - struct i40e_tx_buffer *tx_bi; - struct i40e_tx_desc *tx_desc; + struct iavf_tx_buffer *tx_bi; + struct iavf_tx_desc *tx_desc; u16 i = tx_ring->next_to_use; u32 td_tag = 0; dma_addr_t dma; - if (tx_flags & I40E_TX_FLAGS_HW_VLAN) { - td_cmd |= I40E_TX_DESC_CMD_IL2TAG1; - td_tag = (tx_flags & I40E_TX_FLAGS_VLAN_MASK) >> - I40E_TX_FLAGS_VLAN_SHIFT; + if (tx_flags & IAVF_TX_FLAGS_HW_VLAN) { + td_cmd |= IAVF_TX_DESC_CMD_IL2TAG1; + td_tag = (tx_flags & IAVF_TX_FLAGS_VLAN_MASK) >> + IAVF_TX_FLAGS_VLAN_SHIFT; } first->tx_flags = tx_flags; dma = dma_map_single(tx_ring->dev, skb->data, size, DMA_TO_DEVICE); - tx_desc = I40E_TX_DESC(tx_ring, i); + tx_desc = IAVF_TX_DESC(tx_ring, i); tx_bi = first; for (frag = &skb_shinfo(skb)->frags[0];; frag++) { - unsigned int max_data = I40E_MAX_DATA_PER_TXD_ALIGNED; + unsigned int max_data = IAVF_MAX_DATA_PER_TXD_ALIGNED; if (dma_mapping_error(tx_ring->dev, dma)) goto dma_error; @@ -2283,10 +2283,10 @@ static inline void i40evf_tx_map(struct i40e_ring *tx_ring, struct sk_buff *skb, dma_unmap_addr_set(tx_bi, dma, dma); /* align size to end of page */ - max_data += -dma & (I40E_MAX_READ_REQ_SIZE - 1); + max_data += -dma & (IAVF_MAX_READ_REQ_SIZE - 1); tx_desc->buffer_addr = cpu_to_le64(dma); - while (unlikely(size > I40E_MAX_DATA_PER_TXD)) { + while (unlikely(size > IAVF_MAX_DATA_PER_TXD)) { tx_desc->cmd_type_offset_bsz = build_ctob(td_cmd, td_offset, max_data, td_tag); @@ -2295,14 +2295,14 @@ static inline void i40evf_tx_map(struct i40e_ring *tx_ring, struct sk_buff *skb, i++; if (i == tx_ring->count) { - tx_desc = I40E_TX_DESC(tx_ring, 0); + tx_desc = IAVF_TX_DESC(tx_ring, 0); i = 0; } dma += max_data; size -= max_data; - max_data = I40E_MAX_DATA_PER_TXD_ALIGNED; + max_data = IAVF_MAX_DATA_PER_TXD_ALIGNED; tx_desc->buffer_addr = cpu_to_le64(dma); } @@ -2316,7 +2316,7 @@ static inline void i40evf_tx_map(struct i40e_ring *tx_ring, struct sk_buff *skb, i++; if (i == tx_ring->count) { - tx_desc = I40E_TX_DESC(tx_ring, 0); + tx_desc = IAVF_TX_DESC(tx_ring, 0); i = 0; } @@ -2337,10 +2337,10 @@ static inline void i40evf_tx_map(struct i40e_ring *tx_ring, struct sk_buff *skb, tx_ring->next_to_use = i; - i40e_maybe_stop_tx(tx_ring, DESC_NEEDED); + iavf_maybe_stop_tx(tx_ring, DESC_NEEDED); /* write last descriptor with RS and EOP bits */ - td_cmd |= I40E_TXD_CMD; + td_cmd |= IAVF_TXD_CMD; tx_desc->cmd_type_offset_bsz = build_ctob(td_cmd, td_offset, size, td_tag); @@ -2373,7 +2373,7 @@ dma_error: /* clear dma mappings for failed tx_bi map */ for (;;) { tx_bi = &tx_ring->tx_bi[i]; - i40e_unmap_and_free_tx_resource(tx_ring, tx_bi); + iavf_unmap_and_free_tx_resource(tx_ring, tx_bi); if (tx_bi == first) break; if (i == 0) @@ -2385,18 +2385,18 @@ dma_error: } /** - * i40e_xmit_frame_ring - Sends buffer on Tx ring + * iavf_xmit_frame_ring - Sends buffer on Tx ring * @skb: send buffer * @tx_ring: ring to send buffer on * * Returns NETDEV_TX_OK if sent, else an error code **/ -static netdev_tx_t i40e_xmit_frame_ring(struct sk_buff *skb, - struct i40e_ring *tx_ring) +static netdev_tx_t iavf_xmit_frame_ring(struct sk_buff *skb, + struct iavf_ring *tx_ring) { - u64 cd_type_cmd_tso_mss = I40E_TX_DESC_DTYPE_CONTEXT; + u64 cd_type_cmd_tso_mss = IAVF_TX_DESC_DTYPE_CONTEXT; u32 cd_tunneling = 0, cd_l2tag2 = 0; - struct i40e_tx_buffer *first; + struct iavf_tx_buffer *first; u32 td_offset = 0; u32 tx_flags = 0; __be16 protocol; @@ -2407,25 +2407,25 @@ static netdev_tx_t i40e_xmit_frame_ring(struct sk_buff *skb, /* prefetch the data, we'll need it later */ prefetch(skb->data); - i40e_trace(xmit_frame_ring, skb, tx_ring); + iavf_trace(xmit_frame_ring, skb, tx_ring); - count = i40e_xmit_descriptor_count(skb); - if (i40e_chk_linearize(skb, count)) { + count = iavf_xmit_descriptor_count(skb); + if (iavf_chk_linearize(skb, count)) { if (__skb_linearize(skb)) { dev_kfree_skb_any(skb); return NETDEV_TX_OK; } - count = i40e_txd_use_count(skb->len); + count = iavf_txd_use_count(skb->len); tx_ring->tx_stats.tx_linearize++; } - /* need: 1 descriptor per page * PAGE_SIZE/I40E_MAX_DATA_PER_TXD, - * + 1 desc for skb_head_len/I40E_MAX_DATA_PER_TXD, + /* need: 1 descriptor per page * PAGE_SIZE/IAVF_MAX_DATA_PER_TXD, + * + 1 desc for skb_head_len/IAVF_MAX_DATA_PER_TXD, * + 4 desc gap to avoid the cache line where head is, * + 1 desc for context descriptor, * otherwise try next time */ - if (i40e_maybe_stop_tx(tx_ring, count + 4 + 1)) { + if (iavf_maybe_stop_tx(tx_ring, count + 4 + 1)) { tx_ring->tx_stats.tx_busy++; return NETDEV_TX_BUSY; } @@ -2437,7 +2437,7 @@ static netdev_tx_t i40e_xmit_frame_ring(struct sk_buff *skb, first->gso_segs = 1; /* prepare the xmit flags */ - if (i40evf_tx_prepare_vlan_flags(skb, tx_ring, &tx_flags)) + if (iavf_tx_prepare_vlan_flags(skb, tx_ring, &tx_flags)) goto out_drop; /* obtain protocol of skb */ @@ -2445,19 +2445,19 @@ static netdev_tx_t i40e_xmit_frame_ring(struct sk_buff *skb, /* setup IPv4/IPv6 offloads */ if (protocol == htons(ETH_P_IP)) - tx_flags |= I40E_TX_FLAGS_IPV4; + tx_flags |= IAVF_TX_FLAGS_IPV4; else if (protocol == htons(ETH_P_IPV6)) - tx_flags |= I40E_TX_FLAGS_IPV6; + tx_flags |= IAVF_TX_FLAGS_IPV6; - tso = i40e_tso(first, &hdr_len, &cd_type_cmd_tso_mss); + tso = iavf_tso(first, &hdr_len, &cd_type_cmd_tso_mss); if (tso < 0) goto out_drop; else if (tso) - tx_flags |= I40E_TX_FLAGS_TSO; + tx_flags |= IAVF_TX_FLAGS_TSO; /* Always offload the checksum, since it's in the data descriptor */ - tso = i40e_tx_enable_csum(skb, &tx_flags, &td_cmd, &td_offset, + tso = iavf_tx_enable_csum(skb, &tx_flags, &td_cmd, &td_offset, tx_ring, &cd_tunneling); if (tso < 0) goto out_drop; @@ -2465,44 +2465,44 @@ static netdev_tx_t i40e_xmit_frame_ring(struct sk_buff *skb, skb_tx_timestamp(skb); /* always enable CRC insertion offload */ - td_cmd |= I40E_TX_DESC_CMD_ICRC; + td_cmd |= IAVF_TX_DESC_CMD_ICRC; - i40e_create_tx_ctx(tx_ring, cd_type_cmd_tso_mss, + iavf_create_tx_ctx(tx_ring, cd_type_cmd_tso_mss, cd_tunneling, cd_l2tag2); - i40evf_tx_map(tx_ring, skb, first, tx_flags, hdr_len, - td_cmd, td_offset); + iavf_tx_map(tx_ring, skb, first, tx_flags, hdr_len, + td_cmd, td_offset); return NETDEV_TX_OK; out_drop: - i40e_trace(xmit_frame_ring_drop, first->skb, tx_ring); + iavf_trace(xmit_frame_ring_drop, first->skb, tx_ring); dev_kfree_skb_any(first->skb); first->skb = NULL; return NETDEV_TX_OK; } /** - * i40evf_xmit_frame - Selects the correct VSI and Tx queue to send buffer + * iavf_xmit_frame - Selects the correct VSI and Tx queue to send buffer * @skb: send buffer * @netdev: network interface device structure * * Returns NETDEV_TX_OK if sent, else an error code **/ -netdev_tx_t i40evf_xmit_frame(struct sk_buff *skb, struct net_device *netdev) +netdev_tx_t iavf_xmit_frame(struct sk_buff *skb, struct net_device *netdev) { - struct i40evf_adapter *adapter = netdev_priv(netdev); - struct i40e_ring *tx_ring = &adapter->tx_rings[skb->queue_mapping]; + struct iavf_adapter *adapter = netdev_priv(netdev); + struct iavf_ring *tx_ring = &adapter->tx_rings[skb->queue_mapping]; /* hardware can't handle really short frames, hardware padding works * beyond this point */ - if (unlikely(skb->len < I40E_MIN_TX_LEN)) { - if (skb_pad(skb, I40E_MIN_TX_LEN - skb->len)) + if (unlikely(skb->len < IAVF_MIN_TX_LEN)) { + if (skb_pad(skb, IAVF_MIN_TX_LEN - skb->len)) return NETDEV_TX_OK; - skb->len = I40E_MIN_TX_LEN; - skb_set_tail_pointer(skb, I40E_MIN_TX_LEN); + skb->len = IAVF_MIN_TX_LEN; + skb_set_tail_pointer(skb, IAVF_MIN_TX_LEN); } - return i40e_xmit_frame_ring(skb, tx_ring); + return iavf_xmit_frame_ring(skb, tx_ring); } diff --git a/drivers/net/ethernet/intel/i40evf/i40e_txrx.h b/drivers/net/ethernet/intel/iavf/iavf_txrx.h index 3b5a63b3236e..71e7d090f8db 100644 --- a/drivers/net/ethernet/intel/i40evf/i40e_txrx.h +++ b/drivers/net/ethernet/intel/iavf/iavf_txrx.h @@ -1,11 +1,11 @@ /* SPDX-License-Identifier: GPL-2.0 */ /* Copyright(c) 2013 - 2018 Intel Corporation. */ -#ifndef _I40E_TXRX_H_ -#define _I40E_TXRX_H_ +#ifndef _IAVF_TXRX_H_ +#define _IAVF_TXRX_H_ /* Interrupt Throttling and Rate Limiting Goodies */ -#define I40E_DEFAULT_IRQ_WORK 256 +#define IAVF_DEFAULT_IRQ_WORK 256 /* The datasheet for the X710 and XL710 indicate that the maximum value for * the ITR is 8160usec which is then called out as 0xFF0 with a 2usec @@ -13,80 +13,80 @@ * the register value which is divided by 2 lets use the actual values and * avoid an excessive amount of translation. */ -#define I40E_ITR_DYNAMIC 0x8000 /* use top bit as a flag */ -#define I40E_ITR_MASK 0x1FFE /* mask for ITR register value */ -#define I40E_MIN_ITR 2 /* reg uses 2 usec resolution */ -#define I40E_ITR_100K 10 /* all values below must be even */ -#define I40E_ITR_50K 20 -#define I40E_ITR_20K 50 -#define I40E_ITR_18K 60 -#define I40E_ITR_8K 122 -#define I40E_MAX_ITR 8160 /* maximum value as per datasheet */ -#define ITR_TO_REG(setting) ((setting) & ~I40E_ITR_DYNAMIC) -#define ITR_REG_ALIGN(setting) __ALIGN_MASK(setting, ~I40E_ITR_MASK) -#define ITR_IS_DYNAMIC(setting) (!!((setting) & I40E_ITR_DYNAMIC)) - -#define I40E_ITR_RX_DEF (I40E_ITR_20K | I40E_ITR_DYNAMIC) -#define I40E_ITR_TX_DEF (I40E_ITR_20K | I40E_ITR_DYNAMIC) +#define IAVF_ITR_DYNAMIC 0x8000 /* use top bit as a flag */ +#define IAVF_ITR_MASK 0x1FFE /* mask for ITR register value */ +#define IAVF_MIN_ITR 2 /* reg uses 2 usec resolution */ +#define IAVF_ITR_100K 10 /* all values below must be even */ +#define IAVF_ITR_50K 20 +#define IAVF_ITR_20K 50 +#define IAVF_ITR_18K 60 +#define IAVF_ITR_8K 122 +#define IAVF_MAX_ITR 8160 /* maximum value as per datasheet */ +#define ITR_TO_REG(setting) ((setting) & ~IAVF_ITR_DYNAMIC) +#define ITR_REG_ALIGN(setting) __ALIGN_MASK(setting, ~IAVF_ITR_MASK) +#define ITR_IS_DYNAMIC(setting) (!!((setting) & IAVF_ITR_DYNAMIC)) + +#define IAVF_ITR_RX_DEF (IAVF_ITR_20K | IAVF_ITR_DYNAMIC) +#define IAVF_ITR_TX_DEF (IAVF_ITR_20K | IAVF_ITR_DYNAMIC) /* 0x40 is the enable bit for interrupt rate limiting, and must be set if * the value of the rate limit is non-zero */ #define INTRL_ENA BIT(6) -#define I40E_MAX_INTRL 0x3B /* reg uses 4 usec resolution */ +#define IAVF_MAX_INTRL 0x3B /* reg uses 4 usec resolution */ #define INTRL_REG_TO_USEC(intrl) ((intrl & ~INTRL_ENA) << 2) #define INTRL_USEC_TO_REG(set) ((set) ? ((set) >> 2) | INTRL_ENA : 0) -#define I40E_INTRL_8K 125 /* 8000 ints/sec */ -#define I40E_INTRL_62K 16 /* 62500 ints/sec */ -#define I40E_INTRL_83K 12 /* 83333 ints/sec */ +#define IAVF_INTRL_8K 125 /* 8000 ints/sec */ +#define IAVF_INTRL_62K 16 /* 62500 ints/sec */ +#define IAVF_INTRL_83K 12 /* 83333 ints/sec */ -#define I40E_QUEUE_END_OF_LIST 0x7FF +#define IAVF_QUEUE_END_OF_LIST 0x7FF /* this enum matches hardware bits and is meant to be used by DYN_CTLN * registers and QINT registers or more generally anywhere in the manual * mentioning ITR_INDX, ITR_NONE cannot be used as an index 'n' into any * register but instead is a special value meaning "don't update" ITR0/1/2. */ -enum i40e_dyn_idx_t { - I40E_IDX_ITR0 = 0, - I40E_IDX_ITR1 = 1, - I40E_IDX_ITR2 = 2, - I40E_ITR_NONE = 3 /* ITR_NONE must not be used as an index */ +enum iavf_dyn_idx_t { + IAVF_IDX_ITR0 = 0, + IAVF_IDX_ITR1 = 1, + IAVF_IDX_ITR2 = 2, + IAVF_ITR_NONE = 3 /* ITR_NONE must not be used as an index */ }; /* these are indexes into ITRN registers */ -#define I40E_RX_ITR I40E_IDX_ITR0 -#define I40E_TX_ITR I40E_IDX_ITR1 -#define I40E_PE_ITR I40E_IDX_ITR2 +#define IAVF_RX_ITR IAVF_IDX_ITR0 +#define IAVF_TX_ITR IAVF_IDX_ITR1 +#define IAVF_PE_ITR IAVF_IDX_ITR2 /* Supported RSS offloads */ -#define I40E_DEFAULT_RSS_HENA ( \ - BIT_ULL(I40E_FILTER_PCTYPE_NONF_IPV4_UDP) | \ - BIT_ULL(I40E_FILTER_PCTYPE_NONF_IPV4_SCTP) | \ - BIT_ULL(I40E_FILTER_PCTYPE_NONF_IPV4_TCP) | \ - BIT_ULL(I40E_FILTER_PCTYPE_NONF_IPV4_OTHER) | \ - BIT_ULL(I40E_FILTER_PCTYPE_FRAG_IPV4) | \ - BIT_ULL(I40E_FILTER_PCTYPE_NONF_IPV6_UDP) | \ - BIT_ULL(I40E_FILTER_PCTYPE_NONF_IPV6_TCP) | \ - BIT_ULL(I40E_FILTER_PCTYPE_NONF_IPV6_SCTP) | \ - BIT_ULL(I40E_FILTER_PCTYPE_NONF_IPV6_OTHER) | \ - BIT_ULL(I40E_FILTER_PCTYPE_FRAG_IPV6) | \ - BIT_ULL(I40E_FILTER_PCTYPE_L2_PAYLOAD)) - -#define I40E_DEFAULT_RSS_HENA_EXPANDED (I40E_DEFAULT_RSS_HENA | \ - BIT_ULL(I40E_FILTER_PCTYPE_NONF_IPV4_TCP_SYN_NO_ACK) | \ - BIT_ULL(I40E_FILTER_PCTYPE_NONF_UNICAST_IPV4_UDP) | \ - BIT_ULL(I40E_FILTER_PCTYPE_NONF_MULTICAST_IPV4_UDP) | \ - BIT_ULL(I40E_FILTER_PCTYPE_NONF_IPV6_TCP_SYN_NO_ACK) | \ - BIT_ULL(I40E_FILTER_PCTYPE_NONF_UNICAST_IPV6_UDP) | \ - BIT_ULL(I40E_FILTER_PCTYPE_NONF_MULTICAST_IPV6_UDP)) +#define IAVF_DEFAULT_RSS_HENA ( \ + BIT_ULL(IAVF_FILTER_PCTYPE_NONF_IPV4_UDP) | \ + BIT_ULL(IAVF_FILTER_PCTYPE_NONF_IPV4_SCTP) | \ + BIT_ULL(IAVF_FILTER_PCTYPE_NONF_IPV4_TCP) | \ + BIT_ULL(IAVF_FILTER_PCTYPE_NONF_IPV4_OTHER) | \ + BIT_ULL(IAVF_FILTER_PCTYPE_FRAG_IPV4) | \ + BIT_ULL(IAVF_FILTER_PCTYPE_NONF_IPV6_UDP) | \ + BIT_ULL(IAVF_FILTER_PCTYPE_NONF_IPV6_TCP) | \ + BIT_ULL(IAVF_FILTER_PCTYPE_NONF_IPV6_SCTP) | \ + BIT_ULL(IAVF_FILTER_PCTYPE_NONF_IPV6_OTHER) | \ + BIT_ULL(IAVF_FILTER_PCTYPE_FRAG_IPV6) | \ + BIT_ULL(IAVF_FILTER_PCTYPE_L2_PAYLOAD)) + +#define IAVF_DEFAULT_RSS_HENA_EXPANDED (IAVF_DEFAULT_RSS_HENA | \ + BIT_ULL(IAVF_FILTER_PCTYPE_NONF_IPV4_TCP_SYN_NO_ACK) | \ + BIT_ULL(IAVF_FILTER_PCTYPE_NONF_UNICAST_IPV4_UDP) | \ + BIT_ULL(IAVF_FILTER_PCTYPE_NONF_MULTICAST_IPV4_UDP) | \ + BIT_ULL(IAVF_FILTER_PCTYPE_NONF_IPV6_TCP_SYN_NO_ACK) | \ + BIT_ULL(IAVF_FILTER_PCTYPE_NONF_UNICAST_IPV6_UDP) | \ + BIT_ULL(IAVF_FILTER_PCTYPE_NONF_MULTICAST_IPV6_UDP)) /* Supported Rx Buffer Sizes (a multiple of 128) */ -#define I40E_RXBUFFER_256 256 -#define I40E_RXBUFFER_1536 1536 /* 128B aligned standard Ethernet frame */ -#define I40E_RXBUFFER_2048 2048 -#define I40E_RXBUFFER_3072 3072 /* Used for large frames w/ padding */ -#define I40E_MAX_RXBUFFER 9728 /* largest size for single descriptor */ +#define IAVF_RXBUFFER_256 256 +#define IAVF_RXBUFFER_1536 1536 /* 128B aligned standard Ethernet frame */ +#define IAVF_RXBUFFER_2048 2048 +#define IAVF_RXBUFFER_3072 3072 /* Used for large frames w/ padding */ +#define IAVF_MAX_RXBUFFER 9728 /* largest size for single descriptor */ /* NOTE: netdev_alloc_skb reserves up to 64 bytes, NET_IP_ALIGN means we * reserve 2 more, and skb_shared_info adds an additional 384 bytes more, @@ -95,11 +95,11 @@ enum i40e_dyn_idx_t { * i.e. RXBUFFER_256 --> 960 byte skb (size-1024 slab) * i.e. RXBUFFER_512 --> 1216 byte skb (size-2048 slab) */ -#define I40E_RX_HDR_SIZE I40E_RXBUFFER_256 -#define I40E_PACKET_HDR_PAD (ETH_HLEN + ETH_FCS_LEN + (VLAN_HLEN * 2)) -#define i40e_rx_desc i40e_32byte_rx_desc +#define IAVF_RX_HDR_SIZE IAVF_RXBUFFER_256 +#define IAVF_PACKET_HDR_PAD (ETH_HLEN + ETH_FCS_LEN + (VLAN_HLEN * 2)) +#define iavf_rx_desc iavf_32byte_rx_desc -#define I40E_RX_DMA_ATTR \ +#define IAVF_RX_DMA_ATTR \ (DMA_ATTR_SKIP_CPU_SYNC | DMA_ATTR_WEAK_ORDERING) /* Attempt to maximize the headroom available for incoming frames. We @@ -113,10 +113,10 @@ enum i40e_dyn_idx_t { * receive path. */ #if (PAGE_SIZE < 8192) -#define I40E_2K_TOO_SMALL_WITH_PADDING \ -((NET_SKB_PAD + I40E_RXBUFFER_1536) > SKB_WITH_OVERHEAD(I40E_RXBUFFER_2048)) +#define IAVF_2K_TOO_SMALL_WITH_PADDING \ +((NET_SKB_PAD + IAVF_RXBUFFER_1536) > SKB_WITH_OVERHEAD(IAVF_RXBUFFER_2048)) -static inline int i40e_compute_pad(int rx_buf_len) +static inline int iavf_compute_pad(int rx_buf_len) { int page_size, pad_size; @@ -126,7 +126,7 @@ static inline int i40e_compute_pad(int rx_buf_len) return pad_size; } -static inline int i40e_skb_pad(void) +static inline int iavf_skb_pad(void) { int rx_buf_len; @@ -137,25 +137,25 @@ static inline int i40e_skb_pad(void) * tailroom due to NET_IP_ALIGN possibly shifting us out of * cache-line alignment. */ - if (I40E_2K_TOO_SMALL_WITH_PADDING) - rx_buf_len = I40E_RXBUFFER_3072 + SKB_DATA_ALIGN(NET_IP_ALIGN); + if (IAVF_2K_TOO_SMALL_WITH_PADDING) + rx_buf_len = IAVF_RXBUFFER_3072 + SKB_DATA_ALIGN(NET_IP_ALIGN); else - rx_buf_len = I40E_RXBUFFER_1536; + rx_buf_len = IAVF_RXBUFFER_1536; /* if needed make room for NET_IP_ALIGN */ rx_buf_len -= NET_IP_ALIGN; - return i40e_compute_pad(rx_buf_len); + return iavf_compute_pad(rx_buf_len); } -#define I40E_SKB_PAD i40e_skb_pad() +#define IAVF_SKB_PAD iavf_skb_pad() #else -#define I40E_2K_TOO_SMALL_WITH_PADDING false -#define I40E_SKB_PAD (NET_SKB_PAD + NET_IP_ALIGN) +#define IAVF_2K_TOO_SMALL_WITH_PADDING false +#define IAVF_SKB_PAD (NET_SKB_PAD + NET_IP_ALIGN) #endif /** - * i40e_test_staterr - tests bits in Rx descriptor status and error fields + * iavf_test_staterr - tests bits in Rx descriptor status and error fields * @rx_desc: pointer to receive descriptor (in le64 format) * @stat_err_bits: value to mask * @@ -164,7 +164,7 @@ static inline int i40e_skb_pad(void) * The status_error_len doesn't need to be shifted because it begins * at offset zero. */ -static inline bool i40e_test_staterr(union i40e_rx_desc *rx_desc, +static inline bool iavf_test_staterr(union iavf_rx_desc *rx_desc, const u64 stat_err_bits) { return !!(rx_desc->wb.qword1.status_error_len & @@ -172,8 +172,7 @@ static inline bool i40e_test_staterr(union i40e_rx_desc *rx_desc, } /* How many Rx Buffers do we bundle into one write to the hardware ? */ -#define I40E_RX_BUFFER_WRITE 32 /* Must be power of 2 */ -#define I40E_RX_INCREMENT(r, i) \ +#define IAVF_RX_INCREMENT(r, i) \ do { \ (i)++; \ if ((i) == (r)->count) \ @@ -181,34 +180,34 @@ static inline bool i40e_test_staterr(union i40e_rx_desc *rx_desc, r->next_to_clean = i; \ } while (0) -#define I40E_RX_NEXT_DESC(r, i, n) \ +#define IAVF_RX_NEXT_DESC(r, i, n) \ do { \ (i)++; \ if ((i) == (r)->count) \ i = 0; \ - (n) = I40E_RX_DESC((r), (i)); \ + (n) = IAVF_RX_DESC((r), (i)); \ } while (0) -#define I40E_RX_NEXT_DESC_PREFETCH(r, i, n) \ +#define IAVF_RX_NEXT_DESC_PREFETCH(r, i, n) \ do { \ - I40E_RX_NEXT_DESC((r), (i), (n)); \ + IAVF_RX_NEXT_DESC((r), (i), (n)); \ prefetch((n)); \ } while (0) -#define I40E_MAX_BUFFER_TXD 8 -#define I40E_MIN_TX_LEN 17 +#define IAVF_MAX_BUFFER_TXD 8 +#define IAVF_MIN_TX_LEN 17 /* The size limit for a transmit buffer in a descriptor is (16K - 1). * In order to align with the read requests we will align the value to * the nearest 4K which represents our maximum read request size. */ -#define I40E_MAX_READ_REQ_SIZE 4096 -#define I40E_MAX_DATA_PER_TXD (16 * 1024 - 1) -#define I40E_MAX_DATA_PER_TXD_ALIGNED \ - (I40E_MAX_DATA_PER_TXD & ~(I40E_MAX_READ_REQ_SIZE - 1)) +#define IAVF_MAX_READ_REQ_SIZE 4096 +#define IAVF_MAX_DATA_PER_TXD (16 * 1024 - 1) +#define IAVF_MAX_DATA_PER_TXD_ALIGNED \ + (IAVF_MAX_DATA_PER_TXD & ~(IAVF_MAX_READ_REQ_SIZE - 1)) /** - * i40e_txd_use_count - estimate the number of descriptors needed for Tx + * iavf_txd_use_count - estimate the number of descriptors needed for Tx * @size: transmit request size in bytes * * Due to hardware alignment restrictions (4K alignment), we need to @@ -235,31 +234,31 @@ static inline bool i40e_test_staterr(union i40e_rx_desc *rx_desc, * operations into: * return ((size * 85) >> 20) + 1; */ -static inline unsigned int i40e_txd_use_count(unsigned int size) +static inline unsigned int iavf_txd_use_count(unsigned int size) { return ((size * 85) >> 20) + 1; } /* Tx Descriptors needed, worst case */ #define DESC_NEEDED (MAX_SKB_FRAGS + 6) -#define I40E_MIN_DESC_PENDING 4 - -#define I40E_TX_FLAGS_HW_VLAN BIT(1) -#define I40E_TX_FLAGS_SW_VLAN BIT(2) -#define I40E_TX_FLAGS_TSO BIT(3) -#define I40E_TX_FLAGS_IPV4 BIT(4) -#define I40E_TX_FLAGS_IPV6 BIT(5) -#define I40E_TX_FLAGS_FCCRC BIT(6) -#define I40E_TX_FLAGS_FSO BIT(7) -#define I40E_TX_FLAGS_FD_SB BIT(9) -#define I40E_TX_FLAGS_VXLAN_TUNNEL BIT(10) -#define I40E_TX_FLAGS_VLAN_MASK 0xffff0000 -#define I40E_TX_FLAGS_VLAN_PRIO_MASK 0xe0000000 -#define I40E_TX_FLAGS_VLAN_PRIO_SHIFT 29 -#define I40E_TX_FLAGS_VLAN_SHIFT 16 - -struct i40e_tx_buffer { - struct i40e_tx_desc *next_to_watch; +#define IAVF_MIN_DESC_PENDING 4 + +#define IAVF_TX_FLAGS_HW_VLAN BIT(1) +#define IAVF_TX_FLAGS_SW_VLAN BIT(2) +#define IAVF_TX_FLAGS_TSO BIT(3) +#define IAVF_TX_FLAGS_IPV4 BIT(4) +#define IAVF_TX_FLAGS_IPV6 BIT(5) +#define IAVF_TX_FLAGS_FCCRC BIT(6) +#define IAVF_TX_FLAGS_FSO BIT(7) +#define IAVF_TX_FLAGS_FD_SB BIT(9) +#define IAVF_TX_FLAGS_VXLAN_TUNNEL BIT(10) +#define IAVF_TX_FLAGS_VLAN_MASK 0xffff0000 +#define IAVF_TX_FLAGS_VLAN_PRIO_MASK 0xe0000000 +#define IAVF_TX_FLAGS_VLAN_PRIO_SHIFT 29 +#define IAVF_TX_FLAGS_VLAN_SHIFT 16 + +struct iavf_tx_buffer { + struct iavf_tx_desc *next_to_watch; union { struct sk_buff *skb; void *raw_buf; @@ -272,7 +271,7 @@ struct i40e_tx_buffer { u32 tx_flags; }; -struct i40e_rx_buffer { +struct iavf_rx_buffer { dma_addr_t dma; struct page *page; #if (BITS_PER_LONG > 32) || (PAGE_SIZE >= 65536) @@ -283,12 +282,12 @@ struct i40e_rx_buffer { __u16 pagecnt_bias; }; -struct i40e_queue_stats { +struct iavf_queue_stats { u64 packets; u64 bytes; }; -struct i40e_tx_queue_stats { +struct iavf_tx_queue_stats { u64 restart_queue; u64 tx_busy; u64 tx_done_old; @@ -298,7 +297,7 @@ struct i40e_tx_queue_stats { u64 tx_lost_interrupt; }; -struct i40e_rx_queue_stats { +struct iavf_rx_queue_stats { u64 non_eop_descs; u64 alloc_page_failed; u64 alloc_buff_failed; @@ -306,34 +305,34 @@ struct i40e_rx_queue_stats { u64 realloc_count; }; -enum i40e_ring_state_t { - __I40E_TX_FDIR_INIT_DONE, - __I40E_TX_XPS_INIT_DONE, - __I40E_RING_STATE_NBITS /* must be last */ +enum iavf_ring_state_t { + __IAVF_TX_FDIR_INIT_DONE, + __IAVF_TX_XPS_INIT_DONE, + __IAVF_RING_STATE_NBITS /* must be last */ }; /* some useful defines for virtchannel interface, which * is the only remaining user of header split */ -#define I40E_RX_DTYPE_NO_SPLIT 0 -#define I40E_RX_DTYPE_HEADER_SPLIT 1 -#define I40E_RX_DTYPE_SPLIT_ALWAYS 2 -#define I40E_RX_SPLIT_L2 0x1 -#define I40E_RX_SPLIT_IP 0x2 -#define I40E_RX_SPLIT_TCP_UDP 0x4 -#define I40E_RX_SPLIT_SCTP 0x8 +#define IAVF_RX_DTYPE_NO_SPLIT 0 +#define IAVF_RX_DTYPE_HEADER_SPLIT 1 +#define IAVF_RX_DTYPE_SPLIT_ALWAYS 2 +#define IAVF_RX_SPLIT_L2 0x1 +#define IAVF_RX_SPLIT_IP 0x2 +#define IAVF_RX_SPLIT_TCP_UDP 0x4 +#define IAVF_RX_SPLIT_SCTP 0x8 /* struct that defines a descriptor ring, associated with a VSI */ -struct i40e_ring { - struct i40e_ring *next; /* pointer to next ring in q_vector */ +struct iavf_ring { + struct iavf_ring *next; /* pointer to next ring in q_vector */ void *desc; /* Descriptor ring memory */ struct device *dev; /* Used for DMA mapping */ struct net_device *netdev; /* netdev ring maps to */ union { - struct i40e_tx_buffer *tx_bi; - struct i40e_rx_buffer *rx_bi; + struct iavf_tx_buffer *tx_bi; + struct iavf_rx_buffer *rx_bi; }; - DECLARE_BITMAP(state, __I40E_RING_STATE_NBITS); + DECLARE_BITMAP(state, __IAVF_RING_STATE_NBITS); u16 queue_index; /* Queue number of ring */ u8 dcb_tc; /* Traffic class of ring */ u8 __iomem *tail; @@ -361,59 +360,59 @@ struct i40e_ring { u8 packet_stride; u16 flags; -#define I40E_TXR_FLAGS_WB_ON_ITR BIT(0) -#define I40E_RXR_FLAGS_BUILD_SKB_ENABLED BIT(1) +#define IAVF_TXR_FLAGS_WB_ON_ITR BIT(0) +#define IAVF_RXR_FLAGS_BUILD_SKB_ENABLED BIT(1) /* stats structs */ - struct i40e_queue_stats stats; + struct iavf_queue_stats stats; struct u64_stats_sync syncp; union { - struct i40e_tx_queue_stats tx_stats; - struct i40e_rx_queue_stats rx_stats; + struct iavf_tx_queue_stats tx_stats; + struct iavf_rx_queue_stats rx_stats; }; unsigned int size; /* length of descriptor ring in bytes */ dma_addr_t dma; /* physical address of ring */ - struct i40e_vsi *vsi; /* Backreference to associated VSI */ - struct i40e_q_vector *q_vector; /* Backreference to associated vector */ + struct iavf_vsi *vsi; /* Backreference to associated VSI */ + struct iavf_q_vector *q_vector; /* Backreference to associated vector */ struct rcu_head rcu; /* to avoid race on free */ u16 next_to_alloc; - struct sk_buff *skb; /* When i40evf_clean_rx_ring_irq() must + struct sk_buff *skb; /* When iavf_clean_rx_ring_irq() must * return before it sees the EOP for * the current packet, we save that skb * here and resume receiving this * packet the next time - * i40evf_clean_rx_ring_irq() is called + * iavf_clean_rx_ring_irq() is called * for this ring. */ } ____cacheline_internodealigned_in_smp; -static inline bool ring_uses_build_skb(struct i40e_ring *ring) +static inline bool ring_uses_build_skb(struct iavf_ring *ring) { - return !!(ring->flags & I40E_RXR_FLAGS_BUILD_SKB_ENABLED); + return !!(ring->flags & IAVF_RXR_FLAGS_BUILD_SKB_ENABLED); } -static inline void set_ring_build_skb_enabled(struct i40e_ring *ring) +static inline void set_ring_build_skb_enabled(struct iavf_ring *ring) { - ring->flags |= I40E_RXR_FLAGS_BUILD_SKB_ENABLED; + ring->flags |= IAVF_RXR_FLAGS_BUILD_SKB_ENABLED; } -static inline void clear_ring_build_skb_enabled(struct i40e_ring *ring) +static inline void clear_ring_build_skb_enabled(struct iavf_ring *ring) { - ring->flags &= ~I40E_RXR_FLAGS_BUILD_SKB_ENABLED; + ring->flags &= ~IAVF_RXR_FLAGS_BUILD_SKB_ENABLED; } -#define I40E_ITR_ADAPTIVE_MIN_INC 0x0002 -#define I40E_ITR_ADAPTIVE_MIN_USECS 0x0002 -#define I40E_ITR_ADAPTIVE_MAX_USECS 0x007e -#define I40E_ITR_ADAPTIVE_LATENCY 0x8000 -#define I40E_ITR_ADAPTIVE_BULK 0x0000 -#define ITR_IS_BULK(x) (!((x) & I40E_ITR_ADAPTIVE_LATENCY)) +#define IAVF_ITR_ADAPTIVE_MIN_INC 0x0002 +#define IAVF_ITR_ADAPTIVE_MIN_USECS 0x0002 +#define IAVF_ITR_ADAPTIVE_MAX_USECS 0x007e +#define IAVF_ITR_ADAPTIVE_LATENCY 0x8000 +#define IAVF_ITR_ADAPTIVE_BULK 0x0000 +#define ITR_IS_BULK(x) (!((x) & IAVF_ITR_ADAPTIVE_LATENCY)) -struct i40e_ring_container { - struct i40e_ring *ring; /* pointer to linked list of ring(s) */ +struct iavf_ring_container { + struct iavf_ring *ring; /* pointer to linked list of ring(s) */ unsigned long next_update; /* jiffies value of next update */ unsigned int total_bytes; /* total bytes processed this int */ unsigned int total_packets; /* total packets processed this int */ @@ -423,10 +422,10 @@ struct i40e_ring_container { }; /* iterator for handling rings in ring container */ -#define i40e_for_each_ring(pos, head) \ +#define iavf_for_each_ring(pos, head) \ for (pos = (head).ring; pos != NULL; pos = pos->next) -static inline unsigned int i40e_rx_pg_order(struct i40e_ring *ring) +static inline unsigned int iavf_rx_pg_order(struct iavf_ring *ring) { #if (PAGE_SIZE < 8192) if (ring->rx_buf_len > (PAGE_SIZE / 2)) @@ -435,25 +434,25 @@ static inline unsigned int i40e_rx_pg_order(struct i40e_ring *ring) return 0; } -#define i40e_rx_pg_size(_ring) (PAGE_SIZE << i40e_rx_pg_order(_ring)) - -bool i40evf_alloc_rx_buffers(struct i40e_ring *rxr, u16 cleaned_count); -netdev_tx_t i40evf_xmit_frame(struct sk_buff *skb, struct net_device *netdev); -void i40evf_clean_tx_ring(struct i40e_ring *tx_ring); -void i40evf_clean_rx_ring(struct i40e_ring *rx_ring); -int i40evf_setup_tx_descriptors(struct i40e_ring *tx_ring); -int i40evf_setup_rx_descriptors(struct i40e_ring *rx_ring); -void i40evf_free_tx_resources(struct i40e_ring *tx_ring); -void i40evf_free_rx_resources(struct i40e_ring *rx_ring); -int i40evf_napi_poll(struct napi_struct *napi, int budget); -void i40evf_force_wb(struct i40e_vsi *vsi, struct i40e_q_vector *q_vector); -u32 i40evf_get_tx_pending(struct i40e_ring *ring, bool in_sw); -void i40evf_detect_recover_hung(struct i40e_vsi *vsi); -int __i40evf_maybe_stop_tx(struct i40e_ring *tx_ring, int size); -bool __i40evf_chk_linearize(struct sk_buff *skb); +#define iavf_rx_pg_size(_ring) (PAGE_SIZE << iavf_rx_pg_order(_ring)) + +bool iavf_alloc_rx_buffers(struct iavf_ring *rxr, u16 cleaned_count); +netdev_tx_t iavf_xmit_frame(struct sk_buff *skb, struct net_device *netdev); +void iavf_clean_tx_ring(struct iavf_ring *tx_ring); +void iavf_clean_rx_ring(struct iavf_ring *rx_ring); +int iavf_setup_tx_descriptors(struct iavf_ring *tx_ring); +int iavf_setup_rx_descriptors(struct iavf_ring *rx_ring); +void iavf_free_tx_resources(struct iavf_ring *tx_ring); +void iavf_free_rx_resources(struct iavf_ring *rx_ring); +int iavf_napi_poll(struct napi_struct *napi, int budget); +void iavf_force_wb(struct iavf_vsi *vsi, struct iavf_q_vector *q_vector); +u32 iavf_get_tx_pending(struct iavf_ring *ring, bool in_sw); +void iavf_detect_recover_hung(struct iavf_vsi *vsi); +int __iavf_maybe_stop_tx(struct iavf_ring *tx_ring, int size); +bool __iavf_chk_linearize(struct sk_buff *skb); /** - * i40e_xmit_descriptor_count - calculate number of Tx descriptors needed + * iavf_xmit_descriptor_count - calculate number of Tx descriptors needed * @skb: send buffer * @tx_ring: ring to send buffer on * @@ -461,14 +460,14 @@ bool __i40evf_chk_linearize(struct sk_buff *skb); * there is not enough descriptors available in this ring since we need at least * one descriptor. **/ -static inline int i40e_xmit_descriptor_count(struct sk_buff *skb) +static inline int iavf_xmit_descriptor_count(struct sk_buff *skb) { const struct skb_frag_struct *frag = &skb_shinfo(skb)->frags[0]; unsigned int nr_frags = skb_shinfo(skb)->nr_frags; int count = 0, size = skb_headlen(skb); for (;;) { - count += i40e_txd_use_count(size); + count += iavf_txd_use_count(size); if (!nr_frags--) break; @@ -480,21 +479,21 @@ static inline int i40e_xmit_descriptor_count(struct sk_buff *skb) } /** - * i40e_maybe_stop_tx - 1st level check for Tx stop conditions + * iavf_maybe_stop_tx - 1st level check for Tx stop conditions * @tx_ring: the ring to be checked * @size: the size buffer we want to assure is available * * Returns 0 if stop is not needed **/ -static inline int i40e_maybe_stop_tx(struct i40e_ring *tx_ring, int size) +static inline int iavf_maybe_stop_tx(struct iavf_ring *tx_ring, int size) { - if (likely(I40E_DESC_UNUSED(tx_ring) >= size)) + if (likely(IAVF_DESC_UNUSED(tx_ring) >= size)) return 0; - return __i40evf_maybe_stop_tx(tx_ring, size); + return __iavf_maybe_stop_tx(tx_ring, size); } /** - * i40e_chk_linearize - Check if there are more than 8 fragments per packet + * iavf_chk_linearize - Check if there are more than 8 fragments per packet * @skb: send buffer * @count: number of buffers used * @@ -502,23 +501,23 @@ static inline int i40e_maybe_stop_tx(struct i40e_ring *tx_ring, int size) * a packet on the wire and so we need to figure out the cases where we * need to linearize the skb. **/ -static inline bool i40e_chk_linearize(struct sk_buff *skb, int count) +static inline bool iavf_chk_linearize(struct sk_buff *skb, int count) { /* Both TSO and single send will work if count is less than 8 */ - if (likely(count < I40E_MAX_BUFFER_TXD)) + if (likely(count < IAVF_MAX_BUFFER_TXD)) return false; if (skb_is_gso(skb)) - return __i40evf_chk_linearize(skb); + return __iavf_chk_linearize(skb); /* we can support up to 8 data buffers for a single send */ - return count != I40E_MAX_BUFFER_TXD; + return count != IAVF_MAX_BUFFER_TXD; } /** * @ring: Tx ring to find the netdev equivalent of **/ -static inline struct netdev_queue *txring_txq(const struct i40e_ring *ring) +static inline struct netdev_queue *txring_txq(const struct iavf_ring *ring) { return netdev_get_tx_queue(ring->netdev, ring->queue_index); } -#endif /* _I40E_TXRX_H_ */ +#endif /* _IAVF_TXRX_H_ */ diff --git a/drivers/net/ethernet/intel/iavf/iavf_type.h b/drivers/net/ethernet/intel/iavf/iavf_type.h new file mode 100644 index 000000000000..ca89583613fb --- /dev/null +++ b/drivers/net/ethernet/intel/iavf/iavf_type.h @@ -0,0 +1,688 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright(c) 2013 - 2018 Intel Corporation. */ + +#ifndef _IAVF_TYPE_H_ +#define _IAVF_TYPE_H_ + +#include "iavf_status.h" +#include "iavf_osdep.h" +#include "iavf_register.h" +#include "i40e_adminq.h" +#include "iavf_devids.h" + +#define IAVF_RXQ_CTX_DBUFF_SHIFT 7 + +/* IAVF_MASK is a macro used on 32 bit registers */ +#define IAVF_MASK(mask, shift) ((u32)(mask) << (shift)) + +#define IAVF_MAX_VSI_QP 16 +#define IAVF_MAX_VF_VSI 3 +#define IAVF_MAX_CHAINED_RX_BUFFERS 5 + +/* forward declaration */ +struct iavf_hw; +typedef void (*I40E_ADMINQ_CALLBACK)(struct iavf_hw *, struct i40e_aq_desc *); + +/* Data type manipulation macros. */ + +#define IAVF_DESC_UNUSED(R) \ + ((((R)->next_to_clean > (R)->next_to_use) ? 0 : (R)->count) + \ + (R)->next_to_clean - (R)->next_to_use - 1) + +/* bitfields for Tx queue mapping in QTX_CTL */ +#define IAVF_QTX_CTL_VF_QUEUE 0x0 +#define IAVF_QTX_CTL_VM_QUEUE 0x1 +#define IAVF_QTX_CTL_PF_QUEUE 0x2 + +/* debug masks - set these bits in hw->debug_mask to control output */ +enum iavf_debug_mask { + IAVF_DEBUG_INIT = 0x00000001, + IAVF_DEBUG_RELEASE = 0x00000002, + + IAVF_DEBUG_LINK = 0x00000010, + IAVF_DEBUG_PHY = 0x00000020, + IAVF_DEBUG_HMC = 0x00000040, + IAVF_DEBUG_NVM = 0x00000080, + IAVF_DEBUG_LAN = 0x00000100, + IAVF_DEBUG_FLOW = 0x00000200, + IAVF_DEBUG_DCB = 0x00000400, + IAVF_DEBUG_DIAG = 0x00000800, + IAVF_DEBUG_FD = 0x00001000, + IAVF_DEBUG_PACKAGE = 0x00002000, + + IAVF_DEBUG_AQ_MESSAGE = 0x01000000, + IAVF_DEBUG_AQ_DESCRIPTOR = 0x02000000, + IAVF_DEBUG_AQ_DESC_BUFFER = 0x04000000, + IAVF_DEBUG_AQ_COMMAND = 0x06000000, + IAVF_DEBUG_AQ = 0x0F000000, + + IAVF_DEBUG_USER = 0xF0000000, + + IAVF_DEBUG_ALL = 0xFFFFFFFF +}; + +/* These are structs for managing the hardware information and the operations. + * The structures of function pointers are filled out at init time when we + * know for sure exactly which hardware we're working with. This gives us the + * flexibility of using the same main driver code but adapting to slightly + * different hardware needs as new parts are developed. For this architecture, + * the Firmware and AdminQ are intended to insulate the driver from most of the + * future changes, but these structures will also do part of the job. + */ +enum iavf_mac_type { + IAVF_MAC_UNKNOWN = 0, + IAVF_MAC_XL710, + IAVF_MAC_VF, + IAVF_MAC_X722, + IAVF_MAC_X722_VF, + IAVF_MAC_GENERIC, +}; + +enum iavf_vsi_type { + IAVF_VSI_MAIN = 0, + IAVF_VSI_VMDQ1 = 1, + IAVF_VSI_VMDQ2 = 2, + IAVF_VSI_CTRL = 3, + IAVF_VSI_FCOE = 4, + IAVF_VSI_MIRROR = 5, + IAVF_VSI_SRIOV = 6, + IAVF_VSI_FDIR = 7, + IAVF_VSI_TYPE_UNKNOWN +}; + +enum iavf_queue_type { + IAVF_QUEUE_TYPE_RX = 0, + IAVF_QUEUE_TYPE_TX, + IAVF_QUEUE_TYPE_PE_CEQ, + IAVF_QUEUE_TYPE_UNKNOWN +}; + +#define IAVF_HW_CAP_MAX_GPIO 30 +/* Capabilities of a PF or a VF or the whole device */ +struct iavf_hw_capabilities { + bool dcb; + bool fcoe; + u32 num_vsis; + u32 num_rx_qp; + u32 num_tx_qp; + u32 base_queue; + u32 num_msix_vectors_vf; +}; + +struct iavf_mac_info { + enum iavf_mac_type type; + u8 addr[ETH_ALEN]; + u8 perm_addr[ETH_ALEN]; + u8 san_addr[ETH_ALEN]; + u16 max_fcoeq; +}; + +/* PCI bus types */ +enum iavf_bus_type { + iavf_bus_type_unknown = 0, + iavf_bus_type_pci, + iavf_bus_type_pcix, + iavf_bus_type_pci_express, + iavf_bus_type_reserved +}; + +/* PCI bus speeds */ +enum iavf_bus_speed { + iavf_bus_speed_unknown = 0, + iavf_bus_speed_33 = 33, + iavf_bus_speed_66 = 66, + iavf_bus_speed_100 = 100, + iavf_bus_speed_120 = 120, + iavf_bus_speed_133 = 133, + iavf_bus_speed_2500 = 2500, + iavf_bus_speed_5000 = 5000, + iavf_bus_speed_8000 = 8000, + iavf_bus_speed_reserved +}; + +/* PCI bus widths */ +enum iavf_bus_width { + iavf_bus_width_unknown = 0, + iavf_bus_width_pcie_x1 = 1, + iavf_bus_width_pcie_x2 = 2, + iavf_bus_width_pcie_x4 = 4, + iavf_bus_width_pcie_x8 = 8, + iavf_bus_width_32 = 32, + iavf_bus_width_64 = 64, + iavf_bus_width_reserved +}; + +/* Bus parameters */ +struct iavf_bus_info { + enum iavf_bus_speed speed; + enum iavf_bus_width width; + enum iavf_bus_type type; + + u16 func; + u16 device; + u16 lan_id; + u16 bus_id; +}; + +#define IAVF_MAX_USER_PRIORITY 8 +/* Port hardware description */ +struct iavf_hw { + u8 __iomem *hw_addr; + void *back; + + /* subsystem structs */ + struct iavf_mac_info mac; + struct iavf_bus_info bus; + + /* pci info */ + u16 device_id; + u16 vendor_id; + u16 subsystem_device_id; + u16 subsystem_vendor_id; + u8 revision_id; + + /* capabilities for entire device and PCI func */ + struct iavf_hw_capabilities dev_caps; + + /* Admin Queue info */ + struct iavf_adminq_info aq; + + /* debug mask */ + u32 debug_mask; + char err_str[16]; +}; + +struct iavf_driver_version { + u8 major_version; + u8 minor_version; + u8 build_version; + u8 subbuild_version; + u8 driver_string[32]; +}; + +/* RX Descriptors */ +union iavf_16byte_rx_desc { + struct { + __le64 pkt_addr; /* Packet buffer address */ + __le64 hdr_addr; /* Header buffer address */ + } read; + struct { + struct { + struct { + union { + __le16 mirroring_status; + __le16 fcoe_ctx_id; + } mirr_fcoe; + __le16 l2tag1; + } lo_dword; + union { + __le32 rss; /* RSS Hash */ + __le32 fd_id; /* Flow director filter id */ + __le32 fcoe_param; /* FCoE DDP Context id */ + } hi_dword; + } qword0; + struct { + /* ext status/error/pktype/length */ + __le64 status_error_len; + } qword1; + } wb; /* writeback */ +}; + +union iavf_32byte_rx_desc { + struct { + __le64 pkt_addr; /* Packet buffer address */ + __le64 hdr_addr; /* Header buffer address */ + /* bit 0 of hdr_buffer_addr is DD bit */ + __le64 rsvd1; + __le64 rsvd2; + } read; + struct { + struct { + struct { + union { + __le16 mirroring_status; + __le16 fcoe_ctx_id; + } mirr_fcoe; + __le16 l2tag1; + } lo_dword; + union { + __le32 rss; /* RSS Hash */ + __le32 fcoe_param; /* FCoE DDP Context id */ + /* Flow director filter id in case of + * Programming status desc WB + */ + __le32 fd_id; + } hi_dword; + } qword0; + struct { + /* status/error/pktype/length */ + __le64 status_error_len; + } qword1; + struct { + __le16 ext_status; /* extended status */ + __le16 rsvd; + __le16 l2tag2_1; + __le16 l2tag2_2; + } qword2; + struct { + union { + __le32 flex_bytes_lo; + __le32 pe_status; + } lo_dword; + union { + __le32 flex_bytes_hi; + __le32 fd_id; + } hi_dword; + } qword3; + } wb; /* writeback */ +}; + +enum iavf_rx_desc_status_bits { + /* Note: These are predefined bit offsets */ + IAVF_RX_DESC_STATUS_DD_SHIFT = 0, + IAVF_RX_DESC_STATUS_EOF_SHIFT = 1, + IAVF_RX_DESC_STATUS_L2TAG1P_SHIFT = 2, + IAVF_RX_DESC_STATUS_L3L4P_SHIFT = 3, + IAVF_RX_DESC_STATUS_CRCP_SHIFT = 4, + IAVF_RX_DESC_STATUS_TSYNINDX_SHIFT = 5, /* 2 BITS */ + IAVF_RX_DESC_STATUS_TSYNVALID_SHIFT = 7, + /* Note: Bit 8 is reserved in X710 and XL710 */ + IAVF_RX_DESC_STATUS_EXT_UDP_0_SHIFT = 8, + IAVF_RX_DESC_STATUS_UMBCAST_SHIFT = 9, /* 2 BITS */ + IAVF_RX_DESC_STATUS_FLM_SHIFT = 11, + IAVF_RX_DESC_STATUS_FLTSTAT_SHIFT = 12, /* 2 BITS */ + IAVF_RX_DESC_STATUS_LPBK_SHIFT = 14, + IAVF_RX_DESC_STATUS_IPV6EXADD_SHIFT = 15, + IAVF_RX_DESC_STATUS_RESERVED_SHIFT = 16, /* 2 BITS */ + /* Note: For non-tunnel packets INT_UDP_0 is the right status for + * UDP header + */ + IAVF_RX_DESC_STATUS_INT_UDP_0_SHIFT = 18, + IAVF_RX_DESC_STATUS_LAST /* this entry must be last!!! */ +}; + +#define IAVF_RXD_QW1_STATUS_SHIFT 0 +#define IAVF_RXD_QW1_STATUS_MASK ((BIT(IAVF_RX_DESC_STATUS_LAST) - 1) \ + << IAVF_RXD_QW1_STATUS_SHIFT) + +#define IAVF_RXD_QW1_STATUS_TSYNINDX_SHIFT IAVF_RX_DESC_STATUS_TSYNINDX_SHIFT +#define IAVF_RXD_QW1_STATUS_TSYNINDX_MASK (0x3UL << \ + IAVF_RXD_QW1_STATUS_TSYNINDX_SHIFT) + +#define IAVF_RXD_QW1_STATUS_TSYNVALID_SHIFT IAVF_RX_DESC_STATUS_TSYNVALID_SHIFT +#define IAVF_RXD_QW1_STATUS_TSYNVALID_MASK \ + BIT_ULL(IAVF_RXD_QW1_STATUS_TSYNVALID_SHIFT) + +enum iavf_rx_desc_fltstat_values { + IAVF_RX_DESC_FLTSTAT_NO_DATA = 0, + IAVF_RX_DESC_FLTSTAT_RSV_FD_ID = 1, /* 16byte desc? FD_ID : RSV */ + IAVF_RX_DESC_FLTSTAT_RSV = 2, + IAVF_RX_DESC_FLTSTAT_RSS_HASH = 3, +}; + +#define IAVF_RXD_QW1_ERROR_SHIFT 19 +#define IAVF_RXD_QW1_ERROR_MASK (0xFFUL << IAVF_RXD_QW1_ERROR_SHIFT) + +enum iavf_rx_desc_error_bits { + /* Note: These are predefined bit offsets */ + IAVF_RX_DESC_ERROR_RXE_SHIFT = 0, + IAVF_RX_DESC_ERROR_RECIPE_SHIFT = 1, + IAVF_RX_DESC_ERROR_HBO_SHIFT = 2, + IAVF_RX_DESC_ERROR_L3L4E_SHIFT = 3, /* 3 BITS */ + IAVF_RX_DESC_ERROR_IPE_SHIFT = 3, + IAVF_RX_DESC_ERROR_L4E_SHIFT = 4, + IAVF_RX_DESC_ERROR_EIPE_SHIFT = 5, + IAVF_RX_DESC_ERROR_OVERSIZE_SHIFT = 6, + IAVF_RX_DESC_ERROR_PPRS_SHIFT = 7 +}; + +enum iavf_rx_desc_error_l3l4e_fcoe_masks { + IAVF_RX_DESC_ERROR_L3L4E_NONE = 0, + IAVF_RX_DESC_ERROR_L3L4E_PROT = 1, + IAVF_RX_DESC_ERROR_L3L4E_FC = 2, + IAVF_RX_DESC_ERROR_L3L4E_DMAC_ERR = 3, + IAVF_RX_DESC_ERROR_L3L4E_DMAC_WARN = 4 +}; + +#define IAVF_RXD_QW1_PTYPE_SHIFT 30 +#define IAVF_RXD_QW1_PTYPE_MASK (0xFFULL << IAVF_RXD_QW1_PTYPE_SHIFT) + +/* Packet type non-ip values */ +enum iavf_rx_l2_ptype { + IAVF_RX_PTYPE_L2_RESERVED = 0, + IAVF_RX_PTYPE_L2_MAC_PAY2 = 1, + IAVF_RX_PTYPE_L2_TIMESYNC_PAY2 = 2, + IAVF_RX_PTYPE_L2_FIP_PAY2 = 3, + IAVF_RX_PTYPE_L2_OUI_PAY2 = 4, + IAVF_RX_PTYPE_L2_MACCNTRL_PAY2 = 5, + IAVF_RX_PTYPE_L2_LLDP_PAY2 = 6, + IAVF_RX_PTYPE_L2_ECP_PAY2 = 7, + IAVF_RX_PTYPE_L2_EVB_PAY2 = 8, + IAVF_RX_PTYPE_L2_QCN_PAY2 = 9, + IAVF_RX_PTYPE_L2_EAPOL_PAY2 = 10, + IAVF_RX_PTYPE_L2_ARP = 11, + IAVF_RX_PTYPE_L2_FCOE_PAY3 = 12, + IAVF_RX_PTYPE_L2_FCOE_FCDATA_PAY3 = 13, + IAVF_RX_PTYPE_L2_FCOE_FCRDY_PAY3 = 14, + IAVF_RX_PTYPE_L2_FCOE_FCRSP_PAY3 = 15, + IAVF_RX_PTYPE_L2_FCOE_FCOTHER_PA = 16, + IAVF_RX_PTYPE_L2_FCOE_VFT_PAY3 = 17, + IAVF_RX_PTYPE_L2_FCOE_VFT_FCDATA = 18, + IAVF_RX_PTYPE_L2_FCOE_VFT_FCRDY = 19, + IAVF_RX_PTYPE_L2_FCOE_VFT_FCRSP = 20, + IAVF_RX_PTYPE_L2_FCOE_VFT_FCOTHER = 21, + IAVF_RX_PTYPE_GRENAT4_MAC_PAY3 = 58, + IAVF_RX_PTYPE_GRENAT4_MACVLAN_IPV6_ICMP_PAY4 = 87, + IAVF_RX_PTYPE_GRENAT6_MAC_PAY3 = 124, + IAVF_RX_PTYPE_GRENAT6_MACVLAN_IPV6_ICMP_PAY4 = 153 +}; + +struct iavf_rx_ptype_decoded { + u32 ptype:8; + u32 known:1; + u32 outer_ip:1; + u32 outer_ip_ver:1; + u32 outer_frag:1; + u32 tunnel_type:3; + u32 tunnel_end_prot:2; + u32 tunnel_end_frag:1; + u32 inner_prot:4; + u32 payload_layer:3; +}; + +enum iavf_rx_ptype_outer_ip { + IAVF_RX_PTYPE_OUTER_L2 = 0, + IAVF_RX_PTYPE_OUTER_IP = 1 +}; + +enum iavf_rx_ptype_outer_ip_ver { + IAVF_RX_PTYPE_OUTER_NONE = 0, + IAVF_RX_PTYPE_OUTER_IPV4 = 0, + IAVF_RX_PTYPE_OUTER_IPV6 = 1 +}; + +enum iavf_rx_ptype_outer_fragmented { + IAVF_RX_PTYPE_NOT_FRAG = 0, + IAVF_RX_PTYPE_FRAG = 1 +}; + +enum iavf_rx_ptype_tunnel_type { + IAVF_RX_PTYPE_TUNNEL_NONE = 0, + IAVF_RX_PTYPE_TUNNEL_IP_IP = 1, + IAVF_RX_PTYPE_TUNNEL_IP_GRENAT = 2, + IAVF_RX_PTYPE_TUNNEL_IP_GRENAT_MAC = 3, + IAVF_RX_PTYPE_TUNNEL_IP_GRENAT_MAC_VLAN = 4, +}; + +enum iavf_rx_ptype_tunnel_end_prot { + IAVF_RX_PTYPE_TUNNEL_END_NONE = 0, + IAVF_RX_PTYPE_TUNNEL_END_IPV4 = 1, + IAVF_RX_PTYPE_TUNNEL_END_IPV6 = 2, +}; + +enum iavf_rx_ptype_inner_prot { + IAVF_RX_PTYPE_INNER_PROT_NONE = 0, + IAVF_RX_PTYPE_INNER_PROT_UDP = 1, + IAVF_RX_PTYPE_INNER_PROT_TCP = 2, + IAVF_RX_PTYPE_INNER_PROT_SCTP = 3, + IAVF_RX_PTYPE_INNER_PROT_ICMP = 4, + IAVF_RX_PTYPE_INNER_PROT_TIMESYNC = 5 +}; + +enum iavf_rx_ptype_payload_layer { + IAVF_RX_PTYPE_PAYLOAD_LAYER_NONE = 0, + IAVF_RX_PTYPE_PAYLOAD_LAYER_PAY2 = 1, + IAVF_RX_PTYPE_PAYLOAD_LAYER_PAY3 = 2, + IAVF_RX_PTYPE_PAYLOAD_LAYER_PAY4 = 3, +}; + +#define IAVF_RXD_QW1_LENGTH_PBUF_SHIFT 38 +#define IAVF_RXD_QW1_LENGTH_PBUF_MASK (0x3FFFULL << \ + IAVF_RXD_QW1_LENGTH_PBUF_SHIFT) + +#define IAVF_RXD_QW1_LENGTH_HBUF_SHIFT 52 +#define IAVF_RXD_QW1_LENGTH_HBUF_MASK (0x7FFULL << \ + IAVF_RXD_QW1_LENGTH_HBUF_SHIFT) + +#define IAVF_RXD_QW1_LENGTH_SPH_SHIFT 63 +#define IAVF_RXD_QW1_LENGTH_SPH_MASK BIT_ULL(IAVF_RXD_QW1_LENGTH_SPH_SHIFT) + +enum iavf_rx_desc_ext_status_bits { + /* Note: These are predefined bit offsets */ + IAVF_RX_DESC_EXT_STATUS_L2TAG2P_SHIFT = 0, + IAVF_RX_DESC_EXT_STATUS_L2TAG3P_SHIFT = 1, + IAVF_RX_DESC_EXT_STATUS_FLEXBL_SHIFT = 2, /* 2 BITS */ + IAVF_RX_DESC_EXT_STATUS_FLEXBH_SHIFT = 4, /* 2 BITS */ + IAVF_RX_DESC_EXT_STATUS_FDLONGB_SHIFT = 9, + IAVF_RX_DESC_EXT_STATUS_FCOELONGB_SHIFT = 10, + IAVF_RX_DESC_EXT_STATUS_PELONGB_SHIFT = 11, +}; + +enum iavf_rx_desc_pe_status_bits { + /* Note: These are predefined bit offsets */ + IAVF_RX_DESC_PE_STATUS_QPID_SHIFT = 0, /* 18 BITS */ + IAVF_RX_DESC_PE_STATUS_L4PORT_SHIFT = 0, /* 16 BITS */ + IAVF_RX_DESC_PE_STATUS_IPINDEX_SHIFT = 16, /* 8 BITS */ + IAVF_RX_DESC_PE_STATUS_QPIDHIT_SHIFT = 24, + IAVF_RX_DESC_PE_STATUS_APBVTHIT_SHIFT = 25, + IAVF_RX_DESC_PE_STATUS_PORTV_SHIFT = 26, + IAVF_RX_DESC_PE_STATUS_URG_SHIFT = 27, + IAVF_RX_DESC_PE_STATUS_IPFRAG_SHIFT = 28, + IAVF_RX_DESC_PE_STATUS_IPOPT_SHIFT = 29 +}; + +#define IAVF_RX_PROG_STATUS_DESC_LENGTH_SHIFT 38 +#define IAVF_RX_PROG_STATUS_DESC_LENGTH 0x2000000 + +#define IAVF_RX_PROG_STATUS_DESC_QW1_PROGID_SHIFT 2 +#define IAVF_RX_PROG_STATUS_DESC_QW1_PROGID_MASK (0x7UL << \ + IAVF_RX_PROG_STATUS_DESC_QW1_PROGID_SHIFT) + +#define IAVF_RX_PROG_STATUS_DESC_QW1_ERROR_SHIFT 19 +#define IAVF_RX_PROG_STATUS_DESC_QW1_ERROR_MASK (0x3FUL << \ + IAVF_RX_PROG_STATUS_DESC_QW1_ERROR_SHIFT) + +enum iavf_rx_prog_status_desc_status_bits { + /* Note: These are predefined bit offsets */ + IAVF_RX_PROG_STATUS_DESC_DD_SHIFT = 0, + IAVF_RX_PROG_STATUS_DESC_PROG_ID_SHIFT = 2 /* 3 BITS */ +}; + +enum iavf_rx_prog_status_desc_prog_id_masks { + IAVF_RX_PROG_STATUS_DESC_FD_FILTER_STATUS = 1, + IAVF_RX_PROG_STATUS_DESC_FCOE_CTXT_PROG_STATUS = 2, + IAVF_RX_PROG_STATUS_DESC_FCOE_CTXT_INVL_STATUS = 4, +}; + +enum iavf_rx_prog_status_desc_error_bits { + /* Note: These are predefined bit offsets */ + IAVF_RX_PROG_STATUS_DESC_FD_TBL_FULL_SHIFT = 0, + IAVF_RX_PROG_STATUS_DESC_NO_FD_ENTRY_SHIFT = 1, + IAVF_RX_PROG_STATUS_DESC_FCOE_TBL_FULL_SHIFT = 2, + IAVF_RX_PROG_STATUS_DESC_FCOE_CONFLICT_SHIFT = 3 +}; + +/* TX Descriptor */ +struct iavf_tx_desc { + __le64 buffer_addr; /* Address of descriptor's data buf */ + __le64 cmd_type_offset_bsz; +}; + +#define IAVF_TXD_QW1_DTYPE_SHIFT 0 +#define IAVF_TXD_QW1_DTYPE_MASK (0xFUL << IAVF_TXD_QW1_DTYPE_SHIFT) + +enum iavf_tx_desc_dtype_value { + IAVF_TX_DESC_DTYPE_DATA = 0x0, + IAVF_TX_DESC_DTYPE_NOP = 0x1, /* same as Context desc */ + IAVF_TX_DESC_DTYPE_CONTEXT = 0x1, + IAVF_TX_DESC_DTYPE_FCOE_CTX = 0x2, + IAVF_TX_DESC_DTYPE_FILTER_PROG = 0x8, + IAVF_TX_DESC_DTYPE_DDP_CTX = 0x9, + IAVF_TX_DESC_DTYPE_FLEX_DATA = 0xB, + IAVF_TX_DESC_DTYPE_FLEX_CTX_1 = 0xC, + IAVF_TX_DESC_DTYPE_FLEX_CTX_2 = 0xD, + IAVF_TX_DESC_DTYPE_DESC_DONE = 0xF +}; + +#define IAVF_TXD_QW1_CMD_SHIFT 4 +#define IAVF_TXD_QW1_CMD_MASK (0x3FFUL << IAVF_TXD_QW1_CMD_SHIFT) + +enum iavf_tx_desc_cmd_bits { + IAVF_TX_DESC_CMD_EOP = 0x0001, + IAVF_TX_DESC_CMD_RS = 0x0002, + IAVF_TX_DESC_CMD_ICRC = 0x0004, + IAVF_TX_DESC_CMD_IL2TAG1 = 0x0008, + IAVF_TX_DESC_CMD_DUMMY = 0x0010, + IAVF_TX_DESC_CMD_IIPT_NONIP = 0x0000, /* 2 BITS */ + IAVF_TX_DESC_CMD_IIPT_IPV6 = 0x0020, /* 2 BITS */ + IAVF_TX_DESC_CMD_IIPT_IPV4 = 0x0040, /* 2 BITS */ + IAVF_TX_DESC_CMD_IIPT_IPV4_CSUM = 0x0060, /* 2 BITS */ + IAVF_TX_DESC_CMD_FCOET = 0x0080, + IAVF_TX_DESC_CMD_L4T_EOFT_UNK = 0x0000, /* 2 BITS */ + IAVF_TX_DESC_CMD_L4T_EOFT_TCP = 0x0100, /* 2 BITS */ + IAVF_TX_DESC_CMD_L4T_EOFT_SCTP = 0x0200, /* 2 BITS */ + IAVF_TX_DESC_CMD_L4T_EOFT_UDP = 0x0300, /* 2 BITS */ + IAVF_TX_DESC_CMD_L4T_EOFT_EOF_N = 0x0000, /* 2 BITS */ + IAVF_TX_DESC_CMD_L4T_EOFT_EOF_T = 0x0100, /* 2 BITS */ + IAVF_TX_DESC_CMD_L4T_EOFT_EOF_NI = 0x0200, /* 2 BITS */ + IAVF_TX_DESC_CMD_L4T_EOFT_EOF_A = 0x0300, /* 2 BITS */ +}; + +#define IAVF_TXD_QW1_OFFSET_SHIFT 16 +#define IAVF_TXD_QW1_OFFSET_MASK (0x3FFFFULL << \ + IAVF_TXD_QW1_OFFSET_SHIFT) + +enum iavf_tx_desc_length_fields { + /* Note: These are predefined bit offsets */ + IAVF_TX_DESC_LENGTH_MACLEN_SHIFT = 0, /* 7 BITS */ + IAVF_TX_DESC_LENGTH_IPLEN_SHIFT = 7, /* 7 BITS */ + IAVF_TX_DESC_LENGTH_L4_FC_LEN_SHIFT = 14 /* 4 BITS */ +}; + +#define IAVF_TXD_QW1_TX_BUF_SZ_SHIFT 34 +#define IAVF_TXD_QW1_TX_BUF_SZ_MASK (0x3FFFULL << \ + IAVF_TXD_QW1_TX_BUF_SZ_SHIFT) + +#define IAVF_TXD_QW1_L2TAG1_SHIFT 48 +#define IAVF_TXD_QW1_L2TAG1_MASK (0xFFFFULL << IAVF_TXD_QW1_L2TAG1_SHIFT) + +/* Context descriptors */ +struct iavf_tx_context_desc { + __le32 tunneling_params; + __le16 l2tag2; + __le16 rsvd; + __le64 type_cmd_tso_mss; +}; + +#define IAVF_TXD_CTX_QW1_CMD_SHIFT 4 +#define IAVF_TXD_CTX_QW1_CMD_MASK (0xFFFFUL << IAVF_TXD_CTX_QW1_CMD_SHIFT) + +enum iavf_tx_ctx_desc_cmd_bits { + IAVF_TX_CTX_DESC_TSO = 0x01, + IAVF_TX_CTX_DESC_TSYN = 0x02, + IAVF_TX_CTX_DESC_IL2TAG2 = 0x04, + IAVF_TX_CTX_DESC_IL2TAG2_IL2H = 0x08, + IAVF_TX_CTX_DESC_SWTCH_NOTAG = 0x00, + IAVF_TX_CTX_DESC_SWTCH_UPLINK = 0x10, + IAVF_TX_CTX_DESC_SWTCH_LOCAL = 0x20, + IAVF_TX_CTX_DESC_SWTCH_VSI = 0x30, + IAVF_TX_CTX_DESC_SWPE = 0x40 +}; + +/* Packet Classifier Types for filters */ +enum iavf_filter_pctype { + /* Note: Values 0-28 are reserved for future use. + * Value 29, 30, 32 are not supported on XL710 and X710. + */ + IAVF_FILTER_PCTYPE_NONF_UNICAST_IPV4_UDP = 29, + IAVF_FILTER_PCTYPE_NONF_MULTICAST_IPV4_UDP = 30, + IAVF_FILTER_PCTYPE_NONF_IPV4_UDP = 31, + IAVF_FILTER_PCTYPE_NONF_IPV4_TCP_SYN_NO_ACK = 32, + IAVF_FILTER_PCTYPE_NONF_IPV4_TCP = 33, + IAVF_FILTER_PCTYPE_NONF_IPV4_SCTP = 34, + IAVF_FILTER_PCTYPE_NONF_IPV4_OTHER = 35, + IAVF_FILTER_PCTYPE_FRAG_IPV4 = 36, + /* Note: Values 37-38 are reserved for future use. + * Value 39, 40, 42 are not supported on XL710 and X710. + */ + IAVF_FILTER_PCTYPE_NONF_UNICAST_IPV6_UDP = 39, + IAVF_FILTER_PCTYPE_NONF_MULTICAST_IPV6_UDP = 40, + IAVF_FILTER_PCTYPE_NONF_IPV6_UDP = 41, + IAVF_FILTER_PCTYPE_NONF_IPV6_TCP_SYN_NO_ACK = 42, + IAVF_FILTER_PCTYPE_NONF_IPV6_TCP = 43, + IAVF_FILTER_PCTYPE_NONF_IPV6_SCTP = 44, + IAVF_FILTER_PCTYPE_NONF_IPV6_OTHER = 45, + IAVF_FILTER_PCTYPE_FRAG_IPV6 = 46, + /* Note: Value 47 is reserved for future use */ + IAVF_FILTER_PCTYPE_FCOE_OX = 48, + IAVF_FILTER_PCTYPE_FCOE_RX = 49, + IAVF_FILTER_PCTYPE_FCOE_OTHER = 50, + /* Note: Values 51-62 are reserved for future use */ + IAVF_FILTER_PCTYPE_L2_PAYLOAD = 63, +}; + +#define IAVF_TXD_CTX_QW1_TSO_LEN_SHIFT 30 +#define IAVF_TXD_CTX_QW1_TSO_LEN_MASK (0x3FFFFULL << \ + IAVF_TXD_CTX_QW1_TSO_LEN_SHIFT) + +#define IAVF_TXD_CTX_QW1_MSS_SHIFT 50 +#define IAVF_TXD_CTX_QW1_MSS_MASK (0x3FFFULL << \ + IAVF_TXD_CTX_QW1_MSS_SHIFT) + +#define IAVF_TXD_CTX_QW1_VSI_SHIFT 50 +#define IAVF_TXD_CTX_QW1_VSI_MASK (0x1FFULL << IAVF_TXD_CTX_QW1_VSI_SHIFT) + +#define IAVF_TXD_CTX_QW0_EXT_IP_SHIFT 0 +#define IAVF_TXD_CTX_QW0_EXT_IP_MASK (0x3ULL << \ + IAVF_TXD_CTX_QW0_EXT_IP_SHIFT) + +enum iavf_tx_ctx_desc_eipt_offload { + IAVF_TX_CTX_EXT_IP_NONE = 0x0, + IAVF_TX_CTX_EXT_IP_IPV6 = 0x1, + IAVF_TX_CTX_EXT_IP_IPV4_NO_CSUM = 0x2, + IAVF_TX_CTX_EXT_IP_IPV4 = 0x3 +}; + +#define IAVF_TXD_CTX_QW0_EXT_IPLEN_SHIFT 2 +#define IAVF_TXD_CTX_QW0_EXT_IPLEN_MASK (0x3FULL << \ + IAVF_TXD_CTX_QW0_EXT_IPLEN_SHIFT) + +#define IAVF_TXD_CTX_QW0_NATT_SHIFT 9 +#define IAVF_TXD_CTX_QW0_NATT_MASK (0x3ULL << IAVF_TXD_CTX_QW0_NATT_SHIFT) + +#define IAVF_TXD_CTX_UDP_TUNNELING BIT_ULL(IAVF_TXD_CTX_QW0_NATT_SHIFT) +#define IAVF_TXD_CTX_GRE_TUNNELING (0x2ULL << IAVF_TXD_CTX_QW0_NATT_SHIFT) + +#define IAVF_TXD_CTX_QW0_EIP_NOINC_SHIFT 11 +#define IAVF_TXD_CTX_QW0_EIP_NOINC_MASK \ + BIT_ULL(IAVF_TXD_CTX_QW0_EIP_NOINC_SHIFT) + +#define IAVF_TXD_CTX_EIP_NOINC_IPID_CONST IAVF_TXD_CTX_QW0_EIP_NOINC_MASK + +#define IAVF_TXD_CTX_QW0_NATLEN_SHIFT 12 +#define IAVF_TXD_CTX_QW0_NATLEN_MASK (0X7FULL << \ + IAVF_TXD_CTX_QW0_NATLEN_SHIFT) + +#define IAVF_TXD_CTX_QW0_DECTTL_SHIFT 19 +#define IAVF_TXD_CTX_QW0_DECTTL_MASK (0xFULL << \ + IAVF_TXD_CTX_QW0_DECTTL_SHIFT) + +#define IAVF_TXD_CTX_QW0_L4T_CS_SHIFT 23 +#define IAVF_TXD_CTX_QW0_L4T_CS_MASK BIT_ULL(IAVF_TXD_CTX_QW0_L4T_CS_SHIFT) + +/* Statistics collected by each port, VSI, VEB, and S-channel */ +struct iavf_eth_stats { + u64 rx_bytes; /* gorc */ + u64 rx_unicast; /* uprc */ + u64 rx_multicast; /* mprc */ + u64 rx_broadcast; /* bprc */ + u64 rx_discards; /* rdpc */ + u64 rx_unknown_protocol; /* rupp */ + u64 tx_bytes; /* gotc */ + u64 tx_unicast; /* uptc */ + u64 tx_multicast; /* mptc */ + u64 tx_broadcast; /* bptc */ + u64 tx_discards; /* tdpc */ + u64 tx_errors; /* tepc */ +}; +#endif /* _IAVF_TYPE_H_ */ diff --git a/drivers/net/ethernet/intel/i40evf/i40evf_virtchnl.c b/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c index 6579dabab78c..e64751da0921 100644 --- a/drivers/net/ethernet/intel/i40evf/i40evf_virtchnl.c +++ b/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c @@ -1,16 +1,16 @@ // SPDX-License-Identifier: GPL-2.0 /* Copyright(c) 2013 - 2018 Intel Corporation. */ -#include "i40evf.h" -#include "i40e_prototype.h" -#include "i40evf_client.h" +#include "iavf.h" +#include "iavf_prototype.h" +#include "iavf_client.h" /* busy wait delay in msec */ -#define I40EVF_BUSY_WAIT_DELAY 10 -#define I40EVF_BUSY_WAIT_COUNT 50 +#define IAVF_BUSY_WAIT_DELAY 10 +#define IAVF_BUSY_WAIT_COUNT 50 /** - * i40evf_send_pf_msg + * iavf_send_pf_msg * @adapter: adapter structure * @op: virtual channel opcode * @msg: pointer to message buffer @@ -18,44 +18,44 @@ * * Send message to PF and print status if failure. **/ -static int i40evf_send_pf_msg(struct i40evf_adapter *adapter, - enum virtchnl_ops op, u8 *msg, u16 len) +static int iavf_send_pf_msg(struct iavf_adapter *adapter, + enum virtchnl_ops op, u8 *msg, u16 len) { - struct i40e_hw *hw = &adapter->hw; - i40e_status err; + struct iavf_hw *hw = &adapter->hw; + iavf_status err; - if (adapter->flags & I40EVF_FLAG_PF_COMMS_FAILED) + if (adapter->flags & IAVF_FLAG_PF_COMMS_FAILED) return 0; /* nothing to see here, move along */ - err = i40e_aq_send_msg_to_pf(hw, op, 0, msg, len, NULL); + err = iavf_aq_send_msg_to_pf(hw, op, 0, msg, len, NULL); if (err) dev_dbg(&adapter->pdev->dev, "Unable to send opcode %d to PF, err %s, aq_err %s\n", - op, i40evf_stat_str(hw, err), - i40evf_aq_str(hw, hw->aq.asq_last_status)); + op, iavf_stat_str(hw, err), + iavf_aq_str(hw, hw->aq.asq_last_status)); return err; } /** - * i40evf_send_api_ver + * iavf_send_api_ver * @adapter: adapter structure * * Send API version admin queue message to the PF. The reply is not checked * in this function. Returns 0 if the message was successfully * sent, or one of the I40E_ADMIN_QUEUE_ERROR_ statuses if not. **/ -int i40evf_send_api_ver(struct i40evf_adapter *adapter) +int iavf_send_api_ver(struct iavf_adapter *adapter) { struct virtchnl_version_info vvi; vvi.major = VIRTCHNL_VERSION_MAJOR; vvi.minor = VIRTCHNL_VERSION_MINOR; - return i40evf_send_pf_msg(adapter, VIRTCHNL_OP_VERSION, (u8 *)&vvi, - sizeof(vvi)); + return iavf_send_pf_msg(adapter, VIRTCHNL_OP_VERSION, (u8 *)&vvi, + sizeof(vvi)); } /** - * i40evf_verify_api_ver + * iavf_verify_api_ver * @adapter: adapter structure * * Compare API versions with the PF. Must be called after admin queue is @@ -63,15 +63,15 @@ int i40evf_send_api_ver(struct i40evf_adapter *adapter) * I40E_ERR_ADMIN_QUEUE_NO_WORK if the admin queue is empty, and any errors * from the firmware are propagated. **/ -int i40evf_verify_api_ver(struct i40evf_adapter *adapter) +int iavf_verify_api_ver(struct iavf_adapter *adapter) { struct virtchnl_version_info *pf_vvi; - struct i40e_hw *hw = &adapter->hw; + struct iavf_hw *hw = &adapter->hw; struct i40e_arq_event_info event; enum virtchnl_ops op; - i40e_status err; + iavf_status err; - event.buf_len = I40EVF_MAX_AQ_BUF_SIZE; + event.buf_len = IAVF_MAX_AQ_BUF_SIZE; event.msg_buf = kzalloc(event.buf_len, GFP_KERNEL); if (!event.msg_buf) { err = -ENOMEM; @@ -79,8 +79,8 @@ int i40evf_verify_api_ver(struct i40evf_adapter *adapter) } while (1) { - err = i40evf_clean_arq_element(hw, &event, NULL); - /* When the AQ is empty, i40evf_clean_arq_element will return + err = iavf_clean_arq_element(hw, &event, NULL); + /* When the AQ is empty, iavf_clean_arq_element will return * nonzero and this loop will terminate. */ if (err) @@ -92,7 +92,7 @@ int i40evf_verify_api_ver(struct i40evf_adapter *adapter) } - err = (i40e_status)le32_to_cpu(event.desc.cookie_low); + err = (iavf_status)le32_to_cpu(event.desc.cookie_low); if (err) goto out_alloc; @@ -118,14 +118,14 @@ out: } /** - * i40evf_send_vf_config_msg + * iavf_send_vf_config_msg * @adapter: adapter structure * * Send VF configuration request admin queue message to the PF. The reply * is not checked in this function. Returns 0 if the message was * successfully sent, or one of the I40E_ADMIN_QUEUE_ERROR_ statuses if not. **/ -int i40evf_send_vf_config_msg(struct i40evf_adapter *adapter) +int iavf_send_vf_config_msg(struct iavf_adapter *adapter) { u32 caps; @@ -142,45 +142,43 @@ int i40evf_send_vf_config_msg(struct i40evf_adapter *adapter) VIRTCHNL_VF_OFFLOAD_ADQ; adapter->current_op = VIRTCHNL_OP_GET_VF_RESOURCES; - adapter->aq_required &= ~I40EVF_FLAG_AQ_GET_CONFIG; + adapter->aq_required &= ~IAVF_FLAG_AQ_GET_CONFIG; if (PF_IS_V11(adapter)) - return i40evf_send_pf_msg(adapter, - VIRTCHNL_OP_GET_VF_RESOURCES, - (u8 *)&caps, sizeof(caps)); + return iavf_send_pf_msg(adapter, VIRTCHNL_OP_GET_VF_RESOURCES, + (u8 *)&caps, sizeof(caps)); else - return i40evf_send_pf_msg(adapter, - VIRTCHNL_OP_GET_VF_RESOURCES, - NULL, 0); + return iavf_send_pf_msg(adapter, VIRTCHNL_OP_GET_VF_RESOURCES, + NULL, 0); } /** - * i40evf_validate_num_queues + * iavf_validate_num_queues * @adapter: adapter structure * * Validate that the number of queues the PF has sent in * VIRTCHNL_OP_GET_VF_RESOURCES is not larger than the VF can handle. **/ -static void i40evf_validate_num_queues(struct i40evf_adapter *adapter) +static void iavf_validate_num_queues(struct iavf_adapter *adapter) { - if (adapter->vf_res->num_queue_pairs > I40EVF_MAX_REQ_QUEUES) { + if (adapter->vf_res->num_queue_pairs > IAVF_MAX_REQ_QUEUES) { struct virtchnl_vsi_resource *vsi_res; int i; dev_info(&adapter->pdev->dev, "Received %d queues, but can only have a max of %d\n", adapter->vf_res->num_queue_pairs, - I40EVF_MAX_REQ_QUEUES); + IAVF_MAX_REQ_QUEUES); dev_info(&adapter->pdev->dev, "Fixing by reducing queues to %d\n", - I40EVF_MAX_REQ_QUEUES); - adapter->vf_res->num_queue_pairs = I40EVF_MAX_REQ_QUEUES; + IAVF_MAX_REQ_QUEUES); + adapter->vf_res->num_queue_pairs = IAVF_MAX_REQ_QUEUES; for (i = 0; i < adapter->vf_res->num_vsis; i++) { vsi_res = &adapter->vf_res->vsi_res[i]; - vsi_res->num_queue_pairs = I40EVF_MAX_REQ_QUEUES; + vsi_res->num_queue_pairs = IAVF_MAX_REQ_QUEUES; } } } /** - * i40evf_get_vf_config + * iavf_get_vf_config * @adapter: private adapter structure * * Get VF configuration from PF and populate hw structure. Must be called after @@ -188,16 +186,16 @@ static void i40evf_validate_num_queues(struct i40evf_adapter *adapter) * with maximum timeout. Response from PF is returned in the buffer for further * processing by the caller. **/ -int i40evf_get_vf_config(struct i40evf_adapter *adapter) +int iavf_get_vf_config(struct iavf_adapter *adapter) { - struct i40e_hw *hw = &adapter->hw; + struct iavf_hw *hw = &adapter->hw; struct i40e_arq_event_info event; enum virtchnl_ops op; - i40e_status err; + iavf_status err; u16 len; len = sizeof(struct virtchnl_vf_resource) + - I40E_MAX_VF_VSI * sizeof(struct virtchnl_vsi_resource); + IAVF_MAX_VF_VSI * sizeof(struct virtchnl_vsi_resource); event.buf_len = len; event.msg_buf = kzalloc(event.buf_len, GFP_KERNEL); if (!event.msg_buf) { @@ -206,10 +204,10 @@ int i40evf_get_vf_config(struct i40evf_adapter *adapter) } while (1) { - /* When the AQ is empty, i40evf_clean_arq_element will return + /* When the AQ is empty, iavf_clean_arq_element will return * nonzero and this loop will terminate. */ - err = i40evf_clean_arq_element(hw, &event, NULL); + err = iavf_clean_arq_element(hw, &event, NULL); if (err) goto out_alloc; op = @@ -218,15 +216,15 @@ int i40evf_get_vf_config(struct i40evf_adapter *adapter) break; } - err = (i40e_status)le32_to_cpu(event.desc.cookie_low); + err = (iavf_status)le32_to_cpu(event.desc.cookie_low); memcpy(adapter->vf_res, event.msg_buf, min(event.msg_len, len)); /* some PFs send more queues than we should have so validate that * we aren't getting too many queues */ if (!err) - i40evf_validate_num_queues(adapter); - i40e_vf_parse_hw_config(hw, adapter->vf_res); + iavf_validate_num_queues(adapter); + iavf_vf_parse_hw_config(hw, adapter->vf_res); out_alloc: kfree(event.msg_buf); out: @@ -234,17 +232,17 @@ out: } /** - * i40evf_configure_queues + * iavf_configure_queues * @adapter: adapter structure * * Request that the PF set up our (previously allocated) queues. **/ -void i40evf_configure_queues(struct i40evf_adapter *adapter) +void iavf_configure_queues(struct iavf_adapter *adapter) { struct virtchnl_vsi_queue_config_info *vqci; struct virtchnl_queue_pair_info *vqpi; int pairs = adapter->num_active_queues; - int i, len, max_frame = I40E_MAX_RXBUFFER; + int i, len, max_frame = IAVF_MAX_RXBUFFER; if (adapter->current_op != VIRTCHNL_OP_UNKNOWN) { /* bail because we already have a command pending */ @@ -260,9 +258,9 @@ void i40evf_configure_queues(struct i40evf_adapter *adapter) return; /* Limit maximum frame size when jumbo frames is not enabled */ - if (!(adapter->flags & I40EVF_FLAG_LEGACY_RX) && + if (!(adapter->flags & IAVF_FLAG_LEGACY_RX) && (adapter->netdev->mtu <= ETH_DATA_LEN)) - max_frame = I40E_RXBUFFER_1536 - NET_IP_ALIGN; + max_frame = IAVF_RXBUFFER_1536 - NET_IP_ALIGN; vqci->vsi_id = adapter->vsi_res->vsi_id; vqci->num_queue_pairs = pairs; @@ -282,23 +280,23 @@ void i40evf_configure_queues(struct i40evf_adapter *adapter) vqpi->rxq.max_pkt_size = max_frame; vqpi->rxq.databuffer_size = ALIGN(adapter->rx_rings[i].rx_buf_len, - BIT_ULL(I40E_RXQ_CTX_DBUFF_SHIFT)); + BIT_ULL(IAVF_RXQ_CTX_DBUFF_SHIFT)); vqpi++; } - adapter->aq_required &= ~I40EVF_FLAG_AQ_CONFIGURE_QUEUES; - i40evf_send_pf_msg(adapter, VIRTCHNL_OP_CONFIG_VSI_QUEUES, - (u8 *)vqci, len); + adapter->aq_required &= ~IAVF_FLAG_AQ_CONFIGURE_QUEUES; + iavf_send_pf_msg(adapter, VIRTCHNL_OP_CONFIG_VSI_QUEUES, + (u8 *)vqci, len); kfree(vqci); } /** - * i40evf_enable_queues + * iavf_enable_queues * @adapter: adapter structure * * Request that the PF enable all of our queues. **/ -void i40evf_enable_queues(struct i40evf_adapter *adapter) +void iavf_enable_queues(struct iavf_adapter *adapter) { struct virtchnl_queue_select vqs; @@ -312,18 +310,18 @@ void i40evf_enable_queues(struct i40evf_adapter *adapter) vqs.vsi_id = adapter->vsi_res->vsi_id; vqs.tx_queues = BIT(adapter->num_active_queues) - 1; vqs.rx_queues = vqs.tx_queues; - adapter->aq_required &= ~I40EVF_FLAG_AQ_ENABLE_QUEUES; - i40evf_send_pf_msg(adapter, VIRTCHNL_OP_ENABLE_QUEUES, - (u8 *)&vqs, sizeof(vqs)); + adapter->aq_required &= ~IAVF_FLAG_AQ_ENABLE_QUEUES; + iavf_send_pf_msg(adapter, VIRTCHNL_OP_ENABLE_QUEUES, + (u8 *)&vqs, sizeof(vqs)); } /** - * i40evf_disable_queues + * iavf_disable_queues * @adapter: adapter structure * * Request that the PF disable all of our queues. **/ -void i40evf_disable_queues(struct i40evf_adapter *adapter) +void iavf_disable_queues(struct iavf_adapter *adapter) { struct virtchnl_queue_select vqs; @@ -337,24 +335,24 @@ void i40evf_disable_queues(struct i40evf_adapter *adapter) vqs.vsi_id = adapter->vsi_res->vsi_id; vqs.tx_queues = BIT(adapter->num_active_queues) - 1; vqs.rx_queues = vqs.tx_queues; - adapter->aq_required &= ~I40EVF_FLAG_AQ_DISABLE_QUEUES; - i40evf_send_pf_msg(adapter, VIRTCHNL_OP_DISABLE_QUEUES, - (u8 *)&vqs, sizeof(vqs)); + adapter->aq_required &= ~IAVF_FLAG_AQ_DISABLE_QUEUES; + iavf_send_pf_msg(adapter, VIRTCHNL_OP_DISABLE_QUEUES, + (u8 *)&vqs, sizeof(vqs)); } /** - * i40evf_map_queues + * iavf_map_queues * @adapter: adapter structure * * Request that the PF map queues to interrupt vectors. Misc causes, including * admin queue, are always mapped to vector 0. **/ -void i40evf_map_queues(struct i40evf_adapter *adapter) +void iavf_map_queues(struct iavf_adapter *adapter) { struct virtchnl_irq_map_info *vimi; struct virtchnl_vector_map *vecmap; int v_idx, q_vectors, len; - struct i40e_q_vector *q_vector; + struct iavf_q_vector *q_vector; if (adapter->current_op != VIRTCHNL_OP_UNKNOWN) { /* bail because we already have a command pending */ @@ -383,8 +381,8 @@ void i40evf_map_queues(struct i40evf_adapter *adapter) vecmap->vector_id = v_idx + NONQ_VECS; vecmap->txq_map = q_vector->ring_mask; vecmap->rxq_map = q_vector->ring_mask; - vecmap->rxitr_idx = I40E_RX_ITR; - vecmap->txitr_idx = I40E_TX_ITR; + vecmap->rxitr_idx = IAVF_RX_ITR; + vecmap->txitr_idx = IAVF_TX_ITR; } /* Misc vector last - this is only for AdminQ messages */ vecmap = &vimi->vecmap[v_idx]; @@ -393,21 +391,21 @@ void i40evf_map_queues(struct i40evf_adapter *adapter) vecmap->txq_map = 0; vecmap->rxq_map = 0; - adapter->aq_required &= ~I40EVF_FLAG_AQ_MAP_VECTORS; - i40evf_send_pf_msg(adapter, VIRTCHNL_OP_CONFIG_IRQ_MAP, - (u8 *)vimi, len); + adapter->aq_required &= ~IAVF_FLAG_AQ_MAP_VECTORS; + iavf_send_pf_msg(adapter, VIRTCHNL_OP_CONFIG_IRQ_MAP, + (u8 *)vimi, len); kfree(vimi); } /** - * i40evf_request_queues + * iavf_request_queues * @adapter: adapter structure * @num: number of requested queues * * We get a default number of queues from the PF. This enables us to request a * different number. Returns 0 on success, negative on failure **/ -int i40evf_request_queues(struct i40evf_adapter *adapter, int num) +int iavf_request_queues(struct iavf_adapter *adapter, int num) { struct virtchnl_vf_res_request vfres; @@ -421,22 +419,22 @@ int i40evf_request_queues(struct i40evf_adapter *adapter, int num) vfres.num_queue_pairs = num; adapter->current_op = VIRTCHNL_OP_REQUEST_QUEUES; - adapter->flags |= I40EVF_FLAG_REINIT_ITR_NEEDED; - return i40evf_send_pf_msg(adapter, VIRTCHNL_OP_REQUEST_QUEUES, - (u8 *)&vfres, sizeof(vfres)); + adapter->flags |= IAVF_FLAG_REINIT_ITR_NEEDED; + return iavf_send_pf_msg(adapter, VIRTCHNL_OP_REQUEST_QUEUES, + (u8 *)&vfres, sizeof(vfres)); } /** - * i40evf_add_ether_addrs + * iavf_add_ether_addrs * @adapter: adapter structure * * Request that the PF add one or more addresses to our filters. **/ -void i40evf_add_ether_addrs(struct i40evf_adapter *adapter) +void iavf_add_ether_addrs(struct iavf_adapter *adapter) { struct virtchnl_ether_addr_list *veal; int len, i = 0, count = 0; - struct i40evf_mac_filter *f; + struct iavf_mac_filter *f; bool more = false; if (adapter->current_op != VIRTCHNL_OP_UNKNOWN) { @@ -453,7 +451,7 @@ void i40evf_add_ether_addrs(struct i40evf_adapter *adapter) count++; } if (!count) { - adapter->aq_required &= ~I40EVF_FLAG_AQ_ADD_MAC_FILTER; + adapter->aq_required &= ~IAVF_FLAG_AQ_ADD_MAC_FILTER; spin_unlock_bh(&adapter->mac_vlan_list_lock); return; } @@ -461,9 +459,9 @@ void i40evf_add_ether_addrs(struct i40evf_adapter *adapter) len = sizeof(struct virtchnl_ether_addr_list) + (count * sizeof(struct virtchnl_ether_addr)); - if (len > I40EVF_MAX_AQ_BUF_SIZE) { + if (len > IAVF_MAX_AQ_BUF_SIZE) { dev_warn(&adapter->pdev->dev, "Too many add MAC changes in one request\n"); - count = (I40EVF_MAX_AQ_BUF_SIZE - + count = (IAVF_MAX_AQ_BUF_SIZE - sizeof(struct virtchnl_ether_addr_list)) / sizeof(struct virtchnl_ether_addr); len = sizeof(struct virtchnl_ether_addr_list) + @@ -489,25 +487,24 @@ void i40evf_add_ether_addrs(struct i40evf_adapter *adapter) } } if (!more) - adapter->aq_required &= ~I40EVF_FLAG_AQ_ADD_MAC_FILTER; + adapter->aq_required &= ~IAVF_FLAG_AQ_ADD_MAC_FILTER; spin_unlock_bh(&adapter->mac_vlan_list_lock); - i40evf_send_pf_msg(adapter, VIRTCHNL_OP_ADD_ETH_ADDR, - (u8 *)veal, len); + iavf_send_pf_msg(adapter, VIRTCHNL_OP_ADD_ETH_ADDR, (u8 *)veal, len); kfree(veal); } /** - * i40evf_del_ether_addrs + * iavf_del_ether_addrs * @adapter: adapter structure * * Request that the PF remove one or more addresses from our filters. **/ -void i40evf_del_ether_addrs(struct i40evf_adapter *adapter) +void iavf_del_ether_addrs(struct iavf_adapter *adapter) { struct virtchnl_ether_addr_list *veal; - struct i40evf_mac_filter *f, *ftmp; + struct iavf_mac_filter *f, *ftmp; int len, i = 0, count = 0; bool more = false; @@ -525,7 +522,7 @@ void i40evf_del_ether_addrs(struct i40evf_adapter *adapter) count++; } if (!count) { - adapter->aq_required &= ~I40EVF_FLAG_AQ_DEL_MAC_FILTER; + adapter->aq_required &= ~IAVF_FLAG_AQ_DEL_MAC_FILTER; spin_unlock_bh(&adapter->mac_vlan_list_lock); return; } @@ -533,9 +530,9 @@ void i40evf_del_ether_addrs(struct i40evf_adapter *adapter) len = sizeof(struct virtchnl_ether_addr_list) + (count * sizeof(struct virtchnl_ether_addr)); - if (len > I40EVF_MAX_AQ_BUF_SIZE) { + if (len > IAVF_MAX_AQ_BUF_SIZE) { dev_warn(&adapter->pdev->dev, "Too many delete MAC changes in one request\n"); - count = (I40EVF_MAX_AQ_BUF_SIZE - + count = (IAVF_MAX_AQ_BUF_SIZE - sizeof(struct virtchnl_ether_addr_list)) / sizeof(struct virtchnl_ether_addr); len = sizeof(struct virtchnl_ether_addr_list) + @@ -561,26 +558,25 @@ void i40evf_del_ether_addrs(struct i40evf_adapter *adapter) } } if (!more) - adapter->aq_required &= ~I40EVF_FLAG_AQ_DEL_MAC_FILTER; + adapter->aq_required &= ~IAVF_FLAG_AQ_DEL_MAC_FILTER; spin_unlock_bh(&adapter->mac_vlan_list_lock); - i40evf_send_pf_msg(adapter, VIRTCHNL_OP_DEL_ETH_ADDR, - (u8 *)veal, len); + iavf_send_pf_msg(adapter, VIRTCHNL_OP_DEL_ETH_ADDR, (u8 *)veal, len); kfree(veal); } /** - * i40evf_add_vlans + * iavf_add_vlans * @adapter: adapter structure * * Request that the PF add one or more VLAN filters to our VSI. **/ -void i40evf_add_vlans(struct i40evf_adapter *adapter) +void iavf_add_vlans(struct iavf_adapter *adapter) { struct virtchnl_vlan_filter_list *vvfl; int len, i = 0, count = 0; - struct i40evf_vlan_filter *f; + struct iavf_vlan_filter *f; bool more = false; if (adapter->current_op != VIRTCHNL_OP_UNKNOWN) { @@ -597,7 +593,7 @@ void i40evf_add_vlans(struct i40evf_adapter *adapter) count++; } if (!count) { - adapter->aq_required &= ~I40EVF_FLAG_AQ_ADD_VLAN_FILTER; + adapter->aq_required &= ~IAVF_FLAG_AQ_ADD_VLAN_FILTER; spin_unlock_bh(&adapter->mac_vlan_list_lock); return; } @@ -605,9 +601,9 @@ void i40evf_add_vlans(struct i40evf_adapter *adapter) len = sizeof(struct virtchnl_vlan_filter_list) + (count * sizeof(u16)); - if (len > I40EVF_MAX_AQ_BUF_SIZE) { + if (len > IAVF_MAX_AQ_BUF_SIZE) { dev_warn(&adapter->pdev->dev, "Too many add VLAN changes in one request\n"); - count = (I40EVF_MAX_AQ_BUF_SIZE - + count = (IAVF_MAX_AQ_BUF_SIZE - sizeof(struct virtchnl_vlan_filter_list)) / sizeof(u16); len = sizeof(struct virtchnl_vlan_filter_list) + @@ -632,24 +628,24 @@ void i40evf_add_vlans(struct i40evf_adapter *adapter) } } if (!more) - adapter->aq_required &= ~I40EVF_FLAG_AQ_ADD_VLAN_FILTER; + adapter->aq_required &= ~IAVF_FLAG_AQ_ADD_VLAN_FILTER; spin_unlock_bh(&adapter->mac_vlan_list_lock); - i40evf_send_pf_msg(adapter, VIRTCHNL_OP_ADD_VLAN, (u8 *)vvfl, len); + iavf_send_pf_msg(adapter, VIRTCHNL_OP_ADD_VLAN, (u8 *)vvfl, len); kfree(vvfl); } /** - * i40evf_del_vlans + * iavf_del_vlans * @adapter: adapter structure * * Request that the PF remove one or more VLAN filters from our VSI. **/ -void i40evf_del_vlans(struct i40evf_adapter *adapter) +void iavf_del_vlans(struct iavf_adapter *adapter) { struct virtchnl_vlan_filter_list *vvfl; - struct i40evf_vlan_filter *f, *ftmp; + struct iavf_vlan_filter *f, *ftmp; int len, i = 0, count = 0; bool more = false; @@ -667,7 +663,7 @@ void i40evf_del_vlans(struct i40evf_adapter *adapter) count++; } if (!count) { - adapter->aq_required &= ~I40EVF_FLAG_AQ_DEL_VLAN_FILTER; + adapter->aq_required &= ~IAVF_FLAG_AQ_DEL_VLAN_FILTER; spin_unlock_bh(&adapter->mac_vlan_list_lock); return; } @@ -675,9 +671,9 @@ void i40evf_del_vlans(struct i40evf_adapter *adapter) len = sizeof(struct virtchnl_vlan_filter_list) + (count * sizeof(u16)); - if (len > I40EVF_MAX_AQ_BUF_SIZE) { + if (len > IAVF_MAX_AQ_BUF_SIZE) { dev_warn(&adapter->pdev->dev, "Too many delete VLAN changes in one request\n"); - count = (I40EVF_MAX_AQ_BUF_SIZE - + count = (IAVF_MAX_AQ_BUF_SIZE - sizeof(struct virtchnl_vlan_filter_list)) / sizeof(u16); len = sizeof(struct virtchnl_vlan_filter_list) + @@ -703,22 +699,22 @@ void i40evf_del_vlans(struct i40evf_adapter *adapter) } } if (!more) - adapter->aq_required &= ~I40EVF_FLAG_AQ_DEL_VLAN_FILTER; + adapter->aq_required &= ~IAVF_FLAG_AQ_DEL_VLAN_FILTER; spin_unlock_bh(&adapter->mac_vlan_list_lock); - i40evf_send_pf_msg(adapter, VIRTCHNL_OP_DEL_VLAN, (u8 *)vvfl, len); + iavf_send_pf_msg(adapter, VIRTCHNL_OP_DEL_VLAN, (u8 *)vvfl, len); kfree(vvfl); } /** - * i40evf_set_promiscuous + * iavf_set_promiscuous * @adapter: adapter structure * @flags: bitmask to control unicast/multicast promiscuous. * * Request that the PF enable promiscuous mode for our VSI. **/ -void i40evf_set_promiscuous(struct i40evf_adapter *adapter, int flags) +void iavf_set_promiscuous(struct iavf_adapter *adapter, int flags) { struct virtchnl_promisc_info vpi; int promisc_all; @@ -733,39 +729,39 @@ void i40evf_set_promiscuous(struct i40evf_adapter *adapter, int flags) promisc_all = FLAG_VF_UNICAST_PROMISC | FLAG_VF_MULTICAST_PROMISC; if ((flags & promisc_all) == promisc_all) { - adapter->flags |= I40EVF_FLAG_PROMISC_ON; - adapter->aq_required &= ~I40EVF_FLAG_AQ_REQUEST_PROMISC; + adapter->flags |= IAVF_FLAG_PROMISC_ON; + adapter->aq_required &= ~IAVF_FLAG_AQ_REQUEST_PROMISC; dev_info(&adapter->pdev->dev, "Entering promiscuous mode\n"); } if (flags & FLAG_VF_MULTICAST_PROMISC) { - adapter->flags |= I40EVF_FLAG_ALLMULTI_ON; - adapter->aq_required &= ~I40EVF_FLAG_AQ_REQUEST_ALLMULTI; + adapter->flags |= IAVF_FLAG_ALLMULTI_ON; + adapter->aq_required &= ~IAVF_FLAG_AQ_REQUEST_ALLMULTI; dev_info(&adapter->pdev->dev, "Entering multicast promiscuous mode\n"); } if (!flags) { - adapter->flags &= ~(I40EVF_FLAG_PROMISC_ON | - I40EVF_FLAG_ALLMULTI_ON); - adapter->aq_required &= ~(I40EVF_FLAG_AQ_RELEASE_PROMISC | - I40EVF_FLAG_AQ_RELEASE_ALLMULTI); + adapter->flags &= ~(IAVF_FLAG_PROMISC_ON | + IAVF_FLAG_ALLMULTI_ON); + adapter->aq_required &= ~(IAVF_FLAG_AQ_RELEASE_PROMISC | + IAVF_FLAG_AQ_RELEASE_ALLMULTI); dev_info(&adapter->pdev->dev, "Leaving promiscuous mode\n"); } adapter->current_op = VIRTCHNL_OP_CONFIG_PROMISCUOUS_MODE; vpi.vsi_id = adapter->vsi_res->vsi_id; vpi.flags = flags; - i40evf_send_pf_msg(adapter, VIRTCHNL_OP_CONFIG_PROMISCUOUS_MODE, - (u8 *)&vpi, sizeof(vpi)); + iavf_send_pf_msg(adapter, VIRTCHNL_OP_CONFIG_PROMISCUOUS_MODE, + (u8 *)&vpi, sizeof(vpi)); } /** - * i40evf_request_stats + * iavf_request_stats * @adapter: adapter structure * * Request VSI statistics from PF. **/ -void i40evf_request_stats(struct i40evf_adapter *adapter) +void iavf_request_stats(struct iavf_adapter *adapter) { struct virtchnl_queue_select vqs; @@ -776,19 +772,19 @@ void i40evf_request_stats(struct i40evf_adapter *adapter) adapter->current_op = VIRTCHNL_OP_GET_STATS; vqs.vsi_id = adapter->vsi_res->vsi_id; /* queue maps are ignored for this message - only the vsi is used */ - if (i40evf_send_pf_msg(adapter, VIRTCHNL_OP_GET_STATS, - (u8 *)&vqs, sizeof(vqs))) + if (iavf_send_pf_msg(adapter, VIRTCHNL_OP_GET_STATS, (u8 *)&vqs, + sizeof(vqs))) /* if the request failed, don't lock out others */ adapter->current_op = VIRTCHNL_OP_UNKNOWN; } /** - * i40evf_get_hena + * iavf_get_hena * @adapter: adapter structure * * Request hash enable capabilities from PF **/ -void i40evf_get_hena(struct i40evf_adapter *adapter) +void iavf_get_hena(struct iavf_adapter *adapter) { if (adapter->current_op != VIRTCHNL_OP_UNKNOWN) { /* bail because we already have a command pending */ @@ -797,18 +793,17 @@ void i40evf_get_hena(struct i40evf_adapter *adapter) return; } adapter->current_op = VIRTCHNL_OP_GET_RSS_HENA_CAPS; - adapter->aq_required &= ~I40EVF_FLAG_AQ_GET_HENA; - i40evf_send_pf_msg(adapter, VIRTCHNL_OP_GET_RSS_HENA_CAPS, - NULL, 0); + adapter->aq_required &= ~IAVF_FLAG_AQ_GET_HENA; + iavf_send_pf_msg(adapter, VIRTCHNL_OP_GET_RSS_HENA_CAPS, NULL, 0); } /** - * i40evf_set_hena + * iavf_set_hena * @adapter: adapter structure * * Request the PF to set our RSS hash capabilities **/ -void i40evf_set_hena(struct i40evf_adapter *adapter) +void iavf_set_hena(struct iavf_adapter *adapter) { struct virtchnl_rss_hena vrh; @@ -820,18 +815,18 @@ void i40evf_set_hena(struct i40evf_adapter *adapter) } vrh.hena = adapter->hena; adapter->current_op = VIRTCHNL_OP_SET_RSS_HENA; - adapter->aq_required &= ~I40EVF_FLAG_AQ_SET_HENA; - i40evf_send_pf_msg(adapter, VIRTCHNL_OP_SET_RSS_HENA, - (u8 *)&vrh, sizeof(vrh)); + adapter->aq_required &= ~IAVF_FLAG_AQ_SET_HENA; + iavf_send_pf_msg(adapter, VIRTCHNL_OP_SET_RSS_HENA, (u8 *)&vrh, + sizeof(vrh)); } /** - * i40evf_set_rss_key + * iavf_set_rss_key * @adapter: adapter structure * * Request the PF to set our RSS hash key **/ -void i40evf_set_rss_key(struct i40evf_adapter *adapter) +void iavf_set_rss_key(struct iavf_adapter *adapter) { struct virtchnl_rss_key *vrk; int len; @@ -852,19 +847,18 @@ void i40evf_set_rss_key(struct i40evf_adapter *adapter) memcpy(vrk->key, adapter->rss_key, adapter->rss_key_size); adapter->current_op = VIRTCHNL_OP_CONFIG_RSS_KEY; - adapter->aq_required &= ~I40EVF_FLAG_AQ_SET_RSS_KEY; - i40evf_send_pf_msg(adapter, VIRTCHNL_OP_CONFIG_RSS_KEY, - (u8 *)vrk, len); + adapter->aq_required &= ~IAVF_FLAG_AQ_SET_RSS_KEY; + iavf_send_pf_msg(adapter, VIRTCHNL_OP_CONFIG_RSS_KEY, (u8 *)vrk, len); kfree(vrk); } /** - * i40evf_set_rss_lut + * iavf_set_rss_lut * @adapter: adapter structure * * Request the PF to set our RSS lookup table **/ -void i40evf_set_rss_lut(struct i40evf_adapter *adapter) +void iavf_set_rss_lut(struct iavf_adapter *adapter) { struct virtchnl_rss_lut *vrl; int len; @@ -884,19 +878,18 @@ void i40evf_set_rss_lut(struct i40evf_adapter *adapter) vrl->lut_entries = adapter->rss_lut_size; memcpy(vrl->lut, adapter->rss_lut, adapter->rss_lut_size); adapter->current_op = VIRTCHNL_OP_CONFIG_RSS_LUT; - adapter->aq_required &= ~I40EVF_FLAG_AQ_SET_RSS_LUT; - i40evf_send_pf_msg(adapter, VIRTCHNL_OP_CONFIG_RSS_LUT, - (u8 *)vrl, len); + adapter->aq_required &= ~IAVF_FLAG_AQ_SET_RSS_LUT; + iavf_send_pf_msg(adapter, VIRTCHNL_OP_CONFIG_RSS_LUT, (u8 *)vrl, len); kfree(vrl); } /** - * i40evf_enable_vlan_stripping + * iavf_enable_vlan_stripping * @adapter: adapter structure * * Request VLAN header stripping to be enabled **/ -void i40evf_enable_vlan_stripping(struct i40evf_adapter *adapter) +void iavf_enable_vlan_stripping(struct iavf_adapter *adapter) { if (adapter->current_op != VIRTCHNL_OP_UNKNOWN) { /* bail because we already have a command pending */ @@ -905,18 +898,17 @@ void i40evf_enable_vlan_stripping(struct i40evf_adapter *adapter) return; } adapter->current_op = VIRTCHNL_OP_ENABLE_VLAN_STRIPPING; - adapter->aq_required &= ~I40EVF_FLAG_AQ_ENABLE_VLAN_STRIPPING; - i40evf_send_pf_msg(adapter, VIRTCHNL_OP_ENABLE_VLAN_STRIPPING, - NULL, 0); + adapter->aq_required &= ~IAVF_FLAG_AQ_ENABLE_VLAN_STRIPPING; + iavf_send_pf_msg(adapter, VIRTCHNL_OP_ENABLE_VLAN_STRIPPING, NULL, 0); } /** - * i40evf_disable_vlan_stripping + * iavf_disable_vlan_stripping * @adapter: adapter structure * * Request VLAN header stripping to be disabled **/ -void i40evf_disable_vlan_stripping(struct i40evf_adapter *adapter) +void iavf_disable_vlan_stripping(struct iavf_adapter *adapter) { if (adapter->current_op != VIRTCHNL_OP_UNKNOWN) { /* bail because we already have a command pending */ @@ -925,18 +917,17 @@ void i40evf_disable_vlan_stripping(struct i40evf_adapter *adapter) return; } adapter->current_op = VIRTCHNL_OP_DISABLE_VLAN_STRIPPING; - adapter->aq_required &= ~I40EVF_FLAG_AQ_DISABLE_VLAN_STRIPPING; - i40evf_send_pf_msg(adapter, VIRTCHNL_OP_DISABLE_VLAN_STRIPPING, - NULL, 0); + adapter->aq_required &= ~IAVF_FLAG_AQ_DISABLE_VLAN_STRIPPING; + iavf_send_pf_msg(adapter, VIRTCHNL_OP_DISABLE_VLAN_STRIPPING, NULL, 0); } /** - * i40evf_print_link_message - print link up or down + * iavf_print_link_message - print link up or down * @adapter: adapter structure * * Log a message telling the world of our wonderous link status */ -static void i40evf_print_link_message(struct i40evf_adapter *adapter) +static void iavf_print_link_message(struct iavf_adapter *adapter) { struct net_device *netdev = adapter->netdev; char *speed = "Unknown "; @@ -973,13 +964,13 @@ static void i40evf_print_link_message(struct i40evf_adapter *adapter) } /** - * i40evf_enable_channel + * iavf_enable_channel * @adapter: adapter structure * * Request that the PF enable channels as specified by * the user via tc tool. **/ -void i40evf_enable_channels(struct i40evf_adapter *adapter) +void iavf_enable_channels(struct iavf_adapter *adapter) { struct virtchnl_tc_info *vti = NULL; u16 len; @@ -1007,22 +998,21 @@ void i40evf_enable_channels(struct i40evf_adapter *adapter) adapter->ch_config.ch_info[i].max_tx_rate; } - adapter->ch_config.state = __I40EVF_TC_RUNNING; - adapter->flags |= I40EVF_FLAG_REINIT_ITR_NEEDED; + adapter->ch_config.state = __IAVF_TC_RUNNING; + adapter->flags |= IAVF_FLAG_REINIT_ITR_NEEDED; adapter->current_op = VIRTCHNL_OP_ENABLE_CHANNELS; - adapter->aq_required &= ~I40EVF_FLAG_AQ_ENABLE_CHANNELS; - i40evf_send_pf_msg(adapter, VIRTCHNL_OP_ENABLE_CHANNELS, - (u8 *)vti, len); + adapter->aq_required &= ~IAVF_FLAG_AQ_ENABLE_CHANNELS; + iavf_send_pf_msg(adapter, VIRTCHNL_OP_ENABLE_CHANNELS, (u8 *)vti, len); kfree(vti); } /** - * i40evf_disable_channel + * iavf_disable_channel * @adapter: adapter structure * * Request that the PF disable channels that are configured **/ -void i40evf_disable_channels(struct i40evf_adapter *adapter) +void iavf_disable_channels(struct iavf_adapter *adapter) { if (adapter->current_op != VIRTCHNL_OP_UNKNOWN) { /* bail because we already have a command pending */ @@ -1031,23 +1021,22 @@ void i40evf_disable_channels(struct i40evf_adapter *adapter) return; } - adapter->ch_config.state = __I40EVF_TC_INVALID; - adapter->flags |= I40EVF_FLAG_REINIT_ITR_NEEDED; + adapter->ch_config.state = __IAVF_TC_INVALID; + adapter->flags |= IAVF_FLAG_REINIT_ITR_NEEDED; adapter->current_op = VIRTCHNL_OP_DISABLE_CHANNELS; - adapter->aq_required &= ~I40EVF_FLAG_AQ_DISABLE_CHANNELS; - i40evf_send_pf_msg(adapter, VIRTCHNL_OP_DISABLE_CHANNELS, - NULL, 0); + adapter->aq_required &= ~IAVF_FLAG_AQ_DISABLE_CHANNELS; + iavf_send_pf_msg(adapter, VIRTCHNL_OP_DISABLE_CHANNELS, NULL, 0); } /** - * i40evf_print_cloud_filter + * iavf_print_cloud_filter * @adapter: adapter structure * @f: cloud filter to print * * Print the cloud filter **/ -static void i40evf_print_cloud_filter(struct i40evf_adapter *adapter, - struct virtchnl_filter *f) +static void iavf_print_cloud_filter(struct iavf_adapter *adapter, + struct virtchnl_filter *f) { switch (f->flow_type) { case VIRTCHNL_TCP_V4_FLOW: @@ -1074,15 +1063,15 @@ static void i40evf_print_cloud_filter(struct i40evf_adapter *adapter, } /** - * i40evf_add_cloud_filter + * iavf_add_cloud_filter * @adapter: adapter structure * * Request that the PF add cloud filters as specified * by the user via tc tool. **/ -void i40evf_add_cloud_filter(struct i40evf_adapter *adapter) +void iavf_add_cloud_filter(struct iavf_adapter *adapter) { - struct i40evf_cloud_filter *cf; + struct iavf_cloud_filter *cf; struct virtchnl_filter *f; int len = 0, count = 0; @@ -1099,7 +1088,7 @@ void i40evf_add_cloud_filter(struct i40evf_adapter *adapter) } } if (!count) { - adapter->aq_required &= ~I40EVF_FLAG_AQ_ADD_CLOUD_FILTER; + adapter->aq_required &= ~IAVF_FLAG_AQ_ADD_CLOUD_FILTER; return; } adapter->current_op = VIRTCHNL_OP_ADD_CLOUD_FILTER; @@ -1113,25 +1102,24 @@ void i40evf_add_cloud_filter(struct i40evf_adapter *adapter) if (cf->add) { memcpy(f, &cf->f, sizeof(struct virtchnl_filter)); cf->add = false; - cf->state = __I40EVF_CF_ADD_PENDING; - i40evf_send_pf_msg(adapter, - VIRTCHNL_OP_ADD_CLOUD_FILTER, - (u8 *)f, len); + cf->state = __IAVF_CF_ADD_PENDING; + iavf_send_pf_msg(adapter, VIRTCHNL_OP_ADD_CLOUD_FILTER, + (u8 *)f, len); } } kfree(f); } /** - * i40evf_del_cloud_filter + * iavf_del_cloud_filter * @adapter: adapter structure * * Request that the PF delete cloud filters as specified * by the user via tc tool. **/ -void i40evf_del_cloud_filter(struct i40evf_adapter *adapter) +void iavf_del_cloud_filter(struct iavf_adapter *adapter) { - struct i40evf_cloud_filter *cf, *cftmp; + struct iavf_cloud_filter *cf, *cftmp; struct virtchnl_filter *f; int len = 0, count = 0; @@ -1148,7 +1136,7 @@ void i40evf_del_cloud_filter(struct i40evf_adapter *adapter) } } if (!count) { - adapter->aq_required &= ~I40EVF_FLAG_AQ_DEL_CLOUD_FILTER; + adapter->aq_required &= ~IAVF_FLAG_AQ_DEL_CLOUD_FILTER; return; } adapter->current_op = VIRTCHNL_OP_DEL_CLOUD_FILTER; @@ -1162,30 +1150,29 @@ void i40evf_del_cloud_filter(struct i40evf_adapter *adapter) if (cf->del) { memcpy(f, &cf->f, sizeof(struct virtchnl_filter)); cf->del = false; - cf->state = __I40EVF_CF_DEL_PENDING; - i40evf_send_pf_msg(adapter, - VIRTCHNL_OP_DEL_CLOUD_FILTER, - (u8 *)f, len); + cf->state = __IAVF_CF_DEL_PENDING; + iavf_send_pf_msg(adapter, VIRTCHNL_OP_DEL_CLOUD_FILTER, + (u8 *)f, len); } } kfree(f); } /** - * i40evf_request_reset + * iavf_request_reset * @adapter: adapter structure * * Request that the PF reset this VF. No response is expected. **/ -void i40evf_request_reset(struct i40evf_adapter *adapter) +void iavf_request_reset(struct iavf_adapter *adapter) { /* Don't check CURRENT_OP - this is always higher priority */ - i40evf_send_pf_msg(adapter, VIRTCHNL_OP_RESET_VF, NULL, 0); + iavf_send_pf_msg(adapter, VIRTCHNL_OP_RESET_VF, NULL, 0); adapter->current_op = VIRTCHNL_OP_UNKNOWN; } /** - * i40evf_virtchnl_completion + * iavf_virtchnl_completion * @adapter: adapter structure * @v_opcode: opcode sent by PF * @v_retval: retval sent by PF @@ -1196,10 +1183,9 @@ void i40evf_request_reset(struct i40evf_adapter *adapter) * wait, we fire off our requests and assume that no errors will be returned. * This function handles the reply messages. **/ -void i40evf_virtchnl_completion(struct i40evf_adapter *adapter, - enum virtchnl_ops v_opcode, - i40e_status v_retval, - u8 *msg, u16 msglen) +void iavf_virtchnl_completion(struct iavf_adapter *adapter, + enum virtchnl_ops v_opcode, iavf_status v_retval, + u8 *msg, u16 msglen) { struct net_device *netdev = adapter->netdev; @@ -1207,6 +1193,7 @@ void i40evf_virtchnl_completion(struct i40evf_adapter *adapter, struct virtchnl_pf_event *vpe = (struct virtchnl_pf_event *)msg; bool link_up = vpe->event_data.link_event.link_status; + switch (vpe->event) { case VIRTCHNL_EVENT_LINK_CHANGE: adapter->link_speed = @@ -1224,7 +1211,7 @@ void i40evf_virtchnl_completion(struct i40evf_adapter *adapter, * after we enable queues and actually prepared * to send traffic. */ - if (adapter->state != __I40EVF_RUNNING) + if (adapter->state != __IAVF_RUNNING) break; /* For ADq enabled VF, we reconfigure VSIs and @@ -1232,7 +1219,7 @@ void i40evf_virtchnl_completion(struct i40evf_adapter *adapter, * queues are enabled. */ if (adapter->flags & - I40EVF_FLAG_QUEUES_DISABLED) + IAVF_FLAG_QUEUES_DISABLED) break; } @@ -1244,12 +1231,12 @@ void i40evf_virtchnl_completion(struct i40evf_adapter *adapter, netif_tx_stop_all_queues(netdev); netif_carrier_off(netdev); } - i40evf_print_link_message(adapter); + iavf_print_link_message(adapter); break; case VIRTCHNL_EVENT_RESET_IMPENDING: dev_info(&adapter->pdev->dev, "Reset warning received from the PF\n"); - if (!(adapter->flags & I40EVF_FLAG_RESET_PENDING)) { - adapter->flags |= I40EVF_FLAG_RESET_PENDING; + if (!(adapter->flags & IAVF_FLAG_RESET_PENDING)) { + adapter->flags |= IAVF_FLAG_RESET_PENDING; dev_info(&adapter->pdev->dev, "Scheduling reset task\n"); schedule_work(&adapter->reset_task); } @@ -1265,48 +1252,48 @@ void i40evf_virtchnl_completion(struct i40evf_adapter *adapter, switch (v_opcode) { case VIRTCHNL_OP_ADD_VLAN: dev_err(&adapter->pdev->dev, "Failed to add VLAN filter, error %s\n", - i40evf_stat_str(&adapter->hw, v_retval)); + iavf_stat_str(&adapter->hw, v_retval)); break; case VIRTCHNL_OP_ADD_ETH_ADDR: dev_err(&adapter->pdev->dev, "Failed to add MAC filter, error %s\n", - i40evf_stat_str(&adapter->hw, v_retval)); + iavf_stat_str(&adapter->hw, v_retval)); break; case VIRTCHNL_OP_DEL_VLAN: dev_err(&adapter->pdev->dev, "Failed to delete VLAN filter, error %s\n", - i40evf_stat_str(&adapter->hw, v_retval)); + iavf_stat_str(&adapter->hw, v_retval)); break; case VIRTCHNL_OP_DEL_ETH_ADDR: dev_err(&adapter->pdev->dev, "Failed to delete MAC filter, error %s\n", - i40evf_stat_str(&adapter->hw, v_retval)); + iavf_stat_str(&adapter->hw, v_retval)); break; case VIRTCHNL_OP_ENABLE_CHANNELS: dev_err(&adapter->pdev->dev, "Failed to configure queue channels, error %s\n", - i40evf_stat_str(&adapter->hw, v_retval)); - adapter->flags &= ~I40EVF_FLAG_REINIT_ITR_NEEDED; - adapter->ch_config.state = __I40EVF_TC_INVALID; + iavf_stat_str(&adapter->hw, v_retval)); + adapter->flags &= ~IAVF_FLAG_REINIT_ITR_NEEDED; + adapter->ch_config.state = __IAVF_TC_INVALID; netdev_reset_tc(netdev); netif_tx_start_all_queues(netdev); break; case VIRTCHNL_OP_DISABLE_CHANNELS: dev_err(&adapter->pdev->dev, "Failed to disable queue channels, error %s\n", - i40evf_stat_str(&adapter->hw, v_retval)); - adapter->flags &= ~I40EVF_FLAG_REINIT_ITR_NEEDED; - adapter->ch_config.state = __I40EVF_TC_RUNNING; + iavf_stat_str(&adapter->hw, v_retval)); + adapter->flags &= ~IAVF_FLAG_REINIT_ITR_NEEDED; + adapter->ch_config.state = __IAVF_TC_RUNNING; netif_tx_start_all_queues(netdev); break; case VIRTCHNL_OP_ADD_CLOUD_FILTER: { - struct i40evf_cloud_filter *cf, *cftmp; + struct iavf_cloud_filter *cf, *cftmp; list_for_each_entry_safe(cf, cftmp, &adapter->cloud_filter_list, list) { - if (cf->state == __I40EVF_CF_ADD_PENDING) { - cf->state = __I40EVF_CF_INVALID; + if (cf->state == __IAVF_CF_ADD_PENDING) { + cf->state = __IAVF_CF_INVALID; dev_info(&adapter->pdev->dev, "Failed to add cloud filter, error %s\n", - i40evf_stat_str(&adapter->hw, - v_retval)); - i40evf_print_cloud_filter(adapter, - &cf->f); + iavf_stat_str(&adapter->hw, + v_retval)); + iavf_print_cloud_filter(adapter, + &cf->f); list_del(&cf->list); kfree(cf); adapter->num_cloud_filters--; @@ -1315,32 +1302,31 @@ void i40evf_virtchnl_completion(struct i40evf_adapter *adapter, } break; case VIRTCHNL_OP_DEL_CLOUD_FILTER: { - struct i40evf_cloud_filter *cf; + struct iavf_cloud_filter *cf; list_for_each_entry(cf, &adapter->cloud_filter_list, list) { - if (cf->state == __I40EVF_CF_DEL_PENDING) { - cf->state = __I40EVF_CF_ACTIVE; + if (cf->state == __IAVF_CF_DEL_PENDING) { + cf->state = __IAVF_CF_ACTIVE; dev_info(&adapter->pdev->dev, "Failed to del cloud filter, error %s\n", - i40evf_stat_str(&adapter->hw, - v_retval)); - i40evf_print_cloud_filter(adapter, - &cf->f); + iavf_stat_str(&adapter->hw, + v_retval)); + iavf_print_cloud_filter(adapter, + &cf->f); } } } break; default: dev_err(&adapter->pdev->dev, "PF returned error %d (%s) to our request %d\n", - v_retval, - i40evf_stat_str(&adapter->hw, v_retval), + v_retval, iavf_stat_str(&adapter->hw, v_retval), v_opcode); } } switch (v_opcode) { case VIRTCHNL_OP_GET_STATS: { - struct i40e_eth_stats *stats = - (struct i40e_eth_stats *)msg; + struct iavf_eth_stats *stats = + (struct iavf_eth_stats *)msg; netdev->stats.rx_packets = stats->rx_unicast + stats->rx_multicast + stats->rx_broadcast; @@ -1357,11 +1343,11 @@ void i40evf_virtchnl_completion(struct i40evf_adapter *adapter, break; case VIRTCHNL_OP_GET_VF_RESOURCES: { u16 len = sizeof(struct virtchnl_vf_resource) + - I40E_MAX_VF_VSI * + IAVF_MAX_VF_VSI * sizeof(struct virtchnl_vsi_resource); memcpy(adapter->vf_res, msg, min(msglen, len)); - i40evf_validate_num_queues(adapter); - i40e_vf_parse_hw_config(&adapter->hw, adapter->vf_res); + iavf_validate_num_queues(adapter); + iavf_vf_parse_hw_config(&adapter->hw, adapter->vf_res); if (is_zero_ether_addr(adapter->hw.mac.addr)) { /* restore current mac address */ ether_addr_copy(adapter->hw.mac.addr, netdev->dev_addr); @@ -1371,19 +1357,19 @@ void i40evf_virtchnl_completion(struct i40evf_adapter *adapter, ether_addr_copy(netdev->perm_addr, adapter->hw.mac.addr); } - i40evf_process_config(adapter); + iavf_process_config(adapter); } break; case VIRTCHNL_OP_ENABLE_QUEUES: /* enable transmits */ - i40evf_irq_enable(adapter, true); - adapter->flags &= ~I40EVF_FLAG_QUEUES_DISABLED; + iavf_irq_enable(adapter, true); + adapter->flags &= ~IAVF_FLAG_QUEUES_DISABLED; break; case VIRTCHNL_OP_DISABLE_QUEUES: - i40evf_free_all_tx_resources(adapter); - i40evf_free_all_rx_resources(adapter); - if (adapter->state == __I40EVF_DOWN_PENDING) { - adapter->state = __I40EVF_DOWN; + iavf_free_all_tx_resources(adapter); + iavf_free_all_rx_resources(adapter); + if (adapter->state == __IAVF_DOWN_PENDING) { + adapter->state = __IAVF_DOWN; wake_up(&adapter->down_waitqueue); } break; @@ -1402,8 +1388,7 @@ void i40evf_virtchnl_completion(struct i40evf_adapter *adapter, * care about that. */ if (msglen && CLIENT_ENABLED(adapter)) - i40evf_notify_client_message(&adapter->vsi, - msg, msglen); + iavf_notify_client_message(&adapter->vsi, msg, msglen); break; case VIRTCHNL_OP_CONFIG_IWARP_IRQ_MAP: @@ -1412,6 +1397,7 @@ void i40evf_virtchnl_completion(struct i40evf_adapter *adapter, break; case VIRTCHNL_OP_GET_RSS_HENA_CAPS: { struct virtchnl_rss_hena *vrh = (struct virtchnl_rss_hena *)msg; + if (msglen == sizeof(*vrh)) adapter->hena = vrh->hena; else @@ -1422,32 +1408,33 @@ void i40evf_virtchnl_completion(struct i40evf_adapter *adapter, case VIRTCHNL_OP_REQUEST_QUEUES: { struct virtchnl_vf_res_request *vfres = (struct virtchnl_vf_res_request *)msg; + if (vfres->num_queue_pairs != adapter->num_req_queues) { dev_info(&adapter->pdev->dev, "Requested %d queues, PF can support %d\n", adapter->num_req_queues, vfres->num_queue_pairs); adapter->num_req_queues = 0; - adapter->flags &= ~I40EVF_FLAG_REINIT_ITR_NEEDED; + adapter->flags &= ~IAVF_FLAG_REINIT_ITR_NEEDED; } } break; case VIRTCHNL_OP_ADD_CLOUD_FILTER: { - struct i40evf_cloud_filter *cf; + struct iavf_cloud_filter *cf; list_for_each_entry(cf, &adapter->cloud_filter_list, list) { - if (cf->state == __I40EVF_CF_ADD_PENDING) - cf->state = __I40EVF_CF_ACTIVE; + if (cf->state == __IAVF_CF_ADD_PENDING) + cf->state = __IAVF_CF_ACTIVE; } } break; case VIRTCHNL_OP_DEL_CLOUD_FILTER: { - struct i40evf_cloud_filter *cf, *cftmp; + struct iavf_cloud_filter *cf, *cftmp; list_for_each_entry_safe(cf, cftmp, &adapter->cloud_filter_list, list) { - if (cf->state == __I40EVF_CF_DEL_PENDING) { - cf->state = __I40EVF_CF_INVALID; + if (cf->state == __IAVF_CF_DEL_PENDING) { + cf->state = __IAVF_CF_INVALID; list_del(&cf->list); kfree(cf); adapter->num_cloud_filters--; diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c index 1b49a605d094..4f5fe6af6dac 100644 --- a/drivers/net/ethernet/intel/ice/ice_main.c +++ b/drivers/net/ethernet/intel/ice/ice_main.c @@ -15,7 +15,7 @@ static const char ice_copyright[] = "Copyright (c) 2018, Intel Corporation."; MODULE_AUTHOR("Intel Corporation, <linux.nics@intel.com>"); MODULE_DESCRIPTION(DRV_SUMMARY); -MODULE_LICENSE("GPL"); +MODULE_LICENSE("GPL v2"); MODULE_VERSION(DRV_VERSION); static int debug = -1; @@ -5117,30 +5117,6 @@ void ice_get_stats64(struct net_device *netdev, struct rtnl_link_stats64 *stats) stats->rx_length_errors = vsi_stats->rx_length_errors; } -#ifdef CONFIG_NET_POLL_CONTROLLER -/** - * ice_netpoll - polling "interrupt" handler - * @netdev: network interface device structure - * - * Used by netconsole to send skbs without having to re-enable interrupts. - * This is not called in the normal interrupt path. - */ -static void ice_netpoll(struct net_device *netdev) -{ - struct ice_netdev_priv *np = netdev_priv(netdev); - struct ice_vsi *vsi = np->vsi; - struct ice_pf *pf = vsi->back; - int i; - - if (test_bit(__ICE_DOWN, vsi->state) || - !test_bit(ICE_FLAG_MSIX_ENA, pf->flags)) - return; - - for (i = 0; i < vsi->num_q_vectors; i++) - ice_msix_clean_rings(0, vsi->q_vectors[i]); -} -#endif /* CONFIG_NET_POLL_CONTROLLER */ - /** * ice_napi_disable_all - Disable NAPI for all q_vectors in the VSI * @vsi: VSI having NAPI disabled @@ -6136,9 +6112,6 @@ static const struct net_device_ops ice_netdev_ops = { .ndo_validate_addr = eth_validate_addr, .ndo_change_mtu = ice_change_mtu, .ndo_get_stats64 = ice_get_stats64, -#ifdef CONFIG_NET_POLL_CONTROLLER - .ndo_poll_controller = ice_netpoll, -#endif /* CONFIG_NET_POLL_CONTROLLER */ .ndo_vlan_rx_add_vid = ice_vlan_rx_add_vid, .ndo_vlan_rx_kill_vid = ice_vlan_rx_kill_vid, .ndo_set_features = ice_set_features, diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c index a32c576c1e65..0d29df8accd8 100644 --- a/drivers/net/ethernet/intel/igb/igb_main.c +++ b/drivers/net/ethernet/intel/igb/igb_main.c @@ -205,10 +205,6 @@ static struct notifier_block dca_notifier = { .priority = 0 }; #endif -#ifdef CONFIG_NET_POLL_CONTROLLER -/* for netdump / net console */ -static void igb_netpoll(struct net_device *); -#endif #ifdef CONFIG_PCI_IOV static unsigned int max_vfs; module_param(max_vfs, uint, 0); @@ -243,7 +239,7 @@ static struct pci_driver igb_driver = { MODULE_AUTHOR("Intel Corporation, <e1000-devel@lists.sourceforge.net>"); MODULE_DESCRIPTION("Intel(R) Gigabit Ethernet Network Driver"); -MODULE_LICENSE("GPL"); +MODULE_LICENSE("GPL v2"); MODULE_VERSION(DRV_VERSION); #define DEFAULT_MSG_ENABLE (NETIF_MSG_DRV|NETIF_MSG_PROBE|NETIF_MSG_LINK) @@ -2881,9 +2877,6 @@ static const struct net_device_ops igb_netdev_ops = { .ndo_set_vf_spoofchk = igb_ndo_set_vf_spoofchk, .ndo_set_vf_trust = igb_ndo_set_vf_trust, .ndo_get_vf_config = igb_ndo_get_vf_config, -#ifdef CONFIG_NET_POLL_CONTROLLER - .ndo_poll_controller = igb_netpoll, -#endif .ndo_fix_features = igb_fix_features, .ndo_set_features = igb_set_features, .ndo_fdb_add = igb_ndo_fdb_add, @@ -9053,29 +9046,6 @@ static int igb_pci_sriov_configure(struct pci_dev *dev, int num_vfs) return 0; } -#ifdef CONFIG_NET_POLL_CONTROLLER -/* Polling 'interrupt' - used by things like netconsole to send skbs - * without having to re-enable interrupts. It's not called while - * the interrupt routine is executing. - */ -static void igb_netpoll(struct net_device *netdev) -{ - struct igb_adapter *adapter = netdev_priv(netdev); - struct e1000_hw *hw = &adapter->hw; - struct igb_q_vector *q_vector; - int i; - - for (i = 0; i < adapter->num_q_vectors; i++) { - q_vector = adapter->q_vector[i]; - if (adapter->flags & IGB_FLAG_HAS_MSIX) - wr32(E1000_EIMC, q_vector->eims_value); - else - igb_irq_disable(adapter); - napi_schedule(&q_vector->napi); - } -} -#endif /* CONFIG_NET_POLL_CONTROLLER */ - /** * igb_io_error_detected - called when PCI error is detected * @pdev: Pointer to PCI device diff --git a/drivers/net/ethernet/intel/igbvf/netdev.c b/drivers/net/ethernet/intel/igbvf/netdev.c index e0c989ffb2b3..820d49eb41ab 100644 --- a/drivers/net/ethernet/intel/igbvf/netdev.c +++ b/drivers/net/ethernet/intel/igbvf/netdev.c @@ -3011,7 +3011,7 @@ module_exit(igbvf_exit_module); MODULE_AUTHOR("Intel Corporation, <e1000-devel@lists.sourceforge.net>"); MODULE_DESCRIPTION("Intel(R) Gigabit Virtual Function Network Driver"); -MODULE_LICENSE("GPL"); +MODULE_LICENSE("GPL v2"); MODULE_VERSION(DRV_VERSION); /* netdev.c */ diff --git a/drivers/net/ethernet/intel/ixgb/ixgb_main.c b/drivers/net/ethernet/intel/ixgb/ixgb_main.c index d3e72d0f66ef..1d4d1686909a 100644 --- a/drivers/net/ethernet/intel/ixgb/ixgb_main.c +++ b/drivers/net/ethernet/intel/ixgb/ixgb_main.c @@ -81,11 +81,6 @@ static int ixgb_vlan_rx_kill_vid(struct net_device *netdev, __be16 proto, u16 vid); static void ixgb_restore_vlan(struct ixgb_adapter *adapter); -#ifdef CONFIG_NET_POLL_CONTROLLER -/* for netdump / net console */ -static void ixgb_netpoll(struct net_device *dev); -#endif - static pci_ers_result_t ixgb_io_error_detected (struct pci_dev *pdev, enum pci_channel_state state); static pci_ers_result_t ixgb_io_slot_reset (struct pci_dev *pdev); @@ -107,7 +102,7 @@ static struct pci_driver ixgb_driver = { MODULE_AUTHOR("Intel Corporation, <linux.nics@intel.com>"); MODULE_DESCRIPTION("Intel(R) PRO/10GbE Network Driver"); -MODULE_LICENSE("GPL"); +MODULE_LICENSE("GPL v2"); MODULE_VERSION(DRV_VERSION); #define DEFAULT_MSG_ENABLE (NETIF_MSG_DRV|NETIF_MSG_PROBE|NETIF_MSG_LINK) @@ -348,9 +343,6 @@ static const struct net_device_ops ixgb_netdev_ops = { .ndo_tx_timeout = ixgb_tx_timeout, .ndo_vlan_rx_add_vid = ixgb_vlan_rx_add_vid, .ndo_vlan_rx_kill_vid = ixgb_vlan_rx_kill_vid, -#ifdef CONFIG_NET_POLL_CONTROLLER - .ndo_poll_controller = ixgb_netpoll, -#endif .ndo_fix_features = ixgb_fix_features, .ndo_set_features = ixgb_set_features, }; @@ -2195,23 +2187,6 @@ ixgb_restore_vlan(struct ixgb_adapter *adapter) ixgb_vlan_rx_add_vid(adapter->netdev, htons(ETH_P_8021Q), vid); } -#ifdef CONFIG_NET_POLL_CONTROLLER -/* - * Polling 'interrupt' - used by things like netconsole to send skbs - * without having to re-enable interrupts. It's not called while - * the interrupt routine is executing. - */ - -static void ixgb_netpoll(struct net_device *dev) -{ - struct ixgb_adapter *adapter = netdev_priv(dev); - - disable_irq(adapter->pdev->irq); - ixgb_intr(adapter->pdev->irq, dev); - enable_irq(adapter->pdev->irq); -} -#endif - /** * ixgb_io_error_detected - called when PCI error is detected * @pdev: pointer to pci device with error diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c index 604282f03d23..140e87a10ff5 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c @@ -159,7 +159,7 @@ MODULE_PARM_DESC(debug, "Debug level (0=none,...,16=all)"); MODULE_AUTHOR("Intel Corporation, <linux.nics@intel.com>"); MODULE_DESCRIPTION("Intel(R) 10 Gigabit PCI Express Network Driver"); -MODULE_LICENSE("GPL"); +MODULE_LICENSE("GPL v2"); MODULE_VERSION(DRV_VERSION); static struct workqueue_struct *ixgbe_wq; @@ -8804,28 +8804,6 @@ static int ixgbe_del_sanmac_netdev(struct net_device *dev) return err; } -#ifdef CONFIG_NET_POLL_CONTROLLER -/* - * Polling 'interrupt' - used by things like netconsole to send skbs - * without having to re-enable interrupts. It's not called while - * the interrupt routine is executing. - */ -static void ixgbe_netpoll(struct net_device *netdev) -{ - struct ixgbe_adapter *adapter = netdev_priv(netdev); - int i; - - /* if interface is down do nothing */ - if (test_bit(__IXGBE_DOWN, &adapter->state)) - return; - - /* loop through and schedule all active queues */ - for (i = 0; i < adapter->num_q_vectors; i++) - ixgbe_msix_clean_rings(0, adapter->q_vector[i]); -} - -#endif - static void ixgbe_get_ring_stats64(struct rtnl_link_stats64 *stats, struct ixgbe_ring *ring) { @@ -10287,9 +10265,6 @@ static const struct net_device_ops ixgbe_netdev_ops = { .ndo_get_vf_config = ixgbe_ndo_get_vf_config, .ndo_get_stats64 = ixgbe_get_stats64, .ndo_setup_tc = __ixgbe_setup_tc, -#ifdef CONFIG_NET_POLL_CONTROLLER - .ndo_poll_controller = ixgbe_netpoll, -#endif #ifdef IXGBE_FCOE .ndo_select_queue = ixgbe_select_queue, .ndo_fcoe_ddp_setup = ixgbe_fcoe_ddp_get, diff --git a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c index 17e23f609d74..98707ee11d72 100644 --- a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c +++ b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c @@ -79,7 +79,7 @@ MODULE_DEVICE_TABLE(pci, ixgbevf_pci_tbl); MODULE_AUTHOR("Intel Corporation, <linux.nics@intel.com>"); MODULE_DESCRIPTION("Intel(R) 10 Gigabit Virtual Function Network Driver"); -MODULE_LICENSE("GPL"); +MODULE_LICENSE("GPL v2"); MODULE_VERSION(DRV_VERSION); #define DEFAULT_MSG_ENABLE (NETIF_MSG_DRV|NETIF_MSG_PROBE|NETIF_MSG_LINK) @@ -4268,24 +4268,6 @@ static int ixgbevf_change_mtu(struct net_device *netdev, int new_mtu) return 0; } -#ifdef CONFIG_NET_POLL_CONTROLLER -/* Polling 'interrupt' - used by things like netconsole to send skbs - * without having to re-enable interrupts. It's not called while - * the interrupt routine is executing. - */ -static void ixgbevf_netpoll(struct net_device *netdev) -{ - struct ixgbevf_adapter *adapter = netdev_priv(netdev); - int i; - - /* if interface is down do nothing */ - if (test_bit(__IXGBEVF_DOWN, &adapter->state)) - return; - for (i = 0; i < adapter->num_rx_queues; i++) - ixgbevf_msix_clean_rings(0, adapter->q_vector[i]); -} -#endif /* CONFIG_NET_POLL_CONTROLLER */ - static int ixgbevf_suspend(struct pci_dev *pdev, pm_message_t state) { struct net_device *netdev = pci_get_drvdata(pdev); @@ -4517,9 +4499,6 @@ static const struct net_device_ops ixgbevf_netdev_ops = { .ndo_tx_timeout = ixgbevf_tx_timeout, .ndo_vlan_rx_add_vid = ixgbevf_vlan_rx_add_vid, .ndo_vlan_rx_kill_vid = ixgbevf_vlan_rx_kill_vid, -#ifdef CONFIG_NET_POLL_CONTROLLER - .ndo_poll_controller = ixgbevf_netpoll, -#endif .ndo_features_check = ixgbevf_features_check, .ndo_bpf = ixgbevf_xdp, }; diff --git a/drivers/net/ethernet/lantiq_etop.c b/drivers/net/ethernet/lantiq_etop.c index 7a637b51c7d2..32ac9045cdae 100644 --- a/drivers/net/ethernet/lantiq_etop.c +++ b/drivers/net/ethernet/lantiq_etop.c @@ -274,6 +274,7 @@ ltq_etop_hw_init(struct net_device *dev) struct ltq_etop_chan *ch = &priv->ch[i]; ch->idx = ch->dma.nr = i; + ch->dma.dev = &priv->pdev->dev; if (IS_TX(i)) { ltq_dma_alloc_tx(&ch->dma); @@ -364,15 +365,8 @@ ltq_etop_mdio_probe(struct net_device *dev) return PTR_ERR(phydev); } - phydev->supported &= (SUPPORTED_10baseT_Half - | SUPPORTED_10baseT_Full - | SUPPORTED_100baseT_Half - | SUPPORTED_100baseT_Full - | SUPPORTED_Autoneg - | SUPPORTED_MII - | SUPPORTED_TP); + phy_set_max_speed(phydev, SPEED_100); - phydev->advertising = phydev->supported; phy_attached_info(phydev); return 0; @@ -438,6 +432,7 @@ ltq_etop_open(struct net_device *dev) if (!IS_TX(i) && (!IS_RX(i))) continue; ltq_dma_open(&ch->dma); + ltq_dma_enable_irq(&ch->dma); napi_enable(&ch->napi); } phy_start(dev->phydev); diff --git a/drivers/net/ethernet/lantiq_xrx200.c b/drivers/net/ethernet/lantiq_xrx200.c new file mode 100644 index 000000000000..8c5ba4b81fb7 --- /dev/null +++ b/drivers/net/ethernet/lantiq_xrx200.c @@ -0,0 +1,567 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Lantiq / Intel PMAC driver for XRX200 SoCs + * + * Copyright (C) 2010 Lantiq Deutschland + * Copyright (C) 2012 John Crispin <john@phrozen.org> + * Copyright (C) 2017 - 2018 Hauke Mehrtens <hauke@hauke-m.de> + */ + +#include <linux/etherdevice.h> +#include <linux/module.h> +#include <linux/platform_device.h> +#include <linux/interrupt.h> +#include <linux/clk.h> +#include <linux/delay.h> + +#include <linux/of_net.h> +#include <linux/of_platform.h> + +#include <xway_dma.h> + +/* DMA */ +#define XRX200_DMA_DATA_LEN 0x600 +#define XRX200_DMA_RX 0 +#define XRX200_DMA_TX 1 + +/* cpu port mac */ +#define PMAC_RX_IPG 0x0024 +#define PMAC_RX_IPG_MASK 0xf + +#define PMAC_HD_CTL 0x0000 +/* Add Ethernet header to packets from DMA to PMAC */ +#define PMAC_HD_CTL_ADD BIT(0) +/* Add VLAN tag to Packets from DMA to PMAC */ +#define PMAC_HD_CTL_TAG BIT(1) +/* Add CRC to packets from DMA to PMAC */ +#define PMAC_HD_CTL_AC BIT(2) +/* Add status header to packets from PMAC to DMA */ +#define PMAC_HD_CTL_AS BIT(3) +/* Remove CRC from packets from PMAC to DMA */ +#define PMAC_HD_CTL_RC BIT(4) +/* Remove Layer-2 header from packets from PMAC to DMA */ +#define PMAC_HD_CTL_RL2 BIT(5) +/* Status header is present from DMA to PMAC */ +#define PMAC_HD_CTL_RXSH BIT(6) +/* Add special tag from PMAC to switch */ +#define PMAC_HD_CTL_AST BIT(7) +/* Remove specail Tag from PMAC to DMA */ +#define PMAC_HD_CTL_RST BIT(8) +/* Check CRC from DMA to PMAC */ +#define PMAC_HD_CTL_CCRC BIT(9) +/* Enable reaction to Pause frames in the PMAC */ +#define PMAC_HD_CTL_FC BIT(10) + +struct xrx200_chan { + int tx_free; + + struct napi_struct napi; + struct ltq_dma_channel dma; + struct sk_buff *skb[LTQ_DESC_NUM]; + + struct xrx200_priv *priv; +}; + +struct xrx200_priv { + struct clk *clk; + + struct xrx200_chan chan_tx; + struct xrx200_chan chan_rx; + + struct net_device *net_dev; + struct device *dev; + + __iomem void *pmac_reg; +}; + +static u32 xrx200_pmac_r32(struct xrx200_priv *priv, u32 offset) +{ + return __raw_readl(priv->pmac_reg + offset); +} + +static void xrx200_pmac_w32(struct xrx200_priv *priv, u32 val, u32 offset) +{ + __raw_writel(val, priv->pmac_reg + offset); +} + +static void xrx200_pmac_mask(struct xrx200_priv *priv, u32 clear, u32 set, + u32 offset) +{ + u32 val = xrx200_pmac_r32(priv, offset); + + val &= ~(clear); + val |= set; + xrx200_pmac_w32(priv, val, offset); +} + +/* drop all the packets from the DMA ring */ +static void xrx200_flush_dma(struct xrx200_chan *ch) +{ + int i; + + for (i = 0; i < LTQ_DESC_NUM; i++) { + struct ltq_dma_desc *desc = &ch->dma.desc_base[ch->dma.desc]; + + if ((desc->ctl & (LTQ_DMA_OWN | LTQ_DMA_C)) != LTQ_DMA_C) + break; + + desc->ctl = LTQ_DMA_OWN | LTQ_DMA_RX_OFFSET(NET_IP_ALIGN) | + XRX200_DMA_DATA_LEN; + ch->dma.desc++; + ch->dma.desc %= LTQ_DESC_NUM; + } +} + +static int xrx200_open(struct net_device *net_dev) +{ + struct xrx200_priv *priv = netdev_priv(net_dev); + + napi_enable(&priv->chan_tx.napi); + ltq_dma_open(&priv->chan_tx.dma); + ltq_dma_enable_irq(&priv->chan_tx.dma); + + napi_enable(&priv->chan_rx.napi); + ltq_dma_open(&priv->chan_rx.dma); + /* The boot loader does not always deactivate the receiving of frames + * on the ports and then some packets queue up in the PPE buffers. + * They already passed the PMAC so they do not have the tags + * configured here. Read the these packets here and drop them. + * The HW should have written them into memory after 10us + */ + usleep_range(20, 40); + xrx200_flush_dma(&priv->chan_rx); + ltq_dma_enable_irq(&priv->chan_rx.dma); + + netif_wake_queue(net_dev); + + return 0; +} + +static int xrx200_close(struct net_device *net_dev) +{ + struct xrx200_priv *priv = netdev_priv(net_dev); + + netif_stop_queue(net_dev); + + napi_disable(&priv->chan_rx.napi); + ltq_dma_close(&priv->chan_rx.dma); + + napi_disable(&priv->chan_tx.napi); + ltq_dma_close(&priv->chan_tx.dma); + + return 0; +} + +static int xrx200_alloc_skb(struct xrx200_chan *ch) +{ + int ret = 0; + + ch->skb[ch->dma.desc] = netdev_alloc_skb_ip_align(ch->priv->net_dev, + XRX200_DMA_DATA_LEN); + if (!ch->skb[ch->dma.desc]) { + ret = -ENOMEM; + goto skip; + } + + ch->dma.desc_base[ch->dma.desc].addr = dma_map_single(ch->priv->dev, + ch->skb[ch->dma.desc]->data, XRX200_DMA_DATA_LEN, + DMA_FROM_DEVICE); + if (unlikely(dma_mapping_error(ch->priv->dev, + ch->dma.desc_base[ch->dma.desc].addr))) { + dev_kfree_skb_any(ch->skb[ch->dma.desc]); + ret = -ENOMEM; + goto skip; + } + +skip: + ch->dma.desc_base[ch->dma.desc].ctl = + LTQ_DMA_OWN | LTQ_DMA_RX_OFFSET(NET_IP_ALIGN) | + XRX200_DMA_DATA_LEN; + + return ret; +} + +static int xrx200_hw_receive(struct xrx200_chan *ch) +{ + struct xrx200_priv *priv = ch->priv; + struct ltq_dma_desc *desc = &ch->dma.desc_base[ch->dma.desc]; + struct sk_buff *skb = ch->skb[ch->dma.desc]; + int len = (desc->ctl & LTQ_DMA_SIZE_MASK); + struct net_device *net_dev = priv->net_dev; + int ret; + + ret = xrx200_alloc_skb(ch); + + ch->dma.desc++; + ch->dma.desc %= LTQ_DESC_NUM; + + if (ret) { + netdev_err(net_dev, "failed to allocate new rx buffer\n"); + return ret; + } + + skb_put(skb, len); + skb->protocol = eth_type_trans(skb, net_dev); + netif_receive_skb(skb); + net_dev->stats.rx_packets++; + net_dev->stats.rx_bytes += len - ETH_FCS_LEN; + + return 0; +} + +static int xrx200_poll_rx(struct napi_struct *napi, int budget) +{ + struct xrx200_chan *ch = container_of(napi, + struct xrx200_chan, napi); + int rx = 0; + int ret; + + while (rx < budget) { + struct ltq_dma_desc *desc = &ch->dma.desc_base[ch->dma.desc]; + + if ((desc->ctl & (LTQ_DMA_OWN | LTQ_DMA_C)) == LTQ_DMA_C) { + ret = xrx200_hw_receive(ch); + if (ret) + return ret; + rx++; + } else { + break; + } + } + + if (rx < budget) { + napi_complete(&ch->napi); + ltq_dma_enable_irq(&ch->dma); + } + + return rx; +} + +static int xrx200_tx_housekeeping(struct napi_struct *napi, int budget) +{ + struct xrx200_chan *ch = container_of(napi, + struct xrx200_chan, napi); + struct net_device *net_dev = ch->priv->net_dev; + int pkts = 0; + int bytes = 0; + + while (pkts < budget) { + struct ltq_dma_desc *desc = &ch->dma.desc_base[ch->tx_free]; + + if ((desc->ctl & (LTQ_DMA_OWN | LTQ_DMA_C)) == LTQ_DMA_C) { + struct sk_buff *skb = ch->skb[ch->tx_free]; + + pkts++; + bytes += skb->len; + ch->skb[ch->tx_free] = NULL; + consume_skb(skb); + memset(&ch->dma.desc_base[ch->tx_free], 0, + sizeof(struct ltq_dma_desc)); + ch->tx_free++; + ch->tx_free %= LTQ_DESC_NUM; + } else { + break; + } + } + + net_dev->stats.tx_packets += pkts; + net_dev->stats.tx_bytes += bytes; + netdev_completed_queue(ch->priv->net_dev, pkts, bytes); + + if (pkts < budget) { + napi_complete(&ch->napi); + ltq_dma_enable_irq(&ch->dma); + } + + return pkts; +} + +static int xrx200_start_xmit(struct sk_buff *skb, struct net_device *net_dev) +{ + struct xrx200_priv *priv = netdev_priv(net_dev); + struct xrx200_chan *ch = &priv->chan_tx; + struct ltq_dma_desc *desc = &ch->dma.desc_base[ch->dma.desc]; + u32 byte_offset; + dma_addr_t mapping; + int len; + + skb->dev = net_dev; + if (skb_put_padto(skb, ETH_ZLEN)) { + net_dev->stats.tx_dropped++; + return NETDEV_TX_OK; + } + + len = skb->len; + + if ((desc->ctl & (LTQ_DMA_OWN | LTQ_DMA_C)) || ch->skb[ch->dma.desc]) { + netdev_err(net_dev, "tx ring full\n"); + netif_stop_queue(net_dev); + return NETDEV_TX_BUSY; + } + + ch->skb[ch->dma.desc] = skb; + + mapping = dma_map_single(priv->dev, skb->data, len, DMA_TO_DEVICE); + if (unlikely(dma_mapping_error(priv->dev, mapping))) + goto err_drop; + + /* dma needs to start on a 16 byte aligned address */ + byte_offset = mapping % 16; + + desc->addr = mapping - byte_offset; + /* Make sure the address is written before we give it to HW */ + wmb(); + desc->ctl = LTQ_DMA_OWN | LTQ_DMA_SOP | LTQ_DMA_EOP | + LTQ_DMA_TX_OFFSET(byte_offset) | (len & LTQ_DMA_SIZE_MASK); + ch->dma.desc++; + ch->dma.desc %= LTQ_DESC_NUM; + if (ch->dma.desc == ch->tx_free) + netif_stop_queue(net_dev); + + netdev_sent_queue(net_dev, len); + + return NETDEV_TX_OK; + +err_drop: + dev_kfree_skb(skb); + net_dev->stats.tx_dropped++; + net_dev->stats.tx_errors++; + return NETDEV_TX_OK; +} + +static const struct net_device_ops xrx200_netdev_ops = { + .ndo_open = xrx200_open, + .ndo_stop = xrx200_close, + .ndo_start_xmit = xrx200_start_xmit, + .ndo_set_mac_address = eth_mac_addr, + .ndo_validate_addr = eth_validate_addr, + .ndo_change_mtu = eth_change_mtu, +}; + +static irqreturn_t xrx200_dma_irq(int irq, void *ptr) +{ + struct xrx200_chan *ch = ptr; + + ltq_dma_disable_irq(&ch->dma); + ltq_dma_ack_irq(&ch->dma); + + napi_schedule(&ch->napi); + + return IRQ_HANDLED; +} + +static int xrx200_dma_init(struct xrx200_priv *priv) +{ + struct xrx200_chan *ch_rx = &priv->chan_rx; + struct xrx200_chan *ch_tx = &priv->chan_tx; + int ret = 0; + int i; + + ltq_dma_init_port(DMA_PORT_ETOP); + + ch_rx->dma.nr = XRX200_DMA_RX; + ch_rx->dma.dev = priv->dev; + ch_rx->priv = priv; + + ltq_dma_alloc_rx(&ch_rx->dma); + for (ch_rx->dma.desc = 0; ch_rx->dma.desc < LTQ_DESC_NUM; + ch_rx->dma.desc++) { + ret = xrx200_alloc_skb(ch_rx); + if (ret) + goto rx_free; + } + ch_rx->dma.desc = 0; + ret = devm_request_irq(priv->dev, ch_rx->dma.irq, xrx200_dma_irq, 0, + "xrx200_net_rx", &priv->chan_rx); + if (ret) { + dev_err(priv->dev, "failed to request RX irq %d\n", + ch_rx->dma.irq); + goto rx_ring_free; + } + + ch_tx->dma.nr = XRX200_DMA_TX; + ch_tx->dma.dev = priv->dev; + ch_tx->priv = priv; + + ltq_dma_alloc_tx(&ch_tx->dma); + ret = devm_request_irq(priv->dev, ch_tx->dma.irq, xrx200_dma_irq, 0, + "xrx200_net_tx", &priv->chan_tx); + if (ret) { + dev_err(priv->dev, "failed to request TX irq %d\n", + ch_tx->dma.irq); + goto tx_free; + } + + return ret; + +tx_free: + ltq_dma_free(&ch_tx->dma); + +rx_ring_free: + /* free the allocated RX ring */ + for (i = 0; i < LTQ_DESC_NUM; i++) { + if (priv->chan_rx.skb[i]) + dev_kfree_skb_any(priv->chan_rx.skb[i]); + } + +rx_free: + ltq_dma_free(&ch_rx->dma); + return ret; +} + +static void xrx200_hw_cleanup(struct xrx200_priv *priv) +{ + int i; + + ltq_dma_free(&priv->chan_tx.dma); + ltq_dma_free(&priv->chan_rx.dma); + + /* free the allocated RX ring */ + for (i = 0; i < LTQ_DESC_NUM; i++) + dev_kfree_skb_any(priv->chan_rx.skb[i]); +} + +static int xrx200_probe(struct platform_device *pdev) +{ + struct device *dev = &pdev->dev; + struct device_node *np = dev->of_node; + struct resource *res; + struct xrx200_priv *priv; + struct net_device *net_dev; + const u8 *mac; + int err; + + /* alloc the network device */ + net_dev = devm_alloc_etherdev(dev, sizeof(struct xrx200_priv)); + if (!net_dev) + return -ENOMEM; + + priv = netdev_priv(net_dev); + priv->net_dev = net_dev; + priv->dev = dev; + + net_dev->netdev_ops = &xrx200_netdev_ops; + SET_NETDEV_DEV(net_dev, dev); + net_dev->min_mtu = ETH_ZLEN; + net_dev->max_mtu = XRX200_DMA_DATA_LEN; + + /* load the memory ranges */ + res = platform_get_resource(pdev, IORESOURCE_MEM, 0); + if (!res) { + dev_err(dev, "failed to get resources\n"); + return -ENOENT; + } + + priv->pmac_reg = devm_ioremap_resource(dev, res); + if (IS_ERR(priv->pmac_reg)) { + dev_err(dev, "failed to request and remap io ranges\n"); + return PTR_ERR(priv->pmac_reg); + } + + priv->chan_rx.dma.irq = platform_get_irq_byname(pdev, "rx"); + if (priv->chan_rx.dma.irq < 0) { + dev_err(dev, "failed to get RX IRQ, %i\n", + priv->chan_rx.dma.irq); + return -ENOENT; + } + priv->chan_tx.dma.irq = platform_get_irq_byname(pdev, "tx"); + if (priv->chan_tx.dma.irq < 0) { + dev_err(dev, "failed to get TX IRQ, %i\n", + priv->chan_tx.dma.irq); + return -ENOENT; + } + + /* get the clock */ + priv->clk = devm_clk_get(dev, NULL); + if (IS_ERR(priv->clk)) { + dev_err(dev, "failed to get clock\n"); + return PTR_ERR(priv->clk); + } + + mac = of_get_mac_address(np); + if (mac && is_valid_ether_addr(mac)) + ether_addr_copy(net_dev->dev_addr, mac); + else + eth_hw_addr_random(net_dev); + + /* bring up the dma engine and IP core */ + err = xrx200_dma_init(priv); + if (err) + return err; + + /* enable clock gate */ + err = clk_prepare_enable(priv->clk); + if (err) + goto err_uninit_dma; + + /* set IPG to 12 */ + xrx200_pmac_mask(priv, PMAC_RX_IPG_MASK, 0xb, PMAC_RX_IPG); + + /* enable status header, enable CRC */ + xrx200_pmac_mask(priv, 0, + PMAC_HD_CTL_RST | PMAC_HD_CTL_AST | PMAC_HD_CTL_RXSH | + PMAC_HD_CTL_AS | PMAC_HD_CTL_AC | PMAC_HD_CTL_RC, + PMAC_HD_CTL); + + /* setup NAPI */ + netif_napi_add(net_dev, &priv->chan_rx.napi, xrx200_poll_rx, 32); + netif_napi_add(net_dev, &priv->chan_tx.napi, xrx200_tx_housekeeping, 32); + + platform_set_drvdata(pdev, priv); + + err = register_netdev(net_dev); + if (err) + goto err_unprepare_clk; + return err; + +err_unprepare_clk: + clk_disable_unprepare(priv->clk); + +err_uninit_dma: + xrx200_hw_cleanup(priv); + + return 0; +} + +static int xrx200_remove(struct platform_device *pdev) +{ + struct xrx200_priv *priv = platform_get_drvdata(pdev); + struct net_device *net_dev = priv->net_dev; + + /* free stack related instances */ + netif_stop_queue(net_dev); + netif_napi_del(&priv->chan_tx.napi); + netif_napi_del(&priv->chan_rx.napi); + + /* remove the actual device */ + unregister_netdev(net_dev); + + /* release the clock */ + clk_disable_unprepare(priv->clk); + + /* shut down hardware */ + xrx200_hw_cleanup(priv); + + return 0; +} + +static const struct of_device_id xrx200_match[] = { + { .compatible = "lantiq,xrx200-net" }, + {}, +}; +MODULE_DEVICE_TABLE(of, xrx200_match); + +static struct platform_driver xrx200_driver = { + .probe = xrx200_probe, + .remove = xrx200_remove, + .driver = { + .name = "lantiq,xrx200-net", + .of_match_table = xrx200_match, + }, +}; + +module_platform_driver(xrx200_driver); + +MODULE_AUTHOR("John Crispin <john@phrozen.org>"); +MODULE_DESCRIPTION("Lantiq SoC XRX200 ethernet"); +MODULE_LICENSE("GPL"); diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c index fe3edb3c2bf4..a66f8f8552e4 100644 --- a/drivers/net/ethernet/marvell/mvneta.c +++ b/drivers/net/ethernet/marvell/mvneta.c @@ -1890,8 +1890,8 @@ static void mvneta_rxq_drop_pkts(struct mvneta_port *pp, if (!data || !(rx_desc->buf_phys_addr)) continue; - dma_unmap_single(pp->dev->dev.parent, rx_desc->buf_phys_addr, - MVNETA_RX_BUF_SIZE(pp->pkt_size), DMA_FROM_DEVICE); + dma_unmap_page(pp->dev->dev.parent, rx_desc->buf_phys_addr, + PAGE_SIZE, DMA_FROM_DEVICE); __free_page(data); } } @@ -2008,8 +2008,8 @@ static int mvneta_rx_swbm(struct napi_struct *napi, skb_add_rx_frag(rxq->skb, frag_num, page, frag_offset, frag_size, PAGE_SIZE); - dma_unmap_single(dev->dev.parent, phys_addr, - PAGE_SIZE, DMA_FROM_DEVICE); + dma_unmap_page(dev->dev.parent, phys_addr, + PAGE_SIZE, DMA_FROM_DEVICE); rxq->left_size -= frag_size; } } else { @@ -2039,9 +2039,8 @@ static int mvneta_rx_swbm(struct napi_struct *napi, frag_offset, frag_size, PAGE_SIZE); - dma_unmap_single(dev->dev.parent, phys_addr, - PAGE_SIZE, - DMA_FROM_DEVICE); + dma_unmap_page(dev->dev.parent, phys_addr, + PAGE_SIZE, DMA_FROM_DEVICE); rxq->left_size -= frag_size; } @@ -2393,7 +2392,7 @@ error: } /* Main tx processing */ -static int mvneta_tx(struct sk_buff *skb, struct net_device *dev) +static netdev_tx_t mvneta_tx(struct sk_buff *skb, struct net_device *dev) { struct mvneta_port *pp = netdev_priv(dev); u16 txq_id = skb_get_queue_mapping(skb); @@ -3791,9 +3790,6 @@ static int mvneta_open(struct net_device *dev) goto err_free_online_hp; } - /* In default link is down */ - netif_carrier_off(pp->dev); - ret = mvneta_mdio_probe(pp); if (ret < 0) { netdev_err(dev, "cannot probe MDIO bus\n"); diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2.h b/drivers/net/ethernet/marvell/mvpp2/mvpp2.h index 67b9e81b7c02..176c6b56fdcc 100644 --- a/drivers/net/ethernet/marvell/mvpp2/mvpp2.h +++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2.h @@ -253,7 +253,8 @@ #define MVPP2_ISR_ENABLE_INTERRUPT(mask) ((mask) & 0xffff) #define MVPP2_ISR_DISABLE_INTERRUPT(mask) (((mask) << 16) & 0xffff0000) #define MVPP2_ISR_RX_TX_CAUSE_REG(port) (0x5480 + 4 * (port)) -#define MVPP2_CAUSE_RXQ_OCCUP_DESC_ALL_MASK 0xffff +#define MVPP2_CAUSE_RXQ_OCCUP_DESC_ALL_MASK(version) \ + ((version) == MVPP21 ? 0xffff : 0xff) #define MVPP2_CAUSE_TXQ_OCCUP_DESC_ALL_MASK 0xff0000 #define MVPP2_CAUSE_TXQ_OCCUP_DESC_ALL_OFFSET 16 #define MVPP2_CAUSE_RX_FIFO_OVERRUN_MASK BIT(24) @@ -330,6 +331,7 @@ #define MVPP2_TXP_SCHED_ENQ_MASK 0xff #define MVPP2_TXP_SCHED_DISQ_OFFSET 8 #define MVPP2_TXP_SCHED_CMD_1_REG 0x8010 +#define MVPP2_TXP_SCHED_FIXED_PRIO_REG 0x8014 #define MVPP2_TXP_SCHED_PERIOD_REG 0x8018 #define MVPP2_TXP_SCHED_MTU_REG 0x801c #define MVPP2_TXP_MTU_MAX 0x7FFFF @@ -613,6 +615,7 @@ /* Port flags */ #define MVPP2_F_LOOPBACK BIT(0) +#define MVPP2_F_DT_COMPAT BIT(1) /* Marvell tag types */ enum mvpp2_tag_type { @@ -662,7 +665,7 @@ enum mvpp2_prs_l3_cast { #define MVPP21_ADDR_SPACE_SZ 0 #define MVPP22_ADDR_SPACE_SZ SZ_64K -#define MVPP2_MAX_THREADS 8 +#define MVPP2_MAX_THREADS 9 #define MVPP2_MAX_QVECS MVPP2_MAX_THREADS /* GMAC MIB Counters register definitions */ @@ -734,6 +737,11 @@ struct mvpp2 { int port_count; struct mvpp2_port *port_list[MVPP2_MAX_PORTS]; + /* Number of Tx threads used */ + unsigned int nthreads; + /* Map of threads needing locking */ + unsigned long lock_map; + /* Aggregated TXQs */ struct mvpp2_tx_queue *aggr_txqs; @@ -823,6 +831,12 @@ struct mvpp2_port { /* Per-CPU port control */ struct mvpp2_port_pcpu __percpu *pcpu; + /* Protect the BM refills and the Tx paths when a thread is used on more + * than a single CPU. + */ + spinlock_t bm_lock[MVPP2_MAX_THREADS]; + spinlock_t tx_lock[MVPP2_MAX_THREADS]; + /* Flags */ unsigned long flags; @@ -969,7 +983,7 @@ struct mvpp2_txq_pcpu_buf { /* Per-CPU Tx queue control */ struct mvpp2_txq_pcpu { - int cpu; + unsigned int thread; /* Number of Tx DMA descriptors in the descriptor ring */ int size; @@ -1095,14 +1109,6 @@ struct mvpp2_bm_pool { void mvpp2_write(struct mvpp2 *priv, u32 offset, u32 data); u32 mvpp2_read(struct mvpp2 *priv, u32 offset); -u32 mvpp2_read_relaxed(struct mvpp2 *priv, u32 offset); - -void mvpp2_percpu_write(struct mvpp2 *priv, int cpu, u32 offset, u32 data); -u32 mvpp2_percpu_read(struct mvpp2 *priv, int cpu, u32 offset); - -void mvpp2_percpu_write_relaxed(struct mvpp2 *priv, int cpu, u32 offset, - u32 data); - void mvpp2_dbgfs_init(struct mvpp2 *priv, const char *name); void mvpp2_dbgfs_cleanup(struct mvpp2 *priv); diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c index 28500417843e..2373cd41a625 100644 --- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c +++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c @@ -58,6 +58,8 @@ static struct { */ static void mvpp2_mac_config(struct net_device *dev, unsigned int mode, const struct phylink_link_state *state); +static void mvpp2_mac_link_up(struct net_device *dev, unsigned int mode, + phy_interface_t interface, struct phy_device *phy); /* Queue modes */ #define MVPP2_QDIST_SINGLE_MODE 0 @@ -80,13 +82,19 @@ u32 mvpp2_read(struct mvpp2 *priv, u32 offset) return readl(priv->swth_base[0] + offset); } -u32 mvpp2_read_relaxed(struct mvpp2 *priv, u32 offset) +static u32 mvpp2_read_relaxed(struct mvpp2 *priv, u32 offset) { return readl_relaxed(priv->swth_base[0] + offset); } + +static inline u32 mvpp2_cpu_to_thread(struct mvpp2 *priv, int cpu) +{ + return cpu % priv->nthreads; +} + /* These accessors should be used to access: * - * - per-CPU registers, where each CPU has its own copy of the + * - per-thread registers, where each thread has its own copy of the * register. * * MVPP2_BM_VIRT_ALLOC_REG @@ -102,8 +110,8 @@ u32 mvpp2_read_relaxed(struct mvpp2 *priv, u32 offset) * MVPP2_TXQ_SENT_REG * MVPP2_RXQ_NUM_REG * - * - global registers that must be accessed through a specific CPU - * window, because they are related to an access to a per-CPU + * - global registers that must be accessed through a specific thread + * window, because they are related to an access to a per-thread * register * * MVPP2_BM_PHY_ALLOC_REG (related to MVPP2_BM_VIRT_ALLOC_REG) @@ -120,28 +128,28 @@ u32 mvpp2_read_relaxed(struct mvpp2 *priv, u32 offset) * MVPP2_TXQ_PREF_BUF_REG (related to MVPP2_TXQ_NUM_REG) * MVPP2_TXQ_PREF_BUF_REG (related to MVPP2_TXQ_NUM_REG) */ -void mvpp2_percpu_write(struct mvpp2 *priv, int cpu, +static void mvpp2_thread_write(struct mvpp2 *priv, unsigned int thread, u32 offset, u32 data) { - writel(data, priv->swth_base[cpu] + offset); + writel(data, priv->swth_base[thread] + offset); } -u32 mvpp2_percpu_read(struct mvpp2 *priv, int cpu, +static u32 mvpp2_thread_read(struct mvpp2 *priv, unsigned int thread, u32 offset) { - return readl(priv->swth_base[cpu] + offset); + return readl(priv->swth_base[thread] + offset); } -void mvpp2_percpu_write_relaxed(struct mvpp2 *priv, int cpu, +static void mvpp2_thread_write_relaxed(struct mvpp2 *priv, unsigned int thread, u32 offset, u32 data) { - writel_relaxed(data, priv->swth_base[cpu] + offset); + writel_relaxed(data, priv->swth_base[thread] + offset); } -static u32 mvpp2_percpu_read_relaxed(struct mvpp2 *priv, int cpu, +static u32 mvpp2_thread_read_relaxed(struct mvpp2 *priv, unsigned int thread, u32 offset) { - return readl_relaxed(priv->swth_base[cpu] + offset); + return readl_relaxed(priv->swth_base[thread] + offset); } static dma_addr_t mvpp2_txdesc_dma_addr_get(struct mvpp2_port *port, @@ -383,17 +391,17 @@ static void mvpp2_bm_bufs_get_addrs(struct device *dev, struct mvpp2 *priv, dma_addr_t *dma_addr, phys_addr_t *phys_addr) { - int cpu = get_cpu(); + unsigned int thread = mvpp2_cpu_to_thread(priv, get_cpu()); - *dma_addr = mvpp2_percpu_read(priv, cpu, + *dma_addr = mvpp2_thread_read(priv, thread, MVPP2_BM_PHY_ALLOC_REG(bm_pool->id)); - *phys_addr = mvpp2_percpu_read(priv, cpu, MVPP2_BM_VIRT_ALLOC_REG); + *phys_addr = mvpp2_thread_read(priv, thread, MVPP2_BM_VIRT_ALLOC_REG); if (priv->hw_version == MVPP22) { u32 val; u32 dma_addr_highbits, phys_addr_highbits; - val = mvpp2_percpu_read(priv, cpu, MVPP22_BM_ADDR_HIGH_ALLOC); + val = mvpp2_thread_read(priv, thread, MVPP22_BM_ADDR_HIGH_ALLOC); dma_addr_highbits = (val & MVPP22_BM_ADDR_HIGH_PHYS_MASK); phys_addr_highbits = (val & MVPP22_BM_ADDR_HIGH_VIRT_MASK) >> MVPP22_BM_ADDR_HIGH_VIRT_SHIFT; @@ -624,7 +632,11 @@ static inline void mvpp2_bm_pool_put(struct mvpp2_port *port, int pool, dma_addr_t buf_dma_addr, phys_addr_t buf_phys_addr) { - int cpu = get_cpu(); + unsigned int thread = mvpp2_cpu_to_thread(port->priv, get_cpu()); + unsigned long flags = 0; + + if (test_bit(thread, &port->priv->lock_map)) + spin_lock_irqsave(&port->bm_lock[thread], flags); if (port->priv->hw_version == MVPP22) { u32 val = 0; @@ -638,7 +650,7 @@ static inline void mvpp2_bm_pool_put(struct mvpp2_port *port, int pool, << MVPP22_BM_ADDR_HIGH_VIRT_RLS_SHIFT) & MVPP22_BM_ADDR_HIGH_VIRT_RLS_MASK; - mvpp2_percpu_write_relaxed(port->priv, cpu, + mvpp2_thread_write_relaxed(port->priv, thread, MVPP22_BM_ADDR_HIGH_RLS_REG, val); } @@ -647,11 +659,14 @@ static inline void mvpp2_bm_pool_put(struct mvpp2_port *port, int pool, * descriptor. Instead of storing the virtual address, we * store the physical address */ - mvpp2_percpu_write_relaxed(port->priv, cpu, + mvpp2_thread_write_relaxed(port->priv, thread, MVPP2_BM_VIRT_RLS_REG, buf_phys_addr); - mvpp2_percpu_write_relaxed(port->priv, cpu, + mvpp2_thread_write_relaxed(port->priv, thread, MVPP2_BM_PHY_RLS_REG(pool), buf_dma_addr); + if (test_bit(thread, &port->priv->lock_map)) + spin_unlock_irqrestore(&port->bm_lock[thread], flags); + put_cpu(); } @@ -884,7 +899,7 @@ static inline void mvpp2_qvec_interrupt_disable(struct mvpp2_queue_vector *qvec) MVPP2_ISR_DISABLE_INTERRUPT(qvec->sw_thread_mask)); } -/* Mask the current CPU's Rx/Tx interrupts +/* Mask the current thread's Rx/Tx interrupts * Called by on_each_cpu(), guaranteed to run with migration disabled, * using smp_processor_id() is OK. */ @@ -892,11 +907,16 @@ static void mvpp2_interrupts_mask(void *arg) { struct mvpp2_port *port = arg; - mvpp2_percpu_write(port->priv, smp_processor_id(), + /* If the thread isn't used, don't do anything */ + if (smp_processor_id() > port->priv->nthreads) + return; + + mvpp2_thread_write(port->priv, + mvpp2_cpu_to_thread(port->priv, smp_processor_id()), MVPP2_ISR_RX_TX_MASK_REG(port->id), 0); } -/* Unmask the current CPU's Rx/Tx interrupts. +/* Unmask the current thread's Rx/Tx interrupts. * Called by on_each_cpu(), guaranteed to run with migration disabled, * using smp_processor_id() is OK. */ @@ -905,12 +925,17 @@ static void mvpp2_interrupts_unmask(void *arg) struct mvpp2_port *port = arg; u32 val; + /* If the thread isn't used, don't do anything */ + if (smp_processor_id() > port->priv->nthreads) + return; + val = MVPP2_CAUSE_MISC_SUM_MASK | - MVPP2_CAUSE_RXQ_OCCUP_DESC_ALL_MASK; + MVPP2_CAUSE_RXQ_OCCUP_DESC_ALL_MASK(port->priv->hw_version); if (port->has_tx_irqs) val |= MVPP2_CAUSE_TXQ_OCCUP_DESC_ALL_MASK; - mvpp2_percpu_write(port->priv, smp_processor_id(), + mvpp2_thread_write(port->priv, + mvpp2_cpu_to_thread(port->priv, smp_processor_id()), MVPP2_ISR_RX_TX_MASK_REG(port->id), val); } @@ -926,7 +951,7 @@ mvpp2_shared_interrupt_mask_unmask(struct mvpp2_port *port, bool mask) if (mask) val = 0; else - val = MVPP2_CAUSE_RXQ_OCCUP_DESC_ALL_MASK; + val = MVPP2_CAUSE_RXQ_OCCUP_DESC_ALL_MASK(MVPP22); for (i = 0; i < port->nqvecs; i++) { struct mvpp2_queue_vector *v = port->qvecs + i; @@ -934,7 +959,7 @@ mvpp2_shared_interrupt_mask_unmask(struct mvpp2_port *port, bool mask) if (v->type != MVPP2_QUEUE_VECTOR_SHARED) continue; - mvpp2_percpu_write(port->priv, v->sw_thread_id, + mvpp2_thread_write(port->priv, v->sw_thread_id, MVPP2_ISR_RX_TX_MASK_REG(port->id), val); } } @@ -1423,6 +1448,9 @@ static void mvpp2_defaults_set(struct mvpp2_port *port) tx_port_num); mvpp2_write(port->priv, MVPP2_TXP_SCHED_CMD_1_REG, 0); + /* Set TXQ scheduling to Round-Robin */ + mvpp2_write(port->priv, MVPP2_TXP_SCHED_FIXED_PRIO_REG, 0); + /* Close bandwidth for all queues */ for (queue = 0; queue < MVPP2_MAX_TXQ; queue++) { ptxq = mvpp2_txq_phys(port->id, queue); @@ -1622,7 +1650,8 @@ mvpp2_txq_next_desc_get(struct mvpp2_tx_queue *txq) static void mvpp2_aggr_txq_pend_desc_add(struct mvpp2_port *port, int pending) { /* aggregated access - relevant TXQ number is written in TX desc */ - mvpp2_percpu_write(port->priv, smp_processor_id(), + mvpp2_thread_write(port->priv, + mvpp2_cpu_to_thread(port->priv, smp_processor_id()), MVPP2_AGGR_TXQ_UPDATE_REG, pending); } @@ -1632,14 +1661,15 @@ static void mvpp2_aggr_txq_pend_desc_add(struct mvpp2_port *port, int pending) * Called only from mvpp2_tx(), so migration is disabled, using * smp_processor_id() is OK. */ -static int mvpp2_aggr_desc_num_check(struct mvpp2 *priv, +static int mvpp2_aggr_desc_num_check(struct mvpp2_port *port, struct mvpp2_tx_queue *aggr_txq, int num) { if ((aggr_txq->count + num) > MVPP2_AGGR_TXQ_SIZE) { /* Update number of occupied aggregated Tx descriptors */ - int cpu = smp_processor_id(); - u32 val = mvpp2_read_relaxed(priv, - MVPP2_AGGR_TXQ_STATUS_REG(cpu)); + unsigned int thread = + mvpp2_cpu_to_thread(port->priv, smp_processor_id()); + u32 val = mvpp2_read_relaxed(port->priv, + MVPP2_AGGR_TXQ_STATUS_REG(thread)); aggr_txq->count = val & MVPP2_AGGR_TXQ_PENDING_MASK; @@ -1655,16 +1685,17 @@ static int mvpp2_aggr_desc_num_check(struct mvpp2 *priv, * only by mvpp2_tx(), so migration is disabled, using * smp_processor_id() is OK. */ -static int mvpp2_txq_alloc_reserved_desc(struct mvpp2 *priv, +static int mvpp2_txq_alloc_reserved_desc(struct mvpp2_port *port, struct mvpp2_tx_queue *txq, int num) { + unsigned int thread = mvpp2_cpu_to_thread(port->priv, smp_processor_id()); + struct mvpp2 *priv = port->priv; u32 val; - int cpu = smp_processor_id(); val = (txq->id << MVPP2_TXQ_RSVD_REQ_Q_OFFSET) | num; - mvpp2_percpu_write_relaxed(priv, cpu, MVPP2_TXQ_RSVD_REQ_REG, val); + mvpp2_thread_write_relaxed(priv, thread, MVPP2_TXQ_RSVD_REQ_REG, val); - val = mvpp2_percpu_read_relaxed(priv, cpu, MVPP2_TXQ_RSVD_RSLT_REG); + val = mvpp2_thread_read_relaxed(priv, thread, MVPP2_TXQ_RSVD_RSLT_REG); return val & MVPP2_TXQ_RSVD_RSLT_MASK; } @@ -1672,12 +1703,13 @@ static int mvpp2_txq_alloc_reserved_desc(struct mvpp2 *priv, /* Check if there are enough reserved descriptors for transmission. * If not, request chunk of reserved descriptors and check again. */ -static int mvpp2_txq_reserved_desc_num_proc(struct mvpp2 *priv, +static int mvpp2_txq_reserved_desc_num_proc(struct mvpp2_port *port, struct mvpp2_tx_queue *txq, struct mvpp2_txq_pcpu *txq_pcpu, int num) { - int req, cpu, desc_count; + int req, desc_count; + unsigned int thread; if (txq_pcpu->reserved_num >= num) return 0; @@ -1688,10 +1720,10 @@ static int mvpp2_txq_reserved_desc_num_proc(struct mvpp2 *priv, desc_count = 0; /* Compute total of used descriptors */ - for_each_present_cpu(cpu) { + for (thread = 0; thread < port->priv->nthreads; thread++) { struct mvpp2_txq_pcpu *txq_pcpu_aux; - txq_pcpu_aux = per_cpu_ptr(txq->pcpu, cpu); + txq_pcpu_aux = per_cpu_ptr(txq->pcpu, thread); desc_count += txq_pcpu_aux->count; desc_count += txq_pcpu_aux->reserved_num; } @@ -1700,10 +1732,10 @@ static int mvpp2_txq_reserved_desc_num_proc(struct mvpp2 *priv, desc_count += req; if (desc_count > - (txq->size - (num_present_cpus() * MVPP2_CPU_DESC_CHUNK))) + (txq->size - (MVPP2_MAX_THREADS * MVPP2_CPU_DESC_CHUNK))) return -ENOMEM; - txq_pcpu->reserved_num += mvpp2_txq_alloc_reserved_desc(priv, txq, req); + txq_pcpu->reserved_num += mvpp2_txq_alloc_reserved_desc(port, txq, req); /* OK, the descriptor could have been updated: check again. */ if (txq_pcpu->reserved_num < num) @@ -1757,7 +1789,7 @@ static u32 mvpp2_txq_desc_csum(int l3_offs, int l3_proto, /* Get number of sent descriptors and decrement counter. * The number of sent descriptors is returned. - * Per-CPU access + * Per-thread access * * Called only from mvpp2_txq_done(), called from mvpp2_tx() * (migration disabled) and from the TX completion tasklet (migration @@ -1769,7 +1801,8 @@ static inline int mvpp2_txq_sent_desc_proc(struct mvpp2_port *port, u32 val; /* Reading status reg resets transmitted descriptor counter */ - val = mvpp2_percpu_read_relaxed(port->priv, smp_processor_id(), + val = mvpp2_thread_read_relaxed(port->priv, + mvpp2_cpu_to_thread(port->priv, smp_processor_id()), MVPP2_TXQ_SENT_REG(txq->id)); return (val & MVPP2_TRANSMITTED_COUNT_MASK) >> @@ -1784,10 +1817,15 @@ static void mvpp2_txq_sent_counter_clear(void *arg) struct mvpp2_port *port = arg; int queue; + /* If the thread isn't used, don't do anything */ + if (smp_processor_id() > port->priv->nthreads) + return; + for (queue = 0; queue < port->ntxqs; queue++) { int id = port->txqs[queue]->id; - mvpp2_percpu_read(port->priv, smp_processor_id(), + mvpp2_thread_read(port->priv, + mvpp2_cpu_to_thread(port->priv, smp_processor_id()), MVPP2_TXQ_SENT_REG(id)); } } @@ -1847,13 +1885,13 @@ static void mvpp2_txp_max_tx_size_set(struct mvpp2_port *port) static void mvpp2_rx_pkts_coal_set(struct mvpp2_port *port, struct mvpp2_rx_queue *rxq) { - int cpu = get_cpu(); + unsigned int thread = mvpp2_cpu_to_thread(port->priv, get_cpu()); if (rxq->pkts_coal > MVPP2_OCCUPIED_THRESH_MASK) rxq->pkts_coal = MVPP2_OCCUPIED_THRESH_MASK; - mvpp2_percpu_write(port->priv, cpu, MVPP2_RXQ_NUM_REG, rxq->id); - mvpp2_percpu_write(port->priv, cpu, MVPP2_RXQ_THRESH_REG, + mvpp2_thread_write(port->priv, thread, MVPP2_RXQ_NUM_REG, rxq->id); + mvpp2_thread_write(port->priv, thread, MVPP2_RXQ_THRESH_REG, rxq->pkts_coal); put_cpu(); @@ -1863,15 +1901,15 @@ static void mvpp2_rx_pkts_coal_set(struct mvpp2_port *port, static void mvpp2_tx_pkts_coal_set(struct mvpp2_port *port, struct mvpp2_tx_queue *txq) { - int cpu = get_cpu(); + unsigned int thread = mvpp2_cpu_to_thread(port->priv, get_cpu()); u32 val; if (txq->done_pkts_coal > MVPP2_TXQ_THRESH_MASK) txq->done_pkts_coal = MVPP2_TXQ_THRESH_MASK; val = (txq->done_pkts_coal << MVPP2_TXQ_THRESH_OFFSET); - mvpp2_percpu_write(port->priv, cpu, MVPP2_TXQ_NUM_REG, txq->id); - mvpp2_percpu_write(port->priv, cpu, MVPP2_TXQ_THRESH_REG, val); + mvpp2_thread_write(port->priv, thread, MVPP2_TXQ_NUM_REG, txq->id); + mvpp2_thread_write(port->priv, thread, MVPP2_TXQ_THRESH_REG, val); put_cpu(); } @@ -1972,7 +2010,7 @@ static void mvpp2_txq_done(struct mvpp2_port *port, struct mvpp2_tx_queue *txq, struct netdev_queue *nq = netdev_get_tx_queue(port->dev, txq->log_id); int tx_done; - if (txq_pcpu->cpu != smp_processor_id()) + if (txq_pcpu->thread != mvpp2_cpu_to_thread(port->priv, smp_processor_id())) netdev_err(port->dev, "wrong cpu on the end of Tx processing\n"); tx_done = mvpp2_txq_sent_desc_proc(port, txq); @@ -1988,7 +2026,7 @@ static void mvpp2_txq_done(struct mvpp2_port *port, struct mvpp2_tx_queue *txq, } static unsigned int mvpp2_tx_done(struct mvpp2_port *port, u32 cause, - int cpu) + unsigned int thread) { struct mvpp2_tx_queue *txq; struct mvpp2_txq_pcpu *txq_pcpu; @@ -1999,7 +2037,7 @@ static unsigned int mvpp2_tx_done(struct mvpp2_port *port, u32 cause, if (!txq) break; - txq_pcpu = per_cpu_ptr(txq->pcpu, cpu); + txq_pcpu = per_cpu_ptr(txq->pcpu, thread); if (txq_pcpu->count) { mvpp2_txq_done(port, txq, txq_pcpu); @@ -2015,8 +2053,8 @@ static unsigned int mvpp2_tx_done(struct mvpp2_port *port, u32 cause, /* Allocate and initialize descriptors for aggr TXQ */ static int mvpp2_aggr_txq_init(struct platform_device *pdev, - struct mvpp2_tx_queue *aggr_txq, int cpu, - struct mvpp2 *priv) + struct mvpp2_tx_queue *aggr_txq, + unsigned int thread, struct mvpp2 *priv) { u32 txq_dma; @@ -2031,7 +2069,7 @@ static int mvpp2_aggr_txq_init(struct platform_device *pdev, /* Aggr TXQ no reset WA */ aggr_txq->next_desc_to_proc = mvpp2_read(priv, - MVPP2_AGGR_TXQ_INDEX_REG(cpu)); + MVPP2_AGGR_TXQ_INDEX_REG(thread)); /* Set Tx descriptors queue starting address indirect * access @@ -2042,8 +2080,8 @@ static int mvpp2_aggr_txq_init(struct platform_device *pdev, txq_dma = aggr_txq->descs_dma >> MVPP22_AGGR_TXQ_DESC_ADDR_OFFS; - mvpp2_write(priv, MVPP2_AGGR_TXQ_DESC_ADDR_REG(cpu), txq_dma); - mvpp2_write(priv, MVPP2_AGGR_TXQ_DESC_SIZE_REG(cpu), + mvpp2_write(priv, MVPP2_AGGR_TXQ_DESC_ADDR_REG(thread), txq_dma); + mvpp2_write(priv, MVPP2_AGGR_TXQ_DESC_SIZE_REG(thread), MVPP2_AGGR_TXQ_SIZE); return 0; @@ -2054,8 +2092,8 @@ static int mvpp2_rxq_init(struct mvpp2_port *port, struct mvpp2_rx_queue *rxq) { + unsigned int thread; u32 rxq_dma; - int cpu; rxq->size = port->rx_ring_size; @@ -2072,15 +2110,15 @@ static int mvpp2_rxq_init(struct mvpp2_port *port, mvpp2_write(port->priv, MVPP2_RXQ_STATUS_REG(rxq->id), 0); /* Set Rx descriptors queue starting address - indirect access */ - cpu = get_cpu(); - mvpp2_percpu_write(port->priv, cpu, MVPP2_RXQ_NUM_REG, rxq->id); + thread = mvpp2_cpu_to_thread(port->priv, get_cpu()); + mvpp2_thread_write(port->priv, thread, MVPP2_RXQ_NUM_REG, rxq->id); if (port->priv->hw_version == MVPP21) rxq_dma = rxq->descs_dma; else rxq_dma = rxq->descs_dma >> MVPP22_DESC_ADDR_OFFS; - mvpp2_percpu_write(port->priv, cpu, MVPP2_RXQ_DESC_ADDR_REG, rxq_dma); - mvpp2_percpu_write(port->priv, cpu, MVPP2_RXQ_DESC_SIZE_REG, rxq->size); - mvpp2_percpu_write(port->priv, cpu, MVPP2_RXQ_INDEX_REG, 0); + mvpp2_thread_write(port->priv, thread, MVPP2_RXQ_DESC_ADDR_REG, rxq_dma); + mvpp2_thread_write(port->priv, thread, MVPP2_RXQ_DESC_SIZE_REG, rxq->size); + mvpp2_thread_write(port->priv, thread, MVPP2_RXQ_INDEX_REG, 0); put_cpu(); /* Set Offset */ @@ -2125,7 +2163,7 @@ static void mvpp2_rxq_drop_pkts(struct mvpp2_port *port, static void mvpp2_rxq_deinit(struct mvpp2_port *port, struct mvpp2_rx_queue *rxq) { - int cpu; + unsigned int thread; mvpp2_rxq_drop_pkts(port, rxq); @@ -2144,10 +2182,10 @@ static void mvpp2_rxq_deinit(struct mvpp2_port *port, * free descriptor number */ mvpp2_write(port->priv, MVPP2_RXQ_STATUS_REG(rxq->id), 0); - cpu = get_cpu(); - mvpp2_percpu_write(port->priv, cpu, MVPP2_RXQ_NUM_REG, rxq->id); - mvpp2_percpu_write(port->priv, cpu, MVPP2_RXQ_DESC_ADDR_REG, 0); - mvpp2_percpu_write(port->priv, cpu, MVPP2_RXQ_DESC_SIZE_REG, 0); + thread = mvpp2_cpu_to_thread(port->priv, get_cpu()); + mvpp2_thread_write(port->priv, thread, MVPP2_RXQ_NUM_REG, rxq->id); + mvpp2_thread_write(port->priv, thread, MVPP2_RXQ_DESC_ADDR_REG, 0); + mvpp2_thread_write(port->priv, thread, MVPP2_RXQ_DESC_SIZE_REG, 0); put_cpu(); } @@ -2156,7 +2194,8 @@ static int mvpp2_txq_init(struct mvpp2_port *port, struct mvpp2_tx_queue *txq) { u32 val; - int cpu, desc, desc_per_txq, tx_port_num; + unsigned int thread; + int desc, desc_per_txq, tx_port_num; struct mvpp2_txq_pcpu *txq_pcpu; txq->size = port->tx_ring_size; @@ -2171,18 +2210,18 @@ static int mvpp2_txq_init(struct mvpp2_port *port, txq->last_desc = txq->size - 1; /* Set Tx descriptors queue starting address - indirect access */ - cpu = get_cpu(); - mvpp2_percpu_write(port->priv, cpu, MVPP2_TXQ_NUM_REG, txq->id); - mvpp2_percpu_write(port->priv, cpu, MVPP2_TXQ_DESC_ADDR_REG, + thread = mvpp2_cpu_to_thread(port->priv, get_cpu()); + mvpp2_thread_write(port->priv, thread, MVPP2_TXQ_NUM_REG, txq->id); + mvpp2_thread_write(port->priv, thread, MVPP2_TXQ_DESC_ADDR_REG, txq->descs_dma); - mvpp2_percpu_write(port->priv, cpu, MVPP2_TXQ_DESC_SIZE_REG, + mvpp2_thread_write(port->priv, thread, MVPP2_TXQ_DESC_SIZE_REG, txq->size & MVPP2_TXQ_DESC_SIZE_MASK); - mvpp2_percpu_write(port->priv, cpu, MVPP2_TXQ_INDEX_REG, 0); - mvpp2_percpu_write(port->priv, cpu, MVPP2_TXQ_RSVD_CLR_REG, + mvpp2_thread_write(port->priv, thread, MVPP2_TXQ_INDEX_REG, 0); + mvpp2_thread_write(port->priv, thread, MVPP2_TXQ_RSVD_CLR_REG, txq->id << MVPP2_TXQ_RSVD_CLR_OFFSET); - val = mvpp2_percpu_read(port->priv, cpu, MVPP2_TXQ_PENDING_REG); + val = mvpp2_thread_read(port->priv, thread, MVPP2_TXQ_PENDING_REG); val &= ~MVPP2_TXQ_PENDING_MASK; - mvpp2_percpu_write(port->priv, cpu, MVPP2_TXQ_PENDING_REG, val); + mvpp2_thread_write(port->priv, thread, MVPP2_TXQ_PENDING_REG, val); /* Calculate base address in prefetch buffer. We reserve 16 descriptors * for each existing TXQ. @@ -2193,7 +2232,7 @@ static int mvpp2_txq_init(struct mvpp2_port *port, desc = (port->id * MVPP2_MAX_TXQ * desc_per_txq) + (txq->log_id * desc_per_txq); - mvpp2_percpu_write(port->priv, cpu, MVPP2_TXQ_PREF_BUF_REG, + mvpp2_thread_write(port->priv, thread, MVPP2_TXQ_PREF_BUF_REG, MVPP2_PREF_BUF_PTR(desc) | MVPP2_PREF_BUF_SIZE_16 | MVPP2_PREF_BUF_THRESH(desc_per_txq / 2)); put_cpu(); @@ -2212,8 +2251,8 @@ static int mvpp2_txq_init(struct mvpp2_port *port, mvpp2_write(port->priv, MVPP2_TXQ_SCHED_TOKEN_SIZE_REG(txq->log_id), val); - for_each_present_cpu(cpu) { - txq_pcpu = per_cpu_ptr(txq->pcpu, cpu); + for (thread = 0; thread < port->priv->nthreads; thread++) { + txq_pcpu = per_cpu_ptr(txq->pcpu, thread); txq_pcpu->size = txq->size; txq_pcpu->buffs = kmalloc_array(txq_pcpu->size, sizeof(*txq_pcpu->buffs), @@ -2247,10 +2286,10 @@ static void mvpp2_txq_deinit(struct mvpp2_port *port, struct mvpp2_tx_queue *txq) { struct mvpp2_txq_pcpu *txq_pcpu; - int cpu; + unsigned int thread; - for_each_present_cpu(cpu) { - txq_pcpu = per_cpu_ptr(txq->pcpu, cpu); + for (thread = 0; thread < port->priv->nthreads; thread++) { + txq_pcpu = per_cpu_ptr(txq->pcpu, thread); kfree(txq_pcpu->buffs); if (txq_pcpu->tso_headers) @@ -2276,10 +2315,10 @@ static void mvpp2_txq_deinit(struct mvpp2_port *port, mvpp2_write(port->priv, MVPP2_TXQ_SCHED_TOKEN_CNTR_REG(txq->id), 0); /* Set Tx descriptors queue starting address and size */ - cpu = get_cpu(); - mvpp2_percpu_write(port->priv, cpu, MVPP2_TXQ_NUM_REG, txq->id); - mvpp2_percpu_write(port->priv, cpu, MVPP2_TXQ_DESC_ADDR_REG, 0); - mvpp2_percpu_write(port->priv, cpu, MVPP2_TXQ_DESC_SIZE_REG, 0); + thread = mvpp2_cpu_to_thread(port->priv, get_cpu()); + mvpp2_thread_write(port->priv, thread, MVPP2_TXQ_NUM_REG, txq->id); + mvpp2_thread_write(port->priv, thread, MVPP2_TXQ_DESC_ADDR_REG, 0); + mvpp2_thread_write(port->priv, thread, MVPP2_TXQ_DESC_SIZE_REG, 0); put_cpu(); } @@ -2287,14 +2326,14 @@ static void mvpp2_txq_deinit(struct mvpp2_port *port, static void mvpp2_txq_clean(struct mvpp2_port *port, struct mvpp2_tx_queue *txq) { struct mvpp2_txq_pcpu *txq_pcpu; - int delay, pending, cpu; + int delay, pending; + unsigned int thread = mvpp2_cpu_to_thread(port->priv, get_cpu()); u32 val; - cpu = get_cpu(); - mvpp2_percpu_write(port->priv, cpu, MVPP2_TXQ_NUM_REG, txq->id); - val = mvpp2_percpu_read(port->priv, cpu, MVPP2_TXQ_PREF_BUF_REG); + mvpp2_thread_write(port->priv, thread, MVPP2_TXQ_NUM_REG, txq->id); + val = mvpp2_thread_read(port->priv, thread, MVPP2_TXQ_PREF_BUF_REG); val |= MVPP2_TXQ_DRAIN_EN_MASK; - mvpp2_percpu_write(port->priv, cpu, MVPP2_TXQ_PREF_BUF_REG, val); + mvpp2_thread_write(port->priv, thread, MVPP2_TXQ_PREF_BUF_REG, val); /* The napi queue has been stopped so wait for all packets * to be transmitted. @@ -2310,17 +2349,17 @@ static void mvpp2_txq_clean(struct mvpp2_port *port, struct mvpp2_tx_queue *txq) mdelay(1); delay++; - pending = mvpp2_percpu_read(port->priv, cpu, + pending = mvpp2_thread_read(port->priv, thread, MVPP2_TXQ_PENDING_REG); pending &= MVPP2_TXQ_PENDING_MASK; } while (pending); val &= ~MVPP2_TXQ_DRAIN_EN_MASK; - mvpp2_percpu_write(port->priv, cpu, MVPP2_TXQ_PREF_BUF_REG, val); + mvpp2_thread_write(port->priv, thread, MVPP2_TXQ_PREF_BUF_REG, val); put_cpu(); - for_each_present_cpu(cpu) { - txq_pcpu = per_cpu_ptr(txq->pcpu, cpu); + for (thread = 0; thread < port->priv->nthreads; thread++) { + txq_pcpu = per_cpu_ptr(txq->pcpu, thread); /* Release all packets */ mvpp2_txq_bufs_free(port, txq, txq_pcpu, txq_pcpu->count); @@ -2387,13 +2426,17 @@ err_cleanup: static int mvpp2_setup_txqs(struct mvpp2_port *port) { struct mvpp2_tx_queue *txq; - int queue, err; + int queue, err, cpu; for (queue = 0; queue < port->ntxqs; queue++) { txq = port->txqs[queue]; err = mvpp2_txq_init(port, txq); if (err) goto err_cleanup; + + /* Assign this queue to a CPU */ + cpu = queue % num_present_cpus(); + netif_set_xps_queue(port->dev, cpumask_of(cpu), queue); } if (port->has_tx_irqs) { @@ -2501,16 +2544,20 @@ static void mvpp2_tx_proc_cb(unsigned long data) { struct net_device *dev = (struct net_device *)data; struct mvpp2_port *port = netdev_priv(dev); - struct mvpp2_port_pcpu *port_pcpu = this_cpu_ptr(port->pcpu); + struct mvpp2_port_pcpu *port_pcpu; unsigned int tx_todo, cause; + port_pcpu = per_cpu_ptr(port->pcpu, + mvpp2_cpu_to_thread(port->priv, smp_processor_id())); + if (!netif_running(dev)) return; port_pcpu->timer_scheduled = false; /* Process all the Tx queues */ cause = (1 << port->ntxqs) - 1; - tx_todo = mvpp2_tx_done(port, cause, smp_processor_id()); + tx_todo = mvpp2_tx_done(port, cause, + mvpp2_cpu_to_thread(port->priv, smp_processor_id())); /* Set the timer in case not all the packets were processed */ if (tx_todo) @@ -2726,7 +2773,8 @@ static inline void tx_desc_unmap_put(struct mvpp2_port *port, struct mvpp2_tx_queue *txq, struct mvpp2_tx_desc *desc) { - struct mvpp2_txq_pcpu *txq_pcpu = this_cpu_ptr(txq->pcpu); + unsigned int thread = mvpp2_cpu_to_thread(port->priv, smp_processor_id()); + struct mvpp2_txq_pcpu *txq_pcpu = per_cpu_ptr(txq->pcpu, thread); dma_addr_t buf_dma_addr = mvpp2_txdesc_dma_addr_get(port, desc); @@ -2743,7 +2791,8 @@ static int mvpp2_tx_frag_process(struct mvpp2_port *port, struct sk_buff *skb, struct mvpp2_tx_queue *aggr_txq, struct mvpp2_tx_queue *txq) { - struct mvpp2_txq_pcpu *txq_pcpu = this_cpu_ptr(txq->pcpu); + unsigned int thread = mvpp2_cpu_to_thread(port->priv, smp_processor_id()); + struct mvpp2_txq_pcpu *txq_pcpu = per_cpu_ptr(txq->pcpu, thread); struct mvpp2_tx_desc *tx_desc; int i; dma_addr_t buf_dma_addr; @@ -2862,9 +2911,8 @@ static int mvpp2_tx_tso(struct sk_buff *skb, struct net_device *dev, int i, len, descs = 0; /* Check number of available descriptors */ - if (mvpp2_aggr_desc_num_check(port->priv, aggr_txq, - tso_count_descs(skb)) || - mvpp2_txq_reserved_desc_num_proc(port->priv, txq, txq_pcpu, + if (mvpp2_aggr_desc_num_check(port, aggr_txq, tso_count_descs(skb)) || + mvpp2_txq_reserved_desc_num_proc(port, txq, txq_pcpu, tso_count_descs(skb))) return 0; @@ -2904,21 +2952,28 @@ release: } /* Main tx processing */ -static int mvpp2_tx(struct sk_buff *skb, struct net_device *dev) +static netdev_tx_t mvpp2_tx(struct sk_buff *skb, struct net_device *dev) { struct mvpp2_port *port = netdev_priv(dev); struct mvpp2_tx_queue *txq, *aggr_txq; struct mvpp2_txq_pcpu *txq_pcpu; struct mvpp2_tx_desc *tx_desc; dma_addr_t buf_dma_addr; + unsigned long flags = 0; + unsigned int thread; int frags = 0; u16 txq_id; u32 tx_cmd; + thread = mvpp2_cpu_to_thread(port->priv, smp_processor_id()); + txq_id = skb_get_queue_mapping(skb); txq = port->txqs[txq_id]; - txq_pcpu = this_cpu_ptr(txq->pcpu); - aggr_txq = &port->priv->aggr_txqs[smp_processor_id()]; + txq_pcpu = per_cpu_ptr(txq->pcpu, thread); + aggr_txq = &port->priv->aggr_txqs[thread]; + + if (test_bit(thread, &port->priv->lock_map)) + spin_lock_irqsave(&port->tx_lock[thread], flags); if (skb_is_gso(skb)) { frags = mvpp2_tx_tso(skb, dev, txq, aggr_txq, txq_pcpu); @@ -2927,9 +2982,8 @@ static int mvpp2_tx(struct sk_buff *skb, struct net_device *dev) frags = skb_shinfo(skb)->nr_frags + 1; /* Check number of available descriptors */ - if (mvpp2_aggr_desc_num_check(port->priv, aggr_txq, frags) || - mvpp2_txq_reserved_desc_num_proc(port->priv, txq, - txq_pcpu, frags)) { + if (mvpp2_aggr_desc_num_check(port, aggr_txq, frags) || + mvpp2_txq_reserved_desc_num_proc(port, txq, txq_pcpu, frags)) { frags = 0; goto out; } @@ -2971,7 +3025,7 @@ static int mvpp2_tx(struct sk_buff *skb, struct net_device *dev) out: if (frags > 0) { - struct mvpp2_pcpu_stats *stats = this_cpu_ptr(port->stats); + struct mvpp2_pcpu_stats *stats = per_cpu_ptr(port->stats, thread); struct netdev_queue *nq = netdev_get_tx_queue(dev, txq_id); txq_pcpu->reserved_num -= frags; @@ -3001,11 +3055,14 @@ out: /* Set the timer in case not all frags were processed */ if (!port->has_tx_irqs && txq_pcpu->count <= frags && txq_pcpu->count > 0) { - struct mvpp2_port_pcpu *port_pcpu = this_cpu_ptr(port->pcpu); + struct mvpp2_port_pcpu *port_pcpu = per_cpu_ptr(port->pcpu, thread); mvpp2_timer_set(port_pcpu); } + if (test_bit(thread, &port->priv->lock_map)) + spin_unlock_irqrestore(&port->tx_lock[thread], flags); + return NETDEV_TX_OK; } @@ -3025,7 +3082,7 @@ static int mvpp2_poll(struct napi_struct *napi, int budget) int rx_done = 0; struct mvpp2_port *port = netdev_priv(napi->dev); struct mvpp2_queue_vector *qv; - int cpu = smp_processor_id(); + unsigned int thread = mvpp2_cpu_to_thread(port->priv, smp_processor_id()); qv = container_of(napi, struct mvpp2_queue_vector, napi); @@ -3039,7 +3096,7 @@ static int mvpp2_poll(struct napi_struct *napi, int budget) * * Each CPU has its own Rx/Tx cause register */ - cause_rx_tx = mvpp2_percpu_read_relaxed(port->priv, qv->sw_thread_id, + cause_rx_tx = mvpp2_thread_read_relaxed(port->priv, qv->sw_thread_id, MVPP2_ISR_RX_TX_CAUSE_REG(port->id)); cause_misc = cause_rx_tx & MVPP2_CAUSE_MISC_SUM_MASK; @@ -3048,19 +3105,22 @@ static int mvpp2_poll(struct napi_struct *napi, int budget) /* Clear the cause register */ mvpp2_write(port->priv, MVPP2_ISR_MISC_CAUSE_REG, 0); - mvpp2_percpu_write(port->priv, cpu, + mvpp2_thread_write(port->priv, thread, MVPP2_ISR_RX_TX_CAUSE_REG(port->id), cause_rx_tx & ~MVPP2_CAUSE_MISC_SUM_MASK); } - cause_tx = cause_rx_tx & MVPP2_CAUSE_TXQ_OCCUP_DESC_ALL_MASK; - if (cause_tx) { - cause_tx >>= MVPP2_CAUSE_TXQ_OCCUP_DESC_ALL_OFFSET; - mvpp2_tx_done(port, cause_tx, qv->sw_thread_id); + if (port->has_tx_irqs) { + cause_tx = cause_rx_tx & MVPP2_CAUSE_TXQ_OCCUP_DESC_ALL_MASK; + if (cause_tx) { + cause_tx >>= MVPP2_CAUSE_TXQ_OCCUP_DESC_ALL_OFFSET; + mvpp2_tx_done(port, cause_tx, qv->sw_thread_id); + } } /* Process RX packets */ - cause_rx = cause_rx_tx & MVPP2_CAUSE_RXQ_OCCUP_DESC_ALL_MASK; + cause_rx = cause_rx_tx & + MVPP2_CAUSE_RXQ_OCCUP_DESC_ALL_MASK(port->priv->hw_version); cause_rx <<= qv->first_rxq; cause_rx |= qv->pending_cause_rx; while (cause_rx && budget > 0) { @@ -3135,7 +3195,7 @@ static void mvpp2_start_dev(struct mvpp2_port *port) for (i = 0; i < port->nqvecs; i++) napi_enable(&port->qvecs[i].napi); - /* Enable interrupts on all CPUs */ + /* Enable interrupts on all threads */ mvpp2_interrupts_enable(port); if (port->priv->hw_version == MVPP22) @@ -3150,9 +3210,10 @@ static void mvpp2_start_dev(struct mvpp2_port *port) */ struct phylink_link_state state = { .interface = port->phy_interface, - .link = 1, }; mvpp2_mac_config(port->dev, MLO_AN_INBAND, &state); + mvpp2_mac_link_up(port->dev, MLO_AN_INBAND, port->phy_interface, + NULL); } netif_tx_start_all_queues(port->dev); @@ -3163,7 +3224,7 @@ static void mvpp2_stop_dev(struct mvpp2_port *port) { int i; - /* Disable interrupts on all CPUs */ + /* Disable interrupts on all threads */ mvpp2_interrupts_disable(port); for (i = 0; i < port->nqvecs; i++) @@ -3243,9 +3304,18 @@ static int mvpp2_irqs_init(struct mvpp2_port *port) if (err) goto err; - if (qv->type == MVPP2_QUEUE_VECTOR_PRIVATE) - irq_set_affinity_hint(qv->irq, - cpumask_of(qv->sw_thread_id)); + if (qv->type == MVPP2_QUEUE_VECTOR_PRIVATE) { + unsigned long mask = 0; + unsigned int cpu; + + for_each_present_cpu(cpu) { + if (mvpp2_cpu_to_thread(port->priv, cpu) == + qv->sw_thread_id) + mask |= BIT(cpu); + } + + irq_set_affinity_hint(qv->irq, to_cpumask(&mask)); + } } return 0; @@ -3389,11 +3459,11 @@ static int mvpp2_stop(struct net_device *dev) { struct mvpp2_port *port = netdev_priv(dev); struct mvpp2_port_pcpu *port_pcpu; - int cpu; + unsigned int thread; mvpp2_stop_dev(port); - /* Mask interrupts on all CPUs */ + /* Mask interrupts on all threads */ on_each_cpu(mvpp2_interrupts_mask, port, 1); mvpp2_shared_interrupt_mask_unmask(port, true); @@ -3404,8 +3474,8 @@ static int mvpp2_stop(struct net_device *dev) mvpp2_irqs_deinit(port); if (!port->has_tx_irqs) { - for_each_present_cpu(cpu) { - port_pcpu = per_cpu_ptr(port->pcpu, cpu); + for (thread = 0; thread < port->priv->nthreads; thread++) { + port_pcpu = per_cpu_ptr(port->pcpu, thread); hrtimer_cancel(&port_pcpu->tx_done_timer); port_pcpu->timer_scheduled = false; @@ -3550,7 +3620,7 @@ mvpp2_get_stats64(struct net_device *dev, struct rtnl_link_stats64 *stats) { struct mvpp2_port *port = netdev_priv(dev); unsigned int start; - int cpu; + unsigned int cpu; for_each_possible_cpu(cpu) { struct mvpp2_pcpu_stats *cpu_stats; @@ -3977,12 +4047,18 @@ static int mvpp2_simple_queue_vectors_init(struct mvpp2_port *port, static int mvpp2_multi_queue_vectors_init(struct mvpp2_port *port, struct device_node *port_node) { + struct mvpp2 *priv = port->priv; struct mvpp2_queue_vector *v; int i, ret; - port->nqvecs = num_possible_cpus(); - if (queue_mode == MVPP2_QDIST_SINGLE_MODE) - port->nqvecs += 1; + switch (queue_mode) { + case MVPP2_QDIST_SINGLE_MODE: + port->nqvecs = priv->nthreads + 1; + break; + case MVPP2_QDIST_MULTI_MODE: + port->nqvecs = priv->nthreads; + break; + } for (i = 0; i < port->nqvecs; i++) { char irqname[16]; @@ -3994,7 +4070,10 @@ static int mvpp2_multi_queue_vectors_init(struct mvpp2_port *port, v->sw_thread_id = i; v->sw_thread_mask = BIT(i); - snprintf(irqname, sizeof(irqname), "tx-cpu%d", i); + if (port->flags & MVPP2_F_DT_COMPAT) + snprintf(irqname, sizeof(irqname), "tx-cpu%d", i); + else + snprintf(irqname, sizeof(irqname), "hif%d", i); if (queue_mode == MVPP2_QDIST_MULTI_MODE) { v->first_rxq = i * MVPP2_DEFAULT_RXQ; @@ -4004,7 +4083,9 @@ static int mvpp2_multi_queue_vectors_init(struct mvpp2_port *port, v->first_rxq = 0; v->nrxqs = port->nrxqs; v->type = MVPP2_QUEUE_VECTOR_SHARED; - strncpy(irqname, "rx-shared", sizeof(irqname)); + + if (port->flags & MVPP2_F_DT_COMPAT) + strncpy(irqname, "rx-shared", sizeof(irqname)); } if (port_node) @@ -4081,7 +4162,8 @@ static int mvpp2_port_init(struct mvpp2_port *port) struct device *dev = port->dev->dev.parent; struct mvpp2 *priv = port->priv; struct mvpp2_txq_pcpu *txq_pcpu; - int queue, cpu, err; + unsigned int thread; + int queue, err; /* Checks for hardware constraints */ if (port->first_rxq + port->nrxqs > @@ -4125,9 +4207,9 @@ static int mvpp2_port_init(struct mvpp2_port *port) txq->id = queue_phy_id; txq->log_id = queue; txq->done_pkts_coal = MVPP2_TXDONE_COAL_PKTS_THRESH; - for_each_present_cpu(cpu) { - txq_pcpu = per_cpu_ptr(txq->pcpu, cpu); - txq_pcpu->cpu = cpu; + for (thread = 0; thread < priv->nthreads; thread++) { + txq_pcpu = per_cpu_ptr(txq->pcpu, thread); + txq_pcpu->thread = thread; } port->txqs[queue] = txq; @@ -4200,24 +4282,51 @@ err_free_percpu: return err; } -/* Checks if the port DT description has the TX interrupts - * described. On PPv2.1, there are no such interrupts. On PPv2.2, - * there are available, but we need to keep support for old DTs. +static bool mvpp22_port_has_legacy_tx_irqs(struct device_node *port_node, + unsigned long *flags) +{ + char *irqs[5] = { "rx-shared", "tx-cpu0", "tx-cpu1", "tx-cpu2", + "tx-cpu3" }; + int i; + + for (i = 0; i < 5; i++) + if (of_property_match_string(port_node, "interrupt-names", + irqs[i]) < 0) + return false; + + *flags |= MVPP2_F_DT_COMPAT; + return true; +} + +/* Checks if the port dt description has the required Tx interrupts: + * - PPv2.1: there are no such interrupts. + * - PPv2.2: + * - The old DTs have: "rx-shared", "tx-cpuX" with X in [0...3] + * - The new ones have: "hifX" with X in [0..8] + * + * All those variants are supported to keep the backward compatibility. */ -static bool mvpp2_port_has_tx_irqs(struct mvpp2 *priv, - struct device_node *port_node) +static bool mvpp2_port_has_irqs(struct mvpp2 *priv, + struct device_node *port_node, + unsigned long *flags) { - char *irqs[5] = { "rx-shared", "tx-cpu0", "tx-cpu1", - "tx-cpu2", "tx-cpu3" }; - int ret, i; + char name[5]; + int i; + + /* ACPI */ + if (!port_node) + return true; if (priv->hw_version == MVPP21) return false; - for (i = 0; i < 5; i++) { - ret = of_property_match_string(port_node, "interrupt-names", - irqs[i]); - if (ret < 0) + if (mvpp22_port_has_legacy_tx_irqs(port_node, flags)) + return true; + + for (i = 0; i < MVPP2_MAX_THREADS; i++) { + snprintf(name, 5, "hif%d", i); + if (of_property_match_string(port_node, "interrupt-names", + name) < 0) return false; } @@ -4495,10 +4604,6 @@ static void mvpp2_mac_config(struct net_device *dev, unsigned int mode, return; } - netif_tx_stop_all_queues(port->dev); - if (!port->has_phy) - netif_carrier_off(port->dev); - /* Make sure the port is disabled when reconfiguring the mode */ mvpp2_port_disable(port); @@ -4523,16 +4628,7 @@ static void mvpp2_mac_config(struct net_device *dev, unsigned int mode, if (port->priv->hw_version == MVPP21 && port->flags & MVPP2_F_LOOPBACK) mvpp2_port_loopback_set(port, state); - /* If the port already was up, make sure it's still in the same state */ - if (state->link || !port->has_phy) { - mvpp2_port_enable(port); - - mvpp2_egress_enable(port); - mvpp2_ingress_enable(port); - if (!port->has_phy) - netif_carrier_on(dev); - netif_tx_wake_all_queues(dev); - } + mvpp2_port_enable(port); } static void mvpp2_mac_link_up(struct net_device *dev, unsigned int mode, @@ -4607,23 +4703,21 @@ static int mvpp2_port_probe(struct platform_device *pdev, struct resource *res; struct phylink *phylink; char *mac_from = ""; - unsigned int ntxqs, nrxqs; + unsigned int ntxqs, nrxqs, thread; + unsigned long flags = 0; bool has_tx_irqs; u32 id; int features; int phy_mode; - int err, i, cpu; + int err, i; - if (port_node) { - has_tx_irqs = mvpp2_port_has_tx_irqs(priv, port_node); - } else { - has_tx_irqs = true; - queue_mode = MVPP2_QDIST_MULTI_MODE; + has_tx_irqs = mvpp2_port_has_irqs(priv, port_node, &flags); + if (!has_tx_irqs && queue_mode == MVPP2_QDIST_MULTI_MODE) { + dev_err(&pdev->dev, + "not enough IRQs to support multi queue mode\n"); + return -EINVAL; } - if (!has_tx_irqs) - queue_mode = MVPP2_QDIST_SINGLE_MODE; - ntxqs = MVPP2_MAX_TXQ; if (priv->hw_version == MVPP22 && queue_mode == MVPP2_QDIST_MULTI_MODE) nrxqs = MVPP2_DEFAULT_RXQ * num_possible_cpus(); @@ -4671,6 +4765,7 @@ static int mvpp2_port_probe(struct platform_device *pdev, port->nrxqs = nrxqs; port->priv = priv; port->has_tx_irqs = has_tx_irqs; + port->flags = flags; err = mvpp2_queue_vectors_init(port, port_node); if (err) @@ -4767,8 +4862,8 @@ static int mvpp2_port_probe(struct platform_device *pdev, } if (!port->has_tx_irqs) { - for_each_present_cpu(cpu) { - port_pcpu = per_cpu_ptr(port->pcpu, cpu); + for (thread = 0; thread < priv->nthreads; thread++) { + port_pcpu = per_cpu_ptr(port->pcpu, thread); hrtimer_init(&port_pcpu->tx_done_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL_PINNED); @@ -5052,13 +5147,13 @@ static int mvpp2_init(struct platform_device *pdev, struct mvpp2 *priv) } /* Allocate and initialize aggregated TXQs */ - priv->aggr_txqs = devm_kcalloc(&pdev->dev, num_present_cpus(), + priv->aggr_txqs = devm_kcalloc(&pdev->dev, MVPP2_MAX_THREADS, sizeof(*priv->aggr_txqs), GFP_KERNEL); if (!priv->aggr_txqs) return -ENOMEM; - for_each_present_cpu(i) { + for (i = 0; i < MVPP2_MAX_THREADS; i++) { priv->aggr_txqs[i].id = i; priv->aggr_txqs[i].size = MVPP2_AGGR_TXQ_SIZE; err = mvpp2_aggr_txq_init(pdev, &priv->aggr_txqs[i], i, priv); @@ -5105,7 +5200,7 @@ static int mvpp2_probe(struct platform_device *pdev) struct mvpp2 *priv; struct resource *res; void __iomem *base; - int i; + int i, shared; int err; priv = devm_kzalloc(&pdev->dev, sizeof(*priv), GFP_KERNEL); @@ -5170,6 +5265,15 @@ static int mvpp2_probe(struct platform_device *pdev) mvpp2_setup_bm_pool(); + + priv->nthreads = min_t(unsigned int, num_present_cpus(), + MVPP2_MAX_THREADS); + + shared = num_present_cpus() - priv->nthreads; + if (shared > 0) + bitmap_fill(&priv->lock_map, + min_t(int, shared, MVPP2_MAX_THREADS)); + for (i = 0; i < MVPP2_MAX_THREADS; i++) { u32 addr_space_sz; @@ -5344,7 +5448,7 @@ static int mvpp2_remove(struct platform_device *pdev) mvpp2_bm_pool_destroy(pdev, priv, bm_pool); } - for_each_present_cpu(i) { + for (i = 0; i < MVPP2_MAX_THREADS; i++) { struct mvpp2_tx_queue *aggr_txq = &priv->aggr_txqs[i]; dma_free_coherent(&pdev->dev, diff --git a/drivers/net/ethernet/marvell/pxa168_eth.c b/drivers/net/ethernet/marvell/pxa168_eth.c index 3a9730612a70..ff2fea0f8b75 100644 --- a/drivers/net/ethernet/marvell/pxa168_eth.c +++ b/drivers/net/ethernet/marvell/pxa168_eth.c @@ -1260,7 +1260,8 @@ static int pxa168_rx_poll(struct napi_struct *napi, int budget) return work_done; } -static int pxa168_eth_start_xmit(struct sk_buff *skb, struct net_device *dev) +static netdev_tx_t +pxa168_eth_start_xmit(struct sk_buff *skb, struct net_device *dev) { struct pxa168_eth_private *pep = netdev_priv(dev); struct net_device_stats *stats = &dev->stats; diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.c b/drivers/net/ethernet/mediatek/mtk_eth_soc.c index b44bcfd85b05..cc1e9a96a43b 100644 --- a/drivers/net/ethernet/mediatek/mtk_eth_soc.c +++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.c @@ -355,12 +355,8 @@ static int mtk_phy_connect(struct net_device *dev) dev->phydev->speed = 0; dev->phydev->duplex = 0; - if (of_phy_is_fixed_link(mac->of_node)) - dev->phydev->supported |= - SUPPORTED_Pause | SUPPORTED_Asym_Pause; - - dev->phydev->supported &= PHY_GBIT_FEATURES | SUPPORTED_Pause | - SUPPORTED_Asym_Pause; + phy_set_max_speed(dev->phydev, SPEED_1000); + phy_support_asym_pause(dev->phydev); dev->phydev->advertising = dev->phydev->supported | ADVERTISED_Autoneg; phy_start_aneg(dev->phydev); diff --git a/drivers/net/ethernet/mellanox/mlx4/alloc.c b/drivers/net/ethernet/mellanox/mlx4/alloc.c index 4bdf25059542..deef5a998985 100644 --- a/drivers/net/ethernet/mellanox/mlx4/alloc.c +++ b/drivers/net/ethernet/mellanox/mlx4/alloc.c @@ -614,7 +614,7 @@ int mlx4_buf_alloc(struct mlx4_dev *dev, int size, int max_direct, int i; buf->direct.buf = NULL; - buf->nbufs = (size + PAGE_SIZE - 1) / PAGE_SIZE; + buf->nbufs = DIV_ROUND_UP(size, PAGE_SIZE); buf->npages = buf->nbufs; buf->page_shift = PAGE_SHIFT; buf->page_list = kcalloc(buf->nbufs, sizeof(*buf->page_list), diff --git a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c index 6785661d1a72..fe49384eba48 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c @@ -1286,20 +1286,6 @@ out: mutex_unlock(&mdev->state_lock); } -#ifdef CONFIG_NET_POLL_CONTROLLER -static void mlx4_en_netpoll(struct net_device *dev) -{ - struct mlx4_en_priv *priv = netdev_priv(dev); - struct mlx4_en_cq *cq; - int i; - - for (i = 0; i < priv->tx_ring_num[TX]; i++) { - cq = priv->tx_cq[TX][i]; - napi_schedule(&cq->napi); - } -} -#endif - static int mlx4_en_set_rss_steer_rules(struct mlx4_en_priv *priv) { u64 reg_id; @@ -2946,9 +2932,6 @@ static const struct net_device_ops mlx4_netdev_ops = { .ndo_tx_timeout = mlx4_en_tx_timeout, .ndo_vlan_rx_add_vid = mlx4_en_vlan_rx_add_vid, .ndo_vlan_rx_kill_vid = mlx4_en_vlan_rx_kill_vid, -#ifdef CONFIG_NET_POLL_CONTROLLER - .ndo_poll_controller = mlx4_en_netpoll, -#endif .ndo_set_features = mlx4_en_set_features, .ndo_fix_features = mlx4_en_fix_features, .ndo_setup_tc = __mlx4_en_setup_tc, @@ -2983,9 +2966,6 @@ static const struct net_device_ops mlx4_netdev_ops_master = { .ndo_set_vf_link_state = mlx4_en_set_vf_link_state, .ndo_get_vf_stats = mlx4_en_get_vf_stats, .ndo_get_vf_config = mlx4_en_get_vf_config, -#ifdef CONFIG_NET_POLL_CONTROLLER - .ndo_poll_controller = mlx4_en_netpoll, -#endif .ndo_set_features = mlx4_en_set_features, .ndo_fix_features = mlx4_en_fix_features, .ndo_setup_tc = __mlx4_en_setup_tc, diff --git a/drivers/net/ethernet/mellanox/mlx4/eq.c b/drivers/net/ethernet/mellanox/mlx4/eq.c index 1f3372c1802e..2df92dbd38e1 100644 --- a/drivers/net/ethernet/mellanox/mlx4/eq.c +++ b/drivers/net/ethernet/mellanox/mlx4/eq.c @@ -240,7 +240,8 @@ static void mlx4_set_eq_affinity_hint(struct mlx4_priv *priv, int vec) struct mlx4_dev *dev = &priv->dev; struct mlx4_eq *eq = &priv->eq_table.eq[vec]; - if (!eq->affinity_mask || cpumask_empty(eq->affinity_mask)) + if (!cpumask_available(eq->affinity_mask) || + cpumask_empty(eq->affinity_mask)) return; hint_err = irq_set_affinity_hint(eq->irq, eq->affinity_mask); diff --git a/drivers/net/ethernet/mellanox/mlx4/icm.c b/drivers/net/ethernet/mellanox/mlx4/icm.c index 7262c6310650..4b4351141b94 100644 --- a/drivers/net/ethernet/mellanox/mlx4/icm.c +++ b/drivers/net/ethernet/mellanox/mlx4/icm.c @@ -406,7 +406,7 @@ int mlx4_init_icm_table(struct mlx4_dev *dev, struct mlx4_icm_table *table, obj_per_chunk = MLX4_TABLE_CHUNK_SIZE / obj_size; if (WARN_ON(!obj_per_chunk)) return -EINVAL; - num_icm = (nobj + obj_per_chunk - 1) / obj_per_chunk; + num_icm = DIV_ROUND_UP(nobj, obj_per_chunk); table->icm = kvcalloc(num_icm, sizeof(*table->icm), GFP_KERNEL); if (!table->icm) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c index 3ce14d42ddc8..a53736c26c0c 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c @@ -206,7 +206,7 @@ static void poll_timeout(struct mlx5_cmd_work_ent *ent) u8 own; do { - own = ent->lay->status_own; + own = READ_ONCE(ent->lay->status_own); if (!(own & CMD_OWNER_HW)) { ent->ret = 0; return; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/dev.c b/drivers/net/ethernet/mellanox/mlx5/core/dev.c index b994b80d5714..37ba7c78859d 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/dev.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/dev.c @@ -132,11 +132,11 @@ void mlx5_add_device(struct mlx5_interface *intf, struct mlx5_priv *priv) delayed_event_start(priv); dev_ctx->context = intf->add(dev); - set_bit(MLX5_INTERFACE_ADDED, &dev_ctx->state); - if (intf->attach) - set_bit(MLX5_INTERFACE_ATTACHED, &dev_ctx->state); - if (dev_ctx->context) { + set_bit(MLX5_INTERFACE_ADDED, &dev_ctx->state); + if (intf->attach) + set_bit(MLX5_INTERFACE_ATTACHED, &dev_ctx->state); + spin_lock_irq(&priv->ctx_lock); list_add_tail(&dev_ctx->list, &priv->ctx_list); @@ -211,12 +211,17 @@ static void mlx5_attach_interface(struct mlx5_interface *intf, struct mlx5_priv if (intf->attach) { if (test_bit(MLX5_INTERFACE_ATTACHED, &dev_ctx->state)) goto out; - intf->attach(dev, dev_ctx->context); + if (intf->attach(dev, dev_ctx->context)) + goto out; + set_bit(MLX5_INTERFACE_ATTACHED, &dev_ctx->state); } else { if (test_bit(MLX5_INTERFACE_ADDED, &dev_ctx->state)) goto out; dev_ctx->context = intf->add(dev); + if (!dev_ctx->context) + goto out; + set_bit(MLX5_INTERFACE_ADDED, &dev_ctx->state); } @@ -391,16 +396,17 @@ void mlx5_remove_dev_by_protocol(struct mlx5_core_dev *dev, int protocol) } } -static u16 mlx5_gen_pci_id(struct mlx5_core_dev *dev) +static u32 mlx5_gen_pci_id(struct mlx5_core_dev *dev) { - return (u16)((dev->pdev->bus->number << 8) | + return (u32)((pci_domain_nr(dev->pdev->bus) << 16) | + (dev->pdev->bus->number << 8) | PCI_SLOT(dev->pdev->devfn)); } /* Must be called with intf_mutex held */ struct mlx5_core_dev *mlx5_get_next_phys_dev(struct mlx5_core_dev *dev) { - u16 pci_id = mlx5_gen_pci_id(dev); + u32 pci_id = mlx5_gen_pci_id(dev); struct mlx5_core_dev *res = NULL; struct mlx5_core_dev *tmp_dev; struct mlx5_priv *priv; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h index db2cfcd21d43..01a967e717e7 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h @@ -204,13 +204,6 @@ struct mlx5e_umr_wqe { extern const char mlx5e_self_tests[][ETH_GSTRING_LEN]; -static const char mlx5e_priv_flags[][ETH_GSTRING_LEN] = { - "rx_cqe_moder", - "tx_cqe_moder", - "rx_cqe_compress", - "rx_striding_rq", -}; - enum mlx5e_priv_flag { MLX5E_PFLAG_RX_CQE_BASED_MODER = (1 << 0), MLX5E_PFLAG_TX_CQE_BASED_MODER = (1 << 1), @@ -905,6 +898,12 @@ void mlx5e_destroy_mdev_resources(struct mlx5_core_dev *mdev); int mlx5e_refresh_tirs(struct mlx5e_priv *priv, bool enable_uc_lb); /* common netdev helpers */ +void mlx5e_create_q_counters(struct mlx5e_priv *priv); +void mlx5e_destroy_q_counters(struct mlx5e_priv *priv); +int mlx5e_open_drop_rq(struct mlx5e_priv *priv, + struct mlx5e_rq *drop_rq); +void mlx5e_close_drop_rq(struct mlx5e_rq *drop_rq); + int mlx5e_create_indirect_rqt(struct mlx5e_priv *priv); int mlx5e_create_indirect_tirs(struct mlx5e_priv *priv); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls.c index eddd7702680b..e88340e196f7 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls.c @@ -183,12 +183,13 @@ static const struct tlsdev_ops mlx5e_tls_ops = { void mlx5e_tls_build_netdev(struct mlx5e_priv *priv) { - u32 caps = mlx5_accel_tls_device_caps(priv->mdev); struct net_device *netdev = priv->netdev; + u32 caps; if (!mlx5_accel_is_tls_device(priv->mdev)) return; + caps = mlx5_accel_tls_device_caps(priv->mdev); if (caps & MLX5_ACCEL_TLS_TX) { netdev->features |= NETIF_F_HW_TLS_TX; netdev->hw_features |= NETIF_F_HW_TLS_TX; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c index 98dd3e0ada72..8cd338ceb237 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c @@ -135,6 +135,13 @@ void mlx5e_build_ptys2ethtool_map(void) ETHTOOL_LINK_MODE_50000baseKR2_Full_BIT); } +static const char mlx5e_priv_flags[][ETH_GSTRING_LEN] = { + "rx_cqe_moder", + "tx_cqe_moder", + "rx_cqe_compress", + "rx_striding_rq", +}; + int mlx5e_ethtool_get_sset_count(struct mlx5e_priv *priv, int sset) { int i, num_stats = 0; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c index 75bb981e00b7..41cde926cdab 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c @@ -191,7 +191,7 @@ set_udp(void *headers_c, void *headers_v, __be16 psrc_m, __be16 psrc_v, { if (psrc_m) { MLX5E_FTE_SET(headers_c, udp_sport, 0xffff); - MLX5E_FTE_SET(headers_c, udp_sport, ntohs(psrc_v)); + MLX5E_FTE_SET(headers_v, udp_sport, ntohs(psrc_v)); } if (pdst_m) { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index 5a7939e70190..5955b4d844cc 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -3049,8 +3049,8 @@ static int mlx5e_alloc_drop_cq(struct mlx5_core_dev *mdev, return mlx5e_alloc_cq_common(mdev, param, cq); } -static int mlx5e_open_drop_rq(struct mlx5e_priv *priv, - struct mlx5e_rq *drop_rq) +int mlx5e_open_drop_rq(struct mlx5e_priv *priv, + struct mlx5e_rq *drop_rq) { struct mlx5_core_dev *mdev = priv->mdev; struct mlx5e_cq_param cq_param = {}; @@ -3094,7 +3094,7 @@ err_free_cq: return err; } -static void mlx5e_close_drop_rq(struct mlx5e_rq *drop_rq) +void mlx5e_close_drop_rq(struct mlx5e_rq *drop_rq) { mlx5e_destroy_rq(drop_rq); mlx5e_free_rq(drop_rq); @@ -4315,22 +4315,6 @@ static int mlx5e_xdp(struct net_device *dev, struct netdev_bpf *xdp) } } -#ifdef CONFIG_NET_POLL_CONTROLLER -/* Fake "interrupt" called by netpoll (eg netconsole) to send skbs without - * reenabling interrupts. - */ -static void mlx5e_netpoll(struct net_device *dev) -{ - struct mlx5e_priv *priv = netdev_priv(dev); - struct mlx5e_channels *chs = &priv->channels; - - int i; - - for (i = 0; i < chs->num; i++) - napi_schedule(&chs->c[i]->napi); -} -#endif - static const struct net_device_ops mlx5e_netdev_ops = { .ndo_open = mlx5e_open, .ndo_stop = mlx5e_close, @@ -4356,9 +4340,6 @@ static const struct net_device_ops mlx5e_netdev_ops = { #ifdef CONFIG_MLX5_EN_ARFS .ndo_rx_flow_steer = mlx5e_rx_flow_steer, #endif -#ifdef CONFIG_NET_POLL_CONTROLLER - .ndo_poll_controller = mlx5e_netpoll, -#endif #ifdef CONFIG_MLX5_ESWITCH /* SRIOV E-Switch NDOs */ .ndo_set_vf_mac = mlx5e_set_vf_mac, @@ -4726,7 +4707,7 @@ static void mlx5e_build_nic_netdev(struct net_device *netdev) mlx5e_tls_build_netdev(priv); } -static void mlx5e_create_q_counters(struct mlx5e_priv *priv) +void mlx5e_create_q_counters(struct mlx5e_priv *priv) { struct mlx5_core_dev *mdev = priv->mdev; int err; @@ -4744,7 +4725,7 @@ static void mlx5e_create_q_counters(struct mlx5e_priv *priv) } } -static void mlx5e_destroy_q_counters(struct mlx5e_priv *priv) +void mlx5e_destroy_q_counters(struct mlx5e_priv *priv) { if (priv->q_counter) mlx5_core_dealloc_q_counter(priv->mdev, priv->q_counter); @@ -4783,9 +4764,17 @@ static int mlx5e_init_nic_rx(struct mlx5e_priv *priv) struct mlx5_core_dev *mdev = priv->mdev; int err; + mlx5e_create_q_counters(priv); + + err = mlx5e_open_drop_rq(priv, &priv->drop_rq); + if (err) { + mlx5_core_err(mdev, "open drop rq failed, %d\n", err); + goto err_destroy_q_counters; + } + err = mlx5e_create_indirect_rqt(priv); if (err) - return err; + goto err_close_drop_rq; err = mlx5e_create_direct_rqts(priv); if (err) @@ -4821,6 +4810,10 @@ err_destroy_direct_rqts: mlx5e_destroy_direct_rqts(priv); err_destroy_indirect_rqts: mlx5e_destroy_rqt(priv, &priv->indir_rqt); +err_close_drop_rq: + mlx5e_close_drop_rq(&priv->drop_rq); +err_destroy_q_counters: + mlx5e_destroy_q_counters(priv); return err; } @@ -4832,6 +4825,8 @@ static void mlx5e_cleanup_nic_rx(struct mlx5e_priv *priv) mlx5e_destroy_indirect_tirs(priv); mlx5e_destroy_direct_rqts(priv); mlx5e_destroy_rqt(priv, &priv->indir_rqt); + mlx5e_close_drop_rq(&priv->drop_rq); + mlx5e_destroy_q_counters(priv); } static int mlx5e_init_nic_tx(struct mlx5e_priv *priv) @@ -4975,7 +4970,6 @@ err_cleanup_nic: int mlx5e_attach_netdev(struct mlx5e_priv *priv) { - struct mlx5_core_dev *mdev = priv->mdev; const struct mlx5e_profile *profile; int err; @@ -4986,28 +4980,16 @@ int mlx5e_attach_netdev(struct mlx5e_priv *priv) if (err) goto out; - mlx5e_create_q_counters(priv); - - err = mlx5e_open_drop_rq(priv, &priv->drop_rq); - if (err) { - mlx5_core_err(mdev, "open drop rq failed, %d\n", err); - goto err_destroy_q_counters; - } - err = profile->init_rx(priv); if (err) - goto err_close_drop_rq; + goto err_cleanup_tx; if (profile->enable) profile->enable(priv); return 0; -err_close_drop_rq: - mlx5e_close_drop_rq(&priv->drop_rq); - -err_destroy_q_counters: - mlx5e_destroy_q_counters(priv); +err_cleanup_tx: profile->cleanup_tx(priv); out: @@ -5025,8 +5007,6 @@ void mlx5e_detach_netdev(struct mlx5e_priv *priv) flush_workqueue(priv->wq); profile->cleanup_rx(priv); - mlx5e_close_drop_rq(&priv->drop_rq); - mlx5e_destroy_q_counters(priv); profile->cleanup_tx(priv); cancel_delayed_work_sync(&priv->update_stats_work); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c index c9cc9747d21d..f6eead24931f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c @@ -999,14 +999,21 @@ static int mlx5e_init_rep_rx(struct mlx5e_priv *priv) struct mlx5_eswitch *esw = priv->mdev->priv.eswitch; struct mlx5e_rep_priv *rpriv = priv->ppriv; struct mlx5_eswitch_rep *rep = rpriv->rep; + struct mlx5_core_dev *mdev = priv->mdev; struct mlx5_flow_handle *flow_rule; int err; mlx5e_init_l2_addr(priv); + err = mlx5e_open_drop_rq(priv, &priv->drop_rq); + if (err) { + mlx5_core_err(mdev, "open drop rq failed, %d\n", err); + return err; + } + err = mlx5e_create_direct_rqts(priv); if (err) - return err; + goto err_close_drop_rq; err = mlx5e_create_direct_tirs(priv); if (err) @@ -1027,6 +1034,8 @@ err_destroy_direct_tirs: mlx5e_destroy_direct_tirs(priv); err_destroy_direct_rqts: mlx5e_destroy_direct_rqts(priv); +err_close_drop_rq: + mlx5e_close_drop_rq(&priv->drop_rq); return err; } @@ -1037,6 +1046,7 @@ static void mlx5e_cleanup_rep_rx(struct mlx5e_priv *priv) mlx5_del_flow_rules(rpriv->vport_rx_rule); mlx5e_destroy_direct_tirs(priv); mlx5e_destroy_direct_rqts(priv); + mlx5e_close_drop_rq(&priv->drop_rq); } static int mlx5e_init_rep_tx(struct mlx5e_priv *priv) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c index 6a959e8b1f9d..424bc89184c6 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c @@ -37,6 +37,7 @@ #include <net/busy_poll.h> #include <net/ip6_checksum.h> #include <net/page_pool.h> +#include <net/inet_ecn.h> #include "en.h" #include "en_tc.h" #include "eswitch.h" @@ -690,12 +691,29 @@ static inline void mlx5e_skb_set_hash(struct mlx5_cqe64 *cqe, skb_set_hash(skb, be32_to_cpu(cqe->rss_hash_result), ht); } -static inline bool is_last_ethertype_ip(struct sk_buff *skb, int *network_depth) +static inline bool is_last_ethertype_ip(struct sk_buff *skb, int *network_depth, + __be16 *proto) { - __be16 ethertype = ((struct ethhdr *)skb->data)->h_proto; + *proto = ((struct ethhdr *)skb->data)->h_proto; + *proto = __vlan_get_protocol(skb, *proto, network_depth); + return (*proto == htons(ETH_P_IP) || *proto == htons(ETH_P_IPV6)); +} + +static inline void mlx5e_enable_ecn(struct mlx5e_rq *rq, struct sk_buff *skb) +{ + int network_depth = 0; + __be16 proto; + void *ip; + int rc; + + if (unlikely(!is_last_ethertype_ip(skb, &network_depth, &proto))) + return; + + ip = skb->data + network_depth; + rc = ((proto == htons(ETH_P_IP)) ? IP_ECN_set_ce((struct iphdr *)ip) : + IP6_ECN_set_ce(skb, (struct ipv6hdr *)ip)); - ethertype = __vlan_get_protocol(skb, ethertype, network_depth); - return (ethertype == htons(ETH_P_IP) || ethertype == htons(ETH_P_IPV6)); + rq->stats->ecn_mark += !!rc; } static __be32 mlx5e_get_fcs(struct sk_buff *skb) @@ -737,6 +755,14 @@ static __be32 mlx5e_get_fcs(struct sk_buff *skb) return fcs_bytes; } +static u8 get_ip_proto(struct sk_buff *skb, __be16 proto) +{ + void *ip_p = skb->data + sizeof(struct ethhdr); + + return (proto == htons(ETH_P_IP)) ? ((struct iphdr *)ip_p)->protocol : + ((struct ipv6hdr *)ip_p)->nexthdr; +} + static inline void mlx5e_handle_csum(struct net_device *netdev, struct mlx5_cqe64 *cqe, struct mlx5e_rq *rq, @@ -745,6 +771,7 @@ static inline void mlx5e_handle_csum(struct net_device *netdev, { struct mlx5e_rq_stats *stats = rq->stats; int network_depth = 0; + __be16 proto; if (unlikely(!(netdev->features & NETIF_F_RXCSUM))) goto csum_none; @@ -755,7 +782,10 @@ static inline void mlx5e_handle_csum(struct net_device *netdev, return; } - if (likely(is_last_ethertype_ip(skb, &network_depth))) { + if (likely(is_last_ethertype_ip(skb, &network_depth, &proto))) { + if (unlikely(get_ip_proto(skb, proto) == IPPROTO_SCTP)) + goto csum_unnecessary; + skb->ip_summed = CHECKSUM_COMPLETE; skb->csum = csum_unfold((__force __sum16)cqe->check_sum); if (network_depth > ETH_HLEN) @@ -773,6 +803,7 @@ static inline void mlx5e_handle_csum(struct net_device *netdev, return; } +csum_unnecessary: if (likely((cqe->hds_ip_ext & CQE_L3_OK) && (cqe->hds_ip_ext & CQE_L4_OK))) { skb->ip_summed = CHECKSUM_UNNECESSARY; @@ -790,6 +821,8 @@ csum_none: stats->csum_none++; } +#define MLX5E_CE_BIT_MASK 0x80 + static inline void mlx5e_build_rx_skb(struct mlx5_cqe64 *cqe, u32 cqe_bcnt, struct mlx5e_rq *rq, @@ -834,6 +867,10 @@ static inline void mlx5e_build_rx_skb(struct mlx5_cqe64 *cqe, skb->mark = be32_to_cpu(cqe->sop_drop_qpn) & MLX5E_TC_FLOW_ID_MASK; mlx5e_handle_csum(netdev, cqe, rq, skb, !!lro_num_seg); + /* checking CE bit in cqe - MSB in ml_path field */ + if (unlikely(cqe->ml_path & MLX5E_CE_BIT_MASK)) + mlx5e_enable_ecn(rq, skb); + skb->protocol = eth_type_trans(skb, netdev); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c index 6839481f7697..90c7607b1f44 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c @@ -53,6 +53,7 @@ static const struct counter_desc sw_stats_desc[] = { { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_lro_packets) }, { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_lro_bytes) }, + { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_ecn_mark) }, { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_removed_vlan_packets) }, { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_csum_unnecessary) }, { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_csum_none) }, @@ -144,6 +145,7 @@ void mlx5e_grp_sw_update_stats(struct mlx5e_priv *priv) s->rx_bytes += rq_stats->bytes; s->rx_lro_packets += rq_stats->lro_packets; s->rx_lro_bytes += rq_stats->lro_bytes; + s->rx_ecn_mark += rq_stats->ecn_mark; s->rx_removed_vlan_packets += rq_stats->removed_vlan_packets; s->rx_csum_none += rq_stats->csum_none; s->rx_csum_complete += rq_stats->csum_complete; @@ -1144,6 +1146,7 @@ static const struct counter_desc rq_stats_desc[] = { { MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, xdp_redirect) }, { MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, lro_packets) }, { MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, lro_bytes) }, + { MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, ecn_mark) }, { MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, removed_vlan_packets) }, { MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, wqe_err) }, { MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, mpwqe_filler_cqes) }, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h index a4c035aedd46..a5fb3dc27f50 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h @@ -66,6 +66,7 @@ struct mlx5e_sw_stats { u64 tx_nop; u64 rx_lro_packets; u64 rx_lro_bytes; + u64 rx_ecn_mark; u64 rx_removed_vlan_packets; u64 rx_csum_unnecessary; u64 rx_csum_none; @@ -184,6 +185,7 @@ struct mlx5e_rq_stats { u64 csum_none; u64 lro_packets; u64 lro_bytes; + u64 ecn_mark; u64 removed_vlan_packets; u64 xdp_drop; u64 xdp_redirect; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c index f72b5c9dcfe9..3028e8d90920 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c @@ -663,6 +663,7 @@ static int esw_create_offloads_fdb_tables(struct mlx5_eswitch *esw, int nvports) if (err) goto miss_rule_err; + kvfree(flow_group_in); return 0; miss_rule_err: diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c index f418541af7cf..37d114c668b7 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c @@ -1578,6 +1578,33 @@ static u64 matched_fgs_get_version(struct list_head *match_head) return version; } +static struct fs_fte * +lookup_fte_locked(struct mlx5_flow_group *g, + u32 *match_value, + bool take_write) +{ + struct fs_fte *fte_tmp; + + if (take_write) + nested_down_write_ref_node(&g->node, FS_LOCK_PARENT); + else + nested_down_read_ref_node(&g->node, FS_LOCK_PARENT); + fte_tmp = rhashtable_lookup_fast(&g->ftes_hash, match_value, + rhash_fte); + if (!fte_tmp || !tree_get_node(&fte_tmp->node)) { + fte_tmp = NULL; + goto out; + } + + nested_down_write_ref_node(&fte_tmp->node, FS_LOCK_CHILD); +out: + if (take_write) + up_write_ref_node(&g->node); + else + up_read_ref_node(&g->node); + return fte_tmp; +} + static struct mlx5_flow_handle * try_add_to_existing_fg(struct mlx5_flow_table *ft, struct list_head *match_head, @@ -1600,10 +1627,6 @@ try_add_to_existing_fg(struct mlx5_flow_table *ft, if (IS_ERR(fte)) return ERR_PTR(-ENOMEM); - list_for_each_entry(iter, match_head, list) { - nested_down_read_ref_node(&iter->g->node, FS_LOCK_PARENT); - } - search_again_locked: version = matched_fgs_get_version(match_head); /* Try to find a fg that already contains a matching fte */ @@ -1611,20 +1634,9 @@ search_again_locked: struct fs_fte *fte_tmp; g = iter->g; - fte_tmp = rhashtable_lookup_fast(&g->ftes_hash, spec->match_value, - rhash_fte); - if (!fte_tmp || !tree_get_node(&fte_tmp->node)) + fte_tmp = lookup_fte_locked(g, spec->match_value, take_write); + if (!fte_tmp) continue; - - nested_down_write_ref_node(&fte_tmp->node, FS_LOCK_CHILD); - if (!take_write) { - list_for_each_entry(iter, match_head, list) - up_read_ref_node(&iter->g->node); - } else { - list_for_each_entry(iter, match_head, list) - up_write_ref_node(&iter->g->node); - } - rule = add_rule_fg(g, spec->match_value, flow_act, dest, dest_num, fte_tmp); up_write_ref_node(&fte_tmp->node); @@ -1633,19 +1645,6 @@ search_again_locked: return rule; } - /* No group with matching fte found. Try to add a new fte to any - * matching fg. - */ - - if (!take_write) { - list_for_each_entry(iter, match_head, list) - up_read_ref_node(&iter->g->node); - list_for_each_entry(iter, match_head, list) - nested_down_write_ref_node(&iter->g->node, - FS_LOCK_PARENT); - take_write = true; - } - /* Check the ft version, for case that new flow group * was added while the fgs weren't locked */ @@ -1657,27 +1656,30 @@ search_again_locked: /* Check the fgs version, for case the new FTE with the * same values was added while the fgs weren't locked */ - if (version != matched_fgs_get_version(match_head)) + if (version != matched_fgs_get_version(match_head)) { + take_write = true; goto search_again_locked; + } list_for_each_entry(iter, match_head, list) { g = iter->g; if (!g->node.active) continue; + + nested_down_write_ref_node(&g->node, FS_LOCK_PARENT); + err = insert_fte(g, fte); if (err) { + up_write_ref_node(&g->node); if (err == -ENOSPC) continue; - list_for_each_entry(iter, match_head, list) - up_write_ref_node(&iter->g->node); kmem_cache_free(steering->ftes_cache, fte); return ERR_PTR(err); } nested_down_write_ref_node(&fte->node, FS_LOCK_CHILD); - list_for_each_entry(iter, match_head, list) - up_write_ref_node(&iter->g->node); + up_write_ref_node(&g->node); rule = add_rule_fg(g, spec->match_value, flow_act, dest, dest_num, fte); up_write_ref_node(&fte->node); @@ -1686,8 +1688,6 @@ search_again_locked: } rule = ERR_PTR(-ENOENT); out: - list_for_each_entry(iter, match_head, list) - up_write_ref_node(&iter->g->node); kmem_cache_free(steering->ftes_cache, fte); return rule; } @@ -1726,6 +1726,8 @@ search_again_locked: if (err) { if (take_write) up_write_ref_node(&ft->node); + else + up_read_ref_node(&ft->node); return ERR_PTR(err); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h index 32070e5d993d..a06f83c0c2b6 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h @@ -36,6 +36,7 @@ #include <linux/refcount.h> #include <linux/mlx5/fs.h> #include <linux/rhashtable.h> +#include <linux/llist.h> enum fs_node_type { FS_TYPE_NAMESPACE, @@ -138,8 +139,9 @@ struct mlx5_fc_cache { }; struct mlx5_fc { - struct rb_node node; struct list_head list; + struct llist_node addlist; + struct llist_node dellist; /* last{packets,bytes} members are used when calculating the delta since * last reading @@ -148,7 +150,6 @@ struct mlx5_fc { u64 lastbytes; u32 id; - bool deleted; bool aging; struct mlx5_fc_cache cache ____cacheline_aligned_in_smp; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_counters.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_counters.c index 58af6be13dfa..09206c4acd9a 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_counters.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_counters.c @@ -52,11 +52,13 @@ * access to counter list: * - create (user context) * - mlx5_fc_create() only adds to an addlist to be used by - * mlx5_fc_stats_query_work(). addlist is protected by a spinlock. + * mlx5_fc_stats_query_work(). addlist is a lockless single linked list + * that doesn't require any additional synchronization when adding single + * node. * - spawn thread to do the actual destroy * * - destroy (user context) - * - mark a counter as deleted + * - add a counter to lockless dellist * - spawn thread to do the actual del * * - dump (user context) @@ -71,36 +73,43 @@ * elapsed, the thread will actually query the hardware. */ -static void mlx5_fc_stats_insert(struct rb_root *root, struct mlx5_fc *counter) +static struct list_head *mlx5_fc_counters_lookup_next(struct mlx5_core_dev *dev, + u32 id) { - struct rb_node **new = &root->rb_node; - struct rb_node *parent = NULL; - - while (*new) { - struct mlx5_fc *this = rb_entry(*new, struct mlx5_fc, node); - int result = counter->id - this->id; - - parent = *new; - if (result < 0) - new = &((*new)->rb_left); - else - new = &((*new)->rb_right); - } + struct mlx5_fc_stats *fc_stats = &dev->priv.fc_stats; + unsigned long next_id = (unsigned long)id + 1; + struct mlx5_fc *counter; + + rcu_read_lock(); + /* skip counters that are in idr, but not yet in counters list */ + while ((counter = idr_get_next_ul(&fc_stats->counters_idr, + &next_id)) != NULL && + list_empty(&counter->list)) + next_id++; + rcu_read_unlock(); + + return counter ? &counter->list : &fc_stats->counters; +} - /* Add new node and rebalance tree. */ - rb_link_node(&counter->node, parent, new); - rb_insert_color(&counter->node, root); +static void mlx5_fc_stats_insert(struct mlx5_core_dev *dev, + struct mlx5_fc *counter) +{ + struct list_head *next = mlx5_fc_counters_lookup_next(dev, counter->id); + + list_add_tail(&counter->list, next); } -/* The function returns the last node that was queried so the caller +/* The function returns the last counter that was queried so the caller * function can continue calling it till all counters are queried. */ -static struct rb_node *mlx5_fc_stats_query(struct mlx5_core_dev *dev, +static struct mlx5_fc *mlx5_fc_stats_query(struct mlx5_core_dev *dev, struct mlx5_fc *first, u32 last_id) { + struct mlx5_fc_stats *fc_stats = &dev->priv.fc_stats; + struct mlx5_fc *counter = NULL; struct mlx5_cmd_fc_bulk *b; - struct rb_node *node = NULL; + bool more = false; u32 afirst_id; int num; int err; @@ -130,14 +139,16 @@ static struct rb_node *mlx5_fc_stats_query(struct mlx5_core_dev *dev, goto out; } - for (node = &first->node; node; node = rb_next(node)) { - struct mlx5_fc *counter = rb_entry(node, struct mlx5_fc, node); + counter = first; + list_for_each_entry_from(counter, &fc_stats->counters, list) { struct mlx5_fc_cache *c = &counter->cache; u64 packets; u64 bytes; - if (counter->id > last_id) + if (counter->id > last_id) { + more = true; break; + } mlx5_cmd_fc_bulk_get(dev, b, counter->id, &packets, &bytes); @@ -153,7 +164,14 @@ static struct rb_node *mlx5_fc_stats_query(struct mlx5_core_dev *dev, out: mlx5_cmd_fc_bulk_free(b); - return node; + return more ? counter : NULL; +} + +static void mlx5_free_fc(struct mlx5_core_dev *dev, + struct mlx5_fc *counter) +{ + mlx5_cmd_fc_free(dev, counter->id); + kfree(counter); } static void mlx5_fc_stats_work(struct work_struct *work) @@ -161,52 +179,33 @@ static void mlx5_fc_stats_work(struct work_struct *work) struct mlx5_core_dev *dev = container_of(work, struct mlx5_core_dev, priv.fc_stats.work.work); struct mlx5_fc_stats *fc_stats = &dev->priv.fc_stats; + struct llist_node *tmplist = llist_del_all(&fc_stats->addlist); + struct mlx5_fc *counter = NULL, *last = NULL, *tmp; unsigned long now = jiffies; - struct mlx5_fc *counter = NULL; - struct mlx5_fc *last = NULL; - struct rb_node *node; - LIST_HEAD(tmplist); - - spin_lock(&fc_stats->addlist_lock); - list_splice_tail_init(&fc_stats->addlist, &tmplist); - - if (!list_empty(&tmplist) || !RB_EMPTY_ROOT(&fc_stats->counters)) + if (tmplist || !list_empty(&fc_stats->counters)) queue_delayed_work(fc_stats->wq, &fc_stats->work, fc_stats->sampling_interval); - spin_unlock(&fc_stats->addlist_lock); - - list_for_each_entry(counter, &tmplist, list) - mlx5_fc_stats_insert(&fc_stats->counters, counter); - - node = rb_first(&fc_stats->counters); - while (node) { - counter = rb_entry(node, struct mlx5_fc, node); - - node = rb_next(node); - - if (counter->deleted) { - rb_erase(&counter->node, &fc_stats->counters); + llist_for_each_entry(counter, tmplist, addlist) + mlx5_fc_stats_insert(dev, counter); - mlx5_cmd_fc_free(dev, counter->id); - - kfree(counter); - continue; - } + tmplist = llist_del_all(&fc_stats->dellist); + llist_for_each_entry_safe(counter, tmp, tmplist, dellist) { + list_del(&counter->list); - last = counter; + mlx5_free_fc(dev, counter); } - if (time_before(now, fc_stats->next_query) || !last) + if (time_before(now, fc_stats->next_query) || + list_empty(&fc_stats->counters)) return; + last = list_last_entry(&fc_stats->counters, struct mlx5_fc, list); - node = rb_first(&fc_stats->counters); - while (node) { - counter = rb_entry(node, struct mlx5_fc, node); - - node = mlx5_fc_stats_query(dev, counter, last->id); - } + counter = list_first_entry(&fc_stats->counters, struct mlx5_fc, + list); + while (counter) + counter = mlx5_fc_stats_query(dev, counter, last->id); fc_stats->next_query = now + fc_stats->sampling_interval; } @@ -220,24 +219,38 @@ struct mlx5_fc *mlx5_fc_create(struct mlx5_core_dev *dev, bool aging) counter = kzalloc(sizeof(*counter), GFP_KERNEL); if (!counter) return ERR_PTR(-ENOMEM); + INIT_LIST_HEAD(&counter->list); err = mlx5_cmd_fc_alloc(dev, &counter->id); if (err) goto err_out; if (aging) { + u32 id = counter->id; + counter->cache.lastuse = jiffies; counter->aging = true; - spin_lock(&fc_stats->addlist_lock); - list_add(&counter->list, &fc_stats->addlist); - spin_unlock(&fc_stats->addlist_lock); + idr_preload(GFP_KERNEL); + spin_lock(&fc_stats->counters_idr_lock); + + err = idr_alloc_u32(&fc_stats->counters_idr, counter, &id, id, + GFP_NOWAIT); + + spin_unlock(&fc_stats->counters_idr_lock); + idr_preload_end(); + if (err) + goto err_out_alloc; + + llist_add(&counter->addlist, &fc_stats->addlist); mod_delayed_work(fc_stats->wq, &fc_stats->work, 0); } return counter; +err_out_alloc: + mlx5_cmd_fc_free(dev, counter->id); err_out: kfree(counter); @@ -253,13 +266,16 @@ void mlx5_fc_destroy(struct mlx5_core_dev *dev, struct mlx5_fc *counter) return; if (counter->aging) { - counter->deleted = true; + spin_lock(&fc_stats->counters_idr_lock); + WARN_ON(!idr_remove(&fc_stats->counters_idr, counter->id)); + spin_unlock(&fc_stats->counters_idr_lock); + + llist_add(&counter->dellist, &fc_stats->dellist); mod_delayed_work(fc_stats->wq, &fc_stats->work, 0); return; } - mlx5_cmd_fc_free(dev, counter->id); - kfree(counter); + mlx5_free_fc(dev, counter); } EXPORT_SYMBOL(mlx5_fc_destroy); @@ -267,9 +283,11 @@ int mlx5_init_fc_stats(struct mlx5_core_dev *dev) { struct mlx5_fc_stats *fc_stats = &dev->priv.fc_stats; - fc_stats->counters = RB_ROOT; - INIT_LIST_HEAD(&fc_stats->addlist); - spin_lock_init(&fc_stats->addlist_lock); + spin_lock_init(&fc_stats->counters_idr_lock); + idr_init(&fc_stats->counters_idr); + INIT_LIST_HEAD(&fc_stats->counters); + init_llist_head(&fc_stats->addlist); + init_llist_head(&fc_stats->dellist); fc_stats->wq = create_singlethread_workqueue("mlx5_fc"); if (!fc_stats->wq) @@ -284,34 +302,22 @@ int mlx5_init_fc_stats(struct mlx5_core_dev *dev) void mlx5_cleanup_fc_stats(struct mlx5_core_dev *dev) { struct mlx5_fc_stats *fc_stats = &dev->priv.fc_stats; + struct llist_node *tmplist; struct mlx5_fc *counter; struct mlx5_fc *tmp; - struct rb_node *node; cancel_delayed_work_sync(&dev->priv.fc_stats.work); destroy_workqueue(dev->priv.fc_stats.wq); dev->priv.fc_stats.wq = NULL; - list_for_each_entry_safe(counter, tmp, &fc_stats->addlist, list) { - list_del(&counter->list); - - mlx5_cmd_fc_free(dev, counter->id); + idr_destroy(&fc_stats->counters_idr); - kfree(counter); - } + tmplist = llist_del_all(&fc_stats->addlist); + llist_for_each_entry_safe(counter, tmp, tmplist, addlist) + mlx5_free_fc(dev, counter); - node = rb_first(&fc_stats->counters); - while (node) { - counter = rb_entry(node, struct mlx5_fc, node); - - node = rb_next(node); - - rb_erase(&counter->node, &fc_stats->counters); - - mlx5_cmd_fc_free(dev, counter->id); - - kfree(counter); - } + list_for_each_entry_safe(counter, tmp, &fc_stats->counters, list) + mlx5_free_fc(dev, counter); } int mlx5_fc_query(struct mlx5_core_dev *dev, struct mlx5_fc *counter, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/health.c b/drivers/net/ethernet/mellanox/mlx5/core/health.c index d39b0b7011b2..9f39aeca863f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/health.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/health.c @@ -331,9 +331,17 @@ void mlx5_start_health_poll(struct mlx5_core_dev *dev) add_timer(&health->timer); } -void mlx5_stop_health_poll(struct mlx5_core_dev *dev) +void mlx5_stop_health_poll(struct mlx5_core_dev *dev, bool disable_health) { struct mlx5_core_health *health = &dev->priv.health; + unsigned long flags; + + if (disable_health) { + spin_lock_irqsave(&health->wq_lock, flags); + set_bit(MLX5_DROP_NEW_HEALTH_WORK, &health->flags); + set_bit(MLX5_DROP_NEW_RECOVERY_WORK, &health->flags); + spin_unlock_irqrestore(&health->wq_lock, flags); + } del_timer_sync(&health->timer); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c index 3dd9f885ed8b..a825ed093efd 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c @@ -349,11 +349,20 @@ static void mlx5i_destroy_flow_steering(struct mlx5e_priv *priv) static int mlx5i_init_rx(struct mlx5e_priv *priv) { + struct mlx5_core_dev *mdev = priv->mdev; int err; + mlx5e_create_q_counters(priv); + + err = mlx5e_open_drop_rq(priv, &priv->drop_rq); + if (err) { + mlx5_core_err(mdev, "open drop rq failed, %d\n", err); + goto err_destroy_q_counters; + } + err = mlx5e_create_indirect_rqt(priv); if (err) - return err; + goto err_close_drop_rq; err = mlx5e_create_direct_rqts(priv); if (err) @@ -381,6 +390,10 @@ err_destroy_direct_rqts: mlx5e_destroy_direct_rqts(priv); err_destroy_indirect_rqts: mlx5e_destroy_rqt(priv, &priv->indir_rqt); +err_close_drop_rq: + mlx5e_close_drop_rq(&priv->drop_rq); +err_destroy_q_counters: + mlx5e_destroy_q_counters(priv); return err; } @@ -391,6 +404,8 @@ static void mlx5i_cleanup_rx(struct mlx5e_priv *priv) mlx5e_destroy_indirect_tirs(priv); mlx5e_destroy_direct_rqts(priv); mlx5e_destroy_rqt(priv, &priv->indir_rqt); + mlx5e_close_drop_rq(&priv->drop_rq); + mlx5e_destroy_q_counters(priv); } static const struct mlx5e_profile mlx5i_nic_profile = { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c index 3f767cde4c1d..0d90b1b4a3d3 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c @@ -111,10 +111,10 @@ static void mlx5_pps_out(struct work_struct *work) for (i = 0; i < clock->ptp_info.n_pins; i++) { u64 tstart; - write_lock_irqsave(&clock->lock, flags); + write_seqlock_irqsave(&clock->lock, flags); tstart = clock->pps_info.start[i]; clock->pps_info.start[i] = 0; - write_unlock_irqrestore(&clock->lock, flags); + write_sequnlock_irqrestore(&clock->lock, flags); if (!tstart) continue; @@ -132,10 +132,10 @@ static void mlx5_timestamp_overflow(struct work_struct *work) overflow_work); unsigned long flags; - write_lock_irqsave(&clock->lock, flags); + write_seqlock_irqsave(&clock->lock, flags); timecounter_read(&clock->tc); mlx5_update_clock_info_page(clock->mdev); - write_unlock_irqrestore(&clock->lock, flags); + write_sequnlock_irqrestore(&clock->lock, flags); schedule_delayed_work(&clock->overflow_work, clock->overflow_period); } @@ -147,10 +147,10 @@ static int mlx5_ptp_settime(struct ptp_clock_info *ptp, u64 ns = timespec64_to_ns(ts); unsigned long flags; - write_lock_irqsave(&clock->lock, flags); + write_seqlock_irqsave(&clock->lock, flags); timecounter_init(&clock->tc, &clock->cycles, ns); mlx5_update_clock_info_page(clock->mdev); - write_unlock_irqrestore(&clock->lock, flags); + write_sequnlock_irqrestore(&clock->lock, flags); return 0; } @@ -162,9 +162,9 @@ static int mlx5_ptp_gettime(struct ptp_clock_info *ptp, struct timespec64 *ts) u64 ns; unsigned long flags; - write_lock_irqsave(&clock->lock, flags); + write_seqlock_irqsave(&clock->lock, flags); ns = timecounter_read(&clock->tc); - write_unlock_irqrestore(&clock->lock, flags); + write_sequnlock_irqrestore(&clock->lock, flags); *ts = ns_to_timespec64(ns); @@ -177,10 +177,10 @@ static int mlx5_ptp_adjtime(struct ptp_clock_info *ptp, s64 delta) ptp_info); unsigned long flags; - write_lock_irqsave(&clock->lock, flags); + write_seqlock_irqsave(&clock->lock, flags); timecounter_adjtime(&clock->tc, delta); mlx5_update_clock_info_page(clock->mdev); - write_unlock_irqrestore(&clock->lock, flags); + write_sequnlock_irqrestore(&clock->lock, flags); return 0; } @@ -203,12 +203,12 @@ static int mlx5_ptp_adjfreq(struct ptp_clock_info *ptp, s32 delta) adj *= delta; diff = div_u64(adj, 1000000000ULL); - write_lock_irqsave(&clock->lock, flags); + write_seqlock_irqsave(&clock->lock, flags); timecounter_read(&clock->tc); clock->cycles.mult = neg_adj ? clock->nominal_c_mult - diff : clock->nominal_c_mult + diff; mlx5_update_clock_info_page(clock->mdev); - write_unlock_irqrestore(&clock->lock, flags); + write_sequnlock_irqrestore(&clock->lock, flags); return 0; } @@ -307,12 +307,12 @@ static int mlx5_perout_configure(struct ptp_clock_info *ptp, ts.tv_nsec = rq->perout.start.nsec; ns = timespec64_to_ns(&ts); cycles_now = mlx5_read_internal_timer(mdev); - write_lock_irqsave(&clock->lock, flags); + write_seqlock_irqsave(&clock->lock, flags); nsec_now = timecounter_cyc2time(&clock->tc, cycles_now); nsec_delta = ns - nsec_now; cycles_delta = div64_u64(nsec_delta << clock->cycles.shift, clock->cycles.mult); - write_unlock_irqrestore(&clock->lock, flags); + write_sequnlock_irqrestore(&clock->lock, flags); time_stamp = cycles_now + cycles_delta; field_select = MLX5_MTPPS_FS_PIN_MODE | MLX5_MTPPS_FS_PATTERN | @@ -471,14 +471,14 @@ void mlx5_pps_event(struct mlx5_core_dev *mdev, ts.tv_sec += 1; ts.tv_nsec = 0; ns = timespec64_to_ns(&ts); - write_lock_irqsave(&clock->lock, flags); + write_seqlock_irqsave(&clock->lock, flags); nsec_now = timecounter_cyc2time(&clock->tc, cycles_now); nsec_delta = ns - nsec_now; cycles_delta = div64_u64(nsec_delta << clock->cycles.shift, clock->cycles.mult); clock->pps_info.start[pin] = cycles_now + cycles_delta; schedule_work(&clock->pps_info.out_work); - write_unlock_irqrestore(&clock->lock, flags); + write_sequnlock_irqrestore(&clock->lock, flags); break; default: mlx5_core_err(mdev, " Unhandled event\n"); @@ -498,7 +498,7 @@ void mlx5_init_clock(struct mlx5_core_dev *mdev) mlx5_core_warn(mdev, "invalid device_frequency_khz, aborting HW clock init\n"); return; } - rwlock_init(&clock->lock); + seqlock_init(&clock->lock); clock->cycles.read = read_internal_timer; clock->cycles.shift = MLX5_CYCLES_SHIFT; clock->cycles.mult = clocksource_khz2mult(dev_freq, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.h b/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.h index 02e2e4575e4f..263cb6e2aeee 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.h @@ -46,11 +46,13 @@ static inline int mlx5_clock_get_ptp_index(struct mlx5_core_dev *mdev) static inline ktime_t mlx5_timecounter_cyc2time(struct mlx5_clock *clock, u64 timestamp) { + unsigned int seq; u64 nsec; - read_lock(&clock->lock); - nsec = timecounter_cyc2time(&clock->tc, timestamp); - read_unlock(&clock->lock); + do { + seq = read_seqbegin(&clock->lock); + nsec = timecounter_cyc2time(&clock->tc, timestamp); + } while (read_seqretry(&clock->lock, seq)); return ns_to_ktime(nsec); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c index cf3e4a659052..b5e9f664fc66 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c @@ -878,8 +878,10 @@ static int mlx5_pci_init(struct mlx5_core_dev *dev, struct mlx5_priv *priv) priv->numa_node = dev_to_node(&dev->pdev->dev); priv->dbg_root = debugfs_create_dir(dev_name(&pdev->dev), mlx5_debugfs_root); - if (!priv->dbg_root) + if (!priv->dbg_root) { + dev_err(&pdev->dev, "Cannot create debugfs dir, aborting\n"); return -ENOMEM; + } err = mlx5_pci_enable_device(dev); if (err) { @@ -928,7 +930,7 @@ static void mlx5_pci_close(struct mlx5_core_dev *dev, struct mlx5_priv *priv) pci_clear_master(dev->pdev); release_bar(dev->pdev); mlx5_pci_disable_device(dev); - debugfs_remove(priv->dbg_root); + debugfs_remove_recursive(priv->dbg_root); } static int mlx5_init_once(struct mlx5_core_dev *dev, struct mlx5_priv *priv) @@ -1286,7 +1288,7 @@ err_cleanup_once: mlx5_cleanup_once(dev); err_stop_poll: - mlx5_stop_health_poll(dev); + mlx5_stop_health_poll(dev, boot); if (mlx5_cmd_teardown_hca(dev)) { dev_err(&dev->pdev->dev, "tear_down_hca failed, skip cleanup\n"); goto out_err; @@ -1346,7 +1348,7 @@ static int mlx5_unload_one(struct mlx5_core_dev *dev, struct mlx5_priv *priv, mlx5_free_irq_vectors(dev); if (cleanup) mlx5_cleanup_once(dev); - mlx5_stop_health_poll(dev); + mlx5_stop_health_poll(dev, cleanup); err = mlx5_cmd_teardown_hca(dev); if (err) { dev_err(&dev->pdev->dev, "tear_down_hca failed, skip cleanup\n"); @@ -1608,7 +1610,7 @@ static int mlx5_try_fast_unload(struct mlx5_core_dev *dev) * with the HCA, so the health polll is no longer needed. */ mlx5_drain_health_wq(dev); - mlx5_stop_health_poll(dev); + mlx5_stop_health_poll(dev, false); ret = mlx5_cmd_force_teardown_hca(dev); if (ret) { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/srq.c b/drivers/net/ethernet/mellanox/mlx5/core/srq.c index 23cc337a96c9..7e20666ce5ae 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/srq.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/srq.c @@ -73,7 +73,7 @@ static int get_pas_size(struct mlx5_srq_attr *in) u32 rq_sz = 1 << (log_srq_size + 4 + log_rq_stride); u32 page_size = 1 << log_page_size; u32 rq_sz_po = rq_sz + (page_offset * po_quanta); - u32 rq_num_pas = (rq_sz_po + page_size - 1) / page_size; + u32 rq_num_pas = DIV_ROUND_UP(rq_sz_po, page_size); return rq_num_pas * sizeof(u64); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/transobj.c b/drivers/net/ethernet/mellanox/mlx5/core/transobj.c index dae1c5c5d27c..d2f76070ea7c 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/transobj.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/transobj.c @@ -509,7 +509,7 @@ static int mlx5_hairpin_modify_sq(struct mlx5_core_dev *peer_mdev, u32 sqn, sqc = MLX5_ADDR_OF(modify_sq_in, in, ctx); - if (next_state == MLX5_RQC_STATE_RDY) { + if (next_state == MLX5_SQC_STATE_RDY) { MLX5_SET(sqc, sqc, hairpin_peer_rq, peer_rq); MLX5_SET(sqc, sqc, hairpin_peer_vhca, peer_vhca); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/wq.c b/drivers/net/ethernet/mellanox/mlx5/core/wq.c index c8c315eb5128..68e7f8df2a6d 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/wq.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/wq.c @@ -39,9 +39,9 @@ u32 mlx5_wq_cyc_get_size(struct mlx5_wq_cyc *wq) return (u32)wq->fbc.sz_m1 + 1; } -u32 mlx5_wq_cyc_get_frag_size(struct mlx5_wq_cyc *wq) +u16 mlx5_wq_cyc_get_frag_size(struct mlx5_wq_cyc *wq) { - return (u32)wq->fbc.frag_sz_m1 + 1; + return wq->fbc.frag_sz_m1 + 1; } u32 mlx5_cqwq_get_size(struct mlx5_cqwq *wq) @@ -138,7 +138,7 @@ int mlx5_wq_qp_create(struct mlx5_core_dev *mdev, struct mlx5_wq_param *param, void *qpc, struct mlx5_wq_qp *wq, struct mlx5_wq_ctrl *wq_ctrl) { - u32 sq_strides_offset; + u16 sq_strides_offset; u32 rq_pg_remainder; int err; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/wq.h b/drivers/net/ethernet/mellanox/mlx5/core/wq.h index 2bd4c3184eba..3a1a170bb2d7 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/wq.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/wq.h @@ -80,7 +80,7 @@ int mlx5_wq_cyc_create(struct mlx5_core_dev *mdev, struct mlx5_wq_param *param, void *wqc, struct mlx5_wq_cyc *wq, struct mlx5_wq_ctrl *wq_ctrl); u32 mlx5_wq_cyc_get_size(struct mlx5_wq_cyc *wq); -u32 mlx5_wq_cyc_get_frag_size(struct mlx5_wq_cyc *wq); +u16 mlx5_wq_cyc_get_frag_size(struct mlx5_wq_cyc *wq); int mlx5_wq_qp_create(struct mlx5_core_dev *mdev, struct mlx5_wq_param *param, void *qpc, struct mlx5_wq_qp *wq, diff --git a/drivers/net/ethernet/mellanox/mlxsw/reg.h b/drivers/net/ethernet/mellanox/mlxsw/reg.h index 6e8b619b769b..df81e0a1eb64 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/reg.h +++ b/drivers/net/ethernet/mellanox/mlxsw/reg.h @@ -8336,8 +8336,15 @@ MLXSW_ITEM32(reg, sbpr, dir, 0x00, 24, 2); */ MLXSW_ITEM32(reg, sbpr, pool, 0x00, 0, 4); +/* reg_sbpr_infi_size + * Size is infinite. + * Access: RW + */ +MLXSW_ITEM32(reg, sbpr, infi_size, 0x04, 31, 1); + /* reg_sbpr_size * Pool size in buffer cells. + * Reserved when infi_size = 1. * Access: RW */ MLXSW_ITEM32(reg, sbpr, size, 0x04, 0, 24); @@ -8355,13 +8362,15 @@ MLXSW_ITEM32(reg, sbpr, mode, 0x08, 0, 4); static inline void mlxsw_reg_sbpr_pack(char *payload, u8 pool, enum mlxsw_reg_sbxx_dir dir, - enum mlxsw_reg_sbpr_mode mode, u32 size) + enum mlxsw_reg_sbpr_mode mode, u32 size, + bool infi_size) { MLXSW_REG_ZERO(sbpr, payload); mlxsw_reg_sbpr_pool_set(payload, pool); mlxsw_reg_sbpr_dir_set(payload, dir); mlxsw_reg_sbpr_mode_set(payload, mode); mlxsw_reg_sbpr_size_set(payload, size); + mlxsw_reg_sbpr_infi_size_set(payload, infi_size); } /* SBCM - Shared Buffer Class Management Register @@ -8409,6 +8418,12 @@ MLXSW_ITEM32(reg, sbcm, min_buff, 0x18, 0, 24); #define MLXSW_REG_SBXX_DYN_MAX_BUFF_MIN 1 #define MLXSW_REG_SBXX_DYN_MAX_BUFF_MAX 14 +/* reg_sbcm_infi_max + * Max buffer is infinite. + * Access: RW + */ +MLXSW_ITEM32(reg, sbcm, infi_max, 0x1C, 31, 1); + /* reg_sbcm_max_buff * When the pool associated to the port-pg/tclass is configured to * static, Maximum buffer size for the limiter configured in cells. @@ -8418,6 +8433,7 @@ MLXSW_ITEM32(reg, sbcm, min_buff, 0x18, 0, 24); * 0: 0 * i: (1/128)*2^(i-1), for i=1..14 * 0xFF: Infinity + * Reserved when infi_max = 1. * Access: RW */ MLXSW_ITEM32(reg, sbcm, max_buff, 0x1C, 0, 24); @@ -8430,7 +8446,8 @@ MLXSW_ITEM32(reg, sbcm, pool, 0x24, 0, 4); static inline void mlxsw_reg_sbcm_pack(char *payload, u8 local_port, u8 pg_buff, enum mlxsw_reg_sbxx_dir dir, - u32 min_buff, u32 max_buff, u8 pool) + u32 min_buff, u32 max_buff, + bool infi_max, u8 pool) { MLXSW_REG_ZERO(sbcm, payload); mlxsw_reg_sbcm_local_port_set(payload, local_port); @@ -8438,6 +8455,7 @@ static inline void mlxsw_reg_sbcm_pack(char *payload, u8 local_port, u8 pg_buff, mlxsw_reg_sbcm_dir_set(payload, dir); mlxsw_reg_sbcm_min_buff_set(payload, min_buff); mlxsw_reg_sbcm_max_buff_set(payload, max_buff); + mlxsw_reg_sbcm_infi_max_set(payload, infi_max); mlxsw_reg_sbcm_pool_set(payload, pool); } diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c index 930700413b1d..88c33a8474eb 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c @@ -44,8 +44,8 @@ #define MLXSW_SP_FWREV_MINOR_TO_BRANCH(minor) ((minor) / 100) #define MLXSW_SP1_FWREV_MAJOR 13 -#define MLXSW_SP1_FWREV_MINOR 1702 -#define MLXSW_SP1_FWREV_SUBMINOR 6 +#define MLXSW_SP1_FWREV_MINOR 1703 +#define MLXSW_SP1_FWREV_SUBMINOR 4 #define MLXSW_SP1_FWREV_CAN_RESET_MINOR 1702 static const struct mlxsw_fw_rev mlxsw_sp1_fw_rev = { @@ -331,7 +331,10 @@ static int mlxsw_sp_fw_rev_validate(struct mlxsw_sp *mlxsw_sp) return -EINVAL; } if (MLXSW_SP_FWREV_MINOR_TO_BRANCH(rev->minor) == - MLXSW_SP_FWREV_MINOR_TO_BRANCH(req_rev->minor)) + MLXSW_SP_FWREV_MINOR_TO_BRANCH(req_rev->minor) && + (rev->minor > req_rev->minor || + (rev->minor == req_rev->minor && + rev->subminor >= req_rev->subminor))) return 0; dev_info(mlxsw_sp->bus_info->dev, "The firmware version %d.%d.%d is incompatible with the driver\n", @@ -2804,6 +2807,13 @@ static int mlxsw_sp_port_ets_init(struct mlxsw_sp_port *mlxsw_sp_port) MLXSW_REG_QEEC_MAS_DIS); if (err) return err; + + err = mlxsw_sp_port_ets_maxrate_set(mlxsw_sp_port, + MLXSW_REG_QEEC_HIERARCY_TC, + i + 8, i, + MLXSW_REG_QEEC_MAS_DIS); + if (err) + return err; } /* Map all priorities to traffic class 0. */ diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_buffers.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_buffers.c index 4327487553c5..12c61e0cc570 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_buffers.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_buffers.c @@ -25,28 +25,52 @@ struct mlxsw_cp_sb_occ { struct mlxsw_sp_sb_cm { u32 min_buff; u32 max_buff; - u8 pool; + u16 pool_index; struct mlxsw_cp_sb_occ occ; }; +#define MLXSW_SP_SB_INFI -1U + struct mlxsw_sp_sb_pm { u32 min_buff; u32 max_buff; struct mlxsw_cp_sb_occ occ; }; -#define MLXSW_SP_SB_POOL_COUNT 4 -#define MLXSW_SP_SB_TC_COUNT 8 +struct mlxsw_sp_sb_pool_des { + enum mlxsw_reg_sbxx_dir dir; + u8 pool; +}; + +/* Order ingress pools before egress pools. */ +static const struct mlxsw_sp_sb_pool_des mlxsw_sp_sb_pool_dess[] = { + {MLXSW_REG_SBXX_DIR_INGRESS, 0}, + {MLXSW_REG_SBXX_DIR_INGRESS, 1}, + {MLXSW_REG_SBXX_DIR_INGRESS, 2}, + {MLXSW_REG_SBXX_DIR_INGRESS, 3}, + {MLXSW_REG_SBXX_DIR_EGRESS, 0}, + {MLXSW_REG_SBXX_DIR_EGRESS, 1}, + {MLXSW_REG_SBXX_DIR_EGRESS, 2}, + {MLXSW_REG_SBXX_DIR_EGRESS, 3}, + {MLXSW_REG_SBXX_DIR_EGRESS, 15}, +}; + +#define MLXSW_SP_SB_POOL_DESS_LEN ARRAY_SIZE(mlxsw_sp_sb_pool_dess) + +#define MLXSW_SP_SB_ING_TC_COUNT 8 +#define MLXSW_SP_SB_EG_TC_COUNT 16 struct mlxsw_sp_sb_port { - struct mlxsw_sp_sb_cm cms[2][MLXSW_SP_SB_TC_COUNT]; - struct mlxsw_sp_sb_pm pms[2][MLXSW_SP_SB_POOL_COUNT]; + struct mlxsw_sp_sb_cm ing_cms[MLXSW_SP_SB_ING_TC_COUNT]; + struct mlxsw_sp_sb_cm eg_cms[MLXSW_SP_SB_EG_TC_COUNT]; + struct mlxsw_sp_sb_pm pms[MLXSW_SP_SB_POOL_DESS_LEN]; }; struct mlxsw_sp_sb { - struct mlxsw_sp_sb_pr prs[2][MLXSW_SP_SB_POOL_COUNT]; + struct mlxsw_sp_sb_pr prs[MLXSW_SP_SB_POOL_DESS_LEN]; struct mlxsw_sp_sb_port *ports; u32 cell_size; + u64 sb_size; }; u32 mlxsw_sp_cells_bytes(const struct mlxsw_sp *mlxsw_sp, u32 cells) @@ -60,95 +84,122 @@ u32 mlxsw_sp_bytes_cells(const struct mlxsw_sp *mlxsw_sp, u32 bytes) } static struct mlxsw_sp_sb_pr *mlxsw_sp_sb_pr_get(struct mlxsw_sp *mlxsw_sp, - u8 pool, - enum mlxsw_reg_sbxx_dir dir) + u16 pool_index) { - return &mlxsw_sp->sb->prs[dir][pool]; + return &mlxsw_sp->sb->prs[pool_index]; +} + +static bool mlxsw_sp_sb_cm_exists(u8 pg_buff, enum mlxsw_reg_sbxx_dir dir) +{ + if (dir == MLXSW_REG_SBXX_DIR_INGRESS) + return pg_buff < MLXSW_SP_SB_ING_TC_COUNT; + else + return pg_buff < MLXSW_SP_SB_EG_TC_COUNT; } static struct mlxsw_sp_sb_cm *mlxsw_sp_sb_cm_get(struct mlxsw_sp *mlxsw_sp, u8 local_port, u8 pg_buff, enum mlxsw_reg_sbxx_dir dir) { - return &mlxsw_sp->sb->ports[local_port].cms[dir][pg_buff]; + struct mlxsw_sp_sb_port *sb_port = &mlxsw_sp->sb->ports[local_port]; + + WARN_ON(!mlxsw_sp_sb_cm_exists(pg_buff, dir)); + if (dir == MLXSW_REG_SBXX_DIR_INGRESS) + return &sb_port->ing_cms[pg_buff]; + else + return &sb_port->eg_cms[pg_buff]; } static struct mlxsw_sp_sb_pm *mlxsw_sp_sb_pm_get(struct mlxsw_sp *mlxsw_sp, - u8 local_port, u8 pool, - enum mlxsw_reg_sbxx_dir dir) + u8 local_port, u16 pool_index) { - return &mlxsw_sp->sb->ports[local_port].pms[dir][pool]; + return &mlxsw_sp->sb->ports[local_port].pms[pool_index]; } -static int mlxsw_sp_sb_pr_write(struct mlxsw_sp *mlxsw_sp, u8 pool, - enum mlxsw_reg_sbxx_dir dir, - enum mlxsw_reg_sbpr_mode mode, u32 size) +static int mlxsw_sp_sb_pr_write(struct mlxsw_sp *mlxsw_sp, u16 pool_index, + enum mlxsw_reg_sbpr_mode mode, + u32 size, bool infi_size) { + const struct mlxsw_sp_sb_pool_des *des = + &mlxsw_sp_sb_pool_dess[pool_index]; char sbpr_pl[MLXSW_REG_SBPR_LEN]; struct mlxsw_sp_sb_pr *pr; int err; - mlxsw_reg_sbpr_pack(sbpr_pl, pool, dir, mode, size); + mlxsw_reg_sbpr_pack(sbpr_pl, des->pool, des->dir, mode, + size, infi_size); err = mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(sbpr), sbpr_pl); if (err) return err; - pr = mlxsw_sp_sb_pr_get(mlxsw_sp, pool, dir); + if (infi_size) + size = mlxsw_sp_bytes_cells(mlxsw_sp, mlxsw_sp->sb->sb_size); + pr = mlxsw_sp_sb_pr_get(mlxsw_sp, pool_index); pr->mode = mode; pr->size = size; return 0; } static int mlxsw_sp_sb_cm_write(struct mlxsw_sp *mlxsw_sp, u8 local_port, - u8 pg_buff, enum mlxsw_reg_sbxx_dir dir, - u32 min_buff, u32 max_buff, u8 pool) + u8 pg_buff, u32 min_buff, u32 max_buff, + bool infi_max, u16 pool_index) { + const struct mlxsw_sp_sb_pool_des *des = + &mlxsw_sp_sb_pool_dess[pool_index]; char sbcm_pl[MLXSW_REG_SBCM_LEN]; + struct mlxsw_sp_sb_cm *cm; int err; - mlxsw_reg_sbcm_pack(sbcm_pl, local_port, pg_buff, dir, - min_buff, max_buff, pool); + mlxsw_reg_sbcm_pack(sbcm_pl, local_port, pg_buff, des->dir, + min_buff, max_buff, infi_max, des->pool); err = mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(sbcm), sbcm_pl); if (err) return err; - if (pg_buff < MLXSW_SP_SB_TC_COUNT) { - struct mlxsw_sp_sb_cm *cm; - cm = mlxsw_sp_sb_cm_get(mlxsw_sp, local_port, pg_buff, dir); + if (mlxsw_sp_sb_cm_exists(pg_buff, des->dir)) { + if (infi_max) + max_buff = mlxsw_sp_bytes_cells(mlxsw_sp, + mlxsw_sp->sb->sb_size); + + cm = mlxsw_sp_sb_cm_get(mlxsw_sp, local_port, pg_buff, + des->dir); cm->min_buff = min_buff; cm->max_buff = max_buff; - cm->pool = pool; + cm->pool_index = pool_index; } return 0; } static int mlxsw_sp_sb_pm_write(struct mlxsw_sp *mlxsw_sp, u8 local_port, - u8 pool, enum mlxsw_reg_sbxx_dir dir, - u32 min_buff, u32 max_buff) + u16 pool_index, u32 min_buff, u32 max_buff) { + const struct mlxsw_sp_sb_pool_des *des = + &mlxsw_sp_sb_pool_dess[pool_index]; char sbpm_pl[MLXSW_REG_SBPM_LEN]; struct mlxsw_sp_sb_pm *pm; int err; - mlxsw_reg_sbpm_pack(sbpm_pl, local_port, pool, dir, false, + mlxsw_reg_sbpm_pack(sbpm_pl, local_port, des->pool, des->dir, false, min_buff, max_buff); err = mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(sbpm), sbpm_pl); if (err) return err; - pm = mlxsw_sp_sb_pm_get(mlxsw_sp, local_port, pool, dir); + pm = mlxsw_sp_sb_pm_get(mlxsw_sp, local_port, pool_index); pm->min_buff = min_buff; pm->max_buff = max_buff; return 0; } static int mlxsw_sp_sb_pm_occ_clear(struct mlxsw_sp *mlxsw_sp, u8 local_port, - u8 pool, enum mlxsw_reg_sbxx_dir dir, - struct list_head *bulk_list) + u16 pool_index, struct list_head *bulk_list) { + const struct mlxsw_sp_sb_pool_des *des = + &mlxsw_sp_sb_pool_dess[pool_index]; char sbpm_pl[MLXSW_REG_SBPM_LEN]; - mlxsw_reg_sbpm_pack(sbpm_pl, local_port, pool, dir, true, 0, 0); + mlxsw_reg_sbpm_pack(sbpm_pl, local_port, des->pool, des->dir, + true, 0, 0); return mlxsw_reg_trans_query(mlxsw_sp->core, MLXSW_REG(sbpm), sbpm_pl, bulk_list, NULL, 0); } @@ -163,14 +214,16 @@ static void mlxsw_sp_sb_pm_occ_query_cb(struct mlxsw_core *mlxsw_core, } static int mlxsw_sp_sb_pm_occ_query(struct mlxsw_sp *mlxsw_sp, u8 local_port, - u8 pool, enum mlxsw_reg_sbxx_dir dir, - struct list_head *bulk_list) + u16 pool_index, struct list_head *bulk_list) { + const struct mlxsw_sp_sb_pool_des *des = + &mlxsw_sp_sb_pool_dess[pool_index]; char sbpm_pl[MLXSW_REG_SBPM_LEN]; struct mlxsw_sp_sb_pm *pm; - pm = mlxsw_sp_sb_pm_get(mlxsw_sp, local_port, pool, dir); - mlxsw_reg_sbpm_pack(sbpm_pl, local_port, pool, dir, false, 0, 0); + pm = mlxsw_sp_sb_pm_get(mlxsw_sp, local_port, pool_index); + mlxsw_reg_sbpm_pack(sbpm_pl, local_port, des->pool, des->dir, + false, 0, 0); return mlxsw_reg_trans_query(mlxsw_sp->core, MLXSW_REG(sbpm), sbpm_pl, bulk_list, mlxsw_sp_sb_pm_occ_query_cb, @@ -254,63 +307,54 @@ static void mlxsw_sp_sb_ports_fini(struct mlxsw_sp *mlxsw_sp) .size = _size, \ } -static const struct mlxsw_sp_sb_pr mlxsw_sp_sb_prs_ingress[] = { +static const struct mlxsw_sp_sb_pr mlxsw_sp_sb_prs[] = { + /* Ingress pools. */ MLXSW_SP_SB_PR(MLXSW_REG_SBPR_MODE_DYNAMIC, MLXSW_SP_SB_PR_INGRESS_SIZE), MLXSW_SP_SB_PR(MLXSW_REG_SBPR_MODE_DYNAMIC, 0), MLXSW_SP_SB_PR(MLXSW_REG_SBPR_MODE_DYNAMIC, 0), MLXSW_SP_SB_PR(MLXSW_REG_SBPR_MODE_DYNAMIC, MLXSW_SP_SB_PR_INGRESS_MNG_SIZE), -}; - -#define MLXSW_SP_SB_PRS_INGRESS_LEN ARRAY_SIZE(mlxsw_sp_sb_prs_ingress) - -static const struct mlxsw_sp_sb_pr mlxsw_sp_sb_prs_egress[] = { + /* Egress pools. */ MLXSW_SP_SB_PR(MLXSW_REG_SBPR_MODE_DYNAMIC, MLXSW_SP_SB_PR_EGRESS_SIZE), MLXSW_SP_SB_PR(MLXSW_REG_SBPR_MODE_DYNAMIC, 0), MLXSW_SP_SB_PR(MLXSW_REG_SBPR_MODE_DYNAMIC, 0), MLXSW_SP_SB_PR(MLXSW_REG_SBPR_MODE_DYNAMIC, 0), + MLXSW_SP_SB_PR(MLXSW_REG_SBPR_MODE_STATIC, MLXSW_SP_SB_INFI), }; -#define MLXSW_SP_SB_PRS_EGRESS_LEN ARRAY_SIZE(mlxsw_sp_sb_prs_egress) +#define MLXSW_SP_SB_PRS_LEN ARRAY_SIZE(mlxsw_sp_sb_prs) -static int __mlxsw_sp_sb_prs_init(struct mlxsw_sp *mlxsw_sp, - enum mlxsw_reg_sbxx_dir dir, - const struct mlxsw_sp_sb_pr *prs, - size_t prs_len) +static int mlxsw_sp_sb_prs_init(struct mlxsw_sp *mlxsw_sp, + const struct mlxsw_sp_sb_pr *prs, + size_t prs_len) { int i; int err; for (i = 0; i < prs_len; i++) { - u32 size = mlxsw_sp_bytes_cells(mlxsw_sp, prs[i].size); - - err = mlxsw_sp_sb_pr_write(mlxsw_sp, i, dir, prs[i].mode, size); + u32 size = prs[i].size; + u32 size_cells; + + if (size == MLXSW_SP_SB_INFI) { + err = mlxsw_sp_sb_pr_write(mlxsw_sp, i, prs[i].mode, + 0, true); + } else { + size_cells = mlxsw_sp_bytes_cells(mlxsw_sp, size); + err = mlxsw_sp_sb_pr_write(mlxsw_sp, i, prs[i].mode, + size_cells, false); + } if (err) return err; } return 0; } -static int mlxsw_sp_sb_prs_init(struct mlxsw_sp *mlxsw_sp) -{ - int err; - - err = __mlxsw_sp_sb_prs_init(mlxsw_sp, MLXSW_REG_SBXX_DIR_INGRESS, - mlxsw_sp_sb_prs_ingress, - MLXSW_SP_SB_PRS_INGRESS_LEN); - if (err) - return err; - return __mlxsw_sp_sb_prs_init(mlxsw_sp, MLXSW_REG_SBXX_DIR_EGRESS, - mlxsw_sp_sb_prs_egress, - MLXSW_SP_SB_PRS_EGRESS_LEN); -} - #define MLXSW_SP_SB_CM(_min_buff, _max_buff, _pool) \ { \ .min_buff = _min_buff, \ .max_buff = _max_buff, \ - .pool = _pool, \ + .pool_index = _pool, \ } static const struct mlxsw_sp_sb_cm mlxsw_sp_sb_cms_ingress[] = { @@ -329,38 +373,38 @@ static const struct mlxsw_sp_sb_cm mlxsw_sp_sb_cms_ingress[] = { #define MLXSW_SP_SB_CMS_INGRESS_LEN ARRAY_SIZE(mlxsw_sp_sb_cms_ingress) static const struct mlxsw_sp_sb_cm mlxsw_sp_sb_cms_egress[] = { - MLXSW_SP_SB_CM(1500, 9, 0), - MLXSW_SP_SB_CM(1500, 9, 0), - MLXSW_SP_SB_CM(1500, 9, 0), - MLXSW_SP_SB_CM(1500, 9, 0), - MLXSW_SP_SB_CM(1500, 9, 0), - MLXSW_SP_SB_CM(1500, 9, 0), - MLXSW_SP_SB_CM(1500, 9, 0), - MLXSW_SP_SB_CM(1500, 9, 0), - MLXSW_SP_SB_CM(0, 0, 0), - MLXSW_SP_SB_CM(0, 0, 0), - MLXSW_SP_SB_CM(0, 0, 0), - MLXSW_SP_SB_CM(0, 0, 0), - MLXSW_SP_SB_CM(0, 0, 0), - MLXSW_SP_SB_CM(0, 0, 0), - MLXSW_SP_SB_CM(0, 0, 0), - MLXSW_SP_SB_CM(0, 0, 0), - MLXSW_SP_SB_CM(1, 0xff, 0), + MLXSW_SP_SB_CM(1500, 9, 4), + MLXSW_SP_SB_CM(1500, 9, 4), + MLXSW_SP_SB_CM(1500, 9, 4), + MLXSW_SP_SB_CM(1500, 9, 4), + MLXSW_SP_SB_CM(1500, 9, 4), + MLXSW_SP_SB_CM(1500, 9, 4), + MLXSW_SP_SB_CM(1500, 9, 4), + MLXSW_SP_SB_CM(1500, 9, 4), + MLXSW_SP_SB_CM(0, MLXSW_SP_SB_INFI, 8), + MLXSW_SP_SB_CM(0, MLXSW_SP_SB_INFI, 8), + MLXSW_SP_SB_CM(0, MLXSW_SP_SB_INFI, 8), + MLXSW_SP_SB_CM(0, MLXSW_SP_SB_INFI, 8), + MLXSW_SP_SB_CM(0, MLXSW_SP_SB_INFI, 8), + MLXSW_SP_SB_CM(0, MLXSW_SP_SB_INFI, 8), + MLXSW_SP_SB_CM(0, MLXSW_SP_SB_INFI, 8), + MLXSW_SP_SB_CM(0, MLXSW_SP_SB_INFI, 8), + MLXSW_SP_SB_CM(1, 0xff, 4), }; #define MLXSW_SP_SB_CMS_EGRESS_LEN ARRAY_SIZE(mlxsw_sp_sb_cms_egress) -#define MLXSW_SP_CPU_PORT_SB_CM MLXSW_SP_SB_CM(0, 0, 0) +#define MLXSW_SP_CPU_PORT_SB_CM MLXSW_SP_SB_CM(0, 0, 4) static const struct mlxsw_sp_sb_cm mlxsw_sp_cpu_port_sb_cms[] = { MLXSW_SP_CPU_PORT_SB_CM, - MLXSW_SP_SB_CM(MLXSW_PORT_MAX_MTU, 0, 0), - MLXSW_SP_SB_CM(MLXSW_PORT_MAX_MTU, 0, 0), - MLXSW_SP_SB_CM(MLXSW_PORT_MAX_MTU, 0, 0), - MLXSW_SP_SB_CM(MLXSW_PORT_MAX_MTU, 0, 0), - MLXSW_SP_SB_CM(MLXSW_PORT_MAX_MTU, 0, 0), + MLXSW_SP_SB_CM(MLXSW_PORT_MAX_MTU, 0, 4), + MLXSW_SP_SB_CM(MLXSW_PORT_MAX_MTU, 0, 4), + MLXSW_SP_SB_CM(MLXSW_PORT_MAX_MTU, 0, 4), + MLXSW_SP_SB_CM(MLXSW_PORT_MAX_MTU, 0, 4), + MLXSW_SP_SB_CM(MLXSW_PORT_MAX_MTU, 0, 4), MLXSW_SP_CPU_PORT_SB_CM, - MLXSW_SP_SB_CM(MLXSW_PORT_MAX_MTU, 0, 0), + MLXSW_SP_SB_CM(MLXSW_PORT_MAX_MTU, 0, 4), MLXSW_SP_CPU_PORT_SB_CM, MLXSW_SP_CPU_PORT_SB_CM, MLXSW_SP_CPU_PORT_SB_CM, @@ -390,6 +434,14 @@ static const struct mlxsw_sp_sb_cm mlxsw_sp_cpu_port_sb_cms[] = { #define MLXSW_SP_CPU_PORT_SB_MCS_LEN \ ARRAY_SIZE(mlxsw_sp_cpu_port_sb_cms) +static bool +mlxsw_sp_sb_pool_is_static(struct mlxsw_sp *mlxsw_sp, u16 pool_index) +{ + struct mlxsw_sp_sb_pr *pr = mlxsw_sp_sb_pr_get(mlxsw_sp, pool_index); + + return pr->mode == MLXSW_REG_SBPR_MODE_STATIC; +} + static int __mlxsw_sp_sb_cms_init(struct mlxsw_sp *mlxsw_sp, u8 local_port, enum mlxsw_reg_sbxx_dir dir, const struct mlxsw_sp_sb_cm *cms, @@ -401,16 +453,29 @@ static int __mlxsw_sp_sb_cms_init(struct mlxsw_sp *mlxsw_sp, u8 local_port, for (i = 0; i < cms_len; i++) { const struct mlxsw_sp_sb_cm *cm; u32 min_buff; + u32 max_buff; if (i == 8 && dir == MLXSW_REG_SBXX_DIR_INGRESS) continue; /* PG number 8 does not exist, skip it */ cm = &cms[i]; - /* All pools are initialized using dynamic thresholds, - * therefore 'max_buff' isn't specified in cells. - */ + if (WARN_ON(mlxsw_sp_sb_pool_dess[cm->pool_index].dir != dir)) + continue; + min_buff = mlxsw_sp_bytes_cells(mlxsw_sp, cm->min_buff); - err = mlxsw_sp_sb_cm_write(mlxsw_sp, local_port, i, dir, - min_buff, cm->max_buff, cm->pool); + max_buff = cm->max_buff; + if (max_buff == MLXSW_SP_SB_INFI) { + err = mlxsw_sp_sb_cm_write(mlxsw_sp, local_port, i, + min_buff, 0, + true, cm->pool_index); + } else { + if (mlxsw_sp_sb_pool_is_static(mlxsw_sp, + cm->pool_index)) + max_buff = mlxsw_sp_bytes_cells(mlxsw_sp, + max_buff); + err = mlxsw_sp_sb_cm_write(mlxsw_sp, local_port, i, + min_buff, max_buff, + false, cm->pool_index); + } if (err) return err; } @@ -448,91 +513,74 @@ static int mlxsw_sp_cpu_port_sb_cms_init(struct mlxsw_sp *mlxsw_sp) .max_buff = _max_buff, \ } -static const struct mlxsw_sp_sb_pm mlxsw_sp_sb_pms_ingress[] = { +static const struct mlxsw_sp_sb_pm mlxsw_sp_sb_pms[] = { + /* Ingress pools. */ MLXSW_SP_SB_PM(0, MLXSW_REG_SBXX_DYN_MAX_BUFF_MAX), MLXSW_SP_SB_PM(0, MLXSW_REG_SBXX_DYN_MAX_BUFF_MIN), MLXSW_SP_SB_PM(0, MLXSW_REG_SBXX_DYN_MAX_BUFF_MIN), MLXSW_SP_SB_PM(0, MLXSW_REG_SBXX_DYN_MAX_BUFF_MAX), -}; - -#define MLXSW_SP_SB_PMS_INGRESS_LEN ARRAY_SIZE(mlxsw_sp_sb_pms_ingress) - -static const struct mlxsw_sp_sb_pm mlxsw_sp_sb_pms_egress[] = { + /* Egress pools. */ MLXSW_SP_SB_PM(0, 7), MLXSW_SP_SB_PM(0, MLXSW_REG_SBXX_DYN_MAX_BUFF_MIN), MLXSW_SP_SB_PM(0, MLXSW_REG_SBXX_DYN_MAX_BUFF_MIN), MLXSW_SP_SB_PM(0, MLXSW_REG_SBXX_DYN_MAX_BUFF_MIN), + MLXSW_SP_SB_PM(10000, 90000), }; -#define MLXSW_SP_SB_PMS_EGRESS_LEN ARRAY_SIZE(mlxsw_sp_sb_pms_egress) +#define MLXSW_SP_SB_PMS_LEN ARRAY_SIZE(mlxsw_sp_sb_pms) -static int __mlxsw_sp_port_sb_pms_init(struct mlxsw_sp *mlxsw_sp, u8 local_port, - enum mlxsw_reg_sbxx_dir dir, - const struct mlxsw_sp_sb_pm *pms, - size_t pms_len) +static int mlxsw_sp_port_sb_pms_init(struct mlxsw_sp_port *mlxsw_sp_port) { + struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp; int i; int err; - for (i = 0; i < pms_len; i++) { - const struct mlxsw_sp_sb_pm *pm; + for (i = 0; i < MLXSW_SP_SB_PMS_LEN; i++) { + const struct mlxsw_sp_sb_pm *pm = &mlxsw_sp_sb_pms[i]; + u32 max_buff; + u32 min_buff; - pm = &pms[i]; - err = mlxsw_sp_sb_pm_write(mlxsw_sp, local_port, i, dir, - pm->min_buff, pm->max_buff); + min_buff = mlxsw_sp_bytes_cells(mlxsw_sp, pm->min_buff); + max_buff = pm->max_buff; + if (mlxsw_sp_sb_pool_is_static(mlxsw_sp, i)) + max_buff = mlxsw_sp_bytes_cells(mlxsw_sp, max_buff); + err = mlxsw_sp_sb_pm_write(mlxsw_sp, mlxsw_sp_port->local_port, + i, min_buff, max_buff); if (err) return err; } return 0; } -static int mlxsw_sp_port_sb_pms_init(struct mlxsw_sp_port *mlxsw_sp_port) -{ - int err; - - err = __mlxsw_sp_port_sb_pms_init(mlxsw_sp_port->mlxsw_sp, - mlxsw_sp_port->local_port, - MLXSW_REG_SBXX_DIR_INGRESS, - mlxsw_sp_sb_pms_ingress, - MLXSW_SP_SB_PMS_INGRESS_LEN); - if (err) - return err; - return __mlxsw_sp_port_sb_pms_init(mlxsw_sp_port->mlxsw_sp, - mlxsw_sp_port->local_port, - MLXSW_REG_SBXX_DIR_EGRESS, - mlxsw_sp_sb_pms_egress, - MLXSW_SP_SB_PMS_EGRESS_LEN); -} - struct mlxsw_sp_sb_mm { u32 min_buff; u32 max_buff; - u8 pool; + u16 pool_index; }; #define MLXSW_SP_SB_MM(_min_buff, _max_buff, _pool) \ { \ .min_buff = _min_buff, \ .max_buff = _max_buff, \ - .pool = _pool, \ + .pool_index = _pool, \ } static const struct mlxsw_sp_sb_mm mlxsw_sp_sb_mms[] = { - MLXSW_SP_SB_MM(20000, 0xff, 0), - MLXSW_SP_SB_MM(20000, 0xff, 0), - MLXSW_SP_SB_MM(20000, 0xff, 0), - MLXSW_SP_SB_MM(20000, 0xff, 0), - MLXSW_SP_SB_MM(20000, 0xff, 0), - MLXSW_SP_SB_MM(20000, 0xff, 0), - MLXSW_SP_SB_MM(20000, 0xff, 0), - MLXSW_SP_SB_MM(20000, 0xff, 0), - MLXSW_SP_SB_MM(20000, 0xff, 0), - MLXSW_SP_SB_MM(20000, 0xff, 0), - MLXSW_SP_SB_MM(20000, 0xff, 0), - MLXSW_SP_SB_MM(20000, 0xff, 0), - MLXSW_SP_SB_MM(20000, 0xff, 0), - MLXSW_SP_SB_MM(20000, 0xff, 0), - MLXSW_SP_SB_MM(20000, 0xff, 0), + MLXSW_SP_SB_MM(0, 6, 4), + MLXSW_SP_SB_MM(0, 6, 4), + MLXSW_SP_SB_MM(0, 6, 4), + MLXSW_SP_SB_MM(0, 6, 4), + MLXSW_SP_SB_MM(0, 6, 4), + MLXSW_SP_SB_MM(0, 6, 4), + MLXSW_SP_SB_MM(0, 6, 4), + MLXSW_SP_SB_MM(0, 6, 4), + MLXSW_SP_SB_MM(0, 6, 4), + MLXSW_SP_SB_MM(0, 6, 4), + MLXSW_SP_SB_MM(0, 6, 4), + MLXSW_SP_SB_MM(0, 6, 4), + MLXSW_SP_SB_MM(0, 6, 4), + MLXSW_SP_SB_MM(0, 6, 4), + MLXSW_SP_SB_MM(0, 6, 4), }; #define MLXSW_SP_SB_MMS_LEN ARRAY_SIZE(mlxsw_sp_sb_mms) @@ -544,16 +592,18 @@ static int mlxsw_sp_sb_mms_init(struct mlxsw_sp *mlxsw_sp) int err; for (i = 0; i < MLXSW_SP_SB_MMS_LEN; i++) { + const struct mlxsw_sp_sb_pool_des *des; const struct mlxsw_sp_sb_mm *mc; u32 min_buff; mc = &mlxsw_sp_sb_mms[i]; - /* All pools are initialized using dynamic thresholds, - * therefore 'max_buff' isn't specified in cells. + des = &mlxsw_sp_sb_pool_dess[mc->pool_index]; + /* All pools used by sb_mm's are initialized using dynamic + * thresholds, therefore 'max_buff' isn't specified in cells. */ min_buff = mlxsw_sp_bytes_cells(mlxsw_sp, mc->min_buff); mlxsw_reg_sbmm_pack(sbmm_pl, i, min_buff, mc->max_buff, - mc->pool); + des->pool); err = mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(sbmm), sbmm_pl); if (err) return err; @@ -561,9 +611,24 @@ static int mlxsw_sp_sb_mms_init(struct mlxsw_sp *mlxsw_sp) return 0; } +static void mlxsw_sp_pool_count(u16 *p_ingress_len, u16 *p_egress_len) +{ + int i; + + for (i = 0; i < MLXSW_SP_SB_POOL_DESS_LEN; ++i) + if (mlxsw_sp_sb_pool_dess[i].dir == MLXSW_REG_SBXX_DIR_EGRESS) + goto out; + WARN(1, "No egress pools\n"); + +out: + *p_ingress_len = i; + *p_egress_len = MLXSW_SP_SB_POOL_DESS_LEN - i; +} + int mlxsw_sp_buffers_init(struct mlxsw_sp *mlxsw_sp) { - u64 sb_size; + u16 ing_pool_count; + u16 eg_pool_count; int err; if (!MLXSW_CORE_RES_VALID(mlxsw_sp->core, CELL_SIZE)) @@ -571,17 +636,19 @@ int mlxsw_sp_buffers_init(struct mlxsw_sp *mlxsw_sp) if (!MLXSW_CORE_RES_VALID(mlxsw_sp->core, MAX_BUFFER_SIZE)) return -EIO; - sb_size = MLXSW_CORE_RES_GET(mlxsw_sp->core, MAX_BUFFER_SIZE); mlxsw_sp->sb = kzalloc(sizeof(*mlxsw_sp->sb), GFP_KERNEL); if (!mlxsw_sp->sb) return -ENOMEM; mlxsw_sp->sb->cell_size = MLXSW_CORE_RES_GET(mlxsw_sp->core, CELL_SIZE); + mlxsw_sp->sb->sb_size = MLXSW_CORE_RES_GET(mlxsw_sp->core, + MAX_BUFFER_SIZE); err = mlxsw_sp_sb_ports_init(mlxsw_sp); if (err) goto err_sb_ports_init; - err = mlxsw_sp_sb_prs_init(mlxsw_sp); + err = mlxsw_sp_sb_prs_init(mlxsw_sp, mlxsw_sp_sb_prs, + MLXSW_SP_SB_PRS_LEN); if (err) goto err_sb_prs_init; err = mlxsw_sp_cpu_port_sb_cms_init(mlxsw_sp); @@ -590,11 +657,13 @@ int mlxsw_sp_buffers_init(struct mlxsw_sp *mlxsw_sp) err = mlxsw_sp_sb_mms_init(mlxsw_sp); if (err) goto err_sb_mms_init; - err = devlink_sb_register(priv_to_devlink(mlxsw_sp->core), 0, sb_size, - MLXSW_SP_SB_POOL_COUNT, - MLXSW_SP_SB_POOL_COUNT, - MLXSW_SP_SB_TC_COUNT, - MLXSW_SP_SB_TC_COUNT); + mlxsw_sp_pool_count(&ing_pool_count, &eg_pool_count); + err = devlink_sb_register(priv_to_devlink(mlxsw_sp->core), 0, + mlxsw_sp->sb->sb_size, + ing_pool_count, + eg_pool_count, + MLXSW_SP_SB_ING_TC_COUNT, + MLXSW_SP_SB_EG_TC_COUNT); if (err) goto err_devlink_sb_register; @@ -632,36 +701,15 @@ int mlxsw_sp_port_buffers_init(struct mlxsw_sp_port *mlxsw_sp_port) return err; } -static u8 pool_get(u16 pool_index) -{ - return pool_index % MLXSW_SP_SB_POOL_COUNT; -} - -static u16 pool_index_get(u8 pool, enum mlxsw_reg_sbxx_dir dir) -{ - u16 pool_index; - - pool_index = pool; - if (dir == MLXSW_REG_SBXX_DIR_EGRESS) - pool_index += MLXSW_SP_SB_POOL_COUNT; - return pool_index; -} - -static enum mlxsw_reg_sbxx_dir dir_get(u16 pool_index) -{ - return pool_index < MLXSW_SP_SB_POOL_COUNT ? - MLXSW_REG_SBXX_DIR_INGRESS : MLXSW_REG_SBXX_DIR_EGRESS; -} - int mlxsw_sp_sb_pool_get(struct mlxsw_core *mlxsw_core, unsigned int sb_index, u16 pool_index, struct devlink_sb_pool_info *pool_info) { + enum mlxsw_reg_sbxx_dir dir = mlxsw_sp_sb_pool_dess[pool_index].dir; struct mlxsw_sp *mlxsw_sp = mlxsw_core_driver_priv(mlxsw_core); - u8 pool = pool_get(pool_index); - enum mlxsw_reg_sbxx_dir dir = dir_get(pool_index); - struct mlxsw_sp_sb_pr *pr = mlxsw_sp_sb_pr_get(mlxsw_sp, pool, dir); + struct mlxsw_sp_sb_pr *pr; + pr = mlxsw_sp_sb_pr_get(mlxsw_sp, pool_index); pool_info->pool_type = (enum devlink_sb_pool_type) dir; pool_info->size = mlxsw_sp_cells_bytes(mlxsw_sp, pr->size); pool_info->threshold_type = (enum devlink_sb_threshold_type) pr->mode; @@ -674,34 +722,32 @@ int mlxsw_sp_sb_pool_set(struct mlxsw_core *mlxsw_core, { struct mlxsw_sp *mlxsw_sp = mlxsw_core_driver_priv(mlxsw_core); u32 pool_size = mlxsw_sp_bytes_cells(mlxsw_sp, size); - u8 pool = pool_get(pool_index); - enum mlxsw_reg_sbxx_dir dir = dir_get(pool_index); enum mlxsw_reg_sbpr_mode mode; if (size > MLXSW_CORE_RES_GET(mlxsw_sp->core, MAX_BUFFER_SIZE)) return -EINVAL; mode = (enum mlxsw_reg_sbpr_mode) threshold_type; - return mlxsw_sp_sb_pr_write(mlxsw_sp, pool, dir, mode, pool_size); + return mlxsw_sp_sb_pr_write(mlxsw_sp, pool_index, mode, + pool_size, false); } #define MLXSW_SP_SB_THRESHOLD_TO_ALPHA_OFFSET (-2) /* 3->1, 16->14 */ -static u32 mlxsw_sp_sb_threshold_out(struct mlxsw_sp *mlxsw_sp, u8 pool, - enum mlxsw_reg_sbxx_dir dir, u32 max_buff) +static u32 mlxsw_sp_sb_threshold_out(struct mlxsw_sp *mlxsw_sp, u16 pool_index, + u32 max_buff) { - struct mlxsw_sp_sb_pr *pr = mlxsw_sp_sb_pr_get(mlxsw_sp, pool, dir); + struct mlxsw_sp_sb_pr *pr = mlxsw_sp_sb_pr_get(mlxsw_sp, pool_index); if (pr->mode == MLXSW_REG_SBPR_MODE_DYNAMIC) return max_buff - MLXSW_SP_SB_THRESHOLD_TO_ALPHA_OFFSET; return mlxsw_sp_cells_bytes(mlxsw_sp, max_buff); } -static int mlxsw_sp_sb_threshold_in(struct mlxsw_sp *mlxsw_sp, u8 pool, - enum mlxsw_reg_sbxx_dir dir, u32 threshold, - u32 *p_max_buff) +static int mlxsw_sp_sb_threshold_in(struct mlxsw_sp *mlxsw_sp, u16 pool_index, + u32 threshold, u32 *p_max_buff) { - struct mlxsw_sp_sb_pr *pr = mlxsw_sp_sb_pr_get(mlxsw_sp, pool, dir); + struct mlxsw_sp_sb_pr *pr = mlxsw_sp_sb_pr_get(mlxsw_sp, pool_index); if (pr->mode == MLXSW_REG_SBPR_MODE_DYNAMIC) { int val; @@ -725,12 +771,10 @@ int mlxsw_sp_sb_port_pool_get(struct mlxsw_core_port *mlxsw_core_port, mlxsw_core_port_driver_priv(mlxsw_core_port); struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp; u8 local_port = mlxsw_sp_port->local_port; - u8 pool = pool_get(pool_index); - enum mlxsw_reg_sbxx_dir dir = dir_get(pool_index); struct mlxsw_sp_sb_pm *pm = mlxsw_sp_sb_pm_get(mlxsw_sp, local_port, - pool, dir); + pool_index); - *p_threshold = mlxsw_sp_sb_threshold_out(mlxsw_sp, pool, dir, + *p_threshold = mlxsw_sp_sb_threshold_out(mlxsw_sp, pool_index, pm->max_buff); return 0; } @@ -743,17 +787,15 @@ int mlxsw_sp_sb_port_pool_set(struct mlxsw_core_port *mlxsw_core_port, mlxsw_core_port_driver_priv(mlxsw_core_port); struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp; u8 local_port = mlxsw_sp_port->local_port; - u8 pool = pool_get(pool_index); - enum mlxsw_reg_sbxx_dir dir = dir_get(pool_index); u32 max_buff; int err; - err = mlxsw_sp_sb_threshold_in(mlxsw_sp, pool, dir, + err = mlxsw_sp_sb_threshold_in(mlxsw_sp, pool_index, threshold, &max_buff); if (err) return err; - return mlxsw_sp_sb_pm_write(mlxsw_sp, local_port, pool, dir, + return mlxsw_sp_sb_pm_write(mlxsw_sp, local_port, pool_index, 0, max_buff); } @@ -771,9 +813,9 @@ int mlxsw_sp_sb_tc_pool_bind_get(struct mlxsw_core_port *mlxsw_core_port, struct mlxsw_sp_sb_cm *cm = mlxsw_sp_sb_cm_get(mlxsw_sp, local_port, pg_buff, dir); - *p_threshold = mlxsw_sp_sb_threshold_out(mlxsw_sp, cm->pool, dir, + *p_threshold = mlxsw_sp_sb_threshold_out(mlxsw_sp, cm->pool_index, cm->max_buff); - *p_pool_index = pool_index_get(cm->pool, dir); + *p_pool_index = cm->pool_index; return 0; } @@ -788,24 +830,24 @@ int mlxsw_sp_sb_tc_pool_bind_set(struct mlxsw_core_port *mlxsw_core_port, u8 local_port = mlxsw_sp_port->local_port; u8 pg_buff = tc_index; enum mlxsw_reg_sbxx_dir dir = (enum mlxsw_reg_sbxx_dir) pool_type; - u8 pool = pool_get(pool_index); u32 max_buff; int err; - if (dir != dir_get(pool_index)) + if (dir != mlxsw_sp_sb_pool_dess[pool_index].dir) return -EINVAL; - err = mlxsw_sp_sb_threshold_in(mlxsw_sp, pool, dir, + err = mlxsw_sp_sb_threshold_in(mlxsw_sp, pool_index, threshold, &max_buff); if (err) return err; - return mlxsw_sp_sb_cm_write(mlxsw_sp, local_port, pg_buff, dir, - 0, max_buff, pool); + return mlxsw_sp_sb_cm_write(mlxsw_sp, local_port, pg_buff, + 0, max_buff, false, pool_index); } #define MASKED_COUNT_MAX \ - (MLXSW_REG_SBSR_REC_MAX_COUNT / (MLXSW_SP_SB_TC_COUNT * 2)) + (MLXSW_REG_SBSR_REC_MAX_COUNT / \ + (MLXSW_SP_SB_ING_TC_COUNT + MLXSW_SP_SB_EG_TC_COUNT)) struct mlxsw_sp_sb_sr_occ_query_cb_ctx { u8 masked_count; @@ -831,7 +873,7 @@ static void mlxsw_sp_sb_sr_occ_query_cb(struct mlxsw_core *mlxsw_core, local_port < mlxsw_core_max_ports(mlxsw_core); local_port++) { if (!mlxsw_sp->ports[local_port]) continue; - for (i = 0; i < MLXSW_SP_SB_TC_COUNT; i++) { + for (i = 0; i < MLXSW_SP_SB_ING_TC_COUNT; i++) { cm = mlxsw_sp_sb_cm_get(mlxsw_sp, local_port, i, MLXSW_REG_SBXX_DIR_INGRESS); mlxsw_reg_sbsr_rec_unpack(sbsr_pl, rec_index++, @@ -845,7 +887,7 @@ static void mlxsw_sp_sb_sr_occ_query_cb(struct mlxsw_core *mlxsw_core, local_port < mlxsw_core_max_ports(mlxsw_core); local_port++) { if (!mlxsw_sp->ports[local_port]) continue; - for (i = 0; i < MLXSW_SP_SB_TC_COUNT; i++) { + for (i = 0; i < MLXSW_SP_SB_EG_TC_COUNT; i++) { cm = mlxsw_sp_sb_cm_get(mlxsw_sp, local_port, i, MLXSW_REG_SBXX_DIR_EGRESS); mlxsw_reg_sbsr_rec_unpack(sbsr_pl, rec_index++, @@ -880,23 +922,17 @@ next_batch: local_port_1 = local_port; masked_count = 0; mlxsw_reg_sbsr_pack(sbsr_pl, false); - for (i = 0; i < MLXSW_SP_SB_TC_COUNT; i++) { + for (i = 0; i < MLXSW_SP_SB_ING_TC_COUNT; i++) mlxsw_reg_sbsr_pg_buff_mask_set(sbsr_pl, i, 1); + for (i = 0; i < MLXSW_SP_SB_EG_TC_COUNT; i++) mlxsw_reg_sbsr_tclass_mask_set(sbsr_pl, i, 1); - } for (; local_port < mlxsw_core_max_ports(mlxsw_core); local_port++) { if (!mlxsw_sp->ports[local_port]) continue; mlxsw_reg_sbsr_ingress_port_mask_set(sbsr_pl, local_port, 1); mlxsw_reg_sbsr_egress_port_mask_set(sbsr_pl, local_port, 1); - for (i = 0; i < MLXSW_SP_SB_POOL_COUNT; i++) { - err = mlxsw_sp_sb_pm_occ_query(mlxsw_sp, local_port, i, - MLXSW_REG_SBXX_DIR_INGRESS, - &bulk_list); - if (err) - goto out; + for (i = 0; i < MLXSW_SP_SB_POOL_DESS_LEN; i++) { err = mlxsw_sp_sb_pm_occ_query(mlxsw_sp, local_port, i, - MLXSW_REG_SBXX_DIR_EGRESS, &bulk_list); if (err) goto out; @@ -945,23 +981,17 @@ next_batch: local_port++; masked_count = 0; mlxsw_reg_sbsr_pack(sbsr_pl, true); - for (i = 0; i < MLXSW_SP_SB_TC_COUNT; i++) { + for (i = 0; i < MLXSW_SP_SB_ING_TC_COUNT; i++) mlxsw_reg_sbsr_pg_buff_mask_set(sbsr_pl, i, 1); + for (i = 0; i < MLXSW_SP_SB_EG_TC_COUNT; i++) mlxsw_reg_sbsr_tclass_mask_set(sbsr_pl, i, 1); - } for (; local_port < mlxsw_core_max_ports(mlxsw_core); local_port++) { if (!mlxsw_sp->ports[local_port]) continue; mlxsw_reg_sbsr_ingress_port_mask_set(sbsr_pl, local_port, 1); mlxsw_reg_sbsr_egress_port_mask_set(sbsr_pl, local_port, 1); - for (i = 0; i < MLXSW_SP_SB_POOL_COUNT; i++) { - err = mlxsw_sp_sb_pm_occ_clear(mlxsw_sp, local_port, i, - MLXSW_REG_SBXX_DIR_INGRESS, - &bulk_list); - if (err) - goto out; + for (i = 0; i < MLXSW_SP_SB_POOL_DESS_LEN; i++) { err = mlxsw_sp_sb_pm_occ_clear(mlxsw_sp, local_port, i, - MLXSW_REG_SBXX_DIR_EGRESS, &bulk_list); if (err) goto out; @@ -994,10 +1024,8 @@ int mlxsw_sp_sb_occ_port_pool_get(struct mlxsw_core_port *mlxsw_core_port, mlxsw_core_port_driver_priv(mlxsw_core_port); struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp; u8 local_port = mlxsw_sp_port->local_port; - u8 pool = pool_get(pool_index); - enum mlxsw_reg_sbxx_dir dir = dir_get(pool_index); struct mlxsw_sp_sb_pm *pm = mlxsw_sp_sb_pm_get(mlxsw_sp, local_port, - pool, dir); + pool_index); *p_cur = mlxsw_sp_cells_bytes(mlxsw_sp, pm->occ.cur); *p_max = mlxsw_sp_cells_bytes(mlxsw_sp, pm->occ.max); diff --git a/drivers/net/ethernet/micrel/ks8695net.c b/drivers/net/ethernet/micrel/ks8695net.c index bd51e057e915..b881f5d4a7f9 100644 --- a/drivers/net/ethernet/micrel/ks8695net.c +++ b/drivers/net/ethernet/micrel/ks8695net.c @@ -1164,7 +1164,7 @@ ks8695_timeout(struct net_device *ndev) * sk_buff and adds it to the TX ring. It then kicks the TX DMA * engine to ensure transmission begins. */ -static int +static netdev_tx_t ks8695_start_xmit(struct sk_buff *skb, struct net_device *ndev) { struct ks8695_priv *ksp = netdev_priv(ndev); diff --git a/drivers/net/ethernet/micrel/ks8851_mll.c b/drivers/net/ethernet/micrel/ks8851_mll.c index 0e9719fbc624..35f8c9ef204d 100644 --- a/drivers/net/ethernet/micrel/ks8851_mll.c +++ b/drivers/net/ethernet/micrel/ks8851_mll.c @@ -1021,9 +1021,9 @@ static void ks_write_qmu(struct ks_net *ks, u8 *pdata, u16 len) * spin_lock_irqsave is required because tx and rx should be mutual exclusive. * So while tx is in-progress, prevent IRQ interrupt from happenning. */ -static int ks_start_xmit(struct sk_buff *skb, struct net_device *netdev) +static netdev_tx_t ks_start_xmit(struct sk_buff *skb, struct net_device *netdev) { - int retv = NETDEV_TX_OK; + netdev_tx_t retv = NETDEV_TX_OK; struct ks_net *ks = netdev_priv(netdev); disable_irq(netdev->irq); diff --git a/drivers/net/ethernet/microchip/lan743x_main.c b/drivers/net/ethernet/microchip/lan743x_main.c index e7dce79ff2c9..867cddba840f 100644 --- a/drivers/net/ethernet/microchip/lan743x_main.c +++ b/drivers/net/ethernet/microchip/lan743x_main.c @@ -999,7 +999,6 @@ static int lan743x_phy_open(struct lan743x_adapter *adapter) struct phy_device *phydev; struct net_device *netdev; int ret = -EIO; - u32 mii_adv; netdev = adapter->netdev; phydev = phy_find_first(adapter->mdiobus); @@ -1013,13 +1012,11 @@ static int lan743x_phy_open(struct lan743x_adapter *adapter) goto return_error; /* MAC doesn't support 1000T Half */ - phydev->supported &= ~SUPPORTED_1000baseT_Half; + phy_remove_link_mode(phydev, ETHTOOL_LINK_MODE_1000baseT_Half_BIT); /* support both flow controls */ + phy_support_asym_pause(phydev); phy->fc_request_control = (FLOW_CTRL_RX | FLOW_CTRL_TX); - phydev->advertising &= ~(ADVERTISED_Pause | ADVERTISED_Asym_Pause); - mii_adv = (u32)mii_advertise_flowctrl(phy->fc_request_control); - phydev->advertising |= mii_adv_to_ethtool_adv_t(mii_adv); phy->fc_autoneg = phydev->autoneg; phy_start(phydev); @@ -2850,7 +2847,7 @@ static void lan743x_pcidev_shutdown(struct pci_dev *pdev) lan743x_hardware_cleanup(adapter); } -#ifdef CONFIG_PM +#ifdef CONFIG_PM_SLEEP static u16 lan743x_pm_wakeframe_crc16(const u8 *buf, int len) { return bitrev16(crc16(0xFFFF, buf, len)); @@ -3016,7 +3013,7 @@ static int lan743x_pm_resume(struct device *dev) static const struct dev_pm_ops lan743x_pm_ops = { SET_SYSTEM_SLEEP_PM_OPS(lan743x_pm_suspend, lan743x_pm_resume) }; -#endif /*CONFIG_PM */ +#endif /* CONFIG_PM_SLEEP */ static const struct pci_device_id lan743x_pcidev_tbl[] = { { PCI_DEVICE(PCI_VENDOR_ID_SMSC, PCI_DEVICE_ID_SMSC_LAN7430) }, @@ -3028,7 +3025,7 @@ static struct pci_driver lan743x_pcidev_driver = { .id_table = lan743x_pcidev_tbl, .probe = lan743x_pcidev_probe, .remove = lan743x_pcidev_remove, -#ifdef CONFIG_PM +#ifdef CONFIG_PM_SLEEP .driver.pm = &lan743x_pm_ops, #endif .shutdown = lan743x_pcidev_shutdown, diff --git a/drivers/net/ethernet/mscc/ocelot_board.c b/drivers/net/ethernet/mscc/ocelot_board.c index 26bb3b18f3be..3cdf63e35b53 100644 --- a/drivers/net/ethernet/mscc/ocelot_board.c +++ b/drivers/net/ethernet/mscc/ocelot_board.c @@ -91,7 +91,7 @@ static irqreturn_t ocelot_xtr_irq_handler(int irq, void *arg) struct sk_buff *skb; struct net_device *dev; u32 *buf; - int sz, len; + int sz, len, buf_len; u32 ifh[4]; u32 val; struct frame_info info; @@ -116,14 +116,20 @@ static irqreturn_t ocelot_xtr_irq_handler(int irq, void *arg) err = -ENOMEM; break; } - buf = (u32 *)skb_put(skb, info.len); + buf_len = info.len - ETH_FCS_LEN; + buf = (u32 *)skb_put(skb, buf_len); len = 0; do { sz = ocelot_rx_frame_word(ocelot, grp, false, &val); *buf++ = val; len += sz; - } while ((sz == 4) && (len < info.len)); + } while (len < buf_len); + + /* Read the FCS and discard it */ + sz = ocelot_rx_frame_word(ocelot, grp, false, &val); + /* Update the statistics if part of the FCS was read before */ + len -= ETH_FCS_LEN - sz; if (sz < 0) { err = sz; diff --git a/drivers/net/ethernet/mscc/ocelot_dev_gmii.h b/drivers/net/ethernet/mscc/ocelot_dev_gmii.h deleted file mode 100644 index 6aa40ea223a2..000000000000 --- a/drivers/net/ethernet/mscc/ocelot_dev_gmii.h +++ /dev/null @@ -1,154 +0,0 @@ -/* SPDX-License-Identifier: (GPL-2.0 OR MIT) */ -/* - * Microsemi Ocelot Switch driver - * - * Copyright (c) 2017 Microsemi Corporation - */ - -#ifndef _MSCC_OCELOT_DEV_GMII_H_ -#define _MSCC_OCELOT_DEV_GMII_H_ - -#define DEV_GMII_PORT_MODE_CLOCK_CFG 0x0 - -#define DEV_GMII_PORT_MODE_CLOCK_CFG_MAC_TX_RST BIT(5) -#define DEV_GMII_PORT_MODE_CLOCK_CFG_MAC_RX_RST BIT(4) -#define DEV_GMII_PORT_MODE_CLOCK_CFG_PORT_RST BIT(3) -#define DEV_GMII_PORT_MODE_CLOCK_CFG_PHY_RST BIT(2) -#define DEV_GMII_PORT_MODE_CLOCK_CFG_LINK_SPEED(x) ((x) & GENMASK(1, 0)) -#define DEV_GMII_PORT_MODE_CLOCK_CFG_LINK_SPEED_M GENMASK(1, 0) - -#define DEV_GMII_PORT_MODE_PORT_MISC 0x4 - -#define DEV_GMII_PORT_MODE_PORT_MISC_MPLS_RX_ENA BIT(5) -#define DEV_GMII_PORT_MODE_PORT_MISC_FWD_ERROR_ENA BIT(4) -#define DEV_GMII_PORT_MODE_PORT_MISC_FWD_PAUSE_ENA BIT(3) -#define DEV_GMII_PORT_MODE_PORT_MISC_FWD_CTRL_ENA BIT(2) -#define DEV_GMII_PORT_MODE_PORT_MISC_GMII_LOOP_ENA BIT(1) -#define DEV_GMII_PORT_MODE_PORT_MISC_DEV_LOOP_ENA BIT(0) - -#define DEV_GMII_PORT_MODE_EVENTS 0x8 - -#define DEV_GMII_PORT_MODE_EEE_CFG 0xc - -#define DEV_GMII_PORT_MODE_EEE_CFG_EEE_ENA BIT(22) -#define DEV_GMII_PORT_MODE_EEE_CFG_EEE_TIMER_AGE(x) (((x) << 15) & GENMASK(21, 15)) -#define DEV_GMII_PORT_MODE_EEE_CFG_EEE_TIMER_AGE_M GENMASK(21, 15) -#define DEV_GMII_PORT_MODE_EEE_CFG_EEE_TIMER_AGE_X(x) (((x) & GENMASK(21, 15)) >> 15) -#define DEV_GMII_PORT_MODE_EEE_CFG_EEE_TIMER_WAKEUP(x) (((x) << 8) & GENMASK(14, 8)) -#define DEV_GMII_PORT_MODE_EEE_CFG_EEE_TIMER_WAKEUP_M GENMASK(14, 8) -#define DEV_GMII_PORT_MODE_EEE_CFG_EEE_TIMER_WAKEUP_X(x) (((x) & GENMASK(14, 8)) >> 8) -#define DEV_GMII_PORT_MODE_EEE_CFG_EEE_TIMER_HOLDOFF(x) (((x) << 1) & GENMASK(7, 1)) -#define DEV_GMII_PORT_MODE_EEE_CFG_EEE_TIMER_HOLDOFF_M GENMASK(7, 1) -#define DEV_GMII_PORT_MODE_EEE_CFG_EEE_TIMER_HOLDOFF_X(x) (((x) & GENMASK(7, 1)) >> 1) -#define DEV_GMII_PORT_MODE_EEE_CFG_PORT_LPI BIT(0) - -#define DEV_GMII_PORT_MODE_RX_PATH_DELAY 0x10 - -#define DEV_GMII_PORT_MODE_TX_PATH_DELAY 0x14 - -#define DEV_GMII_PORT_MODE_PTP_PREDICT_CFG 0x18 - -#define DEV_GMII_MAC_CFG_STATUS_MAC_ENA_CFG 0x1c - -#define DEV_GMII_MAC_CFG_STATUS_MAC_ENA_CFG_RX_ENA BIT(4) -#define DEV_GMII_MAC_CFG_STATUS_MAC_ENA_CFG_TX_ENA BIT(0) - -#define DEV_GMII_MAC_CFG_STATUS_MAC_MODE_CFG 0x20 - -#define DEV_GMII_MAC_CFG_STATUS_MAC_MODE_CFG_FC_WORD_SYNC_ENA BIT(8) -#define DEV_GMII_MAC_CFG_STATUS_MAC_MODE_CFG_GIGA_MODE_ENA BIT(4) -#define DEV_GMII_MAC_CFG_STATUS_MAC_MODE_CFG_FDX_ENA BIT(0) - -#define DEV_GMII_MAC_CFG_STATUS_MAC_MAXLEN_CFG 0x24 - -#define DEV_GMII_MAC_CFG_STATUS_MAC_TAGS_CFG 0x28 - -#define DEV_GMII_MAC_CFG_STATUS_MAC_TAGS_CFG_TAG_ID(x) (((x) << 16) & GENMASK(31, 16)) -#define DEV_GMII_MAC_CFG_STATUS_MAC_TAGS_CFG_TAG_ID_M GENMASK(31, 16) -#define DEV_GMII_MAC_CFG_STATUS_MAC_TAGS_CFG_TAG_ID_X(x) (((x) & GENMASK(31, 16)) >> 16) -#define DEV_GMII_MAC_CFG_STATUS_MAC_TAGS_CFG_PB_ENA BIT(1) -#define DEV_GMII_MAC_CFG_STATUS_MAC_TAGS_CFG_VLAN_AWR_ENA BIT(0) -#define DEV_GMII_MAC_CFG_STATUS_MAC_TAGS_CFG_VLAN_LEN_AWR_ENA BIT(2) - -#define DEV_GMII_MAC_CFG_STATUS_MAC_ADV_CHK_CFG 0x2c - -#define DEV_GMII_MAC_CFG_STATUS_MAC_ADV_CHK_CFG_LEN_DROP_ENA BIT(0) - -#define DEV_GMII_MAC_CFG_STATUS_MAC_IFG_CFG 0x30 - -#define DEV_GMII_MAC_CFG_STATUS_MAC_IFG_CFG_RESTORE_OLD_IPG_CHECK BIT(17) -#define DEV_GMII_MAC_CFG_STATUS_MAC_IFG_CFG_REDUCED_TX_IFG BIT(16) -#define DEV_GMII_MAC_CFG_STATUS_MAC_IFG_CFG_TX_IFG(x) (((x) << 8) & GENMASK(12, 8)) -#define DEV_GMII_MAC_CFG_STATUS_MAC_IFG_CFG_TX_IFG_M GENMASK(12, 8) -#define DEV_GMII_MAC_CFG_STATUS_MAC_IFG_CFG_TX_IFG_X(x) (((x) & GENMASK(12, 8)) >> 8) -#define DEV_GMII_MAC_CFG_STATUS_MAC_IFG_CFG_RX_IFG2(x) (((x) << 4) & GENMASK(7, 4)) -#define DEV_GMII_MAC_CFG_STATUS_MAC_IFG_CFG_RX_IFG2_M GENMASK(7, 4) -#define DEV_GMII_MAC_CFG_STATUS_MAC_IFG_CFG_RX_IFG2_X(x) (((x) & GENMASK(7, 4)) >> 4) -#define DEV_GMII_MAC_CFG_STATUS_MAC_IFG_CFG_RX_IFG1(x) ((x) & GENMASK(3, 0)) -#define DEV_GMII_MAC_CFG_STATUS_MAC_IFG_CFG_RX_IFG1_M GENMASK(3, 0) - -#define DEV_GMII_MAC_CFG_STATUS_MAC_HDX_CFG 0x34 - -#define DEV_GMII_MAC_CFG_STATUS_MAC_HDX_CFG_BYPASS_COL_SYNC BIT(26) -#define DEV_GMII_MAC_CFG_STATUS_MAC_HDX_CFG_OB_ENA BIT(25) -#define DEV_GMII_MAC_CFG_STATUS_MAC_HDX_CFG_WEXC_DIS BIT(24) -#define DEV_GMII_MAC_CFG_STATUS_MAC_HDX_CFG_SEED(x) (((x) << 16) & GENMASK(23, 16)) -#define DEV_GMII_MAC_CFG_STATUS_MAC_HDX_CFG_SEED_M GENMASK(23, 16) -#define DEV_GMII_MAC_CFG_STATUS_MAC_HDX_CFG_SEED_X(x) (((x) & GENMASK(23, 16)) >> 16) -#define DEV_GMII_MAC_CFG_STATUS_MAC_HDX_CFG_SEED_LOAD BIT(12) -#define DEV_GMII_MAC_CFG_STATUS_MAC_HDX_CFG_RETRY_AFTER_EXC_COL_ENA BIT(8) -#define DEV_GMII_MAC_CFG_STATUS_MAC_HDX_CFG_LATE_COL_POS(x) ((x) & GENMASK(6, 0)) -#define DEV_GMII_MAC_CFG_STATUS_MAC_HDX_CFG_LATE_COL_POS_M GENMASK(6, 0) - -#define DEV_GMII_MAC_CFG_STATUS_MAC_DBG_CFG 0x38 - -#define DEV_GMII_MAC_CFG_STATUS_MAC_DBG_CFG_TBI_MODE BIT(4) -#define DEV_GMII_MAC_CFG_STATUS_MAC_DBG_CFG_IFG_CRS_EXT_CHK_ENA BIT(0) - -#define DEV_GMII_MAC_CFG_STATUS_MAC_FC_MAC_LOW_CFG 0x3c - -#define DEV_GMII_MAC_CFG_STATUS_MAC_FC_MAC_HIGH_CFG 0x40 - -#define DEV_GMII_MAC_CFG_STATUS_MAC_STICKY 0x44 - -#define DEV_GMII_MAC_CFG_STATUS_MAC_STICKY_RX_IPG_SHRINK_STICKY BIT(9) -#define DEV_GMII_MAC_CFG_STATUS_MAC_STICKY_RX_PREAM_SHRINK_STICKY BIT(8) -#define DEV_GMII_MAC_CFG_STATUS_MAC_STICKY_RX_CARRIER_EXT_STICKY BIT(7) -#define DEV_GMII_MAC_CFG_STATUS_MAC_STICKY_RX_CARRIER_EXT_ERR_STICKY BIT(6) -#define DEV_GMII_MAC_CFG_STATUS_MAC_STICKY_RX_JUNK_STICKY BIT(5) -#define DEV_GMII_MAC_CFG_STATUS_MAC_STICKY_TX_RETRANSMIT_STICKY BIT(4) -#define DEV_GMII_MAC_CFG_STATUS_MAC_STICKY_TX_JAM_STICKY BIT(3) -#define DEV_GMII_MAC_CFG_STATUS_MAC_STICKY_TX_FIFO_OFLW_STICKY BIT(2) -#define DEV_GMII_MAC_CFG_STATUS_MAC_STICKY_TX_FRM_LEN_OVR_STICKY BIT(1) -#define DEV_GMII_MAC_CFG_STATUS_MAC_STICKY_TX_ABORT_STICKY BIT(0) - -#define DEV_GMII_MM_CONFIG_ENABLE_CONFIG 0x48 - -#define DEV_GMII_MM_CONFIG_ENABLE_CONFIG_MM_RX_ENA BIT(0) -#define DEV_GMII_MM_CONFIG_ENABLE_CONFIG_MM_TX_ENA BIT(4) -#define DEV_GMII_MM_CONFIG_ENABLE_CONFIG_KEEP_S_AFTER_D BIT(8) - -#define DEV_GMII_MM_CONFIG_VERIF_CONFIG 0x4c - -#define DEV_GMII_MM_CONFIG_VERIF_CONFIG_PRM_VERIFY_DIS BIT(0) -#define DEV_GMII_MM_CONFIG_VERIF_CONFIG_PRM_VERIFY_TIME(x) (((x) << 4) & GENMASK(11, 4)) -#define DEV_GMII_MM_CONFIG_VERIF_CONFIG_PRM_VERIFY_TIME_M GENMASK(11, 4) -#define DEV_GMII_MM_CONFIG_VERIF_CONFIG_PRM_VERIFY_TIME_X(x) (((x) & GENMASK(11, 4)) >> 4) -#define DEV_GMII_MM_CONFIG_VERIF_CONFIG_VERIF_TIMER_UNITS(x) (((x) << 12) & GENMASK(13, 12)) -#define DEV_GMII_MM_CONFIG_VERIF_CONFIG_VERIF_TIMER_UNITS_M GENMASK(13, 12) -#define DEV_GMII_MM_CONFIG_VERIF_CONFIG_VERIF_TIMER_UNITS_X(x) (((x) & GENMASK(13, 12)) >> 12) - -#define DEV_GMII_MM_STATISTICS_MM_STATUS 0x50 - -#define DEV_GMII_MM_STATISTICS_MM_STATUS_PRMPT_ACTIVE_STATUS BIT(0) -#define DEV_GMII_MM_STATISTICS_MM_STATUS_PRMPT_ACTIVE_STICKY BIT(4) -#define DEV_GMII_MM_STATISTICS_MM_STATUS_PRMPT_VERIFY_STATE(x) (((x) << 8) & GENMASK(10, 8)) -#define DEV_GMII_MM_STATISTICS_MM_STATUS_PRMPT_VERIFY_STATE_M GENMASK(10, 8) -#define DEV_GMII_MM_STATISTICS_MM_STATUS_PRMPT_VERIFY_STATE_X(x) (((x) & GENMASK(10, 8)) >> 8) -#define DEV_GMII_MM_STATISTICS_MM_STATUS_UNEXP_RX_PFRM_STICKY BIT(12) -#define DEV_GMII_MM_STATISTICS_MM_STATUS_UNEXP_TX_PFRM_STICKY BIT(16) -#define DEV_GMII_MM_STATISTICS_MM_STATUS_MM_RX_FRAME_STATUS BIT(20) -#define DEV_GMII_MM_STATISTICS_MM_STATUS_MM_TX_FRAME_STATUS BIT(24) -#define DEV_GMII_MM_STATISTICS_MM_STATUS_MM_TX_PRMPT_STATUS BIT(28) - -#endif diff --git a/drivers/net/ethernet/neterion/s2io.c b/drivers/net/ethernet/neterion/s2io.c index b8983e73265a..82be90075695 100644 --- a/drivers/net/ethernet/neterion/s2io.c +++ b/drivers/net/ethernet/neterion/s2io.c @@ -75,6 +75,7 @@ #include <linux/tcp.h> #include <linux/uaccess.h> #include <linux/io.h> +#include <linux/io-64-nonatomic-lo-hi.h> #include <linux/slab.h> #include <linux/prefetch.h> #include <net/tcp.h> @@ -491,7 +492,7 @@ static struct pci_driver s2io_driver = { }; /* A simplifier macro used both by init and free shared_mem Fns(). */ -#define TXD_MEM_PAGE_CNT(len, per_each) ((len+per_each - 1) / per_each) +#define TXD_MEM_PAGE_CNT(len, per_each) DIV_ROUND_UP(len, per_each) /* netqueue manipulation helper functions */ static inline void s2io_stop_all_tx_queue(struct s2io_nic *sp) @@ -3679,11 +3680,9 @@ static void restore_xmsi_data(struct s2io_nic *nic) writeq(nic->msix_info[i].data, &bar0->xmsi_data); val64 = (s2BIT(7) | s2BIT(15) | vBIT(msix_index, 26, 6)); writeq(val64, &bar0->xmsi_access); - if (wait_for_msix_trans(nic, msix_index)) { + if (wait_for_msix_trans(nic, msix_index)) DBG_PRINT(ERR_DBG, "%s: index: %d failed\n", __func__, msix_index); - continue; - } } } diff --git a/drivers/net/ethernet/neterion/s2io.h b/drivers/net/ethernet/neterion/s2io.h index 1a24a7218794..0a921f30f98f 100644 --- a/drivers/net/ethernet/neterion/s2io.h +++ b/drivers/net/ethernet/neterion/s2io.h @@ -10,6 +10,7 @@ * system is licensed under the GPL. * See the file COPYING in this distribution for more information. ************************************************************************/ +#include <linux/io-64-nonatomic-lo-hi.h> #ifndef _S2IO_H #define _S2IO_H @@ -970,27 +971,6 @@ struct s2io_nic { #define RESET_ERROR 1 #define CMD_ERROR 2 -/* OS related system calls */ -#ifndef readq -static inline u64 readq(void __iomem *addr) -{ - u64 ret = 0; - ret = readl(addr + 4); - ret <<= 32; - ret |= readl(addr); - - return ret; -} -#endif - -#ifndef writeq -static inline void writeq(u64 val, void __iomem *addr) -{ - writel((u32) (val), addr); - writel((u32) (val >> 32), (addr + 4)); -} -#endif - /* * Some registers have to be written in a particular order to * expect correct hardware operation. The macro SPECIAL_REG_WRITE diff --git a/drivers/net/ethernet/neterion/vxge/vxge-config.c b/drivers/net/ethernet/neterion/vxge/vxge-config.c index 398011c87643..4c1fb7e57888 100644 --- a/drivers/net/ethernet/neterion/vxge/vxge-config.c +++ b/drivers/net/ethernet/neterion/vxge/vxge-config.c @@ -13,6 +13,7 @@ ******************************************************************************/ #include <linux/vmalloc.h> #include <linux/etherdevice.h> +#include <linux/io-64-nonatomic-lo-hi.h> #include <linux/pci.h> #include <linux/slab.h> diff --git a/drivers/net/ethernet/neterion/vxge/vxge-config.h b/drivers/net/ethernet/neterion/vxge/vxge-config.h index d743a37a3cee..e678ba379598 100644 --- a/drivers/net/ethernet/neterion/vxge/vxge-config.h +++ b/drivers/net/ethernet/neterion/vxge/vxge-config.h @@ -2011,26 +2011,6 @@ enum vxge_hw_status vxge_hw_vpath_mtu_set( void vxge_hw_vpath_rx_doorbell_init(struct __vxge_hw_vpath_handle *vp); -#ifndef readq -static inline u64 readq(void __iomem *addr) -{ - u64 ret = 0; - ret = readl(addr + 4); - ret <<= 32; - ret |= readl(addr); - - return ret; -} -#endif - -#ifndef writeq -static inline void writeq(u64 val, void __iomem *addr) -{ - writel((u32) (val), addr); - writel((u32) (val >> 32), (addr + 4)); -} -#endif - static inline void __vxge_hw_pio_mem_write32_upper(u32 val, void __iomem *addr) { writel(val, addr + 4); diff --git a/drivers/net/ethernet/neterion/vxge/vxge-traffic.c b/drivers/net/ethernet/neterion/vxge/vxge-traffic.c index 0c3b5dea2858..f7a0d1d5885e 100644 --- a/drivers/net/ethernet/neterion/vxge/vxge-traffic.c +++ b/drivers/net/ethernet/neterion/vxge/vxge-traffic.c @@ -12,6 +12,7 @@ * Copyright(c) 2002-2010 Exar Corp. ******************************************************************************/ #include <linux/etherdevice.h> +#include <linux/io-64-nonatomic-lo-hi.h> #include <linux/prefetch.h> #include "vxge-traffic.h" @@ -2261,7 +2262,7 @@ void vxge_hw_vpath_msix_clear(struct __vxge_hw_vpath_handle *vp, int msix_id) { struct __vxge_hw_device *hldev = vp->vpath->hldev; - if ((hldev->config.intr_mode == VXGE_HW_INTR_MODE_MSIX_ONE_SHOT)) + if (hldev->config.intr_mode == VXGE_HW_INTR_MODE_MSIX_ONE_SHOT) __vxge_hw_pio_mem_write32_upper( (u32) vxge_bVALn(vxge_mBIT((msix_id >> 2)), 0, 32), &hldev->common_reg->clr_msix_one_shot_vec[msix_id % 4]); diff --git a/drivers/net/ethernet/netronome/nfp/flower/action.c b/drivers/net/ethernet/netronome/nfp/flower/action.c index 9044496803e6..46ba0cf257c6 100644 --- a/drivers/net/ethernet/netronome/nfp/flower/action.c +++ b/drivers/net/ethernet/netronome/nfp/flower/action.c @@ -52,6 +52,7 @@ #define NFP_FL_TUNNEL_CSUM cpu_to_be16(0x01) #define NFP_FL_TUNNEL_KEY cpu_to_be16(0x04) #define NFP_FL_TUNNEL_GENEVE_OPT cpu_to_be16(0x0800) +#define NFP_FL_SUPPORTED_TUNNEL_INFO_FLAGS IP_TUNNEL_INFO_TX #define NFP_FL_SUPPORTED_IPV4_UDP_TUN_FLAGS (NFP_FL_TUNNEL_CSUM | \ NFP_FL_TUNNEL_KEY | \ NFP_FL_TUNNEL_GENEVE_OPT) @@ -741,11 +742,16 @@ nfp_flower_loop_action(struct nfp_app *app, const struct tc_action *a, nfp_fl_push_vlan(psh_v, a); *a_len += sizeof(struct nfp_fl_push_vlan); } else if (is_tcf_tunnel_set(a)) { + struct ip_tunnel_info *ip_tun = tcf_tunnel_info(a); struct nfp_repr *repr = netdev_priv(netdev); + *tun_type = nfp_fl_get_tun_from_act_l4_port(repr->app, a); if (*tun_type == NFP_FL_TUNNEL_NONE) return -EOPNOTSUPP; + if (ip_tun->mode & ~NFP_FL_SUPPORTED_TUNNEL_INFO_FLAGS) + return -EOPNOTSUPP; + /* Pre-tunnel action is required for tunnel encap. * This checks for next hop entries on NFP. * If none, the packet falls back before applying other actions. diff --git a/drivers/net/ethernet/netronome/nfp/flower/main.h b/drivers/net/ethernet/netronome/nfp/flower/main.h index 85f8209bf007..81d941ab895c 100644 --- a/drivers/net/ethernet/netronome/nfp/flower/main.h +++ b/drivers/net/ethernet/netronome/nfp/flower/main.h @@ -70,6 +70,7 @@ struct nfp_app; #define NFP_FL_FEATS_GENEVE BIT(0) #define NFP_FL_NBI_MTU_SETTING BIT(1) #define NFP_FL_FEATS_GENEVE_OPT BIT(2) +#define NFP_FL_FEATS_VLAN_PCP BIT(3) #define NFP_FL_FEATS_LAG BIT(31) struct nfp_fl_mask_id { diff --git a/drivers/net/ethernet/netronome/nfp/flower/match.c b/drivers/net/ethernet/netronome/nfp/flower/match.c index a0c72f277faa..17acb8cc6044 100644 --- a/drivers/net/ethernet/netronome/nfp/flower/match.c +++ b/drivers/net/ethernet/netronome/nfp/flower/match.c @@ -56,7 +56,7 @@ nfp_flower_compile_meta_tci(struct nfp_flower_meta_tci *frame, FLOW_DISSECTOR_KEY_VLAN, target); /* Populate the tci field. */ - if (flow_vlan->vlan_id) { + if (flow_vlan->vlan_id || flow_vlan->vlan_priority) { tmp_tci = FIELD_PREP(NFP_FLOWER_MASK_VLAN_PRIO, flow_vlan->vlan_priority) | FIELD_PREP(NFP_FLOWER_MASK_VLAN_VID, diff --git a/drivers/net/ethernet/netronome/nfp/flower/offload.c b/drivers/net/ethernet/netronome/nfp/flower/offload.c index 2edab01c3beb..bd19624f10cf 100644 --- a/drivers/net/ethernet/netronome/nfp/flower/offload.c +++ b/drivers/net/ethernet/netronome/nfp/flower/offload.c @@ -192,6 +192,17 @@ nfp_flower_calculate_key_layers(struct nfp_app *app, key_size += sizeof(struct nfp_flower_mac_mpls); } + if (dissector_uses_key(flow->dissector, FLOW_DISSECTOR_KEY_VLAN)) { + struct flow_dissector_key_vlan *flow_vlan; + + flow_vlan = skb_flow_dissector_target(flow->dissector, + FLOW_DISSECTOR_KEY_VLAN, + flow->mask); + if (!(priv->flower_ext_feats & NFP_FL_FEATS_VLAN_PCP) && + flow_vlan->vlan_priority) + return -EOPNOTSUPP; + } + if (dissector_uses_key(flow->dissector, FLOW_DISSECTOR_KEY_ENC_CONTROL)) { struct flow_dissector_key_ipv4_addrs *mask_ipv4 = NULL; diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c index 253bdaef1505..d05e37fcc1b2 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c +++ b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c @@ -2091,10 +2091,10 @@ static void nfp_ctrl_poll(unsigned long arg) { struct nfp_net_r_vector *r_vec = (void *)arg; - spin_lock_bh(&r_vec->lock); + spin_lock(&r_vec->lock); nfp_net_tx_complete(r_vec->tx_ring, 0); __nfp_ctrl_tx_queued(r_vec); - spin_unlock_bh(&r_vec->lock); + spin_unlock(&r_vec->lock); nfp_ctrl_rx(r_vec); @@ -2180,9 +2180,13 @@ nfp_net_tx_ring_alloc(struct nfp_net_dp *dp, struct nfp_net_tx_ring *tx_ring) tx_ring->size = array_size(tx_ring->cnt, sizeof(*tx_ring->txds)); tx_ring->txds = dma_zalloc_coherent(dp->dev, tx_ring->size, - &tx_ring->dma, GFP_KERNEL); - if (!tx_ring->txds) + &tx_ring->dma, + GFP_KERNEL | __GFP_NOWARN); + if (!tx_ring->txds) { + netdev_warn(dp->netdev, "failed to allocate TX descriptor ring memory, requested descriptor count: %d, consider lowering descriptor count\n", + tx_ring->cnt); goto err_alloc; + } tx_ring->txbufs = kvcalloc(tx_ring->cnt, sizeof(*tx_ring->txbufs), GFP_KERNEL); @@ -2334,9 +2338,13 @@ nfp_net_rx_ring_alloc(struct nfp_net_dp *dp, struct nfp_net_rx_ring *rx_ring) rx_ring->cnt = dp->rxd_cnt; rx_ring->size = array_size(rx_ring->cnt, sizeof(*rx_ring->rxds)); rx_ring->rxds = dma_zalloc_coherent(dp->dev, rx_ring->size, - &rx_ring->dma, GFP_KERNEL); - if (!rx_ring->rxds) + &rx_ring->dma, + GFP_KERNEL | __GFP_NOWARN); + if (!rx_ring->rxds) { + netdev_warn(dp->netdev, "failed to allocate RX descriptor ring memory, requested descriptor count: %d, consider lowering descriptor count\n", + rx_ring->cnt); goto err_alloc; + } rx_ring->rxbufs = kvcalloc(rx_ring->cnt, sizeof(*rx_ring->rxbufs), GFP_KERNEL); @@ -3146,27 +3154,13 @@ nfp_net_vlan_rx_kill_vid(struct net_device *netdev, __be16 proto, u16 vid) return nfp_net_reconfig_mbox(nn, NFP_NET_CFG_MBOX_CMD_CTAG_FILTER_KILL); } -#ifdef CONFIG_NET_POLL_CONTROLLER -static void nfp_net_netpoll(struct net_device *netdev) -{ - struct nfp_net *nn = netdev_priv(netdev); - int i; - - /* nfp_net's NAPIs are statically allocated so even if there is a race - * with reconfig path this will simply try to schedule some disabled - * NAPI instances. - */ - for (i = 0; i < nn->dp.num_stack_tx_rings; i++) - napi_schedule_irqoff(&nn->r_vecs[i].napi); -} -#endif - static void nfp_net_stat64(struct net_device *netdev, struct rtnl_link_stats64 *stats) { struct nfp_net *nn = netdev_priv(netdev); int r; + /* Collect software stats */ for (r = 0; r < nn->max_r_vecs; r++) { struct nfp_net_r_vector *r_vec = &nn->r_vecs[r]; u64 data[3]; @@ -3192,6 +3186,14 @@ static void nfp_net_stat64(struct net_device *netdev, stats->tx_bytes += data[1]; stats->tx_errors += data[2]; } + + /* Add in device stats */ + stats->multicast += nn_readq(nn, NFP_NET_CFG_STATS_RX_MC_FRAMES); + stats->rx_dropped += nn_readq(nn, NFP_NET_CFG_STATS_RX_DISCARDS); + stats->rx_errors += nn_readq(nn, NFP_NET_CFG_STATS_RX_ERRORS); + + stats->tx_dropped += nn_readq(nn, NFP_NET_CFG_STATS_TX_DISCARDS); + stats->tx_errors += nn_readq(nn, NFP_NET_CFG_STATS_TX_ERRORS); } static int nfp_net_set_features(struct net_device *netdev, @@ -3519,9 +3521,6 @@ const struct net_device_ops nfp_net_netdev_ops = { .ndo_get_stats64 = nfp_net_stat64, .ndo_vlan_rx_add_vid = nfp_net_vlan_rx_add_vid, .ndo_vlan_rx_kill_vid = nfp_net_vlan_rx_kill_vid, -#ifdef CONFIG_NET_POLL_CONTROLLER - .ndo_poll_controller = nfp_net_netpoll, -#endif .ndo_set_vf_mac = nfp_app_set_vf_mac, .ndo_set_vf_vlan = nfp_app_set_vf_vlan, .ndo_set_vf_spoofchk = nfp_app_set_vf_spoofchk, @@ -3762,15 +3761,18 @@ static void nfp_net_netdev_init(struct nfp_net *nn) } if (nn->cap & NFP_NET_CFG_CTRL_RSS_ANY) netdev->hw_features |= NETIF_F_RXHASH; - if (nn->cap & NFP_NET_CFG_CTRL_VXLAN && - nn->cap & NFP_NET_CFG_CTRL_NVGRE) { + if (nn->cap & NFP_NET_CFG_CTRL_VXLAN) { if (nn->cap & NFP_NET_CFG_CTRL_LSO) - netdev->hw_features |= NETIF_F_GSO_GRE | - NETIF_F_GSO_UDP_TUNNEL; - nn->dp.ctrl |= NFP_NET_CFG_CTRL_VXLAN | NFP_NET_CFG_CTRL_NVGRE; - - netdev->hw_enc_features = netdev->hw_features; + netdev->hw_features |= NETIF_F_GSO_UDP_TUNNEL; + nn->dp.ctrl |= NFP_NET_CFG_CTRL_VXLAN; + } + if (nn->cap & NFP_NET_CFG_CTRL_NVGRE) { + if (nn->cap & NFP_NET_CFG_CTRL_LSO) + netdev->hw_features |= NETIF_F_GSO_GRE; + nn->dp.ctrl |= NFP_NET_CFG_CTRL_NVGRE; } + if (nn->cap & (NFP_NET_CFG_CTRL_VXLAN | NFP_NET_CFG_CTRL_NVGRE)) + netdev->hw_enc_features = netdev->hw_features; netdev->vlan_features = netdev->hw_features; diff --git a/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_rtsym.c b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_rtsym.c index 108ce8c5e68e..1ad0a015572e 100644 --- a/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_rtsym.c +++ b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_rtsym.c @@ -39,6 +39,8 @@ * Espen Skoglund <espen.skoglund@netronome.com> * Francois H. Theron <francois.theron@netronome.com> */ + +#include <asm/unaligned.h> #include <linux/kernel.h> #include <linux/module.h> #include <linux/slab.h> @@ -237,10 +239,10 @@ u64 nfp_rtsym_size(const struct nfp_rtsym *sym) { switch (sym->type) { case NFP_RTSYM_TYPE_NONE: - pr_err("rtsym type NONE\n"); + pr_err("rtsym '%s': type NONE\n", sym->name); return 0; default: - pr_warn("Unknown rtsym type: %d\n", sym->type); + pr_warn("rtsym '%s': unknown type: %d\n", sym->name, sym->type); /* fall through */ case NFP_RTSYM_TYPE_OBJECT: case NFP_RTSYM_TYPE_FUNCTION: @@ -255,7 +257,8 @@ nfp_rtsym_to_dest(struct nfp_cpp *cpp, const struct nfp_rtsym *sym, u8 action, u8 token, u64 off, u32 *cpp_id, u64 *addr) { if (sym->type != NFP_RTSYM_TYPE_OBJECT) { - nfp_err(cpp, "Direct access attempt to non-object rtsym\n"); + nfp_err(cpp, "rtsym '%s': direct access to non-object rtsym\n", + sym->name); return -EINVAL; } @@ -270,8 +273,8 @@ nfp_rtsym_to_dest(struct nfp_cpp *cpp, const struct nfp_rtsym *sym, *cpp_id = NFP_CPP_ISLAND_ID(NFP_CPP_TARGET_MU, action, token, sym->domain); } else if (sym->target < 0) { - nfp_err(cpp, "Unhandled RTsym target encoding: %d\n", - sym->target); + nfp_err(cpp, "rtsym '%s': unhandled target encoding: %d\n", + sym->name, sym->target); return -EINVAL; } else { *cpp_id = NFP_CPP_ISLAND_ID(sym->target, action, token, @@ -284,15 +287,23 @@ nfp_rtsym_to_dest(struct nfp_cpp *cpp, const struct nfp_rtsym *sym, int __nfp_rtsym_read(struct nfp_cpp *cpp, const struct nfp_rtsym *sym, u8 action, u8 token, u64 off, void *buf, size_t len) { + u64 sym_size = nfp_rtsym_size(sym); u32 cpp_id; u64 addr; int err; + if (off > sym_size) { + nfp_err(cpp, "rtsym '%s': read out of bounds: off: %lld + len: %zd > size: %lld\n", + sym->name, off, len, sym_size); + return -ENXIO; + } + len = min_t(size_t, len, sym_size - off); + if (sym->type == NFP_RTSYM_TYPE_ABS) { - __le64 tmp = cpu_to_le64(sym->addr); + u8 tmp[8]; - len = min(len, sizeof(tmp)); - memcpy(buf, &tmp, len); + put_unaligned_le64(sym->addr, tmp); + memcpy(buf, &tmp[off], len); return len; } @@ -317,6 +328,12 @@ int __nfp_rtsym_readl(struct nfp_cpp *cpp, const struct nfp_rtsym *sym, u64 addr; int err; + if (off + 4 > nfp_rtsym_size(sym)) { + nfp_err(cpp, "rtsym '%s': readl out of bounds: off: %lld + 4 > size: %lld\n", + sym->name, off, nfp_rtsym_size(sym)); + return -ENXIO; + } + err = nfp_rtsym_to_dest(cpp, sym, action, token, off, &cpp_id, &addr); if (err) return err; @@ -337,8 +354,16 @@ int __nfp_rtsym_readq(struct nfp_cpp *cpp, const struct nfp_rtsym *sym, u64 addr; int err; - if (sym->type == NFP_RTSYM_TYPE_ABS) - return sym->addr; + if (off + 8 > nfp_rtsym_size(sym)) { + nfp_err(cpp, "rtsym '%s': readq out of bounds: off: %lld + 8 > size: %lld\n", + sym->name, off, nfp_rtsym_size(sym)); + return -ENXIO; + } + + if (sym->type == NFP_RTSYM_TYPE_ABS) { + *value = sym->addr; + return 0; + } err = nfp_rtsym_to_dest(cpp, sym, action, token, off, &cpp_id, &addr); if (err) @@ -356,10 +381,18 @@ int nfp_rtsym_readq(struct nfp_cpp *cpp, const struct nfp_rtsym *sym, u64 off, int __nfp_rtsym_write(struct nfp_cpp *cpp, const struct nfp_rtsym *sym, u8 action, u8 token, u64 off, void *buf, size_t len) { + u64 sym_size = nfp_rtsym_size(sym); u32 cpp_id; u64 addr; int err; + if (off > sym_size) { + nfp_err(cpp, "rtsym '%s': write out of bounds: off: %lld + len: %zd > size: %lld\n", + sym->name, off, len, sym_size); + return -ENXIO; + } + len = min_t(size_t, len, sym_size - off); + err = nfp_rtsym_to_dest(cpp, sym, action, token, off, &cpp_id, &addr); if (err) return err; @@ -380,6 +413,12 @@ int __nfp_rtsym_writel(struct nfp_cpp *cpp, const struct nfp_rtsym *sym, u64 addr; int err; + if (off + 4 > nfp_rtsym_size(sym)) { + nfp_err(cpp, "rtsym '%s': writel out of bounds: off: %lld + 4 > size: %lld\n", + sym->name, off, nfp_rtsym_size(sym)); + return -ENXIO; + } + err = nfp_rtsym_to_dest(cpp, sym, action, token, off, &cpp_id, &addr); if (err) return err; @@ -400,6 +439,12 @@ int __nfp_rtsym_writeq(struct nfp_cpp *cpp, const struct nfp_rtsym *sym, u64 addr; int err; + if (off + 8 > nfp_rtsym_size(sym)) { + nfp_err(cpp, "rtsym '%s': writeq out of bounds: off: %lld + 8 > size: %lld\n", + sym->name, off, nfp_rtsym_size(sym)); + return -ENXIO; + } + err = nfp_rtsym_to_dest(cpp, sym, action, token, off, &cpp_id, &addr); if (err) return err; @@ -449,7 +494,7 @@ u64 nfp_rtsym_read_le(struct nfp_rtsym_table *rtbl, const char *name, break; default: nfp_err(rtbl->cpp, - "rtsym '%s' unsupported or non-scalar size: %lld\n", + "rtsym '%s': unsupported or non-scalar size: %lld\n", name, nfp_rtsym_size(sym)); err = -EINVAL; break; @@ -495,7 +540,7 @@ int nfp_rtsym_write_le(struct nfp_rtsym_table *rtbl, const char *name, break; default: nfp_err(rtbl->cpp, - "rtsym '%s' unsupported or non-scalar size: %lld\n", + "rtsym '%s': unsupported or non-scalar size: %lld\n", name, nfp_rtsym_size(sym)); err = -EINVAL; break; @@ -521,18 +566,18 @@ nfp_rtsym_map(struct nfp_rtsym_table *rtbl, const char *name, const char *id, err = nfp_rtsym_to_dest(rtbl->cpp, sym, NFP_CPP_ACTION_RW, 0, 0, &cpp_id, &addr); if (err) { - nfp_err(rtbl->cpp, "Symbol %s mapping failed\n", name); + nfp_err(rtbl->cpp, "rtsym '%s': mapping failed\n", name); return (u8 __iomem *)ERR_PTR(err); } if (sym->size < min_size) { - nfp_err(rtbl->cpp, "Symbol %s too small\n", name); + nfp_err(rtbl->cpp, "rtsym '%s': too small\n", name); return (u8 __iomem *)ERR_PTR(-EINVAL); } mem = nfp_cpp_map_area(rtbl->cpp, id, cpp_id, addr, sym->size, area); if (IS_ERR(mem)) { - nfp_err(rtbl->cpp, "Failed to map symbol %s: %ld\n", + nfp_err(rtbl->cpp, "rtysm '%s': failed to map: %ld\n", name, PTR_ERR(mem)); return mem; } diff --git a/drivers/net/ethernet/nxp/lpc_eth.c b/drivers/net/ethernet/nxp/lpc_eth.c index 08381ef8bdb4..8b23d2848457 100644 --- a/drivers/net/ethernet/nxp/lpc_eth.c +++ b/drivers/net/ethernet/nxp/lpc_eth.c @@ -797,8 +797,7 @@ static int lpc_mii_probe(struct net_device *ndev) return PTR_ERR(phydev); } - /* mask with MAC supported features */ - phydev->supported &= PHY_BASIC_FEATURES; + phy_set_max_speed(phydev, SPEED_100); phydev->advertising = phydev->supported; diff --git a/drivers/net/ethernet/qlogic/qed/qed.h b/drivers/net/ethernet/qlogic/qed/qed.h index a60e1c8d470a..5f0962d353ce 100644 --- a/drivers/net/ethernet/qlogic/qed/qed.h +++ b/drivers/net/ethernet/qlogic/qed/qed.h @@ -623,6 +623,7 @@ struct qed_hwfn { void *unzip_buf; struct dbg_tools_data dbg_info; + void *dbg_user_info; /* PWM region specific data */ u16 wid_count; diff --git a/drivers/net/ethernet/qlogic/qed/qed_cxt.c b/drivers/net/ethernet/qlogic/qed/qed_cxt.c index f1977aa440e5..dc1c1b616084 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_cxt.c +++ b/drivers/net/ethernet/qlogic/qed/qed_cxt.c @@ -40,7 +40,6 @@ #include <linux/pci.h> #include <linux/slab.h> #include <linux/string.h> -#include <linux/bitops.h> #include "qed.h" #include "qed_cxt.h" #include "qed_dev_api.h" diff --git a/drivers/net/ethernet/qlogic/qed/qed_dcbx.c b/drivers/net/ethernet/qlogic/qed/qed_dcbx.c index 6ce9a762cfc0..8e8fa823d611 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_dcbx.c +++ b/drivers/net/ethernet/qlogic/qed/qed_dcbx.c @@ -190,10 +190,8 @@ qed_dcbx_dp_protocol(struct qed_hwfn *p_hwfn, struct qed_dcbx_results *p_data) static void qed_dcbx_set_params(struct qed_dcbx_results *p_data, - struct qed_hw_info *p_info, - bool enable, - u8 prio, - u8 tc, + struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt, + bool enable, u8 prio, u8 tc, enum dcbx_protocol_type type, enum qed_pci_personality personality) { @@ -206,19 +204,30 @@ qed_dcbx_set_params(struct qed_dcbx_results *p_data, else p_data->arr[type].update = DONT_UPDATE_DCB_DSCP; + /* Do not add vlan tag 0 when DCB is enabled and port in UFP/OV mode */ + if ((test_bit(QED_MF_8021Q_TAGGING, &p_hwfn->cdev->mf_bits) || + test_bit(QED_MF_8021AD_TAGGING, &p_hwfn->cdev->mf_bits))) + p_data->arr[type].dont_add_vlan0 = true; + /* QM reconf data */ - if (p_info->personality == personality) - qed_hw_info_set_offload_tc(p_info, tc); + if (p_hwfn->hw_info.personality == personality) + qed_hw_info_set_offload_tc(&p_hwfn->hw_info, tc); + + /* Configure dcbx vlan priority in doorbell block for roce EDPM */ + if (test_bit(QED_MF_UFP_SPECIFIC, &p_hwfn->cdev->mf_bits) && + type == DCBX_PROTOCOL_ROCE) { + qed_wr(p_hwfn, p_ptt, DORQ_REG_TAG1_OVRD_MODE, 1); + qed_wr(p_hwfn, p_ptt, DORQ_REG_PF_PCP_BB_K2, prio << 1); + } } /* Update app protocol data and hw_info fields with the TLV info */ static void qed_dcbx_update_app_info(struct qed_dcbx_results *p_data, - struct qed_hwfn *p_hwfn, - bool enable, - u8 prio, u8 tc, enum dcbx_protocol_type type) + struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt, + bool enable, u8 prio, u8 tc, + enum dcbx_protocol_type type) { - struct qed_hw_info *p_info = &p_hwfn->hw_info; enum qed_pci_personality personality; enum dcbx_protocol_type id; int i; @@ -231,7 +240,7 @@ qed_dcbx_update_app_info(struct qed_dcbx_results *p_data, personality = qed_dcbx_app_update[i].personality; - qed_dcbx_set_params(p_data, p_info, enable, + qed_dcbx_set_params(p_data, p_hwfn, p_ptt, enable, prio, tc, type, personality); } } @@ -266,7 +275,7 @@ qed_dcbx_get_app_protocol_type(struct qed_hwfn *p_hwfn, * reconfiguring QM. Get protocol specific data for PF update ramrod command. */ static int -qed_dcbx_process_tlv(struct qed_hwfn *p_hwfn, +qed_dcbx_process_tlv(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt, struct qed_dcbx_results *p_data, struct dcbx_app_priority_entry *p_tbl, u32 pri_tc_tbl, int count, u8 dcbx_version) @@ -310,7 +319,7 @@ qed_dcbx_process_tlv(struct qed_hwfn *p_hwfn, enable = true; } - qed_dcbx_update_app_info(p_data, p_hwfn, enable, + qed_dcbx_update_app_info(p_data, p_hwfn, p_ptt, enable, priority, tc, type); } } @@ -332,7 +341,7 @@ qed_dcbx_process_tlv(struct qed_hwfn *p_hwfn, continue; enable = (type == DCBX_PROTOCOL_ETH) ? false : !!dcbx_version; - qed_dcbx_update_app_info(p_data, p_hwfn, enable, + qed_dcbx_update_app_info(p_data, p_hwfn, p_ptt, enable, priority, tc, type); } @@ -342,7 +351,8 @@ qed_dcbx_process_tlv(struct qed_hwfn *p_hwfn, /* Parse app TLV's to update TC information in hw_info structure for * reconfiguring QM. Get protocol specific data for PF update ramrod command. */ -static int qed_dcbx_process_mib_info(struct qed_hwfn *p_hwfn) +static int +qed_dcbx_process_mib_info(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt) { struct dcbx_app_priority_feature *p_app; struct dcbx_app_priority_entry *p_tbl; @@ -366,7 +376,7 @@ static int qed_dcbx_process_mib_info(struct qed_hwfn *p_hwfn) p_info = &p_hwfn->hw_info; num_entries = QED_MFW_GET_FIELD(p_app->flags, DCBX_APP_NUM_ENTRIES); - rc = qed_dcbx_process_tlv(p_hwfn, &data, p_tbl, pri_tc_tbl, + rc = qed_dcbx_process_tlv(p_hwfn, p_ptt, &data, p_tbl, pri_tc_tbl, num_entries, dcbx_version); if (rc) return rc; @@ -892,7 +902,7 @@ qed_dcbx_mib_update_event(struct qed_hwfn *p_hwfn, return rc; if (type == QED_DCBX_OPERATIONAL_MIB) { - rc = qed_dcbx_process_mib_info(p_hwfn); + rc = qed_dcbx_process_mib_info(p_hwfn, p_ptt); if (!rc) { /* reconfigure tcs of QM queues according * to negotiation results @@ -955,6 +965,7 @@ static void qed_dcbx_update_protocol_data(struct protocol_dcb_data *p_data, p_data->dcb_enable_flag = p_src->arr[type].enable; p_data->dcb_priority = p_src->arr[type].priority; p_data->dcb_tc = p_src->arr[type].tc; + p_data->dcb_dont_add_vlan0 = p_src->arr[type].dont_add_vlan0; } /* Set pf update ramrod command params */ diff --git a/drivers/net/ethernet/qlogic/qed/qed_dcbx.h b/drivers/net/ethernet/qlogic/qed/qed_dcbx.h index a4d688c04e18..01f253ea4b22 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_dcbx.h +++ b/drivers/net/ethernet/qlogic/qed/qed_dcbx.h @@ -55,6 +55,7 @@ struct qed_dcbx_app_data { u8 update; /* Update indication */ u8 priority; /* Priority */ u8 tc; /* Traffic Class */ + bool dont_add_vlan0; /* Do not insert a vlan tag with id 0 */ }; #define QED_DCBX_VERSION_DISABLED 0 diff --git a/drivers/net/ethernet/qlogic/qed/qed_debug.c b/drivers/net/ethernet/qlogic/qed/qed_debug.c index 1aa9fc1c5890..78a638ec7c0a 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_debug.c +++ b/drivers/net/ethernet/qlogic/qed/qed_debug.c @@ -3454,7 +3454,8 @@ static u32 qed_grc_dump_iors(struct qed_hwfn *p_hwfn, addr = BYTES_TO_DWORDS(storm->sem_fast_mem_addr + SEM_FAST_REG_STORM_REG_FILE) + IOR_SET_OFFSET(set_id); - buf[strlen(buf) - 1] = '0' + set_id; + if (strlen(buf) > 0) + buf[strlen(buf) - 1] = '0' + set_id; offset += qed_grc_dump_mem(p_hwfn, p_ptt, dump_buf + offset, @@ -5563,35 +5564,6 @@ struct block_info { enum block_id id; }; -struct mcp_trace_format { - u32 data; -#define MCP_TRACE_FORMAT_MODULE_MASK 0x0000ffff -#define MCP_TRACE_FORMAT_MODULE_SHIFT 0 -#define MCP_TRACE_FORMAT_LEVEL_MASK 0x00030000 -#define MCP_TRACE_FORMAT_LEVEL_SHIFT 16 -#define MCP_TRACE_FORMAT_P1_SIZE_MASK 0x000c0000 -#define MCP_TRACE_FORMAT_P1_SIZE_SHIFT 18 -#define MCP_TRACE_FORMAT_P2_SIZE_MASK 0x00300000 -#define MCP_TRACE_FORMAT_P2_SIZE_SHIFT 20 -#define MCP_TRACE_FORMAT_P3_SIZE_MASK 0x00c00000 -#define MCP_TRACE_FORMAT_P3_SIZE_SHIFT 22 -#define MCP_TRACE_FORMAT_LEN_MASK 0xff000000 -#define MCP_TRACE_FORMAT_LEN_SHIFT 24 - - char *format_str; -}; - -/* Meta data structure, generated by a perl script during MFW build. therefore, - * the structs mcp_trace_meta and mcp_trace_format are duplicated in the perl - * script. - */ -struct mcp_trace_meta { - u32 modules_num; - char **modules; - u32 formats_num; - struct mcp_trace_format *formats; -}; - /* REG fifo element */ struct reg_fifo_element { u64 data; @@ -5714,6 +5686,20 @@ struct igu_fifo_addr_data { enum igu_fifo_addr_types type; }; +struct mcp_trace_meta { + u32 modules_num; + char **modules; + u32 formats_num; + struct mcp_trace_format *formats; + bool is_allocated; +}; + +/* Debug Tools user data */ +struct dbg_tools_user_data { + struct mcp_trace_meta mcp_trace_meta; + const u32 *mcp_trace_user_meta_buf; +}; + /******************************** Constants **********************************/ #define MAX_MSG_LEN 1024 @@ -6137,15 +6123,6 @@ static const struct igu_fifo_addr_data s_igu_fifo_addr_data[] = { /******************************** Variables **********************************/ -/* MCP Trace meta data array - used in case the dump doesn't contain the - * meta data (e.g. due to no NVRAM access). - */ -static struct user_dbg_array s_mcp_trace_meta_arr = { NULL, 0 }; - -/* Parsed MCP Trace meta data info, based on MCP trace meta array */ -static struct mcp_trace_meta s_mcp_trace_meta; -static bool s_mcp_trace_meta_valid; - /* Temporary buffer, used for print size calculations */ static char s_temp_buf[MAX_MSG_LEN]; @@ -6311,6 +6288,12 @@ static u32 qed_print_section_params(u32 *dump_buf, return dump_offset; } +static struct dbg_tools_user_data * +qed_dbg_get_user_data(struct qed_hwfn *p_hwfn) +{ + return (struct dbg_tools_user_data *)p_hwfn->dbg_user_info; +} + /* Parses the idle check rules and returns the number of characters printed. * In case of parsing error, returns 0. */ @@ -6570,43 +6553,26 @@ static enum dbg_status qed_parse_idle_chk_dump(u32 *dump_buf, return DBG_STATUS_OK; } -/* Frees the specified MCP Trace meta data */ -static void qed_mcp_trace_free_meta(struct qed_hwfn *p_hwfn, - struct mcp_trace_meta *meta) -{ - u32 i; - - s_mcp_trace_meta_valid = false; - - /* Release modules */ - if (meta->modules) { - for (i = 0; i < meta->modules_num; i++) - kfree(meta->modules[i]); - kfree(meta->modules); - } - - /* Release formats */ - if (meta->formats) { - for (i = 0; i < meta->formats_num; i++) - kfree(meta->formats[i].format_str); - kfree(meta->formats); - } -} - /* Allocates and fills MCP Trace meta data based on the specified meta data * dump buffer. * Returns debug status code. */ -static enum dbg_status qed_mcp_trace_alloc_meta(struct qed_hwfn *p_hwfn, - const u32 *meta_buf, - struct mcp_trace_meta *meta) +static enum dbg_status +qed_mcp_trace_alloc_meta_data(struct qed_hwfn *p_hwfn, + const u32 *meta_buf) { - u8 *meta_buf_bytes = (u8 *)meta_buf; + struct dbg_tools_user_data *dev_user_data; u32 offset = 0, signature, i; + struct mcp_trace_meta *meta; + u8 *meta_buf_bytes; + + dev_user_data = qed_dbg_get_user_data(p_hwfn); + meta = &dev_user_data->mcp_trace_meta; + meta_buf_bytes = (u8 *)meta_buf; /* Free the previous meta before loading a new one. */ - if (s_mcp_trace_meta_valid) - qed_mcp_trace_free_meta(p_hwfn, meta); + if (meta->is_allocated) + qed_mcp_trace_free_meta_data(p_hwfn); memset(meta, 0, sizeof(*meta)); @@ -6674,7 +6640,7 @@ static enum dbg_status qed_mcp_trace_alloc_meta(struct qed_hwfn *p_hwfn, format_len, format_ptr->format_str); } - s_mcp_trace_meta_valid = true; + meta->is_allocated = true; return DBG_STATUS_OK; } @@ -6687,21 +6653,26 @@ static enum dbg_status qed_mcp_trace_alloc_meta(struct qed_hwfn *p_hwfn, * buffer. * data_size - size in bytes of data to parse. * parsed_buf - destination buffer for parsed data. - * parsed_bytes - size of parsed data in bytes. + * parsed_results_bytes - size of parsed data in bytes. */ -static enum dbg_status qed_parse_mcp_trace_buf(u8 *trace_buf, +static enum dbg_status qed_parse_mcp_trace_buf(struct qed_hwfn *p_hwfn, + u8 *trace_buf, u32 trace_buf_size, u32 data_offset, u32 data_size, char *parsed_buf, - u32 *parsed_bytes) + u32 *parsed_results_bytes) { + struct dbg_tools_user_data *dev_user_data; + struct mcp_trace_meta *meta; u32 param_mask, param_shift; enum dbg_status status; - *parsed_bytes = 0; + dev_user_data = qed_dbg_get_user_data(p_hwfn); + meta = &dev_user_data->mcp_trace_meta; + *parsed_results_bytes = 0; - if (!s_mcp_trace_meta_valid) + if (!meta->is_allocated) return DBG_STATUS_MCP_TRACE_BAD_DATA; status = DBG_STATUS_OK; @@ -6723,7 +6694,7 @@ static enum dbg_status qed_parse_mcp_trace_buf(u8 *trace_buf, format_idx = header & MFW_TRACE_EVENTID_MASK; /* Skip message if its index doesn't exist in the meta data */ - if (format_idx >= s_mcp_trace_meta.formats_num) { + if (format_idx >= meta->formats_num) { u8 format_size = (u8)((header & MFW_TRACE_PRM_SIZE_MASK) >> MFW_TRACE_PRM_SIZE_SHIFT); @@ -6738,7 +6709,7 @@ static enum dbg_status qed_parse_mcp_trace_buf(u8 *trace_buf, continue; } - format_ptr = &s_mcp_trace_meta.formats[format_idx]; + format_ptr = &meta->formats[format_idx]; for (i = 0, param_mask = MCP_TRACE_FORMAT_P1_SIZE_MASK, @@ -6783,19 +6754,20 @@ static enum dbg_status qed_parse_mcp_trace_buf(u8 *trace_buf, return DBG_STATUS_MCP_TRACE_BAD_DATA; /* Print current message to results buffer */ - *parsed_bytes += - sprintf(qed_get_buf_ptr(parsed_buf, *parsed_bytes), + *parsed_results_bytes += + sprintf(qed_get_buf_ptr(parsed_buf, + *parsed_results_bytes), "%s %-8s: ", s_mcp_trace_level_str[format_level], - s_mcp_trace_meta.modules[format_module]); - *parsed_bytes += - sprintf(qed_get_buf_ptr(parsed_buf, *parsed_bytes), + meta->modules[format_module]); + *parsed_results_bytes += + sprintf(qed_get_buf_ptr(parsed_buf, *parsed_results_bytes), format_ptr->format_str, params[0], params[1], params[2]); } /* Add string NULL terminator */ - (*parsed_bytes)++; + (*parsed_results_bytes)++; return status; } @@ -6803,24 +6775,25 @@ static enum dbg_status qed_parse_mcp_trace_buf(u8 *trace_buf, /* Parses an MCP Trace dump buffer. * If result_buf is not NULL, the MCP Trace results are printed to it. * In any case, the required results buffer size is assigned to - * parsed_bytes. + * parsed_results_bytes. * The parsing status is returned. */ static enum dbg_status qed_parse_mcp_trace_dump(struct qed_hwfn *p_hwfn, u32 *dump_buf, - char *parsed_buf, - u32 *parsed_bytes) + char *results_buf, + u32 *parsed_results_bytes, + bool free_meta_data) { const char *section_name, *param_name, *param_str_val; u32 data_size, trace_data_dwords, trace_meta_dwords; - u32 offset, results_offset, parsed_buf_bytes; + u32 offset, results_offset, results_buf_bytes; u32 param_num_val, num_section_params; struct mcp_trace *trace; enum dbg_status status; const u32 *meta_buf; u8 *trace_buf; - *parsed_bytes = 0; + *parsed_results_bytes = 0; /* Read global_params section */ dump_buf += qed_read_section_hdr(dump_buf, @@ -6831,7 +6804,7 @@ static enum dbg_status qed_parse_mcp_trace_dump(struct qed_hwfn *p_hwfn, /* Print global params */ dump_buf += qed_print_section_params(dump_buf, num_section_params, - parsed_buf, &results_offset); + results_buf, &results_offset); /* Read trace_data section */ dump_buf += qed_read_section_hdr(dump_buf, @@ -6846,6 +6819,9 @@ static enum dbg_status qed_parse_mcp_trace_dump(struct qed_hwfn *p_hwfn, /* Prepare trace info */ trace = (struct mcp_trace *)dump_buf; + if (trace->signature != MFW_TRACE_SIGNATURE || !trace->size) + return DBG_STATUS_MCP_TRACE_BAD_DATA; + trace_buf = (u8 *)dump_buf + sizeof(*trace); offset = trace->trace_oldest; data_size = qed_cyclic_sub(trace->trace_prod, offset, trace->size); @@ -6865,31 +6841,39 @@ static enum dbg_status qed_parse_mcp_trace_dump(struct qed_hwfn *p_hwfn, /* Choose meta data buffer */ if (!trace_meta_dwords) { /* Dump doesn't include meta data */ - if (!s_mcp_trace_meta_arr.ptr) + struct dbg_tools_user_data *dev_user_data = + qed_dbg_get_user_data(p_hwfn); + + if (!dev_user_data->mcp_trace_user_meta_buf) return DBG_STATUS_MCP_TRACE_NO_META; - meta_buf = s_mcp_trace_meta_arr.ptr; + + meta_buf = dev_user_data->mcp_trace_user_meta_buf; } else { /* Dump includes meta data */ meta_buf = dump_buf; } /* Allocate meta data memory */ - status = qed_mcp_trace_alloc_meta(p_hwfn, meta_buf, &s_mcp_trace_meta); + status = qed_mcp_trace_alloc_meta_data(p_hwfn, meta_buf); if (status != DBG_STATUS_OK) return status; - status = qed_parse_mcp_trace_buf(trace_buf, + status = qed_parse_mcp_trace_buf(p_hwfn, + trace_buf, trace->size, offset, data_size, - parsed_buf ? - parsed_buf + results_offset : + results_buf ? + results_buf + results_offset : NULL, - &parsed_buf_bytes); + &results_buf_bytes); if (status != DBG_STATUS_OK) return status; - *parsed_bytes = results_offset + parsed_buf_bytes; + if (free_meta_data) + qed_mcp_trace_free_meta_data(p_hwfn); + + *parsed_results_bytes = results_offset + results_buf_bytes; return DBG_STATUS_OK; } @@ -7361,6 +7345,16 @@ enum dbg_status qed_dbg_user_set_bin_ptr(const u8 * const bin_ptr) return DBG_STATUS_OK; } +enum dbg_status qed_dbg_alloc_user_data(struct qed_hwfn *p_hwfn) +{ + p_hwfn->dbg_user_info = kzalloc(sizeof(struct dbg_tools_user_data), + GFP_KERNEL); + if (!p_hwfn->dbg_user_info) + return DBG_STATUS_VIRT_MEM_ALLOC_FAILED; + + return DBG_STATUS_OK; +} + const char *qed_dbg_get_status_str(enum dbg_status status) { return (status < @@ -7397,10 +7391,13 @@ enum dbg_status qed_print_idle_chk_results(struct qed_hwfn *p_hwfn, num_errors, num_warnings); } -void qed_dbg_mcp_trace_set_meta_data(u32 *data, u32 size) +void qed_dbg_mcp_trace_set_meta_data(struct qed_hwfn *p_hwfn, + const u32 *meta_buf) { - s_mcp_trace_meta_arr.ptr = data; - s_mcp_trace_meta_arr.size_in_dwords = size; + struct dbg_tools_user_data *dev_user_data = + qed_dbg_get_user_data(p_hwfn); + + dev_user_data->mcp_trace_user_meta_buf = meta_buf; } enum dbg_status qed_get_mcp_trace_results_buf_size(struct qed_hwfn *p_hwfn, @@ -7409,7 +7406,7 @@ enum dbg_status qed_get_mcp_trace_results_buf_size(struct qed_hwfn *p_hwfn, u32 *results_buf_size) { return qed_parse_mcp_trace_dump(p_hwfn, - dump_buf, NULL, results_buf_size); + dump_buf, NULL, results_buf_size, true); } enum dbg_status qed_print_mcp_trace_results(struct qed_hwfn *p_hwfn, @@ -7421,20 +7418,61 @@ enum dbg_status qed_print_mcp_trace_results(struct qed_hwfn *p_hwfn, return qed_parse_mcp_trace_dump(p_hwfn, dump_buf, - results_buf, &parsed_buf_size); + results_buf, &parsed_buf_size, true); +} + +enum dbg_status qed_print_mcp_trace_results_cont(struct qed_hwfn *p_hwfn, + u32 *dump_buf, + char *results_buf) +{ + u32 parsed_buf_size; + + return qed_parse_mcp_trace_dump(p_hwfn, dump_buf, results_buf, + &parsed_buf_size, false); } -enum dbg_status qed_print_mcp_trace_line(u8 *dump_buf, +enum dbg_status qed_print_mcp_trace_line(struct qed_hwfn *p_hwfn, + u8 *dump_buf, u32 num_dumped_bytes, char *results_buf) { - u32 parsed_bytes; + u32 parsed_results_bytes; - return qed_parse_mcp_trace_buf(dump_buf, + return qed_parse_mcp_trace_buf(p_hwfn, + dump_buf, num_dumped_bytes, 0, num_dumped_bytes, - results_buf, &parsed_bytes); + results_buf, &parsed_results_bytes); +} + +/* Frees the specified MCP Trace meta data */ +void qed_mcp_trace_free_meta_data(struct qed_hwfn *p_hwfn) +{ + struct dbg_tools_user_data *dev_user_data; + struct mcp_trace_meta *meta; + u32 i; + + dev_user_data = qed_dbg_get_user_data(p_hwfn); + meta = &dev_user_data->mcp_trace_meta; + if (!meta->is_allocated) + return; + + /* Release modules */ + if (meta->modules) { + for (i = 0; i < meta->modules_num; i++) + kfree(meta->modules[i]); + kfree(meta->modules); + } + + /* Release formats */ + if (meta->formats) { + for (i = 0; i < meta->formats_num; i++) + kfree(meta->formats[i].format_str); + kfree(meta->formats); + } + + meta->is_allocated = false; } enum dbg_status qed_get_reg_fifo_results_buf_size(struct qed_hwfn *p_hwfn, diff --git a/drivers/net/ethernet/qlogic/qed/qed_dev.c b/drivers/net/ethernet/qlogic/qed/qed_dev.c index 016ca8a7ec8a..0fbeafeef7a0 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_dev.c +++ b/drivers/net/ethernet/qlogic/qed/qed_dev.c @@ -144,6 +144,12 @@ static void qed_qm_info_free(struct qed_hwfn *p_hwfn) qm_info->wfq_data = NULL; } +static void qed_dbg_user_data_free(struct qed_hwfn *p_hwfn) +{ + kfree(p_hwfn->dbg_user_info); + p_hwfn->dbg_user_info = NULL; +} + void qed_resc_free(struct qed_dev *cdev) { int i; @@ -183,6 +189,7 @@ void qed_resc_free(struct qed_dev *cdev) qed_l2_free(p_hwfn); qed_dmae_info_free(p_hwfn); qed_dcbx_info_free(p_hwfn); + qed_dbg_user_data_free(p_hwfn); } } @@ -1083,6 +1090,10 @@ int qed_resc_alloc(struct qed_dev *cdev) rc = qed_dcbx_info_alloc(p_hwfn); if (rc) goto alloc_err; + + rc = qed_dbg_alloc_user_data(p_hwfn); + if (rc) + goto alloc_err; } cdev->reset_stats = kzalloc(sizeof(*cdev->reset_stats), GFP_KERNEL); @@ -1706,7 +1717,7 @@ static int qed_vf_start(struct qed_hwfn *p_hwfn, int qed_hw_init(struct qed_dev *cdev, struct qed_hw_init_params *p_params) { struct qed_load_req_params load_req_params; - u32 load_code, param, drv_mb_param; + u32 load_code, resp, param, drv_mb_param; bool b_default_mtu = true; struct qed_hwfn *p_hwfn; int rc = 0, mfw_rc, i; @@ -1852,6 +1863,19 @@ int qed_hw_init(struct qed_dev *cdev, struct qed_hw_init_params *p_params) if (IS_PF(cdev)) { p_hwfn = QED_LEADING_HWFN(cdev); + + /* Get pre-negotiated values for stag, bandwidth etc. */ + DP_VERBOSE(p_hwfn, + QED_MSG_SPQ, + "Sending GET_OEM_UPDATES command to trigger stag/bandwidth attention handling\n"); + drv_mb_param = 1 << DRV_MB_PARAM_DUMMY_OEM_UPDATES_OFFSET; + rc = qed_mcp_cmd(p_hwfn, p_hwfn->p_main_ptt, + DRV_MSG_CODE_GET_OEM_UPDATES, + drv_mb_param, &resp, ¶m); + if (rc) + DP_NOTICE(p_hwfn, + "Failed to send GET_OEM_UPDATES attention request\n"); + drv_mb_param = STORM_FW_VERSION; rc = qed_mcp_cmd(p_hwfn, p_hwfn->p_main_ptt, DRV_MSG_CODE_OV_UPDATE_STORM_FW_VER, diff --git a/drivers/net/ethernet/qlogic/qed/qed_hsi.h b/drivers/net/ethernet/qlogic/qed/qed_hsi.h index 8faceb691657..d4d08383c753 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_hsi.h +++ b/drivers/net/ethernet/qlogic/qed/qed_hsi.h @@ -274,7 +274,8 @@ struct core_rx_start_ramrod_data { u8 mf_si_mcast_accept_all; struct core_rx_action_on_error action_on_error; u8 gsi_offload_flag; - u8 reserved[6]; + u8 wipe_inner_vlan_pri_en; + u8 reserved[5]; }; /* Ramrod data for rx queue stop ramrod */ @@ -351,7 +352,8 @@ struct core_tx_start_ramrod_data { __le16 pbl_size; __le16 qm_pq_id; u8 gsi_offload_flag; - u8 resrved[3]; + u8 vport_id; + u8 resrved[2]; }; /* Ramrod data for tx queue stop ramrod */ @@ -914,6 +916,16 @@ struct eth_rx_rate_limit { __le16 reserved1; }; +/* Update RSS indirection table entry command */ +struct eth_tstorm_rss_update_data { + u8 valid; + u8 vport_id; + u8 ind_table_index; + u8 reserved; + __le16 ind_table_value; + __le16 reserved1; +}; + struct eth_ustorm_per_pf_stat { struct regpair rcv_lb_ucast_bytes; struct regpair rcv_lb_mcast_bytes; @@ -1241,6 +1253,10 @@ struct rl_update_ramrod_data { u8 rl_id_first; u8 rl_id_last; u8 rl_dc_qcn_flg; + u8 dcqcn_reset_alpha_on_idle; + u8 rl_bc_stage_th; + u8 rl_timer_stage_th; + u8 reserved1; __le32 rl_bc_rate; __le16 rl_max_rate; __le16 rl_r_ai; @@ -1249,7 +1265,7 @@ struct rl_update_ramrod_data { __le32 dcqcn_k_us; __le32 dcqcn_timeuot_us; __le32 qcn_timeuot_us; - __le32 reserved[2]; + __le32 reserved2; }; /* Slowpath Element (SPQE) */ @@ -3322,6 +3338,25 @@ enum dbg_status qed_dbg_read_attn(struct qed_hwfn *p_hwfn, enum dbg_status qed_dbg_print_attn(struct qed_hwfn *p_hwfn, struct dbg_attn_block_result *results); +/******************************* Data Types **********************************/ + +struct mcp_trace_format { + u32 data; +#define MCP_TRACE_FORMAT_MODULE_MASK 0x0000ffff +#define MCP_TRACE_FORMAT_MODULE_SHIFT 0 +#define MCP_TRACE_FORMAT_LEVEL_MASK 0x00030000 +#define MCP_TRACE_FORMAT_LEVEL_SHIFT 16 +#define MCP_TRACE_FORMAT_P1_SIZE_MASK 0x000c0000 +#define MCP_TRACE_FORMAT_P1_SIZE_SHIFT 18 +#define MCP_TRACE_FORMAT_P2_SIZE_MASK 0x00300000 +#define MCP_TRACE_FORMAT_P2_SIZE_SHIFT 20 +#define MCP_TRACE_FORMAT_P3_SIZE_MASK 0x00c00000 +#define MCP_TRACE_FORMAT_P3_SIZE_SHIFT 22 +#define MCP_TRACE_FORMAT_LEN_MASK 0xff000000 +#define MCP_TRACE_FORMAT_LEN_SHIFT 24 + char *format_str; +}; + /******************************** Constants **********************************/ #define MAX_NAME_LEN 16 @@ -3337,6 +3372,13 @@ enum dbg_status qed_dbg_print_attn(struct qed_hwfn *p_hwfn, enum dbg_status qed_dbg_user_set_bin_ptr(const u8 * const bin_ptr); /** + * @brief qed_dbg_alloc_user_data - Allocates user debug data. + * + * @param p_hwfn - HW device data + */ +enum dbg_status qed_dbg_alloc_user_data(struct qed_hwfn *p_hwfn); + +/** * @brief qed_dbg_get_status_str - Returns a string for the specified status. * * @param status - a debug status code. @@ -3381,8 +3423,7 @@ enum dbg_status qed_print_idle_chk_results(struct qed_hwfn *p_hwfn, u32 *num_warnings); /** - * @brief qed_dbg_mcp_trace_set_meta_data - Sets a pointer to the MCP Trace - * meta data. + * @brief qed_dbg_mcp_trace_set_meta_data - Sets the MCP Trace meta data. * * Needed in case the MCP Trace dump doesn't contain the meta data (e.g. due to * no NVRAM access). @@ -3390,7 +3431,8 @@ enum dbg_status qed_print_idle_chk_results(struct qed_hwfn *p_hwfn, * @param data - pointer to MCP Trace meta data * @param size - size of MCP Trace meta data in dwords */ -void qed_dbg_mcp_trace_set_meta_data(u32 *data, u32 size); +void qed_dbg_mcp_trace_set_meta_data(struct qed_hwfn *p_hwfn, + const u32 *meta_buf); /** * @brief qed_get_mcp_trace_results_buf_size - Returns the required buffer size @@ -3425,19 +3467,45 @@ enum dbg_status qed_print_mcp_trace_results(struct qed_hwfn *p_hwfn, char *results_buf); /** + * @brief qed_print_mcp_trace_results_cont - Prints MCP Trace results, and + * keeps the MCP trace meta data allocated, to support continuous MCP Trace + * parsing. After the continuous parsing ends, mcp_trace_free_meta_data should + * be called to free the meta data. + * + * @param p_hwfn - HW device data + * @param dump_buf - mcp trace dump buffer, starting from the header. + * @param results_buf - buffer for printing the mcp trace results. + * + * @return error if the parsing fails, ok otherwise. + */ +enum dbg_status qed_print_mcp_trace_results_cont(struct qed_hwfn *p_hwfn, + u32 *dump_buf, + char *results_buf); + +/** * @brief print_mcp_trace_line - Prints MCP Trace results for a single line * + * @param p_hwfn - HW device data * @param dump_buf - mcp trace dump buffer, starting from the header. * @param num_dumped_bytes - number of bytes that were dumped. * @param results_buf - buffer for printing the mcp trace results. * * @return error if the parsing fails, ok otherwise. */ -enum dbg_status qed_print_mcp_trace_line(u8 *dump_buf, +enum dbg_status qed_print_mcp_trace_line(struct qed_hwfn *p_hwfn, + u8 *dump_buf, u32 num_dumped_bytes, char *results_buf); /** + * @brief mcp_trace_free_meta_data - Frees the MCP Trace meta data. + * Should be called after continuous MCP Trace parsing. + * + * @param p_hwfn - HW device data + */ +void qed_mcp_trace_free_meta_data(struct qed_hwfn *p_hwfn); + +/** * @brief qed_get_reg_fifo_results_buf_size - Returns the required buffer size * for reg_fifo results (in bytes). * @@ -4303,154 +4371,161 @@ void qed_set_rdma_error_level(struct qed_hwfn *p_hwfn, (IRO[29].base + ((pf_id) * IRO[29].m1)) #define ETH_RX_RATE_LIMIT_SIZE (IRO[29].size) +/* RSS indirection table entry update command per PF offset in TSTORM PF BAR0. + * Use eth_tstorm_rss_update_data for update. + */ +#define TSTORM_ETH_RSS_UPDATE_OFFSET(pf_id) \ + (IRO[30].base + ((pf_id) * IRO[30].m1)) +#define TSTORM_ETH_RSS_UPDATE_SIZE (IRO[30].size) + /* Xstorm queue zone */ #define XSTORM_ETH_QUEUE_ZONE_OFFSET(queue_id) \ - (IRO[30].base + ((queue_id) * IRO[30].m1)) -#define XSTORM_ETH_QUEUE_ZONE_SIZE (IRO[30].size) + (IRO[31].base + ((queue_id) * IRO[31].m1)) +#define XSTORM_ETH_QUEUE_ZONE_SIZE (IRO[31].size) /* Ystorm cqe producer */ #define YSTORM_TOE_CQ_PROD_OFFSET(rss_id) \ - (IRO[31].base + ((rss_id) * IRO[31].m1)) -#define YSTORM_TOE_CQ_PROD_SIZE (IRO[31].size) + (IRO[32].base + ((rss_id) * IRO[32].m1)) +#define YSTORM_TOE_CQ_PROD_SIZE (IRO[32].size) /* Ustorm cqe producer */ #define USTORM_TOE_CQ_PROD_OFFSET(rss_id) \ - (IRO[32].base + ((rss_id) * IRO[32].m1)) -#define USTORM_TOE_CQ_PROD_SIZE (IRO[32].size) + (IRO[33].base + ((rss_id) * IRO[33].m1)) +#define USTORM_TOE_CQ_PROD_SIZE (IRO[33].size) /* Ustorm grq producer */ #define USTORM_TOE_GRQ_PROD_OFFSET(pf_id) \ - (IRO[33].base + ((pf_id) * IRO[33].m1)) -#define USTORM_TOE_GRQ_PROD_SIZE (IRO[33].size) + (IRO[34].base + ((pf_id) * IRO[34].m1)) +#define USTORM_TOE_GRQ_PROD_SIZE (IRO[34].size) /* Tstorm cmdq-cons of given command queue-id */ #define TSTORM_SCSI_CMDQ_CONS_OFFSET(cmdq_queue_id) \ - (IRO[34].base + ((cmdq_queue_id) * IRO[34].m1)) -#define TSTORM_SCSI_CMDQ_CONS_SIZE (IRO[34].size) + (IRO[35].base + ((cmdq_queue_id) * IRO[35].m1)) +#define TSTORM_SCSI_CMDQ_CONS_SIZE (IRO[35].size) /* Tstorm (reflects M-Storm) bdq-external-producer of given function ID, * BDqueue-id. */ #define TSTORM_SCSI_BDQ_EXT_PROD_OFFSET(func_id, bdq_id) \ - (IRO[35].base + ((func_id) * IRO[35].m1) + ((bdq_id) * IRO[35].m2)) -#define TSTORM_SCSI_BDQ_EXT_PROD_SIZE (IRO[35].size) + (IRO[36].base + ((func_id) * IRO[36].m1) + ((bdq_id) * IRO[36].m2)) +#define TSTORM_SCSI_BDQ_EXT_PROD_SIZE (IRO[36].size) /* Mstorm bdq-external-producer of given BDQ resource ID, BDqueue-id */ #define MSTORM_SCSI_BDQ_EXT_PROD_OFFSET(func_id, bdq_id) \ - (IRO[36].base + ((func_id) * IRO[36].m1) + ((bdq_id) * IRO[36].m2)) -#define MSTORM_SCSI_BDQ_EXT_PROD_SIZE (IRO[36].size) + (IRO[37].base + ((func_id) * IRO[37].m1) + ((bdq_id) * IRO[37].m2)) +#define MSTORM_SCSI_BDQ_EXT_PROD_SIZE (IRO[37].size) /* Tstorm iSCSI RX stats */ #define TSTORM_ISCSI_RX_STATS_OFFSET(pf_id) \ - (IRO[37].base + ((pf_id) * IRO[37].m1)) -#define TSTORM_ISCSI_RX_STATS_SIZE (IRO[37].size) + (IRO[38].base + ((pf_id) * IRO[38].m1)) +#define TSTORM_ISCSI_RX_STATS_SIZE (IRO[38].size) /* Mstorm iSCSI RX stats */ #define MSTORM_ISCSI_RX_STATS_OFFSET(pf_id) \ - (IRO[38].base + ((pf_id) * IRO[38].m1)) -#define MSTORM_ISCSI_RX_STATS_SIZE (IRO[38].size) + (IRO[39].base + ((pf_id) * IRO[39].m1)) +#define MSTORM_ISCSI_RX_STATS_SIZE (IRO[39].size) /* Ustorm iSCSI RX stats */ #define USTORM_ISCSI_RX_STATS_OFFSET(pf_id) \ - (IRO[39].base + ((pf_id) * IRO[39].m1)) -#define USTORM_ISCSI_RX_STATS_SIZE (IRO[39].size) + (IRO[40].base + ((pf_id) * IRO[40].m1)) +#define USTORM_ISCSI_RX_STATS_SIZE (IRO[40].size) /* Xstorm iSCSI TX stats */ #define XSTORM_ISCSI_TX_STATS_OFFSET(pf_id) \ - (IRO[40].base + ((pf_id) * IRO[40].m1)) -#define XSTORM_ISCSI_TX_STATS_SIZE (IRO[40].size) + (IRO[41].base + ((pf_id) * IRO[41].m1)) +#define XSTORM_ISCSI_TX_STATS_SIZE (IRO[41].size) /* Ystorm iSCSI TX stats */ #define YSTORM_ISCSI_TX_STATS_OFFSET(pf_id) \ - (IRO[41].base + ((pf_id) * IRO[41].m1)) -#define YSTORM_ISCSI_TX_STATS_SIZE (IRO[41].size) + (IRO[42].base + ((pf_id) * IRO[42].m1)) +#define YSTORM_ISCSI_TX_STATS_SIZE (IRO[42].size) /* Pstorm iSCSI TX stats */ #define PSTORM_ISCSI_TX_STATS_OFFSET(pf_id) \ - (IRO[42].base + ((pf_id) * IRO[42].m1)) -#define PSTORM_ISCSI_TX_STATS_SIZE (IRO[42].size) + (IRO[43].base + ((pf_id) * IRO[43].m1)) +#define PSTORM_ISCSI_TX_STATS_SIZE (IRO[43].size) /* Tstorm FCoE RX stats */ #define TSTORM_FCOE_RX_STATS_OFFSET(pf_id) \ - (IRO[43].base + ((pf_id) * IRO[43].m1)) -#define TSTORM_FCOE_RX_STATS_SIZE (IRO[43].size) + (IRO[44].base + ((pf_id) * IRO[44].m1)) +#define TSTORM_FCOE_RX_STATS_SIZE (IRO[44].size) /* Pstorm FCoE TX stats */ #define PSTORM_FCOE_TX_STATS_OFFSET(pf_id) \ - (IRO[44].base + ((pf_id) * IRO[44].m1)) -#define PSTORM_FCOE_TX_STATS_SIZE (IRO[44].size) + (IRO[45].base + ((pf_id) * IRO[45].m1)) +#define PSTORM_FCOE_TX_STATS_SIZE (IRO[45].size) /* Pstorm RDMA queue statistics */ #define PSTORM_RDMA_QUEUE_STAT_OFFSET(rdma_stat_counter_id) \ - (IRO[45].base + ((rdma_stat_counter_id) * IRO[45].m1)) -#define PSTORM_RDMA_QUEUE_STAT_SIZE (IRO[45].size) + (IRO[46].base + ((rdma_stat_counter_id) * IRO[46].m1)) +#define PSTORM_RDMA_QUEUE_STAT_SIZE (IRO[46].size) /* Tstorm RDMA queue statistics */ #define TSTORM_RDMA_QUEUE_STAT_OFFSET(rdma_stat_counter_id) \ - (IRO[46].base + ((rdma_stat_counter_id) * IRO[46].m1)) -#define TSTORM_RDMA_QUEUE_STAT_SIZE (IRO[46].size) + (IRO[47].base + ((rdma_stat_counter_id) * IRO[47].m1)) +#define TSTORM_RDMA_QUEUE_STAT_SIZE (IRO[47].size) /* Xstorm error level for assert */ #define XSTORM_RDMA_ASSERT_LEVEL_OFFSET(pf_id) \ - (IRO[47].base + ((pf_id) * IRO[47].m1)) -#define XSTORM_RDMA_ASSERT_LEVEL_SIZE (IRO[47].size) + (IRO[48].base + ((pf_id) * IRO[48].m1)) +#define XSTORM_RDMA_ASSERT_LEVEL_SIZE (IRO[48].size) /* Ystorm error level for assert */ #define YSTORM_RDMA_ASSERT_LEVEL_OFFSET(pf_id) \ - (IRO[48].base + ((pf_id) * IRO[48].m1)) -#define YSTORM_RDMA_ASSERT_LEVEL_SIZE (IRO[48].size) + (IRO[49].base + ((pf_id) * IRO[49].m1)) +#define YSTORM_RDMA_ASSERT_LEVEL_SIZE (IRO[49].size) /* Pstorm error level for assert */ #define PSTORM_RDMA_ASSERT_LEVEL_OFFSET(pf_id) \ - (IRO[49].base + ((pf_id) * IRO[49].m1)) -#define PSTORM_RDMA_ASSERT_LEVEL_SIZE (IRO[49].size) + (IRO[50].base + ((pf_id) * IRO[50].m1)) +#define PSTORM_RDMA_ASSERT_LEVEL_SIZE (IRO[50].size) /* Tstorm error level for assert */ #define TSTORM_RDMA_ASSERT_LEVEL_OFFSET(pf_id) \ - (IRO[50].base + ((pf_id) * IRO[50].m1)) -#define TSTORM_RDMA_ASSERT_LEVEL_SIZE (IRO[50].size) + (IRO[51].base + ((pf_id) * IRO[51].m1)) +#define TSTORM_RDMA_ASSERT_LEVEL_SIZE (IRO[51].size) /* Mstorm error level for assert */ #define MSTORM_RDMA_ASSERT_LEVEL_OFFSET(pf_id) \ - (IRO[51].base + ((pf_id) * IRO[51].m1)) -#define MSTORM_RDMA_ASSERT_LEVEL_SIZE (IRO[51].size) + (IRO[52].base + ((pf_id) * IRO[52].m1)) +#define MSTORM_RDMA_ASSERT_LEVEL_SIZE (IRO[52].size) /* Ustorm error level for assert */ #define USTORM_RDMA_ASSERT_LEVEL_OFFSET(pf_id) \ - (IRO[52].base + ((pf_id) * IRO[52].m1)) -#define USTORM_RDMA_ASSERT_LEVEL_SIZE (IRO[52].size) + (IRO[53].base + ((pf_id) * IRO[53].m1)) +#define USTORM_RDMA_ASSERT_LEVEL_SIZE (IRO[53].size) /* Xstorm iWARP rxmit stats */ #define XSTORM_IWARP_RXMIT_STATS_OFFSET(pf_id) \ - (IRO[53].base + ((pf_id) * IRO[53].m1)) -#define XSTORM_IWARP_RXMIT_STATS_SIZE (IRO[53].size) + (IRO[54].base + ((pf_id) * IRO[54].m1)) +#define XSTORM_IWARP_RXMIT_STATS_SIZE (IRO[54].size) /* Tstorm RoCE Event Statistics */ #define TSTORM_ROCE_EVENTS_STAT_OFFSET(roce_pf_id) \ - (IRO[54].base + ((roce_pf_id) * IRO[54].m1)) -#define TSTORM_ROCE_EVENTS_STAT_SIZE (IRO[54].size) + (IRO[55].base + ((roce_pf_id) * IRO[55].m1)) +#define TSTORM_ROCE_EVENTS_STAT_SIZE (IRO[55].size) /* DCQCN Received Statistics */ #define YSTORM_ROCE_DCQCN_RECEIVED_STATS_OFFSET(roce_pf_id) \ - (IRO[55].base + ((roce_pf_id) * IRO[55].m1)) -#define YSTORM_ROCE_DCQCN_RECEIVED_STATS_SIZE (IRO[55].size) + (IRO[56].base + ((roce_pf_id) * IRO[56].m1)) +#define YSTORM_ROCE_DCQCN_RECEIVED_STATS_SIZE (IRO[56].size) /* RoCE Error Statistics */ #define YSTORM_ROCE_ERROR_STATS_OFFSET(roce_pf_id) \ - (IRO[56].base + ((roce_pf_id) * IRO[56].m1)) -#define YSTORM_ROCE_ERROR_STATS_SIZE (IRO[56].size) + (IRO[57].base + ((roce_pf_id) * IRO[57].m1)) +#define YSTORM_ROCE_ERROR_STATS_SIZE (IRO[57].size) /* DCQCN Sent Statistics */ #define PSTORM_ROCE_DCQCN_SENT_STATS_OFFSET(roce_pf_id) \ - (IRO[57].base + ((roce_pf_id) * IRO[57].m1)) -#define PSTORM_ROCE_DCQCN_SENT_STATS_SIZE (IRO[57].size) + (IRO[58].base + ((roce_pf_id) * IRO[58].m1)) +#define PSTORM_ROCE_DCQCN_SENT_STATS_SIZE (IRO[58].size) /* RoCE CQEs Statistics */ #define USTORM_ROCE_CQE_STATS_OFFSET(roce_pf_id) \ - (IRO[58].base + ((roce_pf_id) * IRO[58].m1)) -#define USTORM_ROCE_CQE_STATS_SIZE (IRO[58].size) + (IRO[59].base + ((roce_pf_id) * IRO[59].m1)) +#define USTORM_ROCE_CQE_STATS_SIZE (IRO[59].size) -static const struct iro iro_arr[59] = { +static const struct iro iro_arr[60] = { {0x0, 0x0, 0x0, 0x0, 0x8}, {0x4cb8, 0x88, 0x0, 0x0, 0x88}, {0x6530, 0x20, 0x0, 0x0, 0x20}, @@ -4461,14 +4536,14 @@ static const struct iro iro_arr[59] = { {0x84, 0x8, 0x0, 0x0, 0x2}, {0x4c48, 0x0, 0x0, 0x0, 0x78}, {0x3e38, 0x0, 0x0, 0x0, 0x78}, - {0x2b78, 0x0, 0x0, 0x0, 0x78}, + {0x3ef8, 0x0, 0x0, 0x0, 0x78}, {0x4c40, 0x0, 0x0, 0x0, 0x78}, {0x4998, 0x0, 0x0, 0x0, 0x78}, {0x7f50, 0x0, 0x0, 0x0, 0x78}, {0xa28, 0x8, 0x0, 0x0, 0x8}, {0x6210, 0x10, 0x0, 0x0, 0x10}, {0xb820, 0x30, 0x0, 0x0, 0x30}, - {0x96c0, 0x30, 0x0, 0x0, 0x30}, + {0xa990, 0x30, 0x0, 0x0, 0x30}, {0x4b68, 0x80, 0x0, 0x0, 0x40}, {0x1f8, 0x4, 0x0, 0x0, 0x4}, {0x53a8, 0x80, 0x4, 0x0, 0x4}, @@ -4476,11 +4551,12 @@ static const struct iro iro_arr[59] = { {0x4ba8, 0x80, 0x0, 0x0, 0x20}, {0x8158, 0x40, 0x0, 0x0, 0x30}, {0xe770, 0x60, 0x0, 0x0, 0x60}, - {0x2d10, 0x80, 0x0, 0x0, 0x38}, - {0xf2b8, 0x78, 0x0, 0x0, 0x78}, + {0x4090, 0x80, 0x0, 0x0, 0x38}, + {0xfea8, 0x78, 0x0, 0x0, 0x78}, {0x1f8, 0x4, 0x0, 0x0, 0x4}, {0xaf20, 0x0, 0x0, 0x0, 0xf0}, {0xb010, 0x8, 0x0, 0x0, 0x8}, + {0xc00, 0x8, 0x0, 0x0, 0x8}, {0x1f8, 0x8, 0x0, 0x0, 0x8}, {0xac0, 0x8, 0x0, 0x0, 0x8}, {0x2578, 0x8, 0x0, 0x0, 0x8}, @@ -4492,23 +4568,23 @@ static const struct iro iro_arr[59] = { {0x12908, 0x18, 0x0, 0x0, 0x10}, {0x11aa8, 0x40, 0x0, 0x0, 0x18}, {0xa588, 0x50, 0x0, 0x0, 0x20}, - {0x8700, 0x40, 0x0, 0x0, 0x28}, - {0x10300, 0x18, 0x0, 0x0, 0x10}, + {0x8f00, 0x40, 0x0, 0x0, 0x28}, + {0x10e30, 0x18, 0x0, 0x0, 0x10}, {0xde48, 0x48, 0x0, 0x0, 0x38}, - {0x10768, 0x20, 0x0, 0x0, 0x20}, - {0x2d48, 0x80, 0x0, 0x0, 0x10}, + {0x11298, 0x20, 0x0, 0x0, 0x20}, + {0x40c8, 0x80, 0x0, 0x0, 0x10}, {0x5048, 0x10, 0x0, 0x0, 0x10}, {0xc748, 0x8, 0x0, 0x0, 0x1}, - {0xa128, 0x8, 0x0, 0x0, 0x1}, - {0x10f00, 0x8, 0x0, 0x0, 0x1}, + {0xa928, 0x8, 0x0, 0x0, 0x1}, + {0x11a30, 0x8, 0x0, 0x0, 0x1}, {0xf030, 0x8, 0x0, 0x0, 0x1}, {0x13028, 0x8, 0x0, 0x0, 0x1}, {0x12c58, 0x8, 0x0, 0x0, 0x1}, {0xc9b8, 0x30, 0x0, 0x0, 0x10}, {0xed90, 0x28, 0x0, 0x0, 0x28}, - {0xa520, 0x18, 0x0, 0x0, 0x18}, - {0xa6a0, 0x8, 0x0, 0x0, 0x8}, - {0x13108, 0x8, 0x0, 0x0, 0x8}, + {0xad20, 0x18, 0x0, 0x0, 0x18}, + {0xaea0, 0x8, 0x0, 0x0, 0x8}, + {0x13c38, 0x8, 0x0, 0x0, 0x8}, {0x13c50, 0x18, 0x0, 0x0, 0x18}, }; @@ -5661,6 +5737,14 @@ enum eth_filter_type { MAX_ETH_FILTER_TYPE }; +/* inner to inner vlan priority translation configurations */ +struct eth_in_to_in_pri_map_cfg { + u8 inner_vlan_pri_remap_en; + u8 reserved[7]; + u8 non_rdma_in_to_in_pri_map[8]; + u8 rdma_in_to_in_pri_map[8]; +}; + /* Eth IPv4 Fragment Type */ enum eth_ipv4_frag_type { ETH_IPV4_NOT_FRAG, @@ -6018,6 +6102,14 @@ struct tx_queue_update_ramrod_data { struct regpair reserved1[5]; }; +/* Inner to Inner VLAN priority map update mode */ +enum update_in_to_in_pri_map_mode_enum { + ETH_IN_TO_IN_PRI_MAP_UPDATE_DISABLED, + ETH_IN_TO_IN_PRI_MAP_UPDATE_NON_RDMA_TBL, + ETH_IN_TO_IN_PRI_MAP_UPDATE_RDMA_TBL, + MAX_UPDATE_IN_TO_IN_PRI_MAP_MODE_ENUM +}; + /* Ramrod data for vport update ramrod */ struct vport_filter_update_ramrod_data { struct eth_filter_cmd_header filter_cmd_hdr; @@ -6048,7 +6140,8 @@ struct vport_start_ramrod_data { u8 zero_placement_offset; u8 ctl_frame_mac_check_en; u8 ctl_frame_ethtype_check_en; - u8 reserved[1]; + u8 wipe_inner_vlan_pri_en; + struct eth_in_to_in_pri_map_cfg in_to_in_vlan_pri_map_cfg; }; /* Ramrod data for vport stop ramrod */ @@ -6100,7 +6193,9 @@ struct vport_update_ramrod_data_cmn { u8 update_ctl_frame_checks_en_flg; u8 ctl_frame_mac_check_en; u8 ctl_frame_ethtype_check_en; - u8 reserved[15]; + u8 update_in_to_in_pri_map_mode; + u8 in_to_in_pri_map[8]; + u8 reserved[6]; }; struct vport_update_ramrod_mcast { @@ -6929,11 +7024,6 @@ struct mstorm_rdma_task_st_ctx { struct regpair temp[4]; }; -/* The roce task context of Ustorm */ -struct ustorm_rdma_task_st_ctx { - struct regpair temp[2]; -}; - struct e4_ustorm_rdma_task_ag_ctx { u8 reserved; u8 state; @@ -7007,8 +7097,6 @@ struct e4_rdma_task_context { struct e4_mstorm_rdma_task_ag_ctx mstorm_ag_context; struct mstorm_rdma_task_st_ctx mstorm_st_context; struct rdif_task_context rdif_context; - struct ustorm_rdma_task_st_ctx ustorm_st_context; - struct regpair ustorm_st_padding[2]; struct e4_ustorm_rdma_task_ag_ctx ustorm_ag_context; }; @@ -7388,7 +7476,7 @@ struct e4_ustorm_rdma_conn_ag_ctx { #define E4_USTORM_RDMA_CONN_AG_CTX_RULE8EN_MASK 0x1 #define E4_USTORM_RDMA_CONN_AG_CTX_RULE8EN_SHIFT 7 u8 byte2; - u8 byte3; + u8 nvmf_only; __le16 conn_dpi; __le16 word1; __le32 cq_cons; @@ -7831,7 +7919,12 @@ struct roce_create_qp_req_ramrod_data { struct regpair qp_handle_for_cqe; struct regpair qp_handle_for_async; u8 stats_counter_id; - u8 reserved3[7]; + u8 reserved3[6]; + u8 flags2; +#define ROCE_CREATE_QP_REQ_RAMROD_DATA_EDPM_MODE_MASK 0x1 +#define ROCE_CREATE_QP_REQ_RAMROD_DATA_EDPM_MODE_SHIFT 0 +#define ROCE_CREATE_QP_REQ_RAMROD_DATA_RESERVED_MASK 0x7F +#define ROCE_CREATE_QP_REQ_RAMROD_DATA_RESERVED_SHIFT 1 __le16 regular_latency_phy_queue; __le16 dpi; }; @@ -7954,6 +8047,7 @@ enum roce_event_opcode { ROCE_EVENT_DESTROY_QP, ROCE_EVENT_CREATE_UD_QP, ROCE_EVENT_DESTROY_UD_QP, + ROCE_EVENT_FUNC_UPDATE, MAX_ROCE_EVENT_OPCODE }; @@ -7962,7 +8056,13 @@ struct roce_init_func_params { u8 ll2_queue_id; u8 cnp_vlan_priority; u8 cnp_dscp; - u8 reserved; + u8 flags; +#define ROCE_INIT_FUNC_PARAMS_DCQCN_NP_EN_MASK 0x1 +#define ROCE_INIT_FUNC_PARAMS_DCQCN_NP_EN_SHIFT 0 +#define ROCE_INIT_FUNC_PARAMS_DCQCN_RP_EN_MASK 0x1 +#define ROCE_INIT_FUNC_PARAMS_DCQCN_RP_EN_SHIFT 1 +#define ROCE_INIT_FUNC_PARAMS_RESERVED0_MASK 0x3F +#define ROCE_INIT_FUNC_PARAMS_RESERVED0_SHIFT 2 __le32 cnp_send_timeout; __le16 rl_offset; u8 rl_count_log; @@ -8109,9 +8209,24 @@ enum roce_ramrod_cmd_id { ROCE_RAMROD_DESTROY_QP, ROCE_RAMROD_CREATE_UD_QP, ROCE_RAMROD_DESTROY_UD_QP, + ROCE_RAMROD_FUNC_UPDATE, MAX_ROCE_RAMROD_CMD_ID }; +/* RoCE func init ramrod data */ +struct roce_update_func_params { + u8 cnp_vlan_priority; + u8 cnp_dscp; + __le16 flags; +#define ROCE_UPDATE_FUNC_PARAMS_DCQCN_NP_EN_MASK 0x1 +#define ROCE_UPDATE_FUNC_PARAMS_DCQCN_NP_EN_SHIFT 0 +#define ROCE_UPDATE_FUNC_PARAMS_DCQCN_RP_EN_MASK 0x1 +#define ROCE_UPDATE_FUNC_PARAMS_DCQCN_RP_EN_SHIFT 1 +#define ROCE_UPDATE_FUNC_PARAMS_RESERVED0_MASK 0x3FFF +#define ROCE_UPDATE_FUNC_PARAMS_RESERVED0_SHIFT 2 + __le32 cnp_send_timeout; +}; + struct e4_xstorm_roce_conn_ag_ctx_dq_ext_ld_part { u8 reserved0; u8 state; @@ -12414,6 +12529,7 @@ struct public_drv_mb { #define DRV_MSG_SET_RESOURCE_VALUE_MSG 0x35000000 #define DRV_MSG_CODE_OV_UPDATE_WOL 0x38000000 #define DRV_MSG_CODE_OV_UPDATE_ESWITCH_MODE 0x39000000 +#define DRV_MSG_CODE_GET_OEM_UPDATES 0x41000000 #define DRV_MSG_CODE_BW_UPDATE_ACK 0x32000000 #define DRV_MSG_CODE_NIG_DRAIN 0x30000000 @@ -12541,6 +12657,9 @@ struct public_drv_mb { #define DRV_MB_PARAM_ESWITCH_MODE_VEB 0x1 #define DRV_MB_PARAM_ESWITCH_MODE_VEPA 0x2 +#define DRV_MB_PARAM_DUMMY_OEM_UPDATES_MASK 0x1 +#define DRV_MB_PARAM_DUMMY_OEM_UPDATES_OFFSET 0 + #define DRV_MB_PARAM_SET_LED_MODE_OPER 0x0 #define DRV_MB_PARAM_SET_LED_MODE_ON 0x1 #define DRV_MB_PARAM_SET_LED_MODE_OFF 0x2 diff --git a/drivers/net/ethernet/qlogic/qed/qed_mcp.c b/drivers/net/ethernet/qlogic/qed/qed_mcp.c index 5d37ec7e9b0b..58c7eb9d8e1b 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_mcp.c +++ b/drivers/net/ethernet/qlogic/qed/qed_mcp.c @@ -1581,13 +1581,29 @@ static void qed_mcp_update_stag(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt) p_hwfn->mcp_info->func_info.ovlan = (u16)shmem_info.ovlan_stag & FUNC_MF_CFG_OV_STAG_MASK; p_hwfn->hw_info.ovlan = p_hwfn->mcp_info->func_info.ovlan; - if ((p_hwfn->hw_info.hw_mode & BIT(MODE_MF_SD)) && - (p_hwfn->hw_info.ovlan != QED_MCP_VLAN_UNSET)) { - qed_wr(p_hwfn, p_ptt, - NIG_REG_LLH_FUNC_TAG_VALUE, p_hwfn->hw_info.ovlan); + if (test_bit(QED_MF_OVLAN_CLSS, &p_hwfn->cdev->mf_bits)) { + if (p_hwfn->hw_info.ovlan != QED_MCP_VLAN_UNSET) { + qed_wr(p_hwfn, p_ptt, NIG_REG_LLH_FUNC_TAG_VALUE, + p_hwfn->hw_info.ovlan); + qed_wr(p_hwfn, p_ptt, NIG_REG_LLH_FUNC_TAG_EN, 1); + + /* Configure DB to add external vlan to EDPM packets */ + qed_wr(p_hwfn, p_ptt, DORQ_REG_TAG1_OVRD_MODE, 1); + qed_wr(p_hwfn, p_ptt, DORQ_REG_PF_EXT_VID_BB_K2, + p_hwfn->hw_info.ovlan); + } else { + qed_wr(p_hwfn, p_ptt, NIG_REG_LLH_FUNC_TAG_EN, 0); + qed_wr(p_hwfn, p_ptt, NIG_REG_LLH_FUNC_TAG_VALUE, 0); + qed_wr(p_hwfn, p_ptt, DORQ_REG_TAG1_OVRD_MODE, 0); + qed_wr(p_hwfn, p_ptt, DORQ_REG_PF_EXT_VID_BB_K2, 0); + } + qed_sp_pf_update_stag(p_hwfn); } + DP_VERBOSE(p_hwfn, QED_MSG_SP, "ovlan = %d hw_mode = 0x%x\n", + p_hwfn->mcp_info->func_info.ovlan, p_hwfn->hw_info.hw_mode); + /* Acknowledge the MFW */ qed_mcp_cmd(p_hwfn, p_ptt, DRV_MSG_CODE_S_TAG_UPDATE_ACK, 0, &resp, ¶m); diff --git a/drivers/net/ethernet/qlogic/qed/qed_reg_addr.h b/drivers/net/ethernet/qlogic/qed/qed_reg_addr.h index f736f70956fd..2440970882c4 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_reg_addr.h +++ b/drivers/net/ethernet/qlogic/qed/qed_reg_addr.h @@ -216,6 +216,12 @@ 0x00c000UL #define DORQ_REG_IFEN \ 0x100040UL +#define DORQ_REG_TAG1_OVRD_MODE \ + 0x1008b4UL +#define DORQ_REG_PF_PCP_BB_K2 \ + 0x1008c4UL +#define DORQ_REG_PF_EXT_VID_BB_K2 \ + 0x1008c8UL #define DORQ_REG_DB_DROP_REASON \ 0x100a2cUL #define DORQ_REG_DB_DROP_DETAILS \ diff --git a/drivers/net/ethernet/qlogic/qede/qede.h b/drivers/net/ethernet/qlogic/qede/qede.h index 6a4d266fb8e2..de98a974673b 100644 --- a/drivers/net/ethernet/qlogic/qede/qede.h +++ b/drivers/net/ethernet/qlogic/qede/qede.h @@ -440,7 +440,7 @@ struct qede_fastpath { struct qede_tx_queue *txq; struct qede_tx_queue *xdp_tx; -#define VEC_NAME_SIZE (sizeof(((struct net_device *)0)->name) + 8) +#define VEC_NAME_SIZE (FIELD_SIZEOF(struct net_device, name) + 8) char name[VEC_NAME_SIZE]; }; diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sriov_common.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sriov_common.c index 77e386ebff09..f7c2f32237cb 100644 --- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sriov_common.c +++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sriov_common.c @@ -904,13 +904,11 @@ static void qlcnic_sriov_pull_bc_msg(struct qlcnic_adapter *adapter, u32 *hdr, u32 *pay, u32 size) { struct qlcnic_hardware_context *ahw = adapter->ahw; - u32 fw_mbx; u8 i, max = 2, hdr_size, j; hdr_size = (sizeof(struct qlcnic_bc_hdr) / sizeof(u32)); max = (size / sizeof(u32)) + hdr_size; - fw_mbx = readl(QLCNIC_MBX_FW(ahw, 0)); for (i = 2, j = 0; j < hdr_size; i++, j++) *(hdr++) = readl(QLCNIC_MBX_FW(ahw, i)); for (; j < max; i++, j++) @@ -936,7 +934,7 @@ static int __qlcnic_sriov_issue_bc_post(struct qlcnic_vf_info *vf) static int qlcnic_sriov_issue_bc_post(struct qlcnic_bc_trans *trans, u8 type) { struct qlcnic_vf_info *vf = trans->vf; - u32 pay_size, hdr_size; + u32 pay_size; u32 *hdr, *pay; int ret; u8 pci_func = trans->func_id; @@ -947,14 +945,12 @@ static int qlcnic_sriov_issue_bc_post(struct qlcnic_bc_trans *trans, u8 type) if (type == QLC_BC_COMMAND) { hdr = (u32 *)(trans->req_hdr + trans->curr_req_frag); pay = (u32 *)(trans->req_pay + trans->curr_req_frag); - hdr_size = (sizeof(struct qlcnic_bc_hdr) / sizeof(u32)); pay_size = qlcnic_sriov_get_bc_paysize(trans->req_pay_size, trans->curr_req_frag); pay_size = (pay_size / sizeof(u32)); } else { hdr = (u32 *)(trans->rsp_hdr + trans->curr_rsp_frag); pay = (u32 *)(trans->rsp_pay + trans->curr_rsp_frag); - hdr_size = (sizeof(struct qlcnic_bc_hdr) / sizeof(u32)); pay_size = qlcnic_sriov_get_bc_paysize(trans->rsp_pay_size, trans->curr_rsp_frag); pay_size = (pay_size / sizeof(u32)); diff --git a/drivers/net/ethernet/qualcomm/qca_7k.c b/drivers/net/ethernet/qualcomm/qca_7k.c index ffe7a16bdfc8..4292c89bd35c 100644 --- a/drivers/net/ethernet/qualcomm/qca_7k.c +++ b/drivers/net/ethernet/qualcomm/qca_7k.c @@ -45,34 +45,33 @@ qcaspi_read_register(struct qcaspi *qca, u16 reg, u16 *result) { __be16 rx_data; __be16 tx_data; - struct spi_transfer *transfer; - struct spi_message *msg; + struct spi_transfer transfer[2]; + struct spi_message msg; int ret; + memset(transfer, 0, sizeof(transfer)); + + spi_message_init(&msg); + tx_data = cpu_to_be16(QCA7K_SPI_READ | QCA7K_SPI_INTERNAL | reg); + *result = 0; + + transfer[0].tx_buf = &tx_data; + transfer[0].len = QCASPI_CMD_LEN; + transfer[1].rx_buf = &rx_data; + transfer[1].len = QCASPI_CMD_LEN; + + spi_message_add_tail(&transfer[0], &msg); if (qca->legacy_mode) { - msg = &qca->spi_msg1; - transfer = &qca->spi_xfer1; - transfer->tx_buf = &tx_data; - transfer->rx_buf = NULL; - transfer->len = QCASPI_CMD_LEN; - spi_sync(qca->spi_dev, msg); - } else { - msg = &qca->spi_msg2; - transfer = &qca->spi_xfer2[0]; - transfer->tx_buf = &tx_data; - transfer->rx_buf = NULL; - transfer->len = QCASPI_CMD_LEN; - transfer = &qca->spi_xfer2[1]; + spi_sync(qca->spi_dev, &msg); + spi_message_init(&msg); } - transfer->tx_buf = NULL; - transfer->rx_buf = &rx_data; - transfer->len = QCASPI_CMD_LEN; - ret = spi_sync(qca->spi_dev, msg); + spi_message_add_tail(&transfer[1], &msg); + ret = spi_sync(qca->spi_dev, &msg); if (!ret) - ret = msg->status; + ret = msg.status; if (ret) qcaspi_spi_error(qca); @@ -82,42 +81,69 @@ qcaspi_read_register(struct qcaspi *qca, u16 reg, u16 *result) return ret; } -int -qcaspi_write_register(struct qcaspi *qca, u16 reg, u16 value) +static int +__qcaspi_write_register(struct qcaspi *qca, u16 reg, u16 value) { __be16 tx_data[2]; - struct spi_transfer *transfer; - struct spi_message *msg; + struct spi_transfer transfer[2]; + struct spi_message msg; int ret; + memset(&transfer, 0, sizeof(transfer)); + + spi_message_init(&msg); + tx_data[0] = cpu_to_be16(QCA7K_SPI_WRITE | QCA7K_SPI_INTERNAL | reg); tx_data[1] = cpu_to_be16(value); + transfer[0].tx_buf = &tx_data[0]; + transfer[0].len = QCASPI_CMD_LEN; + transfer[1].tx_buf = &tx_data[1]; + transfer[1].len = QCASPI_CMD_LEN; + + spi_message_add_tail(&transfer[0], &msg); if (qca->legacy_mode) { - msg = &qca->spi_msg1; - transfer = &qca->spi_xfer1; - transfer->tx_buf = &tx_data[0]; - transfer->rx_buf = NULL; - transfer->len = QCASPI_CMD_LEN; - spi_sync(qca->spi_dev, msg); - } else { - msg = &qca->spi_msg2; - transfer = &qca->spi_xfer2[0]; - transfer->tx_buf = &tx_data[0]; - transfer->rx_buf = NULL; - transfer->len = QCASPI_CMD_LEN; - transfer = &qca->spi_xfer2[1]; + spi_sync(qca->spi_dev, &msg); + spi_message_init(&msg); } - transfer->tx_buf = &tx_data[1]; - transfer->rx_buf = NULL; - transfer->len = QCASPI_CMD_LEN; - ret = spi_sync(qca->spi_dev, msg); + spi_message_add_tail(&transfer[1], &msg); + ret = spi_sync(qca->spi_dev, &msg); if (!ret) - ret = msg->status; + ret = msg.status; if (ret) qcaspi_spi_error(qca); return ret; } + +int +qcaspi_write_register(struct qcaspi *qca, u16 reg, u16 value, int retry) +{ + int ret, i = 0; + u16 confirmed; + + do { + ret = __qcaspi_write_register(qca, reg, value); + if (ret) + return ret; + + if (!retry) + return 0; + + ret = qcaspi_read_register(qca, reg, &confirmed); + if (ret) + return ret; + + ret = confirmed != value; + if (!ret) + return 0; + + i++; + qca->stats.write_verify_failed++; + + } while (i <= retry); + + return ret; +} diff --git a/drivers/net/ethernet/qualcomm/qca_7k.h b/drivers/net/ethernet/qualcomm/qca_7k.h index 27124c2bb77a..356de8ec5d48 100644 --- a/drivers/net/ethernet/qualcomm/qca_7k.h +++ b/drivers/net/ethernet/qualcomm/qca_7k.h @@ -66,6 +66,6 @@ void qcaspi_spi_error(struct qcaspi *qca); int qcaspi_read_register(struct qcaspi *qca, u16 reg, u16 *result); -int qcaspi_write_register(struct qcaspi *qca, u16 reg, u16 value); +int qcaspi_write_register(struct qcaspi *qca, u16 reg, u16 value, int retry); #endif /* _QCA_7K_H */ diff --git a/drivers/net/ethernet/qualcomm/qca_debug.c b/drivers/net/ethernet/qualcomm/qca_debug.c index 51d89c86e60f..a9f1bc013364 100644 --- a/drivers/net/ethernet/qualcomm/qca_debug.c +++ b/drivers/net/ethernet/qualcomm/qca_debug.c @@ -60,6 +60,7 @@ static const char qcaspi_gstrings_stats[][ETH_GSTRING_LEN] = { "Write buffer misses", "Transmit ring full", "SPI errors", + "Write verify errors", }; #ifdef CONFIG_DEBUG_FS diff --git a/drivers/net/ethernet/qualcomm/qca_spi.c b/drivers/net/ethernet/qualcomm/qca_spi.c index 206f0266463e..d5310504f436 100644 --- a/drivers/net/ethernet/qualcomm/qca_spi.c +++ b/drivers/net/ethernet/qualcomm/qca_spi.c @@ -69,6 +69,12 @@ static int qcaspi_pluggable = QCASPI_PLUGGABLE_MIN; module_param(qcaspi_pluggable, int, 0); MODULE_PARM_DESC(qcaspi_pluggable, "Pluggable SPI connection (yes/no)."); +#define QCASPI_WRITE_VERIFY_MIN 0 +#define QCASPI_WRITE_VERIFY_MAX 3 +static int wr_verify = QCASPI_WRITE_VERIFY_MIN; +module_param(wr_verify, int, 0); +MODULE_PARM_DESC(wr_verify, "SPI register write verify trails. Use 0-3."); + #define QCASPI_TX_TIMEOUT (1 * HZ) #define QCASPI_QCA7K_REBOOT_TIME_MS 1000 @@ -77,7 +83,7 @@ start_spi_intr_handling(struct qcaspi *qca, u16 *intr_cause) { *intr_cause = 0; - qcaspi_write_register(qca, SPI_REG_INTR_ENABLE, 0); + qcaspi_write_register(qca, SPI_REG_INTR_ENABLE, 0, wr_verify); qcaspi_read_register(qca, SPI_REG_INTR_CAUSE, intr_cause); netdev_dbg(qca->net_dev, "interrupts: 0x%04x\n", *intr_cause); } @@ -90,8 +96,8 @@ end_spi_intr_handling(struct qcaspi *qca, u16 intr_cause) SPI_INT_RDBUF_ERR | SPI_INT_WRBUF_ERR); - qcaspi_write_register(qca, SPI_REG_INTR_CAUSE, intr_cause); - qcaspi_write_register(qca, SPI_REG_INTR_ENABLE, intr_enable); + qcaspi_write_register(qca, SPI_REG_INTR_CAUSE, intr_cause, 0); + qcaspi_write_register(qca, SPI_REG_INTR_ENABLE, intr_enable, wr_verify); netdev_dbg(qca->net_dev, "acking int: 0x%04x\n", intr_cause); } @@ -99,22 +105,24 @@ static u32 qcaspi_write_burst(struct qcaspi *qca, u8 *src, u32 len) { __be16 cmd; - struct spi_message *msg = &qca->spi_msg2; - struct spi_transfer *transfer = &qca->spi_xfer2[0]; + struct spi_message msg; + struct spi_transfer transfer[2]; int ret; + memset(&transfer, 0, sizeof(transfer)); + spi_message_init(&msg); + cmd = cpu_to_be16(QCA7K_SPI_WRITE | QCA7K_SPI_EXTERNAL); - transfer->tx_buf = &cmd; - transfer->rx_buf = NULL; - transfer->len = QCASPI_CMD_LEN; - transfer = &qca->spi_xfer2[1]; - transfer->tx_buf = src; - transfer->rx_buf = NULL; - transfer->len = len; + transfer[0].tx_buf = &cmd; + transfer[0].len = QCASPI_CMD_LEN; + transfer[1].tx_buf = src; + transfer[1].len = len; - ret = spi_sync(qca->spi_dev, msg); + spi_message_add_tail(&transfer[0], &msg); + spi_message_add_tail(&transfer[1], &msg); + ret = spi_sync(qca->spi_dev, &msg); - if (ret || (msg->actual_length != QCASPI_CMD_LEN + len)) { + if (ret || (msg.actual_length != QCASPI_CMD_LEN + len)) { qcaspi_spi_error(qca); return 0; } @@ -125,17 +133,20 @@ qcaspi_write_burst(struct qcaspi *qca, u8 *src, u32 len) static u32 qcaspi_write_legacy(struct qcaspi *qca, u8 *src, u32 len) { - struct spi_message *msg = &qca->spi_msg1; - struct spi_transfer *transfer = &qca->spi_xfer1; + struct spi_message msg; + struct spi_transfer transfer; int ret; - transfer->tx_buf = src; - transfer->rx_buf = NULL; - transfer->len = len; + memset(&transfer, 0, sizeof(transfer)); + spi_message_init(&msg); - ret = spi_sync(qca->spi_dev, msg); + transfer.tx_buf = src; + transfer.len = len; - if (ret || (msg->actual_length != len)) { + spi_message_add_tail(&transfer, &msg); + ret = spi_sync(qca->spi_dev, &msg); + + if (ret || (msg.actual_length != len)) { qcaspi_spi_error(qca); return 0; } @@ -146,23 +157,25 @@ qcaspi_write_legacy(struct qcaspi *qca, u8 *src, u32 len) static u32 qcaspi_read_burst(struct qcaspi *qca, u8 *dst, u32 len) { - struct spi_message *msg = &qca->spi_msg2; + struct spi_message msg; __be16 cmd; - struct spi_transfer *transfer = &qca->spi_xfer2[0]; + struct spi_transfer transfer[2]; int ret; + memset(&transfer, 0, sizeof(transfer)); + spi_message_init(&msg); + cmd = cpu_to_be16(QCA7K_SPI_READ | QCA7K_SPI_EXTERNAL); - transfer->tx_buf = &cmd; - transfer->rx_buf = NULL; - transfer->len = QCASPI_CMD_LEN; - transfer = &qca->spi_xfer2[1]; - transfer->tx_buf = NULL; - transfer->rx_buf = dst; - transfer->len = len; + transfer[0].tx_buf = &cmd; + transfer[0].len = QCASPI_CMD_LEN; + transfer[1].rx_buf = dst; + transfer[1].len = len; - ret = spi_sync(qca->spi_dev, msg); + spi_message_add_tail(&transfer[0], &msg); + spi_message_add_tail(&transfer[1], &msg); + ret = spi_sync(qca->spi_dev, &msg); - if (ret || (msg->actual_length != QCASPI_CMD_LEN + len)) { + if (ret || (msg.actual_length != QCASPI_CMD_LEN + len)) { qcaspi_spi_error(qca); return 0; } @@ -173,17 +186,20 @@ qcaspi_read_burst(struct qcaspi *qca, u8 *dst, u32 len) static u32 qcaspi_read_legacy(struct qcaspi *qca, u8 *dst, u32 len) { - struct spi_message *msg = &qca->spi_msg1; - struct spi_transfer *transfer = &qca->spi_xfer1; + struct spi_message msg; + struct spi_transfer transfer; int ret; - transfer->tx_buf = NULL; - transfer->rx_buf = dst; - transfer->len = len; + memset(&transfer, 0, sizeof(transfer)); + spi_message_init(&msg); - ret = spi_sync(qca->spi_dev, msg); + transfer.rx_buf = dst; + transfer.len = len; - if (ret || (msg->actual_length != len)) { + spi_message_add_tail(&transfer, &msg); + ret = spi_sync(qca->spi_dev, &msg); + + if (ret || (msg.actual_length != len)) { qcaspi_spi_error(qca); return 0; } @@ -195,19 +211,23 @@ static int qcaspi_tx_cmd(struct qcaspi *qca, u16 cmd) { __be16 tx_data; - struct spi_message *msg = &qca->spi_msg1; - struct spi_transfer *transfer = &qca->spi_xfer1; + struct spi_message msg; + struct spi_transfer transfer; int ret; + memset(&transfer, 0, sizeof(transfer)); + + spi_message_init(&msg); + tx_data = cpu_to_be16(cmd); - transfer->len = sizeof(tx_data); - transfer->tx_buf = &tx_data; - transfer->rx_buf = NULL; + transfer.len = sizeof(cmd); + transfer.tx_buf = &tx_data; + spi_message_add_tail(&transfer, &msg); - ret = spi_sync(qca->spi_dev, msg); + ret = spi_sync(qca->spi_dev, &msg); if (!ret) - ret = msg->status; + ret = msg.status; if (ret) qcaspi_spi_error(qca); @@ -225,7 +245,7 @@ qcaspi_tx_frame(struct qcaspi *qca, struct sk_buff *skb) len = skb->len; - qcaspi_write_register(qca, SPI_REG_BFR_SIZE, len); + qcaspi_write_register(qca, SPI_REG_BFR_SIZE, len, wr_verify); if (qca->legacy_mode) qcaspi_tx_cmd(qca, QCA7K_SPI_WRITE | QCA7K_SPI_EXTERNAL); @@ -331,6 +351,7 @@ qcaspi_receive(struct qcaspi *qca) /* Read the packet size. */ qcaspi_read_register(qca, SPI_REG_RDBUF_BYTE_AVA, &available); + netdev_dbg(net_dev, "qcaspi_receive: SPI_REG_RDBUF_BYTE_AVA: Value: %08x\n", available); @@ -339,7 +360,7 @@ qcaspi_receive(struct qcaspi *qca) return -1; } - qcaspi_write_register(qca, SPI_REG_BFR_SIZE, available); + qcaspi_write_register(qca, SPI_REG_BFR_SIZE, available, wr_verify); if (qca->legacy_mode) qcaspi_tx_cmd(qca, QCA7K_SPI_READ | QCA7K_SPI_EXTERNAL); @@ -510,7 +531,7 @@ qcaspi_qca7k_sync(struct qcaspi *qca, int event) netdev_dbg(qca->net_dev, "sync: resetting device.\n"); qcaspi_read_register(qca, SPI_REG_SPI_CONFIG, &spi_config); spi_config |= QCASPI_SLAVE_RESET_BIT; - qcaspi_write_register(qca, SPI_REG_SPI_CONFIG, spi_config); + qcaspi_write_register(qca, SPI_REG_SPI_CONFIG, spi_config, 0); qca->sync = QCASPI_SYNC_RESET; qca->stats.trig_reset++; @@ -670,7 +691,7 @@ qcaspi_netdev_close(struct net_device *dev) netif_stop_queue(dev); - qcaspi_write_register(qca, SPI_REG_INTR_ENABLE, 0); + qcaspi_write_register(qca, SPI_REG_INTR_ENABLE, 0, wr_verify); free_irq(qca->spi_dev->irq, qca); kthread_stop(qca->spi_thread); @@ -835,16 +856,6 @@ qcaspi_netdev_setup(struct net_device *dev) qca = netdev_priv(dev); memset(qca, 0, sizeof(struct qcaspi)); - memset(&qca->spi_xfer1, 0, sizeof(struct spi_transfer)); - memset(&qca->spi_xfer2, 0, sizeof(struct spi_transfer) * 2); - - spi_message_init(&qca->spi_msg1); - spi_message_add_tail(&qca->spi_xfer1, &qca->spi_msg1); - - spi_message_init(&qca->spi_msg2); - spi_message_add_tail(&qca->spi_xfer2[0], &qca->spi_msg2); - spi_message_add_tail(&qca->spi_xfer2[1], &qca->spi_msg2); - memset(&qca->txr, 0, sizeof(qca->txr)); qca->txr.count = TX_RING_MAX_LEN; } @@ -900,6 +911,13 @@ qca_spi_probe(struct spi_device *spi) return -EINVAL; } + if (wr_verify < QCASPI_WRITE_VERIFY_MIN || + wr_verify > QCASPI_WRITE_VERIFY_MAX) { + dev_err(&spi->dev, "Invalid write verify: %d\n", + wr_verify); + return -EINVAL; + } + dev_info(&spi->dev, "ver=%s, clkspeed=%d, burst_len=%d, pluggable=%d\n", QCASPI_DRV_VERSION, qcaspi_clkspeed, diff --git a/drivers/net/ethernet/qualcomm/qca_spi.h b/drivers/net/ethernet/qualcomm/qca_spi.h index fc4beb1b32d1..2d2c49726492 100644 --- a/drivers/net/ethernet/qualcomm/qca_spi.h +++ b/drivers/net/ethernet/qualcomm/qca_spi.h @@ -73,6 +73,7 @@ struct qcaspi_stats { u64 write_buf_miss; u64 ring_full; u64 spi_err; + u64 write_verify_failed; }; struct qcaspi { @@ -83,11 +84,6 @@ struct qcaspi { struct tx_ring txr; struct qcaspi_stats stats; - struct spi_message spi_msg1; - struct spi_message spi_msg2; - struct spi_transfer spi_xfer1; - struct spi_transfer spi_xfer2[2]; - u8 *rx_buffer; u32 buffer_size; u8 sync; diff --git a/drivers/net/ethernet/rdc/r6040.c b/drivers/net/ethernet/rdc/r6040.c index aa11b70b9ca4..04aa592f35c3 100644 --- a/drivers/net/ethernet/rdc/r6040.c +++ b/drivers/net/ethernet/rdc/r6040.c @@ -1024,16 +1024,8 @@ static int r6040_mii_probe(struct net_device *dev) return PTR_ERR(phydev); } - /* mask with MAC supported features */ - phydev->supported &= (SUPPORTED_10baseT_Half - | SUPPORTED_10baseT_Full - | SUPPORTED_100baseT_Half - | SUPPORTED_100baseT_Full - | SUPPORTED_Autoneg - | SUPPORTED_MII - | SUPPORTED_TP); - - phydev->advertising = phydev->supported; + phy_set_max_speed(phydev, SPEED_100); + lp->old_link = 0; lp->old_duplex = -1; diff --git a/drivers/net/ethernet/realtek/r8169.c b/drivers/net/ethernet/realtek/r8169.c index b08d51bf7a20..ed8ffd498c88 100644 --- a/drivers/net/ethernet/realtek/r8169.c +++ b/drivers/net/ethernet/realtek/r8169.c @@ -13,6 +13,7 @@ #include <linux/pci.h> #include <linux/netdevice.h> #include <linux/etherdevice.h> +#include <linux/clk.h> #include <linux/delay.h> #include <linux/ethtool.h> #include <linux/phy.h> @@ -76,8 +77,6 @@ static const int multicast_filter_limit = 32; #define R8169_TX_RING_BYTES (NUM_TX_DESC * sizeof(struct TxDesc)) #define R8169_RX_RING_BYTES (NUM_RX_DESC * sizeof(struct RxDesc)) -#define RTL8169_TX_TIMEOUT (6*HZ) - /* write/read MMIO register */ #define RTL_W8(tp, reg, val8) writeb((val8), tp->mmio_addr + (reg)) #define RTL_W16(tp, reg, val16) writew((val16), tp->mmio_addr + (reg)) @@ -631,7 +630,7 @@ struct rtl8169_tc_offsets { }; enum rtl_flag { - RTL_FLAG_TASK_ENABLED, + RTL_FLAG_TASK_ENABLED = 0, RTL_FLAG_TASK_SLOW_PENDING, RTL_FLAG_TASK_RESET_PENDING, RTL_FLAG_MAX @@ -665,6 +664,7 @@ struct rtl8169_private { u16 event_slow; const struct rtl_coalesce_info *coalesce_info; + struct clk *clk; struct mdio_ops { void (*write)(struct rtl8169_private *, int, int); @@ -1352,7 +1352,8 @@ static void rtl_irq_enable_all(struct rtl8169_private *tp) static void rtl8169_irq_mask_and_ack(struct rtl8169_private *tp) { rtl_irq_disable(tp); - rtl_ack_events(tp, RTL_EVENT_NAPI | tp->event_slow); + rtl_ack_events(tp, 0xffff); + /* PCI commit */ RTL_R8(tp, ChipCmd); } @@ -4046,29 +4047,26 @@ static void rtl8169_init_phy(struct net_device *dev, struct rtl8169_private *tp) rtl_hw_phy_config(dev); if (tp->mac_version <= RTL_GIGA_MAC_VER_06) { - netif_dbg(tp, drv, dev, - "Set MAC Reg C+CR Offset 0x82h = 0x01h\n"); - RTL_W8(tp, 0x82, 0x01); - } - - pci_write_config_byte(tp->pci_dev, PCI_LATENCY_TIMER, 0x40); - - if (tp->mac_version <= RTL_GIGA_MAC_VER_06) + pci_write_config_byte(tp->pci_dev, PCI_LATENCY_TIMER, 0x40); pci_write_config_byte(tp->pci_dev, PCI_CACHE_LINE_SIZE, 0x08); - - if (tp->mac_version == RTL_GIGA_MAC_VER_02) { netif_dbg(tp, drv, dev, "Set MAC Reg C+CR Offset 0x82h = 0x01h\n"); RTL_W8(tp, 0x82, 0x01); - netif_dbg(tp, drv, dev, - "Set PHY Reg 0x0bh = 0x00h\n"); - rtl_writephy(tp, 0x0b, 0x0000); //w 0x0b 15 0 0 } /* We may have called phy_speed_down before */ phy_speed_up(dev->phydev); genphy_soft_reset(dev->phydev); + + /* It was reported that chip version 33 ends up with 10MBit/Half on a + * 1GBit link after resuming from S3. For whatever reason the PHY on + * this chip doesn't properly start a renegotiation when soft-reset. + * Explicitly requesting a renegotiation fixes this. + */ + if (tp->mac_version == RTL_GIGA_MAC_VER_33 && + dev->phydev->autoneg == AUTONEG_ENABLE) + phy_restart_aneg(dev->phydev); } static void rtl_rar_set(struct rtl8169_private *tp, u8 *addr) @@ -4634,13 +4632,13 @@ static void rtl_hw_start(struct rtl8169_private *tp) rtl_set_rx_max_size(tp); rtl_set_rx_tx_desc_registers(tp); - rtl_set_tx_config_registers(tp); RTL_W8(tp, Cfg9346, Cfg9346_Lock); /* Initially a 10 us delay. Turned it into a PCI commit. - FR */ RTL_R8(tp, IntrMask); RTL_W8(tp, ChipCmd, CmdTxEnb | CmdRxEnb); rtl_init_rxcfg(tp); + rtl_set_tx_config_registers(tp); rtl_set_rx_mode(tp->dev); /* no early-rx interrupts */ @@ -4775,12 +4773,14 @@ static void rtl_pcie_state_l2l3_enable(struct rtl8169_private *tp, bool enable) static void rtl_hw_aspm_clkreq_enable(struct rtl8169_private *tp, bool enable) { if (enable) { - RTL_W8(tp, Config2, RTL_R8(tp, Config2) | ClkReqEn); RTL_W8(tp, Config5, RTL_R8(tp, Config5) | ASPM_en); + RTL_W8(tp, Config2, RTL_R8(tp, Config2) | ClkReqEn); } else { RTL_W8(tp, Config2, RTL_R8(tp, Config2) & ~ClkReqEn); RTL_W8(tp, Config5, RTL_R8(tp, Config5) & ~ASPM_en); } + + udelay(10); } static void rtl_hw_start_8168bb(struct rtl8169_private *tp) @@ -5625,6 +5625,8 @@ static void rtl_hw_start_8402(struct rtl8169_private *tp) static void rtl_hw_start_8106(struct rtl8169_private *tp) { + rtl_hw_aspm_clkreq_enable(tp, false); + /* Force LAN exit from ASPM if Rx/Tx are not idle */ RTL_W32(tp, FuncEvent, RTL_R32(tp, FuncEvent) | 0x002800); @@ -5633,6 +5635,7 @@ static void rtl_hw_start_8106(struct rtl8169_private *tp) RTL_W8(tp, DLLPR, RTL_R8(tp, DLLPR) & ~PFM_EN); rtl_pcie_state_l2l3_enable(tp, false); + rtl_hw_aspm_clkreq_enable(tp, true); } static void rtl_hw_start_8101(struct rtl8169_private *tp) @@ -6655,7 +6658,8 @@ static int rtl8169_close(struct net_device *dev) rtl8169_update_counters(tp); rtl_lock_work(tp); - clear_bit(RTL_FLAG_TASK_ENABLED, tp->wk.flags); + /* Clear all task flags */ + bitmap_zero(tp->wk.flags, RTL_FLAG_MAX); rtl8169_down(dev); rtl_unlock_work(tp); @@ -6838,7 +6842,9 @@ static void rtl8169_net_suspend(struct net_device *dev) rtl_lock_work(tp); napi_disable(&tp->napi); - clear_bit(RTL_FLAG_TASK_ENABLED, tp->wk.flags); + /* Clear all task flags */ + bitmap_zero(tp->wk.flags, RTL_FLAG_MAX); + rtl_unlock_work(tp); rtl_pll_power_down(tp); @@ -7254,6 +7260,11 @@ static int rtl_jumbo_max(struct rtl8169_private *tp) } } +static void rtl_disable_clk(void *data) +{ + clk_disable_unprepare(data); +} + static int rtl_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) { const struct rtl_cfg_info *cfg = rtl_cfg_infos + ent->driver_data; @@ -7274,6 +7285,32 @@ static int rtl_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) tp->msg_enable = netif_msg_init(debug.msg_enable, R8169_MSG_DEFAULT); tp->supports_gmii = cfg->has_gmii; + /* Get the *optional* external "ether_clk" used on some boards */ + tp->clk = devm_clk_get(&pdev->dev, "ether_clk"); + if (IS_ERR(tp->clk)) { + rc = PTR_ERR(tp->clk); + if (rc == -ENOENT) { + /* clk-core allows NULL (for suspend / resume) */ + tp->clk = NULL; + } else if (rc == -EPROBE_DEFER) { + return rc; + } else { + dev_err(&pdev->dev, "failed to get clk: %d\n", rc); + return rc; + } + } else { + rc = clk_prepare_enable(tp->clk); + if (rc) { + dev_err(&pdev->dev, "failed to enable clk: %d\n", rc); + return rc; + } + + rc = devm_add_action_or_reset(&pdev->dev, rtl_disable_clk, + tp->clk); + if (rc) + return rc; + } + /* enable device (incl. PCI PM wakeup and hotplug setup) */ rc = pcim_enable_device(pdev); if (rc < 0) { @@ -7318,11 +7355,9 @@ static int rtl_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) tp->cp_cmd = RTL_R16(tp, CPlusCmd); - if ((sizeof(dma_addr_t) > 4) && - (use_dac == 1 || (use_dac == -1 && pci_is_pcie(pdev) && - tp->mac_version >= RTL_GIGA_MAC_VER_18)) && - !pci_set_dma_mask(pdev, DMA_BIT_MASK(64)) && - !pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(64))) { + if (sizeof(dma_addr_t) > 4 && (use_dac == 1 || (use_dac == -1 && + tp->mac_version >= RTL_GIGA_MAC_VER_18)) && + !dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(64))) { /* CPlusCmd Dual Access Cycle is only needed for non-PCIe */ if (!pci_is_pcie(pdev)) @@ -7338,14 +7373,12 @@ static int rtl_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) rtl_init_rxcfg(tp); - rtl_irq_disable(tp); + rtl8169_irq_mask_and_ack(tp); rtl_hw_initialize(tp); rtl_hw_reset(tp); - rtl_ack_events(tp, 0xffff); - pci_set_master(pdev); rtl_init_mdio_ops(tp); @@ -7385,7 +7418,6 @@ static int rtl_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) dev->dev_addr[i] = RTL_R8(tp, MAC0 + i); dev->ethtool_ops = &rtl8169_ethtool_ops; - dev->watchdog_timeo = RTL8169_TX_TIMEOUT; netif_napi_add(dev, &tp->napi, rtl8169_poll, NAPI_POLL_WEIGHT); diff --git a/drivers/net/ethernet/renesas/Kconfig b/drivers/net/ethernet/renesas/Kconfig index f3f7477043ce..bb0ebdfd4459 100644 --- a/drivers/net/ethernet/renesas/Kconfig +++ b/drivers/net/ethernet/renesas/Kconfig @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0 # # Renesas device configuration # diff --git a/drivers/net/ethernet/renesas/Makefile b/drivers/net/ethernet/renesas/Makefile index a05102a7df02..f21ab8c02af0 100644 --- a/drivers/net/ethernet/renesas/Makefile +++ b/drivers/net/ethernet/renesas/Makefile @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0 # # Makefile for the Renesas device drivers. # diff --git a/drivers/net/ethernet/renesas/ravb.h b/drivers/net/ethernet/renesas/ravb.h index 1470fc12282b..1c6e4df94f01 100644 --- a/drivers/net/ethernet/renesas/ravb.h +++ b/drivers/net/ethernet/renesas/ravb.h @@ -428,6 +428,7 @@ enum EIS_BIT { EIS_CULF1 = 0x00000080, EIS_TFFF = 0x00000100, EIS_QFS = 0x00010000, + EIS_RESERVED = (GENMASK(31, 17) | GENMASK(15, 11)), }; /* RIC0 */ @@ -472,6 +473,7 @@ enum RIS0_BIT { RIS0_FRF15 = 0x00008000, RIS0_FRF16 = 0x00010000, RIS0_FRF17 = 0x00020000, + RIS0_RESERVED = GENMASK(31, 18), }; /* RIC1 */ @@ -528,6 +530,7 @@ enum RIS2_BIT { RIS2_QFF16 = 0x00010000, RIS2_QFF17 = 0x00020000, RIS2_RFFF = 0x80000000, + RIS2_RESERVED = GENMASK(30, 18), }; /* TIC */ @@ -544,6 +547,7 @@ enum TIS_BIT { TIS_FTF1 = 0x00000002, /* Undocumented? */ TIS_TFUF = 0x00000100, TIS_TFWF = 0x00000200, + TIS_RESERVED = (GENMASK(31, 20) | GENMASK(15, 12) | GENMASK(7, 4)) }; /* ISS */ @@ -617,6 +621,7 @@ enum GIC_BIT { enum GIS_BIT { GIS_PTCF = 0x00000001, /* Undocumented? */ GIS_PTMF = 0x00000004, + GIS_RESERVED = GENMASK(15, 10), }; /* GIE (R-Car Gen3 only) */ @@ -954,7 +959,10 @@ enum RAVB_QUEUE { #define RX_QUEUE_OFFSET 4 #define NUM_RX_QUEUE 2 #define NUM_TX_QUEUE 2 -#define NUM_TX_DESC 2 /* TX descriptors per packet */ + +/* TX descriptors per packet */ +#define NUM_TX_DESC_GEN2 2 +#define NUM_TX_DESC_GEN3 1 struct ravb_tstamp_skb { struct list_head list; @@ -1033,6 +1041,7 @@ struct ravb_private { unsigned no_avb_link:1; unsigned avb_link_active_low:1; unsigned wol_enabled:1; + int num_tx_desc; /* TX descriptors per packet */ }; static inline u32 ravb_read(struct net_device *ndev, enum ravb_reg reg) diff --git a/drivers/net/ethernet/renesas/ravb_main.c b/drivers/net/ethernet/renesas/ravb_main.c index aff5516b781e..defed0d0c51d 100644 --- a/drivers/net/ethernet/renesas/ravb_main.c +++ b/drivers/net/ethernet/renesas/ravb_main.c @@ -182,6 +182,7 @@ static int ravb_tx_free(struct net_device *ndev, int q, bool free_txed_only) { struct ravb_private *priv = netdev_priv(ndev); struct net_device_stats *stats = &priv->stats[q]; + int num_tx_desc = priv->num_tx_desc; struct ravb_tx_desc *desc; int free_num = 0; int entry; @@ -191,7 +192,7 @@ static int ravb_tx_free(struct net_device *ndev, int q, bool free_txed_only) bool txed; entry = priv->dirty_tx[q] % (priv->num_tx_ring[q] * - NUM_TX_DESC); + num_tx_desc); desc = &priv->tx_ring[q][entry]; txed = desc->die_dt == DT_FEMPTY; if (free_txed_only && !txed) @@ -200,12 +201,12 @@ static int ravb_tx_free(struct net_device *ndev, int q, bool free_txed_only) dma_rmb(); size = le16_to_cpu(desc->ds_tagl) & TX_DS; /* Free the original skb. */ - if (priv->tx_skb[q][entry / NUM_TX_DESC]) { + if (priv->tx_skb[q][entry / num_tx_desc]) { dma_unmap_single(ndev->dev.parent, le32_to_cpu(desc->dptr), size, DMA_TO_DEVICE); /* Last packet descriptor? */ - if (entry % NUM_TX_DESC == NUM_TX_DESC - 1) { - entry /= NUM_TX_DESC; + if (entry % num_tx_desc == num_tx_desc - 1) { + entry /= num_tx_desc; dev_kfree_skb_any(priv->tx_skb[q][entry]); priv->tx_skb[q][entry] = NULL; if (txed) @@ -224,6 +225,7 @@ static int ravb_tx_free(struct net_device *ndev, int q, bool free_txed_only) static void ravb_ring_free(struct net_device *ndev, int q) { struct ravb_private *priv = netdev_priv(ndev); + int num_tx_desc = priv->num_tx_desc; int ring_size; int i; @@ -249,7 +251,7 @@ static void ravb_ring_free(struct net_device *ndev, int q) ravb_tx_free(ndev, q, false); ring_size = sizeof(struct ravb_tx_desc) * - (priv->num_tx_ring[q] * NUM_TX_DESC + 1); + (priv->num_tx_ring[q] * num_tx_desc + 1); dma_free_coherent(ndev->dev.parent, ring_size, priv->tx_ring[q], priv->tx_desc_dma[q]); priv->tx_ring[q] = NULL; @@ -278,12 +280,13 @@ static void ravb_ring_free(struct net_device *ndev, int q) static void ravb_ring_format(struct net_device *ndev, int q) { struct ravb_private *priv = netdev_priv(ndev); + int num_tx_desc = priv->num_tx_desc; struct ravb_ex_rx_desc *rx_desc; struct ravb_tx_desc *tx_desc; struct ravb_desc *desc; int rx_ring_size = sizeof(*rx_desc) * priv->num_rx_ring[q]; int tx_ring_size = sizeof(*tx_desc) * priv->num_tx_ring[q] * - NUM_TX_DESC; + num_tx_desc; dma_addr_t dma_addr; int i; @@ -318,8 +321,10 @@ static void ravb_ring_format(struct net_device *ndev, int q) for (i = 0, tx_desc = priv->tx_ring[q]; i < priv->num_tx_ring[q]; i++, tx_desc++) { tx_desc->die_dt = DT_EEMPTY; - tx_desc++; - tx_desc->die_dt = DT_EEMPTY; + if (num_tx_desc > 1) { + tx_desc++; + tx_desc->die_dt = DT_EEMPTY; + } } tx_desc->dptr = cpu_to_le32((u32)priv->tx_desc_dma[q]); tx_desc->die_dt = DT_LINKFIX; /* type */ @@ -339,6 +344,7 @@ static void ravb_ring_format(struct net_device *ndev, int q) static int ravb_ring_init(struct net_device *ndev, int q) { struct ravb_private *priv = netdev_priv(ndev); + int num_tx_desc = priv->num_tx_desc; struct sk_buff *skb; int ring_size; int i; @@ -362,11 +368,13 @@ static int ravb_ring_init(struct net_device *ndev, int q) priv->rx_skb[q][i] = skb; } - /* Allocate rings for the aligned buffers */ - priv->tx_align[q] = kmalloc(DPTR_ALIGN * priv->num_tx_ring[q] + - DPTR_ALIGN - 1, GFP_KERNEL); - if (!priv->tx_align[q]) - goto error; + if (num_tx_desc > 1) { + /* Allocate rings for the aligned buffers */ + priv->tx_align[q] = kmalloc(DPTR_ALIGN * priv->num_tx_ring[q] + + DPTR_ALIGN - 1, GFP_KERNEL); + if (!priv->tx_align[q]) + goto error; + } /* Allocate all RX descriptors. */ ring_size = sizeof(struct ravb_ex_rx_desc) * (priv->num_rx_ring[q] + 1); @@ -380,7 +388,7 @@ static int ravb_ring_init(struct net_device *ndev, int q) /* Allocate all TX descriptors. */ ring_size = sizeof(struct ravb_tx_desc) * - (priv->num_tx_ring[q] * NUM_TX_DESC + 1); + (priv->num_tx_ring[q] * num_tx_desc + 1); priv->tx_ring[q] = dma_alloc_coherent(ndev->dev.parent, ring_size, &priv->tx_desc_dma[q], GFP_KERNEL); @@ -739,10 +747,11 @@ static void ravb_error_interrupt(struct net_device *ndev) u32 eis, ris2; eis = ravb_read(ndev, EIS); - ravb_write(ndev, ~EIS_QFS, EIS); + ravb_write(ndev, ~(EIS_QFS | EIS_RESERVED), EIS); if (eis & EIS_QFS) { ris2 = ravb_read(ndev, RIS2); - ravb_write(ndev, ~(RIS2_QFF0 | RIS2_RFFF), RIS2); + ravb_write(ndev, ~(RIS2_QFF0 | RIS2_RFFF | RIS2_RESERVED), + RIS2); /* Receive Descriptor Empty int */ if (ris2 & RIS2_QFF0) @@ -795,7 +804,7 @@ static bool ravb_timestamp_interrupt(struct net_device *ndev) u32 tis = ravb_read(ndev, TIS); if (tis & TIS_TFUF) { - ravb_write(ndev, ~TIS_TFUF, TIS); + ravb_write(ndev, ~(TIS_TFUF | TIS_RESERVED), TIS); ravb_get_tx_tstamp(ndev); return true; } @@ -930,7 +939,7 @@ static int ravb_poll(struct napi_struct *napi, int budget) /* Processing RX Descriptor Ring */ if (ris0 & mask) { /* Clear RX interrupt */ - ravb_write(ndev, ~mask, RIS0); + ravb_write(ndev, ~(mask | RIS0_RESERVED), RIS0); if (ravb_rx(ndev, "a, q)) goto out; } @@ -938,7 +947,7 @@ static int ravb_poll(struct napi_struct *napi, int budget) if (tis & mask) { spin_lock_irqsave(&priv->lock, flags); /* Clear TX interrupt */ - ravb_write(ndev, ~mask, TIS); + ravb_write(ndev, ~(mask | TIS_RESERVED), TIS); ravb_tx_free(ndev, q, true); netif_wake_subqueue(ndev, q); mmiowb(); @@ -1073,8 +1082,11 @@ static int ravb_phy_init(struct net_device *ndev) netdev_info(ndev, "limited PHY to 100Mbit/s\n"); } - /* 10BASE is not supported */ - phydev->supported &= ~PHY_10BT_FEATURES; + /* 10BASE, Pause and Asym Pause is not supported */ + phy_remove_link_mode(phydev, ETHTOOL_LINK_MODE_10baseT_Half_BIT); + phy_remove_link_mode(phydev, ETHTOOL_LINK_MODE_10baseT_Full_BIT); + phy_remove_link_mode(phydev, ETHTOOL_LINK_MODE_Pause_BIT); + phy_remove_link_mode(phydev, ETHTOOL_LINK_MODE_Asym_Pause_BIT); phy_attached_info(phydev); @@ -1484,6 +1496,7 @@ static void ravb_tx_timeout_work(struct work_struct *work) static netdev_tx_t ravb_start_xmit(struct sk_buff *skb, struct net_device *ndev) { struct ravb_private *priv = netdev_priv(ndev); + int num_tx_desc = priv->num_tx_desc; u16 q = skb_get_queue_mapping(skb); struct ravb_tstamp_skb *ts_skb; struct ravb_tx_desc *desc; @@ -1495,7 +1508,7 @@ static netdev_tx_t ravb_start_xmit(struct sk_buff *skb, struct net_device *ndev) spin_lock_irqsave(&priv->lock, flags); if (priv->cur_tx[q] - priv->dirty_tx[q] > (priv->num_tx_ring[q] - 1) * - NUM_TX_DESC) { + num_tx_desc) { netif_err(priv, tx_queued, ndev, "still transmitting with the full ring!\n"); netif_stop_subqueue(ndev, q); @@ -1506,41 +1519,55 @@ static netdev_tx_t ravb_start_xmit(struct sk_buff *skb, struct net_device *ndev) if (skb_put_padto(skb, ETH_ZLEN)) goto exit; - entry = priv->cur_tx[q] % (priv->num_tx_ring[q] * NUM_TX_DESC); - priv->tx_skb[q][entry / NUM_TX_DESC] = skb; - - buffer = PTR_ALIGN(priv->tx_align[q], DPTR_ALIGN) + - entry / NUM_TX_DESC * DPTR_ALIGN; - len = PTR_ALIGN(skb->data, DPTR_ALIGN) - skb->data; - /* Zero length DMA descriptors are problematic as they seem to - * terminate DMA transfers. Avoid them by simply using a length of - * DPTR_ALIGN (4) when skb data is aligned to DPTR_ALIGN. - * - * As skb is guaranteed to have at least ETH_ZLEN (60) bytes of - * data by the call to skb_put_padto() above this is safe with - * respect to both the length of the first DMA descriptor (len) - * overflowing the available data and the length of the second DMA - * descriptor (skb->len - len) being negative. - */ - if (len == 0) - len = DPTR_ALIGN; + entry = priv->cur_tx[q] % (priv->num_tx_ring[q] * num_tx_desc); + priv->tx_skb[q][entry / num_tx_desc] = skb; + + if (num_tx_desc > 1) { + buffer = PTR_ALIGN(priv->tx_align[q], DPTR_ALIGN) + + entry / num_tx_desc * DPTR_ALIGN; + len = PTR_ALIGN(skb->data, DPTR_ALIGN) - skb->data; + + /* Zero length DMA descriptors are problematic as they seem + * to terminate DMA transfers. Avoid them by simply using a + * length of DPTR_ALIGN (4) when skb data is aligned to + * DPTR_ALIGN. + * + * As skb is guaranteed to have at least ETH_ZLEN (60) + * bytes of data by the call to skb_put_padto() above this + * is safe with respect to both the length of the first DMA + * descriptor (len) overflowing the available data and the + * length of the second DMA descriptor (skb->len - len) + * being negative. + */ + if (len == 0) + len = DPTR_ALIGN; - memcpy(buffer, skb->data, len); - dma_addr = dma_map_single(ndev->dev.parent, buffer, len, DMA_TO_DEVICE); - if (dma_mapping_error(ndev->dev.parent, dma_addr)) - goto drop; + memcpy(buffer, skb->data, len); + dma_addr = dma_map_single(ndev->dev.parent, buffer, len, + DMA_TO_DEVICE); + if (dma_mapping_error(ndev->dev.parent, dma_addr)) + goto drop; - desc = &priv->tx_ring[q][entry]; - desc->ds_tagl = cpu_to_le16(len); - desc->dptr = cpu_to_le32(dma_addr); + desc = &priv->tx_ring[q][entry]; + desc->ds_tagl = cpu_to_le16(len); + desc->dptr = cpu_to_le32(dma_addr); - buffer = skb->data + len; - len = skb->len - len; - dma_addr = dma_map_single(ndev->dev.parent, buffer, len, DMA_TO_DEVICE); - if (dma_mapping_error(ndev->dev.parent, dma_addr)) - goto unmap; + buffer = skb->data + len; + len = skb->len - len; + dma_addr = dma_map_single(ndev->dev.parent, buffer, len, + DMA_TO_DEVICE); + if (dma_mapping_error(ndev->dev.parent, dma_addr)) + goto unmap; - desc++; + desc++; + } else { + desc = &priv->tx_ring[q][entry]; + len = skb->len; + dma_addr = dma_map_single(ndev->dev.parent, skb->data, skb->len, + DMA_TO_DEVICE); + if (dma_mapping_error(ndev->dev.parent, dma_addr)) + goto drop; + } desc->ds_tagl = cpu_to_le16(len); desc->dptr = cpu_to_le32(dma_addr); @@ -1548,9 +1575,11 @@ static netdev_tx_t ravb_start_xmit(struct sk_buff *skb, struct net_device *ndev) if (q == RAVB_NC) { ts_skb = kmalloc(sizeof(*ts_skb), GFP_ATOMIC); if (!ts_skb) { - desc--; - dma_unmap_single(ndev->dev.parent, dma_addr, len, - DMA_TO_DEVICE); + if (num_tx_desc > 1) { + desc--; + dma_unmap_single(ndev->dev.parent, dma_addr, + len, DMA_TO_DEVICE); + } goto unmap; } ts_skb->skb = skb; @@ -1567,15 +1596,18 @@ static netdev_tx_t ravb_start_xmit(struct sk_buff *skb, struct net_device *ndev) skb_tx_timestamp(skb); /* Descriptor type must be set after all the above writes */ dma_wmb(); - desc->die_dt = DT_FEND; - desc--; - desc->die_dt = DT_FSTART; - + if (num_tx_desc > 1) { + desc->die_dt = DT_FEND; + desc--; + desc->die_dt = DT_FSTART; + } else { + desc->die_dt = DT_FSINGLE; + } ravb_modify(ndev, TCCR, TCCR_TSRQ0 << q, TCCR_TSRQ0 << q); - priv->cur_tx[q] += NUM_TX_DESC; + priv->cur_tx[q] += num_tx_desc; if (priv->cur_tx[q] - priv->dirty_tx[q] > - (priv->num_tx_ring[q] - 1) * NUM_TX_DESC && + (priv->num_tx_ring[q] - 1) * num_tx_desc && !ravb_tx_free(ndev, q, true)) netif_stop_subqueue(ndev, q); @@ -1589,7 +1621,7 @@ unmap: le16_to_cpu(desc->ds_tagl), DMA_TO_DEVICE); drop: dev_kfree_skb_any(skb); - priv->tx_skb[q][entry / NUM_TX_DESC] = NULL; + priv->tx_skb[q][entry / num_tx_desc] = NULL; goto exit; } @@ -2075,6 +2107,9 @@ static int ravb_probe(struct platform_device *pdev) ndev->max_mtu = 2048 - (ETH_HLEN + VLAN_HLEN + ETH_FCS_LEN); ndev->min_mtu = ETH_MIN_MTU; + priv->num_tx_desc = chip_id == RCAR_GEN2 ? + NUM_TX_DESC_GEN2 : NUM_TX_DESC_GEN3; + /* Set function */ ndev->netdev_ops = &ravb_netdev_ops; ndev->ethtool_ops = &ravb_ethtool_ops; diff --git a/drivers/net/ethernet/renesas/ravb_ptp.c b/drivers/net/ethernet/renesas/ravb_ptp.c index eede70ec37f8..dce2a40a31e3 100644 --- a/drivers/net/ethernet/renesas/ravb_ptp.c +++ b/drivers/net/ethernet/renesas/ravb_ptp.c @@ -1,13 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0+ /* PTP 1588 clock using the Renesas Ethernet AVB * * Copyright (C) 2013-2015 Renesas Electronics Corporation * Copyright (C) 2015 Renesas Solutions Corp. * Copyright (C) 2015-2016 Cogent Embedded, Inc. <source@cogentembedded.com> - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. */ #include "ravb.h" @@ -319,7 +315,7 @@ void ravb_ptp_interrupt(struct net_device *ndev) } } - ravb_write(ndev, ~gis, GIS); + ravb_write(ndev, ~(gis | GIS_RESERVED), GIS); } void ravb_ptp_init(struct net_device *ndev, struct platform_device *pdev) diff --git a/drivers/net/ethernet/samsung/sxgbe/sxgbe_main.c b/drivers/net/ethernet/samsung/sxgbe/sxgbe_main.c index a9da1ad4b4f2..690aee88f0eb 100644 --- a/drivers/net/ethernet/samsung/sxgbe/sxgbe_main.c +++ b/drivers/net/ethernet/samsung/sxgbe/sxgbe_main.c @@ -298,8 +298,8 @@ static int sxgbe_init_phy(struct net_device *ndev) /* Stop Advertising 1000BASE Capability if interface is not GMII */ if ((phy_iface == PHY_INTERFACE_MODE_MII) || (phy_iface == PHY_INTERFACE_MODE_RMII)) - phydev->advertising &= ~(SUPPORTED_1000baseT_Half | - SUPPORTED_1000baseT_Full); + phy_set_max_speed(phydev, SPEED_1000); + if (phydev->phy_id == 0) { phy_disconnect(phydev); return -ENODEV; diff --git a/drivers/net/ethernet/seeq/ether3.c b/drivers/net/ethernet/seeq/ether3.c index c5bc124b41a9..d1bb73bf9914 100644 --- a/drivers/net/ethernet/seeq/ether3.c +++ b/drivers/net/ethernet/seeq/ether3.c @@ -77,7 +77,8 @@ static void ether3_setmulticastlist(struct net_device *dev); static int ether3_rx(struct net_device *dev, unsigned int maxcnt); static void ether3_tx(struct net_device *dev); static int ether3_open (struct net_device *dev); -static int ether3_sendpacket (struct sk_buff *skb, struct net_device *dev); +static netdev_tx_t ether3_sendpacket(struct sk_buff *skb, + struct net_device *dev); static irqreturn_t ether3_interrupt (int irq, void *dev_id); static int ether3_close (struct net_device *dev); static void ether3_setmulticastlist (struct net_device *dev); @@ -481,7 +482,7 @@ static void ether3_timeout(struct net_device *dev) /* * Transmit a packet */ -static int +static netdev_tx_t ether3_sendpacket(struct sk_buff *skb, struct net_device *dev) { unsigned long flags; diff --git a/drivers/net/ethernet/seeq/sgiseeq.c b/drivers/net/ethernet/seeq/sgiseeq.c index 573691bc3b71..70cce63a6081 100644 --- a/drivers/net/ethernet/seeq/sgiseeq.c +++ b/drivers/net/ethernet/seeq/sgiseeq.c @@ -578,7 +578,8 @@ static inline int sgiseeq_reset(struct net_device *dev) return 0; } -static int sgiseeq_start_xmit(struct sk_buff *skb, struct net_device *dev) +static netdev_tx_t +sgiseeq_start_xmit(struct sk_buff *skb, struct net_device *dev) { struct sgiseeq_private *sp = netdev_priv(dev); struct hpc3_ethregs *hregs = sp->hregs; diff --git a/drivers/net/ethernet/sgi/ioc3-eth.c b/drivers/net/ethernet/sgi/ioc3-eth.c index 18d533fdf14c..3140999642ba 100644 --- a/drivers/net/ethernet/sgi/ioc3-eth.c +++ b/drivers/net/ethernet/sgi/ioc3-eth.c @@ -99,7 +99,7 @@ struct ioc3_private { static int ioc3_ioctl(struct net_device *dev, struct ifreq *rq, int cmd); static void ioc3_set_multicast_list(struct net_device *dev); -static int ioc3_start_xmit(struct sk_buff *skb, struct net_device *dev); +static netdev_tx_t ioc3_start_xmit(struct sk_buff *skb, struct net_device *dev); static void ioc3_timeout(struct net_device *dev); static inline unsigned int ioc3_hash(const unsigned char *addr); static inline void ioc3_stop(struct ioc3_private *ip); @@ -1390,7 +1390,7 @@ static struct pci_driver ioc3_driver = { .remove = ioc3_remove_one, }; -static int ioc3_start_xmit(struct sk_buff *skb, struct net_device *dev) +static netdev_tx_t ioc3_start_xmit(struct sk_buff *skb, struct net_device *dev) { unsigned long data; struct ioc3_private *ip = netdev_priv(dev); diff --git a/drivers/net/ethernet/sgi/meth.c b/drivers/net/ethernet/sgi/meth.c index ea55abd62ec7..703fbbefea44 100644 --- a/drivers/net/ethernet/sgi/meth.c +++ b/drivers/net/ethernet/sgi/meth.c @@ -697,7 +697,7 @@ static void meth_add_to_tx_ring(struct meth_private *priv, struct sk_buff *skb) /* * Transmit a packet (called by the kernel) */ -static int meth_tx(struct sk_buff *skb, struct net_device *dev) +static netdev_tx_t meth_tx(struct sk_buff *skb, struct net_device *dev) { struct meth_private *priv = netdev_priv(dev); unsigned long flags; diff --git a/drivers/net/ethernet/smsc/smsc911x.c b/drivers/net/ethernet/smsc/smsc911x.c index f0afb88d7bc2..c009407618d9 100644 --- a/drivers/net/ethernet/smsc/smsc911x.c +++ b/drivers/net/ethernet/smsc/smsc911x.c @@ -1048,10 +1048,10 @@ static int smsc911x_mii_probe(struct net_device *dev) phy_attached_info(phydev); + phy_set_max_speed(phydev, SPEED_100); + /* mask with MAC supported features */ - phydev->supported &= (PHY_BASIC_FEATURES | SUPPORTED_Pause | - SUPPORTED_Asym_Pause); - phydev->advertising = phydev->supported; + phy_support_asym_pause(phydev); pdata->last_duplex = -1; pdata->last_carrier = -1; diff --git a/drivers/net/ethernet/smsc/smsc9420.c b/drivers/net/ethernet/smsc/smsc9420.c index 2fa3c1d03abc..9b6366b20110 100644 --- a/drivers/net/ethernet/smsc/smsc9420.c +++ b/drivers/net/ethernet/smsc/smsc9420.c @@ -1135,10 +1135,10 @@ static int smsc9420_mii_probe(struct net_device *dev) return PTR_ERR(phydev); } + phy_set_max_speed(phydev, SPEED_100); + /* mask with MAC supported features */ - phydev->supported &= (PHY_BASIC_FEATURES | SUPPORTED_Pause | - SUPPORTED_Asym_Pause); - phydev->advertising = phydev->supported; + phy_support_asym_pause(phydev); phy_attached_info(phydev); diff --git a/drivers/net/ethernet/socionext/sni_ave.c b/drivers/net/ethernet/socionext/sni_ave.c index f7ecceeb1e28..2a156dcd4534 100644 --- a/drivers/net/ethernet/socionext/sni_ave.c +++ b/drivers/net/ethernet/socionext/sni_ave.c @@ -461,16 +461,7 @@ static int ave_ethtool_set_pauseparam(struct net_device *ndev, priv->pause_rx = pause->rx_pause; priv->pause_tx = pause->tx_pause; - phydev->advertising &= ~(ADVERTISED_Pause | ADVERTISED_Asym_Pause); - if (pause->rx_pause) - phydev->advertising |= ADVERTISED_Pause | ADVERTISED_Asym_Pause; - if (pause->tx_pause) - phydev->advertising ^= ADVERTISED_Asym_Pause; - - if (pause->autoneg) { - if (netif_running(ndev)) - phy_start_aneg(phydev); - } + phy_set_asym_pause(phydev, pause->rx_pause, pause->tx_pause); return 0; } @@ -904,11 +895,11 @@ static void ave_rxfifo_reset(struct net_device *ndev) /* assert reset */ writel(AVE_GRR_RXFFR, priv->base + AVE_GRR); - usleep_range(40, 50); + udelay(50); /* negate reset */ writel(0, priv->base + AVE_GRR); - usleep_range(10, 20); + udelay(20); /* negate interrupt status */ writel(AVE_GI_RXOVF, priv->base + AVE_GISR); @@ -1223,11 +1214,10 @@ static int ave_init(struct net_device *ndev) phy_ethtool_get_wol(phydev, &wol); device_set_wakeup_capable(&ndev->dev, !!wol.supported); - if (!phy_interface_is_rgmii(phydev)) { - phydev->supported &= ~PHY_GBIT_FEATURES; - phydev->supported |= PHY_BASIC_FEATURES; - } - phydev->supported |= SUPPORTED_Pause | SUPPORTED_Asym_Pause; + if (!phy_interface_is_rgmii(phydev)) + phy_set_max_speed(phydev, SPEED_100); + + phy_support_asym_pause(phydev); phy_attached_info(phydev); diff --git a/drivers/net/ethernet/stmicro/stmmac/common.h b/drivers/net/ethernet/stmicro/stmmac/common.h index 1854f270ad66..b1b305f8f414 100644 --- a/drivers/net/ethernet/stmicro/stmmac/common.h +++ b/drivers/net/ethernet/stmicro/stmmac/common.h @@ -258,10 +258,10 @@ struct stmmac_safety_stats { #define MAX_DMA_RIWT 0xff #define MIN_DMA_RIWT 0x20 /* Tx coalesce parameters */ -#define STMMAC_COAL_TX_TIMER 40000 +#define STMMAC_COAL_TX_TIMER 1000 #define STMMAC_MAX_COAL_TX_TICK 100000 #define STMMAC_TX_MAX_FRAMES 256 -#define STMMAC_TX_FRAMES 64 +#define STMMAC_TX_FRAMES 25 /* Packets types */ enum packets_types { diff --git a/drivers/net/ethernet/stmicro/stmmac/hwif.c b/drivers/net/ethernet/stmicro/stmmac/hwif.c index d9a34a4d08b3..81b966a8261b 100644 --- a/drivers/net/ethernet/stmicro/stmmac/hwif.c +++ b/drivers/net/ethernet/stmicro/stmmac/hwif.c @@ -133,7 +133,7 @@ static const struct stmmac_hwif_entry { .mac = &dwmac4_ops, .hwtimestamp = &stmmac_ptp, .mode = NULL, - .tc = NULL, + .tc = &dwmac510_tc_ops, .setup = dwmac4_setup, .quirks = stmmac_dwmac4_quirks, }, { @@ -150,7 +150,7 @@ static const struct stmmac_hwif_entry { .mac = &dwmac410_ops, .hwtimestamp = &stmmac_ptp, .mode = &dwmac4_ring_mode_ops, - .tc = NULL, + .tc = &dwmac510_tc_ops, .setup = dwmac4_setup, .quirks = NULL, }, { @@ -167,7 +167,7 @@ static const struct stmmac_hwif_entry { .mac = &dwmac410_ops, .hwtimestamp = &stmmac_ptp, .mode = &dwmac4_ring_mode_ops, - .tc = NULL, + .tc = &dwmac510_tc_ops, .setup = dwmac4_setup, .quirks = NULL, }, { diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac.h b/drivers/net/ethernet/stmicro/stmmac/stmmac.h index c0a855b7ab3b..63e1064b27a2 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac.h +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac.h @@ -48,6 +48,8 @@ struct stmmac_tx_info { /* Frequently used values are kept adjacent for cache effect */ struct stmmac_tx_queue { + u32 tx_count_frames; + struct timer_list txtimer; u32 queue_index; struct stmmac_priv *priv_data; struct dma_extended_desc *dma_etx ____cacheline_aligned_in_smp; @@ -73,7 +75,14 @@ struct stmmac_rx_queue { u32 rx_zeroc_thresh; dma_addr_t dma_rx_phy; u32 rx_tail_addr; +}; + +struct stmmac_channel { struct napi_struct napi ____cacheline_aligned_in_smp; + struct stmmac_priv *priv_data; + u32 index; + int has_rx; + int has_tx; }; struct stmmac_tc_entry { @@ -109,14 +118,12 @@ struct stmmac_pps_cfg { struct stmmac_priv { /* Frequently used values are kept adjacent for cache effect */ - u32 tx_count_frames; u32 tx_coal_frames; u32 tx_coal_timer; int tx_coalesce; int hwts_tx_en; bool tx_path_in_lpi_mode; - struct timer_list txtimer; bool tso; unsigned int dma_buf_sz; @@ -137,6 +144,9 @@ struct stmmac_priv { /* TX Queue */ struct stmmac_tx_queue tx_queue[MTL_MAX_TX_QUEUES]; + /* Generic channel for NAPI */ + struct stmmac_channel channel[STMMAC_CH_MAX]; + bool oldlink; int speed; int oldduplex; diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index 9f458bb16f2a..076a8be18d67 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -148,12 +148,14 @@ static void stmmac_verify_args(void) static void stmmac_disable_all_queues(struct stmmac_priv *priv) { u32 rx_queues_cnt = priv->plat->rx_queues_to_use; + u32 tx_queues_cnt = priv->plat->tx_queues_to_use; + u32 maxq = max(rx_queues_cnt, tx_queues_cnt); u32 queue; - for (queue = 0; queue < rx_queues_cnt; queue++) { - struct stmmac_rx_queue *rx_q = &priv->rx_queue[queue]; + for (queue = 0; queue < maxq; queue++) { + struct stmmac_channel *ch = &priv->channel[queue]; - napi_disable(&rx_q->napi); + napi_disable(&ch->napi); } } @@ -164,12 +166,14 @@ static void stmmac_disable_all_queues(struct stmmac_priv *priv) static void stmmac_enable_all_queues(struct stmmac_priv *priv) { u32 rx_queues_cnt = priv->plat->rx_queues_to_use; + u32 tx_queues_cnt = priv->plat->tx_queues_to_use; + u32 maxq = max(rx_queues_cnt, tx_queues_cnt); u32 queue; - for (queue = 0; queue < rx_queues_cnt; queue++) { - struct stmmac_rx_queue *rx_q = &priv->rx_queue[queue]; + for (queue = 0; queue < maxq; queue++) { + struct stmmac_channel *ch = &priv->channel[queue]; - napi_enable(&rx_q->napi); + napi_enable(&ch->napi); } } @@ -987,17 +991,20 @@ static int stmmac_init_phy(struct net_device *dev) if ((interface == PHY_INTERFACE_MODE_MII) || (interface == PHY_INTERFACE_MODE_RMII) || (max_speed < 1000 && max_speed > 0)) - phydev->advertising &= ~(SUPPORTED_1000baseT_Half | - SUPPORTED_1000baseT_Full); + phy_set_max_speed(phydev, SPEED_100); /* * Half-duplex mode not supported with multiqueue * half-duplex can only works with single queue */ - if (tx_cnt > 1) - phydev->supported &= ~(SUPPORTED_1000baseT_Half | - SUPPORTED_100baseT_Half | - SUPPORTED_10baseT_Half); + if (tx_cnt > 1) { + phy_remove_link_mode(phydev, + ETHTOOL_LINK_MODE_10baseT_Half_BIT); + phy_remove_link_mode(phydev, + ETHTOOL_LINK_MODE_100baseT_Half_BIT); + phy_remove_link_mode(phydev, + ETHTOOL_LINK_MODE_1000baseT_Half_BIT); + } /* * Broken HW is sometimes missing the pull-up resistor on the @@ -1843,18 +1850,18 @@ static void stmmac_dma_operation_mode(struct stmmac_priv *priv) * @queue: TX queue index * Description: it reclaims the transmit resources after transmission completes. */ -static void stmmac_tx_clean(struct stmmac_priv *priv, u32 queue) +static int stmmac_tx_clean(struct stmmac_priv *priv, int budget, u32 queue) { struct stmmac_tx_queue *tx_q = &priv->tx_queue[queue]; unsigned int bytes_compl = 0, pkts_compl = 0; - unsigned int entry; + unsigned int entry, count = 0; - netif_tx_lock(priv->dev); + __netif_tx_lock_bh(netdev_get_tx_queue(priv->dev, queue)); priv->xstats.tx_clean++; entry = tx_q->dirty_tx; - while (entry != tx_q->cur_tx) { + while ((entry != tx_q->cur_tx) && (count < budget)) { struct sk_buff *skb = tx_q->tx_skbuff[entry]; struct dma_desc *p; int status; @@ -1870,6 +1877,8 @@ static void stmmac_tx_clean(struct stmmac_priv *priv, u32 queue) if (unlikely(status & tx_dma_own)) break; + count++; + /* Make sure descriptor fields are read after reading * the own bit. */ @@ -1937,7 +1946,10 @@ static void stmmac_tx_clean(struct stmmac_priv *priv, u32 queue) stmmac_enable_eee_mode(priv); mod_timer(&priv->eee_ctrl_timer, STMMAC_LPI_T(eee_timer)); } - netif_tx_unlock(priv->dev); + + __netif_tx_unlock_bh(netdev_get_tx_queue(priv->dev, queue)); + + return count; } /** @@ -2020,6 +2032,33 @@ static bool stmmac_safety_feat_interrupt(struct stmmac_priv *priv) return false; } +static int stmmac_napi_check(struct stmmac_priv *priv, u32 chan) +{ + int status = stmmac_dma_interrupt_status(priv, priv->ioaddr, + &priv->xstats, chan); + struct stmmac_channel *ch = &priv->channel[chan]; + bool needs_work = false; + + if ((status & handle_rx) && ch->has_rx) { + needs_work = true; + } else { + status &= ~handle_rx; + } + + if ((status & handle_tx) && ch->has_tx) { + needs_work = true; + } else { + status &= ~handle_tx; + } + + if (needs_work && napi_schedule_prep(&ch->napi)) { + stmmac_disable_dma_irq(priv, priv->ioaddr, chan); + __napi_schedule(&ch->napi); + } + + return status; +} + /** * stmmac_dma_interrupt - DMA ISR * @priv: driver private structure @@ -2034,57 +2073,14 @@ static void stmmac_dma_interrupt(struct stmmac_priv *priv) u32 channels_to_check = tx_channel_count > rx_channel_count ? tx_channel_count : rx_channel_count; u32 chan; - bool poll_scheduled = false; int status[max_t(u32, MTL_MAX_TX_QUEUES, MTL_MAX_RX_QUEUES)]; /* Make sure we never check beyond our status buffer. */ if (WARN_ON_ONCE(channels_to_check > ARRAY_SIZE(status))) channels_to_check = ARRAY_SIZE(status); - /* Each DMA channel can be used for rx and tx simultaneously, yet - * napi_struct is embedded in struct stmmac_rx_queue rather than in a - * stmmac_channel struct. - * Because of this, stmmac_poll currently checks (and possibly wakes) - * all tx queues rather than just a single tx queue. - */ for (chan = 0; chan < channels_to_check; chan++) - status[chan] = stmmac_dma_interrupt_status(priv, priv->ioaddr, - &priv->xstats, chan); - - for (chan = 0; chan < rx_channel_count; chan++) { - if (likely(status[chan] & handle_rx)) { - struct stmmac_rx_queue *rx_q = &priv->rx_queue[chan]; - - if (likely(napi_schedule_prep(&rx_q->napi))) { - stmmac_disable_dma_irq(priv, priv->ioaddr, chan); - __napi_schedule(&rx_q->napi); - poll_scheduled = true; - } - } - } - - /* If we scheduled poll, we already know that tx queues will be checked. - * If we didn't schedule poll, see if any DMA channel (used by tx) has a - * completed transmission, if so, call stmmac_poll (once). - */ - if (!poll_scheduled) { - for (chan = 0; chan < tx_channel_count; chan++) { - if (status[chan] & handle_tx) { - /* It doesn't matter what rx queue we choose - * here. We use 0 since it always exists. - */ - struct stmmac_rx_queue *rx_q = - &priv->rx_queue[0]; - - if (likely(napi_schedule_prep(&rx_q->napi))) { - stmmac_disable_dma_irq(priv, - priv->ioaddr, chan); - __napi_schedule(&rx_q->napi); - } - break; - } - } - } + status[chan] = stmmac_napi_check(priv, chan); for (chan = 0; chan < tx_channel_count; chan++) { if (unlikely(status[chan] & tx_hard_error_bump_tc)) { @@ -2220,8 +2216,7 @@ static int stmmac_init_dma_engine(struct stmmac_priv *priv) stmmac_init_tx_chan(priv, priv->ioaddr, priv->plat->dma_cfg, tx_q->dma_tx_phy, chan); - tx_q->tx_tail_addr = tx_q->dma_tx_phy + - (DMA_TX_SIZE * sizeof(struct dma_desc)); + tx_q->tx_tail_addr = tx_q->dma_tx_phy; stmmac_set_tx_tail_ptr(priv, priv->ioaddr, tx_q->tx_tail_addr, chan); } @@ -2233,6 +2228,13 @@ static int stmmac_init_dma_engine(struct stmmac_priv *priv) return ret; } +static void stmmac_tx_timer_arm(struct stmmac_priv *priv, u32 queue) +{ + struct stmmac_tx_queue *tx_q = &priv->tx_queue[queue]; + + mod_timer(&tx_q->txtimer, STMMAC_COAL_TIMER(priv->tx_coal_timer)); +} + /** * stmmac_tx_timer - mitigation sw timer for tx. * @data: data pointer @@ -2241,13 +2243,14 @@ static int stmmac_init_dma_engine(struct stmmac_priv *priv) */ static void stmmac_tx_timer(struct timer_list *t) { - struct stmmac_priv *priv = from_timer(priv, t, txtimer); - u32 tx_queues_count = priv->plat->tx_queues_to_use; - u32 queue; + struct stmmac_tx_queue *tx_q = from_timer(tx_q, t, txtimer); + struct stmmac_priv *priv = tx_q->priv_data; + struct stmmac_channel *ch; + + ch = &priv->channel[tx_q->queue_index]; - /* let's scan all the tx queues */ - for (queue = 0; queue < tx_queues_count; queue++) - stmmac_tx_clean(priv, queue); + if (likely(napi_schedule_prep(&ch->napi))) + __napi_schedule(&ch->napi); } /** @@ -2260,11 +2263,17 @@ static void stmmac_tx_timer(struct timer_list *t) */ static void stmmac_init_tx_coalesce(struct stmmac_priv *priv) { + u32 tx_channel_count = priv->plat->tx_queues_to_use; + u32 chan; + priv->tx_coal_frames = STMMAC_TX_FRAMES; priv->tx_coal_timer = STMMAC_COAL_TX_TIMER; - timer_setup(&priv->txtimer, stmmac_tx_timer, 0); - priv->txtimer.expires = STMMAC_COAL_TIMER(priv->tx_coal_timer); - add_timer(&priv->txtimer); + + for (chan = 0; chan < tx_channel_count; chan++) { + struct stmmac_tx_queue *tx_q = &priv->tx_queue[chan]; + + timer_setup(&tx_q->txtimer, stmmac_tx_timer, 0); + } } static void stmmac_set_rings_length(struct stmmac_priv *priv) @@ -2592,6 +2601,7 @@ static void stmmac_hw_teardown(struct net_device *dev) static int stmmac_open(struct net_device *dev) { struct stmmac_priv *priv = netdev_priv(dev); + u32 chan; int ret; stmmac_check_ether_addr(priv); @@ -2688,7 +2698,9 @@ irq_error: if (dev->phydev) phy_stop(dev->phydev); - del_timer_sync(&priv->txtimer); + for (chan = 0; chan < priv->plat->tx_queues_to_use; chan++) + del_timer_sync(&priv->tx_queue[chan].txtimer); + stmmac_hw_teardown(dev); init_error: free_dma_desc_resources(priv); @@ -2708,6 +2720,7 @@ dma_desc_error: static int stmmac_release(struct net_device *dev) { struct stmmac_priv *priv = netdev_priv(dev); + u32 chan; if (priv->eee_enabled) del_timer_sync(&priv->eee_ctrl_timer); @@ -2722,7 +2735,8 @@ static int stmmac_release(struct net_device *dev) stmmac_disable_all_queues(priv); - del_timer_sync(&priv->txtimer); + for (chan = 0; chan < priv->plat->tx_queues_to_use; chan++) + del_timer_sync(&priv->tx_queue[chan].txtimer); /* Free the IRQ lines */ free_irq(dev->irq, dev); @@ -2936,14 +2950,13 @@ static netdev_tx_t stmmac_tso_xmit(struct sk_buff *skb, struct net_device *dev) priv->xstats.tx_tso_nfrags += nfrags; /* Manage tx mitigation */ - priv->tx_count_frames += nfrags + 1; - if (likely(priv->tx_coal_frames > priv->tx_count_frames)) { - mod_timer(&priv->txtimer, - STMMAC_COAL_TIMER(priv->tx_coal_timer)); - } else { - priv->tx_count_frames = 0; + tx_q->tx_count_frames += nfrags + 1; + if (priv->tx_coal_frames <= tx_q->tx_count_frames) { stmmac_set_tx_ic(priv, desc); priv->xstats.tx_set_ic_bit++; + tx_q->tx_count_frames = 0; + } else { + stmmac_tx_timer_arm(priv, queue); } skb_tx_timestamp(skb); @@ -2992,6 +3005,7 @@ static netdev_tx_t stmmac_tso_xmit(struct sk_buff *skb, struct net_device *dev) netdev_tx_sent_queue(netdev_get_tx_queue(dev, queue), skb->len); + tx_q->tx_tail_addr = tx_q->dma_tx_phy + (tx_q->cur_tx * sizeof(*desc)); stmmac_set_tx_tail_ptr(priv, priv->ioaddr, tx_q->tx_tail_addr, queue); return NETDEV_TX_OK; @@ -3146,14 +3160,13 @@ static netdev_tx_t stmmac_xmit(struct sk_buff *skb, struct net_device *dev) * This approach takes care about the fragments: desc is the first * element in case of no SG. */ - priv->tx_count_frames += nfrags + 1; - if (likely(priv->tx_coal_frames > priv->tx_count_frames)) { - mod_timer(&priv->txtimer, - STMMAC_COAL_TIMER(priv->tx_coal_timer)); - } else { - priv->tx_count_frames = 0; + tx_q->tx_count_frames += nfrags + 1; + if (priv->tx_coal_frames <= tx_q->tx_count_frames) { stmmac_set_tx_ic(priv, desc); priv->xstats.tx_set_ic_bit++; + tx_q->tx_count_frames = 0; + } else { + stmmac_tx_timer_arm(priv, queue); } skb_tx_timestamp(skb); @@ -3199,6 +3212,8 @@ static netdev_tx_t stmmac_xmit(struct sk_buff *skb, struct net_device *dev) netdev_tx_sent_queue(netdev_get_tx_queue(dev, queue), skb->len); stmmac_enable_dma_transmission(priv, priv->ioaddr); + + tx_q->tx_tail_addr = tx_q->dma_tx_phy + (tx_q->cur_tx * sizeof(*desc)); stmmac_set_tx_tail_ptr(priv, priv->ioaddr, tx_q->tx_tail_addr, queue); return NETDEV_TX_OK; @@ -3319,6 +3334,7 @@ static inline void stmmac_rx_refill(struct stmmac_priv *priv, u32 queue) static int stmmac_rx(struct stmmac_priv *priv, int limit, u32 queue) { struct stmmac_rx_queue *rx_q = &priv->rx_queue[queue]; + struct stmmac_channel *ch = &priv->channel[queue]; unsigned int entry = rx_q->cur_rx; int coe = priv->hw->rx_csum; unsigned int next_entry; @@ -3491,7 +3507,7 @@ static int stmmac_rx(struct stmmac_priv *priv, int limit, u32 queue) else skb->ip_summed = CHECKSUM_UNNECESSARY; - napi_gro_receive(&rx_q->napi, skb); + napi_gro_receive(&ch->napi, skb); priv->dev->stats.rx_packets++; priv->dev->stats.rx_bytes += frame_len; @@ -3514,27 +3530,33 @@ static int stmmac_rx(struct stmmac_priv *priv, int limit, u32 queue) * Description : * To look at the incoming frames and clear the tx resources. */ -static int stmmac_poll(struct napi_struct *napi, int budget) +static int stmmac_napi_poll(struct napi_struct *napi, int budget) { - struct stmmac_rx_queue *rx_q = - container_of(napi, struct stmmac_rx_queue, napi); - struct stmmac_priv *priv = rx_q->priv_data; - u32 tx_count = priv->plat->tx_queues_to_use; - u32 chan = rx_q->queue_index; - int work_done = 0; - u32 queue; + struct stmmac_channel *ch = + container_of(napi, struct stmmac_channel, napi); + struct stmmac_priv *priv = ch->priv_data; + int work_done = 0, work_rem = budget; + u32 chan = ch->index; priv->xstats.napi_poll++; - /* check all the queues */ - for (queue = 0; queue < tx_count; queue++) - stmmac_tx_clean(priv, queue); + if (ch->has_tx) { + int done = stmmac_tx_clean(priv, work_rem, chan); - work_done = stmmac_rx(priv, budget, rx_q->queue_index); - if (work_done < budget) { - napi_complete_done(napi, work_done); - stmmac_enable_dma_irq(priv, priv->ioaddr, chan); + work_done += done; + work_rem -= done; + } + + if (ch->has_rx) { + int done = stmmac_rx(priv, work_rem, chan); + + work_done += done; + work_rem -= done; } + + if (work_done < budget && napi_complete_done(napi, work_done)) + stmmac_enable_dma_irq(priv, priv->ioaddr, chan); + return work_done; } @@ -4198,8 +4220,8 @@ int stmmac_dvr_probe(struct device *device, { struct net_device *ndev = NULL; struct stmmac_priv *priv; + u32 queue, maxq; int ret = 0; - u32 queue; ndev = alloc_etherdev_mqs(sizeof(struct stmmac_priv), MTL_MAX_TX_QUEUES, @@ -4322,11 +4344,22 @@ int stmmac_dvr_probe(struct device *device, "Enable RX Mitigation via HW Watchdog Timer\n"); } - for (queue = 0; queue < priv->plat->rx_queues_to_use; queue++) { - struct stmmac_rx_queue *rx_q = &priv->rx_queue[queue]; + /* Setup channels NAPI */ + maxq = max(priv->plat->rx_queues_to_use, priv->plat->tx_queues_to_use); - netif_napi_add(ndev, &rx_q->napi, stmmac_poll, - (8 * priv->plat->rx_queues_to_use)); + for (queue = 0; queue < maxq; queue++) { + struct stmmac_channel *ch = &priv->channel[queue]; + + ch->priv_data = priv; + ch->index = queue; + + if (queue < priv->plat->rx_queues_to_use) + ch->has_rx = true; + if (queue < priv->plat->tx_queues_to_use) + ch->has_tx = true; + + netif_napi_add(ndev, &ch->napi, stmmac_napi_poll, + NAPI_POLL_WEIGHT); } mutex_init(&priv->lock); @@ -4372,10 +4405,10 @@ error_netdev_register: priv->hw->pcs != STMMAC_PCS_RTBI) stmmac_mdio_unregister(ndev); error_mdio_register: - for (queue = 0; queue < priv->plat->rx_queues_to_use; queue++) { - struct stmmac_rx_queue *rx_q = &priv->rx_queue[queue]; + for (queue = 0; queue < maxq; queue++) { + struct stmmac_channel *ch = &priv->channel[queue]; - netif_napi_del(&rx_q->napi); + netif_napi_del(&ch->napi); } error_hw_init: destroy_workqueue(priv->wq); diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c index 3609c7b696c7..2b800ce1d5bf 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c @@ -67,7 +67,7 @@ static int dwmac1000_validate_mcast_bins(int mcast_bins) * Description: * This function validates the number of Unicast address entries supported * by a particular Synopsys 10/100/1000 controller. The Synopsys controller - * supports 1, 32, 64, or 128 Unicast filter entries for it's Unicast filter + * supports 1..32, 64, or 128 Unicast filter entries for it's Unicast filter * logic. This function validates a valid, supported configuration is * selected, and defaults to 1 Unicast address if an unsupported * configuration is selected. @@ -77,8 +77,7 @@ static int dwmac1000_validate_ucast_entries(int ucast_entries) int x = ucast_entries; switch (x) { - case 1: - case 32: + case 1 ... 32: case 64: case 128: break; diff --git a/drivers/net/ethernet/sun/ldmvsw.c b/drivers/net/ethernet/sun/ldmvsw.c index d42f47f6c632..644e42c181ee 100644 --- a/drivers/net/ethernet/sun/ldmvsw.c +++ b/drivers/net/ethernet/sun/ldmvsw.c @@ -113,7 +113,7 @@ static u16 vsw_select_queue(struct net_device *dev, struct sk_buff *skb, } /* Wrappers to common functions */ -static int vsw_start_xmit(struct sk_buff *skb, struct net_device *dev) +static netdev_tx_t vsw_start_xmit(struct sk_buff *skb, struct net_device *dev) { return sunvnet_start_xmit_common(skb, dev, vsw_tx_port_find); } diff --git a/drivers/net/ethernet/sun/sunbmac.c b/drivers/net/ethernet/sun/sunbmac.c index f047b2797156..720b7ac77f3b 100644 --- a/drivers/net/ethernet/sun/sunbmac.c +++ b/drivers/net/ethernet/sun/sunbmac.c @@ -950,7 +950,8 @@ static void bigmac_tx_timeout(struct net_device *dev) } /* Put a packet on the wire. */ -static int bigmac_start_xmit(struct sk_buff *skb, struct net_device *dev) +static netdev_tx_t +bigmac_start_xmit(struct sk_buff *skb, struct net_device *dev) { struct bigmac *bp = netdev_priv(dev); int len, entry; diff --git a/drivers/net/ethernet/sun/sunqe.c b/drivers/net/ethernet/sun/sunqe.c index 7fe0d5e33922..1468fa0a54e9 100644 --- a/drivers/net/ethernet/sun/sunqe.c +++ b/drivers/net/ethernet/sun/sunqe.c @@ -570,7 +570,7 @@ out: } /* Get a packet queued to go onto the wire. */ -static int qe_start_xmit(struct sk_buff *skb, struct net_device *dev) +static netdev_tx_t qe_start_xmit(struct sk_buff *skb, struct net_device *dev) { struct sunqe *qep = netdev_priv(dev); struct sunqe_buffers *qbufs = qep->buffers; diff --git a/drivers/net/ethernet/sun/sunvnet.c b/drivers/net/ethernet/sun/sunvnet.c index 12539b357a78..590172818b92 100644 --- a/drivers/net/ethernet/sun/sunvnet.c +++ b/drivers/net/ethernet/sun/sunvnet.c @@ -247,7 +247,7 @@ static u16 vnet_select_queue(struct net_device *dev, struct sk_buff *skb, } /* Wrappers to common functions */ -static int vnet_start_xmit(struct sk_buff *skb, struct net_device *dev) +static netdev_tx_t vnet_start_xmit(struct sk_buff *skb, struct net_device *dev) { return sunvnet_start_xmit_common(skb, dev, vnet_tx_port_find); } diff --git a/drivers/net/ethernet/sun/sunvnet_common.c b/drivers/net/ethernet/sun/sunvnet_common.c index d8f4c3f28150..baa3088b475c 100644 --- a/drivers/net/ethernet/sun/sunvnet_common.c +++ b/drivers/net/ethernet/sun/sunvnet_common.c @@ -1216,9 +1216,10 @@ static inline struct sk_buff *vnet_skb_shape(struct sk_buff *skb, int ncookies) return skb; } -static int vnet_handle_offloads(struct vnet_port *port, struct sk_buff *skb, - struct vnet_port *(*vnet_tx_port) - (struct sk_buff *, struct net_device *)) +static netdev_tx_t +vnet_handle_offloads(struct vnet_port *port, struct sk_buff *skb, + struct vnet_port *(*vnet_tx_port) + (struct sk_buff *, struct net_device *)) { struct net_device *dev = VNET_PORT_TO_NET_DEVICE(port); struct vio_dring_state *dr = &port->vio.drings[VIO_DRIVER_TX_RING]; @@ -1321,9 +1322,10 @@ out_dropped: return NETDEV_TX_OK; } -int sunvnet_start_xmit_common(struct sk_buff *skb, struct net_device *dev, - struct vnet_port *(*vnet_tx_port) - (struct sk_buff *, struct net_device *)) +netdev_tx_t +sunvnet_start_xmit_common(struct sk_buff *skb, struct net_device *dev, + struct vnet_port *(*vnet_tx_port) + (struct sk_buff *, struct net_device *)) { struct vnet_port *port = NULL; struct vio_dring_state *dr; diff --git a/drivers/net/ethernet/sun/sunvnet_common.h b/drivers/net/ethernet/sun/sunvnet_common.h index 1ea0b016580a..2b808d2482d6 100644 --- a/drivers/net/ethernet/sun/sunvnet_common.h +++ b/drivers/net/ethernet/sun/sunvnet_common.h @@ -136,9 +136,10 @@ int sunvnet_close_common(struct net_device *dev); void sunvnet_set_rx_mode_common(struct net_device *dev, struct vnet *vp); int sunvnet_set_mac_addr_common(struct net_device *dev, void *p); void sunvnet_tx_timeout_common(struct net_device *dev); -int sunvnet_start_xmit_common(struct sk_buff *skb, struct net_device *dev, - struct vnet_port *(*vnet_tx_port) - (struct sk_buff *, struct net_device *)); +netdev_tx_t +sunvnet_start_xmit_common(struct sk_buff *skb, struct net_device *dev, + struct vnet_port *(*vnet_tx_port) + (struct sk_buff *, struct net_device *)); #ifdef CONFIG_NET_POLL_CONTROLLER void sunvnet_poll_controller_common(struct net_device *dev, struct vnet *vp); #endif diff --git a/drivers/net/ethernet/ti/Kconfig b/drivers/net/ethernet/ti/Kconfig index 9263d638bd6d..f932923f7d56 100644 --- a/drivers/net/ethernet/ti/Kconfig +++ b/drivers/net/ethernet/ti/Kconfig @@ -41,6 +41,7 @@ config TI_DAVINCI_MDIO config TI_DAVINCI_CPDMA tristate "TI DaVinci CPDMA Support" depends on ARCH_DAVINCI || ARCH_OMAP2PLUS || COMPILE_TEST + select GENERIC_ALLOCATOR ---help--- This driver supports TI's DaVinci CPDMA dma engine. diff --git a/drivers/net/ethernet/ti/cpsw.c b/drivers/net/ethernet/ti/cpsw.c index 832bce07c385..16dcbf36f8cc 100644 --- a/drivers/net/ethernet/ti/cpsw.c +++ b/drivers/net/ethernet/ti/cpsw.c @@ -484,13 +484,13 @@ enum { }; #define CPSW_STAT(m) CPSW_STATS, \ - sizeof(((struct cpsw_hw_stats *)0)->m), \ + FIELD_SIZEOF(struct cpsw_hw_stats, m), \ offsetof(struct cpsw_hw_stats, m) #define CPDMA_RX_STAT(m) CPDMA_RX_STATS, \ - sizeof(((struct cpdma_chan_stats *)0)->m), \ + FIELD_SIZEOF(struct cpdma_chan_stats, m), \ offsetof(struct cpdma_chan_stats, m) #define CPDMA_TX_STAT(m) CPDMA_TX_STATS, \ - sizeof(((struct cpdma_chan_stats *)0)->m), \ + FIELD_SIZEOF(struct cpdma_chan_stats, m), \ offsetof(struct cpdma_chan_stats, m) static const struct cpsw_stats cpsw_gstrings_stats[] = { diff --git a/drivers/net/ethernet/toshiba/ps3_gelic_net.c b/drivers/net/ethernet/toshiba/ps3_gelic_net.c index 88d74aef218a..75237c81c63d 100644 --- a/drivers/net/ethernet/toshiba/ps3_gelic_net.c +++ b/drivers/net/ethernet/toshiba/ps3_gelic_net.c @@ -845,9 +845,9 @@ static int gelic_card_kick_txdma(struct gelic_card *card, * @skb: packet to send out * @netdev: interface device structure * - * returns 0 on success, <0 on failure + * returns NETDEV_TX_OK on success, NETDEV_TX_BUSY on failure */ -int gelic_net_xmit(struct sk_buff *skb, struct net_device *netdev) +netdev_tx_t gelic_net_xmit(struct sk_buff *skb, struct net_device *netdev) { struct gelic_card *card = netdev_card(netdev); struct gelic_descr *descr; diff --git a/drivers/net/ethernet/toshiba/ps3_gelic_net.h b/drivers/net/ethernet/toshiba/ps3_gelic_net.h index 003d0452d9cb..fbbf9b54b173 100644 --- a/drivers/net/ethernet/toshiba/ps3_gelic_net.h +++ b/drivers/net/ethernet/toshiba/ps3_gelic_net.h @@ -370,7 +370,7 @@ void gelic_card_up(struct gelic_card *card); void gelic_card_down(struct gelic_card *card); int gelic_net_open(struct net_device *netdev); int gelic_net_stop(struct net_device *netdev); -int gelic_net_xmit(struct sk_buff *skb, struct net_device *netdev); +netdev_tx_t gelic_net_xmit(struct sk_buff *skb, struct net_device *netdev); void gelic_net_set_multi(struct net_device *netdev); void gelic_net_tx_timeout(struct net_device *netdev); int gelic_net_setup_netdev(struct net_device *netdev, struct gelic_card *card); diff --git a/drivers/net/ethernet/toshiba/ps3_gelic_wireless.c b/drivers/net/ethernet/toshiba/ps3_gelic_wireless.c index 302079e22b06..00ab417694ad 100644 --- a/drivers/net/ethernet/toshiba/ps3_gelic_wireless.c +++ b/drivers/net/ethernet/toshiba/ps3_gelic_wireless.c @@ -1094,7 +1094,7 @@ static int gelic_wl_get_encode(struct net_device *netdev, struct gelic_wl_info *wl = port_wl(netdev_priv(netdev)); struct iw_point *enc = &data->encoding; unsigned long irqflag; - unsigned int key_index, index_specified; + unsigned int key_index; int ret = 0; pr_debug("%s: <-\n", __func__); @@ -1105,13 +1105,10 @@ static int gelic_wl_get_encode(struct net_device *netdev, return -EINVAL; spin_lock_irqsave(&wl->lock, irqflag); - if (key_index) { - index_specified = 1; + if (key_index) key_index--; - } else { - index_specified = 0; + else key_index = wl->current_key; - } if (wl->group_cipher_method == GELIC_WL_CIPHER_WEP) { switch (wl->auth_method) { diff --git a/drivers/net/ethernet/toshiba/spider_net.c b/drivers/net/ethernet/toshiba/spider_net.c index d925b8203996..23417266b7ec 100644 --- a/drivers/net/ethernet/toshiba/spider_net.c +++ b/drivers/net/ethernet/toshiba/spider_net.c @@ -880,9 +880,9 @@ out: * @skb: packet to send out * @netdev: interface device structure * - * returns 0 on success, !0 on failure + * returns NETDEV_TX_OK on success, NETDEV_TX_BUSY on failure */ -static int +static netdev_tx_t spider_net_xmit(struct sk_buff *skb, struct net_device *netdev) { int cnt; diff --git a/drivers/net/ethernet/toshiba/tc35815.c b/drivers/net/ethernet/toshiba/tc35815.c index cce9c9ed46aa..6a71c2c0f17d 100644 --- a/drivers/net/ethernet/toshiba/tc35815.c +++ b/drivers/net/ethernet/toshiba/tc35815.c @@ -474,7 +474,8 @@ static void free_rxbuf_skb(struct pci_dev *hwdev, struct sk_buff *skb, dma_addr_ /* Index to functions, as function prototypes. */ static int tc35815_open(struct net_device *dev); -static int tc35815_send_packet(struct sk_buff *skb, struct net_device *dev); +static netdev_tx_t tc35815_send_packet(struct sk_buff *skb, + struct net_device *dev); static irqreturn_t tc35815_interrupt(int irq, void *dev_id); static int tc35815_rx(struct net_device *dev, int limit); static int tc35815_poll(struct napi_struct *napi, int budget); @@ -628,7 +629,7 @@ static int tc_mii_probe(struct net_device *dev) phy_attached_info(phydev); /* mask with MAC supported features */ - phydev->supported &= PHY_BASIC_FEATURES; + phy_set_max_speed(phydev, SPEED_100); dropmask = 0; if (options.speed == 10) dropmask |= SUPPORTED_100baseT_Half | SUPPORTED_100baseT_Full; @@ -1248,7 +1249,8 @@ tc35815_open(struct net_device *dev) * invariant will hold if you make sure that the netif_*_queue() * calls are done at the proper times. */ -static int tc35815_send_packet(struct sk_buff *skb, struct net_device *dev) +static netdev_tx_t +tc35815_send_packet(struct sk_buff *skb, struct net_device *dev) { struct tc35815_local *lp = netdev_priv(dev); struct TxFD *txfd; diff --git a/drivers/net/ethernet/wiznet/w5100.c b/drivers/net/ethernet/wiznet/w5100.c index 2bdfb39215e9..d8ba512f166a 100644 --- a/drivers/net/ethernet/wiznet/w5100.c +++ b/drivers/net/ethernet/wiznet/w5100.c @@ -835,7 +835,7 @@ static void w5100_tx_work(struct work_struct *work) w5100_tx_skb(priv->ndev, skb); } -static int w5100_start_tx(struct sk_buff *skb, struct net_device *ndev) +static netdev_tx_t w5100_start_tx(struct sk_buff *skb, struct net_device *ndev) { struct w5100_priv *priv = netdev_priv(ndev); diff --git a/drivers/net/ethernet/wiznet/w5300.c b/drivers/net/ethernet/wiznet/w5300.c index 56ae573001e8..80fdbff67d82 100644 --- a/drivers/net/ethernet/wiznet/w5300.c +++ b/drivers/net/ethernet/wiznet/w5300.c @@ -365,7 +365,7 @@ static void w5300_tx_timeout(struct net_device *ndev) netif_wake_queue(ndev); } -static int w5300_start_tx(struct sk_buff *skb, struct net_device *ndev) +static netdev_tx_t w5300_start_tx(struct sk_buff *skb, struct net_device *ndev) { struct w5300_priv *priv = netdev_priv(ndev); diff --git a/drivers/net/ethernet/xilinx/ll_temac_main.c b/drivers/net/ethernet/xilinx/ll_temac_main.c index 60abc9250f56..2241f9897092 100644 --- a/drivers/net/ethernet/xilinx/ll_temac_main.c +++ b/drivers/net/ethernet/xilinx/ll_temac_main.c @@ -674,7 +674,8 @@ static inline int temac_check_tx_bd_space(struct temac_local *lp, int num_frag) return 0; } -static int temac_start_xmit(struct sk_buff *skb, struct net_device *ndev) +static netdev_tx_t +temac_start_xmit(struct sk_buff *skb, struct net_device *ndev) { struct temac_local *lp = netdev_priv(ndev); struct cdmac_bd *cur_p; diff --git a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c index f24f48f33802..12a14609ec47 100644 --- a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c +++ b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c @@ -653,7 +653,8 @@ static inline int axienet_check_tx_bd_space(struct axienet_local *lp, * start the transmission. Additionally if checksum offloading is supported, * it populates AXI Stream Control fields with appropriate values. */ -static int axienet_start_xmit(struct sk_buff *skb, struct net_device *ndev) +static netdev_tx_t +axienet_start_xmit(struct sk_buff *skb, struct net_device *ndev) { u32 ii; u32 num_frag; diff --git a/drivers/net/ethernet/xilinx/xilinx_emaclite.c b/drivers/net/ethernet/xilinx/xilinx_emaclite.c index 42f1f518dad6..639e3e99af46 100644 --- a/drivers/net/ethernet/xilinx/xilinx_emaclite.c +++ b/drivers/net/ethernet/xilinx/xilinx_emaclite.c @@ -941,8 +941,7 @@ static int xemaclite_open(struct net_device *dev) } /* EmacLite doesn't support giga-bit speeds */ - lp->phy_dev->supported &= (PHY_BASIC_FEATURES); - lp->phy_dev->advertising = lp->phy_dev->supported; + phy_set_max_speed(lp->phy_dev, SPEED_100); /* Don't advertise 1000BASE-T Full/Half duplex speeds */ phy_write(lp->phy_dev, MII_CTRL1000, 0); @@ -1020,9 +1019,10 @@ static int xemaclite_close(struct net_device *dev) * deferred and the Tx queue is stopped so that the deferred socket buffer can * be transmitted when the Emaclite device is free to transmit data. * - * Return: 0, always. + * Return: NETDEV_TX_OK, always. */ -static int xemaclite_send(struct sk_buff *orig_skb, struct net_device *dev) +static netdev_tx_t +xemaclite_send(struct sk_buff *orig_skb, struct net_device *dev) { struct net_local *lp = netdev_priv(dev); struct sk_buff *new_skb; @@ -1044,7 +1044,7 @@ static int xemaclite_send(struct sk_buff *orig_skb, struct net_device *dev) /* Take the time stamp now, since we can't do this in an ISR. */ skb_tx_timestamp(new_skb); spin_unlock_irqrestore(&lp->reset_lock, flags); - return 0; + return NETDEV_TX_OK; } spin_unlock_irqrestore(&lp->reset_lock, flags); @@ -1053,7 +1053,7 @@ static int xemaclite_send(struct sk_buff *orig_skb, struct net_device *dev) dev->stats.tx_bytes += len; dev_consume_skb_any(new_skb); - return 0; + return NETDEV_TX_OK; } /** diff --git a/drivers/net/fddi/skfp/ecm.c b/drivers/net/fddi/skfp/ecm.c index eee9ba91346a..c813e462183d 100644 --- a/drivers/net/fddi/skfp/ecm.c +++ b/drivers/net/fddi/skfp/ecm.c @@ -30,7 +30,6 @@ * * The following external HW dependent functions are referenced : * sm_pm_bypass_req() - * sm_pm_ls_latch() * sm_pm_get_ls() * * The following HW dependent events are required : @@ -356,8 +355,6 @@ static void ecm_fsm(struct s_smc *smc, int cmd) */ start_ecm_timer(smc,smc->s.ecm_check_poll,0) ; smc->e.ecm_line_state = TRUE ; /* flag to pcm: report Q/HLS */ - (void) sm_pm_ls_latch(smc,PA,1) ; /* enable line state latch */ - (void) sm_pm_ls_latch(smc,PB,1) ; /* enable line state latch */ ACTIONS_DONE() ; break ; case EC6_CHECK : diff --git a/drivers/net/fddi/skfp/h/cmtdef.h b/drivers/net/fddi/skfp/h/cmtdef.h index 5d6891154367..a12f464941ed 100644 --- a/drivers/net/fddi/skfp/h/cmtdef.h +++ b/drivers/net/fddi/skfp/h/cmtdef.h @@ -513,7 +513,6 @@ void pcm_status_state(struct s_smc *smc, int np, int *type, int *state, void plc_config_mux(struct s_smc *smc, int mux); void sm_lem_evaluate(struct s_smc *smc); void mac_update_counter(struct s_smc *smc); -void sm_pm_ls_latch(struct s_smc *smc, int phy, int on_off); void sm_ma_control(struct s_smc *smc, int mode); void sm_mac_check_beacon_claim(struct s_smc *smc); void config_mux(struct s_smc *smc, int mux); diff --git a/drivers/net/fddi/skfp/pcmplc.c b/drivers/net/fddi/skfp/pcmplc.c index a9ecf923f63d..6ef44c480bd5 100644 --- a/drivers/net/fddi/skfp/pcmplc.c +++ b/drivers/net/fddi/skfp/pcmplc.c @@ -30,7 +30,6 @@ * The following external HW dependent functions are referenced : * sm_pm_control() * sm_ph_linestate() - * sm_pm_ls_latch() * * The following HW dependent events are required : * PC_QLS @@ -1248,16 +1247,6 @@ static void sm_ph_lem_stop(struct s_smc *smc, int np) CLEAR(PLC(np,PL_INTR_MASK),PL_LE_CTR) ; } -/* ARGSUSED */ -void sm_pm_ls_latch(struct s_smc *smc, int phy, int on_off) -/* int on_off; en- or disable ident. ls */ -{ - SK_UNUSED(smc) ; - - phy = phy ; on_off = on_off ; -} - - /* * PCM pseudo code * receive actions are called AFTER the bit n is received, diff --git a/drivers/net/geneve.c b/drivers/net/geneve.c index 6acb6b5718b9..6625fabe2c88 100644 --- a/drivers/net/geneve.c +++ b/drivers/net/geneve.c @@ -69,6 +69,7 @@ struct geneve_dev { struct gro_cells gro_cells; bool collect_md; bool use_udp6_rx_checksums; + bool ttl_inherit; }; struct geneve_sock { @@ -843,7 +844,11 @@ static int geneve_xmit_skb(struct sk_buff *skb, struct net_device *dev, ttl = key->ttl; } else { tos = ip_tunnel_ecn_encap(fl4.flowi4_tos, ip_hdr(skb), skb); - ttl = key->ttl ? : ip4_dst_hoplimit(&rt->dst); + if (geneve->ttl_inherit) + ttl = ip_tunnel_get_ttl(ip_hdr(skb), skb); + else + ttl = key->ttl; + ttl = ttl ? : ip4_dst_hoplimit(&rt->dst); } df = key->tun_flags & TUNNEL_DONT_FRAGMENT ? htons(IP_DF) : 0; @@ -889,7 +894,11 @@ static int geneve6_xmit_skb(struct sk_buff *skb, struct net_device *dev, } else { prio = ip_tunnel_ecn_encap(ip6_tclass(fl6.flowlabel), ip_hdr(skb), skb); - ttl = key->ttl ? : ip6_dst_hoplimit(dst); + if (geneve->ttl_inherit) + ttl = ip_tunnel_get_ttl(ip_hdr(skb), skb); + else + ttl = key->ttl; + ttl = ttl ? : ip6_dst_hoplimit(dst); } err = geneve_build_skb(dst, skb, info, xnet, sizeof(struct ipv6hdr)); if (unlikely(err)) @@ -1091,6 +1100,7 @@ static const struct nla_policy geneve_policy[IFLA_GENEVE_MAX + 1] = { [IFLA_GENEVE_UDP_CSUM] = { .type = NLA_U8 }, [IFLA_GENEVE_UDP_ZERO_CSUM6_TX] = { .type = NLA_U8 }, [IFLA_GENEVE_UDP_ZERO_CSUM6_RX] = { .type = NLA_U8 }, + [IFLA_GENEVE_TTL_INHERIT] = { .type = NLA_U8 }, }; static int geneve_validate(struct nlattr *tb[], struct nlattr *data[], @@ -1170,7 +1180,8 @@ static bool geneve_dst_addr_equal(struct ip_tunnel_info *a, static int geneve_configure(struct net *net, struct net_device *dev, struct netlink_ext_ack *extack, const struct ip_tunnel_info *info, - bool metadata, bool ipv6_rx_csum) + bool metadata, bool ipv6_rx_csum, + bool ttl_inherit) { struct geneve_net *gn = net_generic(net, geneve_net_id); struct geneve_dev *t, *geneve = netdev_priv(dev); @@ -1219,6 +1230,7 @@ static int geneve_configure(struct net *net, struct net_device *dev, geneve->info = *info; geneve->collect_md = metadata; geneve->use_udp6_rx_checksums = ipv6_rx_csum; + geneve->ttl_inherit = ttl_inherit; err = register_netdevice(dev); if (err) @@ -1237,7 +1249,8 @@ static void init_tnl_info(struct ip_tunnel_info *info, __u16 dst_port) static int geneve_nl2info(struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack, struct ip_tunnel_info *info, bool *metadata, - bool *use_udp6_rx_checksums, bool changelink) + bool *use_udp6_rx_checksums, bool *ttl_inherit, + bool changelink) { int attrtype; @@ -1315,6 +1328,9 @@ static int geneve_nl2info(struct nlattr *tb[], struct nlattr *data[], if (data[IFLA_GENEVE_TTL]) info->key.ttl = nla_get_u8(data[IFLA_GENEVE_TTL]); + if (data[IFLA_GENEVE_TTL_INHERIT]) + *ttl_inherit = true; + if (data[IFLA_GENEVE_TOS]) info->key.tos = nla_get_u8(data[IFLA_GENEVE_TOS]); @@ -1438,17 +1454,18 @@ static int geneve_newlink(struct net *net, struct net_device *dev, { bool use_udp6_rx_checksums = false; struct ip_tunnel_info info; + bool ttl_inherit = false; bool metadata = false; int err; init_tnl_info(&info, GENEVE_UDP_PORT); err = geneve_nl2info(tb, data, extack, &info, &metadata, - &use_udp6_rx_checksums, false); + &use_udp6_rx_checksums, &ttl_inherit, false); if (err) return err; err = geneve_configure(net, dev, extack, &info, metadata, - use_udp6_rx_checksums); + use_udp6_rx_checksums, ttl_inherit); if (err) return err; @@ -1511,6 +1528,7 @@ static int geneve_changelink(struct net_device *dev, struct nlattr *tb[], struct ip_tunnel_info info; bool metadata; bool use_udp6_rx_checksums; + bool ttl_inherit; int err; /* If the geneve device is configured for metadata (or externally @@ -1523,8 +1541,9 @@ static int geneve_changelink(struct net_device *dev, struct nlattr *tb[], memcpy(&info, &geneve->info, sizeof(info)); metadata = geneve->collect_md; use_udp6_rx_checksums = geneve->use_udp6_rx_checksums; + ttl_inherit = geneve->ttl_inherit; err = geneve_nl2info(tb, data, extack, &info, &metadata, - &use_udp6_rx_checksums, true); + &use_udp6_rx_checksums, &ttl_inherit, true); if (err) return err; @@ -1537,6 +1556,7 @@ static int geneve_changelink(struct net_device *dev, struct nlattr *tb[], geneve->info = info; geneve->collect_md = metadata; geneve->use_udp6_rx_checksums = use_udp6_rx_checksums; + geneve->ttl_inherit = ttl_inherit; geneve_unquiesce(geneve, gs4, gs6); return 0; @@ -1562,6 +1582,7 @@ static size_t geneve_get_size(const struct net_device *dev) nla_total_size(sizeof(__u8)) + /* IFLA_GENEVE_UDP_CSUM */ nla_total_size(sizeof(__u8)) + /* IFLA_GENEVE_UDP_ZERO_CSUM6_TX */ nla_total_size(sizeof(__u8)) + /* IFLA_GENEVE_UDP_ZERO_CSUM6_RX */ + nla_total_size(sizeof(__u8)) + /* IFLA_GENEVE_TTL_INHERIT */ 0; } @@ -1569,6 +1590,7 @@ static int geneve_fill_info(struct sk_buff *skb, const struct net_device *dev) { struct geneve_dev *geneve = netdev_priv(dev); struct ip_tunnel_info *info = &geneve->info; + bool ttl_inherit = geneve->ttl_inherit; bool metadata = geneve->collect_md; __u8 tmp_vni[3]; __u32 vni; @@ -1614,6 +1636,9 @@ static int geneve_fill_info(struct sk_buff *skb, const struct net_device *dev) goto nla_put_failure; #endif + if (nla_put_u8(skb, IFLA_GENEVE_TTL_INHERIT, ttl_inherit)) + goto nla_put_failure; + return 0; nla_put_failure: @@ -1650,7 +1675,7 @@ struct net_device *geneve_dev_create_fb(struct net *net, const char *name, return dev; init_tnl_info(&info, dst_port); - err = geneve_configure(net, dev, NULL, &info, true, true); + err = geneve_configure(net, dev, NULL, &info, true, true, false); if (err) { free_netdev(dev); return ERR_PTR(err); diff --git a/drivers/net/hyperv/hyperv_net.h b/drivers/net/hyperv/hyperv_net.h index a32ded5b4f41..ef6f766f6389 100644 --- a/drivers/net/hyperv/hyperv_net.h +++ b/drivers/net/hyperv/hyperv_net.h @@ -185,7 +185,9 @@ struct rndis_device { /* Interface */ struct rndis_message; +struct ndis_offload_params; struct netvsc_device; +struct netvsc_channel; struct net_device_context; extern u32 netvsc_ring_bytes; @@ -203,10 +205,7 @@ void netvsc_linkstatus_callback(struct net_device *net, struct rndis_message *resp); int netvsc_recv_callback(struct net_device *net, struct netvsc_device *nvdev, - struct vmbus_channel *channel, - void *data, u32 len, - const struct ndis_tcp_ip_checksum_info *csum_info, - const struct ndis_pkt_8021q_info *vlan); + struct netvsc_channel *nvchan); void netvsc_channel_cb(void *context); int netvsc_poll(struct napi_struct *napi, int budget); @@ -220,9 +219,12 @@ void rndis_filter_device_remove(struct hv_device *dev, struct netvsc_device *nvdev); int rndis_filter_set_rss_param(struct rndis_device *rdev, const u8 *key); +int rndis_filter_set_offload_params(struct net_device *ndev, + struct netvsc_device *nvdev, + struct ndis_offload_params *req_offloads); int rndis_filter_receive(struct net_device *ndev, struct netvsc_device *net_dev, - struct vmbus_channel *channel, + struct netvsc_channel *nvchan, void *data, u32 buflen); int rndis_filter_set_device_mac(struct netvsc_device *ndev, @@ -524,6 +526,8 @@ struct nvsp_2_vsc_capability { u64 ieee8021q:1; u64 correlation_id:1; u64 teaming:1; + u64 vsubnetid:1; + u64 rsc:1; }; }; } __packed; @@ -826,7 +830,7 @@ struct nvsp_message { #define NETVSC_SUPPORTED_HW_FEATURES (NETIF_F_RXCSUM | NETIF_F_IP_CSUM | \ NETIF_F_TSO | NETIF_F_IPV6_CSUM | \ - NETIF_F_TSO6) + NETIF_F_TSO6 | NETIF_F_LRO) #define VRSS_SEND_TAB_SIZE 16 /* must be power of 2 */ #define VRSS_CHANNEL_MAX 64 @@ -852,6 +856,18 @@ struct multi_recv_comp { u32 next; /* next entry for writing */ }; +#define NVSP_RSC_MAX 562 /* Max #RSC frags in a vmbus xfer page pkt */ + +struct nvsc_rsc { + const struct ndis_pkt_8021q_info *vlan; + const struct ndis_tcp_ip_checksum_info *csum_info; + u8 is_last; /* last RNDIS msg in a vmtransfer_page */ + u32 cnt; /* #fragments in an RSC packet */ + u32 pktlen; /* Full packet length */ + void *data[NVSP_RSC_MAX]; + u32 len[NVSP_RSC_MAX]; +}; + struct netvsc_stats { u64 packets; u64 bytes; @@ -955,6 +971,7 @@ struct netvsc_channel { struct multi_send_data msd; struct multi_recv_comp mrc; atomic_t queue_sends; + struct nvsc_rsc rsc; struct netvsc_stats tx_stats; struct netvsc_stats rx_stats; @@ -1136,7 +1153,8 @@ struct rndis_oobd { /* Packet extension field contents associated with a Data message. */ struct rndis_per_packet_info { u32 size; - u32 type; + u32 type:31; + u32 internal:1; u32 ppi_offset; }; @@ -1157,6 +1175,25 @@ enum ndis_per_pkt_info_type { MAX_PER_PKT_INFO }; +enum rndis_per_pkt_info_interal_type { + RNDIS_PKTINFO_ID = 1, + /* Add more memebers here */ + + RNDIS_PKTINFO_MAX +}; + +#define RNDIS_PKTINFO_SUBALLOC BIT(0) +#define RNDIS_PKTINFO_1ST_FRAG BIT(1) +#define RNDIS_PKTINFO_LAST_FRAG BIT(2) + +#define RNDIS_PKTINFO_ID_V1 1 + +struct rndis_pktinfo_id { + u8 ver; + u8 flag; + u16 pkt_id; +}; + struct ndis_pkt_8021q_info { union { struct { diff --git a/drivers/net/hyperv/netvsc.c b/drivers/net/hyperv/netvsc.c index 31c3d77b4733..922054c1d544 100644 --- a/drivers/net/hyperv/netvsc.c +++ b/drivers/net/hyperv/netvsc.c @@ -542,6 +542,9 @@ static int negotiate_nvsp_ver(struct hv_device *device, init_packet->msg.v2_msg.send_ndis_config.capability.teaming = 1; } + if (nvsp_ver >= NVSP_PROTOCOL_VERSION_61) + init_packet->msg.v2_msg.send_ndis_config.capability.rsc = 1; + trace_nvsp_send(ndev, init_packet); ret = vmbus_sendpacket(device->channel, init_packet, @@ -1111,11 +1114,12 @@ static void enq_receive_complete(struct net_device *ndev, static int netvsc_receive(struct net_device *ndev, struct netvsc_device *net_device, - struct vmbus_channel *channel, + struct netvsc_channel *nvchan, const struct vmpacket_descriptor *desc, const struct nvsp_message *nvsp) { struct net_device_context *net_device_ctx = netdev_priv(ndev); + struct vmbus_channel *channel = nvchan->channel; const struct vmtransfer_page_packet_header *vmxferpage_packet = container_of(desc, const struct vmtransfer_page_packet_header, d); u16 q_idx = channel->offermsg.offer.sub_channel_index; @@ -1150,6 +1154,7 @@ static int netvsc_receive(struct net_device *ndev, int ret; if (unlikely(offset + buflen > net_device->recv_buf_size)) { + nvchan->rsc.cnt = 0; status = NVSP_STAT_FAIL; netif_err(net_device_ctx, rx_err, ndev, "Packet offset:%u + len:%u too big\n", @@ -1160,11 +1165,13 @@ static int netvsc_receive(struct net_device *ndev, data = recv_buf + offset; + nvchan->rsc.is_last = (i == count - 1); + trace_rndis_recv(ndev, q_idx, data); /* Pass it to the upper layer */ ret = rndis_filter_receive(ndev, net_device, - channel, data, buflen); + nvchan, data, buflen); if (unlikely(ret != NVSP_STAT_SUCCESS)) status = NVSP_STAT_FAIL; @@ -1203,6 +1210,9 @@ static void netvsc_send_vf(struct net_device *ndev, net_device_ctx->vf_alloc = nvmsg->msg.v4_msg.vf_assoc.allocated; net_device_ctx->vf_serial = nvmsg->msg.v4_msg.vf_assoc.serial; + netdev_info(ndev, "VF slot %u %s\n", + net_device_ctx->vf_serial, + net_device_ctx->vf_alloc ? "added" : "removed"); } static void netvsc_receive_inband(struct net_device *ndev, @@ -1220,12 +1230,13 @@ static void netvsc_receive_inband(struct net_device *ndev, } static int netvsc_process_raw_pkt(struct hv_device *device, - struct vmbus_channel *channel, + struct netvsc_channel *nvchan, struct netvsc_device *net_device, struct net_device *ndev, const struct vmpacket_descriptor *desc, int budget) { + struct vmbus_channel *channel = nvchan->channel; const struct nvsp_message *nvmsg = hv_pkt_data(desc); trace_nvsp_recv(ndev, channel, nvmsg); @@ -1237,7 +1248,7 @@ static int netvsc_process_raw_pkt(struct hv_device *device, break; case VM_PKT_DATA_USING_XFER_PAGES: - return netvsc_receive(ndev, net_device, channel, + return netvsc_receive(ndev, net_device, nvchan, desc, nvmsg); break; @@ -1281,7 +1292,7 @@ int netvsc_poll(struct napi_struct *napi, int budget) nvchan->desc = hv_pkt_iter_first(channel); while (nvchan->desc && work_done < budget) { - work_done += netvsc_process_raw_pkt(device, channel, net_device, + work_done += netvsc_process_raw_pkt(device, nvchan, net_device, ndev, nvchan->desc, budget); nvchan->desc = hv_pkt_iter_next(channel, nvchan->desc); } diff --git a/drivers/net/hyperv/netvsc_drv.c b/drivers/net/hyperv/netvsc_drv.c index 70921bbe0e28..ec699741170b 100644 --- a/drivers/net/hyperv/netvsc_drv.c +++ b/drivers/net/hyperv/netvsc_drv.c @@ -744,14 +744,16 @@ void netvsc_linkstatus_callback(struct net_device *net, } static struct sk_buff *netvsc_alloc_recv_skb(struct net_device *net, - struct napi_struct *napi, - const struct ndis_tcp_ip_checksum_info *csum_info, - const struct ndis_pkt_8021q_info *vlan, - void *data, u32 buflen) + struct netvsc_channel *nvchan) { + struct napi_struct *napi = &nvchan->napi; + const struct ndis_pkt_8021q_info *vlan = nvchan->rsc.vlan; + const struct ndis_tcp_ip_checksum_info *csum_info = + nvchan->rsc.csum_info; struct sk_buff *skb; + int i; - skb = napi_alloc_skb(napi, buflen); + skb = napi_alloc_skb(napi, nvchan->rsc.pktlen); if (!skb) return skb; @@ -759,7 +761,8 @@ static struct sk_buff *netvsc_alloc_recv_skb(struct net_device *net, * Copy to skb. This copy is needed here since the memory pointed by * hv_netvsc_packet cannot be deallocated */ - skb_put_data(skb, data, buflen); + for (i = 0; i < nvchan->rsc.cnt; i++) + skb_put_data(skb, nvchan->rsc.data[i], nvchan->rsc.len[i]); skb->protocol = eth_type_trans(skb, net); @@ -792,14 +795,11 @@ static struct sk_buff *netvsc_alloc_recv_skb(struct net_device *net, */ int netvsc_recv_callback(struct net_device *net, struct netvsc_device *net_device, - struct vmbus_channel *channel, - void *data, u32 len, - const struct ndis_tcp_ip_checksum_info *csum_info, - const struct ndis_pkt_8021q_info *vlan) + struct netvsc_channel *nvchan) { struct net_device_context *net_device_ctx = netdev_priv(net); + struct vmbus_channel *channel = nvchan->channel; u16 q_idx = channel->offermsg.offer.sub_channel_index; - struct netvsc_channel *nvchan = &net_device->chan_table[q_idx]; struct sk_buff *skb; struct netvsc_stats *rx_stats; @@ -807,8 +807,8 @@ int netvsc_recv_callback(struct net_device *net, return NVSP_STAT_FAIL; /* Allocate a skb - TODO direct I/O to pages? */ - skb = netvsc_alloc_recv_skb(net, &nvchan->napi, - csum_info, vlan, data, len); + skb = netvsc_alloc_recv_skb(net, nvchan); + if (unlikely(!skb)) { ++net_device_ctx->eth_stats.rx_no_memory; rcu_read_unlock(); @@ -825,7 +825,7 @@ int netvsc_recv_callback(struct net_device *net, rx_stats = &nvchan->rx_stats; u64_stats_update_begin(&rx_stats->syncp); rx_stats->packets++; - rx_stats->bytes += len; + rx_stats->bytes += nvchan->rsc.pktlen; if (skb->pkt_type == PACKET_BROADCAST) ++rx_stats->broadcast; @@ -1006,6 +1006,8 @@ static void netvsc_init_settings(struct net_device *dev) ndc->speed = SPEED_UNKNOWN; ndc->duplex = DUPLEX_FULL; + + dev->features = NETIF_F_LRO; } static int netvsc_get_link_ksettings(struct net_device *dev, @@ -1733,6 +1735,33 @@ static int netvsc_set_ringparam(struct net_device *ndev, return ret; } +static int netvsc_set_features(struct net_device *ndev, + netdev_features_t features) +{ + netdev_features_t change = features ^ ndev->features; + struct net_device_context *ndevctx = netdev_priv(ndev); + struct netvsc_device *nvdev = rtnl_dereference(ndevctx->nvdev); + struct ndis_offload_params offloads; + + if (!nvdev || nvdev->destroy) + return -ENODEV; + + if (!(change & NETIF_F_LRO)) + return 0; + + memset(&offloads, 0, sizeof(struct ndis_offload_params)); + + if (features & NETIF_F_LRO) { + offloads.rsc_ip_v4 = NDIS_OFFLOAD_PARAMETERS_RSC_ENABLED; + offloads.rsc_ip_v6 = NDIS_OFFLOAD_PARAMETERS_RSC_ENABLED; + } else { + offloads.rsc_ip_v4 = NDIS_OFFLOAD_PARAMETERS_RSC_DISABLED; + offloads.rsc_ip_v6 = NDIS_OFFLOAD_PARAMETERS_RSC_DISABLED; + } + + return rndis_filter_set_offload_params(ndev, nvdev, &offloads); +} + static u32 netvsc_get_msglevel(struct net_device *ndev) { struct net_device_context *ndev_ctx = netdev_priv(ndev); @@ -1776,6 +1805,7 @@ static const struct net_device_ops device_ops = { .ndo_start_xmit = netvsc_start_xmit, .ndo_change_rx_flags = netvsc_change_rx_flags, .ndo_set_rx_mode = netvsc_set_rx_mode, + .ndo_set_features = netvsc_set_features, .ndo_change_mtu = netvsc_change_mtu, .ndo_validate_addr = eth_validate_addr, .ndo_set_mac_address = netvsc_set_mac_addr, @@ -1894,20 +1924,6 @@ out_unlock: rtnl_unlock(); } -static struct net_device *get_netvsc_bymac(const u8 *mac) -{ - struct net_device_context *ndev_ctx; - - list_for_each_entry(ndev_ctx, &netvsc_dev_list, list) { - struct net_device *dev = hv_get_drvdata(ndev_ctx->device_ctx); - - if (ether_addr_equal(mac, dev->perm_addr)) - return dev; - } - - return NULL; -} - static struct net_device *get_netvsc_byref(struct net_device *vf_netdev) { struct net_device_context *net_device_ctx; @@ -2036,26 +2052,48 @@ static void netvsc_vf_setup(struct work_struct *w) rtnl_unlock(); } +/* Find netvsc by VMBus serial number. + * The PCI hyperv controller records the serial number as the slot. + */ +static struct net_device *get_netvsc_byslot(const struct net_device *vf_netdev) +{ + struct device *parent = vf_netdev->dev.parent; + struct net_device_context *ndev_ctx; + struct pci_dev *pdev; + + if (!parent || !dev_is_pci(parent)) + return NULL; /* not a PCI device */ + + pdev = to_pci_dev(parent); + if (!pdev->slot) { + netdev_notice(vf_netdev, "no PCI slot information\n"); + return NULL; + } + + list_for_each_entry(ndev_ctx, &netvsc_dev_list, list) { + if (!ndev_ctx->vf_alloc) + continue; + + if (ndev_ctx->vf_serial == pdev->slot->number) + return hv_get_drvdata(ndev_ctx->device_ctx); + } + + netdev_notice(vf_netdev, + "no netdev found for slot %u\n", pdev->slot->number); + return NULL; +} + static int netvsc_register_vf(struct net_device *vf_netdev) { - struct net_device *ndev; struct net_device_context *net_device_ctx; - struct device *pdev = vf_netdev->dev.parent; struct netvsc_device *netvsc_dev; + struct net_device *ndev; int ret; if (vf_netdev->addr_len != ETH_ALEN) return NOTIFY_DONE; - if (!pdev || !dev_is_pci(pdev) || dev_is_pf(pdev)) - return NOTIFY_DONE; - - /* - * We will use the MAC address to locate the synthetic interface to - * associate with the VF interface. If we don't find a matching - * synthetic interface, move on. - */ - ndev = get_netvsc_bymac(vf_netdev->perm_addr); + ndev = get_netvsc_byslot(vf_netdev); if (!ndev) return NOTIFY_DONE; @@ -2272,17 +2310,15 @@ static int netvsc_remove(struct hv_device *dev) cancel_delayed_work_sync(&ndev_ctx->dwork); - rcu_read_lock(); - nvdev = rcu_dereference(ndev_ctx->nvdev); - - if (nvdev) + rtnl_lock(); + nvdev = rtnl_dereference(ndev_ctx->nvdev); + if (nvdev) cancel_work_sync(&nvdev->subchan_work); /* * Call to the vsc driver to let it know that the device is being * removed. Also blocks mtu and channel changes. */ - rtnl_lock(); vf_netdev = rtnl_dereference(ndev_ctx->vf_netdev); if (vf_netdev) netvsc_unregister_vf(vf_netdev); @@ -2294,7 +2330,6 @@ static int netvsc_remove(struct hv_device *dev) list_del(&ndev_ctx->list); rtnl_unlock(); - rcu_read_unlock(); hv_set_drvdata(dev, NULL); diff --git a/drivers/net/hyperv/rndis_filter.c b/drivers/net/hyperv/rndis_filter.c index 2a5209f23f29..8b537a049c1e 100644 --- a/drivers/net/hyperv/rndis_filter.c +++ b/drivers/net/hyperv/rndis_filter.c @@ -342,7 +342,8 @@ static void rndis_filter_receive_response(struct net_device *ndev, * Get the Per-Packet-Info with the specified type * return NULL if not found. */ -static inline void *rndis_get_ppi(struct rndis_packet *rpkt, u32 type) +static inline void *rndis_get_ppi(struct rndis_packet *rpkt, + u32 type, u8 internal) { struct rndis_per_packet_info *ppi; int len; @@ -355,7 +356,7 @@ static inline void *rndis_get_ppi(struct rndis_packet *rpkt, u32 type) len = rpkt->per_pkt_info_len; while (len > 0) { - if (ppi->type == type) + if (ppi->type == type && ppi->internal == internal) return (void *)((ulong)ppi + ppi->ppi_offset); len -= ppi->size; ppi = (struct rndis_per_packet_info *)((ulong)ppi + ppi->size); @@ -364,17 +365,41 @@ static inline void *rndis_get_ppi(struct rndis_packet *rpkt, u32 type) return NULL; } +static inline +void rsc_add_data(struct netvsc_channel *nvchan, + const struct ndis_pkt_8021q_info *vlan, + const struct ndis_tcp_ip_checksum_info *csum_info, + void *data, u32 len) +{ + u32 cnt = nvchan->rsc.cnt; + + if (cnt) { + nvchan->rsc.pktlen += len; + } else { + nvchan->rsc.vlan = vlan; + nvchan->rsc.csum_info = csum_info; + nvchan->rsc.pktlen = len; + } + + nvchan->rsc.data[cnt] = data; + nvchan->rsc.len[cnt] = len; + nvchan->rsc.cnt++; +} + static int rndis_filter_receive_data(struct net_device *ndev, struct netvsc_device *nvdev, - struct vmbus_channel *channel, + struct netvsc_channel *nvchan, struct rndis_message *msg, u32 data_buflen) { struct rndis_packet *rndis_pkt = &msg->msg.pkt; const struct ndis_tcp_ip_checksum_info *csum_info; const struct ndis_pkt_8021q_info *vlan; + const struct rndis_pktinfo_id *pktinfo_id; u32 data_offset; void *data; + bool rsc_more = false; + int ret; /* Remove the rndis header and pass it back up the stack */ data_offset = RNDIS_HEADER_SIZE + rndis_pkt->data_offset; @@ -393,25 +418,59 @@ static int rndis_filter_receive_data(struct net_device *ndev, return NVSP_STAT_FAIL; } - vlan = rndis_get_ppi(rndis_pkt, IEEE_8021Q_INFO); + vlan = rndis_get_ppi(rndis_pkt, IEEE_8021Q_INFO, 0); + + csum_info = rndis_get_ppi(rndis_pkt, TCPIP_CHKSUM_PKTINFO, 0); - csum_info = rndis_get_ppi(rndis_pkt, TCPIP_CHKSUM_PKTINFO); + pktinfo_id = rndis_get_ppi(rndis_pkt, RNDIS_PKTINFO_ID, 1); data = (void *)msg + data_offset; - /* - * Remove the rndis trailer padding from rndis packet message + /* Identify RSC frags, drop erroneous packets */ + if (pktinfo_id && (pktinfo_id->flag & RNDIS_PKTINFO_SUBALLOC)) { + if (pktinfo_id->flag & RNDIS_PKTINFO_1ST_FRAG) + nvchan->rsc.cnt = 0; + else if (nvchan->rsc.cnt == 0) + goto drop; + + rsc_more = true; + + if (pktinfo_id->flag & RNDIS_PKTINFO_LAST_FRAG) + rsc_more = false; + + if (rsc_more && nvchan->rsc.is_last) + goto drop; + } else { + nvchan->rsc.cnt = 0; + } + + if (unlikely(nvchan->rsc.cnt >= NVSP_RSC_MAX)) + goto drop; + + /* Put data into per channel structure. + * Also, remove the rndis trailer padding from rndis packet message * rndis_pkt->data_len tell us the real data length, we only copy * the data packet to the stack, without the rndis trailer padding */ - return netvsc_recv_callback(ndev, nvdev, channel, - data, rndis_pkt->data_len, - csum_info, vlan); + rsc_add_data(nvchan, vlan, csum_info, data, rndis_pkt->data_len); + + if (rsc_more) + return NVSP_STAT_SUCCESS; + + ret = netvsc_recv_callback(ndev, nvdev, nvchan); + nvchan->rsc.cnt = 0; + + return ret; + +drop: + /* Drop incomplete packet */ + nvchan->rsc.cnt = 0; + return NVSP_STAT_FAIL; } int rndis_filter_receive(struct net_device *ndev, struct netvsc_device *net_dev, - struct vmbus_channel *channel, + struct netvsc_channel *nvchan, void *data, u32 buflen) { struct net_device_context *net_device_ctx = netdev_priv(ndev); @@ -422,7 +481,7 @@ int rndis_filter_receive(struct net_device *ndev, switch (rndis_msg->ndis_msg_type) { case RNDIS_MSG_PACKET: - return rndis_filter_receive_data(ndev, net_dev, channel, + return rndis_filter_receive_data(ndev, net_dev, nvchan, rndis_msg, buflen); case RNDIS_MSG_INIT_C: case RNDIS_MSG_QUERY_C: @@ -657,7 +716,7 @@ cleanup: return ret; } -static int +int rndis_filter_set_offload_params(struct net_device *ndev, struct netvsc_device *nvdev, struct ndis_offload_params *req_offloads) @@ -1184,6 +1243,18 @@ static int rndis_netdev_set_hwcaps(struct rndis_device *rndis_device, } } + if (hwcaps.rsc.ip4 && hwcaps.rsc.ip6) { + net->hw_features |= NETIF_F_LRO; + + if (net->features & NETIF_F_LRO) { + offloads.rsc_ip_v4 = NDIS_OFFLOAD_PARAMETERS_RSC_ENABLED; + offloads.rsc_ip_v6 = NDIS_OFFLOAD_PARAMETERS_RSC_ENABLED; + } else { + offloads.rsc_ip_v4 = NDIS_OFFLOAD_PARAMETERS_RSC_DISABLED; + offloads.rsc_ip_v6 = NDIS_OFFLOAD_PARAMETERS_RSC_DISABLED; + } + } + /* In case some hw_features disappeared we need to remove them from * net->features list as they're no longer supported. */ diff --git a/drivers/net/loopback.c b/drivers/net/loopback.c index 30612497643c..a7207fa7e451 100644 --- a/drivers/net/loopback.c +++ b/drivers/net/loopback.c @@ -59,12 +59,6 @@ #include <net/net_namespace.h> #include <linux/u64_stats_sync.h> -struct pcpu_lstats { - u64 packets; - u64 bytes; - struct u64_stats_sync syncp; -}; - /* The higher levels take care of making this non-reentrant (it's * called with bh's disabled). */ diff --git a/drivers/net/macsec.c b/drivers/net/macsec.c index 7de88b33d5b9..4bb90b6867a2 100644 --- a/drivers/net/macsec.c +++ b/drivers/net/macsec.c @@ -64,9 +64,9 @@ struct macsec_eth_header { #define MACSEC_NUM_AN 4 /* 2 bits for the association number */ -#define for_each_rxsc(secy, sc) \ +#define for_each_rxsc(secy, sc) \ for (sc = rcu_dereference_bh(secy->rx_sc); \ - sc; \ + sc; \ sc = rcu_dereference_bh(sc->next)) #define for_each_rxsc_rtnl(secy, sc) \ for (sc = rtnl_dereference(secy->rx_sc); \ @@ -1142,6 +1142,7 @@ static rx_handler_result_t macsec_handle_frame(struct sk_buff **pskb) list_for_each_entry_rcu(macsec, &rxd->secys, secys) { struct macsec_rx_sc *sc = find_rx_sc(&macsec->secy, sci); + sc = sc ? macsec_rxsc_get(sc) : NULL; if (sc) { @@ -1584,7 +1585,6 @@ static struct macsec_rx_sa *get_rxsa_from_nl(struct net *net, return rx_sa; } - static const struct nla_policy macsec_genl_policy[NUM_MACSEC_ATTR] = { [MACSEC_ATTR_IFINDEX] = { .type = NLA_U32 }, [MACSEC_ATTR_RXSC_CONFIG] = { .type = NLA_NESTED }, @@ -2156,7 +2156,7 @@ static int macsec_upd_rxsc(struct sk_buff *skb, struct genl_info *info) } static int copy_tx_sa_stats(struct sk_buff *skb, - struct macsec_tx_sa_stats __percpu *pstats) + struct macsec_tx_sa_stats __percpu *pstats) { struct macsec_tx_sa_stats sum = {0, }; int cpu; @@ -2176,7 +2176,7 @@ static int copy_tx_sa_stats(struct sk_buff *skb, } static int copy_rx_sa_stats(struct sk_buff *skb, - struct macsec_rx_sa_stats __percpu *pstats) + struct macsec_rx_sa_stats __percpu *pstats) { struct macsec_rx_sa_stats sum = {0, }; int cpu; @@ -2202,7 +2202,7 @@ static int copy_rx_sa_stats(struct sk_buff *skb, } static int copy_rx_sc_stats(struct sk_buff *skb, - struct pcpu_rx_sc_stats __percpu *pstats) + struct pcpu_rx_sc_stats __percpu *pstats) { struct macsec_rx_sc_stats sum = {0, }; int cpu; @@ -2266,7 +2266,7 @@ static int copy_rx_sc_stats(struct sk_buff *skb, } static int copy_tx_sc_stats(struct sk_buff *skb, - struct pcpu_tx_sc_stats __percpu *pstats) + struct pcpu_tx_sc_stats __percpu *pstats) { struct macsec_tx_sc_stats sum = {0, }; int cpu; @@ -2306,7 +2306,7 @@ static int copy_tx_sc_stats(struct sk_buff *skb, } static int copy_secy_stats(struct sk_buff *skb, - struct pcpu_secy_stats __percpu *pstats) + struct pcpu_secy_stats __percpu *pstats) { struct macsec_dev_stats sum = {0, }; int cpu; @@ -2962,13 +2962,11 @@ static int macsec_get_iflink(const struct net_device *dev) return macsec_priv(dev)->real_dev->ifindex; } - static int macsec_get_nest_level(struct net_device *dev) { return macsec_priv(dev)->nest_level; } - static const struct net_device_ops macsec_netdev_ops = { .ndo_init = macsec_dev_init, .ndo_uninit = macsec_dev_uninit, diff --git a/drivers/net/net_failover.c b/drivers/net/net_failover.c index 192ae1cd17f0..e964d312f4ca 100644 --- a/drivers/net/net_failover.c +++ b/drivers/net/net_failover.c @@ -602,6 +602,9 @@ static int net_failover_slave_unregister(struct net_device *slave_dev, primary_dev = rtnl_dereference(nfo_info->primary_dev); standby_dev = rtnl_dereference(nfo_info->standby_dev); + if (WARN_ON_ONCE(slave_dev != primary_dev && slave_dev != standby_dev)) + return -ENODEV; + vlan_vids_del_by_dev(slave_dev, failover_dev); dev_uc_unsync(slave_dev, failover_dev); dev_mc_unsync(slave_dev, failover_dev); @@ -761,8 +764,10 @@ struct failover *net_failover_create(struct net_device *standby_dev) netif_carrier_off(failover_dev); failover = failover_register(failover_dev, &net_failover_ops); - if (IS_ERR(failover)) + if (IS_ERR(failover)) { + err = PTR_ERR(failover); goto err_failover_register; + } return failover; diff --git a/drivers/net/nlmon.c b/drivers/net/nlmon.c index 4b22955de191..dd0db7534cb3 100644 --- a/drivers/net/nlmon.c +++ b/drivers/net/nlmon.c @@ -6,12 +6,6 @@ #include <linux/if_arp.h> #include <net/rtnetlink.h> -struct pcpu_lstats { - u64 packets; - u64 bytes; - struct u64_stats_sync syncp; -}; - static netdev_tx_t nlmon_xmit(struct sk_buff *skb, struct net_device *dev) { int len = skb->len; diff --git a/drivers/net/phy/Kconfig b/drivers/net/phy/Kconfig index 82070792edbb..3d187cd50eb0 100644 --- a/drivers/net/phy/Kconfig +++ b/drivers/net/phy/Kconfig @@ -240,7 +240,7 @@ config AT803X_PHY config BCM63XX_PHY tristate "Broadcom 63xx SOCs internal PHY" - depends on BCM63XX + depends on BCM63XX || COMPILE_TEST select BCM_NET_PHYLIB ---help--- Currently supports the 6348 and 6358 PHYs. diff --git a/drivers/net/phy/et1011c.c b/drivers/net/phy/et1011c.c index a9a4edfa23c8..565e49e7f76f 100644 --- a/drivers/net/phy/et1011c.c +++ b/drivers/net/phy/et1011c.c @@ -91,8 +91,7 @@ static struct phy_driver et1011c_driver[] = { { .phy_id = 0x0282f014, .name = "ET1011C", .phy_id_mask = 0xfffffff0, - .features = (PHY_BASIC_FEATURES | SUPPORTED_1000baseT_Full), - .flags = PHY_POLL, + .features = PHY_GBIT_FEATURES, .config_aneg = et1011c_config_aneg, .read_status = et1011c_read_status, } }; diff --git a/drivers/net/phy/marvell.c b/drivers/net/phy/marvell.c index f7c69ca34056..b55a7376bfdc 100644 --- a/drivers/net/phy/marvell.c +++ b/drivers/net/phy/marvell.c @@ -265,7 +265,7 @@ static int marvell_set_polarity(struct phy_device *phydev, int polarity) return err; } - return 0; + return val != reg; } static int marvell_set_downshift(struct phy_device *phydev, bool enable, @@ -287,12 +287,15 @@ static int marvell_set_downshift(struct phy_device *phydev, bool enable, static int marvell_config_aneg(struct phy_device *phydev) { + int changed = 0; int err; err = marvell_set_polarity(phydev, phydev->mdix_ctrl); if (err < 0) return err; + changed = err; + err = phy_write(phydev, MII_M1111_PHY_LED_CONTROL, MII_M1111_PHY_LED_DIRECT); if (err < 0) @@ -302,7 +305,7 @@ static int marvell_config_aneg(struct phy_device *phydev) if (err < 0) return err; - if (phydev->autoneg != AUTONEG_ENABLE) { + if (phydev->autoneg != AUTONEG_ENABLE || changed) { /* A write to speed/duplex bits (that is performed by * genphy_config_aneg() call above) must be followed by * a software reset. Otherwise, the write has no effect. @@ -350,42 +353,6 @@ static int m88e1101_config_aneg(struct phy_device *phydev) return marvell_config_aneg(phydev); } -static int m88e1111_config_aneg(struct phy_device *phydev) -{ - int err; - - /* The Marvell PHY has an errata which requires - * that certain registers get written in order - * to restart autonegotiation - */ - err = genphy_soft_reset(phydev); - - err = marvell_set_polarity(phydev, phydev->mdix_ctrl); - if (err < 0) - return err; - - err = phy_write(phydev, MII_M1111_PHY_LED_CONTROL, - MII_M1111_PHY_LED_DIRECT); - if (err < 0) - return err; - - err = genphy_config_aneg(phydev); - if (err < 0) - return err; - - if (phydev->autoneg != AUTONEG_ENABLE) { - /* A write to speed/duplex bits (that is performed by - * genphy_config_aneg() call above) must be followed by - * a software reset. Otherwise, the write has no effect. - */ - err = genphy_soft_reset(phydev); - if (err < 0) - return err; - } - - return 0; -} - #ifdef CONFIG_OF_MDIO /* Set and/or override some configuration registers based on the * marvell,reg-init property stored in the of_node for the phydev. @@ -479,6 +446,7 @@ static int m88e1121_config_aneg_rgmii_delays(struct phy_device *phydev) static int m88e1121_config_aneg(struct phy_device *phydev) { + int changed = 0; int err = 0; if (phy_interface_is_rgmii(phydev)) { @@ -487,15 +455,26 @@ static int m88e1121_config_aneg(struct phy_device *phydev) return err; } - err = genphy_soft_reset(phydev); + err = marvell_set_polarity(phydev, phydev->mdix_ctrl); if (err < 0) return err; - err = marvell_set_polarity(phydev, phydev->mdix_ctrl); + changed = err; + + err = genphy_config_aneg(phydev); if (err < 0) return err; - return genphy_config_aneg(phydev); + if (phydev->autoneg != autoneg || changed) { + /* A software reset is used to ensure a "commit" of the + * changes is done. + */ + err = genphy_soft_reset(phydev); + if (err < 0) + return err; + } + + return 0; } static int m88e1318_config_aneg(struct phy_device *phydev) @@ -2067,7 +2046,7 @@ static struct phy_driver marvell_drivers[] = { .flags = PHY_HAS_INTERRUPT, .probe = marvell_probe, .config_init = &m88e1111_config_init, - .config_aneg = &m88e1111_config_aneg, + .config_aneg = &marvell_config_aneg, .read_status = &marvell_read_status, .ack_interrupt = &marvell_ack_interrupt, .config_intr = &marvell_config_intr, diff --git a/drivers/net/phy/mdio-bcm-unimac.c b/drivers/net/phy/mdio-bcm-unimac.c index 8d370667fa1b..80b9583eaa95 100644 --- a/drivers/net/phy/mdio-bcm-unimac.c +++ b/drivers/net/phy/mdio-bcm-unimac.c @@ -16,6 +16,7 @@ #include <linux/module.h> #include <linux/io.h> #include <linux/delay.h> +#include <linux/clk.h> #include <linux/of.h> #include <linux/of_platform.h> @@ -45,6 +46,8 @@ struct unimac_mdio_priv { void __iomem *base; int (*wait_func) (void *wait_func_data); void *wait_func_data; + struct clk *clk; + u32 clk_freq; }; static inline u32 unimac_mdio_readl(struct unimac_mdio_priv *priv, u32 offset) @@ -189,6 +192,35 @@ static int unimac_mdio_reset(struct mii_bus *bus) return 0; } +static void unimac_mdio_clk_set(struct unimac_mdio_priv *priv) +{ + unsigned long rate; + u32 reg, div; + + /* Keep the hardware default values */ + if (!priv->clk_freq) + return; + + if (!priv->clk) + rate = 250000000; + else + rate = clk_get_rate(priv->clk); + + div = (rate / (2 * priv->clk_freq)) - 1; + if (div & ~MDIO_CLK_DIV_MASK) { + pr_warn("Incorrect MDIO clock frequency, ignoring\n"); + return; + } + + /* The MDIO clock is the reference clock (typicaly 250Mhz) divided by + * 2 x (MDIO_CLK_DIV + 1) + */ + reg = unimac_mdio_readl(priv, MDIO_CFG); + reg &= ~(MDIO_CLK_DIV_MASK << MDIO_CLK_DIV_SHIFT); + reg |= div << MDIO_CLK_DIV_SHIFT; + unimac_mdio_writel(priv, reg, MDIO_CFG); +} + static int unimac_mdio_probe(struct platform_device *pdev) { struct unimac_mdio_pdata *pdata = pdev->dev.platform_data; @@ -217,9 +249,26 @@ static int unimac_mdio_probe(struct platform_device *pdev) return -ENOMEM; } + priv->clk = devm_clk_get(&pdev->dev, NULL); + if (PTR_ERR(priv->clk) == -EPROBE_DEFER) + return PTR_ERR(priv->clk); + else + priv->clk = NULL; + + ret = clk_prepare_enable(priv->clk); + if (ret) + return ret; + + if (of_property_read_u32(np, "clock-frequency", &priv->clk_freq)) + priv->clk_freq = 0; + + unimac_mdio_clk_set(priv); + priv->mii_bus = mdiobus_alloc(); - if (!priv->mii_bus) - return -ENOMEM; + if (!priv->mii_bus) { + ret = -ENOMEM; + goto out_clk_disable; + } bus = priv->mii_bus; bus->priv = priv; @@ -253,6 +302,8 @@ static int unimac_mdio_probe(struct platform_device *pdev) out_mdio_free: mdiobus_free(bus); +out_clk_disable: + clk_disable_unprepare(priv->clk); return ret; } @@ -262,10 +313,37 @@ static int unimac_mdio_remove(struct platform_device *pdev) mdiobus_unregister(priv->mii_bus); mdiobus_free(priv->mii_bus); + clk_disable_unprepare(priv->clk); + + return 0; +} + +static int unimac_mdio_suspend(struct device *d) +{ + struct unimac_mdio_priv *priv = dev_get_drvdata(d); + + clk_disable_unprepare(priv->clk); + + return 0; +} + +static int unimac_mdio_resume(struct device *d) +{ + struct unimac_mdio_priv *priv = dev_get_drvdata(d); + int ret; + + ret = clk_prepare_enable(priv->clk); + if (ret) + return ret; + + unimac_mdio_clk_set(priv); return 0; } +static SIMPLE_DEV_PM_OPS(unimac_mdio_pm_ops, + unimac_mdio_suspend, unimac_mdio_resume); + static const struct of_device_id unimac_mdio_ids[] = { { .compatible = "brcm,genet-mdio-v5", }, { .compatible = "brcm,genet-mdio-v4", }, @@ -281,6 +359,7 @@ static struct platform_driver unimac_mdio_driver = { .driver = { .name = UNIMAC_MDIO_DRV_NAME, .of_match_table = unimac_mdio_ids, + .pm = &unimac_mdio_pm_ops, }, .probe = unimac_mdio_probe, .remove = unimac_mdio_remove, diff --git a/drivers/net/phy/mdio_bus.c b/drivers/net/phy/mdio_bus.c index 98f4b1f706df..2e59a8419b17 100644 --- a/drivers/net/phy/mdio_bus.c +++ b/drivers/net/phy/mdio_bus.c @@ -38,7 +38,6 @@ #include <linux/phy.h> #include <linux/io.h> #include <linux/uaccess.h> -#include <linux/gpio/consumer.h> #include <asm/irq.h> diff --git a/drivers/net/phy/phy.c b/drivers/net/phy/phy.c index 1ee25877c4d1..a1f8e4816f72 100644 --- a/drivers/net/phy/phy.c +++ b/drivers/net/phy/phy.c @@ -861,6 +861,8 @@ void phy_stop(struct phy_device *phydev) out_unlock: mutex_unlock(&phydev->lock); + phy_state_machine(&phydev->state_queue.work); + /* Cannot call flush_scheduled_work() here as desired because * of rtnl_lock(), but PHY_HALTED shall guarantee phy_change() * will not reenable interrupts. @@ -1121,9 +1123,13 @@ void phy_state_machine(struct work_struct *work) /* Only re-schedule a PHY state machine change if we are polling the * PHY, if PHY_IGNORE_INTERRUPT is set, then we will be moving - * between states from phy_mac_interrupt() + * between states from phy_mac_interrupt(). + * + * In state PHY_HALTED the PHY gets suspended, so rescheduling the + * state machine would be pointless and possibly error prone when + * called from phy_disconnect() synchronously. */ - if (phy_polling_mode(phydev)) + if (phy_polling_mode(phydev) && old_state != PHY_HALTED) queue_delayed_work(system_power_efficient_wq, &phydev->state_queue, PHY_STATE_TIME * HZ); } diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c index db1172db1e7c..ee676d75fe02 100644 --- a/drivers/net/phy/phy_device.c +++ b/drivers/net/phy/phy_device.c @@ -880,8 +880,6 @@ int phy_init_hw(struct phy_device *phydev) if (phydev->drv->soft_reset) ret = phydev->drv->soft_reset(phydev); - else - ret = genphy_soft_reset(phydev); if (ret < 0) return ret; @@ -1765,6 +1763,124 @@ int phy_set_max_speed(struct phy_device *phydev, u32 max_speed) } EXPORT_SYMBOL(phy_set_max_speed); +/** + * phy_remove_link_mode - Remove a supported link mode + * @phydev: phy_device structure to remove link mode from + * @link_mode: Link mode to be removed + * + * Description: Some MACs don't support all link modes which the PHY + * does. e.g. a 1G MAC often does not support 1000Half. Add a helper + * to remove a link mode. + */ +void phy_remove_link_mode(struct phy_device *phydev, u32 link_mode) +{ + WARN_ON(link_mode > 31); + + phydev->supported &= ~BIT(link_mode); + phydev->advertising = phydev->supported; +} +EXPORT_SYMBOL(phy_remove_link_mode); + +/** + * phy_support_sym_pause - Enable support of symmetrical pause + * @phydev: target phy_device struct + * + * Description: Called by the MAC to indicate is supports symmetrical + * Pause, but not asym pause. + */ +void phy_support_sym_pause(struct phy_device *phydev) +{ + phydev->supported |= SUPPORTED_Pause; + phydev->advertising = phydev->supported; +} +EXPORT_SYMBOL(phy_support_sym_pause); + +/** + * phy_support_asym_pause - Enable support of asym pause + * @phydev: target phy_device struct + * + * Description: Called by the MAC to indicate is supports Asym Pause. + */ +void phy_support_asym_pause(struct phy_device *phydev) +{ + phydev->supported |= SUPPORTED_Pause | SUPPORTED_Asym_Pause; + phydev->advertising = phydev->supported; +} +EXPORT_SYMBOL(phy_support_asym_pause); + +/** + * phy_set_sym_pause - Configure symmetric Pause + * @phydev: target phy_device struct + * @rx: Receiver Pause is supported + * @tx: Transmit Pause is supported + * @autoneg: Auto neg should be used + * + * Description: Configure advertised Pause support depending on if + * receiver pause and pause auto neg is supported. Generally called + * from the set_pauseparam .ndo. + */ +void phy_set_sym_pause(struct phy_device *phydev, bool rx, bool tx, + bool autoneg) +{ + phydev->supported &= ~SUPPORTED_Pause; + + if (rx && tx && autoneg) + phydev->supported |= SUPPORTED_Pause; + + phydev->advertising = phydev->supported; +} +EXPORT_SYMBOL(phy_set_sym_pause); + +/** + * phy_set_asym_pause - Configure Pause and Asym Pause + * @phydev: target phy_device struct + * @rx: Receiver Pause is supported + * @tx: Transmit Pause is supported + * + * Description: Configure advertised Pause support depending on if + * transmit and receiver pause is supported. If there has been a + * change in adverting, trigger a new autoneg. Generally called from + * the set_pauseparam .ndo. + */ +void phy_set_asym_pause(struct phy_device *phydev, bool rx, bool tx) +{ + u16 oldadv = phydev->advertising; + u16 newadv = oldadv &= ~(SUPPORTED_Pause | SUPPORTED_Asym_Pause); + + if (rx) + newadv |= SUPPORTED_Pause | SUPPORTED_Asym_Pause; + if (tx) + newadv ^= SUPPORTED_Asym_Pause; + + if (oldadv != newadv) { + phydev->advertising = newadv; + + if (phydev->autoneg) + phy_start_aneg(phydev); + } +} +EXPORT_SYMBOL(phy_set_asym_pause); + +/** + * phy_validate_pause - Test if the PHY/MAC support the pause configuration + * @phydev: phy_device struct + * @pp: requested pause configuration + * + * Description: Test if the PHY/MAC combination supports the Pause + * configuration the user is requesting. Returns True if it is + * supported, false otherwise. + */ +bool phy_validate_pause(struct phy_device *phydev, + struct ethtool_pauseparam *pp) +{ + if (!(phydev->supported & SUPPORTED_Pause) || + (!(phydev->supported & SUPPORTED_Asym_Pause) && + pp->rx_pause != pp->tx_pause)) + return false; + return true; +} +EXPORT_SYMBOL(phy_validate_pause); + static void of_set_phy_supported(struct phy_device *phydev) { struct device_node *node = phydev->mdio.dev.of_node; diff --git a/drivers/net/phy/phylink.c b/drivers/net/phy/phylink.c index 3ba5cf2a8a5f..1d01e0c625a5 100644 --- a/drivers/net/phy/phylink.c +++ b/drivers/net/phy/phylink.c @@ -901,6 +901,9 @@ void phylink_start(struct phylink *pl) phylink_an_mode_str(pl->link_an_mode), phy_modes(pl->link_config.interface)); + /* Always set the carrier off */ + netif_carrier_off(pl->netdev); + /* Apply the link configuration to the MAC when starting. This allows * a fixed-link to start with the correct parameters, and also * ensures that we set the appropriate advertisement for Serdes links. diff --git a/drivers/net/phy/sfp-bus.c b/drivers/net/phy/sfp-bus.c index 740655261e5b..83060fb349f4 100644 --- a/drivers/net/phy/sfp-bus.c +++ b/drivers/net/phy/sfp-bus.c @@ -349,6 +349,7 @@ static int sfp_register_bus(struct sfp_bus *bus) } if (bus->started) bus->socket_ops->start(bus->sfp); + bus->netdev->sfp_bus = bus; bus->registered = true; return 0; } @@ -357,6 +358,7 @@ static void sfp_unregister_bus(struct sfp_bus *bus) { const struct sfp_upstream_ops *ops = bus->upstream_ops; + bus->netdev->sfp_bus = NULL; if (bus->registered) { if (bus->started) bus->socket_ops->stop(bus->sfp); @@ -438,7 +440,6 @@ static void sfp_upstream_clear(struct sfp_bus *bus) { bus->upstream_ops = NULL; bus->upstream = NULL; - bus->netdev->sfp_bus = NULL; bus->netdev = NULL; } @@ -467,7 +468,6 @@ struct sfp_bus *sfp_register_upstream(struct fwnode_handle *fwnode, bus->upstream_ops = ops; bus->upstream = upstream; bus->netdev = ndev; - ndev->sfp_bus = bus; if (bus->sfp) { ret = sfp_register_bus(bus); diff --git a/drivers/net/phy/ste10Xp.c b/drivers/net/phy/ste10Xp.c index fbd548a1ad84..2fe9a87b55b5 100644 --- a/drivers/net/phy/ste10Xp.c +++ b/drivers/net/phy/ste10Xp.c @@ -86,7 +86,7 @@ static struct phy_driver ste10xp_pdriver[] = { .phy_id = STE101P_PHY_ID, .phy_id_mask = 0xfffffff0, .name = "STe101p", - .features = PHY_BASIC_FEATURES | SUPPORTED_Pause, + .features = PHY_BASIC_FEATURES, .flags = PHY_HAS_INTERRUPT, .config_init = ste10Xp_config_init, .ack_interrupt = ste10Xp_ack_interrupt, @@ -97,7 +97,7 @@ static struct phy_driver ste10xp_pdriver[] = { .phy_id = STE100P_PHY_ID, .phy_id_mask = 0xffffffff, .name = "STe100p", - .features = PHY_BASIC_FEATURES | SUPPORTED_Pause, + .features = PHY_BASIC_FEATURES, .flags = PHY_HAS_INTERRUPT, .config_init = ste10Xp_config_init, .ack_interrupt = ste10Xp_ack_interrupt, diff --git a/drivers/net/ppp/ppp_generic.c b/drivers/net/ppp/ppp_generic.c index 02ad03a2fab7..500bc0027c1b 100644 --- a/drivers/net/ppp/ppp_generic.c +++ b/drivers/net/ppp/ppp_generic.c @@ -2400,7 +2400,7 @@ ppp_mp_reconstruct(struct ppp *ppp) if (ppp->mrru == 0) /* do nothing until mrru is set */ return NULL; - head = list->next; + head = __skb_peek(list); tail = NULL; skb_queue_walk_safe(list, p, tmp) { again: diff --git a/drivers/net/ppp/pppoe.c b/drivers/net/ppp/pppoe.c index ce61231e96ea..62dc564b251d 100644 --- a/drivers/net/ppp/pppoe.c +++ b/drivers/net/ppp/pppoe.c @@ -429,6 +429,9 @@ static int pppoe_rcv(struct sk_buff *skb, struct net_device *dev, if (!skb) goto out; + if (skb_mac_header_len(skb) < ETH_HLEN) + goto drop; + if (!pskb_may_pull(skb, sizeof(struct pppoe_hdr))) goto drop; diff --git a/drivers/net/tap.c b/drivers/net/tap.c index f0f7cd977667..f03004f37eca 100644 --- a/drivers/net/tap.c +++ b/drivers/net/tap.c @@ -619,7 +619,7 @@ static inline struct sk_buff *tap_alloc_skb(struct sock *sk, size_t prepad, #define TAP_RESERVE HH_DATA_OFF(ETH_HLEN) /* Get packet from user space buffer */ -static ssize_t tap_get_user(struct tap_queue *q, struct msghdr *m, +static ssize_t tap_get_user(struct tap_queue *q, void *msg_control, struct iov_iter *from, int noblock) { int good_linear = SKB_MAX_HEAD(TAP_RESERVE); @@ -663,7 +663,7 @@ static ssize_t tap_get_user(struct tap_queue *q, struct msghdr *m, if (unlikely(len < ETH_HLEN)) goto err; - if (m && m->msg_control && sock_flag(&q->sk, SOCK_ZEROCOPY)) { + if (msg_control && sock_flag(&q->sk, SOCK_ZEROCOPY)) { struct iov_iter i; copylen = vnet_hdr.hdr_len ? @@ -724,11 +724,11 @@ static ssize_t tap_get_user(struct tap_queue *q, struct msghdr *m, tap = rcu_dereference(q->tap); /* copy skb_ubuf_info for callback when skb has no error */ if (zerocopy) { - skb_shinfo(skb)->destructor_arg = m->msg_control; + skb_shinfo(skb)->destructor_arg = msg_control; skb_shinfo(skb)->tx_flags |= SKBTX_DEV_ZEROCOPY; skb_shinfo(skb)->tx_flags |= SKBTX_SHARED_FRAG; - } else if (m && m->msg_control) { - struct ubuf_info *uarg = m->msg_control; + } else if (msg_control) { + struct ubuf_info *uarg = msg_control; uarg->callback(uarg, false); } @@ -830,8 +830,7 @@ static ssize_t tap_do_read(struct tap_queue *q, ssize_t ret = 0; if (!iov_iter_count(to)) { - if (skb) - kfree_skb(skb); + kfree_skb(skb); return 0; } @@ -1146,11 +1145,87 @@ static const struct file_operations tap_fops = { #endif }; +static int tap_get_user_xdp(struct tap_queue *q, struct xdp_buff *xdp) +{ + struct tun_xdp_hdr *hdr = xdp->data_hard_start; + struct virtio_net_hdr *gso = &hdr->gso; + int buflen = hdr->buflen; + int vnet_hdr_len = 0; + struct tap_dev *tap; + struct sk_buff *skb; + int err, depth; + + if (q->flags & IFF_VNET_HDR) + vnet_hdr_len = READ_ONCE(q->vnet_hdr_sz); + + skb = build_skb(xdp->data_hard_start, buflen); + if (!skb) { + err = -ENOMEM; + goto err; + } + + skb_reserve(skb, xdp->data - xdp->data_hard_start); + skb_put(skb, xdp->data_end - xdp->data); + + skb_set_network_header(skb, ETH_HLEN); + skb_reset_mac_header(skb); + skb->protocol = eth_hdr(skb)->h_proto; + + if (vnet_hdr_len) { + err = virtio_net_hdr_to_skb(skb, gso, tap_is_little_endian(q)); + if (err) + goto err_kfree; + } + + skb_probe_transport_header(skb, ETH_HLEN); + + /* Move network header to the right position for VLAN tagged packets */ + if ((skb->protocol == htons(ETH_P_8021Q) || + skb->protocol == htons(ETH_P_8021AD)) && + __vlan_get_protocol(skb, skb->protocol, &depth) != 0) + skb_set_network_header(skb, depth); + + rcu_read_lock(); + tap = rcu_dereference(q->tap); + if (tap) { + skb->dev = tap->dev; + dev_queue_xmit(skb); + } else { + kfree_skb(skb); + } + rcu_read_unlock(); + + return 0; + +err_kfree: + kfree_skb(skb); +err: + rcu_read_lock(); + tap = rcu_dereference(q->tap); + if (tap && tap->count_tx_dropped) + tap->count_tx_dropped(tap); + rcu_read_unlock(); + return err; +} + static int tap_sendmsg(struct socket *sock, struct msghdr *m, size_t total_len) { struct tap_queue *q = container_of(sock, struct tap_queue, sock); - return tap_get_user(q, m, &m->msg_iter, m->msg_flags & MSG_DONTWAIT); + struct tun_msg_ctl *ctl = m->msg_control; + struct xdp_buff *xdp; + int i; + + if (ctl && (ctl->type == TUN_MSG_PTR)) { + for (i = 0; i < ctl->num; i++) { + xdp = &((struct xdp_buff *)ctl->ptr)[i]; + tap_get_user_xdp(q, xdp); + } + return 0; + } + + return tap_get_user(q, ctl ? ctl->ptr : NULL, &m->msg_iter, + m->msg_flags & MSG_DONTWAIT); } static int tap_recvmsg(struct socket *sock, struct msghdr *m, @@ -1160,8 +1235,7 @@ static int tap_recvmsg(struct socket *sock, struct msghdr *m, struct sk_buff *skb = m->msg_control; int ret; if (flags & ~(MSG_DONTWAIT|MSG_TRUNC)) { - if (skb) - kfree_skb(skb); + kfree_skb(skb); return -EINVAL; } ret = tap_do_read(q, &m->msg_iter, flags & MSG_DONTWAIT, skb); diff --git a/drivers/net/tun.c b/drivers/net/tun.c index ebd07ad82431..3eb88b7147f0 100644 --- a/drivers/net/tun.c +++ b/drivers/net/tun.c @@ -113,7 +113,6 @@ do { \ } while (0) #endif -#define TUN_HEADROOM 256 #define TUN_RX_PAD (NET_IP_ALIGN + NET_SKB_PAD) /* TUN device flags */ @@ -869,6 +868,9 @@ static int tun_attach(struct tun_struct *tun, struct file *file, tun_napi_init(tun, tfile, napi); } + if (rtnl_dereference(tun->xdp_prog)) + sock_set_flag(&tfile->sk, SOCK_XDP); + tun_set_real_num_queues(tun); /* device is allowed to go away first, so no need to hold extra @@ -1153,43 +1155,6 @@ static netdev_features_t tun_net_fix_features(struct net_device *dev, return (features & tun->set_features) | (features & ~TUN_USER_FEATURES); } -#ifdef CONFIG_NET_POLL_CONTROLLER -static void tun_poll_controller(struct net_device *dev) -{ - /* - * Tun only receives frames when: - * 1) the char device endpoint gets data from user space - * 2) the tun socket gets a sendmsg call from user space - * If NAPI is not enabled, since both of those are synchronous - * operations, we are guaranteed never to have pending data when we poll - * for it so there is nothing to do here but return. - * We need this though so netpoll recognizes us as an interface that - * supports polling, which enables bridge devices in virt setups to - * still use netconsole - * If NAPI is enabled, however, we need to schedule polling for all - * queues unless we are using napi_gro_frags(), which we call in - * process context and not in NAPI context. - */ - struct tun_struct *tun = netdev_priv(dev); - - if (tun->flags & IFF_NAPI) { - struct tun_file *tfile; - int i; - - if (tun_napi_frags_enabled(tun)) - return; - - rcu_read_lock(); - for (i = 0; i < tun->numqueues; i++) { - tfile = rcu_dereference(tun->tfiles[i]); - if (tfile->napi_enabled) - napi_schedule(&tfile->napi); - } - rcu_read_unlock(); - } - return; -} -#endif static void tun_set_headroom(struct net_device *dev, int new_hr) { @@ -1241,13 +1206,29 @@ static int tun_xdp_set(struct net_device *dev, struct bpf_prog *prog, struct netlink_ext_ack *extack) { struct tun_struct *tun = netdev_priv(dev); + struct tun_file *tfile; struct bpf_prog *old_prog; + int i; old_prog = rtnl_dereference(tun->xdp_prog); rcu_assign_pointer(tun->xdp_prog, prog); if (old_prog) bpf_prog_put(old_prog); + for (i = 0; i < tun->numqueues; i++) { + tfile = rtnl_dereference(tun->tfiles[i]); + if (prog) + sock_set_flag(&tfile->sk, SOCK_XDP); + else + sock_reset_flag(&tfile->sk, SOCK_XDP); + } + list_for_each_entry(tfile, &tun->disabled, next) { + if (prog) + sock_set_flag(&tfile->sk, SOCK_XDP); + else + sock_reset_flag(&tfile->sk, SOCK_XDP); + } + return 0; } @@ -1283,9 +1264,6 @@ static const struct net_device_ops tun_netdev_ops = { .ndo_start_xmit = tun_net_xmit, .ndo_fix_features = tun_net_fix_features, .ndo_select_queue = tun_select_queue, -#ifdef CONFIG_NET_POLL_CONTROLLER - .ndo_poll_controller = tun_poll_controller, -#endif .ndo_set_rx_headroom = tun_set_headroom, .ndo_get_stats64 = tun_net_get_stats64, }; @@ -1365,9 +1343,6 @@ static const struct net_device_ops tap_netdev_ops = { .ndo_set_mac_address = eth_mac_addr, .ndo_validate_addr = eth_validate_addr, .ndo_select_queue = tun_select_queue, -#ifdef CONFIG_NET_POLL_CONTROLLER - .ndo_poll_controller = tun_poll_controller, -#endif .ndo_features_check = passthru_features_check, .ndo_set_rx_headroom = tun_set_headroom, .ndo_get_stats64 = tun_net_get_stats64, @@ -1617,6 +1592,55 @@ static bool tun_can_build_skb(struct tun_struct *tun, struct tun_file *tfile, return true; } +static struct sk_buff *__tun_build_skb(struct page_frag *alloc_frag, char *buf, + int buflen, int len, int pad) +{ + struct sk_buff *skb = build_skb(buf, buflen); + + if (!skb) + return ERR_PTR(-ENOMEM); + + skb_reserve(skb, pad); + skb_put(skb, len); + + get_page(alloc_frag->page); + alloc_frag->offset += buflen; + + return skb; +} + +static int tun_xdp_act(struct tun_struct *tun, struct bpf_prog *xdp_prog, + struct xdp_buff *xdp, u32 act) +{ + int err; + + switch (act) { + case XDP_REDIRECT: + err = xdp_do_redirect(tun->dev, xdp, xdp_prog); + if (err) + return err; + break; + case XDP_TX: + err = tun_xdp_tx(tun->dev, xdp); + if (err < 0) + return err; + break; + case XDP_PASS: + break; + default: + bpf_warn_invalid_xdp_action(act); + /* fall through */ + case XDP_ABORTED: + trace_xdp_exception(tun->dev, xdp_prog, act); + /* fall through */ + case XDP_DROP: + this_cpu_inc(tun->pcpu_stats->rx_dropped); + break; + } + + return act; +} + static struct sk_buff *tun_build_skb(struct tun_struct *tun, struct tun_file *tfile, struct iov_iter *from, @@ -1624,18 +1648,17 @@ static struct sk_buff *tun_build_skb(struct tun_struct *tun, int len, int *skb_xdp) { struct page_frag *alloc_frag = ¤t->task_frag; - struct sk_buff *skb; struct bpf_prog *xdp_prog; int buflen = SKB_DATA_ALIGN(sizeof(struct skb_shared_info)); - unsigned int delta = 0; char *buf; size_t copied; - int err, pad = TUN_RX_PAD; + int pad = TUN_RX_PAD; + int err = 0; rcu_read_lock(); xdp_prog = rcu_dereference(tun->xdp_prog); if (xdp_prog) - pad += TUN_HEADROOM; + pad += XDP_PACKET_HEADROOM; buflen += SKB_DATA_ALIGN(len + pad); rcu_read_unlock(); @@ -1654,17 +1677,18 @@ static struct sk_buff *tun_build_skb(struct tun_struct *tun, * of xdp_prog above, this should be rare and for simplicity * we do XDP on skb in case the headroom is not enough. */ - if (hdr->gso_type || !xdp_prog) + if (hdr->gso_type || !xdp_prog) { *skb_xdp = 1; - else - *skb_xdp = 0; + return __tun_build_skb(alloc_frag, buf, buflen, len, pad); + } + + *skb_xdp = 0; local_bh_disable(); rcu_read_lock(); xdp_prog = rcu_dereference(tun->xdp_prog); - if (xdp_prog && !*skb_xdp) { + if (xdp_prog) { struct xdp_buff xdp; - void *orig_data; u32 act; xdp.data_hard_start = buf; @@ -1672,66 +1696,33 @@ static struct sk_buff *tun_build_skb(struct tun_struct *tun, xdp_set_data_meta_invalid(&xdp); xdp.data_end = xdp.data + len; xdp.rxq = &tfile->xdp_rxq; - orig_data = xdp.data; - act = bpf_prog_run_xdp(xdp_prog, &xdp); - switch (act) { - case XDP_REDIRECT: - get_page(alloc_frag->page); - alloc_frag->offset += buflen; - err = xdp_do_redirect(tun->dev, &xdp, xdp_prog); - xdp_do_flush_map(); - if (err) - goto err_redirect; - rcu_read_unlock(); - local_bh_enable(); - return NULL; - case XDP_TX: + act = bpf_prog_run_xdp(xdp_prog, &xdp); + if (act == XDP_REDIRECT || act == XDP_TX) { get_page(alloc_frag->page); alloc_frag->offset += buflen; - if (tun_xdp_tx(tun->dev, &xdp) < 0) - goto err_redirect; - rcu_read_unlock(); - local_bh_enable(); - return NULL; - case XDP_PASS: - delta = orig_data - xdp.data; - len = xdp.data_end - xdp.data; - break; - default: - bpf_warn_invalid_xdp_action(act); - /* fall through */ - case XDP_ABORTED: - trace_xdp_exception(tun->dev, xdp_prog, act); - /* fall through */ - case XDP_DROP: - goto err_xdp; } - } + err = tun_xdp_act(tun, xdp_prog, &xdp, act); + if (err < 0) + goto err_xdp; + if (err == XDP_REDIRECT) + xdp_do_flush_map(); + if (err != XDP_PASS) + goto out; - skb = build_skb(buf, buflen); - if (!skb) { - rcu_read_unlock(); - local_bh_enable(); - return ERR_PTR(-ENOMEM); + pad = xdp.data - xdp.data_hard_start; + len = xdp.data_end - xdp.data; } - - skb_reserve(skb, pad - delta); - skb_put(skb, len); - get_page(alloc_frag->page); - alloc_frag->offset += buflen; - rcu_read_unlock(); local_bh_enable(); - return skb; + return __tun_build_skb(alloc_frag, buf, buflen, len, pad); -err_redirect: - put_page(alloc_frag->page); err_xdp: + put_page(alloc_frag->page); +out: rcu_read_unlock(); local_bh_enable(); - this_cpu_inc(tun->pcpu_stats->rx_dropped); return NULL; } @@ -2392,18 +2383,133 @@ static void tun_sock_write_space(struct sock *sk) kill_fasync(&tfile->fasync, SIGIO, POLL_OUT); } +static int tun_xdp_one(struct tun_struct *tun, + struct tun_file *tfile, + struct xdp_buff *xdp, int *flush) +{ + struct tun_xdp_hdr *hdr = xdp->data_hard_start; + struct virtio_net_hdr *gso = &hdr->gso; + struct tun_pcpu_stats *stats; + struct bpf_prog *xdp_prog; + struct sk_buff *skb = NULL; + u32 rxhash = 0, act; + int buflen = hdr->buflen; + int err = 0; + bool skb_xdp = false; + + xdp_prog = rcu_dereference(tun->xdp_prog); + if (xdp_prog) { + if (gso->gso_type) { + skb_xdp = true; + goto build; + } + xdp_set_data_meta_invalid(xdp); + xdp->rxq = &tfile->xdp_rxq; + + act = bpf_prog_run_xdp(xdp_prog, xdp); + err = tun_xdp_act(tun, xdp_prog, xdp, act); + if (err < 0) { + put_page(virt_to_head_page(xdp->data)); + return err; + } + + switch (err) { + case XDP_REDIRECT: + *flush = true; + /* fall through */ + case XDP_TX: + return 0; + case XDP_PASS: + break; + default: + put_page(virt_to_head_page(xdp->data)); + return 0; + } + } + +build: + skb = build_skb(xdp->data_hard_start, buflen); + if (!skb) { + err = -ENOMEM; + goto out; + } + + skb_reserve(skb, xdp->data - xdp->data_hard_start); + skb_put(skb, xdp->data_end - xdp->data); + + if (virtio_net_hdr_to_skb(skb, gso, tun_is_little_endian(tun))) { + this_cpu_inc(tun->pcpu_stats->rx_frame_errors); + kfree_skb(skb); + err = -EINVAL; + goto out; + } + + skb->protocol = eth_type_trans(skb, tun->dev); + skb_reset_network_header(skb); + skb_probe_transport_header(skb, 0); + + if (skb_xdp) { + err = do_xdp_generic(xdp_prog, skb); + if (err != XDP_PASS) + goto out; + } + + if (!rcu_dereference(tun->steering_prog)) + rxhash = __skb_get_hash_symmetric(skb); + + netif_receive_skb(skb); + + stats = get_cpu_ptr(tun->pcpu_stats); + u64_stats_update_begin(&stats->syncp); + stats->rx_packets++; + stats->rx_bytes += skb->len; + u64_stats_update_end(&stats->syncp); + put_cpu_ptr(stats); + + if (rxhash) + tun_flow_update(tun, rxhash, tfile); + +out: + return err; +} + static int tun_sendmsg(struct socket *sock, struct msghdr *m, size_t total_len) { - int ret; + int ret, i; struct tun_file *tfile = container_of(sock, struct tun_file, socket); struct tun_struct *tun = tun_get(tfile); + struct tun_msg_ctl *ctl = m->msg_control; + struct xdp_buff *xdp; if (!tun) return -EBADFD; - ret = tun_get_user(tun, tfile, m->msg_control, &m->msg_iter, + if (ctl && (ctl->type == TUN_MSG_PTR)) { + int n = ctl->num; + int flush = 0; + + local_bh_disable(); + rcu_read_lock(); + + for (i = 0; i < n; i++) { + xdp = &((struct xdp_buff *)ctl->ptr)[i]; + tun_xdp_one(tun, tfile, xdp, &flush); + } + + if (flush) + xdp_do_flush_map(); + + rcu_read_unlock(); + local_bh_enable(); + + ret = total_len; + goto out; + } + + ret = tun_get_user(tun, tfile, ctl ? ctl->ptr : NULL, &m->msg_iter, m->msg_flags & MSG_DONTWAIT, m->msg_flags & MSG_MORE); +out: tun_put(tun); return ret; } diff --git a/drivers/net/usb/lan78xx.c b/drivers/net/usb/lan78xx.c index a9991c5f4736..656441d9a955 100644 --- a/drivers/net/usb/lan78xx.c +++ b/drivers/net/usb/lan78xx.c @@ -1,18 +1,6 @@ +// SPDX-License-Identifier: GPL-2.0+ /* * Copyright (C) 2015 Microchip Technology - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version 2 - * of the License, or (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, see <http://www.gnu.org/licenses/>. */ #include <linux/version.h> #include <linux/module.h> @@ -948,11 +936,9 @@ static int lan78xx_read_otp(struct lan78xx_net *dev, u32 offset, ret = lan78xx_read_raw_otp(dev, 0, 1, &sig); if (ret == 0) { - if (sig == OTP_INDICATOR_1) - offset = offset; - else if (sig == OTP_INDICATOR_2) + if (sig == OTP_INDICATOR_2) offset += 0x100; - else + else if (sig != OTP_INDICATOR_1) ret = -EINVAL; if (!ret) ret = lan78xx_read_raw_otp(dev, offset, length, data); @@ -1027,7 +1013,7 @@ done: static void lan78xx_set_addr_filter(struct lan78xx_priv *pdata, int index, u8 addr[ETH_ALEN]) { - u32 temp; + u32 temp; if ((pdata) && (index > 0) && (index < NUM_OF_MAF)) { temp = addr[3]; @@ -1847,8 +1833,7 @@ static int lan78xx_mdio_init(struct lan78xx_net *dev) node = of_get_child_by_name(dev->udev->dev.of_node, "mdio"); ret = of_mdiobus_register(dev->mdiobus, node); - if (node) - of_node_put(node); + of_node_put(node); if (ret) { netdev_err(dev->net, "can't register MDIO bus\n"); goto exit1; @@ -2178,7 +2163,7 @@ static int lan78xx_phy_init(struct lan78xx_net *dev) } /* MAC doesn't support 1000T Half */ - phydev->supported &= ~SUPPORTED_1000baseT_Half; + phy_remove_link_mode(phydev, ETHTOOL_LINK_MODE_1000baseT_Half_BIT); /* support both flow controls */ dev->fc_request_control = (FLOW_CTRL_RX | FLOW_CTRL_TX); @@ -2702,7 +2687,7 @@ static void lan78xx_terminate_urbs(struct lan78xx_net *dev) static int lan78xx_stop(struct net_device *net) { - struct lan78xx_net *dev = netdev_priv(net); + struct lan78xx_net *dev = netdev_priv(net); if (timer_pending(&dev->stat_monitor)) del_timer_sync(&dev->stat_monitor); @@ -2952,6 +2937,11 @@ static int lan78xx_bind(struct lan78xx_net *dev, struct usb_interface *intf) int i; ret = lan78xx_get_endpoints(dev, intf); + if (ret) { + netdev_warn(dev->net, "lan78xx_get_endpoints failed: %d\n", + ret); + return ret; + } dev->data[0] = (unsigned long)kzalloc(sizeof(*pdata), GFP_KERNEL); @@ -3080,7 +3070,7 @@ static void lan78xx_rx_vlan_offload(struct lan78xx_net *dev, static void lan78xx_skb_return(struct lan78xx_net *dev, struct sk_buff *skb) { - int status; + int status; if (test_bit(EVENT_RX_PAUSED, &dev->flags)) { skb_queue_tail(&dev->rxq_pause, skb); @@ -3347,9 +3337,9 @@ static void lan78xx_tx_bh(struct lan78xx_net *dev) count = 0; length = 0; spin_lock_irqsave(&tqp->lock, flags); - for (skb = tqp->next; pkt_cnt < tqp->qlen; skb = skb->next) { + skb_queue_walk(tqp, skb) { if (skb_is_gso(skb)) { - if (pkt_cnt) { + if (!skb_queue_is_first(tqp, skb)) { /* handle previous packets first */ break; } @@ -3640,10 +3630,10 @@ static void intr_complete(struct urb *urb) static void lan78xx_disconnect(struct usb_interface *intf) { - struct lan78xx_net *dev; - struct usb_device *udev; - struct net_device *net; - struct phy_device *phydev; + struct lan78xx_net *dev; + struct usb_device *udev; + struct net_device *net; + struct phy_device *phydev; dev = usb_get_intfdata(intf); usb_set_intfdata(intf, NULL); @@ -3761,7 +3751,6 @@ static int lan78xx_probe(struct usb_interface *intf, ret = lan78xx_bind(dev, intf); if (ret < 0) goto out2; - strcpy(netdev->name, "eth%d"); if (netdev->mtu > (dev->hard_mtu - netdev->hard_header_len)) netdev->mtu = dev->hard_mtu - netdev->hard_header_len; diff --git a/drivers/net/usb/lan78xx.h b/drivers/net/usb/lan78xx.h index 25aa54611774..968e5e5faee0 100644 --- a/drivers/net/usb/lan78xx.h +++ b/drivers/net/usb/lan78xx.h @@ -1,18 +1,6 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ /* * Copyright (C) 2015 Microchip Technology - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version 2 - * of the License, or (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, see <http://www.gnu.org/licenses/>. */ #ifndef _LAN78XX_H #define _LAN78XX_H diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c index cb0cc30c3d6a..533b6fb8d923 100644 --- a/drivers/net/usb/qmi_wwan.c +++ b/drivers/net/usb/qmi_wwan.c @@ -967,6 +967,13 @@ static const struct usb_device_id products[] = { USB_DEVICE_AND_INTERFACE_INFO(0x03f0, 0x581d, USB_CLASS_VENDOR_SPEC, 1, 7), .driver_info = (unsigned long)&qmi_wwan_info, }, + { /* Quectel EP06/EG06/EM06 */ + USB_DEVICE_AND_INTERFACE_INFO(0x2c7c, 0x0306, + USB_CLASS_VENDOR_SPEC, + USB_SUBCLASS_VENDOR_SPEC, + 0xff), + .driver_info = (unsigned long)&qmi_wwan_info_quirk_dtr, + }, /* 3. Combined interface devices matching on interface number */ {QMI_FIXED_INTF(0x0408, 0xea42, 4)}, /* Yota / Megafon M100-1 */ @@ -1206,13 +1213,13 @@ static const struct usb_device_id products[] = { {QMI_FIXED_INTF(0x1199, 0x9061, 8)}, /* Sierra Wireless Modem */ {QMI_FIXED_INTF(0x1199, 0x9063, 8)}, /* Sierra Wireless EM7305 */ {QMI_FIXED_INTF(0x1199, 0x9063, 10)}, /* Sierra Wireless EM7305 */ - {QMI_FIXED_INTF(0x1199, 0x9071, 8)}, /* Sierra Wireless MC74xx */ - {QMI_FIXED_INTF(0x1199, 0x9071, 10)}, /* Sierra Wireless MC74xx */ - {QMI_FIXED_INTF(0x1199, 0x9079, 8)}, /* Sierra Wireless EM74xx */ - {QMI_FIXED_INTF(0x1199, 0x9079, 10)}, /* Sierra Wireless EM74xx */ - {QMI_FIXED_INTF(0x1199, 0x907b, 8)}, /* Sierra Wireless EM74xx */ - {QMI_FIXED_INTF(0x1199, 0x907b, 10)}, /* Sierra Wireless EM74xx */ - {QMI_FIXED_INTF(0x1199, 0x9091, 8)}, /* Sierra Wireless EM7565 */ + {QMI_QUIRK_SET_DTR(0x1199, 0x9071, 8)}, /* Sierra Wireless MC74xx */ + {QMI_QUIRK_SET_DTR(0x1199, 0x9071, 10)},/* Sierra Wireless MC74xx */ + {QMI_QUIRK_SET_DTR(0x1199, 0x9079, 8)}, /* Sierra Wireless EM74xx */ + {QMI_QUIRK_SET_DTR(0x1199, 0x9079, 10)},/* Sierra Wireless EM74xx */ + {QMI_QUIRK_SET_DTR(0x1199, 0x907b, 8)}, /* Sierra Wireless EM74xx */ + {QMI_QUIRK_SET_DTR(0x1199, 0x907b, 10)},/* Sierra Wireless EM74xx */ + {QMI_QUIRK_SET_DTR(0x1199, 0x9091, 8)}, /* Sierra Wireless EM7565 */ {QMI_FIXED_INTF(0x1bbb, 0x011e, 4)}, /* Telekom Speedstick LTE II (Alcatel One Touch L100V LTE) */ {QMI_FIXED_INTF(0x1bbb, 0x0203, 2)}, /* Alcatel L800MA */ {QMI_FIXED_INTF(0x2357, 0x0201, 4)}, /* TP-LINK HSUPA Modem MA180 */ @@ -1255,7 +1262,6 @@ static const struct usb_device_id products[] = { {QMI_QUIRK_SET_DTR(0x2c7c, 0x0121, 4)}, /* Quectel EC21 Mini PCIe */ {QMI_QUIRK_SET_DTR(0x2c7c, 0x0191, 4)}, /* Quectel EG91 */ {QMI_FIXED_INTF(0x2c7c, 0x0296, 4)}, /* Quectel BG96 */ - {QMI_QUIRK_SET_DTR(0x2c7c, 0x0306, 4)}, /* Quectel EP06 Mini PCIe */ /* 4. Gobi 1000 devices */ {QMI_GOBI1K_DEVICE(0x05c6, 0x9212)}, /* Acer Gobi Modem Device */ @@ -1331,6 +1337,19 @@ static bool quectel_ec20_detected(struct usb_interface *intf) return false; } +static bool quectel_ep06_diag_detected(struct usb_interface *intf) +{ + struct usb_device *dev = interface_to_usbdev(intf); + struct usb_interface_descriptor intf_desc = intf->cur_altsetting->desc; + + if (le16_to_cpu(dev->descriptor.idVendor) == 0x2c7c && + le16_to_cpu(dev->descriptor.idProduct) == 0x0306 && + intf_desc.bNumEndpoints == 2) + return true; + + return false; +} + static int qmi_wwan_probe(struct usb_interface *intf, const struct usb_device_id *prod) { @@ -1365,6 +1384,15 @@ static int qmi_wwan_probe(struct usb_interface *intf, return -ENODEV; } + /* Quectel EP06/EM06/EG06 supports dynamic interface configuration, so + * we need to match on class/subclass/protocol. These values are + * identical for the diagnostic- and QMI-interface, but bNumEndpoints is + * different. Ignore the current interface if the number of endpoints + * the number for the diag interface (two). + */ + if (quectel_ep06_diag_detected(intf)) + return -ENODEV; + return usbnet_probe(intf, id); } diff --git a/drivers/net/veth.c b/drivers/net/veth.c index bc8faf13a731..224c56a4e2b1 100644 --- a/drivers/net/veth.c +++ b/drivers/net/veth.c @@ -37,12 +37,6 @@ #define VETH_XDP_TX BIT(0) #define VETH_XDP_REDIR BIT(1) -struct pcpu_vstats { - u64 packets; - u64 bytes; - struct u64_stats_sync syncp; -}; - struct veth_rq { struct napi_struct xdp_napi; struct net_device *dev; @@ -217,7 +211,7 @@ static netdev_tx_t veth_xmit(struct sk_buff *skb, struct net_device *dev) skb_tx_timestamp(skb); if (likely(veth_forward_skb(rcv, skb, rq, rcv_xdp) == NET_RX_SUCCESS)) { - struct pcpu_vstats *stats = this_cpu_ptr(dev->vstats); + struct pcpu_lstats *stats = this_cpu_ptr(dev->lstats); u64_stats_update_begin(&stats->syncp); stats->bytes += length; @@ -236,7 +230,7 @@ drop: return NETDEV_TX_OK; } -static u64 veth_stats_one(struct pcpu_vstats *result, struct net_device *dev) +static u64 veth_stats_one(struct pcpu_lstats *result, struct net_device *dev) { struct veth_priv *priv = netdev_priv(dev); int cpu; @@ -244,7 +238,7 @@ static u64 veth_stats_one(struct pcpu_vstats *result, struct net_device *dev) result->packets = 0; result->bytes = 0; for_each_possible_cpu(cpu) { - struct pcpu_vstats *stats = per_cpu_ptr(dev->vstats, cpu); + struct pcpu_lstats *stats = per_cpu_ptr(dev->lstats, cpu); u64 packets, bytes; unsigned int start; @@ -264,7 +258,7 @@ static void veth_get_stats64(struct net_device *dev, { struct veth_priv *priv = netdev_priv(dev); struct net_device *peer; - struct pcpu_vstats one; + struct pcpu_lstats one; tot->tx_dropped = veth_stats_one(&one, dev); tot->tx_bytes = one.bytes; @@ -478,6 +472,8 @@ static struct sk_buff *veth_xdp_rcv_skb(struct veth_rq *rq, struct sk_buff *skb, int mac_len, delta, off; struct xdp_buff xdp; + skb_orphan(skb); + rcu_read_lock(); xdp_prog = rcu_dereference(rq->xdp_prog); if (unlikely(!xdp_prog)) { @@ -523,8 +519,6 @@ static struct sk_buff *veth_xdp_rcv_skb(struct veth_rq *rq, struct sk_buff *skb, skb_copy_header(nskb, skb); head_off = skb_headroom(nskb) - skb_headroom(skb); skb_headers_offset_update(nskb, head_off); - if (skb->sk) - skb_set_owner_w(nskb, skb->sk); consume_skb(skb); skb = nskb; } @@ -830,13 +824,13 @@ static int veth_dev_init(struct net_device *dev) { int err; - dev->vstats = netdev_alloc_pcpu_stats(struct pcpu_vstats); - if (!dev->vstats) + dev->lstats = netdev_alloc_pcpu_stats(struct pcpu_lstats); + if (!dev->lstats) return -ENOMEM; err = veth_alloc_queues(dev); if (err) { - free_percpu(dev->vstats); + free_percpu(dev->lstats); return err; } @@ -846,7 +840,7 @@ static int veth_dev_init(struct net_device *dev) static void veth_dev_free(struct net_device *dev) { veth_free_queues(dev); - free_percpu(dev->vstats); + free_percpu(dev->lstats); } #ifdef CONFIG_NET_POLL_CONTROLLER diff --git a/drivers/net/vsockmon.c b/drivers/net/vsockmon.c index c28bdce14fd5..7bad5c95551f 100644 --- a/drivers/net/vsockmon.c +++ b/drivers/net/vsockmon.c @@ -11,12 +11,6 @@ #define DEFAULT_MTU (VIRTIO_VSOCK_MAX_PKT_BUF_SIZE + \ sizeof(struct af_vsockmon_hdr)) -struct pcpu_lstats { - u64 rx_packets; - u64 rx_bytes; - struct u64_stats_sync syncp; -}; - static int vsockmon_dev_init(struct net_device *dev) { dev->lstats = netdev_alloc_pcpu_stats(struct pcpu_lstats); @@ -56,8 +50,8 @@ static netdev_tx_t vsockmon_xmit(struct sk_buff *skb, struct net_device *dev) struct pcpu_lstats *stats = this_cpu_ptr(dev->lstats); u64_stats_update_begin(&stats->syncp); - stats->rx_bytes += len; - stats->rx_packets++; + stats->bytes += len; + stats->packets++; u64_stats_update_end(&stats->syncp); dev_kfree_skb(skb); @@ -80,8 +74,8 @@ vsockmon_get_stats64(struct net_device *dev, struct rtnl_link_stats64 *stats) do { start = u64_stats_fetch_begin_irq(&vstats->syncp); - tbytes = vstats->rx_bytes; - tpackets = vstats->rx_packets; + tbytes = vstats->bytes; + tpackets = vstats->packets; } while (u64_stats_fetch_retry_irq(&vstats->syncp, start)); packets += tpackets; diff --git a/drivers/net/wan/c101.c b/drivers/net/wan/c101.c index 2371e078afbb..91dbbde3c35b 100644 --- a/drivers/net/wan/c101.c +++ b/drivers/net/wan/c101.c @@ -24,7 +24,6 @@ #include <linux/string.h> #include <linux/errno.h> #include <linux/init.h> -#include <linux/moduleparam.h> #include <linux/netdevice.h> #include <linux/hdlc.h> #include <linux/delay.h> diff --git a/drivers/net/wan/pci200syn.c b/drivers/net/wan/pci200syn.c index 4e437c599e9a..1f8a3f77a7b9 100644 --- a/drivers/net/wan/pci200syn.c +++ b/drivers/net/wan/pci200syn.c @@ -27,7 +27,6 @@ #include <linux/errno.h> #include <linux/init.h> #include <linux/ioport.h> -#include <linux/moduleparam.h> #include <linux/netdevice.h> #include <linux/hdlc.h> #include <linux/pci.h> diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/bcmsdh.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/bcmsdh.c index d2f788d88668..3e37c8cf82c6 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/bcmsdh.c +++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/bcmsdh.c @@ -576,7 +576,7 @@ int brcmf_sdiod_recv_chain(struct brcmf_sdio_dev *sdiodev, if (pktq->qlen == 1) err = brcmf_sdiod_skbuff_read(sdiodev, sdiodev->func2, addr, - pktq->next); + __skb_peek(pktq)); else if (!sdiodev->sg_support) { glom_skb = brcmu_pkt_buf_get_skb(totlen); if (!glom_skb) diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.c index a907d7b065fa..1e2fd289323a 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.c +++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.c @@ -2189,7 +2189,7 @@ brcmf_sdio_txpkt_prep(struct brcmf_sdio *bus, struct sk_buff_head *pktq, * length of the chain (including padding) */ if (bus->txglom) - brcmf_sdio_update_hwhdr(pktq->next->data, total_len); + brcmf_sdio_update_hwhdr(__skb_peek(pktq)->data, total_len); return 0; } diff --git a/drivers/net/wireless/intersil/p54/txrx.c b/drivers/net/wireless/intersil/p54/txrx.c index 3a4214d362ff..790784568ad2 100644 --- a/drivers/net/wireless/intersil/p54/txrx.c +++ b/drivers/net/wireless/intersil/p54/txrx.c @@ -121,8 +121,8 @@ static int p54_assign_address(struct p54_common *priv, struct sk_buff *skb) } if (unlikely(!target_skb)) { if (priv->rx_end - last_addr >= len) { - target_skb = priv->tx_queue.prev; - if (!skb_queue_empty(&priv->tx_queue)) { + target_skb = skb_peek_tail(&priv->tx_queue); + if (target_skb) { info = IEEE80211_SKB_CB(target_skb); range = (void *)info->rate_driver_data; target_addr = range->end_addr; diff --git a/drivers/net/wireless/realtek/rtl818x/rtl8187/dev.c b/drivers/net/wireless/realtek/rtl818x/rtl8187/dev.c index 9a1d15b3ce45..cec37787ecf8 100644 --- a/drivers/net/wireless/realtek/rtl818x/rtl8187/dev.c +++ b/drivers/net/wireless/realtek/rtl818x/rtl8187/dev.c @@ -499,7 +499,7 @@ static void rtl8187b_status_cb(struct urb *urb) if (cmd_type == 1) { unsigned int pkt_rc, seq_no; bool tok; - struct sk_buff *skb; + struct sk_buff *skb, *iter; struct ieee80211_hdr *ieee80211hdr; unsigned long flags; @@ -508,8 +508,9 @@ static void rtl8187b_status_cb(struct urb *urb) seq_no = (val >> 16) & 0xFFF; spin_lock_irqsave(&priv->b_tx_status.queue.lock, flags); - skb_queue_reverse_walk(&priv->b_tx_status.queue, skb) { - ieee80211hdr = (struct ieee80211_hdr *)skb->data; + skb = NULL; + skb_queue_reverse_walk(&priv->b_tx_status.queue, iter) { + ieee80211hdr = (struct ieee80211_hdr *)iter->data; /* * While testing, it was discovered that the seq_no @@ -522,10 +523,12 @@ static void rtl8187b_status_cb(struct urb *urb) * it's unlikely we wrongly ack some sent data */ if ((le16_to_cpu(ieee80211hdr->seq_ctrl) - & 0xFFF) == seq_no) + & 0xFFF) == seq_no) { + skb = iter; break; + } } - if (skb != (struct sk_buff *) &priv->b_tx_status.queue) { + if (skb) { struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb); __skb_unlink(skb, &priv->b_tx_status.queue); diff --git a/drivers/net/xen-netback/netback.c b/drivers/net/xen-netback/netback.c index 3621e05a7494..80aae3a32c2a 100644 --- a/drivers/net/xen-netback/netback.c +++ b/drivers/net/xen-netback/netback.c @@ -1660,8 +1660,7 @@ module_init(netback_init); static void __exit netback_fini(void) { #ifdef CONFIG_DEBUG_FS - if (!IS_ERR_OR_NULL(xen_netback_dbg_root)) - debugfs_remove_recursive(xen_netback_dbg_root); + debugfs_remove_recursive(xen_netback_dbg_root); #endif /* CONFIG_DEBUG_FS */ xenvif_xenbus_fini(); } diff --git a/drivers/net/xen-netback/xenbus.c b/drivers/net/xen-netback/xenbus.c index cd51492ae6c2..fe1d52247bbe 100644 --- a/drivers/net/xen-netback/xenbus.c +++ b/drivers/net/xen-netback/xenbus.c @@ -254,8 +254,7 @@ static void xenvif_debugfs_delif(struct xenvif *vif) if (IS_ERR_OR_NULL(xen_netback_dbg_root)) return; - if (!IS_ERR_OR_NULL(vif->xenvif_dbg_root)) - debugfs_remove_recursive(vif->xenvif_dbg_root); + debugfs_remove_recursive(vif->xenvif_dbg_root); vif->xenvif_dbg_root = NULL; } #endif /* CONFIG_DEBUG_FS */ diff --git a/drivers/net/xen-netfront.c b/drivers/net/xen-netfront.c index 73f596a90c69..f17f602e6171 100644 --- a/drivers/net/xen-netfront.c +++ b/drivers/net/xen-netfront.c @@ -87,8 +87,7 @@ struct netfront_cb { /* IRQ name is queue name with "-tx" or "-rx" appended */ #define IRQ_NAME_SIZE (QUEUE_NAME_SIZE + 3) -static DECLARE_WAIT_QUEUE_HEAD(module_load_q); -static DECLARE_WAIT_QUEUE_HEAD(module_unload_q); +static DECLARE_WAIT_QUEUE_HEAD(module_wq); struct netfront_stats { u64 packets; @@ -909,7 +908,11 @@ static RING_IDX xennet_fill_frags(struct netfront_queue *queue, BUG_ON(pull_to <= skb_headlen(skb)); __pskb_pull_tail(skb, pull_to - skb_headlen(skb)); } - BUG_ON(skb_shinfo(skb)->nr_frags >= MAX_SKB_FRAGS); + if (unlikely(skb_shinfo(skb)->nr_frags >= MAX_SKB_FRAGS)) { + queue->rx.rsp_cons = ++cons; + kfree_skb(nskb); + return ~0U; + } skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags, skb_frag_page(nfrag), @@ -1046,6 +1049,8 @@ err: skb->len += rx->status; i = xennet_fill_frags(queue, skb, &tmpq); + if (unlikely(i == ~0U)) + goto err; if (rx->flags & XEN_NETRXF_csum_blank) skb->ip_summed = CHECKSUM_PARTIAL; @@ -1332,11 +1337,11 @@ static struct net_device *xennet_create_dev(struct xenbus_device *dev) netif_carrier_off(netdev); xenbus_switch_state(dev, XenbusStateInitialising); - wait_event(module_load_q, - xenbus_read_driver_state(dev->otherend) != - XenbusStateClosed && - xenbus_read_driver_state(dev->otherend) != - XenbusStateUnknown); + wait_event(module_wq, + xenbus_read_driver_state(dev->otherend) != + XenbusStateClosed && + xenbus_read_driver_state(dev->otherend) != + XenbusStateUnknown); return netdev; exit: @@ -2010,15 +2015,14 @@ static void netback_changed(struct xenbus_device *dev, dev_dbg(&dev->dev, "%s\n", xenbus_strstate(backend_state)); + wake_up_all(&module_wq); + switch (backend_state) { case XenbusStateInitialising: case XenbusStateInitialised: case XenbusStateReconfiguring: case XenbusStateReconfigured: - break; - case XenbusStateUnknown: - wake_up_all(&module_unload_q); break; case XenbusStateInitWait: @@ -2034,12 +2038,10 @@ static void netback_changed(struct xenbus_device *dev, break; case XenbusStateClosed: - wake_up_all(&module_unload_q); if (dev->state == XenbusStateClosed) break; /* Missed the backend's CLOSING state -- fallthrough */ case XenbusStateClosing: - wake_up_all(&module_unload_q); xenbus_frontend_closed(dev); break; } @@ -2147,14 +2149,14 @@ static int xennet_remove(struct xenbus_device *dev) if (xenbus_read_driver_state(dev->otherend) != XenbusStateClosed) { xenbus_switch_state(dev, XenbusStateClosing); - wait_event(module_unload_q, + wait_event(module_wq, xenbus_read_driver_state(dev->otherend) == XenbusStateClosing || xenbus_read_driver_state(dev->otherend) == XenbusStateUnknown); xenbus_switch_state(dev, XenbusStateClosed); - wait_event(module_unload_q, + wait_event(module_wq, xenbus_read_driver_state(dev->otherend) == XenbusStateClosed || xenbus_read_driver_state(dev->otherend) == diff --git a/drivers/nvme/target/admin-cmd.c b/drivers/nvme/target/admin-cmd.c index a21caea1e080..2008fa62a373 100644 --- a/drivers/nvme/target/admin-cmd.c +++ b/drivers/nvme/target/admin-cmd.c @@ -245,6 +245,10 @@ static void nvmet_execute_get_log_page_ana(struct nvmet_req *req) offset += len; ngrps++; } + for ( ; grpid <= NVMET_MAX_ANAGRPS; grpid++) { + if (nvmet_ana_group_enabled[grpid]) + ngrps++; + } hdr.chgcnt = cpu_to_le64(nvmet_ana_chgcnt); hdr.ngrps = cpu_to_le16(ngrps); diff --git a/drivers/nvme/target/rdma.c b/drivers/nvme/target/rdma.c index 3533e918ea37..bfc4da660bb4 100644 --- a/drivers/nvme/target/rdma.c +++ b/drivers/nvme/target/rdma.c @@ -66,6 +66,7 @@ struct nvmet_rdma_rsp { struct nvmet_req req; + bool allocated; u8 n_rdma; u32 flags; u32 invalidate_rkey; @@ -174,11 +175,19 @@ nvmet_rdma_get_rsp(struct nvmet_rdma_queue *queue) unsigned long flags; spin_lock_irqsave(&queue->rsps_lock, flags); - rsp = list_first_entry(&queue->free_rsps, + rsp = list_first_entry_or_null(&queue->free_rsps, struct nvmet_rdma_rsp, free_list); - list_del(&rsp->free_list); + if (likely(rsp)) + list_del(&rsp->free_list); spin_unlock_irqrestore(&queue->rsps_lock, flags); + if (unlikely(!rsp)) { + rsp = kmalloc(sizeof(*rsp), GFP_KERNEL); + if (unlikely(!rsp)) + return NULL; + rsp->allocated = true; + } + return rsp; } @@ -187,6 +196,11 @@ nvmet_rdma_put_rsp(struct nvmet_rdma_rsp *rsp) { unsigned long flags; + if (rsp->allocated) { + kfree(rsp); + return; + } + spin_lock_irqsave(&rsp->queue->rsps_lock, flags); list_add_tail(&rsp->free_list, &rsp->queue->free_rsps); spin_unlock_irqrestore(&rsp->queue->rsps_lock, flags); @@ -776,6 +790,15 @@ static void nvmet_rdma_recv_done(struct ib_cq *cq, struct ib_wc *wc) cmd->queue = queue; rsp = nvmet_rdma_get_rsp(queue); + if (unlikely(!rsp)) { + /* + * we get here only under memory pressure, + * silently drop and have the host retry + * as we can't even fail it. + */ + nvmet_rdma_post_recv(queue->dev, cmd); + return; + } rsp->queue = queue; rsp->cmd = cmd; rsp->flags = 0; diff --git a/drivers/of/base.c b/drivers/of/base.c index 9095b8290150..74eaedd5b860 100644 --- a/drivers/of/base.c +++ b/drivers/of/base.c @@ -140,6 +140,9 @@ void of_populate_phandle_cache(void) if (np->phandle && np->phandle != OF_PHANDLE_ILLEGAL) phandles++; + if (!phandles) + goto out; + cache_entries = roundup_pow_of_two(phandles); phandle_cache_mask = cache_entries - 1; diff --git a/drivers/pci/controller/pci-hyperv.c b/drivers/pci/controller/pci-hyperv.c index c00f82cc54aa..9ba4d12c179c 100644 --- a/drivers/pci/controller/pci-hyperv.c +++ b/drivers/pci/controller/pci-hyperv.c @@ -89,6 +89,9 @@ static enum pci_protocol_version_t pci_protocol_version; #define STATUS_REVISION_MISMATCH 0xC0000059 +/* space for 32bit serial number as string */ +#define SLOT_NAME_SIZE 11 + /* * Message Types */ @@ -494,6 +497,7 @@ struct hv_pci_dev { struct list_head list_entry; refcount_t refs; enum hv_pcichild_state state; + struct pci_slot *pci_slot; struct pci_function_description desc; bool reported_missing; struct hv_pcibus_device *hbus; @@ -1457,6 +1461,36 @@ static void prepopulate_bars(struct hv_pcibus_device *hbus) spin_unlock_irqrestore(&hbus->device_list_lock, flags); } +/* + * Assign entries in sysfs pci slot directory. + * + * Note that this function does not need to lock the children list + * because it is called from pci_devices_present_work which + * is serialized with hv_eject_device_work because they are on the + * same ordered workqueue. Therefore hbus->children list will not change + * even when pci_create_slot sleeps. + */ +static void hv_pci_assign_slots(struct hv_pcibus_device *hbus) +{ + struct hv_pci_dev *hpdev; + char name[SLOT_NAME_SIZE]; + int slot_nr; + + list_for_each_entry(hpdev, &hbus->children, list_entry) { + if (hpdev->pci_slot) + continue; + + slot_nr = PCI_SLOT(wslot_to_devfn(hpdev->desc.win_slot.slot)); + snprintf(name, SLOT_NAME_SIZE, "%u", hpdev->desc.ser); + hpdev->pci_slot = pci_create_slot(hbus->pci_bus, slot_nr, + name, NULL); + if (IS_ERR(hpdev->pci_slot)) { + pr_warn("pci_create slot %s failed\n", name); + hpdev->pci_slot = NULL; + } + } +} + /** * create_root_hv_pci_bus() - Expose a new root PCI bus * @hbus: Root PCI bus, as understood by this driver @@ -1480,6 +1514,7 @@ static int create_root_hv_pci_bus(struct hv_pcibus_device *hbus) pci_lock_rescan_remove(); pci_scan_child_bus(hbus->pci_bus); pci_bus_assign_resources(hbus->pci_bus); + hv_pci_assign_slots(hbus); pci_bus_add_devices(hbus->pci_bus); pci_unlock_rescan_remove(); hbus->state = hv_pcibus_installed; @@ -1742,6 +1777,7 @@ static void pci_devices_present_work(struct work_struct *work) */ pci_lock_rescan_remove(); pci_scan_child_bus(hbus->pci_bus); + hv_pci_assign_slots(hbus); pci_unlock_rescan_remove(); break; @@ -1858,6 +1894,9 @@ static void hv_eject_device_work(struct work_struct *work) list_del(&hpdev->list_entry); spin_unlock_irqrestore(&hpdev->hbus->device_list_lock, flags); + if (hpdev->pci_slot) + pci_destroy_slot(hpdev->pci_slot); + memset(&ctxt, 0, sizeof(ctxt)); ejct_pkt = (struct pci_eject_response *)&ctxt.pkt.message; ejct_pkt->message_type.type = PCI_EJECTION_COMPLETE; diff --git a/drivers/pci/hotplug/pciehp_hpc.c b/drivers/pci/hotplug/pciehp_hpc.c index 7136e3430925..a938abdb41ce 100644 --- a/drivers/pci/hotplug/pciehp_hpc.c +++ b/drivers/pci/hotplug/pciehp_hpc.c @@ -496,7 +496,7 @@ int pciehp_power_on_slot(struct slot *slot) u16 slot_status; int retval; - /* Clear sticky power-fault bit from previous power failures */ + /* Clear power-fault bit from previous power failures */ pcie_capability_read_word(pdev, PCI_EXP_SLTSTA, &slot_status); if (slot_status & PCI_EXP_SLTSTA_PFD) pcie_capability_write_word(pdev, PCI_EXP_SLTSTA, @@ -646,6 +646,14 @@ static irqreturn_t pciehp_ist(int irq, void *dev_id) pciehp_handle_button_press(slot); } + /* Check Power Fault Detected */ + if ((events & PCI_EXP_SLTSTA_PFD) && !ctrl->power_fault_detected) { + ctrl->power_fault_detected = 1; + ctrl_err(ctrl, "Slot(%s): Power fault\n", slot_name(slot)); + pciehp_set_attention_status(slot, 1); + pciehp_green_led_off(slot); + } + /* * Disable requests have higher priority than Presence Detect Changed * or Data Link Layer State Changed events. @@ -657,14 +665,6 @@ static irqreturn_t pciehp_ist(int irq, void *dev_id) pciehp_handle_presence_or_link_change(slot, events); up_read(&ctrl->reset_lock); - /* Check Power Fault Detected */ - if ((events & PCI_EXP_SLTSTA_PFD) && !ctrl->power_fault_detected) { - ctrl->power_fault_detected = 1; - ctrl_err(ctrl, "Slot(%s): Power fault\n", slot_name(slot)); - pciehp_set_attention_status(slot, 1); - pciehp_green_led_off(slot); - } - pci_config_pm_runtime_put(pdev); wake_up(&ctrl->requester); return IRQ_HANDLED; diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c index 29ff9619b5fa..1835f3a7aa8d 100644 --- a/drivers/pci/pci.c +++ b/drivers/pci/pci.c @@ -4547,6 +4547,7 @@ int pci_bridge_secondary_bus_reset(struct pci_dev *dev) return pci_dev_wait(dev, "bus reset", PCIE_RESET_READY_POLL_MS); } +EXPORT_SYMBOL_GPL(pci_bridge_secondary_bus_reset); static int pci_parent_bus_reset(struct pci_dev *dev, int probe) { @@ -5200,7 +5201,7 @@ static int __pci_reset_bus(struct pci_bus *bus) */ int pci_reset_bus(struct pci_dev *pdev) { - return pci_probe_reset_slot(pdev->slot) ? + return (!pci_probe_reset_slot(pdev->slot)) ? __pci_reset_slot(pdev->slot) : __pci_reset_bus(pdev->bus); } EXPORT_SYMBOL_GPL(pci_reset_bus); diff --git a/drivers/pci/probe.c b/drivers/pci/probe.c index ec784009a36b..201f9e5ff55c 100644 --- a/drivers/pci/probe.c +++ b/drivers/pci/probe.c @@ -2074,6 +2074,7 @@ static void pci_configure_eetlp_prefix(struct pci_dev *dev) { #ifdef CONFIG_PCI_PASID struct pci_dev *bridge; + int pcie_type; u32 cap; if (!pci_is_pcie(dev)) @@ -2083,7 +2084,9 @@ static void pci_configure_eetlp_prefix(struct pci_dev *dev) if (!(cap & PCI_EXP_DEVCAP2_EE_PREFIX)) return; - if (pci_pcie_type(dev) == PCI_EXP_TYPE_ROOT_PORT) + pcie_type = pci_pcie_type(dev); + if (pcie_type == PCI_EXP_TYPE_ROOT_PORT || + pcie_type == PCI_EXP_TYPE_RC_END) dev->eetlp_prefix_path = 1; else { bridge = pci_upstream_bridge(dev); diff --git a/drivers/pci/quirks.c b/drivers/pci/quirks.c index ef7143a274e0..6bc27b7fd452 100644 --- a/drivers/pci/quirks.c +++ b/drivers/pci/quirks.c @@ -4355,11 +4355,6 @@ static int pci_quirk_qcom_rp_acs(struct pci_dev *dev, u16 acs_flags) * * 0x9d10-0x9d1b PCI Express Root port #{1-12} * - * The 300 series chipset suffers from the same bug so include those root - * ports here as well. - * - * 0xa32c-0xa343 PCI Express Root port #{0-24} - * * [1] http://www.intel.com/content/www/us/en/chipsets/100-series-chipset-datasheet-vol-2.html * [2] http://www.intel.com/content/www/us/en/chipsets/100-series-chipset-datasheet-vol-1.html * [3] http://www.intel.com/content/www/us/en/chipsets/100-series-chipset-spec-update.html @@ -4377,7 +4372,6 @@ static bool pci_quirk_intel_spt_pch_acs_match(struct pci_dev *dev) case 0xa110 ... 0xa11f: case 0xa167 ... 0xa16a: /* Sunrise Point */ case 0xa290 ... 0xa29f: case 0xa2e7 ... 0xa2ee: /* Union Point */ case 0x9d10 ... 0x9d1b: /* 7th & 8th Gen Mobile */ - case 0xa32c ... 0xa343: /* 300 series */ return true; } diff --git a/drivers/pci/switch/switchtec.c b/drivers/pci/switch/switchtec.c index 9940cc70f38b..54a8b30dda38 100644 --- a/drivers/pci/switch/switchtec.c +++ b/drivers/pci/switch/switchtec.c @@ -14,6 +14,8 @@ #include <linux/poll.h> #include <linux/wait.h> +#include <linux/nospec.h> + MODULE_DESCRIPTION("Microsemi Switchtec(tm) PCIe Management Driver"); MODULE_VERSION("0.1"); MODULE_LICENSE("GPL"); @@ -909,6 +911,8 @@ static int ioctl_port_to_pff(struct switchtec_dev *stdev, default: if (p.port > ARRAY_SIZE(pcfg->dsp_pff_inst_id)) return -EINVAL; + p.port = array_index_nospec(p.port, + ARRAY_SIZE(pcfg->dsp_pff_inst_id) + 1); p.pff = ioread32(&pcfg->dsp_pff_inst_id[p.port - 1]); break; } diff --git a/drivers/pinctrl/cirrus/pinctrl-madera-core.c b/drivers/pinctrl/cirrus/pinctrl-madera-core.c index ece41fb2848f..c4f4d904e4a6 100644 --- a/drivers/pinctrl/cirrus/pinctrl-madera-core.c +++ b/drivers/pinctrl/cirrus/pinctrl-madera-core.c @@ -1040,7 +1040,7 @@ static int madera_pin_probe(struct platform_device *pdev) } /* if the configuration is provided through pdata, apply it */ - if (pdata) { + if (pdata && pdata->gpio_configs) { ret = pinctrl_register_mappings(pdata->gpio_configs, pdata->n_gpio_configs); if (ret) { diff --git a/drivers/pinctrl/intel/pinctrl-cannonlake.c b/drivers/pinctrl/intel/pinctrl-cannonlake.c index fb1afe55bf53..8d48371caaa2 100644 --- a/drivers/pinctrl/intel/pinctrl-cannonlake.c +++ b/drivers/pinctrl/intel/pinctrl-cannonlake.c @@ -379,7 +379,7 @@ static const struct intel_padgroup cnlh_community1_gpps[] = { static const struct intel_padgroup cnlh_community3_gpps[] = { CNL_GPP(0, 155, 178, 192), /* GPP_K */ CNL_GPP(1, 179, 202, 224), /* GPP_H */ - CNL_GPP(2, 203, 215, 258), /* GPP_E */ + CNL_GPP(2, 203, 215, 256), /* GPP_E */ CNL_GPP(3, 216, 239, 288), /* GPP_F */ CNL_GPP(4, 240, 248, CNL_NO_GPIO), /* SPI */ }; diff --git a/drivers/pinctrl/intel/pinctrl-intel.c b/drivers/pinctrl/intel/pinctrl-intel.c index 62b009b27eda..ec8dafc94694 100644 --- a/drivers/pinctrl/intel/pinctrl-intel.c +++ b/drivers/pinctrl/intel/pinctrl-intel.c @@ -747,13 +747,63 @@ static const struct pinctrl_desc intel_pinctrl_desc = { .owner = THIS_MODULE, }; +/** + * intel_gpio_to_pin() - Translate from GPIO offset to pin number + * @pctrl: Pinctrl structure + * @offset: GPIO offset from gpiolib + * @commmunity: Community is filled here if not %NULL + * @padgrp: Pad group is filled here if not %NULL + * + * When coming through gpiolib irqchip, the GPIO offset is not + * automatically translated to pinctrl pin number. This function can be + * used to find out the corresponding pinctrl pin. + */ +static int intel_gpio_to_pin(struct intel_pinctrl *pctrl, unsigned offset, + const struct intel_community **community, + const struct intel_padgroup **padgrp) +{ + int i; + + for (i = 0; i < pctrl->ncommunities; i++) { + const struct intel_community *comm = &pctrl->communities[i]; + int j; + + for (j = 0; j < comm->ngpps; j++) { + const struct intel_padgroup *pgrp = &comm->gpps[j]; + + if (pgrp->gpio_base < 0) + continue; + + if (offset >= pgrp->gpio_base && + offset < pgrp->gpio_base + pgrp->size) { + int pin; + + pin = pgrp->base + offset - pgrp->gpio_base; + if (community) + *community = comm; + if (padgrp) + *padgrp = pgrp; + + return pin; + } + } + } + + return -EINVAL; +} + static int intel_gpio_get(struct gpio_chip *chip, unsigned offset) { struct intel_pinctrl *pctrl = gpiochip_get_data(chip); void __iomem *reg; u32 padcfg0; + int pin; + + pin = intel_gpio_to_pin(pctrl, offset, NULL, NULL); + if (pin < 0) + return -EINVAL; - reg = intel_get_padcfg(pctrl, offset, PADCFG0); + reg = intel_get_padcfg(pctrl, pin, PADCFG0); if (!reg) return -EINVAL; @@ -770,8 +820,13 @@ static void intel_gpio_set(struct gpio_chip *chip, unsigned offset, int value) unsigned long flags; void __iomem *reg; u32 padcfg0; + int pin; + + pin = intel_gpio_to_pin(pctrl, offset, NULL, NULL); + if (pin < 0) + return; - reg = intel_get_padcfg(pctrl, offset, PADCFG0); + reg = intel_get_padcfg(pctrl, pin, PADCFG0); if (!reg) return; @@ -790,8 +845,13 @@ static int intel_gpio_get_direction(struct gpio_chip *chip, unsigned int offset) struct intel_pinctrl *pctrl = gpiochip_get_data(chip); void __iomem *reg; u32 padcfg0; + int pin; - reg = intel_get_padcfg(pctrl, offset, PADCFG0); + pin = intel_gpio_to_pin(pctrl, offset, NULL, NULL); + if (pin < 0) + return -EINVAL; + + reg = intel_get_padcfg(pctrl, pin, PADCFG0); if (!reg) return -EINVAL; @@ -827,51 +887,6 @@ static const struct gpio_chip intel_gpio_chip = { .set_config = gpiochip_generic_config, }; -/** - * intel_gpio_to_pin() - Translate from GPIO offset to pin number - * @pctrl: Pinctrl structure - * @offset: GPIO offset from gpiolib - * @commmunity: Community is filled here if not %NULL - * @padgrp: Pad group is filled here if not %NULL - * - * When coming through gpiolib irqchip, the GPIO offset is not - * automatically translated to pinctrl pin number. This function can be - * used to find out the corresponding pinctrl pin. - */ -static int intel_gpio_to_pin(struct intel_pinctrl *pctrl, unsigned offset, - const struct intel_community **community, - const struct intel_padgroup **padgrp) -{ - int i; - - for (i = 0; i < pctrl->ncommunities; i++) { - const struct intel_community *comm = &pctrl->communities[i]; - int j; - - for (j = 0; j < comm->ngpps; j++) { - const struct intel_padgroup *pgrp = &comm->gpps[j]; - - if (pgrp->gpio_base < 0) - continue; - - if (offset >= pgrp->gpio_base && - offset < pgrp->gpio_base + pgrp->size) { - int pin; - - pin = pgrp->base + offset - pgrp->gpio_base; - if (community) - *community = comm; - if (padgrp) - *padgrp = pgrp; - - return pin; - } - } - } - - return -EINVAL; -} - static int intel_gpio_irq_reqres(struct irq_data *d) { struct gpio_chip *gc = irq_data_get_irq_chip_data(d); diff --git a/drivers/pinctrl/pinctrl-ingenic.c b/drivers/pinctrl/pinctrl-ingenic.c index 6a1b6058b991..628817c40e3b 100644 --- a/drivers/pinctrl/pinctrl-ingenic.c +++ b/drivers/pinctrl/pinctrl-ingenic.c @@ -793,7 +793,7 @@ static int ingenic_pinctrl_probe(struct platform_device *pdev) err = pinctrl_generic_add_group(jzpc->pctl, group->name, group->pins, group->num_pins, group->data); - if (err) { + if (err < 0) { dev_err(dev, "Failed to register group %s\n", group->name); return err; @@ -806,7 +806,7 @@ static int ingenic_pinctrl_probe(struct platform_device *pdev) err = pinmux_generic_add_function(jzpc->pctl, func->name, func->group_names, func->num_group_names, func->data); - if (err) { + if (err < 0) { dev_err(dev, "Failed to register function %s\n", func->name); return err; diff --git a/drivers/pinctrl/qcom/pinctrl-msm.c b/drivers/pinctrl/qcom/pinctrl-msm.c index 2155a30c282b..5d72ffad32c2 100644 --- a/drivers/pinctrl/qcom/pinctrl-msm.c +++ b/drivers/pinctrl/qcom/pinctrl-msm.c @@ -634,6 +634,29 @@ static void msm_gpio_irq_mask(struct irq_data *d) raw_spin_lock_irqsave(&pctrl->lock, flags); val = readl(pctrl->regs + g->intr_cfg_reg); + /* + * There are two bits that control interrupt forwarding to the CPU. The + * RAW_STATUS_EN bit causes the level or edge sensed on the line to be + * latched into the interrupt status register when the hardware detects + * an irq that it's configured for (either edge for edge type or level + * for level type irq). The 'non-raw' status enable bit causes the + * hardware to assert the summary interrupt to the CPU if the latched + * status bit is set. There's a bug though, the edge detection logic + * seems to have a problem where toggling the RAW_STATUS_EN bit may + * cause the status bit to latch spuriously when there isn't any edge + * so we can't touch that bit for edge type irqs and we have to keep + * the bit set anyway so that edges are latched while the line is masked. + * + * To make matters more complicated, leaving the RAW_STATUS_EN bit + * enabled all the time causes level interrupts to re-latch into the + * status register because the level is still present on the line after + * we ack it. We clear the raw status enable bit during mask here and + * set the bit on unmask so the interrupt can't latch into the hardware + * while it's masked. + */ + if (irqd_get_trigger_type(d) & IRQ_TYPE_LEVEL_MASK) + val &= ~BIT(g->intr_raw_status_bit); + val &= ~BIT(g->intr_enable_bit); writel(val, pctrl->regs + g->intr_cfg_reg); @@ -655,6 +678,7 @@ static void msm_gpio_irq_unmask(struct irq_data *d) raw_spin_lock_irqsave(&pctrl->lock, flags); val = readl(pctrl->regs + g->intr_cfg_reg); + val |= BIT(g->intr_raw_status_bit); val |= BIT(g->intr_enable_bit); writel(val, pctrl->regs + g->intr_cfg_reg); diff --git a/drivers/platform/x86/alienware-wmi.c b/drivers/platform/x86/alienware-wmi.c index d975462a4c57..f10af5c383c5 100644 --- a/drivers/platform/x86/alienware-wmi.c +++ b/drivers/platform/x86/alienware-wmi.c @@ -536,6 +536,7 @@ static acpi_status alienware_wmax_command(struct wmax_basic_args *in_args, if (obj && obj->type == ACPI_TYPE_INTEGER) *out_data = (u32) obj->integer.value; } + kfree(output.pointer); return status; } diff --git a/drivers/platform/x86/dell-smbios-wmi.c b/drivers/platform/x86/dell-smbios-wmi.c index 88afe5651d24..cf2229ece9ff 100644 --- a/drivers/platform/x86/dell-smbios-wmi.c +++ b/drivers/platform/x86/dell-smbios-wmi.c @@ -78,6 +78,7 @@ static int run_smbios_call(struct wmi_device *wdev) dev_dbg(&wdev->dev, "result: [%08x,%08x,%08x,%08x]\n", priv->buf->std.output[0], priv->buf->std.output[1], priv->buf->std.output[2], priv->buf->std.output[3]); + kfree(output.pointer); return 0; } diff --git a/drivers/s390/crypto/ap_bus.c b/drivers/s390/crypto/ap_bus.c index ec891bc7d10a..f039266b275d 100644 --- a/drivers/s390/crypto/ap_bus.c +++ b/drivers/s390/crypto/ap_bus.c @@ -872,8 +872,6 @@ static int hex2bitmap(const char *str, unsigned long *bitmap, int bits) if (bits & 0x07) return -EINVAL; - memset(bitmap, 0, bits / 8); - if (str[0] == '0' && str[1] == 'x') str++; if (*str == 'x') @@ -895,25 +893,23 @@ static int hex2bitmap(const char *str, unsigned long *bitmap, int bits) } /* - * str2clrsetmasks() - parse bitmask argument and set the clear and - * the set bitmap mask. A concatenation (done with ',') of these terms - * is recognized: + * modify_bitmap() - parse bitmask argument and modify an existing + * bit mask accordingly. A concatenation (done with ',') of these + * terms is recognized: * +<bitnr>[-<bitnr>] or -<bitnr>[-<bitnr>] * <bitnr> may be any valid number (hex, decimal or octal) in the range * 0...bits-1; the leading + or - is required. Here are some examples: * +0-15,+32,-128,-0xFF * -0-255,+1-16,+0x128 * +1,+2,+3,+4,-5,-7-10 - * Returns a clear and a set bitmask. Every positive value in the string - * results in a bit set in the set mask and every negative value in the - * string results in a bit SET in the clear mask. As a bit may be touched - * more than once, the last 'operation' wins: +0-255,-128 = all but bit - * 128 set in the set mask, only bit 128 set in the clear mask. + * Returns the new bitmap after all changes have been applied. Every + * positive value in the string will set a bit and every negative value + * in the string will clear a bit. As a bit may be touched more than once, + * the last 'operation' wins: + * +0-255,-128 = first bits 0-255 will be set, then bit 128 will be + * cleared again. All other bits are unmodified. */ -static int str2clrsetmasks(const char *str, - unsigned long *clrmap, - unsigned long *setmap, - int bits) +static int modify_bitmap(const char *str, unsigned long *bitmap, int bits) { int a, i, z; char *np, sign; @@ -922,9 +918,6 @@ static int str2clrsetmasks(const char *str, if (bits & 0x07) return -EINVAL; - memset(clrmap, 0, bits / 8); - memset(setmap, 0, bits / 8); - while (*str) { sign = *str++; if (sign != '+' && sign != '-') @@ -940,13 +933,10 @@ static int str2clrsetmasks(const char *str, str = np; } for (i = a; i <= z; i++) - if (sign == '+') { - set_bit_inv(i, setmap); - clear_bit_inv(i, clrmap); - } else { - clear_bit_inv(i, setmap); - set_bit_inv(i, clrmap); - } + if (sign == '+') + set_bit_inv(i, bitmap); + else + clear_bit_inv(i, bitmap); while (*str == ',' || *str == '\n') str++; } @@ -970,44 +960,34 @@ static int process_mask_arg(const char *str, unsigned long *bitmap, int bits, struct mutex *lock) { - int i; + unsigned long *newmap, size; + int rc; /* bits needs to be a multiple of 8 */ if (bits & 0x07) return -EINVAL; + size = BITS_TO_LONGS(bits)*sizeof(unsigned long); + newmap = kmalloc(size, GFP_KERNEL); + if (!newmap) + return -ENOMEM; + if (mutex_lock_interruptible(lock)) { + kfree(newmap); + return -ERESTARTSYS; + } + if (*str == '+' || *str == '-') { - DECLARE_BITMAP(clrm, bits); - DECLARE_BITMAP(setm, bits); - - i = str2clrsetmasks(str, clrm, setm, bits); - if (i) - return i; - if (mutex_lock_interruptible(lock)) - return -ERESTARTSYS; - for (i = 0; i < bits; i++) { - if (test_bit_inv(i, clrm)) - clear_bit_inv(i, bitmap); - if (test_bit_inv(i, setm)) - set_bit_inv(i, bitmap); - } + memcpy(newmap, bitmap, size); + rc = modify_bitmap(str, newmap, bits); } else { - DECLARE_BITMAP(setm, bits); - - i = hex2bitmap(str, setm, bits); - if (i) - return i; - if (mutex_lock_interruptible(lock)) - return -ERESTARTSYS; - for (i = 0; i < bits; i++) - if (test_bit_inv(i, setm)) - set_bit_inv(i, bitmap); - else - clear_bit_inv(i, bitmap); + memset(newmap, 0, size); + rc = hex2bitmap(str, newmap, bits); } + if (rc == 0) + memcpy(bitmap, newmap, size); mutex_unlock(lock); - - return 0; + kfree(newmap); + return rc; } /* diff --git a/drivers/s390/net/qeth_core.h b/drivers/s390/net/qeth_core.h index 34e0d476c5c6..0dbe81f958f0 100644 --- a/drivers/s390/net/qeth_core.h +++ b/drivers/s390/net/qeth_core.h @@ -26,6 +26,7 @@ #include <net/ipv6.h> #include <net/if_inet6.h> #include <net/addrconf.h> +#include <net/tcp.h> #include <asm/debug.h> #include <asm/qdio.h> @@ -638,7 +639,6 @@ struct qeth_reply { atomic_t received; int rc; void *param; - struct qeth_card *card; refcount_t refcnt; }; @@ -892,11 +892,6 @@ static inline void qeth_tx_csum(struct sk_buff *skb, u8 *flags, int ipv) if ((ipv == 4 && ip_hdr(skb)->protocol == IPPROTO_UDP) || (ipv == 6 && ipv6_hdr(skb)->nexthdr == IPPROTO_UDP)) *flags |= QETH_HDR_EXT_UDP; - if (ipv == 4) { - /* some HW requires combined L3+L4 csum offload: */ - *flags |= QETH_HDR_EXT_CSUM_HDR_REQ; - ip_hdr(skb)->check = 0; - } } static inline void qeth_put_buffer_pool_entry(struct qeth_card *card, @@ -1007,9 +1002,7 @@ int qeth_query_switch_attributes(struct qeth_card *card, int qeth_send_control_data(struct qeth_card *, int, struct qeth_cmd_buffer *, int (*reply_cb)(struct qeth_card *, struct qeth_reply*, unsigned long), void *reply_param); -int qeth_get_elements_no(struct qeth_card *card, struct sk_buff *skb, - int extra_elems, int data_offset); -int qeth_get_elements_for_frags(struct sk_buff *); +unsigned int qeth_count_elements(struct sk_buff *skb, unsigned int data_offset); int qeth_do_send_packet_fast(struct qeth_qdio_out_q *queue, struct sk_buff *skb, struct qeth_hdr *hdr, unsigned int offset, unsigned int hd_len); @@ -1027,7 +1020,6 @@ void qeth_dbf_longtext(debug_info_t *id, int level, char *text, ...); int qeth_core_ethtool_get_link_ksettings(struct net_device *netdev, struct ethtool_link_ksettings *cmd); int qeth_set_access_ctrl_online(struct qeth_card *card, int fallback); -int qeth_hdr_chk_and_bounce(struct sk_buff *, struct qeth_hdr **, int); int qeth_configure_cq(struct qeth_card *, enum qeth_cq); int qeth_hw_trap(struct qeth_card *, enum qeth_diags_trap_action); void qeth_trace_features(struct qeth_card *); @@ -1052,6 +1044,11 @@ int qeth_vm_request_mac(struct qeth_card *card); int qeth_add_hw_header(struct qeth_card *card, struct sk_buff *skb, struct qeth_hdr **hdr, unsigned int hdr_len, unsigned int proto_len, unsigned int *elements); +int qeth_xmit(struct qeth_card *card, struct sk_buff *skb, + struct qeth_qdio_out_q *queue, int ipv, int cast_type, + void (*fill_header)(struct qeth_card *card, struct qeth_hdr *hdr, + struct sk_buff *skb, int ipv, int cast_type, + unsigned int data_len)); /* exports for OSN */ int qeth_osn_assist(struct net_device *, void *, int); diff --git a/drivers/s390/net/qeth_core_main.c b/drivers/s390/net/qeth_core_main.c index 49f64eb3eab0..89e09e7b8fff 100644 --- a/drivers/s390/net/qeth_core_main.c +++ b/drivers/s390/net/qeth_core_main.c @@ -16,6 +16,7 @@ #include <linux/string.h> #include <linux/errno.h> #include <linux/kernel.h> +#include <linux/log2.h> #include <linux/ip.h> #include <linux/tcp.h> #include <linux/mii.h> @@ -25,6 +26,7 @@ #include <linux/netdevice.h> #include <linux/netdev_features.h> #include <linux/skbuff.h> +#include <linux/vmalloc.h> #include <net/iucv/af_iucv.h> #include <net/dsfield.h> @@ -590,7 +592,6 @@ static struct qeth_reply *qeth_alloc_reply(struct qeth_card *card) if (reply) { refcount_set(&reply->refcnt, 1); atomic_set(&reply->received, 0); - reply->card = card; } return reply; } @@ -779,7 +780,6 @@ void qeth_release_buffer(struct qeth_channel *channel, QETH_CARD_TEXT(CARD_FROM_CDEV(channel->ccwdev), 6, "relbuff"); spin_lock_irqsave(&channel->iob_lock, flags); - memset(iob->data, 0, QETH_BUFSIZE); iob->state = BUF_STATE_FREE; iob->callback = qeth_send_control_data_cb; iob->rc = 0; @@ -899,44 +899,6 @@ out: qeth_release_buffer(channel, iob); } -static int qeth_setup_channel(struct qeth_channel *channel, bool alloc_buffers) -{ - int cnt; - - QETH_DBF_TEXT(SETUP, 2, "setupch"); - - channel->ccw = kmalloc(sizeof(struct ccw1), GFP_KERNEL | GFP_DMA); - if (!channel->ccw) - return -ENOMEM; - channel->state = CH_STATE_DOWN; - atomic_set(&channel->irq_pending, 0); - init_waitqueue_head(&channel->wait_q); - - if (!alloc_buffers) - return 0; - - for (cnt = 0; cnt < QETH_CMD_BUFFER_NO; cnt++) { - channel->iob[cnt].data = - kzalloc(QETH_BUFSIZE, GFP_DMA|GFP_KERNEL); - if (channel->iob[cnt].data == NULL) - break; - channel->iob[cnt].state = BUF_STATE_FREE; - channel->iob[cnt].channel = channel; - channel->iob[cnt].callback = qeth_send_control_data_cb; - channel->iob[cnt].rc = 0; - } - if (cnt < QETH_CMD_BUFFER_NO) { - kfree(channel->ccw); - while (cnt-- > 0) - kfree(channel->iob[cnt].data); - return -ENOMEM; - } - channel->io_buf_no = 0; - spin_lock_init(&channel->iob_lock); - - return 0; -} - static int qeth_set_thread_start_bit(struct qeth_card *card, unsigned long thread) { @@ -1335,14 +1297,61 @@ static void qeth_free_buffer_pool(struct qeth_card *card) static void qeth_clean_channel(struct qeth_channel *channel) { + struct ccw_device *cdev = channel->ccwdev; int cnt; QETH_DBF_TEXT(SETUP, 2, "freech"); + + spin_lock_irq(get_ccwdev_lock(cdev)); + cdev->handler = NULL; + spin_unlock_irq(get_ccwdev_lock(cdev)); + for (cnt = 0; cnt < QETH_CMD_BUFFER_NO; cnt++) kfree(channel->iob[cnt].data); kfree(channel->ccw); } +static int qeth_setup_channel(struct qeth_channel *channel, bool alloc_buffers) +{ + struct ccw_device *cdev = channel->ccwdev; + int cnt; + + QETH_DBF_TEXT(SETUP, 2, "setupch"); + + channel->ccw = kmalloc(sizeof(struct ccw1), GFP_KERNEL | GFP_DMA); + if (!channel->ccw) + return -ENOMEM; + channel->state = CH_STATE_DOWN; + atomic_set(&channel->irq_pending, 0); + init_waitqueue_head(&channel->wait_q); + + spin_lock_irq(get_ccwdev_lock(cdev)); + cdev->handler = qeth_irq; + spin_unlock_irq(get_ccwdev_lock(cdev)); + + if (!alloc_buffers) + return 0; + + for (cnt = 0; cnt < QETH_CMD_BUFFER_NO; cnt++) { + channel->iob[cnt].data = kmalloc(QETH_BUFSIZE, + GFP_KERNEL | GFP_DMA); + if (channel->iob[cnt].data == NULL) + break; + channel->iob[cnt].state = BUF_STATE_FREE; + channel->iob[cnt].channel = channel; + channel->iob[cnt].callback = qeth_send_control_data_cb; + channel->iob[cnt].rc = 0; + } + if (cnt < QETH_CMD_BUFFER_NO) { + qeth_clean_channel(channel); + return -ENOMEM; + } + channel->io_buf_no = 0; + spin_lock_init(&channel->iob_lock); + + return 0; +} + static void qeth_set_single_write_queues(struct qeth_card *card) { if ((atomic_read(&card->qdio.state) != QETH_QDIO_UNINITIALIZED) && @@ -1493,7 +1502,7 @@ static void qeth_core_sl_print(struct seq_file *m, struct service_level *slr) CARD_BUS_ID(card), card->info.mcl_level); } -static struct qeth_card *qeth_alloc_card(void) +static struct qeth_card *qeth_alloc_card(struct ccwgroup_device *gdev) { struct qeth_card *card; @@ -1502,6 +1511,11 @@ static struct qeth_card *qeth_alloc_card(void) if (!card) goto out; QETH_DBF_HEX(SETUP, 2, &card, sizeof(void *)); + + card->gdev = gdev; + CARD_RDEV(card) = gdev->cdev[0]; + CARD_WDEV(card) = gdev->cdev[1]; + CARD_DDEV(card) = gdev->cdev[2]; if (qeth_setup_channel(&card->read, true)) goto out_ip; if (qeth_setup_channel(&card->write, true)) @@ -1525,15 +1539,14 @@ out: static int qeth_clear_channel(struct qeth_channel *channel) { - unsigned long flags; struct qeth_card *card; int rc; card = CARD_FROM_CDEV(channel->ccwdev); QETH_CARD_TEXT(card, 3, "clearch"); - spin_lock_irqsave(get_ccwdev_lock(channel->ccwdev), flags); + spin_lock_irq(get_ccwdev_lock(channel->ccwdev)); rc = ccw_device_clear(channel->ccwdev, QETH_CLEAR_CHANNEL_PARM); - spin_unlock_irqrestore(get_ccwdev_lock(channel->ccwdev), flags); + spin_unlock_irq(get_ccwdev_lock(channel->ccwdev)); if (rc) return rc; @@ -1549,15 +1562,14 @@ static int qeth_clear_channel(struct qeth_channel *channel) static int qeth_halt_channel(struct qeth_channel *channel) { - unsigned long flags; struct qeth_card *card; int rc; card = CARD_FROM_CDEV(channel->ccwdev); QETH_CARD_TEXT(card, 3, "haltch"); - spin_lock_irqsave(get_ccwdev_lock(channel->ccwdev), flags); + spin_lock_irq(get_ccwdev_lock(channel->ccwdev)); rc = ccw_device_halt(channel->ccwdev, QETH_HALT_CHANNEL_PARM); - spin_unlock_irqrestore(get_ccwdev_lock(channel->ccwdev), flags); + spin_unlock_irq(get_ccwdev_lock(channel->ccwdev)); if (rc) return rc; @@ -1651,7 +1663,6 @@ static int qeth_read_conf_data(struct qeth_card *card, void **buffer, char *rcd_buf; int ret; struct qeth_channel *channel = &card->data; - unsigned long flags; /* * scan for RCD command in extended SenseID data @@ -1665,11 +1676,11 @@ static int qeth_read_conf_data(struct qeth_card *card, void **buffer, qeth_setup_ccw(channel->ccw, ciw->cmd, ciw->count, rcd_buf); channel->state = CH_STATE_RCD; - spin_lock_irqsave(get_ccwdev_lock(channel->ccwdev), flags); + spin_lock_irq(get_ccwdev_lock(channel->ccwdev)); ret = ccw_device_start_timeout(channel->ccwdev, channel->ccw, QETH_RCD_PARM, LPM_ANYPATH, 0, QETH_RCD_TIMEOUT); - spin_unlock_irqrestore(get_ccwdev_lock(channel->ccwdev), flags); + spin_unlock_irq(get_ccwdev_lock(channel->ccwdev)); if (!ret) wait_event(card->wait_q, (channel->state == CH_STATE_RCD_DONE || @@ -1827,7 +1838,6 @@ static int qeth_idx_activate_get_answer(struct qeth_channel *channel, struct qeth_cmd_buffer *)) { struct qeth_cmd_buffer *iob; - unsigned long flags; int rc; struct qeth_card *card; @@ -1842,10 +1852,10 @@ static int qeth_idx_activate_get_answer(struct qeth_channel *channel, wait_event(card->wait_q, atomic_cmpxchg(&channel->irq_pending, 0, 1) == 0); QETH_DBF_TEXT(SETUP, 6, "noirqpnd"); - spin_lock_irqsave(get_ccwdev_lock(channel->ccwdev), flags); + spin_lock_irq(get_ccwdev_lock(channel->ccwdev)); rc = ccw_device_start_timeout(channel->ccwdev, channel->ccw, (addr_t) iob, 0, 0, QETH_TIMEOUT); - spin_unlock_irqrestore(get_ccwdev_lock(channel->ccwdev), flags); + spin_unlock_irq(get_ccwdev_lock(channel->ccwdev)); if (rc) { QETH_DBF_MESSAGE(2, "Error2 in activating channel rc=%d\n", rc); @@ -1872,7 +1882,6 @@ static int qeth_idx_activate_channel(struct qeth_channel *channel, { struct qeth_card *card; struct qeth_cmd_buffer *iob; - unsigned long flags; __u16 temp; __u8 tmp; int rc; @@ -1912,10 +1921,10 @@ static int qeth_idx_activate_channel(struct qeth_channel *channel, wait_event(card->wait_q, atomic_cmpxchg(&channel->irq_pending, 0, 1) == 0); QETH_DBF_TEXT(SETUP, 6, "noirqpnd"); - spin_lock_irqsave(get_ccwdev_lock(channel->ccwdev), flags); + spin_lock_irq(get_ccwdev_lock(channel->ccwdev)); rc = ccw_device_start_timeout(channel->ccwdev, channel->ccw, (addr_t) iob, 0, 0, QETH_TIMEOUT); - spin_unlock_irqrestore(get_ccwdev_lock(channel->ccwdev), flags); + spin_unlock_irq(get_ccwdev_lock(channel->ccwdev)); if (rc) { QETH_DBF_MESSAGE(2, "Error1 in activating channel. rc=%d\n", @@ -2096,7 +2105,6 @@ int qeth_send_control_data(struct qeth_card *card, int len, { struct qeth_channel *channel = iob->channel; int rc; - unsigned long flags; struct qeth_reply *reply = NULL; unsigned long timeout, event_timeout; struct qeth_ipa_cmd *cmd = NULL; @@ -2129,26 +2137,26 @@ int qeth_send_control_data(struct qeth_card *card, int len, } qeth_prepare_control_data(card, len, iob); - spin_lock_irqsave(&card->lock, flags); + spin_lock_irq(&card->lock); list_add_tail(&reply->list, &card->cmd_waiter_list); - spin_unlock_irqrestore(&card->lock, flags); + spin_unlock_irq(&card->lock); timeout = jiffies + event_timeout; QETH_CARD_TEXT(card, 6, "noirqpnd"); - spin_lock_irqsave(get_ccwdev_lock(channel->ccwdev), flags); + spin_lock_irq(get_ccwdev_lock(channel->ccwdev)); rc = ccw_device_start_timeout(channel->ccwdev, channel->ccw, (addr_t) iob, 0, 0, event_timeout); - spin_unlock_irqrestore(get_ccwdev_lock(channel->ccwdev), flags); + spin_unlock_irq(get_ccwdev_lock(channel->ccwdev)); if (rc) { QETH_DBF_MESSAGE(2, "%s qeth_send_control_data: " "ccw_device_start rc = %i\n", dev_name(&channel->ccwdev->dev), rc); QETH_CARD_TEXT_(card, 2, " err%d", rc); - spin_lock_irqsave(&card->lock, flags); + spin_lock_irq(&card->lock); list_del_init(&reply->list); qeth_put_reply(reply); - spin_unlock_irqrestore(&card->lock, flags); + spin_unlock_irq(&card->lock); qeth_release_buffer(channel, iob); atomic_set(&channel->irq_pending, 0); wake_up(&card->wait_q); @@ -2176,9 +2184,9 @@ int qeth_send_control_data(struct qeth_card *card, int len, time_err: reply->rc = -ETIME; - spin_lock_irqsave(&reply->card->lock, flags); + spin_lock_irq(&card->lock); list_del_init(&reply->list); - spin_unlock_irqrestore(&reply->card->lock, flags); + spin_unlock_irq(&card->lock); atomic_inc(&reply->received); rc = reply->rc; qeth_put_reply(reply); @@ -2879,10 +2887,10 @@ static __u8 qeth_get_ipa_adp_type(enum qeth_link_types link_type) } static void qeth_fill_ipacmd_header(struct qeth_card *card, - struct qeth_ipa_cmd *cmd, __u8 command, - enum qeth_prot_versions prot) + struct qeth_ipa_cmd *cmd, + enum qeth_ipa_cmds command, + enum qeth_prot_versions prot) { - memset(cmd, 0, sizeof(struct qeth_ipa_cmd)); cmd->hdr.command = command; cmd->hdr.initiator = IPA_CMD_INITIATOR_HOST; /* cmd->hdr.seqno is set by qeth_send_control_data() */ @@ -2894,8 +2902,6 @@ static void qeth_fill_ipacmd_header(struct qeth_card *card, cmd->hdr.prim_version_no = 1; cmd->hdr.param_count = 1; cmd->hdr.prot_version = prot; - cmd->hdr.ipa_supported = 0; - cmd->hdr.ipa_enabled = 0; } struct qeth_cmd_buffer *qeth_get_ipacmd_buffer(struct qeth_card *card, @@ -3042,7 +3048,7 @@ static int qeth_query_ipassists_cb(struct qeth_card *card, QETH_DBF_TEXT(SETUP, 2, "ipaunsup"); card->options.ipa4.supported_funcs |= IPA_SETADAPTERPARMS; card->options.ipa6.supported_funcs |= IPA_SETADAPTERPARMS; - return -0; + return 0; default: if (cmd->hdr.return_code) { QETH_DBF_MESSAGE(1, "%s IPA_CMD_QIPASSIST: Unhandled " @@ -3786,7 +3792,7 @@ EXPORT_SYMBOL_GPL(qeth_get_priority_queue); * Returns the number of pages, and thus QDIO buffer elements, needed to cover * fragmented part of the SKB. Returns zero for linear SKB. */ -int qeth_get_elements_for_frags(struct sk_buff *skb) +static int qeth_get_elements_for_frags(struct sk_buff *skb) { int cnt, elements = 0; @@ -3799,9 +3805,17 @@ int qeth_get_elements_for_frags(struct sk_buff *skb) } return elements; } -EXPORT_SYMBOL_GPL(qeth_get_elements_for_frags); -static unsigned int qeth_count_elements(struct sk_buff *skb, int data_offset) +/** + * qeth_count_elements() - Counts the number of QDIO buffer elements needed + * to transmit an skb. + * @skb: the skb to operate on. + * @data_offset: skip this part of the skb's linear data + * + * Returns the number of pages, and thus QDIO buffer elements, needed to map the + * skb's data (both its linear part and paged fragments). + */ +unsigned int qeth_count_elements(struct sk_buff *skb, unsigned int data_offset) { unsigned int elements = qeth_get_elements_for_frags(skb); addr_t end = (addr_t)skb->data + skb_headlen(skb); @@ -3811,54 +3825,10 @@ static unsigned int qeth_count_elements(struct sk_buff *skb, int data_offset) elements += qeth_get_elements_for_range(start, end); return elements; } +EXPORT_SYMBOL_GPL(qeth_count_elements); -/** - * qeth_get_elements_no() - find number of SBALEs for skb data, inc. frags. - * @card: qeth card structure, to check max. elems. - * @skb: SKB address - * @extra_elems: extra elems needed, to check against max. - * @data_offset: range starts at skb->data + data_offset - * - * Returns the number of pages, and thus QDIO buffer elements, needed to cover - * skb data, including linear part and fragments. Checks if the result plus - * extra_elems fits under the limit for the card. Returns 0 if it does not. - * Note: extra_elems is not included in the returned result. - */ -int qeth_get_elements_no(struct qeth_card *card, - struct sk_buff *skb, int extra_elems, int data_offset) -{ - int elements = qeth_count_elements(skb, data_offset); - - if ((elements + extra_elems) > QETH_MAX_BUFFER_ELEMENTS(card)) { - QETH_DBF_MESSAGE(2, "Invalid size of IP packet " - "(Number=%d / Length=%d). Discarded.\n", - elements + extra_elems, skb->len); - return 0; - } - return elements; -} -EXPORT_SYMBOL_GPL(qeth_get_elements_no); - -int qeth_hdr_chk_and_bounce(struct sk_buff *skb, struct qeth_hdr **hdr, int len) -{ - int hroom, inpage, rest; - - if (((unsigned long)skb->data & PAGE_MASK) != - (((unsigned long)skb->data + len - 1) & PAGE_MASK)) { - hroom = skb_headroom(skb); - inpage = PAGE_SIZE - ((unsigned long) skb->data % PAGE_SIZE); - rest = len - inpage; - if (rest > hroom) - return 1; - memmove(skb->data - rest, skb->data, skb_headlen(skb)); - skb->data -= rest; - skb->tail -= rest; - *hdr = (struct qeth_hdr *)skb->data; - QETH_DBF_MESSAGE(2, "skb bounce len: %d rest: %d\n", len, rest); - } - return 0; -} -EXPORT_SYMBOL_GPL(qeth_hdr_chk_and_bounce); +#define QETH_HDR_CACHE_OBJ_SIZE (sizeof(struct qeth_hdr_tso) + \ + MAX_TCP_HEADER) /** * qeth_add_hw_header() - add a HW header to an skb. @@ -3893,7 +3863,11 @@ check_layout: if (qeth_get_elements_for_range(start, end + contiguous) == 1) { /* Push HW header into same page as first protocol header. */ push_ok = true; - __elements = qeth_count_elements(skb, 0); + /* ... but TSO always needs a separate element for headers: */ + if (skb_is_gso(skb)) + __elements = 1 + qeth_count_elements(skb, proto_len); + else + __elements = qeth_count_elements(skb, 0); } else if (!proto_len && qeth_get_elements_for_range(start, end) == 1) { /* Push HW header into a new page. */ push_ok = true; @@ -3934,6 +3908,8 @@ check_layout: return hdr_len; } /* fall back */ + if (hdr_len + proto_len > QETH_HDR_CACHE_OBJ_SIZE) + return -E2BIG; *hdr = kmem_cache_alloc(qeth_core_header_cache, GFP_ATOMIC); if (!*hdr) return -ENOMEM; @@ -4175,6 +4151,66 @@ out: } EXPORT_SYMBOL_GPL(qeth_do_send_packet); +int qeth_xmit(struct qeth_card *card, struct sk_buff *skb, + struct qeth_qdio_out_q *queue, int ipv, int cast_type, + void (*fill_header)(struct qeth_card *card, struct qeth_hdr *hdr, + struct sk_buff *skb, int ipv, int cast_type, + unsigned int data_len)) +{ + const unsigned int proto_len = IS_IQD(card) ? ETH_HLEN : 0; + const unsigned int hw_hdr_len = sizeof(struct qeth_hdr); + unsigned int frame_len = skb->len; + unsigned int data_offset = 0; + struct qeth_hdr *hdr = NULL; + unsigned int hd_len = 0; + unsigned int elements; + int push_len, rc; + bool is_sg; + + rc = skb_cow_head(skb, hw_hdr_len); + if (rc) + return rc; + + push_len = qeth_add_hw_header(card, skb, &hdr, hw_hdr_len, proto_len, + &elements); + if (push_len < 0) + return push_len; + if (!push_len) { + /* HW header needs its own buffer element. */ + hd_len = hw_hdr_len + proto_len; + data_offset = proto_len; + } + memset(hdr, 0, hw_hdr_len); + fill_header(card, hdr, skb, ipv, cast_type, frame_len); + + is_sg = skb_is_nonlinear(skb); + if (IS_IQD(card)) { + rc = qeth_do_send_packet_fast(queue, skb, hdr, data_offset, + hd_len); + } else { + /* TODO: drop skb_orphan() once TX completion is fast enough */ + skb_orphan(skb); + rc = qeth_do_send_packet(card, queue, skb, hdr, data_offset, + hd_len, elements); + } + + if (!rc) { + if (card->options.performance_stats) { + card->perf_stats.buf_elements_sent += elements; + if (is_sg) + card->perf_stats.sg_skbs_sent++; + } + } else { + if (!push_len) + kmem_cache_free(qeth_core_header_cache, hdr); + if (rc == -EBUSY) + /* roll back to ETH header */ + skb_pull(skb, push_len); + } + return rc; +} +EXPORT_SYMBOL_GPL(qeth_xmit); + static int qeth_setadp_promisc_mode_cb(struct qeth_card *card, struct qeth_reply *reply, unsigned long data) { @@ -4699,7 +4735,7 @@ static int qeth_query_oat_command(struct qeth_card *card, char __user *udata) priv.buffer_len = oat_data.buffer_len; priv.response_len = 0; - priv.buffer = kzalloc(oat_data.buffer_len, GFP_KERNEL); + priv.buffer = vzalloc(oat_data.buffer_len); if (!priv.buffer) { rc = -ENOMEM; goto out; @@ -4740,7 +4776,7 @@ static int qeth_query_oat_command(struct qeth_card *card, char __user *udata) rc = -EFAULT; out_free: - kfree(priv.buffer); + vfree(priv.buffer); out: return rc; } @@ -5455,8 +5491,6 @@ struct qeth_cmd_buffer *qeth_get_setassparms_cmd(struct qeth_card *card, cmd->data.setassparms.hdr.assist_no = ipa_func; cmd->data.setassparms.hdr.length = 8 + len; cmd->data.setassparms.hdr.command_code = cmd_code; - cmd->data.setassparms.hdr.return_code = 0; - cmd->data.setassparms.hdr.seq_no = 0; } return iob; @@ -5706,6 +5740,8 @@ static struct net_device *qeth_alloc_netdev(struct qeth_card *card) dev->priv_flags &= ~IFF_TX_SKB_SHARING; dev->hw_features |= NETIF_F_SG; dev->vlan_features |= NETIF_F_SG; + if (IS_IQD(card)) + dev->features |= NETIF_F_SG; } return dev; @@ -5728,7 +5764,6 @@ static int qeth_core_probe_device(struct ccwgroup_device *gdev) struct device *dev; int rc; enum qeth_discipline_id enforced_disc; - unsigned long flags; char dbf_name[DBF_NAME_LEN]; QETH_DBF_TEXT(SETUP, 2, "probedev"); @@ -5739,7 +5774,7 @@ static int qeth_core_probe_device(struct ccwgroup_device *gdev) QETH_DBF_TEXT_(SETUP, 2, "%s", dev_name(&gdev->dev)); - card = qeth_alloc_card(); + card = qeth_alloc_card(gdev); if (!card) { QETH_DBF_TEXT_(SETUP, 2, "1err%d", -ENOMEM); rc = -ENOMEM; @@ -5755,21 +5790,15 @@ static int qeth_core_probe_device(struct ccwgroup_device *gdev) goto err_card; } - card->read.ccwdev = gdev->cdev[0]; - card->write.ccwdev = gdev->cdev[1]; - card->data.ccwdev = gdev->cdev[2]; dev_set_drvdata(&gdev->dev, card); - card->gdev = gdev; - gdev->cdev[0]->handler = qeth_irq; - gdev->cdev[1]->handler = qeth_irq; - gdev->cdev[2]->handler = qeth_irq; - qeth_setup_card(card); qeth_update_from_chp_desc(card); card->dev = qeth_alloc_netdev(card); - if (!card->dev) + if (!card->dev) { + rc = -ENOMEM; goto err_card; + } qeth_determine_capabilities(card); enforced_disc = qeth_enforce_discipline(card); @@ -5792,9 +5821,9 @@ static int qeth_core_probe_device(struct ccwgroup_device *gdev) break; } - write_lock_irqsave(&qeth_core_card_list.rwlock, flags); + write_lock_irq(&qeth_core_card_list.rwlock); list_add_tail(&card->list, &qeth_core_card_list.list); - write_unlock_irqrestore(&qeth_core_card_list.rwlock, flags); + write_unlock_irq(&qeth_core_card_list.rwlock); return 0; err_disc: @@ -5810,7 +5839,6 @@ err_dev: static void qeth_core_remove_device(struct ccwgroup_device *gdev) { - unsigned long flags; struct qeth_card *card = dev_get_drvdata(&gdev->dev); QETH_DBF_TEXT(SETUP, 2, "removedv"); @@ -5820,9 +5848,9 @@ static void qeth_core_remove_device(struct ccwgroup_device *gdev) qeth_core_free_discipline(card); } - write_lock_irqsave(&qeth_core_card_list.rwlock, flags); + write_lock_irq(&qeth_core_card_list.rwlock); list_del(&card->list); - write_unlock_irqrestore(&qeth_core_card_list.rwlock, flags); + write_unlock_irq(&qeth_core_card_list.rwlock); free_netdev(card->dev); qeth_core_free_card(card); dev_set_drvdata(&gdev->dev, NULL); @@ -6614,8 +6642,10 @@ static int __init qeth_core_init(void) rc = PTR_ERR_OR_ZERO(qeth_core_root_dev); if (rc) goto register_err; - qeth_core_header_cache = kmem_cache_create("qeth_hdr", - sizeof(struct qeth_hdr) + ETH_HLEN, 64, 0, NULL); + qeth_core_header_cache = + kmem_cache_create("qeth_hdr", QETH_HDR_CACHE_OBJ_SIZE, + roundup_pow_of_two(QETH_HDR_CACHE_OBJ_SIZE), + 0, NULL); if (!qeth_core_header_cache) { rc = -ENOMEM; goto slab_err; diff --git a/drivers/s390/net/qeth_l2_main.c b/drivers/s390/net/qeth_l2_main.c index 710fa74892ae..12858ffa28cf 100644 --- a/drivers/s390/net/qeth_l2_main.c +++ b/drivers/s390/net/qeth_l2_main.c @@ -193,15 +193,21 @@ static int qeth_l2_get_cast_type(struct qeth_card *card, struct sk_buff *skb) return RTN_UNICAST; } -static void qeth_l2_fill_header(struct qeth_hdr *hdr, struct sk_buff *skb, - int cast_type, unsigned int data_len) +static void qeth_l2_fill_header(struct qeth_card *card, struct qeth_hdr *hdr, + struct sk_buff *skb, int ipv, int cast_type, + unsigned int data_len) { struct vlan_ethhdr *veth = (struct vlan_ethhdr *)skb_mac_header(skb); - memset(hdr, 0, sizeof(struct qeth_hdr)); hdr->hdr.l2.id = QETH_HEADER_TYPE_LAYER2; hdr->hdr.l2.pkt_length = data_len; + if (skb->ip_summed == CHECKSUM_PARTIAL) { + qeth_tx_csum(skb, &hdr->hdr.l2.flags[1], ipv); + if (card->options.performance_stats) + card->perf_stats.tx_csum++; + } + /* set byte byte 3 to casting flags */ if (cast_type == RTN_MULTICAST) hdr->hdr.l2.flags[2] |= QETH_LAYER2_FLAG_MULTICAST; @@ -423,7 +429,7 @@ static int qeth_l2_process_inbound_buffer(struct qeth_card *card, default: dev_kfree_skb_any(skb); QETH_CARD_TEXT(card, 3, "inbunkno"); - QETH_DBF_HEX(CTRL, 3, hdr, QETH_DBF_CTRL_LEN); + QETH_DBF_HEX(CTRL, 3, hdr, sizeof(*hdr)); continue; } work_done++; @@ -641,84 +647,43 @@ static void qeth_l2_set_rx_mode(struct net_device *dev) qeth_promisc_to_bridge(card); } -static int qeth_l2_xmit(struct qeth_card *card, struct sk_buff *skb, - struct qeth_qdio_out_q *queue, int cast_type, int ipv) +static int qeth_l2_xmit_osn(struct qeth_card *card, struct sk_buff *skb, + struct qeth_qdio_out_q *queue) { - const unsigned int proto_len = IS_IQD(card) ? ETH_HLEN : 0; - const unsigned int hw_hdr_len = sizeof(struct qeth_hdr); - unsigned int frame_len = skb->len; - unsigned int data_offset = 0; - struct qeth_hdr *hdr = NULL; + struct qeth_hdr *hdr = (struct qeth_hdr *)skb->data; + addr_t end = (addr_t)(skb->data + sizeof(*hdr)); + addr_t start = (addr_t)skb->data; + unsigned int elements = 0; unsigned int hd_len = 0; - unsigned int elements; - int push_len, rc; - bool is_sg; + int rc; - rc = skb_cow_head(skb, hw_hdr_len); - if (rc) - return rc; + if (skb->protocol == htons(ETH_P_IPV6)) + return -EPROTONOSUPPORT; - push_len = qeth_add_hw_header(card, skb, &hdr, hw_hdr_len, proto_len, - &elements); - if (push_len < 0) - return push_len; - if (!push_len) { - /* HW header needs its own buffer element. */ - hd_len = hw_hdr_len + proto_len; - data_offset = proto_len; - } - qeth_l2_fill_header(hdr, skb, cast_type, frame_len); - if (skb->ip_summed == CHECKSUM_PARTIAL) { - qeth_tx_csum(skb, &hdr->hdr.l2.flags[1], ipv); - if (card->options.performance_stats) - card->perf_stats.tx_csum++; + if (qeth_get_elements_for_range(start, end) > 1) { + /* Misaligned HW header, move it to its own buffer element. */ + hdr = kmem_cache_alloc(qeth_core_header_cache, GFP_ATOMIC); + if (!hdr) + return -ENOMEM; + hd_len = sizeof(*hdr); + skb_copy_from_linear_data(skb, (char *)hdr, hd_len); + elements++; } - is_sg = skb_is_nonlinear(skb); - if (IS_IQD(card)) { - rc = qeth_do_send_packet_fast(queue, skb, hdr, data_offset, - hd_len); - } else { - /* TODO: drop skb_orphan() once TX completion is fast enough */ - skb_orphan(skb); - rc = qeth_do_send_packet(card, queue, skb, hdr, data_offset, - hd_len, elements); + elements += qeth_count_elements(skb, hd_len); + if (elements > QETH_MAX_BUFFER_ELEMENTS(card)) { + rc = -E2BIG; + goto out; } - if (!rc) { - if (card->options.performance_stats) { - card->perf_stats.buf_elements_sent += elements; - if (is_sg) - card->perf_stats.sg_skbs_sent++; - } - } else { - if (!push_len) - kmem_cache_free(qeth_core_header_cache, hdr); - if (rc == -EBUSY) - /* roll back to ETH header */ - skb_pull(skb, push_len); - } + rc = qeth_do_send_packet(card, queue, skb, hdr, hd_len, hd_len, + elements); +out: + if (rc && hd_len) + kmem_cache_free(qeth_core_header_cache, hdr); return rc; } -static int qeth_l2_xmit_osn(struct qeth_card *card, struct sk_buff *skb, - struct qeth_qdio_out_q *queue) -{ - unsigned int elements; - struct qeth_hdr *hdr; - - if (skb->protocol == htons(ETH_P_IPV6)) - return -EPROTONOSUPPORT; - - hdr = (struct qeth_hdr *)skb->data; - elements = qeth_get_elements_no(card, skb, 0, 0); - if (!elements) - return -E2BIG; - if (qeth_hdr_chk_and_bounce(skb, &hdr, sizeof(*hdr))) - return -EINVAL; - return qeth_do_send_packet(card, queue, skb, hdr, 0, 0, elements); -} - static netdev_tx_t qeth_l2_hard_start_xmit(struct sk_buff *skb, struct net_device *dev) { @@ -745,7 +710,8 @@ static netdev_tx_t qeth_l2_hard_start_xmit(struct sk_buff *skb, if (IS_OSN(card)) rc = qeth_l2_xmit_osn(card, skb, queue); else - rc = qeth_l2_xmit(card, skb, queue, cast_type, ipv); + rc = qeth_xmit(card, skb, queue, ipv, cast_type, + qeth_l2_fill_header); if (!rc) { card->stats.tx_packets++; @@ -789,7 +755,10 @@ static int __qeth_l2_open(struct net_device *dev) if (qdio_stop_irq(card->data.ccwdev, 0) >= 0) { napi_enable(&card->napi); + local_bh_disable(); napi_schedule(&card->napi); + /* kick-start the NAPI softirq: */ + local_bh_enable(); } else rc = -EIO; return rc; @@ -1240,7 +1209,6 @@ static int qeth_osn_send_control_data(struct qeth_card *card, int len, struct qeth_cmd_buffer *iob) { struct qeth_channel *channel = iob->channel; - unsigned long flags; int rc = 0; QETH_CARD_TEXT(card, 5, "osndctrd"); @@ -1249,10 +1217,10 @@ static int qeth_osn_send_control_data(struct qeth_card *card, int len, atomic_cmpxchg(&channel->irq_pending, 0, 1) == 0); qeth_prepare_control_data(card, len, iob); QETH_CARD_TEXT(card, 6, "osnoirqp"); - spin_lock_irqsave(get_ccwdev_lock(channel->ccwdev), flags); + spin_lock_irq(get_ccwdev_lock(channel->ccwdev)); rc = ccw_device_start_timeout(channel->ccwdev, channel->ccw, (addr_t) iob, 0, 0, QETH_IPA_TIMEOUT); - spin_unlock_irqrestore(get_ccwdev_lock(channel->ccwdev), flags); + spin_unlock_irq(get_ccwdev_lock(channel->ccwdev)); if (rc) { QETH_DBF_MESSAGE(2, "qeth_osn_send_control_data: " "ccw_device_start rc = %i\n", rc); diff --git a/drivers/s390/net/qeth_l3_main.c b/drivers/s390/net/qeth_l3_main.c index 7175086677fb..8930d2a9fcad 100644 --- a/drivers/s390/net/qeth_l3_main.c +++ b/drivers/s390/net/qeth_l3_main.c @@ -33,7 +33,6 @@ #include <net/ipv6.h> #include <net/ip6_route.h> #include <net/ip6_fib.h> -#include <net/ip6_checksum.h> #include <net/iucv/af_iucv.h> #include <linux/hashtable.h> @@ -1390,7 +1389,7 @@ static int qeth_l3_process_inbound_buffer(struct qeth_card *card, default: dev_kfree_skb_any(skb); QETH_CARD_TEXT(card, 3, "inbunkno"); - QETH_DBF_HEX(CTRL, 3, hdr, QETH_DBF_CTRL_LEN); + QETH_DBF_HEX(CTRL, 3, hdr, sizeof(*hdr)); continue; } work_done++; @@ -1983,21 +1982,23 @@ static int qeth_l3_get_cast_type(struct sk_buff *skb) rcu_read_unlock(); /* no neighbour (eg AF_PACKET), fall back to target's IP address ... */ - if (be16_to_cpu(skb->protocol) == ETH_P_IPV6) - return ipv6_addr_is_multicast(&ipv6_hdr(skb)->daddr) ? - RTN_MULTICAST : RTN_UNICAST; - else if (be16_to_cpu(skb->protocol) == ETH_P_IP) + switch (qeth_get_ip_version(skb)) { + case 4: return ipv4_is_multicast(ip_hdr(skb)->daddr) ? RTN_MULTICAST : RTN_UNICAST; - - /* ... and MAC address */ - if (ether_addr_equal_64bits(eth_hdr(skb)->h_dest, skb->dev->broadcast)) - return RTN_BROADCAST; - if (is_multicast_ether_addr(eth_hdr(skb)->h_dest)) - return RTN_MULTICAST; - - /* default to unicast */ - return RTN_UNICAST; + case 6: + return ipv6_addr_is_multicast(&ipv6_hdr(skb)->daddr) ? + RTN_MULTICAST : RTN_UNICAST; + default: + /* ... and MAC address */ + if (ether_addr_equal_64bits(eth_hdr(skb)->h_dest, + skb->dev->broadcast)) + return RTN_BROADCAST; + if (is_multicast_ether_addr(eth_hdr(skb)->h_dest)) + return RTN_MULTICAST; + /* default to unicast */ + return RTN_UNICAST; + } } static void qeth_l3_fill_af_iucv_hdr(struct qeth_hdr *hdr, struct sk_buff *skb, @@ -2006,7 +2007,6 @@ static void qeth_l3_fill_af_iucv_hdr(struct qeth_hdr *hdr, struct sk_buff *skb, char daddr[16]; struct af_iucv_trans_hdr *iucv_hdr; - memset(hdr, 0, sizeof(struct qeth_hdr)); hdr->hdr.l3.id = QETH_HEADER_TYPE_LAYER3; hdr->hdr.l3.length = data_len; hdr->hdr.l3.flags = QETH_HDR_IPV6 | QETH_CAST_UNICAST; @@ -2034,26 +2034,33 @@ static void qeth_l3_fill_header(struct qeth_card *card, struct qeth_hdr *hdr, struct sk_buff *skb, int ipv, int cast_type, unsigned int data_len) { - memset(hdr, 0, sizeof(struct qeth_hdr)); - hdr->hdr.l3.id = QETH_HEADER_TYPE_LAYER3; + struct vlan_ethhdr *veth = vlan_eth_hdr(skb); + hdr->hdr.l3.length = data_len; - /* - * before we're going to overwrite this location with next hop ip. - * v6 uses passthrough, v4 sets the tag in the QDIO header. - */ - if (skb_vlan_tag_present(skb)) { - if ((ipv == 4) || (card->info.type == QETH_CARD_TYPE_IQD)) - hdr->hdr.l3.ext_flags = QETH_HDR_EXT_VLAN_FRAME; - else - hdr->hdr.l3.ext_flags = QETH_HDR_EXT_INCLUDE_VLAN_TAG; - hdr->hdr.l3.vlan_id = skb_vlan_tag_get(skb); + if (skb_is_gso(skb)) { + hdr->hdr.l3.id = QETH_HEADER_TYPE_TSO; + } else { + hdr->hdr.l3.id = QETH_HEADER_TYPE_LAYER3; + if (skb->ip_summed == CHECKSUM_PARTIAL) { + qeth_tx_csum(skb, &hdr->hdr.l3.ext_flags, ipv); + /* some HW requires combined L3+L4 csum offload: */ + if (ipv == 4) + hdr->hdr.l3.ext_flags |= QETH_HDR_EXT_CSUM_HDR_REQ; + if (card->options.performance_stats) + card->perf_stats.tx_csum++; + } } - if (!skb_is_gso(skb) && skb->ip_summed == CHECKSUM_PARTIAL) { - qeth_tx_csum(skb, &hdr->hdr.l3.ext_flags, ipv); - if (card->options.performance_stats) - card->perf_stats.tx_csum++; + if (ipv == 4 || IS_IQD(card)) { + /* NETIF_F_HW_VLAN_CTAG_TX */ + if (skb_vlan_tag_present(skb)) { + hdr->hdr.l3.ext_flags |= QETH_HDR_EXT_VLAN_FRAME; + hdr->hdr.l3.vlan_id = skb_vlan_tag_get(skb); + } + } else if (veth->h_vlan_proto == htons(ETH_P_8021Q)) { + hdr->hdr.l3.ext_flags |= QETH_HDR_EXT_INCLUDE_VLAN_TAG; + hdr->hdr.l3.vlan_id = ntohs(veth->h_vlan_TCI); } /* OSA only: */ @@ -2094,85 +2101,57 @@ static void qeth_l3_fill_header(struct qeth_card *card, struct qeth_hdr *hdr, rcu_read_unlock(); } -static void qeth_tso_fill_header(struct qeth_card *card, - struct qeth_hdr *qhdr, struct sk_buff *skb) +static void qeth_l3_fill_tso_ext(struct qeth_hdr_tso *hdr, + unsigned int payload_len, struct sk_buff *skb, + unsigned int proto_len) { - struct qeth_hdr_tso *hdr = (struct qeth_hdr_tso *)qhdr; - struct tcphdr *tcph = tcp_hdr(skb); - struct iphdr *iph = ip_hdr(skb); - struct ipv6hdr *ip6h = ipv6_hdr(skb); - - /*fix header to TSO values ...*/ - hdr->hdr.hdr.l3.id = QETH_HEADER_TYPE_TSO; - /*set values which are fix for the first approach ...*/ - hdr->ext.hdr_tot_len = (__u16) sizeof(struct qeth_hdr_ext_tso); - hdr->ext.imb_hdr_no = 1; - hdr->ext.hdr_type = 1; - hdr->ext.hdr_version = 1; - hdr->ext.hdr_len = 28; - /*insert non-fix values */ - hdr->ext.mss = skb_shinfo(skb)->gso_size; - hdr->ext.dg_hdr_len = (__u16)(ip_hdrlen(skb) + tcp_hdrlen(skb)); - hdr->ext.payload_len = (__u16)(skb->len - hdr->ext.dg_hdr_len - - sizeof(struct qeth_hdr_tso)); - tcph->check = 0; - if (be16_to_cpu(skb->protocol) == ETH_P_IPV6) { - ip6h->payload_len = 0; - tcph->check = ~csum_ipv6_magic(&ip6h->saddr, &ip6h->daddr, - 0, IPPROTO_TCP, 0); - } else { - /*OSA want us to set these values ...*/ - tcph->check = ~csum_tcpudp_magic(iph->saddr, iph->daddr, - 0, IPPROTO_TCP, 0); - iph->tot_len = 0; - iph->check = 0; - } + struct qeth_hdr_ext_tso *ext = &hdr->ext; + + ext->hdr_tot_len = sizeof(*ext); + ext->imb_hdr_no = 1; + ext->hdr_type = 1; + ext->hdr_version = 1; + ext->hdr_len = 28; + ext->payload_len = payload_len; + ext->mss = skb_shinfo(skb)->gso_size; + ext->dg_hdr_len = proto_len; } -/** - * qeth_l3_get_elements_no_tso() - find number of SBALEs for skb data for tso - * @card: qeth card structure, to check max. elems. - * @skb: SKB address - * @extra_elems: extra elems needed, to check against max. - * - * Returns the number of pages, and thus QDIO buffer elements, needed to cover - * skb data, including linear part and fragments, but excluding TCP header. - * (Exclusion of TCP header distinguishes it from qeth_get_elements_no().) - * Checks if the result plus extra_elems fits under the limit for the card. - * Returns 0 if it does not. - * Note: extra_elems is not included in the returned result. - */ -static int qeth_l3_get_elements_no_tso(struct qeth_card *card, - struct sk_buff *skb, int extra_elems) +static void qeth_l3_fixup_headers(struct sk_buff *skb) { - addr_t start = (addr_t)tcp_hdr(skb) + tcp_hdrlen(skb); - addr_t end = (addr_t)skb->data + skb_headlen(skb); - int elements = qeth_get_elements_for_frags(skb); - - if (start != end) - elements += qeth_get_elements_for_range(start, end); + struct iphdr *iph = ip_hdr(skb); - if ((elements + extra_elems) > QETH_MAX_BUFFER_ELEMENTS(card)) { - QETH_DBF_MESSAGE(2, - "Invalid size of TSO IP packet (Number=%d / Length=%d). Discarded.\n", - elements + extra_elems, skb->len); - return 0; + /* this is safe, IPv6 traffic takes a different path */ + if (skb->ip_summed == CHECKSUM_PARTIAL) + iph->check = 0; + if (skb_is_gso(skb)) { + iph->tot_len = 0; + tcp_hdr(skb)->check = ~tcp_v4_check(0, iph->saddr, + iph->daddr, 0); } - return elements; } -static int qeth_l3_xmit_offload(struct qeth_card *card, struct sk_buff *skb, - struct qeth_qdio_out_q *queue, int ipv, - int cast_type) +static int qeth_l3_xmit(struct qeth_card *card, struct sk_buff *skb, + struct qeth_qdio_out_q *queue, int ipv, int cast_type) { - const unsigned int hw_hdr_len = sizeof(struct qeth_hdr); - unsigned int frame_len, elements; + unsigned int hw_hdr_len, proto_len, frame_len, elements; unsigned char eth_hdr[ETH_HLEN]; + bool is_tso = skb_is_gso(skb); + unsigned int data_offset = 0; struct qeth_hdr *hdr = NULL; unsigned int hd_len = 0; int push_len, rc; bool is_sg; + if (is_tso) { + hw_hdr_len = sizeof(struct qeth_hdr_tso); + proto_len = skb_transport_offset(skb) + tcp_hdrlen(skb) - + ETH_HLEN; + } else { + hw_hdr_len = sizeof(struct qeth_hdr); + proto_len = 0; + } + /* re-use the L2 header area for the HW header: */ rc = skb_cow_head(skb, hw_hdr_len - ETH_HLEN); if (rc) @@ -2181,28 +2160,37 @@ static int qeth_l3_xmit_offload(struct qeth_card *card, struct sk_buff *skb, skb_pull(skb, ETH_HLEN); frame_len = skb->len; - push_len = qeth_add_hw_header(card, skb, &hdr, hw_hdr_len, 0, + qeth_l3_fixup_headers(skb); + push_len = qeth_add_hw_header(card, skb, &hdr, hw_hdr_len, proto_len, &elements); if (push_len < 0) return push_len; - if (!push_len) { - /* hdr was added discontiguous from skb->data */ - hd_len = hw_hdr_len; + if (is_tso || !push_len) { + /* HW header needs its own buffer element. */ + hd_len = hw_hdr_len + proto_len; + data_offset = push_len + proto_len; } + memset(hdr, 0, hw_hdr_len); - if (skb->protocol == htons(ETH_P_AF_IUCV)) + if (skb->protocol == htons(ETH_P_AF_IUCV)) { qeth_l3_fill_af_iucv_hdr(hdr, skb, frame_len); - else + } else { qeth_l3_fill_header(card, hdr, skb, ipv, cast_type, frame_len); + if (is_tso) + qeth_l3_fill_tso_ext((struct qeth_hdr_tso *) hdr, + frame_len - proto_len, skb, + proto_len); + } is_sg = skb_is_nonlinear(skb); if (IS_IQD(card)) { - rc = qeth_do_send_packet_fast(queue, skb, hdr, 0, hd_len); + rc = qeth_do_send_packet_fast(queue, skb, hdr, data_offset, + hd_len); } else { /* TODO: drop skb_orphan() once TX completion is fast enough */ skb_orphan(skb); - rc = qeth_do_send_packet(card, queue, skb, hdr, 0, hd_len, - elements); + rc = qeth_do_send_packet(card, queue, skb, hdr, data_offset, + hd_len, elements); } if (!rc) { @@ -2210,6 +2198,10 @@ static int qeth_l3_xmit_offload(struct qeth_card *card, struct sk_buff *skb, card->perf_stats.buf_elements_sent += elements; if (is_sg) card->perf_stats.sg_skbs_sent++; + if (is_tso) { + card->perf_stats.large_send_bytes += frame_len; + card->perf_stats.large_send_cnt++; + } } } else { if (!push_len) @@ -2224,118 +2216,6 @@ static int qeth_l3_xmit_offload(struct qeth_card *card, struct sk_buff *skb, return rc; } -static int qeth_l3_xmit(struct qeth_card *card, struct sk_buff *skb, - struct qeth_qdio_out_q *queue, int ipv, int cast_type) -{ - int elements, len, rc; - __be16 *tag; - struct qeth_hdr *hdr = NULL; - int hdr_elements = 0; - struct sk_buff *new_skb = NULL; - int tx_bytes = skb->len; - unsigned int hd_len; - bool use_tso, is_sg; - - /* Ignore segment size from skb_is_gso(), 1 page is always used. */ - use_tso = skb_is_gso(skb) && - (skb_shinfo(skb)->gso_type & SKB_GSO_TCPV4); - - /* create a clone with writeable headroom */ - new_skb = skb_realloc_headroom(skb, sizeof(struct qeth_hdr_tso) + - VLAN_HLEN); - if (!new_skb) - return -ENOMEM; - - if (ipv == 4) { - skb_pull(new_skb, ETH_HLEN); - } else if (skb_vlan_tag_present(new_skb)) { - skb_push(new_skb, VLAN_HLEN); - skb_copy_to_linear_data(new_skb, new_skb->data + 4, 4); - skb_copy_to_linear_data_offset(new_skb, 4, - new_skb->data + 8, 4); - skb_copy_to_linear_data_offset(new_skb, 8, - new_skb->data + 12, 4); - tag = (__be16 *)(new_skb->data + 12); - *tag = cpu_to_be16(ETH_P_8021Q); - *(tag + 1) = cpu_to_be16(skb_vlan_tag_get(new_skb)); - } - - /* fix hardware limitation: as long as we do not have sbal - * chaining we can not send long frag lists - */ - if ((use_tso && !qeth_l3_get_elements_no_tso(card, new_skb, 1)) || - (!use_tso && !qeth_get_elements_no(card, new_skb, 0, 0))) { - rc = skb_linearize(new_skb); - - if (card->options.performance_stats) { - if (rc) - card->perf_stats.tx_linfail++; - else - card->perf_stats.tx_lin++; - } - if (rc) - goto out; - } - - if (use_tso) { - hdr = skb_push(new_skb, sizeof(struct qeth_hdr_tso)); - memset(hdr, 0, sizeof(struct qeth_hdr_tso)); - qeth_l3_fill_header(card, hdr, new_skb, ipv, cast_type, - new_skb->len - sizeof(struct qeth_hdr_tso)); - qeth_tso_fill_header(card, hdr, new_skb); - hdr_elements++; - } else { - hdr = skb_push(new_skb, sizeof(struct qeth_hdr)); - qeth_l3_fill_header(card, hdr, new_skb, ipv, cast_type, - new_skb->len - sizeof(struct qeth_hdr)); - } - - elements = use_tso ? - qeth_l3_get_elements_no_tso(card, new_skb, hdr_elements) : - qeth_get_elements_no(card, new_skb, hdr_elements, 0); - if (!elements) { - rc = -E2BIG; - goto out; - } - elements += hdr_elements; - - if (use_tso) { - hd_len = sizeof(struct qeth_hdr_tso) + - ip_hdrlen(new_skb) + tcp_hdrlen(new_skb); - len = hd_len; - } else { - hd_len = 0; - len = sizeof(struct qeth_hdr_layer3); - } - - if (qeth_hdr_chk_and_bounce(new_skb, &hdr, len)) { - rc = -EINVAL; - goto out; - } - - is_sg = skb_is_nonlinear(new_skb); - rc = qeth_do_send_packet(card, queue, new_skb, hdr, hd_len, hd_len, - elements); -out: - if (!rc) { - if (new_skb != skb) - dev_kfree_skb_any(skb); - if (card->options.performance_stats) { - card->perf_stats.buf_elements_sent += elements; - if (is_sg) - card->perf_stats.sg_skbs_sent++; - if (use_tso) { - card->perf_stats.large_send_bytes += tx_bytes; - card->perf_stats.large_send_cnt++; - } - } - } else { - if (new_skb != skb) - dev_kfree_skb_any(new_skb); - } - return rc; -} - static netdev_tx_t qeth_l3_hard_start_xmit(struct sk_buff *skb, struct net_device *dev) { @@ -2371,10 +2251,11 @@ static netdev_tx_t qeth_l3_hard_start_xmit(struct sk_buff *skb, } netif_stop_queue(dev); - if (IS_IQD(card) || (!skb_is_gso(skb) && ipv == 4)) - rc = qeth_l3_xmit_offload(card, skb, queue, ipv, cast_type); - else + if (ipv == 4 || IS_IQD(card)) rc = qeth_l3_xmit(card, skb, queue, ipv, cast_type); + else + rc = qeth_xmit(card, skb, queue, ipv, cast_type, + qeth_l3_fill_header); if (!rc) { card->stats.tx_packets++; @@ -2412,7 +2293,10 @@ static int __qeth_l3_open(struct net_device *dev) if (qdio_stop_irq(card->data.ccwdev, 0) >= 0) { napi_enable(&card->napi); + local_bh_disable(); napi_schedule(&card->napi); + /* kick-start the NAPI softirq: */ + local_bh_enable(); } else rc = -EIO; return rc; @@ -2476,6 +2360,15 @@ qeth_l3_neigh_setup(struct net_device *dev, struct neigh_parms *np) return 0; } +static netdev_features_t qeth_l3_osa_features_check(struct sk_buff *skb, + struct net_device *dev, + netdev_features_t features) +{ + if (qeth_get_ip_version(skb) != 4) + features &= ~NETIF_F_HW_VLAN_CTAG_TX; + return qeth_features_check(skb, dev, features); +} + static const struct net_device_ops qeth_l3_netdev_ops = { .ndo_open = qeth_l3_open, .ndo_stop = qeth_l3_stop, @@ -2496,7 +2389,7 @@ static const struct net_device_ops qeth_l3_osa_netdev_ops = { .ndo_stop = qeth_l3_stop, .ndo_get_stats = qeth_get_stats, .ndo_start_xmit = qeth_l3_hard_start_xmit, - .ndo_features_check = qeth_features_check, + .ndo_features_check = qeth_l3_osa_features_check, .ndo_validate_addr = eth_validate_addr, .ndo_set_rx_mode = qeth_l3_set_rx_mode, .ndo_do_ioctl = qeth_do_ioctl, @@ -2524,6 +2417,11 @@ static int qeth_l3_setup_netdev(struct qeth_card *card) } card->dev->netdev_ops = &qeth_l3_osa_netdev_ops; + card->dev->needed_headroom = sizeof(struct qeth_hdr); + /* allow for de-acceleration of NETIF_F_HW_VLAN_CTAG_TX: */ + card->dev->needed_headroom += VLAN_HLEN; + if (qeth_is_supported(card, IPA_OUTBOUND_TSO)) + card->dev->needed_headroom = sizeof(struct qeth_hdr_tso); /*IPv6 address autoconfiguration stuff*/ qeth_l3_get_unique_id(card); @@ -2545,6 +2443,7 @@ static int qeth_l3_setup_netdev(struct qeth_card *card) } else if (card->info.type == QETH_CARD_TYPE_IQD) { card->dev->flags |= IFF_NOARP; card->dev->netdev_ops = &qeth_l3_netdev_ops; + card->dev->needed_headroom = sizeof(struct qeth_hdr) - ETH_HLEN; rc = qeth_l3_iqd_read_initial_mac(card); if (rc) @@ -2556,7 +2455,6 @@ static int qeth_l3_setup_netdev(struct qeth_card *card) return -ENODEV; card->dev->ethtool_ops = &qeth_l3_ethtool_ops; - card->dev->needed_headroom = sizeof(struct qeth_hdr) - ETH_HLEN; card->dev->features |= NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_CTAG_RX | NETIF_F_HW_VLAN_CTAG_FILTER; diff --git a/drivers/scsi/Kconfig b/drivers/scsi/Kconfig index 8fc851a9e116..7c097006c54d 100644 --- a/drivers/scsi/Kconfig +++ b/drivers/scsi/Kconfig @@ -52,12 +52,12 @@ config SCSI_MQ_DEFAULT default y depends on SCSI ---help--- - This option enables the new blk-mq based I/O path for SCSI - devices by default. With the option the scsi_mod.use_blk_mq - module/boot option defaults to Y, without it to N, but it can - still be overridden either way. + This option enables the blk-mq based I/O path for SCSI devices by + default. With this option the scsi_mod.use_blk_mq module/boot + option defaults to Y, without it to N, but it can still be + overridden either way. - If unsure say N. + If unsure say Y. config SCSI_PROC_FS bool "legacy /proc/scsi/ support" diff --git a/drivers/scsi/aacraid/aacraid.h b/drivers/scsi/aacraid/aacraid.h index 29bf1e60f542..39eb415987fc 100644 --- a/drivers/scsi/aacraid/aacraid.h +++ b/drivers/scsi/aacraid/aacraid.h @@ -1346,7 +1346,7 @@ struct fib { struct aac_hba_map_info { __le32 rmw_nexus; /* nexus for native HBA devices */ u8 devtype; /* device type */ - u8 reset_state; /* 0 - no reset, 1..x - */ + s8 reset_state; /* 0 - no reset, 1..x - */ /* after xth TM LUN reset */ u16 qd_limit; u32 scan_counter; diff --git a/drivers/scsi/bnx2fc/bnx2fc_fcoe.c b/drivers/scsi/bnx2fc/bnx2fc_fcoe.c index f00045813378..27c8d6ba05bb 100644 --- a/drivers/scsi/bnx2fc/bnx2fc_fcoe.c +++ b/drivers/scsi/bnx2fc/bnx2fc_fcoe.c @@ -150,15 +150,11 @@ static void bnx2fc_clean_rx_queue(struct fc_lport *lp) struct fcoe_rcv_info *fr; struct sk_buff_head *list; struct sk_buff *skb, *next; - struct sk_buff *head; bg = &bnx2fc_global; spin_lock_bh(&bg->fcoe_rx_list.lock); list = &bg->fcoe_rx_list; - head = list->next; - for (skb = head; skb != (struct sk_buff *)list; - skb = next) { - next = skb->next; + skb_queue_walk_safe(list, skb, next) { fr = fcoe_dev_from_skb(skb); if (fr->fr_dev == lp) { __skb_unlink(skb, list); diff --git a/drivers/scsi/csiostor/csio_hw.c b/drivers/scsi/csiostor/csio_hw.c index 23d07e9f87d0..e51923886475 100644 --- a/drivers/scsi/csiostor/csio_hw.c +++ b/drivers/scsi/csiostor/csio_hw.c @@ -1602,6 +1602,46 @@ fw_port_cap32_t fwcaps16_to_caps32(fw_port_cap16_t caps16) } /** + * fwcaps32_to_caps16 - convert 32-bit Port Capabilities to 16-bits + * @caps32: a 32-bit Port Capabilities value + * + * Returns the equivalent 16-bit Port Capabilities value. Note that + * not all 32-bit Port Capabilities can be represented in the 16-bit + * Port Capabilities and some fields/values may not make it. + */ +fw_port_cap16_t fwcaps32_to_caps16(fw_port_cap32_t caps32) +{ + fw_port_cap16_t caps16 = 0; + + #define CAP32_TO_CAP16(__cap) \ + do { \ + if (caps32 & FW_PORT_CAP32_##__cap) \ + caps16 |= FW_PORT_CAP_##__cap; \ + } while (0) + + CAP32_TO_CAP16(SPEED_100M); + CAP32_TO_CAP16(SPEED_1G); + CAP32_TO_CAP16(SPEED_10G); + CAP32_TO_CAP16(SPEED_25G); + CAP32_TO_CAP16(SPEED_40G); + CAP32_TO_CAP16(SPEED_100G); + CAP32_TO_CAP16(FC_RX); + CAP32_TO_CAP16(FC_TX); + CAP32_TO_CAP16(802_3_PAUSE); + CAP32_TO_CAP16(802_3_ASM_DIR); + CAP32_TO_CAP16(ANEG); + CAP32_TO_CAP16(FORCE_PAUSE); + CAP32_TO_CAP16(MDIAUTO); + CAP32_TO_CAP16(MDISTRAIGHT); + CAP32_TO_CAP16(FEC_RS); + CAP32_TO_CAP16(FEC_BASER_RS); + + #undef CAP32_TO_CAP16 + + return caps16; +} + +/** * lstatus_to_fwcap - translate old lstatus to 32-bit Port Capabilities * @lstatus: old FW_PORT_ACTION_GET_PORT_INFO lstatus value * @@ -1759,7 +1799,7 @@ csio_enable_ports(struct csio_hw *hw) val = 1; csio_mb_params(hw, mbp, CSIO_MB_DEFAULT_TMO, - hw->pfn, 0, 1, ¶m, &val, false, + hw->pfn, 0, 1, ¶m, &val, true, NULL); if (csio_mb_issue(hw, mbp)) { @@ -1769,16 +1809,9 @@ csio_enable_ports(struct csio_hw *hw) return -EINVAL; } - csio_mb_process_read_params_rsp(hw, mbp, &retval, 1, - &val); - if (retval != FW_SUCCESS) { - csio_err(hw, "FW_PARAMS_CMD(r) port:%d failed: 0x%x\n", - portid, retval); - mempool_free(mbp, hw->mb_mempool); - return -EINVAL; - } - - fw_caps = val; + csio_mb_process_read_params_rsp(hw, mbp, &retval, + 0, NULL); + fw_caps = retval ? FW_CAPS16 : FW_CAPS32; } /* Read PORT information */ @@ -2364,8 +2397,8 @@ bye: } /* - * Returns -EINVAL if attempts to flash the firmware failed - * else returns 0, + * Returns -EINVAL if attempts to flash the firmware failed, + * -ENOMEM if memory allocation failed else returns 0, * if flashing was not attempted because the card had the * latest firmware ECANCELED is returned */ @@ -2393,6 +2426,13 @@ csio_hw_flash_fw(struct csio_hw *hw, int *reset) return -EINVAL; } + /* allocate memory to read the header of the firmware on the + * card + */ + card_fw = kmalloc(sizeof(*card_fw), GFP_KERNEL); + if (!card_fw) + return -ENOMEM; + if (csio_is_t5(pci_dev->device & CSIO_HW_CHIP_MASK)) fw_bin_file = FW_FNAME_T5; else @@ -2406,11 +2446,6 @@ csio_hw_flash_fw(struct csio_hw *hw, int *reset) fw_size = fw->size; } - /* allocate memory to read the header of the firmware on the - * card - */ - card_fw = kmalloc(sizeof(*card_fw), GFP_KERNEL); - /* upgrade FW logic */ ret = csio_hw_prep_fw(hw, fw_info, fw_data, fw_size, card_fw, hw->fw_state, reset); diff --git a/drivers/scsi/csiostor/csio_hw.h b/drivers/scsi/csiostor/csio_hw.h index 9e73ef771eb7..e351af6e7c81 100644 --- a/drivers/scsi/csiostor/csio_hw.h +++ b/drivers/scsi/csiostor/csio_hw.h @@ -639,6 +639,7 @@ int csio_handle_intr_status(struct csio_hw *, unsigned int, fw_port_cap32_t fwcap_to_fwspeed(fw_port_cap32_t acaps); fw_port_cap32_t fwcaps16_to_caps32(fw_port_cap16_t caps16); +fw_port_cap16_t fwcaps32_to_caps16(fw_port_cap32_t caps32); fw_port_cap32_t lstatus_to_fwcap(u32 lstatus); int csio_hw_start(struct csio_hw *); diff --git a/drivers/scsi/csiostor/csio_mb.c b/drivers/scsi/csiostor/csio_mb.c index c026417269c3..6f13673d6aa0 100644 --- a/drivers/scsi/csiostor/csio_mb.c +++ b/drivers/scsi/csiostor/csio_mb.c @@ -368,7 +368,7 @@ csio_mb_port(struct csio_hw *hw, struct csio_mb *mbp, uint32_t tmo, FW_CMD_LEN16_V(sizeof(*cmdp) / 16)); if (fw_caps == FW_CAPS16) - cmdp->u.l1cfg.rcap = cpu_to_be32(fc); + cmdp->u.l1cfg.rcap = cpu_to_be32(fwcaps32_to_caps16(fc)); else cmdp->u.l1cfg32.rcap32 = cpu_to_be32(fc); } @@ -395,8 +395,8 @@ csio_mb_process_read_port_rsp(struct csio_hw *hw, struct csio_mb *mbp, *pcaps = fwcaps16_to_caps32(ntohs(rsp->u.info.pcap)); *acaps = fwcaps16_to_caps32(ntohs(rsp->u.info.acap)); } else { - *pcaps = ntohs(rsp->u.info32.pcaps32); - *acaps = ntohs(rsp->u.info32.acaps32); + *pcaps = be32_to_cpu(rsp->u.info32.pcaps32); + *acaps = be32_to_cpu(rsp->u.info32.acaps32); } } } diff --git a/drivers/scsi/cxgbi/libcxgbi.c b/drivers/scsi/cxgbi/libcxgbi.c index 3f3af5e74a07..75f876409fb9 100644 --- a/drivers/scsi/cxgbi/libcxgbi.c +++ b/drivers/scsi/cxgbi/libcxgbi.c @@ -784,7 +784,8 @@ cxgbi_check_route6(struct sockaddr *dst_addr, int ifindex) csk->mtu = mtu; csk->dst = dst; - if (ipv6_addr_any(&rt->rt6i_prefsrc.addr)) { + rt6_get_prefsrc(rt, &pref_saddr); + if (ipv6_addr_any(&pref_saddr)) { struct inet6_dev *idev = ip6_dst_idev((struct dst_entry *)rt); err = ipv6_dev_get_saddr(&init_net, idev ? idev->dev : NULL, @@ -794,8 +795,6 @@ cxgbi_check_route6(struct sockaddr *dst_addr, int ifindex) &daddr6->sin6_addr); goto rel_rt; } - } else { - pref_saddr = rt->rt6i_prefsrc.addr; } csk->csk_family = AF_INET6; diff --git a/drivers/scsi/hosts.c b/drivers/scsi/hosts.c index f02dcc875a09..ea4b0bb0c1cd 100644 --- a/drivers/scsi/hosts.c +++ b/drivers/scsi/hosts.c @@ -563,35 +563,13 @@ struct Scsi_Host *scsi_host_get(struct Scsi_Host *shost) } EXPORT_SYMBOL(scsi_host_get); -struct scsi_host_mq_in_flight { - int cnt; -}; - -static void scsi_host_check_in_flight(struct request *rq, void *data, - bool reserved) -{ - struct scsi_host_mq_in_flight *in_flight = data; - - if (blk_mq_request_started(rq)) - in_flight->cnt++; -} - /** * scsi_host_busy - Return the host busy counter * @shost: Pointer to Scsi_Host to inc. **/ int scsi_host_busy(struct Scsi_Host *shost) { - struct scsi_host_mq_in_flight in_flight = { - .cnt = 0, - }; - - if (!shost->use_blk_mq) - return atomic_read(&shost->host_busy); - - blk_mq_tagset_busy_iter(&shost->tag_set, scsi_host_check_in_flight, - &in_flight); - return in_flight.cnt; + return atomic_read(&shost->host_busy); } EXPORT_SYMBOL(scsi_host_busy); diff --git a/drivers/scsi/hpsa.c b/drivers/scsi/hpsa.c index 58bb70b886d7..c120929d4ffe 100644 --- a/drivers/scsi/hpsa.c +++ b/drivers/scsi/hpsa.c @@ -976,7 +976,7 @@ static struct scsi_host_template hpsa_driver_template = { #endif .sdev_attrs = hpsa_sdev_attrs, .shost_attrs = hpsa_shost_attrs, - .max_sectors = 1024, + .max_sectors = 2048, .no_write_same = 1, }; diff --git a/drivers/scsi/ibmvscsi_tgt/ibmvscsi_tgt.c b/drivers/scsi/ibmvscsi_tgt/ibmvscsi_tgt.c index fac377320158..f42a619198c4 100644 --- a/drivers/scsi/ibmvscsi_tgt/ibmvscsi_tgt.c +++ b/drivers/scsi/ibmvscsi_tgt/ibmvscsi_tgt.c @@ -3474,11 +3474,10 @@ static int ibmvscsis_probe(struct vio_dev *vdev, vscsi->dds.window[LOCAL].liobn, vscsi->dds.window[REMOTE].liobn); - strcpy(vscsi->eye, "VSCSI "); - strncat(vscsi->eye, vdev->name, MAX_EYE); + snprintf(vscsi->eye, sizeof(vscsi->eye), "VSCSI %s", vdev->name); vscsi->dds.unit_id = vdev->unit_address; - strncpy(vscsi->dds.partition_name, partition_name, + strscpy(vscsi->dds.partition_name, partition_name, sizeof(vscsi->dds.partition_name)); vscsi->dds.partition_num = partition_number; diff --git a/drivers/scsi/ipr.c b/drivers/scsi/ipr.c index f2ec80b0ffc0..271990bc065b 100644 --- a/drivers/scsi/ipr.c +++ b/drivers/scsi/ipr.c @@ -3335,6 +3335,65 @@ static void ipr_release_dump(struct kref *kref) LEAVE; } +static void ipr_add_remove_thread(struct work_struct *work) +{ + unsigned long lock_flags; + struct ipr_resource_entry *res; + struct scsi_device *sdev; + struct ipr_ioa_cfg *ioa_cfg = + container_of(work, struct ipr_ioa_cfg, scsi_add_work_q); + u8 bus, target, lun; + int did_work; + + ENTER; + spin_lock_irqsave(ioa_cfg->host->host_lock, lock_flags); + +restart: + do { + did_work = 0; + if (!ioa_cfg->hrrq[IPR_INIT_HRRQ].allow_cmds) { + spin_unlock_irqrestore(ioa_cfg->host->host_lock, lock_flags); + return; + } + + list_for_each_entry(res, &ioa_cfg->used_res_q, queue) { + if (res->del_from_ml && res->sdev) { + did_work = 1; + sdev = res->sdev; + if (!scsi_device_get(sdev)) { + if (!res->add_to_ml) + list_move_tail(&res->queue, &ioa_cfg->free_res_q); + else + res->del_from_ml = 0; + spin_unlock_irqrestore(ioa_cfg->host->host_lock, lock_flags); + scsi_remove_device(sdev); + scsi_device_put(sdev); + spin_lock_irqsave(ioa_cfg->host->host_lock, lock_flags); + } + break; + } + } + } while (did_work); + + list_for_each_entry(res, &ioa_cfg->used_res_q, queue) { + if (res->add_to_ml) { + bus = res->bus; + target = res->target; + lun = res->lun; + res->add_to_ml = 0; + spin_unlock_irqrestore(ioa_cfg->host->host_lock, lock_flags); + scsi_add_device(ioa_cfg->host, bus, target, lun); + spin_lock_irqsave(ioa_cfg->host->host_lock, lock_flags); + goto restart; + } + } + + ioa_cfg->scan_done = 1; + spin_unlock_irqrestore(ioa_cfg->host->host_lock, lock_flags); + kobject_uevent(&ioa_cfg->host->shost_dev.kobj, KOBJ_CHANGE); + LEAVE; +} + /** * ipr_worker_thread - Worker thread * @work: ioa config struct @@ -3349,13 +3408,9 @@ static void ipr_release_dump(struct kref *kref) static void ipr_worker_thread(struct work_struct *work) { unsigned long lock_flags; - struct ipr_resource_entry *res; - struct scsi_device *sdev; struct ipr_dump *dump; struct ipr_ioa_cfg *ioa_cfg = container_of(work, struct ipr_ioa_cfg, work_q); - u8 bus, target, lun; - int did_work; ENTER; spin_lock_irqsave(ioa_cfg->host->host_lock, lock_flags); @@ -3393,49 +3448,9 @@ static void ipr_worker_thread(struct work_struct *work) return; } -restart: - do { - did_work = 0; - if (!ioa_cfg->hrrq[IPR_INIT_HRRQ].allow_cmds) { - spin_unlock_irqrestore(ioa_cfg->host->host_lock, lock_flags); - return; - } + schedule_work(&ioa_cfg->scsi_add_work_q); - list_for_each_entry(res, &ioa_cfg->used_res_q, queue) { - if (res->del_from_ml && res->sdev) { - did_work = 1; - sdev = res->sdev; - if (!scsi_device_get(sdev)) { - if (!res->add_to_ml) - list_move_tail(&res->queue, &ioa_cfg->free_res_q); - else - res->del_from_ml = 0; - spin_unlock_irqrestore(ioa_cfg->host->host_lock, lock_flags); - scsi_remove_device(sdev); - scsi_device_put(sdev); - spin_lock_irqsave(ioa_cfg->host->host_lock, lock_flags); - } - break; - } - } - } while (did_work); - - list_for_each_entry(res, &ioa_cfg->used_res_q, queue) { - if (res->add_to_ml) { - bus = res->bus; - target = res->target; - lun = res->lun; - res->add_to_ml = 0; - spin_unlock_irqrestore(ioa_cfg->host->host_lock, lock_flags); - scsi_add_device(ioa_cfg->host, bus, target, lun); - spin_lock_irqsave(ioa_cfg->host->host_lock, lock_flags); - goto restart; - } - } - - ioa_cfg->scan_done = 1; spin_unlock_irqrestore(ioa_cfg->host->host_lock, lock_flags); - kobject_uevent(&ioa_cfg->host->shost_dev.kobj, KOBJ_CHANGE); LEAVE; } @@ -9933,6 +9948,7 @@ static void ipr_init_ioa_cfg(struct ipr_ioa_cfg *ioa_cfg, INIT_LIST_HEAD(&ioa_cfg->free_res_q); INIT_LIST_HEAD(&ioa_cfg->used_res_q); INIT_WORK(&ioa_cfg->work_q, ipr_worker_thread); + INIT_WORK(&ioa_cfg->scsi_add_work_q, ipr_add_remove_thread); init_waitqueue_head(&ioa_cfg->reset_wait_q); init_waitqueue_head(&ioa_cfg->msi_wait_q); init_waitqueue_head(&ioa_cfg->eeh_wait_q); diff --git a/drivers/scsi/ipr.h b/drivers/scsi/ipr.h index 68afbbde54d3..f6baa2351313 100644 --- a/drivers/scsi/ipr.h +++ b/drivers/scsi/ipr.h @@ -1575,6 +1575,7 @@ struct ipr_ioa_cfg { u8 saved_mode_page_len; struct work_struct work_q; + struct work_struct scsi_add_work_q; struct workqueue_struct *reset_work_q; wait_queue_head_t reset_wait_q; diff --git a/drivers/scsi/lpfc/lpfc.h b/drivers/scsi/lpfc/lpfc.h index e0d0da5f43d6..43732e8d1347 100644 --- a/drivers/scsi/lpfc/lpfc.h +++ b/drivers/scsi/lpfc/lpfc.h @@ -672,7 +672,7 @@ struct lpfc_hba { #define LS_NPIV_FAB_SUPPORTED 0x2 /* Fabric supports NPIV */ #define LS_IGNORE_ERATT 0x4 /* intr handler should ignore ERATT */ #define LS_MDS_LINK_DOWN 0x8 /* MDS Diagnostics Link Down */ -#define LS_MDS_LOOPBACK 0x16 /* MDS Diagnostics Link Up (Loopback) */ +#define LS_MDS_LOOPBACK 0x10 /* MDS Diagnostics Link Up (Loopback) */ uint32_t hba_flag; /* hba generic flags */ #define HBA_ERATT_HANDLED 0x1 /* This flag is set when eratt handled */ diff --git a/drivers/scsi/lpfc/lpfc_attr.c b/drivers/scsi/lpfc/lpfc_attr.c index 5a25553415f8..1a6ed9b0a249 100644 --- a/drivers/scsi/lpfc/lpfc_attr.c +++ b/drivers/scsi/lpfc/lpfc_attr.c @@ -360,12 +360,12 @@ lpfc_nvme_info_show(struct device *dev, struct device_attribute *attr, goto buffer_done; list_for_each_entry(ndlp, &vport->fc_nodes, nlp_listp) { + nrport = NULL; + spin_lock(&vport->phba->hbalock); rport = lpfc_ndlp_get_nrport(ndlp); - if (!rport) - continue; - - /* local short-hand pointer. */ - nrport = rport->remoteport; + if (rport) + nrport = rport->remoteport; + spin_unlock(&vport->phba->hbalock); if (!nrport) continue; @@ -3386,6 +3386,7 @@ lpfc_update_rport_devloss_tmo(struct lpfc_vport *vport) struct lpfc_nodelist *ndlp; #if (IS_ENABLED(CONFIG_NVME_FC)) struct lpfc_nvme_rport *rport; + struct nvme_fc_remote_port *remoteport = NULL; #endif shost = lpfc_shost_from_vport(vport); @@ -3396,8 +3397,12 @@ lpfc_update_rport_devloss_tmo(struct lpfc_vport *vport) if (ndlp->rport) ndlp->rport->dev_loss_tmo = vport->cfg_devloss_tmo; #if (IS_ENABLED(CONFIG_NVME_FC)) + spin_lock(&vport->phba->hbalock); rport = lpfc_ndlp_get_nrport(ndlp); if (rport) + remoteport = rport->remoteport; + spin_unlock(&vport->phba->hbalock); + if (remoteport) nvme_fc_set_remoteport_devloss(rport->remoteport, vport->cfg_devloss_tmo); #endif @@ -5122,16 +5127,16 @@ LPFC_ATTR_R(enable_SmartSAN, 0, 0, 1, "Enable SmartSAN functionality"); /* # lpfc_fdmi_on: Controls FDMI support. -# 0 No FDMI support (default) -# 1 Traditional FDMI support +# 0 No FDMI support +# 1 Traditional FDMI support (default) # Traditional FDMI support means the driver will assume FDMI-2 support; # however, if that fails, it will fallback to FDMI-1. # If lpfc_enable_SmartSAN is set to 1, the driver ignores lpfc_fdmi_on. # If lpfc_enable_SmartSAN is set 0, the driver uses the current value of # lpfc_fdmi_on. -# Value range [0,1]. Default value is 0. +# Value range [0,1]. Default value is 1. */ -LPFC_ATTR_R(fdmi_on, 0, 0, 1, "Enable FDMI support"); +LPFC_ATTR_R(fdmi_on, 1, 0, 1, "Enable FDMI support"); /* # Specifies the maximum number of ELS cmds we can have outstanding (for diff --git a/drivers/scsi/lpfc/lpfc_debugfs.c b/drivers/scsi/lpfc/lpfc_debugfs.c index 9df0c051349f..aec5b10a8c85 100644 --- a/drivers/scsi/lpfc/lpfc_debugfs.c +++ b/drivers/scsi/lpfc/lpfc_debugfs.c @@ -551,7 +551,7 @@ lpfc_debugfs_nodelist_data(struct lpfc_vport *vport, char *buf, int size) unsigned char *statep; struct nvme_fc_local_port *localport; struct lpfc_nvmet_tgtport *tgtp; - struct nvme_fc_remote_port *nrport; + struct nvme_fc_remote_port *nrport = NULL; struct lpfc_nvme_rport *rport; cnt = (LPFC_NODELIST_SIZE / LPFC_NODELIST_ENTRY_SIZE); @@ -696,11 +696,11 @@ lpfc_debugfs_nodelist_data(struct lpfc_vport *vport, char *buf, int size) len += snprintf(buf + len, size - len, "\tRport List:\n"); list_for_each_entry(ndlp, &vport->fc_nodes, nlp_listp) { /* local short-hand pointer. */ + spin_lock(&phba->hbalock); rport = lpfc_ndlp_get_nrport(ndlp); - if (!rport) - continue; - - nrport = rport->remoteport; + if (rport) + nrport = rport->remoteport; + spin_unlock(&phba->hbalock); if (!nrport) continue; diff --git a/drivers/scsi/lpfc/lpfc_nvme.c b/drivers/scsi/lpfc/lpfc_nvme.c index 028462e5994d..918ae18ef8a8 100644 --- a/drivers/scsi/lpfc/lpfc_nvme.c +++ b/drivers/scsi/lpfc/lpfc_nvme.c @@ -2725,7 +2725,9 @@ lpfc_nvme_register_port(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp) rpinfo.port_name = wwn_to_u64(ndlp->nlp_portname.u.wwn); rpinfo.node_name = wwn_to_u64(ndlp->nlp_nodename.u.wwn); + spin_lock_irq(&vport->phba->hbalock); oldrport = lpfc_ndlp_get_nrport(ndlp); + spin_unlock_irq(&vport->phba->hbalock); if (!oldrport) lpfc_nlp_get(ndlp); @@ -2840,7 +2842,7 @@ lpfc_nvme_unregister_port(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp) struct nvme_fc_local_port *localport; struct lpfc_nvme_lport *lport; struct lpfc_nvme_rport *rport; - struct nvme_fc_remote_port *remoteport; + struct nvme_fc_remote_port *remoteport = NULL; localport = vport->localport; @@ -2854,11 +2856,14 @@ lpfc_nvme_unregister_port(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp) if (!lport) goto input_err; + spin_lock_irq(&vport->phba->hbalock); rport = lpfc_ndlp_get_nrport(ndlp); - if (!rport) + if (rport) + remoteport = rport->remoteport; + spin_unlock_irq(&vport->phba->hbalock); + if (!remoteport) goto input_err; - remoteport = rport->remoteport; lpfc_printf_vlog(vport, KERN_INFO, LOG_NVME_DISC, "6033 Unreg nvme remoteport %p, portname x%llx, " "port_id x%06x, portstate x%x port type x%x\n", diff --git a/drivers/scsi/qedi/qedi.h b/drivers/scsi/qedi/qedi.h index fc3babc15fa3..a6f96b35e971 100644 --- a/drivers/scsi/qedi/qedi.h +++ b/drivers/scsi/qedi/qedi.h @@ -77,6 +77,11 @@ enum qedi_nvm_tgts { QEDI_NVM_TGT_SEC, }; +struct qedi_nvm_iscsi_image { + struct nvm_iscsi_cfg iscsi_cfg; + u32 crc; +}; + struct qedi_uio_ctrl { /* meta data */ u32 uio_hsi_version; @@ -294,7 +299,7 @@ struct qedi_ctx { void *bdq_pbl_list; dma_addr_t bdq_pbl_list_dma; u8 bdq_pbl_list_num_entries; - struct nvm_iscsi_cfg *iscsi_cfg; + struct qedi_nvm_iscsi_image *iscsi_image; dma_addr_t nvm_buf_dma; void __iomem *bdq_primary_prod; void __iomem *bdq_secondary_prod; diff --git a/drivers/scsi/qedi/qedi_main.c b/drivers/scsi/qedi/qedi_main.c index aa96bccb5a96..cc8e64dc65ad 100644 --- a/drivers/scsi/qedi/qedi_main.c +++ b/drivers/scsi/qedi/qedi_main.c @@ -1346,23 +1346,26 @@ exit_setup_int: static void qedi_free_nvm_iscsi_cfg(struct qedi_ctx *qedi) { - if (qedi->iscsi_cfg) + if (qedi->iscsi_image) dma_free_coherent(&qedi->pdev->dev, - sizeof(struct nvm_iscsi_cfg), - qedi->iscsi_cfg, qedi->nvm_buf_dma); + sizeof(struct qedi_nvm_iscsi_image), + qedi->iscsi_image, qedi->nvm_buf_dma); } static int qedi_alloc_nvm_iscsi_cfg(struct qedi_ctx *qedi) { - qedi->iscsi_cfg = dma_zalloc_coherent(&qedi->pdev->dev, - sizeof(struct nvm_iscsi_cfg), - &qedi->nvm_buf_dma, GFP_KERNEL); - if (!qedi->iscsi_cfg) { + struct qedi_nvm_iscsi_image nvm_image; + + qedi->iscsi_image = dma_zalloc_coherent(&qedi->pdev->dev, + sizeof(nvm_image), + &qedi->nvm_buf_dma, + GFP_KERNEL); + if (!qedi->iscsi_image) { QEDI_ERR(&qedi->dbg_ctx, "Could not allocate NVM BUF.\n"); return -ENOMEM; } QEDI_INFO(&qedi->dbg_ctx, QEDI_LOG_INFO, - "NVM BUF addr=0x%p dma=0x%llx.\n", qedi->iscsi_cfg, + "NVM BUF addr=0x%p dma=0x%llx.\n", qedi->iscsi_image, qedi->nvm_buf_dma); return 0; @@ -1905,7 +1908,7 @@ qedi_get_nvram_block(struct qedi_ctx *qedi) struct nvm_iscsi_block *block; pf = qedi->dev_info.common.abs_pf_id; - block = &qedi->iscsi_cfg->block[0]; + block = &qedi->iscsi_image->iscsi_cfg.block[0]; for (i = 0; i < NUM_OF_ISCSI_PF_SUPPORTED; i++, block++) { flags = ((block->id) & NVM_ISCSI_CFG_BLK_CTRL_FLAG_MASK) >> NVM_ISCSI_CFG_BLK_CTRL_FLAG_OFFSET; @@ -2194,15 +2197,14 @@ static void qedi_boot_release(void *data) static int qedi_get_boot_info(struct qedi_ctx *qedi) { int ret = 1; - u16 len; - - len = sizeof(struct nvm_iscsi_cfg); + struct qedi_nvm_iscsi_image nvm_image; QEDI_INFO(&qedi->dbg_ctx, QEDI_LOG_INFO, "Get NVM iSCSI CFG image\n"); ret = qedi_ops->common->nvm_get_image(qedi->cdev, QED_NVM_IMAGE_ISCSI_CFG, - (char *)qedi->iscsi_cfg, len); + (char *)qedi->iscsi_image, + sizeof(nvm_image)); if (ret) QEDI_ERR(&qedi->dbg_ctx, "Could not get NVM image. ret = %d\n", ret); diff --git a/drivers/scsi/qla2xxx/qla_target.h b/drivers/scsi/qla2xxx/qla_target.h index fecf96f0225c..199d3ba1916d 100644 --- a/drivers/scsi/qla2xxx/qla_target.h +++ b/drivers/scsi/qla2xxx/qla_target.h @@ -374,8 +374,8 @@ struct atio_from_isp { static inline int fcpcmd_is_corrupted(struct atio *atio) { if (atio->entry_type == ATIO_TYPE7 && - (le16_to_cpu(atio->attr_n_length & FCP_CMD_LENGTH_MASK) < - FCP_CMD_LENGTH_MIN)) + ((le16_to_cpu(atio->attr_n_length) & FCP_CMD_LENGTH_MASK) < + FCP_CMD_LENGTH_MIN)) return 1; else return 0; diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c index 0adfb3bce0fd..eb97d2dd3651 100644 --- a/drivers/scsi/scsi_lib.c +++ b/drivers/scsi/scsi_lib.c @@ -345,8 +345,7 @@ static void scsi_dec_host_busy(struct Scsi_Host *shost) unsigned long flags; rcu_read_lock(); - if (!shost->use_blk_mq) - atomic_dec(&shost->host_busy); + atomic_dec(&shost->host_busy); if (unlikely(scsi_host_in_recovery(shost))) { spin_lock_irqsave(shost->host_lock, flags); if (shost->host_failed || shost->host_eh_scheduled) @@ -445,12 +444,7 @@ static inline bool scsi_target_is_busy(struct scsi_target *starget) static inline bool scsi_host_is_busy(struct Scsi_Host *shost) { - /* - * blk-mq can handle host queue busy efficiently via host-wide driver - * tag allocation - */ - - if (!shost->use_blk_mq && shost->can_queue > 0 && + if (shost->can_queue > 0 && atomic_read(&shost->host_busy) >= shost->can_queue) return true; if (atomic_read(&shost->host_blocked) > 0) @@ -1606,10 +1600,7 @@ static inline int scsi_host_queue_ready(struct request_queue *q, if (scsi_host_in_recovery(shost)) return 0; - if (!shost->use_blk_mq) - busy = atomic_inc_return(&shost->host_busy) - 1; - else - busy = 0; + busy = atomic_inc_return(&shost->host_busy) - 1; if (atomic_read(&shost->host_blocked) > 0) { if (busy) goto starved; @@ -1625,7 +1616,7 @@ static inline int scsi_host_queue_ready(struct request_queue *q, "unblocking host at zero depth\n")); } - if (!shost->use_blk_mq && shost->can_queue > 0 && busy >= shost->can_queue) + if (shost->can_queue > 0 && busy >= shost->can_queue) goto starved; if (shost->host_self_blocked) goto starved; @@ -1711,9 +1702,7 @@ static void scsi_kill_request(struct request *req, struct request_queue *q) * with the locks as normal issue path does. */ atomic_inc(&sdev->device_busy); - - if (!shost->use_blk_mq) - atomic_inc(&shost->host_busy); + atomic_inc(&shost->host_busy); if (starget->can_queue > 0) atomic_inc(&starget->target_busy); diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c index b79b366a94f7..4a57ffecc7e6 100644 --- a/drivers/scsi/sd.c +++ b/drivers/scsi/sd.c @@ -1276,7 +1276,8 @@ static int sd_init_command(struct scsi_cmnd *cmd) case REQ_OP_ZONE_RESET: return sd_zbc_setup_reset_cmnd(cmd); default: - BUG(); + WARN_ON_ONCE(1); + return BLKPREP_KILL; } } @@ -2959,6 +2960,9 @@ static void sd_read_block_characteristics(struct scsi_disk *sdkp) if (rot == 1) { blk_queue_flag_set(QUEUE_FLAG_NONROT, q); blk_queue_flag_clear(QUEUE_FLAG_ADD_RANDOM, q); + } else { + blk_queue_flag_clear(QUEUE_FLAG_NONROT, q); + blk_queue_flag_set(QUEUE_FLAG_ADD_RANDOM, q); } if (sdkp->device->type == TYPE_ZBC) { diff --git a/drivers/scsi/ufs/ufshcd.c b/drivers/scsi/ufs/ufshcd.c index 9d5d2ca7fc4f..c55f38ec391c 100644 --- a/drivers/scsi/ufs/ufshcd.c +++ b/drivers/scsi/ufs/ufshcd.c @@ -7940,6 +7940,13 @@ int ufshcd_alloc_host(struct device *dev, struct ufs_hba **hba_handle) err = -ENOMEM; goto out_error; } + + /* + * Do not use blk-mq at this time because blk-mq does not support + * runtime pm. + */ + host->use_blk_mq = false; + hba = shost_priv(host); hba->host = host; hba->dev = dev; diff --git a/drivers/soundwire/stream.c b/drivers/soundwire/stream.c index 4b5e250e8615..e5c7e1ef6318 100644 --- a/drivers/soundwire/stream.c +++ b/drivers/soundwire/stream.c @@ -899,9 +899,10 @@ static void sdw_release_master_stream(struct sdw_stream_runtime *stream) struct sdw_master_runtime *m_rt = stream->m_rt; struct sdw_slave_runtime *s_rt, *_s_rt; - list_for_each_entry_safe(s_rt, _s_rt, - &m_rt->slave_rt_list, m_rt_node) - sdw_stream_remove_slave(s_rt->slave, stream); + list_for_each_entry_safe(s_rt, _s_rt, &m_rt->slave_rt_list, m_rt_node) { + sdw_slave_port_release(s_rt->slave->bus, s_rt->slave, stream); + sdw_release_slave_stream(s_rt->slave, stream); + } list_del(&m_rt->bus_node); } @@ -1112,7 +1113,7 @@ int sdw_stream_add_master(struct sdw_bus *bus, "Master runtime config failed for stream:%s", stream->name); ret = -ENOMEM; - goto error; + goto unlock; } ret = sdw_config_stream(bus->dev, stream, stream_config, false); @@ -1123,11 +1124,11 @@ int sdw_stream_add_master(struct sdw_bus *bus, if (ret) goto stream_error; - stream->state = SDW_STREAM_CONFIGURED; + goto unlock; stream_error: sdw_release_master_stream(stream); -error: +unlock: mutex_unlock(&bus->bus_lock); return ret; } @@ -1141,6 +1142,10 @@ EXPORT_SYMBOL(sdw_stream_add_master); * @stream: SoundWire stream * @port_config: Port configuration for audio stream * @num_ports: Number of ports + * + * It is expected that Slave is added before adding Master + * to the Stream. + * */ int sdw_stream_add_slave(struct sdw_slave *slave, struct sdw_stream_config *stream_config, @@ -1186,6 +1191,12 @@ int sdw_stream_add_slave(struct sdw_slave *slave, if (ret) goto stream_error; + /* + * Change stream state to CONFIGURED on first Slave add. + * Bus is not aware of number of Slave(s) in a stream at this + * point so cannot depend on all Slave(s) to be added in order to + * change stream state to CONFIGURED. + */ stream->state = SDW_STREAM_CONFIGURED; goto error; diff --git a/drivers/spi/spi-fsl-dspi.c b/drivers/spi/spi-fsl-dspi.c index 7cb3ab0a35a0..3082e72e4f6c 100644 --- a/drivers/spi/spi-fsl-dspi.c +++ b/drivers/spi/spi-fsl-dspi.c @@ -30,7 +30,11 @@ #define DRIVER_NAME "fsl-dspi" +#ifdef CONFIG_M5441x +#define DSPI_FIFO_SIZE 16 +#else #define DSPI_FIFO_SIZE 4 +#endif #define DSPI_DMA_BUFSIZE (DSPI_FIFO_SIZE * 1024) #define SPI_MCR 0x00 @@ -623,9 +627,11 @@ static void dspi_tcfq_read(struct fsl_dspi *dspi) static void dspi_eoq_write(struct fsl_dspi *dspi) { int fifo_size = DSPI_FIFO_SIZE; + u16 xfer_cmd = dspi->tx_cmd; /* Fill TX FIFO with as many transfers as possible */ while (dspi->len && fifo_size--) { + dspi->tx_cmd = xfer_cmd; /* Request EOQF for last transfer in FIFO */ if (dspi->len == dspi->bytes_per_word || fifo_size == 0) dspi->tx_cmd |= SPI_PUSHR_CMD_EOQ; diff --git a/drivers/spi/spi.c b/drivers/spi/spi.c index ec395a6baf9c..9da0bc5a036c 100644 --- a/drivers/spi/spi.c +++ b/drivers/spi/spi.c @@ -2143,8 +2143,17 @@ int spi_register_controller(struct spi_controller *ctlr) */ if (ctlr->num_chipselect == 0) return -EINVAL; - /* allocate dynamic bus number using Linux idr */ - if ((ctlr->bus_num < 0) && ctlr->dev.of_node) { + if (ctlr->bus_num >= 0) { + /* devices with a fixed bus num must check-in with the num */ + mutex_lock(&board_lock); + id = idr_alloc(&spi_master_idr, ctlr, ctlr->bus_num, + ctlr->bus_num + 1, GFP_KERNEL); + mutex_unlock(&board_lock); + if (WARN(id < 0, "couldn't get idr")) + return id == -ENOSPC ? -EBUSY : id; + ctlr->bus_num = id; + } else if (ctlr->dev.of_node) { + /* allocate dynamic bus number using Linux idr */ id = of_alias_get_id(ctlr->dev.of_node, "spi"); if (id >= 0) { ctlr->bus_num = id; diff --git a/drivers/staging/erofs/Kconfig b/drivers/staging/erofs/Kconfig index 96f614934df1..663b755bf2fb 100644 --- a/drivers/staging/erofs/Kconfig +++ b/drivers/staging/erofs/Kconfig @@ -2,7 +2,7 @@ config EROFS_FS tristate "EROFS filesystem support" - depends on BROKEN + depends on BLOCK help EROFS(Enhanced Read-Only File System) is a lightweight read-only file system with modern designs (eg. page-sized diff --git a/drivers/staging/erofs/super.c b/drivers/staging/erofs/super.c index 1aec509c805f..2df9768edac9 100644 --- a/drivers/staging/erofs/super.c +++ b/drivers/staging/erofs/super.c @@ -340,7 +340,7 @@ static int erofs_read_super(struct super_block *sb, goto err_sbread; sb->s_magic = EROFS_SUPER_MAGIC; - sb->s_flags |= MS_RDONLY | MS_NOATIME; + sb->s_flags |= SB_RDONLY | SB_NOATIME; sb->s_maxbytes = MAX_LFS_FILESIZE; sb->s_time_gran = 1; @@ -627,7 +627,7 @@ static int erofs_remount(struct super_block *sb, int *flags, char *data) { BUG_ON(!sb_rdonly(sb)); - *flags |= MS_RDONLY; + *flags |= SB_RDONLY; return 0; } diff --git a/drivers/staging/fbtft/TODO b/drivers/staging/fbtft/TODO index 7e64c7e438f0..a9f4802bb6be 100644 --- a/drivers/staging/fbtft/TODO +++ b/drivers/staging/fbtft/TODO @@ -2,3 +2,7 @@ GPIO descriptor API in <linux/gpio/consumer.h> and look up GPIO lines from device tree, ACPI or board files, board files should use <linux/gpio/machine.h> + +* convert all these over to drm_simple_display_pipe and submit for inclusion + into the DRM subsystem under drivers/gpu/drm - fbdev doesn't take any new + drivers anymore. diff --git a/drivers/staging/gasket/TODO b/drivers/staging/gasket/TODO index 6ff8e01b04cc..5b1865f8af2d 100644 --- a/drivers/staging/gasket/TODO +++ b/drivers/staging/gasket/TODO @@ -1,9 +1,22 @@ This is a list of things that need to be done to get this driver out of the staging directory. + +- Implement the gasket framework's functionality through UIO instead of + introducing a new user-space drivers framework that is quite similar. + + UIO provides the necessary bits to implement user-space drivers. Meanwhile + the gasket APIs adds some extra conveniences like PCI BAR mapping, and + MSI interrupts. Add these features to the UIO subsystem, then re-implement + the Apex driver as a basic UIO driver instead (include/linux/uio_driver.h) + - Document sysfs files with Documentation/ABI/ entries. + - Use misc interface instead of major number for driver version description. + - Add descriptions of module_param's + - apex_get_status() should actually check status. + - "drivers" should never be dealing with "raw" sysfs calls or mess around with kobjects at all. The driver core should handle all of this for you automaically. There should not be a need for raw attribute macros. diff --git a/drivers/staging/media/mt9t031/Kconfig b/drivers/staging/media/mt9t031/Kconfig index f48e06a03cdb..9a58aaf72edd 100644 --- a/drivers/staging/media/mt9t031/Kconfig +++ b/drivers/staging/media/mt9t031/Kconfig @@ -1,9 +1,3 @@ -config SOC_CAMERA_IMX074 - tristate "imx074 support (DEPRECATED)" - depends on SOC_CAMERA && I2C - help - This driver supports IMX074 cameras from Sony - config SOC_CAMERA_MT9T031 tristate "mt9t031 support (DEPRECATED)" depends on SOC_CAMERA && I2C diff --git a/drivers/staging/mt7621-eth/mdio.c b/drivers/staging/mt7621-eth/mdio.c index 7ad0c4141205..2c6e1800a3fd 100644 --- a/drivers/staging/mt7621-eth/mdio.c +++ b/drivers/staging/mt7621-eth/mdio.c @@ -112,7 +112,7 @@ static void phy_init(struct mtk_eth *eth, struct mtk_mac *mac, phy->autoneg = AUTONEG_ENABLE; phy->speed = 0; phy->duplex = 0; - phy->supported &= PHY_BASIC_FEATURES; + phy_set_max_speed(phy, SPEED_100); phy->advertising = phy->supported | ADVERTISED_Autoneg; phy_start_aneg(phy); diff --git a/drivers/staging/rtl8192e/rtl8192e/rtl_core.c b/drivers/staging/rtl8192e/rtl8192e/rtl_core.c index d2605158546b..96f265eee007 100644 --- a/drivers/staging/rtl8192e/rtl8192e/rtl_core.c +++ b/drivers/staging/rtl8192e/rtl8192e/rtl_core.c @@ -1149,7 +1149,7 @@ static enum reset_type _rtl92e_tx_check_stuck(struct net_device *dev) if (skb_queue_len(&ring->queue) == 0) { continue; } else { - skb = (&ring->queue)->next; + skb = __skb_peek(&ring->queue); tcb_desc = (struct cb_desc *)(skb->cb + MAX_DEV_ADDR_SIZE); tcb_desc->nStuckCount++; diff --git a/drivers/staging/vboxvideo/vbox_drv.c b/drivers/staging/vboxvideo/vbox_drv.c index da92c493f157..69cc508af1bc 100644 --- a/drivers/staging/vboxvideo/vbox_drv.c +++ b/drivers/staging/vboxvideo/vbox_drv.c @@ -59,6 +59,11 @@ static int vbox_pci_probe(struct pci_dev *pdev, const struct pci_device_id *ent) ret = PTR_ERR(dev); goto err_drv_alloc; } + + ret = pci_enable_device(pdev); + if (ret) + goto err_pci_enable; + dev->pdev = pdev; pci_set_drvdata(pdev, dev); @@ -75,6 +80,8 @@ static int vbox_pci_probe(struct pci_dev *pdev, const struct pci_device_id *ent) err_drv_dev_register: vbox_driver_unload(dev); err_vbox_driver_load: + pci_disable_device(pdev); + err_pci_enable: drm_dev_put(dev); err_drv_alloc: return ret; diff --git a/drivers/staging/vboxvideo/vbox_mode.c b/drivers/staging/vboxvideo/vbox_mode.c index a83eac8668d0..79836c8fb909 100644 --- a/drivers/staging/vboxvideo/vbox_mode.c +++ b/drivers/staging/vboxvideo/vbox_mode.c @@ -323,6 +323,11 @@ static int vbox_crtc_page_flip(struct drm_crtc *crtc, if (rc) return rc; + mutex_lock(&vbox->hw_mutex); + vbox_set_view(crtc); + vbox_do_modeset(crtc, &crtc->mode); + mutex_unlock(&vbox->hw_mutex); + spin_lock_irqsave(&drm->event_lock, flags); if (event) diff --git a/drivers/staging/wilc1000/Makefile b/drivers/staging/wilc1000/Makefile index f7b07c0b5ce2..ee7e26b886a5 100644 --- a/drivers/staging/wilc1000/Makefile +++ b/drivers/staging/wilc1000/Makefile @@ -1,4 +1,5 @@ # SPDX-License-Identifier: GPL-2.0 +obj-$(CONFIG_WILC1000) += wilc1000.o ccflags-y += -DFIRMWARE_1002=\"atmel/wilc1002_firmware.bin\" \ -DFIRMWARE_1003=\"atmel/wilc1003_firmware.bin\" @@ -11,9 +12,7 @@ wilc1000-objs := wilc_wfi_cfgoperations.o linux_wlan.o linux_mon.o \ wilc_wlan.o obj-$(CONFIG_WILC1000_SDIO) += wilc1000-sdio.o -wilc1000-sdio-objs += $(wilc1000-objs) wilc1000-sdio-objs += wilc_sdio.o obj-$(CONFIG_WILC1000_SPI) += wilc1000-spi.o -wilc1000-spi-objs += $(wilc1000-objs) wilc1000-spi-objs += wilc_spi.o diff --git a/drivers/staging/wilc1000/linux_wlan.c b/drivers/staging/wilc1000/linux_wlan.c index 01cf4bd2e192..3b8d237decbf 100644 --- a/drivers/staging/wilc1000/linux_wlan.c +++ b/drivers/staging/wilc1000/linux_wlan.c @@ -1038,8 +1038,8 @@ void wilc_netdev_cleanup(struct wilc *wilc) } kfree(wilc); - wilc_debugfs_remove(); } +EXPORT_SYMBOL_GPL(wilc_netdev_cleanup); static const struct net_device_ops wilc_netdev_ops = { .ndo_init = mac_init_fn, @@ -1062,7 +1062,6 @@ int wilc_netdev_init(struct wilc **wilc, struct device *dev, int io_type, if (!wl) return -ENOMEM; - wilc_debugfs_init(); *wilc = wl; wl->io_type = io_type; wl->hif_func = ops; @@ -1124,3 +1123,6 @@ int wilc_netdev_init(struct wilc **wilc, struct device *dev, int io_type, return 0; } +EXPORT_SYMBOL_GPL(wilc_netdev_init); + +MODULE_LICENSE("GPL"); diff --git a/drivers/staging/wilc1000/wilc_debugfs.c b/drivers/staging/wilc1000/wilc_debugfs.c index edc72876458d..8001df66b8c2 100644 --- a/drivers/staging/wilc1000/wilc_debugfs.c +++ b/drivers/staging/wilc1000/wilc_debugfs.c @@ -19,6 +19,7 @@ static struct dentry *wilc_dir; #define DBG_LEVEL_ALL (DEBUG | INFO | WRN | ERR) static atomic_t WILC_DEBUG_LEVEL = ATOMIC_INIT(ERR); +EXPORT_SYMBOL_GPL(WILC_DEBUG_LEVEL); static ssize_t wilc_debug_level_read(struct file *file, char __user *userbuf, size_t count, loff_t *ppos) @@ -87,7 +88,7 @@ static struct wilc_debugfs_info_t debugfs_info[] = { }, }; -int wilc_debugfs_init(void) +static int __init wilc_debugfs_init(void) { int i; struct wilc_debugfs_info_t *info; @@ -103,10 +104,12 @@ int wilc_debugfs_init(void) } return 0; } +module_init(wilc_debugfs_init); -void wilc_debugfs_remove(void) +static void __exit wilc_debugfs_remove(void) { debugfs_remove_recursive(wilc_dir); } +module_exit(wilc_debugfs_remove); #endif diff --git a/drivers/staging/wilc1000/wilc_wlan.c b/drivers/staging/wilc1000/wilc_wlan.c index 6787b6e9f124..8b184aa30d25 100644 --- a/drivers/staging/wilc1000/wilc_wlan.c +++ b/drivers/staging/wilc1000/wilc_wlan.c @@ -417,6 +417,7 @@ void chip_allow_sleep(struct wilc *wilc) wilc->hif_func->hif_write_reg(wilc, 0xf0, reg & ~BIT(0)); wilc->hif_func->hif_write_reg(wilc, 0xfa, 0); } +EXPORT_SYMBOL_GPL(chip_allow_sleep); void chip_wakeup(struct wilc *wilc) { @@ -471,6 +472,7 @@ void chip_wakeup(struct wilc *wilc) } chip_ps_state = CHIP_WAKEDUP; } +EXPORT_SYMBOL_GPL(chip_wakeup); void wilc_chip_sleep_manually(struct wilc *wilc) { @@ -484,6 +486,7 @@ void wilc_chip_sleep_manually(struct wilc *wilc) chip_ps_state = CHIP_SLEEPING_MANUAL; release_bus(wilc, RELEASE_ONLY); } +EXPORT_SYMBOL_GPL(wilc_chip_sleep_manually); void host_wakeup_notify(struct wilc *wilc) { @@ -491,6 +494,7 @@ void host_wakeup_notify(struct wilc *wilc) wilc->hif_func->hif_write_reg(wilc, 0x10b0, 1); release_bus(wilc, RELEASE_ONLY); } +EXPORT_SYMBOL_GPL(host_wakeup_notify); void host_sleep_notify(struct wilc *wilc) { @@ -498,6 +502,7 @@ void host_sleep_notify(struct wilc *wilc) wilc->hif_func->hif_write_reg(wilc, 0x10ac, 1); release_bus(wilc, RELEASE_ONLY); } +EXPORT_SYMBOL_GPL(host_sleep_notify); int wilc_wlan_handle_txq(struct net_device *dev, u32 *txq_count) { @@ -871,6 +876,7 @@ void wilc_handle_isr(struct wilc *wilc) release_bus(wilc, RELEASE_ALLOW_SLEEP); } +EXPORT_SYMBOL_GPL(wilc_handle_isr); int wilc_wlan_firmware_download(struct wilc *wilc, const u8 *buffer, u32 buffer_size) diff --git a/drivers/staging/wilc1000/wilc_wlan_if.h b/drivers/staging/wilc1000/wilc_wlan_if.h index 00d13b153f80..b81a73b9bd67 100644 --- a/drivers/staging/wilc1000/wilc_wlan_if.h +++ b/drivers/staging/wilc1000/wilc_wlan_if.h @@ -831,6 +831,4 @@ struct wilc; int wilc_wlan_init(struct net_device *dev); u32 wilc_get_chipid(struct wilc *wilc, bool update); -int wilc_debugfs_init(void); -void wilc_debugfs_remove(void); #endif diff --git a/drivers/target/iscsi/cxgbit/cxgbit_ddp.c b/drivers/target/iscsi/cxgbit/cxgbit_ddp.c index 768cce0ccb80..76a262674c8d 100644 --- a/drivers/target/iscsi/cxgbit/cxgbit_ddp.c +++ b/drivers/target/iscsi/cxgbit/cxgbit_ddp.c @@ -207,8 +207,8 @@ cxgbit_ddp_reserve(struct cxgbit_sock *csk, struct cxgbi_task_tag_info *ttinfo, ret = dma_map_sg(&ppm->pdev->dev, sgl, sgcnt, DMA_FROM_DEVICE); sgl->offset = sg_offset; if (!ret) { - pr_info("%s: 0x%x, xfer %u, sgl %u dma mapping err.\n", - __func__, 0, xferlen, sgcnt); + pr_debug("%s: 0x%x, xfer %u, sgl %u dma mapping err.\n", + __func__, 0, xferlen, sgcnt); goto rel_ppods; } @@ -250,8 +250,8 @@ cxgbit_get_r2t_ttt(struct iscsi_conn *conn, struct iscsi_cmd *cmd, ret = cxgbit_ddp_reserve(csk, ttinfo, cmd->se_cmd.data_length); if (ret < 0) { - pr_info("csk 0x%p, cmd 0x%p, xfer len %u, sgcnt %u no ddp.\n", - csk, cmd, cmd->se_cmd.data_length, ttinfo->nents); + pr_debug("csk 0x%p, cmd 0x%p, xfer len %u, sgcnt %u no ddp.\n", + csk, cmd, cmd->se_cmd.data_length, ttinfo->nents); ttinfo->sgl = NULL; ttinfo->nents = 0; diff --git a/drivers/target/iscsi/iscsi_target.c b/drivers/target/iscsi/iscsi_target.c index 94bad43c41ff..cc756a123fd8 100644 --- a/drivers/target/iscsi/iscsi_target.c +++ b/drivers/target/iscsi/iscsi_target.c @@ -1416,7 +1416,8 @@ static void iscsit_do_crypto_hash_buf(struct ahash_request *hash, sg_init_table(sg, ARRAY_SIZE(sg)); sg_set_buf(sg, buf, payload_length); - sg_set_buf(sg + 1, pad_bytes, padding); + if (padding) + sg_set_buf(sg + 1, pad_bytes, padding); ahash_request_set_crypt(hash, sg, data_crc, payload_length + padding); @@ -3910,10 +3911,14 @@ static bool iscsi_target_check_conn_state(struct iscsi_conn *conn) static void iscsit_get_rx_pdu(struct iscsi_conn *conn) { int ret; - u8 buffer[ISCSI_HDR_LEN], opcode; + u8 *buffer, opcode; u32 checksum = 0, digest = 0; struct kvec iov; + buffer = kcalloc(ISCSI_HDR_LEN, sizeof(*buffer), GFP_KERNEL); + if (!buffer) + return; + while (!kthread_should_stop()) { /* * Ensure that both TX and RX per connection kthreads @@ -3921,7 +3926,6 @@ static void iscsit_get_rx_pdu(struct iscsi_conn *conn) */ iscsit_thread_check_cpumask(conn, current, 0); - memset(buffer, 0, ISCSI_HDR_LEN); memset(&iov, 0, sizeof(struct kvec)); iov.iov_base = buffer; @@ -3930,7 +3934,7 @@ static void iscsit_get_rx_pdu(struct iscsi_conn *conn) ret = rx_data(conn, &iov, 1, ISCSI_HDR_LEN); if (ret != ISCSI_HDR_LEN) { iscsit_rx_thread_wait_for_tcp(conn); - return; + break; } if (conn->conn_ops->HeaderDigest) { @@ -3940,7 +3944,7 @@ static void iscsit_get_rx_pdu(struct iscsi_conn *conn) ret = rx_data(conn, &iov, 1, ISCSI_CRC_LEN); if (ret != ISCSI_CRC_LEN) { iscsit_rx_thread_wait_for_tcp(conn); - return; + break; } iscsit_do_crypto_hash_buf(conn->conn_rx_hash, buffer, @@ -3964,7 +3968,7 @@ static void iscsit_get_rx_pdu(struct iscsi_conn *conn) } if (conn->conn_state == TARG_CONN_STATE_IN_LOGOUT) - return; + break; opcode = buffer[0] & ISCSI_OPCODE_MASK; @@ -3975,13 +3979,15 @@ static void iscsit_get_rx_pdu(struct iscsi_conn *conn) " while in Discovery Session, rejecting.\n", opcode); iscsit_add_reject(conn, ISCSI_REASON_PROTOCOL_ERROR, buffer); - return; + break; } ret = iscsi_target_rx_opcode(conn, buffer); if (ret < 0) - return; + break; } + + kfree(buffer); } int iscsi_target_rx_thread(void *arg) @@ -4208,22 +4214,15 @@ int iscsit_close_connection( crypto_free_ahash(tfm); } - free_cpumask_var(conn->conn_cpumask); - - kfree(conn->conn_ops); - conn->conn_ops = NULL; - if (conn->sock) sock_release(conn->sock); if (conn->conn_transport->iscsit_free_conn) conn->conn_transport->iscsit_free_conn(conn); - iscsit_put_transport(conn->conn_transport); - pr_debug("Moving to TARG_CONN_STATE_FREE.\n"); conn->conn_state = TARG_CONN_STATE_FREE; - kfree(conn); + iscsit_free_conn(conn); spin_lock_bh(&sess->conn_lock); atomic_dec(&sess->nconn); diff --git a/drivers/target/iscsi/iscsi_target_auth.c b/drivers/target/iscsi/iscsi_target_auth.c index 9518ffd8b8ba..4e680d753941 100644 --- a/drivers/target/iscsi/iscsi_target_auth.c +++ b/drivers/target/iscsi/iscsi_target_auth.c @@ -26,27 +26,6 @@ #include "iscsi_target_nego.h" #include "iscsi_target_auth.h" -static int chap_string_to_hex(unsigned char *dst, unsigned char *src, int len) -{ - int j = DIV_ROUND_UP(len, 2), rc; - - rc = hex2bin(dst, src, j); - if (rc < 0) - pr_debug("CHAP string contains non hex digit symbols\n"); - - dst[j] = '\0'; - return j; -} - -static void chap_binaryhex_to_asciihex(char *dst, char *src, int src_len) -{ - int i; - - for (i = 0; i < src_len; i++) { - sprintf(&dst[i*2], "%02x", (int) src[i] & 0xff); - } -} - static int chap_gen_challenge( struct iscsi_conn *conn, int caller, @@ -62,7 +41,7 @@ static int chap_gen_challenge( ret = get_random_bytes_wait(chap->challenge, CHAP_CHALLENGE_LENGTH); if (unlikely(ret)) return ret; - chap_binaryhex_to_asciihex(challenge_asciihex, chap->challenge, + bin2hex(challenge_asciihex, chap->challenge, CHAP_CHALLENGE_LENGTH); /* * Set CHAP_C, and copy the generated challenge into c_str. @@ -248,9 +227,16 @@ static int chap_server_compute_md5( pr_err("Could not find CHAP_R.\n"); goto out; } + if (strlen(chap_r) != MD5_SIGNATURE_SIZE * 2) { + pr_err("Malformed CHAP_R\n"); + goto out; + } + if (hex2bin(client_digest, chap_r, MD5_SIGNATURE_SIZE) < 0) { + pr_err("Malformed CHAP_R\n"); + goto out; + } pr_debug("[server] Got CHAP_R=%s\n", chap_r); - chap_string_to_hex(client_digest, chap_r, strlen(chap_r)); tfm = crypto_alloc_shash("md5", 0, 0); if (IS_ERR(tfm)) { @@ -294,7 +280,7 @@ static int chap_server_compute_md5( goto out; } - chap_binaryhex_to_asciihex(response, server_digest, MD5_SIGNATURE_SIZE); + bin2hex(response, server_digest, MD5_SIGNATURE_SIZE); pr_debug("[server] MD5 Server Digest: %s\n", response); if (memcmp(server_digest, client_digest, MD5_SIGNATURE_SIZE) != 0) { @@ -349,9 +335,7 @@ static int chap_server_compute_md5( pr_err("Could not find CHAP_C.\n"); goto out; } - pr_debug("[server] Got CHAP_C=%s\n", challenge); - challenge_len = chap_string_to_hex(challenge_binhex, challenge, - strlen(challenge)); + challenge_len = DIV_ROUND_UP(strlen(challenge), 2); if (!challenge_len) { pr_err("Unable to convert incoming challenge\n"); goto out; @@ -360,6 +344,11 @@ static int chap_server_compute_md5( pr_err("CHAP_C exceeds maximum binary size of 1024 bytes\n"); goto out; } + if (hex2bin(challenge_binhex, challenge, challenge_len) < 0) { + pr_err("Malformed CHAP_C\n"); + goto out; + } + pr_debug("[server] Got CHAP_C=%s\n", challenge); /* * During mutual authentication, the CHAP_C generated by the * initiator must not match the original CHAP_C generated by @@ -413,7 +402,7 @@ static int chap_server_compute_md5( /* * Convert response from binary hex to ascii hext. */ - chap_binaryhex_to_asciihex(response, digest, MD5_SIGNATURE_SIZE); + bin2hex(response, digest, MD5_SIGNATURE_SIZE); *nr_out_len += sprintf(nr_out_ptr + *nr_out_len, "CHAP_R=0x%s", response); *nr_out_len += 1; diff --git a/drivers/target/iscsi/iscsi_target_login.c b/drivers/target/iscsi/iscsi_target_login.c index 9e74f8bc2963..bb90c80ff388 100644 --- a/drivers/target/iscsi/iscsi_target_login.c +++ b/drivers/target/iscsi/iscsi_target_login.c @@ -67,45 +67,10 @@ static struct iscsi_login *iscsi_login_init_conn(struct iscsi_conn *conn) goto out_req_buf; } - conn->conn_ops = kzalloc(sizeof(struct iscsi_conn_ops), GFP_KERNEL); - if (!conn->conn_ops) { - pr_err("Unable to allocate memory for" - " struct iscsi_conn_ops.\n"); - goto out_rsp_buf; - } - - init_waitqueue_head(&conn->queues_wq); - INIT_LIST_HEAD(&conn->conn_list); - INIT_LIST_HEAD(&conn->conn_cmd_list); - INIT_LIST_HEAD(&conn->immed_queue_list); - INIT_LIST_HEAD(&conn->response_queue_list); - init_completion(&conn->conn_post_wait_comp); - init_completion(&conn->conn_wait_comp); - init_completion(&conn->conn_wait_rcfr_comp); - init_completion(&conn->conn_waiting_on_uc_comp); - init_completion(&conn->conn_logout_comp); - init_completion(&conn->rx_half_close_comp); - init_completion(&conn->tx_half_close_comp); - init_completion(&conn->rx_login_comp); - spin_lock_init(&conn->cmd_lock); - spin_lock_init(&conn->conn_usage_lock); - spin_lock_init(&conn->immed_queue_lock); - spin_lock_init(&conn->nopin_timer_lock); - spin_lock_init(&conn->response_queue_lock); - spin_lock_init(&conn->state_lock); - - if (!zalloc_cpumask_var(&conn->conn_cpumask, GFP_KERNEL)) { - pr_err("Unable to allocate conn->conn_cpumask\n"); - goto out_conn_ops; - } conn->conn_login = login; return login; -out_conn_ops: - kfree(conn->conn_ops); -out_rsp_buf: - kfree(login->rsp_buf); out_req_buf: kfree(login->req_buf); out_login: @@ -310,11 +275,9 @@ static int iscsi_login_zero_tsih_s1( return -ENOMEM; } - ret = iscsi_login_set_conn_values(sess, conn, pdu->cid); - if (unlikely(ret)) { - kfree(sess); - return ret; - } + if (iscsi_login_set_conn_values(sess, conn, pdu->cid)) + goto free_sess; + sess->init_task_tag = pdu->itt; memcpy(&sess->isid, pdu->isid, 6); sess->exp_cmd_sn = be32_to_cpu(pdu->cmdsn); @@ -1149,6 +1112,75 @@ iscsit_conn_set_transport(struct iscsi_conn *conn, struct iscsit_transport *t) return 0; } +static struct iscsi_conn *iscsit_alloc_conn(struct iscsi_np *np) +{ + struct iscsi_conn *conn; + + conn = kzalloc(sizeof(struct iscsi_conn), GFP_KERNEL); + if (!conn) { + pr_err("Could not allocate memory for new connection\n"); + return NULL; + } + pr_debug("Moving to TARG_CONN_STATE_FREE.\n"); + conn->conn_state = TARG_CONN_STATE_FREE; + + init_waitqueue_head(&conn->queues_wq); + INIT_LIST_HEAD(&conn->conn_list); + INIT_LIST_HEAD(&conn->conn_cmd_list); + INIT_LIST_HEAD(&conn->immed_queue_list); + INIT_LIST_HEAD(&conn->response_queue_list); + init_completion(&conn->conn_post_wait_comp); + init_completion(&conn->conn_wait_comp); + init_completion(&conn->conn_wait_rcfr_comp); + init_completion(&conn->conn_waiting_on_uc_comp); + init_completion(&conn->conn_logout_comp); + init_completion(&conn->rx_half_close_comp); + init_completion(&conn->tx_half_close_comp); + init_completion(&conn->rx_login_comp); + spin_lock_init(&conn->cmd_lock); + spin_lock_init(&conn->conn_usage_lock); + spin_lock_init(&conn->immed_queue_lock); + spin_lock_init(&conn->nopin_timer_lock); + spin_lock_init(&conn->response_queue_lock); + spin_lock_init(&conn->state_lock); + + timer_setup(&conn->nopin_response_timer, + iscsit_handle_nopin_response_timeout, 0); + timer_setup(&conn->nopin_timer, iscsit_handle_nopin_timeout, 0); + + if (iscsit_conn_set_transport(conn, np->np_transport) < 0) + goto free_conn; + + conn->conn_ops = kzalloc(sizeof(struct iscsi_conn_ops), GFP_KERNEL); + if (!conn->conn_ops) { + pr_err("Unable to allocate memory for struct iscsi_conn_ops.\n"); + goto put_transport; + } + + if (!zalloc_cpumask_var(&conn->conn_cpumask, GFP_KERNEL)) { + pr_err("Unable to allocate conn->conn_cpumask\n"); + goto free_mask; + } + + return conn; + +free_mask: + free_cpumask_var(conn->conn_cpumask); +put_transport: + iscsit_put_transport(conn->conn_transport); +free_conn: + kfree(conn); + return NULL; +} + +void iscsit_free_conn(struct iscsi_conn *conn) +{ + free_cpumask_var(conn->conn_cpumask); + kfree(conn->conn_ops); + iscsit_put_transport(conn->conn_transport); + kfree(conn); +} + void iscsi_target_login_sess_out(struct iscsi_conn *conn, struct iscsi_np *np, bool zero_tsih, bool new_sess) { @@ -1198,10 +1230,6 @@ old_sess_out: crypto_free_ahash(tfm); } - free_cpumask_var(conn->conn_cpumask); - - kfree(conn->conn_ops); - if (conn->param_list) { iscsi_release_param_list(conn->param_list); conn->param_list = NULL; @@ -1219,8 +1247,7 @@ old_sess_out: if (conn->conn_transport->iscsit_free_conn) conn->conn_transport->iscsit_free_conn(conn); - iscsit_put_transport(conn->conn_transport); - kfree(conn); + iscsit_free_conn(conn); } static int __iscsi_target_login_thread(struct iscsi_np *np) @@ -1250,31 +1277,16 @@ static int __iscsi_target_login_thread(struct iscsi_np *np) } spin_unlock_bh(&np->np_thread_lock); - conn = kzalloc(sizeof(struct iscsi_conn), GFP_KERNEL); + conn = iscsit_alloc_conn(np); if (!conn) { - pr_err("Could not allocate memory for" - " new connection\n"); /* Get another socket */ return 1; } - pr_debug("Moving to TARG_CONN_STATE_FREE.\n"); - conn->conn_state = TARG_CONN_STATE_FREE; - - timer_setup(&conn->nopin_response_timer, - iscsit_handle_nopin_response_timeout, 0); - timer_setup(&conn->nopin_timer, iscsit_handle_nopin_timeout, 0); - - if (iscsit_conn_set_transport(conn, np->np_transport) < 0) { - kfree(conn); - return 1; - } rc = np->np_transport->iscsit_accept_np(np, conn); if (rc == -ENOSYS) { complete(&np->np_restart_comp); - iscsit_put_transport(conn->conn_transport); - kfree(conn); - conn = NULL; + iscsit_free_conn(conn); goto exit; } else if (rc < 0) { spin_lock_bh(&np->np_thread_lock); @@ -1282,17 +1294,13 @@ static int __iscsi_target_login_thread(struct iscsi_np *np) np->np_thread_state = ISCSI_NP_THREAD_ACTIVE; spin_unlock_bh(&np->np_thread_lock); complete(&np->np_restart_comp); - iscsit_put_transport(conn->conn_transport); - kfree(conn); - conn = NULL; + iscsit_free_conn(conn); /* Get another socket */ return 1; } spin_unlock_bh(&np->np_thread_lock); - iscsit_put_transport(conn->conn_transport); - kfree(conn); - conn = NULL; - goto out; + iscsit_free_conn(conn); + return 1; } /* * Perform the remaining iSCSI connection initialization items.. @@ -1442,7 +1450,6 @@ old_sess_out: tpg_np = NULL; } -out: return 1; exit: diff --git a/drivers/target/iscsi/iscsi_target_login.h b/drivers/target/iscsi/iscsi_target_login.h index 74ac3abc44a0..3b8e3639ff5d 100644 --- a/drivers/target/iscsi/iscsi_target_login.h +++ b/drivers/target/iscsi/iscsi_target_login.h @@ -19,7 +19,7 @@ extern int iscsi_target_setup_login_socket(struct iscsi_np *, extern int iscsit_accept_np(struct iscsi_np *, struct iscsi_conn *); extern int iscsit_get_login_rx(struct iscsi_conn *, struct iscsi_login *); extern int iscsit_put_login_tx(struct iscsi_conn *, struct iscsi_login *, u32); -extern void iscsit_free_conn(struct iscsi_np *, struct iscsi_conn *); +extern void iscsit_free_conn(struct iscsi_conn *); extern int iscsit_start_kthreads(struct iscsi_conn *); extern void iscsi_post_login_handler(struct iscsi_np *, struct iscsi_conn *, u8); extern void iscsi_target_login_sess_out(struct iscsi_conn *, struct iscsi_np *, diff --git a/drivers/tty/hvc/hvc_console.c b/drivers/tty/hvc/hvc_console.c index 5414c4a87bea..27284a2dcd2b 100644 --- a/drivers/tty/hvc/hvc_console.c +++ b/drivers/tty/hvc/hvc_console.c @@ -522,6 +522,8 @@ static int hvc_write(struct tty_struct *tty, const unsigned char *buf, int count return -EIO; while (count > 0) { + int ret = 0; + spin_lock_irqsave(&hp->lock, flags); rsize = hp->outbuf_size - hp->n_outbuf; @@ -537,10 +539,13 @@ static int hvc_write(struct tty_struct *tty, const unsigned char *buf, int count } if (hp->n_outbuf > 0) - hvc_push(hp); + ret = hvc_push(hp); spin_unlock_irqrestore(&hp->lock, flags); + if (!ret) + break; + if (count) { if (hp->n_outbuf > 0) hvc_flush(hp); @@ -623,6 +628,15 @@ static int hvc_chars_in_buffer(struct tty_struct *tty) #define MAX_TIMEOUT (2000) static u32 timeout = MIN_TIMEOUT; +/* + * Maximum number of bytes to get from the console driver if hvc_poll is + * called from driver (and can't sleep). Any more than this and we break + * and start polling with khvcd. This value was derived from from an OpenBMC + * console with the OPAL driver that results in about 0.25ms interrupts off + * latency. + */ +#define HVC_ATOMIC_READ_MAX 128 + #define HVC_POLL_READ 0x00000001 #define HVC_POLL_WRITE 0x00000002 @@ -669,8 +683,8 @@ static int __hvc_poll(struct hvc_struct *hp, bool may_sleep) if (!hp->irq_requested) poll_mask |= HVC_POLL_READ; + read_again: /* Read data if any */ - count = tty_buffer_request_room(&hp->port, N_INBUF); /* If flip is full, just reschedule a later read */ @@ -717,9 +731,23 @@ static int __hvc_poll(struct hvc_struct *hp, bool may_sleep) #endif /* CONFIG_MAGIC_SYSRQ */ tty_insert_flip_char(&hp->port, buf[i], 0); } - if (n == count) - poll_mask |= HVC_POLL_READ; - read_total = n; + read_total += n; + + if (may_sleep) { + /* Keep going until the flip is full */ + spin_unlock_irqrestore(&hp->lock, flags); + cond_resched(); + spin_lock_irqsave(&hp->lock, flags); + goto read_again; + } else if (read_total < HVC_ATOMIC_READ_MAX) { + /* Break and defer if it's a large read in atomic */ + goto read_again; + } + + /* + * Latency break, schedule another poll immediately. + */ + poll_mask |= HVC_POLL_READ; out: /* Wakeup write queue if necessary */ diff --git a/drivers/tty/serial/cpm_uart/cpm_uart_core.c b/drivers/tty/serial/cpm_uart/cpm_uart_core.c index 24a5f05e769b..e5389591bb4f 100644 --- a/drivers/tty/serial/cpm_uart/cpm_uart_core.c +++ b/drivers/tty/serial/cpm_uart/cpm_uart_core.c @@ -1054,8 +1054,8 @@ static int poll_wait_key(char *obuf, struct uart_cpm_port *pinfo) /* Get the address of the host memory buffer. */ bdp = pinfo->rx_cur; - while (bdp->cbd_sc & BD_SC_EMPTY) - ; + if (bdp->cbd_sc & BD_SC_EMPTY) + return NO_POLL_CHAR; /* If the buffer address is in the CPM DPRAM, don't * convert it. @@ -1090,7 +1090,11 @@ static int cpm_get_poll_char(struct uart_port *port) poll_chars = 0; } if (poll_chars <= 0) { - poll_chars = poll_wait_key(poll_buf, pinfo); + int ret = poll_wait_key(poll_buf, pinfo); + + if (ret == NO_POLL_CHAR) + return ret; + poll_chars = ret; pollp = poll_buf; } poll_chars--; diff --git a/drivers/tty/serial/fsl_lpuart.c b/drivers/tty/serial/fsl_lpuart.c index 51e47a63d61a..3f8d1274fc85 100644 --- a/drivers/tty/serial/fsl_lpuart.c +++ b/drivers/tty/serial/fsl_lpuart.c @@ -979,7 +979,8 @@ static inline int lpuart_start_rx_dma(struct lpuart_port *sport) struct circ_buf *ring = &sport->rx_ring; int ret, nent; int bits, baud; - struct tty_struct *tty = tty_port_tty_get(&sport->port.state->port); + struct tty_port *port = &sport->port.state->port; + struct tty_struct *tty = port->tty; struct ktermios *termios = &tty->termios; baud = tty_get_baud_rate(tty); diff --git a/drivers/tty/serial/imx.c b/drivers/tty/serial/imx.c index 239c0fa2e981..0f67197a3783 100644 --- a/drivers/tty/serial/imx.c +++ b/drivers/tty/serial/imx.c @@ -2351,6 +2351,14 @@ static int imx_uart_probe(struct platform_device *pdev) ret); return ret; } + + ret = devm_request_irq(&pdev->dev, rtsirq, imx_uart_rtsint, 0, + dev_name(&pdev->dev), sport); + if (ret) { + dev_err(&pdev->dev, "failed to request rts irq: %d\n", + ret); + return ret; + } } else { ret = devm_request_irq(&pdev->dev, rxirq, imx_uart_int, 0, dev_name(&pdev->dev), sport); diff --git a/drivers/tty/serial/mvebu-uart.c b/drivers/tty/serial/mvebu-uart.c index d04b5eeea3c6..170e446a2f62 100644 --- a/drivers/tty/serial/mvebu-uart.c +++ b/drivers/tty/serial/mvebu-uart.c @@ -511,6 +511,7 @@ static void mvebu_uart_set_termios(struct uart_port *port, termios->c_iflag |= old->c_iflag & ~(INPCK | IGNPAR); termios->c_cflag &= CREAD | CBAUD; termios->c_cflag |= old->c_cflag & ~(CREAD | CBAUD); + termios->c_cflag |= CS8; } spin_unlock_irqrestore(&port->lock, flags); diff --git a/drivers/tty/tty_io.c b/drivers/tty/tty_io.c index 32bc3e3fe4d3..5e5da9acaf0a 100644 --- a/drivers/tty/tty_io.c +++ b/drivers/tty/tty_io.c @@ -1255,6 +1255,7 @@ static void tty_driver_remove_tty(struct tty_driver *driver, struct tty_struct * static int tty_reopen(struct tty_struct *tty) { struct tty_driver *driver = tty->driver; + int retval; if (driver->type == TTY_DRIVER_TYPE_PTY && driver->subtype == PTY_TYPE_MASTER) @@ -1268,10 +1269,14 @@ static int tty_reopen(struct tty_struct *tty) tty->count++; - if (!tty->ldisc) - return tty_ldisc_reinit(tty, tty->termios.c_line); + if (tty->ldisc) + return 0; - return 0; + retval = tty_ldisc_reinit(tty, tty->termios.c_line); + if (retval) + tty->count--; + + return retval; } /** diff --git a/drivers/tty/vt/vt_ioctl.c b/drivers/tty/vt/vt_ioctl.c index a78ad10a119b..73cdc0d633dd 100644 --- a/drivers/tty/vt/vt_ioctl.c +++ b/drivers/tty/vt/vt_ioctl.c @@ -32,6 +32,8 @@ #include <asm/io.h> #include <linux/uaccess.h> +#include <linux/nospec.h> + #include <linux/kbd_kern.h> #include <linux/vt_kern.h> #include <linux/kbd_diacr.h> @@ -700,6 +702,8 @@ int vt_ioctl(struct tty_struct *tty, if (vsa.console == 0 || vsa.console > MAX_NR_CONSOLES) ret = -ENXIO; else { + vsa.console = array_index_nospec(vsa.console, + MAX_NR_CONSOLES + 1); vsa.console--; console_lock(); ret = vc_allocate(vsa.console); diff --git a/drivers/usb/class/cdc-acm.c b/drivers/usb/class/cdc-acm.c index 27346d69f393..f9b40a9dc4d3 100644 --- a/drivers/usb/class/cdc-acm.c +++ b/drivers/usb/class/cdc-acm.c @@ -780,20 +780,9 @@ static int acm_tty_write(struct tty_struct *tty, } if (acm->susp_count) { - if (acm->putbuffer) { - /* now to preserve order */ - usb_anchor_urb(acm->putbuffer->urb, &acm->delayed); - acm->putbuffer = NULL; - } usb_anchor_urb(wb->urb, &acm->delayed); spin_unlock_irqrestore(&acm->write_lock, flags); return count; - } else { - if (acm->putbuffer) { - /* at this point there is no good way to handle errors */ - acm_start_wb(acm, acm->putbuffer); - acm->putbuffer = NULL; - } } stat = acm_start_wb(acm, wb); @@ -804,66 +793,6 @@ static int acm_tty_write(struct tty_struct *tty, return count; } -static void acm_tty_flush_chars(struct tty_struct *tty) -{ - struct acm *acm = tty->driver_data; - struct acm_wb *cur; - int err; - unsigned long flags; - - spin_lock_irqsave(&acm->write_lock, flags); - - cur = acm->putbuffer; - if (!cur) /* nothing to do */ - goto out; - - acm->putbuffer = NULL; - err = usb_autopm_get_interface_async(acm->control); - if (err < 0) { - cur->use = 0; - acm->putbuffer = cur; - goto out; - } - - if (acm->susp_count) - usb_anchor_urb(cur->urb, &acm->delayed); - else - acm_start_wb(acm, cur); -out: - spin_unlock_irqrestore(&acm->write_lock, flags); - return; -} - -static int acm_tty_put_char(struct tty_struct *tty, unsigned char ch) -{ - struct acm *acm = tty->driver_data; - struct acm_wb *cur; - int wbn; - unsigned long flags; - -overflow: - cur = acm->putbuffer; - if (!cur) { - spin_lock_irqsave(&acm->write_lock, flags); - wbn = acm_wb_alloc(acm); - if (wbn >= 0) { - cur = &acm->wb[wbn]; - acm->putbuffer = cur; - } - spin_unlock_irqrestore(&acm->write_lock, flags); - if (!cur) - return 0; - } - - if (cur->len == acm->writesize) { - acm_tty_flush_chars(tty); - goto overflow; - } - - cur->buf[cur->len++] = ch; - return 1; -} - static int acm_tty_write_room(struct tty_struct *tty) { struct acm *acm = tty->driver_data; @@ -1987,8 +1916,6 @@ static const struct tty_operations acm_ops = { .cleanup = acm_tty_cleanup, .hangup = acm_tty_hangup, .write = acm_tty_write, - .put_char = acm_tty_put_char, - .flush_chars = acm_tty_flush_chars, .write_room = acm_tty_write_room, .ioctl = acm_tty_ioctl, .throttle = acm_tty_throttle, diff --git a/drivers/usb/class/cdc-acm.h b/drivers/usb/class/cdc-acm.h index eacc116e83da..ca06b20d7af9 100644 --- a/drivers/usb/class/cdc-acm.h +++ b/drivers/usb/class/cdc-acm.h @@ -96,7 +96,6 @@ struct acm { unsigned long read_urbs_free; struct urb *read_urbs[ACM_NR]; struct acm_rb read_buffers[ACM_NR]; - struct acm_wb *putbuffer; /* for acm_tty_put_char() */ int rx_buflimit; spinlock_t read_lock; u8 *notification_buffer; /* to reassemble fragmented notifications */ diff --git a/drivers/usb/common/common.c b/drivers/usb/common/common.c index 50a2362ed3ea..48277bbc15e4 100644 --- a/drivers/usb/common/common.c +++ b/drivers/usb/common/common.c @@ -246,6 +246,31 @@ int of_usb_update_otg_caps(struct device_node *np, } EXPORT_SYMBOL_GPL(of_usb_update_otg_caps); +/** + * usb_of_get_companion_dev - Find the companion device + * @dev: the device pointer to find a companion + * + * Find the companion device from platform bus. + * + * Takes a reference to the returned struct device which needs to be dropped + * after use. + * + * Return: On success, a pointer to the companion device, %NULL on failure. + */ +struct device *usb_of_get_companion_dev(struct device *dev) +{ + struct device_node *node; + struct platform_device *pdev = NULL; + + node = of_parse_phandle(dev->of_node, "companion", 0); + if (node) + pdev = of_find_device_by_node(node); + + of_node_put(node); + + return pdev ? &pdev->dev : NULL; +} +EXPORT_SYMBOL_GPL(usb_of_get_companion_dev); #endif MODULE_LICENSE("GPL"); diff --git a/drivers/usb/common/roles.c b/drivers/usb/common/roles.c index 15cc76e22123..99116af07f1d 100644 --- a/drivers/usb/common/roles.c +++ b/drivers/usb/common/roles.c @@ -109,8 +109,15 @@ static void *usb_role_switch_match(struct device_connection *con, int ep, */ struct usb_role_switch *usb_role_switch_get(struct device *dev) { - return device_connection_find_match(dev, "usb-role-switch", NULL, - usb_role_switch_match); + struct usb_role_switch *sw; + + sw = device_connection_find_match(dev, "usb-role-switch", NULL, + usb_role_switch_match); + + if (!IS_ERR_OR_NULL(sw)) + WARN_ON(!try_module_get(sw->dev.parent->driver->owner)); + + return sw; } EXPORT_SYMBOL_GPL(usb_role_switch_get); @@ -122,8 +129,10 @@ EXPORT_SYMBOL_GPL(usb_role_switch_get); */ void usb_role_switch_put(struct usb_role_switch *sw) { - if (!IS_ERR_OR_NULL(sw)) + if (!IS_ERR_OR_NULL(sw)) { put_device(&sw->dev); + module_put(sw->dev.parent->driver->owner); + } } EXPORT_SYMBOL_GPL(usb_role_switch_put); diff --git a/drivers/usb/core/devio.c b/drivers/usb/core/devio.c index 6ce77b33da61..244417d0dfd1 100644 --- a/drivers/usb/core/devio.c +++ b/drivers/usb/core/devio.c @@ -1434,10 +1434,13 @@ static int proc_do_submiturb(struct usb_dev_state *ps, struct usbdevfs_urb *uurb struct async *as = NULL; struct usb_ctrlrequest *dr = NULL; unsigned int u, totlen, isofrmlen; - int i, ret, is_in, num_sgs = 0, ifnum = -1; + int i, ret, num_sgs = 0, ifnum = -1; int number_of_packets = 0; unsigned int stream_id = 0; void *buf; + bool is_in; + bool allow_short = false; + bool allow_zero = false; unsigned long mask = USBDEVFS_URB_SHORT_NOT_OK | USBDEVFS_URB_BULK_CONTINUATION | USBDEVFS_URB_NO_FSBR | @@ -1471,6 +1474,8 @@ static int proc_do_submiturb(struct usb_dev_state *ps, struct usbdevfs_urb *uurb u = 0; switch (uurb->type) { case USBDEVFS_URB_TYPE_CONTROL: + if (is_in) + allow_short = true; if (!usb_endpoint_xfer_control(&ep->desc)) return -EINVAL; /* min 8 byte setup packet */ @@ -1511,6 +1516,10 @@ static int proc_do_submiturb(struct usb_dev_state *ps, struct usbdevfs_urb *uurb break; case USBDEVFS_URB_TYPE_BULK: + if (!is_in) + allow_zero = true; + else + allow_short = true; switch (usb_endpoint_type(&ep->desc)) { case USB_ENDPOINT_XFER_CONTROL: case USB_ENDPOINT_XFER_ISOC: @@ -1531,6 +1540,10 @@ static int proc_do_submiturb(struct usb_dev_state *ps, struct usbdevfs_urb *uurb if (!usb_endpoint_xfer_int(&ep->desc)) return -EINVAL; interrupt_urb: + if (!is_in) + allow_zero = true; + else + allow_short = true; break; case USBDEVFS_URB_TYPE_ISO: @@ -1676,14 +1689,19 @@ static int proc_do_submiturb(struct usb_dev_state *ps, struct usbdevfs_urb *uurb u = (is_in ? URB_DIR_IN : URB_DIR_OUT); if (uurb->flags & USBDEVFS_URB_ISO_ASAP) u |= URB_ISO_ASAP; - if (uurb->flags & USBDEVFS_URB_SHORT_NOT_OK && is_in) + if (allow_short && uurb->flags & USBDEVFS_URB_SHORT_NOT_OK) u |= URB_SHORT_NOT_OK; - if (uurb->flags & USBDEVFS_URB_ZERO_PACKET) + if (allow_zero && uurb->flags & USBDEVFS_URB_ZERO_PACKET) u |= URB_ZERO_PACKET; if (uurb->flags & USBDEVFS_URB_NO_INTERRUPT) u |= URB_NO_INTERRUPT; as->urb->transfer_flags = u; + if (!allow_short && uurb->flags & USBDEVFS_URB_SHORT_NOT_OK) + dev_warn(&ps->dev->dev, "Requested nonsensical USBDEVFS_URB_SHORT_NOT_OK.\n"); + if (!allow_zero && uurb->flags & USBDEVFS_URB_ZERO_PACKET) + dev_warn(&ps->dev->dev, "Requested nonsensical USBDEVFS_URB_ZERO_PACKET.\n"); + as->urb->transfer_buffer_length = uurb->buffer_length; as->urb->setup_packet = (unsigned char *)dr; dr = NULL; diff --git a/drivers/usb/core/driver.c b/drivers/usb/core/driver.c index e76e95f62f76..a1f225f077cd 100644 --- a/drivers/usb/core/driver.c +++ b/drivers/usb/core/driver.c @@ -512,7 +512,6 @@ int usb_driver_claim_interface(struct usb_driver *driver, struct device *dev; struct usb_device *udev; int retval = 0; - int lpm_disable_error = -ENODEV; if (!iface) return -ENODEV; @@ -533,16 +532,6 @@ int usb_driver_claim_interface(struct usb_driver *driver, iface->condition = USB_INTERFACE_BOUND; - /* See the comment about disabling LPM in usb_probe_interface(). */ - if (driver->disable_hub_initiated_lpm) { - lpm_disable_error = usb_unlocked_disable_lpm(udev); - if (lpm_disable_error) { - dev_err(&iface->dev, "%s Failed to disable LPM for driver %s\n", - __func__, driver->name); - return -ENOMEM; - } - } - /* Claimed interfaces are initially inactive (suspended) and * runtime-PM-enabled, but only if the driver has autosuspend * support. Otherwise they are marked active, to prevent the @@ -561,9 +550,20 @@ int usb_driver_claim_interface(struct usb_driver *driver, if (device_is_registered(dev)) retval = device_bind_driver(dev); - /* Attempt to re-enable USB3 LPM, if the disable was successful. */ - if (!lpm_disable_error) - usb_unlocked_enable_lpm(udev); + if (retval) { + dev->driver = NULL; + usb_set_intfdata(iface, NULL); + iface->needs_remote_wakeup = 0; + iface->condition = USB_INTERFACE_UNBOUND; + + /* + * Unbound interfaces are always runtime-PM-disabled + * and runtime-PM-suspended + */ + if (driver->supports_autosuspend) + pm_runtime_disable(dev); + pm_runtime_set_suspended(dev); + } return retval; } diff --git a/drivers/usb/core/hcd-pci.c b/drivers/usb/core/hcd-pci.c index 66fe1b78d952..03432467b05f 100644 --- a/drivers/usb/core/hcd-pci.c +++ b/drivers/usb/core/hcd-pci.c @@ -515,8 +515,6 @@ static int resume_common(struct device *dev, int event) event == PM_EVENT_RESTORE); if (retval) { dev_err(dev, "PCI post-resume error %d!\n", retval); - if (hcd->shared_hcd) - usb_hc_died(hcd->shared_hcd); usb_hc_died(hcd); } } diff --git a/drivers/usb/core/message.c b/drivers/usb/core/message.c index 228672f2c4a1..bfa5eda0cc26 100644 --- a/drivers/usb/core/message.c +++ b/drivers/usb/core/message.c @@ -1341,6 +1341,11 @@ void usb_enable_interface(struct usb_device *dev, * is submitted that needs that bandwidth. Some other operating systems * allocate bandwidth early, when a configuration is chosen. * + * xHCI reserves bandwidth and configures the alternate setting in + * usb_hcd_alloc_bandwidth(). If it fails the original interface altsetting + * may be disabled. Drivers cannot rely on any particular alternate + * setting being in effect after a failure. + * * This call is synchronous, and may not be used in an interrupt context. * Also, drivers must not change altsettings while urbs are scheduled for * endpoints in that interface; all such urbs must first be completed @@ -1376,6 +1381,12 @@ int usb_set_interface(struct usb_device *dev, int interface, int alternate) alternate); return -EINVAL; } + /* + * usb3 hosts configure the interface in usb_hcd_alloc_bandwidth, + * including freeing dropped endpoint ring buffers. + * Make sure the interface endpoints are flushed before that + */ + usb_disable_interface(dev, iface, false); /* Make sure we have enough bandwidth for this alternate interface. * Remove the current alt setting and add the new alt setting. diff --git a/drivers/usb/core/of.c b/drivers/usb/core/of.c index fd77442c2d12..651708d8c908 100644 --- a/drivers/usb/core/of.c +++ b/drivers/usb/core/of.c @@ -105,29 +105,3 @@ usb_of_get_interface_node(struct usb_device *udev, u8 config, u8 ifnum) return NULL; } EXPORT_SYMBOL_GPL(usb_of_get_interface_node); - -/** - * usb_of_get_companion_dev - Find the companion device - * @dev: the device pointer to find a companion - * - * Find the companion device from platform bus. - * - * Takes a reference to the returned struct device which needs to be dropped - * after use. - * - * Return: On success, a pointer to the companion device, %NULL on failure. - */ -struct device *usb_of_get_companion_dev(struct device *dev) -{ - struct device_node *node; - struct platform_device *pdev = NULL; - - node = of_parse_phandle(dev->of_node, "companion", 0); - if (node) - pdev = of_find_device_by_node(node); - - of_node_put(node); - - return pdev ? &pdev->dev : NULL; -} -EXPORT_SYMBOL_GPL(usb_of_get_companion_dev); diff --git a/drivers/usb/core/quirks.c b/drivers/usb/core/quirks.c index 097057d2eacf..178d6c6063c0 100644 --- a/drivers/usb/core/quirks.c +++ b/drivers/usb/core/quirks.c @@ -58,6 +58,7 @@ static int quirks_param_set(const char *val, const struct kernel_param *kp) quirk_list = kcalloc(quirk_count, sizeof(struct quirk_entry), GFP_KERNEL); if (!quirk_list) { + quirk_count = 0; mutex_unlock(&quirk_mutex); return -ENOMEM; } @@ -154,7 +155,7 @@ static struct kparam_string quirks_param_string = { .string = quirks_param, }; -module_param_cb(quirks, &quirks_param_ops, &quirks_param_string, 0644); +device_param_cb(quirks, &quirks_param_ops, &quirks_param_string, 0644); MODULE_PARM_DESC(quirks, "Add/modify USB quirks by specifying quirks=vendorID:productID:quirks"); /* Lists of quirky USB devices, split in device quirks and interface quirks. @@ -178,6 +179,10 @@ static const struct usb_device_id usb_quirk_list[] = { /* CBM - Flash disk */ { USB_DEVICE(0x0204, 0x6025), .driver_info = USB_QUIRK_RESET_RESUME }, + /* WORLDE Controller KS49 or Prodipe MIDI 49C USB controller */ + { USB_DEVICE(0x0218, 0x0201), .driver_info = + USB_QUIRK_CONFIG_INTF_STRINGS }, + /* WORLDE easy key (easykey.25) MIDI controller */ { USB_DEVICE(0x0218, 0x0401), .driver_info = USB_QUIRK_CONFIG_INTF_STRINGS }, @@ -406,6 +411,9 @@ static const struct usb_device_id usb_quirk_list[] = { { USB_DEVICE(0x2040, 0x7200), .driver_info = USB_QUIRK_CONFIG_INTF_STRINGS }, + /* DJI CineSSD */ + { USB_DEVICE(0x2ca3, 0x0031), .driver_info = USB_QUIRK_NO_LPM }, + /* INTEL VALUE SSD */ { USB_DEVICE(0x8086, 0xf1a5), .driver_info = USB_QUIRK_RESET_RESUME }, diff --git a/drivers/usb/core/usb.c b/drivers/usb/core/usb.c index 623be3174fb3..79d8bd7a612e 100644 --- a/drivers/usb/core/usb.c +++ b/drivers/usb/core/usb.c @@ -228,6 +228,8 @@ struct usb_host_interface *usb_find_alt_setting( struct usb_interface_cache *intf_cache = NULL; int i; + if (!config) + return NULL; for (i = 0; i < config->desc.bNumInterfaces; i++) { if (config->intf_cache[i]->altsetting[0].desc.bInterfaceNumber == iface_num) { diff --git a/drivers/usb/dwc2/platform.c b/drivers/usb/dwc2/platform.c index 9a53a58e676e..577642895b57 100644 --- a/drivers/usb/dwc2/platform.c +++ b/drivers/usb/dwc2/platform.c @@ -412,8 +412,6 @@ static int dwc2_driver_probe(struct platform_device *dev) dev_dbg(&dev->dev, "mapped PA %08lx to VA %p\n", (unsigned long)res->start, hsotg->regs); - hsotg->needs_byte_swap = dwc2_check_core_endianness(hsotg); - retval = dwc2_lowlevel_hw_init(hsotg); if (retval) return retval; @@ -438,6 +436,8 @@ static int dwc2_driver_probe(struct platform_device *dev) if (retval) return retval; + hsotg->needs_byte_swap = dwc2_check_core_endianness(hsotg); + retval = dwc2_get_dr_mode(hsotg); if (retval) goto error; diff --git a/drivers/usb/dwc3/dwc3-of-simple.c b/drivers/usb/dwc3/dwc3-of-simple.c index 40bf9e0bbc59..4c2771c5e727 100644 --- a/drivers/usb/dwc3/dwc3-of-simple.c +++ b/drivers/usb/dwc3/dwc3-of-simple.c @@ -180,8 +180,7 @@ static int dwc3_of_simple_remove(struct platform_device *pdev) return 0; } -#ifdef CONFIG_PM -static int dwc3_of_simple_runtime_suspend(struct device *dev) +static int __maybe_unused dwc3_of_simple_runtime_suspend(struct device *dev) { struct dwc3_of_simple *simple = dev_get_drvdata(dev); int i; @@ -192,7 +191,7 @@ static int dwc3_of_simple_runtime_suspend(struct device *dev) return 0; } -static int dwc3_of_simple_runtime_resume(struct device *dev) +static int __maybe_unused dwc3_of_simple_runtime_resume(struct device *dev) { struct dwc3_of_simple *simple = dev_get_drvdata(dev); int ret; @@ -210,7 +209,7 @@ static int dwc3_of_simple_runtime_resume(struct device *dev) return 0; } -static int dwc3_of_simple_suspend(struct device *dev) +static int __maybe_unused dwc3_of_simple_suspend(struct device *dev) { struct dwc3_of_simple *simple = dev_get_drvdata(dev); @@ -220,7 +219,7 @@ static int dwc3_of_simple_suspend(struct device *dev) return 0; } -static int dwc3_of_simple_resume(struct device *dev) +static int __maybe_unused dwc3_of_simple_resume(struct device *dev) { struct dwc3_of_simple *simple = dev_get_drvdata(dev); @@ -229,7 +228,6 @@ static int dwc3_of_simple_resume(struct device *dev) return 0; } -#endif static const struct dev_pm_ops dwc3_of_simple_dev_pm_ops = { SET_SYSTEM_SLEEP_PM_OPS(dwc3_of_simple_suspend, dwc3_of_simple_resume) diff --git a/drivers/usb/dwc3/dwc3-pci.c b/drivers/usb/dwc3/dwc3-pci.c index 5edd79470368..1286076a8890 100644 --- a/drivers/usb/dwc3/dwc3-pci.c +++ b/drivers/usb/dwc3/dwc3-pci.c @@ -85,8 +85,8 @@ static int dwc3_byt_enable_ulpi_refclock(struct pci_dev *pci) u32 value; reg = pcim_iomap(pci, GP_RWBAR, 0); - if (IS_ERR(reg)) - return PTR_ERR(reg); + if (!reg) + return -ENOMEM; value = readl(reg + GP_RWREG1); if (!(value & GP_RWREG1_ULPI_REFCLK_DISABLE)) diff --git a/drivers/usb/dwc3/gadget.c b/drivers/usb/dwc3/gadget.c index 032ea7d709ba..2b53194081ba 100644 --- a/drivers/usb/dwc3/gadget.c +++ b/drivers/usb/dwc3/gadget.c @@ -473,7 +473,6 @@ static int dwc3_gadget_set_xfer_resource(struct dwc3_ep *dep) /** * dwc3_gadget_start_config - configure ep resources - * @dwc: pointer to our controller context structure * @dep: endpoint that is being enabled * * Issue a %DWC3_DEPCMD_DEPSTARTCFG command to @dep. After the command's diff --git a/drivers/usb/gadget/udc/fotg210-udc.c b/drivers/usb/gadget/udc/fotg210-udc.c index 53a48f561458..587c5037ff07 100644 --- a/drivers/usb/gadget/udc/fotg210-udc.c +++ b/drivers/usb/gadget/udc/fotg210-udc.c @@ -1063,12 +1063,15 @@ static const struct usb_gadget_ops fotg210_gadget_ops = { static int fotg210_udc_remove(struct platform_device *pdev) { struct fotg210_udc *fotg210 = platform_get_drvdata(pdev); + int i; usb_del_gadget_udc(&fotg210->gadget); iounmap(fotg210->reg); free_irq(platform_get_irq(pdev, 0), fotg210); fotg210_ep_free_request(&fotg210->ep[0]->ep, fotg210->ep0_req); + for (i = 0; i < FOTG210_MAX_NUM_EP; i++) + kfree(fotg210->ep[i]); kfree(fotg210); return 0; @@ -1099,7 +1102,7 @@ static int fotg210_udc_probe(struct platform_device *pdev) /* initialize udc */ fotg210 = kzalloc(sizeof(struct fotg210_udc), GFP_KERNEL); if (fotg210 == NULL) - goto err_alloc; + goto err; for (i = 0; i < FOTG210_MAX_NUM_EP; i++) { _ep[i] = kzalloc(sizeof(struct fotg210_ep), GFP_KERNEL); @@ -1111,7 +1114,7 @@ static int fotg210_udc_probe(struct platform_device *pdev) fotg210->reg = ioremap(res->start, resource_size(res)); if (fotg210->reg == NULL) { pr_err("ioremap error.\n"); - goto err_map; + goto err_alloc; } spin_lock_init(&fotg210->lock); @@ -1159,7 +1162,7 @@ static int fotg210_udc_probe(struct platform_device *pdev) fotg210->ep0_req = fotg210_ep_alloc_request(&fotg210->ep[0]->ep, GFP_KERNEL); if (fotg210->ep0_req == NULL) - goto err_req; + goto err_map; fotg210_init(fotg210); @@ -1187,12 +1190,14 @@ err_req: fotg210_ep_free_request(&fotg210->ep[0]->ep, fotg210->ep0_req); err_map: - if (fotg210->reg) - iounmap(fotg210->reg); + iounmap(fotg210->reg); err_alloc: + for (i = 0; i < FOTG210_MAX_NUM_EP; i++) + kfree(fotg210->ep[i]); kfree(fotg210); +err: return ret; } diff --git a/drivers/usb/gadget/udc/net2280.c b/drivers/usb/gadget/udc/net2280.c index 318246d8b2e2..b02ab2a8d927 100644 --- a/drivers/usb/gadget/udc/net2280.c +++ b/drivers/usb/gadget/udc/net2280.c @@ -1545,11 +1545,14 @@ static int net2280_pullup(struct usb_gadget *_gadget, int is_on) writel(tmp | BIT(USB_DETECT_ENABLE), &dev->usb->usbctl); } else { writel(tmp & ~BIT(USB_DETECT_ENABLE), &dev->usb->usbctl); - stop_activity(dev, dev->driver); + stop_activity(dev, NULL); } spin_unlock_irqrestore(&dev->lock, flags); + if (!is_on && dev->driver) + dev->driver->disconnect(&dev->gadget); + return 0; } @@ -2466,8 +2469,11 @@ static void stop_activity(struct net2280 *dev, struct usb_gadget_driver *driver) nuke(&dev->ep[i]); /* report disconnect; the driver is already quiesced */ - if (driver) + if (driver) { + spin_unlock(&dev->lock); driver->disconnect(&dev->gadget); + spin_lock(&dev->lock); + } usb_reinit(dev); } @@ -3341,6 +3347,8 @@ next_endpoints: BIT(PCI_RETRY_ABORT_INTERRUPT)) static void handle_stat1_irqs(struct net2280 *dev, u32 stat) +__releases(dev->lock) +__acquires(dev->lock) { struct net2280_ep *ep; u32 tmp, num, mask, scratch; @@ -3381,12 +3389,14 @@ static void handle_stat1_irqs(struct net2280 *dev, u32 stat) if (disconnect || reset) { stop_activity(dev, dev->driver); ep0_start(dev); + spin_unlock(&dev->lock); if (reset) usb_gadget_udc_reset (&dev->gadget, dev->driver); else (dev->driver->disconnect) (&dev->gadget); + spin_lock(&dev->lock); return; } } @@ -3405,6 +3415,7 @@ static void handle_stat1_irqs(struct net2280 *dev, u32 stat) tmp = BIT(SUSPEND_REQUEST_CHANGE_INTERRUPT); if (stat & tmp) { writel(tmp, &dev->regs->irqstat1); + spin_unlock(&dev->lock); if (stat & BIT(SUSPEND_REQUEST_INTERRUPT)) { if (dev->driver->suspend) dev->driver->suspend(&dev->gadget); @@ -3415,6 +3426,7 @@ static void handle_stat1_irqs(struct net2280 *dev, u32 stat) dev->driver->resume(&dev->gadget); /* at high speed, note erratum 0133 */ } + spin_lock(&dev->lock); stat &= ~tmp; } diff --git a/drivers/usb/gadget/udc/renesas_usb3.c b/drivers/usb/gadget/udc/renesas_usb3.c index 1f879b3f2c96..e1656f361e08 100644 --- a/drivers/usb/gadget/udc/renesas_usb3.c +++ b/drivers/usb/gadget/udc/renesas_usb3.c @@ -812,12 +812,15 @@ static void usb3_irq_epc_int_1_speed(struct renesas_usb3 *usb3) switch (speed) { case USB_STA_SPEED_SS: usb3->gadget.speed = USB_SPEED_SUPER; + usb3->gadget.ep0->maxpacket = USB3_EP0_SS_MAX_PACKET_SIZE; break; case USB_STA_SPEED_HS: usb3->gadget.speed = USB_SPEED_HIGH; + usb3->gadget.ep0->maxpacket = USB3_EP0_HSFS_MAX_PACKET_SIZE; break; case USB_STA_SPEED_FS: usb3->gadget.speed = USB_SPEED_FULL; + usb3->gadget.ep0->maxpacket = USB3_EP0_HSFS_MAX_PACKET_SIZE; break; default: usb3->gadget.speed = USB_SPEED_UNKNOWN; @@ -2513,7 +2516,7 @@ static int renesas_usb3_init_ep(struct renesas_usb3 *usb3, struct device *dev, /* for control pipe */ usb3->gadget.ep0 = &usb3_ep->ep; usb_ep_set_maxpacket_limit(&usb3_ep->ep, - USB3_EP0_HSFS_MAX_PACKET_SIZE); + USB3_EP0_SS_MAX_PACKET_SIZE); usb3_ep->ep.caps.type_control = true; usb3_ep->ep.caps.dir_in = true; usb3_ep->ep.caps.dir_out = true; diff --git a/drivers/usb/host/u132-hcd.c b/drivers/usb/host/u132-hcd.c index 072bd5d5738e..5b8a3d9530c4 100644 --- a/drivers/usb/host/u132-hcd.c +++ b/drivers/usb/host/u132-hcd.c @@ -2555,7 +2555,7 @@ static int u132_get_frame(struct usb_hcd *hcd) } else { int frame = 0; dev_err(&u132->platform_dev->dev, "TODO: u132_get_frame\n"); - msleep(100); + mdelay(100); return frame; } } diff --git a/drivers/usb/host/xhci-mem.c b/drivers/usb/host/xhci-mem.c index ef350c33dc4a..b1f27aa38b10 100644 --- a/drivers/usb/host/xhci-mem.c +++ b/drivers/usb/host/xhci-mem.c @@ -1613,6 +1613,10 @@ void xhci_endpoint_copy(struct xhci_hcd *xhci, in_ep_ctx->ep_info2 = out_ep_ctx->ep_info2; in_ep_ctx->deq = out_ep_ctx->deq; in_ep_ctx->tx_info = out_ep_ctx->tx_info; + if (xhci->quirks & XHCI_MTK_HOST) { + in_ep_ctx->reserved[0] = out_ep_ctx->reserved[0]; + in_ep_ctx->reserved[1] = out_ep_ctx->reserved[1]; + } } /* Copy output xhci_slot_ctx to the input xhci_slot_ctx. diff --git a/drivers/usb/host/xhci-plat.c b/drivers/usb/host/xhci-plat.c index 8dc77e34a859..94e939249b2b 100644 --- a/drivers/usb/host/xhci-plat.c +++ b/drivers/usb/host/xhci-plat.c @@ -153,7 +153,7 @@ static int xhci_plat_probe(struct platform_device *pdev) { const struct xhci_plat_priv *priv_match; const struct hc_driver *driver; - struct device *sysdev; + struct device *sysdev, *tmpdev; struct xhci_hcd *xhci; struct resource *res; struct usb_hcd *hcd; @@ -273,19 +273,24 @@ static int xhci_plat_probe(struct platform_device *pdev) goto disable_clk; } - if (device_property_read_bool(sysdev, "usb2-lpm-disable")) - xhci->quirks |= XHCI_HW_LPM_DISABLE; + /* imod_interval is the interrupt moderation value in nanoseconds. */ + xhci->imod_interval = 40000; - if (device_property_read_bool(sysdev, "usb3-lpm-capable")) - xhci->quirks |= XHCI_LPM_SUPPORT; + /* Iterate over all parent nodes for finding quirks */ + for (tmpdev = &pdev->dev; tmpdev; tmpdev = tmpdev->parent) { - if (device_property_read_bool(&pdev->dev, "quirk-broken-port-ped")) - xhci->quirks |= XHCI_BROKEN_PORT_PED; + if (device_property_read_bool(tmpdev, "usb2-lpm-disable")) + xhci->quirks |= XHCI_HW_LPM_DISABLE; - /* imod_interval is the interrupt moderation value in nanoseconds. */ - xhci->imod_interval = 40000; - device_property_read_u32(sysdev, "imod-interval-ns", - &xhci->imod_interval); + if (device_property_read_bool(tmpdev, "usb3-lpm-capable")) + xhci->quirks |= XHCI_LPM_SUPPORT; + + if (device_property_read_bool(tmpdev, "quirk-broken-port-ped")) + xhci->quirks |= XHCI_BROKEN_PORT_PED; + + device_property_read_u32(tmpdev, "imod-interval-ns", + &xhci->imod_interval); + } hcd->usb_phy = devm_usb_get_phy_by_phandle(sysdev, "usb-phy", 0); if (IS_ERR(hcd->usb_phy)) { diff --git a/drivers/usb/host/xhci.c b/drivers/usb/host/xhci.c index 61f48b17e57b..0420eefa647a 100644 --- a/drivers/usb/host/xhci.c +++ b/drivers/usb/host/xhci.c @@ -37,6 +37,21 @@ static unsigned long long quirks; module_param(quirks, ullong, S_IRUGO); MODULE_PARM_DESC(quirks, "Bit flags for quirks to be enabled as default"); +static bool td_on_ring(struct xhci_td *td, struct xhci_ring *ring) +{ + struct xhci_segment *seg = ring->first_seg; + + if (!td || !td->start_seg) + return false; + do { + if (seg == td->start_seg) + return true; + seg = seg->next; + } while (seg && seg != ring->first_seg); + + return false; +} + /* TODO: copied from ehci-hcd.c - can this be refactored? */ /* * xhci_handshake - spin reading hc until handshake completes or fails @@ -1571,6 +1586,21 @@ static int xhci_urb_dequeue(struct usb_hcd *hcd, struct urb *urb, int status) goto done; } + /* + * check ring is not re-allocated since URB was enqueued. If it is, then + * make sure none of the ring related pointers in this URB private data + * are touched, such as td_list, otherwise we overwrite freed data + */ + if (!td_on_ring(&urb_priv->td[0], ep_ring)) { + xhci_err(xhci, "Canceled URB td not found on endpoint ring"); + for (i = urb_priv->num_tds_done; i < urb_priv->num_tds; i++) { + td = &urb_priv->td[i]; + if (!list_empty(&td->cancelled_td_list)) + list_del_init(&td->cancelled_td_list); + } + goto err_giveback; + } + if (xhci->xhc_state & XHCI_STATE_HALTED) { xhci_dbg_trace(xhci, trace_xhci_dbg_cancel_urb, "HC halted, freeing TD manually."); diff --git a/drivers/usb/misc/uss720.c b/drivers/usb/misc/uss720.c index 82f220631bd7..b5d661644263 100644 --- a/drivers/usb/misc/uss720.c +++ b/drivers/usb/misc/uss720.c @@ -369,7 +369,7 @@ static unsigned char parport_uss720_frob_control(struct parport *pp, unsigned ch mask &= 0x0f; val &= 0x0f; d = (priv->reg[1] & (~mask)) ^ val; - if (set_1284_register(pp, 2, d, GFP_KERNEL)) + if (set_1284_register(pp, 2, d, GFP_ATOMIC)) return 0; priv->reg[1] = d; return d & 0xf; @@ -379,7 +379,7 @@ static unsigned char parport_uss720_read_status(struct parport *pp) { unsigned char ret; - if (get_1284_register(pp, 1, &ret, GFP_KERNEL)) + if (get_1284_register(pp, 1, &ret, GFP_ATOMIC)) return 0; return ret & 0xf8; } diff --git a/drivers/usb/misc/yurex.c b/drivers/usb/misc/yurex.c index 3be40eaa1ac9..6d9fd5f64903 100644 --- a/drivers/usb/misc/yurex.c +++ b/drivers/usb/misc/yurex.c @@ -413,6 +413,9 @@ static ssize_t yurex_read(struct file *file, char __user *buffer, size_t count, spin_unlock_irqrestore(&dev->lock, flags); mutex_unlock(&dev->io_mutex); + if (WARN_ON_ONCE(len >= sizeof(in_buffer))) + return -EIO; + return simple_read_from_buffer(buffer, count, ppos, in_buffer, len); } @@ -421,13 +424,13 @@ static ssize_t yurex_write(struct file *file, const char __user *user_buffer, { struct usb_yurex *dev; int i, set = 0, retval = 0; - char buffer[16]; + char buffer[16 + 1]; char *data = buffer; unsigned long long c, c2 = 0; signed long timeout = 0; DEFINE_WAIT(wait); - count = min(sizeof(buffer), count); + count = min(sizeof(buffer) - 1, count); dev = file->private_data; /* verify that we actually have some data to write */ @@ -446,6 +449,7 @@ static ssize_t yurex_write(struct file *file, const char __user *user_buffer, retval = -EFAULT; goto error; } + buffer[count] = 0; memset(dev->cntl_buffer, CMD_PADDING, YUREX_BUF_SIZE); switch (buffer[0]) { diff --git a/drivers/usb/mtu3/mtu3_core.c b/drivers/usb/mtu3/mtu3_core.c index eecfd0671362..d045d8458f81 100644 --- a/drivers/usb/mtu3/mtu3_core.c +++ b/drivers/usb/mtu3/mtu3_core.c @@ -107,8 +107,12 @@ static int mtu3_device_enable(struct mtu3 *mtu) (SSUSB_U2_PORT_DIS | SSUSB_U2_PORT_PDN | SSUSB_U2_PORT_HOST_SEL)); - if (mtu->ssusb->dr_mode == USB_DR_MODE_OTG) + if (mtu->ssusb->dr_mode == USB_DR_MODE_OTG) { mtu3_setbits(ibase, SSUSB_U2_CTRL(0), SSUSB_U2_PORT_OTG_SEL); + if (mtu->is_u3_ip) + mtu3_setbits(ibase, SSUSB_U3_CTRL(0), + SSUSB_U3_PORT_DUAL_MODE); + } return ssusb_check_clocks(mtu->ssusb, check_clk); } diff --git a/drivers/usb/mtu3/mtu3_hw_regs.h b/drivers/usb/mtu3/mtu3_hw_regs.h index 6ee371478d89..a45bb253939f 100644 --- a/drivers/usb/mtu3/mtu3_hw_regs.h +++ b/drivers/usb/mtu3/mtu3_hw_regs.h @@ -459,6 +459,7 @@ /* U3D_SSUSB_U3_CTRL_0P */ #define SSUSB_U3_PORT_SSP_SPEED BIT(9) +#define SSUSB_U3_PORT_DUAL_MODE BIT(7) #define SSUSB_U3_PORT_HOST_SEL BIT(2) #define SSUSB_U3_PORT_PDN BIT(1) #define SSUSB_U3_PORT_DIS BIT(0) diff --git a/drivers/usb/musb/musb_dsps.c b/drivers/usb/musb/musb_dsps.c index df827ff57b0d..23a0df79ef21 100644 --- a/drivers/usb/musb/musb_dsps.c +++ b/drivers/usb/musb/musb_dsps.c @@ -658,16 +658,6 @@ dsps_dma_controller_create(struct musb *musb, void __iomem *base) return controller; } -static void dsps_dma_controller_destroy(struct dma_controller *c) -{ - struct musb *musb = c->musb; - struct dsps_glue *glue = dev_get_drvdata(musb->controller->parent); - void __iomem *usbss_base = glue->usbss_base; - - musb_writel(usbss_base, USBSS_IRQ_CLEARR, USBSS_IRQ_PD_COMP); - cppi41_dma_controller_destroy(c); -} - #ifdef CONFIG_PM_SLEEP static void dsps_dma_controller_suspend(struct dsps_glue *glue) { @@ -697,7 +687,7 @@ static struct musb_platform_ops dsps_ops = { #ifdef CONFIG_USB_TI_CPPI41_DMA .dma_init = dsps_dma_controller_create, - .dma_exit = dsps_dma_controller_destroy, + .dma_exit = cppi41_dma_controller_destroy, #endif .enable = dsps_musb_enable, .disable = dsps_musb_disable, diff --git a/drivers/usb/serial/io_ti.h b/drivers/usb/serial/io_ti.h index e53c68261017..9bbcee37524e 100644 --- a/drivers/usb/serial/io_ti.h +++ b/drivers/usb/serial/io_ti.h @@ -173,7 +173,7 @@ struct ump_interrupt { } __attribute__((packed)); -#define TIUMP_GET_PORT_FROM_CODE(c) (((c) >> 4) - 3) +#define TIUMP_GET_PORT_FROM_CODE(c) (((c) >> 6) & 0x01) #define TIUMP_GET_FUNC_FROM_CODE(c) ((c) & 0x0f) #define TIUMP_INTERRUPT_CODE_LSR 0x03 #define TIUMP_INTERRUPT_CODE_MSR 0x04 diff --git a/drivers/usb/serial/ti_usb_3410_5052.c b/drivers/usb/serial/ti_usb_3410_5052.c index 3010878f7f8e..e3c5832337e0 100644 --- a/drivers/usb/serial/ti_usb_3410_5052.c +++ b/drivers/usb/serial/ti_usb_3410_5052.c @@ -1119,7 +1119,7 @@ static void ti_break(struct tty_struct *tty, int break_state) static int ti_get_port_from_code(unsigned char code) { - return (code >> 4) - 3; + return (code >> 6) & 0x01; } static int ti_get_func_from_code(unsigned char code) diff --git a/drivers/usb/storage/scsiglue.c b/drivers/usb/storage/scsiglue.c index c267f2812a04..e227bb5b794f 100644 --- a/drivers/usb/storage/scsiglue.c +++ b/drivers/usb/storage/scsiglue.c @@ -376,6 +376,15 @@ static int queuecommand_lck(struct scsi_cmnd *srb, return 0; } + if ((us->fflags & US_FL_NO_ATA_1X) && + (srb->cmnd[0] == ATA_12 || srb->cmnd[0] == ATA_16)) { + memcpy(srb->sense_buffer, usb_stor_sense_invalidCDB, + sizeof(usb_stor_sense_invalidCDB)); + srb->result = SAM_STAT_CHECK_CONDITION; + done(srb); + return 0; + } + /* enqueue the command and wake up the control thread */ srb->scsi_done = done; us->srb = srb; diff --git a/drivers/usb/storage/uas.c b/drivers/usb/storage/uas.c index 9e9de5452860..1f7b401c4d04 100644 --- a/drivers/usb/storage/uas.c +++ b/drivers/usb/storage/uas.c @@ -842,6 +842,27 @@ static int uas_slave_configure(struct scsi_device *sdev) sdev->skip_ms_page_8 = 1; sdev->wce_default_on = 1; } + + /* + * Some disks return the total number of blocks in response + * to READ CAPACITY rather than the highest block number. + * If this device makes that mistake, tell the sd driver. + */ + if (devinfo->flags & US_FL_FIX_CAPACITY) + sdev->fix_capacity = 1; + + /* + * Some devices don't like MODE SENSE with page=0x3f, + * which is the command used for checking if a device + * is write-protected. Now that we tell the sd driver + * to do a 192-byte transfer with this command the + * majority of devices work fine, but a few still can't + * handle it. The sd driver will simply assume those + * devices are write-enabled. + */ + if (devinfo->flags & US_FL_NO_WP_DETECT) + sdev->skip_ms_page_3f = 1; + scsi_change_queue_depth(sdev, devinfo->qdepth - 2); return 0; } diff --git a/drivers/usb/storage/unusual_devs.h b/drivers/usb/storage/unusual_devs.h index 22fcfccf453a..f7f83b21dc74 100644 --- a/drivers/usb/storage/unusual_devs.h +++ b/drivers/usb/storage/unusual_devs.h @@ -2288,6 +2288,13 @@ UNUSUAL_DEV( 0x2735, 0x100b, 0x0000, 0x9999, USB_SC_DEVICE, USB_PR_DEVICE, NULL, US_FL_GO_SLOW ), +/* Reported-by: Tim Anderson <tsa@biglakesoftware.com> */ +UNUSUAL_DEV( 0x2ca3, 0x0031, 0x0000, 0x9999, + "DJI", + "CineSSD", + USB_SC_DEVICE, USB_PR_DEVICE, NULL, + US_FL_NO_ATA_1X), + /* * Reported by Frederic Marchal <frederic.marchal@wowcompany.com> * Mio Moov 330 diff --git a/drivers/usb/typec/bus.c b/drivers/usb/typec/bus.c index 95a2b10127db..76299b6ff06d 100644 --- a/drivers/usb/typec/bus.c +++ b/drivers/usb/typec/bus.c @@ -255,12 +255,13 @@ EXPORT_SYMBOL_GPL(typec_altmode_unregister_driver); /* API for the port drivers */ /** - * typec_match_altmode - Match SVID to an array of alternate modes + * typec_match_altmode - Match SVID and mode to an array of alternate modes * @altmodes: Array of alternate modes - * @n: Number of elements in the array, or -1 for NULL termiated arrays + * @n: Number of elements in the array, or -1 for NULL terminated arrays * @svid: Standard or Vendor ID to match with + * @mode: Mode to match with * - * Return pointer to an alternate mode with SVID mathing @svid, or NULL when no + * Return pointer to an alternate mode with SVID matching @svid, or NULL when no * match is found. */ struct typec_altmode *typec_match_altmode(struct typec_altmode **altmodes, diff --git a/drivers/usb/typec/class.c b/drivers/usb/typec/class.c index c202975f8097..e61dffb27a0c 100644 --- a/drivers/usb/typec/class.c +++ b/drivers/usb/typec/class.c @@ -1484,7 +1484,6 @@ EXPORT_SYMBOL_GPL(typec_set_mode); * typec_port_register_altmode - Register USB Type-C Port Alternate Mode * @port: USB Type-C Port that supports the alternate mode * @desc: Description of the alternate mode - * @drvdata: Private pointer to driver specific info * * This routine is used to register an alternate mode that @port is capable of * supporting. diff --git a/drivers/usb/typec/mux.c b/drivers/usb/typec/mux.c index ddaac63ecf12..d990aa510fab 100644 --- a/drivers/usb/typec/mux.c +++ b/drivers/usb/typec/mux.c @@ -9,6 +9,7 @@ #include <linux/device.h> #include <linux/list.h> +#include <linux/module.h> #include <linux/mutex.h> #include <linux/usb/typec_mux.h> @@ -49,8 +50,10 @@ struct typec_switch *typec_switch_get(struct device *dev) mutex_lock(&switch_lock); sw = device_connection_find_match(dev, "typec-switch", NULL, typec_switch_match); - if (!IS_ERR_OR_NULL(sw)) + if (!IS_ERR_OR_NULL(sw)) { + WARN_ON(!try_module_get(sw->dev->driver->owner)); get_device(sw->dev); + } mutex_unlock(&switch_lock); return sw; @@ -65,8 +68,10 @@ EXPORT_SYMBOL_GPL(typec_switch_get); */ void typec_switch_put(struct typec_switch *sw) { - if (!IS_ERR_OR_NULL(sw)) + if (!IS_ERR_OR_NULL(sw)) { + module_put(sw->dev->driver->owner); put_device(sw->dev); + } } EXPORT_SYMBOL_GPL(typec_switch_put); @@ -136,8 +141,10 @@ struct typec_mux *typec_mux_get(struct device *dev, const char *name) mutex_lock(&mux_lock); mux = device_connection_find_match(dev, name, NULL, typec_mux_match); - if (!IS_ERR_OR_NULL(mux)) + if (!IS_ERR_OR_NULL(mux)) { + WARN_ON(!try_module_get(mux->dev->driver->owner)); get_device(mux->dev); + } mutex_unlock(&mux_lock); return mux; @@ -152,8 +159,10 @@ EXPORT_SYMBOL_GPL(typec_mux_get); */ void typec_mux_put(struct typec_mux *mux) { - if (!IS_ERR_OR_NULL(mux)) + if (!IS_ERR_OR_NULL(mux)) { + module_put(mux->dev->driver->owner); put_device(mux->dev); + } } EXPORT_SYMBOL_GPL(typec_mux_put); diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c index 4e656f89cb22..1bff6bc8161a 100644 --- a/drivers/vhost/net.c +++ b/drivers/vhost/net.c @@ -116,6 +116,8 @@ struct vhost_net_virtqueue { * For RX, number of batched heads */ int done_idx; + /* Number of XDP frames batched */ + int batched_xdp; /* an array of userspace buffers info */ struct ubuf_info *ubuf_info; /* Reference counting for outstanding ubufs. @@ -123,6 +125,8 @@ struct vhost_net_virtqueue { struct vhost_net_ubuf_ref *ubufs; struct ptr_ring *rx_ring; struct vhost_net_buf rxq; + /* Batched XDP buffs */ + struct xdp_buff *xdp; }; struct vhost_net { @@ -338,6 +342,11 @@ static bool vhost_sock_zcopy(struct socket *sock) sock_flag(sock->sk, SOCK_ZEROCOPY); } +static bool vhost_sock_xdp(struct socket *sock) +{ + return sock_flag(sock->sk, SOCK_XDP); +} + /* In case of DMA done not in order in lower device driver for some reason. * upend_idx is used to track end of used idx, done_idx is used to track head * of used idx. Once lower device DMA done contiguously, we will signal KVM @@ -444,10 +453,37 @@ static void vhost_net_signal_used(struct vhost_net_virtqueue *nvq) nvq->done_idx = 0; } +static void vhost_tx_batch(struct vhost_net *net, + struct vhost_net_virtqueue *nvq, + struct socket *sock, + struct msghdr *msghdr) +{ + struct tun_msg_ctl ctl = { + .type = TUN_MSG_PTR, + .num = nvq->batched_xdp, + .ptr = nvq->xdp, + }; + int err; + + if (nvq->batched_xdp == 0) + goto signal_used; + + msghdr->msg_control = &ctl; + err = sock->ops->sendmsg(sock, msghdr, 0); + if (unlikely(err < 0)) { + vq_err(&nvq->vq, "Fail to batch sending packets\n"); + return; + } + +signal_used: + vhost_net_signal_used(nvq); + nvq->batched_xdp = 0; +} + static int vhost_net_tx_get_vq_desc(struct vhost_net *net, struct vhost_net_virtqueue *nvq, unsigned int *out_num, unsigned int *in_num, - bool *busyloop_intr) + struct msghdr *msghdr, bool *busyloop_intr) { struct vhost_virtqueue *vq = &nvq->vq; unsigned long uninitialized_var(endtime); @@ -455,8 +491,9 @@ static int vhost_net_tx_get_vq_desc(struct vhost_net *net, out_num, in_num, NULL, NULL); if (r == vq->num && vq->busyloop_timeout) { + /* Flush batched packets first */ if (!vhost_sock_zcopy(vq->private_data)) - vhost_net_signal_used(nvq); + vhost_tx_batch(net, nvq, vq->private_data, msghdr); preempt_disable(); endtime = busy_clock() + vq->busyloop_timeout; while (vhost_can_busy_poll(endtime)) { @@ -512,7 +549,7 @@ static int get_tx_bufs(struct vhost_net *net, struct vhost_virtqueue *vq = &nvq->vq; int ret; - ret = vhost_net_tx_get_vq_desc(net, nvq, out, in, busyloop_intr); + ret = vhost_net_tx_get_vq_desc(net, nvq, out, in, msg, busyloop_intr); if (ret < 0 || ret == vq->num) return ret; @@ -540,6 +577,80 @@ static bool tx_can_batch(struct vhost_virtqueue *vq, size_t total_len) !vhost_vq_avail_empty(vq->dev, vq); } +#define VHOST_NET_RX_PAD (NET_IP_ALIGN + NET_SKB_PAD) + +static int vhost_net_build_xdp(struct vhost_net_virtqueue *nvq, + struct iov_iter *from) +{ + struct vhost_virtqueue *vq = &nvq->vq; + struct socket *sock = vq->private_data; + struct page_frag *alloc_frag = ¤t->task_frag; + struct virtio_net_hdr *gso; + struct xdp_buff *xdp = &nvq->xdp[nvq->batched_xdp]; + struct tun_xdp_hdr *hdr; + size_t len = iov_iter_count(from); + int headroom = vhost_sock_xdp(sock) ? XDP_PACKET_HEADROOM : 0; + int buflen = SKB_DATA_ALIGN(sizeof(struct skb_shared_info)); + int pad = SKB_DATA_ALIGN(VHOST_NET_RX_PAD + headroom + nvq->sock_hlen); + int sock_hlen = nvq->sock_hlen; + void *buf; + int copied; + + if (unlikely(len < nvq->sock_hlen)) + return -EFAULT; + + if (SKB_DATA_ALIGN(len + pad) + + SKB_DATA_ALIGN(sizeof(struct skb_shared_info)) > PAGE_SIZE) + return -ENOSPC; + + buflen += SKB_DATA_ALIGN(len + pad); + alloc_frag->offset = ALIGN((u64)alloc_frag->offset, SMP_CACHE_BYTES); + if (unlikely(!skb_page_frag_refill(buflen, alloc_frag, GFP_KERNEL))) + return -ENOMEM; + + buf = (char *)page_address(alloc_frag->page) + alloc_frag->offset; + copied = copy_page_from_iter(alloc_frag->page, + alloc_frag->offset + + offsetof(struct tun_xdp_hdr, gso), + sock_hlen, from); + if (copied != sock_hlen) + return -EFAULT; + + hdr = buf; + gso = &hdr->gso; + + if ((gso->flags & VIRTIO_NET_HDR_F_NEEDS_CSUM) && + vhost16_to_cpu(vq, gso->csum_start) + + vhost16_to_cpu(vq, gso->csum_offset) + 2 > + vhost16_to_cpu(vq, gso->hdr_len)) { + gso->hdr_len = cpu_to_vhost16(vq, + vhost16_to_cpu(vq, gso->csum_start) + + vhost16_to_cpu(vq, gso->csum_offset) + 2); + + if (vhost16_to_cpu(vq, gso->hdr_len) > len) + return -EINVAL; + } + + len -= sock_hlen; + copied = copy_page_from_iter(alloc_frag->page, + alloc_frag->offset + pad, + len, from); + if (copied != len) + return -EFAULT; + + xdp->data_hard_start = buf; + xdp->data = buf + pad; + xdp->data_end = xdp->data + len; + hdr->buflen = buflen; + + get_page(alloc_frag->page); + alloc_frag->offset += buflen; + + ++nvq->batched_xdp; + + return 0; +} + static void handle_tx_copy(struct vhost_net *net, struct socket *sock) { struct vhost_net_virtqueue *nvq = &net->vqs[VHOST_NET_VQ_TX]; @@ -556,10 +667,14 @@ static void handle_tx_copy(struct vhost_net *net, struct socket *sock) size_t len, total_len = 0; int err; int sent_pkts = 0; + bool sock_can_batch = (sock->sk->sk_sndbuf == INT_MAX); for (;;) { bool busyloop_intr = false; + if (nvq->done_idx == VHOST_NET_BATCH) + vhost_tx_batch(net, nvq, sock, &msg); + head = get_tx_bufs(net, nvq, &msg, &out, &in, &len, &busyloop_intr); /* On error, stop handling until the next kick. */ @@ -577,14 +692,34 @@ static void handle_tx_copy(struct vhost_net *net, struct socket *sock) break; } - vq->heads[nvq->done_idx].id = cpu_to_vhost32(vq, head); - vq->heads[nvq->done_idx].len = 0; - total_len += len; - if (tx_can_batch(vq, total_len)) - msg.msg_flags |= MSG_MORE; - else - msg.msg_flags &= ~MSG_MORE; + + /* For simplicity, TX batching is only enabled if + * sndbuf is unlimited. + */ + if (sock_can_batch) { + err = vhost_net_build_xdp(nvq, &msg.msg_iter); + if (!err) { + goto done; + } else if (unlikely(err != -ENOSPC)) { + vhost_tx_batch(net, nvq, sock, &msg); + vhost_discard_vq_desc(vq, 1); + vhost_net_enable_vq(net, vq); + break; + } + + /* We can't build XDP buff, go for single + * packet path but let's flush batched + * packets. + */ + vhost_tx_batch(net, nvq, sock, &msg); + msg.msg_control = NULL; + } else { + if (tx_can_batch(vq, total_len)) + msg.msg_flags |= MSG_MORE; + else + msg.msg_flags &= ~MSG_MORE; + } /* TODO: Check specific error and bomb out unless ENOBUFS? */ err = sock->ops->sendmsg(sock, &msg, len); @@ -596,15 +731,17 @@ static void handle_tx_copy(struct vhost_net *net, struct socket *sock) if (err != len) pr_debug("Truncated TX packet: len %d != %zd\n", err, len); - if (++nvq->done_idx >= VHOST_NET_BATCH) - vhost_net_signal_used(nvq); +done: + vq->heads[nvq->done_idx].id = cpu_to_vhost32(vq, head); + vq->heads[nvq->done_idx].len = 0; + ++nvq->done_idx; if (vhost_exceeds_weight(++sent_pkts, total_len)) { vhost_poll_queue(&vq->poll); break; } } - vhost_net_signal_used(nvq); + vhost_tx_batch(net, nvq, sock, &msg); } static void handle_tx_zerocopy(struct vhost_net *net, struct socket *sock) @@ -620,6 +757,7 @@ static void handle_tx_zerocopy(struct vhost_net *net, struct socket *sock) .msg_controllen = 0, .msg_flags = MSG_DONTWAIT, }; + struct tun_msg_ctl ctl; size_t len, total_len = 0; int err; struct vhost_net_ubuf_ref *uninitialized_var(ubufs); @@ -664,8 +802,10 @@ static void handle_tx_zerocopy(struct vhost_net *net, struct socket *sock) ubuf->ctx = nvq->ubufs; ubuf->desc = nvq->upend_idx; refcount_set(&ubuf->refcnt, 1); - msg.msg_control = ubuf; - msg.msg_controllen = sizeof(ubuf); + msg.msg_control = &ctl; + ctl.type = TUN_MSG_UBUF; + ctl.ptr = ubuf; + msg.msg_controllen = sizeof(ctl); ubufs = nvq->ubufs; atomic_inc(&ubufs->refcount); nvq->upend_idx = (nvq->upend_idx + 1) % UIO_MAXIOV; @@ -1078,6 +1218,7 @@ static int vhost_net_open(struct inode *inode, struct file *f) struct vhost_dev *dev; struct vhost_virtqueue **vqs; void **queue; + struct xdp_buff *xdp; int i; n = kvmalloc(sizeof *n, GFP_KERNEL | __GFP_RETRY_MAYFAIL); @@ -1098,6 +1239,15 @@ static int vhost_net_open(struct inode *inode, struct file *f) } n->vqs[VHOST_NET_VQ_RX].rxq.queue = queue; + xdp = kmalloc_array(VHOST_NET_BATCH, sizeof(*xdp), GFP_KERNEL); + if (!xdp) { + kfree(vqs); + kvfree(n); + kfree(queue); + return -ENOMEM; + } + n->vqs[VHOST_NET_VQ_TX].xdp = xdp; + dev = &n->dev; vqs[VHOST_NET_VQ_TX] = &n->vqs[VHOST_NET_VQ_TX].vq; vqs[VHOST_NET_VQ_RX] = &n->vqs[VHOST_NET_VQ_RX].vq; @@ -1108,6 +1258,7 @@ static int vhost_net_open(struct inode *inode, struct file *f) n->vqs[i].ubuf_info = NULL; n->vqs[i].upend_idx = 0; n->vqs[i].done_idx = 0; + n->vqs[i].batched_xdp = 0; n->vqs[i].vhost_hlen = 0; n->vqs[i].sock_hlen = 0; n->vqs[i].rx_ring = NULL; @@ -1191,6 +1342,7 @@ static int vhost_net_release(struct inode *inode, struct file *f) * since jobs can re-queue themselves. */ vhost_net_flush(n); kfree(n->vqs[VHOST_NET_VQ_RX].rxq.queue); + kfree(n->vqs[VHOST_NET_VQ_TX].xdp); kfree(n->dev.vqs); kvfree(n); return 0; diff --git a/drivers/xen/Kconfig b/drivers/xen/Kconfig index b459edfacff3..90d387b50ab7 100644 --- a/drivers/xen/Kconfig +++ b/drivers/xen/Kconfig @@ -79,15 +79,19 @@ config XEN_BALLOON_MEMORY_HOTPLUG_LIMIT This value is used to allocate enough space in internal tables needed for physical memory administration. -config XEN_SCRUB_PAGES - bool "Scrub pages before returning them to system" +config XEN_SCRUB_PAGES_DEFAULT + bool "Scrub pages before returning them to system by default" depends on XEN_BALLOON default y help Scrub pages before returning them to the system for reuse by other domains. This makes sure that any confidential data is not accidentally visible to other domains. Is it more - secure, but slightly less efficient. + secure, but slightly less efficient. This can be controlled with + xen_scrub_pages=0 parameter and + /sys/devices/system/xen_memory/xen_memory0/scrub_pages. + This option only sets the default value. + If in doubt, say yes. config XEN_DEV_EVTCHN diff --git a/drivers/xen/cpu_hotplug.c b/drivers/xen/cpu_hotplug.c index d4265c8ebb22..b1357aa4bc55 100644 --- a/drivers/xen/cpu_hotplug.c +++ b/drivers/xen/cpu_hotplug.c @@ -19,15 +19,16 @@ static void enable_hotplug_cpu(int cpu) static void disable_hotplug_cpu(int cpu) { - if (cpu_online(cpu)) { - lock_device_hotplug(); + if (!cpu_is_hotpluggable(cpu)) + return; + lock_device_hotplug(); + if (cpu_online(cpu)) device_offline(get_cpu_device(cpu)); - unlock_device_hotplug(); - } - if (cpu_present(cpu)) + if (!cpu_online(cpu) && cpu_present(cpu)) { xen_arch_unregister_cpu(cpu); - - set_cpu_present(cpu, false); + set_cpu_present(cpu, false); + } + unlock_device_hotplug(); } static int vcpu_online(unsigned int cpu) diff --git a/drivers/xen/events/events_base.c b/drivers/xen/events/events_base.c index 08e4af04d6f2..e6c1934734b7 100644 --- a/drivers/xen/events/events_base.c +++ b/drivers/xen/events/events_base.c @@ -138,7 +138,7 @@ static int set_evtchn_to_irq(unsigned evtchn, unsigned irq) clear_evtchn_to_irq_row(row); } - evtchn_to_irq[EVTCHN_ROW(evtchn)][EVTCHN_COL(evtchn)] = irq; + evtchn_to_irq[row][col] = irq; return 0; } diff --git a/drivers/xen/gntdev.c b/drivers/xen/gntdev.c index 57390c7666e5..b0b02a501167 100644 --- a/drivers/xen/gntdev.c +++ b/drivers/xen/gntdev.c @@ -492,12 +492,19 @@ static bool in_range(struct gntdev_grant_map *map, return true; } -static void unmap_if_in_range(struct gntdev_grant_map *map, - unsigned long start, unsigned long end) +static int unmap_if_in_range(struct gntdev_grant_map *map, + unsigned long start, unsigned long end, + bool blockable) { unsigned long mstart, mend; int err; + if (!in_range(map, start, end)) + return 0; + + if (!blockable) + return -EAGAIN; + mstart = max(start, map->vma->vm_start); mend = min(end, map->vma->vm_end); pr_debug("map %d+%d (%lx %lx), range %lx %lx, mrange %lx %lx\n", @@ -508,6 +515,8 @@ static void unmap_if_in_range(struct gntdev_grant_map *map, (mstart - map->vma->vm_start) >> PAGE_SHIFT, (mend - mstart) >> PAGE_SHIFT); WARN_ON(err); + + return 0; } static int mn_invl_range_start(struct mmu_notifier *mn, @@ -519,25 +528,20 @@ static int mn_invl_range_start(struct mmu_notifier *mn, struct gntdev_grant_map *map; int ret = 0; - /* TODO do we really need a mutex here? */ if (blockable) mutex_lock(&priv->lock); else if (!mutex_trylock(&priv->lock)) return -EAGAIN; list_for_each_entry(map, &priv->maps, next) { - if (in_range(map, start, end)) { - ret = -EAGAIN; + ret = unmap_if_in_range(map, start, end, blockable); + if (ret) goto out_unlock; - } - unmap_if_in_range(map, start, end); } list_for_each_entry(map, &priv->freeable_maps, next) { - if (in_range(map, start, end)) { - ret = -EAGAIN; + ret = unmap_if_in_range(map, start, end, blockable); + if (ret) goto out_unlock; - } - unmap_if_in_range(map, start, end); } out_unlock: diff --git a/drivers/xen/grant-table.c b/drivers/xen/grant-table.c index 7bafa703a992..84575baceebc 100644 --- a/drivers/xen/grant-table.c +++ b/drivers/xen/grant-table.c @@ -1040,18 +1040,33 @@ int gnttab_map_refs(struct gnttab_map_grant_ref *map_ops, return ret; for (i = 0; i < count; i++) { - /* Retry eagain maps */ - if (map_ops[i].status == GNTST_eagain) - gnttab_retry_eagain_gop(GNTTABOP_map_grant_ref, map_ops + i, - &map_ops[i].status, __func__); - - if (map_ops[i].status == GNTST_okay) { + switch (map_ops[i].status) { + case GNTST_okay: + { struct xen_page_foreign *foreign; SetPageForeign(pages[i]); foreign = xen_page_foreign(pages[i]); foreign->domid = map_ops[i].dom; foreign->gref = map_ops[i].ref; + break; + } + + case GNTST_no_device_space: + pr_warn_ratelimited("maptrack limit reached, can't map all guest pages\n"); + break; + + case GNTST_eagain: + /* Retry eagain maps */ + gnttab_retry_eagain_gop(GNTTABOP_map_grant_ref, + map_ops + i, + &map_ops[i].status, __func__); + /* Test status in next loop iteration. */ + i--; + break; + + default: + break; } } diff --git a/drivers/xen/manage.c b/drivers/xen/manage.c index c93d8ef8df34..5bb01a62f214 100644 --- a/drivers/xen/manage.c +++ b/drivers/xen/manage.c @@ -280,9 +280,11 @@ static void sysrq_handler(struct xenbus_watch *watch, const char *path, /* * The Xenstore watch fires directly after registering it and * after a suspend/resume cycle. So ENOENT is no error but - * might happen in those cases. + * might happen in those cases. ERANGE is observed when we get + * an empty value (''), this happens when we acknowledge the + * request by writing '\0' below. */ - if (err != -ENOENT) + if (err != -ENOENT && err != -ERANGE) pr_err("Error %d reading sysrq code in control/sysrq\n", err); xenbus_transaction_end(xbt, 1); diff --git a/drivers/xen/mem-reservation.c b/drivers/xen/mem-reservation.c index 084799c6180e..3782cf070338 100644 --- a/drivers/xen/mem-reservation.c +++ b/drivers/xen/mem-reservation.c @@ -14,6 +14,10 @@ #include <xen/interface/memory.h> #include <xen/mem-reservation.h> +#include <linux/moduleparam.h> + +bool __read_mostly xen_scrub_pages = IS_ENABLED(CONFIG_XEN_SCRUB_PAGES_DEFAULT); +core_param(xen_scrub_pages, xen_scrub_pages, bool, 0); /* * Use one extent per PAGE_SIZE to avoid to break down the page into diff --git a/drivers/xen/xen-balloon.c b/drivers/xen/xen-balloon.c index 294f35ce9e46..63c1494a8d73 100644 --- a/drivers/xen/xen-balloon.c +++ b/drivers/xen/xen-balloon.c @@ -44,6 +44,7 @@ #include <xen/xenbus.h> #include <xen/features.h> #include <xen/page.h> +#include <xen/mem-reservation.h> #define PAGES2KB(_p) ((_p)<<(PAGE_SHIFT-10)) @@ -137,6 +138,7 @@ static DEVICE_ULONG_ATTR(schedule_delay, 0444, balloon_stats.schedule_delay); static DEVICE_ULONG_ATTR(max_schedule_delay, 0644, balloon_stats.max_schedule_delay); static DEVICE_ULONG_ATTR(retry_count, 0444, balloon_stats.retry_count); static DEVICE_ULONG_ATTR(max_retry_count, 0644, balloon_stats.max_retry_count); +static DEVICE_BOOL_ATTR(scrub_pages, 0644, xen_scrub_pages); static ssize_t show_target_kb(struct device *dev, struct device_attribute *attr, char *buf) @@ -203,6 +205,7 @@ static struct attribute *balloon_attrs[] = { &dev_attr_max_schedule_delay.attr.attr, &dev_attr_retry_count.attr.attr, &dev_attr_max_retry_count.attr.attr, + &dev_attr_scrub_pages.attr.attr, NULL }; diff --git a/fs/afs/proc.c b/fs/afs/proc.c index 0c3285c8db95..476dcbb79713 100644 --- a/fs/afs/proc.c +++ b/fs/afs/proc.c @@ -98,13 +98,13 @@ static int afs_proc_cells_write(struct file *file, char *buf, size_t size) goto inval; args = strchr(name, ' '); - if (!args) - goto inval; - do { - *args++ = 0; - } while(*args == ' '); - if (!*args) - goto inval; + if (args) { + do { + *args++ = 0; + } while(*args == ' '); + if (!*args) + goto inval; + } /* determine command to perform */ _debug("cmd=%s name=%s args=%s", buf, name, args); @@ -120,7 +120,6 @@ static int afs_proc_cells_write(struct file *file, char *buf, size_t size) if (test_and_set_bit(AFS_CELL_FL_NO_GC, &cell->flags)) afs_put_cell(net, cell); - printk("kAFS: Added new cell '%s'\n", name); } else { goto inval; } diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index 53af9f5253f4..2cddfe7806a4 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -1280,6 +1280,7 @@ struct btrfs_root { int send_in_progress; struct btrfs_subvolume_writers *subv_writers; atomic_t will_be_snapshotted; + atomic_t snapshot_force_cow; /* For qgroup metadata reserved space */ spinlock_t qgroup_meta_rsv_lock; @@ -3390,9 +3391,9 @@ do { \ #define btrfs_debug(fs_info, fmt, args...) \ btrfs_no_printk(fs_info, KERN_DEBUG fmt, ##args) #define btrfs_debug_in_rcu(fs_info, fmt, args...) \ - btrfs_no_printk(fs_info, KERN_DEBUG fmt, ##args) + btrfs_no_printk_in_rcu(fs_info, KERN_DEBUG fmt, ##args) #define btrfs_debug_rl_in_rcu(fs_info, fmt, args...) \ - btrfs_no_printk(fs_info, KERN_DEBUG fmt, ##args) + btrfs_no_printk_in_rcu(fs_info, KERN_DEBUG fmt, ##args) #define btrfs_debug_rl(fs_info, fmt, args...) \ btrfs_no_printk(fs_info, KERN_DEBUG fmt, ##args) #endif @@ -3404,6 +3405,13 @@ do { \ rcu_read_unlock(); \ } while (0) +#define btrfs_no_printk_in_rcu(fs_info, fmt, args...) \ +do { \ + rcu_read_lock(); \ + btrfs_no_printk(fs_info, fmt, ##args); \ + rcu_read_unlock(); \ +} while (0) + #define btrfs_printk_ratelimited(fs_info, fmt, args...) \ do { \ static DEFINE_RATELIMIT_STATE(_rs, \ diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index 5124c15705ce..05dc3c17cb62 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -1187,6 +1187,7 @@ static void __setup_root(struct btrfs_root *root, struct btrfs_fs_info *fs_info, atomic_set(&root->log_batch, 0); refcount_set(&root->refs, 1); atomic_set(&root->will_be_snapshotted, 0); + atomic_set(&root->snapshot_force_cow, 0); root->log_transid = 0; root->log_transid_committed = -1; root->last_log_commit = 0; diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index de6f75f5547b..2d9074295d7f 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -5800,7 +5800,7 @@ void btrfs_trans_release_chunk_metadata(struct btrfs_trans_handle *trans) * root: the root of the parent directory * rsv: block reservation * items: the number of items that we need do reservation - * qgroup_reserved: used to return the reserved size in qgroup + * use_global_rsv: allow fallback to the global block reservation * * This function is used to reserve the space for snapshot/subvolume * creation and deletion. Those operations are different with the @@ -5810,10 +5810,10 @@ void btrfs_trans_release_chunk_metadata(struct btrfs_trans_handle *trans) * the space reservation mechanism in start_transaction(). */ int btrfs_subvolume_reserve_metadata(struct btrfs_root *root, - struct btrfs_block_rsv *rsv, - int items, + struct btrfs_block_rsv *rsv, int items, bool use_global_rsv) { + u64 qgroup_num_bytes = 0; u64 num_bytes; int ret; struct btrfs_fs_info *fs_info = root->fs_info; @@ -5821,12 +5821,11 @@ int btrfs_subvolume_reserve_metadata(struct btrfs_root *root, if (test_bit(BTRFS_FS_QUOTA_ENABLED, &fs_info->flags)) { /* One for parent inode, two for dir entries */ - num_bytes = 3 * fs_info->nodesize; - ret = btrfs_qgroup_reserve_meta_prealloc(root, num_bytes, true); + qgroup_num_bytes = 3 * fs_info->nodesize; + ret = btrfs_qgroup_reserve_meta_prealloc(root, + qgroup_num_bytes, true); if (ret) return ret; - } else { - num_bytes = 0; } num_bytes = btrfs_calc_trans_metadata_size(fs_info, items); @@ -5838,8 +5837,8 @@ int btrfs_subvolume_reserve_metadata(struct btrfs_root *root, if (ret == -ENOSPC && use_global_rsv) ret = btrfs_block_rsv_migrate(global_rsv, rsv, num_bytes, 1); - if (ret && num_bytes) - btrfs_qgroup_free_meta_prealloc(root, num_bytes); + if (ret && qgroup_num_bytes) + btrfs_qgroup_free_meta_prealloc(root, qgroup_num_bytes); return ret; } diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 9357a19d2bff..3ea5339603cf 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -1271,7 +1271,7 @@ static noinline int run_delalloc_nocow(struct inode *inode, u64 disk_num_bytes; u64 ram_bytes; int extent_type; - int ret, err; + int ret; int type; int nocow; int check_prev = 1; @@ -1403,11 +1403,8 @@ next_slot: * if there are pending snapshots for this root, * we fall into common COW way. */ - if (!nolock) { - err = btrfs_start_write_no_snapshotting(root); - if (!err) - goto out_check; - } + if (!nolock && atomic_read(&root->snapshot_force_cow)) + goto out_check; /* * force cow if csum exists in the range. * this ensure that csum for a given extent are @@ -1416,9 +1413,6 @@ next_slot: ret = csum_exist_in_range(fs_info, disk_bytenr, num_bytes); if (ret) { - if (!nolock) - btrfs_end_write_no_snapshotting(root); - /* * ret could be -EIO if the above fails to read * metadata. @@ -1431,11 +1425,8 @@ next_slot: WARN_ON_ONCE(nolock); goto out_check; } - if (!btrfs_inc_nocow_writers(fs_info, disk_bytenr)) { - if (!nolock) - btrfs_end_write_no_snapshotting(root); + if (!btrfs_inc_nocow_writers(fs_info, disk_bytenr)) goto out_check; - } nocow = 1; } else if (extent_type == BTRFS_FILE_EXTENT_INLINE) { extent_end = found_key.offset + @@ -1448,8 +1439,6 @@ next_slot: out_check: if (extent_end <= start) { path->slots[0]++; - if (!nolock && nocow) - btrfs_end_write_no_snapshotting(root); if (nocow) btrfs_dec_nocow_writers(fs_info, disk_bytenr); goto next_slot; @@ -1471,8 +1460,6 @@ out_check: end, page_started, nr_written, 1, NULL); if (ret) { - if (!nolock && nocow) - btrfs_end_write_no_snapshotting(root); if (nocow) btrfs_dec_nocow_writers(fs_info, disk_bytenr); @@ -1492,8 +1479,6 @@ out_check: ram_bytes, BTRFS_COMPRESS_NONE, BTRFS_ORDERED_PREALLOC); if (IS_ERR(em)) { - if (!nolock && nocow) - btrfs_end_write_no_snapshotting(root); if (nocow) btrfs_dec_nocow_writers(fs_info, disk_bytenr); @@ -1532,8 +1517,6 @@ out_check: EXTENT_CLEAR_DATA_RESV, PAGE_UNLOCK | PAGE_SET_PRIVATE2); - if (!nolock && nocow) - btrfs_end_write_no_snapshotting(root); cur_offset = extent_end; /* @@ -6639,6 +6622,8 @@ static int btrfs_link(struct dentry *old_dentry, struct inode *dir, drop_inode = 1; } else { struct dentry *parent = dentry->d_parent; + int ret; + err = btrfs_update_inode(trans, root, inode); if (err) goto fail; @@ -6652,7 +6637,12 @@ static int btrfs_link(struct dentry *old_dentry, struct inode *dir, goto fail; } d_instantiate(dentry, inode); - btrfs_log_new_name(trans, BTRFS_I(inode), NULL, parent); + ret = btrfs_log_new_name(trans, BTRFS_I(inode), NULL, parent, + true, NULL); + if (ret == BTRFS_NEED_TRANS_COMMIT) { + err = btrfs_commit_transaction(trans); + trans = NULL; + } } fail: @@ -9388,14 +9378,21 @@ static int btrfs_rename_exchange(struct inode *old_dir, u64 new_idx = 0; u64 root_objectid; int ret; - int ret2; bool root_log_pinned = false; bool dest_log_pinned = false; + struct btrfs_log_ctx ctx_root; + struct btrfs_log_ctx ctx_dest; + bool sync_log_root = false; + bool sync_log_dest = false; + bool commit_transaction = false; /* we only allow rename subvolume link between subvolumes */ if (old_ino != BTRFS_FIRST_FREE_OBJECTID && root != dest) return -EXDEV; + btrfs_init_log_ctx(&ctx_root, old_inode); + btrfs_init_log_ctx(&ctx_dest, new_inode); + /* close the race window with snapshot create/destroy ioctl */ if (old_ino == BTRFS_FIRST_FREE_OBJECTID) down_read(&fs_info->subvol_sem); @@ -9542,15 +9539,29 @@ static int btrfs_rename_exchange(struct inode *old_dir, if (root_log_pinned) { parent = new_dentry->d_parent; - btrfs_log_new_name(trans, BTRFS_I(old_inode), BTRFS_I(old_dir), - parent); + ret = btrfs_log_new_name(trans, BTRFS_I(old_inode), + BTRFS_I(old_dir), parent, + false, &ctx_root); + if (ret == BTRFS_NEED_LOG_SYNC) + sync_log_root = true; + else if (ret == BTRFS_NEED_TRANS_COMMIT) + commit_transaction = true; + ret = 0; btrfs_end_log_trans(root); root_log_pinned = false; } if (dest_log_pinned) { - parent = old_dentry->d_parent; - btrfs_log_new_name(trans, BTRFS_I(new_inode), BTRFS_I(new_dir), - parent); + if (!commit_transaction) { + parent = old_dentry->d_parent; + ret = btrfs_log_new_name(trans, BTRFS_I(new_inode), + BTRFS_I(new_dir), parent, + false, &ctx_dest); + if (ret == BTRFS_NEED_LOG_SYNC) + sync_log_dest = true; + else if (ret == BTRFS_NEED_TRANS_COMMIT) + commit_transaction = true; + ret = 0; + } btrfs_end_log_trans(dest); dest_log_pinned = false; } @@ -9583,8 +9594,26 @@ out_fail: dest_log_pinned = false; } } - ret2 = btrfs_end_transaction(trans); - ret = ret ? ret : ret2; + if (!ret && sync_log_root && !commit_transaction) { + ret = btrfs_sync_log(trans, BTRFS_I(old_inode)->root, + &ctx_root); + if (ret) + commit_transaction = true; + } + if (!ret && sync_log_dest && !commit_transaction) { + ret = btrfs_sync_log(trans, BTRFS_I(new_inode)->root, + &ctx_dest); + if (ret) + commit_transaction = true; + } + if (commit_transaction) { + ret = btrfs_commit_transaction(trans); + } else { + int ret2; + + ret2 = btrfs_end_transaction(trans); + ret = ret ? ret : ret2; + } out_notrans: if (new_ino == BTRFS_FIRST_FREE_OBJECTID) up_read(&fs_info->subvol_sem); @@ -9661,6 +9690,9 @@ static int btrfs_rename(struct inode *old_dir, struct dentry *old_dentry, int ret; u64 old_ino = btrfs_ino(BTRFS_I(old_inode)); bool log_pinned = false; + struct btrfs_log_ctx ctx; + bool sync_log = false; + bool commit_transaction = false; if (btrfs_ino(BTRFS_I(new_dir)) == BTRFS_EMPTY_SUBVOL_DIR_OBJECTID) return -EPERM; @@ -9818,8 +9850,15 @@ static int btrfs_rename(struct inode *old_dir, struct dentry *old_dentry, if (log_pinned) { struct dentry *parent = new_dentry->d_parent; - btrfs_log_new_name(trans, BTRFS_I(old_inode), BTRFS_I(old_dir), - parent); + btrfs_init_log_ctx(&ctx, old_inode); + ret = btrfs_log_new_name(trans, BTRFS_I(old_inode), + BTRFS_I(old_dir), parent, + false, &ctx); + if (ret == BTRFS_NEED_LOG_SYNC) + sync_log = true; + else if (ret == BTRFS_NEED_TRANS_COMMIT) + commit_transaction = true; + ret = 0; btrfs_end_log_trans(root); log_pinned = false; } @@ -9856,7 +9895,19 @@ out_fail: btrfs_end_log_trans(root); log_pinned = false; } - btrfs_end_transaction(trans); + if (!ret && sync_log) { + ret = btrfs_sync_log(trans, BTRFS_I(old_inode)->root, &ctx); + if (ret) + commit_transaction = true; + } + if (commit_transaction) { + ret = btrfs_commit_transaction(trans); + } else { + int ret2; + + ret2 = btrfs_end_transaction(trans); + ret = ret ? ret : ret2; + } out_notrans: if (old_ino == BTRFS_FIRST_FREE_OBJECTID) up_read(&fs_info->subvol_sem); diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index 63600dc2ac4c..d60b6caf09e8 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -747,6 +747,7 @@ static int create_snapshot(struct btrfs_root *root, struct inode *dir, struct btrfs_pending_snapshot *pending_snapshot; struct btrfs_trans_handle *trans; int ret; + bool snapshot_force_cow = false; if (!test_bit(BTRFS_ROOT_REF_COWS, &root->state)) return -EINVAL; @@ -763,6 +764,11 @@ static int create_snapshot(struct btrfs_root *root, struct inode *dir, goto free_pending; } + /* + * Force new buffered writes to reserve space even when NOCOW is + * possible. This is to avoid later writeback (running dealloc) to + * fallback to COW mode and unexpectedly fail with ENOSPC. + */ atomic_inc(&root->will_be_snapshotted); smp_mb__after_atomic(); /* wait for no snapshot writes */ @@ -773,6 +779,14 @@ static int create_snapshot(struct btrfs_root *root, struct inode *dir, if (ret) goto dec_and_free; + /* + * All previous writes have started writeback in NOCOW mode, so now + * we force future writes to fallback to COW mode during snapshot + * creation. + */ + atomic_inc(&root->snapshot_force_cow); + snapshot_force_cow = true; + btrfs_wait_ordered_extents(root, U64_MAX, 0, (u64)-1); btrfs_init_block_rsv(&pending_snapshot->block_rsv, @@ -837,6 +851,8 @@ static int create_snapshot(struct btrfs_root *root, struct inode *dir, fail: btrfs_subvolume_release_metadata(fs_info, &pending_snapshot->block_rsv); dec_and_free: + if (snapshot_force_cow) + atomic_dec(&root->snapshot_force_cow); if (atomic_dec_and_test(&root->will_be_snapshotted)) wake_up_var(&root->will_be_snapshotted); free_pending: @@ -3453,6 +3469,25 @@ static int btrfs_extent_same_range(struct inode *src, u64 loff, u64 olen, same_lock_start = min_t(u64, loff, dst_loff); same_lock_len = max_t(u64, loff, dst_loff) + len - same_lock_start; + } else { + /* + * If the source and destination inodes are different, the + * source's range end offset matches the source's i_size, that + * i_size is not a multiple of the sector size, and the + * destination range does not go past the destination's i_size, + * we must round down the length to the nearest sector size + * multiple. If we don't do this adjustment we end replacing + * with zeroes the bytes in the range that starts at the + * deduplication range's end offset and ends at the next sector + * size multiple. + */ + if (loff + olen == i_size_read(src) && + dst_loff + len < i_size_read(dst)) { + const u64 sz = BTRFS_I(src)->root->fs_info->sectorsize; + + len = round_down(i_size_read(src), sz) - loff; + olen = len; + } } again: diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c index 4353bb69bb86..d4917c0cddf5 100644 --- a/fs/btrfs/qgroup.c +++ b/fs/btrfs/qgroup.c @@ -1019,10 +1019,9 @@ out_add_root: spin_unlock(&fs_info->qgroup_lock); ret = btrfs_commit_transaction(trans); - if (ret) { - trans = NULL; + trans = NULL; + if (ret) goto out_free_path; - } ret = qgroup_rescan_init(fs_info, 0, 1); if (!ret) { diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c index 1650dc44a5e3..3c2ae0e4f25a 100644 --- a/fs/btrfs/tree-log.c +++ b/fs/btrfs/tree-log.c @@ -6025,14 +6025,25 @@ void btrfs_record_snapshot_destroy(struct btrfs_trans_handle *trans, * Call this after adding a new name for a file and it will properly * update the log to reflect the new name. * - * It will return zero if all goes well, and it will return 1 if a - * full transaction commit is required. + * @ctx can not be NULL when @sync_log is false, and should be NULL when it's + * true (because it's not used). + * + * Return value depends on whether @sync_log is true or false. + * When true: returns BTRFS_NEED_TRANS_COMMIT if the transaction needs to be + * committed by the caller, and BTRFS_DONT_NEED_TRANS_COMMIT + * otherwise. + * When false: returns BTRFS_DONT_NEED_LOG_SYNC if the caller does not need to + * to sync the log, BTRFS_NEED_LOG_SYNC if it needs to sync the log, + * or BTRFS_NEED_TRANS_COMMIT if the transaction needs to be + * committed (without attempting to sync the log). */ int btrfs_log_new_name(struct btrfs_trans_handle *trans, struct btrfs_inode *inode, struct btrfs_inode *old_dir, - struct dentry *parent) + struct dentry *parent, + bool sync_log, struct btrfs_log_ctx *ctx) { struct btrfs_fs_info *fs_info = trans->fs_info; + int ret; /* * this will force the logging code to walk the dentry chain @@ -6047,9 +6058,34 @@ int btrfs_log_new_name(struct btrfs_trans_handle *trans, */ if (inode->logged_trans <= fs_info->last_trans_committed && (!old_dir || old_dir->logged_trans <= fs_info->last_trans_committed)) - return 0; + return sync_log ? BTRFS_DONT_NEED_TRANS_COMMIT : + BTRFS_DONT_NEED_LOG_SYNC; + + if (sync_log) { + struct btrfs_log_ctx ctx2; + + btrfs_init_log_ctx(&ctx2, &inode->vfs_inode); + ret = btrfs_log_inode_parent(trans, inode, parent, 0, LLONG_MAX, + LOG_INODE_EXISTS, &ctx2); + if (ret == BTRFS_NO_LOG_SYNC) + return BTRFS_DONT_NEED_TRANS_COMMIT; + else if (ret) + return BTRFS_NEED_TRANS_COMMIT; + + ret = btrfs_sync_log(trans, inode->root, &ctx2); + if (ret) + return BTRFS_NEED_TRANS_COMMIT; + return BTRFS_DONT_NEED_TRANS_COMMIT; + } + + ASSERT(ctx); + ret = btrfs_log_inode_parent(trans, inode, parent, 0, LLONG_MAX, + LOG_INODE_EXISTS, ctx); + if (ret == BTRFS_NO_LOG_SYNC) + return BTRFS_DONT_NEED_LOG_SYNC; + else if (ret) + return BTRFS_NEED_TRANS_COMMIT; - return btrfs_log_inode_parent(trans, inode, parent, 0, LLONG_MAX, - LOG_INODE_EXISTS, NULL); + return BTRFS_NEED_LOG_SYNC; } diff --git a/fs/btrfs/tree-log.h b/fs/btrfs/tree-log.h index 122e68b89a5a..7ab9bb88a639 100644 --- a/fs/btrfs/tree-log.h +++ b/fs/btrfs/tree-log.h @@ -71,8 +71,16 @@ void btrfs_record_unlink_dir(struct btrfs_trans_handle *trans, int for_rename); void btrfs_record_snapshot_destroy(struct btrfs_trans_handle *trans, struct btrfs_inode *dir); +/* Return values for btrfs_log_new_name() */ +enum { + BTRFS_DONT_NEED_TRANS_COMMIT, + BTRFS_NEED_TRANS_COMMIT, + BTRFS_DONT_NEED_LOG_SYNC, + BTRFS_NEED_LOG_SYNC, +}; int btrfs_log_new_name(struct btrfs_trans_handle *trans, struct btrfs_inode *inode, struct btrfs_inode *old_dir, - struct dentry *parent); + struct dentry *parent, + bool sync_log, struct btrfs_log_ctx *ctx); #endif diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index da86706123ff..f4405e430da6 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -4491,7 +4491,12 @@ again: /* Now btrfs_update_device() will change the on-disk size. */ ret = btrfs_update_device(trans, device); - btrfs_end_transaction(trans); + if (ret < 0) { + btrfs_abort_transaction(trans, ret); + btrfs_end_transaction(trans); + } else { + ret = btrfs_commit_transaction(trans); + } done: btrfs_free_path(path); if (ret) { diff --git a/fs/ceph/super.c b/fs/ceph/super.c index 43ca3b763875..eab1359d0553 100644 --- a/fs/ceph/super.c +++ b/fs/ceph/super.c @@ -602,6 +602,8 @@ static int extra_mon_dispatch(struct ceph_client *client, struct ceph_msg *msg) /* * create a new fs client + * + * Success or not, this function consumes @fsopt and @opt. */ static struct ceph_fs_client *create_fs_client(struct ceph_mount_options *fsopt, struct ceph_options *opt) @@ -609,17 +611,20 @@ static struct ceph_fs_client *create_fs_client(struct ceph_mount_options *fsopt, struct ceph_fs_client *fsc; int page_count; size_t size; - int err = -ENOMEM; + int err; fsc = kzalloc(sizeof(*fsc), GFP_KERNEL); - if (!fsc) - return ERR_PTR(-ENOMEM); + if (!fsc) { + err = -ENOMEM; + goto fail; + } fsc->client = ceph_create_client(opt, fsc); if (IS_ERR(fsc->client)) { err = PTR_ERR(fsc->client); goto fail; } + opt = NULL; /* fsc->client now owns this */ fsc->client->extra_mon_dispatch = extra_mon_dispatch; fsc->client->osdc.abort_on_full = true; @@ -677,6 +682,9 @@ fail_client: ceph_destroy_client(fsc->client); fail: kfree(fsc); + if (opt) + ceph_destroy_options(opt); + destroy_mount_options(fsopt); return ERR_PTR(err); } @@ -1042,8 +1050,6 @@ static struct dentry *ceph_mount(struct file_system_type *fs_type, fsc = create_fs_client(fsopt, opt); if (IS_ERR(fsc)) { res = ERR_CAST(fsc); - destroy_mount_options(fsopt); - ceph_destroy_options(opt); goto out_final; } diff --git a/fs/cifs/Kconfig b/fs/cifs/Kconfig index 35c83fe7dba0..abcd78e332fe 100644 --- a/fs/cifs/Kconfig +++ b/fs/cifs/Kconfig @@ -6,6 +6,7 @@ config CIFS select CRYPTO_MD4 select CRYPTO_MD5 select CRYPTO_SHA256 + select CRYPTO_SHA512 select CRYPTO_CMAC select CRYPTO_HMAC select CRYPTO_ARC4 diff --git a/fs/cifs/cifs_unicode.c b/fs/cifs/cifs_unicode.c index b380e0871372..a2b2355e7f01 100644 --- a/fs/cifs/cifs_unicode.c +++ b/fs/cifs/cifs_unicode.c @@ -105,9 +105,6 @@ convert_sfm_char(const __u16 src_char, char *target) case SFM_LESSTHAN: *target = '<'; break; - case SFM_SLASH: - *target = '\\'; - break; case SFM_SPACE: *target = ' '; break; diff --git a/fs/cifs/cifssmb.c b/fs/cifs/cifssmb.c index dc2f4cf08fe9..5657b79dbc99 100644 --- a/fs/cifs/cifssmb.c +++ b/fs/cifs/cifssmb.c @@ -601,10 +601,15 @@ CIFSSMBNegotiate(const unsigned int xid, struct cifs_ses *ses) } count = 0; + /* + * We know that all the name entries in the protocols array + * are short (< 16 bytes anyway) and are NUL terminated. + */ for (i = 0; i < CIFS_NUM_PROT; i++) { - strncpy(pSMB->DialectsArray+count, protocols[i].name, 16); - count += strlen(protocols[i].name) + 1; - /* null at end of source and target buffers anyway */ + size_t len = strlen(protocols[i].name) + 1; + + memcpy(pSMB->DialectsArray+count, protocols[i].name, len); + count += len; } inc_rfc1001_len(pSMB, count); pSMB->ByteCount = cpu_to_le16(count); diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c index c832a8a1970a..7aa08dba4719 100644 --- a/fs/cifs/connect.c +++ b/fs/cifs/connect.c @@ -2547,7 +2547,7 @@ cifs_setup_ipc(struct cifs_ses *ses, struct smb_vol *volume_info) if (tcon == NULL) return -ENOMEM; - snprintf(unc, sizeof(unc), "\\\\%s\\IPC$", ses->serverName); + snprintf(unc, sizeof(unc), "\\\\%s\\IPC$", ses->server->hostname); /* cannot fail */ nls_codepage = load_nls_default(); diff --git a/fs/cifs/inode.c b/fs/cifs/inode.c index d32eaa4b2437..6e8765f44508 100644 --- a/fs/cifs/inode.c +++ b/fs/cifs/inode.c @@ -467,6 +467,8 @@ cifs_sfu_type(struct cifs_fattr *fattr, const char *path, oparms.cifs_sb = cifs_sb; oparms.desired_access = GENERIC_READ; oparms.create_options = CREATE_NOT_DIR; + if (backup_cred(cifs_sb)) + oparms.create_options |= CREATE_OPEN_BACKUP_INTENT; oparms.disposition = FILE_OPEN; oparms.path = path; oparms.fid = &fid; diff --git a/fs/cifs/misc.c b/fs/cifs/misc.c index dacb2c05674c..6926685e513c 100644 --- a/fs/cifs/misc.c +++ b/fs/cifs/misc.c @@ -402,9 +402,17 @@ is_valid_oplock_break(char *buffer, struct TCP_Server_Info *srv) (struct smb_com_transaction_change_notify_rsp *)buf; struct file_notify_information *pnotify; __u32 data_offset = 0; + size_t len = srv->total_read - sizeof(pSMBr->hdr.smb_buf_length); + if (get_bcc(buf) > sizeof(struct file_notify_information)) { data_offset = le32_to_cpu(pSMBr->DataOffset); + if (data_offset > + len - sizeof(struct file_notify_information)) { + cifs_dbg(FYI, "invalid data_offset %u\n", + data_offset); + return true; + } pnotify = (struct file_notify_information *) ((char *)&pSMBr->hdr.Protocol + data_offset); cifs_dbg(FYI, "dnotify on %s Action: 0x%x\n", diff --git a/fs/cifs/readdir.c b/fs/cifs/readdir.c index eeab81c9452f..e169e1a5fd35 100644 --- a/fs/cifs/readdir.c +++ b/fs/cifs/readdir.c @@ -376,8 +376,15 @@ static char *nxt_dir_entry(char *old_entry, char *end_of_smb, int level) new_entry = old_entry + sizeof(FIND_FILE_STANDARD_INFO) + pfData->FileNameLength; - } else - new_entry = old_entry + le32_to_cpu(pDirInfo->NextEntryOffset); + } else { + u32 next_offset = le32_to_cpu(pDirInfo->NextEntryOffset); + + if (old_entry + next_offset < old_entry) { + cifs_dbg(VFS, "invalid offset %u\n", next_offset); + return NULL; + } + new_entry = old_entry + next_offset; + } cifs_dbg(FYI, "new entry %p old entry %p\n", new_entry, old_entry); /* validate that new_entry is not past end of SMB */ if (new_entry >= end_of_smb) { diff --git a/fs/cifs/smb2misc.c b/fs/cifs/smb2misc.c index db0453660ff6..6a9c47541c53 100644 --- a/fs/cifs/smb2misc.c +++ b/fs/cifs/smb2misc.c @@ -248,16 +248,20 @@ smb2_check_message(char *buf, unsigned int len, struct TCP_Server_Info *srvr) * MacOS server pads after SMB2.1 write response with 3 bytes * of junk. Other servers match RFC1001 len to actual * SMB2/SMB3 frame length (header + smb2 response specific data) - * Some windows servers do too when compounding is used. - * Log the server error (once), but allow it and continue + * Some windows servers also pad up to 8 bytes when compounding. + * If pad is longer than eight bytes, log the server behavior + * (once), since may indicate a problem but allow it and continue * since the frame is parseable. */ if (clc_len < len) { - printk_once(KERN_WARNING - "SMB2 server sent bad RFC1001 len %d not %d\n", - len, clc_len); + pr_warn_once( + "srv rsp padded more than expected. Length %d not %d for cmd:%d mid:%llu\n", + len, clc_len, command, mid); return 0; } + pr_warn_once( + "srv rsp too short, len %d not %d. cmd:%d mid:%llu\n", + len, clc_len, command, mid); return 1; } diff --git a/fs/cifs/smb2ops.c b/fs/cifs/smb2ops.c index 247a98e6c856..d954ce36b473 100644 --- a/fs/cifs/smb2ops.c +++ b/fs/cifs/smb2ops.c @@ -630,7 +630,10 @@ smb2_is_path_accessible(const unsigned int xid, struct cifs_tcon *tcon, oparms.tcon = tcon; oparms.desired_access = FILE_READ_ATTRIBUTES; oparms.disposition = FILE_OPEN; - oparms.create_options = 0; + if (backup_cred(cifs_sb)) + oparms.create_options = CREATE_OPEN_BACKUP_INTENT; + else + oparms.create_options = 0; oparms.fid = &fid; oparms.reconnect = false; @@ -779,7 +782,10 @@ smb2_query_eas(const unsigned int xid, struct cifs_tcon *tcon, oparms.tcon = tcon; oparms.desired_access = FILE_READ_EA; oparms.disposition = FILE_OPEN; - oparms.create_options = 0; + if (backup_cred(cifs_sb)) + oparms.create_options = CREATE_OPEN_BACKUP_INTENT; + else + oparms.create_options = 0; oparms.fid = &fid; oparms.reconnect = false; @@ -858,7 +864,10 @@ smb2_set_ea(const unsigned int xid, struct cifs_tcon *tcon, oparms.tcon = tcon; oparms.desired_access = FILE_WRITE_EA; oparms.disposition = FILE_OPEN; - oparms.create_options = 0; + if (backup_cred(cifs_sb)) + oparms.create_options = CREATE_OPEN_BACKUP_INTENT; + else + oparms.create_options = 0; oparms.fid = &fid; oparms.reconnect = false; @@ -1453,7 +1462,10 @@ smb2_query_dir_first(const unsigned int xid, struct cifs_tcon *tcon, oparms.tcon = tcon; oparms.desired_access = FILE_READ_ATTRIBUTES | FILE_READ_DATA; oparms.disposition = FILE_OPEN; - oparms.create_options = 0; + if (backup_cred(cifs_sb)) + oparms.create_options = CREATE_OPEN_BACKUP_INTENT; + else + oparms.create_options = 0; oparms.fid = fid; oparms.reconnect = false; @@ -1857,7 +1869,10 @@ smb2_query_symlink(const unsigned int xid, struct cifs_tcon *tcon, oparms.tcon = tcon; oparms.desired_access = FILE_READ_ATTRIBUTES; oparms.disposition = FILE_OPEN; - oparms.create_options = 0; + if (backup_cred(cifs_sb)) + oparms.create_options = CREATE_OPEN_BACKUP_INTENT; + else + oparms.create_options = 0; oparms.fid = &fid; oparms.reconnect = false; @@ -3639,7 +3654,7 @@ struct smb_version_values smb21_values = { struct smb_version_values smb3any_values = { .version_string = SMB3ANY_VERSION_STRING, .protocol_id = SMB302_PROT_ID, /* doesn't matter, send protocol array */ - .req_capabilities = SMB2_GLOBAL_CAP_DFS | SMB2_GLOBAL_CAP_LEASING | SMB2_GLOBAL_CAP_LARGE_MTU | SMB2_GLOBAL_CAP_PERSISTENT_HANDLES | SMB2_GLOBAL_CAP_ENCRYPTION, + .req_capabilities = SMB2_GLOBAL_CAP_DFS | SMB2_GLOBAL_CAP_LEASING | SMB2_GLOBAL_CAP_LARGE_MTU | SMB2_GLOBAL_CAP_PERSISTENT_HANDLES | SMB2_GLOBAL_CAP_ENCRYPTION | SMB2_GLOBAL_CAP_DIRECTORY_LEASING, .large_lock_type = 0, .exclusive_lock_type = SMB2_LOCKFLAG_EXCLUSIVE_LOCK, .shared_lock_type = SMB2_LOCKFLAG_SHARED_LOCK, @@ -3660,7 +3675,7 @@ struct smb_version_values smb3any_values = { struct smb_version_values smbdefault_values = { .version_string = SMBDEFAULT_VERSION_STRING, .protocol_id = SMB302_PROT_ID, /* doesn't matter, send protocol array */ - .req_capabilities = SMB2_GLOBAL_CAP_DFS | SMB2_GLOBAL_CAP_LEASING | SMB2_GLOBAL_CAP_LARGE_MTU | SMB2_GLOBAL_CAP_PERSISTENT_HANDLES | SMB2_GLOBAL_CAP_ENCRYPTION, + .req_capabilities = SMB2_GLOBAL_CAP_DFS | SMB2_GLOBAL_CAP_LEASING | SMB2_GLOBAL_CAP_LARGE_MTU | SMB2_GLOBAL_CAP_PERSISTENT_HANDLES | SMB2_GLOBAL_CAP_ENCRYPTION | SMB2_GLOBAL_CAP_DIRECTORY_LEASING, .large_lock_type = 0, .exclusive_lock_type = SMB2_LOCKFLAG_EXCLUSIVE_LOCK, .shared_lock_type = SMB2_LOCKFLAG_SHARED_LOCK, @@ -3681,7 +3696,7 @@ struct smb_version_values smbdefault_values = { struct smb_version_values smb30_values = { .version_string = SMB30_VERSION_STRING, .protocol_id = SMB30_PROT_ID, - .req_capabilities = SMB2_GLOBAL_CAP_DFS | SMB2_GLOBAL_CAP_LEASING | SMB2_GLOBAL_CAP_LARGE_MTU | SMB2_GLOBAL_CAP_PERSISTENT_HANDLES | SMB2_GLOBAL_CAP_ENCRYPTION, + .req_capabilities = SMB2_GLOBAL_CAP_DFS | SMB2_GLOBAL_CAP_LEASING | SMB2_GLOBAL_CAP_LARGE_MTU | SMB2_GLOBAL_CAP_PERSISTENT_HANDLES | SMB2_GLOBAL_CAP_ENCRYPTION | SMB2_GLOBAL_CAP_DIRECTORY_LEASING, .large_lock_type = 0, .exclusive_lock_type = SMB2_LOCKFLAG_EXCLUSIVE_LOCK, .shared_lock_type = SMB2_LOCKFLAG_SHARED_LOCK, @@ -3702,7 +3717,7 @@ struct smb_version_values smb30_values = { struct smb_version_values smb302_values = { .version_string = SMB302_VERSION_STRING, .protocol_id = SMB302_PROT_ID, - .req_capabilities = SMB2_GLOBAL_CAP_DFS | SMB2_GLOBAL_CAP_LEASING | SMB2_GLOBAL_CAP_LARGE_MTU | SMB2_GLOBAL_CAP_PERSISTENT_HANDLES | SMB2_GLOBAL_CAP_ENCRYPTION, + .req_capabilities = SMB2_GLOBAL_CAP_DFS | SMB2_GLOBAL_CAP_LEASING | SMB2_GLOBAL_CAP_LARGE_MTU | SMB2_GLOBAL_CAP_PERSISTENT_HANDLES | SMB2_GLOBAL_CAP_ENCRYPTION | SMB2_GLOBAL_CAP_DIRECTORY_LEASING, .large_lock_type = 0, .exclusive_lock_type = SMB2_LOCKFLAG_EXCLUSIVE_LOCK, .shared_lock_type = SMB2_LOCKFLAG_SHARED_LOCK, @@ -3723,7 +3738,7 @@ struct smb_version_values smb302_values = { struct smb_version_values smb311_values = { .version_string = SMB311_VERSION_STRING, .protocol_id = SMB311_PROT_ID, - .req_capabilities = SMB2_GLOBAL_CAP_DFS | SMB2_GLOBAL_CAP_LEASING | SMB2_GLOBAL_CAP_LARGE_MTU | SMB2_GLOBAL_CAP_PERSISTENT_HANDLES | SMB2_GLOBAL_CAP_ENCRYPTION, + .req_capabilities = SMB2_GLOBAL_CAP_DFS | SMB2_GLOBAL_CAP_LEASING | SMB2_GLOBAL_CAP_LARGE_MTU | SMB2_GLOBAL_CAP_PERSISTENT_HANDLES | SMB2_GLOBAL_CAP_ENCRYPTION | SMB2_GLOBAL_CAP_DIRECTORY_LEASING, .large_lock_type = 0, .exclusive_lock_type = SMB2_LOCKFLAG_EXCLUSIVE_LOCK, .shared_lock_type = SMB2_LOCKFLAG_SHARED_LOCK, diff --git a/fs/cifs/smb2pdu.c b/fs/cifs/smb2pdu.c index 5740aa809be6..f54d07bda067 100644 --- a/fs/cifs/smb2pdu.c +++ b/fs/cifs/smb2pdu.c @@ -2178,6 +2178,9 @@ SMB2_open_init(struct cifs_tcon *tcon, struct smb_rqst *rqst, __u8 *oplock, if (!(server->capabilities & SMB2_GLOBAL_CAP_LEASING) || *oplock == SMB2_OPLOCK_LEVEL_NONE) req->RequestedOplockLevel = *oplock; + else if (!(server->capabilities & SMB2_GLOBAL_CAP_DIRECTORY_LEASING) && + (oparms->create_options & CREATE_NOT_FILE)) + req->RequestedOplockLevel = *oplock; /* no srv lease support */ else { rc = add_lease_context(server, iov, &n_iov, oparms->fid->lease_key, oplock); @@ -2456,14 +2459,14 @@ SMB2_ioctl(const unsigned int xid, struct cifs_tcon *tcon, u64 persistent_fid, /* We check for obvious errors in the output buffer length and offset */ if (*plen == 0) goto ioctl_exit; /* server returned no data */ - else if (*plen > 0xFF00) { + else if (*plen > rsp_iov.iov_len || *plen > 0xFF00) { cifs_dbg(VFS, "srv returned invalid ioctl length: %d\n", *plen); *plen = 0; rc = -EIO; goto ioctl_exit; } - if (rsp_iov.iov_len < le32_to_cpu(rsp->OutputOffset) + *plen) { + if (rsp_iov.iov_len - *plen < le32_to_cpu(rsp->OutputOffset)) { cifs_dbg(VFS, "Malformed ioctl resp: len %d offset %d\n", *plen, le32_to_cpu(rsp->OutputOffset)); *plen = 0; @@ -3574,33 +3577,38 @@ num_entries(char *bufstart, char *end_of_buf, char **lastentry, size_t size) int len; unsigned int entrycount = 0; unsigned int next_offset = 0; - FILE_DIRECTORY_INFO *entryptr; + char *entryptr; + FILE_DIRECTORY_INFO *dir_info; if (bufstart == NULL) return 0; - entryptr = (FILE_DIRECTORY_INFO *)bufstart; + entryptr = bufstart; while (1) { - entryptr = (FILE_DIRECTORY_INFO *) - ((char *)entryptr + next_offset); - - if ((char *)entryptr + size > end_of_buf) { + if (entryptr + next_offset < entryptr || + entryptr + next_offset > end_of_buf || + entryptr + next_offset + size > end_of_buf) { cifs_dbg(VFS, "malformed search entry would overflow\n"); break; } - len = le32_to_cpu(entryptr->FileNameLength); - if ((char *)entryptr + len + size > end_of_buf) { + entryptr = entryptr + next_offset; + dir_info = (FILE_DIRECTORY_INFO *)entryptr; + + len = le32_to_cpu(dir_info->FileNameLength); + if (entryptr + len < entryptr || + entryptr + len > end_of_buf || + entryptr + len + size > end_of_buf) { cifs_dbg(VFS, "directory entry name would overflow frame end of buf %p\n", end_of_buf); break; } - *lastentry = (char *)entryptr; + *lastentry = entryptr; entrycount++; - next_offset = le32_to_cpu(entryptr->NextEntryOffset); + next_offset = le32_to_cpu(dir_info->NextEntryOffset); if (!next_offset) break; } diff --git a/fs/ext4/dir.c b/fs/ext4/dir.c index e2902d394f1b..f93f9881ec18 100644 --- a/fs/ext4/dir.c +++ b/fs/ext4/dir.c @@ -76,7 +76,7 @@ int __ext4_check_dir_entry(const char *function, unsigned int line, else if (unlikely(rlen < EXT4_DIR_REC_LEN(de->name_len))) error_msg = "rec_len is too small for name_len"; else if (unlikely(((char *) de - buf) + rlen > size)) - error_msg = "directory entry across range"; + error_msg = "directory entry overrun"; else if (unlikely(le32_to_cpu(de->inode) > le32_to_cpu(EXT4_SB(dir->i_sb)->s_es->s_inodes_count))) error_msg = "inode out of bounds"; @@ -85,18 +85,16 @@ int __ext4_check_dir_entry(const char *function, unsigned int line, if (filp) ext4_error_file(filp, function, line, bh->b_blocknr, - "bad entry in directory: %s - offset=%u(%u), " - "inode=%u, rec_len=%d, name_len=%d", - error_msg, (unsigned) (offset % size), - offset, le32_to_cpu(de->inode), - rlen, de->name_len); + "bad entry in directory: %s - offset=%u, " + "inode=%u, rec_len=%d, name_len=%d, size=%d", + error_msg, offset, le32_to_cpu(de->inode), + rlen, de->name_len, size); else ext4_error_inode(dir, function, line, bh->b_blocknr, - "bad entry in directory: %s - offset=%u(%u), " - "inode=%u, rec_len=%d, name_len=%d", - error_msg, (unsigned) (offset % size), - offset, le32_to_cpu(de->inode), - rlen, de->name_len); + "bad entry in directory: %s - offset=%u, " + "inode=%u, rec_len=%d, name_len=%d, size=%d", + error_msg, offset, le32_to_cpu(de->inode), + rlen, de->name_len, size); return 1; } diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index 0f0edd1cd0cd..caff935fbeb8 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -43,6 +43,17 @@ #define __FS_HAS_ENCRYPTION IS_ENABLED(CONFIG_EXT4_FS_ENCRYPTION) #include <linux/fscrypt.h> +#include <linux/compiler.h> + +/* Until this gets included into linux/compiler-gcc.h */ +#ifndef __nonstring +#if defined(GCC_VERSION) && (GCC_VERSION >= 80000) +#define __nonstring __attribute__((nonstring)) +#else +#define __nonstring +#endif +#endif + /* * The fourth extended filesystem constants/structures */ @@ -675,6 +686,9 @@ enum { /* Max physical block we can address w/o extents */ #define EXT4_MAX_BLOCK_FILE_PHYS 0xFFFFFFFF +/* Max logical block we can support */ +#define EXT4_MAX_LOGICAL_BLOCK 0xFFFFFFFF + /* * Structure of an inode on the disk */ @@ -1226,7 +1240,7 @@ struct ext4_super_block { __le32 s_feature_ro_compat; /* readonly-compatible feature set */ /*68*/ __u8 s_uuid[16]; /* 128-bit uuid for volume */ /*78*/ char s_volume_name[16]; /* volume name */ -/*88*/ char s_last_mounted[64]; /* directory where last mounted */ +/*88*/ char s_last_mounted[64] __nonstring; /* directory where last mounted */ /*C8*/ __le32 s_algorithm_usage_bitmap; /* For compression */ /* * Performance hints. Directory preallocation should only @@ -1277,13 +1291,13 @@ struct ext4_super_block { __le32 s_first_error_time; /* first time an error happened */ __le32 s_first_error_ino; /* inode involved in first error */ __le64 s_first_error_block; /* block involved of first error */ - __u8 s_first_error_func[32]; /* function where the error happened */ + __u8 s_first_error_func[32] __nonstring; /* function where the error happened */ __le32 s_first_error_line; /* line number where error happened */ __le32 s_last_error_time; /* most recent time of an error */ __le32 s_last_error_ino; /* inode involved in last error */ __le32 s_last_error_line; /* line number where error happened */ __le64 s_last_error_block; /* block involved of last error */ - __u8 s_last_error_func[32]; /* function where the error happened */ + __u8 s_last_error_func[32] __nonstring; /* function where the error happened */ #define EXT4_S_ERR_END offsetof(struct ext4_super_block, s_mount_opts) __u8 s_mount_opts[64]; __le32 s_usr_quota_inum; /* inode for tracking user quota */ diff --git a/fs/ext4/inline.c b/fs/ext4/inline.c index 3543fe80a3c4..7b4736022761 100644 --- a/fs/ext4/inline.c +++ b/fs/ext4/inline.c @@ -1753,6 +1753,7 @@ bool empty_inline_dir(struct inode *dir, int *has_inline_data) { int err, inline_size; struct ext4_iloc iloc; + size_t inline_len; void *inline_pos; unsigned int offset; struct ext4_dir_entry_2 *de; @@ -1780,8 +1781,9 @@ bool empty_inline_dir(struct inode *dir, int *has_inline_data) goto out; } + inline_len = ext4_get_inline_size(dir); offset = EXT4_INLINE_DOTDOT_SIZE; - while (offset < dir->i_size) { + while (offset < inline_len) { de = ext4_get_inline_entry(dir, &iloc, offset, &inline_pos, &inline_size); if (ext4_check_dir_entry(dir, NULL, de, diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index d0dd585add6a..d767e993591d 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -3413,12 +3413,16 @@ static int ext4_iomap_begin(struct inode *inode, loff_t offset, loff_t length, { struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); unsigned int blkbits = inode->i_blkbits; - unsigned long first_block = offset >> blkbits; - unsigned long last_block = (offset + length - 1) >> blkbits; + unsigned long first_block, last_block; struct ext4_map_blocks map; bool delalloc = false; int ret; + if ((offset >> blkbits) > EXT4_MAX_LOGICAL_BLOCK) + return -EINVAL; + first_block = offset >> blkbits; + last_block = min_t(loff_t, (offset + length - 1) >> blkbits, + EXT4_MAX_LOGICAL_BLOCK); if (flags & IOMAP_REPORT) { if (ext4_has_inline_data(inode)) { @@ -3948,6 +3952,7 @@ static const struct address_space_operations ext4_dax_aops = { .writepages = ext4_dax_writepages, .direct_IO = noop_direct_IO, .set_page_dirty = noop_set_page_dirty, + .bmap = ext4_bmap, .invalidatepage = noop_invalidatepage, }; @@ -4192,9 +4197,8 @@ int ext4_update_disksize_before_punch(struct inode *inode, loff_t offset, return 0; } -static void ext4_wait_dax_page(struct ext4_inode_info *ei, bool *did_unlock) +static void ext4_wait_dax_page(struct ext4_inode_info *ei) { - *did_unlock = true; up_write(&ei->i_mmap_sem); schedule(); down_write(&ei->i_mmap_sem); @@ -4204,14 +4208,12 @@ int ext4_break_layouts(struct inode *inode) { struct ext4_inode_info *ei = EXT4_I(inode); struct page *page; - bool retry; int error; if (WARN_ON_ONCE(!rwsem_is_locked(&ei->i_mmap_sem))) return -EINVAL; do { - retry = false; page = dax_layout_busy_page(inode->i_mapping); if (!page) return 0; @@ -4219,8 +4221,8 @@ int ext4_break_layouts(struct inode *inode) error = ___wait_var_event(&page->_refcount, atomic_read(&page->_refcount) == 1, TASK_INTERRUPTIBLE, 0, 0, - ext4_wait_dax_page(ei, &retry)); - } while (error == 0 && retry); + ext4_wait_dax_page(ei)); + } while (error == 0); return error; } @@ -4895,6 +4897,7 @@ struct inode *ext4_iget(struct super_block *sb, unsigned long ino) * not initialized on a new filesystem. */ } ei->i_flags = le32_to_cpu(raw_inode->i_flags); + ext4_set_inode_flags(inode); inode->i_blocks = ext4_inode_blocks(raw_inode, ei); ei->i_file_acl = le32_to_cpu(raw_inode->i_file_acl_lo); if (ext4_has_feature_64bit(sb)) @@ -5041,7 +5044,6 @@ struct inode *ext4_iget(struct super_block *sb, unsigned long ino) goto bad_inode; } brelse(iloc.bh); - ext4_set_inode_flags(inode); unlock_new_inode(inode); return inode; diff --git a/fs/ext4/mmp.c b/fs/ext4/mmp.c index 39b07c2d3384..2305b4374fd3 100644 --- a/fs/ext4/mmp.c +++ b/fs/ext4/mmp.c @@ -49,7 +49,6 @@ static int write_mmp_block(struct super_block *sb, struct buffer_head *bh) */ sb_start_write(sb); ext4_mmp_csum_set(sb, mmp); - mark_buffer_dirty(bh); lock_buffer(bh); bh->b_end_io = end_buffer_write_sync; get_bh(bh); diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c index 116ff68c5bd4..377d516c475f 100644 --- a/fs/ext4/namei.c +++ b/fs/ext4/namei.c @@ -3478,6 +3478,12 @@ static int ext4_rename(struct inode *old_dir, struct dentry *old_dentry, int credits; u8 old_file_type; + if (new.inode && new.inode->i_nlink == 0) { + EXT4_ERROR_INODE(new.inode, + "target of rename is already freed"); + return -EFSCORRUPTED; + } + if ((ext4_test_inode_flag(new_dir, EXT4_INODE_PROJINHERIT)) && (!projid_eq(EXT4_I(new_dir)->i_projid, EXT4_I(old_dentry->d_inode)->i_projid))) diff --git a/fs/ext4/resize.c b/fs/ext4/resize.c index e5fb38451a73..ebbc663d0798 100644 --- a/fs/ext4/resize.c +++ b/fs/ext4/resize.c @@ -19,6 +19,7 @@ int ext4_resize_begin(struct super_block *sb) { + struct ext4_sb_info *sbi = EXT4_SB(sb); int ret = 0; if (!capable(CAP_SYS_RESOURCE)) @@ -29,7 +30,7 @@ int ext4_resize_begin(struct super_block *sb) * because the user tools have no way of handling this. Probably a * bad time to do it anyways. */ - if (EXT4_SB(sb)->s_sbh->b_blocknr != + if (EXT4_B2C(sbi, sbi->s_sbh->b_blocknr) != le32_to_cpu(EXT4_SB(sb)->s_es->s_first_data_block)) { ext4_warning(sb, "won't resize using backup superblock at %llu", (unsigned long long)EXT4_SB(sb)->s_sbh->b_blocknr); @@ -1986,6 +1987,26 @@ retry: } } + /* + * Make sure the last group has enough space so that it's + * guaranteed to have enough space for all metadata blocks + * that it might need to hold. (We might not need to store + * the inode table blocks in the last block group, but there + * will be cases where this might be needed.) + */ + if ((ext4_group_first_block_no(sb, n_group) + + ext4_group_overhead_blocks(sb, n_group) + 2 + + sbi->s_itb_per_group + sbi->s_cluster_ratio) >= n_blocks_count) { + n_blocks_count = ext4_group_first_block_no(sb, n_group); + n_group--; + n_blocks_count_retry = 0; + if (resize_inode) { + iput(resize_inode); + resize_inode = NULL; + } + goto retry; + } + /* extend the last group */ if (n_group == o_group) add = n_blocks_count - o_blocks_count; diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 5863fd22e90b..1145109968ef 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -2145,6 +2145,8 @@ static int _ext4_show_options(struct seq_file *seq, struct super_block *sb, SEQ_OPTS_PRINT("max_dir_size_kb=%u", sbi->s_max_dir_size_kb); if (test_opt(sb, DATA_ERR_ABORT)) SEQ_OPTS_PUTS("data_err=abort"); + if (DUMMY_ENCRYPTION_ENABLED(sbi)) + SEQ_OPTS_PUTS("test_dummy_encryption"); ext4_show_quota_options(seq, sb); return 0; @@ -4378,11 +4380,13 @@ no_journal: block = ext4_count_free_clusters(sb); ext4_free_blocks_count_set(sbi->s_es, EXT4_C2B(sbi, block)); + ext4_superblock_csum_set(sb); err = percpu_counter_init(&sbi->s_freeclusters_counter, block, GFP_KERNEL); if (!err) { unsigned long freei = ext4_count_free_inodes(sb); sbi->s_es->s_free_inodes_count = cpu_to_le32(freei); + ext4_superblock_csum_set(sb); err = percpu_counter_init(&sbi->s_freeinodes_counter, freei, GFP_KERNEL); } diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index 34830f6457ea..8220a168282e 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -1637,6 +1637,14 @@ static void nfs_state_set_delegation(struct nfs4_state *state, write_sequnlock(&state->seqlock); } +static void nfs_state_clear_delegation(struct nfs4_state *state) +{ + write_seqlock(&state->seqlock); + nfs4_stateid_copy(&state->stateid, &state->open_stateid); + clear_bit(NFS_DELEGATED_STATE, &state->flags); + write_sequnlock(&state->seqlock); +} + static int update_open_stateid(struct nfs4_state *state, const nfs4_stateid *open_stateid, const nfs4_stateid *delegation, @@ -2145,10 +2153,7 @@ int nfs4_open_delegation_recall(struct nfs_open_context *ctx, if (IS_ERR(opendata)) return PTR_ERR(opendata); nfs4_stateid_copy(&opendata->o_arg.u.delegation, stateid); - write_seqlock(&state->seqlock); - nfs4_stateid_copy(&state->stateid, &state->open_stateid); - write_sequnlock(&state->seqlock); - clear_bit(NFS_DELEGATED_STATE, &state->flags); + nfs_state_clear_delegation(state); switch (type & (FMODE_READ|FMODE_WRITE)) { case FMODE_READ|FMODE_WRITE: case FMODE_WRITE: @@ -2601,10 +2606,7 @@ static void nfs_finish_clear_delegation_stateid(struct nfs4_state *state, const nfs4_stateid *stateid) { nfs_remove_bad_delegation(state->inode, stateid); - write_seqlock(&state->seqlock); - nfs4_stateid_copy(&state->stateid, &state->open_stateid); - write_sequnlock(&state->seqlock); - clear_bit(NFS_DELEGATED_STATE, &state->flags); + nfs_state_clear_delegation(state); } static void nfs40_clear_delegation_stateid(struct nfs4_state *state) @@ -2672,15 +2674,20 @@ static void nfs41_check_delegation_stateid(struct nfs4_state *state) delegation = rcu_dereference(NFS_I(state->inode)->delegation); if (delegation == NULL) { rcu_read_unlock(); + nfs_state_clear_delegation(state); return; } nfs4_stateid_copy(&stateid, &delegation->stateid); - if (test_bit(NFS_DELEGATION_REVOKED, &delegation->flags) || - !test_and_clear_bit(NFS_DELEGATION_TEST_EXPIRED, - &delegation->flags)) { + if (test_bit(NFS_DELEGATION_REVOKED, &delegation->flags)) { + rcu_read_unlock(); + nfs_state_clear_delegation(state); + return; + } + + if (!test_and_clear_bit(NFS_DELEGATION_TEST_EXPIRED, + &delegation->flags)) { rcu_read_unlock(); - nfs_finish_clear_delegation_stateid(state, &stateid); return; } diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c index 3df0eb52da1c..40a08cd483f0 100644 --- a/fs/nfs/nfs4state.c +++ b/fs/nfs/nfs4state.c @@ -1390,6 +1390,8 @@ int nfs4_schedule_stateid_recovery(const struct nfs_server *server, struct nfs4_ if (!nfs4_state_mark_reclaim_nograce(clp, state)) return -EBADF; + nfs_inode_find_delegation_state_and_recover(state->inode, + &state->stateid); dprintk("%s: scheduling stateid recovery for server %s\n", __func__, clp->cl_hostname); nfs4_schedule_state_manager(clp); diff --git a/fs/nfs/nfs4trace.h b/fs/nfs/nfs4trace.h index a275fba93170..b1483b303e0b 100644 --- a/fs/nfs/nfs4trace.h +++ b/fs/nfs/nfs4trace.h @@ -1137,7 +1137,7 @@ DECLARE_EVENT_CLASS(nfs4_inode_callback_event, TP_fast_assign( __entry->error = error; __entry->fhandle = nfs_fhandle_hash(fhandle); - if (inode != NULL) { + if (!IS_ERR_OR_NULL(inode)) { __entry->fileid = NFS_FILEID(inode); __entry->dev = inode->i_sb->s_dev; } else { @@ -1194,7 +1194,7 @@ DECLARE_EVENT_CLASS(nfs4_inode_stateid_callback_event, TP_fast_assign( __entry->error = error; __entry->fhandle = nfs_fhandle_hash(fhandle); - if (inode != NULL) { + if (!IS_ERR_OR_NULL(inode)) { __entry->fileid = NFS_FILEID(inode); __entry->dev = inode->i_sb->s_dev; } else { diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c index e8f232de484f..7d9a51e6b847 100644 --- a/fs/nfs/pnfs.c +++ b/fs/nfs/pnfs.c @@ -1740,16 +1740,16 @@ static bool pnfs_within_mdsthreshold(struct nfs_open_context *ctx, return ret; } -static bool pnfs_prepare_to_retry_layoutget(struct pnfs_layout_hdr *lo) +static int pnfs_prepare_to_retry_layoutget(struct pnfs_layout_hdr *lo) { /* * send layoutcommit as it can hold up layoutreturn due to lseg * reference */ pnfs_layoutcommit_inode(lo->plh_inode, false); - return !wait_on_bit_action(&lo->plh_flags, NFS_LAYOUT_RETURN, + return wait_on_bit_action(&lo->plh_flags, NFS_LAYOUT_RETURN, nfs_wait_bit_killable, - TASK_UNINTERRUPTIBLE); + TASK_KILLABLE); } static void nfs_layoutget_begin(struct pnfs_layout_hdr *lo) @@ -1830,7 +1830,9 @@ pnfs_update_layout(struct inode *ino, } lookup_again: - nfs4_client_recover_expired_lease(clp); + lseg = ERR_PTR(nfs4_client_recover_expired_lease(clp)); + if (IS_ERR(lseg)) + goto out; first = false; spin_lock(&ino->i_lock); lo = pnfs_find_alloc_layout(ino, ctx, gfp_flags); @@ -1863,9 +1865,9 @@ lookup_again: if (list_empty(&lo->plh_segs) && atomic_read(&lo->plh_outstanding) != 0) { spin_unlock(&ino->i_lock); - if (wait_var_event_killable(&lo->plh_outstanding, - atomic_read(&lo->plh_outstanding) == 0 - || !list_empty(&lo->plh_segs))) + lseg = ERR_PTR(wait_var_event_killable(&lo->plh_outstanding, + atomic_read(&lo->plh_outstanding))); + if (IS_ERR(lseg) || !list_empty(&lo->plh_segs)) goto out_put_layout_hdr; pnfs_put_layout_hdr(lo); goto lookup_again; @@ -1898,8 +1900,11 @@ lookup_again: if (test_and_set_bit(NFS_LAYOUT_FIRST_LAYOUTGET, &lo->plh_flags)) { spin_unlock(&ino->i_lock); - wait_on_bit(&lo->plh_flags, NFS_LAYOUT_FIRST_LAYOUTGET, - TASK_UNINTERRUPTIBLE); + lseg = ERR_PTR(wait_on_bit(&lo->plh_flags, + NFS_LAYOUT_FIRST_LAYOUTGET, + TASK_KILLABLE)); + if (IS_ERR(lseg)) + goto out_put_layout_hdr; pnfs_put_layout_hdr(lo); dprintk("%s retrying\n", __func__); goto lookup_again; @@ -1925,7 +1930,8 @@ lookup_again: if (test_bit(NFS_LAYOUT_RETURN, &lo->plh_flags)) { spin_unlock(&ino->i_lock); dprintk("%s wait for layoutreturn\n", __func__); - if (pnfs_prepare_to_retry_layoutget(lo)) { + lseg = ERR_PTR(pnfs_prepare_to_retry_layoutget(lo)); + if (!IS_ERR(lseg)) { if (first) pnfs_clear_first_layoutget(lo); pnfs_put_layout_hdr(lo); diff --git a/fs/nilfs2/alloc.c b/fs/nilfs2/alloc.c index 03b8ba933eb2..235b959fc2b3 100644 --- a/fs/nilfs2/alloc.c +++ b/fs/nilfs2/alloc.c @@ -1,18 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0+ /* * alloc.c - NILFS dat/inode allocator * * Copyright (C) 2006-2008 Nippon Telegraph and Telephone Corporation. * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * * Originally written by Koji Sato. * Two allocators were unified by Ryusuke Konishi and Amagai Yoshiji. */ diff --git a/fs/nilfs2/alloc.h b/fs/nilfs2/alloc.h index 05149e606a78..0303c3968cee 100644 --- a/fs/nilfs2/alloc.h +++ b/fs/nilfs2/alloc.h @@ -1,18 +1,9 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ /* * alloc.h - persistent object (dat entry/disk inode) allocator/deallocator * * Copyright (C) 2006-2008 Nippon Telegraph and Telephone Corporation. * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * * Originally written by Koji Sato. * Two allocators were unified by Ryusuke Konishi and Amagai Yoshiji. */ diff --git a/fs/nilfs2/bmap.c b/fs/nilfs2/bmap.c index 01fb1831ca25..fb5a9a8a13cf 100644 --- a/fs/nilfs2/bmap.c +++ b/fs/nilfs2/bmap.c @@ -1,18 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0+ /* * bmap.c - NILFS block mapping. * * Copyright (C) 2006-2008 Nippon Telegraph and Telephone Corporation. * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * * Written by Koji Sato. */ diff --git a/fs/nilfs2/bmap.h b/fs/nilfs2/bmap.h index 2b6ffbe5997a..2c63858e81c9 100644 --- a/fs/nilfs2/bmap.h +++ b/fs/nilfs2/bmap.h @@ -1,18 +1,9 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ /* * bmap.h - NILFS block mapping. * * Copyright (C) 2006-2008 Nippon Telegraph and Telephone Corporation. * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * * Written by Koji Sato. */ diff --git a/fs/nilfs2/btnode.c b/fs/nilfs2/btnode.c index dec98cab729d..ebb24a314f43 100644 --- a/fs/nilfs2/btnode.c +++ b/fs/nilfs2/btnode.c @@ -1,18 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0+ /* * btnode.c - NILFS B-tree node cache * * Copyright (C) 2005-2008 Nippon Telegraph and Telephone Corporation. * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * * Originally written by Seiji Kihara. * Fully revised by Ryusuke Konishi for stabilization and simplification. * diff --git a/fs/nilfs2/btnode.h b/fs/nilfs2/btnode.h index 4e8aaa1aeb65..0f88dbc9bcb3 100644 --- a/fs/nilfs2/btnode.h +++ b/fs/nilfs2/btnode.h @@ -1,18 +1,9 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ /* * btnode.h - NILFS B-tree node cache * * Copyright (C) 2005-2008 Nippon Telegraph and Telephone Corporation. * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * * Written by Seiji Kihara. * Revised by Ryusuke Konishi. */ diff --git a/fs/nilfs2/btree.c b/fs/nilfs2/btree.c index 16a7a67a11c9..23e043eca237 100644 --- a/fs/nilfs2/btree.c +++ b/fs/nilfs2/btree.c @@ -1,18 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0+ /* * btree.c - NILFS B-tree. * * Copyright (C) 2005-2008 Nippon Telegraph and Telephone Corporation. * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * * Written by Koji Sato. */ diff --git a/fs/nilfs2/btree.h b/fs/nilfs2/btree.h index 2184e47fa4bf..d1421b646ce4 100644 --- a/fs/nilfs2/btree.h +++ b/fs/nilfs2/btree.h @@ -1,18 +1,9 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ /* * btree.h - NILFS B-tree. * * Copyright (C) 2005-2008 Nippon Telegraph and Telephone Corporation. * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * * Written by Koji Sato. */ diff --git a/fs/nilfs2/cpfile.c b/fs/nilfs2/cpfile.c index a15a1601e931..8d41311b5db4 100644 --- a/fs/nilfs2/cpfile.c +++ b/fs/nilfs2/cpfile.c @@ -1,18 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0+ /* * cpfile.c - NILFS checkpoint file. * * Copyright (C) 2006-2008 Nippon Telegraph and Telephone Corporation. * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * * Written by Koji Sato. */ diff --git a/fs/nilfs2/cpfile.h b/fs/nilfs2/cpfile.h index 6eca972f9673..6336222df24a 100644 --- a/fs/nilfs2/cpfile.h +++ b/fs/nilfs2/cpfile.h @@ -1,18 +1,9 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ /* * cpfile.h - NILFS checkpoint file. * * Copyright (C) 2006-2008 Nippon Telegraph and Telephone Corporation. * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * * Written by Koji Sato. */ diff --git a/fs/nilfs2/dat.c b/fs/nilfs2/dat.c index dffedb2f8817..6f4066636be9 100644 --- a/fs/nilfs2/dat.c +++ b/fs/nilfs2/dat.c @@ -1,18 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0+ /* * dat.c - NILFS disk address translation. * * Copyright (C) 2006-2008 Nippon Telegraph and Telephone Corporation. * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * * Written by Koji Sato. */ diff --git a/fs/nilfs2/dat.h b/fs/nilfs2/dat.h index 57dc6cf466d0..b17ee34580ae 100644 --- a/fs/nilfs2/dat.h +++ b/fs/nilfs2/dat.h @@ -1,18 +1,9 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ /* * dat.h - NILFS disk address translation. * * Copyright (C) 2006-2008 Nippon Telegraph and Telephone Corporation. * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * * Written by Koji Sato. */ diff --git a/fs/nilfs2/dir.c b/fs/nilfs2/dir.c index 582831ab3eb9..81394e22d0a0 100644 --- a/fs/nilfs2/dir.c +++ b/fs/nilfs2/dir.c @@ -1,18 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0+ /* * dir.c - NILFS directory entry operations * * Copyright (C) 2005-2008 Nippon Telegraph and Telephone Corporation. * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * * Modified for NILFS by Amagai Yoshiji. */ /* diff --git a/fs/nilfs2/direct.c b/fs/nilfs2/direct.c index 96e3ed0d9652..533e24ea3a88 100644 --- a/fs/nilfs2/direct.c +++ b/fs/nilfs2/direct.c @@ -1,18 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0+ /* * direct.c - NILFS direct block pointer. * * Copyright (C) 2006-2008 Nippon Telegraph and Telephone Corporation. * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * * Written by Koji Sato. */ diff --git a/fs/nilfs2/direct.h b/fs/nilfs2/direct.h index cfe85e848bba..ec9a23c77994 100644 --- a/fs/nilfs2/direct.h +++ b/fs/nilfs2/direct.h @@ -1,18 +1,9 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ /* * direct.h - NILFS direct block pointer. * * Copyright (C) 2006-2008 Nippon Telegraph and Telephone Corporation. * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * * Written by Koji Sato. */ diff --git a/fs/nilfs2/file.c b/fs/nilfs2/file.c index 7da0fac71dc2..64bc81363c6c 100644 --- a/fs/nilfs2/file.c +++ b/fs/nilfs2/file.c @@ -1,18 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0+ /* * file.c - NILFS regular file handling primitives including fsync(). * * Copyright (C) 2005-2008 Nippon Telegraph and Telephone Corporation. * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * * Written by Amagai Yoshiji and Ryusuke Konishi. */ diff --git a/fs/nilfs2/gcinode.c b/fs/nilfs2/gcinode.c index 853a831dcde0..aa3c328ee189 100644 --- a/fs/nilfs2/gcinode.c +++ b/fs/nilfs2/gcinode.c @@ -1,18 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0+ /* * gcinode.c - dummy inodes to buffer blocks for garbage collection * * Copyright (C) 2005-2008 Nippon Telegraph and Telephone Corporation. * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * * Written by Seiji Kihara, Amagai Yoshiji, and Ryusuke Konishi. * Revised by Ryusuke Konishi. * diff --git a/fs/nilfs2/ifile.c b/fs/nilfs2/ifile.c index b8fa45c20c63..4140d232cadc 100644 --- a/fs/nilfs2/ifile.c +++ b/fs/nilfs2/ifile.c @@ -1,18 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0+ /* * ifile.c - NILFS inode file * * Copyright (C) 2006-2008 Nippon Telegraph and Telephone Corporation. * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * * Written by Amagai Yoshiji. * Revised by Ryusuke Konishi. * diff --git a/fs/nilfs2/ifile.h b/fs/nilfs2/ifile.h index 188b94fe0ec5..a1e1e5711a05 100644 --- a/fs/nilfs2/ifile.h +++ b/fs/nilfs2/ifile.h @@ -1,18 +1,9 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ /* * ifile.h - NILFS inode file * * Copyright (C) 2006-2008 Nippon Telegraph and Telephone Corporation. * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * * Written by Amagai Yoshiji. * Revised by Ryusuke Konishi. * diff --git a/fs/nilfs2/inode.c b/fs/nilfs2/inode.c index 6a612d832e7d..671085512e0f 100644 --- a/fs/nilfs2/inode.c +++ b/fs/nilfs2/inode.c @@ -1,18 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0+ /* * inode.c - NILFS inode operations. * * Copyright (C) 2005-2008 Nippon Telegraph and Telephone Corporation. * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * * Written by Ryusuke Konishi. * */ diff --git a/fs/nilfs2/ioctl.c b/fs/nilfs2/ioctl.c index 1d2c3d7711fe..9b96d79eea6c 100644 --- a/fs/nilfs2/ioctl.c +++ b/fs/nilfs2/ioctl.c @@ -1,18 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0+ /* * ioctl.c - NILFS ioctl operations. * * Copyright (C) 2007, 2008 Nippon Telegraph and Telephone Corporation. * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * * Written by Koji Sato. */ diff --git a/fs/nilfs2/mdt.c b/fs/nilfs2/mdt.c index c6bc1033e7d2..700870a92bc4 100644 --- a/fs/nilfs2/mdt.c +++ b/fs/nilfs2/mdt.c @@ -1,18 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0+ /* * mdt.c - meta data file for NILFS * * Copyright (C) 2005-2008 Nippon Telegraph and Telephone Corporation. * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * * Written by Ryusuke Konishi. */ diff --git a/fs/nilfs2/mdt.h b/fs/nilfs2/mdt.h index 3f67f3932097..e77aea4bb921 100644 --- a/fs/nilfs2/mdt.h +++ b/fs/nilfs2/mdt.h @@ -1,18 +1,9 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ /* * mdt.h - NILFS meta data file prototype and definitions * * Copyright (C) 2005-2008 Nippon Telegraph and Telephone Corporation. * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * * Written by Ryusuke Konishi. */ diff --git a/fs/nilfs2/namei.c b/fs/nilfs2/namei.c index dd52d3f82e8d..9fe6d4ab74f0 100644 --- a/fs/nilfs2/namei.c +++ b/fs/nilfs2/namei.c @@ -1,18 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0+ /* * namei.c - NILFS pathname lookup operations. * * Copyright (C) 2005-2008 Nippon Telegraph and Telephone Corporation. * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * * Modified for NILFS by Amagai Yoshiji and Ryusuke Konishi. */ /* diff --git a/fs/nilfs2/nilfs.h b/fs/nilfs2/nilfs.h index 33f8c8fc96e8..a2f247b6a209 100644 --- a/fs/nilfs2/nilfs.h +++ b/fs/nilfs2/nilfs.h @@ -1,18 +1,9 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ /* * nilfs.h - NILFS local header file. * * Copyright (C) 2005-2008 Nippon Telegraph and Telephone Corporation. * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * * Written by Koji Sato and Ryusuke Konishi. */ diff --git a/fs/nilfs2/page.c b/fs/nilfs2/page.c index 4cb850a6f1c2..329a056b73b1 100644 --- a/fs/nilfs2/page.c +++ b/fs/nilfs2/page.c @@ -1,18 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0+ /* * page.c - buffer/page management specific to NILFS * * Copyright (C) 2005-2008 Nippon Telegraph and Telephone Corporation. * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * * Written by Ryusuke Konishi and Seiji Kihara. */ diff --git a/fs/nilfs2/page.h b/fs/nilfs2/page.h index f3687c958fa8..62b9bb469e92 100644 --- a/fs/nilfs2/page.h +++ b/fs/nilfs2/page.h @@ -1,18 +1,9 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ /* * page.h - buffer/page management specific to NILFS * * Copyright (C) 2005-2008 Nippon Telegraph and Telephone Corporation. * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * * Written by Ryusuke Konishi and Seiji Kihara. */ diff --git a/fs/nilfs2/recovery.c b/fs/nilfs2/recovery.c index 5139efed1888..140b663e91c7 100644 --- a/fs/nilfs2/recovery.c +++ b/fs/nilfs2/recovery.c @@ -1,18 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0+ /* * recovery.c - NILFS recovery logic * * Copyright (C) 2005-2008 Nippon Telegraph and Telephone Corporation. * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * * Written by Ryusuke Konishi. */ diff --git a/fs/nilfs2/segbuf.c b/fs/nilfs2/segbuf.c index 68cb9e4740b4..20c479b5e41b 100644 --- a/fs/nilfs2/segbuf.c +++ b/fs/nilfs2/segbuf.c @@ -1,18 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0+ /* * segbuf.c - NILFS segment buffer * * Copyright (C) 2005-2008 Nippon Telegraph and Telephone Corporation. * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * * Written by Ryusuke Konishi. * */ diff --git a/fs/nilfs2/segbuf.h b/fs/nilfs2/segbuf.h index 10e16935fff6..9bea1bd59041 100644 --- a/fs/nilfs2/segbuf.h +++ b/fs/nilfs2/segbuf.h @@ -1,18 +1,9 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ /* * segbuf.h - NILFS Segment buffer prototypes and definitions * * Copyright (C) 2005-2008 Nippon Telegraph and Telephone Corporation. * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * * Written by Ryusuke Konishi. * */ diff --git a/fs/nilfs2/segment.c b/fs/nilfs2/segment.c index 0953635e7d48..445eef41bfaf 100644 --- a/fs/nilfs2/segment.c +++ b/fs/nilfs2/segment.c @@ -1,18 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0+ /* * segment.c - NILFS segment constructor. * * Copyright (C) 2005-2008 Nippon Telegraph and Telephone Corporation. * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * * Written by Ryusuke Konishi. * */ diff --git a/fs/nilfs2/segment.h b/fs/nilfs2/segment.h index 04634e3e3d58..f5cf5308f3fc 100644 --- a/fs/nilfs2/segment.h +++ b/fs/nilfs2/segment.h @@ -1,18 +1,9 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ /* * segment.h - NILFS Segment constructor prototypes and definitions * * Copyright (C) 2005-2008 Nippon Telegraph and Telephone Corporation. * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * * Written by Ryusuke Konishi. * */ diff --git a/fs/nilfs2/sufile.c b/fs/nilfs2/sufile.c index c7fa139d50e8..bf3f8f05c89b 100644 --- a/fs/nilfs2/sufile.c +++ b/fs/nilfs2/sufile.c @@ -1,18 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0+ /* * sufile.c - NILFS segment usage file. * * Copyright (C) 2006-2008 Nippon Telegraph and Telephone Corporation. * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * * Written by Koji Sato. * Revised by Ryusuke Konishi. */ diff --git a/fs/nilfs2/sufile.h b/fs/nilfs2/sufile.h index 673a891350f4..c4e2c7a7add1 100644 --- a/fs/nilfs2/sufile.h +++ b/fs/nilfs2/sufile.h @@ -1,18 +1,9 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ /* * sufile.h - NILFS segment usage file. * * Copyright (C) 2006-2008 Nippon Telegraph and Telephone Corporation. * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * * Written by Koji Sato. */ diff --git a/fs/nilfs2/super.c b/fs/nilfs2/super.c index 1b9067cf4511..26290aa1023f 100644 --- a/fs/nilfs2/super.c +++ b/fs/nilfs2/super.c @@ -1,18 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0+ /* * super.c - NILFS module and super block management. * * Copyright (C) 2005-2008 Nippon Telegraph and Telephone Corporation. * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * * Written by Ryusuke Konishi. */ /* diff --git a/fs/nilfs2/sysfs.c b/fs/nilfs2/sysfs.c index 4b25837e7724..e60be7bb55b0 100644 --- a/fs/nilfs2/sysfs.c +++ b/fs/nilfs2/sysfs.c @@ -1,19 +1,10 @@ +// SPDX-License-Identifier: GPL-2.0+ /* * sysfs.c - sysfs support implementation. * * Copyright (C) 2005-2014 Nippon Telegraph and Telephone Corporation. * Copyright (C) 2014 HGST, Inc., a Western Digital Company. * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * * Written by Vyacheslav Dubeyko <Vyacheslav.Dubeyko@hgst.com> */ diff --git a/fs/nilfs2/sysfs.h b/fs/nilfs2/sysfs.h index 648cedf9c06e..d001eb862dae 100644 --- a/fs/nilfs2/sysfs.h +++ b/fs/nilfs2/sysfs.h @@ -1,19 +1,10 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ /* * sysfs.h - sysfs support declarations. * * Copyright (C) 2005-2014 Nippon Telegraph and Telephone Corporation. * Copyright (C) 2014 HGST, Inc., a Western Digital Company. * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * * Written by Vyacheslav Dubeyko <Vyacheslav.Dubeyko@hgst.com> */ diff --git a/fs/nilfs2/the_nilfs.c b/fs/nilfs2/the_nilfs.c index 1a85317e83f0..484785cdf96e 100644 --- a/fs/nilfs2/the_nilfs.c +++ b/fs/nilfs2/the_nilfs.c @@ -1,18 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0+ /* * the_nilfs.c - the_nilfs shared structure. * * Copyright (C) 2005-2008 Nippon Telegraph and Telephone Corporation. * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * * Written by Ryusuke Konishi. * */ diff --git a/fs/nilfs2/the_nilfs.h b/fs/nilfs2/the_nilfs.h index 36da1779f976..380a543c5b19 100644 --- a/fs/nilfs2/the_nilfs.h +++ b/fs/nilfs2/the_nilfs.h @@ -1,18 +1,9 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ /* * the_nilfs.h - the_nilfs shared structure. * * Copyright (C) 2005-2008 Nippon Telegraph and Telephone Corporation. * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * * Written by Ryusuke Konishi. * */ diff --git a/fs/notify/fsnotify.c b/fs/notify/fsnotify.c index f174397b63a0..ababdbfab537 100644 --- a/fs/notify/fsnotify.c +++ b/fs/notify/fsnotify.c @@ -351,16 +351,9 @@ int fsnotify(struct inode *to_tell, __u32 mask, const void *data, int data_is, iter_info.srcu_idx = srcu_read_lock(&fsnotify_mark_srcu); - if ((mask & FS_MODIFY) || - (test_mask & to_tell->i_fsnotify_mask)) { - iter_info.marks[FSNOTIFY_OBJ_TYPE_INODE] = - fsnotify_first_mark(&to_tell->i_fsnotify_marks); - } - - if (mnt && ((mask & FS_MODIFY) || - (test_mask & mnt->mnt_fsnotify_mask))) { - iter_info.marks[FSNOTIFY_OBJ_TYPE_INODE] = - fsnotify_first_mark(&to_tell->i_fsnotify_marks); + iter_info.marks[FSNOTIFY_OBJ_TYPE_INODE] = + fsnotify_first_mark(&to_tell->i_fsnotify_marks); + if (mnt) { iter_info.marks[FSNOTIFY_OBJ_TYPE_VFSMOUNT] = fsnotify_first_mark(&mnt->mnt_fsnotify_marks); } diff --git a/fs/ocfs2/buffer_head_io.c b/fs/ocfs2/buffer_head_io.c index d9ebe11c8990..1d098c3c00e0 100644 --- a/fs/ocfs2/buffer_head_io.c +++ b/fs/ocfs2/buffer_head_io.c @@ -342,6 +342,7 @@ int ocfs2_read_blocks(struct ocfs2_caching_info *ci, u64 block, int nr, * for this bh as it's not marked locally * uptodate. */ status = -EIO; + clear_buffer_needs_validate(bh); put_bh(bh); bhs[i] = NULL; continue; diff --git a/fs/overlayfs/file.c b/fs/overlayfs/file.c index 32e9282893c9..aeaefd2a551b 100644 --- a/fs/overlayfs/file.c +++ b/fs/overlayfs/file.c @@ -131,9 +131,6 @@ static int ovl_open(struct inode *inode, struct file *file) if (IS_ERR(realfile)) return PTR_ERR(realfile); - /* For O_DIRECT dentry_open() checks f_mapping->a_ops->direct_IO */ - file->f_mapping = realfile->f_mapping; - file->private_data = realfile; return 0; @@ -334,6 +331,25 @@ static long ovl_fallocate(struct file *file, int mode, loff_t offset, loff_t len return ret; } +static int ovl_fadvise(struct file *file, loff_t offset, loff_t len, int advice) +{ + struct fd real; + const struct cred *old_cred; + int ret; + + ret = ovl_real_fdget(file, &real); + if (ret) + return ret; + + old_cred = ovl_override_creds(file_inode(file)->i_sb); + ret = vfs_fadvise(real.file, offset, len, advice); + revert_creds(old_cred); + + fdput(real); + + return ret; +} + static long ovl_real_ioctl(struct file *file, unsigned int cmd, unsigned long arg) { @@ -502,6 +518,7 @@ const struct file_operations ovl_file_operations = { .fsync = ovl_fsync, .mmap = ovl_mmap, .fallocate = ovl_fallocate, + .fadvise = ovl_fadvise, .unlocked_ioctl = ovl_ioctl, .compat_ioctl = ovl_compat_ioctl, diff --git a/fs/overlayfs/inode.c b/fs/overlayfs/inode.c index e0bb217c01e2..b6ac545b5a32 100644 --- a/fs/overlayfs/inode.c +++ b/fs/overlayfs/inode.c @@ -467,6 +467,10 @@ static int ovl_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo, return -EOPNOTSUPP; old_cred = ovl_override_creds(inode->i_sb); + + if (fieinfo->fi_flags & FIEMAP_FLAG_SYNC) + filemap_write_and_wait(realinode->i_mapping); + err = realinode->i_op->fiemap(realinode, fieinfo, start, len); revert_creds(old_cred); @@ -500,6 +504,11 @@ static const struct inode_operations ovl_special_inode_operations = { .update_time = ovl_update_time, }; +const struct address_space_operations ovl_aops = { + /* For O_DIRECT dentry_open() checks f_mapping->a_ops->direct_IO */ + .direct_IO = noop_direct_IO, +}; + /* * It is possible to stack overlayfs instance on top of another * overlayfs instance as lower layer. We need to annonate the @@ -571,6 +580,7 @@ static void ovl_fill_inode(struct inode *inode, umode_t mode, dev_t rdev, case S_IFREG: inode->i_op = &ovl_file_inode_operations; inode->i_fop = &ovl_file_operations; + inode->i_mapping->a_ops = &ovl_aops; break; case S_IFDIR: diff --git a/fs/overlayfs/super.c b/fs/overlayfs/super.c index 2e0fc93c2c06..30adc9d408a0 100644 --- a/fs/overlayfs/super.c +++ b/fs/overlayfs/super.c @@ -982,16 +982,6 @@ static int ovl_get_upper(struct ovl_fs *ofs, struct path *upperpath) if (err) goto out; - err = -EBUSY; - if (ovl_inuse_trylock(upperpath->dentry)) { - ofs->upperdir_locked = true; - } else if (ofs->config.index) { - pr_err("overlayfs: upperdir is in-use by another mount, mount with '-o index=off' to override exclusive upperdir protection.\n"); - goto out; - } else { - pr_warn("overlayfs: upperdir is in-use by another mount, accessing files from both mounts will result in undefined behavior.\n"); - } - upper_mnt = clone_private_mount(upperpath); err = PTR_ERR(upper_mnt); if (IS_ERR(upper_mnt)) { @@ -1002,6 +992,17 @@ static int ovl_get_upper(struct ovl_fs *ofs, struct path *upperpath) /* Don't inherit atime flags */ upper_mnt->mnt_flags &= ~(MNT_NOATIME | MNT_NODIRATIME | MNT_RELATIME); ofs->upper_mnt = upper_mnt; + + err = -EBUSY; + if (ovl_inuse_trylock(ofs->upper_mnt->mnt_root)) { + ofs->upperdir_locked = true; + } else if (ofs->config.index) { + pr_err("overlayfs: upperdir is in-use by another mount, mount with '-o index=off' to override exclusive upperdir protection.\n"); + goto out; + } else { + pr_warn("overlayfs: upperdir is in-use by another mount, accessing files from both mounts will result in undefined behavior.\n"); + } + err = 0; out: return err; @@ -1101,8 +1102,10 @@ static int ovl_get_workdir(struct ovl_fs *ofs, struct path *upperpath) goto out; } + ofs->workbasedir = dget(workpath.dentry); + err = -EBUSY; - if (ovl_inuse_trylock(workpath.dentry)) { + if (ovl_inuse_trylock(ofs->workbasedir)) { ofs->workdir_locked = true; } else if (ofs->config.index) { pr_err("overlayfs: workdir is in-use by another mount, mount with '-o index=off' to override exclusive workdir protection.\n"); @@ -1111,7 +1114,6 @@ static int ovl_get_workdir(struct ovl_fs *ofs, struct path *upperpath) pr_warn("overlayfs: workdir is in-use by another mount, accessing files from both mounts will result in undefined behavior.\n"); } - ofs->workbasedir = dget(workpath.dentry); err = ovl_make_workdir(ofs, &workpath); if (err) goto out; diff --git a/fs/proc/kcore.c b/fs/proc/kcore.c index ad72261ee3fe..d297fe4472a9 100644 --- a/fs/proc/kcore.c +++ b/fs/proc/kcore.c @@ -464,6 +464,7 @@ read_kcore(struct file *file, char __user *buffer, size_t buflen, loff_t *fpos) ret = -EFAULT; goto out; } + m = NULL; /* skip the list anchor */ } else if (m->type == KCORE_VMALLOC) { vread(buf, (char *)start, tsz); /* we have to zero-fill user buffer even if no read */ diff --git a/fs/pstore/ram_core.c b/fs/pstore/ram_core.c index 951a14edcf51..0792595ebcfb 100644 --- a/fs/pstore/ram_core.c +++ b/fs/pstore/ram_core.c @@ -429,7 +429,12 @@ static void *persistent_ram_vmap(phys_addr_t start, size_t size, vaddr = vmap(pages, page_count, VM_MAP, prot); kfree(pages); - return vaddr; + /* + * Since vmap() uses page granularity, we must add the offset + * into the page here, to get the byte granularity address + * into the mapping to represent the actual "start" location. + */ + return vaddr + offset_in_page(start); } static void *persistent_ram_iomap(phys_addr_t start, size_t size, @@ -448,6 +453,11 @@ static void *persistent_ram_iomap(phys_addr_t start, size_t size, else va = ioremap_wc(start, size); + /* + * Since request_mem_region() and ioremap() are byte-granularity + * there is no need handle anything special like we do when the + * vmap() case in persistent_ram_vmap() above. + */ return va; } @@ -468,7 +478,7 @@ static int persistent_ram_buffer_map(phys_addr_t start, phys_addr_t size, return -ENOMEM; } - prz->buffer = prz->vaddr + offset_in_page(start); + prz->buffer = prz->vaddr; prz->buffer_size = size - sizeof(struct persistent_ram_buffer); return 0; @@ -515,7 +525,8 @@ void persistent_ram_free(struct persistent_ram_zone *prz) if (prz->vaddr) { if (pfn_valid(prz->paddr >> PAGE_SHIFT)) { - vunmap(prz->vaddr); + /* We must vunmap() at page-granularity. */ + vunmap(prz->vaddr - offset_in_page(prz->paddr)); } else { iounmap(prz->vaddr); release_mem_region(prz->paddr, prz->size); diff --git a/fs/ubifs/super.c b/fs/ubifs/super.c index 23e7042666a7..bf000c8aeffb 100644 --- a/fs/ubifs/super.c +++ b/fs/ubifs/super.c @@ -1912,7 +1912,9 @@ static int ubifs_remount_fs(struct super_block *sb, int *flags, char *data) mutex_unlock(&c->bu_mutex); } - ubifs_assert(c, c->lst.taken_empty_lebs > 0); + if (!c->need_recovery) + ubifs_assert(c, c->lst.taken_empty_lebs > 0); + return 0; } @@ -1954,6 +1956,9 @@ static struct ubi_volume_desc *open_ubi(const char *name, int mode) int dev, vol; char *endptr; + if (!name || !*name) + return ERR_PTR(-EINVAL); + /* First, try to open using the device node path method */ ubi = ubi_open_volume_path(name, mode); if (!IS_ERR(ubi)) diff --git a/fs/ubifs/xattr.c b/fs/ubifs/xattr.c index 61afdfee4b28..f5ad1ede7990 100644 --- a/fs/ubifs/xattr.c +++ b/fs/ubifs/xattr.c @@ -152,12 +152,6 @@ static int create_xattr(struct ubifs_info *c, struct inode *host, ui->data_len = size; mutex_lock(&host_ui->ui_mutex); - - if (!host->i_nlink) { - err = -ENOENT; - goto out_noent; - } - host->i_ctime = current_time(host); host_ui->xattr_cnt += 1; host_ui->xattr_size += CALC_DENT_SIZE(fname_len(nm)); @@ -190,7 +184,6 @@ out_cancel: host_ui->xattr_size -= CALC_XATTR_BYTES(size); host_ui->xattr_names -= fname_len(nm); host_ui->flags &= ~UBIFS_CRYPT_FL; -out_noent: mutex_unlock(&host_ui->ui_mutex); out_free: make_bad_inode(inode); @@ -242,12 +235,6 @@ static int change_xattr(struct ubifs_info *c, struct inode *host, mutex_unlock(&ui->ui_mutex); mutex_lock(&host_ui->ui_mutex); - - if (!host->i_nlink) { - err = -ENOENT; - goto out_noent; - } - host->i_ctime = current_time(host); host_ui->xattr_size -= CALC_XATTR_BYTES(old_size); host_ui->xattr_size += CALC_XATTR_BYTES(size); @@ -269,7 +256,6 @@ static int change_xattr(struct ubifs_info *c, struct inode *host, out_cancel: host_ui->xattr_size -= CALC_XATTR_BYTES(size); host_ui->xattr_size += CALC_XATTR_BYTES(old_size); -out_noent: mutex_unlock(&host_ui->ui_mutex); make_bad_inode(inode); out_free: @@ -496,12 +482,6 @@ static int remove_xattr(struct ubifs_info *c, struct inode *host, return err; mutex_lock(&host_ui->ui_mutex); - - if (!host->i_nlink) { - err = -ENOENT; - goto out_noent; - } - host->i_ctime = current_time(host); host_ui->xattr_cnt -= 1; host_ui->xattr_size -= CALC_DENT_SIZE(fname_len(nm)); @@ -521,7 +501,6 @@ out_cancel: host_ui->xattr_size += CALC_DENT_SIZE(fname_len(nm)); host_ui->xattr_size += CALC_XATTR_BYTES(ui->data_len); host_ui->xattr_names += fname_len(nm); -out_noent: mutex_unlock(&host_ui->ui_mutex); ubifs_release_budget(c, &req); make_bad_inode(inode); @@ -561,9 +540,6 @@ static int ubifs_xattr_remove(struct inode *host, const char *name) ubifs_assert(c, inode_is_locked(host)); - if (!host->i_nlink) - return -ENOENT; - if (fname_len(&nm) > UBIFS_MAX_NLEN) return -ENAMETOOLONG; diff --git a/include/asm-generic/io.h b/include/asm-generic/io.h index 66d1d45fa2e1..d356f802945a 100644 --- a/include/asm-generic/io.h +++ b/include/asm-generic/io.h @@ -1026,7 +1026,8 @@ static inline void __iomem *ioremap_wt(phys_addr_t offset, size_t size) #define ioport_map ioport_map static inline void __iomem *ioport_map(unsigned long port, unsigned int nr) { - return PCI_IOBASE + (port & MMIO_UPPER_LIMIT); + port &= IO_SPACE_LIMIT; + return (port > MMIO_UPPER_LIMIT) ? NULL : PCI_IOBASE + port; } #endif diff --git a/include/drm/drm_drv.h b/include/drm/drm_drv.h index 46a8009784df..152b3055e9e1 100644 --- a/include/drm/drm_drv.h +++ b/include/drm/drm_drv.h @@ -675,7 +675,7 @@ static inline bool drm_core_check_feature(struct drm_device *dev, int feature) static inline bool drm_drv_uses_atomic_modeset(struct drm_device *dev) { return drm_core_check_feature(dev, DRIVER_ATOMIC) || - dev->mode_config.funcs->atomic_commit != NULL; + (dev->mode_config.funcs && dev->mode_config.funcs->atomic_commit != NULL); } diff --git a/include/linux/blk-cgroup.h b/include/linux/blk-cgroup.h index 34aec30e06c7..6d766a19f2bb 100644 --- a/include/linux/blk-cgroup.h +++ b/include/linux/blk-cgroup.h @@ -56,6 +56,7 @@ struct blkcg { struct list_head all_blkcgs_node; #ifdef CONFIG_CGROUP_WRITEBACK struct list_head cgwb_list; + refcount_t cgwb_refcnt; #endif }; @@ -89,7 +90,6 @@ struct blkg_policy_data { /* the blkg and policy id this per-policy data belongs to */ struct blkcg_gq *blkg; int plid; - bool offline; }; /* @@ -387,6 +387,49 @@ static inline struct blkcg *cpd_to_blkcg(struct blkcg_policy_data *cpd) return cpd ? cpd->blkcg : NULL; } +extern void blkcg_destroy_blkgs(struct blkcg *blkcg); + +#ifdef CONFIG_CGROUP_WRITEBACK + +/** + * blkcg_cgwb_get - get a reference for blkcg->cgwb_list + * @blkcg: blkcg of interest + * + * This is used to track the number of active wb's related to a blkcg. + */ +static inline void blkcg_cgwb_get(struct blkcg *blkcg) +{ + refcount_inc(&blkcg->cgwb_refcnt); +} + +/** + * blkcg_cgwb_put - put a reference for @blkcg->cgwb_list + * @blkcg: blkcg of interest + * + * This is used to track the number of active wb's related to a blkcg. + * When this count goes to zero, all active wb has finished so the + * blkcg can continue destruction by calling blkcg_destroy_blkgs(). + * This work may occur in cgwb_release_workfn() on the cgwb_release + * workqueue. + */ +static inline void blkcg_cgwb_put(struct blkcg *blkcg) +{ + if (refcount_dec_and_test(&blkcg->cgwb_refcnt)) + blkcg_destroy_blkgs(blkcg); +} + +#else + +static inline void blkcg_cgwb_get(struct blkcg *blkcg) { } + +static inline void blkcg_cgwb_put(struct blkcg *blkcg) +{ + /* wb isn't being accounted, so trigger destruction right away */ + blkcg_destroy_blkgs(blkcg); +} + +#endif + /** * blkg_path - format cgroup path of blkg * @blkg: blkg of interest diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index d6869e0e2b64..6980014357d4 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -54,7 +54,7 @@ struct blk_stat_callback; * Maximum number of blkcg policies allowed to be registered concurrently. * Defined here to simplify include dependency. */ -#define BLKCG_MAX_POLS 3 +#define BLKCG_MAX_POLS 5 typedef void (rq_end_io_fn)(struct request *, blk_status_t); diff --git a/include/linux/compiler-gcc.h b/include/linux/compiler-gcc.h index 763bbad1e258..4d36b27214fd 100644 --- a/include/linux/compiler-gcc.h +++ b/include/linux/compiler-gcc.h @@ -79,20 +79,6 @@ #define __noretpoline __attribute__((indirect_branch("keep"))) #endif -/* - * it doesn't make sense on ARM (currently the only user of __naked) - * to trace naked functions because then mcount is called without - * stack and frame pointer being set up and there is no chance to - * restore the lr register to the value before mcount was called. - * - * The asm() bodies of naked functions often depend on standard calling - * conventions, therefore they must be noinline and noclone. - * - * GCC 4.[56] currently fail to enforce this, so we must do so ourselves. - * See GCC PR44290. - */ -#define __naked __attribute__((naked)) noinline __noclone notrace - #define __UNIQUE_ID(prefix) __PASTE(__PASTE(__UNIQUE_ID_, prefix), __COUNTER__) #define __optimize(level) __attribute__((__optimize__(level))) diff --git a/include/linux/compiler_types.h b/include/linux/compiler_types.h index 3525c179698c..db192becfec4 100644 --- a/include/linux/compiler_types.h +++ b/include/linux/compiler_types.h @@ -226,6 +226,14 @@ struct ftrace_likely_data { #define notrace __attribute__((no_instrument_function)) #endif +/* + * it doesn't make sense on ARM (currently the only user of __naked) + * to trace naked functions because then mcount is called without + * stack and frame pointer being set up and there is no chance to + * restore the lr register to the value before mcount was called. + */ +#define __naked __attribute__((naked)) notrace + #define __compiler_offsetof(a, b) __builtin_offsetof(a, b) /* diff --git a/include/linux/fs.h b/include/linux/fs.h index 33322702c910..6c0b4a1c22ff 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1763,6 +1763,7 @@ struct file_operations { u64); int (*dedupe_file_range)(struct file *, loff_t, struct file *, loff_t, u64); + int (*fadvise)(struct file *, loff_t, loff_t, int); } __randomize_layout; struct inode_operations { @@ -3459,4 +3460,8 @@ static inline bool dir_relax_shared(struct inode *inode) extern bool path_noexec(const struct path *path); extern void inode_nohighmem(struct inode *inode); +/* mm/fadvise.c */ +extern int vfs_fadvise(struct file *file, loff_t offset, loff_t len, + int advice); + #endif /* _LINUX_FS_H */ diff --git a/include/linux/genhd.h b/include/linux/genhd.h index 57864422a2c8..25c08c6c7f99 100644 --- a/include/linux/genhd.h +++ b/include/linux/genhd.h @@ -83,10 +83,10 @@ struct partition { } __attribute__((packed)); struct disk_stats { + u64 nsecs[NR_STAT_GROUPS]; unsigned long sectors[NR_STAT_GROUPS]; unsigned long ios[NR_STAT_GROUPS]; unsigned long merges[NR_STAT_GROUPS]; - unsigned long ticks[NR_STAT_GROUPS]; unsigned long io_ticks; unsigned long time_in_queue; }; @@ -354,6 +354,9 @@ static inline void free_part_stats(struct hd_struct *part) #endif /* CONFIG_SMP */ +#define part_stat_read_msecs(part, which) \ + div_u64(part_stat_read(part, nsecs[which]), NSEC_PER_MSEC) + #define part_stat_read_accum(part, field) \ (part_stat_read(part, field[STAT_READ]) + \ part_stat_read(part, field[STAT_WRITE]) + \ diff --git a/include/linux/hid.h b/include/linux/hid.h index 834e6461a690..d44a78362942 100644 --- a/include/linux/hid.h +++ b/include/linux/hid.h @@ -526,6 +526,7 @@ struct hid_input { const char *name; bool registered; struct list_head reports; /* the list of reports */ + unsigned int application; /* application usage for this input */ }; enum hid_type { diff --git a/include/linux/if_tun.h b/include/linux/if_tun.h index 3d2996dc7d85..12e3eebf0ce6 100644 --- a/include/linux/if_tun.h +++ b/include/linux/if_tun.h @@ -16,9 +16,23 @@ #define __IF_TUN_H #include <uapi/linux/if_tun.h> +#include <uapi/linux/virtio_net.h> #define TUN_XDP_FLAG 0x1UL +#define TUN_MSG_UBUF 1 +#define TUN_MSG_PTR 2 +struct tun_msg_ctl { + unsigned short type; + unsigned short num; + void *ptr; +}; + +struct tun_xdp_hdr { + int buflen; + struct virtio_net_hdr gso; +}; + #if defined(CONFIG_TUN) || defined(CONFIG_TUN_MODULE) struct socket *tun_get_socket(struct file *); struct ptr_ring *tun_get_tx_ring(struct file *file); diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h index 8415bf1a9776..495e834c1367 100644 --- a/include/linux/ipv6.h +++ b/include/linux/ipv6.h @@ -274,7 +274,8 @@ struct ipv6_pinfo { */ dontfrag:1, autoflowlabel:1, - autoflowlabel_set:1; + autoflowlabel_set:1, + mc_all:1; __u8 min_hopcount; __u8 tclass; __be32 rcv_flowinfo; diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 0205aee44ded..c926698040e0 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -733,8 +733,6 @@ bool kvm_vcpu_wake_up(struct kvm_vcpu *vcpu); void kvm_vcpu_kick(struct kvm_vcpu *vcpu); int kvm_vcpu_yield_to(struct kvm_vcpu *target); void kvm_vcpu_on_spin(struct kvm_vcpu *vcpu, bool usermode_vcpu_not_eligible); -void kvm_load_guest_fpu(struct kvm_vcpu *vcpu); -void kvm_put_guest_fpu(struct kvm_vcpu *vcpu); void kvm_flush_remote_tlbs(struct kvm *kvm); void kvm_reload_remote_mmus(struct kvm *kvm); diff --git a/include/linux/mfd/da9063/pdata.h b/include/linux/mfd/da9063/pdata.h index 8a125701ef7b..50bed4f89c1a 100644 --- a/include/linux/mfd/da9063/pdata.h +++ b/include/linux/mfd/da9063/pdata.h @@ -21,7 +21,7 @@ /* * Regulator configuration */ -/* DA9063 regulator IDs */ +/* DA9063 and DA9063L regulator IDs */ enum { /* BUCKs */ DA9063_ID_BCORE1, @@ -37,18 +37,20 @@ enum { DA9063_ID_BMEM_BIO_MERGED, /* When two BUCKs are merged, they cannot be reused separately */ - /* LDOs */ + /* LDOs on both DA9063 and DA9063L */ + DA9063_ID_LDO3, + DA9063_ID_LDO7, + DA9063_ID_LDO8, + DA9063_ID_LDO9, + DA9063_ID_LDO11, + + /* DA9063-only LDOs */ DA9063_ID_LDO1, DA9063_ID_LDO2, - DA9063_ID_LDO3, DA9063_ID_LDO4, DA9063_ID_LDO5, DA9063_ID_LDO6, - DA9063_ID_LDO7, - DA9063_ID_LDO8, - DA9063_ID_LDO9, DA9063_ID_LDO10, - DA9063_ID_LDO11, }; /* Regulators platform data */ diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 7a452716de4b..ed73b51f6697 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -362,8 +362,8 @@ struct mlx5_frag_buf { struct mlx5_frag_buf_ctrl { struct mlx5_frag_buf frag_buf; u32 sz_m1; - u32 frag_sz_m1; - u32 strides_offset; + u16 frag_sz_m1; + u16 strides_offset; u8 log_sz; u8 log_stride; u8 log_frag_strides; @@ -583,10 +583,11 @@ struct mlx5_irq_info { }; struct mlx5_fc_stats { - struct rb_root counters; - struct list_head addlist; - /* protect addlist add/splice operations */ - spinlock_t addlist_lock; + spinlock_t counters_idr_lock; /* protects counters_idr */ + struct idr counters_idr; + struct list_head counters; + struct llist_head addlist; + struct llist_head dellist; struct workqueue_struct *wq; struct delayed_work work; @@ -804,7 +805,7 @@ struct mlx5_pps { }; struct mlx5_clock { - rwlock_t lock; + seqlock_t lock; struct cyclecounter cycles; struct timecounter tc; struct hwtstamp_config hwtstamp_config; @@ -995,7 +996,7 @@ static inline u32 mlx5_base_mkey(const u32 key) } static inline void mlx5_fill_fbc_offset(u8 log_stride, u8 log_sz, - u32 strides_offset, + u16 strides_offset, struct mlx5_frag_buf_ctrl *fbc) { fbc->log_stride = log_stride; @@ -1052,7 +1053,7 @@ int mlx5_cmd_free_uar(struct mlx5_core_dev *dev, u32 uarn); void mlx5_health_cleanup(struct mlx5_core_dev *dev); int mlx5_health_init(struct mlx5_core_dev *dev); void mlx5_start_health_poll(struct mlx5_core_dev *dev); -void mlx5_stop_health_poll(struct mlx5_core_dev *dev); +void mlx5_stop_health_poll(struct mlx5_core_dev *dev, bool disable_health); void mlx5_drain_health_wq(struct mlx5_core_dev *dev); void mlx5_trigger_health_work(struct mlx5_core_dev *dev); void mlx5_drain_health_recovery(struct mlx5_core_dev *dev); diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index cd2bc939efd0..5ed8f6292a53 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -341,7 +341,7 @@ struct mm_struct { struct { struct vm_area_struct *mmap; /* list of VMAs */ struct rb_root mm_rb; - u32 vmacache_seqnum; /* per-thread vmacache */ + u64 vmacache_seqnum; /* per-thread vmacache */ #ifdef CONFIG_MMU unsigned long (*get_unmapped_area) (struct file *filp, unsigned long addr, unsigned long len, diff --git a/include/linux/mm_types_task.h b/include/linux/mm_types_task.h index 5fe87687664c..d7016dcb245e 100644 --- a/include/linux/mm_types_task.h +++ b/include/linux/mm_types_task.h @@ -32,7 +32,7 @@ #define VMACACHE_MASK (VMACACHE_SIZE - 1) struct vmacache { - u32 seqnum; + u64 seqnum; struct vm_area_struct *vmas[VMACACHE_SIZE]; }; diff --git a/include/linux/mod_devicetable.h b/include/linux/mod_devicetable.h index 1298a7daa57d..01797cb4587e 100644 --- a/include/linux/mod_devicetable.h +++ b/include/linux/mod_devicetable.h @@ -754,6 +754,7 @@ struct tb_service_id { * struct typec_device_id - USB Type-C alternate mode identifiers * @svid: Standard or Vendor ID * @mode: Mode index + * @driver_data: Driver specific data */ struct typec_device_id { __u16 svid; diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index e2b3bd750c98..1cbbf77a685f 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -2000,7 +2000,6 @@ struct net_device { struct pcpu_lstats __percpu *lstats; struct pcpu_sw_netstats __percpu *tstats; struct pcpu_dstats __percpu *dstats; - struct pcpu_vstats __percpu *vstats; }; #if IS_ENABLED(CONFIG_GARP) @@ -2382,6 +2381,12 @@ struct pcpu_sw_netstats { struct u64_stats_sync syncp; }; +struct pcpu_lstats { + u64 packets; + u64 bytes; + struct u64_stats_sync syncp; +}; + #define __netdev_alloc_pcpu_stats(type, gfp) \ ({ \ typeof(type) __percpu *pcpu_stats = alloc_percpu_gfp(type, gfp);\ diff --git a/include/linux/netpoll.h b/include/linux/netpoll.h index 67662d01130a..3ef82d3a78db 100644 --- a/include/linux/netpoll.h +++ b/include/linux/netpoll.h @@ -49,8 +49,9 @@ struct netpoll_info { }; #ifdef CONFIG_NETPOLL -extern void netpoll_poll_disable(struct net_device *dev); -extern void netpoll_poll_enable(struct net_device *dev); +void netpoll_poll_dev(struct net_device *dev); +void netpoll_poll_disable(struct net_device *dev); +void netpoll_poll_enable(struct net_device *dev); #else static inline void netpoll_poll_disable(struct net_device *dev) { return; } static inline void netpoll_poll_enable(struct net_device *dev) { return; } diff --git a/include/linux/pci.h b/include/linux/pci.h index e72ca8dd6241..6925828f9f25 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -1235,6 +1235,9 @@ void pci_bus_remove_resources(struct pci_bus *bus); int devm_request_pci_bus_resources(struct device *dev, struct list_head *resources); +/* Temporary until new and working PCI SBR API in place */ +int pci_bridge_secondary_bus_reset(struct pci_dev *dev); + #define pci_bus_for_each_resource(bus, res, i) \ for (i = 0; \ (res = pci_bus_resource_n(bus, i)) || i < PCI_BRIDGE_RESOURCE_NUM; \ diff --git a/include/linux/phy.h b/include/linux/phy.h index cd6f637cbbfb..192a1fa0c73b 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -1049,6 +1049,14 @@ int phy_mii_ioctl(struct phy_device *phydev, struct ifreq *ifr, int cmd); int phy_start_interrupts(struct phy_device *phydev); void phy_print_status(struct phy_device *phydev); int phy_set_max_speed(struct phy_device *phydev, u32 max_speed); +void phy_remove_link_mode(struct phy_device *phydev, u32 link_mode); +void phy_support_sym_pause(struct phy_device *phydev); +void phy_support_asym_pause(struct phy_device *phydev); +void phy_set_sym_pause(struct phy_device *phydev, bool rx, bool tx, + bool autoneg); +void phy_set_asym_pause(struct phy_device *phydev, bool rx, bool tx); +bool phy_validate_pause(struct phy_device *phydev, + struct ethtool_pauseparam *pp); int phy_register_fixup(const char *bus_id, u32 phy_uid, u32 phy_uid_mask, int (*run)(struct phy_device *)); diff --git a/include/linux/qed/common_hsi.h b/include/linux/qed/common_hsi.h index 0081fa6d1268..03f59a28fefd 100644 --- a/include/linux/qed/common_hsi.h +++ b/include/linux/qed/common_hsi.h @@ -110,7 +110,7 @@ #define FW_MAJOR_VERSION 8 #define FW_MINOR_VERSION 37 -#define FW_REVISION_VERSION 2 +#define FW_REVISION_VERSION 7 #define FW_ENGINEERING_VERSION 0 /***********************/ @@ -931,12 +931,12 @@ struct db_rdma_dpm_params { #define DB_RDMA_DPM_PARAMS_WQE_SIZE_SHIFT 16 #define DB_RDMA_DPM_PARAMS_RESERVED0_MASK 0x1 #define DB_RDMA_DPM_PARAMS_RESERVED0_SHIFT 27 -#define DB_RDMA_DPM_PARAMS_COMPLETION_FLG_MASK 0x1 -#define DB_RDMA_DPM_PARAMS_COMPLETION_FLG_SHIFT 28 +#define DB_RDMA_DPM_PARAMS_ACK_REQUEST_MASK 0x1 +#define DB_RDMA_DPM_PARAMS_ACK_REQUEST_SHIFT 28 #define DB_RDMA_DPM_PARAMS_S_FLG_MASK 0x1 #define DB_RDMA_DPM_PARAMS_S_FLG_SHIFT 29 -#define DB_RDMA_DPM_PARAMS_RESERVED1_MASK 0x1 -#define DB_RDMA_DPM_PARAMS_RESERVED1_SHIFT 30 +#define DB_RDMA_DPM_PARAMS_COMPLETION_FLG_MASK 0x1 +#define DB_RDMA_DPM_PARAMS_COMPLETION_FLG_SHIFT 30 #define DB_RDMA_DPM_PARAMS_CONN_TYPE_IS_IWARP_MASK 0x1 #define DB_RDMA_DPM_PARAMS_CONN_TYPE_IS_IWARP_SHIFT 31 }; diff --git a/include/linux/qed/iscsi_common.h b/include/linux/qed/iscsi_common.h index b34c573f2b30..66aba505ec56 100644 --- a/include/linux/qed/iscsi_common.h +++ b/include/linux/qed/iscsi_common.h @@ -896,7 +896,7 @@ struct e4_ustorm_iscsi_task_ag_ctx { __le32 exp_cont_len; __le32 total_data_acked; __le32 exp_data_acked; - u8 next_tid_valid; + u8 byte2; u8 byte3; __le16 word1; __le16 next_tid; diff --git a/include/linux/rtnetlink.h b/include/linux/rtnetlink.h index 5225832bd6ff..bb9cb84114c1 100644 --- a/include/linux/rtnetlink.h +++ b/include/linux/rtnetlink.h @@ -6,6 +6,7 @@ #include <linux/mutex.h> #include <linux/netdevice.h> #include <linux/wait.h> +#include <linux/refcount.h> #include <uapi/linux/rtnetlink.h> extern int rtnetlink_send(struct sk_buff *skb, struct net *net, u32 pid, u32 group, int echo); @@ -34,6 +35,7 @@ extern void rtnl_unlock(void); extern int rtnl_trylock(void); extern int rtnl_is_locked(void); extern int rtnl_lock_killable(void); +extern bool refcount_dec_and_rtnl_lock(refcount_t *r); extern wait_queue_head_t netdev_unregistering_wq; extern struct rw_semaphore pernet_ops_rwsem; @@ -83,6 +85,11 @@ static inline struct netdev_queue *dev_ingress_queue(struct net_device *dev) return rtnl_dereference(dev->ingress_queue); } +static inline struct netdev_queue *dev_ingress_queue_rcu(struct net_device *dev) +{ + return rcu_dereference(dev->ingress_queue); +} + struct netdev_queue *dev_ingress_queue_create(struct net_device *dev); #ifdef CONFIG_NET_INGRESS diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 76be85ea392a..87e29710373f 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -691,7 +691,7 @@ struct sk_buff { union { ktime_t tstamp; - u64 skb_mstamp; + u64 skb_mstamp_ns; /* earliest departure time */ }; /* * This is the control buffer. It is free to use for every @@ -1359,6 +1359,17 @@ static inline void skb_zcopy_abort(struct sk_buff *skb) } } +static inline void skb_mark_not_on_list(struct sk_buff *skb) +{ + skb->next = NULL; +} + +static inline void skb_list_del_init(struct sk_buff *skb) +{ + __list_del_entry(&skb->list); + skb_mark_not_on_list(skb); +} + /** * skb_queue_empty - check if a queue is empty * @list: queue head @@ -1613,6 +1624,17 @@ static inline struct sk_buff *skb_peek(const struct sk_buff_head *list_) } /** + * __skb_peek - peek at the head of a non-empty &sk_buff_head + * @list_: list to peek at + * + * Like skb_peek(), but the caller knows that the list is not empty. + */ +static inline struct sk_buff *__skb_peek(const struct sk_buff_head *list_) +{ + return list_->next; +} + +/** * skb_peek_next - peek skb following the given one from a queue * @skb: skb to start from * @list_: list to peek at diff --git a/include/linux/stmmac.h b/include/linux/stmmac.h index c43e9a01b892..7ddfc65586b0 100644 --- a/include/linux/stmmac.h +++ b/include/linux/stmmac.h @@ -30,6 +30,7 @@ #define MTL_MAX_RX_QUEUES 8 #define MTL_MAX_TX_QUEUES 8 +#define STMMAC_CH_MAX 8 #define STMMAC_RX_COE_NONE 0 #define STMMAC_RX_COE_TYPE1 1 diff --git a/include/linux/tcp.h b/include/linux/tcp.h index 263e37271afd..848f5b25e178 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -248,6 +248,8 @@ struct tcp_sock { syn_smc:1; /* SYN includes SMC */ u32 tlp_high_seq; /* snd_nxt at the time of TLP retransmit. */ + u64 tcp_wstamp_ns; /* departure time for next sent data packet */ + /* RTT measurement */ u64 tcp_mstamp; /* most recent packet received/sent */ u32 srtt_us; /* smoothed round trip time << 3 in usecs */ diff --git a/include/linux/timekeeping.h b/include/linux/timekeeping.h index 5d738804e3d6..a5a3cfc3c2fa 100644 --- a/include/linux/timekeeping.h +++ b/include/linux/timekeeping.h @@ -258,8 +258,8 @@ extern void ktime_get_snapshot(struct system_time_snapshot *systime_snapshot); extern int persistent_clock_is_local; extern void read_persistent_clock64(struct timespec64 *ts); -void read_persistent_clock_and_boot_offset(struct timespec64 *wall_clock, - struct timespec64 *boot_offset); +void read_persistent_wall_and_boot_offset(struct timespec64 *wall_clock, + struct timespec64 *boot_offset); extern int update_persistent_clock64(struct timespec64 now); /* diff --git a/include/linux/tracepoint.h b/include/linux/tracepoint.h index 7f2e16e76ac4..041f7e56a289 100644 --- a/include/linux/tracepoint.h +++ b/include/linux/tracepoint.h @@ -158,8 +158,10 @@ extern void syscall_unregfunc(void); * For rcuidle callers, use srcu since sched-rcu \ * doesn't work from the idle path. \ */ \ - if (rcuidle) \ + if (rcuidle) { \ idx = srcu_read_lock_notrace(&tracepoint_srcu); \ + rcu_irq_enter_irqson(); \ + } \ \ it_func_ptr = rcu_dereference_raw((tp)->funcs); \ \ @@ -171,8 +173,10 @@ extern void syscall_unregfunc(void); } while ((++it_func_ptr)->func); \ } \ \ - if (rcuidle) \ + if (rcuidle) { \ + rcu_irq_exit_irqson(); \ srcu_read_unlock_notrace(&tracepoint_srcu, idx);\ + } \ \ preempt_enable_notrace(); \ } while (0) diff --git a/include/linux/vga_switcheroo.h b/include/linux/vga_switcheroo.h index a34539b7f750..7e6ac0114d55 100644 --- a/include/linux/vga_switcheroo.h +++ b/include/linux/vga_switcheroo.h @@ -133,15 +133,18 @@ struct vga_switcheroo_handler { * @can_switch: check if the device is in a position to switch now. * Mandatory. The client should return false if a user space process * has one of its device files open + * @gpu_bound: notify the client id to audio client when the GPU is bound. * * Client callbacks. A client can be either a GPU or an audio device on a GPU. * The @set_gpu_state and @can_switch methods are mandatory, @reprobe may be * set to NULL. For audio clients, the @reprobe member is bogus. + * OTOH, @gpu_bound is only for audio clients, and not used for GPU clients. */ struct vga_switcheroo_client_ops { void (*set_gpu_state)(struct pci_dev *dev, enum vga_switcheroo_state); void (*reprobe)(struct pci_dev *dev); bool (*can_switch)(struct pci_dev *dev); + void (*gpu_bound)(struct pci_dev *dev, enum vga_switcheroo_client_id); }; #if defined(CONFIG_VGA_SWITCHEROO) diff --git a/include/linux/vm_event_item.h b/include/linux/vm_event_item.h index 5c7f010676a7..47a3441cf4c4 100644 --- a/include/linux/vm_event_item.h +++ b/include/linux/vm_event_item.h @@ -105,7 +105,6 @@ enum vm_event_item { PGPGIN, PGPGOUT, PSWPIN, PSWPOUT, #ifdef CONFIG_DEBUG_VM_VMACACHE VMACACHE_FIND_CALLS, VMACACHE_FIND_HITS, - VMACACHE_FULL_FLUSHES, #endif #ifdef CONFIG_SWAP SWAP_RA, diff --git a/include/linux/vmacache.h b/include/linux/vmacache.h index 3e9a963edd6a..6fce268a4588 100644 --- a/include/linux/vmacache.h +++ b/include/linux/vmacache.h @@ -10,7 +10,6 @@ static inline void vmacache_flush(struct task_struct *tsk) memset(tsk->vmacache.vmas, 0, sizeof(tsk->vmacache.vmas)); } -extern void vmacache_flush_all(struct mm_struct *mm); extern void vmacache_update(unsigned long addr, struct vm_area_struct *newvma); extern struct vm_area_struct *vmacache_find(struct mm_struct *mm, unsigned long addr); @@ -24,10 +23,6 @@ extern struct vm_area_struct *vmacache_find_exact(struct mm_struct *mm, static inline void vmacache_invalidate(struct mm_struct *mm) { mm->vmacache_seqnum++; - - /* deal with overflows */ - if (unlikely(mm->vmacache_seqnum == 0)) - vmacache_flush_all(mm); } #endif /* __LINUX_VMACACHE_H */ diff --git a/include/net/act_api.h b/include/net/act_api.h index c6f195b3c706..1ddff3360592 100644 --- a/include/net/act_api.h +++ b/include/net/act_api.h @@ -31,10 +31,12 @@ struct tc_action { int tcfa_action; struct tcf_t tcfa_tm; struct gnet_stats_basic_packed tcfa_bstats; + struct gnet_stats_basic_packed tcfa_bstats_hw; struct gnet_stats_queue tcfa_qstats; struct net_rate_estimator __rcu *tcfa_rate_est; spinlock_t tcfa_lock; struct gnet_stats_basic_cpu __percpu *cpu_bstats; + struct gnet_stats_basic_cpu __percpu *cpu_bstats_hw; struct gnet_stats_queue __percpu *cpu_qstats; struct tc_cookie __rcu *act_cookie; struct tcf_chain *goto_chain; @@ -94,7 +96,7 @@ struct tc_action_ops { struct netlink_callback *, int, const struct tc_action_ops *, struct netlink_ext_ack *); - void (*stats_update)(struct tc_action *, u64, u32, u64); + void (*stats_update)(struct tc_action *, u64, u32, u64, bool); size_t (*get_fill_size)(const struct tc_action *act); struct net_device *(*get_dev)(const struct tc_action *a); void (*put_dev)(struct net_device *dev); @@ -182,13 +184,13 @@ int tcf_action_copy_stats(struct sk_buff *, struct tc_action *, int); #endif /* CONFIG_NET_CLS_ACT */ static inline void tcf_action_stats_update(struct tc_action *a, u64 bytes, - u64 packets, u64 lastuse) + u64 packets, u64 lastuse, bool hw) { #ifdef CONFIG_NET_CLS_ACT if (!a->ops->stats_update) return; - a->ops->stats_update(a, bytes, packets, lastuse); + a->ops->stats_update(a, bytes, packets, lastuse, hw); #endif } diff --git a/include/net/dsa.h b/include/net/dsa.h index 461e8a7661b7..23690c44e167 100644 --- a/include/net/dsa.h +++ b/include/net/dsa.h @@ -35,6 +35,7 @@ enum dsa_tag_protocol { DSA_TAG_PROTO_BRCM_PREPEND, DSA_TAG_PROTO_DSA, DSA_TAG_PROTO_EDSA, + DSA_TAG_PROTO_GSWIP, DSA_TAG_PROTO_KSZ, DSA_TAG_PROTO_LAN9303, DSA_TAG_PROTO_MTK, diff --git a/include/net/gen_stats.h b/include/net/gen_stats.h index 883bb9085f15..946bd53a9f81 100644 --- a/include/net/gen_stats.h +++ b/include/net/gen_stats.h @@ -44,6 +44,10 @@ void __gnet_stats_copy_basic(const seqcount_t *running, struct gnet_stats_basic_packed *bstats, struct gnet_stats_basic_cpu __percpu *cpu, struct gnet_stats_basic_packed *b); +int gnet_stats_copy_basic_hw(const seqcount_t *running, + struct gnet_dump *d, + struct gnet_stats_basic_cpu __percpu *cpu, + struct gnet_stats_basic_packed *b); int gnet_stats_copy_rate_est(struct gnet_dump *d, struct net_rate_estimator __rcu **ptr); int gnet_stats_copy_queue(struct gnet_dump *d, diff --git a/include/net/ip6_fib.h b/include/net/ip6_fib.h index 3d4930528db0..f06e968f1992 100644 --- a/include/net/ip6_fib.h +++ b/include/net/ip6_fib.h @@ -182,7 +182,6 @@ struct rt6_info { struct in6_addr rt6i_gateway; struct inet6_dev *rt6i_idev; u32 rt6i_flags; - struct rt6key rt6i_prefsrc; struct list_head rt6i_uncached; struct uncached_list *rt6i_uncached_list; @@ -413,6 +412,25 @@ int fib6_add(struct fib6_node *root, struct fib6_info *rt, struct nl_info *info, struct netlink_ext_ack *extack); int fib6_del(struct fib6_info *rt, struct nl_info *info); +static inline +void rt6_get_prefsrc(const struct rt6_info *rt, struct in6_addr *addr) +{ + const struct fib6_info *from; + + rcu_read_lock(); + + from = rcu_dereference(rt->from); + if (from) { + *addr = from->fib6_prefsrc.addr; + } else { + struct in6_addr in6_zero = {}; + + *addr = in6_zero; + } + + rcu_read_unlock(); +} + static inline struct net_device *fib6_info_nh_dev(const struct fib6_info *f6i) { return f6i->fib6_nh.nh_dev; diff --git a/include/net/ip_fib.h b/include/net/ip_fib.h index 69c91d1934c1..f7c109e37298 100644 --- a/include/net/ip_fib.h +++ b/include/net/ip_fib.h @@ -373,6 +373,7 @@ static inline bool fib4_rules_early_flow_dissect(struct net *net, extern const struct nla_policy rtm_ipv4_policy[]; void ip_fib_init(void); __be32 fib_compute_spec_dst(struct sk_buff *skb); +bool fib_info_nh_uses_dev(struct fib_info *fi, const struct net_device *dev); int fib_validate_source(struct sk_buff *skb, __be32 src, __be32 dst, u8 tos, int oif, struct net_device *dev, struct in_device *idev, u32 *itag); diff --git a/include/net/llc.h b/include/net/llc.h index 890a87318014..df282d9b4017 100644 --- a/include/net/llc.h +++ b/include/net/llc.h @@ -66,6 +66,7 @@ struct llc_sap { int sk_count; struct hlist_nulls_head sk_laddr_hash[LLC_SK_LADDR_HASH_ENTRIES]; struct hlist_head sk_dev_hash[LLC_SK_DEV_HASH_ENTRIES]; + struct rcu_head rcu; }; static inline diff --git a/include/net/neighbour.h b/include/net/neighbour.h index 6c1eecd56a4d..0874f7fcd859 100644 --- a/include/net/neighbour.h +++ b/include/net/neighbour.h @@ -544,4 +544,19 @@ static inline void neigh_update_ext_learned(struct neighbour *neigh, u32 flags, *notify = 1; } } + +static inline void neigh_update_is_router(struct neighbour *neigh, u32 flags, + int *notify) +{ + u8 ndm_flags = 0; + + ndm_flags |= (flags & NEIGH_UPDATE_F_ISROUTER) ? NTF_ROUTER : 0; + if ((neigh->flags ^ ndm_flags) & NTF_ROUTER) { + if (ndm_flags & NTF_ROUTER) + neigh->flags |= NTF_ROUTER; + else + neigh->flags &= ~NTF_ROUTER; + *notify = 1; + } +} #endif diff --git a/include/net/netfilter/nf_conntrack_timeout.h b/include/net/netfilter/nf_conntrack_timeout.h index d5f62cc6c2ae..3394d75e1c80 100644 --- a/include/net/netfilter/nf_conntrack_timeout.h +++ b/include/net/netfilter/nf_conntrack_timeout.h @@ -30,7 +30,7 @@ struct nf_conn_timeout { }; static inline unsigned int * -nf_ct_timeout_data(struct nf_conn_timeout *t) +nf_ct_timeout_data(const struct nf_conn_timeout *t) { struct nf_ct_timeout *timeout; diff --git a/include/net/netlink.h b/include/net/netlink.h index 0c154f98e987..318b1ded3833 100644 --- a/include/net/netlink.h +++ b/include/net/netlink.h @@ -180,6 +180,9 @@ enum { NLA_S32, NLA_S64, NLA_BITFIELD32, + NLA_REJECT, + NLA_EXACT_LEN, + NLA_EXACT_LEN_WARN, __NLA_TYPE_MAX, }; @@ -208,9 +211,23 @@ enum { * NLA_MSECS Leaving the length field zero will verify the * given type fits, using it verifies minimum length * just like "All other" - * NLA_BITFIELD32 A 32-bit bitmap/bitselector attribute + * NLA_BITFIELD32 Unused + * NLA_REJECT Unused + * NLA_EXACT_LEN Attribute must have exactly this length, otherwise + * it is rejected. + * NLA_EXACT_LEN_WARN Attribute should have exactly this length, a warning + * is logged if it is longer, shorter is rejected. * All other Minimum length of attribute payload * + * Meaning of `validation_data' field: + * NLA_BITFIELD32 This is a 32-bit bitmap/bitselector attribute and + * validation data must point to a u32 value of valid + * flags + * NLA_REJECT This attribute is always rejected and validation data + * may point to a string to report as the error instead + * of the generic one in extended ACK. + * All other Unused + * * Example: * static const struct nla_policy my_policy[ATTR_MAX+1] = { * [ATTR_FOO] = { .type = NLA_U16 }, @@ -225,6 +242,13 @@ struct nla_policy { void *validation_data; }; +#define NLA_POLICY_EXACT_LEN(_len) { .type = NLA_EXACT_LEN, .len = _len } +#define NLA_POLICY_EXACT_LEN_WARN(_len) { .type = NLA_EXACT_LEN_WARN, \ + .len = _len } + +#define NLA_POLICY_ETH_ADDR NLA_POLICY_EXACT_LEN(ETH_ALEN) +#define NLA_POLICY_ETH_ADDR_COMPAT NLA_POLICY_EXACT_LEN_WARN(ETH_ALEN) + /** * struct nl_info - netlink source information * @nlh: Netlink message header of original request diff --git a/include/net/nfc/hci.h b/include/net/nfc/hci.h index 316694dafa5b..008f466d1da7 100644 --- a/include/net/nfc/hci.h +++ b/include/net/nfc/hci.h @@ -87,7 +87,7 @@ struct nfc_hci_pipe { * According to specification 102 622 chapter 4.4 Pipes, * the pipe identifier is 7 bits long. */ -#define NFC_HCI_MAX_PIPES 127 +#define NFC_HCI_MAX_PIPES 128 struct nfc_hci_init_data { u8 gate_count; struct nfc_hci_gate gates[NFC_HCI_MAX_CUSTOM_GATES]; diff --git a/include/net/pkt_cls.h b/include/net/pkt_cls.h index 75a3f3fdb359..bbfe27f86d5f 100644 --- a/include/net/pkt_cls.h +++ b/include/net/pkt_cls.h @@ -318,7 +318,7 @@ tcf_exts_stats_update(const struct tcf_exts *exts, for (i = 0; i < exts->nr_actions; i++) { struct tc_action *a = exts->actions[i]; - tcf_action_stats_update(a, bytes, packets, lastuse); + tcf_action_stats_update(a, bytes, packets, lastuse, true); } preempt_enable(); diff --git a/include/net/pkt_sched.h b/include/net/pkt_sched.h index 7dc769e5452b..a16fbe9a2a67 100644 --- a/include/net/pkt_sched.h +++ b/include/net/pkt_sched.h @@ -102,6 +102,7 @@ int qdisc_set_default(const char *id); void qdisc_hash_add(struct Qdisc *q, bool invisible); void qdisc_hash_del(struct Qdisc *q); struct Qdisc *qdisc_lookup(struct net_device *dev, u32 handle); +struct Qdisc *qdisc_lookup_rcu(struct net_device *dev, u32 handle); struct qdisc_rate_table *qdisc_get_rtab(struct tc_ratespec *r, struct nlattr *tab, struct netlink_ext_ack *extack); diff --git a/include/net/rtnetlink.h b/include/net/rtnetlink.h index 0bbaa5488423..cf26e5aacac4 100644 --- a/include/net/rtnetlink.h +++ b/include/net/rtnetlink.h @@ -165,6 +165,7 @@ int rtnl_configure_link(struct net_device *dev, const struct ifinfomsg *ifm); int rtnl_nla_parse_ifla(struct nlattr **tb, const struct nlattr *head, int len, struct netlink_ext_ack *exterr); +struct net *rtnl_get_net_ns_capable(struct sock *sk, int netnsid); #define MODULE_ALIAS_RTNL_LINK(kind) MODULE_ALIAS("rtnl-link-" kind) diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h index 1b81ba85fd2d..4d736427a4cb 100644 --- a/include/net/sch_generic.h +++ b/include/net/sch_generic.h @@ -106,6 +106,7 @@ struct Qdisc { spinlock_t busylock ____cacheline_aligned_in_smp; spinlock_t seqlock; + struct rcu_head rcu; }; static inline void qdisc_refcount_inc(struct Qdisc *qdisc) @@ -115,6 +116,19 @@ static inline void qdisc_refcount_inc(struct Qdisc *qdisc) refcount_inc(&qdisc->refcnt); } +/* Intended to be used by unlocked users, when concurrent qdisc release is + * possible. + */ + +static inline struct Qdisc *qdisc_refcount_inc_nz(struct Qdisc *qdisc) +{ + if (qdisc->flags & TCQ_F_BUILTIN) + return qdisc; + if (refcount_inc_not_zero(&qdisc->refcnt)) + return qdisc; + return NULL; +} + static inline bool qdisc_is_running(struct Qdisc *qdisc) { if (qdisc->flags & TCQ_F_NOLOCK) @@ -337,7 +351,7 @@ struct tcf_chain { struct tcf_block { struct list_head chain_list; u32 index; /* block index for shared blocks */ - unsigned int refcnt; + refcount_t refcnt; struct net *net; struct Qdisc *q; struct list_head cb_list; @@ -349,6 +363,7 @@ struct tcf_block { struct tcf_chain *chain; struct list_head filter_chain_list; } chain0; + struct rcu_head rcu; }; static inline void tcf_block_offload_inc(struct tcf_block *block, u32 *flags) @@ -368,7 +383,7 @@ static inline void tcf_block_offload_dec(struct tcf_block *block, u32 *flags) } static inline void -tc_cls_offload_cnt_update(struct tcf_block *block, unsigned int *cnt, +tc_cls_offload_cnt_update(struct tcf_block *block, u32 *cnt, u32 *flags, bool add) { if (add) { @@ -560,7 +575,8 @@ void dev_deactivate_many(struct list_head *head); struct Qdisc *dev_graft_qdisc(struct netdev_queue *dev_queue, struct Qdisc *qdisc); void qdisc_reset(struct Qdisc *qdisc); -void qdisc_destroy(struct Qdisc *qdisc); +void qdisc_put(struct Qdisc *qdisc); +void qdisc_put_unlocked(struct Qdisc *qdisc); void qdisc_tree_reduce_backlog(struct Qdisc *qdisc, unsigned int n, unsigned int len); struct Qdisc *qdisc_alloc(struct netdev_queue *dev_queue, @@ -834,8 +850,8 @@ static inline void qdisc_skb_head_init(struct qdisc_skb_head *qh) qh->qlen = 0; } -static inline int __qdisc_enqueue_tail(struct sk_buff *skb, struct Qdisc *sch, - struct qdisc_skb_head *qh) +static inline void __qdisc_enqueue_tail(struct sk_buff *skb, + struct qdisc_skb_head *qh) { struct sk_buff *last = qh->tail; @@ -848,14 +864,24 @@ static inline int __qdisc_enqueue_tail(struct sk_buff *skb, struct Qdisc *sch, qh->head = skb; } qh->qlen++; - qdisc_qstats_backlog_inc(sch, skb); +} +static inline int qdisc_enqueue_tail(struct sk_buff *skb, struct Qdisc *sch) +{ + __qdisc_enqueue_tail(skb, &sch->q); + qdisc_qstats_backlog_inc(sch, skb); return NET_XMIT_SUCCESS; } -static inline int qdisc_enqueue_tail(struct sk_buff *skb, struct Qdisc *sch) +static inline void __qdisc_enqueue_head(struct sk_buff *skb, + struct qdisc_skb_head *qh) { - return __qdisc_enqueue_tail(skb, sch, &sch->q); + skb->next = qh->head; + + if (!qh->head) + qh->tail = skb; + qh->head = skb; + qh->qlen++; } static inline struct sk_buff *__qdisc_dequeue_head(struct qdisc_skb_head *qh) diff --git a/include/net/sock.h b/include/net/sock.h index 433f45fc2d68..38cae35f6e16 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -800,6 +800,7 @@ enum sock_flags { SOCK_SELECT_ERR_QUEUE, /* Wake select on error queue */ SOCK_RCU_FREE, /* wait rcu grace period in sk_destruct() */ SOCK_TXTIME, + SOCK_XDP, /* XDP is attached */ }; #define SK_FLAGS_TIMESTAMP ((1UL << SOCK_TIMESTAMP) | (1UL << SOCK_TIMESTAMPING_RX_SOFTWARE)) diff --git a/include/net/tcp.h b/include/net/tcp.h index 770917d0caa7..ff15d8e0d525 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -732,7 +732,7 @@ void tcp_send_window_probe(struct sock *sk); static inline u64 tcp_clock_ns(void) { - return local_clock(); + return ktime_get_tai_ns(); } static inline u64 tcp_clock_us(void) @@ -752,17 +752,7 @@ static inline u32 tcp_time_stamp_raw(void) return div_u64(tcp_clock_ns(), NSEC_PER_SEC / TCP_TS_HZ); } - -/* Refresh 1us clock of a TCP socket, - * ensuring monotically increasing values. - */ -static inline void tcp_mstamp_refresh(struct tcp_sock *tp) -{ - u64 val = tcp_clock_us(); - - if (val > tp->tcp_mstamp) - tp->tcp_mstamp = val; -} +void tcp_mstamp_refresh(struct tcp_sock *tp); static inline u32 tcp_stamp_us_delta(u64 t1, u64 t0) { @@ -771,7 +761,13 @@ static inline u32 tcp_stamp_us_delta(u64 t1, u64 t0) static inline u32 tcp_skb_timestamp(const struct sk_buff *skb) { - return div_u64(skb->skb_mstamp, USEC_PER_SEC / TCP_TS_HZ); + return div_u64(skb->skb_mstamp_ns, NSEC_PER_SEC / TCP_TS_HZ); +} + +/* provide the departure time in us unit */ +static inline u64 tcp_skb_timestamp_us(const struct sk_buff *skb) +{ + return div_u64(skb->skb_mstamp_ns, NSEC_PER_USEC); } @@ -817,7 +813,7 @@ struct tcp_skb_cb { #define TCPCB_SACKED_RETRANS 0x02 /* SKB retransmitted */ #define TCPCB_LOST 0x04 /* SKB is lost */ #define TCPCB_TAGBITS 0x07 /* All tag bits */ -#define TCPCB_REPAIRED 0x10 /* SKB repaired (no skb_mstamp) */ +#define TCPCB_REPAIRED 0x10 /* SKB repaired (no skb_mstamp_ns) */ #define TCPCB_EVER_RETRANS 0x80 /* Ever retransmitted frame */ #define TCPCB_RETRANS (TCPCB_SACKED_RETRANS|TCPCB_EVER_RETRANS| \ TCPCB_REPAIRED) @@ -1940,7 +1936,7 @@ static inline s64 tcp_rto_delta_us(const struct sock *sk) { const struct sk_buff *skb = tcp_rtx_queue_head(sk); u32 rto = inet_csk(sk)->icsk_rto; - u64 rto_time_stamp_us = skb->skb_mstamp + jiffies_to_usecs(rto); + u64 rto_time_stamp_us = tcp_skb_timestamp_us(skb) + jiffies_to_usecs(rto); return rto_time_stamp_us - tcp_sk(sk)->tcp_mstamp; } diff --git a/include/net/tls.h b/include/net/tls.h index cd0a65bd92f9..1615fb5ea114 100644 --- a/include/net/tls.h +++ b/include/net/tls.h @@ -41,7 +41,7 @@ #include <linux/tcp.h> #include <net/tcp.h> #include <net/strparser.h> - +#include <crypto/aead.h> #include <uapi/linux/tls.h> @@ -93,24 +93,48 @@ enum { TLS_NUM_CONFIG, }; -struct tls_sw_context_tx { - struct crypto_aead *aead_send; - struct crypto_wait async_wait; - - char aad_space[TLS_AAD_SPACE_SIZE]; - - unsigned int sg_plaintext_size; - int sg_plaintext_num_elem; +/* TLS records are maintained in 'struct tls_rec'. It stores the memory pages + * allocated or mapped for each TLS record. After encryption, the records are + * stores in a linked list. + */ +struct tls_rec { + struct list_head list; + int tx_ready; + int tx_flags; struct scatterlist sg_plaintext_data[MAX_SKB_FRAGS]; - - unsigned int sg_encrypted_size; - int sg_encrypted_num_elem; struct scatterlist sg_encrypted_data[MAX_SKB_FRAGS]; /* AAD | sg_plaintext_data | sg_tag */ struct scatterlist sg_aead_in[2]; /* AAD | sg_encrypted_data (data contain overhead for hdr&iv&tag) */ struct scatterlist sg_aead_out[2]; + + unsigned int sg_plaintext_size; + unsigned int sg_encrypted_size; + int sg_plaintext_num_elem; + int sg_encrypted_num_elem; + + char aad_space[TLS_AAD_SPACE_SIZE]; + struct aead_request aead_req; + u8 aead_req_ctx[]; +}; + +struct tx_work { + struct delayed_work work; + struct sock *sk; +}; + +struct tls_sw_context_tx { + struct crypto_aead *aead_send; + struct crypto_wait async_wait; + struct tx_work tx_work; + struct tls_rec *open_rec; + struct list_head tx_list; + atomic_t encrypt_pending; + int async_notify; + +#define BIT_TX_SCHEDULED 0 + unsigned long tx_bitmask; }; struct tls_sw_context_rx { @@ -128,10 +152,6 @@ struct tls_sw_context_rx { bool async_notify; }; -struct decrypt_req_ctx { - struct sock *sk; -}; - struct tls_record_info { struct list_head list; u32 end_seq; @@ -177,15 +197,14 @@ struct cipher_context { char *rec_seq; }; +union tls_crypto_context { + struct tls_crypto_info info; + struct tls12_crypto_info_aes_gcm_128 aes_gcm_128; +}; + struct tls_context { - union { - struct tls_crypto_info crypto_send; - struct tls12_crypto_info_aes_gcm_128 crypto_send_aes_gcm_128; - }; - union { - struct tls_crypto_info crypto_recv; - struct tls12_crypto_info_aes_gcm_128 crypto_recv_aes_gcm_128; - }; + union tls_crypto_context crypto_send; + union tls_crypto_context crypto_recv; struct list_head list; struct net_device *netdev; @@ -202,6 +221,7 @@ struct tls_context { struct scatterlist *partially_sent_record; u16 partially_sent_offset; + unsigned long flags; bool in_tcp_sendpages; @@ -266,6 +286,7 @@ int tls_device_sendpage(struct sock *sk, struct page *page, void tls_device_sk_destruct(struct sock *sk); void tls_device_init(void); void tls_device_cleanup(void); +int tls_tx_records(struct sock *sk, int flags); struct tls_record_info *tls_get_record(struct tls_offload_context_tx *context, u32 seq, u64 *p_record_sn); @@ -284,6 +305,9 @@ void tls_sk_destruct(struct sock *sk, struct tls_context *ctx); int tls_push_sg(struct sock *sk, struct tls_context *ctx, struct scatterlist *sg, u16 first_offset, int flags); +int tls_push_partial_record(struct sock *sk, struct tls_context *ctx, + int flags); + int tls_push_pending_closed_record(struct sock *sk, struct tls_context *ctx, int flags, long *timeo); @@ -317,6 +341,17 @@ static inline bool tls_is_pending_open_record(struct tls_context *tls_ctx) return tls_ctx->pending_open_record_frags; } +static inline bool is_tx_ready(struct tls_sw_context_tx *ctx) +{ + struct tls_rec *rec; + + rec = list_first_entry(&ctx->tx_list, struct tls_rec, list); + if (!rec) + return false; + + return READ_ONCE(rec->tx_ready); +} + struct sk_buff * tls_validate_xmit_skb(struct sock *sk, struct net_device *dev, struct sk_buff *skb); @@ -373,8 +408,8 @@ static inline void tls_fill_prepend(struct tls_context *ctx, * size KTLS_DTLS_HEADER_SIZE + KTLS_DTLS_NONCE_EXPLICIT_SIZE */ buf[0] = record_type; - buf[1] = TLS_VERSION_MINOR(ctx->crypto_send.version); - buf[2] = TLS_VERSION_MAJOR(ctx->crypto_send.version); + buf[1] = TLS_VERSION_MINOR(ctx->crypto_send.info.version); + buf[2] = TLS_VERSION_MAJOR(ctx->crypto_send.info.version); /* we can use IV for nonce explicit according to spec */ buf[3] = pkt_len >> 8; buf[4] = pkt_len & 0xFF; diff --git a/include/net/vxlan.h b/include/net/vxlan.h index b99a02ae3934..7ef15179f263 100644 --- a/include/net/vxlan.h +++ b/include/net/vxlan.h @@ -5,7 +5,6 @@ #include <linux/if_vlan.h> #include <net/udp_tunnel.h> #include <net/dst_metadata.h> -#include <net/udp_tunnel.h> /* VXLAN protocol (RFC 7348) header: * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ diff --git a/include/net/xdp_sock.h b/include/net/xdp_sock.h index 932ca0dad6f3..70a115bea4f4 100644 --- a/include/net/xdp_sock.h +++ b/include/net/xdp_sock.h @@ -21,6 +21,12 @@ struct xdp_umem_page { dma_addr_t dma; }; +struct xdp_umem_fq_reuse { + u32 nentries; + u32 length; + u64 handles[]; +}; + struct xdp_umem { struct xsk_queue *fq; struct xsk_queue *cq; @@ -37,6 +43,7 @@ struct xdp_umem { struct page **pgs; u32 npgs; struct net_device *dev; + struct xdp_umem_fq_reuse *fq_reuse; u16 queue_id; bool zc; spinlock_t xsk_list_lock; @@ -75,6 +82,10 @@ void xsk_umem_discard_addr(struct xdp_umem *umem); void xsk_umem_complete_tx(struct xdp_umem *umem, u32 nb_entries); bool xsk_umem_consume_tx(struct xdp_umem *umem, dma_addr_t *dma, u32 *len); void xsk_umem_consume_tx_done(struct xdp_umem *umem); +struct xdp_umem_fq_reuse *xsk_reuseq_prepare(u32 nentries); +struct xdp_umem_fq_reuse *xsk_reuseq_swap(struct xdp_umem *umem, + struct xdp_umem_fq_reuse *newq); +void xsk_reuseq_free(struct xdp_umem_fq_reuse *rq); static inline char *xdp_umem_get_data(struct xdp_umem *umem, u64 addr) { @@ -85,6 +96,35 @@ static inline dma_addr_t xdp_umem_get_dma(struct xdp_umem *umem, u64 addr) { return umem->pages[addr >> PAGE_SHIFT].dma + (addr & (PAGE_SIZE - 1)); } + +/* Reuse-queue aware version of FILL queue helpers */ +static inline u64 *xsk_umem_peek_addr_rq(struct xdp_umem *umem, u64 *addr) +{ + struct xdp_umem_fq_reuse *rq = umem->fq_reuse; + + if (!rq->length) + return xsk_umem_peek_addr(umem, addr); + + *addr = rq->handles[rq->length - 1]; + return addr; +} + +static inline void xsk_umem_discard_addr_rq(struct xdp_umem *umem) +{ + struct xdp_umem_fq_reuse *rq = umem->fq_reuse; + + if (!rq->length) + xsk_umem_discard_addr(umem); + else + rq->length--; +} + +static inline void xsk_umem_fq_reuse(struct xdp_umem *umem, u64 addr) +{ + struct xdp_umem_fq_reuse *rq = umem->fq_reuse; + + rq->handles[rq->length++] = addr; +} #else static inline int xsk_generic_rcv(struct xdp_sock *xs, struct xdp_buff *xdp) { @@ -128,6 +168,21 @@ static inline void xsk_umem_consume_tx_done(struct xdp_umem *umem) { } +static inline struct xdp_umem_fq_reuse *xsk_reuseq_prepare(u32 nentries) +{ + return NULL; +} + +static inline struct xdp_umem_fq_reuse *xsk_reuseq_swap( + struct xdp_umem *umem, + struct xdp_umem_fq_reuse *newq) +{ + return NULL; +} +static inline void xsk_reuseq_free(struct xdp_umem_fq_reuse *rq) +{ +} + static inline char *xdp_umem_get_data(struct xdp_umem *umem, u64 addr) { return NULL; @@ -137,6 +192,20 @@ static inline dma_addr_t xdp_umem_get_dma(struct xdp_umem *umem, u64 addr) { return 0; } + +static inline u64 *xsk_umem_peek_addr_rq(struct xdp_umem *umem, u64 *addr) +{ + return NULL; +} + +static inline void xsk_umem_discard_addr_rq(struct xdp_umem *umem) +{ +} + +static inline void xsk_umem_fq_reuse(struct xdp_umem *umem, u64 addr) +{ +} + #endif /* CONFIG_XDP_SOCKETS */ #endif /* _LINUX_XDP_SOCK_H */ diff --git a/include/sound/hdaudio.h b/include/sound/hdaudio.h index 6f1e1f3b3063..cd1773d0e08f 100644 --- a/include/sound/hdaudio.h +++ b/include/sound/hdaudio.h @@ -412,6 +412,7 @@ void snd_hdac_bus_init_cmd_io(struct hdac_bus *bus); void snd_hdac_bus_stop_cmd_io(struct hdac_bus *bus); void snd_hdac_bus_enter_link_reset(struct hdac_bus *bus); void snd_hdac_bus_exit_link_reset(struct hdac_bus *bus); +int snd_hdac_bus_reset_link(struct hdac_bus *bus, bool full_reset); void snd_hdac_bus_update_rirb(struct hdac_bus *bus); int snd_hdac_bus_handle_stream_irq(struct hdac_bus *bus, unsigned int status, diff --git a/include/sound/soc-dapm.h b/include/sound/soc-dapm.h index af9ef16cc34d..fdaaafdc7a00 100644 --- a/include/sound/soc-dapm.h +++ b/include/sound/soc-dapm.h @@ -407,6 +407,7 @@ int snd_soc_dapm_new_dai_widgets(struct snd_soc_dapm_context *dapm, int snd_soc_dapm_link_dai_widgets(struct snd_soc_card *card); void snd_soc_dapm_connect_dai_link_widgets(struct snd_soc_card *card); int snd_soc_dapm_new_pcm(struct snd_soc_card *card, + struct snd_soc_pcm_runtime *rtd, const struct snd_soc_pcm_stream *params, unsigned int num_params, struct snd_soc_dapm_widget *source, diff --git a/include/uapi/linux/gen_stats.h b/include/uapi/linux/gen_stats.h index 24a861c0d29d..065408e16a80 100644 --- a/include/uapi/linux/gen_stats.h +++ b/include/uapi/linux/gen_stats.h @@ -12,6 +12,7 @@ enum { TCA_STATS_APP, TCA_STATS_RATE_EST64, TCA_STATS_PAD, + TCA_STATS_BASIC_HW, __TCA_STATS_MAX, }; #define TCA_STATS_MAX (__TCA_STATS_MAX - 1) diff --git a/include/uapi/linux/if_addr.h b/include/uapi/linux/if_addr.h index ebaf5701c9db..dfcf3ce0097f 100644 --- a/include/uapi/linux/if_addr.h +++ b/include/uapi/linux/if_addr.h @@ -34,6 +34,7 @@ enum { IFA_MULTICAST, IFA_FLAGS, IFA_RT_PRIORITY, /* u32, priority/metric for prefix route */ + IFA_TARGET_NETNSID, __IFA_MAX, }; diff --git a/include/uapi/linux/if_arp.h b/include/uapi/linux/if_arp.h index 4605527ca41b..c3cc5a9e5eaf 100644 --- a/include/uapi/linux/if_arp.h +++ b/include/uapi/linux/if_arp.h @@ -114,18 +114,18 @@ /* ARP ioctl request. */ struct arpreq { - struct sockaddr arp_pa; /* protocol address */ - struct sockaddr arp_ha; /* hardware address */ - int arp_flags; /* flags */ - struct sockaddr arp_netmask; /* netmask (only for proxy arps) */ - char arp_dev[16]; + struct sockaddr arp_pa; /* protocol address */ + struct sockaddr arp_ha; /* hardware address */ + int arp_flags; /* flags */ + struct sockaddr arp_netmask; /* netmask (only for proxy arps) */ + char arp_dev[IFNAMSIZ]; }; struct arpreq_old { - struct sockaddr arp_pa; /* protocol address */ - struct sockaddr arp_ha; /* hardware address */ - int arp_flags; /* flags */ - struct sockaddr arp_netmask; /* netmask (only for proxy arps) */ + struct sockaddr arp_pa; /* protocol address */ + struct sockaddr arp_ha; /* hardware address */ + int arp_flags; /* flags */ + struct sockaddr arp_netmask; /* netmask (only for proxy arps) */ }; /* ARP Flag values. */ diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index 43391e2d1153..58faab897201 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -161,6 +161,7 @@ enum { IFLA_EVENT, IFLA_NEW_NETNSID, IFLA_IF_NETNSID, + IFLA_TARGET_NETNSID = IFLA_IF_NETNSID, /* new alias */ IFLA_CARRIER_UP_COUNT, IFLA_CARRIER_DOWN_COUNT, IFLA_NEW_IFINDEX, @@ -554,6 +555,7 @@ enum { IFLA_GENEVE_UDP_ZERO_CSUM6_TX, IFLA_GENEVE_UDP_ZERO_CSUM6_RX, IFLA_GENEVE_LABEL, + IFLA_GENEVE_TTL_INHERIT, __IFLA_GENEVE_MAX }; #define IFLA_GENEVE_MAX (__IFLA_GENEVE_MAX - 1) diff --git a/include/uapi/linux/in6.h b/include/uapi/linux/in6.h index ed291e55f024..71d82fe15b03 100644 --- a/include/uapi/linux/in6.h +++ b/include/uapi/linux/in6.h @@ -177,6 +177,7 @@ struct in6_flowlabel_req { #define IPV6_V6ONLY 26 #define IPV6_JOIN_ANYCAST 27 #define IPV6_LEAVE_ANYCAST 28 +#define IPV6_MULTICAST_ALL 29 /* IPV6_MTU_DISCOVER values */ #define IPV6_PMTUDISC_DONT 0 diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index 07548de5c988..251be353f950 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -952,6 +952,7 @@ struct kvm_ppc_resize_hpt { #define KVM_CAP_S390_HPAGE_1M 156 #define KVM_CAP_NESTED_STATE 157 #define KVM_CAP_ARM_INJECT_SERROR_ESR 158 +#define KVM_CAP_MSR_PLATFORM_INFO 159 #ifdef KVM_CAP_IRQ_ROUTING diff --git a/include/uapi/linux/neighbour.h b/include/uapi/linux/neighbour.h index 904db6148476..998155444e0d 100644 --- a/include/uapi/linux/neighbour.h +++ b/include/uapi/linux/neighbour.h @@ -43,6 +43,7 @@ enum { #define NTF_PROXY 0x08 /* == ATF_PUBL */ #define NTF_EXT_LEARNED 0x10 #define NTF_OFFLOADED 0x20 +#define NTF_STICKY 0x40 #define NTF_ROUTER 0x80 /* diff --git a/include/uapi/linux/perf_event.h b/include/uapi/linux/perf_event.h index eeb787b1c53c..f35eb72739c0 100644 --- a/include/uapi/linux/perf_event.h +++ b/include/uapi/linux/perf_event.h @@ -144,7 +144,7 @@ enum perf_event_sample_format { PERF_SAMPLE_MAX = 1U << 20, /* non-ABI */ - __PERF_SAMPLE_CALLCHAIN_EARLY = 1ULL << 63, + __PERF_SAMPLE_CALLCHAIN_EARLY = 1ULL << 63, /* non-ABI; internal use */ }; /* diff --git a/include/uapi/linux/pkt_cls.h b/include/uapi/linux/pkt_cls.h index be382fb0592d..401d0c1e612d 100644 --- a/include/uapi/linux/pkt_cls.h +++ b/include/uapi/linux/pkt_cls.h @@ -483,6 +483,8 @@ enum { TCA_FLOWER_KEY_ENC_OPTS, TCA_FLOWER_KEY_ENC_OPTS_MASK, + TCA_FLOWER_IN_HW_COUNT, + __TCA_FLOWER_MAX, }; diff --git a/include/uapi/sound/skl-tplg-interface.h b/include/uapi/sound/skl-tplg-interface.h index f58cafa42f18..f39352cef382 100644 --- a/include/uapi/sound/skl-tplg-interface.h +++ b/include/uapi/sound/skl-tplg-interface.h @@ -10,6 +10,8 @@ #ifndef __HDA_TPLG_INTERFACE_H__ #define __HDA_TPLG_INTERFACE_H__ +#include <linux/types.h> + /* * Default types range from 0~12. type can range from 0 to 0xff * SST types start at higher to avoid any overlapping in future @@ -143,10 +145,10 @@ enum skl_module_param_type { }; struct skl_dfw_algo_data { - u32 set_params:2; - u32 rsvd:30; - u32 param_id; - u32 max; + __u32 set_params:2; + __u32 rsvd:30; + __u32 param_id; + __u32 max; char params[0]; } __packed; @@ -163,68 +165,68 @@ enum skl_tuple_type { /* v4 configuration data */ struct skl_dfw_v4_module_pin { - u16 module_id; - u16 instance_id; + __u16 module_id; + __u16 instance_id; } __packed; struct skl_dfw_v4_module_fmt { - u32 channels; - u32 freq; - u32 bit_depth; - u32 valid_bit_depth; - u32 ch_cfg; - u32 interleaving_style; - u32 sample_type; - u32 ch_map; + __u32 channels; + __u32 freq; + __u32 bit_depth; + __u32 valid_bit_depth; + __u32 ch_cfg; + __u32 interleaving_style; + __u32 sample_type; + __u32 ch_map; } __packed; struct skl_dfw_v4_module_caps { - u32 set_params:2; - u32 rsvd:30; - u32 param_id; - u32 caps_size; - u32 caps[HDA_SST_CFG_MAX]; + __u32 set_params:2; + __u32 rsvd:30; + __u32 param_id; + __u32 caps_size; + __u32 caps[HDA_SST_CFG_MAX]; } __packed; struct skl_dfw_v4_pipe { - u8 pipe_id; - u8 pipe_priority; - u16 conn_type:4; - u16 rsvd:4; - u16 memory_pages:8; + __u8 pipe_id; + __u8 pipe_priority; + __u16 conn_type:4; + __u16 rsvd:4; + __u16 memory_pages:8; } __packed; struct skl_dfw_v4_module { char uuid[SKL_UUID_STR_SZ]; - u16 module_id; - u16 instance_id; - u32 max_mcps; - u32 mem_pages; - u32 obs; - u32 ibs; - u32 vbus_id; - - u32 max_in_queue:8; - u32 max_out_queue:8; - u32 time_slot:8; - u32 core_id:4; - u32 rsvd1:4; - - u32 module_type:8; - u32 conn_type:4; - u32 dev_type:4; - u32 hw_conn_type:4; - u32 rsvd2:12; - - u32 params_fixup:8; - u32 converter:8; - u32 input_pin_type:1; - u32 output_pin_type:1; - u32 is_dynamic_in_pin:1; - u32 is_dynamic_out_pin:1; - u32 is_loadable:1; - u32 rsvd3:11; + __u16 module_id; + __u16 instance_id; + __u32 max_mcps; + __u32 mem_pages; + __u32 obs; + __u32 ibs; + __u32 vbus_id; + + __u32 max_in_queue:8; + __u32 max_out_queue:8; + __u32 time_slot:8; + __u32 core_id:4; + __u32 rsvd1:4; + + __u32 module_type:8; + __u32 conn_type:4; + __u32 dev_type:4; + __u32 hw_conn_type:4; + __u32 rsvd2:12; + + __u32 params_fixup:8; + __u32 converter:8; + __u32 input_pin_type:1; + __u32 output_pin_type:1; + __u32 is_dynamic_in_pin:1; + __u32 is_dynamic_out_pin:1; + __u32 is_loadable:1; + __u32 rsvd3:11; struct skl_dfw_v4_pipe pipe; struct skl_dfw_v4_module_fmt in_fmt[MAX_IN_QUEUE]; diff --git a/include/xen/mem-reservation.h b/include/xen/mem-reservation.h index 80b52b4945e9..a2ab516fcd2c 100644 --- a/include/xen/mem-reservation.h +++ b/include/xen/mem-reservation.h @@ -17,11 +17,12 @@ #include <xen/page.h> +extern bool xen_scrub_pages; + static inline void xenmem_reservation_scrub_page(struct page *page) { -#ifdef CONFIG_XEN_SCRUB_PAGES - clear_highpage(page); -#endif + if (xen_scrub_pages) + clear_highpage(page); } #ifdef CONFIG_XEN_HAVE_PVMMU diff --git a/ipc/shm.c b/ipc/shm.c index b0eb3757ab89..4cd402e4cfeb 100644 --- a/ipc/shm.c +++ b/ipc/shm.c @@ -199,6 +199,7 @@ static inline struct shmid_kernel *shm_lock(struct ipc_namespace *ns, int id) } ipc_unlock_object(ipcp); + ipcp = ERR_PTR(-EIDRM); err: rcu_read_unlock(); /* diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c index 2590700237c1..138f0302692e 100644 --- a/kernel/bpf/btf.c +++ b/kernel/bpf/btf.c @@ -1844,7 +1844,7 @@ static int btf_check_all_metas(struct btf_verifier_env *env) hdr = &btf->hdr; cur = btf->nohdr_data + hdr->type_off; - end = btf->nohdr_data + hdr->type_len; + end = cur + hdr->type_len; env->log_type_id = 1; while (cur < end) { diff --git a/kernel/bpf/sockmap.c b/kernel/bpf/sockmap.c index a9359cbc3f93..d37a1a0a6e1e 100644 --- a/kernel/bpf/sockmap.c +++ b/kernel/bpf/sockmap.c @@ -132,6 +132,7 @@ struct smap_psock { struct work_struct gc_work; struct proto *sk_proto; + void (*save_unhash)(struct sock *sk); void (*save_close)(struct sock *sk, long timeout); void (*save_data_ready)(struct sock *sk); void (*save_write_space)(struct sock *sk); @@ -143,6 +144,7 @@ static int bpf_tcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, static int bpf_tcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t size); static int bpf_tcp_sendpage(struct sock *sk, struct page *page, int offset, size_t size, int flags); +static void bpf_tcp_unhash(struct sock *sk); static void bpf_tcp_close(struct sock *sk, long timeout); static inline struct smap_psock *smap_psock_sk(const struct sock *sk) @@ -184,6 +186,7 @@ static void build_protos(struct proto prot[SOCKMAP_NUM_CONFIGS], struct proto *base) { prot[SOCKMAP_BASE] = *base; + prot[SOCKMAP_BASE].unhash = bpf_tcp_unhash; prot[SOCKMAP_BASE].close = bpf_tcp_close; prot[SOCKMAP_BASE].recvmsg = bpf_tcp_recvmsg; prot[SOCKMAP_BASE].stream_memory_read = bpf_tcp_stream_read; @@ -217,6 +220,7 @@ static int bpf_tcp_init(struct sock *sk) return -EBUSY; } + psock->save_unhash = sk->sk_prot->unhash; psock->save_close = sk->sk_prot->close; psock->sk_proto = sk->sk_prot; @@ -305,30 +309,12 @@ static struct smap_psock_map_entry *psock_map_pop(struct sock *sk, return e; } -static void bpf_tcp_close(struct sock *sk, long timeout) +static void bpf_tcp_remove(struct sock *sk, struct smap_psock *psock) { - void (*close_fun)(struct sock *sk, long timeout); struct smap_psock_map_entry *e; struct sk_msg_buff *md, *mtmp; - struct smap_psock *psock; struct sock *osk; - lock_sock(sk); - rcu_read_lock(); - psock = smap_psock_sk(sk); - if (unlikely(!psock)) { - rcu_read_unlock(); - release_sock(sk); - return sk->sk_prot->close(sk, timeout); - } - - /* The psock may be destroyed anytime after exiting the RCU critial - * section so by the time we use close_fun the psock may no longer - * be valid. However, bpf_tcp_close is called with the sock lock - * held so the close hook and sk are still valid. - */ - close_fun = psock->save_close; - if (psock->cork) { free_start_sg(psock->sock, psock->cork, true); kfree(psock->cork); @@ -379,6 +365,42 @@ static void bpf_tcp_close(struct sock *sk, long timeout) kfree(e); e = psock_map_pop(sk, psock); } +} + +static void bpf_tcp_unhash(struct sock *sk) +{ + void (*unhash_fun)(struct sock *sk); + struct smap_psock *psock; + + rcu_read_lock(); + psock = smap_psock_sk(sk); + if (unlikely(!psock)) { + rcu_read_unlock(); + if (sk->sk_prot->unhash) + sk->sk_prot->unhash(sk); + return; + } + unhash_fun = psock->save_unhash; + bpf_tcp_remove(sk, psock); + rcu_read_unlock(); + unhash_fun(sk); +} + +static void bpf_tcp_close(struct sock *sk, long timeout) +{ + void (*close_fun)(struct sock *sk, long timeout); + struct smap_psock *psock; + + lock_sock(sk); + rcu_read_lock(); + psock = smap_psock_sk(sk); + if (unlikely(!psock)) { + rcu_read_unlock(); + release_sock(sk); + return sk->sk_prot->close(sk, timeout); + } + close_fun = psock->save_close; + bpf_tcp_remove(sk, psock); rcu_read_unlock(); release_sock(sk); close_fun(sk, timeout); @@ -2095,8 +2117,12 @@ static int sock_map_update_elem(struct bpf_map *map, return -EINVAL; } + /* ULPs are currently supported only for TCP sockets in ESTABLISHED + * state. + */ if (skops.sk->sk_type != SOCK_STREAM || - skops.sk->sk_protocol != IPPROTO_TCP) { + skops.sk->sk_protocol != IPPROTO_TCP || + skops.sk->sk_state != TCP_ESTABLISHED) { fput(socket->file); return -EOPNOTSUPP; } @@ -2451,6 +2477,16 @@ static int sock_hash_update_elem(struct bpf_map *map, return -EINVAL; } + /* ULPs are currently supported only for TCP sockets in ESTABLISHED + * state. + */ + if (skops.sk->sk_type != SOCK_STREAM || + skops.sk->sk_protocol != IPPROTO_TCP || + skops.sk->sk_state != TCP_ESTABLISHED) { + fput(socket->file); + return -EOPNOTSUPP; + } + lock_sock(skops.sk); preempt_disable(); rcu_read_lock(); @@ -2541,10 +2577,22 @@ const struct bpf_map_ops sock_hash_ops = { .map_check_btf = map_check_no_btf, }; +static bool bpf_is_valid_sock_op(struct bpf_sock_ops_kern *ops) +{ + return ops->op == BPF_SOCK_OPS_PASSIVE_ESTABLISHED_CB || + ops->op == BPF_SOCK_OPS_ACTIVE_ESTABLISHED_CB; +} BPF_CALL_4(bpf_sock_map_update, struct bpf_sock_ops_kern *, bpf_sock, struct bpf_map *, map, void *, key, u64, flags) { WARN_ON_ONCE(!rcu_read_lock_held()); + + /* ULPs are currently supported only for TCP sockets in ESTABLISHED + * state. This checks that the sock ops triggering the update is + * one indicating we are (or will be soon) in an ESTABLISHED state. + */ + if (!bpf_is_valid_sock_op(bpf_sock)) + return -EOPNOTSUPP; return sock_map_ctx_update_elem(bpf_sock, map, key, flags); } @@ -2563,6 +2611,9 @@ BPF_CALL_4(bpf_sock_hash_update, struct bpf_sock_ops_kern *, bpf_sock, struct bpf_map *, map, void *, key, u64, flags) { WARN_ON_ONCE(!rcu_read_lock_held()); + + if (!bpf_is_valid_sock_op(bpf_sock)) + return -EOPNOTSUPP; return sock_hash_ctx_update_elem(bpf_sock, map, key, flags); } diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 8ccbff4fff93..e986518d7bc3 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -3109,7 +3109,7 @@ static int adjust_reg_min_max_vals(struct bpf_verifier_env *env, * an arbitrary scalar. Disallow all math except * pointer subtraction */ - if (opcode == BPF_SUB){ + if (opcode == BPF_SUB && env->allow_ptr_leaks) { mark_reg_unknown(env, regs, insn->dst_reg); return 0; } diff --git a/kernel/cpu.c b/kernel/cpu.c index aa7fe85ad62e..0097acec1c71 100644 --- a/kernel/cpu.c +++ b/kernel/cpu.c @@ -607,15 +607,15 @@ static void cpuhp_thread_fun(unsigned int cpu) bool bringup = st->bringup; enum cpuhp_state state; + if (WARN_ON_ONCE(!st->should_run)) + return; + /* * ACQUIRE for the cpuhp_should_run() load of ->should_run. Ensures * that if we see ->should_run we also see the rest of the state. */ smp_mb(); - if (WARN_ON_ONCE(!st->should_run)) - return; - cpuhp_lock_acquire(bringup); if (st->single) { @@ -916,7 +916,8 @@ static int cpuhp_down_callbacks(unsigned int cpu, struct cpuhp_cpu_state *st, ret = cpuhp_invoke_callback(cpu, st->state, false, NULL, NULL); if (ret) { st->target = prev_state; - undo_cpu_down(cpu, st); + if (st->state < prev_state) + undo_cpu_down(cpu, st); break; } } @@ -969,7 +970,7 @@ static int __ref _cpu_down(unsigned int cpu, int tasks_frozen, * to do the further cleanups. */ ret = cpuhp_down_callbacks(cpu, st, target); - if (ret && st->state > CPUHP_TEARDOWN_CPU && st->state < prev_state) { + if (ret && st->state == CPUHP_TEARDOWN_CPU && st->state < prev_state) { cpuhp_reset_state(st, prev_state); __cpuhp_kick_ap(st); } diff --git a/kernel/events/core.c b/kernel/events/core.c index 2a62b96600ad..c80549bf82c6 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -2867,16 +2867,11 @@ static int perf_event_modify_breakpoint(struct perf_event *bp, _perf_event_disable(bp); err = modify_user_hw_breakpoint_check(bp, attr, true); - if (err) { - if (!bp->attr.disabled) - _perf_event_enable(bp); - return err; - } - - if (!attr->disabled) + if (!bp->attr.disabled) _perf_event_enable(bp); - return 0; + + return err; } static int perf_event_modify_attr(struct perf_event *event, @@ -5948,6 +5943,7 @@ perf_output_sample_ustack(struct perf_output_handle *handle, u64 dump_size, unsigned long sp; unsigned int rem; u64 dyn_size; + mm_segment_t fs; /* * We dump: @@ -5965,7 +5961,10 @@ perf_output_sample_ustack(struct perf_output_handle *handle, u64 dump_size, /* Data. */ sp = perf_user_stack_pointer(regs); + fs = get_fs(); + set_fs(USER_DS); rem = __output_copy_user(handle, (void *) sp, dump_size); + set_fs(fs); dyn_size = dump_size - rem; perf_output_skip(handle, rem); diff --git a/kernel/events/hw_breakpoint.c b/kernel/events/hw_breakpoint.c index b3814fce5ecb..d6b56180827c 100644 --- a/kernel/events/hw_breakpoint.c +++ b/kernel/events/hw_breakpoint.c @@ -509,6 +509,8 @@ modify_user_hw_breakpoint_check(struct perf_event *bp, struct perf_event_attr *a */ int modify_user_hw_breakpoint(struct perf_event *bp, struct perf_event_attr *attr) { + int err; + /* * modify_user_hw_breakpoint can be invoked with IRQs disabled and hence it * will not be possible to raise IPIs that invoke __perf_event_disable. @@ -520,15 +522,12 @@ int modify_user_hw_breakpoint(struct perf_event *bp, struct perf_event_attr *att else perf_event_disable(bp); - if (!attr->disabled) { - int err = modify_user_hw_breakpoint_check(bp, attr, false); + err = modify_user_hw_breakpoint_check(bp, attr, false); - if (err) - return err; + if (!bp->attr.disabled) perf_event_enable(bp); - bp->attr.disabled = 0; - } - return 0; + + return err; } EXPORT_SYMBOL_GPL(modify_user_hw_breakpoint); diff --git a/kernel/fork.c b/kernel/fork.c index d896e9ca38b0..f0b58479534f 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -550,8 +550,7 @@ static __latent_entropy int dup_mmap(struct mm_struct *mm, goto out; } /* a new mm has just been created */ - arch_dup_mmap(oldmm, mm); - retval = 0; + retval = arch_dup_mmap(oldmm, mm); out: up_write(&mm->mmap_sem); flush_tlb_mm(oldmm); diff --git a/kernel/jump_label.c b/kernel/jump_label.c index 01ebdf1f9f40..2e62503bea0d 100644 --- a/kernel/jump_label.c +++ b/kernel/jump_label.c @@ -678,7 +678,7 @@ jump_label_module_notify(struct notifier_block *self, unsigned long val, case MODULE_STATE_COMING: ret = jump_label_add_module(mod); if (ret) { - WARN(1, "Failed to allocatote memory: jump_label may not work properly.\n"); + WARN(1, "Failed to allocate memory: jump_label may not work properly.\n"); jump_label_del_module(mod); } break; diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c index e406c5fdb41e..dd13f865ad40 100644 --- a/kernel/locking/lockdep.c +++ b/kernel/locking/lockdep.c @@ -55,7 +55,6 @@ #include "lockdep_internals.h" -#include <trace/events/preemptirq.h> #define CREATE_TRACE_POINTS #include <trace/events/lock.h> diff --git a/kernel/locking/mutex.c b/kernel/locking/mutex.c index 1a81a1257b3f..3f8a35104285 100644 --- a/kernel/locking/mutex.c +++ b/kernel/locking/mutex.c @@ -389,7 +389,7 @@ static bool __ww_mutex_wound(struct mutex *lock, /* * wake_up_process() paired with set_current_state() * inserts sufficient barriers to make sure @owner either sees - * it's wounded in __ww_mutex_lock_check_stamp() or has a + * it's wounded in __ww_mutex_check_kill() or has a * wakeup pending to re-read the wounded state. */ if (owner != current) @@ -946,7 +946,6 @@ __mutex_lock_common(struct mutex *lock, long state, unsigned int subclass, } debug_mutex_lock_common(lock, &waiter); - debug_mutex_add_waiter(lock, &waiter, current); lock_contended(&lock->dep_map, ip); diff --git a/kernel/locking/test-ww_mutex.c b/kernel/locking/test-ww_mutex.c index 5b915b370d5a..0be047dbd897 100644 --- a/kernel/locking/test-ww_mutex.c +++ b/kernel/locking/test-ww_mutex.c @@ -324,7 +324,7 @@ static int __test_cycle(unsigned int nthreads) if (!cycle->result) continue; - pr_err("cylic deadlock not resolved, ret[%d/%d] = %d\n", + pr_err("cyclic deadlock not resolved, ret[%d/%d] = %d\n", n, nthreads, cycle->result); ret = -EINVAL; break; diff --git a/kernel/pid.c b/kernel/pid.c index de1cfc4f75a2..cdf63e53a014 100644 --- a/kernel/pid.c +++ b/kernel/pid.c @@ -195,7 +195,7 @@ struct pid *alloc_pid(struct pid_namespace *ns) idr_preload_end(); if (nr < 0) { - retval = nr; + retval = (nr == -ENOSPC) ? -EAGAIN : nr; goto out_free; } diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c index fd6f8ed28e01..9bf5404397e0 100644 --- a/kernel/printk/printk.c +++ b/kernel/printk/printk.c @@ -351,7 +351,6 @@ static int console_msg_format = MSG_FORMAT_DEFAULT; */ enum log_flags { - LOG_NOCONS = 1, /* suppress print, do not print to console */ LOG_NEWLINE = 2, /* text ended with a newline */ LOG_PREFIX = 4, /* text started with a prefix */ LOG_CONT = 8, /* text is a fragment of a continuation line */ @@ -1881,9 +1880,6 @@ int vprintk_store(int facility, int level, if (dict) lflags |= LOG_PREFIX|LOG_NEWLINE; - if (suppress_message_printing(level)) - lflags |= LOG_NOCONS; - return log_output(facility, level, lflags, dict, dictlen, text, text_len); } @@ -2032,6 +2028,7 @@ static void call_console_drivers(const char *ext_text, size_t ext_len, const char *text, size_t len) {} static size_t msg_print_text(const struct printk_log *msg, bool syslog, char *buf, size_t size) { return 0; } +static bool suppress_message_printing(int level) { return false; } #endif /* CONFIG_PRINTK */ @@ -2368,10 +2365,11 @@ skip: break; msg = log_from_idx(console_idx); - if (msg->flags & LOG_NOCONS) { + if (suppress_message_printing(msg->level)) { /* - * Skip record if !ignore_loglevel, and - * record has level above the console loglevel. + * Skip record we have buffered and already printed + * directly to the console when we received it, and + * record that has level above the console loglevel. */ console_idx = log_next(console_idx); console_seq++; diff --git a/kernel/printk/printk_safe.c b/kernel/printk/printk_safe.c index a0a74c533e4b..0913b4d385de 100644 --- a/kernel/printk/printk_safe.c +++ b/kernel/printk/printk_safe.c @@ -306,12 +306,12 @@ static __printf(1, 0) int vprintk_nmi(const char *fmt, va_list args) return printk_safe_log_store(s, fmt, args); } -void printk_nmi_enter(void) +void notrace printk_nmi_enter(void) { this_cpu_or(printk_context, PRINTK_NMI_CONTEXT_MASK); } -void printk_nmi_exit(void) +void notrace printk_nmi_exit(void) { this_cpu_and(printk_context, ~PRINTK_NMI_CONTEXT_MASK); } diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c index 60caf1fb94e0..6383aa6a60ca 100644 --- a/kernel/sched/debug.c +++ b/kernel/sched/debug.c @@ -89,12 +89,12 @@ struct static_key sched_feat_keys[__SCHED_FEAT_NR] = { static void sched_feat_disable(int i) { - static_key_disable(&sched_feat_keys[i]); + static_key_disable_cpuslocked(&sched_feat_keys[i]); } static void sched_feat_enable(int i) { - static_key_enable(&sched_feat_keys[i]); + static_key_enable_cpuslocked(&sched_feat_keys[i]); } #else static void sched_feat_disable(int i) { }; @@ -146,9 +146,11 @@ sched_feat_write(struct file *filp, const char __user *ubuf, /* Ensure the static_key remains in a consistent state */ inode = file_inode(filp); + cpus_read_lock(); inode_lock(inode); ret = sched_feat_set(cmp); inode_unlock(inode); + cpus_read_unlock(); if (ret < 0) return ret; diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index b39fb596f6c1..f808ddf2a868 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -3362,6 +3362,7 @@ update_cfs_rq_load_avg(u64 now, struct cfs_rq *cfs_rq) * attach_entity_load_avg - attach this entity to its cfs_rq load avg * @cfs_rq: cfs_rq to attach to * @se: sched_entity to attach + * @flags: migration hints * * Must call update_cfs_rq_load_avg() before this, since we rely on * cfs_rq->avg.last_update_time being current. @@ -7263,6 +7264,7 @@ static void update_blocked_averages(int cpu) { struct rq *rq = cpu_rq(cpu); struct cfs_rq *cfs_rq, *pos; + const struct sched_class *curr_class; struct rq_flags rf; bool done = true; @@ -7299,8 +7301,10 @@ static void update_blocked_averages(int cpu) if (cfs_rq_has_blocked(cfs_rq)) done = false; } - update_rt_rq_load_avg(rq_clock_task(rq), rq, 0); - update_dl_rq_load_avg(rq_clock_task(rq), rq, 0); + + curr_class = rq->curr->sched_class; + update_rt_rq_load_avg(rq_clock_task(rq), rq, curr_class == &rt_sched_class); + update_dl_rq_load_avg(rq_clock_task(rq), rq, curr_class == &dl_sched_class); update_irq_load_avg(rq, 0); /* Don't need periodic decay once load/util_avg are null */ if (others_have_blocked(rq)) @@ -7365,13 +7369,16 @@ static inline void update_blocked_averages(int cpu) { struct rq *rq = cpu_rq(cpu); struct cfs_rq *cfs_rq = &rq->cfs; + const struct sched_class *curr_class; struct rq_flags rf; rq_lock_irqsave(rq, &rf); update_rq_clock(rq); update_cfs_rq_load_avg(cfs_rq_clock_task(cfs_rq), cfs_rq); - update_rt_rq_load_avg(rq_clock_task(rq), rq, 0); - update_dl_rq_load_avg(rq_clock_task(rq), rq, 0); + + curr_class = rq->curr->sched_class; + update_rt_rq_load_avg(rq_clock_task(rq), rq, curr_class == &rt_sched_class); + update_dl_rq_load_avg(rq_clock_task(rq), rq, curr_class == &dl_sched_class); update_irq_load_avg(rq, 0); #ifdef CONFIG_NO_HZ_COMMON rq->last_blocked_load_update_tick = jiffies; @@ -7482,10 +7489,10 @@ static inline int get_sd_load_idx(struct sched_domain *sd, return load_idx; } -static unsigned long scale_rt_capacity(int cpu) +static unsigned long scale_rt_capacity(struct sched_domain *sd, int cpu) { struct rq *rq = cpu_rq(cpu); - unsigned long max = arch_scale_cpu_capacity(NULL, cpu); + unsigned long max = arch_scale_cpu_capacity(sd, cpu); unsigned long used, free; unsigned long irq; @@ -7507,7 +7514,7 @@ static unsigned long scale_rt_capacity(int cpu) static void update_cpu_capacity(struct sched_domain *sd, int cpu) { - unsigned long capacity = scale_rt_capacity(cpu); + unsigned long capacity = scale_rt_capacity(sd, cpu); struct sched_group *sdg = sd->groups; cpu_rq(cpu)->cpu_capacity_orig = arch_scale_cpu_capacity(sd, cpu); @@ -8269,7 +8276,7 @@ static struct sched_group *find_busiest_group(struct lb_env *env) force_balance: /* Looks like there is an imbalance. Compute it */ calculate_imbalance(env, &sds); - return sds.busiest; + return env->imbalance ? sds.busiest : NULL; out_balanced: env->imbalance = 0; @@ -9638,7 +9645,8 @@ static inline bool vruntime_normalized(struct task_struct *p) * - A task which has been woken up by try_to_wake_up() and * waiting for actually being woken up by sched_ttwu_pending(). */ - if (!se->sum_exec_runtime || p->state == TASK_WAKING) + if (!se->sum_exec_runtime || + (p->state == TASK_WAKING && p->sched_remote_wakeup)) return true; return false; diff --git a/kernel/sched/topology.c b/kernel/sched/topology.c index 56a0fed30c0a..505a41c42b96 100644 --- a/kernel/sched/topology.c +++ b/kernel/sched/topology.c @@ -1295,7 +1295,7 @@ static void init_numa_topology_type(void) n = sched_max_numa_distance; - if (sched_domains_numa_levels <= 1) { + if (sched_domains_numa_levels <= 2) { sched_numa_topology_type = NUMA_DIRECT; return; } @@ -1380,9 +1380,6 @@ void sched_init_numa(void) break; } - if (!level) - return; - /* * 'level' contains the number of unique distances * diff --git a/kernel/sys.c b/kernel/sys.c index cf5c67533ff1..123bd73046ec 100644 --- a/kernel/sys.c +++ b/kernel/sys.c @@ -71,9 +71,6 @@ #include <asm/io.h> #include <asm/unistd.h> -/* Hardening for Spectre-v1 */ -#include <linux/nospec.h> - #include "uid16.h" #ifndef SET_UNALIGN_CTL diff --git a/kernel/time/clocksource.c b/kernel/time/clocksource.c index f74fb00d8064..0e6e97a01942 100644 --- a/kernel/time/clocksource.c +++ b/kernel/time/clocksource.c @@ -133,19 +133,40 @@ static void inline clocksource_watchdog_unlock(unsigned long *flags) spin_unlock_irqrestore(&watchdog_lock, *flags); } +static int clocksource_watchdog_kthread(void *data); +static void __clocksource_change_rating(struct clocksource *cs, int rating); + /* * Interval: 0.5sec Threshold: 0.0625s */ #define WATCHDOG_INTERVAL (HZ >> 1) #define WATCHDOG_THRESHOLD (NSEC_PER_SEC >> 4) +static void clocksource_watchdog_work(struct work_struct *work) +{ + /* + * We cannot directly run clocksource_watchdog_kthread() here, because + * clocksource_select() calls timekeeping_notify() which uses + * stop_machine(). One cannot use stop_machine() from a workqueue() due + * lock inversions wrt CPU hotplug. + * + * Also, we only ever run this work once or twice during the lifetime + * of the kernel, so there is no point in creating a more permanent + * kthread for this. + * + * If kthread_run fails the next watchdog scan over the + * watchdog_list will find the unstable clock again. + */ + kthread_run(clocksource_watchdog_kthread, NULL, "kwatchdog"); +} + static void __clocksource_unstable(struct clocksource *cs) { cs->flags &= ~(CLOCK_SOURCE_VALID_FOR_HRES | CLOCK_SOURCE_WATCHDOG); cs->flags |= CLOCK_SOURCE_UNSTABLE; /* - * If the clocksource is registered clocksource_watchdog_work() will + * If the clocksource is registered clocksource_watchdog_kthread() will * re-rate and re-select. */ if (list_empty(&cs->list)) { @@ -156,7 +177,7 @@ static void __clocksource_unstable(struct clocksource *cs) if (cs->mark_unstable) cs->mark_unstable(cs); - /* kick clocksource_watchdog_work() */ + /* kick clocksource_watchdog_kthread() */ if (finished_booting) schedule_work(&watchdog_work); } @@ -166,7 +187,7 @@ static void __clocksource_unstable(struct clocksource *cs) * @cs: clocksource to be marked unstable * * This function is called by the x86 TSC code to mark clocksources as unstable; - * it defers demotion and re-selection to a work. + * it defers demotion and re-selection to a kthread. */ void clocksource_mark_unstable(struct clocksource *cs) { @@ -391,9 +412,7 @@ static void clocksource_dequeue_watchdog(struct clocksource *cs) } } -static void __clocksource_change_rating(struct clocksource *cs, int rating); - -static int __clocksource_watchdog_work(void) +static int __clocksource_watchdog_kthread(void) { struct clocksource *cs, *tmp; unsigned long flags; @@ -418,12 +437,13 @@ static int __clocksource_watchdog_work(void) return select; } -static void clocksource_watchdog_work(struct work_struct *work) +static int clocksource_watchdog_kthread(void *data) { mutex_lock(&clocksource_mutex); - if (__clocksource_watchdog_work()) + if (__clocksource_watchdog_kthread()) clocksource_select(); mutex_unlock(&clocksource_mutex); + return 0; } static bool clocksource_is_watchdog(struct clocksource *cs) @@ -442,7 +462,7 @@ static void clocksource_enqueue_watchdog(struct clocksource *cs) static void clocksource_select_watchdog(bool fallback) { } static inline void clocksource_dequeue_watchdog(struct clocksource *cs) { } static inline void clocksource_resume_watchdog(void) { } -static inline int __clocksource_watchdog_work(void) { return 0; } +static inline int __clocksource_watchdog_kthread(void) { return 0; } static bool clocksource_is_watchdog(struct clocksource *cs) { return false; } void clocksource_mark_unstable(struct clocksource *cs) { } @@ -810,7 +830,7 @@ static int __init clocksource_done_booting(void) /* * Run the watchdog first to eliminate unstable clock sources */ - __clocksource_watchdog_work(); + __clocksource_watchdog_kthread(); clocksource_select(); mutex_unlock(&clocksource_mutex); return 0; diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index 1d92d4a982fd..65bd4616220d 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -1546,6 +1546,8 @@ rb_remove_pages(struct ring_buffer_per_cpu *cpu_buffer, unsigned long nr_pages) tmp_iter_page = first_page; do { + cond_resched(); + to_remove_page = tmp_iter_page; rb_inc_page(cpu_buffer, &tmp_iter_page); diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index 613316724c6a..4966c4fbe7f7 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -1277,13 +1277,13 @@ config WARN_ALL_UNSEEDED_RANDOM time. This is really bad from a security perspective, and so architecture maintainers really need to do what they can to get the CRNG seeded sooner after the system is booted. - However, since users can not do anything actionble to + However, since users cannot do anything actionable to address this, by default the kernel will issue only a single warning for the first use of unseeded randomness. Say Y here if you want to receive warnings for all uses of unseeded randomness. This will be of use primarily for - those developers interersted in improving the security of + those developers interested in improving the security of Linux kernels running on their architecture (or subarchitecture). diff --git a/lib/nlattr.c b/lib/nlattr.c index e335bcafa9e4..bb6fe5ed4ecf 100644 --- a/lib/nlattr.c +++ b/lib/nlattr.c @@ -69,7 +69,8 @@ static int validate_nla_bitfield32(const struct nlattr *nla, } static int validate_nla(const struct nlattr *nla, int maxtype, - const struct nla_policy *policy) + const struct nla_policy *policy, + const char **error_msg) { const struct nla_policy *pt; int minlen = 0, attrlen = nla_len(nla), type = nla_type(nla); @@ -81,12 +82,23 @@ static int validate_nla(const struct nlattr *nla, int maxtype, BUG_ON(pt->type > NLA_TYPE_MAX); - if (nla_attr_len[pt->type] && attrlen != nla_attr_len[pt->type]) { + if ((nla_attr_len[pt->type] && attrlen != nla_attr_len[pt->type]) || + (pt->type == NLA_EXACT_LEN_WARN && attrlen != pt->len)) { pr_warn_ratelimited("netlink: '%s': attribute type %d has an invalid length.\n", current->comm, type); } switch (pt->type) { + case NLA_EXACT_LEN: + if (attrlen != pt->len) + return -ERANGE; + break; + + case NLA_REJECT: + if (pt->validation_data && error_msg) + *error_msg = pt->validation_data; + return -EINVAL; + case NLA_FLAG: if (attrlen > 0) return -ERANGE; @@ -180,11 +192,10 @@ int nla_validate(const struct nlattr *head, int len, int maxtype, int rem; nla_for_each_attr(nla, head, len, rem) { - int err = validate_nla(nla, maxtype, policy); + int err = validate_nla(nla, maxtype, policy, NULL); if (err < 0) { - if (extack) - extack->bad_attr = nla; + NL_SET_BAD_ATTR(extack, nla); return err; } } @@ -250,11 +261,15 @@ int nla_parse(struct nlattr **tb, int maxtype, const struct nlattr *head, u16 type = nla_type(nla); if (type > 0 && type <= maxtype) { + static const char _msg[] = "Attribute failed policy validation"; + const char *msg = _msg; + if (policy) { - err = validate_nla(nla, maxtype, policy); + err = validate_nla(nla, maxtype, policy, &msg); if (err < 0) { - NL_SET_ERR_MSG_ATTR(extack, nla, - "Attribute failed policy validation"); + NL_SET_BAD_ATTR(extack, nla); + if (extack) + extack->_msg = msg; goto errout; } } diff --git a/mm/Kconfig b/mm/Kconfig index a550635ea5c3..de64ea658716 100644 --- a/mm/Kconfig +++ b/mm/Kconfig @@ -637,6 +637,7 @@ config DEFERRED_STRUCT_PAGE_INIT depends on NO_BOOTMEM depends on SPARSEMEM depends on !NEED_PER_CPU_KM + depends on 64BIT help Ordinarily all struct pages are initialised during early boot in a single thread. On very large machines this can take a considerable diff --git a/mm/Makefile b/mm/Makefile index 8716bdabe1e6..26ef77a3883b 100644 --- a/mm/Makefile +++ b/mm/Makefile @@ -32,7 +32,7 @@ ifdef CONFIG_CROSS_MEMORY_ATTACH mmu-$(CONFIG_MMU) += process_vm_access.o endif -obj-y := filemap.o mempool.o oom_kill.o \ +obj-y := filemap.o mempool.o oom_kill.o fadvise.o \ maccess.o page_alloc.o page-writeback.o \ readahead.o swap.o truncate.o vmscan.o shmem.o \ util.o mmzone.o vmstat.o backing-dev.o \ @@ -49,7 +49,6 @@ else obj-y += bootmem.o endif -obj-$(CONFIG_ADVISE_SYSCALLS) += fadvise.o ifdef CONFIG_MMU obj-$(CONFIG_ADVISE_SYSCALLS) += madvise.o endif diff --git a/mm/backing-dev.c b/mm/backing-dev.c index f5981e9d6ae2..8a8bb8796c6c 100644 --- a/mm/backing-dev.c +++ b/mm/backing-dev.c @@ -491,6 +491,7 @@ static void cgwb_release_workfn(struct work_struct *work) { struct bdi_writeback *wb = container_of(work, struct bdi_writeback, release_work); + struct blkcg *blkcg = css_to_blkcg(wb->blkcg_css); mutex_lock(&wb->bdi->cgwb_release_mutex); wb_shutdown(wb); @@ -499,6 +500,9 @@ static void cgwb_release_workfn(struct work_struct *work) css_put(wb->blkcg_css); mutex_unlock(&wb->bdi->cgwb_release_mutex); + /* triggers blkg destruction if cgwb_refcnt becomes zero */ + blkcg_cgwb_put(blkcg); + fprop_local_destroy_percpu(&wb->memcg_completions); percpu_ref_exit(&wb->refcnt); wb_exit(wb); @@ -597,6 +601,7 @@ static int cgwb_create(struct backing_dev_info *bdi, list_add_tail_rcu(&wb->bdi_node, &bdi->wb_list); list_add(&wb->memcg_node, memcg_cgwb_list); list_add(&wb->blkcg_node, blkcg_cgwb_list); + blkcg_cgwb_get(blkcg); css_get(memcg_css); css_get(blkcg_css); } diff --git a/mm/debug.c b/mm/debug.c index 38c926520c97..bd10aad8539a 100644 --- a/mm/debug.c +++ b/mm/debug.c @@ -114,7 +114,7 @@ EXPORT_SYMBOL(dump_vma); void dump_mm(const struct mm_struct *mm) { - pr_emerg("mm %px mmap %px seqnum %d task_size %lu\n" + pr_emerg("mm %px mmap %px seqnum %llu task_size %lu\n" #ifdef CONFIG_MMU "get_unmapped_area %px\n" #endif @@ -142,7 +142,7 @@ void dump_mm(const struct mm_struct *mm) "tlb_flush_pending %d\n" "def_flags: %#lx(%pGv)\n", - mm, mm->mmap, mm->vmacache_seqnum, mm->task_size, + mm, mm->mmap, (long long) mm->vmacache_seqnum, mm->task_size, #ifdef CONFIG_MMU mm->get_unmapped_area, #endif diff --git a/mm/fadvise.c b/mm/fadvise.c index 2d8376e3c640..467bcd032037 100644 --- a/mm/fadvise.c +++ b/mm/fadvise.c @@ -27,9 +27,9 @@ * deactivate the pages and clear PG_Referenced. */ -int ksys_fadvise64_64(int fd, loff_t offset, loff_t len, int advice) +static int generic_fadvise(struct file *file, loff_t offset, loff_t len, + int advice) { - struct fd f = fdget(fd); struct inode *inode; struct address_space *mapping; struct backing_dev_info *bdi; @@ -37,22 +37,14 @@ int ksys_fadvise64_64(int fd, loff_t offset, loff_t len, int advice) pgoff_t start_index; pgoff_t end_index; unsigned long nrpages; - int ret = 0; - - if (!f.file) - return -EBADF; - inode = file_inode(f.file); - if (S_ISFIFO(inode->i_mode)) { - ret = -ESPIPE; - goto out; - } + inode = file_inode(file); + if (S_ISFIFO(inode->i_mode)) + return -ESPIPE; - mapping = f.file->f_mapping; - if (!mapping || len < 0) { - ret = -EINVAL; - goto out; - } + mapping = file->f_mapping; + if (!mapping || len < 0) + return -EINVAL; bdi = inode_to_bdi(mapping->host); @@ -67,9 +59,9 @@ int ksys_fadvise64_64(int fd, loff_t offset, loff_t len, int advice) /* no bad return value, but ignore advice */ break; default: - ret = -EINVAL; + return -EINVAL; } - goto out; + return 0; } /* @@ -85,21 +77,21 @@ int ksys_fadvise64_64(int fd, loff_t offset, loff_t len, int advice) switch (advice) { case POSIX_FADV_NORMAL: - f.file->f_ra.ra_pages = bdi->ra_pages; - spin_lock(&f.file->f_lock); - f.file->f_mode &= ~FMODE_RANDOM; - spin_unlock(&f.file->f_lock); + file->f_ra.ra_pages = bdi->ra_pages; + spin_lock(&file->f_lock); + file->f_mode &= ~FMODE_RANDOM; + spin_unlock(&file->f_lock); break; case POSIX_FADV_RANDOM: - spin_lock(&f.file->f_lock); - f.file->f_mode |= FMODE_RANDOM; - spin_unlock(&f.file->f_lock); + spin_lock(&file->f_lock); + file->f_mode |= FMODE_RANDOM; + spin_unlock(&file->f_lock); break; case POSIX_FADV_SEQUENTIAL: - f.file->f_ra.ra_pages = bdi->ra_pages * 2; - spin_lock(&f.file->f_lock); - f.file->f_mode &= ~FMODE_RANDOM; - spin_unlock(&f.file->f_lock); + file->f_ra.ra_pages = bdi->ra_pages * 2; + spin_lock(&file->f_lock); + file->f_mode &= ~FMODE_RANDOM; + spin_unlock(&file->f_lock); break; case POSIX_FADV_WILLNEED: /* First and last PARTIAL page! */ @@ -115,8 +107,7 @@ int ksys_fadvise64_64(int fd, loff_t offset, loff_t len, int advice) * Ignore return value because fadvise() shall return * success even if filesystem can't retrieve a hint, */ - force_page_cache_readahead(mapping, f.file, start_index, - nrpages); + force_page_cache_readahead(mapping, file, start_index, nrpages); break; case POSIX_FADV_NOREUSE: break; @@ -183,9 +174,32 @@ int ksys_fadvise64_64(int fd, loff_t offset, loff_t len, int advice) } break; default: - ret = -EINVAL; + return -EINVAL; } -out: + return 0; +} + +int vfs_fadvise(struct file *file, loff_t offset, loff_t len, int advice) +{ + if (file->f_op->fadvise) + return file->f_op->fadvise(file, offset, len, advice); + + return generic_fadvise(file, offset, len, advice); +} +EXPORT_SYMBOL(vfs_fadvise); + +#ifdef CONFIG_ADVISE_SYSCALLS + +int ksys_fadvise64_64(int fd, loff_t offset, loff_t len, int advice) +{ + struct fd f = fdget(fd); + int ret; + + if (!f.file) + return -EBADF; + + ret = vfs_fadvise(f.file, offset, len, advice); + fdput(f); return ret; } @@ -203,3 +217,4 @@ SYSCALL_DEFINE4(fadvise64, int, fd, loff_t, offset, size_t, len, int, advice) } #endif +#endif diff --git a/mm/huge_memory.c b/mm/huge_memory.c index c3bc7e9c9a2a..533f9b00147d 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -821,11 +821,11 @@ vm_fault_t vmf_insert_pfn_pud(struct vm_area_struct *vma, unsigned long addr, * but we need to be consistent with PTEs and architectures that * can't support a 'special' bit. */ - BUG_ON(!(vma->vm_flags & (VM_PFNMAP|VM_MIXEDMAP))); + BUG_ON(!(vma->vm_flags & (VM_PFNMAP|VM_MIXEDMAP)) && + !pfn_t_devmap(pfn)); BUG_ON((vma->vm_flags & (VM_PFNMAP|VM_MIXEDMAP)) == (VM_PFNMAP|VM_MIXEDMAP)); BUG_ON((vma->vm_flags & VM_PFNMAP) && is_cow_mapping(vma->vm_flags)); - BUG_ON(!pfn_t_devmap(pfn)); if (addr < vma->vm_start || addr >= vma->vm_end) return VM_FAULT_SIGBUS; diff --git a/mm/kmemleak.c b/mm/kmemleak.c index 9a085d525bbc..17dd883198ae 100644 --- a/mm/kmemleak.c +++ b/mm/kmemleak.c @@ -2097,6 +2097,11 @@ static int __init kmemleak_late_init(void) kmemleak_initialized = 1; + dentry = debugfs_create_file("kmemleak", 0644, NULL, NULL, + &kmemleak_fops); + if (!dentry) + pr_warn("Failed to create the debugfs kmemleak file\n"); + if (kmemleak_error) { /* * Some error occurred and kmemleak was disabled. There is a @@ -2108,10 +2113,6 @@ static int __init kmemleak_late_init(void) return -ENOMEM; } - dentry = debugfs_create_file("kmemleak", 0644, NULL, NULL, - &kmemleak_fops); - if (!dentry) - pr_warn("Failed to create the debugfs kmemleak file\n"); mutex_lock(&scan_mutex); start_scan_thread(); mutex_unlock(&scan_mutex); diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 4ead5a4817de..e79cb59552d9 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -1701,8 +1701,6 @@ static enum oom_status mem_cgroup_oom(struct mem_cgroup *memcg, gfp_t mask, int if (mem_cgroup_out_of_memory(memcg, mask, order)) return OOM_SUCCESS; - WARN(1,"Memory cgroup charge failed because of no reclaimable memory! " - "This looks like a misconfiguration or a kernel bug."); return OOM_FAILED; } diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index 9eea6e809a4e..38d94b703e9d 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -1333,7 +1333,8 @@ static unsigned long scan_movable_pages(unsigned long start, unsigned long end) if (__PageMovable(page)) return pfn; if (PageHuge(page)) { - if (page_huge_active(page)) + if (hugepage_migration_supported(page_hstate(page)) && + page_huge_active(page)) return pfn; else pfn = round_up(pfn + 1, diff --git a/mm/oom_kill.c b/mm/oom_kill.c index b5b25e4dcbbb..f10aa5360616 100644 --- a/mm/oom_kill.c +++ b/mm/oom_kill.c @@ -522,6 +522,7 @@ bool __oom_reap_task_mm(struct mm_struct *mm) tlb_gather_mmu(&tlb, mm, start, end); if (mmu_notifier_invalidate_range_start_nonblock(mm, start, end)) { + tlb_finish_mmu(&tlb, start, end); ret = false; continue; } @@ -1103,10 +1104,17 @@ bool out_of_memory(struct oom_control *oc) } select_bad_process(oc); - /* Found nothing?!?! Either we hang forever, or we panic. */ - if (!oc->chosen && !is_sysrq_oom(oc) && !is_memcg_oom(oc)) { + /* Found nothing?!?! */ + if (!oc->chosen) { dump_header(oc, NULL); - panic("Out of memory and no killable processes...\n"); + pr_warn("Out of memory and no killable processes...\n"); + /* + * If we got here due to an actual allocation at the + * system level, we cannot survive this and will enter + * an endless loop in the allocator. Bail out now. + */ + if (!is_sysrq_oom(oc) && !is_memcg_oom(oc)) + panic("System is deadlocked on memory\n"); } if (oc->chosen && oc->chosen != (void *)-1UL) oom_kill_process(oc, !is_memcg_oom(oc) ? "Out of memory" : diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 05e983f42316..89d2a2ab3fe6 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -7708,6 +7708,10 @@ bool has_unmovable_pages(struct zone *zone, struct page *page, int count, * handle each tail page individually in migration. */ if (PageHuge(page)) { + + if (!hugepage_migration_supported(page_hstate(page))) + goto unmovable; + iter = round_up(iter + 1, 1<<compound_order(page)) - 1; continue; } diff --git a/mm/readahead.c b/mm/readahead.c index a59ea70527b9..4e630143a0ba 100644 --- a/mm/readahead.c +++ b/mm/readahead.c @@ -20,6 +20,7 @@ #include <linux/file.h> #include <linux/mm_inline.h> #include <linux/blk-cgroup.h> +#include <linux/fadvise.h> #include "internal.h" @@ -575,24 +576,6 @@ page_cache_async_readahead(struct address_space *mapping, } EXPORT_SYMBOL_GPL(page_cache_async_readahead); -static ssize_t -do_readahead(struct address_space *mapping, struct file *filp, - pgoff_t index, unsigned long nr) -{ - if (!mapping || !mapping->a_ops) - return -EINVAL; - - /* - * Readahead doesn't make sense for DAX inodes, but we don't want it - * to report a failure either. Instead, we just return success and - * don't do any work. - */ - if (dax_mapping(mapping)) - return 0; - - return force_page_cache_readahead(mapping, filp, index, nr); -} - ssize_t ksys_readahead(int fd, loff_t offset, size_t count) { ssize_t ret; @@ -600,16 +583,22 @@ ssize_t ksys_readahead(int fd, loff_t offset, size_t count) ret = -EBADF; f = fdget(fd); - if (f.file) { - if (f.file->f_mode & FMODE_READ) { - struct address_space *mapping = f.file->f_mapping; - pgoff_t start = offset >> PAGE_SHIFT; - pgoff_t end = (offset + count - 1) >> PAGE_SHIFT; - unsigned long len = end - start + 1; - ret = do_readahead(mapping, f.file, start, len); - } - fdput(f); - } + if (!f.file || !(f.file->f_mode & FMODE_READ)) + goto out; + + /* + * The readahead() syscall is intended to run only on files + * that can execute readahead. If readahead is not possible + * on this file, then we must return -EINVAL. + */ + ret = -EINVAL; + if (!f.file->f_mapping || !f.file->f_mapping->a_ops || + !S_ISREG(file_inode(f.file)->i_mode)) + goto out; + + ret = vfs_fadvise(f.file, offset, count, POSIX_FADV_WILLNEED); +out: + fdput(f); return ret; } diff --git a/mm/shmem.c b/mm/shmem.c index 0376c124b043..446942677cd4 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -2227,6 +2227,8 @@ static struct inode *shmem_get_inode(struct super_block *sb, const struct inode mpol_shared_policy_init(&info->policy, NULL); break; } + + lockdep_annotate_inode_mutex_key(inode); } else shmem_free_inode(sb); return inode; diff --git a/mm/util.c b/mm/util.c index d2890a407332..9e3ebd2ef65f 100644 --- a/mm/util.c +++ b/mm/util.c @@ -435,11 +435,14 @@ void *kvmalloc_node(size_t size, gfp_t flags, int node) EXPORT_SYMBOL(kvmalloc_node); /** - * kvfree - free memory allocated with kvmalloc - * @addr: pointer returned by kvmalloc + * kvfree() - Free memory. + * @addr: Pointer to allocated memory. * - * If the memory is allocated from vmalloc area it is freed with vfree(). - * Otherwise kfree() is used. + * kvfree frees memory allocated by any of vmalloc(), kmalloc() or kvmalloc(). + * It is slightly more efficient to use kfree() or vfree() if you are certain + * that you know which one to use. + * + * Context: Any context except NMI. */ void kvfree(const void *addr) { diff --git a/mm/vmacache.c b/mm/vmacache.c index ea517bef7dc5..cdc32a3b02fa 100644 --- a/mm/vmacache.c +++ b/mm/vmacache.c @@ -20,44 +20,6 @@ #define VMACACHE_HASH(addr) ((addr >> VMACACHE_SHIFT) & VMACACHE_MASK) /* - * Flush vma caches for threads that share a given mm. - * - * The operation is safe because the caller holds the mmap_sem - * exclusively and other threads accessing the vma cache will - * have mmap_sem held at least for read, so no extra locking - * is required to maintain the vma cache. - */ -void vmacache_flush_all(struct mm_struct *mm) -{ - struct task_struct *g, *p; - - count_vm_vmacache_event(VMACACHE_FULL_FLUSHES); - - /* - * Single threaded tasks need not iterate the entire - * list of process. We can avoid the flushing as well - * since the mm's seqnum was increased and don't have - * to worry about other threads' seqnum. Current's - * flush will occur upon the next lookup. - */ - if (atomic_read(&mm->mm_users) == 1) - return; - - rcu_read_lock(); - for_each_process_thread(g, p) { - /* - * Only flush the vmacache pointers as the - * mm seqnum is already set and curr's will - * be set upon invalidation when the next - * lookup is done. - */ - if (mm == p->mm) - vmacache_flush(p); - } - rcu_read_unlock(); -} - -/* * This task may be accessing a foreign mm via (for example) * get_user_pages()->find_vma(). The vmacache is task-local and this * task's vmacache pertains to a different mm (ie, its own). There is diff --git a/mm/vmscan.c b/mm/vmscan.c index 7e7d25504651..c7ce2c161225 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -476,6 +476,17 @@ static unsigned long do_shrink_slab(struct shrink_control *shrinkctl, delta = freeable >> priority; delta *= 4; do_div(delta, shrinker->seeks); + + /* + * Make sure we apply some minimal pressure on default priority + * even on small cgroups. Stale objects are not only consuming memory + * by themselves, but can also hold a reference to a dying cgroup, + * preventing it from being reclaimed. A dying cgroup with all + * corresponding structures like per-cpu stats and kmem caches + * can be really big, so it may lead to a significant waste of memory. + */ + delta = max_t(unsigned long long, delta, min(freeable, batch_size)); + total_scan += delta; if (total_scan < 0) { pr_err("shrink_slab: %pF negative objects to delete nr=%ld\n", diff --git a/net/batman-adv/Kconfig b/net/batman-adv/Kconfig index 361116f77cb9..f75816f58107 100644 --- a/net/batman-adv/Kconfig +++ b/net/batman-adv/Kconfig @@ -106,3 +106,14 @@ config BATMAN_ADV_DEBUG say N here. This enables compilation of support for outputting debugging information to the kernel log. The output is controlled via the module parameter debug. + +config BATMAN_ADV_TRACING + bool "B.A.T.M.A.N. tracing support" + depends on BATMAN_ADV + depends on EVENT_TRACING + help + This is an option for use by developers; most people should + say N here. Select this option to gather traces like the debug + messages using the generic tracing infrastructure of the kernel. + BATMAN_ADV_DEBUG must also be selected to get trace events for + batadv_dbg. diff --git a/net/batman-adv/Makefile b/net/batman-adv/Makefile index b97ba6fb8353..9b58160fe485 100644 --- a/net/batman-adv/Makefile +++ b/net/batman-adv/Makefile @@ -42,6 +42,9 @@ batman-adv-y += routing.o batman-adv-y += send.o batman-adv-y += soft-interface.o batman-adv-y += sysfs.o +batman-adv-$(CONFIG_BATMAN_ADV_TRACING) += trace.o batman-adv-y += tp_meter.o batman-adv-y += translation-table.o batman-adv-y += tvlv.o + +CFLAGS_trace.o := -I$(src) diff --git a/net/batman-adv/bat_iv_ogm.c b/net/batman-adv/bat_iv_ogm.c index 73bf6a93a3cf..d2227091029f 100644 --- a/net/batman-adv/bat_iv_ogm.c +++ b/net/batman-adv/bat_iv_ogm.c @@ -138,169 +138,6 @@ static u8 batadv_ring_buffer_avg(const u8 lq_recv[]) } /** - * batadv_iv_ogm_orig_free() - free the private resources allocated for this - * orig_node - * @orig_node: the orig_node for which the resources have to be free'd - */ -static void batadv_iv_ogm_orig_free(struct batadv_orig_node *orig_node) -{ - kfree(orig_node->bat_iv.bcast_own); - kfree(orig_node->bat_iv.bcast_own_sum); -} - -/** - * batadv_iv_ogm_orig_add_if() - change the private structures of the orig_node - * to include the new hard-interface - * @orig_node: the orig_node that has to be changed - * @max_if_num: the current amount of interfaces - * - * Return: 0 on success, a negative error code otherwise. - */ -static int batadv_iv_ogm_orig_add_if(struct batadv_orig_node *orig_node, - unsigned int max_if_num) -{ - void *data_ptr; - size_t old_size; - int ret = -ENOMEM; - - spin_lock_bh(&orig_node->bat_iv.ogm_cnt_lock); - - old_size = (max_if_num - 1) * sizeof(unsigned long) * BATADV_NUM_WORDS; - data_ptr = kmalloc_array(max_if_num, - BATADV_NUM_WORDS * sizeof(unsigned long), - GFP_ATOMIC); - if (!data_ptr) - goto unlock; - - memcpy(data_ptr, orig_node->bat_iv.bcast_own, old_size); - kfree(orig_node->bat_iv.bcast_own); - orig_node->bat_iv.bcast_own = data_ptr; - - data_ptr = kmalloc_array(max_if_num, sizeof(u8), GFP_ATOMIC); - if (!data_ptr) - goto unlock; - - memcpy(data_ptr, orig_node->bat_iv.bcast_own_sum, - (max_if_num - 1) * sizeof(u8)); - kfree(orig_node->bat_iv.bcast_own_sum); - orig_node->bat_iv.bcast_own_sum = data_ptr; - - ret = 0; - -unlock: - spin_unlock_bh(&orig_node->bat_iv.ogm_cnt_lock); - - return ret; -} - -/** - * batadv_iv_ogm_drop_bcast_own_entry() - drop section of bcast_own - * @orig_node: the orig_node that has to be changed - * @max_if_num: the current amount of interfaces - * @del_if_num: the index of the interface being removed - */ -static void -batadv_iv_ogm_drop_bcast_own_entry(struct batadv_orig_node *orig_node, - unsigned int max_if_num, - unsigned int del_if_num) -{ - size_t chunk_size; - size_t if_offset; - void *data_ptr; - - lockdep_assert_held(&orig_node->bat_iv.ogm_cnt_lock); - - chunk_size = sizeof(unsigned long) * BATADV_NUM_WORDS; - data_ptr = kmalloc_array(max_if_num, chunk_size, GFP_ATOMIC); - if (!data_ptr) - /* use old buffer when new one could not be allocated */ - data_ptr = orig_node->bat_iv.bcast_own; - - /* copy first part */ - memmove(data_ptr, orig_node->bat_iv.bcast_own, del_if_num * chunk_size); - - /* copy second part */ - if_offset = (del_if_num + 1) * chunk_size; - memmove((char *)data_ptr + del_if_num * chunk_size, - (uint8_t *)orig_node->bat_iv.bcast_own + if_offset, - (max_if_num - del_if_num) * chunk_size); - - /* bcast_own was shrunk down in new buffer; free old one */ - if (orig_node->bat_iv.bcast_own != data_ptr) { - kfree(orig_node->bat_iv.bcast_own); - orig_node->bat_iv.bcast_own = data_ptr; - } -} - -/** - * batadv_iv_ogm_drop_bcast_own_sum_entry() - drop section of bcast_own_sum - * @orig_node: the orig_node that has to be changed - * @max_if_num: the current amount of interfaces - * @del_if_num: the index of the interface being removed - */ -static void -batadv_iv_ogm_drop_bcast_own_sum_entry(struct batadv_orig_node *orig_node, - unsigned int max_if_num, - unsigned int del_if_num) -{ - size_t if_offset; - void *data_ptr; - - lockdep_assert_held(&orig_node->bat_iv.ogm_cnt_lock); - - data_ptr = kmalloc_array(max_if_num, sizeof(u8), GFP_ATOMIC); - if (!data_ptr) - /* use old buffer when new one could not be allocated */ - data_ptr = orig_node->bat_iv.bcast_own_sum; - - memmove(data_ptr, orig_node->bat_iv.bcast_own_sum, - del_if_num * sizeof(u8)); - - if_offset = (del_if_num + 1) * sizeof(u8); - memmove((char *)data_ptr + del_if_num * sizeof(u8), - orig_node->bat_iv.bcast_own_sum + if_offset, - (max_if_num - del_if_num) * sizeof(u8)); - - /* bcast_own_sum was shrunk down in new buffer; free old one */ - if (orig_node->bat_iv.bcast_own_sum != data_ptr) { - kfree(orig_node->bat_iv.bcast_own_sum); - orig_node->bat_iv.bcast_own_sum = data_ptr; - } -} - -/** - * batadv_iv_ogm_orig_del_if() - change the private structures of the orig_node - * to exclude the removed interface - * @orig_node: the orig_node that has to be changed - * @max_if_num: the current amount of interfaces - * @del_if_num: the index of the interface being removed - * - * Return: 0 on success, a negative error code otherwise. - */ -static int batadv_iv_ogm_orig_del_if(struct batadv_orig_node *orig_node, - unsigned int max_if_num, - unsigned int del_if_num) -{ - spin_lock_bh(&orig_node->bat_iv.ogm_cnt_lock); - - if (max_if_num == 0) { - kfree(orig_node->bat_iv.bcast_own); - kfree(orig_node->bat_iv.bcast_own_sum); - orig_node->bat_iv.bcast_own = NULL; - orig_node->bat_iv.bcast_own_sum = NULL; - } else { - batadv_iv_ogm_drop_bcast_own_entry(orig_node, max_if_num, - del_if_num); - batadv_iv_ogm_drop_bcast_own_sum_entry(orig_node, max_if_num, - del_if_num); - } - - spin_unlock_bh(&orig_node->bat_iv.ogm_cnt_lock); - - return 0; -} - -/** * batadv_iv_ogm_orig_get() - retrieve or create (if does not exist) an * originator * @bat_priv: the bat priv with all the soft interface information @@ -315,7 +152,6 @@ batadv_iv_ogm_orig_get(struct batadv_priv *bat_priv, const u8 *addr) { struct batadv_orig_node *orig_node; int hash_added; - size_t size; orig_node = batadv_orig_hash_find(bat_priv, addr); if (orig_node) @@ -327,16 +163,6 @@ batadv_iv_ogm_orig_get(struct batadv_priv *bat_priv, const u8 *addr) spin_lock_init(&orig_node->bat_iv.ogm_cnt_lock); - size = bat_priv->num_ifaces * sizeof(unsigned long) * BATADV_NUM_WORDS; - orig_node->bat_iv.bcast_own = kzalloc(size, GFP_ATOMIC); - if (!orig_node->bat_iv.bcast_own) - goto free_orig_node; - - size = bat_priv->num_ifaces * sizeof(u8); - orig_node->bat_iv.bcast_own_sum = kzalloc(size, GFP_ATOMIC); - if (!orig_node->bat_iv.bcast_own_sum) - goto free_orig_node; - kref_get(&orig_node->refcount); hash_added = batadv_hash_add(bat_priv->orig_hash, batadv_compare_orig, batadv_choose_orig, orig_node, @@ -347,8 +173,9 @@ batadv_iv_ogm_orig_get(struct batadv_priv *bat_priv, const u8 *addr) return orig_node; free_orig_node_hash: + /* reference for batadv_hash_add */ batadv_orig_node_put(orig_node); -free_orig_node: + /* reference from batadv_orig_node_new */ batadv_orig_node_put(orig_node); return NULL; @@ -893,26 +720,30 @@ batadv_iv_ogm_slide_own_bcast_window(struct batadv_hard_iface *hard_iface) struct batadv_hashtable *hash = bat_priv->orig_hash; struct hlist_head *head; struct batadv_orig_node *orig_node; + struct batadv_orig_ifinfo *orig_ifinfo; unsigned long *word; u32 i; - size_t word_index; u8 *w; - unsigned int if_num; for (i = 0; i < hash->size; i++) { head = &hash->table[i]; rcu_read_lock(); hlist_for_each_entry_rcu(orig_node, head, hash_entry) { - spin_lock_bh(&orig_node->bat_iv.ogm_cnt_lock); - word_index = hard_iface->if_num * BATADV_NUM_WORDS; - word = &orig_node->bat_iv.bcast_own[word_index]; - - batadv_bit_get_packet(bat_priv, word, 1, 0); - if_num = hard_iface->if_num; - w = &orig_node->bat_iv.bcast_own_sum[if_num]; - *w = bitmap_weight(word, BATADV_TQ_LOCAL_WINDOW_SIZE); - spin_unlock_bh(&orig_node->bat_iv.ogm_cnt_lock); + hlist_for_each_entry_rcu(orig_ifinfo, + &orig_node->ifinfo_list, + list) { + if (orig_ifinfo->if_outgoing != hard_iface) + continue; + + spin_lock_bh(&orig_node->bat_iv.ogm_cnt_lock); + word = orig_ifinfo->bat_iv.bcast_own; + batadv_bit_get_packet(bat_priv, word, 1, 0); + w = &orig_ifinfo->bat_iv.bcast_own_sum; + *w = bitmap_weight(word, + BATADV_TQ_LOCAL_WINDOW_SIZE); + spin_unlock_bh(&orig_node->bat_iv.ogm_cnt_lock); + } } rcu_read_unlock(); } @@ -1000,6 +831,35 @@ out: } /** + * batadv_iv_orig_ifinfo_sum() - Get bcast_own sum for originator over iterface + * @orig_node: originator which reproadcasted the OGMs directly + * @if_outgoing: interface which transmitted the original OGM and received the + * direct rebroadcast + * + * Return: Number of replied (rebroadcasted) OGMs which were transmitted by + * an originator and directly (without intermediate hop) received by a specific + * interface + */ +static u8 batadv_iv_orig_ifinfo_sum(struct batadv_orig_node *orig_node, + struct batadv_hard_iface *if_outgoing) +{ + struct batadv_orig_ifinfo *orig_ifinfo; + u8 sum; + + orig_ifinfo = batadv_orig_ifinfo_get(orig_node, if_outgoing); + if (!orig_ifinfo) + return 0; + + spin_lock_bh(&orig_node->bat_iv.ogm_cnt_lock); + sum = orig_ifinfo->bat_iv.bcast_own_sum; + spin_unlock_bh(&orig_node->bat_iv.ogm_cnt_lock); + + batadv_orig_ifinfo_put(orig_ifinfo); + + return sum; +} + +/** * batadv_iv_ogm_orig_update() - use OGM to update corresponding data in an * originator * @bat_priv: the bat priv with all the soft interface information @@ -1026,8 +886,6 @@ batadv_iv_ogm_orig_update(struct batadv_priv *bat_priv, struct batadv_neigh_node *neigh_node = NULL; struct batadv_neigh_node *tmp_neigh_node = NULL; struct batadv_neigh_node *router = NULL; - struct batadv_orig_node *orig_node_tmp; - unsigned int if_num; u8 sum_orig, sum_neigh; u8 *neigh_addr; u8 tq_avg; @@ -1132,18 +990,10 @@ batadv_iv_ogm_orig_update(struct batadv_priv *bat_priv, */ if (router_ifinfo && neigh_ifinfo->bat_iv.tq_avg == router_ifinfo->bat_iv.tq_avg) { - orig_node_tmp = router->orig_node; - spin_lock_bh(&orig_node_tmp->bat_iv.ogm_cnt_lock); - if_num = router->if_incoming->if_num; - sum_orig = orig_node_tmp->bat_iv.bcast_own_sum[if_num]; - spin_unlock_bh(&orig_node_tmp->bat_iv.ogm_cnt_lock); - - orig_node_tmp = neigh_node->orig_node; - spin_lock_bh(&orig_node_tmp->bat_iv.ogm_cnt_lock); - if_num = neigh_node->if_incoming->if_num; - sum_neigh = orig_node_tmp->bat_iv.bcast_own_sum[if_num]; - spin_unlock_bh(&orig_node_tmp->bat_iv.ogm_cnt_lock); - + sum_orig = batadv_iv_orig_ifinfo_sum(router->orig_node, + router->if_incoming); + sum_neigh = batadv_iv_orig_ifinfo_sum(neigh_node->orig_node, + neigh_node->if_incoming); if (sum_orig >= sum_neigh) goto out; } @@ -1186,7 +1036,6 @@ static bool batadv_iv_ogm_calc_tq(struct batadv_orig_node *orig_node, u8 total_count; u8 orig_eq_count, neigh_rq_count, neigh_rq_inv, tq_own; unsigned int neigh_rq_inv_cube, neigh_rq_max_cube; - unsigned int if_num; unsigned int tq_asym_penalty, inv_asym_penalty; unsigned int combined_tq; unsigned int tq_iface_penalty; @@ -1227,9 +1076,7 @@ static bool batadv_iv_ogm_calc_tq(struct batadv_orig_node *orig_node, orig_node->last_seen = jiffies; /* find packet count of corresponding one hop neighbor */ - spin_lock_bh(&orig_neigh_node->bat_iv.ogm_cnt_lock); - if_num = if_incoming->if_num; - orig_eq_count = orig_neigh_node->bat_iv.bcast_own_sum[if_num]; + orig_eq_count = batadv_iv_orig_ifinfo_sum(orig_neigh_node, if_incoming); neigh_ifinfo = batadv_neigh_ifinfo_new(neigh_node, if_outgoing); if (neigh_ifinfo) { neigh_rq_count = neigh_ifinfo->bat_iv.real_packet_count; @@ -1237,7 +1084,6 @@ static bool batadv_iv_ogm_calc_tq(struct batadv_orig_node *orig_node, } else { neigh_rq_count = 0; } - spin_unlock_bh(&orig_neigh_node->bat_iv.ogm_cnt_lock); /* pay attention to not get a value bigger than 100 % */ if (orig_eq_count > neigh_rq_count) @@ -1622,6 +1468,49 @@ out: } /** + * batadv_iv_ogm_process_reply() - Check OGM for direct reply and process it + * @ogm_packet: rebroadcast OGM packet to process + * @if_incoming: the interface where this packet was received + * @orig_node: originator which reproadcasted the OGMs + * @if_incoming_seqno: OGM sequence number when rebroadcast was received + */ +static void batadv_iv_ogm_process_reply(struct batadv_ogm_packet *ogm_packet, + struct batadv_hard_iface *if_incoming, + struct batadv_orig_node *orig_node, + u32 if_incoming_seqno) +{ + struct batadv_orig_ifinfo *orig_ifinfo; + s32 bit_pos; + u8 *weight; + + /* neighbor has to indicate direct link and it has to + * come via the corresponding interface + */ + if (!(ogm_packet->flags & BATADV_DIRECTLINK)) + return; + + if (!batadv_compare_eth(if_incoming->net_dev->dev_addr, + ogm_packet->orig)) + return; + + orig_ifinfo = batadv_orig_ifinfo_get(orig_node, if_incoming); + if (!orig_ifinfo) + return; + + /* save packet seqno for bidirectional check */ + spin_lock_bh(&orig_node->bat_iv.ogm_cnt_lock); + bit_pos = if_incoming_seqno - 2; + bit_pos -= ntohl(ogm_packet->seqno); + batadv_set_bit(orig_ifinfo->bat_iv.bcast_own, bit_pos); + weight = &orig_ifinfo->bat_iv.bcast_own_sum; + *weight = bitmap_weight(orig_ifinfo->bat_iv.bcast_own, + BATADV_TQ_LOCAL_WINDOW_SIZE); + spin_unlock_bh(&orig_node->bat_iv.ogm_cnt_lock); + + batadv_orig_ifinfo_put(orig_ifinfo); +} + +/** * batadv_iv_ogm_process() - process an incoming batman iv OGM * @skb: the skb containing the OGM * @ogm_offset: offset to the OGM which should be processed (for aggregates) @@ -1705,37 +1594,13 @@ static void batadv_iv_ogm_process(const struct sk_buff *skb, int ogm_offset, } if (is_my_orig) { - unsigned long *word; - size_t offset; - s32 bit_pos; - unsigned int if_num; - u8 *weight; - orig_neigh_node = batadv_iv_ogm_orig_get(bat_priv, ethhdr->h_source); if (!orig_neigh_node) return; - /* neighbor has to indicate direct link and it has to - * come via the corresponding interface - * save packet seqno for bidirectional check - */ - if (has_directlink_flag && - batadv_compare_eth(if_incoming->net_dev->dev_addr, - ogm_packet->orig)) { - if_num = if_incoming->if_num; - offset = if_num * BATADV_NUM_WORDS; - - spin_lock_bh(&orig_neigh_node->bat_iv.ogm_cnt_lock); - word = &orig_neigh_node->bat_iv.bcast_own[offset]; - bit_pos = if_incoming_seqno - 2; - bit_pos -= ntohl(ogm_packet->seqno); - batadv_set_bit(word, bit_pos); - weight = &orig_neigh_node->bat_iv.bcast_own_sum[if_num]; - *weight = bitmap_weight(word, - BATADV_TQ_LOCAL_WINDOW_SIZE); - spin_unlock_bh(&orig_neigh_node->bat_iv.ogm_cnt_lock); - } + batadv_iv_ogm_process_reply(ogm_packet, if_incoming, + orig_neigh_node, if_incoming_seqno); batadv_dbg(BATADV_DBG_BATMAN, bat_priv, "Drop packet: originator packet from myself (via neighbor)\n"); @@ -2844,9 +2709,6 @@ static struct batadv_algo_ops batadv_batman_iv __read_mostly = { .print = batadv_iv_ogm_orig_print, #endif .dump = batadv_iv_ogm_orig_dump, - .free = batadv_iv_ogm_orig_free, - .add_if = batadv_iv_ogm_orig_add_if, - .del_if = batadv_iv_ogm_orig_del_if, }, .gw = { .init_sel_class = batadv_iv_init_sel_class, diff --git a/net/batman-adv/bat_v_elp.c b/net/batman-adv/bat_v_elp.c index 71c20c1d4002..9f481cfdf77d 100644 --- a/net/batman-adv/bat_v_elp.c +++ b/net/batman-adv/bat_v_elp.c @@ -241,7 +241,7 @@ batadv_v_elp_wifi_neigh_probe(struct batadv_hardif_neigh_node *neigh) * the packet to be exactly of that size to make the link * throughput estimation effective. */ - skb_put(skb, probe_len - hard_iface->bat_v.elp_skb->len); + skb_put_zero(skb, probe_len - hard_iface->bat_v.elp_skb->len); batadv_dbg(BATADV_DBG_BATMAN, bat_priv, "Sending unicast (probe) ELP packet on interface %s to %pM\n", @@ -268,6 +268,7 @@ static void batadv_v_elp_periodic_work(struct work_struct *work) struct batadv_priv *bat_priv; struct sk_buff *skb; u32 elp_interval; + bool ret; bat_v = container_of(work, struct batadv_hard_iface_bat_v, elp_wq.work); hard_iface = container_of(bat_v, struct batadv_hard_iface, bat_v); @@ -329,8 +330,11 @@ static void batadv_v_elp_periodic_work(struct work_struct *work) * may sleep and that is not allowed in an rcu protected * context. Therefore schedule a task for that. */ - queue_work(batadv_event_workqueue, - &hardif_neigh->bat_v.metric_work); + ret = queue_work(batadv_event_workqueue, + &hardif_neigh->bat_v.metric_work); + + if (!ret) + batadv_hardif_neigh_put(hardif_neigh); } rcu_read_unlock(); diff --git a/net/batman-adv/bridge_loop_avoidance.c b/net/batman-adv/bridge_loop_avoidance.c index ff9659af6b91..5f1aeeded0e3 100644 --- a/net/batman-adv/bridge_loop_avoidance.c +++ b/net/batman-adv/bridge_loop_avoidance.c @@ -1772,6 +1772,7 @@ batadv_bla_loopdetect_check(struct batadv_priv *bat_priv, struct sk_buff *skb, { struct batadv_bla_backbone_gw *backbone_gw; struct ethhdr *ethhdr; + bool ret; ethhdr = eth_hdr(skb); @@ -1795,8 +1796,13 @@ batadv_bla_loopdetect_check(struct batadv_priv *bat_priv, struct sk_buff *skb, if (unlikely(!backbone_gw)) return true; - queue_work(batadv_event_workqueue, &backbone_gw->report_work); - /* backbone_gw is unreferenced in the report work function function */ + ret = queue_work(batadv_event_workqueue, &backbone_gw->report_work); + + /* backbone_gw is unreferenced in the report work function function + * if queue_work() call was successful + */ + if (!ret) + batadv_backbone_gw_put(backbone_gw); return true; } diff --git a/net/batman-adv/debugfs.c b/net/batman-adv/debugfs.c index 3cb82378300b..8b608a2e2653 100644 --- a/net/batman-adv/debugfs.c +++ b/net/batman-adv/debugfs.c @@ -47,8 +47,24 @@ static struct dentry *batadv_debugfs; +/** + * batadv_debugfs_deprecated() - Log use of deprecated batadv debugfs access + * @file: file which was accessed + * @alt: explanation what can be used as alternative + */ +void batadv_debugfs_deprecated(struct file *file, const char *alt) +{ + struct dentry *dentry = file_dentry(file); + const char *name = dentry->d_name.name; + + pr_warn_ratelimited(DEPRECATED "%s (pid %d) Use of debugfs file \"%s\".\n%s", + current->comm, task_pid_nr(current), name, alt); +} + static int batadv_algorithms_open(struct inode *inode, struct file *file) { + batadv_debugfs_deprecated(file, + "Use genl command BATADV_CMD_GET_ROUTING_ALGOS instead\n"); return single_open(file, batadv_algo_seq_print_text, NULL); } @@ -56,6 +72,8 @@ static int neighbors_open(struct inode *inode, struct file *file) { struct net_device *net_dev = (struct net_device *)inode->i_private; + batadv_debugfs_deprecated(file, + "Use genl command BATADV_CMD_GET_NEIGHBORS instead\n"); return single_open(file, batadv_hardif_neigh_seq_print_text, net_dev); } @@ -63,6 +81,8 @@ static int batadv_originators_open(struct inode *inode, struct file *file) { struct net_device *net_dev = (struct net_device *)inode->i_private; + batadv_debugfs_deprecated(file, + "Use genl command BATADV_CMD_GET_ORIGINATORS instead\n"); return single_open(file, batadv_orig_seq_print_text, net_dev); } @@ -79,6 +99,8 @@ static int batadv_originators_hardif_open(struct inode *inode, { struct net_device *net_dev = (struct net_device *)inode->i_private; + batadv_debugfs_deprecated(file, + "Use genl command BATADV_CMD_GET_HARDIFS instead\n"); return single_open(file, batadv_orig_hardif_seq_print_text, net_dev); } @@ -86,6 +108,8 @@ static int batadv_gateways_open(struct inode *inode, struct file *file) { struct net_device *net_dev = (struct net_device *)inode->i_private; + batadv_debugfs_deprecated(file, + "Use genl command BATADV_CMD_GET_GATEWAYS instead\n"); return single_open(file, batadv_gw_client_seq_print_text, net_dev); } @@ -93,6 +117,8 @@ static int batadv_transtable_global_open(struct inode *inode, struct file *file) { struct net_device *net_dev = (struct net_device *)inode->i_private; + batadv_debugfs_deprecated(file, + "Use genl command BATADV_CMD_GET_TRANSTABLE_GLOBAL instead\n"); return single_open(file, batadv_tt_global_seq_print_text, net_dev); } @@ -101,6 +127,8 @@ static int batadv_bla_claim_table_open(struct inode *inode, struct file *file) { struct net_device *net_dev = (struct net_device *)inode->i_private; + batadv_debugfs_deprecated(file, + "Use genl command BATADV_CMD_GET_BLA_CLAIM instead\n"); return single_open(file, batadv_bla_claim_table_seq_print_text, net_dev); } @@ -110,6 +138,8 @@ static int batadv_bla_backbone_table_open(struct inode *inode, { struct net_device *net_dev = (struct net_device *)inode->i_private; + batadv_debugfs_deprecated(file, + "Use genl command BATADV_CMD_GET_BLA_BACKBONE instead\n"); return single_open(file, batadv_bla_backbone_table_seq_print_text, net_dev); } @@ -128,6 +158,8 @@ static int batadv_dat_cache_open(struct inode *inode, struct file *file) { struct net_device *net_dev = (struct net_device *)inode->i_private; + batadv_debugfs_deprecated(file, + "Use genl command BATADV_CMD_GET_DAT_CACHE instead\n"); return single_open(file, batadv_dat_cache_seq_print_text, net_dev); } #endif @@ -136,6 +168,8 @@ static int batadv_transtable_local_open(struct inode *inode, struct file *file) { struct net_device *net_dev = (struct net_device *)inode->i_private; + batadv_debugfs_deprecated(file, + "Use genl command BATADV_CMD_GET_TRANSTABLE_LOCAL instead\n"); return single_open(file, batadv_tt_local_seq_print_text, net_dev); } @@ -149,6 +183,7 @@ static int batadv_nc_nodes_open(struct inode *inode, struct file *file) { struct net_device *net_dev = (struct net_device *)inode->i_private; + batadv_debugfs_deprecated(file, ""); return single_open(file, batadv_nc_nodes_seq_print_text, net_dev); } #endif @@ -165,6 +200,8 @@ static int batadv_mcast_flags_open(struct inode *inode, struct file *file) { struct net_device *net_dev = (struct net_device *)inode->i_private; + batadv_debugfs_deprecated(file, + "Use genl command BATADV_CMD_GET_MCAST_FLAGS instead\n"); return single_open(file, batadv_mcast_flags_seq_print_text, net_dev); } #endif diff --git a/net/batman-adv/debugfs.h b/net/batman-adv/debugfs.h index 08a592ffbee5..8de018e5c577 100644 --- a/net/batman-adv/debugfs.h +++ b/net/batman-adv/debugfs.h @@ -21,12 +21,14 @@ #include "main.h" +struct file; struct net_device; #define BATADV_DEBUGFS_SUBDIR "batman_adv" #if IS_ENABLED(CONFIG_BATMAN_ADV_DEBUGFS) +void batadv_debugfs_deprecated(struct file *file, const char *alt); void batadv_debugfs_init(void); void batadv_debugfs_destroy(void); int batadv_debugfs_add_meshif(struct net_device *dev); @@ -38,6 +40,10 @@ void batadv_debugfs_del_hardif(struct batadv_hard_iface *hard_iface); #else +static inline void batadv_debugfs_deprecated(struct file *file, const char *alt) +{ +} + static inline void batadv_debugfs_init(void) { } diff --git a/net/batman-adv/gateway_client.c b/net/batman-adv/gateway_client.c index 8b198ee798c9..140c61a3f1ec 100644 --- a/net/batman-adv/gateway_client.c +++ b/net/batman-adv/gateway_client.c @@ -32,6 +32,7 @@ #include <linux/kernel.h> #include <linux/kref.h> #include <linux/list.h> +#include <linux/lockdep.h> #include <linux/netdevice.h> #include <linux/netlink.h> #include <linux/rculist.h> @@ -348,6 +349,9 @@ out: * @bat_priv: the bat priv with all the soft interface information * @orig_node: originator announcing gateway capabilities * @gateway: announced bandwidth information + * + * Has to be called with the appropriate locks being acquired + * (gw.list_lock). */ static void batadv_gw_node_add(struct batadv_priv *bat_priv, struct batadv_orig_node *orig_node, @@ -355,6 +359,8 @@ static void batadv_gw_node_add(struct batadv_priv *bat_priv, { struct batadv_gw_node *gw_node; + lockdep_assert_held(&bat_priv->gw.list_lock); + if (gateway->bandwidth_down == 0) return; @@ -369,10 +375,8 @@ static void batadv_gw_node_add(struct batadv_priv *bat_priv, gw_node->bandwidth_down = ntohl(gateway->bandwidth_down); gw_node->bandwidth_up = ntohl(gateway->bandwidth_up); - spin_lock_bh(&bat_priv->gw.list_lock); kref_get(&gw_node->refcount); hlist_add_head_rcu(&gw_node->list, &bat_priv->gw.gateway_list); - spin_unlock_bh(&bat_priv->gw.list_lock); batadv_dbg(BATADV_DBG_BATMAN, bat_priv, "Found new gateway %pM -> gw bandwidth: %u.%u/%u.%u MBit\n", @@ -428,11 +432,14 @@ void batadv_gw_node_update(struct batadv_priv *bat_priv, { struct batadv_gw_node *gw_node, *curr_gw = NULL; + spin_lock_bh(&bat_priv->gw.list_lock); gw_node = batadv_gw_node_get(bat_priv, orig_node); if (!gw_node) { batadv_gw_node_add(bat_priv, orig_node, gateway); + spin_unlock_bh(&bat_priv->gw.list_lock); goto out; } + spin_unlock_bh(&bat_priv->gw.list_lock); if (gw_node->bandwidth_down == ntohl(gateway->bandwidth_down) && gw_node->bandwidth_up == ntohl(gateway->bandwidth_up)) diff --git a/net/batman-adv/hard-interface.c b/net/batman-adv/hard-interface.c index 2f0d42f2f913..781c5b6e6e8e 100644 --- a/net/batman-adv/hard-interface.c +++ b/net/batman-adv/hard-interface.c @@ -763,11 +763,6 @@ int batadv_hardif_enable_interface(struct batadv_hard_iface *hard_iface, hard_iface->soft_iface = soft_iface; bat_priv = netdev_priv(hard_iface->soft_iface); - if (bat_priv->num_ifaces >= UINT_MAX) { - ret = -ENOSPC; - goto err_dev; - } - ret = netdev_master_upper_dev_link(hard_iface->net_dev, soft_iface, NULL, NULL, NULL); if (ret) @@ -777,16 +772,7 @@ int batadv_hardif_enable_interface(struct batadv_hard_iface *hard_iface, if (ret < 0) goto err_upper; - hard_iface->if_num = bat_priv->num_ifaces; - bat_priv->num_ifaces++; hard_iface->if_status = BATADV_IF_INACTIVE; - ret = batadv_orig_hash_add_if(hard_iface, bat_priv->num_ifaces); - if (ret < 0) { - bat_priv->algo_ops->iface.disable(hard_iface); - bat_priv->num_ifaces--; - hard_iface->if_status = BATADV_IF_NOT_IN_USE; - goto err_upper; - } kref_get(&hard_iface->refcount); hard_iface->batman_adv_ptype.type = ethertype; @@ -834,6 +820,33 @@ err: } /** + * batadv_hardif_cnt() - get number of interfaces enslaved to soft interface + * @soft_iface: soft interface to check + * + * This function is only using RCU for locking - the result can therefore be + * off when another functions is modifying the list at the same time. The + * caller can use the rtnl_lock to make sure that the count is accurate. + * + * Return: number of connected/enslaved hard interfaces + */ +static size_t batadv_hardif_cnt(const struct net_device *soft_iface) +{ + struct batadv_hard_iface *hard_iface; + size_t count = 0; + + rcu_read_lock(); + list_for_each_entry_rcu(hard_iface, &batadv_hardif_list, list) { + if (hard_iface->soft_iface != soft_iface) + continue; + + count++; + } + rcu_read_unlock(); + + return count; +} + +/** * batadv_hardif_disable_interface() - Remove hard interface from soft interface * @hard_iface: hard interface to be removed * @autodel: whether to delete soft interface when it doesn't contain any other @@ -855,9 +868,6 @@ void batadv_hardif_disable_interface(struct batadv_hard_iface *hard_iface, dev_remove_pack(&hard_iface->batman_adv_ptype); batadv_hardif_put(hard_iface); - bat_priv->num_ifaces--; - batadv_orig_hash_del_if(hard_iface, bat_priv->num_ifaces); - primary_if = batadv_primary_if_get_selected(bat_priv); if (hard_iface == primary_if) { struct batadv_hard_iface *new_if; @@ -881,7 +891,7 @@ void batadv_hardif_disable_interface(struct batadv_hard_iface *hard_iface, batadv_hardif_recalc_extra_skbroom(hard_iface->soft_iface); /* nobody uses this interface anymore */ - if (bat_priv->num_ifaces == 0) { + if (batadv_hardif_cnt(hard_iface->soft_iface) <= 1) { batadv_gw_check_client_stop(bat_priv); if (autodel == BATADV_IF_CLEANUP_AUTO) @@ -917,7 +927,6 @@ batadv_hardif_add_interface(struct net_device *net_dev) if (ret) goto free_if; - hard_iface->if_num = 0; hard_iface->net_dev = net_dev; hard_iface->soft_iface = NULL; hard_iface->if_status = BATADV_IF_NOT_IN_USE; diff --git a/net/batman-adv/icmp_socket.c b/net/batman-adv/icmp_socket.c index 55c358ad3331..d70f363c52ae 100644 --- a/net/batman-adv/icmp_socket.c +++ b/net/batman-adv/icmp_socket.c @@ -47,6 +47,7 @@ #include <linux/wait.h> #include <uapi/linux/batadv_packet.h> +#include "debugfs.h" #include "hard-interface.h" #include "log.h" #include "originator.h" @@ -74,6 +75,8 @@ static int batadv_socket_open(struct inode *inode, struct file *file) if (!try_module_get(THIS_MODULE)) return -EBUSY; + batadv_debugfs_deprecated(file, ""); + nonseekable_open(inode, file); socket_client = kmalloc(sizeof(*socket_client), GFP_KERNEL); diff --git a/net/batman-adv/log.c b/net/batman-adv/log.c index 853773e45f79..6beb5f067810 100644 --- a/net/batman-adv/log.c +++ b/net/batman-adv/log.c @@ -40,6 +40,9 @@ #include <linux/wait.h> #include <stdarg.h> +#include "debugfs.h" +#include "trace.h" + #define BATADV_LOG_BUFF_MASK (batadv_log_buff_len - 1) static const int batadv_log_buff_len = BATADV_LOG_BUF_LEN; @@ -98,13 +101,19 @@ static int batadv_fdebug_log(struct batadv_priv_debug_log *debug_log, */ int batadv_debug_log(struct batadv_priv *bat_priv, const char *fmt, ...) { + struct va_format vaf; va_list args; - char tmp_log_buf[256]; va_start(args, fmt); - vscnprintf(tmp_log_buf, sizeof(tmp_log_buf), fmt, args); - batadv_fdebug_log(bat_priv->debug_log, "[%10u] %s", - jiffies_to_msecs(jiffies), tmp_log_buf); + + vaf.fmt = fmt; + vaf.va = &args; + + batadv_fdebug_log(bat_priv->debug_log, "[%10u] %pV", + jiffies_to_msecs(jiffies), &vaf); + + trace_batadv_dbg(bat_priv, &vaf); + va_end(args); return 0; @@ -115,6 +124,9 @@ static int batadv_log_open(struct inode *inode, struct file *file) if (!try_module_get(THIS_MODULE)) return -EBUSY; + batadv_debugfs_deprecated(file, + "Use tracepoint batadv:batadv_dbg instead\n"); + nonseekable_open(inode, file); file->private_data = inode->i_private; return 0; diff --git a/net/batman-adv/main.h b/net/batman-adv/main.h index 8da3c9336111..2002b70e18db 100644 --- a/net/batman-adv/main.h +++ b/net/batman-adv/main.h @@ -25,7 +25,7 @@ #define BATADV_DRIVER_DEVICE "batman-adv" #ifndef BATADV_SOURCE_VERSION -#define BATADV_SOURCE_VERSION "2018.2" +#define BATADV_SOURCE_VERSION "2018.4" #endif /* B.A.T.M.A.N. parameters */ diff --git a/net/batman-adv/network-coding.c b/net/batman-adv/network-coding.c index c3578444f3cb..34caf129a9bf 100644 --- a/net/batman-adv/network-coding.c +++ b/net/batman-adv/network-coding.c @@ -854,16 +854,27 @@ batadv_nc_get_nc_node(struct batadv_priv *bat_priv, spinlock_t *lock; /* Used to lock list selected by "int in_coding" */ struct list_head *list; + /* Select ingoing or outgoing coding node */ + if (in_coding) { + lock = &orig_neigh_node->in_coding_list_lock; + list = &orig_neigh_node->in_coding_list; + } else { + lock = &orig_neigh_node->out_coding_list_lock; + list = &orig_neigh_node->out_coding_list; + } + + spin_lock_bh(lock); + /* Check if nc_node is already added */ nc_node = batadv_nc_find_nc_node(orig_node, orig_neigh_node, in_coding); /* Node found */ if (nc_node) - return nc_node; + goto unlock; nc_node = kzalloc(sizeof(*nc_node), GFP_ATOMIC); if (!nc_node) - return NULL; + goto unlock; /* Initialize nc_node */ INIT_LIST_HEAD(&nc_node->list); @@ -872,22 +883,14 @@ batadv_nc_get_nc_node(struct batadv_priv *bat_priv, kref_get(&orig_neigh_node->refcount); nc_node->orig_node = orig_neigh_node; - /* Select ingoing or outgoing coding node */ - if (in_coding) { - lock = &orig_neigh_node->in_coding_list_lock; - list = &orig_neigh_node->in_coding_list; - } else { - lock = &orig_neigh_node->out_coding_list_lock; - list = &orig_neigh_node->out_coding_list; - } - batadv_dbg(BATADV_DBG_NC, bat_priv, "Adding nc_node %pM -> %pM\n", nc_node->addr, nc_node->orig_node->orig); /* Add nc_node to orig_node */ - spin_lock_bh(lock); kref_get(&nc_node->refcount); list_add_tail_rcu(&nc_node->list, list); + +unlock: spin_unlock_bh(lock); return nc_node; diff --git a/net/batman-adv/originator.c b/net/batman-adv/originator.c index 1d295da3e342..56a981af5c92 100644 --- a/net/batman-adv/originator.c +++ b/net/batman-adv/originator.c @@ -904,9 +904,6 @@ static void batadv_orig_node_free_rcu(struct rcu_head *rcu) batadv_frag_purge_orig(orig_node, NULL); - if (orig_node->bat_priv->algo_ops->orig.free) - orig_node->bat_priv->algo_ops->orig.free(orig_node); - kfree(orig_node->tt_buff); kfree(orig_node); } @@ -1555,107 +1552,3 @@ int batadv_orig_dump(struct sk_buff *msg, struct netlink_callback *cb) return ret; } - -/** - * batadv_orig_hash_add_if() - Add interface to originators in orig_hash - * @hard_iface: hard interface to add (already slave of the soft interface) - * @max_if_num: new number of interfaces - * - * Return: 0 on success or negative error number in case of failure - */ -int batadv_orig_hash_add_if(struct batadv_hard_iface *hard_iface, - unsigned int max_if_num) -{ - struct batadv_priv *bat_priv = netdev_priv(hard_iface->soft_iface); - struct batadv_algo_ops *bao = bat_priv->algo_ops; - struct batadv_hashtable *hash = bat_priv->orig_hash; - struct hlist_head *head; - struct batadv_orig_node *orig_node; - u32 i; - int ret; - - /* resize all orig nodes because orig_node->bcast_own(_sum) depend on - * if_num - */ - for (i = 0; i < hash->size; i++) { - head = &hash->table[i]; - - rcu_read_lock(); - hlist_for_each_entry_rcu(orig_node, head, hash_entry) { - ret = 0; - if (bao->orig.add_if) - ret = bao->orig.add_if(orig_node, max_if_num); - if (ret == -ENOMEM) - goto err; - } - rcu_read_unlock(); - } - - return 0; - -err: - rcu_read_unlock(); - return -ENOMEM; -} - -/** - * batadv_orig_hash_del_if() - Remove interface from originators in orig_hash - * @hard_iface: hard interface to remove (still slave of the soft interface) - * @max_if_num: new number of interfaces - * - * Return: 0 on success or negative error number in case of failure - */ -int batadv_orig_hash_del_if(struct batadv_hard_iface *hard_iface, - unsigned int max_if_num) -{ - struct batadv_priv *bat_priv = netdev_priv(hard_iface->soft_iface); - struct batadv_hashtable *hash = bat_priv->orig_hash; - struct hlist_head *head; - struct batadv_hard_iface *hard_iface_tmp; - struct batadv_orig_node *orig_node; - struct batadv_algo_ops *bao = bat_priv->algo_ops; - u32 i; - int ret; - - /* resize all orig nodes because orig_node->bcast_own(_sum) depend on - * if_num - */ - for (i = 0; i < hash->size; i++) { - head = &hash->table[i]; - - rcu_read_lock(); - hlist_for_each_entry_rcu(orig_node, head, hash_entry) { - ret = 0; - if (bao->orig.del_if) - ret = bao->orig.del_if(orig_node, max_if_num, - hard_iface->if_num); - if (ret == -ENOMEM) - goto err; - } - rcu_read_unlock(); - } - - /* renumber remaining batman interfaces _inside_ of orig_hash_lock */ - rcu_read_lock(); - list_for_each_entry_rcu(hard_iface_tmp, &batadv_hardif_list, list) { - if (hard_iface_tmp->if_status == BATADV_IF_NOT_IN_USE) - continue; - - if (hard_iface == hard_iface_tmp) - continue; - - if (hard_iface->soft_iface != hard_iface_tmp->soft_iface) - continue; - - if (hard_iface_tmp->if_num > hard_iface->if_num) - hard_iface_tmp->if_num--; - } - rcu_read_unlock(); - - hard_iface->if_num = -1; - return 0; - -err: - rcu_read_unlock(); - return -ENOMEM; -} diff --git a/net/batman-adv/originator.h b/net/batman-adv/originator.h index 3b3f59b881e1..a8b4c7b667ec 100644 --- a/net/batman-adv/originator.h +++ b/net/batman-adv/originator.h @@ -72,10 +72,6 @@ void batadv_orig_ifinfo_put(struct batadv_orig_ifinfo *orig_ifinfo); int batadv_orig_seq_print_text(struct seq_file *seq, void *offset); int batadv_orig_dump(struct sk_buff *msg, struct netlink_callback *cb); int batadv_orig_hardif_seq_print_text(struct seq_file *seq, void *offset); -int batadv_orig_hash_add_if(struct batadv_hard_iface *hard_iface, - unsigned int max_if_num); -int batadv_orig_hash_del_if(struct batadv_hard_iface *hard_iface, - unsigned int max_if_num); struct batadv_orig_node_vlan * batadv_orig_node_vlan_new(struct batadv_orig_node *orig_node, unsigned short vid); diff --git a/net/batman-adv/soft-interface.c b/net/batman-adv/soft-interface.c index 1485263a348b..5db5a0a4c959 100644 --- a/net/batman-adv/soft-interface.c +++ b/net/batman-adv/soft-interface.c @@ -574,15 +574,20 @@ int batadv_softif_create_vlan(struct batadv_priv *bat_priv, unsigned short vid) struct batadv_softif_vlan *vlan; int err; + spin_lock_bh(&bat_priv->softif_vlan_list_lock); + vlan = batadv_softif_vlan_get(bat_priv, vid); if (vlan) { batadv_softif_vlan_put(vlan); + spin_unlock_bh(&bat_priv->softif_vlan_list_lock); return -EEXIST; } vlan = kzalloc(sizeof(*vlan), GFP_ATOMIC); - if (!vlan) + if (!vlan) { + spin_unlock_bh(&bat_priv->softif_vlan_list_lock); return -ENOMEM; + } vlan->bat_priv = bat_priv; vlan->vid = vid; @@ -590,17 +595,23 @@ int batadv_softif_create_vlan(struct batadv_priv *bat_priv, unsigned short vid) atomic_set(&vlan->ap_isolation, 0); + kref_get(&vlan->refcount); + hlist_add_head_rcu(&vlan->list, &bat_priv->softif_vlan_list); + spin_unlock_bh(&bat_priv->softif_vlan_list_lock); + + /* batadv_sysfs_add_vlan cannot be in the spinlock section due to the + * sleeping behavior of the sysfs functions and the fs_reclaim lock + */ err = batadv_sysfs_add_vlan(bat_priv->soft_iface, vlan); if (err) { - kfree(vlan); + /* ref for the function */ + batadv_softif_vlan_put(vlan); + + /* ref for the list */ + batadv_softif_vlan_put(vlan); return err; } - spin_lock_bh(&bat_priv->softif_vlan_list_lock); - kref_get(&vlan->refcount); - hlist_add_head_rcu(&vlan->list, &bat_priv->softif_vlan_list); - spin_unlock_bh(&bat_priv->softif_vlan_list_lock); - /* add a new TT local entry. This one will be marked with the NOPURGE * flag */ @@ -833,7 +844,6 @@ static int batadv_softif_init_late(struct net_device *dev) atomic_set(&bat_priv->frag_seqno, random_seqno); bat_priv->primary_if = NULL; - bat_priv->num_ifaces = 0; batadv_nc_init_bat_priv(bat_priv); @@ -1051,6 +1061,7 @@ static void batadv_softif_init_early(struct net_device *dev) dev->needs_free_netdev = true; dev->priv_destructor = batadv_softif_free; dev->features |= NETIF_F_HW_VLAN_CTAG_FILTER | NETIF_F_NETNS_LOCAL; + dev->features |= NETIF_F_LLTX; dev->priv_flags |= IFF_NO_QUEUE; /* can't call min_mtu, because the needed variables diff --git a/net/batman-adv/sysfs.c b/net/batman-adv/sysfs.c index f2eef43bd2ec..09427fc6494a 100644 --- a/net/batman-adv/sysfs.c +++ b/net/batman-adv/sysfs.c @@ -188,7 +188,8 @@ ssize_t batadv_store_##_name(struct kobject *kobj, \ \ return __batadv_store_uint_attr(buff, count, _min, _max, \ _post_func, attr, \ - &bat_priv->_var, net_dev); \ + &bat_priv->_var, net_dev, \ + NULL); \ } #define BATADV_ATTR_SIF_SHOW_UINT(_name, _var) \ @@ -262,7 +263,9 @@ ssize_t batadv_store_##_name(struct kobject *kobj, \ \ length = __batadv_store_uint_attr(buff, count, _min, _max, \ _post_func, attr, \ - &hard_iface->_var, net_dev); \ + &hard_iface->_var, \ + hard_iface->soft_iface, \ + net_dev); \ \ batadv_hardif_put(hard_iface); \ return length; \ @@ -356,10 +359,12 @@ __batadv_store_bool_attr(char *buff, size_t count, static int batadv_store_uint_attr(const char *buff, size_t count, struct net_device *net_dev, + struct net_device *slave_dev, const char *attr_name, unsigned int min, unsigned int max, atomic_t *attr) { + char ifname[IFNAMSIZ + 3] = ""; unsigned long uint_val; int ret; @@ -385,8 +390,11 @@ static int batadv_store_uint_attr(const char *buff, size_t count, if (atomic_read(attr) == uint_val) return count; - batadv_info(net_dev, "%s: Changing from: %i to: %lu\n", - attr_name, atomic_read(attr), uint_val); + if (slave_dev) + snprintf(ifname, sizeof(ifname), "%s: ", slave_dev->name); + + batadv_info(net_dev, "%s: %sChanging from: %i to: %lu\n", + attr_name, ifname, atomic_read(attr), uint_val); atomic_set(attr, uint_val); return count; @@ -397,12 +405,13 @@ static ssize_t __batadv_store_uint_attr(const char *buff, size_t count, void (*post_func)(struct net_device *), const struct attribute *attr, atomic_t *attr_store, - struct net_device *net_dev) + struct net_device *net_dev, + struct net_device *slave_dev) { int ret; - ret = batadv_store_uint_attr(buff, count, net_dev, attr->name, min, max, - attr_store); + ret = batadv_store_uint_attr(buff, count, net_dev, slave_dev, + attr->name, min, max, attr_store); if (post_func && ret) post_func(net_dev); @@ -571,7 +580,7 @@ static ssize_t batadv_store_gw_sel_class(struct kobject *kobj, return __batadv_store_uint_attr(buff, count, 1, BATADV_TQ_MAX_VALUE, batadv_post_gw_reselect, attr, &bat_priv->gw.sel_class, - bat_priv->soft_iface); + bat_priv->soft_iface, NULL); } static ssize_t batadv_show_gw_bwidth(struct kobject *kobj, @@ -1090,8 +1099,9 @@ static ssize_t batadv_store_throughput_override(struct kobject *kobj, if (old_tp_override == tp_override) goto out; - batadv_info(net_dev, "%s: Changing from: %u.%u MBit to: %u.%u MBit\n", - "throughput_override", + batadv_info(hard_iface->soft_iface, + "%s: %s: Changing from: %u.%u MBit to: %u.%u MBit\n", + "throughput_override", net_dev->name, old_tp_override / 10, old_tp_override % 10, tp_override / 10, tp_override % 10); diff --git a/net/batman-adv/trace.c b/net/batman-adv/trace.c new file mode 100644 index 000000000000..3d57f9981f25 --- /dev/null +++ b/net/batman-adv/trace.c @@ -0,0 +1,22 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (C) 2010-2018 B.A.T.M.A.N. contributors: + * + * Sven Eckelmann + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of version 2 of the GNU General Public + * License as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, but + * WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, see <http://www.gnu.org/licenses/>. + */ + +#include <linux/module.h> + +#define CREATE_TRACE_POINTS +#include "trace.h" diff --git a/net/batman-adv/trace.h b/net/batman-adv/trace.h new file mode 100644 index 000000000000..3acda26a30ca --- /dev/null +++ b/net/batman-adv/trace.h @@ -0,0 +1,78 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright (C) 2010-2018 B.A.T.M.A.N. contributors: + * + * Sven Eckelmann + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of version 2 of the GNU General Public + * License as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, but + * WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, see <http://www.gnu.org/licenses/>. + */ + +#if !defined(_NET_BATMAN_ADV_TRACE_H_) || defined(TRACE_HEADER_MULTI_READ) +#define _NET_BATMAN_ADV_TRACE_H_ + +#include "main.h" + +#include <linux/tracepoint.h> + +#undef TRACE_SYSTEM +#define TRACE_SYSTEM batadv + +/* provide dummy function when tracing is disabled */ +#if !defined(CONFIG_BATMAN_ADV_TRACING) + +#undef TRACE_EVENT +#define TRACE_EVENT(name, proto, ...) \ + static inline void trace_ ## name(proto) {} + +#endif /* CONFIG_BATMAN_ADV_TRACING */ + +#define BATADV_MAX_MSG_LEN 256 + +TRACE_EVENT(batadv_dbg, + + TP_PROTO(struct batadv_priv *bat_priv, + struct va_format *vaf), + + TP_ARGS(bat_priv, vaf), + + TP_STRUCT__entry( + __string(device, bat_priv->soft_iface->name) + __string(driver, KBUILD_MODNAME) + __dynamic_array(char, msg, BATADV_MAX_MSG_LEN) + ), + + TP_fast_assign( + __assign_str(device, bat_priv->soft_iface->name); + __assign_str(driver, KBUILD_MODNAME); + WARN_ON_ONCE(vsnprintf(__get_dynamic_array(msg), + BATADV_MAX_MSG_LEN, + vaf->fmt, + *vaf->va) >= BATADV_MAX_MSG_LEN); + ), + + TP_printk( + "%s %s %s", + __get_str(driver), + __get_str(device), + __get_str(msg) + ) +); + +#endif /* _NET_BATMAN_ADV_TRACE_H_ || TRACE_HEADER_MULTI_READ */ + +#undef TRACE_INCLUDE_PATH +#define TRACE_INCLUDE_PATH . +#undef TRACE_INCLUDE_FILE +#define TRACE_INCLUDE_FILE trace + +/* This part must be outside protection */ +#include <trace/define_trace.h> diff --git a/net/batman-adv/translation-table.c b/net/batman-adv/translation-table.c index 12a2b7d21376..d21624c44665 100644 --- a/net/batman-adv/translation-table.c +++ b/net/batman-adv/translation-table.c @@ -1613,6 +1613,8 @@ batadv_tt_global_orig_entry_add(struct batadv_tt_global_entry *tt_global, { struct batadv_tt_orig_list_entry *orig_entry; + spin_lock_bh(&tt_global->list_lock); + orig_entry = batadv_tt_global_orig_entry_find(tt_global, orig_node); if (orig_entry) { /* refresh the ttvn: the current value could be a bogus one that @@ -1635,11 +1637,9 @@ batadv_tt_global_orig_entry_add(struct batadv_tt_global_entry *tt_global, orig_entry->flags = flags; kref_init(&orig_entry->refcount); - spin_lock_bh(&tt_global->list_lock); kref_get(&orig_entry->refcount); hlist_add_head_rcu(&orig_entry->list, &tt_global->orig_list); - spin_unlock_bh(&tt_global->list_lock); atomic_inc(&tt_global->orig_list_count); sync_flags: @@ -1647,6 +1647,8 @@ sync_flags: out: if (orig_entry) batadv_tt_orig_list_entry_put(orig_entry); + + spin_unlock_bh(&tt_global->list_lock); } /** diff --git a/net/batman-adv/tvlv.c b/net/batman-adv/tvlv.c index a637458205d1..40e69c9346d2 100644 --- a/net/batman-adv/tvlv.c +++ b/net/batman-adv/tvlv.c @@ -529,15 +529,20 @@ void batadv_tvlv_handler_register(struct batadv_priv *bat_priv, { struct batadv_tvlv_handler *tvlv_handler; + spin_lock_bh(&bat_priv->tvlv.handler_list_lock); + tvlv_handler = batadv_tvlv_handler_get(bat_priv, type, version); if (tvlv_handler) { + spin_unlock_bh(&bat_priv->tvlv.handler_list_lock); batadv_tvlv_handler_put(tvlv_handler); return; } tvlv_handler = kzalloc(sizeof(*tvlv_handler), GFP_ATOMIC); - if (!tvlv_handler) + if (!tvlv_handler) { + spin_unlock_bh(&bat_priv->tvlv.handler_list_lock); return; + } tvlv_handler->ogm_handler = optr; tvlv_handler->unicast_handler = uptr; @@ -547,7 +552,6 @@ void batadv_tvlv_handler_register(struct batadv_priv *bat_priv, kref_init(&tvlv_handler->refcount); INIT_HLIST_NODE(&tvlv_handler->list); - spin_lock_bh(&bat_priv->tvlv.handler_list_lock); kref_get(&tvlv_handler->refcount); hlist_add_head_rcu(&tvlv_handler->list, &bat_priv->tvlv.handler_list); spin_unlock_bh(&bat_priv->tvlv.handler_list_lock); diff --git a/net/batman-adv/types.h b/net/batman-adv/types.h index 343d304851a5..45b5592de816 100644 --- a/net/batman-adv/types.h +++ b/net/batman-adv/types.h @@ -167,9 +167,6 @@ struct batadv_hard_iface { /** @list: list node for batadv_hardif_list */ struct list_head list; - /** @if_num: identificator of the interface */ - unsigned int if_num; - /** @if_status: status of the interface for batman-adv */ char if_status; @@ -233,6 +230,20 @@ struct batadv_hard_iface { }; /** + * struct batadv_orig_ifinfo - B.A.T.M.A.N. IV private orig_ifinfo members + */ +struct batadv_orig_ifinfo_bat_iv { + /** + * @bcast_own: bitfield which counts the number of our OGMs this + * orig_node rebroadcasted "back" to us (relative to last_real_seqno) + */ + DECLARE_BITMAP(bcast_own, BATADV_TQ_LOCAL_WINDOW_SIZE); + + /** @bcast_own_sum: sum of bcast_own */ + u8 bcast_own_sum; +}; + +/** * struct batadv_orig_ifinfo - originator info per outgoing interface */ struct batadv_orig_ifinfo { @@ -257,6 +268,9 @@ struct batadv_orig_ifinfo { /** @batman_seqno_reset: time when the batman seqno window was reset */ unsigned long batman_seqno_reset; + /** @bat_iv: B.A.T.M.A.N. IV private structure */ + struct batadv_orig_ifinfo_bat_iv bat_iv; + /** @refcount: number of contexts the object is used */ struct kref refcount; @@ -339,19 +353,10 @@ struct batadv_orig_node_vlan { */ struct batadv_orig_bat_iv { /** - * @bcast_own: set of bitfields (one per hard-interface) where each one - * counts the number of our OGMs this orig_node rebroadcasted "back" to - * us (relative to last_real_seqno). Every bitfield is - * BATADV_TQ_LOCAL_WINDOW_SIZE bits long. - */ - unsigned long *bcast_own; - - /** @bcast_own_sum: sum of bcast_own */ - u8 *bcast_own_sum; - - /** - * @ogm_cnt_lock: lock protecting bcast_own, bcast_own_sum, - * neigh_node->bat_iv.real_bits & neigh_node->bat_iv.real_packet_count + * @ogm_cnt_lock: lock protecting &batadv_orig_ifinfo_bat_iv.bcast_own, + * &batadv_orig_ifinfo_bat_iv.bcast_own_sum, + * &batadv_neigh_ifinfo_bat_iv.bat_iv.real_bits and + * &batadv_neigh_ifinfo_bat_iv.real_packet_count */ spinlock_t ogm_cnt_lock; }; @@ -1597,9 +1602,6 @@ struct batadv_priv { /** @batman_queue_left: number of remaining OGM packet slots */ atomic_t batman_queue_left; - /** @num_ifaces: number of interfaces assigned to this mesh interface */ - unsigned int num_ifaces; - /** @mesh_obj: kobject for sysfs mesh subdirectory */ struct kobject *mesh_obj; @@ -2179,28 +2181,6 @@ struct batadv_algo_neigh_ops { * struct batadv_algo_orig_ops - mesh algorithm callbacks (originator specific) */ struct batadv_algo_orig_ops { - /** - * @free: free the resources allocated by the routing algorithm for an - * orig_node object (optional) - */ - void (*free)(struct batadv_orig_node *orig_node); - - /** - * @add_if: ask the routing algorithm to apply the needed changes to the - * orig_node due to a new hard-interface being added into the mesh - * (optional) - */ - int (*add_if)(struct batadv_orig_node *orig_node, - unsigned int max_if_num); - - /** - * @del_if: ask the routing algorithm to apply the needed changes to the - * orig_node due to an hard-interface being removed from the mesh - * (optional) - */ - int (*del_if)(struct batadv_orig_node *orig_node, - unsigned int max_if_num, unsigned int del_if_num); - #ifdef CONFIG_BATMAN_ADV_DEBUGFS /** @print: print the originator table (optional) */ void (*print)(struct batadv_priv *priv, struct seq_file *seq, diff --git a/net/bluetooth/smp.c b/net/bluetooth/smp.c index ae91e2d40056..3a7b0773536b 100644 --- a/net/bluetooth/smp.c +++ b/net/bluetooth/smp.c @@ -83,6 +83,7 @@ enum { struct smp_dev { /* Secure Connections OOB data */ + bool local_oob; u8 local_pk[64]; u8 local_rand[16]; bool debug_key; @@ -599,6 +600,8 @@ int smp_generate_oob(struct hci_dev *hdev, u8 hash[16], u8 rand[16]) memcpy(rand, smp->local_rand, 16); + smp->local_oob = true; + return 0; } @@ -1785,7 +1788,7 @@ static u8 smp_cmd_pairing_req(struct l2cap_conn *conn, struct sk_buff *skb) * successfully received our local OOB data - therefore set the * flag to indicate that local OOB is in use. */ - if (req->oob_flag == SMP_OOB_PRESENT) + if (req->oob_flag == SMP_OOB_PRESENT && SMP_DEV(hdev)->local_oob) set_bit(SMP_FLAG_LOCAL_OOB, &smp->flags); /* SMP over BR/EDR requires special treatment */ @@ -1967,7 +1970,7 @@ static u8 smp_cmd_pairing_rsp(struct l2cap_conn *conn, struct sk_buff *skb) * successfully received our local OOB data - therefore set the * flag to indicate that local OOB is in use. */ - if (rsp->oob_flag == SMP_OOB_PRESENT) + if (rsp->oob_flag == SMP_OOB_PRESENT && SMP_DEV(hdev)->local_oob) set_bit(SMP_FLAG_LOCAL_OOB, &smp->flags); smp->prsp[0] = SMP_CMD_PAIRING_RSP; @@ -2697,7 +2700,13 @@ static int smp_cmd_public_key(struct l2cap_conn *conn, struct sk_buff *skb) * key was set/generated. */ if (test_bit(SMP_FLAG_LOCAL_OOB, &smp->flags)) { - struct smp_dev *smp_dev = chan->data; + struct l2cap_chan *hchan = hdev->smp_data; + struct smp_dev *smp_dev; + + if (!hchan || !hchan->data) + return SMP_UNSPECIFIED; + + smp_dev = hchan->data; tfm_ecdh = smp_dev->tfm_ecdh; } else { @@ -3230,6 +3239,7 @@ static struct l2cap_chan *smp_add_cid(struct hci_dev *hdev, u16 cid) return ERR_CAST(tfm_ecdh); } + smp->local_oob = false; smp->tfm_aes = tfm_aes; smp->tfm_cmac = tfm_cmac; smp->tfm_ecdh = tfm_ecdh; diff --git a/net/bridge/br_fdb.c b/net/bridge/br_fdb.c index 502f66349530..a56ed7f2a3a3 100644 --- a/net/bridge/br_fdb.c +++ b/net/bridge/br_fdb.c @@ -584,7 +584,7 @@ void br_fdb_update(struct net_bridge *br, struct net_bridge_port *source, unsigned long now = jiffies; /* fastpath: update of existing entry */ - if (unlikely(source != fdb->dst)) { + if (unlikely(source != fdb->dst && !fdb->is_sticky)) { fdb->dst = source; fdb_modified = true; /* Take over HW learned entry */ @@ -656,6 +656,8 @@ static int fdb_fill_info(struct sk_buff *skb, const struct net_bridge *br, ndm->ndm_flags |= NTF_OFFLOADED; if (fdb->added_by_external_learn) ndm->ndm_flags |= NTF_EXT_LEARNED; + if (fdb->is_sticky) + ndm->ndm_flags |= NTF_STICKY; if (nla_put(skb, NDA_LLADDR, ETH_ALEN, &fdb->key.addr)) goto nla_put_failure; @@ -772,8 +774,10 @@ skip: /* Update (create or replace) forwarding database entry */ static int fdb_add_entry(struct net_bridge *br, struct net_bridge_port *source, - const __u8 *addr, __u16 state, __u16 flags, __u16 vid) + const u8 *addr, u16 state, u16 flags, u16 vid, + u8 ndm_flags) { + u8 is_sticky = !!(ndm_flags & NTF_STICKY); struct net_bridge_fdb_entry *fdb; bool modified = false; @@ -789,6 +793,9 @@ static int fdb_add_entry(struct net_bridge *br, struct net_bridge_port *source, return -EINVAL; } + if (is_sticky && (state & NUD_PERMANENT)) + return -EINVAL; + fdb = br_fdb_find(br, addr, vid); if (fdb == NULL) { if (!(flags & NLM_F_CREATE)) @@ -832,6 +839,12 @@ static int fdb_add_entry(struct net_bridge *br, struct net_bridge_port *source, modified = true; } + + if (is_sticky != fdb->is_sticky) { + fdb->is_sticky = is_sticky; + modified = true; + } + fdb->added_by_user = 1; fdb->used = jiffies; @@ -865,7 +878,7 @@ static int __br_fdb_add(struct ndmsg *ndm, struct net_bridge *br, } else { spin_lock_bh(&br->hash_lock); err = fdb_add_entry(br, p, addr, ndm->ndm_state, - nlh_flags, vid); + nlh_flags, vid, ndm->ndm_flags); spin_unlock_bh(&br->hash_lock); } diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h index 11ed2029985f..d21035a17f4c 100644 --- a/net/bridge/br_private.h +++ b/net/bridge/br_private.h @@ -181,6 +181,7 @@ struct net_bridge_fdb_entry { struct hlist_node fdb_node; unsigned char is_local:1, is_static:1, + is_sticky:1, added_by_user:1, added_by_external_learn:1, offloaded:1; diff --git a/net/caif/cfrfml.c b/net/caif/cfrfml.c index b82440e1fcb4..a931a71ef6df 100644 --- a/net/caif/cfrfml.c +++ b/net/caif/cfrfml.c @@ -264,9 +264,6 @@ static int cfrfml_transmit(struct cflayer *layr, struct cfpkt *pkt) frontpkt = rearpkt; rearpkt = NULL; - err = -ENOMEM; - if (frontpkt == NULL) - goto out; err = -EPROTO; if (cfpkt_add_head(frontpkt, head, 6) < 0) goto out; diff --git a/net/core/dev.c b/net/core/dev.c index ca78dc5a79a3..0b2d777e5b9e 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -3231,7 +3231,7 @@ struct sk_buff *dev_hard_start_xmit(struct sk_buff *first, struct net_device *de while (skb) { struct sk_buff *next = skb->next; - skb->next = NULL; + skb_mark_not_on_list(skb); rc = xmit_one(skb, dev, txq, next != NULL); if (unlikely(!dev_xmit_complete(rc))) { skb->next = next; @@ -3331,7 +3331,7 @@ struct sk_buff *validate_xmit_skb_list(struct sk_buff *skb, struct net_device *d for (; skb != NULL; skb = next) { next = skb->next; - skb->next = NULL; + skb_mark_not_on_list(skb); /* in case skb wont be segmented, point to itself */ skb->prev = skb; @@ -5295,8 +5295,7 @@ static void __napi_gro_flush_chain(struct napi_struct *napi, u32 index, list_for_each_entry_safe_reverse(skb, p, head, list) { if (flush_old && NAPI_GRO_CB(skb)->age == jiffies) return; - list_del(&skb->list); - skb->next = NULL; + skb_list_del_init(skb); napi_gro_complete(skb); napi->gro_hash[index].count--; } @@ -5481,8 +5480,7 @@ static enum gro_result dev_gro_receive(struct napi_struct *napi, struct sk_buff ret = NAPI_GRO_CB(skb)->free ? GRO_MERGED_FREE : GRO_MERGED; if (pp) { - list_del(&pp->list); - pp->next = NULL; + skb_list_del_init(pp); napi_gro_complete(pp); napi->gro_hash[hash].count--; } diff --git a/net/core/devlink.c b/net/core/devlink.c index 65fc366a78a4..8c0ed225e280 100644 --- a/net/core/devlink.c +++ b/net/core/devlink.c @@ -2592,7 +2592,7 @@ send_done: if (!nlh) { err = devlink_dpipe_send_and_alloc_skb(&skb, info); if (err) - goto err_skb_send_alloc; + return err; goto send_done; } return genlmsg_reply(skb, info); @@ -2600,7 +2600,6 @@ send_done: nla_put_failure: err = -EMSGSIZE; err_resource_put: -err_skb_send_alloc: nlmsg_free(skb); return err; } diff --git a/net/core/ethtool.c b/net/core/ethtool.c index 9d4e56d97080..96afc55aa61e 100644 --- a/net/core/ethtool.c +++ b/net/core/ethtool.c @@ -2536,6 +2536,7 @@ int dev_ethtool(struct net *net, struct ifreq *ifr) case ETHTOOL_GPHYSTATS: case ETHTOOL_GTSO: case ETHTOOL_GPERMADDR: + case ETHTOOL_GUFO: case ETHTOOL_GGSO: case ETHTOOL_GGRO: case ETHTOOL_GFLAGS: diff --git a/net/core/filter.c b/net/core/filter.c index 9cc76f134ddb..72db8afb7cb6 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -2344,7 +2344,8 @@ BPF_CALL_4(bpf_msg_pull_data, if (unlikely(bytes_sg_total > copy)) return -EINVAL; - page = alloc_pages(__GFP_NOWARN | GFP_ATOMIC, get_order(copy)); + page = alloc_pages(__GFP_NOWARN | GFP_ATOMIC | __GFP_COMP, + get_order(copy)); if (unlikely(!page)) return -ENOMEM; p = page_address(page); diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c index 738c7562e1e0..676f3ad629f9 100644 --- a/net/core/flow_dissector.c +++ b/net/core/flow_dissector.c @@ -423,8 +423,8 @@ __skb_flow_dissect_gre(const struct sk_buff *skb, offset += sizeof(struct gre_base_hdr); if (hdr->flags & GRE_CSUM) - offset += sizeof(((struct gre_full_hdr *) 0)->csum) + - sizeof(((struct gre_full_hdr *) 0)->reserved1); + offset += FIELD_SIZEOF(struct gre_full_hdr, csum) + + FIELD_SIZEOF(struct gre_full_hdr, reserved1); if (hdr->flags & GRE_KEY) { const __be32 *keyid; @@ -446,11 +446,11 @@ __skb_flow_dissect_gre(const struct sk_buff *skb, else key_keyid->keyid = *keyid & GRE_PPTP_KEY_MASK; } - offset += sizeof(((struct gre_full_hdr *) 0)->key); + offset += FIELD_SIZEOF(struct gre_full_hdr, key); } if (hdr->flags & GRE_SEQ) - offset += sizeof(((struct pptp_gre_header *) 0)->seq); + offset += FIELD_SIZEOF(struct pptp_gre_header, seq); if (gre_ver == 0) { if (*p_proto == htons(ETH_P_TEB)) { @@ -477,7 +477,7 @@ __skb_flow_dissect_gre(const struct sk_buff *skb, u8 *ppp_hdr; if (hdr->flags & GRE_ACK) - offset += sizeof(((struct pptp_gre_header *) 0)->ack); + offset += FIELD_SIZEOF(struct pptp_gre_header, ack); ppp_hdr = __skb_header_pointer(skb, *p_nhoff + offset, sizeof(_ppp_hdr), diff --git a/net/core/gen_stats.c b/net/core/gen_stats.c index 188d693cb251..65a2e820364f 100644 --- a/net/core/gen_stats.c +++ b/net/core/gen_stats.c @@ -162,30 +162,18 @@ __gnet_stats_copy_basic(const seqcount_t *running, } EXPORT_SYMBOL(__gnet_stats_copy_basic); -/** - * gnet_stats_copy_basic - copy basic statistics into statistic TLV - * @running: seqcount_t pointer - * @d: dumping handle - * @cpu: copy statistic per cpu - * @b: basic statistics - * - * Appends the basic statistics to the top level TLV created by - * gnet_stats_start_copy(). - * - * Returns 0 on success or -1 with the statistic lock released - * if the room in the socket buffer was not sufficient. - */ int -gnet_stats_copy_basic(const seqcount_t *running, - struct gnet_dump *d, - struct gnet_stats_basic_cpu __percpu *cpu, - struct gnet_stats_basic_packed *b) +___gnet_stats_copy_basic(const seqcount_t *running, + struct gnet_dump *d, + struct gnet_stats_basic_cpu __percpu *cpu, + struct gnet_stats_basic_packed *b, + int type) { struct gnet_stats_basic_packed bstats = {0}; __gnet_stats_copy_basic(running, &bstats, cpu, b); - if (d->compat_tc_stats) { + if (d->compat_tc_stats && type == TCA_STATS_BASIC) { d->tc_stats.bytes = bstats.bytes; d->tc_stats.packets = bstats.packets; } @@ -196,14 +184,61 @@ gnet_stats_copy_basic(const seqcount_t *running, memset(&sb, 0, sizeof(sb)); sb.bytes = bstats.bytes; sb.packets = bstats.packets; - return gnet_stats_copy(d, TCA_STATS_BASIC, &sb, sizeof(sb), + return gnet_stats_copy(d, type, &sb, sizeof(sb), TCA_STATS_PAD); } return 0; } + +/** + * gnet_stats_copy_basic - copy basic statistics into statistic TLV + * @running: seqcount_t pointer + * @d: dumping handle + * @cpu: copy statistic per cpu + * @b: basic statistics + * + * Appends the basic statistics to the top level TLV created by + * gnet_stats_start_copy(). + * + * Returns 0 on success or -1 with the statistic lock released + * if the room in the socket buffer was not sufficient. + */ +int +gnet_stats_copy_basic(const seqcount_t *running, + struct gnet_dump *d, + struct gnet_stats_basic_cpu __percpu *cpu, + struct gnet_stats_basic_packed *b) +{ + return ___gnet_stats_copy_basic(running, d, cpu, b, + TCA_STATS_BASIC); +} EXPORT_SYMBOL(gnet_stats_copy_basic); /** + * gnet_stats_copy_basic_hw - copy basic hw statistics into statistic TLV + * @running: seqcount_t pointer + * @d: dumping handle + * @cpu: copy statistic per cpu + * @b: basic statistics + * + * Appends the basic statistics to the top level TLV created by + * gnet_stats_start_copy(). + * + * Returns 0 on success or -1 with the statistic lock released + * if the room in the socket buffer was not sufficient. + */ +int +gnet_stats_copy_basic_hw(const seqcount_t *running, + struct gnet_dump *d, + struct gnet_stats_basic_cpu __percpu *cpu, + struct gnet_stats_basic_packed *b) +{ + return ___gnet_stats_copy_basic(running, d, cpu, b, + TCA_STATS_BASIC_HW); +} +EXPORT_SYMBOL(gnet_stats_copy_basic_hw); + +/** * gnet_stats_copy_rate_est - copy rate estimator statistics into statistics TLV * @d: dumping handle * @rate_est: rate estimator diff --git a/net/core/link_watch.c b/net/core/link_watch.c index e38e641e98d5..7f51efb2b3ab 100644 --- a/net/core/link_watch.c +++ b/net/core/link_watch.c @@ -155,7 +155,7 @@ static void linkwatch_do_dev(struct net_device *dev) clear_bit(__LINK_STATE_LINKWATCH_PENDING, &dev->state); rfc2863_policy(dev); - if (dev->flags & IFF_UP) { + if (dev->flags & IFF_UP && netif_device_present(dev)) { if (netif_carrier_ok(dev)) dev_activate(dev); else diff --git a/net/core/neighbour.c b/net/core/neighbour.c index aa19d86937af..20e0d3308148 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -1180,6 +1180,12 @@ int neigh_update(struct neighbour *neigh, const u8 *lladdr, u8 new, lladdr = neigh->ha; } + /* Update confirmed timestamp for neighbour entry after we + * received ARP packet even if it doesn't change IP to MAC binding. + */ + if (new & NUD_CONNECTED) + neigh->confirmed = jiffies; + /* If entry was valid and address is not changed, do not change entry state, if new one is STALE. */ @@ -1201,15 +1207,12 @@ int neigh_update(struct neighbour *neigh, const u8 *lladdr, u8 new, } } - /* Update timestamps only once we know we will make a change to the + /* Update timestamp only once we know we will make a change to the * neighbour entry. Otherwise we risk to move the locktime window with * noop updates and ignore relevant ARP updates. */ - if (new != old || lladdr != neigh->ha) { - if (new & NUD_CONNECTED) - neigh->confirmed = jiffies; + if (new != old || lladdr != neigh->ha) neigh->updated = jiffies; - } if (new != old) { neigh_del_timer(neigh); @@ -1277,11 +1280,8 @@ int neigh_update(struct neighbour *neigh, const u8 *lladdr, u8 new, neigh->arp_queue_len_bytes = 0; } out: - if (update_isrouter) { - neigh->flags = (flags & NEIGH_UPDATE_F_ISROUTER) ? - (neigh->flags | NTF_ROUTER) : - (neigh->flags & ~NTF_ROUTER); - } + if (update_isrouter) + neigh_update_is_router(neigh, flags, ¬ify); write_unlock_bh(&neigh->lock); if (notify) @@ -1709,7 +1709,8 @@ out: static int neigh_add(struct sk_buff *skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack) { - int flags = NEIGH_UPDATE_F_ADMIN | NEIGH_UPDATE_F_OVERRIDE; + int flags = NEIGH_UPDATE_F_ADMIN | NEIGH_UPDATE_F_OVERRIDE | + NEIGH_UPDATE_F_OVERRIDE_ISROUTER; struct net *net = sock_net(skb->sk); struct ndmsg *ndm; struct nlattr *tb[NDA_MAX+1]; @@ -1784,12 +1785,16 @@ static int neigh_add(struct sk_buff *skb, struct nlmsghdr *nlh, } if (!(nlh->nlmsg_flags & NLM_F_REPLACE)) - flags &= ~NEIGH_UPDATE_F_OVERRIDE; + flags &= ~(NEIGH_UPDATE_F_OVERRIDE | + NEIGH_UPDATE_F_OVERRIDE_ISROUTER); } if (ndm->ndm_flags & NTF_EXT_LEARNED) flags |= NEIGH_UPDATE_F_EXT_LEARNED; + if (ndm->ndm_flags & NTF_ROUTER) + flags |= NEIGH_UPDATE_F_ISROUTER; + if (ndm->ndm_flags & NTF_USE) { neigh_event_send(neigh, NULL); err = 0; diff --git a/net/core/netpoll.c b/net/core/netpoll.c index 57557a6a950c..3219a2932463 100644 --- a/net/core/netpoll.c +++ b/net/core/netpoll.c @@ -187,16 +187,16 @@ static void poll_napi(struct net_device *dev) } } -static void netpoll_poll_dev(struct net_device *dev) +void netpoll_poll_dev(struct net_device *dev) { - const struct net_device_ops *ops; struct netpoll_info *ni = rcu_dereference_bh(dev->npinfo); + const struct net_device_ops *ops; /* Don't do any rx activity if the dev_lock mutex is held * the dev_open/close paths use this to block netpoll activity * while changing device state */ - if (down_trylock(&ni->dev_lock)) + if (!ni || down_trylock(&ni->dev_lock)) return; if (!netif_running(dev)) { @@ -205,13 +205,8 @@ static void netpoll_poll_dev(struct net_device *dev) } ops = dev->netdev_ops; - if (!ops->ndo_poll_controller) { - up(&ni->dev_lock); - return; - } - - /* Process pending work on NIC */ - ops->ndo_poll_controller(dev); + if (ops->ndo_poll_controller) + ops->ndo_poll_controller(dev); poll_napi(dev); @@ -219,6 +214,7 @@ static void netpoll_poll_dev(struct net_device *dev) zap_completion_queue(); } +EXPORT_SYMBOL(netpoll_poll_dev); void netpoll_poll_disable(struct net_device *dev) { @@ -613,8 +609,7 @@ int __netpoll_setup(struct netpoll *np, struct net_device *ndev) strlcpy(np->dev_name, ndev->name, IFNAMSIZ); INIT_WORK(&np->cleanup_work, netpoll_async_cleanup); - if ((ndev->priv_flags & IFF_DISABLE_NETPOLL) || - !ndev->netdev_ops->ndo_poll_controller) { + if (ndev->priv_flags & IFF_DISABLE_NETPOLL) { np_err(np, "%s doesn't support polling, aborting\n", np->dev_name); err = -ENOTSUPP; diff --git a/net/core/pktgen.c b/net/core/pktgen.c index 7f6938405fa1..6ac919847ce6 100644 --- a/net/core/pktgen.c +++ b/net/core/pktgen.c @@ -3426,7 +3426,7 @@ xmit_more: net_info_ratelimited("%s xmit error: %d\n", pkt_dev->odevname, ret); pkt_dev->errors++; - /* fallthru */ + /* fall through */ case NETDEV_TX_BUSY: /* Retry it next time */ refcount_dec(&(pkt_dev->skb->users)); diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 60c928894a78..35162e1b06ad 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -130,6 +130,12 @@ int rtnl_is_locked(void) } EXPORT_SYMBOL(rtnl_is_locked); +bool refcount_dec_and_rtnl_lock(refcount_t *r) +{ + return refcount_dec_and_mutex_lock(r, &rtnl_mutex); +} +EXPORT_SYMBOL(refcount_dec_and_rtnl_lock); + #ifdef CONFIG_PROVE_LOCKING bool lockdep_rtnl_is_held(void) { @@ -1016,7 +1022,7 @@ static noinline size_t if_nlmsg_size(const struct net_device *dev, + nla_total_size(4) /* IFLA_NEW_NETNSID */ + nla_total_size(4) /* IFLA_NEW_IFINDEX */ + nla_total_size(1) /* IFLA_PROTO_DOWN */ - + nla_total_size(4) /* IFLA_IF_NETNSID */ + + nla_total_size(4) /* IFLA_TARGET_NETNSID */ + nla_total_size(4) /* IFLA_CARRIER_UP_COUNT */ + nla_total_size(4) /* IFLA_CARRIER_DOWN_COUNT */ + nla_total_size(4) /* IFLA_MIN_MTU */ @@ -1598,7 +1604,7 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, ifm->ifi_flags = dev_get_flags(dev); ifm->ifi_change = change; - if (tgt_netnsid >= 0 && nla_put_s32(skb, IFLA_IF_NETNSID, tgt_netnsid)) + if (tgt_netnsid >= 0 && nla_put_s32(skb, IFLA_TARGET_NETNSID, tgt_netnsid)) goto nla_put_failure; if (nla_put_string(skb, IFLA_IFNAME, dev->name) || @@ -1737,7 +1743,7 @@ static const struct nla_policy ifla_policy[IFLA_MAX+1] = { [IFLA_XDP] = { .type = NLA_NESTED }, [IFLA_EVENT] = { .type = NLA_U32 }, [IFLA_GROUP] = { .type = NLA_U32 }, - [IFLA_IF_NETNSID] = { .type = NLA_S32 }, + [IFLA_TARGET_NETNSID] = { .type = NLA_S32 }, [IFLA_CARRIER_UP_COUNT] = { .type = NLA_U32 }, [IFLA_CARRIER_DOWN_COUNT] = { .type = NLA_U32 }, [IFLA_MIN_MTU] = { .type = NLA_U32 }, @@ -1845,7 +1851,15 @@ static bool link_dump_filtered(struct net_device *dev, return false; } -static struct net *get_target_net(struct sock *sk, int netnsid) +/** + * rtnl_get_net_ns_capable - Get netns if sufficiently privileged. + * @sk: netlink socket + * @netnsid: network namespace identifier + * + * Returns the network namespace identified by netnsid on success or an error + * pointer on failure. + */ +struct net *rtnl_get_net_ns_capable(struct sock *sk, int netnsid) { struct net *net; @@ -1862,6 +1876,7 @@ static struct net *get_target_net(struct sock *sk, int netnsid) } return net; } +EXPORT_SYMBOL_GPL(rtnl_get_net_ns_capable); static int rtnl_dump_ifinfo(struct sk_buff *skb, struct netlink_callback *cb) { @@ -1895,9 +1910,9 @@ static int rtnl_dump_ifinfo(struct sk_buff *skb, struct netlink_callback *cb) if (nlmsg_parse(cb->nlh, hdrlen, tb, IFLA_MAX, ifla_policy, NULL) >= 0) { - if (tb[IFLA_IF_NETNSID]) { - netnsid = nla_get_s32(tb[IFLA_IF_NETNSID]); - tgt_net = get_target_net(skb->sk, netnsid); + if (tb[IFLA_TARGET_NETNSID]) { + netnsid = nla_get_s32(tb[IFLA_TARGET_NETNSID]); + tgt_net = rtnl_get_net_ns_capable(skb->sk, netnsid); if (IS_ERR(tgt_net)) { tgt_net = net; netnsid = -1; @@ -1984,7 +1999,7 @@ EXPORT_SYMBOL(rtnl_link_get_net); * * 1. IFLA_NET_NS_PID * 2. IFLA_NET_NS_FD - * 3. IFLA_IF_NETNSID + * 3. IFLA_TARGET_NETNSID */ static struct net *rtnl_link_get_net_by_nlattr(struct net *src_net, struct nlattr *tb[]) @@ -1994,10 +2009,10 @@ static struct net *rtnl_link_get_net_by_nlattr(struct net *src_net, if (tb[IFLA_NET_NS_PID] || tb[IFLA_NET_NS_FD]) return rtnl_link_get_net(src_net, tb); - if (!tb[IFLA_IF_NETNSID]) + if (!tb[IFLA_TARGET_NETNSID]) return get_net(src_net); - net = get_net_ns_by_id(src_net, nla_get_u32(tb[IFLA_IF_NETNSID])); + net = get_net_ns_by_id(src_net, nla_get_u32(tb[IFLA_TARGET_NETNSID])); if (!net) return ERR_PTR(-EINVAL); @@ -2038,13 +2053,13 @@ static int rtnl_ensure_unique_netns(struct nlattr *tb[], return -EOPNOTSUPP; } - if (tb[IFLA_IF_NETNSID] && (tb[IFLA_NET_NS_PID] || tb[IFLA_NET_NS_FD])) + if (tb[IFLA_TARGET_NETNSID] && (tb[IFLA_NET_NS_PID] || tb[IFLA_NET_NS_FD])) goto invalid_attr; - if (tb[IFLA_NET_NS_PID] && (tb[IFLA_IF_NETNSID] || tb[IFLA_NET_NS_FD])) + if (tb[IFLA_NET_NS_PID] && (tb[IFLA_TARGET_NETNSID] || tb[IFLA_NET_NS_FD])) goto invalid_attr; - if (tb[IFLA_NET_NS_FD] && (tb[IFLA_IF_NETNSID] || tb[IFLA_NET_NS_PID])) + if (tb[IFLA_NET_NS_FD] && (tb[IFLA_TARGET_NETNSID] || tb[IFLA_NET_NS_PID])) goto invalid_attr; return 0; @@ -2320,7 +2335,7 @@ static int do_setlink(const struct sk_buff *skb, if (err < 0) return err; - if (tb[IFLA_NET_NS_PID] || tb[IFLA_NET_NS_FD] || tb[IFLA_IF_NETNSID]) { + if (tb[IFLA_NET_NS_PID] || tb[IFLA_NET_NS_FD] || tb[IFLA_TARGET_NETNSID]) { struct net *net = rtnl_link_get_net_capable(skb, dev_net(dev), tb, CAP_NET_ADMIN); if (IS_ERR(net)) { @@ -2763,9 +2778,9 @@ static int rtnl_dellink(struct sk_buff *skb, struct nlmsghdr *nlh, if (tb[IFLA_IFNAME]) nla_strlcpy(ifname, tb[IFLA_IFNAME], IFNAMSIZ); - if (tb[IFLA_IF_NETNSID]) { - netnsid = nla_get_s32(tb[IFLA_IF_NETNSID]); - tgt_net = get_target_net(NETLINK_CB(skb).sk, netnsid); + if (tb[IFLA_TARGET_NETNSID]) { + netnsid = nla_get_s32(tb[IFLA_TARGET_NETNSID]); + tgt_net = rtnl_get_net_ns_capable(NETLINK_CB(skb).sk, netnsid); if (IS_ERR(tgt_net)) return PTR_ERR(tgt_net); } @@ -2810,7 +2825,7 @@ int rtnl_configure_link(struct net_device *dev, const struct ifinfomsg *ifm) } if (dev->rtnl_link_state == RTNL_LINK_INITIALIZED) { - __dev_notify_flags(dev, old_flags, 0U); + __dev_notify_flags(dev, old_flags, (old_flags ^ dev->flags)); } else { dev->rtnl_link_state = RTNL_LINK_INITIALIZED; __dev_notify_flags(dev, old_flags, ~0U); @@ -3173,9 +3188,9 @@ static int rtnl_getlink(struct sk_buff *skb, struct nlmsghdr *nlh, if (err < 0) return err; - if (tb[IFLA_IF_NETNSID]) { - netnsid = nla_get_s32(tb[IFLA_IF_NETNSID]); - tgt_net = get_target_net(NETLINK_CB(skb).sk, netnsid); + if (tb[IFLA_TARGET_NETNSID]) { + netnsid = nla_get_s32(tb[IFLA_TARGET_NETNSID]); + tgt_net = rtnl_get_net_ns_capable(NETLINK_CB(skb).sk, netnsid); if (IS_ERR(tgt_net)) return PTR_ERR(tgt_net); } @@ -3260,13 +3275,13 @@ static int rtnl_dump_all(struct sk_buff *skb, struct netlink_callback *cb) { int idx; int s_idx = cb->family; + int type = cb->nlh->nlmsg_type - RTM_BASE; if (s_idx == 0) s_idx = 1; for (idx = 1; idx <= RTNL_FAMILY_MAX; idx++) { struct rtnl_link **tab; - int type = cb->nlh->nlmsg_type-RTM_BASE; struct rtnl_link *link; rtnl_dumpit_func dumpit; diff --git a/net/core/skbuff.c b/net/core/skbuff.c index c996c09d095f..b2c807f67aba 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -939,9 +939,6 @@ struct ubuf_info *sock_zerocopy_alloc(struct sock *sk, size_t size) WARN_ON_ONCE(!in_task()); - if (!sock_flag(sk, SOCK_ZEROCOPY)) - return NULL; - skb = sock_omalloc(sk, 0, GFP_KERNEL); if (!skb) return NULL; diff --git a/net/core/sock.c b/net/core/sock.c index 3730eb855095..8537b6ca72c5 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -2332,7 +2332,7 @@ static void __release_sock(struct sock *sk) next = skb->next; prefetch(next); WARN_ON_ONCE(skb_dst_is_noref(skb)); - skb->next = NULL; + skb_mark_not_on_list(skb); sk_backlog_rcv(sk, skb); cond_resched(); diff --git a/net/decnet/dn_dev.c b/net/decnet/dn_dev.c index bfd43e8f2c06..d0b3e69c6b39 100644 --- a/net/decnet/dn_dev.c +++ b/net/decnet/dn_dev.c @@ -1363,7 +1363,7 @@ static int dn_dev_seq_show(struct seq_file *seq, void *v) seq_printf(seq, "%-8s %1s %04u %04u %04lu %04lu" " %04hu %03d %02x %-10s %-7s %-7s\n", - dev->name ? dev->name : "???", + dev->name, dn_type2asc(dn_db->parms.mode), 0, 0, dn_db->t3, dn_db->parms.t3, diff --git a/net/dsa/Kconfig b/net/dsa/Kconfig index 4183e4ba27a5..48c41918fb35 100644 --- a/net/dsa/Kconfig +++ b/net/dsa/Kconfig @@ -38,6 +38,9 @@ config NET_DSA_TAG_DSA config NET_DSA_TAG_EDSA bool +config NET_DSA_TAG_GSWIP + bool + config NET_DSA_TAG_KSZ bool diff --git a/net/dsa/Makefile b/net/dsa/Makefile index 9e4d3536f977..6e721f7a2947 100644 --- a/net/dsa/Makefile +++ b/net/dsa/Makefile @@ -9,6 +9,7 @@ dsa_core-$(CONFIG_NET_DSA_TAG_BRCM) += tag_brcm.o dsa_core-$(CONFIG_NET_DSA_TAG_BRCM_PREPEND) += tag_brcm.o dsa_core-$(CONFIG_NET_DSA_TAG_DSA) += tag_dsa.o dsa_core-$(CONFIG_NET_DSA_TAG_EDSA) += tag_edsa.o +dsa_core-$(CONFIG_NET_DSA_TAG_GSWIP) += tag_gswip.o dsa_core-$(CONFIG_NET_DSA_TAG_KSZ) += tag_ksz.o dsa_core-$(CONFIG_NET_DSA_TAG_LAN9303) += tag_lan9303.o dsa_core-$(CONFIG_NET_DSA_TAG_MTK) += tag_mtk.o diff --git a/net/dsa/dsa.c b/net/dsa/dsa.c index 9f3209ff7ffd..a69c1790bbfc 100644 --- a/net/dsa/dsa.c +++ b/net/dsa/dsa.c @@ -52,6 +52,9 @@ const struct dsa_device_ops *dsa_device_ops[DSA_TAG_LAST] = { #ifdef CONFIG_NET_DSA_TAG_EDSA [DSA_TAG_PROTO_EDSA] = &edsa_netdev_ops, #endif +#ifdef CONFIG_NET_DSA_TAG_GSWIP + [DSA_TAG_PROTO_GSWIP] = &gswip_netdev_ops, +#endif #ifdef CONFIG_NET_DSA_TAG_KSZ [DSA_TAG_PROTO_KSZ] = &ksz_netdev_ops, #endif @@ -70,6 +73,52 @@ const struct dsa_device_ops *dsa_device_ops[DSA_TAG_LAST] = { [DSA_TAG_PROTO_NONE] = &none_ops, }; +const char *dsa_tag_protocol_to_str(const struct dsa_device_ops *ops) +{ + const char *protocol_name[DSA_TAG_LAST] = { +#ifdef CONFIG_NET_DSA_TAG_BRCM + [DSA_TAG_PROTO_BRCM] = "brcm", +#endif +#ifdef CONFIG_NET_DSA_TAG_BRCM_PREPEND + [DSA_TAG_PROTO_BRCM_PREPEND] = "brcm-prepend", +#endif +#ifdef CONFIG_NET_DSA_TAG_DSA + [DSA_TAG_PROTO_DSA] = "dsa", +#endif +#ifdef CONFIG_NET_DSA_TAG_EDSA + [DSA_TAG_PROTO_EDSA] = "edsa", +#endif +#ifdef CONFIG_NET_DSA_TAG_GSWIP + [DSA_TAG_PROTO_GSWIP] = "gswip", +#endif +#ifdef CONFIG_NET_DSA_TAG_KSZ + [DSA_TAG_PROTO_KSZ] = "ksz", +#endif +#ifdef CONFIG_NET_DSA_TAG_LAN9303 + [DSA_TAG_PROTO_LAN9303] = "lan9303", +#endif +#ifdef CONFIG_NET_DSA_TAG_MTK + [DSA_TAG_PROTO_MTK] = "mtk", +#endif +#ifdef CONFIG_NET_DSA_TAG_QCA + [DSA_TAG_PROTO_QCA] = "qca", +#endif +#ifdef CONFIG_NET_DSA_TAG_TRAILER + [DSA_TAG_PROTO_TRAILER] = "trailer", +#endif + [DSA_TAG_PROTO_NONE] = "none", + }; + unsigned int i; + + BUILD_BUG_ON(ARRAY_SIZE(protocol_name) != DSA_TAG_LAST); + + for (i = 0; i < ARRAY_SIZE(dsa_device_ops); i++) + if (ops == dsa_device_ops[i]) + return protocol_name[i]; + + return protocol_name[DSA_TAG_PROTO_NONE]; +}; + const struct dsa_device_ops *dsa_resolve_tag_protocol(int tag_protocol) { const struct dsa_device_ops *ops; diff --git a/net/dsa/dsa_priv.h b/net/dsa/dsa_priv.h index 3964c6f7a7c0..9e4fd04ab53c 100644 --- a/net/dsa/dsa_priv.h +++ b/net/dsa/dsa_priv.h @@ -86,6 +86,7 @@ struct dsa_slave_priv { /* dsa.c */ const struct dsa_device_ops *dsa_resolve_tag_protocol(int tag_protocol); bool dsa_schedule_work(struct work_struct *work); +const char *dsa_tag_protocol_to_str(const struct dsa_device_ops *ops); /* legacy.c */ #if IS_ENABLED(CONFIG_NET_DSA_LEGACY) @@ -205,6 +206,9 @@ extern const struct dsa_device_ops dsa_netdev_ops; /* tag_edsa.c */ extern const struct dsa_device_ops edsa_netdev_ops; +/* tag_gswip.c */ +extern const struct dsa_device_ops gswip_netdev_ops; + /* tag_ksz.c */ extern const struct dsa_device_ops ksz_netdev_ops; diff --git a/net/dsa/legacy.c b/net/dsa/legacy.c index 42a7b85b84e1..8aa92b09db76 100644 --- a/net/dsa/legacy.c +++ b/net/dsa/legacy.c @@ -392,8 +392,7 @@ static void dsa_of_free_platform_data(struct dsa_platform_data *pd) } /* Drop our reference to the MDIO bus device */ - if (pd->chip[i].host_dev) - put_device(pd->chip[i].host_dev); + put_device(pd->chip[i].host_dev); } kfree(pd->chip); } diff --git a/net/dsa/slave.c b/net/dsa/slave.c index 1c45c1d6d241..3f840b6eea69 100644 --- a/net/dsa/slave.c +++ b/net/dsa/slave.c @@ -1058,6 +1058,27 @@ static struct device_type dsa_type = { .name = "dsa", }; +static ssize_t tagging_show(struct device *d, struct device_attribute *attr, + char *buf) +{ + struct net_device *dev = to_net_dev(d); + struct dsa_port *dp = dsa_slave_to_port(dev); + + return sprintf(buf, "%s\n", + dsa_tag_protocol_to_str(dp->cpu_dp->tag_ops)); +} +static DEVICE_ATTR_RO(tagging); + +static struct attribute *dsa_slave_attrs[] = { + &dev_attr_tagging.attr, + NULL +}; + +static const struct attribute_group dsa_group = { + .name = "dsa", + .attrs = dsa_slave_attrs, +}; + static void dsa_slave_phylink_validate(struct net_device *dev, unsigned long *supported, struct phylink_link_state *state) @@ -1353,8 +1374,14 @@ int dsa_slave_create(struct dsa_port *port) goto out_phy; } + ret = sysfs_create_group(&slave_dev->dev.kobj, &dsa_group); + if (ret) + goto out_unreg; + return 0; +out_unreg: + unregister_netdev(slave_dev); out_phy: rtnl_lock(); phylink_disconnect_phy(p->dp->pl); @@ -1378,6 +1405,7 @@ void dsa_slave_destroy(struct net_device *slave_dev) rtnl_unlock(); dsa_slave_notify(slave_dev, DSA_PORT_UNREGISTER); + sysfs_remove_group(&slave_dev->dev.kobj, &dsa_group); unregister_netdev(slave_dev); phylink_destroy(dp->pl); free_percpu(p->stats64); diff --git a/net/dsa/tag_gswip.c b/net/dsa/tag_gswip.c new file mode 100644 index 000000000000..49e9b73f1be3 --- /dev/null +++ b/net/dsa/tag_gswip.c @@ -0,0 +1,109 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Intel / Lantiq GSWIP V2.0 PMAC tag support + * + * Copyright (C) 2017 - 2018 Hauke Mehrtens <hauke@hauke-m.de> + */ + +#include <linux/bitops.h> +#include <linux/etherdevice.h> +#include <linux/skbuff.h> +#include <net/dsa.h> + +#include "dsa_priv.h" + +#define GSWIP_TX_HEADER_LEN 4 + +/* special tag in TX path header */ +/* Byte 0 */ +#define GSWIP_TX_SLPID_SHIFT 0 /* source port ID */ +#define GSWIP_TX_SLPID_CPU 2 +#define GSWIP_TX_SLPID_APP1 3 +#define GSWIP_TX_SLPID_APP2 4 +#define GSWIP_TX_SLPID_APP3 5 +#define GSWIP_TX_SLPID_APP4 6 +#define GSWIP_TX_SLPID_APP5 7 + +/* Byte 1 */ +#define GSWIP_TX_CRCGEN_DIS BIT(7) +#define GSWIP_TX_DPID_SHIFT 0 /* destination group ID */ +#define GSWIP_TX_DPID_ELAN 0 +#define GSWIP_TX_DPID_EWAN 1 +#define GSWIP_TX_DPID_CPU 2 +#define GSWIP_TX_DPID_APP1 3 +#define GSWIP_TX_DPID_APP2 4 +#define GSWIP_TX_DPID_APP3 5 +#define GSWIP_TX_DPID_APP4 6 +#define GSWIP_TX_DPID_APP5 7 + +/* Byte 2 */ +#define GSWIP_TX_PORT_MAP_EN BIT(7) +#define GSWIP_TX_PORT_MAP_SEL BIT(6) +#define GSWIP_TX_LRN_DIS BIT(5) +#define GSWIP_TX_CLASS_EN BIT(4) +#define GSWIP_TX_CLASS_SHIFT 0 +#define GSWIP_TX_CLASS_MASK GENMASK(3, 0) + +/* Byte 3 */ +#define GSWIP_TX_DPID_EN BIT(0) +#define GSWIP_TX_PORT_MAP_SHIFT 1 +#define GSWIP_TX_PORT_MAP_MASK GENMASK(6, 1) + +#define GSWIP_RX_HEADER_LEN 8 + +/* special tag in RX path header */ +/* Byte 7 */ +#define GSWIP_RX_SPPID_SHIFT 4 +#define GSWIP_RX_SPPID_MASK GENMASK(6, 4) + +static struct sk_buff *gswip_tag_xmit(struct sk_buff *skb, + struct net_device *dev) +{ + struct dsa_port *dp = dsa_slave_to_port(dev); + int err; + u8 *gswip_tag; + + err = skb_cow_head(skb, GSWIP_TX_HEADER_LEN); + if (err) + return NULL; + + skb_push(skb, GSWIP_TX_HEADER_LEN); + + gswip_tag = skb->data; + gswip_tag[0] = GSWIP_TX_SLPID_CPU; + gswip_tag[1] = GSWIP_TX_DPID_ELAN; + gswip_tag[2] = GSWIP_TX_PORT_MAP_EN | GSWIP_TX_PORT_MAP_SEL; + gswip_tag[3] = BIT(dp->index + GSWIP_TX_PORT_MAP_SHIFT) & GSWIP_TX_PORT_MAP_MASK; + gswip_tag[3] |= GSWIP_TX_DPID_EN; + + return skb; +} + +static struct sk_buff *gswip_tag_rcv(struct sk_buff *skb, + struct net_device *dev, + struct packet_type *pt) +{ + int port; + u8 *gswip_tag; + + if (unlikely(!pskb_may_pull(skb, GSWIP_RX_HEADER_LEN))) + return NULL; + + gswip_tag = skb->data - ETH_HLEN; + + /* Get source port information */ + port = (gswip_tag[7] & GSWIP_RX_SPPID_MASK) >> GSWIP_RX_SPPID_SHIFT; + skb->dev = dsa_master_find_slave(dev, 0, port); + if (!skb->dev) + return NULL; + + /* remove GSWIP tag */ + skb_pull_rcsum(skb, GSWIP_RX_HEADER_LEN); + + return skb; +} + +const struct dsa_device_ops gswip_netdev_ops = { + .xmit = gswip_tag_xmit, + .rcv = gswip_tag_rcv, +}; diff --git a/net/ieee802154/6lowpan/reassembly.c b/net/ieee802154/6lowpan/reassembly.c index e7857a8ac86d..d14226ecfde4 100644 --- a/net/ieee802154/6lowpan/reassembly.c +++ b/net/ieee802154/6lowpan/reassembly.c @@ -260,7 +260,7 @@ static int lowpan_frag_reasm(struct lowpan_frag_queue *fq, struct sk_buff *prev, } sub_frag_mem_limit(fq->q.net, sum_truesize); - head->next = NULL; + skb_mark_not_on_list(head); head->dev = ldev; head->tstamp = fq->q.stamp; @@ -463,7 +463,6 @@ static int __net_init lowpan_frags_ns_sysctl_register(struct net *net) table[0].data = &ieee802154_lowpan->frags.high_thresh; table[0].extra1 = &ieee802154_lowpan->frags.low_thresh; - table[0].extra2 = &init_net.ieee802154_lowpan.frags.high_thresh; table[1].data = &ieee802154_lowpan->frags.low_thresh; table[1].extra2 = &ieee802154_lowpan->frags.high_thresh; table[2].data = &ieee802154_lowpan->frags.timeout; diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index 20fda8fb8ffd..1fbe2f815474 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -1377,6 +1377,7 @@ struct sk_buff *inet_gso_segment(struct sk_buff *skb, if (encap) skb_reset_inner_headers(skb); skb->network_header = (u8 *)iph - skb->head; + skb_reset_mac_len(skb); } while ((skb = skb->next)); out: diff --git a/net/ipv4/cipso_ipv4.c b/net/ipv4/cipso_ipv4.c index 82178cc69c96..777fa3b7fb13 100644 --- a/net/ipv4/cipso_ipv4.c +++ b/net/ipv4/cipso_ipv4.c @@ -1512,7 +1512,7 @@ static int cipso_v4_parsetag_loc(const struct cipso_v4_doi *doi_def, * * Description: * Parse the packet's IP header looking for a CIPSO option. Returns a pointer - * to the start of the CIPSO option on success, NULL if one if not found. + * to the start of the CIPSO option on success, NULL if one is not found. * */ unsigned char *cipso_v4_optptr(const struct sk_buff *skb) @@ -1522,10 +1522,8 @@ unsigned char *cipso_v4_optptr(const struct sk_buff *skb) int optlen; int taglen; - for (optlen = iph->ihl*4 - sizeof(struct iphdr); optlen > 0; ) { + for (optlen = iph->ihl*4 - sizeof(struct iphdr); optlen > 1; ) { switch (optptr[0]) { - case IPOPT_CIPSO: - return optptr; case IPOPT_END: return NULL; case IPOPT_NOOP: @@ -1534,6 +1532,11 @@ unsigned char *cipso_v4_optptr(const struct sk_buff *skb) default: taglen = optptr[1]; } + if (!taglen || taglen > optlen) + return NULL; + if (optptr[0] == IPOPT_CIPSO) + return optptr; + optlen -= taglen; optptr += taglen; } diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c index ea4bd8a52422..44d931a3cd50 100644 --- a/net/ipv4/devinet.c +++ b/net/ipv4/devinet.c @@ -100,6 +100,15 @@ static const struct nla_policy ifa_ipv4_policy[IFA_MAX+1] = { [IFA_CACHEINFO] = { .len = sizeof(struct ifa_cacheinfo) }, [IFA_FLAGS] = { .type = NLA_U32 }, [IFA_RT_PRIORITY] = { .type = NLA_U32 }, + [IFA_TARGET_NETNSID] = { .type = NLA_S32 }, +}; + +struct inet_fill_args { + u32 portid; + u32 seq; + int event; + unsigned int flags; + int netnsid; }; #define IN4_ADDR_HSIZE_SHIFT 8 @@ -1584,13 +1593,14 @@ static int put_cacheinfo(struct sk_buff *skb, unsigned long cstamp, } static int inet_fill_ifaddr(struct sk_buff *skb, struct in_ifaddr *ifa, - u32 portid, u32 seq, int event, unsigned int flags) + struct inet_fill_args *args) { struct ifaddrmsg *ifm; struct nlmsghdr *nlh; u32 preferred, valid; - nlh = nlmsg_put(skb, portid, seq, event, sizeof(*ifm), flags); + nlh = nlmsg_put(skb, args->portid, args->seq, args->event, sizeof(*ifm), + args->flags); if (!nlh) return -EMSGSIZE; @@ -1601,6 +1611,10 @@ static int inet_fill_ifaddr(struct sk_buff *skb, struct in_ifaddr *ifa, ifm->ifa_scope = ifa->ifa_scope; ifm->ifa_index = ifa->ifa_dev->dev->ifindex; + if (args->netnsid >= 0 && + nla_put_s32(skb, IFA_TARGET_NETNSID, args->netnsid)) + goto nla_put_failure; + if (!(ifm->ifa_flags & IFA_F_PERMANENT)) { preferred = ifa->ifa_preferred_lft; valid = ifa->ifa_valid_lft; @@ -1647,7 +1661,16 @@ nla_put_failure: static int inet_dump_ifaddr(struct sk_buff *skb, struct netlink_callback *cb) { + struct inet_fill_args fillargs = { + .portid = NETLINK_CB(cb->skb).portid, + .seq = cb->nlh->nlmsg_seq, + .event = RTM_NEWADDR, + .flags = NLM_F_MULTI, + .netnsid = -1, + }; struct net *net = sock_net(skb->sk); + struct nlattr *tb[IFA_MAX+1]; + struct net *tgt_net = net; int h, s_h; int idx, s_idx; int ip_idx, s_ip_idx; @@ -1660,12 +1683,24 @@ static int inet_dump_ifaddr(struct sk_buff *skb, struct netlink_callback *cb) s_idx = idx = cb->args[1]; s_ip_idx = ip_idx = cb->args[2]; + if (nlmsg_parse(cb->nlh, sizeof(struct ifaddrmsg), tb, IFA_MAX, + ifa_ipv4_policy, NULL) >= 0) { + if (tb[IFA_TARGET_NETNSID]) { + fillargs.netnsid = nla_get_s32(tb[IFA_TARGET_NETNSID]); + + tgt_net = rtnl_get_net_ns_capable(skb->sk, + fillargs.netnsid); + if (IS_ERR(tgt_net)) + return PTR_ERR(tgt_net); + } + } + for (h = s_h; h < NETDEV_HASHENTRIES; h++, s_idx = 0) { idx = 0; - head = &net->dev_index_head[h]; + head = &tgt_net->dev_index_head[h]; rcu_read_lock(); - cb->seq = atomic_read(&net->ipv4.dev_addr_genid) ^ - net->dev_base_seq; + cb->seq = atomic_read(&tgt_net->ipv4.dev_addr_genid) ^ + tgt_net->dev_base_seq; hlist_for_each_entry_rcu(dev, head, index_hlist) { if (idx < s_idx) goto cont; @@ -1679,10 +1714,7 @@ static int inet_dump_ifaddr(struct sk_buff *skb, struct netlink_callback *cb) ifa = ifa->ifa_next, ip_idx++) { if (ip_idx < s_ip_idx) continue; - if (inet_fill_ifaddr(skb, ifa, - NETLINK_CB(cb->skb).portid, - cb->nlh->nlmsg_seq, - RTM_NEWADDR, NLM_F_MULTI) < 0) { + if (inet_fill_ifaddr(skb, ifa, &fillargs) < 0) { rcu_read_unlock(); goto done; } @@ -1698,6 +1730,8 @@ done: cb->args[0] = h; cb->args[1] = idx; cb->args[2] = ip_idx; + if (fillargs.netnsid >= 0) + put_net(tgt_net); return skb->len; } @@ -1705,8 +1739,14 @@ done: static void rtmsg_ifa(int event, struct in_ifaddr *ifa, struct nlmsghdr *nlh, u32 portid) { + struct inet_fill_args fillargs = { + .portid = portid, + .seq = nlh ? nlh->nlmsg_seq : 0, + .event = event, + .flags = 0, + .netnsid = -1, + }; struct sk_buff *skb; - u32 seq = nlh ? nlh->nlmsg_seq : 0; int err = -ENOBUFS; struct net *net; @@ -1715,7 +1755,7 @@ static void rtmsg_ifa(int event, struct in_ifaddr *ifa, struct nlmsghdr *nlh, if (!skb) goto errout; - err = inet_fill_ifaddr(skb, ifa, portid, seq, event, 0); + err = inet_fill_ifaddr(skb, ifa, &fillargs); if (err < 0) { /* -EMSGSIZE implies BUG in inet_nlmsg_size() */ WARN_ON(err == -EMSGSIZE); diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c index 2998b0e47d4b..30e2bcc3ef2a 100644 --- a/net/ipv4/fib_frontend.c +++ b/net/ipv4/fib_frontend.c @@ -315,6 +315,32 @@ __be32 fib_compute_spec_dst(struct sk_buff *skb) return inet_select_addr(dev, ip_hdr(skb)->saddr, scope); } +bool fib_info_nh_uses_dev(struct fib_info *fi, const struct net_device *dev) +{ + bool dev_match = false; +#ifdef CONFIG_IP_ROUTE_MULTIPATH + int ret; + + for (ret = 0; ret < fi->fib_nhs; ret++) { + struct fib_nh *nh = &fi->fib_nh[ret]; + + if (nh->nh_dev == dev) { + dev_match = true; + break; + } else if (l3mdev_master_ifindex_rcu(nh->nh_dev) == dev->ifindex) { + dev_match = true; + break; + } + } +#else + if (fi->fib_nh[0].nh_dev == dev) + dev_match = true; +#endif + + return dev_match; +} +EXPORT_SYMBOL_GPL(fib_info_nh_uses_dev); + /* Given (packet source, input interface) and optional (dst, oif, tos): * - (main) check, that source is valid i.e. not broadcast or our local * address. @@ -361,24 +387,8 @@ static int __fib_validate_source(struct sk_buff *skb, __be32 src, __be32 dst, (res.type != RTN_LOCAL || !IN_DEV_ACCEPT_LOCAL(idev))) goto e_inval; fib_combine_itag(itag, &res); - dev_match = false; - -#ifdef CONFIG_IP_ROUTE_MULTIPATH - for (ret = 0; ret < res.fi->fib_nhs; ret++) { - struct fib_nh *nh = &res.fi->fib_nh[ret]; - if (nh->nh_dev == dev) { - dev_match = true; - break; - } else if (l3mdev_master_ifindex_rcu(nh->nh_dev) == dev->ifindex) { - dev_match = true; - break; - } - } -#else - if (FIB_RES_DEV(res) == dev) - dev_match = true; -#endif + dev_match = fib_info_nh_uses_dev(res.fi, dev); if (dev_match) { ret = FIB_RES_NH(res).nh_scope >= RT_SCOPE_HOST; return ret; diff --git a/net/ipv4/gre_demux.c b/net/ipv4/gre_demux.c index b798862b6be5..7efe740c06eb 100644 --- a/net/ipv4/gre_demux.c +++ b/net/ipv4/gre_demux.c @@ -86,13 +86,14 @@ int gre_parse_header(struct sk_buff *skb, struct tnl_ptk_info *tpi, options = (__be32 *)(greh + 1); if (greh->flags & GRE_CSUM) { - if (skb_checksum_simple_validate(skb)) { + if (!skb_checksum_simple_validate(skb)) { + skb_checksum_try_convert(skb, IPPROTO_GRE, 0, + null_compute_pseudo); + } else if (csum_err) { *csum_err = true; return -EINVAL; } - skb_checksum_try_convert(skb, IPPROTO_GRE, 0, - null_compute_pseudo); options++; } diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c index 330f62353b11..9b0158fa431f 100644 --- a/net/ipv4/ip_fragment.c +++ b/net/ipv4/ip_fragment.c @@ -260,8 +260,7 @@ out: spin_unlock(&qp->q.lock); out_rcu_unlock: rcu_read_unlock(); - if (head) - kfree_skb(head); + kfree_skb(head); ipq_put(qp); } @@ -602,6 +601,7 @@ static int ip_frag_reasm(struct ipq *qp, struct sk_buff *skb, nextp = &fp->next; fp->prev = NULL; memset(&fp->rbnode, 0, sizeof(fp->rbnode)); + fp->sk = NULL; head->data_len += fp->len; head->len += fp->len; if (head->ip_summed != fp->ip_summed) @@ -623,7 +623,7 @@ static int ip_frag_reasm(struct ipq *qp, struct sk_buff *skb, sub_frag_mem_limit(qp->q.net, head->truesize); *nextp = NULL; - head->next = NULL; + skb_mark_not_on_list(head); head->prev = NULL; head->dev = dev; head->tstamp = qp->q.stamp; @@ -822,7 +822,6 @@ static int __net_init ip4_frags_ns_ctl_register(struct net *net) table[0].data = &net->ipv4.frags.high_thresh; table[0].extra1 = &net->ipv4.frags.low_thresh; - table[0].extra2 = &init_net.ipv4.frags.high_thresh; table[1].data = &net->ipv4.frags.low_thresh; table[1].extra2 = &net->ipv4.frags.high_thresh; table[2].data = &net->ipv4.frags.timeout; diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c index ae714aecc31c..c3385a84f8ff 100644 --- a/net/ipv4/ip_gre.c +++ b/net/ipv4/ip_gre.c @@ -178,6 +178,9 @@ static void ipgre_err(struct sk_buff *skb, u32 info, if (tpi->proto == htons(ETH_P_TEB)) itn = net_generic(net, gre_tap_net_id); + else if (tpi->proto == htons(ETH_P_ERSPAN) || + tpi->proto == htons(ETH_P_ERSPAN2)) + itn = net_generic(net, erspan_net_id); else itn = net_generic(net, ipgre_net_id); @@ -229,13 +232,10 @@ static void gre_err(struct sk_buff *skb, u32 info) const int type = icmp_hdr(skb)->type; const int code = icmp_hdr(skb)->code; struct tnl_ptk_info tpi; - bool csum_err = false; - if (gre_parse_header(skb, &tpi, &csum_err, htons(ETH_P_IP), - iph->ihl * 4) < 0) { - if (!csum_err) /* ignore csum errors. */ - return; - } + if (gre_parse_header(skb, &tpi, NULL, htons(ETH_P_IP), + iph->ihl * 4) < 0) + return; if (type == ICMP_DEST_UNREACH && code == ICMP_FRAG_NEEDED) { ipv4_update_pmtu(skb, dev_net(skb->dev), info, @@ -328,6 +328,8 @@ static int erspan_rcv(struct sk_buff *skb, struct tnl_ptk_info *tpi, ip_tunnel_rcv(tunnel, skb, tpi, tun_dst, log_ecn_error); return PACKET_RCVD; } + return PACKET_REJECT; + drop: kfree_skb(skb); return PACKET_RCVD; diff --git a/net/ipv4/ip_input.c b/net/ipv4/ip_input.c index 3196cf58f418..35a786c0aaa0 100644 --- a/net/ipv4/ip_input.c +++ b/net/ipv4/ip_input.c @@ -531,11 +531,7 @@ static void ip_sublist_rcv_finish(struct list_head *head) struct sk_buff *skb, *next; list_for_each_entry_safe(skb, next, head, list) { - list_del(&skb->list); - /* Handle ip{6}_forward case, as sch_direct_xmit have - * another kind of SKB-list usage (see validate_xmit_skb_list) - */ - skb->next = NULL; + skb_list_del_init(skb); dst_input(skb); } } diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index 9c4e72e9c60a..c09219e7f230 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -278,7 +278,7 @@ static int ip_finish_output_gso(struct net *net, struct sock *sk, struct sk_buff *nskb = segs->next; int err; - segs->next = NULL; + skb_mark_not_on_list(segs); err = ip_fragment(net, sk, segs, mtu, ip_finish_output2); if (err && ret == 0) @@ -684,7 +684,7 @@ int ip_do_fragment(struct net *net, struct sock *sk, struct sk_buff *skb, skb = frag; frag = skb->next; - skb->next = NULL; + skb_mark_not_on_list(skb); } if (err == 0) { diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c index c4f5602308ed..284a22154b4e 100644 --- a/net/ipv4/ip_tunnel.c +++ b/net/ipv4/ip_tunnel.c @@ -627,6 +627,7 @@ void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev, const struct iphdr *tnl_params, u8 protocol) { struct ip_tunnel *tunnel = netdev_priv(dev); + unsigned int inner_nhdr_len = 0; const struct iphdr *inner_iph; struct flowi4 fl4; u8 tos, ttl; @@ -636,6 +637,14 @@ void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev, __be32 dst; bool connected; + /* ensure we can access the inner net header, for several users below */ + if (skb->protocol == htons(ETH_P_IP)) + inner_nhdr_len = sizeof(struct iphdr); + else if (skb->protocol == htons(ETH_P_IPV6)) + inner_nhdr_len = sizeof(struct ipv6hdr); + if (unlikely(!pskb_may_pull(skb, inner_nhdr_len))) + goto tx_error; + inner_iph = (const struct iphdr *)skb_inner_network_header(skb); connected = (tunnel->parms.iph.daddr != 0); diff --git a/net/ipv4/netfilter/Kconfig b/net/ipv4/netfilter/Kconfig index d9504adc47b3..184bf2e0a1ed 100644 --- a/net/ipv4/netfilter/Kconfig +++ b/net/ipv4/netfilter/Kconfig @@ -106,6 +106,10 @@ config NF_NAT_IPV4 if NF_NAT_IPV4 +config NF_NAT_MASQUERADE_IPV4 + bool + +if NF_TABLES config NFT_CHAIN_NAT_IPV4 depends on NF_TABLES_IPV4 tristate "IPv4 nf_tables nat chain support" @@ -115,9 +119,6 @@ config NFT_CHAIN_NAT_IPV4 packet transformations such as the source, destination address and source and destination ports. -config NF_NAT_MASQUERADE_IPV4 - bool - config NFT_MASQ_IPV4 tristate "IPv4 masquerading support for nf_tables" depends on NF_TABLES_IPV4 @@ -135,6 +136,7 @@ config NFT_REDIR_IPV4 help This is the expression that provides IPv4 redirect support for nf_tables. +endif # NF_TABLES config NF_NAT_SNMP_BASIC tristate "Basic SNMP-ALG support" diff --git a/net/ipv4/netfilter/ipt_rpfilter.c b/net/ipv4/netfilter/ipt_rpfilter.c index 12843c9ef142..0b10d8812828 100644 --- a/net/ipv4/netfilter/ipt_rpfilter.c +++ b/net/ipv4/netfilter/ipt_rpfilter.c @@ -36,7 +36,6 @@ static bool rpfilter_lookup_reverse(struct net *net, struct flowi4 *fl4, const struct net_device *dev, u8 flags) { struct fib_result res; - bool dev_match; int ret __maybe_unused; if (fib_lookup(net, fl4, &res, FIB_LOOKUP_IGNORE_LINKSTATE)) @@ -46,21 +45,7 @@ static bool rpfilter_lookup_reverse(struct net *net, struct flowi4 *fl4, if (res.type != RTN_LOCAL || !(flags & XT_RPFILTER_ACCEPT_LOCAL)) return false; } - dev_match = false; -#ifdef CONFIG_IP_ROUTE_MULTIPATH - for (ret = 0; ret < res.fi->fib_nhs; ret++) { - struct fib_nh *nh = &res.fi->fib_nh[ret]; - - if (nh->nh_dev == dev) { - dev_match = true; - break; - } - } -#else - if (FIB_RES_DEV(res) == dev) - dev_match = true; -#endif - return dev_match || flags & XT_RPFILTER_LOOSE; + return fib_info_nh_uses_dev(res.fi, dev) || flags & XT_RPFILTER_LOOSE; } static bool diff --git a/net/ipv4/netfilter/nft_fib_ipv4.c b/net/ipv4/netfilter/nft_fib_ipv4.c index e50976e3c213..94eb25bc8d7e 100644 --- a/net/ipv4/netfilter/nft_fib_ipv4.c +++ b/net/ipv4/netfilter/nft_fib_ipv4.c @@ -76,10 +76,7 @@ void nft_fib4_eval(const struct nft_expr *expr, struct nft_regs *regs, .flowi4_iif = LOOPBACK_IFINDEX, }; const struct net_device *oif; - struct net_device *found; -#ifdef CONFIG_IP_ROUTE_MULTIPATH - int i; -#endif + const struct net_device *found; /* * Do not set flowi4_oif, it restricts results (for example, asking @@ -146,25 +143,13 @@ void nft_fib4_eval(const struct nft_expr *expr, struct nft_regs *regs, if (!oif) { found = FIB_RES_DEV(res); - goto ok; - } - -#ifdef CONFIG_IP_ROUTE_MULTIPATH - for (i = 0; i < res.fi->fib_nhs; i++) { - struct fib_nh *nh = &res.fi->fib_nh[i]; + } else { + if (!fib_info_nh_uses_dev(res.fi, oif)) + return; - if (nh->nh_dev == oif) { - found = nh->nh_dev; - goto ok; - } + found = oif; } - return; -#else - found = FIB_RES_DEV(res); - if (found != oif) - return; -#endif -ok: + switch (priv->result) { case NFT_FIB_RESULT_OIF: *dest = found->ifindex; diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c index c3387dfd725b..606f868d9f3f 100644 --- a/net/ipv4/syncookies.c +++ b/net/ipv4/syncookies.c @@ -88,7 +88,7 @@ u64 cookie_init_timestamp(struct request_sock *req) ts <<= TSBITS; ts |= options; } - return (u64)ts * (USEC_PER_SEC / TCP_TS_HZ); + return (u64)ts * (NSEC_PER_SEC / TCP_TS_HZ); } diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 8c4235c098fd..69c236943f56 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -1185,7 +1185,7 @@ int tcp_sendmsg_locked(struct sock *sk, struct msghdr *msg, size_t size) flags = msg->msg_flags; - if (flags & MSG_ZEROCOPY && size) { + if (flags & MSG_ZEROCOPY && size && sock_flag(sk, SOCK_ZEROCOPY)) { if (sk->sk_state != TCP_ESTABLISHED) { err = -EINVAL; goto out_err; @@ -1295,7 +1295,7 @@ new_segment: copy = size_goal; /* All packets are restored as if they have - * already been sent. skb_mstamp isn't set to + * already been sent. skb_mstamp_ns isn't set to * avoid wrong rtt estimation. */ if (tp->repair) diff --git a/net/ipv4/tcp_bbr.c b/net/ipv4/tcp_bbr.c index 02ff2dde9609..a5786e3e2c16 100644 --- a/net/ipv4/tcp_bbr.c +++ b/net/ipv4/tcp_bbr.c @@ -128,6 +128,9 @@ static const u32 bbr_probe_rtt_mode_ms = 200; /* Skip TSO below the following bandwidth (bits/sec): */ static const int bbr_min_tso_rate = 1200000; +/* Pace at ~1% below estimated bw, on average, to reduce queue at bottleneck. */ +static const int bbr_pacing_marging_percent = 1; + /* We use a high_gain value of 2/ln(2) because it's the smallest pacing gain * that will allow a smoothly increasing pacing rate that will double each RTT * and send the same number of packets per RTT that an un-paced, slow-starting @@ -208,12 +211,10 @@ static u64 bbr_rate_bytes_per_sec(struct sock *sk, u64 rate, int gain) { unsigned int mss = tcp_sk(sk)->mss_cache; - if (!tcp_needs_internal_pacing(sk)) - mss = tcp_mss_to_mtu(sk, mss); rate *= mss; rate *= gain; rate >>= BBR_SCALE; - rate *= USEC_PER_SEC; + rate *= USEC_PER_SEC / 100 * (100 - bbr_pacing_marging_percent); return rate >> BW_SCALE; } diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 62508a2f9b21..d703a0b3b6a2 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -1305,7 +1305,7 @@ static bool tcp_shifted_skb(struct sock *sk, struct sk_buff *prev, */ tcp_sacktag_one(sk, state, TCP_SKB_CB(skb)->sacked, start_seq, end_seq, dup_sack, pcount, - skb->skb_mstamp); + tcp_skb_timestamp_us(skb)); tcp_rate_skb_delivered(sk, skb, state->rate); if (skb == tp->lost_skb_hint) @@ -1580,7 +1580,7 @@ static struct sk_buff *tcp_sacktag_walk(struct sk_buff *skb, struct sock *sk, TCP_SKB_CB(skb)->end_seq, dup_sack, tcp_skb_pcount(skb), - skb->skb_mstamp); + tcp_skb_timestamp_us(skb)); tcp_rate_skb_delivered(sk, skb, state->rate); if (TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_ACKED) list_del_init(&skb->tcp_tsorted_anchor); @@ -3103,7 +3103,7 @@ static int tcp_clean_rtx_queue(struct sock *sk, u32 prior_fack, tp->retrans_out -= acked_pcount; flag |= FLAG_RETRANS_DATA_ACKED; } else if (!(sacked & TCPCB_SACKED_ACKED)) { - last_ackt = skb->skb_mstamp; + last_ackt = tcp_skb_timestamp_us(skb); WARN_ON_ONCE(last_ackt == 0); if (!first_ackt) first_ackt = last_ackt; @@ -3121,7 +3121,7 @@ static int tcp_clean_rtx_queue(struct sock *sk, u32 prior_fack, tp->delivered += acked_pcount; if (!tcp_skb_spurious_retrans(tp, skb)) tcp_rack_advance(tp, sacked, scb->end_seq, - skb->skb_mstamp); + tcp_skb_timestamp_us(skb)); } if (sacked & TCPCB_LOST) tp->lost_out -= acked_pcount; @@ -3215,7 +3215,8 @@ static int tcp_clean_rtx_queue(struct sock *sk, u32 prior_fack, tp->lost_cnt_hint -= min(tp->lost_cnt_hint, delta); } } else if (skb && rtt_update && sack_rtt_us >= 0 && - sack_rtt_us > tcp_stamp_us_delta(tp->tcp_mstamp, skb->skb_mstamp)) { + sack_rtt_us > tcp_stamp_us_delta(tp->tcp_mstamp, + tcp_skb_timestamp_us(skb))) { /* Do not re-arm RTO if the sack RTT is measured from data sent * after when the head was last (re)transmitted. Otherwise the * timeout may continue to extend in loss recovery. @@ -6380,8 +6381,8 @@ static bool tcp_syn_flood_action(const struct sock *sk, if (!queue->synflood_warned && net->ipv4.sysctl_tcp_syncookies != 2 && xchg(&queue->synflood_warned, 1) == 0) - pr_info("%s: Possible SYN flooding on port %d. %s. Check SNMP counters.\n", - proto, ntohs(tcp_hdr(skb)->dest), msg); + net_info_ratelimited("%s: Possible SYN flooding on port %d. %s. Check SNMP counters.\n", + proto, ntohs(tcp_hdr(skb)->dest), msg); return want_cookie; } diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 09547ef9c4c6..1f2496e8620d 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -544,7 +544,7 @@ void tcp_v4_err(struct sk_buff *icmp_skb, u32 info) BUG_ON(!skb); tcp_mstamp_refresh(tp); - delta_us = (u32)(tp->tcp_mstamp - skb->skb_mstamp); + delta_us = (u32)(tp->tcp_mstamp - tcp_skb_timestamp_us(skb)); remaining = icsk->icsk_rto - usecs_to_jiffies(delta_us); diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 597dbd749f05..fe7855b090e4 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -45,6 +45,22 @@ #include <trace/events/tcp.h> +/* Refresh clocks of a TCP socket, + * ensuring monotically increasing values. + */ +void tcp_mstamp_refresh(struct tcp_sock *tp) +{ + u64 val = tcp_clock_ns(); + + /* departure time for next data packet */ + if (val > tp->tcp_wstamp_ns) + tp->tcp_wstamp_ns = val; + + val = div_u64(val, NSEC_PER_USEC); + if (val > tp->tcp_mstamp) + tp->tcp_mstamp = val; +} + static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle, int push_one, gfp_t gfp); @@ -977,28 +993,34 @@ enum hrtimer_restart tcp_pace_kick(struct hrtimer *timer) return HRTIMER_NORESTART; } -static void tcp_internal_pacing(struct sock *sk, const struct sk_buff *skb) +static void tcp_internal_pacing(struct sock *sk) { - u64 len_ns; - u32 rate; - if (!tcp_needs_internal_pacing(sk)) return; - rate = sk->sk_pacing_rate; - if (!rate || rate == ~0U) - return; - - len_ns = (u64)skb->len * NSEC_PER_SEC; - do_div(len_ns, rate); hrtimer_start(&tcp_sk(sk)->pacing_timer, - ktime_add_ns(ktime_get(), len_ns), + ns_to_ktime(tcp_sk(sk)->tcp_wstamp_ns), HRTIMER_MODE_ABS_PINNED_SOFT); sock_hold(sk); } -static void tcp_update_skb_after_send(struct tcp_sock *tp, struct sk_buff *skb) +static void tcp_update_skb_after_send(struct sock *sk, struct sk_buff *skb) { - skb->skb_mstamp = tp->tcp_mstamp; + struct tcp_sock *tp = tcp_sk(sk); + + skb->skb_mstamp_ns = tp->tcp_wstamp_ns; + if (sk->sk_pacing_status != SK_PACING_NONE) { + u32 rate = sk->sk_pacing_rate; + + /* Original sch_fq does not pace first 10 MSS + * Note that tp->data_segs_out overflows after 2^32 packets, + * this is a minor annoyance. + */ + if (rate != ~0U && rate && tp->data_segs_out >= 10) { + tp->tcp_wstamp_ns += div_u64((u64)skb->len * NSEC_PER_SEC, rate); + + tcp_internal_pacing(sk); + } + } list_move_tail(&skb->tcp_tsorted_anchor, &tp->tsorted_sent_queue); } @@ -1045,7 +1067,7 @@ static int __tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, if (unlikely(!skb)) return -ENOBUFS; } - skb->skb_mstamp = tp->tcp_mstamp; + skb->skb_mstamp_ns = tp->tcp_wstamp_ns; inet = inet_sk(sk); tcb = TCP_SKB_CB(skb); @@ -1137,7 +1159,6 @@ static int __tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, tcp_event_data_sent(tp, sk); tp->data_segs_out += tcp_skb_pcount(skb); tp->bytes_sent += skb->len - tcp_header_size; - tcp_internal_pacing(sk, skb); } if (after(tcb->end_seq, tp->snd_nxt) || tcb->seq == tcb->end_seq) @@ -1149,8 +1170,7 @@ static int __tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, skb_shinfo(skb)->gso_segs = tcp_skb_pcount(skb); skb_shinfo(skb)->gso_size = tcp_skb_mss(skb); - /* Our usage of tstamp should remain private */ - skb->tstamp = 0; + /* Leave earliest departure time in skb->tstamp (skb->skb_mstamp_ns) */ /* Cleanup our debris for IP stacks */ memset(skb->cb, 0, max(sizeof(struct inet_skb_parm), @@ -1163,7 +1183,7 @@ static int __tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, err = net_xmit_eval(err); } if (!err && oskb) { - tcp_update_skb_after_send(tp, oskb); + tcp_update_skb_after_send(sk, oskb); tcp_rate_skb_sent(sk, oskb); } return err; @@ -1966,7 +1986,7 @@ static bool tcp_tso_should_defer(struct sock *sk, struct sk_buff *skb, head = tcp_rtx_queue_head(sk); if (!head) goto send_now; - age = tcp_stamp_us_delta(tp->tcp_mstamp, head->skb_mstamp); + age = tcp_stamp_us_delta(tp->tcp_mstamp, tcp_skb_timestamp_us(head)); /* If next ACK is likely to come too late (half srtt), do not defer */ if (age < (tp->srtt_us >> 4)) goto send_now; @@ -2312,7 +2332,7 @@ static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle, if (unlikely(tp->repair) && tp->repair_queue == TCP_SEND_QUEUE) { /* "skb_mstamp" is used as a start point for the retransmit timer */ - tcp_update_skb_after_send(tp, skb); + tcp_update_skb_after_send(sk, skb); goto repair; /* Skip network transmission */ } @@ -2887,7 +2907,7 @@ int __tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb, int segs) } tcp_skb_tsorted_restore(skb); if (!err) { - tcp_update_skb_after_send(tp, skb); + tcp_update_skb_after_send(sk, skb); tcp_rate_skb_sent(sk, skb); } } else { @@ -3205,10 +3225,10 @@ struct sk_buff *tcp_make_synack(const struct sock *sk, struct dst_entry *dst, memset(&opts, 0, sizeof(opts)); #ifdef CONFIG_SYN_COOKIES if (unlikely(req->cookie_ts)) - skb->skb_mstamp = cookie_init_timestamp(req); + skb->skb_mstamp_ns = cookie_init_timestamp(req); else #endif - skb->skb_mstamp = tcp_clock_us(); + skb->skb_mstamp_ns = tcp_clock_ns(); #ifdef CONFIG_TCP_MD5SIG rcu_read_lock(); @@ -3424,7 +3444,7 @@ static int tcp_send_syn_data(struct sock *sk, struct sk_buff *syn) err = tcp_transmit_skb(sk, syn_data, 1, sk->sk_allocation); - syn->skb_mstamp = syn_data->skb_mstamp; + syn->skb_mstamp_ns = syn_data->skb_mstamp_ns; /* Now full SYN+DATA was cloned and sent (or not), * remove the SYN from the original skb (syn_data) diff --git a/net/ipv4/tcp_rate.c b/net/ipv4/tcp_rate.c index 4dff40dad4dc..baed2186c7c6 100644 --- a/net/ipv4/tcp_rate.c +++ b/net/ipv4/tcp_rate.c @@ -55,8 +55,10 @@ void tcp_rate_skb_sent(struct sock *sk, struct sk_buff *skb) * bandwidth estimate. */ if (!tp->packets_out) { - tp->first_tx_mstamp = skb->skb_mstamp; - tp->delivered_mstamp = skb->skb_mstamp; + u64 tstamp_us = tcp_skb_timestamp_us(skb); + + tp->first_tx_mstamp = tstamp_us; + tp->delivered_mstamp = tstamp_us; } TCP_SKB_CB(skb)->tx.first_tx_mstamp = tp->first_tx_mstamp; @@ -88,13 +90,12 @@ void tcp_rate_skb_delivered(struct sock *sk, struct sk_buff *skb, rs->is_app_limited = scb->tx.is_app_limited; rs->is_retrans = scb->sacked & TCPCB_RETRANS; + /* Record send time of most recently ACKed packet: */ + tp->first_tx_mstamp = tcp_skb_timestamp_us(skb); /* Find the duration of the "send phase" of this window: */ - rs->interval_us = tcp_stamp_us_delta( - skb->skb_mstamp, - scb->tx.first_tx_mstamp); + rs->interval_us = tcp_stamp_us_delta(tp->first_tx_mstamp, + scb->tx.first_tx_mstamp); - /* Record send time of most recently ACKed packet: */ - tp->first_tx_mstamp = skb->skb_mstamp; } /* Mark off the skb delivered once it's sacked to avoid being * used again when it's cumulatively acked. For acked packets diff --git a/net/ipv4/tcp_recovery.c b/net/ipv4/tcp_recovery.c index c81aadff769b..fdb715bdd2d1 100644 --- a/net/ipv4/tcp_recovery.c +++ b/net/ipv4/tcp_recovery.c @@ -50,7 +50,7 @@ static u32 tcp_rack_reo_wnd(const struct sock *sk) s32 tcp_rack_skb_timeout(struct tcp_sock *tp, struct sk_buff *skb, u32 reo_wnd) { return tp->rack.rtt_us + reo_wnd - - tcp_stamp_us_delta(tp->tcp_mstamp, skb->skb_mstamp); + tcp_stamp_us_delta(tp->tcp_mstamp, tcp_skb_timestamp_us(skb)); } /* RACK loss detection (IETF draft draft-ietf-tcpm-rack-01): @@ -91,7 +91,8 @@ static void tcp_rack_detect_loss(struct sock *sk, u32 *reo_timeout) !(scb->sacked & TCPCB_SACKED_RETRANS)) continue; - if (!tcp_rack_sent_after(tp->rack.mstamp, skb->skb_mstamp, + if (!tcp_rack_sent_after(tp->rack.mstamp, + tcp_skb_timestamp_us(skb), tp->rack.end_seq, scb->end_seq)) break; diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c index 7fdf222a0bdf..4f661e178da8 100644 --- a/net/ipv4/tcp_timer.c +++ b/net/ipv4/tcp_timer.c @@ -360,7 +360,7 @@ static void tcp_probe_timer(struct sock *sk) */ start_ts = tcp_skb_timestamp(skb); if (!start_ts) - skb->skb_mstamp = tp->tcp_mstamp; + skb->skb_mstamp_ns = tp->tcp_wstamp_ns; else if (icsk->icsk_user_timeout && (s32)(tcp_time_stamp(tp) - start_ts) > icsk->icsk_user_timeout) goto abort; @@ -758,7 +758,7 @@ void tcp_init_xmit_timers(struct sock *sk) { inet_csk_init_xmit_timers(sk, &tcp_write_timer, &tcp_delack_timer, &tcp_keepalive_timer); - hrtimer_init(&tcp_sk(sk)->pacing_timer, CLOCK_MONOTONIC, + hrtimer_init(&tcp_sk(sk)->pacing_timer, CLOCK_TAI, HRTIMER_MODE_ABS_PINNED_SOFT); tcp_sk(sk)->pacing_timer.function = tcp_pace_kick; diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index f4e35b2ff8b8..7d69dd6fa7e8 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -2124,6 +2124,28 @@ static inline int udp4_csum_init(struct sk_buff *skb, struct udphdr *uh, inet_compute_pseudo); } +/* wrapper for udp_queue_rcv_skb tacking care of csum conversion and + * return code conversion for ip layer consumption + */ +static int udp_unicast_rcv_skb(struct sock *sk, struct sk_buff *skb, + struct udphdr *uh) +{ + int ret; + + if (inet_get_convert_csum(sk) && uh->check && !IS_UDPLITE(sk)) + skb_checksum_try_convert(skb, IPPROTO_UDP, uh->check, + inet_compute_pseudo); + + ret = udp_queue_rcv_skb(sk, skb); + + /* a return value > 0 means to resubmit the input, but + * it wants the return to be -protocol, or 0 + */ + if (ret > 0) + return -ret; + return 0; +} + /* * All we need to do is get the socket, and then do a checksum. */ @@ -2170,14 +2192,9 @@ int __udp4_lib_rcv(struct sk_buff *skb, struct udp_table *udptable, if (unlikely(sk->sk_rx_dst != dst)) udp_sk_rx_dst_set(sk, dst); - ret = udp_queue_rcv_skb(sk, skb); + ret = udp_unicast_rcv_skb(sk, skb, uh); sock_put(sk); - /* a return value > 0 means to resubmit the input, but - * it wants the return to be -protocol, or 0 - */ - if (ret > 0) - return -ret; - return 0; + return ret; } if (rt->rt_flags & (RTCF_BROADCAST|RTCF_MULTICAST)) @@ -2185,22 +2202,8 @@ int __udp4_lib_rcv(struct sk_buff *skb, struct udp_table *udptable, saddr, daddr, udptable, proto); sk = __udp4_lib_lookup_skb(skb, uh->source, uh->dest, udptable); - if (sk) { - int ret; - - if (inet_get_convert_csum(sk) && uh->check && !IS_UDPLITE(sk)) - skb_checksum_try_convert(skb, IPPROTO_UDP, uh->check, - inet_compute_pseudo); - - ret = udp_queue_rcv_skb(sk, skb); - - /* a return value > 0 means to resubmit the input, but - * it wants the return to be -protocol, or 0 - */ - if (ret > 0) - return -ret; - return 0; - } + if (sk) + return udp_unicast_rcv_skb(sk, skb, uh); if (!xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb)) goto drop; diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index d51a8c0b3372..a9a317322388 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -997,6 +997,7 @@ ipv6_add_addr(struct inet6_dev *idev, struct ifa6_config *cfg, if (addr_type == IPV6_ADDR_ANY || addr_type & IPV6_ADDR_MULTICAST || (!(idev->dev->flags & IFF_LOOPBACK) && + !netif_is_l3_master(idev->dev) && addr_type & IPV6_ADDR_LOOPBACK)) return ERR_PTR(-EADDRNOTAVAIL); @@ -4201,7 +4202,6 @@ static struct inet6_ifaddr *if6_get_first(struct seq_file *seq, loff_t pos) p++; continue; } - state->offset++; return ifa; } @@ -4225,13 +4225,12 @@ static struct inet6_ifaddr *if6_get_next(struct seq_file *seq, return ifa; } + state->offset = 0; while (++state->bucket < IN6_ADDR_HSIZE) { - state->offset = 0; hlist_for_each_entry_rcu(ifa, &inet6_addr_lst[state->bucket], addr_lst) { if (!net_eq(dev_net(ifa->idev->dev), net)) continue; - state->offset++; return ifa; } } @@ -4491,6 +4490,7 @@ static const struct nla_policy ifa_ipv6_policy[IFA_MAX+1] = { [IFA_CACHEINFO] = { .len = sizeof(struct ifa_cacheinfo) }, [IFA_FLAGS] = { .len = sizeof(u32) }, [IFA_RT_PRIORITY] = { .len = sizeof(u32) }, + [IFA_TARGET_NETNSID] = { .type = NLA_S32 }, }; static int @@ -4793,19 +4793,32 @@ static inline int inet6_ifaddr_msgsize(void) + nla_total_size(4) /* IFA_RT_PRIORITY */; } +struct inet6_fill_args { + u32 portid; + u32 seq; + int event; + unsigned int flags; + int netnsid; +}; + static int inet6_fill_ifaddr(struct sk_buff *skb, struct inet6_ifaddr *ifa, - u32 portid, u32 seq, int event, unsigned int flags) + struct inet6_fill_args *args) { struct nlmsghdr *nlh; u32 preferred, valid; - nlh = nlmsg_put(skb, portid, seq, event, sizeof(struct ifaddrmsg), flags); + nlh = nlmsg_put(skb, args->portid, args->seq, args->event, + sizeof(struct ifaddrmsg), args->flags); if (!nlh) return -EMSGSIZE; put_ifaddrmsg(nlh, ifa->prefix_len, ifa->flags, rt_scope(ifa->scope), ifa->idev->dev->ifindex); + if (args->netnsid >= 0 && + nla_put_s32(skb, IFA_TARGET_NETNSID, args->netnsid)) + goto error; + if (!((ifa->flags&IFA_F_PERMANENT) && (ifa->prefered_lft == INFINITY_LIFE_TIME))) { preferred = ifa->prefered_lft; @@ -4855,7 +4868,7 @@ error: } static int inet6_fill_ifmcaddr(struct sk_buff *skb, struct ifmcaddr6 *ifmca, - u32 portid, u32 seq, int event, u16 flags) + struct inet6_fill_args *args) { struct nlmsghdr *nlh; u8 scope = RT_SCOPE_UNIVERSE; @@ -4864,10 +4877,15 @@ static int inet6_fill_ifmcaddr(struct sk_buff *skb, struct ifmcaddr6 *ifmca, if (ipv6_addr_scope(&ifmca->mca_addr) & IFA_SITE) scope = RT_SCOPE_SITE; - nlh = nlmsg_put(skb, portid, seq, event, sizeof(struct ifaddrmsg), flags); + nlh = nlmsg_put(skb, args->portid, args->seq, args->event, + sizeof(struct ifaddrmsg), args->flags); if (!nlh) return -EMSGSIZE; + if (args->netnsid >= 0 && + nla_put_s32(skb, IFA_TARGET_NETNSID, args->netnsid)) + return -EMSGSIZE; + put_ifaddrmsg(nlh, 128, IFA_F_PERMANENT, scope, ifindex); if (nla_put_in6_addr(skb, IFA_MULTICAST, &ifmca->mca_addr) < 0 || put_cacheinfo(skb, ifmca->mca_cstamp, ifmca->mca_tstamp, @@ -4881,7 +4899,7 @@ static int inet6_fill_ifmcaddr(struct sk_buff *skb, struct ifmcaddr6 *ifmca, } static int inet6_fill_ifacaddr(struct sk_buff *skb, struct ifacaddr6 *ifaca, - u32 portid, u32 seq, int event, unsigned int flags) + struct inet6_fill_args *args) { struct net_device *dev = fib6_info_nh_dev(ifaca->aca_rt); int ifindex = dev ? dev->ifindex : 1; @@ -4891,10 +4909,15 @@ static int inet6_fill_ifacaddr(struct sk_buff *skb, struct ifacaddr6 *ifaca, if (ipv6_addr_scope(&ifaca->aca_addr) & IFA_SITE) scope = RT_SCOPE_SITE; - nlh = nlmsg_put(skb, portid, seq, event, sizeof(struct ifaddrmsg), flags); + nlh = nlmsg_put(skb, args->portid, args->seq, args->event, + sizeof(struct ifaddrmsg), args->flags); if (!nlh) return -EMSGSIZE; + if (args->netnsid >= 0 && + nla_put_s32(skb, IFA_TARGET_NETNSID, args->netnsid)) + return -EMSGSIZE; + put_ifaddrmsg(nlh, 128, IFA_F_PERMANENT, scope, ifindex); if (nla_put_in6_addr(skb, IFA_ANYCAST, &ifaca->aca_addr) < 0 || put_cacheinfo(skb, ifaca->aca_cstamp, ifaca->aca_tstamp, @@ -4916,8 +4939,14 @@ enum addr_type_t { /* called with rcu_read_lock() */ static int in6_dump_addrs(struct inet6_dev *idev, struct sk_buff *skb, struct netlink_callback *cb, enum addr_type_t type, - int s_ip_idx, int *p_ip_idx) + int s_ip_idx, int *p_ip_idx, int netnsid) { + struct inet6_fill_args fillargs = { + .portid = NETLINK_CB(cb->skb).portid, + .seq = cb->nlh->nlmsg_seq, + .flags = NLM_F_MULTI, + .netnsid = netnsid, + }; struct ifmcaddr6 *ifmca; struct ifacaddr6 *ifaca; int err = 1; @@ -4927,16 +4956,13 @@ static int in6_dump_addrs(struct inet6_dev *idev, struct sk_buff *skb, switch (type) { case UNICAST_ADDR: { struct inet6_ifaddr *ifa; + fillargs.event = RTM_NEWADDR; /* unicast address incl. temp addr */ list_for_each_entry(ifa, &idev->addr_list, if_list) { if (++ip_idx < s_ip_idx) continue; - err = inet6_fill_ifaddr(skb, ifa, - NETLINK_CB(cb->skb).portid, - cb->nlh->nlmsg_seq, - RTM_NEWADDR, - NLM_F_MULTI); + err = inet6_fill_ifaddr(skb, ifa, &fillargs); if (err < 0) break; nl_dump_check_consistent(cb, nlmsg_hdr(skb)); @@ -4944,31 +4970,26 @@ static int in6_dump_addrs(struct inet6_dev *idev, struct sk_buff *skb, break; } case MULTICAST_ADDR: + fillargs.event = RTM_GETMULTICAST; + /* multicast address */ for (ifmca = idev->mc_list; ifmca; ifmca = ifmca->next, ip_idx++) { if (ip_idx < s_ip_idx) continue; - err = inet6_fill_ifmcaddr(skb, ifmca, - NETLINK_CB(cb->skb).portid, - cb->nlh->nlmsg_seq, - RTM_GETMULTICAST, - NLM_F_MULTI); + err = inet6_fill_ifmcaddr(skb, ifmca, &fillargs); if (err < 0) break; } break; case ANYCAST_ADDR: + fillargs.event = RTM_GETANYCAST; /* anycast address */ for (ifaca = idev->ac_list; ifaca; ifaca = ifaca->aca_next, ip_idx++) { if (ip_idx < s_ip_idx) continue; - err = inet6_fill_ifacaddr(skb, ifaca, - NETLINK_CB(cb->skb).portid, - cb->nlh->nlmsg_seq, - RTM_GETANYCAST, - NLM_F_MULTI); + err = inet6_fill_ifacaddr(skb, ifaca, &fillargs); if (err < 0) break; } @@ -4985,6 +5006,9 @@ static int inet6_dump_addr(struct sk_buff *skb, struct netlink_callback *cb, enum addr_type_t type) { struct net *net = sock_net(skb->sk); + struct nlattr *tb[IFA_MAX+1]; + struct net *tgt_net = net; + int netnsid = -1; int h, s_h; int idx, ip_idx; int s_idx, s_ip_idx; @@ -4996,11 +5020,22 @@ static int inet6_dump_addr(struct sk_buff *skb, struct netlink_callback *cb, s_idx = idx = cb->args[1]; s_ip_idx = ip_idx = cb->args[2]; + if (nlmsg_parse(cb->nlh, sizeof(struct ifaddrmsg), tb, IFA_MAX, + ifa_ipv6_policy, NULL) >= 0) { + if (tb[IFA_TARGET_NETNSID]) { + netnsid = nla_get_s32(tb[IFA_TARGET_NETNSID]); + + tgt_net = rtnl_get_net_ns_capable(skb->sk, netnsid); + if (IS_ERR(tgt_net)) + return PTR_ERR(tgt_net); + } + } + rcu_read_lock(); - cb->seq = atomic_read(&net->ipv6.dev_addr_genid) ^ net->dev_base_seq; + cb->seq = atomic_read(&tgt_net->ipv6.dev_addr_genid) ^ tgt_net->dev_base_seq; for (h = s_h; h < NETDEV_HASHENTRIES; h++, s_idx = 0) { idx = 0; - head = &net->dev_index_head[h]; + head = &tgt_net->dev_index_head[h]; hlist_for_each_entry_rcu(dev, head, index_hlist) { if (idx < s_idx) goto cont; @@ -5012,7 +5047,7 @@ static int inet6_dump_addr(struct sk_buff *skb, struct netlink_callback *cb, goto cont; if (in6_dump_addrs(idev, skb, cb, type, - s_ip_idx, &ip_idx) < 0) + s_ip_idx, &ip_idx, netnsid) < 0) goto done; cont: idx++; @@ -5023,6 +5058,8 @@ done: cb->args[0] = h; cb->args[1] = idx; cb->args[2] = ip_idx; + if (netnsid >= 0) + put_net(tgt_net); return skb->len; } @@ -5053,6 +5090,14 @@ static int inet6_rtm_getaddr(struct sk_buff *in_skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack) { struct net *net = sock_net(in_skb->sk); + struct inet6_fill_args fillargs = { + .portid = NETLINK_CB(in_skb).portid, + .seq = nlh->nlmsg_seq, + .event = RTM_NEWADDR, + .flags = 0, + .netnsid = -1, + }; + struct net *tgt_net = net; struct ifaddrmsg *ifm; struct nlattr *tb[IFA_MAX+1]; struct in6_addr *addr = NULL, *peer; @@ -5066,15 +5111,24 @@ static int inet6_rtm_getaddr(struct sk_buff *in_skb, struct nlmsghdr *nlh, if (err < 0) return err; + if (tb[IFA_TARGET_NETNSID]) { + fillargs.netnsid = nla_get_s32(tb[IFA_TARGET_NETNSID]); + + tgt_net = rtnl_get_net_ns_capable(NETLINK_CB(in_skb).sk, + fillargs.netnsid); + if (IS_ERR(tgt_net)) + return PTR_ERR(tgt_net); + } + addr = extract_addr(tb[IFA_ADDRESS], tb[IFA_LOCAL], &peer); if (!addr) return -EINVAL; ifm = nlmsg_data(nlh); if (ifm->ifa_index) - dev = dev_get_by_index(net, ifm->ifa_index); + dev = dev_get_by_index(tgt_net, ifm->ifa_index); - ifa = ipv6_get_ifaddr(net, addr, dev, 1); + ifa = ipv6_get_ifaddr(tgt_net, addr, dev, 1); if (!ifa) { err = -EADDRNOTAVAIL; goto errout; @@ -5086,20 +5140,22 @@ static int inet6_rtm_getaddr(struct sk_buff *in_skb, struct nlmsghdr *nlh, goto errout_ifa; } - err = inet6_fill_ifaddr(skb, ifa, NETLINK_CB(in_skb).portid, - nlh->nlmsg_seq, RTM_NEWADDR, 0); + err = inet6_fill_ifaddr(skb, ifa, &fillargs); if (err < 0) { /* -EMSGSIZE implies BUG in inet6_ifaddr_msgsize() */ WARN_ON(err == -EMSGSIZE); kfree_skb(skb); goto errout_ifa; } - err = rtnl_unicast(skb, net, NETLINK_CB(in_skb).portid); + err = rtnl_unicast(skb, tgt_net, NETLINK_CB(in_skb).portid); errout_ifa: in6_ifa_put(ifa); errout: if (dev) dev_put(dev); + if (fillargs.netnsid >= 0) + put_net(tgt_net); + return err; } @@ -5107,13 +5163,20 @@ static void inet6_ifa_notify(int event, struct inet6_ifaddr *ifa) { struct sk_buff *skb; struct net *net = dev_net(ifa->idev->dev); + struct inet6_fill_args fillargs = { + .portid = 0, + .seq = 0, + .event = event, + .flags = 0, + .netnsid = -1, + }; int err = -ENOBUFS; skb = nlmsg_new(inet6_ifaddr_msgsize(), GFP_ATOMIC); if (!skb) goto errout; - err = inet6_fill_ifaddr(skb, ifa, 0, 0, event, 0); + err = inet6_fill_ifaddr(skb, ifa, &fillargs); if (err < 0) { /* -EMSGSIZE implies BUG in inet6_ifaddr_msgsize() */ WARN_ON(err == -EMSGSIZE); diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c index 9a4261e50272..e9c8cfdf4b4c 100644 --- a/net/ipv6/af_inet6.c +++ b/net/ipv6/af_inet6.c @@ -209,6 +209,7 @@ lookup_protocol: np->hop_limit = -1; np->mcast_hops = IPV6_DEFAULT_MCASTHOPS; np->mc_loop = 1; + np->mc_all = 1; np->pmtudisc = IPV6_PMTUDISC_WANT; np->repflow = net->ipv6.sysctl.flowlabel_reflect; sk->sk_ipv6only = net->ipv6.sysctl.bindv6only; @@ -467,12 +468,10 @@ void inet6_destroy_sock(struct sock *sk) /* Release rx options */ skb = xchg(&np->pktoptions, NULL); - if (skb) - kfree_skb(skb); + kfree_skb(skb); skb = xchg(&np->rxpmtu, NULL); - if (skb) - kfree_skb(skb); + kfree_skb(skb); /* Free flowlabels */ fl6_free_socklist(sk); diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c index e493b041d4ac..515adbdba1d2 100644 --- a/net/ipv6/ip6_gre.c +++ b/net/ipv6/ip6_gre.c @@ -427,35 +427,17 @@ static void ip6gre_err(struct sk_buff *skb, struct inet6_skb_parm *opt, u8 type, u8 code, int offset, __be32 info) { struct net *net = dev_net(skb->dev); - const struct gre_base_hdr *greh; const struct ipv6hdr *ipv6h; - int grehlen = sizeof(*greh); + struct tnl_ptk_info tpi; struct ip6_tnl *t; - int key_off = 0; - __be16 flags; - __be32 key; - if (!pskb_may_pull(skb, offset + grehlen)) - return; - greh = (const struct gre_base_hdr *)(skb->data + offset); - flags = greh->flags; - if (flags & (GRE_VERSION | GRE_ROUTING)) + if (gre_parse_header(skb, &tpi, NULL, htons(ETH_P_IPV6), + offset) < 0) return; - if (flags & GRE_CSUM) - grehlen += 4; - if (flags & GRE_KEY) { - key_off = grehlen + offset; - grehlen += 4; - } - if (!pskb_may_pull(skb, offset + grehlen)) - return; ipv6h = (const struct ipv6hdr *)skb->data; - greh = (const struct gre_base_hdr *)(skb->data + offset); - key = key_off ? *(__be32 *)(skb->data + key_off) : 0; - t = ip6gre_tunnel_lookup(skb->dev, &ipv6h->daddr, &ipv6h->saddr, - key, greh->protocol); + tpi.key, tpi.proto); if (!t) return; diff --git a/net/ipv6/ip6_input.c b/net/ipv6/ip6_input.c index 6242682be876..96577e742afd 100644 --- a/net/ipv6/ip6_input.c +++ b/net/ipv6/ip6_input.c @@ -178,7 +178,8 @@ static struct sk_buff *ip6_rcv_core(struct sk_buff *skb, struct net_device *dev, */ if ((ipv6_addr_loopback(&hdr->saddr) || ipv6_addr_loopback(&hdr->daddr)) && - !(dev->flags & IFF_LOOPBACK)) + !(dev->flags & IFF_LOOPBACK) && + !netif_is_l3_master(dev)) goto err; /* RFC4291 Errata ID: 3480 diff --git a/net/ipv6/ip6_offload.c b/net/ipv6/ip6_offload.c index 37ff4805b20c..c7e495f12011 100644 --- a/net/ipv6/ip6_offload.c +++ b/net/ipv6/ip6_offload.c @@ -115,6 +115,7 @@ static struct sk_buff *ipv6_gso_segment(struct sk_buff *skb, payload_len = skb->len - nhoff - sizeof(*ipv6h); ipv6h->payload_len = htons(payload_len); skb->network_header = (u8 *)ipv6h - skb->head; + skb_reset_mac_len(skb); if (udpfrag) { int err = ip6_find_1stfragopt(skb, &prevhdr); diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index 16f200f06500..89e0d5118afe 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -219,12 +219,10 @@ int ip6_xmit(const struct sock *sk, struct sk_buff *skb, struct flowi6 *fl6, kfree_skb(skb); return -ENOBUFS; } + if (skb->sk) + skb_set_owner_w(skb2, skb->sk); consume_skb(skb); skb = skb2; - /* skb_set_owner_w() changes sk->sk_wmem_alloc atomically, - * it is safe to call in our context (socket lock not held) - */ - skb_set_owner_w(skb, (struct sock *)sk); } if (opt->opt_flen) ipv6_push_frag_opts(skb, opt, &proto); @@ -727,7 +725,7 @@ int ip6_fragment(struct net *net, struct sock *sk, struct sk_buff *skb, skb = frag; frag = skb->next; - skb->next = NULL; + skb_mark_not_on_list(skb); } kfree(tmp_hdr); diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c index 419960b0ba16..a0b6932c3afd 100644 --- a/net/ipv6/ip6_tunnel.c +++ b/net/ipv6/ip6_tunnel.c @@ -1234,7 +1234,7 @@ static inline int ip4ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev) { struct ip6_tnl *t = netdev_priv(dev); - const struct iphdr *iph = ip_hdr(skb); + const struct iphdr *iph; int encap_limit = -1; struct flowi6 fl6; __u8 dsfield; @@ -1242,6 +1242,11 @@ ip4ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev) u8 tproto; int err; + /* ensure we can access the full inner ip header */ + if (!pskb_may_pull(skb, sizeof(struct iphdr))) + return -1; + + iph = ip_hdr(skb); memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt)); tproto = READ_ONCE(t->parms.proto); @@ -1306,7 +1311,7 @@ static inline int ip6ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev) { struct ip6_tnl *t = netdev_priv(dev); - struct ipv6hdr *ipv6h = ipv6_hdr(skb); + struct ipv6hdr *ipv6h; int encap_limit = -1; __u16 offset; struct flowi6 fl6; @@ -1315,6 +1320,10 @@ ip6ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev) u8 tproto; int err; + if (unlikely(!pskb_may_pull(skb, sizeof(*ipv6h)))) + return -1; + + ipv6h = ipv6_hdr(skb); tproto = READ_ONCE(t->parms.proto); if ((tproto != IPPROTO_IPV6 && tproto != 0) || ip6_tnl_addr_conflict(t, ipv6h)) diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c index c0cac9cc3a28..381ce38940ae 100644 --- a/net/ipv6/ipv6_sockglue.c +++ b/net/ipv6/ipv6_sockglue.c @@ -674,6 +674,13 @@ done: retv = ipv6_sock_ac_drop(sk, mreq.ipv6mr_ifindex, &mreq.ipv6mr_acaddr); break; } + case IPV6_MULTICAST_ALL: + if (optlen < sizeof(int)) + goto e_inval; + np->mc_all = valbool; + retv = 0; + break; + case MCAST_JOIN_GROUP: case MCAST_LEAVE_GROUP: { @@ -1266,6 +1273,10 @@ static int do_ipv6_getsockopt(struct sock *sk, int level, int optname, val = np->mcast_oif; break; + case IPV6_MULTICAST_ALL: + val = np->mc_all; + break; + case IPV6_UNICAST_IF: val = (__force int)htonl((__u32) np->ucast_oif); break; diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c index 4ae54aaca373..6895e1dc0b03 100644 --- a/net/ipv6/mcast.c +++ b/net/ipv6/mcast.c @@ -636,7 +636,7 @@ bool inet6_mc_check(struct sock *sk, const struct in6_addr *mc_addr, } if (!mc) { rcu_read_unlock(); - return true; + return np->mc_all; } read_lock(&mc->sflock); psl = mc->sflist; diff --git a/net/ipv6/netfilter/nf_conntrack_reasm.c b/net/ipv6/netfilter/nf_conntrack_reasm.c index 2a14d8b65924..b8ac369f98ad 100644 --- a/net/ipv6/netfilter/nf_conntrack_reasm.c +++ b/net/ipv6/netfilter/nf_conntrack_reasm.c @@ -445,11 +445,12 @@ nf_ct_frag6_reasm(struct frag_queue *fq, struct sk_buff *prev, struct net_devic else if (head->ip_summed == CHECKSUM_COMPLETE) head->csum = csum_add(head->csum, fp->csum); head->truesize += fp->truesize; + fp->sk = NULL; } sub_frag_mem_limit(fq->q.net, head->truesize); head->ignore_df = 1; - head->next = NULL; + skb_mark_not_on_list(head); head->dev = dev; head->tstamp = fq->q.stamp; ipv6_hdr(head)->payload_len = htons(payload_len); diff --git a/net/ipv6/reassembly.c b/net/ipv6/reassembly.c index 5c5b4f79296e..5c3c92713096 100644 --- a/net/ipv6/reassembly.c +++ b/net/ipv6/reassembly.c @@ -145,7 +145,7 @@ static int ip6_frag_queue(struct frag_queue *fq, struct sk_buff *skb, */ if (end < fq->q.len || ((fq->q.flags & INET_FRAG_LAST_IN) && end != fq->q.len)) - goto err; + goto discard_fq; fq->q.flags |= INET_FRAG_LAST_IN; fq->q.len = end; } else { @@ -162,20 +162,20 @@ static int ip6_frag_queue(struct frag_queue *fq, struct sk_buff *skb, if (end > fq->q.len) { /* Some bits beyond end -> corruption. */ if (fq->q.flags & INET_FRAG_LAST_IN) - goto err; + goto discard_fq; fq->q.len = end; } } if (end == offset) - goto err; + goto discard_fq; /* Point into the IP datagram 'data' part. */ if (!pskb_pull(skb, (u8 *) (fhdr + 1) - skb->data)) - goto err; + goto discard_fq; if (pskb_trim_rcsum(skb, end - offset)) - goto err; + goto discard_fq; /* Find out which fragments are in front and at the back of us * in the chain of fragments so far. We must know where to put @@ -388,7 +388,7 @@ static int ip6_frag_reasm(struct frag_queue *fq, struct sk_buff *prev, } sub_frag_mem_limit(fq->q.net, sum_truesize); - head->next = NULL; + skb_mark_not_on_list(head); head->dev = dev; head->tstamp = fq->q.stamp; ipv6_hdr(head)->payload_len = htons(payload_len); @@ -418,6 +418,7 @@ out_fail: rcu_read_lock(); __IP6_INC_STATS(net, __in6_dev_get(dev), IPSTATS_MIB_REASMFAILS); rcu_read_unlock(); + inet_frag_kill(&fq->q); return -1; } @@ -553,7 +554,6 @@ static int __net_init ip6_frags_ns_sysctl_register(struct net *net) table[0].data = &net->ipv6.frags.high_thresh; table[0].extra1 = &net->ipv6.frags.low_thresh; - table[0].extra2 = &init_net.ipv6.frags.high_thresh; table[1].data = &net->ipv6.frags.low_thresh; table[1].extra2 = &net->ipv6.frags.high_thresh; table[2].data = &net->ipv6.frags.timeout; diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 0fa62acc923c..d28f83e01593 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -364,11 +364,14 @@ EXPORT_SYMBOL(ip6_dst_alloc); static void ip6_dst_destroy(struct dst_entry *dst) { + struct dst_metrics *p = (struct dst_metrics *)DST_METRICS_PTR(dst); struct rt6_info *rt = (struct rt6_info *)dst; struct fib6_info *from; struct inet6_dev *idev; - dst_destroy_metrics_generic(dst); + if (p != &dst_default_metrics && refcount_dec_and_test(&p->refcnt)) + kfree(p); + rt6_uncached_list_del(rt); idev = rt->rt6i_idev; @@ -946,8 +949,6 @@ static void ip6_rt_init_dst_reject(struct rt6_info *rt, struct fib6_info *ort) static void ip6_rt_init_dst(struct rt6_info *rt, struct fib6_info *ort) { - rt->dst.flags |= fib6_info_dst_flags(ort); - if (ort->fib6_flags & RTF_REJECT) { ip6_rt_init_dst_reject(rt, ort); return; @@ -978,6 +979,10 @@ static void rt6_set_from(struct rt6_info *rt, struct fib6_info *from) rt->rt6i_flags &= ~RTF_EXPIRES; rcu_assign_pointer(rt->from, from); dst_init_metrics(&rt->dst, from->fib6_metrics->metrics, true); + if (from->fib6_metrics != &dst_default_metrics) { + rt->dst._metrics |= DST_METRICS_REFCOUNTED; + refcount_inc(&from->fib6_metrics->refcnt); + } } /* Caller must already hold reference to @ort */ @@ -995,7 +1000,6 @@ static void ip6_rt_copy_init(struct rt6_info *rt, struct fib6_info *ort) #ifdef CONFIG_IPV6_SUBTREES rt->rt6i_src = ort->fib6_src; #endif - rt->rt6i_prefsrc = ort->fib6_prefsrc; } static struct fib6_node* fib6_backtrack(struct fib6_node *fn, @@ -1449,11 +1453,6 @@ static int rt6_insert_exception(struct rt6_info *nrt, if (ort->fib6_src.plen) src_key = &nrt->rt6i_src.addr; #endif - - /* Update rt6i_prefsrc as it could be changed - * in rt6_remove_prefsrc() - */ - nrt->rt6i_prefsrc = ort->fib6_prefsrc; /* rt6_mtu_change() might lower mtu on ort. * Only insert this exception route if its mtu * is less than ort's mtu value. @@ -1635,25 +1634,6 @@ static void rt6_update_exception_stamp_rt(struct rt6_info *rt) rcu_read_unlock(); } -static void rt6_exceptions_remove_prefsrc(struct fib6_info *rt) -{ - struct rt6_exception_bucket *bucket; - struct rt6_exception *rt6_ex; - int i; - - bucket = rcu_dereference_protected(rt->rt6i_exception_bucket, - lockdep_is_held(&rt6_exception_lock)); - - if (bucket) { - for (i = 0; i < FIB6_EXCEPTION_BUCKET_SIZE; i++) { - hlist_for_each_entry(rt6_ex, &bucket->chain, hlist) { - rt6_ex->rt6i->rt6i_prefsrc.plen = 0; - } - bucket++; - } - } -} - static bool rt6_mtu_change_route_allowed(struct inet6_dev *idev, struct rt6_info *rt, int mtu) { @@ -2098,7 +2078,8 @@ struct dst_entry *ip6_route_output_flags(struct net *net, const struct sock *sk, { bool any_src; - if (rt6_need_strict(&fl6->daddr)) { + if (ipv6_addr_type(&fl6->daddr) & + (IPV6_ADDR_MULTICAST | IPV6_ADDR_LINKLOCAL)) { struct dst_entry *dst; dst = l3mdev_link_scope_lookup(net, fl6); @@ -3793,8 +3774,6 @@ static int fib6_remove_prefsrc(struct fib6_info *rt, void *arg) spin_lock_bh(&rt6_exception_lock); /* remove prefsrc entry */ rt->fib6_prefsrc.plen = 0; - /* need to update cache as well */ - rt6_exceptions_remove_prefsrc(rt); spin_unlock_bh(&rt6_exception_lock); } return 0; @@ -4668,20 +4647,31 @@ static int rt6_fill_node(struct net *net, struct sk_buff *skb, int iif, int type, u32 portid, u32 seq, unsigned int flags) { - struct rtmsg *rtm; + struct rt6_info *rt6 = (struct rt6_info *)dst; + struct rt6key *rt6_dst, *rt6_src; + u32 *pmetrics, table, rt6_flags; struct nlmsghdr *nlh; + struct rtmsg *rtm; long expires = 0; - u32 *pmetrics; - u32 table; nlh = nlmsg_put(skb, portid, seq, type, sizeof(*rtm), flags); if (!nlh) return -EMSGSIZE; + if (rt6) { + rt6_dst = &rt6->rt6i_dst; + rt6_src = &rt6->rt6i_src; + rt6_flags = rt6->rt6i_flags; + } else { + rt6_dst = &rt->fib6_dst; + rt6_src = &rt->fib6_src; + rt6_flags = rt->fib6_flags; + } + rtm = nlmsg_data(nlh); rtm->rtm_family = AF_INET6; - rtm->rtm_dst_len = rt->fib6_dst.plen; - rtm->rtm_src_len = rt->fib6_src.plen; + rtm->rtm_dst_len = rt6_dst->plen; + rtm->rtm_src_len = rt6_src->plen; rtm->rtm_tos = 0; if (rt->fib6_table) table = rt->fib6_table->tb6_id; @@ -4696,7 +4686,7 @@ static int rt6_fill_node(struct net *net, struct sk_buff *skb, rtm->rtm_scope = RT_SCOPE_UNIVERSE; rtm->rtm_protocol = rt->fib6_protocol; - if (rt->fib6_flags & RTF_CACHE) + if (rt6_flags & RTF_CACHE) rtm->rtm_flags |= RTM_F_CLONED; if (dest) { @@ -4704,7 +4694,7 @@ static int rt6_fill_node(struct net *net, struct sk_buff *skb, goto nla_put_failure; rtm->rtm_dst_len = 128; } else if (rtm->rtm_dst_len) - if (nla_put_in6_addr(skb, RTA_DST, &rt->fib6_dst.addr)) + if (nla_put_in6_addr(skb, RTA_DST, &rt6_dst->addr)) goto nla_put_failure; #ifdef CONFIG_IPV6_SUBTREES if (src) { @@ -4712,12 +4702,12 @@ static int rt6_fill_node(struct net *net, struct sk_buff *skb, goto nla_put_failure; rtm->rtm_src_len = 128; } else if (rtm->rtm_src_len && - nla_put_in6_addr(skb, RTA_SRC, &rt->fib6_src.addr)) + nla_put_in6_addr(skb, RTA_SRC, &rt6_src->addr)) goto nla_put_failure; #endif if (iif) { #ifdef CONFIG_IPV6_MROUTE - if (ipv6_addr_is_multicast(&rt->fib6_dst.addr)) { + if (ipv6_addr_is_multicast(&rt6_dst->addr)) { int err = ip6mr_get_route(net, skb, rtm, portid); if (err == 0) @@ -4752,7 +4742,14 @@ static int rt6_fill_node(struct net *net, struct sk_buff *skb, /* For multipath routes, walk the siblings list and add * each as a nexthop within RTA_MULTIPATH. */ - if (rt->fib6_nsiblings) { + if (rt6) { + if (rt6_flags & RTF_GATEWAY && + nla_put_in6_addr(skb, RTA_GATEWAY, &rt6->rt6i_gateway)) + goto nla_put_failure; + + if (dst->dev && nla_put_u32(skb, RTA_OIF, dst->dev->ifindex)) + goto nla_put_failure; + } else if (rt->fib6_nsiblings) { struct fib6_info *sibling, *next_sibling; struct nlattr *mp; @@ -4775,7 +4772,7 @@ static int rt6_fill_node(struct net *net, struct sk_buff *skb, goto nla_put_failure; } - if (rt->fib6_flags & RTF_EXPIRES) { + if (rt6_flags & RTF_EXPIRES) { expires = dst ? dst->expires : rt->expires; expires -= jiffies; } @@ -4783,7 +4780,7 @@ static int rt6_fill_node(struct net *net, struct sk_buff *skb, if (rtnl_put_cacheinfo(skb, dst, 0, expires, dst ? dst->error : 0) < 0) goto nla_put_failure; - if (nla_put_u8(skb, RTA_PREF, IPV6_EXTRACT_PREF(rt->fib6_flags))) + if (nla_put_u8(skb, RTA_PREF, IPV6_EXTRACT_PREF(rt6_flags))) goto nla_put_failure; diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index 83f4c77c79d8..28c4aa5078fc 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -752,6 +752,28 @@ static void udp6_sk_rx_dst_set(struct sock *sk, struct dst_entry *dst) } } +/* wrapper for udp_queue_rcv_skb tacking care of csum conversion and + * return code conversion for ip layer consumption + */ +static int udp6_unicast_rcv_skb(struct sock *sk, struct sk_buff *skb, + struct udphdr *uh) +{ + int ret; + + if (inet_get_convert_csum(sk) && uh->check && !IS_UDPLITE(sk)) + skb_checksum_try_convert(skb, IPPROTO_UDP, uh->check, + ip6_compute_pseudo); + + ret = udpv6_queue_rcv_skb(sk, skb); + + /* a return value > 0 means to resubmit the input, but + * it wants the return to be -protocol, or 0 + */ + if (ret > 0) + return -ret; + return 0; +} + int __udp6_lib_rcv(struct sk_buff *skb, struct udp_table *udptable, int proto) { @@ -803,13 +825,14 @@ int __udp6_lib_rcv(struct sk_buff *skb, struct udp_table *udptable, if (unlikely(sk->sk_rx_dst != dst)) udp6_sk_rx_dst_set(sk, dst); - ret = udpv6_queue_rcv_skb(sk, skb); - sock_put(sk); + if (!uh->check && !udp_sk(sk)->no_check6_rx) { + sock_put(sk); + goto report_csum_error; + } - /* a return value > 0 means to resubmit the input */ - if (ret > 0) - return ret; - return 0; + ret = udp6_unicast_rcv_skb(sk, skb, uh); + sock_put(sk); + return ret; } /* @@ -822,30 +845,13 @@ int __udp6_lib_rcv(struct sk_buff *skb, struct udp_table *udptable, /* Unicast */ sk = __udp6_lib_lookup_skb(skb, uh->source, uh->dest, udptable); if (sk) { - int ret; - - if (!uh->check && !udp_sk(sk)->no_check6_rx) { - udp6_csum_zero_error(skb); - goto csum_error; - } - - if (inet_get_convert_csum(sk) && uh->check && !IS_UDPLITE(sk)) - skb_checksum_try_convert(skb, IPPROTO_UDP, uh->check, - ip6_compute_pseudo); - - ret = udpv6_queue_rcv_skb(sk, skb); - - /* a return value > 0 means to resubmit the input */ - if (ret > 0) - return ret; - - return 0; + if (!uh->check && !udp_sk(sk)->no_check6_rx) + goto report_csum_error; + return udp6_unicast_rcv_skb(sk, skb, uh); } - if (!uh->check) { - udp6_csum_zero_error(skb); - goto csum_error; - } + if (!uh->check) + goto report_csum_error; if (!xfrm6_policy_check(NULL, XFRM_POLICY_IN, skb)) goto discard; @@ -866,6 +872,9 @@ short_packet: ulen, skb->len, daddr, ntohs(uh->dest)); goto discard; + +report_csum_error: + udp6_csum_zero_error(skb); csum_error: __UDP6_INC_STATS(net, UDP_MIB_CSUMERRORS, proto == IPPROTO_UDPLITE); discard: diff --git a/net/iucv/af_iucv.c b/net/iucv/af_iucv.c index a21d8ed0a325..5b68ee908107 100644 --- a/net/iucv/af_iucv.c +++ b/net/iucv/af_iucv.c @@ -48,7 +48,7 @@ static struct iucv_interface *pr_iucv; static const u8 iprm_shutdown[8] = {0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x01}; -#define TRGCLS_SIZE (sizeof(((struct iucv_message *)0)->class)) +#define TRGCLS_SIZE FIELD_SIZEOF(struct iucv_message, class) #define __iucv_sock_wait(sk, condition, timeo, ret) \ do { \ @@ -351,20 +351,28 @@ static int afiucv_hs_send(struct iucv_message *imsg, struct sock *sock, memcpy(&phs_hdr->iucv_hdr, imsg, sizeof(struct iucv_message)); skb->dev = iucv->hs_dev; - if (!skb->dev) - return -ENODEV; - if (!(skb->dev->flags & IFF_UP) || !netif_carrier_ok(skb->dev)) - return -ENETDOWN; + if (!skb->dev) { + err = -ENODEV; + goto err_free; + } + if (!(skb->dev->flags & IFF_UP) || !netif_carrier_ok(skb->dev)) { + err = -ENETDOWN; + goto err_free; + } if (skb->len > skb->dev->mtu) { - if (sock->sk_type == SOCK_SEQPACKET) - return -EMSGSIZE; - else - skb_trim(skb, skb->dev->mtu); + if (sock->sk_type == SOCK_SEQPACKET) { + err = -EMSGSIZE; + goto err_free; + } + skb_trim(skb, skb->dev->mtu); } skb->protocol = cpu_to_be16(ETH_P_AF_IUCV); nskb = skb_clone(skb, GFP_ATOMIC); - if (!nskb) - return -ENOMEM; + if (!nskb) { + err = -ENOMEM; + goto err_free; + } + skb_queue_tail(&iucv->send_skb_q, nskb); err = dev_queue_xmit(skb); if (net_xmit_eval(err)) { @@ -375,6 +383,10 @@ static int afiucv_hs_send(struct iucv_message *imsg, struct sock *sock, WARN_ON(atomic_read(&iucv->msg_recv) < 0); } return net_xmit_eval(err); + +err_free: + kfree_skb(skb); + return err; } static struct sock *__iucv_get_sock_by_name(char *nm) @@ -1167,7 +1179,7 @@ static int iucv_sock_sendmsg(struct socket *sock, struct msghdr *msg, err = afiucv_hs_send(&txmsg, sk, skb, 0); if (err) { atomic_dec(&iucv->msg_sent); - goto fail; + goto out; } } else { /* Classic VM IUCV transport */ skb_queue_tail(&iucv->send_skb_q, skb); @@ -2155,8 +2167,8 @@ static int afiucv_hs_rcv(struct sk_buff *skb, struct net_device *dev, struct sock *sk; struct iucv_sock *iucv; struct af_iucv_trans_hdr *trans_hdr; + int err = NET_RX_SUCCESS; char nullstring[8]; - int err = 0; if (skb->len < (ETH_HLEN + sizeof(struct af_iucv_trans_hdr))) { WARN_ONCE(1, "AF_IUCV too short skb, len=%d, min=%d", @@ -2254,7 +2266,7 @@ static int afiucv_hs_rcv(struct sk_buff *skb, struct net_device *dev, err = afiucv_hs_callback_rx(sk, skb); break; default: - ; + kfree_skb(skb); } return err; diff --git a/net/iucv/iucv.c b/net/iucv/iucv.c index 8f7ef167c45a..eb502c6290c2 100644 --- a/net/iucv/iucv.c +++ b/net/iucv/iucv.c @@ -1874,7 +1874,7 @@ static void iucv_pm_complete(struct device *dev) * Returns 0 if there are still iucv pathes defined * 1 if there are no iucv pathes defined */ -int iucv_path_table_empty(void) +static int iucv_path_table_empty(void) { int i; diff --git a/net/llc/llc_core.c b/net/llc/llc_core.c index 260b3dc1b4a2..64d4bef04e73 100644 --- a/net/llc/llc_core.c +++ b/net/llc/llc_core.c @@ -127,9 +127,7 @@ void llc_sap_close(struct llc_sap *sap) list_del_rcu(&sap->node); spin_unlock_bh(&llc_sap_list_lock); - synchronize_rcu(); - - kfree(sap); + kfree_rcu(sap, rcu); } static struct packet_type llc_packet_type __read_mostly = { diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c index c6bfd4019d44..a0ca27aeb732 100644 --- a/net/mac80211/rx.c +++ b/net/mac80211/rx.c @@ -2077,6 +2077,7 @@ ieee80211_reassemble_find(struct ieee80211_sub_if_data *sdata, idx = sdata->fragment_next; for (i = 0; i < IEEE80211_FRAGMENT_MAX; i++) { struct ieee80211_hdr *f_hdr; + struct sk_buff *f_skb; idx--; if (idx < 0) @@ -2088,7 +2089,8 @@ ieee80211_reassemble_find(struct ieee80211_sub_if_data *sdata, entry->last_frag + 1 != frag) continue; - f_hdr = (struct ieee80211_hdr *)entry->skb_list.next->data; + f_skb = __skb_peek(&entry->skb_list); + f_hdr = (struct ieee80211_hdr *) f_skb->data; /* * Check ftype and addresses are equal, else check next fragment diff --git a/net/mpls/af_mpls.c b/net/mpls/af_mpls.c index 7a4de6d618b1..8fbe6cdbe255 100644 --- a/net/mpls/af_mpls.c +++ b/net/mpls/af_mpls.c @@ -1533,10 +1533,14 @@ static int mpls_dev_notify(struct notifier_block *this, unsigned long event, unsigned int flags; if (event == NETDEV_REGISTER) { - /* For now just support Ethernet, IPGRE, SIT and IPIP devices */ + + /* For now just support Ethernet, IPGRE, IP6GRE, SIT and + * IPIP devices + */ if (dev->type == ARPHRD_ETHER || dev->type == ARPHRD_LOOPBACK || dev->type == ARPHRD_IPGRE || + dev->type == ARPHRD_IP6GRE || dev->type == ARPHRD_SIT || dev->type == ARPHRD_TUNNEL) { mdev = mpls_add_dev(dev); diff --git a/net/netfilter/Kconfig b/net/netfilter/Kconfig index 71709c104081..f61c306de1d0 100644 --- a/net/netfilter/Kconfig +++ b/net/netfilter/Kconfig @@ -771,13 +771,13 @@ config NETFILTER_XT_TARGET_CHECKSUM depends on NETFILTER_ADVANCED ---help--- This option adds a `CHECKSUM' target, which can be used in the iptables mangle - table. + table to work around buggy DHCP clients in virtualized environments. - You can use this target to compute and fill in the checksum in - a packet that lacks a checksum. This is particularly useful, - if you need to work around old applications such as dhcp clients, - that do not work well with checksum offloads, but don't want to disable - checksum offload in your device. + Some old DHCP clients drop packets because they are not aware + that the checksum would normally be offloaded to hardware and + thus should be considered valid. + This target can be used to fill in the checksum using iptables + when such packets are sent via a virtual network device. To compile it as a module, choose M here. If unsure, say N. diff --git a/net/netfilter/nf_conntrack_proto.c b/net/netfilter/nf_conntrack_proto.c index 9f14b0df6960..51c5d7eec0a3 100644 --- a/net/netfilter/nf_conntrack_proto.c +++ b/net/netfilter/nf_conntrack_proto.c @@ -776,9 +776,26 @@ static const struct nf_hook_ops ipv6_conntrack_ops[] = { }; #endif +static int nf_ct_tcp_fixup(struct nf_conn *ct, void *_nfproto) +{ + u8 nfproto = (unsigned long)_nfproto; + + if (nf_ct_l3num(ct) != nfproto) + return 0; + + if (nf_ct_protonum(ct) == IPPROTO_TCP && + ct->proto.tcp.state == TCP_CONNTRACK_ESTABLISHED) { + ct->proto.tcp.seen[0].td_maxwin = 0; + ct->proto.tcp.seen[1].td_maxwin = 0; + } + + return 0; +} + static int nf_ct_netns_do_get(struct net *net, u8 nfproto) { struct nf_conntrack_net *cnet = net_generic(net, nf_conntrack_net_id); + bool fixup_needed = false; int err = 0; mutex_lock(&nf_ct_proto_mutex); @@ -798,6 +815,8 @@ static int nf_ct_netns_do_get(struct net *net, u8 nfproto) ARRAY_SIZE(ipv4_conntrack_ops)); if (err) cnet->users4 = 0; + else + fixup_needed = true; break; #if IS_ENABLED(CONFIG_IPV6) case NFPROTO_IPV6: @@ -814,6 +833,8 @@ static int nf_ct_netns_do_get(struct net *net, u8 nfproto) ARRAY_SIZE(ipv6_conntrack_ops)); if (err) cnet->users6 = 0; + else + fixup_needed = true; break; #endif default: @@ -822,6 +843,11 @@ static int nf_ct_netns_do_get(struct net *net, u8 nfproto) } out_unlock: mutex_unlock(&nf_ct_proto_mutex); + + if (fixup_needed) + nf_ct_iterate_cleanup_net(net, nf_ct_tcp_fixup, + (void *)(unsigned long)nfproto, 0, 0); + return err; } diff --git a/net/netfilter/nf_conntrack_proto_dccp.c b/net/netfilter/nf_conntrack_proto_dccp.c index 8c58f96b59e7..f3f91ed2c21a 100644 --- a/net/netfilter/nf_conntrack_proto_dccp.c +++ b/net/netfilter/nf_conntrack_proto_dccp.c @@ -675,7 +675,7 @@ static int nlattr_to_dccp(struct nlattr *cda[], struct nf_conn *ct) } #endif -#if IS_ENABLED(CONFIG_NF_CT_NETLINK_TIMEOUT) +#ifdef CONFIG_NF_CONNTRACK_TIMEOUT #include <linux/netfilter/nfnetlink.h> #include <linux/netfilter/nfnetlink_cttimeout.h> @@ -697,6 +697,8 @@ static int dccp_timeout_nlattr_to_obj(struct nlattr *tb[], timeouts[i] = ntohl(nla_get_be32(tb[i])) * HZ; } } + + timeouts[CTA_TIMEOUT_DCCP_UNSPEC] = timeouts[CTA_TIMEOUT_DCCP_REQUEST]; return 0; } @@ -726,7 +728,7 @@ dccp_timeout_nla_policy[CTA_TIMEOUT_DCCP_MAX+1] = { [CTA_TIMEOUT_DCCP_CLOSING] = { .type = NLA_U32 }, [CTA_TIMEOUT_DCCP_TIMEWAIT] = { .type = NLA_U32 }, }; -#endif /* CONFIG_NF_CT_NETLINK_TIMEOUT */ +#endif /* CONFIG_NF_CONNTRACK_TIMEOUT */ #ifdef CONFIG_SYSCTL /* template, data assigned later */ @@ -827,6 +829,11 @@ static int dccp_init_net(struct net *net, u_int16_t proto) dn->dccp_timeout[CT_DCCP_CLOSEREQ] = 64 * HZ; dn->dccp_timeout[CT_DCCP_CLOSING] = 64 * HZ; dn->dccp_timeout[CT_DCCP_TIMEWAIT] = 2 * DCCP_MSL; + + /* timeouts[0] is unused, make it same as SYN_SENT so + * ->timeouts[0] contains 'new' timeout, like udp or icmp. + */ + dn->dccp_timeout[CT_DCCP_NONE] = dn->dccp_timeout[CT_DCCP_REQUEST]; } return dccp_kmemdup_sysctl_table(net, pn, dn); @@ -856,7 +863,7 @@ const struct nf_conntrack_l4proto nf_conntrack_l4proto_dccp4 = { .nlattr_to_tuple = nf_ct_port_nlattr_to_tuple, .nla_policy = nf_ct_port_nla_policy, #endif -#if IS_ENABLED(CONFIG_NF_CT_NETLINK_TIMEOUT) +#ifdef CONFIG_NF_CONNTRACK_TIMEOUT .ctnl_timeout = { .nlattr_to_obj = dccp_timeout_nlattr_to_obj, .obj_to_nlattr = dccp_timeout_obj_to_nlattr, @@ -864,7 +871,7 @@ const struct nf_conntrack_l4proto nf_conntrack_l4proto_dccp4 = { .obj_size = sizeof(unsigned int) * CT_DCCP_MAX, .nla_policy = dccp_timeout_nla_policy, }, -#endif /* CONFIG_NF_CT_NETLINK_TIMEOUT */ +#endif /* CONFIG_NF_CONNTRACK_TIMEOUT */ .init_net = dccp_init_net, .get_net_proto = dccp_get_net_proto, }; @@ -889,7 +896,7 @@ const struct nf_conntrack_l4proto nf_conntrack_l4proto_dccp6 = { .nlattr_to_tuple = nf_ct_port_nlattr_to_tuple, .nla_policy = nf_ct_port_nla_policy, #endif -#if IS_ENABLED(CONFIG_NF_CT_NETLINK_TIMEOUT) +#ifdef CONFIG_NF_CONNTRACK_TIMEOUT .ctnl_timeout = { .nlattr_to_obj = dccp_timeout_nlattr_to_obj, .obj_to_nlattr = dccp_timeout_obj_to_nlattr, @@ -897,7 +904,7 @@ const struct nf_conntrack_l4proto nf_conntrack_l4proto_dccp6 = { .obj_size = sizeof(unsigned int) * CT_DCCP_MAX, .nla_policy = dccp_timeout_nla_policy, }, -#endif /* CONFIG_NF_CT_NETLINK_TIMEOUT */ +#endif /* CONFIG_NF_CONNTRACK_TIMEOUT */ .init_net = dccp_init_net, .get_net_proto = dccp_get_net_proto, }; diff --git a/net/netfilter/nf_conntrack_proto_generic.c b/net/netfilter/nf_conntrack_proto_generic.c index ac4a0b296dcd..1df3244ecd07 100644 --- a/net/netfilter/nf_conntrack_proto_generic.c +++ b/net/netfilter/nf_conntrack_proto_generic.c @@ -70,7 +70,7 @@ static bool generic_new(struct nf_conn *ct, const struct sk_buff *skb, return ret; } -#if IS_ENABLED(CONFIG_NF_CT_NETLINK_TIMEOUT) +#ifdef CONFIG_NF_CONNTRACK_TIMEOUT #include <linux/netfilter/nfnetlink.h> #include <linux/netfilter/nfnetlink_cttimeout.h> @@ -113,7 +113,7 @@ static const struct nla_policy generic_timeout_nla_policy[CTA_TIMEOUT_GENERIC_MAX+1] = { [CTA_TIMEOUT_GENERIC_TIMEOUT] = { .type = NLA_U32 }, }; -#endif /* CONFIG_NF_CT_NETLINK_TIMEOUT */ +#endif /* CONFIG_NF_CONNTRACK_TIMEOUT */ #ifdef CONFIG_SYSCTL static struct ctl_table generic_sysctl_table[] = { @@ -164,7 +164,7 @@ const struct nf_conntrack_l4proto nf_conntrack_l4proto_generic = .pkt_to_tuple = generic_pkt_to_tuple, .packet = generic_packet, .new = generic_new, -#if IS_ENABLED(CONFIG_NF_CT_NETLINK_TIMEOUT) +#ifdef CONFIG_NF_CONNTRACK_TIMEOUT .ctnl_timeout = { .nlattr_to_obj = generic_timeout_nlattr_to_obj, .obj_to_nlattr = generic_timeout_obj_to_nlattr, @@ -172,7 +172,7 @@ const struct nf_conntrack_l4proto nf_conntrack_l4proto_generic = .obj_size = sizeof(unsigned int), .nla_policy = generic_timeout_nla_policy, }, -#endif /* CONFIG_NF_CT_NETLINK_TIMEOUT */ +#endif /* CONFIG_NF_CONNTRACK_TIMEOUT */ .init_net = generic_init_net, .get_net_proto = generic_get_net_proto, }; diff --git a/net/netfilter/nf_conntrack_proto_gre.c b/net/netfilter/nf_conntrack_proto_gre.c index d1632252bf5b..650eb4fba2c5 100644 --- a/net/netfilter/nf_conntrack_proto_gre.c +++ b/net/netfilter/nf_conntrack_proto_gre.c @@ -285,7 +285,7 @@ static void gre_destroy(struct nf_conn *ct) nf_ct_gre_keymap_destroy(master); } -#if IS_ENABLED(CONFIG_NF_CT_NETLINK_TIMEOUT) +#ifdef CONFIG_NF_CONNTRACK_TIMEOUT #include <linux/netfilter/nfnetlink.h> #include <linux/netfilter/nfnetlink_cttimeout.h> @@ -334,7 +334,7 @@ gre_timeout_nla_policy[CTA_TIMEOUT_GRE_MAX+1] = { [CTA_TIMEOUT_GRE_UNREPLIED] = { .type = NLA_U32 }, [CTA_TIMEOUT_GRE_REPLIED] = { .type = NLA_U32 }, }; -#endif /* CONFIG_NF_CT_NETLINK_TIMEOUT */ +#endif /* CONFIG_NF_CONNTRACK_TIMEOUT */ static int gre_init_net(struct net *net, u_int16_t proto) { @@ -367,7 +367,7 @@ static const struct nf_conntrack_l4proto nf_conntrack_l4proto_gre4 = { .nlattr_to_tuple = nf_ct_port_nlattr_to_tuple, .nla_policy = nf_ct_port_nla_policy, #endif -#if IS_ENABLED(CONFIG_NF_CT_NETLINK_TIMEOUT) +#ifdef CONFIG_NF_CONNTRACK_TIMEOUT .ctnl_timeout = { .nlattr_to_obj = gre_timeout_nlattr_to_obj, .obj_to_nlattr = gre_timeout_obj_to_nlattr, @@ -375,7 +375,7 @@ static const struct nf_conntrack_l4proto nf_conntrack_l4proto_gre4 = { .obj_size = sizeof(unsigned int) * GRE_CT_MAX, .nla_policy = gre_timeout_nla_policy, }, -#endif /* CONFIG_NF_CT_NETLINK_TIMEOUT */ +#endif /* CONFIG_NF_CONNTRACK_TIMEOUT */ .net_id = &proto_gre_net_id, .init_net = gre_init_net, }; diff --git a/net/netfilter/nf_conntrack_proto_icmp.c b/net/netfilter/nf_conntrack_proto_icmp.c index 036670b38282..43c7e1a217b9 100644 --- a/net/netfilter/nf_conntrack_proto_icmp.c +++ b/net/netfilter/nf_conntrack_proto_icmp.c @@ -273,7 +273,7 @@ static unsigned int icmp_nlattr_tuple_size(void) } #endif -#if IS_ENABLED(CONFIG_NF_CT_NETLINK_TIMEOUT) +#ifdef CONFIG_NF_CONNTRACK_TIMEOUT #include <linux/netfilter/nfnetlink.h> #include <linux/netfilter/nfnetlink_cttimeout.h> @@ -313,7 +313,7 @@ static const struct nla_policy icmp_timeout_nla_policy[CTA_TIMEOUT_ICMP_MAX+1] = { [CTA_TIMEOUT_ICMP_TIMEOUT] = { .type = NLA_U32 }, }; -#endif /* CONFIG_NF_CT_NETLINK_TIMEOUT */ +#endif /* CONFIG_NF_CONNTRACK_TIMEOUT */ #ifdef CONFIG_SYSCTL static struct ctl_table icmp_sysctl_table[] = { @@ -374,7 +374,7 @@ const struct nf_conntrack_l4proto nf_conntrack_l4proto_icmp = .nlattr_to_tuple = icmp_nlattr_to_tuple, .nla_policy = icmp_nla_policy, #endif -#if IS_ENABLED(CONFIG_NF_CT_NETLINK_TIMEOUT) +#ifdef CONFIG_NF_CONNTRACK_TIMEOUT .ctnl_timeout = { .nlattr_to_obj = icmp_timeout_nlattr_to_obj, .obj_to_nlattr = icmp_timeout_obj_to_nlattr, @@ -382,7 +382,7 @@ const struct nf_conntrack_l4proto nf_conntrack_l4proto_icmp = .obj_size = sizeof(unsigned int), .nla_policy = icmp_timeout_nla_policy, }, -#endif /* CONFIG_NF_CT_NETLINK_TIMEOUT */ +#endif /* CONFIG_NF_CONNTRACK_TIMEOUT */ .init_net = icmp_init_net, .get_net_proto = icmp_get_net_proto, }; diff --git a/net/netfilter/nf_conntrack_proto_icmpv6.c b/net/netfilter/nf_conntrack_proto_icmpv6.c index bed07b998a10..97e40f77d678 100644 --- a/net/netfilter/nf_conntrack_proto_icmpv6.c +++ b/net/netfilter/nf_conntrack_proto_icmpv6.c @@ -274,7 +274,7 @@ static unsigned int icmpv6_nlattr_tuple_size(void) } #endif -#if IS_ENABLED(CONFIG_NF_CT_NETLINK_TIMEOUT) +#ifdef CONFIG_NF_CONNTRACK_TIMEOUT #include <linux/netfilter/nfnetlink.h> #include <linux/netfilter/nfnetlink_cttimeout.h> @@ -314,7 +314,7 @@ static const struct nla_policy icmpv6_timeout_nla_policy[CTA_TIMEOUT_ICMPV6_MAX+1] = { [CTA_TIMEOUT_ICMPV6_TIMEOUT] = { .type = NLA_U32 }, }; -#endif /* CONFIG_NF_CT_NETLINK_TIMEOUT */ +#endif /* CONFIG_NF_CONNTRACK_TIMEOUT */ #ifdef CONFIG_SYSCTL static struct ctl_table icmpv6_sysctl_table[] = { @@ -373,7 +373,7 @@ const struct nf_conntrack_l4proto nf_conntrack_l4proto_icmpv6 = .nlattr_to_tuple = icmpv6_nlattr_to_tuple, .nla_policy = icmpv6_nla_policy, #endif -#if IS_ENABLED(CONFIG_NF_CT_NETLINK_TIMEOUT) +#ifdef CONFIG_NF_CONNTRACK_TIMEOUT .ctnl_timeout = { .nlattr_to_obj = icmpv6_timeout_nlattr_to_obj, .obj_to_nlattr = icmpv6_timeout_obj_to_nlattr, @@ -381,7 +381,7 @@ const struct nf_conntrack_l4proto nf_conntrack_l4proto_icmpv6 = .obj_size = sizeof(unsigned int), .nla_policy = icmpv6_timeout_nla_policy, }, -#endif /* CONFIG_NF_CT_NETLINK_TIMEOUT */ +#endif /* CONFIG_NF_CONNTRACK_TIMEOUT */ .init_net = icmpv6_init_net, .get_net_proto = icmpv6_get_net_proto, }; diff --git a/net/netfilter/nf_conntrack_proto_sctp.c b/net/netfilter/nf_conntrack_proto_sctp.c index 8d1e085fc14a..e4d738d34cd0 100644 --- a/net/netfilter/nf_conntrack_proto_sctp.c +++ b/net/netfilter/nf_conntrack_proto_sctp.c @@ -591,7 +591,7 @@ static int nlattr_to_sctp(struct nlattr *cda[], struct nf_conn *ct) } #endif -#if IS_ENABLED(CONFIG_NF_CT_NETLINK_TIMEOUT) +#ifdef CONFIG_NF_CONNTRACK_TIMEOUT #include <linux/netfilter/nfnetlink.h> #include <linux/netfilter/nfnetlink_cttimeout.h> @@ -613,6 +613,8 @@ static int sctp_timeout_nlattr_to_obj(struct nlattr *tb[], timeouts[i] = ntohl(nla_get_be32(tb[i])) * HZ; } } + + timeouts[CTA_TIMEOUT_SCTP_UNSPEC] = timeouts[CTA_TIMEOUT_SCTP_CLOSED]; return 0; } @@ -644,7 +646,7 @@ sctp_timeout_nla_policy[CTA_TIMEOUT_SCTP_MAX+1] = { [CTA_TIMEOUT_SCTP_HEARTBEAT_SENT] = { .type = NLA_U32 }, [CTA_TIMEOUT_SCTP_HEARTBEAT_ACKED] = { .type = NLA_U32 }, }; -#endif /* CONFIG_NF_CT_NETLINK_TIMEOUT */ +#endif /* CONFIG_NF_CONNTRACK_TIMEOUT */ #ifdef CONFIG_SYSCTL @@ -743,6 +745,11 @@ static int sctp_init_net(struct net *net, u_int16_t proto) for (i = 0; i < SCTP_CONNTRACK_MAX; i++) sn->timeouts[i] = sctp_timeouts[i]; + + /* timeouts[0] is unused, init it so ->timeouts[0] contains + * 'new' timeout, like udp or icmp. + */ + sn->timeouts[0] = sctp_timeouts[SCTP_CONNTRACK_CLOSED]; } return sctp_kmemdup_sysctl_table(pn, sn); @@ -773,7 +780,7 @@ const struct nf_conntrack_l4proto nf_conntrack_l4proto_sctp4 = { .nlattr_to_tuple = nf_ct_port_nlattr_to_tuple, .nla_policy = nf_ct_port_nla_policy, #endif -#if IS_ENABLED(CONFIG_NF_CT_NETLINK_TIMEOUT) +#ifdef CONFIG_NF_CONNTRACK_TIMEOUT .ctnl_timeout = { .nlattr_to_obj = sctp_timeout_nlattr_to_obj, .obj_to_nlattr = sctp_timeout_obj_to_nlattr, @@ -781,7 +788,7 @@ const struct nf_conntrack_l4proto nf_conntrack_l4proto_sctp4 = { .obj_size = sizeof(unsigned int) * SCTP_CONNTRACK_MAX, .nla_policy = sctp_timeout_nla_policy, }, -#endif /* CONFIG_NF_CT_NETLINK_TIMEOUT */ +#endif /* CONFIG_NF_CONNTRACK_TIMEOUT */ .init_net = sctp_init_net, .get_net_proto = sctp_get_net_proto, }; @@ -806,7 +813,8 @@ const struct nf_conntrack_l4proto nf_conntrack_l4proto_sctp6 = { .nlattr_tuple_size = nf_ct_port_nlattr_tuple_size, .nlattr_to_tuple = nf_ct_port_nlattr_to_tuple, .nla_policy = nf_ct_port_nla_policy, -#if IS_ENABLED(CONFIG_NF_CT_NETLINK_TIMEOUT) +#endif +#ifdef CONFIG_NF_CONNTRACK_TIMEOUT .ctnl_timeout = { .nlattr_to_obj = sctp_timeout_nlattr_to_obj, .obj_to_nlattr = sctp_timeout_obj_to_nlattr, @@ -814,8 +822,7 @@ const struct nf_conntrack_l4proto nf_conntrack_l4proto_sctp6 = { .obj_size = sizeof(unsigned int) * SCTP_CONNTRACK_MAX, .nla_policy = sctp_timeout_nla_policy, }, -#endif /* CONFIG_NF_CT_NETLINK_TIMEOUT */ -#endif +#endif /* CONFIG_NF_CONNTRACK_TIMEOUT */ .init_net = sctp_init_net, .get_net_proto = sctp_get_net_proto, }; diff --git a/net/netfilter/nf_conntrack_proto_tcp.c b/net/netfilter/nf_conntrack_proto_tcp.c index d80d322b9d8b..b4bdf9eda7b7 100644 --- a/net/netfilter/nf_conntrack_proto_tcp.c +++ b/net/netfilter/nf_conntrack_proto_tcp.c @@ -1279,7 +1279,7 @@ static unsigned int tcp_nlattr_tuple_size(void) } #endif -#if IS_ENABLED(CONFIG_NF_CT_NETLINK_TIMEOUT) +#ifdef CONFIG_NF_CONNTRACK_TIMEOUT #include <linux/netfilter/nfnetlink.h> #include <linux/netfilter/nfnetlink_cttimeout.h> @@ -1301,6 +1301,7 @@ static int tcp_timeout_nlattr_to_obj(struct nlattr *tb[], timeouts[TCP_CONNTRACK_SYN_SENT] = ntohl(nla_get_be32(tb[CTA_TIMEOUT_TCP_SYN_SENT]))*HZ; } + if (tb[CTA_TIMEOUT_TCP_SYN_RECV]) { timeouts[TCP_CONNTRACK_SYN_RECV] = ntohl(nla_get_be32(tb[CTA_TIMEOUT_TCP_SYN_RECV]))*HZ; @@ -1341,6 +1342,8 @@ static int tcp_timeout_nlattr_to_obj(struct nlattr *tb[], timeouts[TCP_CONNTRACK_UNACK] = ntohl(nla_get_be32(tb[CTA_TIMEOUT_TCP_UNACK]))*HZ; } + + timeouts[CTA_TIMEOUT_TCP_UNSPEC] = timeouts[CTA_TIMEOUT_TCP_SYN_SENT]; return 0; } @@ -1391,7 +1394,7 @@ static const struct nla_policy tcp_timeout_nla_policy[CTA_TIMEOUT_TCP_MAX+1] = { [CTA_TIMEOUT_TCP_RETRANS] = { .type = NLA_U32 }, [CTA_TIMEOUT_TCP_UNACK] = { .type = NLA_U32 }, }; -#endif /* CONFIG_NF_CT_NETLINK_TIMEOUT */ +#endif /* CONFIG_NF_CONNTRACK_TIMEOUT */ #ifdef CONFIG_SYSCTL static struct ctl_table tcp_sysctl_table[] = { @@ -1518,6 +1521,10 @@ static int tcp_init_net(struct net *net, u_int16_t proto) for (i = 0; i < TCP_CONNTRACK_TIMEOUT_MAX; i++) tn->timeouts[i] = tcp_timeouts[i]; + /* timeouts[0] is unused, make it same as SYN_SENT so + * ->timeouts[0] contains 'new' timeout, like udp or icmp. + */ + tn->timeouts[0] = tcp_timeouts[TCP_CONNTRACK_SYN_SENT]; tn->tcp_loose = nf_ct_tcp_loose; tn->tcp_be_liberal = nf_ct_tcp_be_liberal; tn->tcp_max_retrans = nf_ct_tcp_max_retrans; @@ -1551,7 +1558,7 @@ const struct nf_conntrack_l4proto nf_conntrack_l4proto_tcp4 = .nlattr_size = TCP_NLATTR_SIZE, .nla_policy = nf_ct_port_nla_policy, #endif -#if IS_ENABLED(CONFIG_NF_CT_NETLINK_TIMEOUT) +#ifdef CONFIG_NF_CONNTRACK_TIMEOUT .ctnl_timeout = { .nlattr_to_obj = tcp_timeout_nlattr_to_obj, .obj_to_nlattr = tcp_timeout_obj_to_nlattr, @@ -1560,7 +1567,7 @@ const struct nf_conntrack_l4proto nf_conntrack_l4proto_tcp4 = TCP_CONNTRACK_TIMEOUT_MAX, .nla_policy = tcp_timeout_nla_policy, }, -#endif /* CONFIG_NF_CT_NETLINK_TIMEOUT */ +#endif /* CONFIG_NF_CONNTRACK_TIMEOUT */ .init_net = tcp_init_net, .get_net_proto = tcp_get_net_proto, }; @@ -1586,7 +1593,7 @@ const struct nf_conntrack_l4proto nf_conntrack_l4proto_tcp6 = .nlattr_tuple_size = tcp_nlattr_tuple_size, .nla_policy = nf_ct_port_nla_policy, #endif -#if IS_ENABLED(CONFIG_NF_CT_NETLINK_TIMEOUT) +#ifdef CONFIG_NF_CONNTRACK_TIMEOUT .ctnl_timeout = { .nlattr_to_obj = tcp_timeout_nlattr_to_obj, .obj_to_nlattr = tcp_timeout_obj_to_nlattr, @@ -1595,7 +1602,7 @@ const struct nf_conntrack_l4proto nf_conntrack_l4proto_tcp6 = TCP_CONNTRACK_TIMEOUT_MAX, .nla_policy = tcp_timeout_nla_policy, }, -#endif /* CONFIG_NF_CT_NETLINK_TIMEOUT */ +#endif /* CONFIG_NF_CONNTRACK_TIMEOUT */ .init_net = tcp_init_net, .get_net_proto = tcp_get_net_proto, }; diff --git a/net/netfilter/nf_conntrack_proto_udp.c b/net/netfilter/nf_conntrack_proto_udp.c index 7a1b8988a931..3065fb8ef91b 100644 --- a/net/netfilter/nf_conntrack_proto_udp.c +++ b/net/netfilter/nf_conntrack_proto_udp.c @@ -171,7 +171,7 @@ static int udp_error(struct net *net, struct nf_conn *tmpl, struct sk_buff *skb, return NF_ACCEPT; } -#if IS_ENABLED(CONFIG_NF_CT_NETLINK_TIMEOUT) +#ifdef CONFIG_NF_CONNTRACK_TIMEOUT #include <linux/netfilter/nfnetlink.h> #include <linux/netfilter/nfnetlink_cttimeout.h> @@ -221,7 +221,7 @@ udp_timeout_nla_policy[CTA_TIMEOUT_UDP_MAX+1] = { [CTA_TIMEOUT_UDP_UNREPLIED] = { .type = NLA_U32 }, [CTA_TIMEOUT_UDP_REPLIED] = { .type = NLA_U32 }, }; -#endif /* CONFIG_NF_CT_NETLINK_TIMEOUT */ +#endif /* CONFIG_NF_CONNTRACK_TIMEOUT */ #ifdef CONFIG_SYSCTL static struct ctl_table udp_sysctl_table[] = { @@ -292,7 +292,7 @@ const struct nf_conntrack_l4proto nf_conntrack_l4proto_udp4 = .nlattr_tuple_size = nf_ct_port_nlattr_tuple_size, .nla_policy = nf_ct_port_nla_policy, #endif -#if IS_ENABLED(CONFIG_NF_CT_NETLINK_TIMEOUT) +#ifdef CONFIG_NF_CONNTRACK_TIMEOUT .ctnl_timeout = { .nlattr_to_obj = udp_timeout_nlattr_to_obj, .obj_to_nlattr = udp_timeout_obj_to_nlattr, @@ -300,7 +300,7 @@ const struct nf_conntrack_l4proto nf_conntrack_l4proto_udp4 = .obj_size = sizeof(unsigned int) * CTA_TIMEOUT_UDP_MAX, .nla_policy = udp_timeout_nla_policy, }, -#endif /* CONFIG_NF_CT_NETLINK_TIMEOUT */ +#endif /* CONFIG_NF_CONNTRACK_TIMEOUT */ .init_net = udp_init_net, .get_net_proto = udp_get_net_proto, }; @@ -321,7 +321,7 @@ const struct nf_conntrack_l4proto nf_conntrack_l4proto_udplite4 = .nlattr_tuple_size = nf_ct_port_nlattr_tuple_size, .nla_policy = nf_ct_port_nla_policy, #endif -#if IS_ENABLED(CONFIG_NF_CT_NETLINK_TIMEOUT) +#ifdef CONFIG_NF_CONNTRACK_TIMEOUT .ctnl_timeout = { .nlattr_to_obj = udp_timeout_nlattr_to_obj, .obj_to_nlattr = udp_timeout_obj_to_nlattr, @@ -329,7 +329,7 @@ const struct nf_conntrack_l4proto nf_conntrack_l4proto_udplite4 = .obj_size = sizeof(unsigned int) * CTA_TIMEOUT_UDP_MAX, .nla_policy = udp_timeout_nla_policy, }, -#endif /* CONFIG_NF_CT_NETLINK_TIMEOUT */ +#endif /* CONFIG_NF_CONNTRACK_TIMEOUT */ .init_net = udp_init_net, .get_net_proto = udp_get_net_proto, }; @@ -350,7 +350,7 @@ const struct nf_conntrack_l4proto nf_conntrack_l4proto_udp6 = .nlattr_tuple_size = nf_ct_port_nlattr_tuple_size, .nla_policy = nf_ct_port_nla_policy, #endif -#if IS_ENABLED(CONFIG_NF_CT_NETLINK_TIMEOUT) +#ifdef CONFIG_NF_CONNTRACK_TIMEOUT .ctnl_timeout = { .nlattr_to_obj = udp_timeout_nlattr_to_obj, .obj_to_nlattr = udp_timeout_obj_to_nlattr, @@ -358,7 +358,7 @@ const struct nf_conntrack_l4proto nf_conntrack_l4proto_udp6 = .obj_size = sizeof(unsigned int) * CTA_TIMEOUT_UDP_MAX, .nla_policy = udp_timeout_nla_policy, }, -#endif /* CONFIG_NF_CT_NETLINK_TIMEOUT */ +#endif /* CONFIG_NF_CONNTRACK_TIMEOUT */ .init_net = udp_init_net, .get_net_proto = udp_get_net_proto, }; @@ -379,7 +379,7 @@ const struct nf_conntrack_l4proto nf_conntrack_l4proto_udplite6 = .nlattr_tuple_size = nf_ct_port_nlattr_tuple_size, .nla_policy = nf_ct_port_nla_policy, #endif -#if IS_ENABLED(CONFIG_NF_CT_NETLINK_TIMEOUT) +#ifdef CONFIG_NF_CONNTRACK_TIMEOUT .ctnl_timeout = { .nlattr_to_obj = udp_timeout_nlattr_to_obj, .obj_to_nlattr = udp_timeout_obj_to_nlattr, @@ -387,10 +387,9 @@ const struct nf_conntrack_l4proto nf_conntrack_l4proto_udplite6 = .obj_size = sizeof(unsigned int) * CTA_TIMEOUT_UDP_MAX, .nla_policy = udp_timeout_nla_policy, }, -#endif /* CONFIG_NF_CT_NETLINK_TIMEOUT */ +#endif /* CONFIG_NF_CONNTRACK_TIMEOUT */ .init_net = udp_init_net, .get_net_proto = udp_get_net_proto, }; EXPORT_SYMBOL_GPL(nf_conntrack_l4proto_udplite6); #endif -#include <net/netfilter/nf_conntrack_timeout.h> diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 1dca5683f59f..2cfb173cd0b2 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -4637,6 +4637,7 @@ static int nft_flush_set(const struct nft_ctx *ctx, } set->ndeact++; + nft_set_elem_deactivate(ctx->net, set, elem); nft_trans_elem_set(trans) = set; nft_trans_elem(trans) = *elem; list_add_tail(&trans->list, &ctx->net->nft.commit_list); diff --git a/net/netfilter/nfnetlink_cttimeout.c b/net/netfilter/nfnetlink_cttimeout.c index d46a236cdf31..a30f8ba4b89a 100644 --- a/net/netfilter/nfnetlink_cttimeout.c +++ b/net/netfilter/nfnetlink_cttimeout.c @@ -489,8 +489,8 @@ err: return err; } -static struct ctnl_timeout * -ctnl_timeout_find_get(struct net *net, const char *name) +static struct nf_ct_timeout *ctnl_timeout_find_get(struct net *net, + const char *name) { struct ctnl_timeout *timeout, *matching = NULL; @@ -509,7 +509,7 @@ ctnl_timeout_find_get(struct net *net, const char *name) break; } err: - return matching; + return matching ? &matching->timeout : NULL; } static void ctnl_timeout_put(struct nf_ct_timeout *t) diff --git a/net/netfilter/nfnetlink_queue.c b/net/netfilter/nfnetlink_queue.c index ea4ba551abb2..43041f087eb3 100644 --- a/net/netfilter/nfnetlink_queue.c +++ b/net/netfilter/nfnetlink_queue.c @@ -233,6 +233,7 @@ static void nfqnl_reinject(struct nf_queue_entry *entry, unsigned int verdict) int err; if (verdict == NF_ACCEPT || + verdict == NF_REPEAT || verdict == NF_STOP) { rcu_read_lock(); ct_hook = rcu_dereference(nf_ct_hook); @@ -764,7 +765,7 @@ __nfqnl_enqueue_packet_gso(struct net *net, struct nfqnl_instance *queue, return ret; } - skb->next = NULL; + skb_mark_not_on_list(skb); entry_seg = nf_queue_entry_dup(entry); if (entry_seg) { diff --git a/net/netfilter/nft_ct.c b/net/netfilter/nft_ct.c index 26a8baebd072..5dd87748afa8 100644 --- a/net/netfilter/nft_ct.c +++ b/net/netfilter/nft_ct.c @@ -799,7 +799,7 @@ err: } struct nft_ct_timeout_obj { - struct nf_conn *tmpl; + struct nf_ct_timeout *timeout; u8 l4proto; }; @@ -809,26 +809,42 @@ static void nft_ct_timeout_obj_eval(struct nft_object *obj, { const struct nft_ct_timeout_obj *priv = nft_obj_data(obj); struct nf_conn *ct = (struct nf_conn *)skb_nfct(pkt->skb); - struct sk_buff *skb = pkt->skb; + struct nf_conn_timeout *timeout; + const unsigned int *values; + + if (priv->l4proto != pkt->tprot) + return; - if (ct || - priv->l4proto != pkt->tprot) + if (!ct || nf_ct_is_template(ct) || nf_ct_is_confirmed(ct)) return; - nf_ct_set(skb, priv->tmpl, IP_CT_NEW); + timeout = nf_ct_timeout_find(ct); + if (!timeout) { + timeout = nf_ct_timeout_ext_add(ct, priv->timeout, GFP_ATOMIC); + if (!timeout) { + regs->verdict.code = NF_DROP; + return; + } + } + + rcu_assign_pointer(timeout->timeout, priv->timeout); + + /* adjust the timeout as per 'new' state. ct is unconfirmed, + * so the current timestamp must not be added. + */ + values = nf_ct_timeout_data(timeout); + if (values) + nf_ct_refresh(ct, pkt->skb, values[0]); } static int nft_ct_timeout_obj_init(const struct nft_ctx *ctx, const struct nlattr * const tb[], struct nft_object *obj) { - const struct nf_conntrack_zone *zone = &nf_ct_zone_dflt; struct nft_ct_timeout_obj *priv = nft_obj_data(obj); const struct nf_conntrack_l4proto *l4proto; - struct nf_conn_timeout *timeout_ext; struct nf_ct_timeout *timeout; int l3num = ctx->family; - struct nf_conn *tmpl; __u8 l4num; int ret; @@ -863,28 +879,14 @@ static int nft_ct_timeout_obj_init(const struct nft_ctx *ctx, timeout->l3num = l3num; timeout->l4proto = l4proto; - tmpl = nf_ct_tmpl_alloc(ctx->net, zone, GFP_ATOMIC); - if (!tmpl) { - ret = -ENOMEM; - goto err_free_timeout; - } - - timeout_ext = nf_ct_timeout_ext_add(tmpl, timeout, GFP_ATOMIC); - if (!timeout_ext) { - ret = -ENOMEM; - goto err_free_tmpl; - } ret = nf_ct_netns_get(ctx->net, ctx->family); if (ret < 0) - goto err_free_tmpl; - - priv->tmpl = tmpl; + goto err_free_timeout; + priv->timeout = timeout; return 0; -err_free_tmpl: - nf_ct_tmpl_free(tmpl); err_free_timeout: kfree(timeout); err_proto_put: @@ -896,22 +898,19 @@ static void nft_ct_timeout_obj_destroy(const struct nft_ctx *ctx, struct nft_object *obj) { struct nft_ct_timeout_obj *priv = nft_obj_data(obj); - struct nf_conn_timeout *t = nf_ct_timeout_find(priv->tmpl); - struct nf_ct_timeout *timeout; + struct nf_ct_timeout *timeout = priv->timeout; - timeout = rcu_dereference_raw(t->timeout); nf_ct_untimeout(ctx->net, timeout); nf_ct_l4proto_put(timeout->l4proto); nf_ct_netns_put(ctx->net, ctx->family); - nf_ct_tmpl_free(priv->tmpl); + kfree(priv->timeout); } static int nft_ct_timeout_obj_dump(struct sk_buff *skb, struct nft_object *obj, bool reset) { const struct nft_ct_timeout_obj *priv = nft_obj_data(obj); - const struct nf_conn_timeout *t = nf_ct_timeout_find(priv->tmpl); - const struct nf_ct_timeout *timeout = rcu_dereference_raw(t->timeout); + const struct nf_ct_timeout *timeout = priv->timeout; struct nlattr *nest_params; int ret; diff --git a/net/netfilter/xt_CHECKSUM.c b/net/netfilter/xt_CHECKSUM.c index 9f4151ec3e06..6c7aa6a0a0d2 100644 --- a/net/netfilter/xt_CHECKSUM.c +++ b/net/netfilter/xt_CHECKSUM.c @@ -16,6 +16,9 @@ #include <linux/netfilter/x_tables.h> #include <linux/netfilter/xt_CHECKSUM.h> +#include <linux/netfilter_ipv4/ip_tables.h> +#include <linux/netfilter_ipv6/ip6_tables.h> + MODULE_LICENSE("GPL"); MODULE_AUTHOR("Michael S. Tsirkin <mst@redhat.com>"); MODULE_DESCRIPTION("Xtables: checksum modification"); @@ -25,7 +28,7 @@ MODULE_ALIAS("ip6t_CHECKSUM"); static unsigned int checksum_tg(struct sk_buff *skb, const struct xt_action_param *par) { - if (skb->ip_summed == CHECKSUM_PARTIAL) + if (skb->ip_summed == CHECKSUM_PARTIAL && !skb_is_gso(skb)) skb_checksum_help(skb); return XT_CONTINUE; @@ -34,6 +37,8 @@ checksum_tg(struct sk_buff *skb, const struct xt_action_param *par) static int checksum_tg_check(const struct xt_tgchk_param *par) { const struct xt_CHECKSUM_info *einfo = par->targinfo; + const struct ip6t_ip6 *i6 = par->entryinfo; + const struct ipt_ip *i4 = par->entryinfo; if (einfo->operation & ~XT_CHECKSUM_OP_FILL) { pr_info_ratelimited("unsupported CHECKSUM operation %x\n", @@ -43,6 +48,21 @@ static int checksum_tg_check(const struct xt_tgchk_param *par) if (!einfo->operation) return -EINVAL; + switch (par->family) { + case NFPROTO_IPV4: + if (i4->proto == IPPROTO_UDP && + (i4->invflags & XT_INV_PROTO) == 0) + return 0; + break; + case NFPROTO_IPV6: + if ((i6->flags & IP6T_F_PROTO) && + i6->proto == IPPROTO_UDP && + (i6->invflags & XT_INV_PROTO) == 0) + return 0; + break; + } + + pr_warn_once("CHECKSUM should be avoided. If really needed, restrict with \"-p udp\" and only use in OUTPUT\n"); return 0; } diff --git a/net/netfilter/xt_cluster.c b/net/netfilter/xt_cluster.c index dfbdbb2fc0ed..51d0c257e7a5 100644 --- a/net/netfilter/xt_cluster.c +++ b/net/netfilter/xt_cluster.c @@ -125,6 +125,7 @@ xt_cluster_mt(const struct sk_buff *skb, struct xt_action_param *par) static int xt_cluster_mt_checkentry(const struct xt_mtchk_param *par) { struct xt_cluster_match_info *info = par->matchinfo; + int ret; if (info->total_nodes > XT_CLUSTER_NODES_MAX) { pr_info_ratelimited("you have exceeded the maximum number of cluster nodes (%u > %u)\n", @@ -135,7 +136,17 @@ static int xt_cluster_mt_checkentry(const struct xt_mtchk_param *par) pr_info_ratelimited("node mask cannot exceed total number of nodes\n"); return -EDOM; } - return 0; + + ret = nf_ct_netns_get(par->net, par->family); + if (ret < 0) + pr_info_ratelimited("cannot load conntrack support for proto=%u\n", + par->family); + return ret; +} + +static void xt_cluster_mt_destroy(const struct xt_mtdtor_param *par) +{ + nf_ct_netns_put(par->net, par->family); } static struct xt_match xt_cluster_match __read_mostly = { @@ -144,6 +155,7 @@ static struct xt_match xt_cluster_match __read_mostly = { .match = xt_cluster_mt, .checkentry = xt_cluster_mt_checkentry, .matchsize = sizeof(struct xt_cluster_match_info), + .destroy = xt_cluster_mt_destroy, .me = THIS_MODULE, }; diff --git a/net/netfilter/xt_hashlimit.c b/net/netfilter/xt_hashlimit.c index 9b16402f29af..3e7d259e5d8d 100644 --- a/net/netfilter/xt_hashlimit.c +++ b/net/netfilter/xt_hashlimit.c @@ -1057,7 +1057,7 @@ static struct xt_match hashlimit_mt_reg[] __read_mostly = { static void *dl_seq_start(struct seq_file *s, loff_t *pos) __acquires(htable->lock) { - struct xt_hashlimit_htable *htable = PDE_DATA(file_inode(s->private)); + struct xt_hashlimit_htable *htable = PDE_DATA(file_inode(s->file)); unsigned int *bucket; spin_lock_bh(&htable->lock); @@ -1074,7 +1074,7 @@ static void *dl_seq_start(struct seq_file *s, loff_t *pos) static void *dl_seq_next(struct seq_file *s, void *v, loff_t *pos) { - struct xt_hashlimit_htable *htable = PDE_DATA(file_inode(s->private)); + struct xt_hashlimit_htable *htable = PDE_DATA(file_inode(s->file)); unsigned int *bucket = v; *pos = ++(*bucket); @@ -1088,7 +1088,7 @@ static void *dl_seq_next(struct seq_file *s, void *v, loff_t *pos) static void dl_seq_stop(struct seq_file *s, void *v) __releases(htable->lock) { - struct xt_hashlimit_htable *htable = PDE_DATA(file_inode(s->private)); + struct xt_hashlimit_htable *htable = PDE_DATA(file_inode(s->file)); unsigned int *bucket = v; if (!IS_ERR(bucket)) @@ -1130,7 +1130,7 @@ static void dl_seq_print(struct dsthash_ent *ent, u_int8_t family, static int dl_seq_real_show_v2(struct dsthash_ent *ent, u_int8_t family, struct seq_file *s) { - struct xt_hashlimit_htable *ht = PDE_DATA(file_inode(s->private)); + struct xt_hashlimit_htable *ht = PDE_DATA(file_inode(s->file)); spin_lock(&ent->lock); /* recalculate to show accurate numbers */ @@ -1145,7 +1145,7 @@ static int dl_seq_real_show_v2(struct dsthash_ent *ent, u_int8_t family, static int dl_seq_real_show_v1(struct dsthash_ent *ent, u_int8_t family, struct seq_file *s) { - struct xt_hashlimit_htable *ht = PDE_DATA(file_inode(s->private)); + struct xt_hashlimit_htable *ht = PDE_DATA(file_inode(s->file)); spin_lock(&ent->lock); /* recalculate to show accurate numbers */ @@ -1160,7 +1160,7 @@ static int dl_seq_real_show_v1(struct dsthash_ent *ent, u_int8_t family, static int dl_seq_real_show(struct dsthash_ent *ent, u_int8_t family, struct seq_file *s) { - struct xt_hashlimit_htable *ht = PDE_DATA(file_inode(s->private)); + struct xt_hashlimit_htable *ht = PDE_DATA(file_inode(s->file)); spin_lock(&ent->lock); /* recalculate to show accurate numbers */ @@ -1174,7 +1174,7 @@ static int dl_seq_real_show(struct dsthash_ent *ent, u_int8_t family, static int dl_seq_show_v2(struct seq_file *s, void *v) { - struct xt_hashlimit_htable *htable = PDE_DATA(file_inode(s->private)); + struct xt_hashlimit_htable *htable = PDE_DATA(file_inode(s->file)); unsigned int *bucket = (unsigned int *)v; struct dsthash_ent *ent; @@ -1188,7 +1188,7 @@ static int dl_seq_show_v2(struct seq_file *s, void *v) static int dl_seq_show_v1(struct seq_file *s, void *v) { - struct xt_hashlimit_htable *htable = PDE_DATA(file_inode(s->private)); + struct xt_hashlimit_htable *htable = PDE_DATA(file_inode(s->file)); unsigned int *bucket = v; struct dsthash_ent *ent; @@ -1202,7 +1202,7 @@ static int dl_seq_show_v1(struct seq_file *s, void *v) static int dl_seq_show(struct seq_file *s, void *v) { - struct xt_hashlimit_htable *htable = PDE_DATA(file_inode(s->private)); + struct xt_hashlimit_htable *htable = PDE_DATA(file_inode(s->file)); unsigned int *bucket = v; struct dsthash_ent *ent; diff --git a/net/netlabel/netlabel_unlabeled.c b/net/netlabel/netlabel_unlabeled.c index c070dfc0190a..c92894c3e40a 100644 --- a/net/netlabel/netlabel_unlabeled.c +++ b/net/netlabel/netlabel_unlabeled.c @@ -781,7 +781,8 @@ static int netlbl_unlabel_addrinfo_get(struct genl_info *info, { u32 addr_len; - if (info->attrs[NLBL_UNLABEL_A_IPV4ADDR]) { + if (info->attrs[NLBL_UNLABEL_A_IPV4ADDR] && + info->attrs[NLBL_UNLABEL_A_IPV4MASK]) { addr_len = nla_len(info->attrs[NLBL_UNLABEL_A_IPV4ADDR]); if (addr_len != sizeof(struct in_addr) && addr_len != nla_len(info->attrs[NLBL_UNLABEL_A_IPV4MASK])) diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index b4a29bcc33b9..e3a0538ec0be 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -574,11 +574,6 @@ static int netlink_insert(struct sock *sk, u32 portid) if (nlk_sk(sk)->bound) goto err; - err = -ENOMEM; - if (BITS_PER_LONG > 32 && - unlikely(atomic_read(&table->hash.nelems) >= UINT_MAX)) - goto err; - nlk_sk(sk)->portid = portid; sock_hold(sk); diff --git a/net/nfc/hci/core.c b/net/nfc/hci/core.c index ac8030c4bcf8..19cb2e473ea6 100644 --- a/net/nfc/hci/core.c +++ b/net/nfc/hci/core.c @@ -209,6 +209,11 @@ void nfc_hci_cmd_received(struct nfc_hci_dev *hdev, u8 pipe, u8 cmd, } create_info = (struct hci_create_pipe_resp *)skb->data; + if (create_info->pipe >= NFC_HCI_MAX_PIPES) { + status = NFC_HCI_ANY_E_NOK; + goto exit; + } + /* Save the new created pipe and bind with local gate, * the description for skb->data[3] is destination gate id * but since we received this cmd from host controller, we @@ -232,6 +237,11 @@ void nfc_hci_cmd_received(struct nfc_hci_dev *hdev, u8 pipe, u8 cmd, } delete_info = (struct hci_delete_pipe_noti *)skb->data; + if (delete_info->pipe >= NFC_HCI_MAX_PIPES) { + status = NFC_HCI_ANY_E_NOK; + goto exit; + } + hdev->pipes[delete_info->pipe].gate = NFC_HCI_INVALID_GATE; hdev->pipes[delete_info->pipe].dest_host = NFC_HCI_INVALID_HOST; break; diff --git a/net/nfc/nci/uart.c b/net/nfc/nci/uart.c index a66f102c6c01..4503937915ad 100644 --- a/net/nfc/nci/uart.c +++ b/net/nfc/nci/uart.c @@ -192,10 +192,8 @@ static void nci_uart_tty_close(struct tty_struct *tty) if (!nu) return; - if (nu->tx_skb) - kfree_skb(nu->tx_skb); - if (nu->rx_skb) - kfree_skb(nu->rx_skb); + kfree_skb(nu->tx_skb); + kfree_skb(nu->rx_skb); skb_queue_purge(&nu->tx_q); diff --git a/net/openvswitch/flow.c b/net/openvswitch/flow.c index 56b8e7167790..35966da84769 100644 --- a/net/openvswitch/flow.c +++ b/net/openvswitch/flow.c @@ -254,21 +254,18 @@ static bool icmphdr_ok(struct sk_buff *skb) static int parse_ipv6hdr(struct sk_buff *skb, struct sw_flow_key *key) { + unsigned short frag_off; + unsigned int payload_ofs = 0; unsigned int nh_ofs = skb_network_offset(skb); unsigned int nh_len; - int payload_ofs; struct ipv6hdr *nh; - uint8_t nexthdr; - __be16 frag_off; - int err; + int err, nexthdr, flags = 0; err = check_header(skb, nh_ofs + sizeof(*nh)); if (unlikely(err)) return err; nh = ipv6_hdr(skb); - nexthdr = nh->nexthdr; - payload_ofs = (u8 *)(nh + 1) - skb->data; key->ip.proto = NEXTHDR_NONE; key->ip.tos = ipv6_get_dsfield(nh); @@ -277,10 +274,9 @@ static int parse_ipv6hdr(struct sk_buff *skb, struct sw_flow_key *key) key->ipv6.addr.src = nh->saddr; key->ipv6.addr.dst = nh->daddr; - payload_ofs = ipv6_skip_exthdr(skb, payload_ofs, &nexthdr, &frag_off); - - if (frag_off) { - if (frag_off & htons(~0x7)) + nexthdr = ipv6_find_hdr(skb, &payload_ofs, -1, &frag_off, &flags); + if (flags & IP6_FH_F_FRAG) { + if (frag_off) key->ip.frag = OVS_FRAG_TYPE_LATER; else key->ip.frag = OVS_FRAG_TYPE_FIRST; @@ -288,11 +284,11 @@ static int parse_ipv6hdr(struct sk_buff *skb, struct sw_flow_key *key) key->ip.frag = OVS_FRAG_TYPE_NONE; } - /* Delayed handling of error in ipv6_skip_exthdr() as it - * always sets frag_off to a valid value which may be + /* Delayed handling of error in ipv6_find_hdr() as it + * always sets flags and frag_off to a valid value which may be * used to set key->ip.frag above. */ - if (unlikely(payload_ofs < 0)) + if (unlikely(nexthdr < 0)) return -EPROTO; nh_len = payload_ofs - nh_ofs; diff --git a/net/rds/bind.c b/net/rds/bind.c index 3ab55784b637..762d2c6788a3 100644 --- a/net/rds/bind.c +++ b/net/rds/bind.c @@ -76,11 +76,13 @@ struct rds_sock *rds_find_bound(const struct in6_addr *addr, __be16 port, struct rds_sock *rs; __rds_create_bind_key(key, addr, port, scope_id); - rs = rhashtable_lookup_fast(&bind_hash_table, key, ht_parms); + rcu_read_lock(); + rs = rhashtable_lookup(&bind_hash_table, key, ht_parms); if (rs && !sock_flag(rds_rs_to_sk(rs), SOCK_DEAD)) rds_sock_addref(rs); else rs = NULL; + rcu_read_unlock(); rdsdebug("returning rs %p for %pI6c:%u\n", rs, addr, ntohs(port)); @@ -235,6 +237,7 @@ int rds_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) goto out; } + sock_set_flag(sk, SOCK_RCU_FREE); ret = rds_add_bound(rs, binding_addr, &port, scope_id); if (ret) goto out; diff --git a/net/rds/ib.h b/net/rds/ib.h index 73427ff439f9..71ff356ee702 100644 --- a/net/rds/ib.h +++ b/net/rds/ib.h @@ -443,7 +443,7 @@ int rds_ib_send_grab_credits(struct rds_ib_connection *ic, u32 wanted, int rds_ib_xmit_atomic(struct rds_connection *conn, struct rm_atomic_op *op); /* ib_stats.c */ -DECLARE_PER_CPU(struct rds_ib_statistics, rds_ib_stats); +DECLARE_PER_CPU_SHARED_ALIGNED(struct rds_ib_statistics, rds_ib_stats); #define rds_ib_stats_inc(member) rds_stats_inc_which(rds_ib_stats, member) #define rds_ib_stats_add(member, count) \ rds_stats_add_which(rds_ib_stats, member, count) diff --git a/net/rds/recv.c b/net/rds/recv.c index 12719653188a..727639dac8a7 100644 --- a/net/rds/recv.c +++ b/net/rds/recv.c @@ -43,8 +43,6 @@ void rds_inc_init(struct rds_incoming *inc, struct rds_connection *conn, struct in6_addr *saddr) { - int i; - refcount_set(&inc->i_refcount, 1); INIT_LIST_HEAD(&inc->i_item); inc->i_conn = conn; @@ -52,8 +50,7 @@ void rds_inc_init(struct rds_incoming *inc, struct rds_connection *conn, inc->i_rdma_cookie = 0; inc->i_rx_tstamp = ktime_set(0, 0); - for (i = 0; i < RDS_RX_MAX_TRACES; i++) - inc->i_rx_lat_trace[i] = 0; + memset(inc->i_rx_lat_trace, 0, sizeof(inc->i_rx_lat_trace)); } EXPORT_SYMBOL_GPL(rds_inc_init); diff --git a/net/rxrpc/input.c b/net/rxrpc/input.c index cfdc199c6351..ee8e7e1d5c0f 100644 --- a/net/rxrpc/input.c +++ b/net/rxrpc/input.c @@ -259,7 +259,7 @@ static void rxrpc_rotate_tx_window(struct rxrpc_call *call, rxrpc_seq_t to, while (list) { skb = list; list = skb->next; - skb->next = NULL; + skb_mark_not_on_list(skb); rxrpc_free_skb(skb, rxrpc_skb_tx_freed); } } diff --git a/net/sched/act_api.c b/net/sched/act_api.c index 6f118d62c731..3c7c23421885 100644 --- a/net/sched/act_api.c +++ b/net/sched/act_api.c @@ -81,6 +81,7 @@ static void tcf_set_action_cookie(struct tc_cookie __rcu **old_cookie, static void free_tcf(struct tc_action *p) { free_percpu(p->cpu_bstats); + free_percpu(p->cpu_bstats_hw); free_percpu(p->cpu_qstats); tcf_set_action_cookie(&p->act_cookie, NULL); @@ -246,6 +247,20 @@ nla_put_failure: goto done; } +static int tcf_idr_release_unsafe(struct tc_action *p) +{ + if (atomic_read(&p->tcfa_bindcnt) > 0) + return -EPERM; + + if (refcount_dec_and_test(&p->tcfa_refcnt)) { + idr_remove(&p->idrinfo->action_idr, p->tcfa_index); + tcf_action_cleanup(p); + return ACT_P_DELETED; + } + + return 0; +} + static int tcf_del_walker(struct tcf_idrinfo *idrinfo, struct sk_buff *skb, const struct tc_action_ops *ops) { @@ -262,15 +277,19 @@ static int tcf_del_walker(struct tcf_idrinfo *idrinfo, struct sk_buff *skb, if (nla_put_string(skb, TCA_KIND, ops->kind)) goto nla_put_failure; + spin_lock(&idrinfo->lock); idr_for_each_entry_ul(idr, p, id) { - ret = __tcf_idr_release(p, false, true); + ret = tcf_idr_release_unsafe(p); if (ret == ACT_P_DELETED) { module_put(ops->owner); n_i++; } else if (ret < 0) { + spin_unlock(&idrinfo->lock); goto nla_put_failure; } } + spin_unlock(&idrinfo->lock); + if (nla_put_u32(skb, TCA_FCNT, n_i)) goto nla_put_failure; nla_nest_end(skb, nest); @@ -372,9 +391,12 @@ int tcf_idr_create(struct tc_action_net *tn, u32 index, struct nlattr *est, p->cpu_bstats = netdev_alloc_pcpu_stats(struct gnet_stats_basic_cpu); if (!p->cpu_bstats) goto err1; + p->cpu_bstats_hw = netdev_alloc_pcpu_stats(struct gnet_stats_basic_cpu); + if (!p->cpu_bstats_hw) + goto err2; p->cpu_qstats = alloc_percpu(struct gnet_stats_queue); if (!p->cpu_qstats) - goto err2; + goto err3; } spin_lock_init(&p->tcfa_lock); p->tcfa_index = index; @@ -386,15 +408,17 @@ int tcf_idr_create(struct tc_action_net *tn, u32 index, struct nlattr *est, &p->tcfa_rate_est, &p->tcfa_lock, NULL, est); if (err) - goto err3; + goto err4; } p->idrinfo = idrinfo; p->ops = ops; *a = p; return 0; -err3: +err4: free_percpu(p->cpu_qstats); +err3: + free_percpu(p->cpu_bstats_hw); err2: free_percpu(p->cpu_bstats); err1: @@ -979,6 +1003,8 @@ int tcf_action_copy_stats(struct sk_buff *skb, struct tc_action *p, goto errout; if (gnet_stats_copy_basic(NULL, &d, p->cpu_bstats, &p->tcfa_bstats) < 0 || + gnet_stats_copy_basic_hw(NULL, &d, p->cpu_bstats_hw, + &p->tcfa_bstats_hw) < 0 || gnet_stats_copy_rate_est(&d, &p->tcfa_rate_est) < 0 || gnet_stats_copy_queue(&d, p->cpu_qstats, &p->tcfa_qstats, diff --git a/net/sched/act_gact.c b/net/sched/act_gact.c index aa44d14b43c7..c89a7fa43d1b 100644 --- a/net/sched/act_gact.c +++ b/net/sched/act_gact.c @@ -157,7 +157,7 @@ static int tcf_gact_act(struct sk_buff *skb, const struct tc_action *a, } static void tcf_gact_stats_update(struct tc_action *a, u64 bytes, u32 packets, - u64 lastuse) + u64 lastuse, bool hw) { struct tcf_gact *gact = to_gact(a); int action = READ_ONCE(gact->tcf_action); @@ -168,6 +168,10 @@ static void tcf_gact_stats_update(struct tc_action *a, u64 bytes, u32 packets, if (action == TC_ACT_SHOT) this_cpu_ptr(gact->common.cpu_qstats)->drops += packets; + if (hw) + _bstats_cpu_update(this_cpu_ptr(gact->common.cpu_bstats_hw), + bytes, packets); + tm->lastuse = max_t(u64, tm->lastuse, lastuse); } diff --git a/net/sched/act_mirred.c b/net/sched/act_mirred.c index a9d64bfe5a2a..1dae5f2b358f 100644 --- a/net/sched/act_mirred.c +++ b/net/sched/act_mirred.c @@ -283,12 +283,15 @@ out: } static void tcf_stats_update(struct tc_action *a, u64 bytes, u32 packets, - u64 lastuse) + u64 lastuse, bool hw) { struct tcf_mirred *m = to_mirred(a); struct tcf_t *tm = &m->tcf_tm; _bstats_cpu_update(this_cpu_ptr(a->cpu_bstats), bytes, packets); + if (hw) + _bstats_cpu_update(this_cpu_ptr(a->cpu_bstats_hw), + bytes, packets); tm->lastuse = max_t(u64, tm->lastuse, lastuse); } diff --git a/net/sched/act_nat.c b/net/sched/act_nat.c index d98f33fdffe2..c5c1e23add77 100644 --- a/net/sched/act_nat.c +++ b/net/sched/act_nat.c @@ -256,28 +256,31 @@ static int tcf_nat_dump(struct sk_buff *skb, struct tc_action *a, unsigned char *b = skb_tail_pointer(skb); struct tcf_nat *p = to_tcf_nat(a); struct tc_nat opt = { - .old_addr = p->old_addr, - .new_addr = p->new_addr, - .mask = p->mask, - .flags = p->flags, - .index = p->tcf_index, - .action = p->tcf_action, .refcnt = refcount_read(&p->tcf_refcnt) - ref, .bindcnt = atomic_read(&p->tcf_bindcnt) - bind, }; struct tcf_t t; + spin_lock_bh(&p->tcf_lock); + opt.old_addr = p->old_addr; + opt.new_addr = p->new_addr; + opt.mask = p->mask; + opt.flags = p->flags; + opt.action = p->tcf_action; + if (nla_put(skb, TCA_NAT_PARMS, sizeof(opt), &opt)) goto nla_put_failure; tcf_tm_dump(&t, &p->tcf_tm); if (nla_put_64bit(skb, TCA_NAT_TM, sizeof(t), &t, TCA_NAT_PAD)) goto nla_put_failure; + spin_unlock_bh(&p->tcf_lock); return skb->len; nla_put_failure: + spin_unlock_bh(&p->tcf_lock); nlmsg_trim(skb, b); return -1; } diff --git a/net/sched/act_police.c b/net/sched/act_police.c index 393c7a670300..92649d2667ed 100644 --- a/net/sched/act_police.c +++ b/net/sched/act_police.c @@ -22,8 +22,7 @@ #include <net/act_api.h> #include <net/netlink.h> -struct tcf_police { - struct tc_action common; +struct tcf_police_params { int tcfp_result; u32 tcfp_ewma_rate; s64 tcfp_burst; @@ -36,6 +35,12 @@ struct tcf_police { bool rate_present; struct psched_ratecfg peak; bool peak_present; + struct rcu_head rcu; +}; + +struct tcf_police { + struct tc_action common; + struct tcf_police_params __rcu *params; }; #define to_police(pc) ((struct tcf_police *)pc) @@ -84,6 +89,7 @@ static int tcf_police_init(struct net *net, struct nlattr *nla, struct tcf_police *police; struct qdisc_rate_table *R_tab = NULL, *P_tab = NULL; struct tc_action_net *tn = net_generic(net, police_net_id); + struct tcf_police_params *new; bool exists = false; int size; @@ -110,7 +116,7 @@ static int tcf_police_init(struct net *net, struct nlattr *nla, if (!exists) { ret = tcf_idr_create(tn, parm->index, NULL, a, - &act_police_ops, bind, false); + &act_police_ops, bind, true); if (ret) { tcf_idr_cleanup(tn, parm->index); return ret; @@ -137,7 +143,8 @@ static int tcf_police_init(struct net *net, struct nlattr *nla, } if (est) { - err = gen_replace_estimator(&police->tcf_bstats, NULL, + err = gen_replace_estimator(&police->tcf_bstats, + police->common.cpu_bstats, &police->tcf_rate_est, &police->tcf_lock, NULL, est); @@ -150,50 +157,60 @@ static int tcf_police_init(struct net *net, struct nlattr *nla, goto failure; } - spin_lock_bh(&police->tcf_lock); + new = kzalloc(sizeof(*new), GFP_KERNEL); + if (unlikely(!new)) { + err = -ENOMEM; + goto failure; + } + /* No failure allowed after this point */ - police->tcfp_mtu = parm->mtu; - if (police->tcfp_mtu == 0) { - police->tcfp_mtu = ~0; + new->tcfp_mtu = parm->mtu; + if (!new->tcfp_mtu) { + new->tcfp_mtu = ~0; if (R_tab) - police->tcfp_mtu = 255 << R_tab->rate.cell_log; + new->tcfp_mtu = 255 << R_tab->rate.cell_log; } if (R_tab) { - police->rate_present = true; - psched_ratecfg_precompute(&police->rate, &R_tab->rate, 0); + new->rate_present = true; + psched_ratecfg_precompute(&new->rate, &R_tab->rate, 0); qdisc_put_rtab(R_tab); } else { - police->rate_present = false; + new->rate_present = false; } if (P_tab) { - police->peak_present = true; - psched_ratecfg_precompute(&police->peak, &P_tab->rate, 0); + new->peak_present = true; + psched_ratecfg_precompute(&new->peak, &P_tab->rate, 0); qdisc_put_rtab(P_tab); } else { - police->peak_present = false; + new->peak_present = false; } if (tb[TCA_POLICE_RESULT]) - police->tcfp_result = nla_get_u32(tb[TCA_POLICE_RESULT]); - police->tcfp_burst = PSCHED_TICKS2NS(parm->burst); - police->tcfp_toks = police->tcfp_burst; - if (police->peak_present) { - police->tcfp_mtu_ptoks = (s64) psched_l2t_ns(&police->peak, - police->tcfp_mtu); - police->tcfp_ptoks = police->tcfp_mtu_ptoks; + new->tcfp_result = nla_get_u32(tb[TCA_POLICE_RESULT]); + new->tcfp_burst = PSCHED_TICKS2NS(parm->burst); + new->tcfp_toks = new->tcfp_burst; + if (new->peak_present) { + new->tcfp_mtu_ptoks = (s64)psched_l2t_ns(&new->peak, + new->tcfp_mtu); + new->tcfp_ptoks = new->tcfp_mtu_ptoks; } - police->tcf_action = parm->action; if (tb[TCA_POLICE_AVRATE]) - police->tcfp_ewma_rate = nla_get_u32(tb[TCA_POLICE_AVRATE]); + new->tcfp_ewma_rate = nla_get_u32(tb[TCA_POLICE_AVRATE]); + spin_lock_bh(&police->tcf_lock); + new->tcfp_t_c = ktime_get_ns(); + police->tcf_action = parm->action; + rcu_swap_protected(police->params, + new, + lockdep_is_held(&police->tcf_lock)); spin_unlock_bh(&police->tcf_lock); - if (ret != ACT_P_CREATED) - return ret; - police->tcfp_t_c = ktime_get_ns(); - tcf_idr_insert(tn, *a); + if (new) + kfree_rcu(new, rcu); + if (ret == ACT_P_CREATED) + tcf_idr_insert(tn, *a); return ret; failure: @@ -207,64 +224,69 @@ static int tcf_police_act(struct sk_buff *skb, const struct tc_action *a, struct tcf_result *res) { struct tcf_police *police = to_police(a); - s64 now; - s64 toks; - s64 ptoks = 0; - - spin_lock(&police->tcf_lock); + struct tcf_police_params *p; + s64 now, toks, ptoks = 0; + int ret; - bstats_update(&police->tcf_bstats, skb); tcf_lastuse_update(&police->tcf_tm); + bstats_cpu_update(this_cpu_ptr(police->common.cpu_bstats), skb); - if (police->tcfp_ewma_rate) { + ret = READ_ONCE(police->tcf_action); + p = rcu_dereference_bh(police->params); + + if (p->tcfp_ewma_rate) { struct gnet_stats_rate_est64 sample; if (!gen_estimator_read(&police->tcf_rate_est, &sample) || - sample.bps >= police->tcfp_ewma_rate) { - police->tcf_qstats.overlimits++; - if (police->tcf_action == TC_ACT_SHOT) - police->tcf_qstats.drops++; - spin_unlock(&police->tcf_lock); - return police->tcf_action; - } + sample.bps >= p->tcfp_ewma_rate) + goto inc_overlimits; } - if (qdisc_pkt_len(skb) <= police->tcfp_mtu) { - if (!police->rate_present) { - spin_unlock(&police->tcf_lock); - return police->tcfp_result; + if (qdisc_pkt_len(skb) <= p->tcfp_mtu) { + if (!p->rate_present) { + ret = p->tcfp_result; + goto end; } now = ktime_get_ns(); - toks = min_t(s64, now - police->tcfp_t_c, - police->tcfp_burst); - if (police->peak_present) { - ptoks = toks + police->tcfp_ptoks; - if (ptoks > police->tcfp_mtu_ptoks) - ptoks = police->tcfp_mtu_ptoks; - ptoks -= (s64) psched_l2t_ns(&police->peak, - qdisc_pkt_len(skb)); + toks = min_t(s64, now - p->tcfp_t_c, p->tcfp_burst); + if (p->peak_present) { + ptoks = toks + p->tcfp_ptoks; + if (ptoks > p->tcfp_mtu_ptoks) + ptoks = p->tcfp_mtu_ptoks; + ptoks -= (s64)psched_l2t_ns(&p->peak, + qdisc_pkt_len(skb)); } - toks += police->tcfp_toks; - if (toks > police->tcfp_burst) - toks = police->tcfp_burst; - toks -= (s64) psched_l2t_ns(&police->rate, qdisc_pkt_len(skb)); + toks += p->tcfp_toks; + if (toks > p->tcfp_burst) + toks = p->tcfp_burst; + toks -= (s64)psched_l2t_ns(&p->rate, qdisc_pkt_len(skb)); if ((toks|ptoks) >= 0) { - police->tcfp_t_c = now; - police->tcfp_toks = toks; - police->tcfp_ptoks = ptoks; - if (police->tcfp_result == TC_ACT_SHOT) - police->tcf_qstats.drops++; - spin_unlock(&police->tcf_lock); - return police->tcfp_result; + p->tcfp_t_c = now; + p->tcfp_toks = toks; + p->tcfp_ptoks = ptoks; + ret = p->tcfp_result; + goto inc_drops; } } - police->tcf_qstats.overlimits++; - if (police->tcf_action == TC_ACT_SHOT) - police->tcf_qstats.drops++; - spin_unlock(&police->tcf_lock); - return police->tcf_action; +inc_overlimits: + qstats_overlimit_inc(this_cpu_ptr(police->common.cpu_qstats)); +inc_drops: + if (ret == TC_ACT_SHOT) + qstats_drop_inc(this_cpu_ptr(police->common.cpu_qstats)); +end: + return ret; +} + +static void tcf_police_cleanup(struct tc_action *a) +{ + struct tcf_police *police = to_police(a); + struct tcf_police_params *p; + + p = rcu_dereference_protected(police->params, 1); + if (p) + kfree_rcu(p, rcu); } static int tcf_police_dump(struct sk_buff *skb, struct tc_action *a, @@ -272,6 +294,7 @@ static int tcf_police_dump(struct sk_buff *skb, struct tc_action *a, { unsigned char *b = skb_tail_pointer(skb); struct tcf_police *police = to_police(a); + struct tcf_police_params *p; struct tc_police opt = { .index = police->tcf_index, .refcnt = refcount_read(&police->tcf_refcnt) - ref, @@ -281,19 +304,21 @@ static int tcf_police_dump(struct sk_buff *skb, struct tc_action *a, spin_lock_bh(&police->tcf_lock); opt.action = police->tcf_action; - opt.mtu = police->tcfp_mtu; - opt.burst = PSCHED_NS2TICKS(police->tcfp_burst); - if (police->rate_present) - psched_ratecfg_getrate(&opt.rate, &police->rate); - if (police->peak_present) - psched_ratecfg_getrate(&opt.peakrate, &police->peak); + p = rcu_dereference_protected(police->params, + lockdep_is_held(&police->tcf_lock)); + opt.mtu = p->tcfp_mtu; + opt.burst = PSCHED_NS2TICKS(p->tcfp_burst); + if (p->rate_present) + psched_ratecfg_getrate(&opt.rate, &p->rate); + if (p->peak_present) + psched_ratecfg_getrate(&opt.peakrate, &p->peak); if (nla_put(skb, TCA_POLICE_TBF, sizeof(opt), &opt)) goto nla_put_failure; - if (police->tcfp_result && - nla_put_u32(skb, TCA_POLICE_RESULT, police->tcfp_result)) + if (p->tcfp_result && + nla_put_u32(skb, TCA_POLICE_RESULT, p->tcfp_result)) goto nla_put_failure; - if (police->tcfp_ewma_rate && - nla_put_u32(skb, TCA_POLICE_AVRATE, police->tcfp_ewma_rate)) + if (p->tcfp_ewma_rate && + nla_put_u32(skb, TCA_POLICE_AVRATE, p->tcfp_ewma_rate)) goto nla_put_failure; t.install = jiffies_to_clock_t(jiffies - police->tcf_tm.install); @@ -332,6 +357,7 @@ static struct tc_action_ops act_police_ops = { .init = tcf_police_init, .walk = tcf_police_walker, .lookup = tcf_police_search, + .cleanup = tcf_police_cleanup, .size = sizeof(struct tcf_police), }; diff --git a/net/sched/act_sample.c b/net/sched/act_sample.c index 83a133375d6d..1a0c682fd734 100644 --- a/net/sched/act_sample.c +++ b/net/sched/act_sample.c @@ -69,7 +69,7 @@ static int tcf_sample_init(struct net *net, struct nlattr *nla, if (!exists) { ret = tcf_idr_create(tn, parm->index, est, a, - &act_sample_ops, bind, false); + &act_sample_ops, bind, true); if (ret) { tcf_idr_cleanup(tn, parm->index); return ret; diff --git a/net/sched/act_skbedit.c b/net/sched/act_skbedit.c index b6263704ea57..64dba3708fce 100644 --- a/net/sched/act_skbedit.c +++ b/net/sched/act_skbedit.c @@ -99,7 +99,7 @@ static int tcf_skbedit_init(struct net *net, struct nlattr *nla, struct netlink_ext_ack *extack) { struct tc_action_net *tn = net_generic(net, skbedit_net_id); - struct tcf_skbedit_params *params_old, *params_new; + struct tcf_skbedit_params *params_new; struct nlattr *tb[TCA_SKBEDIT_MAX + 1]; struct tc_skbedit *parm; struct tcf_skbedit *d; @@ -187,8 +187,6 @@ static int tcf_skbedit_init(struct net *net, struct nlattr *nla, } } - ASSERT_RTNL(); - params_new = kzalloc(sizeof(*params_new), GFP_KERNEL); if (unlikely(!params_new)) { if (ret == ACT_P_CREATED) @@ -210,11 +208,13 @@ static int tcf_skbedit_init(struct net *net, struct nlattr *nla, if (flags & SKBEDIT_F_MASK) params_new->mask = *mask; + spin_lock_bh(&d->tcf_lock); d->tcf_action = parm->action; - params_old = rtnl_dereference(d->params); - rcu_assign_pointer(d->params, params_new); - if (params_old) - kfree_rcu(params_old, rcu); + rcu_swap_protected(d->params, params_new, + lockdep_is_held(&d->tcf_lock)); + spin_unlock_bh(&d->tcf_lock); + if (params_new) + kfree_rcu(params_new, rcu); if (ret == ACT_P_CREATED) tcf_idr_insert(tn, *a); @@ -231,12 +231,14 @@ static int tcf_skbedit_dump(struct sk_buff *skb, struct tc_action *a, .index = d->tcf_index, .refcnt = refcount_read(&d->tcf_refcnt) - ref, .bindcnt = atomic_read(&d->tcf_bindcnt) - bind, - .action = d->tcf_action, }; u64 pure_flags = 0; struct tcf_t t; - params = rtnl_dereference(d->params); + spin_lock_bh(&d->tcf_lock); + params = rcu_dereference_protected(d->params, + lockdep_is_held(&d->tcf_lock)); + opt.action = d->tcf_action; if (nla_put(skb, TCA_SKBEDIT_PARMS, sizeof(opt), &opt)) goto nla_put_failure; @@ -264,9 +266,12 @@ static int tcf_skbedit_dump(struct sk_buff *skb, struct tc_action *a, tcf_tm_dump(&t, &d->tcf_tm); if (nla_put_64bit(skb, TCA_SKBEDIT_TM, sizeof(t), &t, TCA_SKBEDIT_PAD)) goto nla_put_failure; + spin_unlock_bh(&d->tcf_lock); + return skb->len; nla_put_failure: + spin_unlock_bh(&d->tcf_lock); nlmsg_trim(skb, b); return -1; } diff --git a/net/sched/act_tunnel_key.c b/net/sched/act_tunnel_key.c index 6d95b6919d9d..4cca8f274662 100644 --- a/net/sched/act_tunnel_key.c +++ b/net/sched/act_tunnel_key.c @@ -317,7 +317,7 @@ static int tunnel_key_init(struct net *net, struct nlattr *nla, &metadata->u.tun_info, opts_len, extack); if (ret < 0) - goto err_out; + goto release_tun_meta; } metadata->u.tun_info.mode |= IP_TUNNEL_INFO_TX; @@ -333,23 +333,24 @@ static int tunnel_key_init(struct net *net, struct nlattr *nla, &act_tunnel_key_ops, bind, true); if (ret) { NL_SET_ERR_MSG(extack, "Cannot create TC IDR"); - goto err_out; + goto release_tun_meta; } ret = ACT_P_CREATED; } else if (!ovr) { - tcf_idr_release(*a, bind); NL_SET_ERR_MSG(extack, "TC IDR already exists"); - return -EEXIST; + ret = -EEXIST; + goto release_tun_meta; } t = to_tunnel_key(*a); params_new = kzalloc(sizeof(*params_new), GFP_KERNEL); if (unlikely(!params_new)) { - tcf_idr_release(*a, bind); NL_SET_ERR_MSG(extack, "Cannot allocate tunnel key parameters"); - return -ENOMEM; + ret = -ENOMEM; + exists = true; + goto release_tun_meta; } params_new->tcft_action = parm->t_action; params_new->tcft_enc_metadata = metadata; @@ -367,6 +368,9 @@ static int tunnel_key_init(struct net *net, struct nlattr *nla, return ret; +release_tun_meta: + dst_release(&metadata->dst); + err_out: if (exists) tcf_idr_release(*a, bind); @@ -408,8 +412,10 @@ static int tunnel_key_geneve_opts_dump(struct sk_buff *skb, nla_put_u8(skb, TCA_TUNNEL_KEY_ENC_OPT_GENEVE_TYPE, opt->type) || nla_put(skb, TCA_TUNNEL_KEY_ENC_OPT_GENEVE_DATA, - opt->length * 4, opt + 1)) + opt->length * 4, opt + 1)) { + nla_nest_cancel(skb, start); return -EMSGSIZE; + } len -= sizeof(struct geneve_opt) + opt->length * 4; src += sizeof(struct geneve_opt) + opt->length * 4; @@ -423,7 +429,7 @@ static int tunnel_key_opts_dump(struct sk_buff *skb, const struct ip_tunnel_info *info) { struct nlattr *start; - int err; + int err = -EINVAL; if (!info->options_len) return 0; @@ -435,9 +441,11 @@ static int tunnel_key_opts_dump(struct sk_buff *skb, if (info->key.tun_flags & TUNNEL_GENEVE_OPT) { err = tunnel_key_geneve_opts_dump(skb, info); if (err) - return err; + goto err_out; } else { - return -EINVAL; +err_out: + nla_nest_cancel(skb, start); + return err; } nla_nest_end(skb, start); diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c index 1a67af8a6e8c..3de47e99b788 100644 --- a/net/sched/cls_api.c +++ b/net/sched/cls_api.c @@ -240,8 +240,8 @@ static void tcf_chain_destroy(struct tcf_chain *chain) if (!chain->index) block->chain0.chain = NULL; kfree(chain); - if (list_empty(&block->chain_list) && block->refcnt == 0) - kfree(block); + if (list_empty(&block->chain_list) && !refcount_read(&block->refcnt)) + kfree_rcu(block, rcu); } static void tcf_chain_hold(struct tcf_chain *chain) @@ -473,6 +473,7 @@ tcf_chain0_head_change_cb_del(struct tcf_block *block, } struct tcf_net { + spinlock_t idr_lock; /* Protects idr */ struct idr idr; }; @@ -482,16 +483,25 @@ static int tcf_block_insert(struct tcf_block *block, struct net *net, struct netlink_ext_ack *extack) { struct tcf_net *tn = net_generic(net, tcf_net_id); + int err; + + idr_preload(GFP_KERNEL); + spin_lock(&tn->idr_lock); + err = idr_alloc_u32(&tn->idr, block, &block->index, block->index, + GFP_NOWAIT); + spin_unlock(&tn->idr_lock); + idr_preload_end(); - return idr_alloc_u32(&tn->idr, block, &block->index, block->index, - GFP_KERNEL); + return err; } static void tcf_block_remove(struct tcf_block *block, struct net *net) { struct tcf_net *tn = net_generic(net, tcf_net_id); + spin_lock(&tn->idr_lock); idr_remove(&tn->idr, block->index); + spin_unlock(&tn->idr_lock); } static struct tcf_block *tcf_block_create(struct net *net, struct Qdisc *q, @@ -510,7 +520,7 @@ static struct tcf_block *tcf_block_create(struct net *net, struct Qdisc *q, INIT_LIST_HEAD(&block->owner_list); INIT_LIST_HEAD(&block->chain0.filter_chain_list); - block->refcnt = 1; + refcount_set(&block->refcnt, 1); block->net = net; block->index = block_index; @@ -527,6 +537,78 @@ static struct tcf_block *tcf_block_lookup(struct net *net, u32 block_index) return idr_find(&tn->idr, block_index); } +static struct tcf_block *tcf_block_refcnt_get(struct net *net, u32 block_index) +{ + struct tcf_block *block; + + rcu_read_lock(); + block = tcf_block_lookup(net, block_index); + if (block && !refcount_inc_not_zero(&block->refcnt)) + block = NULL; + rcu_read_unlock(); + + return block; +} + +static void tcf_block_flush_all_chains(struct tcf_block *block) +{ + struct tcf_chain *chain; + + /* Hold a refcnt for all chains, so that they don't disappear + * while we are iterating. + */ + list_for_each_entry(chain, &block->chain_list, list) + tcf_chain_hold(chain); + + list_for_each_entry(chain, &block->chain_list, list) + tcf_chain_flush(chain); +} + +static void tcf_block_put_all_chains(struct tcf_block *block) +{ + struct tcf_chain *chain, *tmp; + + /* At this point, all the chains should have refcnt >= 1. */ + list_for_each_entry_safe(chain, tmp, &block->chain_list, list) { + tcf_chain_put_explicitly_created(chain); + tcf_chain_put(chain); + } +} + +static void __tcf_block_put(struct tcf_block *block, struct Qdisc *q, + struct tcf_block_ext_info *ei) +{ + if (refcount_dec_and_test(&block->refcnt)) { + /* Flushing/putting all chains will cause the block to be + * deallocated when last chain is freed. However, if chain_list + * is empty, block has to be manually deallocated. After block + * reference counter reached 0, it is no longer possible to + * increment it or add new chains to block. + */ + bool free_block = list_empty(&block->chain_list); + + if (tcf_block_shared(block)) + tcf_block_remove(block, block->net); + if (!free_block) + tcf_block_flush_all_chains(block); + + if (q) + tcf_block_offload_unbind(block, q, ei); + + if (free_block) + kfree_rcu(block, rcu); + else + tcf_block_put_all_chains(block); + } else if (q) { + tcf_block_offload_unbind(block, q, ei); + } +} + +static void tcf_block_refcnt_put(struct tcf_block *block) +{ + __tcf_block_put(block, NULL, NULL); +} + /* Find tcf block. * Set q, parent, cl when appropriate. */ @@ -537,9 +619,10 @@ static struct tcf_block *tcf_block_find(struct net *net, struct Qdisc **q, struct netlink_ext_ack *extack) { struct tcf_block *block; + int err = 0; if (ifindex == TCM_IFINDEX_MAGIC_BLOCK) { - block = tcf_block_lookup(net, block_index); + block = tcf_block_refcnt_get(net, block_index); if (!block) { NL_SET_ERR_MSG(extack, "Block of given index was not found"); return ERR_PTR(-EINVAL); @@ -548,55 +631,104 @@ static struct tcf_block *tcf_block_find(struct net *net, struct Qdisc **q, const struct Qdisc_class_ops *cops; struct net_device *dev; + rcu_read_lock(); + /* Find link */ - dev = __dev_get_by_index(net, ifindex); - if (!dev) + dev = dev_get_by_index_rcu(net, ifindex); + if (!dev) { + rcu_read_unlock(); return ERR_PTR(-ENODEV); + } /* Find qdisc */ if (!*parent) { *q = dev->qdisc; *parent = (*q)->handle; } else { - *q = qdisc_lookup(dev, TC_H_MAJ(*parent)); + *q = qdisc_lookup_rcu(dev, TC_H_MAJ(*parent)); if (!*q) { NL_SET_ERR_MSG(extack, "Parent Qdisc doesn't exists"); - return ERR_PTR(-EINVAL); + err = -EINVAL; + goto errout_rcu; } } + *q = qdisc_refcount_inc_nz(*q); + if (!*q) { + NL_SET_ERR_MSG(extack, "Parent Qdisc doesn't exists"); + err = -EINVAL; + goto errout_rcu; + } + /* Is it classful? */ cops = (*q)->ops->cl_ops; if (!cops) { NL_SET_ERR_MSG(extack, "Qdisc not classful"); - return ERR_PTR(-EINVAL); + err = -EINVAL; + goto errout_rcu; } if (!cops->tcf_block) { NL_SET_ERR_MSG(extack, "Class doesn't support blocks"); - return ERR_PTR(-EOPNOTSUPP); + err = -EOPNOTSUPP; + goto errout_rcu; } + /* At this point we know that qdisc is not noop_qdisc, + * which means that qdisc holds a reference to net_device + * and we hold a reference to qdisc, so it is safe to release + * rcu read lock. + */ + rcu_read_unlock(); + /* Do we search for filter, attached to class? */ if (TC_H_MIN(*parent)) { *cl = cops->find(*q, *parent); if (*cl == 0) { NL_SET_ERR_MSG(extack, "Specified class doesn't exist"); - return ERR_PTR(-ENOENT); + err = -ENOENT; + goto errout_qdisc; } } /* And the last stroke */ block = cops->tcf_block(*q, *cl, extack); - if (!block) - return ERR_PTR(-EINVAL); + if (!block) { + err = -EINVAL; + goto errout_qdisc; + } if (tcf_block_shared(block)) { NL_SET_ERR_MSG(extack, "This filter block is shared. Please use the block index to manipulate the filters"); - return ERR_PTR(-EOPNOTSUPP); + err = -EOPNOTSUPP; + goto errout_qdisc; } + + /* Always take reference to block in order to support execution + * of rules update path of cls API without rtnl lock. Caller + * must release block when it is finished using it. 'if' block + * of this conditional obtain reference to block by calling + * tcf_block_refcnt_get(). + */ + refcount_inc(&block->refcnt); } return block; + +errout_rcu: + rcu_read_unlock(); +errout_qdisc: + if (*q) + qdisc_put(*q); + return ERR_PTR(err); +} + +static void tcf_block_release(struct Qdisc *q, struct tcf_block *block) +{ + if (!IS_ERR_OR_NULL(block)) + tcf_block_refcnt_put(block); + + if (q) + qdisc_put(q); } struct tcf_block_owner_item { @@ -664,21 +796,16 @@ int tcf_block_get_ext(struct tcf_block **p_block, struct Qdisc *q, { struct net *net = qdisc_net(q); struct tcf_block *block = NULL; - bool created = false; int err; - if (ei->block_index) { + if (ei->block_index) /* block_index not 0 means the shared block is requested */ - block = tcf_block_lookup(net, ei->block_index); - if (block) - block->refcnt++; - } + block = tcf_block_refcnt_get(net, ei->block_index); if (!block) { block = tcf_block_create(net, q, ei->block_index, extack); if (IS_ERR(block)) return PTR_ERR(block); - created = true; if (tcf_block_shared(block)) { err = tcf_block_insert(block, net, extack); if (err) @@ -708,14 +835,8 @@ err_block_offload_bind: err_chain0_head_change_cb_add: tcf_block_owner_del(block, q, ei->binder_type); err_block_owner_add: - if (created) { - if (tcf_block_shared(block)) - tcf_block_remove(block, net); err_block_insert: - kfree(block); - } else { - block->refcnt--; - } + tcf_block_refcnt_put(block); return err; } EXPORT_SYMBOL(tcf_block_get_ext); @@ -747,42 +868,12 @@ EXPORT_SYMBOL(tcf_block_get); void tcf_block_put_ext(struct tcf_block *block, struct Qdisc *q, struct tcf_block_ext_info *ei) { - struct tcf_chain *chain, *tmp; - if (!block) return; tcf_chain0_head_change_cb_del(block, ei); tcf_block_owner_del(block, q, ei->binder_type); - if (block->refcnt == 1) { - if (tcf_block_shared(block)) - tcf_block_remove(block, block->net); - - /* Hold a refcnt for all chains, so that they don't disappear - * while we are iterating. - */ - list_for_each_entry(chain, &block->chain_list, list) - tcf_chain_hold(chain); - - list_for_each_entry(chain, &block->chain_list, list) - tcf_chain_flush(chain); - } - - tcf_block_offload_unbind(block, q, ei); - - if (block->refcnt == 1) { - /* At this point, all the chains should have refcnt >= 1. */ - list_for_each_entry_safe(chain, tmp, &block->chain_list, list) { - tcf_chain_put_explicitly_created(chain); - tcf_chain_put(chain); - } - - block->refcnt--; - if (list_empty(&block->chain_list)) - kfree(block); - } else { - block->refcnt--; - } + __tcf_block_put(block, q, ei); } EXPORT_SYMBOL(tcf_block_put_ext); @@ -1332,6 +1423,7 @@ replay: errout: if (chain) tcf_chain_put(chain); + tcf_block_release(q, block); if (err == -EAGAIN) /* Replay the request. */ goto replay; @@ -1453,6 +1545,7 @@ static int tc_del_tfilter(struct sk_buff *skb, struct nlmsghdr *n, errout: if (chain) tcf_chain_put(chain); + tcf_block_release(q, block); return err; } @@ -1538,6 +1631,7 @@ static int tc_get_tfilter(struct sk_buff *skb, struct nlmsghdr *n, errout: if (chain) tcf_chain_put(chain); + tcf_block_release(q, block); return err; } @@ -1636,7 +1730,7 @@ static int tc_dump_tfilter(struct sk_buff *skb, struct netlink_callback *cb) return err; if (tcm->tcm_ifindex == TCM_IFINDEX_MAGIC_BLOCK) { - block = tcf_block_lookup(net, tcm->tcm_block_index); + block = tcf_block_refcnt_get(net, tcm->tcm_block_index); if (!block) goto out; /* If we work with block index, q is NULL and parent value @@ -1695,6 +1789,8 @@ static int tc_dump_tfilter(struct sk_buff *skb, struct netlink_callback *cb) } } + if (tcm->tcm_ifindex == TCM_IFINDEX_MAGIC_BLOCK) + tcf_block_refcnt_put(block); cb->args[0] = index; out: @@ -1854,7 +1950,8 @@ replay: chain_index = tca[TCA_CHAIN] ? nla_get_u32(tca[TCA_CHAIN]) : 0; if (chain_index > TC_ACT_EXT_VAL_MASK) { NL_SET_ERR_MSG(extack, "Specified chain index exceeds upper limit"); - return -EINVAL; + err = -EINVAL; + goto errout_block; } chain = tcf_chain_lookup(block, chain_index); if (n->nlmsg_type == RTM_NEWCHAIN) { @@ -1866,23 +1963,27 @@ replay: tcf_chain_hold(chain); } else { NL_SET_ERR_MSG(extack, "Filter chain already exists"); - return -EEXIST; + err = -EEXIST; + goto errout_block; } } else { if (!(n->nlmsg_flags & NLM_F_CREATE)) { NL_SET_ERR_MSG(extack, "Need both RTM_NEWCHAIN and NLM_F_CREATE to create a new chain"); - return -ENOENT; + err = -ENOENT; + goto errout_block; } chain = tcf_chain_create(block, chain_index); if (!chain) { NL_SET_ERR_MSG(extack, "Failed to create filter chain"); - return -ENOMEM; + err = -ENOMEM; + goto errout_block; } } } else { if (!chain || tcf_chain_held_by_acts_only(chain)) { NL_SET_ERR_MSG(extack, "Cannot find specified filter chain"); - return -EINVAL; + err = -EINVAL; + goto errout_block; } tcf_chain_hold(chain); } @@ -1902,6 +2003,8 @@ replay: RTM_NEWCHAIN, false); break; case RTM_DELCHAIN: + tfilter_notify_chain(net, skb, block, q, parent, n, + chain, RTM_DELTFILTER); /* Flush the chain first as the user requested chain removal. */ tcf_chain_flush(chain); /* In case the chain was successfully deleted, put a reference @@ -1924,6 +2027,8 @@ replay: errout: tcf_chain_put(chain); +errout_block: + tcf_block_release(q, block); if (err == -EAGAIN) /* Replay the request. */ goto replay; @@ -1952,7 +2057,7 @@ static int tc_dump_chain(struct sk_buff *skb, struct netlink_callback *cb) return err; if (tcm->tcm_ifindex == TCM_IFINDEX_MAGIC_BLOCK) { - block = tcf_block_lookup(net, tcm->tcm_block_index); + block = tcf_block_refcnt_get(net, tcm->tcm_block_index); if (!block) goto out; /* If we work with block index, q is NULL and parent value @@ -2019,6 +2124,8 @@ static int tc_dump_chain(struct sk_buff *skb, struct netlink_callback *cb) index++; } + if (tcm->tcm_ifindex == TCM_IFINDEX_MAGIC_BLOCK) + tcf_block_refcnt_put(block); cb->args[0] = index; out: @@ -2211,6 +2318,7 @@ static __net_init int tcf_net_init(struct net *net) { struct tcf_net *tn = net_generic(net, tcf_net_id); + spin_lock_init(&tn->idr_lock); idr_init(&tn->idr); return 0; } diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c index 6fd9bdd93796..92dd5071a708 100644 --- a/net/sched/cls_flower.c +++ b/net/sched/cls_flower.c @@ -79,6 +79,7 @@ struct fl_flow_tmplt { struct fl_flow_key mask; struct flow_dissector dissector; struct tcf_chain *chain; + struct rcu_work rwork; }; struct cls_fl_head { @@ -98,7 +99,7 @@ struct cls_fl_filter { struct list_head list; u32 handle; u32 flags; - unsigned int in_hw_count; + u32 in_hw_count; struct rcu_work rwork; struct net_device *hw_dev; }; @@ -993,7 +994,7 @@ static int fl_init_mask_hashtable(struct fl_flow_mask *mask) } #define FL_KEY_MEMBER_OFFSET(member) offsetof(struct fl_flow_key, member) -#define FL_KEY_MEMBER_SIZE(member) (sizeof(((struct fl_flow_key *) 0)->member)) +#define FL_KEY_MEMBER_SIZE(member) FIELD_SIZEOF(struct fl_flow_key, member) #define FL_KEY_IS_MASKED(mask, member) \ memchr_inv(((char *)mask) + FL_KEY_MEMBER_OFFSET(member), \ @@ -1437,14 +1438,22 @@ errout_tb: return ERR_PTR(err); } -static void fl_tmplt_destroy(void *tmplt_priv) +static void fl_tmplt_destroy_work(struct work_struct *work) { - struct fl_flow_tmplt *tmplt = tmplt_priv; + struct fl_flow_tmplt *tmplt = container_of(to_rcu_work(work), + struct fl_flow_tmplt, rwork); fl_hw_destroy_tmplt(tmplt->chain, tmplt); kfree(tmplt); } +static void fl_tmplt_destroy(void *tmplt_priv) +{ + struct fl_flow_tmplt *tmplt = tmplt_priv; + + tcf_queue_work(&tmplt->rwork, fl_tmplt_destroy_work); +} + static int fl_dump_key_val(struct sk_buff *skb, void *val, int val_type, void *mask, int mask_type, int len) @@ -1880,6 +1889,9 @@ static int fl_dump(struct net *net, struct tcf_proto *tp, void *fh, if (f->flags && nla_put_u32(skb, TCA_FLOWER_FLAGS, f->flags)) goto nla_put_failure; + if (nla_put_u32(skb, TCA_FLOWER_IN_HW_COUNT, f->in_hw_count)) + goto nla_put_failure; + if (tcf_exts_dump(skb, &f->exts)) goto nla_put_failure; diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c index 98541c6399db..22e9799e5b69 100644 --- a/net/sched/sch_api.c +++ b/net/sched/sch_api.c @@ -27,7 +27,6 @@ #include <linux/kmod.h> #include <linux/list.h> #include <linux/hrtimer.h> -#include <linux/lockdep.h> #include <linux/slab.h> #include <linux/hashtable.h> @@ -315,6 +314,24 @@ out: return q; } +struct Qdisc *qdisc_lookup_rcu(struct net_device *dev, u32 handle) +{ + struct netdev_queue *nq; + struct Qdisc *q; + + if (!handle) + return NULL; + q = qdisc_match_from_root(dev->qdisc, handle); + if (q) + goto out; + + nq = dev_ingress_queue_rcu(dev); + if (nq) + q = qdisc_match_from_root(nq->qdisc_sleeping, handle); +out: + return q; +} + static struct Qdisc *qdisc_leaf(struct Qdisc *p, u32 classid) { unsigned long cl; @@ -921,7 +938,7 @@ static void notify_and_destroy(struct net *net, struct sk_buff *skb, qdisc_notify(net, skb, n, clid, old, new); if (old) - qdisc_destroy(old); + qdisc_put(old); } /* Graft qdisc "new" to class "classid" of qdisc "parent" or @@ -974,7 +991,7 @@ static int qdisc_graft(struct net_device *dev, struct Qdisc *parent, qdisc_refcount_inc(new); if (!ingress) - qdisc_destroy(old); + qdisc_put(old); } skip: @@ -1053,10 +1070,6 @@ static int qdisc_block_indexes_set(struct Qdisc *sch, struct nlattr **tca, return 0; } -/* lockdep annotation is needed for ingress; egress gets it only for name */ -static struct lock_class_key qdisc_tx_lock; -static struct lock_class_key qdisc_rx_lock; - /* Allocate and initialize new qdisc. @@ -1121,7 +1134,6 @@ static struct Qdisc *qdisc_create(struct net_device *dev, if (handle == TC_H_INGRESS) { sch->flags |= TCQ_F_INGRESS; handle = TC_H_MAKE(TC_H_INGRESS, 0); - lockdep_set_class(qdisc_lock(sch), &qdisc_rx_lock); } else { if (handle == 0) { handle = qdisc_alloc_handle(dev); @@ -1129,7 +1141,6 @@ static struct Qdisc *qdisc_create(struct net_device *dev, if (handle == 0) goto err_out3; } - lockdep_set_class(qdisc_lock(sch), &qdisc_tx_lock); if (!netif_is_multiqueue(dev)) sch->flags |= TCQ_F_ONETXQUEUE; } @@ -1568,7 +1579,7 @@ graft: err = qdisc_graft(dev, p, skb, n, clid, q, NULL, extack); if (err) { if (q) - qdisc_destroy(q); + qdisc_put(q); return err; } diff --git a/net/sched/sch_atm.c b/net/sched/sch_atm.c index cd49afca9617..d714d3747bcb 100644 --- a/net/sched/sch_atm.c +++ b/net/sched/sch_atm.c @@ -150,7 +150,7 @@ static void atm_tc_put(struct Qdisc *sch, unsigned long cl) pr_debug("atm_tc_put: destroying\n"); list_del_init(&flow->list); pr_debug("atm_tc_put: qdisc %p\n", flow->q); - qdisc_destroy(flow->q); + qdisc_put(flow->q); tcf_block_put(flow->block); if (flow->sock) { pr_debug("atm_tc_put: f_count %ld\n", diff --git a/net/sched/sch_cake.c b/net/sched/sch_cake.c index c07c30b916d5..dc539295ae65 100644 --- a/net/sched/sch_cake.c +++ b/net/sched/sch_cake.c @@ -812,7 +812,7 @@ static struct sk_buff *dequeue_head(struct cake_flow *flow) if (skb) { flow->head = skb->next; - skb->next = NULL; + skb_mark_not_on_list(skb); } return skb; @@ -1252,7 +1252,7 @@ found: else flow->head = elig_ack->next; - elig_ack->next = NULL; + skb_mark_not_on_list(elig_ack); return elig_ack; } @@ -1675,7 +1675,7 @@ static s32 cake_enqueue(struct sk_buff *skb, struct Qdisc *sch, while (segs) { nskb = segs->next; - segs->next = NULL; + skb_mark_not_on_list(segs); qdisc_skb_cb(segs)->pkt_len = segs->len; cobalt_set_enqueue_time(segs, now); get_cobalt_cb(segs)->adjusted_len = cake_overhead(q, diff --git a/net/sched/sch_cbq.c b/net/sched/sch_cbq.c index f42025d53cfe..4dc05409e3fb 100644 --- a/net/sched/sch_cbq.c +++ b/net/sched/sch_cbq.c @@ -1418,7 +1418,7 @@ static void cbq_destroy_class(struct Qdisc *sch, struct cbq_class *cl) WARN_ON(cl->filters); tcf_block_put(cl->block); - qdisc_destroy(cl->q); + qdisc_put(cl->q); qdisc_put_rtab(cl->R_tab); gen_kill_estimator(&cl->rate_est); if (cl != &q->link) diff --git a/net/sched/sch_cbs.c b/net/sched/sch_cbs.c index e26a24017faa..e689e11b6d0f 100644 --- a/net/sched/sch_cbs.c +++ b/net/sched/sch_cbs.c @@ -379,7 +379,7 @@ static void cbs_destroy(struct Qdisc *sch) cbs_disable_offload(dev, q); if (q->qdisc) - qdisc_destroy(q->qdisc); + qdisc_put(q->qdisc); } static int cbs_dump(struct Qdisc *sch, struct sk_buff *skb) diff --git a/net/sched/sch_drr.c b/net/sched/sch_drr.c index e0b0cf8a9939..cdebaed0f8cf 100644 --- a/net/sched/sch_drr.c +++ b/net/sched/sch_drr.c @@ -134,7 +134,7 @@ static int drr_change_class(struct Qdisc *sch, u32 classid, u32 parentid, tca[TCA_RATE]); if (err) { NL_SET_ERR_MSG(extack, "Failed to replace estimator"); - qdisc_destroy(cl->qdisc); + qdisc_put(cl->qdisc); kfree(cl); return err; } @@ -153,7 +153,7 @@ static int drr_change_class(struct Qdisc *sch, u32 classid, u32 parentid, static void drr_destroy_class(struct Qdisc *sch, struct drr_class *cl) { gen_kill_estimator(&cl->rate_est); - qdisc_destroy(cl->qdisc); + qdisc_put(cl->qdisc); kfree(cl); } diff --git a/net/sched/sch_dsmark.c b/net/sched/sch_dsmark.c index 049714c57075..f6f480784bc6 100644 --- a/net/sched/sch_dsmark.c +++ b/net/sched/sch_dsmark.c @@ -412,7 +412,7 @@ static void dsmark_destroy(struct Qdisc *sch) pr_debug("%s(sch %p,[qdisc %p])\n", __func__, sch, p); tcf_block_put(p->block); - qdisc_destroy(p->q); + qdisc_put(p->q); if (p->mv != p->embedded) kfree(p->mv); } diff --git a/net/sched/sch_fifo.c b/net/sched/sch_fifo.c index 24893d3b5d22..3809c9bf8896 100644 --- a/net/sched/sch_fifo.c +++ b/net/sched/sch_fifo.c @@ -177,7 +177,7 @@ struct Qdisc *fifo_create_dflt(struct Qdisc *sch, struct Qdisc_ops *ops, if (q) { err = fifo_set_limit(q, limit); if (err < 0) { - qdisc_destroy(q); + qdisc_put(q); q = NULL; } } diff --git a/net/sched/sch_fq.c b/net/sched/sch_fq.c index 4808713c73b9..628a2cdcfc6f 100644 --- a/net/sched/sch_fq.c +++ b/net/sched/sch_fq.c @@ -106,7 +106,6 @@ struct fq_sched_data { u64 stat_gc_flows; u64 stat_internal_packets; - u64 stat_tcp_retrans; u64 stat_throttled; u64 stat_flows_plimit; u64 stat_pkts_too_long; @@ -319,7 +318,7 @@ static struct sk_buff *fq_dequeue_head(struct Qdisc *sch, struct fq_flow *flow) if (skb) { flow->head = skb->next; - skb->next = NULL; + skb_mark_not_on_list(skb); flow->qlen--; qdisc_qstats_backlog_dec(sch, skb); sch->q.qlen--; @@ -327,62 +326,17 @@ static struct sk_buff *fq_dequeue_head(struct Qdisc *sch, struct fq_flow *flow) return skb; } -/* We might add in the future detection of retransmits - * For the time being, just return false - */ -static bool skb_is_retransmit(struct sk_buff *skb) -{ - return false; -} - -/* add skb to flow queue - * flow queue is a linked list, kind of FIFO, except for TCP retransmits - * We special case tcp retransmits to be transmitted before other packets. - * We rely on fact that TCP retransmits are unlikely, so we do not waste - * a separate queue or a pointer. - * head-> [retrans pkt 1] - * [retrans pkt 2] - * [ normal pkt 1] - * [ normal pkt 2] - * [ normal pkt 3] - * tail-> [ normal pkt 4] - */ static void flow_queue_add(struct fq_flow *flow, struct sk_buff *skb) { - struct sk_buff *prev, *head = flow->head; + struct sk_buff *head = flow->head; skb->next = NULL; - if (!head) { + if (!head) flow->head = skb; - flow->tail = skb; - return; - } - if (likely(!skb_is_retransmit(skb))) { + else flow->tail->next = skb; - flow->tail = skb; - return; - } - /* This skb is a tcp retransmit, - * find the last retrans packet in the queue - */ - prev = NULL; - while (skb_is_retransmit(head)) { - prev = head; - head = head->next; - if (!head) - break; - } - if (!prev) { /* no rtx packet in queue, become the new head */ - skb->next = flow->head; - flow->head = skb; - } else { - if (prev == flow->tail) - flow->tail = skb; - else - skb->next = prev->next; - prev->next = skb; - } + flow->tail = skb; } static int fq_enqueue(struct sk_buff *skb, struct Qdisc *sch, @@ -401,8 +355,6 @@ static int fq_enqueue(struct sk_buff *skb, struct Qdisc *sch, } f->qlen++; - if (skb_is_retransmit(skb)) - q->stat_tcp_retrans++; qdisc_qstats_backlog_inc(sch, skb); if (fq_flow_is_detached(f)) { struct sock *sk = skb->sk; @@ -460,7 +412,7 @@ static void fq_check_throttled(struct fq_sched_data *q, u64 now) static struct sk_buff *fq_dequeue(struct Qdisc *sch) { struct fq_sched_data *q = qdisc_priv(sch); - u64 now = ktime_get_ns(); + u64 now = ktime_get_tai_ns(); struct fq_flow_head *head; struct sk_buff *skb; struct fq_flow *f; @@ -491,11 +443,16 @@ begin: } skb = f->head; - if (unlikely(skb && now < f->time_next_packet && - !skb_is_tcp_pure_ack(skb))) { - head->first = f->next; - fq_flow_set_throttled(q, f); - goto begin; + if (skb && !skb_is_tcp_pure_ack(skb)) { + u64 time_next_packet = max_t(u64, ktime_to_ns(skb->tstamp), + f->time_next_packet); + + if (now < time_next_packet) { + head->first = f->next; + f->time_next_packet = time_next_packet; + fq_flow_set_throttled(q, f); + goto begin; + } } skb = fq_dequeue_head(sch, f); @@ -513,11 +470,7 @@ begin: prefetch(&skb->end); f->credit -= qdisc_pkt_len(skb); - if (!q->rate_enable) - goto out; - - /* Do not pace locally generated ack packets */ - if (skb_is_tcp_pure_ack(skb)) + if (ktime_to_ns(skb->tstamp) || !q->rate_enable) goto out; rate = q->flow_max_rate; @@ -823,7 +776,7 @@ static int fq_init(struct Qdisc *sch, struct nlattr *opt, q->fq_trees_log = ilog2(1024); q->orphan_mask = 1024 - 1; q->low_rate_threshold = 550000 / 8; - qdisc_watchdog_init(&q->watchdog, sch); + qdisc_watchdog_init_clockid(&q->watchdog, sch, CLOCK_TAI); if (opt) err = fq_change(sch, opt, extack); @@ -873,12 +826,12 @@ static int fq_dump_stats(struct Qdisc *sch, struct gnet_dump *d) st.gc_flows = q->stat_gc_flows; st.highprio_packets = q->stat_internal_packets; - st.tcp_retrans = q->stat_tcp_retrans; + st.tcp_retrans = 0; st.throttled = q->stat_throttled; st.flows_plimit = q->stat_flows_plimit; st.pkts_too_long = q->stat_pkts_too_long; st.allocation_errors = q->stat_allocation_errors; - st.time_next_delayed_flow = q->time_next_delayed_flow - ktime_get_ns(); + st.time_next_delayed_flow = q->time_next_delayed_flow - ktime_get_tai_ns(); st.flows = q->flows; st.inactive_flows = q->inactive_flows; st.throttled_flows = q->throttled_flows; diff --git a/net/sched/sch_fq_codel.c b/net/sched/sch_fq_codel.c index 6c0a9d5dbf94..cd04d40c30b6 100644 --- a/net/sched/sch_fq_codel.c +++ b/net/sched/sch_fq_codel.c @@ -124,7 +124,7 @@ static inline struct sk_buff *dequeue_head(struct fq_codel_flow *flow) struct sk_buff *skb = flow->head; flow->head = skb->next; - skb->next = NULL; + skb_mark_not_on_list(skb); return skb; } diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c index 69078c82963e..531fac1d2875 100644 --- a/net/sched/sch_generic.c +++ b/net/sched/sch_generic.c @@ -184,7 +184,7 @@ static void try_bulk_dequeue_skb(struct Qdisc *q, skb = nskb; (*packets)++; /* GSO counts as one pkt */ } - skb->next = NULL; + skb_mark_not_on_list(skb); } /* This variant of try_bulk_dequeue_skb() makes sure @@ -210,7 +210,7 @@ static void try_bulk_dequeue_skb_slow(struct Qdisc *q, skb = nskb; } while (++cnt < 8); (*packets) += cnt; - skb->next = NULL; + skb_mark_not_on_list(skb); } /* Note that dequeue_skb can possibly return a SKB list (via skb->next). @@ -901,7 +901,7 @@ struct Qdisc *qdisc_create_dflt(struct netdev_queue *dev_queue, if (!ops->init || ops->init(sch, NULL, extack) == 0) return sch; - qdisc_destroy(sch); + qdisc_put(sch); return NULL; } EXPORT_SYMBOL(qdisc_create_dflt); @@ -941,15 +941,18 @@ void qdisc_free(struct Qdisc *qdisc) kfree((char *) qdisc - qdisc->padded); } -void qdisc_destroy(struct Qdisc *qdisc) +void qdisc_free_cb(struct rcu_head *head) +{ + struct Qdisc *q = container_of(head, struct Qdisc, rcu); + + qdisc_free(q); +} + +static void qdisc_destroy(struct Qdisc *qdisc) { const struct Qdisc_ops *ops = qdisc->ops; struct sk_buff *skb, *tmp; - if (qdisc->flags & TCQ_F_BUILTIN || - !refcount_dec_and_test(&qdisc->refcnt)) - return; - #ifdef CONFIG_NET_SCHED qdisc_hash_del(qdisc); @@ -974,9 +977,34 @@ void qdisc_destroy(struct Qdisc *qdisc) kfree_skb_list(skb); } - qdisc_free(qdisc); + call_rcu(&qdisc->rcu, qdisc_free_cb); +} + +void qdisc_put(struct Qdisc *qdisc) +{ + if (qdisc->flags & TCQ_F_BUILTIN || + !refcount_dec_and_test(&qdisc->refcnt)) + return; + + qdisc_destroy(qdisc); +} +EXPORT_SYMBOL(qdisc_put); + +/* Version of qdisc_put() that is called with rtnl mutex unlocked. + * Intended to be used as optimization, this function only takes rtnl lock if + * qdisc reference counter reached zero. + */ + +void qdisc_put_unlocked(struct Qdisc *qdisc) +{ + if (qdisc->flags & TCQ_F_BUILTIN || + !refcount_dec_and_rtnl_lock(&qdisc->refcnt)) + return; + + qdisc_destroy(qdisc); + rtnl_unlock(); } -EXPORT_SYMBOL(qdisc_destroy); +EXPORT_SYMBOL(qdisc_put_unlocked); /* Attach toplevel qdisc to device queue. */ struct Qdisc *dev_graft_qdisc(struct netdev_queue *dev_queue, @@ -1270,7 +1298,7 @@ static void shutdown_scheduler_queue(struct net_device *dev, rcu_assign_pointer(dev_queue->qdisc, qdisc_default); dev_queue->qdisc_sleeping = qdisc_default; - qdisc_destroy(qdisc); + qdisc_put(qdisc); } } @@ -1279,7 +1307,7 @@ void dev_shutdown(struct net_device *dev) netdev_for_each_tx_queue(dev, shutdown_scheduler_queue, &noop_qdisc); if (dev_ingress_queue(dev)) shutdown_scheduler_queue(dev, dev_ingress_queue(dev), &noop_qdisc); - qdisc_destroy(dev->qdisc); + qdisc_put(dev->qdisc); dev->qdisc = &noop_qdisc; WARN_ON(timer_pending(&dev->watchdog_timer)); diff --git a/net/sched/sch_hfsc.c b/net/sched/sch_hfsc.c index 3278a76f6861..b18ec1f6de60 100644 --- a/net/sched/sch_hfsc.c +++ b/net/sched/sch_hfsc.c @@ -1092,7 +1092,7 @@ hfsc_destroy_class(struct Qdisc *sch, struct hfsc_class *cl) struct hfsc_sched *q = qdisc_priv(sch); tcf_block_put(cl->block); - qdisc_destroy(cl->qdisc); + qdisc_put(cl->qdisc); gen_kill_estimator(&cl->rate_est); if (cl != &q->root) kfree(cl); diff --git a/net/sched/sch_hhf.c b/net/sched/sch_hhf.c index c3a8388dcdf6..9d6a47697406 100644 --- a/net/sched/sch_hhf.c +++ b/net/sched/sch_hhf.c @@ -330,7 +330,7 @@ static struct sk_buff *dequeue_head(struct wdrr_bucket *bucket) struct sk_buff *skb = bucket->head; bucket->head = skb->next; - skb->next = NULL; + skb_mark_not_on_list(skb); return skb; } diff --git a/net/sched/sch_htb.c b/net/sched/sch_htb.c index 43c4bfe625a9..58b449490757 100644 --- a/net/sched/sch_htb.c +++ b/net/sched/sch_htb.c @@ -132,7 +132,7 @@ struct htb_class { struct htb_class_inner { struct htb_prio clprio[TC_HTB_NUMPRIO]; } inner; - } un; + }; s64 pq_key; int prio_activity; /* for which prios are we active */ @@ -411,13 +411,13 @@ static void htb_activate_prios(struct htb_sched *q, struct htb_class *cl) int prio = ffz(~m); m &= ~(1 << prio); - if (p->un.inner.clprio[prio].feed.rb_node) + if (p->inner.clprio[prio].feed.rb_node) /* parent already has its feed in use so that * reset bit in mask as parent is already ok */ mask &= ~(1 << prio); - htb_add_to_id_tree(&p->un.inner.clprio[prio].feed, cl, prio); + htb_add_to_id_tree(&p->inner.clprio[prio].feed, cl, prio); } p->prio_activity |= mask; cl = p; @@ -447,19 +447,19 @@ static void htb_deactivate_prios(struct htb_sched *q, struct htb_class *cl) int prio = ffz(~m); m &= ~(1 << prio); - if (p->un.inner.clprio[prio].ptr == cl->node + prio) { + if (p->inner.clprio[prio].ptr == cl->node + prio) { /* we are removing child which is pointed to from * parent feed - forget the pointer but remember * classid */ - p->un.inner.clprio[prio].last_ptr_id = cl->common.classid; - p->un.inner.clprio[prio].ptr = NULL; + p->inner.clprio[prio].last_ptr_id = cl->common.classid; + p->inner.clprio[prio].ptr = NULL; } htb_safe_rb_erase(cl->node + prio, - &p->un.inner.clprio[prio].feed); + &p->inner.clprio[prio].feed); - if (!p->un.inner.clprio[prio].feed.rb_node) + if (!p->inner.clprio[prio].feed.rb_node) mask |= 1 << prio; } @@ -555,7 +555,7 @@ htb_change_class_mode(struct htb_sched *q, struct htb_class *cl, s64 *diff) */ static inline void htb_activate(struct htb_sched *q, struct htb_class *cl) { - WARN_ON(cl->level || !cl->un.leaf.q || !cl->un.leaf.q->q.qlen); + WARN_ON(cl->level || !cl->leaf.q || !cl->leaf.q->q.qlen); if (!cl->prio_activity) { cl->prio_activity = 1 << cl->prio; @@ -577,22 +577,6 @@ static inline void htb_deactivate(struct htb_sched *q, struct htb_class *cl) cl->prio_activity = 0; } -static void htb_enqueue_tail(struct sk_buff *skb, struct Qdisc *sch, - struct qdisc_skb_head *qh) -{ - struct sk_buff *last = qh->tail; - - if (last) { - skb->next = NULL; - last->next = skb; - qh->tail = skb; - } else { - qh->tail = skb; - qh->head = skb; - } - qh->qlen++; -} - static int htb_enqueue(struct sk_buff *skb, struct Qdisc *sch, struct sk_buff **to_free) { @@ -603,7 +587,7 @@ static int htb_enqueue(struct sk_buff *skb, struct Qdisc *sch, if (cl == HTB_DIRECT) { /* enqueue to helper queue */ if (q->direct_queue.qlen < q->direct_qlen) { - htb_enqueue_tail(skb, sch, &q->direct_queue); + __qdisc_enqueue_tail(skb, &q->direct_queue); q->direct_pkts++; } else { return qdisc_drop(skb, sch, to_free); @@ -615,7 +599,7 @@ static int htb_enqueue(struct sk_buff *skb, struct Qdisc *sch, __qdisc_drop(skb, to_free); return ret; #endif - } else if ((ret = qdisc_enqueue(skb, cl->un.leaf.q, + } else if ((ret = qdisc_enqueue(skb, cl->leaf.q, to_free)) != NET_XMIT_SUCCESS) { if (net_xmit_drop_count(ret)) { qdisc_qstats_drop(sch); @@ -823,7 +807,7 @@ static struct htb_class *htb_lookup_leaf(struct htb_prio *hprio, const int prio) cl = rb_entry(*sp->pptr, struct htb_class, node[prio]); if (!cl->level) return cl; - clp = &cl->un.inner.clprio[prio]; + clp = &cl->inner.clprio[prio]; (++sp)->root = clp->feed.rb_node; sp->pptr = &clp->ptr; sp->pid = &clp->last_ptr_id; @@ -857,7 +841,7 @@ next: * graft operation on the leaf since last dequeue; * simply deactivate and skip such class */ - if (unlikely(cl->un.leaf.q->q.qlen == 0)) { + if (unlikely(cl->leaf.q->q.qlen == 0)) { struct htb_class *next; htb_deactivate(q, cl); @@ -873,12 +857,12 @@ next: goto next; } - skb = cl->un.leaf.q->dequeue(cl->un.leaf.q); + skb = cl->leaf.q->dequeue(cl->leaf.q); if (likely(skb != NULL)) break; - qdisc_warn_nonwc("htb", cl->un.leaf.q); - htb_next_rb_node(level ? &cl->parent->un.inner.clprio[prio].ptr: + qdisc_warn_nonwc("htb", cl->leaf.q); + htb_next_rb_node(level ? &cl->parent->inner.clprio[prio].ptr: &q->hlevel[0].hprio[prio].ptr); cl = htb_lookup_leaf(hprio, prio); @@ -886,16 +870,16 @@ next: if (likely(skb != NULL)) { bstats_update(&cl->bstats, skb); - cl->un.leaf.deficit[level] -= qdisc_pkt_len(skb); - if (cl->un.leaf.deficit[level] < 0) { - cl->un.leaf.deficit[level] += cl->quantum; - htb_next_rb_node(level ? &cl->parent->un.inner.clprio[prio].ptr : + cl->leaf.deficit[level] -= qdisc_pkt_len(skb); + if (cl->leaf.deficit[level] < 0) { + cl->leaf.deficit[level] += cl->quantum; + htb_next_rb_node(level ? &cl->parent->inner.clprio[prio].ptr : &q->hlevel[0].hprio[prio].ptr); } /* this used to be after charge_class but this constelation * gives us slightly better performance */ - if (!cl->un.leaf.q->q.qlen) + if (!cl->leaf.q->q.qlen) htb_deactivate(q, cl); htb_charge_class(q, cl, level, skb); } @@ -972,10 +956,10 @@ static void htb_reset(struct Qdisc *sch) for (i = 0; i < q->clhash.hashsize; i++) { hlist_for_each_entry(cl, &q->clhash.hash[i], common.hnode) { if (cl->level) - memset(&cl->un.inner, 0, sizeof(cl->un.inner)); + memset(&cl->inner, 0, sizeof(cl->inner)); else { - if (cl->un.leaf.q) - qdisc_reset(cl->un.leaf.q); + if (cl->leaf.q) + qdisc_reset(cl->leaf.q); } cl->prio_activity = 0; cl->cmode = HTB_CAN_SEND; @@ -1098,8 +1082,8 @@ static int htb_dump_class(struct Qdisc *sch, unsigned long arg, */ tcm->tcm_parent = cl->parent ? cl->parent->common.classid : TC_H_ROOT; tcm->tcm_handle = cl->common.classid; - if (!cl->level && cl->un.leaf.q) - tcm->tcm_info = cl->un.leaf.q->handle; + if (!cl->level && cl->leaf.q) + tcm->tcm_info = cl->leaf.q->handle; nest = nla_nest_start(skb, TCA_OPTIONS); if (nest == NULL) @@ -1142,9 +1126,9 @@ htb_dump_class_stats(struct Qdisc *sch, unsigned long arg, struct gnet_dump *d) }; __u32 qlen = 0; - if (!cl->level && cl->un.leaf.q) { - qlen = cl->un.leaf.q->q.qlen; - qs.backlog = cl->un.leaf.q->qstats.backlog; + if (!cl->level && cl->leaf.q) { + qlen = cl->leaf.q->q.qlen; + qs.backlog = cl->leaf.q->qstats.backlog; } cl->xstats.tokens = clamp_t(s64, PSCHED_NS2TICKS(cl->tokens), INT_MIN, INT_MAX); @@ -1172,14 +1156,14 @@ static int htb_graft(struct Qdisc *sch, unsigned long arg, struct Qdisc *new, cl->common.classid, extack)) == NULL) return -ENOBUFS; - *old = qdisc_replace(sch, new, &cl->un.leaf.q); + *old = qdisc_replace(sch, new, &cl->leaf.q); return 0; } static struct Qdisc *htb_leaf(struct Qdisc *sch, unsigned long arg) { struct htb_class *cl = (struct htb_class *)arg; - return !cl->level ? cl->un.leaf.q : NULL; + return !cl->level ? cl->leaf.q : NULL; } static void htb_qlen_notify(struct Qdisc *sch, unsigned long arg) @@ -1205,15 +1189,15 @@ static void htb_parent_to_leaf(struct htb_sched *q, struct htb_class *cl, { struct htb_class *parent = cl->parent; - WARN_ON(cl->level || !cl->un.leaf.q || cl->prio_activity); + WARN_ON(cl->level || !cl->leaf.q || cl->prio_activity); if (parent->cmode != HTB_CAN_SEND) htb_safe_rb_erase(&parent->pq_node, &q->hlevel[parent->level].wait_pq); parent->level = 0; - memset(&parent->un.inner, 0, sizeof(parent->un.inner)); - parent->un.leaf.q = new_q ? new_q : &noop_qdisc; + memset(&parent->inner, 0, sizeof(parent->inner)); + parent->leaf.q = new_q ? new_q : &noop_qdisc; parent->tokens = parent->buffer; parent->ctokens = parent->cbuffer; parent->t_c = ktime_get_ns(); @@ -1223,8 +1207,8 @@ static void htb_parent_to_leaf(struct htb_sched *q, struct htb_class *cl, static void htb_destroy_class(struct Qdisc *sch, struct htb_class *cl) { if (!cl->level) { - WARN_ON(!cl->un.leaf.q); - qdisc_destroy(cl->un.leaf.q); + WARN_ON(!cl->leaf.q); + qdisc_put(cl->leaf.q); } gen_kill_estimator(&cl->rate_est); tcf_block_put(cl->block); @@ -1286,11 +1270,11 @@ static int htb_delete(struct Qdisc *sch, unsigned long arg) sch_tree_lock(sch); if (!cl->level) { - unsigned int qlen = cl->un.leaf.q->q.qlen; - unsigned int backlog = cl->un.leaf.q->qstats.backlog; + unsigned int qlen = cl->leaf.q->q.qlen; + unsigned int backlog = cl->leaf.q->qstats.backlog; - qdisc_reset(cl->un.leaf.q); - qdisc_tree_reduce_backlog(cl->un.leaf.q, qlen, backlog); + qdisc_reset(cl->leaf.q); + qdisc_tree_reduce_backlog(cl->leaf.q, qlen, backlog); } /* delete from hash and active; remainder in destroy_class */ @@ -1419,13 +1403,13 @@ static int htb_change_class(struct Qdisc *sch, u32 classid, classid, NULL); sch_tree_lock(sch); if (parent && !parent->level) { - unsigned int qlen = parent->un.leaf.q->q.qlen; - unsigned int backlog = parent->un.leaf.q->qstats.backlog; + unsigned int qlen = parent->leaf.q->q.qlen; + unsigned int backlog = parent->leaf.q->qstats.backlog; /* turn parent into inner node */ - qdisc_reset(parent->un.leaf.q); - qdisc_tree_reduce_backlog(parent->un.leaf.q, qlen, backlog); - qdisc_destroy(parent->un.leaf.q); + qdisc_reset(parent->leaf.q); + qdisc_tree_reduce_backlog(parent->leaf.q, qlen, backlog); + qdisc_put(parent->leaf.q); if (parent->prio_activity) htb_deactivate(q, parent); @@ -1436,10 +1420,10 @@ static int htb_change_class(struct Qdisc *sch, u32 classid, } parent->level = (parent->parent ? parent->parent->level : TC_HTB_MAXDEPTH) - 1; - memset(&parent->un.inner, 0, sizeof(parent->un.inner)); + memset(&parent->inner, 0, sizeof(parent->inner)); } /* leaf (we) needs elementary qdisc */ - cl->un.leaf.q = new_q ? new_q : &noop_qdisc; + cl->leaf.q = new_q ? new_q : &noop_qdisc; cl->common.classid = classid; cl->parent = parent; @@ -1455,8 +1439,8 @@ static int htb_change_class(struct Qdisc *sch, u32 classid, qdisc_class_hash_insert(&q->clhash, &cl->common); if (parent) parent->children++; - if (cl->un.leaf.q != &noop_qdisc) - qdisc_hash_add(cl->un.leaf.q, true); + if (cl->leaf.q != &noop_qdisc) + qdisc_hash_add(cl->leaf.q, true); } else { if (tca[TCA_RATE]) { err = gen_replace_estimator(&cl->bstats, NULL, @@ -1478,7 +1462,7 @@ static int htb_change_class(struct Qdisc *sch, u32 classid, psched_ratecfg_precompute(&cl->ceil, &hopt->ceil, ceil64); /* it used to be a nasty bug here, we have to check that node - * is really leaf before changing cl->un.leaf ! + * is really leaf before changing cl->leaf ! */ if (!cl->level) { u64 quantum = cl->rate.rate_bytes_ps; diff --git a/net/sched/sch_mq.c b/net/sched/sch_mq.c index d6b8ae4ed7a3..f20f3a0f8424 100644 --- a/net/sched/sch_mq.c +++ b/net/sched/sch_mq.c @@ -65,7 +65,7 @@ static void mq_destroy(struct Qdisc *sch) if (!priv->qdiscs) return; for (ntx = 0; ntx < dev->num_tx_queues && priv->qdiscs[ntx]; ntx++) - qdisc_destroy(priv->qdiscs[ntx]); + qdisc_put(priv->qdiscs[ntx]); kfree(priv->qdiscs); } @@ -119,7 +119,7 @@ static void mq_attach(struct Qdisc *sch) qdisc = priv->qdiscs[ntx]; old = dev_graft_qdisc(qdisc->dev_queue, qdisc); if (old) - qdisc_destroy(old); + qdisc_put(old); #ifdef CONFIG_NET_SCHED if (ntx < dev->real_num_tx_queues) qdisc_hash_add(qdisc, false); diff --git a/net/sched/sch_mqprio.c b/net/sched/sch_mqprio.c index 0e9d761cdd80..d364e63c396d 100644 --- a/net/sched/sch_mqprio.c +++ b/net/sched/sch_mqprio.c @@ -40,7 +40,7 @@ static void mqprio_destroy(struct Qdisc *sch) for (ntx = 0; ntx < dev->num_tx_queues && priv->qdiscs[ntx]; ntx++) - qdisc_destroy(priv->qdiscs[ntx]); + qdisc_put(priv->qdiscs[ntx]); kfree(priv->qdiscs); } @@ -300,7 +300,7 @@ static void mqprio_attach(struct Qdisc *sch) qdisc = priv->qdiscs[ntx]; old = dev_graft_qdisc(qdisc->dev_queue, qdisc); if (old) - qdisc_destroy(old); + qdisc_put(old); if (ntx < dev->real_num_tx_queues) qdisc_hash_add(qdisc, false); } diff --git a/net/sched/sch_multiq.c b/net/sched/sch_multiq.c index 1da7ea8de0ad..7410ce4d0321 100644 --- a/net/sched/sch_multiq.c +++ b/net/sched/sch_multiq.c @@ -175,7 +175,7 @@ multiq_destroy(struct Qdisc *sch) tcf_block_put(q->block); for (band = 0; band < q->bands; band++) - qdisc_destroy(q->queues[band]); + qdisc_put(q->queues[band]); kfree(q->queues); } @@ -204,7 +204,7 @@ static int multiq_tune(struct Qdisc *sch, struct nlattr *opt, q->queues[i] = &noop_qdisc; qdisc_tree_reduce_backlog(child, child->q.qlen, child->qstats.backlog); - qdisc_destroy(child); + qdisc_put(child); } } @@ -228,7 +228,7 @@ static int multiq_tune(struct Qdisc *sch, struct nlattr *opt, qdisc_tree_reduce_backlog(old, old->q.qlen, old->qstats.backlog); - qdisc_destroy(old); + qdisc_put(old); } sch_tree_unlock(sch); } diff --git a/net/sched/sch_netem.c b/net/sched/sch_netem.c index ad18a2052416..57b3ad9394ad 100644 --- a/net/sched/sch_netem.c +++ b/net/sched/sch_netem.c @@ -412,16 +412,6 @@ static struct sk_buff *netem_segment(struct sk_buff *skb, struct Qdisc *sch, return segs; } -static void netem_enqueue_skb_head(struct qdisc_skb_head *qh, struct sk_buff *skb) -{ - skb->next = qh->head; - - if (!qh->head) - qh->tail = skb; - qh->head = skb; - qh->qlen++; -} - /* * Insert one skb into qdisc. * Note: parent depends on return value to account for queue length. @@ -570,7 +560,7 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch, cb->time_to_send = ktime_get_ns(); q->counter = 0; - netem_enqueue_skb_head(&sch->q, skb); + __qdisc_enqueue_head(skb, &sch->q); sch->qstats.requeues++; } @@ -578,7 +568,7 @@ finish_segs: if (segs) { while (segs) { skb2 = segs->next; - segs->next = NULL; + skb_mark_not_on_list(segs); qdisc_skb_cb(segs)->pkt_len = segs->len; last_len = segs->len; rc = qdisc_enqueue(segs, sch, to_free); @@ -1032,7 +1022,7 @@ static void netem_destroy(struct Qdisc *sch) qdisc_watchdog_cancel(&q->watchdog); if (q->qdisc) - qdisc_destroy(q->qdisc); + qdisc_put(q->qdisc); dist_free(q->delay_dist); dist_free(q->slot_dist); } diff --git a/net/sched/sch_prio.c b/net/sched/sch_prio.c index 222e53d3d27a..f8af98621179 100644 --- a/net/sched/sch_prio.c +++ b/net/sched/sch_prio.c @@ -175,7 +175,7 @@ prio_destroy(struct Qdisc *sch) tcf_block_put(q->block); prio_offload(sch, NULL); for (prio = 0; prio < q->bands; prio++) - qdisc_destroy(q->queues[prio]); + qdisc_put(q->queues[prio]); } static int prio_tune(struct Qdisc *sch, struct nlattr *opt, @@ -205,7 +205,7 @@ static int prio_tune(struct Qdisc *sch, struct nlattr *opt, extack); if (!queues[i]) { while (i > oldbands) - qdisc_destroy(queues[--i]); + qdisc_put(queues[--i]); return -ENOMEM; } } @@ -220,7 +220,7 @@ static int prio_tune(struct Qdisc *sch, struct nlattr *opt, qdisc_tree_reduce_backlog(child, child->q.qlen, child->qstats.backlog); - qdisc_destroy(child); + qdisc_put(child); } for (i = oldbands; i < q->bands; i++) { diff --git a/net/sched/sch_qfq.c b/net/sched/sch_qfq.c index bb1a9c11fc54..dc37c4ead439 100644 --- a/net/sched/sch_qfq.c +++ b/net/sched/sch_qfq.c @@ -526,7 +526,7 @@ set_change_agg: return 0; destroy_class: - qdisc_destroy(cl->qdisc); + qdisc_put(cl->qdisc); kfree(cl); return err; } @@ -537,7 +537,7 @@ static void qfq_destroy_class(struct Qdisc *sch, struct qfq_class *cl) qfq_rm_from_agg(q, cl); gen_kill_estimator(&cl->rate_est); - qdisc_destroy(cl->qdisc); + qdisc_put(cl->qdisc); kfree(cl); } diff --git a/net/sched/sch_red.c b/net/sched/sch_red.c index 56c181c3feeb..3ce6c0a2c493 100644 --- a/net/sched/sch_red.c +++ b/net/sched/sch_red.c @@ -181,7 +181,7 @@ static void red_destroy(struct Qdisc *sch) del_timer_sync(&q->adapt_timer); red_offload(sch, false); - qdisc_destroy(q->qdisc); + qdisc_put(q->qdisc); } static const struct nla_policy red_policy[TCA_RED_MAX + 1] = { @@ -233,7 +233,7 @@ static int red_change(struct Qdisc *sch, struct nlattr *opt, if (child) { qdisc_tree_reduce_backlog(q->qdisc, q->qdisc->q.qlen, q->qdisc->qstats.backlog); - qdisc_destroy(q->qdisc); + qdisc_put(q->qdisc); q->qdisc = child; } diff --git a/net/sched/sch_sfb.c b/net/sched/sch_sfb.c index 7cbdad8419b7..bab506b01a32 100644 --- a/net/sched/sch_sfb.c +++ b/net/sched/sch_sfb.c @@ -469,7 +469,7 @@ static void sfb_destroy(struct Qdisc *sch) struct sfb_sched_data *q = qdisc_priv(sch); tcf_block_put(q->block); - qdisc_destroy(q->qdisc); + qdisc_put(q->qdisc); } static const struct nla_policy sfb_policy[TCA_SFB_MAX + 1] = { @@ -523,7 +523,7 @@ static int sfb_change(struct Qdisc *sch, struct nlattr *opt, qdisc_tree_reduce_backlog(q->qdisc, q->qdisc->q.qlen, q->qdisc->qstats.backlog); - qdisc_destroy(q->qdisc); + qdisc_put(q->qdisc); q->qdisc = child; q->rehash_interval = msecs_to_jiffies(ctl->rehash_interval); diff --git a/net/sched/sch_tbf.c b/net/sched/sch_tbf.c index 6f74a426f159..942dcca09cf2 100644 --- a/net/sched/sch_tbf.c +++ b/net/sched/sch_tbf.c @@ -162,7 +162,7 @@ static int tbf_segment(struct sk_buff *skb, struct Qdisc *sch, nb = 0; while (segs) { nskb = segs->next; - segs->next = NULL; + skb_mark_not_on_list(segs); qdisc_skb_cb(segs)->pkt_len = segs->len; len += segs->len; ret = qdisc_enqueue(segs, q->qdisc, to_free); @@ -392,7 +392,7 @@ static int tbf_change(struct Qdisc *sch, struct nlattr *opt, if (child) { qdisc_tree_reduce_backlog(q->qdisc, q->qdisc->q.qlen, q->qdisc->qstats.backlog); - qdisc_destroy(q->qdisc); + qdisc_put(q->qdisc); q->qdisc = child; } q->limit = qopt->limit; @@ -438,7 +438,7 @@ static void tbf_destroy(struct Qdisc *sch) struct tbf_sched_data *q = qdisc_priv(sch); qdisc_watchdog_cancel(&q->watchdog); - qdisc_destroy(q->qdisc); + qdisc_put(q->qdisc); } static int tbf_dump(struct Qdisc *sch, struct sk_buff *skb) diff --git a/net/sctp/transport.c b/net/sctp/transport.c index 12cac85da994..033696e6f74f 100644 --- a/net/sctp/transport.c +++ b/net/sctp/transport.c @@ -260,6 +260,7 @@ void sctp_transport_pmtu(struct sctp_transport *transport, struct sock *sk) bool sctp_transport_update_pmtu(struct sctp_transport *t, u32 pmtu) { struct dst_entry *dst = sctp_transport_dst_check(t); + struct sock *sk = t->asoc->base.sk; bool change = true; if (unlikely(pmtu < SCTP_DEFAULT_MINSEGMENT)) { @@ -271,12 +272,19 @@ bool sctp_transport_update_pmtu(struct sctp_transport *t, u32 pmtu) pmtu = SCTP_TRUNC4(pmtu); if (dst) { - dst->ops->update_pmtu(dst, t->asoc->base.sk, NULL, pmtu); + struct sctp_pf *pf = sctp_get_pf_specific(dst->ops->family); + union sctp_addr addr; + + pf->af->from_sk(&addr, sk); + pf->to_sk_daddr(&t->ipaddr, sk); + dst->ops->update_pmtu(dst, sk, NULL, pmtu); + pf->to_sk_daddr(&addr, sk); + dst = sctp_transport_dst_check(t); } if (!dst) { - t->af_specific->get_dst(t, &t->saddr, &t->fl, t->asoc->base.sk); + t->af_specific->get_dst(t, &t->saddr, &t->fl, sk); dst = t->dst; } diff --git a/net/sctp/ulpqueue.c b/net/sctp/ulpqueue.c index 0b427100b0d4..331cc734e3db 100644 --- a/net/sctp/ulpqueue.c +++ b/net/sctp/ulpqueue.c @@ -459,7 +459,7 @@ static struct sctp_ulpevent *sctp_ulpq_retrieve_reassembled(struct sctp_ulpq *ul * element in the queue, then count it towards * possible PD. */ - if (pos == ulpq->reasm.next) { + if (skb_queue_is_first(&ulpq->reasm, pos)) { pd_first = pos; pd_last = pos; pd_len = pos->len; diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c index 2d8a1e15e4f9..015231789ed2 100644 --- a/net/smc/af_smc.c +++ b/net/smc/af_smc.c @@ -742,7 +742,10 @@ static void smc_connect_work(struct work_struct *work) smc->sk.sk_err = -rc; out: - smc->sk.sk_state_change(&smc->sk); + if (smc->sk.sk_err) + smc->sk.sk_state_change(&smc->sk); + else + smc->sk.sk_write_space(&smc->sk); kfree(smc->connect_info); smc->connect_info = NULL; release_sock(&smc->sk); @@ -1150,9 +1153,9 @@ static int smc_listen_rdma_reg(struct smc_sock *new_smc, int local_contact) } /* listen worker: finish RDMA setup */ -static void smc_listen_rdma_finish(struct smc_sock *new_smc, - struct smc_clc_msg_accept_confirm *cclc, - int local_contact) +static int smc_listen_rdma_finish(struct smc_sock *new_smc, + struct smc_clc_msg_accept_confirm *cclc, + int local_contact) { struct smc_link *link = &new_smc->conn.lgr->lnk[SMC_SINGLE_LINK]; int reason_code = 0; @@ -1175,11 +1178,12 @@ static void smc_listen_rdma_finish(struct smc_sock *new_smc, if (reason_code) goto decline; } - return; + return 0; decline: mutex_unlock(&smc_create_lgr_pending); smc_listen_decline(new_smc, reason_code, local_contact); + return reason_code; } /* setup for RDMA connection of server */ @@ -1276,8 +1280,10 @@ static void smc_listen_work(struct work_struct *work) } /* finish worker */ - if (!ism_supported) - smc_listen_rdma_finish(new_smc, &cclc, local_contact); + if (!ism_supported) { + if (smc_listen_rdma_finish(new_smc, &cclc, local_contact)) + return; + } smc_conn_save_peer_info(new_smc, &cclc); mutex_unlock(&smc_create_lgr_pending); smc_listen_out_connected(new_smc); @@ -1529,7 +1535,7 @@ static __poll_t smc_poll(struct file *file, struct socket *sock, return EPOLLNVAL; smc = smc_sk(sock->sk); - if ((sk->sk_state == SMC_INIT) || smc->use_fallback) { + if (smc->use_fallback) { /* delegate to CLC child sock */ mask = smc->clcsock->ops->poll(file, smc->clcsock, wait); sk->sk_err = smc->clcsock->sk->sk_err; @@ -1560,9 +1566,9 @@ static __poll_t smc_poll(struct file *file, struct socket *sock, mask |= EPOLLIN | EPOLLRDNORM | EPOLLRDHUP; if (sk->sk_state == SMC_APPCLOSEWAIT1) mask |= EPOLLIN; + if (smc->conn.urg_state == SMC_URG_VALID) + mask |= EPOLLPRI; } - if (smc->conn.urg_state == SMC_URG_VALID) - mask |= EPOLLPRI; } return mask; diff --git a/net/smc/smc_clc.c b/net/smc/smc_clc.c index 83aba9ade060..52241d679cc9 100644 --- a/net/smc/smc_clc.c +++ b/net/smc/smc_clc.c @@ -446,14 +446,12 @@ int smc_clc_send_proposal(struct smc_sock *smc, int smc_type, vec[i++].iov_len = sizeof(trl); /* due to the few bytes needed for clc-handshake this cannot block */ len = kernel_sendmsg(smc->clcsock, &msg, vec, i, plen); - if (len < sizeof(pclc)) { - if (len >= 0) { - reason_code = -ENETUNREACH; - smc->sk.sk_err = -reason_code; - } else { - smc->sk.sk_err = smc->clcsock->sk->sk_err; - reason_code = -smc->sk.sk_err; - } + if (len < 0) { + smc->sk.sk_err = smc->clcsock->sk->sk_err; + reason_code = -smc->sk.sk_err; + } else if (len < (int)sizeof(pclc)) { + reason_code = -ENETUNREACH; + smc->sk.sk_err = -reason_code; } return reason_code; diff --git a/net/smc/smc_close.c b/net/smc/smc_close.c index ac961dfb1ea1..ea2b87f29469 100644 --- a/net/smc/smc_close.c +++ b/net/smc/smc_close.c @@ -100,15 +100,14 @@ static void smc_close_active_abort(struct smc_sock *smc) struct smc_cdc_conn_state_flags *txflags = &smc->conn.local_tx_ctrl.conn_state_flags; - sk->sk_err = ECONNABORTED; - if (smc->clcsock && smc->clcsock->sk) { - smc->clcsock->sk->sk_err = ECONNABORTED; - smc->clcsock->sk->sk_state_change(smc->clcsock->sk); + if (sk->sk_state != SMC_INIT && smc->clcsock && smc->clcsock->sk) { + sk->sk_err = ECONNABORTED; + if (smc->clcsock && smc->clcsock->sk) { + smc->clcsock->sk->sk_err = ECONNABORTED; + smc->clcsock->sk->sk_state_change(smc->clcsock->sk); + } } switch (sk->sk_state) { - case SMC_INIT: - sk->sk_state = SMC_PEERABORTWAIT; - break; case SMC_ACTIVE: sk->sk_state = SMC_PEERABORTWAIT; release_sock(sk); @@ -143,6 +142,7 @@ static void smc_close_active_abort(struct smc_sock *smc) case SMC_PEERFINCLOSEWAIT: sock_put(sk); /* passive closing */ break; + case SMC_INIT: case SMC_PEERABORTWAIT: case SMC_CLOSED: break; diff --git a/net/smc/smc_pnet.c b/net/smc/smc_pnet.c index 01c6ce042a1c..7cb3e4f07c10 100644 --- a/net/smc/smc_pnet.c +++ b/net/smc/smc_pnet.c @@ -461,7 +461,7 @@ static const struct genl_ops smc_pnet_ops[] = { }; /* SMC_PNETID family definition */ -static struct genl_family smc_pnet_nl_family = { +static struct genl_family smc_pnet_nl_family __ro_after_init = { .hdrsize = 0, .name = SMCR_GENL_FAMILY_NAME, .version = SMCR_GENL_FAMILY_VERSION, diff --git a/net/socket.c b/net/socket.c index e6945e318f02..01f3f8f32d6f 100644 --- a/net/socket.c +++ b/net/socket.c @@ -941,7 +941,8 @@ void dlci_ioctl_set(int (*hook) (unsigned int, void __user *)) EXPORT_SYMBOL(dlci_ioctl_set); static long sock_do_ioctl(struct net *net, struct socket *sock, - unsigned int cmd, unsigned long arg) + unsigned int cmd, unsigned long arg, + unsigned int ifreq_size) { int err; void __user *argp = (void __user *)arg; @@ -967,11 +968,11 @@ static long sock_do_ioctl(struct net *net, struct socket *sock, } else { struct ifreq ifr; bool need_copyout; - if (copy_from_user(&ifr, argp, sizeof(struct ifreq))) + if (copy_from_user(&ifr, argp, ifreq_size)) return -EFAULT; err = dev_ioctl(net, cmd, &ifr, &need_copyout); if (!err && need_copyout) - if (copy_to_user(argp, &ifr, sizeof(struct ifreq))) + if (copy_to_user(argp, &ifr, ifreq_size)) return -EFAULT; } return err; @@ -1070,7 +1071,8 @@ static long sock_ioctl(struct file *file, unsigned cmd, unsigned long arg) err = open_related_ns(&net->ns, get_net_ns); break; default: - err = sock_do_ioctl(net, sock, cmd, arg); + err = sock_do_ioctl(net, sock, cmd, arg, + sizeof(struct ifreq)); break; } return err; @@ -2750,7 +2752,8 @@ static int do_siocgstamp(struct net *net, struct socket *sock, int err; set_fs(KERNEL_DS); - err = sock_do_ioctl(net, sock, cmd, (unsigned long)&ktv); + err = sock_do_ioctl(net, sock, cmd, (unsigned long)&ktv, + sizeof(struct compat_ifreq)); set_fs(old_fs); if (!err) err = compat_put_timeval(&ktv, up); @@ -2766,7 +2769,8 @@ static int do_siocgstampns(struct net *net, struct socket *sock, int err; set_fs(KERNEL_DS); - err = sock_do_ioctl(net, sock, cmd, (unsigned long)&kts); + err = sock_do_ioctl(net, sock, cmd, (unsigned long)&kts, + sizeof(struct compat_ifreq)); set_fs(old_fs); if (!err) err = compat_put_timespec(&kts, up); @@ -3072,7 +3076,8 @@ static int routing_ioctl(struct net *net, struct socket *sock, } set_fs(KERNEL_DS); - ret = sock_do_ioctl(net, sock, cmd, (unsigned long) r); + ret = sock_do_ioctl(net, sock, cmd, (unsigned long) r, + sizeof(struct compat_ifreq)); set_fs(old_fs); out: @@ -3185,7 +3190,8 @@ static int compat_sock_ioctl_trans(struct file *file, struct socket *sock, case SIOCBONDSETHWADDR: case SIOCBONDCHANGEACTIVE: case SIOCGIFNAME: - return sock_do_ioctl(net, sock, cmd, arg); + return sock_do_ioctl(net, sock, cmd, arg, + sizeof(struct compat_ifreq)); } return -ENOIOCTLCMD; diff --git a/net/tipc/bearer.c b/net/tipc/bearer.c index 418f03d0be90..91891041e5e1 100644 --- a/net/tipc/bearer.c +++ b/net/tipc/bearer.c @@ -577,7 +577,7 @@ static int tipc_l2_rcv_msg(struct sk_buff *skb, struct net_device *dev, rcu_dereference_rtnl(orig_dev->tipc_ptr); if (likely(b && test_bit(0, &b->up) && (skb->pkt_type <= PACKET_MULTICAST))) { - skb->next = NULL; + skb_mark_not_on_list(skb); tipc_rcv(dev_net(b->pt.dev), skb, b); rcu_read_unlock(); return NET_RX_SUCCESS; diff --git a/net/tipc/netlink_compat.c b/net/tipc/netlink_compat.c index a2f76743c73a..6376467e78f8 100644 --- a/net/tipc/netlink_compat.c +++ b/net/tipc/netlink_compat.c @@ -185,6 +185,10 @@ static int __tipc_nl_compat_dumpit(struct tipc_nl_compat_cmd_dump *cmd, return -ENOMEM; buf->sk = msg->dst_sk; + if (__tipc_dump_start(&cb, msg->net)) { + kfree_skb(buf); + return -ENOMEM; + } do { int rem; @@ -216,6 +220,7 @@ static int __tipc_nl_compat_dumpit(struct tipc_nl_compat_cmd_dump *cmd, err = 0; err_out: + tipc_dump_done(&cb); kfree_skb(buf); if (err == -EMSGSIZE) { diff --git a/net/tipc/socket.c b/net/tipc/socket.c index ab7a2a7178f7..3f03ddd0e35b 100644 --- a/net/tipc/socket.c +++ b/net/tipc/socket.c @@ -576,6 +576,7 @@ static int tipc_release(struct socket *sock) sk_stop_timer(sk, &sk->sk_timer); tipc_sk_remove(tsk); + sock_orphan(sk); /* Reject any messages that accumulated in backlog queue */ release_sock(sk); tipc_dest_list_purge(&tsk->cong_links); @@ -3229,7 +3230,7 @@ int tipc_nl_sk_walk(struct sk_buff *skb, struct netlink_callback *cb, struct netlink_callback *cb, struct tipc_sock *tsk)) { - struct rhashtable_iter *iter = (void *)cb->args[0]; + struct rhashtable_iter *iter = (void *)cb->args[4]; struct tipc_sock *tsk; int err; @@ -3265,8 +3266,14 @@ EXPORT_SYMBOL(tipc_nl_sk_walk); int tipc_dump_start(struct netlink_callback *cb) { - struct rhashtable_iter *iter = (void *)cb->args[0]; - struct net *net = sock_net(cb->skb->sk); + return __tipc_dump_start(cb, sock_net(cb->skb->sk)); +} +EXPORT_SYMBOL(tipc_dump_start); + +int __tipc_dump_start(struct netlink_callback *cb, struct net *net) +{ + /* tipc_nl_name_table_dump() uses cb->args[0...3]. */ + struct rhashtable_iter *iter = (void *)cb->args[4]; struct tipc_net *tn = tipc_net(net); if (!iter) { @@ -3274,17 +3281,16 @@ int tipc_dump_start(struct netlink_callback *cb) if (!iter) return -ENOMEM; - cb->args[0] = (long)iter; + cb->args[4] = (long)iter; } rhashtable_walk_enter(&tn->sk_rht, iter); return 0; } -EXPORT_SYMBOL(tipc_dump_start); int tipc_dump_done(struct netlink_callback *cb) { - struct rhashtable_iter *hti = (void *)cb->args[0]; + struct rhashtable_iter *hti = (void *)cb->args[4]; rhashtable_walk_exit(hti); kfree(hti); diff --git a/net/tipc/socket.h b/net/tipc/socket.h index d43032e26532..5e575f205afe 100644 --- a/net/tipc/socket.h +++ b/net/tipc/socket.h @@ -69,5 +69,6 @@ int tipc_nl_sk_walk(struct sk_buff *skb, struct netlink_callback *cb, struct netlink_callback *cb, struct tipc_sock *tsk)); int tipc_dump_start(struct netlink_callback *cb); +int __tipc_dump_start(struct netlink_callback *cb, struct net *net); int tipc_dump_done(struct netlink_callback *cb); #endif diff --git a/net/tls/tls_device.c b/net/tls/tls_device.c index 292742e50bfa..961b07d4d41c 100644 --- a/net/tls/tls_device.c +++ b/net/tls/tls_device.c @@ -686,7 +686,7 @@ int tls_set_device_offload(struct sock *sk, struct tls_context *ctx) goto free_marker_record; } - crypto_info = &ctx->crypto_send; + crypto_info = &ctx->crypto_send.info; switch (crypto_info->cipher_type) { case TLS_CIPHER_AES_GCM_128: nonce_size = TLS_CIPHER_AES_GCM_128_IV_SIZE; @@ -780,7 +780,7 @@ int tls_set_device_offload(struct sock *sk, struct tls_context *ctx) ctx->priv_ctx_tx = offload_ctx; rc = netdev->tlsdev_ops->tls_dev_add(netdev, sk, TLS_OFFLOAD_CTX_DIR_TX, - &ctx->crypto_send, + &ctx->crypto_send.info, tcp_sk(sk)->write_seq); if (rc) goto release_netdev; @@ -862,7 +862,7 @@ int tls_set_device_offload_rx(struct sock *sk, struct tls_context *ctx) goto release_ctx; rc = netdev->tlsdev_ops->tls_dev_add(netdev, sk, TLS_OFFLOAD_CTX_DIR_RX, - &ctx->crypto_recv, + &ctx->crypto_recv.info, tcp_sk(sk)->copied_seq); if (rc) { pr_err_ratelimited("%s: The netdev has refused to offload this socket\n", diff --git a/net/tls/tls_device_fallback.c b/net/tls/tls_device_fallback.c index 6102169239d1..450a6dbc5a88 100644 --- a/net/tls/tls_device_fallback.c +++ b/net/tls/tls_device_fallback.c @@ -320,7 +320,7 @@ static struct sk_buff *tls_enc_skb(struct tls_context *tls_ctx, goto free_req; iv = buf; - memcpy(iv, tls_ctx->crypto_send_aes_gcm_128.salt, + memcpy(iv, tls_ctx->crypto_send.aes_gcm_128.salt, TLS_CIPHER_AES_GCM_128_SALT_SIZE); aad = buf + TLS_CIPHER_AES_GCM_128_SALT_SIZE + TLS_CIPHER_AES_GCM_128_IV_SIZE; diff --git a/net/tls/tls_main.c b/net/tls/tls_main.c index 180b6640e531..b428069a1b05 100644 --- a/net/tls/tls_main.c +++ b/net/tls/tls_main.c @@ -141,7 +141,6 @@ retry: size = sg->length; } - clear_bit(TLS_PENDING_CLOSED_RECORD, &ctx->flags); ctx->in_tcp_sendpages = false; ctx->sk_write_space(sk); @@ -193,15 +192,12 @@ int tls_proccess_cmsg(struct sock *sk, struct msghdr *msg, return rc; } -int tls_push_pending_closed_record(struct sock *sk, struct tls_context *ctx, - int flags, long *timeo) +int tls_push_partial_record(struct sock *sk, struct tls_context *ctx, + int flags) { struct scatterlist *sg; u16 offset; - if (!tls_is_partially_sent_record(ctx)) - return ctx->push_pending_record(sk, flags); - sg = ctx->partially_sent_record; offset = ctx->partially_sent_offset; @@ -209,9 +205,23 @@ int tls_push_pending_closed_record(struct sock *sk, struct tls_context *ctx, return tls_push_sg(sk, ctx, sg, offset, flags); } +int tls_push_pending_closed_record(struct sock *sk, + struct tls_context *tls_ctx, + int flags, long *timeo) +{ + struct tls_sw_context_tx *ctx = tls_sw_ctx_tx(tls_ctx); + + if (tls_is_partially_sent_record(tls_ctx) || + !list_empty(&ctx->tx_list)) + return tls_tx_records(sk, flags); + else + return tls_ctx->push_pending_record(sk, flags); +} + static void tls_write_space(struct sock *sk) { struct tls_context *ctx = tls_get_ctx(sk); + struct tls_sw_context_tx *tx_ctx = tls_sw_ctx_tx(ctx); /* If in_tcp_sendpages call lower protocol write space handler * to ensure we wake up any waiting operations there. For example @@ -222,25 +232,26 @@ static void tls_write_space(struct sock *sk) return; } - if (!sk->sk_write_pending && tls_is_pending_closed_record(ctx)) { - gfp_t sk_allocation = sk->sk_allocation; - int rc; - long timeo = 0; - - sk->sk_allocation = GFP_ATOMIC; - rc = tls_push_pending_closed_record(sk, ctx, - MSG_DONTWAIT | - MSG_NOSIGNAL, - &timeo); - sk->sk_allocation = sk_allocation; - - if (rc < 0) - return; + /* Schedule the transmission if tx list is ready */ + if (is_tx_ready(tx_ctx) && !sk->sk_write_pending) { + /* Schedule the transmission */ + if (!test_and_set_bit(BIT_TX_SCHEDULED, &tx_ctx->tx_bitmask)) + schedule_delayed_work(&tx_ctx->tx_work.work, 0); } ctx->sk_write_space(sk); } +static void tls_ctx_free(struct tls_context *ctx) +{ + if (!ctx) + return; + + memzero_explicit(&ctx->crypto_send, sizeof(ctx->crypto_send)); + memzero_explicit(&ctx->crypto_recv, sizeof(ctx->crypto_recv)); + kfree(ctx); +} + static void tls_sk_proto_close(struct sock *sk, long timeout) { struct tls_context *ctx = tls_get_ctx(sk); @@ -260,19 +271,6 @@ static void tls_sk_proto_close(struct sock *sk, long timeout) if (!tls_complete_pending_work(sk, ctx, 0, &timeo)) tls_handle_open_record(sk, 0); - if (ctx->partially_sent_record) { - struct scatterlist *sg = ctx->partially_sent_record; - - while (1) { - put_page(sg_page(sg)); - sk_mem_uncharge(sk, sg->length); - - if (sg_is_last(sg)) - break; - sg++; - } - } - /* We need these for tls_sw_fallback handling of other packets */ if (ctx->tx_conf == TLS_SW) { kfree(ctx->tx.rec_seq); @@ -294,7 +292,7 @@ static void tls_sk_proto_close(struct sock *sk, long timeout) #else { #endif - kfree(ctx); + tls_ctx_free(ctx); ctx = NULL; } @@ -305,7 +303,7 @@ skip_tx_cleanup: * for sk->sk_prot->unhash [tls_hw_unhash] */ if (free_ctx) - kfree(ctx); + tls_ctx_free(ctx); } static int do_tls_getsockopt_tx(struct sock *sk, char __user *optval, @@ -330,7 +328,7 @@ static int do_tls_getsockopt_tx(struct sock *sk, char __user *optval, } /* get user crypto info */ - crypto_info = &ctx->crypto_send; + crypto_info = &ctx->crypto_send.info; if (!TLS_CRYPTO_INFO_READY(crypto_info)) { rc = -EBUSY; @@ -417,9 +415,9 @@ static int do_tls_setsockopt_conf(struct sock *sk, char __user *optval, } if (tx) - crypto_info = &ctx->crypto_send; + crypto_info = &ctx->crypto_send.info; else - crypto_info = &ctx->crypto_recv; + crypto_info = &ctx->crypto_recv.info; /* Currently we don't support set crypto info more than one time */ if (TLS_CRYPTO_INFO_READY(crypto_info)) { @@ -499,7 +497,7 @@ static int do_tls_setsockopt_conf(struct sock *sk, char __user *optval, goto out; err_crypto_info: - memset(crypto_info, 0, sizeof(*crypto_info)); + memzero_explicit(crypto_info, sizeof(union tls_crypto_context)); out: return rc; } diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c index be4f2e990f9f..4c18b4dba284 100644 --- a/net/tls/tls_sw.c +++ b/net/tls/tls_sw.c @@ -122,25 +122,32 @@ static int skb_nsg(struct sk_buff *skb, int offset, int len) static void tls_decrypt_done(struct crypto_async_request *req, int err) { struct aead_request *aead_req = (struct aead_request *)req; - struct decrypt_req_ctx *req_ctx = - (struct decrypt_req_ctx *)(aead_req + 1); - struct scatterlist *sgout = aead_req->dst; - - struct tls_context *tls_ctx = tls_get_ctx(req_ctx->sk); - struct tls_sw_context_rx *ctx = tls_sw_ctx_rx(tls_ctx); - int pending = atomic_dec_return(&ctx->decrypt_pending); + struct tls_sw_context_rx *ctx; + struct tls_context *tls_ctx; struct scatterlist *sg; + struct sk_buff *skb; unsigned int pages; + int pending; + + skb = (struct sk_buff *)req->data; + tls_ctx = tls_get_ctx(skb->sk); + ctx = tls_sw_ctx_rx(tls_ctx); + pending = atomic_dec_return(&ctx->decrypt_pending); /* Propagate if there was an err */ if (err) { ctx->async_wait.err = err; - tls_err_abort(req_ctx->sk, err); + tls_err_abort(skb->sk, err); } + /* After using skb->sk to propagate sk through crypto async callback + * we need to NULL it again. + */ + skb->sk = NULL; + /* Release the skb, pages and memory allocated for crypto req */ - kfree_skb(req->data); + kfree_skb(skb); /* Skip the first S/G entry as it points to AAD */ for_each_sg(sg_next(sgout), sg, UINT_MAX, pages) { @@ -175,11 +182,13 @@ static int tls_do_decryption(struct sock *sk, (u8 *)iv_recv); if (async) { - struct decrypt_req_ctx *req_ctx; - - req_ctx = (struct decrypt_req_ctx *)(aead_req + 1); - req_ctx->sk = sk; - + /* Using skb->sk to push sk through to crypto async callback + * handler. This allows propagating errors up to the socket + * if needed. It _must_ be cleared in the async handler + * before kfree_skb is called. We _know_ skb->sk is NULL + * because it is a clone from strparser. + */ + skb->sk = sk; aead_request_set_callback(aead_req, CRYPTO_TFM_REQ_MAY_BACKLOG, tls_decrypt_done, skb); @@ -237,18 +246,19 @@ static void trim_both_sgl(struct sock *sk, int target_size) { struct tls_context *tls_ctx = tls_get_ctx(sk); struct tls_sw_context_tx *ctx = tls_sw_ctx_tx(tls_ctx); + struct tls_rec *rec = ctx->open_rec; - trim_sg(sk, ctx->sg_plaintext_data, - &ctx->sg_plaintext_num_elem, - &ctx->sg_plaintext_size, + trim_sg(sk, rec->sg_plaintext_data, + &rec->sg_plaintext_num_elem, + &rec->sg_plaintext_size, target_size); if (target_size > 0) target_size += tls_ctx->tx.overhead_size; - trim_sg(sk, ctx->sg_encrypted_data, - &ctx->sg_encrypted_num_elem, - &ctx->sg_encrypted_size, + trim_sg(sk, rec->sg_encrypted_data, + &rec->sg_encrypted_num_elem, + &rec->sg_encrypted_size, target_size); } @@ -256,12 +266,16 @@ static int alloc_encrypted_sg(struct sock *sk, int len) { struct tls_context *tls_ctx = tls_get_ctx(sk); struct tls_sw_context_tx *ctx = tls_sw_ctx_tx(tls_ctx); + struct tls_rec *rec = ctx->open_rec; int rc = 0; rc = sk_alloc_sg(sk, len, - ctx->sg_encrypted_data, 0, - &ctx->sg_encrypted_num_elem, - &ctx->sg_encrypted_size, 0); + rec->sg_encrypted_data, 0, + &rec->sg_encrypted_num_elem, + &rec->sg_encrypted_size, 0); + + if (rc == -ENOSPC) + rec->sg_encrypted_num_elem = ARRAY_SIZE(rec->sg_encrypted_data); return rc; } @@ -270,12 +284,16 @@ static int alloc_plaintext_sg(struct sock *sk, int len) { struct tls_context *tls_ctx = tls_get_ctx(sk); struct tls_sw_context_tx *ctx = tls_sw_ctx_tx(tls_ctx); + struct tls_rec *rec = ctx->open_rec; int rc = 0; - rc = sk_alloc_sg(sk, len, ctx->sg_plaintext_data, 0, - &ctx->sg_plaintext_num_elem, &ctx->sg_plaintext_size, + rc = sk_alloc_sg(sk, len, rec->sg_plaintext_data, 0, + &rec->sg_plaintext_num_elem, &rec->sg_plaintext_size, tls_ctx->pending_open_record_frags); + if (rc == -ENOSPC) + rec->sg_plaintext_num_elem = ARRAY_SIZE(rec->sg_plaintext_data); + return rc; } @@ -292,41 +310,190 @@ static void free_sg(struct sock *sk, struct scatterlist *sg, *sg_size = 0; } -static void tls_free_both_sg(struct sock *sk) +static void tls_free_open_rec(struct sock *sk) { struct tls_context *tls_ctx = tls_get_ctx(sk); struct tls_sw_context_tx *ctx = tls_sw_ctx_tx(tls_ctx); + struct tls_rec *rec = ctx->open_rec; + + /* Return if there is no open record */ + if (!rec) + return; + + free_sg(sk, rec->sg_encrypted_data, + &rec->sg_encrypted_num_elem, + &rec->sg_encrypted_size); + + free_sg(sk, rec->sg_plaintext_data, + &rec->sg_plaintext_num_elem, + &rec->sg_plaintext_size); + + kfree(rec); +} + +int tls_tx_records(struct sock *sk, int flags) +{ + struct tls_context *tls_ctx = tls_get_ctx(sk); + struct tls_sw_context_tx *ctx = tls_sw_ctx_tx(tls_ctx); + struct tls_rec *rec, *tmp; + int tx_flags, rc = 0; + + if (tls_is_partially_sent_record(tls_ctx)) { + rec = list_first_entry(&ctx->tx_list, + struct tls_rec, list); + + if (flags == -1) + tx_flags = rec->tx_flags; + else + tx_flags = flags; - free_sg(sk, ctx->sg_encrypted_data, &ctx->sg_encrypted_num_elem, - &ctx->sg_encrypted_size); + rc = tls_push_partial_record(sk, tls_ctx, tx_flags); + if (rc) + goto tx_err; - free_sg(sk, ctx->sg_plaintext_data, &ctx->sg_plaintext_num_elem, - &ctx->sg_plaintext_size); + /* Full record has been transmitted. + * Remove the head of tx_list + */ + list_del(&rec->list); + free_sg(sk, rec->sg_plaintext_data, + &rec->sg_plaintext_num_elem, &rec->sg_plaintext_size); + + kfree(rec); + } + + /* Tx all ready records */ + list_for_each_entry_safe(rec, tmp, &ctx->tx_list, list) { + if (READ_ONCE(rec->tx_ready)) { + if (flags == -1) + tx_flags = rec->tx_flags; + else + tx_flags = flags; + + rc = tls_push_sg(sk, tls_ctx, + &rec->sg_encrypted_data[0], + 0, tx_flags); + if (rc) + goto tx_err; + + list_del(&rec->list); + free_sg(sk, rec->sg_plaintext_data, + &rec->sg_plaintext_num_elem, + &rec->sg_plaintext_size); + + kfree(rec); + } else { + break; + } + } + +tx_err: + if (rc < 0 && rc != -EAGAIN) + tls_err_abort(sk, EBADMSG); + + return rc; } -static int tls_do_encryption(struct tls_context *tls_ctx, +static void tls_encrypt_done(struct crypto_async_request *req, int err) +{ + struct aead_request *aead_req = (struct aead_request *)req; + struct sock *sk = req->data; + struct tls_context *tls_ctx = tls_get_ctx(sk); + struct tls_sw_context_tx *ctx = tls_sw_ctx_tx(tls_ctx); + struct tls_rec *rec; + bool ready = false; + int pending; + + rec = container_of(aead_req, struct tls_rec, aead_req); + + rec->sg_encrypted_data[0].offset -= tls_ctx->tx.prepend_size; + rec->sg_encrypted_data[0].length += tls_ctx->tx.prepend_size; + + + /* Free the record if error is previously set on socket */ + if (err || sk->sk_err) { + free_sg(sk, rec->sg_encrypted_data, + &rec->sg_encrypted_num_elem, &rec->sg_encrypted_size); + + kfree(rec); + rec = NULL; + + /* If err is already set on socket, return the same code */ + if (sk->sk_err) { + ctx->async_wait.err = sk->sk_err; + } else { + ctx->async_wait.err = err; + tls_err_abort(sk, err); + } + } + + if (rec) { + struct tls_rec *first_rec; + + /* Mark the record as ready for transmission */ + smp_store_mb(rec->tx_ready, true); + + /* If received record is at head of tx_list, schedule tx */ + first_rec = list_first_entry(&ctx->tx_list, + struct tls_rec, list); + if (rec == first_rec) + ready = true; + } + + pending = atomic_dec_return(&ctx->encrypt_pending); + + if (!pending && READ_ONCE(ctx->async_notify)) + complete(&ctx->async_wait.completion); + + if (!ready) + return; + + /* Schedule the transmission */ + if (!test_and_set_bit(BIT_TX_SCHEDULED, &ctx->tx_bitmask)) + schedule_delayed_work(&ctx->tx_work.work, 1); +} + +static int tls_do_encryption(struct sock *sk, + struct tls_context *tls_ctx, struct tls_sw_context_tx *ctx, struct aead_request *aead_req, size_t data_len) { + struct tls_rec *rec = ctx->open_rec; int rc; - ctx->sg_encrypted_data[0].offset += tls_ctx->tx.prepend_size; - ctx->sg_encrypted_data[0].length -= tls_ctx->tx.prepend_size; + rec->sg_encrypted_data[0].offset += tls_ctx->tx.prepend_size; + rec->sg_encrypted_data[0].length -= tls_ctx->tx.prepend_size; aead_request_set_tfm(aead_req, ctx->aead_send); aead_request_set_ad(aead_req, TLS_AAD_SPACE_SIZE); - aead_request_set_crypt(aead_req, ctx->sg_aead_in, ctx->sg_aead_out, + aead_request_set_crypt(aead_req, rec->sg_aead_in, + rec->sg_aead_out, data_len, tls_ctx->tx.iv); aead_request_set_callback(aead_req, CRYPTO_TFM_REQ_MAY_BACKLOG, - crypto_req_done, &ctx->async_wait); + tls_encrypt_done, sk); + + /* Add the record in tx_list */ + list_add_tail((struct list_head *)&rec->list, &ctx->tx_list); + atomic_inc(&ctx->encrypt_pending); - rc = crypto_wait_req(crypto_aead_encrypt(aead_req), &ctx->async_wait); + rc = crypto_aead_encrypt(aead_req); + if (!rc || rc != -EINPROGRESS) { + atomic_dec(&ctx->encrypt_pending); + rec->sg_encrypted_data[0].offset -= tls_ctx->tx.prepend_size; + rec->sg_encrypted_data[0].length += tls_ctx->tx.prepend_size; + } - ctx->sg_encrypted_data[0].offset -= tls_ctx->tx.prepend_size; - ctx->sg_encrypted_data[0].length += tls_ctx->tx.prepend_size; + if (!rc) { + WRITE_ONCE(rec->tx_ready, true); + } else if (rc != -EINPROGRESS) { + list_del(&rec->list); + return rc; + } + /* Unhook the record from context if encryption is not failure */ + ctx->open_rec = NULL; + tls_advance_record_sn(sk, &tls_ctx->tx); return rc; } @@ -335,53 +502,40 @@ static int tls_push_record(struct sock *sk, int flags, { struct tls_context *tls_ctx = tls_get_ctx(sk); struct tls_sw_context_tx *ctx = tls_sw_ctx_tx(tls_ctx); + struct tls_rec *rec = ctx->open_rec; struct aead_request *req; int rc; - req = aead_request_alloc(ctx->aead_send, sk->sk_allocation); - if (!req) - return -ENOMEM; + if (!rec) + return 0; + + rec->tx_flags = flags; + req = &rec->aead_req; - sg_mark_end(ctx->sg_plaintext_data + ctx->sg_plaintext_num_elem - 1); - sg_mark_end(ctx->sg_encrypted_data + ctx->sg_encrypted_num_elem - 1); + sg_mark_end(rec->sg_plaintext_data + rec->sg_plaintext_num_elem - 1); + sg_mark_end(rec->sg_encrypted_data + rec->sg_encrypted_num_elem - 1); - tls_make_aad(ctx->aad_space, ctx->sg_plaintext_size, + tls_make_aad(rec->aad_space, rec->sg_plaintext_size, tls_ctx->tx.rec_seq, tls_ctx->tx.rec_seq_size, record_type); tls_fill_prepend(tls_ctx, - page_address(sg_page(&ctx->sg_encrypted_data[0])) + - ctx->sg_encrypted_data[0].offset, - ctx->sg_plaintext_size, record_type); + page_address(sg_page(&rec->sg_encrypted_data[0])) + + rec->sg_encrypted_data[0].offset, + rec->sg_plaintext_size, record_type); tls_ctx->pending_open_record_frags = 0; - set_bit(TLS_PENDING_CLOSED_RECORD, &tls_ctx->flags); - rc = tls_do_encryption(tls_ctx, ctx, req, ctx->sg_plaintext_size); - if (rc < 0) { - /* If we are called from write_space and - * we fail, we need to set this SOCK_NOSPACE - * to trigger another write_space in the future. - */ - set_bit(SOCK_NOSPACE, &sk->sk_socket->flags); - goto out_req; - } - - free_sg(sk, ctx->sg_plaintext_data, &ctx->sg_plaintext_num_elem, - &ctx->sg_plaintext_size); - - ctx->sg_encrypted_num_elem = 0; - ctx->sg_encrypted_size = 0; + rc = tls_do_encryption(sk, tls_ctx, ctx, req, rec->sg_plaintext_size); + if (rc == -EINPROGRESS) + return -EINPROGRESS; - /* Only pass through MSG_DONTWAIT and MSG_NOSIGNAL flags */ - rc = tls_push_sg(sk, tls_ctx, ctx->sg_encrypted_data, 0, flags); - if (rc < 0 && rc != -EAGAIN) + if (rc < 0) { tls_err_abort(sk, EBADMSG); + return rc; + } - tls_advance_record_sn(sk, &tls_ctx->tx); -out_req: - aead_request_free(req); - return rc; + return tls_tx_records(sk, flags); } static int tls_sw_push_pending_record(struct sock *sk, int flags) @@ -458,11 +612,12 @@ static int memcopy_from_iter(struct sock *sk, struct iov_iter *from, { struct tls_context *tls_ctx = tls_get_ctx(sk); struct tls_sw_context_tx *ctx = tls_sw_ctx_tx(tls_ctx); - struct scatterlist *sg = ctx->sg_plaintext_data; + struct tls_rec *rec = ctx->open_rec; + struct scatterlist *sg = rec->sg_plaintext_data; int copy, i, rc = 0; for (i = tls_ctx->pending_open_record_frags; - i < ctx->sg_plaintext_num_elem; ++i) { + i < rec->sg_plaintext_num_elem; ++i) { copy = sg[i].length; if (copy_from_iter( page_address(sg_page(&sg[i])) + sg[i].offset, @@ -482,33 +637,85 @@ out: return rc; } -int tls_sw_sendmsg(struct sock *sk, struct msghdr *msg, size_t size) +struct tls_rec *get_rec(struct sock *sk) { struct tls_context *tls_ctx = tls_get_ctx(sk); struct tls_sw_context_tx *ctx = tls_sw_ctx_tx(tls_ctx); - int ret = 0; - int required_size; + struct tls_rec *rec; + int mem_size; + + /* Return if we already have an open record */ + if (ctx->open_rec) + return ctx->open_rec; + + mem_size = sizeof(struct tls_rec) + crypto_aead_reqsize(ctx->aead_send); + + rec = kzalloc(mem_size, sk->sk_allocation); + if (!rec) + return NULL; + + sg_init_table(&rec->sg_plaintext_data[0], + ARRAY_SIZE(rec->sg_plaintext_data)); + sg_init_table(&rec->sg_encrypted_data[0], + ARRAY_SIZE(rec->sg_encrypted_data)); + + sg_init_table(rec->sg_aead_in, 2); + sg_set_buf(&rec->sg_aead_in[0], rec->aad_space, + sizeof(rec->aad_space)); + sg_unmark_end(&rec->sg_aead_in[1]); + sg_chain(rec->sg_aead_in, 2, rec->sg_plaintext_data); + + sg_init_table(rec->sg_aead_out, 2); + sg_set_buf(&rec->sg_aead_out[0], rec->aad_space, + sizeof(rec->aad_space)); + sg_unmark_end(&rec->sg_aead_out[1]); + sg_chain(rec->sg_aead_out, 2, rec->sg_encrypted_data); + + ctx->open_rec = rec; + + return rec; +} + +int tls_sw_sendmsg(struct sock *sk, struct msghdr *msg, size_t size) +{ long timeo = sock_sndtimeo(sk, msg->msg_flags & MSG_DONTWAIT); + struct tls_context *tls_ctx = tls_get_ctx(sk); + struct tls_sw_context_tx *ctx = tls_sw_ctx_tx(tls_ctx); + struct crypto_tfm *tfm = crypto_aead_tfm(ctx->aead_send); + bool async_capable = tfm->__crt_alg->cra_flags & CRYPTO_ALG_ASYNC; + unsigned char record_type = TLS_RECORD_TYPE_DATA; + bool is_kvec = msg->msg_iter.type & ITER_KVEC; bool eor = !(msg->msg_flags & MSG_MORE); size_t try_to_copy, copied = 0; - unsigned char record_type = TLS_RECORD_TYPE_DATA; - int record_room; + struct tls_rec *rec; + int required_size; + int num_async = 0; bool full_record; + int record_room; + int num_zc = 0; int orig_size; - bool is_kvec = msg->msg_iter.type & ITER_KVEC; + int ret = 0; if (msg->msg_flags & ~(MSG_MORE | MSG_DONTWAIT | MSG_NOSIGNAL)) return -ENOTSUPP; lock_sock(sk); - if (tls_complete_pending_work(sk, tls_ctx, msg->msg_flags, &timeo)) - goto send_end; + /* Wait till there is any pending write on socket */ + if (unlikely(sk->sk_write_pending)) { + ret = wait_on_pending_writer(sk, &timeo); + if (unlikely(ret)) + goto send_end; + } if (unlikely(msg->msg_controllen)) { ret = tls_proccess_cmsg(sk, msg, &record_type); - if (ret) - goto send_end; + if (ret) { + if (ret == -EINPROGRESS) + num_async++; + else if (ret != -EAGAIN) + goto send_end; + } } while (msg_data_left(msg)) { @@ -517,20 +724,27 @@ int tls_sw_sendmsg(struct sock *sk, struct msghdr *msg, size_t size) goto send_end; } - orig_size = ctx->sg_plaintext_size; + rec = get_rec(sk); + if (!rec) { + ret = -ENOMEM; + goto send_end; + } + + orig_size = rec->sg_plaintext_size; full_record = false; try_to_copy = msg_data_left(msg); - record_room = TLS_MAX_PAYLOAD_SIZE - ctx->sg_plaintext_size; + record_room = TLS_MAX_PAYLOAD_SIZE - rec->sg_plaintext_size; if (try_to_copy >= record_room) { try_to_copy = record_room; full_record = true; } - required_size = ctx->sg_plaintext_size + try_to_copy + + required_size = rec->sg_plaintext_size + try_to_copy + tls_ctx->tx.overhead_size; if (!sk_stream_memory_free(sk)) goto wait_for_sndbuf; + alloc_encrypted: ret = alloc_encrypted_sg(sk, required_size); if (ret) { @@ -541,33 +755,39 @@ alloc_encrypted: * actually allocated. The difference is due * to max sg elements limit */ - try_to_copy -= required_size - ctx->sg_encrypted_size; + try_to_copy -= required_size - rec->sg_encrypted_size; full_record = true; } - if (!is_kvec && (full_record || eor)) { + + if (!is_kvec && (full_record || eor) && !async_capable) { ret = zerocopy_from_iter(sk, &msg->msg_iter, - try_to_copy, &ctx->sg_plaintext_num_elem, - &ctx->sg_plaintext_size, - ctx->sg_plaintext_data, - ARRAY_SIZE(ctx->sg_plaintext_data), + try_to_copy, &rec->sg_plaintext_num_elem, + &rec->sg_plaintext_size, + rec->sg_plaintext_data, + ARRAY_SIZE(rec->sg_plaintext_data), true); if (ret) goto fallback_to_reg_send; + num_zc++; copied += try_to_copy; ret = tls_push_record(sk, msg->msg_flags, record_type); - if (ret) - goto send_end; + if (ret) { + if (ret == -EINPROGRESS) + num_async++; + else if (ret != -EAGAIN) + goto send_end; + } continue; fallback_to_reg_send: - trim_sg(sk, ctx->sg_plaintext_data, - &ctx->sg_plaintext_num_elem, - &ctx->sg_plaintext_size, + trim_sg(sk, rec->sg_plaintext_data, + &rec->sg_plaintext_num_elem, + &rec->sg_plaintext_size, orig_size); } - required_size = ctx->sg_plaintext_size + try_to_copy; + required_size = rec->sg_plaintext_size + try_to_copy; alloc_plaintext: ret = alloc_plaintext_sg(sk, required_size); if (ret) { @@ -578,13 +798,13 @@ alloc_plaintext: * actually allocated. The difference is due * to max sg elements limit */ - try_to_copy -= required_size - ctx->sg_plaintext_size; + try_to_copy -= required_size - rec->sg_plaintext_size; full_record = true; - trim_sg(sk, ctx->sg_encrypted_data, - &ctx->sg_encrypted_num_elem, - &ctx->sg_encrypted_size, - ctx->sg_plaintext_size + + trim_sg(sk, rec->sg_encrypted_data, + &rec->sg_encrypted_num_elem, + &rec->sg_encrypted_size, + rec->sg_plaintext_size + tls_ctx->tx.overhead_size); } @@ -594,13 +814,12 @@ alloc_plaintext: copied += try_to_copy; if (full_record || eor) { -push_record: ret = tls_push_record(sk, msg->msg_flags, record_type); if (ret) { - if (ret == -ENOMEM) - goto wait_for_memory; - - goto send_end; + if (ret == -EINPROGRESS) + num_async++; + else if (ret != -EAGAIN) + goto send_end; } } @@ -616,15 +835,37 @@ trim_sgl: goto send_end; } - if (tls_is_pending_closed_record(tls_ctx)) - goto push_record; - - if (ctx->sg_encrypted_size < required_size) + if (rec->sg_encrypted_size < required_size) goto alloc_encrypted; goto alloc_plaintext; } + if (!num_async) { + goto send_end; + } else if (num_zc) { + /* Wait for pending encryptions to get completed */ + smp_store_mb(ctx->async_notify, true); + + if (atomic_read(&ctx->encrypt_pending)) + crypto_wait_req(-EINPROGRESS, &ctx->async_wait); + else + reinit_completion(&ctx->async_wait.completion); + + WRITE_ONCE(ctx->async_notify, false); + + if (ctx->async_wait.err) { + ret = ctx->async_wait.err; + copied = 0; + } + } + + /* Transmit if any encryptions have completed */ + if (test_and_clear_bit(BIT_TX_SCHEDULED, &ctx->tx_bitmask)) { + cancel_delayed_work(&ctx->tx_work.work); + tls_tx_records(sk, msg->msg_flags); + } + send_end: ret = sk_stream_error(sk, msg->msg_flags, ret); @@ -635,16 +876,18 @@ send_end: int tls_sw_sendpage(struct sock *sk, struct page *page, int offset, size_t size, int flags) { + long timeo = sock_sndtimeo(sk, flags & MSG_DONTWAIT); struct tls_context *tls_ctx = tls_get_ctx(sk); struct tls_sw_context_tx *ctx = tls_sw_ctx_tx(tls_ctx); - int ret = 0; - long timeo = sock_sndtimeo(sk, flags & MSG_DONTWAIT); - bool eor; - size_t orig_size = size; unsigned char record_type = TLS_RECORD_TYPE_DATA; + size_t orig_size = size; struct scatterlist *sg; + struct tls_rec *rec; + int num_async = 0; bool full_record; int record_room; + int ret = 0; + bool eor; if (flags & ~(MSG_MORE | MSG_DONTWAIT | MSG_NOSIGNAL | MSG_SENDPAGE_NOTLAST)) @@ -657,8 +900,12 @@ int tls_sw_sendpage(struct sock *sk, struct page *page, sk_clear_bit(SOCKWQ_ASYNC_NOSPACE, sk); - if (tls_complete_pending_work(sk, tls_ctx, flags, &timeo)) - goto sendpage_end; + /* Wait till there is any pending write on socket */ + if (unlikely(sk->sk_write_pending)) { + ret = wait_on_pending_writer(sk, &timeo); + if (unlikely(ret)) + goto sendpage_end; + } /* Call the sk_stream functions to manage the sndbuf mem. */ while (size > 0) { @@ -669,14 +916,20 @@ int tls_sw_sendpage(struct sock *sk, struct page *page, goto sendpage_end; } + rec = get_rec(sk); + if (!rec) { + ret = -ENOMEM; + goto sendpage_end; + } + full_record = false; - record_room = TLS_MAX_PAYLOAD_SIZE - ctx->sg_plaintext_size; + record_room = TLS_MAX_PAYLOAD_SIZE - rec->sg_plaintext_size; copy = size; if (copy >= record_room) { copy = record_room; full_record = true; } - required_size = ctx->sg_plaintext_size + copy + + required_size = rec->sg_plaintext_size + copy + tls_ctx->tx.overhead_size; if (!sk_stream_memory_free(sk)) @@ -691,33 +944,32 @@ alloc_payload: * actually allocated. The difference is due * to max sg elements limit */ - copy -= required_size - ctx->sg_plaintext_size; + copy -= required_size - rec->sg_plaintext_size; full_record = true; } get_page(page); - sg = ctx->sg_plaintext_data + ctx->sg_plaintext_num_elem; + sg = rec->sg_plaintext_data + rec->sg_plaintext_num_elem; sg_set_page(sg, page, copy, offset); sg_unmark_end(sg); - ctx->sg_plaintext_num_elem++; + rec->sg_plaintext_num_elem++; sk_mem_charge(sk, copy); offset += copy; size -= copy; - ctx->sg_plaintext_size += copy; - tls_ctx->pending_open_record_frags = ctx->sg_plaintext_num_elem; + rec->sg_plaintext_size += copy; + tls_ctx->pending_open_record_frags = rec->sg_plaintext_num_elem; if (full_record || eor || - ctx->sg_plaintext_num_elem == - ARRAY_SIZE(ctx->sg_plaintext_data)) { -push_record: + rec->sg_plaintext_num_elem == + ARRAY_SIZE(rec->sg_plaintext_data)) { ret = tls_push_record(sk, flags, record_type); if (ret) { - if (ret == -ENOMEM) - goto wait_for_memory; - - goto sendpage_end; + if (ret == -EINPROGRESS) + num_async++; + else if (ret != -EAGAIN) + goto sendpage_end; } } continue; @@ -726,16 +978,20 @@ wait_for_sndbuf: wait_for_memory: ret = sk_stream_wait_memory(sk, &timeo); if (ret) { - trim_both_sgl(sk, ctx->sg_plaintext_size); + trim_both_sgl(sk, rec->sg_plaintext_size); goto sendpage_end; } - if (tls_is_pending_closed_record(tls_ctx)) - goto push_record; - goto alloc_payload; } + if (num_async) { + /* Transmit if any encryptions have completed */ + if (test_and_clear_bit(BIT_TX_SCHEDULED, &ctx->tx_bitmask)) { + cancel_delayed_work(&ctx->tx_work.work); + tls_tx_records(sk, flags); + } + } sendpage_end: if (orig_size > size) ret = orig_size - size; @@ -1092,6 +1348,13 @@ pick_next_record: } else { break; } + } else { + /* MSG_PEEK right now cannot look beyond current skb + * from strparser, meaning we cannot advance skb here + * and thus unpause strparser since we'd loose original + * one. + */ + break; } /* If we have a new message from strparser, continue now. */ @@ -1233,8 +1496,8 @@ static int tls_read_size(struct strparser *strp, struct sk_buff *skb) goto read_failure; } - if (header[1] != TLS_VERSION_MINOR(tls_ctx->crypto_recv.version) || - header[2] != TLS_VERSION_MAJOR(tls_ctx->crypto_recv.version)) { + if (header[1] != TLS_VERSION_MINOR(tls_ctx->crypto_recv.info.version) || + header[2] != TLS_VERSION_MAJOR(tls_ctx->crypto_recv.info.version)) { ret = -EINVAL; goto read_failure; } @@ -1276,9 +1539,61 @@ void tls_sw_free_resources_tx(struct sock *sk) { struct tls_context *tls_ctx = tls_get_ctx(sk); struct tls_sw_context_tx *ctx = tls_sw_ctx_tx(tls_ctx); + struct tls_rec *rec, *tmp; + + /* Wait for any pending async encryptions to complete */ + smp_store_mb(ctx->async_notify, true); + if (atomic_read(&ctx->encrypt_pending)) + crypto_wait_req(-EINPROGRESS, &ctx->async_wait); + + cancel_delayed_work_sync(&ctx->tx_work.work); + + /* Tx whatever records we can transmit and abandon the rest */ + tls_tx_records(sk, -1); + + /* Free up un-sent records in tx_list. First, free + * the partially sent record if any at head of tx_list. + */ + if (tls_ctx->partially_sent_record) { + struct scatterlist *sg = tls_ctx->partially_sent_record; + + while (1) { + put_page(sg_page(sg)); + sk_mem_uncharge(sk, sg->length); + + if (sg_is_last(sg)) + break; + sg++; + } + + tls_ctx->partially_sent_record = NULL; + + rec = list_first_entry(&ctx->tx_list, + struct tls_rec, list); + + free_sg(sk, rec->sg_plaintext_data, + &rec->sg_plaintext_num_elem, + &rec->sg_plaintext_size); + + list_del(&rec->list); + kfree(rec); + } + + list_for_each_entry_safe(rec, tmp, &ctx->tx_list, list) { + free_sg(sk, rec->sg_encrypted_data, + &rec->sg_encrypted_num_elem, + &rec->sg_encrypted_size); + + free_sg(sk, rec->sg_plaintext_data, + &rec->sg_plaintext_num_elem, + &rec->sg_plaintext_size); + + list_del(&rec->list); + kfree(rec); + } crypto_free_aead(ctx->aead_send); - tls_free_both_sg(sk); + tls_free_open_rec(sk); kfree(ctx); } @@ -1312,9 +1627,26 @@ void tls_sw_free_resources_rx(struct sock *sk) kfree(ctx); } +/* The work handler to transmitt the encrypted records in tx_list */ +static void tx_work_handler(struct work_struct *work) +{ + struct delayed_work *delayed_work = to_delayed_work(work); + struct tx_work *tx_work = container_of(delayed_work, + struct tx_work, work); + struct sock *sk = tx_work->sk; + struct tls_context *tls_ctx = tls_get_ctx(sk); + struct tls_sw_context_tx *ctx = tls_sw_ctx_tx(tls_ctx); + + if (!test_and_clear_bit(BIT_TX_SCHEDULED, &ctx->tx_bitmask)) + return; + + lock_sock(sk); + tls_tx_records(sk, -1); + release_sock(sk); +} + int tls_set_sw_offload(struct sock *sk, struct tls_context *ctx, int tx) { - char keyval[TLS_CIPHER_AES_GCM_128_KEY_SIZE]; struct tls_crypto_info *crypto_info; struct tls12_crypto_info_aes_gcm_128 *gcm_128_info; struct tls_sw_context_tx *sw_ctx_tx = NULL; @@ -1359,12 +1691,15 @@ int tls_set_sw_offload(struct sock *sk, struct tls_context *ctx, int tx) if (tx) { crypto_init_wait(&sw_ctx_tx->async_wait); - crypto_info = &ctx->crypto_send; + crypto_info = &ctx->crypto_send.info; cctx = &ctx->tx; aead = &sw_ctx_tx->aead_send; + INIT_LIST_HEAD(&sw_ctx_tx->tx_list); + INIT_DELAYED_WORK(&sw_ctx_tx->tx_work.work, tx_work_handler); + sw_ctx_tx->tx_work.sk = sk; } else { crypto_init_wait(&sw_ctx_rx->async_wait); - crypto_info = &ctx->crypto_recv; + crypto_info = &ctx->crypto_recv.info; cctx = &ctx->rx; aead = &sw_ctx_rx->aead_recv; } @@ -1412,26 +1747,6 @@ int tls_set_sw_offload(struct sock *sk, struct tls_context *ctx, int tx) goto free_iv; } - if (sw_ctx_tx) { - sg_init_table(sw_ctx_tx->sg_encrypted_data, - ARRAY_SIZE(sw_ctx_tx->sg_encrypted_data)); - sg_init_table(sw_ctx_tx->sg_plaintext_data, - ARRAY_SIZE(sw_ctx_tx->sg_plaintext_data)); - - sg_init_table(sw_ctx_tx->sg_aead_in, 2); - sg_set_buf(&sw_ctx_tx->sg_aead_in[0], sw_ctx_tx->aad_space, - sizeof(sw_ctx_tx->aad_space)); - sg_unmark_end(&sw_ctx_tx->sg_aead_in[1]); - sg_chain(sw_ctx_tx->sg_aead_in, 2, - sw_ctx_tx->sg_plaintext_data); - sg_init_table(sw_ctx_tx->sg_aead_out, 2); - sg_set_buf(&sw_ctx_tx->sg_aead_out[0], sw_ctx_tx->aad_space, - sizeof(sw_ctx_tx->aad_space)); - sg_unmark_end(&sw_ctx_tx->sg_aead_out[1]); - sg_chain(sw_ctx_tx->sg_aead_out, 2, - sw_ctx_tx->sg_encrypted_data); - } - if (!*aead) { *aead = crypto_alloc_aead("gcm(aes)", 0, 0); if (IS_ERR(*aead)) { @@ -1443,9 +1758,7 @@ int tls_set_sw_offload(struct sock *sk, struct tls_context *ctx, int tx) ctx->push_pending_record = tls_sw_push_pending_record; - memcpy(keyval, gcm_128_info->key, TLS_CIPHER_AES_GCM_128_KEY_SIZE); - - rc = crypto_aead_setkey(*aead, keyval, + rc = crypto_aead_setkey(*aead, gcm_128_info->key, TLS_CIPHER_AES_GCM_128_KEY_SIZE); if (rc) goto free_aead; @@ -1455,8 +1768,6 @@ int tls_set_sw_offload(struct sock *sk, struct tls_context *ctx, int tx) goto free_aead; if (sw_ctx_rx) { - (*aead)->reqsize = sizeof(struct decrypt_req_ctx); - /* Set up strparser */ memset(&cb, 0, sizeof(cb)); cb.rcv_msg = tls_queue; diff --git a/net/xdp/xdp_umem.c b/net/xdp/xdp_umem.c index b3b632c5aeae..555427b3e0fe 100644 --- a/net/xdp/xdp_umem.c +++ b/net/xdp/xdp_umem.c @@ -165,6 +165,8 @@ static void xdp_umem_release(struct xdp_umem *umem) umem->cq = NULL; } + xsk_reuseq_destroy(umem); + xdp_umem_unpin_pages(umem); task = get_pid_task(umem->pid, PIDTYPE_PID); diff --git a/net/xdp/xsk_queue.c b/net/xdp/xsk_queue.c index 2dc1384d9f27..b66504592d9b 100644 --- a/net/xdp/xsk_queue.c +++ b/net/xdp/xsk_queue.c @@ -3,7 +3,9 @@ * Copyright(c) 2018 Intel Corporation. */ +#include <linux/log2.h> #include <linux/slab.h> +#include <linux/overflow.h> #include "xsk_queue.h" @@ -62,3 +64,56 @@ void xskq_destroy(struct xsk_queue *q) page_frag_free(q->ring); kfree(q); } + +struct xdp_umem_fq_reuse *xsk_reuseq_prepare(u32 nentries) +{ + struct xdp_umem_fq_reuse *newq; + + /* Check for overflow */ + if (nentries > (u32)roundup_pow_of_two(nentries)) + return NULL; + nentries = roundup_pow_of_two(nentries); + + newq = kvmalloc(struct_size(newq, handles, nentries), GFP_KERNEL); + if (!newq) + return NULL; + memset(newq, 0, offsetof(typeof(*newq), handles)); + + newq->nentries = nentries; + return newq; +} +EXPORT_SYMBOL_GPL(xsk_reuseq_prepare); + +struct xdp_umem_fq_reuse *xsk_reuseq_swap(struct xdp_umem *umem, + struct xdp_umem_fq_reuse *newq) +{ + struct xdp_umem_fq_reuse *oldq = umem->fq_reuse; + + if (!oldq) { + umem->fq_reuse = newq; + return NULL; + } + + if (newq->nentries < oldq->length) + return newq; + + memcpy(newq->handles, oldq->handles, + array_size(oldq->length, sizeof(u64))); + newq->length = oldq->length; + + umem->fq_reuse = newq; + return oldq; +} +EXPORT_SYMBOL_GPL(xsk_reuseq_swap); + +void xsk_reuseq_free(struct xdp_umem_fq_reuse *rq) +{ + kvfree(rq); +} +EXPORT_SYMBOL_GPL(xsk_reuseq_free); + +void xsk_reuseq_destroy(struct xdp_umem *umem) +{ + xsk_reuseq_free(umem->fq_reuse); + umem->fq_reuse = NULL; +} diff --git a/net/xdp/xsk_queue.h b/net/xdp/xsk_queue.h index 82252cccb4e0..bcb5cbb40419 100644 --- a/net/xdp/xsk_queue.h +++ b/net/xdp/xsk_queue.h @@ -258,4 +258,7 @@ void xskq_set_umem(struct xsk_queue *q, u64 size, u64 chunk_mask); struct xsk_queue *xskq_create(u32 nentries, bool umem_queue); void xskq_destroy(struct xsk_queue *q_ops); +/* Executed by the core when the entire UMEM gets freed */ +void xsk_reuseq_destroy(struct xdp_umem *umem); + #endif /* _LINUX_XSK_QUEUE_H */ diff --git a/net/xfrm/xfrm_device.c b/net/xfrm/xfrm_device.c index 5611b7521020..260fbba4f03e 100644 --- a/net/xfrm/xfrm_device.c +++ b/net/xfrm/xfrm_device.c @@ -99,7 +99,7 @@ struct sk_buff *validate_xmit_xfrm(struct sk_buff *skb, netdev_features_t featur do { struct sk_buff *nskb = skb2->next; - skb2->next = NULL; + skb_mark_not_on_list(skb2); xo = xfrm_offload(skb2); xo->flags |= XFRM_DEV_RESUME; diff --git a/net/xfrm/xfrm_output.c b/net/xfrm/xfrm_output.c index 45ba07ab3e4f..2d42cb0c94b8 100644 --- a/net/xfrm/xfrm_output.c +++ b/net/xfrm/xfrm_output.c @@ -189,7 +189,7 @@ static int xfrm_output_gso(struct net *net, struct sock *sk, struct sk_buff *skb struct sk_buff *nskb = segs->next; int err; - segs->next = NULL; + skb_mark_not_on_list(segs); err = xfrm_output2(net, sk, segs); if (unlikely(err)) { diff --git a/scripts/checkpatch.pl b/scripts/checkpatch.pl index 5219280bf7ff..161b0224d6ae 100755 --- a/scripts/checkpatch.pl +++ b/scripts/checkpatch.pl @@ -380,6 +380,7 @@ our $Attribute = qr{ __noclone| __deprecated| __read_mostly| + __ro_after_init| __kprobes| $InitAttribute| ____cacheline_aligned| @@ -3311,7 +3312,7 @@ sub process { # known declaration macros $sline =~ /^\+\s+$declaration_macros/ || # start of struct or union or enum - $sline =~ /^\+\s+(?:union|struct|enum|typedef)\b/ || + $sline =~ /^\+\s+(?:static\s+)?(?:const\s+)?(?:union|struct|enum|typedef)\b/ || # start or end of block or continuation of declaration $sline =~ /^\+\s+(?:$|[\{\}\.\#\"\?\:\(\[])/ || # bitfield continuation diff --git a/scripts/depmod.sh b/scripts/depmod.sh index 999d585eaa73..e083bcae343f 100755 --- a/scripts/depmod.sh +++ b/scripts/depmod.sh @@ -11,13 +11,14 @@ DEPMOD=$1 KERNELRELEASE=$2 if ! test -r System.map ; then + echo "Warning: modules_install: missing 'System.map' file. Skipping depmod." >&2 exit 0 fi if [ -z $(command -v $DEPMOD) ]; then - echo "'make modules_install' requires $DEPMOD. Please install it." >&2 + echo "Warning: 'make modules_install' requires $DEPMOD. Please install it." >&2 echo "This is probably in the kmod package." >&2 - exit 1 + exit 0 fi # older versions of depmod require the version string to start with three diff --git a/scripts/kconfig/Makefile b/scripts/kconfig/Makefile index 4a7bd2192073..67ed9f6ccdf8 100644 --- a/scripts/kconfig/Makefile +++ b/scripts/kconfig/Makefile @@ -221,7 +221,6 @@ $(obj)/zconf.tab.o: $(obj)/zconf.lex.c # check if necessary packages are available, and configure build flags define filechk_conf_cfg - $(CONFIG_SHELL) $(srctree)/scripts/kconfig/check-pkgconfig.sh; \ $(CONFIG_SHELL) $< endef diff --git a/scripts/kconfig/check-pkgconfig.sh b/scripts/kconfig/check-pkgconfig.sh deleted file mode 100644 index 7a1c40bfb58c..000000000000 --- a/scripts/kconfig/check-pkgconfig.sh +++ /dev/null @@ -1,8 +0,0 @@ -#!/bin/sh -# SPDX-License-Identifier: GPL-2.0 -# Check for pkg-config presence - -if [ -z $(command -v pkg-config) ]; then - echo "'make *config' requires 'pkg-config'. Please install it." 1>&2 - exit 1 -fi diff --git a/scripts/kconfig/gconf-cfg.sh b/scripts/kconfig/gconf-cfg.sh index 533b3d8f8f08..480ecd8b9f41 100755 --- a/scripts/kconfig/gconf-cfg.sh +++ b/scripts/kconfig/gconf-cfg.sh @@ -3,6 +3,13 @@ PKG="gtk+-2.0 gmodule-2.0 libglade-2.0" +if [ -z "$(command -v pkg-config)" ]; then + echo >&2 "*" + echo >&2 "* 'make gconfig' requires 'pkg-config'. Please install it." + echo >&2 "*" + exit 1 +fi + if ! pkg-config --exists $PKG; then echo >&2 "*" echo >&2 "* Unable to find the GTK+ installation. Please make sure that" diff --git a/scripts/kconfig/mconf-cfg.sh b/scripts/kconfig/mconf-cfg.sh index e6f9facd0077..c812872d7f9d 100755 --- a/scripts/kconfig/mconf-cfg.sh +++ b/scripts/kconfig/mconf-cfg.sh @@ -4,20 +4,23 @@ PKG="ncursesw" PKG2="ncurses" -if pkg-config --exists $PKG; then - echo cflags=\"$(pkg-config --cflags $PKG)\" - echo libs=\"$(pkg-config --libs $PKG)\" - exit 0 -fi +if [ -n "$(command -v pkg-config)" ]; then + if pkg-config --exists $PKG; then + echo cflags=\"$(pkg-config --cflags $PKG)\" + echo libs=\"$(pkg-config --libs $PKG)\" + exit 0 + fi -if pkg-config --exists $PKG2; then - echo cflags=\"$(pkg-config --cflags $PKG2)\" - echo libs=\"$(pkg-config --libs $PKG2)\" - exit 0 + if pkg-config --exists $PKG2; then + echo cflags=\"$(pkg-config --cflags $PKG2)\" + echo libs=\"$(pkg-config --libs $PKG2)\" + exit 0 + fi fi -# Unfortunately, some distributions (e.g. openSUSE) cannot find ncurses -# by pkg-config. +# Check the default paths in case pkg-config is not installed. +# (Even if it is installed, some distributions such as openSUSE cannot +# find ncurses by pkg-config.) if [ -f /usr/include/ncursesw/ncurses.h ]; then echo cflags=\"-D_GNU_SOURCE -I/usr/include/ncursesw\" echo libs=\"-lncursesw\" diff --git a/scripts/kconfig/mconf.c b/scripts/kconfig/mconf.c index 83b5836615fb..143c05fec161 100644 --- a/scripts/kconfig/mconf.c +++ b/scripts/kconfig/mconf.c @@ -490,7 +490,6 @@ static void build_conf(struct menu *menu) switch (prop->type) { case P_MENU: child_count++; - prompt = prompt; if (single_menu_mode) { item_make("%s%*c%s", menu->data ? "-->" : "++>", diff --git a/scripts/kconfig/nconf-cfg.sh b/scripts/kconfig/nconf-cfg.sh index 42f5ac73548e..001559ef0a60 100644 --- a/scripts/kconfig/nconf-cfg.sh +++ b/scripts/kconfig/nconf-cfg.sh @@ -4,20 +4,23 @@ PKG="ncursesw menuw panelw" PKG2="ncurses menu panel" -if pkg-config --exists $PKG; then - echo cflags=\"$(pkg-config --cflags $PKG)\" - echo libs=\"$(pkg-config --libs $PKG)\" - exit 0 -fi +if [ -n "$(command -v pkg-config)" ]; then + if pkg-config --exists $PKG; then + echo cflags=\"$(pkg-config --cflags $PKG)\" + echo libs=\"$(pkg-config --libs $PKG)\" + exit 0 + fi -if pkg-config --exists $PKG2; then - echo cflags=\"$(pkg-config --cflags $PKG2)\" - echo libs=\"$(pkg-config --libs $PKG2)\" - exit 0 + if pkg-config --exists $PKG2; then + echo cflags=\"$(pkg-config --cflags $PKG2)\" + echo libs=\"$(pkg-config --libs $PKG2)\" + exit 0 + fi fi -# Unfortunately, some distributions (e.g. openSUSE) cannot find ncurses -# by pkg-config. +# Check the default paths in case pkg-config is not installed. +# (Even if it is installed, some distributions such as openSUSE cannot +# find ncurses by pkg-config.) if [ -f /usr/include/ncursesw/ncurses.h ]; then echo cflags=\"-D_GNU_SOURCE -I/usr/include/ncursesw\" echo libs=\"-lncursesw -lmenuw -lpanelw\" diff --git a/scripts/kconfig/qconf-cfg.sh b/scripts/kconfig/qconf-cfg.sh index 0862e1562536..02ccc0ae1031 100755 --- a/scripts/kconfig/qconf-cfg.sh +++ b/scripts/kconfig/qconf-cfg.sh @@ -4,6 +4,13 @@ PKG="Qt5Core Qt5Gui Qt5Widgets" PKG2="QtCore QtGui" +if [ -z "$(command -v pkg-config)" ]; then + echo >&2 "*" + echo >&2 "* 'make xconfig' requires 'pkg-config'. Please install it." + echo >&2 "*" + exit 1 +fi + if pkg-config --exists $PKG; then echo cflags=\"-std=c++11 -fPIC $(pkg-config --cflags Qt5Core Qt5Gui Qt5Widgets)\" echo libs=\"$(pkg-config --libs $PKG)\" diff --git a/scripts/recordmcount.pl b/scripts/recordmcount.pl index fe06e77c15eb..f599031260d5 100755 --- a/scripts/recordmcount.pl +++ b/scripts/recordmcount.pl @@ -389,6 +389,9 @@ if ($arch eq "x86_64") { $mcount_regex = "^\\s*([0-9a-fA-F]+):\\sR_RISCV_CALL\\s_mcount\$"; $type = ".quad"; $alignment = 2; +} elsif ($arch eq "nds32") { + $mcount_regex = "^\\s*([0-9a-fA-F]+):\\s*R_NDS32_HI20_RELA\\s+_mcount\$"; + $alignment = 2; } else { die "Arch $arch is not supported with CONFIG_FTRACE_MCOUNT_RECORD"; } diff --git a/scripts/setlocalversion b/scripts/setlocalversion index 71f39410691b..79f7dd57d571 100755 --- a/scripts/setlocalversion +++ b/scripts/setlocalversion @@ -74,7 +74,7 @@ scm_version() fi # Check for uncommitted changes - if git diff-index --name-only HEAD | grep -qv "^scripts/package"; then + if git status -uno --porcelain | grep -qv '^.. scripts/package'; then printf '%s' -dirty fi diff --git a/scripts/subarch.include b/scripts/subarch.include new file mode 100644 index 000000000000..650682821126 --- /dev/null +++ b/scripts/subarch.include @@ -0,0 +1,13 @@ +# SUBARCH tells the usermode build what the underlying arch is. That is set +# first, and if a usermode build is happening, the "ARCH=um" on the command +# line overrides the setting of ARCH below. If a native build is happening, +# then ARCH is assigned, getting whatever value it gets normally, and +# SUBARCH is subsequently ignored. + +SUBARCH := $(shell uname -m | sed -e s/i.86/x86/ -e s/x86_64/x86/ \ + -e s/sun4u/sparc64/ \ + -e s/arm.*/arm/ -e s/sa110/arm/ \ + -e s/s390x/s390/ -e s/parisc64/parisc/ \ + -e s/ppc.*/powerpc/ -e s/mips.*/mips/ \ + -e s/sh[234].*/sh/ -e s/aarch64.*/arm64/ \ + -e s/riscv.*/riscv/) diff --git a/security/Kconfig b/security/Kconfig index 27d8b2688f75..d9aa521b5206 100644 --- a/security/Kconfig +++ b/security/Kconfig @@ -57,7 +57,7 @@ config SECURITY_NETWORK config PAGE_TABLE_ISOLATION bool "Remove the kernel mapping in user mode" default y - depends on X86 && !UML + depends on (X86_64 || X86_PAE) && !UML help This feature reduces the number of hardware side channels by ensuring that the majority of kernel addresses are not mapped diff --git a/security/apparmor/secid.c b/security/apparmor/secid.c index f2f22d00db18..4ccec1bcf6f5 100644 --- a/security/apparmor/secid.c +++ b/security/apparmor/secid.c @@ -79,7 +79,6 @@ int apparmor_secid_to_secctx(u32 secid, char **secdata, u32 *seclen) struct aa_label *label = aa_secid_to_label(secid); int len; - AA_BUG(!secdata); AA_BUG(!seclen); if (!label) diff --git a/sound/core/rawmidi.c b/sound/core/rawmidi.c index 69517e18ef07..08d5662039e3 100644 --- a/sound/core/rawmidi.c +++ b/sound/core/rawmidi.c @@ -129,7 +129,7 @@ static int snd_rawmidi_runtime_create(struct snd_rawmidi_substream *substream) runtime->avail = 0; else runtime->avail = runtime->buffer_size; - runtime->buffer = kvmalloc(runtime->buffer_size, GFP_KERNEL); + runtime->buffer = kvzalloc(runtime->buffer_size, GFP_KERNEL); if (!runtime->buffer) { kfree(runtime); return -ENOMEM; @@ -655,7 +655,7 @@ static int resize_runtime_buffer(struct snd_rawmidi_runtime *runtime, if (params->avail_min < 1 || params->avail_min > params->buffer_size) return -EINVAL; if (params->buffer_size != runtime->buffer_size) { - newbuf = kvmalloc(params->buffer_size, GFP_KERNEL); + newbuf = kvzalloc(params->buffer_size, GFP_KERNEL); if (!newbuf) return -ENOMEM; spin_lock_irq(&runtime->lock); diff --git a/sound/firewire/bebob/bebob.c b/sound/firewire/bebob/bebob.c index 730ea91d9be8..93676354f87f 100644 --- a/sound/firewire/bebob/bebob.c +++ b/sound/firewire/bebob/bebob.c @@ -263,6 +263,8 @@ do_registration(struct work_struct *work) error: mutex_unlock(&devices_mutex); snd_bebob_stream_destroy_duplex(bebob); + kfree(bebob->maudio_special_quirk); + bebob->maudio_special_quirk = NULL; snd_card_free(bebob->card); dev_info(&bebob->unit->device, "Sound card registration failed: %d\n", err); diff --git a/sound/firewire/bebob/bebob_maudio.c b/sound/firewire/bebob/bebob_maudio.c index bd55620c6a47..c266997ad299 100644 --- a/sound/firewire/bebob/bebob_maudio.c +++ b/sound/firewire/bebob/bebob_maudio.c @@ -96,17 +96,13 @@ int snd_bebob_maudio_load_firmware(struct fw_unit *unit) struct fw_device *device = fw_parent_device(unit); int err, rcode; u64 date; - __le32 cues[3] = { - cpu_to_le32(MAUDIO_BOOTLOADER_CUE1), - cpu_to_le32(MAUDIO_BOOTLOADER_CUE2), - cpu_to_le32(MAUDIO_BOOTLOADER_CUE3) - }; + __le32 *cues; /* check date of software used to build */ err = snd_bebob_read_block(unit, INFO_OFFSET_SW_DATE, &date, sizeof(u64)); if (err < 0) - goto end; + return err; /* * firmware version 5058 or later has date later than "20070401", but * 'date' is not null-terminated. @@ -114,20 +110,28 @@ int snd_bebob_maudio_load_firmware(struct fw_unit *unit) if (date < 0x3230303730343031LL) { dev_err(&unit->device, "Use firmware version 5058 or later\n"); - err = -ENOSYS; - goto end; + return -ENXIO; } + cues = kmalloc_array(3, sizeof(*cues), GFP_KERNEL); + if (!cues) + return -ENOMEM; + + cues[0] = cpu_to_le32(MAUDIO_BOOTLOADER_CUE1); + cues[1] = cpu_to_le32(MAUDIO_BOOTLOADER_CUE2); + cues[2] = cpu_to_le32(MAUDIO_BOOTLOADER_CUE3); + rcode = fw_run_transaction(device->card, TCODE_WRITE_BLOCK_REQUEST, device->node_id, device->generation, device->max_speed, BEBOB_ADDR_REG_REQ, - cues, sizeof(cues)); + cues, 3 * sizeof(*cues)); + kfree(cues); if (rcode != RCODE_COMPLETE) { dev_err(&unit->device, "Failed to send a cue to load firmware\n"); err = -EIO; } -end: + return err; } @@ -290,10 +294,6 @@ snd_bebob_maudio_special_discover(struct snd_bebob *bebob, bool is1814) bebob->midi_output_ports = 2; } end: - if (err < 0) { - kfree(params); - bebob->maudio_special_quirk = NULL; - } mutex_unlock(&bebob->mutex); return err; } diff --git a/sound/firewire/digi00x/digi00x.c b/sound/firewire/digi00x/digi00x.c index 1f5e1d23f31a..ef689997d6a5 100644 --- a/sound/firewire/digi00x/digi00x.c +++ b/sound/firewire/digi00x/digi00x.c @@ -49,6 +49,7 @@ static void dg00x_free(struct snd_dg00x *dg00x) fw_unit_put(dg00x->unit); mutex_destroy(&dg00x->mutex); + kfree(dg00x); } static void dg00x_card_free(struct snd_card *card) diff --git a/sound/firewire/fireface/ff-protocol-ff400.c b/sound/firewire/fireface/ff-protocol-ff400.c index ad7a0a32557d..64c3cb0fb926 100644 --- a/sound/firewire/fireface/ff-protocol-ff400.c +++ b/sound/firewire/fireface/ff-protocol-ff400.c @@ -146,6 +146,7 @@ static int ff400_switch_fetching_mode(struct snd_ff *ff, bool enable) { __le32 *reg; int i; + int err; reg = kcalloc(18, sizeof(__le32), GFP_KERNEL); if (reg == NULL) @@ -163,9 +164,11 @@ static int ff400_switch_fetching_mode(struct snd_ff *ff, bool enable) reg[i] = cpu_to_le32(0x00000001); } - return snd_fw_transaction(ff->unit, TCODE_WRITE_BLOCK_REQUEST, - FF400_FETCH_PCM_FRAMES, reg, - sizeof(__le32) * 18, 0); + err = snd_fw_transaction(ff->unit, TCODE_WRITE_BLOCK_REQUEST, + FF400_FETCH_PCM_FRAMES, reg, + sizeof(__le32) * 18, 0); + kfree(reg); + return err; } static void ff400_dump_sync_status(struct snd_ff *ff, diff --git a/sound/firewire/fireworks/fireworks.c b/sound/firewire/fireworks/fireworks.c index 71a0613d3da0..f2d073365cf6 100644 --- a/sound/firewire/fireworks/fireworks.c +++ b/sound/firewire/fireworks/fireworks.c @@ -301,6 +301,8 @@ error: snd_efw_transaction_remove_instance(efw); snd_efw_stream_destroy_duplex(efw); snd_card_free(efw->card); + kfree(efw->resp_buf); + efw->resp_buf = NULL; dev_info(&efw->unit->device, "Sound card registration failed: %d\n", err); } diff --git a/sound/firewire/oxfw/oxfw.c b/sound/firewire/oxfw/oxfw.c index 1e5b2c802635..2ea8be6c8584 100644 --- a/sound/firewire/oxfw/oxfw.c +++ b/sound/firewire/oxfw/oxfw.c @@ -130,6 +130,7 @@ static void oxfw_free(struct snd_oxfw *oxfw) kfree(oxfw->spec); mutex_destroy(&oxfw->mutex); + kfree(oxfw); } /* @@ -207,6 +208,7 @@ static int detect_quirks(struct snd_oxfw *oxfw) static void do_registration(struct work_struct *work) { struct snd_oxfw *oxfw = container_of(work, struct snd_oxfw, dwork.work); + int i; int err; if (oxfw->registered) @@ -269,7 +271,15 @@ error: snd_oxfw_stream_destroy_simplex(oxfw, &oxfw->rx_stream); if (oxfw->has_output) snd_oxfw_stream_destroy_simplex(oxfw, &oxfw->tx_stream); + for (i = 0; i < SND_OXFW_STREAM_FORMAT_ENTRIES; ++i) { + kfree(oxfw->tx_stream_formats[i]); + oxfw->tx_stream_formats[i] = NULL; + kfree(oxfw->rx_stream_formats[i]); + oxfw->rx_stream_formats[i] = NULL; + } snd_card_free(oxfw->card); + kfree(oxfw->spec); + oxfw->spec = NULL; dev_info(&oxfw->unit->device, "Sound card registration failed: %d\n", err); } diff --git a/sound/firewire/tascam/tascam.c b/sound/firewire/tascam/tascam.c index 44ad41fb7374..d3fdc463a884 100644 --- a/sound/firewire/tascam/tascam.c +++ b/sound/firewire/tascam/tascam.c @@ -93,6 +93,7 @@ static void tscm_free(struct snd_tscm *tscm) fw_unit_put(tscm->unit); mutex_destroy(&tscm->mutex); + kfree(tscm); } static void tscm_card_free(struct snd_card *card) diff --git a/sound/hda/ext/hdac_ext_stream.c b/sound/hda/ext/hdac_ext_stream.c index 1bd27576db98..a835558ddbc9 100644 --- a/sound/hda/ext/hdac_ext_stream.c +++ b/sound/hda/ext/hdac_ext_stream.c @@ -146,7 +146,8 @@ EXPORT_SYMBOL_GPL(snd_hdac_ext_stream_decouple); */ void snd_hdac_ext_link_stream_start(struct hdac_ext_stream *stream) { - snd_hdac_updatel(stream->pplc_addr, AZX_REG_PPLCCTL, 0, AZX_PPLCCTL_RUN); + snd_hdac_updatel(stream->pplc_addr, AZX_REG_PPLCCTL, + AZX_PPLCCTL_RUN, AZX_PPLCCTL_RUN); } EXPORT_SYMBOL_GPL(snd_hdac_ext_link_stream_start); @@ -171,7 +172,8 @@ void snd_hdac_ext_link_stream_reset(struct hdac_ext_stream *stream) snd_hdac_ext_link_stream_clear(stream); - snd_hdac_updatel(stream->pplc_addr, AZX_REG_PPLCCTL, 0, AZX_PPLCCTL_STRST); + snd_hdac_updatel(stream->pplc_addr, AZX_REG_PPLCCTL, + AZX_PPLCCTL_STRST, AZX_PPLCCTL_STRST); udelay(3); timeout = 50; do { @@ -242,7 +244,7 @@ EXPORT_SYMBOL_GPL(snd_hdac_ext_link_set_stream_id); void snd_hdac_ext_link_clear_stream_id(struct hdac_ext_link *link, int stream) { - snd_hdac_updatew(link->ml_addr, AZX_REG_ML_LOSIDV, 0, (1 << stream)); + snd_hdac_updatew(link->ml_addr, AZX_REG_ML_LOSIDV, (1 << stream), 0); } EXPORT_SYMBOL_GPL(snd_hdac_ext_link_clear_stream_id); @@ -415,7 +417,6 @@ void snd_hdac_ext_stream_spbcap_enable(struct hdac_bus *bus, bool enable, int index) { u32 mask = 0; - u32 register_mask = 0; if (!bus->spbcap) { dev_err(bus->dev, "Address of SPB capability is NULL\n"); @@ -424,12 +425,8 @@ void snd_hdac_ext_stream_spbcap_enable(struct hdac_bus *bus, mask |= (1 << index); - register_mask = readl(bus->spbcap + AZX_REG_SPB_SPBFCCTL); - - mask |= register_mask; - if (enable) - snd_hdac_updatel(bus->spbcap, AZX_REG_SPB_SPBFCCTL, 0, mask); + snd_hdac_updatel(bus->spbcap, AZX_REG_SPB_SPBFCCTL, mask, mask); else snd_hdac_updatel(bus->spbcap, AZX_REG_SPB_SPBFCCTL, mask, 0); } @@ -503,7 +500,6 @@ void snd_hdac_ext_stream_drsm_enable(struct hdac_bus *bus, bool enable, int index) { u32 mask = 0; - u32 register_mask = 0; if (!bus->drsmcap) { dev_err(bus->dev, "Address of DRSM capability is NULL\n"); @@ -512,12 +508,8 @@ void snd_hdac_ext_stream_drsm_enable(struct hdac_bus *bus, mask |= (1 << index); - register_mask = readl(bus->drsmcap + AZX_REG_SPB_SPBFCCTL); - - mask |= register_mask; - if (enable) - snd_hdac_updatel(bus->drsmcap, AZX_REG_DRSM_CTL, 0, mask); + snd_hdac_updatel(bus->drsmcap, AZX_REG_DRSM_CTL, mask, mask); else snd_hdac_updatel(bus->drsmcap, AZX_REG_DRSM_CTL, mask, 0); } diff --git a/sound/hda/hdac_controller.c b/sound/hda/hdac_controller.c index 560ec0986e1a..74244d8e2909 100644 --- a/sound/hda/hdac_controller.c +++ b/sound/hda/hdac_controller.c @@ -40,6 +40,8 @@ static void azx_clear_corbrp(struct hdac_bus *bus) */ void snd_hdac_bus_init_cmd_io(struct hdac_bus *bus) { + WARN_ON_ONCE(!bus->rb.area); + spin_lock_irq(&bus->reg_lock); /* CORB set up */ bus->corb.addr = bus->rb.addr; @@ -383,7 +385,7 @@ void snd_hdac_bus_exit_link_reset(struct hdac_bus *bus) EXPORT_SYMBOL_GPL(snd_hdac_bus_exit_link_reset); /* reset codec link */ -static int azx_reset(struct hdac_bus *bus, bool full_reset) +int snd_hdac_bus_reset_link(struct hdac_bus *bus, bool full_reset) { if (!full_reset) goto skip_reset; @@ -408,7 +410,7 @@ static int azx_reset(struct hdac_bus *bus, bool full_reset) skip_reset: /* check to see if controller is ready */ if (!snd_hdac_chip_readb(bus, GCTL)) { - dev_dbg(bus->dev, "azx_reset: controller not ready!\n"); + dev_dbg(bus->dev, "controller not ready!\n"); return -EBUSY; } @@ -423,6 +425,7 @@ static int azx_reset(struct hdac_bus *bus, bool full_reset) return 0; } +EXPORT_SYMBOL_GPL(snd_hdac_bus_reset_link); /* enable interrupts */ static void azx_int_enable(struct hdac_bus *bus) @@ -477,15 +480,17 @@ bool snd_hdac_bus_init_chip(struct hdac_bus *bus, bool full_reset) return false; /* reset controller */ - azx_reset(bus, full_reset); + snd_hdac_bus_reset_link(bus, full_reset); - /* initialize interrupts */ + /* clear interrupts */ azx_int_clear(bus); - azx_int_enable(bus); /* initialize the codec command I/O */ snd_hdac_bus_init_cmd_io(bus); + /* enable interrupts after CORB/RIRB buffers are initialized above */ + azx_int_enable(bus); + /* program the position buffer */ if (bus->use_posbuf && bus->posbuf.addr) { snd_hdac_chip_writel(bus, DPLBASE, (u32)bus->posbuf.addr); diff --git a/sound/pci/emu10k1/emufx.c b/sound/pci/emu10k1/emufx.c index 90713741c2dc..6ebe817801ea 100644 --- a/sound/pci/emu10k1/emufx.c +++ b/sound/pci/emu10k1/emufx.c @@ -2540,7 +2540,7 @@ static int snd_emu10k1_fx8010_ioctl(struct snd_hwdep * hw, struct file *file, un emu->support_tlv = 1; return put_user(SNDRV_EMU10K1_VERSION, (int __user *)argp); case SNDRV_EMU10K1_IOCTL_INFO: - info = kmalloc(sizeof(*info), GFP_KERNEL); + info = kzalloc(sizeof(*info), GFP_KERNEL); if (!info) return -ENOMEM; snd_emu10k1_fx8010_info(emu, info); diff --git a/sound/pci/hda/hda_codec.c b/sound/pci/hda/hda_codec.c index 0a5085537034..26d348b47867 100644 --- a/sound/pci/hda/hda_codec.c +++ b/sound/pci/hda/hda_codec.c @@ -3935,7 +3935,8 @@ void snd_hda_bus_reset_codecs(struct hda_bus *bus) list_for_each_codec(codec, bus) { /* FIXME: maybe a better way needed for forced reset */ - cancel_delayed_work_sync(&codec->jackpoll_work); + if (current_work() != &codec->jackpoll_work.work) + cancel_delayed_work_sync(&codec->jackpoll_work); #ifdef CONFIG_PM if (hda_codec_is_power_on(codec)) { hda_call_codec_suspend(codec); diff --git a/sound/pci/hda/hda_intel.c b/sound/pci/hda/hda_intel.c index 1b2ce304152a..aa4c672dbaf7 100644 --- a/sound/pci/hda/hda_intel.c +++ b/sound/pci/hda/hda_intel.c @@ -365,8 +365,10 @@ enum { */ #ifdef SUPPORT_VGA_SWITCHEROO #define use_vga_switcheroo(chip) ((chip)->use_vga_switcheroo) +#define needs_eld_notify_link(chip) ((chip)->need_eld_notify_link) #else #define use_vga_switcheroo(chip) 0 +#define needs_eld_notify_link(chip) false #endif #define CONTROLLER_IN_GPU(pci) (((pci)->device == 0x0a0c) || \ @@ -453,6 +455,7 @@ static inline void mark_runtime_wc(struct azx *chip, struct azx_dev *azx_dev, #endif static int azx_acquire_irq(struct azx *chip, int do_disconnect); +static void set_default_power_save(struct azx *chip); /* * initialize the PCI registers @@ -1201,6 +1204,10 @@ static int azx_runtime_idle(struct device *dev) azx_bus(chip)->codec_powered || !chip->running) return -EBUSY; + /* ELD notification gets broken when HD-audio bus is off */ + if (needs_eld_notify_link(hda)) + return -EBUSY; + return 0; } @@ -1298,6 +1305,36 @@ static bool azx_vs_can_switch(struct pci_dev *pci) return true; } +/* + * The discrete GPU cannot power down unless the HDA controller runtime + * suspends, so activate runtime PM on codecs even if power_save == 0. + */ +static void setup_vga_switcheroo_runtime_pm(struct azx *chip) +{ + struct hda_intel *hda = container_of(chip, struct hda_intel, chip); + struct hda_codec *codec; + + if (hda->use_vga_switcheroo && !hda->need_eld_notify_link) { + list_for_each_codec(codec, &chip->bus) + codec->auto_runtime_pm = 1; + /* reset the power save setup */ + if (chip->running) + set_default_power_save(chip); + } +} + +static void azx_vs_gpu_bound(struct pci_dev *pci, + enum vga_switcheroo_client_id client_id) +{ + struct snd_card *card = pci_get_drvdata(pci); + struct azx *chip = card->private_data; + struct hda_intel *hda = container_of(chip, struct hda_intel, chip); + + if (client_id == VGA_SWITCHEROO_DIS) + hda->need_eld_notify_link = 0; + setup_vga_switcheroo_runtime_pm(chip); +} + static void init_vga_switcheroo(struct azx *chip) { struct hda_intel *hda = container_of(chip, struct hda_intel, chip); @@ -1306,6 +1343,7 @@ static void init_vga_switcheroo(struct azx *chip) dev_info(chip->card->dev, "Handle vga_switcheroo audio client\n"); hda->use_vga_switcheroo = 1; + hda->need_eld_notify_link = 1; /* cleared in gpu_bound op */ chip->driver_caps |= AZX_DCAPS_PM_RUNTIME; pci_dev_put(p); } @@ -1314,6 +1352,7 @@ static void init_vga_switcheroo(struct azx *chip) static const struct vga_switcheroo_client_ops azx_vs_ops = { .set_gpu_state = azx_vs_set_state, .can_switch = azx_vs_can_switch, + .gpu_bound = azx_vs_gpu_bound, }; static int register_vga_switcheroo(struct azx *chip) @@ -1339,6 +1378,7 @@ static int register_vga_switcheroo(struct azx *chip) #define init_vga_switcheroo(chip) /* NOP */ #define register_vga_switcheroo(chip) 0 #define check_hdmi_disabled(pci) false +#define setup_vga_switcheroo_runtime_pm(chip) /* NOP */ #endif /* SUPPORT_VGA_SWITCHER */ /* @@ -1352,6 +1392,7 @@ static int azx_free(struct azx *chip) if (azx_has_pm_runtime(chip) && chip->running) pm_runtime_get_noresume(&pci->dev); + chip->running = 0; azx_del_card_list(chip); @@ -2230,6 +2271,25 @@ static struct snd_pci_quirk power_save_blacklist[] = { }; #endif /* CONFIG_PM */ +static void set_default_power_save(struct azx *chip) +{ + int val = power_save; + +#ifdef CONFIG_PM + if (pm_blacklist) { + const struct snd_pci_quirk *q; + + q = snd_pci_quirk_lookup(chip->pci, power_save_blacklist); + if (q && val) { + dev_info(chip->card->dev, "device %04x:%04x is on the power_save blacklist, forcing power_save to 0\n", + q->subvendor, q->subdevice); + val = 0; + } + } +#endif /* CONFIG_PM */ + snd_hda_set_power_save(&chip->bus, val * 1000); +} + /* number of codec slots for each chipset: 0 = default slots (i.e. 4) */ static unsigned int azx_max_codecs[AZX_NUM_DRIVERS] = { [AZX_DRIVER_NVIDIA] = 8, @@ -2241,9 +2301,7 @@ static int azx_probe_continue(struct azx *chip) struct hda_intel *hda = container_of(chip, struct hda_intel, chip); struct hdac_bus *bus = azx_bus(chip); struct pci_dev *pci = chip->pci; - struct hda_codec *codec; int dev = chip->dev_index; - int val; int err; hda->probe_continued = 1; @@ -2322,31 +2380,13 @@ static int azx_probe_continue(struct azx *chip) if (err < 0) goto out_free; + setup_vga_switcheroo_runtime_pm(chip); + chip->running = 1; azx_add_card_list(chip); - val = power_save; -#ifdef CONFIG_PM - if (pm_blacklist) { - const struct snd_pci_quirk *q; - - q = snd_pci_quirk_lookup(chip->pci, power_save_blacklist); - if (q && val) { - dev_info(chip->card->dev, "device %04x:%04x is on the power_save blacklist, forcing power_save to 0\n", - q->subvendor, q->subdevice); - val = 0; - } - } -#endif /* CONFIG_PM */ - /* - * The discrete GPU cannot power down unless the HDA controller runtime - * suspends, so activate runtime PM on codecs even if power_save == 0. - */ - if (use_vga_switcheroo(hda)) - list_for_each_codec(codec, &chip->bus) - codec->auto_runtime_pm = 1; + set_default_power_save(chip); - snd_hda_set_power_save(&chip->bus, val * 1000); if (azx_has_pm_runtime(chip)) pm_runtime_put_autosuspend(&pci->dev); diff --git a/sound/pci/hda/hda_intel.h b/sound/pci/hda/hda_intel.h index e3a3d318d2e5..f59719e06b91 100644 --- a/sound/pci/hda/hda_intel.h +++ b/sound/pci/hda/hda_intel.h @@ -37,6 +37,7 @@ struct hda_intel { /* vga_switcheroo setup */ unsigned int use_vga_switcheroo:1; + unsigned int need_eld_notify_link:1; unsigned int vga_switcheroo_registered:1; unsigned int init_failed:1; /* delayed init failed */ diff --git a/sound/soc/amd/acp-pcm-dma.c b/sound/soc/amd/acp-pcm-dma.c index e359938e3d7e..77b265bd0505 100644 --- a/sound/soc/amd/acp-pcm-dma.c +++ b/sound/soc/amd/acp-pcm-dma.c @@ -16,6 +16,7 @@ #include <linux/module.h> #include <linux/delay.h> #include <linux/io.h> +#include <linux/iopoll.h> #include <linux/sizes.h> #include <linux/pm_runtime.h> @@ -184,6 +185,24 @@ static void config_dma_descriptor_in_sram(void __iomem *acp_mmio, acp_reg_write(descr_info->xfer_val, acp_mmio, mmACP_SRBM_Targ_Idx_Data); } +static void pre_config_reset(void __iomem *acp_mmio, u16 ch_num) +{ + u32 dma_ctrl; + int ret; + + /* clear the reset bit */ + dma_ctrl = acp_reg_read(acp_mmio, mmACP_DMA_CNTL_0 + ch_num); + dma_ctrl &= ~ACP_DMA_CNTL_0__DMAChRst_MASK; + acp_reg_write(dma_ctrl, acp_mmio, mmACP_DMA_CNTL_0 + ch_num); + /* check the reset bit before programming configuration registers */ + ret = readl_poll_timeout(acp_mmio + ((mmACP_DMA_CNTL_0 + ch_num) * 4), + dma_ctrl, + !(dma_ctrl & ACP_DMA_CNTL_0__DMAChRst_MASK), + 100, ACP_DMA_RESET_TIME); + if (ret < 0) + pr_err("Failed to clear reset of channel : %d\n", ch_num); +} + /* * Initialize the DMA descriptor information for transfer between * system memory <-> ACP SRAM @@ -236,6 +255,7 @@ static void set_acp_sysmem_dma_descriptors(void __iomem *acp_mmio, config_dma_descriptor_in_sram(acp_mmio, dma_dscr_idx, &dmadscr[i]); } + pre_config_reset(acp_mmio, ch); config_acp_dma_channel(acp_mmio, ch, dma_dscr_idx - 1, NUM_DSCRS_PER_CHANNEL, @@ -275,6 +295,7 @@ static void set_acp_to_i2s_dma_descriptors(void __iomem *acp_mmio, u32 size, config_dma_descriptor_in_sram(acp_mmio, dma_dscr_idx, &dmadscr[i]); } + pre_config_reset(acp_mmio, ch); /* Configure the DMA channel with the above descriptore */ config_acp_dma_channel(acp_mmio, ch, dma_dscr_idx - 1, NUM_DSCRS_PER_CHANNEL, diff --git a/sound/soc/codecs/cs4265.c b/sound/soc/codecs/cs4265.c index 275677de669f..407554175282 100644 --- a/sound/soc/codecs/cs4265.c +++ b/sound/soc/codecs/cs4265.c @@ -157,8 +157,8 @@ static const struct snd_kcontrol_new cs4265_snd_controls[] = { SOC_SINGLE("Validity Bit Control Switch", CS4265_SPDIF_CTL2, 3, 1, 0), SOC_ENUM("SPDIF Mono/Stereo", spdif_mono_stereo_enum), - SOC_SINGLE("MMTLR Data Switch", 0, - 1, 1, 0), + SOC_SINGLE("MMTLR Data Switch", CS4265_SPDIF_CTL2, + 0, 1, 0), SOC_ENUM("Mono Channel Select", spdif_mono_select_enum), SND_SOC_BYTES("C Data Buffer", CS4265_C_DATA_BUFF, 24), }; diff --git a/sound/soc/codecs/max98373.c b/sound/soc/codecs/max98373.c index 92b7125ea169..1093f766d0d2 100644 --- a/sound/soc/codecs/max98373.c +++ b/sound/soc/codecs/max98373.c @@ -520,6 +520,7 @@ static bool max98373_volatile_reg(struct device *dev, unsigned int reg) { switch (reg) { case MAX98373_R2000_SW_RESET ... MAX98373_R2009_INT_FLAG3: + case MAX98373_R203E_AMP_PATH_GAIN: case MAX98373_R2054_MEAS_ADC_PVDD_CH_READBACK: case MAX98373_R2055_MEAS_ADC_THERM_CH_READBACK: case MAX98373_R20B6_BDE_CUR_STATE_READBACK: @@ -729,6 +730,7 @@ static int max98373_probe(struct snd_soc_component *component) /* Software Reset */ regmap_write(max98373->regmap, MAX98373_R2000_SW_RESET, MAX98373_SOFT_RESET); + usleep_range(10000, 11000); /* IV default slot configuration */ regmap_write(max98373->regmap, @@ -817,6 +819,7 @@ static int max98373_resume(struct device *dev) regmap_write(max98373->regmap, MAX98373_R2000_SW_RESET, MAX98373_SOFT_RESET); + usleep_range(10000, 11000); regcache_cache_only(max98373->regmap, false); regcache_sync(max98373->regmap); return 0; diff --git a/sound/soc/codecs/rt5514.c b/sound/soc/codecs/rt5514.c index dca82dd6e3bf..32fe76c3134a 100644 --- a/sound/soc/codecs/rt5514.c +++ b/sound/soc/codecs/rt5514.c @@ -64,8 +64,8 @@ static const struct reg_sequence rt5514_patch[] = { {RT5514_ANA_CTRL_LDO10, 0x00028604}, {RT5514_ANA_CTRL_ADCFED, 0x00000800}, {RT5514_ASRC_IN_CTRL1, 0x00000003}, - {RT5514_DOWNFILTER0_CTRL3, 0x10000352}, - {RT5514_DOWNFILTER1_CTRL3, 0x10000352}, + {RT5514_DOWNFILTER0_CTRL3, 0x10000342}, + {RT5514_DOWNFILTER1_CTRL3, 0x10000342}, }; static const struct reg_default rt5514_reg[] = { @@ -92,10 +92,10 @@ static const struct reg_default rt5514_reg[] = { {RT5514_ASRC_IN_CTRL1, 0x00000003}, {RT5514_DOWNFILTER0_CTRL1, 0x00020c2f}, {RT5514_DOWNFILTER0_CTRL2, 0x00020c2f}, - {RT5514_DOWNFILTER0_CTRL3, 0x10000352}, + {RT5514_DOWNFILTER0_CTRL3, 0x10000342}, {RT5514_DOWNFILTER1_CTRL1, 0x00020c2f}, {RT5514_DOWNFILTER1_CTRL2, 0x00020c2f}, - {RT5514_DOWNFILTER1_CTRL3, 0x10000352}, + {RT5514_DOWNFILTER1_CTRL3, 0x10000342}, {RT5514_ANA_CTRL_LDO10, 0x00028604}, {RT5514_ANA_CTRL_LDO18_16, 0x02000345}, {RT5514_ANA_CTRL_ADC12, 0x0000a2a8}, diff --git a/sound/soc/codecs/rt5682.c b/sound/soc/codecs/rt5682.c index 640d400ca013..afe7d5b19313 100644 --- a/sound/soc/codecs/rt5682.c +++ b/sound/soc/codecs/rt5682.c @@ -750,8 +750,8 @@ static bool rt5682_readable_register(struct device *dev, unsigned int reg) } static const DECLARE_TLV_DB_SCALE(hp_vol_tlv, -2250, 150, 0); -static const DECLARE_TLV_DB_SCALE(dac_vol_tlv, -65625, 375, 0); -static const DECLARE_TLV_DB_SCALE(adc_vol_tlv, -17625, 375, 0); +static const DECLARE_TLV_DB_SCALE(dac_vol_tlv, -6525, 75, 0); +static const DECLARE_TLV_DB_SCALE(adc_vol_tlv, -1725, 75, 0); static const DECLARE_TLV_DB_SCALE(adc_bst_tlv, 0, 1200, 0); /* {0, +20, +24, +30, +35, +40, +44, +50, +52} dB */ @@ -1114,7 +1114,7 @@ static const struct snd_kcontrol_new rt5682_snd_controls[] = { /* DAC Digital Volume */ SOC_DOUBLE_TLV("DAC1 Playback Volume", RT5682_DAC1_DIG_VOL, - RT5682_L_VOL_SFT, RT5682_R_VOL_SFT, 175, 0, dac_vol_tlv), + RT5682_L_VOL_SFT + 1, RT5682_R_VOL_SFT + 1, 86, 0, dac_vol_tlv), /* IN Boost Volume */ SOC_SINGLE_TLV("CBJ Boost Volume", RT5682_CBJ_BST_CTRL, @@ -1124,7 +1124,7 @@ static const struct snd_kcontrol_new rt5682_snd_controls[] = { SOC_DOUBLE("STO1 ADC Capture Switch", RT5682_STO1_ADC_DIG_VOL, RT5682_L_MUTE_SFT, RT5682_R_MUTE_SFT, 1, 1), SOC_DOUBLE_TLV("STO1 ADC Capture Volume", RT5682_STO1_ADC_DIG_VOL, - RT5682_L_VOL_SFT, RT5682_R_VOL_SFT, 127, 0, adc_vol_tlv), + RT5682_L_VOL_SFT + 1, RT5682_R_VOL_SFT + 1, 63, 0, adc_vol_tlv), /* ADC Boost Volume Control */ SOC_DOUBLE_TLV("STO1 ADC Boost Gain Volume", RT5682_STO1_ADC_BOOST, diff --git a/sound/soc/codecs/sigmadsp.c b/sound/soc/codecs/sigmadsp.c index d53680ac78e4..6df158669420 100644 --- a/sound/soc/codecs/sigmadsp.c +++ b/sound/soc/codecs/sigmadsp.c @@ -117,8 +117,7 @@ static int sigmadsp_ctrl_write(struct sigmadsp *sigmadsp, struct sigmadsp_control *ctrl, void *data) { /* safeload loads up to 20 bytes in a atomic operation */ - if (ctrl->num_bytes > 4 && ctrl->num_bytes <= 20 && sigmadsp->ops && - sigmadsp->ops->safeload) + if (ctrl->num_bytes <= 20 && sigmadsp->ops && sigmadsp->ops->safeload) return sigmadsp->ops->safeload(sigmadsp, ctrl->addr, data, ctrl->num_bytes); else diff --git a/sound/soc/codecs/tas6424.c b/sound/soc/codecs/tas6424.c index 14999b999fd3..0d6145549a98 100644 --- a/sound/soc/codecs/tas6424.c +++ b/sound/soc/codecs/tas6424.c @@ -424,8 +424,10 @@ static void tas6424_fault_check_work(struct work_struct *work) TAS6424_FAULT_PVDD_UV | TAS6424_FAULT_VBAT_UV; - if (reg) + if (!reg) { + tas6424->last_fault1 = reg; goto check_global_fault2_reg; + } /* * Only flag errors once for a given occurrence. This is needed as @@ -461,8 +463,10 @@ check_global_fault2_reg: TAS6424_FAULT_OTSD_CH3 | TAS6424_FAULT_OTSD_CH4; - if (!reg) + if (!reg) { + tas6424->last_fault2 = reg; goto check_warn_reg; + } if ((reg & TAS6424_FAULT_OTSD) && !(tas6424->last_fault2 & TAS6424_FAULT_OTSD)) dev_crit(dev, "experienced a global overtemp shutdown\n"); @@ -497,8 +501,10 @@ check_warn_reg: TAS6424_WARN_VDD_OTW_CH3 | TAS6424_WARN_VDD_OTW_CH4; - if (!reg) + if (!reg) { + tas6424->last_warn = reg; goto out; + } if ((reg & TAS6424_WARN_VDD_UV) && !(tas6424->last_warn & TAS6424_WARN_VDD_UV)) dev_warn(dev, "experienced a VDD under voltage condition\n"); diff --git a/sound/soc/codecs/wm8804-i2c.c b/sound/soc/codecs/wm8804-i2c.c index f27464c2c5ba..79541960f45d 100644 --- a/sound/soc/codecs/wm8804-i2c.c +++ b/sound/soc/codecs/wm8804-i2c.c @@ -13,6 +13,7 @@ #include <linux/init.h> #include <linux/module.h> #include <linux/i2c.h> +#include <linux/acpi.h> #include "wm8804.h" @@ -40,17 +41,29 @@ static const struct i2c_device_id wm8804_i2c_id[] = { }; MODULE_DEVICE_TABLE(i2c, wm8804_i2c_id); +#if defined(CONFIG_OF) static const struct of_device_id wm8804_of_match[] = { { .compatible = "wlf,wm8804", }, { } }; MODULE_DEVICE_TABLE(of, wm8804_of_match); +#endif + +#ifdef CONFIG_ACPI +static const struct acpi_device_id wm8804_acpi_match[] = { + { "1AEC8804", 0 }, /* Wolfson PCI ID + part ID */ + { "10138804", 0 }, /* Cirrus Logic PCI ID + part ID */ + { }, +}; +MODULE_DEVICE_TABLE(acpi, wm8804_acpi_match); +#endif static struct i2c_driver wm8804_i2c_driver = { .driver = { .name = "wm8804", .pm = &wm8804_pm, - .of_match_table = wm8804_of_match, + .of_match_table = of_match_ptr(wm8804_of_match), + .acpi_match_table = ACPI_PTR(wm8804_acpi_match), }, .probe = wm8804_i2c_probe, .remove = wm8804_i2c_remove, diff --git a/sound/soc/codecs/wm9712.c b/sound/soc/codecs/wm9712.c index 953d94d50586..ade34c26ad2f 100644 --- a/sound/soc/codecs/wm9712.c +++ b/sound/soc/codecs/wm9712.c @@ -719,7 +719,7 @@ static int wm9712_probe(struct platform_device *pdev) static struct platform_driver wm9712_component_driver = { .driver = { - .name = "wm9712-component", + .name = "wm9712-codec", }, .probe = wm9712_probe, diff --git a/sound/soc/intel/boards/bytcr_rt5640.c b/sound/soc/intel/boards/bytcr_rt5640.c index d32844f94d74..b6dc524830b2 100644 --- a/sound/soc/intel/boards/bytcr_rt5640.c +++ b/sound/soc/intel/boards/bytcr_rt5640.c @@ -575,6 +575,17 @@ static const struct dmi_system_id byt_rt5640_quirk_table[] = { BYT_RT5640_MONO_SPEAKER | BYT_RT5640_MCLK_EN), }, + { /* Linx Linx7 tablet */ + .matches = { + DMI_EXACT_MATCH(DMI_SYS_VENDOR, "LINX"), + DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "LINX7"), + }, + .driver_data = (void *)(BYTCR_INPUT_DEFAULTS | + BYT_RT5640_MONO_SPEAKER | + BYT_RT5640_JD_NOT_INV | + BYT_RT5640_SSP0_AIF1 | + BYT_RT5640_MCLK_EN), + }, { /* MSI S100 tablet */ .matches = { DMI_EXACT_MATCH(DMI_SYS_VENDOR, "Micro-Star International Co., Ltd."), @@ -602,6 +613,21 @@ static const struct dmi_system_id byt_rt5640_quirk_table[] = { BYT_RT5640_SSP0_AIF1 | BYT_RT5640_MCLK_EN), }, + { /* Onda v975w */ + .matches = { + DMI_EXACT_MATCH(DMI_BOARD_VENDOR, "AMI Corporation"), + DMI_EXACT_MATCH(DMI_BOARD_NAME, "Aptio CRB"), + /* The above are too generic, also match BIOS info */ + DMI_EXACT_MATCH(DMI_BIOS_VERSION, "5.6.5"), + DMI_EXACT_MATCH(DMI_BIOS_DATE, "07/25/2014"), + }, + .driver_data = (void *)(BYT_RT5640_IN1_MAP | + BYT_RT5640_JD_SRC_JD2_IN4N | + BYT_RT5640_OVCD_TH_2000UA | + BYT_RT5640_OVCD_SF_0P75 | + BYT_RT5640_DIFF_MIC | + BYT_RT5640_MCLK_EN), + }, { /* Pipo W4 */ .matches = { DMI_EXACT_MATCH(DMI_BOARD_VENDOR, "AMI Corporation"), diff --git a/sound/soc/intel/skylake/skl.c b/sound/soc/intel/skylake/skl.c index dce649485649..1d17be0f78a0 100644 --- a/sound/soc/intel/skylake/skl.c +++ b/sound/soc/intel/skylake/skl.c @@ -834,7 +834,7 @@ static int skl_first_init(struct hdac_bus *bus) return -ENXIO; } - skl_init_chip(bus, true); + snd_hdac_bus_reset_link(bus, true); snd_hdac_bus_parse_capabilities(bus); diff --git a/sound/soc/qcom/qdsp6/q6routing.c b/sound/soc/qcom/qdsp6/q6routing.c index dc94c5c53788..c6b51571be94 100644 --- a/sound/soc/qcom/qdsp6/q6routing.c +++ b/sound/soc/qcom/qdsp6/q6routing.c @@ -960,8 +960,10 @@ static int msm_routing_probe(struct snd_soc_component *c) { int i; - for (i = 0; i < MAX_SESSIONS; i++) + for (i = 0; i < MAX_SESSIONS; i++) { routing_data->sessions[i].port_id = -1; + routing_data->sessions[i].fedai_id = -1; + } return 0; } diff --git a/sound/soc/sh/rcar/adg.c b/sound/soc/sh/rcar/adg.c index 3a3064dda57f..051f96405346 100644 --- a/sound/soc/sh/rcar/adg.c +++ b/sound/soc/sh/rcar/adg.c @@ -462,6 +462,11 @@ static void rsnd_adg_get_clkout(struct rsnd_priv *priv, goto rsnd_adg_get_clkout_end; req_size = prop->length / sizeof(u32); + if (req_size > REQ_SIZE) { + dev_err(dev, + "too many clock-frequency, use top %d\n", REQ_SIZE); + req_size = REQ_SIZE; + } of_property_read_u32_array(np, "clock-frequency", req_rate, req_size); req_48kHz_rate = 0; diff --git a/sound/soc/sh/rcar/core.c b/sound/soc/sh/rcar/core.c index f8425d8b44d2..d23c2bbff0cf 100644 --- a/sound/soc/sh/rcar/core.c +++ b/sound/soc/sh/rcar/core.c @@ -478,7 +478,7 @@ static int rsnd_status_update(u32 *status, (func_call && (mod)->ops->fn) ? #fn : ""); \ if (func_call && (mod)->ops->fn) \ tmp = (mod)->ops->fn(mod, io, param); \ - if (tmp) \ + if (tmp && (tmp != -EPROBE_DEFER)) \ dev_err(dev, "%s[%d] : %s error %d\n", \ rsnd_mod_name(mod), rsnd_mod_id(mod), \ #fn, tmp); \ @@ -958,12 +958,23 @@ static void rsnd_soc_dai_shutdown(struct snd_pcm_substream *substream, rsnd_dai_stream_quit(io); } +static int rsnd_soc_dai_prepare(struct snd_pcm_substream *substream, + struct snd_soc_dai *dai) +{ + struct rsnd_priv *priv = rsnd_dai_to_priv(dai); + struct rsnd_dai *rdai = rsnd_dai_to_rdai(dai); + struct rsnd_dai_stream *io = rsnd_rdai_to_io(rdai, substream); + + return rsnd_dai_call(prepare, io, priv); +} + static const struct snd_soc_dai_ops rsnd_soc_dai_ops = { .startup = rsnd_soc_dai_startup, .shutdown = rsnd_soc_dai_shutdown, .trigger = rsnd_soc_dai_trigger, .set_fmt = rsnd_soc_dai_set_fmt, .set_tdm_slot = rsnd_soc_set_dai_tdm_slot, + .prepare = rsnd_soc_dai_prepare, }; void rsnd_parse_connect_common(struct rsnd_dai *rdai, @@ -1550,6 +1561,14 @@ exit_snd_probe: rsnd_dai_call(remove, &rdai->capture, priv); } + /* + * adg is very special mod which can't use rsnd_dai_call(remove), + * and it registers ADG clock on probe. + * It should be unregister if probe failed. + * Mainly it is assuming -EPROBE_DEFER case + */ + rsnd_adg_remove(priv); + return ret; } diff --git a/sound/soc/sh/rcar/dma.c b/sound/soc/sh/rcar/dma.c index fe63ef8600d0..d65ea7bc4dac 100644 --- a/sound/soc/sh/rcar/dma.c +++ b/sound/soc/sh/rcar/dma.c @@ -241,6 +241,10 @@ static int rsnd_dmaen_attach(struct rsnd_dai_stream *io, /* try to get DMAEngine channel */ chan = rsnd_dmaen_request_channel(io, mod_from, mod_to); if (IS_ERR_OR_NULL(chan)) { + /* Let's follow when -EPROBE_DEFER case */ + if (PTR_ERR(chan) == -EPROBE_DEFER) + return PTR_ERR(chan); + /* * DMA failed. try to PIO mode * see diff --git a/sound/soc/sh/rcar/rsnd.h b/sound/soc/sh/rcar/rsnd.h index 96d93330b1e1..8f7a0abfa751 100644 --- a/sound/soc/sh/rcar/rsnd.h +++ b/sound/soc/sh/rcar/rsnd.h @@ -280,6 +280,9 @@ struct rsnd_mod_ops { int (*nolock_stop)(struct rsnd_mod *mod, struct rsnd_dai_stream *io, struct rsnd_priv *priv); + int (*prepare)(struct rsnd_mod *mod, + struct rsnd_dai_stream *io, + struct rsnd_priv *priv); }; struct rsnd_dai_stream; @@ -309,6 +312,7 @@ struct rsnd_mod { * H 0: fallback * H 0: hw_params * H 0: pointer + * H 0: prepare */ #define __rsnd_mod_shift_nolock_start 0 #define __rsnd_mod_shift_nolock_stop 0 @@ -323,6 +327,7 @@ struct rsnd_mod { #define __rsnd_mod_shift_fallback 28 /* always called */ #define __rsnd_mod_shift_hw_params 28 /* always called */ #define __rsnd_mod_shift_pointer 28 /* always called */ +#define __rsnd_mod_shift_prepare 28 /* always called */ #define __rsnd_mod_add_probe 0 #define __rsnd_mod_add_remove 0 @@ -337,6 +342,7 @@ struct rsnd_mod { #define __rsnd_mod_add_fallback 0 #define __rsnd_mod_add_hw_params 0 #define __rsnd_mod_add_pointer 0 +#define __rsnd_mod_add_prepare 0 #define __rsnd_mod_call_probe 0 #define __rsnd_mod_call_remove 0 @@ -351,6 +357,7 @@ struct rsnd_mod { #define __rsnd_mod_call_pointer 0 #define __rsnd_mod_call_nolock_start 0 #define __rsnd_mod_call_nolock_stop 1 +#define __rsnd_mod_call_prepare 0 #define rsnd_mod_to_priv(mod) ((mod)->priv) #define rsnd_mod_name(mod) ((mod)->ops->name) diff --git a/sound/soc/sh/rcar/ssi.c b/sound/soc/sh/rcar/ssi.c index 8304e4ec9242..3f880ec66459 100644 --- a/sound/soc/sh/rcar/ssi.c +++ b/sound/soc/sh/rcar/ssi.c @@ -283,7 +283,7 @@ static int rsnd_ssi_master_clk_start(struct rsnd_mod *mod, if (rsnd_ssi_is_multi_slave(mod, io)) return 0; - if (ssi->usrcnt > 1) { + if (ssi->rate) { if (ssi->rate != rate) { dev_err(dev, "SSI parent/child should use same rate\n"); return -EINVAL; @@ -434,7 +434,6 @@ static int rsnd_ssi_init(struct rsnd_mod *mod, struct rsnd_priv *priv) { struct rsnd_ssi *ssi = rsnd_mod_to_ssi(mod); - int ret; if (!rsnd_ssi_is_run_mods(mod, io)) return 0; @@ -443,10 +442,6 @@ static int rsnd_ssi_init(struct rsnd_mod *mod, rsnd_mod_power_on(mod); - ret = rsnd_ssi_master_clk_start(mod, io); - if (ret < 0) - return ret; - rsnd_ssi_config_init(mod, io); rsnd_ssi_register_setup(mod); @@ -852,6 +847,13 @@ static int rsnd_ssi_pio_pointer(struct rsnd_mod *mod, return 0; } +static int rsnd_ssi_prepare(struct rsnd_mod *mod, + struct rsnd_dai_stream *io, + struct rsnd_priv *priv) +{ + return rsnd_ssi_master_clk_start(mod, io); +} + static struct rsnd_mod_ops rsnd_ssi_pio_ops = { .name = SSI_NAME, .probe = rsnd_ssi_common_probe, @@ -864,6 +866,7 @@ static struct rsnd_mod_ops rsnd_ssi_pio_ops = { .pointer = rsnd_ssi_pio_pointer, .pcm_new = rsnd_ssi_pcm_new, .hw_params = rsnd_ssi_hw_params, + .prepare = rsnd_ssi_prepare, }; static int rsnd_ssi_dma_probe(struct rsnd_mod *mod, @@ -940,6 +943,7 @@ static struct rsnd_mod_ops rsnd_ssi_dma_ops = { .pcm_new = rsnd_ssi_pcm_new, .fallback = rsnd_ssi_fallback, .hw_params = rsnd_ssi_hw_params, + .prepare = rsnd_ssi_prepare, }; int rsnd_ssi_is_dma_mode(struct rsnd_mod *mod) diff --git a/sound/soc/soc-core.c b/sound/soc/soc-core.c index 9cfe10d8040c..473eefe8658e 100644 --- a/sound/soc/soc-core.c +++ b/sound/soc/soc-core.c @@ -1447,7 +1447,7 @@ static int soc_link_dai_widgets(struct snd_soc_card *card, sink = codec_dai->playback_widget; source = cpu_dai->capture_widget; if (sink && source) { - ret = snd_soc_dapm_new_pcm(card, dai_link->params, + ret = snd_soc_dapm_new_pcm(card, rtd, dai_link->params, dai_link->num_params, source, sink); if (ret != 0) { @@ -1460,7 +1460,7 @@ static int soc_link_dai_widgets(struct snd_soc_card *card, sink = cpu_dai->playback_widget; source = codec_dai->capture_widget; if (sink && source) { - ret = snd_soc_dapm_new_pcm(card, dai_link->params, + ret = snd_soc_dapm_new_pcm(card, rtd, dai_link->params, dai_link->num_params, source, sink); if (ret != 0) { diff --git a/sound/soc/soc-dapm.c b/sound/soc/soc-dapm.c index 7e96793050c9..461d951917c0 100644 --- a/sound/soc/soc-dapm.c +++ b/sound/soc/soc-dapm.c @@ -3652,6 +3652,7 @@ static int snd_soc_dai_link_event(struct snd_soc_dapm_widget *w, { struct snd_soc_dapm_path *source_p, *sink_p; struct snd_soc_dai *source, *sink; + struct snd_soc_pcm_runtime *rtd = w->priv; const struct snd_soc_pcm_stream *config = w->params + w->params_select; struct snd_pcm_substream substream; struct snd_pcm_hw_params *params = NULL; @@ -3711,6 +3712,7 @@ static int snd_soc_dai_link_event(struct snd_soc_dapm_widget *w, goto out; } substream.runtime = runtime; + substream.private_data = rtd; switch (event) { case SND_SOC_DAPM_PRE_PMU: @@ -3895,6 +3897,7 @@ outfree_w_param: } int snd_soc_dapm_new_pcm(struct snd_soc_card *card, + struct snd_soc_pcm_runtime *rtd, const struct snd_soc_pcm_stream *params, unsigned int num_params, struct snd_soc_dapm_widget *source, @@ -3963,6 +3966,7 @@ int snd_soc_dapm_new_pcm(struct snd_soc_card *card, w->params = params; w->num_params = num_params; + w->priv = rtd; ret = snd_soc_dapm_add_path(&card->dapm, source, w, NULL, NULL); if (ret) diff --git a/tools/arch/arm/include/uapi/asm/kvm.h b/tools/arch/arm/include/uapi/asm/kvm.h index 16e006f708ca..4602464ebdfb 100644 --- a/tools/arch/arm/include/uapi/asm/kvm.h +++ b/tools/arch/arm/include/uapi/asm/kvm.h @@ -27,6 +27,7 @@ #define __KVM_HAVE_GUEST_DEBUG #define __KVM_HAVE_IRQ_LINE #define __KVM_HAVE_READONLY_MEM +#define __KVM_HAVE_VCPU_EVENTS #define KVM_COALESCED_MMIO_PAGE_OFFSET 1 @@ -125,6 +126,18 @@ struct kvm_sync_regs { struct kvm_arch_memory_slot { }; +/* for KVM_GET/SET_VCPU_EVENTS */ +struct kvm_vcpu_events { + struct { + __u8 serror_pending; + __u8 serror_has_esr; + /* Align it to 8 bytes */ + __u8 pad[6]; + __u64 serror_esr; + } exception; + __u32 reserved[12]; +}; + /* If you need to interpret the index values, here is the key: */ #define KVM_REG_ARM_COPROC_MASK 0x000000000FFF0000 #define KVM_REG_ARM_COPROC_SHIFT 16 diff --git a/tools/arch/arm64/include/uapi/asm/kvm.h b/tools/arch/arm64/include/uapi/asm/kvm.h index 4e76630dd655..97c3478ee6e7 100644 --- a/tools/arch/arm64/include/uapi/asm/kvm.h +++ b/tools/arch/arm64/include/uapi/asm/kvm.h @@ -39,6 +39,7 @@ #define __KVM_HAVE_GUEST_DEBUG #define __KVM_HAVE_IRQ_LINE #define __KVM_HAVE_READONLY_MEM +#define __KVM_HAVE_VCPU_EVENTS #define KVM_COALESCED_MMIO_PAGE_OFFSET 1 @@ -154,6 +155,18 @@ struct kvm_sync_regs { struct kvm_arch_memory_slot { }; +/* for KVM_GET/SET_VCPU_EVENTS */ +struct kvm_vcpu_events { + struct { + __u8 serror_pending; + __u8 serror_has_esr; + /* Align it to 8 bytes */ + __u8 pad[6]; + __u64 serror_esr; + } exception; + __u32 reserved[12]; +}; + /* If you need to interpret the index values, here is the key: */ #define KVM_REG_ARM_COPROC_MASK 0x000000000FFF0000 #define KVM_REG_ARM_COPROC_SHIFT 16 diff --git a/tools/arch/s390/include/uapi/asm/kvm.h b/tools/arch/s390/include/uapi/asm/kvm.h index 4cdaa55fabfe..9a50f02b9894 100644 --- a/tools/arch/s390/include/uapi/asm/kvm.h +++ b/tools/arch/s390/include/uapi/asm/kvm.h @@ -4,7 +4,7 @@ /* * KVM s390 specific structures and definitions * - * Copyright IBM Corp. 2008 + * Copyright IBM Corp. 2008, 2018 * * Author(s): Carsten Otte <cotte@de.ibm.com> * Christian Borntraeger <borntraeger@de.ibm.com> @@ -225,6 +225,7 @@ struct kvm_guest_debug_arch { #define KVM_SYNC_FPRS (1UL << 8) #define KVM_SYNC_GSCB (1UL << 9) #define KVM_SYNC_BPBC (1UL << 10) +#define KVM_SYNC_ETOKEN (1UL << 11) /* length and alignment of the sdnx as a power of two */ #define SDNXC 8 #define SDNXL (1UL << SDNXC) @@ -258,6 +259,8 @@ struct kvm_sync_regs { struct { __u64 reserved1[2]; __u64 gscb[4]; + __u64 etoken; + __u64 etoken_extension; }; }; }; diff --git a/tools/arch/x86/include/uapi/asm/kvm.h b/tools/arch/x86/include/uapi/asm/kvm.h index c535c2fdea13..86299efa804a 100644 --- a/tools/arch/x86/include/uapi/asm/kvm.h +++ b/tools/arch/x86/include/uapi/asm/kvm.h @@ -378,4 +378,41 @@ struct kvm_sync_regs { #define KVM_X86_QUIRK_LINT0_REENABLED (1 << 0) #define KVM_X86_QUIRK_CD_NW_CLEARED (1 << 1) +#define KVM_STATE_NESTED_GUEST_MODE 0x00000001 +#define KVM_STATE_NESTED_RUN_PENDING 0x00000002 + +#define KVM_STATE_NESTED_SMM_GUEST_MODE 0x00000001 +#define KVM_STATE_NESTED_SMM_VMXON 0x00000002 + +struct kvm_vmx_nested_state { + __u64 vmxon_pa; + __u64 vmcs_pa; + + struct { + __u16 flags; + } smm; +}; + +/* for KVM_CAP_NESTED_STATE */ +struct kvm_nested_state { + /* KVM_STATE_* flags */ + __u16 flags; + + /* 0 for VMX, 1 for SVM. */ + __u16 format; + + /* 128 for SVM, 128 + VMCS size for VMX. */ + __u32 size; + + union { + /* VMXON, VMCS */ + struct kvm_vmx_nested_state vmx; + + /* Pad the header to 128 bytes. */ + __u8 pad[120]; + }; + + __u8 data[0]; +}; + #endif /* _ASM_X86_KVM_H */ diff --git a/tools/hv/hv_kvp_daemon.c b/tools/hv/hv_kvp_daemon.c index dbf6e8bd98ba..bbb2a8ef367c 100644 --- a/tools/hv/hv_kvp_daemon.c +++ b/tools/hv/hv_kvp_daemon.c @@ -286,7 +286,7 @@ static int kvp_key_delete(int pool, const __u8 *key, int key_size) * Found a match; just move the remaining * entries up. */ - if (i == num_records) { + if (i == (num_records - 1)) { kvp_file_info[pool].num_records--; kvp_update_file(pool); return 0; diff --git a/tools/include/linux/lockdep.h b/tools/include/linux/lockdep.h index 6b0c36a58fcb..e56997288f2b 100644 --- a/tools/include/linux/lockdep.h +++ b/tools/include/linux/lockdep.h @@ -30,9 +30,12 @@ struct task_struct { struct held_lock held_locks[MAX_LOCK_DEPTH]; gfp_t lockdep_reclaim_gfp; int pid; + int state; char comm[17]; }; +#define TASK_RUNNING 0 + extern struct task_struct *__curr(void); #define current (__curr()) diff --git a/tools/include/linux/nmi.h b/tools/include/linux/nmi.h new file mode 100644 index 000000000000..e69de29bb2d1 --- /dev/null +++ b/tools/include/linux/nmi.h diff --git a/tools/include/tools/libc_compat.h b/tools/include/tools/libc_compat.h index 664ced8cb1b0..e907ba6f15e5 100644 --- a/tools/include/tools/libc_compat.h +++ b/tools/include/tools/libc_compat.h @@ -1,4 +1,4 @@ -// SPDX-License-Identifier: GPL-2.0+ +// SPDX-License-Identifier: (LGPL-2.0+ OR BSD-2-Clause) /* Copyright (C) 2018 Netronome Systems, Inc. */ #ifndef __TOOLS_LIBC_COMPAT_H diff --git a/tools/include/uapi/asm-generic/unistd.h b/tools/include/uapi/asm-generic/unistd.h index 42990676a55e..df4bedb9b01c 100644 --- a/tools/include/uapi/asm-generic/unistd.h +++ b/tools/include/uapi/asm-generic/unistd.h @@ -734,9 +734,11 @@ __SYSCALL(__NR_pkey_free, sys_pkey_free) __SYSCALL(__NR_statx, sys_statx) #define __NR_io_pgetevents 292 __SC_COMP(__NR_io_pgetevents, sys_io_pgetevents, compat_sys_io_pgetevents) +#define __NR_rseq 293 +__SYSCALL(__NR_rseq, sys_rseq) #undef __NR_syscalls -#define __NR_syscalls 293 +#define __NR_syscalls 294 /* * 32 bit systems traditionally used different diff --git a/tools/include/uapi/drm/drm.h b/tools/include/uapi/drm/drm.h index 9c660e1688ab..300f336633f2 100644 --- a/tools/include/uapi/drm/drm.h +++ b/tools/include/uapi/drm/drm.h @@ -687,6 +687,15 @@ struct drm_get_cap { */ #define DRM_CLIENT_CAP_ASPECT_RATIO 4 +/** + * DRM_CLIENT_CAP_WRITEBACK_CONNECTORS + * + * If set to 1, the DRM core will expose special connectors to be used for + * writing back to memory the scene setup in the commit. Depends on client + * also supporting DRM_CLIENT_CAP_ATOMIC + */ +#define DRM_CLIENT_CAP_WRITEBACK_CONNECTORS 5 + /** DRM_IOCTL_SET_CLIENT_CAP ioctl argument type */ struct drm_set_client_cap { __u64 capability; diff --git a/tools/include/uapi/linux/if_link.h b/tools/include/uapi/linux/if_link.h index 43391e2d1153..58faab897201 100644 --- a/tools/include/uapi/linux/if_link.h +++ b/tools/include/uapi/linux/if_link.h @@ -161,6 +161,7 @@ enum { IFLA_EVENT, IFLA_NEW_NETNSID, IFLA_IF_NETNSID, + IFLA_TARGET_NETNSID = IFLA_IF_NETNSID, /* new alias */ IFLA_CARRIER_UP_COUNT, IFLA_CARRIER_DOWN_COUNT, IFLA_NEW_IFINDEX, @@ -554,6 +555,7 @@ enum { IFLA_GENEVE_UDP_ZERO_CSUM6_TX, IFLA_GENEVE_UDP_ZERO_CSUM6_RX, IFLA_GENEVE_LABEL, + IFLA_GENEVE_TTL_INHERIT, __IFLA_GENEVE_MAX }; #define IFLA_GENEVE_MAX (__IFLA_GENEVE_MAX - 1) diff --git a/tools/include/uapi/linux/kvm.h b/tools/include/uapi/linux/kvm.h index b6270a3b38e9..07548de5c988 100644 --- a/tools/include/uapi/linux/kvm.h +++ b/tools/include/uapi/linux/kvm.h @@ -949,6 +949,9 @@ struct kvm_ppc_resize_hpt { #define KVM_CAP_GET_MSR_FEATURES 153 #define KVM_CAP_HYPERV_EVENTFD 154 #define KVM_CAP_HYPERV_TLBFLUSH 155 +#define KVM_CAP_S390_HPAGE_1M 156 +#define KVM_CAP_NESTED_STATE 157 +#define KVM_CAP_ARM_INJECT_SERROR_ESR 158 #ifdef KVM_CAP_IRQ_ROUTING @@ -1391,6 +1394,9 @@ struct kvm_enc_region { /* Available with KVM_CAP_HYPERV_EVENTFD */ #define KVM_HYPERV_EVENTFD _IOW(KVMIO, 0xbd, struct kvm_hyperv_eventfd) +/* Available with KVM_CAP_NESTED_STATE */ +#define KVM_GET_NESTED_STATE _IOWR(KVMIO, 0xbe, struct kvm_nested_state) +#define KVM_SET_NESTED_STATE _IOW(KVMIO, 0xbf, struct kvm_nested_state) /* Secure Encrypted Virtualization command */ enum sev_cmd_id { diff --git a/tools/include/uapi/linux/perf_event.h b/tools/include/uapi/linux/perf_event.h index eeb787b1c53c..f35eb72739c0 100644 --- a/tools/include/uapi/linux/perf_event.h +++ b/tools/include/uapi/linux/perf_event.h @@ -144,7 +144,7 @@ enum perf_event_sample_format { PERF_SAMPLE_MAX = 1U << 20, /* non-ABI */ - __PERF_SAMPLE_CALLCHAIN_EARLY = 1ULL << 63, + __PERF_SAMPLE_CALLCHAIN_EARLY = 1ULL << 63, /* non-ABI; internal use */ }; /* diff --git a/tools/include/uapi/linux/vhost.h b/tools/include/uapi/linux/vhost.h index c51f8e5cc608..84c3de89696a 100644 --- a/tools/include/uapi/linux/vhost.h +++ b/tools/include/uapi/linux/vhost.h @@ -65,6 +65,7 @@ struct vhost_iotlb_msg { }; #define VHOST_IOTLB_MSG 0x1 +#define VHOST_IOTLB_MSG_V2 0x2 struct vhost_msg { int type; @@ -74,6 +75,15 @@ struct vhost_msg { }; }; +struct vhost_msg_v2 { + __u32 type; + __u32 reserved; + union { + struct vhost_iotlb_msg iotlb; + __u8 padding[64]; + }; +}; + struct vhost_memory_region { __u64 guest_phys_addr; __u64 memory_size; /* bytes */ @@ -160,6 +170,14 @@ struct vhost_memory { #define VHOST_GET_VRING_BUSYLOOP_TIMEOUT _IOW(VHOST_VIRTIO, 0x24, \ struct vhost_vring_state) +/* Set or get vhost backend capability */ + +/* Use message type V2 */ +#define VHOST_BACKEND_F_IOTLB_MSG_V2 0x1 + +#define VHOST_SET_BACKEND_FEATURES _IOW(VHOST_VIRTIO, 0x25, __u64) +#define VHOST_GET_BACKEND_FEATURES _IOR(VHOST_VIRTIO, 0x26, __u64) + /* VHOST_NET specific defines */ /* Attach virtio net ring to a raw socket, or tap device. diff --git a/tools/kvm/kvm_stat/kvm_stat b/tools/kvm/kvm_stat/kvm_stat index 56c4b3f8a01b..439b8a27488d 100755 --- a/tools/kvm/kvm_stat/kvm_stat +++ b/tools/kvm/kvm_stat/kvm_stat @@ -759,12 +759,18 @@ class DebugfsProvider(Provider): if len(vms) == 0: self.do_read = False - self.paths = filter(lambda x: "{}-".format(pid) in x, vms) + self.paths = list(filter(lambda x: "{}-".format(pid) in x, vms)) else: self.paths = [] self.do_read = True - self.reset() + + def _verify_paths(self): + """Remove invalid paths""" + for path in self.paths: + if not os.path.exists(os.path.join(PATH_DEBUGFS_KVM, path)): + self.paths.remove(path) + continue def read(self, reset=0, by_guest=0): """Returns a dict with format:'file name / field -> current value'. @@ -780,6 +786,7 @@ class DebugfsProvider(Provider): # If no debugfs filtering support is available, then don't read. if not self.do_read: return results + self._verify_paths() paths = self.paths if self._pid == 0: @@ -1096,15 +1103,16 @@ class Tui(object): pid = self.stats.pid_filter self.screen.erase() gname = self.get_gname_from_pid(pid) + self._gname = gname if gname: gname = ('({})'.format(gname[:MAX_GUEST_NAME_LEN] + '...' if len(gname) > MAX_GUEST_NAME_LEN else gname)) if pid > 0: - self.screen.addstr(0, 0, 'kvm statistics - pid {0} {1}' - .format(pid, gname), curses.A_BOLD) + self._headline = 'kvm statistics - pid {0} {1}'.format(pid, gname) else: - self.screen.addstr(0, 0, 'kvm statistics - summary', curses.A_BOLD) + self._headline = 'kvm statistics - summary' + self.screen.addstr(0, 0, self._headline, curses.A_BOLD) if self.stats.fields_filter: regex = self.stats.fields_filter if len(regex) > MAX_REGEX_LEN: @@ -1162,6 +1170,19 @@ class Tui(object): return sorted_items + if not self._is_running_guest(self.stats.pid_filter): + if self._gname: + try: # ...to identify the guest by name in case it's back + pids = self.get_pid_from_gname(self._gname) + if len(pids) == 1: + self._refresh_header(pids[0]) + self._update_pid(pids[0]) + return + except: + pass + self._display_guest_dead() + # leave final data on screen + return row = 3 self.screen.move(row, 0) self.screen.clrtobot() @@ -1184,6 +1205,7 @@ class Tui(object): # print events tavg = 0 tcur = 0 + guest_removed = False for key, values in get_sorted_events(self, stats): if row >= self.screen.getmaxyx()[0] - 1 or values == (0, 0): break @@ -1191,7 +1213,10 @@ class Tui(object): key = self.get_gname_from_pid(key) if not key: continue - cur = int(round(values.delta / sleeptime)) if values.delta else '' + cur = int(round(values.delta / sleeptime)) if values.delta else 0 + if cur < 0: + guest_removed = True + continue if key[0] != ' ': if values.delta: tcur += values.delta @@ -1204,13 +1229,21 @@ class Tui(object): values.value * 100 / float(ltotal), cur)) row += 1 if row == 3: - self.screen.addstr(4, 1, 'No matching events reported yet') + if guest_removed: + self.screen.addstr(4, 1, 'Guest removed, updating...') + else: + self.screen.addstr(4, 1, 'No matching events reported yet') if row > 4: tavg = int(round(tcur / sleeptime)) if tcur > 0 else '' self.screen.addstr(row, 1, '%-40s %10d %8s' % ('Total', total, tavg), curses.A_BOLD) self.screen.refresh() + def _display_guest_dead(self): + marker = ' Guest is DEAD ' + y = min(len(self._headline), 80 - len(marker)) + self.screen.addstr(0, y, marker, curses.A_BLINK | curses.A_STANDOUT) + def _show_msg(self, text): """Display message centered text and exit on key press""" hint = 'Press any key to continue' @@ -1219,10 +1252,10 @@ class Tui(object): (x, term_width) = self.screen.getmaxyx() row = 2 for line in text: - start = (term_width - len(line)) / 2 + start = (term_width - len(line)) // 2 self.screen.addstr(row, start, line) row += 1 - self.screen.addstr(row + 1, (term_width - len(hint)) / 2, hint, + self.screen.addstr(row + 1, (term_width - len(hint)) // 2, hint, curses.A_STANDOUT) self.screen.getkey() @@ -1319,6 +1352,12 @@ class Tui(object): msg = '"' + str(val) + '": Invalid value' self._refresh_header() + def _is_running_guest(self, pid): + """Check if pid is still a running process.""" + if not pid: + return True + return os.path.isdir(os.path.join('/proc/', str(pid))) + def _show_vm_selection_by_guest(self): """Draws guest selection mask. @@ -1346,7 +1385,7 @@ class Tui(object): if not guest or guest == '0': break if guest.isdigit(): - if not os.path.isdir(os.path.join('/proc/', guest)): + if not self._is_running_guest(guest): msg = '"' + guest + '": Not a running process' continue pid = int(guest) diff --git a/tools/lib/bpf/Build b/tools/lib/bpf/Build index 512b2c0ba0d2..7bc31c905018 100644 --- a/tools/lib/bpf/Build +++ b/tools/lib/bpf/Build @@ -1 +1 @@ -libbpf-y := libbpf.o bpf.o nlattr.o btf.o libbpf_errno.o netlink.o +libbpf-y := libbpf.o bpf.o nlattr.o btf.o libbpf_errno.o str_error.o netlink.o diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c index 9ca8e0e624d8..4f8d43ae20d2 100644 --- a/tools/lib/bpf/libbpf.c +++ b/tools/lib/bpf/libbpf.c @@ -50,6 +50,7 @@ #include "libbpf.h" #include "bpf.h" #include "btf.h" +#include "str_error.h" #ifndef EM_BPF #define EM_BPF 247 @@ -469,7 +470,7 @@ static int bpf_object__elf_init(struct bpf_object *obj) obj->efile.fd = open(obj->path, O_RDONLY); if (obj->efile.fd < 0) { char errmsg[STRERR_BUFSIZE]; - char *cp = strerror_r(errno, errmsg, sizeof(errmsg)); + char *cp = str_error(errno, errmsg, sizeof(errmsg)); pr_warning("failed to open %s: %s\n", obj->path, cp); return -errno; @@ -810,8 +811,7 @@ static int bpf_object__elf_collect(struct bpf_object *obj) data->d_size, name, idx); if (err) { char errmsg[STRERR_BUFSIZE]; - char *cp = strerror_r(-err, errmsg, - sizeof(errmsg)); + char *cp = str_error(-err, errmsg, sizeof(errmsg)); pr_warning("failed to alloc program %s (%s): %s", name, obj->path, cp); @@ -1140,7 +1140,7 @@ bpf_object__create_maps(struct bpf_object *obj) *pfd = bpf_create_map_xattr(&create_attr); if (*pfd < 0 && create_attr.btf_key_type_id) { - cp = strerror_r(errno, errmsg, sizeof(errmsg)); + cp = str_error(errno, errmsg, sizeof(errmsg)); pr_warning("Error in bpf_create_map_xattr(%s):%s(%d). Retrying without BTF.\n", map->name, cp, errno); create_attr.btf_fd = 0; @@ -1155,7 +1155,7 @@ bpf_object__create_maps(struct bpf_object *obj) size_t j; err = *pfd; - cp = strerror_r(errno, errmsg, sizeof(errmsg)); + cp = str_error(errno, errmsg, sizeof(errmsg)); pr_warning("failed to create map (name: '%s'): %s\n", map->name, cp); for (j = 0; j < i; j++) @@ -1339,7 +1339,7 @@ load_program(enum bpf_prog_type type, enum bpf_attach_type expected_attach_type, } ret = -LIBBPF_ERRNO__LOAD; - cp = strerror_r(errno, errmsg, sizeof(errmsg)); + cp = str_error(errno, errmsg, sizeof(errmsg)); pr_warning("load bpf program failed: %s\n", cp); if (log_buf && log_buf[0] != '\0') { @@ -1655,7 +1655,7 @@ static int check_path(const char *path) dir = dirname(dname); if (statfs(dir, &st_fs)) { - cp = strerror_r(errno, errmsg, sizeof(errmsg)); + cp = str_error(errno, errmsg, sizeof(errmsg)); pr_warning("failed to statfs %s: %s\n", dir, cp); err = -errno; } @@ -1691,7 +1691,7 @@ int bpf_program__pin_instance(struct bpf_program *prog, const char *path, } if (bpf_obj_pin(prog->instances.fds[instance], path)) { - cp = strerror_r(errno, errmsg, sizeof(errmsg)); + cp = str_error(errno, errmsg, sizeof(errmsg)); pr_warning("failed to pin program: %s\n", cp); return -errno; } @@ -1709,7 +1709,7 @@ static int make_dir(const char *path) err = -errno; if (err) { - cp = strerror_r(-err, errmsg, sizeof(errmsg)); + cp = str_error(-err, errmsg, sizeof(errmsg)); pr_warning("failed to mkdir %s: %s\n", path, cp); } return err; @@ -1771,7 +1771,7 @@ int bpf_map__pin(struct bpf_map *map, const char *path) } if (bpf_obj_pin(map->fd, path)) { - cp = strerror_r(errno, errmsg, sizeof(errmsg)); + cp = str_error(errno, errmsg, sizeof(errmsg)); pr_warning("failed to pin map: %s\n", cp); return -errno; } diff --git a/tools/lib/bpf/str_error.c b/tools/lib/bpf/str_error.c new file mode 100644 index 000000000000..b8798114a357 --- /dev/null +++ b/tools/lib/bpf/str_error.c @@ -0,0 +1,18 @@ +// SPDX-License-Identifier: LGPL-2.1 +#undef _GNU_SOURCE +#include <string.h> +#include <stdio.h> +#include "str_error.h" + +/* + * Wrapper to allow for building in non-GNU systems such as Alpine Linux's musl + * libc, while checking strerror_r() return to avoid having to check this in + * all places calling it. + */ +char *str_error(int err, char *dst, int len) +{ + int ret = strerror_r(err, dst, len); + if (ret) + snprintf(dst, len, "ERROR: strerror_r(%d)=%d", err, ret); + return dst; +} diff --git a/tools/lib/bpf/str_error.h b/tools/lib/bpf/str_error.h new file mode 100644 index 000000000000..355b1db571d1 --- /dev/null +++ b/tools/lib/bpf/str_error.h @@ -0,0 +1,6 @@ +// SPDX-License-Identifier: LGPL-2.1 +#ifndef BPF_STR_ERROR +#define BPF_STR_ERROR + +char *str_error(int err, char *dst, int len); +#endif // BPF_STR_ERROR diff --git a/tools/perf/Documentation/Makefile b/tools/perf/Documentation/Makefile index 42261a9b280e..ac841bc5c35b 100644 --- a/tools/perf/Documentation/Makefile +++ b/tools/perf/Documentation/Makefile @@ -280,7 +280,7 @@ $(MAN_HTML): $(OUTPUT)%.html : %.txt mv $@+ $@ ifdef USE_ASCIIDOCTOR -$(OUTPUT)%.1 $(OUTPUT)%.5 $(OUTPUT)%.7 : $(OUTPUT)%.txt +$(OUTPUT)%.1 $(OUTPUT)%.5 $(OUTPUT)%.7 : %.txt $(QUIET_ASCIIDOC)$(RM) $@+ $@ && \ $(ASCIIDOC) -b manpage -d manpage \ $(ASCIIDOC_EXTRA) -aperf_version=$(PERF_VERSION) -o $@+ $< && \ diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf index b3d1b12a5081..5224ade3d5af 100644 --- a/tools/perf/Makefile.perf +++ b/tools/perf/Makefile.perf @@ -777,14 +777,12 @@ endif $(call QUIET_INSTALL, libexec) \ $(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)' ifndef NO_LIBBPF - $(call QUIET_INSTALL, lib) \ - $(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perf_include_instdir_SQ)/bpf' - $(call QUIET_INSTALL, include/bpf) \ - $(INSTALL) include/bpf/*.h '$(DESTDIR_SQ)$(perf_include_instdir_SQ)/bpf' - $(call QUIET_INSTALL, lib) \ - $(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perf_examples_instdir_SQ)/bpf' - $(call QUIET_INSTALL, examples/bpf) \ - $(INSTALL) examples/bpf/*.c '$(DESTDIR_SQ)$(perf_examples_instdir_SQ)/bpf' + $(call QUIET_INSTALL, bpf-headers) \ + $(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perf_include_instdir_SQ)/bpf'; \ + $(INSTALL) include/bpf/*.h -t '$(DESTDIR_SQ)$(perf_include_instdir_SQ)/bpf' + $(call QUIET_INSTALL, bpf-examples) \ + $(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perf_examples_instdir_SQ)/bpf'; \ + $(INSTALL) examples/bpf/*.c -t '$(DESTDIR_SQ)$(perf_examples_instdir_SQ)/bpf' endif $(call QUIET_INSTALL, perf-archive) \ $(INSTALL) $(OUTPUT)perf-archive -t '$(DESTDIR_SQ)$(perfexec_instdir_SQ)' diff --git a/tools/perf/arch/arm64/Makefile b/tools/perf/arch/arm64/Makefile index f013b115dc86..dbef716a1913 100644 --- a/tools/perf/arch/arm64/Makefile +++ b/tools/perf/arch/arm64/Makefile @@ -11,7 +11,8 @@ PERF_HAVE_ARCH_REGS_QUERY_REGISTER_OFFSET := 1 out := $(OUTPUT)arch/arm64/include/generated/asm header := $(out)/syscalls.c -sysdef := $(srctree)/tools/include/uapi/asm-generic/unistd.h +incpath := $(srctree)/tools +sysdef := $(srctree)/tools/arch/arm64/include/uapi/asm/unistd.h sysprf := $(srctree)/tools/perf/arch/arm64/entry/syscalls/ systbl := $(sysprf)/mksyscalltbl @@ -19,7 +20,7 @@ systbl := $(sysprf)/mksyscalltbl _dummy := $(shell [ -d '$(out)' ] || mkdir -p '$(out)') $(header): $(sysdef) $(systbl) - $(Q)$(SHELL) '$(systbl)' '$(CC)' '$(HOSTCC)' $(sysdef) > $@ + $(Q)$(SHELL) '$(systbl)' '$(CC)' '$(HOSTCC)' $(incpath) $(sysdef) > $@ clean:: $(call QUIET_CLEAN, arm64) $(RM) $(header) diff --git a/tools/perf/arch/arm64/entry/syscalls/mksyscalltbl b/tools/perf/arch/arm64/entry/syscalls/mksyscalltbl index 52e197317d3e..2dbb8cade048 100755 --- a/tools/perf/arch/arm64/entry/syscalls/mksyscalltbl +++ b/tools/perf/arch/arm64/entry/syscalls/mksyscalltbl @@ -11,7 +11,8 @@ gcc=$1 hostcc=$2 -input=$3 +incpath=$3 +input=$4 if ! test -r $input; then echo "Could not read input file" >&2 @@ -28,7 +29,6 @@ create_table_from_c() cat <<-_EoHEADER #include <stdio.h> - #define __ARCH_WANT_RENAMEAT #include "$input" int main(int argc, char *argv[]) { @@ -42,7 +42,7 @@ create_table_from_c() printf "%s\n" " printf(\"#define SYSCALLTBL_ARM64_MAX_ID %d\\n\", __NR_$last_sc);" printf "}\n" - } | $hostcc -o $create_table_exe -x c - + } | $hostcc -I $incpath/include/uapi -o $create_table_exe -x c - $create_table_exe diff --git a/tools/perf/arch/powerpc/util/sym-handling.c b/tools/perf/arch/powerpc/util/sym-handling.c index 20e7d74d86cd..10a44e946f77 100644 --- a/tools/perf/arch/powerpc/util/sym-handling.c +++ b/tools/perf/arch/powerpc/util/sym-handling.c @@ -22,15 +22,16 @@ bool elf__needs_adjust_symbols(GElf_Ehdr ehdr) #endif -#if !defined(_CALL_ELF) || _CALL_ELF != 2 int arch__choose_best_symbol(struct symbol *syma, struct symbol *symb __maybe_unused) { char *sym = syma->name; +#if !defined(_CALL_ELF) || _CALL_ELF != 2 /* Skip over any initial dot */ if (*sym == '.') sym++; +#endif /* Avoid "SyS" kernel syscall aliases */ if (strlen(sym) >= 3 && !strncmp(sym, "SyS", 3)) @@ -41,6 +42,7 @@ int arch__choose_best_symbol(struct symbol *syma, return SYMBOL_A; } +#if !defined(_CALL_ELF) || _CALL_ELF != 2 /* Allow matching against dot variants */ int arch__compare_symbol_names(const char *namea, const char *nameb) { diff --git a/tools/perf/arch/x86/include/arch-tests.h b/tools/perf/arch/x86/include/arch-tests.h index c1bd979b957b..613709cfbbd0 100644 --- a/tools/perf/arch/x86/include/arch-tests.h +++ b/tools/perf/arch/x86/include/arch-tests.h @@ -9,6 +9,7 @@ struct test; int test__rdpmc(struct test *test __maybe_unused, int subtest); int test__perf_time_to_tsc(struct test *test __maybe_unused, int subtest); int test__insn_x86(struct test *test __maybe_unused, int subtest); +int test__bp_modify(struct test *test, int subtest); #ifdef HAVE_DWARF_UNWIND_SUPPORT struct thread; diff --git a/tools/perf/arch/x86/tests/Build b/tools/perf/arch/x86/tests/Build index 8e2c5a38c3b9..586849ff83a0 100644 --- a/tools/perf/arch/x86/tests/Build +++ b/tools/perf/arch/x86/tests/Build @@ -5,3 +5,4 @@ libperf-y += arch-tests.o libperf-y += rdpmc.o libperf-y += perf-time-to-tsc.o libperf-$(CONFIG_AUXTRACE) += insn-x86.o +libperf-$(CONFIG_X86_64) += bp-modify.o diff --git a/tools/perf/arch/x86/tests/arch-tests.c b/tools/perf/arch/x86/tests/arch-tests.c index cc1802ff5410..d47d3f8e3c8e 100644 --- a/tools/perf/arch/x86/tests/arch-tests.c +++ b/tools/perf/arch/x86/tests/arch-tests.c @@ -24,6 +24,12 @@ struct test arch_tests[] = { .func = test__insn_x86, }, #endif +#if defined(__x86_64__) + { + .desc = "x86 bp modify", + .func = test__bp_modify, + }, +#endif { .func = NULL, }, diff --git a/tools/perf/arch/x86/tests/bp-modify.c b/tools/perf/arch/x86/tests/bp-modify.c new file mode 100644 index 000000000000..f53e4406709f --- /dev/null +++ b/tools/perf/arch/x86/tests/bp-modify.c @@ -0,0 +1,213 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <linux/compiler.h> +#include <sys/types.h> +#include <sys/wait.h> +#include <sys/user.h> +#include <syscall.h> +#include <unistd.h> +#include <stdio.h> +#include <stdlib.h> +#include <sys/ptrace.h> +#include <asm/ptrace.h> +#include <errno.h> +#include "debug.h" +#include "tests/tests.h" +#include "arch-tests.h" + +static noinline int bp_1(void) +{ + pr_debug("in %s\n", __func__); + return 0; +} + +static noinline int bp_2(void) +{ + pr_debug("in %s\n", __func__); + return 0; +} + +static int spawn_child(void) +{ + int child = fork(); + + if (child == 0) { + /* + * The child sets itself for as tracee and + * waits in signal for parent to trace it, + * then it calls bp_1 and quits. + */ + int err = ptrace(PTRACE_TRACEME, 0, NULL, NULL); + + if (err) { + pr_debug("failed to PTRACE_TRACEME\n"); + exit(1); + } + + raise(SIGCONT); + bp_1(); + exit(0); + } + + return child; +} + +/* + * This tests creates HW breakpoint, tries to + * change it and checks it was properly changed. + */ +static int bp_modify1(void) +{ + pid_t child; + int status; + unsigned long rip = 0, dr7 = 1; + + child = spawn_child(); + + waitpid(child, &status, 0); + if (WIFEXITED(status)) { + pr_debug("tracee exited prematurely 1\n"); + return TEST_FAIL; + } + + /* + * The parent does following steps: + * - creates a new breakpoint (id 0) for bp_2 function + * - changes that breakponit to bp_1 function + * - waits for the breakpoint to hit and checks + * it has proper rip of bp_1 function + * - detaches the child + */ + if (ptrace(PTRACE_POKEUSER, child, + offsetof(struct user, u_debugreg[0]), bp_2)) { + pr_debug("failed to set breakpoint, 1st time: %s\n", + strerror(errno)); + goto out; + } + + if (ptrace(PTRACE_POKEUSER, child, + offsetof(struct user, u_debugreg[0]), bp_1)) { + pr_debug("failed to set breakpoint, 2nd time: %s\n", + strerror(errno)); + goto out; + } + + if (ptrace(PTRACE_POKEUSER, child, + offsetof(struct user, u_debugreg[7]), dr7)) { + pr_debug("failed to set dr7: %s\n", strerror(errno)); + goto out; + } + + if (ptrace(PTRACE_CONT, child, NULL, NULL)) { + pr_debug("failed to PTRACE_CONT: %s\n", strerror(errno)); + goto out; + } + + waitpid(child, &status, 0); + if (WIFEXITED(status)) { + pr_debug("tracee exited prematurely 2\n"); + return TEST_FAIL; + } + + rip = ptrace(PTRACE_PEEKUSER, child, + offsetof(struct user_regs_struct, rip), NULL); + if (rip == (unsigned long) -1) { + pr_debug("failed to PTRACE_PEEKUSER: %s\n", + strerror(errno)); + goto out; + } + + pr_debug("rip %lx, bp_1 %p\n", rip, bp_1); + +out: + if (ptrace(PTRACE_DETACH, child, NULL, NULL)) { + pr_debug("failed to PTRACE_DETACH: %s", strerror(errno)); + return TEST_FAIL; + } + + return rip == (unsigned long) bp_1 ? TEST_OK : TEST_FAIL; +} + +/* + * This tests creates HW breakpoint, tries to + * change it to bogus value and checks the original + * breakpoint is hit. + */ +static int bp_modify2(void) +{ + pid_t child; + int status; + unsigned long rip = 0, dr7 = 1; + + child = spawn_child(); + + waitpid(child, &status, 0); + if (WIFEXITED(status)) { + pr_debug("tracee exited prematurely 1\n"); + return TEST_FAIL; + } + + /* + * The parent does following steps: + * - creates a new breakpoint (id 0) for bp_1 function + * - tries to change that breakpoint to (-1) address + * - waits for the breakpoint to hit and checks + * it has proper rip of bp_1 function + * - detaches the child + */ + if (ptrace(PTRACE_POKEUSER, child, + offsetof(struct user, u_debugreg[0]), bp_1)) { + pr_debug("failed to set breakpoint: %s\n", + strerror(errno)); + goto out; + } + + if (ptrace(PTRACE_POKEUSER, child, + offsetof(struct user, u_debugreg[7]), dr7)) { + pr_debug("failed to set dr7: %s\n", strerror(errno)); + goto out; + } + + if (!ptrace(PTRACE_POKEUSER, child, + offsetof(struct user, u_debugreg[0]), (unsigned long) (-1))) { + pr_debug("failed, breakpoint set to bogus address\n"); + goto out; + } + + if (ptrace(PTRACE_CONT, child, NULL, NULL)) { + pr_debug("failed to PTRACE_CONT: %s\n", strerror(errno)); + goto out; + } + + waitpid(child, &status, 0); + if (WIFEXITED(status)) { + pr_debug("tracee exited prematurely 2\n"); + return TEST_FAIL; + } + + rip = ptrace(PTRACE_PEEKUSER, child, + offsetof(struct user_regs_struct, rip), NULL); + if (rip == (unsigned long) -1) { + pr_debug("failed to PTRACE_PEEKUSER: %s\n", + strerror(errno)); + goto out; + } + + pr_debug("rip %lx, bp_1 %p\n", rip, bp_1); + +out: + if (ptrace(PTRACE_DETACH, child, NULL, NULL)) { + pr_debug("failed to PTRACE_DETACH: %s", strerror(errno)); + return TEST_FAIL; + } + + return rip == (unsigned long) bp_1 ? TEST_OK : TEST_FAIL; +} + +int test__bp_modify(struct test *test __maybe_unused, + int subtest __maybe_unused) +{ + TEST_ASSERT_VAL("modify test 1 failed\n", !bp_modify1()); + TEST_ASSERT_VAL("modify test 2 failed\n", !bp_modify2()); + + return 0; +} diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c index 20061cf42288..28cd6a17491b 100644 --- a/tools/perf/util/annotate.c +++ b/tools/perf/util/annotate.c @@ -246,8 +246,14 @@ find_target: indirect_call: tok = strchr(endptr, '*'); - if (tok != NULL) - ops->target.addr = strtoull(tok + 1, NULL, 16); + if (tok != NULL) { + endptr++; + + /* Indirect call can use a non-rip register and offset: callq *0x8(%rbx). + * Do not parse such instruction. */ + if (strstr(endptr, "(%r") == NULL) + ops->target.addr = strtoull(endptr, NULL, 16); + } goto find_target; } @@ -276,7 +282,19 @@ bool ins__is_call(const struct ins *ins) return ins->ops == &call_ops || ins->ops == &s390_call_ops; } -static int jump__parse(struct arch *arch __maybe_unused, struct ins_operands *ops, struct map_symbol *ms) +/* + * Prevents from matching commas in the comment section, e.g.: + * ffff200008446e70: b.cs ffff2000084470f4 <generic_exec_single+0x314> // b.hs, b.nlast + */ +static inline const char *validate_comma(const char *c, struct ins_operands *ops) +{ + if (ops->raw_comment && c > ops->raw_comment) + return NULL; + + return c; +} + +static int jump__parse(struct arch *arch, struct ins_operands *ops, struct map_symbol *ms) { struct map *map = ms->map; struct symbol *sym = ms->sym; @@ -285,6 +303,10 @@ static int jump__parse(struct arch *arch __maybe_unused, struct ins_operands *op }; const char *c = strchr(ops->raw, ','); u64 start, end; + + ops->raw_comment = strchr(ops->raw, arch->objdump.comment_char); + c = validate_comma(c, ops); + /* * Examples of lines to parse for the _cpp_lex_token@@Base * function: @@ -304,6 +326,7 @@ static int jump__parse(struct arch *arch __maybe_unused, struct ins_operands *op ops->target.addr = strtoull(c, NULL, 16); if (!ops->target.addr) { c = strchr(c, ','); + c = validate_comma(c, ops); if (c++ != NULL) ops->target.addr = strtoull(c, NULL, 16); } @@ -361,9 +384,12 @@ static int jump__scnprintf(struct ins *ins, char *bf, size_t size, return scnprintf(bf, size, "%-6s %s", ins->name, ops->target.sym->name); c = strchr(ops->raw, ','); + c = validate_comma(c, ops); + if (c != NULL) { const char *c2 = strchr(c + 1, ','); + c2 = validate_comma(c2, ops); /* check for 3-op insn */ if (c2 != NULL) c = c2; diff --git a/tools/perf/util/annotate.h b/tools/perf/util/annotate.h index 005a5fe8a8c6..5399ba2321bb 100644 --- a/tools/perf/util/annotate.h +++ b/tools/perf/util/annotate.h @@ -22,6 +22,7 @@ struct ins { struct ins_operands { char *raw; + char *raw_comment; struct { char *raw; char *name; diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c index c980bbff6353..1a61628a1c12 100644 --- a/tools/perf/util/evsel.c +++ b/tools/perf/util/evsel.c @@ -251,8 +251,9 @@ struct perf_evsel *perf_evsel__new_idx(struct perf_event_attr *attr, int idx) { struct perf_evsel *evsel = zalloc(perf_evsel__object.size); - if (evsel != NULL) - perf_evsel__init(evsel, attr, idx); + if (!evsel) + return NULL; + perf_evsel__init(evsel, attr, idx); if (perf_evsel__is_bpf_output(evsel)) { evsel->attr.sample_type |= (PERF_SAMPLE_RAW | PERF_SAMPLE_TIME | diff --git a/tools/perf/util/map.c b/tools/perf/util/map.c index 36d0763311ef..6a6929f208b4 100644 --- a/tools/perf/util/map.c +++ b/tools/perf/util/map.c @@ -576,6 +576,13 @@ struct symbol *map_groups__find_symbol(struct map_groups *mg, return NULL; } +static bool map__contains_symbol(struct map *map, struct symbol *sym) +{ + u64 ip = map->unmap_ip(map, sym->start); + + return ip >= map->start && ip < map->end; +} + struct symbol *maps__find_symbol_by_name(struct maps *maps, const char *name, struct map **mapp) { @@ -591,6 +598,10 @@ struct symbol *maps__find_symbol_by_name(struct maps *maps, const char *name, if (sym == NULL) continue; + if (!map__contains_symbol(pos, sym)) { + sym = NULL; + continue; + } if (mapp != NULL) *mapp = pos; goto out; diff --git a/tools/perf/util/trace-event-info.c b/tools/perf/util/trace-event-info.c index c85d0d1a65ed..7b0ca7cbb7de 100644 --- a/tools/perf/util/trace-event-info.c +++ b/tools/perf/util/trace-event-info.c @@ -377,7 +377,7 @@ out: static int record_saved_cmdline(void) { - unsigned int size; + unsigned long long size; char *path; struct stat st; int ret, err = 0; diff --git a/tools/perf/util/trace-event-parse.c b/tools/perf/util/trace-event-parse.c index 920b1d58a068..e76214f8d596 100644 --- a/tools/perf/util/trace-event-parse.c +++ b/tools/perf/util/trace-event-parse.c @@ -164,16 +164,15 @@ void parse_ftrace_printk(struct tep_handle *pevent, void parse_saved_cmdline(struct tep_handle *pevent, char *file, unsigned int size __maybe_unused) { - char *comm; + char comm[17]; /* Max comm length in the kernel is 16. */ char *line; char *next = NULL; int pid; line = strtok_r(file, "\n", &next); while (line) { - sscanf(line, "%d %ms", &pid, &comm); - tep_register_comm(pevent, comm, pid); - free(comm); + if (sscanf(line, "%d %16s", &pid, comm) == 2) + tep_register_comm(pevent, comm, pid); line = strtok_r(NULL, "\n", &next); } } diff --git a/tools/testing/selftests/android/Makefile b/tools/testing/selftests/android/Makefile index 72c25a3cb658..d9a725478375 100644 --- a/tools/testing/selftests/android/Makefile +++ b/tools/testing/selftests/android/Makefile @@ -6,7 +6,7 @@ TEST_PROGS := run.sh include ../lib.mk -all: +all: khdr @for DIR in $(SUBDIRS); do \ BUILD_TARGET=$(OUTPUT)/$$DIR; \ mkdir $$BUILD_TARGET -p; \ diff --git a/tools/testing/selftests/android/ion/config b/tools/testing/selftests/android/config index b4ad748a9dd9..b4ad748a9dd9 100644 --- a/tools/testing/selftests/android/ion/config +++ b/tools/testing/selftests/android/config diff --git a/tools/testing/selftests/android/ion/Makefile b/tools/testing/selftests/android/ion/Makefile index e03695287f76..88cfe88e466f 100644 --- a/tools/testing/selftests/android/ion/Makefile +++ b/tools/testing/selftests/android/ion/Makefile @@ -10,6 +10,8 @@ $(TEST_GEN_FILES): ipcsocket.c ionutils.c TEST_PROGS := ion_test.sh +KSFT_KHDR_INSTALL := 1 +top_srcdir = ../../../../.. include ../../lib.mk $(OUTPUT)/ionapp_export: ionapp_export.c ipcsocket.c ionutils.c diff --git a/tools/testing/selftests/bpf/test_maps.c b/tools/testing/selftests/bpf/test_maps.c index 6f54f84144a0..9b552c0fc47d 100644 --- a/tools/testing/selftests/bpf/test_maps.c +++ b/tools/testing/selftests/bpf/test_maps.c @@ -580,7 +580,11 @@ static void test_sockmap(int tasks, void *data) /* Test update without programs */ for (i = 0; i < 6; i++) { err = bpf_map_update_elem(fd, &i, &sfd[i], BPF_ANY); - if (err) { + if (i < 2 && !err) { + printf("Allowed update sockmap '%i:%i' not in ESTABLISHED\n", + i, sfd[i]); + goto out_sockmap; + } else if (i >= 2 && err) { printf("Failed noprog update sockmap '%i:%i'\n", i, sfd[i]); goto out_sockmap; @@ -741,7 +745,7 @@ static void test_sockmap(int tasks, void *data) } /* Test map update elem afterwards fd lives in fd and map_fd */ - for (i = 0; i < 6; i++) { + for (i = 2; i < 6; i++) { err = bpf_map_update_elem(map_fd_rx, &i, &sfd[i], BPF_ANY); if (err) { printf("Failed map_fd_rx update sockmap %i '%i:%i'\n", @@ -845,7 +849,7 @@ static void test_sockmap(int tasks, void *data) } /* Delete the elems without programs */ - for (i = 0; i < 6; i++) { + for (i = 2; i < 6; i++) { err = bpf_map_delete_elem(fd, &i); if (err) { printf("Failed delete sockmap %i '%i:%i'\n", diff --git a/tools/testing/selftests/cgroup/.gitignore b/tools/testing/selftests/cgroup/.gitignore index 95eb3a53c381..adacda50a4b2 100644 --- a/tools/testing/selftests/cgroup/.gitignore +++ b/tools/testing/selftests/cgroup/.gitignore @@ -1 +1,2 @@ test_memcontrol +test_core diff --git a/tools/testing/selftests/cgroup/cgroup_util.c b/tools/testing/selftests/cgroup/cgroup_util.c index 1c5d2b2a583b..14c9fe284806 100644 --- a/tools/testing/selftests/cgroup/cgroup_util.c +++ b/tools/testing/selftests/cgroup/cgroup_util.c @@ -89,17 +89,28 @@ int cg_read(const char *cgroup, const char *control, char *buf, size_t len) int cg_read_strcmp(const char *cgroup, const char *control, const char *expected) { - size_t size = strlen(expected) + 1; + size_t size; char *buf; + int ret; + + /* Handle the case of comparing against empty string */ + if (!expected) + size = 32; + else + size = strlen(expected) + 1; buf = malloc(size); if (!buf) return -1; - if (cg_read(cgroup, control, buf, size)) + if (cg_read(cgroup, control, buf, size)) { + free(buf); return -1; + } - return strcmp(expected, buf); + ret = strcmp(expected, buf); + free(buf); + return ret; } int cg_read_strstr(const char *cgroup, const char *control, const char *needle) @@ -337,3 +348,24 @@ int is_swap_enabled(void) return cnt > 1; } + +int set_oom_adj_score(int pid, int score) +{ + char path[PATH_MAX]; + int fd, len; + + sprintf(path, "/proc/%d/oom_score_adj", pid); + + fd = open(path, O_WRONLY | O_APPEND); + if (fd < 0) + return fd; + + len = dprintf(fd, "%d", score); + if (len < 0) { + close(fd); + return len; + } + + close(fd); + return 0; +} diff --git a/tools/testing/selftests/cgroup/cgroup_util.h b/tools/testing/selftests/cgroup/cgroup_util.h index 1ff6f9f1abdc..9ac8b7958f83 100644 --- a/tools/testing/selftests/cgroup/cgroup_util.h +++ b/tools/testing/selftests/cgroup/cgroup_util.h @@ -40,3 +40,4 @@ extern int get_temp_fd(void); extern int alloc_pagecache(int fd, size_t size); extern int alloc_anon(const char *cgroup, void *arg); extern int is_swap_enabled(void); +extern int set_oom_adj_score(int pid, int score); diff --git a/tools/testing/selftests/cgroup/test_memcontrol.c b/tools/testing/selftests/cgroup/test_memcontrol.c index cf0bddc9d271..28d321ba311b 100644 --- a/tools/testing/selftests/cgroup/test_memcontrol.c +++ b/tools/testing/selftests/cgroup/test_memcontrol.c @@ -2,6 +2,7 @@ #define _GNU_SOURCE #include <linux/limits.h> +#include <linux/oom.h> #include <fcntl.h> #include <stdio.h> #include <stdlib.h> @@ -202,6 +203,36 @@ static int alloc_pagecache_50M_noexit(const char *cgroup, void *arg) return 0; } +static int alloc_anon_noexit(const char *cgroup, void *arg) +{ + int ppid = getppid(); + + if (alloc_anon(cgroup, arg)) + return -1; + + while (getppid() == ppid) + sleep(1); + + return 0; +} + +/* + * Wait until processes are killed asynchronously by the OOM killer + * If we exceed a timeout, fail. + */ +static int cg_test_proc_killed(const char *cgroup) +{ + int limit; + + for (limit = 10; limit > 0; limit--) { + if (cg_read_strcmp(cgroup, "cgroup.procs", "") == 0) + return 0; + + usleep(100000); + } + return -1; +} + /* * First, this test creates the following hierarchy: * A memory.min = 50M, memory.max = 200M @@ -964,6 +995,177 @@ cleanup: return ret; } +/* + * This test disables swapping and tries to allocate anonymous memory + * up to OOM with memory.group.oom set. Then it checks that all + * processes in the leaf (but not the parent) were killed. + */ +static int test_memcg_oom_group_leaf_events(const char *root) +{ + int ret = KSFT_FAIL; + char *parent, *child; + + parent = cg_name(root, "memcg_test_0"); + child = cg_name(root, "memcg_test_0/memcg_test_1"); + + if (!parent || !child) + goto cleanup; + + if (cg_create(parent)) + goto cleanup; + + if (cg_create(child)) + goto cleanup; + + if (cg_write(parent, "cgroup.subtree_control", "+memory")) + goto cleanup; + + if (cg_write(child, "memory.max", "50M")) + goto cleanup; + + if (cg_write(child, "memory.swap.max", "0")) + goto cleanup; + + if (cg_write(child, "memory.oom.group", "1")) + goto cleanup; + + cg_run_nowait(parent, alloc_anon_noexit, (void *) MB(60)); + cg_run_nowait(child, alloc_anon_noexit, (void *) MB(1)); + cg_run_nowait(child, alloc_anon_noexit, (void *) MB(1)); + if (!cg_run(child, alloc_anon, (void *)MB(100))) + goto cleanup; + + if (cg_test_proc_killed(child)) + goto cleanup; + + if (cg_read_key_long(child, "memory.events", "oom_kill ") <= 0) + goto cleanup; + + if (cg_read_key_long(parent, "memory.events", "oom_kill ") != 0) + goto cleanup; + + ret = KSFT_PASS; + +cleanup: + if (child) + cg_destroy(child); + if (parent) + cg_destroy(parent); + free(child); + free(parent); + + return ret; +} + +/* + * This test disables swapping and tries to allocate anonymous memory + * up to OOM with memory.group.oom set. Then it checks that all + * processes in the parent and leaf were killed. + */ +static int test_memcg_oom_group_parent_events(const char *root) +{ + int ret = KSFT_FAIL; + char *parent, *child; + + parent = cg_name(root, "memcg_test_0"); + child = cg_name(root, "memcg_test_0/memcg_test_1"); + + if (!parent || !child) + goto cleanup; + + if (cg_create(parent)) + goto cleanup; + + if (cg_create(child)) + goto cleanup; + + if (cg_write(parent, "memory.max", "80M")) + goto cleanup; + + if (cg_write(parent, "memory.swap.max", "0")) + goto cleanup; + + if (cg_write(parent, "memory.oom.group", "1")) + goto cleanup; + + cg_run_nowait(parent, alloc_anon_noexit, (void *) MB(60)); + cg_run_nowait(child, alloc_anon_noexit, (void *) MB(1)); + cg_run_nowait(child, alloc_anon_noexit, (void *) MB(1)); + + if (!cg_run(child, alloc_anon, (void *)MB(100))) + goto cleanup; + + if (cg_test_proc_killed(child)) + goto cleanup; + if (cg_test_proc_killed(parent)) + goto cleanup; + + ret = KSFT_PASS; + +cleanup: + if (child) + cg_destroy(child); + if (parent) + cg_destroy(parent); + free(child); + free(parent); + + return ret; +} + +/* + * This test disables swapping and tries to allocate anonymous memory + * up to OOM with memory.group.oom set. Then it checks that all + * processes were killed except those set with OOM_SCORE_ADJ_MIN + */ +static int test_memcg_oom_group_score_events(const char *root) +{ + int ret = KSFT_FAIL; + char *memcg; + int safe_pid; + + memcg = cg_name(root, "memcg_test_0"); + + if (!memcg) + goto cleanup; + + if (cg_create(memcg)) + goto cleanup; + + if (cg_write(memcg, "memory.max", "50M")) + goto cleanup; + + if (cg_write(memcg, "memory.swap.max", "0")) + goto cleanup; + + if (cg_write(memcg, "memory.oom.group", "1")) + goto cleanup; + + safe_pid = cg_run_nowait(memcg, alloc_anon_noexit, (void *) MB(1)); + if (set_oom_adj_score(safe_pid, OOM_SCORE_ADJ_MIN)) + goto cleanup; + + cg_run_nowait(memcg, alloc_anon_noexit, (void *) MB(1)); + if (!cg_run(memcg, alloc_anon, (void *)MB(100))) + goto cleanup; + + if (cg_read_key_long(memcg, "memory.events", "oom_kill ") != 3) + goto cleanup; + + if (kill(safe_pid, SIGKILL)) + goto cleanup; + + ret = KSFT_PASS; + +cleanup: + if (memcg) + cg_destroy(memcg); + free(memcg); + + return ret; +} + + #define T(x) { x, #x } struct memcg_test { int (*fn)(const char *root); @@ -978,6 +1180,9 @@ struct memcg_test { T(test_memcg_oom_events), T(test_memcg_swap_max), T(test_memcg_sock), + T(test_memcg_oom_group_leaf_events), + T(test_memcg_oom_group_parent_events), + T(test_memcg_oom_group_score_events), }; #undef T diff --git a/tools/testing/selftests/drivers/net/mlxsw/qos_mc_aware.sh b/tools/testing/selftests/drivers/net/mlxsw/qos_mc_aware.sh new file mode 100644 index 000000000000..0150bb2741eb --- /dev/null +++ b/tools/testing/selftests/drivers/net/mlxsw/qos_mc_aware.sh @@ -0,0 +1,347 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 +# +# A test for switch behavior under MC overload. An issue in Spectrum chips +# causes throughput of UC traffic to drop severely when a switch is under heavy +# MC load. This issue can be overcome by putting the switch to MC-aware mode. +# This test verifies that UC performance stays intact even as the switch is +# under MC flood, and therefore that the MC-aware mode is enabled and correctly +# configured. +# +# Because mlxsw throttles CPU port, the traffic can't actually reach userspace +# at full speed. That makes it impossible to use iperf3 to simply measure the +# throughput, because many packets (that reach $h3) don't get to the kernel at +# all even in UDP mode (the situation is even worse in TCP mode, where one can't +# hope to see more than a couple Mbps). +# +# So instead we send traffic with mausezahn and use RX ethtool counters at $h3. +# Multicast traffic is untagged, unicast traffic is tagged with PCP 1. Therefore +# each gets a different priority and we can use per-prio ethtool counters to +# measure the throughput. In order to avoid prioritizing unicast traffic, prio +# qdisc is installed on $swp3 and maps all priorities to the same band #7 (and +# thus TC 0). +# +# Mausezahn can't actually saturate the links unless it's using large frames. +# Thus we set MTU to 10K on all involved interfaces. Then both unicast and +# multicast traffic uses 8K frames. +# +# +-----------------------+ +----------------------------------+ +# | H1 | | H2 | +# | | | unicast --> + $h2.111 | +# | | | traffic | 192.0.2.129/28 | +# | multicast | | | e-qos-map 0:1 | +# | traffic | | | | +# | $h1 + <----- | | + $h2 | +# +-----|-----------------+ +--------------|-------------------+ +# | | +# +-----|-------------------------------------------------|-------------------+ +# | + $swp1 + $swp2 | +# | | >1Gbps | >1Gbps | +# | +---|----------------+ +----------|----------------+ | +# | | + $swp1.1 | | + $swp2.111 | | +# | | BR1 | SW | BR111 | | +# | | + $swp3.1 | | + $swp3.111 | | +# | +---|----------------+ +----------|----------------+ | +# | \_________________________________________________/ | +# | | | +# | + $swp3 | +# | | 1Gbps bottleneck | +# | | prio qdisc: {0..7} -> 7 | +# +------------------------------------|--------------------------------------+ +# | +# +--|-----------------+ +# | + $h3 H3 | +# | | | +# | + $h3.111 | +# | 192.0.2.130/28 | +# +--------------------+ + +ALL_TESTS=" + ping_ipv4 + test_mc_aware +" + +lib_dir=$(dirname $0)/../../../net/forwarding + +NUM_NETIFS=6 +source $lib_dir/lib.sh + +h1_create() +{ + simple_if_init $h1 + mtu_set $h1 10000 +} + +h1_destroy() +{ + mtu_restore $h1 + simple_if_fini $h1 +} + +h2_create() +{ + simple_if_init $h2 + mtu_set $h2 10000 + + vlan_create $h2 111 v$h2 192.0.2.129/28 + ip link set dev $h2.111 type vlan egress-qos-map 0:1 +} + +h2_destroy() +{ + vlan_destroy $h2 111 + + mtu_restore $h2 + simple_if_fini $h2 +} + +h3_create() +{ + simple_if_init $h3 + mtu_set $h3 10000 + + vlan_create $h3 111 v$h3 192.0.2.130/28 +} + +h3_destroy() +{ + vlan_destroy $h3 111 + + mtu_restore $h3 + simple_if_fini $h3 +} + +switch_create() +{ + ip link set dev $swp1 up + mtu_set $swp1 10000 + + ip link set dev $swp2 up + mtu_set $swp2 10000 + + ip link set dev $swp3 up + mtu_set $swp3 10000 + + vlan_create $swp2 111 + vlan_create $swp3 111 + + ethtool -s $swp3 speed 1000 autoneg off + tc qdisc replace dev $swp3 root handle 3: \ + prio bands 8 priomap 7 7 7 7 7 7 7 7 + + ip link add name br1 type bridge vlan_filtering 0 + ip link set dev br1 up + ip link set dev $swp1 master br1 + ip link set dev $swp3 master br1 + + ip link add name br111 type bridge vlan_filtering 0 + ip link set dev br111 up + ip link set dev $swp2.111 master br111 + ip link set dev $swp3.111 master br111 +} + +switch_destroy() +{ + ip link del dev br111 + ip link del dev br1 + + tc qdisc del dev $swp3 root handle 3: + ethtool -s $swp3 autoneg on + + vlan_destroy $swp3 111 + vlan_destroy $swp2 111 + + mtu_restore $swp3 + ip link set dev $swp3 down + + mtu_restore $swp2 + ip link set dev $swp2 down + + mtu_restore $swp1 + ip link set dev $swp1 down +} + +setup_prepare() +{ + h1=${NETIFS[p1]} + swp1=${NETIFS[p2]} + + swp2=${NETIFS[p3]} + h2=${NETIFS[p4]} + + swp3=${NETIFS[p5]} + h3=${NETIFS[p6]} + + h3mac=$(mac_get $h3) + + vrf_prepare + + h1_create + h2_create + h3_create + switch_create +} + +cleanup() +{ + pre_cleanup + + switch_destroy + h3_destroy + h2_destroy + h1_destroy + + vrf_cleanup +} + +ping_ipv4() +{ + ping_test $h2 192.0.2.130 +} + +humanize() +{ + local speed=$1; shift + + for unit in bps Kbps Mbps Gbps; do + if (($(echo "$speed < 1024" | bc))); then + break + fi + + speed=$(echo "scale=1; $speed / 1024" | bc) + done + + echo "$speed${unit}" +} + +rate() +{ + local t0=$1; shift + local t1=$1; shift + local interval=$1; shift + + echo $((8 * (t1 - t0) / interval)) +} + +check_rate() +{ + local rate=$1; shift + local min=$1; shift + local what=$1; shift + + if ((rate > min)); then + return 0 + fi + + echo "$what $(humanize $ir) < $(humanize $min_ingress)" > /dev/stderr + return 1 +} + +measure_uc_rate() +{ + local what=$1; shift + + local interval=10 + local i + local ret=0 + + # Dips in performance might cause momentary ingress rate to drop below + # 1Gbps. That wouldn't saturate egress and MC would thus get through, + # seemingly winning bandwidth on account of UC. Demand at least 2Gbps + # average ingress rate to somewhat mitigate this. + local min_ingress=2147483648 + + mausezahn $h2.111 -p 8000 -A 192.0.2.129 -B 192.0.2.130 -c 0 \ + -a own -b $h3mac -t udp -q & + sleep 1 + + for i in {5..0}; do + local t0=$(ethtool_stats_get $h3 rx_octets_prio_1) + local u0=$(ethtool_stats_get $swp2 rx_octets_prio_1) + sleep $interval + local t1=$(ethtool_stats_get $h3 rx_octets_prio_1) + local u1=$(ethtool_stats_get $swp2 rx_octets_prio_1) + + local ir=$(rate $u0 $u1 $interval) + local er=$(rate $t0 $t1 $interval) + + if check_rate $ir $min_ingress "$what ingress rate"; then + break + fi + + # Fail the test if we can't get the throughput. + if ((i == 0)); then + ret=1 + fi + done + + # Suppress noise from killing mausezahn. + { kill %% && wait; } 2>/dev/null + + echo $ir $er + exit $ret +} + +test_mc_aware() +{ + RET=0 + + local -a uc_rate + uc_rate=($(measure_uc_rate "UC-only")) + check_err $? "Could not get high enough UC-only ingress rate" + local ucth1=${uc_rate[1]} + + mausezahn $h1 -p 8000 -c 0 -a own -b bc -t udp -q & + + local d0=$(date +%s) + local t0=$(ethtool_stats_get $h3 rx_octets_prio_0) + local u0=$(ethtool_stats_get $swp1 rx_octets_prio_0) + + local -a uc_rate_2 + uc_rate_2=($(measure_uc_rate "UC+MC")) + check_err $? "Could not get high enough UC+MC ingress rate" + local ucth2=${uc_rate_2[1]} + + local d1=$(date +%s) + local t1=$(ethtool_stats_get $h3 rx_octets_prio_0) + local u1=$(ethtool_stats_get $swp1 rx_octets_prio_0) + + local deg=$(bc <<< " + scale=2 + ret = 100 * ($ucth1 - $ucth2) / $ucth1 + if (ret > 0) { ret } else { 0 } + ") + check_err $(bc <<< "$deg > 10") + + local interval=$((d1 - d0)) + local mc_ir=$(rate $u0 $u1 $interval) + local mc_er=$(rate $t0 $t1 $interval) + + # Suppress noise from killing mausezahn. + { kill %% && wait; } 2>/dev/null + + log_test "UC performace under MC overload" + + echo "UC-only throughput $(humanize $ucth1)" + echo "UC+MC throughput $(humanize $ucth2)" + echo "Degradation $deg %" + echo + echo "Full report:" + echo " UC only:" + echo " ingress UC throughput $(humanize ${uc_rate[0]})" + echo " egress UC throughput $(humanize ${uc_rate[1]})" + echo " UC+MC:" + echo " ingress UC throughput $(humanize ${uc_rate_2[0]})" + echo " egress UC throughput $(humanize ${uc_rate_2[1]})" + echo " ingress MC throughput $(humanize $mc_ir)" + echo " egress MC throughput $(humanize $mc_er)" +} + +trap cleanup EXIT + +setup_prepare +setup_wait + +tests_run + +exit $EXIT_STATUS diff --git a/tools/testing/selftests/efivarfs/config b/tools/testing/selftests/efivarfs/config new file mode 100644 index 000000000000..4e151f1005b2 --- /dev/null +++ b/tools/testing/selftests/efivarfs/config @@ -0,0 +1 @@ +CONFIG_EFIVAR_FS=y diff --git a/tools/testing/selftests/futex/functional/Makefile b/tools/testing/selftests/futex/functional/Makefile index ff8feca49746..ad1eeb14fda7 100644 --- a/tools/testing/selftests/futex/functional/Makefile +++ b/tools/testing/selftests/futex/functional/Makefile @@ -18,6 +18,7 @@ TEST_GEN_FILES := \ TEST_PROGS := run.sh +top_srcdir = ../../../../.. include ../../lib.mk $(TEST_GEN_FILES): $(HEADERS) diff --git a/tools/testing/selftests/gpio/Makefile b/tools/testing/selftests/gpio/Makefile index 1bbb47565c55..4665cdbf1a8d 100644 --- a/tools/testing/selftests/gpio/Makefile +++ b/tools/testing/selftests/gpio/Makefile @@ -21,11 +21,8 @@ endef CFLAGS += -O2 -g -std=gnu99 -Wall -I../../../../usr/include/ LDLIBS += -lmount -I/usr/include/libmount -$(BINARIES): ../../../gpio/gpio-utils.o ../../../../usr/include/linux/gpio.h +$(BINARIES):| khdr +$(BINARIES): ../../../gpio/gpio-utils.o ../../../gpio/gpio-utils.o: make ARCH=$(ARCH) CROSS_COMPILE=$(CROSS_COMPILE) -C ../../../gpio - -../../../../usr/include/linux/gpio.h: - make -C ../../../.. headers_install INSTALL_HDR_PATH=$(shell pwd)/../../../../usr/ - diff --git a/tools/testing/selftests/kselftest.h b/tools/testing/selftests/kselftest.h index 15e6b75fc3a5..a3edb2c8e43d 100644 --- a/tools/testing/selftests/kselftest.h +++ b/tools/testing/selftests/kselftest.h @@ -19,7 +19,6 @@ #define KSFT_FAIL 1 #define KSFT_XFAIL 2 #define KSFT_XPASS 3 -/* Treat skip as pass */ #define KSFT_SKIP 4 /* counters */ diff --git a/tools/testing/selftests/kvm/.gitignore b/tools/testing/selftests/kvm/.gitignore index 4202139d81d9..5c34752e1cff 100644 --- a/tools/testing/selftests/kvm/.gitignore +++ b/tools/testing/selftests/kvm/.gitignore @@ -1,4 +1,5 @@ cr4_cpuid_sync_test +platform_info_test set_sregs_test sync_regs_test vmx_tsc_adjust_test diff --git a/tools/testing/selftests/kvm/Makefile b/tools/testing/selftests/kvm/Makefile index 03b0f551bedf..ec32dad3c3f0 100644 --- a/tools/testing/selftests/kvm/Makefile +++ b/tools/testing/selftests/kvm/Makefile @@ -6,7 +6,8 @@ UNAME_M := $(shell uname -m) LIBKVM = lib/assert.c lib/elf.c lib/io.c lib/kvm_util.c lib/sparsebit.c LIBKVM_x86_64 = lib/x86.c lib/vmx.c -TEST_GEN_PROGS_x86_64 = set_sregs_test +TEST_GEN_PROGS_x86_64 = platform_info_test +TEST_GEN_PROGS_x86_64 += set_sregs_test TEST_GEN_PROGS_x86_64 += sync_regs_test TEST_GEN_PROGS_x86_64 += vmx_tsc_adjust_test TEST_GEN_PROGS_x86_64 += cr4_cpuid_sync_test @@ -20,7 +21,7 @@ INSTALL_HDR_PATH = $(top_srcdir)/usr LINUX_HDR_PATH = $(INSTALL_HDR_PATH)/include/ LINUX_TOOL_INCLUDE = $(top_srcdir)tools/include CFLAGS += -O2 -g -std=gnu99 -I$(LINUX_TOOL_INCLUDE) -I$(LINUX_HDR_PATH) -Iinclude -I$(<D) -I.. -LDFLAGS += -lpthread +LDFLAGS += -pthread # After inclusion, $(OUTPUT) is defined and # $(TEST_GEN_PROGS) starts with $(OUTPUT)/ @@ -37,9 +38,6 @@ $(LIBKVM_OBJ): $(OUTPUT)/%.o: %.c $(OUTPUT)/libkvm.a: $(LIBKVM_OBJ) $(AR) crs $@ $^ -$(LINUX_HDR_PATH): - make -C $(top_srcdir) headers_install - -all: $(STATIC_LIBS) $(LINUX_HDR_PATH) +all: $(STATIC_LIBS) $(TEST_GEN_PROGS): $(STATIC_LIBS) -$(TEST_GEN_PROGS) $(LIBKVM_OBJ): | $(LINUX_HDR_PATH) +$(STATIC_LIBS):| khdr diff --git a/tools/testing/selftests/kvm/include/kvm_util.h b/tools/testing/selftests/kvm/include/kvm_util.h index bb5a25fb82c6..3acf9a91704c 100644 --- a/tools/testing/selftests/kvm/include/kvm_util.h +++ b/tools/testing/selftests/kvm/include/kvm_util.h @@ -50,6 +50,7 @@ enum vm_mem_backing_src_type { }; int kvm_check_cap(long cap); +int vm_enable_cap(struct kvm_vm *vm, struct kvm_enable_cap *cap); struct kvm_vm *vm_create(enum vm_guest_mode mode, uint64_t phy_pages, int perm); void kvm_vm_free(struct kvm_vm *vmp); @@ -108,6 +109,9 @@ void vcpu_events_get(struct kvm_vm *vm, uint32_t vcpuid, struct kvm_vcpu_events *events); void vcpu_events_set(struct kvm_vm *vm, uint32_t vcpuid, struct kvm_vcpu_events *events); +uint64_t vcpu_get_msr(struct kvm_vm *vm, uint32_t vcpuid, uint64_t msr_index); +void vcpu_set_msr(struct kvm_vm *vm, uint32_t vcpuid, uint64_t msr_index, + uint64_t msr_value); const char *exit_reason_str(unsigned int exit_reason); diff --git a/tools/testing/selftests/kvm/lib/kvm_util.c b/tools/testing/selftests/kvm/lib/kvm_util.c index e9ba389c48db..6fd8c089cafc 100644 --- a/tools/testing/selftests/kvm/lib/kvm_util.c +++ b/tools/testing/selftests/kvm/lib/kvm_util.c @@ -63,6 +63,29 @@ int kvm_check_cap(long cap) return ret; } +/* VM Enable Capability + * + * Input Args: + * vm - Virtual Machine + * cap - Capability + * + * Output Args: None + * + * Return: On success, 0. On failure a TEST_ASSERT failure is produced. + * + * Enables a capability (KVM_CAP_*) on the VM. + */ +int vm_enable_cap(struct kvm_vm *vm, struct kvm_enable_cap *cap) +{ + int ret; + + ret = ioctl(vm->fd, KVM_ENABLE_CAP, cap); + TEST_ASSERT(ret == 0, "KVM_ENABLE_CAP IOCTL failed,\n" + " rc: %i errno: %i", ret, errno); + + return ret; +} + static void vm_open(struct kvm_vm *vm, int perm) { vm->kvm_fd = open(KVM_DEV_PATH, perm); @@ -1220,6 +1243,72 @@ void vcpu_events_set(struct kvm_vm *vm, uint32_t vcpuid, ret, errno); } +/* VCPU Get MSR + * + * Input Args: + * vm - Virtual Machine + * vcpuid - VCPU ID + * msr_index - Index of MSR + * + * Output Args: None + * + * Return: On success, value of the MSR. On failure a TEST_ASSERT is produced. + * + * Get value of MSR for VCPU. + */ +uint64_t vcpu_get_msr(struct kvm_vm *vm, uint32_t vcpuid, uint64_t msr_index) +{ + struct vcpu *vcpu = vcpu_find(vm, vcpuid); + struct { + struct kvm_msrs header; + struct kvm_msr_entry entry; + } buffer = {}; + int r; + + TEST_ASSERT(vcpu != NULL, "vcpu not found, vcpuid: %u", vcpuid); + buffer.header.nmsrs = 1; + buffer.entry.index = msr_index; + r = ioctl(vcpu->fd, KVM_GET_MSRS, &buffer.header); + TEST_ASSERT(r == 1, "KVM_GET_MSRS IOCTL failed,\n" + " rc: %i errno: %i", r, errno); + + return buffer.entry.data; +} + +/* VCPU Set MSR + * + * Input Args: + * vm - Virtual Machine + * vcpuid - VCPU ID + * msr_index - Index of MSR + * msr_value - New value of MSR + * + * Output Args: None + * + * Return: On success, nothing. On failure a TEST_ASSERT is produced. + * + * Set value of MSR for VCPU. + */ +void vcpu_set_msr(struct kvm_vm *vm, uint32_t vcpuid, uint64_t msr_index, + uint64_t msr_value) +{ + struct vcpu *vcpu = vcpu_find(vm, vcpuid); + struct { + struct kvm_msrs header; + struct kvm_msr_entry entry; + } buffer = {}; + int r; + + TEST_ASSERT(vcpu != NULL, "vcpu not found, vcpuid: %u", vcpuid); + memset(&buffer, 0, sizeof(buffer)); + buffer.header.nmsrs = 1; + buffer.entry.index = msr_index; + buffer.entry.data = msr_value; + r = ioctl(vcpu->fd, KVM_SET_MSRS, &buffer.header); + TEST_ASSERT(r == 1, "KVM_SET_MSRS IOCTL failed,\n" + " rc: %i errno: %i", r, errno); +} + /* VM VCPU Args Set * * Input Args: diff --git a/tools/testing/selftests/kvm/platform_info_test.c b/tools/testing/selftests/kvm/platform_info_test.c new file mode 100644 index 000000000000..3764e7121265 --- /dev/null +++ b/tools/testing/selftests/kvm/platform_info_test.c @@ -0,0 +1,110 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Test for x86 KVM_CAP_MSR_PLATFORM_INFO + * + * Copyright (C) 2018, Google LLC. + * + * This work is licensed under the terms of the GNU GPL, version 2. + * + * Verifies expected behavior of controlling guest access to + * MSR_PLATFORM_INFO. + */ + +#define _GNU_SOURCE /* for program_invocation_short_name */ +#include <fcntl.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <sys/ioctl.h> + +#include "test_util.h" +#include "kvm_util.h" +#include "x86.h" + +#define VCPU_ID 0 +#define MSR_PLATFORM_INFO_MAX_TURBO_RATIO 0xff00 + +static void guest_code(void) +{ + uint64_t msr_platform_info; + + for (;;) { + msr_platform_info = rdmsr(MSR_PLATFORM_INFO); + GUEST_SYNC(msr_platform_info); + asm volatile ("inc %r11"); + } +} + +static void set_msr_platform_info_enabled(struct kvm_vm *vm, bool enable) +{ + struct kvm_enable_cap cap = {}; + + cap.cap = KVM_CAP_MSR_PLATFORM_INFO; + cap.flags = 0; + cap.args[0] = (int)enable; + vm_enable_cap(vm, &cap); +} + +static void test_msr_platform_info_enabled(struct kvm_vm *vm) +{ + struct kvm_run *run = vcpu_state(vm, VCPU_ID); + struct guest_args args; + + set_msr_platform_info_enabled(vm, true); + vcpu_run(vm, VCPU_ID); + TEST_ASSERT(run->exit_reason == KVM_EXIT_IO, + "Exit_reason other than KVM_EXIT_IO: %u (%s),\n", + run->exit_reason, + exit_reason_str(run->exit_reason)); + guest_args_read(vm, VCPU_ID, &args); + TEST_ASSERT(args.port == GUEST_PORT_SYNC, + "Received IO from port other than PORT_HOST_SYNC: %u\n", + run->io.port); + TEST_ASSERT((args.arg1 & MSR_PLATFORM_INFO_MAX_TURBO_RATIO) == + MSR_PLATFORM_INFO_MAX_TURBO_RATIO, + "Expected MSR_PLATFORM_INFO to have max turbo ratio mask: %i.", + MSR_PLATFORM_INFO_MAX_TURBO_RATIO); +} + +static void test_msr_platform_info_disabled(struct kvm_vm *vm) +{ + struct kvm_run *run = vcpu_state(vm, VCPU_ID); + + set_msr_platform_info_enabled(vm, false); + vcpu_run(vm, VCPU_ID); + TEST_ASSERT(run->exit_reason == KVM_EXIT_SHUTDOWN, + "Exit_reason other than KVM_EXIT_SHUTDOWN: %u (%s)\n", + run->exit_reason, + exit_reason_str(run->exit_reason)); +} + +int main(int argc, char *argv[]) +{ + struct kvm_vm *vm; + struct kvm_run *state; + int rv; + uint64_t msr_platform_info; + + /* Tell stdout not to buffer its content */ + setbuf(stdout, NULL); + + rv = kvm_check_cap(KVM_CAP_MSR_PLATFORM_INFO); + if (!rv) { + fprintf(stderr, + "KVM_CAP_MSR_PLATFORM_INFO not supported, skip test\n"); + exit(KSFT_SKIP); + } + + vm = vm_create_default(VCPU_ID, 0, guest_code); + + msr_platform_info = vcpu_get_msr(vm, VCPU_ID, MSR_PLATFORM_INFO); + vcpu_set_msr(vm, VCPU_ID, MSR_PLATFORM_INFO, + msr_platform_info | MSR_PLATFORM_INFO_MAX_TURBO_RATIO); + test_msr_platform_info_disabled(vm); + test_msr_platform_info_enabled(vm); + vcpu_set_msr(vm, VCPU_ID, MSR_PLATFORM_INFO, msr_platform_info); + + kvm_vm_free(vm); + + return 0; +} diff --git a/tools/testing/selftests/lib.mk b/tools/testing/selftests/lib.mk index 17ab36605a8e..0a8e75886224 100644 --- a/tools/testing/selftests/lib.mk +++ b/tools/testing/selftests/lib.mk @@ -16,8 +16,20 @@ TEST_GEN_PROGS := $(patsubst %,$(OUTPUT)/%,$(TEST_GEN_PROGS)) TEST_GEN_PROGS_EXTENDED := $(patsubst %,$(OUTPUT)/%,$(TEST_GEN_PROGS_EXTENDED)) TEST_GEN_FILES := $(patsubst %,$(OUTPUT)/%,$(TEST_GEN_FILES)) +top_srcdir ?= ../../../.. +include $(top_srcdir)/scripts/subarch.include +ARCH ?= $(SUBARCH) + all: $(TEST_GEN_PROGS) $(TEST_GEN_PROGS_EXTENDED) $(TEST_GEN_FILES) +.PHONY: khdr +khdr: + make ARCH=$(ARCH) -C $(top_srcdir) headers_install + +ifdef KSFT_KHDR_INSTALL +$(TEST_GEN_PROGS) $(TEST_GEN_PROGS_EXTENDED) $(TEST_GEN_FILES):| khdr +endif + .ONESHELL: define RUN_TEST_PRINT_RESULT TEST_HDR_MSG="selftests: "`basename $$PWD`:" $$BASENAME_TEST"; \ diff --git a/tools/testing/selftests/memory-hotplug/config b/tools/testing/selftests/memory-hotplug/config index 2fde30191a47..a7e8cd5bb265 100644 --- a/tools/testing/selftests/memory-hotplug/config +++ b/tools/testing/selftests/memory-hotplug/config @@ -2,3 +2,4 @@ CONFIG_MEMORY_HOTPLUG=y CONFIG_MEMORY_HOTPLUG_SPARSE=y CONFIG_NOTIFIER_ERROR_INJECTION=y CONFIG_MEMORY_NOTIFIER_ERROR_INJECT=m +CONFIG_MEMORY_HOTREMOVE=y diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile index cccdb2295567..256d82d5fa87 100644 --- a/tools/testing/selftests/net/Makefile +++ b/tools/testing/selftests/net/Makefile @@ -15,6 +15,7 @@ TEST_GEN_FILES += udpgso udpgso_bench_tx udpgso_bench_rx ip_defrag TEST_GEN_PROGS = reuseport_bpf reuseport_bpf_cpu reuseport_bpf_numa TEST_GEN_PROGS += reuseport_dualstack reuseaddr_conflict tls +KSFT_KHDR_INSTALL := 1 include ../lib.mk $(OUTPUT)/reuseport_bpf_numa: LDFLAGS += -lnuma diff --git a/tools/testing/selftests/net/forwarding/lib.sh b/tools/testing/selftests/net/forwarding/lib.sh index ca53b539aa2d..0e73698b2048 100644 --- a/tools/testing/selftests/net/forwarding/lib.sh +++ b/tools/testing/selftests/net/forwarding/lib.sh @@ -494,6 +494,14 @@ tc_rule_stats_get() | jq '.[1].options.actions[].stats.packets' } +ethtool_stats_get() +{ + local dev=$1; shift + local stat=$1; shift + + ethtool -S $dev | grep "^ *$stat:" | head -n 1 | cut -d: -f2 +} + mac_get() { local if_name=$1 @@ -541,6 +549,23 @@ forwarding_restore() sysctl_restore net.ipv4.conf.all.forwarding } +declare -A MTU_ORIG +mtu_set() +{ + local dev=$1; shift + local mtu=$1; shift + + MTU_ORIG["$dev"]=$(ip -j link show dev $dev | jq -e '.[].mtu') + ip link set dev $dev mtu $mtu +} + +mtu_restore() +{ + local dev=$1; shift + + ip link set dev $dev mtu ${MTU_ORIG["$dev"]} +} + tc_offload_check() { local num_netifs=${1:-$NUM_NETIFS} diff --git a/tools/testing/selftests/net/ip_defrag.c b/tools/testing/selftests/net/ip_defrag.c index 55fdcdc78eef..2366dc6bce71 100644 --- a/tools/testing/selftests/net/ip_defrag.c +++ b/tools/testing/selftests/net/ip_defrag.c @@ -23,21 +23,28 @@ static bool cfg_overlap; static unsigned short cfg_port = 9000; const struct in_addr addr4 = { .s_addr = __constant_htonl(INADDR_LOOPBACK + 2) }; +const struct in6_addr addr6 = IN6ADDR_LOOPBACK_INIT; #define IP4_HLEN (sizeof(struct iphdr)) #define IP6_HLEN (sizeof(struct ip6_hdr)) #define UDP_HLEN (sizeof(struct udphdr)) -static int msg_len; +/* IPv6 fragment header lenth. */ +#define FRAG_HLEN 8 + +static int payload_len; static int max_frag_len; #define MSG_LEN_MAX 60000 /* Max UDP payload length. */ #define IP4_MF (1u << 13) /* IPv4 MF flag. */ +#define IP6_MF (1) /* IPv6 MF flag. */ + +#define CSUM_MANGLED_0 (0xffff) static uint8_t udp_payload[MSG_LEN_MAX]; static uint8_t ip_frame[IP_MAXPACKET]; -static uint16_t ip_id = 0xabcd; +static uint32_t ip_id = 0xabcd; static int msg_counter; static int frag_counter; static unsigned int seed; @@ -48,25 +55,25 @@ static void recv_validate_udp(int fd_udp) ssize_t ret; static uint8_t recv_buff[MSG_LEN_MAX]; - ret = recv(fd_udp, recv_buff, msg_len, 0); + ret = recv(fd_udp, recv_buff, payload_len, 0); msg_counter++; if (cfg_overlap) { if (ret != -1) - error(1, 0, "recv: expected timeout; got %d; seed = %u", - (int)ret, seed); + error(1, 0, "recv: expected timeout; got %d", + (int)ret); if (errno != ETIMEDOUT && errno != EAGAIN) - error(1, errno, "recv: expected timeout: %d; seed = %u", - errno, seed); + error(1, errno, "recv: expected timeout: %d", + errno); return; /* OK */ } if (ret == -1) - error(1, errno, "recv: msg_len = %d max_frag_len = %d", - msg_len, max_frag_len); - if (ret != msg_len) - error(1, 0, "recv: wrong size: %d vs %d", (int)ret, msg_len); - if (memcmp(udp_payload, recv_buff, msg_len)) + error(1, errno, "recv: payload_len = %d max_frag_len = %d", + payload_len, max_frag_len); + if (ret != payload_len) + error(1, 0, "recv: wrong size: %d vs %d", (int)ret, payload_len); + if (memcmp(udp_payload, recv_buff, payload_len)) error(1, 0, "recv: wrong data"); } @@ -92,31 +99,95 @@ static uint32_t raw_checksum(uint8_t *buf, int len, uint32_t sum) static uint16_t udp_checksum(struct ip *iphdr, struct udphdr *udphdr) { uint32_t sum = 0; + uint16_t res; sum = raw_checksum((uint8_t *)&iphdr->ip_src, 2 * sizeof(iphdr->ip_src), - IPPROTO_UDP + (uint32_t)(UDP_HLEN + msg_len)); - sum = raw_checksum((uint8_t *)udp_payload, msg_len, sum); + IPPROTO_UDP + (uint32_t)(UDP_HLEN + payload_len)); + sum = raw_checksum((uint8_t *)udphdr, UDP_HLEN, sum); + sum = raw_checksum((uint8_t *)udp_payload, payload_len, sum); + res = 0xffff & ~sum; + if (res) + return htons(res); + else + return CSUM_MANGLED_0; +} + +static uint16_t udp6_checksum(struct ip6_hdr *iphdr, struct udphdr *udphdr) +{ + uint32_t sum = 0; + uint16_t res; + + sum = raw_checksum((uint8_t *)&iphdr->ip6_src, 2 * sizeof(iphdr->ip6_src), + IPPROTO_UDP); + sum = raw_checksum((uint8_t *)&udphdr->len, sizeof(udphdr->len), sum); sum = raw_checksum((uint8_t *)udphdr, UDP_HLEN, sum); - return htons(0xffff & ~sum); + sum = raw_checksum((uint8_t *)udp_payload, payload_len, sum); + res = 0xffff & ~sum; + if (res) + return htons(res); + else + return CSUM_MANGLED_0; } static void send_fragment(int fd_raw, struct sockaddr *addr, socklen_t alen, - struct ip *iphdr, int offset) + int offset, bool ipv6) { int frag_len; int res; + int payload_offset = offset > 0 ? offset - UDP_HLEN : 0; + uint8_t *frag_start = ipv6 ? ip_frame + IP6_HLEN + FRAG_HLEN : + ip_frame + IP4_HLEN; + + if (offset == 0) { + struct udphdr udphdr; + udphdr.source = htons(cfg_port + 1); + udphdr.dest = htons(cfg_port); + udphdr.len = htons(UDP_HLEN + payload_len); + udphdr.check = 0; + if (ipv6) + udphdr.check = udp6_checksum((struct ip6_hdr *)ip_frame, &udphdr); + else + udphdr.check = udp_checksum((struct ip *)ip_frame, &udphdr); + memcpy(frag_start, &udphdr, UDP_HLEN); + } - if (msg_len - offset <= max_frag_len) { - /* This is the last fragment. */ - frag_len = IP4_HLEN + msg_len - offset; - iphdr->ip_off = htons((offset + UDP_HLEN) / 8); + if (ipv6) { + struct ip6_hdr *ip6hdr = (struct ip6_hdr *)ip_frame; + struct ip6_frag *fraghdr = (struct ip6_frag *)(ip_frame + IP6_HLEN); + if (payload_len - payload_offset <= max_frag_len && offset > 0) { + /* This is the last fragment. */ + frag_len = FRAG_HLEN + payload_len - payload_offset; + fraghdr->ip6f_offlg = htons(offset); + } else { + frag_len = FRAG_HLEN + max_frag_len; + fraghdr->ip6f_offlg = htons(offset | IP6_MF); + } + ip6hdr->ip6_plen = htons(frag_len); + if (offset == 0) + memcpy(frag_start + UDP_HLEN, udp_payload, + frag_len - FRAG_HLEN - UDP_HLEN); + else + memcpy(frag_start, udp_payload + payload_offset, + frag_len - FRAG_HLEN); + frag_len += IP6_HLEN; } else { - frag_len = IP4_HLEN + max_frag_len; - iphdr->ip_off = htons((offset + UDP_HLEN) / 8 | IP4_MF); + struct ip *iphdr = (struct ip *)ip_frame; + if (payload_len - payload_offset <= max_frag_len && offset > 0) { + /* This is the last fragment. */ + frag_len = IP4_HLEN + payload_len - payload_offset; + iphdr->ip_off = htons(offset / 8); + } else { + frag_len = IP4_HLEN + max_frag_len; + iphdr->ip_off = htons(offset / 8 | IP4_MF); + } + iphdr->ip_len = htons(frag_len); + if (offset == 0) + memcpy(frag_start + UDP_HLEN, udp_payload, + frag_len - IP4_HLEN - UDP_HLEN); + else + memcpy(frag_start, udp_payload + payload_offset, + frag_len - IP4_HLEN); } - iphdr->ip_len = htons(frag_len); - memcpy(ip_frame + IP4_HLEN, udp_payload + offset, - frag_len - IP4_HLEN); res = sendto(fd_raw, ip_frame, frag_len, 0, addr, alen); if (res < 0) @@ -127,9 +198,11 @@ static void send_fragment(int fd_raw, struct sockaddr *addr, socklen_t alen, frag_counter++; } -static void send_udp_frags_v4(int fd_raw, struct sockaddr *addr, socklen_t alen) +static void send_udp_frags(int fd_raw, struct sockaddr *addr, + socklen_t alen, bool ipv6) { struct ip *iphdr = (struct ip *)ip_frame; + struct ip6_hdr *ip6hdr = (struct ip6_hdr *)ip_frame; struct udphdr udphdr; int res; int offset; @@ -142,31 +215,55 @@ static void send_udp_frags_v4(int fd_raw, struct sockaddr *addr, socklen_t alen) * Odd fragments (1st, 3rd, 5th, etc.) are sent out first, then * even fragments (0th, 2nd, etc.) are sent out. */ - memset(iphdr, 0, sizeof(*iphdr)); - iphdr->ip_hl = 5; - iphdr->ip_v = 4; - iphdr->ip_tos = 0; - iphdr->ip_id = htons(ip_id++); - iphdr->ip_ttl = 0x40; - iphdr->ip_p = IPPROTO_UDP; - iphdr->ip_src.s_addr = htonl(INADDR_LOOPBACK); - iphdr->ip_dst = addr4; - iphdr->ip_sum = 0; + if (ipv6) { + struct ip6_frag *fraghdr = (struct ip6_frag *)(ip_frame + IP6_HLEN); + ((struct sockaddr_in6 *)addr)->sin6_port = 0; + memset(ip6hdr, 0, sizeof(*ip6hdr)); + ip6hdr->ip6_flow = htonl(6<<28); /* Version. */ + ip6hdr->ip6_nxt = IPPROTO_FRAGMENT; + ip6hdr->ip6_hops = 255; + ip6hdr->ip6_src = addr6; + ip6hdr->ip6_dst = addr6; + fraghdr->ip6f_nxt = IPPROTO_UDP; + fraghdr->ip6f_reserved = 0; + fraghdr->ip6f_ident = htonl(ip_id++); + } else { + memset(iphdr, 0, sizeof(*iphdr)); + iphdr->ip_hl = 5; + iphdr->ip_v = 4; + iphdr->ip_tos = 0; + iphdr->ip_id = htons(ip_id++); + iphdr->ip_ttl = 0x40; + iphdr->ip_p = IPPROTO_UDP; + iphdr->ip_src.s_addr = htonl(INADDR_LOOPBACK); + iphdr->ip_dst = addr4; + iphdr->ip_sum = 0; + } /* Odd fragments. */ - offset = 0; - while (offset < msg_len) { - send_fragment(fd_raw, addr, alen, iphdr, offset); + offset = max_frag_len; + while (offset < (UDP_HLEN + payload_len)) { + send_fragment(fd_raw, addr, alen, offset, ipv6); offset += 2 * max_frag_len; } if (cfg_overlap) { /* Send an extra random fragment. */ - offset = rand() % (UDP_HLEN + msg_len - 1); + offset = rand() % (UDP_HLEN + payload_len - 1); /* sendto() returns EINVAL if offset + frag_len is too small. */ - frag_len = IP4_HLEN + UDP_HLEN + rand() % 256; - iphdr->ip_off = htons(offset / 8 | IP4_MF); - iphdr->ip_len = htons(frag_len); + if (ipv6) { + struct ip6_frag *fraghdr = (struct ip6_frag *)(ip_frame + IP6_HLEN); + frag_len = max_frag_len + rand() % 256; + /* In IPv6 if !!(frag_len % 8), the fragment is dropped. */ + frag_len &= ~0x7; + fraghdr->ip6f_offlg = htons(offset / 8 | IP6_MF); + ip6hdr->ip6_plen = htons(frag_len); + frag_len += IP6_HLEN; + } else { + frag_len = IP4_HLEN + UDP_HLEN + rand() % 256; + iphdr->ip_off = htons(offset / 8 | IP4_MF); + iphdr->ip_len = htons(frag_len); + } res = sendto(fd_raw, ip_frame, frag_len, 0, addr, alen); if (res < 0) error(1, errno, "sendto overlap"); @@ -175,48 +272,26 @@ static void send_udp_frags_v4(int fd_raw, struct sockaddr *addr, socklen_t alen) frag_counter++; } - /* Zeroth fragment (UDP header). */ - frag_len = IP4_HLEN + UDP_HLEN; - iphdr->ip_len = htons(frag_len); - iphdr->ip_off = htons(IP4_MF); - - udphdr.source = htons(cfg_port + 1); - udphdr.dest = htons(cfg_port); - udphdr.len = htons(UDP_HLEN + msg_len); - udphdr.check = 0; - udphdr.check = udp_checksum(iphdr, &udphdr); - - memcpy(ip_frame + IP4_HLEN, &udphdr, UDP_HLEN); - res = sendto(fd_raw, ip_frame, frag_len, 0, addr, alen); - if (res < 0) - error(1, errno, "sendto UDP header"); - if (res != frag_len) - error(1, 0, "sendto UDP header: %d vs %d", (int)res, frag_len); - frag_counter++; - - /* Even fragments. */ - offset = max_frag_len; - while (offset < msg_len) { - send_fragment(fd_raw, addr, alen, iphdr, offset); + /* Event fragments. */ + offset = 0; + while (offset < (UDP_HLEN + payload_len)) { + send_fragment(fd_raw, addr, alen, offset, ipv6); offset += 2 * max_frag_len; } } -static void run_test(struct sockaddr *addr, socklen_t alen) +static void run_test(struct sockaddr *addr, socklen_t alen, bool ipv6) { - int fd_tx_udp, fd_tx_raw, fd_rx_udp; + int fd_tx_raw, fd_rx_udp; struct timeval tv = { .tv_sec = 0, .tv_usec = 10 * 1000 }; int idx; + int min_frag_len = ipv6 ? 1280 : 8; /* Initialize the payload. */ for (idx = 0; idx < MSG_LEN_MAX; ++idx) udp_payload[idx] = idx % 256; /* Open sockets. */ - fd_tx_udp = socket(addr->sa_family, SOCK_DGRAM, 0); - if (fd_tx_udp == -1) - error(1, errno, "socket tx_udp"); - fd_tx_raw = socket(addr->sa_family, SOCK_RAW, IPPROTO_RAW); if (fd_tx_raw == -1) error(1, errno, "socket tx_raw"); @@ -230,22 +305,21 @@ static void run_test(struct sockaddr *addr, socklen_t alen) if (setsockopt(fd_rx_udp, SOL_SOCKET, SO_RCVTIMEO, &tv, sizeof(tv))) error(1, errno, "setsockopt rcv timeout"); - for (msg_len = 1; msg_len < MSG_LEN_MAX; msg_len += (rand() % 4096)) { + for (payload_len = min_frag_len; payload_len < MSG_LEN_MAX; + payload_len += (rand() % 4096)) { if (cfg_verbose) - printf("msg_len: %d\n", msg_len); - max_frag_len = addr->sa_family == AF_INET ? 8 : 1280; - for (; max_frag_len < 1500 && max_frag_len <= msg_len; - max_frag_len += 8) { - send_udp_frags_v4(fd_tx_raw, addr, alen); + printf("payload_len: %d\n", payload_len); + max_frag_len = min_frag_len; + do { + send_udp_frags(fd_tx_raw, addr, alen, ipv6); recv_validate_udp(fd_rx_udp); - } + max_frag_len += 8 * (rand() % 8); + } while (max_frag_len < (1500 - FRAG_HLEN) && max_frag_len <= payload_len); } /* Cleanup. */ if (close(fd_tx_raw)) error(1, errno, "close tx_raw"); - if (close(fd_tx_udp)) - error(1, errno, "close tx_udp"); if (close(fd_rx_udp)) error(1, errno, "close rx_udp"); @@ -265,13 +339,18 @@ static void run_test_v4(void) addr.sin_port = htons(cfg_port); addr.sin_addr = addr4; - run_test((void *)&addr, sizeof(addr)); + run_test((void *)&addr, sizeof(addr), false /* !ipv6 */); } static void run_test_v6(void) { - fprintf(stderr, "NOT IMPL.\n"); - exit(1); + struct sockaddr_in6 addr = {0}; + + addr.sin6_family = AF_INET6; + addr.sin6_port = htons(cfg_port); + addr.sin6_addr = addr6; + + run_test((void *)&addr, sizeof(addr), true /* ipv6 */); } static void parse_opts(int argc, char **argv) @@ -303,6 +382,8 @@ int main(int argc, char **argv) parse_opts(argc, argv); seed = time(NULL); srand(seed); + /* Print the seed to track/reproduce potential failures. */ + printf("seed = %d\n", seed); if (cfg_do_ipv4) run_test_v4(); diff --git a/tools/testing/selftests/net/ip_defrag.sh b/tools/testing/selftests/net/ip_defrag.sh index 78743adcca9e..3a4042d918f0 100755 --- a/tools/testing/selftests/net/ip_defrag.sh +++ b/tools/testing/selftests/net/ip_defrag.sh @@ -6,23 +6,34 @@ set +x set -e -echo "ipv4 defrag" +readonly NETNS="ns-$(mktemp -u XXXXXX)" + +setup() { + ip netns add "${NETNS}" + ip -netns "${NETNS}" link set lo up + ip netns exec "${NETNS}" sysctl -w net.ipv4.ipfrag_high_thresh=9000000 &> /dev/null + ip netns exec "${NETNS}" sysctl -w net.ipv4.ipfrag_low_thresh=7000000 &> /dev/null + ip netns exec "${NETNS}" sysctl -w net.ipv6.ip6frag_high_thresh=9000000 &> /dev/null + ip netns exec "${NETNS}" sysctl -w net.ipv6.ip6frag_low_thresh=7000000 &> /dev/null +} -run_v4() { -sysctl -w net.ipv4.ipfrag_high_thresh=9000000 &> /dev/null -sysctl -w net.ipv4.ipfrag_low_thresh=7000000 &> /dev/null -./ip_defrag -4 +cleanup() { + ip netns del "${NETNS}" } -export -f run_v4 -./in_netns.sh "run_v4" +trap cleanup EXIT +setup + +echo "ipv4 defrag" +ip netns exec "${NETNS}" ./ip_defrag -4 + echo "ipv4 defrag with overlaps" -run_v4o() { -sysctl -w net.ipv4.ipfrag_high_thresh=9000000 &> /dev/null -sysctl -w net.ipv4.ipfrag_low_thresh=7000000 &> /dev/null -./ip_defrag -4o -} -export -f run_v4o +ip netns exec "${NETNS}" ./ip_defrag -4o + +echo "ipv6 defrag" +ip netns exec "${NETNS}" ./ip_defrag -6 + +echo "ipv6 defrag with overlaps" +ip netns exec "${NETNS}" ./ip_defrag -6o -./in_netns.sh "run_v4o" diff --git a/tools/testing/selftests/net/pmtu.sh b/tools/testing/selftests/net/pmtu.sh index 32a194e3e07a..0ab9423d009f 100755 --- a/tools/testing/selftests/net/pmtu.sh +++ b/tools/testing/selftests/net/pmtu.sh @@ -178,8 +178,8 @@ setup() { cleanup() { [ ${cleanup_done} -eq 1 ] && return - ip netns del ${NS_A} 2 > /dev/null - ip netns del ${NS_B} 2 > /dev/null + ip netns del ${NS_A} 2> /dev/null + ip netns del ${NS_B} 2> /dev/null cleanup_done=1 } diff --git a/tools/testing/selftests/net/tls.c b/tools/testing/selftests/net/tls.c index 07daff076ce0..11d54c36ae49 100644 --- a/tools/testing/selftests/net/tls.c +++ b/tools/testing/selftests/net/tls.c @@ -121,11 +121,11 @@ TEST_F(tls, send_then_sendfile) buf = (char *)malloc(st.st_size); EXPECT_EQ(send(self->fd, test_str, to_send, 0), to_send); - EXPECT_EQ(recv(self->cfd, recv_buf, to_send, 0), to_send); + EXPECT_EQ(recv(self->cfd, recv_buf, to_send, MSG_WAITALL), to_send); EXPECT_EQ(memcmp(test_str, recv_buf, to_send), 0); EXPECT_GE(sendfile(self->fd, filefd, 0, st.st_size), 0); - EXPECT_EQ(recv(self->cfd, buf, st.st_size, 0), st.st_size); + EXPECT_EQ(recv(self->cfd, buf, st.st_size, MSG_WAITALL), st.st_size); } TEST_F(tls, recv_max) @@ -160,7 +160,7 @@ TEST_F(tls, msg_more) EXPECT_EQ(send(self->fd, test_str, send_len, MSG_MORE), send_len); EXPECT_EQ(recv(self->cfd, buf, send_len, MSG_DONTWAIT), -1); EXPECT_EQ(send(self->fd, test_str, send_len, 0), send_len); - EXPECT_EQ(recv(self->cfd, buf, send_len * 2, MSG_DONTWAIT), + EXPECT_EQ(recv(self->cfd, buf, send_len * 2, MSG_WAITALL), send_len * 2); EXPECT_EQ(memcmp(buf, test_str, send_len), 0); } @@ -180,7 +180,7 @@ TEST_F(tls, sendmsg_single) msg.msg_iov = &vec; msg.msg_iovlen = 1; EXPECT_EQ(sendmsg(self->fd, &msg, 0), send_len); - EXPECT_EQ(recv(self->cfd, buf, send_len, 0), send_len); + EXPECT_EQ(recv(self->cfd, buf, send_len, MSG_WAITALL), send_len); EXPECT_EQ(memcmp(buf, test_str, send_len), 0); } @@ -306,7 +306,7 @@ TEST_F(tls, splice_from_pipe2) EXPECT_GE(splice(p[0], NULL, self->fd, NULL, 8000, 0), 0); EXPECT_GE(write(p2[1], mem_send + 8000, 8000), 0); EXPECT_GE(splice(p2[0], NULL, self->fd, NULL, 8000, 0), 0); - EXPECT_GE(recv(self->cfd, mem_recv, send_len, 0), 0); + EXPECT_EQ(recv(self->cfd, mem_recv, send_len, MSG_WAITALL), send_len); EXPECT_EQ(memcmp(mem_send, mem_recv, send_len), 0); } @@ -436,7 +436,7 @@ TEST_F(tls, multiple_send_single_recv) EXPECT_GE(send(self->fd, send_mem, send_len, 0), 0); EXPECT_GE(send(self->fd, send_mem, send_len, 0), 0); memset(recv_mem, 0, total_len); - EXPECT_EQ(recv(self->cfd, recv_mem, total_len, 0), total_len); + EXPECT_EQ(recv(self->cfd, recv_mem, total_len, MSG_WAITALL), total_len); EXPECT_EQ(memcmp(send_mem, recv_mem, send_len), 0); EXPECT_EQ(memcmp(send_mem, recv_mem + send_len, send_len), 0); @@ -502,6 +502,55 @@ TEST_F(tls, recv_peek_multiple) EXPECT_EQ(memcmp(test_str, buf, send_len), 0); } +TEST_F(tls, recv_peek_multiple_records) +{ + char const *test_str = "test_read_peek_mult_recs"; + char const *test_str_first = "test_read_peek"; + char const *test_str_second = "_mult_recs"; + int len; + char buf[64]; + + len = strlen(test_str_first); + EXPECT_EQ(send(self->fd, test_str_first, len, 0), len); + + len = strlen(test_str_second) + 1; + EXPECT_EQ(send(self->fd, test_str_second, len, 0), len); + + len = sizeof(buf); + memset(buf, 0, len); + EXPECT_NE(recv(self->cfd, buf, len, MSG_PEEK), -1); + + /* MSG_PEEK can only peek into the current record. */ + len = strlen(test_str_first) + 1; + EXPECT_EQ(memcmp(test_str_first, buf, len), 0); + + len = sizeof(buf); + memset(buf, 0, len); + EXPECT_NE(recv(self->cfd, buf, len, 0), -1); + + /* Non-MSG_PEEK will advance strparser (and therefore record) + * however. + */ + len = strlen(test_str) + 1; + EXPECT_EQ(memcmp(test_str, buf, len), 0); + + /* MSG_MORE will hold current record open, so later MSG_PEEK + * will see everything. + */ + len = strlen(test_str_first); + EXPECT_EQ(send(self->fd, test_str_first, len, MSG_MORE), len); + + len = strlen(test_str_second) + 1; + EXPECT_EQ(send(self->fd, test_str_second, len, 0), len); + + len = sizeof(buf); + memset(buf, 0, len); + EXPECT_NE(recv(self->cfd, buf, len, MSG_PEEK), -1); + + len = strlen(test_str) + 1; + EXPECT_EQ(memcmp(test_str, buf, len), 0); +} + TEST_F(tls, recv_peek_large_buf_mult_recs) { char const *test_str = "test_read_peek_mult_recs"; @@ -524,6 +573,7 @@ TEST_F(tls, recv_peek_large_buf_mult_recs) EXPECT_EQ(memcmp(test_str, buf, len), 0); } + TEST_F(tls, pollin) { char const *test_str = "test_poll"; @@ -537,7 +587,7 @@ TEST_F(tls, pollin) EXPECT_EQ(poll(&fd, 1, 20), 1); EXPECT_EQ(fd.revents & POLLIN, 1); - EXPECT_EQ(recv(self->cfd, buf, send_len, 0), send_len); + EXPECT_EQ(recv(self->cfd, buf, send_len, MSG_WAITALL), send_len); /* Test timing out */ EXPECT_EQ(poll(&fd, 1, 20), 0); } @@ -555,7 +605,7 @@ TEST_F(tls, poll_wait) /* Set timeout to inf. secs */ EXPECT_EQ(poll(&fd, 1, -1), 1); EXPECT_EQ(fd.revents & POLLIN, 1); - EXPECT_EQ(recv(self->cfd, recv_mem, send_len, 0), send_len); + EXPECT_EQ(recv(self->cfd, recv_mem, send_len, MSG_WAITALL), send_len); } TEST_F(tls, blocking) @@ -701,7 +751,7 @@ TEST_F(tls, control_msg) EXPECT_EQ(recv(self->cfd, buf, send_len, 0), -1); vec.iov_base = buf; - EXPECT_EQ(recvmsg(self->cfd, &msg, 0), send_len); + EXPECT_EQ(recvmsg(self->cfd, &msg, MSG_WAITALL), send_len); cmsg = CMSG_FIRSTHDR(&msg); EXPECT_NE(cmsg, NULL); EXPECT_EQ(cmsg->cmsg_level, SOL_TLS); diff --git a/tools/testing/selftests/networking/timestamping/Makefile b/tools/testing/selftests/networking/timestamping/Makefile index a728040edbe1..14cfcf006936 100644 --- a/tools/testing/selftests/networking/timestamping/Makefile +++ b/tools/testing/selftests/networking/timestamping/Makefile @@ -5,6 +5,7 @@ TEST_PROGS := hwtstamp_config rxtimestamp timestamping txtimestamp all: $(TEST_PROGS) +top_srcdir = ../../../../.. include ../../lib.mk clean: diff --git a/tools/testing/selftests/vm/Makefile b/tools/testing/selftests/vm/Makefile index 9881876d2aa0..e94b7b14bcb2 100644 --- a/tools/testing/selftests/vm/Makefile +++ b/tools/testing/selftests/vm/Makefile @@ -26,10 +26,6 @@ TEST_PROGS := run_vmtests include ../lib.mk -$(OUTPUT)/userfaultfd: ../../../../usr/include/linux/kernel.h $(OUTPUT)/userfaultfd: LDLIBS += -lpthread $(OUTPUT)/mlock-random-test: LDLIBS += -lcap - -../../../../usr/include/linux/kernel.h: - make -C ../../../.. headers_install diff --git a/tools/vm/page-types.c b/tools/vm/page-types.c index 30cb0a0713ff..37908a83ddc2 100644 --- a/tools/vm/page-types.c +++ b/tools/vm/page-types.c @@ -159,12 +159,6 @@ static const char * const page_flag_names[] = { }; -static const char * const debugfs_known_mountpoints[] = { - "/sys/kernel/debug", - "/debug", - 0, -}; - /* * data structures */ diff --git a/tools/vm/slabinfo.c b/tools/vm/slabinfo.c index f82c2eaa859d..334b16db0ebb 100644 --- a/tools/vm/slabinfo.c +++ b/tools/vm/slabinfo.c @@ -30,8 +30,8 @@ struct slabinfo { int alias; int refs; int aliases, align, cache_dma, cpu_slabs, destroy_by_rcu; - int hwcache_align, object_size, objs_per_slab; - int sanity_checks, slab_size, store_user, trace; + unsigned int hwcache_align, object_size, objs_per_slab; + unsigned int sanity_checks, slab_size, store_user, trace; int order, poison, reclaim_account, red_zone; unsigned long partial, objects, slabs, objects_partial, objects_total; unsigned long alloc_fastpath, alloc_slowpath; diff --git a/virt/kvm/arm/mmu.c b/virt/kvm/arm/mmu.c index 91aaf73b00df..ed162a6c57c5 100644 --- a/virt/kvm/arm/mmu.c +++ b/virt/kvm/arm/mmu.c @@ -1817,18 +1817,6 @@ static int kvm_unmap_hva_handler(struct kvm *kvm, gpa_t gpa, u64 size, void *dat return 0; } -int kvm_unmap_hva(struct kvm *kvm, unsigned long hva) -{ - unsigned long end = hva + PAGE_SIZE; - - if (!kvm->arch.pgd) - return 0; - - trace_kvm_unmap_hva(hva); - handle_hva_to_gpa(kvm, hva, end, &kvm_unmap_hva_handler, NULL); - return 0; -} - int kvm_unmap_hva_range(struct kvm *kvm, unsigned long start, unsigned long end) { @@ -1860,13 +1848,20 @@ static int kvm_set_spte_handler(struct kvm *kvm, gpa_t gpa, u64 size, void *data void kvm_set_spte_hva(struct kvm *kvm, unsigned long hva, pte_t pte) { unsigned long end = hva + PAGE_SIZE; + kvm_pfn_t pfn = pte_pfn(pte); pte_t stage2_pte; if (!kvm->arch.pgd) return; trace_kvm_set_spte_hva(hva); - stage2_pte = pfn_pte(pte_pfn(pte), PAGE_S2); + + /* + * We've moved a page around, probably through CoW, so let's treat it + * just like a translation fault and clean the cache to the PoC. + */ + clean_dcache_guest_page(pfn, PAGE_SIZE); + stage2_pte = pfn_pte(pfn, PAGE_S2); handle_hva_to_gpa(kvm, hva, end, &kvm_set_spte_handler, &stage2_pte); } diff --git a/virt/kvm/arm/trace.h b/virt/kvm/arm/trace.h index e53b596f483b..57b3edebbb40 100644 --- a/virt/kvm/arm/trace.h +++ b/virt/kvm/arm/trace.h @@ -134,21 +134,6 @@ TRACE_EVENT(kvm_mmio_emulate, __entry->vcpu_pc, __entry->instr, __entry->cpsr) ); -TRACE_EVENT(kvm_unmap_hva, - TP_PROTO(unsigned long hva), - TP_ARGS(hva), - - TP_STRUCT__entry( - __field( unsigned long, hva ) - ), - - TP_fast_assign( - __entry->hva = hva; - ), - - TP_printk("mmu notifier unmap hva: %#08lx", __entry->hva) -); - TRACE_EVENT(kvm_unmap_hva_range, TP_PROTO(unsigned long start, unsigned long end), TP_ARGS(start, end), |