diff options
634 files changed, 6651 insertions, 3916 deletions
diff --git a/Documentation/ABI/testing/sysfs-bus-iio-proximity-as3935 b/Documentation/ABI/testing/sysfs-bus-iio-proximity-as3935 index 33e96f740639..147d4e8a1403 100644 --- a/Documentation/ABI/testing/sysfs-bus-iio-proximity-as3935 +++ b/Documentation/ABI/testing/sysfs-bus-iio-proximity-as3935 @@ -14,3 +14,11 @@ Description: Show or set the gain boost of the amp, from 0-31 range. 18 = indoors (default) 14 = outdoors + +What /sys/bus/iio/devices/iio:deviceX/noise_level_tripped +Date: May 2017 +KernelVersion: 4.13 +Contact: Matt Ranostay <matt.ranostay@konsulko.com> +Description: + When 1 the noise level is over the trip level and not reporting + valid data diff --git a/Documentation/ABI/testing/sysfs-kernel-mm-swap b/Documentation/ABI/testing/sysfs-kernel-mm-swap index 587db52084c7..94672016c268 100644 --- a/Documentation/ABI/testing/sysfs-kernel-mm-swap +++ b/Documentation/ABI/testing/sysfs-kernel-mm-swap @@ -14,13 +14,3 @@ Description: Enable/disable VMA based swap readahead. still used for tmpfs etc. other users. If set to false, the global swap readahead algorithm will be used for all swappable pages. - -What: /sys/kernel/mm/swap/vma_ra_max_order -Date: August 2017 -Contact: Linux memory management mailing list <linux-mm@kvack.org> -Description: The max readahead size in order for VMA based swap readahead - - VMA based swap readahead algorithm will readahead at - most 1 << max_order pages for each readahead. The - real readahead size for each readahead will be scaled - according to the estimation algorithm. diff --git a/Documentation/core-api/kernel-api.rst b/Documentation/core-api/kernel-api.rst index 8282099e0cbf..5da10184d908 100644 --- a/Documentation/core-api/kernel-api.rst +++ b/Documentation/core-api/kernel-api.rst @@ -352,44 +352,30 @@ Read-Copy Update (RCU) ---------------------- .. kernel-doc:: include/linux/rcupdate.h - :external: .. kernel-doc:: include/linux/rcupdate_wait.h - :external: .. kernel-doc:: include/linux/rcutree.h - :external: .. kernel-doc:: kernel/rcu/tree.c - :external: .. kernel-doc:: kernel/rcu/tree_plugin.h - :external: .. kernel-doc:: kernel/rcu/tree_exp.h - :external: .. kernel-doc:: kernel/rcu/update.c - :external: .. kernel-doc:: include/linux/srcu.h - :external: .. kernel-doc:: kernel/rcu/srcutree.c - :external: .. kernel-doc:: include/linux/rculist_bl.h - :external: .. kernel-doc:: include/linux/rculist.h - :external: .. kernel-doc:: include/linux/rculist_nulls.h - :external: .. kernel-doc:: include/linux/rcu_sync.h - :external: .. kernel-doc:: kernel/rcu/sync.c - :external: diff --git a/Documentation/devicetree/bindings/iio/proximity/as3935.txt b/Documentation/devicetree/bindings/iio/proximity/as3935.txt index 38d74314b7ab..b6c1afa6f02d 100644 --- a/Documentation/devicetree/bindings/iio/proximity/as3935.txt +++ b/Documentation/devicetree/bindings/iio/proximity/as3935.txt @@ -16,6 +16,10 @@ Optional properties: - ams,tuning-capacitor-pf: Calibration tuning capacitor stepping value 0 - 120pF. This will require using the calibration data from the manufacturer. + - ams,nflwdth: Set the noise and watchdog threshold register on + startup. This will need to set according to the noise from the + MCU board, and possibly the local environment. Refer to the + datasheet for the threshold settings. Example: @@ -27,4 +31,5 @@ as3935@0 { interrupt-parent = <&gpio1>; interrupts = <16 1>; ams,tuning-capacitor-pf = <80>; + ams,nflwdth = <0x44>; }; diff --git a/Documentation/devicetree/bindings/interrupt-controller/arm,gic-v3.txt b/Documentation/devicetree/bindings/interrupt-controller/arm,gic-v3.txt index 4c29cdab0ea5..5eb108e180fa 100644 --- a/Documentation/devicetree/bindings/interrupt-controller/arm,gic-v3.txt +++ b/Documentation/devicetree/bindings/interrupt-controller/arm,gic-v3.txt @@ -99,7 +99,7 @@ Examples: compatible = "arm,gic-v3-its"; msi-controller; #msi-cells = <1>; - reg = <0x0 0x2c200000 0 0x200000>; + reg = <0x0 0x2c200000 0 0x20000>; }; }; @@ -124,14 +124,14 @@ Examples: compatible = "arm,gic-v3-its"; msi-controller; #msi-cells = <1>; - reg = <0x0 0x2c200000 0 0x200000>; + reg = <0x0 0x2c200000 0 0x20000>; }; gic-its@2c400000 { compatible = "arm,gic-v3-its"; msi-controller; #msi-cells = <1>; - reg = <0x0 0x2c400000 0 0x200000>; + reg = <0x0 0x2c400000 0 0x20000>; }; ppi-partitions { diff --git a/Documentation/kbuild/makefiles.txt b/Documentation/kbuild/makefiles.txt index 329e740adea7..f6f80380dff2 100644 --- a/Documentation/kbuild/makefiles.txt +++ b/Documentation/kbuild/makefiles.txt @@ -1108,14 +1108,6 @@ When kbuild executes, the following steps are followed (roughly): ld Link target. Often, LDFLAGS_$@ is used to set specific options to ld. - objcopy - Copy binary. Uses OBJCOPYFLAGS usually specified in - arch/$(ARCH)/Makefile. - OBJCOPYFLAGS_$@ may be used to set additional options. - - gzip - Compress target. Use maximum compression to compress target. - Example: #arch/x86/boot/Makefile LDFLAGS_bootsect := -Ttext 0x0 -s --oformat binary @@ -1139,6 +1131,19 @@ When kbuild executes, the following steps are followed (roughly): resulting in the target file being recompiled for no obvious reason. + objcopy + Copy binary. Uses OBJCOPYFLAGS usually specified in + arch/$(ARCH)/Makefile. + OBJCOPYFLAGS_$@ may be used to set additional options. + + gzip + Compress target. Use maximum compression to compress target. + + Example: + #arch/x86/boot/compressed/Makefile + $(obj)/vmlinux.bin.gz: $(vmlinux.bin.all-y) FORCE + $(call if_changed,gzip) + dtc Create flattened device tree blob object suitable for linking into vmlinux. Device tree blobs linked into vmlinux are placed @@ -1219,7 +1224,7 @@ When kbuild executes, the following steps are followed (roughly): that may be shared between individual architectures. The recommended approach how to use a generic header file is to list the file in the Kbuild file. - See "7.3 generic-y" for further info on syntax etc. + See "7.2 generic-y" for further info on syntax etc. --- 6.11 Post-link pass @@ -1254,13 +1259,13 @@ A Kbuild file may be defined under arch/<arch>/include/uapi/asm/ and arch/<arch>/include/asm/ to list asm files coming from asm-generic. See subsequent chapter for the syntax of the Kbuild file. - --- 7.1 no-export-headers +--- 7.1 no-export-headers no-export-headers is essentially used by include/uapi/linux/Kbuild to avoid exporting specific headers (e.g. kvm.h) on architectures that do not support it. It should be avoided as much as possible. - --- 7.2 generic-y +--- 7.2 generic-y If an architecture uses a verbatim copy of a header from include/asm-generic then this is listed in the file @@ -1287,7 +1292,7 @@ See subsequent chapter for the syntax of the Kbuild file. Example: termios.h #include <asm-generic/termios.h> - --- 7.3 generated-y +--- 7.3 generated-y If an architecture generates other header files alongside generic-y wrappers, generated-y specifies them. @@ -1299,7 +1304,7 @@ See subsequent chapter for the syntax of the Kbuild file. #arch/x86/include/asm/Kbuild generated-y += syscalls_32.h - --- 7.5 mandatory-y +--- 7.4 mandatory-y mandatory-y is essentially used by include/uapi/asm-generic/Kbuild.asm to define the minimum set of headers that must be exported in diff --git a/Documentation/process/index.rst b/Documentation/process/index.rst index 82fc399fcd33..61e43cc3ed17 100644 --- a/Documentation/process/index.rst +++ b/Documentation/process/index.rst @@ -25,6 +25,7 @@ Below are the essential guides that every developer should read. submitting-patches coding-style email-clients + kernel-enforcement-statement Other guides to the community that are of interest to most developers are: diff --git a/Documentation/process/kernel-enforcement-statement.rst b/Documentation/process/kernel-enforcement-statement.rst new file mode 100644 index 000000000000..1e23d4227337 --- /dev/null +++ b/Documentation/process/kernel-enforcement-statement.rst @@ -0,0 +1,147 @@ +Linux Kernel Enforcement Statement +---------------------------------- + +As developers of the Linux kernel, we have a keen interest in how our software +is used and how the license for our software is enforced. Compliance with the +reciprocal sharing obligations of GPL-2.0 is critical to the long-term +sustainability of our software and community. + +Although there is a right to enforce the separate copyright interests in the +contributions made to our community, we share an interest in ensuring that +individual enforcement actions are conducted in a manner that benefits our +community and do not have an unintended negative impact on the health and +growth of our software ecosystem. In order to deter unhelpful enforcement +actions, we agree that it is in the best interests of our development +community to undertake the following commitment to users of the Linux kernel +on behalf of ourselves and any successors to our copyright interests: + + Notwithstanding the termination provisions of the GPL-2.0, we agree that + it is in the best interests of our development community to adopt the + following provisions of GPL-3.0 as additional permissions under our + license with respect to any non-defensive assertion of rights under the + license. + + However, if you cease all violation of this License, then your license + from a particular copyright holder is reinstated (a) provisionally, + unless and until the copyright holder explicitly and finally + terminates your license, and (b) permanently, if the copyright holder + fails to notify you of the violation by some reasonable means prior to + 60 days after the cessation. + + Moreover, your license from a particular copyright holder is + reinstated permanently if the copyright holder notifies you of the + violation by some reasonable means, this is the first time you have + received notice of violation of this License (for any work) from that + copyright holder, and you cure the violation prior to 30 days after + your receipt of the notice. + +Our intent in providing these assurances is to encourage more use of the +software. We want companies and individuals to use, modify and distribute +this software. We want to work with users in an open and transparent way to +eliminate any uncertainty about our expectations regarding compliance or +enforcement that might limit adoption of our software. We view legal action +as a last resort, to be initiated only when other community efforts have +failed to resolve the problem. + +Finally, once a non-compliance issue is resolved, we hope the user will feel +welcome to join us in our efforts on this project. Working together, we will +be stronger. + +Except where noted below, we speak only for ourselves, and not for any company +we might work for today, have in the past, or will in the future. + + - Bjorn Andersson (Linaro) + - Andrea Arcangeli (Red Hat) + - Neil Armstrong + - Jens Axboe + - Pablo Neira Ayuso + - Khalid Aziz + - Ralf Baechle + - Felipe Balbi + - Arnd Bergmann + - Ard Biesheuvel + - Paolo Bonzini (Red Hat) + - Christian Borntraeger + - Mark Brown (Linaro) + - Paul Burton + - Javier Martinez Canillas + - Rob Clark + - Jonathan Corbet + - Vivien Didelot (Savoir-faire Linux) + - Hans de Goede (Red Hat) + - Mel Gorman (SUSE) + - Sven Eckelmann + - Alex Elder (Linaro) + - Fabio Estevam + - Larry Finger + - Bhumika Goyal + - Andy Gross + - Juergen Gross + - Shawn Guo + - Ulf Hansson + - Tejun Heo + - Rob Herring + - Masami Hiramatsu + - Michal Hocko + - Simon Horman + - Johan Hovold (Hovold Consulting AB) + - Christophe JAILLET + - Olof Johansson + - Lee Jones (Linaro) + - Heiner Kallweit + - Srinivas Kandagatla + - Jan Kara + - Shuah Khan (Samsung) + - David Kershner + - Jaegeuk Kim + - Namhyung Kim + - Colin Ian King + - Jeff Kirsher + - Greg Kroah-Hartman (Linux Foundation) + - Christian König + - Vinod Koul + - Krzysztof Kozlowski + - Viresh Kumar + - Aneesh Kumar K.V + - Julia Lawall + - Doug Ledford (Red Hat) + - Chuck Lever (Oracle) + - Daniel Lezcano + - Shaohua Li + - Xin Long (Red Hat) + - Tony Luck + - Mike Marshall + - Chris Mason + - Paul E. McKenney + - David S. Miller + - Ingo Molnar + - Kuninori Morimoto + - Borislav Petkov + - Jiri Pirko + - Josh Poimboeuf + - Sebastian Reichel (Collabora) + - Guenter Roeck + - Joerg Roedel + - Leon Romanovsky + - Steven Rostedt (VMware) + - Ivan Safonov + - Ivan Safonov + - Anna Schumaker + - Jes Sorensen + - K.Y. Srinivasan + - Heiko Stuebner + - Jiri Kosina (SUSE) + - Dmitry Torokhov + - Linus Torvalds + - Thierry Reding + - Rik van Riel + - Geert Uytterhoeven (Glider bvba) + - Daniel Vetter + - Linus Walleij + - Richard Weinberger + - Dan Williams + - Rafael J. Wysocki + - Arvind Yadav + - Masahiro Yamada + - Wei Yongjun + - Lv Zheng diff --git a/MAINTAINERS b/MAINTAINERS index 2d3d750b19c0..bf1d20695cbf 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -5346,9 +5346,7 @@ M: "J. Bruce Fields" <bfields@fieldses.org> L: linux-fsdevel@vger.kernel.org S: Maintained F: include/linux/fcntl.h -F: include/linux/fs.h F: include/uapi/linux/fcntl.h -F: include/uapi/linux/fs.h F: fs/fcntl.c F: fs/locks.c @@ -5357,6 +5355,8 @@ M: Alexander Viro <viro@zeniv.linux.org.uk> L: linux-fsdevel@vger.kernel.org S: Maintained F: fs/* +F: include/linux/fs.h +F: include/uapi/linux/fs.h FINTEK F75375S HARDWARE MONITOR AND FAN CONTROLLER DRIVER M: Riku Voipio <riku.voipio@iki.fi> @@ -6671,7 +6671,7 @@ F: include/net/ieee802154_netdev.h F: Documentation/networking/ieee802154.txt IFE PROTOCOL -M: Yotam Gigi <yotamg@mellanox.com> +M: Yotam Gigi <yotam.gi@gmail.com> M: Jamal Hadi Salim <jhs@mojatatu.com> F: net/ife F: include/net/ife.h @@ -7571,7 +7571,7 @@ F: arch/mips/include/asm/kvm* F: arch/mips/kvm/ KERNEL VIRTUAL MACHINE FOR POWERPC (KVM/powerpc) -M: Alexander Graf <agraf@suse.com> +M: Paul Mackerras <paulus@ozlabs.org> L: kvm-ppc@vger.kernel.org W: http://www.linux-kvm.org/ T: git git://github.com/agraf/linux-2.6.git @@ -8743,7 +8743,7 @@ Q: http://patchwork.ozlabs.org/project/netdev/list/ F: drivers/net/ethernet/mellanox/mlxsw/ MELLANOX FIRMWARE FLASH LIBRARY (mlxfw) -M: Yotam Gigi <yotamg@mellanox.com> +M: mlxsw@mellanox.com L: netdev@vger.kernel.org S: Supported W: http://www.mellanox.com @@ -9213,7 +9213,6 @@ F: include/linux/isicom.h MUSB MULTIPOINT HIGH SPEED DUAL-ROLE CONTROLLER M: Bin Liu <b-liu@ti.com> L: linux-usb@vger.kernel.org -T: git git://git.kernel.org/pub/scm/linux/kernel/git/balbi/usb.git S: Maintained F: drivers/usb/musb/ @@ -10180,7 +10179,6 @@ F: Documentation/parport*.txt PARAVIRT_OPS INTERFACE M: Juergen Gross <jgross@suse.com> -M: Chris Wright <chrisw@sous-sol.org> M: Alok Kataria <akataria@vmware.com> M: Rusty Russell <rusty@rustcorp.com.au> L: virtualization@lists.linux-foundation.org @@ -10560,6 +10558,8 @@ M: Peter Zijlstra <peterz@infradead.org> M: Ingo Molnar <mingo@redhat.com> M: Arnaldo Carvalho de Melo <acme@kernel.org> R: Alexander Shishkin <alexander.shishkin@linux.intel.com> +R: Jiri Olsa <jolsa@redhat.com> +R: Namhyung Kim <namhyung@kernel.org> L: linux-kernel@vger.kernel.org T: git git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf/core S: Supported @@ -10890,7 +10890,7 @@ S: Maintained F: drivers/block/ps3vram.c PSAMPLE PACKET SAMPLING SUPPORT: -M: Yotam Gigi <yotamg@mellanox.com> +M: Yotam Gigi <yotam.gi@gmail.com> S: Maintained F: net/psample F: include/net/psample.h @@ -1,7 +1,7 @@ VERSION = 4 PATCHLEVEL = 14 SUBLEVEL = 0 -EXTRAVERSION = -rc4 +EXTRAVERSION = -rc7 NAME = Fearless Coyote # *DOCUMENTATION* @@ -130,8 +130,8 @@ endif ifneq ($(KBUILD_OUTPUT),) # check that the output directory actually exists saved-output := $(KBUILD_OUTPUT) -$(shell [ -d $(KBUILD_OUTPUT) ] || mkdir -p $(KBUILD_OUTPUT)) -KBUILD_OUTPUT := $(realpath $(KBUILD_OUTPUT)) +KBUILD_OUTPUT := $(shell mkdir -p $(KBUILD_OUTPUT) && cd $(KBUILD_OUTPUT) \ + && /bin/pwd) $(if $(KBUILD_OUTPUT),, \ $(error failed to create output directory "$(saved-output)")) @@ -697,11 +697,11 @@ KBUILD_CFLAGS += $(stackp-flag) ifeq ($(cc-name),clang) ifneq ($(CROSS_COMPILE),) -CLANG_TARGET := -target $(notdir $(CROSS_COMPILE:%-=%)) +CLANG_TARGET := --target=$(notdir $(CROSS_COMPILE:%-=%)) GCC_TOOLCHAIN := $(realpath $(dir $(shell which $(LD)))/..) endif ifneq ($(GCC_TOOLCHAIN),) -CLANG_GCC_TC := -gcc-toolchain $(GCC_TOOLCHAIN) +CLANG_GCC_TC := --gcc-toolchain=$(GCC_TOOLCHAIN) endif KBUILD_CFLAGS += $(CLANG_TARGET) $(CLANG_GCC_TC) KBUILD_AFLAGS += $(CLANG_TARGET) $(CLANG_GCC_TC) @@ -933,7 +933,11 @@ ifdef CONFIG_STACK_VALIDATION ifeq ($(has_libelf),1) objtool_target := tools/objtool FORCE else - $(warning "Cannot use CONFIG_STACK_VALIDATION, please install libelf-dev, libelf-devel or elfutils-libelf-devel") + ifdef CONFIG_ORC_UNWINDER + $(error "Cannot generate ORC metadata for CONFIG_ORC_UNWINDER=y, please install libelf-dev, libelf-devel or elfutils-libelf-devel") + else + $(warning "Cannot use CONFIG_STACK_VALIDATION=y, please install libelf-dev, libelf-devel or elfutils-libelf-devel") + endif SKIP_STACK_VALIDATION := 1 export SKIP_STACK_VALIDATION endif @@ -1395,7 +1399,7 @@ help: @echo ' Build, install, and boot kernel before' @echo ' running kselftest on it' @echo ' kselftest-clean - Remove all generated kselftest files' - @echo ' kselftest-merge - Merge all the config dependencies of kselftest to existed' + @echo ' kselftest-merge - Merge all the config dependencies of kselftest to existing' @echo ' .config.' @echo '' @echo 'Userspace tools targets:' diff --git a/arch/alpha/kernel/sys_alcor.c b/arch/alpha/kernel/sys_alcor.c index 118dc6af1805..7ad074fd5ab5 100644 --- a/arch/alpha/kernel/sys_alcor.c +++ b/arch/alpha/kernel/sys_alcor.c @@ -181,10 +181,10 @@ alcor_init_irq(void) * comes in on. This makes interrupt processing much easier. */ -static int __init +static int alcor_map_irq(const struct pci_dev *dev, u8 slot, u8 pin) { - static char irq_tab[7][5] __initdata = { + static char irq_tab[7][5] = { /*INT INTA INTB INTC INTD */ /* note: IDSEL 17 is XLT only */ {16+13, 16+13, 16+13, 16+13, 16+13}, /* IdSel 17, TULIP */ diff --git a/arch/alpha/kernel/sys_cabriolet.c b/arch/alpha/kernel/sys_cabriolet.c index 4c50f8f40cbb..c0fa1fe5ce77 100644 --- a/arch/alpha/kernel/sys_cabriolet.c +++ b/arch/alpha/kernel/sys_cabriolet.c @@ -173,10 +173,10 @@ pc164_init_irq(void) * because it is the Saturn IO (SIO) PCI/ISA Bridge Chip. */ -static inline int __init +static inline int eb66p_map_irq(const struct pci_dev *dev, u8 slot, u8 pin) { - static char irq_tab[5][5] __initdata = { + static char irq_tab[5][5] = { /*INT INTA INTB INTC INTD */ {16+0, 16+0, 16+5, 16+9, 16+13}, /* IdSel 6, slot 0, J25 */ {16+1, 16+1, 16+6, 16+10, 16+14}, /* IdSel 7, slot 1, J26 */ @@ -203,10 +203,10 @@ eb66p_map_irq(const struct pci_dev *dev, u8 slot, u8 pin) * because it is the Saturn IO (SIO) PCI/ISA Bridge Chip. */ -static inline int __init +static inline int cabriolet_map_irq(const struct pci_dev *dev, u8 slot, u8 pin) { - static char irq_tab[5][5] __initdata = { + static char irq_tab[5][5] = { /*INT INTA INTB INTC INTD */ { 16+2, 16+2, 16+7, 16+11, 16+15}, /* IdSel 5, slot 2, J21 */ { 16+0, 16+0, 16+5, 16+9, 16+13}, /* IdSel 6, slot 0, J19 */ @@ -287,10 +287,10 @@ cia_cab_init_pci(void) * */ -static inline int __init +static inline int alphapc164_map_irq(const struct pci_dev *dev, u8 slot, u8 pin) { - static char irq_tab[7][5] __initdata = { + static char irq_tab[7][5] = { /*INT INTA INTB INTC INTD */ { 16+2, 16+2, 16+9, 16+13, 16+17}, /* IdSel 5, slot 2, J20 */ { 16+0, 16+0, 16+7, 16+11, 16+15}, /* IdSel 6, slot 0, J29 */ diff --git a/arch/alpha/kernel/sys_dp264.c b/arch/alpha/kernel/sys_dp264.c index 6c35159bc00e..9e1e40ea1d14 100644 --- a/arch/alpha/kernel/sys_dp264.c +++ b/arch/alpha/kernel/sys_dp264.c @@ -356,7 +356,7 @@ clipper_init_irq(void) * 10 64 bit PCI option slot 3 (not bus 0) */ -static int __init +static int isa_irq_fixup(const struct pci_dev *dev, int irq) { u8 irq8; @@ -372,10 +372,10 @@ isa_irq_fixup(const struct pci_dev *dev, int irq) return irq8 & 0xf; } -static int __init +static int dp264_map_irq(const struct pci_dev *dev, u8 slot, u8 pin) { - static char irq_tab[6][5] __initdata = { + static char irq_tab[6][5] = { /*INT INTA INTB INTC INTD */ { -1, -1, -1, -1, -1}, /* IdSel 5 ISA Bridge */ { 16+ 3, 16+ 3, 16+ 2, 16+ 2, 16+ 2}, /* IdSel 6 SCSI builtin*/ @@ -394,10 +394,10 @@ dp264_map_irq(const struct pci_dev *dev, u8 slot, u8 pin) return isa_irq_fixup(dev, irq); } -static int __init +static int monet_map_irq(const struct pci_dev *dev, u8 slot, u8 pin) { - static char irq_tab[13][5] __initdata = { + static char irq_tab[13][5] = { /*INT INTA INTB INTC INTD */ { 45, 45, 45, 45, 45}, /* IdSel 3 21143 PCI1 */ { -1, -1, -1, -1, -1}, /* IdSel 4 unused */ @@ -423,7 +423,7 @@ monet_map_irq(const struct pci_dev *dev, u8 slot, u8 pin) return isa_irq_fixup(dev, COMMON_TABLE_LOOKUP); } -static u8 __init +static u8 monet_swizzle(struct pci_dev *dev, u8 *pinp) { struct pci_controller *hose = dev->sysdata; @@ -456,10 +456,10 @@ monet_swizzle(struct pci_dev *dev, u8 *pinp) return slot; } -static int __init +static int webbrick_map_irq(const struct pci_dev *dev, u8 slot, u8 pin) { - static char irq_tab[13][5] __initdata = { + static char irq_tab[13][5] = { /*INT INTA INTB INTC INTD */ { -1, -1, -1, -1, -1}, /* IdSel 7 ISA Bridge */ { -1, -1, -1, -1, -1}, /* IdSel 8 unused */ @@ -478,10 +478,10 @@ webbrick_map_irq(const struct pci_dev *dev, u8 slot, u8 pin) return isa_irq_fixup(dev, COMMON_TABLE_LOOKUP); } -static int __init +static int clipper_map_irq(const struct pci_dev *dev, u8 slot, u8 pin) { - static char irq_tab[7][5] __initdata = { + static char irq_tab[7][5] = { /*INT INTA INTB INTC INTD */ { 16+ 8, 16+ 8, 16+ 9, 16+10, 16+11}, /* IdSel 1 slot 1 */ { 16+12, 16+12, 16+13, 16+14, 16+15}, /* IdSel 2 slot 2 */ diff --git a/arch/alpha/kernel/sys_eb64p.c b/arch/alpha/kernel/sys_eb64p.c index ad40a425e841..372661c56537 100644 --- a/arch/alpha/kernel/sys_eb64p.c +++ b/arch/alpha/kernel/sys_eb64p.c @@ -167,10 +167,10 @@ eb64p_init_irq(void) * comes in on. This makes interrupt processing much easier. */ -static int __init +static int eb64p_map_irq(const struct pci_dev *dev, u8 slot, u8 pin) { - static char irq_tab[5][5] __initdata = { + static char irq_tab[5][5] = { /*INT INTA INTB INTC INTD */ {16+7, 16+7, 16+7, 16+7, 16+7}, /* IdSel 5, slot ?, ?? */ {16+0, 16+0, 16+2, 16+4, 16+9}, /* IdSel 6, slot ?, ?? */ diff --git a/arch/alpha/kernel/sys_eiger.c b/arch/alpha/kernel/sys_eiger.c index 15f42083bdb3..2731738b5872 100644 --- a/arch/alpha/kernel/sys_eiger.c +++ b/arch/alpha/kernel/sys_eiger.c @@ -141,7 +141,7 @@ eiger_init_irq(void) } } -static int __init +static int eiger_map_irq(const struct pci_dev *dev, u8 slot, u8 pin) { u8 irq_orig; @@ -158,7 +158,7 @@ eiger_map_irq(const struct pci_dev *dev, u8 slot, u8 pin) return irq_orig - 0x80; } -static u8 __init +static u8 eiger_swizzle(struct pci_dev *dev, u8 *pinp) { struct pci_controller *hose = dev->sysdata; diff --git a/arch/alpha/kernel/sys_miata.c b/arch/alpha/kernel/sys_miata.c index d5b9776a608d..731d693fa1f9 100644 --- a/arch/alpha/kernel/sys_miata.c +++ b/arch/alpha/kernel/sys_miata.c @@ -149,10 +149,10 @@ miata_init_irq(void) * comes in on. This makes interrupt processing much easier. */ -static int __init +static int miata_map_irq(const struct pci_dev *dev, u8 slot, u8 pin) { - static char irq_tab[18][5] __initdata = { + static char irq_tab[18][5] = { /*INT INTA INTB INTC INTD */ {16+ 8, 16+ 8, 16+ 8, 16+ 8, 16+ 8}, /* IdSel 14, DC21142 */ { -1, -1, -1, -1, -1}, /* IdSel 15, EIDE */ @@ -196,7 +196,7 @@ miata_map_irq(const struct pci_dev *dev, u8 slot, u8 pin) return COMMON_TABLE_LOOKUP; } -static u8 __init +static u8 miata_swizzle(struct pci_dev *dev, u8 *pinp) { int slot, pin = *pinp; diff --git a/arch/alpha/kernel/sys_mikasa.c b/arch/alpha/kernel/sys_mikasa.c index 5e82dc1ad6f2..350ec9c8335b 100644 --- a/arch/alpha/kernel/sys_mikasa.c +++ b/arch/alpha/kernel/sys_mikasa.c @@ -145,10 +145,10 @@ mikasa_init_irq(void) * comes in on. This makes interrupt processing much easier. */ -static int __init +static int mikasa_map_irq(const struct pci_dev *dev, u8 slot, u8 pin) { - static char irq_tab[8][5] __initdata = { + static char irq_tab[8][5] = { /*INT INTA INTB INTC INTD */ {16+12, 16+12, 16+12, 16+12, 16+12}, /* IdSel 17, SCSI */ { -1, -1, -1, -1, -1}, /* IdSel 18, PCEB */ diff --git a/arch/alpha/kernel/sys_nautilus.c b/arch/alpha/kernel/sys_nautilus.c index 8ae04a121186..d019e4ce07bd 100644 --- a/arch/alpha/kernel/sys_nautilus.c +++ b/arch/alpha/kernel/sys_nautilus.c @@ -62,7 +62,7 @@ nautilus_init_irq(void) common_init_isa_dma(); } -static int __init +static int nautilus_map_irq(const struct pci_dev *dev, u8 slot, u8 pin) { /* Preserve the IRQ set up by the console. */ diff --git a/arch/alpha/kernel/sys_noritake.c b/arch/alpha/kernel/sys_noritake.c index 063e594fd969..2301678d9f9d 100644 --- a/arch/alpha/kernel/sys_noritake.c +++ b/arch/alpha/kernel/sys_noritake.c @@ -193,10 +193,10 @@ noritake_init_irq(void) * comes in on. This makes interrupt processing much easier. */ -static int __init +static int noritake_map_irq(const struct pci_dev *dev, u8 slot, u8 pin) { - static char irq_tab[15][5] __initdata = { + static char irq_tab[15][5] = { /*INT INTA INTB INTC INTD */ /* note: IDSELs 16, 17, and 25 are CORELLE only */ { 16+1, 16+1, 16+1, 16+1, 16+1}, /* IdSel 16, QLOGIC */ @@ -221,7 +221,7 @@ noritake_map_irq(const struct pci_dev *dev, u8 slot, u8 pin) return COMMON_TABLE_LOOKUP; } -static u8 __init +static u8 noritake_swizzle(struct pci_dev *dev, u8 *pinp) { int slot, pin = *pinp; diff --git a/arch/alpha/kernel/sys_rawhide.c b/arch/alpha/kernel/sys_rawhide.c index dfd510ae5d8c..546822d07dc7 100644 --- a/arch/alpha/kernel/sys_rawhide.c +++ b/arch/alpha/kernel/sys_rawhide.c @@ -221,10 +221,10 @@ rawhide_init_irq(void) * */ -static int __init +static int rawhide_map_irq(const struct pci_dev *dev, u8 slot, u8 pin) { - static char irq_tab[5][5] __initdata = { + static char irq_tab[5][5] = { /*INT INTA INTB INTC INTD */ { 16+16, 16+16, 16+16, 16+16, 16+16}, /* IdSel 1 SCSI PCI 1 */ { 16+ 0, 16+ 0, 16+ 1, 16+ 2, 16+ 3}, /* IdSel 2 slot 2 */ diff --git a/arch/alpha/kernel/sys_ruffian.c b/arch/alpha/kernel/sys_ruffian.c index a3f485257170..3b35e1913492 100644 --- a/arch/alpha/kernel/sys_ruffian.c +++ b/arch/alpha/kernel/sys_ruffian.c @@ -117,10 +117,10 @@ ruffian_kill_arch (int mode) * */ -static int __init +static int ruffian_map_irq(const struct pci_dev *dev, u8 slot, u8 pin) { - static char irq_tab[11][5] __initdata = { + static char irq_tab[11][5] = { /*INT INTA INTB INTC INTD */ {-1, -1, -1, -1, -1}, /* IdSel 13, 21052 */ {-1, -1, -1, -1, -1}, /* IdSel 14, SIO */ @@ -139,7 +139,7 @@ ruffian_map_irq(const struct pci_dev *dev, u8 slot, u8 pin) return COMMON_TABLE_LOOKUP; } -static u8 __init +static u8 ruffian_swizzle(struct pci_dev *dev, u8 *pinp) { int slot, pin = *pinp; diff --git a/arch/alpha/kernel/sys_rx164.c b/arch/alpha/kernel/sys_rx164.c index 08ee737d4fba..e178007107ef 100644 --- a/arch/alpha/kernel/sys_rx164.c +++ b/arch/alpha/kernel/sys_rx164.c @@ -142,7 +142,7 @@ rx164_init_irq(void) * */ -static int __init +static int rx164_map_irq(const struct pci_dev *dev, u8 slot, u8 pin) { #if 0 @@ -156,7 +156,7 @@ rx164_map_irq(const struct pci_dev *dev, u8 slot, u8 pin) { 16+1, 16+1, 16+6, 16+11, 16+16}, /* IdSel 10, slot 4 */ }; #else - static char irq_tab[6][5] __initdata = { + static char irq_tab[6][5] = { /*INT INTA INTB INTC INTD */ { 16+0, 16+0, 16+6, 16+11, 16+16}, /* IdSel 5, slot 0 */ { 16+1, 16+1, 16+7, 16+12, 16+17}, /* IdSel 6, slot 1 */ diff --git a/arch/alpha/kernel/sys_sable.c b/arch/alpha/kernel/sys_sable.c index 8a0aa6d67b53..86d259c2612d 100644 --- a/arch/alpha/kernel/sys_sable.c +++ b/arch/alpha/kernel/sys_sable.c @@ -192,10 +192,10 @@ sable_init_irq(void) * with the values in the irq swizzling tables above. */ -static int __init +static int sable_map_irq(const struct pci_dev *dev, u8 slot, u8 pin) { - static char irq_tab[9][5] __initdata = { + static char irq_tab[9][5] = { /*INT INTA INTB INTC INTD */ { 32+0, 32+0, 32+0, 32+0, 32+0}, /* IdSel 0, TULIP */ { 32+1, 32+1, 32+1, 32+1, 32+1}, /* IdSel 1, SCSI */ @@ -374,10 +374,10 @@ lynx_init_irq(void) * with the values in the irq swizzling tables above. */ -static int __init +static int lynx_map_irq(const struct pci_dev *dev, u8 slot, u8 pin) { - static char irq_tab[19][5] __initdata = { + static char irq_tab[19][5] = { /*INT INTA INTB INTC INTD */ { -1, -1, -1, -1, -1}, /* IdSel 13, PCEB */ { -1, -1, -1, -1, -1}, /* IdSel 14, PPB */ @@ -404,7 +404,7 @@ lynx_map_irq(const struct pci_dev *dev, u8 slot, u8 pin) return COMMON_TABLE_LOOKUP; } -static u8 __init +static u8 lynx_swizzle(struct pci_dev *dev, u8 *pinp) { int slot, pin = *pinp; diff --git a/arch/alpha/kernel/sys_sio.c b/arch/alpha/kernel/sys_sio.c index febd24eba7a6..9fd2895639d5 100644 --- a/arch/alpha/kernel/sys_sio.c +++ b/arch/alpha/kernel/sys_sio.c @@ -144,7 +144,7 @@ sio_fixup_irq_levels(unsigned int level_bits) outb((level_bits >> 8) & 0xff, 0x4d1); } -static inline int __init +static inline int noname_map_irq(const struct pci_dev *dev, u8 slot, u8 pin) { /* @@ -165,7 +165,7 @@ noname_map_irq(const struct pci_dev *dev, u8 slot, u8 pin) * that they use the default INTA line, if they are interrupt * driven at all). */ - static char irq_tab[][5] __initdata = { + static char irq_tab[][5] = { /*INT A B C D */ { 3, 3, 3, 3, 3}, /* idsel 6 (53c810) */ {-1, -1, -1, -1, -1}, /* idsel 7 (SIO: PCI/ISA bridge) */ @@ -183,10 +183,10 @@ noname_map_irq(const struct pci_dev *dev, u8 slot, u8 pin) return irq >= 0 ? tmp : -1; } -static inline int __init +static inline int p2k_map_irq(const struct pci_dev *dev, u8 slot, u8 pin) { - static char irq_tab[][5] __initdata = { + static char irq_tab[][5] = { /*INT A B C D */ { 0, 0, -1, -1, -1}, /* idsel 6 (53c810) */ {-1, -1, -1, -1, -1}, /* idsel 7 (SIO: PCI/ISA bridge) */ diff --git a/arch/alpha/kernel/sys_sx164.c b/arch/alpha/kernel/sys_sx164.c index d063b360efed..23eee54d714a 100644 --- a/arch/alpha/kernel/sys_sx164.c +++ b/arch/alpha/kernel/sys_sx164.c @@ -94,10 +94,10 @@ sx164_init_irq(void) * 9 32 bit PCI option slot 3 */ -static int __init +static int sx164_map_irq(const struct pci_dev *dev, u8 slot, u8 pin) { - static char irq_tab[5][5] __initdata = { + static char irq_tab[5][5] = { /*INT INTA INTB INTC INTD */ { 16+ 9, 16+ 9, 16+13, 16+17, 16+21}, /* IdSel 5 slot 2 J17 */ { 16+11, 16+11, 16+15, 16+19, 16+23}, /* IdSel 6 slot 0 J19 */ diff --git a/arch/alpha/kernel/sys_takara.c b/arch/alpha/kernel/sys_takara.c index dd0f1eae3c68..9101f2bb6176 100644 --- a/arch/alpha/kernel/sys_takara.c +++ b/arch/alpha/kernel/sys_takara.c @@ -155,10 +155,10 @@ takara_init_irq(void) * assign it whatever the hell IRQ we like and it doesn't matter. */ -static int __init +static int takara_map_irq_srm(const struct pci_dev *dev, u8 slot, u8 pin) { - static char irq_tab[15][5] __initdata = { + static char irq_tab[15][5] = { { 16+3, 16+3, 16+3, 16+3, 16+3}, /* slot 6 == device 3 */ { 16+2, 16+2, 16+2, 16+2, 16+2}, /* slot 7 == device 2 */ { 16+1, 16+1, 16+1, 16+1, 16+1}, /* slot 8 == device 1 */ @@ -210,7 +210,7 @@ takara_map_irq(const struct pci_dev *dev, u8 slot, u8 pin) return COMMON_TABLE_LOOKUP; } -static u8 __init +static u8 takara_swizzle(struct pci_dev *dev, u8 *pinp) { int slot = PCI_SLOT(dev->devfn); diff --git a/arch/alpha/kernel/sys_wildfire.c b/arch/alpha/kernel/sys_wildfire.c index ee1874887776..c3f8b79fe214 100644 --- a/arch/alpha/kernel/sys_wildfire.c +++ b/arch/alpha/kernel/sys_wildfire.c @@ -288,10 +288,10 @@ wildfire_device_interrupt(unsigned long vector) * 7 64 bit PCI 1 option slot 7 */ -static int __init +static int wildfire_map_irq(const struct pci_dev *dev, u8 slot, u8 pin) { - static char irq_tab[8][5] __initdata = { + static char irq_tab[8][5] = { /*INT INTA INTB INTC INTD */ { -1, -1, -1, -1, -1}, /* IdSel 0 ISA Bridge */ { 36, 36, 36+1, 36+2, 36+3}, /* IdSel 1 SCSI builtin */ diff --git a/arch/arc/boot/dts/hsdk.dts b/arch/arc/boot/dts/hsdk.dts index 8adde1b492f1..8f627c200d60 100644 --- a/arch/arc/boot/dts/hsdk.dts +++ b/arch/arc/boot/dts/hsdk.dts @@ -137,14 +137,15 @@ /* * DW sdio controller has external ciu clock divider * controlled via register in SDIO IP. Due to its - * unexpected default value (it should devide by 1 - * but it devides by 8) SDIO IP uses wrong clock and + * unexpected default value (it should divide by 1 + * but it divides by 8) SDIO IP uses wrong clock and * works unstable (see STAR 9001204800) + * We switched to the minimum possible value of the + * divisor (div-by-2) in HSDK platform code. * So add temporary fix and change clock frequency - * from 100000000 to 12500000 Hz until we fix dw sdio - * driver itself. + * to 50000000 Hz until we fix dw sdio driver itself. */ - clock-frequency = <12500000>; + clock-frequency = <50000000>; #clock-cells = <0>; }; diff --git a/arch/arc/configs/hsdk_defconfig b/arch/arc/configs/hsdk_defconfig index 15f0f6b5fec1..7b8f8faf8a24 100644 --- a/arch/arc/configs/hsdk_defconfig +++ b/arch/arc/configs/hsdk_defconfig @@ -63,7 +63,6 @@ CONFIG_MMC_SDHCI=y CONFIG_MMC_SDHCI_PLTFM=y CONFIG_MMC_DW=y # CONFIG_IOMMU_SUPPORT is not set -CONFIG_RESET_HSDK=y CONFIG_EXT3_FS=y CONFIG_VFAT_FS=y CONFIG_TMPFS=y diff --git a/arch/arc/kernel/smp.c b/arch/arc/kernel/smp.c index f46267153ec2..6df9d94a9537 100644 --- a/arch/arc/kernel/smp.c +++ b/arch/arc/kernel/smp.c @@ -23,6 +23,8 @@ #include <linux/cpumask.h> #include <linux/reboot.h> #include <linux/irqdomain.h> +#include <linux/export.h> + #include <asm/processor.h> #include <asm/setup.h> #include <asm/mach_desc.h> @@ -30,6 +32,9 @@ #ifndef CONFIG_ARC_HAS_LLSC arch_spinlock_t smp_atomic_ops_lock = __ARCH_SPIN_LOCK_UNLOCKED; arch_spinlock_t smp_bitops_lock = __ARCH_SPIN_LOCK_UNLOCKED; + +EXPORT_SYMBOL_GPL(smp_atomic_ops_lock); +EXPORT_SYMBOL_GPL(smp_bitops_lock); #endif struct plat_smp_ops __weak plat_smp_ops; diff --git a/arch/arc/plat-hsdk/Kconfig b/arch/arc/plat-hsdk/Kconfig index bd08de4be75e..19ab3cf98f0f 100644 --- a/arch/arc/plat-hsdk/Kconfig +++ b/arch/arc/plat-hsdk/Kconfig @@ -8,3 +8,4 @@ menuconfig ARC_SOC_HSDK bool "ARC HS Development Kit SOC" select CLK_HSDK + select RESET_HSDK diff --git a/arch/arc/plat-hsdk/platform.c b/arch/arc/plat-hsdk/platform.c index 744e62e58788..fd0ae5e38639 100644 --- a/arch/arc/plat-hsdk/platform.c +++ b/arch/arc/plat-hsdk/platform.c @@ -74,6 +74,10 @@ static void __init hsdk_set_cpu_freq_1ghz(void) pr_err("Failed to setup CPU frequency to 1GHz!"); } +#define SDIO_BASE (ARC_PERIPHERAL_BASE + 0xA000) +#define SDIO_UHS_REG_EXT (SDIO_BASE + 0x108) +#define SDIO_UHS_REG_EXT_DIV_2 (2 << 30) + static void __init hsdk_init_early(void) { /* @@ -90,6 +94,12 @@ static void __init hsdk_init_early(void) writel(1, (void __iomem *) CREG_PAE_UPDATE); /* + * Switch SDIO external ciu clock divider from default div-by-8 to + * minimum possible div-by-2. + */ + iowrite32(SDIO_UHS_REG_EXT_DIV_2, (void __iomem *) SDIO_UHS_REG_EXT); + + /* * Setup CPU frequency to 1GHz. * TODO: remove it after smart hsdk pll driver will be introduced. */ diff --git a/arch/arm/Makefile b/arch/arm/Makefile index 47d3a1ab08d2..817e5cfef83a 100644 --- a/arch/arm/Makefile +++ b/arch/arm/Makefile @@ -131,7 +131,7 @@ endif KBUILD_CFLAGS +=$(CFLAGS_ABI) $(CFLAGS_ISA) $(arch-y) $(tune-y) $(call cc-option,-mshort-load-bytes,$(call cc-option,-malignment-traps,)) -msoft-float -Uarm KBUILD_AFLAGS +=$(CFLAGS_ABI) $(AFLAGS_ISA) $(arch-y) $(tune-y) -include asm/unified.h -msoft-float -CHECKFLAGS += -D__arm__ +CHECKFLAGS += -D__arm__ -m32 #Default value head-y := arch/arm/kernel/head$(MMUEXT).o diff --git a/arch/arm/boot/compressed/debug.S b/arch/arm/boot/compressed/debug.S index 5392ee63338f..8f6e37177de1 100644 --- a/arch/arm/boot/compressed/debug.S +++ b/arch/arm/boot/compressed/debug.S @@ -23,7 +23,11 @@ ENTRY(putc) strb r0, [r1] mov r0, #0x03 @ SYS_WRITEC ARM( svc #0x123456 ) +#ifdef CONFIG_CPU_V7M + THUMB( bkpt #0xab ) +#else THUMB( svc #0xab ) +#endif mov pc, lr .align 2 1: .word _GLOBAL_OFFSET_TABLE_ - . diff --git a/arch/arm/boot/dts/armada-38x.dtsi b/arch/arm/boot/dts/armada-38x.dtsi index 7ff0811e61db..4960722aab32 100644 --- a/arch/arm/boot/dts/armada-38x.dtsi +++ b/arch/arm/boot/dts/armada-38x.dtsi @@ -178,7 +178,7 @@ }; i2c0: i2c@11000 { - compatible = "marvell,mv64xxx-i2c"; + compatible = "marvell,mv78230-a0-i2c", "marvell,mv64xxx-i2c"; reg = <0x11000 0x20>; #address-cells = <1>; #size-cells = <0>; @@ -189,7 +189,7 @@ }; i2c1: i2c@11100 { - compatible = "marvell,mv64xxx-i2c"; + compatible = "marvell,mv78230-a0-i2c", "marvell,mv64xxx-i2c"; reg = <0x11100 0x20>; #address-cells = <1>; #size-cells = <0>; diff --git a/arch/arm/boot/dts/at91-sama5d27_som1.dtsi b/arch/arm/boot/dts/at91-sama5d27_som1.dtsi index 63a5af898165..cf0087b4c9e1 100644 --- a/arch/arm/boot/dts/at91-sama5d27_som1.dtsi +++ b/arch/arm/boot/dts/at91-sama5d27_som1.dtsi @@ -67,8 +67,8 @@ pinctrl-0 = <&pinctrl_macb0_default>; phy-mode = "rmii"; - ethernet-phy@1 { - reg = <0x1>; + ethernet-phy@0 { + reg = <0x0>; interrupt-parent = <&pioA>; interrupts = <PIN_PD31 IRQ_TYPE_LEVEL_LOW>; pinctrl-names = "default"; diff --git a/arch/arm/boot/dts/at91-sama5d2_xplained.dts b/arch/arm/boot/dts/at91-sama5d2_xplained.dts index c7e9ccf2bc87..cbc26001247b 100644 --- a/arch/arm/boot/dts/at91-sama5d2_xplained.dts +++ b/arch/arm/boot/dts/at91-sama5d2_xplained.dts @@ -309,7 +309,7 @@ vddana-supply = <&vdd_3v3_lp_reg>; vref-supply = <&vdd_3v3_lp_reg>; pinctrl-names = "default"; - pinctrl-0 = <&pinctrl_adc_default>; + pinctrl-0 = <&pinctrl_adc_default &pinctrl_adtrg_default>; status = "okay"; }; @@ -340,6 +340,20 @@ bias-disable; }; + /* + * The ADTRG pin can work on any edge type. + * In here it's being pulled up, so need to + * connect it to ground to get an edge e.g. + * Trigger can be configured on falling, rise + * or any edge, and the pull-up can be changed + * to pull-down or left floating according to + * needs. + */ + pinctrl_adtrg_default: adtrg_default { + pinmux = <PIN_PD31__ADTRG>; + bias-pull-up; + }; + pinctrl_charger_chglev: charger_chglev { pinmux = <PIN_PA12__GPIO>; bias-disable; diff --git a/arch/arm/boot/dts/bcm2835-rpi-zero-w.dts b/arch/arm/boot/dts/bcm2835-rpi-zero-w.dts index 82651c3eb682..b8565fc33eea 100644 --- a/arch/arm/boot/dts/bcm2835-rpi-zero-w.dts +++ b/arch/arm/boot/dts/bcm2835-rpi-zero-w.dts @@ -18,12 +18,9 @@ compatible = "raspberrypi,model-zero-w", "brcm,bcm2835"; model = "Raspberry Pi Zero W"; - /* Needed by firmware to properly init UARTs */ - aliases { - uart0 = "/soc/serial@7e201000"; - uart1 = "/soc/serial@7e215040"; - serial0 = "/soc/serial@7e201000"; - serial1 = "/soc/serial@7e215040"; + chosen { + /* 8250 auxiliary UART instead of pl011 */ + stdout-path = "serial1:115200n8"; }; leds { diff --git a/arch/arm/boot/dts/bcm2837-rpi-3-b.dts b/arch/arm/boot/dts/bcm2837-rpi-3-b.dts index 20725ca487f3..c71a0d73d2a2 100644 --- a/arch/arm/boot/dts/bcm2837-rpi-3-b.dts +++ b/arch/arm/boot/dts/bcm2837-rpi-3-b.dts @@ -8,6 +8,11 @@ compatible = "raspberrypi,3-model-b", "brcm,bcm2837"; model = "Raspberry Pi 3 Model B"; + chosen { + /* 8250 auxiliary UART instead of pl011 */ + stdout-path = "serial1:115200n8"; + }; + memory { reg = <0 0x40000000>; }; diff --git a/arch/arm/boot/dts/bcm283x.dtsi b/arch/arm/boot/dts/bcm283x.dtsi index 431dcfc900c0..013431e3d7c3 100644 --- a/arch/arm/boot/dts/bcm283x.dtsi +++ b/arch/arm/boot/dts/bcm283x.dtsi @@ -20,8 +20,13 @@ #address-cells = <1>; #size-cells = <1>; + aliases { + serial0 = &uart0; + serial1 = &uart1; + }; + chosen { - bootargs = "earlyprintk console=ttyAMA0"; + stdout-path = "serial0:115200n8"; }; thermal-zones { diff --git a/arch/arm/boot/dts/gemini.dtsi b/arch/arm/boot/dts/gemini.dtsi index c68e8d430234..f0d178c77153 100644 --- a/arch/arm/boot/dts/gemini.dtsi +++ b/arch/arm/boot/dts/gemini.dtsi @@ -145,11 +145,12 @@ }; watchdog@41000000 { - compatible = "cortina,gemini-watchdog"; + compatible = "cortina,gemini-watchdog", "faraday,ftwdt010"; reg = <0x41000000 0x1000>; interrupts = <3 IRQ_TYPE_LEVEL_HIGH>; resets = <&syscon GEMINI_RESET_WDOG>; clocks = <&syscon GEMINI_CLK_APB>; + clock-names = "PCLK"; }; uart0: serial@42000000 { diff --git a/arch/arm/boot/dts/imx7d.dtsi b/arch/arm/boot/dts/imx7d.dtsi index f46814a7ea44..4d308d17f040 100644 --- a/arch/arm/boot/dts/imx7d.dtsi +++ b/arch/arm/boot/dts/imx7d.dtsi @@ -144,10 +144,10 @@ interrupt-names = "msi"; #interrupt-cells = <1>; interrupt-map-mask = <0 0 0 0x7>; - interrupt-map = <0 0 0 1 &intc GIC_SPI 125 IRQ_TYPE_LEVEL_HIGH>, - <0 0 0 2 &intc GIC_SPI 124 IRQ_TYPE_LEVEL_HIGH>, - <0 0 0 3 &intc GIC_SPI 123 IRQ_TYPE_LEVEL_HIGH>, - <0 0 0 4 &intc GIC_SPI 122 IRQ_TYPE_LEVEL_HIGH>; + interrupt-map = <0 0 0 1 &intc GIC_SPI 122 IRQ_TYPE_LEVEL_HIGH>, + <0 0 0 2 &intc GIC_SPI 123 IRQ_TYPE_LEVEL_HIGH>, + <0 0 0 3 &intc GIC_SPI 124 IRQ_TYPE_LEVEL_HIGH>, + <0 0 0 4 &intc GIC_SPI 125 IRQ_TYPE_LEVEL_HIGH>; clocks = <&clks IMX7D_PCIE_CTRL_ROOT_CLK>, <&clks IMX7D_PLL_ENET_MAIN_100M_CLK>, <&clks IMX7D_PCIE_PHY_ROOT_CLK>; diff --git a/arch/arm/boot/dts/moxart.dtsi b/arch/arm/boot/dts/moxart.dtsi index 1f4c795d3f72..da7b3237bfe9 100644 --- a/arch/arm/boot/dts/moxart.dtsi +++ b/arch/arm/boot/dts/moxart.dtsi @@ -87,9 +87,10 @@ }; watchdog: watchdog@98500000 { - compatible = "moxa,moxart-watchdog"; + compatible = "moxa,moxart-watchdog", "faraday,ftwdt010"; reg = <0x98500000 0x10>; clocks = <&clk_apb>; + clock-names = "PCLK"; }; sdhci: sdhci@98e00000 { diff --git a/arch/arm/boot/dts/sama5d2.dtsi b/arch/arm/boot/dts/sama5d2.dtsi index 38d2216c7ead..b1a26b42d190 100644 --- a/arch/arm/boot/dts/sama5d2.dtsi +++ b/arch/arm/boot/dts/sama5d2.dtsi @@ -1430,6 +1430,7 @@ atmel,min-sample-rate-hz = <200000>; atmel,max-sample-rate-hz = <20000000>; atmel,startup-time-ms = <4>; + atmel,trigger-edge-type = <IRQ_TYPE_EDGE_RISING>; status = "disabled"; }; diff --git a/arch/arm/boot/dts/sun6i-a31.dtsi b/arch/arm/boot/dts/sun6i-a31.dtsi index b147cb0dc14b..eef072a21acc 100644 --- a/arch/arm/boot/dts/sun6i-a31.dtsi +++ b/arch/arm/boot/dts/sun6i-a31.dtsi @@ -311,8 +311,8 @@ #size-cells = <0>; reg = <0>; - tcon1_in_drc1: endpoint@0 { - reg = <0>; + tcon1_in_drc1: endpoint@1 { + reg = <1>; remote-endpoint = <&drc1_out_tcon1>; }; }; @@ -1012,8 +1012,8 @@ #size-cells = <0>; reg = <1>; - be1_out_drc1: endpoint@0 { - reg = <0>; + be1_out_drc1: endpoint@1 { + reg = <1>; remote-endpoint = <&drc1_in_be1>; }; }; @@ -1042,8 +1042,8 @@ #size-cells = <0>; reg = <0>; - drc1_in_be1: endpoint@0 { - reg = <0>; + drc1_in_be1: endpoint@1 { + reg = <1>; remote-endpoint = <&be1_out_drc1>; }; }; @@ -1053,8 +1053,8 @@ #size-cells = <0>; reg = <1>; - drc1_out_tcon1: endpoint@0 { - reg = <0>; + drc1_out_tcon1: endpoint@1 { + reg = <1>; remote-endpoint = <&tcon1_in_drc1>; }; }; diff --git a/arch/arm/kernel/debug.S b/arch/arm/kernel/debug.S index ea9646cc2a0e..0a498cb3fad8 100644 --- a/arch/arm/kernel/debug.S +++ b/arch/arm/kernel/debug.S @@ -115,7 +115,11 @@ ENTRY(printascii) mov r1, r0 mov r0, #0x04 @ SYS_WRITE0 ARM( svc #0x123456 ) +#ifdef CONFIG_CPU_V7M + THUMB( bkpt #0xab ) +#else THUMB( svc #0xab ) +#endif ret lr ENDPROC(printascii) @@ -124,7 +128,11 @@ ENTRY(printch) strb r0, [r1] mov r0, #0x03 @ SYS_WRITEC ARM( svc #0x123456 ) +#ifdef CONFIG_CPU_V7M + THUMB( bkpt #0xab ) +#else THUMB( svc #0xab ) +#endif ret lr ENDPROC(printch) diff --git a/arch/arm/mach-ux500/cpu-db8500.c b/arch/arm/mach-ux500/cpu-db8500.c index 71a34e8c345a..57058ac46f49 100644 --- a/arch/arm/mach-ux500/cpu-db8500.c +++ b/arch/arm/mach-ux500/cpu-db8500.c @@ -32,6 +32,7 @@ #include <asm/mach/arch.h> #include "db8500-regs.h" +#include "pm_domains.h" static int __init ux500_l2x0_unlock(void) { @@ -157,6 +158,9 @@ static const struct of_device_id u8500_local_bus_nodes[] = { static void __init u8500_init_machine(void) { + /* Initialize ux500 power domains */ + ux500_pm_domains_init(); + /* automatically probe child nodes of dbx5x0 devices */ if (of_machine_is_compatible("st-ericsson,u8540")) of_platform_populate(NULL, u8500_local_bus_nodes, diff --git a/arch/arm/mach-ux500/pm.c b/arch/arm/mach-ux500/pm.c index a970e7fcba9e..f6c33a0c1c61 100644 --- a/arch/arm/mach-ux500/pm.c +++ b/arch/arm/mach-ux500/pm.c @@ -19,7 +19,6 @@ #include <linux/of_address.h> #include "db8500-regs.h" -#include "pm_domains.h" /* ARM WFI Standby signal register */ #define PRCM_ARM_WFI_STANDBY (prcmu_base + 0x130) @@ -203,7 +202,4 @@ void __init ux500_pm_init(u32 phy_base, u32 size) /* Set up ux500 suspend callbacks. */ suspend_set_ops(UX500_SUSPEND_OPS); - - /* Initialize ux500 power domains */ - ux500_pm_domains_init(); } diff --git a/arch/arm/mm/nommu.c b/arch/arm/mm/nommu.c index 3b8e728cc944..91537d90f5f5 100644 --- a/arch/arm/mm/nommu.c +++ b/arch/arm/mm/nommu.c @@ -344,6 +344,11 @@ void __init arm_mm_memblock_reserve(void) * reserved here. */ #endif + /* + * In any case, always ensure address 0 is never used as many things + * get very confused if 0 is returned as a legitimate address. + */ + memblock_reserve(0, 1); } void __init adjust_lowmem_bounds(void) diff --git a/arch/arm/xen/p2m.c b/arch/arm/xen/p2m.c index e71eefa2e427..0641ba54ab62 100644 --- a/arch/arm/xen/p2m.c +++ b/arch/arm/xen/p2m.c @@ -1,7 +1,7 @@ #include <linux/bootmem.h> #include <linux/gfp.h> #include <linux/export.h> -#include <linux/rwlock.h> +#include <linux/spinlock.h> #include <linux/slab.h> #include <linux/types.h> #include <linux/dma-mapping.h> diff --git a/arch/arm64/boot/dts/allwinner/sun50i-a64-pine64.dts b/arch/arm64/boot/dts/allwinner/sun50i-a64-pine64.dts index caf8b6fbe5e3..d06e34b5d192 100644 --- a/arch/arm64/boot/dts/allwinner/sun50i-a64-pine64.dts +++ b/arch/arm64/boot/dts/allwinner/sun50i-a64-pine64.dts @@ -61,13 +61,6 @@ chosen { stdout-path = "serial0:115200n8"; }; - - reg_vcc3v3: vcc3v3 { - compatible = "regulator-fixed"; - regulator-name = "vcc3v3"; - regulator-min-microvolt = <3300000>; - regulator-max-microvolt = <3300000>; - }; }; &ehci0 { @@ -91,7 +84,7 @@ &mmc0 { pinctrl-names = "default"; pinctrl-0 = <&mmc0_pins>; - vmmc-supply = <®_vcc3v3>; + vmmc-supply = <®_dcdc1>; cd-gpios = <&pio 5 6 GPIO_ACTIVE_HIGH>; cd-inverted; disable-wp; diff --git a/arch/arm64/boot/dts/marvell/armada-cp110-master.dtsi b/arch/arm64/boot/dts/marvell/armada-cp110-master.dtsi index 8263a8a504a8..f2aa2a81de4d 100644 --- a/arch/arm64/boot/dts/marvell/armada-cp110-master.dtsi +++ b/arch/arm64/boot/dts/marvell/armada-cp110-master.dtsi @@ -336,7 +336,7 @@ /* non-prefetchable memory */ 0x82000000 0 0xf6000000 0 0xf6000000 0 0xf00000>; interrupt-map-mask = <0 0 0 0>; - interrupt-map = <0 0 0 0 &cpm_icu 0 ICU_GRP_NSR 22 IRQ_TYPE_LEVEL_HIGH>; + interrupt-map = <0 0 0 0 &cpm_icu ICU_GRP_NSR 22 IRQ_TYPE_LEVEL_HIGH>; interrupts = <ICU_GRP_NSR 22 IRQ_TYPE_LEVEL_HIGH>; num-lanes = <1>; clocks = <&cpm_clk 1 13>; @@ -362,7 +362,7 @@ /* non-prefetchable memory */ 0x82000000 0 0xf7000000 0 0xf7000000 0 0xf00000>; interrupt-map-mask = <0 0 0 0>; - interrupt-map = <0 0 0 0 &cpm_icu 0 ICU_GRP_NSR 24 IRQ_TYPE_LEVEL_HIGH>; + interrupt-map = <0 0 0 0 &cpm_icu ICU_GRP_NSR 24 IRQ_TYPE_LEVEL_HIGH>; interrupts = <ICU_GRP_NSR 24 IRQ_TYPE_LEVEL_HIGH>; num-lanes = <1>; @@ -389,7 +389,7 @@ /* non-prefetchable memory */ 0x82000000 0 0xf8000000 0 0xf8000000 0 0xf00000>; interrupt-map-mask = <0 0 0 0>; - interrupt-map = <0 0 0 0 &cpm_icu 0 ICU_GRP_NSR 23 IRQ_TYPE_LEVEL_HIGH>; + interrupt-map = <0 0 0 0 &cpm_icu ICU_GRP_NSR 23 IRQ_TYPE_LEVEL_HIGH>; interrupts = <ICU_GRP_NSR 23 IRQ_TYPE_LEVEL_HIGH>; num-lanes = <1>; diff --git a/arch/arm64/boot/dts/marvell/armada-cp110-slave.dtsi b/arch/arm64/boot/dts/marvell/armada-cp110-slave.dtsi index b71ee6c83668..4fe70323abb3 100644 --- a/arch/arm64/boot/dts/marvell/armada-cp110-slave.dtsi +++ b/arch/arm64/boot/dts/marvell/armada-cp110-slave.dtsi @@ -335,7 +335,7 @@ /* non-prefetchable memory */ 0x82000000 0 0xfa000000 0 0xfa000000 0 0xf00000>; interrupt-map-mask = <0 0 0 0>; - interrupt-map = <0 0 0 0 &cps_icu 0 ICU_GRP_NSR 22 IRQ_TYPE_LEVEL_HIGH>; + interrupt-map = <0 0 0 0 &cps_icu ICU_GRP_NSR 22 IRQ_TYPE_LEVEL_HIGH>; interrupts = <ICU_GRP_NSR 22 IRQ_TYPE_LEVEL_HIGH>; num-lanes = <1>; clocks = <&cps_clk 1 13>; @@ -361,7 +361,7 @@ /* non-prefetchable memory */ 0x82000000 0 0xfb000000 0 0xfb000000 0 0xf00000>; interrupt-map-mask = <0 0 0 0>; - interrupt-map = <0 0 0 0 &cps_icu 0 ICU_GRP_NSR 24 IRQ_TYPE_LEVEL_HIGH>; + interrupt-map = <0 0 0 0 &cps_icu ICU_GRP_NSR 24 IRQ_TYPE_LEVEL_HIGH>; interrupts = <ICU_GRP_NSR 24 IRQ_TYPE_LEVEL_HIGH>; num-lanes = <1>; @@ -388,7 +388,7 @@ /* non-prefetchable memory */ 0x82000000 0 0xfc000000 0 0xfc000000 0 0xf00000>; interrupt-map-mask = <0 0 0 0>; - interrupt-map = <0 0 0 0 &cps_icu 0 ICU_GRP_NSR 23 IRQ_TYPE_LEVEL_HIGH>; + interrupt-map = <0 0 0 0 &cps_icu ICU_GRP_NSR 23 IRQ_TYPE_LEVEL_HIGH>; interrupts = <ICU_GRP_NSR 23 IRQ_TYPE_LEVEL_HIGH>; num-lanes = <1>; diff --git a/arch/arm64/boot/dts/renesas/salvator-common.dtsi b/arch/arm64/boot/dts/renesas/salvator-common.dtsi index 4786c67b5e65..d9d885006a8e 100644 --- a/arch/arm64/boot/dts/renesas/salvator-common.dtsi +++ b/arch/arm64/boot/dts/renesas/salvator-common.dtsi @@ -62,6 +62,7 @@ brightness-levels = <256 128 64 16 8 4 0>; default-brightness-level = <6>; + power-supply = <®_12v>; enable-gpios = <&gpio6 7 GPIO_ACTIVE_HIGH>; }; @@ -83,6 +84,15 @@ regulator-always-on; }; + reg_12v: regulator2 { + compatible = "regulator-fixed"; + regulator-name = "fixed-12V"; + regulator-min-microvolt = <12000000>; + regulator-max-microvolt = <12000000>; + regulator-boot-on; + regulator-always-on; + }; + rsnd_ak4613: sound { compatible = "simple-audio-card"; diff --git a/arch/arm64/boot/dts/rockchip/rk3328.dtsi b/arch/arm64/boot/dts/rockchip/rk3328.dtsi index 6d615cb6e64d..41d61840fb99 100644 --- a/arch/arm64/boot/dts/rockchip/rk3328.dtsi +++ b/arch/arm64/boot/dts/rockchip/rk3328.dtsi @@ -582,7 +582,7 @@ vop_mmu: iommu@ff373f00 { compatible = "rockchip,iommu"; reg = <0x0 0xff373f00 0x0 0x100>; - interrupts = <GIC_SPI 32 IRQ_TYPE_LEVEL_HIGH 0>; + interrupts = <GIC_SPI 32 IRQ_TYPE_LEVEL_HIGH>; interrupt-names = "vop_mmu"; #iommu-cells = <0>; status = "disabled"; diff --git a/arch/arm64/boot/dts/rockchip/rk3368.dtsi b/arch/arm64/boot/dts/rockchip/rk3368.dtsi index 19fbaa5e7bdd..1070c8264c13 100644 --- a/arch/arm64/boot/dts/rockchip/rk3368.dtsi +++ b/arch/arm64/boot/dts/rockchip/rk3368.dtsi @@ -740,7 +740,7 @@ iep_mmu: iommu@ff900800 { compatible = "rockchip,iommu"; reg = <0x0 0xff900800 0x0 0x100>; - interrupts = <GIC_SPI 17 IRQ_TYPE_LEVEL_HIGH 0>; + interrupts = <GIC_SPI 17 IRQ_TYPE_LEVEL_HIGH>; interrupt-names = "iep_mmu"; #iommu-cells = <0>; status = "disabled"; diff --git a/arch/arm64/boot/dts/rockchip/rk3399-firefly.dts b/arch/arm64/boot/dts/rockchip/rk3399-firefly.dts index 7fd4bfcaa38e..fef82274a39d 100644 --- a/arch/arm64/boot/dts/rockchip/rk3399-firefly.dts +++ b/arch/arm64/boot/dts/rockchip/rk3399-firefly.dts @@ -371,10 +371,10 @@ regulator-always-on; regulator-boot-on; regulator-min-microvolt = <1800000>; - regulator-max-microvolt = <3300000>; + regulator-max-microvolt = <3000000>; regulator-state-mem { regulator-on-in-suspend; - regulator-suspend-microvolt = <3300000>; + regulator-suspend-microvolt = <3000000>; }; }; diff --git a/arch/arm64/boot/dts/rockchip/rk3399-puma.dtsi b/arch/arm64/boot/dts/rockchip/rk3399-puma.dtsi index 53ff3d191a1d..910628d18add 100644 --- a/arch/arm64/boot/dts/rockchip/rk3399-puma.dtsi +++ b/arch/arm64/boot/dts/rockchip/rk3399-puma.dtsi @@ -325,12 +325,12 @@ vcc_sd: LDO_REG4 { regulator-name = "vcc_sd"; regulator-min-microvolt = <1800000>; - regulator-max-microvolt = <3300000>; + regulator-max-microvolt = <3000000>; regulator-always-on; regulator-boot-on; regulator-state-mem { regulator-on-in-suspend; - regulator-suspend-microvolt = <3300000>; + regulator-suspend-microvolt = <3000000>; }; }; diff --git a/arch/arm64/boot/dts/rockchip/rk3399-sapphire.dtsi b/arch/arm64/boot/dts/rockchip/rk3399-sapphire.dtsi index 6c30bb02210d..0f873c897d0d 100644 --- a/arch/arm64/boot/dts/rockchip/rk3399-sapphire.dtsi +++ b/arch/arm64/boot/dts/rockchip/rk3399-sapphire.dtsi @@ -315,10 +315,10 @@ regulator-always-on; regulator-boot-on; regulator-min-microvolt = <1800000>; - regulator-max-microvolt = <3300000>; + regulator-max-microvolt = <3000000>; regulator-state-mem { regulator-on-in-suspend; - regulator-suspend-microvolt = <3300000>; + regulator-suspend-microvolt = <3000000>; }; }; diff --git a/arch/mips/include/asm/cmpxchg.h b/arch/mips/include/asm/cmpxchg.h index 903f3bf48419..7e25c5cc353a 100644 --- a/arch/mips/include/asm/cmpxchg.h +++ b/arch/mips/include/asm/cmpxchg.h @@ -155,14 +155,16 @@ static inline unsigned long __cmpxchg(volatile void *ptr, unsigned long old, return __cmpxchg_small(ptr, old, new, size); case 4: - return __cmpxchg_asm("ll", "sc", (volatile u32 *)ptr, old, new); + return __cmpxchg_asm("ll", "sc", (volatile u32 *)ptr, + (u32)old, new); case 8: /* lld/scd are only available for MIPS64 */ if (!IS_ENABLED(CONFIG_64BIT)) return __cmpxchg_called_with_bad_pointer(); - return __cmpxchg_asm("lld", "scd", (volatile u64 *)ptr, old, new); + return __cmpxchg_asm("lld", "scd", (volatile u64 *)ptr, + (u64)old, new); default: return __cmpxchg_called_with_bad_pointer(); diff --git a/arch/mips/loongson32/common/platform.c b/arch/mips/loongson32/common/platform.c index 100f23dfa438..ac584c5823d0 100644 --- a/arch/mips/loongson32/common/platform.c +++ b/arch/mips/loongson32/common/platform.c @@ -183,18 +183,20 @@ int ls1x_eth_mux_init(struct platform_device *pdev, void *priv) } static struct plat_stmmacenet_data ls1x_eth0_pdata = { - .bus_id = 0, - .phy_addr = -1, + .bus_id = 0, + .phy_addr = -1, #if defined(CONFIG_LOONGSON1_LS1B) - .interface = PHY_INTERFACE_MODE_MII, + .interface = PHY_INTERFACE_MODE_MII, #elif defined(CONFIG_LOONGSON1_LS1C) - .interface = PHY_INTERFACE_MODE_RMII, + .interface = PHY_INTERFACE_MODE_RMII, #endif - .mdio_bus_data = &ls1x_mdio_bus_data, - .dma_cfg = &ls1x_eth_dma_cfg, - .has_gmac = 1, - .tx_coe = 1, - .init = ls1x_eth_mux_init, + .mdio_bus_data = &ls1x_mdio_bus_data, + .dma_cfg = &ls1x_eth_dma_cfg, + .has_gmac = 1, + .tx_coe = 1, + .rx_queues_to_use = 1, + .tx_queues_to_use = 1, + .init = ls1x_eth_mux_init, }; static struct resource ls1x_eth0_resources[] = { @@ -222,14 +224,16 @@ struct platform_device ls1x_eth0_pdev = { #ifdef CONFIG_LOONGSON1_LS1B static struct plat_stmmacenet_data ls1x_eth1_pdata = { - .bus_id = 1, - .phy_addr = -1, - .interface = PHY_INTERFACE_MODE_MII, - .mdio_bus_data = &ls1x_mdio_bus_data, - .dma_cfg = &ls1x_eth_dma_cfg, - .has_gmac = 1, - .tx_coe = 1, - .init = ls1x_eth_mux_init, + .bus_id = 1, + .phy_addr = -1, + .interface = PHY_INTERFACE_MODE_MII, + .mdio_bus_data = &ls1x_mdio_bus_data, + .dma_cfg = &ls1x_eth_dma_cfg, + .has_gmac = 1, + .tx_coe = 1, + .rx_queues_to_use = 1, + .tx_queues_to_use = 1, + .init = ls1x_eth_mux_init, }; static struct resource ls1x_eth1_resources[] = { diff --git a/arch/mips/math-emu/cp1emu.c b/arch/mips/math-emu/cp1emu.c index 192542dbd972..16d9ef5a78c5 100644 --- a/arch/mips/math-emu/cp1emu.c +++ b/arch/mips/math-emu/cp1emu.c @@ -2558,7 +2558,6 @@ dcopuop: break; default: /* Reserved R6 ops */ - pr_err("Reserved MIPS R6 CMP.condn.S operation\n"); return SIGILL; } } @@ -2719,7 +2718,6 @@ dcopuop: break; default: /* Reserved R6 ops */ - pr_err("Reserved MIPS R6 CMP.condn.D operation\n"); return SIGILL; } } diff --git a/arch/mips/net/ebpf_jit.c b/arch/mips/net/ebpf_jit.c index 7646891c4e9b..01b7a87ea678 100644 --- a/arch/mips/net/ebpf_jit.c +++ b/arch/mips/net/ebpf_jit.c @@ -667,7 +667,7 @@ static int build_one_insn(const struct bpf_insn *insn, struct jit_ctx *ctx, { int src, dst, r, td, ts, mem_off, b_off; bool need_swap, did_move, cmp_eq; - unsigned int target; + unsigned int target = 0; u64 t64; s64 t64s; int bpf_op = BPF_OP(insn->code); diff --git a/arch/mips/tools/generic-board-config.sh b/arch/mips/tools/generic-board-config.sh index 5c4f93687039..654d652d7fa1 100755 --- a/arch/mips/tools/generic-board-config.sh +++ b/arch/mips/tools/generic-board-config.sh @@ -30,8 +30,6 @@ cfg="$4" boards_origin="$5" shift 5 -cd "${srctree}" - # Only print Skipping... lines if the user explicitly specified BOARDS=. In the # general case it only serves to obscure the useful output about what actually # was included. @@ -48,7 +46,7 @@ environment*) esac for board in $@; do - board_cfg="arch/mips/configs/generic/board-${board}.config" + board_cfg="${srctree}/arch/mips/configs/generic/board-${board}.config" if [ ! -f "${board_cfg}" ]; then echo "WARNING: Board config '${board_cfg}' not found" continue @@ -84,7 +82,7 @@ for board in $@; do done || continue # Merge this board config fragment into our final config file - ./scripts/kconfig/merge_config.sh \ + ${srctree}/scripts/kconfig/merge_config.sh \ -m -O ${objtree} ${cfg} ${board_cfg} \ | grep -Ev '^(#|Using)' done diff --git a/arch/parisc/kernel/parisc_ksyms.c b/arch/parisc/kernel/parisc_ksyms.c index c6d6272a934f..7baa2265d439 100644 --- a/arch/parisc/kernel/parisc_ksyms.c +++ b/arch/parisc/kernel/parisc_ksyms.c @@ -35,12 +35,12 @@ EXPORT_SYMBOL(memset); EXPORT_SYMBOL(__xchg8); EXPORT_SYMBOL(__xchg32); EXPORT_SYMBOL(__cmpxchg_u32); +EXPORT_SYMBOL(__cmpxchg_u64); #ifdef CONFIG_SMP EXPORT_SYMBOL(__atomic_hash); #endif #ifdef CONFIG_64BIT EXPORT_SYMBOL(__xchg64); -EXPORT_SYMBOL(__cmpxchg_u64); #endif #include <linux/uaccess.h> diff --git a/arch/parisc/kernel/syscall.S b/arch/parisc/kernel/syscall.S index 23de307c3052..41e60a9c7db2 100644 --- a/arch/parisc/kernel/syscall.S +++ b/arch/parisc/kernel/syscall.S @@ -742,7 +742,7 @@ lws_compare_and_swap_2: 10: ldd 0(%r25), %r25 11: ldd 0(%r24), %r24 #else - /* Load new value into r22/r23 - high/low */ + /* Load old value into r22/r23 - high/low */ 10: ldw 0(%r25), %r22 11: ldw 4(%r25), %r23 /* Load new value into fr4 for atomic store later */ @@ -834,11 +834,11 @@ cas2_action: copy %r0, %r28 #else /* Compare first word */ -19: ldw,ma 0(%r26), %r29 +19: ldw 0(%r26), %r29 sub,= %r29, %r22, %r0 b,n cas2_end /* Compare second word */ -20: ldw,ma 4(%r26), %r29 +20: ldw 4(%r26), %r29 sub,= %r29, %r23, %r0 b,n cas2_end /* Perform the store */ diff --git a/arch/parisc/kernel/time.c b/arch/parisc/kernel/time.c index 2d956aa0a38a..8c0105a49839 100644 --- a/arch/parisc/kernel/time.c +++ b/arch/parisc/kernel/time.c @@ -253,7 +253,10 @@ static int __init init_cr16_clocksource(void) cpu0_loc = per_cpu(cpu_data, 0).cpu_loc; for_each_online_cpu(cpu) { - if (cpu0_loc == per_cpu(cpu_data, cpu).cpu_loc) + if (cpu == 0) + continue; + if ((cpu0_loc != 0) && + (cpu0_loc == per_cpu(cpu_data, cpu).cpu_loc)) continue; clocksource_cr16.name = "cr16_unstable"; diff --git a/arch/powerpc/kernel/trace/ftrace_64_mprofile.S b/arch/powerpc/kernel/trace/ftrace_64_mprofile.S index c98e90b4ea7b..b4e2b7165f79 100644 --- a/arch/powerpc/kernel/trace/ftrace_64_mprofile.S +++ b/arch/powerpc/kernel/trace/ftrace_64_mprofile.S @@ -181,34 +181,25 @@ _GLOBAL(ftrace_stub) * - we have no stack frame and can not allocate one * - LR points back to the original caller (in A) * - CTR holds the new NIP in C - * - r0 & r12 are free - * - * r0 can't be used as the base register for a DS-form load or store, so - * we temporarily shuffle r1 (stack pointer) into r0 and then put it back. + * - r0, r11 & r12 are free */ livepatch_handler: CURRENT_THREAD_INFO(r12, r1) - /* Save stack pointer into r0 */ - mr r0, r1 - /* Allocate 3 x 8 bytes */ - ld r1, TI_livepatch_sp(r12) - addi r1, r1, 24 - std r1, TI_livepatch_sp(r12) + ld r11, TI_livepatch_sp(r12) + addi r11, r11, 24 + std r11, TI_livepatch_sp(r12) /* Save toc & real LR on livepatch stack */ - std r2, -24(r1) + std r2, -24(r11) mflr r12 - std r12, -16(r1) + std r12, -16(r11) /* Store stack end marker */ lis r12, STACK_END_MAGIC@h ori r12, r12, STACK_END_MAGIC@l - std r12, -8(r1) - - /* Restore real stack pointer */ - mr r1, r0 + std r12, -8(r11) /* Put ctr in r12 for global entry and branch there */ mfctr r12 @@ -216,36 +207,30 @@ livepatch_handler: /* * Now we are returning from the patched function to the original - * caller A. We are free to use r0 and r12, and we can use r2 until we + * caller A. We are free to use r11, r12 and we can use r2 until we * restore it. */ CURRENT_THREAD_INFO(r12, r1) - /* Save stack pointer into r0 */ - mr r0, r1 - - ld r1, TI_livepatch_sp(r12) + ld r11, TI_livepatch_sp(r12) /* Check stack marker hasn't been trashed */ lis r2, STACK_END_MAGIC@h ori r2, r2, STACK_END_MAGIC@l - ld r12, -8(r1) + ld r12, -8(r11) 1: tdne r12, r2 EMIT_BUG_ENTRY 1b, __FILE__, __LINE__ - 1, 0 /* Restore LR & toc from livepatch stack */ - ld r12, -16(r1) + ld r12, -16(r11) mtlr r12 - ld r2, -24(r1) + ld r2, -24(r11) /* Pop livepatch stack frame */ - CURRENT_THREAD_INFO(r12, r0) - subi r1, r1, 24 - std r1, TI_livepatch_sp(r12) - - /* Restore real stack pointer */ - mr r1, r0 + CURRENT_THREAD_INFO(r12, r1) + subi r11, r11, 24 + std r11, TI_livepatch_sp(r12) /* Return to original caller of live patched function */ blr diff --git a/arch/powerpc/kvm/book3s_64_vio.c b/arch/powerpc/kvm/book3s_64_vio.c index 8f2da8bba737..4dffa611376d 100644 --- a/arch/powerpc/kvm/book3s_64_vio.c +++ b/arch/powerpc/kvm/book3s_64_vio.c @@ -478,28 +478,30 @@ long kvmppc_h_put_tce(struct kvm_vcpu *vcpu, unsigned long liobn, return ret; dir = iommu_tce_direction(tce); + + idx = srcu_read_lock(&vcpu->kvm->srcu); + if ((dir != DMA_NONE) && kvmppc_gpa_to_ua(vcpu->kvm, - tce & ~(TCE_PCI_READ | TCE_PCI_WRITE), &ua, NULL)) - return H_PARAMETER; + tce & ~(TCE_PCI_READ | TCE_PCI_WRITE), &ua, NULL)) { + ret = H_PARAMETER; + goto unlock_exit; + } entry = ioba >> stt->page_shift; list_for_each_entry_lockless(stit, &stt->iommu_tables, next) { - if (dir == DMA_NONE) { + if (dir == DMA_NONE) ret = kvmppc_tce_iommu_unmap(vcpu->kvm, stit->tbl, entry); - } else { - idx = srcu_read_lock(&vcpu->kvm->srcu); + else ret = kvmppc_tce_iommu_map(vcpu->kvm, stit->tbl, entry, ua, dir); - srcu_read_unlock(&vcpu->kvm->srcu, idx); - } if (ret == H_SUCCESS) continue; if (ret == H_TOO_HARD) - return ret; + goto unlock_exit; WARN_ON_ONCE(1); kvmppc_clear_tce(stit->tbl, entry); @@ -507,7 +509,10 @@ long kvmppc_h_put_tce(struct kvm_vcpu *vcpu, unsigned long liobn, kvmppc_tce_put(stt, entry, tce); - return H_SUCCESS; +unlock_exit: + srcu_read_unlock(&vcpu->kvm->srcu, idx); + + return ret; } EXPORT_SYMBOL_GPL(kvmppc_h_put_tce); diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S index ec69fa45d5a2..42639fba89e8 100644 --- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S +++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S @@ -989,13 +989,14 @@ ALT_FTR_SECTION_END_IFCLR(CPU_FTR_ARCH_300) beq no_xive ld r11, VCPU_XIVE_SAVED_STATE(r4) li r9, TM_QW1_OS - stdcix r11,r9,r10 eieio + stdcix r11,r9,r10 lwz r11, VCPU_XIVE_CAM_WORD(r4) li r9, TM_QW1_OS + TM_WORD2 stwcix r11,r9,r10 li r9, 1 stw r9, VCPU_XIVE_PUSHED(r4) + eieio no_xive: #endif /* CONFIG_KVM_XICS */ @@ -1310,6 +1311,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR) bne 3f BEGIN_FTR_SECTION PPC_MSGSYNC + lwsync END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300) lbz r0, HSTATE_HOST_IPI(r13) cmpwi r0, 0 @@ -1400,8 +1402,8 @@ guest_exit_cont: /* r9 = vcpu, r12 = trap, r13 = paca */ cmpldi cr0, r10, 0 beq 1f /* First load to pull the context, we ignore the value */ - lwzx r11, r7, r10 eieio + lwzx r11, r7, r10 /* Second load to recover the context state (Words 0 and 1) */ ldx r11, r6, r10 b 3f @@ -1409,8 +1411,8 @@ guest_exit_cont: /* r9 = vcpu, r12 = trap, r13 = paca */ cmpldi cr0, r10, 0 beq 1f /* First load to pull the context, we ignore the value */ - lwzcix r11, r7, r10 eieio + lwzcix r11, r7, r10 /* Second load to recover the context state (Words 0 and 1) */ ldcix r11, r6, r10 3: std r11, VCPU_XIVE_SAVED_STATE(r9) @@ -1420,6 +1422,7 @@ guest_exit_cont: /* r9 = vcpu, r12 = trap, r13 = paca */ stw r10, VCPU_XIVE_PUSHED(r9) stb r10, (VCPU_XIVE_SAVED_STATE+3)(r9) stb r0, (VCPU_XIVE_SAVED_STATE+4)(r9) + eieio 1: #endif /* CONFIG_KVM_XICS */ /* Save more register state */ @@ -2788,6 +2791,10 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S) PPC_MSGCLR(6) /* see if it's a host IPI */ li r3, 1 +BEGIN_FTR_SECTION + PPC_MSGSYNC + lwsync +END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300) lbz r0, HSTATE_HOST_IPI(r13) cmpwi r0, 0 bnelr diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c index 3480faaf1ef8..ee279c7f4802 100644 --- a/arch/powerpc/kvm/powerpc.c +++ b/arch/powerpc/kvm/powerpc.c @@ -644,8 +644,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) break; #endif case KVM_CAP_PPC_HTM: - r = cpu_has_feature(CPU_FTR_TM_COMP) && - is_kvmppc_hv_enabled(kvm); + r = cpu_has_feature(CPU_FTR_TM_COMP) && hv_enabled; break; default: r = 0; diff --git a/arch/powerpc/lib/sstep.c b/arch/powerpc/lib/sstep.c index 5e8418c28bd8..f208f560aecd 100644 --- a/arch/powerpc/lib/sstep.c +++ b/arch/powerpc/lib/sstep.c @@ -1684,11 +1684,13 @@ int analyse_instr(struct instruction_op *op, const struct pt_regs *regs, * Logical instructions */ case 26: /* cntlzw */ - op->val = __builtin_clz((unsigned int) regs->gpr[rd]); + val = (unsigned int) regs->gpr[rd]; + op->val = ( val ? __builtin_clz(val) : 32 ); goto logical_done; #ifdef __powerpc64__ case 58: /* cntlzd */ - op->val = __builtin_clzl(regs->gpr[rd]); + val = regs->gpr[rd]; + op->val = ( val ? __builtin_clzl(val) : 64 ); goto logical_done; #endif case 28: /* and */ diff --git a/arch/powerpc/mm/numa.c b/arch/powerpc/mm/numa.c index b95c584ce19d..a51df9ef529d 100644 --- a/arch/powerpc/mm/numa.c +++ b/arch/powerpc/mm/numa.c @@ -1438,7 +1438,6 @@ out: int arch_update_cpu_topology(void) { - lockdep_assert_cpus_held(); return numa_update_cpu_topology(true); } diff --git a/arch/powerpc/perf/imc-pmu.c b/arch/powerpc/perf/imc-pmu.c index 9ccac86f3463..88126245881b 100644 --- a/arch/powerpc/perf/imc-pmu.c +++ b/arch/powerpc/perf/imc-pmu.c @@ -399,6 +399,20 @@ static void nest_imc_counters_release(struct perf_event *event) /* Take the mutex lock for this node and then decrement the reference count */ mutex_lock(&ref->lock); + if (ref->refc == 0) { + /* + * The scenario where this is true is, when perf session is + * started, followed by offlining of all cpus in a given node. + * + * In the cpuhotplug offline path, ppc_nest_imc_cpu_offline() + * function set the ref->count to zero, if the cpu which is + * about to offline is the last cpu in a given node and make + * an OPAL call to disable the engine in that node. + * + */ + mutex_unlock(&ref->lock); + return; + } ref->refc--; if (ref->refc == 0) { rc = opal_imc_counters_stop(OPAL_IMC_COUNTERS_NEST, @@ -523,8 +537,8 @@ static int core_imc_mem_init(int cpu, int size) /* We need only vbase for core counters */ mem_info->vbase = page_address(alloc_pages_node(phys_id, - GFP_KERNEL | __GFP_ZERO | __GFP_THISNODE, - get_order(size))); + GFP_KERNEL | __GFP_ZERO | __GFP_THISNODE | + __GFP_NOWARN, get_order(size))); if (!mem_info->vbase) return -ENOMEM; @@ -646,6 +660,20 @@ static void core_imc_counters_release(struct perf_event *event) return; mutex_lock(&ref->lock); + if (ref->refc == 0) { + /* + * The scenario where this is true is, when perf session is + * started, followed by offlining of all cpus in a given core. + * + * In the cpuhotplug offline path, ppc_core_imc_cpu_offline() + * function set the ref->count to zero, if the cpu which is + * about to offline is the last cpu in a given core and make + * an OPAL call to disable the engine in that core. + * + */ + mutex_unlock(&ref->lock); + return; + } ref->refc--; if (ref->refc == 0) { rc = opal_imc_counters_stop(OPAL_IMC_COUNTERS_CORE, @@ -763,8 +791,8 @@ static int thread_imc_mem_alloc(int cpu_id, int size) * free the memory in cpu offline path. */ local_mem = page_address(alloc_pages_node(phys_id, - GFP_KERNEL | __GFP_ZERO | __GFP_THISNODE, - get_order(size))); + GFP_KERNEL | __GFP_ZERO | __GFP_THISNODE | + __GFP_NOWARN, get_order(size))); if (!local_mem) return -ENOMEM; @@ -1148,7 +1176,8 @@ static void imc_common_cpuhp_mem_free(struct imc_pmu *pmu_ptr) } /* Only free the attr_groups which are dynamically allocated */ - kfree(pmu_ptr->attr_groups[IMC_EVENT_ATTR]->attrs); + if (pmu_ptr->attr_groups[IMC_EVENT_ATTR]) + kfree(pmu_ptr->attr_groups[IMC_EVENT_ATTR]->attrs); kfree(pmu_ptr->attr_groups[IMC_EVENT_ATTR]); kfree(pmu_ptr); return; diff --git a/arch/s390/configs/zfcpdump_defconfig b/arch/s390/configs/zfcpdump_defconfig index afa46a7406ea..04e042edbab7 100644 --- a/arch/s390/configs/zfcpdump_defconfig +++ b/arch/s390/configs/zfcpdump_defconfig @@ -27,6 +27,7 @@ CONFIG_NET=y CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug" CONFIG_DEVTMPFS=y # CONFIG_FIRMWARE_IN_KERNEL is not set +CONFIG_BLK_DEV_RAM=y # CONFIG_BLK_DEV_XPRAM is not set # CONFIG_DCSSBLK is not set # CONFIG_DASD is not set @@ -59,6 +60,7 @@ CONFIG_CONFIGFS_FS=y # CONFIG_NETWORK_FILESYSTEMS is not set CONFIG_PRINTK_TIME=y CONFIG_DEBUG_INFO=y +CONFIG_DEBUG_FS=y CONFIG_DEBUG_KERNEL=y CONFIG_PANIC_ON_OOPS=y # CONFIG_SCHED_DEBUG is not set diff --git a/arch/s390/kernel/entry.S b/arch/s390/kernel/entry.S index 21900e1cee9c..d185aa3965bf 100644 --- a/arch/s390/kernel/entry.S +++ b/arch/s390/kernel/entry.S @@ -521,12 +521,15 @@ ENTRY(pgm_check_handler) tmhh %r8,0x0001 # test problem state bit jnz 2f # -> fault in user space #if IS_ENABLED(CONFIG_KVM) - # cleanup critical section for sie64a + # cleanup critical section for program checks in sie64a lgr %r14,%r9 slg %r14,BASED(.Lsie_critical_start) clg %r14,BASED(.Lsie_critical_length) jhe 0f - brasl %r14,.Lcleanup_sie + lg %r14,__SF_EMPTY(%r15) # get control block pointer + ni __SIE_PROG0C+3(%r14),0xfe # no longer in SIE + lctlg %c1,%c1,__LC_USER_ASCE # load primary asce + larl %r9,sie_exit # skip forward to sie_exit #endif 0: tmhh %r8,0x4000 # PER bit set in old PSW ? jnz 1f # -> enabled, can't be a double fault diff --git a/arch/s390/kernel/smp.c b/arch/s390/kernel/smp.c index 1cee6753d47a..495ff6959dec 100644 --- a/arch/s390/kernel/smp.c +++ b/arch/s390/kernel/smp.c @@ -293,7 +293,10 @@ static void pcpu_attach_task(struct pcpu *pcpu, struct task_struct *tsk) lc->lpp = LPP_MAGIC; lc->current_pid = tsk->pid; lc->user_timer = tsk->thread.user_timer; + lc->guest_timer = tsk->thread.guest_timer; lc->system_timer = tsk->thread.system_timer; + lc->hardirq_timer = tsk->thread.hardirq_timer; + lc->softirq_timer = tsk->thread.softirq_timer; lc->steal_timer = 0; } diff --git a/arch/x86/crypto/chacha20-avx2-x86_64.S b/arch/x86/crypto/chacha20-avx2-x86_64.S index 3a2dc3dc6cac..f3cd26f48332 100644 --- a/arch/x86/crypto/chacha20-avx2-x86_64.S +++ b/arch/x86/crypto/chacha20-avx2-x86_64.S @@ -45,7 +45,7 @@ ENTRY(chacha20_8block_xor_avx2) vzeroupper # 4 * 32 byte stack, 32-byte aligned - mov %rsp, %r8 + lea 8(%rsp),%r10 and $~31, %rsp sub $0x80, %rsp @@ -443,6 +443,6 @@ ENTRY(chacha20_8block_xor_avx2) vmovdqu %ymm15,0x01e0(%rsi) vzeroupper - mov %r8,%rsp + lea -8(%r10),%rsp ret ENDPROC(chacha20_8block_xor_avx2) diff --git a/arch/x86/crypto/chacha20-ssse3-x86_64.S b/arch/x86/crypto/chacha20-ssse3-x86_64.S index 3f511a7d73b8..512a2b500fd1 100644 --- a/arch/x86/crypto/chacha20-ssse3-x86_64.S +++ b/arch/x86/crypto/chacha20-ssse3-x86_64.S @@ -160,7 +160,7 @@ ENTRY(chacha20_4block_xor_ssse3) # done with the slightly better performing SSSE3 byte shuffling, # 7/12-bit word rotation uses traditional shift+OR. - mov %rsp,%r11 + lea 8(%rsp),%r10 sub $0x80,%rsp and $~63,%rsp @@ -625,6 +625,6 @@ ENTRY(chacha20_4block_xor_ssse3) pxor %xmm1,%xmm15 movdqu %xmm15,0xf0(%rsi) - mov %r11,%rsp + lea -8(%r10),%rsp ret ENDPROC(chacha20_4block_xor_ssse3) diff --git a/arch/x86/entry/entry_32.S b/arch/x86/entry/entry_32.S index 8a13d468635a..50e0d2bc4528 100644 --- a/arch/x86/entry/entry_32.S +++ b/arch/x86/entry/entry_32.S @@ -176,7 +176,7 @@ /* * This is a sneaky trick to help the unwinder find pt_regs on the stack. The * frame pointer is replaced with an encoded pointer to pt_regs. The encoding - * is just setting the LSB, which makes it an invalid stack address and is also + * is just clearing the MSB, which makes it an invalid stack address and is also * a signal to the unwinder that it's a pt_regs pointer in disguise. * * NOTE: This macro must be used *after* SAVE_ALL because it corrupts the @@ -185,7 +185,7 @@ .macro ENCODE_FRAME_POINTER #ifdef CONFIG_FRAME_POINTER mov %esp, %ebp - orl $0x1, %ebp + andl $0x7fffffff, %ebp #endif .endm diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S index 49167258d587..f6cdb7a1455e 100644 --- a/arch/x86/entry/entry_64.S +++ b/arch/x86/entry/entry_64.S @@ -808,7 +808,7 @@ apicinterrupt IRQ_WORK_VECTOR irq_work_interrupt smp_irq_work_interrupt .macro idtentry sym do_sym has_error_code:req paranoid=0 shift_ist=-1 ENTRY(\sym) - UNWIND_HINT_IRET_REGS offset=8 + UNWIND_HINT_IRET_REGS offset=\has_error_code*8 /* Sanity check */ .if \shift_ist != -1 && \paranoid == 0 diff --git a/arch/x86/events/intel/bts.c b/arch/x86/events/intel/bts.c index 16076eb34699..141e07b06216 100644 --- a/arch/x86/events/intel/bts.c +++ b/arch/x86/events/intel/bts.c @@ -546,9 +546,6 @@ static int bts_event_init(struct perf_event *event) if (event->attr.type != bts_pmu.type) return -ENOENT; - if (x86_add_exclusive(x86_lbr_exclusive_bts)) - return -EBUSY; - /* * BTS leaks kernel addresses even when CPL0 tracing is * disabled, so disallow intel_bts driver for unprivileged @@ -562,6 +559,9 @@ static int bts_event_init(struct perf_event *event) !capable(CAP_SYS_ADMIN)) return -EACCES; + if (x86_add_exclusive(x86_lbr_exclusive_bts)) + return -EBUSY; + ret = x86_reserve_hardware(); if (ret) { x86_del_exclusive(x86_lbr_exclusive_bts); diff --git a/arch/x86/events/intel/uncore.c b/arch/x86/events/intel/uncore.c index 1c5390f1cf09..d45e06346f14 100644 --- a/arch/x86/events/intel/uncore.c +++ b/arch/x86/events/intel/uncore.c @@ -822,7 +822,7 @@ static int __init uncore_type_init(struct intel_uncore_type *type, bool setid) pmus[i].type = type; pmus[i].boxes = kzalloc(size, GFP_KERNEL); if (!pmus[i].boxes) - return -ENOMEM; + goto err; } type->pmus = pmus; @@ -836,7 +836,7 @@ static int __init uncore_type_init(struct intel_uncore_type *type, bool setid) attr_group = kzalloc(sizeof(struct attribute *) * (i + 1) + sizeof(*attr_group), GFP_KERNEL); if (!attr_group) - return -ENOMEM; + goto err; attrs = (struct attribute **)(attr_group + 1); attr_group->name = "events"; @@ -849,7 +849,15 @@ static int __init uncore_type_init(struct intel_uncore_type *type, bool setid) } type->pmu_group = &uncore_pmu_attr_group; + return 0; + +err: + for (i = 0; i < type->num_boxes; i++) + kfree(pmus[i].boxes); + kfree(pmus); + + return -ENOMEM; } static int __init diff --git a/arch/x86/hyperv/hv_init.c b/arch/x86/hyperv/hv_init.c index 1a8eb550c40f..a5db63f728a2 100644 --- a/arch/x86/hyperv/hv_init.c +++ b/arch/x86/hyperv/hv_init.c @@ -85,6 +85,8 @@ EXPORT_SYMBOL_GPL(hyperv_cs); u32 *hv_vp_index; EXPORT_SYMBOL_GPL(hv_vp_index); +u32 hv_max_vp_index; + static int hv_cpu_init(unsigned int cpu) { u64 msr_vp_index; @@ -93,6 +95,9 @@ static int hv_cpu_init(unsigned int cpu) hv_vp_index[smp_processor_id()] = msr_vp_index; + if (msr_vp_index > hv_max_vp_index) + hv_max_vp_index = msr_vp_index; + return 0; } diff --git a/arch/x86/hyperv/mmu.c b/arch/x86/hyperv/mmu.c index 39e7f6e50919..9cc9e1c1e2db 100644 --- a/arch/x86/hyperv/mmu.c +++ b/arch/x86/hyperv/mmu.c @@ -36,9 +36,9 @@ struct hv_flush_pcpu_ex { /* Each gva in gva_list encodes up to 4096 pages to flush */ #define HV_TLB_FLUSH_UNIT (4096 * PAGE_SIZE) -static struct hv_flush_pcpu __percpu *pcpu_flush; +static struct hv_flush_pcpu __percpu **pcpu_flush; -static struct hv_flush_pcpu_ex __percpu *pcpu_flush_ex; +static struct hv_flush_pcpu_ex __percpu **pcpu_flush_ex; /* * Fills in gva_list starting from offset. Returns the number of items added. @@ -76,6 +76,18 @@ static inline int cpumask_to_vp_set(struct hv_flush_pcpu_ex *flush, { int cpu, vcpu, vcpu_bank, vcpu_offset, nr_bank = 1; + /* valid_bank_mask can represent up to 64 banks */ + if (hv_max_vp_index / 64 >= 64) + return 0; + + /* + * Clear all banks up to the maximum possible bank as hv_flush_pcpu_ex + * structs are not cleared between calls, we risk flushing unneeded + * vCPUs otherwise. + */ + for (vcpu_bank = 0; vcpu_bank <= hv_max_vp_index / 64; vcpu_bank++) + flush->hv_vp_set.bank_contents[vcpu_bank] = 0; + /* * Some banks may end up being empty but this is acceptable. */ @@ -83,11 +95,6 @@ static inline int cpumask_to_vp_set(struct hv_flush_pcpu_ex *flush, vcpu = hv_cpu_number_to_vp_number(cpu); vcpu_bank = vcpu / 64; vcpu_offset = vcpu % 64; - - /* valid_bank_mask can represent up to 64 banks */ - if (vcpu_bank >= 64) - return 0; - __set_bit(vcpu_offset, (unsigned long *) &flush->hv_vp_set.bank_contents[vcpu_bank]); if (vcpu_bank >= nr_bank) @@ -102,6 +109,7 @@ static void hyperv_flush_tlb_others(const struct cpumask *cpus, const struct flush_tlb_info *info) { int cpu, vcpu, gva_n, max_gvas; + struct hv_flush_pcpu **flush_pcpu; struct hv_flush_pcpu *flush; u64 status = U64_MAX; unsigned long flags; @@ -116,7 +124,17 @@ static void hyperv_flush_tlb_others(const struct cpumask *cpus, local_irq_save(flags); - flush = this_cpu_ptr(pcpu_flush); + flush_pcpu = this_cpu_ptr(pcpu_flush); + + if (unlikely(!*flush_pcpu)) + *flush_pcpu = page_address(alloc_page(GFP_ATOMIC)); + + flush = *flush_pcpu; + + if (unlikely(!flush)) { + local_irq_restore(flags); + goto do_native; + } if (info->mm) { flush->address_space = virt_to_phys(info->mm->pgd); @@ -173,6 +191,7 @@ static void hyperv_flush_tlb_others_ex(const struct cpumask *cpus, const struct flush_tlb_info *info) { int nr_bank = 0, max_gvas, gva_n; + struct hv_flush_pcpu_ex **flush_pcpu; struct hv_flush_pcpu_ex *flush; u64 status = U64_MAX; unsigned long flags; @@ -187,7 +206,17 @@ static void hyperv_flush_tlb_others_ex(const struct cpumask *cpus, local_irq_save(flags); - flush = this_cpu_ptr(pcpu_flush_ex); + flush_pcpu = this_cpu_ptr(pcpu_flush_ex); + + if (unlikely(!*flush_pcpu)) + *flush_pcpu = page_address(alloc_page(GFP_ATOMIC)); + + flush = *flush_pcpu; + + if (unlikely(!flush)) { + local_irq_restore(flags); + goto do_native; + } if (info->mm) { flush->address_space = virt_to_phys(info->mm->pgd); @@ -222,18 +251,18 @@ static void hyperv_flush_tlb_others_ex(const struct cpumask *cpus, flush->flags |= HV_FLUSH_NON_GLOBAL_MAPPINGS_ONLY; status = hv_do_rep_hypercall( HVCALL_FLUSH_VIRTUAL_ADDRESS_SPACE_EX, - 0, nr_bank + 2, flush, NULL); + 0, nr_bank, flush, NULL); } else if (info->end && ((info->end - info->start)/HV_TLB_FLUSH_UNIT) > max_gvas) { status = hv_do_rep_hypercall( HVCALL_FLUSH_VIRTUAL_ADDRESS_SPACE_EX, - 0, nr_bank + 2, flush, NULL); + 0, nr_bank, flush, NULL); } else { gva_n = fill_gva_list(flush->gva_list, nr_bank, info->start, info->end); status = hv_do_rep_hypercall( HVCALL_FLUSH_VIRTUAL_ADDRESS_LIST_EX, - gva_n, nr_bank + 2, flush, NULL); + gva_n, nr_bank, flush, NULL); } local_irq_restore(flags); @@ -266,7 +295,7 @@ void hyper_alloc_mmu(void) return; if (!(ms_hyperv.hints & HV_X64_EX_PROCESSOR_MASKS_RECOMMENDED)) - pcpu_flush = __alloc_percpu(PAGE_SIZE, PAGE_SIZE); + pcpu_flush = alloc_percpu(struct hv_flush_pcpu *); else - pcpu_flush_ex = __alloc_percpu(PAGE_SIZE, PAGE_SIZE); + pcpu_flush_ex = alloc_percpu(struct hv_flush_pcpu_ex *); } diff --git a/arch/x86/include/asm/alternative-asm.h b/arch/x86/include/asm/alternative-asm.h index e7636bac7372..6c98821fef5e 100644 --- a/arch/x86/include/asm/alternative-asm.h +++ b/arch/x86/include/asm/alternative-asm.h @@ -62,8 +62,10 @@ #define new_len2 145f-144f /* - * max without conditionals. Idea adapted from: + * gas compatible max based on the idea from: * http://graphics.stanford.edu/~seander/bithacks.html#IntegerMinOrMax + * + * The additional "-" is needed because gas uses a "true" value of -1. */ #define alt_max_short(a, b) ((a) ^ (((a) ^ (b)) & -(-((a) < (b))))) diff --git a/arch/x86/include/asm/alternative.h b/arch/x86/include/asm/alternative.h index c096624137ae..ccbe24e697c4 100644 --- a/arch/x86/include/asm/alternative.h +++ b/arch/x86/include/asm/alternative.h @@ -103,12 +103,12 @@ static inline int alternatives_text_reserved(void *start, void *end) alt_end_marker ":\n" /* - * max without conditionals. Idea adapted from: + * gas compatible max based on the idea from: * http://graphics.stanford.edu/~seander/bithacks.html#IntegerMinOrMax * - * The additional "-" is needed because gas works with s32s. + * The additional "-" is needed because gas uses a "true" value of -1. */ -#define alt_max_short(a, b) "((" a ") ^ (((" a ") ^ (" b ")) & -(-((" a ") - (" b ")))))" +#define alt_max_short(a, b) "((" a ") ^ (((" a ") ^ (" b ")) & -(-((" a ") < (" b ")))))" /* * Pad the second replacement alternative with additional NOPs if it is diff --git a/arch/x86/include/asm/mce.h b/arch/x86/include/asm/mce.h index 181264989db5..8edac1de2e35 100644 --- a/arch/x86/include/asm/mce.h +++ b/arch/x86/include/asm/mce.h @@ -187,7 +187,6 @@ struct mca_msr_regs { extern struct mce_vendor_flags mce_flags; -extern struct mca_config mca_cfg; extern struct mca_msr_regs msr_ops; enum mce_notifier_prios { diff --git a/arch/x86/include/asm/mmu_context.h b/arch/x86/include/asm/mmu_context.h index c120b5db178a..3c856a15b98e 100644 --- a/arch/x86/include/asm/mmu_context.h +++ b/arch/x86/include/asm/mmu_context.h @@ -126,13 +126,7 @@ static inline void switch_ldt(struct mm_struct *prev, struct mm_struct *next) DEBUG_LOCKS_WARN_ON(preemptible()); } -static inline void enter_lazy_tlb(struct mm_struct *mm, struct task_struct *tsk) -{ - int cpu = smp_processor_id(); - - if (cpumask_test_cpu(cpu, mm_cpumask(mm))) - cpumask_clear_cpu(cpu, mm_cpumask(mm)); -} +void enter_lazy_tlb(struct mm_struct *mm, struct task_struct *tsk); static inline int init_new_context(struct task_struct *tsk, struct mm_struct *mm) diff --git a/arch/x86/include/asm/mshyperv.h b/arch/x86/include/asm/mshyperv.h index 738503e1f80c..530f448fddaf 100644 --- a/arch/x86/include/asm/mshyperv.h +++ b/arch/x86/include/asm/mshyperv.h @@ -289,6 +289,7 @@ static inline u64 hv_do_rep_hypercall(u16 code, u16 rep_count, u16 varhead_size, * to this information. */ extern u32 *hv_vp_index; +extern u32 hv_max_vp_index; /** * hv_cpu_number_to_vp_number() - Map CPU to VP. diff --git a/arch/x86/include/asm/tlbflush.h b/arch/x86/include/asm/tlbflush.h index 4893abf7f74f..c4aed0de565e 100644 --- a/arch/x86/include/asm/tlbflush.h +++ b/arch/x86/include/asm/tlbflush.h @@ -82,6 +82,22 @@ static inline u64 inc_mm_tlb_gen(struct mm_struct *mm) #define __flush_tlb_single(addr) __native_flush_tlb_single(addr) #endif +static inline bool tlb_defer_switch_to_init_mm(void) +{ + /* + * If we have PCID, then switching to init_mm is reasonably + * fast. If we don't have PCID, then switching to init_mm is + * quite slow, so we try to defer it in the hopes that we can + * avoid it entirely. The latter approach runs the risk of + * receiving otherwise unnecessary IPIs. + * + * This choice is just a heuristic. The tlb code can handle this + * function returning true or false regardless of whether we have + * PCID. + */ + return !static_cpu_has(X86_FEATURE_PCID); +} + /* * 6 because 6 should be plenty and struct tlb_state will fit in * two cache lines. @@ -105,6 +121,23 @@ struct tlb_state { u16 next_asid; /* + * We can be in one of several states: + * + * - Actively using an mm. Our CPU's bit will be set in + * mm_cpumask(loaded_mm) and is_lazy == false; + * + * - Not using a real mm. loaded_mm == &init_mm. Our CPU's bit + * will not be set in mm_cpumask(&init_mm) and is_lazy == false. + * + * - Lazily using a real mm. loaded_mm != &init_mm, our bit + * is set in mm_cpumask(loaded_mm), but is_lazy == true. + * We're heuristically guessing that the CR3 load we + * skipped more than makes up for the overhead added by + * lazy mode. + */ + bool is_lazy; + + /* * Access to this CR4 shadow and to H/W CR4 is protected by * disabling interrupts when modifying either one. */ diff --git a/arch/x86/kernel/amd_nb.c b/arch/x86/kernel/amd_nb.c index 458da8509b75..6db28f17ff28 100644 --- a/arch/x86/kernel/amd_nb.c +++ b/arch/x86/kernel/amd_nb.c @@ -27,6 +27,8 @@ static const struct pci_device_id amd_root_ids[] = { {} }; +#define PCI_DEVICE_ID_AMD_CNB17H_F4 0x1704 + const struct pci_device_id amd_nb_misc_ids[] = { { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_K8_NB_MISC) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_10H_NB_MISC) }, @@ -37,6 +39,7 @@ const struct pci_device_id amd_nb_misc_ids[] = { { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_16H_NB_F3) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_16H_M30H_NB_F3) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_DF_F3) }, + { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_CNB17H_F3) }, {} }; EXPORT_SYMBOL_GPL(amd_nb_misc_ids); @@ -48,6 +51,7 @@ static const struct pci_device_id amd_nb_link_ids[] = { { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_16H_NB_F4) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_16H_M30H_NB_F4) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_DF_F4) }, + { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_CNB17H_F4) }, {} }; @@ -402,11 +406,48 @@ void amd_flush_garts(void) } EXPORT_SYMBOL_GPL(amd_flush_garts); +static void __fix_erratum_688(void *info) +{ +#define MSR_AMD64_IC_CFG 0xC0011021 + + msr_set_bit(MSR_AMD64_IC_CFG, 3); + msr_set_bit(MSR_AMD64_IC_CFG, 14); +} + +/* Apply erratum 688 fix so machines without a BIOS fix work. */ +static __init void fix_erratum_688(void) +{ + struct pci_dev *F4; + u32 val; + + if (boot_cpu_data.x86 != 0x14) + return; + + if (!amd_northbridges.num) + return; + + F4 = node_to_amd_nb(0)->link; + if (!F4) + return; + + if (pci_read_config_dword(F4, 0x164, &val)) + return; + + if (val & BIT(2)) + return; + + on_each_cpu(__fix_erratum_688, NULL, 0); + + pr_info("x86/cpu/AMD: CPU erratum 688 worked around\n"); +} + static __init int init_amd_nbs(void) { amd_cache_northbridges(); amd_cache_gart(); + fix_erratum_688(); + return 0; } diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c index d705c769f77d..ff891772c9f8 100644 --- a/arch/x86/kernel/apic/apic.c +++ b/arch/x86/kernel/apic/apic.c @@ -573,11 +573,21 @@ static u32 bdx_deadline_rev(void) return ~0U; } +static u32 skx_deadline_rev(void) +{ + switch (boot_cpu_data.x86_mask) { + case 0x03: return 0x01000136; + case 0x04: return 0x02000014; + } + + return ~0U; +} + static const struct x86_cpu_id deadline_match[] = { DEADLINE_MODEL_MATCH_FUNC( INTEL_FAM6_HASWELL_X, hsx_deadline_rev), DEADLINE_MODEL_MATCH_REV ( INTEL_FAM6_BROADWELL_X, 0x0b000020), DEADLINE_MODEL_MATCH_FUNC( INTEL_FAM6_BROADWELL_XEON_D, bdx_deadline_rev), - DEADLINE_MODEL_MATCH_REV ( INTEL_FAM6_SKYLAKE_X, 0x02000014), + DEADLINE_MODEL_MATCH_FUNC( INTEL_FAM6_SKYLAKE_X, skx_deadline_rev), DEADLINE_MODEL_MATCH_REV ( INTEL_FAM6_HASWELL_CORE, 0x22), DEADLINE_MODEL_MATCH_REV ( INTEL_FAM6_HASWELL_ULT, 0x20), @@ -600,7 +610,8 @@ static void apic_check_deadline_errata(void) const struct x86_cpu_id *m; u32 rev; - if (!boot_cpu_has(X86_FEATURE_TSC_DEADLINE_TIMER)) + if (!boot_cpu_has(X86_FEATURE_TSC_DEADLINE_TIMER) || + boot_cpu_has(X86_FEATURE_HYPERVISOR)) return; m = x86_match_cpu(deadline_match); diff --git a/arch/x86/kernel/cpu/intel_cacheinfo.c b/arch/x86/kernel/cpu/intel_cacheinfo.c index 24f749324c0f..9990a71e311f 100644 --- a/arch/x86/kernel/cpu/intel_cacheinfo.c +++ b/arch/x86/kernel/cpu/intel_cacheinfo.c @@ -831,7 +831,6 @@ static int __cache_amd_cpumap_setup(unsigned int cpu, int index, } else if (boot_cpu_has(X86_FEATURE_TOPOEXT)) { unsigned int apicid, nshared, first, last; - this_leaf = this_cpu_ci->info_list + index; nshared = base->eax.split.num_threads_sharing + 1; apicid = cpu_data(cpu).apicid; first = apicid - (apicid % nshared); diff --git a/arch/x86/kernel/cpu/mcheck/mce-internal.h b/arch/x86/kernel/cpu/mcheck/mce-internal.h index 098530a93bb7..debb974fd17d 100644 --- a/arch/x86/kernel/cpu/mcheck/mce-internal.h +++ b/arch/x86/kernel/cpu/mcheck/mce-internal.h @@ -1,3 +1,6 @@ +#ifndef __X86_MCE_INTERNAL_H__ +#define __X86_MCE_INTERNAL_H__ + #include <linux/device.h> #include <asm/mce.h> @@ -108,3 +111,7 @@ static inline void mce_work_trigger(void) { } static inline void mce_register_injector_chain(struct notifier_block *nb) { } static inline void mce_unregister_injector_chain(struct notifier_block *nb) { } #endif + +extern struct mca_config mca_cfg; + +#endif /* __X86_MCE_INTERNAL_H__ */ diff --git a/arch/x86/kernel/cpu/mcheck/mce_amd.c b/arch/x86/kernel/cpu/mcheck/mce_amd.c index 40e28ed77fbf..486f640b02ef 100644 --- a/arch/x86/kernel/cpu/mcheck/mce_amd.c +++ b/arch/x86/kernel/cpu/mcheck/mce_amd.c @@ -28,6 +28,8 @@ #include <asm/msr.h> #include <asm/trace/irq_vectors.h> +#include "mce-internal.h" + #define NR_BLOCKS 5 #define THRESHOLD_MAX 0xFFF #define INT_TYPE_APIC 0x00020000 diff --git a/arch/x86/kernel/cpu/microcode/core.c b/arch/x86/kernel/cpu/microcode/core.c index 86e8f0b2537b..c4fa4a85d4cb 100644 --- a/arch/x86/kernel/cpu/microcode/core.c +++ b/arch/x86/kernel/cpu/microcode/core.c @@ -122,9 +122,6 @@ static bool __init check_loader_disabled_bsp(void) bool *res = &dis_ucode_ldr; #endif - if (!have_cpuid_p()) - return *res; - /* * CPUID(1).ECX[31]: reserved for hypervisor use. This is still not * completely accurate as xen pv guests don't see that CPUID bit set but @@ -166,24 +163,36 @@ bool get_builtin_firmware(struct cpio_data *cd, const char *name) void __init load_ucode_bsp(void) { unsigned int cpuid_1_eax; + bool intel = true; - if (check_loader_disabled_bsp()) + if (!have_cpuid_p()) return; cpuid_1_eax = native_cpuid_eax(1); switch (x86_cpuid_vendor()) { case X86_VENDOR_INTEL: - if (x86_family(cpuid_1_eax) >= 6) - load_ucode_intel_bsp(); + if (x86_family(cpuid_1_eax) < 6) + return; break; + case X86_VENDOR_AMD: - if (x86_family(cpuid_1_eax) >= 0x10) - load_ucode_amd_bsp(cpuid_1_eax); + if (x86_family(cpuid_1_eax) < 0x10) + return; + intel = false; break; + default: - break; + return; } + + if (check_loader_disabled_bsp()) + return; + + if (intel) + load_ucode_intel_bsp(); + else + load_ucode_amd_bsp(cpuid_1_eax); } static bool check_loader_disabled_ap(void) diff --git a/arch/x86/kernel/cpu/microcode/intel.c b/arch/x86/kernel/cpu/microcode/intel.c index 8f7a9bbad514..7dbcb7adf797 100644 --- a/arch/x86/kernel/cpu/microcode/intel.c +++ b/arch/x86/kernel/cpu/microcode/intel.c @@ -34,6 +34,7 @@ #include <linux/mm.h> #include <asm/microcode_intel.h> +#include <asm/intel-family.h> #include <asm/processor.h> #include <asm/tlbflush.h> #include <asm/setup.h> @@ -918,6 +919,18 @@ static int get_ucode_fw(void *to, const void *from, size_t n) return 0; } +static bool is_blacklisted(unsigned int cpu) +{ + struct cpuinfo_x86 *c = &cpu_data(cpu); + + if (c->x86 == 6 && c->x86_model == INTEL_FAM6_BROADWELL_X) { + pr_err_once("late loading on model 79 is disabled.\n"); + return true; + } + + return false; +} + static enum ucode_state request_microcode_fw(int cpu, struct device *device, bool refresh_fw) { @@ -926,6 +939,9 @@ static enum ucode_state request_microcode_fw(int cpu, struct device *device, const struct firmware *firmware; enum ucode_state ret; + if (is_blacklisted(cpu)) + return UCODE_NFOUND; + sprintf(name, "intel-ucode/%02x-%02x-%02x", c->x86, c->x86_model, c->x86_mask); @@ -950,6 +966,9 @@ static int get_ucode_user(void *to, const void *from, size_t n) static enum ucode_state request_microcode_user(int cpu, const void __user *buf, size_t size) { + if (is_blacklisted(cpu)) + return UCODE_NFOUND; + return generic_load_microcode(cpu, (void *)buf, size, &get_ucode_user); } diff --git a/arch/x86/kernel/head32.c b/arch/x86/kernel/head32.c index cf2ce063f65a..2902ca4d5993 100644 --- a/arch/x86/kernel/head32.c +++ b/arch/x86/kernel/head32.c @@ -30,10 +30,11 @@ static void __init i386_default_early_setup(void) asmlinkage __visible void __init i386_start_kernel(void) { - cr4_init_shadow(); - + /* Make sure IDT is set up before any exception happens */ idt_setup_early_handler(); + cr4_init_shadow(); + sanitize_boot_params(&boot_params); x86_early_init_platform_quirks(); diff --git a/arch/x86/kernel/kprobes/common.h b/arch/x86/kernel/kprobes/common.h index db2182d63ed0..3fc0f9a794cb 100644 --- a/arch/x86/kernel/kprobes/common.h +++ b/arch/x86/kernel/kprobes/common.h @@ -3,6 +3,15 @@ /* Kprobes and Optprobes common header */ +#include <asm/asm.h> + +#ifdef CONFIG_FRAME_POINTER +# define SAVE_RBP_STRING " push %" _ASM_BP "\n" \ + " mov %" _ASM_SP ", %" _ASM_BP "\n" +#else +# define SAVE_RBP_STRING " push %" _ASM_BP "\n" +#endif + #ifdef CONFIG_X86_64 #define SAVE_REGS_STRING \ /* Skip cs, ip, orig_ax. */ \ @@ -17,7 +26,7 @@ " pushq %r10\n" \ " pushq %r11\n" \ " pushq %rbx\n" \ - " pushq %rbp\n" \ + SAVE_RBP_STRING \ " pushq %r12\n" \ " pushq %r13\n" \ " pushq %r14\n" \ @@ -48,7 +57,7 @@ " pushl %es\n" \ " pushl %ds\n" \ " pushl %eax\n" \ - " pushl %ebp\n" \ + SAVE_RBP_STRING \ " pushl %edi\n" \ " pushl %esi\n" \ " pushl %edx\n" \ diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c index f0153714ddac..0742491cbb73 100644 --- a/arch/x86/kernel/kprobes/core.c +++ b/arch/x86/kernel/kprobes/core.c @@ -1080,8 +1080,6 @@ int setjmp_pre_handler(struct kprobe *p, struct pt_regs *regs) * raw stack chunk with redzones: */ __memcpy(kcb->jprobes_stack, (kprobe_opcode_t *)addr, MIN_STACK_SIZE(addr)); - regs->flags &= ~X86_EFLAGS_IF; - trace_hardirqs_off(); regs->ip = (unsigned long)(jp->entry); /* diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c index 54180fa6f66f..add33f600531 100644 --- a/arch/x86/kernel/reboot.c +++ b/arch/x86/kernel/reboot.c @@ -105,6 +105,10 @@ void __noreturn machine_real_restart(unsigned int type) load_cr3(initial_page_table); #else write_cr3(real_mode_header->trampoline_pgd); + + /* Exiting long mode will fail if CR4.PCIDE is set. */ + if (static_cpu_has(X86_FEATURE_PCID)) + cr4_clear_bits(X86_CR4_PCIDE); #endif /* Jump to the identity-mapped low memory code */ diff --git a/arch/x86/kernel/unwind_frame.c b/arch/x86/kernel/unwind_frame.c index d145a0b1f529..3dc26f95d46e 100644 --- a/arch/x86/kernel/unwind_frame.c +++ b/arch/x86/kernel/unwind_frame.c @@ -44,7 +44,8 @@ static void unwind_dump(struct unwind_state *state) state->stack_info.type, state->stack_info.next_sp, state->stack_mask, state->graph_idx); - for (sp = state->orig_sp; sp; sp = PTR_ALIGN(stack_info.next_sp, sizeof(long))) { + for (sp = PTR_ALIGN(state->orig_sp, sizeof(long)); sp; + sp = PTR_ALIGN(stack_info.next_sp, sizeof(long))) { if (get_stack_info(sp, state->task, &stack_info, &visit_mask)) break; @@ -174,6 +175,7 @@ static bool is_last_task_frame(struct unwind_state *state) * This determines if the frame pointer actually contains an encoded pointer to * pt_regs on the stack. See ENCODE_FRAME_POINTER. */ +#ifdef CONFIG_X86_64 static struct pt_regs *decode_frame_pointer(unsigned long *bp) { unsigned long regs = (unsigned long)bp; @@ -183,6 +185,23 @@ static struct pt_regs *decode_frame_pointer(unsigned long *bp) return (struct pt_regs *)(regs & ~0x1); } +#else +static struct pt_regs *decode_frame_pointer(unsigned long *bp) +{ + unsigned long regs = (unsigned long)bp; + + if (regs & 0x80000000) + return NULL; + + return (struct pt_regs *)(regs | 0x80000000); +} +#endif + +#ifdef CONFIG_X86_32 +#define KERNEL_REGS_SIZE (sizeof(struct pt_regs) - 2*sizeof(long)) +#else +#define KERNEL_REGS_SIZE (sizeof(struct pt_regs)) +#endif static bool update_stack_state(struct unwind_state *state, unsigned long *next_bp) @@ -202,7 +221,7 @@ static bool update_stack_state(struct unwind_state *state, regs = decode_frame_pointer(next_bp); if (regs) { frame = (unsigned long *)regs; - len = regs_size(regs); + len = KERNEL_REGS_SIZE; state->got_irq = true; } else { frame = next_bp; @@ -226,6 +245,14 @@ static bool update_stack_state(struct unwind_state *state, frame < prev_frame_end) return false; + /* + * On 32-bit with user mode regs, make sure the last two regs are safe + * to access: + */ + if (IS_ENABLED(CONFIG_X86_32) && regs && user_mode(regs) && + !on_stack(info, frame, len + 2*sizeof(long))) + return false; + /* Move state to the next frame: */ if (regs) { state->regs = regs; @@ -328,6 +355,13 @@ bad_address: state->regs->sp < (unsigned long)task_pt_regs(state->task)) goto the_end; + /* + * There are some known frame pointer issues on 32-bit. Disable + * unwinder warnings on 32-bit until it gets objtool support. + */ + if (IS_ENABLED(CONFIG_X86_32)) + goto the_end; + if (state->regs) { printk_deferred_once(KERN_WARNING "WARNING: kernel stack regs at %p in %s:%d has bad 'bp' value %p\n", diff --git a/arch/x86/kernel/unwind_orc.c b/arch/x86/kernel/unwind_orc.c index 570b70d3f604..b95007e7c1b3 100644 --- a/arch/x86/kernel/unwind_orc.c +++ b/arch/x86/kernel/unwind_orc.c @@ -86,8 +86,8 @@ static struct orc_entry *orc_find(unsigned long ip) idx = (ip - LOOKUP_START_IP) / LOOKUP_BLOCK_SIZE; if (unlikely((idx >= lookup_num_blocks-1))) { - orc_warn("WARNING: bad lookup idx: idx=%u num=%u ip=%lx\n", - idx, lookup_num_blocks, ip); + orc_warn("WARNING: bad lookup idx: idx=%u num=%u ip=%pB\n", + idx, lookup_num_blocks, (void *)ip); return NULL; } @@ -96,8 +96,8 @@ static struct orc_entry *orc_find(unsigned long ip) if (unlikely((__start_orc_unwind + start >= __stop_orc_unwind) || (__start_orc_unwind + stop > __stop_orc_unwind))) { - orc_warn("WARNING: bad lookup value: idx=%u num=%u start=%u stop=%u ip=%lx\n", - idx, lookup_num_blocks, start, stop, ip); + orc_warn("WARNING: bad lookup value: idx=%u num=%u start=%u stop=%u ip=%pB\n", + idx, lookup_num_blocks, start, stop, (void *)ip); return NULL; } @@ -373,7 +373,7 @@ bool unwind_next_frame(struct unwind_state *state) case ORC_REG_R10: if (!state->regs || !state->full_regs) { - orc_warn("missing regs for base reg R10 at ip %p\n", + orc_warn("missing regs for base reg R10 at ip %pB\n", (void *)state->ip); goto done; } @@ -382,7 +382,7 @@ bool unwind_next_frame(struct unwind_state *state) case ORC_REG_R13: if (!state->regs || !state->full_regs) { - orc_warn("missing regs for base reg R13 at ip %p\n", + orc_warn("missing regs for base reg R13 at ip %pB\n", (void *)state->ip); goto done; } @@ -391,7 +391,7 @@ bool unwind_next_frame(struct unwind_state *state) case ORC_REG_DI: if (!state->regs || !state->full_regs) { - orc_warn("missing regs for base reg DI at ip %p\n", + orc_warn("missing regs for base reg DI at ip %pB\n", (void *)state->ip); goto done; } @@ -400,7 +400,7 @@ bool unwind_next_frame(struct unwind_state *state) case ORC_REG_DX: if (!state->regs || !state->full_regs) { - orc_warn("missing regs for base reg DX at ip %p\n", + orc_warn("missing regs for base reg DX at ip %pB\n", (void *)state->ip); goto done; } @@ -408,7 +408,7 @@ bool unwind_next_frame(struct unwind_state *state) break; default: - orc_warn("unknown SP base reg %d for ip %p\n", + orc_warn("unknown SP base reg %d for ip %pB\n", orc->sp_reg, (void *)state->ip); goto done; } @@ -436,7 +436,7 @@ bool unwind_next_frame(struct unwind_state *state) case ORC_TYPE_REGS: if (!deref_stack_regs(state, sp, &state->ip, &state->sp, true)) { - orc_warn("can't dereference registers at %p for ip %p\n", + orc_warn("can't dereference registers at %p for ip %pB\n", (void *)sp, (void *)orig_ip); goto done; } @@ -448,7 +448,7 @@ bool unwind_next_frame(struct unwind_state *state) case ORC_TYPE_REGS_IRET: if (!deref_stack_regs(state, sp, &state->ip, &state->sp, false)) { - orc_warn("can't dereference iret registers at %p for ip %p\n", + orc_warn("can't dereference iret registers at %p for ip %pB\n", (void *)sp, (void *)orig_ip); goto done; } @@ -465,7 +465,8 @@ bool unwind_next_frame(struct unwind_state *state) break; default: - orc_warn("unknown .orc_unwind entry type %d\n", orc->type); + orc_warn("unknown .orc_unwind entry type %d for ip %pB\n", + orc->type, (void *)orig_ip); break; } @@ -487,7 +488,7 @@ bool unwind_next_frame(struct unwind_state *state) break; default: - orc_warn("unknown BP base reg %d for ip %p\n", + orc_warn("unknown BP base reg %d for ip %pB\n", orc->bp_reg, (void *)orig_ip); goto done; } @@ -496,7 +497,7 @@ bool unwind_next_frame(struct unwind_state *state) if (state->stack_info.type == prev_type && on_stack(&state->stack_info, (void *)state->sp, sizeof(long)) && state->sp <= prev_sp) { - orc_warn("stack going in the wrong direction? ip=%p\n", + orc_warn("stack going in the wrong direction? ip=%pB\n", (void *)orig_ip); goto done; } diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index 106d4a029a8a..7a69cf053711 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -3974,19 +3974,19 @@ static inline bool is_last_gpte(struct kvm_mmu *mmu, unsigned level, unsigned gpte) { /* - * PT_PAGE_TABLE_LEVEL always terminates. The RHS has bit 7 set - * iff level <= PT_PAGE_TABLE_LEVEL, which for our purpose means - * level == PT_PAGE_TABLE_LEVEL; set PT_PAGE_SIZE_MASK in gpte then. - */ - gpte |= level - PT_PAGE_TABLE_LEVEL - 1; - - /* * The RHS has bit 7 set iff level < mmu->last_nonleaf_level. * If it is clear, there are no large pages at this level, so clear * PT_PAGE_SIZE_MASK in gpte if that is the case. */ gpte &= level - mmu->last_nonleaf_level; + /* + * PT_PAGE_TABLE_LEVEL always terminates. The RHS has bit 7 set + * iff level <= PT_PAGE_TABLE_LEVEL, which for our purpose means + * level == PT_PAGE_TABLE_LEVEL; set PT_PAGE_SIZE_MASK in gpte then. + */ + gpte |= level - PT_PAGE_TABLE_LEVEL - 1; + return gpte & PT_PAGE_SIZE_MASK; } @@ -4555,6 +4555,7 @@ void kvm_init_shadow_ept_mmu(struct kvm_vcpu *vcpu, bool execonly, update_permission_bitmask(vcpu, context, true); update_pkru_bitmask(vcpu, context, true); + update_last_nonleaf_level(vcpu, context); reset_rsvds_bits_mask_ept(vcpu, context, execonly); reset_ept_shadow_zero_bits_mask(vcpu, context, execonly); } diff --git a/arch/x86/kvm/paging_tmpl.h b/arch/x86/kvm/paging_tmpl.h index 86b68dc5a649..f18d1f8d332b 100644 --- a/arch/x86/kvm/paging_tmpl.h +++ b/arch/x86/kvm/paging_tmpl.h @@ -334,10 +334,11 @@ retry_walk: --walker->level; index = PT_INDEX(addr, walker->level); - table_gfn = gpte_to_gfn(pte); offset = index * sizeof(pt_element_t); pte_gpa = gfn_to_gpa(table_gfn) + offset; + + BUG_ON(walker->level < 1); walker->table_gfn[walker->level - 1] = table_gfn; walker->pte_gpa[walker->level - 1] = pte_gpa; diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index a2b804e10c95..95a01609d7ee 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -11297,7 +11297,7 @@ static void load_vmcs12_host_state(struct kvm_vcpu *vcpu, /* Same as above - no reason to call set_cr4_guest_host_mask(). */ vcpu->arch.cr4_guest_owned_bits = ~vmcs_readl(CR4_GUEST_HOST_MASK); - kvm_set_cr4(vcpu, vmcs12->host_cr4); + vmx_set_cr4(vcpu, vmcs12->host_cr4); nested_ept_uninit_mmu_context(vcpu); diff --git a/arch/x86/mm/Makefile b/arch/x86/mm/Makefile index 72bf8c01c6e3..e1f095884386 100644 --- a/arch/x86/mm/Makefile +++ b/arch/x86/mm/Makefile @@ -1,5 +1,12 @@ -# Kernel does not boot with instrumentation of tlb.c. -KCOV_INSTRUMENT_tlb.o := n +# Kernel does not boot with instrumentation of tlb.c and mem_encrypt.c +KCOV_INSTRUMENT_tlb.o := n +KCOV_INSTRUMENT_mem_encrypt.o := n + +KASAN_SANITIZE_mem_encrypt.o := n + +ifdef CONFIG_FUNCTION_TRACER +CFLAGS_REMOVE_mem_encrypt.o = -pg +endif obj-y := init.o init_$(BITS).o fault.o ioremap.o extable.o pageattr.o mmap.o \ pat.o pgtable.o physaddr.o setup_nx.o tlb.o diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c index e2baeaa053a5..7101c281c7ce 100644 --- a/arch/x86/mm/fault.c +++ b/arch/x86/mm/fault.c @@ -1440,7 +1440,17 @@ good_area: * make sure we exit gracefully rather than endlessly redo * the fault. Since we never set FAULT_FLAG_RETRY_NOWAIT, if * we get VM_FAULT_RETRY back, the mmap_sem has been unlocked. + * + * Note that handle_userfault() may also release and reacquire mmap_sem + * (and not return with VM_FAULT_RETRY), when returning to userland to + * repeat the page fault later with a VM_FAULT_NOPAGE retval + * (potentially after handling any pending signal during the return to + * userland). The return to userland is identified whenever + * FAULT_FLAG_USER|FAULT_FLAG_KILLABLE are both set in flags. + * Thus we have to be careful about not touching vma after handling the + * fault, so we read the pkey beforehand. */ + pkey = vma_pkey(vma); fault = handle_mm_fault(vma, address, flags); major |= fault & VM_FAULT_MAJOR; @@ -1467,7 +1477,6 @@ good_area: return; } - pkey = vma_pkey(vma); up_read(&mm->mmap_sem); if (unlikely(fault & VM_FAULT_ERROR)) { mm_fault_error(regs, error_code, address, &pkey, fault); diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c index 49d9778376d7..0f3d0cea4d00 100644 --- a/arch/x86/mm/tlb.c +++ b/arch/x86/mm/tlb.c @@ -30,6 +30,7 @@ atomic64_t last_mm_ctx_id = ATOMIC64_INIT(1); + static void choose_new_asid(struct mm_struct *next, u64 next_tlb_gen, u16 *new_asid, bool *need_flush) { @@ -80,7 +81,7 @@ void leave_mm(int cpu) return; /* Warn if we're not lazy. */ - WARN_ON(cpumask_test_cpu(smp_processor_id(), mm_cpumask(loaded_mm))); + WARN_ON(!this_cpu_read(cpu_tlbstate.is_lazy)); switch_mm(NULL, &init_mm, NULL); } @@ -142,45 +143,24 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next, __flush_tlb_all(); } #endif + this_cpu_write(cpu_tlbstate.is_lazy, false); if (real_prev == next) { - VM_BUG_ON(this_cpu_read(cpu_tlbstate.ctxs[prev_asid].ctx_id) != - next->context.ctx_id); - - if (cpumask_test_cpu(cpu, mm_cpumask(next))) { - /* - * There's nothing to do: we weren't lazy, and we - * aren't changing our mm. We don't need to flush - * anything, nor do we need to update CR3, CR4, or - * LDTR. - */ - return; - } - - /* Resume remote flushes and then read tlb_gen. */ - cpumask_set_cpu(cpu, mm_cpumask(next)); - next_tlb_gen = atomic64_read(&next->context.tlb_gen); - - if (this_cpu_read(cpu_tlbstate.ctxs[prev_asid].tlb_gen) < - next_tlb_gen) { - /* - * Ideally, we'd have a flush_tlb() variant that - * takes the known CR3 value as input. This would - * be faster on Xen PV and on hypothetical CPUs - * on which INVPCID is fast. - */ - this_cpu_write(cpu_tlbstate.ctxs[prev_asid].tlb_gen, - next_tlb_gen); - write_cr3(build_cr3(next, prev_asid)); - trace_tlb_flush(TLB_FLUSH_ON_TASK_SWITCH, - TLB_FLUSH_ALL); - } + VM_WARN_ON(this_cpu_read(cpu_tlbstate.ctxs[prev_asid].ctx_id) != + next->context.ctx_id); /* - * We just exited lazy mode, which means that CR4 and/or LDTR - * may be stale. (Changes to the required CR4 and LDTR states - * are not reflected in tlb_gen.) + * We don't currently support having a real mm loaded without + * our cpu set in mm_cpumask(). We have all the bookkeeping + * in place to figure out whether we would need to flush + * if our cpu were cleared in mm_cpumask(), but we don't + * currently use it. */ + if (WARN_ON_ONCE(real_prev != &init_mm && + !cpumask_test_cpu(cpu, mm_cpumask(next)))) + cpumask_set_cpu(cpu, mm_cpumask(next)); + + return; } else { u16 new_asid; bool need_flush; @@ -199,10 +179,9 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next, } /* Stop remote flushes for the previous mm */ - if (cpumask_test_cpu(cpu, mm_cpumask(real_prev))) - cpumask_clear_cpu(cpu, mm_cpumask(real_prev)); - - VM_WARN_ON_ONCE(cpumask_test_cpu(cpu, mm_cpumask(next))); + VM_WARN_ON_ONCE(!cpumask_test_cpu(cpu, mm_cpumask(real_prev)) && + real_prev != &init_mm); + cpumask_clear_cpu(cpu, mm_cpumask(real_prev)); /* * Start remote flushes and then read tlb_gen. @@ -233,6 +212,40 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next, } /* + * Please ignore the name of this function. It should be called + * switch_to_kernel_thread(). + * + * enter_lazy_tlb() is a hint from the scheduler that we are entering a + * kernel thread or other context without an mm. Acceptable implementations + * include doing nothing whatsoever, switching to init_mm, or various clever + * lazy tricks to try to minimize TLB flushes. + * + * The scheduler reserves the right to call enter_lazy_tlb() several times + * in a row. It will notify us that we're going back to a real mm by + * calling switch_mm_irqs_off(). + */ +void enter_lazy_tlb(struct mm_struct *mm, struct task_struct *tsk) +{ + if (this_cpu_read(cpu_tlbstate.loaded_mm) == &init_mm) + return; + + if (tlb_defer_switch_to_init_mm()) { + /* + * There's a significant optimization that may be possible + * here. We have accurate enough TLB flush tracking that we + * don't need to maintain coherence of TLB per se when we're + * lazy. We do, however, need to maintain coherence of + * paging-structure caches. We could, in principle, leave our + * old mm loaded and only switch to init_mm when + * tlb_remove_page() happens. + */ + this_cpu_write(cpu_tlbstate.is_lazy, true); + } else { + switch_mm(NULL, &init_mm, NULL); + } +} + +/* * Call this when reinitializing a CPU. It fixes the following potential * problems: * @@ -303,16 +316,20 @@ static void flush_tlb_func_common(const struct flush_tlb_info *f, /* This code cannot presently handle being reentered. */ VM_WARN_ON(!irqs_disabled()); + if (unlikely(loaded_mm == &init_mm)) + return; + VM_WARN_ON(this_cpu_read(cpu_tlbstate.ctxs[loaded_mm_asid].ctx_id) != loaded_mm->context.ctx_id); - if (!cpumask_test_cpu(smp_processor_id(), mm_cpumask(loaded_mm))) { + if (this_cpu_read(cpu_tlbstate.is_lazy)) { /* - * We're in lazy mode -- don't flush. We can get here on - * remote flushes due to races and on local flushes if a - * kernel thread coincidentally flushes the mm it's lazily - * still using. + * We're in lazy mode. We need to at least flush our + * paging-structure cache to avoid speculatively reading + * garbage into our TLB. Since switching to init_mm is barely + * slower than a minimal flush, just switch to init_mm. */ + switch_mm_irqs_off(NULL, &init_mm, NULL); return; } diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c index 0e7ef69e8531..d669e9d89001 100644 --- a/arch/x86/xen/enlighten.c +++ b/arch/x86/xen/enlighten.c @@ -93,11 +93,11 @@ int xen_cpuhp_setup(int (*cpu_up_prepare_cb)(unsigned int), int rc; rc = cpuhp_setup_state_nocalls(CPUHP_XEN_PREPARE, - "x86/xen/hvm_guest:prepare", + "x86/xen/guest:prepare", cpu_up_prepare_cb, cpu_dead_cb); if (rc >= 0) { rc = cpuhp_setup_state_nocalls(CPUHP_AP_ONLINE_DYN, - "x86/xen/hvm_guest:online", + "x86/xen/guest:online", xen_cpu_up_online, NULL); if (rc < 0) cpuhp_remove_state_nocalls(CPUHP_XEN_PREPARE); diff --git a/block/bio.c b/block/bio.c index b38e962fa83e..101c2a9b5481 100644 --- a/block/bio.c +++ b/block/bio.c @@ -1239,8 +1239,8 @@ struct bio *bio_copy_user_iov(struct request_queue *q, */ bmd->is_our_pages = map_data ? 0 : 1; memcpy(bmd->iov, iter->iov, sizeof(struct iovec) * iter->nr_segs); - iov_iter_init(&bmd->iter, iter->type, bmd->iov, - iter->nr_segs, iter->count); + bmd->iter = *iter; + bmd->iter.iov = bmd->iov; ret = -ENOMEM; bio = bio_kmalloc(gfp_mask, nr_pages); @@ -1331,6 +1331,7 @@ struct bio *bio_map_user_iov(struct request_queue *q, int ret, offset; struct iov_iter i; struct iovec iov; + struct bio_vec *bvec; iov_for_each(iov, i, *iter) { unsigned long uaddr = (unsigned long) iov.iov_base; @@ -1375,7 +1376,12 @@ struct bio *bio_map_user_iov(struct request_queue *q, ret = get_user_pages_fast(uaddr, local_nr_pages, (iter->type & WRITE) != WRITE, &pages[cur_page]); - if (ret < local_nr_pages) { + if (unlikely(ret < local_nr_pages)) { + for (j = cur_page; j < page_limit; j++) { + if (!pages[j]) + break; + put_page(pages[j]); + } ret = -EFAULT; goto out_unmap; } @@ -1383,6 +1389,7 @@ struct bio *bio_map_user_iov(struct request_queue *q, offset = offset_in_page(uaddr); for (j = cur_page; j < page_limit; j++) { unsigned int bytes = PAGE_SIZE - offset; + unsigned short prev_bi_vcnt = bio->bi_vcnt; if (len <= 0) break; @@ -1397,6 +1404,13 @@ struct bio *bio_map_user_iov(struct request_queue *q, bytes) break; + /* + * check if vector was merged with previous + * drop page reference if needed + */ + if (bio->bi_vcnt == prev_bi_vcnt) + put_page(pages[j]); + len -= bytes; offset = 0; } @@ -1423,10 +1437,8 @@ struct bio *bio_map_user_iov(struct request_queue *q, return bio; out_unmap: - for (j = 0; j < nr_pages; j++) { - if (!pages[j]) - break; - put_page(pages[j]); + bio_for_each_segment_all(bvec, bio, j) { + put_page(bvec->bv_page); } out: kfree(pages); diff --git a/crypto/asymmetric_keys/asymmetric_type.c b/crypto/asymmetric_keys/asymmetric_type.c index e4b0ed386bc8..39aecad286fe 100644 --- a/crypto/asymmetric_keys/asymmetric_type.c +++ b/crypto/asymmetric_keys/asymmetric_type.c @@ -57,6 +57,8 @@ struct key *find_asymmetric_key(struct key *keyring, char *req, *p; int len; + BUG_ON(!id_0 && !id_1); + if (id_0) { lookup = id_0->data; len = id_0->len; @@ -105,7 +107,7 @@ struct key *find_asymmetric_key(struct key *keyring, if (id_0 && id_1) { const struct asymmetric_key_ids *kids = asymmetric_key_ids(key); - if (!kids->id[0]) { + if (!kids->id[1]) { pr_debug("First ID matches, but second is missing\n"); goto reject; } diff --git a/crypto/asymmetric_keys/pkcs7_parser.c b/crypto/asymmetric_keys/pkcs7_parser.c index af4cd8649117..d140d8bb2c96 100644 --- a/crypto/asymmetric_keys/pkcs7_parser.c +++ b/crypto/asymmetric_keys/pkcs7_parser.c @@ -88,6 +88,9 @@ static int pkcs7_check_authattrs(struct pkcs7_message *msg) bool want = false; sinfo = msg->signed_infos; + if (!sinfo) + goto inconsistent; + if (sinfo->authattrs) { want = true; msg->have_authattrs = true; diff --git a/crypto/shash.c b/crypto/shash.c index 5e31c8d776df..325a14da5827 100644 --- a/crypto/shash.c +++ b/crypto/shash.c @@ -41,7 +41,7 @@ static int shash_setkey_unaligned(struct crypto_shash *tfm, const u8 *key, int err; absize = keylen + (alignmask & ~(crypto_tfm_ctx_alignment() - 1)); - buffer = kmalloc(absize, GFP_KERNEL); + buffer = kmalloc(absize, GFP_ATOMIC); if (!buffer) return -ENOMEM; @@ -275,12 +275,14 @@ static int shash_async_finup(struct ahash_request *req) int shash_ahash_digest(struct ahash_request *req, struct shash_desc *desc) { - struct scatterlist *sg = req->src; - unsigned int offset = sg->offset; unsigned int nbytes = req->nbytes; + struct scatterlist *sg; + unsigned int offset; int err; - if (nbytes < min(sg->length, ((unsigned int)(PAGE_SIZE)) - offset)) { + if (nbytes && + (sg = req->src, offset = sg->offset, + nbytes < min(sg->length, ((unsigned int)(PAGE_SIZE)) - offset))) { void *data; data = kmap_atomic(sg_page(sg)); diff --git a/crypto/skcipher.c b/crypto/skcipher.c index 4faa0fd53b0c..d5692e35fab1 100644 --- a/crypto/skcipher.c +++ b/crypto/skcipher.c @@ -426,14 +426,9 @@ static int skcipher_copy_iv(struct skcipher_walk *walk) static int skcipher_walk_first(struct skcipher_walk *walk) { - walk->nbytes = 0; - if (WARN_ON_ONCE(in_irq())) return -EDEADLK; - if (unlikely(!walk->total)) - return 0; - walk->buffer = NULL; if (unlikely(((unsigned long)walk->iv & walk->alignmask))) { int err = skcipher_copy_iv(walk); @@ -452,10 +447,15 @@ static int skcipher_walk_skcipher(struct skcipher_walk *walk, { struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req); + walk->total = req->cryptlen; + walk->nbytes = 0; + + if (unlikely(!walk->total)) + return 0; + scatterwalk_start(&walk->in, req->src); scatterwalk_start(&walk->out, req->dst); - walk->total = req->cryptlen; walk->iv = req->iv; walk->oiv = req->iv; @@ -509,6 +509,11 @@ static int skcipher_walk_aead_common(struct skcipher_walk *walk, struct crypto_aead *tfm = crypto_aead_reqtfm(req); int err; + walk->nbytes = 0; + + if (unlikely(!walk->total)) + return 0; + walk->flags &= ~SKCIPHER_WALK_PHYS; scatterwalk_start(&walk->in, req->src); diff --git a/crypto/xts.c b/crypto/xts.c index d86c11a8c882..e31828ed0046 100644 --- a/crypto/xts.c +++ b/crypto/xts.c @@ -554,8 +554,10 @@ static int create(struct crypto_template *tmpl, struct rtattr **tb) ctx->name[len - 1] = 0; if (snprintf(inst->alg.base.cra_name, CRYPTO_MAX_ALG_NAME, - "xts(%s)", ctx->name) >= CRYPTO_MAX_ALG_NAME) - return -ENAMETOOLONG; + "xts(%s)", ctx->name) >= CRYPTO_MAX_ALG_NAME) { + err = -ENAMETOOLONG; + goto err_drop_spawn; + } } else goto err_drop_spawn; diff --git a/drivers/acpi/property.c b/drivers/acpi/property.c index 3fb8ff513461..e26ea209b63e 100644 --- a/drivers/acpi/property.c +++ b/drivers/acpi/property.c @@ -571,10 +571,9 @@ static int acpi_data_get_property_array(const struct acpi_device_data *data, * } * } * - * Calling this function with index %2 return %-ENOENT and with index %3 - * returns the last entry. If the property does not contain any more values - * %-ENODATA is returned. The NULL entry must be single integer and - * preferably contain value %0. + * Calling this function with index %2 or index %3 return %-ENOENT. If the + * property does not contain any more values %-ENOENT is returned. The NULL + * entry must be single integer and preferably contain value %0. * * Return: %0 on success, negative error code on failure. */ @@ -590,11 +589,11 @@ int __acpi_node_get_property_reference(const struct fwnode_handle *fwnode, data = acpi_device_data_of_node(fwnode); if (!data) - return -EINVAL; + return -ENOENT; ret = acpi_data_get_property(data, propname, ACPI_TYPE_ANY, &obj); if (ret) - return ret; + return ret == -EINVAL ? -ENOENT : -EINVAL; /* * The simplest case is when the value is a single reference. Just @@ -606,7 +605,7 @@ int __acpi_node_get_property_reference(const struct fwnode_handle *fwnode, ret = acpi_bus_get_device(obj->reference.handle, &device); if (ret) - return ret; + return ret == -ENODEV ? -EINVAL : ret; args->adev = device; args->nargs = 0; @@ -622,8 +621,10 @@ int __acpi_node_get_property_reference(const struct fwnode_handle *fwnode, * The index argument is then used to determine which reference * the caller wants (along with the arguments). */ - if (obj->type != ACPI_TYPE_PACKAGE || index >= obj->package.count) - return -EPROTO; + if (obj->type != ACPI_TYPE_PACKAGE) + return -EINVAL; + if (index >= obj->package.count) + return -ENOENT; element = obj->package.elements; end = element + obj->package.count; @@ -635,7 +636,7 @@ int __acpi_node_get_property_reference(const struct fwnode_handle *fwnode, ret = acpi_bus_get_device(element->reference.handle, &device); if (ret) - return -ENODEV; + return -EINVAL; nargs = 0; element++; @@ -649,11 +650,11 @@ int __acpi_node_get_property_reference(const struct fwnode_handle *fwnode, else if (type == ACPI_TYPE_LOCAL_REFERENCE) break; else - return -EPROTO; + return -EINVAL; } if (nargs > MAX_ACPI_REFERENCE_ARGS) - return -EPROTO; + return -EINVAL; if (idx == index) { args->adev = device; @@ -670,13 +671,13 @@ int __acpi_node_get_property_reference(const struct fwnode_handle *fwnode, return -ENOENT; element++; } else { - return -EPROTO; + return -EINVAL; } idx++; } - return -ENODATA; + return -ENOENT; } EXPORT_SYMBOL_GPL(__acpi_node_get_property_reference); diff --git a/drivers/android/binder.c b/drivers/android/binder.c index ab34239a76ee..fddf76ef5bd6 100644 --- a/drivers/android/binder.c +++ b/drivers/android/binder.c @@ -2582,6 +2582,48 @@ static bool binder_proc_transaction(struct binder_transaction *t, return true; } +/** + * binder_get_node_refs_for_txn() - Get required refs on node for txn + * @node: struct binder_node for which to get refs + * @proc: returns @node->proc if valid + * @error: if no @proc then returns BR_DEAD_REPLY + * + * User-space normally keeps the node alive when creating a transaction + * since it has a reference to the target. The local strong ref keeps it + * alive if the sending process dies before the target process processes + * the transaction. If the source process is malicious or has a reference + * counting bug, relying on the local strong ref can fail. + * + * Since user-space can cause the local strong ref to go away, we also take + * a tmpref on the node to ensure it survives while we are constructing + * the transaction. We also need a tmpref on the proc while we are + * constructing the transaction, so we take that here as well. + * + * Return: The target_node with refs taken or NULL if no @node->proc is NULL. + * Also sets @proc if valid. If the @node->proc is NULL indicating that the + * target proc has died, @error is set to BR_DEAD_REPLY + */ +static struct binder_node *binder_get_node_refs_for_txn( + struct binder_node *node, + struct binder_proc **procp, + uint32_t *error) +{ + struct binder_node *target_node = NULL; + + binder_node_inner_lock(node); + if (node->proc) { + target_node = node; + binder_inc_node_nilocked(node, 1, 0, NULL); + binder_inc_node_tmpref_ilocked(node); + node->proc->tmp_ref++; + *procp = node->proc; + } else + *error = BR_DEAD_REPLY; + binder_node_inner_unlock(node); + + return target_node; +} + static void binder_transaction(struct binder_proc *proc, struct binder_thread *thread, struct binder_transaction_data *tr, int reply, @@ -2685,43 +2727,35 @@ static void binder_transaction(struct binder_proc *proc, ref = binder_get_ref_olocked(proc, tr->target.handle, true); if (ref) { - binder_inc_node(ref->node, 1, 0, NULL); - target_node = ref->node; - } - binder_proc_unlock(proc); - if (target_node == NULL) { + target_node = binder_get_node_refs_for_txn( + ref->node, &target_proc, + &return_error); + } else { binder_user_error("%d:%d got transaction to invalid handle\n", - proc->pid, thread->pid); + proc->pid, thread->pid); return_error = BR_FAILED_REPLY; - return_error_param = -EINVAL; - return_error_line = __LINE__; - goto err_invalid_target_handle; } + binder_proc_unlock(proc); } else { mutex_lock(&context->context_mgr_node_lock); target_node = context->binder_context_mgr_node; - if (target_node == NULL) { + if (target_node) + target_node = binder_get_node_refs_for_txn( + target_node, &target_proc, + &return_error); + else return_error = BR_DEAD_REPLY; - mutex_unlock(&context->context_mgr_node_lock); - return_error_line = __LINE__; - goto err_no_context_mgr_node; - } - binder_inc_node(target_node, 1, 0, NULL); mutex_unlock(&context->context_mgr_node_lock); } - e->to_node = target_node->debug_id; - binder_node_lock(target_node); - target_proc = target_node->proc; - if (target_proc == NULL) { - binder_node_unlock(target_node); - return_error = BR_DEAD_REPLY; + if (!target_node) { + /* + * return_error is set above + */ + return_error_param = -EINVAL; return_error_line = __LINE__; goto err_dead_binder; } - binder_inner_proc_lock(target_proc); - target_proc->tmp_ref++; - binder_inner_proc_unlock(target_proc); - binder_node_unlock(target_node); + e->to_node = target_node->debug_id; if (security_binder_transaction(proc->tsk, target_proc->tsk) < 0) { return_error = BR_FAILED_REPLY; @@ -3071,6 +3105,8 @@ static void binder_transaction(struct binder_proc *proc, if (target_thread) binder_thread_dec_tmpref(target_thread); binder_proc_dec_tmpref(target_proc); + if (target_node) + binder_dec_node_tmpref(target_node); /* * write barrier to synchronize with initialization * of log entry @@ -3090,6 +3126,8 @@ err_bad_parent: err_copy_data_failed: trace_binder_transaction_failed_buffer_release(t->buffer); binder_transaction_buffer_release(target_proc, t->buffer, offp); + if (target_node) + binder_dec_node_tmpref(target_node); target_node = NULL; t->buffer->transaction = NULL; binder_alloc_free_buf(&target_proc->alloc, t->buffer); @@ -3104,13 +3142,14 @@ err_bad_call_stack: err_empty_call_stack: err_dead_binder: err_invalid_target_handle: -err_no_context_mgr_node: if (target_thread) binder_thread_dec_tmpref(target_thread); if (target_proc) binder_proc_dec_tmpref(target_proc); - if (target_node) + if (target_node) { binder_dec_node(target_node, 1, 0); + binder_dec_node_tmpref(target_node); + } binder_debug(BINDER_DEBUG_FAILED_TRANSACTION, "%d:%d transaction failed %d/%d, size %lld-%lld line %d\n", @@ -3623,12 +3662,6 @@ static void binder_stat_br(struct binder_proc *proc, } } -static int binder_has_thread_work(struct binder_thread *thread) -{ - return !binder_worklist_empty(thread->proc, &thread->todo) || - thread->looper_need_return; -} - static int binder_put_node_cmd(struct binder_proc *proc, struct binder_thread *thread, void __user **ptrp, @@ -4258,12 +4291,9 @@ static unsigned int binder_poll(struct file *filp, binder_inner_proc_unlock(thread->proc); - if (binder_has_work(thread, wait_for_proc_work)) - return POLLIN; - poll_wait(filp, &thread->wait, wait); - if (binder_has_thread_work(thread)) + if (binder_has_work(thread, wait_for_proc_work)) return POLLIN; return 0; diff --git a/drivers/android/binder_alloc.c b/drivers/android/binder_alloc.c index 064f5e31ec55..c2819a3d58a6 100644 --- a/drivers/android/binder_alloc.c +++ b/drivers/android/binder_alloc.c @@ -215,17 +215,12 @@ static int binder_update_page_range(struct binder_alloc *alloc, int allocate, } } - if (!vma && need_mm) - mm = get_task_mm(alloc->tsk); + if (!vma && need_mm && mmget_not_zero(alloc->vma_vm_mm)) + mm = alloc->vma_vm_mm; if (mm) { down_write(&mm->mmap_sem); vma = alloc->vma; - if (vma && mm != alloc->vma_vm_mm) { - pr_err("%d: vma mm and task mm mismatch\n", - alloc->pid); - vma = NULL; - } } if (!vma && need_mm) { @@ -565,7 +560,7 @@ static void binder_delete_free_buffer(struct binder_alloc *alloc, binder_alloc_debug(BINDER_DEBUG_BUFFER_ALLOC, "%d: merge free, buffer %pK do not share page with %pK or %pK\n", alloc->pid, buffer->data, - prev->data, next->data); + prev->data, next ? next->data : NULL); binder_update_page_range(alloc, 0, buffer_start_page(buffer), buffer_start_page(buffer) + PAGE_SIZE, NULL); @@ -720,6 +715,7 @@ int binder_alloc_mmap_handler(struct binder_alloc *alloc, barrier(); alloc->vma = vma; alloc->vma_vm_mm = vma->vm_mm; + mmgrab(alloc->vma_vm_mm); return 0; @@ -795,6 +791,8 @@ void binder_alloc_deferred_release(struct binder_alloc *alloc) vfree(alloc->buffer); } mutex_unlock(&alloc->mutex); + if (alloc->vma_vm_mm) + mmdrop(alloc->vma_vm_mm); binder_alloc_debug(BINDER_DEBUG_OPEN_CLOSE, "%s: %d buffers %d, pages %d\n", @@ -889,7 +887,6 @@ int binder_alloc_get_allocated_count(struct binder_alloc *alloc) void binder_alloc_vma_close(struct binder_alloc *alloc) { WRITE_ONCE(alloc->vma, NULL); - WRITE_ONCE(alloc->vma_vm_mm, NULL); } /** @@ -926,9 +923,9 @@ enum lru_status binder_alloc_free_page(struct list_head *item, page_addr = (uintptr_t)alloc->buffer + index * PAGE_SIZE; vma = alloc->vma; if (vma) { - mm = get_task_mm(alloc->tsk); - if (!mm) - goto err_get_task_mm_failed; + if (!mmget_not_zero(alloc->vma_vm_mm)) + goto err_mmget; + mm = alloc->vma_vm_mm; if (!down_write_trylock(&mm->mmap_sem)) goto err_down_write_mmap_sem_failed; } @@ -963,7 +960,7 @@ enum lru_status binder_alloc_free_page(struct list_head *item, err_down_write_mmap_sem_failed: mmput_async(mm); -err_get_task_mm_failed: +err_mmget: err_page_already_freed: mutex_unlock(&alloc->mutex); err_get_alloc_mutex_failed: @@ -1002,7 +999,6 @@ struct shrinker binder_shrinker = { */ void binder_alloc_init(struct binder_alloc *alloc) { - alloc->tsk = current->group_leader; alloc->pid = current->group_leader->pid; mutex_init(&alloc->mutex); INIT_LIST_HEAD(&alloc->buffers); diff --git a/drivers/android/binder_alloc.h b/drivers/android/binder_alloc.h index a3a3602c689c..2dd33b6df104 100644 --- a/drivers/android/binder_alloc.h +++ b/drivers/android/binder_alloc.h @@ -100,7 +100,6 @@ struct binder_lru_page { */ struct binder_alloc { struct mutex mutex; - struct task_struct *tsk; struct vm_area_struct *vma; struct mm_struct *vma_vm_mm; void *buffer; diff --git a/drivers/base/node.c b/drivers/base/node.c index 3855902f2c5b..aae2402f3791 100644 --- a/drivers/base/node.c +++ b/drivers/base/node.c @@ -27,13 +27,21 @@ static struct bus_type node_subsys = { static ssize_t node_read_cpumap(struct device *dev, bool list, char *buf) { + ssize_t n; + cpumask_var_t mask; struct node *node_dev = to_node(dev); - const struct cpumask *mask = cpumask_of_node(node_dev->dev.id); /* 2008/04/07: buf currently PAGE_SIZE, need 9 chars per 32 bits. */ BUILD_BUG_ON((NR_CPUS/32 * 9) > (PAGE_SIZE-1)); - return cpumap_print_to_pagebuf(list, buf, mask); + if (!alloc_cpumask_var(&mask, GFP_KERNEL)) + return 0; + + cpumask_and(mask, cpumask_of_node(node_dev->dev.id), cpu_online_mask); + n = cpumap_print_to_pagebuf(list, buf, mask); + free_cpumask_var(mask); + + return n; } static inline ssize_t node_read_cpumask(struct device *dev, diff --git a/drivers/base/property.c b/drivers/base/property.c index d0b65bbe7e15..7ed99c1b2a8b 100644 --- a/drivers/base/property.c +++ b/drivers/base/property.c @@ -21,6 +21,7 @@ #include <linux/phy.h> struct property_set { + struct device *dev; struct fwnode_handle fwnode; const struct property_entry *properties; }; @@ -682,6 +683,10 @@ EXPORT_SYMBOL_GPL(fwnode_property_match_string); * Caller is responsible to call fwnode_handle_put() on the returned * args->fwnode pointer. * + * Returns: %0 on success + * %-ENOENT when the index is out of bounds, the index has an empty + * reference or the property was not found + * %-EINVAL on parse error */ int fwnode_property_get_reference_args(const struct fwnode_handle *fwnode, const char *prop, const char *nargs_prop, @@ -891,6 +896,7 @@ static struct property_set *pset_copy_set(const struct property_set *pset) void device_remove_properties(struct device *dev) { struct fwnode_handle *fwnode; + struct property_set *pset; fwnode = dev_fwnode(dev); if (!fwnode) @@ -900,16 +906,16 @@ void device_remove_properties(struct device *dev) * the pset. If there is no real firmware node (ACPI/DT) primary * will hold the pset. */ - if (is_pset_node(fwnode)) { + pset = to_pset_node(fwnode); + if (pset) { set_primary_fwnode(dev, NULL); - pset_free_set(to_pset_node(fwnode)); } else { - fwnode = fwnode->secondary; - if (!IS_ERR(fwnode) && is_pset_node(fwnode)) { + pset = to_pset_node(fwnode->secondary); + if (pset && dev == pset->dev) set_secondary_fwnode(dev, NULL); - pset_free_set(to_pset_node(fwnode)); - } } + if (pset && dev == pset->dev) + pset_free_set(pset); } EXPORT_SYMBOL_GPL(device_remove_properties); @@ -938,6 +944,7 @@ int device_add_properties(struct device *dev, p->fwnode.ops = &pset_fwnode_ops; set_secondary_fwnode(dev, &p->fwnode); + p->dev = dev; return 0; } EXPORT_SYMBOL_GPL(device_add_properties); diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c index 883dfebd3014..9adfb5445f8d 100644 --- a/drivers/block/nbd.c +++ b/drivers/block/nbd.c @@ -243,7 +243,6 @@ static void nbd_size_set(struct nbd_device *nbd, loff_t blocksize, struct nbd_config *config = nbd->config; config->blksize = blocksize; config->bytesize = blocksize * nr_blocks; - nbd_size_update(nbd); } static void nbd_complete_rq(struct request *req) @@ -387,6 +386,15 @@ static int sock_xmit(struct nbd_device *nbd, int index, int send, return result; } +/* + * Different settings for sk->sk_sndtimeo can result in different return values + * if there is a signal pending when we enter sendmsg, because reasons? + */ +static inline int was_interrupted(int result) +{ + return result == -ERESTARTSYS || result == -EINTR; +} + /* always call with the tx_lock held */ static int nbd_send_cmd(struct nbd_device *nbd, struct nbd_cmd *cmd, int index) { @@ -459,7 +467,7 @@ static int nbd_send_cmd(struct nbd_device *nbd, struct nbd_cmd *cmd, int index) result = sock_xmit(nbd, index, 1, &from, (type == NBD_CMD_WRITE) ? MSG_MORE : 0, &sent); if (result <= 0) { - if (result == -ERESTARTSYS) { + if (was_interrupted(result)) { /* If we havne't sent anything we can just return BUSY, * however if we have sent something we need to make * sure we only allow this req to be sent until we are @@ -503,7 +511,7 @@ send_pages: } result = sock_xmit(nbd, index, 1, &from, flags, &sent); if (result <= 0) { - if (result == -ERESTARTSYS) { + if (was_interrupted(result)) { /* We've already sent the header, we * have no choice but to set pending and * return BUSY. @@ -1094,6 +1102,7 @@ static int nbd_start_device(struct nbd_device *nbd) args->index = i; queue_work(recv_workqueue, &args->work); } + nbd_size_update(nbd); return error; } diff --git a/drivers/block/skd_main.c b/drivers/block/skd_main.c index 7cedb4295e9d..64d0fc17c174 100644 --- a/drivers/block/skd_main.c +++ b/drivers/block/skd_main.c @@ -2604,7 +2604,7 @@ static void *skd_alloc_dma(struct skd_device *skdev, struct kmem_cache *s, return NULL; *dma_handle = dma_map_single(dev, buf, s->size, dir); if (dma_mapping_error(dev, *dma_handle)) { - kfree(buf); + kmem_cache_free(s, buf); buf = NULL; } return buf; diff --git a/drivers/block/virtio_blk.c b/drivers/block/virtio_blk.c index 34e17ee799be..68846897d213 100644 --- a/drivers/block/virtio_blk.c +++ b/drivers/block/virtio_blk.c @@ -593,10 +593,22 @@ static int virtblk_map_queues(struct blk_mq_tag_set *set) return blk_mq_virtio_map_queues(set, vblk->vdev, 0); } +#ifdef CONFIG_VIRTIO_BLK_SCSI +static void virtblk_initialize_rq(struct request *req) +{ + struct virtblk_req *vbr = blk_mq_rq_to_pdu(req); + + scsi_req_init(&vbr->sreq); +} +#endif + static const struct blk_mq_ops virtio_mq_ops = { .queue_rq = virtio_queue_rq, .complete = virtblk_request_done, .init_request = virtblk_init_request, +#ifdef CONFIG_VIRTIO_BLK_SCSI + .initialize_rq_fn = virtblk_initialize_rq, +#endif .map_queues = virtblk_map_queues, }; diff --git a/drivers/bus/mvebu-mbus.c b/drivers/bus/mvebu-mbus.c index c7f396903184..70db4d5638a6 100644 --- a/drivers/bus/mvebu-mbus.c +++ b/drivers/bus/mvebu-mbus.c @@ -720,7 +720,7 @@ mvebu_mbus_default_setup_cpu_target(struct mvebu_mbus_state *mbus) if (mbus->hw_io_coherency) w->mbus_attr |= ATTR_HW_COHERENCY; w->base = base & DDR_BASE_CS_LOW_MASK; - w->size = (size | ~DDR_SIZE_MASK) + 1; + w->size = (u64)(size | ~DDR_SIZE_MASK) + 1; } } mvebu_mbus_dram_info.num_cs = cs; diff --git a/drivers/clocksource/cs5535-clockevt.c b/drivers/clocksource/cs5535-clockevt.c index a1df588343f2..1de8cac99a0e 100644 --- a/drivers/clocksource/cs5535-clockevt.c +++ b/drivers/clocksource/cs5535-clockevt.c @@ -117,7 +117,8 @@ static irqreturn_t mfgpt_tick(int irq, void *dev_id) /* Turn off the clock (and clear the event) */ disable_timer(cs5535_event_clock); - if (clockevent_state_shutdown(&cs5535_clockevent)) + if (clockevent_state_detached(&cs5535_clockevent) || + clockevent_state_shutdown(&cs5535_clockevent)) return IRQ_HANDLED; /* Clear the counter */ diff --git a/drivers/crypto/axis/artpec6_crypto.c b/drivers/crypto/axis/artpec6_crypto.c index d9fbbf01062b..0f9754e07719 100644 --- a/drivers/crypto/axis/artpec6_crypto.c +++ b/drivers/crypto/axis/artpec6_crypto.c @@ -349,8 +349,6 @@ struct artpec6_crypto_aead_req_ctx { /* The crypto framework makes it hard to avoid this global. */ static struct device *artpec6_crypto_dev; -static struct dentry *dbgfs_root; - #ifdef CONFIG_FAULT_INJECTION static DECLARE_FAULT_ATTR(artpec6_crypto_fail_status_read); static DECLARE_FAULT_ATTR(artpec6_crypto_fail_dma_array_full); @@ -2984,6 +2982,8 @@ struct dbgfs_u32 { char *desc; }; +static struct dentry *dbgfs_root; + static void artpec6_crypto_init_debugfs(void) { dbgfs_root = debugfs_create_dir("artpec6_crypto", NULL); diff --git a/drivers/crypto/stm32/stm32-hash.c b/drivers/crypto/stm32/stm32-hash.c index b585ce54a802..4835dd4a9e50 100644 --- a/drivers/crypto/stm32/stm32-hash.c +++ b/drivers/crypto/stm32/stm32-hash.c @@ -553,9 +553,9 @@ static int stm32_hash_dma_send(struct stm32_hash_dev *hdev) { struct stm32_hash_request_ctx *rctx = ahash_request_ctx(hdev->req); struct scatterlist sg[1], *tsg; - int err = 0, len = 0, reg, ncp; + int err = 0, len = 0, reg, ncp = 0; unsigned int i; - const u32 *buffer = (const u32 *)rctx->buffer; + u32 *buffer = (void *)rctx->buffer; rctx->sg = hdev->req->src; rctx->total = hdev->req->nbytes; @@ -620,10 +620,13 @@ static int stm32_hash_dma_send(struct stm32_hash_dev *hdev) reg |= HASH_CR_DMAA; stm32_hash_write(hdev, HASH_CR, reg); - for (i = 0; i < DIV_ROUND_UP(ncp, sizeof(u32)); i++) - stm32_hash_write(hdev, HASH_DIN, buffer[i]); - - stm32_hash_set_nblw(hdev, ncp); + if (ncp) { + memset(buffer + ncp, 0, + DIV_ROUND_UP(ncp, sizeof(u32)) - ncp); + writesl(hdev->io_base + HASH_DIN, buffer, + DIV_ROUND_UP(ncp, sizeof(u32))); + } + stm32_hash_set_nblw(hdev, DIV_ROUND_UP(ncp, sizeof(u32))); reg = stm32_hash_read(hdev, HASH_STR); reg |= HASH_STR_DCAL; stm32_hash_write(hdev, HASH_STR, reg); diff --git a/drivers/dma-buf/sync_file.c b/drivers/dma-buf/sync_file.c index 66fb40d0ebdb..03830634e141 100644 --- a/drivers/dma-buf/sync_file.c +++ b/drivers/dma-buf/sync_file.c @@ -383,7 +383,7 @@ err_put_fd: return err; } -static void sync_fill_fence_info(struct dma_fence *fence, +static int sync_fill_fence_info(struct dma_fence *fence, struct sync_fence_info *info) { strlcpy(info->obj_name, fence->ops->get_timeline_name(fence), @@ -399,6 +399,8 @@ static void sync_fill_fence_info(struct dma_fence *fence, test_bit(DMA_FENCE_FLAG_TIMESTAMP_BIT, &fence->flags) ? ktime_to_ns(fence->timestamp) : ktime_set(0, 0); + + return info->status; } static long sync_file_ioctl_fence_info(struct sync_file *sync_file, @@ -424,8 +426,12 @@ static long sync_file_ioctl_fence_info(struct sync_file *sync_file, * sync_fence_info and return the actual number of fences on * info->num_fences. */ - if (!info.num_fences) + if (!info.num_fences) { + info.status = dma_fence_is_signaled(sync_file->fence); goto no_fences; + } else { + info.status = 1; + } if (info.num_fences < num_fences) return -EINVAL; @@ -435,8 +441,10 @@ static long sync_file_ioctl_fence_info(struct sync_file *sync_file, if (!fence_info) return -ENOMEM; - for (i = 0; i < num_fences; i++) - sync_fill_fence_info(fences[i], &fence_info[i]); + for (i = 0; i < num_fences; i++) { + int status = sync_fill_fence_info(fences[i], &fence_info[i]); + info.status = info.status <= 0 ? info.status : status; + } if (copy_to_user(u64_to_user_ptr(info.sync_fence_info), fence_info, size)) { @@ -446,7 +454,6 @@ static long sync_file_ioctl_fence_info(struct sync_file *sync_file, no_fences: sync_file_get_name(sync_file, info.name, sizeof(info.name)); - info.status = dma_fence_is_signaled(sync_file->fence); info.num_fences = num_fences; if (copy_to_user((void __user *)arg, &info, sizeof(info))) diff --git a/drivers/dma/altera-msgdma.c b/drivers/dma/altera-msgdma.c index 32905d5606ac..55f9c62ee54b 100644 --- a/drivers/dma/altera-msgdma.c +++ b/drivers/dma/altera-msgdma.c @@ -212,11 +212,12 @@ struct msgdma_device { static struct msgdma_sw_desc *msgdma_get_descriptor(struct msgdma_device *mdev) { struct msgdma_sw_desc *desc; + unsigned long flags; - spin_lock_bh(&mdev->lock); + spin_lock_irqsave(&mdev->lock, flags); desc = list_first_entry(&mdev->free_list, struct msgdma_sw_desc, node); list_del(&desc->node); - spin_unlock_bh(&mdev->lock); + spin_unlock_irqrestore(&mdev->lock, flags); INIT_LIST_HEAD(&desc->tx_list); @@ -306,13 +307,14 @@ static dma_cookie_t msgdma_tx_submit(struct dma_async_tx_descriptor *tx) struct msgdma_device *mdev = to_mdev(tx->chan); struct msgdma_sw_desc *new; dma_cookie_t cookie; + unsigned long flags; new = tx_to_desc(tx); - spin_lock_bh(&mdev->lock); + spin_lock_irqsave(&mdev->lock, flags); cookie = dma_cookie_assign(tx); list_add_tail(&new->node, &mdev->pending_list); - spin_unlock_bh(&mdev->lock); + spin_unlock_irqrestore(&mdev->lock, flags); return cookie; } @@ -336,17 +338,18 @@ msgdma_prep_memcpy(struct dma_chan *dchan, dma_addr_t dma_dst, struct msgdma_extended_desc *desc; size_t copy; u32 desc_cnt; + unsigned long irqflags; desc_cnt = DIV_ROUND_UP(len, MSGDMA_MAX_TRANS_LEN); - spin_lock_bh(&mdev->lock); + spin_lock_irqsave(&mdev->lock, irqflags); if (desc_cnt > mdev->desc_free_cnt) { - spin_unlock_bh(&mdev->lock); + spin_unlock_irqrestore(&mdev->lock, irqflags); dev_dbg(mdev->dev, "mdev %p descs are not available\n", mdev); return NULL; } mdev->desc_free_cnt -= desc_cnt; - spin_unlock_bh(&mdev->lock); + spin_unlock_irqrestore(&mdev->lock, irqflags); do { /* Allocate and populate the descriptor */ @@ -397,18 +400,19 @@ msgdma_prep_slave_sg(struct dma_chan *dchan, struct scatterlist *sgl, u32 desc_cnt = 0, i; struct scatterlist *sg; u32 stride; + unsigned long irqflags; for_each_sg(sgl, sg, sg_len, i) desc_cnt += DIV_ROUND_UP(sg_dma_len(sg), MSGDMA_MAX_TRANS_LEN); - spin_lock_bh(&mdev->lock); + spin_lock_irqsave(&mdev->lock, irqflags); if (desc_cnt > mdev->desc_free_cnt) { - spin_unlock_bh(&mdev->lock); + spin_unlock_irqrestore(&mdev->lock, irqflags); dev_dbg(mdev->dev, "mdev %p descs are not available\n", mdev); return NULL; } mdev->desc_free_cnt -= desc_cnt; - spin_unlock_bh(&mdev->lock); + spin_unlock_irqrestore(&mdev->lock, irqflags); avail = sg_dma_len(sgl); @@ -566,10 +570,11 @@ static void msgdma_start_transfer(struct msgdma_device *mdev) static void msgdma_issue_pending(struct dma_chan *chan) { struct msgdma_device *mdev = to_mdev(chan); + unsigned long flags; - spin_lock_bh(&mdev->lock); + spin_lock_irqsave(&mdev->lock, flags); msgdma_start_transfer(mdev); - spin_unlock_bh(&mdev->lock); + spin_unlock_irqrestore(&mdev->lock, flags); } /** @@ -634,10 +639,11 @@ static void msgdma_free_descriptors(struct msgdma_device *mdev) static void msgdma_free_chan_resources(struct dma_chan *dchan) { struct msgdma_device *mdev = to_mdev(dchan); + unsigned long flags; - spin_lock_bh(&mdev->lock); + spin_lock_irqsave(&mdev->lock, flags); msgdma_free_descriptors(mdev); - spin_unlock_bh(&mdev->lock); + spin_unlock_irqrestore(&mdev->lock, flags); kfree(mdev->sw_desq); } @@ -682,8 +688,9 @@ static void msgdma_tasklet(unsigned long data) u32 count; u32 __maybe_unused size; u32 __maybe_unused status; + unsigned long flags; - spin_lock(&mdev->lock); + spin_lock_irqsave(&mdev->lock, flags); /* Read number of responses that are available */ count = ioread32(mdev->csr + MSGDMA_CSR_RESP_FILL_LEVEL); @@ -698,13 +705,13 @@ static void msgdma_tasklet(unsigned long data) * bits. So we need to just drop these values. */ size = ioread32(mdev->resp + MSGDMA_RESP_BYTES_TRANSFERRED); - status = ioread32(mdev->resp - MSGDMA_RESP_STATUS); + status = ioread32(mdev->resp + MSGDMA_RESP_STATUS); msgdma_complete_descriptor(mdev); msgdma_chan_desc_cleanup(mdev); } - spin_unlock(&mdev->lock); + spin_unlock_irqrestore(&mdev->lock, flags); } /** diff --git a/drivers/dma/edma.c b/drivers/dma/edma.c index 3879f80a4815..a7ea20e7b8e9 100644 --- a/drivers/dma/edma.c +++ b/drivers/dma/edma.c @@ -1143,11 +1143,24 @@ static struct dma_async_tx_descriptor *edma_prep_dma_memcpy( struct edma_desc *edesc; struct device *dev = chan->device->dev; struct edma_chan *echan = to_edma_chan(chan); - unsigned int width, pset_len; + unsigned int width, pset_len, array_size; if (unlikely(!echan || !len)) return NULL; + /* Align the array size (acnt block) with the transfer properties */ + switch (__ffs((src | dest | len))) { + case 0: + array_size = SZ_32K - 1; + break; + case 1: + array_size = SZ_32K - 2; + break; + default: + array_size = SZ_32K - 4; + break; + } + if (len < SZ_64K) { /* * Transfer size less than 64K can be handled with one paRAM @@ -1169,7 +1182,7 @@ static struct dma_async_tx_descriptor *edma_prep_dma_memcpy( * When the full_length is multibple of 32767 one slot can be * used to complete the transfer. */ - width = SZ_32K - 1; + width = array_size; pset_len = rounddown(len, width); /* One slot is enough for lengths multiple of (SZ_32K -1) */ if (unlikely(pset_len == len)) @@ -1217,7 +1230,7 @@ static struct dma_async_tx_descriptor *edma_prep_dma_memcpy( } dest += pset_len; src += pset_len; - pset_len = width = len % (SZ_32K - 1); + pset_len = width = len % array_size; ret = edma_config_pset(chan, &edesc->pset[1], src, dest, 1, width, pset_len, DMA_MEM_TO_MEM); diff --git a/drivers/dma/ti-dma-crossbar.c b/drivers/dma/ti-dma-crossbar.c index 2f65a8fde21d..f1d04b70ee67 100644 --- a/drivers/dma/ti-dma-crossbar.c +++ b/drivers/dma/ti-dma-crossbar.c @@ -262,13 +262,14 @@ static void *ti_dra7_xbar_route_allocate(struct of_phandle_args *dma_spec, mutex_lock(&xbar->mutex); map->xbar_out = find_first_zero_bit(xbar->dma_inuse, xbar->dma_requests); - mutex_unlock(&xbar->mutex); if (map->xbar_out == xbar->dma_requests) { + mutex_unlock(&xbar->mutex); dev_err(&pdev->dev, "Run out of free DMA requests\n"); kfree(map); return ERR_PTR(-ENOMEM); } set_bit(map->xbar_out, xbar->dma_inuse); + mutex_unlock(&xbar->mutex); map->xbar_in = (u16)dma_spec->args[0]; diff --git a/drivers/firmware/efi/libstub/arm-stub.c b/drivers/firmware/efi/libstub/arm-stub.c index 1cb2d1c070c3..a94601d5939e 100644 --- a/drivers/firmware/efi/libstub/arm-stub.c +++ b/drivers/firmware/efi/libstub/arm-stub.c @@ -238,7 +238,8 @@ unsigned long efi_entry(void *handle, efi_system_table_t *sys_table, efi_random_get_seed(sys_table); - if (!nokaslr()) { + /* hibernation expects the runtime regions to stay in the same place */ + if (!IS_ENABLED(CONFIG_HIBERNATION) && !nokaslr()) { /* * Randomize the base of the UEFI runtime services region. * Preserve the 2 MB alignment of the region by taking a diff --git a/drivers/firmware/efi/test/efi_test.c b/drivers/firmware/efi/test/efi_test.c index 08129b7b80ab..41c48a1e8baa 100644 --- a/drivers/firmware/efi/test/efi_test.c +++ b/drivers/firmware/efi/test/efi_test.c @@ -593,6 +593,9 @@ static long efi_runtime_query_capsulecaps(unsigned long arg) if (copy_from_user(&qcaps, qcaps_user, sizeof(qcaps))) return -EFAULT; + if (qcaps.capsule_count == ULONG_MAX) + return -EINVAL; + capsules = kcalloc(qcaps.capsule_count + 1, sizeof(efi_capsule_header_t), GFP_KERNEL); if (!capsules) diff --git a/drivers/gpio/Kconfig b/drivers/gpio/Kconfig index 3388d54ba114..3f80f167ed56 100644 --- a/drivers/gpio/Kconfig +++ b/drivers/gpio/Kconfig @@ -453,7 +453,8 @@ config GPIO_TS4800 config GPIO_THUNDERX tristate "Cavium ThunderX/OCTEON-TX GPIO" depends on ARCH_THUNDER || (64BIT && COMPILE_TEST) - depends on PCI_MSI && IRQ_DOMAIN_HIERARCHY + depends on PCI_MSI + select IRQ_DOMAIN_HIERARCHY select IRQ_FASTEOI_HIERARCHY_HANDLERS help Say yes here to support the on-chip GPIO lines on the ThunderX diff --git a/drivers/gpio/gpio-omap.c b/drivers/gpio/gpio-omap.c index dbf869fb63ce..3233b72b6828 100644 --- a/drivers/gpio/gpio-omap.c +++ b/drivers/gpio/gpio-omap.c @@ -518,7 +518,13 @@ static int omap_gpio_irq_type(struct irq_data *d, unsigned type) if (type & (IRQ_TYPE_LEVEL_LOW | IRQ_TYPE_LEVEL_HIGH)) irq_set_handler_locked(d, handle_level_irq); else if (type & (IRQ_TYPE_EDGE_FALLING | IRQ_TYPE_EDGE_RISING)) - irq_set_handler_locked(d, handle_edge_irq); + /* + * Edge IRQs are already cleared/acked in irq_handler and + * not need to be masked, as result handle_edge_irq() + * logic is excessed here and may cause lose of interrupts. + * So just use handle_simple_irq. + */ + irq_set_handler_locked(d, handle_simple_irq); return 0; @@ -678,7 +684,7 @@ static void omap_gpio_free(struct gpio_chip *chip, unsigned offset) static irqreturn_t omap_gpio_irq_handler(int irq, void *gpiobank) { void __iomem *isr_reg = NULL; - u32 isr; + u32 enabled, isr, level_mask; unsigned int bit; struct gpio_bank *bank = gpiobank; unsigned long wa_lock_flags; @@ -691,23 +697,21 @@ static irqreturn_t omap_gpio_irq_handler(int irq, void *gpiobank) pm_runtime_get_sync(bank->chip.parent); while (1) { - u32 isr_saved, level_mask = 0; - u32 enabled; - raw_spin_lock_irqsave(&bank->lock, lock_flags); enabled = omap_get_gpio_irqbank_mask(bank); - isr_saved = isr = readl_relaxed(isr_reg) & enabled; + isr = readl_relaxed(isr_reg) & enabled; if (bank->level_mask) level_mask = bank->level_mask & enabled; + else + level_mask = 0; /* clear edge sensitive interrupts before handler(s) are called so that we don't miss any interrupt occurred while executing them */ - omap_disable_gpio_irqbank(bank, isr_saved & ~level_mask); - omap_clear_gpio_irqbank(bank, isr_saved & ~level_mask); - omap_enable_gpio_irqbank(bank, isr_saved & ~level_mask); + if (isr & ~level_mask) + omap_clear_gpio_irqbank(bank, isr & ~level_mask); raw_spin_unlock_irqrestore(&bank->lock, lock_flags); @@ -1010,7 +1014,7 @@ static void omap_gpio_set(struct gpio_chip *chip, unsigned offset, int value) /*---------------------------------------------------------------------*/ -static void __init omap_gpio_show_rev(struct gpio_bank *bank) +static void omap_gpio_show_rev(struct gpio_bank *bank) { static bool called; u32 rev; diff --git a/drivers/gpio/gpiolib-acpi.c b/drivers/gpio/gpiolib-acpi.c index 4d2113530735..eb4528c87c0b 100644 --- a/drivers/gpio/gpiolib-acpi.c +++ b/drivers/gpio/gpiolib-acpi.c @@ -203,7 +203,7 @@ static acpi_status acpi_gpiochip_request_interrupt(struct acpi_resource *ares, if (pin <= 255) { char ev_name[5]; - sprintf(ev_name, "_%c%02X", + sprintf(ev_name, "_%c%02hhX", agpio->triggering == ACPI_EDGE_SENSITIVE ? 'E' : 'L', pin); if (ACPI_SUCCESS(acpi_get_handle(handle, ev_name, &evt_handle))) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c index 7ef6c28a34d9..bc746131987f 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c @@ -834,7 +834,7 @@ int amdgpu_ttm_bind(struct ttm_buffer_object *bo, struct ttm_mem_reg *bo_mem) placement.busy_placement = &placements; placements.fpfn = 0; placements.lpfn = adev->mc.gart_size >> PAGE_SHIFT; - placements.flags = TTM_PL_MASK_CACHING | TTM_PL_FLAG_TT; + placements.flags = bo->mem.placement | TTM_PL_FLAG_TT; r = ttm_bo_mem_space(bo, &placement, &tmp, true, false); if (unlikely(r)) diff --git a/drivers/gpu/drm/amd/amdgpu/uvd_v6_0.c b/drivers/gpu/drm/amd/amdgpu/uvd_v6_0.c index 31db356476f8..430a6b4dfac9 100644 --- a/drivers/gpu/drm/amd/amdgpu/uvd_v6_0.c +++ b/drivers/gpu/drm/amd/amdgpu/uvd_v6_0.c @@ -225,11 +225,7 @@ static int uvd_v6_0_suspend(void *handle) if (r) return r; - /* Skip this for APU for now */ - if (!(adev->flags & AMD_IS_APU)) - r = amdgpu_uvd_suspend(adev); - - return r; + return amdgpu_uvd_suspend(adev); } static int uvd_v6_0_resume(void *handle) @@ -237,12 +233,10 @@ static int uvd_v6_0_resume(void *handle) int r; struct amdgpu_device *adev = (struct amdgpu_device *)handle; - /* Skip this for APU for now */ - if (!(adev->flags & AMD_IS_APU)) { - r = amdgpu_uvd_resume(adev); - if (r) - return r; - } + r = amdgpu_uvd_resume(adev); + if (r) + return r; + return uvd_v6_0_hw_init(adev); } diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_hwmgr.c b/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_hwmgr.c index c2743233ba10..b526f49be65d 100644 --- a/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_hwmgr.c +++ b/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_hwmgr.c @@ -830,7 +830,7 @@ uint32_t smu7_get_xclk(struct pp_hwmgr *hwmgr) { uint32_t reference_clock, tmp; struct cgs_display_info info = {0}; - struct cgs_mode_info mode_info; + struct cgs_mode_info mode_info = {0}; info.mode_info = &mode_info; @@ -3948,10 +3948,9 @@ static int smu7_program_display_gap(struct pp_hwmgr *hwmgr) uint32_t ref_clock; uint32_t refresh_rate = 0; struct cgs_display_info info = {0}; - struct cgs_mode_info mode_info; + struct cgs_mode_info mode_info = {0}; info.mode_info = &mode_info; - cgs_get_active_displays_info(hwmgr->device, &info); num_active_displays = info.display_count; @@ -3967,6 +3966,7 @@ static int smu7_program_display_gap(struct pp_hwmgr *hwmgr) frame_time_in_us = 1000000 / refresh_rate; pre_vbi_time_in_us = frame_time_in_us - 200 - mode_info.vblank_time_us; + data->frame_time_x2 = frame_time_in_us * 2 / 100; display_gap2 = pre_vbi_time_in_us * (ref_clock / 100); diff --git a/drivers/gpu/drm/amd/scheduler/gpu_scheduler.c b/drivers/gpu/drm/amd/scheduler/gpu_scheduler.c index 97c94f9683fa..38cea6fb25a8 100644 --- a/drivers/gpu/drm/amd/scheduler/gpu_scheduler.c +++ b/drivers/gpu/drm/amd/scheduler/gpu_scheduler.c @@ -205,32 +205,17 @@ void amd_sched_entity_fini(struct amd_gpu_scheduler *sched, struct amd_sched_entity *entity) { struct amd_sched_rq *rq = entity->rq; - int r; if (!amd_sched_entity_is_initialized(sched, entity)) return; + /** * The client will not queue more IBs during this fini, consume existing - * queued IBs or discard them on SIGKILL + * queued IBs */ - if ((current->flags & PF_SIGNALED) && current->exit_code == SIGKILL) - r = -ERESTARTSYS; - else - r = wait_event_killable(sched->job_scheduled, - amd_sched_entity_is_idle(entity)); - amd_sched_rq_remove_entity(rq, entity); - if (r) { - struct amd_sched_job *job; + wait_event(sched->job_scheduled, amd_sched_entity_is_idle(entity)); - /* Park the kernel for a moment to make sure it isn't processing - * our enity. - */ - kthread_park(sched->thread); - kthread_unpark(sched->thread); - while (kfifo_out(&entity->job_queue, &job, sizeof(job))) - sched->ops->free_job(job); - - } + amd_sched_rq_remove_entity(rq, entity); kfifo_free(&entity->job_queue); } diff --git a/drivers/gpu/drm/drm_atomic_helper.c b/drivers/gpu/drm/drm_atomic_helper.c index 4e53aae9a1fb..0028591f3f95 100644 --- a/drivers/gpu/drm/drm_atomic_helper.c +++ b/drivers/gpu/drm/drm_atomic_helper.c @@ -2960,6 +2960,7 @@ out: drm_modeset_backoff(&ctx); } + drm_atomic_state_put(state); drm_modeset_drop_locks(&ctx); drm_modeset_acquire_fini(&ctx); diff --git a/drivers/gpu/drm/exynos/exynos_drm_drv.c b/drivers/gpu/drm/exynos/exynos_drm_drv.c index e651a58c18cf..82b72425a42f 100644 --- a/drivers/gpu/drm/exynos/exynos_drm_drv.c +++ b/drivers/gpu/drm/exynos/exynos_drm_drv.c @@ -168,11 +168,13 @@ static struct drm_driver exynos_drm_driver = { static int exynos_drm_suspend(struct device *dev) { struct drm_device *drm_dev = dev_get_drvdata(dev); - struct exynos_drm_private *private = drm_dev->dev_private; + struct exynos_drm_private *private; if (pm_runtime_suspended(dev) || !drm_dev) return 0; + private = drm_dev->dev_private; + drm_kms_helper_poll_disable(drm_dev); exynos_drm_fbdev_suspend(drm_dev); private->suspend_state = drm_atomic_helper_suspend(drm_dev); @@ -188,11 +190,12 @@ static int exynos_drm_suspend(struct device *dev) static int exynos_drm_resume(struct device *dev) { struct drm_device *drm_dev = dev_get_drvdata(dev); - struct exynos_drm_private *private = drm_dev->dev_private; + struct exynos_drm_private *private; if (pm_runtime_suspended(dev) || !drm_dev) return 0; + private = drm_dev->dev_private; drm_atomic_helper_resume(drm_dev, private->suspend_state); exynos_drm_fbdev_resume(drm_dev); drm_kms_helper_poll_enable(drm_dev); @@ -427,6 +430,7 @@ static void exynos_drm_unbind(struct device *dev) kfree(drm->dev_private); drm->dev_private = NULL; + dev_set_drvdata(dev, NULL); drm_dev_unref(drm); } diff --git a/drivers/gpu/drm/i915/gvt/cmd_parser.c b/drivers/gpu/drm/i915/gvt/cmd_parser.c index 21c36e256884..d4726a3358a4 100644 --- a/drivers/gpu/drm/i915/gvt/cmd_parser.c +++ b/drivers/gpu/drm/i915/gvt/cmd_parser.c @@ -2723,6 +2723,9 @@ static int combine_wa_ctx(struct intel_shadow_wa_ctx *wa_ctx) uint32_t per_ctx_start[CACHELINE_DWORDS] = {0}; unsigned char *bb_start_sva; + if (!wa_ctx->per_ctx.valid) + return 0; + per_ctx_start[0] = 0x18800001; per_ctx_start[1] = wa_ctx->per_ctx.guest_gma; diff --git a/drivers/gpu/drm/i915/gvt/execlist.c b/drivers/gpu/drm/i915/gvt/execlist.c index 91b4300f3b39..e5320b4eb698 100644 --- a/drivers/gpu/drm/i915/gvt/execlist.c +++ b/drivers/gpu/drm/i915/gvt/execlist.c @@ -701,8 +701,7 @@ static int submit_context(struct intel_vgpu *vgpu, int ring_id, CACHELINE_BYTES; workload->wa_ctx.per_ctx.guest_gma = per_ctx & PER_CTX_ADDR_MASK; - - WARN_ON(workload->wa_ctx.indirect_ctx.size && !(per_ctx & 0x1)); + workload->wa_ctx.per_ctx.valid = per_ctx & 1; } if (emulate_schedule_in) diff --git a/drivers/gpu/drm/i915/gvt/handlers.c b/drivers/gpu/drm/i915/gvt/handlers.c index 2294466dd415..a5bed2e71b92 100644 --- a/drivers/gpu/drm/i915/gvt/handlers.c +++ b/drivers/gpu/drm/i915/gvt/handlers.c @@ -1429,18 +1429,7 @@ static int skl_lcpll_write(struct intel_vgpu *vgpu, unsigned int offset, return 0; } -static int ring_timestamp_mmio_read(struct intel_vgpu *vgpu, - unsigned int offset, void *p_data, unsigned int bytes) -{ - struct drm_i915_private *dev_priv = vgpu->gvt->dev_priv; - - mmio_hw_access_pre(dev_priv); - vgpu_vreg(vgpu, offset) = I915_READ(_MMIO(offset)); - mmio_hw_access_post(dev_priv); - return intel_vgpu_default_mmio_read(vgpu, offset, p_data, bytes); -} - -static int instdone_mmio_read(struct intel_vgpu *vgpu, +static int mmio_read_from_hw(struct intel_vgpu *vgpu, unsigned int offset, void *p_data, unsigned int bytes) { struct drm_i915_private *dev_priv = vgpu->gvt->dev_priv; @@ -1589,6 +1578,8 @@ static int ring_reset_ctl_write(struct intel_vgpu *vgpu, MMIO_F(prefix(BLT_RING_BASE), s, f, am, rm, d, r, w); \ MMIO_F(prefix(GEN6_BSD_RING_BASE), s, f, am, rm, d, r, w); \ MMIO_F(prefix(VEBOX_RING_BASE), s, f, am, rm, d, r, w); \ + if (HAS_BSD2(dev_priv)) \ + MMIO_F(prefix(GEN8_BSD2_RING_BASE), s, f, am, rm, d, r, w); \ } while (0) #define MMIO_RING_D(prefix, d) \ @@ -1635,10 +1626,9 @@ static int init_generic_mmio_info(struct intel_gvt *gvt) #undef RING_REG #define RING_REG(base) (base + 0x6c) - MMIO_RING_DFH(RING_REG, D_ALL, 0, instdone_mmio_read, NULL); - MMIO_DH(RING_REG(GEN8_BSD2_RING_BASE), D_ALL, instdone_mmio_read, NULL); + MMIO_RING_DFH(RING_REG, D_ALL, 0, mmio_read_from_hw, NULL); #undef RING_REG - MMIO_DH(GEN7_SC_INSTDONE, D_BDW_PLUS, instdone_mmio_read, NULL); + MMIO_DH(GEN7_SC_INSTDONE, D_BDW_PLUS, mmio_read_from_hw, NULL); MMIO_GM_RDR(0x2148, D_ALL, NULL, NULL); MMIO_GM_RDR(CCID, D_ALL, NULL, NULL); @@ -1648,7 +1638,7 @@ static int init_generic_mmio_info(struct intel_gvt *gvt) MMIO_RING_DFH(RING_TAIL, D_ALL, F_CMD_ACCESS, NULL, NULL); MMIO_RING_DFH(RING_HEAD, D_ALL, F_CMD_ACCESS, NULL, NULL); MMIO_RING_DFH(RING_CTL, D_ALL, F_CMD_ACCESS, NULL, NULL); - MMIO_RING_DFH(RING_ACTHD, D_ALL, F_CMD_ACCESS, NULL, NULL); + MMIO_RING_DFH(RING_ACTHD, D_ALL, F_CMD_ACCESS, mmio_read_from_hw, NULL); MMIO_RING_GM_RDR(RING_START, D_ALL, NULL, NULL); /* RING MODE */ @@ -1662,9 +1652,9 @@ static int init_generic_mmio_info(struct intel_gvt *gvt) MMIO_RING_DFH(RING_INSTPM, D_ALL, F_MODE_MASK | F_CMD_ACCESS, NULL, NULL); MMIO_RING_DFH(RING_TIMESTAMP, D_ALL, F_CMD_ACCESS, - ring_timestamp_mmio_read, NULL); + mmio_read_from_hw, NULL); MMIO_RING_DFH(RING_TIMESTAMP_UDW, D_ALL, F_CMD_ACCESS, - ring_timestamp_mmio_read, NULL); + mmio_read_from_hw, NULL); MMIO_DFH(GEN7_GT_MODE, D_ALL, F_MODE_MASK | F_CMD_ACCESS, NULL, NULL); MMIO_DFH(CACHE_MODE_0_GEN7, D_ALL, F_MODE_MASK | F_CMD_ACCESS, @@ -2411,9 +2401,6 @@ static int init_broadwell_mmio_info(struct intel_gvt *gvt) struct drm_i915_private *dev_priv = gvt->dev_priv; int ret; - MMIO_DFH(RING_IMR(GEN8_BSD2_RING_BASE), D_BDW_PLUS, F_CMD_ACCESS, NULL, - intel_vgpu_reg_imr_handler); - MMIO_DH(GEN8_GT_IMR(0), D_BDW_PLUS, NULL, intel_vgpu_reg_imr_handler); MMIO_DH(GEN8_GT_IER(0), D_BDW_PLUS, NULL, intel_vgpu_reg_ier_handler); MMIO_DH(GEN8_GT_IIR(0), D_BDW_PLUS, NULL, intel_vgpu_reg_iir_handler); @@ -2476,68 +2463,34 @@ static int init_broadwell_mmio_info(struct intel_gvt *gvt) MMIO_DH(GEN8_MASTER_IRQ, D_BDW_PLUS, NULL, intel_vgpu_reg_master_irq_handler); - MMIO_DFH(RING_HWSTAM(GEN8_BSD2_RING_BASE), D_BDW_PLUS, - F_CMD_ACCESS, NULL, NULL); - MMIO_DFH(0x1c134, D_BDW_PLUS, F_CMD_ACCESS, NULL, NULL); - - MMIO_DFH(RING_TAIL(GEN8_BSD2_RING_BASE), D_BDW_PLUS, F_CMD_ACCESS, - NULL, NULL); - MMIO_DFH(RING_HEAD(GEN8_BSD2_RING_BASE), D_BDW_PLUS, - F_CMD_ACCESS, NULL, NULL); - MMIO_GM_RDR(RING_START(GEN8_BSD2_RING_BASE), D_BDW_PLUS, NULL, NULL); - MMIO_DFH(RING_CTL(GEN8_BSD2_RING_BASE), D_BDW_PLUS, F_CMD_ACCESS, - NULL, NULL); - MMIO_DFH(RING_ACTHD(GEN8_BSD2_RING_BASE), D_BDW_PLUS, - F_CMD_ACCESS, NULL, NULL); - MMIO_DFH(RING_ACTHD_UDW(GEN8_BSD2_RING_BASE), D_BDW_PLUS, - F_CMD_ACCESS, NULL, NULL); - MMIO_DFH(0x1c29c, D_BDW_PLUS, F_MODE_MASK | F_CMD_ACCESS, NULL, - ring_mode_mmio_write); - MMIO_DFH(RING_MI_MODE(GEN8_BSD2_RING_BASE), D_BDW_PLUS, - F_MODE_MASK | F_CMD_ACCESS, NULL, NULL); - MMIO_DFH(RING_INSTPM(GEN8_BSD2_RING_BASE), D_BDW_PLUS, - F_MODE_MASK | F_CMD_ACCESS, NULL, NULL); - MMIO_DFH(RING_TIMESTAMP(GEN8_BSD2_RING_BASE), D_BDW_PLUS, F_CMD_ACCESS, - ring_timestamp_mmio_read, NULL); - - MMIO_RING_DFH(RING_ACTHD_UDW, D_BDW_PLUS, F_CMD_ACCESS, NULL, NULL); + MMIO_RING_DFH(RING_ACTHD_UDW, D_BDW_PLUS, F_CMD_ACCESS, + mmio_read_from_hw, NULL); #define RING_REG(base) (base + 0xd0) MMIO_RING_F(RING_REG, 4, F_RO, 0, ~_MASKED_BIT_ENABLE(RESET_CTL_REQUEST_RESET), D_BDW_PLUS, NULL, ring_reset_ctl_write); - MMIO_F(RING_REG(GEN8_BSD2_RING_BASE), 4, F_RO, 0, - ~_MASKED_BIT_ENABLE(RESET_CTL_REQUEST_RESET), D_BDW_PLUS, NULL, - ring_reset_ctl_write); #undef RING_REG #define RING_REG(base) (base + 0x230) MMIO_RING_DFH(RING_REG, D_BDW_PLUS, 0, NULL, elsp_mmio_write); - MMIO_DH(RING_REG(GEN8_BSD2_RING_BASE), D_BDW_PLUS, NULL, elsp_mmio_write); #undef RING_REG #define RING_REG(base) (base + 0x234) MMIO_RING_F(RING_REG, 8, F_RO | F_CMD_ACCESS, 0, ~0, D_BDW_PLUS, NULL, NULL); - MMIO_F(RING_REG(GEN8_BSD2_RING_BASE), 4, F_RO | F_CMD_ACCESS, 0, - ~0LL, D_BDW_PLUS, NULL, NULL); #undef RING_REG #define RING_REG(base) (base + 0x244) MMIO_RING_DFH(RING_REG, D_BDW_PLUS, F_CMD_ACCESS, NULL, NULL); - MMIO_DFH(RING_REG(GEN8_BSD2_RING_BASE), D_BDW_PLUS, F_CMD_ACCESS, - NULL, NULL); #undef RING_REG #define RING_REG(base) (base + 0x370) MMIO_RING_F(RING_REG, 48, F_RO, 0, ~0, D_BDW_PLUS, NULL, NULL); - MMIO_F(RING_REG(GEN8_BSD2_RING_BASE), 48, F_RO, 0, ~0, D_BDW_PLUS, - NULL, NULL); #undef RING_REG #define RING_REG(base) (base + 0x3a0) MMIO_RING_DFH(RING_REG, D_BDW_PLUS, F_MODE_MASK, NULL, NULL); - MMIO_DFH(RING_REG(GEN8_BSD2_RING_BASE), D_BDW_PLUS, F_MODE_MASK, NULL, NULL); #undef RING_REG MMIO_D(PIPEMISC(PIPE_A), D_BDW_PLUS); @@ -2557,11 +2510,9 @@ static int init_broadwell_mmio_info(struct intel_gvt *gvt) #define RING_REG(base) (base + 0x270) MMIO_RING_F(RING_REG, 32, 0, 0, 0, D_BDW_PLUS, NULL, NULL); - MMIO_F(RING_REG(GEN8_BSD2_RING_BASE), 32, 0, 0, 0, D_BDW_PLUS, NULL, NULL); #undef RING_REG MMIO_RING_GM_RDR(RING_HWS_PGA, D_BDW_PLUS, NULL, NULL); - MMIO_GM_RDR(RING_HWS_PGA(GEN8_BSD2_RING_BASE), D_BDW_PLUS, NULL, NULL); MMIO_DFH(HDC_CHICKEN0, D_BDW_PLUS, F_MODE_MASK | F_CMD_ACCESS, NULL, NULL); @@ -2849,7 +2800,6 @@ static int init_skl_mmio_info(struct intel_gvt *gvt) MMIO_D(0x65f08, D_SKL | D_KBL); MMIO_D(0x320f0, D_SKL | D_KBL); - MMIO_DFH(_REG_VCS2_EXCC, D_SKL_PLUS, F_CMD_ACCESS, NULL, NULL); MMIO_D(0x70034, D_SKL_PLUS); MMIO_D(0x71034, D_SKL_PLUS); MMIO_D(0x72034, D_SKL_PLUS); diff --git a/drivers/gpu/drm/i915/gvt/reg.h b/drivers/gpu/drm/i915/gvt/reg.h index fbd023a16f18..7d01c77a0f7a 100644 --- a/drivers/gpu/drm/i915/gvt/reg.h +++ b/drivers/gpu/drm/i915/gvt/reg.h @@ -54,9 +54,6 @@ #define VGT_SPRSTRIDE(pipe) _PIPE(pipe, _SPRA_STRIDE, _PLANE_STRIDE_2_B) -#define _REG_VECS_EXCC 0x1A028 -#define _REG_VCS2_EXCC 0x1c028 - #define _REG_701C0(pipe, plane) (0x701c0 + pipe * 0x1000 + (plane - 1) * 0x100) #define _REG_701C4(pipe, plane) (0x701c4 + pipe * 0x1000 + (plane - 1) * 0x100) diff --git a/drivers/gpu/drm/i915/gvt/sched_policy.c b/drivers/gpu/drm/i915/gvt/sched_policy.c index 436377da41ba..03532dfc0cd5 100644 --- a/drivers/gpu/drm/i915/gvt/sched_policy.c +++ b/drivers/gpu/drm/i915/gvt/sched_policy.c @@ -308,20 +308,8 @@ static int tbs_sched_init_vgpu(struct intel_vgpu *vgpu) static void tbs_sched_clean_vgpu(struct intel_vgpu *vgpu) { - struct intel_gvt_workload_scheduler *scheduler = &vgpu->gvt->scheduler; - int ring_id; - kfree(vgpu->sched_data); vgpu->sched_data = NULL; - - 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) { - intel_gvt_switch_mmio(vgpu, NULL, ring_id); - scheduler->engine_owner[ring_id] = NULL; - } - } - spin_unlock_bh(&scheduler->mmio_context_lock); } static void tbs_sched_start_schedule(struct intel_vgpu *vgpu) @@ -388,6 +376,7 @@ void intel_vgpu_stop_schedule(struct intel_vgpu *vgpu) { struct intel_gvt_workload_scheduler *scheduler = &vgpu->gvt->scheduler; + int ring_id; gvt_dbg_core("vgpu%d: stop schedule\n", vgpu->id); @@ -401,4 +390,13 @@ void intel_vgpu_stop_schedule(struct intel_vgpu *vgpu) scheduler->need_reschedule = true; scheduler->current_vgpu = NULL; } + + 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) { + intel_gvt_switch_mmio(vgpu, NULL, ring_id); + scheduler->engine_owner[ring_id] = NULL; + } + } + spin_unlock_bh(&scheduler->mmio_context_lock); } diff --git a/drivers/gpu/drm/i915/gvt/scheduler.h b/drivers/gpu/drm/i915/gvt/scheduler.h index 0d431a968a32..93a49eb0209e 100644 --- a/drivers/gpu/drm/i915/gvt/scheduler.h +++ b/drivers/gpu/drm/i915/gvt/scheduler.h @@ -68,6 +68,7 @@ struct shadow_indirect_ctx { struct shadow_per_ctx { unsigned long guest_gma; unsigned long shadow_gma; + unsigned valid; }; struct intel_shadow_wa_ctx { diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c index 19404c96eeb1..32e857dc507c 100644 --- a/drivers/gpu/drm/i915/i915_gem.c +++ b/drivers/gpu/drm/i915/i915_gem.c @@ -2657,6 +2657,9 @@ i915_gem_object_pwrite_gtt(struct drm_i915_gem_object *obj, if (READ_ONCE(obj->mm.pages)) return -ENODEV; + if (obj->mm.madv != I915_MADV_WILLNEED) + return -EFAULT; + /* Before the pages are instantiated the object is treated as being * in the CPU domain. The pages will be clflushed as required before * use, and we can freely write into the pages directly. If userspace @@ -3013,10 +3016,15 @@ void i915_gem_reset_finish(struct drm_i915_private *dev_priv) static void nop_submit_request(struct drm_i915_gem_request *request) { + unsigned long flags; + GEM_BUG_ON(!i915_terminally_wedged(&request->i915->gpu_error)); dma_fence_set_error(&request->fence, -EIO); - i915_gem_request_submit(request); + + spin_lock_irqsave(&request->engine->timeline->lock, flags); + __i915_gem_request_submit(request); intel_engine_init_global_seqno(request->engine, request->global_seqno); + spin_unlock_irqrestore(&request->engine->timeline->lock, flags); } static void engine_set_wedged(struct intel_engine_cs *engine) diff --git a/drivers/gpu/drm/i915/i915_gem_evict.c b/drivers/gpu/drm/i915/i915_gem_evict.c index 4df039ef2ce3..e161d383b526 100644 --- a/drivers/gpu/drm/i915/i915_gem_evict.c +++ b/drivers/gpu/drm/i915/i915_gem_evict.c @@ -33,21 +33,20 @@ #include "intel_drv.h" #include "i915_trace.h" -static bool ggtt_is_idle(struct drm_i915_private *dev_priv) +static bool ggtt_is_idle(struct drm_i915_private *i915) { - struct i915_ggtt *ggtt = &dev_priv->ggtt; - struct intel_engine_cs *engine; - enum intel_engine_id id; + struct intel_engine_cs *engine; + enum intel_engine_id id; - for_each_engine(engine, dev_priv, id) { - struct intel_timeline *tl; + if (i915->gt.active_requests) + return false; - tl = &ggtt->base.timeline.engine[engine->id]; - if (i915_gem_active_isset(&tl->last_request)) - return false; - } + for_each_engine(engine, i915, id) { + if (engine->last_retired_context != i915->kernel_context) + return false; + } - return true; + return true; } static int ggtt_flush(struct drm_i915_private *i915) @@ -157,7 +156,8 @@ i915_gem_evict_something(struct i915_address_space *vm, min_size, alignment, cache_level, start, end, mode); - /* Retire before we search the active list. Although we have + /* + * Retire before we search the active list. Although we have * reasonable accuracy in our retirement lists, we may have * a stray pin (preventing eviction) that can only be resolved by * retiring. @@ -182,7 +182,8 @@ search_again: BUG_ON(ret); } - /* Can we unpin some objects such as idle hw contents, + /* + * Can we unpin some objects such as idle hw contents, * or pending flips? But since only the GGTT has global entries * such as scanouts, rinbuffers and contexts, we can skip the * purge when inspecting per-process local address spaces. @@ -190,19 +191,33 @@ search_again: if (!i915_is_ggtt(vm) || flags & PIN_NONBLOCK) return -ENOSPC; - if (ggtt_is_idle(dev_priv)) { - /* If we still have pending pageflip completions, drop - * back to userspace to give our workqueues time to - * acquire our locks and unpin the old scanouts. - */ - return intel_has_pending_fb_unpin(dev_priv) ? -EAGAIN : -ENOSPC; - } + /* + * Not everything in the GGTT is tracked via VMA using + * i915_vma_move_to_active(), otherwise we could evict as required + * with minimal stalling. Instead we are forced to idle the GPU and + * explicitly retire outstanding requests which will then remove + * the pinning for active objects such as contexts and ring, + * enabling us to evict them on the next iteration. + * + * To ensure that all user contexts are evictable, we perform + * a switch to the perma-pinned kernel context. This all also gives + * us a termination condition, when the last retired context is + * the kernel's there is no more we can evict. + */ + if (!ggtt_is_idle(dev_priv)) { + ret = ggtt_flush(dev_priv); + if (ret) + return ret; - ret = ggtt_flush(dev_priv); - if (ret) - return ret; + goto search_again; + } - goto search_again; + /* + * If we still have pending pageflip completions, drop + * back to userspace to give our workqueues time to + * acquire our locks and unpin the old scanouts. + */ + return intel_has_pending_fb_unpin(dev_priv) ? -EAGAIN : -ENOSPC; found: /* drm_mm doesn't allow any other other operations while diff --git a/drivers/gpu/drm/i915/i915_perf.c b/drivers/gpu/drm/i915/i915_perf.c index 94185d610673..370b9d248fed 100644 --- a/drivers/gpu/drm/i915/i915_perf.c +++ b/drivers/gpu/drm/i915/i915_perf.c @@ -2537,6 +2537,10 @@ static const struct file_operations fops = { .poll = i915_perf_poll, .read = i915_perf_read, .unlocked_ioctl = i915_perf_ioctl, + /* Our ioctl have no arguments, so it's safe to use the same function + * to handle 32bits compatibility. + */ + .compat_ioctl = i915_perf_ioctl, }; diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h index ed7cd9ee2c2a..c9bcc6c45012 100644 --- a/drivers/gpu/drm/i915/i915_reg.h +++ b/drivers/gpu/drm/i915/i915_reg.h @@ -6998,6 +6998,7 @@ enum { */ #define L3_GENERAL_PRIO_CREDITS(x) (((x) >> 1) << 19) #define L3_HIGH_PRIO_CREDITS(x) (((x) >> 1) << 14) +#define L3_PRIO_CREDITS_MASK ((0x1f << 19) | (0x1f << 14)) #define GEN7_L3CNTLREG1 _MMIO(0xB01C) #define GEN7_WA_FOR_GEN7_L3_CONTROL 0x3C47FF8C diff --git a/drivers/gpu/drm/i915/intel_bios.c b/drivers/gpu/drm/i915/intel_bios.c index 00c6aee0a9a1..5d4cd3d00564 100644 --- a/drivers/gpu/drm/i915/intel_bios.c +++ b/drivers/gpu/drm/i915/intel_bios.c @@ -1240,7 +1240,7 @@ static void parse_ddi_ports(struct drm_i915_private *dev_priv, { enum port port; - if (!HAS_DDI(dev_priv)) + if (!HAS_DDI(dev_priv) && !IS_CHERRYVIEW(dev_priv)) return; if (!dev_priv->vbt.child_dev_num) diff --git a/drivers/gpu/drm/i915/intel_color.c b/drivers/gpu/drm/i915/intel_color.c index ff9ecd211abb..b8315bca852b 100644 --- a/drivers/gpu/drm/i915/intel_color.c +++ b/drivers/gpu/drm/i915/intel_color.c @@ -74,7 +74,7 @@ #define I9XX_CSC_COEFF_1_0 \ ((7 << 12) | I9XX_CSC_COEFF_FP(CTM_COEFF_1_0, 8)) -static bool crtc_state_is_legacy(struct drm_crtc_state *state) +static bool crtc_state_is_legacy_gamma(struct drm_crtc_state *state) { return !state->degamma_lut && !state->ctm && @@ -288,7 +288,7 @@ static void cherryview_load_csc_matrix(struct drm_crtc_state *state) } mode = (state->ctm ? CGM_PIPE_MODE_CSC : 0); - if (!crtc_state_is_legacy(state)) { + if (!crtc_state_is_legacy_gamma(state)) { mode |= (state->degamma_lut ? CGM_PIPE_MODE_DEGAMMA : 0) | (state->gamma_lut ? CGM_PIPE_MODE_GAMMA : 0); } @@ -469,7 +469,7 @@ static void broadwell_load_luts(struct drm_crtc_state *state) struct intel_crtc_state *intel_state = to_intel_crtc_state(state); enum pipe pipe = to_intel_crtc(state->crtc)->pipe; - if (crtc_state_is_legacy(state)) { + if (crtc_state_is_legacy_gamma(state)) { haswell_load_luts(state); return; } @@ -529,7 +529,7 @@ static void glk_load_luts(struct drm_crtc_state *state) glk_load_degamma_lut(state); - if (crtc_state_is_legacy(state)) { + if (crtc_state_is_legacy_gamma(state)) { haswell_load_luts(state); return; } @@ -551,7 +551,7 @@ static void cherryview_load_luts(struct drm_crtc_state *state) uint32_t i, lut_size; uint32_t word0, word1; - if (crtc_state_is_legacy(state)) { + if (crtc_state_is_legacy_gamma(state)) { /* Turn off degamma/gamma on CGM block. */ I915_WRITE(CGM_PIPE_MODE(pipe), (state->ctm ? CGM_PIPE_MODE_CSC : 0)); @@ -632,12 +632,10 @@ int intel_color_check(struct drm_crtc *crtc, return 0; /* - * We also allow no degamma lut and a gamma lut at the legacy + * We also allow no degamma lut/ctm and a gamma lut at the legacy * size (256 entries). */ - if (!crtc_state->degamma_lut && - crtc_state->gamma_lut && - crtc_state->gamma_lut->length == LEGACY_LUT_LENGTH) + if (crtc_state_is_legacy_gamma(crtc_state)) return 0; return -EINVAL; diff --git a/drivers/gpu/drm/i915/intel_ddi.c b/drivers/gpu/drm/i915/intel_ddi.c index 476681d5940c..5e5fe03b638c 100644 --- a/drivers/gpu/drm/i915/intel_ddi.c +++ b/drivers/gpu/drm/i915/intel_ddi.c @@ -664,8 +664,8 @@ intel_ddi_get_buf_trans_fdi(struct drm_i915_private *dev_priv, int *n_entries) { if (IS_BROADWELL(dev_priv)) { - *n_entries = ARRAY_SIZE(hsw_ddi_translations_fdi); - return hsw_ddi_translations_fdi; + *n_entries = ARRAY_SIZE(bdw_ddi_translations_fdi); + return bdw_ddi_translations_fdi; } else if (IS_HASWELL(dev_priv)) { *n_entries = ARRAY_SIZE(hsw_ddi_translations_fdi); return hsw_ddi_translations_fdi; @@ -2102,8 +2102,7 @@ static void intel_ddi_clk_select(struct intel_encoder *encoder, * register writes. */ val = I915_READ(DPCLKA_CFGCR0); - val &= ~(DPCLKA_CFGCR0_DDI_CLK_OFF(port) | - DPCLKA_CFGCR0_DDI_CLK_SEL_MASK(port)); + val &= ~DPCLKA_CFGCR0_DDI_CLK_OFF(port); I915_WRITE(DPCLKA_CFGCR0, val); } else if (IS_GEN9_BC(dev_priv)) { /* DDI -> PLL mapping */ diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c index 64f7b51ed97c..5c7828c52d12 100644 --- a/drivers/gpu/drm/i915/intel_display.c +++ b/drivers/gpu/drm/i915/intel_display.c @@ -10245,13 +10245,10 @@ struct drm_display_mode *intel_crtc_mode_get(struct drm_device *dev, { struct drm_i915_private *dev_priv = to_i915(dev); struct intel_crtc *intel_crtc = to_intel_crtc(crtc); - enum transcoder cpu_transcoder = intel_crtc->config->cpu_transcoder; + enum transcoder cpu_transcoder; struct drm_display_mode *mode; struct intel_crtc_state *pipe_config; - int htot = I915_READ(HTOTAL(cpu_transcoder)); - int hsync = I915_READ(HSYNC(cpu_transcoder)); - int vtot = I915_READ(VTOTAL(cpu_transcoder)); - int vsync = I915_READ(VSYNC(cpu_transcoder)); + u32 htot, hsync, vtot, vsync; enum pipe pipe = intel_crtc->pipe; mode = kzalloc(sizeof(*mode), GFP_KERNEL); @@ -10279,6 +10276,13 @@ struct drm_display_mode *intel_crtc_mode_get(struct drm_device *dev, i9xx_crtc_clock_get(intel_crtc, pipe_config); mode->clock = pipe_config->port_clock / pipe_config->pixel_multiplier; + + cpu_transcoder = pipe_config->cpu_transcoder; + htot = I915_READ(HTOTAL(cpu_transcoder)); + hsync = I915_READ(HSYNC(cpu_transcoder)); + vtot = I915_READ(VTOTAL(cpu_transcoder)); + vsync = I915_READ(VSYNC(cpu_transcoder)); + mode->hdisplay = (htot & 0xffff) + 1; mode->htotal = ((htot & 0xffff0000) >> 16) + 1; mode->hsync_start = (hsync & 0xffff) + 1; diff --git a/drivers/gpu/drm/i915/intel_dp.c b/drivers/gpu/drm/i915/intel_dp.c index 64134947c0aa..203198659ab2 100644 --- a/drivers/gpu/drm/i915/intel_dp.c +++ b/drivers/gpu/drm/i915/intel_dp.c @@ -2307,8 +2307,8 @@ static void edp_panel_off(struct intel_dp *intel_dp) I915_WRITE(pp_ctrl_reg, pp); POSTING_READ(pp_ctrl_reg); - intel_dp->panel_power_off_time = ktime_get_boottime(); wait_panel_off(intel_dp); + intel_dp->panel_power_off_time = ktime_get_boottime(); /* We got a reference when we enabled the VDD. */ intel_display_power_put(dev_priv, intel_dp->aux_power_domain); @@ -5273,7 +5273,7 @@ intel_dp_init_panel_power_sequencer(struct drm_device *dev, * seems sufficient to avoid this problem. */ if (dev_priv->quirks & QUIRK_INCREASE_T12_DELAY) { - vbt.t11_t12 = max_t(u16, vbt.t11_t12, 900 * 10); + vbt.t11_t12 = max_t(u16, vbt.t11_t12, 1300 * 10); DRM_DEBUG_KMS("Increasing T12 panel delay as per the quirk to %d\n", vbt.t11_t12); } diff --git a/drivers/gpu/drm/i915/intel_dpll_mgr.c b/drivers/gpu/drm/i915/intel_dpll_mgr.c index a2a3d93d67bd..df808a94c511 100644 --- a/drivers/gpu/drm/i915/intel_dpll_mgr.c +++ b/drivers/gpu/drm/i915/intel_dpll_mgr.c @@ -1996,7 +1996,7 @@ static void cnl_ddi_pll_enable(struct drm_i915_private *dev_priv, /* 3. Configure DPLL_CFGCR0 */ /* Avoid touch CFGCR1 if HDMI mode is not enabled */ - if (pll->state.hw_state.cfgcr0 & DPLL_CTRL1_HDMI_MODE(pll->id)) { + if (pll->state.hw_state.cfgcr0 & DPLL_CFGCR0_HDMI_MODE) { val = pll->state.hw_state.cfgcr1; I915_WRITE(CNL_DPLL_CFGCR1(pll->id), val); /* 4. Reab back to ensure writes completed */ diff --git a/drivers/gpu/drm/i915/intel_engine_cs.c b/drivers/gpu/drm/i915/intel_engine_cs.c index 9ab596941372..3c2d9cf22ed5 100644 --- a/drivers/gpu/drm/i915/intel_engine_cs.c +++ b/drivers/gpu/drm/i915/intel_engine_cs.c @@ -1048,9 +1048,12 @@ static int bxt_init_workarounds(struct intel_engine_cs *engine) } /* WaProgramL3SqcReg1DefaultForPerf:bxt */ - if (IS_BXT_REVID(dev_priv, BXT_REVID_B0, REVID_FOREVER)) - I915_WRITE(GEN8_L3SQCREG1, L3_GENERAL_PRIO_CREDITS(62) | - L3_HIGH_PRIO_CREDITS(2)); + if (IS_BXT_REVID(dev_priv, BXT_REVID_B0, REVID_FOREVER)) { + u32 val = I915_READ(GEN8_L3SQCREG1); + val &= ~L3_PRIO_CREDITS_MASK; + val |= L3_GENERAL_PRIO_CREDITS(62) | L3_HIGH_PRIO_CREDITS(2); + I915_WRITE(GEN8_L3SQCREG1, val); + } /* WaToEnableHwFixForPushConstHWBug:bxt */ if (IS_BXT_REVID(dev_priv, BXT_REVID_C0, REVID_FOREVER)) diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c index ed662937ec3c..0a09f8ff6aff 100644 --- a/drivers/gpu/drm/i915/intel_pm.c +++ b/drivers/gpu/drm/i915/intel_pm.c @@ -8245,14 +8245,17 @@ static void gen8_set_l3sqc_credits(struct drm_i915_private *dev_priv, int high_prio_credits) { u32 misccpctl; + u32 val; /* WaTempDisableDOPClkGating:bdw */ misccpctl = I915_READ(GEN7_MISCCPCTL); I915_WRITE(GEN7_MISCCPCTL, misccpctl & ~GEN7_DOP_CLOCK_GATE_ENABLE); - I915_WRITE(GEN8_L3SQCREG1, - L3_GENERAL_PRIO_CREDITS(general_prio_credits) | - L3_HIGH_PRIO_CREDITS(high_prio_credits)); + val = I915_READ(GEN8_L3SQCREG1); + val &= ~L3_PRIO_CREDITS_MASK; + val |= L3_GENERAL_PRIO_CREDITS(general_prio_credits); + val |= L3_HIGH_PRIO_CREDITS(high_prio_credits); + I915_WRITE(GEN8_L3SQCREG1, val); /* * Wait at least 100 clocks before re-enabling clock gating. diff --git a/drivers/gpu/drm/i915/intel_runtime_pm.c b/drivers/gpu/drm/i915/intel_runtime_pm.c index b3a087cb0860..49577eba8e7e 100644 --- a/drivers/gpu/drm/i915/intel_runtime_pm.c +++ b/drivers/gpu/drm/i915/intel_runtime_pm.c @@ -368,7 +368,7 @@ static void hsw_power_well_enable(struct drm_i915_private *dev_priv, { enum i915_power_well_id id = power_well->id; bool wait_fuses = power_well->hsw.has_fuses; - enum skl_power_gate pg; + enum skl_power_gate uninitialized_var(pg); u32 val; if (wait_fuses) { diff --git a/drivers/gpu/drm/msm/dsi/dsi_host.c b/drivers/gpu/drm/msm/dsi/dsi_host.c index dbb31a014419..deaf869374ea 100644 --- a/drivers/gpu/drm/msm/dsi/dsi_host.c +++ b/drivers/gpu/drm/msm/dsi/dsi_host.c @@ -248,7 +248,7 @@ disable_clks: clk_disable_unprepare(ahb_clk); disable_gdsc: regulator_disable(gdsc_reg); - pm_runtime_put_autosuspend(dev); + pm_runtime_put_sync(dev); put_clk: clk_put(ahb_clk); put_gdsc: diff --git a/drivers/gpu/drm/msm/mdp/mdp5/mdp5_cfg.c b/drivers/gpu/drm/msm/mdp/mdp5/mdp5_cfg.c index c2bdad88447e..824067d2d427 100644 --- a/drivers/gpu/drm/msm/mdp/mdp5/mdp5_cfg.c +++ b/drivers/gpu/drm/msm/mdp/mdp5/mdp5_cfg.c @@ -83,6 +83,8 @@ const struct mdp5_cfg_hw msm8x74v1_config = { .caps = MDP_LM_CAP_WB }, }, .nb_stages = 5, + .max_width = 2048, + .max_height = 0xFFFF, }, .dspp = { .count = 3, diff --git a/drivers/gpu/drm/msm/mdp/mdp5/mdp5_crtc.c b/drivers/gpu/drm/msm/mdp/mdp5/mdp5_crtc.c index 6fcb58ab718c..440977677001 100644 --- a/drivers/gpu/drm/msm/mdp/mdp5/mdp5_crtc.c +++ b/drivers/gpu/drm/msm/mdp/mdp5/mdp5_crtc.c @@ -804,8 +804,6 @@ static int mdp5_crtc_cursor_set(struct drm_crtc *crtc, spin_unlock_irqrestore(&mdp5_crtc->cursor.lock, flags); - pm_runtime_put_autosuspend(&pdev->dev); - set_cursor: ret = mdp5_ctl_set_cursor(ctl, pipeline, 0, cursor_enable); if (ret) { diff --git a/drivers/gpu/drm/msm/msm_gem.c b/drivers/gpu/drm/msm/msm_gem.c index f15821a0d900..ea5bb0e1632c 100644 --- a/drivers/gpu/drm/msm/msm_gem.c +++ b/drivers/gpu/drm/msm/msm_gem.c @@ -610,17 +610,6 @@ int msm_gem_sync_object(struct drm_gem_object *obj, struct dma_fence *fence; int i, ret; - if (!exclusive) { - /* NOTE: _reserve_shared() must happen before _add_shared_fence(), - * which makes this a slightly strange place to call it. OTOH this - * is a convenient can-fail point to hook it in. (And similar to - * how etnaviv and nouveau handle this.) - */ - ret = reservation_object_reserve_shared(msm_obj->resv); - if (ret) - return ret; - } - fobj = reservation_object_get_list(msm_obj->resv); if (!fobj || (fobj->shared_count == 0)) { fence = reservation_object_get_excl(msm_obj->resv); @@ -1045,10 +1034,10 @@ static void *_msm_gem_kernel_new(struct drm_device *dev, uint32_t size, } vaddr = msm_gem_get_vaddr(obj); - if (!vaddr) { + if (IS_ERR(vaddr)) { msm_gem_put_iova(obj, aspace); drm_gem_object_unreference(obj); - return ERR_PTR(-ENOMEM); + return ERR_CAST(vaddr); } if (bo) diff --git a/drivers/gpu/drm/msm/msm_gem_submit.c b/drivers/gpu/drm/msm/msm_gem_submit.c index 5d0a75d4b249..93535cac0676 100644 --- a/drivers/gpu/drm/msm/msm_gem_submit.c +++ b/drivers/gpu/drm/msm/msm_gem_submit.c @@ -221,7 +221,7 @@ fail: return ret; } -static int submit_fence_sync(struct msm_gem_submit *submit) +static int submit_fence_sync(struct msm_gem_submit *submit, bool no_implicit) { int i, ret = 0; @@ -229,6 +229,20 @@ static int submit_fence_sync(struct msm_gem_submit *submit) struct msm_gem_object *msm_obj = submit->bos[i].obj; bool write = submit->bos[i].flags & MSM_SUBMIT_BO_WRITE; + if (!write) { + /* NOTE: _reserve_shared() must happen before + * _add_shared_fence(), which makes this a slightly + * strange place to call it. OTOH this is a + * convenient can-fail point to hook it in. + */ + ret = reservation_object_reserve_shared(msm_obj->resv); + if (ret) + return ret; + } + + if (no_implicit) + continue; + ret = msm_gem_sync_object(&msm_obj->base, submit->gpu->fctx, write); if (ret) break; @@ -451,11 +465,9 @@ int msm_ioctl_gem_submit(struct drm_device *dev, void *data, if (ret) goto out; - if (!(args->flags & MSM_SUBMIT_NO_IMPLICIT)) { - ret = submit_fence_sync(submit); - if (ret) - goto out; - } + ret = submit_fence_sync(submit, !!(args->flags & MSM_SUBMIT_NO_IMPLICIT)); + if (ret) + goto out; ret = submit_pin_objects(submit); if (ret) diff --git a/drivers/gpu/drm/msm/msm_gpu.c b/drivers/gpu/drm/msm/msm_gpu.c index ffbff27600e0..6a887032c66a 100644 --- a/drivers/gpu/drm/msm/msm_gpu.c +++ b/drivers/gpu/drm/msm/msm_gpu.c @@ -718,7 +718,8 @@ void msm_gpu_cleanup(struct msm_gpu *gpu) msm_gem_put_iova(gpu->rb->bo, gpu->aspace); msm_ringbuffer_destroy(gpu->rb); } - if (gpu->aspace) { + + if (!IS_ERR_OR_NULL(gpu->aspace)) { gpu->aspace->mmu->funcs->detach(gpu->aspace->mmu, NULL, 0); msm_gem_address_space_put(gpu->aspace); diff --git a/drivers/gpu/drm/msm/msm_rd.c b/drivers/gpu/drm/msm/msm_rd.c index 0366b8092f97..ec56794ad039 100644 --- a/drivers/gpu/drm/msm/msm_rd.c +++ b/drivers/gpu/drm/msm/msm_rd.c @@ -111,10 +111,14 @@ static void rd_write(struct msm_rd_state *rd, const void *buf, int sz) wait_event(rd->fifo_event, circ_space(&rd->fifo) > 0); + /* Note that smp_load_acquire() is not strictly required + * as CIRC_SPACE_TO_END() does not access the tail more + * than once. + */ n = min(sz, circ_space_to_end(&rd->fifo)); memcpy(fptr, ptr, n); - fifo->head = (fifo->head + n) & (BUF_SZ - 1); + smp_store_release(&fifo->head, (fifo->head + n) & (BUF_SZ - 1)); sz -= n; ptr += n; @@ -145,13 +149,17 @@ static ssize_t rd_read(struct file *file, char __user *buf, if (ret) goto out; + /* Note that smp_load_acquire() is not strictly required + * as CIRC_CNT_TO_END() does not access the head more than + * once. + */ n = min_t(int, sz, circ_count_to_end(&rd->fifo)); if (copy_to_user(buf, fptr, n)) { ret = -EFAULT; goto out; } - fifo->tail = (fifo->tail + n) & (BUF_SZ - 1); + smp_store_release(&fifo->tail, (fifo->tail + n) & (BUF_SZ - 1)); *ppos += n; wake_up_all(&rd->fifo_event); diff --git a/drivers/gpu/drm/nouveau/nouveau_fbcon.c b/drivers/gpu/drm/nouveau/nouveau_fbcon.c index f7707849bb53..2b12d82aac15 100644 --- a/drivers/gpu/drm/nouveau/nouveau_fbcon.c +++ b/drivers/gpu/drm/nouveau/nouveau_fbcon.c @@ -223,7 +223,7 @@ void nouveau_fbcon_accel_save_disable(struct drm_device *dev) { struct nouveau_drm *drm = nouveau_drm(dev); - if (drm->fbcon) { + if (drm->fbcon && drm->fbcon->helper.fbdev) { drm->fbcon->saved_flags = drm->fbcon->helper.fbdev->flags; drm->fbcon->helper.fbdev->flags |= FBINFO_HWACCEL_DISABLED; } @@ -233,7 +233,7 @@ void nouveau_fbcon_accel_restore(struct drm_device *dev) { struct nouveau_drm *drm = nouveau_drm(dev); - if (drm->fbcon) { + if (drm->fbcon && drm->fbcon->helper.fbdev) { drm->fbcon->helper.fbdev->flags = drm->fbcon->saved_flags; } } @@ -245,7 +245,8 @@ nouveau_fbcon_accel_fini(struct drm_device *dev) struct nouveau_fbdev *fbcon = drm->fbcon; if (fbcon && drm->channel) { console_lock(); - fbcon->helper.fbdev->flags |= FBINFO_HWACCEL_DISABLED; + if (fbcon->helper.fbdev) + fbcon->helper.fbdev->flags |= FBINFO_HWACCEL_DISABLED; console_unlock(); nouveau_channel_idle(drm->channel); nvif_object_fini(&fbcon->twod); diff --git a/drivers/gpu/drm/nouveau/nv50_display.c b/drivers/gpu/drm/nouveau/nv50_display.c index 2dbf62a2ac41..e4751f92b342 100644 --- a/drivers/gpu/drm/nouveau/nv50_display.c +++ b/drivers/gpu/drm/nouveau/nv50_display.c @@ -3265,11 +3265,14 @@ nv50_mstm = { void nv50_mstm_service(struct nv50_mstm *mstm) { - struct drm_dp_aux *aux = mstm->mgr.aux; + struct drm_dp_aux *aux = mstm ? mstm->mgr.aux : NULL; bool handled = true; int ret; u8 esi[8] = {}; + if (!aux) + return; + while (handled) { ret = drm_dp_dpcd_read(aux, DP_SINK_COUNT_ESI, esi, 8); if (ret != 8) { diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/bsp/g84.c b/drivers/gpu/drm/nouveau/nvkm/engine/bsp/g84.c index 8e2e24a74774..44e116f7880d 100644 --- a/drivers/gpu/drm/nouveau/nvkm/engine/bsp/g84.c +++ b/drivers/gpu/drm/nouveau/nvkm/engine/bsp/g84.c @@ -39,5 +39,5 @@ int g84_bsp_new(struct nvkm_device *device, int index, struct nvkm_engine **pengine) { return nvkm_xtensa_new_(&g84_bsp, device, index, - true, 0x103000, pengine); + device->chipset != 0x92, 0x103000, pengine); } diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/mmu/base.c b/drivers/gpu/drm/nouveau/nvkm/subdev/mmu/base.c index d06ad2c372bf..455da298227f 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/mmu/base.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/mmu/base.c @@ -241,6 +241,8 @@ nvkm_vm_unmap_pgt(struct nvkm_vm *vm, int big, u32 fpde, u32 lpde) mmu->func->map_pgt(vpgd->obj, pde, vpgt->mem); } + mmu->func->flush(vm); + nvkm_memory_del(&pgt); } } diff --git a/drivers/gpu/ipu-v3/ipu-common.c b/drivers/gpu/ipu-v3/ipu-common.c index 6a573d21d3cc..658fa2d3e40c 100644 --- a/drivers/gpu/ipu-v3/ipu-common.c +++ b/drivers/gpu/ipu-v3/ipu-common.c @@ -405,6 +405,14 @@ int ipu_idmac_lock_enable(struct ipuv3_channel *channel, int num_bursts) return -EINVAL; } + /* + * IPUv3EX / i.MX51 has a different register layout, and on IPUv3M / + * i.MX53 channel arbitration locking doesn't seem to work properly. + * Allow enabling the lock feature on IPUv3H / i.MX6 only. + */ + if (bursts && ipu->ipu_type != IPUV3H) + return -EINVAL; + for (i = 0; i < ARRAY_SIZE(idmac_lock_en_info); i++) { if (channel->num == idmac_lock_en_info[i].chnum) break; diff --git a/drivers/gpu/ipu-v3/ipu-pre.c b/drivers/gpu/ipu-v3/ipu-pre.c index c35f74c83065..c860a7997cb5 100644 --- a/drivers/gpu/ipu-v3/ipu-pre.c +++ b/drivers/gpu/ipu-v3/ipu-pre.c @@ -73,6 +73,14 @@ #define IPU_PRE_STORE_ENG_CTRL_WR_NUM_BYTES(v) ((v & 0x7) << 1) #define IPU_PRE_STORE_ENG_CTRL_OUTPUT_ACTIVE_BPP(v) ((v & 0x3) << 4) +#define IPU_PRE_STORE_ENG_STATUS 0x120 +#define IPU_PRE_STORE_ENG_STATUS_STORE_BLOCK_X_MASK 0xffff +#define IPU_PRE_STORE_ENG_STATUS_STORE_BLOCK_X_SHIFT 0 +#define IPU_PRE_STORE_ENG_STATUS_STORE_BLOCK_Y_MASK 0x3fff +#define IPU_PRE_STORE_ENG_STATUS_STORE_BLOCK_Y_SHIFT 16 +#define IPU_PRE_STORE_ENG_STATUS_STORE_FIFO_FULL (1 << 30) +#define IPU_PRE_STORE_ENG_STATUS_STORE_FIELD (1 << 31) + #define IPU_PRE_STORE_ENG_SIZE 0x130 #define IPU_PRE_STORE_ENG_SIZE_INPUT_WIDTH(v) ((v & 0xffff) << 0) #define IPU_PRE_STORE_ENG_SIZE_INPUT_HEIGHT(v) ((v & 0xffff) << 16) @@ -93,6 +101,7 @@ struct ipu_pre { dma_addr_t buffer_paddr; void *buffer_virt; bool in_use; + unsigned int safe_window_end; }; static DEFINE_MUTEX(ipu_pre_list_mutex); @@ -160,6 +169,9 @@ void ipu_pre_configure(struct ipu_pre *pre, unsigned int width, u32 active_bpp = info->cpp[0] >> 1; u32 val; + /* calculate safe window for ctrl register updates */ + pre->safe_window_end = height - 2; + writel(bufaddr, pre->regs + IPU_PRE_CUR_BUF); writel(bufaddr, pre->regs + IPU_PRE_NEXT_BUF); @@ -199,7 +211,24 @@ void ipu_pre_configure(struct ipu_pre *pre, unsigned int width, void ipu_pre_update(struct ipu_pre *pre, unsigned int bufaddr) { + unsigned long timeout = jiffies + msecs_to_jiffies(5); + unsigned short current_yblock; + u32 val; + writel(bufaddr, pre->regs + IPU_PRE_NEXT_BUF); + + do { + if (time_after(jiffies, timeout)) { + dev_warn(pre->dev, "timeout waiting for PRE safe window\n"); + return; + } + + val = readl(pre->regs + IPU_PRE_STORE_ENG_STATUS); + current_yblock = + (val >> IPU_PRE_STORE_ENG_STATUS_STORE_BLOCK_Y_SHIFT) & + IPU_PRE_STORE_ENG_STATUS_STORE_BLOCK_Y_MASK; + } while (current_yblock == 0 || current_yblock >= pre->safe_window_end); + writel(IPU_PRE_CTRL_SDW_UPDATE, pre->regs + IPU_PRE_CTRL_SET); } diff --git a/drivers/gpu/ipu-v3/ipu-prg.c b/drivers/gpu/ipu-v3/ipu-prg.c index ecc9ea44dc50..0013ca9f72c8 100644 --- a/drivers/gpu/ipu-v3/ipu-prg.c +++ b/drivers/gpu/ipu-v3/ipu-prg.c @@ -14,6 +14,7 @@ #include <drm/drm_fourcc.h> #include <linux/clk.h> #include <linux/err.h> +#include <linux/iopoll.h> #include <linux/mfd/syscon.h> #include <linux/mfd/syscon/imx6q-iomuxc-gpr.h> #include <linux/module.h> @@ -329,6 +330,12 @@ int ipu_prg_channel_configure(struct ipuv3_channel *ipu_chan, val = IPU_PRG_REG_UPDATE_REG_UPDATE; writel(val, prg->regs + IPU_PRG_REG_UPDATE); + /* wait for both double buffers to be filled */ + readl_poll_timeout(prg->regs + IPU_PRG_STATUS, val, + (val & IPU_PRG_STATUS_BUFFER0_READY(prg_chan)) && + (val & IPU_PRG_STATUS_BUFFER1_READY(prg_chan)), + 5, 1000); + clk_disable_unprepare(prg->clk_ipg); chan->enabled = true; diff --git a/drivers/hid/Kconfig b/drivers/hid/Kconfig index 0a3117cc29e7..374301fcbc86 100644 --- a/drivers/hid/Kconfig +++ b/drivers/hid/Kconfig @@ -281,6 +281,7 @@ config HID_ELECOM Support for ELECOM devices: - BM084 Bluetooth Mouse - DEFT Trackball (Wired and wireless) + - HUGE Trackball (Wired and wireless) config HID_ELO tristate "ELO USB 4000/4500 touchscreen" diff --git a/drivers/hid/hid-core.c b/drivers/hid/hid-core.c index 9bc91160819b..330ca983828b 100644 --- a/drivers/hid/hid-core.c +++ b/drivers/hid/hid-core.c @@ -2032,6 +2032,8 @@ static const struct hid_device_id hid_have_special_driver[] = { { HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_ELECOM, USB_DEVICE_ID_ELECOM_BM084) }, { HID_USB_DEVICE(USB_VENDOR_ID_ELECOM, USB_DEVICE_ID_ELECOM_DEFT_WIRED) }, { HID_USB_DEVICE(USB_VENDOR_ID_ELECOM, USB_DEVICE_ID_ELECOM_DEFT_WIRELESS) }, + { HID_USB_DEVICE(USB_VENDOR_ID_ELECOM, USB_DEVICE_ID_ELECOM_HUGE_WIRED) }, + { HID_USB_DEVICE(USB_VENDOR_ID_ELECOM, USB_DEVICE_ID_ELECOM_HUGE_WIRELESS) }, #endif #if IS_ENABLED(CONFIG_HID_ELO) { HID_USB_DEVICE(USB_VENDOR_ID_ELO, 0x0009) }, diff --git a/drivers/hid/hid-elecom.c b/drivers/hid/hid-elecom.c index e2c7465df69f..54aeea57d209 100644 --- a/drivers/hid/hid-elecom.c +++ b/drivers/hid/hid-elecom.c @@ -3,6 +3,7 @@ * Copyright (c) 2010 Richard Nauber <Richard.Nauber@gmail.com> * Copyright (c) 2016 Yuxuan Shui <yshuiv7@gmail.com> * Copyright (c) 2017 Diego Elio Pettenò <flameeyes@flameeyes.eu> + * Copyright (c) 2017 Alex Manoussakis <amanou@gnu.org> */ /* @@ -32,9 +33,11 @@ static __u8 *elecom_report_fixup(struct hid_device *hdev, __u8 *rdesc, break; case USB_DEVICE_ID_ELECOM_DEFT_WIRED: case USB_DEVICE_ID_ELECOM_DEFT_WIRELESS: - /* The DEFT trackball has eight buttons, but its descriptor only - * reports five, disabling the three Fn buttons on the top of - * the mouse. + case USB_DEVICE_ID_ELECOM_HUGE_WIRED: + case USB_DEVICE_ID_ELECOM_HUGE_WIRELESS: + /* The DEFT/HUGE trackball has eight buttons, but its descriptor + * only reports five, disabling the three Fn buttons on the top + * of the mouse. * * Apply the following diff to the descriptor: * @@ -62,7 +65,7 @@ static __u8 *elecom_report_fixup(struct hid_device *hdev, __u8 *rdesc, * End Collection, End Collection, */ if (*rsize == 213 && rdesc[13] == 5 && rdesc[21] == 5) { - hid_info(hdev, "Fixing up Elecom DEFT Fn buttons\n"); + hid_info(hdev, "Fixing up Elecom DEFT/HUGE Fn buttons\n"); rdesc[13] = 8; /* Button/Variable Report Count */ rdesc[21] = 8; /* Button/Variable Usage Maximum */ rdesc[29] = 0; /* Button/Constant Report Count */ @@ -76,6 +79,8 @@ static const struct hid_device_id elecom_devices[] = { { HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_ELECOM, USB_DEVICE_ID_ELECOM_BM084) }, { HID_USB_DEVICE(USB_VENDOR_ID_ELECOM, USB_DEVICE_ID_ELECOM_DEFT_WIRED) }, { HID_USB_DEVICE(USB_VENDOR_ID_ELECOM, USB_DEVICE_ID_ELECOM_DEFT_WIRELESS) }, + { HID_USB_DEVICE(USB_VENDOR_ID_ELECOM, USB_DEVICE_ID_ELECOM_HUGE_WIRED) }, + { HID_USB_DEVICE(USB_VENDOR_ID_ELECOM, USB_DEVICE_ID_ELECOM_HUGE_WIRELESS) }, { } }; MODULE_DEVICE_TABLE(hid, elecom_devices); diff --git a/drivers/hid/hid-ids.h b/drivers/hid/hid-ids.h index a98919199858..be2e005c3c51 100644 --- a/drivers/hid/hid-ids.h +++ b/drivers/hid/hid-ids.h @@ -368,6 +368,8 @@ #define USB_DEVICE_ID_ELECOM_BM084 0x0061 #define USB_DEVICE_ID_ELECOM_DEFT_WIRED 0x00fe #define USB_DEVICE_ID_ELECOM_DEFT_WIRELESS 0x00ff +#define USB_DEVICE_ID_ELECOM_HUGE_WIRED 0x010c +#define USB_DEVICE_ID_ELECOM_HUGE_WIRELESS 0x010d #define USB_VENDOR_ID_DREAM_CHEEKY 0x1d34 #define USB_DEVICE_ID_DREAM_CHEEKY_WN 0x0004 diff --git a/drivers/hid/usbhid/hid-core.c b/drivers/hid/usbhid/hid-core.c index 089bad8a9a21..045b5da9b992 100644 --- a/drivers/hid/usbhid/hid-core.c +++ b/drivers/hid/usbhid/hid-core.c @@ -975,6 +975,8 @@ static int usbhid_parse(struct hid_device *hid) unsigned int rsize = 0; char *rdesc; int ret, n; + int num_descriptors; + size_t offset = offsetof(struct hid_descriptor, desc); quirks = usbhid_lookup_quirk(le16_to_cpu(dev->descriptor.idVendor), le16_to_cpu(dev->descriptor.idProduct)); @@ -997,10 +999,18 @@ static int usbhid_parse(struct hid_device *hid) return -ENODEV; } + if (hdesc->bLength < sizeof(struct hid_descriptor)) { + dbg_hid("hid descriptor is too short\n"); + return -EINVAL; + } + hid->version = le16_to_cpu(hdesc->bcdHID); hid->country = hdesc->bCountryCode; - for (n = 0; n < hdesc->bNumDescriptors; n++) + num_descriptors = min_t(int, hdesc->bNumDescriptors, + (hdesc->bLength - offset) / sizeof(struct hid_class_descriptor)); + + for (n = 0; n < num_descriptors; n++) if (hdesc->desc[n].bDescriptorType == HID_DT_REPORT) rsize = le16_to_cpu(hdesc->desc[n].wDescriptorLength); diff --git a/drivers/hv/channel.c b/drivers/hv/channel.c index efd5db743319..894b67ac2cae 100644 --- a/drivers/hv/channel.c +++ b/drivers/hv/channel.c @@ -640,6 +640,7 @@ void vmbus_close(struct vmbus_channel *channel) */ return; } + mutex_lock(&vmbus_connection.channel_mutex); /* * Close all the sub-channels first and then close the * primary channel. @@ -648,16 +649,15 @@ void vmbus_close(struct vmbus_channel *channel) cur_channel = list_entry(cur, struct vmbus_channel, sc_list); vmbus_close_internal(cur_channel); if (cur_channel->rescind) { - mutex_lock(&vmbus_connection.channel_mutex); - hv_process_channel_removal(cur_channel, + hv_process_channel_removal( cur_channel->offermsg.child_relid); - mutex_unlock(&vmbus_connection.channel_mutex); } } /* * Now close the primary. */ vmbus_close_internal(channel); + mutex_unlock(&vmbus_connection.channel_mutex); } EXPORT_SYMBOL_GPL(vmbus_close); diff --git a/drivers/hv/channel_mgmt.c b/drivers/hv/channel_mgmt.c index bcbb031f7263..379b0df123be 100644 --- a/drivers/hv/channel_mgmt.c +++ b/drivers/hv/channel_mgmt.c @@ -159,7 +159,7 @@ static void vmbus_rescind_cleanup(struct vmbus_channel *channel) spin_lock_irqsave(&vmbus_connection.channelmsg_lock, flags); - + channel->rescind = true; list_for_each_entry(msginfo, &vmbus_connection.chn_msg_list, msglistentry) { @@ -381,14 +381,21 @@ static void vmbus_release_relid(u32 relid) true); } -void hv_process_channel_removal(struct vmbus_channel *channel, u32 relid) +void hv_process_channel_removal(u32 relid) { unsigned long flags; - struct vmbus_channel *primary_channel; + struct vmbus_channel *primary_channel, *channel; - BUG_ON(!channel->rescind); BUG_ON(!mutex_is_locked(&vmbus_connection.channel_mutex)); + /* + * Make sure channel is valid as we may have raced. + */ + channel = relid2channel(relid); + if (!channel) + return; + + BUG_ON(!channel->rescind); if (channel->target_cpu != get_cpu()) { put_cpu(); smp_call_function_single(channel->target_cpu, @@ -515,6 +522,7 @@ static void vmbus_process_offer(struct vmbus_channel *newchannel) if (!fnew) { if (channel->sc_creation_callback != NULL) channel->sc_creation_callback(newchannel); + newchannel->probe_done = true; return; } @@ -834,7 +842,6 @@ static void vmbus_onoffer_rescind(struct vmbus_channel_message_header *hdr) { struct vmbus_channel_rescind_offer *rescind; struct vmbus_channel *channel; - unsigned long flags; struct device *dev; rescind = (struct vmbus_channel_rescind_offer *)hdr; @@ -873,16 +880,6 @@ static void vmbus_onoffer_rescind(struct vmbus_channel_message_header *hdr) return; } - spin_lock_irqsave(&channel->lock, flags); - channel->rescind = true; - spin_unlock_irqrestore(&channel->lock, flags); - - /* - * Now that we have posted the rescind state, perform - * rescind related cleanup. - */ - vmbus_rescind_cleanup(channel); - /* * Now wait for offer handling to complete. */ @@ -901,6 +898,7 @@ static void vmbus_onoffer_rescind(struct vmbus_channel_message_header *hdr) if (channel->device_obj) { if (channel->chn_rescind_callback) { channel->chn_rescind_callback(channel); + vmbus_rescind_cleanup(channel); return; } /* @@ -909,6 +907,7 @@ static void vmbus_onoffer_rescind(struct vmbus_channel_message_header *hdr) */ dev = get_device(&channel->device_obj->device); if (dev) { + vmbus_rescind_cleanup(channel); vmbus_device_unregister(channel->device_obj); put_device(dev); } @@ -921,16 +920,16 @@ static void vmbus_onoffer_rescind(struct vmbus_channel_message_header *hdr) * 1. Close all sub-channels first * 2. Then close the primary channel. */ + mutex_lock(&vmbus_connection.channel_mutex); + vmbus_rescind_cleanup(channel); if (channel->state == CHANNEL_OPEN_STATE) { /* * The channel is currently not open; * it is safe for us to cleanup the channel. */ - mutex_lock(&vmbus_connection.channel_mutex); - hv_process_channel_removal(channel, - channel->offermsg.child_relid); - mutex_unlock(&vmbus_connection.channel_mutex); + hv_process_channel_removal(rescind->child_relid); } + mutex_unlock(&vmbus_connection.channel_mutex); } } @@ -938,7 +937,10 @@ void vmbus_hvsock_device_unregister(struct vmbus_channel *channel) { BUG_ON(!is_hvsock_channel(channel)); - channel->rescind = true; + /* We always get a rescind msg when a connection is closed. */ + while (!READ_ONCE(channel->probe_done) || !READ_ONCE(channel->rescind)) + msleep(1); + vmbus_device_unregister(channel->device_obj); } EXPORT_SYMBOL_GPL(vmbus_hvsock_device_unregister); diff --git a/drivers/hv/vmbus_drv.c b/drivers/hv/vmbus_drv.c index a9d49f6f6501..937801ac2fe0 100644 --- a/drivers/hv/vmbus_drv.c +++ b/drivers/hv/vmbus_drv.c @@ -768,8 +768,7 @@ static void vmbus_device_release(struct device *device) struct vmbus_channel *channel = hv_dev->channel; mutex_lock(&vmbus_connection.channel_mutex); - hv_process_channel_removal(channel, - channel->offermsg.child_relid); + hv_process_channel_removal(channel->offermsg.child_relid); mutex_unlock(&vmbus_connection.channel_mutex); kfree(hv_dev); diff --git a/drivers/hwmon/da9052-hwmon.c b/drivers/hwmon/da9052-hwmon.c index 97a62f5b9ea4..a973eb6a2890 100644 --- a/drivers/hwmon/da9052-hwmon.c +++ b/drivers/hwmon/da9052-hwmon.c @@ -477,6 +477,11 @@ static int da9052_hwmon_probe(struct platform_device *pdev) /* disable touchscreen features */ da9052_reg_write(hwmon->da9052, DA9052_TSI_CONT_A_REG, 0x00); + /* Sample every 1ms */ + da9052_reg_update(hwmon->da9052, DA9052_ADC_CONT_REG, + DA9052_ADCCONT_ADCMODE, + DA9052_ADCCONT_ADCMODE); + err = da9052_request_irq(hwmon->da9052, DA9052_IRQ_TSIREADY, "tsiready-irq", da9052_tsi_datardy_irq, hwmon); diff --git a/drivers/hwmon/tmp102.c b/drivers/hwmon/tmp102.c index 5eafbaada795..dfc40c740d07 100644 --- a/drivers/hwmon/tmp102.c +++ b/drivers/hwmon/tmp102.c @@ -268,14 +268,11 @@ static int tmp102_probe(struct i2c_client *client, return err; } - tmp102->ready_time = jiffies; - if (tmp102->config_orig & TMP102_CONF_SD) { - /* - * Mark that we are not ready with data until the first - * conversion is complete - */ - tmp102->ready_time += msecs_to_jiffies(CONVERSION_TIME_MS); - } + /* + * Mark that we are not ready with data until the first + * conversion is complete + */ + tmp102->ready_time = jiffies + msecs_to_jiffies(CONVERSION_TIME_MS); hwmon_dev = devm_hwmon_device_register_with_info(dev, client->name, tmp102, diff --git a/drivers/i2c/busses/i2c-imx.c b/drivers/i2c/busses/i2c-imx.c index 54a47b40546f..f96830ffd9f1 100644 --- a/drivers/i2c/busses/i2c-imx.c +++ b/drivers/i2c/busses/i2c-imx.c @@ -1021,7 +1021,7 @@ static int i2c_imx_init_recovery_info(struct imx_i2c_struct *i2c_imx, } dev_dbg(&pdev->dev, "using scl-gpio %d and sda-gpio %d for recovery\n", - rinfo->sda_gpio, rinfo->scl_gpio); + rinfo->scl_gpio, rinfo->sda_gpio); rinfo->prepare_recovery = i2c_imx_prepare_recovery; rinfo->unprepare_recovery = i2c_imx_unprepare_recovery; @@ -1100,7 +1100,7 @@ static int i2c_imx_probe(struct platform_device *pdev) } /* Request IRQ */ - ret = devm_request_irq(&pdev->dev, irq, i2c_imx_isr, 0, + ret = devm_request_irq(&pdev->dev, irq, i2c_imx_isr, IRQF_SHARED, pdev->name, i2c_imx); if (ret) { dev_err(&pdev->dev, "can't claim irq %d\n", irq); diff --git a/drivers/i2c/busses/i2c-ismt.c b/drivers/i2c/busses/i2c-ismt.c index 22ffcb73c185..b51adffa4841 100644 --- a/drivers/i2c/busses/i2c-ismt.c +++ b/drivers/i2c/busses/i2c-ismt.c @@ -340,12 +340,15 @@ static int ismt_process_desc(const struct ismt_desc *desc, data->word = dma_buffer[0] | (dma_buffer[1] << 8); break; case I2C_SMBUS_BLOCK_DATA: - case I2C_SMBUS_I2C_BLOCK_DATA: if (desc->rxbytes != dma_buffer[0] + 1) return -EMSGSIZE; memcpy(data->block, dma_buffer, desc->rxbytes); break; + case I2C_SMBUS_I2C_BLOCK_DATA: + memcpy(&data->block[1], dma_buffer, desc->rxbytes); + data->block[0] = desc->rxbytes; + break; } return 0; } diff --git a/drivers/i2c/busses/i2c-omap.c b/drivers/i2c/busses/i2c-omap.c index 1ebb5e947e0b..23c2ea2baedc 100644 --- a/drivers/i2c/busses/i2c-omap.c +++ b/drivers/i2c/busses/i2c-omap.c @@ -360,6 +360,7 @@ static int omap_i2c_init(struct omap_i2c_dev *omap) unsigned long fclk_rate = 12000000; unsigned long internal_clk = 0; struct clk *fclk; + int error; if (omap->rev >= OMAP_I2C_REV_ON_3430_3530) { /* @@ -378,6 +379,13 @@ static int omap_i2c_init(struct omap_i2c_dev *omap) * do this bit unconditionally. */ fclk = clk_get(omap->dev, "fck"); + if (IS_ERR(fclk)) { + error = PTR_ERR(fclk); + dev_err(omap->dev, "could not get fck: %i\n", error); + + return error; + } + fclk_rate = clk_get_rate(fclk); clk_put(fclk); @@ -410,6 +418,12 @@ static int omap_i2c_init(struct omap_i2c_dev *omap) else internal_clk = 4000; fclk = clk_get(omap->dev, "fck"); + if (IS_ERR(fclk)) { + error = PTR_ERR(fclk); + dev_err(omap->dev, "could not get fck: %i\n", error); + + return error; + } fclk_rate = clk_get_rate(fclk) / 1000; clk_put(fclk); diff --git a/drivers/i2c/busses/i2c-piix4.c b/drivers/i2c/busses/i2c-piix4.c index 0ecdb47a23ab..174579d32e5f 100644 --- a/drivers/i2c/busses/i2c-piix4.c +++ b/drivers/i2c/busses/i2c-piix4.c @@ -85,6 +85,9 @@ /* SB800 constants */ #define SB800_PIIX4_SMB_IDX 0xcd6 +#define KERNCZ_IMC_IDX 0x3e +#define KERNCZ_IMC_DATA 0x3f + /* * SB800 port is selected by bits 2:1 of the smb_en register (0x2c) * or the smb_sel register (0x2e), depending on bit 0 of register 0x2f. @@ -94,6 +97,12 @@ #define SB800_PIIX4_PORT_IDX_ALT 0x2e #define SB800_PIIX4_PORT_IDX_SEL 0x2f #define SB800_PIIX4_PORT_IDX_MASK 0x06 +#define SB800_PIIX4_PORT_IDX_SHIFT 1 + +/* On kerncz, SmBus0Sel is at bit 20:19 of PMx00 DecodeEn */ +#define SB800_PIIX4_PORT_IDX_KERNCZ 0x02 +#define SB800_PIIX4_PORT_IDX_MASK_KERNCZ 0x18 +#define SB800_PIIX4_PORT_IDX_SHIFT_KERNCZ 3 /* insmod parameters */ @@ -149,6 +158,8 @@ static const struct dmi_system_id piix4_dmi_ibm[] = { */ static DEFINE_MUTEX(piix4_mutex_sb800); static u8 piix4_port_sel_sb800; +static u8 piix4_port_mask_sb800; +static u8 piix4_port_shift_sb800; static const char *piix4_main_port_names_sb800[PIIX4_MAX_ADAPTERS] = { " port 0", " port 2", " port 3", " port 4" }; @@ -159,6 +170,7 @@ struct i2c_piix4_adapdata { /* SB800 */ bool sb800_main; + bool notify_imc; u8 port; /* Port number, shifted */ }; @@ -347,7 +359,19 @@ static int piix4_setup_sb800(struct pci_dev *PIIX4_dev, /* Find which register is used for port selection */ if (PIIX4_dev->vendor == PCI_VENDOR_ID_AMD) { - piix4_port_sel_sb800 = SB800_PIIX4_PORT_IDX_ALT; + switch (PIIX4_dev->device) { + case PCI_DEVICE_ID_AMD_KERNCZ_SMBUS: + piix4_port_sel_sb800 = SB800_PIIX4_PORT_IDX_KERNCZ; + piix4_port_mask_sb800 = SB800_PIIX4_PORT_IDX_MASK_KERNCZ; + piix4_port_shift_sb800 = SB800_PIIX4_PORT_IDX_SHIFT_KERNCZ; + break; + case PCI_DEVICE_ID_AMD_HUDSON2_SMBUS: + default: + piix4_port_sel_sb800 = SB800_PIIX4_PORT_IDX_ALT; + piix4_port_mask_sb800 = SB800_PIIX4_PORT_IDX_MASK; + piix4_port_shift_sb800 = SB800_PIIX4_PORT_IDX_SHIFT; + break; + } } else { mutex_lock(&piix4_mutex_sb800); outb_p(SB800_PIIX4_PORT_IDX_SEL, SB800_PIIX4_SMB_IDX); @@ -355,6 +379,8 @@ static int piix4_setup_sb800(struct pci_dev *PIIX4_dev, piix4_port_sel_sb800 = (port_sel & 0x01) ? SB800_PIIX4_PORT_IDX_ALT : SB800_PIIX4_PORT_IDX; + piix4_port_mask_sb800 = SB800_PIIX4_PORT_IDX_MASK; + piix4_port_shift_sb800 = SB800_PIIX4_PORT_IDX_SHIFT; mutex_unlock(&piix4_mutex_sb800); } @@ -572,6 +598,67 @@ static s32 piix4_access(struct i2c_adapter * adap, u16 addr, return 0; } +static uint8_t piix4_imc_read(uint8_t idx) +{ + outb_p(idx, KERNCZ_IMC_IDX); + return inb_p(KERNCZ_IMC_DATA); +} + +static void piix4_imc_write(uint8_t idx, uint8_t value) +{ + outb_p(idx, KERNCZ_IMC_IDX); + outb_p(value, KERNCZ_IMC_DATA); +} + +static int piix4_imc_sleep(void) +{ + int timeout = MAX_TIMEOUT; + + if (!request_muxed_region(KERNCZ_IMC_IDX, 2, "smbus_kerncz_imc")) + return -EBUSY; + + /* clear response register */ + piix4_imc_write(0x82, 0x00); + /* request ownership flag */ + piix4_imc_write(0x83, 0xB4); + /* kick off IMC Mailbox command 96 */ + piix4_imc_write(0x80, 0x96); + + while (timeout--) { + if (piix4_imc_read(0x82) == 0xfa) { + release_region(KERNCZ_IMC_IDX, 2); + return 0; + } + usleep_range(1000, 2000); + } + + release_region(KERNCZ_IMC_IDX, 2); + return -ETIMEDOUT; +} + +static void piix4_imc_wakeup(void) +{ + int timeout = MAX_TIMEOUT; + + if (!request_muxed_region(KERNCZ_IMC_IDX, 2, "smbus_kerncz_imc")) + return; + + /* clear response register */ + piix4_imc_write(0x82, 0x00); + /* release ownership flag */ + piix4_imc_write(0x83, 0xB5); + /* kick off IMC Mailbox command 96 */ + piix4_imc_write(0x80, 0x96); + + while (timeout--) { + if (piix4_imc_read(0x82) == 0xfa) + break; + usleep_range(1000, 2000); + } + + release_region(KERNCZ_IMC_IDX, 2); +} + /* * Handles access to multiple SMBus ports on the SB800. * The port is selected by bits 2:1 of the smb_en register (0x2c). @@ -612,12 +699,47 @@ static s32 piix4_access_sb800(struct i2c_adapter *adap, u16 addr, return -EBUSY; } + /* + * Notify the IMC (Integrated Micro Controller) if required. + * Among other responsibilities, the IMC is in charge of monitoring + * the System fans and temperature sensors, and act accordingly. + * All this is done through SMBus and can/will collide + * with our transactions if they are long (BLOCK_DATA). + * Therefore we need to request the ownership flag during those + * transactions. + */ + if ((size == I2C_SMBUS_BLOCK_DATA) && adapdata->notify_imc) { + int ret; + + ret = piix4_imc_sleep(); + switch (ret) { + case -EBUSY: + dev_warn(&adap->dev, + "IMC base address index region 0x%x already in use.\n", + KERNCZ_IMC_IDX); + break; + case -ETIMEDOUT: + dev_warn(&adap->dev, + "Failed to communicate with the IMC.\n"); + break; + default: + break; + } + + /* If IMC communication fails do not retry */ + if (ret) { + dev_warn(&adap->dev, + "Continuing without IMC notification.\n"); + adapdata->notify_imc = false; + } + } + outb_p(piix4_port_sel_sb800, SB800_PIIX4_SMB_IDX); smba_en_lo = inb_p(SB800_PIIX4_SMB_IDX + 1); port = adapdata->port; - if ((smba_en_lo & SB800_PIIX4_PORT_IDX_MASK) != port) - outb_p((smba_en_lo & ~SB800_PIIX4_PORT_IDX_MASK) | port, + if ((smba_en_lo & piix4_port_mask_sb800) != port) + outb_p((smba_en_lo & ~piix4_port_mask_sb800) | port, SB800_PIIX4_SMB_IDX + 1); retval = piix4_access(adap, addr, flags, read_write, @@ -628,6 +750,9 @@ static s32 piix4_access_sb800(struct i2c_adapter *adap, u16 addr, /* Release the semaphore */ outb_p(smbslvcnt | 0x20, SMBSLVCNT); + if ((size == I2C_SMBUS_BLOCK_DATA) && adapdata->notify_imc) + piix4_imc_wakeup(); + mutex_unlock(&piix4_mutex_sb800); return retval; @@ -679,7 +804,7 @@ static struct i2c_adapter *piix4_main_adapters[PIIX4_MAX_ADAPTERS]; static struct i2c_adapter *piix4_aux_adapter; static int piix4_add_adapter(struct pci_dev *dev, unsigned short smba, - bool sb800_main, u8 port, + bool sb800_main, u8 port, bool notify_imc, const char *name, struct i2c_adapter **padap) { struct i2c_adapter *adap; @@ -706,7 +831,8 @@ static int piix4_add_adapter(struct pci_dev *dev, unsigned short smba, adapdata->smba = smba; adapdata->sb800_main = sb800_main; - adapdata->port = port << 1; + adapdata->port = port << piix4_port_shift_sb800; + adapdata->notify_imc = notify_imc; /* set up the sysfs linkage to our parent device */ adap->dev.parent = &dev->dev; @@ -728,14 +854,15 @@ static int piix4_add_adapter(struct pci_dev *dev, unsigned short smba, return 0; } -static int piix4_add_adapters_sb800(struct pci_dev *dev, unsigned short smba) +static int piix4_add_adapters_sb800(struct pci_dev *dev, unsigned short smba, + bool notify_imc) { struct i2c_piix4_adapdata *adapdata; int port; int retval; for (port = 0; port < PIIX4_MAX_ADAPTERS; port++) { - retval = piix4_add_adapter(dev, smba, true, port, + retval = piix4_add_adapter(dev, smba, true, port, notify_imc, piix4_main_port_names_sb800[port], &piix4_main_adapters[port]); if (retval < 0) @@ -769,6 +896,7 @@ static int piix4_probe(struct pci_dev *dev, const struct pci_device_id *id) dev->device == PCI_DEVICE_ID_ATI_SBX00_SMBUS && dev->revision >= 0x40) || dev->vendor == PCI_VENDOR_ID_AMD) { + bool notify_imc = false; is_sb800 = true; if (!request_region(SB800_PIIX4_SMB_IDX, 2, "smba_idx")) { @@ -778,6 +906,20 @@ static int piix4_probe(struct pci_dev *dev, const struct pci_device_id *id) return -EBUSY; } + if (dev->vendor == PCI_VENDOR_ID_AMD && + dev->device == PCI_DEVICE_ID_AMD_KERNCZ_SMBUS) { + u8 imc; + + /* + * Detect if IMC is active or not, this method is + * described on coreboot's AMD IMC notes + */ + pci_bus_read_config_byte(dev->bus, PCI_DEVFN(0x14, 3), + 0x40, &imc); + if (imc & 0x80) + notify_imc = true; + } + /* base address location etc changed in SB800 */ retval = piix4_setup_sb800(dev, id, 0); if (retval < 0) { @@ -789,7 +931,7 @@ static int piix4_probe(struct pci_dev *dev, const struct pci_device_id *id) * Try to register multiplexed main SMBus adapter, * give up if we can't */ - retval = piix4_add_adapters_sb800(dev, retval); + retval = piix4_add_adapters_sb800(dev, retval, notify_imc); if (retval < 0) { release_region(SB800_PIIX4_SMB_IDX, 2); return retval; @@ -800,7 +942,7 @@ static int piix4_probe(struct pci_dev *dev, const struct pci_device_id *id) return retval; /* Try to register main SMBus adapter, give up if we can't */ - retval = piix4_add_adapter(dev, retval, false, 0, "", + retval = piix4_add_adapter(dev, retval, false, 0, false, "", &piix4_main_adapters[0]); if (retval < 0) return retval; @@ -827,7 +969,7 @@ static int piix4_probe(struct pci_dev *dev, const struct pci_device_id *id) if (retval > 0) { /* Try to add the aux adapter if it exists, * piix4_add_adapter will clean up if this fails */ - piix4_add_adapter(dev, retval, false, 0, + piix4_add_adapter(dev, retval, false, 0, false, is_sb800 ? piix4_aux_port_name_sb800 : "", &piix4_aux_adapter); } diff --git a/drivers/ide/ide-cd.c b/drivers/ide/ide-cd.c index 81e18f9628d0..a7355ab3bb22 100644 --- a/drivers/ide/ide-cd.c +++ b/drivers/ide/ide-cd.c @@ -1328,6 +1328,7 @@ static int ide_cdrom_prep_fs(struct request_queue *q, struct request *rq) unsigned long blocks = blk_rq_sectors(rq) / (hard_sect >> 9); struct scsi_request *req = scsi_req(rq); + scsi_req_init(req); memset(req->cmd, 0, BLK_MAX_CDB); if (rq_data_dir(rq) == READ) diff --git a/drivers/iio/adc/Kconfig b/drivers/iio/adc/Kconfig index 57625653fcb6..1d13bf03c758 100644 --- a/drivers/iio/adc/Kconfig +++ b/drivers/iio/adc/Kconfig @@ -243,6 +243,8 @@ config DA9150_GPADC config DLN2_ADC tristate "Diolan DLN-2 ADC driver support" depends on MFD_DLN2 + select IIO_BUFFER + select IIO_TRIGGERED_BUFFER help Say yes here to build support for Diolan DLN-2 ADC. diff --git a/drivers/iio/adc/at91-sama5d2_adc.c b/drivers/iio/adc/at91-sama5d2_adc.c index bc5b38e3a147..a70ef7fec95f 100644 --- a/drivers/iio/adc/at91-sama5d2_adc.c +++ b/drivers/iio/adc/at91-sama5d2_adc.c @@ -225,6 +225,7 @@ struct at91_adc_trigger { char *name; unsigned int trgmod_value; unsigned int edge_type; + bool hw_trig; }; struct at91_adc_state { @@ -254,16 +255,25 @@ static const struct at91_adc_trigger at91_adc_trigger_list[] = { .name = "external_rising", .trgmod_value = AT91_SAMA5D2_TRGR_TRGMOD_EXT_TRIG_RISE, .edge_type = IRQ_TYPE_EDGE_RISING, + .hw_trig = true, }, { .name = "external_falling", .trgmod_value = AT91_SAMA5D2_TRGR_TRGMOD_EXT_TRIG_FALL, .edge_type = IRQ_TYPE_EDGE_FALLING, + .hw_trig = true, }, { .name = "external_any", .trgmod_value = AT91_SAMA5D2_TRGR_TRGMOD_EXT_TRIG_ANY, .edge_type = IRQ_TYPE_EDGE_BOTH, + .hw_trig = true, + }, + { + .name = "software", + .trgmod_value = AT91_SAMA5D2_TRGR_TRGMOD_NO_TRIGGER, + .edge_type = IRQ_TYPE_NONE, + .hw_trig = false, }, }; @@ -597,7 +607,7 @@ static int at91_adc_probe(struct platform_device *pdev) struct at91_adc_state *st; struct resource *res; int ret, i; - u32 edge_type; + u32 edge_type = IRQ_TYPE_NONE; indio_dev = devm_iio_device_alloc(&pdev->dev, sizeof(*st)); if (!indio_dev) @@ -641,14 +651,14 @@ static int at91_adc_probe(struct platform_device *pdev) ret = of_property_read_u32(pdev->dev.of_node, "atmel,trigger-edge-type", &edge_type); if (ret) { - dev_err(&pdev->dev, - "invalid or missing value for atmel,trigger-edge-type\n"); - return ret; + dev_dbg(&pdev->dev, + "atmel,trigger-edge-type not specified, only software trigger available\n"); } st->selected_trig = NULL; - for (i = 0; i < AT91_SAMA5D2_HW_TRIG_CNT; i++) + /* find the right trigger, or no trigger at all */ + for (i = 0; i < AT91_SAMA5D2_HW_TRIG_CNT + 1; i++) if (at91_adc_trigger_list[i].edge_type == edge_type) { st->selected_trig = &at91_adc_trigger_list[i]; break; @@ -717,24 +727,27 @@ static int at91_adc_probe(struct platform_device *pdev) platform_set_drvdata(pdev, indio_dev); - ret = at91_adc_buffer_init(indio_dev); - if (ret < 0) { - dev_err(&pdev->dev, "couldn't initialize the buffer.\n"); - goto per_clk_disable_unprepare; - } + if (st->selected_trig->hw_trig) { + ret = at91_adc_buffer_init(indio_dev); + if (ret < 0) { + dev_err(&pdev->dev, "couldn't initialize the buffer.\n"); + goto per_clk_disable_unprepare; + } - ret = at91_adc_trigger_init(indio_dev); - if (ret < 0) { - dev_err(&pdev->dev, "couldn't setup the triggers.\n"); - goto per_clk_disable_unprepare; + ret = at91_adc_trigger_init(indio_dev); + if (ret < 0) { + dev_err(&pdev->dev, "couldn't setup the triggers.\n"); + goto per_clk_disable_unprepare; + } } ret = iio_device_register(indio_dev); if (ret < 0) goto per_clk_disable_unprepare; - dev_info(&pdev->dev, "setting up trigger as %s\n", - st->selected_trig->name); + if (st->selected_trig->hw_trig) + dev_info(&pdev->dev, "setting up trigger as %s\n", + st->selected_trig->name); dev_info(&pdev->dev, "version: %x\n", readl_relaxed(st->base + AT91_SAMA5D2_VERSION)); diff --git a/drivers/iio/dummy/iio_simple_dummy_events.c b/drivers/iio/dummy/iio_simple_dummy_events.c index ed63ffd849f8..7ec2a0bb0807 100644 --- a/drivers/iio/dummy/iio_simple_dummy_events.c +++ b/drivers/iio/dummy/iio_simple_dummy_events.c @@ -72,6 +72,7 @@ int iio_simple_dummy_write_event_config(struct iio_dev *indio_dev, st->event_en = state; else return -EINVAL; + break; default: return -EINVAL; } diff --git a/drivers/iio/pressure/zpa2326.c b/drivers/iio/pressure/zpa2326.c index ebfb1de7377f..91431454eb85 100644 --- a/drivers/iio/pressure/zpa2326.c +++ b/drivers/iio/pressure/zpa2326.c @@ -865,7 +865,6 @@ complete: static int zpa2326_wait_oneshot_completion(const struct iio_dev *indio_dev, struct zpa2326_private *private) { - int ret; unsigned int val; long timeout; @@ -887,14 +886,11 @@ static int zpa2326_wait_oneshot_completion(const struct iio_dev *indio_dev, /* Timed out. */ zpa2326_warn(indio_dev, "no one shot interrupt occurred (%ld)", timeout); - ret = -ETIME; - } else if (timeout < 0) { - zpa2326_warn(indio_dev, - "wait for one shot interrupt cancelled"); - ret = -ERESTARTSYS; + return -ETIME; } - return ret; + zpa2326_warn(indio_dev, "wait for one shot interrupt cancelled"); + return -ERESTARTSYS; } static int zpa2326_init_managed_irq(struct device *parent, diff --git a/drivers/iio/proximity/as3935.c b/drivers/iio/proximity/as3935.c index 0eeff29b61be..4a48b7ba3a1c 100644 --- a/drivers/iio/proximity/as3935.c +++ b/drivers/iio/proximity/as3935.c @@ -39,8 +39,12 @@ #define AS3935_AFE_GAIN_MAX 0x1F #define AS3935_AFE_PWR_BIT BIT(0) +#define AS3935_NFLWDTH 0x01 +#define AS3935_NFLWDTH_MASK 0x7f + #define AS3935_INT 0x03 #define AS3935_INT_MASK 0x0f +#define AS3935_DISTURB_INT BIT(2) #define AS3935_EVENT_INT BIT(3) #define AS3935_NOISE_INT BIT(0) @@ -48,6 +52,7 @@ #define AS3935_DATA_MASK 0x3F #define AS3935_TUNE_CAP 0x08 +#define AS3935_DEFAULTS 0x3C #define AS3935_CALIBRATE 0x3D #define AS3935_READ_DATA BIT(14) @@ -62,7 +67,9 @@ struct as3935_state { struct mutex lock; struct delayed_work work; + unsigned long noise_tripped; u32 tune_cap; + u32 nflwdth_reg; u8 buffer[16]; /* 8-bit data + 56-bit padding + 64-bit timestamp */ u8 buf[2] ____cacheline_aligned; }; @@ -145,12 +152,29 @@ static ssize_t as3935_sensor_sensitivity_store(struct device *dev, return len; } +static ssize_t as3935_noise_level_tripped_show(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + struct as3935_state *st = iio_priv(dev_to_iio_dev(dev)); + int ret; + + mutex_lock(&st->lock); + ret = sprintf(buf, "%d\n", !time_after(jiffies, st->noise_tripped + HZ)); + mutex_unlock(&st->lock); + + return ret; +} + static IIO_DEVICE_ATTR(sensor_sensitivity, S_IRUGO | S_IWUSR, as3935_sensor_sensitivity_show, as3935_sensor_sensitivity_store, 0); +static IIO_DEVICE_ATTR(noise_level_tripped, S_IRUGO, + as3935_noise_level_tripped_show, NULL, 0); static struct attribute *as3935_attributes[] = { &iio_dev_attr_sensor_sensitivity.dev_attr.attr, + &iio_dev_attr_noise_level_tripped.dev_attr.attr, NULL, }; @@ -246,7 +270,11 @@ static void as3935_event_work(struct work_struct *work) case AS3935_EVENT_INT: iio_trigger_poll_chained(st->trig); break; + case AS3935_DISTURB_INT: case AS3935_NOISE_INT: + mutex_lock(&st->lock); + st->noise_tripped = jiffies; + mutex_unlock(&st->lock); dev_warn(&st->spi->dev, "noise level is too high\n"); break; } @@ -269,15 +297,14 @@ static irqreturn_t as3935_interrupt_handler(int irq, void *private) static void calibrate_as3935(struct as3935_state *st) { - /* mask disturber interrupt bit */ - as3935_write(st, AS3935_INT, BIT(5)); - + as3935_write(st, AS3935_DEFAULTS, 0x96); as3935_write(st, AS3935_CALIBRATE, 0x96); as3935_write(st, AS3935_TUNE_CAP, BIT(5) | (st->tune_cap / TUNE_CAP_DIV)); mdelay(2); as3935_write(st, AS3935_TUNE_CAP, (st->tune_cap / TUNE_CAP_DIV)); + as3935_write(st, AS3935_NFLWDTH, st->nflwdth_reg); } #ifdef CONFIG_PM_SLEEP @@ -370,6 +397,15 @@ static int as3935_probe(struct spi_device *spi) return -EINVAL; } + ret = of_property_read_u32(np, + "ams,nflwdth", &st->nflwdth_reg); + if (!ret && st->nflwdth_reg > AS3935_NFLWDTH_MASK) { + dev_err(&spi->dev, + "invalid nflwdth setting of %d\n", + st->nflwdth_reg); + return -EINVAL; + } + indio_dev->dev.parent = &spi->dev; indio_dev->name = spi_get_device_id(spi)->name; indio_dev->channels = as3935_channels; @@ -384,6 +420,7 @@ static int as3935_probe(struct spi_device *spi) return -ENOMEM; st->trig = trig; + st->noise_tripped = jiffies - HZ; trig->dev.parent = indio_dev->dev.parent; iio_trigger_set_drvdata(trig, indio_dev); trig->ops = &iio_interrupt_trigger_ops; diff --git a/drivers/infiniband/core/netlink.c b/drivers/infiniband/core/netlink.c index b12e58787c3d..1fb72c356e36 100644 --- a/drivers/infiniband/core/netlink.c +++ b/drivers/infiniband/core/netlink.c @@ -175,13 +175,24 @@ static int rdma_nl_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh, !netlink_capable(skb, CAP_NET_ADMIN)) return -EPERM; + /* + * LS responses overload the 0x100 (NLM_F_ROOT) flag. Don't + * mistakenly call the .dump() function. + */ + if (index == RDMA_NL_LS) { + if (cb_table[op].doit) + return cb_table[op].doit(skb, nlh, extack); + return -EINVAL; + } /* FIXME: Convert IWCM to properly handle doit callbacks */ if ((nlh->nlmsg_flags & NLM_F_DUMP) || index == RDMA_NL_RDMA_CM || index == RDMA_NL_IWCM) { struct netlink_dump_control c = { .dump = cb_table[op].dump, }; - return netlink_dump_start(nls, skb, nlh, &c); + if (c.dump) + return netlink_dump_start(nls, skb, nlh, &c); + return -EINVAL; } if (cb_table[op].doit) diff --git a/drivers/infiniband/core/nldev.c b/drivers/infiniband/core/nldev.c index 3ba24c428c3b..2fae850a3eff 100644 --- a/drivers/infiniband/core/nldev.c +++ b/drivers/infiniband/core/nldev.c @@ -214,7 +214,9 @@ static int nldev_port_get_doit(struct sk_buff *skb, struct nlmsghdr *nlh, err = nlmsg_parse(nlh, 0, tb, RDMA_NLDEV_ATTR_MAX - 1, nldev_policy, extack); - if (err || !tb[RDMA_NLDEV_ATTR_PORT_INDEX]) + if (err || + !tb[RDMA_NLDEV_ATTR_DEV_INDEX] || + !tb[RDMA_NLDEV_ATTR_PORT_INDEX]) return -EINVAL; index = nla_get_u32(tb[RDMA_NLDEV_ATTR_DEV_INDEX]); diff --git a/drivers/input/input.c b/drivers/input/input.c index d268fdc23c64..762bfb9487dc 100644 --- a/drivers/input/input.c +++ b/drivers/input/input.c @@ -933,58 +933,52 @@ int input_set_keycode(struct input_dev *dev, } EXPORT_SYMBOL(input_set_keycode); +bool input_match_device_id(const struct input_dev *dev, + const struct input_device_id *id) +{ + if (id->flags & INPUT_DEVICE_ID_MATCH_BUS) + if (id->bustype != dev->id.bustype) + return false; + + if (id->flags & INPUT_DEVICE_ID_MATCH_VENDOR) + if (id->vendor != dev->id.vendor) + return false; + + if (id->flags & INPUT_DEVICE_ID_MATCH_PRODUCT) + if (id->product != dev->id.product) + return false; + + if (id->flags & INPUT_DEVICE_ID_MATCH_VERSION) + if (id->version != dev->id.version) + return false; + + if (!bitmap_subset(id->evbit, dev->evbit, EV_MAX) || + !bitmap_subset(id->keybit, dev->keybit, KEY_MAX) || + !bitmap_subset(id->relbit, dev->relbit, REL_MAX) || + !bitmap_subset(id->absbit, dev->absbit, ABS_MAX) || + !bitmap_subset(id->mscbit, dev->mscbit, MSC_MAX) || + !bitmap_subset(id->ledbit, dev->ledbit, LED_MAX) || + !bitmap_subset(id->sndbit, dev->sndbit, SND_MAX) || + !bitmap_subset(id->ffbit, dev->ffbit, FF_MAX) || + !bitmap_subset(id->swbit, dev->swbit, SW_MAX) || + !bitmap_subset(id->propbit, dev->propbit, INPUT_PROP_MAX)) { + return false; + } + + return true; +} +EXPORT_SYMBOL(input_match_device_id); + static const struct input_device_id *input_match_device(struct input_handler *handler, struct input_dev *dev) { const struct input_device_id *id; for (id = handler->id_table; id->flags || id->driver_info; id++) { - - if (id->flags & INPUT_DEVICE_ID_MATCH_BUS) - if (id->bustype != dev->id.bustype) - continue; - - if (id->flags & INPUT_DEVICE_ID_MATCH_VENDOR) - if (id->vendor != dev->id.vendor) - continue; - - if (id->flags & INPUT_DEVICE_ID_MATCH_PRODUCT) - if (id->product != dev->id.product) - continue; - - if (id->flags & INPUT_DEVICE_ID_MATCH_VERSION) - if (id->version != dev->id.version) - continue; - - if (!bitmap_subset(id->evbit, dev->evbit, EV_MAX)) - continue; - - if (!bitmap_subset(id->keybit, dev->keybit, KEY_MAX)) - continue; - - if (!bitmap_subset(id->relbit, dev->relbit, REL_MAX)) - continue; - - if (!bitmap_subset(id->absbit, dev->absbit, ABS_MAX)) - continue; - - if (!bitmap_subset(id->mscbit, dev->mscbit, MSC_MAX)) - continue; - - if (!bitmap_subset(id->ledbit, dev->ledbit, LED_MAX)) - continue; - - if (!bitmap_subset(id->sndbit, dev->sndbit, SND_MAX)) - continue; - - if (!bitmap_subset(id->ffbit, dev->ffbit, FF_MAX)) - continue; - - if (!bitmap_subset(id->swbit, dev->swbit, SW_MAX)) - continue; - - if (!handler->match || handler->match(handler, dev)) + if (input_match_device_id(dev, id) && + (!handler->match || handler->match(handler, dev))) { return id; + } } return NULL; diff --git a/drivers/input/joydev.c b/drivers/input/joydev.c index 29d677c714d2..7b29a8944039 100644 --- a/drivers/input/joydev.c +++ b/drivers/input/joydev.c @@ -747,6 +747,68 @@ static void joydev_cleanup(struct joydev *joydev) input_close_device(handle); } +/* + * These codes are copied from from hid-ids.h, unfortunately there is no common + * usb_ids/bt_ids.h header. + */ +#define USB_VENDOR_ID_SONY 0x054c +#define USB_DEVICE_ID_SONY_PS3_CONTROLLER 0x0268 +#define USB_DEVICE_ID_SONY_PS4_CONTROLLER 0x05c4 +#define USB_DEVICE_ID_SONY_PS4_CONTROLLER_2 0x09cc +#define USB_DEVICE_ID_SONY_PS4_CONTROLLER_DONGLE 0x0ba0 + +#define USB_VENDOR_ID_THQ 0x20d6 +#define USB_DEVICE_ID_THQ_PS3_UDRAW 0xcb17 + +#define ACCEL_DEV(vnd, prd) \ + { \ + .flags = INPUT_DEVICE_ID_MATCH_VENDOR | \ + INPUT_DEVICE_ID_MATCH_PRODUCT | \ + INPUT_DEVICE_ID_MATCH_PROPBIT, \ + .vendor = (vnd), \ + .product = (prd), \ + .propbit = { BIT_MASK(INPUT_PROP_ACCELEROMETER) }, \ + } + +static const struct input_device_id joydev_blacklist[] = { + /* Avoid touchpads and touchscreens */ + { + .flags = INPUT_DEVICE_ID_MATCH_EVBIT | + INPUT_DEVICE_ID_MATCH_KEYBIT, + .evbit = { BIT_MASK(EV_KEY) }, + .keybit = { [BIT_WORD(BTN_TOUCH)] = BIT_MASK(BTN_TOUCH) }, + }, + /* Avoid tablets, digitisers and similar devices */ + { + .flags = INPUT_DEVICE_ID_MATCH_EVBIT | + INPUT_DEVICE_ID_MATCH_KEYBIT, + .evbit = { BIT_MASK(EV_KEY) }, + .keybit = { [BIT_WORD(BTN_DIGI)] = BIT_MASK(BTN_DIGI) }, + }, + /* Disable accelerometers on composite devices */ + ACCEL_DEV(USB_VENDOR_ID_SONY, USB_DEVICE_ID_SONY_PS3_CONTROLLER), + ACCEL_DEV(USB_VENDOR_ID_SONY, USB_DEVICE_ID_SONY_PS4_CONTROLLER), + ACCEL_DEV(USB_VENDOR_ID_SONY, USB_DEVICE_ID_SONY_PS4_CONTROLLER_2), + ACCEL_DEV(USB_VENDOR_ID_SONY, USB_DEVICE_ID_SONY_PS4_CONTROLLER_DONGLE), + ACCEL_DEV(USB_VENDOR_ID_THQ, USB_DEVICE_ID_THQ_PS3_UDRAW), + { /* sentinel */ } +}; + +static bool joydev_dev_is_blacklisted(struct input_dev *dev) +{ + const struct input_device_id *id; + + for (id = joydev_blacklist; id->flags; id++) { + if (input_match_device_id(dev, id)) { + dev_dbg(&dev->dev, + "joydev: blacklisting '%s'\n", dev->name); + return true; + } + } + + return false; +} + static bool joydev_dev_is_absolute_mouse(struct input_dev *dev) { DECLARE_BITMAP(jd_scratch, KEY_CNT); @@ -807,12 +869,8 @@ static bool joydev_dev_is_absolute_mouse(struct input_dev *dev) static bool joydev_match(struct input_handler *handler, struct input_dev *dev) { - /* Avoid touchpads and touchscreens */ - if (test_bit(EV_KEY, dev->evbit) && test_bit(BTN_TOUCH, dev->keybit)) - return false; - - /* Avoid tablets, digitisers and similar devices */ - if (test_bit(EV_KEY, dev->evbit) && test_bit(BTN_DIGI, dev->keybit)) + /* Disable blacklisted devices */ + if (joydev_dev_is_blacklisted(dev)) return false; /* Avoid absolute mice */ diff --git a/drivers/input/keyboard/tca8418_keypad.c b/drivers/input/keyboard/tca8418_keypad.c index e37e335e406f..6da607d3b811 100644 --- a/drivers/input/keyboard/tca8418_keypad.c +++ b/drivers/input/keyboard/tca8418_keypad.c @@ -234,14 +234,7 @@ static irqreturn_t tca8418_irq_handler(int irq, void *dev_id) static int tca8418_configure(struct tca8418_keypad *keypad_data, u32 rows, u32 cols) { - int reg, error; - - /* Write config register, if this fails assume device not present */ - error = tca8418_write_byte(keypad_data, REG_CFG, - CFG_INT_CFG | CFG_OVR_FLOW_IEN | CFG_KE_IEN); - if (error < 0) - return -ENODEV; - + int reg, error = 0; /* Assemble a mask for row and column registers */ reg = ~(~0 << rows); @@ -257,6 +250,12 @@ static int tca8418_configure(struct tca8418_keypad *keypad_data, error |= tca8418_write_byte(keypad_data, REG_DEBOUNCE_DIS2, reg >> 8); error |= tca8418_write_byte(keypad_data, REG_DEBOUNCE_DIS3, reg >> 16); + if (error) + return error; + + error = tca8418_write_byte(keypad_data, REG_CFG, + CFG_INT_CFG | CFG_OVR_FLOW_IEN | CFG_KE_IEN); + return error; } @@ -268,6 +267,7 @@ static int tca8418_keypad_probe(struct i2c_client *client, struct input_dev *input; u32 rows = 0, cols = 0; int error, row_shift, max_keys; + u8 reg; /* Check i2c driver capabilities */ if (!i2c_check_functionality(client->adapter, I2C_FUNC_SMBUS_BYTE)) { @@ -301,10 +301,10 @@ static int tca8418_keypad_probe(struct i2c_client *client, keypad_data->client = client; keypad_data->row_shift = row_shift; - /* Initialize the chip or fail if chip isn't present */ - error = tca8418_configure(keypad_data, rows, cols); - if (error < 0) - return error; + /* Read key lock register, if this fails assume device not present */ + error = tca8418_read_byte(keypad_data, REG_KEY_LCK_EC, ®); + if (error) + return -ENODEV; /* Configure input device */ input = devm_input_allocate_device(dev); @@ -340,6 +340,11 @@ static int tca8418_keypad_probe(struct i2c_client *client, return error; } + /* Initialize the chip */ + error = tca8418_configure(keypad_data, rows, cols); + if (error < 0) + return error; + error = input_register_device(input); if (error) { dev_err(dev, "Unable to register input device, error: %d\n", diff --git a/drivers/input/misc/axp20x-pek.c b/drivers/input/misc/axp20x-pek.c index 6cee5adc3b5c..debeeaeb8812 100644 --- a/drivers/input/misc/axp20x-pek.c +++ b/drivers/input/misc/axp20x-pek.c @@ -403,6 +403,7 @@ static const struct platform_device_id axp_pek_id_match[] = { }, { /* sentinel */ } }; +MODULE_DEVICE_TABLE(platform, axp_pek_id_match); static struct platform_driver axp20x_pek_driver = { .probe = axp20x_pek_probe, @@ -417,4 +418,3 @@ module_platform_driver(axp20x_pek_driver); MODULE_DESCRIPTION("axp20x Power Button"); MODULE_AUTHOR("Carlo Caione <carlo@caione.org>"); MODULE_LICENSE("GPL"); -MODULE_ALIAS("platform:axp20x-pek"); diff --git a/drivers/input/misc/ims-pcu.c b/drivers/input/misc/ims-pcu.c index 6bf82ea8c918..ae473123583b 100644 --- a/drivers/input/misc/ims-pcu.c +++ b/drivers/input/misc/ims-pcu.c @@ -1635,13 +1635,25 @@ ims_pcu_get_cdc_union_desc(struct usb_interface *intf) return NULL; } - while (buflen > 0) { + while (buflen >= sizeof(*union_desc)) { union_desc = (struct usb_cdc_union_desc *)buf; + if (union_desc->bLength > buflen) { + dev_err(&intf->dev, "Too large descriptor\n"); + return NULL; + } + if (union_desc->bDescriptorType == USB_DT_CS_INTERFACE && union_desc->bDescriptorSubType == USB_CDC_UNION_TYPE) { dev_dbg(&intf->dev, "Found union header\n"); - return union_desc; + + if (union_desc->bLength >= sizeof(*union_desc)) + return union_desc; + + dev_err(&intf->dev, + "Union descriptor to short (%d vs %zd\n)", + union_desc->bLength, sizeof(*union_desc)); + return NULL; } buflen -= union_desc->bLength; diff --git a/drivers/input/mouse/elan_i2c_core.c b/drivers/input/mouse/elan_i2c_core.c index 0e761d079dc4..6d6b092e2da9 100644 --- a/drivers/input/mouse/elan_i2c_core.c +++ b/drivers/input/mouse/elan_i2c_core.c @@ -1258,6 +1258,7 @@ static const struct acpi_device_id elan_acpi_id[] = { { "ELAN0605", 0 }, { "ELAN0609", 0 }, { "ELAN060B", 0 }, + { "ELAN0611", 0 }, { "ELAN1000", 0 }, { } }; diff --git a/drivers/input/mouse/synaptics.c b/drivers/input/mouse/synaptics.c index 5af0b7d200bc..ee5466a374bf 100644 --- a/drivers/input/mouse/synaptics.c +++ b/drivers/input/mouse/synaptics.c @@ -1709,8 +1709,7 @@ static int synaptics_create_intertouch(struct psmouse *psmouse, .sensor_pdata = { .sensor_type = rmi_sensor_touchpad, .axis_align.flip_y = true, - /* to prevent cursors jumps: */ - .kernel_tracking = true, + .kernel_tracking = false, .topbuttonpad = topbuttonpad, }, .f30_data = { diff --git a/drivers/input/rmi4/rmi_f30.c b/drivers/input/rmi4/rmi_f30.c index 34dfee555b20..82e0f0d43d55 100644 --- a/drivers/input/rmi4/rmi_f30.c +++ b/drivers/input/rmi4/rmi_f30.c @@ -232,9 +232,10 @@ static int rmi_f30_map_gpios(struct rmi_function *fn, unsigned int trackstick_button = BTN_LEFT; bool button_mapped = false; int i; + int button_count = min_t(u8, f30->gpioled_count, TRACKSTICK_RANGE_END); f30->gpioled_key_map = devm_kcalloc(&fn->dev, - f30->gpioled_count, + button_count, sizeof(f30->gpioled_key_map[0]), GFP_KERNEL); if (!f30->gpioled_key_map) { @@ -242,7 +243,7 @@ static int rmi_f30_map_gpios(struct rmi_function *fn, return -ENOMEM; } - for (i = 0; i < f30->gpioled_count; i++) { + for (i = 0; i < button_count; i++) { if (!rmi_f30_is_valid_button(i, f30->ctrl)) continue; diff --git a/drivers/input/tablet/gtco.c b/drivers/input/tablet/gtco.c index b796e891e2ee..4b8b9d7aa75e 100644 --- a/drivers/input/tablet/gtco.c +++ b/drivers/input/tablet/gtco.c @@ -230,13 +230,17 @@ static void parse_hid_report_descriptor(struct gtco *device, char * report, /* Walk this report and pull out the info we need */ while (i < length) { - prefix = report[i]; - - /* Skip over prefix */ - i++; + prefix = report[i++]; /* Determine data size and save the data in the proper variable */ - size = PREF_SIZE(prefix); + size = (1U << PREF_SIZE(prefix)) >> 1; + if (i + size > length) { + dev_err(ddev, + "Not enough data (need %d, have %d)\n", + i + size, length); + break; + } + switch (size) { case 1: data = report[i]; @@ -244,8 +248,7 @@ static void parse_hid_report_descriptor(struct gtco *device, char * report, case 2: data16 = get_unaligned_le16(&report[i]); break; - case 3: - size = 4; + case 4: data32 = get_unaligned_le32(&report[i]); break; } diff --git a/drivers/input/touchscreen/goodix.c b/drivers/input/touchscreen/goodix.c index 32d2762448aa..b3bbad7d2282 100644 --- a/drivers/input/touchscreen/goodix.c +++ b/drivers/input/touchscreen/goodix.c @@ -72,6 +72,9 @@ struct goodix_ts_data { #define GOODIX_REG_CONFIG_DATA 0x8047 #define GOODIX_REG_ID 0x8140 +#define GOODIX_BUFFER_STATUS_READY BIT(7) +#define GOODIX_BUFFER_STATUS_TIMEOUT 20 + #define RESOLUTION_LOC 1 #define MAX_CONTACTS_LOC 5 #define TRIGGER_LOC 6 @@ -195,35 +198,53 @@ static int goodix_get_cfg_len(u16 id) static int goodix_ts_read_input_report(struct goodix_ts_data *ts, u8 *data) { + unsigned long max_timeout; int touch_num; int error; - error = goodix_i2c_read(ts->client, GOODIX_READ_COOR_ADDR, data, - GOODIX_CONTACT_SIZE + 1); - if (error) { - dev_err(&ts->client->dev, "I2C transfer error: %d\n", error); - return error; - } + /* + * The 'buffer status' bit, which indicates that the data is valid, is + * not set as soon as the interrupt is raised, but slightly after. + * This takes around 10 ms to happen, so we poll for 20 ms. + */ + max_timeout = jiffies + msecs_to_jiffies(GOODIX_BUFFER_STATUS_TIMEOUT); + do { + error = goodix_i2c_read(ts->client, GOODIX_READ_COOR_ADDR, + data, GOODIX_CONTACT_SIZE + 1); + if (error) { + dev_err(&ts->client->dev, "I2C transfer error: %d\n", + error); + return error; + } - if (!(data[0] & 0x80)) - return -EAGAIN; + if (data[0] & GOODIX_BUFFER_STATUS_READY) { + touch_num = data[0] & 0x0f; + if (touch_num > ts->max_touch_num) + return -EPROTO; + + if (touch_num > 1) { + data += 1 + GOODIX_CONTACT_SIZE; + error = goodix_i2c_read(ts->client, + GOODIX_READ_COOR_ADDR + + 1 + GOODIX_CONTACT_SIZE, + data, + GOODIX_CONTACT_SIZE * + (touch_num - 1)); + if (error) + return error; + } + + return touch_num; + } - touch_num = data[0] & 0x0f; - if (touch_num > ts->max_touch_num) - return -EPROTO; - - if (touch_num > 1) { - data += 1 + GOODIX_CONTACT_SIZE; - error = goodix_i2c_read(ts->client, - GOODIX_READ_COOR_ADDR + - 1 + GOODIX_CONTACT_SIZE, - data, - GOODIX_CONTACT_SIZE * (touch_num - 1)); - if (error) - return error; - } + usleep_range(1000, 2000); /* Poll every 1 - 2 ms */ + } while (time_before(jiffies, max_timeout)); - return touch_num; + /* + * The Goodix panel will send spurious interrupts after a + * 'finger up' event, which will always cause a timeout. + */ + return 0; } static void goodix_ts_report_touch(struct goodix_ts_data *ts, u8 *coor_data) diff --git a/drivers/input/touchscreen/stmfts.c b/drivers/input/touchscreen/stmfts.c index 157fdb4bb2e8..8c6c6178ec12 100644 --- a/drivers/input/touchscreen/stmfts.c +++ b/drivers/input/touchscreen/stmfts.c @@ -663,12 +663,10 @@ static int stmfts_probe(struct i2c_client *client, sdata->input->open = stmfts_input_open; sdata->input->close = stmfts_input_close; + input_set_capability(sdata->input, EV_ABS, ABS_MT_POSITION_X); + input_set_capability(sdata->input, EV_ABS, ABS_MT_POSITION_Y); touchscreen_parse_properties(sdata->input, true, &sdata->prop); - input_set_abs_params(sdata->input, ABS_MT_POSITION_X, 0, - sdata->prop.max_x, 0, 0); - input_set_abs_params(sdata->input, ABS_MT_POSITION_Y, 0, - sdata->prop.max_y, 0, 0); input_set_abs_params(sdata->input, ABS_MT_TOUCH_MAJOR, 0, 255, 0, 0); input_set_abs_params(sdata->input, ABS_MT_TOUCH_MINOR, 0, 255, 0, 0); input_set_abs_params(sdata->input, ABS_MT_ORIENTATION, 0, 255, 0, 0); diff --git a/drivers/input/touchscreen/ti_am335x_tsc.c b/drivers/input/touchscreen/ti_am335x_tsc.c index 7953381d939a..f1043ae71dcc 100644 --- a/drivers/input/touchscreen/ti_am335x_tsc.c +++ b/drivers/input/touchscreen/ti_am335x_tsc.c @@ -161,7 +161,7 @@ static void titsc_step_config(struct titsc *ts_dev) break; case 5: config |= ts_dev->bit_xp | STEPCONFIG_INP_AN4 | - ts_dev->bit_xn | ts_dev->bit_yp; + STEPCONFIG_XNP | STEPCONFIG_YPN; break; case 8: config |= ts_dev->bit_yp | STEPCONFIG_INP(ts_dev->inp_xp); diff --git a/drivers/iommu/amd_iommu.c b/drivers/iommu/amd_iommu.c index 51f8215877f5..8e8874d23717 100644 --- a/drivers/iommu/amd_iommu.c +++ b/drivers/iommu/amd_iommu.c @@ -2773,14 +2773,16 @@ int __init amd_iommu_init_api(void) int __init amd_iommu_init_dma_ops(void) { - swiotlb = iommu_pass_through ? 1 : 0; + swiotlb = (iommu_pass_through || sme_me_mask) ? 1 : 0; iommu_detected = 1; /* * In case we don't initialize SWIOTLB (actually the common case - * when AMD IOMMU is enabled), make sure there are global - * dma_ops set as a fall-back for devices not handled by this - * driver (for example non-PCI devices). + * when AMD IOMMU is enabled and SME is not active), make sure there + * are global dma_ops set as a fall-back for devices not handled by + * this driver (for example non-PCI devices). When SME is active, + * make sure that swiotlb variable remains set so the global dma_ops + * continue to be SWIOTLB. */ if (!swiotlb) dma_ops = &nommu_dma_ops; @@ -3046,6 +3048,7 @@ static size_t amd_iommu_unmap(struct iommu_domain *dom, unsigned long iova, mutex_unlock(&domain->api_lock); domain_flush_tlb_pde(domain); + domain_flush_complete(domain); return unmap_size; } diff --git a/drivers/iommu/exynos-iommu.c b/drivers/iommu/exynos-iommu.c index f596fcc32898..25c2c75f5332 100644 --- a/drivers/iommu/exynos-iommu.c +++ b/drivers/iommu/exynos-iommu.c @@ -709,7 +709,7 @@ static const struct dev_pm_ops sysmmu_pm_ops = { pm_runtime_force_resume) }; -static const struct of_device_id sysmmu_of_match[] __initconst = { +static const struct of_device_id sysmmu_of_match[] = { { .compatible = "samsung,exynos-sysmmu", }, { }, }; diff --git a/drivers/irqchip/irq-gic-v3-its.c b/drivers/irqchip/irq-gic-v3-its.c index e8d89343d613..e88395605e32 100644 --- a/drivers/irqchip/irq-gic-v3-its.c +++ b/drivers/irqchip/irq-gic-v3-its.c @@ -107,6 +107,10 @@ struct its_node { #define ITS_ITT_ALIGN SZ_256 +/* The maximum number of VPEID bits supported by VLPI commands */ +#define ITS_MAX_VPEID_BITS (16) +#define ITS_MAX_VPEID (1 << (ITS_MAX_VPEID_BITS)) + /* Convert page order to size in bytes */ #define PAGE_ORDER_TO_SIZE(o) (PAGE_SIZE << (o)) @@ -308,7 +312,7 @@ static void its_encode_size(struct its_cmd_block *cmd, u8 size) static void its_encode_itt(struct its_cmd_block *cmd, u64 itt_addr) { - its_mask_encode(&cmd->raw_cmd[2], itt_addr >> 8, 50, 8); + its_mask_encode(&cmd->raw_cmd[2], itt_addr >> 8, 51, 8); } static void its_encode_valid(struct its_cmd_block *cmd, int valid) @@ -318,7 +322,7 @@ static void its_encode_valid(struct its_cmd_block *cmd, int valid) static void its_encode_target(struct its_cmd_block *cmd, u64 target_addr) { - its_mask_encode(&cmd->raw_cmd[2], target_addr >> 16, 50, 16); + its_mask_encode(&cmd->raw_cmd[2], target_addr >> 16, 51, 16); } static void its_encode_collection(struct its_cmd_block *cmd, u16 col) @@ -358,7 +362,7 @@ static void its_encode_its_list(struct its_cmd_block *cmd, u16 its_list) static void its_encode_vpt_addr(struct its_cmd_block *cmd, u64 vpt_pa) { - its_mask_encode(&cmd->raw_cmd[3], vpt_pa >> 16, 50, 16); + its_mask_encode(&cmd->raw_cmd[3], vpt_pa >> 16, 51, 16); } static void its_encode_vpt_size(struct its_cmd_block *cmd, u8 vpt_size) @@ -1478,9 +1482,9 @@ static int its_setup_baser(struct its_node *its, struct its_baser *baser, u64 val = its_read_baser(its, baser); u64 esz = GITS_BASER_ENTRY_SIZE(val); u64 type = GITS_BASER_TYPE(val); + u64 baser_phys, tmp; u32 alloc_pages; void *base; - u64 tmp; retry_alloc_baser: alloc_pages = (PAGE_ORDER_TO_SIZE(order) / psz); @@ -1496,8 +1500,24 @@ retry_alloc_baser: if (!base) return -ENOMEM; + baser_phys = virt_to_phys(base); + + /* Check if the physical address of the memory is above 48bits */ + if (IS_ENABLED(CONFIG_ARM64_64K_PAGES) && (baser_phys >> 48)) { + + /* 52bit PA is supported only when PageSize=64K */ + if (psz != SZ_64K) { + pr_err("ITS: no 52bit PA support when psz=%d\n", psz); + free_pages((unsigned long)base, order); + return -ENXIO; + } + + /* Convert 52bit PA to 48bit field */ + baser_phys = GITS_BASER_PHYS_52_to_48(baser_phys); + } + retry_baser: - val = (virt_to_phys(base) | + val = (baser_phys | (type << GITS_BASER_TYPE_SHIFT) | ((esz - 1) << GITS_BASER_ENTRY_SIZE_SHIFT) | ((alloc_pages - 1) << GITS_BASER_PAGES_SHIFT) | @@ -1582,13 +1602,12 @@ retry_baser: static bool its_parse_indirect_baser(struct its_node *its, struct its_baser *baser, - u32 psz, u32 *order) + u32 psz, u32 *order, u32 ids) { u64 tmp = its_read_baser(its, baser); u64 type = GITS_BASER_TYPE(tmp); u64 esz = GITS_BASER_ENTRY_SIZE(tmp); u64 val = GITS_BASER_InnerShareable | GITS_BASER_RaWaWb; - u32 ids = its->device_ids; u32 new_order = *order; bool indirect = false; @@ -1680,9 +1699,13 @@ static int its_alloc_tables(struct its_node *its) continue; case GITS_BASER_TYPE_DEVICE: + indirect = its_parse_indirect_baser(its, baser, + psz, &order, + its->device_ids); case GITS_BASER_TYPE_VCPU: indirect = its_parse_indirect_baser(its, baser, - psz, &order); + psz, &order, + ITS_MAX_VPEID_BITS); break; } @@ -2551,7 +2574,7 @@ static struct irq_chip its_vpe_irq_chip = { static int its_vpe_id_alloc(void) { - return ida_simple_get(&its_vpeid_ida, 0, 1 << 16, GFP_KERNEL); + return ida_simple_get(&its_vpeid_ida, 0, ITS_MAX_VPEID, GFP_KERNEL); } static void its_vpe_id_free(u16 id) @@ -2851,7 +2874,7 @@ static int its_init_vpe_domain(void) return -ENOMEM; } - BUG_ON(entries != vpe_proxy.dev->nr_ites); + BUG_ON(entries > vpe_proxy.dev->nr_ites); raw_spin_lock_init(&vpe_proxy.lock); vpe_proxy.next_victim = 0; diff --git a/drivers/irqchip/irq-tango.c b/drivers/irqchip/irq-tango.c index bdbb5c0ff7fe..0c085303a583 100644 --- a/drivers/irqchip/irq-tango.c +++ b/drivers/irqchip/irq-tango.c @@ -141,7 +141,7 @@ static void __init tangox_irq_init_chip(struct irq_chip_generic *gc, for (i = 0; i < 2; i++) { ct[i].chip.irq_ack = irq_gc_ack_set_bit; ct[i].chip.irq_mask = irq_gc_mask_disable_reg; - ct[i].chip.irq_mask_ack = irq_gc_mask_disable_reg_and_ack; + ct[i].chip.irq_mask_ack = irq_gc_mask_disable_and_ack_set; ct[i].chip.irq_unmask = irq_gc_unmask_enable_reg; ct[i].chip.irq_set_type = tangox_irq_set_type; ct[i].chip.name = gc->domain->name; diff --git a/drivers/media/cec/cec-adap.c b/drivers/media/cec/cec-adap.c index eed6c397d840..f8a808d45034 100644 --- a/drivers/media/cec/cec-adap.c +++ b/drivers/media/cec/cec-adap.c @@ -1797,12 +1797,19 @@ static int cec_receive_notify(struct cec_adapter *adap, struct cec_msg *msg, */ switch (msg->msg[1]) { case CEC_MSG_GET_CEC_VERSION: - case CEC_MSG_GIVE_DEVICE_VENDOR_ID: case CEC_MSG_ABORT: case CEC_MSG_GIVE_DEVICE_POWER_STATUS: - case CEC_MSG_GIVE_PHYSICAL_ADDR: case CEC_MSG_GIVE_OSD_NAME: + /* + * These messages reply with a directed message, so ignore if + * the initiator is Unregistered. + */ + if (!adap->passthrough && from_unregistered) + return 0; + /* Fall through */ + case CEC_MSG_GIVE_DEVICE_VENDOR_ID: case CEC_MSG_GIVE_FEATURES: + case CEC_MSG_GIVE_PHYSICAL_ADDR: /* * Skip processing these messages if the passthrough mode * is on. @@ -1810,7 +1817,7 @@ static int cec_receive_notify(struct cec_adapter *adap, struct cec_msg *msg, if (adap->passthrough) goto skip_processing; /* Ignore if addressing is wrong */ - if (is_broadcast || from_unregistered) + if (is_broadcast) return 0; break; diff --git a/drivers/media/dvb-core/dvb_frontend.c b/drivers/media/dvb-core/dvb_frontend.c index 2fcba1616168..9139d01ba7ed 100644 --- a/drivers/media/dvb-core/dvb_frontend.c +++ b/drivers/media/dvb-core/dvb_frontend.c @@ -141,22 +141,39 @@ struct dvb_frontend_private { static void dvb_frontend_invoke_release(struct dvb_frontend *fe, void (*release)(struct dvb_frontend *fe)); -static void dvb_frontend_free(struct kref *ref) +static void __dvb_frontend_free(struct dvb_frontend *fe) { - struct dvb_frontend *fe = - container_of(ref, struct dvb_frontend, refcount); struct dvb_frontend_private *fepriv = fe->frontend_priv; + if (!fepriv) + return; + dvb_free_device(fepriv->dvbdev); dvb_frontend_invoke_release(fe, fe->ops.release); kfree(fepriv); + fe->frontend_priv = NULL; +} + +static void dvb_frontend_free(struct kref *ref) +{ + struct dvb_frontend *fe = + container_of(ref, struct dvb_frontend, refcount); + + __dvb_frontend_free(fe); } static void dvb_frontend_put(struct dvb_frontend *fe) { - kref_put(&fe->refcount, dvb_frontend_free); + /* + * Check if the frontend was registered, as otherwise + * kref was not initialized yet. + */ + if (fe->frontend_priv) + kref_put(&fe->refcount, dvb_frontend_free); + else + __dvb_frontend_free(fe); } static void dvb_frontend_get(struct dvb_frontend *fe) diff --git a/drivers/media/dvb-frontends/dib3000mc.c b/drivers/media/dvb-frontends/dib3000mc.c index 224283fe100a..4d086a7248e9 100644 --- a/drivers/media/dvb-frontends/dib3000mc.c +++ b/drivers/media/dvb-frontends/dib3000mc.c @@ -55,29 +55,57 @@ struct dib3000mc_state { static u16 dib3000mc_read_word(struct dib3000mc_state *state, u16 reg) { - u8 wb[2] = { (reg >> 8) | 0x80, reg & 0xff }; - u8 rb[2]; struct i2c_msg msg[2] = { - { .addr = state->i2c_addr >> 1, .flags = 0, .buf = wb, .len = 2 }, - { .addr = state->i2c_addr >> 1, .flags = I2C_M_RD, .buf = rb, .len = 2 }, + { .addr = state->i2c_addr >> 1, .flags = 0, .len = 2 }, + { .addr = state->i2c_addr >> 1, .flags = I2C_M_RD, .len = 2 }, }; + u16 word; + u8 *b; + + b = kmalloc(4, GFP_KERNEL); + if (!b) + return 0; + + b[0] = (reg >> 8) | 0x80; + b[1] = reg; + b[2] = 0; + b[3] = 0; + + msg[0].buf = b; + msg[1].buf = b + 2; if (i2c_transfer(state->i2c_adap, msg, 2) != 2) dprintk("i2c read error on %d\n",reg); - return (rb[0] << 8) | rb[1]; + word = (b[2] << 8) | b[3]; + kfree(b); + + return word; } static int dib3000mc_write_word(struct dib3000mc_state *state, u16 reg, u16 val) { - u8 b[4] = { - (reg >> 8) & 0xff, reg & 0xff, - (val >> 8) & 0xff, val & 0xff, - }; struct i2c_msg msg = { - .addr = state->i2c_addr >> 1, .flags = 0, .buf = b, .len = 4 + .addr = state->i2c_addr >> 1, .flags = 0, .len = 4 }; - return i2c_transfer(state->i2c_adap, &msg, 1) != 1 ? -EREMOTEIO : 0; + int rc; + u8 *b; + + b = kmalloc(4, GFP_KERNEL); + if (!b) + return -ENOMEM; + + b[0] = reg >> 8; + b[1] = reg; + b[2] = val >> 8; + b[3] = val; + + msg.buf = b; + + rc = i2c_transfer(state->i2c_adap, &msg, 1) != 1 ? -EREMOTEIO : 0; + kfree(b); + + return rc; } static int dib3000mc_identify(struct dib3000mc_state *state) diff --git a/drivers/media/dvb-frontends/dvb-pll.c b/drivers/media/dvb-frontends/dvb-pll.c index 7bec3e028bee..5553b89b804e 100644 --- a/drivers/media/dvb-frontends/dvb-pll.c +++ b/drivers/media/dvb-frontends/dvb-pll.c @@ -753,13 +753,19 @@ struct dvb_frontend *dvb_pll_attach(struct dvb_frontend *fe, int pll_addr, struct i2c_adapter *i2c, unsigned int pll_desc_id) { - u8 b1 [] = { 0 }; - struct i2c_msg msg = { .addr = pll_addr, .flags = I2C_M_RD, - .buf = b1, .len = 1 }; + u8 *b1; + struct i2c_msg msg = { .addr = pll_addr, .flags = I2C_M_RD, .len = 1 }; struct dvb_pll_priv *priv = NULL; int ret; const struct dvb_pll_desc *desc; + b1 = kmalloc(1, GFP_KERNEL); + if (!b1) + return NULL; + + b1[0] = 0; + msg.buf = b1; + if ((id[dvb_pll_devcount] > DVB_PLL_UNDEFINED) && (id[dvb_pll_devcount] < ARRAY_SIZE(pll_list))) pll_desc_id = id[dvb_pll_devcount]; @@ -773,15 +779,19 @@ struct dvb_frontend *dvb_pll_attach(struct dvb_frontend *fe, int pll_addr, fe->ops.i2c_gate_ctrl(fe, 1); ret = i2c_transfer (i2c, &msg, 1); - if (ret != 1) + if (ret != 1) { + kfree(b1); return NULL; + } if (fe->ops.i2c_gate_ctrl) fe->ops.i2c_gate_ctrl(fe, 0); } priv = kzalloc(sizeof(struct dvb_pll_priv), GFP_KERNEL); - if (priv == NULL) + if (!priv) { + kfree(b1); return NULL; + } priv->pll_i2c_address = pll_addr; priv->i2c = i2c; @@ -811,6 +821,8 @@ struct dvb_frontend *dvb_pll_attach(struct dvb_frontend *fe, int pll_addr, "insmod option" : "autodetected"); } + kfree(b1); + return fe; } EXPORT_SYMBOL(dvb_pll_attach); diff --git a/drivers/media/platform/Kconfig b/drivers/media/platform/Kconfig index 7e7cc49b8674..3c4f7fa7b9d8 100644 --- a/drivers/media/platform/Kconfig +++ b/drivers/media/platform/Kconfig @@ -112,7 +112,7 @@ config VIDEO_PXA27x config VIDEO_QCOM_CAMSS tristate "Qualcomm 8x16 V4L2 Camera Subsystem driver" - depends on VIDEO_V4L2 && VIDEO_V4L2_SUBDEV_API + depends on VIDEO_V4L2 && VIDEO_V4L2_SUBDEV_API && HAS_DMA depends on (ARCH_QCOM && IOMMU_DMA) || COMPILE_TEST select VIDEOBUF2_DMA_SG select V4L2_FWNODE diff --git a/drivers/media/platform/qcom/camss-8x16/camss-vfe.c b/drivers/media/platform/qcom/camss-8x16/camss-vfe.c index b21b3c2dc77f..b22d2dfcd3c2 100644 --- a/drivers/media/platform/qcom/camss-8x16/camss-vfe.c +++ b/drivers/media/platform/qcom/camss-8x16/camss-vfe.c @@ -2660,7 +2660,7 @@ static int vfe_get_selection(struct v4l2_subdev *sd, * * Return -EINVAL or zero on success */ -int vfe_set_selection(struct v4l2_subdev *sd, +static int vfe_set_selection(struct v4l2_subdev *sd, struct v4l2_subdev_pad_config *cfg, struct v4l2_subdev_selection *sel) { diff --git a/drivers/media/platform/qcom/venus/helpers.c b/drivers/media/platform/qcom/venus/helpers.c index 68933d208063..9b2a401a4891 100644 --- a/drivers/media/platform/qcom/venus/helpers.c +++ b/drivers/media/platform/qcom/venus/helpers.c @@ -682,6 +682,7 @@ void venus_helper_vb2_stop_streaming(struct vb2_queue *q) hfi_session_abort(inst); load_scale_clocks(core); + INIT_LIST_HEAD(&inst->registeredbufs); } venus_helper_buffers_done(inst, VB2_BUF_STATE_ERROR); diff --git a/drivers/media/platform/s5p-cec/exynos_hdmi_cecctrl.c b/drivers/media/platform/s5p-cec/exynos_hdmi_cecctrl.c index 1edf667d562a..146ae6f25cdb 100644 --- a/drivers/media/platform/s5p-cec/exynos_hdmi_cecctrl.c +++ b/drivers/media/platform/s5p-cec/exynos_hdmi_cecctrl.c @@ -172,7 +172,8 @@ u32 s5p_cec_get_status(struct s5p_cec_dev *cec) { u32 status = 0; - status = readb(cec->reg + S5P_CEC_STATUS_0); + status = readb(cec->reg + S5P_CEC_STATUS_0) & 0xf; + status |= (readb(cec->reg + S5P_CEC_TX_STAT1) & 0xf) << 4; status |= readb(cec->reg + S5P_CEC_STATUS_1) << 8; status |= readb(cec->reg + S5P_CEC_STATUS_2) << 16; status |= readb(cec->reg + S5P_CEC_STATUS_3) << 24; diff --git a/drivers/media/platform/s5p-cec/s5p_cec.c b/drivers/media/platform/s5p-cec/s5p_cec.c index 58d200e7c838..8837e2678bde 100644 --- a/drivers/media/platform/s5p-cec/s5p_cec.c +++ b/drivers/media/platform/s5p-cec/s5p_cec.c @@ -92,7 +92,10 @@ static irqreturn_t s5p_cec_irq_handler(int irq, void *priv) dev_dbg(cec->dev, "irq received\n"); if (status & CEC_STATUS_TX_DONE) { - if (status & CEC_STATUS_TX_ERROR) { + if (status & CEC_STATUS_TX_NACK) { + dev_dbg(cec->dev, "CEC_STATUS_TX_NACK set\n"); + cec->tx = STATE_NACK; + } else if (status & CEC_STATUS_TX_ERROR) { dev_dbg(cec->dev, "CEC_STATUS_TX_ERROR set\n"); cec->tx = STATE_ERROR; } else { @@ -135,6 +138,12 @@ static irqreturn_t s5p_cec_irq_handler_thread(int irq, void *priv) cec_transmit_done(cec->adap, CEC_TX_STATUS_OK, 0, 0, 0, 0); cec->tx = STATE_IDLE; break; + case STATE_NACK: + cec_transmit_done(cec->adap, + CEC_TX_STATUS_MAX_RETRIES | CEC_TX_STATUS_NACK, + 0, 1, 0, 0); + cec->tx = STATE_IDLE; + break; case STATE_ERROR: cec_transmit_done(cec->adap, CEC_TX_STATUS_MAX_RETRIES | CEC_TX_STATUS_ERROR, diff --git a/drivers/media/platform/s5p-cec/s5p_cec.h b/drivers/media/platform/s5p-cec/s5p_cec.h index 8bcd8dc1aeb9..86ded522ef27 100644 --- a/drivers/media/platform/s5p-cec/s5p_cec.h +++ b/drivers/media/platform/s5p-cec/s5p_cec.h @@ -35,6 +35,7 @@ #define CEC_STATUS_TX_TRANSFERRING (1 << 1) #define CEC_STATUS_TX_DONE (1 << 2) #define CEC_STATUS_TX_ERROR (1 << 3) +#define CEC_STATUS_TX_NACK (1 << 4) #define CEC_STATUS_TX_BYTES (0xFF << 8) #define CEC_STATUS_RX_RUNNING (1 << 16) #define CEC_STATUS_RX_RECEIVING (1 << 17) @@ -55,6 +56,7 @@ enum cec_state { STATE_IDLE, STATE_BUSY, STATE_DONE, + STATE_NACK, STATE_ERROR }; diff --git a/drivers/media/tuners/mt2060.c b/drivers/media/tuners/mt2060.c index 2e487f9a2cc3..4983eeb39f36 100644 --- a/drivers/media/tuners/mt2060.c +++ b/drivers/media/tuners/mt2060.c @@ -38,41 +38,74 @@ MODULE_PARM_DESC(debug, "Turn on/off debugging (default:off)."); static int mt2060_readreg(struct mt2060_priv *priv, u8 reg, u8 *val) { struct i2c_msg msg[2] = { - { .addr = priv->cfg->i2c_address, .flags = 0, .buf = ®, .len = 1 }, - { .addr = priv->cfg->i2c_address, .flags = I2C_M_RD, .buf = val, .len = 1 }, + { .addr = priv->cfg->i2c_address, .flags = 0, .len = 1 }, + { .addr = priv->cfg->i2c_address, .flags = I2C_M_RD, .len = 1 }, }; + int rc = 0; + u8 *b; + + b = kmalloc(2, GFP_KERNEL); + if (!b) + return -ENOMEM; + + b[0] = reg; + b[1] = 0; + + msg[0].buf = b; + msg[1].buf = b + 1; if (i2c_transfer(priv->i2c, msg, 2) != 2) { printk(KERN_WARNING "mt2060 I2C read failed\n"); - return -EREMOTEIO; + rc = -EREMOTEIO; } - return 0; + *val = b[1]; + kfree(b); + + return rc; } // Writes a single register static int mt2060_writereg(struct mt2060_priv *priv, u8 reg, u8 val) { - u8 buf[2] = { reg, val }; struct i2c_msg msg = { - .addr = priv->cfg->i2c_address, .flags = 0, .buf = buf, .len = 2 + .addr = priv->cfg->i2c_address, .flags = 0, .len = 2 }; + u8 *buf; + int rc = 0; + + buf = kmalloc(2, GFP_KERNEL); + if (!buf) + return -ENOMEM; + + buf[0] = reg; + buf[1] = val; + + msg.buf = buf; if (i2c_transfer(priv->i2c, &msg, 1) != 1) { printk(KERN_WARNING "mt2060 I2C write failed\n"); - return -EREMOTEIO; + rc = -EREMOTEIO; } - return 0; + kfree(buf); + return rc; } // Writes a set of consecutive registers static int mt2060_writeregs(struct mt2060_priv *priv,u8 *buf, u8 len) { int rem, val_len; - u8 xfer_buf[16]; + u8 *xfer_buf; + int rc = 0; struct i2c_msg msg = { - .addr = priv->cfg->i2c_address, .flags = 0, .buf = xfer_buf + .addr = priv->cfg->i2c_address, .flags = 0 }; + xfer_buf = kmalloc(16, GFP_KERNEL); + if (!xfer_buf) + return -ENOMEM; + + msg.buf = xfer_buf; + for (rem = len - 1; rem > 0; rem -= priv->i2c_max_regs) { val_len = min_t(int, rem, priv->i2c_max_regs); msg.len = 1 + val_len; @@ -81,11 +114,13 @@ static int mt2060_writeregs(struct mt2060_priv *priv,u8 *buf, u8 len) if (i2c_transfer(priv->i2c, &msg, 1) != 1) { printk(KERN_WARNING "mt2060 I2C write failed (len=%i)\n", val_len); - return -EREMOTEIO; + rc = -EREMOTEIO; + break; } } - return 0; + kfree(xfer_buf); + return rc; } // Initialisation sequences diff --git a/drivers/misc/mei/hw-me-regs.h b/drivers/misc/mei/hw-me-regs.h index c8307e8b4c16..0ccccbaf530d 100644 --- a/drivers/misc/mei/hw-me-regs.h +++ b/drivers/misc/mei/hw-me-regs.h @@ -127,6 +127,8 @@ #define MEI_DEV_ID_BXT_M 0x1A9A /* Broxton M */ #define MEI_DEV_ID_APL_I 0x5A9A /* Apollo Lake I */ +#define MEI_DEV_ID_GLK 0x319A /* Gemini Lake */ + #define MEI_DEV_ID_KBP 0xA2BA /* Kaby Point */ #define MEI_DEV_ID_KBP_2 0xA2BB /* Kaby Point 2 */ diff --git a/drivers/misc/mei/pci-me.c b/drivers/misc/mei/pci-me.c index 4ff40d319676..78b3172c8e6e 100644 --- a/drivers/misc/mei/pci-me.c +++ b/drivers/misc/mei/pci-me.c @@ -93,6 +93,8 @@ static const struct pci_device_id mei_me_pci_tbl[] = { {MEI_PCI_DEVICE(MEI_DEV_ID_BXT_M, MEI_ME_PCH8_CFG)}, {MEI_PCI_DEVICE(MEI_DEV_ID_APL_I, MEI_ME_PCH8_CFG)}, + {MEI_PCI_DEVICE(MEI_DEV_ID_GLK, MEI_ME_PCH8_CFG)}, + {MEI_PCI_DEVICE(MEI_DEV_ID_KBP, MEI_ME_PCH8_CFG)}, {MEI_PCI_DEVICE(MEI_DEV_ID_KBP_2, MEI_ME_PCH8_CFG)}, @@ -226,12 +228,15 @@ static int mei_me_probe(struct pci_dev *pdev, const struct pci_device_id *ent) pdev->dev_flags |= PCI_DEV_FLAGS_NEEDS_RESUME; /* - * For not wake-able HW runtime pm framework - * can't be used on pci device level. - * Use domain runtime pm callbacks instead. - */ - if (!pci_dev_run_wake(pdev)) - mei_me_set_pm_domain(dev); + * ME maps runtime suspend/resume to D0i states, + * hence we need to go around native PCI runtime service which + * eventually brings the device into D3cold/hot state, + * but the mei device cannot wake up from D3 unlike from D0i3. + * To get around the PCI device native runtime pm, + * ME uses runtime pm domain handlers which take precedence + * over the driver's pm handlers. + */ + mei_me_set_pm_domain(dev); if (mei_pg_is_enabled(dev)) pm_runtime_put_noidle(&pdev->dev); @@ -271,8 +276,7 @@ static void mei_me_shutdown(struct pci_dev *pdev) dev_dbg(&pdev->dev, "shutdown\n"); mei_stop(dev); - if (!pci_dev_run_wake(pdev)) - mei_me_unset_pm_domain(dev); + mei_me_unset_pm_domain(dev); mei_disable_interrupts(dev); free_irq(pdev->irq, dev); @@ -300,8 +304,7 @@ static void mei_me_remove(struct pci_dev *pdev) dev_dbg(&pdev->dev, "stop\n"); mei_stop(dev); - if (!pci_dev_run_wake(pdev)) - mei_me_unset_pm_domain(dev); + mei_me_unset_pm_domain(dev); mei_disable_interrupts(dev); diff --git a/drivers/misc/mei/pci-txe.c b/drivers/misc/mei/pci-txe.c index e38a5f144373..0566f9bfa7de 100644 --- a/drivers/misc/mei/pci-txe.c +++ b/drivers/misc/mei/pci-txe.c @@ -144,12 +144,14 @@ static int mei_txe_probe(struct pci_dev *pdev, const struct pci_device_id *ent) pdev->dev_flags |= PCI_DEV_FLAGS_NEEDS_RESUME; /* - * For not wake-able HW runtime pm framework - * can't be used on pci device level. - * Use domain runtime pm callbacks instead. - */ - if (!pci_dev_run_wake(pdev)) - mei_txe_set_pm_domain(dev); + * TXE maps runtime suspend/resume to own power gating states, + * hence we need to go around native PCI runtime service which + * eventually brings the device into D3cold/hot state. + * But the TXE device cannot wake up from D3 unlike from own + * power gating. To get around PCI device native runtime pm, + * TXE uses runtime pm domain handlers which take precedence. + */ + mei_txe_set_pm_domain(dev); pm_runtime_put_noidle(&pdev->dev); @@ -186,8 +188,7 @@ static void mei_txe_shutdown(struct pci_dev *pdev) dev_dbg(&pdev->dev, "shutdown\n"); mei_stop(dev); - if (!pci_dev_run_wake(pdev)) - mei_txe_unset_pm_domain(dev); + mei_txe_unset_pm_domain(dev); mei_disable_interrupts(dev); free_irq(pdev->irq, dev); @@ -215,8 +216,7 @@ static void mei_txe_remove(struct pci_dev *pdev) mei_stop(dev); - if (!pci_dev_run_wake(pdev)) - mei_txe_unset_pm_domain(dev); + mei_txe_unset_pm_domain(dev); mei_disable_interrupts(dev); free_irq(pdev->irq, dev); @@ -318,15 +318,7 @@ static int mei_txe_pm_runtime_suspend(struct device *device) else ret = -EAGAIN; - /* - * If everything is okay we're about to enter PCI low - * power state (D3) therefor we need to disable the - * interrupts towards host. - * However if device is not wakeable we do not enter - * D-low state and we need to keep the interrupt kicking - */ - if (!ret && pci_dev_run_wake(pdev)) - mei_disable_interrupts(dev); + /* keep irq on we are staying in D0 */ dev_dbg(&pdev->dev, "rpm: txe: runtime suspend ret=%d\n", ret); diff --git a/drivers/mmc/host/renesas_sdhi_internal_dmac.c b/drivers/mmc/host/renesas_sdhi_internal_dmac.c index f905f2361d12..8bae88a150fd 100644 --- a/drivers/mmc/host/renesas_sdhi_internal_dmac.c +++ b/drivers/mmc/host/renesas_sdhi_internal_dmac.c @@ -146,11 +146,8 @@ renesas_sdhi_internal_dmac_start_dma(struct tmio_mmc_host *host, WARN_ON(host->sg_len > 1); /* This DMAC cannot handle if buffer is not 8-bytes alignment */ - if (!IS_ALIGNED(sg->offset, 8)) { - host->force_pio = true; - renesas_sdhi_internal_dmac_enable_dma(host, false); - return; - } + if (!IS_ALIGNED(sg->offset, 8)) + goto force_pio; if (data->flags & MMC_DATA_READ) { dtran_mode |= DTRAN_MODE_CH_NUM_CH1; @@ -163,8 +160,8 @@ renesas_sdhi_internal_dmac_start_dma(struct tmio_mmc_host *host, } ret = dma_map_sg(&host->pdev->dev, sg, host->sg_len, dir); - if (ret < 0) - return; + if (ret == 0) + goto force_pio; renesas_sdhi_internal_dmac_enable_dma(host, true); @@ -176,6 +173,12 @@ renesas_sdhi_internal_dmac_start_dma(struct tmio_mmc_host *host, dtran_mode); renesas_sdhi_internal_dmac_dm_write(host, DM_DTRAN_ADDR, sg->dma_address); + + return; + +force_pio: + host->force_pio = true; + renesas_sdhi_internal_dmac_enable_dma(host, false); } static void renesas_sdhi_internal_dmac_issue_tasklet_fn(unsigned long arg) diff --git a/drivers/mmc/host/sdhci-pci-core.c b/drivers/mmc/host/sdhci-pci-core.c index d0ccc6729fd2..67d787fa3306 100644 --- a/drivers/mmc/host/sdhci-pci-core.c +++ b/drivers/mmc/host/sdhci-pci-core.c @@ -448,6 +448,8 @@ static void intel_dsm_init(struct intel_host *intel_host, struct device *dev, int err; u32 val; + intel_host->d3_retune = true; + err = __intel_dsm(intel_host, dev, INTEL_DSM_FNS, &intel_host->dsm_fns); if (err) { pr_debug("%s: DSM not supported, error %d\n", diff --git a/drivers/mmc/host/tmio_mmc_core.c b/drivers/mmc/host/tmio_mmc_core.c index a7293e186e03..9c4e6199b854 100644 --- a/drivers/mmc/host/tmio_mmc_core.c +++ b/drivers/mmc/host/tmio_mmc_core.c @@ -47,6 +47,7 @@ #include <linux/mmc/sdio.h> #include <linux/scatterlist.h> #include <linux/spinlock.h> +#include <linux/swiotlb.h> #include <linux/workqueue.h> #include "tmio_mmc.h" @@ -1215,6 +1216,18 @@ int tmio_mmc_host_probe(struct tmio_mmc_host *_host, mmc->max_blk_count = pdata->max_blk_count ? : (PAGE_SIZE / mmc->max_blk_size) * mmc->max_segs; mmc->max_req_size = mmc->max_blk_size * mmc->max_blk_count; + /* + * Since swiotlb has memory size limitation, this will calculate + * the maximum size locally (because we don't have any APIs for it now) + * and check the current max_req_size. And then, this will update + * the max_req_size if needed as a workaround. + */ + if (swiotlb_max_segment()) { + unsigned int max_size = (1 << IO_TLB_SHIFT) * IO_TLB_SEGSIZE; + + if (mmc->max_req_size > max_size) + mmc->max_req_size = max_size; + } mmc->max_seg_size = mmc->max_req_size; _host->native_hotplug = !(pdata->flags & TMIO_MMC_USE_GPIO_CD || diff --git a/drivers/net/can/flexcan.c b/drivers/net/can/flexcan.c index 13f0f219d8aa..a13a4896a8bd 100644 --- a/drivers/net/can/flexcan.c +++ b/drivers/net/can/flexcan.c @@ -182,22 +182,23 @@ /* FLEXCAN hardware feature flags * * Below is some version info we got: - * SOC Version IP-Version Glitch- [TR]WRN_INT Memory err RTR re- - * Filter? connected? detection ception in MB - * MX25 FlexCAN2 03.00.00.00 no no no no - * MX28 FlexCAN2 03.00.04.00 yes yes no no - * MX35 FlexCAN2 03.00.00.00 no no no no - * MX53 FlexCAN2 03.00.00.00 yes no no no - * MX6s FlexCAN3 10.00.12.00 yes yes no yes - * VF610 FlexCAN3 ? no yes yes yes? + * SOC Version IP-Version Glitch- [TR]WRN_INT IRQ Err Memory err RTR re- + * Filter? connected? Passive detection ception in MB + * MX25 FlexCAN2 03.00.00.00 no no ? no no + * MX28 FlexCAN2 03.00.04.00 yes yes no no no + * MX35 FlexCAN2 03.00.00.00 no no ? no no + * MX53 FlexCAN2 03.00.00.00 yes no no no no + * MX6s FlexCAN3 10.00.12.00 yes yes no no yes + * VF610 FlexCAN3 ? no yes ? yes yes? * * Some SOCs do not have the RX_WARN & TX_WARN interrupt line connected. */ -#define FLEXCAN_QUIRK_BROKEN_ERR_STATE BIT(1) /* [TR]WRN_INT not connected */ +#define FLEXCAN_QUIRK_BROKEN_WERR_STATE BIT(1) /* [TR]WRN_INT not connected */ #define FLEXCAN_QUIRK_DISABLE_RXFG BIT(2) /* Disable RX FIFO Global mask */ #define FLEXCAN_QUIRK_ENABLE_EACEN_RRS BIT(3) /* Enable EACEN and RRS bit in ctrl2 */ #define FLEXCAN_QUIRK_DISABLE_MECR BIT(4) /* Disable Memory error detection */ #define FLEXCAN_QUIRK_USE_OFF_TIMESTAMP BIT(5) /* Use timestamp based offloading */ +#define FLEXCAN_QUIRK_BROKEN_PERR_STATE BIT(6) /* No interrupt for error passive */ /* Structure of the message buffer */ struct flexcan_mb { @@ -281,14 +282,17 @@ struct flexcan_priv { }; static const struct flexcan_devtype_data fsl_p1010_devtype_data = { - .quirks = FLEXCAN_QUIRK_BROKEN_ERR_STATE, + .quirks = FLEXCAN_QUIRK_BROKEN_WERR_STATE | + FLEXCAN_QUIRK_BROKEN_PERR_STATE, }; -static const struct flexcan_devtype_data fsl_imx28_devtype_data; +static const struct flexcan_devtype_data fsl_imx28_devtype_data = { + .quirks = FLEXCAN_QUIRK_BROKEN_PERR_STATE, +}; static const struct flexcan_devtype_data fsl_imx6q_devtype_data = { .quirks = FLEXCAN_QUIRK_DISABLE_RXFG | FLEXCAN_QUIRK_ENABLE_EACEN_RRS | - FLEXCAN_QUIRK_USE_OFF_TIMESTAMP, + FLEXCAN_QUIRK_USE_OFF_TIMESTAMP | FLEXCAN_QUIRK_BROKEN_PERR_STATE, }; static const struct flexcan_devtype_data fsl_vf610_devtype_data = { @@ -335,6 +339,22 @@ static inline void flexcan_write(u32 val, void __iomem *addr) } #endif +static inline void flexcan_error_irq_enable(const struct flexcan_priv *priv) +{ + struct flexcan_regs __iomem *regs = priv->regs; + u32 reg_ctrl = (priv->reg_ctrl_default | FLEXCAN_CTRL_ERR_MSK); + + flexcan_write(reg_ctrl, ®s->ctrl); +} + +static inline void flexcan_error_irq_disable(const struct flexcan_priv *priv) +{ + struct flexcan_regs __iomem *regs = priv->regs; + u32 reg_ctrl = (priv->reg_ctrl_default & ~FLEXCAN_CTRL_ERR_MSK); + + flexcan_write(reg_ctrl, ®s->ctrl); +} + static inline int flexcan_transceiver_enable(const struct flexcan_priv *priv) { if (!priv->reg_xceiver) @@ -713,6 +733,7 @@ static irqreturn_t flexcan_irq(int irq, void *dev_id) struct flexcan_regs __iomem *regs = priv->regs; irqreturn_t handled = IRQ_NONE; u32 reg_iflag1, reg_esr; + enum can_state last_state = priv->can.state; reg_iflag1 = flexcan_read(®s->iflag1); @@ -765,8 +786,10 @@ static irqreturn_t flexcan_irq(int irq, void *dev_id) flexcan_write(reg_esr & FLEXCAN_ESR_ALL_INT, ®s->esr); } - /* state change interrupt */ - if (reg_esr & FLEXCAN_ESR_ERR_STATE) + /* state change interrupt or broken error state quirk fix is enabled */ + if ((reg_esr & FLEXCAN_ESR_ERR_STATE) || + (priv->devtype_data->quirks & (FLEXCAN_QUIRK_BROKEN_WERR_STATE | + FLEXCAN_QUIRK_BROKEN_PERR_STATE))) flexcan_irq_state(dev, reg_esr); /* bus error IRQ - handle if bus error reporting is activated */ @@ -774,6 +797,44 @@ static irqreturn_t flexcan_irq(int irq, void *dev_id) (priv->can.ctrlmode & CAN_CTRLMODE_BERR_REPORTING)) flexcan_irq_bus_err(dev, reg_esr); + /* availability of error interrupt among state transitions in case + * bus error reporting is de-activated and + * FLEXCAN_QUIRK_BROKEN_PERR_STATE is enabled: + * +--------------------------------------------------------------+ + * | +----------------------------------------------+ [stopped / | + * | | | sleeping] -+ + * +-+-> active <-> warning <-> passive -> bus off -+ + * ___________^^^^^^^^^^^^_______________________________ + * disabled(1) enabled disabled + * + * (1): enabled if FLEXCAN_QUIRK_BROKEN_WERR_STATE is enabled + */ + if ((last_state != priv->can.state) && + (priv->devtype_data->quirks & FLEXCAN_QUIRK_BROKEN_PERR_STATE) && + !(priv->can.ctrlmode & CAN_CTRLMODE_BERR_REPORTING)) { + switch (priv->can.state) { + case CAN_STATE_ERROR_ACTIVE: + if (priv->devtype_data->quirks & + FLEXCAN_QUIRK_BROKEN_WERR_STATE) + flexcan_error_irq_enable(priv); + else + flexcan_error_irq_disable(priv); + break; + + case CAN_STATE_ERROR_WARNING: + flexcan_error_irq_enable(priv); + break; + + case CAN_STATE_ERROR_PASSIVE: + case CAN_STATE_BUS_OFF: + flexcan_error_irq_disable(priv); + break; + + default: + break; + } + } + return handled; } @@ -887,7 +948,7 @@ static int flexcan_chip_start(struct net_device *dev) * on most Flexcan cores, too. Otherwise we don't get * any error warning or passive interrupts. */ - if (priv->devtype_data->quirks & FLEXCAN_QUIRK_BROKEN_ERR_STATE || + if (priv->devtype_data->quirks & FLEXCAN_QUIRK_BROKEN_WERR_STATE || priv->can.ctrlmode & CAN_CTRLMODE_BERR_REPORTING) reg_ctrl |= FLEXCAN_CTRL_ERR_MSK; else diff --git a/drivers/net/can/sun4i_can.c b/drivers/net/can/sun4i_can.c index 68ef0a4cd821..b0c80859f746 100644 --- a/drivers/net/can/sun4i_can.c +++ b/drivers/net/can/sun4i_can.c @@ -342,7 +342,7 @@ static int sun4i_can_start(struct net_device *dev) /* enter the selected mode */ mod_reg_val = readl(priv->base + SUN4I_REG_MSEL_ADDR); - if (priv->can.ctrlmode & CAN_CTRLMODE_PRESUME_ACK) + if (priv->can.ctrlmode & CAN_CTRLMODE_LOOPBACK) mod_reg_val |= SUN4I_MSEL_LOOPBACK_MODE; else if (priv->can.ctrlmode & CAN_CTRLMODE_LISTENONLY) mod_reg_val |= SUN4I_MSEL_LISTEN_ONLY_MODE; @@ -811,7 +811,6 @@ static int sun4ican_probe(struct platform_device *pdev) priv->can.ctrlmode_supported = CAN_CTRLMODE_BERR_REPORTING | CAN_CTRLMODE_LISTENONLY | CAN_CTRLMODE_LOOPBACK | - CAN_CTRLMODE_PRESUME_ACK | CAN_CTRLMODE_3_SAMPLES; priv->base = addr; priv->clk = clk; diff --git a/drivers/net/can/usb/esd_usb2.c b/drivers/net/can/usb/esd_usb2.c index be928ce62d32..9fdb0f0bfa06 100644 --- a/drivers/net/can/usb/esd_usb2.c +++ b/drivers/net/can/usb/esd_usb2.c @@ -333,7 +333,7 @@ static void esd_usb2_rx_can_msg(struct esd_usb2_net_priv *priv, } cf->can_id = id & ESD_IDMASK; - cf->can_dlc = get_can_dlc(msg->msg.rx.dlc); + cf->can_dlc = get_can_dlc(msg->msg.rx.dlc & ~ESD_RTR); if (id & ESD_EXTID) cf->can_id |= CAN_EFF_FLAG; diff --git a/drivers/net/can/usb/gs_usb.c b/drivers/net/can/usb/gs_usb.c index afcc1312dbaf..68ac3e88a8ce 100644 --- a/drivers/net/can/usb/gs_usb.c +++ b/drivers/net/can/usb/gs_usb.c @@ -375,6 +375,8 @@ static void gs_usb_receive_bulk_callback(struct urb *urb) gs_free_tx_context(txc); + atomic_dec(&dev->active_tx_urbs); + netif_wake_queue(netdev); } @@ -463,14 +465,6 @@ static void gs_usb_xmit_callback(struct urb *urb) urb->transfer_buffer_length, urb->transfer_buffer, urb->transfer_dma); - - atomic_dec(&dev->active_tx_urbs); - - if (!netif_device_present(netdev)) - return; - - if (netif_queue_stopped(netdev)) - netif_wake_queue(netdev); } static netdev_tx_t gs_can_start_xmit(struct sk_buff *skb, diff --git a/drivers/net/can/usb/kvaser_usb.c b/drivers/net/can/usb/kvaser_usb.c index 18cc529fb807..9b18d96ef526 100644 --- a/drivers/net/can/usb/kvaser_usb.c +++ b/drivers/net/can/usb/kvaser_usb.c @@ -137,6 +137,7 @@ static inline bool kvaser_is_usbcan(const struct usb_device_id *id) #define CMD_RESET_ERROR_COUNTER 49 #define CMD_TX_ACKNOWLEDGE 50 #define CMD_CAN_ERROR_EVENT 51 +#define CMD_FLUSH_QUEUE_REPLY 68 #define CMD_LEAF_USB_THROTTLE 77 #define CMD_LEAF_LOG_MESSAGE 106 @@ -1301,6 +1302,11 @@ static void kvaser_usb_handle_message(const struct kvaser_usb *dev, goto warn; break; + case CMD_FLUSH_QUEUE_REPLY: + if (dev->family != KVASER_LEAF) + goto warn; + break; + default: warn: dev_warn(dev->udev->dev.parent, "Unhandled message (%d)\n", msg->id); @@ -1609,7 +1615,8 @@ static int kvaser_usb_close(struct net_device *netdev) if (err) netdev_warn(netdev, "Cannot flush queue, error %d\n", err); - if (kvaser_usb_send_simple_msg(dev, CMD_RESET_CHIP, priv->channel)) + err = kvaser_usb_send_simple_msg(dev, CMD_RESET_CHIP, priv->channel); + if (err) netdev_warn(netdev, "Cannot reset card, error %d\n", err); err = kvaser_usb_stop_chip(priv); diff --git a/drivers/net/ethernet/amazon/ena/ena_ethtool.c b/drivers/net/ethernet/amazon/ena/ena_ethtool.c index b1212debc2e1..967020fb26ee 100644 --- a/drivers/net/ethernet/amazon/ena/ena_ethtool.c +++ b/drivers/net/ethernet/amazon/ena/ena_ethtool.c @@ -742,8 +742,8 @@ static void ena_get_channels(struct net_device *netdev, { struct ena_adapter *adapter = netdev_priv(netdev); - channels->max_rx = ENA_MAX_NUM_IO_QUEUES; - channels->max_tx = ENA_MAX_NUM_IO_QUEUES; + channels->max_rx = adapter->num_queues; + channels->max_tx = adapter->num_queues; channels->max_other = 0; channels->max_combined = 0; channels->rx_count = adapter->num_queues; diff --git a/drivers/net/ethernet/amazon/ena/ena_netdev.c b/drivers/net/ethernet/amazon/ena/ena_netdev.c index f7dc22f65d9f..c6bd5e24005d 100644 --- a/drivers/net/ethernet/amazon/ena/ena_netdev.c +++ b/drivers/net/ethernet/amazon/ena/ena_netdev.c @@ -966,7 +966,7 @@ static inline void ena_rx_checksum(struct ena_ring *rx_ring, u64_stats_update_begin(&rx_ring->syncp); rx_ring->rx_stats.bad_csum++; u64_stats_update_end(&rx_ring->syncp); - netif_err(rx_ring->adapter, rx_err, rx_ring->netdev, + netif_dbg(rx_ring->adapter, rx_err, rx_ring->netdev, "RX IPv4 header checksum error\n"); return; } @@ -979,7 +979,7 @@ static inline void ena_rx_checksum(struct ena_ring *rx_ring, u64_stats_update_begin(&rx_ring->syncp); rx_ring->rx_stats.bad_csum++; u64_stats_update_end(&rx_ring->syncp); - netif_err(rx_ring->adapter, rx_err, rx_ring->netdev, + netif_dbg(rx_ring->adapter, rx_err, rx_ring->netdev, "RX L4 checksum error\n"); skb->ip_summed = CHECKSUM_NONE; return; @@ -3064,7 +3064,8 @@ static void ena_release_bars(struct ena_com_dev *ena_dev, struct pci_dev *pdev) if (ena_dev->mem_bar) devm_iounmap(&pdev->dev, ena_dev->mem_bar); - devm_iounmap(&pdev->dev, ena_dev->reg_bar); + if (ena_dev->reg_bar) + devm_iounmap(&pdev->dev, ena_dev->reg_bar); release_bars = pci_select_bars(pdev, IORESOURCE_MEM) & ENA_BAR_MASK; pci_release_selected_regions(pdev, release_bars); diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_cfg.h b/drivers/net/ethernet/aquantia/atlantic/aq_cfg.h index 0fdaaa643073..57e796870595 100644 --- a/drivers/net/ethernet/aquantia/atlantic/aq_cfg.h +++ b/drivers/net/ethernet/aquantia/atlantic/aq_cfg.h @@ -22,8 +22,12 @@ #define AQ_CFG_FORCE_LEGACY_INT 0U -#define AQ_CFG_IS_INTERRUPT_MODERATION_DEF 1U -#define AQ_CFG_INTERRUPT_MODERATION_RATE_DEF 0xFFFFU +#define AQ_CFG_INTERRUPT_MODERATION_OFF 0 +#define AQ_CFG_INTERRUPT_MODERATION_ON 1 +#define AQ_CFG_INTERRUPT_MODERATION_AUTO 0xFFFFU + +#define AQ_CFG_INTERRUPT_MODERATION_USEC_MAX (0x1FF * 2) + #define AQ_CFG_IRQ_MASK 0x1FFU #define AQ_CFG_VECS_MAX 8U diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_ethtool.c b/drivers/net/ethernet/aquantia/atlantic/aq_ethtool.c index a761e91471df..d5e99b468870 100644 --- a/drivers/net/ethernet/aquantia/atlantic/aq_ethtool.c +++ b/drivers/net/ethernet/aquantia/atlantic/aq_ethtool.c @@ -56,10 +56,6 @@ aq_ethtool_set_link_ksettings(struct net_device *ndev, return aq_nic_set_link_ksettings(aq_nic, cmd); } -/* there "5U" is number of queue[#] stats lines (InPackets+...+InErrors) */ -static const unsigned int aq_ethtool_stat_queue_lines = 5U; -static const unsigned int aq_ethtool_stat_queue_chars = - 5U * ETH_GSTRING_LEN; static const char aq_ethtool_stat_names[][ETH_GSTRING_LEN] = { "InPackets", "InUCast", @@ -83,56 +79,26 @@ static const char aq_ethtool_stat_names[][ETH_GSTRING_LEN] = { "InOctetsDma", "OutOctetsDma", "InDroppedDma", - "Queue[0] InPackets", - "Queue[0] OutPackets", - "Queue[0] InJumboPackets", - "Queue[0] InLroPackets", - "Queue[0] InErrors", - "Queue[1] InPackets", - "Queue[1] OutPackets", - "Queue[1] InJumboPackets", - "Queue[1] InLroPackets", - "Queue[1] InErrors", - "Queue[2] InPackets", - "Queue[2] OutPackets", - "Queue[2] InJumboPackets", - "Queue[2] InLroPackets", - "Queue[2] InErrors", - "Queue[3] InPackets", - "Queue[3] OutPackets", - "Queue[3] InJumboPackets", - "Queue[3] InLroPackets", - "Queue[3] InErrors", - "Queue[4] InPackets", - "Queue[4] OutPackets", - "Queue[4] InJumboPackets", - "Queue[4] InLroPackets", - "Queue[4] InErrors", - "Queue[5] InPackets", - "Queue[5] OutPackets", - "Queue[5] InJumboPackets", - "Queue[5] InLroPackets", - "Queue[5] InErrors", - "Queue[6] InPackets", - "Queue[6] OutPackets", - "Queue[6] InJumboPackets", - "Queue[6] InLroPackets", - "Queue[6] InErrors", - "Queue[7] InPackets", - "Queue[7] OutPackets", - "Queue[7] InJumboPackets", - "Queue[7] InLroPackets", - "Queue[7] InErrors", +}; + +static const char aq_ethtool_queue_stat_names[][ETH_GSTRING_LEN] = { + "Queue[%d] InPackets", + "Queue[%d] OutPackets", + "Queue[%d] Restarts", + "Queue[%d] InJumboPackets", + "Queue[%d] InLroPackets", + "Queue[%d] InErrors", }; static void aq_ethtool_stats(struct net_device *ndev, struct ethtool_stats *stats, u64 *data) { struct aq_nic_s *aq_nic = netdev_priv(ndev); + struct aq_nic_cfg_s *cfg = aq_nic_get_cfg(aq_nic); -/* ASSERT: Need add lines to aq_ethtool_stat_names if AQ_CFG_VECS_MAX > 8 */ - BUILD_BUG_ON(AQ_CFG_VECS_MAX > 8); - memset(data, 0, ARRAY_SIZE(aq_ethtool_stat_names) * sizeof(u64)); + memset(data, 0, (ARRAY_SIZE(aq_ethtool_stat_names) + + ARRAY_SIZE(aq_ethtool_queue_stat_names) * + cfg->vecs) * sizeof(u64)); aq_nic_get_stats(aq_nic, data); } @@ -154,8 +120,8 @@ static void aq_ethtool_get_drvinfo(struct net_device *ndev, strlcpy(drvinfo->bus_info, pdev ? pci_name(pdev) : "", sizeof(drvinfo->bus_info)); - drvinfo->n_stats = ARRAY_SIZE(aq_ethtool_stat_names) - - (AQ_CFG_VECS_MAX - cfg->vecs) * aq_ethtool_stat_queue_lines; + drvinfo->n_stats = ARRAY_SIZE(aq_ethtool_stat_names) + + cfg->vecs * ARRAY_SIZE(aq_ethtool_queue_stat_names); drvinfo->testinfo_len = 0; drvinfo->regdump_len = regs_count; drvinfo->eedump_len = 0; @@ -164,14 +130,25 @@ static void aq_ethtool_get_drvinfo(struct net_device *ndev, static void aq_ethtool_get_strings(struct net_device *ndev, u32 stringset, u8 *data) { + int i, si; struct aq_nic_s *aq_nic = netdev_priv(ndev); struct aq_nic_cfg_s *cfg = aq_nic_get_cfg(aq_nic); - - if (stringset == ETH_SS_STATS) - memcpy(data, *aq_ethtool_stat_names, - sizeof(aq_ethtool_stat_names) - - (AQ_CFG_VECS_MAX - cfg->vecs) * - aq_ethtool_stat_queue_chars); + u8 *p = data; + + if (stringset == ETH_SS_STATS) { + memcpy(p, *aq_ethtool_stat_names, + sizeof(aq_ethtool_stat_names)); + p = p + sizeof(aq_ethtool_stat_names); + for (i = 0; i < cfg->vecs; i++) { + for (si = 0; + si < ARRAY_SIZE(aq_ethtool_queue_stat_names); + si++) { + snprintf(p, ETH_GSTRING_LEN, + aq_ethtool_queue_stat_names[si], i); + p += ETH_GSTRING_LEN; + } + } + } } static int aq_ethtool_get_sset_count(struct net_device *ndev, int stringset) @@ -182,9 +159,8 @@ static int aq_ethtool_get_sset_count(struct net_device *ndev, int stringset) switch (stringset) { case ETH_SS_STATS: - ret = ARRAY_SIZE(aq_ethtool_stat_names) - - (AQ_CFG_VECS_MAX - cfg->vecs) * - aq_ethtool_stat_queue_lines; + ret = ARRAY_SIZE(aq_ethtool_stat_names) + + cfg->vecs * ARRAY_SIZE(aq_ethtool_queue_stat_names); break; default: ret = -EOPNOTSUPP; @@ -245,6 +221,69 @@ static int aq_ethtool_get_rxnfc(struct net_device *ndev, return err; } +int aq_ethtool_get_coalesce(struct net_device *ndev, + struct ethtool_coalesce *coal) +{ + struct aq_nic_s *aq_nic = netdev_priv(ndev); + struct aq_nic_cfg_s *cfg = aq_nic_get_cfg(aq_nic); + + if (cfg->itr == AQ_CFG_INTERRUPT_MODERATION_ON || + cfg->itr == AQ_CFG_INTERRUPT_MODERATION_AUTO) { + coal->rx_coalesce_usecs = cfg->rx_itr; + coal->tx_coalesce_usecs = cfg->tx_itr; + coal->rx_max_coalesced_frames = 0; + coal->tx_max_coalesced_frames = 0; + } else { + coal->rx_coalesce_usecs = 0; + coal->tx_coalesce_usecs = 0; + coal->rx_max_coalesced_frames = 1; + coal->tx_max_coalesced_frames = 1; + } + return 0; +} + +int aq_ethtool_set_coalesce(struct net_device *ndev, + struct ethtool_coalesce *coal) +{ + struct aq_nic_s *aq_nic = netdev_priv(ndev); + struct aq_nic_cfg_s *cfg = aq_nic_get_cfg(aq_nic); + + /* This is not yet supported + */ + if (coal->use_adaptive_rx_coalesce || coal->use_adaptive_tx_coalesce) + return -EOPNOTSUPP; + + /* Atlantic only supports timing based coalescing + */ + if (coal->rx_max_coalesced_frames > 1 || + coal->rx_coalesce_usecs_irq || + coal->rx_max_coalesced_frames_irq) + return -EOPNOTSUPP; + + if (coal->tx_max_coalesced_frames > 1 || + coal->tx_coalesce_usecs_irq || + coal->tx_max_coalesced_frames_irq) + return -EOPNOTSUPP; + + /* We do not support frame counting. Check this + */ + if (!(coal->rx_max_coalesced_frames == !coal->rx_coalesce_usecs)) + return -EOPNOTSUPP; + if (!(coal->tx_max_coalesced_frames == !coal->tx_coalesce_usecs)) + return -EOPNOTSUPP; + + if (coal->rx_coalesce_usecs > AQ_CFG_INTERRUPT_MODERATION_USEC_MAX || + coal->tx_coalesce_usecs > AQ_CFG_INTERRUPT_MODERATION_USEC_MAX) + return -EINVAL; + + cfg->itr = AQ_CFG_INTERRUPT_MODERATION_ON; + + cfg->rx_itr = coal->rx_coalesce_usecs; + cfg->tx_itr = coal->tx_coalesce_usecs; + + return aq_nic_update_interrupt_moderation_settings(aq_nic); +} + const struct ethtool_ops aq_ethtool_ops = { .get_link = aq_ethtool_get_link, .get_regs_len = aq_ethtool_get_regs_len, @@ -259,4 +298,6 @@ const struct ethtool_ops aq_ethtool_ops = { .get_ethtool_stats = aq_ethtool_stats, .get_link_ksettings = aq_ethtool_get_link_ksettings, .set_link_ksettings = aq_ethtool_set_link_ksettings, + .get_coalesce = aq_ethtool_get_coalesce, + .set_coalesce = aq_ethtool_set_coalesce, }; diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_hw.h b/drivers/net/ethernet/aquantia/atlantic/aq_hw.h index bf9b3f020e10..0207927dc8a6 100644 --- a/drivers/net/ethernet/aquantia/atlantic/aq_hw.h +++ b/drivers/net/ethernet/aquantia/atlantic/aq_hw.h @@ -151,8 +151,7 @@ struct aq_hw_ops { [ETH_ALEN], u32 count); - int (*hw_interrupt_moderation_set)(struct aq_hw_s *self, - bool itr_enabled); + int (*hw_interrupt_moderation_set)(struct aq_hw_s *self); int (*hw_rss_set)(struct aq_hw_s *self, struct aq_rss_parameters *rss_params); @@ -163,6 +162,8 @@ struct aq_hw_ops { int (*hw_get_regs)(struct aq_hw_s *self, struct aq_hw_caps_s *aq_hw_caps, u32 *regs_buff); + int (*hw_update_stats)(struct aq_hw_s *self); + int (*hw_get_hw_stats)(struct aq_hw_s *self, u64 *data, unsigned int *p_count); diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_nic.c b/drivers/net/ethernet/aquantia/atlantic/aq_nic.c index 0a5bb4114eb4..483e97691eea 100644 --- a/drivers/net/ethernet/aquantia/atlantic/aq_nic.c +++ b/drivers/net/ethernet/aquantia/atlantic/aq_nic.c @@ -16,6 +16,7 @@ #include "aq_pci_func.h" #include "aq_nic_internal.h" +#include <linux/moduleparam.h> #include <linux/netdevice.h> #include <linux/etherdevice.h> #include <linux/timer.h> @@ -24,6 +25,18 @@ #include <linux/tcp.h> #include <net/ip.h> +static unsigned int aq_itr = AQ_CFG_INTERRUPT_MODERATION_AUTO; +module_param_named(aq_itr, aq_itr, uint, 0644); +MODULE_PARM_DESC(aq_itr, "Interrupt throttling mode"); + +static unsigned int aq_itr_tx; +module_param_named(aq_itr_tx, aq_itr_tx, uint, 0644); +MODULE_PARM_DESC(aq_itr_tx, "TX interrupt throttle rate"); + +static unsigned int aq_itr_rx; +module_param_named(aq_itr_rx, aq_itr_rx, uint, 0644); +MODULE_PARM_DESC(aq_itr_rx, "RX interrupt throttle rate"); + static void aq_nic_rss_init(struct aq_nic_s *self, unsigned int num_rss_queues) { struct aq_nic_cfg_s *cfg = &self->aq_nic_cfg; @@ -61,9 +74,9 @@ static void aq_nic_cfg_init_defaults(struct aq_nic_s *self) cfg->is_polling = AQ_CFG_IS_POLLING_DEF; - cfg->is_interrupt_moderation = AQ_CFG_IS_INTERRUPT_MODERATION_DEF; - cfg->itr = cfg->is_interrupt_moderation ? - AQ_CFG_INTERRUPT_MODERATION_RATE_DEF : 0U; + cfg->itr = aq_itr; + cfg->tx_itr = aq_itr_tx; + cfg->rx_itr = aq_itr_rx; cfg->is_rss = AQ_CFG_IS_RSS_DEF; cfg->num_rss_queues = AQ_CFG_NUM_RSS_QUEUES_DEF; @@ -126,10 +139,12 @@ static int aq_nic_update_link_status(struct aq_nic_s *self) if (err) return err; - if (self->link_status.mbps != self->aq_hw->aq_link_status.mbps) + if (self->link_status.mbps != self->aq_hw->aq_link_status.mbps) { pr_info("%s: link change old %d new %d\n", AQ_CFG_DRV_NAME, self->link_status.mbps, self->aq_hw->aq_link_status.mbps); + aq_nic_update_interrupt_moderation_settings(self); + } self->link_status = self->aq_hw->aq_link_status; if (!netif_carrier_ok(self->ndev) && self->link_status.mbps) { @@ -164,8 +179,8 @@ static void aq_nic_service_timer_cb(unsigned long param) if (err) goto err_exit; - self->aq_hw_ops.hw_interrupt_moderation_set(self->aq_hw, - self->aq_nic_cfg.is_interrupt_moderation); + if (self->aq_hw_ops.hw_update_stats) + self->aq_hw_ops.hw_update_stats(self->aq_hw); memset(&stats_rx, 0U, sizeof(struct aq_ring_stats_rx_s)); memset(&stats_tx, 0U, sizeof(struct aq_ring_stats_tx_s)); @@ -334,6 +349,7 @@ struct aq_nic_s *aq_nic_alloc_hot(struct net_device *ndev) } if (netif_running(ndev)) netif_tx_disable(ndev); + netif_carrier_off(self->ndev); for (self->aq_vecs = 0; self->aq_vecs < self->aq_nic_cfg.vecs; self->aq_vecs++) { @@ -421,9 +437,8 @@ int aq_nic_start(struct aq_nic_s *self) if (err < 0) goto err_exit; - err = self->aq_hw_ops.hw_interrupt_moderation_set(self->aq_hw, - self->aq_nic_cfg.is_interrupt_moderation); - if (err < 0) + err = aq_nic_update_interrupt_moderation_settings(self); + if (err) goto err_exit; setup_timer(&self->service_timer, &aq_nic_service_timer_cb, (unsigned long)self); @@ -645,6 +660,11 @@ err_exit: return err; } +int aq_nic_update_interrupt_moderation_settings(struct aq_nic_s *self) +{ + return self->aq_hw_ops.hw_interrupt_moderation_set(self->aq_hw); +} + int aq_nic_set_packet_filter(struct aq_nic_s *self, unsigned int flags) { int err = 0; @@ -899,6 +919,7 @@ int aq_nic_stop(struct aq_nic_s *self) unsigned int i = 0U; netif_tx_disable(self->ndev); + netif_carrier_off(self->ndev); del_timer_sync(&self->service_timer); diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_nic.h b/drivers/net/ethernet/aquantia/atlantic/aq_nic.h index 0ddd556ff901..4309983acdd6 100644 --- a/drivers/net/ethernet/aquantia/atlantic/aq_nic.h +++ b/drivers/net/ethernet/aquantia/atlantic/aq_nic.h @@ -40,6 +40,8 @@ struct aq_nic_cfg_s { u32 vecs; /* vecs==allocated irqs */ u32 irq_type; u32 itr; + u16 rx_itr; + u16 tx_itr; u32 num_rss_queues; u32 mtu; u32 ucp_0x364; @@ -49,7 +51,6 @@ struct aq_nic_cfg_s { u16 is_mc_list_enabled; u16 mc_list_count; bool is_autoneg; - bool is_interrupt_moderation; bool is_polling; bool is_rss; bool is_lro; @@ -104,5 +105,6 @@ int aq_nic_set_link_ksettings(struct aq_nic_s *self, struct aq_nic_cfg_s *aq_nic_get_cfg(struct aq_nic_s *self); u32 aq_nic_get_fw_version(struct aq_nic_s *self); int aq_nic_change_pm_state(struct aq_nic_s *self, pm_message_t *pm_msg); +int aq_nic_update_interrupt_moderation_settings(struct aq_nic_s *self); #endif /* AQ_NIC_H */ diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_pci_func.c b/drivers/net/ethernet/aquantia/atlantic/aq_pci_func.c index 4c6c882c6a1c..cadaa646c89f 100644 --- a/drivers/net/ethernet/aquantia/atlantic/aq_pci_func.c +++ b/drivers/net/ethernet/aquantia/atlantic/aq_pci_func.c @@ -85,6 +85,7 @@ int aq_pci_func_init(struct aq_pci_func_s *self) int err = 0; unsigned int bar = 0U; unsigned int port = 0U; + unsigned int numvecs = 0U; err = pci_enable_device(self->pdev); if (err < 0) @@ -142,10 +143,12 @@ int aq_pci_func_init(struct aq_pci_func_s *self) } } - /*enable interrupts */ + numvecs = min((u8)AQ_CFG_VECS_DEF, self->aq_hw_caps.msix_irqs); + numvecs = min(numvecs, num_online_cpus()); + + /* enable interrupts */ #if !AQ_CFG_FORCE_LEGACY_INT - err = pci_alloc_irq_vectors(self->pdev, self->aq_hw_caps.msix_irqs, - self->aq_hw_caps.msix_irqs, PCI_IRQ_MSIX); + err = pci_alloc_irq_vectors(self->pdev, numvecs, numvecs, PCI_IRQ_MSIX); if (err < 0) { err = pci_alloc_irq_vectors(self->pdev, 1, 1, @@ -153,7 +156,7 @@ int aq_pci_func_init(struct aq_pci_func_s *self) if (err < 0) goto err_exit; } -#endif +#endif /* AQ_CFG_FORCE_LEGACY_INT */ /* net device init */ for (port = 0; port < self->ports; ++port) { @@ -265,6 +268,9 @@ void aq_pci_func_free(struct aq_pci_func_s *self) aq_nic_ndev_free(self->port[port]); } + if (self->mmio) + iounmap(self->mmio); + kfree(self); err_exit:; diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_vec.c b/drivers/net/ethernet/aquantia/atlantic/aq_vec.c index 305ff8ffac2c..5fecc9a099ef 100644 --- a/drivers/net/ethernet/aquantia/atlantic/aq_vec.c +++ b/drivers/net/ethernet/aquantia/atlantic/aq_vec.c @@ -373,8 +373,11 @@ int aq_vec_get_sw_stats(struct aq_vec_s *self, u64 *data, unsigned int *p_count) memset(&stats_tx, 0U, sizeof(struct aq_ring_stats_tx_s)); aq_vec_add_stats(self, &stats_rx, &stats_tx); + /* This data should mimic aq_ethtool_queue_stat_names structure + */ data[count] += stats_rx.packets; data[++count] += stats_tx.packets; + data[++count] += stats_tx.queue_restarts; data[++count] += stats_rx.jumbo_packets; data[++count] += stats_rx.lro_packets; data[++count] += stats_rx.errors; 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 c5a02df7a48b..07b3c49a16a4 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 @@ -765,24 +765,23 @@ err_exit: return err; } -static int hw_atl_a0_hw_interrupt_moderation_set(struct aq_hw_s *self, - bool itr_enabled) +static int hw_atl_a0_hw_interrupt_moderation_set(struct aq_hw_s *self) { unsigned int i = 0U; + u32 itr_rx; - if (itr_enabled && self->aq_nic_cfg->itr) { - if (self->aq_nic_cfg->itr != 0xFFFFU) { + if (self->aq_nic_cfg->itr) { + if (self->aq_nic_cfg->itr != AQ_CFG_INTERRUPT_MODERATION_AUTO) { u32 itr_ = (self->aq_nic_cfg->itr >> 1); itr_ = min(AQ_CFG_IRQ_MASK, itr_); - PHAL_ATLANTIC_A0->itr_rx = 0x80000000U | - (itr_ << 0x10); + itr_rx = 0x80000000U | (itr_ << 0x10); } else { u32 n = 0xFFFFU & aq_hw_read_reg(self, 0x00002A00U); if (n < self->aq_link_status.mbps) { - PHAL_ATLANTIC_A0->itr_rx = 0U; + itr_rx = 0U; } else { static unsigned int hw_timers_tbl_[] = { 0x01CU, /* 10Gbit */ @@ -797,8 +796,7 @@ static int hw_atl_a0_hw_interrupt_moderation_set(struct aq_hw_s *self, hw_atl_utils_mbps_2_speed_index( self->aq_link_status.mbps); - PHAL_ATLANTIC_A0->itr_rx = - 0x80000000U | + itr_rx = 0x80000000U | (hw_timers_tbl_[speed_index] << 0x10U); } @@ -806,11 +804,11 @@ static int hw_atl_a0_hw_interrupt_moderation_set(struct aq_hw_s *self, aq_hw_write_reg(self, 0x00002A00U, 0x8D000000U); } } else { - PHAL_ATLANTIC_A0->itr_rx = 0U; + itr_rx = 0U; } for (i = HW_ATL_A0_RINGS_MAX; i--;) - reg_irq_thr_set(self, PHAL_ATLANTIC_A0->itr_rx, i); + reg_irq_thr_set(self, itr_rx, i); return aq_hw_err_from_flags(self); } @@ -885,6 +883,7 @@ static struct aq_hw_ops hw_atl_ops_ = { .hw_rss_set = hw_atl_a0_hw_rss_set, .hw_rss_hash_set = hw_atl_a0_hw_rss_hash_set, .hw_get_regs = hw_atl_utils_hw_get_regs, + .hw_update_stats = hw_atl_utils_update_stats, .hw_get_hw_stats = hw_atl_utils_get_hw_stats, .hw_get_fw_version = hw_atl_utils_get_fw_version, }; 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 21784cc39dab..ec68c20efcbd 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 @@ -788,39 +788,45 @@ err_exit: return err; } -static int hw_atl_b0_hw_interrupt_moderation_set(struct aq_hw_s *self, - bool itr_enabled) +static int hw_atl_b0_hw_interrupt_moderation_set(struct aq_hw_s *self) { unsigned int i = 0U; + u32 itr_tx = 2U; + u32 itr_rx = 2U; - if (itr_enabled && self->aq_nic_cfg->itr) { + switch (self->aq_nic_cfg->itr) { + case AQ_CFG_INTERRUPT_MODERATION_ON: + case AQ_CFG_INTERRUPT_MODERATION_AUTO: tdm_tx_desc_wr_wb_irq_en_set(self, 0U); tdm_tdm_intr_moder_en_set(self, 1U); rdm_rx_desc_wr_wb_irq_en_set(self, 0U); rdm_rdm_intr_moder_en_set(self, 1U); - PHAL_ATLANTIC_B0->itr_tx = 2U; - PHAL_ATLANTIC_B0->itr_rx = 2U; + if (self->aq_nic_cfg->itr == AQ_CFG_INTERRUPT_MODERATION_ON) { + /* HW timers are in 2us units */ + int tx_max_timer = self->aq_nic_cfg->tx_itr / 2; + int tx_min_timer = tx_max_timer / 2; - if (self->aq_nic_cfg->itr != 0xFFFFU) { - unsigned int max_timer = self->aq_nic_cfg->itr / 2U; - unsigned int min_timer = self->aq_nic_cfg->itr / 32U; + int rx_max_timer = self->aq_nic_cfg->rx_itr / 2; + int rx_min_timer = rx_max_timer / 2; - max_timer = min(0x1FFU, max_timer); - min_timer = min(0xFFU, min_timer); + tx_max_timer = min(HW_ATL_INTR_MODER_MAX, tx_max_timer); + tx_min_timer = min(HW_ATL_INTR_MODER_MIN, tx_min_timer); + rx_max_timer = min(HW_ATL_INTR_MODER_MAX, rx_max_timer); + rx_min_timer = min(HW_ATL_INTR_MODER_MIN, rx_min_timer); - PHAL_ATLANTIC_B0->itr_tx |= min_timer << 0x8U; - PHAL_ATLANTIC_B0->itr_tx |= max_timer << 0x10U; - PHAL_ATLANTIC_B0->itr_rx |= min_timer << 0x8U; - PHAL_ATLANTIC_B0->itr_rx |= max_timer << 0x10U; + itr_tx |= tx_min_timer << 0x8U; + itr_tx |= tx_max_timer << 0x10U; + itr_rx |= rx_min_timer << 0x8U; + itr_rx |= rx_max_timer << 0x10U; } else { static unsigned int hw_atl_b0_timers_table_tx_[][2] = { - {0xffU, 0xffU}, /* 10Gbit */ - {0xffU, 0x1ffU}, /* 5Gbit */ - {0xffU, 0x1ffU}, /* 5Gbit 5GS */ - {0xffU, 0x1ffU}, /* 2.5Gbit */ - {0xffU, 0x1ffU}, /* 1Gbit */ - {0xffU, 0x1ffU}, /* 100Mbit */ + {0xfU, 0xffU}, /* 10Gbit */ + {0xfU, 0x1ffU}, /* 5Gbit */ + {0xfU, 0x1ffU}, /* 5Gbit 5GS */ + {0xfU, 0x1ffU}, /* 2.5Gbit */ + {0xfU, 0x1ffU}, /* 1Gbit */ + {0xfU, 0x1ffU}, /* 100Mbit */ }; static unsigned int hw_atl_b0_timers_table_rx_[][2] = { @@ -836,34 +842,36 @@ static int hw_atl_b0_hw_interrupt_moderation_set(struct aq_hw_s *self, hw_atl_utils_mbps_2_speed_index( self->aq_link_status.mbps); - PHAL_ATLANTIC_B0->itr_tx |= - hw_atl_b0_timers_table_tx_[speed_index] - [0] << 0x8U; /* set min timer value */ - PHAL_ATLANTIC_B0->itr_tx |= - hw_atl_b0_timers_table_tx_[speed_index] - [1] << 0x10U; /* set max timer value */ - - PHAL_ATLANTIC_B0->itr_rx |= - hw_atl_b0_timers_table_rx_[speed_index] - [0] << 0x8U; /* set min timer value */ - PHAL_ATLANTIC_B0->itr_rx |= - hw_atl_b0_timers_table_rx_[speed_index] - [1] << 0x10U; /* set max timer value */ + /* Update user visible ITR settings */ + self->aq_nic_cfg->tx_itr = hw_atl_b0_timers_table_tx_ + [speed_index][1] * 2; + self->aq_nic_cfg->rx_itr = hw_atl_b0_timers_table_rx_ + [speed_index][1] * 2; + + itr_tx |= hw_atl_b0_timers_table_tx_ + [speed_index][0] << 0x8U; + itr_tx |= hw_atl_b0_timers_table_tx_ + [speed_index][1] << 0x10U; + + itr_rx |= hw_atl_b0_timers_table_rx_ + [speed_index][0] << 0x8U; + itr_rx |= hw_atl_b0_timers_table_rx_ + [speed_index][1] << 0x10U; } - } else { + break; + case AQ_CFG_INTERRUPT_MODERATION_OFF: tdm_tx_desc_wr_wb_irq_en_set(self, 1U); tdm_tdm_intr_moder_en_set(self, 0U); rdm_rx_desc_wr_wb_irq_en_set(self, 1U); rdm_rdm_intr_moder_en_set(self, 0U); - PHAL_ATLANTIC_B0->itr_tx = 0U; - PHAL_ATLANTIC_B0->itr_rx = 0U; + itr_tx = 0U; + itr_rx = 0U; + break; } for (i = HW_ATL_B0_RINGS_MAX; i--;) { - reg_tx_intr_moder_ctrl_set(self, - PHAL_ATLANTIC_B0->itr_tx, i); - reg_rx_intr_moder_ctrl_set(self, - PHAL_ATLANTIC_B0->itr_rx, i); + reg_tx_intr_moder_ctrl_set(self, itr_tx, i); + reg_rx_intr_moder_ctrl_set(self, itr_rx, i); } return aq_hw_err_from_flags(self); @@ -939,6 +947,7 @@ static struct aq_hw_ops hw_atl_ops_ = { .hw_rss_set = hw_atl_b0_hw_rss_set, .hw_rss_hash_set = hw_atl_b0_hw_rss_hash_set, .hw_get_regs = hw_atl_utils_hw_get_regs, + .hw_update_stats = hw_atl_utils_update_stats, .hw_get_hw_stats = hw_atl_utils_get_hw_stats, .hw_get_fw_version = hw_atl_utils_get_fw_version, }; 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 fcf89e25a773..9aa2c6edfca2 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 @@ -139,6 +139,9 @@ #define HW_ATL_B0_FW_VER_EXPECTED 0x01050006U +#define HW_ATL_INTR_MODER_MAX 0x1FF +#define HW_ATL_INTR_MODER_MIN 0xFF + /* Hardware tx descriptor */ struct __packed hw_atl_txd_s { u64 buf_addr; 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 bf734b32e44b..1fe016fc4bc7 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 @@ -255,6 +255,15 @@ err_exit: return err; } +int hw_atl_utils_mpi_read_mbox(struct aq_hw_s *self, + struct hw_aq_atl_utils_mbox_header *pmbox) +{ + return hw_atl_utils_fw_downld_dwords(self, + PHAL_ATLANTIC->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) { @@ -267,9 +276,6 @@ void hw_atl_utils_mpi_read_stats(struct aq_hw_s *self, if (err < 0) goto err_exit; - if (pmbox != &PHAL_ATLANTIC->mbox) - memcpy(pmbox, &PHAL_ATLANTIC->mbox, sizeof(*pmbox)); - if (IS_CHIP_FEATURE(REVISION_A0)) { unsigned int mtu = self->aq_nic_cfg ? self->aq_nic_cfg->mtu : 1514U; @@ -299,17 +305,17 @@ void hw_atl_utils_mpi_set(struct aq_hw_s *self, { int err = 0; u32 transaction_id = 0; + struct hw_aq_atl_utils_mbox_header mbox; if (state == MPI_RESET) { - hw_atl_utils_mpi_read_stats(self, &PHAL_ATLANTIC->mbox); + hw_atl_utils_mpi_read_mbox(self, &mbox); - transaction_id = PHAL_ATLANTIC->mbox.transaction_id; + transaction_id = mbox.transaction_id; AQ_HW_WAIT_FOR(transaction_id != - (hw_atl_utils_mpi_read_stats - (self, &PHAL_ATLANTIC->mbox), - PHAL_ATLANTIC->mbox.transaction_id), - 1000U, 100U); + (hw_atl_utils_mpi_read_mbox(self, &mbox), + mbox.transaction_id), + 1000U, 100U); if (err < 0) goto err_exit; } @@ -492,16 +498,51 @@ int hw_atl_utils_hw_set_power(struct aq_hw_s *self, return 0; } +int hw_atl_utils_update_stats(struct aq_hw_s *self) +{ + struct hw_atl_s *hw_self = PHAL_ATLANTIC; + struct hw_aq_atl_utils_mbox mbox; + + if (!self->aq_link_status.mbps) + return 0; + + hw_atl_utils_mpi_read_stats(self, &mbox); + +#define AQ_SDELTA(_N_) (hw_self->curr_stats._N_ += \ + mbox.stats._N_ - hw_self->last_stats._N_) + + AQ_SDELTA(uprc); + AQ_SDELTA(mprc); + AQ_SDELTA(bprc); + AQ_SDELTA(erpt); + + AQ_SDELTA(uptc); + AQ_SDELTA(mptc); + AQ_SDELTA(bptc); + AQ_SDELTA(erpr); + + AQ_SDELTA(ubrc); + AQ_SDELTA(ubtc); + AQ_SDELTA(mbrc); + AQ_SDELTA(mbtc); + AQ_SDELTA(bbrc); + AQ_SDELTA(bbtc); + AQ_SDELTA(dpc); + +#undef AQ_SDELTA + + memcpy(&hw_self->last_stats, &mbox.stats, sizeof(mbox.stats)); + + return 0; +} + int hw_atl_utils_get_hw_stats(struct aq_hw_s *self, u64 *data, unsigned int *p_count) { - struct hw_atl_stats_s *stats = NULL; + struct hw_atl_s *hw_self = PHAL_ATLANTIC; + struct hw_atl_stats_s *stats = &hw_self->curr_stats; int i = 0; - hw_atl_utils_mpi_read_stats(self, &PHAL_ATLANTIC->mbox); - - stats = &PHAL_ATLANTIC->mbox.stats; - data[i] = stats->uprc + stats->mprc + stats->bprc; data[++i] = stats->uprc; data[++i] = stats->mprc; 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 e0360a6b2202..c99cc690e425 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 @@ -115,19 +115,22 @@ struct __packed hw_aq_atl_utils_fw_rpc { }; }; -struct __packed hw_aq_atl_utils_mbox { +struct __packed hw_aq_atl_utils_mbox_header { u32 version; u32 transaction_id; - int error; + u32 error; +}; + +struct __packed hw_aq_atl_utils_mbox { + struct hw_aq_atl_utils_mbox_header header; struct hw_atl_stats_s stats; }; struct __packed hw_atl_s { struct aq_hw_s base; - struct hw_aq_atl_utils_mbox mbox; + struct hw_atl_stats_s last_stats; + struct hw_atl_stats_s curr_stats; u64 speed; - u32 itr_tx; - u32 itr_rx; unsigned int chip_features; u32 fw_ver_actual; atomic_t dpc; @@ -170,6 +173,9 @@ enum hal_atl_utils_fw_state_e { 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); + void hw_atl_utils_mpi_read_stats(struct aq_hw_s *self, struct hw_aq_atl_utils_mbox *pmbox); @@ -199,6 +205,8 @@ int hw_atl_utils_hw_deinit(struct aq_hw_s *self); 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); + int hw_atl_utils_get_hw_stats(struct aq_hw_s *self, u64 *data, unsigned int *p_count); diff --git a/drivers/net/ethernet/hisilicon/hns/hns_enet.c b/drivers/net/ethernet/hisilicon/hns/hns_enet.c index 36520634c96a..e77192683dba 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_enet.c +++ b/drivers/net/ethernet/hisilicon/hns/hns_enet.c @@ -2369,8 +2369,8 @@ static int hns_nic_dev_probe(struct platform_device *pdev) priv->enet_ver = AE_VERSION_2; ae_node = of_parse_phandle(dev->of_node, "ae-handle", 0); - if (IS_ERR_OR_NULL(ae_node)) { - ret = PTR_ERR(ae_node); + if (!ae_node) { + ret = -ENODEV; dev_err(dev, "not find ae-handle\n"); goto out_read_prop_fail; } diff --git a/drivers/net/ethernet/intel/e1000/e1000_ethtool.c b/drivers/net/ethernet/intel/e1000/e1000_ethtool.c index ec8aa4562cc9..3b3983a1ffbb 100644 --- a/drivers/net/ethernet/intel/e1000/e1000_ethtool.c +++ b/drivers/net/ethernet/intel/e1000/e1000_ethtool.c @@ -1824,11 +1824,12 @@ static void e1000_get_ethtool_stats(struct net_device *netdev, { struct e1000_adapter *adapter = netdev_priv(netdev); int i; - char *p = NULL; const struct e1000_stats *stat = e1000_gstrings_stats; e1000_update_stats(adapter); - for (i = 0; i < E1000_GLOBAL_STATS_LEN; i++) { + for (i = 0; i < E1000_GLOBAL_STATS_LEN; i++, stat++) { + char *p; + switch (stat->type) { case NETDEV_STATS: p = (char *)netdev + stat->stat_offset; @@ -1839,15 +1840,13 @@ static void e1000_get_ethtool_stats(struct net_device *netdev, default: WARN_ONCE(1, "Invalid E1000 stat type: %u index %d\n", stat->type, i); - break; + continue; } if (stat->sizeof_stat == sizeof(u64)) data[i] = *(u64 *)p; else data[i] = *(u32 *)p; - - stat++; } /* BUG_ON(i != E1000_STATS_LEN); */ } diff --git a/drivers/net/ethernet/intel/e1000/e1000_main.c b/drivers/net/ethernet/intel/e1000/e1000_main.c index 98375e1e1185..1982f7917a8d 100644 --- a/drivers/net/ethernet/intel/e1000/e1000_main.c +++ b/drivers/net/ethernet/intel/e1000/e1000_main.c @@ -520,8 +520,6 @@ void e1000_down(struct e1000_adapter *adapter) struct net_device *netdev = adapter->netdev; u32 rctl, tctl; - netif_carrier_off(netdev); - /* disable receives in the hardware */ rctl = er32(RCTL); ew32(RCTL, rctl & ~E1000_RCTL_EN); @@ -537,6 +535,15 @@ void e1000_down(struct e1000_adapter *adapter) E1000_WRITE_FLUSH(); msleep(10); + /* Set the carrier off after transmits have been disabled in the + * hardware, to avoid race conditions with e1000_watchdog() (which + * may be running concurrently to us, checking for the carrier + * bit to decide whether it should enable transmits again). Such + * a race condition would result into transmission being disabled + * in the hardware until the next IFF_DOWN+IFF_UP cycle. + */ + netif_carrier_off(netdev); + napi_disable(&adapter->napi); e1000_irq_disable(adapter); diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.c b/drivers/net/ethernet/intel/i40e/i40e_txrx.c index 2756131495f0..120c68f78951 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_txrx.c +++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.c @@ -2102,6 +2102,7 @@ static int i40e_clean_rx_irq(struct i40e_ring *rx_ring, int budget) if (unlikely(i40e_rx_is_programming_status(qword))) { i40e_clean_programming_status(rx_ring, rx_desc, qword); + cleaned_count++; continue; } size = (qword & I40E_RXD_QW1_LENGTH_PBUF_MASK) >> @@ -2269,7 +2270,7 @@ static inline void i40e_update_enable_itr(struct i40e_vsi *vsi, goto enable_int; } - if (ITR_IS_DYNAMIC(tx_itr_setting)) { + if (ITR_IS_DYNAMIC(rx_itr_setting)) { rx = i40e_set_new_dynamic_itr(&q_vector->rx); rxval = i40e_buildreg_itr(I40E_RX_ITR, q_vector->rx.itr); } diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c index fd4a46b03cc8..ea69af267d63 100644 --- a/drivers/net/ethernet/intel/igb/igb_main.c +++ b/drivers/net/ethernet/intel/igb/igb_main.c @@ -5326,7 +5326,7 @@ dma_error: DMA_TO_DEVICE); dma_unmap_len_set(tx_buffer, len, 0); - if (i--) + if (i-- == 0) i += tx_ring->count; tx_buffer = &tx_ring->tx_buffer_info[i]; } diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c index 4d76afd13868..6d5f31e94358 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c @@ -8020,29 +8020,23 @@ static int ixgbe_tx_map(struct ixgbe_ring *tx_ring, return 0; dma_error: dev_err(tx_ring->dev, "TX DMA map failed\n"); - tx_buffer = &tx_ring->tx_buffer_info[i]; /* clear dma mappings for failed tx_buffer_info map */ - while (tx_buffer != first) { + for (;;) { + tx_buffer = &tx_ring->tx_buffer_info[i]; if (dma_unmap_len(tx_buffer, len)) dma_unmap_page(tx_ring->dev, dma_unmap_addr(tx_buffer, dma), dma_unmap_len(tx_buffer, len), DMA_TO_DEVICE); dma_unmap_len_set(tx_buffer, len, 0); - - if (i--) + if (tx_buffer == first) + break; + if (i == 0) i += tx_ring->count; - tx_buffer = &tx_ring->tx_buffer_info[i]; + i--; } - if (dma_unmap_len(tx_buffer, len)) - dma_unmap_single(tx_ring->dev, - dma_unmap_addr(tx_buffer, dma), - dma_unmap_len(tx_buffer, len), - DMA_TO_DEVICE); - dma_unmap_len_set(tx_buffer, len, 0); - dev_kfree_skb_any(first->skb); first->skb = NULL; diff --git a/drivers/net/ethernet/marvell/mvpp2.c b/drivers/net/ethernet/marvell/mvpp2.c index 9c86cb7cb988..a37af5813f33 100644 --- a/drivers/net/ethernet/marvell/mvpp2.c +++ b/drivers/net/ethernet/marvell/mvpp2.c @@ -1167,6 +1167,11 @@ struct mvpp2_bm_pool { u32 port_map; }; +#define IS_TSO_HEADER(txq_pcpu, addr) \ + ((addr) >= (txq_pcpu)->tso_headers_dma && \ + (addr) < (txq_pcpu)->tso_headers_dma + \ + (txq_pcpu)->size * TSO_HEADER_SIZE) + /* Queue modes */ #define MVPP2_QDIST_SINGLE_MODE 0 #define MVPP2_QDIST_MULTI_MODE 1 @@ -1534,7 +1539,7 @@ static bool mvpp2_prs_tcam_data_cmp(struct mvpp2_prs_entry *pe, int offs, int off = MVPP2_PRS_TCAM_DATA_BYTE(offs); u16 tcam_data; - tcam_data = (8 << pe->tcam.byte[off + 1]) | pe->tcam.byte[off]; + tcam_data = (pe->tcam.byte[off + 1] << 8) | pe->tcam.byte[off]; if (tcam_data != data) return false; return true; @@ -2609,8 +2614,8 @@ static void mvpp2_prs_mac_init(struct mvpp2 *priv) /* place holders only - no ports */ mvpp2_prs_mac_drop_all_set(priv, 0, false); mvpp2_prs_mac_promisc_set(priv, 0, false); - mvpp2_prs_mac_multi_set(priv, MVPP2_PE_MAC_MC_ALL, 0, false); - mvpp2_prs_mac_multi_set(priv, MVPP2_PE_MAC_MC_IP6, 0, false); + mvpp2_prs_mac_multi_set(priv, 0, MVPP2_PE_MAC_MC_ALL, false); + mvpp2_prs_mac_multi_set(priv, 0, MVPP2_PE_MAC_MC_IP6, false); } /* Set default entries for various types of dsa packets */ @@ -3391,7 +3396,7 @@ mvpp2_prs_mac_da_range_find(struct mvpp2 *priv, int pmap, const u8 *da, struct mvpp2_prs_entry *pe; int tid; - pe = kzalloc(sizeof(*pe), GFP_KERNEL); + pe = kzalloc(sizeof(*pe), GFP_ATOMIC); if (!pe) return NULL; mvpp2_prs_tcam_lu_set(pe, MVPP2_PRS_LU_MAC); @@ -3453,7 +3458,7 @@ static int mvpp2_prs_mac_da_accept(struct mvpp2 *priv, int port, if (tid < 0) return tid; - pe = kzalloc(sizeof(*pe), GFP_KERNEL); + pe = kzalloc(sizeof(*pe), GFP_ATOMIC); if (!pe) return -ENOMEM; mvpp2_prs_tcam_lu_set(pe, MVPP2_PRS_LU_MAC); @@ -5321,8 +5326,9 @@ static void mvpp2_txq_bufs_free(struct mvpp2_port *port, struct mvpp2_txq_pcpu_buf *tx_buf = txq_pcpu->buffs + txq_pcpu->txq_get_index; - dma_unmap_single(port->dev->dev.parent, tx_buf->dma, - tx_buf->size, DMA_TO_DEVICE); + if (!IS_TSO_HEADER(txq_pcpu, tx_buf->dma)) + dma_unmap_single(port->dev->dev.parent, tx_buf->dma, + tx_buf->size, DMA_TO_DEVICE); if (tx_buf->skb) dev_kfree_skb_any(tx_buf->skb); @@ -5609,7 +5615,7 @@ static int mvpp2_txq_init(struct mvpp2_port *port, txq_pcpu->tso_headers = dma_alloc_coherent(port->dev->dev.parent, - MVPP2_AGGR_TXQ_SIZE * TSO_HEADER_SIZE, + txq_pcpu->size * TSO_HEADER_SIZE, &txq_pcpu->tso_headers_dma, GFP_KERNEL); if (!txq_pcpu->tso_headers) @@ -5623,7 +5629,7 @@ cleanup: kfree(txq_pcpu->buffs); dma_free_coherent(port->dev->dev.parent, - MVPP2_AGGR_TXQ_SIZE * MVPP2_DESC_ALIGNED_SIZE, + txq_pcpu->size * TSO_HEADER_SIZE, txq_pcpu->tso_headers, txq_pcpu->tso_headers_dma); } @@ -5647,7 +5653,7 @@ static void mvpp2_txq_deinit(struct mvpp2_port *port, kfree(txq_pcpu->buffs); dma_free_coherent(port->dev->dev.parent, - MVPP2_AGGR_TXQ_SIZE * MVPP2_DESC_ALIGNED_SIZE, + txq_pcpu->size * TSO_HEADER_SIZE, txq_pcpu->tso_headers, txq_pcpu->tso_headers_dma); } @@ -6212,12 +6218,15 @@ 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); + dma_addr_t buf_dma_addr = mvpp2_txdesc_dma_addr_get(port, desc); size_t buf_sz = mvpp2_txdesc_size_get(port, desc); - dma_unmap_single(port->dev->dev.parent, buf_dma_addr, - buf_sz, DMA_TO_DEVICE); + if (!IS_TSO_HEADER(txq_pcpu, buf_dma_addr)) + dma_unmap_single(port->dev->dev.parent, buf_dma_addr, + buf_sz, DMA_TO_DEVICE); mvpp2_txq_desc_put(txq); } @@ -6490,7 +6499,7 @@ out: } /* Finalize TX processing */ - if (txq_pcpu->count >= txq->done_pkts_coal) + if (!port->has_tx_irqs && txq_pcpu->count >= txq->done_pkts_coal) mvpp2_txq_done(port, txq, txq_pcpu); /* Set the timer in case not all frags were processed */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/dev.c b/drivers/net/ethernet/mellanox/mlx5/core/dev.c index ff60cf7342ca..fc281712869b 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/dev.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/dev.c @@ -77,35 +77,41 @@ static void add_delayed_event(struct mlx5_priv *priv, list_add_tail(&delayed_event->list, &priv->waiting_events_list); } -static void fire_delayed_event_locked(struct mlx5_device_context *dev_ctx, - struct mlx5_core_dev *dev, - struct mlx5_priv *priv) +static void delayed_event_release(struct mlx5_device_context *dev_ctx, + struct mlx5_priv *priv) { + struct mlx5_core_dev *dev = container_of(priv, struct mlx5_core_dev, priv); struct mlx5_delayed_event *de; struct mlx5_delayed_event *n; + struct list_head temp; - /* stop delaying events */ - priv->is_accum_events = false; + INIT_LIST_HEAD(&temp); + + spin_lock_irq(&priv->ctx_lock); - /* fire all accumulated events before new event comes */ - list_for_each_entry_safe(de, n, &priv->waiting_events_list, list) { + priv->is_accum_events = false; + list_splice_init(&priv->waiting_events_list, &temp); + if (!dev_ctx->context) + goto out; + list_for_each_entry_safe(de, n, &priv->waiting_events_list, list) dev_ctx->intf->event(dev, dev_ctx->context, de->event, de->param); + +out: + spin_unlock_irq(&priv->ctx_lock); + + list_for_each_entry_safe(de, n, &temp, list) { list_del(&de->list); kfree(de); } } -static void cleanup_delayed_evets(struct mlx5_priv *priv) +/* accumulating events that can come after mlx5_ib calls to + * ib_register_device, till adding that interface to the events list. + */ +static void delayed_event_start(struct mlx5_priv *priv) { - struct mlx5_delayed_event *de; - struct mlx5_delayed_event *n; - spin_lock_irq(&priv->ctx_lock); - priv->is_accum_events = false; - list_for_each_entry_safe(de, n, &priv->waiting_events_list, list) { - list_del(&de->list); - kfree(de); - } + priv->is_accum_events = true; spin_unlock_irq(&priv->ctx_lock); } @@ -122,11 +128,8 @@ void mlx5_add_device(struct mlx5_interface *intf, struct mlx5_priv *priv) return; dev_ctx->intf = intf; - /* accumulating events that can come after mlx5_ib calls to - * ib_register_device, till adding that interface to the events list. - */ - priv->is_accum_events = true; + delayed_event_start(priv); dev_ctx->context = intf->add(dev); set_bit(MLX5_INTERFACE_ADDED, &dev_ctx->state); @@ -137,8 +140,6 @@ void mlx5_add_device(struct mlx5_interface *intf, struct mlx5_priv *priv) spin_lock_irq(&priv->ctx_lock); list_add_tail(&dev_ctx->list, &priv->ctx_list); - fire_delayed_event_locked(dev_ctx, dev, priv); - #ifdef CONFIG_INFINIBAND_ON_DEMAND_PAGING if (dev_ctx->intf->pfault) { if (priv->pfault) { @@ -150,11 +151,12 @@ void mlx5_add_device(struct mlx5_interface *intf, struct mlx5_priv *priv) } #endif spin_unlock_irq(&priv->ctx_lock); - } else { - kfree(dev_ctx); - /* delete all accumulated events */ - cleanup_delayed_evets(priv); } + + delayed_event_release(dev_ctx, priv); + + if (!dev_ctx->context) + kfree(dev_ctx); } static struct mlx5_device_context *mlx5_get_device(struct mlx5_interface *intf, @@ -205,17 +207,21 @@ static void mlx5_attach_interface(struct mlx5_interface *intf, struct mlx5_priv if (!dev_ctx) return; + delayed_event_start(priv); if (intf->attach) { if (test_bit(MLX5_INTERFACE_ATTACHED, &dev_ctx->state)) - return; + goto out; intf->attach(dev, dev_ctx->context); set_bit(MLX5_INTERFACE_ATTACHED, &dev_ctx->state); } else { if (test_bit(MLX5_INTERFACE_ADDED, &dev_ctx->state)) - return; + goto out; dev_ctx->context = intf->add(dev); set_bit(MLX5_INTERFACE_ADDED, &dev_ctx->state); } + +out: + delayed_event_release(dev_ctx, priv); } void mlx5_attach_device(struct mlx5_core_dev *dev) @@ -414,8 +420,14 @@ void mlx5_core_event(struct mlx5_core_dev *dev, enum mlx5_dev_event event, if (priv->is_accum_events) add_delayed_event(priv, dev, event, param); + /* After mlx5_detach_device, the dev_ctx->intf is still set and dev_ctx is + * still in priv->ctx_list. In this case, only notify the dev_ctx if its + * ADDED or ATTACHED bit are set. + */ list_for_each_entry(dev_ctx, &priv->ctx_list, list) - if (dev_ctx->intf->event) + if (dev_ctx->intf->event && + (test_bit(MLX5_INTERFACE_ADDED, &dev_ctx->state) || + test_bit(MLX5_INTERFACE_ATTACHED, &dev_ctx->state))) dev_ctx->intf->event(dev, dev_ctx->context, event, param); spin_unlock_irqrestore(&priv->ctx_lock, flags); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c b/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c index c1d384fca4dc..51c4cc00a186 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c @@ -41,6 +41,11 @@ #define MLX5E_CEE_STATE_UP 1 #define MLX5E_CEE_STATE_DOWN 0 +enum { + MLX5E_VENDOR_TC_GROUP_NUM = 7, + MLX5E_LOWEST_PRIO_GROUP = 0, +}; + /* If dcbx mode is non-host set the dcbx mode to host. */ static int mlx5e_dcbnl_set_dcbx_mode(struct mlx5e_priv *priv, @@ -85,6 +90,9 @@ static int mlx5e_dcbnl_ieee_getets(struct net_device *netdev, { struct mlx5e_priv *priv = netdev_priv(netdev); struct mlx5_core_dev *mdev = priv->mdev; + u8 tc_group[IEEE_8021QAZ_MAX_TCS]; + bool is_tc_group_6_exist = false; + bool is_zero_bw_ets_tc = false; int err = 0; int i; @@ -96,37 +104,64 @@ static int mlx5e_dcbnl_ieee_getets(struct net_device *netdev, err = mlx5_query_port_prio_tc(mdev, i, &ets->prio_tc[i]); if (err) return err; - } - for (i = 0; i < ets->ets_cap; i++) { + err = mlx5_query_port_tc_group(mdev, i, &tc_group[i]); + if (err) + return err; + err = mlx5_query_port_tc_bw_alloc(mdev, i, &ets->tc_tx_bw[i]); if (err) return err; + + if (ets->tc_tx_bw[i] < MLX5E_MAX_BW_ALLOC && + tc_group[i] == (MLX5E_LOWEST_PRIO_GROUP + 1)) + is_zero_bw_ets_tc = true; + + if (tc_group[i] == (MLX5E_VENDOR_TC_GROUP_NUM - 1)) + is_tc_group_6_exist = true; + } + + /* Report 0% ets tc if exits*/ + if (is_zero_bw_ets_tc) { + for (i = 0; i < ets->ets_cap; i++) + if (tc_group[i] == MLX5E_LOWEST_PRIO_GROUP) + ets->tc_tx_bw[i] = 0; + } + + /* Update tc_tsa based on fw setting*/ + for (i = 0; i < ets->ets_cap; i++) { if (ets->tc_tx_bw[i] < MLX5E_MAX_BW_ALLOC) priv->dcbx.tc_tsa[i] = IEEE_8021QAZ_TSA_ETS; + else if (tc_group[i] == MLX5E_VENDOR_TC_GROUP_NUM && + !is_tc_group_6_exist) + priv->dcbx.tc_tsa[i] = IEEE_8021QAZ_TSA_VENDOR; } - memcpy(ets->tc_tsa, priv->dcbx.tc_tsa, sizeof(ets->tc_tsa)); return err; } -enum { - MLX5E_VENDOR_TC_GROUP_NUM = 7, - MLX5E_ETS_TC_GROUP_NUM = 0, -}; - static void mlx5e_build_tc_group(struct ieee_ets *ets, u8 *tc_group, int max_tc) { bool any_tc_mapped_to_ets = false; + bool ets_zero_bw = false; int strict_group; int i; - for (i = 0; i <= max_tc; i++) - if (ets->tc_tsa[i] == IEEE_8021QAZ_TSA_ETS) + for (i = 0; i <= max_tc; i++) { + if (ets->tc_tsa[i] == IEEE_8021QAZ_TSA_ETS) { any_tc_mapped_to_ets = true; + if (!ets->tc_tx_bw[i]) + ets_zero_bw = true; + } + } - strict_group = any_tc_mapped_to_ets ? 1 : 0; + /* strict group has higher priority than ets group */ + strict_group = MLX5E_LOWEST_PRIO_GROUP; + if (any_tc_mapped_to_ets) + strict_group++; + if (ets_zero_bw) + strict_group++; for (i = 0; i <= max_tc; i++) { switch (ets->tc_tsa[i]) { @@ -137,7 +172,9 @@ static void mlx5e_build_tc_group(struct ieee_ets *ets, u8 *tc_group, int max_tc) tc_group[i] = strict_group++; break; case IEEE_8021QAZ_TSA_ETS: - tc_group[i] = MLX5E_ETS_TC_GROUP_NUM; + tc_group[i] = MLX5E_LOWEST_PRIO_GROUP; + if (ets->tc_tx_bw[i] && ets_zero_bw) + tc_group[i] = MLX5E_LOWEST_PRIO_GROUP + 1; break; } } @@ -146,9 +183,23 @@ static void mlx5e_build_tc_group(struct ieee_ets *ets, u8 *tc_group, int max_tc) static void mlx5e_build_tc_tx_bw(struct ieee_ets *ets, u8 *tc_tx_bw, u8 *tc_group, int max_tc) { + int bw_for_ets_zero_bw_tc = 0; + int last_ets_zero_bw_tc = -1; + int num_ets_zero_bw = 0; int i; for (i = 0; i <= max_tc; i++) { + if (ets->tc_tsa[i] == IEEE_8021QAZ_TSA_ETS && + !ets->tc_tx_bw[i]) { + num_ets_zero_bw++; + last_ets_zero_bw_tc = i; + } + } + + if (num_ets_zero_bw) + bw_for_ets_zero_bw_tc = MLX5E_MAX_BW_ALLOC / num_ets_zero_bw; + + for (i = 0; i <= max_tc; i++) { switch (ets->tc_tsa[i]) { case IEEE_8021QAZ_TSA_VENDOR: tc_tx_bw[i] = MLX5E_MAX_BW_ALLOC; @@ -157,12 +208,26 @@ static void mlx5e_build_tc_tx_bw(struct ieee_ets *ets, u8 *tc_tx_bw, tc_tx_bw[i] = MLX5E_MAX_BW_ALLOC; break; case IEEE_8021QAZ_TSA_ETS: - tc_tx_bw[i] = ets->tc_tx_bw[i]; + tc_tx_bw[i] = ets->tc_tx_bw[i] ? + ets->tc_tx_bw[i] : + bw_for_ets_zero_bw_tc; break; } } + + /* Make sure the total bw for ets zero bw group is 100% */ + if (last_ets_zero_bw_tc != -1) + tc_tx_bw[last_ets_zero_bw_tc] += + MLX5E_MAX_BW_ALLOC % num_ets_zero_bw; } +/* If there are ETS BW 0, + * Set ETS group # to 1 for all ETS non zero BW tcs. Their sum must be 100%. + * Set group #0 to all the ETS BW 0 tcs and + * equally splits the 100% BW between them + * Report both group #0 and #1 as ETS type. + * All the tcs in group #0 will be reported with 0% BW. + */ int mlx5e_dcbnl_ieee_setets_core(struct mlx5e_priv *priv, struct ieee_ets *ets) { struct mlx5_core_dev *mdev = priv->mdev; @@ -188,7 +253,6 @@ int mlx5e_dcbnl_ieee_setets_core(struct mlx5e_priv *priv, struct ieee_ets *ets) return err; memcpy(priv->dcbx.tc_tsa, ets->tc_tsa, sizeof(ets->tc_tsa)); - return err; } @@ -209,17 +273,9 @@ static int mlx5e_dbcnl_validate_ets(struct net_device *netdev, } /* Validate Bandwidth Sum */ - for (i = 0; i < IEEE_8021QAZ_MAX_TCS; i++) { - if (ets->tc_tsa[i] == IEEE_8021QAZ_TSA_ETS) { - if (!ets->tc_tx_bw[i]) { - netdev_err(netdev, - "Failed to validate ETS: BW 0 is illegal\n"); - return -EINVAL; - } - + for (i = 0; i < IEEE_8021QAZ_MAX_TCS; i++) + if (ets->tc_tsa[i] == IEEE_8021QAZ_TSA_ETS) bw_sum += ets->tc_tx_bw[i]; - } - } if (bw_sum != 0 && bw_sum != 100) { netdev_err(netdev, @@ -533,8 +589,7 @@ static void mlx5e_dcbnl_getpgtccfgtx(struct net_device *netdev, static void mlx5e_dcbnl_getpgbwgcfgtx(struct net_device *netdev, int pgid, u8 *bw_pct) { - struct mlx5e_priv *priv = netdev_priv(netdev); - struct mlx5_core_dev *mdev = priv->mdev; + struct ieee_ets ets; if (pgid >= CEE_DCBX_MAX_PGS) { netdev_err(netdev, @@ -542,8 +597,8 @@ static void mlx5e_dcbnl_getpgbwgcfgtx(struct net_device *netdev, return; } - if (mlx5_query_port_tc_bw_alloc(mdev, pgid, bw_pct)) - *bw_pct = 0; + mlx5e_dcbnl_ieee_getets(netdev, &ets); + *bw_pct = ets.tc_tx_bw[pgid]; } static void mlx5e_dcbnl_setpfccfg(struct net_device *netdev, @@ -739,8 +794,6 @@ static void mlx5e_ets_init(struct mlx5e_priv *priv) ets.prio_tc[i] = i; } - memcpy(priv->dcbx.tc_tsa, ets.tc_tsa, sizeof(ets.tc_tsa)); - /* tclass[prio=0]=1, tclass[prio=1]=0, tclass[prio=i]=i (for i>1) */ ets.prio_tc[0] = 1; ets.prio_tc[1] = 0; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c index 1aa2028ed995..9ba1f72060aa 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c @@ -78,9 +78,11 @@ struct mlx5e_tc_flow { }; struct mlx5e_tc_flow_parse_attr { + struct ip_tunnel_info tun_info; struct mlx5_flow_spec spec; int num_mod_hdr_actions; void *mod_hdr_actions; + int mirred_ifindex; }; enum { @@ -322,6 +324,12 @@ static void mlx5e_tc_del_nic_flow(struct mlx5e_priv *priv, static void mlx5e_detach_encap(struct mlx5e_priv *priv, struct mlx5e_tc_flow *flow); +static int mlx5e_attach_encap(struct mlx5e_priv *priv, + struct ip_tunnel_info *tun_info, + struct net_device *mirred_dev, + struct net_device **encap_dev, + struct mlx5e_tc_flow *flow); + static struct mlx5_flow_handle * mlx5e_tc_add_fdb_flow(struct mlx5e_priv *priv, struct mlx5e_tc_flow_parse_attr *parse_attr, @@ -329,9 +337,27 @@ mlx5e_tc_add_fdb_flow(struct mlx5e_priv *priv, { struct mlx5_eswitch *esw = priv->mdev->priv.eswitch; struct mlx5_esw_flow_attr *attr = flow->esw_attr; - struct mlx5_flow_handle *rule; + struct net_device *out_dev, *encap_dev = NULL; + struct mlx5_flow_handle *rule = NULL; + struct mlx5e_rep_priv *rpriv; + struct mlx5e_priv *out_priv; int err; + if (attr->action & MLX5_FLOW_CONTEXT_ACTION_ENCAP) { + out_dev = __dev_get_by_index(dev_net(priv->netdev), + attr->parse_attr->mirred_ifindex); + err = mlx5e_attach_encap(priv, &parse_attr->tun_info, + out_dev, &encap_dev, flow); + if (err) { + rule = ERR_PTR(err); + if (err != -EAGAIN) + goto err_attach_encap; + } + out_priv = netdev_priv(encap_dev); + rpriv = out_priv->ppriv; + attr->out_rep = rpriv->rep; + } + err = mlx5_eswitch_add_vlan_action(esw, attr); if (err) { rule = ERR_PTR(err); @@ -347,10 +373,14 @@ mlx5e_tc_add_fdb_flow(struct mlx5e_priv *priv, } } - rule = mlx5_eswitch_add_offloaded_rule(esw, &parse_attr->spec, attr); - if (IS_ERR(rule)) - goto err_add_rule; - + /* we get here if (1) there's no error (rule being null) or when + * (2) there's an encap action and we're on -EAGAIN (no valid neigh) + */ + if (rule != ERR_PTR(-EAGAIN)) { + rule = mlx5_eswitch_add_offloaded_rule(esw, &parse_attr->spec, attr); + if (IS_ERR(rule)) + goto err_add_rule; + } return rule; err_add_rule: @@ -361,6 +391,7 @@ err_mod_hdr: err_add_vlan: if (attr->action & MLX5_FLOW_CONTEXT_ACTION_ENCAP) mlx5e_detach_encap(priv, flow); +err_attach_encap: return rule; } @@ -389,6 +420,8 @@ static void mlx5e_tc_del_fdb_flow(struct mlx5e_priv *priv, void mlx5e_tc_encap_flows_add(struct mlx5e_priv *priv, struct mlx5e_encap_entry *e) { + struct mlx5_eswitch *esw = priv->mdev->priv.eswitch; + struct mlx5_esw_flow_attr *esw_attr; struct mlx5e_tc_flow *flow; int err; @@ -404,10 +437,9 @@ void mlx5e_tc_encap_flows_add(struct mlx5e_priv *priv, mlx5e_rep_queue_neigh_stats_work(priv); list_for_each_entry(flow, &e->flows, encap) { - flow->esw_attr->encap_id = e->encap_id; - flow->rule = mlx5e_tc_add_fdb_flow(priv, - flow->esw_attr->parse_attr, - flow); + esw_attr = flow->esw_attr; + esw_attr->encap_id = e->encap_id; + flow->rule = mlx5_eswitch_add_offloaded_rule(esw, &esw_attr->parse_attr->spec, esw_attr); if (IS_ERR(flow->rule)) { err = PTR_ERR(flow->rule); mlx5_core_warn(priv->mdev, "Failed to update cached encapsulation flow, %d\n", @@ -421,15 +453,13 @@ void mlx5e_tc_encap_flows_add(struct mlx5e_priv *priv, void mlx5e_tc_encap_flows_del(struct mlx5e_priv *priv, struct mlx5e_encap_entry *e) { + struct mlx5_eswitch *esw = priv->mdev->priv.eswitch; struct mlx5e_tc_flow *flow; - struct mlx5_fc *counter; list_for_each_entry(flow, &e->flows, encap) { if (flow->flags & MLX5E_TC_FLOW_OFFLOADED) { flow->flags &= ~MLX5E_TC_FLOW_OFFLOADED; - counter = mlx5_flow_rule_counter(flow->rule); - mlx5_del_flow_rules(flow->rule); - mlx5_fc_destroy(priv->mdev, counter); + mlx5_eswitch_del_offloaded_rule(esw, flow->rule, flow->esw_attr); } } @@ -1942,7 +1972,7 @@ static int parse_tc_fdb_actions(struct mlx5e_priv *priv, struct tcf_exts *exts, if (is_tcf_mirred_egress_redirect(a)) { int ifindex = tcf_mirred_ifindex(a); - struct net_device *out_dev, *encap_dev = NULL; + struct net_device *out_dev; struct mlx5e_priv *out_priv; out_dev = __dev_get_by_index(dev_net(priv->netdev), ifindex); @@ -1955,17 +1985,13 @@ static int parse_tc_fdb_actions(struct mlx5e_priv *priv, struct tcf_exts *exts, rpriv = out_priv->ppriv; attr->out_rep = rpriv->rep; } else if (encap) { - err = mlx5e_attach_encap(priv, info, - out_dev, &encap_dev, flow); - if (err && err != -EAGAIN) - return err; + parse_attr->mirred_ifindex = ifindex; + parse_attr->tun_info = *info; + attr->parse_attr = parse_attr; attr->action |= MLX5_FLOW_CONTEXT_ACTION_ENCAP | MLX5_FLOW_CONTEXT_ACTION_FWD_DEST | MLX5_FLOW_CONTEXT_ACTION_COUNT; - out_priv = netdev_priv(encap_dev); - rpriv = out_priv->ppriv; - attr->out_rep = rpriv->rep; - attr->parse_attr = parse_attr; + /* attr->out_rep is resolved when we handle encap */ } else { pr_err("devices %s %s not on same switch HW, can't offload forwarding\n", priv->netdev->name, out_dev->name); @@ -2047,7 +2073,7 @@ int mlx5e_configure_flower(struct mlx5e_priv *priv, if (flow->flags & MLX5E_TC_FLOW_ESWITCH) { err = parse_tc_fdb_actions(priv, f->exts, parse_attr, flow); if (err < 0) - goto err_handle_encap_flow; + goto err_free; flow->rule = mlx5e_tc_add_fdb_flow(priv, parse_attr, flow); } else { err = parse_tc_nic_actions(priv, f->exts, parse_attr, flow); @@ -2058,10 +2084,13 @@ int mlx5e_configure_flower(struct mlx5e_priv *priv, if (IS_ERR(flow->rule)) { err = PTR_ERR(flow->rule); - goto err_free; + if (err != -EAGAIN) + goto err_free; } - flow->flags |= MLX5E_TC_FLOW_OFFLOADED; + if (err != -EAGAIN) + flow->flags |= MLX5E_TC_FLOW_OFFLOADED; + err = rhashtable_insert_fast(&tc->ht, &flow->node, tc->ht_params); if (err) @@ -2075,16 +2104,6 @@ int mlx5e_configure_flower(struct mlx5e_priv *priv, err_del_rule: mlx5e_tc_del_flow(priv, flow); -err_handle_encap_flow: - if (err == -EAGAIN) { - err = rhashtable_insert_fast(&tc->ht, &flow->node, - tc->ht_params); - if (err) - mlx5e_tc_del_flow(priv, flow); - else - return 0; - } - err_free: kvfree(parse_attr); kfree(flow); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/health.c b/drivers/net/ethernet/mellanox/mlx5/core/health.c index 8aea0a065e56..db86e1506c8b 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/health.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/health.c @@ -356,10 +356,11 @@ void mlx5_drain_health_wq(struct mlx5_core_dev *dev) void mlx5_drain_health_recovery(struct mlx5_core_dev *dev) { struct mlx5_core_health *health = &dev->priv.health; + unsigned long flags; - spin_lock(&health->wq_lock); + spin_lock_irqsave(&health->wq_lock, flags); set_bit(MLX5_DROP_NEW_RECOVERY_WORK, &health->flags); - spin_unlock(&health->wq_lock); + spin_unlock_irqrestore(&health->wq_lock, flags); cancel_delayed_work_sync(&dev->priv.health.recover_work); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/port.c b/drivers/net/ethernet/mellanox/mlx5/core/port.c index 1975d4388d4f..e07061f565d6 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/port.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/port.c @@ -677,6 +677,27 @@ int mlx5_set_port_tc_group(struct mlx5_core_dev *mdev, u8 *tc_group) } EXPORT_SYMBOL_GPL(mlx5_set_port_tc_group); +int mlx5_query_port_tc_group(struct mlx5_core_dev *mdev, + u8 tc, u8 *tc_group) +{ + u32 out[MLX5_ST_SZ_DW(qetc_reg)]; + void *ets_tcn_conf; + int err; + + err = mlx5_query_port_qetcr_reg(mdev, out, sizeof(out)); + if (err) + return err; + + ets_tcn_conf = MLX5_ADDR_OF(qetc_reg, out, + tc_configuration[tc]); + + *tc_group = MLX5_GET(ets_tcn_config_reg, ets_tcn_conf, + group); + + return 0; +} +EXPORT_SYMBOL_GPL(mlx5_query_port_tc_group); + int mlx5_set_port_tc_bw_alloc(struct mlx5_core_dev *mdev, u8 *tc_bw) { u32 in[MLX5_ST_SZ_DW(qetc_reg)] = {0}; diff --git a/drivers/net/ethernet/mellanox/mlxsw/i2c.c b/drivers/net/ethernet/mellanox/mlxsw/i2c.c index 12c3a4449120..c0dcfa05b077 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/i2c.c +++ b/drivers/net/ethernet/mellanox/mlxsw/i2c.c @@ -294,7 +294,7 @@ mlxsw_i2c_write(struct device *dev, size_t in_mbox_size, u8 *in_mbox, int num, write_tran.len = MLXSW_I2C_ADDR_WIDTH + chunk_size; mlxsw_i2c_set_slave_addr(tran_buf, off); memcpy(&tran_buf[MLXSW_I2C_ADDR_BUF_SIZE], in_mbox + - chunk_size * i, chunk_size); + MLXSW_I2C_BLK_MAX * i, chunk_size); j = 0; end = jiffies + timeout; diff --git a/drivers/net/ethernet/mellanox/mlxsw/reg.h b/drivers/net/ethernet/mellanox/mlxsw/reg.h index cc27c5de5a1d..5acfbe5b8b9d 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/reg.h +++ b/drivers/net/ethernet/mellanox/mlxsw/reg.h @@ -5827,6 +5827,29 @@ MLXSW_ITEM32(reg, mtmp, mtr, 0x08, 30, 1); */ MLXSW_ITEM32(reg, mtmp, max_temperature, 0x08, 0, 16); +/* reg_mtmp_tee + * Temperature Event Enable. + * 0 - Do not generate event + * 1 - Generate event + * 2 - Generate single event + * Access: RW + */ +MLXSW_ITEM32(reg, mtmp, tee, 0x0C, 30, 2); + +#define MLXSW_REG_MTMP_THRESH_HI 0x348 /* 105 Celsius */ + +/* reg_mtmp_temperature_threshold_hi + * High threshold for Temperature Warning Event. In 0.125 Celsius. + * Access: RW + */ +MLXSW_ITEM32(reg, mtmp, temperature_threshold_hi, 0x0C, 0, 16); + +/* reg_mtmp_temperature_threshold_lo + * Low threshold for Temperature Warning Event. In 0.125 Celsius. + * Access: RW + */ +MLXSW_ITEM32(reg, mtmp, temperature_threshold_lo, 0x10, 0, 16); + #define MLXSW_REG_MTMP_SENSOR_NAME_SIZE 8 /* reg_mtmp_sensor_name @@ -5843,6 +5866,8 @@ static inline void mlxsw_reg_mtmp_pack(char *payload, u8 sensor_index, mlxsw_reg_mtmp_sensor_index_set(payload, sensor_index); mlxsw_reg_mtmp_mte_set(payload, max_temp_enable); mlxsw_reg_mtmp_mtr_set(payload, max_temp_reset); + mlxsw_reg_mtmp_temperature_threshold_hi_set(payload, + MLXSW_REG_MTMP_THRESH_HI); } static inline void mlxsw_reg_mtmp_unpack(char *payload, unsigned int *p_temp, @@ -6401,6 +6426,36 @@ static inline void mlxsw_reg_mgpc_pack(char *payload, u32 counter_index, mlxsw_reg_mgpc_opcode_set(payload, opcode); } +/* TIGCR - Tunneling IPinIP General Configuration Register + * ------------------------------------------------------- + * The TIGCR register is used for setting up the IPinIP Tunnel configuration. + */ +#define MLXSW_REG_TIGCR_ID 0xA801 +#define MLXSW_REG_TIGCR_LEN 0x10 + +MLXSW_REG_DEFINE(tigcr, MLXSW_REG_TIGCR_ID, MLXSW_REG_TIGCR_LEN); + +/* reg_tigcr_ipip_ttlc + * For IPinIP Tunnel encapsulation: whether to copy the ttl from the packet + * header. + * Access: RW + */ +MLXSW_ITEM32(reg, tigcr, ttlc, 0x04, 8, 1); + +/* reg_tigcr_ipip_ttl_uc + * The TTL for IPinIP Tunnel encapsulation of unicast packets if + * reg_tigcr_ipip_ttlc is unset. + * Access: RW + */ +MLXSW_ITEM32(reg, tigcr, ttl_uc, 0x04, 0, 8); + +static inline void mlxsw_reg_tigcr_pack(char *payload, bool ttlc, u8 ttl_uc) +{ + MLXSW_REG_ZERO(tigcr, payload); + mlxsw_reg_tigcr_ttlc_set(payload, ttlc); + mlxsw_reg_tigcr_ttl_uc_set(payload, ttl_uc); +} + /* SBPR - Shared Buffer Pools Register * ----------------------------------- * The SBPR configures and retrieves the shared buffer pools and configuration. @@ -6881,6 +6936,7 @@ static const struct mlxsw_reg_info *mlxsw_reg_infos[] = { MLXSW_REG(mcc), MLXSW_REG(mcda), MLXSW_REG(mgpc), + MLXSW_REG(tigcr), MLXSW_REG(sbpr), MLXSW_REG(sbcm), MLXSW_REG(sbpm), diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c index c16718d296d3..5189022a1c8c 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c @@ -5896,11 +5896,20 @@ static void mlxsw_sp_rifs_fini(struct mlxsw_sp *mlxsw_sp) kfree(mlxsw_sp->router->rifs); } +static int +mlxsw_sp_ipip_config_tigcr(struct mlxsw_sp *mlxsw_sp) +{ + char tigcr_pl[MLXSW_REG_TIGCR_LEN]; + + mlxsw_reg_tigcr_pack(tigcr_pl, true, 0); + return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(tigcr), tigcr_pl); +} + static int mlxsw_sp_ipips_init(struct mlxsw_sp *mlxsw_sp) { mlxsw_sp->router->ipip_ops_arr = mlxsw_sp_ipip_ops_arr; INIT_LIST_HEAD(&mlxsw_sp->router->ipip_list); - return 0; + return mlxsw_sp_ipip_config_tigcr(mlxsw_sp); } static void mlxsw_sp_ipips_fini(struct mlxsw_sp *mlxsw_sp) diff --git a/drivers/net/ethernet/netronome/nfp/flower/action.c b/drivers/net/ethernet/netronome/nfp/flower/action.c index db9750695dc7..8ea9320014ee 100644 --- a/drivers/net/ethernet/netronome/nfp/flower/action.c +++ b/drivers/net/ethernet/netronome/nfp/flower/action.c @@ -110,6 +110,8 @@ nfp_fl_output(struct nfp_fl_output *output, const struct tc_action *action, */ if (!switchdev_port_same_parent_id(in_dev, out_dev)) return -EOPNOTSUPP; + if (!nfp_netdev_is_nfp_repr(out_dev)) + return -EOPNOTSUPP; output->port = cpu_to_be32(nfp_repr_get_port_id(out_dev)); if (!output->port) diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-dwc-qos-eth.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-dwc-qos-eth.c index 5efef8001edf..3256e5cbad27 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-dwc-qos-eth.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-dwc-qos-eth.c @@ -74,7 +74,7 @@ static int dwc_eth_dwmac_config_dt(struct platform_device *pdev, plat_dat->axi->axi_wr_osr_lmt--; } - if (of_property_read_u32(np, "read,read-requests", + if (of_property_read_u32(np, "snps,read-requests", &plat_dat->axi->axi_rd_osr_lmt)) { /** * Since the register has a reset value of 1, if property diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_descs.c b/drivers/net/ethernet/stmicro/stmmac/dwmac4_descs.c index e0ef02f9503b..4b286e27c4ca 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_descs.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_descs.c @@ -275,7 +275,7 @@ static int dwmac4_wrback_get_rx_timestamp_status(void *desc, u32 ats) goto exit; i++; - } while ((ret == 1) || (i < 10)); + } while ((ret == 1) && (i < 10)); if (i == 10) ret = -EBUSY; diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index 1763e48c84e2..16bd50929084 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -473,19 +473,18 @@ static void stmmac_get_rx_hwtstamp(struct stmmac_priv *priv, struct dma_desc *p, struct dma_desc *np, struct sk_buff *skb) { struct skb_shared_hwtstamps *shhwtstamp = NULL; + struct dma_desc *desc = p; u64 ns; if (!priv->hwts_rx_en) return; + /* For GMAC4, the valid timestamp is from CTX next desc. */ + if (priv->plat->has_gmac4) + desc = np; /* Check if timestamp is available */ - if (priv->hw->desc->get_rx_timestamp_status(p, priv->adv_ts)) { - /* For GMAC4, the valid timestamp is from CTX next desc. */ - if (priv->plat->has_gmac4) - ns = priv->hw->desc->get_timestamp(np, priv->adv_ts); - else - ns = priv->hw->desc->get_timestamp(p, priv->adv_ts); - + if (priv->hw->desc->get_rx_timestamp_status(desc, priv->adv_ts)) { + ns = priv->hw->desc->get_timestamp(desc, priv->adv_ts); netdev_dbg(priv->dev, "get valid RX hw timestamp %llu\n", ns); shhwtstamp = skb_hwtstamps(skb); memset(shhwtstamp, 0, sizeof(struct skb_shared_hwtstamps)); @@ -1800,12 +1799,13 @@ static void stmmac_tx_clean(struct stmmac_priv *priv, u32 queue) { struct stmmac_tx_queue *tx_q = &priv->tx_queue[queue]; unsigned int bytes_compl = 0, pkts_compl = 0; - unsigned int entry = tx_q->dirty_tx; + unsigned int entry; netif_tx_lock(priv->dev); priv->xstats.tx_clean++; + entry = tx_q->dirty_tx; while (entry != tx_q->cur_tx) { struct sk_buff *skb = tx_q->tx_skbuff[entry]; struct dma_desc *p; @@ -3333,6 +3333,7 @@ static int stmmac_rx(struct stmmac_priv *priv, int limit, u32 queue) * them in stmmac_rx_refill() function so that * device can reuse it. */ + dev_kfree_skb_any(rx_q->rx_skbuff[entry]); rx_q->rx_skbuff[entry] = NULL; dma_unmap_single(priv->device, rx_q->rx_skbuff_dma[entry], diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c index 8a280b48e3a9..6383695004a5 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c @@ -150,6 +150,13 @@ static void stmmac_mtl_setup(struct platform_device *pdev, plat->rx_queues_to_use = 1; plat->tx_queues_to_use = 1; + /* First Queue must always be in DCB mode. As MTL_QUEUE_DCB = 1 we need + * to always set this, otherwise Queue will be classified as AVB + * (because MTL_QUEUE_AVB = 0). + */ + plat->rx_queues_cfg[0].mode_to_use = MTL_QUEUE_DCB; + plat->tx_queues_cfg[0].mode_to_use = MTL_QUEUE_DCB; + rx_node = of_parse_phandle(pdev->dev.of_node, "snps,mtl-rx-config", 0); if (!rx_node) return; diff --git a/drivers/net/geneve.c b/drivers/net/geneve.c index f6404074b7b0..ed51018a813e 100644 --- a/drivers/net/geneve.c +++ b/drivers/net/geneve.c @@ -113,13 +113,7 @@ static void tunnel_id_to_vni(__be64 tun_id, __u8 *vni) static bool eq_tun_id_and_vni(u8 *tun_id, u8 *vni) { -#ifdef __BIG_ENDIAN - return (vni[0] == tun_id[2]) && - (vni[1] == tun_id[1]) && - (vni[2] == tun_id[0]); -#else return !memcmp(vni, &tun_id[5], 3); -#endif } static sa_family_t geneve_get_sk_family(struct geneve_sock *gs) diff --git a/drivers/net/ipvlan/ipvtap.c b/drivers/net/ipvlan/ipvtap.c index 5dea2063dbc8..0bcc07f346c3 100644 --- a/drivers/net/ipvlan/ipvtap.c +++ b/drivers/net/ipvlan/ipvtap.c @@ -197,8 +197,8 @@ static int ipvtap_init(void) { int err; - err = tap_create_cdev(&ipvtap_cdev, &ipvtap_major, "ipvtap"); - + err = tap_create_cdev(&ipvtap_cdev, &ipvtap_major, "ipvtap", + THIS_MODULE); if (err) goto out1; diff --git a/drivers/net/macvtap.c b/drivers/net/macvtap.c index c2d0ea2fb019..cba5cb3b849a 100644 --- a/drivers/net/macvtap.c +++ b/drivers/net/macvtap.c @@ -204,8 +204,8 @@ static int macvtap_init(void) { int err; - err = tap_create_cdev(&macvtap_cdev, &macvtap_major, "macvtap"); - + err = tap_create_cdev(&macvtap_cdev, &macvtap_major, "macvtap", + THIS_MODULE); if (err) goto out1; diff --git a/drivers/net/phy/marvell.c b/drivers/net/phy/marvell.c index 15cbcdba618a..4d02b27df044 100644 --- a/drivers/net/phy/marvell.c +++ b/drivers/net/phy/marvell.c @@ -681,9 +681,11 @@ static int m88e1116r_config_init(struct phy_device *phydev) if (err < 0) return err; - err = m88e1121_config_aneg_rgmii_delays(phydev); - if (err < 0) - return err; + if (phy_interface_is_rgmii(phydev)) { + err = m88e1121_config_aneg_rgmii_delays(phydev); + if (err < 0) + return err; + } err = genphy_soft_reset(phydev); if (err < 0) diff --git a/drivers/net/tap.c b/drivers/net/tap.c index 21b71ae947fd..6c0c84c33e1f 100644 --- a/drivers/net/tap.c +++ b/drivers/net/tap.c @@ -517,6 +517,10 @@ static int tap_open(struct inode *inode, struct file *file) &tap_proto, 0); if (!q) goto err; + if (skb_array_init(&q->skb_array, tap->dev->tx_queue_len, GFP_KERNEL)) { + sk_free(&q->sk); + goto err; + } RCU_INIT_POINTER(q->sock.wq, &q->wq); init_waitqueue_head(&q->wq.wait); @@ -540,22 +544,18 @@ static int tap_open(struct inode *inode, struct file *file) if ((tap->dev->features & NETIF_F_HIGHDMA) && (tap->dev->features & NETIF_F_SG)) sock_set_flag(&q->sk, SOCK_ZEROCOPY); - err = -ENOMEM; - if (skb_array_init(&q->skb_array, tap->dev->tx_queue_len, GFP_KERNEL)) - goto err_array; - err = tap_set_queue(tap, file, q); - if (err) - goto err_queue; + if (err) { + /* tap_sock_destruct() will take care of freeing skb_array */ + goto err_put; + } dev_put(tap->dev); rtnl_unlock(); return err; -err_queue: - skb_array_cleanup(&q->skb_array); -err_array: +err_put: sock_put(&q->sk); err: if (tap) @@ -1032,6 +1032,8 @@ static long tap_ioctl(struct file *file, unsigned int cmd, case TUNSETSNDBUF: if (get_user(s, sp)) return -EFAULT; + if (s <= 0) + return -EINVAL; q->sk.sk_sndbuf = s; return 0; @@ -1249,8 +1251,8 @@ static int tap_list_add(dev_t major, const char *device_name) return 0; } -int tap_create_cdev(struct cdev *tap_cdev, - dev_t *tap_major, const char *device_name) +int tap_create_cdev(struct cdev *tap_cdev, dev_t *tap_major, + const char *device_name, struct module *module) { int err; @@ -1259,6 +1261,7 @@ int tap_create_cdev(struct cdev *tap_cdev, goto out1; cdev_init(tap_cdev, &tap_fops); + tap_cdev->owner = module; err = cdev_add(tap_cdev, *tap_major, TAP_NUM_DEVS); if (err) goto out2; diff --git a/drivers/net/tun.c b/drivers/net/tun.c index e21bf90b819f..42bb820a56c9 100644 --- a/drivers/net/tun.c +++ b/drivers/net/tun.c @@ -1286,6 +1286,7 @@ static struct sk_buff *tun_build_skb(struct tun_struct *tun, buflen += SKB_DATA_ALIGN(len + pad); rcu_read_unlock(); + alloc_frag->offset = ALIGN((u64)alloc_frag->offset, SMP_CACHE_BYTES); if (unlikely(!skb_page_frag_refill(buflen, alloc_frag, GFP_KERNEL))) return ERR_PTR(-ENOMEM); @@ -2028,7 +2029,7 @@ static int tun_set_iff(struct net *net, struct file *file, struct ifreq *ifr) if (!dev) return -ENOMEM; err = dev_get_valid_name(net, dev, name); - if (err) + if (err < 0) goto err_free_dev; dev_net_set(dev, net); @@ -2428,6 +2429,10 @@ static long __tun_chr_ioctl(struct file *file, unsigned int cmd, ret = -EFAULT; break; } + if (sndbuf <= 0) { + ret = -EINVAL; + break; + } tun->sndbuf = sndbuf; tun_set_sndbuf(tun); diff --git a/drivers/net/usb/cdc_ether.c b/drivers/net/usb/cdc_ether.c index 52ea80bcd639..3e7a3ac3a362 100644 --- a/drivers/net/usb/cdc_ether.c +++ b/drivers/net/usb/cdc_ether.c @@ -561,6 +561,7 @@ static const struct driver_info wwan_info = { #define HP_VENDOR_ID 0x03f0 #define MICROSOFT_VENDOR_ID 0x045e #define UBLOX_VENDOR_ID 0x1546 +#define TPLINK_VENDOR_ID 0x2357 static const struct usb_device_id products[] = { /* BLACKLIST !! @@ -813,6 +814,13 @@ static const struct usb_device_id products[] = { .driver_info = 0, }, + /* TP-LINK UE300 USB 3.0 Ethernet Adapters (based on Realtek RTL8153) */ +{ + USB_DEVICE_AND_INTERFACE_INFO(TPLINK_VENDOR_ID, 0x0601, USB_CLASS_COMM, + USB_CDC_SUBCLASS_ETHERNET, USB_CDC_PROTO_NONE), + .driver_info = 0, +}, + /* WHITELIST!!! * * CDC Ether uses two interfaces, not necessarily consecutive. @@ -864,6 +872,12 @@ static const struct usb_device_id products[] = { USB_CDC_SUBCLASS_ETHERNET, USB_CDC_PROTO_NONE), .driver_info = (kernel_ulong_t)&wwan_info, }, { + /* Huawei ME906 and ME909 */ + USB_DEVICE_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0x15c1, USB_CLASS_COMM, + USB_CDC_SUBCLASS_ETHERNET, + USB_CDC_PROTO_NONE), + .driver_info = (unsigned long)&wwan_info, +}, { /* ZTE modules */ USB_VENDOR_AND_INTERFACE_INFO(ZTE_VENDOR_ID, USB_CLASS_COMM, USB_CDC_SUBCLASS_ETHERNET, diff --git a/drivers/net/usb/r8152.c b/drivers/net/usb/r8152.c index 941ece08ba78..d51d9abf7986 100644 --- a/drivers/net/usb/r8152.c +++ b/drivers/net/usb/r8152.c @@ -615,6 +615,7 @@ enum rtl8152_flags { #define VENDOR_ID_LENOVO 0x17ef #define VENDOR_ID_LINKSYS 0x13b1 #define VENDOR_ID_NVIDIA 0x0955 +#define VENDOR_ID_TPLINK 0x2357 #define MCU_TYPE_PLA 0x0100 #define MCU_TYPE_USB 0x0000 @@ -5319,6 +5320,7 @@ static const struct usb_device_id rtl8152_table[] = { {REALTEK_USB_DEVICE(VENDOR_ID_LENOVO, 0x7214)}, {REALTEK_USB_DEVICE(VENDOR_ID_LINKSYS, 0x0041)}, {REALTEK_USB_DEVICE(VENDOR_ID_NVIDIA, 0x09ff)}, + {REALTEK_USB_DEVICE(VENDOR_ID_TPLINK, 0x0601)}, {} }; diff --git a/drivers/net/vrf.c b/drivers/net/vrf.c index 9b243e6f3008..7dc3bcac3506 100644 --- a/drivers/net/vrf.c +++ b/drivers/net/vrf.c @@ -1165,7 +1165,7 @@ static int vrf_fib_rule(const struct net_device *dev, __u8 family, bool add_it) frh->family = family; frh->action = FR_ACT_TO_TBL; - if (nla_put_u32(skb, FRA_L3MDEV, 1)) + if (nla_put_u8(skb, FRA_L3MDEV, 1)) goto nla_put_failure; if (nla_put_u32(skb, FRA_PRIORITY, FIB_RULE_PREF)) diff --git a/drivers/net/wan/lapbether.c b/drivers/net/wan/lapbether.c index 63f749078a1f..0e3f8ed84660 100644 --- a/drivers/net/wan/lapbether.c +++ b/drivers/net/wan/lapbether.c @@ -346,7 +346,6 @@ out: fail: dev_put(dev); free_netdev(ndev); - kfree(lapbeth); goto out; } diff --git a/drivers/net/wireless/ath/ath10k/htt_rx.c b/drivers/net/wireless/ath/ath10k/htt_rx.c index a3f5dc78353f..0aeeb233af78 100644 --- a/drivers/net/wireless/ath/ath10k/htt_rx.c +++ b/drivers/net/wireless/ath/ath10k/htt_rx.c @@ -550,6 +550,11 @@ static int ath10k_htt_rx_crypto_param_len(struct ath10k *ar, return IEEE80211_TKIP_IV_LEN; case HTT_RX_MPDU_ENCRYPT_AES_CCM_WPA2: return IEEE80211_CCMP_HDR_LEN; + case HTT_RX_MPDU_ENCRYPT_AES_CCM256_WPA2: + return IEEE80211_CCMP_256_HDR_LEN; + case HTT_RX_MPDU_ENCRYPT_AES_GCMP_WPA2: + case HTT_RX_MPDU_ENCRYPT_AES_GCMP256_WPA2: + return IEEE80211_GCMP_HDR_LEN; case HTT_RX_MPDU_ENCRYPT_WEP128: case HTT_RX_MPDU_ENCRYPT_WAPI: break; @@ -575,6 +580,11 @@ static int ath10k_htt_rx_crypto_tail_len(struct ath10k *ar, return IEEE80211_TKIP_ICV_LEN; case HTT_RX_MPDU_ENCRYPT_AES_CCM_WPA2: return IEEE80211_CCMP_MIC_LEN; + case HTT_RX_MPDU_ENCRYPT_AES_CCM256_WPA2: + return IEEE80211_CCMP_256_MIC_LEN; + case HTT_RX_MPDU_ENCRYPT_AES_GCMP_WPA2: + case HTT_RX_MPDU_ENCRYPT_AES_GCMP256_WPA2: + return IEEE80211_GCMP_MIC_LEN; case HTT_RX_MPDU_ENCRYPT_WEP128: case HTT_RX_MPDU_ENCRYPT_WAPI: break; @@ -1051,9 +1061,21 @@ static void ath10k_htt_rx_h_undecap_raw(struct ath10k *ar, hdr = (void *)msdu->data; /* Tail */ - if (status->flag & RX_FLAG_IV_STRIPPED) + if (status->flag & RX_FLAG_IV_STRIPPED) { skb_trim(msdu, msdu->len - ath10k_htt_rx_crypto_tail_len(ar, enctype)); + } else { + /* MIC */ + if ((status->flag & RX_FLAG_MIC_STRIPPED) && + enctype == HTT_RX_MPDU_ENCRYPT_AES_CCM_WPA2) + skb_trim(msdu, msdu->len - 8); + + /* ICV */ + if (status->flag & RX_FLAG_ICV_STRIPPED && + enctype != HTT_RX_MPDU_ENCRYPT_AES_CCM_WPA2) + skb_trim(msdu, msdu->len - + ath10k_htt_rx_crypto_tail_len(ar, enctype)); + } /* MMIC */ if ((status->flag & RX_FLAG_MMIC_STRIPPED) && @@ -1075,7 +1097,8 @@ static void ath10k_htt_rx_h_undecap_raw(struct ath10k *ar, static void ath10k_htt_rx_h_undecap_nwifi(struct ath10k *ar, struct sk_buff *msdu, struct ieee80211_rx_status *status, - const u8 first_hdr[64]) + const u8 first_hdr[64], + enum htt_rx_mpdu_encrypt_type enctype) { struct ieee80211_hdr *hdr; struct htt_rx_desc *rxd; @@ -1083,6 +1106,7 @@ static void ath10k_htt_rx_h_undecap_nwifi(struct ath10k *ar, u8 da[ETH_ALEN]; u8 sa[ETH_ALEN]; int l3_pad_bytes; + int bytes_aligned = ar->hw_params.decap_align_bytes; /* Delivered decapped frame: * [nwifi 802.11 header] <-- replaced with 802.11 hdr @@ -1111,6 +1135,14 @@ static void ath10k_htt_rx_h_undecap_nwifi(struct ath10k *ar, /* push original 802.11 header */ hdr = (struct ieee80211_hdr *)first_hdr; hdr_len = ieee80211_hdrlen(hdr->frame_control); + + if (!(status->flag & RX_FLAG_IV_STRIPPED)) { + memcpy(skb_push(msdu, + ath10k_htt_rx_crypto_param_len(ar, enctype)), + (void *)hdr + round_up(hdr_len, bytes_aligned), + ath10k_htt_rx_crypto_param_len(ar, enctype)); + } + memcpy(skb_push(msdu, hdr_len), hdr, hdr_len); /* original 802.11 header has a different DA and in @@ -1171,6 +1203,7 @@ static void ath10k_htt_rx_h_undecap_eth(struct ath10k *ar, u8 sa[ETH_ALEN]; int l3_pad_bytes; struct htt_rx_desc *rxd; + int bytes_aligned = ar->hw_params.decap_align_bytes; /* Delivered decapped frame: * [eth header] <-- replaced with 802.11 hdr & rfc1042/llc @@ -1199,6 +1232,14 @@ static void ath10k_htt_rx_h_undecap_eth(struct ath10k *ar, /* push original 802.11 header */ hdr = (struct ieee80211_hdr *)first_hdr; hdr_len = ieee80211_hdrlen(hdr->frame_control); + + if (!(status->flag & RX_FLAG_IV_STRIPPED)) { + memcpy(skb_push(msdu, + ath10k_htt_rx_crypto_param_len(ar, enctype)), + (void *)hdr + round_up(hdr_len, bytes_aligned), + ath10k_htt_rx_crypto_param_len(ar, enctype)); + } + memcpy(skb_push(msdu, hdr_len), hdr, hdr_len); /* original 802.11 header has a different DA and in @@ -1212,12 +1253,14 @@ static void ath10k_htt_rx_h_undecap_eth(struct ath10k *ar, static void ath10k_htt_rx_h_undecap_snap(struct ath10k *ar, struct sk_buff *msdu, struct ieee80211_rx_status *status, - const u8 first_hdr[64]) + const u8 first_hdr[64], + enum htt_rx_mpdu_encrypt_type enctype) { struct ieee80211_hdr *hdr; size_t hdr_len; int l3_pad_bytes; struct htt_rx_desc *rxd; + int bytes_aligned = ar->hw_params.decap_align_bytes; /* Delivered decapped frame: * [amsdu header] <-- replaced with 802.11 hdr @@ -1233,6 +1276,14 @@ static void ath10k_htt_rx_h_undecap_snap(struct ath10k *ar, hdr = (struct ieee80211_hdr *)first_hdr; hdr_len = ieee80211_hdrlen(hdr->frame_control); + + if (!(status->flag & RX_FLAG_IV_STRIPPED)) { + memcpy(skb_push(msdu, + ath10k_htt_rx_crypto_param_len(ar, enctype)), + (void *)hdr + round_up(hdr_len, bytes_aligned), + ath10k_htt_rx_crypto_param_len(ar, enctype)); + } + memcpy(skb_push(msdu, hdr_len), hdr, hdr_len); } @@ -1267,13 +1318,15 @@ static void ath10k_htt_rx_h_undecap(struct ath10k *ar, is_decrypted); break; case RX_MSDU_DECAP_NATIVE_WIFI: - ath10k_htt_rx_h_undecap_nwifi(ar, msdu, status, first_hdr); + ath10k_htt_rx_h_undecap_nwifi(ar, msdu, status, first_hdr, + enctype); break; case RX_MSDU_DECAP_ETHERNET2_DIX: ath10k_htt_rx_h_undecap_eth(ar, msdu, status, first_hdr, enctype); break; case RX_MSDU_DECAP_8023_SNAP_LLC: - ath10k_htt_rx_h_undecap_snap(ar, msdu, status, first_hdr); + ath10k_htt_rx_h_undecap_snap(ar, msdu, status, first_hdr, + enctype); break; } } @@ -1316,7 +1369,8 @@ static void ath10k_htt_rx_h_csum_offload(struct sk_buff *msdu) static void ath10k_htt_rx_h_mpdu(struct ath10k *ar, struct sk_buff_head *amsdu, - struct ieee80211_rx_status *status) + struct ieee80211_rx_status *status, + bool fill_crypt_header) { struct sk_buff *first; struct sk_buff *last; @@ -1326,7 +1380,6 @@ static void ath10k_htt_rx_h_mpdu(struct ath10k *ar, enum htt_rx_mpdu_encrypt_type enctype; u8 first_hdr[64]; u8 *qos; - size_t hdr_len; bool has_fcs_err; bool has_crypto_err; bool has_tkip_err; @@ -1351,15 +1404,17 @@ static void ath10k_htt_rx_h_mpdu(struct ath10k *ar, * decapped header. It'll be used for undecapping of each MSDU. */ hdr = (void *)rxd->rx_hdr_status; - hdr_len = ieee80211_hdrlen(hdr->frame_control); - memcpy(first_hdr, hdr, hdr_len); + memcpy(first_hdr, hdr, RX_HTT_HDR_STATUS_LEN); /* Each A-MSDU subframe will use the original header as the base and be * reported as a separate MSDU so strip the A-MSDU bit from QoS Ctl. */ hdr = (void *)first_hdr; - qos = ieee80211_get_qos_ctl(hdr); - qos[0] &= ~IEEE80211_QOS_CTL_A_MSDU_PRESENT; + + if (ieee80211_is_data_qos(hdr->frame_control)) { + qos = ieee80211_get_qos_ctl(hdr); + qos[0] &= ~IEEE80211_QOS_CTL_A_MSDU_PRESENT; + } /* Some attention flags are valid only in the last MSDU. */ last = skb_peek_tail(amsdu); @@ -1406,9 +1461,14 @@ static void ath10k_htt_rx_h_mpdu(struct ath10k *ar, status->flag |= RX_FLAG_DECRYPTED; if (likely(!is_mgmt)) - status->flag |= RX_FLAG_IV_STRIPPED | - RX_FLAG_MMIC_STRIPPED; -} + status->flag |= RX_FLAG_MMIC_STRIPPED; + + if (fill_crypt_header) + status->flag |= RX_FLAG_MIC_STRIPPED | + RX_FLAG_ICV_STRIPPED; + else + status->flag |= RX_FLAG_IV_STRIPPED; + } skb_queue_walk(amsdu, msdu) { ath10k_htt_rx_h_csum_offload(msdu); @@ -1424,6 +1484,9 @@ static void ath10k_htt_rx_h_mpdu(struct ath10k *ar, if (is_mgmt) continue; + if (fill_crypt_header) + continue; + hdr = (void *)msdu->data; hdr->frame_control &= ~__cpu_to_le16(IEEE80211_FCTL_PROTECTED); } @@ -1434,6 +1497,9 @@ static void ath10k_htt_rx_h_deliver(struct ath10k *ar, struct ieee80211_rx_status *status) { struct sk_buff *msdu; + struct sk_buff *first_subframe; + + first_subframe = skb_peek(amsdu); while ((msdu = __skb_dequeue(amsdu))) { /* Setup per-MSDU flags */ @@ -1442,6 +1508,13 @@ static void ath10k_htt_rx_h_deliver(struct ath10k *ar, else status->flag |= RX_FLAG_AMSDU_MORE; + if (msdu == first_subframe) { + first_subframe = NULL; + status->flag &= ~RX_FLAG_ALLOW_SAME_PN; + } else { + status->flag |= RX_FLAG_ALLOW_SAME_PN; + } + ath10k_process_rx(ar, status, msdu); } } @@ -1584,7 +1657,7 @@ static int ath10k_htt_rx_handle_amsdu(struct ath10k_htt *htt) ath10k_htt_rx_h_unchain(ar, &amsdu); ath10k_htt_rx_h_filter(ar, &amsdu, rx_status); - ath10k_htt_rx_h_mpdu(ar, &amsdu, rx_status); + ath10k_htt_rx_h_mpdu(ar, &amsdu, rx_status, true); ath10k_htt_rx_h_deliver(ar, &amsdu, rx_status); return num_msdus; @@ -1745,8 +1818,7 @@ static void ath10k_htt_rx_delba(struct ath10k *ar, struct htt_resp *resp) } static int ath10k_htt_rx_extract_amsdu(struct sk_buff_head *list, - struct sk_buff_head *amsdu, - int budget_left) + struct sk_buff_head *amsdu) { struct sk_buff *msdu; struct htt_rx_desc *rxd; @@ -1757,9 +1829,8 @@ static int ath10k_htt_rx_extract_amsdu(struct sk_buff_head *list, if (WARN_ON(!skb_queue_empty(amsdu))) return -EINVAL; - while ((msdu = __skb_dequeue(list)) && budget_left) { + while ((msdu = __skb_dequeue(list))) { __skb_queue_tail(amsdu, msdu); - budget_left--; rxd = (void *)msdu->data - sizeof(*rxd); if (rxd->msdu_end.common.info0 & @@ -1850,8 +1921,7 @@ static int ath10k_htt_rx_h_rx_offload(struct ath10k *ar, return num_msdu; } -static int ath10k_htt_rx_in_ord_ind(struct ath10k *ar, struct sk_buff *skb, - int budget_left) +static int ath10k_htt_rx_in_ord_ind(struct ath10k *ar, struct sk_buff *skb) { struct ath10k_htt *htt = &ar->htt; struct htt_resp *resp = (void *)skb->data; @@ -1908,9 +1978,9 @@ static int ath10k_htt_rx_in_ord_ind(struct ath10k *ar, struct sk_buff *skb, if (offload) num_msdus = ath10k_htt_rx_h_rx_offload(ar, &list); - while (!skb_queue_empty(&list) && budget_left) { + while (!skb_queue_empty(&list)) { __skb_queue_head_init(&amsdu); - ret = ath10k_htt_rx_extract_amsdu(&list, &amsdu, budget_left); + ret = ath10k_htt_rx_extract_amsdu(&list, &amsdu); switch (ret) { case 0: /* Note: The in-order indication may report interleaved @@ -1920,10 +1990,9 @@ static int ath10k_htt_rx_in_ord_ind(struct ath10k *ar, struct sk_buff *skb, * should still give an idea about rx rate to the user. */ num_msdus += skb_queue_len(&amsdu); - budget_left -= skb_queue_len(&amsdu); ath10k_htt_rx_h_ppdu(ar, &amsdu, status, vdev_id); ath10k_htt_rx_h_filter(ar, &amsdu, status); - ath10k_htt_rx_h_mpdu(ar, &amsdu, status); + ath10k_htt_rx_h_mpdu(ar, &amsdu, status, false); ath10k_htt_rx_h_deliver(ar, &amsdu, status); break; case -EAGAIN: @@ -2563,8 +2632,7 @@ int ath10k_htt_txrx_compl_task(struct ath10k *ar, int budget) } spin_lock_bh(&htt->rx_ring.lock); - num_rx_msdus = ath10k_htt_rx_in_ord_ind(ar, skb, - (budget - quota)); + num_rx_msdus = ath10k_htt_rx_in_ord_ind(ar, skb); spin_unlock_bh(&htt->rx_ring.lock); if (num_rx_msdus < 0) { resched_napi = true; diff --git a/drivers/net/wireless/ath/ath10k/rx_desc.h b/drivers/net/wireless/ath/ath10k/rx_desc.h index c1022a1cf855..28da14398951 100644 --- a/drivers/net/wireless/ath/ath10k/rx_desc.h +++ b/drivers/net/wireless/ath/ath10k/rx_desc.h @@ -239,6 +239,9 @@ enum htt_rx_mpdu_encrypt_type { HTT_RX_MPDU_ENCRYPT_WAPI = 5, HTT_RX_MPDU_ENCRYPT_AES_CCM_WPA2 = 6, HTT_RX_MPDU_ENCRYPT_NONE = 7, + HTT_RX_MPDU_ENCRYPT_AES_CCM256_WPA2 = 8, + HTT_RX_MPDU_ENCRYPT_AES_GCMP_WPA2 = 9, + HTT_RX_MPDU_ENCRYPT_AES_GCMP256_WPA2 = 10, }; #define RX_MPDU_START_INFO0_PEER_IDX_MASK 0x000007ff diff --git a/drivers/net/wireless/ath/wcn36xx/main.c b/drivers/net/wireless/ath/wcn36xx/main.c index 35bd50bcbbd5..b83f01d6e3dd 100644 --- a/drivers/net/wireless/ath/wcn36xx/main.c +++ b/drivers/net/wireless/ath/wcn36xx/main.c @@ -812,7 +812,6 @@ static void wcn36xx_bss_info_changed(struct ieee80211_hw *hw, if (!sta) { wcn36xx_err("sta %pM is not found\n", bss_conf->bssid); - rcu_read_unlock(); goto out; } sta_priv = wcn36xx_sta_to_priv(sta); diff --git a/drivers/net/xen-netback/interface.c b/drivers/net/xen-netback/interface.c index ee8ed9da00ad..4491ca5aee90 100644 --- a/drivers/net/xen-netback/interface.c +++ b/drivers/net/xen-netback/interface.c @@ -486,7 +486,7 @@ struct xenvif *xenvif_alloc(struct device *parent, domid_t domid, dev->tx_queue_len = XENVIF_QUEUE_LENGTH; - dev->min_mtu = 0; + dev->min_mtu = ETH_MIN_MTU; dev->max_mtu = ETH_MAX_MTU - VLAN_ETH_HLEN; /* diff --git a/drivers/net/xen-netfront.c b/drivers/net/xen-netfront.c index 523387e71a80..8b8689c6d887 100644 --- a/drivers/net/xen-netfront.c +++ b/drivers/net/xen-netfront.c @@ -1316,7 +1316,7 @@ static struct net_device *xennet_create_dev(struct xenbus_device *dev) netdev->features |= netdev->hw_features; netdev->ethtool_ops = &xennet_ethtool_ops; - netdev->min_mtu = 0; + netdev->min_mtu = ETH_MIN_MTU; netdev->max_mtu = XEN_NETIF_MAX_TX_SIZE; SET_NETDEV_DEV(netdev, &dev->dev); diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index 5a14cc7f28ee..37f9039bb9ca 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -1249,6 +1249,7 @@ static int nvme_revalidate_disk(struct gendisk *disk) goto out; } + __nvme_revalidate_disk(disk, id); nvme_report_ns_ids(ctrl, ns->ns_id, id, eui64, nguid, &uuid); if (!uuid_equal(&ns->uuid, &uuid) || memcmp(&ns->nguid, &nguid, sizeof(ns->nguid)) || diff --git a/drivers/nvme/host/fc.c b/drivers/nvme/host/fc.c index af075e998944..be49d0f79381 100644 --- a/drivers/nvme/host/fc.c +++ b/drivers/nvme/host/fc.c @@ -2545,10 +2545,10 @@ nvme_fc_delete_association(struct nvme_fc_ctrl *ctrl) nvme_fc_abort_aen_ops(ctrl); /* wait for all io that had to be aborted */ - spin_lock_irqsave(&ctrl->lock, flags); + spin_lock_irq(&ctrl->lock); wait_event_lock_irq(ctrl->ioabort_wait, ctrl->iocnt == 0, ctrl->lock); ctrl->flags &= ~FCCTRL_TERMIO; - spin_unlock_irqrestore(&ctrl->lock, flags); + spin_unlock_irq(&ctrl->lock); nvme_fc_term_aen_ops(ctrl); @@ -2734,7 +2734,7 @@ nvme_fc_init_ctrl(struct device *dev, struct nvmf_ctrl_options *opts, { struct nvme_fc_ctrl *ctrl; unsigned long flags; - int ret, idx; + int ret, idx, retry; if (!(rport->remoteport.port_role & (FC_PORT_ROLE_NVME_DISCOVERY | FC_PORT_ROLE_NVME_TARGET))) { @@ -2760,6 +2760,7 @@ nvme_fc_init_ctrl(struct device *dev, struct nvmf_ctrl_options *opts, ctrl->rport = rport; ctrl->dev = lport->dev; ctrl->cnum = idx; + init_waitqueue_head(&ctrl->ioabort_wait); get_device(ctrl->dev); kref_init(&ctrl->ref); @@ -2825,9 +2826,37 @@ nvme_fc_init_ctrl(struct device *dev, struct nvmf_ctrl_options *opts, list_add_tail(&ctrl->ctrl_list, &rport->ctrl_list); spin_unlock_irqrestore(&rport->lock, flags); - ret = nvme_fc_create_association(ctrl); + /* + * It's possible that transactions used to create the association + * may fail. Examples: CreateAssociation LS or CreateIOConnection + * LS gets dropped/corrupted/fails; or a frame gets dropped or a + * command times out for one of the actions to init the controller + * (Connect, Get/Set_Property, Set_Features, etc). Many of these + * transport errors (frame drop, LS failure) inherently must kill + * the association. The transport is coded so that any command used + * to create the association (prior to a LIVE state transition + * while NEW or RECONNECTING) will fail if it completes in error or + * times out. + * + * As such: as the connect request was mostly likely due to a + * udev event that discovered the remote port, meaning there is + * not an admin or script there to restart if the connect + * request fails, retry the initial connection creation up to + * three times before giving up and declaring failure. + */ + for (retry = 0; retry < 3; retry++) { + ret = nvme_fc_create_association(ctrl); + if (!ret) + break; + } + if (ret) { + /* couldn't schedule retry - fail out */ + dev_err(ctrl->ctrl.device, + "NVME-FC{%d}: Connect retry failed\n", ctrl->cnum); + ctrl->ctrl.opts = NULL; + /* initiate nvme ctrl ref counting teardown */ nvme_uninit_ctrl(&ctrl->ctrl); nvme_put_ctrl(&ctrl->ctrl); diff --git a/drivers/nvme/host/rdma.c b/drivers/nvme/host/rdma.c index 92a03ff5fb4d..0ebb539f3bd3 100644 --- a/drivers/nvme/host/rdma.c +++ b/drivers/nvme/host/rdma.c @@ -571,6 +571,12 @@ static void nvme_rdma_free_queue(struct nvme_rdma_queue *queue) if (test_and_set_bit(NVME_RDMA_Q_DELETING, &queue->flags)) return; + if (nvme_rdma_queue_idx(queue) == 0) { + nvme_rdma_free_qe(queue->device->dev, + &queue->ctrl->async_event_sqe, + sizeof(struct nvme_command), DMA_TO_DEVICE); + } + nvme_rdma_destroy_queue_ib(queue); rdma_destroy_id(queue->cm_id); } @@ -739,8 +745,6 @@ out: static void nvme_rdma_destroy_admin_queue(struct nvme_rdma_ctrl *ctrl, bool remove) { - nvme_rdma_free_qe(ctrl->queues[0].device->dev, &ctrl->async_event_sqe, - sizeof(struct nvme_command), DMA_TO_DEVICE); nvme_rdma_stop_queue(&ctrl->queues[0]); if (remove) { blk_cleanup_queue(ctrl->ctrl.admin_q); @@ -765,8 +769,10 @@ static int nvme_rdma_configure_admin_queue(struct nvme_rdma_ctrl *ctrl, if (new) { ctrl->ctrl.admin_tagset = nvme_rdma_alloc_tagset(&ctrl->ctrl, true); - if (IS_ERR(ctrl->ctrl.admin_tagset)) + if (IS_ERR(ctrl->ctrl.admin_tagset)) { + error = PTR_ERR(ctrl->ctrl.admin_tagset); goto out_free_queue; + } ctrl->ctrl.admin_q = blk_mq_init_queue(&ctrl->admin_tag_set); if (IS_ERR(ctrl->ctrl.admin_q)) { @@ -846,8 +852,10 @@ static int nvme_rdma_configure_io_queues(struct nvme_rdma_ctrl *ctrl, bool new) if (new) { ctrl->ctrl.tagset = nvme_rdma_alloc_tagset(&ctrl->ctrl, false); - if (IS_ERR(ctrl->ctrl.tagset)) + if (IS_ERR(ctrl->ctrl.tagset)) { + ret = PTR_ERR(ctrl->ctrl.tagset); goto out_free_io_queues; + } ctrl->ctrl.connect_q = blk_mq_init_queue(&ctrl->tag_set); if (IS_ERR(ctrl->ctrl.connect_q)) { @@ -1606,12 +1614,15 @@ nvme_rdma_queue_is_ready(struct nvme_rdma_queue *queue, struct request *rq) /* * reconnecting state means transport disruption, which * can take a long time and even might fail permanently, - * so we can't let incoming I/O be requeued forever. - * fail it fast to allow upper layers a chance to - * failover. + * fail fast to give upper layers a chance to failover. + * deleting state means that the ctrl will never accept + * commands again, fail it permanently. */ - if (queue->ctrl->ctrl.state == NVME_CTRL_RECONNECTING) + if (queue->ctrl->ctrl.state == NVME_CTRL_RECONNECTING || + queue->ctrl->ctrl.state == NVME_CTRL_DELETING) { + nvme_req(rq)->status = NVME_SC_ABORT_REQ; return BLK_STS_IOERR; + } return BLK_STS_RESOURCE; /* try again later */ } } diff --git a/drivers/nvme/target/core.c b/drivers/nvme/target/core.c index 1b208beeef50..645ba7eee35d 100644 --- a/drivers/nvme/target/core.c +++ b/drivers/nvme/target/core.c @@ -387,12 +387,21 @@ struct nvmet_ns *nvmet_ns_alloc(struct nvmet_subsys *subsys, u32 nsid) static void __nvmet_req_complete(struct nvmet_req *req, u16 status) { + u32 old_sqhd, new_sqhd; + u16 sqhd; + if (status) nvmet_set_status(req, status); - if (req->sq->size) - req->sq->sqhd = (req->sq->sqhd + 1) % req->sq->size; - req->rsp->sq_head = cpu_to_le16(req->sq->sqhd); + if (req->sq->size) { + do { + old_sqhd = req->sq->sqhd; + new_sqhd = (old_sqhd + 1) % req->sq->size; + } while (cmpxchg(&req->sq->sqhd, old_sqhd, new_sqhd) != + old_sqhd); + } + sqhd = req->sq->sqhd & 0x0000FFFF; + req->rsp->sq_head = cpu_to_le16(sqhd); req->rsp->sq_id = cpu_to_le16(req->sq->qid); req->rsp->command_id = req->cmd->common.command_id; diff --git a/drivers/nvme/target/nvmet.h b/drivers/nvme/target/nvmet.h index 7b8e20adf760..87e429bfcd8a 100644 --- a/drivers/nvme/target/nvmet.h +++ b/drivers/nvme/target/nvmet.h @@ -74,7 +74,7 @@ struct nvmet_sq { struct percpu_ref ref; u16 qid; u16 size; - u16 sqhd; + u32 sqhd; struct completion free_done; struct completion confirm_done; }; diff --git a/drivers/of/base.c b/drivers/of/base.c index 260d33c0f26c..63897531cd75 100644 --- a/drivers/of/base.c +++ b/drivers/of/base.c @@ -1781,8 +1781,12 @@ bool of_console_check(struct device_node *dn, char *name, int index) { if (!dn || dn != of_stdout || console_set_on_cmdline) return false; - return !add_preferred_console(name, index, - kstrdup(of_stdout_options, GFP_KERNEL)); + + /* + * XXX: cast `options' to char pointer to suppress complication + * warnings: printk, UART and console drivers expect char pointer. + */ + return !add_preferred_console(name, index, (char *)of_stdout_options); } EXPORT_SYMBOL_GPL(of_console_check); diff --git a/drivers/of/of_mdio.c b/drivers/of/of_mdio.c index d94dd8b77abd..98258583abb0 100644 --- a/drivers/of/of_mdio.c +++ b/drivers/of/of_mdio.c @@ -44,7 +44,7 @@ static int of_get_phy_id(struct device_node *device, u32 *phy_id) return -EINVAL; } -static void of_mdiobus_register_phy(struct mii_bus *mdio, +static int of_mdiobus_register_phy(struct mii_bus *mdio, struct device_node *child, u32 addr) { struct phy_device *phy; @@ -60,9 +60,13 @@ static void of_mdiobus_register_phy(struct mii_bus *mdio, else phy = get_phy_device(mdio, addr, is_c45); if (IS_ERR(phy)) - return; + return PTR_ERR(phy); - rc = irq_of_parse_and_map(child, 0); + rc = of_irq_get(child, 0); + if (rc == -EPROBE_DEFER) { + phy_device_free(phy); + return rc; + } if (rc > 0) { phy->irq = rc; mdio->irq[addr] = rc; @@ -84,22 +88,23 @@ static void of_mdiobus_register_phy(struct mii_bus *mdio, if (rc) { phy_device_free(phy); of_node_put(child); - return; + return rc; } dev_dbg(&mdio->dev, "registered phy %s at address %i\n", child->name, addr); + return 0; } -static void of_mdiobus_register_device(struct mii_bus *mdio, - struct device_node *child, u32 addr) +static int of_mdiobus_register_device(struct mii_bus *mdio, + struct device_node *child, u32 addr) { struct mdio_device *mdiodev; int rc; mdiodev = mdio_device_create(mdio, addr); if (IS_ERR(mdiodev)) - return; + return PTR_ERR(mdiodev); /* Associate the OF node with the device structure so it * can be looked up later. @@ -112,11 +117,12 @@ static void of_mdiobus_register_device(struct mii_bus *mdio, if (rc) { mdio_device_free(mdiodev); of_node_put(child); - return; + return rc; } dev_dbg(&mdio->dev, "registered mdio device %s at address %i\n", child->name, addr); + return 0; } /* The following is a list of PHY compatible strings which appear in @@ -219,9 +225,11 @@ int of_mdiobus_register(struct mii_bus *mdio, struct device_node *np) } if (of_mdiobus_child_is_phy(child)) - of_mdiobus_register_phy(mdio, child, addr); + rc = of_mdiobus_register_phy(mdio, child, addr); else - of_mdiobus_register_device(mdio, child, addr); + rc = of_mdiobus_register_device(mdio, child, addr); + if (rc) + goto unregister; } if (!scanphys) @@ -242,12 +250,19 @@ int of_mdiobus_register(struct mii_bus *mdio, struct device_node *np) dev_info(&mdio->dev, "scan phy %s at address %i\n", child->name, addr); - if (of_mdiobus_child_is_phy(child)) - of_mdiobus_register_phy(mdio, child, addr); + if (of_mdiobus_child_is_phy(child)) { + rc = of_mdiobus_register_phy(mdio, child, addr); + if (rc) + goto unregister; + } } } return 0; + +unregister: + mdiobus_unregister(mdio); + return rc; } EXPORT_SYMBOL(of_mdiobus_register); diff --git a/drivers/of/of_reserved_mem.c b/drivers/of/of_reserved_mem.c index d507c3569a88..32771c2ced7b 100644 --- a/drivers/of/of_reserved_mem.c +++ b/drivers/of/of_reserved_mem.c @@ -25,7 +25,7 @@ #include <linux/sort.h> #include <linux/slab.h> -#define MAX_RESERVED_REGIONS 16 +#define MAX_RESERVED_REGIONS 32 static struct reserved_mem reserved_mem[MAX_RESERVED_REGIONS]; static int reserved_mem_count; diff --git a/drivers/of/property.c b/drivers/of/property.c index fbb72116e9d4..264c355ba1ff 100644 --- a/drivers/of/property.c +++ b/drivers/of/property.c @@ -954,7 +954,7 @@ of_fwnode_graph_get_port_parent(struct fwnode_handle *fwnode) struct device_node *np; /* Get the parent of the port */ - np = of_get_next_parent(to_of_node(fwnode)); + np = of_get_parent(to_of_node(fwnode)); if (!np) return NULL; diff --git a/drivers/pci/host/pci-aardvark.c b/drivers/pci/host/pci-aardvark.c index 89f4e3d072d7..26ed0c08f209 100644 --- a/drivers/pci/host/pci-aardvark.c +++ b/drivers/pci/host/pci-aardvark.c @@ -935,6 +935,8 @@ static int advk_pcie_probe(struct platform_device *pdev) bridge->sysdata = pcie; bridge->busnr = 0; bridge->ops = &advk_pcie_ops; + bridge->map_irq = of_irq_parse_and_map_pci; + bridge->swizzle_irq = pci_common_swizzle; ret = pci_scan_root_bus_bridge(bridge); if (ret < 0) { diff --git a/drivers/pci/host/pci-tegra.c b/drivers/pci/host/pci-tegra.c index 9c40da54f88a..1987fec1f126 100644 --- a/drivers/pci/host/pci-tegra.c +++ b/drivers/pci/host/pci-tegra.c @@ -233,6 +233,7 @@ struct tegra_msi { struct msi_controller chip; DECLARE_BITMAP(used, INT_PCI_MSI_NR); struct irq_domain *domain; + unsigned long pages; struct mutex lock; u64 phys; int irq; @@ -1529,22 +1530,9 @@ static int tegra_pcie_enable_msi(struct tegra_pcie *pcie) goto err; } - /* - * The PCI host bridge on Tegra contains some logic that intercepts - * MSI writes, which means that the MSI target address doesn't have - * to point to actual physical memory. Rather than allocating one 4 - * KiB page of system memory that's never used, we can simply pick - * an arbitrary address within an area reserved for system memory - * in the FPCI address map. - * - * However, in order to avoid confusion, we pick an address that - * doesn't map to physical memory. The FPCI address map reserves a - * 1012 GiB region for system memory and memory-mapped I/O. Since - * none of the Tegra SoCs that contain this PCI host bridge can - * address more than 16 GiB of system memory, the last 4 KiB of - * these 1012 GiB is a good candidate. - */ - msi->phys = 0xfcfffff000; + /* setup AFI/FPCI range */ + msi->pages = __get_free_pages(GFP_KERNEL, 0); + msi->phys = virt_to_phys((void *)msi->pages); afi_writel(pcie, msi->phys >> soc->msi_base_shift, AFI_MSI_FPCI_BAR_ST); afi_writel(pcie, msi->phys, AFI_MSI_AXI_BAR_ST); @@ -1596,6 +1584,8 @@ static int tegra_pcie_disable_msi(struct tegra_pcie *pcie) afi_writel(pcie, 0, AFI_MSI_EN_VEC6); afi_writel(pcie, 0, AFI_MSI_EN_VEC7); + free_pages(msi->pages, 0); + if (msi->irq > 0) free_irq(msi->irq, pcie); diff --git a/drivers/phy/marvell/phy-mvebu-cp110-comphy.c b/drivers/phy/marvell/phy-mvebu-cp110-comphy.c index 73ebad6634a7..89c887ea5557 100644 --- a/drivers/phy/marvell/phy-mvebu-cp110-comphy.c +++ b/drivers/phy/marvell/phy-mvebu-cp110-comphy.c @@ -111,6 +111,8 @@ #define MVEBU_COMPHY_CONF6_40B BIT(18) #define MVEBU_COMPHY_SELECTOR 0x1140 #define MVEBU_COMPHY_SELECTOR_PHY(n) ((n) * 0x4) +#define MVEBU_COMPHY_PIPE_SELECTOR 0x1144 +#define MVEBU_COMPHY_PIPE_SELECTOR_PIPE(n) ((n) * 0x4) #define MVEBU_COMPHY_LANES 6 #define MVEBU_COMPHY_PORTS 3 @@ -468,13 +470,17 @@ static int mvebu_comphy_power_on(struct phy *phy) { struct mvebu_comphy_lane *lane = phy_get_drvdata(phy); struct mvebu_comphy_priv *priv = lane->priv; - int ret; - u32 mux, val; + int ret, mux; + u32 val; mux = mvebu_comphy_get_mux(lane->id, lane->port, lane->mode); if (mux < 0) return -ENOTSUPP; + regmap_read(priv->regmap, MVEBU_COMPHY_PIPE_SELECTOR, &val); + val &= ~(0xf << MVEBU_COMPHY_PIPE_SELECTOR_PIPE(lane->id)); + regmap_write(priv->regmap, MVEBU_COMPHY_PIPE_SELECTOR, val); + regmap_read(priv->regmap, MVEBU_COMPHY_SELECTOR, &val); val &= ~(0xf << MVEBU_COMPHY_SELECTOR_PHY(lane->id)); val |= mux << MVEBU_COMPHY_SELECTOR_PHY(lane->id); @@ -526,6 +532,10 @@ static int mvebu_comphy_power_off(struct phy *phy) val &= ~(0xf << MVEBU_COMPHY_SELECTOR_PHY(lane->id)); regmap_write(priv->regmap, MVEBU_COMPHY_SELECTOR, val); + regmap_read(priv->regmap, MVEBU_COMPHY_PIPE_SELECTOR, &val); + val &= ~(0xf << MVEBU_COMPHY_PIPE_SELECTOR_PIPE(lane->id)); + regmap_write(priv->regmap, MVEBU_COMPHY_PIPE_SELECTOR, val); + return 0; } @@ -576,8 +586,8 @@ static int mvebu_comphy_probe(struct platform_device *pdev) return PTR_ERR(priv->regmap); res = platform_get_resource(pdev, IORESOURCE_MEM, 0); priv->base = devm_ioremap_resource(&pdev->dev, res); - if (!priv->base) - return -ENOMEM; + if (IS_ERR(priv->base)) + return PTR_ERR(priv->base); for_each_available_child_of_node(pdev->dev.of_node, child) { struct mvebu_comphy_lane *lane; diff --git a/drivers/phy/mediatek/phy-mtk-tphy.c b/drivers/phy/mediatek/phy-mtk-tphy.c index e3baad78521f..721a2a1c97ef 100644 --- a/drivers/phy/mediatek/phy-mtk-tphy.c +++ b/drivers/phy/mediatek/phy-mtk-tphy.c @@ -27,6 +27,7 @@ /* banks shared by multiple phys */ #define SSUSB_SIFSLV_V1_SPLLC 0x000 /* shared by u3 phys */ #define SSUSB_SIFSLV_V1_U2FREQ 0x100 /* shared by u2 phys */ +#define SSUSB_SIFSLV_V1_CHIP 0x300 /* shared by u3 phys */ /* u2 phy bank */ #define SSUSB_SIFSLV_V1_U2PHY_COM 0x000 /* u3/pcie/sata phy banks */ @@ -762,7 +763,7 @@ static void phy_v1_banks_init(struct mtk_tphy *tphy, case PHY_TYPE_USB3: case PHY_TYPE_PCIE: u3_banks->spllc = tphy->sif_base + SSUSB_SIFSLV_V1_SPLLC; - u3_banks->chip = NULL; + u3_banks->chip = tphy->sif_base + SSUSB_SIFSLV_V1_CHIP; u3_banks->phyd = instance->port_base + SSUSB_SIFSLV_V1_U3PHYD; u3_banks->phya = instance->port_base + SSUSB_SIFSLV_V1_U3PHYA; break; diff --git a/drivers/phy/rockchip/phy-rockchip-typec.c b/drivers/phy/rockchip/phy-rockchip-typec.c index 4d2c57f21d76..a958c9bced01 100644 --- a/drivers/phy/rockchip/phy-rockchip-typec.c +++ b/drivers/phy/rockchip/phy-rockchip-typec.c @@ -443,14 +443,34 @@ static inline int property_enable(struct rockchip_typec_phy *tcphy, return regmap_write(tcphy->grf_regs, reg->offset, val | mask); } +static void tcphy_dp_aux_set_flip(struct rockchip_typec_phy *tcphy) +{ + u16 tx_ana_ctrl_reg_1; + + /* + * Select the polarity of the xcvr: + * 1, Reverses the polarity (If TYPEC, Pulls ups aux_p and pull + * down aux_m) + * 0, Normal polarity (if TYPEC, pulls up aux_m and pulls down + * aux_p) + */ + tx_ana_ctrl_reg_1 = readl(tcphy->base + TX_ANA_CTRL_REG_1); + if (!tcphy->flip) + tx_ana_ctrl_reg_1 |= BIT(12); + else + tx_ana_ctrl_reg_1 &= ~BIT(12); + writel(tx_ana_ctrl_reg_1, tcphy->base + TX_ANA_CTRL_REG_1); +} + static void tcphy_dp_aux_calibration(struct rockchip_typec_phy *tcphy) { + u16 tx_ana_ctrl_reg_1; u16 rdata, rdata2, val; /* disable txda_cal_latch_en for rewrite the calibration values */ - rdata = readl(tcphy->base + TX_ANA_CTRL_REG_1); - val = rdata & 0xdfff; - writel(val, tcphy->base + TX_ANA_CTRL_REG_1); + tx_ana_ctrl_reg_1 = readl(tcphy->base + TX_ANA_CTRL_REG_1); + tx_ana_ctrl_reg_1 &= ~BIT(13); + writel(tx_ana_ctrl_reg_1, tcphy->base + TX_ANA_CTRL_REG_1); /* * read a resistor calibration code from CMN_TXPUCAL_CTRL[6:0] and @@ -472,9 +492,8 @@ static void tcphy_dp_aux_calibration(struct rockchip_typec_phy *tcphy) * Activate this signal for 1 clock cycle to sample new calibration * values. */ - rdata = readl(tcphy->base + TX_ANA_CTRL_REG_1); - val = rdata | 0x2000; - writel(val, tcphy->base + TX_ANA_CTRL_REG_1); + tx_ana_ctrl_reg_1 |= BIT(13); + writel(tx_ana_ctrl_reg_1, tcphy->base + TX_ANA_CTRL_REG_1); usleep_range(150, 200); /* set TX Voltage Level and TX Deemphasis to 0 */ @@ -482,8 +501,10 @@ static void tcphy_dp_aux_calibration(struct rockchip_typec_phy *tcphy) /* re-enable decap */ writel(0x100, tcphy->base + TX_ANA_CTRL_REG_2); writel(0x300, tcphy->base + TX_ANA_CTRL_REG_2); - writel(0x2008, tcphy->base + TX_ANA_CTRL_REG_1); - writel(0x2018, tcphy->base + TX_ANA_CTRL_REG_1); + tx_ana_ctrl_reg_1 |= BIT(3); + writel(tx_ana_ctrl_reg_1, tcphy->base + TX_ANA_CTRL_REG_1); + tx_ana_ctrl_reg_1 |= BIT(4); + writel(tx_ana_ctrl_reg_1, tcphy->base + TX_ANA_CTRL_REG_1); writel(0, tcphy->base + TX_ANA_CTRL_REG_5); @@ -494,8 +515,10 @@ static void tcphy_dp_aux_calibration(struct rockchip_typec_phy *tcphy) writel(0x1001, tcphy->base + TX_ANA_CTRL_REG_4); /* re-enables Bandgap reference for LDO */ - writel(0x2098, tcphy->base + TX_ANA_CTRL_REG_1); - writel(0x2198, tcphy->base + TX_ANA_CTRL_REG_1); + tx_ana_ctrl_reg_1 |= BIT(7); + writel(tx_ana_ctrl_reg_1, tcphy->base + TX_ANA_CTRL_REG_1); + tx_ana_ctrl_reg_1 |= BIT(8); + writel(tx_ana_ctrl_reg_1, tcphy->base + TX_ANA_CTRL_REG_1); /* * re-enables the transmitter pre-driver, driver data selection MUX, @@ -505,27 +528,26 @@ static void tcphy_dp_aux_calibration(struct rockchip_typec_phy *tcphy) writel(0x303, tcphy->base + TX_ANA_CTRL_REG_2); /* - * BIT 12: Controls auxda_polarity, which selects the polarity of the - * xcvr: - * 1, Reverses the polarity (If TYPEC, Pulls ups aux_p and pull - * down aux_m) - * 0, Normal polarity (if TYPE_C, pulls up aux_m and pulls down - * aux_p) + * Do some magic undocumented stuff, some of which appears to + * undo the "re-enables Bandgap reference for LDO" above. */ - val = 0xa078; - if (!tcphy->flip) - val |= BIT(12); - writel(val, tcphy->base + TX_ANA_CTRL_REG_1); + tx_ana_ctrl_reg_1 |= BIT(15); + tx_ana_ctrl_reg_1 &= ~BIT(8); + tx_ana_ctrl_reg_1 &= ~BIT(7); + tx_ana_ctrl_reg_1 |= BIT(6); + tx_ana_ctrl_reg_1 |= BIT(5); + writel(tx_ana_ctrl_reg_1, tcphy->base + TX_ANA_CTRL_REG_1); writel(0, tcphy->base + TX_ANA_CTRL_REG_3); writel(0, tcphy->base + TX_ANA_CTRL_REG_4); writel(0, tcphy->base + TX_ANA_CTRL_REG_5); /* - * Controls low_power_swing_en, set the voltage swing of the driver - * to 400mv. The values below are peak to peak (differential) values. + * Controls low_power_swing_en, don't set the voltage swing of the + * driver to 400mv. The values below are peak to peak (differential) + * values. */ - writel(4, tcphy->base + TXDA_COEFF_CALC_CTRL); + writel(0, tcphy->base + TXDA_COEFF_CALC_CTRL); writel(0, tcphy->base + TXDA_CYA_AUXDA_CYA); /* Controls tx_high_z_tm_en */ @@ -555,6 +577,7 @@ static int tcphy_phy_init(struct rockchip_typec_phy *tcphy, u8 mode) reset_control_deassert(tcphy->tcphy_rst); property_enable(tcphy, &cfg->typec_conn_dir, tcphy->flip); + tcphy_dp_aux_set_flip(tcphy); tcphy_cfg_24m(tcphy); @@ -685,8 +708,11 @@ static int rockchip_usb3_phy_power_on(struct phy *phy) if (tcphy->mode == new_mode) goto unlock_ret; - if (tcphy->mode == MODE_DISCONNECT) - tcphy_phy_init(tcphy, new_mode); + if (tcphy->mode == MODE_DISCONNECT) { + ret = tcphy_phy_init(tcphy, new_mode); + if (ret) + goto unlock_ret; + } /* wait TCPHY for pipe ready */ for (timeout = 0; timeout < 100; timeout++) { @@ -760,10 +786,12 @@ static int rockchip_dp_phy_power_on(struct phy *phy) */ if (new_mode == MODE_DFP_DP && tcphy->mode != MODE_DISCONNECT) { tcphy_phy_deinit(tcphy); - tcphy_phy_init(tcphy, new_mode); + ret = tcphy_phy_init(tcphy, new_mode); } else if (tcphy->mode == MODE_DISCONNECT) { - tcphy_phy_init(tcphy, new_mode); + ret = tcphy_phy_init(tcphy, new_mode); } + if (ret) + goto unlock_ret; ret = readx_poll_timeout(readl, tcphy->base + DP_MODE_CTL, val, val & DP_MODE_A2, 1000, diff --git a/drivers/phy/tegra/xusb.c b/drivers/phy/tegra/xusb.c index 3cbcb2537657..4307bf0013e1 100644 --- a/drivers/phy/tegra/xusb.c +++ b/drivers/phy/tegra/xusb.c @@ -454,6 +454,8 @@ tegra_xusb_find_port_node(struct tegra_xusb_padctl *padctl, const char *type, char *name; name = kasprintf(GFP_KERNEL, "%s-%u", type, index); + if (!name) + return ERR_PTR(-ENOMEM); np = of_find_node_by_name(np, name); kfree(name); } diff --git a/drivers/pinctrl/Kconfig b/drivers/pinctrl/Kconfig index 1778cf4f81c7..82cd8b08d71f 100644 --- a/drivers/pinctrl/Kconfig +++ b/drivers/pinctrl/Kconfig @@ -100,6 +100,7 @@ config PINCTRL_AMD tristate "AMD GPIO pin control" depends on GPIOLIB select GPIOLIB_IRQCHIP + select PINMUX select PINCONF select GENERIC_PINCONF help diff --git a/drivers/pinctrl/bcm/pinctrl-bcm2835.c b/drivers/pinctrl/bcm/pinctrl-bcm2835.c index 0944310225db..ff782445dfb7 100644 --- a/drivers/pinctrl/bcm/pinctrl-bcm2835.c +++ b/drivers/pinctrl/bcm/pinctrl-bcm2835.c @@ -373,16 +373,12 @@ static void bcm2835_gpio_irq_handle_bank(struct bcm2835_pinctrl *pc, unsigned long events; unsigned offset; unsigned gpio; - unsigned int type; events = bcm2835_gpio_rd(pc, GPEDS0 + bank * 4); events &= mask; events &= pc->enabled_irq_map[bank]; for_each_set_bit(offset, &events, 32) { gpio = (32 * bank) + offset; - /* FIXME: no clue why the code looks up the type here */ - type = pc->irq_type[gpio]; - generic_handle_irq(irq_linear_revmap(pc->gpio_chip.irqdomain, gpio)); } diff --git a/drivers/pinctrl/intel/pinctrl-cherryview.c b/drivers/pinctrl/intel/pinctrl-cherryview.c index 04e929fd0ffe..fadbca907c7c 100644 --- a/drivers/pinctrl/intel/pinctrl-cherryview.c +++ b/drivers/pinctrl/intel/pinctrl-cherryview.c @@ -1577,6 +1577,7 @@ static int chv_gpio_probe(struct chv_pinctrl *pctrl, int irq) struct gpio_chip *chip = &pctrl->chip; bool need_valid_mask = !dmi_check_system(chv_no_valid_mask); int ret, i, offset; + int irq_base; *chip = chv_gpio_chip; @@ -1622,7 +1623,18 @@ static int chv_gpio_probe(struct chv_pinctrl *pctrl, int irq) /* Clear all interrupts */ chv_writel(0xffff, pctrl->regs + CHV_INTSTAT); - ret = gpiochip_irqchip_add(chip, &chv_gpio_irqchip, 0, + if (!need_valid_mask) { + irq_base = devm_irq_alloc_descs(pctrl->dev, -1, 0, + chip->ngpio, NUMA_NO_NODE); + if (irq_base < 0) { + dev_err(pctrl->dev, "Failed to allocate IRQ numbers\n"); + return irq_base; + } + } else { + irq_base = 0; + } + + ret = gpiochip_irqchip_add(chip, &chv_gpio_irqchip, irq_base, handle_bad_irq, IRQ_TYPE_NONE); if (ret) { dev_err(pctrl->dev, "failed to add IRQ chip\n"); diff --git a/drivers/pinctrl/pinctrl-amd.c b/drivers/pinctrl/pinctrl-amd.c index 3f6b34febbf1..433af328d981 100644 --- a/drivers/pinctrl/pinctrl-amd.c +++ b/drivers/pinctrl/pinctrl-amd.c @@ -534,8 +534,16 @@ static irqreturn_t amd_gpio_irq_handler(int irq, void *dev_id) continue; irq = irq_find_mapping(gc->irqdomain, irqnr + i); generic_handle_irq(irq); - /* Clear interrupt */ + + /* Clear interrupt. + * We must read the pin register again, in case the + * value was changed while executing + * generic_handle_irq() above. + */ + raw_spin_lock_irqsave(&gpio_dev->lock, flags); + regval = readl(regs + i); writel(regval, regs + i); + raw_spin_unlock_irqrestore(&gpio_dev->lock, flags); ret = IRQ_HANDLED; } } diff --git a/drivers/pinctrl/pinctrl-mcp23s08.c b/drivers/pinctrl/pinctrl-mcp23s08.c index 3e40d4245512..9c950bbf07ba 100644 --- a/drivers/pinctrl/pinctrl-mcp23s08.c +++ b/drivers/pinctrl/pinctrl-mcp23s08.c @@ -407,10 +407,10 @@ static int mcp23s08_get(struct gpio_chip *chip, unsigned offset) ret = mcp_read(mcp, MCP_GPIO, &status); if (ret < 0) status = 0; - else + else { + mcp->cached_gpio = status; status = !!(status & (1 << offset)); - - mcp->cached_gpio = status; + } mutex_unlock(&mcp->lock); return status; diff --git a/drivers/platform/x86/intel_pmc_ipc.c b/drivers/platform/x86/intel_pmc_ipc.c index bb792a52248b..e03fa31446ca 100644 --- a/drivers/platform/x86/intel_pmc_ipc.c +++ b/drivers/platform/x86/intel_pmc_ipc.c @@ -33,6 +33,7 @@ #include <linux/suspend.h> #include <linux/acpi.h> #include <linux/io-64-nonatomic-lo-hi.h> +#include <linux/spinlock.h> #include <asm/intel_pmc_ipc.h> @@ -131,6 +132,7 @@ static struct intel_pmc_ipc_dev { /* gcr */ void __iomem *gcr_mem_base; bool has_gcr_regs; + spinlock_t gcr_lock; /* punit */ struct platform_device *punit_dev; @@ -225,17 +227,17 @@ int intel_pmc_gcr_read(u32 offset, u32 *data) { int ret; - mutex_lock(&ipclock); + spin_lock(&ipcdev.gcr_lock); ret = is_gcr_valid(offset); if (ret < 0) { - mutex_unlock(&ipclock); + spin_unlock(&ipcdev.gcr_lock); return ret; } *data = readl(ipcdev.gcr_mem_base + offset); - mutex_unlock(&ipclock); + spin_unlock(&ipcdev.gcr_lock); return 0; } @@ -255,17 +257,17 @@ int intel_pmc_gcr_write(u32 offset, u32 data) { int ret; - mutex_lock(&ipclock); + spin_lock(&ipcdev.gcr_lock); ret = is_gcr_valid(offset); if (ret < 0) { - mutex_unlock(&ipclock); + spin_unlock(&ipcdev.gcr_lock); return ret; } writel(data, ipcdev.gcr_mem_base + offset); - mutex_unlock(&ipclock); + spin_unlock(&ipcdev.gcr_lock); return 0; } @@ -287,7 +289,7 @@ int intel_pmc_gcr_update(u32 offset, u32 mask, u32 val) u32 new_val; int ret = 0; - mutex_lock(&ipclock); + spin_lock(&ipcdev.gcr_lock); ret = is_gcr_valid(offset); if (ret < 0) @@ -309,7 +311,7 @@ int intel_pmc_gcr_update(u32 offset, u32 mask, u32 val) } gcr_ipc_unlock: - mutex_unlock(&ipclock); + spin_unlock(&ipcdev.gcr_lock); return ret; } EXPORT_SYMBOL_GPL(intel_pmc_gcr_update); @@ -480,52 +482,41 @@ static irqreturn_t ioc(int irq, void *dev_id) static int ipc_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id) { - resource_size_t pci_resource; + struct intel_pmc_ipc_dev *pmc = &ipcdev; int ret; - int len; - ipcdev.dev = &pci_dev_get(pdev)->dev; - ipcdev.irq_mode = IPC_TRIGGER_MODE_IRQ; + /* Only one PMC is supported */ + if (pmc->dev) + return -EBUSY; - ret = pci_enable_device(pdev); + pmc->irq_mode = IPC_TRIGGER_MODE_IRQ; + + spin_lock_init(&ipcdev.gcr_lock); + + ret = pcim_enable_device(pdev); if (ret) return ret; - ret = pci_request_regions(pdev, "intel_pmc_ipc"); + ret = pcim_iomap_regions(pdev, 1 << 0, pci_name(pdev)); if (ret) return ret; - pci_resource = pci_resource_start(pdev, 0); - len = pci_resource_len(pdev, 0); - if (!pci_resource || !len) { - dev_err(&pdev->dev, "Failed to get resource\n"); - return -ENOMEM; - } + init_completion(&pmc->cmd_complete); - init_completion(&ipcdev.cmd_complete); + pmc->ipc_base = pcim_iomap_table(pdev)[0]; - if (request_irq(pdev->irq, ioc, 0, "intel_pmc_ipc", &ipcdev)) { + ret = devm_request_irq(&pdev->dev, pdev->irq, ioc, 0, "intel_pmc_ipc", + pmc); + if (ret) { dev_err(&pdev->dev, "Failed to request irq\n"); - return -EBUSY; + return ret; } - ipcdev.ipc_base = ioremap_nocache(pci_resource, len); - if (!ipcdev.ipc_base) { - dev_err(&pdev->dev, "Failed to ioremap ipc base\n"); - free_irq(pdev->irq, &ipcdev); - ret = -ENOMEM; - } + pmc->dev = &pdev->dev; - return ret; -} + pci_set_drvdata(pdev, pmc); -static void ipc_pci_remove(struct pci_dev *pdev) -{ - free_irq(pdev->irq, &ipcdev); - pci_release_regions(pdev); - pci_dev_put(pdev); - iounmap(ipcdev.ipc_base); - ipcdev.dev = NULL; + return 0; } static const struct pci_device_id ipc_pci_ids[] = { @@ -540,7 +531,6 @@ static struct pci_driver ipc_pci_driver = { .name = "intel_pmc_ipc", .id_table = ipc_pci_ids, .probe = ipc_pci_probe, - .remove = ipc_pci_remove, }; static ssize_t intel_pmc_ipc_simple_cmd_store(struct device *dev, @@ -850,17 +840,12 @@ static int ipc_plat_get_res(struct platform_device *pdev) return -ENXIO; } size = PLAT_RESOURCE_IPC_SIZE + PLAT_RESOURCE_GCR_SIZE; + res->end = res->start + size - 1; + + addr = devm_ioremap_resource(&pdev->dev, res); + if (IS_ERR(addr)) + return PTR_ERR(addr); - if (!request_mem_region(res->start, size, pdev->name)) { - dev_err(&pdev->dev, "Failed to request ipc resource\n"); - return -EBUSY; - } - addr = ioremap_nocache(res->start, size); - if (!addr) { - dev_err(&pdev->dev, "I/O memory remapping failed\n"); - release_mem_region(res->start, size); - return -ENOMEM; - } ipcdev.ipc_base = addr; ipcdev.gcr_mem_base = addr + PLAT_RESOURCE_GCR_OFFSET; @@ -917,12 +902,12 @@ MODULE_DEVICE_TABLE(acpi, ipc_acpi_ids); static int ipc_plat_probe(struct platform_device *pdev) { - struct resource *res; int ret; ipcdev.dev = &pdev->dev; ipcdev.irq_mode = IPC_TRIGGER_MODE_IRQ; init_completion(&ipcdev.cmd_complete); + spin_lock_init(&ipcdev.gcr_lock); ipcdev.irq = platform_get_irq(pdev, 0); if (ipcdev.irq < 0) { @@ -939,11 +924,11 @@ static int ipc_plat_probe(struct platform_device *pdev) ret = ipc_create_pmc_devices(); if (ret) { dev_err(&pdev->dev, "Failed to create pmc devices\n"); - goto err_device; + return ret; } - if (request_irq(ipcdev.irq, ioc, IRQF_NO_SUSPEND, - "intel_pmc_ipc", &ipcdev)) { + if (devm_request_irq(&pdev->dev, ipcdev.irq, ioc, IRQF_NO_SUSPEND, + "intel_pmc_ipc", &ipcdev)) { dev_err(&pdev->dev, "Failed to request irq\n"); ret = -EBUSY; goto err_irq; @@ -960,40 +945,22 @@ static int ipc_plat_probe(struct platform_device *pdev) return 0; err_sys: - free_irq(ipcdev.irq, &ipcdev); + devm_free_irq(&pdev->dev, ipcdev.irq, &ipcdev); err_irq: platform_device_unregister(ipcdev.tco_dev); platform_device_unregister(ipcdev.punit_dev); platform_device_unregister(ipcdev.telemetry_dev); -err_device: - iounmap(ipcdev.ipc_base); - res = platform_get_resource(pdev, IORESOURCE_MEM, - PLAT_RESOURCE_IPC_INDEX); - if (res) { - release_mem_region(res->start, - PLAT_RESOURCE_IPC_SIZE + - PLAT_RESOURCE_GCR_SIZE); - } + return ret; } static int ipc_plat_remove(struct platform_device *pdev) { - struct resource *res; - sysfs_remove_group(&pdev->dev.kobj, &intel_ipc_group); - free_irq(ipcdev.irq, &ipcdev); + devm_free_irq(&pdev->dev, ipcdev.irq, &ipcdev); platform_device_unregister(ipcdev.tco_dev); platform_device_unregister(ipcdev.punit_dev); platform_device_unregister(ipcdev.telemetry_dev); - iounmap(ipcdev.ipc_base); - res = platform_get_resource(pdev, IORESOURCE_MEM, - PLAT_RESOURCE_IPC_INDEX); - if (res) { - release_mem_region(res->start, - PLAT_RESOURCE_IPC_SIZE + - PLAT_RESOURCE_GCR_SIZE); - } ipcdev.dev = NULL; return 0; } diff --git a/drivers/ras/cec.c b/drivers/ras/cec.c index d0e5d6ee882c..e2c1988cd7c0 100644 --- a/drivers/ras/cec.c +++ b/drivers/ras/cec.c @@ -523,7 +523,7 @@ int __init parse_cec_param(char *str) if (*str == '=') str++; - if (!strncmp(str, "cec_disable", 7)) + if (!strcmp(str, "cec_disable")) ce_arr.disabled = 1; else return 0; diff --git a/drivers/regulator/axp20x-regulator.c b/drivers/regulator/axp20x-regulator.c index f18b36dd57dd..376a99b7cf5d 100644 --- a/drivers/regulator/axp20x-regulator.c +++ b/drivers/regulator/axp20x-regulator.c @@ -590,7 +590,7 @@ static bool axp20x_is_polyphase_slave(struct axp20x_dev *axp20x, int id) case AXP803_DCDC3: return !!(reg & BIT(6)); case AXP803_DCDC6: - return !!(reg & BIT(7)); + return !!(reg & BIT(5)); } break; diff --git a/drivers/regulator/rn5t618-regulator.c b/drivers/regulator/rn5t618-regulator.c index ef2be56460fe..790a4a73ea2c 100644 --- a/drivers/regulator/rn5t618-regulator.c +++ b/drivers/regulator/rn5t618-regulator.c @@ -29,7 +29,7 @@ static const struct regulator_ops rn5t618_reg_ops = { }; #define REG(rid, ereg, emask, vreg, vmask, min, max, step) \ - [RN5T618_##rid] = { \ + { \ .name = #rid, \ .of_match = of_match_ptr(#rid), \ .regulators_node = of_match_ptr("regulators"), \ diff --git a/drivers/remoteproc/Kconfig b/drivers/remoteproc/Kconfig index df63e44526ac..bf04479456a0 100644 --- a/drivers/remoteproc/Kconfig +++ b/drivers/remoteproc/Kconfig @@ -109,6 +109,7 @@ config QCOM_Q6V5_PIL depends on OF && ARCH_QCOM depends on QCOM_SMEM depends on RPMSG_QCOM_SMD || (COMPILE_TEST && RPMSG_QCOM_SMD=n) + depends on RPMSG_QCOM_GLINK_SMEM || RPMSG_QCOM_GLINK_SMEM=n select MFD_SYSCON select QCOM_RPROC_COMMON select QCOM_SCM @@ -120,6 +121,7 @@ config QCOM_WCNSS_PIL tristate "Qualcomm WCNSS Peripheral Image Loader" depends on OF && ARCH_QCOM depends on RPMSG_QCOM_SMD || (COMPILE_TEST && RPMSG_QCOM_SMD=n) + depends on RPMSG_QCOM_GLINK_SMEM || RPMSG_QCOM_GLINK_SMEM=n depends on QCOM_SMEM select QCOM_MDT_LOADER select QCOM_RPROC_COMMON diff --git a/drivers/remoteproc/imx_rproc.c b/drivers/remoteproc/imx_rproc.c index 612d91403341..633268e9d550 100644 --- a/drivers/remoteproc/imx_rproc.c +++ b/drivers/remoteproc/imx_rproc.c @@ -264,15 +264,14 @@ static int imx_rproc_addr_init(struct imx_rproc *priv, if (!(att->flags & ATT_OWN)) continue; - if (b > IMX7D_RPROC_MEM_MAX) + if (b >= IMX7D_RPROC_MEM_MAX) break; priv->mem[b].cpu_addr = devm_ioremap(&pdev->dev, att->sa, att->size); - if (IS_ERR(priv->mem[b].cpu_addr)) { + if (!priv->mem[b].cpu_addr) { dev_err(dev, "devm_ioremap_resource failed\n"); - err = PTR_ERR(priv->mem[b].cpu_addr); - return err; + return -ENOMEM; } priv->mem[b].sys_addr = att->sa; priv->mem[b].size = att->size; @@ -296,7 +295,7 @@ static int imx_rproc_addr_init(struct imx_rproc *priv, return err; } - if (b > IMX7D_RPROC_MEM_MAX) + if (b >= IMX7D_RPROC_MEM_MAX) break; priv->mem[b].cpu_addr = devm_ioremap_resource(&pdev->dev, &res); diff --git a/drivers/reset/reset-socfpga.c b/drivers/reset/reset-socfpga.c index c60904ff40b8..3907bbc9c6cf 100644 --- a/drivers/reset/reset-socfpga.c +++ b/drivers/reset/reset-socfpga.c @@ -40,8 +40,9 @@ static int socfpga_reset_assert(struct reset_controller_dev *rcdev, struct socfpga_reset_data *data = container_of(rcdev, struct socfpga_reset_data, rcdev); - int bank = id / BITS_PER_LONG; - int offset = id % BITS_PER_LONG; + int reg_width = sizeof(u32); + int bank = id / (reg_width * BITS_PER_BYTE); + int offset = id % (reg_width * BITS_PER_BYTE); unsigned long flags; u32 reg; @@ -61,8 +62,9 @@ static int socfpga_reset_deassert(struct reset_controller_dev *rcdev, struct socfpga_reset_data, rcdev); - int bank = id / BITS_PER_LONG; - int offset = id % BITS_PER_LONG; + int reg_width = sizeof(u32); + int bank = id / (reg_width * BITS_PER_BYTE); + int offset = id % (reg_width * BITS_PER_BYTE); unsigned long flags; u32 reg; @@ -81,8 +83,9 @@ static int socfpga_reset_status(struct reset_controller_dev *rcdev, { struct socfpga_reset_data *data = container_of(rcdev, struct socfpga_reset_data, rcdev); - int bank = id / BITS_PER_LONG; - int offset = id % BITS_PER_LONG; + int reg_width = sizeof(u32); + int bank = id / (reg_width * BITS_PER_BYTE); + int offset = id % (reg_width * BITS_PER_BYTE); u32 reg; reg = readl(data->membase + (bank * BANK_INCREMENT)); @@ -132,7 +135,7 @@ static int socfpga_reset_probe(struct platform_device *pdev) spin_lock_init(&data->lock); data->rcdev.owner = THIS_MODULE; - data->rcdev.nr_resets = NR_BANKS * BITS_PER_LONG; + data->rcdev.nr_resets = NR_BANKS * (sizeof(u32) * BITS_PER_BYTE); data->rcdev.ops = &socfpga_reset_ops; data->rcdev.of_node = pdev->dev.of_node; diff --git a/drivers/rpmsg/qcom_glink_native.c b/drivers/rpmsg/qcom_glink_native.c index 5a5e927ea50f..5dcc9bf1c5bc 100644 --- a/drivers/rpmsg/qcom_glink_native.c +++ b/drivers/rpmsg/qcom_glink_native.c @@ -635,19 +635,18 @@ qcom_glink_alloc_intent(struct qcom_glink *glink, unsigned long flags; intent = kzalloc(sizeof(*intent), GFP_KERNEL); - if (!intent) return NULL; intent->data = kzalloc(size, GFP_KERNEL); if (!intent->data) - return NULL; + goto free_intent; spin_lock_irqsave(&channel->intent_lock, flags); ret = idr_alloc_cyclic(&channel->liids, intent, 1, -1, GFP_ATOMIC); if (ret < 0) { spin_unlock_irqrestore(&channel->intent_lock, flags); - return NULL; + goto free_data; } spin_unlock_irqrestore(&channel->intent_lock, flags); @@ -656,6 +655,12 @@ qcom_glink_alloc_intent(struct qcom_glink *glink, intent->reuse = reuseable; return intent; + +free_data: + kfree(intent->data); +free_intent: + kfree(intent); + return NULL; } static void qcom_glink_handle_rx_done(struct qcom_glink *glink, @@ -1197,7 +1202,7 @@ static int qcom_glink_request_intent(struct qcom_glink *glink, ret = qcom_glink_tx(glink, &cmd, sizeof(cmd), NULL, 0, true); if (ret) - return ret; + goto unlock; ret = wait_for_completion_timeout(&channel->intent_req_comp, 10 * HZ); if (!ret) { @@ -1207,6 +1212,7 @@ static int qcom_glink_request_intent(struct qcom_glink *glink, ret = channel->intent_req_result ? 0 : -ECANCELED; } +unlock: mutex_unlock(&channel->intent_req_lock); return ret; } diff --git a/drivers/s390/scsi/zfcp_aux.c b/drivers/s390/scsi/zfcp_aux.c index 82ac331d9125..84752152d41f 100644 --- a/drivers/s390/scsi/zfcp_aux.c +++ b/drivers/s390/scsi/zfcp_aux.c @@ -357,6 +357,8 @@ struct zfcp_adapter *zfcp_adapter_enqueue(struct ccw_device *ccw_device) adapter->next_port_scan = jiffies; + adapter->erp_action.adapter = adapter; + if (zfcp_qdio_setup(adapter)) goto failed; @@ -513,6 +515,9 @@ struct zfcp_port *zfcp_port_enqueue(struct zfcp_adapter *adapter, u64 wwpn, port->dev.groups = zfcp_port_attr_groups; port->dev.release = zfcp_port_release; + port->erp_action.adapter = adapter; + port->erp_action.port = port; + if (dev_set_name(&port->dev, "0x%016llx", (unsigned long long)wwpn)) { kfree(port); goto err_out; diff --git a/drivers/s390/scsi/zfcp_erp.c b/drivers/s390/scsi/zfcp_erp.c index 37408f5f81ce..ec2532ee1822 100644 --- a/drivers/s390/scsi/zfcp_erp.c +++ b/drivers/s390/scsi/zfcp_erp.c @@ -193,9 +193,8 @@ static struct zfcp_erp_action *zfcp_erp_setup_act(int need, u32 act_status, atomic_or(ZFCP_STATUS_COMMON_ERP_INUSE, &zfcp_sdev->status); erp_action = &zfcp_sdev->erp_action; - memset(erp_action, 0, sizeof(struct zfcp_erp_action)); - erp_action->port = port; - erp_action->sdev = sdev; + WARN_ON_ONCE(erp_action->port != port); + WARN_ON_ONCE(erp_action->sdev != sdev); if (!(atomic_read(&zfcp_sdev->status) & ZFCP_STATUS_COMMON_RUNNING)) act_status |= ZFCP_STATUS_ERP_CLOSE_ONLY; @@ -208,8 +207,8 @@ static struct zfcp_erp_action *zfcp_erp_setup_act(int need, u32 act_status, zfcp_erp_action_dismiss_port(port); atomic_or(ZFCP_STATUS_COMMON_ERP_INUSE, &port->status); erp_action = &port->erp_action; - memset(erp_action, 0, sizeof(struct zfcp_erp_action)); - erp_action->port = port; + WARN_ON_ONCE(erp_action->port != port); + WARN_ON_ONCE(erp_action->sdev != NULL); if (!(atomic_read(&port->status) & ZFCP_STATUS_COMMON_RUNNING)) act_status |= ZFCP_STATUS_ERP_CLOSE_ONLY; break; @@ -219,7 +218,8 @@ static struct zfcp_erp_action *zfcp_erp_setup_act(int need, u32 act_status, zfcp_erp_action_dismiss_adapter(adapter); atomic_or(ZFCP_STATUS_COMMON_ERP_INUSE, &adapter->status); erp_action = &adapter->erp_action; - memset(erp_action, 0, sizeof(struct zfcp_erp_action)); + WARN_ON_ONCE(erp_action->port != NULL); + WARN_ON_ONCE(erp_action->sdev != NULL); if (!(atomic_read(&adapter->status) & ZFCP_STATUS_COMMON_RUNNING)) act_status |= ZFCP_STATUS_ERP_CLOSE_ONLY; @@ -229,7 +229,11 @@ static struct zfcp_erp_action *zfcp_erp_setup_act(int need, u32 act_status, return NULL; } - erp_action->adapter = adapter; + WARN_ON_ONCE(erp_action->adapter != adapter); + memset(&erp_action->list, 0, sizeof(erp_action->list)); + memset(&erp_action->timer, 0, sizeof(erp_action->timer)); + erp_action->step = ZFCP_ERP_STEP_UNINITIALIZED; + erp_action->fsf_req_id = 0; erp_action->action = need; erp_action->status = act_status; diff --git a/drivers/s390/scsi/zfcp_scsi.c b/drivers/s390/scsi/zfcp_scsi.c index ec3ddd1d31d5..6cf8732627e0 100644 --- a/drivers/s390/scsi/zfcp_scsi.c +++ b/drivers/s390/scsi/zfcp_scsi.c @@ -115,10 +115,15 @@ static int zfcp_scsi_slave_alloc(struct scsi_device *sdev) struct zfcp_unit *unit; int npiv = adapter->connection_features & FSF_FEATURE_NPIV_MODE; + zfcp_sdev->erp_action.adapter = adapter; + zfcp_sdev->erp_action.sdev = sdev; + port = zfcp_get_port_by_wwpn(adapter, rport->port_name); if (!port) return -ENXIO; + zfcp_sdev->erp_action.port = port; + unit = zfcp_unit_find(port, zfcp_scsi_dev_lun(sdev)); if (unit) put_device(&unit->dev); diff --git a/drivers/scsi/aacraid/comminit.c b/drivers/scsi/aacraid/comminit.c index 97d269f16888..1bc623ad3faf 100644 --- a/drivers/scsi/aacraid/comminit.c +++ b/drivers/scsi/aacraid/comminit.c @@ -302,9 +302,11 @@ int aac_send_shutdown(struct aac_dev * dev) return -ENOMEM; aac_fib_init(fibctx); - mutex_lock(&dev->ioctl_mutex); - dev->adapter_shutdown = 1; - mutex_unlock(&dev->ioctl_mutex); + if (!dev->adapter_shutdown) { + mutex_lock(&dev->ioctl_mutex); + dev->adapter_shutdown = 1; + mutex_unlock(&dev->ioctl_mutex); + } cmd = (struct aac_close *) fib_data(fibctx); cmd->command = cpu_to_le32(VM_CloseAll); diff --git a/drivers/scsi/aacraid/linit.c b/drivers/scsi/aacraid/linit.c index 62beb2596466..c9252b138c1f 100644 --- a/drivers/scsi/aacraid/linit.c +++ b/drivers/scsi/aacraid/linit.c @@ -1551,8 +1551,9 @@ static void __aac_shutdown(struct aac_dev * aac) { int i; + mutex_lock(&aac->ioctl_mutex); aac->adapter_shutdown = 1; - aac_send_shutdown(aac); + mutex_unlock(&aac->ioctl_mutex); if (aac->aif_thread) { int i; @@ -1565,7 +1566,11 @@ static void __aac_shutdown(struct aac_dev * aac) } kthread_stop(aac->thread); } + + aac_send_shutdown(aac); + aac_adapter_disable_int(aac); + if (aac_is_src(aac)) { if (aac->max_msix > 1) { for (i = 0; i < aac->max_msix; i++) { diff --git a/drivers/scsi/hpsa.c b/drivers/scsi/hpsa.c index 9abe81021484..4ed3d26ffdde 100644 --- a/drivers/scsi/hpsa.c +++ b/drivers/scsi/hpsa.c @@ -4091,7 +4091,7 @@ static int hpsa_set_local_logical_count(struct ctlr_info *h, memset(id_ctlr, 0, sizeof(*id_ctlr)); rc = hpsa_bmic_id_controller(h, id_ctlr, sizeof(*id_ctlr)); if (!rc) - if (id_ctlr->configured_logical_drive_count < 256) + if (id_ctlr->configured_logical_drive_count < 255) *nlocals = id_ctlr->configured_logical_drive_count; else *nlocals = le16_to_cpu( diff --git a/drivers/scsi/libfc/fc_rport.c b/drivers/scsi/libfc/fc_rport.c index 520325867e2b..31d31aad3de1 100644 --- a/drivers/scsi/libfc/fc_rport.c +++ b/drivers/scsi/libfc/fc_rport.c @@ -383,11 +383,11 @@ static void fc_rport_work(struct work_struct *work) fc_rport_enter_flogi(rdata); mutex_unlock(&rdata->rp_mutex); } else { + mutex_unlock(&rdata->rp_mutex); FC_RPORT_DBG(rdata, "work delete\n"); mutex_lock(&lport->disc.disc_mutex); list_del_rcu(&rdata->peers); mutex_unlock(&lport->disc.disc_mutex); - mutex_unlock(&rdata->rp_mutex); kref_put(&rdata->kref, fc_rport_destroy); } } else { diff --git a/drivers/scsi/libiscsi.c b/drivers/scsi/libiscsi.c index c62e8d111fd9..f8dc1601efd5 100644 --- a/drivers/scsi/libiscsi.c +++ b/drivers/scsi/libiscsi.c @@ -1728,7 +1728,7 @@ int iscsi_queuecommand(struct Scsi_Host *host, struct scsi_cmnd *sc) if (test_bit(ISCSI_SUSPEND_BIT, &conn->suspend_tx)) { reason = FAILURE_SESSION_IN_RECOVERY; - sc->result = DID_REQUEUE; + sc->result = DID_REQUEUE << 16; goto fault; } diff --git a/drivers/scsi/qla2xxx/qla_os.c b/drivers/scsi/qla2xxx/qla_os.c index 5b2437a5ea44..3bd956d3bc5d 100644 --- a/drivers/scsi/qla2xxx/qla_os.c +++ b/drivers/scsi/qla2xxx/qla_os.c @@ -3061,6 +3061,8 @@ qla2x00_probe_one(struct pci_dev *pdev, const struct pci_device_id *id) host->max_cmd_len, host->max_channel, host->max_lun, host->transportt, sht->vendor_id); + INIT_WORK(&base_vha->iocb_work, qla2x00_iocb_work_fn); + /* Set up the irqs */ ret = qla2x00_request_irqs(ha, rsp); if (ret) @@ -3223,7 +3225,6 @@ qla2x00_probe_one(struct pci_dev *pdev, const struct pci_device_id *id) */ qla2xxx_wake_dpc(base_vha); - INIT_WORK(&base_vha->iocb_work, qla2x00_iocb_work_fn); INIT_WORK(&ha->board_disable, qla2x00_disable_board_on_pci_error); if (IS_QLA8031(ha) || IS_MCTP_CAPABLE(ha)) { diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c index 9cf6a80fe297..ad3ea24f0885 100644 --- a/drivers/scsi/scsi_lib.c +++ b/drivers/scsi/scsi_lib.c @@ -1379,8 +1379,6 @@ static int scsi_prep_fn(struct request_queue *q, struct request *req) ret = scsi_setup_cmnd(sdev, req); out: - if (ret != BLKPREP_OK) - cmd->flags &= ~SCMD_INITIALIZED; return scsi_prep_return(q, req, ret); } @@ -1900,7 +1898,6 @@ static int scsi_mq_prep_fn(struct request *req) struct scsi_device *sdev = req->q->queuedata; struct Scsi_Host *shost = sdev->host; struct scatterlist *sg; - int ret; scsi_init_command(sdev, cmd); @@ -1934,10 +1931,7 @@ static int scsi_mq_prep_fn(struct request *req) blk_mq_start_request(req); - ret = scsi_setup_cmnd(sdev, req); - if (ret != BLK_STS_OK) - cmd->flags &= ~SCMD_INITIALIZED; - return ret; + return scsi_setup_cmnd(sdev, req); } static void scsi_mq_done(struct scsi_cmnd *cmd) diff --git a/drivers/scsi/scsi_sysfs.c b/drivers/scsi/scsi_sysfs.c index bf53356f41f0..f796bd61f3f0 100644 --- a/drivers/scsi/scsi_sysfs.c +++ b/drivers/scsi/scsi_sysfs.c @@ -1376,13 +1376,19 @@ static void __scsi_remove_target(struct scsi_target *starget) spin_lock_irqsave(shost->host_lock, flags); restart: list_for_each_entry(sdev, &shost->__devices, siblings) { + /* + * We cannot call scsi_device_get() here, as + * we might've been called from rmmod() causing + * scsi_device_get() to fail the module_is_live() + * check. + */ if (sdev->channel != starget->channel || sdev->id != starget->id || - scsi_device_get(sdev)) + !get_device(&sdev->sdev_gendev)) continue; spin_unlock_irqrestore(shost->host_lock, flags); scsi_remove_device(sdev); - scsi_device_put(sdev); + put_device(&sdev->sdev_gendev); spin_lock_irqsave(shost->host_lock, flags); goto restart; } diff --git a/drivers/scsi/scsi_transport_fc.c b/drivers/scsi/scsi_transport_fc.c index cbd4495d0ff9..8c46a6d536af 100644 --- a/drivers/scsi/scsi_transport_fc.c +++ b/drivers/scsi/scsi_transport_fc.c @@ -3320,6 +3320,9 @@ int fc_block_scsi_eh(struct scsi_cmnd *cmnd) { struct fc_rport *rport = starget_to_rport(scsi_target(cmnd->device)); + if (WARN_ON_ONCE(!rport)) + return FAST_IO_FAIL; + return fc_block_rport(rport); } EXPORT_SYMBOL(fc_block_scsi_eh); diff --git a/drivers/scsi/sg.c b/drivers/scsi/sg.c index 0419c2298eab..aa28874e8fb9 100644 --- a/drivers/scsi/sg.c +++ b/drivers/scsi/sg.c @@ -837,7 +837,7 @@ sg_fill_request_table(Sg_fd *sfp, sg_req_info_t *rinfo) val = 0; list_for_each_entry(srp, &sfp->rq_list, entry) { - if (val > SG_MAX_QUEUE) + if (val >= SG_MAX_QUEUE) break; rinfo[val].req_state = srp->done + 1; rinfo[val].problem = diff --git a/drivers/spi/spi-armada-3700.c b/drivers/spi/spi-armada-3700.c index 6c7d7a460689..568e1c65aa82 100644 --- a/drivers/spi/spi-armada-3700.c +++ b/drivers/spi/spi-armada-3700.c @@ -99,11 +99,6 @@ /* A3700_SPI_IF_TIME_REG */ #define A3700_SPI_CLK_CAPT_EDGE BIT(7) -/* Flags and macros for struct a3700_spi */ -#define A3700_INSTR_CNT 1 -#define A3700_ADDR_CNT 3 -#define A3700_DUMMY_CNT 1 - struct a3700_spi { struct spi_master *master; void __iomem *base; @@ -117,9 +112,6 @@ struct a3700_spi { u8 byte_len; u32 wait_mask; struct completion done; - u32 addr_cnt; - u32 instr_cnt; - size_t hdr_cnt; }; static u32 spireg_read(struct a3700_spi *a3700_spi, u32 offset) @@ -161,7 +153,7 @@ static void a3700_spi_deactivate_cs(struct a3700_spi *a3700_spi, } static int a3700_spi_pin_mode_set(struct a3700_spi *a3700_spi, - unsigned int pin_mode) + unsigned int pin_mode, bool receiving) { u32 val; @@ -177,6 +169,9 @@ static int a3700_spi_pin_mode_set(struct a3700_spi *a3700_spi, break; case SPI_NBITS_QUAD: val |= A3700_SPI_DATA_PIN1; + /* RX during address reception uses 4-pin */ + if (receiving) + val |= A3700_SPI_ADDR_PIN; break; default: dev_err(&a3700_spi->master->dev, "wrong pin mode %u", pin_mode); @@ -392,7 +387,8 @@ static bool a3700_spi_wait_completion(struct spi_device *spi) spireg_write(a3700_spi, A3700_SPI_INT_MASK_REG, 0); - return true; + /* Timeout was reached */ + return false; } static bool a3700_spi_transfer_wait(struct spi_device *spi, @@ -446,59 +442,43 @@ static void a3700_spi_set_cs(struct spi_device *spi, bool enable) static void a3700_spi_header_set(struct a3700_spi *a3700_spi) { - u32 instr_cnt = 0, addr_cnt = 0, dummy_cnt = 0; + unsigned int addr_cnt; u32 val = 0; /* Clear the header registers */ spireg_write(a3700_spi, A3700_SPI_IF_INST_REG, 0); spireg_write(a3700_spi, A3700_SPI_IF_ADDR_REG, 0); spireg_write(a3700_spi, A3700_SPI_IF_RMODE_REG, 0); + spireg_write(a3700_spi, A3700_SPI_IF_HDR_CNT_REG, 0); /* Set header counters */ if (a3700_spi->tx_buf) { - if (a3700_spi->buf_len <= a3700_spi->instr_cnt) { - instr_cnt = a3700_spi->buf_len; - } else if (a3700_spi->buf_len <= (a3700_spi->instr_cnt + - a3700_spi->addr_cnt)) { - instr_cnt = a3700_spi->instr_cnt; - addr_cnt = a3700_spi->buf_len - instr_cnt; - } else if (a3700_spi->buf_len <= a3700_spi->hdr_cnt) { - instr_cnt = a3700_spi->instr_cnt; - addr_cnt = a3700_spi->addr_cnt; - /* Need to handle the normal write case with 1 byte - * data - */ - if (!a3700_spi->tx_buf[instr_cnt + addr_cnt]) - dummy_cnt = a3700_spi->buf_len - instr_cnt - - addr_cnt; + /* + * when tx data is not 4 bytes aligned, there will be unexpected + * bytes out of SPI output register, since it always shifts out + * as whole 4 bytes. This might cause incorrect transaction with + * some devices. To avoid that, use SPI header count feature to + * transfer up to 3 bytes of data first, and then make the rest + * of data 4-byte aligned. + */ + addr_cnt = a3700_spi->buf_len % 4; + if (addr_cnt) { + val = (addr_cnt & A3700_SPI_ADDR_CNT_MASK) + << A3700_SPI_ADDR_CNT_BIT; + spireg_write(a3700_spi, A3700_SPI_IF_HDR_CNT_REG, val); + + /* Update the buffer length to be transferred */ + a3700_spi->buf_len -= addr_cnt; + + /* transfer 1~3 bytes through address count */ + val = 0; + while (addr_cnt--) { + val = (val << 8) | a3700_spi->tx_buf[0]; + a3700_spi->tx_buf++; + } + spireg_write(a3700_spi, A3700_SPI_IF_ADDR_REG, val); } - val |= ((instr_cnt & A3700_SPI_INSTR_CNT_MASK) - << A3700_SPI_INSTR_CNT_BIT); - val |= ((addr_cnt & A3700_SPI_ADDR_CNT_MASK) - << A3700_SPI_ADDR_CNT_BIT); - val |= ((dummy_cnt & A3700_SPI_DUMMY_CNT_MASK) - << A3700_SPI_DUMMY_CNT_BIT); } - spireg_write(a3700_spi, A3700_SPI_IF_HDR_CNT_REG, val); - - /* Update the buffer length to be transferred */ - a3700_spi->buf_len -= (instr_cnt + addr_cnt + dummy_cnt); - - /* Set Instruction */ - val = 0; - while (instr_cnt--) { - val = (val << 8) | a3700_spi->tx_buf[0]; - a3700_spi->tx_buf++; - } - spireg_write(a3700_spi, A3700_SPI_IF_INST_REG, val); - - /* Set Address */ - val = 0; - while (addr_cnt--) { - val = (val << 8) | a3700_spi->tx_buf[0]; - a3700_spi->tx_buf++; - } - spireg_write(a3700_spi, A3700_SPI_IF_ADDR_REG, val); } static int a3700_is_wfifo_full(struct a3700_spi *a3700_spi) @@ -512,35 +492,12 @@ static int a3700_is_wfifo_full(struct a3700_spi *a3700_spi) static int a3700_spi_fifo_write(struct a3700_spi *a3700_spi) { u32 val; - int i = 0; while (!a3700_is_wfifo_full(a3700_spi) && a3700_spi->buf_len) { - val = 0; - if (a3700_spi->buf_len >= 4) { - val = cpu_to_le32(*(u32 *)a3700_spi->tx_buf); - spireg_write(a3700_spi, A3700_SPI_DATA_OUT_REG, val); - - a3700_spi->buf_len -= 4; - a3700_spi->tx_buf += 4; - } else { - /* - * If the remained buffer length is less than 4-bytes, - * we should pad the write buffer with all ones. So that - * it avoids overwrite the unexpected bytes following - * the last one. - */ - val = GENMASK(31, 0); - while (a3700_spi->buf_len) { - val &= ~(0xff << (8 * i)); - val |= *a3700_spi->tx_buf++ << (8 * i); - i++; - a3700_spi->buf_len--; - - spireg_write(a3700_spi, A3700_SPI_DATA_OUT_REG, - val); - } - break; - } + val = cpu_to_le32(*(u32 *)a3700_spi->tx_buf); + spireg_write(a3700_spi, A3700_SPI_DATA_OUT_REG, val); + a3700_spi->buf_len -= 4; + a3700_spi->tx_buf += 4; } return 0; @@ -645,15 +602,18 @@ static int a3700_spi_transfer_one(struct spi_master *master, a3700_spi->rx_buf = xfer->rx_buf; a3700_spi->buf_len = xfer->len; - /* SPI transfer headers */ - a3700_spi_header_set(a3700_spi); - if (xfer->tx_buf) nbits = xfer->tx_nbits; else if (xfer->rx_buf) nbits = xfer->rx_nbits; - a3700_spi_pin_mode_set(a3700_spi, nbits); + a3700_spi_pin_mode_set(a3700_spi, nbits, xfer->rx_buf ? true : false); + + /* Flush the FIFOs */ + a3700_spi_fifo_flush(a3700_spi); + + /* Transfer first bytes of data when buffer is not 4-byte aligned */ + a3700_spi_header_set(a3700_spi); if (xfer->rx_buf) { /* Set read data length */ @@ -733,16 +693,11 @@ static int a3700_spi_transfer_one(struct spi_master *master, dev_err(&spi->dev, "wait wfifo empty timed out\n"); return -ETIMEDOUT; } - } else { - /* - * If the instruction in SPI_INSTR does not require data - * to be written to the SPI device, wait until SPI_RDY - * is 1 for the SPI interface to be in idle. - */ - if (!a3700_spi_transfer_wait(spi, A3700_SPI_XFER_RDY)) { - dev_err(&spi->dev, "wait xfer ready timed out\n"); - return -ETIMEDOUT; - } + } + + if (!a3700_spi_transfer_wait(spi, A3700_SPI_XFER_RDY)) { + dev_err(&spi->dev, "wait xfer ready timed out\n"); + return -ETIMEDOUT; } val = spireg_read(a3700_spi, A3700_SPI_IF_CFG_REG); @@ -834,10 +789,6 @@ static int a3700_spi_probe(struct platform_device *pdev) memset(spi, 0, sizeof(struct a3700_spi)); spi->master = master; - spi->instr_cnt = A3700_INSTR_CNT; - spi->addr_cnt = A3700_ADDR_CNT; - spi->hdr_cnt = A3700_INSTR_CNT + A3700_ADDR_CNT + - A3700_DUMMY_CNT; res = platform_get_resource(pdev, IORESOURCE_MEM, 0); spi->base = devm_ioremap_resource(dev, res); diff --git a/drivers/spi/spi-bcm-qspi.c b/drivers/spi/spi-bcm-qspi.c index 6ef6c44f39f5..a172ab299e80 100644 --- a/drivers/spi/spi-bcm-qspi.c +++ b/drivers/spi/spi-bcm-qspi.c @@ -1250,7 +1250,7 @@ int bcm_qspi_probe(struct platform_device *pdev, goto qspi_probe_err; } } else { - goto qspi_probe_err; + goto qspi_resource_err; } res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "bspi"); @@ -1272,7 +1272,7 @@ int bcm_qspi_probe(struct platform_device *pdev, qspi->base[CHIP_SELECT] = devm_ioremap_resource(dev, res); if (IS_ERR(qspi->base[CHIP_SELECT])) { ret = PTR_ERR(qspi->base[CHIP_SELECT]); - goto qspi_probe_err; + goto qspi_resource_err; } } @@ -1280,7 +1280,7 @@ int bcm_qspi_probe(struct platform_device *pdev, GFP_KERNEL); if (!qspi->dev_ids) { ret = -ENOMEM; - goto qspi_probe_err; + goto qspi_resource_err; } for (val = 0; val < num_irqs; val++) { @@ -1369,8 +1369,9 @@ qspi_reg_err: bcm_qspi_hw_uninit(qspi); clk_disable_unprepare(qspi->clk); qspi_probe_err: - spi_master_put(master); kfree(qspi->dev_ids); +qspi_resource_err: + spi_master_put(master); return ret; } /* probe function to be called by SoC specific platform driver probe */ diff --git a/drivers/spi/spi-stm32.c b/drivers/spi/spi-stm32.c index 680cdf549506..ba9743fa2326 100644 --- a/drivers/spi/spi-stm32.c +++ b/drivers/spi/spi-stm32.c @@ -263,8 +263,8 @@ static int stm32_spi_prepare_mbr(struct stm32_spi *spi, u32 speed_hz) * no need to check it there. * However, we need to ensure the following calculations. */ - if ((div < SPI_MBR_DIV_MIN) && - (div > SPI_MBR_DIV_MAX)) + if (div < SPI_MBR_DIV_MIN || + div > SPI_MBR_DIV_MAX) return -EINVAL; /* Determine the first power of 2 greater than or equal to div */ diff --git a/drivers/spi/spi.c b/drivers/spi/spi.c index 6e65524cbfd9..e8b5a5e21b2e 100644 --- a/drivers/spi/spi.c +++ b/drivers/spi/spi.c @@ -45,7 +45,6 @@ #define CREATE_TRACE_POINTS #include <trace/events/spi.h> -#define SPI_DYN_FIRST_BUS_NUM 0 static DEFINE_IDR(spi_master_idr); @@ -2086,7 +2085,7 @@ int spi_register_controller(struct spi_controller *ctlr) struct device *dev = ctlr->dev.parent; struct boardinfo *bi; int status = -ENODEV; - int id; + int id, first_dynamic; if (!dev) return -ENODEV; @@ -2116,9 +2115,15 @@ int spi_register_controller(struct spi_controller *ctlr) } } if (ctlr->bus_num < 0) { + first_dynamic = of_alias_get_highest_id("spi"); + if (first_dynamic < 0) + first_dynamic = 0; + else + first_dynamic++; + mutex_lock(&board_lock); - id = idr_alloc(&spi_master_idr, ctlr, SPI_DYN_FIRST_BUS_NUM, 0, - GFP_KERNEL); + id = idr_alloc(&spi_master_idr, ctlr, first_dynamic, + 0, GFP_KERNEL); mutex_unlock(&board_lock); if (WARN(id < 0, "couldn't get idr")) return id; diff --git a/drivers/staging/iio/meter/ade7759.c b/drivers/staging/iio/meter/ade7759.c index 1691760339da..02573c517d9d 100644 --- a/drivers/staging/iio/meter/ade7759.c +++ b/drivers/staging/iio/meter/ade7759.c @@ -172,7 +172,7 @@ static int ade7759_spi_read_reg_40(struct device *dev, reg_address); goto error_ret; } - *val = ((u64)st->rx[1] << 32) | (st->rx[2] << 24) | + *val = ((u64)st->rx[1] << 32) | ((u64)st->rx[2] << 24) | (st->rx[3] << 16) | (st->rx[4] << 8) | st->rx[5]; error_ret: diff --git a/drivers/staging/media/imx/imx-media-dev.c b/drivers/staging/media/imx/imx-media-dev.c index d96f4512224f..b55e5ebba8b4 100644 --- a/drivers/staging/media/imx/imx-media-dev.c +++ b/drivers/staging/media/imx/imx-media-dev.c @@ -400,10 +400,10 @@ static int imx_media_create_pad_vdev_lists(struct imx_media_dev *imxmd) struct media_link, list); ret = imx_media_add_vdev_to_pad(imxmd, vdev, link->source); if (ret) - break; + return ret; } - return ret; + return 0; } /* async subdev complete notifier */ diff --git a/drivers/staging/vc04_services/bcm2835-audio/bcm2835-vchiq.c b/drivers/staging/vc04_services/bcm2835-audio/bcm2835-vchiq.c index 5f3d8f2339e3..4be864dbd41c 100644 --- a/drivers/staging/vc04_services/bcm2835-audio/bcm2835-vchiq.c +++ b/drivers/staging/vc04_services/bcm2835-audio/bcm2835-vchiq.c @@ -390,8 +390,7 @@ static int bcm2835_audio_open_connection(struct bcm2835_alsa_stream *alsa_stream __func__, instance); instance->alsa_stream = alsa_stream; alsa_stream->instance = instance; - ret = 0; // xxx todo -1; - goto err_free_mem; + return 0; } /* Initialize and create a VCHI connection */ @@ -401,16 +400,15 @@ static int bcm2835_audio_open_connection(struct bcm2835_alsa_stream *alsa_stream LOG_ERR("%s: failed to initialise VCHI instance (ret=%d)\n", __func__, ret); - ret = -EIO; - goto err_free_mem; + return -EIO; } ret = vchi_connect(NULL, 0, vchi_instance); if (ret) { LOG_ERR("%s: failed to connect VCHI instance (ret=%d)\n", __func__, ret); - ret = -EIO; - goto err_free_mem; + kfree(vchi_instance); + return -EIO; } initted = 1; } @@ -421,19 +419,16 @@ static int bcm2835_audio_open_connection(struct bcm2835_alsa_stream *alsa_stream if (IS_ERR(instance)) { LOG_ERR("%s: failed to initialize audio service\n", __func__); - ret = PTR_ERR(instance); - goto err_free_mem; + /* vchi_instance is retained for use the next time. */ + return PTR_ERR(instance); } instance->alsa_stream = alsa_stream; alsa_stream->instance = instance; LOG_DBG(" success !\n"); - ret = 0; -err_free_mem: - kfree(vchi_instance); - return ret; + return 0; } int bcm2835_audio_open(struct bcm2835_alsa_stream *alsa_stream) diff --git a/drivers/tty/tty_ldisc.c b/drivers/tty/tty_ldisc.c index 2fe216b276e2..84a8ac2a779f 100644 --- a/drivers/tty/tty_ldisc.c +++ b/drivers/tty/tty_ldisc.c @@ -694,10 +694,8 @@ int tty_ldisc_reinit(struct tty_struct *tty, int disc) tty_set_termios_ldisc(tty, disc); retval = tty_ldisc_open(tty, tty->ldisc); if (retval) { - if (!WARN_ON(disc == N_TTY)) { - tty_ldisc_put(tty->ldisc); - tty->ldisc = NULL; - } + tty_ldisc_put(tty->ldisc); + tty->ldisc = NULL; } return retval; } @@ -752,8 +750,9 @@ void tty_ldisc_hangup(struct tty_struct *tty, bool reinit) if (tty->ldisc) { if (reinit) { - if (tty_ldisc_reinit(tty, tty->termios.c_line) < 0) - tty_ldisc_reinit(tty, N_TTY); + if (tty_ldisc_reinit(tty, tty->termios.c_line) < 0 && + tty_ldisc_reinit(tty, N_TTY) < 0) + WARN_ON(tty_ldisc_reinit(tty, N_NULL) < 0); } else tty_ldisc_kill(tty); } diff --git a/drivers/usb/class/cdc-acm.c b/drivers/usb/class/cdc-acm.c index 5e056064259c..18c923a4c16e 100644 --- a/drivers/usb/class/cdc-acm.c +++ b/drivers/usb/class/cdc-acm.c @@ -1832,6 +1832,9 @@ static const struct usb_device_id acm_ids[] = { { USB_DEVICE(0xfff0, 0x0100), /* DATECS FP-2000 */ .driver_info = NO_UNION_NORMAL, /* reports zero length descriptor */ }, + { USB_DEVICE(0x09d8, 0x0320), /* Elatec GmbH TWN3 */ + .driver_info = NO_UNION_NORMAL, /* has misplaced union descriptor */ + }, { USB_DEVICE(0x2912, 0x0001), /* ATOL FPrint */ .driver_info = CLEAR_HALT_CONDITIONS, diff --git a/drivers/usb/core/config.c b/drivers/usb/core/config.c index 68b54bd88d1e..883549ee946c 100644 --- a/drivers/usb/core/config.c +++ b/drivers/usb/core/config.c @@ -960,10 +960,12 @@ int usb_get_bos_descriptor(struct usb_device *dev) for (i = 0; i < num; i++) { buffer += length; cap = (struct usb_dev_cap_header *)buffer; - length = cap->bLength; - if (total_len < length) + if (total_len < sizeof(*cap) || total_len < cap->bLength) { + dev->bos->desc->bNumDeviceCaps = i; break; + } + length = cap->bLength; total_len -= length; if (cap->bDescriptorType != USB_DT_DEVICE_CAPABILITY) { diff --git a/drivers/usb/core/devio.c b/drivers/usb/core/devio.c index 4664e543cf2f..e9326f31db8d 100644 --- a/drivers/usb/core/devio.c +++ b/drivers/usb/core/devio.c @@ -1576,11 +1576,7 @@ static int proc_do_submiturb(struct usb_dev_state *ps, struct usbdevfs_urb *uurb totlen += isopkt[u].length; } u *= sizeof(struct usb_iso_packet_descriptor); - if (totlen <= uurb->buffer_length) - uurb->buffer_length = totlen; - else - WARN_ONCE(1, "uurb->buffer_length is too short %d vs %d", - totlen, uurb->buffer_length); + uurb->buffer_length = totlen; break; default: diff --git a/drivers/usb/core/hub.c b/drivers/usb/core/hub.c index b5c733613823..e9ce6bb0b22d 100644 --- a/drivers/usb/core/hub.c +++ b/drivers/usb/core/hub.c @@ -2710,13 +2710,16 @@ static int hub_port_wait_reset(struct usb_hub *hub, int port1, if (!(portstatus & USB_PORT_STAT_CONNECTION)) return -ENOTCONN; - /* bomb out completely if the connection bounced. A USB 3.0 - * connection may bounce if multiple warm resets were issued, + /* Retry if connect change is set but status is still connected. + * A USB 3.0 connection may bounce if multiple warm resets were issued, * but the device may have successfully re-connected. Ignore it. */ if (!hub_is_superspeed(hub->hdev) && - (portchange & USB_PORT_STAT_C_CONNECTION)) - return -ENOTCONN; + (portchange & USB_PORT_STAT_C_CONNECTION)) { + usb_clear_port_feature(hub->hdev, port1, + USB_PORT_FEAT_C_CONNECTION); + return -EAGAIN; + } if (!(portstatus & USB_PORT_STAT_ENABLE)) return -EBUSY; diff --git a/drivers/usb/core/quirks.c b/drivers/usb/core/quirks.c index 82806e311202..a6aaf2f193a4 100644 --- a/drivers/usb/core/quirks.c +++ b/drivers/usb/core/quirks.c @@ -221,6 +221,10 @@ static const struct usb_device_id usb_quirk_list[] = { /* Corsair Strafe RGB */ { USB_DEVICE(0x1b1c, 0x1b20), .driver_info = USB_QUIRK_DELAY_INIT }, + /* MIDI keyboard WORLDE MINI */ + { USB_DEVICE(0x1c75, 0x0204), .driver_info = + USB_QUIRK_CONFIG_INTF_STRINGS }, + /* Acer C120 LED Projector */ { USB_DEVICE(0x1de1, 0xc102), .driver_info = USB_QUIRK_NO_LPM }, diff --git a/drivers/usb/gadget/composite.c b/drivers/usb/gadget/composite.c index dd74c99d6ce1..5d061b3d8224 100644 --- a/drivers/usb/gadget/composite.c +++ b/drivers/usb/gadget/composite.c @@ -2026,6 +2026,8 @@ static DEVICE_ATTR_RO(suspended); static void __composite_unbind(struct usb_gadget *gadget, bool unbind_driver) { struct usb_composite_dev *cdev = get_gadget_data(gadget); + struct usb_gadget_strings *gstr = cdev->driver->strings[0]; + struct usb_string *dev_str = gstr->strings; /* composite_disconnect() must already have been called * by the underlying peripheral controller driver! @@ -2045,6 +2047,9 @@ static void __composite_unbind(struct usb_gadget *gadget, bool unbind_driver) composite_dev_cleanup(cdev); + if (dev_str[USB_GADGET_MANUFACTURER_IDX].s == cdev->def_manufacturer) + dev_str[USB_GADGET_MANUFACTURER_IDX].s = ""; + kfree(cdev->def_manufacturer); kfree(cdev); set_gadget_data(gadget, NULL); diff --git a/drivers/usb/gadget/configfs.c b/drivers/usb/gadget/configfs.c index a22a892de7b7..aeb9f3c40521 100644 --- a/drivers/usb/gadget/configfs.c +++ b/drivers/usb/gadget/configfs.c @@ -1143,11 +1143,12 @@ static struct configfs_attribute *interf_grp_attrs[] = { NULL }; -int usb_os_desc_prepare_interf_dir(struct config_group *parent, - int n_interf, - struct usb_os_desc **desc, - char **names, - struct module *owner) +struct config_group *usb_os_desc_prepare_interf_dir( + struct config_group *parent, + int n_interf, + struct usb_os_desc **desc, + char **names, + struct module *owner) { struct config_group *os_desc_group; struct config_item_type *os_desc_type, *interface_type; @@ -1159,7 +1160,7 @@ int usb_os_desc_prepare_interf_dir(struct config_group *parent, char *vlabuf = kzalloc(vla_group_size(data_chunk), GFP_KERNEL); if (!vlabuf) - return -ENOMEM; + return ERR_PTR(-ENOMEM); os_desc_group = vla_ptr(vlabuf, data_chunk, os_desc_group); os_desc_type = vla_ptr(vlabuf, data_chunk, os_desc_type); @@ -1184,7 +1185,7 @@ int usb_os_desc_prepare_interf_dir(struct config_group *parent, configfs_add_default_group(&d->group, os_desc_group); } - return 0; + return os_desc_group; } EXPORT_SYMBOL(usb_os_desc_prepare_interf_dir); diff --git a/drivers/usb/gadget/configfs.h b/drivers/usb/gadget/configfs.h index 36c468c4f5e9..540d5e92ed22 100644 --- a/drivers/usb/gadget/configfs.h +++ b/drivers/usb/gadget/configfs.h @@ -5,11 +5,12 @@ void unregister_gadget_item(struct config_item *item); -int usb_os_desc_prepare_interf_dir(struct config_group *parent, - int n_interf, - struct usb_os_desc **desc, - char **names, - struct module *owner); +struct config_group *usb_os_desc_prepare_interf_dir( + struct config_group *parent, + int n_interf, + struct usb_os_desc **desc, + char **names, + struct module *owner); static inline struct usb_os_desc *to_usb_os_desc(struct config_item *item) { diff --git a/drivers/usb/gadget/function/f_rndis.c b/drivers/usb/gadget/function/f_rndis.c index e1d5853ef1e4..c7c5b3ce1d98 100644 --- a/drivers/usb/gadget/function/f_rndis.c +++ b/drivers/usb/gadget/function/f_rndis.c @@ -908,6 +908,7 @@ static void rndis_free_inst(struct usb_function_instance *f) free_netdev(opts->net); } + kfree(opts->rndis_interf_group); /* single VLA chunk */ kfree(opts); } @@ -916,6 +917,7 @@ static struct usb_function_instance *rndis_alloc_inst(void) struct f_rndis_opts *opts; struct usb_os_desc *descs[1]; char *names[1]; + struct config_group *rndis_interf_group; opts = kzalloc(sizeof(*opts), GFP_KERNEL); if (!opts) @@ -940,8 +942,14 @@ static struct usb_function_instance *rndis_alloc_inst(void) names[0] = "rndis"; config_group_init_type_name(&opts->func_inst.group, "", &rndis_func_type); - usb_os_desc_prepare_interf_dir(&opts->func_inst.group, 1, descs, - names, THIS_MODULE); + rndis_interf_group = + usb_os_desc_prepare_interf_dir(&opts->func_inst.group, 1, descs, + names, THIS_MODULE); + if (IS_ERR(rndis_interf_group)) { + rndis_free_inst(&opts->func_inst); + return ERR_CAST(rndis_interf_group); + } + opts->rndis_interf_group = rndis_interf_group; return &opts->func_inst; } diff --git a/drivers/usb/gadget/function/u_rndis.h b/drivers/usb/gadget/function/u_rndis.h index a35ee3c2545d..efdb7ac381d9 100644 --- a/drivers/usb/gadget/function/u_rndis.h +++ b/drivers/usb/gadget/function/u_rndis.h @@ -26,6 +26,7 @@ struct f_rndis_opts { bool bound; bool borrowed_net; + struct config_group *rndis_interf_group; struct usb_os_desc rndis_os_desc; char rndis_ext_compat_id[16]; diff --git a/drivers/usb/gadget/udc/dummy_hcd.c b/drivers/usb/gadget/udc/dummy_hcd.c index b17618a55f1b..f04e91ef9e7c 100644 --- a/drivers/usb/gadget/udc/dummy_hcd.c +++ b/drivers/usb/gadget/udc/dummy_hcd.c @@ -419,6 +419,7 @@ static void set_link_state_by_speed(struct dummy_hcd *dum_hcd) static void set_link_state(struct dummy_hcd *dum_hcd) { struct dummy *dum = dum_hcd->dum; + unsigned int power_bit; dum_hcd->active = 0; if (dum->pullup) @@ -429,17 +430,19 @@ static void set_link_state(struct dummy_hcd *dum_hcd) return; set_link_state_by_speed(dum_hcd); + power_bit = (dummy_hcd_to_hcd(dum_hcd)->speed == HCD_USB3 ? + USB_SS_PORT_STAT_POWER : USB_PORT_STAT_POWER); if ((dum_hcd->port_status & USB_PORT_STAT_ENABLE) == 0 || dum_hcd->active) dum_hcd->resuming = 0; /* Currently !connected or in reset */ - if ((dum_hcd->port_status & USB_PORT_STAT_CONNECTION) == 0 || + if ((dum_hcd->port_status & power_bit) == 0 || (dum_hcd->port_status & USB_PORT_STAT_RESET) != 0) { - unsigned disconnect = USB_PORT_STAT_CONNECTION & + unsigned int disconnect = power_bit & dum_hcd->old_status & (~dum_hcd->port_status); - unsigned reset = USB_PORT_STAT_RESET & + unsigned int reset = USB_PORT_STAT_RESET & (~dum_hcd->old_status) & dum_hcd->port_status; /* Report reset and disconnect events to the driver */ diff --git a/drivers/usb/host/xhci-hub.c b/drivers/usb/host/xhci-hub.c index da9158f171cb..a2336deb5e36 100644 --- a/drivers/usb/host/xhci-hub.c +++ b/drivers/usb/host/xhci-hub.c @@ -420,14 +420,25 @@ static int xhci_stop_device(struct xhci_hcd *xhci, int slot_id, int suspend) GFP_NOWAIT); if (!command) { spin_unlock_irqrestore(&xhci->lock, flags); - xhci_free_command(xhci, cmd); - return -ENOMEM; + ret = -ENOMEM; + goto cmd_cleanup; + } + + ret = xhci_queue_stop_endpoint(xhci, command, slot_id, + i, suspend); + if (ret) { + spin_unlock_irqrestore(&xhci->lock, flags); + xhci_free_command(xhci, command); + goto cmd_cleanup; } - xhci_queue_stop_endpoint(xhci, command, slot_id, i, - suspend); } } - xhci_queue_stop_endpoint(xhci, cmd, slot_id, 0, suspend); + ret = xhci_queue_stop_endpoint(xhci, cmd, slot_id, 0, suspend); + if (ret) { + spin_unlock_irqrestore(&xhci->lock, flags); + goto cmd_cleanup; + } + xhci_ring_cmd_db(xhci); spin_unlock_irqrestore(&xhci->lock, flags); @@ -439,6 +450,8 @@ static int xhci_stop_device(struct xhci_hcd *xhci, int slot_id, int suspend) xhci_warn(xhci, "Timeout while waiting for stop endpoint command\n"); ret = -ETIME; } + +cmd_cleanup: xhci_free_command(xhci, cmd); return ret; } diff --git a/drivers/usb/host/xhci-ring.c b/drivers/usb/host/xhci-ring.c index a9443651ce0f..82c746e2d85c 100644 --- a/drivers/usb/host/xhci-ring.c +++ b/drivers/usb/host/xhci-ring.c @@ -1309,6 +1309,7 @@ static void xhci_complete_del_and_free_cmd(struct xhci_command *cmd, u32 status) void xhci_cleanup_command_queue(struct xhci_hcd *xhci) { struct xhci_command *cur_cmd, *tmp_cmd; + xhci->current_cmd = NULL; list_for_each_entry_safe(cur_cmd, tmp_cmd, &xhci->cmd_list, cmd_list) xhci_complete_del_and_free_cmd(cur_cmd, COMP_COMMAND_ABORTED); } @@ -2579,15 +2580,21 @@ static int handle_tx_event(struct xhci_hcd *xhci, (struct xhci_generic_trb *) ep_trb); /* - * No-op TRB should not trigger interrupts. - * If ep_trb is a no-op TRB, it means the - * corresponding TD has been cancelled. Just ignore - * the TD. + * No-op TRB could trigger interrupts in a case where + * a URB was killed and a STALL_ERROR happens right + * after the endpoint ring stopped. Reset the halted + * endpoint. Otherwise, the endpoint remains stalled + * indefinitely. */ if (trb_is_noop(ep_trb)) { - xhci_dbg(xhci, - "ep_trb is a no-op TRB. Skip it for slot %u ep %u\n", - slot_id, ep_index); + if (trb_comp_code == COMP_STALL_ERROR || + xhci_requires_manual_halt_cleanup(xhci, ep_ctx, + trb_comp_code)) + xhci_cleanup_halted_endpoint(xhci, slot_id, + ep_index, + ep_ring->stream_id, + td, ep_trb, + EP_HARD_RESET); goto cleanup; } diff --git a/drivers/usb/host/xhci.c b/drivers/usb/host/xhci.c index ee198ea47f49..51535ba2bcd4 100644 --- a/drivers/usb/host/xhci.c +++ b/drivers/usb/host/xhci.c @@ -4805,7 +4805,8 @@ int xhci_gen_setup(struct usb_hcd *hcd, xhci_get_quirks_t get_quirks) */ hcd->has_tt = 1; } else { - if (xhci->sbrn == 0x31) { + /* Some 3.1 hosts return sbrn 0x30, can't rely on sbrn alone */ + if (xhci->sbrn == 0x31 || xhci->usb3_rhub.min_rev >= 1) { xhci_info(xhci, "Host supports USB 3.1 Enhanced SuperSpeed\n"); hcd->speed = HCD_USB31; hcd->self.root_hub->speed = USB_SPEED_SUPER_PLUS; diff --git a/drivers/usb/misc/usbtest.c b/drivers/usb/misc/usbtest.c index eee82ca55b7b..b3fc602b2e24 100644 --- a/drivers/usb/misc/usbtest.c +++ b/drivers/usb/misc/usbtest.c @@ -202,12 +202,13 @@ found: return tmp; } - if (in) { + if (in) dev->in_pipe = usb_rcvbulkpipe(udev, in->desc.bEndpointAddress & USB_ENDPOINT_NUMBER_MASK); + if (out) dev->out_pipe = usb_sndbulkpipe(udev, out->desc.bEndpointAddress & USB_ENDPOINT_NUMBER_MASK); - } + if (iso_in) { dev->iso_in = &iso_in->desc; dev->in_iso_pipe = usb_rcvisocpipe(udev, @@ -1964,6 +1965,9 @@ test_queue(struct usbtest_dev *dev, struct usbtest_param_32 *param, int status = 0; struct urb *urbs[param->sglen]; + if (!param->sglen || param->iterations > UINT_MAX / param->sglen) + return -EINVAL; + memset(&context, 0, sizeof(context)); context.count = param->iterations * param->sglen; context.dev = dev; @@ -2087,6 +2091,8 @@ usbtest_do_ioctl(struct usb_interface *intf, struct usbtest_param_32 *param) if (param->iterations <= 0) return -EINVAL; + if (param->sglen > MAX_SGLEN) + return -EINVAL; /* * Just a bunch of test cases that every HCD is expected to handle. * diff --git a/drivers/usb/musb/musb_core.c b/drivers/usb/musb/musb_core.c index 029692053dd3..ff5a1a8989d5 100644 --- a/drivers/usb/musb/musb_core.c +++ b/drivers/usb/musb/musb_core.c @@ -906,7 +906,7 @@ b_host: */ if (int_usb & MUSB_INTR_RESET) { handled = IRQ_HANDLED; - if (devctl & MUSB_DEVCTL_HM) { + if (is_host_active(musb)) { /* * When BABBLE happens what we can depends on which * platform MUSB is running, because some platforms @@ -916,9 +916,7 @@ b_host: * drop the session. */ dev_err(musb->controller, "Babble\n"); - - if (is_host_active(musb)) - musb_recover_from_babble(musb); + musb_recover_from_babble(musb); } else { musb_dbg(musb, "BUS RESET as %s", usb_otg_state_string(musb->xceiv->otg->state)); @@ -1861,22 +1859,22 @@ static void musb_pm_runtime_check_session(struct musb *musb) MUSB_DEVCTL_HR; switch (devctl & ~s) { case MUSB_QUIRK_B_INVALID_VBUS_91: - if (musb->quirk_retries--) { + if (musb->quirk_retries && !musb->flush_irq_work) { musb_dbg(musb, "Poll devctl on invalid vbus, assume no session"); schedule_delayed_work(&musb->irq_work, msecs_to_jiffies(1000)); - + musb->quirk_retries--; return; } /* fall through */ case MUSB_QUIRK_A_DISCONNECT_19: - if (musb->quirk_retries--) { + if (musb->quirk_retries && !musb->flush_irq_work) { musb_dbg(musb, "Poll devctl on possible host mode disconnect"); schedule_delayed_work(&musb->irq_work, msecs_to_jiffies(1000)); - + musb->quirk_retries--; return; } if (!musb->session) @@ -2681,8 +2679,15 @@ static int musb_suspend(struct device *dev) musb_platform_disable(musb); musb_disable_interrupts(musb); + + musb->flush_irq_work = true; + while (flush_delayed_work(&musb->irq_work)) + ; + musb->flush_irq_work = false; + if (!(musb->io.quirks & MUSB_PRESERVE_SESSION)) musb_writeb(musb->mregs, MUSB_DEVCTL, 0); + WARN_ON(!list_empty(&musb->pending_list)); spin_lock_irqsave(&musb->lock, flags); diff --git a/drivers/usb/musb/musb_core.h b/drivers/usb/musb/musb_core.h index c748f4ac1154..20f4614178d9 100644 --- a/drivers/usb/musb/musb_core.h +++ b/drivers/usb/musb/musb_core.h @@ -428,6 +428,8 @@ struct musb { unsigned test_mode:1; unsigned softconnect:1; + unsigned flush_irq_work:1; + u8 address; u8 test_mode_nr; u16 ackpend; /* ep0 */ diff --git a/drivers/usb/musb/musb_cppi41.c b/drivers/usb/musb/musb_cppi41.c index ba255280a624..1ec0a4947b6b 100644 --- a/drivers/usb/musb/musb_cppi41.c +++ b/drivers/usb/musb/musb_cppi41.c @@ -26,15 +26,28 @@ #define MUSB_DMA_NUM_CHANNELS 15 +#define DA8XX_USB_MODE 0x10 +#define DA8XX_USB_AUTOREQ 0x14 +#define DA8XX_USB_TEARDOWN 0x1c + +#define DA8XX_DMA_NUM_CHANNELS 4 + struct cppi41_dma_controller { struct dma_controller controller; - struct cppi41_dma_channel rx_channel[MUSB_DMA_NUM_CHANNELS]; - struct cppi41_dma_channel tx_channel[MUSB_DMA_NUM_CHANNELS]; + struct cppi41_dma_channel *rx_channel; + struct cppi41_dma_channel *tx_channel; struct hrtimer early_tx; struct list_head early_tx_list; u32 rx_mode; u32 tx_mode; u32 auto_req; + + u32 tdown_reg; + u32 autoreq_reg; + + void (*set_dma_mode)(struct cppi41_dma_channel *cppi41_channel, + unsigned int mode); + u8 num_channels; }; static void save_rx_toggle(struct cppi41_dma_channel *cppi41_channel) @@ -349,6 +362,32 @@ static void cppi41_set_dma_mode(struct cppi41_dma_channel *cppi41_channel, } } +static void da8xx_set_dma_mode(struct cppi41_dma_channel *cppi41_channel, + unsigned int mode) +{ + struct cppi41_dma_controller *controller = cppi41_channel->controller; + struct musb *musb = controller->controller.musb; + unsigned int shift; + u32 port; + u32 new_mode; + u32 old_mode; + + old_mode = controller->tx_mode; + port = cppi41_channel->port_num; + + shift = (port - 1) * 4; + if (!cppi41_channel->is_tx) + shift += 16; + new_mode = old_mode & ~(3 << shift); + new_mode |= mode << shift; + + if (new_mode == old_mode) + return; + controller->tx_mode = new_mode; + musb_writel(musb->ctrl_base, DA8XX_USB_MODE, new_mode); +} + + static void cppi41_set_autoreq_mode(struct cppi41_dma_channel *cppi41_channel, unsigned mode) { @@ -364,8 +403,8 @@ static void cppi41_set_autoreq_mode(struct cppi41_dma_channel *cppi41_channel, if (new_mode == old_mode) return; controller->auto_req = new_mode; - musb_writel(controller->controller.musb->ctrl_base, USB_CTRL_AUTOREQ, - new_mode); + musb_writel(controller->controller.musb->ctrl_base, + controller->autoreq_reg, new_mode); } static bool cppi41_configure_channel(struct dma_channel *channel, @@ -373,6 +412,7 @@ static bool cppi41_configure_channel(struct dma_channel *channel, dma_addr_t dma_addr, u32 len) { struct cppi41_dma_channel *cppi41_channel = channel->private_data; + struct cppi41_dma_controller *controller = cppi41_channel->controller; struct dma_chan *dc = cppi41_channel->dc; struct dma_async_tx_descriptor *dma_desc; enum dma_transfer_direction direction; @@ -398,7 +438,7 @@ static bool cppi41_configure_channel(struct dma_channel *channel, musb_writel(musb->ctrl_base, RNDIS_REG(cppi41_channel->port_num), len); /* gen rndis */ - cppi41_set_dma_mode(cppi41_channel, + controller->set_dma_mode(cppi41_channel, EP_MODE_DMA_GEN_RNDIS); /* auto req */ @@ -407,14 +447,15 @@ static bool cppi41_configure_channel(struct dma_channel *channel, } else { musb_writel(musb->ctrl_base, RNDIS_REG(cppi41_channel->port_num), 0); - cppi41_set_dma_mode(cppi41_channel, + controller->set_dma_mode(cppi41_channel, EP_MODE_DMA_TRANSPARENT); cppi41_set_autoreq_mode(cppi41_channel, EP_MODE_AUTOREQ_NONE); } } else { /* fallback mode */ - cppi41_set_dma_mode(cppi41_channel, EP_MODE_DMA_TRANSPARENT); + controller->set_dma_mode(cppi41_channel, + EP_MODE_DMA_TRANSPARENT); cppi41_set_autoreq_mode(cppi41_channel, EP_MODE_AUTOREQ_NONE); len = min_t(u32, packet_sz, len); } @@ -445,7 +486,7 @@ static struct dma_channel *cppi41_dma_channel_allocate(struct dma_controller *c, struct cppi41_dma_channel *cppi41_channel = NULL; u8 ch_num = hw_ep->epnum - 1; - if (ch_num >= MUSB_DMA_NUM_CHANNELS) + if (ch_num >= controller->num_channels) return NULL; if (is_tx) @@ -581,12 +622,13 @@ static int cppi41_dma_channel_abort(struct dma_channel *channel) do { if (is_tx) - musb_writel(musb->ctrl_base, USB_TDOWN, tdbit); + musb_writel(musb->ctrl_base, controller->tdown_reg, + tdbit); ret = dmaengine_terminate_all(cppi41_channel->dc); } while (ret == -EAGAIN); if (is_tx) { - musb_writel(musb->ctrl_base, USB_TDOWN, tdbit); + musb_writel(musb->ctrl_base, controller->tdown_reg, tdbit); csr = musb_readw(epio, MUSB_TXCSR); if (csr & MUSB_TXCSR_TXPKTRDY) { @@ -604,7 +646,7 @@ static void cppi41_release_all_dma_chans(struct cppi41_dma_controller *ctrl) struct dma_chan *dc; int i; - for (i = 0; i < MUSB_DMA_NUM_CHANNELS; i++) { + for (i = 0; i < ctrl->num_channels; i++) { dc = ctrl->tx_channel[i].dc; if (dc) dma_release_channel(dc); @@ -656,7 +698,7 @@ static int cppi41_dma_controller_start(struct cppi41_dma_controller *controller) goto err; ret = -EINVAL; - if (port > MUSB_DMA_NUM_CHANNELS || !port) + if (port > controller->num_channels || !port) goto err; if (is_tx) cppi41_channel = &controller->tx_channel[port - 1]; @@ -697,6 +739,8 @@ void cppi41_dma_controller_destroy(struct dma_controller *c) hrtimer_cancel(&controller->early_tx); cppi41_dma_controller_stop(controller); + kfree(controller->rx_channel); + kfree(controller->tx_channel); kfree(controller); } EXPORT_SYMBOL_GPL(cppi41_dma_controller_destroy); @@ -705,6 +749,7 @@ struct dma_controller * cppi41_dma_controller_create(struct musb *musb, void __iomem *base) { struct cppi41_dma_controller *controller; + int channel_size; int ret = 0; if (!musb->controller->parent->of_node) { @@ -727,12 +772,37 @@ cppi41_dma_controller_create(struct musb *musb, void __iomem *base) controller->controller.is_compatible = cppi41_is_compatible; controller->controller.musb = musb; + if (musb->io.quirks & MUSB_DA8XX) { + controller->tdown_reg = DA8XX_USB_TEARDOWN; + controller->autoreq_reg = DA8XX_USB_AUTOREQ; + controller->set_dma_mode = da8xx_set_dma_mode; + controller->num_channels = DA8XX_DMA_NUM_CHANNELS; + } else { + controller->tdown_reg = USB_TDOWN; + controller->autoreq_reg = USB_CTRL_AUTOREQ; + controller->set_dma_mode = cppi41_set_dma_mode; + controller->num_channels = MUSB_DMA_NUM_CHANNELS; + } + + channel_size = controller->num_channels * + sizeof(struct cppi41_dma_channel); + controller->rx_channel = kzalloc(channel_size, GFP_KERNEL); + if (!controller->rx_channel) + goto rx_channel_alloc_fail; + controller->tx_channel = kzalloc(channel_size, GFP_KERNEL); + if (!controller->tx_channel) + goto tx_channel_alloc_fail; + ret = cppi41_dma_controller_start(controller); if (ret) goto plat_get_fail; return &controller->controller; plat_get_fail: + kfree(controller->tx_channel); +tx_channel_alloc_fail: + kfree(controller->rx_channel); +rx_channel_alloc_fail: kfree(controller); kzalloc_fail: if (ret == -EPROBE_DEFER) diff --git a/drivers/usb/musb/sunxi.c b/drivers/usb/musb/sunxi.c index c9a09b5bb6e5..dc353e24d53c 100644 --- a/drivers/usb/musb/sunxi.c +++ b/drivers/usb/musb/sunxi.c @@ -297,6 +297,8 @@ static int sunxi_musb_exit(struct musb *musb) if (test_bit(SUNXI_MUSB_FL_HAS_SRAM, &glue->flags)) sunxi_sram_release(musb->controller->parent); + devm_usb_put_phy(glue->dev, glue->xceiv); + return 0; } diff --git a/drivers/usb/phy/phy-tegra-usb.c b/drivers/usb/phy/phy-tegra-usb.c index 5fe4a5704bde..ccc2bf5274b4 100644 --- a/drivers/usb/phy/phy-tegra-usb.c +++ b/drivers/usb/phy/phy-tegra-usb.c @@ -329,6 +329,14 @@ static void utmi_phy_clk_disable(struct tegra_usb_phy *phy) unsigned long val; void __iomem *base = phy->regs; + /* + * The USB driver may have already initiated the phy clock + * disable so wait to see if the clock turns off and if not + * then proceed with gating the clock. + */ + if (utmi_wait_register(base + USB_SUSP_CTRL, USB_PHY_CLK_VALID, 0) == 0) + return; + if (phy->is_legacy_phy) { val = readl(base + USB_SUSP_CTRL); val |= USB_SUSP_SET; @@ -351,6 +359,15 @@ static void utmi_phy_clk_enable(struct tegra_usb_phy *phy) unsigned long val; void __iomem *base = phy->regs; + /* + * The USB driver may have already initiated the phy clock + * enable so wait to see if the clock turns on and if not + * then proceed with ungating the clock. + */ + if (utmi_wait_register(base + USB_SUSP_CTRL, USB_PHY_CLK_VALID, + USB_PHY_CLK_VALID) == 0) + return; + if (phy->is_legacy_phy) { val = readl(base + USB_SUSP_CTRL); val |= USB_SUSP_CLR; diff --git a/drivers/usb/renesas_usbhs/fifo.c b/drivers/usb/renesas_usbhs/fifo.c index 68f26904c316..50285b01da92 100644 --- a/drivers/usb/renesas_usbhs/fifo.c +++ b/drivers/usb/renesas_usbhs/fifo.c @@ -857,9 +857,9 @@ static void xfer_work(struct work_struct *work) fifo->name, usbhs_pipe_number(pipe), pkt->length, pkt->zero); usbhs_pipe_running(pipe, 1); - usbhsf_dma_start(pipe, fifo); usbhs_pipe_set_trans_count_if_bulk(pipe, pkt->trans); dma_async_issue_pending(chan); + usbhsf_dma_start(pipe, fifo); usbhs_pipe_enable(pipe); xfer_work_end: diff --git a/drivers/usb/serial/console.c b/drivers/usb/serial/console.c index fdf89800ebc3..43a862a90a77 100644 --- a/drivers/usb/serial/console.c +++ b/drivers/usb/serial/console.c @@ -186,6 +186,7 @@ static int usb_console_setup(struct console *co, char *options) tty_kref_put(tty); reset_open_count: port->port.count = 0; + info->port = NULL; usb_autopm_put_interface(serial->interface); error_get_interface: usb_serial_put(serial); @@ -265,7 +266,7 @@ static struct console usbcons = { void usb_serial_console_disconnect(struct usb_serial *serial) { - if (serial->port[0] == usbcons_info.port) { + if (serial->port[0] && serial->port[0] == usbcons_info.port) { usb_serial_console_exit(); usb_serial_put(serial); } diff --git a/drivers/usb/serial/cp210x.c b/drivers/usb/serial/cp210x.c index 2d945c9f975c..412f812522ee 100644 --- a/drivers/usb/serial/cp210x.c +++ b/drivers/usb/serial/cp210x.c @@ -177,6 +177,7 @@ static const struct usb_device_id id_table[] = { { USB_DEVICE(0x1843, 0x0200) }, /* Vaisala USB Instrument Cable */ { USB_DEVICE(0x18EF, 0xE00F) }, /* ELV USB-I2C-Interface */ { USB_DEVICE(0x18EF, 0xE025) }, /* ELV Marble Sound Board 1 */ + { USB_DEVICE(0x18EF, 0xE032) }, /* ELV TFD500 Data Logger */ { USB_DEVICE(0x1901, 0x0190) }, /* GE B850 CP2105 Recorder interface */ { USB_DEVICE(0x1901, 0x0193) }, /* GE B650 CP2104 PMC interface */ { USB_DEVICE(0x1901, 0x0194) }, /* GE Healthcare Remote Alarm Box */ @@ -352,6 +353,7 @@ static struct usb_serial_driver * const serial_drivers[] = { #define CP210X_PARTNUM_CP2104 0x04 #define CP210X_PARTNUM_CP2105 0x05 #define CP210X_PARTNUM_CP2108 0x08 +#define CP210X_PARTNUM_UNKNOWN 0xFF /* CP210X_GET_COMM_STATUS returns these 0x13 bytes */ struct cp210x_comm_status { @@ -1491,8 +1493,11 @@ static int cp210x_attach(struct usb_serial *serial) result = cp210x_read_vendor_block(serial, REQTYPE_DEVICE_TO_HOST, CP210X_GET_PARTNUM, &priv->partnum, sizeof(priv->partnum)); - if (result < 0) - goto err_free_priv; + if (result < 0) { + dev_warn(&serial->interface->dev, + "querying part number failed\n"); + priv->partnum = CP210X_PARTNUM_UNKNOWN; + } usb_set_serial_data(serial, priv); @@ -1505,10 +1510,6 @@ static int cp210x_attach(struct usb_serial *serial) } return 0; -err_free_priv: - kfree(priv); - - return result; } static void cp210x_disconnect(struct usb_serial *serial) diff --git a/drivers/usb/serial/ftdi_sio.c b/drivers/usb/serial/ftdi_sio.c index 1cec03799cdf..49d1b2d4606d 100644 --- a/drivers/usb/serial/ftdi_sio.c +++ b/drivers/usb/serial/ftdi_sio.c @@ -1015,6 +1015,8 @@ static const struct usb_device_id id_table_combined[] = { { USB_DEVICE(WICED_VID, WICED_USB20706V2_PID) }, { USB_DEVICE(TI_VID, TI_CC3200_LAUNCHPAD_PID), .driver_info = (kernel_ulong_t)&ftdi_jtag_quirk }, + { USB_DEVICE(CYPRESS_VID, CYPRESS_WICED_BT_USB_PID) }, + { USB_DEVICE(CYPRESS_VID, CYPRESS_WICED_WL_USB_PID) }, { } /* Terminating entry */ }; diff --git a/drivers/usb/serial/ftdi_sio_ids.h b/drivers/usb/serial/ftdi_sio_ids.h index 4fcf1cecb6d7..f9d15bd62785 100644 --- a/drivers/usb/serial/ftdi_sio_ids.h +++ b/drivers/usb/serial/ftdi_sio_ids.h @@ -610,6 +610,13 @@ #define ADI_GNICEPLUS_PID 0xF001 /* + * Cypress WICED USB UART + */ +#define CYPRESS_VID 0x04B4 +#define CYPRESS_WICED_BT_USB_PID 0x009B +#define CYPRESS_WICED_WL_USB_PID 0xF900 + +/* * Microchip Technology, Inc. * * MICROCHIP_VID (0x04D8) and MICROCHIP_USB_BOARD_PID (0x000A) are diff --git a/drivers/usb/serial/metro-usb.c b/drivers/usb/serial/metro-usb.c index cc84da8dbb84..14511d6a7d44 100644 --- a/drivers/usb/serial/metro-usb.c +++ b/drivers/usb/serial/metro-usb.c @@ -45,6 +45,7 @@ struct metrousb_private { static const struct usb_device_id id_table[] = { { USB_DEVICE(FOCUS_VENDOR_ID, FOCUS_PRODUCT_ID_BI) }, { USB_DEVICE(FOCUS_VENDOR_ID, FOCUS_PRODUCT_ID_UNI) }, + { USB_DEVICE_INTERFACE_CLASS(0x0c2e, 0x0730, 0xff) }, /* MS7820 */ { }, /* Terminating entry. */ }; MODULE_DEVICE_TABLE(usb, id_table); diff --git a/drivers/usb/serial/option.c b/drivers/usb/serial/option.c index 54bfef13966a..ba672cf4e888 100644 --- a/drivers/usb/serial/option.c +++ b/drivers/usb/serial/option.c @@ -522,6 +522,7 @@ static void option_instat_callback(struct urb *urb); /* TP-LINK Incorporated products */ #define TPLINK_VENDOR_ID 0x2357 +#define TPLINK_PRODUCT_LTE 0x000D #define TPLINK_PRODUCT_MA180 0x0201 /* Changhong products */ @@ -2011,6 +2012,7 @@ static const struct usb_device_id option_ids[] = { { USB_DEVICE(CELLIENT_VENDOR_ID, CELLIENT_PRODUCT_MEN200) }, { USB_DEVICE(PETATEL_VENDOR_ID, PETATEL_PRODUCT_NP10T_600A) }, { USB_DEVICE(PETATEL_VENDOR_ID, PETATEL_PRODUCT_NP10T_600E) }, + { USB_DEVICE_AND_INTERFACE_INFO(TPLINK_VENDOR_ID, TPLINK_PRODUCT_LTE, 0xff, 0x00, 0x00) }, /* TP-Link LTE Module */ { USB_DEVICE(TPLINK_VENDOR_ID, TPLINK_PRODUCT_MA180), .driver_info = (kernel_ulong_t)&net_intf4_blacklist }, { USB_DEVICE(TPLINK_VENDOR_ID, 0x9000), /* TP-Link MA260 */ diff --git a/drivers/usb/serial/qcserial.c b/drivers/usb/serial/qcserial.c index ebc0beea69d6..eb9928963a53 100644 --- a/drivers/usb/serial/qcserial.c +++ b/drivers/usb/serial/qcserial.c @@ -174,6 +174,10 @@ static const struct usb_device_id id_table[] = { {DEVICE_SWI(0x413c, 0x81b3)}, /* Dell Wireless 5809e Gobi(TM) 4G LTE Mobile Broadband Card (rev3) */ {DEVICE_SWI(0x413c, 0x81b5)}, /* Dell Wireless 5811e QDL */ {DEVICE_SWI(0x413c, 0x81b6)}, /* Dell Wireless 5811e QDL */ + {DEVICE_SWI(0x413c, 0x81cf)}, /* Dell Wireless 5819 */ + {DEVICE_SWI(0x413c, 0x81d0)}, /* Dell Wireless 5819 */ + {DEVICE_SWI(0x413c, 0x81d1)}, /* Dell Wireless 5818 */ + {DEVICE_SWI(0x413c, 0x81d2)}, /* Dell Wireless 5818 */ /* Huawei devices */ {DEVICE_HWI(0x03f0, 0x581d)}, /* HP lt4112 LTE/HSPA+ Gobi 4G Modem (Huawei me906e) */ diff --git a/drivers/xen/gntdev.c b/drivers/xen/gntdev.c index 82360594fa8e..57efbd3b053b 100644 --- a/drivers/xen/gntdev.c +++ b/drivers/xen/gntdev.c @@ -1024,6 +1024,7 @@ static int gntdev_mmap(struct file *flip, struct vm_area_struct *vma) mutex_unlock(&priv->lock); if (use_ptemod) { + map->pages_vm_start = vma->vm_start; err = apply_to_page_range(vma->vm_mm, vma->vm_start, vma->vm_end - vma->vm_start, find_grant_ptes, map); @@ -1061,7 +1062,6 @@ static int gntdev_mmap(struct file *flip, struct vm_area_struct *vma) set_grant_ptes_as_special, NULL); } #endif - map->pages_vm_start = vma->vm_start; } return 0; diff --git a/drivers/xen/xen-balloon.c b/drivers/xen/xen-balloon.c index e89136ab851e..b437fccd4e62 100644 --- a/drivers/xen/xen-balloon.c +++ b/drivers/xen/xen-balloon.c @@ -57,7 +57,7 @@ static int register_balloon(struct device *dev); static void watch_target(struct xenbus_watch *watch, const char *path, const char *token) { - unsigned long long new_target; + unsigned long long new_target, static_max; int err; static bool watch_fired; static long target_diff; @@ -72,13 +72,20 @@ static void watch_target(struct xenbus_watch *watch, * pages. PAGE_SHIFT converts bytes to pages, hence PAGE_SHIFT - 10. */ new_target >>= PAGE_SHIFT - 10; - if (watch_fired) { - balloon_set_new_target(new_target - target_diff); - return; + + if (!watch_fired) { + watch_fired = true; + err = xenbus_scanf(XBT_NIL, "memory", "static-max", "%llu", + &static_max); + if (err != 1) + static_max = new_target; + else + static_max >>= PAGE_SHIFT - 10; + target_diff = xen_pv_domain() ? 0 + : static_max - balloon_stats.target_pages; } - watch_fired = true; - target_diff = new_target - balloon_stats.target_pages; + balloon_set_new_target(new_target - target_diff); } static struct xenbus_watch target_watch = { .node = "memory/target", diff --git a/fs/9p/vfs_addr.c b/fs/9p/vfs_addr.c index adaf6f6dd858..e1cbdfdb7c68 100644 --- a/fs/9p/vfs_addr.c +++ b/fs/9p/vfs_addr.c @@ -310,9 +310,13 @@ static int v9fs_write_end(struct file *filp, struct address_space *mapping, p9_debug(P9_DEBUG_VFS, "filp %p, mapping %p\n", filp, mapping); - if (unlikely(copied < len && !PageUptodate(page))) { - copied = 0; - goto out; + if (!PageUptodate(page)) { + if (unlikely(copied < len)) { + copied = 0; + goto out; + } else if (len == PAGE_SIZE) { + SetPageUptodate(page); + } } /* * No need to use i_size_read() here, the i_size diff --git a/fs/binfmt_misc.c b/fs/binfmt_misc.c index 2a46762def31..a7c5a9861bef 100644 --- a/fs/binfmt_misc.c +++ b/fs/binfmt_misc.c @@ -596,7 +596,7 @@ static void bm_evict_inode(struct inode *inode) { Node *e = inode->i_private; - if (e->flags & MISC_FMT_OPEN_FILE) + if (e && e->flags & MISC_FMT_OPEN_FILE) filp_close(e->interp_file, NULL); clear_inode(inode); diff --git a/fs/block_dev.c b/fs/block_dev.c index 93d088ffc05c..789f55e851ae 100644 --- a/fs/block_dev.c +++ b/fs/block_dev.c @@ -716,10 +716,12 @@ int bdev_write_page(struct block_device *bdev, sector_t sector, set_page_writeback(page); result = ops->rw_page(bdev, sector + get_start_sect(bdev), page, true); - if (result) + if (result) { end_page_writeback(page); - else + } else { + clean_page_buffers(page); unlock_page(page); + } blk_queue_exit(bdev->bd_queue); return result; } diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c index 35a128acfbd1..161694b66038 100644 --- a/fs/btrfs/super.c +++ b/fs/btrfs/super.c @@ -1135,7 +1135,7 @@ static int btrfs_fill_super(struct super_block *sb, #ifdef CONFIG_BTRFS_FS_POSIX_ACL sb->s_flags |= MS_POSIXACL; #endif - sb->s_flags |= MS_I_VERSION; + sb->s_flags |= SB_I_VERSION; sb->s_iflags |= SB_I_CGROUPWB; err = super_setup_bdi(sb); diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c index 157fe59fbabe..1978a8cb1cb1 100644 --- a/fs/ceph/caps.c +++ b/fs/ceph/caps.c @@ -1991,6 +1991,7 @@ static int try_flush_caps(struct inode *inode, u64 *ptid) retry: spin_lock(&ci->i_ceph_lock); if (ci->i_ceph_flags & CEPH_I_NOFLUSH) { + spin_unlock(&ci->i_ceph_lock); dout("try_flush_caps skipping %p I_NOFLUSH set\n", inode); goto out; } @@ -2008,8 +2009,10 @@ retry: mutex_lock(&session->s_mutex); goto retry; } - if (cap->session->s_state < CEPH_MDS_SESSION_OPEN) + if (cap->session->s_state < CEPH_MDS_SESSION_OPEN) { + spin_unlock(&ci->i_ceph_lock); goto out; + } flushing = __mark_caps_flushing(inode, session, true, &flush_tid, &oldest_flush_tid); diff --git a/fs/cifs/Kconfig b/fs/cifs/Kconfig index f7243617316c..d5b2e12b5d02 100644 --- a/fs/cifs/Kconfig +++ b/fs/cifs/Kconfig @@ -5,9 +5,14 @@ config CIFS select CRYPTO select CRYPTO_MD4 select CRYPTO_MD5 + select CRYPTO_SHA256 + select CRYPTO_CMAC select CRYPTO_HMAC select CRYPTO_ARC4 + select CRYPTO_AEAD2 + select CRYPTO_CCM select CRYPTO_ECB + select CRYPTO_AES select CRYPTO_DES help This is the client VFS module for the SMB3 family of NAS protocols, diff --git a/fs/cifs/cifsglob.h b/fs/cifs/cifsglob.h index de5b2e1fcce5..e185b2853eab 100644 --- a/fs/cifs/cifsglob.h +++ b/fs/cifs/cifsglob.h @@ -661,7 +661,9 @@ struct TCP_Server_Info { #endif unsigned int max_read; unsigned int max_write; - __u8 preauth_hash[512]; +#ifdef CONFIG_CIFS_SMB311 + __u8 preauth_sha_hash[64]; /* save initital negprot hash */ +#endif /* 3.1.1 */ struct delayed_work reconnect; /* reconnect workqueue job */ struct mutex reconnect_mutex; /* prevent simultaneous reconnects */ unsigned long echo_interval; @@ -849,7 +851,9 @@ struct cifs_ses { __u8 smb3signingkey[SMB3_SIGN_KEY_SIZE]; __u8 smb3encryptionkey[SMB3_SIGN_KEY_SIZE]; __u8 smb3decryptionkey[SMB3_SIGN_KEY_SIZE]; - __u8 preauth_hash[512]; +#ifdef CONFIG_CIFS_SMB311 + __u8 preauth_sha_hash[64]; +#endif /* 3.1.1 */ }; static inline bool diff --git a/fs/cifs/dir.c b/fs/cifs/dir.c index e702d48bd023..81ba6e0d88d8 100644 --- a/fs/cifs/dir.c +++ b/fs/cifs/dir.c @@ -204,7 +204,8 @@ check_name(struct dentry *direntry, struct cifs_tcon *tcon) struct cifs_sb_info *cifs_sb = CIFS_SB(direntry->d_sb); int i; - if (unlikely(direntry->d_name.len > + if (unlikely(tcon->fsAttrInfo.MaxPathNameComponentLength && + direntry->d_name.len > le32_to_cpu(tcon->fsAttrInfo.MaxPathNameComponentLength))) return -ENAMETOOLONG; @@ -520,7 +521,7 @@ cifs_atomic_open(struct inode *inode, struct dentry *direntry, rc = check_name(direntry, tcon); if (rc) - goto out_free_xid; + goto out; server = tcon->ses->server; diff --git a/fs/cifs/smb2maperror.c b/fs/cifs/smb2maperror.c index 7ca9808a0daa..62c88dfed57b 100644 --- a/fs/cifs/smb2maperror.c +++ b/fs/cifs/smb2maperror.c @@ -214,7 +214,7 @@ static const struct status_to_posix_error smb2_error_map_table[] = { {STATUS_DATATYPE_MISALIGNMENT, -EIO, "STATUS_DATATYPE_MISALIGNMENT"}, {STATUS_BREAKPOINT, -EIO, "STATUS_BREAKPOINT"}, {STATUS_SINGLE_STEP, -EIO, "STATUS_SINGLE_STEP"}, - {STATUS_BUFFER_OVERFLOW, -EIO, "STATUS_BUFFER_OVERFLOW"}, + {STATUS_BUFFER_OVERFLOW, -E2BIG, "STATUS_BUFFER_OVERFLOW"}, {STATUS_NO_MORE_FILES, -ENODATA, "STATUS_NO_MORE_FILES"}, {STATUS_WAKE_SYSTEM_DEBUGGER, -EIO, "STATUS_WAKE_SYSTEM_DEBUGGER"}, {STATUS_HANDLES_CLOSED, -EIO, "STATUS_HANDLES_CLOSED"}, diff --git a/fs/cifs/smb2ops.c b/fs/cifs/smb2ops.c index 0dafdbae1f8c..bdb963d0ba32 100644 --- a/fs/cifs/smb2ops.c +++ b/fs/cifs/smb2ops.c @@ -522,6 +522,7 @@ smb2_query_eas(const unsigned int xid, struct cifs_tcon *tcon, struct cifs_open_parms oparms; struct cifs_fid fid; struct smb2_file_full_ea_info *smb2_data; + int ea_buf_size = SMB2_MIN_EA_BUF; utf16_path = cifs_convert_path_to_utf16(path, cifs_sb); if (!utf16_path) @@ -541,14 +542,32 @@ smb2_query_eas(const unsigned int xid, struct cifs_tcon *tcon, return rc; } - smb2_data = kzalloc(SMB2_MAX_EA_BUF, GFP_KERNEL); - if (smb2_data == NULL) { - SMB2_close(xid, tcon, fid.persistent_fid, fid.volatile_fid); - return -ENOMEM; + while (1) { + smb2_data = kzalloc(ea_buf_size, GFP_KERNEL); + if (smb2_data == NULL) { + SMB2_close(xid, tcon, fid.persistent_fid, + fid.volatile_fid); + return -ENOMEM; + } + + rc = SMB2_query_eas(xid, tcon, fid.persistent_fid, + fid.volatile_fid, + ea_buf_size, smb2_data); + + if (rc != -E2BIG) + break; + + kfree(smb2_data); + ea_buf_size <<= 1; + + if (ea_buf_size > SMB2_MAX_EA_BUF) { + cifs_dbg(VFS, "EA size is too large\n"); + SMB2_close(xid, tcon, fid.persistent_fid, + fid.volatile_fid); + return -ENOMEM; + } } - rc = SMB2_query_eas(xid, tcon, fid.persistent_fid, fid.volatile_fid, - smb2_data); SMB2_close(xid, tcon, fid.persistent_fid, fid.volatile_fid); if (!rc) diff --git a/fs/cifs/smb2pdu.c b/fs/cifs/smb2pdu.c index 6f0e6343c15e..5331631386a2 100644 --- a/fs/cifs/smb2pdu.c +++ b/fs/cifs/smb2pdu.c @@ -648,7 +648,7 @@ int smb3_validate_negotiate(const unsigned int xid, struct cifs_tcon *tcon) { int rc = 0; struct validate_negotiate_info_req vneg_inbuf; - struct validate_negotiate_info_rsp *pneg_rsp; + struct validate_negotiate_info_rsp *pneg_rsp = NULL; u32 rsplen; u32 inbuflen; /* max of 4 dialects */ @@ -727,8 +727,9 @@ int smb3_validate_negotiate(const unsigned int xid, struct cifs_tcon *tcon) rsplen); /* relax check since Mac returns max bufsize allowed on ioctl */ - if (rsplen > CIFSMaxBufSize) - return -EIO; + if ((rsplen > CIFSMaxBufSize) + || (rsplen < sizeof(struct validate_negotiate_info_rsp))) + goto err_rsp_free; } /* check validate negotiate info response matches what we got earlier */ @@ -747,10 +748,13 @@ int smb3_validate_negotiate(const unsigned int xid, struct cifs_tcon *tcon) /* validate negotiate successful */ cifs_dbg(FYI, "validate negotiate info successful\n"); + kfree(pneg_rsp); return 0; vneg_out: cifs_dbg(VFS, "protocol revalidation - security settings mismatch\n"); +err_rsp_free: + kfree(pneg_rsp); return -EIO; } @@ -1255,7 +1259,7 @@ SMB2_tcon(const unsigned int xid, struct cifs_ses *ses, const char *tree, struct smb2_tree_connect_req *req; struct smb2_tree_connect_rsp *rsp = NULL; struct kvec iov[2]; - struct kvec rsp_iov; + struct kvec rsp_iov = { NULL, 0 }; int rc = 0; int resp_buftype; int unc_path_len; @@ -1372,7 +1376,7 @@ tcon_exit: return rc; tcon_error_exit: - if (rsp->hdr.sync_hdr.Status == STATUS_BAD_NETWORK_NAME) { + if (rsp && rsp->hdr.sync_hdr.Status == STATUS_BAD_NETWORK_NAME) { cifs_dbg(VFS, "BAD_NETWORK_NAME: %s\n", tree); } goto tcon_exit; @@ -1975,6 +1979,9 @@ SMB2_ioctl(const unsigned int xid, struct cifs_tcon *tcon, u64 persistent_fid, } else iov[0].iov_len = get_rfc1002_length(req) + 4; + /* validate negotiate request must be signed - see MS-SMB2 3.2.5.5 */ + if (opcode == FSCTL_VALIDATE_NEGOTIATE_INFO) + req->hdr.sync_hdr.Flags |= SMB2_FLAGS_SIGNED; rc = SendReceive2(xid, ses, iov, n_iov, &resp_buftype, flags, &rsp_iov); cifs_small_buf_release(req); @@ -2191,9 +2198,13 @@ query_info(const unsigned int xid, struct cifs_tcon *tcon, req->PersistentFileId = persistent_fid; req->VolatileFileId = volatile_fid; req->AdditionalInformation = cpu_to_le32(additional_info); - /* 4 for rfc1002 length field and 1 for Buffer */ - req->InputBufferOffset = - cpu_to_le16(sizeof(struct smb2_query_info_req) - 1 - 4); + + /* + * We do not use the input buffer (do not send extra byte) + */ + req->InputBufferOffset = 0; + inc_rfc1001_len(req, -1); + req->OutputBufferLength = cpu_to_le32(output_len); iov[0].iov_base = (char *)req; @@ -2233,12 +2244,12 @@ qinf_exit: } int SMB2_query_eas(const unsigned int xid, struct cifs_tcon *tcon, - u64 persistent_fid, u64 volatile_fid, - struct smb2_file_full_ea_info *data) + u64 persistent_fid, u64 volatile_fid, + int ea_buf_size, struct smb2_file_full_ea_info *data) { return query_info(xid, tcon, persistent_fid, volatile_fid, FILE_FULL_EA_INFORMATION, SMB2_O_INFO_FILE, 0, - SMB2_MAX_EA_BUF, + ea_buf_size, sizeof(struct smb2_file_full_ea_info), (void **)&data, NULL); diff --git a/fs/cifs/smb2pdu.h b/fs/cifs/smb2pdu.h index 6c9653a130c8..c2ec934be968 100644 --- a/fs/cifs/smb2pdu.h +++ b/fs/cifs/smb2pdu.h @@ -832,7 +832,7 @@ struct smb2_flush_rsp { /* Channel field for read and write: exactly one of following flags can be set*/ #define SMB2_CHANNEL_NONE 0x00000000 #define SMB2_CHANNEL_RDMA_V1 0x00000001 /* SMB3 or later */ -#define SMB2_CHANNEL_RDMA_V1_INVALIDATE 0x00000001 /* SMB3.02 or later */ +#define SMB2_CHANNEL_RDMA_V1_INVALIDATE 0x00000002 /* SMB3.02 or later */ /* SMB2 read request without RFC1001 length at the beginning */ struct smb2_read_plain_req { @@ -1178,7 +1178,8 @@ struct smb2_file_link_info { /* encoding of request for level 11 */ char FileName[0]; /* Name to be assigned to new link */ } __packed; /* level 11 Set */ -#define SMB2_MAX_EA_BUF 2048 +#define SMB2_MIN_EA_BUF 2048 +#define SMB2_MAX_EA_BUF 65536 struct smb2_file_full_ea_info { /* encoding of response for level 15 */ __le32 next_entry_offset; diff --git a/fs/cifs/smb2proto.h b/fs/cifs/smb2proto.h index 003217099ef3..e9ab5227e7a8 100644 --- a/fs/cifs/smb2proto.h +++ b/fs/cifs/smb2proto.h @@ -134,6 +134,7 @@ extern int SMB2_flush(const unsigned int xid, struct cifs_tcon *tcon, u64 persistent_file_id, u64 volatile_file_id); extern int SMB2_query_eas(const unsigned int xid, struct cifs_tcon *tcon, u64 persistent_file_id, u64 volatile_file_id, + int ea_buf_size, struct smb2_file_full_ea_info *data); extern int SMB2_query_info(const unsigned int xid, struct cifs_tcon *tcon, u64 persistent_file_id, u64 volatile_file_id, diff --git a/fs/cifs/smb2transport.c b/fs/cifs/smb2transport.c index 67367cf1f8cd..99493946e2f9 100644 --- a/fs/cifs/smb2transport.c +++ b/fs/cifs/smb2transport.c @@ -390,6 +390,7 @@ generate_smb30signingkey(struct cifs_ses *ses) return generate_smb3signingkey(ses, &triplet); } +#ifdef CONFIG_CIFS_SMB311 int generate_smb311signingkey(struct cifs_ses *ses) @@ -398,25 +399,26 @@ generate_smb311signingkey(struct cifs_ses *ses) struct derivation *d; d = &triplet.signing; - d->label.iov_base = "SMB2AESCMAC"; - d->label.iov_len = 12; - d->context.iov_base = "SmbSign"; - d->context.iov_len = 8; + d->label.iov_base = "SMBSigningKey"; + d->label.iov_len = 14; + d->context.iov_base = ses->preauth_sha_hash; + d->context.iov_len = 64; d = &triplet.encryption; - d->label.iov_base = "SMB2AESCCM"; - d->label.iov_len = 11; - d->context.iov_base = "ServerIn "; - d->context.iov_len = 10; + d->label.iov_base = "SMBC2SCipherKey"; + d->label.iov_len = 16; + d->context.iov_base = ses->preauth_sha_hash; + d->context.iov_len = 64; d = &triplet.decryption; - d->label.iov_base = "SMB2AESCCM"; - d->label.iov_len = 11; - d->context.iov_base = "ServerOut"; - d->context.iov_len = 10; + d->label.iov_base = "SMBS2CCipherKey"; + d->label.iov_len = 16; + d->context.iov_base = ses->preauth_sha_hash; + d->context.iov_len = 64; return generate_smb3signingkey(ses, &triplet); } +#endif /* 311 */ int smb3_calc_signature(struct smb_rqst *rqst, struct TCP_Server_Info *server) diff --git a/fs/crypto/keyinfo.c b/fs/crypto/keyinfo.c index 018c588c7ac3..8e704d12a1cf 100644 --- a/fs/crypto/keyinfo.c +++ b/fs/crypto/keyinfo.c @@ -109,6 +109,11 @@ static int validate_user_key(struct fscrypt_info *crypt_info, goto out; } ukp = user_key_payload_locked(keyring_key); + if (!ukp) { + /* key was revoked before we acquired its semaphore */ + res = -EKEYREVOKED; + goto out; + } if (ukp->datalen != sizeof(struct fscrypt_key)) { res = -EINVAL; goto out; diff --git a/fs/direct-io.c b/fs/direct-io.c index 62cf812ed0e5..b53e66d9abd7 100644 --- a/fs/direct-io.c +++ b/fs/direct-io.c @@ -45,6 +45,12 @@ #define DIO_PAGES 64 /* + * Flags for dio_complete() + */ +#define DIO_COMPLETE_ASYNC 0x01 /* This is async IO */ +#define DIO_COMPLETE_INVALIDATE 0x02 /* Can invalidate pages */ + +/* * This code generally works in units of "dio_blocks". A dio_block is * somewhere between the hard sector size and the filesystem block size. it * is determined on a per-invocation basis. When talking to the filesystem @@ -225,7 +231,7 @@ static inline struct page *dio_get_page(struct dio *dio, * filesystems can use it to hold additional state between get_block calls and * dio_complete. */ -static ssize_t dio_complete(struct dio *dio, ssize_t ret, bool is_async) +static ssize_t dio_complete(struct dio *dio, ssize_t ret, unsigned int flags) { loff_t offset = dio->iocb->ki_pos; ssize_t transferred = 0; @@ -259,14 +265,27 @@ static ssize_t dio_complete(struct dio *dio, ssize_t ret, bool is_async) if (ret == 0) ret = transferred; + if (dio->end_io) { + // XXX: ki_pos?? + err = dio->end_io(dio->iocb, offset, ret, dio->private); + if (err) + ret = err; + } + /* * Try again to invalidate clean pages which might have been cached by * non-direct readahead, or faulted in by get_user_pages() if the source * of the write was an mmap'ed region of the file we're writing. Either * one is a pretty crazy thing to do, so we don't support it 100%. If * this invalidation fails, tough, the write still worked... + * + * And this page cache invalidation has to be after dio->end_io(), as + * some filesystems convert unwritten extents to real allocations in + * end_io() when necessary, otherwise a racing buffer read would cache + * zeros from unwritten extents. */ - if (ret > 0 && dio->op == REQ_OP_WRITE && + if (flags & DIO_COMPLETE_INVALIDATE && + ret > 0 && dio->op == REQ_OP_WRITE && dio->inode->i_mapping->nrpages) { err = invalidate_inode_pages2_range(dio->inode->i_mapping, offset >> PAGE_SHIFT, @@ -274,18 +293,10 @@ static ssize_t dio_complete(struct dio *dio, ssize_t ret, bool is_async) WARN_ON_ONCE(err); } - if (dio->end_io) { - - // XXX: ki_pos?? - err = dio->end_io(dio->iocb, offset, ret, dio->private); - if (err) - ret = err; - } - if (!(dio->flags & DIO_SKIP_DIO_COUNT)) inode_dio_end(dio->inode); - if (is_async) { + if (flags & DIO_COMPLETE_ASYNC) { /* * generic_write_sync expects ki_pos to have been updated * already, but the submission path only does this for @@ -306,7 +317,7 @@ static void dio_aio_complete_work(struct work_struct *work) { struct dio *dio = container_of(work, struct dio, complete_work); - dio_complete(dio, 0, true); + dio_complete(dio, 0, DIO_COMPLETE_ASYNC | DIO_COMPLETE_INVALIDATE); } static blk_status_t dio_bio_complete(struct dio *dio, struct bio *bio); @@ -348,7 +359,7 @@ static void dio_bio_end_aio(struct bio *bio) queue_work(dio->inode->i_sb->s_dio_done_wq, &dio->complete_work); } else { - dio_complete(dio, 0, true); + dio_complete(dio, 0, DIO_COMPLETE_ASYNC); } } } @@ -866,7 +877,8 @@ out: */ if (sdio->boundary) { ret = dio_send_cur_page(dio, sdio, map_bh); - dio_bio_submit(dio, sdio); + if (sdio->bio) + dio_bio_submit(dio, sdio); put_page(sdio->cur_page); sdio->cur_page = NULL; } @@ -1359,7 +1371,7 @@ do_blockdev_direct_IO(struct kiocb *iocb, struct inode *inode, dio_await_completion(dio); if (drop_refcount(dio) == 0) { - retval = dio_complete(dio, retval, false); + retval = dio_complete(dio, retval, DIO_COMPLETE_INVALIDATE); } else BUG_ON(retval != -EIOCBQUEUED); diff --git a/fs/ecryptfs/ecryptfs_kernel.h b/fs/ecryptfs/ecryptfs_kernel.h index 9c351bf757b2..3fbc0ff79699 100644 --- a/fs/ecryptfs/ecryptfs_kernel.h +++ b/fs/ecryptfs/ecryptfs_kernel.h @@ -84,11 +84,16 @@ struct ecryptfs_page_crypt_context { static inline struct ecryptfs_auth_tok * ecryptfs_get_encrypted_key_payload_data(struct key *key) { - if (key->type == &key_type_encrypted) - return (struct ecryptfs_auth_tok *) - (&((struct encrypted_key_payload *)key->payload.data[0])->payload_data); - else + struct encrypted_key_payload *payload; + + if (key->type != &key_type_encrypted) return NULL; + + payload = key->payload.data[0]; + if (!payload) + return ERR_PTR(-EKEYREVOKED); + + return (struct ecryptfs_auth_tok *)payload->payload_data; } static inline struct key *ecryptfs_get_encrypted_key(char *sig) @@ -114,12 +119,17 @@ static inline struct ecryptfs_auth_tok * ecryptfs_get_key_payload_data(struct key *key) { struct ecryptfs_auth_tok *auth_tok; + struct user_key_payload *ukp; auth_tok = ecryptfs_get_encrypted_key_payload_data(key); - if (!auth_tok) - return (struct ecryptfs_auth_tok *)user_key_payload_locked(key)->data; - else + if (auth_tok) return auth_tok; + + ukp = user_key_payload_locked(key); + if (!ukp) + return ERR_PTR(-EKEYREVOKED); + + return (struct ecryptfs_auth_tok *)ukp->data; } #define ECRYPTFS_MAX_KEYSET_SIZE 1024 diff --git a/fs/ecryptfs/keystore.c b/fs/ecryptfs/keystore.c index 3cf1546dca82..fa218cd64f74 100644 --- a/fs/ecryptfs/keystore.c +++ b/fs/ecryptfs/keystore.c @@ -459,7 +459,8 @@ out: * @auth_tok_key: key containing the authentication token * @auth_tok: authentication token * - * Returns zero on valid auth tok; -EINVAL otherwise + * Returns zero on valid auth tok; -EINVAL if the payload is invalid; or + * -EKEYREVOKED if the key was revoked before we acquired its semaphore. */ static int ecryptfs_verify_auth_tok_from_key(struct key *auth_tok_key, @@ -468,6 +469,12 @@ ecryptfs_verify_auth_tok_from_key(struct key *auth_tok_key, int rc = 0; (*auth_tok) = ecryptfs_get_key_payload_data(auth_tok_key); + if (IS_ERR(*auth_tok)) { + rc = PTR_ERR(*auth_tok); + *auth_tok = NULL; + goto out; + } + if (ecryptfs_verify_version((*auth_tok)->version)) { printk(KERN_ERR "Data structure version mismatch. Userspace " "tools must match eCryptfs kernel module with major " diff --git a/fs/exec.c b/fs/exec.c index 5470d3c1892a..3e14ba25f678 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -1802,6 +1802,7 @@ static int do_execveat_common(int fd, struct filename *filename, /* execve succeeded */ current->fs->in_exec = 0; current->in_execve = 0; + membarrier_execve(current); acct_update_integrals(current); task_numa_free(current); free_bprm(bprm); diff --git a/fs/ext4/super.c b/fs/ext4/super.c index b104096fce9e..b0915b734a38 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -1677,7 +1677,7 @@ static int handle_mount_opt(struct super_block *sb, char *opt, int token, sbi->s_mount_flags |= EXT4_MF_FS_ABORTED; return 1; case Opt_i_version: - sb->s_flags |= MS_I_VERSION; + sb->s_flags |= SB_I_VERSION; return 1; case Opt_lazytime: sb->s_flags |= MS_LAZYTIME; @@ -2060,7 +2060,7 @@ static int _ext4_show_options(struct seq_file *seq, struct super_block *sb, SEQ_OPTS_PRINT("min_batch_time=%u", sbi->s_min_batch_time); if (nodefs || sbi->s_max_batch_time != EXT4_DEF_MAX_BATCH_TIME) SEQ_OPTS_PRINT("max_batch_time=%u", sbi->s_max_batch_time); - if (sb->s_flags & MS_I_VERSION) + if (sb->s_flags & SB_I_VERSION) SEQ_OPTS_PUTS("i_version"); if (nodefs || sbi->s_stripe) SEQ_OPTS_PRINT("stripe=%lu", sbi->s_stripe); diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h index 9a7c90386947..4b4a72f392be 100644 --- a/fs/f2fs/f2fs.h +++ b/fs/f2fs/f2fs.h @@ -2525,7 +2525,7 @@ void invalidate_blocks(struct f2fs_sb_info *sbi, block_t addr); bool is_checkpointed_data(struct f2fs_sb_info *sbi, block_t blkaddr); void refresh_sit_entry(struct f2fs_sb_info *sbi, block_t old, block_t new); void stop_discard_thread(struct f2fs_sb_info *sbi); -void f2fs_wait_discard_bios(struct f2fs_sb_info *sbi); +void f2fs_wait_discard_bios(struct f2fs_sb_info *sbi, bool umount); void clear_prefree_segments(struct f2fs_sb_info *sbi, struct cp_control *cpc); void release_discard_addrs(struct f2fs_sb_info *sbi); int npages_for_summary_flush(struct f2fs_sb_info *sbi, bool for_ra); diff --git a/fs/f2fs/segment.c b/fs/f2fs/segment.c index 621b9b3d320b..c695ff462ee6 100644 --- a/fs/f2fs/segment.c +++ b/fs/f2fs/segment.c @@ -1210,11 +1210,11 @@ void stop_discard_thread(struct f2fs_sb_info *sbi) } /* This comes from f2fs_put_super and f2fs_trim_fs */ -void f2fs_wait_discard_bios(struct f2fs_sb_info *sbi) +void f2fs_wait_discard_bios(struct f2fs_sb_info *sbi, bool umount) { __issue_discard_cmd(sbi, false); __drop_discard_cmd(sbi); - __wait_discard_cmd(sbi, false); + __wait_discard_cmd(sbi, !umount); } static void mark_discard_range_all(struct f2fs_sb_info *sbi) @@ -2244,7 +2244,7 @@ int f2fs_trim_fs(struct f2fs_sb_info *sbi, struct fstrim_range *range) } /* It's time to issue all the filed discards */ mark_discard_range_all(sbi); - f2fs_wait_discard_bios(sbi); + f2fs_wait_discard_bios(sbi, false); out: range->len = F2FS_BLK_TO_BYTES(cpc.trimmed); return err; diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c index 89f61eb3d167..933c3d529e65 100644 --- a/fs/f2fs/super.c +++ b/fs/f2fs/super.c @@ -801,7 +801,7 @@ static void f2fs_put_super(struct super_block *sb) } /* be sure to wait for any on-going discard commands */ - f2fs_wait_discard_bios(sbi); + f2fs_wait_discard_bios(sbi, true); if (f2fs_discard_en(sbi) && !sbi->discard_blks) { struct cp_control cpc = { diff --git a/fs/fscache/object-list.c b/fs/fscache/object-list.c index b5ab06fabc60..0438d4cd91ef 100644 --- a/fs/fscache/object-list.c +++ b/fs/fscache/object-list.c @@ -331,6 +331,13 @@ static void fscache_objlist_config(struct fscache_objlist_data *data) rcu_read_lock(); confkey = user_key_payload_rcu(key); + if (!confkey) { + /* key was revoked */ + rcu_read_unlock(); + key_put(key); + goto no_config; + } + buf = confkey->data; for (len = confkey->datalen - 1; len >= 0; len--) { diff --git a/fs/fuse/dir.c b/fs/fuse/dir.c index 622081b97426..24967382a7b1 100644 --- a/fs/fuse/dir.c +++ b/fs/fuse/dir.c @@ -1308,7 +1308,8 @@ static int parse_dirplusfile(char *buf, size_t nbytes, struct file *file, */ over = !dir_emit(ctx, dirent->name, dirent->namelen, dirent->ino, dirent->type); - ctx->pos = dirent->off; + if (!over) + ctx->pos = dirent->off; } buf += reclen; diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c index 65c88379a3a1..94a745acaef8 100644 --- a/fs/fuse/inode.c +++ b/fs/fuse/inode.c @@ -1059,7 +1059,7 @@ static int fuse_fill_super(struct super_block *sb, void *data, int silent) if (sb->s_flags & MS_MANDLOCK) goto err; - sb->s_flags &= ~(MS_NOSEC | MS_I_VERSION); + sb->s_flags &= ~(MS_NOSEC | SB_I_VERSION); if (!parse_fuse_opt(data, &d, is_bdev)) goto err; diff --git a/fs/iomap.c b/fs/iomap.c index be61cf742b5e..d4801f8dd4fd 100644 --- a/fs/iomap.c +++ b/fs/iomap.c @@ -714,23 +714,9 @@ static ssize_t iomap_dio_complete(struct iomap_dio *dio) { struct kiocb *iocb = dio->iocb; struct inode *inode = file_inode(iocb->ki_filp); + loff_t offset = iocb->ki_pos; ssize_t ret; - /* - * Try again to invalidate clean pages which might have been cached by - * non-direct readahead, or faulted in by get_user_pages() if the source - * of the write was an mmap'ed region of the file we're writing. Either - * one is a pretty crazy thing to do, so we don't support it 100%. If - * this invalidation fails, tough, the write still worked... - */ - if (!dio->error && - (dio->flags & IOMAP_DIO_WRITE) && inode->i_mapping->nrpages) { - ret = invalidate_inode_pages2_range(inode->i_mapping, - iocb->ki_pos >> PAGE_SHIFT, - (iocb->ki_pos + dio->size - 1) >> PAGE_SHIFT); - WARN_ON_ONCE(ret); - } - if (dio->end_io) { ret = dio->end_io(iocb, dio->error ? dio->error : dio->size, @@ -742,12 +728,33 @@ static ssize_t iomap_dio_complete(struct iomap_dio *dio) if (likely(!ret)) { ret = dio->size; /* check for short read */ - if (iocb->ki_pos + ret > dio->i_size && + if (offset + ret > dio->i_size && !(dio->flags & IOMAP_DIO_WRITE)) - ret = dio->i_size - iocb->ki_pos; + ret = dio->i_size - offset; iocb->ki_pos += ret; } + /* + * Try again to invalidate clean pages which might have been cached by + * non-direct readahead, or faulted in by get_user_pages() if the source + * of the write was an mmap'ed region of the file we're writing. Either + * one is a pretty crazy thing to do, so we don't support it 100%. If + * this invalidation fails, tough, the write still worked... + * + * And this page cache invalidation has to be after dio->end_io(), as + * some filesystems convert unwritten extents to real allocations in + * end_io() when necessary, otherwise a racing buffer read would cache + * zeros from unwritten extents. + */ + if (!dio->error && + (dio->flags & IOMAP_DIO_WRITE) && inode->i_mapping->nrpages) { + int err; + err = invalidate_inode_pages2_range(inode->i_mapping, + offset >> PAGE_SHIFT, + (offset + dio->size - 1) >> PAGE_SHIFT); + WARN_ON_ONCE(err); + } + inode_dio_end(file_inode(iocb->ki_filp)); kfree(dio); diff --git a/fs/mpage.c b/fs/mpage.c index 37bb77c1302c..c991faec70b9 100644 --- a/fs/mpage.c +++ b/fs/mpage.c @@ -468,6 +468,16 @@ static void clean_buffers(struct page *page, unsigned first_unmapped) try_to_free_buffers(page); } +/* + * For situations where we want to clean all buffers attached to a page. + * We don't need to calculate how many buffers are attached to the page, + * we just need to specify a number larger than the maximum number of buffers. + */ +void clean_page_buffers(struct page *page) +{ + clean_buffers(page, ~0U); +} + static int __mpage_writepage(struct page *page, struct writeback_control *wbc, void *data) { @@ -605,10 +615,8 @@ alloc_new: if (bio == NULL) { if (first_unmapped == blocks_per_page) { if (!bdev_write_page(bdev, blocks[0] << (blkbits - 9), - page, wbc)) { - clean_buffers(page, first_unmapped); + page, wbc)) goto out; - } } bio = mpage_alloc(bdev, blocks[0] << (blkbits - 9), BIO_MAX_PAGES, GFP_NOFS|__GFP_HIGH); diff --git a/fs/namespace.c b/fs/namespace.c index 3b601f115b6c..d18deb4c410b 100644 --- a/fs/namespace.c +++ b/fs/namespace.c @@ -2825,7 +2825,8 @@ long do_mount(const char *dev_name, const char __user *dir_name, SB_MANDLOCK | SB_DIRSYNC | SB_SILENT | - SB_POSIXACL); + SB_POSIXACL | + SB_I_VERSION); if (flags & MS_REMOUNT) retval = do_remount(&path, flags, sb_flags, mnt_flags, diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c index 3c69db7d4905..8487486ec496 100644 --- a/fs/nfsd/nfs4proc.c +++ b/fs/nfsd/nfs4proc.c @@ -927,6 +927,13 @@ nfsd4_secinfo_release(union nfsd4_op_u *u) exp_put(u->secinfo.si_exp); } +static void +nfsd4_secinfo_no_name_release(union nfsd4_op_u *u) +{ + if (u->secinfo_no_name.sin_exp) + exp_put(u->secinfo_no_name.sin_exp); +} + static __be32 nfsd4_setattr(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, union nfsd4_op_u *u) @@ -2375,7 +2382,7 @@ static const struct nfsd4_operation nfsd4_ops[] = { }, [OP_SECINFO_NO_NAME] = { .op_func = nfsd4_secinfo_no_name, - .op_release = nfsd4_secinfo_release, + .op_release = nfsd4_secinfo_no_name_release, .op_flags = OP_HANDLES_WRONGSEC, .op_name = "OP_SECINFO_NO_NAME", .op_rsize_bop = nfsd4_secinfo_rsize, diff --git a/fs/overlayfs/inode.c b/fs/overlayfs/inode.c index a619addecafc..321511ed8c42 100644 --- a/fs/overlayfs/inode.c +++ b/fs/overlayfs/inode.c @@ -598,18 +598,30 @@ static bool ovl_verify_inode(struct inode *inode, struct dentry *lowerdentry, return true; } -struct inode *ovl_get_inode(struct dentry *dentry, struct dentry *upperdentry) +struct inode *ovl_get_inode(struct dentry *dentry, struct dentry *upperdentry, + struct dentry *index) { struct dentry *lowerdentry = ovl_dentry_lower(dentry); struct inode *realinode = upperdentry ? d_inode(upperdentry) : NULL; struct inode *inode; + /* Already indexed or could be indexed on copy up? */ + bool indexed = (index || (ovl_indexdir(dentry->d_sb) && !upperdentry)); + + if (WARN_ON(upperdentry && indexed && !lowerdentry)) + return ERR_PTR(-EIO); if (!realinode) realinode = d_inode(lowerdentry); - if (!S_ISDIR(realinode->i_mode) && - (upperdentry || (lowerdentry && ovl_indexdir(dentry->d_sb)))) { - struct inode *key = d_inode(lowerdentry ?: upperdentry); + /* + * Copy up origin (lower) may exist for non-indexed upper, but we must + * not use lower as hash key in that case. + * Hash inodes that are or could be indexed by origin inode and + * non-indexed upper inodes that could be hard linked by upper inode. + */ + if (!S_ISDIR(realinode->i_mode) && (upperdentry || indexed)) { + struct inode *key = d_inode(indexed ? lowerdentry : + upperdentry); unsigned int nlink; inode = iget5_locked(dentry->d_sb, (unsigned long) key, diff --git a/fs/overlayfs/namei.c b/fs/overlayfs/namei.c index 654bea1a5ac9..a12dc10bf726 100644 --- a/fs/overlayfs/namei.c +++ b/fs/overlayfs/namei.c @@ -405,14 +405,13 @@ int ovl_verify_index(struct dentry *index, struct path *lowerstack, * be treated as stale (i.e. after unlink of the overlay inode). * We don't know the verification rules for directory and whiteout * index entries, because they have not been implemented yet, so return - * EROFS if those entries are found to avoid corrupting an index that - * was created by a newer kernel. + * EINVAL if those entries are found to abort the mount to avoid + * corrupting an index that was created by a newer kernel. */ - err = -EROFS; + err = -EINVAL; if (d_is_dir(index) || ovl_is_whiteout(index)) goto fail; - err = -EINVAL; if (index->d_name.len < sizeof(struct ovl_fh)*2) goto fail; @@ -507,6 +506,10 @@ static struct dentry *ovl_lookup_index(struct dentry *dentry, index = lookup_one_len_unlocked(name.name, ofs->indexdir, name.len); if (IS_ERR(index)) { err = PTR_ERR(index); + if (err == -ENOENT) { + index = NULL; + goto out; + } pr_warn_ratelimited("overlayfs: failed inode index lookup (ino=%lu, key=%*s, err=%i);\n" "overlayfs: mount with '-o index=off' to disable inodes index.\n", d_inode(origin)->i_ino, name.len, name.name, @@ -516,18 +519,9 @@ static struct dentry *ovl_lookup_index(struct dentry *dentry, inode = d_inode(index); if (d_is_negative(index)) { - if (upper && d_inode(origin)->i_nlink > 1) { - pr_warn_ratelimited("overlayfs: hard link with origin but no index (ino=%lu).\n", - d_inode(origin)->i_ino); - goto fail; - } - - dput(index); - index = NULL; + goto out_dput; } else if (upper && d_inode(upper) != inode) { - pr_warn_ratelimited("overlayfs: wrong index found (index=%pd2, ino=%lu, upper ino=%lu).\n", - index, inode->i_ino, d_inode(upper)->i_ino); - goto fail; + goto out_dput; } else if (ovl_dentry_weird(index) || ovl_is_whiteout(index) || ((inode->i_mode ^ d_inode(origin)->i_mode) & S_IFMT)) { /* @@ -547,6 +541,11 @@ out: kfree(name.name); return index; +out_dput: + dput(index); + index = NULL; + goto out; + fail: dput(index); index = ERR_PTR(-EIO); @@ -635,6 +634,7 @@ struct dentry *ovl_lookup(struct inode *dir, struct dentry *dentry, } if (d.redirect) { + err = -ENOMEM; upperredirect = kstrdup(d.redirect, GFP_KERNEL); if (!upperredirect) goto out_put_upper; @@ -709,7 +709,7 @@ struct dentry *ovl_lookup(struct inode *dir, struct dentry *dentry, upperdentry = dget(index); if (upperdentry || ctr) { - inode = ovl_get_inode(dentry, upperdentry); + inode = ovl_get_inode(dentry, upperdentry, index); err = PTR_ERR(inode); if (IS_ERR(inode)) goto out_free_oe; diff --git a/fs/overlayfs/overlayfs.h b/fs/overlayfs/overlayfs.h index c706a6f99928..d9a0edd4e57e 100644 --- a/fs/overlayfs/overlayfs.h +++ b/fs/overlayfs/overlayfs.h @@ -286,7 +286,8 @@ int ovl_update_time(struct inode *inode, struct timespec *ts, int flags); bool ovl_is_private_xattr(const char *name); struct inode *ovl_new_inode(struct super_block *sb, umode_t mode, dev_t rdev); -struct inode *ovl_get_inode(struct dentry *dentry, struct dentry *upperdentry); +struct inode *ovl_get_inode(struct dentry *dentry, struct dentry *upperdentry, + struct dentry *index); static inline void ovl_copyattr(struct inode *from, struct inode *to) { to->i_uid = from->i_uid; diff --git a/fs/overlayfs/readdir.c b/fs/overlayfs/readdir.c index 0f85ee9c3268..698b74dd750e 100644 --- a/fs/overlayfs/readdir.c +++ b/fs/overlayfs/readdir.c @@ -1021,13 +1021,12 @@ int ovl_indexdir_cleanup(struct dentry *dentry, struct vfsmount *mnt, break; } err = ovl_verify_index(index, lowerstack, numlower); - if (err) { - if (err == -EROFS) - break; + /* Cleanup stale and orphan index entries */ + if (err && (err == -ESTALE || err == -ENOENT)) err = ovl_cleanup(dir, index); - if (err) - break; - } + if (err) + break; + dput(index); index = NULL; } diff --git a/fs/overlayfs/super.c b/fs/overlayfs/super.c index 092d150643c1..f5738e96a052 100644 --- a/fs/overlayfs/super.c +++ b/fs/overlayfs/super.c @@ -174,6 +174,9 @@ static struct inode *ovl_alloc_inode(struct super_block *sb) { struct ovl_inode *oi = kmem_cache_alloc(ovl_inode_cachep, GFP_KERNEL); + if (!oi) + return NULL; + oi->cache = NULL; oi->redirect = NULL; oi->version = 0; diff --git a/fs/quota/dquot.c b/fs/quota/dquot.c index 50b0556a124f..52ad15192e72 100644 --- a/fs/quota/dquot.c +++ b/fs/quota/dquot.c @@ -1297,21 +1297,18 @@ static int dquot_add_space(struct dquot *dquot, qsize_t space, spin_lock(&dquot->dq_dqb_lock); if (!sb_has_quota_limits_enabled(sb, dquot->dq_id.type) || test_bit(DQ_FAKE_B, &dquot->dq_flags)) - goto add; + goto finish; tspace = dquot->dq_dqb.dqb_curspace + dquot->dq_dqb.dqb_rsvspace + space + rsv_space; - if (flags & DQUOT_SPACE_NOFAIL) - goto add; - if (dquot->dq_dqb.dqb_bhardlimit && tspace > dquot->dq_dqb.dqb_bhardlimit && !ignore_hardlimit(dquot)) { if (flags & DQUOT_SPACE_WARN) prepare_warning(warn, dquot, QUOTA_NL_BHARDWARN); ret = -EDQUOT; - goto out; + goto finish; } if (dquot->dq_dqb.dqb_bsoftlimit && @@ -1322,7 +1319,7 @@ static int dquot_add_space(struct dquot *dquot, qsize_t space, if (flags & DQUOT_SPACE_WARN) prepare_warning(warn, dquot, QUOTA_NL_BSOFTLONGWARN); ret = -EDQUOT; - goto out; + goto finish; } if (dquot->dq_dqb.dqb_bsoftlimit && @@ -1338,13 +1335,21 @@ static int dquot_add_space(struct dquot *dquot, qsize_t space, * be always printed */ ret = -EDQUOT; - goto out; + goto finish; } } -add: - dquot->dq_dqb.dqb_rsvspace += rsv_space; - dquot->dq_dqb.dqb_curspace += space; -out: +finish: + /* + * We have to be careful and go through warning generation & grace time + * setting even if DQUOT_SPACE_NOFAIL is set. That's why we check it + * only here... + */ + if (flags & DQUOT_SPACE_NOFAIL) + ret = 0; + if (!ret) { + dquot->dq_dqb.dqb_rsvspace += rsv_space; + dquot->dq_dqb.dqb_curspace += space; + } spin_unlock(&dquot->dq_dqb_lock); return ret; } diff --git a/fs/xfs/libxfs/xfs_alloc.c b/fs/xfs/libxfs/xfs_alloc.c index 744dcaec34cc..f965ce832bc0 100644 --- a/fs/xfs/libxfs/xfs_alloc.c +++ b/fs/xfs/libxfs/xfs_alloc.c @@ -1584,6 +1584,10 @@ xfs_alloc_ag_vextent_small( bp = xfs_btree_get_bufs(args->mp, args->tp, args->agno, fbno, 0); + if (!bp) { + error = -EFSCORRUPTED; + goto error0; + } xfs_trans_binval(args->tp, bp); } args->len = 1; @@ -2141,6 +2145,10 @@ xfs_alloc_fix_freelist( if (error) goto out_agbp_relse; bp = xfs_btree_get_bufs(mp, tp, args->agno, bno, 0); + if (!bp) { + error = -EFSCORRUPTED; + goto out_agbp_relse; + } xfs_trans_binval(tp, bp); } diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c index 044a363119be..89263797cf32 100644 --- a/fs/xfs/libxfs/xfs_bmap.c +++ b/fs/xfs/libxfs/xfs_bmap.c @@ -1477,14 +1477,14 @@ xfs_bmap_isaeof( int is_empty; int error; - bma->aeof = 0; + bma->aeof = false; error = xfs_bmap_last_extent(NULL, bma->ip, whichfork, &rec, &is_empty); if (error) return error; if (is_empty) { - bma->aeof = 1; + bma->aeof = true; return 0; } @@ -3852,6 +3852,17 @@ xfs_trim_extent( } } +/* trim extent to within eof */ +void +xfs_trim_extent_eof( + struct xfs_bmbt_irec *irec, + struct xfs_inode *ip) + +{ + xfs_trim_extent(irec, 0, XFS_B_TO_FSB(ip->i_mount, + i_size_read(VFS_I(ip)))); +} + /* * Trim the returned map to the required bounds */ diff --git a/fs/xfs/libxfs/xfs_bmap.h b/fs/xfs/libxfs/xfs_bmap.h index 851982a5dfbc..502e0d8fb4ff 100644 --- a/fs/xfs/libxfs/xfs_bmap.h +++ b/fs/xfs/libxfs/xfs_bmap.h @@ -208,6 +208,7 @@ void xfs_bmap_trace_exlist(struct xfs_inode *ip, xfs_extnum_t cnt, void xfs_trim_extent(struct xfs_bmbt_irec *irec, xfs_fileoff_t bno, xfs_filblks_t len); +void xfs_trim_extent_eof(struct xfs_bmbt_irec *, struct xfs_inode *); int xfs_bmap_add_attrfork(struct xfs_inode *ip, int size, int rsvd); void xfs_bmap_local_to_extents_empty(struct xfs_inode *ip, int whichfork); void xfs_bmap_add_free(struct xfs_mount *mp, struct xfs_defer_ops *dfops, diff --git a/fs/xfs/libxfs/xfs_ialloc.c b/fs/xfs/libxfs/xfs_ialloc.c index 988bb3f31446..dfd643909f85 100644 --- a/fs/xfs/libxfs/xfs_ialloc.c +++ b/fs/xfs/libxfs/xfs_ialloc.c @@ -1962,7 +1962,7 @@ xfs_difree_inobt( if (!(mp->m_flags & XFS_MOUNT_IKEEP) && rec.ir_free == XFS_INOBT_ALL_FREE && mp->m_sb.sb_inopblock <= XFS_INODES_PER_CHUNK) { - xic->deleted = 1; + xic->deleted = true; xic->first_ino = XFS_AGINO_TO_INO(mp, agno, rec.ir_startino); xic->alloc = xfs_inobt_irec_to_allocmask(&rec); @@ -1989,7 +1989,7 @@ xfs_difree_inobt( xfs_difree_inode_chunk(mp, agno, &rec, dfops); } else { - xic->deleted = 0; + xic->deleted = false; error = xfs_inobt_update(cur, &rec); if (error) { diff --git a/fs/xfs/libxfs/xfs_log_format.h b/fs/xfs/libxfs/xfs_log_format.h index 8372e9bcd7b6..71de185735e0 100644 --- a/fs/xfs/libxfs/xfs_log_format.h +++ b/fs/xfs/libxfs/xfs_log_format.h @@ -270,6 +270,7 @@ typedef struct xfs_inode_log_format { uint32_t ilf_fields; /* flags for fields logged */ uint16_t ilf_asize; /* size of attr d/ext/root */ uint16_t ilf_dsize; /* size of data/ext/root */ + uint32_t ilf_pad; /* pad for 64 bit boundary */ uint64_t ilf_ino; /* inode number */ union { uint32_t ilfu_rdev; /* rdev value for dev inode*/ @@ -280,29 +281,17 @@ typedef struct xfs_inode_log_format { int32_t ilf_boffset; /* off of inode in buffer */ } xfs_inode_log_format_t; -typedef struct xfs_inode_log_format_32 { - uint16_t ilf_type; /* inode log item type */ - uint16_t ilf_size; /* size of this item */ - uint32_t ilf_fields; /* flags for fields logged */ - uint16_t ilf_asize; /* size of attr d/ext/root */ - uint16_t ilf_dsize; /* size of data/ext/root */ - uint64_t ilf_ino; /* inode number */ - union { - uint32_t ilfu_rdev; /* rdev value for dev inode*/ - uuid_t ilfu_uuid; /* mount point value */ - } ilf_u; - int64_t ilf_blkno; /* blkno of inode buffer */ - int32_t ilf_len; /* len of inode buffer */ - int32_t ilf_boffset; /* off of inode in buffer */ -} __attribute__((packed)) xfs_inode_log_format_32_t; - -typedef struct xfs_inode_log_format_64 { +/* + * Old 32 bit systems will log in this format without the 64 bit + * alignment padding. Recovery will detect this and convert it to the + * correct format. + */ +struct xfs_inode_log_format_32 { uint16_t ilf_type; /* inode log item type */ uint16_t ilf_size; /* size of this item */ uint32_t ilf_fields; /* flags for fields logged */ uint16_t ilf_asize; /* size of attr d/ext/root */ uint16_t ilf_dsize; /* size of data/ext/root */ - uint32_t ilf_pad; /* pad for 64 bit boundary */ uint64_t ilf_ino; /* inode number */ union { uint32_t ilfu_rdev; /* rdev value for dev inode*/ @@ -311,7 +300,7 @@ typedef struct xfs_inode_log_format_64 { int64_t ilf_blkno; /* blkno of inode buffer */ int32_t ilf_len; /* len of inode buffer */ int32_t ilf_boffset; /* off of inode in buffer */ -} xfs_inode_log_format_64_t; +} __attribute__((packed)); /* diff --git a/fs/xfs/xfs_acl.c b/fs/xfs/xfs_acl.c index 7034e17535de..3354140de07e 100644 --- a/fs/xfs/xfs_acl.c +++ b/fs/xfs/xfs_acl.c @@ -247,6 +247,8 @@ xfs_set_mode(struct inode *inode, umode_t mode) int xfs_set_acl(struct inode *inode, struct posix_acl *acl, int type) { + umode_t mode; + bool set_mode = false; int error = 0; if (!acl) @@ -257,16 +259,24 @@ xfs_set_acl(struct inode *inode, struct posix_acl *acl, int type) return error; if (type == ACL_TYPE_ACCESS) { - umode_t mode; - error = posix_acl_update_mode(inode, &mode, &acl); if (error) return error; - error = xfs_set_mode(inode, mode); - if (error) - return error; + set_mode = true; } set_acl: - return __xfs_set_acl(inode, acl, type); + error = __xfs_set_acl(inode, acl, type); + if (error) + return error; + + /* + * We set the mode after successfully updating the ACL xattr because the + * xattr update can fail at ENOSPC and we don't want to change the mode + * if the ACL update hasn't been applied. + */ + if (set_mode) + error = xfs_set_mode(inode, mode); + + return error; } diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c index f18e5932aec4..a3eeaba156c5 100644 --- a/fs/xfs/xfs_aops.c +++ b/fs/xfs/xfs_aops.c @@ -446,6 +446,19 @@ xfs_imap_valid( { offset >>= inode->i_blkbits; + /* + * We have to make sure the cached mapping is within EOF to protect + * against eofblocks trimming on file release leaving us with a stale + * mapping. Otherwise, a page for a subsequent file extending buffered + * write could get picked up by this writeback cycle and written to the + * wrong blocks. + * + * Note that what we really want here is a generic mapping invalidation + * mechanism to protect us from arbitrary extent modifying contexts, not + * just eofblocks. + */ + xfs_trim_extent_eof(imap, XFS_I(inode)); + return offset >= imap->br_startoff && offset < imap->br_startoff + imap->br_blockcount; } @@ -735,6 +748,14 @@ xfs_vm_invalidatepage( { trace_xfs_invalidatepage(page->mapping->host, page, offset, length); + + /* + * If we are invalidating the entire page, clear the dirty state from it + * so that we can check for attempts to release dirty cached pages in + * xfs_vm_releasepage(). + */ + if (offset == 0 && length >= PAGE_SIZE) + cancel_dirty_page(page); block_invalidatepage(page, offset, length); } @@ -1190,25 +1211,27 @@ xfs_vm_releasepage( * mm accommodates an old ext3 case where clean pages might not have had * the dirty bit cleared. Thus, it can send actual dirty pages to * ->releasepage() via shrink_active_list(). Conversely, - * block_invalidatepage() can send pages that are still marked dirty - * but otherwise have invalidated buffers. + * block_invalidatepage() can send pages that are still marked dirty but + * otherwise have invalidated buffers. * * We want to release the latter to avoid unnecessary buildup of the - * LRU, skip the former and warn if we've left any lingering - * delalloc/unwritten buffers on clean pages. Skip pages with delalloc - * or unwritten buffers and warn if the page is not dirty. Otherwise - * try to release the buffers. + * LRU, so xfs_vm_invalidatepage() clears the page dirty flag on pages + * that are entirely invalidated and need to be released. Hence the + * only time we should get dirty pages here is through + * shrink_active_list() and so we can simply skip those now. + * + * warn if we've left any lingering delalloc/unwritten buffers on clean + * or invalidated pages we are about to release. */ + if (PageDirty(page)) + return 0; + xfs_count_page_state(page, &delalloc, &unwritten); - if (delalloc) { - WARN_ON_ONCE(!PageDirty(page)); + if (WARN_ON_ONCE(delalloc)) return 0; - } - if (unwritten) { - WARN_ON_ONCE(!PageDirty(page)); + if (WARN_ON_ONCE(unwritten)) return 0; - } return try_to_free_buffers(page); } diff --git a/fs/xfs/xfs_attr_inactive.c b/fs/xfs/xfs_attr_inactive.c index ebd66b19fbfc..e3a950ed35a8 100644 --- a/fs/xfs/xfs_attr_inactive.c +++ b/fs/xfs/xfs_attr_inactive.c @@ -302,6 +302,8 @@ xfs_attr3_node_inactive( &bp, XFS_ATTR_FORK); if (error) return error; + node = bp->b_addr; + btree = dp->d_ops->node_tree_p(node); child_fsb = be32_to_cpu(btree[i + 1].before); xfs_trans_brelse(*trans, bp); } diff --git a/fs/xfs/xfs_bmap_util.c b/fs/xfs/xfs_bmap_util.c index e9db7fc95b70..6503cfa44262 100644 --- a/fs/xfs/xfs_bmap_util.c +++ b/fs/xfs/xfs_bmap_util.c @@ -84,6 +84,7 @@ xfs_zero_extent( GFP_NOFS, 0); } +#ifdef CONFIG_XFS_RT int xfs_bmap_rtalloc( struct xfs_bmalloca *ap) /* bmap alloc argument struct */ @@ -190,6 +191,7 @@ xfs_bmap_rtalloc( } return 0; } +#endif /* CONFIG_XFS_RT */ /* * Check if the endoff is outside the last extent. If so the caller will grow diff --git a/fs/xfs/xfs_bmap_util.h b/fs/xfs/xfs_bmap_util.h index 0eaa81dc49be..7d330b3c77c3 100644 --- a/fs/xfs/xfs_bmap_util.h +++ b/fs/xfs/xfs_bmap_util.h @@ -28,7 +28,20 @@ struct xfs_mount; struct xfs_trans; struct xfs_bmalloca; +#ifdef CONFIG_XFS_RT int xfs_bmap_rtalloc(struct xfs_bmalloca *ap); +#else /* !CONFIG_XFS_RT */ +/* + * Attempts to allocate RT extents when RT is disable indicates corruption and + * should trigger a shutdown. + */ +static inline int +xfs_bmap_rtalloc(struct xfs_bmalloca *ap) +{ + return -EFSCORRUPTED; +} +#endif /* CONFIG_XFS_RT */ + int xfs_bmap_eof(struct xfs_inode *ip, xfs_fileoff_t endoff, int whichfork, int *eof); int xfs_bmap_punch_delalloc_range(struct xfs_inode *ip, diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c index 309e26c9dddb..6526ef0e2a23 100644 --- a/fs/xfs/xfs_file.c +++ b/fs/xfs/xfs_file.c @@ -237,11 +237,13 @@ xfs_file_dax_read( if (!count) return 0; /* skip atime */ - if (!xfs_ilock_nowait(ip, XFS_IOLOCK_SHARED)) { - if (iocb->ki_flags & IOCB_NOWAIT) + if (iocb->ki_flags & IOCB_NOWAIT) { + if (!xfs_ilock_nowait(ip, XFS_IOLOCK_SHARED)) return -EAGAIN; + } else { xfs_ilock(ip, XFS_IOLOCK_SHARED); } + ret = dax_iomap_rw(iocb, to, &xfs_iomap_ops); xfs_iunlock(ip, XFS_IOLOCK_SHARED); @@ -259,9 +261,10 @@ xfs_file_buffered_aio_read( trace_xfs_file_buffered_read(ip, iov_iter_count(to), iocb->ki_pos); - if (!xfs_ilock_nowait(ip, XFS_IOLOCK_SHARED)) { - if (iocb->ki_flags & IOCB_NOWAIT) + if (iocb->ki_flags & IOCB_NOWAIT) { + if (!xfs_ilock_nowait(ip, XFS_IOLOCK_SHARED)) return -EAGAIN; + } else { xfs_ilock(ip, XFS_IOLOCK_SHARED); } ret = generic_file_read_iter(iocb, to); @@ -552,9 +555,10 @@ xfs_file_dio_aio_write( iolock = XFS_IOLOCK_SHARED; } - if (!xfs_ilock_nowait(ip, iolock)) { - if (iocb->ki_flags & IOCB_NOWAIT) + if (iocb->ki_flags & IOCB_NOWAIT) { + if (!xfs_ilock_nowait(ip, iolock)) return -EAGAIN; + } else { xfs_ilock(ip, iolock); } @@ -606,9 +610,10 @@ xfs_file_dax_write( size_t count; loff_t pos; - if (!xfs_ilock_nowait(ip, iolock)) { - if (iocb->ki_flags & IOCB_NOWAIT) + if (iocb->ki_flags & IOCB_NOWAIT) { + if (!xfs_ilock_nowait(ip, iolock)) return -EAGAIN; + } else { xfs_ilock(ip, iolock); } @@ -764,7 +769,7 @@ xfs_file_fallocate( enum xfs_prealloc_flags flags = 0; uint iolock = XFS_IOLOCK_EXCL; loff_t new_size = 0; - bool do_file_insert = 0; + bool do_file_insert = false; if (!S_ISREG(inode->i_mode)) return -EINVAL; @@ -825,7 +830,7 @@ xfs_file_fallocate( error = -EINVAL; goto out_unlock; } - do_file_insert = 1; + do_file_insert = true; } else { flags |= XFS_PREALLOC_SET; diff --git a/fs/xfs/xfs_fsmap.c b/fs/xfs/xfs_fsmap.c index 814ed729881d..43cfc07996a4 100644 --- a/fs/xfs/xfs_fsmap.c +++ b/fs/xfs/xfs_fsmap.c @@ -367,29 +367,6 @@ xfs_getfsmap_datadev_helper( return xfs_getfsmap_helper(cur->bc_tp, info, rec, rec_daddr); } -/* Transform a rtbitmap "record" into a fsmap */ -STATIC int -xfs_getfsmap_rtdev_rtbitmap_helper( - struct xfs_trans *tp, - struct xfs_rtalloc_rec *rec, - void *priv) -{ - struct xfs_mount *mp = tp->t_mountp; - struct xfs_getfsmap_info *info = priv; - struct xfs_rmap_irec irec; - xfs_daddr_t rec_daddr; - - rec_daddr = XFS_FSB_TO_BB(mp, rec->ar_startblock); - - irec.rm_startblock = rec->ar_startblock; - irec.rm_blockcount = rec->ar_blockcount; - irec.rm_owner = XFS_RMAP_OWN_NULL; /* "free" */ - irec.rm_offset = 0; - irec.rm_flags = 0; - - return xfs_getfsmap_helper(tp, info, &irec, rec_daddr); -} - /* Transform a bnobt irec into a fsmap */ STATIC int xfs_getfsmap_datadev_bnobt_helper( @@ -475,6 +452,30 @@ xfs_getfsmap_logdev( return xfs_getfsmap_helper(tp, info, &rmap, 0); } +#ifdef CONFIG_XFS_RT +/* Transform a rtbitmap "record" into a fsmap */ +STATIC int +xfs_getfsmap_rtdev_rtbitmap_helper( + struct xfs_trans *tp, + struct xfs_rtalloc_rec *rec, + void *priv) +{ + struct xfs_mount *mp = tp->t_mountp; + struct xfs_getfsmap_info *info = priv; + struct xfs_rmap_irec irec; + xfs_daddr_t rec_daddr; + + rec_daddr = XFS_FSB_TO_BB(mp, rec->ar_startblock); + + irec.rm_startblock = rec->ar_startblock; + irec.rm_blockcount = rec->ar_blockcount; + irec.rm_owner = XFS_RMAP_OWN_NULL; /* "free" */ + irec.rm_offset = 0; + irec.rm_flags = 0; + + return xfs_getfsmap_helper(tp, info, &irec, rec_daddr); +} + /* Execute a getfsmap query against the realtime device. */ STATIC int __xfs_getfsmap_rtdev( @@ -561,6 +562,7 @@ xfs_getfsmap_rtdev_rtbitmap( return __xfs_getfsmap_rtdev(tp, keys, xfs_getfsmap_rtdev_rtbitmap_query, info); } +#endif /* CONFIG_XFS_RT */ /* Execute a getfsmap query against the regular data device. */ STATIC int @@ -795,7 +797,15 @@ xfs_getfsmap_check_keys( return false; } +/* + * There are only two devices if we didn't configure RT devices at build time. + */ +#ifdef CONFIG_XFS_RT #define XFS_GETFSMAP_DEVS 3 +#else +#define XFS_GETFSMAP_DEVS 2 +#endif /* CONFIG_XFS_RT */ + /* * Get filesystem's extents as described in head, and format for * output. Calls formatter to fill the user's buffer until all @@ -853,10 +863,12 @@ xfs_getfsmap( handlers[1].dev = new_encode_dev(mp->m_logdev_targp->bt_dev); handlers[1].fn = xfs_getfsmap_logdev; } +#ifdef CONFIG_XFS_RT if (mp->m_rtdev_targp) { handlers[2].dev = new_encode_dev(mp->m_rtdev_targp->bt_dev); handlers[2].fn = xfs_getfsmap_rtdev_rtbitmap; } +#endif /* CONFIG_XFS_RT */ xfs_sort(handlers, XFS_GETFSMAP_DEVS, sizeof(struct xfs_getfsmap_dev), xfs_getfsmap_dev_compare); diff --git a/fs/xfs/xfs_inode_item.c b/fs/xfs/xfs_inode_item.c index a705f34b58fa..9bbc2d7cc8cb 100644 --- a/fs/xfs/xfs_inode_item.c +++ b/fs/xfs/xfs_inode_item.c @@ -364,6 +364,9 @@ xfs_inode_to_log_dinode( to->di_dmstate = from->di_dmstate; to->di_flags = from->di_flags; + /* log a dummy value to ensure log structure is fully initialised */ + to->di_next_unlinked = NULLAGINO; + if (from->di_version == 3) { to->di_changecount = inode->i_version; to->di_crtime.t_sec = from->di_crtime.t_sec; @@ -404,6 +407,11 @@ xfs_inode_item_format_core( * the second with the on-disk inode structure, and a possible third and/or * fourth with the inode data/extents/b-tree root and inode attributes * data/extents/b-tree root. + * + * Note: Always use the 64 bit inode log format structure so we don't + * leave an uninitialised hole in the format item on 64 bit systems. Log + * recovery on 32 bit systems handles this just fine, so there's no reason + * for not using an initialising the properly padded structure all the time. */ STATIC void xfs_inode_item_format( @@ -412,8 +420,8 @@ xfs_inode_item_format( { struct xfs_inode_log_item *iip = INODE_ITEM(lip); struct xfs_inode *ip = iip->ili_inode; - struct xfs_inode_log_format *ilf; struct xfs_log_iovec *vecp = NULL; + struct xfs_inode_log_format *ilf; ASSERT(ip->i_d.di_version > 1); @@ -425,7 +433,17 @@ xfs_inode_item_format( ilf->ilf_boffset = ip->i_imap.im_boffset; ilf->ilf_fields = XFS_ILOG_CORE; ilf->ilf_size = 2; /* format + core */ - xlog_finish_iovec(lv, vecp, sizeof(struct xfs_inode_log_format)); + + /* + * make sure we don't leak uninitialised data into the log in the case + * when we don't log every field in the inode. + */ + ilf->ilf_dsize = 0; + ilf->ilf_asize = 0; + ilf->ilf_pad = 0; + uuid_copy(&ilf->ilf_u.ilfu_uuid, &uuid_null); + + xlog_finish_iovec(lv, vecp, sizeof(*ilf)); xfs_inode_item_format_core(ip, lv, &vecp); xfs_inode_item_format_data_fork(iip, ilf, lv, &vecp); @@ -855,44 +873,29 @@ xfs_istale_done( } /* - * convert an xfs_inode_log_format struct from either 32 or 64 bit versions - * (which can have different field alignments) to the native version + * convert an xfs_inode_log_format struct from the old 32 bit version + * (which can have different field alignments) to the native 64 bit version */ int xfs_inode_item_format_convert( - xfs_log_iovec_t *buf, - xfs_inode_log_format_t *in_f) + struct xfs_log_iovec *buf, + struct xfs_inode_log_format *in_f) { - if (buf->i_len == sizeof(xfs_inode_log_format_32_t)) { - xfs_inode_log_format_32_t *in_f32 = buf->i_addr; - - in_f->ilf_type = in_f32->ilf_type; - in_f->ilf_size = in_f32->ilf_size; - in_f->ilf_fields = in_f32->ilf_fields; - in_f->ilf_asize = in_f32->ilf_asize; - in_f->ilf_dsize = in_f32->ilf_dsize; - in_f->ilf_ino = in_f32->ilf_ino; - /* copy biggest field of ilf_u */ - uuid_copy(&in_f->ilf_u.ilfu_uuid, &in_f32->ilf_u.ilfu_uuid); - in_f->ilf_blkno = in_f32->ilf_blkno; - in_f->ilf_len = in_f32->ilf_len; - in_f->ilf_boffset = in_f32->ilf_boffset; - return 0; - } else if (buf->i_len == sizeof(xfs_inode_log_format_64_t)){ - xfs_inode_log_format_64_t *in_f64 = buf->i_addr; - - in_f->ilf_type = in_f64->ilf_type; - in_f->ilf_size = in_f64->ilf_size; - in_f->ilf_fields = in_f64->ilf_fields; - in_f->ilf_asize = in_f64->ilf_asize; - in_f->ilf_dsize = in_f64->ilf_dsize; - in_f->ilf_ino = in_f64->ilf_ino; - /* copy biggest field of ilf_u */ - uuid_copy(&in_f->ilf_u.ilfu_uuid, &in_f64->ilf_u.ilfu_uuid); - in_f->ilf_blkno = in_f64->ilf_blkno; - in_f->ilf_len = in_f64->ilf_len; - in_f->ilf_boffset = in_f64->ilf_boffset; - return 0; - } - return -EFSCORRUPTED; + struct xfs_inode_log_format_32 *in_f32 = buf->i_addr; + + if (buf->i_len != sizeof(*in_f32)) + return -EFSCORRUPTED; + + in_f->ilf_type = in_f32->ilf_type; + in_f->ilf_size = in_f32->ilf_size; + in_f->ilf_fields = in_f32->ilf_fields; + in_f->ilf_asize = in_f32->ilf_asize; + in_f->ilf_dsize = in_f32->ilf_dsize; + in_f->ilf_ino = in_f32->ilf_ino; + /* copy biggest field of ilf_u */ + uuid_copy(&in_f->ilf_u.ilfu_uuid, &in_f32->ilf_u.ilfu_uuid); + in_f->ilf_blkno = in_f32->ilf_blkno; + in_f->ilf_len = in_f32->ilf_len; + in_f->ilf_boffset = in_f32->ilf_boffset; + return 0; } diff --git a/fs/xfs/xfs_log.c b/fs/xfs/xfs_log.c index c5107c7bc4bf..dc95a49d62e7 100644 --- a/fs/xfs/xfs_log.c +++ b/fs/xfs/xfs_log.c @@ -2515,7 +2515,7 @@ next_lv: if (lv) vecp = lv->lv_iovecp; } - if (record_cnt == 0 && ordered == false) { + if (record_cnt == 0 && !ordered) { if (!lv) return 0; break; diff --git a/fs/xfs/xfs_mount.c b/fs/xfs/xfs_mount.c index ea7d4b4e50d0..e9727d0a541a 100644 --- a/fs/xfs/xfs_mount.c +++ b/fs/xfs/xfs_mount.c @@ -704,7 +704,7 @@ xfs_mountfs( xfs_set_maxicount(mp); /* enable fail_at_unmount as default */ - mp->m_fail_unmount = 1; + mp->m_fail_unmount = true; error = xfs_sysfs_init(&mp->m_kobj, &xfs_mp_ktype, NULL, mp->m_fsname); if (error) diff --git a/fs/xfs/xfs_ondisk.h b/fs/xfs/xfs_ondisk.h index 0c381d71b242..0492436a053f 100644 --- a/fs/xfs/xfs_ondisk.h +++ b/fs/xfs/xfs_ondisk.h @@ -134,7 +134,7 @@ xfs_check_ondisk_structs(void) XFS_CHECK_STRUCT_SIZE(struct xfs_icreate_log, 28); XFS_CHECK_STRUCT_SIZE(struct xfs_ictimestamp, 8); XFS_CHECK_STRUCT_SIZE(struct xfs_inode_log_format_32, 52); - XFS_CHECK_STRUCT_SIZE(struct xfs_inode_log_format_64, 56); + XFS_CHECK_STRUCT_SIZE(struct xfs_inode_log_format, 56); XFS_CHECK_STRUCT_SIZE(struct xfs_qoff_logformat, 20); XFS_CHECK_STRUCT_SIZE(struct xfs_trans_header, 16); } diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c index 584cf2d573ba..f663022353c0 100644 --- a/fs/xfs/xfs_super.c +++ b/fs/xfs/xfs_super.c @@ -1637,7 +1637,7 @@ xfs_fs_fill_super( /* version 5 superblocks support inode version counters. */ if (XFS_SB_VERSION_NUM(&mp->m_sb) == XFS_SB_VERSION_5) - sb->s_flags |= MS_I_VERSION; + sb->s_flags |= SB_I_VERSION; if (mp->m_flags & XFS_MOUNT_DAX) { xfs_warn(mp, diff --git a/include/linux/buffer_head.h b/include/linux/buffer_head.h index c8dae555eccf..446b24cac67d 100644 --- a/include/linux/buffer_head.h +++ b/include/linux/buffer_head.h @@ -232,6 +232,7 @@ int generic_write_end(struct file *, struct address_space *, loff_t, unsigned, unsigned, struct page *, void *); void page_zero_new_buffers(struct page *page, unsigned from, unsigned to); +void clean_page_buffers(struct page *page); int cont_write_begin(struct file *, struct address_space *, loff_t, unsigned, unsigned, struct page **, void **, get_block_t *, loff_t *); diff --git a/include/linux/filter.h b/include/linux/filter.h index d29e58fde364..818a0b26249e 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -728,7 +728,7 @@ void xdp_do_flush_map(void); void bpf_warn_invalid_xdp_action(u32 act); void bpf_warn_invalid_xdp_redirect(u32 ifindex); -struct sock *do_sk_redirect_map(void); +struct sock *do_sk_redirect_map(struct sk_buff *skb); #ifdef CONFIG_BPF_JIT extern int bpf_jit_enable; diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h index c458d7b7ad19..6431087816ba 100644 --- a/include/linux/hyperv.h +++ b/include/linux/hyperv.h @@ -1403,7 +1403,7 @@ extern bool vmbus_prep_negotiate_resp(struct icmsg_hdr *icmsghdrp, u8 *buf, const int *srv_version, int srv_vercnt, int *nego_fw_version, int *nego_srv_version); -void hv_process_channel_removal(struct vmbus_channel *channel, u32 relid); +void hv_process_channel_removal(u32 relid); void vmbus_setevent(struct vmbus_channel *channel); /* diff --git a/include/linux/if_tap.h b/include/linux/if_tap.h index 4837157da0dc..9ae41cdd0d4c 100644 --- a/include/linux/if_tap.h +++ b/include/linux/if_tap.h @@ -73,8 +73,8 @@ void tap_del_queues(struct tap_dev *tap); int tap_get_minor(dev_t major, struct tap_dev *tap); void tap_free_minor(dev_t major, struct tap_dev *tap); int tap_queue_resize(struct tap_dev *tap); -int tap_create_cdev(struct cdev *tap_cdev, - dev_t *tap_major, const char *device_name); +int tap_create_cdev(struct cdev *tap_cdev, dev_t *tap_major, + const char *device_name, struct module *module); void tap_destroy_cdev(dev_t major, struct cdev *tap_cdev); #endif /*_LINUX_IF_TAP_H_*/ diff --git a/include/linux/input.h b/include/linux/input.h index fb5e23c7ed98..7c7516eb7d76 100644 --- a/include/linux/input.h +++ b/include/linux/input.h @@ -234,6 +234,10 @@ struct input_dev { #error "SW_MAX and INPUT_DEVICE_ID_SW_MAX do not match" #endif +#if INPUT_PROP_MAX != INPUT_DEVICE_ID_PROP_MAX +#error "INPUT_PROP_MAX and INPUT_DEVICE_ID_PROP_MAX do not match" +#endif + #define INPUT_DEVICE_ID_MATCH_DEVICE \ (INPUT_DEVICE_ID_MATCH_BUS | INPUT_DEVICE_ID_MATCH_VENDOR | INPUT_DEVICE_ID_MATCH_PRODUCT) #define INPUT_DEVICE_ID_MATCH_DEVICE_AND_VERSION \ @@ -469,6 +473,9 @@ int input_get_keycode(struct input_dev *dev, struct input_keymap_entry *ke); int input_set_keycode(struct input_dev *dev, const struct input_keymap_entry *ke); +bool input_match_device_id(const struct input_dev *dev, + const struct input_device_id *id); + void input_enable_softrepeat(struct input_dev *dev, int delay, int period); extern struct class input_class; diff --git a/include/linux/irq.h b/include/linux/irq.h index d4728bf6a537..5ad10948ea95 100644 --- a/include/linux/irq.h +++ b/include/linux/irq.h @@ -1009,7 +1009,7 @@ void irq_gc_mask_clr_bit(struct irq_data *d); void irq_gc_unmask_enable_reg(struct irq_data *d); void irq_gc_ack_set_bit(struct irq_data *d); void irq_gc_ack_clr_bit(struct irq_data *d); -void irq_gc_mask_disable_reg_and_ack(struct irq_data *d); +void irq_gc_mask_disable_and_ack_set(struct irq_data *d); void irq_gc_eoi(struct irq_data *d); int irq_gc_set_wake(struct irq_data *d, unsigned int on); diff --git a/include/linux/irqchip/arm-gic-v3.h b/include/linux/irqchip/arm-gic-v3.h index 1ea576c8126f..14b74f22d43c 100644 --- a/include/linux/irqchip/arm-gic-v3.h +++ b/include/linux/irqchip/arm-gic-v3.h @@ -372,6 +372,8 @@ #define GITS_BASER_ENTRY_SIZE_SHIFT (48) #define GITS_BASER_ENTRY_SIZE(r) ((((r) >> GITS_BASER_ENTRY_SIZE_SHIFT) & 0x1f) + 1) #define GITS_BASER_ENTRY_SIZE_MASK GENMASK_ULL(52, 48) +#define GITS_BASER_PHYS_52_to_48(phys) \ + (((phys) & GENMASK_ULL(47, 16)) | (((phys) >> 48) & 0xf) << 12) #define GITS_BASER_SHAREABILITY_SHIFT (10) #define GITS_BASER_InnerShareable \ GIC_BASER_SHAREABILITY(GITS_BASER, InnerShareable) diff --git a/include/linux/kernel.h b/include/linux/kernel.h index 0ad4c3044cf9..91189bb0c818 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -44,6 +44,12 @@ #define STACK_MAGIC 0xdeadbeef +/** + * REPEAT_BYTE - repeat the value @x multiple times as an unsigned long value + * @x: value to repeat + * + * NOTE: @x is not checked for > 0xff; larger values produce odd results. + */ #define REPEAT_BYTE(x) ((~0ul / 0xff) * (x)) /* @a is a power of 2 value */ @@ -57,6 +63,10 @@ #define READ 0 #define WRITE 1 +/** + * ARRAY_SIZE - get the number of elements in array @arr + * @arr: array to be sized + */ #define ARRAY_SIZE(arr) (sizeof(arr) / sizeof((arr)[0]) + __must_be_array(arr)) #define u64_to_user_ptr(x) ( \ @@ -76,7 +86,15 @@ #define round_up(x, y) ((((x)-1) | __round_mask(x, y))+1) #define round_down(x, y) ((x) & ~__round_mask(x, y)) +/** + * FIELD_SIZEOF - get the size of a struct's field + * @t: the target struct + * @f: the target struct's field + * Return: the size of @f in the struct definition without having a + * declared instance of @t. + */ #define FIELD_SIZEOF(t, f) (sizeof(((t*)0)->f)) + #define DIV_ROUND_UP __KERNEL_DIV_ROUND_UP #define DIV_ROUND_DOWN_ULL(ll, d) \ @@ -107,7 +125,7 @@ /* * Divide positive or negative dividend by positive or negative divisor * and round to closest integer. Result is undefined for negative - * divisors if he dividend variable type is unsigned and for negative + * divisors if the dividend variable type is unsigned and for negative * dividends if the divisor variable type is unsigned. */ #define DIV_ROUND_CLOSEST(x, divisor)( \ @@ -247,13 +265,13 @@ extern int _cond_resched(void); * @ep_ro: right open interval endpoint * * Perform a "reciprocal multiplication" in order to "scale" a value into - * range [0, ep_ro), where the upper interval endpoint is right-open. + * range [0, @ep_ro), where the upper interval endpoint is right-open. * This is useful, e.g. for accessing a index of an array containing - * ep_ro elements, for example. Think of it as sort of modulus, only that + * @ep_ro elements, for example. Think of it as sort of modulus, only that * the result isn't that of modulo. ;) Note that if initial input is a * small value, then result will return 0. * - * Return: a result based on val in interval [0, ep_ro). + * Return: a result based on @val in interval [0, @ep_ro). */ static inline u32 reciprocal_scale(u32 val, u32 ep_ro) { @@ -618,8 +636,8 @@ do { \ * trace_printk - printf formatting in the ftrace buffer * @fmt: the printf format for printing * - * Note: __trace_printk is an internal function for trace_printk and - * the @ip is passed in via the trace_printk macro. + * Note: __trace_printk is an internal function for trace_printk() and + * the @ip is passed in via the trace_printk() macro. * * This function allows a kernel developer to debug fast path sections * that printk is not appropriate for. By scattering in various @@ -629,7 +647,7 @@ do { \ * This is intended as a debugging tool for the developer only. * Please refrain from leaving trace_printks scattered around in * your code. (Extra memory is used for special buffers that are - * allocated when trace_printk() is used) + * allocated when trace_printk() is used.) * * A little optization trick is done here. If there's only one * argument, there's no need to scan the string for printf formats. @@ -681,7 +699,7 @@ int __trace_printk(unsigned long ip, const char *fmt, ...); * the @ip is passed in via the trace_puts macro. * * This is similar to trace_printk() but is made for those really fast - * paths that a developer wants the least amount of "Heisenbug" affects, + * paths that a developer wants the least amount of "Heisenbug" effects, * where the processing of the print format is still too much. * * This function allows a kernel developer to debug fast path sections @@ -692,7 +710,7 @@ int __trace_printk(unsigned long ip, const char *fmt, ...); * This is intended as a debugging tool for the developer only. * Please refrain from leaving trace_puts scattered around in * your code. (Extra memory is used for special buffers that are - * allocated when trace_puts() is used) + * allocated when trace_puts() is used.) * * Returns: 0 if nothing was written, positive # if string was. * (1 when __trace_bputs is used, strlen(str) when __trace_puts is used) @@ -771,6 +789,12 @@ static inline void ftrace_dump(enum ftrace_dump_mode oops_dump_mode) { } t2 min2 = (y); \ (void) (&min1 == &min2); \ min1 < min2 ? min1 : min2; }) + +/** + * min - return minimum of two values of the same or compatible types + * @x: first value + * @y: second value + */ #define min(x, y) \ __min(typeof(x), typeof(y), \ __UNIQUE_ID(min1_), __UNIQUE_ID(min2_), \ @@ -781,12 +805,31 @@ static inline void ftrace_dump(enum ftrace_dump_mode oops_dump_mode) { } t2 max2 = (y); \ (void) (&max1 == &max2); \ max1 > max2 ? max1 : max2; }) + +/** + * max - return maximum of two values of the same or compatible types + * @x: first value + * @y: second value + */ #define max(x, y) \ __max(typeof(x), typeof(y), \ __UNIQUE_ID(max1_), __UNIQUE_ID(max2_), \ x, y) +/** + * min3 - return minimum of three values + * @x: first value + * @y: second value + * @z: third value + */ #define min3(x, y, z) min((typeof(x))min(x, y), z) + +/** + * max3 - return maximum of three values + * @x: first value + * @y: second value + * @z: third value + */ #define max3(x, y, z) max((typeof(x))max(x, y), z) /** @@ -805,8 +848,8 @@ static inline void ftrace_dump(enum ftrace_dump_mode oops_dump_mode) { } * @lo: lowest allowable value * @hi: highest allowable value * - * This macro does strict typechecking of lo/hi to make sure they are of the - * same type as val. See the unnecessary pointer comparisons. + * This macro does strict typechecking of @lo/@hi to make sure they are of the + * same type as @val. See the unnecessary pointer comparisons. */ #define clamp(val, lo, hi) min((typeof(val))max(val, lo), hi) @@ -816,11 +859,24 @@ static inline void ftrace_dump(enum ftrace_dump_mode oops_dump_mode) { } * * Or not use min/max/clamp at all, of course. */ + +/** + * min_t - return minimum of two values, using the specified type + * @type: data type to use + * @x: first value + * @y: second value + */ #define min_t(type, x, y) \ __min(type, type, \ __UNIQUE_ID(min1_), __UNIQUE_ID(min2_), \ x, y) +/** + * max_t - return maximum of two values, using the specified type + * @type: data type to use + * @x: first value + * @y: second value + */ #define max_t(type, x, y) \ __max(type, type, \ __UNIQUE_ID(min1_), __UNIQUE_ID(min2_), \ @@ -834,7 +890,7 @@ static inline void ftrace_dump(enum ftrace_dump_mode oops_dump_mode) { } * @hi: maximum allowable value * * This macro does no typechecking and uses temporary variables of type - * 'type' to make all the comparisons. + * @type to make all the comparisons. */ #define clamp_t(type, val, lo, hi) min_t(type, max_t(type, val, lo), hi) @@ -845,15 +901,17 @@ static inline void ftrace_dump(enum ftrace_dump_mode oops_dump_mode) { } * @hi: maximum allowable value * * This macro does no typechecking and uses temporary variables of whatever - * type the input argument 'val' is. This is useful when val is an unsigned - * type and min and max are literals that will otherwise be assigned a signed + * type the input argument @val is. This is useful when @val is an unsigned + * type and @lo and @hi are literals that will otherwise be assigned a signed * integer type. */ #define clamp_val(val, lo, hi) clamp_t(typeof(val), val, lo, hi) -/* - * swap - swap value of @a and @b +/** + * swap - swap values of @a and @b + * @a: first value + * @b: second value */ #define swap(a, b) \ do { typeof(a) __tmp = (a); (a) = (b); (b) = __tmp; } while (0) diff --git a/include/linux/key.h b/include/linux/key.h index e315e16b6ff8..8a15cabe928d 100644 --- a/include/linux/key.h +++ b/include/linux/key.h @@ -138,6 +138,11 @@ struct key_restriction { struct key_type *keytype; }; +enum key_state { + KEY_IS_UNINSTANTIATED, + KEY_IS_POSITIVE, /* Positively instantiated */ +}; + /*****************************************************************************/ /* * authentication token / access credential / keyring @@ -169,6 +174,7 @@ struct key { * - may not match RCU dereferenced payload * - payload should contain own length */ + short state; /* Key state (+) or rejection error (-) */ #ifdef KEY_DEBUGGING unsigned magic; @@ -176,18 +182,16 @@ struct key { #endif unsigned long flags; /* status flags (change with bitops) */ -#define KEY_FLAG_INSTANTIATED 0 /* set if key has been instantiated */ -#define KEY_FLAG_DEAD 1 /* set if key type has been deleted */ -#define KEY_FLAG_REVOKED 2 /* set if key had been revoked */ -#define KEY_FLAG_IN_QUOTA 3 /* set if key consumes quota */ -#define KEY_FLAG_USER_CONSTRUCT 4 /* set if key is being constructed in userspace */ -#define KEY_FLAG_NEGATIVE 5 /* set if key is negative */ -#define KEY_FLAG_ROOT_CAN_CLEAR 6 /* set if key can be cleared by root without permission */ -#define KEY_FLAG_INVALIDATED 7 /* set if key has been invalidated */ -#define KEY_FLAG_BUILTIN 8 /* set if key is built in to the kernel */ -#define KEY_FLAG_ROOT_CAN_INVAL 9 /* set if key can be invalidated by root without permission */ -#define KEY_FLAG_KEEP 10 /* set if key should not be removed */ -#define KEY_FLAG_UID_KEYRING 11 /* set if key is a user or user session keyring */ +#define KEY_FLAG_DEAD 0 /* set if key type has been deleted */ +#define KEY_FLAG_REVOKED 1 /* set if key had been revoked */ +#define KEY_FLAG_IN_QUOTA 2 /* set if key consumes quota */ +#define KEY_FLAG_USER_CONSTRUCT 3 /* set if key is being constructed in userspace */ +#define KEY_FLAG_ROOT_CAN_CLEAR 4 /* set if key can be cleared by root without permission */ +#define KEY_FLAG_INVALIDATED 5 /* set if key has been invalidated */ +#define KEY_FLAG_BUILTIN 6 /* set if key is built in to the kernel */ +#define KEY_FLAG_ROOT_CAN_INVAL 7 /* set if key can be invalidated by root without permission */ +#define KEY_FLAG_KEEP 8 /* set if key should not be removed */ +#define KEY_FLAG_UID_KEYRING 9 /* set if key is a user or user session keyring */ /* the key type and key description string * - the desc is used to match a key against search criteria @@ -213,7 +217,6 @@ struct key { struct list_head name_link; struct assoc_array keys; }; - int reject_error; }; /* This is set on a keyring to restrict the addition of a link to a key @@ -353,17 +356,27 @@ extern void key_set_timeout(struct key *, unsigned); #define KEY_NEED_SETATTR 0x20 /* Require permission to change attributes */ #define KEY_NEED_ALL 0x3f /* All the above permissions */ +static inline short key_read_state(const struct key *key) +{ + /* Barrier versus mark_key_instantiated(). */ + return smp_load_acquire(&key->state); +} + /** - * key_is_instantiated - Determine if a key has been positively instantiated + * key_is_positive - Determine if a key has been positively instantiated * @key: The key to check. * * Return true if the specified key has been positively instantiated, false * otherwise. */ -static inline bool key_is_instantiated(const struct key *key) +static inline bool key_is_positive(const struct key *key) +{ + return key_read_state(key) == KEY_IS_POSITIVE; +} + +static inline bool key_is_negative(const struct key *key) { - return test_bit(KEY_FLAG_INSTANTIATED, &key->flags) && - !test_bit(KEY_FLAG_NEGATIVE, &key->flags); + return key_read_state(key) < 0; } #define dereference_key_rcu(KEY) \ diff --git a/include/linux/mbus.h b/include/linux/mbus.h index 0d3f14fd2621..4773145246ed 100644 --- a/include/linux/mbus.h +++ b/include/linux/mbus.h @@ -31,8 +31,8 @@ struct mbus_dram_target_info struct mbus_dram_window { u8 cs_index; u8 mbus_attr; - u32 base; - u32 size; + u64 base; + u64 size; } cs[4]; }; diff --git a/include/linux/mlx5/port.h b/include/linux/mlx5/port.h index c57d4b7de3a8..c59af8ab753a 100644 --- a/include/linux/mlx5/port.h +++ b/include/linux/mlx5/port.h @@ -157,6 +157,8 @@ int mlx5_set_port_prio_tc(struct mlx5_core_dev *mdev, u8 *prio_tc); int mlx5_query_port_prio_tc(struct mlx5_core_dev *mdev, u8 prio, u8 *tc); int mlx5_set_port_tc_group(struct mlx5_core_dev *mdev, u8 *tc_group); +int mlx5_query_port_tc_group(struct mlx5_core_dev *mdev, + u8 tc, u8 *tc_group); int mlx5_set_port_tc_bw_alloc(struct mlx5_core_dev *mdev, u8 *tc_bw); int mlx5_query_port_tc_bw_alloc(struct mlx5_core_dev *mdev, u8 tc, u8 *bw_pct); diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 46f4ecf5479a..1861ea8dba77 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -445,6 +445,9 @@ struct mm_struct { unsigned long flags; /* Must use atomic bitops to access the bits */ struct core_state *core_state; /* coredumping support */ +#ifdef CONFIG_MEMBARRIER + atomic_t membarrier_state; +#endif #ifdef CONFIG_AIO spinlock_t ioctx_lock; struct kioctx_table __rcu *ioctx_table; diff --git a/include/linux/mod_devicetable.h b/include/linux/mod_devicetable.h index 694cebb50f72..2657f9f51536 100644 --- a/include/linux/mod_devicetable.h +++ b/include/linux/mod_devicetable.h @@ -293,6 +293,7 @@ struct pcmcia_device_id { #define INPUT_DEVICE_ID_SND_MAX 0x07 #define INPUT_DEVICE_ID_FF_MAX 0x7f #define INPUT_DEVICE_ID_SW_MAX 0x0f +#define INPUT_DEVICE_ID_PROP_MAX 0x1f #define INPUT_DEVICE_ID_MATCH_BUS 1 #define INPUT_DEVICE_ID_MATCH_VENDOR 2 @@ -308,6 +309,7 @@ struct pcmcia_device_id { #define INPUT_DEVICE_ID_MATCH_SNDBIT 0x0400 #define INPUT_DEVICE_ID_MATCH_FFBIT 0x0800 #define INPUT_DEVICE_ID_MATCH_SWBIT 0x1000 +#define INPUT_DEVICE_ID_MATCH_PROPBIT 0x2000 struct input_device_id { @@ -327,6 +329,7 @@ struct input_device_id { kernel_ulong_t sndbit[INPUT_DEVICE_ID_SND_MAX / BITS_PER_LONG + 1]; kernel_ulong_t ffbit[INPUT_DEVICE_ID_FF_MAX / BITS_PER_LONG + 1]; kernel_ulong_t swbit[INPUT_DEVICE_ID_SW_MAX / BITS_PER_LONG + 1]; + kernel_ulong_t propbit[INPUT_DEVICE_ID_PROP_MAX / BITS_PER_LONG + 1]; kernel_ulong_t driver_info; }; diff --git a/include/linux/of.h b/include/linux/of.h index cfc34117fc92..b240ed69dc96 100644 --- a/include/linux/of.h +++ b/include/linux/of.h @@ -734,6 +734,16 @@ static inline struct device_node *of_get_cpu_node(int cpu, return NULL; } +static inline int of_n_addr_cells(struct device_node *np) +{ + return 0; + +} +static inline int of_n_size_cells(struct device_node *np) +{ + return 0; +} + static inline int of_property_read_u64(const struct device_node *np, const char *propname, u64 *out_value) { diff --git a/include/linux/rculist.h b/include/linux/rculist.h index b1fd8bf85fdc..2bea1d5e9930 100644 --- a/include/linux/rculist.h +++ b/include/linux/rculist.h @@ -276,7 +276,7 @@ static inline void list_splice_tail_init_rcu(struct list_head *list, #define list_entry_rcu(ptr, type, member) \ container_of(lockless_dereference(ptr), type, member) -/** +/* * Where are list_empty_rcu() and list_first_entry_rcu()? * * Implementing those functions following their counterparts list_empty() and diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index de50d8a4cf41..1a9f70d44af9 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -523,7 +523,7 @@ static inline void rcu_preempt_sleep_check(void) { } * Return the value of the specified RCU-protected pointer, but omit * both the smp_read_barrier_depends() and the READ_ONCE(). This * is useful in cases where update-side locks prevent the value of the - * pointer from changing. Please note that this primitive does -not- + * pointer from changing. Please note that this primitive does *not* * prevent the compiler from repeating this reference or combining it * with other references, so it should not be used without protection * of appropriate locks. @@ -568,7 +568,7 @@ static inline void rcu_preempt_sleep_check(void) { } * is handed off from RCU to some other synchronization mechanism, for * example, reference counting or locking. In C11, it would map to * kill_dependency(). It could be used as follows: - * + * `` * rcu_read_lock(); * p = rcu_dereference(gp); * long_lived = is_long_lived(p); @@ -579,6 +579,7 @@ static inline void rcu_preempt_sleep_check(void) { } * p = rcu_pointer_handoff(p); * } * rcu_read_unlock(); + *`` */ #define rcu_pointer_handoff(p) (p) @@ -778,18 +779,21 @@ static inline notrace void rcu_read_unlock_sched_notrace(void) /** * RCU_INIT_POINTER() - initialize an RCU protected pointer + * @p: The pointer to be initialized. + * @v: The value to initialized the pointer to. * * Initialize an RCU-protected pointer in special cases where readers * do not need ordering constraints on the CPU or the compiler. These * special cases are: * - * 1. This use of RCU_INIT_POINTER() is NULLing out the pointer -or- + * 1. This use of RCU_INIT_POINTER() is NULLing out the pointer *or* * 2. The caller has taken whatever steps are required to prevent - * RCU readers from concurrently accessing this pointer -or- + * RCU readers from concurrently accessing this pointer *or* * 3. The referenced data structure has already been exposed to - * readers either at compile time or via rcu_assign_pointer() -and- - * a. You have not made -any- reader-visible changes to - * this structure since then -or- + * readers either at compile time or via rcu_assign_pointer() *and* + * + * a. You have not made *any* reader-visible changes to + * this structure since then *or* * b. It is OK for readers accessing this structure from its * new location to see the old state of the structure. (For * example, the changes were to statistical counters or to @@ -805,7 +809,7 @@ static inline notrace void rcu_read_unlock_sched_notrace(void) * by a single external-to-structure RCU-protected pointer, then you may * use RCU_INIT_POINTER() to initialize the internal RCU-protected * pointers, but you must use rcu_assign_pointer() to initialize the - * external-to-structure pointer -after- you have completely initialized + * external-to-structure pointer *after* you have completely initialized * the reader-accessible portions of the linked structure. * * Note that unlike rcu_assign_pointer(), RCU_INIT_POINTER() provides no @@ -819,6 +823,8 @@ static inline notrace void rcu_read_unlock_sched_notrace(void) /** * RCU_POINTER_INITIALIZER() - statically initialize an RCU protected pointer + * @p: The pointer to be initialized. + * @v: The value to initialized the pointer to. * * GCC-style initialization for an RCU-protected pointer in a structure field. */ diff --git a/include/linux/sched/mm.h b/include/linux/sched/mm.h index ae53e413fb13..ab9bf7b73954 100644 --- a/include/linux/sched/mm.h +++ b/include/linux/sched/mm.h @@ -211,4 +211,20 @@ static inline void memalloc_noreclaim_restore(unsigned int flags) current->flags = (current->flags & ~PF_MEMALLOC) | flags; } +#ifdef CONFIG_MEMBARRIER +enum { + MEMBARRIER_STATE_PRIVATE_EXPEDITED_READY = (1U << 0), + MEMBARRIER_STATE_SWITCH_MM = (1U << 1), +}; + +static inline void membarrier_execve(struct task_struct *t) +{ + atomic_set(&t->mm->membarrier_state, 0); +} +#else +static inline void membarrier_execve(struct task_struct *t) +{ +} +#endif + #endif /* _LINUX_SCHED_MM_H */ diff --git a/include/linux/sched/topology.h b/include/linux/sched/topology.h index d7b6dab956ec..7d065abc7a47 100644 --- a/include/linux/sched/topology.h +++ b/include/linux/sched/topology.h @@ -71,14 +71,6 @@ struct sched_domain_shared { atomic_t ref; atomic_t nr_busy_cpus; int has_idle_cores; - - /* - * Some variables from the most recent sd_lb_stats for this domain, - * used by wake_affine(). - */ - unsigned long nr_running; - unsigned long load; - unsigned long capacity; }; struct sched_domain { diff --git a/include/linux/sctp.h b/include/linux/sctp.h index 82b171e1aa0b..da803dfc7a39 100644 --- a/include/linux/sctp.h +++ b/include/linux/sctp.h @@ -231,7 +231,7 @@ struct sctp_datahdr { __be32 tsn; __be16 stream; __be16 ssn; - __be32 ppid; + __u32 ppid; __u8 payload[0]; }; @@ -716,28 +716,28 @@ struct sctp_reconf_chunk { struct sctp_strreset_outreq { struct sctp_paramhdr param_hdr; - __u32 request_seq; - __u32 response_seq; - __u32 send_reset_at_tsn; - __u16 list_of_streams[0]; + __be32 request_seq; + __be32 response_seq; + __be32 send_reset_at_tsn; + __be16 list_of_streams[0]; }; struct sctp_strreset_inreq { struct sctp_paramhdr param_hdr; - __u32 request_seq; - __u16 list_of_streams[0]; + __be32 request_seq; + __be16 list_of_streams[0]; }; struct sctp_strreset_tsnreq { struct sctp_paramhdr param_hdr; - __u32 request_seq; + __be32 request_seq; }; struct sctp_strreset_addstrm { struct sctp_paramhdr param_hdr; - __u32 request_seq; - __u16 number_of_streams; - __u16 reserved; + __be32 request_seq; + __be16 number_of_streams; + __be16 reserved; }; enum { @@ -752,16 +752,16 @@ enum { struct sctp_strreset_resp { struct sctp_paramhdr param_hdr; - __u32 response_seq; - __u32 result; + __be32 response_seq; + __be32 result; }; struct sctp_strreset_resptsn { struct sctp_paramhdr param_hdr; - __u32 response_seq; - __u32 result; - __u32 senders_next_tsn; - __u32 receivers_next_tsn; + __be32 response_seq; + __be32 result; + __be32 senders_next_tsn; + __be32 receivers_next_tsn; }; #endif /* __LINUX_SCTP_H__ */ diff --git a/include/linux/srcu.h b/include/linux/srcu.h index 39af9bc0f653..62be8966e837 100644 --- a/include/linux/srcu.h +++ b/include/linux/srcu.h @@ -78,6 +78,7 @@ void synchronize_srcu(struct srcu_struct *sp); /** * srcu_read_lock_held - might we be in SRCU read-side critical section? + * @sp: The srcu_struct structure to check * * If CONFIG_DEBUG_LOCK_ALLOC is selected, returns nonzero iff in an SRCU * read-side critical section. In absence of CONFIG_DEBUG_LOCK_ALLOC, diff --git a/include/linux/swait.h b/include/linux/swait.h index 73e97a08d3d0..cf30f5022472 100644 --- a/include/linux/swait.h +++ b/include/linux/swait.h @@ -9,13 +9,16 @@ /* * Simple wait queues * - * While these are very similar to the other/complex wait queues (wait.h) the - * most important difference is that the simple waitqueue allows for - * deterministic behaviour -- IOW it has strictly bounded IRQ and lock hold - * times. + * While these are very similar to regular wait queues (wait.h) the most + * important difference is that the simple waitqueue allows for deterministic + * behaviour -- IOW it has strictly bounded IRQ and lock hold times. * - * In order to make this so, we had to drop a fair number of features of the - * other waitqueue code; notably: + * Mainly, this is accomplished by two things. Firstly not allowing swake_up_all + * from IRQ disabled, and dropping the lock upon every wakeup, giving a higher + * priority task a chance to run. + * + * Secondly, we had to drop a fair number of features of the other waitqueue + * code; notably: * * - mixing INTERRUPTIBLE and UNINTERRUPTIBLE sleeps on the same waitqueue; * all wakeups are TASK_NORMAL in order to avoid O(n) lookups for the right @@ -24,12 +27,14 @@ * - the exclusive mode; because this requires preserving the list order * and this is hard. * - * - custom wake functions; because you cannot give any guarantees about - * random code. - * - * As a side effect of this; the data structures are slimmer. + * - custom wake callback functions; because you cannot give any guarantees + * about random code. This also allows swait to be used in RT, such that + * raw spinlock can be used for the swait queue head. * - * One would recommend using this wait queue where possible. + * As a side effect of these; the data structures are slimmer albeit more ad-hoc. + * For all the above, note that simple wait queues should _only_ be used under + * very specific realtime constraints -- it is best to stick with the regular + * wait queues in most cases. */ struct task_struct; diff --git a/include/linux/thread_info.h b/include/linux/thread_info.h index 905d769d8ddc..5f7eeab990fe 100644 --- a/include/linux/thread_info.h +++ b/include/linux/thread_info.h @@ -42,7 +42,7 @@ enum { #define THREAD_ALIGN THREAD_SIZE #endif -#ifdef CONFIG_DEBUG_STACK_USAGE +#if IS_ENABLED(CONFIG_DEBUG_STACK_USAGE) || IS_ENABLED(CONFIG_DEBUG_KMEMLEAK) # define THREADINFO_GFP (GFP_KERNEL_ACCOUNT | __GFP_NOTRACK | \ __GFP_ZERO) #else diff --git a/include/net/fq_impl.h b/include/net/fq_impl.h index 4e6131cd3f43..ac1a2317941e 100644 --- a/include/net/fq_impl.h +++ b/include/net/fq_impl.h @@ -146,6 +146,7 @@ static void fq_tin_enqueue(struct fq *fq, fq_flow_get_default_t get_default_func) { struct fq_flow *flow; + bool oom; lockdep_assert_held(&fq->lock); @@ -167,8 +168,8 @@ static void fq_tin_enqueue(struct fq *fq, } __skb_queue_tail(&flow->queue, skb); - - if (fq->backlog > fq->limit || fq->memory_usage > fq->memory_limit) { + oom = (fq->memory_usage > fq->memory_limit); + while (fq->backlog > fq->limit || oom) { flow = list_first_entry_or_null(&fq->backlogs, struct fq_flow, backlogchain); @@ -183,8 +184,10 @@ static void fq_tin_enqueue(struct fq *fq, flow->tin->overlimit++; fq->overlimit++; - if (fq->memory_usage > fq->memory_limit) + if (oom) { fq->overmemory++; + oom = (fq->memory_usage > fq->memory_limit); + } } } diff --git a/include/net/inet_sock.h b/include/net/inet_sock.h index aa95053dfc78..db8162dd8c0b 100644 --- a/include/net/inet_sock.h +++ b/include/net/inet_sock.h @@ -96,7 +96,7 @@ struct inet_request_sock { kmemcheck_bitfield_end(flags); u32 ir_mark; union { - struct ip_options_rcu *opt; + struct ip_options_rcu __rcu *ireq_opt; #if IS_ENABLED(CONFIG_IPV6) struct { struct ipv6_txoptions *ipv6_opt; @@ -132,6 +132,12 @@ static inline int inet_request_bound_dev_if(const struct sock *sk, return sk->sk_bound_dev_if; } +static inline struct ip_options_rcu *ireq_opt_deref(const struct inet_request_sock *ireq) +{ + return rcu_dereference_check(ireq->ireq_opt, + refcount_read(&ireq->req.rsk_refcnt) > 0); +} + struct inet_cork { unsigned int flags; __be32 addr; diff --git a/include/net/pkt_cls.h b/include/net/pkt_cls.h index e80edd8879ef..3009547f3c66 100644 --- a/include/net/pkt_cls.h +++ b/include/net/pkt_cls.h @@ -2,6 +2,7 @@ #define __NET_PKT_CLS_H #include <linux/pkt_cls.h> +#include <linux/workqueue.h> #include <net/sch_generic.h> #include <net/act_api.h> @@ -17,6 +18,8 @@ struct tcf_walker { int register_tcf_proto_ops(struct tcf_proto_ops *ops); int unregister_tcf_proto_ops(struct tcf_proto_ops *ops); +bool tcf_queue_work(struct work_struct *work); + #ifdef CONFIG_NET_CLS struct tcf_chain *tcf_chain_get(struct tcf_block *block, u32 chain_index, bool create); diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h index 135f5a2dd931..0dec8a23be57 100644 --- a/include/net/sch_generic.h +++ b/include/net/sch_generic.h @@ -10,6 +10,7 @@ #include <linux/dynamic_queue_limits.h> #include <linux/list.h> #include <linux/refcount.h> +#include <linux/workqueue.h> #include <net/gen_stats.h> #include <net/rtnetlink.h> @@ -271,6 +272,7 @@ struct tcf_chain { struct tcf_block { struct list_head chain_list; + struct work_struct work; }; static inline void qdisc_cb_private_validate(const struct sk_buff *skb, int sz) diff --git a/include/net/sctp/sm.h b/include/net/sctp/sm.h index 2db3d3a9ce1d..88233cf8b8d4 100644 --- a/include/net/sctp/sm.h +++ b/include/net/sctp/sm.h @@ -261,7 +261,7 @@ struct sctp_chunk *sctp_make_fwdtsn(const struct sctp_association *asoc, struct sctp_fwdtsn_skip *skiplist); struct sctp_chunk *sctp_make_auth(const struct sctp_association *asoc); struct sctp_chunk *sctp_make_strreset_req(const struct sctp_association *asoc, - __u16 stream_num, __u16 *stream_list, + __u16 stream_num, __be16 *stream_list, bool out, bool in); struct sctp_chunk *sctp_make_strreset_tsnreq( const struct sctp_association *asoc); diff --git a/include/net/sctp/ulpevent.h b/include/net/sctp/ulpevent.h index b8c86ec1a8f5..231dc42f1da6 100644 --- a/include/net/sctp/ulpevent.h +++ b/include/net/sctp/ulpevent.h @@ -130,7 +130,7 @@ struct sctp_ulpevent *sctp_ulpevent_make_sender_dry_event( struct sctp_ulpevent *sctp_ulpevent_make_stream_reset_event( const struct sctp_association *asoc, __u16 flags, - __u16 stream_num, __u16 *stream_list, gfp_t gfp); + __u16 stream_num, __be16 *stream_list, gfp_t gfp); struct sctp_ulpevent *sctp_ulpevent_make_assoc_reset_event( const struct sctp_association *asoc, __u16 flags, diff --git a/include/net/strparser.h b/include/net/strparser.h index 7dc131d62ad5..d96b59f45eba 100644 --- a/include/net/strparser.h +++ b/include/net/strparser.h @@ -74,10 +74,9 @@ struct strparser { u32 unrecov_intr : 1; struct sk_buff **skb_nextp; - struct timer_list msg_timer; struct sk_buff *skb_head; unsigned int need_bytes; - struct delayed_work delayed_work; + struct delayed_work msg_timer_work; struct work_struct work; struct strp_stats stats; struct strp_callbacks cb; diff --git a/include/net/tcp.h b/include/net/tcp.h index 89974c5286d8..e6d0002a1b0b 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -840,6 +840,12 @@ struct tcp_skb_cb { struct inet6_skb_parm h6; #endif } header; /* For incoming skbs */ + struct { + __u32 key; + __u32 flags; + struct bpf_map *map; + void *data_end; + } bpf; }; }; @@ -1765,12 +1771,12 @@ static inline void tcp_highest_sack_reset(struct sock *sk) tcp_sk(sk)->highest_sack = tcp_write_queue_head(sk); } -/* Called when old skb is about to be deleted (to be combined with new skb) */ -static inline void tcp_highest_sack_combine(struct sock *sk, +/* Called when old skb is about to be deleted and replaced by new skb */ +static inline void tcp_highest_sack_replace(struct sock *sk, struct sk_buff *old, struct sk_buff *new) { - if (tcp_sk(sk)->sacked_out && (old == tcp_sk(sk)->highest_sack)) + if (old == tcp_highest_sack(sk)) tcp_sk(sk)->highest_sack = new; } diff --git a/include/sound/control.h b/include/sound/control.h index bd7246de58e7..a1f1152bc687 100644 --- a/include/sound/control.h +++ b/include/sound/control.h @@ -248,6 +248,9 @@ int snd_ctl_add_vmaster_hook(struct snd_kcontrol *kctl, void *private_data); void snd_ctl_sync_vmaster(struct snd_kcontrol *kctl, bool hook_only); #define snd_ctl_sync_vmaster_hook(kctl) snd_ctl_sync_vmaster(kctl, true) +int snd_ctl_apply_vmaster_slaves(struct snd_kcontrol *kctl, + int (*func)(struct snd_kcontrol *, void *), + void *arg); /* * Helper functions for jack-detection controls diff --git a/include/sound/seq_virmidi.h b/include/sound/seq_virmidi.h index a03acd0d398a..695257ae64ac 100644 --- a/include/sound/seq_virmidi.h +++ b/include/sound/seq_virmidi.h @@ -60,6 +60,7 @@ struct snd_virmidi_dev { int port; /* created/attached port */ unsigned int flags; /* SNDRV_VIRMIDI_* */ rwlock_t filelist_lock; + struct rw_semaphore filelist_sem; struct list_head filelist; }; diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index f90860d1f897..7bf4c750dd3a 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -575,7 +575,7 @@ union bpf_attr { * @map: pointer to sockmap * @key: key to lookup sock in map * @flags: reserved for future use - * Return: SK_REDIRECT + * Return: SK_PASS * * int bpf_sock_map_update(skops, map, key, flags) * @skops: pointer to bpf_sock_ops @@ -786,9 +786,8 @@ struct xdp_md { }; enum sk_action { - SK_ABORTED = 0, - SK_DROP, - SK_REDIRECT, + SK_DROP = 0, + SK_PASS, }; #define BPF_TAG_SIZE 8 diff --git a/include/uapi/linux/membarrier.h b/include/uapi/linux/membarrier.h index 6d47b3249d8a..4e01ad7ffe98 100644 --- a/include/uapi/linux/membarrier.h +++ b/include/uapi/linux/membarrier.h @@ -52,21 +52,30 @@ * (non-running threads are de facto in such a * state). This only covers threads from the * same processes as the caller thread. This - * command returns 0. The "expedited" commands - * complete faster than the non-expedited ones, - * they never block, but have the downside of - * causing extra overhead. + * command returns 0 on success. The + * "expedited" commands complete faster than + * the non-expedited ones, they never block, + * but have the downside of causing extra + * overhead. A process needs to register its + * intent to use the private expedited command + * prior to using it, otherwise this command + * returns -EPERM. + * @MEMBARRIER_CMD_REGISTER_PRIVATE_EXPEDITED: + * Register the process intent to use + * MEMBARRIER_CMD_PRIVATE_EXPEDITED. Always + * returns 0. * * Command to be passed to the membarrier system call. The commands need to * be a single bit each, except for MEMBARRIER_CMD_QUERY which is assigned to * the value 0. */ enum membarrier_cmd { - MEMBARRIER_CMD_QUERY = 0, - MEMBARRIER_CMD_SHARED = (1 << 0), + MEMBARRIER_CMD_QUERY = 0, + MEMBARRIER_CMD_SHARED = (1 << 0), /* reserved for MEMBARRIER_CMD_SHARED_EXPEDITED (1 << 1) */ /* reserved for MEMBARRIER_CMD_PRIVATE (1 << 2) */ - MEMBARRIER_CMD_PRIVATE_EXPEDITED = (1 << 3), + MEMBARRIER_CMD_PRIVATE_EXPEDITED = (1 << 3), + MEMBARRIER_CMD_REGISTER_PRIVATE_EXPEDITED = (1 << 4), }; #endif /* _UAPI_LINUX_MEMBARRIER_H */ diff --git a/include/uapi/linux/sctp.h b/include/uapi/linux/sctp.h index 6217ff8500a1..84fc2914b7fb 100644 --- a/include/uapi/linux/sctp.h +++ b/include/uapi/linux/sctp.h @@ -376,7 +376,7 @@ struct sctp_remote_error { __u16 sre_type; __u16 sre_flags; __u32 sre_length; - __u16 sre_error; + __be16 sre_error; sctp_assoc_t sre_assoc_id; __u8 sre_data[0]; }; diff --git a/include/uapi/linux/spi/spidev.h b/include/uapi/linux/spi/spidev.h index dd5f21e75805..856de39d0b89 100644 --- a/include/uapi/linux/spi/spidev.h +++ b/include/uapi/linux/spi/spidev.h @@ -23,6 +23,7 @@ #define SPIDEV_H #include <linux/types.h> +#include <linux/ioctl.h> /* User space versions of kernel symbols for SPI clocking modes, * matching <linux/spi/spi.h> diff --git a/init/Kconfig b/init/Kconfig index 78cb2461012e..3c1faaa2af4a 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -1033,7 +1033,7 @@ endif choice prompt "Compiler optimization level" - default CONFIG_CC_OPTIMIZE_FOR_PERFORMANCE + default CC_OPTIMIZE_FOR_PERFORMANCE config CC_OPTIMIZE_FOR_PERFORMANCE bool "Optimize for performance" diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c index 98c0f00c3f5e..e2636737b69b 100644 --- a/kernel/bpf/arraymap.c +++ b/kernel/bpf/arraymap.c @@ -98,7 +98,7 @@ static struct bpf_map *array_map_alloc(union bpf_attr *attr) array_size += (u64) attr->max_entries * elem_size * num_possible_cpus(); if (array_size >= U32_MAX - PAGE_SIZE || - elem_size > PCPU_MIN_UNIT_SIZE || bpf_array_alloc_percpu(array)) { + bpf_array_alloc_percpu(array)) { bpf_map_area_free(array); return ERR_PTR(-ENOMEM); } diff --git a/kernel/bpf/devmap.c b/kernel/bpf/devmap.c index e093d9a2c4dd..e745d6a88224 100644 --- a/kernel/bpf/devmap.c +++ b/kernel/bpf/devmap.c @@ -69,7 +69,7 @@ static LIST_HEAD(dev_map_list); static u64 dev_map_bitmap_size(const union bpf_attr *attr) { - return BITS_TO_LONGS(attr->max_entries) * sizeof(unsigned long); + return BITS_TO_LONGS((u64) attr->max_entries) * sizeof(unsigned long); } static struct bpf_map *dev_map_alloc(union bpf_attr *attr) @@ -78,6 +78,9 @@ static struct bpf_map *dev_map_alloc(union bpf_attr *attr) int err = -EINVAL; u64 cost; + if (!capable(CAP_NET_ADMIN)) + return ERR_PTR(-EPERM); + /* check sanity of attributes */ if (attr->max_entries == 0 || attr->key_size != 4 || attr->value_size != 4 || attr->map_flags & ~BPF_F_NUMA_NODE) @@ -111,8 +114,9 @@ static struct bpf_map *dev_map_alloc(union bpf_attr *attr) err = -ENOMEM; /* A per cpu bitfield with a bit per possible net device */ - dtab->flush_needed = __alloc_percpu(dev_map_bitmap_size(attr), - __alignof__(unsigned long)); + dtab->flush_needed = __alloc_percpu_gfp(dev_map_bitmap_size(attr), + __alignof__(unsigned long), + GFP_KERNEL | __GFP_NOWARN); if (!dtab->flush_needed) goto free_dtab; diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c index 431126f31ea3..6533f08d1238 100644 --- a/kernel/bpf/hashtab.c +++ b/kernel/bpf/hashtab.c @@ -317,10 +317,6 @@ static struct bpf_map *htab_map_alloc(union bpf_attr *attr) */ goto free_htab; - if (percpu && round_up(htab->map.value_size, 8) > PCPU_MIN_UNIT_SIZE) - /* make sure the size for pcpu_alloc() is reasonable */ - goto free_htab; - htab->elem_size = sizeof(struct htab_elem) + round_up(htab->map.key_size, 8); if (percpu) diff --git a/kernel/bpf/sockmap.c b/kernel/bpf/sockmap.c index 6424ce0e4969..dbd7b322a86b 100644 --- a/kernel/bpf/sockmap.c +++ b/kernel/bpf/sockmap.c @@ -39,6 +39,7 @@ #include <linux/workqueue.h> #include <linux/list.h> #include <net/strparser.h> +#include <net/tcp.h> struct bpf_stab { struct bpf_map map; @@ -92,21 +93,45 @@ static inline struct smap_psock *smap_psock_sk(const struct sock *sk) return rcu_dereference_sk_user_data(sk); } +/* compute the linear packet data range [data, data_end) for skb when + * sk_skb type programs are in use. + */ +static inline void bpf_compute_data_end_sk_skb(struct sk_buff *skb) +{ + TCP_SKB_CB(skb)->bpf.data_end = skb->data + skb_headlen(skb); +} + +enum __sk_action { + __SK_DROP = 0, + __SK_PASS, + __SK_REDIRECT, +}; + static int smap_verdict_func(struct smap_psock *psock, struct sk_buff *skb) { struct bpf_prog *prog = READ_ONCE(psock->bpf_verdict); int rc; if (unlikely(!prog)) - return SK_DROP; + return __SK_DROP; skb_orphan(skb); + /* We need to ensure that BPF metadata for maps is also cleared + * when we orphan the skb so that we don't have the possibility + * to reference a stale map. + */ + TCP_SKB_CB(skb)->bpf.map = NULL; skb->sk = psock->sock; - bpf_compute_data_end(skb); + bpf_compute_data_end_sk_skb(skb); + preempt_disable(); rc = (*prog->bpf_func)(skb, prog->insnsi); + preempt_enable(); skb->sk = NULL; - return rc; + /* Moving return codes from UAPI namespace into internal namespace */ + return rc == SK_PASS ? + (TCP_SKB_CB(skb)->bpf.map ? __SK_REDIRECT : __SK_PASS) : + __SK_DROP; } static void smap_do_verdict(struct smap_psock *psock, struct sk_buff *skb) @@ -114,17 +139,10 @@ static void smap_do_verdict(struct smap_psock *psock, struct sk_buff *skb) struct sock *sk; int rc; - /* Because we use per cpu values to feed input from sock redirect - * in BPF program to do_sk_redirect_map() call we need to ensure we - * are not preempted. RCU read lock is not sufficient in this case - * with CONFIG_PREEMPT_RCU enabled so we must be explicit here. - */ - preempt_disable(); rc = smap_verdict_func(psock, skb); switch (rc) { - case SK_REDIRECT: - sk = do_sk_redirect_map(); - preempt_enable(); + case __SK_REDIRECT: + sk = do_sk_redirect_map(skb); if (likely(sk)) { struct smap_psock *peer = smap_psock_sk(sk); @@ -139,10 +157,8 @@ static void smap_do_verdict(struct smap_psock *psock, struct sk_buff *skb) } } /* Fall through and free skb otherwise */ - case SK_DROP: + case __SK_DROP: default: - if (rc != SK_REDIRECT) - preempt_enable(); kfree_skb(skb); } } @@ -369,7 +385,7 @@ static int smap_parse_func_strparser(struct strparser *strp, * any socket yet. */ skb->sk = psock->sock; - bpf_compute_data_end(skb); + bpf_compute_data_end_sk_skb(skb); rc = (*prog->bpf_func)(skb, prog->insnsi); skb->sk = NULL; rcu_read_unlock(); @@ -487,6 +503,9 @@ static struct bpf_map *sock_map_alloc(union bpf_attr *attr) int err = -EINVAL; u64 cost; + if (!capable(CAP_NET_ADMIN)) + return ERR_PTR(-EPERM); + /* check sanity of attributes */ if (attr->max_entries == 0 || attr->key_size != 4 || attr->value_size != 4 || attr->map_flags & ~BPF_F_NUMA_NODE) @@ -840,6 +859,12 @@ static int sock_map_update_elem(struct bpf_map *map, return -EINVAL; } + if (skops.sk->sk_type != SOCK_STREAM || + skops.sk->sk_protocol != IPPROTO_TCP) { + fput(socket->file); + return -EOPNOTSUPP; + } + err = sock_map_ctx_update_elem(&skops, map, key, flags); fput(socket->file); return err; diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 20f3889c006e..c48ca2a34b5e 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -2430,12 +2430,15 @@ static int check_alu_op(struct bpf_verifier_env *env, struct bpf_insn *insn) } static void find_good_pkt_pointers(struct bpf_verifier_state *state, - struct bpf_reg_state *dst_reg) + struct bpf_reg_state *dst_reg, + bool range_right_open) { struct bpf_reg_state *regs = state->regs, *reg; + u16 new_range; int i; - if (dst_reg->off < 0) + if (dst_reg->off < 0 || + (dst_reg->off == 0 && range_right_open)) /* This doesn't give us any range */ return; @@ -2446,9 +2449,13 @@ static void find_good_pkt_pointers(struct bpf_verifier_state *state, */ return; - /* LLVM can generate four kind of checks: + new_range = dst_reg->off; + if (range_right_open) + new_range--; + + /* Examples for register markings: * - * Type 1/2: + * pkt_data in dst register: * * r2 = r3; * r2 += 8; @@ -2465,7 +2472,7 @@ static void find_good_pkt_pointers(struct bpf_verifier_state *state, * r2=pkt(id=n,off=8,r=0) * r3=pkt(id=n,off=0,r=0) * - * Type 3/4: + * pkt_data in src register: * * r2 = r3; * r2 += 8; @@ -2483,7 +2490,9 @@ static void find_good_pkt_pointers(struct bpf_verifier_state *state, * r3=pkt(id=n,off=0,r=0) * * Find register r3 and mark its range as r3=pkt(id=n,off=0,r=8) - * so that range of bytes [r3, r3 + 8) is safe to access. + * or r3=pkt(id=n,off=0,r=8-1), so that range of bytes [r3, r3 + 8) + * and [r3, r3 + 8-1) respectively is safe to access depending on + * the check. */ /* If our ids match, then we must have the same max_value. And we @@ -2494,14 +2503,14 @@ static void find_good_pkt_pointers(struct bpf_verifier_state *state, for (i = 0; i < MAX_BPF_REG; i++) if (regs[i].type == PTR_TO_PACKET && regs[i].id == dst_reg->id) /* keep the maximum range already checked */ - regs[i].range = max_t(u16, regs[i].range, dst_reg->off); + regs[i].range = max(regs[i].range, new_range); for (i = 0; i < MAX_BPF_STACK; i += BPF_REG_SIZE) { if (state->stack_slot_type[i] != STACK_SPILL) continue; reg = &state->spilled_regs[i / BPF_REG_SIZE]; if (reg->type == PTR_TO_PACKET && reg->id == dst_reg->id) - reg->range = max_t(u16, reg->range, dst_reg->off); + reg->range = max(reg->range, new_range); } } @@ -2865,19 +2874,43 @@ static int check_cond_jmp_op(struct bpf_verifier_env *env, } else if (BPF_SRC(insn->code) == BPF_X && opcode == BPF_JGT && dst_reg->type == PTR_TO_PACKET && regs[insn->src_reg].type == PTR_TO_PACKET_END) { - find_good_pkt_pointers(this_branch, dst_reg); + /* pkt_data' > pkt_end */ + find_good_pkt_pointers(this_branch, dst_reg, false); + } else if (BPF_SRC(insn->code) == BPF_X && opcode == BPF_JGT && + dst_reg->type == PTR_TO_PACKET_END && + regs[insn->src_reg].type == PTR_TO_PACKET) { + /* pkt_end > pkt_data' */ + find_good_pkt_pointers(other_branch, ®s[insn->src_reg], true); } else if (BPF_SRC(insn->code) == BPF_X && opcode == BPF_JLT && dst_reg->type == PTR_TO_PACKET && regs[insn->src_reg].type == PTR_TO_PACKET_END) { - find_good_pkt_pointers(other_branch, dst_reg); + /* pkt_data' < pkt_end */ + find_good_pkt_pointers(other_branch, dst_reg, true); + } else if (BPF_SRC(insn->code) == BPF_X && opcode == BPF_JLT && + dst_reg->type == PTR_TO_PACKET_END && + regs[insn->src_reg].type == PTR_TO_PACKET) { + /* pkt_end < pkt_data' */ + find_good_pkt_pointers(this_branch, ®s[insn->src_reg], false); + } else if (BPF_SRC(insn->code) == BPF_X && opcode == BPF_JGE && + dst_reg->type == PTR_TO_PACKET && + regs[insn->src_reg].type == PTR_TO_PACKET_END) { + /* pkt_data' >= pkt_end */ + find_good_pkt_pointers(this_branch, dst_reg, true); } else if (BPF_SRC(insn->code) == BPF_X && opcode == BPF_JGE && dst_reg->type == PTR_TO_PACKET_END && regs[insn->src_reg].type == PTR_TO_PACKET) { - find_good_pkt_pointers(other_branch, ®s[insn->src_reg]); + /* pkt_end >= pkt_data' */ + find_good_pkt_pointers(other_branch, ®s[insn->src_reg], false); + } else if (BPF_SRC(insn->code) == BPF_X && opcode == BPF_JLE && + dst_reg->type == PTR_TO_PACKET && + regs[insn->src_reg].type == PTR_TO_PACKET_END) { + /* pkt_data' <= pkt_end */ + find_good_pkt_pointers(other_branch, dst_reg, false); } else if (BPF_SRC(insn->code) == BPF_X && opcode == BPF_JLE && dst_reg->type == PTR_TO_PACKET_END && regs[insn->src_reg].type == PTR_TO_PACKET) { - find_good_pkt_pointers(this_branch, ®s[insn->src_reg]); + /* pkt_end <= pkt_data' */ + find_good_pkt_pointers(this_branch, ®s[insn->src_reg], true); } else if (is_pointer_value(env, insn->dst_reg)) { verbose("R%d pointer comparison prohibited\n", insn->dst_reg); return -EACCES; diff --git a/kernel/cpu.c b/kernel/cpu.c index d851df22f5c5..04892a82f6ac 100644 --- a/kernel/cpu.c +++ b/kernel/cpu.c @@ -632,6 +632,11 @@ cpuhp_invoke_ap_callback(int cpu, enum cpuhp_state state, bool bringup, __cpuhp_kick_ap(st); } + /* + * Clean up the leftovers so the next hotplug operation wont use stale + * data. + */ + st->node = st->last = NULL; return ret; } diff --git a/kernel/events/core.c b/kernel/events/core.c index 6bc21e202ae4..9d93db81fa36 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -662,7 +662,7 @@ static inline void update_cgrp_time_from_event(struct perf_event *event) /* * Do not update time when cgroup is not active */ - if (cgrp == event->cgrp) + if (cgroup_is_descendant(cgrp->css.cgroup, event->cgrp->css.cgroup)) __update_cgrp_time(event->cgrp); } @@ -8955,6 +8955,14 @@ static struct perf_cpu_context __percpu *find_pmu_context(int ctxn) static void free_pmu_context(struct pmu *pmu) { + /* + * Static contexts such as perf_sw_context have a global lifetime + * and may be shared between different PMUs. Avoid freeing them + * when a single PMU is going away. + */ + if (pmu->task_ctx_nr > perf_invalid_context) + return; + mutex_lock(&pmus_lock); free_percpu(pmu->pmu_cpu_context); mutex_unlock(&pmus_lock); diff --git a/kernel/exit.c b/kernel/exit.c index f2cd53e92147..f6cad39f35df 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -1610,6 +1610,9 @@ SYSCALL_DEFINE5(waitid, int, which, pid_t, upid, struct siginfo __user *, if (!infop) return err; + if (!access_ok(VERIFY_WRITE, infop, sizeof(*infop))) + return -EFAULT; + user_access_begin(); unsafe_put_user(signo, &infop->si_signo, Efault); unsafe_put_user(0, &infop->si_errno, Efault); @@ -1735,6 +1738,9 @@ COMPAT_SYSCALL_DEFINE5(waitid, if (!infop) return err; + if (!access_ok(VERIFY_WRITE, infop, sizeof(*infop))) + return -EFAULT; + user_access_begin(); unsafe_put_user(signo, &infop->si_signo, Efault); unsafe_put_user(0, &infop->si_errno, Efault); diff --git a/kernel/fork.c b/kernel/fork.c index e702cb9ffbd8..07cc743698d3 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -215,6 +215,10 @@ static unsigned long *alloc_thread_stack_node(struct task_struct *tsk, int node) if (!s) continue; +#ifdef CONFIG_DEBUG_KMEMLEAK + /* Clear stale pointers from reused stack. */ + memset(s->addr, 0, THREAD_SIZE); +#endif tsk->stack_vm_area = s; return s->addr; } diff --git a/kernel/irq/chip.c b/kernel/irq/chip.c index 6fc89fd93824..5a2ef92c2782 100644 --- a/kernel/irq/chip.c +++ b/kernel/irq/chip.c @@ -265,8 +265,8 @@ int irq_startup(struct irq_desc *desc, bool resend, bool force) irq_setup_affinity(desc); break; case IRQ_STARTUP_MANAGED: + irq_do_set_affinity(d, aff, false); ret = __irq_startup(desc); - irq_set_affinity_locked(d, aff, false); break; case IRQ_STARTUP_ABORT: return 0; diff --git a/kernel/irq/cpuhotplug.c b/kernel/irq/cpuhotplug.c index 638eb9c83d9f..9eb09aef0313 100644 --- a/kernel/irq/cpuhotplug.c +++ b/kernel/irq/cpuhotplug.c @@ -18,8 +18,34 @@ static inline bool irq_needs_fixup(struct irq_data *d) { const struct cpumask *m = irq_data_get_effective_affinity_mask(d); + unsigned int cpu = smp_processor_id(); - return cpumask_test_cpu(smp_processor_id(), m); +#ifdef CONFIG_GENERIC_IRQ_EFFECTIVE_AFF_MASK + /* + * The cpumask_empty() check is a workaround for interrupt chips, + * which do not implement effective affinity, but the architecture has + * enabled the config switch. Use the general affinity mask instead. + */ + if (cpumask_empty(m)) + m = irq_data_get_affinity_mask(d); + + /* + * Sanity check. If the mask is not empty when excluding the outgoing + * CPU then it must contain at least one online CPU. The outgoing CPU + * has been removed from the online mask already. + */ + if (cpumask_any_but(m, cpu) < nr_cpu_ids && + cpumask_any_and(m, cpu_online_mask) >= nr_cpu_ids) { + /* + * If this happens then there was a missed IRQ fixup at some + * point. Warn about it and enforce fixup. + */ + pr_warn("Eff. affinity %*pbl of IRQ %u contains only offline CPUs after offlining CPU %u\n", + cpumask_pr_args(m), d->irq, cpu); + return true; + } +#endif + return cpumask_test_cpu(cpu, m); } static bool migrate_one_irq(struct irq_desc *desc) diff --git a/kernel/irq/generic-chip.c b/kernel/irq/generic-chip.c index 5270a54b9fa4..c26c5bb6b491 100644 --- a/kernel/irq/generic-chip.c +++ b/kernel/irq/generic-chip.c @@ -135,17 +135,26 @@ void irq_gc_ack_clr_bit(struct irq_data *d) } /** - * irq_gc_mask_disable_reg_and_ack - Mask and ack pending interrupt + * irq_gc_mask_disable_and_ack_set - Mask and ack pending interrupt * @d: irq_data + * + * This generic implementation of the irq_mask_ack method is for chips + * with separate enable/disable registers instead of a single mask + * register and where a pending interrupt is acknowledged by setting a + * bit. + * + * Note: This is the only permutation currently used. Similar generic + * functions should be added here if other permutations are required. */ -void irq_gc_mask_disable_reg_and_ack(struct irq_data *d) +void irq_gc_mask_disable_and_ack_set(struct irq_data *d) { struct irq_chip_generic *gc = irq_data_get_irq_chip_data(d); struct irq_chip_type *ct = irq_data_get_chip_type(d); u32 mask = d->mask; irq_gc_lock(gc); - irq_reg_writel(gc, mask, ct->regs.mask); + irq_reg_writel(gc, mask, ct->regs.disable); + *ct->mask_cache &= ~mask; irq_reg_writel(gc, mask, ct->regs.ack); irq_gc_unlock(gc); } diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c index d00132b5c325..4bff6a10ae8e 100644 --- a/kernel/irq/manage.c +++ b/kernel/irq/manage.c @@ -168,6 +168,19 @@ void irq_set_thread_affinity(struct irq_desc *desc) set_bit(IRQTF_AFFINITY, &action->thread_flags); } +static void irq_validate_effective_affinity(struct irq_data *data) +{ +#ifdef CONFIG_GENERIC_IRQ_EFFECTIVE_AFF_MASK + const struct cpumask *m = irq_data_get_effective_affinity_mask(data); + struct irq_chip *chip = irq_data_get_irq_chip(data); + + if (!cpumask_empty(m)) + return; + pr_warn_once("irq_chip %s did not update eff. affinity mask of irq %u\n", + chip->name, data->irq); +#endif +} + int irq_do_set_affinity(struct irq_data *data, const struct cpumask *mask, bool force) { @@ -175,12 +188,16 @@ int irq_do_set_affinity(struct irq_data *data, const struct cpumask *mask, struct irq_chip *chip = irq_data_get_irq_chip(data); int ret; + if (!chip || !chip->irq_set_affinity) + return -EINVAL; + ret = chip->irq_set_affinity(data, mask, force); switch (ret) { case IRQ_SET_MASK_OK: case IRQ_SET_MASK_OK_DONE: cpumask_copy(desc->irq_common_data.affinity, mask); case IRQ_SET_MASK_OK_NOCOPY: + irq_validate_effective_affinity(data); irq_set_thread_affinity(desc); ret = 0; } diff --git a/kernel/livepatch/core.c b/kernel/livepatch/core.c index b9628e43c78f..bf8c8fd72589 100644 --- a/kernel/livepatch/core.c +++ b/kernel/livepatch/core.c @@ -830,6 +830,41 @@ int klp_register_patch(struct klp_patch *patch) } EXPORT_SYMBOL_GPL(klp_register_patch); +/* + * Remove parts of patches that touch a given kernel module. The list of + * patches processed might be limited. When limit is NULL, all patches + * will be handled. + */ +static void klp_cleanup_module_patches_limited(struct module *mod, + struct klp_patch *limit) +{ + struct klp_patch *patch; + struct klp_object *obj; + + list_for_each_entry(patch, &klp_patches, list) { + if (patch == limit) + break; + + klp_for_each_object(patch, obj) { + if (!klp_is_module(obj) || strcmp(obj->name, mod->name)) + continue; + + /* + * Only unpatch the module if the patch is enabled or + * is in transition. + */ + if (patch->enabled || patch == klp_transition_patch) { + pr_notice("reverting patch '%s' on unloading module '%s'\n", + patch->mod->name, obj->mod->name); + klp_unpatch_object(obj); + } + + klp_free_object_loaded(obj); + break; + } + } +} + int klp_module_coming(struct module *mod) { int ret; @@ -894,7 +929,7 @@ err: pr_warn("patch '%s' failed for module '%s', refusing to load module '%s'\n", patch->mod->name, obj->mod->name, obj->mod->name); mod->klp_alive = false; - klp_free_object_loaded(obj); + klp_cleanup_module_patches_limited(mod, patch); mutex_unlock(&klp_mutex); return ret; @@ -902,9 +937,6 @@ err: void klp_module_going(struct module *mod) { - struct klp_patch *patch; - struct klp_object *obj; - if (WARN_ON(mod->state != MODULE_STATE_GOING && mod->state != MODULE_STATE_COMING)) return; @@ -917,25 +949,7 @@ void klp_module_going(struct module *mod) */ mod->klp_alive = false; - list_for_each_entry(patch, &klp_patches, list) { - klp_for_each_object(patch, obj) { - if (!klp_is_module(obj) || strcmp(obj->name, mod->name)) - continue; - - /* - * Only unpatch the module if the patch is enabled or - * is in transition. - */ - if (patch->enabled || patch == klp_transition_patch) { - pr_notice("reverting patch '%s' on unloading module '%s'\n", - patch->mod->name, obj->mod->name); - klp_unpatch_object(obj); - } - - klp_free_object_loaded(obj); - break; - } - } + klp_cleanup_module_patches_limited(mod, NULL); mutex_unlock(&klp_mutex); } diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c index 44c8d0d17170..e36e652d996f 100644 --- a/kernel/locking/lockdep.c +++ b/kernel/locking/lockdep.c @@ -1873,10 +1873,10 @@ check_prev_add(struct task_struct *curr, struct held_lock *prev, struct held_lock *next, int distance, struct stack_trace *trace, int (*save)(struct stack_trace *trace)) { + struct lock_list *uninitialized_var(target_entry); struct lock_list *entry; - int ret; struct lock_list this; - struct lock_list *uninitialized_var(target_entry); + int ret; /* * Prove that the new <prev> -> <next> dependency would not @@ -1890,8 +1890,17 @@ check_prev_add(struct task_struct *curr, struct held_lock *prev, this.class = hlock_class(next); this.parent = NULL; ret = check_noncircular(&this, hlock_class(prev), &target_entry); - if (unlikely(!ret)) + if (unlikely(!ret)) { + if (!trace->entries) { + /* + * If @save fails here, the printing might trigger + * a WARN but because of the !nr_entries it should + * not do bad things. + */ + save(trace); + } return print_circular_bug(&this, target_entry, next, prev, trace); + } else if (unlikely(ret < 0)) return print_bfs_bug(ret); @@ -1938,7 +1947,7 @@ check_prev_add(struct task_struct *curr, struct held_lock *prev, return print_bfs_bug(ret); - if (save && !save(trace)) + if (!trace->entries && !save(trace)) return 0; /* @@ -1958,20 +1967,6 @@ check_prev_add(struct task_struct *curr, struct held_lock *prev, if (!ret) return 0; - /* - * Debugging printouts: - */ - if (verbose(hlock_class(prev)) || verbose(hlock_class(next))) { - graph_unlock(); - printk("\n new dependency: "); - print_lock_name(hlock_class(prev)); - printk(KERN_CONT " => "); - print_lock_name(hlock_class(next)); - printk(KERN_CONT "\n"); - dump_stack(); - if (!graph_lock()) - return 0; - } return 2; } @@ -1986,8 +1981,12 @@ check_prevs_add(struct task_struct *curr, struct held_lock *next) { int depth = curr->lockdep_depth; struct held_lock *hlock; - struct stack_trace trace; - int (*save)(struct stack_trace *trace) = save_trace; + struct stack_trace trace = { + .nr_entries = 0, + .max_entries = 0, + .entries = NULL, + .skip = 0, + }; /* * Debugging checks. @@ -2018,18 +2017,11 @@ check_prevs_add(struct task_struct *curr, struct held_lock *next) */ if (hlock->read != 2 && hlock->check) { int ret = check_prev_add(curr, hlock, next, - distance, &trace, save); + distance, &trace, save_trace); if (!ret) return 0; /* - * Stop saving stack_trace if save_trace() was - * called at least once: - */ - if (save && ret == 2) - save = NULL; - - /* * Stop after the first non-trylock entry, * as non-trylock entries have added their * own direct dependencies already, so this diff --git a/kernel/rcu/srcutree.c b/kernel/rcu/srcutree.c index 729a8706751d..6d5880089ff6 100644 --- a/kernel/rcu/srcutree.c +++ b/kernel/rcu/srcutree.c @@ -854,7 +854,7 @@ void __call_srcu(struct srcu_struct *sp, struct rcu_head *rhp, /** * call_srcu() - Queue a callback for invocation after an SRCU grace period * @sp: srcu_struct in queue the callback - * @head: structure to be used for queueing the SRCU callback. + * @rhp: structure to be used for queueing the SRCU callback. * @func: function to be invoked after the SRCU grace period * * The callback function will be invoked some time after a full SRCU diff --git a/kernel/rcu/sync.c b/kernel/rcu/sync.c index 50d1861f7759..3f943efcf61c 100644 --- a/kernel/rcu/sync.c +++ b/kernel/rcu/sync.c @@ -85,6 +85,9 @@ void rcu_sync_init(struct rcu_sync *rsp, enum rcu_sync_type type) } /** + * rcu_sync_enter_start - Force readers onto slow path for multiple updates + * @rsp: Pointer to rcu_sync structure to use for synchronization + * * Must be called after rcu_sync_init() and before first use. * * Ensures rcu_sync_is_idle() returns false and rcu_sync_{enter,exit}() @@ -142,7 +145,7 @@ void rcu_sync_enter(struct rcu_sync *rsp) /** * rcu_sync_func() - Callback function managing reader access to fastpath - * @rsp: Pointer to rcu_sync structure to use for synchronization + * @rhp: Pointer to rcu_head in rcu_sync structure to use for synchronization * * This function is passed to one of the call_rcu() functions by * rcu_sync_exit(), so that it is invoked after a grace period following the @@ -158,9 +161,9 @@ void rcu_sync_enter(struct rcu_sync *rsp) * rcu_sync_exit(). Otherwise, set all state back to idle so that readers * can again use their fastpaths. */ -static void rcu_sync_func(struct rcu_head *rcu) +static void rcu_sync_func(struct rcu_head *rhp) { - struct rcu_sync *rsp = container_of(rcu, struct rcu_sync, cb_head); + struct rcu_sync *rsp = container_of(rhp, struct rcu_sync, cb_head); unsigned long flags; BUG_ON(rsp->gp_state != GP_PASSED); diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c index b0ad62b0e7b8..3e3650e94ae6 100644 --- a/kernel/rcu/tree.c +++ b/kernel/rcu/tree.c @@ -3097,9 +3097,10 @@ __call_rcu(struct rcu_head *head, rcu_callback_t func, * read-side critical sections have completed. call_rcu_sched() assumes * that the read-side critical sections end on enabling of preemption * or on voluntary preemption. - * RCU read-side critical sections are delimited by : - * - rcu_read_lock_sched() and rcu_read_unlock_sched(), OR - * - anything that disables preemption. + * RCU read-side critical sections are delimited by: + * + * - rcu_read_lock_sched() and rcu_read_unlock_sched(), OR + * - anything that disables preemption. * * These may be nested. * @@ -3124,11 +3125,12 @@ EXPORT_SYMBOL_GPL(call_rcu_sched); * handler. This means that read-side critical sections in process * context must not be interrupted by softirqs. This interface is to be * used when most of the read-side critical sections are in softirq context. - * RCU read-side critical sections are delimited by : - * - rcu_read_lock() and rcu_read_unlock(), if in interrupt context. - * OR - * - rcu_read_lock_bh() and rcu_read_unlock_bh(), if in process context. - * These may be nested. + * RCU read-side critical sections are delimited by: + * + * - rcu_read_lock() and rcu_read_unlock(), if in interrupt context, OR + * - rcu_read_lock_bh() and rcu_read_unlock_bh(), if in process context. + * + * These may be nested. * * See the description of call_rcu() for more detailed information on * memory ordering guarantees. diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 70ba32e08a23..d3f3094856fe 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -5356,91 +5356,62 @@ static int wake_wide(struct task_struct *p) return 1; } -struct llc_stats { - unsigned long nr_running; - unsigned long load; - unsigned long capacity; - int has_capacity; -}; +/* + * The purpose of wake_affine() is to quickly determine on which CPU we can run + * soonest. For the purpose of speed we only consider the waking and previous + * CPU. + * + * wake_affine_idle() - only considers 'now', it check if the waking CPU is (or + * will be) idle. + * + * wake_affine_weight() - considers the weight to reflect the average + * scheduling latency of the CPUs. This seems to work + * for the overloaded case. + */ -static bool get_llc_stats(struct llc_stats *stats, int cpu) +static bool +wake_affine_idle(struct sched_domain *sd, struct task_struct *p, + int this_cpu, int prev_cpu, int sync) { - struct sched_domain_shared *sds = rcu_dereference(per_cpu(sd_llc_shared, cpu)); - - if (!sds) - return false; + if (idle_cpu(this_cpu)) + return true; - stats->nr_running = READ_ONCE(sds->nr_running); - stats->load = READ_ONCE(sds->load); - stats->capacity = READ_ONCE(sds->capacity); - stats->has_capacity = stats->nr_running < per_cpu(sd_llc_size, cpu); + if (sync && cpu_rq(this_cpu)->nr_running == 1) + return true; - return true; + return false; } -/* - * Can a task be moved from prev_cpu to this_cpu without causing a load - * imbalance that would trigger the load balancer? - * - * Since we're running on 'stale' values, we might in fact create an imbalance - * but recomputing these values is expensive, as that'd mean iteration 2 cache - * domains worth of CPUs. - */ static bool -wake_affine_llc(struct sched_domain *sd, struct task_struct *p, - int this_cpu, int prev_cpu, int sync) +wake_affine_weight(struct sched_domain *sd, struct task_struct *p, + int this_cpu, int prev_cpu, int sync) { - struct llc_stats prev_stats, this_stats; s64 this_eff_load, prev_eff_load; unsigned long task_load; - if (!get_llc_stats(&prev_stats, prev_cpu) || - !get_llc_stats(&this_stats, this_cpu)) - return false; + this_eff_load = target_load(this_cpu, sd->wake_idx); + prev_eff_load = source_load(prev_cpu, sd->wake_idx); - /* - * If sync wakeup then subtract the (maximum possible) - * effect of the currently running task from the load - * of the current LLC. - */ if (sync) { unsigned long current_load = task_h_load(current); - /* in this case load hits 0 and this LLC is considered 'idle' */ - if (current_load > this_stats.load) + if (current_load > this_eff_load) return true; - this_stats.load -= current_load; + this_eff_load -= current_load; } - /* - * The has_capacity stuff is not SMT aware, but by trying to balance - * the nr_running on both ends we try and fill the domain at equal - * rates, thereby first consuming cores before siblings. - */ - - /* if the old cache has capacity, stay there */ - if (prev_stats.has_capacity && prev_stats.nr_running < this_stats.nr_running+1) - return false; - - /* if this cache has capacity, come here */ - if (this_stats.has_capacity && this_stats.nr_running+1 < prev_stats.nr_running) - return true; - - /* - * Check to see if we can move the load without causing too much - * imbalance. - */ task_load = task_h_load(p); - this_eff_load = 100; - this_eff_load *= prev_stats.capacity; - - prev_eff_load = 100 + (sd->imbalance_pct - 100) / 2; - prev_eff_load *= this_stats.capacity; + this_eff_load += task_load; + if (sched_feat(WA_BIAS)) + this_eff_load *= 100; + this_eff_load *= capacity_of(prev_cpu); - this_eff_load *= this_stats.load + task_load; - prev_eff_load *= prev_stats.load - task_load; + prev_eff_load -= task_load; + if (sched_feat(WA_BIAS)) + prev_eff_load *= 100 + (sd->imbalance_pct - 100) / 2; + prev_eff_load *= capacity_of(this_cpu); return this_eff_load <= prev_eff_load; } @@ -5449,22 +5420,13 @@ static int wake_affine(struct sched_domain *sd, struct task_struct *p, int prev_cpu, int sync) { int this_cpu = smp_processor_id(); - bool affine; + bool affine = false; - /* - * Default to no affine wakeups; wake_affine() should not effect a task - * placement the load-balancer feels inclined to undo. The conservative - * option is therefore to not move tasks when they wake up. - */ - affine = false; + if (sched_feat(WA_IDLE) && !affine) + affine = wake_affine_idle(sd, p, this_cpu, prev_cpu, sync); - /* - * If the wakeup is across cache domains, try to evaluate if movement - * makes sense, otherwise rely on select_idle_siblings() to do - * placement inside the cache domain. - */ - if (!cpus_share_cache(prev_cpu, this_cpu)) - affine = wake_affine_llc(sd, p, this_cpu, prev_cpu, sync); + if (sched_feat(WA_WEIGHT) && !affine) + affine = wake_affine_weight(sd, p, this_cpu, prev_cpu, sync); schedstat_inc(p->se.statistics.nr_wakeups_affine_attempts); if (affine) { @@ -7600,7 +7562,6 @@ static inline enum fbq_type fbq_classify_rq(struct rq *rq) */ static inline void update_sd_lb_stats(struct lb_env *env, struct sd_lb_stats *sds) { - struct sched_domain_shared *shared = env->sd->shared; struct sched_domain *child = env->sd->child; struct sched_group *sg = env->sd->groups; struct sg_lb_stats *local = &sds->local_stat; @@ -7672,22 +7633,6 @@ next_group: if (env->dst_rq->rd->overload != overload) env->dst_rq->rd->overload = overload; } - - if (!shared) - return; - - /* - * Since these are sums over groups they can contain some CPUs - * multiple times for the NUMA domains. - * - * Currently only wake_affine_llc() and find_busiest_group() - * uses these numbers, only the last is affected by this problem. - * - * XXX fix that. - */ - WRITE_ONCE(shared->nr_running, sds->total_running); - WRITE_ONCE(shared->load, sds->total_load); - WRITE_ONCE(shared->capacity, sds->total_capacity); } /** @@ -8098,6 +8043,13 @@ static int should_we_balance(struct lb_env *env) int cpu, balance_cpu = -1; /* + * Ensure the balancing environment is consistent; can happen + * when the softirq triggers 'during' hotplug. + */ + if (!cpumask_test_cpu(env->dst_cpu, env->cpus)) + return 0; + + /* * In the newly idle case, we will allow all the cpu's * to do the newly idle load balance. */ diff --git a/kernel/sched/features.h b/kernel/sched/features.h index d3fb15555291..319ed0e8a347 100644 --- a/kernel/sched/features.h +++ b/kernel/sched/features.h @@ -81,3 +81,6 @@ SCHED_FEAT(RT_RUNTIME_SHARE, true) SCHED_FEAT(LB_MIN, false) SCHED_FEAT(ATTACH_AGE_LOAD, true) +SCHED_FEAT(WA_IDLE, true) +SCHED_FEAT(WA_WEIGHT, true) +SCHED_FEAT(WA_BIAS, true) diff --git a/kernel/sched/membarrier.c b/kernel/sched/membarrier.c index a92fddc22747..dd7908743dab 100644 --- a/kernel/sched/membarrier.c +++ b/kernel/sched/membarrier.c @@ -18,6 +18,7 @@ #include <linux/membarrier.h> #include <linux/tick.h> #include <linux/cpumask.h> +#include <linux/atomic.h> #include "sched.h" /* for cpu_rq(). */ @@ -26,21 +27,26 @@ * except MEMBARRIER_CMD_QUERY. */ #define MEMBARRIER_CMD_BITMASK \ - (MEMBARRIER_CMD_SHARED | MEMBARRIER_CMD_PRIVATE_EXPEDITED) + (MEMBARRIER_CMD_SHARED | MEMBARRIER_CMD_PRIVATE_EXPEDITED \ + | MEMBARRIER_CMD_REGISTER_PRIVATE_EXPEDITED) static void ipi_mb(void *info) { smp_mb(); /* IPIs should be serializing but paranoid. */ } -static void membarrier_private_expedited(void) +static int membarrier_private_expedited(void) { int cpu; bool fallback = false; cpumask_var_t tmpmask; + if (!(atomic_read(¤t->mm->membarrier_state) + & MEMBARRIER_STATE_PRIVATE_EXPEDITED_READY)) + return -EPERM; + if (num_online_cpus() == 1) - return; + return 0; /* * Matches memory barriers around rq->curr modification in @@ -94,6 +100,24 @@ static void membarrier_private_expedited(void) * rq->curr modification in scheduler. */ smp_mb(); /* exit from system call is not a mb */ + return 0; +} + +static void membarrier_register_private_expedited(void) +{ + struct task_struct *p = current; + struct mm_struct *mm = p->mm; + + /* + * We need to consider threads belonging to different thread + * groups, which use the same mm. (CLONE_VM but not + * CLONE_THREAD). + */ + if (atomic_read(&mm->membarrier_state) + & MEMBARRIER_STATE_PRIVATE_EXPEDITED_READY) + return; + atomic_or(MEMBARRIER_STATE_PRIVATE_EXPEDITED_READY, + &mm->membarrier_state); } /** @@ -144,7 +168,9 @@ SYSCALL_DEFINE2(membarrier, int, cmd, int, flags) synchronize_sched(); return 0; case MEMBARRIER_CMD_PRIVATE_EXPEDITED: - membarrier_private_expedited(); + return membarrier_private_expedited(); + case MEMBARRIER_CMD_REGISTER_PRIVATE_EXPEDITED: + membarrier_register_private_expedited(); return 0; default: return -EINVAL; diff --git a/kernel/seccomp.c b/kernel/seccomp.c index bb3a38005b9c..0ae832e13b97 100644 --- a/kernel/seccomp.c +++ b/kernel/seccomp.c @@ -473,7 +473,7 @@ static long seccomp_attach_filter(unsigned int flags, return 0; } -void __get_seccomp_filter(struct seccomp_filter *filter) +static void __get_seccomp_filter(struct seccomp_filter *filter) { /* Reference count is bounded by the number of total processes. */ refcount_inc(&filter->usage); diff --git a/kernel/signal.c b/kernel/signal.c index 800a18f77732..8dcd8825b2de 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -2698,7 +2698,7 @@ enum siginfo_layout siginfo_layout(int sig, int si_code) [SIGSEGV] = { NSIGSEGV, SIL_FAULT }, [SIGBUS] = { NSIGBUS, SIL_FAULT }, [SIGTRAP] = { NSIGTRAP, SIL_FAULT }, -#if defined(SIGMET) && defined(NSIGEMT) +#if defined(SIGEMT) && defined(NSIGEMT) [SIGEMT] = { NSIGEMT, SIL_FAULT }, #endif [SIGCHLD] = { NSIGCHLD, SIL_CHLD }, diff --git a/kernel/workqueue.c b/kernel/workqueue.c index 64d0edf428f8..a2dccfe1acec 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -68,6 +68,7 @@ enum { * attach_mutex to avoid changing binding state while * worker_attach_to_pool() is in progress. */ + POOL_MANAGER_ACTIVE = 1 << 0, /* being managed */ POOL_DISASSOCIATED = 1 << 2, /* cpu can't serve workers */ /* worker flags */ @@ -165,7 +166,6 @@ struct worker_pool { /* L: hash of busy workers */ /* see manage_workers() for details on the two manager mutexes */ - struct mutex manager_arb; /* manager arbitration */ struct worker *manager; /* L: purely informational */ struct mutex attach_mutex; /* attach/detach exclusion */ struct list_head workers; /* A: attached workers */ @@ -299,6 +299,7 @@ static struct workqueue_attrs *wq_update_unbound_numa_attrs_buf; static DEFINE_MUTEX(wq_pool_mutex); /* protects pools and workqueues list */ static DEFINE_SPINLOCK(wq_mayday_lock); /* protects wq->maydays list */ +static DECLARE_WAIT_QUEUE_HEAD(wq_manager_wait); /* wait for manager to go away */ static LIST_HEAD(workqueues); /* PR: list of all workqueues */ static bool workqueue_freezing; /* PL: have wqs started freezing? */ @@ -801,7 +802,7 @@ static bool need_to_create_worker(struct worker_pool *pool) /* Do we have too many workers and should some go away? */ static bool too_many_workers(struct worker_pool *pool) { - bool managing = mutex_is_locked(&pool->manager_arb); + bool managing = pool->flags & POOL_MANAGER_ACTIVE; int nr_idle = pool->nr_idle + managing; /* manager is considered idle */ int nr_busy = pool->nr_workers - nr_idle; @@ -1980,24 +1981,17 @@ static bool manage_workers(struct worker *worker) { struct worker_pool *pool = worker->pool; - /* - * Anyone who successfully grabs manager_arb wins the arbitration - * and becomes the manager. mutex_trylock() on pool->manager_arb - * failure while holding pool->lock reliably indicates that someone - * else is managing the pool and the worker which failed trylock - * can proceed to executing work items. This means that anyone - * grabbing manager_arb is responsible for actually performing - * manager duties. If manager_arb is grabbed and released without - * actual management, the pool may stall indefinitely. - */ - if (!mutex_trylock(&pool->manager_arb)) + if (pool->flags & POOL_MANAGER_ACTIVE) return false; + + pool->flags |= POOL_MANAGER_ACTIVE; pool->manager = worker; maybe_create_worker(pool); pool->manager = NULL; - mutex_unlock(&pool->manager_arb); + pool->flags &= ~POOL_MANAGER_ACTIVE; + wake_up(&wq_manager_wait); return true; } @@ -3248,7 +3242,6 @@ static int init_worker_pool(struct worker_pool *pool) setup_timer(&pool->mayday_timer, pool_mayday_timeout, (unsigned long)pool); - mutex_init(&pool->manager_arb); mutex_init(&pool->attach_mutex); INIT_LIST_HEAD(&pool->workers); @@ -3318,13 +3311,15 @@ static void put_unbound_pool(struct worker_pool *pool) hash_del(&pool->hash_node); /* - * Become the manager and destroy all workers. Grabbing - * manager_arb prevents @pool's workers from blocking on - * attach_mutex. + * Become the manager and destroy all workers. This prevents + * @pool's workers from blocking on attach_mutex. We're the last + * manager and @pool gets freed with the flag set. */ - mutex_lock(&pool->manager_arb); - spin_lock_irq(&pool->lock); + wait_event_lock_irq(wq_manager_wait, + !(pool->flags & POOL_MANAGER_ACTIVE), pool->lock); + pool->flags |= POOL_MANAGER_ACTIVE; + while ((worker = first_idle_worker(pool))) destroy_worker(worker); WARN_ON(pool->nr_workers || pool->nr_idle); @@ -3338,8 +3333,6 @@ static void put_unbound_pool(struct worker_pool *pool) if (pool->detach_completion) wait_for_completion(pool->detach_completion); - mutex_unlock(&pool->manager_arb); - /* shut down the timers */ del_timer_sync(&pool->idle_timer); del_timer_sync(&pool->mayday_timer); diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index 2689b7c50c52..dfdad67d8f6c 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -1092,8 +1092,8 @@ config PROVE_LOCKING select DEBUG_MUTEXES select DEBUG_RT_MUTEXES if RT_MUTEXES select DEBUG_LOCK_ALLOC - select LOCKDEP_CROSSRELEASE - select LOCKDEP_COMPLETIONS + select LOCKDEP_CROSSRELEASE if BROKEN + select LOCKDEP_COMPLETIONS if BROKEN select TRACE_IRQFLAGS default n help @@ -1590,6 +1590,54 @@ config LATENCYTOP source kernel/trace/Kconfig +config PROVIDE_OHCI1394_DMA_INIT + bool "Remote debugging over FireWire early on boot" + depends on PCI && X86 + help + If you want to debug problems which hang or crash the kernel early + on boot and the crashing machine has a FireWire port, you can use + this feature to remotely access the memory of the crashed machine + over FireWire. This employs remote DMA as part of the OHCI1394 + specification which is now the standard for FireWire controllers. + + With remote DMA, you can monitor the printk buffer remotely using + firescope and access all memory below 4GB using fireproxy from gdb. + Even controlling a kernel debugger is possible using remote DMA. + + Usage: + + If ohci1394_dma=early is used as boot parameter, it will initialize + all OHCI1394 controllers which are found in the PCI config space. + + As all changes to the FireWire bus such as enabling and disabling + devices cause a bus reset and thereby disable remote DMA for all + devices, be sure to have the cable plugged and FireWire enabled on + the debugging host before booting the debug target for debugging. + + This code (~1k) is freed after boot. By then, the firewire stack + in charge of the OHCI-1394 controllers should be used instead. + + See Documentation/debugging-via-ohci1394.txt for more information. + +config DMA_API_DEBUG + bool "Enable debugging of DMA-API usage" + depends on HAVE_DMA_API_DEBUG + help + Enable this option to debug the use of the DMA API by device drivers. + With this option you will be able to detect common bugs in device + drivers like double-freeing of DMA mappings or freeing mappings that + were never allocated. + + This also attempts to catch cases where a page owned by DMA is + accessed by the cpu in a way that could cause data corruption. For + example, this enables cow_user_page() to check that the source page is + not undergoing DMA. + + This option causes a performance degradation. Use only if you want to + debug device drivers and dma interactions. + + If unsure, say N. + menu "Runtime Testing" config LKDTM @@ -1749,56 +1797,6 @@ config TEST_PARMAN If unsure, say N. -endmenu # runtime tests - -config PROVIDE_OHCI1394_DMA_INIT - bool "Remote debugging over FireWire early on boot" - depends on PCI && X86 - help - If you want to debug problems which hang or crash the kernel early - on boot and the crashing machine has a FireWire port, you can use - this feature to remotely access the memory of the crashed machine - over FireWire. This employs remote DMA as part of the OHCI1394 - specification which is now the standard for FireWire controllers. - - With remote DMA, you can monitor the printk buffer remotely using - firescope and access all memory below 4GB using fireproxy from gdb. - Even controlling a kernel debugger is possible using remote DMA. - - Usage: - - If ohci1394_dma=early is used as boot parameter, it will initialize - all OHCI1394 controllers which are found in the PCI config space. - - As all changes to the FireWire bus such as enabling and disabling - devices cause a bus reset and thereby disable remote DMA for all - devices, be sure to have the cable plugged and FireWire enabled on - the debugging host before booting the debug target for debugging. - - This code (~1k) is freed after boot. By then, the firewire stack - in charge of the OHCI-1394 controllers should be used instead. - - See Documentation/debugging-via-ohci1394.txt for more information. - -config DMA_API_DEBUG - bool "Enable debugging of DMA-API usage" - depends on HAVE_DMA_API_DEBUG - help - Enable this option to debug the use of the DMA API by device drivers. - With this option you will be able to detect common bugs in device - drivers like double-freeing of DMA mappings or freeing mappings that - were never allocated. - - This also attempts to catch cases where a page owned by DMA is - accessed by the cpu in a way that could cause data corruption. For - example, this enables cow_user_page() to check that the source page is - not undergoing DMA. - - This option causes a performance degradation. Use only if you want to - debug device drivers and dma interactions. - - If unsure, say N. - config TEST_LKM tristate "Test module loading with 'hello world' module" default n @@ -1873,18 +1871,6 @@ config TEST_UDELAY If unsure, say N. -config MEMTEST - bool "Memtest" - depends on HAVE_MEMBLOCK - ---help--- - This option adds a kernel parameter 'memtest', which allows memtest - to be set. - memtest=0, mean disabled; -- default - memtest=1, mean do 1 test pattern; - ... - memtest=17, mean do 17 test patterns. - If you are unsure how to answer this question, answer N. - config TEST_STATIC_KEYS tristate "Test static keys" default n @@ -1894,16 +1880,6 @@ config TEST_STATIC_KEYS If unsure, say N. -config BUG_ON_DATA_CORRUPTION - bool "Trigger a BUG when data corruption is detected" - select DEBUG_LIST - help - Select this option if the kernel should BUG when it encounters - data corruption in kernel memory structures when they get checked - for validity. - - If unsure, say N. - config TEST_KMOD tristate "kmod stress tester" default n @@ -1941,6 +1917,29 @@ config TEST_DEBUG_VIRTUAL If unsure, say N. +endmenu # runtime tests + +config MEMTEST + bool "Memtest" + depends on HAVE_MEMBLOCK + ---help--- + This option adds a kernel parameter 'memtest', which allows memtest + to be set. + memtest=0, mean disabled; -- default + memtest=1, mean do 1 test pattern; + ... + memtest=17, mean do 17 test patterns. + If you are unsure how to answer this question, answer N. + +config BUG_ON_DATA_CORRUPTION + bool "Trigger a BUG when data corruption is detected" + select DEBUG_LIST + help + Select this option if the kernel should BUG when it encounters + data corruption in kernel memory structures when they get checked + for validity. + + If unsure, say N. source "samples/Kconfig" diff --git a/lib/assoc_array.c b/lib/assoc_array.c index 155c55d8db5f..4e53be8bc590 100644 --- a/lib/assoc_array.c +++ b/lib/assoc_array.c @@ -598,21 +598,31 @@ static bool assoc_array_insert_into_terminal_node(struct assoc_array_edit *edit, if ((edit->segment_cache[ASSOC_ARRAY_FAN_OUT] ^ base_seg) == 0) goto all_leaves_cluster_together; - /* Otherwise we can just insert a new node ahead of the old - * one. + /* Otherwise all the old leaves cluster in the same slot, but + * the new leaf wants to go into a different slot - so we + * create a new node (n0) to hold the new leaf and a pointer to + * a new node (n1) holding all the old leaves. + * + * This can be done by falling through to the node splitting + * path. */ - goto present_leaves_cluster_but_not_new_leaf; + pr_devel("present leaves cluster but not new leaf\n"); } split_node: pr_devel("split node\n"); - /* We need to split the current node; we know that the node doesn't - * simply contain a full set of leaves that cluster together (it - * contains meta pointers and/or non-clustering leaves). + /* We need to split the current node. The node must contain anything + * from a single leaf (in the one leaf case, this leaf will cluster + * with the new leaf) and the rest meta-pointers, to all leaves, some + * of which may cluster. + * + * It won't contain the case in which all the current leaves plus the + * new leaves want to cluster in the same slot. * * We need to expel at least two leaves out of a set consisting of the - * leaves in the node and the new leaf. + * leaves in the node and the new leaf. The current meta pointers can + * just be copied as they shouldn't cluster with any of the leaves. * * We need a new node (n0) to replace the current one and a new node to * take the expelled nodes (n1). @@ -717,33 +727,6 @@ found_slot_for_multiple_occupancy: pr_devel("<--%s() = ok [split node]\n", __func__); return true; -present_leaves_cluster_but_not_new_leaf: - /* All the old leaves cluster in the same slot, but the new leaf wants - * to go into a different slot, so we create a new node to hold the new - * leaf and a pointer to a new node holding all the old leaves. - */ - pr_devel("present leaves cluster but not new leaf\n"); - - new_n0->back_pointer = node->back_pointer; - new_n0->parent_slot = node->parent_slot; - new_n0->nr_leaves_on_branch = node->nr_leaves_on_branch; - new_n1->back_pointer = assoc_array_node_to_ptr(new_n0); - new_n1->parent_slot = edit->segment_cache[0]; - new_n1->nr_leaves_on_branch = node->nr_leaves_on_branch; - edit->adjust_count_on = new_n0; - - for (i = 0; i < ASSOC_ARRAY_FAN_OUT; i++) - new_n1->slots[i] = node->slots[i]; - - new_n0->slots[edit->segment_cache[0]] = assoc_array_node_to_ptr(new_n0); - edit->leaf_p = &new_n0->slots[edit->segment_cache[ASSOC_ARRAY_FAN_OUT]]; - - edit->set[0].ptr = &assoc_array_ptr_to_node(node->back_pointer)->slots[node->parent_slot]; - edit->set[0].to = assoc_array_node_to_ptr(new_n0); - edit->excised_meta[0] = assoc_array_node_to_ptr(node); - pr_devel("<--%s() = ok [insert node before]\n", __func__); - return true; - all_leaves_cluster_together: /* All the leaves, new and old, want to cluster together in this node * in the same slot, so we have to replace this node with a shortcut to diff --git a/lib/digsig.c b/lib/digsig.c index 03d7c63837ae..6ba6fcd92dd1 100644 --- a/lib/digsig.c +++ b/lib/digsig.c @@ -87,6 +87,12 @@ static int digsig_verify_rsa(struct key *key, down_read(&key->sem); ukp = user_key_payload_locked(key); + if (!ukp) { + /* key was revoked before we acquired its semaphore */ + err = -EKEYREVOKED; + goto err1; + } + if (ukp->datalen < sizeof(*pkh)) goto err1; diff --git a/lib/ioremap.c b/lib/ioremap.c index 4bb30206b942..c835f9080c43 100644 --- a/lib/ioremap.c +++ b/lib/ioremap.c @@ -161,6 +161,7 @@ int ioremap_page_range(unsigned long addr, unsigned long next; int err; + might_sleep(); BUG_ON(addr >= end); start = addr; diff --git a/lib/locking-selftest.c b/lib/locking-selftest.c index cd0b5c964bd0..2b827b8a1d8c 100644 --- a/lib/locking-selftest.c +++ b/lib/locking-selftest.c @@ -2031,11 +2031,13 @@ void locking_selftest(void) print_testname("mixed read-lock/lock-write ABBA"); pr_cont(" |"); dotest(rlock_ABBA1, FAILURE, LOCKTYPE_RWLOCK); +#ifdef CONFIG_PROVE_LOCKING /* * Lockdep does indeed fail here, but there's nothing we can do about * that now. Don't kill lockdep for it. */ unexpected_testcase_failures--; +#endif pr_cont(" |"); dotest(rwsem_ABBA1, FAILURE, LOCKTYPE_RWSEM); diff --git a/lib/ts_fsm.c b/lib/ts_fsm.c index 5696a35184e4..69557c74ef9f 100644 --- a/lib/ts_fsm.c +++ b/lib/ts_fsm.c @@ -11,7 +11,7 @@ * ========================================================================== * * A finite state machine consists of n states (struct ts_fsm_token) - * representing the pattern as a finite automation. The data is read + * representing the pattern as a finite automaton. The data is read * sequentially on an octet basis. Every state token specifies the number * of recurrences and the type of value accepted which can be either a * specific character or ctype based set of characters. The available diff --git a/lib/ts_kmp.c b/lib/ts_kmp.c index 632f783e65f1..ffbe66cbb0ed 100644 --- a/lib/ts_kmp.c +++ b/lib/ts_kmp.c @@ -27,7 +27,7 @@ * * [1] Cormen, Leiserson, Rivest, Stein * Introdcution to Algorithms, 2nd Edition, MIT Press - * [2] See finite automation theory + * [2] See finite automaton theory */ #include <linux/module.h> @@ -460,7 +460,7 @@ struct page *cma_alloc(struct cma *cma, size_t count, unsigned int align, trace_cma_alloc(pfn, page, count, align); - if (ret) { + if (ret && !(gfp_mask & __GFP_NOWARN)) { pr_info("%s: alloc failed, req-size: %zu pages, ret: %d\n", __func__, count, ret); cma_debug_show_areas(cma); diff --git a/mm/madvise.c b/mm/madvise.c index 25bade36e9ca..fd70d6aabc3e 100644 --- a/mm/madvise.c +++ b/mm/madvise.c @@ -757,6 +757,9 @@ madvise_behavior_valid(int behavior) * MADV_DONTFORK - omit this area from child's address space when forking: * typically, to avoid COWing pages pinned by get_user_pages(). * MADV_DOFORK - cancel MADV_DONTFORK: no longer omit this area when forking. + * MADV_WIPEONFORK - present the child process with zero-filled memory in this + * range after a fork. + * MADV_KEEPONFORK - undo the effect of MADV_WIPEONFORK * MADV_HWPOISON - trigger memory error handler as if the given memory range * were corrupted by unrecoverable hardware memory failure. * MADV_SOFT_OFFLINE - try to soft-offline the given range of memory. @@ -777,7 +780,9 @@ madvise_behavior_valid(int behavior) * zero - success * -EINVAL - start + len < 0, start is not page-aligned, * "behavior" is not a valid value, or application - * is attempting to release locked or shared pages. + * is attempting to release locked or shared pages, + * or the specified address range includes file, Huge TLB, + * MAP_SHARED or VMPFNMAP range. * -ENOMEM - addresses in the specified range are not currently * mapped, or are outside the AS of the process. * -EIO - an I/O error occurred while paging in data. diff --git a/mm/mempolicy.c b/mm/mempolicy.c index 006ba625c0b8..a2af6d58a68f 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -1920,8 +1920,11 @@ static struct page *alloc_page_interleave(gfp_t gfp, unsigned order, struct page *page; page = __alloc_pages(gfp, order, nid); - if (page && page_to_nid(page) == nid) - inc_zone_page_state(page, NUMA_INTERLEAVE_HIT); + if (page && page_to_nid(page) == nid) { + preempt_disable(); + __inc_numa_state(page_zone(page), NUMA_INTERLEAVE_HIT); + preempt_enable(); + } return page; } diff --git a/mm/migrate.c b/mm/migrate.c index 6954c1435833..e00814ca390e 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -2146,8 +2146,9 @@ static int migrate_vma_collect_hole(unsigned long start, unsigned long addr; for (addr = start & PAGE_MASK; addr < end; addr += PAGE_SIZE) { - migrate->src[migrate->npages++] = MIGRATE_PFN_MIGRATE; + migrate->src[migrate->npages] = MIGRATE_PFN_MIGRATE; migrate->dst[migrate->npages] = 0; + migrate->npages++; migrate->cpages++; } diff --git a/mm/page_vma_mapped.c b/mm/page_vma_mapped.c index 6a03946469a9..53afbb919a1c 100644 --- a/mm/page_vma_mapped.c +++ b/mm/page_vma_mapped.c @@ -6,17 +6,6 @@ #include "internal.h" -static inline bool check_pmd(struct page_vma_mapped_walk *pvmw) -{ - pmd_t pmde; - /* - * Make sure we don't re-load pmd between present and !trans_huge check. - * We need a consistent view. - */ - pmde = READ_ONCE(*pvmw->pmd); - return pmd_present(pmde) && !pmd_trans_huge(pmde); -} - static inline bool not_found(struct page_vma_mapped_walk *pvmw) { page_vma_mapped_walk_done(pvmw); @@ -116,6 +105,7 @@ bool page_vma_mapped_walk(struct page_vma_mapped_walk *pvmw) pgd_t *pgd; p4d_t *p4d; pud_t *pud; + pmd_t pmde; /* The only possible pmd mapping has been handled on last iteration */ if (pvmw->pmd && !pvmw->pte) @@ -148,7 +138,13 @@ restart: if (!pud_present(*pud)) return false; pvmw->pmd = pmd_offset(pud, pvmw->address); - if (pmd_trans_huge(*pvmw->pmd) || is_pmd_migration_entry(*pvmw->pmd)) { + /* + * Make sure the pmd value isn't cached in a register by the + * compiler and used as a stale value after we've observed a + * subsequent update. + */ + pmde = READ_ONCE(*pvmw->pmd); + if (pmd_trans_huge(pmde) || is_pmd_migration_entry(pmde)) { pvmw->ptl = pmd_lock(mm, pvmw->pmd); if (likely(pmd_trans_huge(*pvmw->pmd))) { if (pvmw->flags & PVMW_MIGRATION) @@ -167,17 +163,15 @@ restart: return not_found(pvmw); return true; } - } else - WARN_ONCE(1, "Non present huge pmd without pmd migration enabled!"); + } return not_found(pvmw); } else { /* THP pmd was split under us: handle on pte level */ spin_unlock(pvmw->ptl); pvmw->ptl = NULL; } - } else { - if (!check_pmd(pvmw)) - return false; + } else if (!pmd_present(pmde)) { + return false; } if (!map_pte(pvmw)) goto next_pte; diff --git a/mm/percpu.c b/mm/percpu.c index aa121cef76de..a0e0c82c1e4c 100644 --- a/mm/percpu.c +++ b/mm/percpu.c @@ -1329,7 +1329,9 @@ static struct pcpu_chunk *pcpu_chunk_addr_search(void *addr) * @gfp: allocation flags * * Allocate percpu area of @size bytes aligned at @align. If @gfp doesn't - * contain %GFP_KERNEL, the allocation is atomic. + * contain %GFP_KERNEL, the allocation is atomic. If @gfp has __GFP_NOWARN + * then no warning will be triggered on invalid or failed allocation + * requests. * * RETURNS: * Percpu pointer to the allocated area on success, NULL on failure. @@ -1337,10 +1339,11 @@ static struct pcpu_chunk *pcpu_chunk_addr_search(void *addr) static void __percpu *pcpu_alloc(size_t size, size_t align, bool reserved, gfp_t gfp) { + bool is_atomic = (gfp & GFP_KERNEL) != GFP_KERNEL; + bool do_warn = !(gfp & __GFP_NOWARN); static int warn_limit = 10; struct pcpu_chunk *chunk; const char *err; - bool is_atomic = (gfp & GFP_KERNEL) != GFP_KERNEL; int slot, off, cpu, ret; unsigned long flags; void __percpu *ptr; @@ -1361,7 +1364,7 @@ static void __percpu *pcpu_alloc(size_t size, size_t align, bool reserved, if (unlikely(!size || size > PCPU_MIN_UNIT_SIZE || align > PAGE_SIZE || !is_power_of_2(align))) { - WARN(true, "illegal size (%zu) or align (%zu) for percpu allocation\n", + WARN(do_warn, "illegal size (%zu) or align (%zu) for percpu allocation\n", size, align); return NULL; } @@ -1482,7 +1485,7 @@ fail_unlock: fail: trace_percpu_alloc_percpu_fail(reserved, is_atomic, size, align); - if (!is_atomic && warn_limit) { + if (!is_atomic && do_warn && warn_limit) { pr_warn("allocation failed, size=%zu align=%zu atomic=%d, %s\n", size, align, is_atomic, err); dump_stack(); @@ -1507,7 +1510,9 @@ fail: * * Allocate zero-filled percpu area of @size bytes aligned at @align. If * @gfp doesn't contain %GFP_KERNEL, the allocation doesn't block and can - * be called from any context but is a lot more likely to fail. + * be called from any context but is a lot more likely to fail. If @gfp + * has __GFP_NOWARN then no warning will be triggered on invalid or failed + * allocation requests. * * RETURNS: * Percpu pointer to the allocated area on success, NULL on failure. diff --git a/mm/swap_state.c b/mm/swap_state.c index ed91091d1e68..05b6803f0cce 100644 --- a/mm/swap_state.c +++ b/mm/swap_state.c @@ -39,10 +39,6 @@ struct address_space *swapper_spaces[MAX_SWAPFILES]; static unsigned int nr_swapper_spaces[MAX_SWAPFILES]; bool swap_vma_readahead = true; -#define SWAP_RA_MAX_ORDER_DEFAULT 3 - -static int swap_ra_max_order = SWAP_RA_MAX_ORDER_DEFAULT; - #define SWAP_RA_WIN_SHIFT (PAGE_SHIFT / 2) #define SWAP_RA_HITS_MASK ((1UL << SWAP_RA_WIN_SHIFT) - 1) #define SWAP_RA_HITS_MAX SWAP_RA_HITS_MASK @@ -664,6 +660,13 @@ struct page *swap_readahead_detect(struct vm_fault *vmf, pte_t *tpte; #endif + max_win = 1 << min_t(unsigned int, READ_ONCE(page_cluster), + SWAP_RA_ORDER_CEILING); + if (max_win == 1) { + swap_ra->win = 1; + return NULL; + } + faddr = vmf->address; entry = pte_to_swp_entry(vmf->orig_pte); if ((unlikely(non_swap_entry(entry)))) @@ -672,12 +675,6 @@ struct page *swap_readahead_detect(struct vm_fault *vmf, if (page) return page; - max_win = 1 << READ_ONCE(swap_ra_max_order); - if (max_win == 1) { - swap_ra->win = 1; - return NULL; - } - fpfn = PFN_DOWN(faddr); swap_ra_info = GET_SWAP_RA_VAL(vma); pfn = PFN_DOWN(SWAP_RA_ADDR(swap_ra_info)); @@ -786,32 +783,8 @@ static struct kobj_attribute vma_ra_enabled_attr = __ATTR(vma_ra_enabled, 0644, vma_ra_enabled_show, vma_ra_enabled_store); -static ssize_t vma_ra_max_order_show(struct kobject *kobj, - struct kobj_attribute *attr, char *buf) -{ - return sprintf(buf, "%d\n", swap_ra_max_order); -} -static ssize_t vma_ra_max_order_store(struct kobject *kobj, - struct kobj_attribute *attr, - const char *buf, size_t count) -{ - int err, v; - - err = kstrtoint(buf, 10, &v); - if (err || v > SWAP_RA_ORDER_CEILING || v <= 0) - return -EINVAL; - - swap_ra_max_order = v; - - return count; -} -static struct kobj_attribute vma_ra_max_order_attr = - __ATTR(vma_ra_max_order, 0644, vma_ra_max_order_show, - vma_ra_max_order_store); - static struct attribute *swap_attrs[] = { &vma_ra_enabled_attr.attr, - &vma_ra_max_order_attr.attr, NULL, }; diff --git a/mm/vmalloc.c b/mm/vmalloc.c index 8a43db6284eb..673942094328 100644 --- a/mm/vmalloc.c +++ b/mm/vmalloc.c @@ -1695,11 +1695,6 @@ static void *__vmalloc_area_node(struct vm_struct *area, gfp_t gfp_mask, for (i = 0; i < area->nr_pages; i++) { struct page *page; - if (fatal_signal_pending(current)) { - area->nr_pages = i; - goto fail_no_warn; - } - if (node == NUMA_NO_NODE) page = alloc_page(alloc_mask|highmem_mask); else @@ -1723,7 +1718,6 @@ fail: warn_alloc(gfp_mask, NULL, "vmalloc: allocation failure, allocated %ld of %ld bytes", (area->nr_pages*PAGE_SIZE), area->size); -fail_no_warn: vfree(area->addr); return NULL; } diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c index 3bc890716c89..de2152730809 100644 --- a/net/bridge/br_netlink.c +++ b/net/bridge/br_netlink.c @@ -573,7 +573,7 @@ static int br_process_vlan_info(struct net_bridge *br, } *vinfo_last = NULL; - return 0; + return err; } return br_vlan_info(br, p, cmd, vinfo_curr); diff --git a/net/can/af_can.c b/net/can/af_can.c index 88edac0f3e36..ecd5c703d11e 100644 --- a/net/can/af_can.c +++ b/net/can/af_can.c @@ -78,7 +78,7 @@ MODULE_PARM_DESC(stats_timer, "enable timer for statistics (default:on)"); static struct kmem_cache *rcv_cache __read_mostly; /* table of registered CAN protocols */ -static const struct can_proto *proto_tab[CAN_NPROTO] __read_mostly; +static const struct can_proto __rcu *proto_tab[CAN_NPROTO] __read_mostly; static DEFINE_MUTEX(proto_tab_lock); static atomic_t skbcounter = ATOMIC_INIT(0); @@ -788,7 +788,7 @@ int can_proto_register(const struct can_proto *cp) mutex_lock(&proto_tab_lock); - if (proto_tab[proto]) { + if (rcu_access_pointer(proto_tab[proto])) { pr_err("can: protocol %d already registered\n", proto); err = -EBUSY; } else @@ -812,7 +812,7 @@ void can_proto_unregister(const struct can_proto *cp) int proto = cp->protocol; mutex_lock(&proto_tab_lock); - BUG_ON(proto_tab[proto] != cp); + BUG_ON(rcu_access_pointer(proto_tab[proto]) != cp); RCU_INIT_POINTER(proto_tab[proto], NULL); mutex_unlock(&proto_tab_lock); @@ -875,9 +875,14 @@ static int can_pernet_init(struct net *net) spin_lock_init(&net->can.can_rcvlists_lock); net->can.can_rx_alldev_list = kzalloc(sizeof(struct dev_rcv_lists), GFP_KERNEL); - + if (!net->can.can_rx_alldev_list) + goto out; net->can.can_stats = kzalloc(sizeof(struct s_stats), GFP_KERNEL); + if (!net->can.can_stats) + goto out_free_alldev_list; net->can.can_pstats = kzalloc(sizeof(struct s_pstats), GFP_KERNEL); + if (!net->can.can_pstats) + goto out_free_can_stats; if (IS_ENABLED(CONFIG_PROC_FS)) { /* the statistics are updated every second (timer triggered) */ @@ -892,6 +897,13 @@ static int can_pernet_init(struct net *net) } return 0; + + out_free_can_stats: + kfree(net->can.can_stats); + out_free_alldev_list: + kfree(net->can.can_rx_alldev_list); + out: + return -ENOMEM; } static void can_pernet_exit(struct net *net) diff --git a/net/can/bcm.c b/net/can/bcm.c index 47a8748d953a..13690334efa3 100644 --- a/net/can/bcm.c +++ b/net/can/bcm.c @@ -1493,13 +1493,14 @@ static int bcm_init(struct sock *sk) static int bcm_release(struct socket *sock) { struct sock *sk = sock->sk; - struct net *net = sock_net(sk); + struct net *net; struct bcm_sock *bo; struct bcm_op *op, *next; - if (sk == NULL) + if (!sk) return 0; + net = sock_net(sk); bo = bcm_sk(sk); /* remove bcm_ops, timer, rx_unregister(), etc. */ diff --git a/net/core/ethtool.c b/net/core/ethtool.c index 3228411ada0f..9a9a3d77e327 100644 --- a/net/core/ethtool.c +++ b/net/core/ethtool.c @@ -436,7 +436,7 @@ bool ethtool_convert_link_mode_to_legacy_u32(u32 *legacy_u32, EXPORT_SYMBOL(ethtool_convert_link_mode_to_legacy_u32); /* return false if legacy contained non-0 deprecated fields - * transceiver/maxtxpkt/maxrxpkt. rest of ksettings always updated + * maxtxpkt/maxrxpkt. rest of ksettings always updated */ static bool convert_legacy_settings_to_link_ksettings( @@ -451,8 +451,7 @@ convert_legacy_settings_to_link_ksettings( * deprecated legacy fields, and they should not use * %ETHTOOL_GLINKSETTINGS/%ETHTOOL_SLINKSETTINGS */ - if (legacy_settings->transceiver || - legacy_settings->maxtxpkt || + if (legacy_settings->maxtxpkt || legacy_settings->maxrxpkt) retval = false; diff --git a/net/core/filter.c b/net/core/filter.c index 74b8c91fb5f4..6ae94f825f72 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -1839,31 +1839,32 @@ static const struct bpf_func_proto bpf_redirect_proto = { .arg2_type = ARG_ANYTHING, }; -BPF_CALL_3(bpf_sk_redirect_map, struct bpf_map *, map, u32, key, u64, flags) +BPF_CALL_4(bpf_sk_redirect_map, struct sk_buff *, skb, + struct bpf_map *, map, u32, key, u64, flags) { - struct redirect_info *ri = this_cpu_ptr(&redirect_info); + struct tcp_skb_cb *tcb = TCP_SKB_CB(skb); + /* If user passes invalid input drop the packet. */ if (unlikely(flags)) - return SK_ABORTED; + return SK_DROP; - ri->ifindex = key; - ri->flags = flags; - ri->map = map; + tcb->bpf.key = key; + tcb->bpf.flags = flags; + tcb->bpf.map = map; - return SK_REDIRECT; + return SK_PASS; } -struct sock *do_sk_redirect_map(void) +struct sock *do_sk_redirect_map(struct sk_buff *skb) { - struct redirect_info *ri = this_cpu_ptr(&redirect_info); + struct tcp_skb_cb *tcb = TCP_SKB_CB(skb); struct sock *sk = NULL; - if (ri->map) { - sk = __sock_map_lookup_elem(ri->map, ri->ifindex); + if (tcb->bpf.map) { + sk = __sock_map_lookup_elem(tcb->bpf.map, tcb->bpf.key); - ri->ifindex = 0; - ri->map = NULL; - /* we do not clear flags for future lookup */ + tcb->bpf.key = 0; + tcb->bpf.map = NULL; } return sk; @@ -1873,9 +1874,10 @@ static const struct bpf_func_proto bpf_sk_redirect_map_proto = { .func = bpf_sk_redirect_map, .gpl_only = false, .ret_type = RET_INTEGER, - .arg1_type = ARG_CONST_MAP_PTR, - .arg2_type = ARG_ANYTHING, + .arg1_type = ARG_PTR_TO_CTX, + .arg2_type = ARG_CONST_MAP_PTR, .arg3_type = ARG_ANYTHING, + .arg4_type = ARG_ANYTHING, }; BPF_CALL_1(bpf_get_cgroup_classid, const struct sk_buff *, skb) @@ -3683,7 +3685,6 @@ static bool sk_skb_is_valid_access(int off, int size, { if (type == BPF_WRITE) { switch (off) { - case bpf_ctx_range(struct __sk_buff, mark): case bpf_ctx_range(struct __sk_buff, tc_index): case bpf_ctx_range(struct __sk_buff, priority): break; @@ -3693,6 +3694,7 @@ static bool sk_skb_is_valid_access(int off, int size, } switch (off) { + case bpf_ctx_range(struct __sk_buff, mark): case bpf_ctx_range(struct __sk_buff, tc_classid): return false; case bpf_ctx_range(struct __sk_buff, data): @@ -4242,6 +4244,31 @@ static u32 sock_ops_convert_ctx_access(enum bpf_access_type type, return insn - insn_buf; } +static u32 sk_skb_convert_ctx_access(enum bpf_access_type type, + const struct bpf_insn *si, + struct bpf_insn *insn_buf, + struct bpf_prog *prog, u32 *target_size) +{ + struct bpf_insn *insn = insn_buf; + int off; + + switch (si->off) { + case offsetof(struct __sk_buff, data_end): + off = si->off; + off -= offsetof(struct __sk_buff, data_end); + off += offsetof(struct sk_buff, cb); + off += offsetof(struct tcp_skb_cb, bpf.data_end); + *insn++ = BPF_LDX_MEM(BPF_SIZEOF(void *), si->dst_reg, + si->src_reg, off); + break; + default: + return bpf_convert_ctx_access(type, si, insn_buf, prog, + target_size); + } + + return insn - insn_buf; +} + const struct bpf_verifier_ops sk_filter_prog_ops = { .get_func_proto = sk_filter_func_proto, .is_valid_access = sk_filter_is_valid_access, @@ -4300,7 +4327,7 @@ const struct bpf_verifier_ops sock_ops_prog_ops = { const struct bpf_verifier_ops sk_skb_prog_ops = { .get_func_proto = sk_skb_func_proto, .is_valid_access = sk_skb_is_valid_access, - .convert_ctx_access = bpf_convert_ctx_access, + .convert_ctx_access = sk_skb_convert_ctx_access, .gen_prologue = sk_skb_prologue, }; diff --git a/net/core/skbuff.c b/net/core/skbuff.c index e62476beee95..24656076906d 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -1124,9 +1124,13 @@ int skb_zerocopy_iter_stream(struct sock *sk, struct sk_buff *skb, err = __zerocopy_sg_from_iter(sk, skb, &msg->msg_iter, len); if (err == -EFAULT || (err == -EMSGSIZE && skb->len == orig_len)) { + struct sock *save_sk = skb->sk; + /* Streams do not free skb on error. Reset to prev state. */ msg->msg_iter = orig_iter; + skb->sk = sk; ___pskb_trim(skb, orig_len); + skb->sk = save_sk; return err; } diff --git a/net/core/sock_reuseport.c b/net/core/sock_reuseport.c index eed1ebf7f29d..b1e0dbea1e8c 100644 --- a/net/core/sock_reuseport.c +++ b/net/core/sock_reuseport.c @@ -36,9 +36,14 @@ int reuseport_alloc(struct sock *sk) * soft irq of receive path or setsockopt from process context */ spin_lock_bh(&reuseport_lock); - WARN_ONCE(rcu_dereference_protected(sk->sk_reuseport_cb, - lockdep_is_held(&reuseport_lock)), - "multiple allocations for the same socket"); + + /* Allocation attempts can occur concurrently via the setsockopt path + * and the bind/hash path. Nothing to do when we lose the race. + */ + if (rcu_dereference_protected(sk->sk_reuseport_cb, + lockdep_is_held(&reuseport_lock))) + goto out; + reuse = __reuseport_alloc(INIT_SOCKS); if (!reuse) { spin_unlock_bh(&reuseport_lock); @@ -49,6 +54,7 @@ int reuseport_alloc(struct sock *sk) reuse->num_socks = 1; rcu_assign_pointer(sk->sk_reuseport_cb, reuse); +out: spin_unlock_bh(&reuseport_lock); return 0; diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c index 001c08696334..e65fcb45c3f6 100644 --- a/net/dccp/ipv4.c +++ b/net/dccp/ipv4.c @@ -414,8 +414,7 @@ struct sock *dccp_v4_request_recv_sock(const struct sock *sk, sk_daddr_set(newsk, ireq->ir_rmt_addr); sk_rcv_saddr_set(newsk, ireq->ir_loc_addr); newinet->inet_saddr = ireq->ir_loc_addr; - newinet->inet_opt = ireq->opt; - ireq->opt = NULL; + RCU_INIT_POINTER(newinet->inet_opt, rcu_dereference(ireq->ireq_opt)); newinet->mc_index = inet_iif(skb); newinet->mc_ttl = ip_hdr(skb)->ttl; newinet->inet_id = jiffies; @@ -430,7 +429,10 @@ struct sock *dccp_v4_request_recv_sock(const struct sock *sk, if (__inet_inherit_port(sk, newsk) < 0) goto put_and_exit; *own_req = inet_ehash_nolisten(newsk, req_to_sk(req_unhash)); - + if (*own_req) + ireq->ireq_opt = NULL; + else + newinet->inet_opt = NULL; return newsk; exit_overflow: @@ -441,6 +443,7 @@ exit: __NET_INC_STATS(sock_net(sk), LINUX_MIB_LISTENDROPS); return NULL; put_and_exit: + newinet->inet_opt = NULL; inet_csk_prepare_forced_close(newsk); dccp_done(newsk); goto exit; @@ -492,7 +495,7 @@ static int dccp_v4_send_response(const struct sock *sk, struct request_sock *req ireq->ir_rmt_addr); err = ip_build_and_send_pkt(skb, sk, ireq->ir_loc_addr, ireq->ir_rmt_addr, - ireq->opt); + ireq_opt_deref(ireq)); err = net_xmit_eval(err); } @@ -548,7 +551,7 @@ out: static void dccp_v4_reqsk_destructor(struct request_sock *req) { dccp_feat_list_purge(&dccp_rsk(req)->dreq_featneg); - kfree(inet_rsk(req)->opt); + kfree(rcu_dereference_protected(inet_rsk(req)->ireq_opt, 1)); } void dccp_syn_ack_timeout(const struct request_sock *req) diff --git a/net/dns_resolver/dns_key.c b/net/dns_resolver/dns_key.c index 8737412c7b27..e1d4d898a007 100644 --- a/net/dns_resolver/dns_key.c +++ b/net/dns_resolver/dns_key.c @@ -224,7 +224,7 @@ static int dns_resolver_match_preparse(struct key_match_data *match_data) static void dns_resolver_describe(const struct key *key, struct seq_file *m) { seq_puts(m, key->description); - if (key_is_instantiated(key)) { + if (key_is_positive(key)) { int err = PTR_ERR(key->payload.data[dns_key_error]); if (err) diff --git a/net/dsa/dsa2.c b/net/dsa/dsa2.c index 873af0108e24..045d8a176279 100644 --- a/net/dsa/dsa2.c +++ b/net/dsa/dsa2.c @@ -496,14 +496,15 @@ static int dsa_cpu_parse(struct dsa_port *port, u32 index, if (!ethernet) return -EINVAL; ethernet_dev = of_find_net_device_by_node(ethernet); + if (!ethernet_dev) + return -EPROBE_DEFER; } else { ethernet_dev = dsa_dev_to_net_device(ds->cd->netdev[index]); + if (!ethernet_dev) + return -EPROBE_DEFER; dev_put(ethernet_dev); } - if (!ethernet_dev) - return -EPROBE_DEFER; - if (!dst->cpu_dp) { dst->cpu_dp = port; dst->cpu_dp->netdev = ethernet_dev; diff --git a/net/ife/ife.c b/net/ife/ife.c index f360341c72eb..7d1ec76e7f43 100644 --- a/net/ife/ife.c +++ b/net/ife/ife.c @@ -137,6 +137,6 @@ int ife_tlv_meta_encode(void *skbdata, u16 attrtype, u16 dlen, const void *dval) EXPORT_SYMBOL_GPL(ife_tlv_meta_encode); MODULE_AUTHOR("Jamal Hadi Salim <jhs@mojatatu.com>"); -MODULE_AUTHOR("Yotam Gigi <yotamg@mellanox.com>"); +MODULE_AUTHOR("Yotam Gigi <yotam.gi@gmail.com>"); MODULE_DESCRIPTION("Inter-FE LFB action"); MODULE_LICENSE("GPL"); diff --git a/net/ipv4/cipso_ipv4.c b/net/ipv4/cipso_ipv4.c index 2ae8f54cb321..82178cc69c96 100644 --- a/net/ipv4/cipso_ipv4.c +++ b/net/ipv4/cipso_ipv4.c @@ -1951,7 +1951,7 @@ int cipso_v4_req_setattr(struct request_sock *req, buf = NULL; req_inet = inet_rsk(req); - opt = xchg(&req_inet->opt, opt); + opt = xchg((__force struct ip_options_rcu **)&req_inet->ireq_opt, opt); if (opt) kfree_rcu(opt, rcu); @@ -1973,11 +1973,13 @@ req_setattr_failure: * values on failure. * */ -static int cipso_v4_delopt(struct ip_options_rcu **opt_ptr) +static int cipso_v4_delopt(struct ip_options_rcu __rcu **opt_ptr) { + struct ip_options_rcu *opt = rcu_dereference_protected(*opt_ptr, 1); int hdr_delta = 0; - struct ip_options_rcu *opt = *opt_ptr; + if (!opt || opt->opt.cipso == 0) + return 0; if (opt->opt.srr || opt->opt.rr || opt->opt.ts || opt->opt.router_alert) { u8 cipso_len; u8 cipso_off; @@ -2039,14 +2041,10 @@ static int cipso_v4_delopt(struct ip_options_rcu **opt_ptr) */ void cipso_v4_sock_delattr(struct sock *sk) { - int hdr_delta; - struct ip_options_rcu *opt; struct inet_sock *sk_inet; + int hdr_delta; sk_inet = inet_sk(sk); - opt = rcu_dereference_protected(sk_inet->inet_opt, 1); - if (!opt || opt->opt.cipso == 0) - return; hdr_delta = cipso_v4_delopt(&sk_inet->inet_opt); if (sk_inet->is_icsk && hdr_delta > 0) { @@ -2066,15 +2064,7 @@ void cipso_v4_sock_delattr(struct sock *sk) */ void cipso_v4_req_delattr(struct request_sock *req) { - struct ip_options_rcu *opt; - struct inet_request_sock *req_inet; - - req_inet = inet_rsk(req); - opt = req_inet->opt; - if (!opt || opt->opt.cipso == 0) - return; - - cipso_v4_delopt(&req_inet->opt); + cipso_v4_delopt(&inet_rsk(req)->ireq_opt); } /** diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c index 67aec7a10686..b47a59cb3573 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/net/ipv4/inet_connection_sock.c @@ -540,9 +540,11 @@ struct dst_entry *inet_csk_route_req(const struct sock *sk, { const struct inet_request_sock *ireq = inet_rsk(req); struct net *net = read_pnet(&ireq->ireq_net); - struct ip_options_rcu *opt = ireq->opt; + struct ip_options_rcu *opt; struct rtable *rt; + opt = ireq_opt_deref(ireq); + flowi4_init_output(fl4, ireq->ir_iif, ireq->ir_mark, RT_CONN_FLAGS(sk), RT_SCOPE_UNIVERSE, sk->sk_protocol, inet_sk_flowi_flags(sk), @@ -576,10 +578,9 @@ struct dst_entry *inet_csk_route_child_sock(const struct sock *sk, struct flowi4 *fl4; struct rtable *rt; + opt = rcu_dereference(ireq->ireq_opt); fl4 = &newinet->cork.fl.u.ip4; - rcu_read_lock(); - opt = rcu_dereference(newinet->inet_opt); flowi4_init_output(fl4, ireq->ir_iif, ireq->ir_mark, RT_CONN_FLAGS(sk), RT_SCOPE_UNIVERSE, sk->sk_protocol, inet_sk_flowi_flags(sk), @@ -592,13 +593,11 @@ struct dst_entry *inet_csk_route_child_sock(const struct sock *sk, goto no_route; if (opt && opt->opt.is_strictroute && rt->rt_uses_gateway) goto route_err; - rcu_read_unlock(); return &rt->dst; route_err: ip_rt_put(rt); no_route: - rcu_read_unlock(); __IP_INC_STATS(net, IPSTATS_MIB_OUTNOROUTES); return NULL; } diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c index 597bb4cfe805..e7d15fb0d94d 100644 --- a/net/ipv4/inet_hashtables.c +++ b/net/ipv4/inet_hashtables.c @@ -456,10 +456,7 @@ static int inet_reuseport_add_sock(struct sock *sk, return reuseport_add_sock(sk, sk2); } - /* Initial allocation may have already happened via setsockopt */ - if (!rcu_access_pointer(sk->sk_reuseport_cb)) - return reuseport_alloc(sk); - return 0; + return reuseport_alloc(sk); } int __inet_hash(struct sock *sk, struct sock *osk) diff --git a/net/ipv4/ipip.c b/net/ipv4/ipip.c index fb1ad22b5e29..cdd627355ed1 100644 --- a/net/ipv4/ipip.c +++ b/net/ipv4/ipip.c @@ -128,43 +128,68 @@ static struct rtnl_link_ops ipip_link_ops __read_mostly; static int ipip_err(struct sk_buff *skb, u32 info) { - -/* All the routers (except for Linux) return only - 8 bytes of packet payload. It means, that precise relaying of - ICMP in the real Internet is absolutely infeasible. - */ + /* All the routers (except for Linux) return only + * 8 bytes of packet payload. It means, that precise relaying of + * ICMP in the real Internet is absolutely infeasible. + */ struct net *net = dev_net(skb->dev); struct ip_tunnel_net *itn = net_generic(net, ipip_net_id); const struct iphdr *iph = (const struct iphdr *)skb->data; - struct ip_tunnel *t; - int err; const int type = icmp_hdr(skb)->type; const int code = icmp_hdr(skb)->code; + struct ip_tunnel *t; + int err = 0; + + switch (type) { + case ICMP_DEST_UNREACH: + switch (code) { + case ICMP_SR_FAILED: + /* Impossible event. */ + goto out; + default: + /* All others are translated to HOST_UNREACH. + * rfc2003 contains "deep thoughts" about NET_UNREACH, + * I believe they are just ether pollution. --ANK + */ + break; + } + break; + + case ICMP_TIME_EXCEEDED: + if (code != ICMP_EXC_TTL) + goto out; + break; + + case ICMP_REDIRECT: + break; + + default: + goto out; + } - err = -ENOENT; t = ip_tunnel_lookup(itn, skb->dev->ifindex, TUNNEL_NO_KEY, iph->daddr, iph->saddr, 0); - if (!t) + if (!t) { + err = -ENOENT; goto out; + } if (type == ICMP_DEST_UNREACH && code == ICMP_FRAG_NEEDED) { - ipv4_update_pmtu(skb, dev_net(skb->dev), info, - t->parms.link, 0, iph->protocol, 0); - err = 0; + ipv4_update_pmtu(skb, net, info, t->parms.link, 0, + iph->protocol, 0); goto out; } if (type == ICMP_REDIRECT) { - ipv4_redirect(skb, dev_net(skb->dev), t->parms.link, 0, - iph->protocol, 0); - err = 0; + ipv4_redirect(skb, net, t->parms.link, 0, iph->protocol, 0); goto out; } - if (t->parms.iph.daddr == 0) + if (t->parms.iph.daddr == 0) { + err = -ENOENT; goto out; + } - err = 0; if (t->parms.iph.ttl == 0 && type == ICMP_TIME_EXCEEDED) goto out; diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c index b1bb1b3a1082..77cf32a80952 100644 --- a/net/ipv4/syncookies.c +++ b/net/ipv4/syncookies.c @@ -355,7 +355,7 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb) /* We throwed the options of the initial SYN away, so we hope * the ACK carries the same options again (see RFC1122 4.2.3.8) */ - ireq->opt = tcp_v4_save_options(sock_net(sk), skb); + RCU_INIT_POINTER(ireq->ireq_opt, tcp_v4_save_options(sock_net(sk), skb)); if (security_inet_conn_request(sk, skb, req)) { reqsk_free(req); diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index c5d7656beeee..7eec3383702b 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -6196,7 +6196,7 @@ struct request_sock *inet_reqsk_alloc(const struct request_sock_ops *ops, struct inet_request_sock *ireq = inet_rsk(req); kmemcheck_annotate_bitfield(ireq, flags); - ireq->opt = NULL; + ireq->ireq_opt = NULL; #if IS_ENABLED(CONFIG_IPV6) ireq->pktopts = NULL; #endif diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 85164d4d3e53..5b027c69cbc5 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -877,7 +877,7 @@ static int tcp_v4_send_synack(const struct sock *sk, struct dst_entry *dst, err = ip_build_and_send_pkt(skb, sk, ireq->ir_loc_addr, ireq->ir_rmt_addr, - ireq->opt); + ireq_opt_deref(ireq)); err = net_xmit_eval(err); } @@ -889,7 +889,7 @@ static int tcp_v4_send_synack(const struct sock *sk, struct dst_entry *dst, */ static void tcp_v4_reqsk_destructor(struct request_sock *req) { - kfree(inet_rsk(req)->opt); + kfree(rcu_dereference_protected(inet_rsk(req)->ireq_opt, 1)); } #ifdef CONFIG_TCP_MD5SIG @@ -1265,10 +1265,11 @@ static void tcp_v4_init_req(struct request_sock *req, struct sk_buff *skb) { struct inet_request_sock *ireq = inet_rsk(req); + struct net *net = sock_net(sk_listener); sk_rcv_saddr_set(req_to_sk(req), ip_hdr(skb)->daddr); sk_daddr_set(req_to_sk(req), ip_hdr(skb)->saddr); - ireq->opt = tcp_v4_save_options(sock_net(sk_listener), skb); + RCU_INIT_POINTER(ireq->ireq_opt, tcp_v4_save_options(net, skb)); } static struct dst_entry *tcp_v4_route_req(const struct sock *sk, @@ -1355,10 +1356,9 @@ struct sock *tcp_v4_syn_recv_sock(const struct sock *sk, struct sk_buff *skb, sk_daddr_set(newsk, ireq->ir_rmt_addr); sk_rcv_saddr_set(newsk, ireq->ir_loc_addr); newsk->sk_bound_dev_if = ireq->ir_iif; - newinet->inet_saddr = ireq->ir_loc_addr; - inet_opt = ireq->opt; - rcu_assign_pointer(newinet->inet_opt, inet_opt); - ireq->opt = NULL; + newinet->inet_saddr = ireq->ir_loc_addr; + inet_opt = rcu_dereference(ireq->ireq_opt); + RCU_INIT_POINTER(newinet->inet_opt, inet_opt); newinet->mc_index = inet_iif(skb); newinet->mc_ttl = ip_hdr(skb)->ttl; newinet->rcv_tos = ip_hdr(skb)->tos; @@ -1403,9 +1403,12 @@ struct sock *tcp_v4_syn_recv_sock(const struct sock *sk, struct sk_buff *skb, if (__inet_inherit_port(sk, newsk) < 0) goto put_and_exit; *own_req = inet_ehash_nolisten(newsk, req_to_sk(req_unhash)); - if (*own_req) + if (likely(*own_req)) { tcp_move_syn(newtp, req); - + ireq->ireq_opt = NULL; + } else { + newinet->inet_opt = NULL; + } return newsk; exit_overflow: @@ -1416,6 +1419,7 @@ exit: tcp_listendrop(sk); return NULL; put_and_exit: + newinet->inet_opt = NULL; inet_csk_prepare_forced_close(newsk); tcp_done(newsk); goto exit; diff --git a/net/ipv4/tcp_nv.c b/net/ipv4/tcp_nv.c index 1ff73982e28c..125fc1450b01 100644 --- a/net/ipv4/tcp_nv.c +++ b/net/ipv4/tcp_nv.c @@ -252,7 +252,7 @@ static void tcpnv_acked(struct sock *sk, const struct ack_sample *sample) /* rate in 100's bits per second */ rate64 = ((u64)sample->in_flight) * 8000000; - rate = (u32)div64_u64(rate64, (u64)(avg_rtt * 100)); + rate = (u32)div64_u64(rate64, (u64)(avg_rtt ?: 1) * 100); /* Remember the maximum rate seen during this RTT * Note: It may be more than one RTT. This function should be diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 0bc9e46a5369..823003eef3a2 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -739,8 +739,10 @@ static void tcp_tsq_handler(struct sock *sk) struct tcp_sock *tp = tcp_sk(sk); if (tp->lost_out > tp->retrans_out && - tp->snd_cwnd > tcp_packets_in_flight(tp)) + tp->snd_cwnd > tcp_packets_in_flight(tp)) { + tcp_mstamp_refresh(tp); tcp_xmit_retransmit_queue(sk); + } tcp_write_xmit(sk, tcp_current_mss(sk), tp->nonagle, 0, GFP_ATOMIC); @@ -2060,6 +2062,7 @@ static int tcp_mtu_probe(struct sock *sk) nskb->ip_summed = skb->ip_summed; tcp_insert_write_queue_before(nskb, skb, sk); + tcp_highest_sack_replace(sk, skb, nskb); len = 0; tcp_for_write_queue_from_safe(skb, next, sk) { @@ -2237,6 +2240,7 @@ static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle, sent_pkts = 0; + tcp_mstamp_refresh(tp); if (!push_one) { /* Do MTU probing. */ result = tcp_mtu_probe(sk); @@ -2248,7 +2252,6 @@ static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle, } max_segs = tcp_tso_segs(sk, mss_now); - tcp_mstamp_refresh(tp); while ((skb = tcp_send_head(sk))) { unsigned int limit; @@ -2663,7 +2666,7 @@ static bool tcp_collapse_retrans(struct sock *sk, struct sk_buff *skb) else if (!skb_shift(skb, next_skb, next_skb_size)) return false; } - tcp_highest_sack_combine(sk, next_skb, skb); + tcp_highest_sack_replace(sk, next_skb, skb); tcp_unlink_write_queue(next_skb, sk); @@ -2841,8 +2844,10 @@ int __tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb, int segs) nskb = __pskb_copy(skb, MAX_TCP_HEADER, GFP_ATOMIC); err = nskb ? tcp_transmit_skb(sk, nskb, 0, GFP_ATOMIC) : -ENOBUFS; - if (!err) + if (!err) { skb->skb_mstamp = tp->tcp_mstamp; + tcp_rate_skb_sent(sk, skb); + } } else { err = tcp_transmit_skb(sk, skb, 1, GFP_ATOMIC); } diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index e45177ceb0ee..ebfbccae62fd 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -231,10 +231,7 @@ static int udp_reuseport_add_sock(struct sock *sk, struct udp_hslot *hslot) } } - /* Initial allocation may have already happened via setsockopt */ - if (!rcu_access_pointer(sk->sk_reuseport_cb)) - return reuseport_alloc(sk); - return 0; + return reuseport_alloc(sk); } /** @@ -1061,7 +1058,7 @@ back_from_confirm: /* ... which is an evident application bug. --ANK */ release_sock(sk); - net_dbg_ratelimited("cork app bug 2\n"); + net_dbg_ratelimited("socket already corked\n"); err = -EINVAL; goto out; } @@ -1144,7 +1141,7 @@ int udp_sendpage(struct sock *sk, struct page *page, int offset, if (unlikely(!up->pending)) { release_sock(sk); - net_dbg_ratelimited("udp cork app bug 3\n"); + net_dbg_ratelimited("cork failed\n"); return -EINVAL; } diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 4a96ebbf8eda..8a1c846d3df9 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -3335,6 +3335,7 @@ static void addrconf_permanent_addr(struct net_device *dev) if ((ifp->flags & IFA_F_PERMANENT) && fixup_permanent_addr(idev, ifp) < 0) { write_unlock_bh(&idev->lock); + in6_ifa_hold(ifp); ipv6_del_addr(ifp); write_lock_bh(&idev->lock); diff --git a/net/ipv6/ip6_flowlabel.c b/net/ipv6/ip6_flowlabel.c index 8081bafe441b..15535ee327c5 100644 --- a/net/ipv6/ip6_flowlabel.c +++ b/net/ipv6/ip6_flowlabel.c @@ -315,6 +315,7 @@ struct ipv6_txoptions *fl6_merge_options(struct ipv6_txoptions *opt_space, } opt_space->dst1opt = fopt->dst1opt; opt_space->opt_flen = fopt->opt_flen; + opt_space->tot_len = fopt->tot_len; return opt_space; } EXPORT_SYMBOL_GPL(fl6_merge_options); diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c index 1602b491b281..59c121b932ac 100644 --- a/net/ipv6/ip6_gre.c +++ b/net/ipv6/ip6_gre.c @@ -408,13 +408,16 @@ static void ip6gre_err(struct sk_buff *skb, struct inet6_skb_parm *opt, case ICMPV6_DEST_UNREACH: net_dbg_ratelimited("%s: Path to destination invalid or inactive!\n", t->parms.name); - break; + if (code != ICMPV6_PORT_UNREACH) + break; + return; case ICMPV6_TIME_EXCEED: if (code == ICMPV6_EXC_HOPLIMIT) { net_dbg_ratelimited("%s: Too small hop limit or routing loop in tunnel!\n", t->parms.name); + break; } - break; + return; case ICMPV6_PARAMPROB: teli = 0; if (code == ICMPV6_HDR_FIELD) @@ -430,7 +433,7 @@ static void ip6gre_err(struct sk_buff *skb, struct inet6_skb_parm *opt, net_dbg_ratelimited("%s: Recipient unable to parse tunneled packet!\n", t->parms.name); } - break; + return; case ICMPV6_PKT_TOOBIG: mtu = be32_to_cpu(info) - offset - t->tun_hlen; if (t->dev->type == ARPHRD_ETHER) @@ -438,7 +441,7 @@ static void ip6gre_err(struct sk_buff *skb, struct inet6_skb_parm *opt, if (mtu < IPV6_MIN_MTU) mtu = IPV6_MIN_MTU; t->dev->mtu = mtu; - break; + return; } if (time_before(jiffies, t->err_time + IP6TUNNEL_ERR_TIMEO)) @@ -500,8 +503,8 @@ static netdev_tx_t __gre6_xmit(struct sk_buff *skb, __u32 *pmtu, __be16 proto) { struct ip6_tnl *tunnel = netdev_priv(dev); - __be16 protocol = (dev->type == ARPHRD_ETHER) ? - htons(ETH_P_TEB) : proto; + struct dst_entry *dst = skb_dst(skb); + __be16 protocol; if (dev->type == ARPHRD_ETHER) IPCB(skb)->flags = 0; @@ -515,9 +518,14 @@ static netdev_tx_t __gre6_xmit(struct sk_buff *skb, tunnel->o_seqno++; /* Push GRE header. */ + protocol = (dev->type == ARPHRD_ETHER) ? htons(ETH_P_TEB) : proto; gre_build_header(skb, tunnel->tun_hlen, tunnel->parms.o_flags, protocol, tunnel->parms.o_key, htonl(tunnel->o_seqno)); + /* TooBig packet may have updated dst->dev's mtu */ + if (dst && dst_mtu(dst) > dst->dev->mtu) + dst->ops->update_pmtu(dst, NULL, skb, dst->dev->mtu); + return ip6_tnl_xmit(skb, dev, dsfield, fl6, encap_limit, pmtu, NEXTHDR_GRE); } diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index 43ca864327c7..5110a418cc4d 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -1161,11 +1161,11 @@ static int ip6_setup_cork(struct sock *sk, struct inet_cork_full *cork, if (WARN_ON(v6_cork->opt)) return -EINVAL; - v6_cork->opt = kzalloc(opt->tot_len, sk->sk_allocation); + v6_cork->opt = kzalloc(sizeof(*opt), sk->sk_allocation); if (unlikely(!v6_cork->opt)) return -ENOBUFS; - v6_cork->opt->tot_len = opt->tot_len; + v6_cork->opt->tot_len = sizeof(*opt); v6_cork->opt->opt_flen = opt->opt_flen; v6_cork->opt->opt_nflen = opt->opt_nflen; diff --git a/net/l2tp/l2tp_ppp.c b/net/l2tp/l2tp_ppp.c index f50452b919d5..0c2738349442 100644 --- a/net/l2tp/l2tp_ppp.c +++ b/net/l2tp/l2tp_ppp.c @@ -584,6 +584,7 @@ static int pppol2tp_connect(struct socket *sock, struct sockaddr *uservaddr, u32 tunnel_id, peer_tunnel_id; u32 session_id, peer_session_id; bool drop_refcnt = false; + bool drop_tunnel = false; int ver = 2; int fd; @@ -652,7 +653,9 @@ static int pppol2tp_connect(struct socket *sock, struct sockaddr *uservaddr, if (tunnel_id == 0) goto end; - tunnel = l2tp_tunnel_find(sock_net(sk), tunnel_id); + tunnel = l2tp_tunnel_get(sock_net(sk), tunnel_id); + if (tunnel) + drop_tunnel = true; /* Special case: create tunnel context if session_id and * peer_session_id is 0. Otherwise look up tunnel using supplied @@ -781,6 +784,8 @@ out_no_ppp: end: if (drop_refcnt) l2tp_session_dec_refcount(session); + if (drop_tunnel) + l2tp_tunnel_dec_refcount(tunnel); release_sock(sk); return error; diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c index a354f1939e49..fb15d3b97cb2 100644 --- a/net/mac80211/cfg.c +++ b/net/mac80211/cfg.c @@ -2727,12 +2727,6 @@ static int ieee80211_set_bitrate_mask(struct wiphy *wiphy, if (!ieee80211_sdata_running(sdata)) return -ENETDOWN; - if (ieee80211_hw_check(&local->hw, HAS_RATE_CONTROL)) { - ret = drv_set_bitrate_mask(local, sdata, mask); - if (ret) - return ret; - } - /* * If active validate the setting and reject it if it doesn't leave * at least one basic rate usable, since we really have to be able @@ -2748,6 +2742,12 @@ static int ieee80211_set_bitrate_mask(struct wiphy *wiphy, return -EINVAL; } + if (ieee80211_hw_check(&local->hw, HAS_RATE_CONTROL)) { + ret = drv_set_bitrate_mask(local, sdata, mask); + if (ret) + return ret; + } + for (i = 0; i < NUM_NL80211_BANDS; i++) { struct ieee80211_supported_band *sband = wiphy->bands[i]; int j; diff --git a/net/mac80211/key.c b/net/mac80211/key.c index ae995c8480db..938049395f90 100644 --- a/net/mac80211/key.c +++ b/net/mac80211/key.c @@ -19,6 +19,7 @@ #include <linux/slab.h> #include <linux/export.h> #include <net/mac80211.h> +#include <crypto/algapi.h> #include <asm/unaligned.h> #include "ieee80211_i.h" #include "driver-ops.h" @@ -609,6 +610,39 @@ void ieee80211_key_free_unused(struct ieee80211_key *key) ieee80211_key_free_common(key); } +static bool ieee80211_key_identical(struct ieee80211_sub_if_data *sdata, + struct ieee80211_key *old, + struct ieee80211_key *new) +{ + u8 tkip_old[WLAN_KEY_LEN_TKIP], tkip_new[WLAN_KEY_LEN_TKIP]; + u8 *tk_old, *tk_new; + + if (!old || new->conf.keylen != old->conf.keylen) + return false; + + tk_old = old->conf.key; + tk_new = new->conf.key; + + /* + * In station mode, don't compare the TX MIC key, as it's never used + * and offloaded rekeying may not care to send it to the host. This + * is the case in iwlwifi, for example. + */ + if (sdata->vif.type == NL80211_IFTYPE_STATION && + new->conf.cipher == WLAN_CIPHER_SUITE_TKIP && + new->conf.keylen == WLAN_KEY_LEN_TKIP && + !(new->conf.flags & IEEE80211_KEY_FLAG_PAIRWISE)) { + memcpy(tkip_old, tk_old, WLAN_KEY_LEN_TKIP); + memcpy(tkip_new, tk_new, WLAN_KEY_LEN_TKIP); + memset(tkip_old + NL80211_TKIP_DATA_OFFSET_TX_MIC_KEY, 0, 8); + memset(tkip_new + NL80211_TKIP_DATA_OFFSET_TX_MIC_KEY, 0, 8); + tk_old = tkip_old; + tk_new = tkip_new; + } + + return !crypto_memneq(tk_old, tk_new, new->conf.keylen); +} + int ieee80211_key_link(struct ieee80211_key *key, struct ieee80211_sub_if_data *sdata, struct sta_info *sta) @@ -634,8 +668,7 @@ int ieee80211_key_link(struct ieee80211_key *key, * Silently accept key re-installation without really installing the * new version of the key to avoid nonce reuse or replay issues. */ - if (old_key && key->conf.keylen == old_key->conf.keylen && - !memcmp(key->conf.key, old_key->conf.key, key->conf.keylen)) { + if (ieee80211_key_identical(sdata, old_key, key)) { ieee80211_key_free_unused(key); ret = 0; goto out; diff --git a/net/ncsi/ncsi-aen.c b/net/ncsi/ncsi-aen.c index 6898e7229285..f135938bf781 100644 --- a/net/ncsi/ncsi-aen.c +++ b/net/ncsi/ncsi-aen.c @@ -187,7 +187,7 @@ static struct ncsi_aen_handler { } ncsi_aen_handlers[] = { { NCSI_PKT_AEN_LSC, 12, ncsi_aen_handler_lsc }, { NCSI_PKT_AEN_CR, 4, ncsi_aen_handler_cr }, - { NCSI_PKT_AEN_HNCDSC, 4, ncsi_aen_handler_hncdsc } + { NCSI_PKT_AEN_HNCDSC, 8, ncsi_aen_handler_hncdsc } }; int ncsi_aen_handler(struct ncsi_dev_priv *ndp, struct sk_buff *skb) diff --git a/net/ncsi/ncsi-manage.c b/net/ncsi/ncsi-manage.c index b6a449aa9d4b..28c42b22b748 100644 --- a/net/ncsi/ncsi-manage.c +++ b/net/ncsi/ncsi-manage.c @@ -189,6 +189,7 @@ static void ncsi_channel_monitor(unsigned long data) struct ncsi_channel *nc = (struct ncsi_channel *)data; struct ncsi_package *np = nc->package; struct ncsi_dev_priv *ndp = np->ndp; + struct ncsi_channel_mode *ncm; struct ncsi_cmd_arg nca; bool enabled, chained; unsigned int monitor_state; @@ -202,11 +203,15 @@ static void ncsi_channel_monitor(unsigned long data) monitor_state = nc->monitor.state; spin_unlock_irqrestore(&nc->lock, flags); - if (!enabled || chained) + if (!enabled || chained) { + ncsi_stop_channel_monitor(nc); return; + } if (state != NCSI_CHANNEL_INACTIVE && - state != NCSI_CHANNEL_ACTIVE) + state != NCSI_CHANNEL_ACTIVE) { + ncsi_stop_channel_monitor(nc); return; + } switch (monitor_state) { case NCSI_CHANNEL_MONITOR_START: @@ -217,28 +222,28 @@ static void ncsi_channel_monitor(unsigned long data) nca.type = NCSI_PKT_CMD_GLS; nca.req_flags = 0; ret = ncsi_xmit_cmd(&nca); - if (ret) { + if (ret) netdev_err(ndp->ndev.dev, "Error %d sending GLS\n", ret); - return; - } - break; case NCSI_CHANNEL_MONITOR_WAIT ... NCSI_CHANNEL_MONITOR_WAIT_MAX: break; default: - if (!(ndp->flags & NCSI_DEV_HWA) && - state == NCSI_CHANNEL_ACTIVE) { + if (!(ndp->flags & NCSI_DEV_HWA)) { ncsi_report_link(ndp, true); ndp->flags |= NCSI_DEV_RESHUFFLE; } + ncsi_stop_channel_monitor(nc); + + ncm = &nc->modes[NCSI_MODE_LINK]; spin_lock_irqsave(&nc->lock, flags); nc->state = NCSI_CHANNEL_INVISIBLE; + ncm->data[2] &= ~0x1; spin_unlock_irqrestore(&nc->lock, flags); spin_lock_irqsave(&ndp->lock, flags); - nc->state = NCSI_CHANNEL_INACTIVE; + nc->state = NCSI_CHANNEL_ACTIVE; list_add_tail_rcu(&nc->link, &ndp->channel_queue); spin_unlock_irqrestore(&ndp->lock, flags); ncsi_process_next_channel(ndp); @@ -1002,12 +1007,15 @@ static bool ncsi_check_hwa(struct ncsi_dev_priv *ndp) struct ncsi_package *np; struct ncsi_channel *nc; unsigned int cap; + bool has_channel = false; /* The hardware arbitration is disabled if any one channel * doesn't support explicitly. */ NCSI_FOR_EACH_PACKAGE(ndp, np) { NCSI_FOR_EACH_CHANNEL(np, nc) { + has_channel = true; + cap = nc->caps[NCSI_CAP_GENERIC].cap; if (!(cap & NCSI_CAP_GENERIC_HWA) || (cap & NCSI_CAP_GENERIC_HWA_MASK) != @@ -1018,8 +1026,13 @@ static bool ncsi_check_hwa(struct ncsi_dev_priv *ndp) } } - ndp->flags |= NCSI_DEV_HWA; - return true; + if (has_channel) { + ndp->flags |= NCSI_DEV_HWA; + return true; + } + + ndp->flags &= ~NCSI_DEV_HWA; + return false; } static int ncsi_enable_hwa(struct ncsi_dev_priv *ndp) diff --git a/net/ncsi/ncsi-rsp.c b/net/ncsi/ncsi-rsp.c index 265b9a892d41..927dad4759d1 100644 --- a/net/ncsi/ncsi-rsp.c +++ b/net/ncsi/ncsi-rsp.c @@ -959,7 +959,7 @@ static struct ncsi_rsp_handler { { NCSI_PKT_RSP_EGMF, 4, ncsi_rsp_handler_egmf }, { NCSI_PKT_RSP_DGMF, 4, ncsi_rsp_handler_dgmf }, { NCSI_PKT_RSP_SNFC, 4, ncsi_rsp_handler_snfc }, - { NCSI_PKT_RSP_GVI, 36, ncsi_rsp_handler_gvi }, + { NCSI_PKT_RSP_GVI, 40, ncsi_rsp_handler_gvi }, { NCSI_PKT_RSP_GC, 32, ncsi_rsp_handler_gc }, { NCSI_PKT_RSP_GP, -1, ncsi_rsp_handler_gp }, { NCSI_PKT_RSP_GCPS, 172, ncsi_rsp_handler_gcps }, diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index bec01a3daf5b..2986941164b1 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -1769,7 +1769,7 @@ static int fanout_add(struct sock *sk, u16 id, u16 type_flags) out: if (err && rollover) { - kfree(rollover); + kfree_rcu(rollover, rcu); po->rollover = NULL; } mutex_unlock(&fanout_mutex); @@ -1796,8 +1796,10 @@ static struct packet_fanout *fanout_release(struct sock *sk) else f = NULL; - if (po->rollover) + if (po->rollover) { kfree_rcu(po->rollover, rcu); + po->rollover = NULL; + } } mutex_unlock(&fanout_mutex); @@ -3851,6 +3853,7 @@ static int packet_getsockopt(struct socket *sock, int level, int optname, void *data = &val; union tpacket_stats_u st; struct tpacket_rollover_stats rstats; + struct packet_rollover *rollover; if (level != SOL_PACKET) return -ENOPROTOOPT; @@ -3929,13 +3932,18 @@ static int packet_getsockopt(struct socket *sock, int level, int optname, 0); break; case PACKET_ROLLOVER_STATS: - if (!po->rollover) + rcu_read_lock(); + rollover = rcu_dereference(po->rollover); + if (rollover) { + rstats.tp_all = atomic_long_read(&rollover->num); + rstats.tp_huge = atomic_long_read(&rollover->num_huge); + rstats.tp_failed = atomic_long_read(&rollover->num_failed); + data = &rstats; + lv = sizeof(rstats); + } + rcu_read_unlock(); + if (!rollover) return -EINVAL; - rstats.tp_all = atomic_long_read(&po->rollover->num); - rstats.tp_huge = atomic_long_read(&po->rollover->num_huge); - rstats.tp_failed = atomic_long_read(&po->rollover->num_failed); - data = &rstats; - lv = sizeof(rstats); break; case PACKET_TX_HAS_OFF: val = po->tp_tx_has_off; diff --git a/net/psample/psample.c b/net/psample/psample.c index 3a6ad0f438dc..64f95624f219 100644 --- a/net/psample/psample.c +++ b/net/psample/psample.c @@ -296,6 +296,6 @@ static void __exit psample_module_exit(void) module_init(psample_module_init); module_exit(psample_module_exit); -MODULE_AUTHOR("Yotam Gigi <yotamg@mellanox.com>"); +MODULE_AUTHOR("Yotam Gigi <yotam.gi@gmail.com>"); MODULE_DESCRIPTION("netlink channel for packet sampling"); MODULE_LICENSE("GPL v2"); diff --git a/net/rds/ib_send.c b/net/rds/ib_send.c index 6ab39dbcca01..8557a1cae041 100644 --- a/net/rds/ib_send.c +++ b/net/rds/ib_send.c @@ -661,13 +661,15 @@ int rds_ib_xmit(struct rds_connection *conn, struct rds_message *rm, } } - rds_ib_set_wr_signal_state(ic, send, 0); + rds_ib_set_wr_signal_state(ic, send, false); /* * Always signal the last one if we're stopping due to flow control. */ - if (ic->i_flowctl && flow_controlled && i == (work_alloc-1)) - send->s_wr.send_flags |= IB_SEND_SIGNALED | IB_SEND_SOLICITED; + if (ic->i_flowctl && flow_controlled && i == (work_alloc - 1)) { + rds_ib_set_wr_signal_state(ic, send, true); + send->s_wr.send_flags |= IB_SEND_SOLICITED; + } if (send->s_wr.send_flags & IB_SEND_SIGNALED) nr_sig++; @@ -705,11 +707,8 @@ int rds_ib_xmit(struct rds_connection *conn, struct rds_message *rm, if (scat == &rm->data.op_sg[rm->data.op_count]) { prev->s_op = ic->i_data_op; prev->s_wr.send_flags |= IB_SEND_SOLICITED; - if (!(prev->s_wr.send_flags & IB_SEND_SIGNALED)) { - ic->i_unsignaled_wrs = rds_ib_sysctl_max_unsig_wrs; - prev->s_wr.send_flags |= IB_SEND_SIGNALED; - nr_sig++; - } + if (!(prev->s_wr.send_flags & IB_SEND_SIGNALED)) + nr_sig += rds_ib_set_wr_signal_state(ic, prev, true); ic->i_data_op = NULL; } @@ -792,6 +791,7 @@ int rds_ib_xmit_atomic(struct rds_connection *conn, struct rm_atomic_op *op) send->s_atomic_wr.compare_add_mask = op->op_m_fadd.nocarry_mask; send->s_atomic_wr.swap_mask = 0; } + send->s_wr.send_flags = 0; nr_sig = rds_ib_set_wr_signal_state(ic, send, op->op_notify); send->s_atomic_wr.wr.num_sge = 1; send->s_atomic_wr.wr.next = NULL; diff --git a/net/rxrpc/af_rxrpc.c b/net/rxrpc/af_rxrpc.c index fb17552fd292..4b0a8288c98a 100644 --- a/net/rxrpc/af_rxrpc.c +++ b/net/rxrpc/af_rxrpc.c @@ -308,10 +308,11 @@ struct rxrpc_call *rxrpc_kernel_begin_call(struct socket *sock, call = rxrpc_new_client_call(rx, &cp, srx, user_call_ID, tx_total_len, gfp); /* The socket has been unlocked. */ - if (!IS_ERR(call)) + if (!IS_ERR(call)) { call->notify_rx = notify_rx; + mutex_unlock(&call->user_mutex); + } - mutex_unlock(&call->user_mutex); _leave(" = %p", call); return call; } diff --git a/net/sched/act_sample.c b/net/sched/act_sample.c index ec986ae52808..8b5abcd2f32f 100644 --- a/net/sched/act_sample.c +++ b/net/sched/act_sample.c @@ -264,12 +264,13 @@ static int __init sample_init_module(void) static void __exit sample_cleanup_module(void) { + rcu_barrier(); tcf_unregister_action(&act_sample_ops, &sample_net_ops); } module_init(sample_init_module); module_exit(sample_cleanup_module); -MODULE_AUTHOR("Yotam Gigi <yotamg@mellanox.com>"); +MODULE_AUTHOR("Yotam Gigi <yotam.gi@gmail.com>"); MODULE_DESCRIPTION("Packet sampling action"); MODULE_LICENSE("GPL v2"); diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c index 0b2219adf520..b2d310745487 100644 --- a/net/sched/cls_api.c +++ b/net/sched/cls_api.c @@ -77,6 +77,8 @@ out: } EXPORT_SYMBOL(register_tcf_proto_ops); +static struct workqueue_struct *tc_filter_wq; + int unregister_tcf_proto_ops(struct tcf_proto_ops *ops) { struct tcf_proto_ops *t; @@ -86,6 +88,7 @@ int unregister_tcf_proto_ops(struct tcf_proto_ops *ops) * tcf_proto_ops's destroy() handler. */ rcu_barrier(); + flush_workqueue(tc_filter_wq); write_lock(&cls_mod_lock); list_for_each_entry(t, &tcf_proto_base, head) { @@ -100,6 +103,12 @@ int unregister_tcf_proto_ops(struct tcf_proto_ops *ops) } EXPORT_SYMBOL(unregister_tcf_proto_ops); +bool tcf_queue_work(struct work_struct *work) +{ + return queue_work(tc_filter_wq, work); +} +EXPORT_SYMBOL(tcf_queue_work); + /* Select new prio value from the range, managed by kernel. */ static inline u32 tcf_auto_prio(struct tcf_proto *tp) @@ -266,6 +275,23 @@ err_chain_create: } EXPORT_SYMBOL(tcf_block_get); +static void tcf_block_put_final(struct work_struct *work) +{ + struct tcf_block *block = container_of(work, struct tcf_block, work); + struct tcf_chain *chain, *tmp; + + rtnl_lock(); + /* Only chain 0 should be still here. */ + list_for_each_entry_safe(chain, tmp, &block->chain_list, list) + tcf_chain_put(chain); + rtnl_unlock(); + kfree(block); +} + +/* XXX: Standalone actions are not allowed to jump to any chain, and bound + * actions should be all removed after flushing. However, filters are now + * destroyed in tc filter workqueue with RTNL lock, they can not race here. + */ void tcf_block_put(struct tcf_block *block) { struct tcf_chain *chain, *tmp; @@ -273,32 +299,15 @@ void tcf_block_put(struct tcf_block *block) if (!block) return; - /* XXX: Standalone actions are not allowed to jump to any chain, and - * bound actions should be all removed after flushing. However, - * filters are destroyed in RCU callbacks, we have to hold the chains - * first, otherwise we would always race with RCU callbacks on this list - * without proper locking. - */ - - /* Wait for existing RCU callbacks to cool down. */ - rcu_barrier(); - - /* Hold a refcnt for all chains, except 0, in case they are gone. */ - list_for_each_entry(chain, &block->chain_list, list) - if (chain->index) - tcf_chain_hold(chain); - - /* No race on the list, because no chain could be destroyed. */ - list_for_each_entry(chain, &block->chain_list, list) + list_for_each_entry_safe(chain, tmp, &block->chain_list, list) tcf_chain_flush(chain); - /* Wait for RCU callbacks to release the reference count. */ + INIT_WORK(&block->work, tcf_block_put_final); + /* Wait for RCU callbacks to release the reference count and make + * sure their works have been queued before this. + */ rcu_barrier(); - - /* At this point, all the chains should have refcnt == 1. */ - list_for_each_entry_safe(chain, tmp, &block->chain_list, list) - tcf_chain_put(chain); - kfree(block); + tcf_queue_work(&block->work); } EXPORT_SYMBOL(tcf_block_put); @@ -879,6 +888,7 @@ void tcf_exts_destroy(struct tcf_exts *exts) #ifdef CONFIG_NET_CLS_ACT LIST_HEAD(actions); + ASSERT_RTNL(); tcf_exts_to_list(exts, &actions); tcf_action_destroy(&actions, TCA_ACT_UNBIND); kfree(exts->actions); @@ -1030,6 +1040,10 @@ EXPORT_SYMBOL(tcf_exts_get_dev); static int __init tc_filter_init(void) { + tc_filter_wq = alloc_ordered_workqueue("tc_filter_workqueue", 0); + if (!tc_filter_wq) + return -ENOMEM; + rtnl_register(PF_UNSPEC, RTM_NEWTFILTER, tc_ctl_tfilter, NULL, 0); rtnl_register(PF_UNSPEC, RTM_DELTFILTER, tc_ctl_tfilter, NULL, 0); rtnl_register(PF_UNSPEC, RTM_GETTFILTER, tc_ctl_tfilter, diff --git a/net/sched/cls_basic.c b/net/sched/cls_basic.c index d89ebafd2239..f177649a2419 100644 --- a/net/sched/cls_basic.c +++ b/net/sched/cls_basic.c @@ -34,7 +34,10 @@ struct basic_filter { struct tcf_result res; struct tcf_proto *tp; struct list_head link; - struct rcu_head rcu; + union { + struct work_struct work; + struct rcu_head rcu; + }; }; static int basic_classify(struct sk_buff *skb, const struct tcf_proto *tp, @@ -82,15 +85,26 @@ static int basic_init(struct tcf_proto *tp) return 0; } -static void basic_delete_filter(struct rcu_head *head) +static void basic_delete_filter_work(struct work_struct *work) { - struct basic_filter *f = container_of(head, struct basic_filter, rcu); + struct basic_filter *f = container_of(work, struct basic_filter, work); + rtnl_lock(); tcf_exts_destroy(&f->exts); tcf_em_tree_destroy(&f->ematches); + rtnl_unlock(); + kfree(f); } +static void basic_delete_filter(struct rcu_head *head) +{ + struct basic_filter *f = container_of(head, struct basic_filter, rcu); + + INIT_WORK(&f->work, basic_delete_filter_work); + tcf_queue_work(&f->work); +} + static void basic_destroy(struct tcf_proto *tp) { struct basic_head *head = rtnl_dereference(tp->root); diff --git a/net/sched/cls_bpf.c b/net/sched/cls_bpf.c index 520c5027646a..037a3ae86829 100644 --- a/net/sched/cls_bpf.c +++ b/net/sched/cls_bpf.c @@ -49,7 +49,10 @@ struct cls_bpf_prog { struct sock_filter *bpf_ops; const char *bpf_name; struct tcf_proto *tp; - struct rcu_head rcu; + union { + struct work_struct work; + struct rcu_head rcu; + }; }; static const struct nla_policy bpf_policy[TCA_BPF_MAX + 1] = { @@ -257,9 +260,21 @@ static void __cls_bpf_delete_prog(struct cls_bpf_prog *prog) kfree(prog); } +static void cls_bpf_delete_prog_work(struct work_struct *work) +{ + struct cls_bpf_prog *prog = container_of(work, struct cls_bpf_prog, work); + + rtnl_lock(); + __cls_bpf_delete_prog(prog); + rtnl_unlock(); +} + static void cls_bpf_delete_prog_rcu(struct rcu_head *rcu) { - __cls_bpf_delete_prog(container_of(rcu, struct cls_bpf_prog, rcu)); + struct cls_bpf_prog *prog = container_of(rcu, struct cls_bpf_prog, rcu); + + INIT_WORK(&prog->work, cls_bpf_delete_prog_work); + tcf_queue_work(&prog->work); } static void __cls_bpf_delete(struct tcf_proto *tp, struct cls_bpf_prog *prog) diff --git a/net/sched/cls_cgroup.c b/net/sched/cls_cgroup.c index d48452f87975..a97e069bee89 100644 --- a/net/sched/cls_cgroup.c +++ b/net/sched/cls_cgroup.c @@ -23,7 +23,10 @@ struct cls_cgroup_head { struct tcf_exts exts; struct tcf_ematch_tree ematches; struct tcf_proto *tp; - struct rcu_head rcu; + union { + struct work_struct work; + struct rcu_head rcu; + }; }; static int cls_cgroup_classify(struct sk_buff *skb, const struct tcf_proto *tp, @@ -57,15 +60,26 @@ static const struct nla_policy cgroup_policy[TCA_CGROUP_MAX + 1] = { [TCA_CGROUP_EMATCHES] = { .type = NLA_NESTED }, }; +static void cls_cgroup_destroy_work(struct work_struct *work) +{ + struct cls_cgroup_head *head = container_of(work, + struct cls_cgroup_head, + work); + rtnl_lock(); + tcf_exts_destroy(&head->exts); + tcf_em_tree_destroy(&head->ematches); + kfree(head); + rtnl_unlock(); +} + static void cls_cgroup_destroy_rcu(struct rcu_head *root) { struct cls_cgroup_head *head = container_of(root, struct cls_cgroup_head, rcu); - tcf_exts_destroy(&head->exts); - tcf_em_tree_destroy(&head->ematches); - kfree(head); + INIT_WORK(&head->work, cls_cgroup_destroy_work); + tcf_queue_work(&head->work); } static int cls_cgroup_change(struct net *net, struct sk_buff *in_skb, diff --git a/net/sched/cls_flow.c b/net/sched/cls_flow.c index 2a3a60ec5b86..67f3a2af6aab 100644 --- a/net/sched/cls_flow.c +++ b/net/sched/cls_flow.c @@ -57,7 +57,10 @@ struct flow_filter { u32 divisor; u32 baseclass; u32 hashrnd; - struct rcu_head rcu; + union { + struct work_struct work; + struct rcu_head rcu; + }; }; static inline u32 addr_fold(void *addr) @@ -369,14 +372,24 @@ static const struct nla_policy flow_policy[TCA_FLOW_MAX + 1] = { [TCA_FLOW_PERTURB] = { .type = NLA_U32 }, }; -static void flow_destroy_filter(struct rcu_head *head) +static void flow_destroy_filter_work(struct work_struct *work) { - struct flow_filter *f = container_of(head, struct flow_filter, rcu); + struct flow_filter *f = container_of(work, struct flow_filter, work); + rtnl_lock(); del_timer_sync(&f->perturb_timer); tcf_exts_destroy(&f->exts); tcf_em_tree_destroy(&f->ematches); kfree(f); + rtnl_unlock(); +} + +static void flow_destroy_filter(struct rcu_head *head) +{ + struct flow_filter *f = container_of(head, struct flow_filter, rcu); + + INIT_WORK(&f->work, flow_destroy_filter_work); + tcf_queue_work(&f->work); } static int flow_change(struct net *net, struct sk_buff *in_skb, diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c index b480d7c792ba..5b5722c8b32c 100644 --- a/net/sched/cls_flower.c +++ b/net/sched/cls_flower.c @@ -87,7 +87,10 @@ struct cls_fl_filter { struct list_head list; u32 handle; u32 flags; - struct rcu_head rcu; + union { + struct work_struct work; + struct rcu_head rcu; + }; struct net_device *hw_dev; }; @@ -215,12 +218,22 @@ static int fl_init(struct tcf_proto *tp) return 0; } -static void fl_destroy_filter(struct rcu_head *head) +static void fl_destroy_filter_work(struct work_struct *work) { - struct cls_fl_filter *f = container_of(head, struct cls_fl_filter, rcu); + struct cls_fl_filter *f = container_of(work, struct cls_fl_filter, work); + rtnl_lock(); tcf_exts_destroy(&f->exts); kfree(f); + rtnl_unlock(); +} + +static void fl_destroy_filter(struct rcu_head *head) +{ + struct cls_fl_filter *f = container_of(head, struct cls_fl_filter, rcu); + + INIT_WORK(&f->work, fl_destroy_filter_work); + tcf_queue_work(&f->work); } static void fl_hw_destroy_filter(struct tcf_proto *tp, struct cls_fl_filter *f) diff --git a/net/sched/cls_fw.c b/net/sched/cls_fw.c index 941245ad07fd..99183b8621ec 100644 --- a/net/sched/cls_fw.c +++ b/net/sched/cls_fw.c @@ -46,7 +46,10 @@ struct fw_filter { #endif /* CONFIG_NET_CLS_IND */ struct tcf_exts exts; struct tcf_proto *tp; - struct rcu_head rcu; + union { + struct work_struct work; + struct rcu_head rcu; + }; }; static u32 fw_hash(u32 handle) @@ -119,12 +122,22 @@ static int fw_init(struct tcf_proto *tp) return 0; } -static void fw_delete_filter(struct rcu_head *head) +static void fw_delete_filter_work(struct work_struct *work) { - struct fw_filter *f = container_of(head, struct fw_filter, rcu); + struct fw_filter *f = container_of(work, struct fw_filter, work); + rtnl_lock(); tcf_exts_destroy(&f->exts); kfree(f); + rtnl_unlock(); +} + +static void fw_delete_filter(struct rcu_head *head) +{ + struct fw_filter *f = container_of(head, struct fw_filter, rcu); + + INIT_WORK(&f->work, fw_delete_filter_work); + tcf_queue_work(&f->work); } static void fw_destroy(struct tcf_proto *tp) diff --git a/net/sched/cls_matchall.c b/net/sched/cls_matchall.c index eeac606c95ab..c33f711b9019 100644 --- a/net/sched/cls_matchall.c +++ b/net/sched/cls_matchall.c @@ -21,7 +21,10 @@ struct cls_mall_head { struct tcf_result res; u32 handle; u32 flags; - struct rcu_head rcu; + union { + struct work_struct work; + struct rcu_head rcu; + }; }; static int mall_classify(struct sk_buff *skb, const struct tcf_proto *tp, @@ -41,13 +44,23 @@ static int mall_init(struct tcf_proto *tp) return 0; } +static void mall_destroy_work(struct work_struct *work) +{ + struct cls_mall_head *head = container_of(work, struct cls_mall_head, + work); + rtnl_lock(); + tcf_exts_destroy(&head->exts); + kfree(head); + rtnl_unlock(); +} + static void mall_destroy_rcu(struct rcu_head *rcu) { struct cls_mall_head *head = container_of(rcu, struct cls_mall_head, rcu); - tcf_exts_destroy(&head->exts); - kfree(head); + INIT_WORK(&head->work, mall_destroy_work); + tcf_queue_work(&head->work); } static int mall_replace_hw_filter(struct tcf_proto *tp, diff --git a/net/sched/cls_route.c b/net/sched/cls_route.c index 9ddde65915d2..4b14ccd8b8f2 100644 --- a/net/sched/cls_route.c +++ b/net/sched/cls_route.c @@ -57,7 +57,10 @@ struct route4_filter { u32 handle; struct route4_bucket *bkt; struct tcf_proto *tp; - struct rcu_head rcu; + union { + struct work_struct work; + struct rcu_head rcu; + }; }; #define ROUTE4_FAILURE ((struct route4_filter *)(-1L)) @@ -254,12 +257,22 @@ static int route4_init(struct tcf_proto *tp) return 0; } -static void route4_delete_filter(struct rcu_head *head) +static void route4_delete_filter_work(struct work_struct *work) { - struct route4_filter *f = container_of(head, struct route4_filter, rcu); + struct route4_filter *f = container_of(work, struct route4_filter, work); + rtnl_lock(); tcf_exts_destroy(&f->exts); kfree(f); + rtnl_unlock(); +} + +static void route4_delete_filter(struct rcu_head *head) +{ + struct route4_filter *f = container_of(head, struct route4_filter, rcu); + + INIT_WORK(&f->work, route4_delete_filter_work); + tcf_queue_work(&f->work); } static void route4_destroy(struct tcf_proto *tp) diff --git a/net/sched/cls_rsvp.h b/net/sched/cls_rsvp.h index b1f6ed48bc72..bdbc541787f8 100644 --- a/net/sched/cls_rsvp.h +++ b/net/sched/cls_rsvp.h @@ -97,7 +97,10 @@ struct rsvp_filter { u32 handle; struct rsvp_session *sess; - struct rcu_head rcu; + union { + struct work_struct work; + struct rcu_head rcu; + }; }; static inline unsigned int hash_dst(__be32 *dst, u8 protocol, u8 tunnelid) @@ -282,12 +285,22 @@ static int rsvp_init(struct tcf_proto *tp) return -ENOBUFS; } -static void rsvp_delete_filter_rcu(struct rcu_head *head) +static void rsvp_delete_filter_work(struct work_struct *work) { - struct rsvp_filter *f = container_of(head, struct rsvp_filter, rcu); + struct rsvp_filter *f = container_of(work, struct rsvp_filter, work); + rtnl_lock(); tcf_exts_destroy(&f->exts); kfree(f); + rtnl_unlock(); +} + +static void rsvp_delete_filter_rcu(struct rcu_head *head) +{ + struct rsvp_filter *f = container_of(head, struct rsvp_filter, rcu); + + INIT_WORK(&f->work, rsvp_delete_filter_work); + tcf_queue_work(&f->work); } static void rsvp_delete_filter(struct tcf_proto *tp, struct rsvp_filter *f) diff --git a/net/sched/cls_tcindex.c b/net/sched/cls_tcindex.c index 14a7e08b2fa9..beaa95e09c25 100644 --- a/net/sched/cls_tcindex.c +++ b/net/sched/cls_tcindex.c @@ -27,14 +27,20 @@ struct tcindex_filter_result { struct tcf_exts exts; struct tcf_result res; - struct rcu_head rcu; + union { + struct work_struct work; + struct rcu_head rcu; + }; }; struct tcindex_filter { u16 key; struct tcindex_filter_result result; struct tcindex_filter __rcu *next; - struct rcu_head rcu; + union { + struct work_struct work; + struct rcu_head rcu; + }; }; @@ -133,12 +139,34 @@ static int tcindex_init(struct tcf_proto *tp) return 0; } +static void tcindex_destroy_rexts_work(struct work_struct *work) +{ + struct tcindex_filter_result *r; + + r = container_of(work, struct tcindex_filter_result, work); + rtnl_lock(); + tcf_exts_destroy(&r->exts); + rtnl_unlock(); +} + static void tcindex_destroy_rexts(struct rcu_head *head) { struct tcindex_filter_result *r; r = container_of(head, struct tcindex_filter_result, rcu); - tcf_exts_destroy(&r->exts); + INIT_WORK(&r->work, tcindex_destroy_rexts_work); + tcf_queue_work(&r->work); +} + +static void tcindex_destroy_fexts_work(struct work_struct *work) +{ + struct tcindex_filter *f = container_of(work, struct tcindex_filter, + work); + + rtnl_lock(); + tcf_exts_destroy(&f->result.exts); + kfree(f); + rtnl_unlock(); } static void tcindex_destroy_fexts(struct rcu_head *head) @@ -146,8 +174,8 @@ static void tcindex_destroy_fexts(struct rcu_head *head) struct tcindex_filter *f = container_of(head, struct tcindex_filter, rcu); - tcf_exts_destroy(&f->result.exts); - kfree(f); + INIT_WORK(&f->work, tcindex_destroy_fexts_work); + tcf_queue_work(&f->work); } static int tcindex_delete(struct tcf_proto *tp, void *arg, bool *last) diff --git a/net/sched/cls_u32.c b/net/sched/cls_u32.c index 10b8d851fc6b..dadd1b344497 100644 --- a/net/sched/cls_u32.c +++ b/net/sched/cls_u32.c @@ -68,7 +68,10 @@ struct tc_u_knode { u32 __percpu *pcpu_success; #endif struct tcf_proto *tp; - struct rcu_head rcu; + union { + struct work_struct work; + struct rcu_head rcu; + }; /* The 'sel' field MUST be the last field in structure to allow for * tc_u32_keys allocated at end of structure. */ @@ -418,11 +421,21 @@ static int u32_destroy_key(struct tcf_proto *tp, struct tc_u_knode *n, * this the u32_delete_key_rcu variant does not free the percpu * statistics. */ +static void u32_delete_key_work(struct work_struct *work) +{ + struct tc_u_knode *key = container_of(work, struct tc_u_knode, work); + + rtnl_lock(); + u32_destroy_key(key->tp, key, false); + rtnl_unlock(); +} + static void u32_delete_key_rcu(struct rcu_head *rcu) { struct tc_u_knode *key = container_of(rcu, struct tc_u_knode, rcu); - u32_destroy_key(key->tp, key, false); + INIT_WORK(&key->work, u32_delete_key_work); + tcf_queue_work(&key->work); } /* u32_delete_key_freepf_rcu is the rcu callback variant @@ -432,11 +445,21 @@ static void u32_delete_key_rcu(struct rcu_head *rcu) * for the variant that should be used with keys return from * u32_init_knode() */ +static void u32_delete_key_freepf_work(struct work_struct *work) +{ + struct tc_u_knode *key = container_of(work, struct tc_u_knode, work); + + rtnl_lock(); + u32_destroy_key(key->tp, key, true); + rtnl_unlock(); +} + static void u32_delete_key_freepf_rcu(struct rcu_head *rcu) { struct tc_u_knode *key = container_of(rcu, struct tc_u_knode, rcu); - u32_destroy_key(key->tp, key, true); + INIT_WORK(&key->work, u32_delete_key_freepf_work); + tcf_queue_work(&key->work); } static int u32_delete_key(struct tcf_proto *tp, struct tc_u_knode *key) diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c index c6deb74e3d2f..22bc6fc48311 100644 --- a/net/sched/sch_api.c +++ b/net/sched/sch_api.c @@ -301,6 +301,8 @@ struct Qdisc *qdisc_lookup(struct net_device *dev, u32 handle) { struct Qdisc *q; + if (!handle) + return NULL; q = qdisc_match_from_root(dev->qdisc, handle); if (q) goto out; diff --git a/net/sctp/input.c b/net/sctp/input.c index 92a07141fd07..621b5ca3fd1c 100644 --- a/net/sctp/input.c +++ b/net/sctp/input.c @@ -421,7 +421,7 @@ void sctp_icmp_redirect(struct sock *sk, struct sctp_transport *t, { struct dst_entry *dst; - if (!t) + if (sock_owned_by_user(sk) || !t) return; dst = sctp_transport_dst_check(t); if (dst) @@ -794,7 +794,7 @@ hit: struct sctp_hash_cmp_arg { const union sctp_addr *paddr; const struct net *net; - u16 lport; + __be16 lport; }; static inline int sctp_hash_cmp(struct rhashtable_compare_arg *arg, @@ -820,37 +820,37 @@ out: return err; } -static inline u32 sctp_hash_obj(const void *data, u32 len, u32 seed) +static inline __u32 sctp_hash_obj(const void *data, u32 len, u32 seed) { const struct sctp_transport *t = data; const union sctp_addr *paddr = &t->ipaddr; const struct net *net = sock_net(t->asoc->base.sk); - u16 lport = htons(t->asoc->base.bind_addr.port); - u32 addr; + __be16 lport = htons(t->asoc->base.bind_addr.port); + __u32 addr; if (paddr->sa.sa_family == AF_INET6) addr = jhash(&paddr->v6.sin6_addr, 16, seed); else - addr = paddr->v4.sin_addr.s_addr; + addr = (__force __u32)paddr->v4.sin_addr.s_addr; - return jhash_3words(addr, ((__u32)paddr->v4.sin_port) << 16 | + return jhash_3words(addr, ((__force __u32)paddr->v4.sin_port) << 16 | (__force __u32)lport, net_hash_mix(net), seed); } -static inline u32 sctp_hash_key(const void *data, u32 len, u32 seed) +static inline __u32 sctp_hash_key(const void *data, u32 len, u32 seed) { const struct sctp_hash_cmp_arg *x = data; const union sctp_addr *paddr = x->paddr; const struct net *net = x->net; - u16 lport = x->lport; - u32 addr; + __be16 lport = x->lport; + __u32 addr; if (paddr->sa.sa_family == AF_INET6) addr = jhash(&paddr->v6.sin6_addr, 16, seed); else - addr = paddr->v4.sin_addr.s_addr; + addr = (__force __u32)paddr->v4.sin_addr.s_addr; - return jhash_3words(addr, ((__u32)paddr->v4.sin_port) << 16 | + return jhash_3words(addr, ((__force __u32)paddr->v4.sin_port) << 16 | (__force __u32)lport, net_hash_mix(net), seed); } diff --git a/net/sctp/ipv6.c b/net/sctp/ipv6.c index 51c488769590..a6dfa86c0201 100644 --- a/net/sctp/ipv6.c +++ b/net/sctp/ipv6.c @@ -738,7 +738,7 @@ static int sctp_v6_skb_iif(const struct sk_buff *skb) /* Was this packet marked by Explicit Congestion Notification? */ static int sctp_v6_is_ce(const struct sk_buff *skb) { - return *((__u32 *)(ipv6_hdr(skb))) & htonl(1 << 20); + return *((__u32 *)(ipv6_hdr(skb))) & (__force __u32)htonl(1 << 20); } /* Dump the v6 addr to the seq file. */ @@ -882,8 +882,10 @@ static int sctp_inet6_bind_verify(struct sctp_sock *opt, union sctp_addr *addr) net = sock_net(&opt->inet.sk); rcu_read_lock(); dev = dev_get_by_index_rcu(net, addr->v6.sin6_scope_id); - if (!dev || - !ipv6_chk_addr(net, &addr->v6.sin6_addr, dev, 0)) { + if (!dev || !(opt->inet.freebind || + net->ipv6.sysctl.ip_nonlocal_bind || + ipv6_chk_addr(net, &addr->v6.sin6_addr, + dev, 0))) { rcu_read_unlock(); return 0; } diff --git a/net/sctp/sm_make_chunk.c b/net/sctp/sm_make_chunk.c index ca8f196b6c6c..514465b03829 100644 --- a/net/sctp/sm_make_chunk.c +++ b/net/sctp/sm_make_chunk.c @@ -2854,7 +2854,7 @@ struct sctp_chunk *sctp_make_asconf_update_ip(struct sctp_association *asoc, addr_param_len = af->to_addr_param(addr, &addr_param); param.param_hdr.type = flags; param.param_hdr.length = htons(paramlen + addr_param_len); - param.crr_id = i; + param.crr_id = htonl(i); sctp_addto_chunk(retval, paramlen, ¶m); sctp_addto_chunk(retval, addr_param_len, &addr_param); @@ -2867,7 +2867,7 @@ struct sctp_chunk *sctp_make_asconf_update_ip(struct sctp_association *asoc, addr_param_len = af->to_addr_param(addr, &addr_param); param.param_hdr.type = SCTP_PARAM_DEL_IP; param.param_hdr.length = htons(paramlen + addr_param_len); - param.crr_id = i; + param.crr_id = htonl(i); sctp_addto_chunk(retval, paramlen, ¶m); sctp_addto_chunk(retval, addr_param_len, &addr_param); @@ -3591,7 +3591,7 @@ static struct sctp_chunk *sctp_make_reconf(const struct sctp_association *asoc, */ struct sctp_chunk *sctp_make_strreset_req( const struct sctp_association *asoc, - __u16 stream_num, __u16 *stream_list, + __u16 stream_num, __be16 *stream_list, bool out, bool in) { struct sctp_strreset_outreq outreq; @@ -3788,7 +3788,8 @@ bool sctp_verify_reconf(const struct sctp_association *asoc, { struct sctp_reconf_chunk *hdr; union sctp_params param; - __u16 last = 0, cnt = 0; + __be16 last = 0; + __u16 cnt = 0; hdr = (struct sctp_reconf_chunk *)chunk->chunk_hdr; sctp_walk_params(param, hdr, params) { diff --git a/net/sctp/sm_sideeffect.c b/net/sctp/sm_sideeffect.c index e6a2974e020e..e2d9a4b49c9c 100644 --- a/net/sctp/sm_sideeffect.c +++ b/net/sctp/sm_sideeffect.c @@ -1607,12 +1607,12 @@ static int sctp_cmd_interpreter(enum sctp_event event_type, break; case SCTP_CMD_INIT_FAILED: - sctp_cmd_init_failed(commands, asoc, cmd->obj.err); + sctp_cmd_init_failed(commands, asoc, cmd->obj.u32); break; case SCTP_CMD_ASSOC_FAILED: sctp_cmd_assoc_failed(commands, asoc, event_type, - subtype, chunk, cmd->obj.err); + subtype, chunk, cmd->obj.u32); break; case SCTP_CMD_INIT_COUNTER_INC: @@ -1680,8 +1680,8 @@ static int sctp_cmd_interpreter(enum sctp_event event_type, case SCTP_CMD_PROCESS_CTSN: /* Dummy up a SACK for processing. */ sackh.cum_tsn_ack = cmd->obj.be32; - sackh.a_rwnd = asoc->peer.rwnd + - asoc->outqueue.outstanding_bytes; + sackh.a_rwnd = htonl(asoc->peer.rwnd + + asoc->outqueue.outstanding_bytes); sackh.num_gap_ack_blocks = 0; sackh.num_dup_tsns = 0; chunk->subh.sack_hdr = &sackh; diff --git a/net/sctp/socket.c b/net/sctp/socket.c index d4730ada7f32..6f45d1713452 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -170,6 +170,36 @@ static inline void sctp_set_owner_w(struct sctp_chunk *chunk) sk_mem_charge(sk, chunk->skb->truesize); } +static void sctp_clear_owner_w(struct sctp_chunk *chunk) +{ + skb_orphan(chunk->skb); +} + +static void sctp_for_each_tx_datachunk(struct sctp_association *asoc, + void (*cb)(struct sctp_chunk *)) + +{ + struct sctp_outq *q = &asoc->outqueue; + struct sctp_transport *t; + struct sctp_chunk *chunk; + + list_for_each_entry(t, &asoc->peer.transport_addr_list, transports) + list_for_each_entry(chunk, &t->transmitted, transmitted_list) + cb(chunk); + + list_for_each_entry(chunk, &q->retransmit, list) + cb(chunk); + + list_for_each_entry(chunk, &q->sacked, list) + cb(chunk); + + list_for_each_entry(chunk, &q->abandoned, list) + cb(chunk); + + list_for_each_entry(chunk, &q->out_chunk_list, list) + cb(chunk); +} + /* Verify that this is a valid address. */ static inline int sctp_verify_addr(struct sock *sk, union sctp_addr *addr, int len) @@ -4906,6 +4936,10 @@ int sctp_do_peeloff(struct sock *sk, sctp_assoc_t id, struct socket **sockp) struct socket *sock; int err = 0; + /* Do not peel off from one netns to another one. */ + if (!net_eq(current->nsproxy->net_ns, sock_net(sk))) + return -EINVAL; + if (!asoc) return -EINVAL; @@ -8208,7 +8242,9 @@ static void sctp_sock_migrate(struct sock *oldsk, struct sock *newsk, * paths won't try to lock it and then oldsk. */ lock_sock_nested(newsk, SINGLE_DEPTH_NESTING); + sctp_for_each_tx_datachunk(assoc, sctp_clear_owner_w); sctp_assoc_migrate(assoc, newsk); + sctp_for_each_tx_datachunk(assoc, sctp_set_owner_w); /* If the association on the newsk is already closed before accept() * is called, set RCV_SHUTDOWN flag. diff --git a/net/sctp/stream.c b/net/sctp/stream.c index 63ea15503714..fa8371ff05c4 100644 --- a/net/sctp/stream.c +++ b/net/sctp/stream.c @@ -118,6 +118,7 @@ int sctp_send_reset_streams(struct sctp_association *asoc, __u16 i, str_nums, *str_list; struct sctp_chunk *chunk; int retval = -EINVAL; + __be16 *nstr_list; bool out, in; if (!asoc->peer.reconf_capable || @@ -148,13 +149,18 @@ int sctp_send_reset_streams(struct sctp_association *asoc, if (str_list[i] >= stream->incnt) goto out; + nstr_list = kcalloc(str_nums, sizeof(__be16), GFP_KERNEL); + if (!nstr_list) { + retval = -ENOMEM; + goto out; + } + for (i = 0; i < str_nums; i++) - str_list[i] = htons(str_list[i]); + nstr_list[i] = htons(str_list[i]); - chunk = sctp_make_strreset_req(asoc, str_nums, str_list, out, in); + chunk = sctp_make_strreset_req(asoc, str_nums, nstr_list, out, in); - for (i = 0; i < str_nums; i++) - str_list[i] = ntohs(str_list[i]); + kfree(nstr_list); if (!chunk) { retval = -ENOMEM; @@ -305,7 +311,7 @@ out: } static struct sctp_paramhdr *sctp_chunk_lookup_strreset_param( - struct sctp_association *asoc, __u32 resp_seq, + struct sctp_association *asoc, __be32 resp_seq, __be16 type) { struct sctp_chunk *chunk = asoc->strreset_chunk; @@ -345,8 +351,9 @@ struct sctp_chunk *sctp_process_strreset_outreq( { struct sctp_strreset_outreq *outreq = param.v; struct sctp_stream *stream = &asoc->stream; - __u16 i, nums, flags = 0, *str_p = NULL; __u32 result = SCTP_STRRESET_DENIED; + __u16 i, nums, flags = 0; + __be16 *str_p = NULL; __u32 request_seq; request_seq = ntohl(outreq->request_seq); @@ -439,8 +446,9 @@ struct sctp_chunk *sctp_process_strreset_inreq( struct sctp_stream *stream = &asoc->stream; __u32 result = SCTP_STRRESET_DENIED; struct sctp_chunk *chunk = NULL; - __u16 i, nums, *str_p; __u32 request_seq; + __u16 i, nums; + __be16 *str_p; request_seq = ntohl(inreq->request_seq); if (TSN_lt(asoc->strreset_inseq, request_seq) || @@ -769,7 +777,7 @@ struct sctp_chunk *sctp_process_strreset_resp( if (req->type == SCTP_PARAM_RESET_OUT_REQUEST) { struct sctp_strreset_outreq *outreq; - __u16 *str_p; + __be16 *str_p; outreq = (struct sctp_strreset_outreq *)req; str_p = outreq->list_of_streams; @@ -794,7 +802,7 @@ struct sctp_chunk *sctp_process_strreset_resp( nums, str_p, GFP_ATOMIC); } else if (req->type == SCTP_PARAM_RESET_IN_REQUEST) { struct sctp_strreset_inreq *inreq; - __u16 *str_p; + __be16 *str_p; /* if the result is performed, it's impossible for inreq */ if (result == SCTP_STRRESET_PERFORMED) diff --git a/net/sctp/ulpevent.c b/net/sctp/ulpevent.c index 67abc0194f30..5447228bf1a0 100644 --- a/net/sctp/ulpevent.c +++ b/net/sctp/ulpevent.c @@ -847,7 +847,7 @@ struct sctp_ulpevent *sctp_ulpevent_make_sender_dry_event( struct sctp_ulpevent *sctp_ulpevent_make_stream_reset_event( const struct sctp_association *asoc, __u16 flags, __u16 stream_num, - __u16 *stream_list, gfp_t gfp) + __be16 *stream_list, gfp_t gfp) { struct sctp_stream_reset_event *sreset; struct sctp_ulpevent *event; diff --git a/net/strparser/strparser.c b/net/strparser/strparser.c index d4ea46a5f233..c5fda15ba319 100644 --- a/net/strparser/strparser.c +++ b/net/strparser/strparser.c @@ -49,7 +49,7 @@ static void strp_abort_strp(struct strparser *strp, int err) { /* Unrecoverable error in receive */ - del_timer(&strp->msg_timer); + cancel_delayed_work(&strp->msg_timer_work); if (strp->stopped) return; @@ -68,7 +68,7 @@ static void strp_abort_strp(struct strparser *strp, int err) static void strp_start_timer(struct strparser *strp, long timeo) { if (timeo) - mod_timer(&strp->msg_timer, timeo); + mod_delayed_work(strp_wq, &strp->msg_timer_work, timeo); } /* Lower lock held */ @@ -319,7 +319,7 @@ static int __strp_recv(read_descriptor_t *desc, struct sk_buff *orig_skb, eaten += (cand_len - extra); /* Hurray, we have a new message! */ - del_timer(&strp->msg_timer); + cancel_delayed_work(&strp->msg_timer_work); strp->skb_head = NULL; STRP_STATS_INCR(strp->stats.msgs); @@ -450,9 +450,10 @@ static void strp_work(struct work_struct *w) do_strp_work(container_of(w, struct strparser, work)); } -static void strp_msg_timeout(unsigned long arg) +static void strp_msg_timeout(struct work_struct *w) { - struct strparser *strp = (struct strparser *)arg; + struct strparser *strp = container_of(w, struct strparser, + msg_timer_work.work); /* Message assembly timed out */ STRP_STATS_INCR(strp->stats.msg_timeouts); @@ -505,9 +506,7 @@ int strp_init(struct strparser *strp, struct sock *sk, strp->cb.read_sock_done = cb->read_sock_done ? : default_read_sock_done; strp->cb.abort_parser = cb->abort_parser ? : strp_abort_strp; - setup_timer(&strp->msg_timer, strp_msg_timeout, - (unsigned long)strp); - + INIT_DELAYED_WORK(&strp->msg_timer_work, strp_msg_timeout); INIT_WORK(&strp->work, strp_work); return 0; @@ -532,7 +531,7 @@ void strp_done(struct strparser *strp) { WARN_ON(!strp->stopped); - del_timer_sync(&strp->msg_timer); + cancel_delayed_work_sync(&strp->msg_timer_work); cancel_work_sync(&strp->work); if (strp->skb_head) { diff --git a/net/sunrpc/xprt.c b/net/sunrpc/xprt.c index e741ec2b4d8e..898485e3ece4 100644 --- a/net/sunrpc/xprt.c +++ b/net/sunrpc/xprt.c @@ -1333,7 +1333,7 @@ void xprt_release(struct rpc_task *task) rpc_count_iostats(task, task->tk_client->cl_metrics); spin_lock(&xprt->recv_lock); if (!list_empty(&req->rq_list)) { - list_del(&req->rq_list); + list_del_init(&req->rq_list); xprt_wait_on_pinned_rqst(req); } spin_unlock(&xprt->recv_lock); @@ -1445,6 +1445,23 @@ out: return xprt; } +static void xprt_destroy_cb(struct work_struct *work) +{ + struct rpc_xprt *xprt = + container_of(work, struct rpc_xprt, task_cleanup); + + rpc_xprt_debugfs_unregister(xprt); + rpc_destroy_wait_queue(&xprt->binding); + rpc_destroy_wait_queue(&xprt->pending); + rpc_destroy_wait_queue(&xprt->sending); + rpc_destroy_wait_queue(&xprt->backlog); + kfree(xprt->servername); + /* + * Tear down transport state and free the rpc_xprt + */ + xprt->ops->destroy(xprt); +} + /** * xprt_destroy - destroy an RPC transport, killing off all requests. * @xprt: transport to destroy @@ -1454,22 +1471,19 @@ static void xprt_destroy(struct rpc_xprt *xprt) { dprintk("RPC: destroying transport %p\n", xprt); - /* Exclude transport connect/disconnect handlers */ + /* + * Exclude transport connect/disconnect handlers and autoclose + */ wait_on_bit_lock(&xprt->state, XPRT_LOCKED, TASK_UNINTERRUPTIBLE); del_timer_sync(&xprt->timer); - rpc_xprt_debugfs_unregister(xprt); - rpc_destroy_wait_queue(&xprt->binding); - rpc_destroy_wait_queue(&xprt->pending); - rpc_destroy_wait_queue(&xprt->sending); - rpc_destroy_wait_queue(&xprt->backlog); - cancel_work_sync(&xprt->task_cleanup); - kfree(xprt->servername); /* - * Tear down transport state and free the rpc_xprt + * Destroy sockets etc from the system workqueue so they can + * safely flush receive work running on rpciod. */ - xprt->ops->destroy(xprt); + INIT_WORK(&xprt->task_cleanup, xprt_destroy_cb); + schedule_work(&xprt->task_cleanup); } static void xprt_destroy_kref(struct kref *kref) diff --git a/net/unix/diag.c b/net/unix/diag.c index 4d9679701a6d..384c84e83462 100644 --- a/net/unix/diag.c +++ b/net/unix/diag.c @@ -257,6 +257,8 @@ static int unix_diag_get_exact(struct sk_buff *in_skb, err = -ENOENT; if (sk == NULL) goto out_nosk; + if (!net_eq(sock_net(sk), net)) + goto out; err = sock_diag_check_cookie(sk, req->udiag_cookie); if (err) diff --git a/net/vmw_vsock/hyperv_transport.c b/net/vmw_vsock/hyperv_transport.c index 14ed5a344cdf..e21991fe883a 100644 --- a/net/vmw_vsock/hyperv_transport.c +++ b/net/vmw_vsock/hyperv_transport.c @@ -310,11 +310,15 @@ static void hvs_close_connection(struct vmbus_channel *chan) struct sock *sk = get_per_channel_state(chan); struct vsock_sock *vsk = vsock_sk(sk); + lock_sock(sk); + sk->sk_state = SS_UNCONNECTED; sock_set_flag(sk, SOCK_DONE); vsk->peer_shutdown |= SEND_SHUTDOWN | RCV_SHUTDOWN; sk->sk_state_change(sk); + + release_sock(sk); } static void hvs_open_connection(struct vmbus_channel *chan) @@ -344,6 +348,8 @@ static void hvs_open_connection(struct vmbus_channel *chan) if (!sk) return; + lock_sock(sk); + if ((conn_from_host && sk->sk_state != VSOCK_SS_LISTEN) || (!conn_from_host && sk->sk_state != SS_CONNECTING)) goto out; @@ -395,9 +401,7 @@ static void hvs_open_connection(struct vmbus_channel *chan) vsock_insert_connected(vnew); - lock_sock(sk); vsock_enqueue_accept(sk, new); - release_sock(sk); } else { sk->sk_state = SS_CONNECTED; sk->sk_socket->state = SS_CONNECTED; @@ -410,6 +414,8 @@ static void hvs_open_connection(struct vmbus_channel *chan) out: /* Release refcnt obtained when we called vsock_find_bound_socket() */ sock_put(sk); + + release_sock(sk); } static u32 hvs_get_local_cid(void) @@ -476,13 +482,21 @@ out: static void hvs_release(struct vsock_sock *vsk) { + struct sock *sk = sk_vsock(vsk); struct hvsock *hvs = vsk->trans; - struct vmbus_channel *chan = hvs->chan; + struct vmbus_channel *chan; + lock_sock(sk); + + sk->sk_state = SS_DISCONNECTING; + vsock_remove_sock(vsk); + + release_sock(sk); + + chan = hvs->chan; if (chan) hvs_shutdown(vsk, RCV_SHUTDOWN | SEND_SHUTDOWN); - vsock_remove_sock(vsk); } static void hvs_destruct(struct vsock_sock *vsk) diff --git a/net/wireless/sme.c b/net/wireless/sme.c index 0a49b88070d0..b6533ecbf5b1 100644 --- a/net/wireless/sme.c +++ b/net/wireless/sme.c @@ -522,11 +522,6 @@ static int cfg80211_sme_connect(struct wireless_dev *wdev, return -EOPNOTSUPP; if (wdev->current_bss) { - if (!prev_bssid) - return -EALREADY; - if (prev_bssid && - !ether_addr_equal(prev_bssid, wdev->current_bss->pub.bssid)) - return -ENOTCONN; cfg80211_unhold_bss(wdev->current_bss); cfg80211_put_bss(wdev->wiphy, &wdev->current_bss->pub); wdev->current_bss = NULL; @@ -1063,11 +1058,35 @@ int cfg80211_connect(struct cfg80211_registered_device *rdev, ASSERT_WDEV_LOCK(wdev); - if (WARN_ON(wdev->connect_keys)) { - kzfree(wdev->connect_keys); - wdev->connect_keys = NULL; + /* + * If we have an ssid_len, we're trying to connect or are + * already connected, so reject a new SSID unless it's the + * same (which is the case for re-association.) + */ + if (wdev->ssid_len && + (wdev->ssid_len != connect->ssid_len || + memcmp(wdev->ssid, connect->ssid, wdev->ssid_len))) + return -EALREADY; + + /* + * If connected, reject (re-)association unless prev_bssid + * matches the current BSSID. + */ + if (wdev->current_bss) { + if (!prev_bssid) + return -EALREADY; + if (!ether_addr_equal(prev_bssid, wdev->current_bss->pub.bssid)) + return -ENOTCONN; } + /* + * Reject if we're in the process of connecting with WEP, + * this case isn't very interesting and trying to handle + * it would make the code much more complex. + */ + if (wdev->connect_keys) + return -EINPROGRESS; + cfg80211_oper_and_ht_capa(&connect->ht_capa_mask, rdev->wiphy.ht_capa_mod_mask); @@ -1118,7 +1137,12 @@ int cfg80211_connect(struct cfg80211_registered_device *rdev, if (err) { wdev->connect_keys = NULL; - wdev->ssid_len = 0; + /* + * This could be reassoc getting refused, don't clear + * ssid_len in that case. + */ + if (!wdev->current_bss) + wdev->ssid_len = 0; return err; } @@ -1145,6 +1169,14 @@ int cfg80211_disconnect(struct cfg80211_registered_device *rdev, else if (wdev->ssid_len) err = rdev_disconnect(rdev, dev, reason); + /* + * Clear ssid_len unless we actually were fully connected, + * in which case cfg80211_disconnected() will take care of + * this later. + */ + if (!wdev->current_bss) + wdev->ssid_len = 0; + return err; } diff --git a/net/xfrm/xfrm_output.c b/net/xfrm/xfrm_output.c index 31a2e6d34dba..73ad8c8ef344 100644 --- a/net/xfrm/xfrm_output.c +++ b/net/xfrm/xfrm_output.c @@ -105,6 +105,9 @@ static int xfrm_output_one(struct sk_buff *skb, int err) if (xfrm_offload(skb)) { x->type_offload->encap(x, skb); } else { + /* Inner headers are invalid now. */ + skb->encapsulation = 0; + err = x->type->output(x, skb); if (err == -EINPROGRESS) goto out; @@ -208,7 +211,6 @@ int xfrm_output(struct sock *sk, struct sk_buff *skb) int err; secpath_reset(skb); - skb->encapsulation = 0; if (xfrm_dev_offload_ok(skb, x)) { struct sec_path *sp; diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index f06253969972..8cafb3c0a4ac 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -1573,6 +1573,14 @@ static struct dst_entry *xfrm_bundle_create(struct xfrm_policy *policy, goto put_states; } + if (!dst_prev) + dst0 = dst1; + else + /* Ref count is taken during xfrm_alloc_dst() + * No need to do dst_clone() on dst1 + */ + dst_prev->child = dst1; + if (xfrm[i]->sel.family == AF_UNSPEC) { inner_mode = xfrm_ip2inner_mode(xfrm[i], xfrm_af2proto(family)); @@ -1584,14 +1592,6 @@ static struct dst_entry *xfrm_bundle_create(struct xfrm_policy *policy, } else inner_mode = xfrm[i]->inner_mode; - if (!dst_prev) - dst0 = dst1; - else - /* Ref count is taken during xfrm_alloc_dst() - * No need to do dst_clone() on dst1 - */ - dst_prev->child = dst1; - xdst->route = dst; dst_copy_metrics(dst1, dst); @@ -2076,7 +2076,6 @@ make_dummy_bundle: xdst->num_xfrms = num_xfrms; memcpy(xdst->pols, pols, sizeof(struct xfrm_policy *) * num_pols); - dst_hold(&xdst->u.dst); return xdst; inc_error: diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c index 12213477cd3a..1f5cee2269af 100644 --- a/net/xfrm/xfrm_state.c +++ b/net/xfrm/xfrm_state.c @@ -2069,6 +2069,7 @@ int xfrm_user_policy(struct sock *sk, int optname, u8 __user *optval, int optlen if (err >= 0) { xfrm_sk_policy_insert(sk, err, pol); xfrm_pol_put(pol); + __sk_dst_reset(sk); err = 0; } diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c index b997f1395357..e44a0fed48dd 100644 --- a/net/xfrm/xfrm_user.c +++ b/net/xfrm/xfrm_user.c @@ -1693,32 +1693,34 @@ static int dump_one_policy(struct xfrm_policy *xp, int dir, int count, void *ptr static int xfrm_dump_policy_done(struct netlink_callback *cb) { - struct xfrm_policy_walk *walk = (struct xfrm_policy_walk *) &cb->args[1]; + struct xfrm_policy_walk *walk = (struct xfrm_policy_walk *)cb->args; struct net *net = sock_net(cb->skb->sk); xfrm_policy_walk_done(walk, net); return 0; } +static int xfrm_dump_policy_start(struct netlink_callback *cb) +{ + struct xfrm_policy_walk *walk = (struct xfrm_policy_walk *)cb->args; + + BUILD_BUG_ON(sizeof(*walk) > sizeof(cb->args)); + + xfrm_policy_walk_init(walk, XFRM_POLICY_TYPE_ANY); + return 0; +} + static int xfrm_dump_policy(struct sk_buff *skb, struct netlink_callback *cb) { struct net *net = sock_net(skb->sk); - struct xfrm_policy_walk *walk = (struct xfrm_policy_walk *) &cb->args[1]; + struct xfrm_policy_walk *walk = (struct xfrm_policy_walk *)cb->args; struct xfrm_dump_info info; - BUILD_BUG_ON(sizeof(struct xfrm_policy_walk) > - sizeof(cb->args) - sizeof(cb->args[0])); - info.in_skb = cb->skb; info.out_skb = skb; info.nlmsg_seq = cb->nlh->nlmsg_seq; info.nlmsg_flags = NLM_F_MULTI; - if (!cb->args[0]) { - cb->args[0] = 1; - xfrm_policy_walk_init(walk, XFRM_POLICY_TYPE_ANY); - } - (void) xfrm_policy_walk(net, walk, dump_one_policy, &info); return skb->len; @@ -2474,6 +2476,7 @@ static const struct nla_policy xfrma_spd_policy[XFRMA_SPD_MAX+1] = { static const struct xfrm_link { int (*doit)(struct sk_buff *, struct nlmsghdr *, struct nlattr **); + int (*start)(struct netlink_callback *); int (*dump)(struct sk_buff *, struct netlink_callback *); int (*done)(struct netlink_callback *); const struct nla_policy *nla_pol; @@ -2487,6 +2490,7 @@ static const struct xfrm_link { [XFRM_MSG_NEWPOLICY - XFRM_MSG_BASE] = { .doit = xfrm_add_policy }, [XFRM_MSG_DELPOLICY - XFRM_MSG_BASE] = { .doit = xfrm_get_policy }, [XFRM_MSG_GETPOLICY - XFRM_MSG_BASE] = { .doit = xfrm_get_policy, + .start = xfrm_dump_policy_start, .dump = xfrm_dump_policy, .done = xfrm_dump_policy_done }, [XFRM_MSG_ALLOCSPI - XFRM_MSG_BASE] = { .doit = xfrm_alloc_userspi }, @@ -2539,6 +2543,7 @@ static int xfrm_user_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh, { struct netlink_dump_control c = { + .start = link->start, .dump = link->dump, .done = link->done, }; diff --git a/samples/sockmap/sockmap_kern.c b/samples/sockmap/sockmap_kern.c index f9b38ef82dc2..52b0053274f4 100644 --- a/samples/sockmap/sockmap_kern.c +++ b/samples/sockmap/sockmap_kern.c @@ -62,7 +62,7 @@ int bpf_prog2(struct __sk_buff *skb) ret = 1; bpf_printk("sockmap: %d -> %d @ %d\n", lport, bpf_ntohl(rport), ret); - return bpf_sk_redirect_map(&sock_map, ret, 0); + return bpf_sk_redirect_map(skb, &sock_map, ret, 0); } SEC("sockops") diff --git a/samples/trace_events/trace-events-sample.c b/samples/trace_events/trace-events-sample.c index bc7fcf010a5b..5522692100ba 100644 --- a/samples/trace_events/trace-events-sample.c +++ b/samples/trace_events/trace-events-sample.c @@ -78,29 +78,37 @@ static int simple_thread_fn(void *arg) } static DEFINE_MUTEX(thread_mutex); +static int simple_thread_cnt; int foo_bar_reg(void) { + mutex_lock(&thread_mutex); + if (simple_thread_cnt++) + goto out; + pr_info("Starting thread for foo_bar_fn\n"); /* * We shouldn't be able to start a trace when the module is * unloading (there's other locks to prevent that). But * for consistency sake, we still take the thread_mutex. */ - mutex_lock(&thread_mutex); simple_tsk_fn = kthread_run(simple_thread_fn, NULL, "event-sample-fn"); + out: mutex_unlock(&thread_mutex); return 0; } void foo_bar_unreg(void) { - pr_info("Killing thread for foo_bar_fn\n"); - /* protect against module unloading */ mutex_lock(&thread_mutex); + if (--simple_thread_cnt) + goto out; + + pr_info("Killing thread for foo_bar_fn\n"); if (simple_tsk_fn) kthread_stop(simple_tsk_fn); simple_tsk_fn = NULL; + out: mutex_unlock(&thread_mutex); } diff --git a/scripts/Makefile.modpost b/scripts/Makefile.modpost index 16923ba4b5b1..756d14f0d763 100644 --- a/scripts/Makefile.modpost +++ b/scripts/Makefile.modpost @@ -97,7 +97,6 @@ vmlinux.o: FORCE $(call cmd,kernel-mod) # Declare generated files as targets for modpost -$(symverfile): __modpost ; $(modules:.ko=.mod.c): __modpost ; diff --git a/scripts/faddr2line b/scripts/faddr2line index 29df825d375c..2f6ce802397d 100755 --- a/scripts/faddr2line +++ b/scripts/faddr2line @@ -103,11 +103,12 @@ __faddr2line() { # Go through each of the object's symbols which match the func name. # In rare cases there might be duplicates. + file_end=$(size -Ax $objfile | awk '$1 == ".text" {print $2}') while read symbol; do local fields=($symbol) local sym_base=0x${fields[0]} local sym_type=${fields[1]} - local sym_end=0x${fields[3]} + local sym_end=${fields[3]} # calculate the size local sym_size=$(($sym_end - $sym_base)) @@ -157,7 +158,7 @@ __faddr2line() { addr2line -fpie $objfile $addr | sed "s; $dir_prefix\(\./\)*; ;" DONE=1 - done < <(nm -n $objfile | awk -v fn=$func '$3 == fn { found=1; line=$0; start=$1; next } found == 1 { found=0; print line, $1 }') + done < <(nm -n $objfile | awk -v fn=$func -v end=$file_end '$3 == fn { found=1; line=$0; start=$1; next } found == 1 { found=0; print line, "0x"$1 } END {if (found == 1) print line, end; }') } [[ $# -lt 2 ]] && usage diff --git a/scripts/kallsyms.c b/scripts/kallsyms.c index 5d554419170b..9ee9bf7fd1a2 100644 --- a/scripts/kallsyms.c +++ b/scripts/kallsyms.c @@ -158,7 +158,7 @@ static int read_symbol(FILE *in, struct sym_entry *s) else if (str[0] == '$') return -1; /* exclude debugging symbols */ - else if (stype == 'N') + else if (stype == 'N' || stype == 'n') return -1; /* include the type field in the symbol name, so that it gets diff --git a/security/apparmor/.gitignore b/security/apparmor/.gitignore index d5b291e94264..9cdec70d72b8 100644 --- a/security/apparmor/.gitignore +++ b/security/apparmor/.gitignore @@ -1,6 +1,5 @@ # # Generated include files # -net_names.h capability_names.h rlim_names.h diff --git a/security/apparmor/Makefile b/security/apparmor/Makefile index dafdd387d42b..81a34426d024 100644 --- a/security/apparmor/Makefile +++ b/security/apparmor/Makefile @@ -4,44 +4,11 @@ obj-$(CONFIG_SECURITY_APPARMOR) += apparmor.o apparmor-y := apparmorfs.o audit.o capability.o context.o ipc.o lib.o match.o \ path.o domain.o policy.o policy_unpack.o procattr.o lsm.o \ - resource.o secid.o file.o policy_ns.o label.o mount.o net.o + resource.o secid.o file.o policy_ns.o label.o mount.o apparmor-$(CONFIG_SECURITY_APPARMOR_HASH) += crypto.o -clean-files := capability_names.h rlim_names.h net_names.h +clean-files := capability_names.h rlim_names.h -# Build a lower case string table of address family names -# Transform lines from -# #define AF_LOCAL 1 /* POSIX name for AF_UNIX */ -# #define AF_INET 2 /* Internet IP Protocol */ -# to -# [1] = "local", -# [2] = "inet", -# -# and build the securityfs entries for the mapping. -# Transforms lines from -# #define AF_INET 2 /* Internet IP Protocol */ -# to -# #define AA_SFS_AF_MASK "local inet" -quiet_cmd_make-af = GEN $@ -cmd_make-af = echo "static const char *address_family_names[] = {" > $@ ;\ - sed $< >>$@ -r -n -e "/AF_MAX/d" -e "/AF_LOCAL/d" -e "/AF_ROUTE/d" -e \ - 's/^\#define[ \t]+AF_([A-Z0-9_]+)[ \t]+([0-9]+)(.*)/[\2] = "\L\1",/p';\ - echo "};" >> $@ ;\ - printf '%s' '\#define AA_SFS_AF_MASK "' >> $@ ;\ - sed -r -n -e "/AF_MAX/d" -e "/AF_LOCAL/d" -e "/AF_ROUTE/d" -e \ - 's/^\#define[ \t]+AF_([A-Z0-9_]+)[ \t]+([0-9]+)(.*)/\L\1/p'\ - $< | tr '\n' ' ' | sed -e 's/ $$/"\n/' >> $@ - -# Build a lower case string table of sock type names -# Transform lines from -# SOCK_STREAM = 1, -# to -# [1] = "stream", -quiet_cmd_make-sock = GEN $@ -cmd_make-sock = echo "static const char *sock_type_names[] = {" >> $@ ;\ - sed $^ >>$@ -r -n \ - -e 's/^\tSOCK_([A-Z0-9_]+)[\t]+=[ \t]+([0-9]+)(.*)/[\2] = "\L\1",/p';\ - echo "};" >> $@ # Build a lower case string table of capability names # Transforms lines from @@ -94,7 +61,6 @@ cmd_make-rlim = echo "static const char *const rlim_names[RLIM_NLIMITS] = {" \ tr '\n' ' ' | sed -e 's/ $$/"\n/' >> $@ $(obj)/capability.o : $(obj)/capability_names.h -$(obj)/net.o : $(obj)/net_names.h $(obj)/resource.o : $(obj)/rlim_names.h $(obj)/capability_names.h : $(srctree)/include/uapi/linux/capability.h \ $(src)/Makefile @@ -102,8 +68,3 @@ $(obj)/capability_names.h : $(srctree)/include/uapi/linux/capability.h \ $(obj)/rlim_names.h : $(srctree)/include/uapi/asm-generic/resource.h \ $(src)/Makefile $(call cmd,make-rlim) -$(obj)/net_names.h : $(srctree)/include/linux/socket.h \ - $(srctree)/include/linux/net.h \ - $(src)/Makefile - $(call cmd,make-af) - $(call cmd,make-sock) diff --git a/security/apparmor/apparmorfs.c b/security/apparmor/apparmorfs.c index 518d5928661b..caaf51dda648 100644 --- a/security/apparmor/apparmorfs.c +++ b/security/apparmor/apparmorfs.c @@ -2202,7 +2202,6 @@ static struct aa_sfs_entry aa_sfs_entry_features[] = { AA_SFS_DIR("policy", aa_sfs_entry_policy), AA_SFS_DIR("domain", aa_sfs_entry_domain), AA_SFS_DIR("file", aa_sfs_entry_file), - AA_SFS_DIR("network", aa_sfs_entry_network), AA_SFS_DIR("mount", aa_sfs_entry_mount), AA_SFS_DIR("namespaces", aa_sfs_entry_ns), AA_SFS_FILE_U64("capability", VFS_CAP_FLAGS_MASK), diff --git a/security/apparmor/file.c b/security/apparmor/file.c index db80221891c6..3382518b87fa 100644 --- a/security/apparmor/file.c +++ b/security/apparmor/file.c @@ -21,7 +21,6 @@ #include "include/context.h" #include "include/file.h" #include "include/match.h" -#include "include/net.h" #include "include/path.h" #include "include/policy.h" #include "include/label.h" @@ -567,32 +566,6 @@ static int __file_path_perm(const char *op, struct aa_label *label, return error; } -static int __file_sock_perm(const char *op, struct aa_label *label, - struct aa_label *flabel, struct file *file, - u32 request, u32 denied) -{ - struct socket *sock = (struct socket *) file->private_data; - int error; - - AA_BUG(!sock); - - /* revalidation due to label out of date. No revocation at this time */ - if (!denied && aa_label_is_subset(flabel, label)) - return 0; - - /* TODO: improve to skip profiles cached in flabel */ - error = aa_sock_file_perm(label, op, request, sock); - if (denied) { - /* TODO: improve to skip profiles checked above */ - /* check every profile in file label to is cached */ - last_error(error, aa_sock_file_perm(flabel, op, request, sock)); - } - if (!error) - update_file_ctx(file_ctx(file), label, request); - - return error; -} - /** * aa_file_perm - do permission revalidation check & audit for @file * @op: operation being checked @@ -637,9 +610,6 @@ int aa_file_perm(const char *op, struct aa_label *label, struct file *file, error = __file_path_perm(op, label, flabel, file, request, denied); - else if (S_ISSOCK(file_inode(file)->i_mode)) - error = __file_sock_perm(op, label, flabel, file, request, - denied); done: rcu_read_unlock(); diff --git a/security/apparmor/include/audit.h b/security/apparmor/include/audit.h index ff4316e1068d..620e81169659 100644 --- a/security/apparmor/include/audit.h +++ b/security/apparmor/include/audit.h @@ -121,29 +121,21 @@ struct apparmor_audit_data { /* these entries require a custom callback fn */ struct { struct aa_label *peer; - union { - struct { - kuid_t ouid; - const char *target; - } fs; - struct { - int type, protocol; - struct sock *peer_sk; - void *addr; - int addrlen; - } net; - int signal; - struct { - int rlim; - unsigned long max; - } rlim; - }; + struct { + const char *target; + kuid_t ouid; + } fs; }; struct { struct aa_profile *profile; const char *ns; long pos; } iface; + int signal; + struct { + int rlim; + unsigned long max; + } rlim; struct { const char *src_name; const char *type; diff --git a/security/apparmor/include/net.h b/security/apparmor/include/net.h deleted file mode 100644 index 140c8efcf364..000000000000 --- a/security/apparmor/include/net.h +++ /dev/null @@ -1,114 +0,0 @@ -/* - * AppArmor security module - * - * This file contains AppArmor network mediation definitions. - * - * Copyright (C) 1998-2008 Novell/SUSE - * Copyright 2009-2017 Canonical Ltd. - * - * 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, version 2 of the - * License. - */ - -#ifndef __AA_NET_H -#define __AA_NET_H - -#include <net/sock.h> -#include <linux/path.h> - -#include "apparmorfs.h" -#include "label.h" -#include "perms.h" -#include "policy.h" - -#define AA_MAY_SEND AA_MAY_WRITE -#define AA_MAY_RECEIVE AA_MAY_READ - -#define AA_MAY_SHUTDOWN AA_MAY_DELETE - -#define AA_MAY_CONNECT AA_MAY_OPEN -#define AA_MAY_ACCEPT 0x00100000 - -#define AA_MAY_BIND 0x00200000 -#define AA_MAY_LISTEN 0x00400000 - -#define AA_MAY_SETOPT 0x01000000 -#define AA_MAY_GETOPT 0x02000000 - -#define NET_PERMS_MASK (AA_MAY_SEND | AA_MAY_RECEIVE | AA_MAY_CREATE | \ - AA_MAY_SHUTDOWN | AA_MAY_BIND | AA_MAY_LISTEN | \ - AA_MAY_CONNECT | AA_MAY_ACCEPT | AA_MAY_SETATTR | \ - AA_MAY_GETATTR | AA_MAY_SETOPT | AA_MAY_GETOPT) - -#define NET_FS_PERMS (AA_MAY_SEND | AA_MAY_RECEIVE | AA_MAY_CREATE | \ - AA_MAY_SHUTDOWN | AA_MAY_CONNECT | AA_MAY_RENAME |\ - AA_MAY_SETATTR | AA_MAY_GETATTR | AA_MAY_CHMOD | \ - AA_MAY_CHOWN | AA_MAY_CHGRP | AA_MAY_LOCK | \ - AA_MAY_MPROT) - -#define NET_PEER_MASK (AA_MAY_SEND | AA_MAY_RECEIVE | AA_MAY_CONNECT | \ - AA_MAY_ACCEPT) -struct aa_sk_ctx { - struct aa_label *label; - struct aa_label *peer; - struct path path; -}; - -#define SK_CTX(X) ((X)->sk_security) -#define SOCK_ctx(X) SOCK_INODE(X)->i_security -#define DEFINE_AUDIT_NET(NAME, OP, SK, F, T, P) \ - struct lsm_network_audit NAME ## _net = { .sk = (SK), \ - .family = (F)}; \ - DEFINE_AUDIT_DATA(NAME, \ - ((SK) && (F) != AF_UNIX) ? LSM_AUDIT_DATA_NET : \ - LSM_AUDIT_DATA_NONE, \ - OP); \ - NAME.u.net = &(NAME ## _net); \ - aad(&NAME)->net.type = (T); \ - aad(&NAME)->net.protocol = (P) - -#define DEFINE_AUDIT_SK(NAME, OP, SK) \ - DEFINE_AUDIT_NET(NAME, OP, SK, (SK)->sk_family, (SK)->sk_type, \ - (SK)->sk_protocol) - -/* struct aa_net - network confinement data - * @allow: basic network families permissions - * @audit: which network permissions to force audit - * @quiet: which network permissions to quiet rejects - */ -struct aa_net { - u16 allow[AF_MAX]; - u16 audit[AF_MAX]; - u16 quiet[AF_MAX]; -}; - - -extern struct aa_sfs_entry aa_sfs_entry_network[]; - -void audit_net_cb(struct audit_buffer *ab, void *va); -int aa_profile_af_perm(struct aa_profile *profile, struct common_audit_data *sa, - u32 request, u16 family, int type); -int aa_af_perm(struct aa_label *label, const char *op, u32 request, u16 family, - int type, int protocol); -static inline int aa_profile_af_sk_perm(struct aa_profile *profile, - struct common_audit_data *sa, - u32 request, - struct sock *sk) -{ - return aa_profile_af_perm(profile, sa, request, sk->sk_family, - sk->sk_type); -} -int aa_sk_perm(const char *op, u32 request, struct sock *sk); - -int aa_sock_file_perm(struct aa_label *label, const char *op, u32 request, - struct socket *sock); - - -static inline void aa_free_net_rules(struct aa_net *new) -{ - /* NOP */ -} - -#endif /* __AA_NET_H */ diff --git a/security/apparmor/include/perms.h b/security/apparmor/include/perms.h index af04d5a7d73d..2b27bb79aec4 100644 --- a/security/apparmor/include/perms.h +++ b/security/apparmor/include/perms.h @@ -135,10 +135,9 @@ extern struct aa_perms allperms; void aa_perm_mask_to_str(char *str, const char *chrs, u32 mask); -void aa_audit_perm_names(struct audit_buffer *ab, const char * const *names, - u32 mask); +void aa_audit_perm_names(struct audit_buffer *ab, const char **names, u32 mask); void aa_audit_perm_mask(struct audit_buffer *ab, u32 mask, const char *chrs, - u32 chrsmask, const char * const *names, u32 namesmask); + u32 chrsmask, const char **names, u32 namesmask); void aa_apply_modes_to_perms(struct aa_profile *profile, struct aa_perms *perms); void aa_compute_perms(struct aa_dfa *dfa, unsigned int state, diff --git a/security/apparmor/include/policy.h b/security/apparmor/include/policy.h index 4364088a0b9e..17fe41a9cac3 100644 --- a/security/apparmor/include/policy.h +++ b/security/apparmor/include/policy.h @@ -30,7 +30,6 @@ #include "file.h" #include "lib.h" #include "label.h" -#include "net.h" #include "perms.h" #include "resource.h" @@ -112,7 +111,6 @@ struct aa_data { * @policy: general match rules governing policy * @file: The set of rules governing basic file access and domain transitions * @caps: capabilities for the profile - * @net: network controls for the profile * @rlimits: rlimits for the profile * * @dents: dentries for the profiles file entries in apparmorfs @@ -150,7 +148,6 @@ struct aa_profile { struct aa_policydb policy; struct aa_file_rules file; struct aa_caps caps; - struct aa_net net; struct aa_rlimit rlimits; struct aa_loaddata *rawdata; @@ -223,16 +220,6 @@ static inline unsigned int PROFILE_MEDIATES_SAFE(struct aa_profile *profile, return 0; } -static inline unsigned int PROFILE_MEDIATES_AF(struct aa_profile *profile, - u16 AF) { - unsigned int state = PROFILE_MEDIATES(profile, AA_CLASS_NET); - u16 be_af = cpu_to_be16(AF); - - if (!state) - return 0; - return aa_dfa_match_len(profile->policy.dfa, state, (char *) &be_af, 2); -} - /** * aa_get_profile - increment refcount on profile @p * @p: profile (MAYBE NULL) diff --git a/security/apparmor/lib.c b/security/apparmor/lib.c index 8818621b5d95..08ca26bcca77 100644 --- a/security/apparmor/lib.c +++ b/security/apparmor/lib.c @@ -211,8 +211,7 @@ void aa_perm_mask_to_str(char *str, const char *chrs, u32 mask) *str = '\0'; } -void aa_audit_perm_names(struct audit_buffer *ab, const char * const *names, - u32 mask) +void aa_audit_perm_names(struct audit_buffer *ab, const char **names, u32 mask) { const char *fmt = "%s"; unsigned int i, perm = 1; @@ -230,7 +229,7 @@ void aa_audit_perm_names(struct audit_buffer *ab, const char * const *names, } void aa_audit_perm_mask(struct audit_buffer *ab, u32 mask, const char *chrs, - u32 chrsmask, const char * const *names, u32 namesmask) + u32 chrsmask, const char **names, u32 namesmask) { char str[33]; diff --git a/security/apparmor/lsm.c b/security/apparmor/lsm.c index 72b915dfcaf7..1346ee5be04f 100644 --- a/security/apparmor/lsm.c +++ b/security/apparmor/lsm.c @@ -33,7 +33,6 @@ #include "include/context.h" #include "include/file.h" #include "include/ipc.h" -#include "include/net.h" #include "include/path.h" #include "include/label.h" #include "include/policy.h" @@ -737,368 +736,6 @@ static int apparmor_task_kill(struct task_struct *target, struct siginfo *info, return error; } -/** - * apparmor_sk_alloc_security - allocate and attach the sk_security field - */ -static int apparmor_sk_alloc_security(struct sock *sk, int family, gfp_t flags) -{ - struct aa_sk_ctx *ctx; - - ctx = kzalloc(sizeof(*ctx), flags); - if (!ctx) - return -ENOMEM; - - SK_CTX(sk) = ctx; - - return 0; -} - -/** - * apparmor_sk_free_security - free the sk_security field - */ -static void apparmor_sk_free_security(struct sock *sk) -{ - struct aa_sk_ctx *ctx = SK_CTX(sk); - - SK_CTX(sk) = NULL; - aa_put_label(ctx->label); - aa_put_label(ctx->peer); - path_put(&ctx->path); - kfree(ctx); -} - -/** - * apparmor_clone_security - clone the sk_security field - */ -static void apparmor_sk_clone_security(const struct sock *sk, - struct sock *newsk) -{ - struct aa_sk_ctx *ctx = SK_CTX(sk); - struct aa_sk_ctx *new = SK_CTX(newsk); - - new->label = aa_get_label(ctx->label); - new->peer = aa_get_label(ctx->peer); - new->path = ctx->path; - path_get(&new->path); -} - -static int aa_sock_create_perm(struct aa_label *label, int family, int type, - int protocol) -{ - AA_BUG(!label); - AA_BUG(in_interrupt()); - - return aa_af_perm(label, OP_CREATE, AA_MAY_CREATE, family, type, - protocol); -} - - -/** - * apparmor_socket_create - check perms before creating a new socket - */ -static int apparmor_socket_create(int family, int type, int protocol, int kern) -{ - struct aa_label *label; - int error = 0; - - label = begin_current_label_crit_section(); - if (!(kern || unconfined(label))) - error = aa_sock_create_perm(label, family, type, protocol); - end_current_label_crit_section(label); - - return error; -} - -/** - * apparmor_socket_post_create - setup the per-socket security struct - * - * Note: - * - kernel sockets currently labeled unconfined but we may want to - * move to a special kernel label - * - socket may not have sk here if created with sock_create_lite or - * sock_alloc. These should be accept cases which will be handled in - * sock_graft. - */ -static int apparmor_socket_post_create(struct socket *sock, int family, - int type, int protocol, int kern) -{ - struct aa_label *label; - - if (kern) { - struct aa_ns *ns = aa_get_current_ns(); - - label = aa_get_label(ns_unconfined(ns)); - aa_put_ns(ns); - } else - label = aa_get_current_label(); - - if (sock->sk) { - struct aa_sk_ctx *ctx = SK_CTX(sock->sk); - - aa_put_label(ctx->label); - ctx->label = aa_get_label(label); - } - aa_put_label(label); - - return 0; -} - -/** - * apparmor_socket_bind - check perms before bind addr to socket - */ -static int apparmor_socket_bind(struct socket *sock, - struct sockaddr *address, int addrlen) -{ - AA_BUG(!sock); - AA_BUG(!sock->sk); - AA_BUG(!address); - AA_BUG(in_interrupt()); - - return aa_sk_perm(OP_BIND, AA_MAY_BIND, sock->sk); -} - -/** - * apparmor_socket_connect - check perms before connecting @sock to @address - */ -static int apparmor_socket_connect(struct socket *sock, - struct sockaddr *address, int addrlen) -{ - AA_BUG(!sock); - AA_BUG(!sock->sk); - AA_BUG(!address); - AA_BUG(in_interrupt()); - - return aa_sk_perm(OP_CONNECT, AA_MAY_CONNECT, sock->sk); -} - -/** - * apparmor_socket_list - check perms before allowing listen - */ -static int apparmor_socket_listen(struct socket *sock, int backlog) -{ - AA_BUG(!sock); - AA_BUG(!sock->sk); - AA_BUG(in_interrupt()); - - return aa_sk_perm(OP_LISTEN, AA_MAY_LISTEN, sock->sk); -} - -/** - * apparmor_socket_accept - check perms before accepting a new connection. - * - * Note: while @newsock is created and has some information, the accept - * has not been done. - */ -static int apparmor_socket_accept(struct socket *sock, struct socket *newsock) -{ - AA_BUG(!sock); - AA_BUG(!sock->sk); - AA_BUG(!newsock); - AA_BUG(in_interrupt()); - - return aa_sk_perm(OP_ACCEPT, AA_MAY_ACCEPT, sock->sk); -} - -static int aa_sock_msg_perm(const char *op, u32 request, struct socket *sock, - struct msghdr *msg, int size) -{ - AA_BUG(!sock); - AA_BUG(!sock->sk); - AA_BUG(!msg); - AA_BUG(in_interrupt()); - - return aa_sk_perm(op, request, sock->sk); -} - -/** - * apparmor_socket_sendmsg - check perms before sending msg to another socket - */ -static int apparmor_socket_sendmsg(struct socket *sock, - struct msghdr *msg, int size) -{ - return aa_sock_msg_perm(OP_SENDMSG, AA_MAY_SEND, sock, msg, size); -} - -/** - * apparmor_socket_recvmsg - check perms before receiving a message - */ -static int apparmor_socket_recvmsg(struct socket *sock, - struct msghdr *msg, int size, int flags) -{ - return aa_sock_msg_perm(OP_RECVMSG, AA_MAY_RECEIVE, sock, msg, size); -} - -/* revaliation, get/set attr, shutdown */ -static int aa_sock_perm(const char *op, u32 request, struct socket *sock) -{ - AA_BUG(!sock); - AA_BUG(!sock->sk); - AA_BUG(in_interrupt()); - - return aa_sk_perm(op, request, sock->sk); -} - -/** - * apparmor_socket_getsockname - check perms before getting the local address - */ -static int apparmor_socket_getsockname(struct socket *sock) -{ - return aa_sock_perm(OP_GETSOCKNAME, AA_MAY_GETATTR, sock); -} - -/** - * apparmor_socket_getpeername - check perms before getting remote address - */ -static int apparmor_socket_getpeername(struct socket *sock) -{ - return aa_sock_perm(OP_GETPEERNAME, AA_MAY_GETATTR, sock); -} - -/* revaliation, get/set attr, opt */ -static int aa_sock_opt_perm(const char *op, u32 request, struct socket *sock, - int level, int optname) -{ - AA_BUG(!sock); - AA_BUG(!sock->sk); - AA_BUG(in_interrupt()); - - return aa_sk_perm(op, request, sock->sk); -} - -/** - * apparmor_getsockopt - check perms before getting socket options - */ -static int apparmor_socket_getsockopt(struct socket *sock, int level, - int optname) -{ - return aa_sock_opt_perm(OP_GETSOCKOPT, AA_MAY_GETOPT, sock, - level, optname); -} - -/** - * apparmor_setsockopt - check perms before setting socket options - */ -static int apparmor_socket_setsockopt(struct socket *sock, int level, - int optname) -{ - return aa_sock_opt_perm(OP_SETSOCKOPT, AA_MAY_SETOPT, sock, - level, optname); -} - -/** - * apparmor_socket_shutdown - check perms before shutting down @sock conn - */ -static int apparmor_socket_shutdown(struct socket *sock, int how) -{ - return aa_sock_perm(OP_SHUTDOWN, AA_MAY_SHUTDOWN, sock); -} - -/** - * apparmor_socket_sock_recv_skb - check perms before associating skb to sk - * - * Note: can not sleep may be called with locks held - * - * dont want protocol specific in __skb_recv_datagram() - * to deny an incoming connection socket_sock_rcv_skb() - */ -static int apparmor_socket_sock_rcv_skb(struct sock *sk, struct sk_buff *skb) -{ - return 0; -} - - -static struct aa_label *sk_peer_label(struct sock *sk) -{ - struct aa_sk_ctx *ctx = SK_CTX(sk); - - if (ctx->peer) - return ctx->peer; - - return ERR_PTR(-ENOPROTOOPT); -} - -/** - * apparmor_socket_getpeersec_stream - get security context of peer - * - * Note: for tcp only valid if using ipsec or cipso on lan - */ -static int apparmor_socket_getpeersec_stream(struct socket *sock, - char __user *optval, - int __user *optlen, - unsigned int len) -{ - char *name; - int slen, error = 0; - struct aa_label *label; - struct aa_label *peer; - - label = begin_current_label_crit_section(); - peer = sk_peer_label(sock->sk); - if (IS_ERR(peer)) { - error = PTR_ERR(peer); - goto done; - } - slen = aa_label_asxprint(&name, labels_ns(label), peer, - FLAG_SHOW_MODE | FLAG_VIEW_SUBNS | - FLAG_HIDDEN_UNCONFINED, GFP_KERNEL); - /* don't include terminating \0 in slen, it breaks some apps */ - if (slen < 0) { - error = -ENOMEM; - } else { - if (slen > len) { - error = -ERANGE; - } else if (copy_to_user(optval, name, slen)) { - error = -EFAULT; - goto out; - } - if (put_user(slen, optlen)) - error = -EFAULT; -out: - kfree(name); - - } - -done: - end_current_label_crit_section(label); - - return error; -} - -/** - * apparmor_socket_getpeersec_dgram - get security label of packet - * @sock: the peer socket - * @skb: packet data - * @secid: pointer to where to put the secid of the packet - * - * Sets the netlabel socket state on sk from parent - */ -static int apparmor_socket_getpeersec_dgram(struct socket *sock, - struct sk_buff *skb, u32 *secid) - -{ - /* TODO: requires secid support */ - return -ENOPROTOOPT; -} - -/** - * apparmor_sock_graft - Initialize newly created socket - * @sk: child sock - * @parent: parent socket - * - * Note: could set off of SOCK_CTX(parent) but need to track inode and we can - * just set sk security information off of current creating process label - * Labeling of sk for accept case - probably should be sock based - * instead of task, because of the case where an implicitly labeled - * socket is shared by different tasks. - */ -static void apparmor_sock_graft(struct sock *sk, struct socket *parent) -{ - struct aa_sk_ctx *ctx = SK_CTX(sk); - - if (!ctx->label) - ctx->label = aa_get_current_label(); -} - static struct security_hook_list apparmor_hooks[] __lsm_ro_after_init = { LSM_HOOK_INIT(ptrace_access_check, apparmor_ptrace_access_check), LSM_HOOK_INIT(ptrace_traceme, apparmor_ptrace_traceme), @@ -1133,30 +770,6 @@ static struct security_hook_list apparmor_hooks[] __lsm_ro_after_init = { LSM_HOOK_INIT(getprocattr, apparmor_getprocattr), LSM_HOOK_INIT(setprocattr, apparmor_setprocattr), - LSM_HOOK_INIT(sk_alloc_security, apparmor_sk_alloc_security), - LSM_HOOK_INIT(sk_free_security, apparmor_sk_free_security), - LSM_HOOK_INIT(sk_clone_security, apparmor_sk_clone_security), - - LSM_HOOK_INIT(socket_create, apparmor_socket_create), - LSM_HOOK_INIT(socket_post_create, apparmor_socket_post_create), - LSM_HOOK_INIT(socket_bind, apparmor_socket_bind), - LSM_HOOK_INIT(socket_connect, apparmor_socket_connect), - LSM_HOOK_INIT(socket_listen, apparmor_socket_listen), - LSM_HOOK_INIT(socket_accept, apparmor_socket_accept), - LSM_HOOK_INIT(socket_sendmsg, apparmor_socket_sendmsg), - LSM_HOOK_INIT(socket_recvmsg, apparmor_socket_recvmsg), - LSM_HOOK_INIT(socket_getsockname, apparmor_socket_getsockname), - LSM_HOOK_INIT(socket_getpeername, apparmor_socket_getpeername), - LSM_HOOK_INIT(socket_getsockopt, apparmor_socket_getsockopt), - LSM_HOOK_INIT(socket_setsockopt, apparmor_socket_setsockopt), - LSM_HOOK_INIT(socket_shutdown, apparmor_socket_shutdown), - LSM_HOOK_INIT(socket_sock_rcv_skb, apparmor_socket_sock_rcv_skb), - LSM_HOOK_INIT(socket_getpeersec_stream, - apparmor_socket_getpeersec_stream), - LSM_HOOK_INIT(socket_getpeersec_dgram, - apparmor_socket_getpeersec_dgram), - LSM_HOOK_INIT(sock_graft, apparmor_sock_graft), - LSM_HOOK_INIT(cred_alloc_blank, apparmor_cred_alloc_blank), LSM_HOOK_INIT(cred_free, apparmor_cred_free), LSM_HOOK_INIT(cred_prepare, apparmor_cred_prepare), diff --git a/security/apparmor/net.c b/security/apparmor/net.c deleted file mode 100644 index 33d54435f8d6..000000000000 --- a/security/apparmor/net.c +++ /dev/null @@ -1,184 +0,0 @@ -/* - * AppArmor security module - * - * This file contains AppArmor network mediation - * - * Copyright (C) 1998-2008 Novell/SUSE - * Copyright 2009-2017 Canonical Ltd. - * - * 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, version 2 of the - * License. - */ - -#include "include/apparmor.h" -#include "include/audit.h" -#include "include/context.h" -#include "include/label.h" -#include "include/net.h" -#include "include/policy.h" - -#include "net_names.h" - - -struct aa_sfs_entry aa_sfs_entry_network[] = { - AA_SFS_FILE_STRING("af_mask", AA_SFS_AF_MASK), - { } -}; - -static const char * const net_mask_names[] = { - "unknown", - "send", - "receive", - "unknown", - - "create", - "shutdown", - "connect", - "unknown", - - "setattr", - "getattr", - "setcred", - "getcred", - - "chmod", - "chown", - "chgrp", - "lock", - - "mmap", - "mprot", - "unknown", - "unknown", - - "accept", - "bind", - "listen", - "unknown", - - "setopt", - "getopt", - "unknown", - "unknown", - - "unknown", - "unknown", - "unknown", - "unknown", -}; - - -/* audit callback for net specific fields */ -void audit_net_cb(struct audit_buffer *ab, void *va) -{ - struct common_audit_data *sa = va; - - audit_log_format(ab, " family="); - if (address_family_names[sa->u.net->family]) - audit_log_string(ab, address_family_names[sa->u.net->family]); - else - audit_log_format(ab, "\"unknown(%d)\"", sa->u.net->family); - audit_log_format(ab, " sock_type="); - if (sock_type_names[aad(sa)->net.type]) - audit_log_string(ab, sock_type_names[aad(sa)->net.type]); - else - audit_log_format(ab, "\"unknown(%d)\"", aad(sa)->net.type); - audit_log_format(ab, " protocol=%d", aad(sa)->net.protocol); - - if (aad(sa)->request & NET_PERMS_MASK) { - audit_log_format(ab, " requested_mask="); - aa_audit_perm_mask(ab, aad(sa)->request, NULL, 0, - net_mask_names, NET_PERMS_MASK); - - if (aad(sa)->denied & NET_PERMS_MASK) { - audit_log_format(ab, " denied_mask="); - aa_audit_perm_mask(ab, aad(sa)->denied, NULL, 0, - net_mask_names, NET_PERMS_MASK); - } - } - if (aad(sa)->peer) { - audit_log_format(ab, " peer="); - aa_label_xaudit(ab, labels_ns(aad(sa)->label), aad(sa)->peer, - FLAGS_NONE, GFP_ATOMIC); - } -} - - -/* Generic af perm */ -int aa_profile_af_perm(struct aa_profile *profile, struct common_audit_data *sa, - u32 request, u16 family, int type) -{ - struct aa_perms perms = { }; - - AA_BUG(family >= AF_MAX); - AA_BUG(type < 0 || type >= SOCK_MAX); - - if (profile_unconfined(profile)) - return 0; - - perms.allow = (profile->net.allow[family] & (1 << type)) ? - ALL_PERMS_MASK : 0; - perms.audit = (profile->net.audit[family] & (1 << type)) ? - ALL_PERMS_MASK : 0; - perms.quiet = (profile->net.quiet[family] & (1 << type)) ? - ALL_PERMS_MASK : 0; - aa_apply_modes_to_perms(profile, &perms); - - return aa_check_perms(profile, &perms, request, sa, audit_net_cb); -} - -int aa_af_perm(struct aa_label *label, const char *op, u32 request, u16 family, - int type, int protocol) -{ - struct aa_profile *profile; - DEFINE_AUDIT_NET(sa, op, NULL, family, type, protocol); - - return fn_for_each_confined(label, profile, - aa_profile_af_perm(profile, &sa, request, family, - type)); -} - -static int aa_label_sk_perm(struct aa_label *label, const char *op, u32 request, - struct sock *sk) -{ - struct aa_profile *profile; - DEFINE_AUDIT_SK(sa, op, sk); - - AA_BUG(!label); - AA_BUG(!sk); - - if (unconfined(label)) - return 0; - - return fn_for_each_confined(label, profile, - aa_profile_af_sk_perm(profile, &sa, request, sk)); -} - -int aa_sk_perm(const char *op, u32 request, struct sock *sk) -{ - struct aa_label *label; - int error; - - AA_BUG(!sk); - AA_BUG(in_interrupt()); - - /* TODO: switch to begin_current_label ???? */ - label = begin_current_label_crit_section(); - error = aa_label_sk_perm(label, op, request, sk); - end_current_label_crit_section(label); - - return error; -} - - -int aa_sock_file_perm(struct aa_label *label, const char *op, u32 request, - struct socket *sock) -{ - AA_BUG(!label); - AA_BUG(!sock); - AA_BUG(!sock->sk); - - return aa_label_sk_perm(label, op, request, sock->sk); -} diff --git a/security/apparmor/policy_unpack.c b/security/apparmor/policy_unpack.c index 5a2aec358322..4ede87c30f8b 100644 --- a/security/apparmor/policy_unpack.c +++ b/security/apparmor/policy_unpack.c @@ -275,19 +275,6 @@ fail: return 0; } -static bool unpack_u16(struct aa_ext *e, u16 *data, const char *name) -{ - if (unpack_nameX(e, AA_U16, name)) { - if (!inbounds(e, sizeof(u16))) - return 0; - if (data) - *data = le16_to_cpu(get_unaligned((__le16 *) e->pos)); - e->pos += sizeof(u16); - return 1; - } - return 0; -} - static bool unpack_u32(struct aa_ext *e, u32 *data, const char *name) { if (unpack_nameX(e, AA_U32, name)) { @@ -597,7 +584,7 @@ static struct aa_profile *unpack_profile(struct aa_ext *e, char **ns_name) struct aa_profile *profile = NULL; const char *tmpname, *tmpns = NULL, *name = NULL; const char *info = "failed to unpack profile"; - size_t size = 0, ns_len; + size_t ns_len; struct rhashtable_params params = { 0 }; char *key = NULL; struct aa_data *data; @@ -730,38 +717,6 @@ static struct aa_profile *unpack_profile(struct aa_ext *e, char **ns_name) goto fail; } - size = unpack_array(e, "net_allowed_af"); - if (size) { - - for (i = 0; i < size; i++) { - /* discard extraneous rules that this kernel will - * never request - */ - if (i >= AF_MAX) { - u16 tmp; - - if (!unpack_u16(e, &tmp, NULL) || - !unpack_u16(e, &tmp, NULL) || - !unpack_u16(e, &tmp, NULL)) - goto fail; - continue; - } - if (!unpack_u16(e, &profile->net.allow[i], NULL)) - goto fail; - if (!unpack_u16(e, &profile->net.audit[i], NULL)) - goto fail; - if (!unpack_u16(e, &profile->net.quiet[i], NULL)) - goto fail; - } - if (!unpack_nameX(e, AA_ARRAYEND, NULL)) - goto fail; - } - if (VERSION_LT(e->version, v7)) { - /* pre v7 policy always allowed these */ - profile->net.allow[AF_UNIX] = 0xffff; - profile->net.allow[AF_NETLINK] = 0xffff; - } - if (unpack_nameX(e, AA_STRUCT, "policydb")) { /* generic policy dfa - optional and may be NULL */ info = "failed to unpack policydb"; diff --git a/security/commoncap.c b/security/commoncap.c index c25e0d27537f..fc46f5b85251 100644 --- a/security/commoncap.c +++ b/security/commoncap.c @@ -585,13 +585,14 @@ int get_vfs_caps_from_disk(const struct dentry *dentry, struct cpu_vfs_cap_data struct vfs_ns_cap_data data, *nscaps = &data; struct vfs_cap_data *caps = (struct vfs_cap_data *) &data; kuid_t rootkuid; - struct user_namespace *fs_ns = inode->i_sb->s_user_ns; + struct user_namespace *fs_ns; memset(cpu_caps, 0, sizeof(struct cpu_vfs_cap_data)); if (!inode) return -ENODATA; + fs_ns = inode->i_sb->s_user_ns; size = __vfs_getxattr((struct dentry *)dentry, inode, XATTR_NAME_CAPS, &data, XATTR_CAPS_SZ); if (size == -ENODATA || size == -EOPNOTSUPP) diff --git a/security/keys/Kconfig b/security/keys/Kconfig index 91eafada3164..6462e6654ccf 100644 --- a/security/keys/Kconfig +++ b/security/keys/Kconfig @@ -45,6 +45,7 @@ config BIG_KEYS bool "Large payload keys" depends on KEYS depends on TMPFS + select CRYPTO select CRYPTO_AES select CRYPTO_GCM help diff --git a/security/keys/big_key.c b/security/keys/big_key.c index e607830b6154..929e14978c42 100644 --- a/security/keys/big_key.c +++ b/security/keys/big_key.c @@ -247,7 +247,7 @@ void big_key_revoke(struct key *key) /* clear the quota */ key_payload_reserve(key, 0); - if (key_is_instantiated(key) && + if (key_is_positive(key) && (size_t)key->payload.data[big_key_len] > BIG_KEY_FILE_THRESHOLD) vfs_truncate(path, 0); } @@ -279,7 +279,7 @@ void big_key_describe(const struct key *key, struct seq_file *m) seq_puts(m, key->description); - if (key_is_instantiated(key)) + if (key_is_positive(key)) seq_printf(m, ": %zu [%s]", datalen, datalen > BIG_KEY_FILE_THRESHOLD ? "file" : "buff"); diff --git a/security/keys/encrypted-keys/encrypted.c b/security/keys/encrypted-keys/encrypted.c index 69855ba0d3b3..d92cbf9687c3 100644 --- a/security/keys/encrypted-keys/encrypted.c +++ b/security/keys/encrypted-keys/encrypted.c @@ -309,6 +309,13 @@ static struct key *request_user_key(const char *master_desc, const u8 **master_k down_read(&ukey->sem); upayload = user_key_payload_locked(ukey); + if (!upayload) { + /* key was revoked before we acquired its semaphore */ + up_read(&ukey->sem); + key_put(ukey); + ukey = ERR_PTR(-EKEYREVOKED); + goto error; + } *master_key = upayload->data; *master_keylen = upayload->datalen; error: @@ -847,7 +854,7 @@ static int encrypted_update(struct key *key, struct key_preparsed_payload *prep) size_t datalen = prep->datalen; int ret = 0; - if (test_bit(KEY_FLAG_NEGATIVE, &key->flags)) + if (key_is_negative(key)) return -ENOKEY; if (datalen <= 0 || datalen > 32767 || !prep->data) return -EINVAL; diff --git a/security/keys/gc.c b/security/keys/gc.c index 87cb260e4890..f01d48cb3de1 100644 --- a/security/keys/gc.c +++ b/security/keys/gc.c @@ -129,15 +129,15 @@ static noinline void key_gc_unused_keys(struct list_head *keys) while (!list_empty(keys)) { struct key *key = list_entry(keys->next, struct key, graveyard_link); + short state = key->state; + list_del(&key->graveyard_link); kdebug("- %u", key->serial); key_check(key); /* Throw away the key data if the key is instantiated */ - if (test_bit(KEY_FLAG_INSTANTIATED, &key->flags) && - !test_bit(KEY_FLAG_NEGATIVE, &key->flags) && - key->type->destroy) + if (state == KEY_IS_POSITIVE && key->type->destroy) key->type->destroy(key); security_key_free(key); @@ -151,7 +151,7 @@ static noinline void key_gc_unused_keys(struct list_head *keys) } atomic_dec(&key->user->nkeys); - if (test_bit(KEY_FLAG_INSTANTIATED, &key->flags)) + if (state != KEY_IS_UNINSTANTIATED) atomic_dec(&key->user->nikeys); key_user_put(key->user); diff --git a/security/keys/key.c b/security/keys/key.c index eb914a838840..83bf4b4afd49 100644 --- a/security/keys/key.c +++ b/security/keys/key.c @@ -402,6 +402,18 @@ int key_payload_reserve(struct key *key, size_t datalen) EXPORT_SYMBOL(key_payload_reserve); /* + * Change the key state to being instantiated. + */ +static void mark_key_instantiated(struct key *key, int reject_error) +{ + /* Commit the payload before setting the state; barrier versus + * key_read_state(). + */ + smp_store_release(&key->state, + (reject_error < 0) ? reject_error : KEY_IS_POSITIVE); +} + +/* * Instantiate a key and link it into the target keyring atomically. Must be * called with the target keyring's semaphore writelocked. The target key's * semaphore need not be locked as instantiation is serialised by @@ -424,14 +436,14 @@ static int __key_instantiate_and_link(struct key *key, mutex_lock(&key_construction_mutex); /* can't instantiate twice */ - if (!test_bit(KEY_FLAG_INSTANTIATED, &key->flags)) { + if (key->state == KEY_IS_UNINSTANTIATED) { /* instantiate the key */ ret = key->type->instantiate(key, prep); if (ret == 0) { /* mark the key as being instantiated */ atomic_inc(&key->user->nikeys); - set_bit(KEY_FLAG_INSTANTIATED, &key->flags); + mark_key_instantiated(key, 0); if (test_and_clear_bit(KEY_FLAG_USER_CONSTRUCT, &key->flags)) awaken = 1; @@ -577,13 +589,10 @@ int key_reject_and_link(struct key *key, mutex_lock(&key_construction_mutex); /* can't instantiate twice */ - if (!test_bit(KEY_FLAG_INSTANTIATED, &key->flags)) { + if (key->state == KEY_IS_UNINSTANTIATED) { /* mark the key as being negatively instantiated */ atomic_inc(&key->user->nikeys); - key->reject_error = -error; - smp_wmb(); - set_bit(KEY_FLAG_NEGATIVE, &key->flags); - set_bit(KEY_FLAG_INSTANTIATED, &key->flags); + mark_key_instantiated(key, -error); now = current_kernel_time(); key->expiry = now.tv_sec + timeout; key_schedule_gc(key->expiry + key_gc_delay); @@ -752,8 +761,8 @@ static inline key_ref_t __key_update(key_ref_t key_ref, ret = key->type->update(key, prep); if (ret == 0) - /* updating a negative key instantiates it */ - clear_bit(KEY_FLAG_NEGATIVE, &key->flags); + /* Updating a negative key positively instantiates it */ + mark_key_instantiated(key, 0); up_write(&key->sem); @@ -936,6 +945,16 @@ error: */ __key_link_end(keyring, &index_key, edit); + key = key_ref_to_ptr(key_ref); + if (test_bit(KEY_FLAG_USER_CONSTRUCT, &key->flags)) { + ret = wait_for_key_construction(key, true); + if (ret < 0) { + key_ref_put(key_ref); + key_ref = ERR_PTR(ret); + goto error_free_prep; + } + } + key_ref = __key_update(key_ref, &prep); goto error_free_prep; } @@ -986,8 +1005,8 @@ int key_update(key_ref_t key_ref, const void *payload, size_t plen) ret = key->type->update(key, &prep); if (ret == 0) - /* updating a negative key instantiates it */ - clear_bit(KEY_FLAG_NEGATIVE, &key->flags); + /* Updating a negative key positively instantiates it */ + mark_key_instantiated(key, 0); up_write(&key->sem); diff --git a/security/keys/keyctl.c b/security/keys/keyctl.c index 365ff85d7e27..76d22f726ae4 100644 --- a/security/keys/keyctl.c +++ b/security/keys/keyctl.c @@ -766,10 +766,9 @@ long keyctl_read_key(key_serial_t keyid, char __user *buffer, size_t buflen) key = key_ref_to_ptr(key_ref); - if (test_bit(KEY_FLAG_NEGATIVE, &key->flags)) { - ret = -ENOKEY; - goto error2; - } + ret = key_read_state(key); + if (ret < 0) + goto error2; /* Negatively instantiated */ /* see if we can read it directly */ ret = key_permission(key_ref, KEY_NEED_READ); @@ -901,7 +900,7 @@ long keyctl_chown_key(key_serial_t id, uid_t user, gid_t group) atomic_dec(&key->user->nkeys); atomic_inc(&newowner->nkeys); - if (test_bit(KEY_FLAG_INSTANTIATED, &key->flags)) { + if (key->state != KEY_IS_UNINSTANTIATED) { atomic_dec(&key->user->nikeys); atomic_inc(&newowner->nikeys); } diff --git a/security/keys/keyring.c b/security/keys/keyring.c index 4fa82a8a9c0e..a7e51f793867 100644 --- a/security/keys/keyring.c +++ b/security/keys/keyring.c @@ -414,7 +414,7 @@ static void keyring_describe(const struct key *keyring, struct seq_file *m) else seq_puts(m, "[anon]"); - if (key_is_instantiated(keyring)) { + if (key_is_positive(keyring)) { if (keyring->keys.nr_leaves_on_tree != 0) seq_printf(m, ": %lu", keyring->keys.nr_leaves_on_tree); else @@ -553,7 +553,8 @@ static int keyring_search_iterator(const void *object, void *iterator_data) { struct keyring_search_context *ctx = iterator_data; const struct key *key = keyring_ptr_to_key(object); - unsigned long kflags = key->flags; + unsigned long kflags = READ_ONCE(key->flags); + short state = READ_ONCE(key->state); kenter("{%d}", key->serial); @@ -565,6 +566,8 @@ static int keyring_search_iterator(const void *object, void *iterator_data) /* skip invalidated, revoked and expired keys */ if (ctx->flags & KEYRING_SEARCH_DO_STATE_CHECK) { + time_t expiry = READ_ONCE(key->expiry); + if (kflags & ((1 << KEY_FLAG_INVALIDATED) | (1 << KEY_FLAG_REVOKED))) { ctx->result = ERR_PTR(-EKEYREVOKED); @@ -572,7 +575,7 @@ static int keyring_search_iterator(const void *object, void *iterator_data) goto skipped; } - if (key->expiry && ctx->now.tv_sec >= key->expiry) { + if (expiry && ctx->now.tv_sec >= expiry) { if (!(ctx->flags & KEYRING_SEARCH_SKIP_EXPIRED)) ctx->result = ERR_PTR(-EKEYEXPIRED); kleave(" = %d [expire]", ctx->skipped_ret); @@ -597,9 +600,8 @@ static int keyring_search_iterator(const void *object, void *iterator_data) if (ctx->flags & KEYRING_SEARCH_DO_STATE_CHECK) { /* we set a different error code if we pass a negative key */ - if (kflags & (1 << KEY_FLAG_NEGATIVE)) { - smp_rmb(); - ctx->result = ERR_PTR(key->reject_error); + if (state < 0) { + ctx->result = ERR_PTR(state); kleave(" = %d [neg]", ctx->skipped_ret); goto skipped; } diff --git a/security/keys/permission.c b/security/keys/permission.c index 732cc0beffdf..a72b4dd70c8a 100644 --- a/security/keys/permission.c +++ b/security/keys/permission.c @@ -88,7 +88,8 @@ EXPORT_SYMBOL(key_task_permission); */ int key_validate(const struct key *key) { - unsigned long flags = key->flags; + unsigned long flags = READ_ONCE(key->flags); + time_t expiry = READ_ONCE(key->expiry); if (flags & (1 << KEY_FLAG_INVALIDATED)) return -ENOKEY; @@ -99,9 +100,9 @@ int key_validate(const struct key *key) return -EKEYREVOKED; /* check it hasn't expired */ - if (key->expiry) { + if (expiry) { struct timespec now = current_kernel_time(); - if (now.tv_sec >= key->expiry) + if (now.tv_sec >= expiry) return -EKEYEXPIRED; } diff --git a/security/keys/proc.c b/security/keys/proc.c index de834309d100..6d1fcbba1e09 100644 --- a/security/keys/proc.c +++ b/security/keys/proc.c @@ -179,9 +179,12 @@ static int proc_keys_show(struct seq_file *m, void *v) struct rb_node *_p = v; struct key *key = rb_entry(_p, struct key, serial_node); struct timespec now; + time_t expiry; unsigned long timo; + unsigned long flags; key_ref_t key_ref, skey_ref; char xbuf[16]; + short state; int rc; struct keyring_search_context ctx = { @@ -217,12 +220,13 @@ static int proc_keys_show(struct seq_file *m, void *v) rcu_read_lock(); /* come up with a suitable timeout value */ - if (key->expiry == 0) { + expiry = READ_ONCE(key->expiry); + if (expiry == 0) { memcpy(xbuf, "perm", 5); - } else if (now.tv_sec >= key->expiry) { + } else if (now.tv_sec >= expiry) { memcpy(xbuf, "expd", 5); } else { - timo = key->expiry - now.tv_sec; + timo = expiry - now.tv_sec; if (timo < 60) sprintf(xbuf, "%lus", timo); @@ -236,18 +240,21 @@ static int proc_keys_show(struct seq_file *m, void *v) sprintf(xbuf, "%luw", timo / (60*60*24*7)); } -#define showflag(KEY, LETTER, FLAG) \ - (test_bit(FLAG, &(KEY)->flags) ? LETTER : '-') + state = key_read_state(key); +#define showflag(FLAGS, LETTER, FLAG) \ + ((FLAGS & (1 << FLAG)) ? LETTER : '-') + + flags = READ_ONCE(key->flags); seq_printf(m, "%08x %c%c%c%c%c%c%c %5d %4s %08x %5d %5d %-9.9s ", key->serial, - showflag(key, 'I', KEY_FLAG_INSTANTIATED), - showflag(key, 'R', KEY_FLAG_REVOKED), - showflag(key, 'D', KEY_FLAG_DEAD), - showflag(key, 'Q', KEY_FLAG_IN_QUOTA), - showflag(key, 'U', KEY_FLAG_USER_CONSTRUCT), - showflag(key, 'N', KEY_FLAG_NEGATIVE), - showflag(key, 'i', KEY_FLAG_INVALIDATED), + state != KEY_IS_UNINSTANTIATED ? 'I' : '-', + showflag(flags, 'R', KEY_FLAG_REVOKED), + showflag(flags, 'D', KEY_FLAG_DEAD), + showflag(flags, 'Q', KEY_FLAG_IN_QUOTA), + showflag(flags, 'U', KEY_FLAG_USER_CONSTRUCT), + state < 0 ? 'N' : '-', + showflag(flags, 'i', KEY_FLAG_INVALIDATED), refcount_read(&key->usage), xbuf, key->perm, diff --git a/security/keys/process_keys.c b/security/keys/process_keys.c index 293d3598153b..740affd65ee9 100644 --- a/security/keys/process_keys.c +++ b/security/keys/process_keys.c @@ -730,7 +730,7 @@ try_again: ret = -EIO; if (!(lflags & KEY_LOOKUP_PARTIAL) && - !test_bit(KEY_FLAG_INSTANTIATED, &key->flags)) + key_read_state(key) == KEY_IS_UNINSTANTIATED) goto invalid_key; /* check the permissions */ diff --git a/security/keys/request_key.c b/security/keys/request_key.c index 63e63a42db3c..e8036cd0ad54 100644 --- a/security/keys/request_key.c +++ b/security/keys/request_key.c @@ -595,10 +595,9 @@ int wait_for_key_construction(struct key *key, bool intr) intr ? TASK_INTERRUPTIBLE : TASK_UNINTERRUPTIBLE); if (ret) return -ERESTARTSYS; - if (test_bit(KEY_FLAG_NEGATIVE, &key->flags)) { - smp_rmb(); - return key->reject_error; - } + ret = key_read_state(key); + if (ret < 0) + return ret; return key_validate(key); } EXPORT_SYMBOL(wait_for_key_construction); diff --git a/security/keys/request_key_auth.c b/security/keys/request_key_auth.c index 6ebf1af8fce9..424e1d90412e 100644 --- a/security/keys/request_key_auth.c +++ b/security/keys/request_key_auth.c @@ -73,7 +73,7 @@ static void request_key_auth_describe(const struct key *key, seq_puts(m, "key:"); seq_puts(m, key->description); - if (key_is_instantiated(key)) + if (key_is_positive(key)) seq_printf(m, " pid:%d ci:%zu", rka->pid, rka->callout_len); } diff --git a/security/keys/trusted.c b/security/keys/trusted.c index ddfaebf60fc8..bd85315cbfeb 100644 --- a/security/keys/trusted.c +++ b/security/keys/trusted.c @@ -1066,7 +1066,7 @@ static int trusted_update(struct key *key, struct key_preparsed_payload *prep) char *datablob; int ret = 0; - if (test_bit(KEY_FLAG_NEGATIVE, &key->flags)) + if (key_is_negative(key)) return -ENOKEY; p = key->payload.data[0]; if (!p->migratable) diff --git a/security/keys/user_defined.c b/security/keys/user_defined.c index 3d8c68eba516..9f558bedba23 100644 --- a/security/keys/user_defined.c +++ b/security/keys/user_defined.c @@ -114,7 +114,7 @@ int user_update(struct key *key, struct key_preparsed_payload *prep) /* attach the new data, displacing the old */ key->expiry = prep->expiry; - if (!test_bit(KEY_FLAG_NEGATIVE, &key->flags)) + if (key_is_positive(key)) zap = dereference_key_locked(key); rcu_assign_keypointer(key, prep->payload.data[0]); prep->payload.data[0] = NULL; @@ -162,7 +162,7 @@ EXPORT_SYMBOL_GPL(user_destroy); void user_describe(const struct key *key, struct seq_file *m) { seq_puts(m, key->description); - if (key_is_instantiated(key)) + if (key_is_positive(key)) seq_printf(m, ": %u", key->datalen); } diff --git a/sound/core/seq/seq_clientmgr.c b/sound/core/seq/seq_clientmgr.c index ea2d0ae85bd3..6c9cba2166d9 100644 --- a/sound/core/seq/seq_clientmgr.c +++ b/sound/core/seq/seq_clientmgr.c @@ -1259,6 +1259,7 @@ static int snd_seq_ioctl_create_port(struct snd_seq_client *client, void *arg) struct snd_seq_port_info *info = arg; struct snd_seq_client_port *port; struct snd_seq_port_callback *callback; + int port_idx; /* it is not allowed to create the port for an another client */ if (info->addr.client != client->number) @@ -1269,7 +1270,9 @@ static int snd_seq_ioctl_create_port(struct snd_seq_client *client, void *arg) return -ENOMEM; if (client->type == USER_CLIENT && info->kernel) { - snd_seq_delete_port(client, port->addr.port); + port_idx = port->addr.port; + snd_seq_port_unlock(port); + snd_seq_delete_port(client, port_idx); return -EINVAL; } if (client->type == KERNEL_CLIENT) { @@ -1290,6 +1293,7 @@ static int snd_seq_ioctl_create_port(struct snd_seq_client *client, void *arg) snd_seq_set_port_info(port, info); snd_seq_system_client_ev_port_start(port->addr.client, port->addr.port); + snd_seq_port_unlock(port); return 0; } diff --git a/sound/core/seq/seq_lock.c b/sound/core/seq/seq_lock.c index 0ff7926a5a69..cda64b489e42 100644 --- a/sound/core/seq/seq_lock.c +++ b/sound/core/seq/seq_lock.c @@ -23,8 +23,6 @@ #include <sound/core.h> #include "seq_lock.h" -#if defined(CONFIG_SMP) || defined(CONFIG_SND_DEBUG) - /* wait until all locks are released */ void snd_use_lock_sync_helper(snd_use_lock_t *lockp, const char *file, int line) { @@ -41,5 +39,3 @@ void snd_use_lock_sync_helper(snd_use_lock_t *lockp, const char *file, int line) } } EXPORT_SYMBOL(snd_use_lock_sync_helper); - -#endif diff --git a/sound/core/seq/seq_lock.h b/sound/core/seq/seq_lock.h index 54044bc2c9ef..ac38031c370e 100644 --- a/sound/core/seq/seq_lock.h +++ b/sound/core/seq/seq_lock.h @@ -3,8 +3,6 @@ #include <linux/sched.h> -#if defined(CONFIG_SMP) || defined(CONFIG_SND_DEBUG) - typedef atomic_t snd_use_lock_t; /* initialize lock */ @@ -20,14 +18,4 @@ typedef atomic_t snd_use_lock_t; void snd_use_lock_sync_helper(snd_use_lock_t *lock, const char *file, int line); #define snd_use_lock_sync(lockp) snd_use_lock_sync_helper(lockp, __BASE_FILE__, __LINE__) -#else /* SMP || CONFIG_SND_DEBUG */ - -typedef spinlock_t snd_use_lock_t; /* dummy */ -#define snd_use_lock_init(lockp) /**/ -#define snd_use_lock_use(lockp) /**/ -#define snd_use_lock_free(lockp) /**/ -#define snd_use_lock_sync(lockp) /**/ - -#endif /* SMP || CONFIG_SND_DEBUG */ - #endif /* __SND_SEQ_LOCK_H */ diff --git a/sound/core/seq/seq_ports.c b/sound/core/seq/seq_ports.c index 0a7020c82bfc..d21ece9f8d73 100644 --- a/sound/core/seq/seq_ports.c +++ b/sound/core/seq/seq_ports.c @@ -122,7 +122,9 @@ static void port_subs_info_init(struct snd_seq_port_subs_info *grp) } -/* create a port, port number is returned (-1 on failure) */ +/* create a port, port number is returned (-1 on failure); + * the caller needs to unref the port via snd_seq_port_unlock() appropriately + */ struct snd_seq_client_port *snd_seq_create_port(struct snd_seq_client *client, int port) { @@ -151,6 +153,7 @@ struct snd_seq_client_port *snd_seq_create_port(struct snd_seq_client *client, snd_use_lock_init(&new_port->use_lock); port_subs_info_init(&new_port->c_src); port_subs_info_init(&new_port->c_dest); + snd_use_lock_use(&new_port->use_lock); num = port >= 0 ? port : 0; mutex_lock(&client->ports_mutex); @@ -165,9 +168,9 @@ struct snd_seq_client_port *snd_seq_create_port(struct snd_seq_client *client, list_add_tail(&new_port->list, &p->list); client->num_ports++; new_port->addr.port = num; /* store the port number in the port */ + sprintf(new_port->name, "port-%d", num); write_unlock_irqrestore(&client->ports_lock, flags); mutex_unlock(&client->ports_mutex); - sprintf(new_port->name, "port-%d", num); return new_port; } diff --git a/sound/core/seq/seq_virmidi.c b/sound/core/seq/seq_virmidi.c index 8d93a4021c78..f48a4cd24ffc 100644 --- a/sound/core/seq/seq_virmidi.c +++ b/sound/core/seq/seq_virmidi.c @@ -77,13 +77,17 @@ static void snd_virmidi_init_event(struct snd_virmidi *vmidi, * decode input event and put to read buffer of each opened file */ static int snd_virmidi_dev_receive_event(struct snd_virmidi_dev *rdev, - struct snd_seq_event *ev) + struct snd_seq_event *ev, + bool atomic) { struct snd_virmidi *vmidi; unsigned char msg[4]; int len; - read_lock(&rdev->filelist_lock); + if (atomic) + read_lock(&rdev->filelist_lock); + else + down_read(&rdev->filelist_sem); list_for_each_entry(vmidi, &rdev->filelist, list) { if (!vmidi->trigger) continue; @@ -97,7 +101,10 @@ static int snd_virmidi_dev_receive_event(struct snd_virmidi_dev *rdev, snd_rawmidi_receive(vmidi->substream, msg, len); } } - read_unlock(&rdev->filelist_lock); + if (atomic) + read_unlock(&rdev->filelist_lock); + else + up_read(&rdev->filelist_sem); return 0; } @@ -115,7 +122,7 @@ int snd_virmidi_receive(struct snd_rawmidi *rmidi, struct snd_seq_event *ev) struct snd_virmidi_dev *rdev; rdev = rmidi->private_data; - return snd_virmidi_dev_receive_event(rdev, ev); + return snd_virmidi_dev_receive_event(rdev, ev, true); } #endif /* 0 */ @@ -130,7 +137,7 @@ static int snd_virmidi_event_input(struct snd_seq_event *ev, int direct, rdev = private_data; if (!(rdev->flags & SNDRV_VIRMIDI_USE)) return 0; /* ignored */ - return snd_virmidi_dev_receive_event(rdev, ev); + return snd_virmidi_dev_receive_event(rdev, ev, atomic); } /* @@ -209,7 +216,6 @@ static int snd_virmidi_input_open(struct snd_rawmidi_substream *substream) struct snd_virmidi_dev *rdev = substream->rmidi->private_data; struct snd_rawmidi_runtime *runtime = substream->runtime; struct snd_virmidi *vmidi; - unsigned long flags; vmidi = kzalloc(sizeof(*vmidi), GFP_KERNEL); if (vmidi == NULL) @@ -223,9 +229,11 @@ static int snd_virmidi_input_open(struct snd_rawmidi_substream *substream) vmidi->client = rdev->client; vmidi->port = rdev->port; runtime->private_data = vmidi; - write_lock_irqsave(&rdev->filelist_lock, flags); + down_write(&rdev->filelist_sem); + write_lock_irq(&rdev->filelist_lock); list_add_tail(&vmidi->list, &rdev->filelist); - write_unlock_irqrestore(&rdev->filelist_lock, flags); + write_unlock_irq(&rdev->filelist_lock); + up_write(&rdev->filelist_sem); vmidi->rdev = rdev; return 0; } @@ -264,9 +272,11 @@ static int snd_virmidi_input_close(struct snd_rawmidi_substream *substream) struct snd_virmidi_dev *rdev = substream->rmidi->private_data; struct snd_virmidi *vmidi = substream->runtime->private_data; + down_write(&rdev->filelist_sem); write_lock_irq(&rdev->filelist_lock); list_del(&vmidi->list); write_unlock_irq(&rdev->filelist_lock); + up_write(&rdev->filelist_sem); snd_midi_event_free(vmidi->parser); substream->runtime->private_data = NULL; kfree(vmidi); @@ -520,6 +530,7 @@ int snd_virmidi_new(struct snd_card *card, int device, struct snd_rawmidi **rrmi rdev->rmidi = rmidi; rdev->device = device; rdev->client = -1; + init_rwsem(&rdev->filelist_sem); rwlock_init(&rdev->filelist_lock); INIT_LIST_HEAD(&rdev->filelist); rdev->seq_mode = SNDRV_VIRMIDI_SEQ_DISPATCH; diff --git a/sound/core/vmaster.c b/sound/core/vmaster.c index 6c58e6f73a01..e43af18d4383 100644 --- a/sound/core/vmaster.c +++ b/sound/core/vmaster.c @@ -484,3 +484,34 @@ void snd_ctl_sync_vmaster(struct snd_kcontrol *kcontrol, bool hook_only) master->hook(master->hook_private_data, master->val); } EXPORT_SYMBOL_GPL(snd_ctl_sync_vmaster); + +/** + * snd_ctl_apply_vmaster_slaves - Apply function to each vmaster slave + * @kctl: vmaster kctl element + * @func: function to apply + * @arg: optional function argument + * + * Apply the function @func to each slave kctl of the given vmaster kctl. + * Returns 0 if successful, or a negative error code. + */ +int snd_ctl_apply_vmaster_slaves(struct snd_kcontrol *kctl, + int (*func)(struct snd_kcontrol *, void *), + void *arg) +{ + struct link_master *master; + struct link_slave *slave; + int err; + + master = snd_kcontrol_chip(kctl); + err = master_init(master); + if (err < 0) + return err; + list_for_each_entry(slave, &master->slaves, list) { + err = func(&slave->slave, arg); + if (err < 0) + return err; + } + + return 0; +} +EXPORT_SYMBOL_GPL(snd_ctl_apply_vmaster_slaves); diff --git a/sound/hda/hdac_controller.c b/sound/hda/hdac_controller.c index 978dc1801b3a..f6d2985b2520 100644 --- a/sound/hda/hdac_controller.c +++ b/sound/hda/hdac_controller.c @@ -284,6 +284,11 @@ int snd_hdac_bus_parse_capabilities(struct hdac_bus *bus) dev_dbg(bus->dev, "HDA capability ID: 0x%x\n", (cur_cap & AZX_CAP_HDR_ID_MASK) >> AZX_CAP_HDR_ID_OFF); + if (cur_cap == -1) { + dev_dbg(bus->dev, "Invalid capability reg read\n"); + break; + } + switch ((cur_cap & AZX_CAP_HDR_ID_MASK) >> AZX_CAP_HDR_ID_OFF) { case AZX_ML_CAP_ID: dev_dbg(bus->dev, "Found ML capability\n"); diff --git a/sound/pci/hda/hda_codec.c b/sound/pci/hda/hda_codec.c index 3db26c451837..a0989d231fd0 100644 --- a/sound/pci/hda/hda_codec.c +++ b/sound/pci/hda/hda_codec.c @@ -1803,36 +1803,6 @@ static int check_slave_present(struct hda_codec *codec, return 1; } -/* guess the value corresponding to 0dB */ -static int get_kctl_0dB_offset(struct hda_codec *codec, - struct snd_kcontrol *kctl, int *step_to_check) -{ - int _tlv[4]; - const int *tlv = NULL; - int val = -1; - - if ((kctl->vd[0].access & SNDRV_CTL_ELEM_ACCESS_TLV_CALLBACK) && - kctl->tlv.c == snd_hda_mixer_amp_tlv) { - get_ctl_amp_tlv(kctl, _tlv); - tlv = _tlv; - } else if (kctl->vd[0].access & SNDRV_CTL_ELEM_ACCESS_TLV_READ) - tlv = kctl->tlv.p; - if (tlv && tlv[0] == SNDRV_CTL_TLVT_DB_SCALE) { - int step = tlv[3]; - step &= ~TLV_DB_SCALE_MUTE; - if (!step) - return -1; - if (*step_to_check && *step_to_check != step) { - codec_err(codec, "Mismatching dB step for vmaster slave (%d!=%d)\n", -- *step_to_check, step); - return -1; - } - *step_to_check = step; - val = -tlv[2] / step; - } - return val; -} - /* call kctl->put with the given value(s) */ static int put_kctl_with_value(struct snd_kcontrol *kctl, int val) { @@ -1847,19 +1817,58 @@ static int put_kctl_with_value(struct snd_kcontrol *kctl, int val) return 0; } -/* initialize the slave volume with 0dB */ -static int init_slave_0dB(struct hda_codec *codec, - void *data, struct snd_kcontrol *slave) +struct slave_init_arg { + struct hda_codec *codec; + int step; +}; + +/* initialize the slave volume with 0dB via snd_ctl_apply_vmaster_slaves() */ +static int init_slave_0dB(struct snd_kcontrol *kctl, void *_arg) { - int offset = get_kctl_0dB_offset(codec, slave, data); - if (offset > 0) - put_kctl_with_value(slave, offset); + struct slave_init_arg *arg = _arg; + int _tlv[4]; + const int *tlv = NULL; + int step; + int val; + + if (kctl->vd[0].access & SNDRV_CTL_ELEM_ACCESS_TLV_CALLBACK) { + if (kctl->tlv.c != snd_hda_mixer_amp_tlv) { + codec_err(arg->codec, + "Unexpected TLV callback for slave %s:%d\n", + kctl->id.name, kctl->id.index); + return 0; /* ignore */ + } + get_ctl_amp_tlv(kctl, _tlv); + tlv = _tlv; + } else if (kctl->vd[0].access & SNDRV_CTL_ELEM_ACCESS_TLV_READ) + tlv = kctl->tlv.p; + + if (!tlv || tlv[0] != SNDRV_CTL_TLVT_DB_SCALE) + return 0; + + step = tlv[3]; + step &= ~TLV_DB_SCALE_MUTE; + if (!step) + return 0; + if (arg->step && arg->step != step) { + codec_err(arg->codec, + "Mismatching dB step for vmaster slave (%d!=%d)\n", + arg->step, step); + return 0; + } + + arg->step = step; + val = -tlv[2] / step; + if (val > 0) { + put_kctl_with_value(kctl, val); + return val; + } + return 0; } -/* unmute the slave */ -static int init_slave_unmute(struct hda_codec *codec, - void *data, struct snd_kcontrol *slave) +/* unmute the slave via snd_ctl_apply_vmaster_slaves() */ +static int init_slave_unmute(struct snd_kcontrol *slave, void *_arg) { return put_kctl_with_value(slave, 1); } @@ -1919,9 +1928,13 @@ int __snd_hda_add_vmaster(struct hda_codec *codec, char *name, /* init with master mute & zero volume */ put_kctl_with_value(kctl, 0); if (init_slave_vol) { - int step = 0; - map_slaves(codec, slaves, suffix, - tlv ? init_slave_0dB : init_slave_unmute, &step); + struct slave_init_arg arg = { + .codec = codec, + .step = 0, + }; + snd_ctl_apply_vmaster_slaves(kctl, + tlv ? init_slave_0dB : init_slave_unmute, + &arg); } if (ctl_ret) diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index 0ce71111b4e3..546d515f3c1f 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -327,6 +327,7 @@ static void alc_fill_eapd_coef(struct hda_codec *codec) case 0x10ec0215: case 0x10ec0225: case 0x10ec0233: + case 0x10ec0236: case 0x10ec0255: case 0x10ec0256: case 0x10ec0282: @@ -911,6 +912,7 @@ static struct alc_codec_rename_pci_table rename_pci_tbl[] = { { 0x10ec0275, 0x1028, 0, "ALC3260" }, { 0x10ec0899, 0x1028, 0, "ALC3861" }, { 0x10ec0298, 0x1028, 0, "ALC3266" }, + { 0x10ec0236, 0x1028, 0, "ALC3204" }, { 0x10ec0256, 0x1028, 0, "ALC3246" }, { 0x10ec0225, 0x1028, 0, "ALC3253" }, { 0x10ec0295, 0x1028, 0, "ALC3254" }, @@ -3930,6 +3932,7 @@ static void alc_headset_mode_unplugged(struct hda_codec *codec) alc_process_coef_fw(codec, coef0255_1); alc_process_coef_fw(codec, coef0255); break; + case 0x10ec0236: case 0x10ec0256: alc_process_coef_fw(codec, coef0256); alc_process_coef_fw(codec, coef0255); @@ -4028,6 +4031,7 @@ static void alc_headset_mode_mic_in(struct hda_codec *codec, hda_nid_t hp_pin, }; switch (codec->core.vendor_id) { + case 0x10ec0236: case 0x10ec0255: case 0x10ec0256: alc_write_coef_idx(codec, 0x45, 0xc489); @@ -4160,6 +4164,7 @@ static void alc_headset_mode_default(struct hda_codec *codec) alc_process_coef_fw(codec, alc225_pre_hsmode); alc_process_coef_fw(codec, coef0225); break; + case 0x10ec0236: case 0x10ec0255: case 0x10ec0256: alc_process_coef_fw(codec, coef0255); @@ -4256,6 +4261,7 @@ static void alc_headset_mode_ctia(struct hda_codec *codec) case 0x10ec0255: alc_process_coef_fw(codec, coef0255); break; + case 0x10ec0236: case 0x10ec0256: alc_process_coef_fw(codec, coef0256); break; @@ -4366,6 +4372,7 @@ static void alc_headset_mode_omtp(struct hda_codec *codec) case 0x10ec0255: alc_process_coef_fw(codec, coef0255); break; + case 0x10ec0236: case 0x10ec0256: alc_process_coef_fw(codec, coef0256); break; @@ -4451,6 +4458,7 @@ static void alc_determine_headset_type(struct hda_codec *codec) }; switch (codec->core.vendor_id) { + case 0x10ec0236: case 0x10ec0255: case 0x10ec0256: alc_process_coef_fw(codec, coef0255); @@ -4705,6 +4713,7 @@ static void alc255_set_default_jack_type(struct hda_codec *codec) case 0x10ec0255: alc_process_coef_fw(codec, alc255fw); break; + case 0x10ec0236: case 0x10ec0256: alc_process_coef_fw(codec, alc256fw); break; @@ -6419,6 +6428,14 @@ static const struct snd_hda_pin_quirk alc269_pin_fixup_tbl[] = { ALC225_STANDARD_PINS, {0x12, 0xb7a60130}, {0x1b, 0x90170110}), + SND_HDA_PIN_QUIRK(0x10ec0236, 0x1028, "Dell", ALC255_FIXUP_DELL1_MIC_NO_PRESENCE, + {0x12, 0x90a60140}, + {0x14, 0x90170110}, + {0x21, 0x02211020}), + SND_HDA_PIN_QUIRK(0x10ec0236, 0x1028, "Dell", ALC255_FIXUP_DELL1_MIC_NO_PRESENCE, + {0x12, 0x90a60140}, + {0x14, 0x90170150}, + {0x21, 0x02211020}), SND_HDA_PIN_QUIRK(0x10ec0255, 0x1028, "Dell", ALC255_FIXUP_DELL2_MIC_NO_PRESENCE, {0x14, 0x90170110}, {0x21, 0x02211020}), @@ -6806,6 +6823,7 @@ static int patch_alc269(struct hda_codec *codec) case 0x10ec0255: spec->codec_variant = ALC269_TYPE_ALC255; break; + case 0x10ec0236: case 0x10ec0256: spec->codec_variant = ALC269_TYPE_ALC256; spec->shutup = alc256_shutup; @@ -7857,6 +7875,7 @@ static const struct hda_device_id snd_hda_id_realtek[] = { HDA_CODEC_ENTRY(0x10ec0233, "ALC233", patch_alc269), HDA_CODEC_ENTRY(0x10ec0234, "ALC234", patch_alc269), HDA_CODEC_ENTRY(0x10ec0235, "ALC233", patch_alc269), + HDA_CODEC_ENTRY(0x10ec0236, "ALC236", patch_alc269), HDA_CODEC_ENTRY(0x10ec0255, "ALC255", patch_alc269), HDA_CODEC_ENTRY(0x10ec0256, "ALC256", patch_alc269), HDA_CODEC_ENTRY(0x10ec0260, "ALC260", patch_alc260), diff --git a/sound/usb/caiaq/device.c b/sound/usb/caiaq/device.c index 0fb6b1b79261..d8409d9ae55b 100644 --- a/sound/usb/caiaq/device.c +++ b/sound/usb/caiaq/device.c @@ -469,10 +469,12 @@ static int init_card(struct snd_usb_caiaqdev *cdev) err = snd_usb_caiaq_send_command(cdev, EP1_CMD_GET_DEVICE_INFO, NULL, 0); if (err) - return err; + goto err_kill_urb; - if (!wait_event_timeout(cdev->ep1_wait_queue, cdev->spec_received, HZ)) - return -ENODEV; + if (!wait_event_timeout(cdev->ep1_wait_queue, cdev->spec_received, HZ)) { + err = -ENODEV; + goto err_kill_urb; + } usb_string(usb_dev, usb_dev->descriptor.iManufacturer, cdev->vendor_name, CAIAQ_USB_STR_LEN); @@ -507,6 +509,10 @@ static int init_card(struct snd_usb_caiaqdev *cdev) setup_card(cdev); return 0; + + err_kill_urb: + usb_kill_urb(&cdev->ep1_in_urb); + return err; } static int snd_probe(struct usb_interface *intf, diff --git a/sound/usb/line6/driver.c b/sound/usb/line6/driver.c index 0ff5a7d2e19f..c8f723c3a033 100644 --- a/sound/usb/line6/driver.c +++ b/sound/usb/line6/driver.c @@ -779,9 +779,10 @@ int line6_probe(struct usb_interface *interface, return 0; error: - if (line6->disconnect) - line6->disconnect(line6); - snd_card_free(card); + /* we can call disconnect callback here because no close-sync is + * needed yet at this point + */ + line6_disconnect(interface); return ret; } EXPORT_SYMBOL_GPL(line6_probe); diff --git a/sound/usb/line6/podhd.c b/sound/usb/line6/podhd.c index 956f847a96e4..451007c27743 100644 --- a/sound/usb/line6/podhd.c +++ b/sound/usb/line6/podhd.c @@ -301,7 +301,8 @@ static void podhd_disconnect(struct usb_line6 *line6) intf = usb_ifnum_to_if(line6->usbdev, pod->line6.properties->ctrl_if); - usb_driver_release_interface(&podhd_driver, intf); + if (intf) + usb_driver_release_interface(&podhd_driver, intf); } } @@ -317,6 +318,9 @@ static int podhd_init(struct usb_line6 *line6, line6->disconnect = podhd_disconnect; + init_timer(&pod->startup_timer); + INIT_WORK(&pod->startup_work, podhd_startup_workqueue); + if (pod->line6.properties->capabilities & LINE6_CAP_CONTROL) { /* claim the data interface */ intf = usb_ifnum_to_if(line6->usbdev, @@ -358,8 +362,6 @@ static int podhd_init(struct usb_line6 *line6, } /* init device and delay registering */ - init_timer(&pod->startup_timer); - INIT_WORK(&pod->startup_work, podhd_startup_workqueue); podhd_startup(pod); return 0; } diff --git a/sound/usb/mixer.c b/sound/usb/mixer.c index 9732edf77f86..91bc8f18791e 100644 --- a/sound/usb/mixer.c +++ b/sound/usb/mixer.c @@ -2234,6 +2234,9 @@ static int parse_audio_unit(struct mixer_build *state, int unitid) static void snd_usb_mixer_free(struct usb_mixer_interface *mixer) { + /* kill pending URBs */ + snd_usb_mixer_disconnect(mixer); + kfree(mixer->id_elems); if (mixer->urb) { kfree(mixer->urb->transfer_buffer); @@ -2584,8 +2587,13 @@ _error: void snd_usb_mixer_disconnect(struct usb_mixer_interface *mixer) { - usb_kill_urb(mixer->urb); - usb_kill_urb(mixer->rc_urb); + if (mixer->disconnected) + return; + if (mixer->urb) + usb_kill_urb(mixer->urb); + if (mixer->rc_urb) + usb_kill_urb(mixer->rc_urb); + mixer->disconnected = true; } #ifdef CONFIG_PM diff --git a/sound/usb/mixer.h b/sound/usb/mixer.h index 2b4b067646ab..545d99b09706 100644 --- a/sound/usb/mixer.h +++ b/sound/usb/mixer.h @@ -22,6 +22,8 @@ struct usb_mixer_interface { struct urb *rc_urb; struct usb_ctrlrequest *rc_setup_packet; u8 rc_buffer[6]; + + bool disconnected; }; #define MAX_CHANNELS 16 /* max logical channels */ diff --git a/sound/usb/quirks.c b/sound/usb/quirks.c index b8cb57aeec77..4f5f18f22974 100644 --- a/sound/usb/quirks.c +++ b/sound/usb/quirks.c @@ -1138,6 +1138,7 @@ bool snd_usb_get_sample_rate_quirk(struct snd_usb_audio *chip) case USB_ID(0x047F, 0x0415): /* Plantronics BT-300 */ case USB_ID(0x047F, 0xAA05): /* Plantronics DA45 */ case USB_ID(0x047F, 0xC022): /* Plantronics C310 */ + case USB_ID(0x047F, 0xC02F): /* Plantronics P610 */ case USB_ID(0x047F, 0xC036): /* Plantronics C520-M */ case USB_ID(0x04D8, 0xFEEA): /* Benchmark DAC1 Pre */ case USB_ID(0x0556, 0x0014): /* Phoenix Audio TMX320VC */ @@ -1353,6 +1354,7 @@ u64 snd_usb_interface_dsd_format_quirks(struct snd_usb_audio *chip, case USB_ID(0x20b1, 0x2008): /* Matrix Audio X-Sabre */ case USB_ID(0x20b1, 0x300a): /* Matrix Audio Mini-i Pro */ case USB_ID(0x22d9, 0x0416): /* OPPO HA-1 */ + case USB_ID(0x2772, 0x0230): /* Pro-Ject Pre Box S2 Digital */ if (fp->altsetting == 2) return SNDRV_PCM_FMTBIT_DSD_U32_BE; break; diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 43ab5c402f98..01cc7ba39924 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -312,7 +312,7 @@ union bpf_attr { * jump into another BPF program * @ctx: context pointer passed to next program * @prog_array_map: pointer to map which type is BPF_MAP_TYPE_PROG_ARRAY - * @index: index inside array that selects specific program to run + * @index: 32-bit index inside array that selects specific program to run * Return: 0 on success or negative error * * int bpf_clone_redirect(skb, ifindex, flags) @@ -569,13 +569,14 @@ union bpf_attr { * @flags: reserved for future use * Return: 0 on success or negative error code * - * int bpf_sk_redirect_map(map, key, flags) + * int bpf_sk_redirect_map(skb, map, key, flags) * Redirect skb to a sock in map using key as a lookup key for the * sock in map. + * @skb: pointer to skb * @map: pointer to sockmap * @key: key to lookup sock in map * @flags: reserved for future use - * Return: SK_REDIRECT + * Return: SK_PASS * * int bpf_sock_map_update(skops, map, key, flags) * @skops: pointer to bpf_sock_ops @@ -786,9 +787,8 @@ struct xdp_md { }; enum sk_action { - SK_ABORTED = 0, - SK_DROP, - SK_REDIRECT, + SK_DROP = 0, + SK_PASS, }; #define BPF_TAG_SIZE 8 diff --git a/tools/objtool/check.c b/tools/objtool/check.c index a0c518ecf085..c0e26ad1fa7e 100644 --- a/tools/objtool/check.c +++ b/tools/objtool/check.c @@ -267,12 +267,13 @@ static int decode_instructions(struct objtool_file *file) &insn->immediate, &insn->stack_op); if (ret) - return ret; + goto err; if (!insn->type || insn->type > INSN_LAST) { WARN_FUNC("invalid instruction type %d", insn->sec, insn->offset, insn->type); - return -1; + ret = -1; + goto err; } hash_add(file->insn_hash, &insn->hash, insn->offset); @@ -296,6 +297,10 @@ static int decode_instructions(struct objtool_file *file) } return 0; + +err: + free(insn); + return ret; } /* diff --git a/tools/perf/Documentation/perf-record.txt b/tools/perf/Documentation/perf-record.txt index e397453e5a46..63526f4416ea 100644 --- a/tools/perf/Documentation/perf-record.txt +++ b/tools/perf/Documentation/perf-record.txt @@ -8,8 +8,8 @@ perf-record - Run a command and record its profile into perf.data SYNOPSIS -------- [verse] -'perf record' [-e <EVENT> | --event=EVENT] [-l] [-a] <command> -'perf record' [-e <EVENT> | --event=EVENT] [-l] [-a] -- <command> [<options>] +'perf record' [-e <EVENT> | --event=EVENT] [-a] <command> +'perf record' [-e <EVENT> | --event=EVENT] [-a] -- <command> [<options>] DESCRIPTION ----------- diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c index 3d4c3b5e1868..0c977b6e0f8b 100644 --- a/tools/perf/builtin-script.c +++ b/tools/perf/builtin-script.c @@ -586,7 +586,7 @@ static void print_sample_brstack(struct perf_sample *sample, thread__find_addr_map(thread, sample->cpumode, MAP__FUNCTION, to, &alt); } - printf("0x%"PRIx64, from); + printf(" 0x%"PRIx64, from); if (PRINT_FIELD(DSO)) { printf("("); map__fprintf_dsoname(alf.map, stdout); @@ -681,7 +681,7 @@ static void print_sample_brstackoff(struct perf_sample *sample, if (alt.map && !alt.map->dso->adjust_symbols) to = map__map_ip(alt.map, to); - printf("0x%"PRIx64, from); + printf(" 0x%"PRIx64, from); if (PRINT_FIELD(DSO)) { printf("("); map__fprintf_dsoname(alf.map, stdout); diff --git a/tools/perf/tests/shell/trace+probe_libc_inet_pton.sh b/tools/perf/tests/shell/trace+probe_libc_inet_pton.sh index 462fc755092e..7a84d73324e3 100755 --- a/tools/perf/tests/shell/trace+probe_libc_inet_pton.sh +++ b/tools/perf/tests/shell/trace+probe_libc_inet_pton.sh @@ -10,6 +10,9 @@ . $(dirname $0)/lib/probe.sh +ld=$(realpath /lib64/ld*.so.* | uniq) +libc=$(echo $ld | sed 's/ld/libc/g') + trace_libc_inet_pton_backtrace() { idx=0 expected[0]="PING.*bytes" @@ -18,8 +21,8 @@ trace_libc_inet_pton_backtrace() { expected[3]=".*packets transmitted.*" expected[4]="rtt min.*" expected[5]="[0-9]+\.[0-9]+[[:space:]]+probe_libc:inet_pton:\([[:xdigit:]]+\)" - expected[6]=".*inet_pton[[:space:]]\(/usr/lib.*/libc-[0-9]+\.[0-9]+\.so\)$" - expected[7]="getaddrinfo[[:space:]]\(/usr/lib.*/libc-[0-9]+\.[0-9]+\.so\)$" + expected[6]=".*inet_pton[[:space:]]\($libc\)$" + expected[7]="getaddrinfo[[:space:]]\($libc\)$" expected[8]=".*\(.*/bin/ping.*\)$" perf trace --no-syscalls -e probe_libc:inet_pton/max-stack=3/ ping -6 -c 1 ::1 2>&1 | grep -v ^$ | while read line ; do @@ -35,7 +38,7 @@ trace_libc_inet_pton_backtrace() { } skip_if_no_perf_probe && \ -perf probe -q /lib64/libc-*.so inet_pton && \ +perf probe -q $libc inet_pton && \ trace_libc_inet_pton_backtrace err=$? rm -f ${file} diff --git a/tools/perf/ui/hist.c b/tools/perf/ui/hist.c index ddb2c6fbdf91..db79017a6e56 100644 --- a/tools/perf/ui/hist.c +++ b/tools/perf/ui/hist.c @@ -532,7 +532,7 @@ void perf_hpp_list__prepend_sort_field(struct perf_hpp_list *list, void perf_hpp__column_unregister(struct perf_hpp_fmt *format) { - list_del(&format->list); + list_del_init(&format->list); } void perf_hpp__cancel_cumulate(void) @@ -606,6 +606,13 @@ next: static void fmt_free(struct perf_hpp_fmt *fmt) { + /* + * At this point fmt should be completely + * unhooked, if not it's a bug. + */ + BUG_ON(!list_empty(&fmt->list)); + BUG_ON(!list_empty(&fmt->sort_list)); + if (fmt->free) fmt->free(fmt); } diff --git a/tools/perf/util/callchain.c b/tools/perf/util/callchain.c index be09d77cade0..a971caf3759d 100644 --- a/tools/perf/util/callchain.c +++ b/tools/perf/util/callchain.c @@ -685,6 +685,8 @@ static enum match_result match_chain(struct callchain_cursor_node *node, { struct symbol *sym = node->sym; u64 left, right; + struct dso *left_dso = NULL; + struct dso *right_dso = NULL; if (callchain_param.key == CCKEY_SRCLINE) { enum match_result match = match_chain_srcline(node, cnode); @@ -696,12 +698,14 @@ static enum match_result match_chain(struct callchain_cursor_node *node, if (cnode->ms.sym && sym && callchain_param.key == CCKEY_FUNCTION) { left = cnode->ms.sym->start; right = sym->start; + left_dso = cnode->ms.map->dso; + right_dso = node->map->dso; } else { left = cnode->ip; right = node->ip; } - if (left == right) { + if (left == right && left_dso == right_dso) { if (node->branch) { cnode->branch_count++; diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c index f6257fb4f08c..39b15968eab1 100644 --- a/tools/perf/util/parse-events.c +++ b/tools/perf/util/parse-events.c @@ -309,10 +309,11 @@ static char *get_config_name(struct list_head *head_terms) static struct perf_evsel * __add_event(struct list_head *list, int *idx, struct perf_event_attr *attr, - char *name, struct cpu_map *cpus, + char *name, struct perf_pmu *pmu, struct list_head *config_terms, bool auto_merge_stats) { struct perf_evsel *evsel; + struct cpu_map *cpus = pmu ? pmu->cpus : NULL; event_attr_init(attr); @@ -323,7 +324,7 @@ __add_event(struct list_head *list, int *idx, (*idx)++; evsel->cpus = cpu_map__get(cpus); evsel->own_cpus = cpu_map__get(cpus); - evsel->system_wide = !!cpus; + evsel->system_wide = pmu ? pmu->is_uncore : false; evsel->auto_merge_stats = auto_merge_stats; if (name) @@ -1233,7 +1234,7 @@ static int __parse_events_add_pmu(struct parse_events_state *parse_state, if (!head_config) { attr.type = pmu->type; - evsel = __add_event(list, &parse_state->idx, &attr, NULL, pmu->cpus, NULL, auto_merge_stats); + evsel = __add_event(list, &parse_state->idx, &attr, NULL, pmu, NULL, auto_merge_stats); return evsel ? 0 : -ENOMEM; } @@ -1254,7 +1255,7 @@ static int __parse_events_add_pmu(struct parse_events_state *parse_state, return -EINVAL; evsel = __add_event(list, &parse_state->idx, &attr, - get_config_name(head_config), pmu->cpus, + get_config_name(head_config), pmu, &config_terms, auto_merge_stats); if (evsel) { evsel->unit = info.unit; diff --git a/tools/perf/util/parse-events.l b/tools/perf/util/parse-events.l index c42edeac451f..dcfdafdc2f1c 100644 --- a/tools/perf/util/parse-events.l +++ b/tools/perf/util/parse-events.l @@ -8,6 +8,9 @@ %{ #include <errno.h> +#include <sys/types.h> +#include <sys/stat.h> +#include <unistd.h> #include "../perf.h" #include "parse-events.h" #include "parse-events-bison.h" @@ -53,9 +56,8 @@ static int str(yyscan_t scanner, int token) return token; } -static bool isbpf(yyscan_t scanner) +static bool isbpf_suffix(char *text) { - char *text = parse_events_get_text(scanner); int len = strlen(text); if (len < 2) @@ -68,6 +70,17 @@ static bool isbpf(yyscan_t scanner) return false; } +static bool isbpf(yyscan_t scanner) +{ + char *text = parse_events_get_text(scanner); + struct stat st; + + if (!isbpf_suffix(text)) + return false; + + return stat(text, &st) == 0; +} + /* * This function is called when the parser gets two kind of input: * diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c index ac16a9db1fb5..1c4d7b4e4fb5 100644 --- a/tools/perf/util/pmu.c +++ b/tools/perf/util/pmu.c @@ -470,17 +470,36 @@ static void pmu_read_sysfs(void) closedir(dir); } +static struct cpu_map *__pmu_cpumask(const char *path) +{ + FILE *file; + struct cpu_map *cpus; + + file = fopen(path, "r"); + if (!file) + return NULL; + + cpus = cpu_map__read(file); + fclose(file); + return cpus; +} + +/* + * Uncore PMUs have a "cpumask" file under sysfs. CPU PMUs (e.g. on arm/arm64) + * may have a "cpus" file. + */ +#define CPUS_TEMPLATE_UNCORE "%s/bus/event_source/devices/%s/cpumask" +#define CPUS_TEMPLATE_CPU "%s/bus/event_source/devices/%s/cpus" + static struct cpu_map *pmu_cpumask(const char *name) { - struct stat st; char path[PATH_MAX]; - FILE *file; struct cpu_map *cpus; const char *sysfs = sysfs__mountpoint(); const char *templates[] = { - "%s/bus/event_source/devices/%s/cpumask", - "%s/bus/event_source/devices/%s/cpus", - NULL + CPUS_TEMPLATE_UNCORE, + CPUS_TEMPLATE_CPU, + NULL }; const char **template; @@ -489,20 +508,25 @@ static struct cpu_map *pmu_cpumask(const char *name) for (template = templates; *template; template++) { snprintf(path, PATH_MAX, *template, sysfs, name); - if (stat(path, &st) == 0) - break; + cpus = __pmu_cpumask(path); + if (cpus) + return cpus; } - if (!*template) - return NULL; + return NULL; +} - file = fopen(path, "r"); - if (!file) - return NULL; +static bool pmu_is_uncore(const char *name) +{ + char path[PATH_MAX]; + struct cpu_map *cpus; + const char *sysfs = sysfs__mountpoint(); - cpus = cpu_map__read(file); - fclose(file); - return cpus; + snprintf(path, PATH_MAX, CPUS_TEMPLATE_UNCORE, sysfs, name); + cpus = __pmu_cpumask(path); + cpu_map__put(cpus); + + return !!cpus; } /* @@ -617,6 +641,8 @@ static struct perf_pmu *pmu_lookup(const char *name) pmu->cpus = pmu_cpumask(name); + pmu->is_uncore = pmu_is_uncore(name); + INIT_LIST_HEAD(&pmu->format); INIT_LIST_HEAD(&pmu->aliases); list_splice(&format, &pmu->format); diff --git a/tools/perf/util/pmu.h b/tools/perf/util/pmu.h index 389e9729331f..fe0de0502ce2 100644 --- a/tools/perf/util/pmu.h +++ b/tools/perf/util/pmu.h @@ -22,6 +22,7 @@ struct perf_pmu { char *name; __u32 type; bool selectable; + bool is_uncore; struct perf_event_attr *default_config; struct cpu_map *cpus; struct list_head format; /* HEAD struct perf_pmu_format -> list */ diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c index a7ebd9fe8e40..76ab0709a20c 100644 --- a/tools/perf/util/session.c +++ b/tools/perf/util/session.c @@ -374,6 +374,8 @@ void perf_tool__fill_defaults(struct perf_tool *tool) tool->mmap2 = process_event_stub; if (tool->comm == NULL) tool->comm = process_event_stub; + if (tool->namespaces == NULL) + tool->namespaces = process_event_stub; if (tool->fork == NULL) tool->fork = process_event_stub; if (tool->exit == NULL) diff --git a/tools/perf/util/xyarray.h b/tools/perf/util/xyarray.h index 4ba726c90870..54af60462130 100644 --- a/tools/perf/util/xyarray.h +++ b/tools/perf/util/xyarray.h @@ -23,12 +23,12 @@ static inline void *xyarray__entry(struct xyarray *xy, int x, int y) static inline int xyarray__max_y(struct xyarray *xy) { - return xy->max_x; + return xy->max_y; } static inline int xyarray__max_x(struct xyarray *xy) { - return xy->max_y; + return xy->max_x; } #endif /* _PERF_XYARRAY_H_ */ diff --git a/tools/power/cpupower/Makefile b/tools/power/cpupower/Makefile index 4c5a481a850c..d6e1c02ddcfe 100644 --- a/tools/power/cpupower/Makefile +++ b/tools/power/cpupower/Makefile @@ -26,7 +26,7 @@ endif ifneq ($(OUTPUT),) # check that the output directory actually exists -OUTDIR := $(realpath $(OUTPUT)) +OUTDIR := $(shell cd $(OUTPUT) && /bin/pwd) $(if $(OUTDIR),, $(error output directory "$(OUTPUT)" does not exist)) endif diff --git a/tools/power/x86/turbostat/turbostat.c b/tools/power/x86/turbostat/turbostat.c index 0dafba2c1e7d..bd9c6b31a504 100644 --- a/tools/power/x86/turbostat/turbostat.c +++ b/tools/power/x86/turbostat/turbostat.c @@ -92,7 +92,6 @@ unsigned int do_ring_perf_limit_reasons; unsigned int crystal_hz; unsigned long long tsc_hz; int base_cpu; -int do_migrate; double discover_bclk(unsigned int family, unsigned int model); unsigned int has_hwp; /* IA32_PM_ENABLE, IA32_HWP_CAPABILITIES */ /* IA32_HWP_REQUEST, IA32_HWP_STATUS */ @@ -303,9 +302,6 @@ int for_all_cpus(int (func)(struct thread_data *, struct core_data *, struct pkg int cpu_migrate(int cpu) { - if (!do_migrate) - return 0; - CPU_ZERO_S(cpu_affinity_setsize, cpu_affinity_set); CPU_SET_S(cpu, cpu_affinity_setsize, cpu_affinity_set); if (sched_setaffinity(0, cpu_affinity_setsize, cpu_affinity_set) == -1) @@ -5007,7 +5003,6 @@ void cmdline(int argc, char **argv) {"hide", required_argument, 0, 'H'}, // meh, -h taken by --help {"Joules", no_argument, 0, 'J'}, {"list", no_argument, 0, 'l'}, - {"migrate", no_argument, 0, 'm'}, {"out", required_argument, 0, 'o'}, {"quiet", no_argument, 0, 'q'}, {"show", required_argument, 0, 's'}, @@ -5019,7 +5014,7 @@ void cmdline(int argc, char **argv) progname = argv[0]; - while ((opt = getopt_long_only(argc, argv, "+C:c:Ddhi:Jmo:qST:v", + while ((opt = getopt_long_only(argc, argv, "+C:c:Ddhi:JM:m:o:qST:v", long_options, &option_index)) != -1) { switch (opt) { case 'a': @@ -5062,9 +5057,6 @@ void cmdline(int argc, char **argv) list_header_only++; quiet++; break; - case 'm': - do_migrate = 1; - break; case 'o': outf = fopen_or_die(optarg, "w"); break; diff --git a/tools/scripts/Makefile.include b/tools/scripts/Makefile.include index 9dc8f078a83c..1e8b6116ba3c 100644 --- a/tools/scripts/Makefile.include +++ b/tools/scripts/Makefile.include @@ -1,7 +1,7 @@ ifneq ($(O),) ifeq ($(origin O), command line) - ABSOLUTE_O := $(realpath $(O)) - dummy := $(if $(ABSOLUTE_O),,$(error O=$(O) does not exist)) + dummy := $(if $(shell test -d $(O) || echo $(O)),$(error O=$(O) does not exist),) + ABSOLUTE_O := $(shell cd $(O) ; pwd) OUTPUT := $(ABSOLUTE_O)/$(if $(subdir),$(subdir)/) COMMAND_O := O=$(ABSOLUTE_O) ifeq ($(objtree),) @@ -12,7 +12,7 @@ endif # check that the output directory actually exists ifneq ($(OUTPUT),) -OUTDIR := $(realpath $(OUTPUT)) +OUTDIR := $(shell cd $(OUTPUT) && /bin/pwd) $(if $(OUTDIR),, $(error output directory "$(OUTPUT)" does not exist)) endif diff --git a/tools/testing/selftests/bpf/bpf_helpers.h b/tools/testing/selftests/bpf/bpf_helpers.h index 36fb9161b34a..b2e02bdcd098 100644 --- a/tools/testing/selftests/bpf/bpf_helpers.h +++ b/tools/testing/selftests/bpf/bpf_helpers.h @@ -65,7 +65,7 @@ static int (*bpf_xdp_adjust_head)(void *ctx, int offset) = static int (*bpf_setsockopt)(void *ctx, int level, int optname, void *optval, int optlen) = (void *) BPF_FUNC_setsockopt; -static int (*bpf_sk_redirect_map)(void *map, int key, int flags) = +static int (*bpf_sk_redirect_map)(void *ctx, void *map, int key, int flags) = (void *) BPF_FUNC_sk_redirect_map; static int (*bpf_sock_map_update)(void *map, void *key, void *value, unsigned long long flags) = diff --git a/tools/testing/selftests/bpf/sockmap_verdict_prog.c b/tools/testing/selftests/bpf/sockmap_verdict_prog.c index 9b99bd10807d..2cd2d552938b 100644 --- a/tools/testing/selftests/bpf/sockmap_verdict_prog.c +++ b/tools/testing/selftests/bpf/sockmap_verdict_prog.c @@ -61,8 +61,8 @@ int bpf_prog2(struct __sk_buff *skb) bpf_printk("verdict: data[0] = redir(%u:%u)\n", map, sk); if (!map) - return bpf_sk_redirect_map(&sock_map_rx, sk, 0); - return bpf_sk_redirect_map(&sock_map_tx, sk, 0); + return bpf_sk_redirect_map(skb, &sock_map_rx, sk, 0); + return bpf_sk_redirect_map(skb, &sock_map_tx, sk, 0); } char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/test_maps.c b/tools/testing/selftests/bpf/test_maps.c index fe3a443a1102..50ce52d2013d 100644 --- a/tools/testing/selftests/bpf/test_maps.c +++ b/tools/testing/selftests/bpf/test_maps.c @@ -466,7 +466,7 @@ static void test_sockmap(int tasks, void *data) int one = 1, map_fd_rx, map_fd_tx, map_fd_break, s, sc, rc; struct bpf_map *bpf_map_rx, *bpf_map_tx, *bpf_map_break; int ports[] = {50200, 50201, 50202, 50204}; - int err, i, fd, sfd[6] = {0xdeadbeef}; + int err, i, fd, udp, sfd[6] = {0xdeadbeef}; u8 buf[20] = {0x0, 0x5, 0x3, 0x2, 0x1, 0x0}; int parse_prog, verdict_prog; struct sockaddr_in addr; @@ -548,6 +548,16 @@ static void test_sockmap(int tasks, void *data) goto out_sockmap; } + /* Test update with unsupported UDP socket */ + udp = socket(AF_INET, SOCK_DGRAM, 0); + i = 0; + err = bpf_map_update_elem(fd, &i, &udp, BPF_ANY); + if (!err) { + printf("Failed socket SOCK_DGRAM allowed '%i:%i'\n", + i, udp); + goto out_sockmap; + } + /* Test update without programs */ for (i = 0; i < 6; i++) { err = bpf_map_update_elem(fd, &i, &sfd[i], BPF_ANY); diff --git a/tools/testing/selftests/bpf/test_verifier.c b/tools/testing/selftests/bpf/test_verifier.c index 3c7d3a45a3c5..64ae21f64489 100644 --- a/tools/testing/selftests/bpf/test_verifier.c +++ b/tools/testing/selftests/bpf/test_verifier.c @@ -1130,15 +1130,27 @@ static struct bpf_test tests[] = { .errstr = "invalid bpf_context access", }, { - "check skb->mark is writeable by SK_SKB", + "invalid access of skb->mark for SK_SKB", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, + offsetof(struct __sk_buff, mark)), + BPF_EXIT_INSN(), + }, + .result = REJECT, + .prog_type = BPF_PROG_TYPE_SK_SKB, + .errstr = "invalid bpf_context access", + }, + { + "check skb->mark is not writeable by SK_SKB", .insns = { BPF_MOV64_IMM(BPF_REG_0, 0), BPF_STX_MEM(BPF_W, BPF_REG_1, BPF_REG_0, offsetof(struct __sk_buff, mark)), BPF_EXIT_INSN(), }, - .result = ACCEPT, + .result = REJECT, .prog_type = BPF_PROG_TYPE_SK_SKB, + .errstr = "invalid bpf_context access", }, { "check skb->tc_index is writeable by SK_SKB", @@ -6659,6 +6671,486 @@ static struct bpf_test tests[] = { .result = REJECT, .prog_type = BPF_PROG_TYPE_SCHED_CLS, }, + { + "XDP pkt read, pkt_end mangling, bad access 1", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, + offsetof(struct xdp_md, data)), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, + offsetof(struct xdp_md, data_end)), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_2), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_3, 8), + BPF_JMP_REG(BPF_JGT, BPF_REG_1, BPF_REG_3, 1), + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .errstr = "R1 offset is outside of the packet", + .result = REJECT, + .prog_type = BPF_PROG_TYPE_XDP, + }, + { + "XDP pkt read, pkt_end mangling, bad access 2", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, + offsetof(struct xdp_md, data)), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, + offsetof(struct xdp_md, data_end)), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_2), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8), + BPF_ALU64_IMM(BPF_SUB, BPF_REG_3, 8), + BPF_JMP_REG(BPF_JGT, BPF_REG_1, BPF_REG_3, 1), + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .errstr = "R1 offset is outside of the packet", + .result = REJECT, + .prog_type = BPF_PROG_TYPE_XDP, + }, + { + "XDP pkt read, pkt_data' > pkt_end, good access", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, + offsetof(struct xdp_md, data)), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, + offsetof(struct xdp_md, data_end)), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_2), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8), + BPF_JMP_REG(BPF_JGT, BPF_REG_1, BPF_REG_3, 1), + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_XDP, + }, + { + "XDP pkt read, pkt_data' > pkt_end, bad access 1", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, + offsetof(struct xdp_md, data)), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, + offsetof(struct xdp_md, data_end)), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_2), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8), + BPF_JMP_REG(BPF_JGT, BPF_REG_1, BPF_REG_3, 1), + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -4), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .errstr = "R1 offset is outside of the packet", + .result = REJECT, + .prog_type = BPF_PROG_TYPE_XDP, + .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, + }, + { + "XDP pkt read, pkt_data' > pkt_end, bad access 2", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, + offsetof(struct xdp_md, data)), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, + offsetof(struct xdp_md, data_end)), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_2), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8), + BPF_JMP_REG(BPF_JGT, BPF_REG_1, BPF_REG_3, 0), + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .errstr = "R1 offset is outside of the packet", + .result = REJECT, + .prog_type = BPF_PROG_TYPE_XDP, + }, + { + "XDP pkt read, pkt_end > pkt_data', good access", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, + offsetof(struct xdp_md, data)), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, + offsetof(struct xdp_md, data_end)), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_2), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8), + BPF_JMP_REG(BPF_JGT, BPF_REG_3, BPF_REG_1, 1), + BPF_JMP_IMM(BPF_JA, 0, 0, 1), + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, -5), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_XDP, + .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, + }, + { + "XDP pkt read, pkt_end > pkt_data', bad access 1", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, + offsetof(struct xdp_md, data)), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, + offsetof(struct xdp_md, data_end)), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_2), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8), + BPF_JMP_REG(BPF_JGT, BPF_REG_3, BPF_REG_1, 1), + BPF_JMP_IMM(BPF_JA, 0, 0, 1), + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .errstr = "R1 offset is outside of the packet", + .result = REJECT, + .prog_type = BPF_PROG_TYPE_XDP, + }, + { + "XDP pkt read, pkt_end > pkt_data', bad access 2", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, + offsetof(struct xdp_md, data)), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, + offsetof(struct xdp_md, data_end)), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_2), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8), + BPF_JMP_REG(BPF_JGT, BPF_REG_3, BPF_REG_1, 1), + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .errstr = "R1 offset is outside of the packet", + .result = REJECT, + .prog_type = BPF_PROG_TYPE_XDP, + }, + { + "XDP pkt read, pkt_data' < pkt_end, good access", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, + offsetof(struct xdp_md, data)), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, + offsetof(struct xdp_md, data_end)), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_2), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8), + BPF_JMP_REG(BPF_JLT, BPF_REG_1, BPF_REG_3, 1), + BPF_JMP_IMM(BPF_JA, 0, 0, 1), + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, -5), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_XDP, + .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, + }, + { + "XDP pkt read, pkt_data' < pkt_end, bad access 1", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, + offsetof(struct xdp_md, data)), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, + offsetof(struct xdp_md, data_end)), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_2), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8), + BPF_JMP_REG(BPF_JLT, BPF_REG_1, BPF_REG_3, 1), + BPF_JMP_IMM(BPF_JA, 0, 0, 1), + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .errstr = "R1 offset is outside of the packet", + .result = REJECT, + .prog_type = BPF_PROG_TYPE_XDP, + }, + { + "XDP pkt read, pkt_data' < pkt_end, bad access 2", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, + offsetof(struct xdp_md, data)), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, + offsetof(struct xdp_md, data_end)), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_2), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8), + BPF_JMP_REG(BPF_JLT, BPF_REG_1, BPF_REG_3, 1), + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .errstr = "R1 offset is outside of the packet", + .result = REJECT, + .prog_type = BPF_PROG_TYPE_XDP, + }, + { + "XDP pkt read, pkt_end < pkt_data', good access", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, + offsetof(struct xdp_md, data)), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, + offsetof(struct xdp_md, data_end)), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_2), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8), + BPF_JMP_REG(BPF_JLT, BPF_REG_3, BPF_REG_1, 1), + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_XDP, + }, + { + "XDP pkt read, pkt_end < pkt_data', bad access 1", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, + offsetof(struct xdp_md, data)), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, + offsetof(struct xdp_md, data_end)), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_2), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8), + BPF_JMP_REG(BPF_JLT, BPF_REG_3, BPF_REG_1, 1), + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -4), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .errstr = "R1 offset is outside of the packet", + .result = REJECT, + .prog_type = BPF_PROG_TYPE_XDP, + .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, + }, + { + "XDP pkt read, pkt_end < pkt_data', bad access 2", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, + offsetof(struct xdp_md, data)), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, + offsetof(struct xdp_md, data_end)), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_2), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8), + BPF_JMP_REG(BPF_JLT, BPF_REG_3, BPF_REG_1, 0), + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .errstr = "R1 offset is outside of the packet", + .result = REJECT, + .prog_type = BPF_PROG_TYPE_XDP, + }, + { + "XDP pkt read, pkt_data' >= pkt_end, good access", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, + offsetof(struct xdp_md, data)), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, + offsetof(struct xdp_md, data_end)), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_2), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8), + BPF_JMP_REG(BPF_JGE, BPF_REG_1, BPF_REG_3, 1), + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, -5), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_XDP, + .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, + }, + { + "XDP pkt read, pkt_data' >= pkt_end, bad access 1", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, + offsetof(struct xdp_md, data)), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, + offsetof(struct xdp_md, data_end)), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_2), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8), + BPF_JMP_REG(BPF_JGE, BPF_REG_1, BPF_REG_3, 1), + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .errstr = "R1 offset is outside of the packet", + .result = REJECT, + .prog_type = BPF_PROG_TYPE_XDP, + }, + { + "XDP pkt read, pkt_data' >= pkt_end, bad access 2", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, + offsetof(struct xdp_md, data)), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, + offsetof(struct xdp_md, data_end)), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_2), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8), + BPF_JMP_REG(BPF_JGE, BPF_REG_1, BPF_REG_3, 0), + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, -5), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .errstr = "R1 offset is outside of the packet", + .result = REJECT, + .prog_type = BPF_PROG_TYPE_XDP, + .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, + }, + { + "XDP pkt read, pkt_end >= pkt_data', good access", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, + offsetof(struct xdp_md, data)), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, + offsetof(struct xdp_md, data_end)), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_2), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8), + BPF_JMP_REG(BPF_JGE, BPF_REG_3, BPF_REG_1, 1), + BPF_JMP_IMM(BPF_JA, 0, 0, 1), + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_XDP, + }, + { + "XDP pkt read, pkt_end >= pkt_data', bad access 1", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, + offsetof(struct xdp_md, data)), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, + offsetof(struct xdp_md, data_end)), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_2), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8), + BPF_JMP_REG(BPF_JGE, BPF_REG_3, BPF_REG_1, 1), + BPF_JMP_IMM(BPF_JA, 0, 0, 1), + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -4), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .errstr = "R1 offset is outside of the packet", + .result = REJECT, + .prog_type = BPF_PROG_TYPE_XDP, + .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, + }, + { + "XDP pkt read, pkt_end >= pkt_data', bad access 2", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, + offsetof(struct xdp_md, data)), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, + offsetof(struct xdp_md, data_end)), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_2), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8), + BPF_JMP_REG(BPF_JGE, BPF_REG_3, BPF_REG_1, 1), + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .errstr = "R1 offset is outside of the packet", + .result = REJECT, + .prog_type = BPF_PROG_TYPE_XDP, + }, + { + "XDP pkt read, pkt_data' <= pkt_end, good access", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, + offsetof(struct xdp_md, data)), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, + offsetof(struct xdp_md, data_end)), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_2), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8), + BPF_JMP_REG(BPF_JLE, BPF_REG_1, BPF_REG_3, 1), + BPF_JMP_IMM(BPF_JA, 0, 0, 1), + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_XDP, + }, + { + "XDP pkt read, pkt_data' <= pkt_end, bad access 1", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, + offsetof(struct xdp_md, data)), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, + offsetof(struct xdp_md, data_end)), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_2), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8), + BPF_JMP_REG(BPF_JLE, BPF_REG_1, BPF_REG_3, 1), + BPF_JMP_IMM(BPF_JA, 0, 0, 1), + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -4), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .errstr = "R1 offset is outside of the packet", + .result = REJECT, + .prog_type = BPF_PROG_TYPE_XDP, + .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, + }, + { + "XDP pkt read, pkt_data' <= pkt_end, bad access 2", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, + offsetof(struct xdp_md, data)), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, + offsetof(struct xdp_md, data_end)), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_2), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8), + BPF_JMP_REG(BPF_JLE, BPF_REG_1, BPF_REG_3, 1), + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .errstr = "R1 offset is outside of the packet", + .result = REJECT, + .prog_type = BPF_PROG_TYPE_XDP, + }, + { + "XDP pkt read, pkt_end <= pkt_data', good access", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, + offsetof(struct xdp_md, data)), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, + offsetof(struct xdp_md, data_end)), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_2), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8), + BPF_JMP_REG(BPF_JLE, BPF_REG_3, BPF_REG_1, 1), + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, -5), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_XDP, + .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, + }, + { + "XDP pkt read, pkt_end <= pkt_data', bad access 1", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, + offsetof(struct xdp_md, data)), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, + offsetof(struct xdp_md, data_end)), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_2), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8), + BPF_JMP_REG(BPF_JLE, BPF_REG_3, BPF_REG_1, 1), + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .errstr = "R1 offset is outside of the packet", + .result = REJECT, + .prog_type = BPF_PROG_TYPE_XDP, + }, + { + "XDP pkt read, pkt_end <= pkt_data', bad access 2", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, + offsetof(struct xdp_md, data)), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, + offsetof(struct xdp_md, data_end)), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_2), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8), + BPF_JMP_REG(BPF_JLE, BPF_REG_3, BPF_REG_1, 0), + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, -5), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .errstr = "R1 offset is outside of the packet", + .result = REJECT, + .prog_type = BPF_PROG_TYPE_XDP, + .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, + }, }; static int probe_filter_length(const struct bpf_insn *fp) diff --git a/tools/testing/selftests/mqueue/Makefile b/tools/testing/selftests/mqueue/Makefile index 0f5e347b068d..152823b6cb21 100644 --- a/tools/testing/selftests/mqueue/Makefile +++ b/tools/testing/selftests/mqueue/Makefile @@ -5,8 +5,8 @@ TEST_GEN_PROGS := mq_open_tests mq_perf_tests include ../lib.mk override define RUN_TESTS - $(OUTPUT)/mq_open_tests /test1 || echo "selftests: mq_open_tests [FAIL]" - $(OUTPUT)//mq_perf_tests || echo "selftests: mq_perf_tests [FAIL]" + @$(OUTPUT)/mq_open_tests /test1 || echo "selftests: mq_open_tests [FAIL]" + @$(OUTPUT)/mq_perf_tests || echo "selftests: mq_perf_tests [FAIL]" endef override define EMIT_TESTS diff --git a/tools/testing/selftests/tc-testing/tc-tests/filters/tests.json b/tools/testing/selftests/tc-testing/tc-tests/filters/tests.json index c727b96a59b0..5fa02d86b35f 100644 --- a/tools/testing/selftests/tc-testing/tc-tests/filters/tests.json +++ b/tools/testing/selftests/tc-testing/tc-tests/filters/tests.json @@ -17,5 +17,26 @@ "teardown": [ "$TC qdisc del dev $DEV1 ingress" ] + }, + { + "id": "d052", + "name": "Add 1M filters with the same action", + "category": [ + "filter", + "flower" + ], + "setup": [ + "$TC qdisc add dev $DEV2 ingress", + "./tdc_batch.py $DEV2 $BATCH_FILE --share_action -n 1000000" + ], + "cmdUnderTest": "$TC -b $BATCH_FILE", + "expExitCode": "0", + "verifyCmd": "$TC actions list action gact", + "matchPattern": "action order 0: gact action drop.*index 1 ref 1000000 bind 1000000", + "matchCount": "1", + "teardown": [ + "$TC qdisc del dev $DEV2 ingress", + "/bin/rm $BATCH_FILE" + ] } -]
\ No newline at end of file +] diff --git a/tools/testing/selftests/tc-testing/tdc.py b/tools/testing/selftests/tc-testing/tdc.py index cd61b7844c0d..a8981c5d0aaf 100755 --- a/tools/testing/selftests/tc-testing/tdc.py +++ b/tools/testing/selftests/tc-testing/tdc.py @@ -88,7 +88,7 @@ def prepare_env(cmdlist): exit(1) -def test_runner(filtered_tests): +def test_runner(filtered_tests, args): """ Driver function for the unit tests. @@ -105,6 +105,8 @@ def test_runner(filtered_tests): for tidx in testlist: result = True tresult = "" + if "flower" in tidx["category"] and args.device == None: + continue print("Test " + tidx["id"] + ": " + tidx["name"]) prepare_env(tidx["setup"]) (p, procout) = exec_cmd(tidx["cmdUnderTest"]) @@ -150,7 +152,11 @@ def ns_create(): exec_cmd(cmd, False) cmd = 'ip link set $DEV0 up' exec_cmd(cmd, False) - cmd = 'ip -s $NS link set $DEV1 up' + cmd = 'ip -n $NS link set $DEV1 up' + exec_cmd(cmd, False) + cmd = 'ip link set $DEV2 netns $NS' + exec_cmd(cmd, False) + cmd = 'ip -n $NS link set $DEV2 up' exec_cmd(cmd, False) @@ -211,7 +217,8 @@ def set_args(parser): help='Execute the single test case with specified ID') parser.add_argument('-i', '--id', action='store_true', dest='gen_id', help='Generate ID numbers for new test cases') - return parser + parser.add_argument('-d', '--device', + help='Execute the test case in flower category') return parser @@ -225,6 +232,8 @@ def check_default_settings(args): if args.path != None: NAMES['TC'] = args.path + if args.device != None: + NAMES['DEV2'] = args.device if not os.path.isfile(NAMES['TC']): print("The specified tc path " + NAMES['TC'] + " does not exist.") exit(1) @@ -381,14 +390,17 @@ def set_operation_mode(args): if (len(alltests) == 0): print("Cannot find a test case with ID matching " + target_id) exit(1) - catresults = test_runner(alltests) + catresults = test_runner(alltests, args) print("All test results: " + "\n\n" + catresults) elif (len(target_category) > 0): + if (target_category == "flower") and args.device == None: + print("Please specify a NIC device (-d) to run category flower") + exit(1) if (target_category not in ucat): print("Specified category is not present in this file.") exit(1) else: - catresults = test_runner(testcases[target_category]) + catresults = test_runner(testcases[target_category], args) print("Category " + target_category + "\n\n" + catresults) ns_destroy() diff --git a/tools/testing/selftests/tc-testing/tdc_batch.py b/tools/testing/selftests/tc-testing/tdc_batch.py new file mode 100755 index 000000000000..707c6bfef689 --- /dev/null +++ b/tools/testing/selftests/tc-testing/tdc_batch.py @@ -0,0 +1,62 @@ +#!/usr/bin/python3 + +""" +tdc_batch.py - a script to generate TC batch file + +Copyright (C) 2017 Chris Mi <chrism@mellanox.com> +""" + +import argparse + +parser = argparse.ArgumentParser(description='TC batch file generator') +parser.add_argument("device", help="device name") +parser.add_argument("file", help="batch file name") +parser.add_argument("-n", "--number", type=int, + help="how many lines in batch file") +parser.add_argument("-o", "--skip_sw", + help="skip_sw (offload), by default skip_hw", + action="store_true") +parser.add_argument("-s", "--share_action", + help="all filters share the same action", + action="store_true") +parser.add_argument("-p", "--prio", + help="all filters have different prio", + action="store_true") +args = parser.parse_args() + +device = args.device +file = open(args.file, 'w') + +number = 1 +if args.number: + number = args.number + +skip = "skip_hw" +if args.skip_sw: + skip = "skip_sw" + +share_action = "" +if args.share_action: + share_action = "index 1" + +prio = "prio 1" +if args.prio: + prio = "" + if number > 0x4000: + number = 0x4000 + +index = 0 +for i in range(0x100): + for j in range(0x100): + for k in range(0x100): + mac = ("%02x:%02x:%02x" % (i, j, k)) + src_mac = "e4:11:00:" + mac + dst_mac = "e4:12:00:" + mac + cmd = ("filter add dev %s %s protocol ip parent ffff: flower %s " + "src_mac %s dst_mac %s action drop %s" % + (device, prio, skip, src_mac, dst_mac, share_action)) + file.write("%s\n" % cmd) + index += 1 + if index >= number: + file.close() + exit(0) diff --git a/tools/testing/selftests/tc-testing/tdc_config.py b/tools/testing/selftests/tc-testing/tdc_config.py index 01087375a7c3..b6352515c1b5 100644 --- a/tools/testing/selftests/tc-testing/tdc_config.py +++ b/tools/testing/selftests/tc-testing/tdc_config.py @@ -12,6 +12,8 @@ NAMES = { # Name of veth devices to be created for the namespace 'DEV0': 'v0p0', 'DEV1': 'v0p1', + 'DEV2': '', + 'BATCH_FILE': './batch.txt', # Name of the namespace to use 'NS': 'tcut' } diff --git a/tools/testing/selftests/vm/userfaultfd.c b/tools/testing/selftests/vm/userfaultfd.c index a2c53a3d223d..de2f9ec8a87f 100644 --- a/tools/testing/selftests/vm/userfaultfd.c +++ b/tools/testing/selftests/vm/userfaultfd.c @@ -397,7 +397,7 @@ static void retry_copy_page(int ufd, struct uffdio_copy *uffdio_copy, } } -static int copy_page(int ufd, unsigned long offset) +static int __copy_page(int ufd, unsigned long offset, bool retry) { struct uffdio_copy uffdio_copy; @@ -418,7 +418,7 @@ static int copy_page(int ufd, unsigned long offset) fprintf(stderr, "UFFDIO_COPY unexpected copy %Ld\n", uffdio_copy.copy), exit(1); } else { - if (test_uffdio_copy_eexist) { + if (test_uffdio_copy_eexist && retry) { test_uffdio_copy_eexist = false; retry_copy_page(ufd, &uffdio_copy, offset); } @@ -427,6 +427,16 @@ static int copy_page(int ufd, unsigned long offset) return 0; } +static int copy_page_retry(int ufd, unsigned long offset) +{ + return __copy_page(ufd, offset, true); +} + +static int copy_page(int ufd, unsigned long offset) +{ + return __copy_page(ufd, offset, false); +} + static void *uffd_poll_thread(void *arg) { unsigned long cpu = (unsigned long) arg; @@ -544,7 +554,7 @@ static void *background_thread(void *arg) for (page_nr = cpu * nr_pages_per_cpu; page_nr < (cpu+1) * nr_pages_per_cpu; page_nr++) - copy_page(uffd, page_nr * page_size); + copy_page_retry(uffd, page_nr * page_size); return NULL; } @@ -779,7 +789,7 @@ static void retry_uffdio_zeropage(int ufd, } } -static int uffdio_zeropage(int ufd, unsigned long offset) +static int __uffdio_zeropage(int ufd, unsigned long offset, bool retry) { struct uffdio_zeropage uffdio_zeropage; int ret; @@ -814,7 +824,7 @@ static int uffdio_zeropage(int ufd, unsigned long offset) fprintf(stderr, "UFFDIO_ZEROPAGE unexpected %Ld\n", uffdio_zeropage.zeropage), exit(1); } else { - if (test_uffdio_zeropage_eexist) { + if (test_uffdio_zeropage_eexist && retry) { test_uffdio_zeropage_eexist = false; retry_uffdio_zeropage(ufd, &uffdio_zeropage, offset); @@ -830,6 +840,11 @@ static int uffdio_zeropage(int ufd, unsigned long offset) return 0; } +static int uffdio_zeropage(int ufd, unsigned long offset) +{ + return __uffdio_zeropage(ufd, offset, false); +} + /* exercise UFFDIO_ZEROPAGE */ static int userfaultfd_zeropage_test(void) { diff --git a/tools/testing/selftests/x86/Makefile b/tools/testing/selftests/x86/Makefile index 97f187e2663f..0a74a20ca32b 100644 --- a/tools/testing/selftests/x86/Makefile +++ b/tools/testing/selftests/x86/Makefile @@ -20,7 +20,7 @@ BINARIES_64 := $(TARGETS_C_64BIT_ALL:%=%_64) BINARIES_32 := $(patsubst %,$(OUTPUT)/%,$(BINARIES_32)) BINARIES_64 := $(patsubst %,$(OUTPUT)/%,$(BINARIES_64)) -CFLAGS := -O2 -g -std=gnu99 -pthread -Wall +CFLAGS := -O2 -g -std=gnu99 -pthread -Wall -no-pie UNAME_M := $(shell uname -m) CAN_BUILD_I386 := $(shell ./check_cc.sh $(CC) trivial_32bit_program.c -m32) |