Merge tag 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/dledford/rdma

Pull rdma updates from Doug Ledford:
 "More exchaustive description of primary updates in this release:

   - Lots of driver fixes and misc fixes across the board.

   - I had to base on a net-next tree because the IPoIB Accelorator
     patches needed it.

     Unfortunately, it was known to Mellanox that there would need to be
     an IPoIB accelorator patch to the net tree (which left some
     functions turned off by an #ifdef construct to avoid warnings about
     defined but unused functions), then one to the RDMA tree, then a
     fixup that went back and re-enabled the functions in the net tree
     and enabled their use in the rdma tree

     Also, a sparse fix was sent to the net tree after I did my pull,
     and the fixup patch conflicts quite directly with that sparse fix,
     so I'm going to submit the fixup patch towards the end of the merge
     window by itself and based upon your master branch at the time.

   - Two separate rounds of hfi1 fixes, one that got dropped from last
     release because it came in just a day or two before the end of the
     merge window and then the one from this release cycle.

     Of note is that I now have a third series that just landed from
     Intel yesterday. It is not included in this pull request, but I may
     submit it by the end of the week. I'll talk to Intel about
     improving the timing of thier submissions for my workflow.

   - Changes to our idr usage in the RDMA subsystem that will tie into
     our cgroup management and also into the upcoming changes for the
     RDMA kernel<->userspace API.

   - Addition of support for a netdev to be tied to an RDMA device at
     the core level

   - Addition of the VNIC driver from Intel.

     While IPoIB provides IP over InfiniBand (and *only* IP, no lower
     layer protocol headers are allowed or supported), the VNIC driver
     presents a virtual Ethernet device with support for things like
     varying Ethertypes, VLANs, priorities and other features of
     Ethernet.

     The virtual devices are centrally managed by the OPA fabric
     manager, making this (for the time being) a strictly OPA specific
     feature.

   - Improvements to the On-Demand Paging support in the RDMA subsystem.

   - Addition of three significant OPA changes.

     While we added OPA support some time ago (via the hfi1 driver), the
     RDMA subsystem has so far glossed over the areas where OPA and
     InfiniBand differ.

     With this release we are starting to add support for the OPA
     extensions into the RDMA core in the following area: Extended port
     information for OPA is now supported, extended Address Handle
     attributes for OPA are now supported, and extended SA Queries to
     get OPA specific subnet information is now supported.

  Concise summary from the tag:
   - idr usage and locking changes
   - build fix for hns
   - ipoib debug path record file fix
   - hfi1 updates
   - core RDMA netdev addition
   - Intel VNIC driver addition
   - Enhanced accelerators for IPoIB addition
   - Debug cleanups in cxgb3/4
   - Trivial cleanups from SF Markus Elfring
   - Misc rxe fixes from Mellanox
   - Misc ipoib fixes from Mellanox
   - Lots of mlx4/mlx5 changes from Mellanox
   - Misc fixes across the RDMA subsystem
   - ODP paging fixes and improvements
   - qedr updates
   - hfi1 updates
   - OPA port info patches
   - OPA AH patches
   - OPA SA Query patches"

* tag 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/dledford/rdma: (191 commits)
  infiniband: avoid dereferencing uninitialized dst on error path
  IB/SA: Add OPA addr header
  IB/mlx5: Add port_xmit_wait to counter registers read
  IB/ocrdma: fix out of bounds access to local buffer
  IB/mlx4: Fix incorrect order of formal and actual parameters
  IB/mlx4: Change flush logic so it adheres to the variable name
  mlx5: Fix mlx5_ib_map_mr_sg mr length
  IB/rxe: Don't clamp residual length to mtu
  IB/SA: Add support to query OPA path records
  IB/SA: Add OPA path record type
  IB/SA: Split struct sa_path_rec based on IB and ROCE specific fields
  IB/SA: Introduce path record specific types
  IB/SA: Rename ib_sa_path_rec to sa_path_rec
  IB/CM: Add braces when using sizeof
  IB/core: Define 'opa' rdma_ah_attr type
  IB/core: Define 'ib' and 'roce' rdma_ah_attr types
  IB/core: Use rdma_ah_attr accessor functions
  IB/core: Add accessor functions for rdma_ah_attr fields
  IB/PVRDMA: Rename ib_ah_attr related functions
  IB/mthca: Rename to_ib_ah_attr to to_rdma_ah_attr
  ...

1 files changed, 78 insertions, 17 deletions

diff --git a/drivers/infiniband/hw/hfi1/hfi.h b/drivers/infiniband/hw/hfi1/hfi.h
index 0808e3c3ba39..f06674317abf 100644
--- a/drivers/infiniband/hw/hfi1/hfi.h
+++ b/drivers/infiniband/hw/hfi1/hfi.h
@@ -1,7 +1,7 @@
 #ifndef _HFI1_KERNEL_H
 #define _HFI1_KERNEL_H
 /*
- * Copyright(c) 2015, 2016 Intel Corporation.
+ * Copyright(c) 2015-2017 Intel Corporation.
  *
  * This file is provided under a dual BSD/GPLv2 license.  When using or
  * redistributing this file, you may do so under either license.
@@ -54,6 +54,7 @@
 #include <linux/list.h>
 #include <linux/scatterlist.h>
 #include <linux/slab.h>
+#include <linux/idr.h>
 #include <linux/io.h>
 #include <linux/fs.h>
 #include <linux/completion.h>
@@ -66,6 +67,7 @@
 #include <linux/i2c-algo-bit.h>
 #include <rdma/ib_hdrs.h>
 #include <linux/rhashtable.h>
+#include <linux/netdevice.h>
 #include <rdma/rdma_vt.h>
 
 #include "chip_registers.h"
@@ -278,6 +280,8 @@ struct hfi1_ctxtdata {
 	struct hfi1_devdata *dd;
 	/* so functions that need physical port can get it easily */
 	struct hfi1_pportdata *ppd;
+	/* associated msix interrupt */
+	u32 msix_intr;
 	/* A page of memory for rcvhdrhead, rcvegrhead, rcvegrtail * N */
 	void *subctxt_uregbase;
 	/* An array of pages for the eager receive buffers * N */
@@ -337,6 +341,12 @@ struct hfi1_ctxtdata {
 	 * packets with the wrong interrupt handler.
 	 */
 	int (*do_interrupt)(struct hfi1_ctxtdata *rcd, int threaded);
+
+	/* Indicates that this is vnic context */
+	bool is_vnic;
+
+	/* vnic queue index this context is mapped to */
+	u8 vnic_q_idx;
 };
 
 /*
@@ -474,7 +484,7 @@ struct rvt_sge_state;
 #define HFI1_PART_ENFORCE_OUT	0x2
 
 /* how often we check for synthetic counter wrap around */
-#define SYNTH_CNT_TIME 2
+#define SYNTH_CNT_TIME 3
 
 /* Counter flags */
 #define CNTR_NORMAL		0x0 /* Normal counters, just read register */
@@ -808,6 +818,32 @@ struct hfi1_asic_data {
 	struct hfi1_i2c_bus *i2c_bus1;
 };
 
+/* sizes for both the QP and RSM map tables */
+#define NUM_MAP_ENTRIES	 256
+#define NUM_MAP_REGS      32
+
+/*
+ * Number of VNIC contexts used. Ensure it is less than or equal to
+ * max queues supported by VNIC (HFI1_VNIC_MAX_QUEUE).
+ */
+#define HFI1_NUM_VNIC_CTXT   8
+
+/* Number of VNIC RSM entries */
+#define NUM_VNIC_MAP_ENTRIES 8
+
+/* Virtual NIC information */
+struct hfi1_vnic_data {
+	struct hfi1_ctxtdata *ctxt[HFI1_NUM_VNIC_CTXT];
+	struct kmem_cache *txreq_cache;
+	u8 num_vports;
+	struct idr vesw_idr;
+	u8 rmt_start;
+	u8 num_ctxt;
+	u32 msix_idx;
+};
+
+struct hfi1_vnic_vport_info;
+
 /* device data struct now contains only "general per-device" info.
  * fields related to a physical IB port are in a hfi1_pportdata struct.
  */
@@ -926,8 +962,9 @@ struct hfi1_devdata {
 	spinlock_t rcvctrl_lock; /* protect changes to RcvCtrl */
 	/* around rcd and (user ctxts) ctxt_cnt use (intr vs free) */
 	spinlock_t uctxt_lock; /* rcd and user context changes */
-	/* exclusive access to 8051 */
-	spinlock_t dc8051_lock;
+	struct mutex dc8051_lock; /* exclusive access to 8051 */
+	struct workqueue_struct *update_cntr_wq;
+	struct work_struct update_cntr_work;
 	/* exclusive access to 8051 memory */
 	spinlock_t dc8051_memlock;
 	int dc8051_timed_out;	/* remember if the 8051 timed out */
@@ -1020,7 +1057,7 @@ struct hfi1_devdata {
 	u8 qos_shift;
 
 	u16 irev;	/* implementation revision */
-	u16 dc8051_ver; /* 8051 firmware version */
+	u32 dc8051_ver; /* 8051 firmware version */
 
 	spinlock_t hfi1_diag_trans_lock; /* protect diag observer ops */
 	struct platform_config platform_config;
@@ -1031,6 +1068,7 @@ struct hfi1_devdata {
 	/* MSI-X information */
 	struct hfi1_msix_entry *msix_entries;
 	u32 num_msix_entries;
+	u32 first_dyn_msix_idx;
 
 	/* INTx information */
 	u32 requested_intx_irq;		/* did we request one? */
@@ -1115,6 +1153,9 @@ struct hfi1_devdata {
 	send_routine process_dma_send;
 	void (*pio_inline_send)(struct hfi1_devdata *dd, struct pio_buf *pbuf,
 				u64 pbc, const void *from, size_t count);
+	int (*process_vnic_dma_send)(struct hfi1_devdata *dd, u8 q_idx,
+				     struct hfi1_vnic_vport_info *vinfo,
+				     struct sk_buff *skb, u64 pbc, u8 plen);
 	/* hfi1_pportdata, points to array of (physical) port-specific
 	 * data structs, indexed by pidx (0..n-1)
 	 */
@@ -1126,8 +1167,8 @@ struct hfi1_devdata {
 	u16 flags;
 	/* Number of physical ports available */
 	u8 num_pports;
-	/* Lowest context number which can be used by user processes */
-	u8 first_user_ctxt;
+	/* Lowest context number which can be used by user processes or VNIC */
+	u8 first_dyn_alloc_ctxt;
 	/* adding a new field here would make it part of this cacheline */
 
 	/* seqlock for sc2vl */
@@ -1167,15 +1208,24 @@ struct hfi1_devdata {
 	bool eprom_available;	/* true if EPROM is available for this device */
 	bool aspm_supported;	/* Does HW support ASPM */
 	bool aspm_enabled;	/* ASPM state: enabled/disabled */
-	struct rhashtable sdma_rht;
+	struct rhashtable *sdma_rht;
 
 	struct kobject kobj;
+
+	/* vnic data */
+	struct hfi1_vnic_data vnic;
 };
 
+static inline bool hfi1_vnic_is_rsm_full(struct hfi1_devdata *dd, int spare)
+{
+	return (dd->vnic.rmt_start + spare) > NUM_MAP_ENTRIES;
+}
+
 /* 8051 firmware version helper */
-#define dc8051_ver(a, b) ((a) << 8 | (b))
-#define dc8051_ver_maj(a) ((a & 0xff00) >> 8)
-#define dc8051_ver_min(a)  (a & 0x00ff)
+#define dc8051_ver(a, b, c) ((a) << 16 | (b) << 8 | (c))
+#define dc8051_ver_maj(a) (((a) & 0xff0000) >> 16)
+#define dc8051_ver_min(a) (((a) & 0x00ff00) >> 8)
+#define dc8051_ver_patch(a) ((a) & 0x0000ff)
 
 /* f_put_tid types */
 #define PT_EXPECTED 0
@@ -1235,6 +1285,9 @@ int handle_receive_interrupt(struct hfi1_ctxtdata *, int);
 int handle_receive_interrupt_nodma_rtail(struct hfi1_ctxtdata *, int);
 int handle_receive_interrupt_dma_rtail(struct hfi1_ctxtdata *, int);
 void set_all_slowpath(struct hfi1_devdata *dd);
+void hfi1_vnic_synchronize_irq(struct hfi1_devdata *dd);
+void hfi1_set_vnic_msix_info(struct hfi1_ctxtdata *rcd);
+void hfi1_reset_vnic_msix_info(struct hfi1_ctxtdata *rcd);
 
 extern const struct pci_device_id hfi1_pci_tbl[];
 
@@ -1254,16 +1307,24 @@ int hfi1_reset_device(int);
 /* return the driver's idea of the logical OPA port state */
 static inline u32 driver_lstate(struct hfi1_pportdata *ppd)
 {
-	return ppd->lstate; /* use the cached value */
+	/*
+	 * The driver does some processing from the time the logical
+	 * link state is at INIT to the time the SM can be notified
+	 * as such. Return IB_PORT_DOWN until the software state
+	 * is ready.
+	 */
+	if (ppd->lstate == IB_PORT_INIT && !(ppd->host_link_state & HLS_UP))
+		return IB_PORT_DOWN;
+	else
+		return ppd->lstate;
 }
 
 void receive_interrupt_work(struct work_struct *work);
 
 /* extract service channel from header and rhf */
-static inline int hdr2sc(struct ib_header *hdr, u64 rhf)
+static inline int hfi1_9B_get_sc5(struct ib_header *hdr, u64 rhf)
 {
-	return ((be16_to_cpu(hdr->lrh[0]) >> 12) & 0xf) |
-	       ((!!(rhf_dc_info(rhf))) << 4);
+	return ib_get_sc(hdr) | ((!!(rhf_dc_info(rhf))) << 4);
 }
 
 #define HFI1_JKEY_WIDTH       16
@@ -1597,9 +1658,9 @@ static inline bool process_ecn(struct rvt_qp *qp, struct hfi1_packet *pkt,
 	u32 bth1;
 
 	bth1 = be32_to_cpu(ohdr->bth[1]);
-	if (unlikely(bth1 & (HFI1_BECN_SMASK | HFI1_FECN_SMASK))) {
+	if (unlikely(bth1 & (IB_BECN_SMASK | IB_FECN_SMASK))) {
 		hfi1_process_ecn_slowpath(qp, pkt, do_cnp);
-		return bth1 & HFI1_FECN_SMASK;
+		return !!(bth1 & IB_FECN_SMASK);
 	}
 	return false;
 }