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, 30 insertions, 34 deletions

diff --git a/drivers/infiniband/hw/cxgb4/resource.c b/drivers/infiniband/hw/cxgb4/resource.c
index 67df71a7012e..8ff0cbe5cb16 100644
--- a/drivers/infiniband/hw/cxgb4/resource.c
+++ b/drivers/infiniband/hw/cxgb4/resource.c
@@ -90,7 +90,7 @@ u32 c4iw_get_resource(struct c4iw_id_table *id_table)
 
 void c4iw_put_resource(struct c4iw_id_table *id_table, u32 entry)
 {
-	PDBG("%s entry 0x%x\n", __func__, entry);
+	pr_debug("%s entry 0x%x\n", __func__, entry);
 	c4iw_id_free(id_table, entry);
 }
 
@@ -141,7 +141,7 @@ u32 c4iw_get_cqid(struct c4iw_rdev *rdev, struct c4iw_dev_ucontext *uctx)
 	}
 out:
 	mutex_unlock(&uctx->lock);
-	PDBG("%s qid 0x%x\n", __func__, qid);
+	pr_debug("%s qid 0x%x\n", __func__, qid);
 	mutex_lock(&rdev->stats.lock);
 	if (rdev->stats.qid.cur > rdev->stats.qid.max)
 		rdev->stats.qid.max = rdev->stats.qid.cur;
@@ -157,7 +157,7 @@ void c4iw_put_cqid(struct c4iw_rdev *rdev, u32 qid,
 	entry = kmalloc(sizeof *entry, GFP_KERNEL);
 	if (!entry)
 		return;
-	PDBG("%s qid 0x%x\n", __func__, qid);
+	pr_debug("%s qid 0x%x\n", __func__, qid);
 	entry->qid = qid;
 	mutex_lock(&uctx->lock);
 	list_add_tail(&entry->entry, &uctx->cqids);
@@ -215,7 +215,7 @@ u32 c4iw_get_qpid(struct c4iw_rdev *rdev, struct c4iw_dev_ucontext *uctx)
 	}
 out:
 	mutex_unlock(&uctx->lock);
-	PDBG("%s qid 0x%x\n", __func__, qid);
+	pr_debug("%s qid 0x%x\n", __func__, qid);
 	mutex_lock(&rdev->stats.lock);
 	if (rdev->stats.qid.cur > rdev->stats.qid.max)
 		rdev->stats.qid.max = rdev->stats.qid.cur;
@@ -231,7 +231,7 @@ void c4iw_put_qpid(struct c4iw_rdev *rdev, u32 qid,
 	entry = kmalloc(sizeof *entry, GFP_KERNEL);
 	if (!entry)
 		return;
-	PDBG("%s qid 0x%x\n", __func__, qid);
+	pr_debug("%s qid 0x%x\n", __func__, qid);
 	entry->qid = qid;
 	mutex_lock(&uctx->lock);
 	list_add_tail(&entry->entry, &uctx->qpids);
@@ -254,7 +254,7 @@ void c4iw_destroy_resource(struct c4iw_resource *rscp)
 u32 c4iw_pblpool_alloc(struct c4iw_rdev *rdev, int size)
 {
 	unsigned long addr = gen_pool_alloc(rdev->pbl_pool, size);
-	PDBG("%s addr 0x%x size %d\n", __func__, (u32)addr, size);
+	pr_debug("%s addr 0x%x size %d\n", __func__, (u32)addr, size);
 	mutex_lock(&rdev->stats.lock);
 	if (addr) {
 		rdev->stats.pbl.cur += roundup(size, 1 << MIN_PBL_SHIFT);
@@ -268,7 +268,7 @@ u32 c4iw_pblpool_alloc(struct c4iw_rdev *rdev, int size)
 
 void c4iw_pblpool_free(struct c4iw_rdev *rdev, u32 addr, int size)
 {
-	PDBG("%s addr 0x%x size %d\n", __func__, addr, size);
+	pr_debug("%s addr 0x%x size %d\n", __func__, addr, size);
 	mutex_lock(&rdev->stats.lock);
 	rdev->stats.pbl.cur -= roundup(size, 1 << MIN_PBL_SHIFT);
 	mutex_unlock(&rdev->stats.lock);
@@ -290,19 +290,17 @@ int c4iw_pblpool_create(struct c4iw_rdev *rdev)
 	while (pbl_start < pbl_top) {
 		pbl_chunk = min(pbl_top - pbl_start + 1, pbl_chunk);
 		if (gen_pool_add(rdev->pbl_pool, pbl_start, pbl_chunk, -1)) {
-			PDBG("%s failed to add PBL chunk (%x/%x)\n",
-			     __func__, pbl_start, pbl_chunk);
+			pr_debug("%s failed to add PBL chunk (%x/%x)\n",
+				 __func__, pbl_start, pbl_chunk);
 			if (pbl_chunk <= 1024 << MIN_PBL_SHIFT) {
-				printk(KERN_WARNING MOD
-				       "Failed to add all PBL chunks (%x/%x)\n",
-				       pbl_start,
-				       pbl_top - pbl_start);
+				pr_warn("Failed to add all PBL chunks (%x/%x)\n",
+					pbl_start, pbl_top - pbl_start);
 				return 0;
 			}
 			pbl_chunk >>= 1;
 		} else {
-			PDBG("%s added PBL chunk (%x/%x)\n",
-			     __func__, pbl_start, pbl_chunk);
+			pr_debug("%s added PBL chunk (%x/%x)\n",
+				 __func__, pbl_start, pbl_chunk);
 			pbl_start += pbl_chunk;
 		}
 	}
@@ -324,9 +322,9 @@ void c4iw_pblpool_destroy(struct c4iw_rdev *rdev)
 u32 c4iw_rqtpool_alloc(struct c4iw_rdev *rdev, int size)
 {
 	unsigned long addr = gen_pool_alloc(rdev->rqt_pool, size << 6);
-	PDBG("%s addr 0x%x size %d\n", __func__, (u32)addr, size << 6);
+	pr_debug("%s addr 0x%x size %d\n", __func__, (u32)addr, size << 6);
 	if (!addr)
-		pr_warn_ratelimited(MOD "%s: Out of RQT memory\n",
+		pr_warn_ratelimited("%s: Out of RQT memory\n",
 				    pci_name(rdev->lldi.pdev));
 	mutex_lock(&rdev->stats.lock);
 	if (addr) {
@@ -341,7 +339,7 @@ u32 c4iw_rqtpool_alloc(struct c4iw_rdev *rdev, int size)
 
 void c4iw_rqtpool_free(struct c4iw_rdev *rdev, u32 addr, int size)
 {
-	PDBG("%s addr 0x%x size %d\n", __func__, addr, size << 6);
+	pr_debug("%s addr 0x%x size %d\n", __func__, addr, size << 6);
 	mutex_lock(&rdev->stats.lock);
 	rdev->stats.rqt.cur -= roundup(size << 6, 1 << MIN_RQT_SHIFT);
 	mutex_unlock(&rdev->stats.lock);
@@ -363,18 +361,17 @@ int c4iw_rqtpool_create(struct c4iw_rdev *rdev)
 	while (rqt_start < rqt_top) {
 		rqt_chunk = min(rqt_top - rqt_start + 1, rqt_chunk);
 		if (gen_pool_add(rdev->rqt_pool, rqt_start, rqt_chunk, -1)) {
-			PDBG("%s failed to add RQT chunk (%x/%x)\n",
-			     __func__, rqt_start, rqt_chunk);
+			pr_debug("%s failed to add RQT chunk (%x/%x)\n",
+				 __func__, rqt_start, rqt_chunk);
 			if (rqt_chunk <= 1024 << MIN_RQT_SHIFT) {
-				printk(KERN_WARNING MOD
-				       "Failed to add all RQT chunks (%x/%x)\n",
-				       rqt_start, rqt_top - rqt_start);
+				pr_warn("Failed to add all RQT chunks (%x/%x)\n",
+					rqt_start, rqt_top - rqt_start);
 				return 0;
 			}
 			rqt_chunk >>= 1;
 		} else {
-			PDBG("%s added RQT chunk (%x/%x)\n",
-			     __func__, rqt_start, rqt_chunk);
+			pr_debug("%s added RQT chunk (%x/%x)\n",
+				 __func__, rqt_start, rqt_chunk);
 			rqt_start += rqt_chunk;
 		}
 	}
@@ -394,7 +391,7 @@ void c4iw_rqtpool_destroy(struct c4iw_rdev *rdev)
 u32 c4iw_ocqp_pool_alloc(struct c4iw_rdev *rdev, int size)
 {
 	unsigned long addr = gen_pool_alloc(rdev->ocqp_pool, size);
-	PDBG("%s addr 0x%x size %d\n", __func__, (u32)addr, size);
+	pr_debug("%s addr 0x%x size %d\n", __func__, (u32)addr, size);
 	if (addr) {
 		mutex_lock(&rdev->stats.lock);
 		rdev->stats.ocqp.cur += roundup(size, 1 << MIN_OCQP_SHIFT);
@@ -407,7 +404,7 @@ u32 c4iw_ocqp_pool_alloc(struct c4iw_rdev *rdev, int size)
 
 void c4iw_ocqp_pool_free(struct c4iw_rdev *rdev, u32 addr, int size)
 {
-	PDBG("%s addr 0x%x size %d\n", __func__, addr, size);
+	pr_debug("%s addr 0x%x size %d\n", __func__, addr, size);
 	mutex_lock(&rdev->stats.lock);
 	rdev->stats.ocqp.cur -= roundup(size, 1 << MIN_OCQP_SHIFT);
 	mutex_unlock(&rdev->stats.lock);
@@ -429,18 +426,17 @@ int c4iw_ocqp_pool_create(struct c4iw_rdev *rdev)
 	while (start < top) {
 		chunk = min(top - start + 1, chunk);
 		if (gen_pool_add(rdev->ocqp_pool, start, chunk, -1)) {
-			PDBG("%s failed to add OCQP chunk (%x/%x)\n",
-			     __func__, start, chunk);
+			pr_debug("%s failed to add OCQP chunk (%x/%x)\n",
+				 __func__, start, chunk);
 			if (chunk <= 1024 << MIN_OCQP_SHIFT) {
-				printk(KERN_WARNING MOD
-				       "Failed to add all OCQP chunks (%x/%x)\n",
-				       start, top - start);
+				pr_warn("Failed to add all OCQP chunks (%x/%x)\n",
+					start, top - start);
 				return 0;
 			}
 			chunk >>= 1;
 		} else {
-			PDBG("%s added OCQP chunk (%x/%x)\n",
-			     __func__, start, chunk);
+			pr_debug("%s added OCQP chunk (%x/%x)\n",
+				 __func__, start, chunk);
 			start += chunk;
 		}
 	}