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

Pull rdma updates from Jason Gunthorpe:

 - Minor bug fixes in mlx5, mthca, pvrdma, rtrs, mlx4, hfi1, hns

 - Minor cleanups: coding style, useless includes and documentation

 - Reorganize how multicast processing works in rxe

 - Replace a red/black tree with xarray in rxe which improves performance

 - DSCP support and HW address handle re-use in irdma

 - Simplify the mailbox command handling in hns

 - Simplify iser now that FMR is eliminated

* tag 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/rdma/rdma: (93 commits)
  RDMA/nldev: Prevent underflow in nldev_stat_set_counter_dynamic_doit()
  IB/iser: Fix error flow in case of registration failure
  IB/iser: Generalize map/unmap dma tasks
  IB/iser: Use iser_fr_desc as registration context
  IB/iser: Remove iser_reg_data_sg helper function
  RDMA/rxe: Use standard names for ref counting
  RDMA/rxe: Replace red-black trees by xarrays
  RDMA/rxe: Shorten pool names in rxe_pool.c
  RDMA/rxe: Move max_elem into rxe_type_info
  RDMA/rxe: Replace obj by elem in declaration
  RDMA/rxe: Delete _locked() APIs for pool objects
  RDMA/rxe: Reverse the sense of RXE_POOL_NO_ALLOC
  RDMA/rxe: Replace mr by rkey in responder resources
  RDMA/rxe: Fix ref error in rxe_av.c
  RDMA/hns: Use the reserved loopback QPs to free MR before destroying MPT
  RDMA/irdma: Add support for address handle re-use
  RDMA/qib: Fix typos in comments
  RDMA/mlx5: Fix memory leak in error flow for subscribe event routine
  Revert "RDMA/core: Fix ib_qp_usecnt_dec() called when error"
  RDMA/rxe: Remove useless argument for update_state()
  ...

8 files changed, 57 insertions, 89 deletions

diff --git a/drivers/infiniband/hw/mlx5/devx.c b/drivers/infiniband/hw/mlx5/devx.c
index fc036b4794fd..2a2a9e9afc9d 100644
--- a/drivers/infiniband/hw/mlx5/devx.c
+++ b/drivers/infiniband/hw/mlx5/devx.c
@@ -1895,8 +1895,10 @@ subscribe_event_xa_alloc(struct mlx5_devx_event_table *devx_event_table,
 				key_level2,
 				obj_event,
 				GFP_KERNEL);
-		if (err)
+		if (err) {
+			kfree(obj_event);
 			return err;
+		}
 		INIT_LIST_HEAD(&obj_event->obj_sub_list);
 	}
 
diff --git a/drivers/infiniband/hw/mlx5/ib_virt.c b/drivers/infiniband/hw/mlx5/ib_virt.c
index f2f62875d072..afeb5e53254f 100644
--- a/drivers/infiniband/hw/mlx5/ib_virt.c
+++ b/drivers/infiniband/hw/mlx5/ib_virt.c
@@ -30,7 +30,6 @@
  * SOFTWARE.
  */
 
-#include <linux/module.h>
 #include <linux/mlx5/vport.h>
 #include "mlx5_ib.h"
 
diff --git a/drivers/infiniband/hw/mlx5/mem.c b/drivers/infiniband/hw/mlx5/mem.c
index 844545064c9e..6191aa833ac2 100644
--- a/drivers/infiniband/hw/mlx5/mem.c
+++ b/drivers/infiniband/hw/mlx5/mem.c
@@ -30,7 +30,6 @@
  * SOFTWARE.
  */
 
-#include <linux/module.h>
 #include <rdma/ib_umem.h>
 #include <rdma/ib_umem_odp.h>
 #include "mlx5_ib.h"
diff --git a/drivers/infiniband/hw/mlx5/mlx5_ib.h b/drivers/infiniband/hw/mlx5/mlx5_ib.h
index cbc20e400be0..4f04bb55c4c6 100644
--- a/drivers/infiniband/hw/mlx5/mlx5_ib.h
+++ b/drivers/infiniband/hw/mlx5/mlx5_ib.h
@@ -763,9 +763,9 @@ struct mlx5_cache_ent {
 
 	char                    name[4];
 	u32                     order;
-	u32			xlt;
 	u32			access_mode;
 	u32			page;
+	unsigned int		ndescs;
 
 	u8 disabled:1;
 	u8 fill_to_high_water:1;
@@ -788,7 +788,6 @@ struct mlx5_cache_ent {
 	u32                     miss;
 
 	struct mlx5_ib_dev     *dev;
-	struct work_struct	work;
 	struct delayed_work	dwork;
 };
 
@@ -1344,7 +1343,8 @@ int mlx5_mr_cache_init(struct mlx5_ib_dev *dev);
 int mlx5_mr_cache_cleanup(struct mlx5_ib_dev *dev);
 
 struct mlx5_ib_mr *mlx5_mr_cache_alloc(struct mlx5_ib_dev *dev,
-				       unsigned int entry, int access_flags);
+				       struct mlx5_cache_ent *ent,
+				       int access_flags);
 
 int mlx5_ib_check_mr_status(struct ib_mr *ibmr, u32 check_mask,
 			    struct ib_mr_status *mr_status);
@@ -1539,12 +1539,6 @@ static inline int get_uars_per_sys_page(struct mlx5_ib_dev *dev, bool lib_suppor
 				MLX5_UARS_IN_PAGE : 1;
 }
 
-static inline int get_num_static_uars(struct mlx5_ib_dev *dev,
-				      struct mlx5_bfreg_info *bfregi)
-{
-	return get_uars_per_sys_page(dev, bfregi->lib_uar_4k) * bfregi->num_static_sys_pages;
-}
-
 extern void *xlt_emergency_page;
 
 int bfregn_to_uar_index(struct mlx5_ib_dev *dev,
diff --git a/drivers/infiniband/hw/mlx5/mr.c b/drivers/infiniband/hw/mlx5/mr.c
index 32cb7068f0ca..956f8e875daa 100644
--- a/drivers/infiniband/hw/mlx5/mr.c
+++ b/drivers/infiniband/hw/mlx5/mr.c
@@ -68,7 +68,6 @@ static void set_mkc_access_pd_addr_fields(void *mkc, int acc, u64 start_addr,
 					  struct ib_pd *pd)
 {
 	struct mlx5_ib_dev *dev = to_mdev(pd->device);
-	bool ro_pci_enabled = pcie_relaxed_ordering_enabled(dev->mdev->pdev);
 
 	MLX5_SET(mkc, mkc, a, !!(acc & IB_ACCESS_REMOTE_ATOMIC));
 	MLX5_SET(mkc, mkc, rw, !!(acc & IB_ACCESS_REMOTE_WRITE));
@@ -76,12 +75,13 @@ static void set_mkc_access_pd_addr_fields(void *mkc, int acc, u64 start_addr,
 	MLX5_SET(mkc, mkc, lw, !!(acc & IB_ACCESS_LOCAL_WRITE));
 	MLX5_SET(mkc, mkc, lr, 1);
 
-	if (MLX5_CAP_GEN(dev->mdev, relaxed_ordering_write))
-		MLX5_SET(mkc, mkc, relaxed_ordering_write,
-			 (acc & IB_ACCESS_RELAXED_ORDERING) && ro_pci_enabled);
-	if (MLX5_CAP_GEN(dev->mdev, relaxed_ordering_read))
-		MLX5_SET(mkc, mkc, relaxed_ordering_read,
-			 (acc & IB_ACCESS_RELAXED_ORDERING) && ro_pci_enabled);
+	if ((acc & IB_ACCESS_RELAXED_ORDERING) &&
+	    pcie_relaxed_ordering_enabled(dev->mdev->pdev)) {
+		if (MLX5_CAP_GEN(dev->mdev, relaxed_ordering_write))
+			MLX5_SET(mkc, mkc, relaxed_ordering_write, 1);
+		if (MLX5_CAP_GEN(dev->mdev, relaxed_ordering_read))
+			MLX5_SET(mkc, mkc, relaxed_ordering_read, 1);
+	}
 
 	MLX5_SET(mkc, mkc, pd, to_mpd(pd)->pdn);
 	MLX5_SET(mkc, mkc, qpn, 0xffffff);
@@ -189,6 +189,25 @@ static void create_mkey_callback(int status, struct mlx5_async_work *context)
 	spin_unlock_irqrestore(&ent->lock, flags);
 }
 
+static int get_mkc_octo_size(unsigned int access_mode, unsigned int ndescs)
+{
+	int ret = 0;
+
+	switch (access_mode) {
+	case MLX5_MKC_ACCESS_MODE_MTT:
+		ret = DIV_ROUND_UP(ndescs, MLX5_IB_UMR_OCTOWORD /
+						   sizeof(struct mlx5_mtt));
+		break;
+	case MLX5_MKC_ACCESS_MODE_KSM:
+		ret = DIV_ROUND_UP(ndescs, MLX5_IB_UMR_OCTOWORD /
+						   sizeof(struct mlx5_klm));
+		break;
+	default:
+		WARN_ON(1);
+	}
+	return ret;
+}
+
 static struct mlx5_ib_mr *alloc_cache_mr(struct mlx5_cache_ent *ent, void *mkc)
 {
 	struct mlx5_ib_mr *mr;
@@ -204,7 +223,8 @@ static struct mlx5_ib_mr *alloc_cache_mr(struct mlx5_cache_ent *ent, void *mkc)
 	MLX5_SET(mkc, mkc, access_mode_1_0, ent->access_mode & 0x3);
 	MLX5_SET(mkc, mkc, access_mode_4_2, (ent->access_mode >> 2) & 0x7);
 
-	MLX5_SET(mkc, mkc, translations_octword_size, ent->xlt);
+	MLX5_SET(mkc, mkc, translations_octword_size,
+		 get_mkc_octo_size(ent->access_mode, ent->ndescs));
 	MLX5_SET(mkc, mkc, log_page_size, ent->page);
 	return mr;
 }
@@ -478,14 +498,14 @@ static void queue_adjust_cache_locked(struct mlx5_cache_ent *ent)
 		return;
 	if (ent->available_mrs < ent->limit) {
 		ent->fill_to_high_water = true;
-		queue_work(ent->dev->cache.wq, &ent->work);
+		mod_delayed_work(ent->dev->cache.wq, &ent->dwork, 0);
 	} else if (ent->fill_to_high_water &&
 		   ent->available_mrs + ent->pending < 2 * ent->limit) {
 		/*
 		 * Once we start populating due to hitting a low water mark
 		 * continue until we pass the high water mark.
 		 */
-		queue_work(ent->dev->cache.wq, &ent->work);
+		mod_delayed_work(ent->dev->cache.wq, &ent->dwork, 0);
 	} else if (ent->available_mrs == 2 * ent->limit) {
 		ent->fill_to_high_water = false;
 	} else if (ent->available_mrs > 2 * ent->limit) {
@@ -495,7 +515,7 @@ static void queue_adjust_cache_locked(struct mlx5_cache_ent *ent)
 			queue_delayed_work(ent->dev->cache.wq, &ent->dwork,
 					   msecs_to_jiffies(1000));
 		else
-			queue_work(ent->dev->cache.wq, &ent->work);
+			mod_delayed_work(ent->dev->cache.wq, &ent->dwork, 0);
 	}
 }
 
@@ -571,33 +591,20 @@ static void delayed_cache_work_func(struct work_struct *work)
 	__cache_work_func(ent);
 }
 
-static void cache_work_func(struct work_struct *work)
-{
-	struct mlx5_cache_ent *ent;
-
-	ent = container_of(work, struct mlx5_cache_ent, work);
-	__cache_work_func(ent);
-}
-
-/* Allocate a special entry from the cache */
 struct mlx5_ib_mr *mlx5_mr_cache_alloc(struct mlx5_ib_dev *dev,
-				       unsigned int entry, int access_flags)
+				       struct mlx5_cache_ent *ent,
+				       int access_flags)
 {
-	struct mlx5_mr_cache *cache = &dev->cache;
-	struct mlx5_cache_ent *ent;
 	struct mlx5_ib_mr *mr;
 
-	if (WARN_ON(entry <= MR_CACHE_LAST_STD_ENTRY ||
-		    entry >= ARRAY_SIZE(cache->ent)))
-		return ERR_PTR(-EINVAL);
-
 	/* Matches access in alloc_cache_mr() */
 	if (!mlx5_ib_can_reconfig_with_umr(dev, 0, access_flags))
 		return ERR_PTR(-EOPNOTSUPP);
 
-	ent = &cache->ent[entry];
 	spin_lock_irq(&ent->lock);
 	if (list_empty(&ent->head)) {
+		queue_adjust_cache_locked(ent);
+		ent->miss++;
 		spin_unlock_irq(&ent->lock);
 		mr = create_cache_mr(ent);
 		if (IS_ERR(mr))
@@ -611,32 +618,9 @@ struct mlx5_ib_mr *mlx5_mr_cache_alloc(struct mlx5_ib_dev *dev,
 
 		mlx5_clear_mr(mr);
 	}
-	mr->access_flags = access_flags;
 	return mr;
 }
 
-/* Return a MR already available in the cache */
-static struct mlx5_ib_mr *get_cache_mr(struct mlx5_cache_ent *req_ent)
-{
-	struct mlx5_ib_mr *mr = NULL;
-	struct mlx5_cache_ent *ent = req_ent;
-
-	spin_lock_irq(&ent->lock);
-	if (!list_empty(&ent->head)) {
-		mr = list_first_entry(&ent->head, struct mlx5_ib_mr, list);
-		list_del(&mr->list);
-		ent->available_mrs--;
-		queue_adjust_cache_locked(ent);
-		spin_unlock_irq(&ent->lock);
-		mlx5_clear_mr(mr);
-		return mr;
-	}
-	queue_adjust_cache_locked(ent);
-	spin_unlock_irq(&ent->lock);
-	req_ent->miss++;
-	return NULL;
-}
-
 static void mlx5_mr_cache_free(struct mlx5_ib_dev *dev, struct mlx5_ib_mr *mr)
 {
 	struct mlx5_cache_ent *ent = mr->cache_ent;
@@ -739,7 +723,6 @@ int mlx5_mr_cache_init(struct mlx5_ib_dev *dev)
 		ent->dev = dev;
 		ent->limit = 0;
 
-		INIT_WORK(&ent->work, cache_work_func);
 		INIT_DELAYED_WORK(&ent->dwork, delayed_cache_work_func);
 
 		if (i > MR_CACHE_LAST_STD_ENTRY) {
@@ -751,8 +734,7 @@ int mlx5_mr_cache_init(struct mlx5_ib_dev *dev)
 			continue;
 
 		ent->page = PAGE_SHIFT;
-		ent->xlt = (1 << ent->order) * sizeof(struct mlx5_mtt) /
-			   MLX5_IB_UMR_OCTOWORD;
+		ent->ndescs = 1 << ent->order;
 		ent->access_mode = MLX5_MKC_ACCESS_MODE_MTT;
 		if ((dev->mdev->profile.mask & MLX5_PROF_MASK_MR_CACHE) &&
 		    !dev->is_rep && mlx5_core_is_pf(dev->mdev) &&
@@ -783,7 +765,6 @@ int mlx5_mr_cache_cleanup(struct mlx5_ib_dev *dev)
 		spin_lock_irq(&ent->lock);
 		ent->disabled = true;
 		spin_unlock_irq(&ent->lock);
-		cancel_work_sync(&ent->work);
 		cancel_delayed_work_sync(&ent->dwork);
 	}
 
@@ -972,16 +953,9 @@ static struct mlx5_ib_mr *alloc_cacheable_mr(struct ib_pd *pd,
 		return mr;
 	}
 
-	mr = get_cache_mr(ent);
-	if (!mr) {
-		mr = create_cache_mr(ent);
-		/*
-		 * The above already tried to do the same stuff as reg_create(),
-		 * no reason to try it again.
-		 */
-		if (IS_ERR(mr))
-			return mr;
-	}
+	mr = mlx5_mr_cache_alloc(dev, ent, access_flags);
+	if (IS_ERR(mr))
+		return mr;
 
 	mr->ibmr.pd = pd;
 	mr->umem = umem;
diff --git a/drivers/infiniband/hw/mlx5/odp.c b/drivers/infiniband/hw/mlx5/odp.c
index 86842cd580ba..41c964a45f89 100644
--- a/drivers/infiniband/hw/mlx5/odp.c
+++ b/drivers/infiniband/hw/mlx5/odp.c
@@ -407,6 +407,7 @@ static void mlx5_ib_page_fault_resume(struct mlx5_ib_dev *dev,
 static struct mlx5_ib_mr *implicit_get_child_mr(struct mlx5_ib_mr *imr,
 						unsigned long idx)
 {
+	struct mlx5_ib_dev *dev = mr_to_mdev(imr);
 	struct ib_umem_odp *odp;
 	struct mlx5_ib_mr *mr;
 	struct mlx5_ib_mr *ret;
@@ -418,13 +419,14 @@ static struct mlx5_ib_mr *implicit_get_child_mr(struct mlx5_ib_mr *imr,
 	if (IS_ERR(odp))
 		return ERR_CAST(odp);
 
-	mr = mlx5_mr_cache_alloc(
-		mr_to_mdev(imr), MLX5_IMR_MTT_CACHE_ENTRY, imr->access_flags);
+	mr = mlx5_mr_cache_alloc(dev, &dev->cache.ent[MLX5_IMR_MTT_CACHE_ENTRY],
+				 imr->access_flags);
 	if (IS_ERR(mr)) {
 		ib_umem_odp_release(odp);
 		return mr;
 	}
 
+	mr->access_flags = imr->access_flags;
 	mr->ibmr.pd = imr->ibmr.pd;
 	mr->ibmr.device = &mr_to_mdev(imr)->ib_dev;
 	mr->umem = &odp->umem;
@@ -493,12 +495,15 @@ struct mlx5_ib_mr *mlx5_ib_alloc_implicit_mr(struct mlx5_ib_pd *pd,
 	if (IS_ERR(umem_odp))
 		return ERR_CAST(umem_odp);
 
-	imr = mlx5_mr_cache_alloc(dev, MLX5_IMR_KSM_CACHE_ENTRY, access_flags);
+	imr = mlx5_mr_cache_alloc(dev,
+				  &dev->cache.ent[MLX5_IMR_KSM_CACHE_ENTRY],
+				  access_flags);
 	if (IS_ERR(imr)) {
 		ib_umem_odp_release(umem_odp);
 		return imr;
 	}
 
+	imr->access_flags = access_flags;
 	imr->ibmr.pd = &pd->ibpd;
 	imr->ibmr.iova = 0;
 	imr->umem = &umem_odp->umem;
@@ -1593,18 +1598,14 @@ void mlx5_odp_init_mr_cache_entry(struct mlx5_cache_ent *ent)
 	switch (ent->order - 2) {
 	case MLX5_IMR_MTT_CACHE_ENTRY:
 		ent->page = PAGE_SHIFT;
-		ent->xlt = MLX5_IMR_MTT_ENTRIES *
-			   sizeof(struct mlx5_mtt) /
-			   MLX5_IB_UMR_OCTOWORD;
+		ent->ndescs = MLX5_IMR_MTT_ENTRIES;
 		ent->access_mode = MLX5_MKC_ACCESS_MODE_MTT;
 		ent->limit = 0;
 		break;
 
 	case MLX5_IMR_KSM_CACHE_ENTRY:
 		ent->page = MLX5_KSM_PAGE_SHIFT;
-		ent->xlt = mlx5_imr_ksm_entries *
-			   sizeof(struct mlx5_klm) /
-			   MLX5_IB_UMR_OCTOWORD;
+		ent->ndescs = mlx5_imr_ksm_entries;
 		ent->access_mode = MLX5_MKC_ACCESS_MODE_KSM;
 		ent->limit = 0;
 		break;
diff --git a/drivers/infiniband/hw/mlx5/qp.c b/drivers/infiniband/hw/mlx5/qp.c
index b7fe47107d76..3f467557d34e 100644
--- a/drivers/infiniband/hw/mlx5/qp.c
+++ b/drivers/infiniband/hw/mlx5/qp.c
@@ -31,7 +31,6 @@
  */
 
 #include <linux/etherdevice.h>
-#include <linux/module.h>
 #include <rdma/ib_umem.h>
 #include <rdma/ib_cache.h>
 #include <rdma/ib_user_verbs.h>
@@ -615,7 +614,8 @@ enum {
 
 static int max_bfregs(struct mlx5_ib_dev *dev, struct mlx5_bfreg_info *bfregi)
 {
-	return get_num_static_uars(dev, bfregi) * MLX5_NON_FP_BFREGS_PER_UAR;
+	return get_uars_per_sys_page(dev, bfregi->lib_uar_4k) *
+	       bfregi->num_static_sys_pages * MLX5_NON_FP_BFREGS_PER_UAR;
 }
 
 static int num_med_bfreg(struct mlx5_ib_dev *dev,
diff --git a/drivers/infiniband/hw/mlx5/srq.c b/drivers/infiniband/hw/mlx5/srq.c
index 191c4ee7db62..09b365a98bbf 100644
--- a/drivers/infiniband/hw/mlx5/srq.c
+++ b/drivers/infiniband/hw/mlx5/srq.c
@@ -3,7 +3,6 @@
  * Copyright (c) 2013-2018, Mellanox Technologies inc.  All rights reserved.
  */
 
-#include <linux/module.h>
 #include <linux/mlx5/qp.h>
 #include <linux/slab.h>
 #include <rdma/ib_umem.h>