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

Pull rdma updates from Jason Gunthorpe:

 - Usual minor updates and fixes for bnxt_re, hfi1, rxe, mana, iser,
   mlx5, vmw_pvrdma, hns

 - Make rxe work on tun devices

 - mana gains more standard verbs as it moves toward supporting
   in-kernel verbs

 - DMABUF support for mana

 - Fix page size calculations when memory registration exceeds 4G

 - On Demand Paging support for rxe

 - mlx5 support for RDMA TRANSPORT flow tables and a new ucap mechanism
   to access control use of them

 - Optional RDMA_TX/RX counters per QP in mlx5

* tag 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/rdma/rdma: (73 commits)
  IB/mad: Check available slots before posting receive WRs
  RDMA/mana_ib: Fix integer overflow during queue creation
  RDMA/mlx5: Fix calculation of total invalidated pages
  RDMA/mlx5: Fix mlx5_poll_one() cur_qp update flow
  RDMA/mlx5: Fix page_size variable overflow
  RDMA/mlx5: Drop access_flags from _mlx5_mr_cache_alloc()
  RDMA/mlx5: Fix cache entry update on dereg error
  RDMA/mlx5: Fix MR cache initialization error flow
  RDMA/mlx5: Support optional-counters binding for QPs
  RDMA/mlx5: Compile fs.c regardless of INFINIBAND_USER_ACCESS config
  RDMA/core: Pass port to counter bind/unbind operations
  RDMA/core: Add support to optional-counters binding configuration
  RDMA/core: Create and destroy rdma_counter using rdma_zalloc_drv_obj()
  RDMA/mlx5: Add optional counters for RDMA_TX/RX_packets/bytes
  RDMA/core: Fix use-after-free when rename device name
  RDMA/bnxt_re: Support perf management counters
  RDMA/rxe: Fix incorrect return value of rxe_odp_atomic_op()
  RDMA/uverbs: Propagate errors from rdma_lookup_get_uobject()
  RDMA/mana_ib: Handle net event for pointing to the current netdev
  net: mana: Change the function signature of mana_get_primary_netdev_rcu
  ...

1 files changed, 32 insertions, 20 deletions

diff --git a/drivers/infiniband/hw/mlx5/mr.c b/drivers/infiniband/hw/mlx5/mr.c
index 753faa9ad06a..b7c8c926c578 100644
--- a/drivers/infiniband/hw/mlx5/mr.c
+++ b/drivers/infiniband/hw/mlx5/mr.c
@@ -56,7 +56,7 @@ static void
 create_mkey_callback(int status, struct mlx5_async_work *context);
 static struct mlx5_ib_mr *reg_create(struct ib_pd *pd, struct ib_umem *umem,
 				     u64 iova, int access_flags,
-				     unsigned int page_size, bool populate,
+				     unsigned long page_size, bool populate,
 				     int access_mode);
 static int __mlx5_ib_dereg_mr(struct ib_mr *ibmr);
 
@@ -718,8 +718,7 @@ mkey_cache_ent_from_rb_key(struct mlx5_ib_dev *dev,
 }
 
 static struct mlx5_ib_mr *_mlx5_mr_cache_alloc(struct mlx5_ib_dev *dev,
-					struct mlx5_cache_ent *ent,
-					int access_flags)
+					       struct mlx5_cache_ent *ent)
 {
 	struct mlx5_ib_mr *mr;
 	int err;
@@ -794,7 +793,7 @@ struct mlx5_ib_mr *mlx5_mr_cache_alloc(struct mlx5_ib_dev *dev,
 	if (!ent)
 		return ERR_PTR(-EOPNOTSUPP);
 
-	return _mlx5_mr_cache_alloc(dev, ent, access_flags);
+	return _mlx5_mr_cache_alloc(dev, ent);
 }
 
 static void mlx5_mkey_cache_debugfs_cleanup(struct mlx5_ib_dev *dev)
@@ -919,6 +918,25 @@ mkeys_err:
 	return ERR_PTR(ret);
 }
 
+static void mlx5r_destroy_cache_entries(struct mlx5_ib_dev *dev)
+{
+	struct rb_root *root = &dev->cache.rb_root;
+	struct mlx5_cache_ent *ent;
+	struct rb_node *node;
+
+	mutex_lock(&dev->cache.rb_lock);
+	node = rb_first(root);
+	while (node) {
+		ent = rb_entry(node, struct mlx5_cache_ent, node);
+		node = rb_next(node);
+		clean_keys(dev, ent);
+		rb_erase(&ent->node, root);
+		mlx5r_mkeys_uninit(ent);
+		kfree(ent);
+	}
+	mutex_unlock(&dev->cache.rb_lock);
+}
+
 int mlx5_mkey_cache_init(struct mlx5_ib_dev *dev)
 {
 	struct mlx5_mkey_cache *cache = &dev->cache;
@@ -970,6 +988,8 @@ int mlx5_mkey_cache_init(struct mlx5_ib_dev *dev)
 err:
 	mutex_unlock(&cache->rb_lock);
 	mlx5_mkey_cache_debugfs_cleanup(dev);
+	mlx5r_destroy_cache_entries(dev);
+	destroy_workqueue(cache->wq);
 	mlx5_ib_warn(dev, "failed to create mkey cache entry\n");
 	return ret;
 }
@@ -1003,17 +1023,7 @@ void mlx5_mkey_cache_cleanup(struct mlx5_ib_dev *dev)
 	mlx5_cmd_cleanup_async_ctx(&dev->async_ctx);
 
 	/* At this point all entries are disabled and have no concurrent work. */
-	mutex_lock(&dev->cache.rb_lock);
-	node = rb_first(root);
-	while (node) {
-		ent = rb_entry(node, struct mlx5_cache_ent, node);
-		node = rb_next(node);
-		clean_keys(dev, ent);
-		rb_erase(&ent->node, root);
-		mlx5r_mkeys_uninit(ent);
-		kfree(ent);
-	}
-	mutex_unlock(&dev->cache.rb_lock);
+	mlx5r_destroy_cache_entries(dev);
 
 	destroy_workqueue(dev->cache.wq);
 	del_timer_sync(&dev->delay_timer);
@@ -1115,7 +1125,7 @@ static struct mlx5_ib_mr *alloc_cacheable_mr(struct ib_pd *pd,
 	struct mlx5r_cache_rb_key rb_key = {};
 	struct mlx5_cache_ent *ent;
 	struct mlx5_ib_mr *mr;
-	unsigned int page_size;
+	unsigned long page_size;
 
 	if (umem->is_dmabuf)
 		page_size = mlx5_umem_dmabuf_default_pgsz(umem, iova);
@@ -1144,7 +1154,7 @@ static struct mlx5_ib_mr *alloc_cacheable_mr(struct ib_pd *pd,
 		return mr;
 	}
 
-	mr = _mlx5_mr_cache_alloc(dev, ent, access_flags);
+	mr = _mlx5_mr_cache_alloc(dev, ent);
 	if (IS_ERR(mr))
 		return mr;
 
@@ -1219,7 +1229,7 @@ err_1:
  */
 static struct mlx5_ib_mr *reg_create(struct ib_pd *pd, struct ib_umem *umem,
 				     u64 iova, int access_flags,
-				     unsigned int page_size, bool populate,
+				     unsigned long page_size, bool populate,
 				     int access_mode)
 {
 	struct mlx5_ib_dev *dev = to_mdev(pd->device);
@@ -1425,7 +1435,7 @@ static struct ib_mr *create_real_mr(struct ib_pd *pd, struct ib_umem *umem,
 		mr = alloc_cacheable_mr(pd, umem, iova, access_flags,
 					MLX5_MKC_ACCESS_MODE_MTT);
 	} else {
-		unsigned int page_size =
+		unsigned long page_size =
 			mlx5_umem_mkc_find_best_pgsz(dev, umem, iova);
 
 		mutex_lock(&dev->slow_path_mutex);
@@ -1957,7 +1967,6 @@ static int cache_ent_find_and_store(struct mlx5_ib_dev *dev,
 
 	if (mr->mmkey.cache_ent) {
 		spin_lock_irq(&mr->mmkey.cache_ent->mkeys_queue.lock);
-		mr->mmkey.cache_ent->in_use--;
 		goto end;
 	}
 
@@ -2025,6 +2034,7 @@ static int mlx5_revoke_mr(struct mlx5_ib_mr *mr)
 	bool is_odp = is_odp_mr(mr);
 	bool is_odp_dma_buf = is_dmabuf_mr(mr) &&
 			!to_ib_umem_dmabuf(mr->umem)->pinned;
+	bool from_cache = !!ent;
 	int ret = 0;
 
 	if (is_odp)
@@ -2037,6 +2047,8 @@ static int mlx5_revoke_mr(struct mlx5_ib_mr *mr)
 		ent = mr->mmkey.cache_ent;
 		/* upon storing to a clean temp entry - schedule its cleanup */
 		spin_lock_irq(&ent->mkeys_queue.lock);
+		if (from_cache)
+			ent->in_use--;
 		if (ent->is_tmp && !ent->tmp_cleanup_scheduled) {
 			mod_delayed_work(ent->dev->cache.wq, &ent->dwork,
 					 msecs_to_jiffies(30 * 1000));