7 files changed, 66 insertions, 42 deletions

diff --git a/drivers/infiniband/hw/mlx5/devx.c b/drivers/infiniband/hw/mlx5/devx.c
index ec4370f99381..af5bbb35c058 100644
--- a/drivers/infiniband/hw/mlx5/devx.c
+++ b/drivers/infiniband/hw/mlx5/devx.c
@@ -2026,7 +2026,7 @@ static int UVERBS_HANDLER(MLX5_IB_METHOD_DEVX_SUBSCRIBE_EVENT)(
 			event_sub->eventfd =
 				eventfd_ctx_fdget(redirect_fd);
 
-			if (IS_ERR(event_sub)) {
+			if (IS_ERR(event_sub->eventfd)) {
 				err = PTR_ERR(event_sub->eventfd);
 				event_sub->eventfd = NULL;
 				goto err;
@@ -2644,12 +2644,13 @@ static int devx_async_event_close(struct inode *inode, struct file *filp)
 	struct devx_async_event_file *ev_file = filp->private_data;
 	struct devx_event_subscription *event_sub, *event_sub_tmp;
 	struct devx_async_event_data *entry, *tmp;
+	struct mlx5_ib_dev *dev = ev_file->dev;
 
-	mutex_lock(&ev_file->dev->devx_event_table.event_xa_lock);
+	mutex_lock(&dev->devx_event_table.event_xa_lock);
 	/* delete the subscriptions which are related to this FD */
 	list_for_each_entry_safe(event_sub, event_sub_tmp,
 				 &ev_file->subscribed_events_list, file_list) {
-		devx_cleanup_subscription(ev_file->dev, event_sub);
+		devx_cleanup_subscription(dev, event_sub);
 		if (event_sub->eventfd)
 			eventfd_ctx_put(event_sub->eventfd);
 
@@ -2658,7 +2659,7 @@ static int devx_async_event_close(struct inode *inode, struct file *filp)
 		kfree_rcu(event_sub, rcu);
 	}
 
-	mutex_unlock(&ev_file->dev->devx_event_table.event_xa_lock);
+	mutex_unlock(&dev->devx_event_table.event_xa_lock);
 
 	/* free the pending events allocation */
 	if (!ev_file->omit_data) {
@@ -2670,7 +2671,7 @@ static int devx_async_event_close(struct inode *inode, struct file *filp)
 	}
 
 	uverbs_close_fd(filp);
-	put_device(&ev_file->dev->ib_dev.dev);
+	put_device(&dev->ib_dev.dev);
 	return 0;
 }
 
diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c
index e12a4404096b..0569bcab02d4 100644
--- a/drivers/infiniband/hw/mlx5/main.c
+++ b/drivers/infiniband/hw/mlx5/main.c
@@ -1023,7 +1023,7 @@ static int mlx5_ib_query_device(struct ib_device *ibdev,
 	props->timestamp_mask = 0x7FFFFFFFFFFFFFFFULL;
 
 	if (IS_ENABLED(CONFIG_INFINIBAND_ON_DEMAND_PAGING)) {
-		if (MLX5_CAP_GEN(mdev, pg))
+		if (dev->odp_caps.general_caps & IB_ODP_SUPPORT)
 			props->device_cap_flags |= IB_DEVICE_ON_DEMAND_PAGING;
 		props->odp_caps = dev->odp_caps;
 	}
@@ -6139,6 +6139,8 @@ static int mlx5_ib_stage_init_init(struct mlx5_ib_dev *dev)
 		dev->port[i].roce.last_port_state = IB_PORT_DOWN;
 	}
 
+	mlx5_ib_internal_fill_odp_caps(dev);
+
 	err = mlx5_ib_init_multiport_master(dev);
 	if (err)
 		return err;
@@ -6563,8 +6565,6 @@ static void mlx5_ib_stage_dev_res_cleanup(struct mlx5_ib_dev *dev)
 
 static int mlx5_ib_stage_odp_init(struct mlx5_ib_dev *dev)
 {
-	mlx5_ib_internal_fill_odp_caps(dev);
-
 	return mlx5_ib_odp_init_one(dev);
 }
 
diff --git a/drivers/infiniband/hw/mlx5/mem.c b/drivers/infiniband/hw/mlx5/mem.c
index fe1a76d8531c..a40e0abf2338 100644
--- a/drivers/infiniband/hw/mlx5/mem.c
+++ b/drivers/infiniband/hw/mlx5/mem.c
@@ -57,9 +57,10 @@ void mlx5_ib_cont_pages(struct ib_umem *umem, u64 addr,
 	int entry;
 
 	if (umem->is_odp) {
-		unsigned int page_shift = to_ib_umem_odp(umem)->page_shift;
+		struct ib_umem_odp *odp = to_ib_umem_odp(umem);
+		unsigned int page_shift = odp->page_shift;
 
-		*ncont = ib_umem_page_count(umem);
+		*ncont = ib_umem_odp_num_pages(odp);
 		*count = *ncont << (page_shift - PAGE_SHIFT);
 		*shift = page_shift;
 		if (order)
diff --git a/drivers/infiniband/hw/mlx5/mlx5_ib.h b/drivers/infiniband/hw/mlx5/mlx5_ib.h
index f6a53455bf8b..9ae587b74b12 100644
--- a/drivers/infiniband/hw/mlx5/mlx5_ib.h
+++ b/drivers/infiniband/hw/mlx5/mlx5_ib.h
@@ -1475,4 +1475,18 @@ int bfregn_to_uar_index(struct mlx5_ib_dev *dev,
 			bool dyn_bfreg);
 
 int mlx5_ib_qp_set_counter(struct ib_qp *qp, struct rdma_counter *counter);
+
+static inline bool mlx5_ib_can_use_umr(struct mlx5_ib_dev *dev,
+				       bool do_modify_atomic)
+{
+	if (MLX5_CAP_GEN(dev->mdev, umr_modify_entity_size_disabled))
+		return false;
+
+	if (do_modify_atomic &&
+	    MLX5_CAP_GEN(dev->mdev, atomic) &&
+	    MLX5_CAP_GEN(dev->mdev, umr_modify_atomic_disabled))
+		return false;
+
+	return true;
+}
 #endif /* MLX5_IB_H */
diff --git a/drivers/infiniband/hw/mlx5/mr.c b/drivers/infiniband/hw/mlx5/mr.c
index b74fad08412f..3401f5f6792e 100644
--- a/drivers/infiniband/hw/mlx5/mr.c
+++ b/drivers/infiniband/hw/mlx5/mr.c
@@ -1293,9 +1293,7 @@ struct ib_mr *mlx5_ib_reg_user_mr(struct ib_pd *pd, u64 start, u64 length,
 	if (err < 0)
 		return ERR_PTR(err);
 
-	use_umr = !MLX5_CAP_GEN(dev->mdev, umr_modify_entity_size_disabled) &&
-		  (!MLX5_CAP_GEN(dev->mdev, umr_modify_atomic_disabled) ||
-		   !MLX5_CAP_GEN(dev->mdev, atomic));
+	use_umr = mlx5_ib_can_use_umr(dev, true);
 
 	if (order <= mr_cache_max_order(dev) && use_umr) {
 		mr = alloc_mr_from_cache(pd, umem, virt_addr, length, ncont,
@@ -1448,7 +1446,8 @@ int mlx5_ib_rereg_user_mr(struct ib_mr *ib_mr, int flags, u64 start,
 			goto err;
 	}
 
-	if (flags & IB_MR_REREG_TRANS && !use_umr_mtt_update(mr, addr, len)) {
+	if (!mlx5_ib_can_use_umr(dev, true) ||
+	    (flags & IB_MR_REREG_TRANS && !use_umr_mtt_update(mr, addr, len))) {
 		/*
 		 * UMR can't be used - MKey needs to be replaced.
 		 */
diff --git a/drivers/infiniband/hw/mlx5/odp.c b/drivers/infiniband/hw/mlx5/odp.c
index 81da82050d05..0a59912a4cef 100644
--- a/drivers/infiniband/hw/mlx5/odp.c
+++ b/drivers/infiniband/hw/mlx5/odp.c
@@ -301,7 +301,8 @@ void mlx5_ib_internal_fill_odp_caps(struct mlx5_ib_dev *dev)
 
 	memset(caps, 0, sizeof(*caps));
 
-	if (!MLX5_CAP_GEN(dev->mdev, pg))
+	if (!MLX5_CAP_GEN(dev->mdev, pg) ||
+	    !mlx5_ib_can_use_umr(dev, true))
 		return;
 
 	caps->general_caps = IB_ODP_SUPPORT;
@@ -355,7 +356,8 @@ void mlx5_ib_internal_fill_odp_caps(struct mlx5_ib_dev *dev)
 
 	if (MLX5_CAP_GEN(dev->mdev, fixed_buffer_size) &&
 	    MLX5_CAP_GEN(dev->mdev, null_mkey) &&
-	    MLX5_CAP_GEN(dev->mdev, umr_extended_translation_offset))
+	    MLX5_CAP_GEN(dev->mdev, umr_extended_translation_offset) &&
+	    !MLX5_CAP_GEN(dev->mdev, umr_indirect_mkey_disabled))
 		caps->general_caps |= IB_ODP_SUPPORT_IMPLICIT;
 
 	return;
@@ -579,7 +581,6 @@ static int pagefault_mr(struct mlx5_ib_dev *dev, struct mlx5_ib_mr *mr,
 			u32 flags)
 {
 	int npages = 0, current_seq, page_shift, ret, np;
-	bool implicit = false;
 	struct ib_umem_odp *odp_mr = to_ib_umem_odp(mr->umem);
 	bool downgrade = flags & MLX5_PF_FLAGS_DOWNGRADE;
 	bool prefetch = flags & MLX5_PF_FLAGS_PREFETCH;
@@ -594,7 +595,6 @@ static int pagefault_mr(struct mlx5_ib_dev *dev, struct mlx5_ib_mr *mr,
 		if (IS_ERR(odp))
 			return PTR_ERR(odp);
 		mr = odp->private;
-		implicit = true;
 	} else {
 		odp = odp_mr;
 	}
@@ -682,19 +682,15 @@ next_mr:
 
 out:
 	if (ret == -EAGAIN) {
-		if (implicit || !odp->dying) {
-			unsigned long timeout =
-				msecs_to_jiffies(MMU_NOTIFIER_TIMEOUT);
-
-			if (!wait_for_completion_timeout(
-					&odp->notifier_completion,
-					timeout)) {
-				mlx5_ib_warn(dev, "timeout waiting for mmu notifier. seq %d against %d. notifiers_count=%d\n",
-					     current_seq, odp->notifiers_seq, odp->notifiers_count);
-			}
-		} else {
-			/* The MR is being killed, kill the QP as well. */
-			ret = -EFAULT;
+		unsigned long timeout = msecs_to_jiffies(MMU_NOTIFIER_TIMEOUT);
+
+		if (!wait_for_completion_timeout(&odp->notifier_completion,
+						 timeout)) {
+			mlx5_ib_warn(
+				dev,
+				"timeout waiting for mmu notifier. seq %d against %d. notifiers_count=%d\n",
+				current_seq, odp->notifiers_seq,
+				odp->notifiers_count);
 		}
 	}
 
@@ -1628,8 +1624,10 @@ int mlx5_ib_odp_init_one(struct mlx5_ib_dev *dev)
 {
 	int ret = 0;
 
-	if (dev->odp_caps.general_caps & IB_ODP_SUPPORT)
-		ib_set_device_ops(&dev->ib_dev, &mlx5_ib_dev_odp_ops);
+	if (!(dev->odp_caps.general_caps & IB_ODP_SUPPORT))
+		return ret;
+
+	ib_set_device_ops(&dev->ib_dev, &mlx5_ib_dev_odp_ops);
 
 	if (dev->odp_caps.general_caps & IB_ODP_SUPPORT_IMPLICIT) {
 		ret = mlx5_cmd_null_mkey(dev->mdev, &dev->null_mkey);
@@ -1639,9 +1637,6 @@ int mlx5_ib_odp_init_one(struct mlx5_ib_dev *dev)
 		}
 	}
 
-	if (!MLX5_CAP_GEN(dev->mdev, pg))
-		return ret;
-
 	ret = mlx5_ib_create_pf_eq(dev, &dev->odp_pf_eq);
 
 	return ret;
@@ -1649,7 +1644,7 @@ int mlx5_ib_odp_init_one(struct mlx5_ib_dev *dev)
 
 void mlx5_ib_odp_cleanup_one(struct mlx5_ib_dev *dev)
 {
-	if (!MLX5_CAP_GEN(dev->mdev, pg))
+	if (!(dev->odp_caps.general_caps & IB_ODP_SUPPORT))
 		return;
 
 	mlx5_ib_destroy_pf_eq(dev, &dev->odp_pf_eq);
diff --git a/drivers/infiniband/hw/mlx5/qp.c b/drivers/infiniband/hw/mlx5/qp.c
index 379328b2598f..72869ff4a334 100644
--- a/drivers/infiniband/hw/mlx5/qp.c
+++ b/drivers/infiniband/hw/mlx5/qp.c
@@ -4162,7 +4162,7 @@ static u64 get_xlt_octo(u64 bytes)
 	       MLX5_IB_UMR_OCTOWORD;
 }
 
-static __be64 frwr_mkey_mask(void)
+static __be64 frwr_mkey_mask(bool atomic)
 {
 	u64 result;
 
@@ -4175,10 +4175,12 @@ static __be64 frwr_mkey_mask(void)
 		MLX5_MKEY_MASK_LW		|
 		MLX5_MKEY_MASK_RR		|
 		MLX5_MKEY_MASK_RW		|
-		MLX5_MKEY_MASK_A		|
 		MLX5_MKEY_MASK_SMALL_FENCE	|
 		MLX5_MKEY_MASK_FREE;
 
+	if (atomic)
+		result |= MLX5_MKEY_MASK_A;
+
 	return cpu_to_be64(result);
 }
 
@@ -4204,7 +4206,7 @@ static __be64 sig_mkey_mask(void)
 }
 
 static void set_reg_umr_seg(struct mlx5_wqe_umr_ctrl_seg *umr,
-			    struct mlx5_ib_mr *mr, u8 flags)
+			    struct mlx5_ib_mr *mr, u8 flags, bool atomic)
 {
 	int size = (mr->ndescs + mr->meta_ndescs) * mr->desc_size;
 
@@ -4212,7 +4214,7 @@ static void set_reg_umr_seg(struct mlx5_wqe_umr_ctrl_seg *umr,
 
 	umr->flags = flags;
 	umr->xlt_octowords = cpu_to_be16(get_xlt_octo(size));
-	umr->mkey_mask = frwr_mkey_mask();
+	umr->mkey_mask = frwr_mkey_mask(atomic);
 }
 
 static void set_linv_umr_seg(struct mlx5_wqe_umr_ctrl_seg *umr)
@@ -4811,10 +4813,22 @@ static int set_reg_wr(struct mlx5_ib_qp *qp,
 {
 	struct mlx5_ib_mr *mr = to_mmr(wr->mr);
 	struct mlx5_ib_pd *pd = to_mpd(qp->ibqp.pd);
+	struct mlx5_ib_dev *dev = to_mdev(pd->ibpd.device);
 	int mr_list_size = (mr->ndescs + mr->meta_ndescs) * mr->desc_size;
 	bool umr_inline = mr_list_size <= MLX5_IB_SQ_UMR_INLINE_THRESHOLD;
+	bool atomic = wr->access & IB_ACCESS_REMOTE_ATOMIC;
 	u8 flags = 0;
 
+	if (!mlx5_ib_can_use_umr(dev, atomic)) {
+		mlx5_ib_warn(to_mdev(qp->ibqp.device),
+			     "Fast update of %s for MR is disabled\n",
+			     (MLX5_CAP_GEN(dev->mdev,
+					   umr_modify_entity_size_disabled)) ?
+				     "entity size" :
+				     "atomic access");
+		return -EINVAL;
+	}
+
 	if (unlikely(wr->wr.send_flags & IB_SEND_INLINE)) {
 		mlx5_ib_warn(to_mdev(qp->ibqp.device),
 			     "Invalid IB_SEND_INLINE send flag\n");
@@ -4826,7 +4840,7 @@ static int set_reg_wr(struct mlx5_ib_qp *qp,
 	if (umr_inline)
 		flags |= MLX5_UMR_INLINE;
 
-	set_reg_umr_seg(*seg, mr, flags);
+	set_reg_umr_seg(*seg, mr, flags, atomic);
 	*seg += sizeof(struct mlx5_wqe_umr_ctrl_seg);
 	*size += sizeof(struct mlx5_wqe_umr_ctrl_seg) / 16;
 	handle_post_send_edge(&qp->sq, seg, *size, cur_edge);