1 files changed, 22 insertions, 26 deletions

diff --git a/drivers/infiniband/hw/mlx5/odp.c b/drivers/infiniband/hw/mlx5/odp.c
index 5b642d81e617..0a59912a4cef 100644
--- a/drivers/infiniband/hw/mlx5/odp.c
+++ b/drivers/infiniband/hw/mlx5/odp.c
@@ -246,7 +246,7 @@ void mlx5_ib_invalidate_range(struct ib_umem_odp *umem_odp, unsigned long start,
 	 * overwrite the same MTTs.  Concurent invalidations might race us,
 	 * but they will write 0s as well, so no difference in the end result.
 	 */
-
+	mutex_lock(&umem_odp->umem_mutex);
 	for (addr = start; addr < end; addr += BIT(umem_odp->page_shift)) {
 		idx = (addr - ib_umem_start(umem_odp)) >> umem_odp->page_shift;
 		/*
@@ -278,6 +278,7 @@ void mlx5_ib_invalidate_range(struct ib_umem_odp *umem_odp, unsigned long start,
 				   idx - blk_start_idx + 1, 0,
 				   MLX5_IB_UPD_XLT_ZAP |
 				   MLX5_IB_UPD_XLT_ATOMIC);
+	mutex_unlock(&umem_odp->umem_mutex);
 	/*
 	 * We are now sure that the device will not access the
 	 * memory. We can safely unmap it, and mark it as dirty if
@@ -300,7 +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;
@@ -354,7 +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;
@@ -578,7 +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;
@@ -593,7 +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;
 	}
@@ -681,19 +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);
 		}
 	}
 
@@ -1627,8 +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);
@@ -1638,9 +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;
@@ -1648,7 +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);
@@ -1771,7 +1767,7 @@ static void mlx5_ib_prefetch_mr_work(struct work_struct *work)
 
 	num_pending_prefetch_dec(to_mdev(w->pd->device), w->sg_list,
 				 w->num_sge, 0);
-	kfree(w);
+	kvfree(w);
 }
 
 int mlx5_ib_advise_mr_prefetch(struct ib_pd *pd,
@@ -1813,7 +1809,7 @@ int mlx5_ib_advise_mr_prefetch(struct ib_pd *pd,
 	if (valid_req)
 		queue_work(system_unbound_wq, &work->work);
 	else
-		kfree(work);
+		kvfree(work);
 
 	srcu_read_unlock(&dev->mr_srcu, srcu_key);