4 files changed, 91 insertions, 96 deletions

diff --git a/drivers/infiniband/hw/mlx5/devx.c b/drivers/infiniband/hw/mlx5/devx.c
index 59022b744144..d609f4659afb 100644
--- a/drivers/infiniband/hw/mlx5/devx.c
+++ b/drivers/infiniband/hw/mlx5/devx.c
@@ -1298,29 +1298,6 @@ static int devx_handle_mkey_create(struct mlx5_ib_dev *dev,
 	return 0;
 }
 
-static void devx_free_indirect_mkey(struct rcu_head *rcu)
-{
-	kfree(container_of(rcu, struct devx_obj, devx_mr.rcu));
-}
-
-/* This function to delete from the radix tree needs to be called before
- * destroying the underlying mkey. Otherwise a race might occur in case that
- * other thread will get the same mkey before this one will be deleted,
- * in that case it will fail via inserting to the tree its own data.
- *
- * Note:
- * An error in the destroy is not expected unless there is some other indirect
- * mkey which points to this one. In a kernel cleanup flow it will be just
- * destroyed in the iterative destruction call. In a user flow, in case
- * the application didn't close in the expected order it's its own problem,
- * the mkey won't be part of the tree, in both cases the kernel is safe.
- */
-static void devx_cleanup_mkey(struct devx_obj *obj)
-{
-	xa_erase(&obj->ib_dev->mdev->priv.mkey_table,
-		 mlx5_base_mkey(obj->devx_mr.mmkey.key));
-}
-
 static void devx_cleanup_subscription(struct mlx5_ib_dev *dev,
 				      struct devx_event_subscription *sub)
 {
@@ -1362,8 +1339,16 @@ static int devx_obj_cleanup(struct ib_uobject *uobject,
 	int ret;
 
 	dev = mlx5_udata_to_mdev(&attrs->driver_udata);
-	if (obj->flags & DEVX_OBJ_FLAGS_INDIRECT_MKEY)
-		devx_cleanup_mkey(obj);
+	if (obj->flags & DEVX_OBJ_FLAGS_INDIRECT_MKEY) {
+		/*
+		 * The pagefault_single_data_segment() does commands against
+		 * the mmkey, we must wait for that to stop before freeing the
+		 * mkey, as another allocation could get the same mkey #.
+		 */
+		xa_erase(&obj->ib_dev->mdev->priv.mkey_table,
+			 mlx5_base_mkey(obj->devx_mr.mmkey.key));
+		synchronize_srcu(&dev->mr_srcu);
+	}
 
 	if (obj->flags & DEVX_OBJ_FLAGS_DCT)
 		ret = mlx5_core_destroy_dct(obj->ib_dev->mdev, &obj->core_dct);
@@ -1382,12 +1367,6 @@ static int devx_obj_cleanup(struct ib_uobject *uobject,
 		devx_cleanup_subscription(dev, sub_entry);
 	mutex_unlock(&devx_event_table->event_xa_lock);
 
-	if (obj->flags & DEVX_OBJ_FLAGS_INDIRECT_MKEY) {
-		call_srcu(&dev->mr_srcu, &obj->devx_mr.rcu,
-			  devx_free_indirect_mkey);
-		return ret;
-	}
-
 	kfree(obj);
 	return ret;
 }
@@ -1491,26 +1470,21 @@ static int UVERBS_HANDLER(MLX5_IB_METHOD_DEVX_OBJ_CREATE)(
 				   &obj_id);
 	WARN_ON(obj->dinlen > MLX5_MAX_DESTROY_INBOX_SIZE_DW * sizeof(u32));
 
-	if (obj->flags & DEVX_OBJ_FLAGS_INDIRECT_MKEY) {
-		err = devx_handle_mkey_indirect(obj, dev, cmd_in, cmd_out);
-		if (err)
-			goto obj_destroy;
-	}
-
 	err = uverbs_copy_to(attrs, MLX5_IB_ATTR_DEVX_OBJ_CREATE_CMD_OUT, cmd_out, cmd_out_len);
 	if (err)
-		goto err_copy;
+		goto obj_destroy;
 
 	if (opcode == MLX5_CMD_OP_CREATE_GENERAL_OBJECT)
 		obj_type = MLX5_GET(general_obj_in_cmd_hdr, cmd_in, obj_type);
-
 	obj->obj_id = get_enc_obj_id(opcode | obj_type << 16, obj_id);
 
+	if (obj->flags & DEVX_OBJ_FLAGS_INDIRECT_MKEY) {
+		err = devx_handle_mkey_indirect(obj, dev, cmd_in, cmd_out);
+		if (err)
+			goto obj_destroy;
+	}
 	return 0;
 
-err_copy:
-	if (obj->flags & DEVX_OBJ_FLAGS_INDIRECT_MKEY)
-		devx_cleanup_mkey(obj);
 obj_destroy:
 	if (obj->flags & DEVX_OBJ_FLAGS_DCT)
 		mlx5_core_destroy_dct(obj->ib_dev->mdev, &obj->core_dct);
diff --git a/drivers/infiniband/hw/mlx5/mlx5_ib.h b/drivers/infiniband/hw/mlx5/mlx5_ib.h
index 2ceaef3ea3fb..1a98ee2e01c4 100644
--- a/drivers/infiniband/hw/mlx5/mlx5_ib.h
+++ b/drivers/infiniband/hw/mlx5/mlx5_ib.h
@@ -606,7 +606,7 @@ struct mlx5_ib_mr {
 	struct mlx5_ib_dev     *dev;
 	u32 out[MLX5_ST_SZ_DW(create_mkey_out)];
 	struct mlx5_core_sig_ctx    *sig;
-	int			live;
+	unsigned int		live;
 	void			*descs_alloc;
 	int			access_flags; /* Needed for rereg MR */
 
@@ -639,7 +639,6 @@ struct mlx5_ib_mw {
 struct mlx5_ib_devx_mr {
 	struct mlx5_core_mkey	mmkey;
 	int			ndescs;
-	struct rcu_head		rcu;
 };
 
 struct mlx5_ib_umr_context {
diff --git a/drivers/infiniband/hw/mlx5/mr.c b/drivers/infiniband/hw/mlx5/mr.c
index 1eff031ef048..630599311586 100644
--- a/drivers/infiniband/hw/mlx5/mr.c
+++ b/drivers/infiniband/hw/mlx5/mr.c
@@ -84,32 +84,6 @@ static bool use_umr_mtt_update(struct mlx5_ib_mr *mr, u64 start, u64 length)
 		length + (start & (MLX5_ADAPTER_PAGE_SIZE - 1));
 }
 
-static void update_odp_mr(struct mlx5_ib_mr *mr)
-{
-	if (is_odp_mr(mr)) {
-		/*
-		 * This barrier prevents the compiler from moving the
-		 * setting of umem->odp_data->private to point to our
-		 * MR, before reg_umr finished, to ensure that the MR
-		 * initialization have finished before starting to
-		 * handle invalidations.
-		 */
-		smp_wmb();
-		to_ib_umem_odp(mr->umem)->private = mr;
-		/*
-		 * Make sure we will see the new
-		 * umem->odp_data->private value in the invalidation
-		 * routines, before we can get page faults on the
-		 * MR. Page faults can happen once we put the MR in
-		 * the tree, below this line. Without the barrier,
-		 * there can be a fault handling and an invalidation
-		 * before umem->odp_data->private == mr is visible to
-		 * the invalidation handler.
-		 */
-		smp_wmb();
-	}
-}
-
 static void reg_mr_callback(int status, struct mlx5_async_work *context)
 {
 	struct mlx5_ib_mr *mr =
@@ -1346,8 +1320,6 @@ struct ib_mr *mlx5_ib_reg_user_mr(struct ib_pd *pd, u64 start, u64 length,
 	mr->umem = umem;
 	set_mr_fields(dev, mr, npages, length, access_flags);
 
-	update_odp_mr(mr);
-
 	if (use_umr) {
 		int update_xlt_flags = MLX5_IB_UPD_XLT_ENABLE;
 
@@ -1363,10 +1335,12 @@ struct ib_mr *mlx5_ib_reg_user_mr(struct ib_pd *pd, u64 start, u64 length,
 		}
 	}
 
-	if (IS_ENABLED(CONFIG_INFINIBAND_ON_DEMAND_PAGING)) {
-		mr->live = 1;
+	if (is_odp_mr(mr)) {
+		to_ib_umem_odp(mr->umem)->private = mr;
 		atomic_set(&mr->num_pending_prefetch, 0);
 	}
+	if (IS_ENABLED(CONFIG_INFINIBAND_ON_DEMAND_PAGING))
+		smp_store_release(&mr->live, 1);
 
 	return &mr->ibmr;
 error:
@@ -1441,6 +1415,9 @@ int mlx5_ib_rereg_user_mr(struct ib_mr *ib_mr, int flags, u64 start,
 	if (!mr->umem)
 		return -EINVAL;
 
+	if (is_odp_mr(mr))
+		return -EOPNOTSUPP;
+
 	if (flags & IB_MR_REREG_TRANS) {
 		addr = virt_addr;
 		len = length;
@@ -1486,8 +1463,6 @@ int mlx5_ib_rereg_user_mr(struct ib_mr *ib_mr, int flags, u64 start,
 		}
 
 		mr->allocated_from_cache = 0;
-		if (IS_ENABLED(CONFIG_INFINIBAND_ON_DEMAND_PAGING))
-			mr->live = 1;
 	} else {
 		/*
 		 * Send a UMR WQE
@@ -1516,7 +1491,6 @@ int mlx5_ib_rereg_user_mr(struct ib_mr *ib_mr, int flags, u64 start,
 
 	set_mr_fields(dev, mr, npages, len, access_flags);
 
-	update_odp_mr(mr);
 	return 0;
 
 err:
@@ -1607,15 +1581,16 @@ static void dereg_mr(struct mlx5_ib_dev *dev, struct mlx5_ib_mr *mr)
 		/* Prevent new page faults and
 		 * prefetch requests from succeeding
 		 */
-		mr->live = 0;
+		WRITE_ONCE(mr->live, 0);
+
+		/* Wait for all running page-fault handlers to finish. */
+		synchronize_srcu(&dev->mr_srcu);
 
 		/* dequeue pending prefetch requests for the mr */
 		if (atomic_read(&mr->num_pending_prefetch))
 			flush_workqueue(system_unbound_wq);
 		WARN_ON(atomic_read(&mr->num_pending_prefetch));
 
-		/* Wait for all running page-fault handlers to finish. */
-		synchronize_srcu(&dev->mr_srcu);
 		/* Destroy all page mappings */
 		if (!umem_odp->is_implicit_odp)
 			mlx5_ib_invalidate_range(umem_odp,
@@ -1987,14 +1962,25 @@ free:
 
 int mlx5_ib_dealloc_mw(struct ib_mw *mw)
 {
+	struct mlx5_ib_dev *dev = to_mdev(mw->device);
 	struct mlx5_ib_mw *mmw = to_mmw(mw);
 	int err;
 
-	err =  mlx5_core_destroy_mkey((to_mdev(mw->device))->mdev,
-				      &mmw->mmkey);
-	if (!err)
-		kfree(mmw);
-	return err;
+	if (IS_ENABLED(CONFIG_INFINIBAND_ON_DEMAND_PAGING)) {
+		xa_erase(&dev->mdev->priv.mkey_table,
+			 mlx5_base_mkey(mmw->mmkey.key));
+		/*
+		 * pagefault_single_data_segment() may be accessing mmw under
+		 * SRCU if the user bound an ODP MR to this MW.
+		 */
+		synchronize_srcu(&dev->mr_srcu);
+	}
+
+	err = mlx5_core_destroy_mkey(dev->mdev, &mmw->mmkey);
+	if (err)
+		return err;
+	kfree(mmw);
+	return 0;
 }
 
 int mlx5_ib_check_mr_status(struct ib_mr *ibmr, u32 check_mask,
diff --git a/drivers/infiniband/hw/mlx5/odp.c b/drivers/infiniband/hw/mlx5/odp.c
index 2e9b43061797..3f9478d19376 100644
--- a/drivers/infiniband/hw/mlx5/odp.c
+++ b/drivers/infiniband/hw/mlx5/odp.c
@@ -178,6 +178,29 @@ void mlx5_odp_populate_klm(struct mlx5_klm *pklm, size_t offset,
 		return;
 	}
 
+	/*
+	 * The locking here is pretty subtle. Ideally the implicit children
+	 * list would be protected by the umem_mutex, however that is not
+	 * possible. Instead this uses a weaker update-then-lock pattern:
+	 *
+	 *  srcu_read_lock()
+	 *    <change children list>
+	 *    mutex_lock(umem_mutex)
+	 *     mlx5_ib_update_xlt()
+	 *    mutex_unlock(umem_mutex)
+	 *    destroy lkey
+	 *
+	 * ie any change the children list must be followed by the locked
+	 * update_xlt before destroying.
+	 *
+	 * The umem_mutex provides the acquire/release semantic needed to make
+	 * the children list visible to a racing thread. While SRCU is not
+	 * technically required, using it gives consistent use of the SRCU
+	 * locking around the children list.
+	 */
+	lockdep_assert_held(&to_ib_umem_odp(mr->umem)->umem_mutex);
+	lockdep_assert_held(&mr->dev->mr_srcu);
+
 	odp = odp_lookup(offset * MLX5_IMR_MTT_SIZE,
 			 nentries * MLX5_IMR_MTT_SIZE, mr);
 
@@ -202,15 +225,22 @@ static void mr_leaf_free_action(struct work_struct *work)
 	struct ib_umem_odp *odp = container_of(work, struct ib_umem_odp, work);
 	int idx = ib_umem_start(odp) >> MLX5_IMR_MTT_SHIFT;
 	struct mlx5_ib_mr *mr = odp->private, *imr = mr->parent;
+	struct ib_umem_odp *odp_imr = to_ib_umem_odp(imr->umem);
+	int srcu_key;
 
 	mr->parent = NULL;
 	synchronize_srcu(&mr->dev->mr_srcu);
 
-	ib_umem_odp_release(odp);
-	if (imr->live)
+	if (smp_load_acquire(&imr->live)) {
+		srcu_key = srcu_read_lock(&mr->dev->mr_srcu);
+		mutex_lock(&odp_imr->umem_mutex);
 		mlx5_ib_update_xlt(imr, idx, 1, 0,
 				   MLX5_IB_UPD_XLT_INDIRECT |
 				   MLX5_IB_UPD_XLT_ATOMIC);
+		mutex_unlock(&odp_imr->umem_mutex);
+		srcu_read_unlock(&mr->dev->mr_srcu, srcu_key);
+	}
+	ib_umem_odp_release(odp);
 	mlx5_mr_cache_free(mr->dev, mr);
 
 	if (atomic_dec_and_test(&imr->num_leaf_free))
@@ -278,7 +308,6 @@ 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
@@ -289,10 +318,12 @@ void mlx5_ib_invalidate_range(struct ib_umem_odp *umem_odp, unsigned long start,
 
 	if (unlikely(!umem_odp->npages && mr->parent &&
 		     !umem_odp->dying)) {
-		WRITE_ONCE(umem_odp->dying, 1);
+		WRITE_ONCE(mr->live, 0);
+		umem_odp->dying = 1;
 		atomic_inc(&mr->parent->num_leaf_free);
 		schedule_work(&umem_odp->work);
 	}
+	mutex_unlock(&umem_odp->umem_mutex);
 }
 
 void mlx5_ib_internal_fill_odp_caps(struct mlx5_ib_dev *dev)
@@ -429,8 +460,6 @@ static struct mlx5_ib_mr *implicit_mr_alloc(struct ib_pd *pd,
 	mr->ibmr.lkey = mr->mmkey.key;
 	mr->ibmr.rkey = mr->mmkey.key;
 
-	mr->live = 1;
-
 	mlx5_ib_dbg(dev, "key %x dev %p mr %p\n",
 		    mr->mmkey.key, dev->mdev, mr);
 
@@ -484,6 +513,8 @@ next_mr:
 		mtt->parent = mr;
 		INIT_WORK(&odp->work, mr_leaf_free_action);
 
+		smp_store_release(&mtt->live, 1);
+
 		if (!nentries)
 			start_idx = addr >> MLX5_IMR_MTT_SHIFT;
 		nentries++;
@@ -536,6 +567,7 @@ struct mlx5_ib_mr *mlx5_ib_alloc_implicit_mr(struct mlx5_ib_pd *pd,
 	init_waitqueue_head(&imr->q_leaf_free);
 	atomic_set(&imr->num_leaf_free, 0);
 	atomic_set(&imr->num_pending_prefetch, 0);
+	smp_store_release(&imr->live, 1);
 
 	return imr;
 }
@@ -555,15 +587,19 @@ void mlx5_ib_free_implicit_mr(struct mlx5_ib_mr *imr)
 		if (mr->parent != imr)
 			continue;
 
+		mutex_lock(&umem_odp->umem_mutex);
 		ib_umem_odp_unmap_dma_pages(umem_odp, ib_umem_start(umem_odp),
 					    ib_umem_end(umem_odp));
 
-		if (umem_odp->dying)
+		if (umem_odp->dying) {
+			mutex_unlock(&umem_odp->umem_mutex);
 			continue;
+		}
 
-		WRITE_ONCE(umem_odp->dying, 1);
+		umem_odp->dying = 1;
 		atomic_inc(&imr->num_leaf_free);
 		schedule_work(&umem_odp->work);
+		mutex_unlock(&umem_odp->umem_mutex);
 	}
 	up_read(&per_mm->umem_rwsem);
 
@@ -773,7 +809,7 @@ next_mr:
 	switch (mmkey->type) {
 	case MLX5_MKEY_MR:
 		mr = container_of(mmkey, struct mlx5_ib_mr, mmkey);
-		if (!mr->live || !mr->ibmr.pd) {
+		if (!smp_load_acquire(&mr->live) || !mr->ibmr.pd) {
 			mlx5_ib_dbg(dev, "got dead MR\n");
 			ret = -EFAULT;
 			goto srcu_unlock;
@@ -1641,12 +1677,12 @@ static bool num_pending_prefetch_inc(struct ib_pd *pd,
 
 		mr = container_of(mmkey, struct mlx5_ib_mr, mmkey);
 
-		if (mr->ibmr.pd != pd) {
+		if (!smp_load_acquire(&mr->live)) {
 			ret = false;
 			break;
 		}
 
-		if (!mr->live) {
+		if (mr->ibmr.pd != pd) {
 			ret = false;
 			break;
 		}