Merge git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net

Conflicts were all overlapping changes.

Signed-off-by: David S. Miller <davem@davemloft.net>

22 files changed, 268 insertions, 115 deletions

diff --git a/fs/btrfs/backref.c b/fs/btrfs/backref.c
index 9c380e7edf62..0cc02577577b 100644
--- a/fs/btrfs/backref.c
+++ b/fs/btrfs/backref.c
@@ -391,7 +391,7 @@ static int is_shared_data_backref(struct preftrees *preftrees, u64 bytenr)
 	struct rb_node **p = &preftrees->direct.root.rb_root.rb_node;
 	struct rb_node *parent = NULL;
 	struct prelim_ref *ref = NULL;
-	struct prelim_ref target = {0};
+	struct prelim_ref target = {};
 	int result;
 
 	target.parent = bytenr;
diff --git a/fs/btrfs/block-group.c b/fs/btrfs/block-group.c
index 47f66c6a7d7f..696f47103cfc 100644
--- a/fs/btrfs/block-group.c
+++ b/fs/btrfs/block-group.c
@@ -916,7 +916,7 @@ int btrfs_remove_block_group(struct btrfs_trans_handle *trans,
 	path = btrfs_alloc_path();
 	if (!path) {
 		ret = -ENOMEM;
-		goto out;
+		goto out_put_group;
 	}
 
 	/*
@@ -954,7 +954,7 @@ int btrfs_remove_block_group(struct btrfs_trans_handle *trans,
 		ret = btrfs_orphan_add(trans, BTRFS_I(inode));
 		if (ret) {
 			btrfs_add_delayed_iput(inode);
-			goto out;
+			goto out_put_group;
 		}
 		clear_nlink(inode);
 		/* One for the block groups ref */
@@ -977,13 +977,13 @@ int btrfs_remove_block_group(struct btrfs_trans_handle *trans,
 
 	ret = btrfs_search_slot(trans, tree_root, &key, path, -1, 1);
 	if (ret < 0)
-		goto out;
+		goto out_put_group;
 	if (ret > 0)
 		btrfs_release_path(path);
 	if (ret == 0) {
 		ret = btrfs_del_item(trans, tree_root, path);
 		if (ret)
-			goto out;
+			goto out_put_group;
 		btrfs_release_path(path);
 	}
 
@@ -1102,9 +1102,9 @@ int btrfs_remove_block_group(struct btrfs_trans_handle *trans,
 
 	ret = remove_block_group_free_space(trans, block_group);
 	if (ret)
-		goto out;
+		goto out_put_group;
 
-	btrfs_put_block_group(block_group);
+	/* Once for the block groups rbtree */
 	btrfs_put_block_group(block_group);
 
 	ret = btrfs_search_slot(trans, root, &key, path, -1, 1);
@@ -1127,6 +1127,10 @@ int btrfs_remove_block_group(struct btrfs_trans_handle *trans,
 		/* once for the tree */
 		free_extent_map(em);
 	}
+
+out_put_group:
+	/* Once for the lookup reference */
+	btrfs_put_block_group(block_group);
 out:
 	if (remove_rsv)
 		btrfs_delayed_refs_rsv_release(fs_info, 1);
@@ -1288,11 +1292,15 @@ static bool clean_pinned_extents(struct btrfs_trans_handle *trans,
 	if (ret)
 		goto err;
 	mutex_unlock(&fs_info->unused_bg_unpin_mutex);
+	if (prev_trans)
+		btrfs_put_transaction(prev_trans);
 
 	return true;
 
 err:
 	mutex_unlock(&fs_info->unused_bg_unpin_mutex);
+	if (prev_trans)
+		btrfs_put_transaction(prev_trans);
 	btrfs_dec_block_group_ro(bg);
 	return false;
 }
diff --git a/fs/btrfs/discard.h b/fs/btrfs/discard.h
index 21a15776dac4..353228d62f5a 100644
--- a/fs/btrfs/discard.h
+++ b/fs/btrfs/discard.h
@@ -1,4 +1,4 @@
-// SPDX-License-Identifier: GPL-2.0
+/* SPDX-License-Identifier: GPL-2.0 */
 
 #ifndef BTRFS_DISCARD_H
 #define BTRFS_DISCARD_H
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index a6cb5cbbdb9f..d10c7be10f3b 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -2036,9 +2036,6 @@ void btrfs_free_fs_roots(struct btrfs_fs_info *fs_info)
 		for (i = 0; i < ret; i++)
 			btrfs_drop_and_free_fs_root(fs_info, gang[i]);
 	}
-
-	if (test_bit(BTRFS_FS_STATE_ERROR, &fs_info->fs_state))
-		btrfs_free_log_root_tree(NULL, fs_info);
 }
 
 static void btrfs_init_scrub(struct btrfs_fs_info *fs_info)
@@ -3888,7 +3885,7 @@ void btrfs_drop_and_free_fs_root(struct btrfs_fs_info *fs_info,
 	spin_unlock(&fs_info->fs_roots_radix_lock);
 
 	if (test_bit(BTRFS_FS_STATE_ERROR, &fs_info->fs_state)) {
-		btrfs_free_log(NULL, root);
+		ASSERT(root->log_root == NULL);
 		if (root->reloc_root) {
 			btrfs_put_root(root->reloc_root);
 			root->reloc_root = NULL;
@@ -4211,6 +4208,36 @@ static void btrfs_error_commit_super(struct btrfs_fs_info *fs_info)
 	up_write(&fs_info->cleanup_work_sem);
 }
 
+static void btrfs_drop_all_logs(struct btrfs_fs_info *fs_info)
+{
+	struct btrfs_root *gang[8];
+	u64 root_objectid = 0;
+	int ret;
+
+	spin_lock(&fs_info->fs_roots_radix_lock);
+	while ((ret = radix_tree_gang_lookup(&fs_info->fs_roots_radix,
+					     (void **)gang, root_objectid,
+					     ARRAY_SIZE(gang))) != 0) {
+		int i;
+
+		for (i = 0; i < ret; i++)
+			gang[i] = btrfs_grab_root(gang[i]);
+		spin_unlock(&fs_info->fs_roots_radix_lock);
+
+		for (i = 0; i < ret; i++) {
+			if (!gang[i])
+				continue;
+			root_objectid = gang[i]->root_key.objectid;
+			btrfs_free_log(NULL, gang[i]);
+			btrfs_put_root(gang[i]);
+		}
+		root_objectid++;
+		spin_lock(&fs_info->fs_roots_radix_lock);
+	}
+	spin_unlock(&fs_info->fs_roots_radix_lock);
+	btrfs_free_log_root_tree(NULL, fs_info);
+}
+
 static void btrfs_destroy_ordered_extents(struct btrfs_root *root)
 {
 	struct btrfs_ordered_extent *ordered;
@@ -4603,6 +4630,7 @@ static int btrfs_cleanup_transaction(struct btrfs_fs_info *fs_info)
 	btrfs_destroy_delayed_inodes(fs_info);
 	btrfs_assert_delayed_root_empty(fs_info);
 	btrfs_destroy_all_delalloc_inodes(fs_info);
+	btrfs_drop_all_logs(fs_info);
 	mutex_unlock(&fs_info->transaction_kthread_mutex);
 
 	return 0;
diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c
index d35936c934ab..03bc7134e8cb 100644
--- a/fs/btrfs/relocation.c
+++ b/fs/btrfs/relocation.c
@@ -4559,6 +4559,7 @@ int btrfs_recover_relocation(struct btrfs_root *root)
 		if (IS_ERR(fs_root)) {
 			err = PTR_ERR(fs_root);
 			list_add_tail(&reloc_root->root_list, &reloc_roots);
+			btrfs_end_transaction(trans);
 			goto out_unset;
 		}
 
diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c
index 8cede6eb9843..2d5498136e5e 100644
--- a/fs/btrfs/transaction.c
+++ b/fs/btrfs/transaction.c
@@ -662,10 +662,19 @@ again:
 	}
 
 got_it:
-	btrfs_record_root_in_trans(h, root);
-
 	if (!current->journal_info)
 		current->journal_info = h;
+
+	/*
+	 * btrfs_record_root_in_trans() needs to alloc new extents, and may
+	 * call btrfs_join_transaction() while we're also starting a
+	 * transaction.
+	 *
+	 * Thus it need to be called after current->journal_info initialized,
+	 * or we can deadlock.
+	 */
+	btrfs_record_root_in_trans(h, root);
+
 	return h;
 
 join_fail:
diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c
index ec36a7c6ba3d..02ebdd9edc19 100644
--- a/fs/btrfs/tree-log.c
+++ b/fs/btrfs/tree-log.c
@@ -4226,6 +4226,9 @@ static int btrfs_log_prealloc_extents(struct btrfs_trans_handle *trans,
 	const u64 ino = btrfs_ino(inode);
 	struct btrfs_path *dst_path = NULL;
 	bool dropped_extents = false;
+	u64 truncate_offset = i_size;
+	struct extent_buffer *leaf;
+	int slot;
 	int ins_nr = 0;
 	int start_slot;
 	int ret;
@@ -4240,9 +4243,43 @@ static int btrfs_log_prealloc_extents(struct btrfs_trans_handle *trans,
 	if (ret < 0)
 		goto out;
 
+	/*
+	 * We must check if there is a prealloc extent that starts before the
+	 * i_size and crosses the i_size boundary. This is to ensure later we
+	 * truncate down to the end of that extent and not to the i_size, as
+	 * otherwise we end up losing part of the prealloc extent after a log
+	 * replay and with an implicit hole if there is another prealloc extent
+	 * that starts at an offset beyond i_size.
+	 */
+	ret = btrfs_previous_item(root, path, ino, BTRFS_EXTENT_DATA_KEY);
+	if (ret < 0)
+		goto out;
+
+	if (ret == 0) {
+		struct btrfs_file_extent_item *ei;
+
+		leaf = path->nodes[0];
+		slot = path->slots[0];
+		ei = btrfs_item_ptr(leaf, slot, struct btrfs_file_extent_item);
+
+		if (btrfs_file_extent_type(leaf, ei) ==
+		    BTRFS_FILE_EXTENT_PREALLOC) {
+			u64 extent_end;
+
+			btrfs_item_key_to_cpu(leaf, &key, slot);
+			extent_end = key.offset +
+				btrfs_file_extent_num_bytes(leaf, ei);
+
+			if (extent_end > i_size)
+				truncate_offset = extent_end;
+		}
+	} else {
+		ret = 0;
+	}
+
 	while (true) {
-		struct extent_buffer *leaf = path->nodes[0];
-		int slot = path->slots[0];
+		leaf = path->nodes[0];
+		slot = path->slots[0];
 
 		if (slot >= btrfs_header_nritems(leaf)) {
 			if (ins_nr > 0) {
@@ -4280,7 +4317,7 @@ static int btrfs_log_prealloc_extents(struct btrfs_trans_handle *trans,
 				ret = btrfs_truncate_inode_items(trans,
 							 root->log_root,
 							 &inode->vfs_inode,
-							 i_size,
+							 truncate_offset,
 							 BTRFS_EXTENT_DATA_KEY);
 			} while (ret == -EAGAIN);
 			if (ret)
diff --git a/fs/cifs/cifsglob.h b/fs/cifs/cifsglob.h
index 05dd3dea684b..39b708d9d86d 100644
--- a/fs/cifs/cifsglob.h
+++ b/fs/cifs/cifsglob.h
@@ -1891,7 +1891,8 @@ GLOBAL_EXTERN struct list_head		cifs_tcp_ses_list;
 /*
  * This lock protects the cifs_tcp_ses_list, the list of smb sessions per
  * tcp session, and the list of tcon's per smb session. It also protects
- * the reference counters for the server, smb session, and tcon. Finally,
+ * the reference counters for the server, smb session, and tcon. It also
+ * protects some fields in the TCP_Server_Info struct such as dstaddr. Finally,
  * changes to the tcon->tidStatus should be done while holding this lock.
  * generally the locks should be taken in order tcp_ses_lock before
  * tcon->open_file_lock and that before file->file_info_lock since the
diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c
index 95b3ab0ca8c0..28268ed461b8 100644
--- a/fs/cifs/connect.c
+++ b/fs/cifs/connect.c
@@ -375,8 +375,10 @@ static int reconn_set_ipaddr(struct TCP_Server_Info *server)
 		return rc;
 	}
 
+	spin_lock(&cifs_tcp_ses_lock);
 	rc = cifs_convert_address((struct sockaddr *)&server->dstaddr, ipaddr,
 				  strlen(ipaddr));
+	spin_unlock(&cifs_tcp_ses_lock);
 	kfree(ipaddr);
 
 	return !rc ? -1 : 0;
@@ -3373,6 +3375,10 @@ cifs_find_tcon(struct cifs_ses *ses, struct smb_vol *volume_info)
 	spin_lock(&cifs_tcp_ses_lock);
 	list_for_each(tmp, &ses->tcon_list) {
 		tcon = list_entry(tmp, struct cifs_tcon, tcon_list);
+#ifdef CONFIG_CIFS_DFS_UPCALL
+		if (tcon->dfs_path)
+			continue;
+#endif
 		if (!match_tcon(tcon, volume_info))
 			continue;
 		++tcon->tc_count;
diff --git a/fs/cifs/misc.c b/fs/cifs/misc.c
index a456febd4109..550ce9020a3e 100644
--- a/fs/cifs/misc.c
+++ b/fs/cifs/misc.c
@@ -1025,51 +1025,99 @@ int copy_path_name(char *dst, const char *src)
 }
 
 struct super_cb_data {
-	struct TCP_Server_Info *server;
+	void *data;
 	struct super_block *sb;
 };
 
-static void super_cb(struct super_block *sb, void *arg)
+static void tcp_super_cb(struct super_block *sb, void *arg)
 {
-	struct super_cb_data *d = arg;
+	struct super_cb_data *sd = arg;
+	struct TCP_Server_Info *server = sd->data;
 	struct cifs_sb_info *cifs_sb;
 	struct cifs_tcon *tcon;
 
-	if (d->sb)
+	if (sd->sb)
 		return;
 
 	cifs_sb = CIFS_SB(sb);
 	tcon = cifs_sb_master_tcon(cifs_sb);
-	if (tcon->ses->server == d->server)
-		d->sb = sb;
+	if (tcon->ses->server == server)
+		sd->sb = sb;
 }
 
-struct super_block *cifs_get_tcp_super(struct TCP_Server_Info *server)
+static struct super_block *__cifs_get_super(void (*f)(struct super_block *, void *),
+					    void *data)
 {
-	struct super_cb_data d = {
-		.server = server,
+	struct super_cb_data sd = {
+		.data = data,
 		.sb = NULL,
 	};
 
-	iterate_supers_type(&cifs_fs_type, super_cb, &d);
+	iterate_supers_type(&cifs_fs_type, f, &sd);
 
-	if (unlikely(!d.sb))
-		return ERR_PTR(-ENOENT);
+	if (!sd.sb)
+		return ERR_PTR(-EINVAL);
 	/*
 	 * Grab an active reference in order to prevent automounts (DFS links)
 	 * of expiring and then freeing up our cifs superblock pointer while
 	 * we're doing failover.
 	 */
-	cifs_sb_active(d.sb);
-	return d.sb;
+	cifs_sb_active(sd.sb);
+	return sd.sb;
 }
 
-void cifs_put_tcp_super(struct super_block *sb)
+static void __cifs_put_super(struct super_block *sb)
 {
 	if (!IS_ERR_OR_NULL(sb))
 		cifs_sb_deactive(sb);
 }
 
+struct super_block *cifs_get_tcp_super(struct TCP_Server_Info *server)
+{
+	return __cifs_get_super(tcp_super_cb, server);
+}
+
+void cifs_put_tcp_super(struct super_block *sb)
+{
+	__cifs_put_super(sb);
+}
+
+#ifdef CONFIG_CIFS_DFS_UPCALL
+static void tcon_super_cb(struct super_block *sb, void *arg)
+{
+	struct super_cb_data *sd = arg;
+	struct cifs_tcon *tcon = sd->data;
+	struct cifs_sb_info *cifs_sb;
+
+	if (sd->sb)
+		return;
+
+	cifs_sb = CIFS_SB(sb);
+	if (tcon->dfs_path && cifs_sb->origin_fullpath &&
+	    !strcasecmp(tcon->dfs_path, cifs_sb->origin_fullpath))
+		sd->sb = sb;
+}
+
+static inline struct super_block *cifs_get_tcon_super(struct cifs_tcon *tcon)
+{
+	return __cifs_get_super(tcon_super_cb, tcon);
+}
+
+static inline void cifs_put_tcon_super(struct super_block *sb)
+{
+	__cifs_put_super(sb);
+}
+#else
+static inline struct super_block *cifs_get_tcon_super(struct cifs_tcon *tcon)
+{
+	return ERR_PTR(-EOPNOTSUPP);
+}
+
+static inline void cifs_put_tcon_super(struct super_block *sb)
+{
+}
+#endif
+
 int update_super_prepath(struct cifs_tcon *tcon, const char *prefix,
 			 size_t prefix_len)
 {
@@ -1077,7 +1125,7 @@ int update_super_prepath(struct cifs_tcon *tcon, const char *prefix,
 	struct cifs_sb_info *cifs_sb;
 	int rc = 0;
 
-	sb = cifs_get_tcp_super(tcon->ses->server);
+	sb = cifs_get_tcon_super(tcon);
 	if (IS_ERR(sb))
 		return PTR_ERR(sb);
 
@@ -1099,6 +1147,6 @@ int update_super_prepath(struct cifs_tcon *tcon, const char *prefix,
 	cifs_sb->mnt_cifs_flags |= CIFS_MOUNT_USE_PREFIX_PATH;
 
 out:
-	cifs_put_tcp_super(sb);
+	cifs_put_tcon_super(sb);
 	return rc;
 }
diff --git a/fs/cifs/smb2ops.c b/fs/cifs/smb2ops.c
index b36c46f48705..f829f4165d38 100644
--- a/fs/cifs/smb2ops.c
+++ b/fs/cifs/smb2ops.c
@@ -687,6 +687,11 @@ int open_shroot(unsigned int xid, struct cifs_tcon *tcon,
 	if (smb3_encryption_required(tcon))
 		flags |= CIFS_TRANSFORM_REQ;
 
+	if (!server->ops->new_lease_key)
+		return -EIO;
+
+	server->ops->new_lease_key(pfid);
+
 	memset(rqst, 0, sizeof(rqst));
 	resp_buftype[0] = resp_buftype[1] = CIFS_NO_BUFFER;
 	memset(rsp_iov, 0, sizeof(rsp_iov));
diff --git a/fs/debugfs/file.c b/fs/debugfs/file.c
index 2d357680094c..ae49a55bda00 100644
--- a/fs/debugfs/file.c
+++ b/fs/debugfs/file.c
@@ -506,20 +506,11 @@ DEFINE_DEBUGFS_ATTRIBUTE(fops_u32_wo, NULL, debugfs_u32_set, "%llu\n");
  * This function creates a file in debugfs with the given name that
  * contains the value of the variable @value.  If the @mode variable is so
  * set, it can be read from, and written to.
- *
- * This function will return a pointer to a dentry if it succeeds.  This
- * pointer must be passed to the debugfs_remove() function when the file is
- * to be removed (no automatic cleanup happens if your module is unloaded,
- * you are responsible here.)  If an error occurs, ERR_PTR(-ERROR) will be
- * returned.
- *
- * If debugfs is not enabled in the kernel, the value ERR_PTR(-ENODEV) will
- * be returned.
  */
-struct dentry *debugfs_create_u32(const char *name, umode_t mode,
-				 struct dentry *parent, u32 *value)
+void debugfs_create_u32(const char *name, umode_t mode, struct dentry *parent,
+			u32 *value)
 {
-	return debugfs_create_mode_unsafe(name, mode, parent, value, &fops_u32,
+	debugfs_create_mode_unsafe(name, mode, parent, value, &fops_u32,
 				   &fops_u32_ro, &fops_u32_wo);
 }
 EXPORT_SYMBOL_GPL(debugfs_create_u32);
diff --git a/fs/io_uring.c b/fs/io_uring.c
index c687f57fb651..0b91b0631173 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -524,6 +524,7 @@ enum {
 	REQ_F_OVERFLOW_BIT,
 	REQ_F_POLLED_BIT,
 	REQ_F_BUFFER_SELECTED_BIT,
+	REQ_F_NO_FILE_TABLE_BIT,
 
 	/* not a real bit, just to check we're not overflowing the space */
 	__REQ_F_LAST_BIT,
@@ -577,6 +578,8 @@ enum {
 	REQ_F_POLLED		= BIT(REQ_F_POLLED_BIT),
 	/* buffer already selected */
 	REQ_F_BUFFER_SELECTED	= BIT(REQ_F_BUFFER_SELECTED_BIT),
+	/* doesn't need file table for this request */
+	REQ_F_NO_FILE_TABLE	= BIT(REQ_F_NO_FILE_TABLE_BIT),
 };
 
 struct async_poll {
@@ -799,6 +802,7 @@ static const struct io_op_def io_op_defs[] = {
 		.needs_file		= 1,
 		.fd_non_neg		= 1,
 		.needs_fs		= 1,
+		.file_table		= 1,
 	},
 	[IORING_OP_READ] = {
 		.needs_mm		= 1,
@@ -1291,7 +1295,7 @@ static struct io_kiocb *io_get_fallback_req(struct io_ring_ctx *ctx)
 	struct io_kiocb *req;
 
 	req = ctx->fallback_req;
-	if (!test_and_set_bit_lock(0, (unsigned long *) ctx->fallback_req))
+	if (!test_and_set_bit_lock(0, (unsigned long *) &ctx->fallback_req))
 		return req;
 
 	return NULL;
@@ -1378,7 +1382,7 @@ static void __io_free_req(struct io_kiocb *req)
 	if (likely(!io_is_fallback_req(req)))
 		kmem_cache_free(req_cachep, req);
 	else
-		clear_bit_unlock(0, (unsigned long *) req->ctx->fallback_req);
+		clear_bit_unlock(0, (unsigned long *) &req->ctx->fallback_req);
 }
 
 struct req_batch {
@@ -2034,7 +2038,7 @@ static struct file *__io_file_get(struct io_submit_state *state, int fd)
  * any file. For now, just ensure that anything potentially problematic is done
  * inline.
  */
-static bool io_file_supports_async(struct file *file)
+static bool io_file_supports_async(struct file *file, int rw)
 {
 	umode_t mode = file_inode(file)->i_mode;
 
@@ -2043,7 +2047,13 @@ static bool io_file_supports_async(struct file *file)
 	if (S_ISREG(mode) && file->f_op != &io_uring_fops)
 		return true;
 
-	return false;
+	if (!(file->f_mode & FMODE_NOWAIT))
+		return false;
+
+	if (rw == READ)
+		return file->f_op->read_iter != NULL;
+
+	return file->f_op->write_iter != NULL;
 }
 
 static int io_prep_rw(struct io_kiocb *req, const struct io_uring_sqe *sqe,
@@ -2571,7 +2581,7 @@ static int io_read(struct io_kiocb *req, bool force_nonblock)
 	 * If the file doesn't support async, mark it as REQ_F_MUST_PUNT so
 	 * we know to async punt it even if it was opened O_NONBLOCK
 	 */
-	if (force_nonblock && !io_file_supports_async(req->file))
+	if (force_nonblock && !io_file_supports_async(req->file, READ))
 		goto copy_iov;
 
 	iov_count = iov_iter_count(&iter);
@@ -2594,7 +2604,8 @@ copy_iov:
 			if (ret)
 				goto out_free;
 			/* any defer here is final, must blocking retry */
-			if (!(req->flags & REQ_F_NOWAIT))
+			if (!(req->flags & REQ_F_NOWAIT) &&
+			    !file_can_poll(req->file))
 				req->flags |= REQ_F_MUST_PUNT;
 			return -EAGAIN;
 		}
@@ -2662,7 +2673,7 @@ static int io_write(struct io_kiocb *req, bool force_nonblock)
 	 * If the file doesn't support async, mark it as REQ_F_MUST_PUNT so
 	 * we know to async punt it even if it was opened O_NONBLOCK
 	 */
-	if (force_nonblock && !io_file_supports_async(req->file))
+	if (force_nonblock && !io_file_supports_async(req->file, WRITE))
 		goto copy_iov;
 
 	/* file path doesn't support NOWAIT for non-direct_IO */
@@ -2716,7 +2727,8 @@ copy_iov:
 			if (ret)
 				goto out_free;
 			/* any defer here is final, must blocking retry */
-			req->flags |= REQ_F_MUST_PUNT;
+			if (!file_can_poll(req->file))
+				req->flags |= REQ_F_MUST_PUNT;
 			return -EAGAIN;
 		}
 	}
@@ -2756,15 +2768,6 @@ static int io_splice_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
 	return 0;
 }
 
-static bool io_splice_punt(struct file *file)
-{
-	if (get_pipe_info(file))
-		return false;
-	if (!io_file_supports_async(file))
-		return true;
-	return !(file->f_flags & O_NONBLOCK);
-}
-
 static int io_splice(struct io_kiocb *req, bool force_nonblock)
 {
 	struct io_splice *sp = &req->splice;
@@ -2774,11 +2777,8 @@ static int io_splice(struct io_kiocb *req, bool force_nonblock)
 	loff_t *poff_in, *poff_out;
 	long ret;
 
-	if (force_nonblock) {
-		if (io_splice_punt(in) || io_splice_punt(out))
-			return -EAGAIN;
-		flags |= SPLICE_F_NONBLOCK;
-	}
+	if (force_nonblock)
+		return -EAGAIN;
 
 	poff_in = (sp->off_in == -1) ? NULL : &sp->off_in;
 	poff_out = (sp->off_out == -1) ? NULL : &sp->off_out;
@@ -3355,8 +3355,12 @@ static int io_statx(struct io_kiocb *req, bool force_nonblock)
 	struct kstat stat;
 	int ret;
 
-	if (force_nonblock)
+	if (force_nonblock) {
+		/* only need file table for an actual valid fd */
+		if (ctx->dfd == -1 || ctx->dfd == AT_FDCWD)
+			req->flags |= REQ_F_NO_FILE_TABLE;
 		return -EAGAIN;
+	}
 
 	if (vfs_stat_set_lookup_flags(&lookup_flags, ctx->how.flags))
 		return -EINVAL;
@@ -3502,7 +3506,7 @@ static void io_sync_file_range_finish(struct io_wq_work **workptr)
 	if (io_req_cancelled(req))
 		return;
 	__io_sync_file_range(req);
-	io_put_req(req); /* put submission ref */
+	io_steal_work(req, workptr);
 }
 
 static int io_sync_file_range(struct io_kiocb *req, bool force_nonblock)
@@ -5015,7 +5019,7 @@ static int io_req_defer(struct io_kiocb *req, const struct io_uring_sqe *sqe)
 	int ret;
 
 	/* Still need defer if there is pending req in defer list. */
-	if (!req_need_defer(req) && list_empty(&ctx->defer_list))
+	if (!req_need_defer(req) && list_empty_careful(&ctx->defer_list))
 		return 0;
 
 	if (!req->io && io_alloc_async_ctx(req))
@@ -5429,7 +5433,7 @@ static int io_grab_files(struct io_kiocb *req)
 	int ret = -EBADF;
 	struct io_ring_ctx *ctx = req->ctx;
 
-	if (req->work.files)
+	if (req->work.files || (req->flags & REQ_F_NO_FILE_TABLE))
 		return 0;
 	if (!ctx->ring_file)
 		return -EBADF;
@@ -7327,7 +7331,7 @@ static void io_ring_ctx_wait_and_kill(struct io_ring_ctx *ctx)
 	 * it could cause shutdown to hang.
 	 */
 	while (ctx->sqo_thread && !wq_has_sleeper(&ctx->sqo_wait))
-		cpu_relax();
+		cond_resched();
 
 	io_kill_timeouts(ctx);
 	io_poll_remove_all(ctx);
diff --git a/fs/ioctl.c b/fs/ioctl.c
index 282d45be6f45..5e80b40bc1b5 100644
--- a/fs/ioctl.c
+++ b/fs/ioctl.c
@@ -55,6 +55,7 @@ EXPORT_SYMBOL(vfs_ioctl);
 static int ioctl_fibmap(struct file *filp, int __user *p)
 {
 	struct inode *inode = file_inode(filp);
+	struct super_block *sb = inode->i_sb;
 	int error, ur_block;
 	sector_t block;
 
@@ -71,6 +72,13 @@ static int ioctl_fibmap(struct file *filp, int __user *p)
 	block = ur_block;
 	error = bmap(inode, &block);
 
+	if (block > INT_MAX) {
+		error = -ERANGE;
+		pr_warn_ratelimited("[%s/%d] FS: %s File: %pD4 would truncate fibmap result\n",
+				    current->comm, task_pid_nr(current),
+				    sb->s_id, filp);
+	}
+
 	if (error)
 		ur_block = 0;
 	else
diff --git a/fs/iomap/fiemap.c b/fs/iomap/fiemap.c
index bccf305ea9ce..d55e8f491a5e 100644
--- a/fs/iomap/fiemap.c
+++ b/fs/iomap/fiemap.c
@@ -117,10 +117,7 @@ iomap_bmap_actor(struct inode *inode, loff_t pos, loff_t length,
 
 	if (iomap->type == IOMAP_MAPPED) {
 		addr = (pos - iomap->offset + iomap->addr) >> inode->i_blkbits;
-		if (addr > INT_MAX)
-			WARN(1, "would truncate bmap result\n");
-		else
-			*bno = addr;
+		*bno = addr;
 	}
 	return 0;
 }
diff --git a/fs/nfs/nfs3acl.c b/fs/nfs/nfs3acl.c
index c5c3fc6e6c60..26c94b32d6f4 100644
--- a/fs/nfs/nfs3acl.c
+++ b/fs/nfs/nfs3acl.c
@@ -253,37 +253,45 @@ int nfs3_proc_setacls(struct inode *inode, struct posix_acl *acl,
 
 int nfs3_set_acl(struct inode *inode, struct posix_acl *acl, int type)
 {
-	struct posix_acl *alloc = NULL, *dfacl = NULL;
+	struct posix_acl *orig = acl, *dfacl = NULL, *alloc;
 	int status;
 
 	if (S_ISDIR(inode->i_mode)) {
 		switch(type) {
 		case ACL_TYPE_ACCESS:
-			alloc = dfacl = get_acl(inode, ACL_TYPE_DEFAULT);
+			alloc = get_acl(inode, ACL_TYPE_DEFAULT);
 			if (IS_ERR(alloc))
 				goto fail;
+			dfacl = alloc;
 			break;
 
 		case ACL_TYPE_DEFAULT:
-			dfacl = acl;
-			alloc = acl = get_acl(inode, ACL_TYPE_ACCESS);
+			alloc = get_acl(inode, ACL_TYPE_ACCESS);
 			if (IS_ERR(alloc))
 				goto fail;
+			dfacl = acl;
+			acl = alloc;
 			break;
 		}
 	}
 
 	if (acl == NULL) {
-		alloc = acl = posix_acl_from_mode(inode->i_mode, GFP_KERNEL);
+		alloc = posix_acl_from_mode(inode->i_mode, GFP_KERNEL);
 		if (IS_ERR(alloc))
 			goto fail;
+		acl = alloc;
 	}
 	status = __nfs3_proc_setacls(inode, acl, dfacl);
-	posix_acl_release(alloc);
+out:
+	if (acl != orig)
+		posix_acl_release(acl);
+	if (dfacl != orig)
+		posix_acl_release(dfacl);
 	return status;
 
 fail:
-	return PTR_ERR(alloc);
+	status = PTR_ERR(alloc);
+	goto out;
 }
 
 const struct xattr_handler *nfs3_xattr_handlers[] = {
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index 512afb1c7867..a0c1e653a935 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -7891,6 +7891,7 @@ static void
 nfs4_bind_one_conn_to_session_done(struct rpc_task *task, void *calldata)
 {
 	struct nfs41_bind_conn_to_session_args *args = task->tk_msg.rpc_argp;
+	struct nfs41_bind_conn_to_session_res *res = task->tk_msg.rpc_resp;
 	struct nfs_client *clp = args->client;
 
 	switch (task->tk_status) {
@@ -7899,6 +7900,12 @@ nfs4_bind_one_conn_to_session_done(struct rpc_task *task, void *calldata)
 		nfs4_schedule_session_recovery(clp->cl_session,
 				task->tk_status);
 	}
+	if (args->dir == NFS4_CDFC4_FORE_OR_BOTH &&
+			res->dir != NFS4_CDFS4_BOTH) {
+		rpc_task_close_connection(task);
+		if (args->retries++ < MAX_BIND_CONN_TO_SESSION_RETRIES)
+			rpc_restart_call(task);
+	}
 }
 
 static const struct rpc_call_ops nfs4_bind_one_conn_to_session_ops = {
@@ -7921,6 +7928,7 @@ int nfs4_proc_bind_one_conn_to_session(struct rpc_clnt *clnt,
 	struct nfs41_bind_conn_to_session_args args = {
 		.client = clp,
 		.dir = NFS4_CDFC4_FORE_OR_BOTH,
+		.retries = 0,
 	};
 	struct nfs41_bind_conn_to_session_res res;
 	struct rpc_message msg = {
@@ -9191,8 +9199,7 @@ nfs4_proc_layoutget(struct nfs4_layoutget *lgp, long *timeout)
 	nfs4_init_sequence(&lgp->args.seq_args, &lgp->res.seq_res, 0, 0);
 
 	task = rpc_run_task(&task_setup_data);
-	if (IS_ERR(task))
-		return ERR_CAST(task);
+
 	status = rpc_wait_for_completion_task(task);
 	if (status != 0)
 		goto out;
diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c
index b8d78f393365..dd2e14f5875d 100644
--- a/fs/nfs/pnfs.c
+++ b/fs/nfs/pnfs.c
@@ -1332,13 +1332,15 @@ _pnfs_return_layout(struct inode *ino)
 			!valid_layout) {
 		spin_unlock(&ino->i_lock);
 		dprintk("NFS: %s no layout segments to return\n", __func__);
-		goto out_put_layout_hdr;
+		goto out_wait_layoutreturn;
 	}
 
 	send = pnfs_prepare_layoutreturn(lo, &stateid, &cred, NULL);
 	spin_unlock(&ino->i_lock);
 	if (send)
 		status = pnfs_send_layoutreturn(lo, &stateid, &cred, IOMODE_ANY, true);
+out_wait_layoutreturn:
+	wait_on_bit(&lo->plh_flags, NFS_LAYOUT_RETURN, TASK_UNINTERRUPTIBLE);
 out_put_layout_hdr:
 	pnfs_free_lseg_list(&tmp_list);
 	pnfs_put_layout_hdr(lo);
@@ -1456,18 +1458,15 @@ retry:
 	/* lo ref dropped in pnfs_roc_release() */
 	layoutreturn = pnfs_prepare_layoutreturn(lo, &stateid, &lc_cred, &iomode);
 	/* If the creds don't match, we can't compound the layoutreturn */
-	if (!layoutreturn)
+	if (!layoutreturn || cred_fscmp(cred, lc_cred) != 0)
 		goto out_noroc;
-	if (cred_fscmp(cred, lc_cred) != 0)
-		goto out_noroc_put_cred;
 
 	roc = layoutreturn;
 	pnfs_init_layoutreturn_args(args, lo, &stateid, iomode);
 	res->lrs_present = 0;
 	layoutreturn = false;
-
-out_noroc_put_cred:
 	put_cred(lc_cred);
+
 out_noroc:
 	spin_unlock(&ino->i_lock);
 	rcu_read_unlock();
diff --git a/fs/nfs/super.c b/fs/nfs/super.c
index 59ef3b13ccca..bdb6d0c2e755 100644
--- a/fs/nfs/super.c
+++ b/fs/nfs/super.c
@@ -185,7 +185,7 @@ static int __nfs_list_for_each_server(struct list_head *head,
 
 	rcu_read_lock();
 	list_for_each_entry_rcu(server, head, client_link) {
-		if (!nfs_sb_active(server->super))
+		if (!(server->super && nfs_sb_active(server->super)))
 			continue;
 		rcu_read_unlock();
 		if (last)
diff --git a/fs/ocfs2/dlmfs/dlmfs.c b/fs/ocfs2/dlmfs/dlmfs.c
index 8e4f1ace467c..1de77f1a600b 100644
--- a/fs/ocfs2/dlmfs/dlmfs.c
+++ b/fs/ocfs2/dlmfs/dlmfs.c
@@ -275,7 +275,6 @@ static ssize_t dlmfs_file_write(struct file *filp,
 				loff_t *ppos)
 {
 	int bytes_left;
-	ssize_t writelen;
 	char *lvb_buf;
 	struct inode *inode = file_inode(filp);
 
@@ -285,32 +284,30 @@ static ssize_t dlmfs_file_write(struct file *filp,
 	if (*ppos >= i_size_read(inode))
 		return -ENOSPC;
 
+	/* don't write past the lvb */
+	if (count > i_size_read(inode) - *ppos)
+		count = i_size_read(inode) - *ppos;
+
 	if (!count)
 		return 0;
 
 	if (!access_ok(buf, count))
 		return -EFAULT;
 
-	/* don't write past the lvb */
-	if ((count + *ppos) > i_size_read(inode))
-		writelen = i_size_read(inode) - *ppos;
-	else
-		writelen = count - *ppos;
-
-	lvb_buf = kmalloc(writelen, GFP_NOFS);
+	lvb_buf = kmalloc(count, GFP_NOFS);
 	if (!lvb_buf)
 		return -ENOMEM;
 
-	bytes_left = copy_from_user(lvb_buf, buf, writelen);
-	writelen -= bytes_left;
-	if (writelen)
-		user_dlm_write_lvb(inode, lvb_buf, writelen);
+	bytes_left = copy_from_user(lvb_buf, buf, count);
+	count -= bytes_left;
+	if (count)
+		user_dlm_write_lvb(inode, lvb_buf, count);
 
 	kfree(lvb_buf);
 
-	*ppos = *ppos + writelen;
-	mlog(0, "wrote %zd bytes\n", writelen);
-	return writelen;
+	*ppos = *ppos + count;
+	mlog(0, "wrote %zu bytes\n", count);
+	return count;
 }
 
 static void dlmfs_init_once(void *foo)
diff --git a/fs/pnode.c b/fs/pnode.c
index 49f6d7ff2139..1106137c747a 100644
--- a/fs/pnode.c
+++ b/fs/pnode.c
@@ -261,14 +261,13 @@ static int propagate_one(struct mount *m)
 	child = copy_tree(last_source, last_source->mnt.mnt_root, type);
 	if (IS_ERR(child))
 		return PTR_ERR(child);
+	read_seqlock_excl(&mount_lock);
 	mnt_set_mountpoint(m, mp, child);
+	if (m->mnt_master != dest_master)
+		SET_MNT_MARK(m->mnt_master);
+	read_sequnlock_excl(&mount_lock);
 	last_dest = m;
 	last_source = child;
-	if (m->mnt_master != dest_master) {
-		read_seqlock_excl(&mount_lock);
-		SET_MNT_MARK(m->mnt_master);
-		read_sequnlock_excl(&mount_lock);
-	}
 	hlist_add_head(&child->mnt_hash, list);
 	return count_mounts(m->mnt_ns, child);
 }
diff --git a/fs/super.c b/fs/super.c
index cd352530eca9..a288cd60d2ae 100644
--- a/fs/super.c
+++ b/fs/super.c
@@ -1302,8 +1302,8 @@ int get_tree_bdev(struct fs_context *fc,
 	mutex_lock(&bdev->bd_fsfreeze_mutex);
 	if (bdev->bd_fsfreeze_count > 0) {
 		mutex_unlock(&bdev->bd_fsfreeze_mutex);
-		blkdev_put(bdev, mode);
 		warnf(fc, "%pg: Can't mount, blockdev is frozen", bdev);
+		blkdev_put(bdev, mode);
 		return -EBUSY;
 	}