Merge 5.8-rc6 into staging-next

We need the staging fixes in here, and it resolves a merge issue with an
iio driver.

Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

62 files changed, 607 insertions, 347 deletions

diff --git a/fs/afs/fs_operation.c b/fs/afs/fs_operation.c
index c264839b2fd0..24fd163c6323 100644
--- a/fs/afs/fs_operation.c
+++ b/fs/afs/fs_operation.c
@@ -71,7 +71,7 @@ static bool afs_get_io_locks(struct afs_operation *op)
 		swap(vnode, vnode2);
 
 	if (mutex_lock_interruptible(&vnode->io_lock) < 0) {
-		op->error = -EINTR;
+		op->error = -ERESTARTSYS;
 		op->flags |= AFS_OPERATION_STOP;
 		_leave(" = f [I 0]");
 		return false;
@@ -80,7 +80,7 @@ static bool afs_get_io_locks(struct afs_operation *op)
 
 	if (vnode2) {
 		if (mutex_lock_interruptible_nested(&vnode2->io_lock, 1) < 0) {
-			op->error = -EINTR;
+			op->error = -ERESTARTSYS;
 			op->flags |= AFS_OPERATION_STOP;
 			mutex_unlock(&vnode->io_lock);
 			op->flags &= ~AFS_OPERATION_LOCK_0;
diff --git a/fs/afs/write.c b/fs/afs/write.c
index 7437806332d9..a121c247d95a 100644
--- a/fs/afs/write.c
+++ b/fs/afs/write.c
@@ -449,6 +449,7 @@ static int afs_store_data(struct address_space *mapping,
 	op->store.first_offset = offset;
 	op->store.last_to = to;
 	op->mtime = vnode->vfs_inode.i_mtime;
+	op->flags |= AFS_OPERATION_UNINTR;
 	op->ops = &afs_store_data_operation;
 
 try_next_key:
diff --git a/fs/autofs/waitq.c b/fs/autofs/waitq.c
index b04c528b19d3..74c886f7c51c 100644
--- a/fs/autofs/waitq.c
+++ b/fs/autofs/waitq.c
@@ -53,7 +53,7 @@ static int autofs_write(struct autofs_sb_info *sbi,
 
 	mutex_lock(&sbi->pipe_mutex);
 	while (bytes) {
-		wr = __kernel_write(file, data, bytes, &file->f_pos);
+		wr = kernel_write(file, data, bytes, &file->f_pos);
 		if (wr <= 0)
 			break;
 		data += wr;
diff --git a/fs/btrfs/ctree.c b/fs/btrfs/ctree.c
index 3a7648bff42c..82ab6e5a386d 100644
--- a/fs/btrfs/ctree.c
+++ b/fs/btrfs/ctree.c
@@ -1196,7 +1196,7 @@ __tree_mod_log_rewind(struct btrfs_fs_info *fs_info, struct extent_buffer *eb,
 		switch (tm->op) {
 		case MOD_LOG_KEY_REMOVE_WHILE_FREEING:
 			BUG_ON(tm->slot < n);
-			/* Fallthrough */
+			fallthrough;
 		case MOD_LOG_KEY_REMOVE_WHILE_MOVING:
 		case MOD_LOG_KEY_REMOVE:
 			btrfs_set_node_key(eb, &tm->key, tm->slot);
diff --git a/fs/btrfs/discard.c b/fs/btrfs/discard.c
index 5615320fa659..741c7e19c32f 100644
--- a/fs/btrfs/discard.c
+++ b/fs/btrfs/discard.c
@@ -619,6 +619,7 @@ void btrfs_discard_punt_unused_bgs_list(struct btrfs_fs_info *fs_info)
 	list_for_each_entry_safe(block_group, next, &fs_info->unused_bgs,
 				 bg_list) {
 		list_del_init(&block_group->bg_list);
+		btrfs_put_block_group(block_group);
 		btrfs_discard_queue_work(&fs_info->discard_ctl, block_group);
 	}
 	spin_unlock(&fs_info->unused_bgs_lock);
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 7c6f0bbb54a5..b1a148058773 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -2593,10 +2593,12 @@ static int __cold init_tree_roots(struct btrfs_fs_info *fs_info)
 		    !extent_buffer_uptodate(tree_root->node)) {
 			handle_error = true;
 
-			if (IS_ERR(tree_root->node))
+			if (IS_ERR(tree_root->node)) {
 				ret = PTR_ERR(tree_root->node);
-			else if (!extent_buffer_uptodate(tree_root->node))
+				tree_root->node = NULL;
+			} else if (!extent_buffer_uptodate(tree_root->node)) {
 				ret = -EUCLEAN;
+			}
 
 			btrfs_warn(fs_info, "failed to read tree root");
 			continue;
diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index 68c96057ad2d..608f93438b29 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -5058,25 +5058,28 @@ struct extent_buffer *alloc_dummy_extent_buffer(struct btrfs_fs_info *fs_info,
 static void check_buffer_tree_ref(struct extent_buffer *eb)
 {
 	int refs;
-	/* the ref bit is tricky.  We have to make sure it is set
-	 * if we have the buffer dirty.   Otherwise the
-	 * code to free a buffer can end up dropping a dirty
-	 * page
+	/*
+	 * The TREE_REF bit is first set when the extent_buffer is added
+	 * to the radix tree. It is also reset, if unset, when a new reference
+	 * is created by find_extent_buffer.
 	 *
-	 * Once the ref bit is set, it won't go away while the
-	 * buffer is dirty or in writeback, and it also won't
-	 * go away while we have the reference count on the
-	 * eb bumped.
+	 * It is only cleared in two cases: freeing the last non-tree
+	 * reference to the extent_buffer when its STALE bit is set or
+	 * calling releasepage when the tree reference is the only reference.
 	 *
-	 * We can't just set the ref bit without bumping the
-	 * ref on the eb because free_extent_buffer might
-	 * see the ref bit and try to clear it.  If this happens
-	 * free_extent_buffer might end up dropping our original
-	 * ref by mistake and freeing the page before we are able
-	 * to add one more ref.
+	 * In both cases, care is taken to ensure that the extent_buffer's
+	 * pages are not under io. However, releasepage can be concurrently
+	 * called with creating new references, which is prone to race
+	 * conditions between the calls to check_buffer_tree_ref in those
+	 * codepaths and clearing TREE_REF in try_release_extent_buffer.
 	 *
-	 * So bump the ref count first, then set the bit.  If someone
-	 * beat us to it, drop the ref we added.
+	 * The actual lifetime of the extent_buffer in the radix tree is
+	 * adequately protected by the refcount, but the TREE_REF bit and
+	 * its corresponding reference are not. To protect against this
+	 * class of races, we call check_buffer_tree_ref from the codepaths
+	 * which trigger io after they set eb->io_pages. Note that once io is
+	 * initiated, TREE_REF can no longer be cleared, so that is the
+	 * moment at which any such race is best fixed.
 	 */
 	refs = atomic_read(&eb->refs);
 	if (refs >= 2 && test_bit(EXTENT_BUFFER_TREE_REF, &eb->bflags))
@@ -5527,6 +5530,11 @@ int read_extent_buffer_pages(struct extent_buffer *eb, int wait, int mirror_num)
 	clear_bit(EXTENT_BUFFER_READ_ERR, &eb->bflags);
 	eb->read_mirror = 0;
 	atomic_set(&eb->io_pages, num_reads);
+	/*
+	 * It is possible for releasepage to clear the TREE_REF bit before we
+	 * set io_pages. See check_buffer_tree_ref for a more detailed comment.
+	 */
+	check_buffer_tree_ref(eb);
 	for (i = 0; i < num_pages; i++) {
 		page = eb->pages[i];
 
diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c
index 2520605afc25..b0d2c976587e 100644
--- a/fs/btrfs/file.c
+++ b/fs/btrfs/file.c
@@ -3509,6 +3509,7 @@ const struct file_operations btrfs_file_operations = {
 	.read_iter      = generic_file_read_iter,
 	.splice_read	= generic_file_splice_read,
 	.write_iter	= btrfs_file_write_iter,
+	.splice_write	= iter_file_splice_write,
 	.mmap		= btrfs_file_mmap,
 	.open		= btrfs_file_open,
 	.release	= btrfs_release_file,
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 18d384f4af54..43c803c16b48 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -1690,12 +1690,8 @@ out_check:
 			ret = fallback_to_cow(inode, locked_page, cow_start,
 					      found_key.offset - 1,
 					      page_started, nr_written);
-			if (ret) {
-				if (nocow)
-					btrfs_dec_nocow_writers(fs_info,
-								disk_bytenr);
+			if (ret)
 				goto error;
-			}
 			cow_start = (u64)-1;
 		}
 
@@ -1711,9 +1707,6 @@ out_check:
 					  ram_bytes, BTRFS_COMPRESS_NONE,
 					  BTRFS_ORDERED_PREALLOC);
 			if (IS_ERR(em)) {
-				if (nocow)
-					btrfs_dec_nocow_writers(fs_info,
-								disk_bytenr);
 				ret = PTR_ERR(em);
 				goto error;
 			}
diff --git a/fs/btrfs/ref-verify.c b/fs/btrfs/ref-verify.c
index 7887317033c9..af92525dbb16 100644
--- a/fs/btrfs/ref-verify.c
+++ b/fs/btrfs/ref-verify.c
@@ -509,7 +509,7 @@ static int process_leaf(struct btrfs_root *root,
 		switch (key.type) {
 		case BTRFS_EXTENT_ITEM_KEY:
 			*num_bytes = key.offset;
-			/* fall through */
+			fallthrough;
 		case BTRFS_METADATA_ITEM_KEY:
 			*bytenr = key.objectid;
 			ret = process_extent_item(fs_info, path, &key, i,
diff --git a/fs/btrfs/space-info.c b/fs/btrfs/space-info.c
index 41ee88633769..c7bd3fdd7792 100644
--- a/fs/btrfs/space-info.c
+++ b/fs/btrfs/space-info.c
@@ -879,8 +879,8 @@ static bool steal_from_global_rsv(struct btrfs_fs_info *fs_info,
 		return false;
 	}
 	global_rsv->reserved -= ticket->bytes;
+	remove_ticket(space_info, ticket);
 	ticket->bytes = 0;
-	list_del_init(&ticket->list);
 	wake_up(&ticket->wait);
 	space_info->tickets_id++;
 	if (global_rsv->reserved < global_rsv->size)
diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c
index bc73fd670702..c3826ae883f0 100644
--- a/fs/btrfs/super.c
+++ b/fs/btrfs/super.c
@@ -523,7 +523,7 @@ int btrfs_parse_options(struct btrfs_fs_info *info, char *options,
 		case Opt_compress_force:
 		case Opt_compress_force_type:
 			compress_force = true;
-			/* Fallthrough */
+			fallthrough;
 		case Opt_compress:
 		case Opt_compress_type:
 			saved_compress_type = btrfs_test_opt(info,
@@ -622,7 +622,7 @@ int btrfs_parse_options(struct btrfs_fs_info *info, char *options,
 			btrfs_set_opt(info->mount_opt, NOSSD);
 			btrfs_clear_and_info(info, SSD,
 					     "not using ssd optimizations");
-			/* Fallthrough */
+			fallthrough;
 		case Opt_nossd_spread:
 			btrfs_clear_and_info(info, SSD_SPREAD,
 					     "not using spread ssd allocation scheme");
@@ -793,7 +793,7 @@ int btrfs_parse_options(struct btrfs_fs_info *info, char *options,
 		case Opt_recovery:
 			btrfs_warn(info,
 				   "'recovery' is deprecated, use 'usebackuproot' instead");
-			/* fall through */
+			fallthrough;
 		case Opt_usebackuproot:
 			btrfs_info(info,
 				   "trying to use backup root at mount time");
diff --git a/fs/btrfs/volumes.h b/fs/btrfs/volumes.h
index f067b5934c46..75af2334b2e3 100644
--- a/fs/btrfs/volumes.h
+++ b/fs/btrfs/volumes.h
@@ -408,7 +408,7 @@ static inline enum btrfs_map_op btrfs_op(struct bio *bio)
 		return BTRFS_MAP_WRITE;
 	default:
 		WARN_ON_ONCE(1);
-		/* fall through */
+		fallthrough;
 	case REQ_OP_READ:
 		return BTRFS_MAP_READ;
 	}
diff --git a/fs/cachefiles/rdwr.c b/fs/cachefiles/rdwr.c
index e7726f5f1241..3080cda9e824 100644
--- a/fs/cachefiles/rdwr.c
+++ b/fs/cachefiles/rdwr.c
@@ -937,7 +937,7 @@ int cachefiles_write_page(struct fscache_storage *op, struct page *page)
 	}
 
 	data = kmap(page);
-	ret = __kernel_write(file, data, len, &pos);
+	ret = kernel_write(file, data, len, &pos);
 	kunmap(page);
 	fput(file);
 	if (ret != len)
diff --git a/fs/cifs/cifs_debug.c b/fs/cifs/cifs_debug.c
index fc98b97b396a..53588d7517b4 100644
--- a/fs/cifs/cifs_debug.c
+++ b/fs/cifs/cifs_debug.c
@@ -399,6 +399,10 @@ skip_rdma:
 			if (ses->sign)
 				seq_puts(m, " signed");
 
+			seq_printf(m, "\n\tUser: %d Cred User: %d",
+				   from_kuid(&init_user_ns, ses->linux_uid),
+				   from_kuid(&init_user_ns, ses->cred_uid));
+
 			if (ses->chan_count > 1) {
 				seq_printf(m, "\n\n\tExtra Channels: %zu\n",
 					   ses->chan_count-1);
@@ -406,7 +410,7 @@ skip_rdma:
 					cifs_dump_channel(m, j, &ses->chans[j]);
 			}
 
-			seq_puts(m, "\n\tShares:");
+			seq_puts(m, "\n\n\tShares:");
 			j = 0;
 
 			seq_printf(m, "\n\t%d) IPC: ", j);
diff --git a/fs/cifs/cifsfs.h b/fs/cifs/cifsfs.h
index c7a311d28d3d..99b3180c613a 100644
--- a/fs/cifs/cifsfs.h
+++ b/fs/cifs/cifsfs.h
@@ -156,5 +156,5 @@ extern int cifs_truncate_page(struct address_space *mapping, loff_t from);
 extern const struct export_operations cifs_export_ops;
 #endif /* CONFIG_CIFS_NFSD_EXPORT */
 
-#define CIFS_VERSION   "2.27"
+#define CIFS_VERSION   "2.28"
 #endif				/* _CIFSFS_H */
diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c
index 5fac34f192af..a61abde09ffe 100644
--- a/fs/cifs/connect.c
+++ b/fs/cifs/connect.c
@@ -5306,9 +5306,15 @@ cifs_construct_tcon(struct cifs_sb_info *cifs_sb, kuid_t fsuid)
 	vol_info->nocase = master_tcon->nocase;
 	vol_info->nohandlecache = master_tcon->nohandlecache;
 	vol_info->local_lease = master_tcon->local_lease;
+	vol_info->no_lease = master_tcon->no_lease;
+	vol_info->resilient = master_tcon->use_resilient;
+	vol_info->persistent = master_tcon->use_persistent;
+	vol_info->handle_timeout = master_tcon->handle_timeout;
 	vol_info->no_linux_ext = !master_tcon->unix_ext;
+	vol_info->linux_ext = master_tcon->posix_extensions;
 	vol_info->sectype = master_tcon->ses->sectype;
 	vol_info->sign = master_tcon->ses->sign;
+	vol_info->seal = master_tcon->seal;
 
 	rc = cifs_set_vol_auth(vol_info, master_tcon->ses);
 	if (rc) {
@@ -5334,10 +5340,6 @@ cifs_construct_tcon(struct cifs_sb_info *cifs_sb, kuid_t fsuid)
 		goto out;
 	}
 
-	/* if new SMB3.11 POSIX extensions are supported do not remap / and \ */
-	if (tcon->posix_extensions)
-		cifs_sb->mnt_cifs_flags |= CIFS_MOUNT_POSIX_PATHS;
-
 	if (cap_unix(ses))
 		reset_cifs_unix_caps(0, tcon, NULL, vol_info);
 
diff --git a/fs/cifs/file.c b/fs/cifs/file.c
index 9b0f8f33f832..be46fab4c96d 100644
--- a/fs/cifs/file.c
+++ b/fs/cifs/file.c
@@ -1149,20 +1149,20 @@ cifs_posix_lock_test(struct file *file, struct file_lock *flock)
 
 /*
  * Set the byte-range lock (posix style). Returns:
- * 1) 0, if we set the lock and don't need to request to the server;
- * 2) 1, if we need to request to the server;
- * 3) <0, if the error occurs while setting the lock.
+ * 1) <0, if the error occurs while setting the lock;
+ * 2) 0, if we set the lock and don't need to request to the server;
+ * 3) FILE_LOCK_DEFERRED, if we will wait for some other file_lock;
+ * 4) FILE_LOCK_DEFERRED + 1, if we need to request to the server.
  */
 static int
 cifs_posix_lock_set(struct file *file, struct file_lock *flock)
 {
 	struct cifsInodeInfo *cinode = CIFS_I(file_inode(file));
-	int rc = 1;
+	int rc = FILE_LOCK_DEFERRED + 1;
 
 	if ((flock->fl_flags & FL_POSIX) == 0)
 		return rc;
 
-try_again:
 	cifs_down_write(&cinode->lock_sem);
 	if (!cinode->can_cache_brlcks) {
 		up_write(&cinode->lock_sem);
@@ -1171,13 +1171,6 @@ try_again:
 
 	rc = posix_lock_file(file, flock, NULL);
 	up_write(&cinode->lock_sem);
-	if (rc == FILE_LOCK_DEFERRED) {
-		rc = wait_event_interruptible(flock->fl_wait,
-					list_empty(&flock->fl_blocked_member));
-		if (!rc)
-			goto try_again;
-		locks_delete_block(flock);
-	}
 	return rc;
 }
 
@@ -1652,7 +1645,7 @@ cifs_setlk(struct file *file, struct file_lock *flock, __u32 type,
 		int posix_lock_type;
 
 		rc = cifs_posix_lock_set(file, flock);
-		if (!rc || rc < 0)
+		if (rc <= FILE_LOCK_DEFERRED)
 			return rc;
 
 		if (type & server->vals->shared_lock_type)
diff --git a/fs/cifs/inode.c b/fs/cifs/inode.c
index ce95801e9b66..49c3ea8aa845 100644
--- a/fs/cifs/inode.c
+++ b/fs/cifs/inode.c
@@ -2044,6 +2044,7 @@ cifs_rename2(struct inode *source_dir, struct dentry *source_dentry,
 	FILE_UNIX_BASIC_INFO *info_buf_target;
 	unsigned int xid;
 	int rc, tmprc;
+	bool new_target = d_really_is_negative(target_dentry);
 
 	if (flags & ~RENAME_NOREPLACE)
 		return -EINVAL;
@@ -2120,8 +2121,13 @@ cifs_rename2(struct inode *source_dir, struct dentry *source_dentry,
 	 */
 
 unlink_target:
-	/* Try unlinking the target dentry if it's not negative */
-	if (d_really_is_positive(target_dentry) && (rc == -EACCES || rc == -EEXIST)) {
+	/*
+	 * If the target dentry was created during the rename, try
+	 * unlinking it if it's not negative
+	 */
+	if (new_target &&
+	    d_really_is_positive(target_dentry) &&
+	    (rc == -EACCES || rc == -EEXIST)) {
 		if (d_is_dir(target_dentry))
 			tmprc = cifs_rmdir(target_dir, target_dentry);
 		else
diff --git a/fs/cifs/ioctl.c b/fs/cifs/ioctl.c
index 4a73e63c4d43..dcde44ff6cf9 100644
--- a/fs/cifs/ioctl.c
+++ b/fs/cifs/ioctl.c
@@ -169,6 +169,7 @@ long cifs_ioctl(struct file *filep, unsigned int command, unsigned long arg)
 	unsigned int xid;
 	struct cifsFileInfo *pSMBFile = filep->private_data;
 	struct cifs_tcon *tcon;
+	struct tcon_link *tlink;
 	struct cifs_sb_info *cifs_sb;
 	__u64	ExtAttrBits = 0;
 	__u64   caps;
@@ -307,13 +308,19 @@ long cifs_ioctl(struct file *filep, unsigned int command, unsigned long arg)
 				break;
 			}
 			cifs_sb = CIFS_SB(inode->i_sb);
-			tcon = tlink_tcon(cifs_sb_tlink(cifs_sb));
+			tlink = cifs_sb_tlink(cifs_sb);
+			if (IS_ERR(tlink)) {
+				rc = PTR_ERR(tlink);
+				break;
+			}
+			tcon = tlink_tcon(tlink);
 			if (tcon && tcon->ses->server->ops->notify) {
 				rc = tcon->ses->server->ops->notify(xid,
 						filep, (void __user *)arg);
 				cifs_dbg(FYI, "ioctl notify rc %d\n", rc);
 			} else
 				rc = -EOPNOTSUPP;
+			cifs_put_tlink(tlink);
 			break;
 		default:
 			cifs_dbg(FYI, "unsupported ioctl\n");
diff --git a/fs/cifs/smb2misc.c b/fs/cifs/smb2misc.c
index 6a39451973f8..157992864ce7 100644
--- a/fs/cifs/smb2misc.c
+++ b/fs/cifs/smb2misc.c
@@ -354,9 +354,13 @@ smb2_get_data_area_len(int *off, int *len, struct smb2_sync_hdr *shdr)
 		  ((struct smb2_ioctl_rsp *)shdr)->OutputCount);
 		break;
 	case SMB2_CHANGE_NOTIFY:
+		*off = le16_to_cpu(
+		  ((struct smb2_change_notify_rsp *)shdr)->OutputBufferOffset);
+		*len = le32_to_cpu(
+		  ((struct smb2_change_notify_rsp *)shdr)->OutputBufferLength);
+		break;
 	default:
-		/* BB FIXME for unimplemented cases above */
-		cifs_dbg(VFS, "no length check for command\n");
+		cifs_dbg(VFS, "no length check for command %d\n", le16_to_cpu(shdr->Command));
 		break;
 	}
 
diff --git a/fs/cifs/smb2ops.c b/fs/cifs/smb2ops.c
index d9fdafa5eb60..32f90dc82c84 100644
--- a/fs/cifs/smb2ops.c
+++ b/fs/cifs/smb2ops.c
@@ -2148,7 +2148,7 @@ smb3_notify(const unsigned int xid, struct file *pfile,
 
 	tcon = cifs_sb_master_tcon(cifs_sb);
 	oparms.tcon = tcon;
-	oparms.desired_access = FILE_READ_ATTRIBUTES;
+	oparms.desired_access = FILE_READ_ATTRIBUTES | FILE_READ_DATA;
 	oparms.disposition = FILE_OPEN;
 	oparms.create_options = cifs_create_options(cifs_sb, 0);
 	oparms.fid = &fid;
diff --git a/fs/cifs/transport.c b/fs/cifs/transport.c
index d11e31064679..84433d0653f9 100644
--- a/fs/cifs/transport.c
+++ b/fs/cifs/transport.c
@@ -523,7 +523,7 @@ wait_for_free_credits(struct TCP_Server_Info *server, const int num_credits,
 		      const int timeout, const int flags,
 		      unsigned int *instance)
 {
-	int rc;
+	long rc;
 	int *credits;
 	int optype;
 	long int t;
diff --git a/fs/exfat/dir.c b/fs/exfat/dir.c
index de43534aa299..91ece649285d 100644
--- a/fs/exfat/dir.c
+++ b/fs/exfat/dir.c
@@ -309,7 +309,7 @@ const struct file_operations exfat_dir_operations = {
 	.llseek		= generic_file_llseek,
 	.read		= generic_read_dir,
 	.iterate	= exfat_iterate,
-	.fsync		= generic_file_fsync,
+	.fsync		= exfat_file_fsync,
 };
 
 int exfat_alloc_new_dir(struct inode *inode, struct exfat_chain *clu)
@@ -425,10 +425,12 @@ static void exfat_init_name_entry(struct exfat_dentry *ep,
 	ep->dentry.name.flags = 0x0;
 
 	for (i = 0; i < EXFAT_FILE_NAME_LEN; i++) {
-		ep->dentry.name.unicode_0_14[i] = cpu_to_le16(*uniname);
-		if (*uniname == 0x0)
-			break;
-		uniname++;
+		if (*uniname != 0x0) {
+			ep->dentry.name.unicode_0_14[i] = cpu_to_le16(*uniname);
+			uniname++;
+		} else {
+			ep->dentry.name.unicode_0_14[i] = 0x0;
+		}
 	}
 }
 
diff --git a/fs/exfat/exfat_fs.h b/fs/exfat/exfat_fs.h
index 595f3117f492..7579cd3bbadb 100644
--- a/fs/exfat/exfat_fs.h
+++ b/fs/exfat/exfat_fs.h
@@ -420,6 +420,7 @@ void exfat_truncate(struct inode *inode, loff_t size);
 int exfat_setattr(struct dentry *dentry, struct iattr *attr);
 int exfat_getattr(const struct path *path, struct kstat *stat,
 		unsigned int request_mask, unsigned int query_flags);
+int exfat_file_fsync(struct file *file, loff_t start, loff_t end, int datasync);
 
 /* namei.c */
 extern const struct dentry_operations exfat_dentry_ops;
diff --git a/fs/exfat/file.c b/fs/exfat/file.c
index fce03f318787..3b7fea465fd4 100644
--- a/fs/exfat/file.c
+++ b/fs/exfat/file.c
@@ -6,6 +6,7 @@
 #include <linux/slab.h>
 #include <linux/cred.h>
 #include <linux/buffer_head.h>
+#include <linux/blkdev.h>
 
 #include "exfat_raw.h"
 #include "exfat_fs.h"
@@ -346,12 +347,28 @@ out:
 	return error;
 }
 
+int exfat_file_fsync(struct file *filp, loff_t start, loff_t end, int datasync)
+{
+	struct inode *inode = filp->f_mapping->host;
+	int err;
+
+	err = __generic_file_fsync(filp, start, end, datasync);
+	if (err)
+		return err;
+
+	err = sync_blockdev(inode->i_sb->s_bdev);
+	if (err)
+		return err;
+
+	return blkdev_issue_flush(inode->i_sb->s_bdev, GFP_KERNEL);
+}
+
 const struct file_operations exfat_file_operations = {
 	.llseek		= generic_file_llseek,
 	.read_iter	= generic_file_read_iter,
 	.write_iter	= generic_file_write_iter,
 	.mmap		= generic_file_mmap,
-	.fsync		= generic_file_fsync,
+	.fsync		= exfat_file_fsync,
 	.splice_read	= generic_file_splice_read,
 	.splice_write	= iter_file_splice_write,
 };
diff --git a/fs/exfat/namei.c b/fs/exfat/namei.c
index 5b0f35329d63..2b9e21094a96 100644
--- a/fs/exfat/namei.c
+++ b/fs/exfat/namei.c
@@ -975,7 +975,6 @@ static int exfat_rmdir(struct inode *dir, struct dentry *dentry)
 		goto unlock;
 	}
 
-	exfat_set_vol_flags(sb, VOL_DIRTY);
 	exfat_chain_set(&clu_to_free, ei->start_clu,
 		EXFAT_B_TO_CLU_ROUND_UP(i_size_read(inode), sbi), ei->flags);
 
@@ -1002,6 +1001,7 @@ static int exfat_rmdir(struct inode *dir, struct dentry *dentry)
 	num_entries++;
 	brelse(bh);
 
+	exfat_set_vol_flags(sb, VOL_DIRTY);
 	err = exfat_remove_entries(dir, &cdir, entry, 0, num_entries);
 	if (err) {
 		exfat_err(sb, "failed to exfat_remove_entries : err(%d)", err);
@@ -1077,10 +1077,14 @@ static int exfat_rename_file(struct inode *inode, struct exfat_chain *p_dir,
 
 		epold = exfat_get_dentry(sb, p_dir, oldentry + 1, &old_bh,
 			&sector_old);
+		if (!epold)
+			return -EIO;
 		epnew = exfat_get_dentry(sb, p_dir, newentry + 1, &new_bh,
 			&sector_new);
-		if (!epold || !epnew)
+		if (!epnew) {
+			brelse(old_bh);
 			return -EIO;
+		}
 
 		memcpy(epnew, epold, DENTRY_SIZE);
 		exfat_update_bh(sb, new_bh, sync);
@@ -1161,10 +1165,14 @@ static int exfat_move_file(struct inode *inode, struct exfat_chain *p_olddir,
 
 	epmov = exfat_get_dentry(sb, p_olddir, oldentry + 1, &mov_bh,
 		&sector_mov);
+	if (!epmov)
+		return -EIO;
 	epnew = exfat_get_dentry(sb, p_newdir, newentry + 1, &new_bh,
 		&sector_new);
-	if (!epmov || !epnew)
+	if (!epnew) {
+		brelse(mov_bh);
 		return -EIO;
+	}
 
 	memcpy(epnew, epmov, DENTRY_SIZE);
 	exfat_update_bh(sb, new_bh, IS_DIRSYNC(inode));
diff --git a/fs/exfat/super.c b/fs/exfat/super.c
index e650e65536f8..253a92460d52 100644
--- a/fs/exfat/super.c
+++ b/fs/exfat/super.c
@@ -693,10 +693,20 @@ static void exfat_free(struct fs_context *fc)
 	}
 }
 
+static int exfat_reconfigure(struct fs_context *fc)
+{
+	fc->sb_flags |= SB_NODIRATIME;
+
+	/* volume flag will be updated in exfat_sync_fs */
+	sync_filesystem(fc->root->d_sb);
+	return 0;
+}
+
 static const struct fs_context_operations exfat_context_ops = {
 	.parse_param	= exfat_parse_param,
 	.get_tree	= exfat_get_tree,
 	.free		= exfat_free,
+	.reconfigure	= exfat_reconfigure,
 };
 
 static int exfat_init_fs_context(struct fs_context *fc)
diff --git a/fs/file_table.c b/fs/file_table.c
index 65603502fed6..656647f9575a 100644
--- a/fs/file_table.c
+++ b/fs/file_table.c
@@ -230,7 +230,7 @@ struct file *alloc_file_pseudo(struct inode *inode, struct vfsmount *mnt,
 		d_set_d_op(path.dentry, &anon_ops);
 	path.mnt = mntget(mnt);
 	d_instantiate(path.dentry, inode);
-	file = alloc_file(&path, flags | FMODE_NONOTIFY, fops);
+	file = alloc_file(&path, flags, fops);
 	if (IS_ERR(file)) {
 		ihold(inode);
 		path_put(&path);
diff --git a/fs/fuse/file.c b/fs/fuse/file.c
index e573b0cd2737..83d917f7e542 100644
--- a/fs/fuse/file.c
+++ b/fs/fuse/file.c
@@ -18,6 +18,7 @@
 #include <linux/swap.h>
 #include <linux/falloc.h>
 #include <linux/uio.h>
+#include <linux/fs.h>
 
 static struct page **fuse_pages_alloc(unsigned int npages, gfp_t flags,
 				      struct fuse_page_desc **desc)
@@ -1586,7 +1587,6 @@ static void fuse_writepage_finish(struct fuse_conn *fc,
 	struct backing_dev_info *bdi = inode_to_bdi(inode);
 	int i;
 
-	rb_erase(&wpa->writepages_entry, &fi->writepages);
 	for (i = 0; i < ap->num_pages; i++) {
 		dec_wb_stat(&bdi->wb, WB_WRITEBACK);
 		dec_node_page_state(ap->pages[i], NR_WRITEBACK_TEMP);
@@ -1637,6 +1637,7 @@ __acquires(fi->lock)
 
  out_free:
 	fi->writectr--;
+	rb_erase(&wpa->writepages_entry, &fi->writepages);
 	fuse_writepage_finish(fc, wpa);
 	spin_unlock(&fi->lock);
 
@@ -1674,7 +1675,8 @@ __acquires(fi->lock)
 	}
 }
 
-static void tree_insert(struct rb_root *root, struct fuse_writepage_args *wpa)
+static struct fuse_writepage_args *fuse_insert_writeback(struct rb_root *root,
+						struct fuse_writepage_args *wpa)
 {
 	pgoff_t idx_from = wpa->ia.write.in.offset >> PAGE_SHIFT;
 	pgoff_t idx_to = idx_from + wpa->ia.ap.num_pages - 1;
@@ -1697,11 +1699,17 @@ static void tree_insert(struct rb_root *root, struct fuse_writepage_args *wpa)
 		else if (idx_to < curr_index)
 			p = &(*p)->rb_left;
 		else
-			return (void) WARN_ON(true);
+			return curr;
 	}
 
 	rb_link_node(&wpa->writepages_entry, parent, p);
 	rb_insert_color(&wpa->writepages_entry, root);
+	return NULL;
+}
+
+static void tree_insert(struct rb_root *root, struct fuse_writepage_args *wpa)
+{
+	WARN_ON(fuse_insert_writeback(root, wpa));
 }
 
 static void fuse_writepage_end(struct fuse_conn *fc, struct fuse_args *args,
@@ -1714,6 +1722,7 @@ static void fuse_writepage_end(struct fuse_conn *fc, struct fuse_args *args,
 
 	mapping_set_error(inode->i_mapping, error);
 	spin_lock(&fi->lock);
+	rb_erase(&wpa->writepages_entry, &fi->writepages);
 	while (wpa->next) {
 		struct fuse_conn *fc = get_fuse_conn(inode);
 		struct fuse_write_in *inarg = &wpa->ia.write.in;
@@ -1952,14 +1961,14 @@ static void fuse_writepages_send(struct fuse_fill_wb_data *data)
 }
 
 /*
- * First recheck under fi->lock if the offending offset is still under
- * writeback.  If yes, then iterate auxiliary write requests, to see if there's
+ * Check under fi->lock if the page is under writeback, and insert it onto the
+ * rb_tree if not. Otherwise iterate auxiliary write requests, to see if there's
  * one already added for a page at this offset.  If there's none, then insert
  * this new request onto the auxiliary list, otherwise reuse the existing one by
- * copying the new page contents over to the old temporary page.
+ * swapping the new temp page with the old one.
  */
-static bool fuse_writepage_in_flight(struct fuse_writepage_args *new_wpa,
-				     struct page *page)
+static bool fuse_writepage_add(struct fuse_writepage_args *new_wpa,
+			       struct page *page)
 {
 	struct fuse_inode *fi = get_fuse_inode(new_wpa->inode);
 	struct fuse_writepage_args *tmp;
@@ -1967,17 +1976,15 @@ static bool fuse_writepage_in_flight(struct fuse_writepage_args *new_wpa,
 	struct fuse_args_pages *new_ap = &new_wpa->ia.ap;
 
 	WARN_ON(new_ap->num_pages != 0);
+	new_ap->num_pages = 1;
 
 	spin_lock(&fi->lock);
-	rb_erase(&new_wpa->writepages_entry, &fi->writepages);
-	old_wpa = fuse_find_writeback(fi, page->index, page->index);
+	old_wpa = fuse_insert_writeback(&fi->writepages, new_wpa);
 	if (!old_wpa) {
-		tree_insert(&fi->writepages, new_wpa);
 		spin_unlock(&fi->lock);
-		return false;
+		return true;
 	}
 
-	new_ap->num_pages = 1;
 	for (tmp = old_wpa->next; tmp; tmp = tmp->next) {
 		pgoff_t curr_index;
 
@@ -2006,7 +2013,41 @@ static bool fuse_writepage_in_flight(struct fuse_writepage_args *new_wpa,
 		fuse_writepage_free(new_wpa);
 	}
 
-	return true;
+	return false;
+}
+
+static bool fuse_writepage_need_send(struct fuse_conn *fc, struct page *page,
+				     struct fuse_args_pages *ap,
+				     struct fuse_fill_wb_data *data)
+{
+	WARN_ON(!ap->num_pages);
+
+	/*
+	 * Being under writeback is unlikely but possible.  For example direct
+	 * read to an mmaped fuse file will set the page dirty twice; once when
+	 * the pages are faulted with get_user_pages(), and then after the read
+	 * completed.
+	 */
+	if (fuse_page_is_writeback(data->inode, page->index))
+		return true;
+
+	/* Reached max pages */
+	if (ap->num_pages == fc->max_pages)
+		return true;
+
+	/* Reached max write bytes */
+	if ((ap->num_pages + 1) * PAGE_SIZE > fc->max_write)
+		return true;
+
+	/* Discontinuity */
+	if (data->orig_pages[ap->num_pages - 1]->index + 1 != page->index)
+		return true;
+
+	/* Need to grow the pages array?  If so, did the expansion fail? */
+	if (ap->num_pages == data->max_pages && !fuse_pages_realloc(data))
+		return true;
+
+	return false;
 }
 
 static int fuse_writepages_fill(struct page *page,
@@ -2019,7 +2060,6 @@ static int fuse_writepages_fill(struct page *page,
 	struct fuse_inode *fi = get_fuse_inode(inode);
 	struct fuse_conn *fc = get_fuse_conn(inode);
 	struct page *tmp_page;
-	bool is_writeback;
 	int err;
 
 	if (!data->ff) {
@@ -2029,25 +2069,9 @@ static int fuse_writepages_fill(struct page *page,
 			goto out_unlock;
 	}
 
-	/*
-	 * Being under writeback is unlikely but possible.  For example direct
-	 * read to an mmaped fuse file will set the page dirty twice; once when
-	 * the pages are faulted with get_user_pages(), and then after the read
-	 * completed.
-	 */
-	is_writeback = fuse_page_is_writeback(inode, page->index);
-
-	if (wpa && ap->num_pages &&
-	    (is_writeback || ap->num_pages == fc->max_pages ||
-	     (ap->num_pages + 1) * PAGE_SIZE > fc->max_write ||
-	     data->orig_pages[ap->num_pages - 1]->index + 1 != page->index)) {
+	if (wpa && fuse_writepage_need_send(fc, page, ap, data)) {
 		fuse_writepages_send(data);
 		data->wpa = NULL;
-	} else if (wpa && ap->num_pages == data->max_pages) {
-		if (!fuse_pages_realloc(data)) {
-			fuse_writepages_send(data);
-			data->wpa = NULL;
-		}
 	}
 
 	err = -ENOMEM;
@@ -2085,12 +2109,6 @@ static int fuse_writepages_fill(struct page *page,
 		ap->args.end = fuse_writepage_end;
 		ap->num_pages = 0;
 		wpa->inode = inode;
-
-		spin_lock(&fi->lock);
-		tree_insert(&fi->writepages, wpa);
-		spin_unlock(&fi->lock);
-
-		data->wpa = wpa;
 	}
 	set_page_writeback(page);
 
@@ -2098,26 +2116,25 @@ static int fuse_writepages_fill(struct page *page,
 	ap->pages[ap->num_pages] = tmp_page;
 	ap->descs[ap->num_pages].offset = 0;
 	ap->descs[ap->num_pages].length = PAGE_SIZE;
+	data->orig_pages[ap->num_pages] = page;
 
 	inc_wb_stat(&inode_to_bdi(inode)->wb, WB_WRITEBACK);
 	inc_node_page_state(tmp_page, NR_WRITEBACK_TEMP);
 
 	err = 0;
-	if (is_writeback && fuse_writepage_in_flight(wpa, page)) {
+	if (data->wpa) {
+		/*
+		 * Protected by fi->lock against concurrent access by
+		 * fuse_page_is_writeback().
+		 */
+		spin_lock(&fi->lock);
+		ap->num_pages++;
+		spin_unlock(&fi->lock);
+	} else if (fuse_writepage_add(wpa, page)) {
+		data->wpa = wpa;
+	} else {
 		end_page_writeback(page);
-		data->wpa = NULL;
-		goto out_unlock;
 	}
-	data->orig_pages[ap->num_pages] = page;
-
-	/*
-	 * Protected by fi->lock against concurrent access by
-	 * fuse_page_is_writeback().
-	 */
-	spin_lock(&fi->lock);
-	ap->num_pages++;
-	spin_unlock(&fi->lock);
-
 out_unlock:
 	unlock_page(page);
 
@@ -2149,10 +2166,8 @@ static int fuse_writepages(struct address_space *mapping,
 
 	err = write_cache_pages(mapping, wbc, fuse_writepages_fill, &data);
 	if (data.wpa) {
-		/* Ignore errors if we can write at least one page */
 		WARN_ON(!data.wpa->ia.ap.num_pages);
 		fuse_writepages_send(&data);
-		err = 0;
 	}
 	if (data.ff)
 		fuse_file_put(data.ff, false, false);
@@ -2761,7 +2776,16 @@ long fuse_do_ioctl(struct file *file, unsigned int cmd, unsigned long arg,
 		struct iovec *iov = iov_page;
 
 		iov->iov_base = (void __user *)arg;
-		iov->iov_len = _IOC_SIZE(cmd);
+
+		switch (cmd) {
+		case FS_IOC_GETFLAGS:
+		case FS_IOC_SETFLAGS:
+			iov->iov_len = sizeof(int);
+			break;
+		default:
+			iov->iov_len = _IOC_SIZE(cmd);
+			break;
+		}
 
 		if (_IOC_DIR(cmd) & _IOC_WRITE) {
 			in_iov = iov;
diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c
index 5b4aebf5821f..bba747520e9b 100644
--- a/fs/fuse/inode.c
+++ b/fs/fuse/inode.c
@@ -121,10 +121,12 @@ static void fuse_evict_inode(struct inode *inode)
 	}
 }
 
-static int fuse_remount_fs(struct super_block *sb, int *flags, char *data)
+static int fuse_reconfigure(struct fs_context *fc)
 {
+	struct super_block *sb = fc->root->d_sb;
+
 	sync_filesystem(sb);
-	if (*flags & SB_MANDLOCK)
+	if (fc->sb_flags & SB_MANDLOCK)
 		return -EINVAL;
 
 	return 0;
@@ -475,6 +477,17 @@ static int fuse_parse_param(struct fs_context *fc, struct fs_parameter *param)
 	struct fuse_fs_context *ctx = fc->fs_private;
 	int opt;
 
+	if (fc->purpose == FS_CONTEXT_FOR_RECONFIGURE) {
+		/*
+		 * Ignore options coming from mount(MS_REMOUNT) for backward
+		 * compatibility.
+		 */
+		if (fc->oldapi)
+			return 0;
+
+		return invalfc(fc, "No changes allowed in reconfigure");
+	}
+
 	opt = fs_parse(fc, fuse_fs_parameters, param, &result);
 	if (opt < 0)
 		return opt;
@@ -817,7 +830,6 @@ static const struct super_operations fuse_super_operations = {
 	.evict_inode	= fuse_evict_inode,
 	.write_inode	= fuse_write_inode,
 	.drop_inode	= generic_delete_inode,
-	.remount_fs	= fuse_remount_fs,
 	.put_super	= fuse_put_super,
 	.umount_begin	= fuse_umount_begin,
 	.statfs		= fuse_statfs,
@@ -1296,6 +1308,7 @@ static int fuse_get_tree(struct fs_context *fc)
 static const struct fs_context_operations fuse_context_ops = {
 	.free		= fuse_free_fc,
 	.parse_param	= fuse_parse_param,
+	.reconfigure	= fuse_reconfigure,
 	.get_tree	= fuse_get_tree,
 };
 
diff --git a/fs/gfs2/aops.c b/fs/gfs2/aops.c
index 72c9560f4467..68cd700a2719 100644
--- a/fs/gfs2/aops.c
+++ b/fs/gfs2/aops.c
@@ -468,21 +468,10 @@ static int stuffed_readpage(struct gfs2_inode *ip, struct page *page)
 }
 
 
-/**
- * __gfs2_readpage - readpage
- * @file: The file to read a page for
- * @page: The page to read
- *
- * This is the core of gfs2's readpage. It's used by the internal file
- * reading code as in that case we already hold the glock. Also it's
- * called by gfs2_readpage() once the required lock has been granted.
- */
-
 static int __gfs2_readpage(void *file, struct page *page)
 {
 	struct gfs2_inode *ip = GFS2_I(page->mapping->host);
 	struct gfs2_sbd *sdp = GFS2_SB(page->mapping->host);
-
 	int error;
 
 	if (i_blocksize(page->mapping->host) == PAGE_SIZE &&
@@ -505,36 +494,11 @@ static int __gfs2_readpage(void *file, struct page *page)
  * gfs2_readpage - read a page of a file
  * @file: The file to read
  * @page: The page of the file
- *
- * This deals with the locking required. We have to unlock and
- * relock the page in order to get the locking in the right
- * order.
  */
 
 static int gfs2_readpage(struct file *file, struct page *page)
 {
-	struct address_space *mapping = page->mapping;
-	struct gfs2_inode *ip = GFS2_I(mapping->host);
-	struct gfs2_holder gh;
-	int error;
-
-	unlock_page(page);
-	gfs2_holder_init(ip->i_gl, LM_ST_SHARED, 0, &gh);
-	error = gfs2_glock_nq(&gh);
-	if (unlikely(error))
-		goto out;
-	error = AOP_TRUNCATED_PAGE;
-	lock_page(page);
-	if (page->mapping == mapping && !PageUptodate(page))
-		error = __gfs2_readpage(file, page);
-	else
-		unlock_page(page);
-	gfs2_glock_dq(&gh);
-out:
-	gfs2_holder_uninit(&gh);
-	if (error && error != AOP_TRUNCATED_PAGE)
-		lock_page(page);
-	return error;
+	return __gfs2_readpage(file, page);
 }
 
 /**
@@ -598,16 +562,9 @@ static void gfs2_readahead(struct readahead_control *rac)
 {
 	struct inode *inode = rac->mapping->host;
 	struct gfs2_inode *ip = GFS2_I(inode);
-	struct gfs2_holder gh;
 
-	gfs2_holder_init(ip->i_gl, LM_ST_SHARED, 0, &gh);
-	if (gfs2_glock_nq(&gh))
-		goto out_uninit;
 	if (!gfs2_is_stuffed(ip))
 		mpage_readahead(rac, gfs2_block_map);
-	gfs2_glock_dq(&gh);
-out_uninit:
-	gfs2_holder_uninit(&gh);
 }
 
 /**
diff --git a/fs/gfs2/file.c b/fs/gfs2/file.c
index fe305e4bfd37..bebde537ac8c 100644
--- a/fs/gfs2/file.c
+++ b/fs/gfs2/file.c
@@ -558,8 +558,29 @@ out_uninit:
 	return block_page_mkwrite_return(ret);
 }
 
+static vm_fault_t gfs2_fault(struct vm_fault *vmf)
+{
+	struct inode *inode = file_inode(vmf->vma->vm_file);
+	struct gfs2_inode *ip = GFS2_I(inode);
+	struct gfs2_holder gh;
+	vm_fault_t ret;
+	int err;
+
+	gfs2_holder_init(ip->i_gl, LM_ST_SHARED, 0, &gh);
+	err = gfs2_glock_nq(&gh);
+	if (err) {
+		ret = block_page_mkwrite_return(err);
+		goto out_uninit;
+	}
+	ret = filemap_fault(vmf);
+	gfs2_glock_dq(&gh);
+out_uninit:
+	gfs2_holder_uninit(&gh);
+	return ret;
+}
+
 static const struct vm_operations_struct gfs2_vm_ops = {
-	.fault = filemap_fault,
+	.fault = gfs2_fault,
 	.map_pages = filemap_map_pages,
 	.page_mkwrite = gfs2_page_mkwrite,
 };
@@ -824,6 +845,9 @@ out_uninit:
 
 static ssize_t gfs2_file_read_iter(struct kiocb *iocb, struct iov_iter *to)
 {
+	struct gfs2_inode *ip;
+	struct gfs2_holder gh;
+	size_t written = 0;
 	ssize_t ret;
 
 	if (iocb->ki_flags & IOCB_DIRECT) {
@@ -832,7 +856,31 @@ static ssize_t gfs2_file_read_iter(struct kiocb *iocb, struct iov_iter *to)
 			return ret;
 		iocb->ki_flags &= ~IOCB_DIRECT;
 	}
-	return generic_file_read_iter(iocb, to);
+	iocb->ki_flags |= IOCB_NOIO;
+	ret = generic_file_read_iter(iocb, to);
+	iocb->ki_flags &= ~IOCB_NOIO;
+	if (ret >= 0) {
+		if (!iov_iter_count(to))
+			return ret;
+		written = ret;
+	} else {
+		if (ret != -EAGAIN)
+			return ret;
+		if (iocb->ki_flags & IOCB_NOWAIT)
+			return ret;
+	}
+	ip = GFS2_I(iocb->ki_filp->f_mapping->host);
+	gfs2_holder_init(ip->i_gl, LM_ST_SHARED, 0, &gh);
+	ret = gfs2_glock_nq(&gh);
+	if (ret)
+		goto out_uninit;
+	ret = generic_file_read_iter(iocb, to);
+	if (ret > 0)
+		written += ret;
+	gfs2_glock_dq(&gh);
+out_uninit:
+	gfs2_holder_uninit(&gh);
+	return written ? written : ret;
 }
 
 /**
diff --git a/fs/gfs2/glock.c b/fs/gfs2/glock.c
index 2299dcc417ea..8545024a1401 100644
--- a/fs/gfs2/glock.c
+++ b/fs/gfs2/glock.c
@@ -1899,7 +1899,10 @@ bool gfs2_delete_work_queued(const struct gfs2_glock *gl)
 
 static void flush_delete_work(struct gfs2_glock *gl)
 {
-	flush_delayed_work(&gl->gl_delete);
+	if (cancel_delayed_work(&gl->gl_delete)) {
+		queue_delayed_work(gfs2_delete_workqueue,
+				   &gl->gl_delete, 0);
+	}
 	gfs2_glock_queue_work(gl, 0);
 }
 
diff --git a/fs/gfs2/glops.c b/fs/gfs2/glops.c
index c84887769b5a..de1d5f1d9ff8 100644
--- a/fs/gfs2/glops.c
+++ b/fs/gfs2/glops.c
@@ -531,8 +531,7 @@ static int freeze_go_sync(struct gfs2_glock *gl)
 	int error = 0;
 	struct gfs2_sbd *sdp = gl->gl_name.ln_sbd;
 
-	if (gl->gl_state == LM_ST_SHARED && !gfs2_withdrawn(sdp) &&
-	    test_bit(SDF_JOURNAL_LIVE, &sdp->sd_flags)) {
+	if (gl->gl_req == LM_ST_EXCLUSIVE && !gfs2_withdrawn(sdp)) {
 		atomic_set(&sdp->sd_freeze_state, SFS_STARTING_FREEZE);
 		error = freeze_super(sdp->sd_vfs);
 		if (error) {
@@ -545,8 +544,11 @@ static int freeze_go_sync(struct gfs2_glock *gl)
 			gfs2_assert_withdraw(sdp, 0);
 		}
 		queue_work(gfs2_freeze_wq, &sdp->sd_freeze_work);
-		gfs2_log_flush(sdp, NULL, GFS2_LOG_HEAD_FLUSH_FREEZE |
-			       GFS2_LFC_FREEZE_GO_SYNC);
+		if (test_bit(SDF_JOURNAL_LIVE, &sdp->sd_flags))
+			gfs2_log_flush(sdp, NULL, GFS2_LOG_HEAD_FLUSH_FREEZE |
+				       GFS2_LFC_FREEZE_GO_SYNC);
+		else /* read-only mounts */
+			atomic_set(&sdp->sd_freeze_state, SFS_FROZEN);
 	}
 	return 0;
 }
diff --git a/fs/gfs2/incore.h b/fs/gfs2/incore.h
index 03ab11fab962..ca2ec02436ec 100644
--- a/fs/gfs2/incore.h
+++ b/fs/gfs2/incore.h
@@ -399,7 +399,6 @@ enum {
 	GIF_QD_LOCKED		= 1,
 	GIF_ALLOC_FAILED	= 2,
 	GIF_SW_PAGED		= 3,
-	GIF_ORDERED		= 4,
 	GIF_FREE_VFS_INODE      = 5,
 	GIF_GLOP_PENDING	= 6,
 	GIF_DEFERRED_DELETE	= 7,
diff --git a/fs/gfs2/inode.c b/fs/gfs2/inode.c
index 370c3a4b31ac..6774865f5b5b 100644
--- a/fs/gfs2/inode.c
+++ b/fs/gfs2/inode.c
@@ -207,10 +207,11 @@ struct inode *gfs2_inode_lookup(struct super_block *sb, unsigned int type,
 
 	if (no_formal_ino && ip->i_no_formal_ino &&
 	    no_formal_ino != ip->i_no_formal_ino) {
+		error = -ESTALE;
 		if (inode->i_state & I_NEW)
 			goto fail;
 		iput(inode);
-		return ERR_PTR(-ESTALE);
+		return ERR_PTR(error);
 	}
 
 	if (inode->i_state & I_NEW)
diff --git a/fs/gfs2/log.c b/fs/gfs2/log.c
index 3e4734431783..a76e55bc28eb 100644
--- a/fs/gfs2/log.c
+++ b/fs/gfs2/log.c
@@ -613,6 +613,12 @@ static int ip_cmp(void *priv, struct list_head *a, struct list_head *b)
 	return 0;
 }
 
+static void __ordered_del_inode(struct gfs2_inode *ip)
+{
+	if (!list_empty(&ip->i_ordered))
+		list_del_init(&ip->i_ordered);
+}
+
 static void gfs2_ordered_write(struct gfs2_sbd *sdp)
 {
 	struct gfs2_inode *ip;
@@ -623,8 +629,7 @@ static void gfs2_ordered_write(struct gfs2_sbd *sdp)
 	while (!list_empty(&sdp->sd_log_ordered)) {
 		ip = list_first_entry(&sdp->sd_log_ordered, struct gfs2_inode, i_ordered);
 		if (ip->i_inode.i_mapping->nrpages == 0) {
-			test_and_clear_bit(GIF_ORDERED, &ip->i_flags);
-			list_del(&ip->i_ordered);
+			__ordered_del_inode(ip);
 			continue;
 		}
 		list_move(&ip->i_ordered, &written);
@@ -643,8 +648,7 @@ static void gfs2_ordered_wait(struct gfs2_sbd *sdp)
 	spin_lock(&sdp->sd_ordered_lock);
 	while (!list_empty(&sdp->sd_log_ordered)) {
 		ip = list_first_entry(&sdp->sd_log_ordered, struct gfs2_inode, i_ordered);
-		list_del(&ip->i_ordered);
-		WARN_ON(!test_and_clear_bit(GIF_ORDERED, &ip->i_flags));
+		__ordered_del_inode(ip);
 		if (ip->i_inode.i_mapping->nrpages == 0)
 			continue;
 		spin_unlock(&sdp->sd_ordered_lock);
@@ -659,8 +663,7 @@ void gfs2_ordered_del_inode(struct gfs2_inode *ip)
 	struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode);
 
 	spin_lock(&sdp->sd_ordered_lock);
-	if (test_and_clear_bit(GIF_ORDERED, &ip->i_flags))
-		list_del(&ip->i_ordered);
+	__ordered_del_inode(ip);
 	spin_unlock(&sdp->sd_ordered_lock);
 }
 
@@ -1002,6 +1005,16 @@ void gfs2_log_flush(struct gfs2_sbd *sdp, struct gfs2_glock *gl, u32 flags)
 
 out:
 	if (gfs2_withdrawn(sdp)) {
+		/**
+		 * If the tr_list is empty, we're withdrawing during a log
+		 * flush that targets a transaction, but the transaction was
+		 * never queued onto any of the ail lists. Here we add it to
+		 * ail1 just so that ail_drain() will find and free it.
+		 */
+		spin_lock(&sdp->sd_ail_lock);
+		if (tr && list_empty(&tr->tr_list))
+			list_add(&tr->tr_list, &sdp->sd_ail1_list);
+		spin_unlock(&sdp->sd_ail_lock);
 		ail_drain(sdp); /* frees all transactions */
 		tr = NULL;
 	}
diff --git a/fs/gfs2/log.h b/fs/gfs2/log.h
index c1cd6ae17659..8965c751a303 100644
--- a/fs/gfs2/log.h
+++ b/fs/gfs2/log.h
@@ -53,9 +53,9 @@ static inline void gfs2_ordered_add_inode(struct gfs2_inode *ip)
 	if (gfs2_is_jdata(ip) || !gfs2_is_ordered(sdp))
 		return;
 
-	if (!test_bit(GIF_ORDERED, &ip->i_flags)) {
+	if (list_empty(&ip->i_ordered)) {
 		spin_lock(&sdp->sd_ordered_lock);
-		if (!test_and_set_bit(GIF_ORDERED, &ip->i_flags))
+		if (list_empty(&ip->i_ordered))
 			list_add(&ip->i_ordered, &sdp->sd_log_ordered);
 		spin_unlock(&sdp->sd_ordered_lock);
 	}
diff --git a/fs/gfs2/main.c b/fs/gfs2/main.c
index 733470ca6be9..c7393ee9cf68 100644
--- a/fs/gfs2/main.c
+++ b/fs/gfs2/main.c
@@ -39,6 +39,7 @@ static void gfs2_init_inode_once(void *foo)
 	atomic_set(&ip->i_sizehint, 0);
 	init_rwsem(&ip->i_rw_mutex);
 	INIT_LIST_HEAD(&ip->i_trunc_list);
+	INIT_LIST_HEAD(&ip->i_ordered);
 	ip->i_qadata = NULL;
 	gfs2_holder_mark_uninitialized(&ip->i_rgd_gh);
 	memset(&ip->i_res, 0, sizeof(ip->i_res));
diff --git a/fs/gfs2/ops_fstype.c b/fs/gfs2/ops_fstype.c
index 094f5fe7c009..6d18d2c91add 100644
--- a/fs/gfs2/ops_fstype.c
+++ b/fs/gfs2/ops_fstype.c
@@ -1136,7 +1136,18 @@ static int gfs2_fill_super(struct super_block *sb, struct fs_context *fc)
 		goto fail_per_node;
 	}
 
-	if (!sb_rdonly(sb)) {
+	if (sb_rdonly(sb)) {
+		struct gfs2_holder freeze_gh;
+
+		error = gfs2_glock_nq_init(sdp->sd_freeze_gl, LM_ST_SHARED,
+					   LM_FLAG_NOEXP | GL_EXACT,
+					   &freeze_gh);
+		if (error) {
+			fs_err(sdp, "can't make FS RO: %d\n", error);
+			goto fail_per_node;
+		}
+		gfs2_glock_dq_uninit(&freeze_gh);
+	} else {
 		error = gfs2_make_fs_rw(sdp);
 		if (error) {
 			fs_err(sdp, "can't make FS RW: %d\n", error);
diff --git a/fs/gfs2/recovery.c b/fs/gfs2/recovery.c
index 96c345f49273..390ea79d682c 100644
--- a/fs/gfs2/recovery.c
+++ b/fs/gfs2/recovery.c
@@ -364,8 +364,8 @@ void gfs2_recover_func(struct work_struct *work)
 		/* Acquire a shared hold on the freeze lock */
 
 		error = gfs2_glock_nq_init(sdp->sd_freeze_gl, LM_ST_SHARED,
-					   LM_FLAG_NOEXP | LM_FLAG_PRIORITY,
-					   &thaw_gh);
+					   LM_FLAG_NOEXP | LM_FLAG_PRIORITY |
+					   GL_EXACT, &thaw_gh);
 		if (error)
 			goto fail_gunlock_ji;
 
diff --git a/fs/gfs2/super.c b/fs/gfs2/super.c
index 32d8d26126a1..47d0ae158b69 100644
--- a/fs/gfs2/super.c
+++ b/fs/gfs2/super.c
@@ -167,7 +167,8 @@ int gfs2_make_fs_rw(struct gfs2_sbd *sdp)
 	if (error)
 		return error;
 
-	error = gfs2_glock_nq_init(sdp->sd_freeze_gl, LM_ST_SHARED, 0,
+	error = gfs2_glock_nq_init(sdp->sd_freeze_gl, LM_ST_SHARED,
+				   LM_FLAG_NOEXP | GL_EXACT,
 				   &freeze_gh);
 	if (error)
 		goto fail_threads;
@@ -203,7 +204,6 @@ int gfs2_make_fs_rw(struct gfs2_sbd *sdp)
 	return 0;
 
 fail:
-	freeze_gh.gh_flags |= GL_NOCACHE;
 	gfs2_glock_dq_uninit(&freeze_gh);
 fail_threads:
 	if (sdp->sd_quotad_process)
@@ -430,7 +430,7 @@ static int gfs2_lock_fs_check_clean(struct gfs2_sbd *sdp)
 	}
 
 	error = gfs2_glock_nq_init(sdp->sd_freeze_gl, LM_ST_EXCLUSIVE,
-				   GL_NOCACHE, &sdp->sd_freeze_gh);
+				   LM_FLAG_NOEXP, &sdp->sd_freeze_gh);
 	if (error)
 		goto out;
 
@@ -613,13 +613,15 @@ int gfs2_make_fs_ro(struct gfs2_sbd *sdp)
 	    !gfs2_glock_is_locked_by_me(sdp->sd_freeze_gl)) {
 		if (!log_write_allowed) {
 			error = gfs2_glock_nq_init(sdp->sd_freeze_gl,
-						   LM_ST_SHARED, GL_NOCACHE |
-						   LM_FLAG_TRY, &freeze_gh);
+						   LM_ST_SHARED, LM_FLAG_TRY |
+						   LM_FLAG_NOEXP | GL_EXACT,
+						   &freeze_gh);
 			if (error == GLR_TRYFAILED)
 				error = 0;
 		} else {
 			error = gfs2_glock_nq_init(sdp->sd_freeze_gl,
-						   LM_ST_SHARED, GL_NOCACHE,
+						   LM_ST_SHARED,
+						   LM_FLAG_NOEXP | GL_EXACT,
 						   &freeze_gh);
 			if (error && !gfs2_withdrawn(sdp))
 				return error;
@@ -761,8 +763,8 @@ void gfs2_freeze_func(struct work_struct *work)
 	struct super_block *sb = sdp->sd_vfs;
 
 	atomic_inc(&sb->s_active);
-	error = gfs2_glock_nq_init(sdp->sd_freeze_gl, LM_ST_SHARED, 0,
-				   &freeze_gh);
+	error = gfs2_glock_nq_init(sdp->sd_freeze_gl, LM_ST_SHARED,
+				   LM_FLAG_NOEXP | GL_EXACT, &freeze_gh);
 	if (error) {
 		fs_info(sdp, "GFS2: couldn't get freeze lock : %d\n", error);
 		gfs2_assert_withdraw(sdp, 0);
@@ -774,8 +776,6 @@ void gfs2_freeze_func(struct work_struct *work)
 				error);
 			gfs2_assert_withdraw(sdp, 0);
 		}
-		if (!test_bit(SDF_JOURNAL_LIVE, &sdp->sd_flags))
-			freeze_gh.gh_flags |= GL_NOCACHE;
 		gfs2_glock_dq_uninit(&freeze_gh);
 	}
 	deactivate_super(sb);
diff --git a/fs/io_uring.c b/fs/io_uring.c
index e507737f044e..74bc4a04befa 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -1096,6 +1096,8 @@ static inline void io_prep_async_work(struct io_kiocb *req,
 {
 	const struct io_op_def *def = &io_op_defs[req->opcode];
 
+	io_req_init_async(req);
+
 	if (req->flags & REQ_F_ISREG) {
 		if (def->hash_reg_file)
 			io_wq_hash_work(&req->work, file_inode(req->file));
@@ -1104,7 +1106,6 @@ static inline void io_prep_async_work(struct io_kiocb *req,
 			req->work.flags |= IO_WQ_WORK_UNBOUND;
 	}
 
-	io_req_init_async(req);
 	io_req_work_grab_env(req, def);
 
 	*link = io_prep_linked_timeout(req);
@@ -1274,6 +1275,7 @@ static bool io_cqring_overflow_flush(struct io_ring_ctx *ctx, bool force)
 	if (cqe) {
 		clear_bit(0, &ctx->sq_check_overflow);
 		clear_bit(0, &ctx->cq_check_overflow);
+		ctx->rings->sq_flags &= ~IORING_SQ_CQ_OVERFLOW;
 	}
 	spin_unlock_irqrestore(&ctx->completion_lock, flags);
 	io_cqring_ev_posted(ctx);
@@ -1311,6 +1313,7 @@ static void __io_cqring_fill_event(struct io_kiocb *req, long res, long cflags)
 		if (list_empty(&ctx->cq_overflow_list)) {
 			set_bit(0, &ctx->sq_check_overflow);
 			set_bit(0, &ctx->cq_check_overflow);
+			ctx->rings->sq_flags |= IORING_SQ_CQ_OVERFLOW;
 		}
 		req->flags |= REQ_F_OVERFLOW;
 		refcount_inc(&req->refs);
@@ -3551,6 +3554,7 @@ static int io_sendmsg_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
 	if (req->flags & REQ_F_NEED_CLEANUP)
 		return 0;
 
+	io->msg.msg.msg_name = &io->msg.addr;
 	io->msg.iov = io->msg.fast_iov;
 	ret = sendmsg_copy_msghdr(&io->msg.msg, sr->msg, sr->msg_flags,
 					&io->msg.iov);
@@ -3732,6 +3736,7 @@ static int __io_compat_recvmsg_copy_hdr(struct io_kiocb *req,
 
 static int io_recvmsg_copy_hdr(struct io_kiocb *req, struct io_async_ctx *io)
 {
+	io->msg.msg.msg_name = &io->msg.addr;
 	io->msg.iov = io->msg.fast_iov;
 
 #ifdef CONFIG_COMPAT
@@ -3840,10 +3845,16 @@ static int io_recvmsg(struct io_kiocb *req, bool force_nonblock)
 
 		ret = __sys_recvmsg_sock(sock, &kmsg->msg, req->sr_msg.msg,
 						kmsg->uaddr, flags);
-		if (force_nonblock && ret == -EAGAIN)
-			return io_setup_async_msg(req, kmsg);
+		if (force_nonblock && ret == -EAGAIN) {
+			ret = io_setup_async_msg(req, kmsg);
+			if (ret != -EAGAIN)
+				kfree(kbuf);
+			return ret;
+		}
 		if (ret == -ERESTARTSYS)
 			ret = -EINTR;
+		if (kbuf)
+			kfree(kbuf);
 	}
 
 	if (kmsg && kmsg->iov != kmsg->fast_iov)
@@ -4072,6 +4083,29 @@ struct io_poll_table {
 	int error;
 };
 
+static int io_req_task_work_add(struct io_kiocb *req, struct callback_head *cb)
+{
+	struct task_struct *tsk = req->task;
+	struct io_ring_ctx *ctx = req->ctx;
+	int ret, notify = TWA_RESUME;
+
+	/*
+	 * SQPOLL kernel thread doesn't need notification, just a wakeup.
+	 * If we're not using an eventfd, then TWA_RESUME is always fine,
+	 * as we won't have dependencies between request completions for
+	 * other kernel wait conditions.
+	 */
+	if (ctx->flags & IORING_SETUP_SQPOLL)
+		notify = 0;
+	else if (ctx->cq_ev_fd)
+		notify = TWA_SIGNAL;
+
+	ret = task_work_add(tsk, cb, notify);
+	if (!ret)
+		wake_up_process(tsk);
+	return ret;
+}
+
 static int __io_async_wake(struct io_kiocb *req, struct io_poll_iocb *poll,
 			   __poll_t mask, task_work_func_t func)
 {
@@ -4095,13 +4129,13 @@ static int __io_async_wake(struct io_kiocb *req, struct io_poll_iocb *poll,
 	 * of executing it. We can't safely execute it anyway, as we may not
 	 * have the needed state needed for it anyway.
 	 */
-	ret = task_work_add(tsk, &req->task_work, true);
+	ret = io_req_task_work_add(req, &req->task_work);
 	if (unlikely(ret)) {
 		WRITE_ONCE(poll->canceled, true);
 		tsk = io_wq_get_task(req->ctx->io_wq);
-		task_work_add(tsk, &req->task_work, true);
+		task_work_add(tsk, &req->task_work, 0);
+		wake_up_process(tsk);
 	}
-	wake_up_process(tsk);
 	return 1;
 }
 
@@ -6057,9 +6091,9 @@ static int io_sq_thread(void *data)
 			}
 
 			/* Tell userspace we may need a wakeup call */
+			spin_lock_irq(&ctx->completion_lock);
 			ctx->rings->sq_flags |= IORING_SQ_NEED_WAKEUP;
-			/* make sure to read SQ tail after writing flags */
-			smp_mb();
+			spin_unlock_irq(&ctx->completion_lock);
 
 			to_submit = io_sqring_entries(ctx);
 			if (!to_submit || ret == -EBUSY) {
@@ -6077,13 +6111,17 @@ static int io_sq_thread(void *data)
 				schedule();
 				finish_wait(&ctx->sqo_wait, &wait);
 
+				spin_lock_irq(&ctx->completion_lock);
 				ctx->rings->sq_flags &= ~IORING_SQ_NEED_WAKEUP;
+				spin_unlock_irq(&ctx->completion_lock);
 				ret = 0;
 				continue;
 			}
 			finish_wait(&ctx->sqo_wait, &wait);
 
+			spin_lock_irq(&ctx->completion_lock);
 			ctx->rings->sq_flags &= ~IORING_SQ_NEED_WAKEUP;
+			spin_unlock_irq(&ctx->completion_lock);
 		}
 
 		mutex_lock(&ctx->uring_lock);
@@ -6182,15 +6220,23 @@ static int io_cqring_wait(struct io_ring_ctx *ctx, int min_events,
 	do {
 		prepare_to_wait_exclusive(&ctx->wait, &iowq.wq,
 						TASK_INTERRUPTIBLE);
+		/* make sure we run task_work before checking for signals */
 		if (current->task_works)
 			task_work_run();
-		if (io_should_wake(&iowq, false))
-			break;
-		schedule();
 		if (signal_pending(current)) {
+			if (current->jobctl & JOBCTL_TASK_WORK) {
+				spin_lock_irq(&current->sighand->siglock);
+				current->jobctl &= ~JOBCTL_TASK_WORK;
+				recalc_sigpending();
+				spin_unlock_irq(&current->sighand->siglock);
+				continue;
+			}
 			ret = -EINTR;
 			break;
 		}
+		if (io_should_wake(&iowq, false))
+			break;
+		schedule();
 	} while (1);
 	finish_wait(&ctx->wait, &iowq.wq);
 
@@ -6662,6 +6708,7 @@ static int io_sqe_files_register(struct io_ring_ctx *ctx, void __user *arg,
 		for (i = 0; i < nr_tables; i++)
 			kfree(ctx->file_data->table[i].files);
 
+		percpu_ref_exit(&ctx->file_data->refs);
 		kfree(ctx->file_data->table);
 		kfree(ctx->file_data);
 		ctx->file_data = NULL;
@@ -6814,8 +6861,10 @@ static int __io_sqe_files_update(struct io_ring_ctx *ctx,
 			}
 			table->files[index] = file;
 			err = io_sqe_file_register(ctx, file, i);
-			if (err)
+			if (err) {
+				fput(file);
 				break;
+			}
 		}
 		nr_args--;
 		done++;
@@ -7311,9 +7360,6 @@ static void io_ring_ctx_free(struct io_ring_ctx *ctx)
 	io_mem_free(ctx->sq_sqes);
 
 	percpu_ref_exit(&ctx->refs);
-	if (ctx->account_mem)
-		io_unaccount_mem(ctx->user,
-				ring_pages(ctx->sq_entries, ctx->cq_entries));
 	free_uid(ctx->user);
 	put_cred(ctx->creds);
 	kfree(ctx->cancel_hash);
@@ -7398,6 +7444,16 @@ static void io_ring_ctx_wait_and_kill(struct io_ring_ctx *ctx)
 	if (ctx->rings)
 		io_cqring_overflow_flush(ctx, true);
 	idr_for_each(&ctx->personality_idr, io_remove_personalities, ctx);
+
+	/*
+	 * Do this upfront, so we won't have a grace period where the ring
+	 * is closed but resources aren't reaped yet. This can cause
+	 * spurious failure in setting up a new ring.
+	 */
+	if (ctx->account_mem)
+		io_unaccount_mem(ctx->user,
+				ring_pages(ctx->sq_entries, ctx->cq_entries));
+
 	INIT_WORK(&ctx->exit_work, io_ring_exit_work);
 	queue_work(system_wq, &ctx->exit_work);
 }
@@ -7457,6 +7513,7 @@ static void io_uring_cancel_files(struct io_ring_ctx *ctx,
 			if (list_empty(&ctx->cq_overflow_list)) {
 				clear_bit(0, &ctx->sq_check_overflow);
 				clear_bit(0, &ctx->cq_check_overflow);
+				ctx->rings->sq_flags &= ~IORING_SQ_CQ_OVERFLOW;
 			}
 			spin_unlock_irq(&ctx->completion_lock);
 
diff --git a/fs/namespace.c b/fs/namespace.c
index f30ed401cc6d..4a0f600a3328 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -2603,6 +2603,7 @@ static int do_remount(struct path *path, int ms_flags, int sb_flags,
 	if (IS_ERR(fc))
 		return PTR_ERR(fc);
 
+	fc->oldapi = true;
 	err = parse_monolithic_mount_data(fc, data);
 	if (!err) {
 		down_write(&sb->s_umount);
diff --git a/fs/nfs/direct.c b/fs/nfs/direct.c
index 3d113cf8908a..1b79dd5cf661 100644
--- a/fs/nfs/direct.c
+++ b/fs/nfs/direct.c
@@ -267,6 +267,8 @@ static void nfs_direct_complete(struct nfs_direct_req *dreq)
 {
 	struct inode *inode = dreq->inode;
 
+	inode_dio_end(inode);
+
 	if (dreq->iocb) {
 		long res = (long) dreq->error;
 		if (dreq->count != 0) {
@@ -278,10 +280,7 @@ static void nfs_direct_complete(struct nfs_direct_req *dreq)
 
 	complete(&dreq->completion);
 
-	igrab(inode);
 	nfs_direct_req_release(dreq);
-	inode_dio_end(inode);
-	iput(inode);
 }
 
 static void nfs_direct_read_completion(struct nfs_pgio_header *hdr)
@@ -411,10 +410,8 @@ static ssize_t nfs_direct_read_schedule_iovec(struct nfs_direct_req *dreq,
 	 * generic layer handle the completion.
 	 */
 	if (requested_bytes == 0) {
-		igrab(inode);
-		nfs_direct_req_release(dreq);
 		inode_dio_end(inode);
-		iput(inode);
+		nfs_direct_req_release(dreq);
 		return result < 0 ? result : -EIO;
 	}
 
@@ -867,10 +864,8 @@ static ssize_t nfs_direct_write_schedule_iovec(struct nfs_direct_req *dreq,
 	 * generic layer handle the completion.
 	 */
 	if (requested_bytes == 0) {
-		igrab(inode);
-		nfs_direct_req_release(dreq);
 		inode_dio_end(inode);
-		iput(inode);
+		nfs_direct_req_release(dreq);
 		return result < 0 ? result : -EIO;
 	}
 
diff --git a/fs/nfs/file.c b/fs/nfs/file.c
index ccd6c1637b27..f96367a2463e 100644
--- a/fs/nfs/file.c
+++ b/fs/nfs/file.c
@@ -83,7 +83,6 @@ nfs_file_release(struct inode *inode, struct file *filp)
 	dprintk("NFS: release(%pD2)\n", filp);
 
 	nfs_inc_stats(inode, NFSIOS_VFSRELEASE);
-	inode_dio_wait(inode);
 	nfs_file_clear_open_context(filp);
 	return 0;
 }
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index e32717fd1169..2e2dac29a9e9 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -774,6 +774,14 @@ static void nfs4_slot_sequence_acked(struct nfs4_slot *slot,
 	slot->seq_nr_last_acked = seqnr;
 }
 
+static void nfs4_probe_sequence(struct nfs_client *client, const struct cred *cred,
+				struct nfs4_slot *slot)
+{
+	struct rpc_task *task = _nfs41_proc_sequence(client, cred, slot, true);
+	if (!IS_ERR(task))
+		rpc_put_task_async(task);
+}
+
 static int nfs41_sequence_process(struct rpc_task *task,
 		struct nfs4_sequence_res *res)
 {
@@ -790,6 +798,7 @@ static int nfs41_sequence_process(struct rpc_task *task,
 		goto out;
 
 	session = slot->table->session;
+	clp = session->clp;
 
 	trace_nfs4_sequence_done(session, res);
 
@@ -804,7 +813,6 @@ static int nfs41_sequence_process(struct rpc_task *task,
 		nfs4_slot_sequence_acked(slot, slot->seq_nr);
 		/* Update the slot's sequence and clientid lease timer */
 		slot->seq_done = 1;
-		clp = session->clp;
 		do_renew_lease(clp, res->sr_timestamp);
 		/* Check sequence flags */
 		nfs41_handle_sequence_flag_errors(clp, res->sr_status_flags,
@@ -852,10 +860,18 @@ static int nfs41_sequence_process(struct rpc_task *task,
 		/*
 		 * Were one or more calls using this slot interrupted?
 		 * If the server never received the request, then our
-		 * transmitted slot sequence number may be too high.
+		 * transmitted slot sequence number may be too high. However,
+		 * if the server did receive the request then it might
+		 * accidentally give us a reply with a mismatched operation.
+		 * We can sort this out by sending a lone sequence operation
+		 * to the server on the same slot.
 		 */
 		if ((s32)(slot->seq_nr - slot->seq_nr_last_acked) > 1) {
 			slot->seq_nr--;
+			if (task->tk_msg.rpc_proc != &nfs4_procedures[NFSPROC4_CLNT_SEQUENCE]) {
+				nfs4_probe_sequence(clp, task->tk_msg.rpc_cred, slot);
+				res->sr_slot = NULL;
+			}
 			goto retry_nowait;
 		}
 		/*
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index bb3d2c32664a..cce2510b2cca 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -7912,9 +7912,14 @@ nfs4_state_start_net(struct net *net)
 	struct nfsd_net *nn = net_generic(net, nfsd_net_id);
 	int ret;
 
-	ret = nfs4_state_create_net(net);
+	ret = get_nfsdfs(net);
 	if (ret)
 		return ret;
+	ret = nfs4_state_create_net(net);
+	if (ret) {
+		mntput(nn->nfsd_mnt);
+		return ret;
+	}
 	locks_start_grace(net, &nn->nfsd4_manager);
 	nfsd4_client_tracking_init(net);
 	if (nn->track_reclaim_completes && nn->reclaim_str_hashtbl_size == 0)
@@ -7984,6 +7989,7 @@ nfs4_state_shutdown_net(struct net *net)
 
 	nfsd4_client_tracking_exit(net);
 	nfs4_state_destroy_net(net);
+	mntput(nn->nfsd_mnt);
 }
 
 void
diff --git a/fs/nfsd/nfsctl.c b/fs/nfsd/nfsctl.c
index b68e96681522..cd05732f8eaa 100644
--- a/fs/nfsd/nfsctl.c
+++ b/fs/nfsd/nfsctl.c
@@ -1335,6 +1335,7 @@ void nfsd_client_rmdir(struct dentry *dentry)
 	WARN_ON_ONCE(ret);
 	fsnotify_rmdir(dir, dentry);
 	d_delete(dentry);
+	dput(dentry);
 	inode_unlock(dir);
 }
 
@@ -1424,6 +1425,18 @@ static struct file_system_type nfsd_fs_type = {
 };
 MODULE_ALIAS_FS("nfsd");
 
+int get_nfsdfs(struct net *net)
+{
+	struct nfsd_net *nn = net_generic(net, nfsd_net_id);
+	struct vfsmount *mnt;
+
+	mnt =  vfs_kern_mount(&nfsd_fs_type, SB_KERNMOUNT, "nfsd", NULL);
+	if (IS_ERR(mnt))
+		return PTR_ERR(mnt);
+	nn->nfsd_mnt = mnt;
+	return 0;
+}
+
 #ifdef CONFIG_PROC_FS
 static int create_proc_exports_entry(void)
 {
@@ -1451,7 +1464,6 @@ unsigned int nfsd_net_id;
 static __net_init int nfsd_init_net(struct net *net)
 {
 	int retval;
-	struct vfsmount *mnt;
 	struct nfsd_net *nn = net_generic(net, nfsd_net_id);
 
 	retval = nfsd_export_init(net);
@@ -1478,16 +1490,8 @@ static __net_init int nfsd_init_net(struct net *net)
 	init_waitqueue_head(&nn->ntf_wq);
 	seqlock_init(&nn->boot_lock);
 
-	mnt =  vfs_kern_mount(&nfsd_fs_type, SB_KERNMOUNT, "nfsd", NULL);
-	if (IS_ERR(mnt)) {
-		retval = PTR_ERR(mnt);
-		goto out_mount_err;
-	}
-	nn->nfsd_mnt = mnt;
 	return 0;
 
-out_mount_err:
-	nfsd_reply_cache_shutdown(nn);
 out_drc_error:
 	nfsd_idmap_shutdown(net);
 out_idmap_error:
@@ -1500,7 +1504,6 @@ static __net_exit void nfsd_exit_net(struct net *net)
 {
 	struct nfsd_net *nn = net_generic(net, nfsd_net_id);
 
-	mntput(nn->nfsd_mnt);
 	nfsd_reply_cache_shutdown(nn);
 	nfsd_idmap_shutdown(net);
 	nfsd_export_shutdown(net);
diff --git a/fs/nfsd/nfsd.h b/fs/nfsd/nfsd.h
index 36cdd81b6688..57c832d1b30f 100644
--- a/fs/nfsd/nfsd.h
+++ b/fs/nfsd/nfsd.h
@@ -90,6 +90,8 @@ void		nfsd_destroy(struct net *net);
 
 bool		i_am_nfsd(void);
 
+int get_nfsdfs(struct net *);
+
 struct nfsdfs_client {
 	struct kref cl_ref;
 	void (*cl_release)(struct kref *kref);
@@ -100,6 +102,7 @@ struct dentry *nfsd_client_mkdir(struct nfsd_net *nn,
 		struct nfsdfs_client *ncl, u32 id, const struct tree_descr *);
 void nfsd_client_rmdir(struct dentry *dentry);
 
+
 #if defined(CONFIG_NFSD_V2_ACL) || defined(CONFIG_NFSD_V3_ACL)
 #ifdef CONFIG_NFSD_V2_ACL
 extern const struct svc_version nfsd_acl_version2;
diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c
index c3fbab1753ec..d22a056da477 100644
--- a/fs/nfsd/vfs.c
+++ b/fs/nfsd/vfs.c
@@ -1226,6 +1226,9 @@ nfsd_create_locked(struct svc_rqst *rqstp, struct svc_fh *fhp,
 		iap->ia_mode = 0;
 	iap->ia_mode = (iap->ia_mode & S_IALLUGO) | type;
 
+	if (!IS_POSIXACL(dirp))
+		iap->ia_mode &= ~current_umask();
+
 	err = 0;
 	host_err = 0;
 	switch (type) {
@@ -1458,6 +1461,9 @@ do_nfsd_create(struct svc_rqst *rqstp, struct svc_fh *fhp,
 		goto out;
 	}
 
+	if (!IS_POSIXACL(dirp))
+		iap->ia_mode &= ~current_umask();
+
 	host_err = vfs_create(dirp, dchild, iap->ia_mode, true);
 	if (host_err < 0) {
 		fh_drop_write(fhp);
diff --git a/fs/overlayfs/copy_up.c b/fs/overlayfs/copy_up.c
index 79dd052c7dbf..5e0cde85bd6b 100644
--- a/fs/overlayfs/copy_up.c
+++ b/fs/overlayfs/copy_up.c
@@ -895,7 +895,7 @@ static int ovl_copy_up_one(struct dentry *parent, struct dentry *dentry,
 	return err;
 }
 
-int ovl_copy_up_flags(struct dentry *dentry, int flags)
+static int ovl_copy_up_flags(struct dentry *dentry, int flags)
 {
 	int err = 0;
 	const struct cred *old_cred = ovl_override_creds(dentry->d_sb);
diff --git a/fs/overlayfs/export.c b/fs/overlayfs/export.c
index 8f4286450f92..0e696f72cf65 100644
--- a/fs/overlayfs/export.c
+++ b/fs/overlayfs/export.c
@@ -476,7 +476,7 @@ static struct dentry *ovl_lookup_real_inode(struct super_block *sb,
 	if (IS_ERR_OR_NULL(this))
 		return this;
 
-	if (WARN_ON(ovl_dentry_real_at(this, layer->idx) != real)) {
+	if (ovl_dentry_real_at(this, layer->idx) != real) {
 		dput(this);
 		this = ERR_PTR(-EIO);
 	}
diff --git a/fs/overlayfs/file.c b/fs/overlayfs/file.c
index 01820e654a21..0d940e29d62b 100644
--- a/fs/overlayfs/file.c
+++ b/fs/overlayfs/file.c
@@ -33,13 +33,16 @@ static char ovl_whatisit(struct inode *inode, struct inode *realinode)
 		return 'm';
 }
 
+/* No atime modificaton nor notify on underlying */
+#define OVL_OPEN_FLAGS (O_NOATIME | FMODE_NONOTIFY)
+
 static struct file *ovl_open_realfile(const struct file *file,
 				      struct inode *realinode)
 {
 	struct inode *inode = file_inode(file);
 	struct file *realfile;
 	const struct cred *old_cred;
-	int flags = file->f_flags | O_NOATIME | FMODE_NONOTIFY;
+	int flags = file->f_flags | OVL_OPEN_FLAGS;
 	int acc_mode = ACC_MODE(flags);
 	int err;
 
@@ -72,8 +75,7 @@ static int ovl_change_flags(struct file *file, unsigned int flags)
 	struct inode *inode = file_inode(file);
 	int err;
 
-	/* No atime modificaton on underlying */
-	flags |= O_NOATIME | FMODE_NONOTIFY;
+	flags |= OVL_OPEN_FLAGS;
 
 	/* If some flag changed that cannot be changed then something's amiss */
 	if (WARN_ON((file->f_flags ^ flags) & ~OVL_SETFL_MASK))
@@ -126,7 +128,7 @@ static int ovl_real_fdget_meta(const struct file *file, struct fd *real,
 	}
 
 	/* Did the flags change since open? */
-	if (unlikely((file->f_flags ^ real->file->f_flags) & ~O_NOATIME))
+	if (unlikely((file->f_flags ^ real->file->f_flags) & ~OVL_OPEN_FLAGS))
 		return ovl_change_flags(real->file, file->f_flags);
 
 	return 0;
diff --git a/fs/overlayfs/namei.c b/fs/overlayfs/namei.c
index 3566282a9199..f7d4358db637 100644
--- a/fs/overlayfs/namei.c
+++ b/fs/overlayfs/namei.c
@@ -389,7 +389,7 @@ invalid:
 }
 
 static int ovl_check_origin(struct ovl_fs *ofs, struct dentry *upperdentry,
-			    struct ovl_path **stackp, unsigned int *ctrp)
+			    struct ovl_path **stackp)
 {
 	struct ovl_fh *fh = ovl_get_fh(upperdentry, OVL_XATTR_ORIGIN);
 	int err;
@@ -406,10 +406,6 @@ static int ovl_check_origin(struct ovl_fs *ofs, struct dentry *upperdentry,
 		return err;
 	}
 
-	if (WARN_ON(*ctrp))
-		return -EIO;
-
-	*ctrp = 1;
 	return 0;
 }
 
@@ -861,8 +857,6 @@ struct dentry *ovl_lookup(struct inode *dir, struct dentry *dentry,
 			goto out;
 		}
 		if (upperdentry && !d.is_dir) {
-			unsigned int origin_ctr = 0;
-
 			/*
 			 * Lookup copy up origin by decoding origin file handle.
 			 * We may get a disconnected dentry, which is fine,
@@ -873,8 +867,7 @@ struct dentry *ovl_lookup(struct inode *dir, struct dentry *dentry,
 			 * number - it's the same as if we held a reference
 			 * to a dentry in lower layer that was moved under us.
 			 */
-			err = ovl_check_origin(ofs, upperdentry, &origin_path,
-					       &origin_ctr);
+			err = ovl_check_origin(ofs, upperdentry, &origin_path);
 			if (err)
 				goto out_put_upper;
 
@@ -1073,6 +1066,10 @@ struct dentry *ovl_lookup(struct inode *dir, struct dentry *dentry,
 			upperredirect = NULL;
 			goto out_free_oe;
 		}
+		err = ovl_check_metacopy_xattr(upperdentry);
+		if (err < 0)
+			goto out_free_oe;
+		uppermetacopy = err;
 	}
 
 	if (upperdentry || ctr) {
diff --git a/fs/overlayfs/overlayfs.h b/fs/overlayfs/overlayfs.h
index b725c7f15ff4..29bc1ec699e7 100644
--- a/fs/overlayfs/overlayfs.h
+++ b/fs/overlayfs/overlayfs.h
@@ -483,7 +483,6 @@ void ovl_aio_request_cache_destroy(void);
 /* copy_up.c */
 int ovl_copy_up(struct dentry *dentry);
 int ovl_copy_up_with_data(struct dentry *dentry);
-int ovl_copy_up_flags(struct dentry *dentry, int flags);
 int ovl_maybe_copy_up(struct dentry *dentry, int flags);
 int ovl_copy_xattr(struct dentry *old, struct dentry *new);
 int ovl_set_attr(struct dentry *upper, struct kstat *stat);
diff --git a/fs/overlayfs/super.c b/fs/overlayfs/super.c
index 91476bc422f9..4b38141c2985 100644
--- a/fs/overlayfs/super.c
+++ b/fs/overlayfs/super.c
@@ -580,12 +580,19 @@ static int ovl_parse_opt(char *opt, struct ovl_config *config)
 		}
 	}
 
-	/* Workdir is useless in non-upper mount */
-	if (!config->upperdir && config->workdir) {
-		pr_info("option \"workdir=%s\" is useless in a non-upper mount, ignore\n",
-			config->workdir);
-		kfree(config->workdir);
-		config->workdir = NULL;
+	/* Workdir/index are useless in non-upper mount */
+	if (!config->upperdir) {
+		if (config->workdir) {
+			pr_info("option \"workdir=%s\" is useless in a non-upper mount, ignore\n",
+				config->workdir);
+			kfree(config->workdir);
+			config->workdir = NULL;
+		}
+		if (config->index && index_opt) {
+			pr_info("option \"index=on\" is useless in a non-upper mount, ignore\n");
+			index_opt = false;
+		}
+		config->index = false;
 	}
 
 	err = ovl_parse_redirect_mode(config, config->redirect_mode);
@@ -622,11 +629,13 @@ static int ovl_parse_opt(char *opt, struct ovl_config *config)
 
 	/* Resolve nfs_export -> index dependency */
 	if (config->nfs_export && !config->index) {
-		if (nfs_export_opt && index_opt) {
+		if (!config->upperdir && config->redirect_follow) {
+			pr_info("NFS export requires \"redirect_dir=nofollow\" on non-upper mount, falling back to nfs_export=off.\n");
+			config->nfs_export = false;
+		} else if (nfs_export_opt && index_opt) {
 			pr_err("conflicting options: nfs_export=on,index=off\n");
 			return -EINVAL;
-		}
-		if (index_opt) {
+		} else if (index_opt) {
 			/*
 			 * There was an explicit index=off that resulted
 			 * in this conflict.
@@ -1352,8 +1361,15 @@ static int ovl_get_indexdir(struct super_block *sb, struct ovl_fs *ofs,
 		goto out;
 	}
 
+	/* index dir will act also as workdir */
+	iput(ofs->workdir_trap);
+	ofs->workdir_trap = NULL;
+	dput(ofs->workdir);
+	ofs->workdir = NULL;
 	ofs->indexdir = ovl_workdir_create(ofs, OVL_INDEXDIR_NAME, true);
 	if (ofs->indexdir) {
+		ofs->workdir = dget(ofs->indexdir);
+
 		err = ovl_setup_trap(sb, ofs->indexdir, &ofs->indexdir_trap,
 				     "indexdir");
 		if (err)
@@ -1396,6 +1412,18 @@ static bool ovl_lower_uuid_ok(struct ovl_fs *ofs, const uuid_t *uuid)
 	if (!ofs->config.nfs_export && !ovl_upper_mnt(ofs))
 		return true;
 
+	/*
+	 * We allow using single lower with null uuid for index and nfs_export
+	 * for example to support those features with single lower squashfs.
+	 * To avoid regressions in setups of overlay with re-formatted lower
+	 * squashfs, do not allow decoding origin with lower null uuid unless
+	 * user opted-in to one of the new features that require following the
+	 * lower inode of non-dir upper.
+	 */
+	if (!ofs->config.index && !ofs->config.metacopy && !ofs->config.xino &&
+	    uuid_is_null(uuid))
+		return false;
+
 	for (i = 0; i < ofs->numfs; i++) {
 		/*
 		 * We use uuid to associate an overlay lower file handle with a
@@ -1493,14 +1521,23 @@ static int ovl_get_layers(struct super_block *sb, struct ovl_fs *ofs,
 		if (err < 0)
 			goto out;
 
+		/*
+		 * Check if lower root conflicts with this overlay layers before
+		 * checking if it is in-use as upperdir/workdir of "another"
+		 * mount, because we do not bother to check in ovl_is_inuse() if
+		 * the upperdir/workdir is in fact in-use by our
+		 * upperdir/workdir.
+		 */
 		err = ovl_setup_trap(sb, stack[i].dentry, &trap, "lowerdir");
 		if (err)
 			goto out;
 
 		if (ovl_is_inuse(stack[i].dentry)) {
 			err = ovl_report_in_use(ofs, "lowerdir");
-			if (err)
+			if (err) {
+				iput(trap);
 				goto out;
+			}
 		}
 
 		mnt = clone_private_mount(&stack[i]);
@@ -1575,10 +1612,6 @@ static struct ovl_entry *ovl_get_lowerstack(struct super_block *sb,
 	if (!ofs->config.upperdir && numlower == 1) {
 		pr_err("at least 2 lowerdir are needed while upperdir nonexistent\n");
 		return ERR_PTR(-EINVAL);
-	} else if (!ofs->config.upperdir && ofs->config.nfs_export &&
-		   ofs->config.redirect_follow) {
-		pr_warn("NFS export requires \"redirect_dir=nofollow\" on non-upper mount, falling back to nfs_export=off.\n");
-		ofs->config.nfs_export = false;
 	}
 
 	stack = kcalloc(numlower, sizeof(struct path), GFP_KERNEL);
@@ -1842,21 +1875,13 @@ static int ovl_fill_super(struct super_block *sb, void *data, int silent)
 	if (!ovl_upper_mnt(ofs))
 		sb->s_flags |= SB_RDONLY;
 
-	if (!(ovl_force_readonly(ofs)) && ofs->config.index) {
-		/* index dir will act also as workdir */
-		dput(ofs->workdir);
-		ofs->workdir = NULL;
-		iput(ofs->workdir_trap);
-		ofs->workdir_trap = NULL;
-
+	if (!ovl_force_readonly(ofs) && ofs->config.index) {
 		err = ovl_get_indexdir(sb, ofs, oe, &upperpath);
 		if (err)
 			goto out_free_oe;
 
 		/* Force r/o mount with no index dir */
-		if (ofs->indexdir)
-			ofs->workdir = dget(ofs->indexdir);
-		else
+		if (!ofs->indexdir)
 			sb->s_flags |= SB_RDONLY;
 	}
 
diff --git a/fs/proc/proc_sysctl.c b/fs/proc/proc_sysctl.c
index 42c5128c7d1c..6c1166ccdaea 100644
--- a/fs/proc/proc_sysctl.c
+++ b/fs/proc/proc_sysctl.c
@@ -566,8 +566,9 @@ static ssize_t proc_sys_call_handler(struct file *filp, void __user *ubuf,
 		goto out;
 
 	/* don't even try if the size is too large */
-	if (count > KMALLOC_MAX_SIZE)
-		return -ENOMEM;
+	error = -ENOMEM;
+	if (count >= KMALLOC_MAX_SIZE)
+		goto out;
 
 	if (write) {
 		kbuf = memdup_user_nul(ubuf, count);
@@ -576,7 +577,6 @@ static ssize_t proc_sys_call_handler(struct file *filp, void __user *ubuf,
 			goto out;
 		}
 	} else {
-		error = -ENOMEM;
 		kbuf = kzalloc(count, GFP_KERNEL);
 		if (!kbuf)
 			goto out;
diff --git a/fs/read_write.c b/fs/read_write.c
index bbfa9b12b15e..4fb797822567 100644
--- a/fs/read_write.c
+++ b/fs/read_write.c
@@ -419,28 +419,42 @@ static ssize_t new_sync_read(struct file *filp, char __user *buf, size_t len, lo
 	return ret;
 }
 
-ssize_t __vfs_read(struct file *file, char __user *buf, size_t count,
-		   loff_t *pos)
+ssize_t __kernel_read(struct file *file, void *buf, size_t count, loff_t *pos)
 {
+	mm_segment_t old_fs = get_fs();
+	ssize_t ret;
+
+	if (WARN_ON_ONCE(!(file->f_mode & FMODE_READ)))
+		return -EINVAL;
+	if (!(file->f_mode & FMODE_CAN_READ))
+		return -EINVAL;
+
+	if (count > MAX_RW_COUNT)
+		count =  MAX_RW_COUNT;
+	set_fs(KERNEL_DS);
 	if (file->f_op->read)
-		return file->f_op->read(file, buf, count, pos);
+		ret = file->f_op->read(file, (void __user *)buf, count, pos);
 	else if (file->f_op->read_iter)
-		return new_sync_read(file, buf, count, pos);
+		ret = new_sync_read(file, (void __user *)buf, count, pos);
 	else
-		return -EINVAL;
+		ret = -EINVAL;
+	set_fs(old_fs);
+	if (ret > 0) {
+		fsnotify_access(file);
+		add_rchar(current, ret);
+	}
+	inc_syscr(current);
+	return ret;
 }
 
 ssize_t kernel_read(struct file *file, void *buf, size_t count, loff_t *pos)
 {
-	mm_segment_t old_fs;
-	ssize_t result;
+	ssize_t ret;
 
-	old_fs = get_fs();
-	set_fs(KERNEL_DS);
-	/* The cast to a user pointer is valid due to the set_fs() */
-	result = vfs_read(file, (void __user *)buf, count, pos);
-	set_fs(old_fs);
-	return result;
+	ret = rw_verify_area(READ, file, pos, count);
+	if (ret)
+		return ret;
+	return __kernel_read(file, buf, count, pos);
 }
 EXPORT_SYMBOL(kernel_read);
 
@@ -456,17 +470,22 @@ ssize_t vfs_read(struct file *file, char __user *buf, size_t count, loff_t *pos)
 		return -EFAULT;
 
 	ret = rw_verify_area(READ, file, pos, count);
-	if (!ret) {
-		if (count > MAX_RW_COUNT)
-			count =  MAX_RW_COUNT;
-		ret = __vfs_read(file, buf, count, pos);
-		if (ret > 0) {
-			fsnotify_access(file);
-			add_rchar(current, ret);
-		}
-		inc_syscr(current);
-	}
+	if (ret)
+		return ret;
+	if (count > MAX_RW_COUNT)
+		count =  MAX_RW_COUNT;
 
+	if (file->f_op->read)
+		ret = file->f_op->read(file, buf, count, pos);
+	else if (file->f_op->read_iter)
+		ret = new_sync_read(file, buf, count, pos);
+	else
+		ret = -EINVAL;
+	if (ret > 0) {
+		fsnotify_access(file);
+		add_rchar(current, ret);
+	}
+	inc_syscr(current);
 	return ret;
 }
 
@@ -488,23 +507,15 @@ static ssize_t new_sync_write(struct file *filp, const char __user *buf, size_t
 	return ret;
 }
 
-static ssize_t __vfs_write(struct file *file, const char __user *p,
-			   size_t count, loff_t *pos)
-{
-	if (file->f_op->write)
-		return file->f_op->write(file, p, count, pos);
-	else if (file->f_op->write_iter)
-		return new_sync_write(file, p, count, pos);
-	else
-		return -EINVAL;
-}
-
+/* caller is responsible for file_start_write/file_end_write */
 ssize_t __kernel_write(struct file *file, const void *buf, size_t count, loff_t *pos)
 {
 	mm_segment_t old_fs;
 	const char __user *p;
 	ssize_t ret;
 
+	if (WARN_ON_ONCE(!(file->f_mode & FMODE_WRITE)))
+		return -EBADF;
 	if (!(file->f_mode & FMODE_CAN_WRITE))
 		return -EINVAL;
 
@@ -513,7 +524,12 @@ ssize_t __kernel_write(struct file *file, const void *buf, size_t count, loff_t
 	p = (__force const char __user *)buf;
 	if (count > MAX_RW_COUNT)
 		count =  MAX_RW_COUNT;
-	ret = __vfs_write(file, p, count, pos);
+	if (file->f_op->write)
+		ret = file->f_op->write(file, p, count, pos);
+	else if (file->f_op->write_iter)
+		ret = new_sync_write(file, p, count, pos);
+	else
+		ret = -EINVAL;
 	set_fs(old_fs);
 	if (ret > 0) {
 		fsnotify_modify(file);
@@ -522,21 +538,20 @@ ssize_t __kernel_write(struct file *file, const void *buf, size_t count, loff_t
 	inc_syscw(current);
 	return ret;
 }
-EXPORT_SYMBOL(__kernel_write);
 
 ssize_t kernel_write(struct file *file, const void *buf, size_t count,
 			    loff_t *pos)
 {
-	mm_segment_t old_fs;
-	ssize_t res;
+	ssize_t ret;
 
-	old_fs = get_fs();
-	set_fs(KERNEL_DS);
-	/* The cast to a user pointer is valid due to the set_fs() */
-	res = vfs_write(file, (__force const char __user *)buf, count, pos);
-	set_fs(old_fs);
+	ret = rw_verify_area(WRITE, file, pos, count);
+	if (ret)
+		return ret;
 
-	return res;
+	file_start_write(file);
+	ret =  __kernel_write(file, buf, count, pos);
+	file_end_write(file);
+	return ret;
 }
 EXPORT_SYMBOL(kernel_write);
 
@@ -552,19 +567,23 @@ ssize_t vfs_write(struct file *file, const char __user *buf, size_t count, loff_
 		return -EFAULT;
 
 	ret = rw_verify_area(WRITE, file, pos, count);
-	if (!ret) {
-		if (count > MAX_RW_COUNT)
-			count =  MAX_RW_COUNT;
-		file_start_write(file);
-		ret = __vfs_write(file, buf, count, pos);
-		if (ret > 0) {
-			fsnotify_modify(file);
-			add_wchar(current, ret);
-		}
-		inc_syscw(current);
-		file_end_write(file);
+	if (ret)
+		return ret;
+	if (count > MAX_RW_COUNT)
+		count =  MAX_RW_COUNT;
+	file_start_write(file);
+	if (file->f_op->write)
+		ret = file->f_op->write(file, buf, count, pos);
+	else if (file->f_op->write_iter)
+		ret = new_sync_write(file, buf, count, pos);
+	else
+		ret = -EINVAL;
+	if (ret > 0) {
+		fsnotify_modify(file);
+		add_wchar(current, ret);
 	}
-
+	inc_syscw(current);
+	file_end_write(file);
 	return ret;
 }
 
diff --git a/fs/xfs/xfs_log_cil.c b/fs/xfs/xfs_log_cil.c
index b43f0e8f43f2..9ed90368ab31 100644
--- a/fs/xfs/xfs_log_cil.c
+++ b/fs/xfs/xfs_log_cil.c
@@ -671,7 +671,8 @@ xlog_cil_push_work(
 	/*
 	 * Wake up any background push waiters now this context is being pushed.
 	 */
-	wake_up_all(&ctx->push_wait);
+	if (ctx->space_used >= XLOG_CIL_BLOCKING_SPACE_LIMIT(log))
+		wake_up_all(&cil->xc_push_wait);
 
 	/*
 	 * Check if we've anything to push. If there is nothing, then we don't
@@ -743,13 +744,12 @@ xlog_cil_push_work(
 
 	/*
 	 * initialise the new context and attach it to the CIL. Then attach
-	 * the current context to the CIL committing lsit so it can be found
+	 * the current context to the CIL committing list so it can be found
 	 * during log forces to extract the commit lsn of the sequence that
 	 * needs to be forced.
 	 */
 	INIT_LIST_HEAD(&new_ctx->committing);
 	INIT_LIST_HEAD(&new_ctx->busy_extents);
-	init_waitqueue_head(&new_ctx->push_wait);
 	new_ctx->sequence = ctx->sequence + 1;
 	new_ctx->cil = cil;
 	cil->xc_ctx = new_ctx;
@@ -937,7 +937,7 @@ xlog_cil_push_background(
 	if (cil->xc_ctx->space_used >= XLOG_CIL_BLOCKING_SPACE_LIMIT(log)) {
 		trace_xfs_log_cil_wait(log, cil->xc_ctx->ticket);
 		ASSERT(cil->xc_ctx->space_used < log->l_logsize);
-		xlog_wait(&cil->xc_ctx->push_wait, &cil->xc_push_lock);
+		xlog_wait(&cil->xc_push_wait, &cil->xc_push_lock);
 		return;
 	}
 
@@ -1216,12 +1216,12 @@ xlog_cil_init(
 	INIT_LIST_HEAD(&cil->xc_committing);
 	spin_lock_init(&cil->xc_cil_lock);
 	spin_lock_init(&cil->xc_push_lock);
+	init_waitqueue_head(&cil->xc_push_wait);
 	init_rwsem(&cil->xc_ctx_lock);
 	init_waitqueue_head(&cil->xc_commit_wait);
 
 	INIT_LIST_HEAD(&ctx->committing);
 	INIT_LIST_HEAD(&ctx->busy_extents);
-	init_waitqueue_head(&ctx->push_wait);
 	ctx->sequence = 1;
 	ctx->cil = cil;
 	cil->xc_ctx = ctx;
diff --git a/fs/xfs/xfs_log_priv.h b/fs/xfs/xfs_log_priv.h
index ec22c7a3867f..75a62870b63a 100644
--- a/fs/xfs/xfs_log_priv.h
+++ b/fs/xfs/xfs_log_priv.h
@@ -240,7 +240,6 @@ struct xfs_cil_ctx {
 	struct xfs_log_vec	*lv_chain;	/* logvecs being pushed */
 	struct list_head	iclog_entry;
 	struct list_head	committing;	/* ctx committing list */
-	wait_queue_head_t	push_wait;	/* background push throttle */
 	struct work_struct	discard_endio_work;
 };
 
@@ -274,6 +273,7 @@ struct xfs_cil {
 	wait_queue_head_t	xc_commit_wait;
 	xfs_lsn_t		xc_current_sequence;
 	struct work_struct	xc_push_work;
+	wait_queue_head_t	xc_push_wait;	/* background push throttle */
 } ____cacheline_aligned_in_smp;
 
 /*