27 files changed, 359 insertions, 161 deletions

diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index c3f386b7cc0b..c6dc4dd16cf7 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -474,6 +474,7 @@ static noinline int compress_file_range(struct async_chunk *async_chunk)
 	u64 start = async_chunk->start;
 	u64 end = async_chunk->end;
 	u64 actual_end;
+	u64 i_size;
 	int ret = 0;
 	struct page **pages = NULL;
 	unsigned long nr_pages;
@@ -488,7 +489,19 @@ static noinline int compress_file_range(struct async_chunk *async_chunk)
 	inode_should_defrag(BTRFS_I(inode), start, end, end - start + 1,
 			SZ_16K);
 
-	actual_end = min_t(u64, i_size_read(inode), end + 1);
+	/*
+	 * We need to save i_size before now because it could change in between
+	 * us evaluating the size and assigning it.  This is because we lock and
+	 * unlock the page in truncate and fallocate, and then modify the i_size
+	 * later on.
+	 *
+	 * The barriers are to emulate READ_ONCE, remove that once i_size_read
+	 * does that for us.
+	 */
+	barrier();
+	i_size = i_size_read(inode);
+	barrier();
+	actual_end = min_t(u64, i_size, end + 1);
 again:
 	will_compress = 0;
 	nr_pages = (end >> PAGE_SHIFT) - (start >> PAGE_SHIFT) + 1;
diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index 7c145a41decd..23272d9154f3 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -4195,9 +4195,6 @@ static noinline long btrfs_ioctl_start_sync(struct btrfs_root *root,
 	u64 transid;
 	int ret;
 
-	btrfs_warn(root->fs_info,
-	"START_SYNC ioctl is deprecated and will be removed in kernel 5.7");
-
 	trans = btrfs_attach_transaction_barrier(root);
 	if (IS_ERR(trans)) {
 		if (PTR_ERR(trans) != -ENOENT)
@@ -4225,9 +4222,6 @@ static noinline long btrfs_ioctl_wait_sync(struct btrfs_fs_info *fs_info,
 {
 	u64 transid;
 
-	btrfs_warn(fs_info,
-		"WAIT_SYNC ioctl is deprecated and will be removed in kernel 5.7");
-
 	if (argp) {
 		if (copy_from_user(&transid, argp, sizeof(transid)))
 			return -EFAULT;
diff --git a/fs/btrfs/space-info.c b/fs/btrfs/space-info.c
index 98dc092a905e..e8a4b0ebe97f 100644
--- a/fs/btrfs/space-info.c
+++ b/fs/btrfs/space-info.c
@@ -893,6 +893,15 @@ static void wait_reserve_ticket(struct btrfs_fs_info *fs_info,
 	while (ticket->bytes > 0 && ticket->error == 0) {
 		ret = prepare_to_wait_event(&ticket->wait, &wait, TASK_KILLABLE);
 		if (ret) {
+			/*
+			 * Delete us from the list. After we unlock the space
+			 * info, we don't want the async reclaim job to reserve
+			 * space for this ticket. If that would happen, then the
+			 * ticket's task would not known that space was reserved
+			 * despite getting an error, resulting in a space leak
+			 * (bytes_may_use counter of our space_info).
+			 */
+			list_del_init(&ticket->list);
 			ticket->error = -EINTR;
 			break;
 		}
@@ -945,12 +954,24 @@ static int handle_reserve_ticket(struct btrfs_fs_info *fs_info,
 	spin_lock(&space_info->lock);
 	ret = ticket->error;
 	if (ticket->bytes || ticket->error) {
+		/*
+		 * Need to delete here for priority tickets. For regular tickets
+		 * either the async reclaim job deletes the ticket from the list
+		 * or we delete it ourselves at wait_reserve_ticket().
+		 */
 		list_del_init(&ticket->list);
 		if (!ret)
 			ret = -ENOSPC;
 	}
 	spin_unlock(&space_info->lock);
 	ASSERT(list_empty(&ticket->list));
+	/*
+	 * Check that we can't have an error set if the reservation succeeded,
+	 * as that would confuse tasks and lead them to error out without
+	 * releasing reserved space (if an error happens the expectation is that
+	 * space wasn't reserved at all).
+	 */
+	ASSERT(!(ticket->bytes == 0 && ticket->error));
 	return ret;
 }
 
diff --git a/fs/btrfs/tree-checker.c b/fs/btrfs/tree-checker.c
index 43e488f5d063..076d5b8014fb 100644
--- a/fs/btrfs/tree-checker.c
+++ b/fs/btrfs/tree-checker.c
@@ -686,9 +686,7 @@ static void dev_item_err(const struct extent_buffer *eb, int slot,
 static int check_dev_item(struct extent_buffer *leaf,
 			  struct btrfs_key *key, int slot)
 {
-	struct btrfs_fs_info *fs_info = leaf->fs_info;
 	struct btrfs_dev_item *ditem;
-	u64 max_devid = max(BTRFS_MAX_DEVS(fs_info), BTRFS_MAX_DEVS_SYS_CHUNK);
 
 	if (key->objectid != BTRFS_DEV_ITEMS_OBJECTID) {
 		dev_item_err(leaf, slot,
@@ -696,12 +694,6 @@ static int check_dev_item(struct extent_buffer *leaf,
 			     key->objectid, BTRFS_DEV_ITEMS_OBJECTID);
 		return -EUCLEAN;
 	}
-	if (key->offset > max_devid) {
-		dev_item_err(leaf, slot,
-			     "invalid devid: has=%llu expect=[0, %llu]",
-			     key->offset, max_devid);
-		return -EUCLEAN;
-	}
 	ditem = btrfs_item_ptr(leaf, slot, struct btrfs_dev_item);
 	if (btrfs_device_id(leaf, ditem) != key->offset) {
 		dev_item_err(leaf, slot,
diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index bdfe4493e43a..e04409f85063 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -4967,6 +4967,7 @@ static int __btrfs_alloc_chunk(struct btrfs_trans_handle *trans,
 	} else if (type & BTRFS_BLOCK_GROUP_SYSTEM) {
 		max_stripe_size = SZ_32M;
 		max_chunk_size = 2 * max_stripe_size;
+		devs_max = min_t(int, devs_max, BTRFS_MAX_DEVS_SYS_CHUNK);
 	} else {
 		btrfs_err(info, "invalid chunk type 0x%llx requested",
 		       type);
diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c
index d3b9c9d5c1bd..f5a38910a82b 100644
--- a/fs/ceph/caps.c
+++ b/fs/ceph/caps.c
@@ -1058,6 +1058,11 @@ void __ceph_remove_cap(struct ceph_cap *cap, bool queue_release)
 
 	dout("__ceph_remove_cap %p from %p\n", cap, &ci->vfs_inode);
 
+	/* remove from inode's cap rbtree, and clear auth cap */
+	rb_erase(&cap->ci_node, &ci->i_caps);
+	if (ci->i_auth_cap == cap)
+		ci->i_auth_cap = NULL;
+
 	/* remove from session list */
 	spin_lock(&session->s_cap_lock);
 	if (session->s_cap_iterator == cap) {
@@ -1091,11 +1096,6 @@ void __ceph_remove_cap(struct ceph_cap *cap, bool queue_release)
 
 	spin_unlock(&session->s_cap_lock);
 
-	/* remove from inode list */
-	rb_erase(&cap->ci_node, &ci->i_caps);
-	if (ci->i_auth_cap == cap)
-		ci->i_auth_cap = NULL;
-
 	if (removed)
 		ceph_put_cap(mdsc, cap);
 
diff --git a/fs/ceph/dir.c b/fs/ceph/dir.c
index 4ca0b8ff9a72..d17a789fd856 100644
--- a/fs/ceph/dir.c
+++ b/fs/ceph/dir.c
@@ -1553,36 +1553,37 @@ static int ceph_d_revalidate(struct dentry *dentry, unsigned int flags)
 {
 	int valid = 0;
 	struct dentry *parent;
-	struct inode *dir;
+	struct inode *dir, *inode;
 
 	if (flags & LOOKUP_RCU) {
 		parent = READ_ONCE(dentry->d_parent);
 		dir = d_inode_rcu(parent);
 		if (!dir)
 			return -ECHILD;
+		inode = d_inode_rcu(dentry);
 	} else {
 		parent = dget_parent(dentry);
 		dir = d_inode(parent);
+		inode = d_inode(dentry);
 	}
 
 	dout("d_revalidate %p '%pd' inode %p offset %lld\n", dentry,
-	     dentry, d_inode(dentry), ceph_dentry(dentry)->offset);
+	     dentry, inode, ceph_dentry(dentry)->offset);
 
 	/* always trust cached snapped dentries, snapdir dentry */
 	if (ceph_snap(dir) != CEPH_NOSNAP) {
 		dout("d_revalidate %p '%pd' inode %p is SNAPPED\n", dentry,
-		     dentry, d_inode(dentry));
+		     dentry, inode);
 		valid = 1;
-	} else if (d_really_is_positive(dentry) &&
-		   ceph_snap(d_inode(dentry)) == CEPH_SNAPDIR) {
+	} else if (inode && ceph_snap(inode) == CEPH_SNAPDIR) {
 		valid = 1;
 	} else {
 		valid = dentry_lease_is_valid(dentry, flags);
 		if (valid == -ECHILD)
 			return valid;
 		if (valid || dir_lease_is_valid(dir, dentry)) {
-			if (d_really_is_positive(dentry))
-				valid = ceph_is_any_caps(d_inode(dentry));
+			if (inode)
+				valid = ceph_is_any_caps(inode);
 			else
 				valid = 1;
 		}
diff --git a/fs/ceph/file.c b/fs/ceph/file.c
index d277f71abe0b..bd77adb64bfd 100644
--- a/fs/ceph/file.c
+++ b/fs/ceph/file.c
@@ -462,6 +462,9 @@ int ceph_atomic_open(struct inode *dir, struct dentry *dentry,
 		err = ceph_security_init_secctx(dentry, mode, &as_ctx);
 		if (err < 0)
 			goto out_ctx;
+	} else if (!d_in_lookup(dentry)) {
+		/* If it's not being looked up, it's negative */
+		return -ENOENT;
 	}
 
 	/* do the open */
@@ -1956,10 +1959,18 @@ static ssize_t __ceph_copy_file_range(struct file *src_file, loff_t src_off,
 	if (ceph_test_mount_opt(src_fsc, NOCOPYFROM))
 		return -EOPNOTSUPP;
 
+	/*
+	 * Striped file layouts require that we copy partial objects, but the
+	 * OSD copy-from operation only supports full-object copies.  Limit
+	 * this to non-striped file layouts for now.
+	 */
 	if ((src_ci->i_layout.stripe_unit != dst_ci->i_layout.stripe_unit) ||
-	    (src_ci->i_layout.stripe_count != dst_ci->i_layout.stripe_count) ||
-	    (src_ci->i_layout.object_size != dst_ci->i_layout.object_size))
+	    (src_ci->i_layout.stripe_count != 1) ||
+	    (dst_ci->i_layout.stripe_count != 1) ||
+	    (src_ci->i_layout.object_size != dst_ci->i_layout.object_size)) {
+		dout("Invalid src/dst files layout\n");
 		return -EOPNOTSUPP;
+	}
 
 	if (len < src_ci->i_layout.object_size)
 		return -EOPNOTSUPP; /* no remote copy will be done */
diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c
index 9f135624ae47..c07407586ce8 100644
--- a/fs/ceph/inode.c
+++ b/fs/ceph/inode.c
@@ -1434,6 +1434,7 @@ retry_lookup:
 		dout(" final dn %p\n", dn);
 	} else if ((req->r_op == CEPH_MDS_OP_LOOKUPSNAP ||
 		    req->r_op == CEPH_MDS_OP_MKSNAP) &&
+	           test_bit(CEPH_MDS_R_PARENT_LOCKED, &req->r_req_flags) &&
 		   !test_bit(CEPH_MDS_R_ABORTED, &req->r_req_flags)) {
 		struct inode *dir = req->r_parent;
 
diff --git a/fs/ceph/super.c b/fs/ceph/super.c
index edfd643a8205..b47f43fc2d68 100644
--- a/fs/ceph/super.c
+++ b/fs/ceph/super.c
@@ -268,6 +268,7 @@ static int parse_fsopt_token(char *c, void *private)
 		}
 		break;
 	case Opt_fscache_uniq:
+#ifdef CONFIG_CEPH_FSCACHE
 		kfree(fsopt->fscache_uniq);
 		fsopt->fscache_uniq = kstrndup(argstr[0].from,
 					       argstr[0].to-argstr[0].from,
@@ -276,7 +277,10 @@ static int parse_fsopt_token(char *c, void *private)
 			return -ENOMEM;
 		fsopt->flags |= CEPH_MOUNT_OPT_FSCACHE;
 		break;
-		/* misc */
+#else
+		pr_err("fscache support is disabled\n");
+		return -EINVAL;
+#endif
 	case Opt_wsize:
 		if (intval < (int)PAGE_SIZE || intval > CEPH_MAX_WRITE_SIZE)
 			return -EINVAL;
@@ -353,10 +357,15 @@ static int parse_fsopt_token(char *c, void *private)
 		fsopt->flags &= ~CEPH_MOUNT_OPT_INO32;
 		break;
 	case Opt_fscache:
+#ifdef CONFIG_CEPH_FSCACHE
 		fsopt->flags |= CEPH_MOUNT_OPT_FSCACHE;
 		kfree(fsopt->fscache_uniq);
 		fsopt->fscache_uniq = NULL;
 		break;
+#else
+		pr_err("fscache support is disabled\n");
+		return -EINVAL;
+#endif
 	case Opt_nofscache:
 		fsopt->flags &= ~CEPH_MOUNT_OPT_FSCACHE;
 		kfree(fsopt->fscache_uniq);
diff --git a/fs/cifs/smb2ops.c b/fs/cifs/smb2ops.c
index 4c0922596467..cd55af9b7cc5 100644
--- a/fs/cifs/smb2ops.c
+++ b/fs/cifs/smb2ops.c
@@ -4084,6 +4084,7 @@ free_pages:
 
 	kfree(dw->ppages);
 	cifs_small_buf_release(dw->buf);
+	kfree(dw);
 }
 
 
@@ -4157,7 +4158,7 @@ receive_encrypted_read(struct TCP_Server_Info *server, struct mid_q_entry **mid,
 		dw->server = server;
 		dw->ppages = pages;
 		dw->len = len;
-		queue_work(cifsiod_wq, &dw->decrypt);
+		queue_work(decrypt_wq, &dw->decrypt);
 		*num_mids = 0; /* worker thread takes care of finding mid */
 		return -1;
 	}
diff --git a/fs/cifs/smb2pdu.h b/fs/cifs/smb2pdu.h
index ea735d59c36e..0abfde6d0b05 100644
--- a/fs/cifs/smb2pdu.h
+++ b/fs/cifs/smb2pdu.h
@@ -838,6 +838,7 @@ struct create_durable_handle_reconnect_v2 {
 	struct create_context ccontext;
 	__u8   Name[8];
 	struct durable_reconnect_context_v2 dcontext;
+	__u8   Pad[4];
 } __packed;
 
 /* See MS-SMB2 2.2.13.2.5 */
diff --git a/fs/configfs/symlink.c b/fs/configfs/symlink.c
index dc5dbf6a81d7..cb61467478ca 100644
--- a/fs/configfs/symlink.c
+++ b/fs/configfs/symlink.c
@@ -101,7 +101,7 @@ static int create_link(struct config_item *parent_item,
 	}
 	target_sd->s_links++;
 	spin_unlock(&configfs_dirent_lock);
-	ret = configfs_get_target_path(item, item, body);
+	ret = configfs_get_target_path(parent_item, item, body);
 	if (!ret)
 		ret = configfs_create_link(target_sd, parent_item->ci_dentry,
 					   dentry, body);
diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c
index 8461a6322039..335607b8c5c0 100644
--- a/fs/fs-writeback.c
+++ b/fs/fs-writeback.c
@@ -576,10 +576,13 @@ void wbc_attach_and_unlock_inode(struct writeback_control *wbc,
 	spin_unlock(&inode->i_lock);
 
 	/*
-	 * A dying wb indicates that the memcg-blkcg mapping has changed
-	 * and a new wb is already serving the memcg.  Switch immediately.
+	 * A dying wb indicates that either the blkcg associated with the
+	 * memcg changed or the associated memcg is dying.  In the first
+	 * case, a replacement wb should already be available and we should
+	 * refresh the wb immediately.  In the second case, trying to
+	 * refresh will keep failing.
 	 */
-	if (unlikely(wb_dying(wbc->wb)))
+	if (unlikely(wb_dying(wbc->wb) && !css_is_dying(wbc->wb->memcg_css)))
 		inode_switch_wbs(inode, wbc->wb_id);
 }
 EXPORT_SYMBOL_GPL(wbc_attach_and_unlock_inode);
diff --git a/fs/fuse/Makefile b/fs/fuse/Makefile
index 6419a2b3510d..3e8cebfb59b7 100644
--- a/fs/fuse/Makefile
+++ b/fs/fuse/Makefile
@@ -5,6 +5,7 @@
 
 obj-$(CONFIG_FUSE_FS) += fuse.o
 obj-$(CONFIG_CUSE) += cuse.o
-obj-$(CONFIG_VIRTIO_FS) += virtio_fs.o
+obj-$(CONFIG_VIRTIO_FS) += virtiofs.o
 
 fuse-objs := dev.o dir.o file.o inode.o control.o xattr.o acl.o readdir.o
+virtiofs-y += virtio_fs.o
diff --git a/fs/fuse/dev.c b/fs/fuse/dev.c
index dadd617d826c..ed1abc9e33cf 100644
--- a/fs/fuse/dev.c
+++ b/fs/fuse/dev.c
@@ -276,10 +276,12 @@ static void flush_bg_queue(struct fuse_conn *fc)
 void fuse_request_end(struct fuse_conn *fc, struct fuse_req *req)
 {
 	struct fuse_iqueue *fiq = &fc->iq;
-	bool async = req->args->end;
+	bool async;
 
 	if (test_and_set_bit(FR_FINISHED, &req->flags))
 		goto put_request;
+
+	async = req->args->end;
 	/*
 	 * test_and_set_bit() implies smp_mb() between bit
 	 * changing and below intr_entry check. Pairs with
diff --git a/fs/fuse/dir.c b/fs/fuse/dir.c
index d572c900bb0f..54d638f9ba1c 100644
--- a/fs/fuse/dir.c
+++ b/fs/fuse/dir.c
@@ -405,7 +405,8 @@ static struct dentry *fuse_lookup(struct inode *dir, struct dentry *entry,
 	else
 		fuse_invalidate_entry_cache(entry);
 
-	fuse_advise_use_readdirplus(dir);
+	if (inode)
+		fuse_advise_use_readdirplus(dir);
 	return newent;
 
  out_iput:
@@ -1521,6 +1522,19 @@ int fuse_do_setattr(struct dentry *dentry, struct iattr *attr,
 		is_truncate = true;
 	}
 
+	/* Flush dirty data/metadata before non-truncate SETATTR */
+	if (is_wb && S_ISREG(inode->i_mode) &&
+	    attr->ia_valid &
+			(ATTR_MODE | ATTR_UID | ATTR_GID | ATTR_MTIME_SET |
+			 ATTR_TIMES_SET)) {
+		err = write_inode_now(inode, true);
+		if (err)
+			return err;
+
+		fuse_set_nowrite(inode);
+		fuse_release_nowrite(inode);
+	}
+
 	if (is_truncate) {
 		fuse_set_nowrite(inode);
 		set_bit(FUSE_I_SIZE_UNSTABLE, &fi->state);
diff --git a/fs/fuse/file.c b/fs/fuse/file.c
index 0f0225686aee..db48a5cf8620 100644
--- a/fs/fuse/file.c
+++ b/fs/fuse/file.c
@@ -217,7 +217,7 @@ int fuse_open_common(struct inode *inode, struct file *file, bool isdir)
 {
 	struct fuse_conn *fc = get_fuse_conn(inode);
 	int err;
-	bool lock_inode = (file->f_flags & O_TRUNC) &&
+	bool is_wb_truncate = (file->f_flags & O_TRUNC) &&
 			  fc->atomic_o_trunc &&
 			  fc->writeback_cache;
 
@@ -225,16 +225,20 @@ int fuse_open_common(struct inode *inode, struct file *file, bool isdir)
 	if (err)
 		return err;
 
-	if (lock_inode)
+	if (is_wb_truncate) {
 		inode_lock(inode);
+		fuse_set_nowrite(inode);
+	}
 
 	err = fuse_do_open(fc, get_node_id(inode), file, isdir);
 
 	if (!err)
 		fuse_finish_open(inode, file);
 
-	if (lock_inode)
+	if (is_wb_truncate) {
+		fuse_release_nowrite(inode);
 		inode_unlock(inode);
+	}
 
 	return err;
 }
@@ -1997,7 +2001,7 @@ static int fuse_writepages_fill(struct page *page,
 
 	if (!data->ff) {
 		err = -EIO;
-		data->ff = fuse_write_file_get(fc, get_fuse_inode(inode));
+		data->ff = fuse_write_file_get(fc, fi);
 		if (!data->ff)
 			goto out_unlock;
 	}
@@ -2042,8 +2046,6 @@ static int fuse_writepages_fill(struct page *page,
 	 * under writeback, so we can release the page lock.
 	 */
 	if (data->wpa == NULL) {
-		struct fuse_inode *fi = get_fuse_inode(inode);
-
 		err = -ENOMEM;
 		wpa = fuse_writepage_args_alloc();
 		if (!wpa) {
diff --git a/fs/fuse/fuse_i.h b/fs/fuse/fuse_i.h
index 956aeaf961ae..d148188cfca4 100644
--- a/fs/fuse/fuse_i.h
+++ b/fs/fuse/fuse_i.h
@@ -479,6 +479,7 @@ struct fuse_fs_context {
 	bool destroy:1;
 	bool no_control:1;
 	bool no_force_umount:1;
+	bool no_mount_options:1;
 	unsigned int max_read;
 	unsigned int blksize;
 	const char *subtype;
@@ -713,6 +714,9 @@ struct fuse_conn {
 	/** Do not allow MNT_FORCE umount */
 	unsigned int no_force_umount:1;
 
+	/* Do not show mount options */
+	unsigned int no_mount_options:1;
+
 	/** The number of requests waiting for completion */
 	atomic_t num_waiting;
 
diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c
index e040e2a2b621..16aec32f7f3d 100644
--- a/fs/fuse/inode.c
+++ b/fs/fuse/inode.c
@@ -558,6 +558,9 @@ static int fuse_show_options(struct seq_file *m, struct dentry *root)
 	struct super_block *sb = root->d_sb;
 	struct fuse_conn *fc = get_fuse_conn_super(sb);
 
+	if (fc->no_mount_options)
+		return 0;
+
 	seq_printf(m, ",user_id=%u", from_kuid_munged(fc->user_ns, fc->user_id));
 	seq_printf(m, ",group_id=%u", from_kgid_munged(fc->user_ns, fc->group_id));
 	if (fc->default_permissions)
@@ -1180,6 +1183,7 @@ int fuse_fill_super_common(struct super_block *sb, struct fuse_fs_context *ctx)
 	fc->destroy = ctx->destroy;
 	fc->no_control = ctx->no_control;
 	fc->no_force_umount = ctx->no_force_umount;
+	fc->no_mount_options = ctx->no_mount_options;
 
 	err = -ENOMEM;
 	root = fuse_get_root_inode(sb, ctx->rootmode);
diff --git a/fs/fuse/virtio_fs.c b/fs/fuse/virtio_fs.c
index 6af3f131e468..a5c86048b96e 100644
--- a/fs/fuse/virtio_fs.c
+++ b/fs/fuse/virtio_fs.c
@@ -30,6 +30,7 @@ struct virtio_fs_vq {
 	struct virtqueue *vq;     /* protected by ->lock */
 	struct work_struct done_work;
 	struct list_head queued_reqs;
+	struct list_head end_reqs;	/* End these requests */
 	struct delayed_work dispatch_work;
 	struct fuse_dev *fud;
 	bool connected;
@@ -54,6 +55,9 @@ struct virtio_fs_forget {
 	struct list_head list;
 };
 
+static int virtio_fs_enqueue_req(struct virtio_fs_vq *fsvq,
+				 struct fuse_req *req, bool in_flight);
+
 static inline struct virtio_fs_vq *vq_to_fsvq(struct virtqueue *vq)
 {
 	struct virtio_fs *fs = vq->vdev->priv;
@@ -66,6 +70,19 @@ static inline struct fuse_pqueue *vq_to_fpq(struct virtqueue *vq)
 	return &vq_to_fsvq(vq)->fud->pq;
 }
 
+/* Should be called with fsvq->lock held. */
+static inline void inc_in_flight_req(struct virtio_fs_vq *fsvq)
+{
+	fsvq->in_flight++;
+}
+
+/* Should be called with fsvq->lock held. */
+static inline void dec_in_flight_req(struct virtio_fs_vq *fsvq)
+{
+	WARN_ON(fsvq->in_flight <= 0);
+	fsvq->in_flight--;
+}
+
 static void release_virtio_fs_obj(struct kref *ref)
 {
 	struct virtio_fs *vfs = container_of(ref, struct virtio_fs, refcount);
@@ -109,22 +126,6 @@ static void virtio_fs_drain_queue(struct virtio_fs_vq *fsvq)
 	flush_delayed_work(&fsvq->dispatch_work);
 }
 
-static inline void drain_hiprio_queued_reqs(struct virtio_fs_vq *fsvq)
-{
-	struct virtio_fs_forget *forget;
-
-	spin_lock(&fsvq->lock);
-	while (1) {
-		forget = list_first_entry_or_null(&fsvq->queued_reqs,
-						struct virtio_fs_forget, list);
-		if (!forget)
-			break;
-		list_del(&forget->list);
-		kfree(forget);
-	}
-	spin_unlock(&fsvq->lock);
-}
-
 static void virtio_fs_drain_all_queues(struct virtio_fs *fs)
 {
 	struct virtio_fs_vq *fsvq;
@@ -132,9 +133,6 @@ static void virtio_fs_drain_all_queues(struct virtio_fs *fs)
 
 	for (i = 0; i < fs->nvqs; i++) {
 		fsvq = &fs->vqs[i];
-		if (i == VQ_HIPRIO)
-			drain_hiprio_queued_reqs(fsvq);
-
 		virtio_fs_drain_queue(fsvq);
 	}
 }
@@ -253,14 +251,66 @@ static void virtio_fs_hiprio_done_work(struct work_struct *work)
 
 		while ((req = virtqueue_get_buf(vq, &len)) != NULL) {
 			kfree(req);
-			fsvq->in_flight--;
+			dec_in_flight_req(fsvq);
 		}
 	} while (!virtqueue_enable_cb(vq) && likely(!virtqueue_is_broken(vq)));
 	spin_unlock(&fsvq->lock);
 }
 
-static void virtio_fs_dummy_dispatch_work(struct work_struct *work)
+static void virtio_fs_request_dispatch_work(struct work_struct *work)
 {
+	struct fuse_req *req;
+	struct virtio_fs_vq *fsvq = container_of(work, struct virtio_fs_vq,
+						 dispatch_work.work);
+	struct fuse_conn *fc = fsvq->fud->fc;
+	int ret;
+
+	pr_debug("virtio-fs: worker %s called.\n", __func__);
+	while (1) {
+		spin_lock(&fsvq->lock);
+		req = list_first_entry_or_null(&fsvq->end_reqs, struct fuse_req,
+					       list);
+		if (!req) {
+			spin_unlock(&fsvq->lock);
+			break;
+		}
+
+		list_del_init(&req->list);
+		spin_unlock(&fsvq->lock);
+		fuse_request_end(fc, req);
+	}
+
+	/* Dispatch pending requests */
+	while (1) {
+		spin_lock(&fsvq->lock);
+		req = list_first_entry_or_null(&fsvq->queued_reqs,
+					       struct fuse_req, list);
+		if (!req) {
+			spin_unlock(&fsvq->lock);
+			return;
+		}
+		list_del_init(&req->list);
+		spin_unlock(&fsvq->lock);
+
+		ret = virtio_fs_enqueue_req(fsvq, req, true);
+		if (ret < 0) {
+			if (ret == -ENOMEM || ret == -ENOSPC) {
+				spin_lock(&fsvq->lock);
+				list_add_tail(&req->list, &fsvq->queued_reqs);
+				schedule_delayed_work(&fsvq->dispatch_work,
+						      msecs_to_jiffies(1));
+				spin_unlock(&fsvq->lock);
+				return;
+			}
+			req->out.h.error = ret;
+			spin_lock(&fsvq->lock);
+			dec_in_flight_req(fsvq);
+			spin_unlock(&fsvq->lock);
+			pr_err("virtio-fs: virtio_fs_enqueue_req() failed %d\n",
+			       ret);
+			fuse_request_end(fc, req);
+		}
+	}
 }
 
 static void virtio_fs_hiprio_dispatch_work(struct work_struct *work)
@@ -286,6 +336,7 @@ static void virtio_fs_hiprio_dispatch_work(struct work_struct *work)
 
 		list_del(&forget->list);
 		if (!fsvq->connected) {
+			dec_in_flight_req(fsvq);
 			spin_unlock(&fsvq->lock);
 			kfree(forget);
 			continue;
@@ -307,13 +358,13 @@ static void virtio_fs_hiprio_dispatch_work(struct work_struct *work)
 			} else {
 				pr_debug("virtio-fs: Could not queue FORGET: err=%d. Dropping it.\n",
 					 ret);
+				dec_in_flight_req(fsvq);
 				kfree(forget);
 			}
 			spin_unlock(&fsvq->lock);
 			return;
 		}
 
-		fsvq->in_flight++;
 		notify = virtqueue_kick_prepare(vq);
 		spin_unlock(&fsvq->lock);
 
@@ -452,7 +503,7 @@ static void virtio_fs_requests_done_work(struct work_struct *work)
 
 		fuse_request_end(fc, req);
 		spin_lock(&fsvq->lock);
-		fsvq->in_flight--;
+		dec_in_flight_req(fsvq);
 		spin_unlock(&fsvq->lock);
 	}
 }
@@ -502,6 +553,7 @@ static int virtio_fs_setup_vqs(struct virtio_device *vdev,
 	names[VQ_HIPRIO] = fs->vqs[VQ_HIPRIO].name;
 	INIT_WORK(&fs->vqs[VQ_HIPRIO].done_work, virtio_fs_hiprio_done_work);
 	INIT_LIST_HEAD(&fs->vqs[VQ_HIPRIO].queued_reqs);
+	INIT_LIST_HEAD(&fs->vqs[VQ_HIPRIO].end_reqs);
 	INIT_DELAYED_WORK(&fs->vqs[VQ_HIPRIO].dispatch_work,
 			virtio_fs_hiprio_dispatch_work);
 	spin_lock_init(&fs->vqs[VQ_HIPRIO].lock);
@@ -511,8 +563,9 @@ static int virtio_fs_setup_vqs(struct virtio_device *vdev,
 		spin_lock_init(&fs->vqs[i].lock);
 		INIT_WORK(&fs->vqs[i].done_work, virtio_fs_requests_done_work);
 		INIT_DELAYED_WORK(&fs->vqs[i].dispatch_work,
-					virtio_fs_dummy_dispatch_work);
+				  virtio_fs_request_dispatch_work);
 		INIT_LIST_HEAD(&fs->vqs[i].queued_reqs);
+		INIT_LIST_HEAD(&fs->vqs[i].end_reqs);
 		snprintf(fs->vqs[i].name, sizeof(fs->vqs[i].name),
 			 "requests.%u", i - VQ_REQUEST);
 		callbacks[i] = virtio_fs_vq_done;
@@ -708,6 +761,7 @@ __releases(fiq->lock)
 			list_add_tail(&forget->list, &fsvq->queued_reqs);
 			schedule_delayed_work(&fsvq->dispatch_work,
 					msecs_to_jiffies(1));
+			inc_in_flight_req(fsvq);
 		} else {
 			pr_debug("virtio-fs: Could not queue FORGET: err=%d. Dropping it.\n",
 				 ret);
@@ -717,7 +771,7 @@ __releases(fiq->lock)
 		goto out;
 	}
 
-	fsvq->in_flight++;
+	inc_in_flight_req(fsvq);
 	notify = virtqueue_kick_prepare(vq);
 
 	spin_unlock(&fsvq->lock);
@@ -819,7 +873,7 @@ static unsigned int sg_init_fuse_args(struct scatterlist *sg,
 
 /* Add a request to a virtqueue and kick the device */
 static int virtio_fs_enqueue_req(struct virtio_fs_vq *fsvq,
-				 struct fuse_req *req)
+				 struct fuse_req *req, bool in_flight)
 {
 	/* requests need at least 4 elements */
 	struct scatterlist *stack_sgs[6];
@@ -835,6 +889,7 @@ static int virtio_fs_enqueue_req(struct virtio_fs_vq *fsvq,
 	unsigned int i;
 	int ret;
 	bool notify;
+	struct fuse_pqueue *fpq;
 
 	/* Does the sglist fit on the stack? */
 	total_sgs = sg_count_fuse_req(req);
@@ -889,7 +944,17 @@ static int virtio_fs_enqueue_req(struct virtio_fs_vq *fsvq,
 		goto out;
 	}
 
-	fsvq->in_flight++;
+	/* Request successfully sent. */
+	fpq = &fsvq->fud->pq;
+	spin_lock(&fpq->lock);
+	list_add_tail(&req->list, fpq->processing);
+	spin_unlock(&fpq->lock);
+	set_bit(FR_SENT, &req->flags);
+	/* matches barrier in request_wait_answer() */
+	smp_mb__after_atomic();
+
+	if (!in_flight)
+		inc_in_flight_req(fsvq);
 	notify = virtqueue_kick_prepare(vq);
 
 	spin_unlock(&fsvq->lock);
@@ -915,9 +980,8 @@ __releases(fiq->lock)
 {
 	unsigned int queue_id = VQ_REQUEST; /* TODO multiqueue */
 	struct virtio_fs *fs;
-	struct fuse_conn *fc;
 	struct fuse_req *req;
-	struct fuse_pqueue *fpq;
+	struct virtio_fs_vq *fsvq;
 	int ret;
 
 	WARN_ON(list_empty(&fiq->pending));
@@ -928,44 +992,36 @@ __releases(fiq->lock)
 	spin_unlock(&fiq->lock);
 
 	fs = fiq->priv;
-	fc = fs->vqs[queue_id].fud->fc;
 
 	pr_debug("%s: opcode %u unique %#llx nodeid %#llx in.len %u out.len %u\n",
 		  __func__, req->in.h.opcode, req->in.h.unique,
 		 req->in.h.nodeid, req->in.h.len,
 		 fuse_len_args(req->args->out_numargs, req->args->out_args));
 
-	fpq = &fs->vqs[queue_id].fud->pq;
-	spin_lock(&fpq->lock);
-	if (!fpq->connected) {
-		spin_unlock(&fpq->lock);
-		req->out.h.error = -ENODEV;
-		pr_err("virtio-fs: %s disconnected\n", __func__);
-		fuse_request_end(fc, req);
-		return;
-	}
-	list_add_tail(&req->list, fpq->processing);
-	spin_unlock(&fpq->lock);
-	set_bit(FR_SENT, &req->flags);
-	/* matches barrier in request_wait_answer() */
-	smp_mb__after_atomic();
-
-retry:
-	ret = virtio_fs_enqueue_req(&fs->vqs[queue_id], req);
+	fsvq = &fs->vqs[queue_id];
+	ret = virtio_fs_enqueue_req(fsvq, req, false);
 	if (ret < 0) {
 		if (ret == -ENOMEM || ret == -ENOSPC) {
-			/* Virtqueue full. Retry submission */
-			/* TODO use completion instead of timeout */
-			usleep_range(20, 30);
-			goto retry;
+			/*
+			 * Virtqueue full. Retry submission from worker
+			 * context as we might be holding fc->bg_lock.
+			 */
+			spin_lock(&fsvq->lock);
+			list_add_tail(&req->list, &fsvq->queued_reqs);
+			inc_in_flight_req(fsvq);
+			schedule_delayed_work(&fsvq->dispatch_work,
+						msecs_to_jiffies(1));
+			spin_unlock(&fsvq->lock);
+			return;
 		}
 		req->out.h.error = ret;
 		pr_err("virtio-fs: virtio_fs_enqueue_req() failed %d\n", ret);
-		spin_lock(&fpq->lock);
-		clear_bit(FR_SENT, &req->flags);
-		list_del_init(&req->list);
-		spin_unlock(&fpq->lock);
-		fuse_request_end(fc, req);
+
+		/* Can't end request in submission context. Use a worker */
+		spin_lock(&fsvq->lock);
+		list_add_tail(&req->list, &fsvq->end_reqs);
+		schedule_delayed_work(&fsvq->dispatch_work, 0);
+		spin_unlock(&fsvq->lock);
 		return;
 	}
 }
@@ -992,6 +1048,7 @@ static int virtio_fs_fill_super(struct super_block *sb)
 		.destroy = true,
 		.no_control = true,
 		.no_force_umount = true,
+		.no_mount_options = true,
 	};
 
 	mutex_lock(&virtio_fs_mutex);
diff --git a/fs/gfs2/ops_fstype.c b/fs/gfs2/ops_fstype.c
index dc61af2c4d5e..18daf494abab 100644
--- a/fs/gfs2/ops_fstype.c
+++ b/fs/gfs2/ops_fstype.c
@@ -1540,17 +1540,23 @@ static int gfs2_init_fs_context(struct fs_context *fc)
 {
 	struct gfs2_args *args;
 
-	args = kzalloc(sizeof(*args), GFP_KERNEL);
+	args = kmalloc(sizeof(*args), GFP_KERNEL);
 	if (args == NULL)
 		return -ENOMEM;
 
-	args->ar_quota = GFS2_QUOTA_DEFAULT;
-	args->ar_data = GFS2_DATA_DEFAULT;
-	args->ar_commit = 30;
-	args->ar_statfs_quantum = 30;
-	args->ar_quota_quantum = 60;
-	args->ar_errors = GFS2_ERRORS_DEFAULT;
+	if (fc->purpose == FS_CONTEXT_FOR_RECONFIGURE) {
+		struct gfs2_sbd *sdp = fc->root->d_sb->s_fs_info;
 
+		*args = sdp->sd_args;
+	} else {
+		memset(args, 0, sizeof(*args));
+		args->ar_quota = GFS2_QUOTA_DEFAULT;
+		args->ar_data = GFS2_DATA_DEFAULT;
+		args->ar_commit = 30;
+		args->ar_statfs_quantum = 30;
+		args->ar_quota_quantum = 60;
+		args->ar_errors = GFS2_ERRORS_DEFAULT;
+	}
 	fc->fs_private = args;
 	fc->ops = &gfs2_context_ops;
 	return 0;
diff --git a/fs/io_uring.c b/fs/io_uring.c
index a30c4f622cb3..f9a38998f2fc 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -1124,6 +1124,7 @@ static int io_prep_rw(struct io_kiocb *req, const struct sqe_submit *s,
 
 		kiocb->ki_flags |= IOCB_HIPRI;
 		kiocb->ki_complete = io_complete_rw_iopoll;
+		req->result = 0;
 	} else {
 		if (kiocb->ki_flags & IOCB_HIPRI)
 			return -EINVAL;
@@ -2413,6 +2414,7 @@ static int io_queue_link_head(struct io_ring_ctx *ctx, struct io_kiocb *req,
 	if (ret) {
 		if (ret != -EIOCBQUEUED) {
 			io_free_req(req);
+			__io_free_req(shadow);
 			io_cqring_add_event(ctx, s->sqe->user_data, ret);
 			return 0;
 		}
@@ -3828,10 +3830,6 @@ static int io_uring_create(unsigned entries, struct io_uring_params *p)
 	if (ret)
 		goto err;
 
-	ret = io_uring_get_fd(ctx);
-	if (ret < 0)
-		goto err;
-
 	memset(&p->sq_off, 0, sizeof(p->sq_off));
 	p->sq_off.head = offsetof(struct io_rings, sq.head);
 	p->sq_off.tail = offsetof(struct io_rings, sq.tail);
@@ -3849,6 +3847,14 @@ static int io_uring_create(unsigned entries, struct io_uring_params *p)
 	p->cq_off.overflow = offsetof(struct io_rings, cq_overflow);
 	p->cq_off.cqes = offsetof(struct io_rings, cqes);
 
+	/*
+	 * Install ring fd as the very last thing, so we don't risk someone
+	 * having closed it before we finish setup
+	 */
+	ret = io_uring_get_fd(ctx);
+	if (ret < 0)
+		goto err;
+
 	p->features = IORING_FEAT_SINGLE_MMAP;
 	return ret;
 err:
diff --git a/fs/nfs/delegation.c b/fs/nfs/delegation.c
index 071b90a45933..af549d70ec50 100644
--- a/fs/nfs/delegation.c
+++ b/fs/nfs/delegation.c
@@ -53,6 +53,16 @@ nfs4_is_valid_delegation(const struct nfs_delegation *delegation,
 	return false;
 }
 
+struct nfs_delegation *nfs4_get_valid_delegation(const struct inode *inode)
+{
+	struct nfs_delegation *delegation;
+
+	delegation = rcu_dereference(NFS_I(inode)->delegation);
+	if (nfs4_is_valid_delegation(delegation, 0))
+		return delegation;
+	return NULL;
+}
+
 static int
 nfs4_do_check_delegation(struct inode *inode, fmode_t flags, bool mark)
 {
@@ -1181,7 +1191,7 @@ bool nfs4_refresh_delegation_stateid(nfs4_stateid *dst, struct inode *inode)
 	if (delegation != NULL &&
 	    nfs4_stateid_match_other(dst, &delegation->stateid)) {
 		dst->seqid = delegation->stateid.seqid;
-		return ret;
+		ret = true;
 	}
 	rcu_read_unlock();
 out:
diff --git a/fs/nfs/delegation.h b/fs/nfs/delegation.h
index 9eb87ae4c982..8b14d441e699 100644
--- a/fs/nfs/delegation.h
+++ b/fs/nfs/delegation.h
@@ -68,6 +68,7 @@ int nfs4_lock_delegation_recall(struct file_lock *fl, struct nfs4_state *state,
 bool nfs4_copy_delegation_stateid(struct inode *inode, fmode_t flags, nfs4_stateid *dst, const struct cred **cred);
 bool nfs4_refresh_delegation_stateid(nfs4_stateid *dst, struct inode *inode);
 
+struct nfs_delegation *nfs4_get_valid_delegation(const struct inode *inode);
 void nfs_mark_delegation_referenced(struct nfs_delegation *delegation);
 int nfs4_have_delegation(struct inode *inode, fmode_t flags);
 int nfs4_check_delegation(struct inode *inode, fmode_t flags);
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index ab8ca20fd579..caacf5e7f5e1 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -1440,8 +1440,6 @@ static int can_open_delegated(struct nfs_delegation *delegation, fmode_t fmode,
 		return 0;
 	if ((delegation->type & fmode) != fmode)
 		return 0;
-	if (test_bit(NFS_DELEGATION_RETURNING, &delegation->flags))
-		return 0;
 	switch (claim) {
 	case NFS4_OPEN_CLAIM_NULL:
 	case NFS4_OPEN_CLAIM_FH:
@@ -1810,7 +1808,6 @@ static void nfs4_return_incompatible_delegation(struct inode *inode, fmode_t fmo
 static struct nfs4_state *nfs4_try_open_cached(struct nfs4_opendata *opendata)
 {
 	struct nfs4_state *state = opendata->state;
-	struct nfs_inode *nfsi = NFS_I(state->inode);
 	struct nfs_delegation *delegation;
 	int open_mode = opendata->o_arg.open_flags;
 	fmode_t fmode = opendata->o_arg.fmode;
@@ -1827,7 +1824,7 @@ static struct nfs4_state *nfs4_try_open_cached(struct nfs4_opendata *opendata)
 		}
 		spin_unlock(&state->owner->so_lock);
 		rcu_read_lock();
-		delegation = rcu_dereference(nfsi->delegation);
+		delegation = nfs4_get_valid_delegation(state->inode);
 		if (!can_open_delegated(delegation, fmode, claim)) {
 			rcu_read_unlock();
 			break;
@@ -2371,7 +2368,7 @@ static void nfs4_open_prepare(struct rpc_task *task, void *calldata)
 					data->o_arg.open_flags, claim))
 			goto out_no_action;
 		rcu_read_lock();
-		delegation = rcu_dereference(NFS_I(data->state->inode)->delegation);
+		delegation = nfs4_get_valid_delegation(data->state->inode);
 		if (can_open_delegated(delegation, data->o_arg.fmode, claim))
 			goto unlock_no_action;
 		rcu_read_unlock();
diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c
index 53939bf9d7d2..9876db52913a 100644
--- a/fs/ocfs2/file.c
+++ b/fs/ocfs2/file.c
@@ -2098,53 +2098,89 @@ static int ocfs2_is_io_unaligned(struct inode *inode, size_t count, loff_t pos)
 	return 0;
 }
 
-static int ocfs2_prepare_inode_for_refcount(struct inode *inode,
-					    struct file *file,
-					    loff_t pos, size_t count,
-					    int *meta_level)
+static int ocfs2_inode_lock_for_extent_tree(struct inode *inode,
+					    struct buffer_head **di_bh,
+					    int meta_level,
+					    int overwrite_io,
+					    int write_sem,
+					    int wait)
 {
-	int ret;
-	struct buffer_head *di_bh = NULL;
-	u32 cpos = pos >> OCFS2_SB(inode->i_sb)->s_clustersize_bits;
-	u32 clusters =
-		ocfs2_clusters_for_bytes(inode->i_sb, pos + count) - cpos;
+	int ret = 0;
 
-	ret = ocfs2_inode_lock(inode, &di_bh, 1);
-	if (ret) {
-		mlog_errno(ret);
+	if (wait)
+		ret = ocfs2_inode_lock(inode, NULL, meta_level);
+	else
+		ret = ocfs2_try_inode_lock(inode,
+			overwrite_io ? NULL : di_bh, meta_level);
+	if (ret < 0)
 		goto out;
+
+	if (wait) {
+		if (write_sem)
+			down_write(&OCFS2_I(inode)->ip_alloc_sem);
+		else
+			down_read(&OCFS2_I(inode)->ip_alloc_sem);
+	} else {
+		if (write_sem)
+			ret = down_write_trylock(&OCFS2_I(inode)->ip_alloc_sem);
+		else
+			ret = down_read_trylock(&OCFS2_I(inode)->ip_alloc_sem);
+
+		if (!ret) {
+			ret = -EAGAIN;
+			goto out_unlock;
+		}
 	}
 
-	*meta_level = 1;
+	return ret;
 
-	ret = ocfs2_refcount_cow(inode, di_bh, cpos, clusters, UINT_MAX);
-	if (ret)
-		mlog_errno(ret);
+out_unlock:
+	brelse(*di_bh);
+	ocfs2_inode_unlock(inode, meta_level);
 out:
-	brelse(di_bh);
 	return ret;
 }
 
+static void ocfs2_inode_unlock_for_extent_tree(struct inode *inode,
+					       struct buffer_head **di_bh,
+					       int meta_level,
+					       int write_sem)
+{
+	if (write_sem)
+		up_write(&OCFS2_I(inode)->ip_alloc_sem);
+	else
+		up_read(&OCFS2_I(inode)->ip_alloc_sem);
+
+	brelse(*di_bh);
+	*di_bh = NULL;
+
+	if (meta_level >= 0)
+		ocfs2_inode_unlock(inode, meta_level);
+}
+
 static int ocfs2_prepare_inode_for_write(struct file *file,
 					 loff_t pos, size_t count, int wait)
 {
 	int ret = 0, meta_level = 0, overwrite_io = 0;
+	int write_sem = 0;
 	struct dentry *dentry = file->f_path.dentry;
 	struct inode *inode = d_inode(dentry);
 	struct buffer_head *di_bh = NULL;
+	u32 cpos;
+	u32 clusters;
 
 	/*
 	 * We start with a read level meta lock and only jump to an ex
 	 * if we need to make modifications here.
 	 */
 	for(;;) {
-		if (wait)
-			ret = ocfs2_inode_lock(inode, NULL, meta_level);
-		else
-			ret = ocfs2_try_inode_lock(inode,
-				overwrite_io ? NULL : &di_bh, meta_level);
+		ret = ocfs2_inode_lock_for_extent_tree(inode,
+						       &di_bh,
+						       meta_level,
+						       overwrite_io,
+						       write_sem,
+						       wait);
 		if (ret < 0) {
-			meta_level = -1;
 			if (ret != -EAGAIN)
 				mlog_errno(ret);
 			goto out;
@@ -2156,15 +2192,8 @@ static int ocfs2_prepare_inode_for_write(struct file *file,
 		 */
 		if (!wait && !overwrite_io) {
 			overwrite_io = 1;
-			if (!down_read_trylock(&OCFS2_I(inode)->ip_alloc_sem)) {
-				ret = -EAGAIN;
-				goto out_unlock;
-			}
 
 			ret = ocfs2_overwrite_io(inode, di_bh, pos, count);
-			brelse(di_bh);
-			di_bh = NULL;
-			up_read(&OCFS2_I(inode)->ip_alloc_sem);
 			if (ret < 0) {
 				if (ret != -EAGAIN)
 					mlog_errno(ret);
@@ -2183,7 +2212,10 @@ static int ocfs2_prepare_inode_for_write(struct file *file,
 		 * set inode->i_size at the end of a write. */
 		if (should_remove_suid(dentry)) {
 			if (meta_level == 0) {
-				ocfs2_inode_unlock(inode, meta_level);
+				ocfs2_inode_unlock_for_extent_tree(inode,
+								   &di_bh,
+								   meta_level,
+								   write_sem);
 				meta_level = 1;
 				continue;
 			}
@@ -2197,18 +2229,32 @@ static int ocfs2_prepare_inode_for_write(struct file *file,
 
 		ret = ocfs2_check_range_for_refcount(inode, pos, count);
 		if (ret == 1) {
-			ocfs2_inode_unlock(inode, meta_level);
-			meta_level = -1;
-
-			ret = ocfs2_prepare_inode_for_refcount(inode,
-							       file,
-							       pos,
-							       count,
-							       &meta_level);
+			ocfs2_inode_unlock_for_extent_tree(inode,
+							   &di_bh,
+							   meta_level,
+							   write_sem);
+			ret = ocfs2_inode_lock_for_extent_tree(inode,
+							       &di_bh,
+							       meta_level,
+							       overwrite_io,
+							       1,
+							       wait);
+			write_sem = 1;
+			if (ret < 0) {
+				if (ret != -EAGAIN)
+					mlog_errno(ret);
+				goto out;
+			}
+
+			cpos = pos >> OCFS2_SB(inode->i_sb)->s_clustersize_bits;
+			clusters =
+				ocfs2_clusters_for_bytes(inode->i_sb, pos + count) - cpos;
+			ret = ocfs2_refcount_cow(inode, di_bh, cpos, clusters, UINT_MAX);
 		}
 
 		if (ret < 0) {
-			mlog_errno(ret);
+			if (ret != -EAGAIN)
+				mlog_errno(ret);
 			goto out_unlock;
 		}
 
@@ -2219,10 +2265,10 @@ out_unlock:
 	trace_ocfs2_prepare_inode_for_write(OCFS2_I(inode)->ip_blkno,
 					    pos, count, wait);
 
-	brelse(di_bh);
-
-	if (meta_level >= 0)
-		ocfs2_inode_unlock(inode, meta_level);
+	ocfs2_inode_unlock_for_extent_tree(inode,
+					   &di_bh,
+					   meta_level,
+					   write_sem);
 
 out:
 	return ret;