Merge branch 'sched/urgent' into sched/core, to pick up fixes

Signed-off-by: Ingo Molnar <mingo@kernel.org>

34 files changed, 269 insertions, 135 deletions

diff --git a/fs/binfmt_misc.c b/fs/binfmt_misc.c
index ce7181ea60fa..2a46762def31 100644
--- a/fs/binfmt_misc.c
+++ b/fs/binfmt_misc.c
@@ -54,7 +54,7 @@ typedef struct {
 	int size;			/* size of magic/mask */
 	char *magic;			/* magic or filename extension */
 	char *mask;			/* mask, NULL for exact match */
-	char *interpreter;		/* filename of interpreter */
+	const char *interpreter;	/* filename of interpreter */
 	char *name;
 	struct dentry *dentry;
 	struct file *interp_file;
@@ -131,27 +131,26 @@ static int load_misc_binary(struct linux_binprm *bprm)
 {
 	Node *fmt;
 	struct file *interp_file = NULL;
-	char iname[BINPRM_BUF_SIZE];
-	const char *iname_addr = iname;
 	int retval;
 	int fd_binary = -1;
 
 	retval = -ENOEXEC;
 	if (!enabled)
-		goto ret;
+		return retval;
 
 	/* to keep locking time low, we copy the interpreter string */
 	read_lock(&entries_lock);
 	fmt = check_file(bprm);
 	if (fmt)
-		strlcpy(iname, fmt->interpreter, BINPRM_BUF_SIZE);
+		dget(fmt->dentry);
 	read_unlock(&entries_lock);
 	if (!fmt)
-		goto ret;
+		return retval;
 
 	/* Need to be able to load the file after exec */
+	retval = -ENOENT;
 	if (bprm->interp_flags & BINPRM_FLAGS_PATH_INACCESSIBLE)
-		return -ENOENT;
+		goto ret;
 
 	if (!(fmt->flags & MISC_FMT_PRESERVE_ARGV0)) {
 		retval = remove_arg_zero(bprm);
@@ -195,22 +194,22 @@ static int load_misc_binary(struct linux_binprm *bprm)
 	bprm->argc++;
 
 	/* add the interp as argv[0] */
-	retval = copy_strings_kernel(1, &iname_addr, bprm);
+	retval = copy_strings_kernel(1, &fmt->interpreter, bprm);
 	if (retval < 0)
 		goto error;
 	bprm->argc++;
 
 	/* Update interp in case binfmt_script needs it. */
-	retval = bprm_change_interp(iname, bprm);
+	retval = bprm_change_interp(fmt->interpreter, bprm);
 	if (retval < 0)
 		goto error;
 
-	if (fmt->flags & MISC_FMT_OPEN_FILE && fmt->interp_file) {
+	if (fmt->flags & MISC_FMT_OPEN_FILE) {
 		interp_file = filp_clone_open(fmt->interp_file);
 		if (!IS_ERR(interp_file))
 			deny_write_access(interp_file);
 	} else {
-		interp_file = open_exec(iname);
+		interp_file = open_exec(fmt->interpreter);
 	}
 	retval = PTR_ERR(interp_file);
 	if (IS_ERR(interp_file))
@@ -238,6 +237,7 @@ static int load_misc_binary(struct linux_binprm *bprm)
 		goto error;
 
 ret:
+	dput(fmt->dentry);
 	return retval;
 error:
 	if (fd_binary > 0)
@@ -594,8 +594,13 @@ static struct inode *bm_get_inode(struct super_block *sb, int mode)
 
 static void bm_evict_inode(struct inode *inode)
 {
+	Node *e = inode->i_private;
+
+	if (e->flags & MISC_FMT_OPEN_FILE)
+		filp_close(e->interp_file, NULL);
+
 	clear_inode(inode);
-	kfree(inode->i_private);
+	kfree(e);
 }
 
 static void kill_node(Node *e)
@@ -603,24 +608,14 @@ static void kill_node(Node *e)
 	struct dentry *dentry;
 
 	write_lock(&entries_lock);
-	dentry = e->dentry;
-	if (dentry) {
-		list_del_init(&e->list);
-		e->dentry = NULL;
-	}
+	list_del_init(&e->list);
 	write_unlock(&entries_lock);
 
-	if ((e->flags & MISC_FMT_OPEN_FILE) && e->interp_file) {
-		filp_close(e->interp_file, NULL);
-		e->interp_file = NULL;
-	}
-
-	if (dentry) {
-		drop_nlink(d_inode(dentry));
-		d_drop(dentry);
-		dput(dentry);
-		simple_release_fs(&bm_mnt, &entry_count);
-	}
+	dentry = e->dentry;
+	drop_nlink(d_inode(dentry));
+	d_drop(dentry);
+	dput(dentry);
+	simple_release_fs(&bm_mnt, &entry_count);
 }
 
 /* /<entry> */
@@ -665,7 +660,8 @@ static ssize_t bm_entry_write(struct file *file, const char __user *buffer,
 		root = file_inode(file)->i_sb->s_root;
 		inode_lock(d_inode(root));
 
-		kill_node(e);
+		if (!list_empty(&e->list))
+			kill_node(e);
 
 		inode_unlock(d_inode(root));
 		break;
@@ -794,7 +790,7 @@ static ssize_t bm_status_write(struct file *file, const char __user *buffer,
 		inode_lock(d_inode(root));
 
 		while (!list_empty(&entries))
-			kill_node(list_entry(entries.next, Node, list));
+			kill_node(list_first_entry(&entries, Node, list));
 
 		inode_unlock(d_inode(root));
 		break;
diff --git a/fs/binfmt_script.c b/fs/binfmt_script.c
index afdf4e3cafc2..7cde3f46ad26 100644
--- a/fs/binfmt_script.c
+++ b/fs/binfmt_script.c
@@ -19,7 +19,6 @@ static int load_script(struct linux_binprm *bprm)
 	const char *i_arg, *i_name;
 	char *cp;
 	struct file *file;
-	char interp[BINPRM_BUF_SIZE];
 	int retval;
 
 	if ((bprm->buf[0] != '#') || (bprm->buf[1] != '!'))
@@ -55,7 +54,7 @@ static int load_script(struct linux_binprm *bprm)
 			break;
 	}
 	for (cp = bprm->buf+2; (*cp == ' ') || (*cp == '\t'); cp++);
-	if (*cp == '\0') 
+	if (*cp == '\0')
 		return -ENOEXEC; /* No interpreter name found */
 	i_name = cp;
 	i_arg = NULL;
@@ -65,7 +64,6 @@ static int load_script(struct linux_binprm *bprm)
 		*cp++ = '\0';
 	if (*cp)
 		i_arg = cp;
-	strcpy (interp, i_name);
 	/*
 	 * OK, we've parsed out the interpreter name and
 	 * (optional) argument.
@@ -80,24 +78,27 @@ static int load_script(struct linux_binprm *bprm)
 	if (retval)
 		return retval;
 	retval = copy_strings_kernel(1, &bprm->interp, bprm);
-	if (retval < 0) return retval; 
+	if (retval < 0)
+		return retval;
 	bprm->argc++;
 	if (i_arg) {
 		retval = copy_strings_kernel(1, &i_arg, bprm);
-		if (retval < 0) return retval; 
+		if (retval < 0)
+			return retval;
 		bprm->argc++;
 	}
 	retval = copy_strings_kernel(1, &i_name, bprm);
-	if (retval) return retval; 
+	if (retval)
+		return retval;
 	bprm->argc++;
-	retval = bprm_change_interp(interp, bprm);
+	retval = bprm_change_interp(i_name, bprm);
 	if (retval < 0)
 		return retval;
 
 	/*
 	 * OK, now restart the process with the interpreter's dentry.
 	 */
-	file = open_exec(interp);
+	file = open_exec(i_name);
 	if (IS_ERR(file))
 		return PTR_ERR(file);
 
diff --git a/fs/btrfs/compression.c b/fs/btrfs/compression.c
index b51d23f5cafa..280384bf34f1 100644
--- a/fs/btrfs/compression.c
+++ b/fs/btrfs/compression.c
@@ -107,7 +107,8 @@ static void end_compressed_bio_read(struct bio *bio)
 	struct inode *inode;
 	struct page *page;
 	unsigned long index;
-	int ret;
+	unsigned int mirror = btrfs_io_bio(bio)->mirror_num;
+	int ret = 0;
 
 	if (bio->bi_status)
 		cb->errors = 1;
@@ -118,6 +119,21 @@ static void end_compressed_bio_read(struct bio *bio)
 	if (!refcount_dec_and_test(&cb->pending_bios))
 		goto out;
 
+	/*
+	 * Record the correct mirror_num in cb->orig_bio so that
+	 * read-repair can work properly.
+	 */
+	ASSERT(btrfs_io_bio(cb->orig_bio));
+	btrfs_io_bio(cb->orig_bio)->mirror_num = mirror;
+	cb->mirror_num = mirror;
+
+	/*
+	 * Some IO in this cb have failed, just skip checksum as there
+	 * is no way it could be correct.
+	 */
+	if (cb->errors == 1)
+		goto csum_failed;
+
 	inode = cb->inode;
 	ret = check_compressed_csum(BTRFS_I(inode), cb,
 				    (u64)bio->bi_iter.bi_sector << 9);
diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index 5a8933da39a7..8fc690384c58 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -709,7 +709,6 @@ struct btrfs_delayed_root;
 #define BTRFS_FS_OPEN				5
 #define BTRFS_FS_QUOTA_ENABLED			6
 #define BTRFS_FS_QUOTA_ENABLING			7
-#define BTRFS_FS_QUOTA_DISABLING		8
 #define BTRFS_FS_UPDATE_UUID_TREE_GEN		9
 #define BTRFS_FS_CREATING_FREE_SPACE_TREE	10
 #define BTRFS_FS_BTREE_ERR			11
@@ -723,7 +722,7 @@ struct btrfs_delayed_root;
  * Indicate that a whole-filesystem exclusive operation is running
  * (device replace, resize, device add/delete, balance)
  */
-#define BTRFS_FS_EXCL_OP			14
+#define BTRFS_FS_EXCL_OP			16
 
 struct btrfs_fs_info {
 	u8 fsid[BTRFS_FSID_SIZE];
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 487bbe4fb3c6..dfdab849037b 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -3643,7 +3643,14 @@ int write_all_supers(struct btrfs_fs_info *fs_info, int max_mirrors)
 	u64 flags;
 
 	do_barriers = !btrfs_test_opt(fs_info, NOBARRIER);
-	backup_super_roots(fs_info);
+
+	/*
+	 * max_mirrors == 0 indicates we're from commit_transaction,
+	 * not from fsync where the tree roots in fs_info have not
+	 * been consistent on disk.
+	 */
+	if (max_mirrors == 0)
+		backup_super_roots(fs_info);
 
 	sb = fs_info->super_for_commit;
 	dev_item = &sb->dev_item;
diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index 3e5bb0cdd3cd..970190cd347e 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -2801,7 +2801,7 @@ static int submit_extent_page(unsigned int opf, struct extent_io_tree *tree,
 		}
 	}
 
-	bio = btrfs_bio_alloc(bdev, sector << 9);
+	bio = btrfs_bio_alloc(bdev, (u64)sector << 9);
 	bio_add_page(bio, page, page_size, offset);
 	bio->bi_end_io = end_io_func;
 	bio->bi_private = tree;
@@ -3471,8 +3471,7 @@ static int __extent_writepage(struct page *page, struct writeback_control *wbc,
 	unsigned int write_flags = 0;
 	unsigned long nr_written = 0;
 
-	if (wbc->sync_mode == WB_SYNC_ALL)
-		write_flags = REQ_SYNC;
+	write_flags = wbc_to_write_flags(wbc);
 
 	trace___extent_writepage(page, inode, wbc);
 
@@ -3718,7 +3717,7 @@ static noinline_for_stack int write_one_eb(struct extent_buffer *eb,
 	unsigned long i, num_pages;
 	unsigned long bio_flags = 0;
 	unsigned long start, end;
-	unsigned int write_flags = (epd->sync_io ? REQ_SYNC : 0) | REQ_META;
+	unsigned int write_flags = wbc_to_write_flags(wbc) | REQ_META;
 	int ret = 0;
 
 	clear_bit(EXTENT_BUFFER_WRITE_ERR, &eb->bflags);
@@ -4063,9 +4062,6 @@ static void flush_epd_write_bio(struct extent_page_data *epd)
 	if (epd->bio) {
 		int ret;
 
-		bio_set_op_attrs(epd->bio, REQ_OP_WRITE,
-				 epd->sync_io ? REQ_SYNC : 0);
-
 		ret = submit_one_bio(epd->bio, 0, epd->bio_flags);
 		BUG_ON(ret < 0); /* -ENOMEM */
 		epd->bio = NULL;
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 128f3e58634f..d94e3f68b9b1 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -135,6 +135,18 @@ static inline void btrfs_cleanup_ordered_extents(struct inode *inode,
 						 const u64 offset,
 						 const u64 bytes)
 {
+	unsigned long index = offset >> PAGE_SHIFT;
+	unsigned long end_index = (offset + bytes - 1) >> PAGE_SHIFT;
+	struct page *page;
+
+	while (index <= end_index) {
+		page = find_get_page(inode->i_mapping, index);
+		index++;
+		if (!page)
+			continue;
+		ClearPagePrivate2(page);
+		put_page(page);
+	}
 	return __endio_write_update_ordered(inode, offset + PAGE_SIZE,
 					    bytes - PAGE_SIZE, false);
 }
@@ -8357,11 +8369,8 @@ static void btrfs_endio_direct_read(struct bio *bio)
 	struct btrfs_io_bio *io_bio = btrfs_io_bio(bio);
 	blk_status_t err = bio->bi_status;
 
-	if (dip->flags & BTRFS_DIO_ORIG_BIO_SUBMITTED) {
+	if (dip->flags & BTRFS_DIO_ORIG_BIO_SUBMITTED)
 		err = btrfs_subio_endio_read(inode, io_bio, err);
-		if (!err)
-			bio->bi_status = 0;
-	}
 
 	unlock_extent(&BTRFS_I(inode)->io_tree, dip->logical_offset,
 		      dip->logical_offset + dip->bytes - 1);
@@ -8369,7 +8378,7 @@ static void btrfs_endio_direct_read(struct bio *bio)
 
 	kfree(dip);
 
-	dio_bio->bi_status = bio->bi_status;
+	dio_bio->bi_status = err;
 	dio_end_io(dio_bio);
 
 	if (io_bio->end_io)
@@ -8387,6 +8396,7 @@ static void __endio_write_update_ordered(struct inode *inode,
 	btrfs_work_func_t func;
 	u64 ordered_offset = offset;
 	u64 ordered_bytes = bytes;
+	u64 last_offset;
 	int ret;
 
 	if (btrfs_is_free_space_inode(BTRFS_I(inode))) {
@@ -8398,6 +8408,7 @@ static void __endio_write_update_ordered(struct inode *inode,
 	}
 
 again:
+	last_offset = ordered_offset;
 	ret = btrfs_dec_test_first_ordered_pending(inode, &ordered,
 						   &ordered_offset,
 						   ordered_bytes,
@@ -8409,6 +8420,12 @@ again:
 	btrfs_queue_work(wq, &ordered->work);
 out_test:
 	/*
+	 * If btrfs_dec_test_ordered_pending does not find any ordered extent
+	 * in the range, we can exit.
+	 */
+	if (ordered_offset == last_offset)
+		return;
+	/*
 	 * our bio might span multiple ordered extents.  If we haven't
 	 * completed the accounting for the whole dio, go back and try again
 	 */
diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index d6715c2bcdc4..6c7a49faf4e0 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -2773,9 +2773,9 @@ static long btrfs_ioctl_fs_info(struct btrfs_fs_info *fs_info,
 	}
 	mutex_unlock(&fs_devices->device_list_mutex);
 
-	fi_args->nodesize = fs_info->super_copy->nodesize;
-	fi_args->sectorsize = fs_info->super_copy->sectorsize;
-	fi_args->clone_alignment = fs_info->super_copy->sectorsize;
+	fi_args->nodesize = fs_info->nodesize;
+	fi_args->sectorsize = fs_info->sectorsize;
+	fi_args->clone_alignment = fs_info->sectorsize;
 
 	if (copy_to_user(arg, fi_args, sizeof(*fi_args)))
 		ret = -EFAULT;
@@ -3032,7 +3032,7 @@ static int btrfs_cmp_data_prepare(struct inode *src, u64 loff,
 out:
 	if (ret)
 		btrfs_cmp_data_free(cmp);
-	return 0;
+	return ret;
 }
 
 static int btrfs_cmp_data(u64 len, struct cmp_pages *cmp)
@@ -4061,6 +4061,10 @@ static long btrfs_ioctl_default_subvol(struct file *file, void __user *argp)
 		ret = PTR_ERR(new_root);
 		goto out;
 	}
+	if (!is_fstree(new_root->objectid)) {
+		ret = -ENOENT;
+		goto out;
+	}
 
 	path = btrfs_alloc_path();
 	if (!path) {
diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c
index 5c8b61c86e61..e172d4843eae 100644
--- a/fs/btrfs/qgroup.c
+++ b/fs/btrfs/qgroup.c
@@ -807,7 +807,6 @@ static int btrfs_clean_quota_tree(struct btrfs_trans_handle *trans,
 	}
 	ret = 0;
 out:
-	set_bit(BTRFS_FS_QUOTA_DISABLING, &root->fs_info->flags);
 	btrfs_free_path(path);
 	return ret;
 }
@@ -953,7 +952,6 @@ int btrfs_quota_disable(struct btrfs_trans_handle *trans,
 	if (!fs_info->quota_root)
 		goto out;
 	clear_bit(BTRFS_FS_QUOTA_ENABLED, &fs_info->flags);
-	set_bit(BTRFS_FS_QUOTA_DISABLING, &fs_info->flags);
 	btrfs_qgroup_wait_for_completion(fs_info, false);
 	spin_lock(&fs_info->qgroup_lock);
 	quota_root = fs_info->quota_root;
@@ -1307,6 +1305,8 @@ int btrfs_remove_qgroup(struct btrfs_trans_handle *trans,
 		}
 	}
 	ret = del_qgroup_item(trans, quota_root, qgroupid);
+	if (ret && ret != -ENOENT)
+		goto out;
 
 	while (!list_empty(&qgroup->groups)) {
 		list = list_first_entry(&qgroup->groups,
@@ -2086,8 +2086,6 @@ int btrfs_run_qgroups(struct btrfs_trans_handle *trans,
 
 	if (test_and_clear_bit(BTRFS_FS_QUOTA_ENABLING, &fs_info->flags))
 		set_bit(BTRFS_FS_QUOTA_ENABLED, &fs_info->flags);
-	if (test_and_clear_bit(BTRFS_FS_QUOTA_DISABLING, &fs_info->flags))
-		clear_bit(BTRFS_FS_QUOTA_ENABLED, &fs_info->flags);
 
 	spin_lock(&fs_info->qgroup_lock);
 	while (!list_empty(&fs_info->dirty_qgroups)) {
diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c
index 3a49a3c2fca4..9841faef08ea 100644
--- a/fs/btrfs/relocation.c
+++ b/fs/btrfs/relocation.c
@@ -2400,11 +2400,11 @@ void free_reloc_roots(struct list_head *list)
 	while (!list_empty(list)) {
 		reloc_root = list_entry(list->next, struct btrfs_root,
 					root_list);
+		__del_reloc_root(reloc_root);
 		free_extent_buffer(reloc_root->node);
 		free_extent_buffer(reloc_root->commit_root);
 		reloc_root->node = NULL;
 		reloc_root->commit_root = NULL;
-		__del_reloc_root(reloc_root);
 	}
 }
 
diff --git a/fs/btrfs/send.c b/fs/btrfs/send.c
index 32b043ef8ac9..8fd195cfe81b 100644
--- a/fs/btrfs/send.c
+++ b/fs/btrfs/send.c
@@ -2630,7 +2630,7 @@ static int send_create_inode(struct send_ctx *sctx, u64 ino)
 	} else {
 		btrfs_warn(sctx->send_root->fs_info, "unexpected inode type %o",
 				(int)(mode & S_IFMT));
-		ret = -ENOTSUPP;
+		ret = -EOPNOTSUPP;
 		goto out;
 	}
 
diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c
index ad7f4bab640b..c800d067fcbf 100644
--- a/fs/btrfs/tree-log.c
+++ b/fs/btrfs/tree-log.c
@@ -4181,6 +4181,7 @@ static int btrfs_log_changed_extents(struct btrfs_trans_handle *trans,
 	struct extent_map *em, *n;
 	struct list_head extents;
 	struct extent_map_tree *tree = &inode->extent_tree;
+	u64 logged_start, logged_end;
 	u64 test_gen;
 	int ret = 0;
 	int num = 0;
@@ -4190,10 +4191,11 @@ static int btrfs_log_changed_extents(struct btrfs_trans_handle *trans,
 	down_write(&inode->dio_sem);
 	write_lock(&tree->lock);
 	test_gen = root->fs_info->last_trans_committed;
+	logged_start = start;
+	logged_end = end;
 
 	list_for_each_entry_safe(em, n, &tree->modified_extents, list) {
 		list_del_init(&em->list);
-
 		/*
 		 * Just an arbitrary number, this can be really CPU intensive
 		 * once we start getting a lot of extents, and really once we
@@ -4208,6 +4210,12 @@ static int btrfs_log_changed_extents(struct btrfs_trans_handle *trans,
 
 		if (em->generation <= test_gen)
 			continue;
+
+		if (em->start < logged_start)
+			logged_start = em->start;
+		if ((em->start + em->len - 1) > logged_end)
+			logged_end = em->start + em->len - 1;
+
 		/* Need a ref to keep it from getting evicted from cache */
 		refcount_inc(&em->refs);
 		set_bit(EXTENT_FLAG_LOGGING, &em->flags);
@@ -4216,7 +4224,7 @@ static int btrfs_log_changed_extents(struct btrfs_trans_handle *trans,
 	}
 
 	list_sort(NULL, &extents, extent_cmp);
-	btrfs_get_logged_extents(inode, logged_list, start, end);
+	btrfs_get_logged_extents(inode, logged_list, logged_start, logged_end);
 	/*
 	 * Some ordered extents started by fsync might have completed
 	 * before we could collect them into the list logged_list, which
diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index 0e8f16c305df..b39737568c22 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -6166,7 +6166,7 @@ blk_status_t btrfs_map_bio(struct btrfs_fs_info *fs_info, struct bio *bio,
 	map_length = length;
 
 	btrfs_bio_counter_inc_blocked(fs_info);
-	ret = __btrfs_map_block(fs_info, bio_op(bio), logical,
+	ret = __btrfs_map_block(fs_info, btrfs_op(bio), logical,
 				&map_length, &bbio, mirror_num, 1);
 	if (ret) {
 		btrfs_bio_counter_dec(fs_info);
diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c
index 84edfc60d87a..f23c820daaed 100644
--- a/fs/ceph/mds_client.c
+++ b/fs/ceph/mds_client.c
@@ -734,12 +734,13 @@ static int __choose_mds(struct ceph_mds_client *mdsc,
 			inode = req->r_inode;
 			ihold(inode);
 		} else {
-			/* req->r_dentry is non-null for LSSNAP request.
-			 * fall-thru */
-			WARN_ON_ONCE(!req->r_dentry);
+			/* req->r_dentry is non-null for LSSNAP request */
+			rcu_read_lock();
+			inode = get_nonsnap_parent(req->r_dentry);
+			rcu_read_unlock();
+			dout("__choose_mds using snapdir's parent %p\n", inode);
 		}
-	}
-	if (!inode && req->r_dentry) {
+	} else if (req->r_dentry) {
 		/* ignore race with rename; old or new d_parent is okay */
 		struct dentry *parent;
 		struct inode *dir;
diff --git a/fs/ceph/snap.c b/fs/ceph/snap.c
index 1ffc8b426c1c..7fc0b850c352 100644
--- a/fs/ceph/snap.c
+++ b/fs/ceph/snap.c
@@ -374,12 +374,10 @@ static int build_snap_context(struct ceph_snap_realm *realm,
 	     realm->ino, realm, snapc, snapc->seq,
 	     (unsigned int) snapc->num_snaps);
 
-	if (realm->cached_context) {
-		ceph_put_snap_context(realm->cached_context);
-		/* queue realm for cap_snap creation */
-		list_add_tail(&realm->dirty_item, dirty_realms);
-	}
+	ceph_put_snap_context(realm->cached_context);
 	realm->cached_context = snapc;
+	/* queue realm for cap_snap creation */
+	list_add_tail(&realm->dirty_item, dirty_realms);
 	return 0;
 
 fail:
diff --git a/fs/exec.c b/fs/exec.c
index ac34d9724684..5470d3c1892a 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -1410,7 +1410,7 @@ static void free_bprm(struct linux_binprm *bprm)
 	kfree(bprm);
 }
 
-int bprm_change_interp(char *interp, struct linux_binprm *bprm)
+int bprm_change_interp(const char *interp, struct linux_binprm *bprm)
 {
 	/* If a binfmt changed the interp, free it first. */
 	if (bprm->interp != bprm->filename)
diff --git a/fs/namespace.c b/fs/namespace.c
index 54059b142d6b..3b601f115b6c 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -468,7 +468,9 @@ static inline int may_write_real(struct file *file)
 
 	/* File refers to upper, writable layer? */
 	upperdentry = d_real(dentry, NULL, 0, D_REAL_UPPER);
-	if (upperdentry && file_inode(file) == d_inode(upperdentry))
+	if (upperdentry &&
+	    (file_inode(file) == d_inode(upperdentry) ||
+	     file_inode(file) == d_inode(dentry)))
 		return 0;
 
 	/* Lower layer: can't write to real file, sorry... */
diff --git a/fs/nfs/client.c b/fs/nfs/client.c
index efebe6cf4378..22880ef6d8dd 100644
--- a/fs/nfs/client.c
+++ b/fs/nfs/client.c
@@ -218,7 +218,6 @@ static void nfs_cb_idr_remove_locked(struct nfs_client *clp)
 static void pnfs_init_server(struct nfs_server *server)
 {
 	rpc_init_wait_queue(&server->roc_rpcwaitq, "pNFS ROC");
-	rpc_init_wait_queue(&server->uoc_rpcwaitq, "NFS UOC");
 }
 
 #else
@@ -888,6 +887,7 @@ struct nfs_server *nfs_alloc_server(void)
 	ida_init(&server->openowner_id);
 	ida_init(&server->lockowner_id);
 	pnfs_init_server(server);
+	rpc_init_wait_queue(&server->uoc_rpcwaitq, "NFS UOC");
 
 	return server;
 }
diff --git a/fs/nfs/filelayout/filelayout.c b/fs/nfs/filelayout/filelayout.c
index 44c638b7876c..508126eb49f9 100644
--- a/fs/nfs/filelayout/filelayout.c
+++ b/fs/nfs/filelayout/filelayout.c
@@ -745,7 +745,8 @@ filelayout_free_lseg(struct pnfs_layout_segment *lseg)
 	struct nfs4_filelayout_segment *fl = FILELAYOUT_LSEG(lseg);
 
 	dprintk("--> %s\n", __func__);
-	nfs4_fl_put_deviceid(fl->dsaddr);
+	if (fl->dsaddr != NULL)
+		nfs4_fl_put_deviceid(fl->dsaddr);
 	/* This assumes a single RW lseg */
 	if (lseg->pls_range.iomode == IOMODE_RW) {
 		struct nfs4_filelayout *flo;
diff --git a/fs/nfs/nfs4idmap.c b/fs/nfs/nfs4idmap.c
index dd5d27da8c0c..30426c1a1bbd 100644
--- a/fs/nfs/nfs4idmap.c
+++ b/fs/nfs/nfs4idmap.c
@@ -274,7 +274,7 @@ static struct key *nfs_idmap_request_key(const char *name, size_t namelen,
 	ssize_t ret;
 
 	ret = nfs_idmap_get_desc(name, namelen, type, strlen(type), &desc);
-	if (ret <= 0)
+	if (ret < 0)
 		return ERR_PTR(ret);
 
 	rkey = request_key(&key_type_id_resolver, desc, "");
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index 6c61e2b99635..f90090e8c959 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -8399,8 +8399,7 @@ nfs4_layoutget_handle_exception(struct rpc_task *task,
 		lo = NFS_I(inode)->layout;
 		/* If the open stateid was bad, then recover it. */
 		if (!lo || test_bit(NFS_LAYOUT_INVALID_STID, &lo->plh_flags) ||
-		    nfs4_stateid_match_other(&lgp->args.stateid,
-					&lgp->args.ctx->state->stateid)) {
+		    !nfs4_stateid_match_other(&lgp->args.stateid, &lo->plh_stateid)) {
 			spin_unlock(&inode->i_lock);
 			exception->state = lgp->args.ctx->state;
 			exception->stateid = &lgp->args.stateid;
diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c
index 37c8af003275..14ed9791ec9c 100644
--- a/fs/nfs/nfs4xdr.c
+++ b/fs/nfs/nfs4xdr.c
@@ -1842,8 +1842,8 @@ static void encode_create_session(struct xdr_stream *xdr,
 	 * Assumes OPEN is the biggest non-idempotent compound.
 	 * 2 is the verifier.
 	 */
-	max_resp_sz_cached = (NFS4_dec_open_sz + RPC_REPHDRSIZE +
-			      RPC_MAX_AUTH_SIZE + 2) * XDR_UNIT;
+	max_resp_sz_cached = (NFS4_dec_open_sz + RPC_REPHDRSIZE + 2)
+				* XDR_UNIT + RPC_MAX_AUTH_SIZE;
 
 	encode_op_hdr(xdr, OP_CREATE_SESSION, decode_create_session_maxsz, hdr);
 	p = reserve_space(xdr, 16 + 2*28 + 20 + clnt->cl_nodelen + 12);
diff --git a/fs/overlayfs/copy_up.c b/fs/overlayfs/copy_up.c
index aad97b30d5e6..c441f9387a1b 100644
--- a/fs/overlayfs/copy_up.c
+++ b/fs/overlayfs/copy_up.c
@@ -561,10 +561,8 @@ static int ovl_do_copy_up(struct ovl_copy_up_ctx *c)
 		c->tmpfile = true;
 		err = ovl_copy_up_locked(c);
 	} else {
-		err = -EIO;
-		if (lock_rename(c->workdir, c->destdir) != NULL) {
-			pr_err("overlayfs: failed to lock workdir+upperdir\n");
-		} else {
+		err = ovl_lock_rename_workdir(c->workdir, c->destdir);
+		if (!err) {
 			err = ovl_copy_up_locked(c);
 			unlock_rename(c->workdir, c->destdir);
 		}
diff --git a/fs/overlayfs/dir.c b/fs/overlayfs/dir.c
index 3309b1912241..cc961a3bd3bd 100644
--- a/fs/overlayfs/dir.c
+++ b/fs/overlayfs/dir.c
@@ -216,26 +216,6 @@ out_unlock:
 	return err;
 }
 
-static int ovl_lock_rename_workdir(struct dentry *workdir,
-				   struct dentry *upperdir)
-{
-	/* Workdir should not be the same as upperdir */
-	if (workdir == upperdir)
-		goto err;
-
-	/* Workdir should not be subdir of upperdir and vice versa */
-	if (lock_rename(workdir, upperdir) != NULL)
-		goto err_unlock;
-
-	return 0;
-
-err_unlock:
-	unlock_rename(workdir, upperdir);
-err:
-	pr_err("overlayfs: failed to lock workdir+upperdir\n");
-	return -EIO;
-}
-
 static struct dentry *ovl_clear_empty(struct dentry *dentry,
 				      struct list_head *list)
 {
diff --git a/fs/overlayfs/namei.c b/fs/overlayfs/namei.c
index c3addd1114f1..654bea1a5ac9 100644
--- a/fs/overlayfs/namei.c
+++ b/fs/overlayfs/namei.c
@@ -506,6 +506,7 @@ static struct dentry *ovl_lookup_index(struct dentry *dentry,
 
 	index = lookup_one_len_unlocked(name.name, ofs->indexdir, name.len);
 	if (IS_ERR(index)) {
+		err = PTR_ERR(index);
 		pr_warn_ratelimited("overlayfs: failed inode index lookup (ino=%lu, key=%*s, err=%i);\n"
 				    "overlayfs: mount with '-o index=off' to disable inodes index.\n",
 				    d_inode(origin)->i_ino, name.len, name.name,
diff --git a/fs/overlayfs/overlayfs.h b/fs/overlayfs/overlayfs.h
index d4e8c1a08fb0..c706a6f99928 100644
--- a/fs/overlayfs/overlayfs.h
+++ b/fs/overlayfs/overlayfs.h
@@ -235,6 +235,7 @@ bool ovl_inuse_trylock(struct dentry *dentry);
 void ovl_inuse_unlock(struct dentry *dentry);
 int ovl_nlink_start(struct dentry *dentry, bool *locked);
 void ovl_nlink_end(struct dentry *dentry, bool locked);
+int ovl_lock_rename_workdir(struct dentry *workdir, struct dentry *upperdir);
 
 static inline bool ovl_is_impuredir(struct dentry *dentry)
 {
diff --git a/fs/overlayfs/ovl_entry.h b/fs/overlayfs/ovl_entry.h
index 878a750986dd..25d9b5adcd42 100644
--- a/fs/overlayfs/ovl_entry.h
+++ b/fs/overlayfs/ovl_entry.h
@@ -37,6 +37,9 @@ struct ovl_fs {
 	bool noxattr;
 	/* sb common to all layers */
 	struct super_block *same_sb;
+	/* Did we take the inuse lock? */
+	bool upperdir_locked;
+	bool workdir_locked;
 };
 
 /* private information held for every overlayfs dentry */
diff --git a/fs/overlayfs/readdir.c b/fs/overlayfs/readdir.c
index 62e9b22a2077..0f85ee9c3268 100644
--- a/fs/overlayfs/readdir.c
+++ b/fs/overlayfs/readdir.c
@@ -988,6 +988,7 @@ int ovl_indexdir_cleanup(struct dentry *dentry, struct vfsmount *mnt,
 			 struct path *lowerstack, unsigned int numlower)
 {
 	int err;
+	struct dentry *index = NULL;
 	struct inode *dir = dentry->d_inode;
 	struct path path = { .mnt = mnt, .dentry = dentry };
 	LIST_HEAD(list);
@@ -1007,8 +1008,6 @@ int ovl_indexdir_cleanup(struct dentry *dentry, struct vfsmount *mnt,
 
 	inode_lock_nested(dir, I_MUTEX_PARENT);
 	list_for_each_entry(p, &list, l_node) {
-		struct dentry *index;
-
 		if (p->name[0] == '.') {
 			if (p->len == 1)
 				continue;
@@ -1018,6 +1017,7 @@ int ovl_indexdir_cleanup(struct dentry *dentry, struct vfsmount *mnt,
 		index = lookup_one_len(p->name, dentry, p->len);
 		if (IS_ERR(index)) {
 			err = PTR_ERR(index);
+			index = NULL;
 			break;
 		}
 		err = ovl_verify_index(index, lowerstack, numlower);
@@ -1029,7 +1029,9 @@ int ovl_indexdir_cleanup(struct dentry *dentry, struct vfsmount *mnt,
 				break;
 		}
 		dput(index);
+		index = NULL;
 	}
+	dput(index);
 	inode_unlock(dir);
 out:
 	ovl_cache_free(&list);
diff --git a/fs/overlayfs/super.c b/fs/overlayfs/super.c
index fd5ea4facc62..092d150643c1 100644
--- a/fs/overlayfs/super.c
+++ b/fs/overlayfs/super.c
@@ -211,9 +211,10 @@ static void ovl_put_super(struct super_block *sb)
 
 	dput(ufs->indexdir);
 	dput(ufs->workdir);
-	ovl_inuse_unlock(ufs->workbasedir);
+	if (ufs->workdir_locked)
+		ovl_inuse_unlock(ufs->workbasedir);
 	dput(ufs->workbasedir);
-	if (ufs->upper_mnt)
+	if (ufs->upper_mnt && ufs->upperdir_locked)
 		ovl_inuse_unlock(ufs->upper_mnt->mnt_root);
 	mntput(ufs->upper_mnt);
 	for (i = 0; i < ufs->numlower; i++)
@@ -881,9 +882,13 @@ static int ovl_fill_super(struct super_block *sb, void *data, int silent)
 			goto out_put_upperpath;
 
 		err = -EBUSY;
-		if (!ovl_inuse_trylock(upperpath.dentry)) {
-			pr_err("overlayfs: upperdir is in-use by another mount\n");
+		if (ovl_inuse_trylock(upperpath.dentry)) {
+			ufs->upperdir_locked = true;
+		} else if (ufs->config.index) {
+			pr_err("overlayfs: upperdir is in-use by another mount, mount with '-o index=off' to override exclusive upperdir protection.\n");
 			goto out_put_upperpath;
+		} else {
+			pr_warn("overlayfs: upperdir is in-use by another mount, accessing files from both mounts will result in undefined behavior.\n");
 		}
 
 		err = ovl_mount_dir(ufs->config.workdir, &workpath);
@@ -901,9 +906,13 @@ static int ovl_fill_super(struct super_block *sb, void *data, int silent)
 		}
 
 		err = -EBUSY;
-		if (!ovl_inuse_trylock(workpath.dentry)) {
-			pr_err("overlayfs: workdir is in-use by another mount\n");
+		if (ovl_inuse_trylock(workpath.dentry)) {
+			ufs->workdir_locked = true;
+		} else if (ufs->config.index) {
+			pr_err("overlayfs: workdir is in-use by another mount, mount with '-o index=off' to override exclusive workdir protection.\n");
 			goto out_put_workpath;
+		} else {
+			pr_warn("overlayfs: workdir is in-use by another mount, accessing files from both mounts will result in undefined behavior.\n");
 		}
 
 		ufs->workbasedir = workpath.dentry;
@@ -1156,11 +1165,13 @@ out_put_lowerpath:
 out_free_lowertmp:
 	kfree(lowertmp);
 out_unlock_workdentry:
-	ovl_inuse_unlock(workpath.dentry);
+	if (ufs->workdir_locked)
+		ovl_inuse_unlock(workpath.dentry);
 out_put_workpath:
 	path_put(&workpath);
 out_unlock_upperdentry:
-	ovl_inuse_unlock(upperpath.dentry);
+	if (ufs->upperdir_locked)
+		ovl_inuse_unlock(upperpath.dentry);
 out_put_upperpath:
 	path_put(&upperpath);
 out_free_config:
diff --git a/fs/overlayfs/util.c b/fs/overlayfs/util.c
index 117794582f9f..b9b239fa5cfd 100644
--- a/fs/overlayfs/util.c
+++ b/fs/overlayfs/util.c
@@ -430,7 +430,7 @@ void ovl_inuse_unlock(struct dentry *dentry)
 	}
 }
 
-/* Called must hold OVL_I(inode)->oi_lock */
+/* Caller must hold OVL_I(inode)->lock */
 static void ovl_cleanup_index(struct dentry *dentry)
 {
 	struct inode *dir = ovl_indexdir(dentry->d_sb)->d_inode;
@@ -469,6 +469,9 @@ static void ovl_cleanup_index(struct dentry *dentry)
 	err = PTR_ERR(index);
 	if (!IS_ERR(index))
 		err = ovl_cleanup(dir, index);
+	else
+		index = NULL;
+
 	inode_unlock(dir);
 	if (err)
 		goto fail;
@@ -557,3 +560,22 @@ void ovl_nlink_end(struct dentry *dentry, bool locked)
 		mutex_unlock(&OVL_I(d_inode(dentry))->lock);
 	}
 }
+
+int ovl_lock_rename_workdir(struct dentry *workdir, struct dentry *upperdir)
+{
+	/* Workdir should not be the same as upperdir */
+	if (workdir == upperdir)
+		goto err;
+
+	/* Workdir should not be subdir of upperdir and vice versa */
+	if (lock_rename(workdir, upperdir) != NULL)
+		goto err_unlock;
+
+	return 0;
+
+err_unlock:
+	unlock_rename(workdir, upperdir);
+err:
+	pr_err("overlayfs: failed to lock workdir+upperdir\n");
+	return -EIO;
+}
diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c
index ef4b48d1ea42..1c713fd5b3e6 100644
--- a/fs/userfaultfd.c
+++ b/fs/userfaultfd.c
@@ -588,6 +588,12 @@ static void userfaultfd_event_wait_completion(struct userfaultfd_ctx *ctx,
 			break;
 		if (ACCESS_ONCE(ctx->released) ||
 		    fatal_signal_pending(current)) {
+			/*
+			 * &ewq->wq may be queued in fork_event, but
+			 * __remove_wait_queue ignores the head
+			 * parameter. It would be a problem if it
+			 * didn't.
+			 */
 			__remove_wait_queue(&ctx->event_wqh, &ewq->wq);
 			if (ewq->msg.event == UFFD_EVENT_FORK) {
 				struct userfaultfd_ctx *new;
@@ -1061,6 +1067,12 @@ static ssize_t userfaultfd_ctx_read(struct userfaultfd_ctx *ctx, int no_wait,
 					(unsigned long)
 					uwq->msg.arg.reserved.reserved1;
 				list_move(&uwq->wq.entry, &fork_event);
+				/*
+				 * fork_nctx can be freed as soon as
+				 * we drop the lock, unless we take a
+				 * reference on it.
+				 */
+				userfaultfd_ctx_get(fork_nctx);
 				spin_unlock(&ctx->event_wqh.lock);
 				ret = 0;
 				break;
@@ -1091,19 +1103,53 @@ static ssize_t userfaultfd_ctx_read(struct userfaultfd_ctx *ctx, int no_wait,
 
 	if (!ret && msg->event == UFFD_EVENT_FORK) {
 		ret = resolve_userfault_fork(ctx, fork_nctx, msg);
+		spin_lock(&ctx->event_wqh.lock);
+		if (!list_empty(&fork_event)) {
+			/*
+			 * The fork thread didn't abort, so we can
+			 * drop the temporary refcount.
+			 */
+			userfaultfd_ctx_put(fork_nctx);
+
+			uwq = list_first_entry(&fork_event,
+					       typeof(*uwq),
+					       wq.entry);
+			/*
+			 * If fork_event list wasn't empty and in turn
+			 * the event wasn't already released by fork
+			 * (the event is allocated on fork kernel
+			 * stack), put the event back to its place in
+			 * the event_wq. fork_event head will be freed
+			 * as soon as we return so the event cannot
+			 * stay queued there no matter the current
+			 * "ret" value.
+			 */
+			list_del(&uwq->wq.entry);
+			__add_wait_queue(&ctx->event_wqh, &uwq->wq);
 
-		if (!ret) {
-			spin_lock(&ctx->event_wqh.lock);
-			if (!list_empty(&fork_event)) {
-				uwq = list_first_entry(&fork_event,
-						       typeof(*uwq),
-						       wq.entry);
-				list_del(&uwq->wq.entry);
-				__add_wait_queue(&ctx->event_wqh, &uwq->wq);
+			/*
+			 * Leave the event in the waitqueue and report
+			 * error to userland if we failed to resolve
+			 * the userfault fork.
+			 */
+			if (likely(!ret))
 				userfaultfd_event_complete(ctx, uwq);
-			}
-			spin_unlock(&ctx->event_wqh.lock);
+		} else {
+			/*
+			 * Here the fork thread aborted and the
+			 * refcount from the fork thread on fork_nctx
+			 * has already been released. We still hold
+			 * the reference we took before releasing the
+			 * lock above. If resolve_userfault_fork
+			 * failed we've to drop it because the
+			 * fork_nctx has to be freed in such case. If
+			 * it succeeded we'll hold it because the new
+			 * uffd references it.
+			 */
+			if (ret)
+				userfaultfd_ctx_put(fork_nctx);
 		}
+		spin_unlock(&ctx->event_wqh.lock);
 	}
 
 	return ret;
diff --git a/fs/xattr.c b/fs/xattr.c
index 4424f7fecf14..61cd28ba25f3 100644
--- a/fs/xattr.c
+++ b/fs/xattr.c
@@ -250,7 +250,7 @@ xattr_getsecurity(struct inode *inode, const char *name, void *value,
 	}
 	memcpy(value, buffer, len);
 out:
-	security_release_secctx(buffer, len);
+	kfree(buffer);
 out_noalloc:
 	return len;
 }
diff --git a/fs/xfs/xfs_bmap_util.c b/fs/xfs/xfs_bmap_util.c
index bc6c6e10a969..e9db7fc95b70 100644
--- a/fs/xfs/xfs_bmap_util.c
+++ b/fs/xfs/xfs_bmap_util.c
@@ -2122,11 +2122,31 @@ xfs_swap_extents(
 		ip->i_d.di_flags2 |= tip->i_d.di_flags2 & XFS_DIFLAG2_REFLINK;
 		tip->i_d.di_flags2 &= ~XFS_DIFLAG2_REFLINK;
 		tip->i_d.di_flags2 |= f & XFS_DIFLAG2_REFLINK;
+	}
+
+	/* Swap the cow forks. */
+	if (xfs_sb_version_hasreflink(&mp->m_sb)) {
+		xfs_extnum_t	extnum;
+
+		ASSERT(ip->i_cformat == XFS_DINODE_FMT_EXTENTS);
+		ASSERT(tip->i_cformat == XFS_DINODE_FMT_EXTENTS);
+
+		extnum = ip->i_cnextents;
+		ip->i_cnextents = tip->i_cnextents;
+		tip->i_cnextents = extnum;
+
 		cowfp = ip->i_cowfp;
 		ip->i_cowfp = tip->i_cowfp;
 		tip->i_cowfp = cowfp;
-		xfs_inode_set_cowblocks_tag(ip);
-		xfs_inode_set_cowblocks_tag(tip);
+
+		if (ip->i_cowfp && ip->i_cnextents)
+			xfs_inode_set_cowblocks_tag(ip);
+		else
+			xfs_inode_clear_cowblocks_tag(ip);
+		if (tip->i_cowfp && tip->i_cnextents)
+			xfs_inode_set_cowblocks_tag(tip);
+		else
+			xfs_inode_clear_cowblocks_tag(tip);
 	}
 
 	xfs_trans_log_inode(tp, ip,  src_log_flags);
diff --git a/fs/xfs/xfs_reflink.c b/fs/xfs/xfs_reflink.c
index 3246815c24d6..37e603bf1591 100644
--- a/fs/xfs/xfs_reflink.c
+++ b/fs/xfs/xfs_reflink.c
@@ -736,7 +736,13 @@ xfs_reflink_end_cow(
 	/* If there is a hole at end_fsb - 1 go to the previous extent */
 	if (!xfs_iext_lookup_extent(ip, ifp, end_fsb - 1, &idx, &got) ||
 	    got.br_startoff > end_fsb) {
-		ASSERT(idx > 0);
+		/*
+		 * In case of racing, overlapping AIO writes no COW extents
+		 * might be left by the time I/O completes for the loser of
+		 * the race.  In that case we are done.
+		 */
+		if (idx <= 0)
+			goto out_cancel;
 		xfs_iext_get_extent(ifp, --idx, &got);
 	}
 
@@ -809,6 +815,7 @@ next_extent:
 
 out_defer:
 	xfs_defer_cancel(&dfops);
+out_cancel:
 	xfs_trans_cancel(tp);
 	xfs_iunlock(ip, XFS_ILOCK_EXCL);
 out: