[PATCH v3 06/33] ext2: don't set SB_RDONLY after filesystem errors

[Christian Brauner <brauner@kernel.org>]

With errors=remount-ro ext2_error() sets SB_RDONLY from whatever context
hit the error and without holding s_umount. That races with everyone
else changing sb->s_flags and it breaks freezing. If it happens while
the filesystem is frozen thaw_super() sees a read-only superblock and
leaves the s_writers rwsems locked so every writer hangs. A lookup in a
corrupted directory is enough. Karl proposed teaching thaw_super() about
it but Jan preferred fixing the filesystems (cf. [1]) like ext4 and f2fs
already did.

So call sb_set_emergency_ro() instead and let the VFS refuse
modifications. ext2 still refuses allocations and ext2_xattr_set()
itself, ecryptfs calls the latter without write access on the lower
mount. Unlinked inodes are left to e2fsck. ext2_write_inode() keeps
working because writeback still writes data, bitmaps, indirect and
directory blocks after the error and they'd be lost without the inode.
A thaw after an error while frozen still writes the superblock but
EXT2_ERROR_FS stays set in it.

After a remount to read-only a remount to read-write fails until umount.
A plain remount to read-write right after the error succeeds but the
filesystem stays read-only. Writes through file descriptors opened
before the error fail with EROFS.

[1]: https://lore.kernel.org/r/hyhuckyohsabx2suvq3z7uy3pbgmihva6wgzxr3op7pzcrlu33@p7zzlgp2ehjf

Reported-by: Karl Mehltretter <kmehltretter@gmail.com>
Link: https://lore.kernel.org/r/20260903060855.4610-1-kmehltretter@gmail.com
Signed-off-by: Christian Brauner (Amutable) <brauner@kernel.org>
---
 fs/ext2/balloc.c |  5 +++++
 fs/ext2/ialloc.c |  2 ++
 fs/ext2/inode.c  |  4 +++-
 fs/ext2/super.c  | 13 ++++++++-----
 fs/ext2/xattr.c  |  2 ++
 5 files changed, 20 insertions(+), 6 deletions(-)

diff --git a/fs/ext2/balloc.c b/fs/ext2/balloc.c
index 80acc1e193871..77f2ed5a76a28 100644
--- a/fs/ext2/balloc.c
+++ b/fs/ext2/balloc.c
@@ -1236,6 +1236,11 @@ ext2_fsblk_t ext2_new_blocks(struct inode *inode, ext2_fsblk_t goal,
 	*errp = -ENOSPC;
 	sb = inode->i_sb;
 
+	if (sb_emergency_ro(sb)) {
+		*errp = -EROFS;
+		return 0;
+	}
+
 	/*
 	 * Check quota for allocation of this block.
 	 */
diff --git a/fs/ext2/ialloc.c b/fs/ext2/ialloc.c
index bf21b57cf98cd..2741ecd2b94fc 100644
--- a/fs/ext2/ialloc.c
+++ b/fs/ext2/ialloc.c
@@ -433,6 +433,8 @@ struct inode *ext2_new_inode(struct inode *dir, umode_t mode,
 	int err;
 
 	sb = dir->i_sb;
+	if (sb_emergency_ro(sb))
+		return ERR_PTR(-EROFS);
 	inode = new_inode(sb);
 	if (!inode)
 		return ERR_PTR(-ENOMEM);
diff --git a/fs/ext2/inode.c b/fs/ext2/inode.c
index 12ac4cfe15003..dd28637c60737 100644
--- a/fs/ext2/inode.c
+++ b/fs/ext2/inode.c
@@ -71,7 +71,9 @@ void ext2_evict_inode(struct inode * inode)
 	struct ext2_block_alloc_info *rsv;
 	int want_delete = 0;
 
-	if (!inode->i_nlink && !is_bad_inode(inode)) {
+	/* After an error made us read-only the inode is left to e2fsck. */
+	if (!inode->i_nlink && !is_bad_inode(inode) &&
+	    !sb_emergency_ro(inode->i_sb)) {
 		want_delete = 1;
 		dquot_initialize(inode);
 	} else {
diff --git a/fs/ext2/super.c b/fs/ext2/super.c
index fb217ef2d69f0..10d5165459749 100644
--- a/fs/ext2/super.c
+++ b/fs/ext2/super.c
@@ -53,7 +53,7 @@ void ext2_error(struct super_block *sb, const char *function,
 	struct ext2_sb_info *sbi = EXT2_SB(sb);
 	struct ext2_super_block *es = sbi->s_es;
 
-	if (!sb_rdonly(sb)) {
+	if (!sb_rdonly_any(sb)) {
 		spin_lock(&sbi->s_lock);
 		sbi->s_mount_state |= EXT2_ERROR_FS;
 		es->s_state |= cpu_to_le16(EXT2_ERROR_FS);
@@ -73,11 +73,11 @@ void ext2_error(struct super_block *sb, const char *function,
 
 	if (test_opt(sb, ERRORS_PANIC))
 		panic("EXT2-fs: panic from previous error\n");
-	if (!sb_rdonly(sb) && test_opt(sb, ERRORS_RO)) {
+	/* SB_RDONLY needs s_umount, see sb_set_emergency_ro(). */
+	if (!sb_rdonly(sb) && test_opt(sb, ERRORS_RO) &&
+	    sb_set_emergency_ro(sb))
 		ext2_msg(sb, KERN_CRIT,
 			     "error: remounting filesystem read-only");
-		sb->s_flags |= SB_RDONLY;
-	}
 }
 
 static void ext2_msg_fc(struct fs_context *fc, const char *prefix,
@@ -179,7 +179,7 @@ static void ext2_put_super (struct super_block * sb)
 	ext2_xattr_destroy_cache(sbi->s_ea_block_cache);
 	sbi->s_ea_block_cache = NULL;
 
-	if (!sb_rdonly(sb)) {
+	if (!sb_rdonly_any(sb)) {
 		struct ext2_super_block *es = sbi->s_es;
 
 		spin_lock(&sbi->s_lock);
@@ -1360,6 +1360,9 @@ static int ext2_reconfigure(struct fs_context *fc)
 	if ((bool)(flags & SB_RDONLY) == sb_rdonly(sb))
 		goto out_set;
 	if (flags & SB_RDONLY) {
+		/* After an error nothing may be written, just go read-only. */
+		if (sb_emergency_ro(sb))
+			goto out_set;
 		if (le16_to_cpu(es->s_state) & EXT2_VALID_FS ||
 		    !(sbi->s_mount_state & EXT2_VALID_FS))
 			goto out_set;
diff --git a/fs/ext2/xattr.c b/fs/ext2/xattr.c
index 8f608930a48c6..12dfffff189cb 100644
--- a/fs/ext2/xattr.c
+++ b/fs/ext2/xattr.c
@@ -429,6 +429,8 @@ ext2_xattr_set(struct inode *inode, int name_index, const char *name,
 	ea_idebug(inode, "name=%d.%s, value=%p, value_len=%ld",
 		  name_index, name, value, (long)value_len);
 
+	if (sb_emergency_ro(sb))
+		return -EROFS;
 	if (value == NULL)
 		value_len = 0;
 	if (name == NULL)

-- 
2.53.0