From d208bbdda991b8808d9c033ce4d31cb1bd87dcfc Mon Sep 17 00:00:00 2001 From: Nick Piggin Date: Mon, 21 Dec 2009 16:28:53 -0800 Subject: fs: improve remount,ro vs buffercache coherency Invalidate sb->s_bdev on remount,ro. Fixes a problem reported by Jorge Boncompte who is seeing corruption trying to snapshot a minix filesystem image. Some filesystems modify their metadata via a path other than the bdev buffer cache (eg. they may use a private linear mapping for their metadata, or implement directories in pagecache, etc). Also, file data modifications usually go to the bdev via their own mappings. These updates are not coherent with buffercache IO (eg. via /dev/bdev) and never have been. However there could be a reasonable expectation that after a mount -oremount,ro operation then the buffercache should subsequently be coherent with previous filesystem modifications. So invalidate the bdev mappings on a remount,ro operation to provide a coherency point. The problem was exposed when we switched the old rd to brd because old rd didn't really function like a normal block device and updates to rd via mappings other than the buffercache would still end up going into its buffercache. But the same problem has always affected other "normal" block devices, including loop. [akpm@linux-foundation.org: repair comment layout] Reported-by: "Jorge Boncompte [DTI2]" Tested-by: "Jorge Boncompte [DTI2]" Signed-off-by: Nick Piggin Cc: Al Viro Signed-off-by: Andrew Morton Signed-off-by: Al Viro --- fs/super.c | 18 +++++++++++++++--- 1 file changed, 15 insertions(+), 3 deletions(-) diff --git a/fs/super.c b/fs/super.c index aff046b0fe78..903896ec7c73 100644 --- a/fs/super.c +++ b/fs/super.c @@ -568,7 +568,7 @@ out: int do_remount_sb(struct super_block *sb, int flags, void *data, int force) { int retval; - int remount_rw; + int remount_rw, remount_ro; if (sb->s_frozen != SB_UNFROZEN) return -EBUSY; @@ -583,9 +583,12 @@ int do_remount_sb(struct super_block *sb, int flags, void *data, int force) shrink_dcache_sb(sb); sync_filesystem(sb); + remount_ro = (flags & MS_RDONLY) && !(sb->s_flags & MS_RDONLY); + remount_rw = !(flags & MS_RDONLY) && (sb->s_flags & MS_RDONLY); + /* If we are remounting RDONLY and current sb is read/write, make sure there are no rw files opened */ - if ((flags & MS_RDONLY) && !(sb->s_flags & MS_RDONLY)) { + if (remount_ro) { if (force) mark_files_ro(sb); else if (!fs_may_remount_ro(sb)) @@ -594,7 +597,6 @@ int do_remount_sb(struct super_block *sb, int flags, void *data, int force) if (retval < 0 && retval != -ENOSYS) return -EBUSY; } - remount_rw = !(flags & MS_RDONLY) && (sb->s_flags & MS_RDONLY); if (sb->s_op->remount_fs) { retval = sb->s_op->remount_fs(sb, &flags, data); @@ -604,6 +606,16 @@ int do_remount_sb(struct super_block *sb, int flags, void *data, int force) sb->s_flags = (sb->s_flags & ~MS_RMT_MASK) | (flags & MS_RMT_MASK); if (remount_rw) vfs_dq_quota_on_remount(sb); + /* + * Some filesystems modify their metadata via some other path than the + * bdev buffer cache (eg. use a private mapping, or directories in + * pagecache, etc). Also file data modifications go via their own + * mappings. So If we try to mount readonly then copy the filesystem + * from bdev, we could get stale data, so invalidate it to give a best + * effort at coherency. + */ + if (remount_ro && sb->s_bdev) + invalidate_bdev(sb->s_bdev); return 0; } -- cgit v1.2.1