xfs: fix scrub and remount-ro protection when running scrub

While running a new fstest that races a readonly remount with scrub
running in repair mode, I observed the kernel tripping over debugging
assertions in the log quiesce code that were checking that the CIL was
empty.  When the sysadmin runs scrub in repair mode, the scrub code
allocates real transactions (with reservations) to change things, but
doesn't increment the superblock writers count to block a readonly
remount attempt while it is running.

We don't require the userspace caller to have a writable file descriptor
to run repairs, so we have to call mnt_want_write_file to obtain freeze
protection and increment the writers count.  It's ok to remove the call
to sb_start_write for the dry-run case because commit 8321ddb2fa29
removed the behavior where scrub and fsfreeze fight over the buffer LRU.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
Reviewed-by: Chandan Babu R <chandanrlinux@gmail.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>

diff --git a/fs/xfs/scrub/scrub.c b/fs/xfs/scrub/scrub.c
index 47c68c72bcac87d9b061757d080031c18861e5ee..21ebd3f4af9f33fdfd529b1c283f7fadd4707371 100644 (file)
--- a/fs/xfs/scrub/scrub.c
+++ b/fs/xfs/scrub/scrub.c
@@ -149,9 +149,10 @@ xchk_probe(
 STATIC int
 xchk_teardown(
        struct xfs_scrub        *sc,
-       struct xfs_inode        *ip_in,
        int                     error)
 {
+       struct xfs_inode        *ip_in = XFS_I(file_inode(sc->file));
+
        xchk_ag_free(sc, &sc->sa);
        if (sc->tp) {
                if (error == 0 && (sc->sm->sm_flags & XFS_SCRUB_IFLAG_REPAIR))
@@ -168,7 +169,8 @@ xchk_teardown(
                        xfs_irele(sc->ip);
                sc->ip = NULL;
        }
-       sb_end_write(sc->mp->m_super);
+       if (sc->sm->sm_flags & XFS_SCRUB_IFLAG_REPAIR)
+               mnt_drop_write_file(sc->file);
        if (sc->flags & XCHK_REAPING_DISABLED)
                xchk_start_reaping(sc);
        if (sc->flags & XCHK_HAS_QUOTAOFFLOCK) {
@@ -456,19 +458,22 @@ static inline void xchk_postmortem(struct xfs_scrub *sc)
 /* Dispatch metadata scrubbing. */
 int
 xfs_scrub_metadata(
-       struct xfs_inode                *ip,
+       struct file                     *file,
        struct xfs_scrub_metadata       *sm)
 {
        struct xfs_scrub                sc = {
-               .mp                     = ip->i_mount,
+               .file                   = file,
                .sm                     = sm,
                .sa                     = {
                        .agno           = NULLAGNUMBER,
                },
        };
+       struct xfs_inode                *ip = XFS_I(file_inode(file));
        struct xfs_mount                *mp = ip->i_mount;
        int                             error = 0;
 
+       sc.mp = mp;
+
        BUILD_BUG_ON(sizeof(meta_scrub_ops) !=
                (sizeof(struct xchk_meta_ops) * XFS_SCRUB_TYPE_NR));
 
@@ -492,12 +497,14 @@ xfs_scrub_metadata(
        sc.sick_mask = xchk_health_mask_for_scrub_type(sm->sm_type);
 retry_op:
        /*
-        * If freeze runs concurrently with a scrub, the freeze can be delayed
-        * indefinitely as we walk the filesystem and iterate over metadata
-        * buffers.  Freeze quiesces the log (which waits for the buffer LRU to
-        * be emptied) and that won't happen while checking is running.
+        * When repairs are allowed, prevent freezing or readonly remount while
+        * scrub is running with a real transaction.
         */
-       sb_start_write(mp->m_super);
+       if (sm->sm_flags & XFS_SCRUB_IFLAG_REPAIR) {
+               error = mnt_want_write_file(sc.file);
+               if (error)
+                       goto out;
+       }
 
        /* Set up for the operation. */
        error = sc.ops->setup(&sc, ip);
@@ -512,7 +519,7 @@ retry_op:
                 * Tear down everything we hold, then set up again with
                 * preparation for worst-case scenarios.
                 */
-               error = xchk_teardown(&sc, ip, 0);
+               error = xchk_teardown(&sc, 0);
                if (error)
                        goto out;
                sc.flags |= XCHK_TRY_HARDER;
@@ -553,7 +560,7 @@ retry_op:
                         * get all the resources it needs; either way, we go
                         * back to the beginning and call the scrub function.
                         */
-                       error = xchk_teardown(&sc, ip, 0);
+                       error = xchk_teardown(&sc, 0);
                        if (error) {
                                xrep_failure(mp);
                                goto out;
@@ -565,7 +572,7 @@ retry_op:
 out_nofix:
        xchk_postmortem(&sc);
 out_teardown:
-       error = xchk_teardown(&sc, ip, error);
+       error = xchk_teardown(&sc, error);
 out:
        trace_xchk_done(ip, sm, error);
        if (error == -EFSCORRUPTED || error == -EFSBADCRC) {

diff --git a/fs/xfs/scrub/scrub.h b/fs/xfs/scrub/scrub.h
index ad1ceb44a628570f122849cc357f9d0d23ecac98..e776ab4ad3223964a8333e55cb1f6d028cbabc54 100644 (file)
--- a/fs/xfs/scrub/scrub.h
+++ b/fs/xfs/scrub/scrub.h
@@ -59,7 +59,18 @@ struct xfs_scrub {
        struct xfs_scrub_metadata       *sm;
        const struct xchk_meta_ops      *ops;
        struct xfs_trans                *tp;
+
+       /* File that scrub was called with. */
+       struct file                     *file;
+
+       /*
+        * File that is undergoing the scrub operation.  This can differ from
+        * the file that scrub was called with if we're checking file-based fs
+        * metadata (e.g. rt bitmaps) or if we're doing a scrub-by-handle for
+        * something that can't be opened directly (e.g. symlinks).
+        */
        struct xfs_inode                *ip;
+
        void                            *buf;
        uint                            ilock_flags;
 

diff --git a/fs/xfs/scrub/xfs_scrub.h b/fs/xfs/scrub/xfs_scrub.h
index 2897ba3a17e62b6fc33962cc06aca71fb80c85be..2ceae614ade86fffde425af9c76a4b23c4d035e1 100644 (file)
--- a/fs/xfs/scrub/xfs_scrub.h
+++ b/fs/xfs/scrub/xfs_scrub.h
@@ -7,9 +7,9 @@
 #define __XFS_SCRUB_H__
 
 #ifndef CONFIG_XFS_ONLINE_SCRUB
-# define xfs_scrub_metadata(ip, sm)    (-ENOTTY)
+# define xfs_scrub_metadata(file, sm)  (-ENOTTY)
 #else
-int xfs_scrub_metadata(struct xfs_inode *ip, struct xfs_scrub_metadata *sm);
+int xfs_scrub_metadata(struct file *file, struct xfs_scrub_metadata *sm);
 #endif /* CONFIG_XFS_ONLINE_SCRUB */
 
 #endif /* __XFS_SCRUB_H__ */

diff --git a/fs/xfs/xfs_ioctl.c b/fs/xfs/xfs_ioctl.c
index e6e4e248cd86229bc1b8920f10410113737f5f03..708b77341a703fbf3aa462d7121ea92a8d6eb6be 100644 (file)
--- a/fs/xfs/xfs_ioctl.c
+++ b/fs/xfs/xfs_ioctl.c
@@ -1847,7 +1847,7 @@ out_free:
 
 STATIC int
 xfs_ioc_scrub_metadata(
-       struct xfs_inode                *ip,
+       struct file                     *file,
        void                            __user *arg)
 {
        struct xfs_scrub_metadata       scrub;
@@ -1859,7 +1859,7 @@ xfs_ioc_scrub_metadata(
        if (copy_from_user(&scrub, arg, sizeof(scrub)))
                return -EFAULT;
 
-       error = xfs_scrub_metadata(ip, &scrub);
+       error = xfs_scrub_metadata(file, &scrub);
        if (error)
                return error;
 
@@ -2158,7 +2158,7 @@ xfs_file_ioctl(
                return xfs_ioc_getfsmap(ip, arg);
 
        case XFS_IOC_SCRUB_METADATA:
-               return xfs_ioc_scrub_metadata(ip, arg);
+               return xfs_ioc_scrub_metadata(filp, arg);
 
        case XFS_IOC_FD_TO_HANDLE:
        case XFS_IOC_PATH_TO_HANDLE: