@@ -22,6 +22,10 @@
#include "scrub/dabtree.h"
#include "scrub/readdir.h"
#include "scrub/repair.h"
+#include "scrub/trace.h"
+#include "scrub/xfile.h"
+#include "scrub/xfarray.h"
+#include "scrub/xfblob.h"
/* Set us up to scrub directories. */
int
@@ -41,6 +45,18 @@ xchk_setup_directory(
/* Directories */
+/* Deferred directory entry that we saved for later. */
+struct xchk_dirent {
+ /* Cookie for retrieval of the dirent name. */
+ xfblob_cookie name_cookie;
+
+ /* Child inode number. */
+ xfs_ino_t ino;
+
+ /* Length of the pptr name. */
+ uint8_t namelen;
+};
+
struct xchk_dir {
struct xfs_scrub *sc;
@@ -50,6 +66,15 @@ struct xchk_dir {
/* xattr key and da args for parent pointer validation. */
struct xfs_parent_scratch pptr_scratch;
+ /* Fixed-size array of xchk_dirent structures. */
+ struct xfarray *dir_entries;
+
+ /* Blobs containing dirent names. */
+ struct xfblob *dir_names;
+
+ /* If we've cycled the ILOCK, we must revalidate deferred dirents. */
+ bool need_revalidate;
+
/* Name buffer for dirent revalidation. */
uint8_t namebuf[MAXNAMELEN];
@@ -150,8 +175,24 @@ xchk_dir_check_pptr_fast(
/* Try to lock the inode. */
lockmode = xchk_dir_lock_child(sc, ip);
if (!lockmode) {
- xchk_set_incomplete(sc);
- return -ECANCELED;
+ struct xchk_dirent save_de = {
+ .namelen = name->len,
+ .ino = ip->i_ino,
+ };
+
+ /* Couldn't lock the inode, so save the dirent for later. */
+ trace_xchk_dir_defer(sc->ip, name->name, name->len, ip->i_ino);
+
+ error = xfblob_store(sd->dir_names, &save_de.name_cookie,
+ name->name, name->len);
+ if (xchk_fblock_process_error(sc, XFS_DATA_FORK, 0, &error))
+ return error;
+
+ error = xfarray_append(sd->dir_entries, &save_de);
+ if (xchk_fblock_process_error(sc, XFS_DATA_FORK, 0, &error))
+ return error;
+
+ return 0;
}
error = xchk_dir_parent_pointer(sd, name, ip);
@@ -861,6 +902,156 @@ xchk_directory_blocks(
return error;
}
+/*
+ * Revalidate a dirent that we collected in the past but couldn't check because
+ * of lock contention. Returns 0 if the dirent is still valid, -ENOENT if it
+ * has gone away on us, or a negative errno.
+ */
+STATIC int
+xchk_dir_revalidate_dirent(
+ struct xchk_dir *sd,
+ const struct xfs_name *xname,
+ xfs_ino_t ino)
+{
+ struct xfs_scrub *sc = sd->sc;
+ xfs_ino_t child_ino;
+ int error;
+
+ /*
+ * Look up the directory entry. If we get -ENOENT, the directory entry
+ * went away and there's nothing to revalidate. Return any other
+ * error.
+ */
+ error = xchk_dir_lookup(sc, sc->ip, xname, &child_ino);
+ if (error)
+ return error;
+
+ /* The inode number changed, nothing to revalidate. */
+ if (ino != child_ino)
+ return -ENOENT;
+
+ return 0;
+}
+
+/*
+ * Check a directory entry's parent pointers the slow way, which means we cycle
+ * locks a bunch and put up with revalidation until we get it done.
+ */
+STATIC int
+xchk_dir_slow_dirent(
+ struct xchk_dir *sd,
+ struct xchk_dirent *dirent)
+{
+ struct xfs_name xname = {
+ .name = sd->namebuf,
+ .len = dirent->namelen,
+ };
+ struct xfs_scrub *sc = sd->sc;
+ struct xfs_inode *ip;
+ unsigned int lockmode;
+ int error;
+
+ /* Check that the deferred dirent still exists. */
+ if (sd->need_revalidate) {
+ error = xchk_dir_revalidate_dirent(sd, &xname, dirent->ino);
+ if (error == -ENOENT)
+ return 0;
+ if (!xchk_fblock_xref_process_error(sc, XFS_DATA_FORK, 0,
+ &error))
+ return error;
+ }
+
+ error = xchk_iget(sc, dirent->ino, &ip);
+ if (error == -EINVAL || error == -ENOENT) {
+ xchk_fblock_set_corrupt(sc, XFS_ATTR_FORK, 0);
+ return 0;
+ }
+ if (!xchk_fblock_xref_process_error(sc, XFS_ATTR_FORK, 0, &error))
+ return error;
+
+ /*
+ * If we can grab both IOLOCK and ILOCK of the alleged child, we can
+ * proceed with the validation.
+ */
+ lockmode = xchk_dir_lock_child(sc, ip);
+ if (lockmode)
+ goto check_pptr;
+
+ /*
+ * We couldn't lock the child file. Drop all the locks and try to
+ * get them again, one at a time.
+ */
+ xchk_iunlock(sc, sc->ilock_flags);
+ sd->need_revalidate = true;
+
+ trace_xchk_dir_slowpath(sc->ip, xname.name, xname.len, ip->i_ino);
+
+ while (true) {
+ xchk_ilock(sc, XFS_IOLOCK_EXCL);
+ if (xfs_ilock_nowait(ip, XFS_IOLOCK_SHARED)) {
+ xchk_ilock(sc, XFS_ILOCK_EXCL);
+ if (xfs_ilock_nowait(ip, XFS_ILOCK_EXCL)) {
+ break;
+ }
+ xchk_iunlock(sc, XFS_ILOCK_EXCL);
+ }
+ xchk_iunlock(sc, XFS_IOLOCK_EXCL);
+
+ if (xchk_should_terminate(sc, &error))
+ goto out_rele;
+
+ delay(1);
+ }
+ lockmode = XFS_IOLOCK_SHARED | XFS_ILOCK_EXCL;
+
+ /* Revalidate, since we just cycled the locks. */
+ error = xchk_dir_revalidate_dirent(sd, &xname, dirent->ino);
+ if (error == -ENOENT)
+ goto out_unlock;
+ if (!xchk_fblock_xref_process_error(sc, XFS_DATA_FORK, 0, &error))
+ goto out_unlock;
+
+check_pptr:
+ error = xchk_dir_parent_pointer(sd, &xname, ip);
+out_unlock:
+ xfs_iunlock(ip, lockmode);
+out_rele:
+ xchk_irele(sc, ip);
+ return error;
+}
+
+/* Check all the dirents that we deferred the first time around. */
+STATIC int
+xchk_dir_finish_slow_dirents(
+ struct xchk_dir *sd)
+{
+ xfarray_idx_t array_cur;
+ int error;
+
+ foreach_xfarray_idx(sd->dir_entries, array_cur) {
+ struct xchk_dirent dirent;
+
+ if (sd->sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT)
+ return 0;
+
+ error = xfarray_load(sd->dir_entries, array_cur, &dirent);
+ if (error)
+ return error;
+
+ error = xfblob_load(sd->dir_names, dirent.name_cookie,
+ sd->namebuf, dirent.namelen);
+ if (error)
+ return error;
+ sd->namebuf[MAXNAMELEN - 1] = 0;
+
+ error = xchk_dir_slow_dirent(sd, &dirent);
+ if (error)
+ return error;
+ }
+
+ return 0;
+}
+
/* Scrub a whole directory. */
int
xchk_directory(
@@ -899,11 +1090,41 @@ xchk_directory(
return -ENOMEM;
sd->sc = sc;
+ if (xfs_has_parent(sc->mp)) {
+ /*
+ * Set up some staging memory for dirents that we can't check
+ * due to locking contention.
+ */
+ error = xfarray_create(sc->mp, "directory entries", 0,
+ sizeof(struct xchk_dirent), &sd->dir_entries);
+ if (error)
+ goto out_sd;
+
+ error = xfblob_create(sc->mp, "dirent names", &sd->dir_names);
+ if (error)
+ goto out_entries;
+ }
+
/* Look up every name in this directory by hash. */
error = xchk_dir_walk(sc, sc->ip, xchk_dir_actor, sd);
if (error == -ECANCELED)
error = 0;
+ if (error)
+ goto out_names;
+ if (xfs_has_parent(sc->mp)) {
+ error = xchk_dir_finish_slow_dirents(sd);
+ if (error)
+ goto out_names;
+ }
+
+out_names:
+ if (sd->dir_names)
+ xfblob_destroy(sd->dir_names);
+out_entries:
+ if (sd->dir_entries)
+ xfarray_destroy(sd->dir_entries);
+out_sd:
kvfree(sd);
return error;
}
@@ -987,6 +987,8 @@ DEFINE_EVENT(xchk_pptr_class, name, \
TP_ARGS(ip, name, namelen, parent_ino))
DEFINE_XCHK_PPTR_CLASS(xchk_parent_defer);
DEFINE_XCHK_PPTR_CLASS(xchk_parent_slowpath);
+DEFINE_XCHK_PPTR_CLASS(xchk_dir_defer);
+DEFINE_XCHK_PPTR_CLASS(xchk_dir_slowpath);
/* repair tracepoints */
#if IS_ENABLED(CONFIG_XFS_ONLINE_REPAIR)