summaryrefslogtreecommitdiffstats
path: root/fs/xfs/scrub
diff options
context:
space:
mode:
Diffstat (limited to 'fs/xfs/scrub')
-rw-r--r--fs/xfs/scrub/agheader.c43
-rw-r--r--fs/xfs/scrub/agheader_repair.c879
-rw-r--r--fs/xfs/scrub/agino_bitmap.h49
-rw-r--r--fs/xfs/scrub/alloc_repair.c2
-rw-r--r--fs/xfs/scrub/attr.c214
-rw-r--r--fs/xfs/scrub/attr.h7
-rw-r--r--fs/xfs/scrub/attr_repair.c1663
-rw-r--r--fs/xfs/scrub/attr_repair.h15
-rw-r--r--fs/xfs/scrub/bitmap.c22
-rw-r--r--fs/xfs/scrub/common.c41
-rw-r--r--fs/xfs/scrub/common.h27
-rw-r--r--fs/xfs/scrub/dab_bitmap.h37
-rw-r--r--fs/xfs/scrub/dabtree.c24
-rw-r--r--fs/xfs/scrub/dabtree.h3
-rw-r--r--fs/xfs/scrub/dir.c377
-rw-r--r--fs/xfs/scrub/dir_repair.c1958
-rw-r--r--fs/xfs/scrub/dirtree.c985
-rw-r--r--fs/xfs/scrub/dirtree.h178
-rw-r--r--fs/xfs/scrub/dirtree_repair.c821
-rw-r--r--fs/xfs/scrub/findparent.c454
-rw-r--r--fs/xfs/scrub/findparent.h56
-rw-r--r--fs/xfs/scrub/fscounters.c14
-rw-r--r--fs/xfs/scrub/fscounters.h1
-rw-r--r--fs/xfs/scrub/fscounters_repair.c12
-rw-r--r--fs/xfs/scrub/health.c1
-rw-r--r--fs/xfs/scrub/ino_bitmap.h37
-rw-r--r--fs/xfs/scrub/inode.c19
-rw-r--r--fs/xfs/scrub/inode_repair.c153
-rw-r--r--fs/xfs/scrub/iscan.c67
-rw-r--r--fs/xfs/scrub/iscan.h16
-rw-r--r--fs/xfs/scrub/listxattr.c320
-rw-r--r--fs/xfs/scrub/listxattr.h19
-rw-r--r--fs/xfs/scrub/nlinks.c133
-rw-r--r--fs/xfs/scrub/nlinks.h7
-rw-r--r--fs/xfs/scrub/nlinks_repair.c186
-rw-r--r--fs/xfs/scrub/orphanage.c627
-rw-r--r--fs/xfs/scrub/orphanage.h86
-rw-r--r--fs/xfs/scrub/parent.c700
-rw-r--r--fs/xfs/scrub/parent_repair.c1612
-rw-r--r--fs/xfs/scrub/quota_repair.c6
-rw-r--r--fs/xfs/scrub/readdir.c140
-rw-r--r--fs/xfs/scrub/readdir.h3
-rw-r--r--fs/xfs/scrub/reap.c445
-rw-r--r--fs/xfs/scrub/reap.h21
-rw-r--r--fs/xfs/scrub/repair.c127
-rw-r--r--fs/xfs/scrub/repair.h31
-rw-r--r--fs/xfs/scrub/rmap_repair.c24
-rw-r--r--fs/xfs/scrub/rtbitmap_repair.c2
-rw-r--r--fs/xfs/scrub/rtsummary.c33
-rw-r--r--fs/xfs/scrub/rtsummary.h37
-rw-r--r--fs/xfs/scrub/rtsummary_repair.c175
-rw-r--r--fs/xfs/scrub/scrub.c310
-rw-r--r--fs/xfs/scrub/scrub.h91
-rw-r--r--fs/xfs/scrub/stats.c1
-rw-r--r--fs/xfs/scrub/symlink.c13
-rw-r--r--fs/xfs/scrub/symlink_repair.c509
-rw-r--r--fs/xfs/scrub/tempexch.h22
-rw-r--r--fs/xfs/scrub/tempfile.c851
-rw-r--r--fs/xfs/scrub/tempfile.h48
-rw-r--r--fs/xfs/scrub/trace.c6
-rw-r--r--fs/xfs/scrub/trace.h1317
-rw-r--r--fs/xfs/scrub/xfarray.c36
-rw-r--r--fs/xfs/scrub/xfarray.h6
-rw-r--r--fs/xfs/scrub/xfblob.c168
-rw-r--r--fs/xfs/scrub/xfblob.h50
-rw-r--r--fs/xfs/scrub/xfile.c14
-rw-r--r--fs/xfs/scrub/xfile.h6
-rw-r--r--fs/xfs/scrub/xfs_scrub.h6
68 files changed, 15895 insertions, 468 deletions
diff --git a/fs/xfs/scrub/agheader.c b/fs/xfs/scrub/agheader.c
index e954f07679..f8e5b67128 100644
--- a/fs/xfs/scrub/agheader.c
+++ b/fs/xfs/scrub/agheader.c
@@ -15,6 +15,7 @@
#include "xfs_ialloc.h"
#include "xfs_rmap.h"
#include "xfs_ag.h"
+#include "xfs_inode.h"
#include "scrub/scrub.h"
#include "scrub/common.h"
@@ -165,8 +166,7 @@ xchk_superblock(
xchk_block_set_corrupt(sc, bp);
/* Check sb_versionnum bits that are set at mkfs time. */
- vernum_mask = cpu_to_be16(~XFS_SB_VERSION_OKBITS |
- XFS_SB_VERSION_NUMBITS |
+ vernum_mask = cpu_to_be16(XFS_SB_VERSION_NUMBITS |
XFS_SB_VERSION_ALIGNBIT |
XFS_SB_VERSION_DALIGNBIT |
XFS_SB_VERSION_SHAREDBIT |
@@ -865,6 +865,43 @@ xchk_agi_xref(
/* scrub teardown will take care of sc->sa for us */
}
+/*
+ * Check the unlinked buckets for links to bad inodes. We hold the AGI, so
+ * there cannot be any threads updating unlinked list pointers in this AG.
+ */
+STATIC void
+xchk_iunlink(
+ struct xfs_scrub *sc,
+ struct xfs_agi *agi)
+{
+ unsigned int i;
+ struct xfs_inode *ip;
+
+ for (i = 0; i < XFS_AGI_UNLINKED_BUCKETS; i++) {
+ xfs_agino_t agino = be32_to_cpu(agi->agi_unlinked[i]);
+
+ while (agino != NULLAGINO) {
+ if (agino % XFS_AGI_UNLINKED_BUCKETS != i) {
+ xchk_block_set_corrupt(sc, sc->sa.agi_bp);
+ return;
+ }
+
+ ip = xfs_iunlink_lookup(sc->sa.pag, agino);
+ if (!ip) {
+ xchk_block_set_corrupt(sc, sc->sa.agi_bp);
+ return;
+ }
+
+ if (!xfs_inode_on_unlinked_list(ip)) {
+ xchk_block_set_corrupt(sc, sc->sa.agi_bp);
+ return;
+ }
+
+ agino = ip->i_next_unlinked;
+ }
+ }
+}
+
/* Scrub the AGI. */
int
xchk_agi(
@@ -949,6 +986,8 @@ xchk_agi(
if (pag->pagi_freecount != be32_to_cpu(agi->agi_freecount))
xchk_block_set_corrupt(sc, sc->sa.agi_bp);
+ xchk_iunlink(sc, agi);
+
xchk_agi_xref(sc);
out:
return error;
diff --git a/fs/xfs/scrub/agheader_repair.c b/fs/xfs/scrub/agheader_repair.c
index 427054b65b..0dbc484b18 100644
--- a/fs/xfs/scrub/agheader_repair.c
+++ b/fs/xfs/scrub/agheader_repair.c
@@ -21,13 +21,18 @@
#include "xfs_rmap_btree.h"
#include "xfs_refcount_btree.h"
#include "xfs_ag.h"
+#include "xfs_inode.h"
+#include "xfs_iunlink_item.h"
#include "scrub/scrub.h"
#include "scrub/common.h"
#include "scrub/trace.h"
#include "scrub/repair.h"
#include "scrub/bitmap.h"
#include "scrub/agb_bitmap.h"
+#include "scrub/agino_bitmap.h"
#include "scrub/reap.h"
+#include "scrub/xfile.h"
+#include "scrub/xfarray.h"
/* Superblock */
@@ -796,15 +801,57 @@ enum {
XREP_AGI_MAX
};
+#define XREP_AGI_LOOKUP_BATCH 32
+
+struct xrep_agi {
+ struct xfs_scrub *sc;
+
+ /* AGI buffer, tracked separately */
+ struct xfs_buf *agi_bp;
+
+ /* context for finding btree roots */
+ struct xrep_find_ag_btree fab[XREP_AGI_MAX];
+
+ /* old AGI contents in case we have to revert */
+ struct xfs_agi old_agi;
+
+ /* bitmap of which inodes are unlinked */
+ struct xagino_bitmap iunlink_bmp;
+
+ /* heads of the unlinked inode bucket lists */
+ xfs_agino_t iunlink_heads[XFS_AGI_UNLINKED_BUCKETS];
+
+ /* scratchpad for batched lookups of the radix tree */
+ struct xfs_inode *lookup_batch[XREP_AGI_LOOKUP_BATCH];
+
+ /* Map of ino -> next_ino for unlinked inode processing. */
+ struct xfarray *iunlink_next;
+
+ /* Map of ino -> prev_ino for unlinked inode processing. */
+ struct xfarray *iunlink_prev;
+};
+
+static void
+xrep_agi_buf_cleanup(
+ void *buf)
+{
+ struct xrep_agi *ragi = buf;
+
+ xfarray_destroy(ragi->iunlink_prev);
+ xfarray_destroy(ragi->iunlink_next);
+ xagino_bitmap_destroy(&ragi->iunlink_bmp);
+}
+
/*
* Given the inode btree roots described by *fab, find the roots, check them
* for sanity, and pass the root data back out via *fab.
*/
STATIC int
xrep_agi_find_btrees(
- struct xfs_scrub *sc,
- struct xrep_find_ag_btree *fab)
+ struct xrep_agi *ragi)
{
+ struct xfs_scrub *sc = ragi->sc;
+ struct xrep_find_ag_btree *fab = ragi->fab;
struct xfs_buf *agf_bp;
struct xfs_mount *mp = sc->mp;
int error;
@@ -837,10 +884,11 @@ xrep_agi_find_btrees(
*/
STATIC void
xrep_agi_init_header(
- struct xfs_scrub *sc,
- struct xfs_buf *agi_bp,
- struct xfs_agi *old_agi)
+ struct xrep_agi *ragi)
{
+ struct xfs_scrub *sc = ragi->sc;
+ struct xfs_buf *agi_bp = ragi->agi_bp;
+ struct xfs_agi *old_agi = &ragi->old_agi;
struct xfs_agi *agi = agi_bp->b_addr;
struct xfs_perag *pag = sc->sa.pag;
struct xfs_mount *mp = sc->mp;
@@ -856,10 +904,6 @@ xrep_agi_init_header(
if (xfs_has_crc(mp))
uuid_copy(&agi->agi_uuid, &mp->m_sb.sb_meta_uuid);
- /* We don't know how to fix the unlinked list yet. */
- memcpy(&agi->agi_unlinked, &old_agi->agi_unlinked,
- sizeof(agi->agi_unlinked));
-
/* Mark the incore AGF data stale until we're done fixing things. */
ASSERT(xfs_perag_initialised_agi(pag));
clear_bit(XFS_AGSTATE_AGI_INIT, &pag->pag_opstate);
@@ -868,10 +912,12 @@ xrep_agi_init_header(
/* Set btree root information in an AGI. */
STATIC void
xrep_agi_set_roots(
- struct xfs_scrub *sc,
- struct xfs_agi *agi,
- struct xrep_find_ag_btree *fab)
+ struct xrep_agi *ragi)
{
+ struct xfs_scrub *sc = ragi->sc;
+ struct xfs_agi *agi = ragi->agi_bp->b_addr;
+ struct xrep_find_ag_btree *fab = ragi->fab;
+
agi->agi_root = cpu_to_be32(fab[XREP_AGI_INOBT].root);
agi->agi_level = cpu_to_be32(fab[XREP_AGI_INOBT].height);
@@ -884,9 +930,10 @@ xrep_agi_set_roots(
/* Update the AGI counters. */
STATIC int
xrep_agi_calc_from_btrees(
- struct xfs_scrub *sc,
- struct xfs_buf *agi_bp)
+ struct xrep_agi *ragi)
{
+ struct xfs_scrub *sc = ragi->sc;
+ struct xfs_buf *agi_bp = ragi->agi_bp;
struct xfs_btree_cur *cur;
struct xfs_agi *agi = agi_bp->b_addr;
struct xfs_mount *mp = sc->mp;
@@ -928,12 +975,721 @@ err:
return error;
}
+/*
+ * Record a forwards unlinked chain pointer from agino -> next_agino in our
+ * staging information.
+ */
+static inline int
+xrep_iunlink_store_next(
+ struct xrep_agi *ragi,
+ xfs_agino_t agino,
+ xfs_agino_t next_agino)
+{
+ ASSERT(next_agino != 0);
+
+ return xfarray_store(ragi->iunlink_next, agino, &next_agino);
+}
+
+/*
+ * Record a backwards unlinked chain pointer from prev_ino <- agino in our
+ * staging information.
+ */
+static inline int
+xrep_iunlink_store_prev(
+ struct xrep_agi *ragi,
+ xfs_agino_t agino,
+ xfs_agino_t prev_agino)
+{
+ ASSERT(prev_agino != 0);
+
+ return xfarray_store(ragi->iunlink_prev, agino, &prev_agino);
+}
+
+/*
+ * Given an @agino, look up the next inode in the iunlink bucket. Returns
+ * NULLAGINO if we're at the end of the chain, 0 if @agino is not in memory
+ * like it should be, or a per-AG inode number.
+ */
+static inline xfs_agino_t
+xrep_iunlink_next(
+ struct xfs_scrub *sc,
+ xfs_agino_t agino)
+{
+ struct xfs_inode *ip;
+
+ ip = xfs_iunlink_lookup(sc->sa.pag, agino);
+ if (!ip)
+ return 0;
+
+ return ip->i_next_unlinked;
+}
+
+/*
+ * Load the inode @agino into memory, set its i_prev_unlinked, and drop the
+ * inode so it can be inactivated. Returns NULLAGINO if we're at the end of
+ * the chain or if we should stop walking the chain due to corruption; or a
+ * per-AG inode number.
+ */
+STATIC xfs_agino_t
+xrep_iunlink_reload_next(
+ struct xrep_agi *ragi,
+ xfs_agino_t prev_agino,
+ xfs_agino_t agino)
+{
+ struct xfs_scrub *sc = ragi->sc;
+ struct xfs_inode *ip;
+ xfs_ino_t ino;
+ xfs_agino_t ret = NULLAGINO;
+ int error;
+
+ ino = XFS_AGINO_TO_INO(sc->mp, sc->sa.pag->pag_agno, agino);
+ error = xchk_iget(ragi->sc, ino, &ip);
+ if (error)
+ return ret;
+
+ trace_xrep_iunlink_reload_next(ip, prev_agino);
+
+ /* If this is a linked inode, stop processing the chain. */
+ if (VFS_I(ip)->i_nlink != 0) {
+ xrep_iunlink_store_next(ragi, agino, NULLAGINO);
+ goto rele;
+ }
+
+ ip->i_prev_unlinked = prev_agino;
+ ret = ip->i_next_unlinked;
+
+ /*
+ * Drop the inode reference that we just took. We hold the AGI, so
+ * this inode cannot move off the unlinked list and hence cannot be
+ * reclaimed.
+ */
+rele:
+ xchk_irele(sc, ip);
+ return ret;
+}
+
+/*
+ * Walk an AGI unlinked bucket's list to load incore any unlinked inodes that
+ * still existed at mount time. This can happen if iunlink processing fails
+ * during log recovery.
+ */
+STATIC int
+xrep_iunlink_walk_ondisk_bucket(
+ struct xrep_agi *ragi,
+ unsigned int bucket)
+{
+ struct xfs_scrub *sc = ragi->sc;
+ struct xfs_agi *agi = sc->sa.agi_bp->b_addr;
+ xfs_agino_t prev_agino = NULLAGINO;
+ xfs_agino_t next_agino;
+ int error = 0;
+
+ next_agino = be32_to_cpu(agi->agi_unlinked[bucket]);
+ while (next_agino != NULLAGINO) {
+ xfs_agino_t agino = next_agino;
+
+ if (xchk_should_terminate(ragi->sc, &error))
+ return error;
+
+ trace_xrep_iunlink_walk_ondisk_bucket(sc->sa.pag, bucket,
+ prev_agino, agino);
+
+ if (bucket != agino % XFS_AGI_UNLINKED_BUCKETS)
+ break;
+
+ next_agino = xrep_iunlink_next(sc, agino);
+ if (!next_agino)
+ next_agino = xrep_iunlink_reload_next(ragi, prev_agino,
+ agino);
+
+ prev_agino = agino;
+ }
+
+ return 0;
+}
+
+/* Decide if this is an unlinked inode in this AG. */
+STATIC bool
+xrep_iunlink_igrab(
+ struct xfs_perag *pag,
+ struct xfs_inode *ip)
+{
+ struct xfs_mount *mp = pag->pag_mount;
+
+ if (XFS_INO_TO_AGNO(mp, ip->i_ino) != pag->pag_agno)
+ return false;
+
+ if (!xfs_inode_on_unlinked_list(ip))
+ return false;
+
+ return true;
+}
+
+/*
+ * Mark the given inode in the lookup batch in our unlinked inode bitmap, and
+ * remember if this inode is the start of the unlinked chain.
+ */
+STATIC int
+xrep_iunlink_visit(
+ struct xrep_agi *ragi,
+ unsigned int batch_idx)
+{
+ struct xfs_mount *mp = ragi->sc->mp;
+ struct xfs_inode *ip = ragi->lookup_batch[batch_idx];
+ xfs_agino_t agino;
+ unsigned int bucket;
+ int error;
+
+ ASSERT(XFS_INO_TO_AGNO(mp, ip->i_ino) == ragi->sc->sa.pag->pag_agno);
+ ASSERT(xfs_inode_on_unlinked_list(ip));
+
+ agino = XFS_INO_TO_AGINO(mp, ip->i_ino);
+ bucket = agino % XFS_AGI_UNLINKED_BUCKETS;
+
+ trace_xrep_iunlink_visit(ragi->sc->sa.pag, bucket,
+ ragi->iunlink_heads[bucket], ip);
+
+ error = xagino_bitmap_set(&ragi->iunlink_bmp, agino, 1);
+ if (error)
+ return error;
+
+ if (ip->i_prev_unlinked == NULLAGINO) {
+ if (ragi->iunlink_heads[bucket] == NULLAGINO)
+ ragi->iunlink_heads[bucket] = agino;
+ }
+
+ return 0;
+}
+
+/*
+ * Find all incore unlinked inodes so that we can rebuild the unlinked buckets.
+ * We hold the AGI so there should not be any modifications to the unlinked
+ * list.
+ */
+STATIC int
+xrep_iunlink_mark_incore(
+ struct xrep_agi *ragi)
+{
+ struct xfs_perag *pag = ragi->sc->sa.pag;
+ struct xfs_mount *mp = pag->pag_mount;
+ uint32_t first_index = 0;
+ bool done = false;
+ unsigned int nr_found = 0;
+
+ do {
+ unsigned int i;
+ int error = 0;
+
+ if (xchk_should_terminate(ragi->sc, &error))
+ return error;
+
+ rcu_read_lock();
+
+ nr_found = radix_tree_gang_lookup(&pag->pag_ici_root,
+ (void **)&ragi->lookup_batch, first_index,
+ XREP_AGI_LOOKUP_BATCH);
+ if (!nr_found) {
+ rcu_read_unlock();
+ return 0;
+ }
+
+ for (i = 0; i < nr_found; i++) {
+ struct xfs_inode *ip = ragi->lookup_batch[i];
+
+ if (done || !xrep_iunlink_igrab(pag, ip))
+ ragi->lookup_batch[i] = NULL;
+
+ /*
+ * Update the index for the next lookup. Catch
+ * overflows into the next AG range which can occur if
+ * we have inodes in the last block of the AG and we
+ * are currently pointing to the last inode.
+ *
+ * Because we may see inodes that are from the wrong AG
+ * due to RCU freeing and reallocation, only update the
+ * index if it lies in this AG. It was a race that lead
+ * us to see this inode, so another lookup from the
+ * same index will not find it again.
+ */
+ if (XFS_INO_TO_AGNO(mp, ip->i_ino) != pag->pag_agno)
+ continue;
+ first_index = XFS_INO_TO_AGINO(mp, ip->i_ino + 1);
+ if (first_index < XFS_INO_TO_AGINO(mp, ip->i_ino))
+ done = true;
+ }
+
+ /* unlock now we've grabbed the inodes. */
+ rcu_read_unlock();
+
+ for (i = 0; i < nr_found; i++) {
+ if (!ragi->lookup_batch[i])
+ continue;
+ error = xrep_iunlink_visit(ragi, i);
+ if (error)
+ return error;
+ }
+ } while (!done);
+
+ return 0;
+}
+
+/* Mark all the unlinked ondisk inodes in this inobt record in iunlink_bmp. */
+STATIC int
+xrep_iunlink_mark_ondisk_rec(
+ struct xfs_btree_cur *cur,
+ const union xfs_btree_rec *rec,
+ void *priv)
+{
+ struct xfs_inobt_rec_incore irec;
+ struct xrep_agi *ragi = priv;
+ struct xfs_scrub *sc = ragi->sc;
+ struct xfs_mount *mp = cur->bc_mp;
+ xfs_agino_t agino;
+ unsigned int i;
+ int error = 0;
+
+ xfs_inobt_btrec_to_irec(mp, rec, &irec);
+
+ for (i = 0, agino = irec.ir_startino;
+ i < XFS_INODES_PER_CHUNK;
+ i++, agino++) {
+ struct xfs_inode *ip;
+ unsigned int len = 1;
+
+ /* Skip free inodes */
+ if (XFS_INOBT_MASK(i) & irec.ir_free)
+ continue;
+ /* Skip inodes we've seen before */
+ if (xagino_bitmap_test(&ragi->iunlink_bmp, agino, &len))
+ continue;
+
+ /*
+ * Skip incore inodes; these were already picked up by
+ * the _mark_incore step.
+ */
+ rcu_read_lock();
+ ip = radix_tree_lookup(&sc->sa.pag->pag_ici_root, agino);
+ rcu_read_unlock();
+ if (ip)
+ continue;
+
+ /*
+ * Try to look up this inode. If we can't get it, just move
+ * on because we haven't actually scrubbed the inobt or the
+ * inodes yet.
+ */
+ error = xchk_iget(ragi->sc,
+ XFS_AGINO_TO_INO(mp, sc->sa.pag->pag_agno,
+ agino),
+ &ip);
+ if (error)
+ continue;
+
+ trace_xrep_iunlink_reload_ondisk(ip);
+
+ if (VFS_I(ip)->i_nlink == 0)
+ error = xagino_bitmap_set(&ragi->iunlink_bmp, agino, 1);
+ xchk_irele(sc, ip);
+ if (error)
+ break;
+ }
+
+ return error;
+}
+
+/*
+ * Find ondisk inodes that are unlinked and not in cache, and mark them in
+ * iunlink_bmp. We haven't checked the inobt yet, so we don't error out if
+ * the btree is corrupt.
+ */
+STATIC void
+xrep_iunlink_mark_ondisk(
+ struct xrep_agi *ragi)
+{
+ struct xfs_scrub *sc = ragi->sc;
+ struct xfs_buf *agi_bp = ragi->agi_bp;
+ struct xfs_btree_cur *cur;
+ int error;
+
+ cur = xfs_inobt_init_cursor(sc->sa.pag, sc->tp, agi_bp);
+ error = xfs_btree_query_all(cur, xrep_iunlink_mark_ondisk_rec, ragi);
+ xfs_btree_del_cursor(cur, error);
+}
+
+/*
+ * Walk an iunlink bucket's inode list. For each inode that should be on this
+ * chain, clear its entry in in iunlink_bmp because it's ok and we don't need
+ * to touch it further.
+ */
+STATIC int
+xrep_iunlink_resolve_bucket(
+ struct xrep_agi *ragi,
+ unsigned int bucket)
+{
+ struct xfs_scrub *sc = ragi->sc;
+ struct xfs_inode *ip;
+ xfs_agino_t prev_agino = NULLAGINO;
+ xfs_agino_t next_agino = ragi->iunlink_heads[bucket];
+ int error = 0;
+
+ while (next_agino != NULLAGINO) {
+ if (xchk_should_terminate(ragi->sc, &error))
+ return error;
+
+ /* Find the next inode in the chain. */
+ ip = xfs_iunlink_lookup(sc->sa.pag, next_agino);
+ if (!ip) {
+ /* Inode not incore? Terminate the chain. */
+ trace_xrep_iunlink_resolve_uncached(sc->sa.pag,
+ bucket, prev_agino, next_agino);
+
+ next_agino = NULLAGINO;
+ break;
+ }
+
+ if (next_agino % XFS_AGI_UNLINKED_BUCKETS != bucket) {
+ /*
+ * Inode is in the wrong bucket. Advance the list,
+ * but pretend we didn't see this inode.
+ */
+ trace_xrep_iunlink_resolve_wronglist(sc->sa.pag,
+ bucket, prev_agino, next_agino);
+
+ next_agino = ip->i_next_unlinked;
+ continue;
+ }
+
+ if (!xfs_inode_on_unlinked_list(ip)) {
+ /*
+ * Incore inode doesn't think this inode is on an
+ * unlinked list. This is probably because we reloaded
+ * it from disk. Advance the list, but pretend we
+ * didn't see this inode; we'll fix that later.
+ */
+ trace_xrep_iunlink_resolve_nolist(sc->sa.pag,
+ bucket, prev_agino, next_agino);
+ next_agino = ip->i_next_unlinked;
+ continue;
+ }
+
+ trace_xrep_iunlink_resolve_ok(sc->sa.pag, bucket, prev_agino,
+ next_agino);
+
+ /*
+ * Otherwise, this inode's unlinked pointers are ok. Clear it
+ * from the unlinked bitmap since we're done with it, and make
+ * sure the chain is still correct.
+ */
+ error = xagino_bitmap_clear(&ragi->iunlink_bmp, next_agino, 1);
+ if (error)
+ return error;
+
+ /* Remember the previous inode's next pointer. */
+ if (prev_agino != NULLAGINO) {
+ error = xrep_iunlink_store_next(ragi, prev_agino,
+ next_agino);
+ if (error)
+ return error;
+ }
+
+ /* Remember this inode's previous pointer. */
+ error = xrep_iunlink_store_prev(ragi, next_agino, prev_agino);
+ if (error)
+ return error;
+
+ /* Advance the list and remember this inode. */
+ prev_agino = next_agino;
+ next_agino = ip->i_next_unlinked;
+ }
+
+ /* Update the previous inode's next pointer. */
+ if (prev_agino != NULLAGINO) {
+ error = xrep_iunlink_store_next(ragi, prev_agino, next_agino);
+ if (error)
+ return error;
+ }
+
+ return 0;
+}
+
+/* Reinsert this unlinked inode into the head of the staged bucket list. */
+STATIC int
+xrep_iunlink_add_to_bucket(
+ struct xrep_agi *ragi,
+ xfs_agino_t agino)
+{
+ xfs_agino_t current_head;
+ unsigned int bucket;
+ int error;
+
+ bucket = agino % XFS_AGI_UNLINKED_BUCKETS;
+
+ /* Point this inode at the current head of the bucket list. */
+ current_head = ragi->iunlink_heads[bucket];
+
+ trace_xrep_iunlink_add_to_bucket(ragi->sc->sa.pag, bucket, agino,
+ current_head);
+
+ error = xrep_iunlink_store_next(ragi, agino, current_head);
+ if (error)
+ return error;
+
+ /* Remember the head inode's previous pointer. */
+ if (current_head != NULLAGINO) {
+ error = xrep_iunlink_store_prev(ragi, current_head, agino);
+ if (error)
+ return error;
+ }
+
+ ragi->iunlink_heads[bucket] = agino;
+ return 0;
+}
+
+/* Reinsert unlinked inodes into the staged iunlink buckets. */
+STATIC int
+xrep_iunlink_add_lost_inodes(
+ uint32_t start,
+ uint32_t len,
+ void *priv)
+{
+ struct xrep_agi *ragi = priv;
+ int error;
+
+ for (; len > 0; start++, len--) {
+ error = xrep_iunlink_add_to_bucket(ragi, start);
+ if (error)
+ return error;
+ }
+
+ return 0;
+}
+
+/*
+ * Figure out the iunlink bucket values and find inodes that need to be
+ * reinserted into the list.
+ */
+STATIC int
+xrep_iunlink_rebuild_buckets(
+ struct xrep_agi *ragi)
+{
+ unsigned int i;
+ int error;
+
+ /*
+ * Walk the ondisk AGI unlinked list to find inodes that are on the
+ * list but aren't in memory. This can happen if a past log recovery
+ * tried to clear the iunlinked list but failed. Our scan rebuilds the
+ * unlinked list using incore inodes, so we must load and link them
+ * properly.
+ */
+ for (i = 0; i < XFS_AGI_UNLINKED_BUCKETS; i++) {
+ error = xrep_iunlink_walk_ondisk_bucket(ragi, i);
+ if (error)
+ return error;
+ }
+
+ /*
+ * Record all the incore unlinked inodes in iunlink_bmp that we didn't
+ * find by walking the ondisk iunlink buckets. This shouldn't happen,
+ * but we can't risk forgetting an inode somewhere.
+ */
+ error = xrep_iunlink_mark_incore(ragi);
+ if (error)
+ return error;
+
+ /*
+ * If there are ondisk inodes that are unlinked and are not been loaded
+ * into cache, record them in iunlink_bmp.
+ */
+ xrep_iunlink_mark_ondisk(ragi);
+
+ /*
+ * Walk each iunlink bucket to (re)construct as much of the incore list
+ * as would be correct. For each inode that survives this step, mark
+ * it clear in iunlink_bmp; we're done with those inodes.
+ */
+ for (i = 0; i < XFS_AGI_UNLINKED_BUCKETS; i++) {
+ error = xrep_iunlink_resolve_bucket(ragi, i);
+ if (error)
+ return error;
+ }
+
+ /*
+ * Any unlinked inodes that we didn't find through the bucket list
+ * walk (or was ignored by the walk) must be inserted into the bucket
+ * list. Stage this in memory for now.
+ */
+ return xagino_bitmap_walk(&ragi->iunlink_bmp,
+ xrep_iunlink_add_lost_inodes, ragi);
+}
+
+/* Update i_next_iunlinked for the inode @agino. */
+STATIC int
+xrep_iunlink_relink_next(
+ struct xrep_agi *ragi,
+ xfarray_idx_t idx,
+ xfs_agino_t next_agino)
+{
+ struct xfs_scrub *sc = ragi->sc;
+ struct xfs_perag *pag = sc->sa.pag;
+ struct xfs_inode *ip;
+ xfarray_idx_t agino = idx - 1;
+ bool want_rele = false;
+ int error = 0;
+
+ ip = xfs_iunlink_lookup(pag, agino);
+ if (!ip) {
+ xfs_ino_t ino;
+ xfs_agino_t prev_agino;
+
+ /*
+ * No inode exists in cache. Load it off the disk so that we
+ * can reinsert it into the incore unlinked list.
+ */
+ ino = XFS_AGINO_TO_INO(sc->mp, pag->pag_agno, agino);
+ error = xchk_iget(sc, ino, &ip);
+ if (error)
+ return -EFSCORRUPTED;
+
+ want_rele = true;
+
+ /* Set the backward pointer since this just came off disk. */
+ error = xfarray_load(ragi->iunlink_prev, agino, &prev_agino);
+ if (error)
+ goto out_rele;
+
+ trace_xrep_iunlink_relink_prev(ip, prev_agino);
+ ip->i_prev_unlinked = prev_agino;
+ }
+
+ /* Update the forward pointer. */
+ if (ip->i_next_unlinked != next_agino) {
+ error = xfs_iunlink_log_inode(sc->tp, ip, pag, next_agino);
+ if (error)
+ goto out_rele;
+
+ trace_xrep_iunlink_relink_next(ip, next_agino);
+ ip->i_next_unlinked = next_agino;
+ }
+
+out_rele:
+ /*
+ * The iunlink lookup doesn't igrab because we hold the AGI buffer lock
+ * and the inode cannot be reclaimed. However, if we used iget to load
+ * a missing inode, we must irele it here.
+ */
+ if (want_rele)
+ xchk_irele(sc, ip);
+ return error;
+}
+
+/* Update i_prev_iunlinked for the inode @agino. */
+STATIC int
+xrep_iunlink_relink_prev(
+ struct xrep_agi *ragi,
+ xfarray_idx_t idx,
+ xfs_agino_t prev_agino)
+{
+ struct xfs_scrub *sc = ragi->sc;
+ struct xfs_perag *pag = sc->sa.pag;
+ struct xfs_inode *ip;
+ xfarray_idx_t agino = idx - 1;
+ bool want_rele = false;
+ int error = 0;
+
+ ASSERT(prev_agino != 0);
+
+ ip = xfs_iunlink_lookup(pag, agino);
+ if (!ip) {
+ xfs_ino_t ino;
+ xfs_agino_t next_agino;
+
+ /*
+ * No inode exists in cache. Load it off the disk so that we
+ * can reinsert it into the incore unlinked list.
+ */
+ ino = XFS_AGINO_TO_INO(sc->mp, pag->pag_agno, agino);
+ error = xchk_iget(sc, ino, &ip);
+ if (error)
+ return -EFSCORRUPTED;
+
+ want_rele = true;
+
+ /* Set the forward pointer since this just came off disk. */
+ error = xfarray_load(ragi->iunlink_prev, agino, &next_agino);
+ if (error)
+ goto out_rele;
+
+ error = xfs_iunlink_log_inode(sc->tp, ip, pag, next_agino);
+ if (error)
+ goto out_rele;
+
+ trace_xrep_iunlink_relink_next(ip, next_agino);
+ ip->i_next_unlinked = next_agino;
+ }
+
+ /* Update the backward pointer. */
+ if (ip->i_prev_unlinked != prev_agino) {
+ trace_xrep_iunlink_relink_prev(ip, prev_agino);
+ ip->i_prev_unlinked = prev_agino;
+ }
+
+out_rele:
+ /*
+ * The iunlink lookup doesn't igrab because we hold the AGI buffer lock
+ * and the inode cannot be reclaimed. However, if we used iget to load
+ * a missing inode, we must irele it here.
+ */
+ if (want_rele)
+ xchk_irele(sc, ip);
+ return error;
+}
+
+/* Log all the iunlink updates we need to finish regenerating the AGI. */
+STATIC int
+xrep_iunlink_commit(
+ struct xrep_agi *ragi)
+{
+ struct xfs_agi *agi = ragi->agi_bp->b_addr;
+ xfarray_idx_t idx = XFARRAY_CURSOR_INIT;
+ xfs_agino_t agino;
+ unsigned int i;
+ int error;
+
+ /* Fix all the forward links */
+ while ((error = xfarray_iter(ragi->iunlink_next, &idx, &agino)) == 1) {
+ error = xrep_iunlink_relink_next(ragi, idx, agino);
+ if (error)
+ return error;
+ }
+
+ /* Fix all the back links */
+ idx = XFARRAY_CURSOR_INIT;
+ while ((error = xfarray_iter(ragi->iunlink_prev, &idx, &agino)) == 1) {
+ error = xrep_iunlink_relink_prev(ragi, idx, agino);
+ if (error)
+ return error;
+ }
+
+ /* Copy the staged iunlink buckets to the new AGI. */
+ for (i = 0; i < XFS_AGI_UNLINKED_BUCKETS; i++) {
+ trace_xrep_iunlink_commit_bucket(ragi->sc->sa.pag, i,
+ be32_to_cpu(ragi->old_agi.agi_unlinked[i]),
+ ragi->iunlink_heads[i]);
+
+ agi->agi_unlinked[i] = cpu_to_be32(ragi->iunlink_heads[i]);
+ }
+
+ return 0;
+}
+
/* Trigger reinitialization of the in-core data. */
STATIC int
xrep_agi_commit_new(
- struct xfs_scrub *sc,
- struct xfs_buf *agi_bp)
+ struct xrep_agi *ragi)
{
+ struct xfs_scrub *sc = ragi->sc;
+ struct xfs_buf *agi_bp = ragi->agi_bp;
struct xfs_perag *pag;
struct xfs_agi *agi = agi_bp->b_addr;
@@ -956,33 +1712,58 @@ xrep_agi_commit_new(
/* Repair the AGI. */
int
xrep_agi(
- struct xfs_scrub *sc)
+ struct xfs_scrub *sc)
{
- struct xrep_find_ag_btree fab[XREP_AGI_MAX] = {
- [XREP_AGI_INOBT] = {
- .rmap_owner = XFS_RMAP_OWN_INOBT,
- .buf_ops = &xfs_inobt_buf_ops,
- .maxlevels = M_IGEO(sc->mp)->inobt_maxlevels,
- },
- [XREP_AGI_FINOBT] = {
- .rmap_owner = XFS_RMAP_OWN_INOBT,
- .buf_ops = &xfs_finobt_buf_ops,
- .maxlevels = M_IGEO(sc->mp)->inobt_maxlevels,
- },
- [XREP_AGI_END] = {
- .buf_ops = NULL
- },
- };
- struct xfs_agi old_agi;
- struct xfs_mount *mp = sc->mp;
- struct xfs_buf *agi_bp;
- struct xfs_agi *agi;
- int error;
+ struct xrep_agi *ragi;
+ struct xfs_mount *mp = sc->mp;
+ char *descr;
+ unsigned int i;
+ int error;
/* We require the rmapbt to rebuild anything. */
if (!xfs_has_rmapbt(mp))
return -EOPNOTSUPP;
+ sc->buf = kzalloc(sizeof(struct xrep_agi), XCHK_GFP_FLAGS);
+ if (!sc->buf)
+ return -ENOMEM;
+ ragi = sc->buf;
+ ragi->sc = sc;
+
+ ragi->fab[XREP_AGI_INOBT] = (struct xrep_find_ag_btree){
+ .rmap_owner = XFS_RMAP_OWN_INOBT,
+ .buf_ops = &xfs_inobt_buf_ops,
+ .maxlevels = M_IGEO(sc->mp)->inobt_maxlevels,
+ };
+ ragi->fab[XREP_AGI_FINOBT] = (struct xrep_find_ag_btree){
+ .rmap_owner = XFS_RMAP_OWN_INOBT,
+ .buf_ops = &xfs_finobt_buf_ops,
+ .maxlevels = M_IGEO(sc->mp)->inobt_maxlevels,
+ };
+ ragi->fab[XREP_AGI_END] = (struct xrep_find_ag_btree){
+ .buf_ops = NULL,
+ };
+
+ for (i = 0; i < XFS_AGI_UNLINKED_BUCKETS; i++)
+ ragi->iunlink_heads[i] = NULLAGINO;
+
+ xagino_bitmap_init(&ragi->iunlink_bmp);
+ sc->buf_cleanup = xrep_agi_buf_cleanup;
+
+ descr = xchk_xfile_ag_descr(sc, "iunlinked next pointers");
+ error = xfarray_create(descr, 0, sizeof(xfs_agino_t),
+ &ragi->iunlink_next);
+ kfree(descr);
+ if (error)
+ return error;
+
+ descr = xchk_xfile_ag_descr(sc, "iunlinked prev pointers");
+ error = xfarray_create(descr, 0, sizeof(xfs_agino_t),
+ &ragi->iunlink_prev);
+ kfree(descr);
+ if (error)
+ return error;
+
/*
* Make sure we have the AGI buffer, as scrub might have decided it
* was corrupt after xfs_ialloc_read_agi failed with -EFSCORRUPTED.
@@ -990,14 +1771,17 @@ xrep_agi(
error = xfs_trans_read_buf(mp, sc->tp, mp->m_ddev_targp,
XFS_AG_DADDR(mp, sc->sa.pag->pag_agno,
XFS_AGI_DADDR(mp)),
- XFS_FSS_TO_BB(mp, 1), 0, &agi_bp, NULL);
+ XFS_FSS_TO_BB(mp, 1), 0, &ragi->agi_bp, NULL);
if (error)
return error;
- agi_bp->b_ops = &xfs_agi_buf_ops;
- agi = agi_bp->b_addr;
+ ragi->agi_bp->b_ops = &xfs_agi_buf_ops;
/* Find the AGI btree roots. */
- error = xrep_agi_find_btrees(sc, fab);
+ error = xrep_agi_find_btrees(ragi);
+ if (error)
+ return error;
+
+ error = xrep_iunlink_rebuild_buckets(ragi);
if (error)
return error;
@@ -1006,18 +1790,21 @@ xrep_agi(
return error;
/* Start rewriting the header and implant the btrees we found. */
- xrep_agi_init_header(sc, agi_bp, &old_agi);
- xrep_agi_set_roots(sc, agi, fab);
- error = xrep_agi_calc_from_btrees(sc, agi_bp);
+ xrep_agi_init_header(ragi);
+ xrep_agi_set_roots(ragi);
+ error = xrep_agi_calc_from_btrees(ragi);
+ if (error)
+ goto out_revert;
+ error = xrep_iunlink_commit(ragi);
if (error)
goto out_revert;
/* Reinitialize in-core state. */
- return xrep_agi_commit_new(sc, agi_bp);
+ return xrep_agi_commit_new(ragi);
out_revert:
/* Mark the incore AGI state stale and revert the AGI. */
clear_bit(XFS_AGSTATE_AGI_INIT, &sc->sa.pag->pag_opstate);
- memcpy(agi, &old_agi, sizeof(old_agi));
+ memcpy(ragi->agi_bp->b_addr, &ragi->old_agi, sizeof(struct xfs_agi));
return error;
}
diff --git a/fs/xfs/scrub/agino_bitmap.h b/fs/xfs/scrub/agino_bitmap.h
new file mode 100644
index 0000000000..56d7db5f16
--- /dev/null
+++ b/fs/xfs/scrub/agino_bitmap.h
@@ -0,0 +1,49 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Copyright (c) 2018-2024 Oracle. All Rights Reserved.
+ * Author: Darrick J. Wong <djwong@kernel.org>
+ */
+#ifndef __XFS_SCRUB_AGINO_BITMAP_H__
+#define __XFS_SCRUB_AGINO_BITMAP_H__
+
+/* Bitmaps, but for type-checked for xfs_agino_t */
+
+struct xagino_bitmap {
+ struct xbitmap32 aginobitmap;
+};
+
+static inline void xagino_bitmap_init(struct xagino_bitmap *bitmap)
+{
+ xbitmap32_init(&bitmap->aginobitmap);
+}
+
+static inline void xagino_bitmap_destroy(struct xagino_bitmap *bitmap)
+{
+ xbitmap32_destroy(&bitmap->aginobitmap);
+}
+
+static inline int xagino_bitmap_clear(struct xagino_bitmap *bitmap,
+ xfs_agino_t agino, unsigned int len)
+{
+ return xbitmap32_clear(&bitmap->aginobitmap, agino, len);
+}
+
+static inline int xagino_bitmap_set(struct xagino_bitmap *bitmap,
+ xfs_agino_t agino, unsigned int len)
+{
+ return xbitmap32_set(&bitmap->aginobitmap, agino, len);
+}
+
+static inline bool xagino_bitmap_test(struct xagino_bitmap *bitmap,
+ xfs_agino_t agino, unsigned int *len)
+{
+ return xbitmap32_test(&bitmap->aginobitmap, agino, len);
+}
+
+static inline int xagino_bitmap_walk(struct xagino_bitmap *bitmap,
+ xbitmap32_walk_fn fn, void *priv)
+{
+ return xbitmap32_walk(&bitmap->aginobitmap, fn, priv);
+}
+
+#endif /* __XFS_SCRUB_AGINO_BITMAP_H__ */
diff --git a/fs/xfs/scrub/alloc_repair.c b/fs/xfs/scrub/alloc_repair.c
index d421b25392..30295898cc 100644
--- a/fs/xfs/scrub/alloc_repair.c
+++ b/fs/xfs/scrub/alloc_repair.c
@@ -778,7 +778,7 @@ xrep_abt_build_new_trees(
error = xrep_bnobt_sort_records(ra);
if (error)
- return error;
+ goto err_levels;
/* Load the free space by block number tree. */
ra->array_cur = XFARRAY_CURSOR_INIT;
diff --git a/fs/xfs/scrub/attr.c b/fs/xfs/scrub/attr.c
index 83c7feb387..708334f9b2 100644
--- a/fs/xfs/scrub/attr.c
+++ b/fs/xfs/scrub/attr.c
@@ -10,16 +10,20 @@
#include "xfs_trans_resv.h"
#include "xfs_mount.h"
#include "xfs_log_format.h"
+#include "xfs_trans.h"
#include "xfs_inode.h"
#include "xfs_da_format.h"
#include "xfs_da_btree.h"
#include "xfs_attr.h"
#include "xfs_attr_leaf.h"
#include "xfs_attr_sf.h"
+#include "xfs_parent.h"
#include "scrub/scrub.h"
#include "scrub/common.h"
#include "scrub/dabtree.h"
#include "scrub/attr.h"
+#include "scrub/listxattr.h"
+#include "scrub/repair.h"
/* Free the buffers linked from the xattr buffer. */
static void
@@ -35,6 +39,8 @@ xchk_xattr_buf_cleanup(
kvfree(ab->value);
ab->value = NULL;
ab->value_sz = 0;
+ kvfree(ab->name);
+ ab->name = NULL;
}
/*
@@ -65,7 +71,7 @@ xchk_xattr_want_freemap(
* reallocating the buffer if necessary. Buffer contents are not preserved
* across a reallocation.
*/
-static int
+int
xchk_setup_xattr_buf(
struct xfs_scrub *sc,
size_t value_size)
@@ -95,6 +101,12 @@ xchk_setup_xattr_buf(
return -ENOMEM;
}
+ if (xchk_could_repair(sc)) {
+ ab->name = kvmalloc(XATTR_NAME_MAX + 1, XCHK_GFP_FLAGS);
+ if (!ab->name)
+ return -ENOMEM;
+ }
+
resize_value:
if (ab->value_sz >= value_size)
return 0;
@@ -121,6 +133,12 @@ xchk_setup_xattr(
{
int error;
+ if (xchk_could_repair(sc)) {
+ error = xrep_setup_xattr(sc);
+ if (error)
+ return error;
+ }
+
/*
* We failed to get memory while checking attrs, so this time try to
* get all the memory we're ever going to need. Allocate the buffer
@@ -137,106 +155,105 @@ xchk_setup_xattr(
/* Extended Attributes */
-struct xchk_xattr {
- struct xfs_attr_list_context context;
- struct xfs_scrub *sc;
-};
-
/*
* Check that an extended attribute key can be looked up by hash.
*
- * We use the XFS attribute list iterator (i.e. xfs_attr_list_ilocked)
- * to call this function for every attribute key in an inode. Once
- * we're here, we load the attribute value to see if any errors happen,
- * or if we get more or less data than we expected.
+ * We use the extended attribute walk helper to call this function for every
+ * attribute key in an inode. Once we're here, we load the attribute value to
+ * see if any errors happen, or if we get more or less data than we expected.
*/
-static void
-xchk_xattr_listent(
- struct xfs_attr_list_context *context,
- int flags,
- unsigned char *name,
- int namelen,
- int valuelen)
+static int
+xchk_xattr_actor(
+ struct xfs_scrub *sc,
+ struct xfs_inode *ip,
+ unsigned int attr_flags,
+ const unsigned char *name,
+ unsigned int namelen,
+ const void *value,
+ unsigned int valuelen,
+ void *priv)
{
struct xfs_da_args args = {
- .op_flags = XFS_DA_OP_NOTIME,
- .attr_filter = flags & XFS_ATTR_NSP_ONDISK_MASK,
- .geo = context->dp->i_mount->m_attr_geo,
+ .attr_filter = attr_flags & XFS_ATTR_NSP_ONDISK_MASK,
+ .geo = sc->mp->m_attr_geo,
.whichfork = XFS_ATTR_FORK,
- .dp = context->dp,
+ .dp = ip,
.name = name,
.namelen = namelen,
- .hashval = xfs_da_hashname(name, namelen),
- .trans = context->tp,
+ .trans = sc->tp,
.valuelen = valuelen,
+ .owner = ip->i_ino,
};
struct xchk_xattr_buf *ab;
- struct xchk_xattr *sx;
int error = 0;
- sx = container_of(context, struct xchk_xattr, context);
- ab = sx->sc->buf;
+ ab = sc->buf;
- if (xchk_should_terminate(sx->sc, &error)) {
- context->seen_enough = error;
- return;
+ if (xchk_should_terminate(sc, &error))
+ return error;
+
+ if (attr_flags & ~XFS_ATTR_ONDISK_MASK) {
+ xchk_fblock_set_corrupt(sc, XFS_ATTR_FORK, args.blkno);
+ return -ECANCELED;
}
- if (flags & XFS_ATTR_INCOMPLETE) {
+ if (attr_flags & XFS_ATTR_INCOMPLETE) {
/* Incomplete attr key, just mark the inode for preening. */
- xchk_ino_set_preen(sx->sc, context->dp->i_ino);
- return;
+ xchk_ino_set_preen(sc, ip->i_ino);
+ return 0;
}
- /* Only one namespace bit allowed. */
- if (hweight32(flags & XFS_ATTR_NSP_ONDISK_MASK) > 1) {
- xchk_fblock_set_corrupt(sx->sc, XFS_ATTR_FORK, args.blkno);
- goto fail_xref;
+ /* Does this name make sense? */
+ if (!xfs_attr_namecheck(attr_flags, name, namelen)) {
+ xchk_fblock_set_corrupt(sc, XFS_ATTR_FORK, args.blkno);
+ return -ECANCELED;
}
- /* Does this name make sense? */
- if (!xfs_attr_namecheck(name, namelen)) {
- xchk_fblock_set_corrupt(sx->sc, XFS_ATTR_FORK, args.blkno);
- goto fail_xref;
+ /* Check parent pointer record. */
+ if ((attr_flags & XFS_ATTR_PARENT) &&
+ !xfs_parent_valuecheck(sc->mp, value, valuelen)) {
+ xchk_fblock_set_corrupt(sc, XFS_ATTR_FORK, args.blkno);
+ return -ECANCELED;
}
/*
- * Local xattr values are stored in the attr leaf block, so we don't
- * need to retrieve the value from a remote block to detect corruption
- * problems.
+ * Try to allocate enough memory to extract the attr value. If that
+ * doesn't work, return -EDEADLOCK as a signal to try again with a
+ * maximally sized buffer.
*/
- if (flags & XFS_ATTR_LOCAL)
- goto fail_xref;
+ error = xchk_setup_xattr_buf(sc, valuelen);
+ if (error == -ENOMEM)
+ error = -EDEADLOCK;
+ if (error)
+ return error;
/*
- * Try to allocate enough memory to extrat the attr value. If that
- * doesn't work, we overload the seen_enough variable to convey
- * the error message back to the main scrub function.
+ * Parent pointers are matched on attr name and value, so we must
+ * supply the xfs_parent_rec here when confirming that the dabtree
+ * indexing works correctly.
*/
- error = xchk_setup_xattr_buf(sx->sc, valuelen);
- if (error == -ENOMEM)
- error = -EDEADLOCK;
- if (error) {
- context->seen_enough = error;
- return;
- }
+ if (attr_flags & XFS_ATTR_PARENT)
+ memcpy(ab->value, value, valuelen);
args.value = ab->value;
+ /*
+ * Get the attr value to ensure that lookup can find this attribute
+ * through the dabtree indexing and that remote value retrieval also
+ * works correctly.
+ */
+ xfs_attr_sethash(&args);
error = xfs_attr_get_ilocked(&args);
/* ENODATA means the hash lookup failed and the attr is bad */
if (error == -ENODATA)
error = -EFSCORRUPTED;
- if (!xchk_fblock_process_error(sx->sc, XFS_ATTR_FORK, args.blkno,
+ if (!xchk_fblock_process_error(sc, XFS_ATTR_FORK, args.blkno,
&error))
- goto fail_xref;
+ return error;
if (args.valuelen != valuelen)
- xchk_fblock_set_corrupt(sx->sc, XFS_ATTR_FORK,
- args.blkno);
-fail_xref:
- if (sx->sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT)
- context->seen_enough = 1;
- return;
+ xchk_fblock_set_corrupt(sc, XFS_ATTR_FORK, args.blkno);
+
+ return 0;
}
/*
@@ -246,7 +263,7 @@ fail_xref:
* Within a char, the lowest bit of the char represents the byte with
* the smallest address
*/
-STATIC bool
+bool
xchk_xattr_set_map(
struct xfs_scrub *sc,
unsigned long *map,
@@ -403,6 +420,17 @@ xchk_xattr_block(
xfs_attr3_leaf_hdr_from_disk(mp->m_attr_geo, &leafhdr, leaf);
hdrsize = xfs_attr3_leaf_hdr_size(leaf);
+ /*
+ * Empty xattr leaf blocks mapped at block 0 are probably a byproduct
+ * of a race between setxattr and a log shutdown. Anywhere else in the
+ * attr fork is a corruption.
+ */
+ if (leafhdr.count == 0) {
+ if (blk->blkno == 0)
+ xchk_da_set_preen(ds, level);
+ else
+ xchk_da_set_corrupt(ds, level);
+ }
if (leafhdr.usedbytes > mp->m_attr_geo->blksize)
xchk_da_set_corrupt(ds, level);
if (leafhdr.firstused > mp->m_attr_geo->blksize)
@@ -411,6 +439,8 @@ xchk_xattr_block(
xchk_da_set_corrupt(ds, level);
if (!xchk_xattr_set_map(ds->sc, ab->usedmap, 0, hdrsize))
xchk_da_set_corrupt(ds, level);
+ if (leafhdr.holes)
+ xchk_da_set_preen(ds, level);
if (ds->sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT)
goto out;
@@ -463,7 +493,6 @@ xchk_xattr_rec(
xfs_dahash_t hash;
int nameidx;
int hdrsize;
- unsigned int badflags;
int error;
ASSERT(blk->magic == XFS_ATTR_LEAF_MAGIC);
@@ -493,10 +522,15 @@ xchk_xattr_rec(
/* Retrieve the entry and check it. */
hash = be32_to_cpu(ent->hashval);
- badflags = ~(XFS_ATTR_LOCAL | XFS_ATTR_ROOT | XFS_ATTR_SECURE |
- XFS_ATTR_INCOMPLETE);
- if ((ent->flags & badflags) != 0)
+ if (ent->flags & ~XFS_ATTR_ONDISK_MASK) {
+ xchk_da_set_corrupt(ds, level);
+ return 0;
+ }
+ if (!xfs_attr_check_namespace(ent->flags)) {
xchk_da_set_corrupt(ds, level);
+ return 0;
+ }
+
if (ent->flags & XFS_ATTR_LOCAL) {
lentry = (struct xfs_attr_leaf_name_local *)
(((char *)bp->b_addr) + nameidx);
@@ -504,7 +538,10 @@ xchk_xattr_rec(
xchk_da_set_corrupt(ds, level);
goto out;
}
- calc_hash = xfs_da_hashname(lentry->nameval, lentry->namelen);
+ calc_hash = xfs_attr_hashval(mp, ent->flags, lentry->nameval,
+ lentry->namelen,
+ lentry->nameval + lentry->namelen,
+ be16_to_cpu(lentry->valuelen));
} else {
rentry = (struct xfs_attr_leaf_name_remote *)
(((char *)bp->b_addr) + nameidx);
@@ -512,7 +549,13 @@ xchk_xattr_rec(
xchk_da_set_corrupt(ds, level);
goto out;
}
- calc_hash = xfs_da_hashname(rentry->name, rentry->namelen);
+ if (ent->flags & XFS_ATTR_PARENT) {
+ xchk_da_set_corrupt(ds, level);
+ goto out;
+ }
+ calc_hash = xfs_attr_hashval(mp, ent->flags, rentry->name,
+ rentry->namelen, NULL,
+ be32_to_cpu(rentry->valuelen));
}
if (calc_hash != hash)
xchk_da_set_corrupt(ds, level);
@@ -556,6 +599,15 @@ xchk_xattr_check_sf(
break;
}
+ /*
+ * Shortform entries do not set LOCAL or INCOMPLETE, so the
+ * only valid flag bits here are for namespaces.
+ */
+ if (sfe->flags & ~XFS_ATTR_NSP_ONDISK_MASK) {
+ xchk_fblock_set_corrupt(sc, XFS_ATTR_FORK, 0);
+ break;
+ }
+
if (!xchk_xattr_set_map(sc, ab->usedmap,
(char *)sfe - (char *)sf,
sizeof(struct xfs_attr_sf_entry))) {
@@ -588,16 +640,6 @@ int
xchk_xattr(
struct xfs_scrub *sc)
{
- struct xchk_xattr sx = {
- .sc = sc,
- .context = {
- .dp = sc->ip,
- .tp = sc->tp,
- .resynch = 1,
- .put_listent = xchk_xattr_listent,
- .allow_incomplete = true,
- },
- };
xfs_dablk_t last_checked = -1U;
int error = 0;
@@ -626,12 +668,6 @@ xchk_xattr(
/*
* Look up every xattr in this file by name and hash.
*
- * Use the backend implementation of xfs_attr_list to call
- * xchk_xattr_listent on every attribute key in this inode.
- * In other words, we use the same iterator/callback mechanism
- * that listattr uses to scrub extended attributes, though in our
- * _listent function, we check the value of the attribute.
- *
* The VFS only locks i_rwsem when modifying attrs, so keep all
* three locks held because that's the only way to ensure we're
* the only thread poking into the da btree. We traverse the da
@@ -639,13 +675,9 @@ xchk_xattr(
* iteration, which doesn't really follow the usual buffer
* locking order.
*/
- error = xfs_attr_list_ilocked(&sx.context);
+ error = xchk_xattr_walk(sc, sc->ip, xchk_xattr_actor, NULL, NULL);
if (!xchk_fblock_process_error(sc, XFS_ATTR_FORK, 0, &error))
return error;
- /* Did our listent function try to return any errors? */
- if (sx.context.seen_enough < 0)
- return sx.context.seen_enough;
-
return 0;
}
diff --git a/fs/xfs/scrub/attr.h b/fs/xfs/scrub/attr.h
index 48fd9402c4..7db58af566 100644
--- a/fs/xfs/scrub/attr.h
+++ b/fs/xfs/scrub/attr.h
@@ -16,9 +16,16 @@ struct xchk_xattr_buf {
/* Bitmap of free space in xattr leaf blocks. */
unsigned long *freemap;
+ /* Memory buffer used to hold salvaged xattr names. */
+ unsigned char *name;
+
/* Memory buffer used to extract xattr values. */
void *value;
size_t value_sz;
};
+bool xchk_xattr_set_map(struct xfs_scrub *sc, unsigned long *map,
+ unsigned int start, unsigned int len);
+int xchk_setup_xattr_buf(struct xfs_scrub *sc, size_t value_size);
+
#endif /* __XFS_SCRUB_ATTR_H__ */
diff --git a/fs/xfs/scrub/attr_repair.c b/fs/xfs/scrub/attr_repair.c
new file mode 100644
index 0000000000..c7eb94069c
--- /dev/null
+++ b/fs/xfs/scrub/attr_repair.c
@@ -0,0 +1,1663 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Copyright (c) 2018-2024 Oracle. All Rights Reserved.
+ * Author: Darrick J. Wong <djwong@kernel.org>
+ */
+#include "xfs.h"
+#include "xfs_fs.h"
+#include "xfs_shared.h"
+#include "xfs_format.h"
+#include "xfs_trans_resv.h"
+#include "xfs_mount.h"
+#include "xfs_defer.h"
+#include "xfs_btree.h"
+#include "xfs_bit.h"
+#include "xfs_log_format.h"
+#include "xfs_trans.h"
+#include "xfs_sb.h"
+#include "xfs_inode.h"
+#include "xfs_da_format.h"
+#include "xfs_da_btree.h"
+#include "xfs_dir2.h"
+#include "xfs_attr.h"
+#include "xfs_attr_leaf.h"
+#include "xfs_attr_sf.h"
+#include "xfs_attr_remote.h"
+#include "xfs_bmap.h"
+#include "xfs_bmap_util.h"
+#include "xfs_exchmaps.h"
+#include "xfs_exchrange.h"
+#include "xfs_acl.h"
+#include "xfs_parent.h"
+#include "scrub/xfs_scrub.h"
+#include "scrub/scrub.h"
+#include "scrub/common.h"
+#include "scrub/trace.h"
+#include "scrub/repair.h"
+#include "scrub/tempfile.h"
+#include "scrub/tempexch.h"
+#include "scrub/xfile.h"
+#include "scrub/xfarray.h"
+#include "scrub/xfblob.h"
+#include "scrub/attr.h"
+#include "scrub/reap.h"
+#include "scrub/attr_repair.h"
+
+/*
+ * Extended Attribute Repair
+ * =========================
+ *
+ * We repair extended attributes by reading the attr leaf blocks looking for
+ * attributes entries that look salvageable (name passes verifiers, value can
+ * be retrieved, etc). Each extended attribute worth salvaging is stashed in
+ * memory, and the stashed entries are periodically replayed into a temporary
+ * file to constrain memory use. Batching the construction of the temporary
+ * extended attribute structure in this fashion reduces lock cycling of the
+ * file being repaired and the temporary file.
+ *
+ * When salvaging completes, the remaining stashed attributes are replayed to
+ * the temporary file. An atomic file contents exchange is used to commit the
+ * new xattr blocks to the file being repaired. This will disrupt attrmulti
+ * cursors.
+ */
+
+struct xrep_xattr_key {
+ /* Cookie for retrieval of the xattr name. */
+ xfblob_cookie name_cookie;
+
+ /* Cookie for retrieval of the xattr value. */
+ xfblob_cookie value_cookie;
+
+ /* XFS_ATTR_* flags */
+ int flags;
+
+ /* Length of the value and name. */
+ uint32_t valuelen;
+ uint16_t namelen;
+};
+
+/*
+ * Stash up to 8 pages of attrs in xattr_records/xattr_blobs before we write
+ * them to the temp file.
+ */
+#define XREP_XATTR_MAX_STASH_BYTES (PAGE_SIZE * 8)
+
+struct xrep_xattr {
+ struct xfs_scrub *sc;
+
+ /* Information for exchanging attr fork mappings at the end. */
+ struct xrep_tempexch tx;
+
+ /* xattr keys */
+ struct xfarray *xattr_records;
+
+ /* xattr values */
+ struct xfblob *xattr_blobs;
+
+ /* Number of attributes that we are salvaging. */
+ unsigned long long attrs_found;
+
+ /* Can we flush stashed attrs to the tempfile? */
+ bool can_flush;
+
+ /* Did the live update fail, and hence the repair is now out of date? */
+ bool live_update_aborted;
+
+ /* Lock protecting parent pointer updates */
+ struct mutex lock;
+
+ /* Fixed-size array of xrep_xattr_pptr structures. */
+ struct xfarray *pptr_recs;
+
+ /* Blobs containing parent pointer names. */
+ struct xfblob *pptr_names;
+
+ /* Hook to capture parent pointer updates. */
+ struct xfs_dir_hook dhook;
+
+ /* Scratch buffer for capturing parent pointers. */
+ struct xfs_da_args pptr_args;
+
+ /* Name buffer */
+ struct xfs_name xname;
+ char namebuf[MAXNAMELEN];
+};
+
+/* Create a parent pointer in the tempfile. */
+#define XREP_XATTR_PPTR_ADD (1)
+
+/* Remove a parent pointer from the tempfile. */
+#define XREP_XATTR_PPTR_REMOVE (2)
+
+/* A stashed parent pointer update. */
+struct xrep_xattr_pptr {
+ /* Cookie for retrieval of the pptr name. */
+ xfblob_cookie name_cookie;
+
+ /* Parent pointer record. */
+ struct xfs_parent_rec pptr_rec;
+
+ /* Length of the pptr name. */
+ uint8_t namelen;
+
+ /* XREP_XATTR_PPTR_{ADD,REMOVE} */
+ uint8_t action;
+};
+
+/* Set up to recreate the extended attributes. */
+int
+xrep_setup_xattr(
+ struct xfs_scrub *sc)
+{
+ if (xfs_has_parent(sc->mp))
+ xchk_fsgates_enable(sc, XCHK_FSGATES_DIRENTS);
+
+ return xrep_tempfile_create(sc, S_IFREG);
+}
+
+/*
+ * Decide if we want to salvage this attribute. We don't bother with
+ * incomplete or oversized keys or values. The @value parameter can be null
+ * for remote attrs.
+ */
+STATIC int
+xrep_xattr_want_salvage(
+ struct xrep_xattr *rx,
+ unsigned int attr_flags,
+ const void *name,
+ int namelen,
+ const void *value,
+ int valuelen)
+{
+ if (attr_flags & XFS_ATTR_INCOMPLETE)
+ return false;
+ if (namelen > XATTR_NAME_MAX || namelen <= 0)
+ return false;
+ if (!xfs_attr_namecheck(attr_flags, name, namelen))
+ return false;
+ if (valuelen > XATTR_SIZE_MAX || valuelen < 0)
+ return false;
+ if (attr_flags & XFS_ATTR_PARENT)
+ return xfs_parent_valuecheck(rx->sc->mp, value, valuelen);
+
+ return true;
+}
+
+/* Allocate an in-core record to hold xattrs while we rebuild the xattr data. */
+STATIC int
+xrep_xattr_salvage_key(
+ struct xrep_xattr *rx,
+ int flags,
+ unsigned char *name,
+ int namelen,
+ unsigned char *value,
+ int valuelen)
+{
+ struct xrep_xattr_key key = {
+ .valuelen = valuelen,
+ .flags = flags & XFS_ATTR_NSP_ONDISK_MASK,
+ };
+ unsigned int i = 0;
+ int error = 0;
+
+ if (xchk_should_terminate(rx->sc, &error))
+ return error;
+
+ /*
+ * Truncate the name to the first character that would trip namecheck.
+ * If we no longer have a name after that, ignore this attribute.
+ */
+ if (flags & XFS_ATTR_PARENT) {
+ key.namelen = namelen;
+
+ trace_xrep_xattr_salvage_pptr(rx->sc->ip, flags, name,
+ key.namelen, value, valuelen);
+ } else {
+ while (i < namelen && name[i] != 0)
+ i++;
+ if (i == 0)
+ return 0;
+ key.namelen = i;
+
+ trace_xrep_xattr_salvage_rec(rx->sc->ip, flags, name,
+ key.namelen, valuelen);
+ }
+
+ error = xfblob_store(rx->xattr_blobs, &key.name_cookie, name,
+ key.namelen);
+ if (error)
+ return error;
+
+ error = xfblob_store(rx->xattr_blobs, &key.value_cookie, value,
+ key.valuelen);
+ if (error)
+ return error;
+
+ error = xfarray_append(rx->xattr_records, &key);
+ if (error)
+ return error;
+
+ rx->attrs_found++;
+ return 0;
+}
+
+/*
+ * Record a shortform extended attribute key & value for later reinsertion
+ * into the inode.
+ */
+STATIC int
+xrep_xattr_salvage_sf_attr(
+ struct xrep_xattr *rx,
+ struct xfs_attr_sf_hdr *hdr,
+ struct xfs_attr_sf_entry *sfe)
+{
+ struct xfs_scrub *sc = rx->sc;
+ struct xchk_xattr_buf *ab = sc->buf;
+ unsigned char *name = sfe->nameval;
+ unsigned char *value = &sfe->nameval[sfe->namelen];
+
+ if (!xchk_xattr_set_map(sc, ab->usedmap, (char *)name - (char *)hdr,
+ sfe->namelen))
+ return 0;
+
+ if (!xchk_xattr_set_map(sc, ab->usedmap, (char *)value - (char *)hdr,
+ sfe->valuelen))
+ return 0;
+
+ if (!xrep_xattr_want_salvage(rx, sfe->flags, sfe->nameval,
+ sfe->namelen, value, sfe->valuelen))
+ return 0;
+
+ return xrep_xattr_salvage_key(rx, sfe->flags, sfe->nameval,
+ sfe->namelen, value, sfe->valuelen);
+}
+
+/*
+ * Record a local format extended attribute key & value for later reinsertion
+ * into the inode.
+ */
+STATIC int
+xrep_xattr_salvage_local_attr(
+ struct xrep_xattr *rx,
+ struct xfs_attr_leaf_entry *ent,
+ unsigned int nameidx,
+ const char *buf_end,
+ struct xfs_attr_leaf_name_local *lentry)
+{
+ struct xchk_xattr_buf *ab = rx->sc->buf;
+ unsigned char *value;
+ unsigned int valuelen;
+ unsigned int namesize;
+
+ /*
+ * Decode the leaf local entry format. If something seems wrong, we
+ * junk the attribute.
+ */
+ value = &lentry->nameval[lentry->namelen];
+ valuelen = be16_to_cpu(lentry->valuelen);
+ namesize = xfs_attr_leaf_entsize_local(lentry->namelen, valuelen);
+ if ((char *)lentry + namesize > buf_end)
+ return 0;
+ if (!xrep_xattr_want_salvage(rx, ent->flags, lentry->nameval,
+ lentry->namelen, value, valuelen))
+ return 0;
+ if (!xchk_xattr_set_map(rx->sc, ab->usedmap, nameidx, namesize))
+ return 0;
+
+ /* Try to save this attribute. */
+ return xrep_xattr_salvage_key(rx, ent->flags, lentry->nameval,
+ lentry->namelen, value, valuelen);
+}
+
+/*
+ * Record a remote format extended attribute key & value for later reinsertion
+ * into the inode.
+ */
+STATIC int
+xrep_xattr_salvage_remote_attr(
+ struct xrep_xattr *rx,
+ struct xfs_attr_leaf_entry *ent,
+ unsigned int nameidx,
+ const char *buf_end,
+ struct xfs_attr_leaf_name_remote *rentry,
+ unsigned int ent_idx,
+ struct xfs_buf *leaf_bp)
+{
+ struct xchk_xattr_buf *ab = rx->sc->buf;
+ struct xfs_da_args args = {
+ .trans = rx->sc->tp,
+ .dp = rx->sc->ip,
+ .index = ent_idx,
+ .geo = rx->sc->mp->m_attr_geo,
+ .owner = rx->sc->ip->i_ino,
+ .attr_filter = ent->flags & XFS_ATTR_NSP_ONDISK_MASK,
+ .namelen = rentry->namelen,
+ .name = rentry->name,
+ .value = ab->value,
+ .valuelen = be32_to_cpu(rentry->valuelen),
+ };
+ unsigned int namesize;
+ int error;
+
+ /*
+ * Decode the leaf remote entry format. If something seems wrong, we
+ * junk the attribute. Note that we should never find a zero-length
+ * remote attribute value.
+ */
+ namesize = xfs_attr_leaf_entsize_remote(rentry->namelen);
+ if ((char *)rentry + namesize > buf_end)
+ return 0;
+ if (args.valuelen == 0 ||
+ !xrep_xattr_want_salvage(rx, ent->flags, rentry->name,
+ rentry->namelen, NULL, args.valuelen))
+ return 0;
+ if (!xchk_xattr_set_map(rx->sc, ab->usedmap, nameidx, namesize))
+ return 0;
+
+ /*
+ * Enlarge the buffer (if needed) to hold the value that we're trying
+ * to salvage from the old extended attribute data.
+ */
+ error = xchk_setup_xattr_buf(rx->sc, args.valuelen);
+ if (error == -ENOMEM)
+ error = -EDEADLOCK;
+ if (error)
+ return error;
+
+ /* Look up the remote value and stash it for reconstruction. */
+ error = xfs_attr3_leaf_getvalue(leaf_bp, &args);
+ if (error || args.rmtblkno == 0)
+ goto err_free;
+
+ error = xfs_attr_rmtval_get(&args);
+ if (error)
+ goto err_free;
+
+ /* Try to save this attribute. */
+ error = xrep_xattr_salvage_key(rx, ent->flags, rentry->name,
+ rentry->namelen, ab->value, args.valuelen);
+err_free:
+ /* remote value was garbage, junk it */
+ if (error == -EFSBADCRC || error == -EFSCORRUPTED)
+ error = 0;
+ return error;
+}
+
+/* Extract every xattr key that we can from this attr fork block. */
+STATIC int
+xrep_xattr_recover_leaf(
+ struct xrep_xattr *rx,
+ struct xfs_buf *bp)
+{
+ struct xfs_attr3_icleaf_hdr leafhdr;
+ struct xfs_scrub *sc = rx->sc;
+ struct xfs_mount *mp = sc->mp;
+ struct xfs_attr_leafblock *leaf;
+ struct xfs_attr_leaf_name_local *lentry;
+ struct xfs_attr_leaf_name_remote *rentry;
+ struct xfs_attr_leaf_entry *ent;
+ struct xfs_attr_leaf_entry *entries;
+ struct xchk_xattr_buf *ab = rx->sc->buf;
+ char *buf_end;
+ size_t off;
+ unsigned int nameidx;
+ unsigned int hdrsize;
+ int i;
+ int error = 0;
+
+ bitmap_zero(ab->usedmap, mp->m_attr_geo->blksize);
+
+ /* Check the leaf header */
+ leaf = bp->b_addr;
+ xfs_attr3_leaf_hdr_from_disk(mp->m_attr_geo, &leafhdr, leaf);
+ hdrsize = xfs_attr3_leaf_hdr_size(leaf);
+ xchk_xattr_set_map(sc, ab->usedmap, 0, hdrsize);
+ entries = xfs_attr3_leaf_entryp(leaf);
+
+ buf_end = (char *)bp->b_addr + mp->m_attr_geo->blksize;
+ for (i = 0, ent = entries; i < leafhdr.count; ent++, i++) {
+ if (xchk_should_terminate(sc, &error))
+ return error;
+
+ /* Skip key if it conflicts with something else? */
+ off = (char *)ent - (char *)leaf;
+ if (!xchk_xattr_set_map(sc, ab->usedmap, off,
+ sizeof(xfs_attr_leaf_entry_t)))
+ continue;
+
+ /* Check the name information. */
+ nameidx = be16_to_cpu(ent->nameidx);
+ if (nameidx < leafhdr.firstused ||
+ nameidx >= mp->m_attr_geo->blksize)
+ continue;
+
+ if (ent->flags & XFS_ATTR_LOCAL) {
+ lentry = xfs_attr3_leaf_name_local(leaf, i);
+ error = xrep_xattr_salvage_local_attr(rx, ent, nameidx,
+ buf_end, lentry);
+ } else {
+ rentry = xfs_attr3_leaf_name_remote(leaf, i);
+ error = xrep_xattr_salvage_remote_attr(rx, ent, nameidx,
+ buf_end, rentry, i, bp);
+ }
+ if (error)
+ return error;
+ }
+
+ return 0;
+}
+
+/* Try to recover shortform attrs. */
+STATIC int
+xrep_xattr_recover_sf(
+ struct xrep_xattr *rx)
+{
+ struct xfs_scrub *sc = rx->sc;
+ struct xchk_xattr_buf *ab = sc->buf;
+ struct xfs_attr_sf_hdr *hdr;
+ struct xfs_attr_sf_entry *sfe;
+ struct xfs_attr_sf_entry *next;
+ struct xfs_ifork *ifp;
+ unsigned char *end;
+ int i;
+ int error = 0;
+
+ ifp = xfs_ifork_ptr(rx->sc->ip, XFS_ATTR_FORK);
+ hdr = ifp->if_data;
+
+ bitmap_zero(ab->usedmap, ifp->if_bytes);
+ end = (unsigned char *)ifp->if_data + ifp->if_bytes;
+ xchk_xattr_set_map(sc, ab->usedmap, 0, sizeof(*hdr));
+
+ sfe = xfs_attr_sf_firstentry(hdr);
+ if ((unsigned char *)sfe > end)
+ return 0;
+
+ for (i = 0; i < hdr->count; i++) {
+ if (xchk_should_terminate(sc, &error))
+ return error;
+
+ next = xfs_attr_sf_nextentry(sfe);
+ if ((unsigned char *)next > end)
+ break;
+
+ if (xchk_xattr_set_map(sc, ab->usedmap,
+ (char *)sfe - (char *)hdr,
+ sizeof(struct xfs_attr_sf_entry))) {
+ /*
+ * No conflicts with the sf entry; let's save this
+ * attribute.
+ */
+ error = xrep_xattr_salvage_sf_attr(rx, hdr, sfe);
+ if (error)
+ return error;
+ }
+
+ sfe = next;
+ }
+
+ return 0;
+}
+
+/*
+ * Try to return a buffer of xattr data for a given physical extent.
+ *
+ * Because the buffer cache get function complains if it finds a buffer
+ * matching the block number but not matching the length, we must be careful to
+ * look for incore buffers (up to the maximum length of a remote value) that
+ * could be hiding anywhere in the physical range. If we find an incore
+ * buffer, we can pass that to the caller. Optionally, read a single block and
+ * pass that back.
+ *
+ * Note the subtlety that remote attr value blocks for which there is no incore
+ * buffer will be passed to the callback one block at a time. These buffers
+ * will not have any ops attached and must be staled to prevent aliasing with
+ * multiblock buffers once we drop the ILOCK.
+ */
+STATIC int
+xrep_xattr_find_buf(
+ struct xfs_mount *mp,
+ xfs_fsblock_t fsbno,
+ xfs_extlen_t max_len,
+ bool can_read,
+ struct xfs_buf **bpp)
+{
+ struct xrep_bufscan scan = {
+ .daddr = XFS_FSB_TO_DADDR(mp, fsbno),
+ .max_sectors = xrep_bufscan_max_sectors(mp, max_len),
+ .daddr_step = XFS_FSB_TO_BB(mp, 1),
+ };
+ struct xfs_buf *bp;
+
+ while ((bp = xrep_bufscan_advance(mp, &scan)) != NULL) {
+ *bpp = bp;
+ return 0;
+ }
+
+ if (!can_read) {
+ *bpp = NULL;
+ return 0;
+ }
+
+ return xfs_buf_read(mp->m_ddev_targp, scan.daddr, XFS_FSB_TO_BB(mp, 1),
+ XBF_TRYLOCK, bpp, NULL);
+}
+
+/*
+ * Deal with a buffer that we found during our walk of the attr fork.
+ *
+ * Attribute leaf and node blocks are simple -- they're a single block, so we
+ * can walk them one at a time and we never have to worry about discontiguous
+ * multiblock buffers like we do for directories.
+ *
+ * Unfortunately, remote attr blocks add a lot of complexity here. Each disk
+ * block is totally self contained, in the sense that the v5 header provides no
+ * indication that there could be more data in the next block. The incore
+ * buffers can span multiple blocks, though they never cross extent records.
+ * However, they don't necessarily start or end on an extent record boundary.
+ * Therefore, we need a special buffer find function to walk the buffer cache
+ * for us.
+ *
+ * The caller must hold the ILOCK on the file being repaired. We use
+ * XBF_TRYLOCK here to skip any locked buffer on the assumption that we don't
+ * own the block and don't want to hang the system on a potentially garbage
+ * buffer.
+ */
+STATIC int
+xrep_xattr_recover_block(
+ struct xrep_xattr *rx,
+ xfs_dablk_t dabno,
+ xfs_fsblock_t fsbno,
+ xfs_extlen_t max_len,
+ xfs_extlen_t *actual_len)
+{
+ struct xfs_da_blkinfo *info;
+ struct xfs_buf *bp;
+ int error;
+
+ error = xrep_xattr_find_buf(rx->sc->mp, fsbno, max_len, true, &bp);
+ if (error)
+ return error;
+ info = bp->b_addr;
+ *actual_len = XFS_BB_TO_FSB(rx->sc->mp, bp->b_length);
+
+ trace_xrep_xattr_recover_leafblock(rx->sc->ip, dabno,
+ be16_to_cpu(info->magic));
+
+ /*
+ * If the buffer has the right magic number for an attr leaf block and
+ * passes a structure check (we don't care about checksums), salvage
+ * as much as we can from the block. */
+ if (info->magic == cpu_to_be16(XFS_ATTR3_LEAF_MAGIC) &&
+ xrep_buf_verify_struct(bp, &xfs_attr3_leaf_buf_ops) &&
+ xfs_attr3_leaf_header_check(bp, rx->sc->ip->i_ino) == NULL)
+ error = xrep_xattr_recover_leaf(rx, bp);
+
+ /*
+ * If the buffer didn't already have buffer ops set, it was read in by
+ * the _find_buf function and could very well be /part/ of a multiblock
+ * remote block. Mark it stale so that it doesn't hang around in
+ * memory to cause problems.
+ */
+ if (bp->b_ops == NULL)
+ xfs_buf_stale(bp);
+
+ xfs_buf_relse(bp);
+ return error;
+}
+
+/* Insert one xattr key/value. */
+STATIC int
+xrep_xattr_insert_rec(
+ struct xrep_xattr *rx,
+ const struct xrep_xattr_key *key)
+{
+ struct xfs_da_args args = {
+ .dp = rx->sc->tempip,
+ .attr_filter = key->flags,
+ .namelen = key->namelen,
+ .valuelen = key->valuelen,
+ .owner = rx->sc->ip->i_ino,
+ .geo = rx->sc->mp->m_attr_geo,
+ .whichfork = XFS_ATTR_FORK,
+ .op_flags = XFS_DA_OP_OKNOENT,
+ };
+ struct xchk_xattr_buf *ab = rx->sc->buf;
+ int error;
+
+ /*
+ * Grab pointers to the scrub buffer so that we can use them to insert
+ * attrs into the temp file.
+ */
+ args.name = ab->name;
+ args.value = ab->value;
+
+ /*
+ * The attribute name is stored near the end of the in-core buffer,
+ * though we reserve one more byte to ensure null termination.
+ */
+ ab->name[XATTR_NAME_MAX] = 0;
+
+ error = xfblob_load(rx->xattr_blobs, key->name_cookie, ab->name,
+ key->namelen);
+ if (error)
+ return error;
+
+ error = xfblob_free(rx->xattr_blobs, key->name_cookie);
+ if (error)
+ return error;
+
+ error = xfblob_load(rx->xattr_blobs, key->value_cookie, args.value,
+ key->valuelen);
+ if (error)
+ return error;
+
+ error = xfblob_free(rx->xattr_blobs, key->value_cookie);
+ if (error)
+ return error;
+
+ ab->name[key->namelen] = 0;
+
+ if (key->flags & XFS_ATTR_PARENT) {
+ trace_xrep_xattr_insert_pptr(rx->sc->tempip, key->flags,
+ ab->name, key->namelen, ab->value,
+ key->valuelen);
+ args.op_flags |= XFS_DA_OP_LOGGED;
+ } else {
+ trace_xrep_xattr_insert_rec(rx->sc->tempip, key->flags,
+ ab->name, key->namelen, key->valuelen);
+ }
+
+ /*
+ * xfs_attr_set creates and commits its own transaction. If the attr
+ * already exists, we'll just drop it during the rebuild.
+ */
+ xfs_attr_sethash(&args);
+ error = xfs_attr_set(&args, XFS_ATTRUPDATE_CREATE, false);
+ if (error == -EEXIST)
+ error = 0;
+
+ return error;
+}
+
+/*
+ * Periodically flush salvaged attributes to the temporary file. This is done
+ * to reduce the memory requirements of the xattr rebuild because files can
+ * contain millions of attributes.
+ */
+STATIC int
+xrep_xattr_flush_stashed(
+ struct xrep_xattr *rx)
+{
+ xfarray_idx_t array_cur;
+ int error;
+
+ /*
+ * Entering this function, the scrub context has a reference to the
+ * inode being repaired, the temporary file, and a scrub transaction
+ * that we use during xattr salvaging to avoid livelocking if there
+ * are cycles in the xattr structures. We hold ILOCK_EXCL on both
+ * the inode being repaired, though it is not ijoined to the scrub
+ * transaction.
+ *
+ * To constrain kernel memory use, we occasionally flush salvaged
+ * xattrs from the xfarray and xfblob structures into the temporary
+ * file in preparation for exchanging the xattr structures at the end.
+ * Updating the temporary file requires a transaction, so we commit the
+ * scrub transaction and drop the two ILOCKs so that xfs_attr_set can
+ * allocate whatever transaction it wants.
+ *
+ * We still hold IOLOCK_EXCL on the inode being repaired, which
+ * prevents anyone from modifying the damaged xattr data while we
+ * repair it.
+ */
+ error = xrep_trans_commit(rx->sc);
+ if (error)
+ return error;
+ xchk_iunlock(rx->sc, XFS_ILOCK_EXCL);
+
+ /*
+ * Take the IOLOCK of the temporary file while we modify xattrs. This
+ * isn't strictly required because the temporary file is never revealed
+ * to userspace, but we follow the same locking rules. We still hold
+ * sc->ip's IOLOCK.
+ */
+ error = xrep_tempfile_iolock_polled(rx->sc);
+ if (error)
+ return error;
+
+ /* Add all the salvaged attrs to the temporary file. */
+ foreach_xfarray_idx(rx->xattr_records, array_cur) {
+ struct xrep_xattr_key key;
+
+ error = xfarray_load(rx->xattr_records, array_cur, &key);
+ if (error)
+ return error;
+
+ error = xrep_xattr_insert_rec(rx, &key);
+ if (error)
+ return error;
+ }
+
+ /* Empty out both arrays now that we've added the entries. */
+ xfarray_truncate(rx->xattr_records);
+ xfblob_truncate(rx->xattr_blobs);
+
+ xrep_tempfile_iounlock(rx->sc);
+
+ /* Recreate the salvage transaction and relock the inode. */
+ error = xchk_trans_alloc(rx->sc, 0);
+ if (error)
+ return error;
+ xchk_ilock(rx->sc, XFS_ILOCK_EXCL);
+ return 0;
+}
+
+/* Decide if we've stashed too much xattr data in memory. */
+static inline bool
+xrep_xattr_want_flush_stashed(
+ struct xrep_xattr *rx)
+{
+ unsigned long long bytes;
+
+ if (!rx->can_flush)
+ return false;
+
+ bytes = xfarray_bytes(rx->xattr_records) +
+ xfblob_bytes(rx->xattr_blobs);
+ return bytes > XREP_XATTR_MAX_STASH_BYTES;
+}
+
+/*
+ * Did we observe rename changing parent pointer xattrs while we were flushing
+ * salvaged attrs?
+ */
+static inline bool
+xrep_xattr_saw_pptr_conflict(
+ struct xrep_xattr *rx)
+{
+ bool ret;
+
+ ASSERT(rx->can_flush);
+
+ if (!xfs_has_parent(rx->sc->mp))
+ return false;
+
+ xfs_assert_ilocked(rx->sc->ip, XFS_ILOCK_EXCL);
+
+ mutex_lock(&rx->lock);
+ ret = xfarray_bytes(rx->pptr_recs) > 0;
+ mutex_unlock(&rx->lock);
+
+ return ret;
+}
+
+/*
+ * Reset the entire repair state back to initial conditions, now that we've
+ * detected a parent pointer update to the attr structure while we were
+ * flushing salvaged attrs. See the locking notes in dir_repair.c for more
+ * information on why this is all necessary.
+ */
+STATIC int
+xrep_xattr_full_reset(
+ struct xrep_xattr *rx)
+{
+ struct xfs_scrub *sc = rx->sc;
+ struct xfs_attr_sf_hdr *hdr;
+ struct xfs_ifork *ifp = &sc->tempip->i_af;
+ int error;
+
+ trace_xrep_xattr_full_reset(sc->ip, sc->tempip);
+
+ /* The temporary file's data fork had better not be in btree format. */
+ if (sc->tempip->i_df.if_format == XFS_DINODE_FMT_BTREE) {
+ ASSERT(0);
+ return -EIO;
+ }
+
+ /*
+ * We begin in transaction context with sc->ip ILOCKed but not joined
+ * to the transaction. To reset to the initial state, we must hold
+ * sc->ip's ILOCK to prevent rename from updating parent pointer
+ * information and the tempfile's ILOCK to clear its contents.
+ */
+ xchk_iunlock(rx->sc, XFS_ILOCK_EXCL);
+ xrep_tempfile_ilock_both(sc);
+ xfs_trans_ijoin(sc->tp, sc->ip, 0);
+ xfs_trans_ijoin(sc->tp, sc->tempip, 0);
+
+ /*
+ * Free all the blocks of the attr fork of the temp file, and reset
+ * it back to local format.
+ */
+ if (xfs_ifork_has_extents(&sc->tempip->i_af)) {
+ error = xrep_reap_ifork(sc, sc->tempip, XFS_ATTR_FORK);
+ if (error)
+ return error;
+
+ ASSERT(ifp->if_bytes == 0);
+ ifp->if_format = XFS_DINODE_FMT_LOCAL;
+ xfs_idata_realloc(sc->tempip, sizeof(*hdr), XFS_ATTR_FORK);
+ }
+
+ /* Reinitialize the attr fork to an empty shortform structure. */
+ hdr = ifp->if_data;
+ memset(hdr, 0, sizeof(*hdr));
+ hdr->totsize = cpu_to_be16(sizeof(*hdr));
+ xfs_trans_log_inode(sc->tp, sc->tempip, XFS_ILOG_CORE | XFS_ILOG_ADATA);
+
+ /*
+ * Roll this transaction to commit our reset ondisk. The tempfile
+ * should no longer be joined to the transaction, so we drop its ILOCK.
+ * This should leave us in transaction context with sc->ip ILOCKed but
+ * not joined to the transaction.
+ */
+ error = xrep_roll_trans(sc);
+ if (error)
+ return error;
+ xrep_tempfile_iunlock(sc);
+
+ /*
+ * Erase any accumulated parent pointer updates now that we've erased
+ * the tempfile's attr fork. We're resetting the entire repair state
+ * back to where we were initially, except now we won't flush salvaged
+ * xattrs until the very end.
+ */
+ mutex_lock(&rx->lock);
+ xfarray_truncate(rx->pptr_recs);
+ xfblob_truncate(rx->pptr_names);
+ mutex_unlock(&rx->lock);
+
+ rx->can_flush = false;
+ rx->attrs_found = 0;
+
+ ASSERT(xfarray_bytes(rx->xattr_records) == 0);
+ ASSERT(xfblob_bytes(rx->xattr_blobs) == 0);
+ return 0;
+}
+
+/* Extract as many attribute keys and values as we can. */
+STATIC int
+xrep_xattr_recover(
+ struct xrep_xattr *rx)
+{
+ struct xfs_bmbt_irec got;
+ struct xfs_scrub *sc = rx->sc;
+ struct xfs_da_geometry *geo = sc->mp->m_attr_geo;
+ xfs_fileoff_t offset;
+ xfs_extlen_t len;
+ xfs_dablk_t dabno;
+ int nmap;
+ int error;
+
+restart:
+ /*
+ * Iterate each xattr leaf block in the attr fork to scan them for any
+ * attributes that we might salvage.
+ */
+ for (offset = 0;
+ offset < XFS_MAX_FILEOFF;
+ offset = got.br_startoff + got.br_blockcount) {
+ nmap = 1;
+ error = xfs_bmapi_read(sc->ip, offset, XFS_MAX_FILEOFF - offset,
+ &got, &nmap, XFS_BMAPI_ATTRFORK);
+ if (error)
+ return error;
+ if (nmap != 1)
+ return -EFSCORRUPTED;
+ if (!xfs_bmap_is_written_extent(&got))
+ continue;
+
+ for (dabno = round_up(got.br_startoff, geo->fsbcount);
+ dabno < got.br_startoff + got.br_blockcount;
+ dabno += len) {
+ xfs_fileoff_t curr_offset = dabno - got.br_startoff;
+ xfs_extlen_t maxlen;
+
+ if (xchk_should_terminate(rx->sc, &error))
+ return error;
+
+ maxlen = min_t(xfs_filblks_t, INT_MAX,
+ got.br_blockcount - curr_offset);
+ error = xrep_xattr_recover_block(rx, dabno,
+ curr_offset + got.br_startblock,
+ maxlen, &len);
+ if (error)
+ return error;
+
+ if (xrep_xattr_want_flush_stashed(rx)) {
+ error = xrep_xattr_flush_stashed(rx);
+ if (error)
+ return error;
+
+ if (xrep_xattr_saw_pptr_conflict(rx)) {
+ error = xrep_xattr_full_reset(rx);
+ if (error)
+ return error;
+
+ goto restart;
+ }
+ }
+ }
+ }
+
+ return 0;
+}
+
+/*
+ * Reset the extended attribute fork to a state where we can start re-adding
+ * the salvaged attributes.
+ */
+STATIC int
+xrep_xattr_fork_remove(
+ struct xfs_scrub *sc,
+ struct xfs_inode *ip)
+{
+ struct xfs_attr_sf_hdr *hdr;
+ struct xfs_ifork *ifp = xfs_ifork_ptr(ip, XFS_ATTR_FORK);
+
+ /*
+ * If the data fork is in btree format, we can't change di_forkoff
+ * because we could run afoul of the rule that the data fork isn't
+ * supposed to be in btree format if there's enough space in the fork
+ * that it could have used extents format. Instead, reinitialize the
+ * attr fork to have a shortform structure with zero attributes.
+ */
+ if (ip->i_df.if_format == XFS_DINODE_FMT_BTREE) {
+ ifp->if_format = XFS_DINODE_FMT_LOCAL;
+ hdr = xfs_idata_realloc(ip, (int)sizeof(*hdr) - ifp->if_bytes,
+ XFS_ATTR_FORK);
+ hdr->count = 0;
+ hdr->totsize = cpu_to_be16(sizeof(*hdr));
+ xfs_trans_log_inode(sc->tp, ip,
+ XFS_ILOG_CORE | XFS_ILOG_ADATA);
+ return 0;
+ }
+
+ /* If we still have attr fork extents, something's wrong. */
+ if (ifp->if_nextents != 0) {
+ struct xfs_iext_cursor icur;
+ struct xfs_bmbt_irec irec;
+ unsigned int i = 0;
+
+ xfs_emerg(sc->mp,
+ "inode 0x%llx attr fork still has %llu attr extents, format %d?!",
+ ip->i_ino, ifp->if_nextents, ifp->if_format);
+ for_each_xfs_iext(ifp, &icur, &irec) {
+ xfs_err(sc->mp,
+ "[%u]: startoff %llu startblock %llu blockcount %llu state %u",
+ i++, irec.br_startoff,
+ irec.br_startblock, irec.br_blockcount,
+ irec.br_state);
+ }
+ ASSERT(0);
+ return -EFSCORRUPTED;
+ }
+
+ xfs_attr_fork_remove(ip, sc->tp);
+ return 0;
+}
+
+/*
+ * Free all the attribute fork blocks of the file being repaired and delete the
+ * fork. The caller must ILOCK the scrub file and join it to the transaction.
+ * This function returns with the inode joined to a clean transaction.
+ */
+int
+xrep_xattr_reset_fork(
+ struct xfs_scrub *sc)
+{
+ int error;
+
+ trace_xrep_xattr_reset_fork(sc->ip, sc->ip);
+
+ /* Unmap all the attr blocks. */
+ if (xfs_ifork_has_extents(&sc->ip->i_af)) {
+ error = xrep_reap_ifork(sc, sc->ip, XFS_ATTR_FORK);
+ if (error)
+ return error;
+ }
+
+ error = xrep_xattr_fork_remove(sc, sc->ip);
+ if (error)
+ return error;
+
+ return xfs_trans_roll_inode(&sc->tp, sc->ip);
+}
+
+/*
+ * Free all the attribute fork blocks of the temporary file and delete the attr
+ * fork. The caller must ILOCK the tempfile and join it to the transaction.
+ * This function returns with the inode joined to a clean scrub transaction.
+ */
+int
+xrep_xattr_reset_tempfile_fork(
+ struct xfs_scrub *sc)
+{
+ int error;
+
+ trace_xrep_xattr_reset_fork(sc->ip, sc->tempip);
+
+ /*
+ * Wipe out the attr fork of the temp file so that regular inode
+ * inactivation won't trip over the corrupt attr fork.
+ */
+ if (xfs_ifork_has_extents(&sc->tempip->i_af)) {
+ error = xrep_reap_ifork(sc, sc->tempip, XFS_ATTR_FORK);
+ if (error)
+ return error;
+ }
+
+ return xrep_xattr_fork_remove(sc, sc->tempip);
+}
+
+/*
+ * Find all the extended attributes for this inode by scraping them out of the
+ * attribute key blocks by hand, and flushing them into the temp file.
+ * When we're done, free the staging memory before exchanging the xattr
+ * structures to reduce memory usage.
+ */
+STATIC int
+xrep_xattr_salvage_attributes(
+ struct xrep_xattr *rx)
+{
+ struct xfs_inode *ip = rx->sc->ip;
+ int error;
+
+ /* Short format xattrs are easy! */
+ if (rx->sc->ip->i_af.if_format == XFS_DINODE_FMT_LOCAL) {
+ error = xrep_xattr_recover_sf(rx);
+ if (error)
+ return error;
+
+ return xrep_xattr_flush_stashed(rx);
+ }
+
+ /*
+ * For non-inline xattr structures, the salvage function scans the
+ * buffer cache looking for potential attr leaf blocks. The scan
+ * requires the ability to lock any buffer found and runs independently
+ * of any transaction <-> buffer item <-> buffer linkage. Therefore,
+ * roll the transaction to ensure there are no buffers joined. We hold
+ * the ILOCK independently of the transaction.
+ */
+ error = xfs_trans_roll(&rx->sc->tp);
+ if (error)
+ return error;
+
+ error = xfs_iread_extents(rx->sc->tp, ip, XFS_ATTR_FORK);
+ if (error)
+ return error;
+
+ error = xrep_xattr_recover(rx);
+ if (error)
+ return error;
+
+ return xrep_xattr_flush_stashed(rx);
+}
+
+/*
+ * Add this stashed incore parent pointer to the temporary file. The caller
+ * must hold the tempdir's IOLOCK, must not hold any ILOCKs, and must not be in
+ * transaction context.
+ */
+STATIC int
+xrep_xattr_replay_pptr_update(
+ struct xrep_xattr *rx,
+ const struct xfs_name *xname,
+ struct xrep_xattr_pptr *pptr)
+{
+ struct xfs_scrub *sc = rx->sc;
+ int error;
+
+ switch (pptr->action) {
+ case XREP_XATTR_PPTR_ADD:
+ /* Create parent pointer. */
+ trace_xrep_xattr_replay_parentadd(sc->tempip, xname,
+ &pptr->pptr_rec);
+
+ error = xfs_parent_set(sc->tempip, sc->ip->i_ino, xname,
+ &pptr->pptr_rec, &rx->pptr_args);
+ ASSERT(error != -EEXIST);
+ return error;
+ case XREP_XATTR_PPTR_REMOVE:
+ /* Remove parent pointer. */
+ trace_xrep_xattr_replay_parentremove(sc->tempip, xname,
+ &pptr->pptr_rec);
+
+ error = xfs_parent_unset(sc->tempip, sc->ip->i_ino, xname,
+ &pptr->pptr_rec, &rx->pptr_args);
+ ASSERT(error != -ENOATTR);
+ return error;
+ }
+
+ ASSERT(0);
+ return -EIO;
+}
+
+/*
+ * Flush stashed parent pointer updates that have been recorded by the scanner.
+ * This is done to reduce the memory requirements of the xattr rebuild, since
+ * files can have a lot of hardlinks and the fs can be busy.
+ *
+ * Caller must not hold transactions or ILOCKs. Caller must hold the tempfile
+ * IOLOCK.
+ */
+STATIC int
+xrep_xattr_replay_pptr_updates(
+ struct xrep_xattr *rx)
+{
+ xfarray_idx_t array_cur;
+ int error;
+
+ mutex_lock(&rx->lock);
+ foreach_xfarray_idx(rx->pptr_recs, array_cur) {
+ struct xrep_xattr_pptr pptr;
+
+ error = xfarray_load(rx->pptr_recs, array_cur, &pptr);
+ if (error)
+ goto out_unlock;
+
+ error = xfblob_loadname(rx->pptr_names, pptr.name_cookie,
+ &rx->xname, pptr.namelen);
+ if (error)
+ goto out_unlock;
+ mutex_unlock(&rx->lock);
+
+ error = xrep_xattr_replay_pptr_update(rx, &rx->xname, &pptr);
+ if (error)
+ return error;
+
+ mutex_lock(&rx->lock);
+ }
+
+ /* Empty out both arrays now that we've added the entries. */
+ xfarray_truncate(rx->pptr_recs);
+ xfblob_truncate(rx->pptr_names);
+ mutex_unlock(&rx->lock);
+ return 0;
+out_unlock:
+ mutex_unlock(&rx->lock);
+ return error;
+}
+
+/*
+ * Remember that we want to create a parent pointer in the tempfile. These
+ * stashed actions will be replayed later.
+ */
+STATIC int
+xrep_xattr_stash_parentadd(
+ struct xrep_xattr *rx,
+ const struct xfs_name *name,
+ const struct xfs_inode *dp)
+{
+ struct xrep_xattr_pptr pptr = {
+ .action = XREP_XATTR_PPTR_ADD,
+ .namelen = name->len,
+ };
+ int error;
+
+ trace_xrep_xattr_stash_parentadd(rx->sc->tempip, dp, name);
+
+ xfs_inode_to_parent_rec(&pptr.pptr_rec, dp);
+ error = xfblob_storename(rx->pptr_names, &pptr.name_cookie, name);
+ if (error)
+ return error;
+
+ return xfarray_append(rx->pptr_recs, &pptr);
+}
+
+/*
+ * Remember that we want to remove a parent pointer from the tempfile. These
+ * stashed actions will be replayed later.
+ */
+STATIC int
+xrep_xattr_stash_parentremove(
+ struct xrep_xattr *rx,
+ const struct xfs_name *name,
+ const struct xfs_inode *dp)
+{
+ struct xrep_xattr_pptr pptr = {
+ .action = XREP_XATTR_PPTR_REMOVE,
+ .namelen = name->len,
+ };
+ int error;
+
+ trace_xrep_xattr_stash_parentremove(rx->sc->tempip, dp, name);
+
+ xfs_inode_to_parent_rec(&pptr.pptr_rec, dp);
+ error = xfblob_storename(rx->pptr_names, &pptr.name_cookie, name);
+ if (error)
+ return error;
+
+ return xfarray_append(rx->pptr_recs, &pptr);
+}
+
+/*
+ * Capture dirent updates being made by other threads. We will have to replay
+ * the parent pointer updates before exchanging attr forks.
+ */
+STATIC int
+xrep_xattr_live_dirent_update(
+ struct notifier_block *nb,
+ unsigned long action,
+ void *data)
+{
+ struct xfs_dir_update_params *p = data;
+ struct xrep_xattr *rx;
+ struct xfs_scrub *sc;
+ int error;
+
+ rx = container_of(nb, struct xrep_xattr, dhook.dirent_hook.nb);
+ sc = rx->sc;
+
+ /*
+ * This thread updated a dirent that points to the file that we're
+ * repairing, so stash the update for replay against the temporary
+ * file.
+ */
+ if (p->ip->i_ino != sc->ip->i_ino)
+ return NOTIFY_DONE;
+
+ mutex_lock(&rx->lock);
+ if (p->delta > 0)
+ error = xrep_xattr_stash_parentadd(rx, p->name, p->dp);
+ else
+ error = xrep_xattr_stash_parentremove(rx, p->name, p->dp);
+ if (error)
+ rx->live_update_aborted = true;
+ mutex_unlock(&rx->lock);
+ return NOTIFY_DONE;
+}
+
+/*
+ * Prepare both inodes' attribute forks for an exchange. Promote the tempfile
+ * from short format to leaf format, and if the file being repaired has a short
+ * format attr fork, turn it into an empty extent list.
+ */
+STATIC int
+xrep_xattr_swap_prep(
+ struct xfs_scrub *sc,
+ bool temp_local,
+ bool ip_local)
+{
+ int error;
+
+ /*
+ * If the tempfile's attributes are in shortform format, convert that
+ * to a single leaf extent so that we can use the atomic mapping
+ * exchange.
+ */
+ if (temp_local) {
+ struct xfs_da_args args = {
+ .dp = sc->tempip,
+ .geo = sc->mp->m_attr_geo,
+ .whichfork = XFS_ATTR_FORK,
+ .trans = sc->tp,
+ .total = 1,
+ .owner = sc->ip->i_ino,
+ };
+
+ error = xfs_attr_shortform_to_leaf(&args);
+ if (error)
+ return error;
+
+ /*
+ * Roll the deferred log items to get us back to a clean
+ * transaction.
+ */
+ error = xfs_defer_finish(&sc->tp);
+ if (error)
+ return error;
+ }
+
+ /*
+ * If the file being repaired had a shortform attribute fork, convert
+ * that to an empty extent list in preparation for the atomic mapping
+ * exchange.
+ */
+ if (ip_local) {
+ struct xfs_ifork *ifp;
+
+ ifp = xfs_ifork_ptr(sc->ip, XFS_ATTR_FORK);
+
+ xfs_idestroy_fork(ifp);
+ ifp->if_format = XFS_DINODE_FMT_EXTENTS;
+ ifp->if_nextents = 0;
+ ifp->if_bytes = 0;
+ ifp->if_data = NULL;
+ ifp->if_height = 0;
+
+ xfs_trans_log_inode(sc->tp, sc->ip,
+ XFS_ILOG_CORE | XFS_ILOG_ADATA);
+ }
+
+ return 0;
+}
+
+/* Exchange the temporary file's attribute fork with the one being repaired. */
+int
+xrep_xattr_swap(
+ struct xfs_scrub *sc,
+ struct xrep_tempexch *tx)
+{
+ bool ip_local, temp_local;
+ int error = 0;
+
+ ip_local = sc->ip->i_af.if_format == XFS_DINODE_FMT_LOCAL;
+ temp_local = sc->tempip->i_af.if_format == XFS_DINODE_FMT_LOCAL;
+
+ /*
+ * If the both files have a local format attr fork and the rebuilt
+ * xattr data would fit in the repaired file's attr fork, just copy
+ * the contents from the tempfile and declare ourselves done.
+ */
+ if (ip_local && temp_local) {
+ int forkoff;
+ int newsize;
+
+ newsize = xfs_attr_sf_totsize(sc->tempip);
+ forkoff = xfs_attr_shortform_bytesfit(sc->ip, newsize);
+ if (forkoff > 0) {
+ sc->ip->i_forkoff = forkoff;
+ xrep_tempfile_copyout_local(sc, XFS_ATTR_FORK);
+ return 0;
+ }
+ }
+
+ /* Otherwise, make sure both attr forks are in block-mapping mode. */
+ error = xrep_xattr_swap_prep(sc, temp_local, ip_local);
+ if (error)
+ return error;
+
+ return xrep_tempexch_contents(sc, tx);
+}
+
+/*
+ * Finish replaying stashed parent pointer updates, allocate a transaction for
+ * exchanging extent mappings, and take the ILOCKs of both files before we
+ * commit the new extended attribute structure.
+ */
+STATIC int
+xrep_xattr_finalize_tempfile(
+ struct xrep_xattr *rx)
+{
+ struct xfs_scrub *sc = rx->sc;
+ int error;
+
+ if (!xfs_has_parent(sc->mp))
+ return xrep_tempexch_trans_alloc(sc, XFS_ATTR_FORK, &rx->tx);
+
+ /*
+ * Repair relies on the ILOCK to quiesce all possible xattr updates.
+ * Replay all queued parent pointer updates into the tempfile before
+ * exchanging the contents, even if that means dropping the ILOCKs and
+ * the transaction.
+ */
+ do {
+ error = xrep_xattr_replay_pptr_updates(rx);
+ if (error)
+ return error;
+
+ error = xrep_tempexch_trans_alloc(sc, XFS_ATTR_FORK, &rx->tx);
+ if (error)
+ return error;
+
+ if (xfarray_length(rx->pptr_recs) == 0)
+ break;
+
+ xchk_trans_cancel(sc);
+ xrep_tempfile_iunlock_both(sc);
+ } while (!xchk_should_terminate(sc, &error));
+ return error;
+}
+
+/*
+ * Exchange the new extended attribute data (which we created in the tempfile)
+ * with the file being repaired.
+ */
+STATIC int
+xrep_xattr_rebuild_tree(
+ struct xrep_xattr *rx)
+{
+ struct xfs_scrub *sc = rx->sc;
+ int error;
+
+ /*
+ * If we didn't find any attributes to salvage, repair the file by
+ * zapping its attr fork.
+ */
+ if (rx->attrs_found == 0) {
+ xfs_trans_ijoin(sc->tp, sc->ip, 0);
+ error = xrep_xattr_reset_fork(sc);
+ if (error)
+ return error;
+
+ goto forget_acls;
+ }
+
+ trace_xrep_xattr_rebuild_tree(sc->ip, sc->tempip);
+
+ /*
+ * Commit the repair transaction and drop the ILOCKs so that we can use
+ * the atomic file content exchange helper functions to compute the
+ * correct resource reservations.
+ *
+ * We still hold IOLOCK_EXCL (aka i_rwsem) which will prevent xattr
+ * modifications, but there's nothing to prevent userspace from reading
+ * the attributes until we're ready for the exchange operation. Reads
+ * will return -EIO without shutting down the fs, so we're ok with
+ * that.
+ */
+ error = xrep_trans_commit(sc);
+ if (error)
+ return error;
+
+ xchk_iunlock(sc, XFS_ILOCK_EXCL);
+
+ /*
+ * Take the IOLOCK on the temporary file so that we can run xattr
+ * operations with the same locks held as we would for a normal file.
+ * We still hold sc->ip's IOLOCK.
+ */
+ error = xrep_tempfile_iolock_polled(rx->sc);
+ if (error)
+ return error;
+
+ /*
+ * Allocate transaction, lock inodes, and make sure that we've replayed
+ * all the stashed parent pointer updates to the temp file. After this
+ * point, we're ready to exchange attr fork mappings.
+ */
+ error = xrep_xattr_finalize_tempfile(rx);
+ if (error)
+ return error;
+
+ /*
+ * Exchange the blocks mapped by the tempfile's attr fork with the file
+ * being repaired. The old attr blocks will then be attached to the
+ * tempfile, so reap its attr fork.
+ */
+ error = xrep_xattr_swap(sc, &rx->tx);
+ if (error)
+ return error;
+
+ error = xrep_xattr_reset_tempfile_fork(sc);
+ if (error)
+ return error;
+
+ /*
+ * Roll to get a transaction without any inodes joined to it. Then we
+ * can drop the tempfile's ILOCK and IOLOCK before doing more work on
+ * the scrub target file.
+ */
+ error = xfs_trans_roll(&sc->tp);
+ if (error)
+ return error;
+
+ xrep_tempfile_iunlock(sc);
+ xrep_tempfile_iounlock(sc);
+
+forget_acls:
+ /* Invalidate cached ACLs now that we've reloaded all the xattrs. */
+ xfs_forget_acl(VFS_I(sc->ip), SGI_ACL_FILE);
+ xfs_forget_acl(VFS_I(sc->ip), SGI_ACL_DEFAULT);
+ return 0;
+}
+
+/* Tear down all the incore scan stuff we created. */
+STATIC void
+xrep_xattr_teardown(
+ struct xrep_xattr *rx)
+{
+ if (xfs_has_parent(rx->sc->mp))
+ xfs_dir_hook_del(rx->sc->mp, &rx->dhook);
+ if (rx->pptr_names)
+ xfblob_destroy(rx->pptr_names);
+ if (rx->pptr_recs)
+ xfarray_destroy(rx->pptr_recs);
+ xfblob_destroy(rx->xattr_blobs);
+ xfarray_destroy(rx->xattr_records);
+ mutex_destroy(&rx->lock);
+ kfree(rx);
+}
+
+/* Set up the filesystem scan so we can regenerate extended attributes. */
+STATIC int
+xrep_xattr_setup_scan(
+ struct xfs_scrub *sc,
+ struct xrep_xattr **rxp)
+{
+ struct xrep_xattr *rx;
+ char *descr;
+ int max_len;
+ int error;
+
+ rx = kzalloc(sizeof(struct xrep_xattr), XCHK_GFP_FLAGS);
+ if (!rx)
+ return -ENOMEM;
+ rx->sc = sc;
+ rx->can_flush = true;
+ rx->xname.name = rx->namebuf;
+
+ mutex_init(&rx->lock);
+
+ /*
+ * Allocate enough memory to handle loading local attr values from the
+ * xfblob data while flushing stashed attrs to the temporary file.
+ * We only realloc the buffer when salvaging remote attr values.
+ */
+ max_len = xfs_attr_leaf_entsize_local_max(sc->mp->m_attr_geo->blksize);
+ error = xchk_setup_xattr_buf(rx->sc, max_len);
+ if (error == -ENOMEM)
+ error = -EDEADLOCK;
+ if (error)
+ goto out_rx;
+
+ /* Set up some staging for salvaged attribute keys and values */
+ descr = xchk_xfile_ino_descr(sc, "xattr keys");
+ error = xfarray_create(descr, 0, sizeof(struct xrep_xattr_key),
+ &rx->xattr_records);
+ kfree(descr);
+ if (error)
+ goto out_rx;
+
+ descr = xchk_xfile_ino_descr(sc, "xattr names");
+ error = xfblob_create(descr, &rx->xattr_blobs);
+ kfree(descr);
+ if (error)
+ goto out_keys;
+
+ if (xfs_has_parent(sc->mp)) {
+ ASSERT(sc->flags & XCHK_FSGATES_DIRENTS);
+
+ descr = xchk_xfile_ino_descr(sc,
+ "xattr retained parent pointer entries");
+ error = xfarray_create(descr, 0,
+ sizeof(struct xrep_xattr_pptr),
+ &rx->pptr_recs);
+ kfree(descr);
+ if (error)
+ goto out_values;
+
+ descr = xchk_xfile_ino_descr(sc,
+ "xattr retained parent pointer names");
+ error = xfblob_create(descr, &rx->pptr_names);
+ kfree(descr);
+ if (error)
+ goto out_pprecs;
+
+ xfs_dir_hook_setup(&rx->dhook, xrep_xattr_live_dirent_update);
+ error = xfs_dir_hook_add(sc->mp, &rx->dhook);
+ if (error)
+ goto out_ppnames;
+ }
+
+ *rxp = rx;
+ return 0;
+out_ppnames:
+ xfblob_destroy(rx->pptr_names);
+out_pprecs:
+ xfarray_destroy(rx->pptr_recs);
+out_values:
+ xfblob_destroy(rx->xattr_blobs);
+out_keys:
+ xfarray_destroy(rx->xattr_records);
+out_rx:
+ mutex_destroy(&rx->lock);
+ kfree(rx);
+ return error;
+}
+
+/*
+ * Repair the extended attribute metadata.
+ *
+ * XXX: Remote attribute value buffers encompass the entire (up to 64k) buffer.
+ * The buffer cache in XFS can't handle aliased multiblock buffers, so this
+ * might misbehave if the attr fork is crosslinked with other filesystem
+ * metadata.
+ */
+int
+xrep_xattr(
+ struct xfs_scrub *sc)
+{
+ struct xrep_xattr *rx = NULL;
+ int error;
+
+ if (!xfs_inode_hasattr(sc->ip))
+ return -ENOENT;
+
+ /* The rmapbt is required to reap the old attr fork. */
+ if (!xfs_has_rmapbt(sc->mp))
+ return -EOPNOTSUPP;
+ /* We require atomic file exchange range to rebuild anything. */
+ if (!xfs_has_exchange_range(sc->mp))
+ return -EOPNOTSUPP;
+
+ error = xrep_xattr_setup_scan(sc, &rx);
+ if (error)
+ return error;
+
+ ASSERT(sc->ilock_flags & XFS_ILOCK_EXCL);
+
+ error = xrep_xattr_salvage_attributes(rx);
+ if (error)
+ goto out_scan;
+
+ if (rx->live_update_aborted) {
+ error = -EIO;
+ goto out_scan;
+ }
+
+ /* Last chance to abort before we start committing fixes. */
+ if (xchk_should_terminate(sc, &error))
+ goto out_scan;
+
+ error = xrep_xattr_rebuild_tree(rx);
+ if (error)
+ goto out_scan;
+
+out_scan:
+ xrep_xattr_teardown(rx);
+ return error;
+}
diff --git a/fs/xfs/scrub/attr_repair.h b/fs/xfs/scrub/attr_repair.h
new file mode 100644
index 0000000000..979729bd4a
--- /dev/null
+++ b/fs/xfs/scrub/attr_repair.h
@@ -0,0 +1,15 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Copyright (c) 2018-2024 Oracle. All Rights Reserved.
+ * Author: Darrick J. Wong <djwong@kernel.org>
+ */
+#ifndef __XFS_SCRUB_ATTR_REPAIR_H__
+#define __XFS_SCRUB_ATTR_REPAIR_H__
+
+struct xrep_tempexch;
+
+int xrep_xattr_swap(struct xfs_scrub *sc, struct xrep_tempexch *tx);
+int xrep_xattr_reset_fork(struct xfs_scrub *sc);
+int xrep_xattr_reset_tempfile_fork(struct xfs_scrub *sc);
+
+#endif /* __XFS_SCRUB_ATTR_REPAIR_H__ */
diff --git a/fs/xfs/scrub/bitmap.c b/fs/xfs/scrub/bitmap.c
index 0cb8d43912..7ba35a7a79 100644
--- a/fs/xfs/scrub/bitmap.c
+++ b/fs/xfs/scrub/bitmap.c
@@ -40,22 +40,23 @@ struct xbitmap64_node {
* These functions are defined by the INTERVAL_TREE_DEFINE macro, but we'll
* forward-declare them anyway for clarity.
*/
-static inline void
+static inline __maybe_unused void
xbitmap64_tree_insert(struct xbitmap64_node *node, struct rb_root_cached *root);
-static inline void
+static inline __maybe_unused void
xbitmap64_tree_remove(struct xbitmap64_node *node, struct rb_root_cached *root);
-static inline struct xbitmap64_node *
+static inline __maybe_unused struct xbitmap64_node *
xbitmap64_tree_iter_first(struct rb_root_cached *root, uint64_t start,
uint64_t last);
-static inline struct xbitmap64_node *
+static inline __maybe_unused struct xbitmap64_node *
xbitmap64_tree_iter_next(struct xbitmap64_node *node, uint64_t start,
uint64_t last);
INTERVAL_TREE_DEFINE(struct xbitmap64_node, bn_rbnode, uint64_t,
- __bn_subtree_last, START, LAST, static inline, xbitmap64_tree)
+ __bn_subtree_last, START, LAST, static inline __maybe_unused,
+ xbitmap64_tree)
/* Iterate each interval of a bitmap. Do not change the bitmap. */
#define for_each_xbitmap64_extent(bn, bitmap) \
@@ -314,22 +315,23 @@ struct xbitmap32_node {
* These functions are defined by the INTERVAL_TREE_DEFINE macro, but we'll
* forward-declare them anyway for clarity.
*/
-static inline void
+static inline __maybe_unused void
xbitmap32_tree_insert(struct xbitmap32_node *node, struct rb_root_cached *root);
-static inline void
+static inline __maybe_unused void
xbitmap32_tree_remove(struct xbitmap32_node *node, struct rb_root_cached *root);
-static inline struct xbitmap32_node *
+static inline __maybe_unused struct xbitmap32_node *
xbitmap32_tree_iter_first(struct rb_root_cached *root, uint32_t start,
uint32_t last);
-static inline struct xbitmap32_node *
+static inline __maybe_unused struct xbitmap32_node *
xbitmap32_tree_iter_next(struct xbitmap32_node *node, uint32_t start,
uint32_t last);
INTERVAL_TREE_DEFINE(struct xbitmap32_node, bn_rbnode, uint32_t,
- __bn_subtree_last, START, LAST, static inline, xbitmap32_tree)
+ __bn_subtree_last, START, LAST, static inline __maybe_unused,
+ xbitmap32_tree)
/* Iterate each interval of a bitmap. Do not change the bitmap. */
#define for_each_xbitmap32_extent(bn, bitmap) \
diff --git a/fs/xfs/scrub/common.c b/fs/xfs/scrub/common.c
index 47a20cf520..1ad8ec63a7 100644
--- a/fs/xfs/scrub/common.c
+++ b/fs/xfs/scrub/common.c
@@ -31,6 +31,8 @@
#include "xfs_ag.h"
#include "xfs_error.h"
#include "xfs_quota.h"
+#include "xfs_exchmaps.h"
+#include "xfs_rtbitmap.h"
#include "scrub/scrub.h"
#include "scrub/common.h"
#include "scrub/trace.h"
@@ -445,7 +447,7 @@ xchk_perag_read_headers(
{
int error;
- error = xfs_ialloc_read_agi(sa->pag, sc->tp, &sa->agi_bp);
+ error = xfs_ialloc_read_agi(sa->pag, sc->tp, 0, &sa->agi_bp);
if (error && want_ag_read_header_failure(sc, XFS_SCRUB_TYPE_AGI))
return error;
@@ -781,7 +783,7 @@ xchk_iget(
{
ASSERT(sc->tp != NULL);
- return xfs_iget(sc->mp, sc->tp, inum, XFS_IGET_UNTRUSTED, 0, ipp);
+ return xfs_iget(sc->mp, sc->tp, inum, XCHK_IGET_FLAGS, 0, ipp);
}
/*
@@ -827,13 +829,13 @@ again:
* in the iget cache miss path.
*/
pag = xfs_perag_get(mp, XFS_INO_TO_AGNO(mp, inum));
- error = xfs_ialloc_read_agi(pag, tp, agi_bpp);
+ error = xfs_ialloc_read_agi(pag, tp, 0, agi_bpp);
xfs_perag_put(pag);
if (error)
return error;
- error = xfs_iget(mp, tp, inum,
- XFS_IGET_NORETRY | XFS_IGET_UNTRUSTED, 0, ipp);
+ error = xfs_iget(mp, tp, inum, XFS_IGET_NORETRY | XCHK_IGET_FLAGS, 0,
+ ipp);
if (error == -EAGAIN) {
/*
* The inode may be in core but temporarily unavailable and may
@@ -1060,12 +1062,6 @@ xchk_irele(
spin_lock(&VFS_I(ip)->i_lock);
VFS_I(ip)->i_state &= ~I_DONTCACHE;
spin_unlock(&VFS_I(ip)->i_lock);
- } else if (atomic_read(&VFS_I(ip)->i_count) == 1) {
- /*
- * If this is the last reference to the inode and the caller
- * permits it, set DONTCACHE to avoid thrashing.
- */
- d_mark_dontcache(VFS_I(ip));
}
xfs_irele(ip);
@@ -1202,27 +1198,12 @@ xchk_metadata_inode_subtype(
struct xfs_scrub *sc,
unsigned int scrub_type)
{
- __u32 smtype = sc->sm->sm_type;
- unsigned int sick_mask = sc->sick_mask;
+ struct xfs_scrub_subord *sub;
int error;
- sc->sm->sm_type = scrub_type;
-
- switch (scrub_type) {
- case XFS_SCRUB_TYPE_INODE:
- error = xchk_inode(sc);
- break;
- case XFS_SCRUB_TYPE_BMBTD:
- error = xchk_bmap_data(sc);
- break;
- default:
- ASSERT(0);
- error = -EFSCORRUPTED;
- break;
- }
-
- sc->sick_mask = sick_mask;
- sc->sm->sm_type = smtype;
+ sub = xchk_scrub_create_subord(sc, scrub_type);
+ error = sub->sc.ops->scrub(&sub->sc);
+ xchk_scrub_free_subord(sub);
return error;
}
diff --git a/fs/xfs/scrub/common.h b/fs/xfs/scrub/common.h
index 89f7bbec88..3d5f1f6b4b 100644
--- a/fs/xfs/scrub/common.h
+++ b/fs/xfs/scrub/common.h
@@ -6,31 +6,6 @@
#ifndef __XFS_SCRUB_COMMON_H__
#define __XFS_SCRUB_COMMON_H__
-/*
- * We /could/ terminate a scrub/repair operation early. If we're not
- * in a good place to continue (fatal signal, etc.) then bail out.
- * Note that we're careful not to make any judgements about *error.
- */
-static inline bool
-xchk_should_terminate(
- struct xfs_scrub *sc,
- int *error)
-{
- /*
- * If preemption is disabled, we need to yield to the scheduler every
- * few seconds so that we don't run afoul of the soft lockup watchdog
- * or RCU stall detector.
- */
- cond_resched();
-
- if (fatal_signal_pending(current)) {
- if (*error == 0)
- *error = -EINTR;
- return true;
- }
- return false;
-}
-
int xchk_trans_alloc(struct xfs_scrub *sc, uint resblks);
int xchk_trans_alloc_empty(struct xfs_scrub *sc);
void xchk_trans_cancel(struct xfs_scrub *sc);
@@ -92,6 +67,7 @@ int xchk_setup_directory(struct xfs_scrub *sc);
int xchk_setup_xattr(struct xfs_scrub *sc);
int xchk_setup_symlink(struct xfs_scrub *sc);
int xchk_setup_parent(struct xfs_scrub *sc);
+int xchk_setup_dirtree(struct xfs_scrub *sc);
#ifdef CONFIG_XFS_RT
int xchk_setup_rtbitmap(struct xfs_scrub *sc);
int xchk_setup_rtsummary(struct xfs_scrub *sc);
@@ -212,6 +188,7 @@ static inline bool xchk_skip_xref(struct xfs_scrub_metadata *sm)
}
bool xchk_dir_looks_zapped(struct xfs_inode *dp);
+bool xchk_pptr_looks_zapped(struct xfs_inode *ip);
#ifdef CONFIG_XFS_ONLINE_REPAIR
/* Decide if a repair is required. */
diff --git a/fs/xfs/scrub/dab_bitmap.h b/fs/xfs/scrub/dab_bitmap.h
new file mode 100644
index 0000000000..0c6e3aad43
--- /dev/null
+++ b/fs/xfs/scrub/dab_bitmap.h
@@ -0,0 +1,37 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Copyright (c) 2022-2024 Oracle. All Rights Reserved.
+ * Author: Darrick J. Wong <djwong@kernel.org>
+ */
+#ifndef __XFS_SCRUB_DAB_BITMAP_H__
+#define __XFS_SCRUB_DAB_BITMAP_H__
+
+/* Bitmaps, but for type-checked for xfs_dablk_t */
+
+struct xdab_bitmap {
+ struct xbitmap32 dabitmap;
+};
+
+static inline void xdab_bitmap_init(struct xdab_bitmap *bitmap)
+{
+ xbitmap32_init(&bitmap->dabitmap);
+}
+
+static inline void xdab_bitmap_destroy(struct xdab_bitmap *bitmap)
+{
+ xbitmap32_destroy(&bitmap->dabitmap);
+}
+
+static inline int xdab_bitmap_set(struct xdab_bitmap *bitmap,
+ xfs_dablk_t dabno, xfs_extlen_t len)
+{
+ return xbitmap32_set(&bitmap->dabitmap, dabno, len);
+}
+
+static inline bool xdab_bitmap_test(struct xdab_bitmap *bitmap,
+ xfs_dablk_t dabno, xfs_extlen_t *len)
+{
+ return xbitmap32_test(&bitmap->dabitmap, dabno, len);
+}
+
+#endif /* __XFS_SCRUB_DAB_BITMAP_H__ */
diff --git a/fs/xfs/scrub/dabtree.c b/fs/xfs/scrub/dabtree.c
index 82b150d3b8..056de4819f 100644
--- a/fs/xfs/scrub/dabtree.c
+++ b/fs/xfs/scrub/dabtree.c
@@ -78,6 +78,22 @@ xchk_da_set_corrupt(
__return_address);
}
+/* Flag a da btree node in need of optimization. */
+void
+xchk_da_set_preen(
+ struct xchk_da_btree *ds,
+ int level)
+{
+ struct xfs_scrub *sc = ds->sc;
+
+ sc->sm->sm_flags |= XFS_SCRUB_OFLAG_PREEN;
+ trace_xchk_fblock_preen(sc, ds->dargs.whichfork,
+ xfs_dir2_da_to_db(ds->dargs.geo,
+ ds->state->path.blk[level].blkno),
+ __return_address);
+}
+
+/* Find an entry at a certain level in a da btree. */
static struct xfs_da_node_entry *
xchk_da_btree_node_entry(
struct xchk_da_btree *ds,
@@ -320,6 +336,7 @@ xchk_da_btree_block(
struct xfs_da3_blkinfo *hdr3;
struct xfs_da_args *dargs = &ds->dargs;
struct xfs_inode *ip = ds->dargs.dp;
+ xfs_failaddr_t fa;
xfs_ino_t owner;
int *pmaxrecs;
struct xfs_da3_icnode_hdr nodehdr;
@@ -442,6 +459,12 @@ xchk_da_btree_block(
goto out_freebp;
}
+ fa = xfs_da3_header_check(blk->bp, dargs->owner);
+ if (fa) {
+ xchk_da_set_corrupt(ds, level);
+ goto out_freebp;
+ }
+
/*
* If we've been handed a block that is below the dabtree root, does
* its hashval match what the parent block expected to see?
@@ -494,6 +517,7 @@ xchk_da_btree(
ds->dargs.whichfork = whichfork;
ds->dargs.trans = sc->tp;
ds->dargs.op_flags = XFS_DA_OP_OKNOENT;
+ ds->dargs.owner = sc->ip->i_ino;
ds->state = xfs_da_state_alloc(&ds->dargs);
ds->sc = sc;
ds->private = private;
diff --git a/fs/xfs/scrub/dabtree.h b/fs/xfs/scrub/dabtree.h
index 4f8c2138a1..de291e3b77 100644
--- a/fs/xfs/scrub/dabtree.h
+++ b/fs/xfs/scrub/dabtree.h
@@ -35,6 +35,9 @@ bool xchk_da_process_error(struct xchk_da_btree *ds, int level, int *error);
/* Check for da btree corruption. */
void xchk_da_set_corrupt(struct xchk_da_btree *ds, int level);
+void xchk_da_set_preen(struct xchk_da_btree *ds, int level);
+
+void xchk_da_set_preen(struct xchk_da_btree *ds, int level);
int xchk_da_btree_hash(struct xchk_da_btree *ds, int level, __be32 *hashp);
int xchk_da_btree(struct xfs_scrub *sc, int whichfork,
diff --git a/fs/xfs/scrub/dir.c b/fs/xfs/scrub/dir.c
index 076a310b8e..bf9199e8df 100644
--- a/fs/xfs/scrub/dir.c
+++ b/fs/xfs/scrub/dir.c
@@ -16,22 +16,70 @@
#include "xfs_dir2.h"
#include "xfs_dir2_priv.h"
#include "xfs_health.h"
+#include "xfs_attr.h"
+#include "xfs_parent.h"
#include "scrub/scrub.h"
#include "scrub/common.h"
#include "scrub/dabtree.h"
#include "scrub/readdir.h"
#include "scrub/health.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
xchk_setup_directory(
struct xfs_scrub *sc)
{
+ int error;
+
+ if (xchk_could_repair(sc)) {
+ error = xrep_setup_directory(sc);
+ if (error)
+ return error;
+ }
+
return xchk_setup_inode_contents(sc, 0);
}
/* 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;
+
+ /* information for parent pointer validation. */
+ struct xfs_parent_rec pptr_rec;
+ struct xfs_da_args pptr_args;
+
+ /* 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. */
+ struct xfs_name xname;
+ uint8_t namebuf[MAXNAMELEN];
+};
+
/* Scrub a directory entry. */
/* Check that an inode's mode matches a given XFS_DIR3_FT_* type. */
@@ -55,6 +103,108 @@ xchk_dir_check_ftype(
}
/*
+ * Try to lock a child file for checking parent pointers. Returns the inode
+ * flags for the locks we now hold, or zero if we failed.
+ */
+STATIC unsigned int
+xchk_dir_lock_child(
+ struct xfs_scrub *sc,
+ struct xfs_inode *ip)
+{
+ if (!xfs_ilock_nowait(ip, XFS_IOLOCK_SHARED))
+ return 0;
+
+ if (!xfs_ilock_nowait(ip, XFS_ILOCK_SHARED)) {
+ xfs_iunlock(ip, XFS_IOLOCK_SHARED);
+ return 0;
+ }
+
+ if (!xfs_inode_has_attr_fork(ip) || !xfs_need_iread_extents(&ip->i_af))
+ return XFS_IOLOCK_SHARED | XFS_ILOCK_SHARED;
+
+ xfs_iunlock(ip, XFS_ILOCK_SHARED);
+
+ if (!xfs_ilock_nowait(ip, XFS_ILOCK_EXCL)) {
+ xfs_iunlock(ip, XFS_IOLOCK_SHARED);
+ return 0;
+ }
+
+ return XFS_IOLOCK_SHARED | XFS_ILOCK_EXCL;
+}
+
+/* Check the backwards link (parent pointer) associated with this dirent. */
+STATIC int
+xchk_dir_parent_pointer(
+ struct xchk_dir *sd,
+ const struct xfs_name *name,
+ struct xfs_inode *ip)
+{
+ struct xfs_scrub *sc = sd->sc;
+ int error;
+
+ xfs_inode_to_parent_rec(&sd->pptr_rec, sc->ip);
+ error = xfs_parent_lookup(sc->tp, ip, name, &sd->pptr_rec,
+ &sd->pptr_args);
+ if (error == -ENOATTR)
+ xchk_fblock_xref_set_corrupt(sc, XFS_DATA_FORK, 0);
+
+ return 0;
+}
+
+/* Look for a parent pointer matching this dirent, if the child isn't busy. */
+STATIC int
+xchk_dir_check_pptr_fast(
+ struct xchk_dir *sd,
+ xfs_dir2_dataptr_t dapos,
+ const struct xfs_name *name,
+ struct xfs_inode *ip)
+{
+ struct xfs_scrub *sc = sd->sc;
+ unsigned int lockmode;
+ int error;
+
+ /* dot and dotdot entries do not have parent pointers */
+ if (xfs_dir2_samename(name, &xfs_name_dot) ||
+ xfs_dir2_samename(name, &xfs_name_dotdot))
+ return 0;
+
+ /* No self-referential non-dot or dotdot dirents. */
+ if (ip == sc->ip) {
+ xchk_fblock_set_corrupt(sc, XFS_DATA_FORK, 0);
+ return -ECANCELED;
+ }
+
+ /* Try to lock the inode. */
+ lockmode = xchk_dir_lock_child(sc, ip);
+ if (!lockmode) {
+ 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, ip->i_ino);
+
+ error = xfblob_storename(sd->dir_names, &save_de.name_cookie,
+ name);
+ if (!xchk_fblock_xref_process_error(sc, XFS_DATA_FORK, 0,
+ &error))
+ return error;
+
+ error = xfarray_append(sd->dir_entries, &save_de);
+ if (!xchk_fblock_xref_process_error(sc, XFS_DATA_FORK, 0,
+ &error))
+ return error;
+
+ return 0;
+ }
+
+ error = xchk_dir_parent_pointer(sd, name, ip);
+ xfs_iunlock(ip, lockmode);
+ return error;
+}
+
+/*
* Scrub a single directory entry.
*
* Check the inode number to make sure it's sane, then we check that we can
@@ -71,6 +221,7 @@ xchk_dir_actor(
{
struct xfs_mount *mp = dp->i_mount;
struct xfs_inode *ip;
+ struct xchk_dir *sd = priv;
xfs_ino_t lookup_ino;
xfs_dablk_t offset;
int error = 0;
@@ -137,6 +288,14 @@ xchk_dir_actor(
goto out;
xchk_dir_check_ftype(sc, offset, ip, name->type);
+
+ if (xfs_has_parent(mp)) {
+ error = xchk_dir_check_pptr_fast(sd, dapos, name, ip);
+ if (error)
+ goto out_rele;
+ }
+
+out_rele:
xchk_irele(sc, ip);
out:
if (sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT)
@@ -196,8 +355,8 @@ xchk_dir_rec(
xchk_da_set_corrupt(ds, level);
goto out;
}
- error = xfs_dir3_data_read(ds->dargs.trans, dp, rec_bno,
- XFS_DABUF_MAP_HOLE_OK, &bp);
+ error = xfs_dir3_data_read(ds->dargs.trans, dp, ds->dargs.owner,
+ rec_bno, XFS_DABUF_MAP_HOLE_OK, &bp);
if (!xchk_fblock_process_error(ds->sc, XFS_DATA_FORK, rec_bno,
&error))
goto out;
@@ -315,10 +474,11 @@ xchk_directory_data_bestfree(
/* dir block format */
if (lblk != XFS_B_TO_FSBT(mp, XFS_DIR2_DATA_OFFSET))
xchk_fblock_set_corrupt(sc, XFS_DATA_FORK, lblk);
- error = xfs_dir3_block_read(sc->tp, sc->ip, &bp);
+ error = xfs_dir3_block_read(sc->tp, sc->ip, sc->ip->i_ino, &bp);
} else {
/* dir data format */
- error = xfs_dir3_data_read(sc->tp, sc->ip, lblk, 0, &bp);
+ error = xfs_dir3_data_read(sc->tp, sc->ip, sc->ip->i_ino, lblk,
+ 0, &bp);
}
if (!xchk_fblock_process_error(sc, XFS_DATA_FORK, lblk, &error))
goto out;
@@ -470,7 +630,7 @@ xchk_directory_leaf1_bestfree(
int error;
/* Read the free space block. */
- error = xfs_dir3_leaf_read(sc->tp, sc->ip, lblk, &bp);
+ error = xfs_dir3_leaf_read(sc->tp, sc->ip, sc->ip->i_ino, lblk, &bp);
if (!xchk_fblock_process_error(sc, XFS_DATA_FORK, lblk, &error))
return error;
xchk_buffer_recheck(sc, bp);
@@ -531,10 +691,9 @@ xchk_directory_leaf1_bestfree(
/* Check all the bestfree entries. */
for (i = 0; i < bestcount; i++, bestp++) {
best = be16_to_cpu(*bestp);
- error = xfs_dir3_data_read(sc->tp, sc->ip,
+ error = xfs_dir3_data_read(sc->tp, sc->ip, args->owner,
xfs_dir2_db_to_da(args->geo, i),
- XFS_DABUF_MAP_HOLE_OK,
- &dbp);
+ XFS_DABUF_MAP_HOLE_OK, &dbp);
if (!xchk_fblock_process_error(sc, XFS_DATA_FORK, lblk,
&error))
break;
@@ -577,7 +736,7 @@ xchk_directory_free_bestfree(
int error;
/* Read the free space block */
- error = xfs_dir2_free_read(sc->tp, sc->ip, lblk, &bp);
+ error = xfs_dir2_free_read(sc->tp, sc->ip, sc->ip->i_ino, lblk, &bp);
if (!xchk_fblock_process_error(sc, XFS_DATA_FORK, lblk, &error))
return error;
xchk_buffer_recheck(sc, bp);
@@ -597,7 +756,7 @@ xchk_directory_free_bestfree(
stale++;
continue;
}
- error = xfs_dir3_data_read(sc->tp, sc->ip,
+ error = xfs_dir3_data_read(sc->tp, sc->ip, args->owner,
(freehdr.firstdb + i) * args->geo->fsbcount,
0, &dbp);
if (!xchk_fblock_process_error(sc, XFS_DATA_FORK, lblk,
@@ -621,10 +780,11 @@ xchk_directory_blocks(
{
struct xfs_bmbt_irec got;
struct xfs_da_args args = {
- .dp = sc ->ip,
+ .dp = sc->ip,
.whichfork = XFS_DATA_FORK,
.geo = sc->mp->m_dir_geo,
.trans = sc->tp,
+ .owner = sc->ip->i_ino,
};
struct xfs_ifork *ifp = xfs_ifork_ptr(sc->ip, XFS_DATA_FORK);
struct xfs_mount *mp = sc->mp;
@@ -648,7 +808,8 @@ xchk_directory_blocks(
free_lblk = XFS_B_TO_FSB(mp, XFS_DIR2_FREE_OFFSET);
/* Is this a block dir? */
- error = xfs_dir2_isblock(&args, &is_block);
+ if (xfs_dir2_format(&args, &error) == XFS_DIR2_FMT_BLOCK)
+ is_block = true;
if (!xchk_fblock_process_error(sc, XFS_DATA_FORK, lblk, &error))
goto out;
@@ -752,11 +913,148 @@ out:
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,
+ const struct xfs_name *xname)
+{
+ 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_DATA_FORK, 0);
+ return 0;
+ }
+ if (!xchk_fblock_xref_process_error(sc, XFS_DATA_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) {
+ trace_xchk_dir_slowpath(sc->ip, xname, ip->i_ino);
+ 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_ultraslowpath(sc->ip, xname, ip->i_ino);
+
+ error = xchk_dir_trylock_for_pptrs(sc, ip, &lockmode);
+ if (error)
+ goto out_rele;
+
+ /* Revalidate, since we just cycled the locks. */
+ error = xchk_dir_revalidate_dirent(sd, xname, dirent->ino);
+ if (error == -ENOENT) {
+ error = 0;
+ 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_loadname(sd->dir_names, dirent.name_cookie,
+ &sd->xname, dirent.namelen);
+ if (error)
+ return error;
+
+ error = xchk_dir_slow_dirent(sd, &dirent, &sd->xname);
+ if (error)
+ return error;
+ }
+
+ return 0;
+}
+
/* Scrub a whole directory. */
int
xchk_directory(
struct xfs_scrub *sc)
{
+ struct xchk_dir *sd;
int error;
if (!S_ISDIR(VFS_I(sc->ip)->i_mode))
@@ -789,9 +1087,60 @@ xchk_directory(
if (sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT)
return 0;
+ sd = kvzalloc(sizeof(struct xchk_dir), XCHK_GFP_FLAGS);
+ if (!sd)
+ return -ENOMEM;
+ sd->sc = sc;
+ sd->xname.name = sd->namebuf;
+
+ if (xfs_has_parent(sc->mp)) {
+ char *descr;
+
+ /*
+ * Set up some staging memory for dirents that we can't check
+ * due to locking contention.
+ */
+ descr = xchk_xfile_ino_descr(sc, "slow directory entries");
+ error = xfarray_create(descr, 0, sizeof(struct xchk_dirent),
+ &sd->dir_entries);
+ kfree(descr);
+ if (error)
+ goto out_sd;
+
+ descr = xchk_xfile_ino_descr(sc, "slow directory entry names");
+ error = xfblob_create(descr, &sd->dir_names);
+ kfree(descr);
+ if (error)
+ goto out_entries;
+ }
+
/* Look up every name in this directory by hash. */
- error = xchk_dir_walk(sc, sc->ip, xchk_dir_actor, NULL);
- if (error && error != -ECANCELED)
+ 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 == -ETIMEDOUT) {
+ /* Couldn't grab a lock, scrub was marked incomplete */
+ error = 0;
+ goto out_names;
+ }
+ 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);
+ if (error)
return error;
/* If the dir is clean, it is clearly not zapped. */
diff --git a/fs/xfs/scrub/dir_repair.c b/fs/xfs/scrub/dir_repair.c
new file mode 100644
index 0000000000..64679fe084
--- /dev/null
+++ b/fs/xfs/scrub/dir_repair.c
@@ -0,0 +1,1958 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Copyright (c) 2020-2024 Oracle. All Rights Reserved.
+ * Author: Darrick J. Wong <djwong@kernel.org>
+ */
+#include "xfs.h"
+#include "xfs_fs.h"
+#include "xfs_shared.h"
+#include "xfs_format.h"
+#include "xfs_trans_resv.h"
+#include "xfs_mount.h"
+#include "xfs_defer.h"
+#include "xfs_bit.h"
+#include "xfs_log_format.h"
+#include "xfs_trans.h"
+#include "xfs_sb.h"
+#include "xfs_inode.h"
+#include "xfs_icache.h"
+#include "xfs_da_format.h"
+#include "xfs_da_btree.h"
+#include "xfs_dir2.h"
+#include "xfs_dir2_priv.h"
+#include "xfs_bmap.h"
+#include "xfs_quota.h"
+#include "xfs_bmap_btree.h"
+#include "xfs_trans_space.h"
+#include "xfs_bmap_util.h"
+#include "xfs_exchmaps.h"
+#include "xfs_exchrange.h"
+#include "xfs_ag.h"
+#include "xfs_parent.h"
+#include "scrub/xfs_scrub.h"
+#include "scrub/scrub.h"
+#include "scrub/common.h"
+#include "scrub/trace.h"
+#include "scrub/repair.h"
+#include "scrub/tempfile.h"
+#include "scrub/tempexch.h"
+#include "scrub/xfile.h"
+#include "scrub/xfarray.h"
+#include "scrub/xfblob.h"
+#include "scrub/iscan.h"
+#include "scrub/readdir.h"
+#include "scrub/reap.h"
+#include "scrub/findparent.h"
+#include "scrub/orphanage.h"
+#include "scrub/listxattr.h"
+
+/*
+ * Directory Repair
+ * ================
+ *
+ * We repair directories by reading the directory data blocks looking for
+ * directory entries that look salvageable (name passes verifiers, entry points
+ * to a valid allocated inode, etc). Each entry worth salvaging is stashed in
+ * memory, and the stashed entries are periodically replayed into a temporary
+ * directory to constrain memory use. Batching the construction of the
+ * temporary directory in this fashion reduces lock cycling of the directory
+ * being repaired and the temporary directory, and will later become important
+ * for parent pointer scanning.
+ *
+ * If parent pointers are enabled on this filesystem, we instead reconstruct
+ * the directory by visiting each parent pointer of each file in the filesystem
+ * and translating the relevant parent pointer records into dirents. In this
+ * case, it is advantageous to stash all directory entries created from parent
+ * pointers for a single child file before replaying them into the temporary
+ * directory. To save memory, the live filesystem scan reuses the findparent
+ * fields. Directory repair chooses either parent pointer scanning or
+ * directory entry salvaging, but not both.
+ *
+ * Directory entries added to the temporary directory do not elevate the link
+ * counts of the inodes found. When salvaging completes, the remaining stashed
+ * entries are replayed to the temporary directory. An atomic mapping exchange
+ * is used to commit the new directory blocks to the directory being repaired.
+ * This will disrupt readdir cursors.
+ *
+ * Locking Issues
+ * --------------
+ *
+ * If /a, /a/b, and /c are all directories, the VFS does not take i_rwsem on
+ * /a/b for a "mv /a/b /c/" operation. This means that only b's ILOCK protects
+ * b's dotdot update. This is in contrast to every other dotdot update (link,
+ * remove, mkdir). If the repair code drops the ILOCK, it must either
+ * revalidate the dotdot entry or use dirent hooks to capture updates from
+ * other threads.
+ */
+
+/* Create a dirent in the tempdir. */
+#define XREP_DIRENT_ADD (1)
+
+/* Remove a dirent from the tempdir. */
+#define XREP_DIRENT_REMOVE (2)
+
+/* Directory entry to be restored in the new directory. */
+struct xrep_dirent {
+ /* Cookie for retrieval of the dirent name. */
+ xfblob_cookie name_cookie;
+
+ /* Target inode number. */
+ xfs_ino_t ino;
+
+ /* Length of the dirent name. */
+ uint8_t namelen;
+
+ /* File type of the dirent. */
+ uint8_t ftype;
+
+ /* XREP_DIRENT_{ADD,REMOVE} */
+ uint8_t action;
+};
+
+/*
+ * Stash up to 8 pages of recovered dirent data in dir_entries and dir_names
+ * before we write them to the temp dir.
+ */
+#define XREP_DIR_MAX_STASH_BYTES (PAGE_SIZE * 8)
+
+struct xrep_dir {
+ struct xfs_scrub *sc;
+
+ /* Fixed-size array of xrep_dirent structures. */
+ struct xfarray *dir_entries;
+
+ /* Blobs containing directory entry names. */
+ struct xfblob *dir_names;
+
+ /* Information for exchanging data forks at the end. */
+ struct xrep_tempexch tx;
+
+ /* Preallocated args struct for performing dir operations */
+ struct xfs_da_args args;
+
+ /*
+ * Information used to scan the filesystem to find the inumber of the
+ * dotdot entry for this directory. For directory salvaging when
+ * parent pointers are not enabled, we use the findparent_* functions
+ * on this object and access only the parent_ino field directly.
+ *
+ * When parent pointers are enabled, however, the pptr scanner uses the
+ * iscan, hooks, lock, and parent_ino fields of this object directly.
+ * @pscan.lock coordinates access to dir_entries, dir_names,
+ * parent_ino, subdirs, dirents, and args. This reduces the memory
+ * requirements of this structure.
+ */
+ struct xrep_parent_scan_info pscan;
+
+ /*
+ * Context information for attaching this directory to the lost+found
+ * if this directory does not have a parent.
+ */
+ struct xrep_adoption adoption;
+
+ /* How many subdirectories did we find? */
+ uint64_t subdirs;
+
+ /* How many dirents did we find? */
+ unsigned int dirents;
+
+ /* Should we move this directory to the orphanage? */
+ bool needs_adoption;
+
+ /* Directory entry name, plus the trailing null. */
+ struct xfs_name xname;
+ unsigned char namebuf[MAXNAMELEN];
+};
+
+/* Tear down all the incore stuff we created. */
+static void
+xrep_dir_teardown(
+ struct xfs_scrub *sc)
+{
+ struct xrep_dir *rd = sc->buf;
+
+ xrep_findparent_scan_teardown(&rd->pscan);
+ xfblob_destroy(rd->dir_names);
+ xfarray_destroy(rd->dir_entries);
+}
+
+/* Set up for a directory repair. */
+int
+xrep_setup_directory(
+ struct xfs_scrub *sc)
+{
+ struct xrep_dir *rd;
+ int error;
+
+ xchk_fsgates_enable(sc, XCHK_FSGATES_DIRENTS);
+
+ error = xrep_orphanage_try_create(sc);
+ if (error)
+ return error;
+
+ error = xrep_tempfile_create(sc, S_IFDIR);
+ if (error)
+ return error;
+
+ rd = kvzalloc(sizeof(struct xrep_dir), XCHK_GFP_FLAGS);
+ if (!rd)
+ return -ENOMEM;
+ rd->sc = sc;
+ rd->xname.name = rd->namebuf;
+ sc->buf = rd;
+
+ return 0;
+}
+
+/*
+ * Look up the dotdot entry and confirm that it's really the parent.
+ * Returns NULLFSINO if we don't know what to do.
+ */
+static inline xfs_ino_t
+xrep_dir_lookup_parent(
+ struct xrep_dir *rd)
+{
+ struct xfs_scrub *sc = rd->sc;
+ xfs_ino_t ino;
+ int error;
+
+ error = xfs_dir_lookup(sc->tp, sc->ip, &xfs_name_dotdot, &ino, NULL);
+ if (error)
+ return NULLFSINO;
+ if (!xfs_verify_dir_ino(sc->mp, ino))
+ return NULLFSINO;
+
+ error = xrep_findparent_confirm(sc, &ino);
+ if (error)
+ return NULLFSINO;
+
+ return ino;
+}
+
+/*
+ * Look up '..' in the dentry cache and confirm that it's really the parent.
+ * Returns NULLFSINO if the dcache misses or if the hit is implausible.
+ */
+static inline xfs_ino_t
+xrep_dir_dcache_parent(
+ struct xrep_dir *rd)
+{
+ struct xfs_scrub *sc = rd->sc;
+ xfs_ino_t parent_ino;
+ int error;
+
+ parent_ino = xrep_findparent_from_dcache(sc);
+ if (parent_ino == NULLFSINO)
+ return parent_ino;
+
+ error = xrep_findparent_confirm(sc, &parent_ino);
+ if (error)
+ return NULLFSINO;
+
+ return parent_ino;
+}
+
+/* Try to find the parent of the directory being repaired. */
+STATIC int
+xrep_dir_find_parent(
+ struct xrep_dir *rd)
+{
+ xfs_ino_t ino;
+
+ ino = xrep_findparent_self_reference(rd->sc);
+ if (ino != NULLFSINO) {
+ xrep_findparent_scan_finish_early(&rd->pscan, ino);
+ return 0;
+ }
+
+ ino = xrep_dir_dcache_parent(rd);
+ if (ino != NULLFSINO) {
+ xrep_findparent_scan_finish_early(&rd->pscan, ino);
+ return 0;
+ }
+
+ ino = xrep_dir_lookup_parent(rd);
+ if (ino != NULLFSINO) {
+ xrep_findparent_scan_finish_early(&rd->pscan, ino);
+ return 0;
+ }
+
+ /*
+ * A full filesystem scan is the last resort. On a busy filesystem,
+ * the scan can fail with -EBUSY if we cannot grab IOLOCKs. That means
+ * that we don't know what who the parent is, so we should return to
+ * userspace.
+ */
+ return xrep_findparent_scan(&rd->pscan);
+}
+
+/*
+ * Decide if we want to salvage this entry. We don't bother with oversized
+ * names or the dot entry.
+ */
+STATIC int
+xrep_dir_want_salvage(
+ struct xrep_dir *rd,
+ const char *name,
+ int namelen,
+ xfs_ino_t ino)
+{
+ struct xfs_mount *mp = rd->sc->mp;
+
+ /* No pointers to ourselves or to garbage. */
+ if (ino == rd->sc->ip->i_ino)
+ return false;
+ if (!xfs_verify_dir_ino(mp, ino))
+ return false;
+
+ /* No weird looking names or dot entries. */
+ if (namelen >= MAXNAMELEN || namelen <= 0)
+ return false;
+ if (namelen == 1 && name[0] == '.')
+ return false;
+ if (!xfs_dir2_namecheck(name, namelen))
+ return false;
+
+ return true;
+}
+
+/*
+ * Remember that we want to create a dirent in the tempdir. These stashed
+ * actions will be replayed later.
+ */
+STATIC int
+xrep_dir_stash_createname(
+ struct xrep_dir *rd,
+ const struct xfs_name *name,
+ xfs_ino_t ino)
+{
+ struct xrep_dirent dirent = {
+ .action = XREP_DIRENT_ADD,
+ .ino = ino,
+ .namelen = name->len,
+ .ftype = name->type,
+ };
+ int error;
+
+ trace_xrep_dir_stash_createname(rd->sc->tempip, name, ino);
+
+ error = xfblob_storename(rd->dir_names, &dirent.name_cookie, name);
+ if (error)
+ return error;
+
+ return xfarray_append(rd->dir_entries, &dirent);
+}
+
+/*
+ * Remember that we want to remove a dirent from the tempdir. These stashed
+ * actions will be replayed later.
+ */
+STATIC int
+xrep_dir_stash_removename(
+ struct xrep_dir *rd,
+ const struct xfs_name *name,
+ xfs_ino_t ino)
+{
+ struct xrep_dirent dirent = {
+ .action = XREP_DIRENT_REMOVE,
+ .ino = ino,
+ .namelen = name->len,
+ .ftype = name->type,
+ };
+ int error;
+
+ trace_xrep_dir_stash_removename(rd->sc->tempip, name, ino);
+
+ error = xfblob_storename(rd->dir_names, &dirent.name_cookie, name);
+ if (error)
+ return error;
+
+ return xfarray_append(rd->dir_entries, &dirent);
+}
+
+/* Allocate an in-core record to hold entries while we rebuild the dir data. */
+STATIC int
+xrep_dir_salvage_entry(
+ struct xrep_dir *rd,
+ unsigned char *name,
+ unsigned int namelen,
+ xfs_ino_t ino)
+{
+ struct xfs_name xname = {
+ .name = name,
+ };
+ struct xfs_scrub *sc = rd->sc;
+ struct xfs_inode *ip;
+ unsigned int i = 0;
+ int error = 0;
+
+ if (xchk_should_terminate(sc, &error))
+ return error;
+
+ /*
+ * Truncate the name to the first character that would trip namecheck.
+ * If we no longer have a name after that, ignore this entry.
+ */
+ while (i < namelen && name[i] != 0 && name[i] != '/')
+ i++;
+ if (i == 0)
+ return 0;
+ xname.len = i;
+
+ /* Ignore '..' entries; we already picked the new parent. */
+ if (xname.len == 2 && name[0] == '.' && name[1] == '.') {
+ trace_xrep_dir_salvaged_parent(sc->ip, ino);
+ return 0;
+ }
+
+ trace_xrep_dir_salvage_entry(sc->ip, &xname, ino);
+
+ /*
+ * Compute the ftype or dump the entry if we can't. We don't lock the
+ * inode because inodes can't change type while we have a reference.
+ */
+ error = xchk_iget(sc, ino, &ip);
+ if (error)
+ return 0;
+
+ xname.type = xfs_mode_to_ftype(VFS_I(ip)->i_mode);
+ xchk_irele(sc, ip);
+
+ return xrep_dir_stash_createname(rd, &xname, ino);
+}
+
+/* Record a shortform directory entry for later reinsertion. */
+STATIC int
+xrep_dir_salvage_sf_entry(
+ struct xrep_dir *rd,
+ struct xfs_dir2_sf_hdr *sfp,
+ struct xfs_dir2_sf_entry *sfep)
+{
+ xfs_ino_t ino;
+
+ ino = xfs_dir2_sf_get_ino(rd->sc->mp, sfp, sfep);
+ if (!xrep_dir_want_salvage(rd, sfep->name, sfep->namelen, ino))
+ return 0;
+
+ return xrep_dir_salvage_entry(rd, sfep->name, sfep->namelen, ino);
+}
+
+/* Record a regular directory entry for later reinsertion. */
+STATIC int
+xrep_dir_salvage_data_entry(
+ struct xrep_dir *rd,
+ struct xfs_dir2_data_entry *dep)
+{
+ xfs_ino_t ino;
+
+ ino = be64_to_cpu(dep->inumber);
+ if (!xrep_dir_want_salvage(rd, dep->name, dep->namelen, ino))
+ return 0;
+
+ return xrep_dir_salvage_entry(rd, dep->name, dep->namelen, ino);
+}
+
+/* Try to recover block/data format directory entries. */
+STATIC int
+xrep_dir_recover_data(
+ struct xrep_dir *rd,
+ struct xfs_buf *bp)
+{
+ struct xfs_da_geometry *geo = rd->sc->mp->m_dir_geo;
+ unsigned int offset;
+ unsigned int end;
+ int error = 0;
+
+ /*
+ * Loop over the data portion of the block.
+ * Each object is a real entry (dep) or an unused one (dup).
+ */
+ offset = geo->data_entry_offset;
+ end = min_t(unsigned int, BBTOB(bp->b_length),
+ xfs_dir3_data_end_offset(geo, bp->b_addr));
+
+ while (offset < end) {
+ struct xfs_dir2_data_unused *dup = bp->b_addr + offset;
+ struct xfs_dir2_data_entry *dep = bp->b_addr + offset;
+
+ if (xchk_should_terminate(rd->sc, &error))
+ return error;
+
+ /* Skip unused entries. */
+ if (be16_to_cpu(dup->freetag) == XFS_DIR2_DATA_FREE_TAG) {
+ offset += be16_to_cpu(dup->length);
+ continue;
+ }
+
+ /* Don't walk off the end of the block. */
+ offset += xfs_dir2_data_entsize(rd->sc->mp, dep->namelen);
+ if (offset > end)
+ break;
+
+ /* Ok, let's save this entry. */
+ error = xrep_dir_salvage_data_entry(rd, dep);
+ if (error)
+ return error;
+
+ }
+
+ return 0;
+}
+
+/* Try to recover shortform directory entries. */
+STATIC int
+xrep_dir_recover_sf(
+ struct xrep_dir *rd)
+{
+ struct xfs_dir2_sf_hdr *hdr;
+ struct xfs_dir2_sf_entry *sfep;
+ struct xfs_dir2_sf_entry *next;
+ struct xfs_ifork *ifp;
+ xfs_ino_t ino;
+ unsigned char *end;
+ int error = 0;
+
+ ifp = xfs_ifork_ptr(rd->sc->ip, XFS_DATA_FORK);
+ hdr = ifp->if_data;
+ end = (unsigned char *)ifp->if_data + ifp->if_bytes;
+
+ ino = xfs_dir2_sf_get_parent_ino(hdr);
+ trace_xrep_dir_salvaged_parent(rd->sc->ip, ino);
+
+ sfep = xfs_dir2_sf_firstentry(hdr);
+ while ((unsigned char *)sfep < end) {
+ if (xchk_should_terminate(rd->sc, &error))
+ return error;
+
+ next = xfs_dir2_sf_nextentry(rd->sc->mp, hdr, sfep);
+ if ((unsigned char *)next > end)
+ break;
+
+ /* Ok, let's save this entry. */
+ error = xrep_dir_salvage_sf_entry(rd, hdr, sfep);
+ if (error)
+ return error;
+
+ sfep = next;
+ }
+
+ return 0;
+}
+
+/*
+ * Try to figure out the format of this directory from the data fork mappings
+ * and the directory size. If we can be reasonably sure of format, we can be
+ * more aggressive in salvaging directory entries. On return, @magic_guess
+ * will be set to DIR3_BLOCK_MAGIC if we think this is a "block format"
+ * directory; DIR3_DATA_MAGIC if we think this is a "data format" directory,
+ * and 0 if we can't tell.
+ */
+STATIC void
+xrep_dir_guess_format(
+ struct xrep_dir *rd,
+ __be32 *magic_guess)
+{
+ struct xfs_inode *dp = rd->sc->ip;
+ struct xfs_mount *mp = rd->sc->mp;
+ struct xfs_da_geometry *geo = mp->m_dir_geo;
+ xfs_fileoff_t last;
+ int error;
+
+ ASSERT(xfs_has_crc(mp));
+
+ *magic_guess = 0;
+
+ /*
+ * If there's a single directory block and the directory size is
+ * exactly one block, this has to be a single block format directory.
+ */
+ error = xfs_bmap_last_offset(dp, &last, XFS_DATA_FORK);
+ if (!error && XFS_FSB_TO_B(mp, last) == geo->blksize &&
+ dp->i_disk_size == geo->blksize) {
+ *magic_guess = cpu_to_be32(XFS_DIR3_BLOCK_MAGIC);
+ return;
+ }
+
+ /*
+ * If the last extent before the leaf offset matches the directory
+ * size and the directory size is larger than 1 block, this is a
+ * data format directory.
+ */
+ last = geo->leafblk;
+ error = xfs_bmap_last_before(rd->sc->tp, dp, &last, XFS_DATA_FORK);
+ if (!error &&
+ XFS_FSB_TO_B(mp, last) > geo->blksize &&
+ XFS_FSB_TO_B(mp, last) == dp->i_disk_size) {
+ *magic_guess = cpu_to_be32(XFS_DIR3_DATA_MAGIC);
+ return;
+ }
+}
+
+/* Recover directory entries from a specific directory block. */
+STATIC int
+xrep_dir_recover_dirblock(
+ struct xrep_dir *rd,
+ __be32 magic_guess,
+ xfs_dablk_t dabno)
+{
+ struct xfs_dir2_data_hdr *hdr;
+ struct xfs_buf *bp;
+ __be32 oldmagic;
+ int error;
+
+ /*
+ * Try to read buffer. We invalidate them in the next step so we don't
+ * bother to set a buffer type or ops.
+ */
+ error = xfs_da_read_buf(rd->sc->tp, rd->sc->ip, dabno,
+ XFS_DABUF_MAP_HOLE_OK, &bp, XFS_DATA_FORK, NULL);
+ if (error || !bp)
+ return error;
+
+ hdr = bp->b_addr;
+ oldmagic = hdr->magic;
+
+ trace_xrep_dir_recover_dirblock(rd->sc->ip, dabno,
+ be32_to_cpu(hdr->magic), be32_to_cpu(magic_guess));
+
+ /*
+ * If we're sure of the block's format, proceed with the salvage
+ * operation using the specified magic number.
+ */
+ if (magic_guess) {
+ hdr->magic = magic_guess;
+ goto recover;
+ }
+
+ /*
+ * If we couldn't guess what type of directory this is, then we will
+ * only salvage entries from directory blocks that match the magic
+ * number and pass verifiers.
+ */
+ switch (hdr->magic) {
+ case cpu_to_be32(XFS_DIR2_BLOCK_MAGIC):
+ case cpu_to_be32(XFS_DIR3_BLOCK_MAGIC):
+ if (!xrep_buf_verify_struct(bp, &xfs_dir3_block_buf_ops))
+ goto out;
+ if (xfs_dir3_block_header_check(bp, rd->sc->ip->i_ino) != NULL)
+ goto out;
+ break;
+ case cpu_to_be32(XFS_DIR2_DATA_MAGIC):
+ case cpu_to_be32(XFS_DIR3_DATA_MAGIC):
+ if (!xrep_buf_verify_struct(bp, &xfs_dir3_data_buf_ops))
+ goto out;
+ if (xfs_dir3_data_header_check(bp, rd->sc->ip->i_ino) != NULL)
+ goto out;
+ break;
+ default:
+ goto out;
+ }
+
+recover:
+ error = xrep_dir_recover_data(rd, bp);
+
+out:
+ hdr->magic = oldmagic;
+ xfs_trans_brelse(rd->sc->tp, bp);
+ return error;
+}
+
+static inline void
+xrep_dir_init_args(
+ struct xrep_dir *rd,
+ struct xfs_inode *dp,
+ const struct xfs_name *name)
+{
+ memset(&rd->args, 0, sizeof(struct xfs_da_args));
+ rd->args.geo = rd->sc->mp->m_dir_geo;
+ rd->args.whichfork = XFS_DATA_FORK;
+ rd->args.owner = rd->sc->ip->i_ino;
+ rd->args.trans = rd->sc->tp;
+ rd->args.dp = dp;
+ if (!name)
+ return;
+ rd->args.name = name->name;
+ rd->args.namelen = name->len;
+ rd->args.filetype = name->type;
+ rd->args.hashval = xfs_dir2_hashname(rd->sc->mp, name);
+}
+
+/* Replay a stashed createname into the temporary directory. */
+STATIC int
+xrep_dir_replay_createname(
+ struct xrep_dir *rd,
+ const struct xfs_name *name,
+ xfs_ino_t inum,
+ xfs_extlen_t total)
+{
+ struct xfs_scrub *sc = rd->sc;
+ struct xfs_inode *dp = rd->sc->tempip;
+ int error;
+
+ ASSERT(S_ISDIR(VFS_I(dp)->i_mode));
+
+ error = xfs_dir_ino_validate(sc->mp, inum);
+ if (error)
+ return error;
+
+ trace_xrep_dir_replay_createname(dp, name, inum);
+
+ xrep_dir_init_args(rd, dp, name);
+ rd->args.inumber = inum;
+ rd->args.total = total;
+ rd->args.op_flags = XFS_DA_OP_ADDNAME | XFS_DA_OP_OKNOENT;
+ return xfs_dir_createname_args(&rd->args);
+}
+
+/* Replay a stashed removename onto the temporary directory. */
+STATIC int
+xrep_dir_replay_removename(
+ struct xrep_dir *rd,
+ const struct xfs_name *name,
+ xfs_extlen_t total)
+{
+ struct xfs_inode *dp = rd->args.dp;
+
+ ASSERT(S_ISDIR(VFS_I(dp)->i_mode));
+
+ xrep_dir_init_args(rd, dp, name);
+ rd->args.op_flags = 0;
+ rd->args.total = total;
+
+ trace_xrep_dir_replay_removename(dp, name, 0);
+ return xfs_dir_removename_args(&rd->args);
+}
+
+/*
+ * Add this stashed incore directory entry to the temporary directory.
+ * The caller must hold the tempdir's IOLOCK, must not hold any ILOCKs, and
+ * must not be in transaction context.
+ */
+STATIC int
+xrep_dir_replay_update(
+ struct xrep_dir *rd,
+ const struct xfs_name *xname,
+ const struct xrep_dirent *dirent)
+{
+ struct xfs_mount *mp = rd->sc->mp;
+#ifdef DEBUG
+ xfs_ino_t ino;
+#endif
+ uint resblks;
+ int error;
+
+ resblks = xfs_link_space_res(mp, xname->len);
+ error = xchk_trans_alloc(rd->sc, resblks);
+ if (error)
+ return error;
+
+ /* Lock the temporary directory and join it to the transaction */
+ xrep_tempfile_ilock(rd->sc);
+ xfs_trans_ijoin(rd->sc->tp, rd->sc->tempip, 0);
+
+ switch (dirent->action) {
+ case XREP_DIRENT_ADD:
+ /*
+ * Create a replacement dirent in the temporary directory.
+ * Note that _createname doesn't check for existing entries.
+ * There shouldn't be any in the temporary dir, but we'll
+ * verify this in debug mode.
+ */
+#ifdef DEBUG
+ error = xchk_dir_lookup(rd->sc, rd->sc->tempip, xname, &ino);
+ if (error != -ENOENT) {
+ ASSERT(error != -ENOENT);
+ goto out_cancel;
+ }
+#endif
+
+ error = xrep_dir_replay_createname(rd, xname, dirent->ino,
+ resblks);
+ if (error)
+ goto out_cancel;
+
+ if (xname->type == XFS_DIR3_FT_DIR)
+ rd->subdirs++;
+ rd->dirents++;
+ break;
+ case XREP_DIRENT_REMOVE:
+ /*
+ * Remove a dirent from the temporary directory. Note that
+ * _removename doesn't check the inode target of the exist
+ * entry. There should be a perfect match in the temporary
+ * dir, but we'll verify this in debug mode.
+ */
+#ifdef DEBUG
+ error = xchk_dir_lookup(rd->sc, rd->sc->tempip, xname, &ino);
+ if (error) {
+ ASSERT(error != 0);
+ goto out_cancel;
+ }
+ if (ino != dirent->ino) {
+ ASSERT(ino == dirent->ino);
+ error = -EIO;
+ goto out_cancel;
+ }
+#endif
+
+ error = xrep_dir_replay_removename(rd, xname, resblks);
+ if (error)
+ goto out_cancel;
+
+ if (xname->type == XFS_DIR3_FT_DIR)
+ rd->subdirs--;
+ rd->dirents--;
+ break;
+ default:
+ ASSERT(0);
+ error = -EIO;
+ goto out_cancel;
+ }
+
+ /* Commit and unlock. */
+ error = xrep_trans_commit(rd->sc);
+ if (error)
+ return error;
+
+ xrep_tempfile_iunlock(rd->sc);
+ return 0;
+out_cancel:
+ xchk_trans_cancel(rd->sc);
+ xrep_tempfile_iunlock(rd->sc);
+ return error;
+}
+
+/*
+ * Flush stashed incore dirent updates that have been recorded by the scanner.
+ * This is done to reduce the memory requirements of the directory rebuild,
+ * since directories can contain up to 32GB of directory data.
+ *
+ * Caller must not hold transactions or ILOCKs. Caller must hold the tempdir
+ * IOLOCK.
+ */
+STATIC int
+xrep_dir_replay_updates(
+ struct xrep_dir *rd)
+{
+ xfarray_idx_t array_cur;
+ int error;
+
+ /* Add all the salvaged dirents to the temporary directory. */
+ mutex_lock(&rd->pscan.lock);
+ foreach_xfarray_idx(rd->dir_entries, array_cur) {
+ struct xrep_dirent dirent;
+
+ error = xfarray_load(rd->dir_entries, array_cur, &dirent);
+ if (error)
+ goto out_unlock;
+
+ error = xfblob_loadname(rd->dir_names, dirent.name_cookie,
+ &rd->xname, dirent.namelen);
+ if (error)
+ goto out_unlock;
+ rd->xname.type = dirent.ftype;
+ mutex_unlock(&rd->pscan.lock);
+
+ error = xrep_dir_replay_update(rd, &rd->xname, &dirent);
+ if (error)
+ return error;
+ mutex_lock(&rd->pscan.lock);
+ }
+
+ /* Empty out both arrays now that we've added the entries. */
+ xfarray_truncate(rd->dir_entries);
+ xfblob_truncate(rd->dir_names);
+ mutex_unlock(&rd->pscan.lock);
+ return 0;
+out_unlock:
+ mutex_unlock(&rd->pscan.lock);
+ return error;
+}
+
+/*
+ * Periodically flush stashed directory entries to the temporary dir. This
+ * is done to reduce the memory requirements of the directory rebuild, since
+ * directories can contain up to 32GB of directory data.
+ */
+STATIC int
+xrep_dir_flush_stashed(
+ struct xrep_dir *rd)
+{
+ int error;
+
+ /*
+ * Entering this function, the scrub context has a reference to the
+ * inode being repaired, the temporary file, and a scrub transaction
+ * that we use during dirent salvaging to avoid livelocking if there
+ * are cycles in the directory structures. We hold ILOCK_EXCL on both
+ * the inode being repaired and the temporary file, though they are
+ * not ijoined to the scrub transaction.
+ *
+ * To constrain kernel memory use, we occasionally write salvaged
+ * dirents from the xfarray and xfblob structures into the temporary
+ * directory in preparation for exchanging the directory structures at
+ * the end. Updating the temporary file requires a transaction, so we
+ * commit the scrub transaction and drop the two ILOCKs so that
+ * we can allocate whatever transaction we want.
+ *
+ * We still hold IOLOCK_EXCL on the inode being repaired, which
+ * prevents anyone from accessing the damaged directory data while we
+ * repair it.
+ */
+ error = xrep_trans_commit(rd->sc);
+ if (error)
+ return error;
+ xchk_iunlock(rd->sc, XFS_ILOCK_EXCL);
+
+ /*
+ * Take the IOLOCK of the temporary file while we modify dirents. This
+ * isn't strictly required because the temporary file is never revealed
+ * to userspace, but we follow the same locking rules. We still hold
+ * sc->ip's IOLOCK.
+ */
+ error = xrep_tempfile_iolock_polled(rd->sc);
+ if (error)
+ return error;
+
+ /* Write to the tempdir all the updates that we've stashed. */
+ error = xrep_dir_replay_updates(rd);
+ xrep_tempfile_iounlock(rd->sc);
+ if (error)
+ return error;
+
+ /*
+ * Recreate the salvage transaction and relock the dir we're salvaging.
+ */
+ error = xchk_trans_alloc(rd->sc, 0);
+ if (error)
+ return error;
+ xchk_ilock(rd->sc, XFS_ILOCK_EXCL);
+ return 0;
+}
+
+/* Decide if we've stashed too much dirent data in memory. */
+static inline bool
+xrep_dir_want_flush_stashed(
+ struct xrep_dir *rd)
+{
+ unsigned long long bytes;
+
+ bytes = xfarray_bytes(rd->dir_entries) + xfblob_bytes(rd->dir_names);
+ return bytes > XREP_DIR_MAX_STASH_BYTES;
+}
+
+/* Extract as many directory entries as we can. */
+STATIC int
+xrep_dir_recover(
+ struct xrep_dir *rd)
+{
+ struct xfs_bmbt_irec got;
+ struct xfs_scrub *sc = rd->sc;
+ struct xfs_da_geometry *geo = sc->mp->m_dir_geo;
+ xfs_fileoff_t offset;
+ xfs_dablk_t dabno;
+ __be32 magic_guess;
+ int nmap;
+ int error;
+
+ xrep_dir_guess_format(rd, &magic_guess);
+
+ /* Iterate each directory data block in the data fork. */
+ for (offset = 0;
+ offset < geo->leafblk;
+ offset = got.br_startoff + got.br_blockcount) {
+ nmap = 1;
+ error = xfs_bmapi_read(sc->ip, offset, geo->leafblk - offset,
+ &got, &nmap, 0);
+ if (error)
+ return error;
+ if (nmap != 1)
+ return -EFSCORRUPTED;
+ if (!xfs_bmap_is_written_extent(&got))
+ continue;
+
+ for (dabno = round_up(got.br_startoff, geo->fsbcount);
+ dabno < got.br_startoff + got.br_blockcount;
+ dabno += geo->fsbcount) {
+ if (xchk_should_terminate(rd->sc, &error))
+ return error;
+
+ error = xrep_dir_recover_dirblock(rd,
+ magic_guess, dabno);
+ if (error)
+ return error;
+
+ /* Flush dirents to constrain memory usage. */
+ if (xrep_dir_want_flush_stashed(rd)) {
+ error = xrep_dir_flush_stashed(rd);
+ if (error)
+ return error;
+ }
+ }
+ }
+
+ return 0;
+}
+
+/*
+ * Find all the directory entries for this inode by scraping them out of the
+ * directory leaf blocks by hand, and flushing them into the temp dir.
+ */
+STATIC int
+xrep_dir_find_entries(
+ struct xrep_dir *rd)
+{
+ struct xfs_inode *dp = rd->sc->ip;
+ int error;
+
+ /*
+ * Salvage directory entries from the old directory, and write them to
+ * the temporary directory.
+ */
+ if (dp->i_df.if_format == XFS_DINODE_FMT_LOCAL) {
+ error = xrep_dir_recover_sf(rd);
+ } else {
+ error = xfs_iread_extents(rd->sc->tp, dp, XFS_DATA_FORK);
+ if (error)
+ return error;
+
+ error = xrep_dir_recover(rd);
+ }
+ if (error)
+ return error;
+
+ return xrep_dir_flush_stashed(rd);
+}
+
+/* Scan all files in the filesystem for dirents. */
+STATIC int
+xrep_dir_salvage_entries(
+ struct xrep_dir *rd)
+{
+ struct xfs_scrub *sc = rd->sc;
+ int error;
+
+ /*
+ * Drop the ILOCK on this directory so that we can scan for this
+ * directory's parent. Figure out who is going to be the parent of
+ * this directory, then retake the ILOCK so that we can salvage
+ * directory entries.
+ */
+ xchk_iunlock(sc, XFS_ILOCK_EXCL);
+ error = xrep_dir_find_parent(rd);
+ xchk_ilock(sc, XFS_ILOCK_EXCL);
+ if (error)
+ return error;
+
+ /*
+ * Collect directory entries by parsing raw leaf blocks to salvage
+ * whatever we can. When we're done, free the staging memory before
+ * exchanging the directories to reduce memory usage.
+ */
+ error = xrep_dir_find_entries(rd);
+ if (error)
+ return error;
+
+ /*
+ * Cancel the repair transaction and drop the ILOCK so that we can
+ * (later) use the atomic mapping exchange functions to compute the
+ * correct block reservations and re-lock the inodes.
+ *
+ * We still hold IOLOCK_EXCL (aka i_rwsem) which will prevent directory
+ * modifications, but there's nothing to prevent userspace from reading
+ * the directory until we're ready for the exchange operation. Reads
+ * will return -EIO without shutting down the fs, so we're ok with
+ * that.
+ *
+ * The VFS can change dotdot on us, but the findparent scan will keep
+ * our incore parent inode up to date. See the note on locking issues
+ * for more details.
+ */
+ error = xrep_trans_commit(sc);
+ if (error)
+ return error;
+
+ xchk_iunlock(sc, XFS_ILOCK_EXCL);
+ return 0;
+}
+
+
+/*
+ * Examine a parent pointer of a file. If it leads us back to the directory
+ * that we're rebuilding, create an incore dirent from the parent pointer and
+ * stash it.
+ */
+STATIC int
+xrep_dir_scan_pptr(
+ struct xfs_scrub *sc,
+ struct xfs_inode *ip,
+ unsigned int attr_flags,
+ const unsigned char *name,
+ unsigned int namelen,
+ const void *value,
+ unsigned int valuelen,
+ void *priv)
+{
+ struct xfs_name xname = {
+ .name = name,
+ .len = namelen,
+ .type = xfs_mode_to_ftype(VFS_I(ip)->i_mode),
+ };
+ xfs_ino_t parent_ino;
+ uint32_t parent_gen;
+ struct xrep_dir *rd = priv;
+ int error;
+
+ if (!(attr_flags & XFS_ATTR_PARENT))
+ return 0;
+
+ /*
+ * Ignore parent pointers that point back to a different dir, list the
+ * wrong generation number, or are invalid.
+ */
+ error = xfs_parent_from_attr(sc->mp, attr_flags, name, namelen, value,
+ valuelen, &parent_ino, &parent_gen);
+ if (error)
+ return error;
+
+ if (parent_ino != sc->ip->i_ino ||
+ parent_gen != VFS_I(sc->ip)->i_generation)
+ return 0;
+
+ mutex_lock(&rd->pscan.lock);
+ error = xrep_dir_stash_createname(rd, &xname, ip->i_ino);
+ mutex_unlock(&rd->pscan.lock);
+ return error;
+}
+
+/*
+ * If this child dirent points to the directory being repaired, remember that
+ * fact so that we can reset the dotdot entry if necessary.
+ */
+STATIC int
+xrep_dir_scan_dirent(
+ struct xfs_scrub *sc,
+ struct xfs_inode *dp,
+ xfs_dir2_dataptr_t dapos,
+ const struct xfs_name *name,
+ xfs_ino_t ino,
+ void *priv)
+{
+ struct xrep_dir *rd = priv;
+
+ /* Dirent doesn't point to this directory. */
+ if (ino != rd->sc->ip->i_ino)
+ return 0;
+
+ /* Ignore garbage inum. */
+ if (!xfs_verify_dir_ino(rd->sc->mp, ino))
+ return 0;
+
+ /* No weird looking names. */
+ if (name->len >= MAXNAMELEN || name->len <= 0)
+ return 0;
+
+ /* Don't pick up dot or dotdot entries; we only want child dirents. */
+ if (xfs_dir2_samename(name, &xfs_name_dotdot) ||
+ xfs_dir2_samename(name, &xfs_name_dot))
+ return 0;
+
+ trace_xrep_dir_stash_createname(sc->tempip, &xfs_name_dotdot,
+ dp->i_ino);
+
+ xrep_findparent_scan_found(&rd->pscan, dp->i_ino);
+ return 0;
+}
+
+/*
+ * Decide if we want to look for child dirents or parent pointers in this file.
+ * Skip the dir being repaired and any files being used to stage repairs.
+ */
+static inline bool
+xrep_dir_want_scan(
+ struct xrep_dir *rd,
+ const struct xfs_inode *ip)
+{
+ return ip != rd->sc->ip && !xrep_is_tempfile(ip);
+}
+
+/*
+ * Take ILOCK on a file that we want to scan.
+ *
+ * Select ILOCK_EXCL if the file is a directory with an unloaded data bmbt or
+ * has an unloaded attr bmbt. Otherwise, take ILOCK_SHARED.
+ */
+static inline unsigned int
+xrep_dir_scan_ilock(
+ struct xrep_dir *rd,
+ struct xfs_inode *ip)
+{
+ uint lock_mode = XFS_ILOCK_SHARED;
+
+ /* Need to take the shared ILOCK to advance the iscan cursor. */
+ if (!xrep_dir_want_scan(rd, ip))
+ goto lock;
+
+ if (S_ISDIR(VFS_I(ip)->i_mode) && xfs_need_iread_extents(&ip->i_df)) {
+ lock_mode = XFS_ILOCK_EXCL;
+ goto lock;
+ }
+
+ if (xfs_inode_has_attr_fork(ip) && xfs_need_iread_extents(&ip->i_af))
+ lock_mode = XFS_ILOCK_EXCL;
+
+lock:
+ xfs_ilock(ip, lock_mode);
+ return lock_mode;
+}
+
+/*
+ * Scan this file for relevant child dirents or parent pointers that point to
+ * the directory we're rebuilding.
+ */
+STATIC int
+xrep_dir_scan_file(
+ struct xrep_dir *rd,
+ struct xfs_inode *ip)
+{
+ unsigned int lock_mode;
+ int error = 0;
+
+ lock_mode = xrep_dir_scan_ilock(rd, ip);
+
+ if (!xrep_dir_want_scan(rd, ip))
+ goto scan_done;
+
+ /*
+ * If the extended attributes look as though they has been zapped by
+ * the inode record repair code, we cannot scan for parent pointers.
+ */
+ if (xchk_pptr_looks_zapped(ip)) {
+ error = -EBUSY;
+ goto scan_done;
+ }
+
+ error = xchk_xattr_walk(rd->sc, ip, xrep_dir_scan_pptr, NULL, rd);
+ if (error)
+ goto scan_done;
+
+ if (S_ISDIR(VFS_I(ip)->i_mode)) {
+ /*
+ * If the directory looks as though it has been zapped by the
+ * inode record repair code, we cannot scan for child dirents.
+ */
+ if (xchk_dir_looks_zapped(ip)) {
+ error = -EBUSY;
+ goto scan_done;
+ }
+
+ error = xchk_dir_walk(rd->sc, ip, xrep_dir_scan_dirent, rd);
+ if (error)
+ goto scan_done;
+ }
+
+scan_done:
+ xchk_iscan_mark_visited(&rd->pscan.iscan, ip);
+ xfs_iunlock(ip, lock_mode);
+ return error;
+}
+
+/*
+ * Scan all files in the filesystem for parent pointers that we can turn into
+ * replacement dirents, and a dirent that we can use to set the dotdot pointer.
+ */
+STATIC int
+xrep_dir_scan_dirtree(
+ struct xrep_dir *rd)
+{
+ struct xfs_scrub *sc = rd->sc;
+ struct xfs_inode *ip;
+ int error;
+
+ /* Roots of directory trees are their own parents. */
+ if (sc->ip == sc->mp->m_rootip)
+ xrep_findparent_scan_found(&rd->pscan, sc->ip->i_ino);
+
+ /*
+ * Filesystem scans are time consuming. Drop the directory ILOCK and
+ * all other resources for the duration of the scan and hope for the
+ * best. The live update hooks will keep our scan information up to
+ * date even though we've dropped the locks.
+ */
+ xchk_trans_cancel(sc);
+ if (sc->ilock_flags & (XFS_ILOCK_SHARED | XFS_ILOCK_EXCL))
+ xchk_iunlock(sc, sc->ilock_flags & (XFS_ILOCK_SHARED |
+ XFS_ILOCK_EXCL));
+ error = xchk_trans_alloc_empty(sc);
+ if (error)
+ return error;
+
+ while ((error = xchk_iscan_iter(&rd->pscan.iscan, &ip)) == 1) {
+ bool flush;
+
+ error = xrep_dir_scan_file(rd, ip);
+ xchk_irele(sc, ip);
+ if (error)
+ break;
+
+ /* Flush stashed dirent updates to constrain memory usage. */
+ mutex_lock(&rd->pscan.lock);
+ flush = xrep_dir_want_flush_stashed(rd);
+ mutex_unlock(&rd->pscan.lock);
+ if (flush) {
+ xchk_trans_cancel(sc);
+
+ error = xrep_tempfile_iolock_polled(sc);
+ if (error)
+ break;
+
+ error = xrep_dir_replay_updates(rd);
+ xrep_tempfile_iounlock(sc);
+ if (error)
+ break;
+
+ error = xchk_trans_alloc_empty(sc);
+ if (error)
+ break;
+ }
+
+ if (xchk_should_terminate(sc, &error))
+ break;
+ }
+ xchk_iscan_iter_finish(&rd->pscan.iscan);
+ if (error) {
+ /*
+ * If we couldn't grab an inode that was busy with a state
+ * change, change the error code so that we exit to userspace
+ * as quickly as possible.
+ */
+ if (error == -EBUSY)
+ return -ECANCELED;
+ return error;
+ }
+
+ /*
+ * Cancel the empty transaction so that we can (later) use the atomic
+ * file mapping exchange functions to lock files and commit the new
+ * directory.
+ */
+ xchk_trans_cancel(rd->sc);
+ return 0;
+}
+
+/*
+ * Capture dirent updates being made by other threads which are relevant to the
+ * directory being repaired.
+ */
+STATIC int
+xrep_dir_live_update(
+ struct notifier_block *nb,
+ unsigned long action,
+ void *data)
+{
+ struct xfs_dir_update_params *p = data;
+ struct xrep_dir *rd;
+ struct xfs_scrub *sc;
+ int error = 0;
+
+ rd = container_of(nb, struct xrep_dir, pscan.dhook.dirent_hook.nb);
+ sc = rd->sc;
+
+ /*
+ * This thread updated a child dirent in the directory that we're
+ * rebuilding. Stash the update for replay against the temporary
+ * directory.
+ */
+ if (p->dp->i_ino == sc->ip->i_ino &&
+ xchk_iscan_want_live_update(&rd->pscan.iscan, p->ip->i_ino)) {
+ mutex_lock(&rd->pscan.lock);
+ if (p->delta > 0)
+ error = xrep_dir_stash_createname(rd, p->name,
+ p->ip->i_ino);
+ else
+ error = xrep_dir_stash_removename(rd, p->name,
+ p->ip->i_ino);
+ mutex_unlock(&rd->pscan.lock);
+ if (error)
+ goto out_abort;
+ }
+
+ /*
+ * This thread updated another directory's child dirent that points to
+ * the directory that we're rebuilding, so remember the new dotdot
+ * target.
+ */
+ if (p->ip->i_ino == sc->ip->i_ino &&
+ xchk_iscan_want_live_update(&rd->pscan.iscan, p->dp->i_ino)) {
+ if (p->delta > 0) {
+ trace_xrep_dir_stash_createname(sc->tempip,
+ &xfs_name_dotdot,
+ p->dp->i_ino);
+
+ xrep_findparent_scan_found(&rd->pscan, p->dp->i_ino);
+ } else {
+ trace_xrep_dir_stash_removename(sc->tempip,
+ &xfs_name_dotdot,
+ rd->pscan.parent_ino);
+
+ xrep_findparent_scan_found(&rd->pscan, NULLFSINO);
+ }
+ }
+
+ return NOTIFY_DONE;
+out_abort:
+ xchk_iscan_abort(&rd->pscan.iscan);
+ return NOTIFY_DONE;
+}
+
+/*
+ * Free all the directory blocks and reset the data fork. The caller must
+ * join the inode to the transaction. This function returns with the inode
+ * joined to a clean scrub transaction.
+ */
+STATIC int
+xrep_dir_reset_fork(
+ struct xrep_dir *rd,
+ xfs_ino_t parent_ino)
+{
+ struct xfs_scrub *sc = rd->sc;
+ struct xfs_ifork *ifp = xfs_ifork_ptr(sc->tempip, XFS_DATA_FORK);
+ int error;
+
+ /* Unmap all the directory buffers. */
+ if (xfs_ifork_has_extents(ifp)) {
+ error = xrep_reap_ifork(sc, sc->tempip, XFS_DATA_FORK);
+ if (error)
+ return error;
+ }
+
+ trace_xrep_dir_reset_fork(sc->tempip, parent_ino);
+
+ /* Reset the data fork to an empty data fork. */
+ xfs_idestroy_fork(ifp);
+ ifp->if_bytes = 0;
+ sc->tempip->i_disk_size = 0;
+
+ /* Reinitialize the short form directory. */
+ xrep_dir_init_args(rd, sc->tempip, NULL);
+ return xfs_dir2_sf_create(&rd->args, parent_ino);
+}
+
+/*
+ * Prepare both inodes' directory forks for exchanging mappings. Promote the
+ * tempfile from short format to leaf format, and if the file being repaired
+ * has a short format data fork, turn it into an empty extent list.
+ */
+STATIC int
+xrep_dir_swap_prep(
+ struct xfs_scrub *sc,
+ bool temp_local,
+ bool ip_local)
+{
+ int error;
+
+ /*
+ * If the tempfile's directory is in shortform format, convert that to
+ * a single leaf extent so that we can use the atomic mapping exchange.
+ */
+ if (temp_local) {
+ struct xfs_da_args args = {
+ .dp = sc->tempip,
+ .geo = sc->mp->m_dir_geo,
+ .whichfork = XFS_DATA_FORK,
+ .trans = sc->tp,
+ .total = 1,
+ .owner = sc->ip->i_ino,
+ };
+
+ error = xfs_dir2_sf_to_block(&args);
+ if (error)
+ return error;
+
+ /*
+ * Roll the deferred log items to get us back to a clean
+ * transaction.
+ */
+ error = xfs_defer_finish(&sc->tp);
+ if (error)
+ return error;
+ }
+
+ /*
+ * If the file being repaired had a shortform data fork, convert that
+ * to an empty extent list in preparation for the atomic mapping
+ * exchange.
+ */
+ if (ip_local) {
+ struct xfs_ifork *ifp;
+
+ ifp = xfs_ifork_ptr(sc->ip, XFS_DATA_FORK);
+ xfs_idestroy_fork(ifp);
+ ifp->if_format = XFS_DINODE_FMT_EXTENTS;
+ ifp->if_nextents = 0;
+ ifp->if_bytes = 0;
+ ifp->if_data = NULL;
+ ifp->if_height = 0;
+
+ xfs_trans_log_inode(sc->tp, sc->ip,
+ XFS_ILOG_CORE | XFS_ILOG_DDATA);
+ }
+
+ return 0;
+}
+
+/*
+ * Replace the inode number of a directory entry.
+ */
+static int
+xrep_dir_replace(
+ struct xrep_dir *rd,
+ struct xfs_inode *dp,
+ const struct xfs_name *name,
+ xfs_ino_t inum,
+ xfs_extlen_t total)
+{
+ struct xfs_scrub *sc = rd->sc;
+ int error;
+
+ ASSERT(S_ISDIR(VFS_I(dp)->i_mode));
+
+ error = xfs_dir_ino_validate(sc->mp, inum);
+ if (error)
+ return error;
+
+ xrep_dir_init_args(rd, dp, name);
+ rd->args.inumber = inum;
+ rd->args.total = total;
+ return xfs_dir_replace_args(&rd->args);
+}
+
+/*
+ * Reset the link count of this directory and adjust the unlinked list pointers
+ * as needed.
+ */
+STATIC int
+xrep_dir_set_nlink(
+ struct xrep_dir *rd)
+{
+ struct xfs_scrub *sc = rd->sc;
+ struct xfs_inode *dp = sc->ip;
+ struct xfs_perag *pag;
+ unsigned int new_nlink = min_t(unsigned long long,
+ rd->subdirs + 2,
+ XFS_NLINK_PINNED);
+ int error;
+
+ /*
+ * The directory is not on the incore unlinked list, which means that
+ * it needs to be reachable via the directory tree. Update the nlink
+ * with our observed link count. If the directory has no parent, it
+ * will be moved to the orphanage.
+ */
+ if (!xfs_inode_on_unlinked_list(dp))
+ goto reset_nlink;
+
+ /*
+ * The directory is on the unlinked list and we did not find any
+ * dirents. Set the link count to zero and let the directory
+ * inactivate when the last reference drops.
+ */
+ if (rd->dirents == 0) {
+ rd->needs_adoption = false;
+ new_nlink = 0;
+ goto reset_nlink;
+ }
+
+ /*
+ * The directory is on the unlinked list and we found dirents. This
+ * directory needs to be reachable via the directory tree. Remove the
+ * dir from the unlinked list and update nlink with the observed link
+ * count. If the directory has no parent, it will be moved to the
+ * orphanage.
+ */
+ pag = xfs_perag_get(sc->mp, XFS_INO_TO_AGNO(sc->mp, dp->i_ino));
+ if (!pag) {
+ ASSERT(0);
+ return -EFSCORRUPTED;
+ }
+
+ error = xfs_iunlink_remove(sc->tp, pag, dp);
+ xfs_perag_put(pag);
+ if (error)
+ return error;
+
+reset_nlink:
+ if (VFS_I(dp)->i_nlink != new_nlink)
+ set_nlink(VFS_I(dp), new_nlink);
+ return 0;
+}
+
+/*
+ * Finish replaying stashed dirent updates, allocate a transaction for
+ * exchanging data fork mappings, and take the ILOCKs of both directories
+ * before we commit the new directory structure.
+ */
+STATIC int
+xrep_dir_finalize_tempdir(
+ struct xrep_dir *rd)
+{
+ struct xfs_scrub *sc = rd->sc;
+ int error;
+
+ if (!xfs_has_parent(sc->mp))
+ return xrep_tempexch_trans_alloc(sc, XFS_DATA_FORK, &rd->tx);
+
+ /*
+ * Repair relies on the ILOCK to quiesce all possible dirent updates.
+ * Replay all queued dirent updates into the tempdir before exchanging
+ * the contents, even if that means dropping the ILOCKs and the
+ * transaction.
+ */
+ do {
+ error = xrep_dir_replay_updates(rd);
+ if (error)
+ return error;
+
+ error = xrep_tempexch_trans_alloc(sc, XFS_DATA_FORK, &rd->tx);
+ if (error)
+ return error;
+
+ if (xfarray_length(rd->dir_entries) == 0)
+ break;
+
+ xchk_trans_cancel(sc);
+ xrep_tempfile_iunlock_both(sc);
+ } while (!xchk_should_terminate(sc, &error));
+ return error;
+}
+
+/* Exchange the temporary directory's data fork with the one being repaired. */
+STATIC int
+xrep_dir_swap(
+ struct xrep_dir *rd)
+{
+ struct xfs_scrub *sc = rd->sc;
+ bool ip_local, temp_local;
+ int error = 0;
+
+ /*
+ * If we never found the parent for this directory, temporarily assign
+ * the root dir as the parent; we'll move this to the orphanage after
+ * exchanging the dir contents. We hold the ILOCK of the dir being
+ * repaired, so we're not worried about racy updates of dotdot.
+ */
+ ASSERT(sc->ilock_flags & XFS_ILOCK_EXCL);
+ if (rd->pscan.parent_ino == NULLFSINO) {
+ rd->needs_adoption = true;
+ rd->pscan.parent_ino = rd->sc->mp->m_sb.sb_rootino;
+ }
+
+ /*
+ * Reset the temporary directory's '..' entry to point to the parent
+ * that we found. The temporary directory was created with the root
+ * directory as the parent, so we can skip this if repairing a
+ * subdirectory of the root.
+ *
+ * It's also possible that this replacement could also expand a sf
+ * tempdir into block format.
+ */
+ if (rd->pscan.parent_ino != sc->mp->m_rootip->i_ino) {
+ error = xrep_dir_replace(rd, rd->sc->tempip, &xfs_name_dotdot,
+ rd->pscan.parent_ino, rd->tx.req.resblks);
+ if (error)
+ return error;
+ }
+
+ /*
+ * Changing the dot and dotdot entries could have changed the shape of
+ * the directory, so we recompute these.
+ */
+ ip_local = sc->ip->i_df.if_format == XFS_DINODE_FMT_LOCAL;
+ temp_local = sc->tempip->i_df.if_format == XFS_DINODE_FMT_LOCAL;
+
+ /*
+ * If the both files have a local format data fork and the rebuilt
+ * directory data would fit in the repaired file's data fork, copy
+ * the contents from the tempfile and update the directory link count.
+ * We're done now.
+ */
+ if (ip_local && temp_local &&
+ sc->tempip->i_disk_size <= xfs_inode_data_fork_size(sc->ip)) {
+ xrep_tempfile_copyout_local(sc, XFS_DATA_FORK);
+ return xrep_dir_set_nlink(rd);
+ }
+
+ /*
+ * Clean the transaction before we start working on exchanging
+ * directory contents.
+ */
+ error = xrep_tempfile_roll_trans(rd->sc);
+ if (error)
+ return error;
+
+ /* Otherwise, make sure both data forks are in block-mapping mode. */
+ error = xrep_dir_swap_prep(sc, temp_local, ip_local);
+ if (error)
+ return error;
+
+ /*
+ * Set nlink of the directory in the same transaction sequence that
+ * (atomically) commits the new directory data.
+ */
+ error = xrep_dir_set_nlink(rd);
+ if (error)
+ return error;
+
+ return xrep_tempexch_contents(sc, &rd->tx);
+}
+
+/*
+ * Exchange the new directory contents (which we created in the tempfile) with
+ * the directory being repaired.
+ */
+STATIC int
+xrep_dir_rebuild_tree(
+ struct xrep_dir *rd)
+{
+ struct xfs_scrub *sc = rd->sc;
+ int error;
+
+ trace_xrep_dir_rebuild_tree(sc->ip, rd->pscan.parent_ino);
+
+ /*
+ * Take the IOLOCK on the temporary file so that we can run dir
+ * operations with the same locks held as we would for a normal file.
+ * We still hold sc->ip's IOLOCK.
+ */
+ error = xrep_tempfile_iolock_polled(rd->sc);
+ if (error)
+ return error;
+
+ /*
+ * Allocate transaction, lock inodes, and make sure that we've replayed
+ * all the stashed dirent updates to the tempdir. After this point,
+ * we're ready to exchange data fork mappings.
+ */
+ error = xrep_dir_finalize_tempdir(rd);
+ if (error)
+ return error;
+
+ if (xchk_iscan_aborted(&rd->pscan.iscan))
+ return -ECANCELED;
+
+ /*
+ * Exchange the tempdir's data fork with the file being repaired. This
+ * recreates the transaction and re-takes the ILOCK in the scrub
+ * context.
+ */
+ error = xrep_dir_swap(rd);
+ if (error)
+ return error;
+
+ /*
+ * Release the old directory blocks and reset the data fork of the temp
+ * directory to an empty shortform directory because inactivation does
+ * nothing for directories.
+ */
+ error = xrep_dir_reset_fork(rd, sc->mp->m_rootip->i_ino);
+ if (error)
+ return error;
+
+ /*
+ * Roll to get a transaction without any inodes joined to it. Then we
+ * can drop the tempfile's ILOCK and IOLOCK before doing more work on
+ * the scrub target directory.
+ */
+ error = xfs_trans_roll(&sc->tp);
+ if (error)
+ return error;
+
+ xrep_tempfile_iunlock(sc);
+ xrep_tempfile_iounlock(sc);
+ return 0;
+}
+
+/* Set up the filesystem scan so we can regenerate directory entries. */
+STATIC int
+xrep_dir_setup_scan(
+ struct xrep_dir *rd)
+{
+ struct xfs_scrub *sc = rd->sc;
+ char *descr;
+ int error;
+
+ /* Set up some staging memory for salvaging dirents. */
+ descr = xchk_xfile_ino_descr(sc, "directory entries");
+ error = xfarray_create(descr, 0, sizeof(struct xrep_dirent),
+ &rd->dir_entries);
+ kfree(descr);
+ if (error)
+ return error;
+
+ descr = xchk_xfile_ino_descr(sc, "directory entry names");
+ error = xfblob_create(descr, &rd->dir_names);
+ kfree(descr);
+ if (error)
+ goto out_xfarray;
+
+ if (xfs_has_parent(sc->mp))
+ error = __xrep_findparent_scan_start(sc, &rd->pscan,
+ xrep_dir_live_update);
+ else
+ error = xrep_findparent_scan_start(sc, &rd->pscan);
+ if (error)
+ goto out_xfblob;
+
+ return 0;
+
+out_xfblob:
+ xfblob_destroy(rd->dir_names);
+ rd->dir_names = NULL;
+out_xfarray:
+ xfarray_destroy(rd->dir_entries);
+ rd->dir_entries = NULL;
+ return error;
+}
+
+/*
+ * Move the current file to the orphanage.
+ *
+ * Caller must hold IOLOCK_EXCL on @sc->ip, and no other inode locks. Upon
+ * successful return, the scrub transaction will have enough extra reservation
+ * to make the move; it will hold IOLOCK_EXCL and ILOCK_EXCL of @sc->ip and the
+ * orphanage; and both inodes will be ijoined.
+ */
+STATIC int
+xrep_dir_move_to_orphanage(
+ struct xrep_dir *rd)
+{
+ struct xfs_scrub *sc = rd->sc;
+ xfs_ino_t orig_parent, new_parent;
+ int error;
+
+ /*
+ * We are about to drop the ILOCK on sc->ip to lock the orphanage and
+ * prepare for the adoption. Therefore, look up the old dotdot entry
+ * for sc->ip so that we can compare it after we re-lock sc->ip.
+ */
+ error = xchk_dir_lookup(sc, sc->ip, &xfs_name_dotdot, &orig_parent);
+ if (error)
+ return error;
+
+ /*
+ * Drop the ILOCK on the scrub target and commit the transaction.
+ * Adoption computes its own resource requirements and gathers the
+ * necessary components.
+ */
+ error = xrep_trans_commit(sc);
+ if (error)
+ return error;
+ xchk_iunlock(sc, XFS_ILOCK_EXCL);
+
+ /* If we can take the orphanage's iolock then we're ready to move. */
+ if (!xrep_orphanage_ilock_nowait(sc, XFS_IOLOCK_EXCL)) {
+ xchk_iunlock(sc, sc->ilock_flags);
+ error = xrep_orphanage_iolock_two(sc);
+ if (error)
+ return error;
+ }
+
+ /* Grab transaction and ILOCK the two files. */
+ error = xrep_adoption_trans_alloc(sc, &rd->adoption);
+ if (error)
+ return error;
+
+ error = xrep_adoption_compute_name(&rd->adoption, &rd->xname);
+ if (error)
+ return error;
+
+ /*
+ * Now that we've reacquired the ILOCK on sc->ip, look up the dotdot
+ * entry again. If the parent changed or the child was unlinked while
+ * the child directory was unlocked, we don't need to move the child to
+ * the orphanage after all.
+ */
+ error = xchk_dir_lookup(sc, sc->ip, &xfs_name_dotdot, &new_parent);
+ if (error)
+ return error;
+
+ /*
+ * Attach to the orphanage if we still have a linked directory and it
+ * hasn't been moved.
+ */
+ if (orig_parent == new_parent && VFS_I(sc->ip)->i_nlink > 0) {
+ error = xrep_adoption_move(&rd->adoption);
+ if (error)
+ return error;
+ }
+
+ /*
+ * Launder the scrub transaction so we can drop the orphanage ILOCK
+ * and IOLOCK. Return holding the scrub target's ILOCK and IOLOCK.
+ */
+ error = xrep_adoption_trans_roll(&rd->adoption);
+ if (error)
+ return error;
+
+ xrep_orphanage_iunlock(sc, XFS_ILOCK_EXCL);
+ xrep_orphanage_iunlock(sc, XFS_IOLOCK_EXCL);
+ return 0;
+}
+
+/*
+ * Repair the directory metadata.
+ *
+ * XXX: Directory entry buffers can be multiple fsblocks in size. The buffer
+ * cache in XFS can't handle aliased multiblock buffers, so this might
+ * misbehave if the directory blocks are crosslinked with other filesystem
+ * metadata.
+ *
+ * XXX: Is it necessary to check the dcache for this directory to make sure
+ * that we always recreate every cached entry?
+ */
+int
+xrep_directory(
+ struct xfs_scrub *sc)
+{
+ struct xrep_dir *rd = sc->buf;
+ int error;
+
+ /* The rmapbt is required to reap the old data fork. */
+ if (!xfs_has_rmapbt(sc->mp))
+ return -EOPNOTSUPP;
+ /* We require atomic file exchange range to rebuild anything. */
+ if (!xfs_has_exchange_range(sc->mp))
+ return -EOPNOTSUPP;
+
+ error = xrep_dir_setup_scan(rd);
+ if (error)
+ return error;
+
+ if (xfs_has_parent(sc->mp))
+ error = xrep_dir_scan_dirtree(rd);
+ else
+ error = xrep_dir_salvage_entries(rd);
+ if (error)
+ goto out_teardown;
+
+ /* Last chance to abort before we start committing fixes. */
+ if (xchk_should_terminate(sc, &error))
+ goto out_teardown;
+
+ error = xrep_dir_rebuild_tree(rd);
+ if (error)
+ goto out_teardown;
+
+ if (rd->needs_adoption) {
+ if (!xrep_orphanage_can_adopt(rd->sc))
+ error = -EFSCORRUPTED;
+ else
+ error = xrep_dir_move_to_orphanage(rd);
+ if (error)
+ goto out_teardown;
+ }
+
+out_teardown:
+ xrep_dir_teardown(sc);
+ return error;
+}
diff --git a/fs/xfs/scrub/dirtree.c b/fs/xfs/scrub/dirtree.c
new file mode 100644
index 0000000000..bde58fb561
--- /dev/null
+++ b/fs/xfs/scrub/dirtree.c
@@ -0,0 +1,985 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Copyright (c) 2023-2024 Oracle. All Rights Reserved.
+ * Author: Darrick J. Wong <djwong@kernel.org>
+ */
+#include "xfs.h"
+#include "xfs_fs.h"
+#include "xfs_shared.h"
+#include "xfs_format.h"
+#include "xfs_trans_resv.h"
+#include "xfs_mount.h"
+#include "xfs_log_format.h"
+#include "xfs_trans.h"
+#include "xfs_inode.h"
+#include "xfs_icache.h"
+#include "xfs_dir2.h"
+#include "xfs_dir2_priv.h"
+#include "xfs_attr.h"
+#include "xfs_parent.h"
+#include "scrub/scrub.h"
+#include "scrub/common.h"
+#include "scrub/bitmap.h"
+#include "scrub/ino_bitmap.h"
+#include "scrub/xfile.h"
+#include "scrub/xfarray.h"
+#include "scrub/xfblob.h"
+#include "scrub/listxattr.h"
+#include "scrub/trace.h"
+#include "scrub/repair.h"
+#include "scrub/orphanage.h"
+#include "scrub/dirtree.h"
+
+/*
+ * Directory Tree Structure Validation
+ * ===================================
+ *
+ * Validating the tree qualities of the directory tree structure can be
+ * difficult. If the tree is frozen, running a depth (or breadth) first search
+ * and marking a bitmap suffices to determine if there is a cycle. XORing the
+ * mark bitmap with the inode bitmap afterwards tells us if there are
+ * disconnected cycles. If the tree is not frozen, directory updates can move
+ * subtrees across the scanner wavefront, which complicates the design greatly.
+ *
+ * Directory parent pointers change that by enabling an incremental approach to
+ * validation of the tree structure. Instead of using one thread to scan the
+ * entire filesystem, we instead can have multiple threads walking individual
+ * subdirectories upwards to the root. In a perfect world, the IOLOCK would
+ * suffice to stabilize two directories in a parent -> child relationship.
+ * Unfortunately, the VFS does not take the IOLOCK when moving a child
+ * subdirectory, so we instead synchronize on ILOCK and use dirent update hooks
+ * to detect a race. If a race occurs in a path, we restart the scan.
+ *
+ * If the walk terminates without reaching the root, we know the path is
+ * disconnected and ought to be attached to the lost and found. If on the walk
+ * we find the same subdir that we're scanning, we know this is a cycle and
+ * should delete an incoming edge. If we find multiple paths to the root, we
+ * know to delete an incoming edge.
+ *
+ * There are two big hitches with this approach: first, all file link counts
+ * must be correct to prevent other writers from doing the wrong thing with the
+ * directory tree structure. Second, because we're walking upwards in a tree
+ * of arbitrary depth, we cannot hold all the ILOCKs. Instead, we will use a
+ * directory update hook to invalidate the scan results if one of the paths
+ * we've scanned has changed.
+ */
+
+/* Clean up the dirtree checking resources. */
+STATIC void
+xchk_dirtree_buf_cleanup(
+ void *buf)
+{
+ struct xchk_dirtree *dl = buf;
+ struct xchk_dirpath *path, *n;
+
+ if (dl->scan_ino != NULLFSINO)
+ xfs_dir_hook_del(dl->sc->mp, &dl->dhook);
+
+ xchk_dirtree_for_each_path_safe(dl, path, n) {
+ list_del_init(&path->list);
+ xino_bitmap_destroy(&path->seen_inodes);
+ kfree(path);
+ }
+
+ xfblob_destroy(dl->path_names);
+ xfarray_destroy(dl->path_steps);
+ mutex_destroy(&dl->lock);
+}
+
+/* Set us up to look for directory loops. */
+int
+xchk_setup_dirtree(
+ struct xfs_scrub *sc)
+{
+ struct xchk_dirtree *dl;
+ char *descr;
+ int error;
+
+ xchk_fsgates_enable(sc, XCHK_FSGATES_DIRENTS);
+
+ if (xchk_could_repair(sc)) {
+ error = xrep_setup_dirtree(sc);
+ if (error)
+ return error;
+ }
+
+ dl = kvzalloc(sizeof(struct xchk_dirtree), XCHK_GFP_FLAGS);
+ if (!dl)
+ return -ENOMEM;
+ dl->sc = sc;
+ dl->xname.name = dl->namebuf;
+ dl->hook_xname.name = dl->hook_namebuf;
+ INIT_LIST_HEAD(&dl->path_list);
+ dl->root_ino = NULLFSINO;
+ dl->scan_ino = NULLFSINO;
+ dl->parent_ino = NULLFSINO;
+
+ mutex_init(&dl->lock);
+
+ descr = xchk_xfile_ino_descr(sc, "dirtree path steps");
+ error = xfarray_create(descr, 0, sizeof(struct xchk_dirpath_step),
+ &dl->path_steps);
+ kfree(descr);
+ if (error)
+ goto out_dl;
+
+ descr = xchk_xfile_ino_descr(sc, "dirtree path names");
+ error = xfblob_create(descr, &dl->path_names);
+ kfree(descr);
+ if (error)
+ goto out_steps;
+
+ error = xchk_setup_inode_contents(sc, 0);
+ if (error)
+ goto out_names;
+
+ sc->buf = dl;
+ sc->buf_cleanup = xchk_dirtree_buf_cleanup;
+ return 0;
+
+out_names:
+ xfblob_destroy(dl->path_names);
+out_steps:
+ xfarray_destroy(dl->path_steps);
+out_dl:
+ mutex_destroy(&dl->lock);
+ kvfree(dl);
+ return error;
+}
+
+/*
+ * Add the parent pointer described by @dl->pptr to the given path as a new
+ * step. Returns -ELNRNG if the path is too deep.
+ */
+int
+xchk_dirpath_append(
+ struct xchk_dirtree *dl,
+ struct xfs_inode *ip,
+ struct xchk_dirpath *path,
+ const struct xfs_name *name,
+ const struct xfs_parent_rec *pptr)
+{
+ struct xchk_dirpath_step step = {
+ .pptr_rec = *pptr, /* struct copy */
+ .name_len = name->len,
+ };
+ int error;
+
+ /*
+ * If this path is more than 2 billion steps long, this directory tree
+ * is too far gone to fix.
+ */
+ if (path->nr_steps >= XFS_MAXLINK)
+ return -ELNRNG;
+
+ error = xfblob_storename(dl->path_names, &step.name_cookie, name);
+ if (error)
+ return error;
+
+ error = xino_bitmap_set(&path->seen_inodes, ip->i_ino);
+ if (error)
+ return error;
+
+ error = xfarray_append(dl->path_steps, &step);
+ if (error)
+ return error;
+
+ path->nr_steps++;
+ return 0;
+}
+
+/*
+ * Create an xchk_path for each parent pointer of the directory that we're
+ * scanning. For each path created, we will eventually try to walk towards the
+ * root with the goal of deleting all parents except for one that leads to the
+ * root.
+ *
+ * Returns -EFSCORRUPTED to signal that the inode being scanned has a corrupt
+ * parent pointer and hence there's no point in continuing; or -ENOSR if there
+ * are too many parent pointers for this directory.
+ */
+STATIC int
+xchk_dirtree_create_path(
+ struct xfs_scrub *sc,
+ struct xfs_inode *ip,
+ unsigned int attr_flags,
+ const unsigned char *name,
+ unsigned int namelen,
+ const void *value,
+ unsigned int valuelen,
+ void *priv)
+{
+ struct xfs_name xname = {
+ .name = name,
+ .len = namelen,
+ };
+ struct xchk_dirtree *dl = priv;
+ struct xchk_dirpath *path;
+ const struct xfs_parent_rec *rec = value;
+ int error;
+
+ if (!(attr_flags & XFS_ATTR_PARENT))
+ return 0;
+
+ error = xfs_parent_from_attr(sc->mp, attr_flags, name, namelen, value,
+ valuelen, NULL, NULL);
+ if (error)
+ return error;
+
+ /*
+ * If there are more than 2 billion actual parent pointers for this
+ * subdirectory, this fs is too far gone to fix.
+ */
+ if (dl->nr_paths >= XFS_MAXLINK)
+ return -ENOSR;
+
+ trace_xchk_dirtree_create_path(sc, ip, dl->nr_paths, &xname, rec);
+
+ /*
+ * Create a new xchk_path structure to remember this parent pointer
+ * and record the first name step.
+ */
+ path = kmalloc(sizeof(struct xchk_dirpath), XCHK_GFP_FLAGS);
+ if (!path)
+ return -ENOMEM;
+
+ INIT_LIST_HEAD(&path->list);
+ xino_bitmap_init(&path->seen_inodes);
+ path->nr_steps = 0;
+ path->outcome = XCHK_DIRPATH_SCANNING;
+
+ error = xchk_dirpath_append(dl, sc->ip, path, &xname, rec);
+ if (error)
+ goto out_path;
+
+ path->first_step = xfarray_length(dl->path_steps) - 1;
+ path->second_step = XFARRAY_NULLIDX;
+ path->path_nr = dl->nr_paths;
+
+ list_add_tail(&path->list, &dl->path_list);
+ dl->nr_paths++;
+ return 0;
+out_path:
+ kfree(path);
+ return error;
+}
+
+/*
+ * Validate that the first step of this path still has a corresponding
+ * parent pointer in @sc->ip. We probably dropped @sc->ip's ILOCK while
+ * walking towards the roots, which is why this is necessary.
+ *
+ * This function has a side effect of loading the first parent pointer of this
+ * path into the parent pointer scratch pad. This prepares us to walk up the
+ * directory tree towards the root. Returns -ESTALE if the scan data is now
+ * out of date.
+ */
+STATIC int
+xchk_dirpath_revalidate(
+ struct xchk_dirtree *dl,
+ struct xchk_dirpath *path)
+{
+ struct xfs_scrub *sc = dl->sc;
+ int error;
+
+ /*
+ * Look up the parent pointer that corresponds to the start of this
+ * path. If the parent pointer has disappeared on us, dump all the
+ * scan results and try again.
+ */
+ error = xfs_parent_lookup(sc->tp, sc->ip, &dl->xname, &dl->pptr_rec,
+ &dl->pptr_args);
+ if (error == -ENOATTR) {
+ trace_xchk_dirpath_disappeared(dl->sc, sc->ip, path->path_nr,
+ path->first_step, &dl->xname, &dl->pptr_rec);
+ dl->stale = true;
+ return -ESTALE;
+ }
+
+ return error;
+}
+
+/*
+ * Walk the parent pointers of a directory at the end of a path and record
+ * the parent that we find in @dl->xname/pptr_rec.
+ */
+STATIC int
+xchk_dirpath_find_next_step(
+ struct xfs_scrub *sc,
+ struct xfs_inode *ip,
+ unsigned int attr_flags,
+ const unsigned char *name,
+ unsigned int namelen,
+ const void *value,
+ unsigned int valuelen,
+ void *priv)
+{
+ struct xchk_dirtree *dl = priv;
+ const struct xfs_parent_rec *rec = value;
+ int error;
+
+ if (!(attr_flags & XFS_ATTR_PARENT))
+ return 0;
+
+ error = xfs_parent_from_attr(sc->mp, attr_flags, name, namelen, value,
+ valuelen, NULL, NULL);
+ if (error)
+ return error;
+
+ /*
+ * If we've already set @dl->pptr_rec, then this directory has multiple
+ * parents. Signal this back to the caller via -EMLINK.
+ */
+ if (dl->parents_found > 0)
+ return -EMLINK;
+
+ dl->parents_found++;
+ memcpy(dl->namebuf, name, namelen);
+ dl->xname.len = namelen;
+ dl->pptr_rec = *rec; /* struct copy */
+ return 0;
+}
+
+/* Set and log the outcome of a path walk. */
+static inline void
+xchk_dirpath_set_outcome(
+ struct xchk_dirtree *dl,
+ struct xchk_dirpath *path,
+ enum xchk_dirpath_outcome outcome)
+{
+ trace_xchk_dirpath_set_outcome(dl->sc, path->path_nr, path->nr_steps,
+ outcome);
+
+ path->outcome = outcome;
+}
+
+/*
+ * Scan the directory at the end of this path for its parent directory link.
+ * If we find one, extend the path. Returns -ESTALE if the scan data out of
+ * date. Returns -EFSCORRUPTED if the parent pointer is bad; or -ELNRNG if
+ * the path got too deep.
+ */
+STATIC int
+xchk_dirpath_step_up(
+ struct xchk_dirtree *dl,
+ struct xchk_dirpath *path)
+{
+ struct xfs_scrub *sc = dl->sc;
+ struct xfs_inode *dp;
+ xfs_ino_t parent_ino = be64_to_cpu(dl->pptr_rec.p_ino);
+ unsigned int lock_mode;
+ int error;
+
+ /* Grab and lock the parent directory. */
+ error = xchk_iget(sc, parent_ino, &dp);
+ if (error)
+ return error;
+
+ lock_mode = xfs_ilock_attr_map_shared(dp);
+ mutex_lock(&dl->lock);
+
+ if (dl->stale) {
+ error = -ESTALE;
+ goto out_scanlock;
+ }
+
+ /* We've reached the root directory; the path is ok. */
+ if (parent_ino == dl->root_ino) {
+ xchk_dirpath_set_outcome(dl, path, XCHK_DIRPATH_OK);
+ error = 0;
+ goto out_scanlock;
+ }
+
+ /*
+ * The inode being scanned is its own distant ancestor! Get rid of
+ * this path.
+ */
+ if (parent_ino == sc->ip->i_ino) {
+ xchk_dirpath_set_outcome(dl, path, XCHK_DIRPATH_DELETE);
+ error = 0;
+ goto out_scanlock;
+ }
+
+ /*
+ * We've seen this inode before during the path walk. There's a loop
+ * above us in the directory tree. This probably means that we cannot
+ * continue, but let's keep walking paths to get a full picture.
+ */
+ if (xino_bitmap_test(&path->seen_inodes, parent_ino)) {
+ xchk_dirpath_set_outcome(dl, path, XCHK_DIRPATH_LOOP);
+ error = 0;
+ goto out_scanlock;
+ }
+
+ /* The handle encoded in the parent pointer must match. */
+ if (VFS_I(dp)->i_generation != be32_to_cpu(dl->pptr_rec.p_gen)) {
+ trace_xchk_dirpath_badgen(dl->sc, dp, path->path_nr,
+ path->nr_steps, &dl->xname, &dl->pptr_rec);
+ error = -EFSCORRUPTED;
+ goto out_scanlock;
+ }
+
+ /* Parent pointer must point up to a directory. */
+ if (!S_ISDIR(VFS_I(dp)->i_mode)) {
+ trace_xchk_dirpath_nondir_parent(dl->sc, dp, path->path_nr,
+ path->nr_steps, &dl->xname, &dl->pptr_rec);
+ error = -EFSCORRUPTED;
+ goto out_scanlock;
+ }
+
+ /* Parent cannot be an unlinked directory. */
+ if (VFS_I(dp)->i_nlink == 0) {
+ trace_xchk_dirpath_unlinked_parent(dl->sc, dp, path->path_nr,
+ path->nr_steps, &dl->xname, &dl->pptr_rec);
+ error = -EFSCORRUPTED;
+ goto out_scanlock;
+ }
+
+ /*
+ * If the extended attributes look as though they has been zapped by
+ * the inode record repair code, we cannot scan for parent pointers.
+ */
+ if (xchk_pptr_looks_zapped(dp)) {
+ error = -EBUSY;
+ xchk_set_incomplete(sc);
+ goto out_scanlock;
+ }
+
+ /*
+ * Walk the parent pointers of @dp to find the parent of this directory
+ * to find the next step in our walk. If we find that @dp has exactly
+ * one parent, the parent pointer information will be stored in
+ * @dl->pptr_rec. This prepares us for the next step of the walk.
+ */
+ mutex_unlock(&dl->lock);
+ dl->parents_found = 0;
+ error = xchk_xattr_walk(sc, dp, xchk_dirpath_find_next_step, NULL, dl);
+ mutex_lock(&dl->lock);
+ if (error == -EFSCORRUPTED || error == -EMLINK ||
+ (!error && dl->parents_found == 0)) {
+ /*
+ * Further up the directory tree from @sc->ip, we found a
+ * corrupt parent pointer, multiple parent pointers while
+ * finding this directory's parent, or zero parents despite
+ * having a nonzero link count. Keep looking for other paths.
+ */
+ xchk_dirpath_set_outcome(dl, path, XCHK_DIRPATH_CORRUPT);
+ error = 0;
+ goto out_scanlock;
+ }
+ if (error)
+ goto out_scanlock;
+
+ if (dl->stale) {
+ error = -ESTALE;
+ goto out_scanlock;
+ }
+
+ trace_xchk_dirpath_found_next_step(sc, dp, path->path_nr,
+ path->nr_steps, &dl->xname, &dl->pptr_rec);
+
+ /* Append to the path steps */
+ error = xchk_dirpath_append(dl, dp, path, &dl->xname, &dl->pptr_rec);
+ if (error)
+ goto out_scanlock;
+
+ if (path->second_step == XFARRAY_NULLIDX)
+ path->second_step = xfarray_length(dl->path_steps) - 1;
+
+out_scanlock:
+ mutex_unlock(&dl->lock);
+ xfs_iunlock(dp, lock_mode);
+ xchk_irele(sc, dp);
+ return error;
+}
+
+/*
+ * Walk the directory tree upwards towards what is hopefully the root
+ * directory, recording path steps as we go. The current path components are
+ * stored in dl->pptr_rec and dl->xname.
+ *
+ * Returns -ESTALE if the scan data are out of date. Returns -EFSCORRUPTED
+ * only if the direct parent pointer of @sc->ip associated with this path is
+ * corrupt.
+ */
+STATIC int
+xchk_dirpath_walk_upwards(
+ struct xchk_dirtree *dl,
+ struct xchk_dirpath *path)
+{
+ struct xfs_scrub *sc = dl->sc;
+ int error;
+
+ ASSERT(sc->ilock_flags & XFS_ILOCK_EXCL);
+
+ /* Reload the start of this path and make sure it's still there. */
+ error = xchk_dirpath_revalidate(dl, path);
+ if (error)
+ return error;
+
+ trace_xchk_dirpath_walk_upwards(sc, sc->ip, path->path_nr, &dl->xname,
+ &dl->pptr_rec);
+
+ /*
+ * The inode being scanned is its own direct ancestor!
+ * Get rid of this path.
+ */
+ if (be64_to_cpu(dl->pptr_rec.p_ino) == sc->ip->i_ino) {
+ xchk_dirpath_set_outcome(dl, path, XCHK_DIRPATH_DELETE);
+ return 0;
+ }
+
+ /*
+ * Drop ILOCK_EXCL on the inode being scanned. We still hold
+ * IOLOCK_EXCL on it, so it cannot move around or be renamed.
+ *
+ * Beyond this point we're walking up the directory tree, which means
+ * that we can acquire and drop the ILOCK on an alias of sc->ip. The
+ * ILOCK state is no longer tracked in the scrub context. Hence we
+ * must drop @sc->ip's ILOCK during the walk.
+ */
+ mutex_unlock(&dl->lock);
+ xchk_iunlock(sc, XFS_ILOCK_EXCL);
+
+ /*
+ * Take the first step in the walk towards the root by checking the
+ * start of this path, which is a direct parent pointer of @sc->ip.
+ * If we see any kind of error here (including corruptions), the parent
+ * pointer of @sc->ip is corrupt. Stop the whole scan.
+ */
+ error = xchk_dirpath_step_up(dl, path);
+ if (error) {
+ xchk_ilock(sc, XFS_ILOCK_EXCL);
+ mutex_lock(&dl->lock);
+ return error;
+ }
+
+ /*
+ * Take steps upward from the second step in this path towards the
+ * root. If we hit corruption errors here, there's a problem
+ * *somewhere* in the path, but we don't need to stop scanning.
+ */
+ while (!error && path->outcome == XCHK_DIRPATH_SCANNING)
+ error = xchk_dirpath_step_up(dl, path);
+
+ /* Retake the locks we had, mark paths, etc. */
+ xchk_ilock(sc, XFS_ILOCK_EXCL);
+ mutex_lock(&dl->lock);
+ if (error == -EFSCORRUPTED) {
+ xchk_dirpath_set_outcome(dl, path, XCHK_DIRPATH_CORRUPT);
+ error = 0;
+ }
+ if (!error && dl->stale)
+ return -ESTALE;
+ return error;
+}
+
+/*
+ * Decide if this path step has been touched by this live update. Returns
+ * 1 for yes, 0 for no, or a negative errno.
+ */
+STATIC int
+xchk_dirpath_step_is_stale(
+ struct xchk_dirtree *dl,
+ struct xchk_dirpath *path,
+ unsigned int step_nr,
+ xfarray_idx_t step_idx,
+ struct xfs_dir_update_params *p,
+ xfs_ino_t *cursor)
+{
+ struct xchk_dirpath_step step;
+ xfs_ino_t child_ino = *cursor;
+ int error;
+
+ error = xfarray_load(dl->path_steps, step_idx, &step);
+ if (error)
+ return error;
+ *cursor = be64_to_cpu(step.pptr_rec.p_ino);
+
+ /*
+ * If the parent and child being updated are not the ones mentioned in
+ * this path step, the scan data is still ok.
+ */
+ if (p->ip->i_ino != child_ino || p->dp->i_ino != *cursor)
+ return 0;
+
+ /*
+ * If the dirent name lengths or byte sequences are different, the scan
+ * data is still ok.
+ */
+ if (p->name->len != step.name_len)
+ return 0;
+
+ error = xfblob_loadname(dl->path_names, step.name_cookie,
+ &dl->hook_xname, step.name_len);
+ if (error)
+ return error;
+
+ if (memcmp(dl->hook_xname.name, p->name->name, p->name->len) != 0)
+ return 0;
+
+ /*
+ * If the update comes from the repair code itself, walk the state
+ * machine forward.
+ */
+ if (p->ip->i_ino == dl->scan_ino &&
+ path->outcome == XREP_DIRPATH_ADOPTING) {
+ xchk_dirpath_set_outcome(dl, path, XREP_DIRPATH_ADOPTED);
+ return 0;
+ }
+
+ if (p->ip->i_ino == dl->scan_ino &&
+ path->outcome == XREP_DIRPATH_DELETING) {
+ xchk_dirpath_set_outcome(dl, path, XREP_DIRPATH_DELETED);
+ return 0;
+ }
+
+ /* Exact match, scan data is out of date. */
+ trace_xchk_dirpath_changed(dl->sc, path->path_nr, step_nr, p->dp,
+ p->ip, p->name);
+ return 1;
+}
+
+/*
+ * Decide if this path has been touched by this live update. Returns 1 for
+ * yes, 0 for no, or a negative errno.
+ */
+STATIC int
+xchk_dirpath_is_stale(
+ struct xchk_dirtree *dl,
+ struct xchk_dirpath *path,
+ struct xfs_dir_update_params *p)
+{
+ xfs_ino_t cursor = dl->scan_ino;
+ xfarray_idx_t idx = path->first_step;
+ unsigned int i;
+ int ret;
+
+ /*
+ * The child being updated has not been seen by this path at all; this
+ * path cannot be stale.
+ */
+ if (!xino_bitmap_test(&path->seen_inodes, p->ip->i_ino))
+ return 0;
+
+ ret = xchk_dirpath_step_is_stale(dl, path, 0, idx, p, &cursor);
+ if (ret != 0)
+ return ret;
+
+ for (i = 1, idx = path->second_step; i < path->nr_steps; i++, idx++) {
+ ret = xchk_dirpath_step_is_stale(dl, path, i, idx, p, &cursor);
+ if (ret != 0)
+ return ret;
+ }
+
+ return 0;
+}
+
+/*
+ * Decide if a directory update from the regular filesystem touches any of the
+ * paths we've scanned, and invalidate the scan data if true.
+ */
+STATIC int
+xchk_dirtree_live_update(
+ struct notifier_block *nb,
+ unsigned long action,
+ void *data)
+{
+ struct xfs_dir_update_params *p = data;
+ struct xchk_dirtree *dl;
+ struct xchk_dirpath *path;
+ int ret;
+
+ dl = container_of(nb, struct xchk_dirtree, dhook.dirent_hook.nb);
+
+ trace_xchk_dirtree_live_update(dl->sc, p->dp, action, p->ip, p->delta,
+ p->name);
+
+ mutex_lock(&dl->lock);
+
+ if (dl->stale || dl->aborted)
+ goto out_unlock;
+
+ xchk_dirtree_for_each_path(dl, path) {
+ ret = xchk_dirpath_is_stale(dl, path, p);
+ if (ret < 0) {
+ dl->aborted = true;
+ break;
+ }
+ if (ret == 1) {
+ dl->stale = true;
+ break;
+ }
+ }
+
+out_unlock:
+ mutex_unlock(&dl->lock);
+ return NOTIFY_DONE;
+}
+
+/* Delete all the collected path information. */
+STATIC void
+xchk_dirtree_reset(
+ void *buf)
+{
+ struct xchk_dirtree *dl = buf;
+ struct xchk_dirpath *path, *n;
+
+ ASSERT(dl->sc->ilock_flags & XFS_ILOCK_EXCL);
+
+ xchk_dirtree_for_each_path_safe(dl, path, n) {
+ list_del_init(&path->list);
+ xino_bitmap_destroy(&path->seen_inodes);
+ kfree(path);
+ }
+ dl->nr_paths = 0;
+
+ xfarray_truncate(dl->path_steps);
+ xfblob_truncate(dl->path_names);
+
+ dl->stale = false;
+}
+
+/*
+ * Load the name/pptr from the first step in this path into @dl->pptr_rec and
+ * @dl->xname.
+ */
+STATIC int
+xchk_dirtree_load_path(
+ struct xchk_dirtree *dl,
+ struct xchk_dirpath *path)
+{
+ struct xchk_dirpath_step step;
+ int error;
+
+ error = xfarray_load(dl->path_steps, path->first_step, &step);
+ if (error)
+ return error;
+
+ error = xfblob_loadname(dl->path_names, step.name_cookie, &dl->xname,
+ step.name_len);
+ if (error)
+ return error;
+
+ dl->pptr_rec = step.pptr_rec; /* struct copy */
+ return 0;
+}
+
+/*
+ * For each parent pointer of this subdir, trace a path upwards towards the
+ * root directory and record what we find. Returns 0 for success;
+ * -EFSCORRUPTED if walking the parent pointers of @sc->ip failed, -ELNRNG if a
+ * path was too deep; -ENOSR if there were too many parent pointers; or
+ * a negative errno.
+ */
+int
+xchk_dirtree_find_paths_to_root(
+ struct xchk_dirtree *dl)
+{
+ struct xfs_scrub *sc = dl->sc;
+ struct xchk_dirpath *path;
+ int error = 0;
+
+ do {
+ if (xchk_should_terminate(sc, &error))
+ return error;
+
+ xchk_dirtree_reset(dl);
+
+ /*
+ * If the extended attributes look as though they has been
+ * zapped by the inode record repair code, we cannot scan for
+ * parent pointers.
+ */
+ if (xchk_pptr_looks_zapped(sc->ip)) {
+ xchk_set_incomplete(sc);
+ return -EBUSY;
+ }
+
+ /*
+ * Create path walk contexts for each parent of the directory
+ * that is being scanned. Directories are supposed to have
+ * only one parent, but this is how we detect multiple parents.
+ */
+ error = xchk_xattr_walk(sc, sc->ip, xchk_dirtree_create_path,
+ NULL, dl);
+ if (error)
+ return error;
+
+ xchk_dirtree_for_each_path(dl, path) {
+ /* Load path components into dl->pptr/xname */
+ error = xchk_dirtree_load_path(dl, path);
+ if (error)
+ return error;
+
+ /*
+ * Try to walk up each path to the root. This enables
+ * us to find directory loops in ancestors, and the
+ * like.
+ */
+ error = xchk_dirpath_walk_upwards(dl, path);
+ if (error == -EFSCORRUPTED) {
+ /*
+ * A parent pointer of @sc->ip is bad, don't
+ * bother continuing.
+ */
+ break;
+ }
+ if (error == -ESTALE) {
+ /* This had better be an invalidation. */
+ ASSERT(dl->stale);
+ break;
+ }
+ if (error)
+ return error;
+ if (dl->aborted)
+ return 0;
+ }
+ } while (dl->stale);
+
+ return error;
+}
+
+/*
+ * Figure out what to do with the paths we tried to find. Do not call this
+ * if the scan results are stale.
+ */
+void
+xchk_dirtree_evaluate(
+ struct xchk_dirtree *dl,
+ struct xchk_dirtree_outcomes *oc)
+{
+ struct xchk_dirpath *path;
+
+ ASSERT(!dl->stale);
+
+ /* Scan the paths we have to decide what to do. */
+ memset(oc, 0, sizeof(struct xchk_dirtree_outcomes));
+ xchk_dirtree_for_each_path(dl, path) {
+ trace_xchk_dirpath_evaluate_path(dl->sc, path->path_nr,
+ path->nr_steps, path->outcome);
+
+ switch (path->outcome) {
+ case XCHK_DIRPATH_SCANNING:
+ /* shouldn't get here */
+ ASSERT(0);
+ break;
+ case XCHK_DIRPATH_DELETE:
+ /* This one is already going away. */
+ oc->bad++;
+ break;
+ case XCHK_DIRPATH_CORRUPT:
+ case XCHK_DIRPATH_LOOP:
+ /* Couldn't find the end of this path. */
+ oc->suspect++;
+ break;
+ case XCHK_DIRPATH_STALE:
+ /* shouldn't get here either */
+ ASSERT(0);
+ break;
+ case XCHK_DIRPATH_OK:
+ /* This path got all the way to the root. */
+ oc->good++;
+ break;
+ case XREP_DIRPATH_DELETING:
+ case XREP_DIRPATH_DELETED:
+ case XREP_DIRPATH_ADOPTING:
+ case XREP_DIRPATH_ADOPTED:
+ /* These should not be in progress! */
+ ASSERT(0);
+ break;
+ }
+ }
+
+ trace_xchk_dirtree_evaluate(dl, oc);
+}
+
+/* Look for directory loops. */
+int
+xchk_dirtree(
+ struct xfs_scrub *sc)
+{
+ struct xchk_dirtree_outcomes oc;
+ struct xchk_dirtree *dl = sc->buf;
+ int error;
+
+ /*
+ * Nondirectories do not point downwards to other files, so they cannot
+ * cause a cycle in the directory tree.
+ */
+ if (!S_ISDIR(VFS_I(sc->ip)->i_mode))
+ return -ENOENT;
+
+ ASSERT(xfs_has_parent(sc->mp));
+
+ /*
+ * Find the root of the directory tree. Remember which directory to
+ * scan, because the hook doesn't detach until after sc->ip gets
+ * released during teardown.
+ */
+ dl->root_ino = sc->mp->m_rootip->i_ino;
+ dl->scan_ino = sc->ip->i_ino;
+
+ trace_xchk_dirtree_start(sc->ip, sc->sm, 0);
+
+ /*
+ * Hook into the directory entry code so that we can capture updates to
+ * paths that we have already scanned. The scanner thread takes each
+ * directory's ILOCK, which means that any in-progress directory update
+ * will finish before we can scan the directory.
+ */
+ ASSERT(sc->flags & XCHK_FSGATES_DIRENTS);
+ xfs_dir_hook_setup(&dl->dhook, xchk_dirtree_live_update);
+ error = xfs_dir_hook_add(sc->mp, &dl->dhook);
+ if (error)
+ goto out;
+
+ mutex_lock(&dl->lock);
+
+ /* Trace each parent pointer's path to the root. */
+ error = xchk_dirtree_find_paths_to_root(dl);
+ if (error == -EFSCORRUPTED || error == -ELNRNG || error == -ENOSR) {
+ /*
+ * Don't bother walking the paths if the xattr structure or the
+ * parent pointers are corrupt; this scan cannot be completed
+ * without full information.
+ */
+ xchk_ino_xref_set_corrupt(sc, sc->ip->i_ino);
+ error = 0;
+ goto out_scanlock;
+ }
+ if (error == -EBUSY) {
+ /*
+ * We couldn't scan some directory's parent pointers because
+ * the attr fork looked like it had been zapped. The
+ * scan was marked incomplete, so no further error code
+ * is necessary.
+ */
+ error = 0;
+ goto out_scanlock;
+ }
+ if (error)
+ goto out_scanlock;
+ if (dl->aborted) {
+ xchk_set_incomplete(sc);
+ goto out_scanlock;
+ }
+
+ /* Assess what we found in our path evaluation. */
+ xchk_dirtree_evaluate(dl, &oc);
+ if (xchk_dirtree_parentless(dl)) {
+ if (oc.good || oc.bad || oc.suspect)
+ xchk_ino_set_corrupt(sc, sc->ip->i_ino);
+ } else {
+ if (oc.bad || oc.good + oc.suspect != 1)
+ xchk_ino_set_corrupt(sc, sc->ip->i_ino);
+ if (oc.suspect)
+ xchk_ino_xref_set_corrupt(sc, sc->ip->i_ino);
+ }
+
+out_scanlock:
+ mutex_unlock(&dl->lock);
+out:
+ trace_xchk_dirtree_done(sc->ip, sc->sm, error);
+ return error;
+}
diff --git a/fs/xfs/scrub/dirtree.h b/fs/xfs/scrub/dirtree.h
new file mode 100644
index 0000000000..1e1686365c
--- /dev/null
+++ b/fs/xfs/scrub/dirtree.h
@@ -0,0 +1,178 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * Copyright (c) 2023-2024 Oracle. All Rights Reserved.
+ * Author: Darrick J. Wong <djwong@kernel.org>
+ */
+#ifndef __XFS_SCRUB_DIRTREE_H__
+#define __XFS_SCRUB_DIRTREE_H__
+
+/*
+ * Each of these represents one parent pointer path step in a chain going
+ * up towards the directory tree root. These are stored inside an xfarray.
+ */
+struct xchk_dirpath_step {
+ /* Directory entry name associated with this parent link. */
+ xfblob_cookie name_cookie;
+ unsigned int name_len;
+
+ /* Handle of the parent directory. */
+ struct xfs_parent_rec pptr_rec;
+};
+
+enum xchk_dirpath_outcome {
+ XCHK_DIRPATH_SCANNING = 0, /* still being put together */
+ XCHK_DIRPATH_DELETE, /* delete this path */
+ XCHK_DIRPATH_CORRUPT, /* corruption detected in path */
+ XCHK_DIRPATH_LOOP, /* cycle detected further up */
+ XCHK_DIRPATH_STALE, /* path is stale */
+ XCHK_DIRPATH_OK, /* path reaches the root */
+
+ XREP_DIRPATH_DELETING, /* path is being deleted */
+ XREP_DIRPATH_DELETED, /* path has been deleted */
+ XREP_DIRPATH_ADOPTING, /* path is being adopted */
+ XREP_DIRPATH_ADOPTED, /* path has been adopted */
+};
+
+/*
+ * Each of these represents one parent pointer path out of the directory being
+ * scanned. These exist in-core, and hopefully there aren't more than a
+ * handful of them.
+ */
+struct xchk_dirpath {
+ struct list_head list;
+
+ /* Index of the first step in this path. */
+ xfarray_idx_t first_step;
+
+ /* Index of the second step in this path. */
+ xfarray_idx_t second_step;
+
+ /* Inodes seen while walking this path. */
+ struct xino_bitmap seen_inodes;
+
+ /* Number of steps in this path. */
+ unsigned int nr_steps;
+
+ /* Which path is this? */
+ unsigned int path_nr;
+
+ /* What did we conclude from following this path? */
+ enum xchk_dirpath_outcome outcome;
+};
+
+struct xchk_dirtree_outcomes {
+ /* Number of XCHK_DIRPATH_DELETE */
+ unsigned int bad;
+
+ /* Number of XCHK_DIRPATH_CORRUPT or XCHK_DIRPATH_LOOP */
+ unsigned int suspect;
+
+ /* Number of XCHK_DIRPATH_OK */
+ unsigned int good;
+
+ /* Directory needs to be added to lost+found */
+ bool needs_adoption;
+};
+
+struct xchk_dirtree {
+ struct xfs_scrub *sc;
+
+ /* Root inode that we're looking for. */
+ xfs_ino_t root_ino;
+
+ /*
+ * This is the inode that we're scanning. The live update hook can
+ * continue to be called after xchk_teardown drops sc->ip but before
+ * it calls buf_cleanup, so we keep a copy.
+ */
+ xfs_ino_t scan_ino;
+
+ /*
+ * If we start deleting redundant paths to this subdirectory, this is
+ * the inode number of the surviving parent and the dotdot entry will
+ * be set to this value. If the value is NULLFSINO, then use @root_ino
+ * as a stand-in until the orphanage can adopt the subdirectory.
+ */
+ xfs_ino_t parent_ino;
+
+ /* Scratch buffer for scanning pptr xattrs */
+ struct xfs_parent_rec pptr_rec;
+ struct xfs_da_args pptr_args;
+
+ /* Name buffer */
+ struct xfs_name xname;
+ char namebuf[MAXNAMELEN];
+
+ /* Information for reparenting this directory. */
+ struct xrep_adoption adoption;
+
+ /*
+ * Hook into directory updates so that we can receive live updates
+ * from other writer threads.
+ */
+ struct xfs_dir_hook dhook;
+
+ /* Parent pointer update arguments. */
+ struct xfs_parent_args ppargs;
+
+ /* lock for everything below here */
+ struct mutex lock;
+
+ /* buffer for the live update functions to use for dirent names */
+ struct xfs_name hook_xname;
+ unsigned char hook_namebuf[MAXNAMELEN];
+
+ /*
+ * All path steps observed during this scan. Each of the path
+ * steps for a particular pathwalk are recorded in sequential
+ * order in the xfarray. A pathwalk ends either with a step
+ * pointing to the root directory (success) or pointing to NULLFSINO
+ * (loop detected, empty dir detected, etc).
+ */
+ struct xfarray *path_steps;
+
+ /* All names observed during this scan. */
+ struct xfblob *path_names;
+
+ /* All paths being tracked by this scanner. */
+ struct list_head path_list;
+
+ /* Number of paths in path_list. */
+ unsigned int nr_paths;
+
+ /* Number of parents found by a pptr scan. */
+ unsigned int parents_found;
+
+ /* Have the path data been invalidated by a concurrent update? */
+ bool stale:1;
+
+ /* Has the scan been aborted? */
+ bool aborted:1;
+};
+
+#define xchk_dirtree_for_each_path_safe(dl, path, n) \
+ list_for_each_entry_safe((path), (n), &(dl)->path_list, list)
+
+#define xchk_dirtree_for_each_path(dl, path) \
+ list_for_each_entry((path), &(dl)->path_list, list)
+
+static inline bool
+xchk_dirtree_parentless(const struct xchk_dirtree *dl)
+{
+ struct xfs_scrub *sc = dl->sc;
+
+ if (sc->ip == sc->mp->m_rootip)
+ return true;
+ if (VFS_I(sc->ip)->i_nlink == 0)
+ return true;
+ return false;
+}
+
+int xchk_dirtree_find_paths_to_root(struct xchk_dirtree *dl);
+int xchk_dirpath_append(struct xchk_dirtree *dl, struct xfs_inode *ip,
+ struct xchk_dirpath *path, const struct xfs_name *name,
+ const struct xfs_parent_rec *pptr);
+void xchk_dirtree_evaluate(struct xchk_dirtree *dl,
+ struct xchk_dirtree_outcomes *oc);
+
+#endif /* __XFS_SCRUB_DIRTREE_H__ */
diff --git a/fs/xfs/scrub/dirtree_repair.c b/fs/xfs/scrub/dirtree_repair.c
new file mode 100644
index 0000000000..5c04e70ba9
--- /dev/null
+++ b/fs/xfs/scrub/dirtree_repair.c
@@ -0,0 +1,821 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Copyright (c) 2023-2024 Oracle. All Rights Reserved.
+ * Author: Darrick J. Wong <djwong@kernel.org>
+ */
+#include "xfs.h"
+#include "xfs_fs.h"
+#include "xfs_shared.h"
+#include "xfs_format.h"
+#include "xfs_trans_resv.h"
+#include "xfs_trans_space.h"
+#include "xfs_mount.h"
+#include "xfs_log_format.h"
+#include "xfs_trans.h"
+#include "xfs_inode.h"
+#include "xfs_icache.h"
+#include "xfs_dir2.h"
+#include "xfs_dir2_priv.h"
+#include "xfs_attr.h"
+#include "xfs_parent.h"
+#include "scrub/scrub.h"
+#include "scrub/common.h"
+#include "scrub/bitmap.h"
+#include "scrub/ino_bitmap.h"
+#include "scrub/xfile.h"
+#include "scrub/xfarray.h"
+#include "scrub/xfblob.h"
+#include "scrub/listxattr.h"
+#include "scrub/trace.h"
+#include "scrub/repair.h"
+#include "scrub/orphanage.h"
+#include "scrub/dirtree.h"
+#include "scrub/readdir.h"
+
+/*
+ * Directory Tree Structure Repairs
+ * ================================
+ *
+ * If we decide that the directory being scanned is participating in a
+ * directory loop, the only change we can make is to remove directory entries
+ * pointing down to @sc->ip. If that leaves it with no parents, the directory
+ * should be adopted by the orphanage.
+ */
+
+/* Set up to repair directory loops. */
+int
+xrep_setup_dirtree(
+ struct xfs_scrub *sc)
+{
+ return xrep_orphanage_try_create(sc);
+}
+
+/* Change the outcome of this path. */
+static inline void
+xrep_dirpath_set_outcome(
+ struct xchk_dirtree *dl,
+ struct xchk_dirpath *path,
+ enum xchk_dirpath_outcome outcome)
+{
+ trace_xrep_dirpath_set_outcome(dl->sc, path->path_nr, path->nr_steps,
+ outcome);
+
+ path->outcome = outcome;
+}
+
+/* Delete all paths. */
+STATIC void
+xrep_dirtree_delete_all_paths(
+ struct xchk_dirtree *dl,
+ struct xchk_dirtree_outcomes *oc)
+{
+ struct xchk_dirpath *path;
+
+ xchk_dirtree_for_each_path(dl, path) {
+ switch (path->outcome) {
+ case XCHK_DIRPATH_CORRUPT:
+ case XCHK_DIRPATH_LOOP:
+ oc->suspect--;
+ oc->bad++;
+ xrep_dirpath_set_outcome(dl, path, XCHK_DIRPATH_DELETE);
+ break;
+ case XCHK_DIRPATH_OK:
+ oc->good--;
+ oc->bad++;
+ xrep_dirpath_set_outcome(dl, path, XCHK_DIRPATH_DELETE);
+ break;
+ default:
+ break;
+ }
+ }
+
+ ASSERT(oc->suspect == 0);
+ ASSERT(oc->good == 0);
+}
+
+/* Since this is the surviving path, set the dotdot entry to this value. */
+STATIC void
+xrep_dirpath_retain_parent(
+ struct xchk_dirtree *dl,
+ struct xchk_dirpath *path)
+{
+ struct xchk_dirpath_step step;
+ int error;
+
+ error = xfarray_load(dl->path_steps, path->first_step, &step);
+ if (error)
+ return;
+
+ dl->parent_ino = be64_to_cpu(step.pptr_rec.p_ino);
+}
+
+/* Find the one surviving path so we know how to set dotdot. */
+STATIC void
+xrep_dirtree_find_surviving_path(
+ struct xchk_dirtree *dl,
+ struct xchk_dirtree_outcomes *oc)
+{
+ struct xchk_dirpath *path;
+ bool foundit = false;
+
+ xchk_dirtree_for_each_path(dl, path) {
+ switch (path->outcome) {
+ case XCHK_DIRPATH_CORRUPT:
+ case XCHK_DIRPATH_LOOP:
+ case XCHK_DIRPATH_OK:
+ if (!foundit) {
+ xrep_dirpath_retain_parent(dl, path);
+ foundit = true;
+ continue;
+ }
+ ASSERT(foundit == false);
+ break;
+ default:
+ break;
+ }
+ }
+
+ ASSERT(oc->suspect + oc->good == 1);
+}
+
+/* Delete all paths except for the one good one. */
+STATIC void
+xrep_dirtree_keep_one_good_path(
+ struct xchk_dirtree *dl,
+ struct xchk_dirtree_outcomes *oc)
+{
+ struct xchk_dirpath *path;
+ bool foundit = false;
+
+ xchk_dirtree_for_each_path(dl, path) {
+ switch (path->outcome) {
+ case XCHK_DIRPATH_CORRUPT:
+ case XCHK_DIRPATH_LOOP:
+ oc->suspect--;
+ oc->bad++;
+ xrep_dirpath_set_outcome(dl, path, XCHK_DIRPATH_DELETE);
+ break;
+ case XCHK_DIRPATH_OK:
+ if (!foundit) {
+ xrep_dirpath_retain_parent(dl, path);
+ foundit = true;
+ continue;
+ }
+ oc->good--;
+ oc->bad++;
+ xrep_dirpath_set_outcome(dl, path, XCHK_DIRPATH_DELETE);
+ break;
+ default:
+ break;
+ }
+ }
+
+ ASSERT(oc->suspect == 0);
+ ASSERT(oc->good < 2);
+}
+
+/* Delete all paths except for one suspect one. */
+STATIC void
+xrep_dirtree_keep_one_suspect_path(
+ struct xchk_dirtree *dl,
+ struct xchk_dirtree_outcomes *oc)
+{
+ struct xchk_dirpath *path;
+ bool foundit = false;
+
+ xchk_dirtree_for_each_path(dl, path) {
+ switch (path->outcome) {
+ case XCHK_DIRPATH_CORRUPT:
+ case XCHK_DIRPATH_LOOP:
+ if (!foundit) {
+ xrep_dirpath_retain_parent(dl, path);
+ foundit = true;
+ continue;
+ }
+ oc->suspect--;
+ oc->bad++;
+ xrep_dirpath_set_outcome(dl, path, XCHK_DIRPATH_DELETE);
+ break;
+ case XCHK_DIRPATH_OK:
+ ASSERT(0);
+ break;
+ default:
+ break;
+ }
+ }
+
+ ASSERT(oc->suspect == 1);
+ ASSERT(oc->good == 0);
+}
+
+/*
+ * Figure out what to do with the paths we tried to find. Returns -EDEADLOCK
+ * if the scan results have become stale.
+ */
+STATIC void
+xrep_dirtree_decide_fate(
+ struct xchk_dirtree *dl,
+ struct xchk_dirtree_outcomes *oc)
+{
+ xchk_dirtree_evaluate(dl, oc);
+
+ /* Parentless directories should not have any paths at all. */
+ if (xchk_dirtree_parentless(dl)) {
+ xrep_dirtree_delete_all_paths(dl, oc);
+ return;
+ }
+
+ /* One path is exactly the number of paths we want. */
+ if (oc->good + oc->suspect == 1) {
+ xrep_dirtree_find_surviving_path(dl, oc);
+ return;
+ }
+
+ /* Zero paths means we should reattach the subdir to the orphanage. */
+ if (oc->good + oc->suspect == 0) {
+ if (dl->sc->orphanage)
+ oc->needs_adoption = true;
+ return;
+ }
+
+ /*
+ * Otherwise, this subdirectory has too many parents. If there's at
+ * least one good path, keep it and delete the others.
+ */
+ if (oc->good > 0) {
+ xrep_dirtree_keep_one_good_path(dl, oc);
+ return;
+ }
+
+ /*
+ * There are no good paths and there are too many suspect paths.
+ * Keep the first suspect path and delete the rest.
+ */
+ xrep_dirtree_keep_one_suspect_path(dl, oc);
+}
+
+/*
+ * Load the first step of this path into @step and @dl->xname/pptr
+ * for later repair work.
+ */
+STATIC int
+xrep_dirtree_prep_path(
+ struct xchk_dirtree *dl,
+ struct xchk_dirpath *path,
+ struct xchk_dirpath_step *step)
+{
+ int error;
+
+ error = xfarray_load(dl->path_steps, path->first_step, step);
+ if (error)
+ return error;
+
+ error = xfblob_loadname(dl->path_names, step->name_cookie, &dl->xname,
+ step->name_len);
+ if (error)
+ return error;
+
+ dl->pptr_rec = step->pptr_rec; /* struct copy */
+ return 0;
+}
+
+/* Delete the VFS dentry for a removed child. */
+STATIC int
+xrep_dirtree_purge_dentry(
+ struct xchk_dirtree *dl,
+ struct xfs_inode *dp,
+ const struct xfs_name *name)
+{
+ struct qstr qname = QSTR_INIT(name->name, name->len);
+ struct dentry *parent_dentry, *child_dentry;
+ int error = 0;
+
+ /*
+ * Find the dentry for the parent directory. If there isn't one, we're
+ * done. Caller already holds i_rwsem for parent and child.
+ */
+ parent_dentry = d_find_alias(VFS_I(dp));
+ if (!parent_dentry)
+ return 0;
+
+ /* The VFS thinks the parent is a directory, right? */
+ if (!d_is_dir(parent_dentry)) {
+ ASSERT(d_is_dir(parent_dentry));
+ error = -EFSCORRUPTED;
+ goto out_dput_parent;
+ }
+
+ /*
+ * Try to find the dirent pointing to the child. If there isn't one,
+ * we're done.
+ */
+ qname.hash = full_name_hash(parent_dentry, name->name, name->len);
+ child_dentry = d_lookup(parent_dentry, &qname);
+ if (!child_dentry) {
+ error = 0;
+ goto out_dput_parent;
+ }
+
+ trace_xrep_dirtree_delete_child(dp->i_mount, child_dentry);
+
+ /* Child is not a directory? We're screwed. */
+ if (!d_is_dir(child_dentry)) {
+ ASSERT(d_is_dir(child_dentry));
+ error = -EFSCORRUPTED;
+ goto out_dput_child;
+ }
+
+ /* Replace the child dentry with a negative one. */
+ d_delete(child_dentry);
+
+out_dput_child:
+ dput(child_dentry);
+out_dput_parent:
+ dput(parent_dentry);
+ return error;
+}
+
+/*
+ * Prepare to delete a link by taking the IOLOCK of the parent and the child
+ * (scrub target). Caller must hold IOLOCK_EXCL on @sc->ip. Returns 0 if we
+ * took both locks, or a negative errno if we couldn't lock the parent in time.
+ */
+static inline int
+xrep_dirtree_unlink_iolock(
+ struct xfs_scrub *sc,
+ struct xfs_inode *dp)
+{
+ int error;
+
+ ASSERT(sc->ilock_flags & XFS_IOLOCK_EXCL);
+
+ if (xfs_ilock_nowait(dp, XFS_IOLOCK_EXCL))
+ return 0;
+
+ xchk_iunlock(sc, XFS_IOLOCK_EXCL);
+ do {
+ xfs_ilock(dp, XFS_IOLOCK_EXCL);
+ if (xchk_ilock_nowait(sc, XFS_IOLOCK_EXCL))
+ break;
+ xfs_iunlock(dp, XFS_IOLOCK_EXCL);
+
+ if (xchk_should_terminate(sc, &error)) {
+ xchk_ilock(sc, XFS_IOLOCK_EXCL);
+ return error;
+ }
+
+ delay(1);
+ } while (1);
+
+ return 0;
+}
+
+/*
+ * Remove a link from the directory tree and update the dcache. Returns
+ * -ESTALE if the scan data are now out of date.
+ */
+STATIC int
+xrep_dirtree_unlink(
+ struct xchk_dirtree *dl,
+ struct xfs_inode *dp,
+ struct xchk_dirpath *path,
+ struct xchk_dirpath_step *step)
+{
+ struct xfs_scrub *sc = dl->sc;
+ struct xfs_mount *mp = sc->mp;
+ xfs_ino_t dotdot_ino;
+ xfs_ino_t parent_ino = dl->parent_ino;
+ unsigned int resblks;
+ int dontcare;
+ int error;
+
+ /* Take IOLOCK_EXCL of the parent and child. */
+ error = xrep_dirtree_unlink_iolock(sc, dp);
+ if (error)
+ return error;
+
+ /*
+ * Create the transaction that we need to sever the path. Ignore
+ * EDQUOT and ENOSPC being returned via nospace_error because the
+ * directory code can handle a reservationless update.
+ */
+ resblks = xfs_remove_space_res(mp, step->name_len);
+ error = xfs_trans_alloc_dir(dp, &M_RES(mp)->tr_remove, sc->ip,
+ &resblks, &sc->tp, &dontcare);
+ if (error)
+ goto out_iolock;
+
+ /*
+ * Cancel if someone invalidate the paths while we were trying to get
+ * the ILOCK.
+ */
+ mutex_lock(&dl->lock);
+ if (dl->stale) {
+ mutex_unlock(&dl->lock);
+ error = -ESTALE;
+ goto out_trans_cancel;
+ }
+ xrep_dirpath_set_outcome(dl, path, XREP_DIRPATH_DELETING);
+ mutex_unlock(&dl->lock);
+
+ trace_xrep_dirtree_delete_path(dl->sc, sc->ip, path->path_nr,
+ &dl->xname, &dl->pptr_rec);
+
+ /*
+ * Decide if we need to reset the dotdot entry. Rules:
+ *
+ * - If there's a surviving parent, we want dotdot to point there.
+ * - If we don't have any surviving parents, then point dotdot at the
+ * root dir.
+ * - If dotdot is already set to the value we want, pass in NULLFSINO
+ * for no change necessary.
+ *
+ * Do this /before/ we dirty anything, in case the dotdot lookup
+ * fails.
+ */
+ error = xchk_dir_lookup(sc, sc->ip, &xfs_name_dotdot, &dotdot_ino);
+ if (error)
+ goto out_trans_cancel;
+ if (parent_ino == NULLFSINO)
+ parent_ino = dl->root_ino;
+ if (dotdot_ino == parent_ino)
+ parent_ino = NULLFSINO;
+
+ /* Drop the link from sc->ip's dotdot entry. */
+ error = xfs_droplink(sc->tp, dp);
+ if (error)
+ goto out_trans_cancel;
+
+ /* Reset the dotdot entry to a surviving parent. */
+ if (parent_ino != NULLFSINO) {
+ error = xfs_dir_replace(sc->tp, sc->ip, &xfs_name_dotdot,
+ parent_ino, 0);
+ if (error)
+ goto out_trans_cancel;
+ }
+
+ /* Drop the link from dp to sc->ip. */
+ error = xfs_droplink(sc->tp, sc->ip);
+ if (error)
+ goto out_trans_cancel;
+
+ error = xfs_dir_removename(sc->tp, dp, &dl->xname, sc->ip->i_ino,
+ resblks);
+ if (error) {
+ ASSERT(error != -ENOENT);
+ goto out_trans_cancel;
+ }
+
+ if (xfs_has_parent(sc->mp)) {
+ error = xfs_parent_removename(sc->tp, &dl->ppargs, dp,
+ &dl->xname, sc->ip);
+ if (error)
+ goto out_trans_cancel;
+ }
+
+ /*
+ * Notify dirent hooks that we removed the bad link, invalidate the
+ * dcache, and commit the repair.
+ */
+ xfs_dir_update_hook(dp, sc->ip, -1, &dl->xname);
+ error = xrep_dirtree_purge_dentry(dl, dp, &dl->xname);
+ if (error)
+ goto out_trans_cancel;
+
+ error = xrep_trans_commit(sc);
+ goto out_ilock;
+
+out_trans_cancel:
+ xchk_trans_cancel(sc);
+out_ilock:
+ xfs_iunlock(sc->ip, XFS_ILOCK_EXCL);
+ xfs_iunlock(dp, XFS_ILOCK_EXCL);
+out_iolock:
+ xfs_iunlock(dp, XFS_IOLOCK_EXCL);
+ return error;
+}
+
+/*
+ * Delete a directory entry that points to this directory. Returns -ESTALE
+ * if the scan data are now out of date.
+ */
+STATIC int
+xrep_dirtree_delete_path(
+ struct xchk_dirtree *dl,
+ struct xchk_dirpath *path)
+{
+ struct xchk_dirpath_step step;
+ struct xfs_scrub *sc = dl->sc;
+ struct xfs_inode *dp;
+ int error;
+
+ /*
+ * Load the parent pointer and directory inode for this path, then
+ * drop the scan lock, the ILOCK, and the transaction so that
+ * _delete_path can reserve the proper transaction. This sets up
+ * @dl->xname for the deletion.
+ */
+ error = xrep_dirtree_prep_path(dl, path, &step);
+ if (error)
+ return error;
+
+ error = xchk_iget(sc, be64_to_cpu(step.pptr_rec.p_ino), &dp);
+ if (error)
+ return error;
+
+ mutex_unlock(&dl->lock);
+ xchk_trans_cancel(sc);
+ xchk_iunlock(sc, XFS_ILOCK_EXCL);
+
+ /* Delete the directory link and release the parent. */
+ error = xrep_dirtree_unlink(dl, dp, path, &step);
+ xchk_irele(sc, dp);
+
+ /*
+ * Retake all the resources we had at the beginning even if the repair
+ * failed or the scan data are now stale. This keeps things simple for
+ * the caller.
+ */
+ xchk_trans_alloc_empty(sc);
+ xchk_ilock(sc, XFS_ILOCK_EXCL);
+ mutex_lock(&dl->lock);
+
+ if (!error && dl->stale)
+ error = -ESTALE;
+ return error;
+}
+
+/* Add a new path to represent our in-progress adoption. */
+STATIC int
+xrep_dirtree_create_adoption_path(
+ struct xchk_dirtree *dl)
+{
+ struct xfs_scrub *sc = dl->sc;
+ struct xchk_dirpath *path;
+ int error;
+
+ /*
+ * We should have capped the number of paths at XFS_MAXLINK-1 in the
+ * scanner.
+ */
+ if (dl->nr_paths > XFS_MAXLINK) {
+ ASSERT(dl->nr_paths <= XFS_MAXLINK);
+ return -EFSCORRUPTED;
+ }
+
+ /*
+ * Create a new xchk_path structure to remember this parent pointer
+ * and record the first name step.
+ */
+ path = kmalloc(sizeof(struct xchk_dirpath), XCHK_GFP_FLAGS);
+ if (!path)
+ return -ENOMEM;
+
+ INIT_LIST_HEAD(&path->list);
+ xino_bitmap_init(&path->seen_inodes);
+ path->nr_steps = 0;
+ path->outcome = XREP_DIRPATH_ADOPTING;
+
+ /*
+ * Record the new link that we just created in the orphanage. Because
+ * adoption is the last repair that we perform, we don't bother filling
+ * in the path all the way back to the root.
+ */
+ xfs_inode_to_parent_rec(&dl->pptr_rec, sc->orphanage);
+
+ error = xino_bitmap_set(&path->seen_inodes, sc->orphanage->i_ino);
+ if (error)
+ goto out_path;
+
+ trace_xrep_dirtree_create_adoption(sc, sc->ip, dl->nr_paths,
+ &dl->xname, &dl->pptr_rec);
+
+ error = xchk_dirpath_append(dl, sc->ip, path, &dl->xname,
+ &dl->pptr_rec);
+ if (error)
+ goto out_path;
+
+ path->first_step = xfarray_length(dl->path_steps) - 1;
+ path->second_step = XFARRAY_NULLIDX;
+ path->path_nr = dl->nr_paths;
+
+ list_add_tail(&path->list, &dl->path_list);
+ dl->nr_paths++;
+ return 0;
+
+out_path:
+ kfree(path);
+ return error;
+}
+
+/*
+ * Prepare to move a file to the orphanage by taking the IOLOCK of the
+ * orphanage and the child (scrub target). Caller must hold IOLOCK_EXCL on
+ * @sc->ip. Returns 0 if we took both locks, or a negative errno if we
+ * couldn't lock the orphanage in time.
+ */
+static inline int
+xrep_dirtree_adopt_iolock(
+ struct xfs_scrub *sc)
+{
+ int error;
+
+ ASSERT(sc->ilock_flags & XFS_IOLOCK_EXCL);
+
+ if (xrep_orphanage_ilock_nowait(sc, XFS_IOLOCK_EXCL))
+ return 0;
+
+ xchk_iunlock(sc, XFS_IOLOCK_EXCL);
+ do {
+ xrep_orphanage_ilock(sc, XFS_IOLOCK_EXCL);
+ if (xchk_ilock_nowait(sc, XFS_IOLOCK_EXCL))
+ break;
+ xrep_orphanage_iunlock(sc, XFS_IOLOCK_EXCL);
+
+ if (xchk_should_terminate(sc, &error)) {
+ xchk_ilock(sc, XFS_IOLOCK_EXCL);
+ return error;
+ }
+
+ delay(1);
+ } while (1);
+
+ return 0;
+}
+
+/*
+ * Reattach this orphaned directory to the orphanage. Do not call this with
+ * any resources held. Returns -ESTALE if the scan data have become out of
+ * date.
+ */
+STATIC int
+xrep_dirtree_adopt(
+ struct xchk_dirtree *dl)
+{
+ struct xfs_scrub *sc = dl->sc;
+ int error;
+
+ /* Take the IOLOCK of the orphanage and the scrub target. */
+ error = xrep_dirtree_adopt_iolock(sc);
+ if (error)
+ return error;
+
+ /*
+ * Set up for an adoption. The directory tree fixer runs after the
+ * link counts have been corrected. Therefore, we must bump the
+ * child's link count since there will be no further opportunity to fix
+ * errors.
+ */
+ error = xrep_adoption_trans_alloc(sc, &dl->adoption);
+ if (error)
+ goto out_iolock;
+ dl->adoption.bump_child_nlink = true;
+
+ /* Figure out what name we're going to use here. */
+ error = xrep_adoption_compute_name(&dl->adoption, &dl->xname);
+ if (error)
+ goto out_trans;
+
+ /*
+ * Now that we have a proposed name for the orphanage entry, create
+ * a faux path so that the live update hook will see it.
+ */
+ mutex_lock(&dl->lock);
+ if (dl->stale) {
+ mutex_unlock(&dl->lock);
+ error = -ESTALE;
+ goto out_trans;
+ }
+ error = xrep_dirtree_create_adoption_path(dl);
+ mutex_unlock(&dl->lock);
+ if (error)
+ goto out_trans;
+
+ /* Reparent the directory. */
+ error = xrep_adoption_move(&dl->adoption);
+ if (error)
+ goto out_trans;
+
+ /*
+ * Commit the name and release all inode locks except for the scrub
+ * target's IOLOCK.
+ */
+ error = xrep_trans_commit(sc);
+ goto out_ilock;
+
+out_trans:
+ xchk_trans_cancel(sc);
+out_ilock:
+ xchk_iunlock(sc, XFS_ILOCK_EXCL);
+ xrep_orphanage_iunlock(sc, XFS_ILOCK_EXCL);
+out_iolock:
+ xrep_orphanage_iunlock(sc, XFS_IOLOCK_EXCL);
+ return error;
+}
+
+/*
+ * This newly orphaned directory needs to be adopted by the orphanage.
+ * Make this happen.
+ */
+STATIC int
+xrep_dirtree_move_to_orphanage(
+ struct xchk_dirtree *dl)
+{
+ struct xfs_scrub *sc = dl->sc;
+ int error;
+
+ /*
+ * Start by dropping all the resources that we hold so that we can grab
+ * all the resources that we need for the adoption.
+ */
+ mutex_unlock(&dl->lock);
+ xchk_trans_cancel(sc);
+ xchk_iunlock(sc, XFS_ILOCK_EXCL);
+
+ /* Perform the adoption. */
+ error = xrep_dirtree_adopt(dl);
+
+ /*
+ * Retake all the resources we had at the beginning even if the repair
+ * failed or the scan data are now stale. This keeps things simple for
+ * the caller.
+ */
+ xchk_trans_alloc_empty(sc);
+ xchk_ilock(sc, XFS_ILOCK_EXCL);
+ mutex_lock(&dl->lock);
+
+ if (!error && dl->stale)
+ error = -ESTALE;
+ return error;
+}
+
+/*
+ * Try to fix all the problems. Returns -ESTALE if the scan data have become
+ * out of date.
+ */
+STATIC int
+xrep_dirtree_fix_problems(
+ struct xchk_dirtree *dl,
+ struct xchk_dirtree_outcomes *oc)
+{
+ struct xchk_dirpath *path;
+ int error;
+
+ /* Delete all the paths we don't want. */
+ xchk_dirtree_for_each_path(dl, path) {
+ if (path->outcome != XCHK_DIRPATH_DELETE)
+ continue;
+
+ error = xrep_dirtree_delete_path(dl, path);
+ if (error)
+ return error;
+ }
+
+ /* Reparent this directory to the orphanage. */
+ if (oc->needs_adoption) {
+ if (xrep_orphanage_can_adopt(dl->sc))
+ return xrep_dirtree_move_to_orphanage(dl);
+ return -EFSCORRUPTED;
+ }
+
+ return 0;
+}
+
+/* Fix directory loops involving this directory. */
+int
+xrep_dirtree(
+ struct xfs_scrub *sc)
+{
+ struct xchk_dirtree *dl = sc->buf;
+ struct xchk_dirtree_outcomes oc;
+ int error;
+
+ /*
+ * Prepare to fix the directory tree by retaking the scan lock. The
+ * order of resource acquisition is still IOLOCK -> transaction ->
+ * ILOCK -> scan lock.
+ */
+ mutex_lock(&dl->lock);
+ do {
+ /*
+ * Decide what we're going to do, then do it. An -ESTALE
+ * return here means the scan results are invalid and we have
+ * to walk again.
+ */
+ if (!dl->stale) {
+ xrep_dirtree_decide_fate(dl, &oc);
+
+ trace_xrep_dirtree_decided_fate(dl, &oc);
+
+ error = xrep_dirtree_fix_problems(dl, &oc);
+ if (!error || error != -ESTALE)
+ break;
+ }
+ error = xchk_dirtree_find_paths_to_root(dl);
+ if (error == -ELNRNG || error == -ENOSR)
+ error = -EFSCORRUPTED;
+ } while (!error);
+ mutex_unlock(&dl->lock);
+
+ return error;
+}
diff --git a/fs/xfs/scrub/findparent.c b/fs/xfs/scrub/findparent.c
new file mode 100644
index 0000000000..01766041ba
--- /dev/null
+++ b/fs/xfs/scrub/findparent.c
@@ -0,0 +1,454 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Copyright (c) 2020-2024 Oracle. All Rights Reserved.
+ * Author: Darrick J. Wong <djwong@kernel.org>
+ */
+#include "xfs.h"
+#include "xfs_fs.h"
+#include "xfs_shared.h"
+#include "xfs_format.h"
+#include "xfs_trans_resv.h"
+#include "xfs_mount.h"
+#include "xfs_defer.h"
+#include "xfs_bit.h"
+#include "xfs_log_format.h"
+#include "xfs_trans.h"
+#include "xfs_sb.h"
+#include "xfs_inode.h"
+#include "xfs_icache.h"
+#include "xfs_da_format.h"
+#include "xfs_da_btree.h"
+#include "xfs_dir2.h"
+#include "xfs_bmap_btree.h"
+#include "xfs_dir2_priv.h"
+#include "xfs_trans_space.h"
+#include "xfs_health.h"
+#include "xfs_exchmaps.h"
+#include "xfs_parent.h"
+#include "scrub/xfs_scrub.h"
+#include "scrub/scrub.h"
+#include "scrub/common.h"
+#include "scrub/trace.h"
+#include "scrub/repair.h"
+#include "scrub/iscan.h"
+#include "scrub/findparent.h"
+#include "scrub/readdir.h"
+#include "scrub/tempfile.h"
+#include "scrub/listxattr.h"
+
+/*
+ * Finding the Parent of a Directory
+ * =================================
+ *
+ * Directories have parent pointers, in the sense that each directory contains
+ * a dotdot entry that points to the single allowed parent. The brute force
+ * way to find the parent of a given directory is to scan every directory in
+ * the filesystem looking for a child dirent that references this directory.
+ *
+ * This module wraps the process of scanning the directory tree. It requires
+ * that @sc->ip is the directory whose parent we want to find, and that the
+ * caller hold only the IOLOCK on that directory. The scan itself needs to
+ * take the ILOCK of each directory visited.
+ *
+ * Because we cannot hold @sc->ip's ILOCK during a scan of the whole fs, it is
+ * necessary to use dirent hook to update the parent scan results. Callers
+ * must not read the scan results without re-taking @sc->ip's ILOCK.
+ *
+ * There are a few shortcuts that we can take to avoid scanning the entire
+ * filesystem, such as noticing directory tree roots and querying the dentry
+ * cache for parent information.
+ */
+
+struct xrep_findparent_info {
+ /* The directory currently being scanned. */
+ struct xfs_inode *dp;
+
+ /*
+ * Scrub context. We're looking for a @dp containing a directory
+ * entry pointing to sc->ip->i_ino.
+ */
+ struct xfs_scrub *sc;
+
+ /* Optional scan information for a xrep_findparent_scan call. */
+ struct xrep_parent_scan_info *parent_scan;
+
+ /*
+ * Parent that we've found for sc->ip. If we're scanning the entire
+ * directory tree, we need this to ensure that we only find /one/
+ * parent directory.
+ */
+ xfs_ino_t found_parent;
+
+ /*
+ * This is set to true if @found_parent was not observed directly from
+ * the directory scan but by noticing a change in dotdot entries after
+ * cycling the sc->ip IOLOCK.
+ */
+ bool parent_tentative;
+};
+
+/*
+ * If this directory entry points to the scrub target inode, then the directory
+ * we're scanning is the parent of the scrub target inode.
+ */
+STATIC int
+xrep_findparent_dirent(
+ struct xfs_scrub *sc,
+ struct xfs_inode *dp,
+ xfs_dir2_dataptr_t dapos,
+ const struct xfs_name *name,
+ xfs_ino_t ino,
+ void *priv)
+{
+ struct xrep_findparent_info *fpi = priv;
+ int error = 0;
+
+ if (xchk_should_terminate(fpi->sc, &error))
+ return error;
+
+ if (ino != fpi->sc->ip->i_ino)
+ return 0;
+
+ /* Ignore garbage directory entry names. */
+ if (name->len == 0 || !xfs_dir2_namecheck(name->name, name->len))
+ return -EFSCORRUPTED;
+
+ /*
+ * Ignore dotdot and dot entries -- we're looking for parent -> child
+ * links only.
+ */
+ if (name->name[0] == '.' && (name->len == 1 ||
+ (name->len == 2 && name->name[1] == '.')))
+ return 0;
+
+ /* Uhoh, more than one parent for a dir? */
+ if (fpi->found_parent != NULLFSINO &&
+ !(fpi->parent_tentative && fpi->found_parent == fpi->dp->i_ino)) {
+ trace_xrep_findparent_dirent(fpi->sc->ip, 0);
+ return -EFSCORRUPTED;
+ }
+
+ /* We found a potential parent; remember this. */
+ trace_xrep_findparent_dirent(fpi->sc->ip, fpi->dp->i_ino);
+ fpi->found_parent = fpi->dp->i_ino;
+ fpi->parent_tentative = false;
+
+ if (fpi->parent_scan)
+ xrep_findparent_scan_found(fpi->parent_scan, fpi->dp->i_ino);
+
+ return 0;
+}
+
+/*
+ * If this is a directory, walk the dirents looking for any that point to the
+ * scrub target inode.
+ */
+STATIC int
+xrep_findparent_walk_directory(
+ struct xrep_findparent_info *fpi)
+{
+ struct xfs_scrub *sc = fpi->sc;
+ struct xfs_inode *dp = fpi->dp;
+ unsigned int lock_mode;
+ int error = 0;
+
+ /*
+ * The inode being scanned cannot be its own parent, nor can any
+ * temporary directory we created to stage this repair.
+ */
+ if (dp == sc->ip || dp == sc->tempip)
+ return 0;
+
+ /*
+ * Similarly, temporary files created to stage a repair cannot be the
+ * parent of this inode.
+ */
+ if (xrep_is_tempfile(dp))
+ return 0;
+
+ /*
+ * Scan the directory to see if there it contains an entry pointing to
+ * the directory that we are repairing.
+ */
+ lock_mode = xfs_ilock_data_map_shared(dp);
+
+ /*
+ * If this directory is known to be sick, we cannot scan it reliably
+ * and must abort.
+ */
+ if (xfs_inode_has_sickness(dp, XFS_SICK_INO_CORE |
+ XFS_SICK_INO_BMBTD |
+ XFS_SICK_INO_DIR)) {
+ error = -EFSCORRUPTED;
+ goto out_unlock;
+ }
+
+ /*
+ * We cannot complete our parent pointer scan if a directory looks as
+ * though it has been zapped by the inode record repair code.
+ */
+ if (xchk_dir_looks_zapped(dp)) {
+ error = -EBUSY;
+ goto out_unlock;
+ }
+
+ error = xchk_dir_walk(sc, dp, xrep_findparent_dirent, fpi);
+ if (error)
+ goto out_unlock;
+
+out_unlock:
+ xfs_iunlock(dp, lock_mode);
+ return error;
+}
+
+/*
+ * Update this directory's dotdot pointer based on ongoing dirent updates.
+ */
+STATIC int
+xrep_findparent_live_update(
+ struct notifier_block *nb,
+ unsigned long action,
+ void *data)
+{
+ struct xfs_dir_update_params *p = data;
+ struct xrep_parent_scan_info *pscan;
+ struct xfs_scrub *sc;
+
+ pscan = container_of(nb, struct xrep_parent_scan_info,
+ dhook.dirent_hook.nb);
+ sc = pscan->sc;
+
+ /*
+ * If @p->ip is the subdirectory that we're interested in and we've
+ * already scanned @p->dp, update the dotdot target inumber to the
+ * parent inode.
+ */
+ if (p->ip->i_ino == sc->ip->i_ino &&
+ xchk_iscan_want_live_update(&pscan->iscan, p->dp->i_ino)) {
+ if (p->delta > 0) {
+ xrep_findparent_scan_found(pscan, p->dp->i_ino);
+ } else {
+ xrep_findparent_scan_found(pscan, NULLFSINO);
+ }
+ }
+
+ return NOTIFY_DONE;
+}
+
+/*
+ * Set up a scan to find the parent of a directory. The provided dirent hook
+ * will be called when there is a dotdot update for the inode being repaired.
+ */
+int
+__xrep_findparent_scan_start(
+ struct xfs_scrub *sc,
+ struct xrep_parent_scan_info *pscan,
+ notifier_fn_t custom_fn)
+{
+ int error;
+
+ if (!(sc->flags & XCHK_FSGATES_DIRENTS)) {
+ ASSERT(sc->flags & XCHK_FSGATES_DIRENTS);
+ return -EINVAL;
+ }
+
+ pscan->sc = sc;
+ pscan->parent_ino = NULLFSINO;
+
+ mutex_init(&pscan->lock);
+
+ xchk_iscan_start(sc, 30000, 100, &pscan->iscan);
+
+ /*
+ * Hook into the dirent update code. The hook only operates on inodes
+ * that were already scanned, and the scanner thread takes each inode's
+ * ILOCK, which means that any in-progress inode updates will finish
+ * before we can scan the inode.
+ */
+ if (custom_fn)
+ xfs_dir_hook_setup(&pscan->dhook, custom_fn);
+ else
+ xfs_dir_hook_setup(&pscan->dhook, xrep_findparent_live_update);
+ error = xfs_dir_hook_add(sc->mp, &pscan->dhook);
+ if (error)
+ goto out_iscan;
+
+ return 0;
+out_iscan:
+ xchk_iscan_teardown(&pscan->iscan);
+ mutex_destroy(&pscan->lock);
+ return error;
+}
+
+/*
+ * Scan the entire filesystem looking for a parent inode for the inode being
+ * scrubbed. @sc->ip must not be the root of a directory tree. Callers must
+ * not hold a dirty transaction or any lock that would interfere with taking
+ * an ILOCK.
+ *
+ * Returns 0 with @pscan->parent_ino set to the parent that we found.
+ * Returns 0 with @pscan->parent_ino set to NULLFSINO if we found no parents.
+ * Returns the usual negative errno if something else happened.
+ */
+int
+xrep_findparent_scan(
+ struct xrep_parent_scan_info *pscan)
+{
+ struct xrep_findparent_info fpi = {
+ .sc = pscan->sc,
+ .found_parent = NULLFSINO,
+ .parent_scan = pscan,
+ };
+ struct xfs_scrub *sc = pscan->sc;
+ int ret;
+
+ ASSERT(S_ISDIR(VFS_IC(sc->ip)->i_mode));
+
+ while ((ret = xchk_iscan_iter(&pscan->iscan, &fpi.dp)) == 1) {
+ if (S_ISDIR(VFS_I(fpi.dp)->i_mode))
+ ret = xrep_findparent_walk_directory(&fpi);
+ else
+ ret = 0;
+ xchk_iscan_mark_visited(&pscan->iscan, fpi.dp);
+ xchk_irele(sc, fpi.dp);
+ if (ret)
+ break;
+
+ if (xchk_should_terminate(sc, &ret))
+ break;
+ }
+ xchk_iscan_iter_finish(&pscan->iscan);
+
+ return ret;
+}
+
+/* Tear down a parent scan. */
+void
+xrep_findparent_scan_teardown(
+ struct xrep_parent_scan_info *pscan)
+{
+ xfs_dir_hook_del(pscan->sc->mp, &pscan->dhook);
+ xchk_iscan_teardown(&pscan->iscan);
+ mutex_destroy(&pscan->lock);
+}
+
+/* Finish a parent scan early. */
+void
+xrep_findparent_scan_finish_early(
+ struct xrep_parent_scan_info *pscan,
+ xfs_ino_t ino)
+{
+ xrep_findparent_scan_found(pscan, ino);
+ xchk_iscan_finish_early(&pscan->iscan);
+}
+
+/*
+ * Confirm that the directory @parent_ino actually contains a directory entry
+ * pointing to the child @sc->ip->ino. This function returns one of several
+ * ways:
+ *
+ * Returns 0 with @parent_ino unchanged if the parent was confirmed.
+ * Returns 0 with @parent_ino set to NULLFSINO if the parent was not valid.
+ * Returns the usual negative errno if something else happened.
+ */
+int
+xrep_findparent_confirm(
+ struct xfs_scrub *sc,
+ xfs_ino_t *parent_ino)
+{
+ struct xrep_findparent_info fpi = {
+ .sc = sc,
+ .found_parent = NULLFSINO,
+ };
+ int error;
+
+ /*
+ * The root directory always points to itself. Unlinked dirs can point
+ * anywhere, so we point them at the root dir too.
+ */
+ if (sc->ip == sc->mp->m_rootip || VFS_I(sc->ip)->i_nlink == 0) {
+ *parent_ino = sc->mp->m_sb.sb_rootino;
+ return 0;
+ }
+
+ /* Reject garbage parent inode numbers and self-referential parents. */
+ if (*parent_ino == NULLFSINO)
+ return 0;
+ if (!xfs_verify_dir_ino(sc->mp, *parent_ino) ||
+ *parent_ino == sc->ip->i_ino) {
+ *parent_ino = NULLFSINO;
+ return 0;
+ }
+
+ error = xchk_iget(sc, *parent_ino, &fpi.dp);
+ if (error)
+ return error;
+
+ if (!S_ISDIR(VFS_I(fpi.dp)->i_mode)) {
+ *parent_ino = NULLFSINO;
+ goto out_rele;
+ }
+
+ error = xrep_findparent_walk_directory(&fpi);
+ if (error)
+ goto out_rele;
+
+ *parent_ino = fpi.found_parent;
+out_rele:
+ xchk_irele(sc, fpi.dp);
+ return error;
+}
+
+/*
+ * If we're the root of a directory tree, we are our own parent. If we're an
+ * unlinked directory, the parent /won't/ have a link to us. Set the parent
+ * directory to the root for both cases. Returns NULLFSINO if we don't know
+ * what to do.
+ */
+xfs_ino_t
+xrep_findparent_self_reference(
+ struct xfs_scrub *sc)
+{
+ if (sc->ip->i_ino == sc->mp->m_sb.sb_rootino)
+ return sc->mp->m_sb.sb_rootino;
+
+ if (VFS_I(sc->ip)->i_nlink == 0)
+ return sc->mp->m_sb.sb_rootino;
+
+ return NULLFSINO;
+}
+
+/* Check the dentry cache to see if knows of a parent for the scrub target. */
+xfs_ino_t
+xrep_findparent_from_dcache(
+ struct xfs_scrub *sc)
+{
+ struct inode *pip = NULL;
+ struct dentry *dentry, *parent;
+ xfs_ino_t ret = NULLFSINO;
+
+ dentry = d_find_alias(VFS_I(sc->ip));
+ if (!dentry)
+ goto out;
+
+ parent = dget_parent(dentry);
+ if (!parent)
+ goto out_dput;
+
+ ASSERT(parent->d_sb == sc->ip->i_mount->m_super);
+
+ pip = igrab(d_inode(parent));
+ dput(parent);
+
+ if (S_ISDIR(pip->i_mode)) {
+ trace_xrep_findparent_from_dcache(sc->ip, XFS_I(pip)->i_ino);
+ ret = XFS_I(pip)->i_ino;
+ }
+
+ xchk_irele(sc, XFS_I(pip));
+
+out_dput:
+ dput(dentry);
+out:
+ return ret;
+}
diff --git a/fs/xfs/scrub/findparent.h b/fs/xfs/scrub/findparent.h
new file mode 100644
index 0000000000..d998c7a881
--- /dev/null
+++ b/fs/xfs/scrub/findparent.h
@@ -0,0 +1,56 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * Copyright (c) 2020-2024 Oracle. All Rights Reserved.
+ * Author: Darrick J. Wong <djwong@kernel.org>
+ */
+#ifndef __XFS_SCRUB_FINDPARENT_H__
+#define __XFS_SCRUB_FINDPARENT_H__
+
+struct xrep_parent_scan_info {
+ struct xfs_scrub *sc;
+
+ /* Inode scan cursor. */
+ struct xchk_iscan iscan;
+
+ /* Hook to capture directory entry updates. */
+ struct xfs_dir_hook dhook;
+
+ /* Lock protecting parent_ino. */
+ struct mutex lock;
+
+ /* Parent inode that we've found. */
+ xfs_ino_t parent_ino;
+
+ bool lookup_parent;
+};
+
+int __xrep_findparent_scan_start(struct xfs_scrub *sc,
+ struct xrep_parent_scan_info *pscan,
+ notifier_fn_t custom_fn);
+static inline int xrep_findparent_scan_start(struct xfs_scrub *sc,
+ struct xrep_parent_scan_info *pscan)
+{
+ return __xrep_findparent_scan_start(sc, pscan, NULL);
+}
+int xrep_findparent_scan(struct xrep_parent_scan_info *pscan);
+void xrep_findparent_scan_teardown(struct xrep_parent_scan_info *pscan);
+
+static inline void
+xrep_findparent_scan_found(
+ struct xrep_parent_scan_info *pscan,
+ xfs_ino_t ino)
+{
+ mutex_lock(&pscan->lock);
+ pscan->parent_ino = ino;
+ mutex_unlock(&pscan->lock);
+}
+
+void xrep_findparent_scan_finish_early(struct xrep_parent_scan_info *pscan,
+ xfs_ino_t ino);
+
+int xrep_findparent_confirm(struct xfs_scrub *sc, xfs_ino_t *parent_ino);
+
+xfs_ino_t xrep_findparent_self_reference(struct xfs_scrub *sc);
+xfs_ino_t xrep_findparent_from_dcache(struct xfs_scrub *sc);
+
+#endif /* __XFS_SCRUB_FINDPARENT_H__ */
diff --git a/fs/xfs/scrub/fscounters.c b/fs/xfs/scrub/fscounters.c
index d310737c88..1d3e983469 100644
--- a/fs/xfs/scrub/fscounters.c
+++ b/fs/xfs/scrub/fscounters.c
@@ -85,7 +85,7 @@ xchk_fscount_warmup(
continue;
/* Lock both AG headers. */
- error = xfs_ialloc_read_agi(pag, sc->tp, &agi_bp);
+ error = xfs_ialloc_read_agi(pag, sc->tp, 0, &agi_bp);
if (error)
break;
error = xfs_alloc_read_agf(pag, sc->tp, 0, &agf_bp);
@@ -412,10 +412,11 @@ xchk_fscount_count_frextents(
int error;
fsc->frextents = 0;
+ fsc->frextents_delayed = 0;
if (!xfs_has_realtime(mp))
return 0;
- xfs_ilock(sc->mp->m_rbmip, XFS_ILOCK_SHARED | XFS_ILOCK_RTBITMAP);
+ xfs_rtbitmap_lock_shared(sc->mp, XFS_RBMLOCK_BITMAP);
error = xfs_rtalloc_query_all(sc->mp, sc->tp,
xchk_fscount_add_frextent, fsc);
if (error) {
@@ -423,8 +424,10 @@ xchk_fscount_count_frextents(
goto out_unlock;
}
+ fsc->frextents_delayed = percpu_counter_sum(&mp->m_delalloc_rtextents);
+
out_unlock:
- xfs_iunlock(sc->mp->m_rbmip, XFS_ILOCK_SHARED | XFS_ILOCK_RTBITMAP);
+ xfs_rtbitmap_unlock_shared(sc->mp, XFS_RBMLOCK_BITMAP);
return error;
}
#else
@@ -434,6 +437,7 @@ xchk_fscount_count_frextents(
struct xchk_fscounters *fsc)
{
fsc->frextents = 0;
+ fsc->frextents_delayed = 0;
return 0;
}
#endif /* CONFIG_XFS_RT */
@@ -517,7 +521,7 @@ xchk_fscounters(
/*
* If the filesystem is not frozen, the counter summation calls above
- * can race with xfs_mod_freecounter, which subtracts a requested space
+ * can race with xfs_dec_freecounter, which subtracts a requested space
* reservation from the counter and undoes the subtraction if that made
* the counter go negative. Therefore, it's possible to see negative
* values here, and we should only flag that as a corruption if we
@@ -593,7 +597,7 @@ xchk_fscounters(
}
if (!xchk_fscount_within_range(sc, frextents, &mp->m_frextents,
- fsc->frextents)) {
+ fsc->frextents - fsc->frextents_delayed)) {
if (fsc->frozen)
xchk_set_corrupt(sc);
else
diff --git a/fs/xfs/scrub/fscounters.h b/fs/xfs/scrub/fscounters.h
index 461a13d25f..bcf56e1c36 100644
--- a/fs/xfs/scrub/fscounters.h
+++ b/fs/xfs/scrub/fscounters.h
@@ -12,6 +12,7 @@ struct xchk_fscounters {
uint64_t ifree;
uint64_t fdblocks;
uint64_t frextents;
+ uint64_t frextents_delayed;
unsigned long long icount_min;
unsigned long long icount_max;
bool frozen;
diff --git a/fs/xfs/scrub/fscounters_repair.c b/fs/xfs/scrub/fscounters_repair.c
index 94cdb852be..469bf645db 100644
--- a/fs/xfs/scrub/fscounters_repair.c
+++ b/fs/xfs/scrub/fscounters_repair.c
@@ -65,7 +65,17 @@ xrep_fscounters(
percpu_counter_set(&mp->m_icount, fsc->icount);
percpu_counter_set(&mp->m_ifree, fsc->ifree);
percpu_counter_set(&mp->m_fdblocks, fsc->fdblocks);
- percpu_counter_set(&mp->m_frextents, fsc->frextents);
+
+ /*
+ * Online repair is only supported on v5 file systems, which require
+ * lazy sb counters and thus no update of sb_fdblocks here. But as of
+ * now we don't support lazy counting sb_frextents yet, and thus need
+ * to also update it directly here. And for that we need to keep
+ * track of the delalloc reservations separately, as they are are
+ * subtracted from m_frextents, but not included in sb_frextents.
+ */
+ percpu_counter_set(&mp->m_frextents,
+ fsc->frextents - fsc->frextents_delayed);
mp->m_sb.sb_frextents = fsc->frextents;
return 0;
diff --git a/fs/xfs/scrub/health.c b/fs/xfs/scrub/health.c
index 9020a6bef7..b712a8bd34 100644
--- a/fs/xfs/scrub/health.c
+++ b/fs/xfs/scrub/health.c
@@ -108,6 +108,7 @@ static const struct xchk_health_map type_to_health_flag[XFS_SCRUB_TYPE_NR] = {
[XFS_SCRUB_TYPE_FSCOUNTERS] = { XHG_FS, XFS_SICK_FS_COUNTERS },
[XFS_SCRUB_TYPE_QUOTACHECK] = { XHG_FS, XFS_SICK_FS_QUOTACHECK },
[XFS_SCRUB_TYPE_NLINKS] = { XHG_FS, XFS_SICK_FS_NLINKS },
+ [XFS_SCRUB_TYPE_DIRTREE] = { XHG_INO, XFS_SICK_INO_DIRTREE },
};
/* Return the health status mask for this scrub type. */
diff --git a/fs/xfs/scrub/ino_bitmap.h b/fs/xfs/scrub/ino_bitmap.h
new file mode 100644
index 0000000000..1300833679
--- /dev/null
+++ b/fs/xfs/scrub/ino_bitmap.h
@@ -0,0 +1,37 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Copyright (c) 2023-2024 Oracle. All Rights Reserved.
+ * Author: Darrick J. Wong <djwong@kernel.org>
+ */
+#ifndef __XFS_SCRUB_INO_BITMAP_H__
+#define __XFS_SCRUB_INO_BITMAP_H__
+
+/* Bitmaps, but for type-checked for xfs_ino_t */
+
+struct xino_bitmap {
+ struct xbitmap64 inobitmap;
+};
+
+static inline void xino_bitmap_init(struct xino_bitmap *bitmap)
+{
+ xbitmap64_init(&bitmap->inobitmap);
+}
+
+static inline void xino_bitmap_destroy(struct xino_bitmap *bitmap)
+{
+ xbitmap64_destroy(&bitmap->inobitmap);
+}
+
+static inline int xino_bitmap_set(struct xino_bitmap *bitmap, xfs_ino_t ino)
+{
+ return xbitmap64_set(&bitmap->inobitmap, ino, 1);
+}
+
+static inline int xino_bitmap_test(struct xino_bitmap *bitmap, xfs_ino_t ino)
+{
+ uint64_t len = 1;
+
+ return xbitmap64_test(&bitmap->inobitmap, ino, &len);
+}
+
+#endif /* __XFS_SCRUB_INO_BITMAP_H__ */
diff --git a/fs/xfs/scrub/inode.c b/fs/xfs/scrub/inode.c
index 6e2fe2d625..d32716fb2f 100644
--- a/fs/xfs/scrub/inode.c
+++ b/fs/xfs/scrub/inode.c
@@ -739,6 +739,23 @@ xchk_inode_check_reflink_iflag(
xchk_ino_set_corrupt(sc, ino);
}
+/*
+ * If this inode has zero link count, it must be on the unlinked list. If
+ * it has nonzero link count, it must not be on the unlinked list.
+ */
+STATIC void
+xchk_inode_check_unlinked(
+ struct xfs_scrub *sc)
+{
+ if (VFS_I(sc->ip)->i_nlink == 0) {
+ if (!xfs_inode_on_unlinked_list(sc->ip))
+ xchk_ino_set_corrupt(sc, sc->ip->i_ino);
+ } else {
+ if (xfs_inode_on_unlinked_list(sc->ip))
+ xchk_ino_set_corrupt(sc, sc->ip->i_ino);
+ }
+}
+
/* Scrub an inode. */
int
xchk_inode(
@@ -771,6 +788,8 @@ xchk_inode(
if (S_ISREG(VFS_I(sc->ip)->i_mode))
xchk_inode_check_reflink_iflag(sc, sc->ip->i_ino);
+ xchk_inode_check_unlinked(sc);
+
xchk_inode_xref(sc, sc->ip->i_ino, &di);
out:
return error;
diff --git a/fs/xfs/scrub/inode_repair.c b/fs/xfs/scrub/inode_repair.c
index eab380e95e..daf9f1ee7c 100644
--- a/fs/xfs/scrub/inode_repair.c
+++ b/fs/xfs/scrub/inode_repair.c
@@ -46,6 +46,7 @@
#include "scrub/repair.h"
#include "scrub/iscan.h"
#include "scrub/readdir.h"
+#include "scrub/tempfile.h"
/*
* Inode Record Repair
@@ -282,6 +283,51 @@ xrep_dinode_findmode_dirent(
return 0;
}
+/* Try to lock a directory, or wait a jiffy. */
+static inline int
+xrep_dinode_ilock_nowait(
+ struct xfs_inode *dp,
+ unsigned int lock_mode)
+{
+ if (xfs_ilock_nowait(dp, lock_mode))
+ return true;
+
+ schedule_timeout_killable(1);
+ return false;
+}
+
+/*
+ * Try to lock a directory to look for ftype hints. Since we already hold the
+ * AGI buffer, we cannot block waiting for the ILOCK because rename can take
+ * the ILOCK and then try to lock AGIs.
+ */
+STATIC int
+xrep_dinode_trylock_directory(
+ struct xrep_inode *ri,
+ struct xfs_inode *dp,
+ unsigned int *lock_modep)
+{
+ unsigned long deadline = jiffies + msecs_to_jiffies(30000);
+ unsigned int lock_mode;
+ int error = 0;
+
+ do {
+ if (xchk_should_terminate(ri->sc, &error))
+ return error;
+
+ if (xfs_need_iread_extents(&dp->i_df))
+ lock_mode = XFS_ILOCK_EXCL;
+ else
+ lock_mode = XFS_ILOCK_SHARED;
+
+ if (xrep_dinode_ilock_nowait(dp, lock_mode)) {
+ *lock_modep = lock_mode;
+ return 0;
+ }
+ } while (!time_is_before_jiffies(deadline));
+ return -EBUSY;
+}
+
/*
* If this is a directory, walk the dirents looking for any that point to the
* scrub target inode.
@@ -295,11 +341,17 @@ xrep_dinode_findmode_walk_directory(
unsigned int lock_mode;
int error = 0;
+ /* Ignore temporary repair directories. */
+ if (xrep_is_tempfile(dp))
+ return 0;
+
/*
* Scan the directory to see if there it contains an entry pointing to
* the directory that we are repairing.
*/
- lock_mode = xfs_ilock_data_map_shared(dp);
+ error = xrep_dinode_trylock_directory(ri, dp, &lock_mode);
+ if (error)
+ return error;
/*
* If this directory is known to be sick, we cannot scan it reliably
@@ -356,6 +408,7 @@ xrep_dinode_find_mode(
* so there's a real possibility that _iscan_iter can return EBUSY.
*/
xchk_iscan_start(sc, 5000, 100, &ri->ftype_iscan);
+ xchk_iscan_set_agi_trylock(&ri->ftype_iscan);
ri->ftype_iscan.skip_ino = sc->sm->sm_ino;
ri->alleged_ftype = XFS_DIR3_FT_UNKNOWN;
while ((error = xchk_iscan_iter(&ri->ftype_iscan, &dp)) == 1) {
@@ -463,6 +516,17 @@ xrep_dinode_mode(
return 0;
}
+/* Fix unused link count fields having nonzero values. */
+STATIC void
+xrep_dinode_nlinks(
+ struct xfs_dinode *dip)
+{
+ if (dip->di_version > 1)
+ dip->di_onlink = 0;
+ else
+ dip->di_nlink = 0;
+}
+
/* Fix any conflicting flags that the verifiers complain about. */
STATIC void
xrep_dinode_flags(
@@ -1324,6 +1388,7 @@ xrep_dinode_core(
iget_error = xrep_dinode_mode(ri, dip);
if (iget_error)
goto write;
+ xrep_dinode_nlinks(dip);
xrep_dinode_flags(sc, dip, ri->rt_extents > 0);
xrep_dinode_size(ri, dip);
xrep_dinode_extsize_hints(sc, dip);
@@ -1671,6 +1736,44 @@ xrep_inode_extsize(
}
}
+/* Ensure this file has an attr fork if it needs to hold a parent pointer. */
+STATIC int
+xrep_inode_pptr(
+ struct xfs_scrub *sc)
+{
+ struct xfs_mount *mp = sc->mp;
+ struct xfs_inode *ip = sc->ip;
+ struct inode *inode = VFS_I(ip);
+
+ if (!xfs_has_parent(mp))
+ return 0;
+
+ /*
+ * Unlinked inodes that cannot be added to the directory tree will not
+ * have a parent pointer.
+ */
+ if (inode->i_nlink == 0 && !(inode->i_state & I_LINKABLE))
+ return 0;
+
+ /* The root directory doesn't have a parent pointer. */
+ if (ip == mp->m_rootip)
+ return 0;
+
+ /*
+ * Metadata inodes are rooted in the superblock and do not have any
+ * parents.
+ */
+ if (xfs_is_metadata_inode(ip))
+ return 0;
+
+ /* Inode already has an attr fork; no further work possible here. */
+ if (xfs_inode_has_attr_fork(ip))
+ return 0;
+
+ return xfs_bmap_add_attrfork(sc->tp, ip,
+ sizeof(struct xfs_attr_sf_hdr), true);
+}
+
/* Fix any irregularities in an inode that the verifiers don't catch. */
STATIC int
xrep_inode_problems(
@@ -1681,6 +1784,9 @@ xrep_inode_problems(
error = xrep_inode_blockcounts(sc);
if (error)
return error;
+ error = xrep_inode_pptr(sc);
+ if (error)
+ return error;
xrep_inode_timestamps(sc->ip);
xrep_inode_flags(sc);
xrep_inode_ids(sc);
@@ -1697,6 +1803,46 @@ xrep_inode_problems(
return xrep_roll_trans(sc);
}
+/*
+ * Make sure this inode's unlinked list pointers are consistent with its
+ * link count.
+ */
+STATIC int
+xrep_inode_unlinked(
+ struct xfs_scrub *sc)
+{
+ unsigned int nlink = VFS_I(sc->ip)->i_nlink;
+ int error;
+
+ /*
+ * If this inode is linked from the directory tree and on the unlinked
+ * list, remove it from the unlinked list.
+ */
+ if (nlink > 0 && xfs_inode_on_unlinked_list(sc->ip)) {
+ struct xfs_perag *pag;
+ int error;
+
+ pag = xfs_perag_get(sc->mp,
+ XFS_INO_TO_AGNO(sc->mp, sc->ip->i_ino));
+ error = xfs_iunlink_remove(sc->tp, pag, sc->ip);
+ xfs_perag_put(pag);
+ if (error)
+ return error;
+ }
+
+ /*
+ * If this inode is not linked from the directory tree yet not on the
+ * unlinked list, put it on the unlinked list.
+ */
+ if (nlink == 0 && !xfs_inode_on_unlinked_list(sc->ip)) {
+ error = xfs_iunlink(sc->tp, sc->ip);
+ if (error)
+ return error;
+ }
+
+ return 0;
+}
+
/* Repair an inode's fields. */
int
xrep_inode(
@@ -1746,5 +1892,10 @@ xrep_inode(
return error;
}
+ /* Reconnect incore unlinked list */
+ error = xrep_inode_unlinked(sc);
+ if (error)
+ return error;
+
return xrep_defer_finish(sc);
}
diff --git a/fs/xfs/scrub/iscan.c b/fs/xfs/scrub/iscan.c
index ec3478bc50..cf9d983667 100644
--- a/fs/xfs/scrub/iscan.c
+++ b/fs/xfs/scrub/iscan.c
@@ -243,6 +243,51 @@ xchk_iscan_finish(
mutex_unlock(&iscan->lock);
}
+/* Mark an inode scan finished before we actually scan anything. */
+void
+xchk_iscan_finish_early(
+ struct xchk_iscan *iscan)
+{
+ ASSERT(iscan->cursor_ino == iscan->scan_start_ino);
+ ASSERT(iscan->__visited_ino == iscan->scan_start_ino);
+
+ xchk_iscan_finish(iscan);
+}
+
+/*
+ * Grab the AGI to advance the inode scan. Returns 0 if *agi_bpp is now set,
+ * -ECANCELED if the live scan aborted, -EBUSY if the AGI could not be grabbed,
+ * or the usual negative errno.
+ */
+STATIC int
+xchk_iscan_read_agi(
+ struct xchk_iscan *iscan,
+ struct xfs_perag *pag,
+ struct xfs_buf **agi_bpp)
+{
+ struct xfs_scrub *sc = iscan->sc;
+ unsigned long relax;
+ int ret;
+
+ if (!xchk_iscan_agi_needs_trylock(iscan))
+ return xfs_ialloc_read_agi(pag, sc->tp, 0, agi_bpp);
+
+ relax = msecs_to_jiffies(iscan->iget_retry_delay);
+ do {
+ ret = xfs_ialloc_read_agi(pag, sc->tp, XFS_IALLOC_FLAG_TRYLOCK,
+ agi_bpp);
+ if (ret != -EAGAIN)
+ return ret;
+ if (!iscan->iget_timeout ||
+ time_is_before_jiffies(iscan->__iget_deadline))
+ return -EBUSY;
+
+ trace_xchk_iscan_agi_retry_wait(iscan);
+ } while (!schedule_timeout_killable(relax) &&
+ !xchk_iscan_aborted(iscan));
+ return -ECANCELED;
+}
+
/*
* Advance ino to the next inode that the inobt thinks is allocated, being
* careful to jump to the next AG if we've reached the right end of this AG's
@@ -281,7 +326,7 @@ xchk_iscan_advance(
if (!pag)
return -ECANCELED;
- ret = xfs_ialloc_read_agi(pag, sc->tp, &agi_bp);
+ ret = xchk_iscan_read_agi(iscan, pag, &agi_bp);
if (ret)
goto out_pag;
@@ -363,6 +408,15 @@ xchk_iscan_iget_retry(
}
/*
+ * For an inode scan, we hold the AGI and want to try to grab a batch of
+ * inodes. Holding the AGI prevents inodegc from clearing freed inodes,
+ * so we must use noretry here. For every inode after the first one in the
+ * batch, we don't want to wait, so we use retry there too. Finally, use
+ * dontcache to avoid polluting the cache.
+ */
+#define ISCAN_IGET_FLAGS (XFS_IGET_NORETRY | XFS_IGET_DONTCACHE)
+
+/*
* Grab an inode as part of an inode scan. While scanning this inode, the
* caller must ensure that no other threads can modify the inode until a call
* to xchk_iscan_visit succeeds.
@@ -389,7 +443,7 @@ xchk_iscan_iget(
ASSERT(iscan->__inodes[0] == NULL);
/* Fill the first slot in the inode array. */
- error = xfs_iget(sc->mp, sc->tp, ino, XFS_IGET_NORETRY, 0,
+ error = xfs_iget(sc->mp, sc->tp, ino, ISCAN_IGET_FLAGS, 0,
&iscan->__inodes[idx]);
trace_xchk_iscan_iget(iscan, error);
@@ -402,8 +456,13 @@ xchk_iscan_iget(
* It's possible that this inode has lost all of its links but
* hasn't yet been inactivated. If we don't have a transaction
* or it's not writable, flush the inodegc workers and wait.
+ * If we have a non-empty transaction, we must not block on
+ * inodegc, which allocates its own transactions.
*/
- xfs_inodegc_flush(mp);
+ if (sc->tp && !(sc->tp->t_flags & XFS_TRANS_NO_WRITECOUNT))
+ xfs_inodegc_push(mp);
+ else
+ xfs_inodegc_flush(mp);
return xchk_iscan_iget_retry(iscan, true);
}
@@ -457,7 +516,7 @@ xchk_iscan_iget(
ASSERT(iscan->__inodes[idx] == NULL);
- error = xfs_iget(sc->mp, sc->tp, ino, XFS_IGET_NORETRY, 0,
+ error = xfs_iget(sc->mp, sc->tp, ino, ISCAN_IGET_FLAGS, 0,
&iscan->__inodes[idx]);
if (error)
break;
diff --git a/fs/xfs/scrub/iscan.h b/fs/xfs/scrub/iscan.h
index 71f657552d..f9f47fa01a 100644
--- a/fs/xfs/scrub/iscan.h
+++ b/fs/xfs/scrub/iscan.h
@@ -59,6 +59,9 @@ struct xchk_iscan {
/* Set if the scan has been aborted due to some event in the fs. */
#define XCHK_ISCAN_OPSTATE_ABORTED (1)
+/* Use trylock to acquire the AGI */
+#define XCHK_ISCAN_OPSTATE_TRYLOCK_AGI (2)
+
static inline bool
xchk_iscan_aborted(const struct xchk_iscan *iscan)
{
@@ -71,8 +74,21 @@ xchk_iscan_abort(struct xchk_iscan *iscan)
set_bit(XCHK_ISCAN_OPSTATE_ABORTED, &iscan->__opstate);
}
+static inline bool
+xchk_iscan_agi_needs_trylock(const struct xchk_iscan *iscan)
+{
+ return test_bit(XCHK_ISCAN_OPSTATE_TRYLOCK_AGI, &iscan->__opstate);
+}
+
+static inline void
+xchk_iscan_set_agi_trylock(struct xchk_iscan *iscan)
+{
+ set_bit(XCHK_ISCAN_OPSTATE_TRYLOCK_AGI, &iscan->__opstate);
+}
+
void xchk_iscan_start(struct xfs_scrub *sc, unsigned int iget_timeout,
unsigned int iget_retry_delay, struct xchk_iscan *iscan);
+void xchk_iscan_finish_early(struct xchk_iscan *iscan);
void xchk_iscan_teardown(struct xchk_iscan *iscan);
int xchk_iscan_iter(struct xchk_iscan *iscan, struct xfs_inode **ipp);
diff --git a/fs/xfs/scrub/listxattr.c b/fs/xfs/scrub/listxattr.c
new file mode 100644
index 0000000000..256ff7700c
--- /dev/null
+++ b/fs/xfs/scrub/listxattr.c
@@ -0,0 +1,320 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Copyright (c) 2022-2024 Oracle. All Rights Reserved.
+ * Author: Darrick J. Wong <djwong@kernel.org>
+ */
+#include "xfs.h"
+#include "xfs_fs.h"
+#include "xfs_shared.h"
+#include "xfs_format.h"
+#include "xfs_log_format.h"
+#include "xfs_trans_resv.h"
+#include "xfs_mount.h"
+#include "xfs_inode.h"
+#include "xfs_da_format.h"
+#include "xfs_da_btree.h"
+#include "xfs_attr.h"
+#include "xfs_attr_leaf.h"
+#include "xfs_attr_sf.h"
+#include "xfs_trans.h"
+#include "scrub/scrub.h"
+#include "scrub/bitmap.h"
+#include "scrub/dab_bitmap.h"
+#include "scrub/listxattr.h"
+
+/* Call a function for every entry in a shortform xattr structure. */
+STATIC int
+xchk_xattr_walk_sf(
+ struct xfs_scrub *sc,
+ struct xfs_inode *ip,
+ xchk_xattr_fn attr_fn,
+ void *priv)
+{
+ struct xfs_attr_sf_hdr *hdr = ip->i_af.if_data;
+ struct xfs_attr_sf_entry *sfe;
+ unsigned int i;
+ int error;
+
+ sfe = xfs_attr_sf_firstentry(hdr);
+ for (i = 0; i < hdr->count; i++) {
+ error = attr_fn(sc, ip, sfe->flags, sfe->nameval, sfe->namelen,
+ &sfe->nameval[sfe->namelen], sfe->valuelen,
+ priv);
+ if (error)
+ return error;
+
+ sfe = xfs_attr_sf_nextentry(sfe);
+ }
+
+ return 0;
+}
+
+/* Call a function for every entry in this xattr leaf block. */
+STATIC int
+xchk_xattr_walk_leaf_entries(
+ struct xfs_scrub *sc,
+ struct xfs_inode *ip,
+ xchk_xattr_fn attr_fn,
+ struct xfs_buf *bp,
+ void *priv)
+{
+ struct xfs_attr3_icleaf_hdr ichdr;
+ struct xfs_mount *mp = sc->mp;
+ struct xfs_attr_leafblock *leaf = bp->b_addr;
+ struct xfs_attr_leaf_entry *entry;
+ unsigned int i;
+ int error;
+
+ xfs_attr3_leaf_hdr_from_disk(mp->m_attr_geo, &ichdr, leaf);
+ entry = xfs_attr3_leaf_entryp(leaf);
+
+ for (i = 0; i < ichdr.count; entry++, i++) {
+ void *value;
+ unsigned char *name;
+ unsigned int namelen, valuelen;
+
+ if (entry->flags & XFS_ATTR_LOCAL) {
+ struct xfs_attr_leaf_name_local *name_loc;
+
+ name_loc = xfs_attr3_leaf_name_local(leaf, i);
+ name = name_loc->nameval;
+ namelen = name_loc->namelen;
+ value = &name_loc->nameval[name_loc->namelen];
+ valuelen = be16_to_cpu(name_loc->valuelen);
+ } else {
+ struct xfs_attr_leaf_name_remote *name_rmt;
+
+ name_rmt = xfs_attr3_leaf_name_remote(leaf, i);
+ name = name_rmt->name;
+ namelen = name_rmt->namelen;
+ value = NULL;
+ valuelen = be32_to_cpu(name_rmt->valuelen);
+ }
+
+ error = attr_fn(sc, ip, entry->flags, name, namelen, value,
+ valuelen, priv);
+ if (error)
+ return error;
+
+ }
+
+ return 0;
+}
+
+/*
+ * Call a function for every entry in a leaf-format xattr structure. Avoid
+ * memory allocations for the loop detector since there's only one block.
+ */
+STATIC int
+xchk_xattr_walk_leaf(
+ struct xfs_scrub *sc,
+ struct xfs_inode *ip,
+ xchk_xattr_fn attr_fn,
+ void *priv)
+{
+ struct xfs_buf *leaf_bp;
+ int error;
+
+ error = xfs_attr3_leaf_read(sc->tp, ip, ip->i_ino, 0, &leaf_bp);
+ if (error)
+ return error;
+
+ error = xchk_xattr_walk_leaf_entries(sc, ip, attr_fn, leaf_bp, priv);
+ xfs_trans_brelse(sc->tp, leaf_bp);
+ return error;
+}
+
+/* Find the leftmost leaf in the xattr dabtree. */
+STATIC int
+xchk_xattr_find_leftmost_leaf(
+ struct xfs_scrub *sc,
+ struct xfs_inode *ip,
+ struct xdab_bitmap *seen_dablks,
+ struct xfs_buf **leaf_bpp)
+{
+ struct xfs_da3_icnode_hdr nodehdr;
+ struct xfs_mount *mp = sc->mp;
+ struct xfs_trans *tp = sc->tp;
+ struct xfs_da_intnode *node;
+ struct xfs_da_node_entry *btree;
+ struct xfs_buf *bp;
+ xfs_failaddr_t fa;
+ xfs_dablk_t blkno = 0;
+ unsigned int expected_level = 0;
+ int error;
+
+ for (;;) {
+ xfs_extlen_t len = 1;
+ uint16_t magic;
+
+ /* Make sure we haven't seen this new block already. */
+ if (xdab_bitmap_test(seen_dablks, blkno, &len))
+ return -EFSCORRUPTED;
+
+ error = xfs_da3_node_read(tp, ip, blkno, &bp, XFS_ATTR_FORK);
+ if (error)
+ return error;
+
+ node = bp->b_addr;
+ magic = be16_to_cpu(node->hdr.info.magic);
+ if (magic == XFS_ATTR_LEAF_MAGIC ||
+ magic == XFS_ATTR3_LEAF_MAGIC)
+ break;
+
+ error = -EFSCORRUPTED;
+ if (magic != XFS_DA_NODE_MAGIC &&
+ magic != XFS_DA3_NODE_MAGIC)
+ goto out_buf;
+
+ fa = xfs_da3_node_header_check(bp, ip->i_ino);
+ if (fa)
+ goto out_buf;
+
+ xfs_da3_node_hdr_from_disk(mp, &nodehdr, node);
+
+ if (nodehdr.count == 0 || nodehdr.level >= XFS_DA_NODE_MAXDEPTH)
+ goto out_buf;
+
+ /* Check the level from the root node. */
+ if (blkno == 0)
+ expected_level = nodehdr.level - 1;
+ else if (expected_level != nodehdr.level)
+ goto out_buf;
+ else
+ expected_level--;
+
+ /* Remember that we've seen this node. */
+ error = xdab_bitmap_set(seen_dablks, blkno, 1);
+ if (error)
+ goto out_buf;
+
+ /* Find the next level towards the leaves of the dabtree. */
+ btree = nodehdr.btree;
+ blkno = be32_to_cpu(btree->before);
+ xfs_trans_brelse(tp, bp);
+ }
+
+ error = -EFSCORRUPTED;
+ fa = xfs_attr3_leaf_header_check(bp, ip->i_ino);
+ if (fa)
+ goto out_buf;
+
+ if (expected_level != 0)
+ goto out_buf;
+
+ /* Remember that we've seen this leaf. */
+ error = xdab_bitmap_set(seen_dablks, blkno, 1);
+ if (error)
+ goto out_buf;
+
+ *leaf_bpp = bp;
+ return 0;
+
+out_buf:
+ xfs_trans_brelse(tp, bp);
+ return error;
+}
+
+/* Call a function for every entry in a node-format xattr structure. */
+STATIC int
+xchk_xattr_walk_node(
+ struct xfs_scrub *sc,
+ struct xfs_inode *ip,
+ xchk_xattr_fn attr_fn,
+ xchk_xattrleaf_fn leaf_fn,
+ void *priv)
+{
+ struct xfs_attr3_icleaf_hdr leafhdr;
+ struct xdab_bitmap seen_dablks;
+ struct xfs_mount *mp = sc->mp;
+ struct xfs_attr_leafblock *leaf;
+ struct xfs_buf *leaf_bp;
+ int error;
+
+ xdab_bitmap_init(&seen_dablks);
+
+ error = xchk_xattr_find_leftmost_leaf(sc, ip, &seen_dablks, &leaf_bp);
+ if (error)
+ goto out_bitmap;
+
+ for (;;) {
+ xfs_extlen_t len;
+
+ error = xchk_xattr_walk_leaf_entries(sc, ip, attr_fn, leaf_bp,
+ priv);
+ if (error)
+ goto out_leaf;
+
+ /* Find the right sibling of this leaf block. */
+ leaf = leaf_bp->b_addr;
+ xfs_attr3_leaf_hdr_from_disk(mp->m_attr_geo, &leafhdr, leaf);
+ if (leafhdr.forw == 0)
+ goto out_leaf;
+
+ xfs_trans_brelse(sc->tp, leaf_bp);
+
+ if (leaf_fn) {
+ error = leaf_fn(sc, priv);
+ if (error)
+ goto out_bitmap;
+ }
+
+ /* Make sure we haven't seen this new leaf already. */
+ len = 1;
+ if (xdab_bitmap_test(&seen_dablks, leafhdr.forw, &len)) {
+ error = -EFSCORRUPTED;
+ goto out_bitmap;
+ }
+
+ error = xfs_attr3_leaf_read(sc->tp, ip, ip->i_ino,
+ leafhdr.forw, &leaf_bp);
+ if (error)
+ goto out_bitmap;
+
+ /* Remember that we've seen this new leaf. */
+ error = xdab_bitmap_set(&seen_dablks, leafhdr.forw, 1);
+ if (error)
+ goto out_leaf;
+ }
+
+out_leaf:
+ xfs_trans_brelse(sc->tp, leaf_bp);
+out_bitmap:
+ xdab_bitmap_destroy(&seen_dablks);
+ return error;
+}
+
+/*
+ * Call a function for every extended attribute in a file.
+ *
+ * Callers must hold the ILOCK. No validation or cursor restarts allowed.
+ * Returns -EFSCORRUPTED on any problem, including loops in the dabtree.
+ */
+int
+xchk_xattr_walk(
+ struct xfs_scrub *sc,
+ struct xfs_inode *ip,
+ xchk_xattr_fn attr_fn,
+ xchk_xattrleaf_fn leaf_fn,
+ void *priv)
+{
+ int error;
+
+ xfs_assert_ilocked(ip, XFS_ILOCK_SHARED | XFS_ILOCK_EXCL);
+
+ if (!xfs_inode_hasattr(ip))
+ return 0;
+
+ if (ip->i_af.if_format == XFS_DINODE_FMT_LOCAL)
+ return xchk_xattr_walk_sf(sc, ip, attr_fn, priv);
+
+ /* attr functions require that the attr fork is loaded */
+ error = xfs_iread_extents(sc->tp, ip, XFS_ATTR_FORK);
+ if (error)
+ return error;
+
+ if (xfs_attr_is_leaf(ip))
+ return xchk_xattr_walk_leaf(sc, ip, attr_fn, priv);
+
+ return xchk_xattr_walk_node(sc, ip, attr_fn, leaf_fn, priv);
+}
diff --git a/fs/xfs/scrub/listxattr.h b/fs/xfs/scrub/listxattr.h
new file mode 100644
index 0000000000..703cfb7b14
--- /dev/null
+++ b/fs/xfs/scrub/listxattr.h
@@ -0,0 +1,19 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * Copyright (c) 2022-2024 Oracle. All Rights Reserved.
+ * Author: Darrick J. Wong <djwong@kernel.org>
+ */
+#ifndef __XFS_SCRUB_LISTXATTR_H__
+#define __XFS_SCRUB_LISTXATTR_H__
+
+typedef int (*xchk_xattr_fn)(struct xfs_scrub *sc, struct xfs_inode *ip,
+ unsigned int attr_flags, const unsigned char *name,
+ unsigned int namelen, const void *value, unsigned int valuelen,
+ void *priv);
+
+typedef int (*xchk_xattrleaf_fn)(struct xfs_scrub *sc, void *priv);
+
+int xchk_xattr_walk(struct xfs_scrub *sc, struct xfs_inode *ip,
+ xchk_xattr_fn attr_fn, xchk_xattrleaf_fn leaf_fn, void *priv);
+
+#endif /* __XFS_SCRUB_LISTXATTR_H__ */
diff --git a/fs/xfs/scrub/nlinks.c b/fs/xfs/scrub/nlinks.c
index 8a7d955789..80aee30886 100644
--- a/fs/xfs/scrub/nlinks.c
+++ b/fs/xfs/scrub/nlinks.c
@@ -18,15 +18,19 @@
#include "xfs_dir2.h"
#include "xfs_dir2_priv.h"
#include "xfs_ag.h"
+#include "xfs_parent.h"
#include "scrub/scrub.h"
#include "scrub/common.h"
#include "scrub/repair.h"
#include "scrub/xfile.h"
#include "scrub/xfarray.h"
#include "scrub/iscan.h"
+#include "scrub/orphanage.h"
#include "scrub/nlinks.h"
#include "scrub/trace.h"
#include "scrub/readdir.h"
+#include "scrub/tempfile.h"
+#include "scrub/listxattr.h"
/*
* Live Inode Link Count Checking
@@ -43,11 +47,23 @@ int
xchk_setup_nlinks(
struct xfs_scrub *sc)
{
+ struct xchk_nlink_ctrs *xnc;
+ int error;
+
xchk_fsgates_enable(sc, XCHK_FSGATES_DIRENTS);
- sc->buf = kzalloc(sizeof(struct xchk_nlink_ctrs), XCHK_GFP_FLAGS);
- if (!sc->buf)
+ if (xchk_could_repair(sc)) {
+ error = xrep_setup_nlinks(sc);
+ if (error)
+ return error;
+ }
+
+ xnc = kvzalloc(sizeof(struct xchk_nlink_ctrs), XCHK_GFP_FLAGS);
+ if (!xnc)
return -ENOMEM;
+ xnc->xname.name = xnc->namebuf;
+ xnc->sc = sc;
+ sc->buf = xnc;
return xchk_setup_fs(sc);
}
@@ -152,6 +168,13 @@ xchk_nlinks_live_update(
xnc = container_of(nb, struct xchk_nlink_ctrs, dhook.dirent_hook.nb);
+ /*
+ * Ignore temporary directories being used to stage dir repairs, since
+ * we don't bump the link counts of the children.
+ */
+ if (xrep_is_tempfile(p->dp))
+ return NOTIFY_DONE;
+
trace_xchk_nlinks_live_update(xnc->sc->mp, p->dp, action, p->ip->i_ino,
p->delta, p->name->name, p->name->len);
@@ -251,12 +274,17 @@ xchk_nlinks_collect_dirent(
* number of parents of the root directory.
*
* Otherwise, increment the number of backrefs pointing back to ino.
+ *
+ * If the filesystem has parent pointers, we walk the pptrs to
+ * determine the backref count.
*/
if (dotdot) {
if (dp == sc->mp->m_rootip)
error = xchk_nlinks_update_incore(xnc, ino, 1, 0, 0);
- else
+ else if (!xfs_has_parent(sc->mp))
error = xchk_nlinks_update_incore(xnc, ino, 0, 1, 0);
+ else
+ error = 0;
if (error)
goto out_unlock;
}
@@ -293,6 +321,61 @@ out_incomplete:
return error;
}
+/* Bump the backref count for the inode referenced by this parent pointer. */
+STATIC int
+xchk_nlinks_collect_pptr(
+ struct xfs_scrub *sc,
+ struct xfs_inode *ip,
+ unsigned int attr_flags,
+ const unsigned char *name,
+ unsigned int namelen,
+ const void *value,
+ unsigned int valuelen,
+ void *priv)
+{
+ struct xfs_name xname = {
+ .name = name,
+ .len = namelen,
+ };
+ struct xchk_nlink_ctrs *xnc = priv;
+ const struct xfs_parent_rec *pptr_rec = value;
+ xfs_ino_t parent_ino;
+ int error;
+
+ /* Update the shadow link counts if we haven't already failed. */
+
+ if (xchk_iscan_aborted(&xnc->collect_iscan)) {
+ error = -ECANCELED;
+ goto out_incomplete;
+ }
+
+ if (!(attr_flags & XFS_ATTR_PARENT))
+ return 0;
+
+ error = xfs_parent_from_attr(sc->mp, attr_flags, name, namelen, value,
+ valuelen, &parent_ino, NULL);
+ if (error)
+ return error;
+
+ trace_xchk_nlinks_collect_pptr(sc->mp, ip, &xname, pptr_rec);
+
+ mutex_lock(&xnc->lock);
+
+ error = xchk_nlinks_update_incore(xnc, parent_ino, 0, 1, 0);
+ if (error)
+ goto out_unlock;
+
+ mutex_unlock(&xnc->lock);
+ return 0;
+
+out_unlock:
+ mutex_unlock(&xnc->lock);
+ xchk_iscan_abort(&xnc->collect_iscan);
+out_incomplete:
+ xchk_set_incomplete(sc);
+ return error;
+}
+
/* Walk a directory to bump the observed link counts of the children. */
STATIC int
xchk_nlinks_collect_dir(
@@ -303,6 +386,13 @@ xchk_nlinks_collect_dir(
unsigned int lock_mode;
int error = 0;
+ /*
+ * Ignore temporary directories being used to stage dir repairs, since
+ * we don't bump the link counts of the children.
+ */
+ if (xrep_is_tempfile(dp))
+ return 0;
+
/* Prevent anyone from changing this directory while we walk it. */
xfs_ilock(dp, XFS_IOLOCK_SHARED);
lock_mode = xfs_ilock_data_map_shared(dp);
@@ -332,6 +422,28 @@ xchk_nlinks_collect_dir(
if (error)
goto out_abort;
+ /* Walk the parent pointers to get real backref counts. */
+ if (xfs_has_parent(sc->mp)) {
+ /*
+ * If the extended attributes look as though they has been
+ * zapped by the inode record repair code, we cannot scan for
+ * parent pointers.
+ */
+ if (xchk_pptr_looks_zapped(dp)) {
+ error = -EBUSY;
+ goto out_unlock;
+ }
+
+ error = xchk_xattr_walk(sc, dp, xchk_nlinks_collect_pptr, NULL,
+ xnc);
+ if (error == -ECANCELED) {
+ error = 0;
+ goto out_unlock;
+ }
+ if (error)
+ goto out_abort;
+ }
+
xchk_iscan_mark_visited(&xnc->collect_iscan, dp);
goto out_unlock;
@@ -537,6 +649,14 @@ xchk_nlinks_compare_inode(
unsigned int actual_nlink;
int error;
+ /*
+ * Ignore temporary files being used to stage repairs, since we assume
+ * they're correct for non-directories, and the directory repair code
+ * doesn't bump the link counts for the children.
+ */
+ if (xrep_is_tempfile(ip))
+ return 0;
+
xfs_ilock(ip, XFS_ILOCK_SHARED);
mutex_lock(&xnc->lock);
@@ -571,9 +691,11 @@ xchk_nlinks_compare_inode(
* this as a corruption. The VFS won't let users increase the link
* count, but it will let them decrease it.
*/
- if (total_links > XFS_MAXLINK) {
+ if (total_links > XFS_NLINK_PINNED) {
xchk_ino_set_corrupt(sc, ip->i_ino);
goto out_corrupt;
+ } else if (total_links > XFS_MAXLINK) {
+ xchk_ino_set_warning(sc, ip->i_ino);
}
/* Link counts should match. */
@@ -850,9 +972,6 @@ xchk_nlinks_setup_scan(
xfs_agino_t first_agino, last_agino;
int error;
- ASSERT(xnc->sc == NULL);
- xnc->sc = sc;
-
mutex_init(&xnc->lock);
/* Retry iget every tenth of a second for up to 30 seconds. */
diff --git a/fs/xfs/scrub/nlinks.h b/fs/xfs/scrub/nlinks.h
index a950f3daf2..b820712bfd 100644
--- a/fs/xfs/scrub/nlinks.h
+++ b/fs/xfs/scrub/nlinks.h
@@ -28,6 +28,13 @@ struct xchk_nlink_ctrs {
* from other writer threads.
*/
struct xfs_dir_hook dhook;
+
+ /* Orphanage reparenting request. */
+ struct xrep_adoption adoption;
+
+ /* Directory entry name, plus the trailing null. */
+ struct xfs_name xname;
+ char namebuf[MAXNAMELEN];
};
/*
diff --git a/fs/xfs/scrub/nlinks_repair.c b/fs/xfs/scrub/nlinks_repair.c
index b87618322f..b3e707f47b 100644
--- a/fs/xfs/scrub/nlinks_repair.c
+++ b/fs/xfs/scrub/nlinks_repair.c
@@ -17,14 +17,19 @@
#include "xfs_iwalk.h"
#include "xfs_ialloc.h"
#include "xfs_sb.h"
+#include "xfs_ag.h"
+#include "xfs_dir2.h"
+#include "xfs_parent.h"
#include "scrub/scrub.h"
#include "scrub/common.h"
#include "scrub/repair.h"
#include "scrub/xfile.h"
#include "scrub/xfarray.h"
#include "scrub/iscan.h"
+#include "scrub/orphanage.h"
#include "scrub/nlinks.h"
#include "scrub/trace.h"
+#include "scrub/tempfile.h"
/*
* Live Inode Link Count Repair
@@ -36,6 +41,48 @@
* inode is locked.
*/
+/* Set up to repair inode link counts. */
+int
+xrep_setup_nlinks(
+ struct xfs_scrub *sc)
+{
+ return xrep_orphanage_try_create(sc);
+}
+
+/*
+ * Inodes that aren't the root directory or the orphanage, have a nonzero link
+ * count, and no observed parents should be moved to the orphanage.
+ */
+static inline bool
+xrep_nlinks_is_orphaned(
+ struct xfs_scrub *sc,
+ struct xfs_inode *ip,
+ unsigned int actual_nlink,
+ const struct xchk_nlink *obs)
+{
+ struct xfs_mount *mp = ip->i_mount;
+
+ if (obs->parents != 0)
+ return false;
+ if (ip == mp->m_rootip || ip == sc->orphanage)
+ return false;
+ return actual_nlink != 0;
+}
+
+/* Remove an inode from the unlinked list. */
+STATIC int
+xrep_nlinks_iunlink_remove(
+ struct xfs_scrub *sc)
+{
+ struct xfs_perag *pag;
+ int error;
+
+ pag = xfs_perag_get(sc->mp, XFS_INO_TO_AGNO(sc->mp, sc->ip->i_ino));
+ error = xfs_iunlink_remove(sc->tp, pag, sc->ip);
+ xfs_perag_put(pag);
+ return error;
+}
+
/*
* Correct the link count of the given inode. Because we have to grab locks
* and resources in a certain order, it's possible that this will be a no-op.
@@ -50,17 +97,55 @@ xrep_nlinks_repair_inode(
struct xfs_inode *ip = sc->ip;
uint64_t total_links;
uint64_t actual_nlink;
+ bool orphanage_available = false;
bool dirty = false;
int error;
- xchk_ilock(sc, XFS_IOLOCK_EXCL);
+ /*
+ * Ignore temporary files being used to stage repairs, since we assume
+ * they're correct for non-directories, and the directory repair code
+ * doesn't bump the link counts for the children.
+ */
+ if (xrep_is_tempfile(ip))
+ return 0;
- error = xfs_trans_alloc(mp, &M_RES(mp)->tr_link, 0, 0, 0, &sc->tp);
- if (error)
- return error;
+ /*
+ * If the filesystem has an orphanage attached to the scrub context,
+ * prepare for a link count repair that could involve @ip being adopted
+ * by the lost+found.
+ */
+ if (xrep_orphanage_can_adopt(sc)) {
+ error = xrep_orphanage_iolock_two(sc);
+ if (error)
+ return error;
- xchk_ilock(sc, XFS_ILOCK_EXCL);
- xfs_trans_ijoin(sc->tp, ip, 0);
+ error = xrep_adoption_trans_alloc(sc, &xnc->adoption);
+ if (error) {
+ xchk_iunlock(sc, XFS_IOLOCK_EXCL);
+ xrep_orphanage_iunlock(sc, XFS_IOLOCK_EXCL);
+ } else {
+ orphanage_available = true;
+ }
+ }
+
+ /*
+ * Either there is no orphanage or we couldn't allocate resources for
+ * that kind of update. Let's try again with only the resources we
+ * need for a simple link count update, since that's much more common.
+ */
+ if (!orphanage_available) {
+ xchk_ilock(sc, XFS_IOLOCK_EXCL);
+
+ error = xfs_trans_alloc(mp, &M_RES(mp)->tr_link, 0, 0, 0,
+ &sc->tp);
+ if (error) {
+ xchk_iunlock(sc, XFS_IOLOCK_EXCL);
+ return error;
+ }
+
+ xchk_ilock(sc, XFS_ILOCK_EXCL);
+ xfs_trans_ijoin(sc->tp, ip, 0);
+ }
mutex_lock(&xnc->lock);
@@ -99,28 +184,68 @@ xrep_nlinks_repair_inode(
}
/*
- * We did not find any links to this inode. If the inode agrees, we
- * have nothing further to do. If not, the inode has a nonzero link
- * count and we don't have anywhere to graft the child onto. Dropping
- * a live inode's link count to zero can cause unexpected shutdowns in
- * inactivation, so leave it alone.
+ * Decide if we're going to move this file to the orphanage, and fix
+ * up the incore link counts if we are.
*/
- if (total_links == 0) {
- if (actual_nlink != 0)
- trace_xrep_nlinks_unfixable_inode(mp, ip, &obs);
- goto out_trans;
+ if (orphanage_available &&
+ xrep_nlinks_is_orphaned(sc, ip, actual_nlink, &obs)) {
+ /* Figure out what name we're going to use here. */
+ error = xrep_adoption_compute_name(&xnc->adoption, &xnc->xname);
+ if (error)
+ goto out_trans;
+
+ /*
+ * Reattach this file to the directory tree by moving it to
+ * the orphanage per the adoption parameters that we already
+ * computed.
+ */
+ error = xrep_adoption_move(&xnc->adoption);
+ if (error)
+ goto out_trans;
+
+ /*
+ * Re-read the link counts since the reparenting will have
+ * updated our scan info.
+ */
+ mutex_lock(&xnc->lock);
+ error = xfarray_load_sparse(xnc->nlinks, ip->i_ino, &obs);
+ mutex_unlock(&xnc->lock);
+ if (error)
+ goto out_trans;
+
+ total_links = xchk_nlink_total(ip, &obs);
+ actual_nlink = VFS_I(ip)->i_nlink;
+ dirty = true;
}
- /* Commit the new link count if it changed. */
- if (total_links != actual_nlink) {
- if (total_links > XFS_MAXLINK) {
- trace_xrep_nlinks_unfixable_inode(mp, ip, &obs);
+ /*
+ * If this inode is linked from the directory tree and on the unlinked
+ * list, remove it from the unlinked list.
+ */
+ if (total_links > 0 && xfs_inode_on_unlinked_list(ip)) {
+ error = xrep_nlinks_iunlink_remove(sc);
+ if (error)
goto out_trans;
- }
+ dirty = true;
+ }
+ /*
+ * If this inode is not linked from the directory tree yet not on the
+ * unlinked list, put it on the unlinked list.
+ */
+ if (total_links == 0 && !xfs_inode_on_unlinked_list(ip)) {
+ error = xfs_iunlink(sc->tp, ip);
+ if (error)
+ goto out_trans;
+ dirty = true;
+ }
+
+ /* Commit the new link count if it changed. */
+ if (total_links != actual_nlink) {
trace_xrep_nlinks_update_inode(mp, ip, &obs);
- set_nlink(VFS_I(ip), total_links);
+ set_nlink(VFS_I(ip), min_t(unsigned long long, total_links,
+ XFS_NLINK_PINNED));
dirty = true;
}
@@ -132,14 +257,19 @@ xrep_nlinks_repair_inode(
xfs_trans_log_inode(sc->tp, ip, XFS_ILOG_CORE);
error = xrep_trans_commit(sc);
- xchk_iunlock(sc, XFS_ILOCK_EXCL | XFS_IOLOCK_EXCL);
- return error;
+ goto out_unlock;
out_scanlock:
mutex_unlock(&xnc->lock);
out_trans:
xchk_trans_cancel(sc);
- xchk_iunlock(sc, XFS_ILOCK_EXCL | XFS_IOLOCK_EXCL);
+out_unlock:
+ xchk_iunlock(sc, XFS_ILOCK_EXCL);
+ if (orphanage_available) {
+ xrep_orphanage_iunlock(sc, XFS_ILOCK_EXCL);
+ xrep_orphanage_iunlock(sc, XFS_IOLOCK_EXCL);
+ }
+ xchk_iunlock(sc, XFS_IOLOCK_EXCL);
return error;
}
@@ -172,10 +302,10 @@ xrep_nlinks(
/*
* We need ftype for an accurate count of the number of child
* subdirectory links. Child subdirectories with a back link (dotdot
- * entry) but no forward link are unfixable, so we cannot repair the
- * link count of the parent directory based on the back link count
- * alone. Filesystems without ftype support are rare (old V4) so we
- * just skip out here.
+ * entry) but no forward link are moved to the orphanage, so we cannot
+ * repair the link count of the parent directory based on the back link
+ * count alone. Filesystems without ftype support are rare (old V4) so
+ * we just skip out here.
*/
if (!xfs_has_ftype(sc->mp))
return -EOPNOTSUPP;
diff --git a/fs/xfs/scrub/orphanage.c b/fs/xfs/scrub/orphanage.c
new file mode 100644
index 0000000000..7148d8362d
--- /dev/null
+++ b/fs/xfs/scrub/orphanage.c
@@ -0,0 +1,627 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Copyright (c) 2021-2024 Oracle. All Rights Reserved.
+ * Author: Darrick J. Wong <djwong@kernel.org>
+ */
+#include "xfs.h"
+#include "xfs_fs.h"
+#include "xfs_shared.h"
+#include "xfs_format.h"
+#include "xfs_trans_resv.h"
+#include "xfs_mount.h"
+#include "xfs_log_format.h"
+#include "xfs_trans.h"
+#include "xfs_inode.h"
+#include "xfs_ialloc.h"
+#include "xfs_quota.h"
+#include "xfs_trans_space.h"
+#include "xfs_dir2.h"
+#include "xfs_icache.h"
+#include "xfs_bmap.h"
+#include "xfs_bmap_btree.h"
+#include "xfs_parent.h"
+#include "xfs_attr_sf.h"
+#include "scrub/scrub.h"
+#include "scrub/common.h"
+#include "scrub/repair.h"
+#include "scrub/trace.h"
+#include "scrub/orphanage.h"
+#include "scrub/readdir.h"
+
+#include <linux/namei.h>
+
+/*
+ * The Orphanage
+ * =============
+ *
+ * If the directory tree is damaged, children of that directory become
+ * inaccessible via that file path. If a child has no other parents, the file
+ * is said to be orphaned. xfs_repair fixes this situation by creating a
+ * orphanage directory (specifically, /lost+found) and creating a directory
+ * entry pointing to the orphaned file.
+ *
+ * Online repair follows this tactic by creating a root-owned /lost+found
+ * directory if one does not exist. If an orphan is found, it will move that
+ * files into orphanage.
+ */
+
+/* Make the orphanage owned by root. */
+STATIC int
+xrep_chown_orphanage(
+ struct xfs_scrub *sc,
+ struct xfs_inode *dp)
+{
+ struct xfs_trans *tp;
+ struct xfs_mount *mp = sc->mp;
+ struct xfs_dquot *udqp = NULL, *gdqp = NULL, *pdqp = NULL;
+ struct xfs_dquot *oldu = NULL, *oldg = NULL, *oldp = NULL;
+ struct inode *inode = VFS_I(dp);
+ int error;
+
+ error = xfs_qm_vop_dqalloc(dp, GLOBAL_ROOT_UID, GLOBAL_ROOT_GID, 0,
+ XFS_QMOPT_QUOTALL, &udqp, &gdqp, &pdqp);
+ if (error)
+ return error;
+
+ error = xfs_trans_alloc_ichange(dp, udqp, gdqp, pdqp, true, &tp);
+ if (error)
+ goto out_dqrele;
+
+ /*
+ * Always clear setuid/setgid/sticky on the orphanage since we don't
+ * normally want that functionality on this directory and xfs_repair
+ * doesn't create it this way either. Leave the other access bits
+ * unchanged.
+ */
+ inode->i_mode &= ~(S_ISUID | S_ISGID | S_ISVTX);
+
+ /*
+ * Change the ownerships and register quota modifications
+ * in the transaction.
+ */
+ if (!uid_eq(inode->i_uid, GLOBAL_ROOT_UID)) {
+ if (XFS_IS_UQUOTA_ON(mp))
+ oldu = xfs_qm_vop_chown(tp, dp, &dp->i_udquot, udqp);
+ inode->i_uid = GLOBAL_ROOT_UID;
+ }
+ if (!gid_eq(inode->i_gid, GLOBAL_ROOT_GID)) {
+ if (XFS_IS_GQUOTA_ON(mp))
+ oldg = xfs_qm_vop_chown(tp, dp, &dp->i_gdquot, gdqp);
+ inode->i_gid = GLOBAL_ROOT_GID;
+ }
+ if (dp->i_projid != 0) {
+ if (XFS_IS_PQUOTA_ON(mp))
+ oldp = xfs_qm_vop_chown(tp, dp, &dp->i_pdquot, pdqp);
+ dp->i_projid = 0;
+ }
+
+ dp->i_diflags &= ~(XFS_DIFLAG_REALTIME | XFS_DIFLAG_RTINHERIT);
+ xfs_trans_log_inode(tp, dp, XFS_ILOG_CORE);
+
+ XFS_STATS_INC(mp, xs_ig_attrchg);
+
+ if (xfs_has_wsync(mp))
+ xfs_trans_set_sync(tp);
+ error = xfs_trans_commit(tp);
+
+ xfs_qm_dqrele(oldu);
+ xfs_qm_dqrele(oldg);
+ xfs_qm_dqrele(oldp);
+
+out_dqrele:
+ xfs_qm_dqrele(udqp);
+ xfs_qm_dqrele(gdqp);
+ xfs_qm_dqrele(pdqp);
+ return error;
+}
+
+#define ORPHANAGE "lost+found"
+
+/* Create the orphanage directory, and set sc->orphanage to it. */
+int
+xrep_orphanage_create(
+ struct xfs_scrub *sc)
+{
+ struct xfs_mount *mp = sc->mp;
+ struct dentry *root_dentry, *orphanage_dentry;
+ struct inode *root_inode = VFS_I(sc->mp->m_rootip);
+ struct inode *orphanage_inode;
+ int error;
+
+ if (xfs_is_shutdown(mp))
+ return -EIO;
+ if (xfs_is_readonly(mp)) {
+ sc->orphanage = NULL;
+ return 0;
+ }
+
+ ASSERT(sc->tp == NULL);
+ ASSERT(sc->orphanage == NULL);
+
+ /* Find the dentry for the root directory... */
+ root_dentry = d_find_alias(root_inode);
+ if (!root_dentry) {
+ error = -EFSCORRUPTED;
+ goto out;
+ }
+
+ /* ...which is a directory, right? */
+ if (!d_is_dir(root_dentry)) {
+ error = -EFSCORRUPTED;
+ goto out_dput_root;
+ }
+
+ /* Try to find the orphanage directory. */
+ inode_lock_nested(root_inode, I_MUTEX_PARENT);
+ orphanage_dentry = lookup_one_len(ORPHANAGE, root_dentry,
+ strlen(ORPHANAGE));
+ if (IS_ERR(orphanage_dentry)) {
+ error = PTR_ERR(orphanage_dentry);
+ goto out_unlock_root;
+ }
+
+ /*
+ * Nothing found? Call mkdir to create the orphanage. Create the
+ * directory without other-user access because we're live and someone
+ * could have been relying partly on minimal access to a parent
+ * directory to control access to a file we put in here.
+ */
+ if (d_really_is_negative(orphanage_dentry)) {
+ error = vfs_mkdir(&nop_mnt_idmap, root_inode, orphanage_dentry,
+ 0750);
+ if (error)
+ goto out_dput_orphanage;
+ }
+
+ /* Not a directory? Bail out. */
+ if (!d_is_dir(orphanage_dentry)) {
+ error = -ENOTDIR;
+ goto out_dput_orphanage;
+ }
+
+ /*
+ * Grab a reference to the orphanage. This /should/ succeed since
+ * we hold the root directory locked and therefore nobody can delete
+ * the orphanage.
+ */
+ orphanage_inode = igrab(d_inode(orphanage_dentry));
+ if (!orphanage_inode) {
+ error = -ENOENT;
+ goto out_dput_orphanage;
+ }
+
+ /* Make sure the orphanage is owned by root. */
+ error = xrep_chown_orphanage(sc, XFS_I(orphanage_inode));
+ if (error)
+ goto out_dput_orphanage;
+
+ /* Stash the reference for later and bail out. */
+ sc->orphanage = XFS_I(orphanage_inode);
+ sc->orphanage_ilock_flags = 0;
+
+out_dput_orphanage:
+ dput(orphanage_dentry);
+out_unlock_root:
+ inode_unlock(VFS_I(sc->mp->m_rootip));
+out_dput_root:
+ dput(root_dentry);
+out:
+ return error;
+}
+
+void
+xrep_orphanage_ilock(
+ struct xfs_scrub *sc,
+ unsigned int ilock_flags)
+{
+ sc->orphanage_ilock_flags |= ilock_flags;
+ xfs_ilock(sc->orphanage, ilock_flags);
+}
+
+bool
+xrep_orphanage_ilock_nowait(
+ struct xfs_scrub *sc,
+ unsigned int ilock_flags)
+{
+ if (xfs_ilock_nowait(sc->orphanage, ilock_flags)) {
+ sc->orphanage_ilock_flags |= ilock_flags;
+ return true;
+ }
+
+ return false;
+}
+
+void
+xrep_orphanage_iunlock(
+ struct xfs_scrub *sc,
+ unsigned int ilock_flags)
+{
+ xfs_iunlock(sc->orphanage, ilock_flags);
+ sc->orphanage_ilock_flags &= ~ilock_flags;
+}
+
+/* Grab the IOLOCK of the orphanage and sc->ip. */
+int
+xrep_orphanage_iolock_two(
+ struct xfs_scrub *sc)
+{
+ int error = 0;
+
+ while (true) {
+ if (xchk_should_terminate(sc, &error))
+ return error;
+
+ /*
+ * Normal XFS takes the IOLOCK before grabbing a transaction.
+ * Scrub holds a transaction, which means that we can't block
+ * on either IOLOCK.
+ */
+ if (xrep_orphanage_ilock_nowait(sc, XFS_IOLOCK_EXCL)) {
+ if (xchk_ilock_nowait(sc, XFS_IOLOCK_EXCL))
+ break;
+ xrep_orphanage_iunlock(sc, XFS_IOLOCK_EXCL);
+ }
+ delay(1);
+ }
+
+ return 0;
+}
+
+/* Release the orphanage. */
+void
+xrep_orphanage_rele(
+ struct xfs_scrub *sc)
+{
+ if (!sc->orphanage)
+ return;
+
+ if (sc->orphanage_ilock_flags)
+ xfs_iunlock(sc->orphanage, sc->orphanage_ilock_flags);
+
+ xchk_irele(sc, sc->orphanage);
+ sc->orphanage = NULL;
+}
+
+/* Adoption moves a file into /lost+found */
+
+/* Can the orphanage adopt @sc->ip? */
+bool
+xrep_orphanage_can_adopt(
+ struct xfs_scrub *sc)
+{
+ ASSERT(sc->ip != NULL);
+
+ if (!sc->orphanage)
+ return false;
+ if (sc->ip == sc->orphanage)
+ return false;
+ if (xfs_internal_inum(sc->mp, sc->ip->i_ino))
+ return false;
+ return true;
+}
+
+/*
+ * Create a new transaction to send a child to the orphanage.
+ *
+ * Allocate a new transaction with sufficient disk space to handle the
+ * adoption, take ILOCK_EXCL of the orphanage and sc->ip, joins them to the
+ * transaction, and reserve quota to reparent the latter. Caller must hold the
+ * IOLOCK of the orphanage and sc->ip.
+ */
+int
+xrep_adoption_trans_alloc(
+ struct xfs_scrub *sc,
+ struct xrep_adoption *adopt)
+{
+ struct xfs_mount *mp = sc->mp;
+ unsigned int child_blkres = 0;
+ int error;
+
+ ASSERT(sc->tp == NULL);
+ ASSERT(sc->ip != NULL);
+ ASSERT(sc->orphanage != NULL);
+ ASSERT(sc->ilock_flags & XFS_IOLOCK_EXCL);
+ ASSERT(sc->orphanage_ilock_flags & XFS_IOLOCK_EXCL);
+ ASSERT(!(sc->ilock_flags & (XFS_ILOCK_SHARED | XFS_ILOCK_EXCL)));
+ ASSERT(!(sc->orphanage_ilock_flags &
+ (XFS_ILOCK_SHARED | XFS_ILOCK_EXCL)));
+
+ /* Compute the worst case space reservation that we need. */
+ adopt->sc = sc;
+ adopt->orphanage_blkres = xfs_link_space_res(mp, MAXNAMELEN);
+ if (S_ISDIR(VFS_I(sc->ip)->i_mode))
+ child_blkres = xfs_rename_space_res(mp, 0, false,
+ xfs_name_dotdot.len, false);
+ if (xfs_has_parent(mp))
+ child_blkres += XFS_ADDAFORK_SPACE_RES(mp);
+ adopt->child_blkres = child_blkres;
+
+ /*
+ * Allocate a transaction to link the child into the parent, along with
+ * enough disk space to handle expansion of both the orphanage and the
+ * dotdot entry of a child directory.
+ */
+ error = xfs_trans_alloc(mp, &M_RES(mp)->tr_link,
+ adopt->orphanage_blkres + adopt->child_blkres, 0, 0,
+ &sc->tp);
+ if (error)
+ return error;
+
+ xfs_lock_two_inodes(sc->orphanage, XFS_ILOCK_EXCL,
+ sc->ip, XFS_ILOCK_EXCL);
+ sc->ilock_flags |= XFS_ILOCK_EXCL;
+ sc->orphanage_ilock_flags |= XFS_ILOCK_EXCL;
+
+ xfs_trans_ijoin(sc->tp, sc->orphanage, 0);
+ xfs_trans_ijoin(sc->tp, sc->ip, 0);
+
+ /*
+ * Reserve enough quota in the orphan directory to add the new name.
+ * Normally the orphanage should have user/group/project ids of zero
+ * and hence is not subject to quota enforcement, but we're allowed to
+ * exceed quota to reattach disconnected parts of the directory tree.
+ */
+ error = xfs_trans_reserve_quota_nblks(sc->tp, sc->orphanage,
+ adopt->orphanage_blkres, 0, true);
+ if (error)
+ goto out_cancel;
+
+ /*
+ * Reserve enough quota in the child directory to change dotdot.
+ * Here we're also allowed to exceed file quota to repair inconsistent
+ * metadata.
+ */
+ if (adopt->child_blkres) {
+ error = xfs_trans_reserve_quota_nblks(sc->tp, sc->ip,
+ adopt->child_blkres, 0, true);
+ if (error)
+ goto out_cancel;
+ }
+
+ return 0;
+out_cancel:
+ xchk_trans_cancel(sc);
+ xrep_orphanage_iunlock(sc, XFS_ILOCK_EXCL);
+ xchk_iunlock(sc, XFS_ILOCK_EXCL);
+ return error;
+}
+
+/*
+ * Compute the xfs_name for the directory entry that we're adding to the
+ * orphanage. Caller must hold ILOCKs of sc->ip and the orphanage and must not
+ * reuse namebuf until the adoption completes or is dissolved.
+ */
+int
+xrep_adoption_compute_name(
+ struct xrep_adoption *adopt,
+ struct xfs_name *xname)
+{
+ struct xfs_scrub *sc = adopt->sc;
+ char *namebuf = (void *)xname->name;
+ xfs_ino_t ino;
+ unsigned int incr = 0;
+ int error = 0;
+
+ adopt->xname = xname;
+ xname->len = snprintf(namebuf, MAXNAMELEN, "%llu", sc->ip->i_ino);
+ xname->type = xfs_mode_to_ftype(VFS_I(sc->ip)->i_mode);
+
+ /* Make sure the filename is unique in the lost+found. */
+ error = xchk_dir_lookup(sc, sc->orphanage, xname, &ino);
+ while (error == 0 && incr < 10000) {
+ xname->len = snprintf(namebuf, MAXNAMELEN, "%llu.%u",
+ sc->ip->i_ino, ++incr);
+ error = xchk_dir_lookup(sc, sc->orphanage, xname, &ino);
+ }
+ if (error == 0) {
+ /* We already have 10,000 entries in the orphanage? */
+ return -EFSCORRUPTED;
+ }
+
+ if (error != -ENOENT)
+ return error;
+ return 0;
+}
+
+/*
+ * Make sure the dcache does not have a positive dentry for the name we've
+ * chosen. The caller should have checked with the ondisk directory, so any
+ * discrepancy is a sign that something is seriously wrong.
+ */
+static int
+xrep_adoption_check_dcache(
+ struct xrep_adoption *adopt)
+{
+ struct qstr qname = QSTR_INIT(adopt->xname->name,
+ adopt->xname->len);
+ struct xfs_scrub *sc = adopt->sc;
+ struct dentry *d_orphanage, *d_child;
+ int error = 0;
+
+ d_orphanage = d_find_alias(VFS_I(sc->orphanage));
+ if (!d_orphanage)
+ return 0;
+
+ d_child = d_hash_and_lookup(d_orphanage, &qname);
+ if (d_child) {
+ trace_xrep_adoption_check_child(sc->mp, d_child);
+
+ if (d_is_positive(d_child)) {
+ ASSERT(d_is_negative(d_child));
+ error = -EFSCORRUPTED;
+ }
+
+ dput(d_child);
+ }
+
+ dput(d_orphanage);
+ return error;
+}
+
+/*
+ * Invalidate all dentries for the name that was added to the orphanage
+ * directory, and all dentries pointing to the child inode that was moved.
+ *
+ * There should not be any positive entries for the name, since we've
+ * maintained our lock on the orphanage directory.
+ */
+static void
+xrep_adoption_zap_dcache(
+ struct xrep_adoption *adopt)
+{
+ struct qstr qname = QSTR_INIT(adopt->xname->name,
+ adopt->xname->len);
+ struct xfs_scrub *sc = adopt->sc;
+ struct dentry *d_orphanage, *d_child;
+
+ /* Invalidate all dentries for the adoption name */
+ d_orphanage = d_find_alias(VFS_I(sc->orphanage));
+ if (!d_orphanage)
+ return;
+
+ d_child = d_hash_and_lookup(d_orphanage, &qname);
+ while (d_child != NULL) {
+ trace_xrep_adoption_invalidate_child(sc->mp, d_child);
+
+ ASSERT(d_is_negative(d_child));
+ d_invalidate(d_child);
+ dput(d_child);
+ d_child = d_lookup(d_orphanage, &qname);
+ }
+
+ dput(d_orphanage);
+
+ /* Invalidate all the dentries pointing down to this file. */
+ while ((d_child = d_find_alias(VFS_I(sc->ip))) != NULL) {
+ trace_xrep_adoption_invalidate_child(sc->mp, d_child);
+
+ d_invalidate(d_child);
+ dput(d_child);
+ }
+}
+
+/*
+ * If we have to add an attr fork ahead of a parent pointer update, how much
+ * space should we ask for?
+ */
+static inline int
+xrep_adoption_attr_sizeof(
+ const struct xrep_adoption *adopt)
+{
+ return sizeof(struct xfs_attr_sf_hdr) +
+ xfs_attr_sf_entsize_byname(sizeof(struct xfs_parent_rec),
+ adopt->xname->len);
+}
+
+/*
+ * Move the current file to the orphanage under the computed name.
+ *
+ * Returns with a dirty transaction so that the caller can handle any other
+ * work, such as fixing up unlinked lists or resetting link counts.
+ */
+int
+xrep_adoption_move(
+ struct xrep_adoption *adopt)
+{
+ struct xfs_scrub *sc = adopt->sc;
+ bool isdir = S_ISDIR(VFS_I(sc->ip)->i_mode);
+ int error;
+
+ trace_xrep_adoption_reparent(sc->orphanage, adopt->xname,
+ sc->ip->i_ino);
+
+ error = xrep_adoption_check_dcache(adopt);
+ if (error)
+ return error;
+
+ /*
+ * If this filesystem has parent pointers, ensure that the file being
+ * moved to the orphanage has an attribute fork. This is required
+ * because the parent pointer code does not itself add attr forks.
+ */
+ if (!xfs_inode_has_attr_fork(sc->ip) && xfs_has_parent(sc->mp)) {
+ int sf_size = xrep_adoption_attr_sizeof(adopt);
+
+ error = xfs_bmap_add_attrfork(sc->tp, sc->ip, sf_size, true);
+ if (error)
+ return error;
+ }
+
+ /* Create the new name in the orphanage. */
+ error = xfs_dir_createname(sc->tp, sc->orphanage, adopt->xname,
+ sc->ip->i_ino, adopt->orphanage_blkres);
+ if (error)
+ return error;
+
+ /*
+ * Bump the link count of the orphanage if we just added a
+ * subdirectory, and update its timestamps.
+ */
+ xfs_trans_ichgtime(sc->tp, sc->orphanage,
+ XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG);
+ if (isdir)
+ xfs_bumplink(sc->tp, sc->orphanage);
+ xfs_trans_log_inode(sc->tp, sc->orphanage, XFS_ILOG_CORE);
+
+ /* Bump the link count of the child. */
+ if (adopt->bump_child_nlink) {
+ xfs_bumplink(sc->tp, sc->ip);
+ xfs_trans_log_inode(sc->tp, sc->ip, XFS_ILOG_CORE);
+ }
+
+ /* Replace the dotdot entry if the child is a subdirectory. */
+ if (isdir) {
+ error = xfs_dir_replace(sc->tp, sc->ip, &xfs_name_dotdot,
+ sc->orphanage->i_ino, adopt->child_blkres);
+ if (error)
+ return error;
+ }
+
+ /* Add a parent pointer from the file back to the lost+found. */
+ if (xfs_has_parent(sc->mp)) {
+ error = xfs_parent_addname(sc->tp, &adopt->ppargs,
+ sc->orphanage, adopt->xname, sc->ip);
+ if (error)
+ return error;
+ }
+
+ /*
+ * Notify dirent hooks that we moved the file to /lost+found, and
+ * finish all the deferred work so that we know the adoption is fully
+ * recorded in the log.
+ */
+ xfs_dir_update_hook(sc->orphanage, sc->ip, 1, adopt->xname);
+
+ /* Remove negative dentries from the lost+found's dcache */
+ xrep_adoption_zap_dcache(adopt);
+ return 0;
+}
+
+/*
+ * Roll to a clean scrub transaction so that we can release the orphanage,
+ * even if xrep_adoption_move was not called.
+ *
+ * Commits all the work and deferred ops attached to an adoption request and
+ * rolls to a clean scrub transaction. On success, returns 0 with the scrub
+ * context holding a clean transaction with no inodes joined. On failure,
+ * returns negative errno with no scrub transaction. All inode locks are
+ * still held after this function returns.
+ */
+int
+xrep_adoption_trans_roll(
+ struct xrep_adoption *adopt)
+{
+ struct xfs_scrub *sc = adopt->sc;
+ int error;
+
+ trace_xrep_adoption_trans_roll(sc->orphanage, sc->ip,
+ !!(sc->tp->t_flags & XFS_TRANS_DIRTY));
+
+ /* Finish all the deferred ops to commit all repairs. */
+ error = xrep_defer_finish(sc);
+ if (error)
+ return error;
+
+ /* Roll the transaction once more to detach the inodes. */
+ return xfs_trans_roll(&sc->tp);
+}
diff --git a/fs/xfs/scrub/orphanage.h b/fs/xfs/scrub/orphanage.h
new file mode 100644
index 0000000000..7c7a2e7d81
--- /dev/null
+++ b/fs/xfs/scrub/orphanage.h
@@ -0,0 +1,86 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Copyright (c) 2021-2024 Oracle. All Rights Reserved.
+ * Author: Darrick J. Wong <djwong@kernel.org>
+ */
+#ifndef __XFS_SCRUB_ORPHANAGE_H__
+#define __XFS_SCRUB_ORPHANAGE_H__
+
+#ifdef CONFIG_XFS_ONLINE_REPAIR
+int xrep_orphanage_create(struct xfs_scrub *sc);
+
+/*
+ * If we're doing a repair, ensure that the orphanage exists and attach it to
+ * the scrub context.
+ */
+static inline int
+xrep_orphanage_try_create(
+ struct xfs_scrub *sc)
+{
+ int error;
+
+ ASSERT(sc->sm->sm_flags & XFS_SCRUB_IFLAG_REPAIR);
+
+ error = xrep_orphanage_create(sc);
+ switch (error) {
+ case 0:
+ case -ENOENT:
+ case -ENOTDIR:
+ case -ENOSPC:
+ /*
+ * If the orphanage can't be found or isn't a directory, we'll
+ * keep going, but we won't be able to attach the file to the
+ * orphanage if we can't find the parent.
+ */
+ return 0;
+ }
+
+ return error;
+}
+
+int xrep_orphanage_iolock_two(struct xfs_scrub *sc);
+
+void xrep_orphanage_ilock(struct xfs_scrub *sc, unsigned int ilock_flags);
+bool xrep_orphanage_ilock_nowait(struct xfs_scrub *sc,
+ unsigned int ilock_flags);
+void xrep_orphanage_iunlock(struct xfs_scrub *sc, unsigned int ilock_flags);
+
+void xrep_orphanage_rele(struct xfs_scrub *sc);
+
+/* Information about a request to add a file to the orphanage. */
+struct xrep_adoption {
+ struct xfs_scrub *sc;
+
+ /* Name used for the adoption. */
+ struct xfs_name *xname;
+
+ /* Parent pointer context tracking */
+ struct xfs_parent_args ppargs;
+
+ /* Block reservations for orphanage and child (if directory). */
+ unsigned int orphanage_blkres;
+ unsigned int child_blkres;
+
+ /*
+ * Does the caller want us to bump the child link count? This is not
+ * needed when reattaching files that have become disconnected but have
+ * nlink > 1. It is necessary when changing the directory tree
+ * structure.
+ */
+ bool bump_child_nlink:1;
+};
+
+bool xrep_orphanage_can_adopt(struct xfs_scrub *sc);
+
+int xrep_adoption_trans_alloc(struct xfs_scrub *sc,
+ struct xrep_adoption *adopt);
+int xrep_adoption_compute_name(struct xrep_adoption *adopt,
+ struct xfs_name *xname);
+int xrep_adoption_move(struct xrep_adoption *adopt);
+int xrep_adoption_trans_roll(struct xrep_adoption *adopt);
+#else
+struct xrep_adoption { /* empty */ };
+# define xrep_orphanage_rele(sc) ((void)0)
+#endif /* CONFIG_XFS_ONLINE_REPAIR */
+
+#endif /* __XFS_SCRUB_ORPHANAGE_H__ */
diff --git a/fs/xfs/scrub/parent.c b/fs/xfs/scrub/parent.c
index 7db8736721..733c410a22 100644
--- a/fs/xfs/scrub/parent.c
+++ b/fs/xfs/scrub/parent.c
@@ -10,19 +10,37 @@
#include "xfs_trans_resv.h"
#include "xfs_mount.h"
#include "xfs_log_format.h"
+#include "xfs_trans.h"
#include "xfs_inode.h"
#include "xfs_icache.h"
#include "xfs_dir2.h"
#include "xfs_dir2_priv.h"
+#include "xfs_attr.h"
+#include "xfs_parent.h"
#include "scrub/scrub.h"
#include "scrub/common.h"
#include "scrub/readdir.h"
+#include "scrub/tempfile.h"
+#include "scrub/repair.h"
+#include "scrub/listxattr.h"
+#include "scrub/xfile.h"
+#include "scrub/xfarray.h"
+#include "scrub/xfblob.h"
+#include "scrub/trace.h"
/* Set us up to scrub parents. */
int
xchk_setup_parent(
struct xfs_scrub *sc)
{
+ int error;
+
+ if (xchk_could_repair(sc)) {
+ error = xrep_setup_parent(sc);
+ if (error)
+ return error;
+ }
+
return xchk_setup_inode_contents(sc, 0);
}
@@ -143,7 +161,8 @@ xchk_parent_validate(
}
if (!xchk_fblock_xref_process_error(sc, XFS_DATA_FORK, 0, &error))
return error;
- if (dp == sc->ip || !S_ISDIR(VFS_I(dp)->i_mode)) {
+ if (dp == sc->ip || xrep_is_tempfile(dp) ||
+ !S_ISDIR(VFS_I(dp)->i_mode)) {
xchk_fblock_set_corrupt(sc, XFS_DATA_FORK, 0);
goto out_rele;
}
@@ -185,6 +204,621 @@ out_rele:
return error;
}
+/*
+ * Checking of Parent Pointers
+ * ===========================
+ *
+ * On filesystems with directory parent pointers, we check the referential
+ * integrity by visiting each parent pointer of a child file and checking that
+ * the directory referenced by the pointer actually has a dirent pointing
+ * forward to the child file.
+ */
+
+/* Deferred parent pointer entry that we saved for later. */
+struct xchk_pptr {
+ /* Cookie for retrieval of the pptr name. */
+ xfblob_cookie name_cookie;
+
+ /* Parent pointer record. */
+ struct xfs_parent_rec pptr_rec;
+
+ /* Length of the pptr name. */
+ uint8_t namelen;
+};
+
+struct xchk_pptrs {
+ struct xfs_scrub *sc;
+
+ /* How many parent pointers did we find at the end? */
+ unsigned long long pptrs_found;
+
+ /* Parent of this directory. */
+ xfs_ino_t parent_ino;
+
+ /* Fixed-size array of xchk_pptr structures. */
+ struct xfarray *pptr_entries;
+
+ /* Blobs containing parent pointer names. */
+ struct xfblob *pptr_names;
+
+ /* Scratch buffer for scanning pptr xattrs */
+ struct xfs_da_args pptr_args;
+
+ /* If we've cycled the ILOCK, we must revalidate all deferred pptrs. */
+ bool need_revalidate;
+
+ /* Name buffer */
+ struct xfs_name xname;
+ char namebuf[MAXNAMELEN];
+};
+
+/* Does this parent pointer match the dotdot entry? */
+STATIC int
+xchk_parent_scan_dotdot(
+ struct xfs_scrub *sc,
+ struct xfs_inode *ip,
+ unsigned int attr_flags,
+ const unsigned char *name,
+ unsigned int namelen,
+ const void *value,
+ unsigned int valuelen,
+ void *priv)
+{
+ struct xchk_pptrs *pp = priv;
+ xfs_ino_t parent_ino;
+ int error;
+
+ if (!(attr_flags & XFS_ATTR_PARENT))
+ return 0;
+
+ error = xfs_parent_from_attr(sc->mp, attr_flags, name, namelen, value,
+ valuelen, &parent_ino, NULL);
+ if (error)
+ return error;
+
+ if (pp->parent_ino == parent_ino)
+ return -ECANCELED;
+
+ return 0;
+}
+
+/* Look up the dotdot entry so that we can check it as we walk the pptrs. */
+STATIC int
+xchk_parent_pptr_and_dotdot(
+ struct xchk_pptrs *pp)
+{
+ struct xfs_scrub *sc = pp->sc;
+ int error;
+
+ /* Look up '..' */
+ error = xchk_dir_lookup(sc, sc->ip, &xfs_name_dotdot, &pp->parent_ino);
+ if (!xchk_fblock_process_error(sc, XFS_DATA_FORK, 0, &error))
+ return error;
+ if (!xfs_verify_dir_ino(sc->mp, pp->parent_ino)) {
+ xchk_fblock_set_corrupt(sc, XFS_DATA_FORK, 0);
+ return 0;
+ }
+
+ /* Is this the root dir? Then '..' must point to itself. */
+ if (sc->ip == sc->mp->m_rootip) {
+ if (sc->ip->i_ino != pp->parent_ino)
+ xchk_fblock_set_corrupt(sc, XFS_DATA_FORK, 0);
+ return 0;
+ }
+
+ /*
+ * If this is now an unlinked directory, the dotdot value is
+ * meaningless as long as it points to a valid inode.
+ */
+ if (VFS_I(sc->ip)->i_nlink == 0)
+ return 0;
+
+ if (pp->sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT)
+ return 0;
+
+ /* Otherwise, walk the pptrs again, and check. */
+ error = xchk_xattr_walk(sc, sc->ip, xchk_parent_scan_dotdot, NULL, pp);
+ if (error == -ECANCELED) {
+ /* Found a parent pointer that matches dotdot. */
+ return 0;
+ }
+ if (!error || error == -EFSCORRUPTED) {
+ /* Found a broken parent pointer or no match. */
+ xchk_fblock_set_corrupt(sc, XFS_ATTR_FORK, 0);
+ return 0;
+ }
+ return error;
+}
+
+/*
+ * Try to lock a parent directory for checking dirents. Returns the inode
+ * flags for the locks we now hold, or zero if we failed.
+ */
+STATIC unsigned int
+xchk_parent_lock_dir(
+ struct xfs_scrub *sc,
+ struct xfs_inode *dp)
+{
+ if (!xfs_ilock_nowait(dp, XFS_IOLOCK_SHARED))
+ return 0;
+
+ if (!xfs_ilock_nowait(dp, XFS_ILOCK_SHARED)) {
+ xfs_iunlock(dp, XFS_IOLOCK_SHARED);
+ return 0;
+ }
+
+ if (!xfs_need_iread_extents(&dp->i_df))
+ return XFS_IOLOCK_SHARED | XFS_ILOCK_SHARED;
+
+ xfs_iunlock(dp, XFS_ILOCK_SHARED);
+
+ if (!xfs_ilock_nowait(dp, XFS_ILOCK_EXCL)) {
+ xfs_iunlock(dp, XFS_IOLOCK_SHARED);
+ return 0;
+ }
+
+ return XFS_IOLOCK_SHARED | XFS_ILOCK_EXCL;
+}
+
+/* Check the forward link (dirent) associated with this parent pointer. */
+STATIC int
+xchk_parent_dirent(
+ struct xchk_pptrs *pp,
+ const struct xfs_name *xname,
+ struct xfs_inode *dp)
+{
+ struct xfs_scrub *sc = pp->sc;
+ xfs_ino_t child_ino;
+ int error;
+
+ /*
+ * Use the name attached to this parent pointer to look up the
+ * directory entry in the alleged parent.
+ */
+ error = xchk_dir_lookup(sc, dp, xname, &child_ino);
+ if (error == -ENOENT) {
+ xchk_fblock_xref_set_corrupt(sc, XFS_ATTR_FORK, 0);
+ return 0;
+ }
+ if (!xchk_fblock_xref_process_error(sc, XFS_ATTR_FORK, 0, &error))
+ return error;
+
+ /* Does the inode number match? */
+ if (child_ino != sc->ip->i_ino) {
+ xchk_fblock_xref_set_corrupt(sc, XFS_ATTR_FORK, 0);
+ return 0;
+ }
+
+ return 0;
+}
+
+/* Try to grab a parent directory. */
+STATIC int
+xchk_parent_iget(
+ struct xchk_pptrs *pp,
+ const struct xfs_parent_rec *pptr,
+ struct xfs_inode **dpp)
+{
+ struct xfs_scrub *sc = pp->sc;
+ struct xfs_inode *ip;
+ xfs_ino_t parent_ino = be64_to_cpu(pptr->p_ino);
+ int error;
+
+ /* Validate inode number. */
+ error = xfs_dir_ino_validate(sc->mp, parent_ino);
+ if (error) {
+ xchk_fblock_set_corrupt(sc, XFS_ATTR_FORK, 0);
+ return -ECANCELED;
+ }
+
+ error = xchk_iget(sc, parent_ino, &ip);
+ if (error == -EINVAL || error == -ENOENT) {
+ xchk_fblock_set_corrupt(sc, XFS_ATTR_FORK, 0);
+ return -ECANCELED;
+ }
+ if (!xchk_fblock_xref_process_error(sc, XFS_ATTR_FORK, 0, &error))
+ return error;
+
+ /* The parent must be a directory. */
+ if (!S_ISDIR(VFS_I(ip)->i_mode)) {
+ xchk_fblock_xref_set_corrupt(sc, XFS_ATTR_FORK, 0);
+ goto out_rele;
+ }
+
+ /* Validate generation number. */
+ if (VFS_I(ip)->i_generation != be32_to_cpu(pptr->p_gen)) {
+ xchk_fblock_xref_set_corrupt(sc, XFS_ATTR_FORK, 0);
+ goto out_rele;
+ }
+
+ *dpp = ip;
+ return 0;
+out_rele:
+ xchk_irele(sc, ip);
+ return 0;
+}
+
+/*
+ * Walk an xattr of a file. If this xattr is a parent pointer, follow it up
+ * to a parent directory and check that the parent has a dirent pointing back
+ * to us.
+ */
+STATIC int
+xchk_parent_scan_attr(
+ struct xfs_scrub *sc,
+ struct xfs_inode *ip,
+ unsigned int attr_flags,
+ const unsigned char *name,
+ unsigned int namelen,
+ const void *value,
+ unsigned int valuelen,
+ void *priv)
+{
+ struct xfs_name xname = {
+ .name = name,
+ .len = namelen,
+ };
+ struct xchk_pptrs *pp = priv;
+ struct xfs_inode *dp = NULL;
+ const struct xfs_parent_rec *pptr_rec = value;
+ xfs_ino_t parent_ino;
+ unsigned int lockmode;
+ int error;
+
+ if (!(attr_flags & XFS_ATTR_PARENT))
+ return 0;
+
+ error = xfs_parent_from_attr(sc->mp, attr_flags, name, namelen, value,
+ valuelen, &parent_ino, NULL);
+ if (error) {
+ xchk_fblock_set_corrupt(sc, XFS_ATTR_FORK, 0);
+ return error;
+ }
+
+ /* No self-referential parent pointers. */
+ if (parent_ino == sc->ip->i_ino) {
+ xchk_fblock_set_corrupt(sc, XFS_ATTR_FORK, 0);
+ return -ECANCELED;
+ }
+
+ pp->pptrs_found++;
+
+ error = xchk_parent_iget(pp, pptr_rec, &dp);
+ if (error)
+ return error;
+ if (!dp)
+ return 0;
+
+ /* Try to lock the inode. */
+ lockmode = xchk_parent_lock_dir(sc, dp);
+ if (!lockmode) {
+ struct xchk_pptr save_pp = {
+ .pptr_rec = *pptr_rec, /* struct copy */
+ .namelen = namelen,
+ };
+
+ /* Couldn't lock the inode, so save the pptr for later. */
+ trace_xchk_parent_defer(sc->ip, &xname, dp->i_ino);
+
+ error = xfblob_storename(pp->pptr_names, &save_pp.name_cookie,
+ &xname);
+ if (!xchk_fblock_xref_process_error(sc, XFS_ATTR_FORK, 0,
+ &error))
+ goto out_rele;
+
+ error = xfarray_append(pp->pptr_entries, &save_pp);
+ if (!xchk_fblock_xref_process_error(sc, XFS_ATTR_FORK, 0,
+ &error))
+ goto out_rele;
+
+ goto out_rele;
+ }
+
+ error = xchk_parent_dirent(pp, &xname, dp);
+ if (error)
+ goto out_unlock;
+
+out_unlock:
+ xfs_iunlock(dp, lockmode);
+out_rele:
+ xchk_irele(sc, dp);
+ return error;
+}
+
+/*
+ * Revalidate a parent pointer that we collected in the past but couldn't check
+ * because of lock contention. Returns 0 if the parent pointer is still valid,
+ * -ENOENT if it has gone away on us, or a negative errno.
+ */
+STATIC int
+xchk_parent_revalidate_pptr(
+ struct xchk_pptrs *pp,
+ const struct xfs_name *xname,
+ struct xfs_parent_rec *pptr)
+{
+ struct xfs_scrub *sc = pp->sc;
+ int error;
+
+ error = xfs_parent_lookup(sc->tp, sc->ip, xname, pptr, &pp->pptr_args);
+ if (error == -ENOATTR) {
+ /* Parent pointer went away, nothing to revalidate. */
+ return -ENOENT;
+ }
+
+ return error;
+}
+
+/*
+ * Check a parent pointer the slow way, which means we cycle locks a bunch
+ * and put up with revalidation until we get it done.
+ */
+STATIC int
+xchk_parent_slow_pptr(
+ struct xchk_pptrs *pp,
+ const struct xfs_name *xname,
+ struct xfs_parent_rec *pptr)
+{
+ struct xfs_scrub *sc = pp->sc;
+ struct xfs_inode *dp = NULL;
+ unsigned int lockmode;
+ int error;
+
+ /* Check that the deferred parent pointer still exists. */
+ if (pp->need_revalidate) {
+ error = xchk_parent_revalidate_pptr(pp, xname, pptr);
+ if (error == -ENOENT)
+ return 0;
+ if (!xchk_fblock_xref_process_error(sc, XFS_ATTR_FORK, 0,
+ &error))
+ return error;
+ }
+
+ error = xchk_parent_iget(pp, pptr, &dp);
+ if (error)
+ return error;
+ if (!dp)
+ return 0;
+
+ /*
+ * If we can grab both IOLOCK and ILOCK of the alleged parent, we
+ * can proceed with the validation.
+ */
+ lockmode = xchk_parent_lock_dir(sc, dp);
+ if (lockmode) {
+ trace_xchk_parent_slowpath(sc->ip, xname, dp->i_ino);
+ goto check_dirent;
+ }
+
+ /*
+ * We couldn't lock the parent dir. Drop all the locks and try to
+ * get them again, one at a time.
+ */
+ xchk_iunlock(sc, sc->ilock_flags);
+ pp->need_revalidate = true;
+
+ trace_xchk_parent_ultraslowpath(sc->ip, xname, dp->i_ino);
+
+ error = xchk_dir_trylock_for_pptrs(sc, dp, &lockmode);
+ if (error)
+ goto out_rele;
+
+ /* Revalidate the parent pointer now that we cycled locks. */
+ error = xchk_parent_revalidate_pptr(pp, xname, pptr);
+ if (error == -ENOENT) {
+ error = 0;
+ goto out_unlock;
+ }
+ if (!xchk_fblock_xref_process_error(sc, XFS_ATTR_FORK, 0, &error))
+ goto out_unlock;
+
+check_dirent:
+ error = xchk_parent_dirent(pp, xname, dp);
+out_unlock:
+ xfs_iunlock(dp, lockmode);
+out_rele:
+ xchk_irele(sc, dp);
+ return error;
+}
+
+/* Check all the parent pointers that we deferred the first time around. */
+STATIC int
+xchk_parent_finish_slow_pptrs(
+ struct xchk_pptrs *pp)
+{
+ xfarray_idx_t array_cur;
+ int error;
+
+ foreach_xfarray_idx(pp->pptr_entries, array_cur) {
+ struct xchk_pptr pptr;
+
+ if (pp->sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT)
+ return 0;
+
+ error = xfarray_load(pp->pptr_entries, array_cur, &pptr);
+ if (error)
+ return error;
+
+ error = xfblob_loadname(pp->pptr_names, pptr.name_cookie,
+ &pp->xname, pptr.namelen);
+ if (error)
+ return error;
+
+ error = xchk_parent_slow_pptr(pp, &pp->xname, &pptr.pptr_rec);
+ if (error)
+ return error;
+ }
+
+ /* Empty out both xfiles now that we've checked everything. */
+ xfarray_truncate(pp->pptr_entries);
+ xfblob_truncate(pp->pptr_names);
+ return 0;
+}
+
+/* Count the number of parent pointers. */
+STATIC int
+xchk_parent_count_pptr(
+ struct xfs_scrub *sc,
+ struct xfs_inode *ip,
+ unsigned int attr_flags,
+ const unsigned char *name,
+ unsigned int namelen,
+ const void *value,
+ unsigned int valuelen,
+ void *priv)
+{
+ struct xchk_pptrs *pp = priv;
+ int error;
+
+ if (!(attr_flags & XFS_ATTR_PARENT))
+ return 0;
+
+ error = xfs_parent_from_attr(sc->mp, attr_flags, name, namelen, value,
+ valuelen, NULL, NULL);
+ if (error)
+ return error;
+
+ pp->pptrs_found++;
+ return 0;
+}
+
+/*
+ * Compare the number of parent pointers to the link count. For
+ * non-directories these should be the same. For unlinked directories the
+ * count should be zero; for linked directories, it should be nonzero.
+ */
+STATIC int
+xchk_parent_count_pptrs(
+ struct xchk_pptrs *pp)
+{
+ struct xfs_scrub *sc = pp->sc;
+ int error;
+
+ /*
+ * If we cycled the ILOCK while cross-checking parent pointers with
+ * dirents, then we need to recalculate the number of parent pointers.
+ */
+ if (pp->need_revalidate) {
+ pp->pptrs_found = 0;
+ error = xchk_xattr_walk(sc, sc->ip, xchk_parent_count_pptr,
+ NULL, pp);
+ if (error == -EFSCORRUPTED) {
+ /* Found a bad parent pointer */
+ xchk_fblock_set_corrupt(sc, XFS_ATTR_FORK, 0);
+ return 0;
+ }
+ if (error)
+ return error;
+ }
+
+ if (S_ISDIR(VFS_I(sc->ip)->i_mode)) {
+ if (sc->ip == sc->mp->m_rootip)
+ pp->pptrs_found++;
+
+ if (VFS_I(sc->ip)->i_nlink == 0 && pp->pptrs_found > 0)
+ xchk_ino_set_corrupt(sc, sc->ip->i_ino);
+ else if (VFS_I(sc->ip)->i_nlink > 0 &&
+ pp->pptrs_found == 0)
+ xchk_ino_set_corrupt(sc, sc->ip->i_ino);
+ } else {
+ if (VFS_I(sc->ip)->i_nlink != pp->pptrs_found)
+ xchk_ino_set_corrupt(sc, sc->ip->i_ino);
+ }
+
+ return 0;
+}
+
+/* Check parent pointers of a file. */
+STATIC int
+xchk_parent_pptr(
+ struct xfs_scrub *sc)
+{
+ struct xchk_pptrs *pp;
+ char *descr;
+ int error;
+
+ pp = kvzalloc(sizeof(struct xchk_pptrs), XCHK_GFP_FLAGS);
+ if (!pp)
+ return -ENOMEM;
+ pp->sc = sc;
+ pp->xname.name = pp->namebuf;
+
+ /*
+ * Set up some staging memory for parent pointers that we can't check
+ * due to locking contention.
+ */
+ descr = xchk_xfile_ino_descr(sc, "slow parent pointer entries");
+ error = xfarray_create(descr, 0, sizeof(struct xchk_pptr),
+ &pp->pptr_entries);
+ kfree(descr);
+ if (error)
+ goto out_pp;
+
+ descr = xchk_xfile_ino_descr(sc, "slow parent pointer names");
+ error = xfblob_create(descr, &pp->pptr_names);
+ kfree(descr);
+ if (error)
+ goto out_entries;
+
+ error = xchk_xattr_walk(sc, sc->ip, xchk_parent_scan_attr, NULL, pp);
+ if (error == -ECANCELED) {
+ error = 0;
+ goto out_names;
+ }
+ if (error)
+ goto out_names;
+
+ error = xchk_parent_finish_slow_pptrs(pp);
+ if (error == -ETIMEDOUT) {
+ /* Couldn't grab a lock, scrub was marked incomplete */
+ error = 0;
+ goto out_names;
+ }
+ if (error)
+ goto out_names;
+
+ if (pp->sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT)
+ goto out_names;
+
+ /*
+ * For subdirectories, make sure the dotdot entry references the same
+ * inode as the parent pointers.
+ *
+ * If we're scanning a /consistent/ directory, there should only be
+ * one parent pointer, and it should point to the same directory as
+ * the dotdot entry.
+ *
+ * However, a corrupt directory tree might feature a subdirectory with
+ * multiple parents. The directory loop scanner is responsible for
+ * correcting that kind of problem, so for now we only validate that
+ * the dotdot entry matches /one/ of the parents.
+ */
+ if (S_ISDIR(VFS_I(sc->ip)->i_mode)) {
+ error = xchk_parent_pptr_and_dotdot(pp);
+ if (error)
+ goto out_names;
+ }
+
+ if (pp->sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT)
+ goto out_pp;
+
+ /*
+ * Complain if the number of parent pointers doesn't match the link
+ * count. This could be a sign of missing parent pointers (or an
+ * incorrect link count).
+ */
+ error = xchk_parent_count_pptrs(pp);
+ if (error)
+ goto out_names;
+
+out_names:
+ xfblob_destroy(pp->pptr_names);
+out_entries:
+ xfarray_destroy(pp->pptr_entries);
+out_pp:
+ kvfree(pp);
+ return error;
+}
+
/* Scrub a parent pointer. */
int
xchk_parent(
@@ -194,6 +828,9 @@ xchk_parent(
xfs_ino_t parent_ino;
int error = 0;
+ if (xfs_has_parent(mp))
+ return xchk_parent_pptr(sc);
+
/*
* If we're a directory, check that the '..' link points up to
* a directory that has one entry pointing to us.
@@ -237,3 +874,64 @@ xchk_parent(
return error;
}
+
+/*
+ * Decide if this file's extended attributes (and therefore its parent
+ * pointers) have been zapped to satisfy the inode and ifork verifiers.
+ * Checking and repairing should be postponed until the extended attribute
+ * structure is fixed.
+ */
+bool
+xchk_pptr_looks_zapped(
+ struct xfs_inode *ip)
+{
+ struct xfs_mount *mp = ip->i_mount;
+ struct inode *inode = VFS_I(ip);
+
+ ASSERT(xfs_has_parent(mp));
+
+ /*
+ * Temporary files that cannot be linked into the directory tree do not
+ * have attr forks because they cannot ever have parents.
+ */
+ if (inode->i_nlink == 0 && !(inode->i_state & I_LINKABLE))
+ return false;
+
+ /*
+ * Directory tree roots do not have parents, so the expected outcome
+ * of a parent pointer scan is always the empty set. It's safe to scan
+ * them even if the attr fork was zapped.
+ */
+ if (ip == mp->m_rootip)
+ return false;
+
+ /*
+ * Metadata inodes are all rooted in the superblock and do not have
+ * any parents. Hence the attr fork will not be initialized, but
+ * there are no parent pointers that might have been zapped.
+ */
+ if (xfs_is_metadata_inode(ip))
+ return false;
+
+ /*
+ * Linked and linkable non-rootdir files should always have an
+ * attribute fork because that is where parent pointers are
+ * stored. If the fork is absent, something is amiss.
+ */
+ if (!xfs_inode_has_attr_fork(ip))
+ return true;
+
+ /* Repair zapped this file's attr fork a short time ago */
+ if (xfs_ifork_zapped(ip, XFS_ATTR_FORK))
+ return true;
+
+ /*
+ * If the dinode repair found a bad attr fork, it will reset the fork
+ * to extents format with zero records and wait for the bmapbta
+ * scrubber to reconstruct the block mappings. The extended attribute
+ * structure always contain some content when parent pointers are
+ * enabled, so this is a clear sign of a zapped attr fork.
+ */
+ return ip->i_af.if_format == XFS_DINODE_FMT_EXTENTS &&
+ ip->i_af.if_nextents == 0;
+}
diff --git a/fs/xfs/scrub/parent_repair.c b/fs/xfs/scrub/parent_repair.c
new file mode 100644
index 0000000000..7b42b7f65a
--- /dev/null
+++ b/fs/xfs/scrub/parent_repair.c
@@ -0,0 +1,1612 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Copyright (c) 2020-2024 Oracle. All Rights Reserved.
+ * Author: Darrick J. Wong <djwong@kernel.org>
+ */
+#include "xfs.h"
+#include "xfs_fs.h"
+#include "xfs_shared.h"
+#include "xfs_format.h"
+#include "xfs_trans_resv.h"
+#include "xfs_mount.h"
+#include "xfs_defer.h"
+#include "xfs_bit.h"
+#include "xfs_log_format.h"
+#include "xfs_trans.h"
+#include "xfs_sb.h"
+#include "xfs_inode.h"
+#include "xfs_icache.h"
+#include "xfs_da_format.h"
+#include "xfs_da_btree.h"
+#include "xfs_dir2.h"
+#include "xfs_bmap_btree.h"
+#include "xfs_dir2_priv.h"
+#include "xfs_trans_space.h"
+#include "xfs_health.h"
+#include "xfs_exchmaps.h"
+#include "xfs_parent.h"
+#include "xfs_attr.h"
+#include "xfs_bmap.h"
+#include "xfs_ag.h"
+#include "scrub/xfs_scrub.h"
+#include "scrub/scrub.h"
+#include "scrub/common.h"
+#include "scrub/trace.h"
+#include "scrub/repair.h"
+#include "scrub/iscan.h"
+#include "scrub/findparent.h"
+#include "scrub/readdir.h"
+#include "scrub/tempfile.h"
+#include "scrub/tempexch.h"
+#include "scrub/orphanage.h"
+#include "scrub/xfile.h"
+#include "scrub/xfarray.h"
+#include "scrub/xfblob.h"
+#include "scrub/attr_repair.h"
+#include "scrub/listxattr.h"
+
+/*
+ * Repairing The Directory Parent Pointer
+ * ======================================
+ *
+ * Currently, only directories support parent pointers (in the form of '..'
+ * entries), so we simply scan the filesystem and update the '..' entry.
+ *
+ * Note that because the only parent pointer is the dotdot entry, we won't
+ * touch an unhealthy directory, since the directory repair code is perfectly
+ * capable of rebuilding a directory with the proper parent inode.
+ *
+ * See the section on locking issues in dir_repair.c for more information about
+ * conflicts with the VFS. The findparent code wll keep our incore parent
+ * inode up to date.
+ *
+ * If parent pointers are enabled, we instead reconstruct the parent pointer
+ * information by visiting every directory entry of every directory in the
+ * system and translating the relevant dirents into parent pointers. In this
+ * case, it is advantageous to stash all parent pointers created from dirents
+ * from a single parent file before replaying them into the temporary file. To
+ * save memory, the live filesystem scan reuses the findparent object. Parent
+ * pointer repair chooses either directory scanning or findparent, but not
+ * both.
+ *
+ * When salvaging completes, the remaining stashed entries are replayed to the
+ * temporary file. All non-parent pointer extended attributes are copied to
+ * the temporary file's extended attributes. An atomic file mapping exchange
+ * is used to commit the new xattr blocks to the file being repaired. This
+ * will disrupt attrmulti cursors.
+ */
+
+/* Create a parent pointer in the tempfile. */
+#define XREP_PPTR_ADD (1)
+
+/* Remove a parent pointer from the tempfile. */
+#define XREP_PPTR_REMOVE (2)
+
+/* A stashed parent pointer update. */
+struct xrep_pptr {
+ /* Cookie for retrieval of the pptr name. */
+ xfblob_cookie name_cookie;
+
+ /* Parent pointer record. */
+ struct xfs_parent_rec pptr_rec;
+
+ /* Length of the pptr name. */
+ uint8_t namelen;
+
+ /* XREP_PPTR_{ADD,REMOVE} */
+ uint8_t action;
+};
+
+/*
+ * Stash up to 8 pages of recovered parent pointers in pptr_recs and
+ * pptr_names before we write them to the temp file.
+ */
+#define XREP_PARENT_MAX_STASH_BYTES (PAGE_SIZE * 8)
+
+struct xrep_parent {
+ struct xfs_scrub *sc;
+
+ /* Fixed-size array of xrep_pptr structures. */
+ struct xfarray *pptr_recs;
+
+ /* Blobs containing parent pointer names. */
+ struct xfblob *pptr_names;
+
+ /* xattr keys */
+ struct xfarray *xattr_records;
+
+ /* xattr values */
+ struct xfblob *xattr_blobs;
+
+ /* Scratch buffers for saving extended attributes */
+ unsigned char *xattr_name;
+ void *xattr_value;
+ unsigned int xattr_value_sz;
+
+ /*
+ * Information used to exchange the attr fork mappings, if the fs
+ * supports parent pointers.
+ */
+ struct xrep_tempexch tx;
+
+ /*
+ * Information used to scan the filesystem to find the inumber of the
+ * dotdot entry for this directory. On filesystems without parent
+ * pointers, we use the findparent_* functions on this object and
+ * access only the parent_ino field directly.
+ *
+ * When parent pointers are enabled, the directory entry scanner uses
+ * the iscan, hooks, and lock fields of this object directly.
+ * @pscan.lock coordinates access to pptr_recs, pptr_names, pptr, and
+ * pptr_scratch. This reduces the memory requirements of this
+ * structure.
+ *
+ * The lock also controls access to xattr_records and xattr_blobs(?)
+ */
+ struct xrep_parent_scan_info pscan;
+
+ /* Orphanage reparenting request. */
+ struct xrep_adoption adoption;
+
+ /* Directory entry name, plus the trailing null. */
+ struct xfs_name xname;
+ unsigned char namebuf[MAXNAMELEN];
+
+ /* Scratch buffer for scanning pptr xattrs */
+ struct xfs_da_args pptr_args;
+
+ /* Have we seen any live updates of parent pointers recently? */
+ bool saw_pptr_updates;
+
+ /* Number of parents we found after all other repairs */
+ unsigned long long parents;
+};
+
+struct xrep_parent_xattr {
+ /* Cookie for retrieval of the xattr name. */
+ xfblob_cookie name_cookie;
+
+ /* Cookie for retrieval of the xattr value. */
+ xfblob_cookie value_cookie;
+
+ /* XFS_ATTR_* flags */
+ int flags;
+
+ /* Length of the value and name. */
+ uint32_t valuelen;
+ uint16_t namelen;
+};
+
+/*
+ * Stash up to 8 pages of attrs in xattr_records/xattr_blobs before we write
+ * them to the temp file.
+ */
+#define XREP_PARENT_XATTR_MAX_STASH_BYTES (PAGE_SIZE * 8)
+
+/* Tear down all the incore stuff we created. */
+static void
+xrep_parent_teardown(
+ struct xrep_parent *rp)
+{
+ xrep_findparent_scan_teardown(&rp->pscan);
+ kvfree(rp->xattr_name);
+ rp->xattr_name = NULL;
+ kvfree(rp->xattr_value);
+ rp->xattr_value = NULL;
+ if (rp->xattr_blobs)
+ xfblob_destroy(rp->xattr_blobs);
+ rp->xattr_blobs = NULL;
+ if (rp->xattr_records)
+ xfarray_destroy(rp->xattr_records);
+ rp->xattr_records = NULL;
+ if (rp->pptr_names)
+ xfblob_destroy(rp->pptr_names);
+ rp->pptr_names = NULL;
+ if (rp->pptr_recs)
+ xfarray_destroy(rp->pptr_recs);
+ rp->pptr_recs = NULL;
+}
+
+/* Set up for a parent repair. */
+int
+xrep_setup_parent(
+ struct xfs_scrub *sc)
+{
+ struct xrep_parent *rp;
+ int error;
+
+ xchk_fsgates_enable(sc, XCHK_FSGATES_DIRENTS);
+
+ rp = kvzalloc(sizeof(struct xrep_parent), XCHK_GFP_FLAGS);
+ if (!rp)
+ return -ENOMEM;
+ rp->sc = sc;
+ rp->xname.name = rp->namebuf;
+ sc->buf = rp;
+
+ error = xrep_tempfile_create(sc, S_IFREG);
+ if (error)
+ return error;
+
+ return xrep_orphanage_try_create(sc);
+}
+
+/*
+ * Scan all files in the filesystem for a child dirent that we can turn into
+ * the dotdot entry for this directory.
+ */
+STATIC int
+xrep_parent_find_dotdot(
+ struct xrep_parent *rp)
+{
+ struct xfs_scrub *sc = rp->sc;
+ xfs_ino_t ino;
+ unsigned int sick, checked;
+ int error;
+
+ /*
+ * Avoid sick directories. There shouldn't be anyone else clearing the
+ * directory's sick status.
+ */
+ xfs_inode_measure_sickness(sc->ip, &sick, &checked);
+ if (sick & XFS_SICK_INO_DIR)
+ return -EFSCORRUPTED;
+
+ ino = xrep_findparent_self_reference(sc);
+ if (ino != NULLFSINO) {
+ xrep_findparent_scan_finish_early(&rp->pscan, ino);
+ return 0;
+ }
+
+ /*
+ * Drop the ILOCK on this directory so that we can scan for the dotdot
+ * entry. Figure out who is going to be the parent of this directory,
+ * then retake the ILOCK so that we can salvage directory entries.
+ */
+ xchk_iunlock(sc, XFS_ILOCK_EXCL);
+
+ /* Does the VFS dcache have an answer for us? */
+ ino = xrep_findparent_from_dcache(sc);
+ if (ino != NULLFSINO) {
+ error = xrep_findparent_confirm(sc, &ino);
+ if (!error && ino != NULLFSINO) {
+ xrep_findparent_scan_finish_early(&rp->pscan, ino);
+ goto out_relock;
+ }
+ }
+
+ /* Scan the entire filesystem for a parent. */
+ error = xrep_findparent_scan(&rp->pscan);
+out_relock:
+ xchk_ilock(sc, XFS_ILOCK_EXCL);
+
+ return error;
+}
+
+/*
+ * Add this stashed incore parent pointer to the temporary file.
+ * The caller must hold the tempdir's IOLOCK, must not hold any ILOCKs, and
+ * must not be in transaction context.
+ */
+STATIC int
+xrep_parent_replay_update(
+ struct xrep_parent *rp,
+ const struct xfs_name *xname,
+ struct xrep_pptr *pptr)
+{
+ struct xfs_scrub *sc = rp->sc;
+
+ switch (pptr->action) {
+ case XREP_PPTR_ADD:
+ /* Create parent pointer. */
+ trace_xrep_parent_replay_parentadd(sc->tempip, xname,
+ &pptr->pptr_rec);
+
+ return xfs_parent_set(sc->tempip, sc->ip->i_ino, xname,
+ &pptr->pptr_rec, &rp->pptr_args);
+ case XREP_PPTR_REMOVE:
+ /* Remove parent pointer. */
+ trace_xrep_parent_replay_parentremove(sc->tempip, xname,
+ &pptr->pptr_rec);
+
+ return xfs_parent_unset(sc->tempip, sc->ip->i_ino, xname,
+ &pptr->pptr_rec, &rp->pptr_args);
+ }
+
+ ASSERT(0);
+ return -EIO;
+}
+
+/*
+ * Flush stashed parent pointer updates that have been recorded by the scanner.
+ * This is done to reduce the memory requirements of the parent pointer
+ * rebuild, since files can have a lot of hardlinks and the fs can be busy.
+ *
+ * Caller must not hold transactions or ILOCKs. Caller must hold the tempfile
+ * IOLOCK.
+ */
+STATIC int
+xrep_parent_replay_updates(
+ struct xrep_parent *rp)
+{
+ xfarray_idx_t array_cur;
+ int error;
+
+ mutex_lock(&rp->pscan.lock);
+ foreach_xfarray_idx(rp->pptr_recs, array_cur) {
+ struct xrep_pptr pptr;
+
+ error = xfarray_load(rp->pptr_recs, array_cur, &pptr);
+ if (error)
+ goto out_unlock;
+
+ error = xfblob_loadname(rp->pptr_names, pptr.name_cookie,
+ &rp->xname, pptr.namelen);
+ if (error)
+ goto out_unlock;
+ rp->xname.len = pptr.namelen;
+ mutex_unlock(&rp->pscan.lock);
+
+ error = xrep_parent_replay_update(rp, &rp->xname, &pptr);
+ if (error)
+ return error;
+
+ mutex_lock(&rp->pscan.lock);
+ }
+
+ /* Empty out both arrays now that we've added the entries. */
+ xfarray_truncate(rp->pptr_recs);
+ xfblob_truncate(rp->pptr_names);
+ mutex_unlock(&rp->pscan.lock);
+ return 0;
+out_unlock:
+ mutex_unlock(&rp->pscan.lock);
+ return error;
+}
+
+/*
+ * Remember that we want to create a parent pointer in the tempfile. These
+ * stashed actions will be replayed later.
+ */
+STATIC int
+xrep_parent_stash_parentadd(
+ struct xrep_parent *rp,
+ const struct xfs_name *name,
+ const struct xfs_inode *dp)
+{
+ struct xrep_pptr pptr = {
+ .action = XREP_PPTR_ADD,
+ .namelen = name->len,
+ };
+ int error;
+
+ trace_xrep_parent_stash_parentadd(rp->sc->tempip, dp, name);
+
+ xfs_inode_to_parent_rec(&pptr.pptr_rec, dp);
+ error = xfblob_storename(rp->pptr_names, &pptr.name_cookie, name);
+ if (error)
+ return error;
+
+ return xfarray_append(rp->pptr_recs, &pptr);
+}
+
+/*
+ * Remember that we want to remove a parent pointer from the tempfile. These
+ * stashed actions will be replayed later.
+ */
+STATIC int
+xrep_parent_stash_parentremove(
+ struct xrep_parent *rp,
+ const struct xfs_name *name,
+ const struct xfs_inode *dp)
+{
+ struct xrep_pptr pptr = {
+ .action = XREP_PPTR_REMOVE,
+ .namelen = name->len,
+ };
+ int error;
+
+ trace_xrep_parent_stash_parentremove(rp->sc->tempip, dp, name);
+
+ xfs_inode_to_parent_rec(&pptr.pptr_rec, dp);
+ error = xfblob_storename(rp->pptr_names, &pptr.name_cookie, name);
+ if (error)
+ return error;
+
+ return xfarray_append(rp->pptr_recs, &pptr);
+}
+
+/*
+ * Examine an entry of a directory. If this dirent leads us back to the file
+ * whose parent pointers we're rebuilding, add a pptr to the temporary
+ * directory.
+ */
+STATIC int
+xrep_parent_scan_dirent(
+ struct xfs_scrub *sc,
+ struct xfs_inode *dp,
+ xfs_dir2_dataptr_t dapos,
+ const struct xfs_name *name,
+ xfs_ino_t ino,
+ void *priv)
+{
+ struct xrep_parent *rp = priv;
+ int error;
+
+ /* Dirent doesn't point to this directory. */
+ if (ino != rp->sc->ip->i_ino)
+ return 0;
+
+ /* No weird looking names. */
+ if (name->len == 0 || !xfs_dir2_namecheck(name->name, name->len))
+ return -EFSCORRUPTED;
+
+ /* No mismatching ftypes. */
+ if (name->type != xfs_mode_to_ftype(VFS_I(sc->ip)->i_mode))
+ return -EFSCORRUPTED;
+
+ /* Don't pick up dot or dotdot entries; we only want child dirents. */
+ if (xfs_dir2_samename(name, &xfs_name_dotdot) ||
+ xfs_dir2_samename(name, &xfs_name_dot))
+ return 0;
+
+ /*
+ * Transform this dirent into a parent pointer and queue it for later
+ * addition to the temporary file.
+ */
+ mutex_lock(&rp->pscan.lock);
+ error = xrep_parent_stash_parentadd(rp, name, dp);
+ mutex_unlock(&rp->pscan.lock);
+ return error;
+}
+
+/*
+ * Decide if we want to look for dirents in this directory. Skip the file
+ * being repaired and any files being used to stage repairs.
+ */
+static inline bool
+xrep_parent_want_scan(
+ struct xrep_parent *rp,
+ const struct xfs_inode *ip)
+{
+ return ip != rp->sc->ip && !xrep_is_tempfile(ip);
+}
+
+/*
+ * Take ILOCK on a file that we want to scan.
+ *
+ * Select ILOCK_EXCL if the file is a directory with an unloaded data bmbt.
+ * Otherwise, take ILOCK_SHARED.
+ */
+static inline unsigned int
+xrep_parent_scan_ilock(
+ struct xrep_parent *rp,
+ struct xfs_inode *ip)
+{
+ uint lock_mode = XFS_ILOCK_SHARED;
+
+ /* Still need to take the shared ILOCK to advance the iscan cursor. */
+ if (!xrep_parent_want_scan(rp, ip))
+ goto lock;
+
+ if (S_ISDIR(VFS_I(ip)->i_mode) && xfs_need_iread_extents(&ip->i_df)) {
+ lock_mode = XFS_ILOCK_EXCL;
+ goto lock;
+ }
+
+lock:
+ xfs_ilock(ip, lock_mode);
+ return lock_mode;
+}
+
+/*
+ * Scan this file for relevant child dirents that point to the file whose
+ * parent pointers we're rebuilding.
+ */
+STATIC int
+xrep_parent_scan_file(
+ struct xrep_parent *rp,
+ struct xfs_inode *ip)
+{
+ unsigned int lock_mode;
+ int error = 0;
+
+ lock_mode = xrep_parent_scan_ilock(rp, ip);
+
+ if (!xrep_parent_want_scan(rp, ip))
+ goto scan_done;
+
+ if (S_ISDIR(VFS_I(ip)->i_mode)) {
+ /*
+ * If the directory looks as though it has been zapped by the
+ * inode record repair code, we cannot scan for child dirents.
+ */
+ if (xchk_dir_looks_zapped(ip)) {
+ error = -EBUSY;
+ goto scan_done;
+ }
+
+ error = xchk_dir_walk(rp->sc, ip, xrep_parent_scan_dirent, rp);
+ if (error)
+ goto scan_done;
+ }
+
+scan_done:
+ xchk_iscan_mark_visited(&rp->pscan.iscan, ip);
+ xfs_iunlock(ip, lock_mode);
+ return error;
+}
+
+/* Decide if we've stashed too much pptr data in memory. */
+static inline bool
+xrep_parent_want_flush_stashed(
+ struct xrep_parent *rp)
+{
+ unsigned long long bytes;
+
+ bytes = xfarray_bytes(rp->pptr_recs) + xfblob_bytes(rp->pptr_names);
+ return bytes > XREP_PARENT_MAX_STASH_BYTES;
+}
+
+/*
+ * Scan all directories in the filesystem to look for dirents that we can turn
+ * into parent pointers.
+ */
+STATIC int
+xrep_parent_scan_dirtree(
+ struct xrep_parent *rp)
+{
+ struct xfs_scrub *sc = rp->sc;
+ struct xfs_inode *ip;
+ int error;
+
+ /*
+ * Filesystem scans are time consuming. Drop the file ILOCK and all
+ * other resources for the duration of the scan and hope for the best.
+ * The live update hooks will keep our scan information up to date.
+ */
+ xchk_trans_cancel(sc);
+ if (sc->ilock_flags & (XFS_ILOCK_SHARED | XFS_ILOCK_EXCL))
+ xchk_iunlock(sc, sc->ilock_flags & (XFS_ILOCK_SHARED |
+ XFS_ILOCK_EXCL));
+ error = xchk_trans_alloc_empty(sc);
+ if (error)
+ return error;
+
+ while ((error = xchk_iscan_iter(&rp->pscan.iscan, &ip)) == 1) {
+ bool flush;
+
+ error = xrep_parent_scan_file(rp, ip);
+ xchk_irele(sc, ip);
+ if (error)
+ break;
+
+ /* Flush stashed pptr updates to constrain memory usage. */
+ mutex_lock(&rp->pscan.lock);
+ flush = xrep_parent_want_flush_stashed(rp);
+ mutex_unlock(&rp->pscan.lock);
+ if (flush) {
+ xchk_trans_cancel(sc);
+
+ error = xrep_tempfile_iolock_polled(sc);
+ if (error)
+ break;
+
+ error = xrep_parent_replay_updates(rp);
+ xrep_tempfile_iounlock(sc);
+ if (error)
+ break;
+
+ error = xchk_trans_alloc_empty(sc);
+ if (error)
+ break;
+ }
+
+ if (xchk_should_terminate(sc, &error))
+ break;
+ }
+ xchk_iscan_iter_finish(&rp->pscan.iscan);
+ if (error) {
+ /*
+ * If we couldn't grab an inode that was busy with a state
+ * change, change the error code so that we exit to userspace
+ * as quickly as possible.
+ */
+ if (error == -EBUSY)
+ return -ECANCELED;
+ return error;
+ }
+
+ /*
+ * Retake sc->ip's ILOCK now that we're done flushing stashed parent
+ * pointers. We end this function with an empty transaction and the
+ * ILOCK.
+ */
+ xchk_ilock(rp->sc, XFS_ILOCK_EXCL);
+ return 0;
+}
+
+/*
+ * Capture dirent updates being made by other threads which are relevant to the
+ * file being repaired.
+ */
+STATIC int
+xrep_parent_live_update(
+ struct notifier_block *nb,
+ unsigned long action,
+ void *data)
+{
+ struct xfs_dir_update_params *p = data;
+ struct xrep_parent *rp;
+ struct xfs_scrub *sc;
+ int error;
+
+ rp = container_of(nb, struct xrep_parent, pscan.dhook.dirent_hook.nb);
+ sc = rp->sc;
+
+ /*
+ * This thread updated a dirent that points to the file that we're
+ * repairing, so stash the update for replay against the temporary
+ * file.
+ */
+ if (p->ip->i_ino == sc->ip->i_ino &&
+ xchk_iscan_want_live_update(&rp->pscan.iscan, p->dp->i_ino)) {
+ mutex_lock(&rp->pscan.lock);
+ if (p->delta > 0)
+ error = xrep_parent_stash_parentadd(rp, p->name, p->dp);
+ else
+ error = xrep_parent_stash_parentremove(rp, p->name,
+ p->dp);
+ if (!error)
+ rp->saw_pptr_updates = true;
+ mutex_unlock(&rp->pscan.lock);
+ if (error)
+ goto out_abort;
+ }
+
+ return NOTIFY_DONE;
+out_abort:
+ xchk_iscan_abort(&rp->pscan.iscan);
+ return NOTIFY_DONE;
+}
+
+/* Reset a directory's dotdot entry, if needed. */
+STATIC int
+xrep_parent_reset_dotdot(
+ struct xrep_parent *rp)
+{
+ struct xfs_scrub *sc = rp->sc;
+ xfs_ino_t ino;
+ unsigned int spaceres;
+ int error = 0;
+
+ ASSERT(sc->ilock_flags & XFS_ILOCK_EXCL);
+
+ error = xchk_dir_lookup(sc, sc->ip, &xfs_name_dotdot, &ino);
+ if (error || ino == rp->pscan.parent_ino)
+ return error;
+
+ xfs_trans_ijoin(sc->tp, sc->ip, 0);
+
+ trace_xrep_parent_reset_dotdot(sc->ip, rp->pscan.parent_ino);
+
+ /*
+ * Reserve more space just in case we have to expand the dir. We're
+ * allowed to exceed quota to repair inconsistent metadata.
+ */
+ spaceres = xfs_rename_space_res(sc->mp, 0, false, xfs_name_dotdot.len,
+ false);
+ error = xfs_trans_reserve_more_inode(sc->tp, sc->ip, spaceres, 0,
+ true);
+ if (error)
+ return error;
+
+ error = xfs_dir_replace(sc->tp, sc->ip, &xfs_name_dotdot,
+ rp->pscan.parent_ino, spaceres);
+ if (error)
+ return error;
+
+ /*
+ * Roll transaction to detach the inode from the transaction but retain
+ * ILOCK_EXCL.
+ */
+ return xfs_trans_roll(&sc->tp);
+}
+
+/* Pass back the parent inumber if this a parent pointer */
+STATIC int
+xrep_parent_lookup_pptr(
+ struct xfs_scrub *sc,
+ struct xfs_inode *ip,
+ unsigned int attr_flags,
+ const unsigned char *name,
+ unsigned int namelen,
+ const void *value,
+ unsigned int valuelen,
+ void *priv)
+{
+ xfs_ino_t *inop = priv;
+ xfs_ino_t parent_ino;
+ int error;
+
+ if (!(attr_flags & XFS_ATTR_PARENT))
+ return 0;
+
+ error = xfs_parent_from_attr(sc->mp, attr_flags, name, namelen, value,
+ valuelen, &parent_ino, NULL);
+ if (error)
+ return error;
+
+ *inop = parent_ino;
+ return -ECANCELED;
+}
+
+/*
+ * Find the first parent of the scrub target by walking parent pointers for
+ * the purpose of deciding if we're going to move it to the orphanage.
+ * We don't care if the attr fork is zapped.
+ */
+STATIC int
+xrep_parent_lookup_pptrs(
+ struct xfs_scrub *sc,
+ xfs_ino_t *inop)
+{
+ int error;
+
+ *inop = NULLFSINO;
+
+ error = xchk_xattr_walk(sc, sc->ip, xrep_parent_lookup_pptr, NULL,
+ inop);
+ if (error && error != -ECANCELED)
+ return error;
+ return 0;
+}
+
+/*
+ * Move the current file to the orphanage.
+ *
+ * Caller must hold IOLOCK_EXCL on @sc->ip, and no other inode locks. Upon
+ * successful return, the scrub transaction will have enough extra reservation
+ * to make the move; it will hold IOLOCK_EXCL and ILOCK_EXCL of @sc->ip and the
+ * orphanage; and both inodes will be ijoined.
+ */
+STATIC int
+xrep_parent_move_to_orphanage(
+ struct xrep_parent *rp)
+{
+ struct xfs_scrub *sc = rp->sc;
+ xfs_ino_t orig_parent, new_parent;
+ int error;
+
+ if (S_ISDIR(VFS_I(sc->ip)->i_mode)) {
+ /*
+ * We are about to drop the ILOCK on sc->ip to lock the
+ * orphanage and prepare for the adoption. Therefore, look up
+ * the old dotdot entry for sc->ip so that we can compare it
+ * after we re-lock sc->ip.
+ */
+ error = xchk_dir_lookup(sc, sc->ip, &xfs_name_dotdot,
+ &orig_parent);
+ if (error)
+ return error;
+ } else {
+ /*
+ * We haven't dropped the ILOCK since we committed the new
+ * xattr structure (and hence the new parent pointer records),
+ * which means that the file cannot have been moved in the
+ * directory tree, and there are no parents.
+ */
+ orig_parent = NULLFSINO;
+ }
+
+ /*
+ * Drop the ILOCK on the scrub target and commit the transaction.
+ * Adoption computes its own resource requirements and gathers the
+ * necessary components.
+ */
+ error = xrep_trans_commit(sc);
+ if (error)
+ return error;
+ xchk_iunlock(sc, XFS_ILOCK_EXCL);
+
+ /* If we can take the orphanage's iolock then we're ready to move. */
+ if (!xrep_orphanage_ilock_nowait(sc, XFS_IOLOCK_EXCL)) {
+ xchk_iunlock(sc, sc->ilock_flags);
+ error = xrep_orphanage_iolock_two(sc);
+ if (error)
+ return error;
+ }
+
+ /* Grab transaction and ILOCK the two files. */
+ error = xrep_adoption_trans_alloc(sc, &rp->adoption);
+ if (error)
+ return error;
+
+ error = xrep_adoption_compute_name(&rp->adoption, &rp->xname);
+ if (error)
+ return error;
+
+ /*
+ * Now that we've reacquired the ILOCK on sc->ip, look up the dotdot
+ * entry again. If the parent changed or the child was unlinked while
+ * the child directory was unlocked, we don't need to move the child to
+ * the orphanage after all. For a non-directory, we have to scan for
+ * the first parent pointer to see if one has been added.
+ */
+ if (S_ISDIR(VFS_I(sc->ip)->i_mode))
+ error = xchk_dir_lookup(sc, sc->ip, &xfs_name_dotdot,
+ &new_parent);
+ else
+ error = xrep_parent_lookup_pptrs(sc, &new_parent);
+ if (error)
+ return error;
+
+ /*
+ * Attach to the orphanage if we still have a linked directory and it
+ * hasn't been moved.
+ */
+ if (orig_parent == new_parent && VFS_I(sc->ip)->i_nlink > 0) {
+ error = xrep_adoption_move(&rp->adoption);
+ if (error)
+ return error;
+ }
+
+ /*
+ * Launder the scrub transaction so we can drop the orphanage ILOCK
+ * and IOLOCK. Return holding the scrub target's ILOCK and IOLOCK.
+ */
+ error = xrep_adoption_trans_roll(&rp->adoption);
+ if (error)
+ return error;
+
+ xrep_orphanage_iunlock(sc, XFS_ILOCK_EXCL);
+ xrep_orphanage_iunlock(sc, XFS_IOLOCK_EXCL);
+ return 0;
+}
+
+/* Ensure that the xattr value buffer is large enough. */
+STATIC int
+xrep_parent_alloc_xattr_value(
+ struct xrep_parent *rp,
+ size_t bufsize)
+{
+ void *new_val;
+
+ if (rp->xattr_value_sz >= bufsize)
+ return 0;
+
+ if (rp->xattr_value) {
+ kvfree(rp->xattr_value);
+ rp->xattr_value = NULL;
+ rp->xattr_value_sz = 0;
+ }
+
+ new_val = kvmalloc(bufsize, XCHK_GFP_FLAGS);
+ if (!new_val)
+ return -ENOMEM;
+
+ rp->xattr_value = new_val;
+ rp->xattr_value_sz = bufsize;
+ return 0;
+}
+
+/* Retrieve the (remote) value of a non-pptr xattr. */
+STATIC int
+xrep_parent_fetch_xattr_remote(
+ struct xrep_parent *rp,
+ struct xfs_inode *ip,
+ unsigned int attr_flags,
+ const unsigned char *name,
+ unsigned int namelen,
+ unsigned int valuelen)
+{
+ struct xfs_scrub *sc = rp->sc;
+ struct xfs_da_args args = {
+ .attr_filter = attr_flags & XFS_ATTR_NSP_ONDISK_MASK,
+ .geo = sc->mp->m_attr_geo,
+ .whichfork = XFS_ATTR_FORK,
+ .dp = ip,
+ .name = name,
+ .namelen = namelen,
+ .trans = sc->tp,
+ .valuelen = valuelen,
+ .owner = ip->i_ino,
+ };
+ int error;
+
+ /*
+ * If we need a larger value buffer, try to allocate one. If that
+ * fails, return with -EDEADLOCK to try harder.
+ */
+ error = xrep_parent_alloc_xattr_value(rp, valuelen);
+ if (error == -ENOMEM)
+ return -EDEADLOCK;
+ if (error)
+ return error;
+
+ args.value = rp->xattr_value;
+ xfs_attr_sethash(&args);
+ return xfs_attr_get_ilocked(&args);
+}
+
+/* Stash non-pptr attributes for later replay into the temporary file. */
+STATIC int
+xrep_parent_stash_xattr(
+ struct xfs_scrub *sc,
+ struct xfs_inode *ip,
+ unsigned int attr_flags,
+ const unsigned char *name,
+ unsigned int namelen,
+ const void *value,
+ unsigned int valuelen,
+ void *priv)
+{
+ struct xrep_parent_xattr key = {
+ .valuelen = valuelen,
+ .namelen = namelen,
+ .flags = attr_flags & XFS_ATTR_NSP_ONDISK_MASK,
+ };
+ struct xrep_parent *rp = priv;
+ int error;
+
+ if (attr_flags & (XFS_ATTR_INCOMPLETE | XFS_ATTR_PARENT))
+ return 0;
+
+ if (!value) {
+ error = xrep_parent_fetch_xattr_remote(rp, ip, attr_flags,
+ name, namelen, valuelen);
+ if (error)
+ return error;
+
+ value = rp->xattr_value;
+ }
+
+ trace_xrep_parent_stash_xattr(rp->sc->tempip, key.flags, (void *)name,
+ key.namelen, key.valuelen);
+
+ error = xfblob_store(rp->xattr_blobs, &key.name_cookie, name,
+ key.namelen);
+ if (error)
+ return error;
+
+ error = xfblob_store(rp->xattr_blobs, &key.value_cookie, value,
+ key.valuelen);
+ if (error)
+ return error;
+
+ return xfarray_append(rp->xattr_records, &key);
+}
+
+/* Insert one xattr key/value. */
+STATIC int
+xrep_parent_insert_xattr(
+ struct xrep_parent *rp,
+ const struct xrep_parent_xattr *key)
+{
+ struct xfs_da_args args = {
+ .dp = rp->sc->tempip,
+ .attr_filter = key->flags,
+ .namelen = key->namelen,
+ .valuelen = key->valuelen,
+ .owner = rp->sc->ip->i_ino,
+ .geo = rp->sc->mp->m_attr_geo,
+ .whichfork = XFS_ATTR_FORK,
+ .op_flags = XFS_DA_OP_OKNOENT,
+ };
+ int error;
+
+ ASSERT(!(key->flags & XFS_ATTR_PARENT));
+
+ /*
+ * Grab pointers to the scrub buffer so that we can use them to insert
+ * attrs into the temp file.
+ */
+ args.name = rp->xattr_name;
+ args.value = rp->xattr_value;
+
+ /*
+ * The attribute name is stored near the end of the in-core buffer,
+ * though we reserve one more byte to ensure null termination.
+ */
+ rp->xattr_name[XATTR_NAME_MAX] = 0;
+
+ error = xfblob_load(rp->xattr_blobs, key->name_cookie, rp->xattr_name,
+ key->namelen);
+ if (error)
+ return error;
+
+ error = xfblob_free(rp->xattr_blobs, key->name_cookie);
+ if (error)
+ return error;
+
+ error = xfblob_load(rp->xattr_blobs, key->value_cookie, args.value,
+ key->valuelen);
+ if (error)
+ return error;
+
+ error = xfblob_free(rp->xattr_blobs, key->value_cookie);
+ if (error)
+ return error;
+
+ rp->xattr_name[key->namelen] = 0;
+
+ trace_xrep_parent_insert_xattr(rp->sc->tempip, key->flags,
+ rp->xattr_name, key->namelen, key->valuelen);
+
+ xfs_attr_sethash(&args);
+ return xfs_attr_set(&args, XFS_ATTRUPDATE_UPSERT, false);
+}
+
+/*
+ * Periodically flush salvaged attributes to the temporary file. This is done
+ * to reduce the memory requirements of the xattr rebuild because files can
+ * contain millions of attributes.
+ */
+STATIC int
+xrep_parent_flush_xattrs(
+ struct xrep_parent *rp)
+{
+ xfarray_idx_t array_cur;
+ int error;
+
+ /*
+ * Entering this function, the scrub context has a reference to the
+ * inode being repaired, the temporary file, and the empty scrub
+ * transaction that we created for the xattr scan. We hold ILOCK_EXCL
+ * on the inode being repaired.
+ *
+ * To constrain kernel memory use, we occasionally flush salvaged
+ * xattrs from the xfarray and xfblob structures into the temporary
+ * file in preparation for exchanging the xattr structures at the end.
+ * Updating the temporary file requires a transaction, so we commit the
+ * scrub transaction and drop the ILOCK so that xfs_attr_set can
+ * allocate whatever transaction it wants.
+ *
+ * We still hold IOLOCK_EXCL on the inode being repaired, which
+ * prevents anyone from adding xattrs (or parent pointers) while we're
+ * flushing.
+ */
+ xchk_trans_cancel(rp->sc);
+ xchk_iunlock(rp->sc, XFS_ILOCK_EXCL);
+
+ /*
+ * Take the IOLOCK of the temporary file while we modify xattrs. This
+ * isn't strictly required because the temporary file is never revealed
+ * to userspace, but we follow the same locking rules. We still hold
+ * sc->ip's IOLOCK.
+ */
+ error = xrep_tempfile_iolock_polled(rp->sc);
+ if (error)
+ return error;
+
+ /* Add all the salvaged attrs to the temporary file. */
+ foreach_xfarray_idx(rp->xattr_records, array_cur) {
+ struct xrep_parent_xattr key;
+
+ error = xfarray_load(rp->xattr_records, array_cur, &key);
+ if (error)
+ return error;
+
+ error = xrep_parent_insert_xattr(rp, &key);
+ if (error)
+ return error;
+ }
+
+ /* Empty out both arrays now that we've added the entries. */
+ xfarray_truncate(rp->xattr_records);
+ xfblob_truncate(rp->xattr_blobs);
+
+ xrep_tempfile_iounlock(rp->sc);
+
+ /* Recreate the empty transaction and relock the inode. */
+ error = xchk_trans_alloc_empty(rp->sc);
+ if (error)
+ return error;
+ xchk_ilock(rp->sc, XFS_ILOCK_EXCL);
+ return 0;
+}
+
+/* Decide if we've stashed too much xattr data in memory. */
+static inline bool
+xrep_parent_want_flush_xattrs(
+ struct xrep_parent *rp)
+{
+ unsigned long long bytes;
+
+ bytes = xfarray_bytes(rp->xattr_records) +
+ xfblob_bytes(rp->xattr_blobs);
+ return bytes > XREP_PARENT_XATTR_MAX_STASH_BYTES;
+}
+
+/* Flush staged attributes to the temporary file if we're over the limit. */
+STATIC int
+xrep_parent_try_flush_xattrs(
+ struct xfs_scrub *sc,
+ void *priv)
+{
+ struct xrep_parent *rp = priv;
+ int error;
+
+ if (!xrep_parent_want_flush_xattrs(rp))
+ return 0;
+
+ error = xrep_parent_flush_xattrs(rp);
+ if (error)
+ return error;
+
+ /*
+ * If there were any parent pointer updates to the xattr structure
+ * while we dropped the ILOCK, the xattr structure is now stale.
+ * Signal to the attr copy process that we need to start over, but
+ * this time without opportunistic attr flushing.
+ *
+ * This is unlikely to happen, so we're ok with restarting the copy.
+ */
+ mutex_lock(&rp->pscan.lock);
+ if (rp->saw_pptr_updates)
+ error = -ESTALE;
+ mutex_unlock(&rp->pscan.lock);
+ return error;
+}
+
+/* Copy all the non-pptr extended attributes into the temporary file. */
+STATIC int
+xrep_parent_copy_xattrs(
+ struct xrep_parent *rp)
+{
+ struct xfs_scrub *sc = rp->sc;
+ int error;
+
+ /*
+ * Clear the pptr updates flag. We hold sc->ip ILOCKed, so there
+ * can't be any parent pointer updates in progress.
+ */
+ mutex_lock(&rp->pscan.lock);
+ rp->saw_pptr_updates = false;
+ mutex_unlock(&rp->pscan.lock);
+
+ /* Copy xattrs, stopping periodically to flush the incore buffers. */
+ error = xchk_xattr_walk(sc, sc->ip, xrep_parent_stash_xattr,
+ xrep_parent_try_flush_xattrs, rp);
+ if (error && error != -ESTALE)
+ return error;
+
+ if (error == -ESTALE) {
+ /*
+ * The xattr copy collided with a parent pointer update.
+ * Restart the copy, but this time hold the ILOCK all the way
+ * to the end to lock out any directory parent pointer updates.
+ */
+ error = xchk_xattr_walk(sc, sc->ip, xrep_parent_stash_xattr,
+ NULL, rp);
+ if (error)
+ return error;
+ }
+
+ /* Flush any remaining stashed xattrs to the temporary file. */
+ if (xfarray_bytes(rp->xattr_records) == 0)
+ return 0;
+
+ return xrep_parent_flush_xattrs(rp);
+}
+
+/*
+ * Ensure that @sc->ip and @sc->tempip both have attribute forks before we head
+ * into the attr fork exchange transaction. All files on a filesystem with
+ * parent pointers must have an attr fork because the parent pointer code does
+ * not itself add attribute forks.
+ *
+ * Note: Unlinkable unlinked files don't need one, but the overhead of having
+ * an unnecessary attr fork is not justified by the additional code complexity
+ * that would be needed to track that state correctly.
+ */
+STATIC int
+xrep_parent_ensure_attr_fork(
+ struct xrep_parent *rp)
+{
+ struct xfs_scrub *sc = rp->sc;
+ int error;
+
+ error = xfs_attr_add_fork(sc->tempip,
+ sizeof(struct xfs_attr_sf_hdr), 1);
+ if (error)
+ return error;
+ return xfs_attr_add_fork(sc->ip, sizeof(struct xfs_attr_sf_hdr), 1);
+}
+
+/*
+ * Finish replaying stashed parent pointer updates, allocate a transaction for
+ * exchanging extent mappings, and take the ILOCKs of both files before we
+ * commit the new attribute structure.
+ */
+STATIC int
+xrep_parent_finalize_tempfile(
+ struct xrep_parent *rp)
+{
+ struct xfs_scrub *sc = rp->sc;
+ int error;
+
+ /*
+ * Repair relies on the ILOCK to quiesce all possible xattr updates.
+ * Replay all queued parent pointer updates into the tempfile before
+ * exchanging the contents, even if that means dropping the ILOCKs and
+ * the transaction.
+ */
+ do {
+ error = xrep_parent_replay_updates(rp);
+ if (error)
+ return error;
+
+ error = xrep_parent_ensure_attr_fork(rp);
+ if (error)
+ return error;
+
+ error = xrep_tempexch_trans_alloc(sc, XFS_ATTR_FORK, &rp->tx);
+ if (error)
+ return error;
+
+ if (xfarray_length(rp->pptr_recs) == 0)
+ break;
+
+ xchk_trans_cancel(sc);
+ xrep_tempfile_iunlock_both(sc);
+ } while (!xchk_should_terminate(sc, &error));
+ return error;
+}
+
+/*
+ * Replay all the stashed parent pointers into the temporary file, copy all
+ * the non-pptr xattrs from the file being repaired into the temporary file,
+ * and exchange the attr fork contents atomically.
+ */
+STATIC int
+xrep_parent_rebuild_pptrs(
+ struct xrep_parent *rp)
+{
+ struct xfs_scrub *sc = rp->sc;
+ xfs_ino_t parent_ino = NULLFSINO;
+ int error;
+
+ /*
+ * Copy non-ppttr xattrs from the file being repaired into the
+ * temporary file's xattr structure. We hold sc->ip's IOLOCK, which
+ * prevents setxattr/removexattr calls from occurring, but renames
+ * update the parent pointers without holding IOLOCK. If we detect
+ * stale attr structures, we restart the scan but only flush at the
+ * end.
+ */
+ error = xrep_parent_copy_xattrs(rp);
+ if (error)
+ return error;
+
+ /*
+ * Cancel the empty transaction that we used to walk and copy attrs,
+ * and drop the ILOCK so that we can take the IOLOCK on the temporary
+ * file. We still hold sc->ip's IOLOCK.
+ */
+ xchk_trans_cancel(sc);
+ xchk_iunlock(sc, XFS_ILOCK_EXCL);
+
+ error = xrep_tempfile_iolock_polled(sc);
+ if (error)
+ return error;
+
+ /*
+ * Allocate transaction, lock inodes, and make sure that we've replayed
+ * all the stashed pptr updates to the tempdir. After this point,
+ * we're ready to exchange the attr fork mappings.
+ */
+ error = xrep_parent_finalize_tempfile(rp);
+ if (error)
+ return error;
+
+ /* Last chance to abort before we start committing pptr fixes. */
+ if (xchk_should_terminate(sc, &error))
+ return error;
+
+ if (xchk_iscan_aborted(&rp->pscan.iscan))
+ return -ECANCELED;
+
+ /*
+ * Exchange the attr fork contents and junk the old attr fork contents,
+ * which are now in the tempfile.
+ */
+ error = xrep_xattr_swap(sc, &rp->tx);
+ if (error)
+ return error;
+ error = xrep_xattr_reset_tempfile_fork(sc);
+ if (error)
+ return error;
+
+ /*
+ * Roll to get a transaction without any inodes joined to it. Then we
+ * can drop the tempfile's ILOCK and IOLOCK before doing more work on
+ * the scrub target file.
+ */
+ error = xfs_trans_roll(&sc->tp);
+ if (error)
+ return error;
+ xrep_tempfile_iunlock(sc);
+ xrep_tempfile_iounlock(sc);
+
+ /*
+ * We've committed the new parent pointers. Find at least one parent
+ * so that we can decide if we're moving this file to the orphanage.
+ * For this purpose, root directories are their own parents.
+ */
+ if (sc->ip == sc->mp->m_rootip) {
+ xrep_findparent_scan_found(&rp->pscan, sc->ip->i_ino);
+ } else {
+ error = xrep_parent_lookup_pptrs(sc, &parent_ino);
+ if (error)
+ return error;
+ if (parent_ino != NULLFSINO)
+ xrep_findparent_scan_found(&rp->pscan, parent_ino);
+ }
+ return 0;
+}
+
+/*
+ * Commit the new parent pointer structure (currently only the dotdot entry) to
+ * the file that we're repairing.
+ */
+STATIC int
+xrep_parent_rebuild_tree(
+ struct xrep_parent *rp)
+{
+ int error;
+
+ if (xfs_has_parent(rp->sc->mp)) {
+ error = xrep_parent_rebuild_pptrs(rp);
+ if (error)
+ return error;
+ }
+
+ if (rp->pscan.parent_ino == NULLFSINO) {
+ if (xrep_orphanage_can_adopt(rp->sc))
+ return xrep_parent_move_to_orphanage(rp);
+ return -EFSCORRUPTED;
+ }
+
+ if (S_ISDIR(VFS_I(rp->sc->ip)->i_mode))
+ return xrep_parent_reset_dotdot(rp);
+
+ return 0;
+}
+
+/* Count the number of parent pointers. */
+STATIC int
+xrep_parent_count_pptr(
+ struct xfs_scrub *sc,
+ struct xfs_inode *ip,
+ unsigned int attr_flags,
+ const unsigned char *name,
+ unsigned int namelen,
+ const void *value,
+ unsigned int valuelen,
+ void *priv)
+{
+ struct xrep_parent *rp = priv;
+ int error;
+
+ if (!(attr_flags & XFS_ATTR_PARENT))
+ return 0;
+
+ error = xfs_parent_from_attr(sc->mp, attr_flags, name, namelen, value,
+ valuelen, NULL, NULL);
+ if (error)
+ return error;
+
+ rp->parents++;
+ return 0;
+}
+
+/*
+ * After all parent pointer rebuilding and adoption activity completes, reset
+ * the link count of this nondirectory, having scanned the fs to rebuild all
+ * parent pointers.
+ */
+STATIC int
+xrep_parent_set_nondir_nlink(
+ struct xrep_parent *rp)
+{
+ struct xfs_scrub *sc = rp->sc;
+ struct xfs_inode *ip = sc->ip;
+ struct xfs_perag *pag;
+ bool joined = false;
+ int error;
+
+ /* Count parent pointers so we can reset the file link count. */
+ rp->parents = 0;
+ error = xchk_xattr_walk(sc, ip, xrep_parent_count_pptr, NULL, rp);
+ if (error)
+ return error;
+
+ if (rp->parents > 0 && xfs_inode_on_unlinked_list(ip)) {
+ xfs_trans_ijoin(sc->tp, sc->ip, 0);
+ joined = true;
+
+ /*
+ * The file is on the unlinked list but we found parents.
+ * Remove the file from the unlinked list.
+ */
+ pag = xfs_perag_get(sc->mp, XFS_INO_TO_AGNO(sc->mp, ip->i_ino));
+ if (!pag) {
+ ASSERT(0);
+ return -EFSCORRUPTED;
+ }
+
+ error = xfs_iunlink_remove(sc->tp, pag, ip);
+ xfs_perag_put(pag);
+ if (error)
+ return error;
+ } else if (rp->parents == 0 && !xfs_inode_on_unlinked_list(ip)) {
+ xfs_trans_ijoin(sc->tp, sc->ip, 0);
+ joined = true;
+
+ /*
+ * The file is not on the unlinked list but we found no
+ * parents. Add the file to the unlinked list.
+ */
+ error = xfs_iunlink(sc->tp, ip);
+ if (error)
+ return error;
+ }
+
+ /* Set the correct link count. */
+ if (VFS_I(ip)->i_nlink != rp->parents) {
+ if (!joined) {
+ xfs_trans_ijoin(sc->tp, sc->ip, 0);
+ joined = true;
+ }
+
+ set_nlink(VFS_I(ip), min_t(unsigned long long, rp->parents,
+ XFS_NLINK_PINNED));
+ }
+
+ /* Log the inode to keep it moving forward if we dirtied anything. */
+ if (joined)
+ xfs_trans_log_inode(sc->tp, ip, XFS_ILOG_CORE);
+ return 0;
+}
+
+/* Set up the filesystem scan so we can look for parents. */
+STATIC int
+xrep_parent_setup_scan(
+ struct xrep_parent *rp)
+{
+ struct xfs_scrub *sc = rp->sc;
+ char *descr;
+ struct xfs_da_geometry *geo = sc->mp->m_attr_geo;
+ int max_len;
+ int error;
+
+ if (!xfs_has_parent(sc->mp))
+ return xrep_findparent_scan_start(sc, &rp->pscan);
+
+ /* Buffers for copying non-pptr attrs to the tempfile */
+ rp->xattr_name = kvmalloc(XATTR_NAME_MAX + 1, XCHK_GFP_FLAGS);
+ if (!rp->xattr_name)
+ return -ENOMEM;
+
+ /*
+ * Allocate enough memory to handle loading local attr values from the
+ * xfblob data while flushing stashed attrs to the temporary file.
+ * We only realloc the buffer when salvaging remote attr values, so
+ * TRY_HARDER means we allocate the maximal attr value size.
+ */
+ if (sc->flags & XCHK_TRY_HARDER)
+ max_len = XATTR_SIZE_MAX;
+ else
+ max_len = xfs_attr_leaf_entsize_local_max(geo->blksize);
+ error = xrep_parent_alloc_xattr_value(rp, max_len);
+ if (error)
+ goto out_xattr_name;
+
+ /* Set up some staging memory for logging parent pointer updates. */
+ descr = xchk_xfile_ino_descr(sc, "parent pointer entries");
+ error = xfarray_create(descr, 0, sizeof(struct xrep_pptr),
+ &rp->pptr_recs);
+ kfree(descr);
+ if (error)
+ goto out_xattr_value;
+
+ descr = xchk_xfile_ino_descr(sc, "parent pointer names");
+ error = xfblob_create(descr, &rp->pptr_names);
+ kfree(descr);
+ if (error)
+ goto out_recs;
+
+ /* Set up some storage for copying attrs before the mapping exchange */
+ descr = xchk_xfile_ino_descr(sc,
+ "parent pointer retained xattr entries");
+ error = xfarray_create(descr, 0, sizeof(struct xrep_parent_xattr),
+ &rp->xattr_records);
+ kfree(descr);
+ if (error)
+ goto out_names;
+
+ descr = xchk_xfile_ino_descr(sc,
+ "parent pointer retained xattr values");
+ error = xfblob_create(descr, &rp->xattr_blobs);
+ kfree(descr);
+ if (error)
+ goto out_attr_keys;
+
+ error = __xrep_findparent_scan_start(sc, &rp->pscan,
+ xrep_parent_live_update);
+ if (error)
+ goto out_attr_values;
+
+ return 0;
+
+out_attr_values:
+ xfblob_destroy(rp->xattr_blobs);
+ rp->xattr_blobs = NULL;
+out_attr_keys:
+ xfarray_destroy(rp->xattr_records);
+ rp->xattr_records = NULL;
+out_names:
+ xfblob_destroy(rp->pptr_names);
+ rp->pptr_names = NULL;
+out_recs:
+ xfarray_destroy(rp->pptr_recs);
+ rp->pptr_recs = NULL;
+out_xattr_value:
+ kvfree(rp->xattr_value);
+ rp->xattr_value = NULL;
+out_xattr_name:
+ kvfree(rp->xattr_name);
+ rp->xattr_name = NULL;
+ return error;
+}
+
+int
+xrep_parent(
+ struct xfs_scrub *sc)
+{
+ struct xrep_parent *rp = sc->buf;
+ int error;
+
+ /*
+ * When the parent pointers feature is enabled, repairs are committed
+ * by atomically committing a new xattr structure and reaping the old
+ * attr fork. Reaping requires rmap and exchange-range to be enabled.
+ */
+ if (xfs_has_parent(sc->mp)) {
+ if (!xfs_has_rmapbt(sc->mp))
+ return -EOPNOTSUPP;
+ if (!xfs_has_exchange_range(sc->mp))
+ return -EOPNOTSUPP;
+ }
+
+ error = xrep_parent_setup_scan(rp);
+ if (error)
+ return error;
+
+ if (xfs_has_parent(sc->mp))
+ error = xrep_parent_scan_dirtree(rp);
+ else
+ error = xrep_parent_find_dotdot(rp);
+ if (error)
+ goto out_teardown;
+
+ /* Last chance to abort before we start committing dotdot fixes. */
+ if (xchk_should_terminate(sc, &error))
+ goto out_teardown;
+
+ error = xrep_parent_rebuild_tree(rp);
+ if (error)
+ goto out_teardown;
+ if (xfs_has_parent(sc->mp) && !S_ISDIR(VFS_I(sc->ip)->i_mode)) {
+ error = xrep_parent_set_nondir_nlink(rp);
+ if (error)
+ goto out_teardown;
+ }
+
+ error = xrep_defer_finish(sc);
+
+out_teardown:
+ xrep_parent_teardown(rp);
+ return error;
+}
diff --git a/fs/xfs/scrub/quota_repair.c b/fs/xfs/scrub/quota_repair.c
index 0bab4c30cb..90cd1512bb 100644
--- a/fs/xfs/scrub/quota_repair.c
+++ b/fs/xfs/scrub/quota_repair.c
@@ -77,8 +77,6 @@ xrep_quota_item_fill_bmap_hole(
irec, &nmaps);
if (error)
return error;
- if (nmaps != 1)
- return -ENOSPC;
dq->q_blkno = XFS_FSB_TO_DADDR(mp, irec->br_startblock);
@@ -444,10 +442,6 @@ xrep_quota_data_fork(
XFS_BMAPI_CONVERT, 0, &nrec, &nmap);
if (error)
goto out;
- if (nmap != 1) {
- error = -ENOSPC;
- goto out;
- }
ASSERT(nrec.br_startoff == irec.br_startoff);
ASSERT(nrec.br_blockcount == irec.br_blockcount);
diff --git a/fs/xfs/scrub/readdir.c b/fs/xfs/scrub/readdir.c
index dfdcb96b6c..01c9a2dc0f 100644
--- a/fs/xfs/scrub/readdir.c
+++ b/fs/xfs/scrub/readdir.c
@@ -18,6 +18,7 @@
#include "xfs_trans.h"
#include "xfs_error.h"
#include "scrub/scrub.h"
+#include "scrub/common.h"
#include "scrub/readdir.h"
/* Call a function for every entry in a shortform directory. */
@@ -99,7 +100,7 @@ xchk_dir_walk_block(
unsigned int off, next_off, end;
int error;
- error = xfs_dir3_block_read(sc->tp, dp, &bp);
+ error = xfs_dir3_block_read(sc->tp, dp, dp->i_ino, &bp);
if (error)
return error;
@@ -175,7 +176,7 @@ xchk_read_leaf_dir_buf(
if (new_off > *curoff)
*curoff = new_off;
- return xfs_dir3_data_read(tp, dp, map.br_startoff, 0, bpp);
+ return xfs_dir3_data_read(tp, dp, dp->i_ino, map.br_startoff, 0, bpp);
}
/* Call a function for every entry in a leaf directory. */
@@ -273,8 +274,8 @@ xchk_dir_walk(
.dp = dp,
.geo = dp->i_mount->m_dir_geo,
.trans = sc->tp,
+ .owner = dp->i_ino,
};
- bool isblock;
int error;
if (xfs_is_shutdown(dp->i_mount))
@@ -283,22 +284,17 @@ xchk_dir_walk(
ASSERT(S_ISDIR(VFS_I(dp)->i_mode));
xfs_assert_ilocked(dp, XFS_ILOCK_SHARED | XFS_ILOCK_EXCL);
- if (dp->i_df.if_format == XFS_DINODE_FMT_LOCAL)
+ switch (xfs_dir2_format(&args, &error)) {
+ case XFS_DIR2_FMT_SF:
return xchk_dir_walk_sf(sc, dp, dirent_fn, priv);
-
- /* dir2 functions require that the data fork is loaded */
- error = xfs_iread_extents(sc->tp, dp, XFS_DATA_FORK);
- if (error)
- return error;
-
- error = xfs_dir2_isblock(&args, &isblock);
- if (error)
- return error;
-
- if (isblock)
+ case XFS_DIR2_FMT_BLOCK:
return xchk_dir_walk_block(sc, dp, dirent_fn, priv);
-
- return xchk_dir_walk_leaf(sc, dp, dirent_fn, priv);
+ case XFS_DIR2_FMT_LEAF:
+ case XFS_DIR2_FMT_NODE:
+ return xchk_dir_walk_leaf(sc, dp, dirent_fn, priv);
+ default:
+ return error;
+ }
}
/*
@@ -324,50 +320,102 @@ xchk_dir_lookup(
.hashval = xfs_dir2_hashname(dp->i_mount, name),
.whichfork = XFS_DATA_FORK,
.op_flags = XFS_DA_OP_OKNOENT,
+ .owner = dp->i_ino,
};
- bool isblock, isleaf;
int error;
if (xfs_is_shutdown(dp->i_mount))
return -EIO;
+ /*
+ * A temporary directory's block headers are written with the owner
+ * set to sc->ip, so we must switch the owner here for the lookup.
+ */
+ if (dp == sc->tempip)
+ args.owner = sc->ip->i_ino;
+
ASSERT(S_ISDIR(VFS_I(dp)->i_mode));
xfs_assert_ilocked(dp, XFS_ILOCK_SHARED | XFS_ILOCK_EXCL);
- if (dp->i_df.if_format == XFS_DINODE_FMT_LOCAL) {
- error = xfs_dir2_sf_lookup(&args);
- goto out_check_rval;
- }
+ error = xfs_dir_lookup_args(&args);
+ if (!error)
+ *ino = args.inumber;
+ return error;
+}
- /* dir2 functions require that the data fork is loaded */
- error = xfs_iread_extents(sc->tp, dp, XFS_DATA_FORK);
- if (error)
- return error;
+/*
+ * Try to grab the IOLOCK and ILOCK of sc->ip and ip, returning @ip's lock
+ * state. The caller may have a transaction, so we must use trylock for both
+ * IOLOCKs.
+ */
+static inline unsigned int
+xchk_dir_trylock_both(
+ struct xfs_scrub *sc,
+ struct xfs_inode *ip)
+{
+ if (!xchk_ilock_nowait(sc, XFS_IOLOCK_EXCL))
+ return 0;
- error = xfs_dir2_isblock(&args, &isblock);
- if (error)
- return error;
+ if (!xfs_ilock_nowait(ip, XFS_IOLOCK_SHARED))
+ goto parent_iolock;
- if (isblock) {
- error = xfs_dir2_block_lookup(&args);
- goto out_check_rval;
- }
+ xchk_ilock(sc, XFS_ILOCK_EXCL);
+ if (!xfs_ilock_nowait(ip, XFS_ILOCK_EXCL))
+ goto parent_ilock;
- error = xfs_dir2_isleaf(&args, &isleaf);
- if (error)
- return error;
+ return XFS_IOLOCK_SHARED | XFS_ILOCK_EXCL;
+
+parent_ilock:
+ xchk_iunlock(sc, XFS_ILOCK_EXCL);
+ xfs_iunlock(ip, XFS_IOLOCK_SHARED);
+parent_iolock:
+ xchk_iunlock(sc, XFS_IOLOCK_EXCL);
+ return 0;
+}
+
+/*
+ * Try for a limited time to grab the IOLOCK and ILOCK of both the scrub target
+ * (@sc->ip) and the inode at the other end (@ip) of a directory or parent
+ * pointer link so that we can check that link.
+ *
+ * We do not know ahead of time that the directory tree is /not/ corrupt, so we
+ * cannot use the "lock two inode" functions because we do not know that there
+ * is not a racing thread trying to take the locks in opposite order. First
+ * take IOLOCK_EXCL of the scrub target, and then try to take IOLOCK_SHARED
+ * of @ip to synchronize with the VFS. Next, take ILOCK_EXCL of the scrub
+ * target and @ip to synchronize with XFS.
+ *
+ * If the trylocks succeed, *lockmode will be set to the locks held for @ip;
+ * @sc->ilock_flags will be set for the locks held for @sc->ip; and zero will
+ * be returned. If not, returns -EDEADLOCK to try again; or -ETIMEDOUT if
+ * XCHK_TRY_HARDER was set. Returns -EINTR if the process has been killed.
+ */
+int
+xchk_dir_trylock_for_pptrs(
+ struct xfs_scrub *sc,
+ struct xfs_inode *ip,
+ unsigned int *lockmode)
+{
+ unsigned int nr;
+ int error = 0;
+
+ ASSERT(sc->ilock_flags == 0);
+
+ for (nr = 0; nr < HZ; nr++) {
+ *lockmode = xchk_dir_trylock_both(sc, ip);
+ if (*lockmode)
+ return 0;
- if (isleaf) {
- error = xfs_dir2_leaf_lookup(&args);
- goto out_check_rval;
+ if (xchk_should_terminate(sc, &error))
+ return error;
+
+ delay(1);
}
- error = xfs_dir2_node_lookup(&args);
+ if (sc->flags & XCHK_TRY_HARDER) {
+ xchk_set_incomplete(sc);
+ return -ETIMEDOUT;
+ }
-out_check_rval:
- if (error == -EEXIST)
- error = 0;
- if (!error)
- *ino = args.inumber;
- return error;
+ return -EDEADLOCK;
}
diff --git a/fs/xfs/scrub/readdir.h b/fs/xfs/scrub/readdir.h
index 55787f4df1..da501877a6 100644
--- a/fs/xfs/scrub/readdir.h
+++ b/fs/xfs/scrub/readdir.h
@@ -16,4 +16,7 @@ int xchk_dir_walk(struct xfs_scrub *sc, struct xfs_inode *dp,
int xchk_dir_lookup(struct xfs_scrub *sc, struct xfs_inode *dp,
const struct xfs_name *name, xfs_ino_t *ino);
+int xchk_dir_trylock_for_pptrs(struct xfs_scrub *sc, struct xfs_inode *ip,
+ unsigned int *lockmode);
+
#endif /* __XFS_SCRUB_READDIR_H__ */
diff --git a/fs/xfs/scrub/reap.c b/fs/xfs/scrub/reap.c
index 0252a3b5b6..be283153c2 100644
--- a/fs/xfs/scrub/reap.c
+++ b/fs/xfs/scrub/reap.c
@@ -211,6 +211,48 @@ static inline void xreap_defer_finish_reset(struct xreap_state *rs)
rs->force_roll = false;
}
+/*
+ * Compute the maximum length of a buffer cache scan (in units of sectors),
+ * given a quantity of fs blocks.
+ */
+xfs_daddr_t
+xrep_bufscan_max_sectors(
+ struct xfs_mount *mp,
+ xfs_extlen_t fsblocks)
+{
+ int max_fsbs;
+
+ /* Remote xattr values are the largest buffers that we support. */
+ max_fsbs = xfs_attr3_max_rmt_blocks(mp);
+
+ return XFS_FSB_TO_BB(mp, min_t(xfs_extlen_t, fsblocks, max_fsbs));
+}
+
+/*
+ * Return an incore buffer from a sector scan, or NULL if there are no buffers
+ * left to return.
+ */
+struct xfs_buf *
+xrep_bufscan_advance(
+ struct xfs_mount *mp,
+ struct xrep_bufscan *scan)
+{
+ scan->__sector_count += scan->daddr_step;
+ while (scan->__sector_count <= scan->max_sectors) {
+ struct xfs_buf *bp = NULL;
+ int error;
+
+ error = xfs_buf_incore(mp->m_ddev_targp, scan->daddr,
+ scan->__sector_count, XBF_LIVESCAN, &bp);
+ if (!error)
+ return bp;
+
+ scan->__sector_count += scan->daddr_step;
+ }
+
+ return NULL;
+}
+
/* Try to invalidate the incore buffers for an extent that we're freeing. */
STATIC void
xreap_agextent_binval(
@@ -241,28 +283,15 @@ xreap_agextent_binval(
* of any plausible size.
*/
while (bno < agbno_next) {
- xfs_agblock_t fsbcount;
- xfs_agblock_t max_fsbs;
-
- /*
- * Max buffer size is the max remote xattr buffer size, which
- * is one fs block larger than 64k.
- */
- max_fsbs = min_t(xfs_agblock_t, agbno_next - bno,
- xfs_attr3_rmt_blocks(mp, XFS_XATTR_SIZE_MAX));
-
- for (fsbcount = 1; fsbcount <= max_fsbs; fsbcount++) {
- struct xfs_buf *bp = NULL;
- xfs_daddr_t daddr;
- int error;
-
- daddr = XFS_AGB_TO_DADDR(mp, agno, bno);
- error = xfs_buf_incore(mp->m_ddev_targp, daddr,
- XFS_FSB_TO_BB(mp, fsbcount),
- XBF_LIVESCAN, &bp);
- if (error)
- continue;
-
+ struct xrep_bufscan scan = {
+ .daddr = XFS_AGB_TO_DADDR(mp, agno, bno),
+ .max_sectors = xrep_bufscan_max_sectors(mp,
+ agbno_next - bno),
+ .daddr_step = XFS_FSB_TO_BB(mp, 1),
+ };
+ struct xfs_buf *bp;
+
+ while ((bp = xrep_bufscan_advance(mp, &scan)) != NULL) {
xfs_trans_bjoin(sc->tp, bp);
xfs_trans_binval(sc->tp, bp);
rs->invalidated++;
@@ -646,3 +675,375 @@ xrep_reap_fsblocks(
return 0;
}
+
+/*
+ * Metadata files are not supposed to share blocks with anything else.
+ * If blocks are shared, we remove the reverse mapping (thus reducing the
+ * crosslink factor); if blocks are not shared, we also need to free them.
+ *
+ * This first step determines the longest subset of the passed-in imap
+ * (starting at its beginning) that is either crosslinked or not crosslinked.
+ * The blockcount will be adjust down as needed.
+ */
+STATIC int
+xreap_bmapi_select(
+ struct xfs_scrub *sc,
+ struct xfs_inode *ip,
+ int whichfork,
+ struct xfs_bmbt_irec *imap,
+ bool *crosslinked)
+{
+ struct xfs_owner_info oinfo;
+ struct xfs_btree_cur *cur;
+ xfs_filblks_t len = 1;
+ xfs_agblock_t bno;
+ xfs_agblock_t agbno;
+ xfs_agblock_t agbno_next;
+ int error;
+
+ agbno = XFS_FSB_TO_AGBNO(sc->mp, imap->br_startblock);
+ agbno_next = agbno + imap->br_blockcount;
+
+ cur = xfs_rmapbt_init_cursor(sc->mp, sc->tp, sc->sa.agf_bp,
+ sc->sa.pag);
+
+ xfs_rmap_ino_owner(&oinfo, ip->i_ino, whichfork, imap->br_startoff);
+ error = xfs_rmap_has_other_keys(cur, agbno, 1, &oinfo, crosslinked);
+ if (error)
+ goto out_cur;
+
+ bno = agbno + 1;
+ while (bno < agbno_next) {
+ bool also_crosslinked;
+
+ oinfo.oi_offset++;
+ error = xfs_rmap_has_other_keys(cur, bno, 1, &oinfo,
+ &also_crosslinked);
+ if (error)
+ goto out_cur;
+
+ if (also_crosslinked != *crosslinked)
+ break;
+
+ len++;
+ bno++;
+ }
+
+ imap->br_blockcount = len;
+ trace_xreap_bmapi_select(sc->sa.pag, agbno, len, *crosslinked);
+out_cur:
+ xfs_btree_del_cursor(cur, error);
+ return error;
+}
+
+/*
+ * Decide if this buffer can be joined to a transaction. This is true for most
+ * buffers, but there are two cases that we want to catch: large remote xattr
+ * value buffers are not logged and can overflow the buffer log item dirty
+ * bitmap size; and oversized cached buffers if things have really gone
+ * haywire.
+ */
+static inline bool
+xreap_buf_loggable(
+ const struct xfs_buf *bp)
+{
+ int i;
+
+ for (i = 0; i < bp->b_map_count; i++) {
+ int chunks;
+ int map_size;
+
+ chunks = DIV_ROUND_UP(BBTOB(bp->b_maps[i].bm_len),
+ XFS_BLF_CHUNK);
+ map_size = DIV_ROUND_UP(chunks, NBWORD);
+ if (map_size > XFS_BLF_DATAMAP_SIZE)
+ return false;
+ }
+
+ return true;
+}
+
+/*
+ * Invalidate any buffers for this file mapping. The @imap blockcount may be
+ * adjusted downward if we need to roll the transaction.
+ */
+STATIC int
+xreap_bmapi_binval(
+ struct xfs_scrub *sc,
+ struct xfs_inode *ip,
+ int whichfork,
+ struct xfs_bmbt_irec *imap)
+{
+ struct xfs_mount *mp = sc->mp;
+ struct xfs_perag *pag = sc->sa.pag;
+ int bmap_flags = xfs_bmapi_aflag(whichfork);
+ xfs_fileoff_t off;
+ xfs_fileoff_t max_off;
+ xfs_extlen_t scan_blocks;
+ xfs_agnumber_t agno = sc->sa.pag->pag_agno;
+ xfs_agblock_t bno;
+ xfs_agblock_t agbno;
+ xfs_agblock_t agbno_next;
+ unsigned int invalidated = 0;
+ int error;
+
+ /*
+ * Avoid invalidating AG headers and post-EOFS blocks because we never
+ * own those.
+ */
+ agbno = bno = XFS_FSB_TO_AGBNO(sc->mp, imap->br_startblock);
+ agbno_next = agbno + imap->br_blockcount;
+ if (!xfs_verify_agbno(pag, agbno) ||
+ !xfs_verify_agbno(pag, agbno_next - 1))
+ return 0;
+
+ /*
+ * Buffers for file blocks can span multiple contiguous mappings. This
+ * means that for each block in the mapping, there could exist an
+ * xfs_buf indexed by that block with any length up to the maximum
+ * buffer size (remote xattr values) or to the next hole in the fork.
+ * To set up our binval scan, first we need to figure out the location
+ * of the next hole.
+ */
+ off = imap->br_startoff + imap->br_blockcount;
+ max_off = off + xfs_attr3_max_rmt_blocks(mp);
+ while (off < max_off) {
+ struct xfs_bmbt_irec hmap;
+ int nhmaps = 1;
+
+ error = xfs_bmapi_read(ip, off, max_off - off, &hmap,
+ &nhmaps, bmap_flags);
+ if (error)
+ return error;
+ if (nhmaps != 1 || hmap.br_startblock == DELAYSTARTBLOCK) {
+ ASSERT(0);
+ return -EFSCORRUPTED;
+ }
+
+ if (!xfs_bmap_is_real_extent(&hmap))
+ break;
+
+ off = hmap.br_startoff + hmap.br_blockcount;
+ }
+ scan_blocks = off - imap->br_startoff;
+
+ trace_xreap_bmapi_binval_scan(sc, imap, scan_blocks);
+
+ /*
+ * If there are incore buffers for these blocks, invalidate them. If
+ * we can't (try)lock the buffer we assume it's owned by someone else
+ * and leave it alone. The buffer cache cannot detect aliasing, so
+ * employ nested loops to detect incore buffers of any plausible size.
+ */
+ while (bno < agbno_next) {
+ struct xrep_bufscan scan = {
+ .daddr = XFS_AGB_TO_DADDR(mp, agno, bno),
+ .max_sectors = xrep_bufscan_max_sectors(mp,
+ scan_blocks),
+ .daddr_step = XFS_FSB_TO_BB(mp, 1),
+ };
+ struct xfs_buf *bp;
+
+ while ((bp = xrep_bufscan_advance(mp, &scan)) != NULL) {
+ if (xreap_buf_loggable(bp)) {
+ xfs_trans_bjoin(sc->tp, bp);
+ xfs_trans_binval(sc->tp, bp);
+ } else {
+ xfs_buf_stale(bp);
+ xfs_buf_relse(bp);
+ }
+ invalidated++;
+
+ /*
+ * Stop invalidating if we've hit the limit; we should
+ * still have enough reservation left to free however
+ * much of the mapping we've seen so far.
+ */
+ if (invalidated > XREAP_MAX_BINVAL) {
+ imap->br_blockcount = agbno_next - bno;
+ goto out;
+ }
+ }
+
+ bno++;
+ scan_blocks--;
+ }
+
+out:
+ trace_xreap_bmapi_binval(sc->sa.pag, agbno, imap->br_blockcount);
+ return 0;
+}
+
+/*
+ * Dispose of as much of the beginning of this file fork mapping as possible.
+ * The number of blocks disposed of is returned in @imap->br_blockcount.
+ */
+STATIC int
+xrep_reap_bmapi_iter(
+ struct xfs_scrub *sc,
+ struct xfs_inode *ip,
+ int whichfork,
+ struct xfs_bmbt_irec *imap,
+ bool crosslinked)
+{
+ int error;
+
+ if (crosslinked) {
+ /*
+ * If there are other rmappings, this block is cross linked and
+ * must not be freed. Remove the reverse mapping, leave the
+ * buffer cache in its possibly confused state, and move on.
+ * We don't want to risk discarding valid data buffers from
+ * anybody else who thinks they own the block, even though that
+ * runs the risk of stale buffer warnings in the future.
+ */
+ trace_xreap_dispose_unmap_extent(sc->sa.pag,
+ XFS_FSB_TO_AGBNO(sc->mp, imap->br_startblock),
+ imap->br_blockcount);
+
+ /*
+ * Schedule removal of the mapping from the fork. We use
+ * deferred log intents in this function to control the exact
+ * sequence of metadata updates.
+ */
+ xfs_bmap_unmap_extent(sc->tp, ip, whichfork, imap);
+ xfs_trans_mod_dquot_byino(sc->tp, ip, XFS_TRANS_DQ_BCOUNT,
+ -(int64_t)imap->br_blockcount);
+ xfs_rmap_unmap_extent(sc->tp, ip, whichfork, imap);
+ return 0;
+ }
+
+ /*
+ * If the block is not crosslinked, we can invalidate all the incore
+ * buffers for the extent, and then free the extent. This is a bit of
+ * a mess since we don't detect discontiguous buffers that are indexed
+ * by a block starting before the first block of the extent but overlap
+ * anyway.
+ */
+ trace_xreap_dispose_free_extent(sc->sa.pag,
+ XFS_FSB_TO_AGBNO(sc->mp, imap->br_startblock),
+ imap->br_blockcount);
+
+ /*
+ * Invalidate as many buffers as we can, starting at the beginning of
+ * this mapping. If this function sets blockcount to zero, the
+ * transaction is full of logged buffer invalidations, so we need to
+ * return early so that we can roll and retry.
+ */
+ error = xreap_bmapi_binval(sc, ip, whichfork, imap);
+ if (error || imap->br_blockcount == 0)
+ return error;
+
+ /*
+ * Schedule removal of the mapping from the fork. We use deferred log
+ * intents in this function to control the exact sequence of metadata
+ * updates.
+ */
+ xfs_bmap_unmap_extent(sc->tp, ip, whichfork, imap);
+ xfs_trans_mod_dquot_byino(sc->tp, ip, XFS_TRANS_DQ_BCOUNT,
+ -(int64_t)imap->br_blockcount);
+ return xfs_free_extent_later(sc->tp, imap->br_startblock,
+ imap->br_blockcount, NULL, XFS_AG_RESV_NONE, true);
+}
+
+/*
+ * Dispose of as much of this file extent as we can. Upon successful return,
+ * the imap will reflect the mapping that was removed from the fork.
+ */
+STATIC int
+xreap_ifork_extent(
+ struct xfs_scrub *sc,
+ struct xfs_inode *ip,
+ int whichfork,
+ struct xfs_bmbt_irec *imap)
+{
+ xfs_agnumber_t agno;
+ bool crosslinked;
+ int error;
+
+ ASSERT(sc->sa.pag == NULL);
+
+ trace_xreap_ifork_extent(sc, ip, whichfork, imap);
+
+ agno = XFS_FSB_TO_AGNO(sc->mp, imap->br_startblock);
+ sc->sa.pag = xfs_perag_get(sc->mp, agno);
+ if (!sc->sa.pag)
+ return -EFSCORRUPTED;
+
+ error = xfs_alloc_read_agf(sc->sa.pag, sc->tp, 0, &sc->sa.agf_bp);
+ if (error)
+ goto out_pag;
+
+ /*
+ * Decide the fate of the blocks at the beginning of the mapping, then
+ * update the mapping to use it with the unmap calls.
+ */
+ error = xreap_bmapi_select(sc, ip, whichfork, imap, &crosslinked);
+ if (error)
+ goto out_agf;
+
+ error = xrep_reap_bmapi_iter(sc, ip, whichfork, imap, crosslinked);
+ if (error)
+ goto out_agf;
+
+out_agf:
+ xfs_trans_brelse(sc->tp, sc->sa.agf_bp);
+ sc->sa.agf_bp = NULL;
+out_pag:
+ xfs_perag_put(sc->sa.pag);
+ sc->sa.pag = NULL;
+ return error;
+}
+
+/*
+ * Dispose of each block mapped to the given fork of the given file. Callers
+ * must hold ILOCK_EXCL, and ip can only be sc->ip or sc->tempip. The fork
+ * must not have any delalloc reservations.
+ */
+int
+xrep_reap_ifork(
+ struct xfs_scrub *sc,
+ struct xfs_inode *ip,
+ int whichfork)
+{
+ xfs_fileoff_t off = 0;
+ int bmap_flags = xfs_bmapi_aflag(whichfork);
+ int error;
+
+ ASSERT(xfs_has_rmapbt(sc->mp));
+ ASSERT(ip == sc->ip || ip == sc->tempip);
+ ASSERT(whichfork == XFS_ATTR_FORK || !XFS_IS_REALTIME_INODE(ip));
+
+ while (off < XFS_MAX_FILEOFF) {
+ struct xfs_bmbt_irec imap;
+ int nimaps = 1;
+
+ /* Read the next extent, skip past holes and delalloc. */
+ error = xfs_bmapi_read(ip, off, XFS_MAX_FILEOFF - off, &imap,
+ &nimaps, bmap_flags);
+ if (error)
+ return error;
+ if (nimaps != 1 || imap.br_startblock == DELAYSTARTBLOCK) {
+ ASSERT(0);
+ return -EFSCORRUPTED;
+ }
+
+ /*
+ * If this is a real space mapping, reap as much of it as we
+ * can in a single transaction.
+ */
+ if (xfs_bmap_is_real_extent(&imap)) {
+ error = xreap_ifork_extent(sc, ip, whichfork, &imap);
+ if (error)
+ return error;
+
+ error = xfs_defer_finish(&sc->tp);
+ if (error)
+ return error;
+ }
+
+ off = imap.br_startoff + imap.br_blockcount;
+ }
+
+ return 0;
+}
diff --git a/fs/xfs/scrub/reap.h b/fs/xfs/scrub/reap.h
index 0b69f16dd9..3f2f1775e2 100644
--- a/fs/xfs/scrub/reap.h
+++ b/fs/xfs/scrub/reap.h
@@ -13,5 +13,26 @@ int xrep_reap_agblocks(struct xfs_scrub *sc, struct xagb_bitmap *bitmap,
const struct xfs_owner_info *oinfo, enum xfs_ag_resv_type type);
int xrep_reap_fsblocks(struct xfs_scrub *sc, struct xfsb_bitmap *bitmap,
const struct xfs_owner_info *oinfo);
+int xrep_reap_ifork(struct xfs_scrub *sc, struct xfs_inode *ip, int whichfork);
+
+/* Buffer cache scan context. */
+struct xrep_bufscan {
+ /* Disk address for the buffers we want to scan. */
+ xfs_daddr_t daddr;
+
+ /* Maximum number of sectors to scan. */
+ xfs_daddr_t max_sectors;
+
+ /* Each round, increment the search length by this number of sectors. */
+ xfs_daddr_t daddr_step;
+
+ /* Internal scan state; initialize to zero. */
+ xfs_daddr_t __sector_count;
+};
+
+xfs_daddr_t xrep_bufscan_max_sectors(struct xfs_mount *mp,
+ xfs_extlen_t fsblocks);
+struct xfs_buf *xrep_bufscan_advance(struct xfs_mount *mp,
+ struct xrep_bufscan *scan);
#endif /* __XFS_SCRUB_REAP_H__ */
diff --git a/fs/xfs/scrub/repair.c b/fs/xfs/scrub/repair.c
index f43dce771c..67478294f1 100644
--- a/fs/xfs/scrub/repair.c
+++ b/fs/xfs/scrub/repair.c
@@ -32,6 +32,10 @@
#include "xfs_reflink.h"
#include "xfs_health.h"
#include "xfs_buf_mem.h"
+#include "xfs_da_format.h"
+#include "xfs_da_btree.h"
+#include "xfs_attr.h"
+#include "xfs_dir2.h"
#include "scrub/scrub.h"
#include "scrub/common.h"
#include "scrub/trace.h"
@@ -39,6 +43,7 @@
#include "scrub/bitmap.h"
#include "scrub/stats.h"
#include "scrub/xfile.h"
+#include "scrub/attr_repair.h"
/*
* Attempt to repair some metadata, if the metadata is corrupt and userspace
@@ -290,7 +295,7 @@ xrep_calc_ag_resblks(
icount = pag->pagi_count;
} else {
/* Try to get the actual counters from disk. */
- error = xfs_ialloc_read_agi(pag, NULL, &bp);
+ error = xfs_ialloc_read_agi(pag, NULL, 0, &bp);
if (!error) {
icount = pag->pagi_count;
xfs_buf_relse(bp);
@@ -724,7 +729,7 @@ xrep_update_qflags(
xfs_trans_log_buf(sc->tp, bp, 0, sizeof(struct xfs_dsb) - 1);
no_update:
- mutex_unlock(&sc->mp->m_quotainfo->qi_quotaofflock);
+ mutex_unlock(&mp->m_quotainfo->qi_quotaofflock);
}
/* Force a quotacheck the next time we mount. */
@@ -908,7 +913,7 @@ xrep_reinit_pagi(
ASSERT(xfs_perag_initialised_agi(pag));
clear_bit(XFS_AGSTATE_AGI_INIT, &pag->pag_opstate);
- error = xfs_ialloc_read_agi(pag, sc->tp, &bp);
+ error = xfs_ialloc_read_agi(pag, sc->tp, 0, &bp);
if (error)
return error;
@@ -934,7 +939,7 @@ xrep_ag_init(
ASSERT(!sa->pag);
- error = xfs_ialloc_read_agi(pag, sc->tp, &sa->agi_bp);
+ error = xfs_ialloc_read_agi(pag, sc->tp, 0, &sa->agi_bp);
if (error)
return error;
@@ -963,9 +968,7 @@ xrep_reset_perag_resv(
ASSERT(sc->tp);
sc->flags &= ~XREP_RESET_PERAG_RESV;
- error = xfs_ag_resv_free(sc->sa.pag);
- if (error)
- goto out;
+ xfs_ag_resv_free(sc->sa.pag);
error = xfs_ag_resv_init(sc->sa.pag, sc->tp);
if (error == -ENOSPC) {
xfs_err(sc->mp,
@@ -974,7 +977,6 @@ xrep_reset_perag_resv(
error = 0;
}
-out:
return error;
}
@@ -1004,55 +1006,27 @@ xrep_metadata_inode_subtype(
struct xfs_scrub *sc,
unsigned int scrub_type)
{
- __u32 smtype = sc->sm->sm_type;
- __u32 smflags = sc->sm->sm_flags;
- unsigned int sick_mask = sc->sick_mask;
+ struct xfs_scrub_subord *sub;
int error;
/*
- * Let's see if the inode needs repair. We're going to open-code calls
- * to the scrub and repair functions so that we can hang on to the
+ * Let's see if the inode needs repair. Use a subordinate scrub context
+ * to call the scrub and repair functions so that we can hang on to the
* resources that we already acquired instead of using the standard
* setup/teardown routines.
*/
- sc->sm->sm_flags &= ~XFS_SCRUB_FLAGS_OUT;
- sc->sm->sm_type = scrub_type;
-
- switch (scrub_type) {
- case XFS_SCRUB_TYPE_INODE:
- error = xchk_inode(sc);
- break;
- case XFS_SCRUB_TYPE_BMBTD:
- error = xchk_bmap_data(sc);
- break;
- case XFS_SCRUB_TYPE_BMBTA:
- error = xchk_bmap_attr(sc);
- break;
- default:
- ASSERT(0);
- error = -EFSCORRUPTED;
- }
+ sub = xchk_scrub_create_subord(sc, scrub_type);
+ error = sub->sc.ops->scrub(&sub->sc);
if (error)
goto out;
-
- if (!xrep_will_attempt(sc))
+ if (!xrep_will_attempt(&sub->sc))
goto out;
/*
* Repair some part of the inode. This will potentially join the inode
* to the transaction.
*/
- switch (scrub_type) {
- case XFS_SCRUB_TYPE_INODE:
- error = xrep_inode(sc);
- break;
- case XFS_SCRUB_TYPE_BMBTD:
- error = xrep_bmap(sc, XFS_DATA_FORK, false);
- break;
- case XFS_SCRUB_TYPE_BMBTA:
- error = xrep_bmap(sc, XFS_ATTR_FORK, false);
- break;
- }
+ error = sub->sc.ops->repair(&sub->sc);
if (error)
goto out;
@@ -1061,10 +1035,10 @@ xrep_metadata_inode_subtype(
* that the inode will not be joined to the transaction when we exit
* the function.
*/
- error = xfs_defer_finish(&sc->tp);
+ error = xfs_defer_finish(&sub->sc.tp);
if (error)
goto out;
- error = xfs_trans_roll(&sc->tp);
+ error = xfs_trans_roll(&sub->sc.tp);
if (error)
goto out;
@@ -1072,31 +1046,18 @@ xrep_metadata_inode_subtype(
* Clear the corruption flags and re-check the metadata that we just
* repaired.
*/
- sc->sm->sm_flags &= ~XFS_SCRUB_FLAGS_OUT;
-
- switch (scrub_type) {
- case XFS_SCRUB_TYPE_INODE:
- error = xchk_inode(sc);
- break;
- case XFS_SCRUB_TYPE_BMBTD:
- error = xchk_bmap_data(sc);
- break;
- case XFS_SCRUB_TYPE_BMBTA:
- error = xchk_bmap_attr(sc);
- break;
- }
+ sub->sc.sm->sm_flags &= ~XFS_SCRUB_FLAGS_OUT;
+ error = sub->sc.ops->scrub(&sub->sc);
if (error)
goto out;
/* If corruption persists, the repair has failed. */
- if (xchk_needs_repair(sc->sm)) {
+ if (xchk_needs_repair(sub->sc.sm)) {
error = -EFSCORRUPTED;
goto out;
}
out:
- sc->sick_mask = sick_mask;
- sc->sm->sm_type = smtype;
- sc->sm->sm_flags = smflags;
+ xchk_scrub_free_subord(sub);
return error;
}
@@ -1136,6 +1097,17 @@ xrep_metadata_inode_forks(
return error;
}
+ /* Clear the attr forks since metadata shouldn't have that. */
+ if (xfs_inode_hasattr(sc->ip)) {
+ if (!dirty) {
+ dirty = true;
+ xfs_trans_ijoin(sc->tp, sc->ip, 0);
+ }
+ error = xrep_xattr_reset_fork(sc);
+ if (error)
+ return error;
+ }
+
/*
* If we modified the inode, roll the transaction but don't rejoin the
* inode to the new transaction because xrep_bmap_data can do that.
@@ -1201,3 +1173,34 @@ xrep_trans_cancel_hook_dummy(
current->journal_info = *cookiep;
*cookiep = NULL;
}
+
+/*
+ * See if this buffer can pass the given ->verify_struct() function.
+ *
+ * If the buffer already has ops attached and they're not the ones that were
+ * passed in, we reject the buffer. Otherwise, we perform the structure test
+ * (note that we do not check CRCs) and return the outcome of the test. The
+ * buffer ops and error state are left unchanged.
+ */
+bool
+xrep_buf_verify_struct(
+ struct xfs_buf *bp,
+ const struct xfs_buf_ops *ops)
+{
+ const struct xfs_buf_ops *old_ops = bp->b_ops;
+ xfs_failaddr_t fa;
+ int old_error;
+
+ if (old_ops) {
+ if (old_ops != ops)
+ return false;
+ }
+
+ old_error = bp->b_error;
+ bp->b_ops = ops;
+ fa = bp->b_ops->verify_struct(bp);
+ bp->b_ops = old_ops;
+ bp->b_error = old_error;
+
+ return fa == NULL;
+}
diff --git a/fs/xfs/scrub/repair.h b/fs/xfs/scrub/repair.h
index ce082d9414..0e0dc2bf98 100644
--- a/fs/xfs/scrub/repair.h
+++ b/fs/xfs/scrub/repair.h
@@ -90,6 +90,12 @@ int xrep_bmap(struct xfs_scrub *sc, int whichfork, bool allow_unwritten);
int xrep_metadata_inode_forks(struct xfs_scrub *sc);
int xrep_setup_ag_rmapbt(struct xfs_scrub *sc);
int xrep_setup_ag_refcountbt(struct xfs_scrub *sc);
+int xrep_setup_xattr(struct xfs_scrub *sc);
+int xrep_setup_directory(struct xfs_scrub *sc);
+int xrep_setup_parent(struct xfs_scrub *sc);
+int xrep_setup_nlinks(struct xfs_scrub *sc);
+int xrep_setup_symlink(struct xfs_scrub *sc, unsigned int *resblks);
+int xrep_setup_dirtree(struct xfs_scrub *sc);
/* Repair setup functions */
int xrep_setup_ag_allocbt(struct xfs_scrub *sc);
@@ -123,11 +129,18 @@ int xrep_bmap_attr(struct xfs_scrub *sc);
int xrep_bmap_cow(struct xfs_scrub *sc);
int xrep_nlinks(struct xfs_scrub *sc);
int xrep_fscounters(struct xfs_scrub *sc);
+int xrep_xattr(struct xfs_scrub *sc);
+int xrep_directory(struct xfs_scrub *sc);
+int xrep_parent(struct xfs_scrub *sc);
+int xrep_symlink(struct xfs_scrub *sc);
+int xrep_dirtree(struct xfs_scrub *sc);
#ifdef CONFIG_XFS_RT
int xrep_rtbitmap(struct xfs_scrub *sc);
+int xrep_rtsummary(struct xfs_scrub *sc);
#else
# define xrep_rtbitmap xrep_notsupported
+# define xrep_rtsummary xrep_notsupported
#endif /* CONFIG_XFS_RT */
#ifdef CONFIG_XFS_QUOTA
@@ -145,6 +158,8 @@ int xrep_trans_alloc_hook_dummy(struct xfs_mount *mp, void **cookiep,
struct xfs_trans **tpp);
void xrep_trans_cancel_hook_dummy(void **cookiep, struct xfs_trans *tp);
+bool xrep_buf_verify_struct(struct xfs_buf *bp, const struct xfs_buf_ops *ops);
+
#else
#define xrep_ino_dqattach(sc) (0)
@@ -188,9 +203,19 @@ xrep_setup_nothing(
#define xrep_setup_ag_allocbt xrep_setup_nothing
#define xrep_setup_ag_rmapbt xrep_setup_nothing
#define xrep_setup_ag_refcountbt xrep_setup_nothing
+#define xrep_setup_xattr xrep_setup_nothing
+#define xrep_setup_directory xrep_setup_nothing
+#define xrep_setup_parent xrep_setup_nothing
+#define xrep_setup_nlinks xrep_setup_nothing
+#define xrep_setup_dirtree xrep_setup_nothing
#define xrep_setup_inode(sc, imap) ((void)0)
+static inline int xrep_setup_symlink(struct xfs_scrub *sc, unsigned int *x)
+{
+ return 0;
+}
+
#define xrep_revalidate_allocbt (NULL)
#define xrep_revalidate_iallocbt (NULL)
@@ -212,6 +237,12 @@ xrep_setup_nothing(
#define xrep_quotacheck xrep_notsupported
#define xrep_nlinks xrep_notsupported
#define xrep_fscounters xrep_notsupported
+#define xrep_rtsummary xrep_notsupported
+#define xrep_xattr xrep_notsupported
+#define xrep_directory xrep_notsupported
+#define xrep_parent xrep_notsupported
+#define xrep_symlink xrep_notsupported
+#define xrep_dirtree xrep_notsupported
#endif /* CONFIG_XFS_ONLINE_REPAIR */
diff --git a/fs/xfs/scrub/rmap_repair.c b/fs/xfs/scrub/rmap_repair.c
index e8e07b683e..e8080eba37 100644
--- a/fs/xfs/scrub/rmap_repair.c
+++ b/fs/xfs/scrub/rmap_repair.c
@@ -432,14 +432,6 @@ out:
return error;
}
-static inline bool
-is_rt_data_fork(
- struct xfs_inode *ip,
- int whichfork)
-{
- return XFS_IS_REALTIME_INODE(ip) && whichfork == XFS_DATA_FORK;
-}
-
/*
* Iterate the block mapping btree to collect rmap records for anything in this
* fork that matches the AG. Sets @mappings_done to true if we've scanned the
@@ -578,23 +570,9 @@ xrep_rmap_scan_inode(
struct xrep_rmap *rr,
struct xfs_inode *ip)
{
- unsigned int lock_mode = 0;
+ unsigned int lock_mode = xrep_rmap_scan_ilock(ip);
int error;
- /*
- * Directory updates (create/link/unlink/rename) drop the directory's
- * ILOCK before finishing any rmapbt updates associated with directory
- * shape changes. For this scan to coordinate correctly with the live
- * update hook, we must take the only lock (i_rwsem) that is held all
- * the way to dir op completion. This will get fixed by the parent
- * pointer patchset.
- */
- if (S_ISDIR(VFS_I(ip)->i_mode)) {
- lock_mode = XFS_IOLOCK_SHARED;
- xfs_ilock(ip, lock_mode);
- }
- lock_mode |= xrep_rmap_scan_ilock(ip);
-
/* Check the data fork. */
error = xrep_rmap_scan_ifork(rr, ip, XFS_DATA_FORK);
if (error)
diff --git a/fs/xfs/scrub/rtbitmap_repair.c b/fs/xfs/scrub/rtbitmap_repair.c
index 46f5d5f605..0fef98e9f8 100644
--- a/fs/xfs/scrub/rtbitmap_repair.c
+++ b/fs/xfs/scrub/rtbitmap_repair.c
@@ -108,8 +108,6 @@ xrep_rtbitmap_data_mappings(
0, &map, &nmaps);
if (error)
return error;
- if (nmaps != 1)
- return -EFSCORRUPTED;
/* Commit new extent and all deferred work. */
error = xrep_defer_finish(sc);
diff --git a/fs/xfs/scrub/rtsummary.c b/fs/xfs/scrub/rtsummary.c
index 5055092bd9..3fee603f52 100644
--- a/fs/xfs/scrub/rtsummary.c
+++ b/fs/xfs/scrub/rtsummary.c
@@ -17,10 +17,14 @@
#include "xfs_bit.h"
#include "xfs_bmap.h"
#include "xfs_sb.h"
+#include "xfs_exchmaps.h"
#include "scrub/scrub.h"
#include "scrub/common.h"
#include "scrub/trace.h"
#include "scrub/xfile.h"
+#include "scrub/repair.h"
+#include "scrub/tempexch.h"
+#include "scrub/rtsummary.h"
/*
* Realtime Summary
@@ -32,18 +36,6 @@
* (potentially large) amount of data in pageable memory.
*/
-struct xchk_rtsummary {
- struct xfs_rtalloc_args args;
-
- uint64_t rextents;
- uint64_t rbmblocks;
- uint64_t rsumsize;
- unsigned int rsumlevels;
-
- /* Memory buffer for the summary comparison. */
- union xfs_suminfo_raw words[];
-};
-
/* Set us up to check the rtsummary file. */
int
xchk_setup_rtsummary(
@@ -60,6 +52,12 @@ xchk_setup_rtsummary(
return -ENOMEM;
sc->buf = rts;
+ if (xchk_could_repair(sc)) {
+ error = xrep_setup_rtsummary(sc, rts);
+ if (error)
+ return error;
+ }
+
/*
* Create an xfile to construct a new rtsummary file. The xfile allows
* us to avoid pinning kernel memory for this purpose.
@@ -70,7 +68,7 @@ xchk_setup_rtsummary(
if (error)
return error;
- error = xchk_trans_alloc(sc, 0);
+ error = xchk_trans_alloc(sc, rts->resblks);
if (error)
return error;
@@ -135,7 +133,7 @@ xfsum_store(
sumoff << XFS_WORDLOG);
}
-static inline int
+inline int
xfsum_copyout(
struct xfs_scrub *sc,
xfs_rtsumoff_t sumoff,
@@ -362,7 +360,12 @@ xchk_rtsummary(
error = xchk_rtsum_compare(sc);
out_rbm:
- /* Unlock the rtbitmap since we're done with it. */
+ /*
+ * Unlock the rtbitmap since we're done with it. All other writers of
+ * the rt free space metadata grab the bitmap and summary ILOCKs in
+ * that order, so we're still protected against allocation activities
+ * even if we continue on to the repair function.
+ */
xfs_iunlock(mp->m_rbmip, XFS_ILOCK_SHARED | XFS_ILOCK_RTBITMAP);
return error;
}
diff --git a/fs/xfs/scrub/rtsummary.h b/fs/xfs/scrub/rtsummary.h
new file mode 100644
index 0000000000..e1d50304d8
--- /dev/null
+++ b/fs/xfs/scrub/rtsummary.h
@@ -0,0 +1,37 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Copyright (c) 2020-2024 Oracle. All Rights Reserved.
+ * Author: Darrick J. Wong <djwong@kernel.org>
+ */
+#ifndef __XFS_SCRUB_RTSUMMARY_H__
+#define __XFS_SCRUB_RTSUMMARY_H__
+
+struct xchk_rtsummary {
+#ifdef CONFIG_XFS_ONLINE_REPAIR
+ struct xrep_tempexch tempexch;
+#endif
+ struct xfs_rtalloc_args args;
+
+ uint64_t rextents;
+ uint64_t rbmblocks;
+ uint64_t rsumsize;
+ unsigned int rsumlevels;
+ unsigned int resblks;
+
+ /* suminfo position of xfile as we write buffers to disk. */
+ xfs_rtsumoff_t prep_wordoff;
+
+ /* Memory buffer for the summary comparison. */
+ union xfs_suminfo_raw words[];
+};
+
+int xfsum_copyout(struct xfs_scrub *sc, xfs_rtsumoff_t sumoff,
+ union xfs_suminfo_raw *rawinfo, unsigned int nr_words);
+
+#ifdef CONFIG_XFS_ONLINE_REPAIR
+int xrep_setup_rtsummary(struct xfs_scrub *sc, struct xchk_rtsummary *rts);
+#else
+# define xrep_setup_rtsummary(sc, rts) (0)
+#endif /* CONFIG_XFS_ONLINE_REPAIR */
+
+#endif /* __XFS_SCRUB_RTSUMMARY_H__ */
diff --git a/fs/xfs/scrub/rtsummary_repair.c b/fs/xfs/scrub/rtsummary_repair.c
new file mode 100644
index 0000000000..d9e971c4c7
--- /dev/null
+++ b/fs/xfs/scrub/rtsummary_repair.c
@@ -0,0 +1,175 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Copyright (c) 2020-2024 Oracle. All Rights Reserved.
+ * Author: Darrick J. Wong <djwong@kernel.org>
+ */
+#include "xfs.h"
+#include "xfs_fs.h"
+#include "xfs_shared.h"
+#include "xfs_format.h"
+#include "xfs_trans_resv.h"
+#include "xfs_mount.h"
+#include "xfs_btree.h"
+#include "xfs_log_format.h"
+#include "xfs_trans.h"
+#include "xfs_rtalloc.h"
+#include "xfs_inode.h"
+#include "xfs_bit.h"
+#include "xfs_bmap.h"
+#include "xfs_bmap_btree.h"
+#include "xfs_exchmaps.h"
+#include "xfs_rtbitmap.h"
+#include "scrub/scrub.h"
+#include "scrub/common.h"
+#include "scrub/trace.h"
+#include "scrub/repair.h"
+#include "scrub/tempfile.h"
+#include "scrub/tempexch.h"
+#include "scrub/reap.h"
+#include "scrub/xfile.h"
+#include "scrub/rtsummary.h"
+
+/* Set us up to repair the rtsummary file. */
+int
+xrep_setup_rtsummary(
+ struct xfs_scrub *sc,
+ struct xchk_rtsummary *rts)
+{
+ struct xfs_mount *mp = sc->mp;
+ unsigned long long blocks;
+ int error;
+
+ error = xrep_tempfile_create(sc, S_IFREG);
+ if (error)
+ return error;
+
+ /*
+ * If we're doing a repair, we reserve enough blocks to write out a
+ * completely new summary file, plus twice as many blocks as we would
+ * need if we can only allocate one block per data fork mapping. This
+ * should cover the preallocation of the temporary file and exchanging
+ * the extent mappings.
+ *
+ * We cannot use xfs_exchmaps_estimate because we have not yet
+ * constructed the replacement rtsummary and therefore do not know how
+ * many extents it will use. By the time we do, we will have a dirty
+ * transaction (which we cannot drop because we cannot drop the
+ * rtsummary ILOCK) and cannot ask for more reservation.
+ */
+ blocks = XFS_B_TO_FSB(mp, mp->m_rsumsize);
+ blocks += xfs_bmbt_calc_size(mp, blocks) * 2;
+ if (blocks > UINT_MAX)
+ return -EOPNOTSUPP;
+
+ rts->resblks += blocks;
+ return 0;
+}
+
+static int
+xrep_rtsummary_prep_buf(
+ struct xfs_scrub *sc,
+ struct xfs_buf *bp,
+ void *data)
+{
+ struct xchk_rtsummary *rts = data;
+ struct xfs_mount *mp = sc->mp;
+ union xfs_suminfo_raw *ondisk;
+ int error;
+
+ rts->args.mp = sc->mp;
+ rts->args.tp = sc->tp;
+ rts->args.sumbp = bp;
+ ondisk = xfs_rsumblock_infoptr(&rts->args, 0);
+ rts->args.sumbp = NULL;
+
+ bp->b_ops = &xfs_rtbuf_ops;
+
+ error = xfsum_copyout(sc, rts->prep_wordoff, ondisk, mp->m_blockwsize);
+ if (error)
+ return error;
+
+ rts->prep_wordoff += mp->m_blockwsize;
+ xfs_trans_buf_set_type(sc->tp, bp, XFS_BLFT_RTSUMMARY_BUF);
+ return 0;
+}
+
+/* Repair the realtime summary. */
+int
+xrep_rtsummary(
+ struct xfs_scrub *sc)
+{
+ struct xchk_rtsummary *rts = sc->buf;
+ struct xfs_mount *mp = sc->mp;
+ xfs_filblks_t rsumblocks;
+ int error;
+
+ /* We require the rmapbt to rebuild anything. */
+ if (!xfs_has_rmapbt(mp))
+ return -EOPNOTSUPP;
+ /* We require atomic file exchange range to rebuild anything. */
+ if (!xfs_has_exchange_range(mp))
+ return -EOPNOTSUPP;
+
+ /* Walk away if we disagree on the size of the rt bitmap. */
+ if (rts->rbmblocks != mp->m_sb.sb_rbmblocks)
+ return 0;
+
+ /* Make sure any problems with the fork are fixed. */
+ error = xrep_metadata_inode_forks(sc);
+ if (error)
+ return error;
+
+ /*
+ * Try to take ILOCK_EXCL of the temporary file. We had better be the
+ * only ones holding onto this inode, but we can't block while holding
+ * the rtsummary file's ILOCK_EXCL.
+ */
+ while (!xrep_tempfile_ilock_nowait(sc)) {
+ if (xchk_should_terminate(sc, &error))
+ return error;
+ delay(1);
+ }
+
+ /* Make sure we have space allocated for the entire summary file. */
+ rsumblocks = XFS_B_TO_FSB(mp, rts->rsumsize);
+ xfs_trans_ijoin(sc->tp, sc->ip, 0);
+ xfs_trans_ijoin(sc->tp, sc->tempip, 0);
+ error = xrep_tempfile_prealloc(sc, 0, rsumblocks);
+ if (error)
+ return error;
+
+ /* Last chance to abort before we start committing fixes. */
+ if (xchk_should_terminate(sc, &error))
+ return error;
+
+ /* Copy the rtsummary file that we generated. */
+ error = xrep_tempfile_copyin(sc, 0, rsumblocks,
+ xrep_rtsummary_prep_buf, rts);
+ if (error)
+ return error;
+ error = xrep_tempfile_set_isize(sc, rts->rsumsize);
+ if (error)
+ return error;
+
+ /*
+ * Now exchange the contents. Nothing in repair uses the temporary
+ * buffer, so we can reuse it for the tempfile exchrange information.
+ */
+ error = xrep_tempexch_trans_reserve(sc, XFS_DATA_FORK, &rts->tempexch);
+ if (error)
+ return error;
+
+ error = xrep_tempexch_contents(sc, &rts->tempexch);
+ if (error)
+ return error;
+
+ /* Reset incore state and blow out the summary cache. */
+ if (mp->m_rsum_cache)
+ memset(mp->m_rsum_cache, 0xFF, mp->m_sb.sb_rbmblocks);
+
+ mp->m_rsumlevels = rts->rsumlevels;
+ mp->m_rsumsize = rts->rsumsize;
+
+ /* Free the old rtsummary blocks if they're not in use. */
+ return xrep_reap_ifork(sc, sc->tempip, XFS_DATA_FORK);
+}
diff --git a/fs/xfs/scrub/scrub.c b/fs/xfs/scrub/scrub.c
index 20fac9723c..4cbcf7a86d 100644
--- a/fs/xfs/scrub/scrub.c
+++ b/fs/xfs/scrub/scrub.c
@@ -17,6 +17,11 @@
#include "xfs_scrub.h"
#include "xfs_buf_mem.h"
#include "xfs_rmap.h"
+#include "xfs_exchrange.h"
+#include "xfs_exchmaps.h"
+#include "xfs_dir2.h"
+#include "xfs_parent.h"
+#include "xfs_icache.h"
#include "scrub/scrub.h"
#include "scrub/common.h"
#include "scrub/trace.h"
@@ -24,6 +29,8 @@
#include "scrub/health.h"
#include "scrub/stats.h"
#include "scrub/xfile.h"
+#include "scrub/tempfile.h"
+#include "scrub/orphanage.h"
/*
* Online Scrub and Repair
@@ -171,6 +178,39 @@ xchk_fsgates_disable(
sc->flags &= ~XCHK_FSGATES_ALL;
}
+/* Free the resources associated with a scrub subtype. */
+void
+xchk_scrub_free_subord(
+ struct xfs_scrub_subord *sub)
+{
+ struct xfs_scrub *sc = sub->parent_sc;
+
+ ASSERT(sc->ip == sub->sc.ip);
+ ASSERT(sc->orphanage == sub->sc.orphanage);
+ ASSERT(sc->tempip == sub->sc.tempip);
+
+ sc->sm->sm_type = sub->old_smtype;
+ sc->sm->sm_flags = sub->old_smflags |
+ (sc->sm->sm_flags & XFS_SCRUB_FLAGS_OUT);
+ sc->tp = sub->sc.tp;
+
+ if (sub->sc.buf) {
+ if (sub->sc.buf_cleanup)
+ sub->sc.buf_cleanup(sub->sc.buf);
+ kvfree(sub->sc.buf);
+ }
+ if (sub->sc.xmbtp)
+ xmbuf_free(sub->sc.xmbtp);
+ if (sub->sc.xfile)
+ xfile_destroy(sub->sc.xfile);
+
+ sc->ilock_flags = sub->sc.ilock_flags;
+ sc->orphanage_ilock_flags = sub->sc.orphanage_ilock_flags;
+ sc->temp_ilock_flags = sub->sc.temp_ilock_flags;
+
+ kfree(sub);
+}
+
/* Free all the resources and finish the transactions. */
STATIC int
xchk_teardown(
@@ -211,6 +251,8 @@ xchk_teardown(
sc->buf = NULL;
}
+ xrep_tempfile_rele(sc);
+ xrep_orphanage_rele(sc);
xchk_fsgates_disable(sc);
return error;
}
@@ -319,25 +361,25 @@ static const struct xchk_meta_ops meta_scrub_ops[] = {
.type = ST_INODE,
.setup = xchk_setup_directory,
.scrub = xchk_directory,
- .repair = xrep_notsupported,
+ .repair = xrep_directory,
},
[XFS_SCRUB_TYPE_XATTR] = { /* extended attributes */
.type = ST_INODE,
.setup = xchk_setup_xattr,
.scrub = xchk_xattr,
- .repair = xrep_notsupported,
+ .repair = xrep_xattr,
},
[XFS_SCRUB_TYPE_SYMLINK] = { /* symbolic link */
.type = ST_INODE,
.setup = xchk_setup_symlink,
.scrub = xchk_symlink,
- .repair = xrep_notsupported,
+ .repair = xrep_symlink,
},
[XFS_SCRUB_TYPE_PARENT] = { /* parent pointers */
.type = ST_INODE,
.setup = xchk_setup_parent,
.scrub = xchk_parent,
- .repair = xrep_notsupported,
+ .repair = xrep_parent,
},
[XFS_SCRUB_TYPE_RTBITMAP] = { /* realtime bitmap */
.type = ST_FS,
@@ -349,7 +391,7 @@ static const struct xchk_meta_ops meta_scrub_ops[] = {
.type = ST_FS,
.setup = xchk_setup_rtsummary,
.scrub = xchk_rtsummary,
- .repair = xrep_notsupported,
+ .repair = xrep_rtsummary,
},
[XFS_SCRUB_TYPE_UQUOTA] = { /* user quota */
.type = ST_FS,
@@ -393,6 +435,13 @@ static const struct xchk_meta_ops meta_scrub_ops[] = {
.scrub = xchk_health_record,
.repair = xrep_notsupported,
},
+ [XFS_SCRUB_TYPE_DIRTREE] = { /* directory tree structure */
+ .type = ST_INODE,
+ .setup = xchk_setup_dirtree,
+ .scrub = xchk_dirtree,
+ .has = xfs_has_parent,
+ .repair = xrep_dirtree,
+ },
};
static int
@@ -497,8 +546,38 @@ static inline void xchk_postmortem(struct xfs_scrub *sc)
}
#endif /* CONFIG_XFS_ONLINE_REPAIR */
+/*
+ * Create a new scrub context from an existing one, but with a different scrub
+ * type.
+ */
+struct xfs_scrub_subord *
+xchk_scrub_create_subord(
+ struct xfs_scrub *sc,
+ unsigned int subtype)
+{
+ struct xfs_scrub_subord *sub;
+
+ sub = kzalloc(sizeof(*sub), XCHK_GFP_FLAGS);
+ if (!sub)
+ return ERR_PTR(-ENOMEM);
+
+ sub->old_smtype = sc->sm->sm_type;
+ sub->old_smflags = sc->sm->sm_flags;
+ sub->parent_sc = sc;
+ memcpy(&sub->sc, sc, sizeof(struct xfs_scrub));
+ sub->sc.ops = &meta_scrub_ops[subtype];
+ sub->sc.sm->sm_type = subtype;
+ sub->sc.sm->sm_flags &= ~XFS_SCRUB_FLAGS_OUT;
+ sub->sc.buf = NULL;
+ sub->sc.buf_cleanup = NULL;
+ sub->sc.xfile = NULL;
+ sub->sc.xmbtp = NULL;
+
+ return sub;
+}
+
/* Dispatch metadata scrubbing. */
-int
+STATIC int
xfs_scrub_metadata(
struct file *file,
struct xfs_scrub_metadata *sm)
@@ -540,6 +619,7 @@ xfs_scrub_metadata(
sc->sm = sm;
sc->ops = &meta_scrub_ops[sm->sm_type];
sc->sick_mask = xchk_health_mask_for_scrub_type(sm->sm_type);
+ sc->relax = INIT_XCHK_RELAX;
retry_op:
/*
* When repairs are allowed, prevent freezing or readonly remount while
@@ -643,3 +723,221 @@ try_harder:
run.retries++;
goto retry_op;
}
+
+/* Scrub one aspect of one piece of metadata. */
+int
+xfs_ioc_scrub_metadata(
+ struct file *file,
+ void __user *arg)
+{
+ struct xfs_scrub_metadata scrub;
+ int error;
+
+ if (!capable(CAP_SYS_ADMIN))
+ return -EPERM;
+
+ if (copy_from_user(&scrub, arg, sizeof(scrub)))
+ return -EFAULT;
+
+ error = xfs_scrub_metadata(file, &scrub);
+ if (error)
+ return error;
+
+ if (copy_to_user(arg, &scrub, sizeof(scrub)))
+ return -EFAULT;
+
+ return 0;
+}
+
+/* Decide if there have been any scrub failures up to this point. */
+static inline int
+xfs_scrubv_check_barrier(
+ struct xfs_mount *mp,
+ const struct xfs_scrub_vec *vectors,
+ const struct xfs_scrub_vec *stop_vec)
+{
+ const struct xfs_scrub_vec *v;
+ __u32 failmask;
+
+ failmask = stop_vec->sv_flags & XFS_SCRUB_FLAGS_OUT;
+
+ for (v = vectors; v < stop_vec; v++) {
+ if (v->sv_type == XFS_SCRUB_TYPE_BARRIER)
+ continue;
+
+ /*
+ * Runtime errors count as a previous failure, except the ones
+ * used to ask userspace to retry.
+ */
+ switch (v->sv_ret) {
+ case -EBUSY:
+ case -ENOENT:
+ case -EUSERS:
+ case 0:
+ break;
+ default:
+ return -ECANCELED;
+ }
+
+ /*
+ * If any of the out-flags on the scrub vector match the mask
+ * that was set on the barrier vector, that's a previous fail.
+ */
+ if (v->sv_flags & failmask)
+ return -ECANCELED;
+ }
+
+ return 0;
+}
+
+/*
+ * If the caller provided us with a nonzero inode number that isn't the ioctl
+ * file, try to grab a reference to it to eliminate all further untrusted inode
+ * lookups. If we can't get the inode, let each scrub function try again.
+ */
+STATIC struct xfs_inode *
+xchk_scrubv_open_by_handle(
+ struct xfs_mount *mp,
+ const struct xfs_scrub_vec_head *head)
+{
+ struct xfs_trans *tp;
+ struct xfs_inode *ip;
+ int error;
+
+ error = xfs_trans_alloc_empty(mp, &tp);
+ if (error)
+ return NULL;
+
+ error = xfs_iget(mp, tp, head->svh_ino, XCHK_IGET_FLAGS, 0, &ip);
+ xfs_trans_cancel(tp);
+ if (error)
+ return NULL;
+
+ if (VFS_I(ip)->i_generation != head->svh_gen) {
+ xfs_irele(ip);
+ return NULL;
+ }
+
+ return ip;
+}
+
+/* Vectored scrub implementation to reduce ioctl calls. */
+int
+xfs_ioc_scrubv_metadata(
+ struct file *file,
+ void __user *arg)
+{
+ struct xfs_scrub_vec_head head;
+ struct xfs_scrub_vec_head __user *uhead = arg;
+ struct xfs_scrub_vec *vectors;
+ struct xfs_scrub_vec __user *uvectors;
+ struct xfs_inode *ip_in = XFS_I(file_inode(file));
+ struct xfs_mount *mp = ip_in->i_mount;
+ struct xfs_inode *handle_ip = NULL;
+ struct xfs_scrub_vec *v;
+ size_t vec_bytes;
+ unsigned int i;
+ int error = 0;
+
+ if (!capable(CAP_SYS_ADMIN))
+ return -EPERM;
+
+ if (copy_from_user(&head, uhead, sizeof(head)))
+ return -EFAULT;
+
+ if (head.svh_reserved)
+ return -EINVAL;
+ if (head.svh_flags & ~XFS_SCRUB_VEC_FLAGS_ALL)
+ return -EINVAL;
+ if (head.svh_nr == 0)
+ return 0;
+
+ vec_bytes = array_size(head.svh_nr, sizeof(struct xfs_scrub_vec));
+ if (vec_bytes > PAGE_SIZE)
+ return -ENOMEM;
+
+ uvectors = u64_to_user_ptr(head.svh_vectors);
+ vectors = memdup_user(uvectors, vec_bytes);
+ if (IS_ERR(vectors))
+ return PTR_ERR(vectors);
+
+ trace_xchk_scrubv_start(ip_in, &head);
+
+ for (i = 0, v = vectors; i < head.svh_nr; i++, v++) {
+ if (v->sv_reserved) {
+ error = -EINVAL;
+ goto out_free;
+ }
+
+ if (v->sv_type == XFS_SCRUB_TYPE_BARRIER &&
+ (v->sv_flags & ~XFS_SCRUB_FLAGS_OUT)) {
+ error = -EINVAL;
+ goto out_free;
+ }
+
+ trace_xchk_scrubv_item(mp, &head, i, v);
+ }
+
+ /*
+ * If the caller wants us to do a scrub-by-handle and the file used to
+ * call the ioctl is not the same file, load the incore inode and pin
+ * it across all the scrubv actions to avoid repeated UNTRUSTED
+ * lookups. The reference is not passed to deeper layers of scrub
+ * because each scrubber gets to decide its own strategy and return
+ * values for getting an inode.
+ */
+ if (head.svh_ino && head.svh_ino != ip_in->i_ino)
+ handle_ip = xchk_scrubv_open_by_handle(mp, &head);
+
+ /* Run all the scrubbers. */
+ for (i = 0, v = vectors; i < head.svh_nr; i++, v++) {
+ struct xfs_scrub_metadata sm = {
+ .sm_type = v->sv_type,
+ .sm_flags = v->sv_flags,
+ .sm_ino = head.svh_ino,
+ .sm_gen = head.svh_gen,
+ .sm_agno = head.svh_agno,
+ };
+
+ if (v->sv_type == XFS_SCRUB_TYPE_BARRIER) {
+ v->sv_ret = xfs_scrubv_check_barrier(mp, vectors, v);
+ if (v->sv_ret) {
+ trace_xchk_scrubv_barrier_fail(mp, &head, i, v);
+ break;
+ }
+
+ continue;
+ }
+
+ v->sv_ret = xfs_scrub_metadata(file, &sm);
+ v->sv_flags = sm.sm_flags;
+
+ trace_xchk_scrubv_outcome(mp, &head, i, v);
+
+ if (head.svh_rest_us) {
+ ktime_t expires;
+
+ expires = ktime_add_ns(ktime_get(),
+ head.svh_rest_us * 1000);
+ set_current_state(TASK_KILLABLE);
+ schedule_hrtimeout(&expires, HRTIMER_MODE_ABS);
+ }
+
+ if (fatal_signal_pending(current)) {
+ error = -EINTR;
+ goto out_free;
+ }
+ }
+
+ if (copy_to_user(uvectors, vectors, vec_bytes) ||
+ copy_to_user(uhead, &head, sizeof(head))) {
+ error = -EFAULT;
+ goto out_free;
+ }
+
+out_free:
+ if (handle_ip)
+ xfs_irele(handle_ip);
+ kfree(vectors);
+ return error;
+}
diff --git a/fs/xfs/scrub/scrub.h b/fs/xfs/scrub/scrub.h
index 9ad65b604f..1bc33f010d 100644
--- a/fs/xfs/scrub/scrub.h
+++ b/fs/xfs/scrub/scrub.h
@@ -8,6 +8,49 @@
struct xfs_scrub;
+struct xchk_relax {
+ unsigned long next_resched;
+ unsigned int resched_nr;
+ bool interruptible;
+};
+
+/* Yield to the scheduler at most 10x per second. */
+#define XCHK_RELAX_NEXT (jiffies + (HZ / 10))
+
+#define INIT_XCHK_RELAX \
+ (struct xchk_relax){ \
+ .next_resched = XCHK_RELAX_NEXT, \
+ .resched_nr = 0, \
+ .interruptible = true, \
+ }
+
+/*
+ * Relax during a scrub operation and exit if there's a fatal signal pending.
+ *
+ * If preemption is disabled, we need to yield to the scheduler every now and
+ * then so that we don't run afoul of the soft lockup watchdog or RCU stall
+ * detector. cond_resched calls are somewhat expensive (~5ns) so we want to
+ * ratelimit this to 10x per second. Amortize the cost of the other checks by
+ * only doing it once every 100 calls.
+ */
+static inline int xchk_maybe_relax(struct xchk_relax *widget)
+{
+ /* Amortize the cost of scheduling and checking signals. */
+ if (likely(++widget->resched_nr < 100))
+ return 0;
+ widget->resched_nr = 0;
+
+ if (unlikely(widget->next_resched <= jiffies)) {
+ cond_resched();
+ widget->next_resched = XCHK_RELAX_NEXT;
+ }
+
+ if (widget->interruptible && fatal_signal_pending(current))
+ return -EINTR;
+
+ return 0;
+}
+
/*
* Standard flags for allocating memory within scrub. NOFS context is
* configured by the process allocation scope. Scrub and repair must be able
@@ -17,6 +60,13 @@ struct xfs_scrub;
#define XCHK_GFP_FLAGS ((__force gfp_t)(GFP_KERNEL | __GFP_NOWARN | \
__GFP_RETRY_MAYFAIL))
+/*
+ * For opening files by handle for fsck operations, we don't trust the inumber
+ * or the allocation state; therefore, perform an untrusted lookup. We don't
+ * want these inodes to pollute the cache, so mark them for immediate removal.
+ */
+#define XCHK_IGET_FLAGS (XFS_IGET_UNTRUSTED | XFS_IGET_DONTCACHE)
+
/* Type info and names for the scrub types. */
enum xchk_type {
ST_NONE = 1, /* disabled */
@@ -105,6 +155,14 @@ struct xfs_scrub {
/* Lock flags for @ip. */
uint ilock_flags;
+ /* The orphanage, for stashing files that have lost their parent. */
+ uint orphanage_ilock_flags;
+ struct xfs_inode *orphanage;
+
+ /* A temporary file on this filesystem, for staging new metadata. */
+ struct xfs_inode *tempip;
+ uint temp_ilock_flags;
+
/* See the XCHK/XREP state flags below. */
unsigned int flags;
@@ -115,6 +173,9 @@ struct xfs_scrub {
*/
unsigned int sick_mask;
+ /* next time we want to cond_resched() */
+ struct xchk_relax relax;
+
/* State tracking for single-AG operations. */
struct xchk_ag sa;
};
@@ -141,6 +202,35 @@ struct xfs_scrub {
XCHK_FSGATES_DIRENTS | \
XCHK_FSGATES_RMAP)
+struct xfs_scrub_subord {
+ struct xfs_scrub sc;
+ struct xfs_scrub *parent_sc;
+ unsigned int old_smtype;
+ unsigned int old_smflags;
+};
+
+struct xfs_scrub_subord *xchk_scrub_create_subord(struct xfs_scrub *sc,
+ unsigned int subtype);
+void xchk_scrub_free_subord(struct xfs_scrub_subord *sub);
+
+/*
+ * We /could/ terminate a scrub/repair operation early. If we're not
+ * in a good place to continue (fatal signal, etc.) then bail out.
+ * Note that we're careful not to make any judgements about *error.
+ */
+static inline bool
+xchk_should_terminate(
+ struct xfs_scrub *sc,
+ int *error)
+{
+ if (xchk_maybe_relax(&sc->relax)) {
+ if (*error == 0)
+ *error = -EINTR;
+ return true;
+ }
+ return false;
+}
+
/* Metadata scrubbers */
int xchk_tester(struct xfs_scrub *sc);
int xchk_superblock(struct xfs_scrub *sc);
@@ -159,6 +249,7 @@ int xchk_directory(struct xfs_scrub *sc);
int xchk_xattr(struct xfs_scrub *sc);
int xchk_symlink(struct xfs_scrub *sc);
int xchk_parent(struct xfs_scrub *sc);
+int xchk_dirtree(struct xfs_scrub *sc);
#ifdef CONFIG_XFS_RT
int xchk_rtbitmap(struct xfs_scrub *sc);
int xchk_rtsummary(struct xfs_scrub *sc);
diff --git a/fs/xfs/scrub/stats.c b/fs/xfs/scrub/stats.c
index 42cafbed94..7996c23354 100644
--- a/fs/xfs/scrub/stats.c
+++ b/fs/xfs/scrub/stats.c
@@ -79,6 +79,7 @@ static const char *name_map[XFS_SCRUB_TYPE_NR] = {
[XFS_SCRUB_TYPE_FSCOUNTERS] = "fscounters",
[XFS_SCRUB_TYPE_QUOTACHECK] = "quotacheck",
[XFS_SCRUB_TYPE_NLINKS] = "nlinks",
+ [XFS_SCRUB_TYPE_DIRTREE] = "dirtree",
};
/* Format the scrub stats into a text buffer, similar to pcp style. */
diff --git a/fs/xfs/scrub/symlink.c b/fs/xfs/scrub/symlink.c
index d77d8a9598..c848bcc07c 100644
--- a/fs/xfs/scrub/symlink.c
+++ b/fs/xfs/scrub/symlink.c
@@ -10,6 +10,7 @@
#include "xfs_trans_resv.h"
#include "xfs_mount.h"
#include "xfs_log_format.h"
+#include "xfs_trans.h"
#include "xfs_inode.h"
#include "xfs_symlink.h"
#include "xfs_health.h"
@@ -17,18 +18,28 @@
#include "scrub/scrub.h"
#include "scrub/common.h"
#include "scrub/health.h"
+#include "scrub/repair.h"
/* Set us up to scrub a symbolic link. */
int
xchk_setup_symlink(
struct xfs_scrub *sc)
{
+ unsigned int resblks = 0;
+ int error;
+
/* Allocate the buffer without the inode lock held. */
sc->buf = kvzalloc(XFS_SYMLINK_MAXLEN + 1, XCHK_GFP_FLAGS);
if (!sc->buf)
return -ENOMEM;
- return xchk_setup_inode_contents(sc, 0);
+ if (xchk_could_repair(sc)) {
+ error = xrep_setup_symlink(sc, &resblks);
+ if (error)
+ return error;
+ }
+
+ return xchk_setup_inode_contents(sc, resblks);
}
/* Symbolic links. */
diff --git a/fs/xfs/scrub/symlink_repair.c b/fs/xfs/scrub/symlink_repair.c
new file mode 100644
index 0000000000..d015a86ef4
--- /dev/null
+++ b/fs/xfs/scrub/symlink_repair.c
@@ -0,0 +1,509 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Copyright (c) 2018-2024 Oracle. All Rights Reserved.
+ * Author: Darrick J. Wong <djwong@kernel.org>
+ */
+#include "xfs.h"
+#include "xfs_fs.h"
+#include "xfs_shared.h"
+#include "xfs_format.h"
+#include "xfs_trans_resv.h"
+#include "xfs_mount.h"
+#include "xfs_defer.h"
+#include "xfs_btree.h"
+#include "xfs_bit.h"
+#include "xfs_log_format.h"
+#include "xfs_trans.h"
+#include "xfs_sb.h"
+#include "xfs_inode.h"
+#include "xfs_inode_fork.h"
+#include "xfs_symlink.h"
+#include "xfs_bmap.h"
+#include "xfs_quota.h"
+#include "xfs_da_format.h"
+#include "xfs_da_btree.h"
+#include "xfs_bmap_btree.h"
+#include "xfs_trans_space.h"
+#include "xfs_symlink_remote.h"
+#include "xfs_exchmaps.h"
+#include "xfs_exchrange.h"
+#include "xfs_health.h"
+#include "scrub/xfs_scrub.h"
+#include "scrub/scrub.h"
+#include "scrub/common.h"
+#include "scrub/trace.h"
+#include "scrub/repair.h"
+#include "scrub/tempfile.h"
+#include "scrub/tempexch.h"
+#include "scrub/reap.h"
+
+/*
+ * Symbolic Link Repair
+ * ====================
+ *
+ * We repair symbolic links by reading whatever target data we can find, up to
+ * the first NULL byte. If the recovered target strlen matches i_size, then
+ * we rewrite the target. In all other cases, we replace the target with an
+ * overly long string that cannot possibly resolve. The new target is written
+ * into a private hidden temporary file, and then a file contents exchange
+ * commits the new symlink target to the file being repaired.
+ */
+
+/* Set us up to repair the symlink file. */
+int
+xrep_setup_symlink(
+ struct xfs_scrub *sc,
+ unsigned int *resblks)
+{
+ struct xfs_mount *mp = sc->mp;
+ unsigned long long blocks;
+ int error;
+
+ error = xrep_tempfile_create(sc, S_IFLNK);
+ if (error)
+ return error;
+
+ /*
+ * If we're doing a repair, we reserve enough blocks to write out a
+ * completely new symlink file, plus twice as many blocks as we would
+ * need if we can only allocate one block per data fork mapping. This
+ * should cover the preallocation of the temporary file and exchanging
+ * the extent mappings.
+ *
+ * We cannot use xfs_exchmaps_estimate because we have not yet
+ * constructed the replacement symlink and therefore do not know how
+ * many extents it will use. By the time we do, we will have a dirty
+ * transaction (which we cannot drop because we cannot drop the
+ * symlink ILOCK) and cannot ask for more reservation.
+ */
+ blocks = xfs_symlink_blocks(sc->mp, XFS_SYMLINK_MAXLEN);
+ blocks += xfs_bmbt_calc_size(mp, blocks) * 2;
+ if (blocks > UINT_MAX)
+ return -EOPNOTSUPP;
+
+ *resblks += blocks;
+ return 0;
+}
+
+/*
+ * Try to salvage the pathname from remote blocks. Returns the number of bytes
+ * salvaged or a negative errno.
+ */
+STATIC ssize_t
+xrep_symlink_salvage_remote(
+ struct xfs_scrub *sc)
+{
+ struct xfs_bmbt_irec mval[XFS_SYMLINK_MAPS];
+ struct xfs_inode *ip = sc->ip;
+ struct xfs_buf *bp;
+ char *target_buf = sc->buf;
+ xfs_failaddr_t fa;
+ xfs_filblks_t fsblocks;
+ xfs_daddr_t d;
+ loff_t len;
+ loff_t offset = 0;
+ unsigned int byte_cnt;
+ bool magic_ok;
+ bool hdr_ok;
+ int n;
+ int nmaps = XFS_SYMLINK_MAPS;
+ int error;
+
+ /* We'll only read until the buffer is full. */
+ len = min_t(loff_t, ip->i_disk_size, XFS_SYMLINK_MAXLEN);
+ fsblocks = xfs_symlink_blocks(sc->mp, len);
+ error = xfs_bmapi_read(ip, 0, fsblocks, mval, &nmaps, 0);
+ if (error)
+ return error;
+
+ for (n = 0; n < nmaps; n++) {
+ struct xfs_dsymlink_hdr *dsl;
+
+ d = XFS_FSB_TO_DADDR(sc->mp, mval[n].br_startblock);
+
+ /* Read the rmt block. We'll run the verifiers manually. */
+ error = xfs_trans_read_buf(sc->mp, sc->tp, sc->mp->m_ddev_targp,
+ d, XFS_FSB_TO_BB(sc->mp, mval[n].br_blockcount),
+ 0, &bp, NULL);
+ if (error)
+ return error;
+ bp->b_ops = &xfs_symlink_buf_ops;
+
+ /* How many bytes do we expect to get out of this buffer? */
+ byte_cnt = XFS_FSB_TO_B(sc->mp, mval[n].br_blockcount);
+ byte_cnt = XFS_SYMLINK_BUF_SPACE(sc->mp, byte_cnt);
+ byte_cnt = min_t(unsigned int, byte_cnt, len);
+
+ /*
+ * See if the verifiers accept this block. We're willing to
+ * salvage if the if the offset/byte/ino are ok and either the
+ * verifier passed or the magic is ok. Anything else and we
+ * stop dead in our tracks.
+ */
+ fa = bp->b_ops->verify_struct(bp);
+ dsl = bp->b_addr;
+ magic_ok = dsl->sl_magic == cpu_to_be32(XFS_SYMLINK_MAGIC);
+ hdr_ok = xfs_symlink_hdr_ok(ip->i_ino, offset, byte_cnt, bp);
+ if (!hdr_ok || (fa != NULL && !magic_ok))
+ break;
+
+ memcpy(target_buf + offset, dsl + 1, byte_cnt);
+
+ len -= byte_cnt;
+ offset += byte_cnt;
+ }
+ return offset;
+}
+
+/*
+ * Try to salvage an inline symlink's contents. Returns the number of bytes
+ * salvaged or a negative errno.
+ */
+STATIC ssize_t
+xrep_symlink_salvage_inline(
+ struct xfs_scrub *sc)
+{
+ struct xfs_inode *ip = sc->ip;
+ char *target_buf = sc->buf;
+ char *old_target;
+ struct xfs_ifork *ifp;
+ unsigned int nr;
+
+ ifp = xfs_ifork_ptr(ip, XFS_DATA_FORK);
+ if (!ifp->if_data)
+ return 0;
+
+ /*
+ * If inode repair zapped the link target, pretend that we didn't find
+ * any bytes at all so that we can replace the (now totally lost) link
+ * target with a warning message.
+ */
+ old_target = ifp->if_data;
+ if (xfs_inode_has_sickness(sc->ip, XFS_SICK_INO_SYMLINK_ZAPPED) &&
+ sc->ip->i_disk_size == 1 && old_target[0] == '?')
+ return 0;
+
+ nr = min(XFS_SYMLINK_MAXLEN, xfs_inode_data_fork_size(ip));
+ strncpy(target_buf, ifp->if_data, nr);
+ return nr;
+}
+
+#define DUMMY_TARGET \
+ "The target of this symbolic link could not be recovered at all and " \
+ "has been replaced with this explanatory message. To avoid " \
+ "accidentally pointing to an existing file path, this message is " \
+ "longer than the maximum supported file name length. That is an " \
+ "acceptable length for a symlink target on XFS but will produce " \
+ "File Name Too Long errors if resolved."
+
+/* Salvage whatever we can of the target. */
+STATIC int
+xrep_symlink_salvage(
+ struct xfs_scrub *sc)
+{
+ char *target_buf = sc->buf;
+ ssize_t buflen = 0;
+
+ BUILD_BUG_ON(sizeof(DUMMY_TARGET) - 1 <= NAME_MAX);
+
+ /*
+ * Salvage the target if there weren't any corruption problems observed
+ * while scanning it.
+ */
+ if (!(sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT)) {
+ if (sc->ip->i_df.if_format == XFS_DINODE_FMT_LOCAL)
+ buflen = xrep_symlink_salvage_inline(sc);
+ else
+ buflen = xrep_symlink_salvage_remote(sc);
+ if (buflen < 0)
+ return buflen;
+
+ /*
+ * NULL-terminate the buffer because the ondisk target does not
+ * do that for us. If salvage didn't find the exact amount of
+ * data that we expected to find, don't salvage anything.
+ */
+ target_buf[buflen] = 0;
+ if (strlen(target_buf) != sc->ip->i_disk_size)
+ buflen = 0;
+ }
+
+ /*
+ * Change an empty target into a dummy target and clear the symlink
+ * target zapped flag.
+ */
+ if (buflen == 0) {
+ sc->sick_mask |= XFS_SICK_INO_SYMLINK_ZAPPED;
+ sprintf(target_buf, DUMMY_TARGET);
+ }
+
+ trace_xrep_symlink_salvage_target(sc->ip, target_buf,
+ strlen(target_buf));
+ return 0;
+}
+
+STATIC void
+xrep_symlink_local_to_remote(
+ struct xfs_trans *tp,
+ struct xfs_buf *bp,
+ struct xfs_inode *ip,
+ struct xfs_ifork *ifp,
+ void *priv)
+{
+ struct xfs_scrub *sc = priv;
+ struct xfs_dsymlink_hdr *dsl = bp->b_addr;
+
+ xfs_symlink_local_to_remote(tp, bp, ip, ifp, NULL);
+
+ if (!xfs_has_crc(sc->mp))
+ return;
+
+ dsl->sl_owner = cpu_to_be64(sc->ip->i_ino);
+ xfs_trans_log_buf(tp, bp, 0,
+ sizeof(struct xfs_dsymlink_hdr) + ifp->if_bytes - 1);
+}
+
+/*
+ * Prepare both links' data forks for an exchange. Promote the tempfile from
+ * local format to extents format, and if the file being repaired has a short
+ * format data fork, turn it into an empty extent list.
+ */
+STATIC int
+xrep_symlink_swap_prep(
+ struct xfs_scrub *sc,
+ bool temp_local,
+ bool ip_local)
+{
+ int error;
+
+ /*
+ * If the temp link is in shortform format, convert that to a remote
+ * target so that we can use the atomic mapping exchange.
+ */
+ if (temp_local) {
+ int logflags = XFS_ILOG_CORE;
+
+ error = xfs_bmap_local_to_extents(sc->tp, sc->tempip, 1,
+ &logflags, XFS_DATA_FORK,
+ xrep_symlink_local_to_remote,
+ sc);
+ if (error)
+ return error;
+
+ xfs_trans_log_inode(sc->tp, sc->ip, 0);
+
+ error = xfs_defer_finish(&sc->tp);
+ if (error)
+ return error;
+ }
+
+ /*
+ * If the file being repaired had a shortform data fork, convert that
+ * to an empty extent list in preparation for the atomic mapping
+ * exchange.
+ */
+ if (ip_local) {
+ struct xfs_ifork *ifp;
+
+ ifp = xfs_ifork_ptr(sc->ip, XFS_DATA_FORK);
+ xfs_idestroy_fork(ifp);
+ ifp->if_format = XFS_DINODE_FMT_EXTENTS;
+ ifp->if_nextents = 0;
+ ifp->if_bytes = 0;
+ ifp->if_data = NULL;
+ ifp->if_height = 0;
+
+ xfs_trans_log_inode(sc->tp, sc->ip,
+ XFS_ILOG_CORE | XFS_ILOG_DDATA);
+ }
+
+ return 0;
+}
+
+/* Exchange the temporary symlink's data fork with the one being repaired. */
+STATIC int
+xrep_symlink_swap(
+ struct xfs_scrub *sc)
+{
+ struct xrep_tempexch *tx = sc->buf;
+ bool ip_local, temp_local;
+ int error;
+
+ ip_local = sc->ip->i_df.if_format == XFS_DINODE_FMT_LOCAL;
+ temp_local = sc->tempip->i_df.if_format == XFS_DINODE_FMT_LOCAL;
+
+ /*
+ * If the both links have a local format data fork and the rebuilt
+ * remote data would fit in the repaired file's data fork, copy the
+ * contents from the tempfile and declare ourselves done.
+ */
+ if (ip_local && temp_local &&
+ sc->tempip->i_disk_size <= xfs_inode_data_fork_size(sc->ip)) {
+ xrep_tempfile_copyout_local(sc, XFS_DATA_FORK);
+ return 0;
+ }
+
+ /* Otherwise, make sure both data forks are in block-mapping mode. */
+ error = xrep_symlink_swap_prep(sc, temp_local, ip_local);
+ if (error)
+ return error;
+
+ return xrep_tempexch_contents(sc, tx);
+}
+
+/*
+ * Free all the remote blocks and reset the data fork. The caller must join
+ * the inode to the transaction. This function returns with the inode joined
+ * to a clean scrub transaction.
+ */
+STATIC int
+xrep_symlink_reset_fork(
+ struct xfs_scrub *sc)
+{
+ struct xfs_ifork *ifp = xfs_ifork_ptr(sc->tempip, XFS_DATA_FORK);
+ int error;
+
+ /* Unmap all the remote target buffers. */
+ if (xfs_ifork_has_extents(ifp)) {
+ error = xrep_reap_ifork(sc, sc->tempip, XFS_DATA_FORK);
+ if (error)
+ return error;
+ }
+
+ trace_xrep_symlink_reset_fork(sc->tempip);
+
+ /* Reset the temp symlink target to dummy content. */
+ xfs_idestroy_fork(ifp);
+ return xfs_symlink_write_target(sc->tp, sc->tempip, sc->tempip->i_ino,
+ "?", 1, 0, 0);
+}
+
+/*
+ * Reinitialize a link target. Caller must ensure the inode is joined to
+ * the transaction.
+ */
+STATIC int
+xrep_symlink_rebuild(
+ struct xfs_scrub *sc)
+{
+ struct xrep_tempexch *tx;
+ char *target_buf = sc->buf;
+ xfs_fsblock_t fs_blocks;
+ unsigned int target_len;
+ unsigned int resblks;
+ int error;
+
+ /* How many blocks do we need? */
+ target_len = strlen(target_buf);
+ ASSERT(target_len != 0);
+ if (target_len == 0 || target_len > XFS_SYMLINK_MAXLEN)
+ return -EFSCORRUPTED;
+
+ trace_xrep_symlink_rebuild(sc->ip);
+
+ /*
+ * In preparation to write the new symlink target to the temporary
+ * file, drop the ILOCK of the file being repaired (it shouldn't be
+ * joined) and take the ILOCK of the temporary file.
+ *
+ * The VFS does not take the IOLOCK while reading a symlink (and new
+ * symlinks are hidden with INEW until they've been written) so it's
+ * possible that a readlink() could see the old corrupted contents
+ * while we're doing this.
+ */
+ xchk_iunlock(sc, XFS_ILOCK_EXCL);
+ xrep_tempfile_ilock(sc);
+ xfs_trans_ijoin(sc->tp, sc->tempip, 0);
+
+ /*
+ * Reserve resources to reinitialize the target. We're allowed to
+ * exceed file quota to repair inconsistent metadata, though this is
+ * unlikely.
+ */
+ fs_blocks = xfs_symlink_blocks(sc->mp, target_len);
+ resblks = xfs_symlink_space_res(sc->mp, target_len, fs_blocks);
+ error = xfs_trans_reserve_quota_nblks(sc->tp, sc->tempip, resblks, 0,
+ true);
+ if (error)
+ return error;
+
+ /* Erase the dummy target set up by the tempfile initialization. */
+ xfs_idestroy_fork(&sc->tempip->i_df);
+ sc->tempip->i_df.if_bytes = 0;
+ sc->tempip->i_df.if_format = XFS_DINODE_FMT_EXTENTS;
+
+ /* Write the salvaged target to the temporary link. */
+ error = xfs_symlink_write_target(sc->tp, sc->tempip, sc->ip->i_ino,
+ target_buf, target_len, fs_blocks, resblks);
+ if (error)
+ return error;
+
+ /*
+ * Commit the repair transaction so that we can use the atomic mapping
+ * exchange functions to compute the correct block reservations and
+ * re-lock the inodes.
+ */
+ target_buf = NULL;
+ error = xrep_trans_commit(sc);
+ if (error)
+ return error;
+
+ /* Last chance to abort before we start committing fixes. */
+ if (xchk_should_terminate(sc, &error))
+ return error;
+
+ xrep_tempfile_iunlock(sc);
+
+ /*
+ * We're done with the temporary buffer, so we can reuse it for the
+ * tempfile contents exchange information.
+ */
+ tx = sc->buf;
+ error = xrep_tempexch_trans_alloc(sc, XFS_DATA_FORK, tx);
+ if (error)
+ return error;
+
+ /*
+ * Exchange the temp link's data fork with the file being repaired.
+ * This recreates the transaction and takes the ILOCKs of the file
+ * being repaired and the temporary file.
+ */
+ error = xrep_symlink_swap(sc);
+ if (error)
+ return error;
+
+ /*
+ * Release the old symlink blocks and reset the data fork of the temp
+ * link to an empty shortform link. This is the last repair action we
+ * perform on the symlink, so we don't need to clean the transaction.
+ */
+ return xrep_symlink_reset_fork(sc);
+}
+
+/* Repair a symbolic link. */
+int
+xrep_symlink(
+ struct xfs_scrub *sc)
+{
+ int error;
+
+ /* The rmapbt is required to reap the old data fork. */
+ if (!xfs_has_rmapbt(sc->mp))
+ return -EOPNOTSUPP;
+ /* We require atomic file exchange range to rebuild anything. */
+ if (!xfs_has_exchange_range(sc->mp))
+ return -EOPNOTSUPP;
+
+ ASSERT(sc->ilock_flags & XFS_ILOCK_EXCL);
+
+ error = xrep_symlink_salvage(sc);
+ if (error)
+ return error;
+
+ /* Now reset the target. */
+ error = xrep_symlink_rebuild(sc);
+ if (error)
+ return error;
+
+ return xrep_trans_commit(sc);
+}
diff --git a/fs/xfs/scrub/tempexch.h b/fs/xfs/scrub/tempexch.h
new file mode 100644
index 0000000000..995ba187c5
--- /dev/null
+++ b/fs/xfs/scrub/tempexch.h
@@ -0,0 +1,22 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Copyright (c) 2022-2024 Oracle. All Rights Reserved.
+ * Author: Darrick J. Wong <djwong@kernel.org>
+ */
+#ifndef __XFS_SCRUB_TEMPEXCH_H__
+#define __XFS_SCRUB_TEMPEXCH_H__
+
+#ifdef CONFIG_XFS_ONLINE_REPAIR
+struct xrep_tempexch {
+ struct xfs_exchmaps_req req;
+};
+
+int xrep_tempexch_trans_reserve(struct xfs_scrub *sc, int whichfork,
+ struct xrep_tempexch *ti);
+int xrep_tempexch_trans_alloc(struct xfs_scrub *sc, int whichfork,
+ struct xrep_tempexch *ti);
+
+int xrep_tempexch_contents(struct xfs_scrub *sc, struct xrep_tempexch *ti);
+#endif /* CONFIG_XFS_ONLINE_REPAIR */
+
+#endif /* __XFS_SCRUB_TEMPEXCH_H__ */
diff --git a/fs/xfs/scrub/tempfile.c b/fs/xfs/scrub/tempfile.c
new file mode 100644
index 0000000000..b747b625c5
--- /dev/null
+++ b/fs/xfs/scrub/tempfile.c
@@ -0,0 +1,851 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Copyright (c) 2021-2024 Oracle. All Rights Reserved.
+ * Author: Darrick J. Wong <djwong@kernel.org>
+ */
+#include "xfs.h"
+#include "xfs_fs.h"
+#include "xfs_shared.h"
+#include "xfs_format.h"
+#include "xfs_trans_resv.h"
+#include "xfs_mount.h"
+#include "xfs_log_format.h"
+#include "xfs_trans.h"
+#include "xfs_inode.h"
+#include "xfs_ialloc.h"
+#include "xfs_quota.h"
+#include "xfs_bmap.h"
+#include "xfs_bmap_btree.h"
+#include "xfs_trans_space.h"
+#include "xfs_dir2.h"
+#include "xfs_exchrange.h"
+#include "xfs_exchmaps.h"
+#include "xfs_defer.h"
+#include "xfs_symlink_remote.h"
+#include "scrub/scrub.h"
+#include "scrub/common.h"
+#include "scrub/repair.h"
+#include "scrub/trace.h"
+#include "scrub/tempfile.h"
+#include "scrub/tempexch.h"
+#include "scrub/xfile.h"
+
+/*
+ * Create a temporary file for reconstructing metadata, with the intention of
+ * atomically exchanging the temporary file's contents with the file that's
+ * being repaired.
+ */
+int
+xrep_tempfile_create(
+ struct xfs_scrub *sc,
+ uint16_t mode)
+{
+ struct xfs_mount *mp = sc->mp;
+ struct xfs_trans *tp = NULL;
+ struct xfs_dquot *udqp = NULL;
+ struct xfs_dquot *gdqp = NULL;
+ struct xfs_dquot *pdqp = NULL;
+ struct xfs_trans_res *tres;
+ struct xfs_inode *dp = mp->m_rootip;
+ xfs_ino_t ino;
+ unsigned int resblks;
+ bool is_dir = S_ISDIR(mode);
+ int error;
+
+ if (xfs_is_shutdown(mp))
+ return -EIO;
+ if (xfs_is_readonly(mp))
+ return -EROFS;
+
+ ASSERT(sc->tp == NULL);
+ ASSERT(sc->tempip == NULL);
+
+ /*
+ * Make sure that we have allocated dquot(s) on disk. The temporary
+ * inode should be completely root owned so that we don't fail due to
+ * quota limits.
+ */
+ error = xfs_qm_vop_dqalloc(dp, GLOBAL_ROOT_UID, GLOBAL_ROOT_GID, 0,
+ XFS_QMOPT_QUOTALL, &udqp, &gdqp, &pdqp);
+ if (error)
+ return error;
+
+ if (is_dir) {
+ resblks = xfs_mkdir_space_res(mp, 0);
+ tres = &M_RES(mp)->tr_mkdir;
+ } else {
+ resblks = XFS_IALLOC_SPACE_RES(mp);
+ tres = &M_RES(mp)->tr_create_tmpfile;
+ }
+
+ error = xfs_trans_alloc_icreate(mp, tres, udqp, gdqp, pdqp, resblks,
+ &tp);
+ if (error)
+ goto out_release_dquots;
+
+ /* Allocate inode, set up directory. */
+ error = xfs_dialloc(&tp, dp->i_ino, mode, &ino);
+ if (error)
+ goto out_trans_cancel;
+ error = xfs_init_new_inode(&nop_mnt_idmap, tp, dp, ino, mode, 0, 0,
+ 0, false, &sc->tempip);
+ if (error)
+ goto out_trans_cancel;
+
+ /* Change the ownership of the inode to root. */
+ VFS_I(sc->tempip)->i_uid = GLOBAL_ROOT_UID;
+ VFS_I(sc->tempip)->i_gid = GLOBAL_ROOT_GID;
+ sc->tempip->i_diflags &= ~(XFS_DIFLAG_REALTIME | XFS_DIFLAG_RTINHERIT);
+ xfs_trans_log_inode(tp, sc->tempip, XFS_ILOG_CORE);
+
+ /*
+ * Mark our temporary file as private so that LSMs and the ACL code
+ * don't try to add their own metadata or reason about these files.
+ * The file should never be exposed to userspace.
+ */
+ VFS_I(sc->tempip)->i_flags |= S_PRIVATE;
+ VFS_I(sc->tempip)->i_opflags &= ~IOP_XATTR;
+
+ if (is_dir) {
+ error = xfs_dir_init(tp, sc->tempip, dp);
+ if (error)
+ goto out_trans_cancel;
+ } else if (S_ISLNK(VFS_I(sc->tempip)->i_mode)) {
+ /*
+ * Initialize the temporary symlink with a meaningless target
+ * that won't trip the verifiers. Repair must rewrite the
+ * target with meaningful content before swapping with the file
+ * being repaired. A single-byte target will not write a
+ * remote target block, so the owner is irrelevant.
+ */
+ error = xfs_symlink_write_target(tp, sc->tempip,
+ sc->tempip->i_ino, ".", 1, 0, 0);
+ if (error)
+ goto out_trans_cancel;
+ }
+
+ /*
+ * Attach the dquot(s) to the inodes and modify them incore.
+ * These ids of the inode couldn't have changed since the new
+ * inode has been locked ever since it was created.
+ */
+ xfs_qm_vop_create_dqattach(tp, sc->tempip, udqp, gdqp, pdqp);
+
+ /*
+ * Put our temp file on the unlinked list so it's purged automatically.
+ * All file-based metadata being reconstructed using this file must be
+ * atomically exchanged with the original file because the contents
+ * here will be purged when the inode is dropped or log recovery cleans
+ * out the unlinked list.
+ */
+ error = xfs_iunlink(tp, sc->tempip);
+ if (error)
+ goto out_trans_cancel;
+
+ error = xfs_trans_commit(tp);
+ if (error)
+ goto out_release_inode;
+
+ trace_xrep_tempfile_create(sc);
+
+ xfs_qm_dqrele(udqp);
+ xfs_qm_dqrele(gdqp);
+ xfs_qm_dqrele(pdqp);
+
+ /* Finish setting up the incore / vfs context. */
+ xfs_iunlock(sc->tempip, XFS_ILOCK_EXCL);
+ xfs_setup_iops(sc->tempip);
+ xfs_finish_inode_setup(sc->tempip);
+
+ sc->temp_ilock_flags = 0;
+ return error;
+
+out_trans_cancel:
+ xfs_trans_cancel(tp);
+out_release_inode:
+ /*
+ * Wait until after the current transaction is aborted to finish the
+ * setup of the inode and release the inode. This prevents recursive
+ * transactions and deadlocks from xfs_inactive.
+ */
+ if (sc->tempip) {
+ xfs_iunlock(sc->tempip, XFS_ILOCK_EXCL);
+ xfs_finish_inode_setup(sc->tempip);
+ xchk_irele(sc, sc->tempip);
+ }
+out_release_dquots:
+ xfs_qm_dqrele(udqp);
+ xfs_qm_dqrele(gdqp);
+ xfs_qm_dqrele(pdqp);
+
+ return error;
+}
+
+/* Take IOLOCK_EXCL on the temporary file, maybe. */
+bool
+xrep_tempfile_iolock_nowait(
+ struct xfs_scrub *sc)
+{
+ if (xfs_ilock_nowait(sc->tempip, XFS_IOLOCK_EXCL)) {
+ sc->temp_ilock_flags |= XFS_IOLOCK_EXCL;
+ return true;
+ }
+
+ return false;
+}
+
+/*
+ * Take the temporary file's IOLOCK while holding a different inode's IOLOCK.
+ * In theory nobody else should hold the tempfile's IOLOCK, but we use trylock
+ * to avoid deadlocks and lockdep complaints.
+ */
+int
+xrep_tempfile_iolock_polled(
+ struct xfs_scrub *sc)
+{
+ int error = 0;
+
+ while (!xrep_tempfile_iolock_nowait(sc)) {
+ if (xchk_should_terminate(sc, &error))
+ return error;
+ delay(1);
+ }
+
+ return 0;
+}
+
+/* Release IOLOCK_EXCL on the temporary file. */
+void
+xrep_tempfile_iounlock(
+ struct xfs_scrub *sc)
+{
+ xfs_iunlock(sc->tempip, XFS_IOLOCK_EXCL);
+ sc->temp_ilock_flags &= ~XFS_IOLOCK_EXCL;
+}
+
+/* Prepare the temporary file for metadata updates by grabbing ILOCK_EXCL. */
+void
+xrep_tempfile_ilock(
+ struct xfs_scrub *sc)
+{
+ sc->temp_ilock_flags |= XFS_ILOCK_EXCL;
+ xfs_ilock(sc->tempip, XFS_ILOCK_EXCL);
+}
+
+/* Try to grab ILOCK_EXCL on the temporary file. */
+bool
+xrep_tempfile_ilock_nowait(
+ struct xfs_scrub *sc)
+{
+ if (xfs_ilock_nowait(sc->tempip, XFS_ILOCK_EXCL)) {
+ sc->temp_ilock_flags |= XFS_ILOCK_EXCL;
+ return true;
+ }
+
+ return false;
+}
+
+/* Unlock ILOCK_EXCL on the temporary file after an update. */
+void
+xrep_tempfile_iunlock(
+ struct xfs_scrub *sc)
+{
+ xfs_iunlock(sc->tempip, XFS_ILOCK_EXCL);
+ sc->temp_ilock_flags &= ~XFS_ILOCK_EXCL;
+}
+
+/*
+ * Begin the process of making changes to both the file being scrubbed and
+ * the temporary file by taking ILOCK_EXCL on both.
+ */
+void
+xrep_tempfile_ilock_both(
+ struct xfs_scrub *sc)
+{
+ xfs_lock_two_inodes(sc->ip, XFS_ILOCK_EXCL, sc->tempip, XFS_ILOCK_EXCL);
+ sc->ilock_flags |= XFS_ILOCK_EXCL;
+ sc->temp_ilock_flags |= XFS_ILOCK_EXCL;
+}
+
+/* Unlock ILOCK_EXCL on both files. */
+void
+xrep_tempfile_iunlock_both(
+ struct xfs_scrub *sc)
+{
+ xrep_tempfile_iunlock(sc);
+ xchk_iunlock(sc, XFS_ILOCK_EXCL);
+}
+
+/* Release the temporary file. */
+void
+xrep_tempfile_rele(
+ struct xfs_scrub *sc)
+{
+ if (!sc->tempip)
+ return;
+
+ if (sc->temp_ilock_flags) {
+ xfs_iunlock(sc->tempip, sc->temp_ilock_flags);
+ sc->temp_ilock_flags = 0;
+ }
+
+ xchk_irele(sc, sc->tempip);
+ sc->tempip = NULL;
+}
+
+/*
+ * Make sure that the given range of the data fork of the temporary file is
+ * mapped to written blocks. The caller must ensure that both inodes are
+ * joined to the transaction.
+ */
+int
+xrep_tempfile_prealloc(
+ struct xfs_scrub *sc,
+ xfs_fileoff_t off,
+ xfs_filblks_t len)
+{
+ struct xfs_bmbt_irec map;
+ xfs_fileoff_t end = off + len;
+ int error;
+
+ ASSERT(sc->tempip != NULL);
+ ASSERT(!XFS_NOT_DQATTACHED(sc->mp, sc->tempip));
+
+ for (; off < end; off = map.br_startoff + map.br_blockcount) {
+ int nmaps = 1;
+
+ /*
+ * If we have a real extent mapping this block then we're
+ * in ok shape.
+ */
+ error = xfs_bmapi_read(sc->tempip, off, end - off, &map, &nmaps,
+ XFS_DATA_FORK);
+ if (error)
+ return error;
+ if (nmaps == 0) {
+ ASSERT(nmaps != 0);
+ return -EFSCORRUPTED;
+ }
+
+ if (xfs_bmap_is_written_extent(&map))
+ continue;
+
+ /*
+ * If we find a delalloc reservation then something is very
+ * very wrong. Bail out.
+ */
+ if (map.br_startblock == DELAYSTARTBLOCK)
+ return -EFSCORRUPTED;
+
+ /*
+ * Make sure this block has a real zeroed extent allocated to
+ * it.
+ */
+ nmaps = 1;
+ error = xfs_bmapi_write(sc->tp, sc->tempip, off, end - off,
+ XFS_BMAPI_CONVERT | XFS_BMAPI_ZERO, 0, &map,
+ &nmaps);
+ if (error)
+ return error;
+ if (nmaps != 1)
+ return -EFSCORRUPTED;
+
+ trace_xrep_tempfile_prealloc(sc, XFS_DATA_FORK, &map);
+
+ /* Commit new extent and all deferred work. */
+ error = xfs_defer_finish(&sc->tp);
+ if (error)
+ return error;
+ }
+
+ return 0;
+}
+
+/*
+ * Write data to each block of a file. The given range of the tempfile's data
+ * fork must already be populated with written extents.
+ */
+int
+xrep_tempfile_copyin(
+ struct xfs_scrub *sc,
+ xfs_fileoff_t off,
+ xfs_filblks_t len,
+ xrep_tempfile_copyin_fn prep_fn,
+ void *data)
+{
+ LIST_HEAD(buffers_list);
+ struct xfs_mount *mp = sc->mp;
+ struct xfs_buf *bp;
+ xfs_fileoff_t flush_mask;
+ xfs_fileoff_t end = off + len;
+ loff_t pos = XFS_FSB_TO_B(mp, off);
+ int error = 0;
+
+ ASSERT(S_ISREG(VFS_I(sc->tempip)->i_mode));
+
+ /* Flush buffers to disk every 512K */
+ flush_mask = XFS_B_TO_FSBT(mp, (1U << 19)) - 1;
+
+ for (; off < end; off++, pos += mp->m_sb.sb_blocksize) {
+ struct xfs_bmbt_irec map;
+ int nmaps = 1;
+
+ /* Read block mapping for this file block. */
+ error = xfs_bmapi_read(sc->tempip, off, 1, &map, &nmaps, 0);
+ if (error)
+ goto out_err;
+ if (nmaps == 0 || !xfs_bmap_is_written_extent(&map)) {
+ error = -EFSCORRUPTED;
+ goto out_err;
+ }
+
+ /* Get the metadata buffer for this offset in the file. */
+ error = xfs_trans_get_buf(sc->tp, mp->m_ddev_targp,
+ XFS_FSB_TO_DADDR(mp, map.br_startblock),
+ mp->m_bsize, 0, &bp);
+ if (error)
+ goto out_err;
+
+ trace_xrep_tempfile_copyin(sc, XFS_DATA_FORK, &map);
+
+ /* Read in a block's worth of data from the xfile. */
+ error = prep_fn(sc, bp, data);
+ if (error) {
+ xfs_trans_brelse(sc->tp, bp);
+ goto out_err;
+ }
+
+ /* Queue buffer, and flush if we have too much dirty data. */
+ xfs_buf_delwri_queue_here(bp, &buffers_list);
+ xfs_trans_brelse(sc->tp, bp);
+
+ if (!(off & flush_mask)) {
+ error = xfs_buf_delwri_submit(&buffers_list);
+ if (error)
+ goto out_err;
+ }
+ }
+
+ /*
+ * Write the new blocks to disk. If the ordered list isn't empty after
+ * that, then something went wrong and we have to fail. This should
+ * never happen, but we'll check anyway.
+ */
+ error = xfs_buf_delwri_submit(&buffers_list);
+ if (error)
+ goto out_err;
+
+ if (!list_empty(&buffers_list)) {
+ ASSERT(list_empty(&buffers_list));
+ error = -EIO;
+ goto out_err;
+ }
+
+ return 0;
+
+out_err:
+ xfs_buf_delwri_cancel(&buffers_list);
+ return error;
+}
+
+/*
+ * Set the temporary file's size. Caller must join the tempfile to the scrub
+ * transaction and is responsible for adjusting block mappings as needed.
+ */
+int
+xrep_tempfile_set_isize(
+ struct xfs_scrub *sc,
+ unsigned long long isize)
+{
+ if (sc->tempip->i_disk_size == isize)
+ return 0;
+
+ sc->tempip->i_disk_size = isize;
+ i_size_write(VFS_I(sc->tempip), isize);
+ return xrep_tempfile_roll_trans(sc);
+}
+
+/*
+ * Roll a repair transaction involving the temporary file. Caller must join
+ * both the temporary file and the file being scrubbed to the transaction.
+ * This function return with both inodes joined to a new scrub transaction,
+ * or the usual negative errno.
+ */
+int
+xrep_tempfile_roll_trans(
+ struct xfs_scrub *sc)
+{
+ int error;
+
+ xfs_trans_log_inode(sc->tp, sc->tempip, XFS_ILOG_CORE);
+ error = xrep_roll_trans(sc);
+ if (error)
+ return error;
+
+ xfs_trans_ijoin(sc->tp, sc->tempip, 0);
+ return 0;
+}
+
+/*
+ * Fill out the mapping exchange request in preparation for atomically
+ * committing the contents of a metadata file that we've rebuilt in the temp
+ * file.
+ */
+STATIC int
+xrep_tempexch_prep_request(
+ struct xfs_scrub *sc,
+ int whichfork,
+ struct xrep_tempexch *tx)
+{
+ struct xfs_exchmaps_req *req = &tx->req;
+
+ memset(tx, 0, sizeof(struct xrep_tempexch));
+
+ /* COW forks don't exist on disk. */
+ if (whichfork == XFS_COW_FORK) {
+ ASSERT(0);
+ return -EINVAL;
+ }
+
+ /* Both files should have the relevant forks. */
+ if (!xfs_ifork_ptr(sc->ip, whichfork) ||
+ !xfs_ifork_ptr(sc->tempip, whichfork)) {
+ ASSERT(xfs_ifork_ptr(sc->ip, whichfork) != NULL);
+ ASSERT(xfs_ifork_ptr(sc->tempip, whichfork) != NULL);
+ return -EINVAL;
+ }
+
+ /* Exchange all mappings in both forks. */
+ req->ip1 = sc->tempip;
+ req->ip2 = sc->ip;
+ req->startoff1 = 0;
+ req->startoff2 = 0;
+ switch (whichfork) {
+ case XFS_ATTR_FORK:
+ req->flags |= XFS_EXCHMAPS_ATTR_FORK;
+ break;
+ case XFS_DATA_FORK:
+ /* Always exchange sizes when exchanging data fork mappings. */
+ req->flags |= XFS_EXCHMAPS_SET_SIZES;
+ break;
+ }
+ req->blockcount = XFS_MAX_FILEOFF;
+
+ return 0;
+}
+
+/*
+ * Fill out the mapping exchange resource estimation structures in preparation
+ * for exchanging the contents of a metadata file that we've rebuilt in the
+ * temp file. Caller must hold IOLOCK_EXCL but not ILOCK_EXCL on both files.
+ */
+STATIC int
+xrep_tempexch_estimate(
+ struct xfs_scrub *sc,
+ struct xrep_tempexch *tx)
+{
+ struct xfs_exchmaps_req *req = &tx->req;
+ struct xfs_ifork *ifp;
+ struct xfs_ifork *tifp;
+ int whichfork = xfs_exchmaps_reqfork(req);
+ int state = 0;
+
+ /*
+ * The exchmaps code only knows how to exchange file fork space
+ * mappings. Any fork data in local format must be promoted to a
+ * single block before the exchange can take place.
+ */
+ ifp = xfs_ifork_ptr(sc->ip, whichfork);
+ if (ifp->if_format == XFS_DINODE_FMT_LOCAL)
+ state |= 1;
+
+ tifp = xfs_ifork_ptr(sc->tempip, whichfork);
+ if (tifp->if_format == XFS_DINODE_FMT_LOCAL)
+ state |= 2;
+
+ switch (state) {
+ case 0:
+ /* Both files have mapped extents; use the regular estimate. */
+ return xfs_exchrange_estimate(req);
+ case 1:
+ /*
+ * The file being repaired is in local format, but the temp
+ * file has mapped extents. To perform the exchange, the file
+ * being repaired must have its shorform data converted to an
+ * ondisk block so that the forks will be in extents format.
+ * We need one resblk for the conversion; the number of
+ * exchanges is (worst case) the temporary file's extent count
+ * plus the block we converted.
+ */
+ req->ip1_bcount = sc->tempip->i_nblocks;
+ req->ip2_bcount = 1;
+ req->nr_exchanges = 1 + tifp->if_nextents;
+ req->resblks = 1;
+ break;
+ case 2:
+ /*
+ * The temporary file is in local format, but the file being
+ * repaired has mapped extents. To perform the exchange, the
+ * temp file must have its shortform data converted to an
+ * ondisk block, and the fork changed to extents format. We
+ * need one resblk for the conversion; the number of exchanges
+ * is (worst case) the extent count of the file being repaired
+ * plus the block we converted.
+ */
+ req->ip1_bcount = 1;
+ req->ip2_bcount = sc->ip->i_nblocks;
+ req->nr_exchanges = 1 + ifp->if_nextents;
+ req->resblks = 1;
+ break;
+ case 3:
+ /*
+ * Both forks are in local format. To perform the exchange,
+ * both files must have their shortform data converted to
+ * fsblocks, and both forks must be converted to extents
+ * format. We need two resblks for the two conversions, and
+ * the number of exchanges is 1 since there's only one block at
+ * fileoff 0. Presumably, the caller could not exchange the
+ * two inode fork areas directly.
+ */
+ req->ip1_bcount = 1;
+ req->ip2_bcount = 1;
+ req->nr_exchanges = 1;
+ req->resblks = 2;
+ break;
+ }
+
+ return xfs_exchmaps_estimate_overhead(req);
+}
+
+/*
+ * Obtain a quota reservation to make sure we don't hit EDQUOT. We can skip
+ * this if quota enforcement is disabled or if both inodes' dquots are the
+ * same. The qretry structure must be initialized to zeroes before the first
+ * call to this function.
+ */
+STATIC int
+xrep_tempexch_reserve_quota(
+ struct xfs_scrub *sc,
+ const struct xrep_tempexch *tx)
+{
+ struct xfs_trans *tp = sc->tp;
+ const struct xfs_exchmaps_req *req = &tx->req;
+ int64_t ddelta, rdelta;
+ int error;
+
+ /*
+ * Don't bother with a quota reservation if we're not enforcing them
+ * or the two inodes have the same dquots.
+ */
+ if (!XFS_IS_QUOTA_ON(tp->t_mountp) || req->ip1 == req->ip2 ||
+ (req->ip1->i_udquot == req->ip2->i_udquot &&
+ req->ip1->i_gdquot == req->ip2->i_gdquot &&
+ req->ip1->i_pdquot == req->ip2->i_pdquot))
+ return 0;
+
+ /*
+ * Quota reservation for each file comes from two sources. First, we
+ * need to account for any net gain in mapped blocks during the
+ * exchange. Second, we need reservation for the gross gain in mapped
+ * blocks so that we don't trip over any quota block reservation
+ * assertions. We must reserve the gross gain because the quota code
+ * subtracts from bcount the number of blocks that we unmap; it does
+ * not add that quantity back to the quota block reservation.
+ */
+ ddelta = max_t(int64_t, 0, req->ip2_bcount - req->ip1_bcount);
+ rdelta = max_t(int64_t, 0, req->ip2_rtbcount - req->ip1_rtbcount);
+ error = xfs_trans_reserve_quota_nblks(tp, req->ip1,
+ ddelta + req->ip1_bcount, rdelta + req->ip1_rtbcount,
+ true);
+ if (error)
+ return error;
+
+ ddelta = max_t(int64_t, 0, req->ip1_bcount - req->ip2_bcount);
+ rdelta = max_t(int64_t, 0, req->ip1_rtbcount - req->ip2_rtbcount);
+ return xfs_trans_reserve_quota_nblks(tp, req->ip2,
+ ddelta + req->ip2_bcount, rdelta + req->ip2_rtbcount,
+ true);
+}
+
+/*
+ * Prepare an existing transaction for an atomic file contents exchange.
+ *
+ * This function fills out the mapping exchange request and resource estimation
+ * structures in preparation for exchanging the contents of a metadata file
+ * that has been rebuilt in the temp file. Next, it reserves space and quota
+ * for the transaction.
+ *
+ * The caller must hold ILOCK_EXCL of the scrub target file and the temporary
+ * file. The caller must join both inodes to the transaction with no unlock
+ * flags, and is responsible for dropping both ILOCKs when appropriate. Only
+ * use this when those ILOCKs cannot be dropped.
+ */
+int
+xrep_tempexch_trans_reserve(
+ struct xfs_scrub *sc,
+ int whichfork,
+ struct xrep_tempexch *tx)
+{
+ int error;
+
+ ASSERT(sc->tp != NULL);
+ xfs_assert_ilocked(sc->ip, XFS_ILOCK_EXCL);
+ xfs_assert_ilocked(sc->tempip, XFS_ILOCK_EXCL);
+
+ error = xrep_tempexch_prep_request(sc, whichfork, tx);
+ if (error)
+ return error;
+
+ error = xfs_exchmaps_estimate(&tx->req);
+ if (error)
+ return error;
+
+ error = xfs_trans_reserve_more(sc->tp, tx->req.resblks, 0);
+ if (error)
+ return error;
+
+ return xrep_tempexch_reserve_quota(sc, tx);
+}
+
+/*
+ * Create a new transaction for a file contents exchange.
+ *
+ * This function fills out the mapping excahange request and resource
+ * estimation structures in preparation for exchanging the contents of a
+ * metadata file that has been rebuilt in the temp file. Next, it reserves
+ * space, takes ILOCK_EXCL of both inodes, joins them to the transaction and
+ * reserves quota for the transaction.
+ *
+ * The caller is responsible for dropping both ILOCKs when appropriate.
+ */
+int
+xrep_tempexch_trans_alloc(
+ struct xfs_scrub *sc,
+ int whichfork,
+ struct xrep_tempexch *tx)
+{
+ unsigned int flags = 0;
+ int error;
+
+ ASSERT(sc->tp == NULL);
+ ASSERT(xfs_has_exchange_range(sc->mp));
+
+ error = xrep_tempexch_prep_request(sc, whichfork, tx);
+ if (error)
+ return error;
+
+ error = xrep_tempexch_estimate(sc, tx);
+ if (error)
+ return error;
+
+ if (xfs_has_lazysbcount(sc->mp))
+ flags |= XFS_TRANS_RES_FDBLKS;
+
+ error = xfs_trans_alloc(sc->mp, &M_RES(sc->mp)->tr_itruncate,
+ tx->req.resblks, 0, flags, &sc->tp);
+ if (error)
+ return error;
+
+ sc->temp_ilock_flags |= XFS_ILOCK_EXCL;
+ sc->ilock_flags |= XFS_ILOCK_EXCL;
+ xfs_exchrange_ilock(sc->tp, sc->ip, sc->tempip);
+
+ return xrep_tempexch_reserve_quota(sc, tx);
+}
+
+/*
+ * Exchange file mappings (and hence file contents) between the file being
+ * repaired and the temporary file. Returns with both inodes locked and joined
+ * to a clean scrub transaction.
+ */
+int
+xrep_tempexch_contents(
+ struct xfs_scrub *sc,
+ struct xrep_tempexch *tx)
+{
+ int error;
+
+ ASSERT(xfs_has_exchange_range(sc->mp));
+
+ xfs_exchange_mappings(sc->tp, &tx->req);
+ error = xfs_defer_finish(&sc->tp);
+ if (error)
+ return error;
+
+ /*
+ * If we exchanged the ondisk sizes of two metadata files, we must
+ * exchanged the incore sizes as well.
+ */
+ if (tx->req.flags & XFS_EXCHMAPS_SET_SIZES) {
+ loff_t temp;
+
+ temp = i_size_read(VFS_I(sc->ip));
+ i_size_write(VFS_I(sc->ip), i_size_read(VFS_I(sc->tempip)));
+ i_size_write(VFS_I(sc->tempip), temp);
+ }
+
+ return 0;
+}
+
+/*
+ * Write local format data from one of the temporary file's forks into the same
+ * fork of file being repaired, and exchange the file sizes, if appropriate.
+ * Caller must ensure that the file being repaired has enough fork space to
+ * hold all the bytes.
+ */
+void
+xrep_tempfile_copyout_local(
+ struct xfs_scrub *sc,
+ int whichfork)
+{
+ struct xfs_ifork *temp_ifp;
+ struct xfs_ifork *ifp;
+ unsigned int ilog_flags = XFS_ILOG_CORE;
+
+ temp_ifp = xfs_ifork_ptr(sc->tempip, whichfork);
+ ifp = xfs_ifork_ptr(sc->ip, whichfork);
+
+ ASSERT(temp_ifp != NULL);
+ ASSERT(ifp != NULL);
+ ASSERT(temp_ifp->if_format == XFS_DINODE_FMT_LOCAL);
+ ASSERT(ifp->if_format == XFS_DINODE_FMT_LOCAL);
+
+ switch (whichfork) {
+ case XFS_DATA_FORK:
+ ASSERT(sc->tempip->i_disk_size <=
+ xfs_inode_data_fork_size(sc->ip));
+ break;
+ case XFS_ATTR_FORK:
+ ASSERT(sc->tempip->i_forkoff >= sc->ip->i_forkoff);
+ break;
+ default:
+ ASSERT(0);
+ return;
+ }
+
+ /* Recreate @sc->ip's incore fork (ifp) with data from temp_ifp. */
+ xfs_idestroy_fork(ifp);
+ xfs_init_local_fork(sc->ip, whichfork, temp_ifp->if_data,
+ temp_ifp->if_bytes);
+
+ if (whichfork == XFS_DATA_FORK) {
+ i_size_write(VFS_I(sc->ip), i_size_read(VFS_I(sc->tempip)));
+ sc->ip->i_disk_size = sc->tempip->i_disk_size;
+ }
+
+ ilog_flags |= xfs_ilog_fdata(whichfork);
+ xfs_trans_log_inode(sc->tp, sc->ip, ilog_flags);
+}
+
+/* Decide if a given XFS inode is a temporary file for a repair. */
+bool
+xrep_is_tempfile(
+ const struct xfs_inode *ip)
+{
+ const struct inode *inode = &ip->i_vnode;
+
+ if (IS_PRIVATE(inode) && !(inode->i_opflags & IOP_XATTR))
+ return true;
+
+ return false;
+}
diff --git a/fs/xfs/scrub/tempfile.h b/fs/xfs/scrub/tempfile.h
new file mode 100644
index 0000000000..e51399f595
--- /dev/null
+++ b/fs/xfs/scrub/tempfile.h
@@ -0,0 +1,48 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Copyright (c) 2021-2024 Oracle. All Rights Reserved.
+ * Author: Darrick J. Wong <djwong@kernel.org>
+ */
+#ifndef __XFS_SCRUB_TEMPFILE_H__
+#define __XFS_SCRUB_TEMPFILE_H__
+
+#ifdef CONFIG_XFS_ONLINE_REPAIR
+int xrep_tempfile_create(struct xfs_scrub *sc, uint16_t mode);
+void xrep_tempfile_rele(struct xfs_scrub *sc);
+
+bool xrep_tempfile_iolock_nowait(struct xfs_scrub *sc);
+int xrep_tempfile_iolock_polled(struct xfs_scrub *sc);
+void xrep_tempfile_iounlock(struct xfs_scrub *sc);
+
+void xrep_tempfile_ilock(struct xfs_scrub *sc);
+bool xrep_tempfile_ilock_nowait(struct xfs_scrub *sc);
+void xrep_tempfile_iunlock(struct xfs_scrub *sc);
+void xrep_tempfile_iunlock_both(struct xfs_scrub *sc);
+void xrep_tempfile_ilock_both(struct xfs_scrub *sc);
+
+int xrep_tempfile_prealloc(struct xfs_scrub *sc, xfs_fileoff_t off,
+ xfs_filblks_t len);
+
+enum xfs_blft;
+
+typedef int (*xrep_tempfile_copyin_fn)(struct xfs_scrub *sc,
+ struct xfs_buf *bp, void *data);
+
+int xrep_tempfile_copyin(struct xfs_scrub *sc, xfs_fileoff_t off,
+ xfs_filblks_t len, xrep_tempfile_copyin_fn fn, void *data);
+
+int xrep_tempfile_set_isize(struct xfs_scrub *sc, unsigned long long isize);
+
+int xrep_tempfile_roll_trans(struct xfs_scrub *sc);
+void xrep_tempfile_copyout_local(struct xfs_scrub *sc, int whichfork);
+bool xrep_is_tempfile(const struct xfs_inode *ip);
+#else
+static inline void xrep_tempfile_iolock_both(struct xfs_scrub *sc)
+{
+ xchk_ilock(sc, XFS_IOLOCK_EXCL);
+}
+# define xrep_is_tempfile(ip) (false)
+# define xrep_tempfile_rele(sc)
+#endif /* CONFIG_XFS_ONLINE_REPAIR */
+
+#endif /* __XFS_SCRUB_TEMPFILE_H__ */
diff --git a/fs/xfs/scrub/trace.c b/fs/xfs/scrub/trace.c
index 3dd281d6d1..4470ad0533 100644
--- a/fs/xfs/scrub/trace.c
+++ b/fs/xfs/scrub/trace.c
@@ -19,13 +19,19 @@
#include "xfs_da_format.h"
#include "xfs_dir2.h"
#include "xfs_rmap.h"
+#include "xfs_parent.h"
#include "scrub/scrub.h"
#include "scrub/xfile.h"
#include "scrub/xfarray.h"
#include "scrub/quota.h"
#include "scrub/iscan.h"
+#include "scrub/orphanage.h"
#include "scrub/nlinks.h"
#include "scrub/fscounters.h"
+#include "scrub/bitmap.h"
+#include "scrub/ino_bitmap.h"
+#include "scrub/xfblob.h"
+#include "scrub/dirtree.h"
/* Figure out which block the btree cursor was pointing to. */
static inline xfs_fsblock_t
diff --git a/fs/xfs/scrub/trace.h b/fs/xfs/scrub/trace.h
index 5b294be52c..92ef4cdc48 100644
--- a/fs/xfs/scrub/trace.h
+++ b/fs/xfs/scrub/trace.h
@@ -26,6 +26,10 @@ struct xchk_iscan;
struct xchk_nlink;
struct xchk_fscounters;
struct xfs_rmap_update_params;
+struct xfs_parent_rec;
+enum xchk_dirpath_outcome;
+struct xchk_dirtree;
+struct xchk_dirtree_outcomes;
/*
* ftrace's __print_symbolic requires that all enum values be wrapped in the
@@ -64,6 +68,8 @@ TRACE_DEFINE_ENUM(XFS_SCRUB_TYPE_FSCOUNTERS);
TRACE_DEFINE_ENUM(XFS_SCRUB_TYPE_QUOTACHECK);
TRACE_DEFINE_ENUM(XFS_SCRUB_TYPE_NLINKS);
TRACE_DEFINE_ENUM(XFS_SCRUB_TYPE_HEALTHY);
+TRACE_DEFINE_ENUM(XFS_SCRUB_TYPE_DIRTREE);
+TRACE_DEFINE_ENUM(XFS_SCRUB_TYPE_BARRIER);
#define XFS_SCRUB_TYPE_STRINGS \
{ XFS_SCRUB_TYPE_PROBE, "probe" }, \
@@ -93,7 +99,9 @@ TRACE_DEFINE_ENUM(XFS_SCRUB_TYPE_HEALTHY);
{ XFS_SCRUB_TYPE_FSCOUNTERS, "fscounters" }, \
{ XFS_SCRUB_TYPE_QUOTACHECK, "quotacheck" }, \
{ XFS_SCRUB_TYPE_NLINKS, "nlinks" }, \
- { XFS_SCRUB_TYPE_HEALTHY, "healthy" }
+ { XFS_SCRUB_TYPE_HEALTHY, "healthy" }, \
+ { XFS_SCRUB_TYPE_DIRTREE, "dirtree" }, \
+ { XFS_SCRUB_TYPE_BARRIER, "barrier" }
#define XFS_SCRUB_FLAG_STRINGS \
{ XFS_SCRUB_IFLAG_REPAIR, "repair" }, \
@@ -169,6 +177,8 @@ DEFINE_EVENT(xchk_class, name, \
DEFINE_SCRUB_EVENT(xchk_start);
DEFINE_SCRUB_EVENT(xchk_done);
DEFINE_SCRUB_EVENT(xchk_deadlock_retry);
+DEFINE_SCRUB_EVENT(xchk_dirtree_start);
+DEFINE_SCRUB_EVENT(xchk_dirtree_done);
DEFINE_SCRUB_EVENT(xrep_attempt);
DEFINE_SCRUB_EVENT(xrep_done);
@@ -199,6 +209,81 @@ DEFINE_EVENT(xchk_fsgate_class, name, \
DEFINE_SCRUB_FSHOOK_EVENT(xchk_fsgates_enable);
DEFINE_SCRUB_FSHOOK_EVENT(xchk_fsgates_disable);
+DECLARE_EVENT_CLASS(xchk_vector_head_class,
+ TP_PROTO(struct xfs_inode *ip, struct xfs_scrub_vec_head *vhead),
+ TP_ARGS(ip, vhead),
+ TP_STRUCT__entry(
+ __field(dev_t, dev)
+ __field(xfs_ino_t, ino)
+ __field(xfs_agnumber_t, agno)
+ __field(xfs_ino_t, inum)
+ __field(unsigned int, gen)
+ __field(unsigned int, flags)
+ __field(unsigned short, rest_us)
+ __field(unsigned short, nr_vecs)
+ ),
+ TP_fast_assign(
+ __entry->dev = ip->i_mount->m_super->s_dev;
+ __entry->ino = ip->i_ino;
+ __entry->agno = vhead->svh_agno;
+ __entry->inum = vhead->svh_ino;
+ __entry->gen = vhead->svh_gen;
+ __entry->flags = vhead->svh_flags;
+ __entry->rest_us = vhead->svh_rest_us;
+ __entry->nr_vecs = vhead->svh_nr;
+ ),
+ TP_printk("dev %d:%d ino 0x%llx agno 0x%x inum 0x%llx gen 0x%x flags 0x%x rest_us %u nr_vecs %u",
+ MAJOR(__entry->dev), MINOR(__entry->dev),
+ __entry->ino,
+ __entry->agno,
+ __entry->inum,
+ __entry->gen,
+ __entry->flags,
+ __entry->rest_us,
+ __entry->nr_vecs)
+)
+#define DEFINE_SCRUBV_HEAD_EVENT(name) \
+DEFINE_EVENT(xchk_vector_head_class, name, \
+ TP_PROTO(struct xfs_inode *ip, struct xfs_scrub_vec_head *vhead), \
+ TP_ARGS(ip, vhead))
+
+DEFINE_SCRUBV_HEAD_EVENT(xchk_scrubv_start);
+
+DECLARE_EVENT_CLASS(xchk_vector_class,
+ TP_PROTO(struct xfs_mount *mp, struct xfs_scrub_vec_head *vhead,
+ unsigned int vec_nr, struct xfs_scrub_vec *v),
+ TP_ARGS(mp, vhead, vec_nr, v),
+ TP_STRUCT__entry(
+ __field(dev_t, dev)
+ __field(unsigned int, vec_nr)
+ __field(unsigned int, vec_type)
+ __field(unsigned int, vec_flags)
+ __field(int, vec_ret)
+ ),
+ TP_fast_assign(
+ __entry->dev = mp->m_super->s_dev;
+ __entry->vec_nr = vec_nr;
+ __entry->vec_type = v->sv_type;
+ __entry->vec_flags = v->sv_flags;
+ __entry->vec_ret = v->sv_ret;
+ ),
+ TP_printk("dev %d:%d vec[%u] type %s flags %s ret %d",
+ MAJOR(__entry->dev), MINOR(__entry->dev),
+ __entry->vec_nr,
+ __print_symbolic(__entry->vec_type, XFS_SCRUB_TYPE_STRINGS),
+ __print_flags(__entry->vec_flags, "|", XFS_SCRUB_FLAG_STRINGS),
+ __entry->vec_ret)
+)
+#define DEFINE_SCRUBV_EVENT(name) \
+DEFINE_EVENT(xchk_vector_class, name, \
+ TP_PROTO(struct xfs_mount *mp, struct xfs_scrub_vec_head *vhead, \
+ unsigned int vec_nr, struct xfs_scrub_vec *v), \
+ TP_ARGS(mp, vhead, vec_nr, v))
+
+DEFINE_SCRUBV_EVENT(xchk_scrubv_barrier_fail);
+DEFINE_SCRUBV_EVENT(xchk_scrubv_item);
+DEFINE_SCRUBV_EVENT(xchk_scrubv_outcome);
+
TRACE_EVENT(xchk_op_error,
TP_PROTO(struct xfs_scrub *sc, xfs_agnumber_t agno,
xfs_agblock_t bno, int error, void *ret_ip),
@@ -364,6 +449,7 @@ DEFINE_EVENT(xchk_fblock_error_class, name, \
DEFINE_SCRUB_FBLOCK_ERROR_EVENT(xchk_fblock_error);
DEFINE_SCRUB_FBLOCK_ERROR_EVENT(xchk_fblock_warning);
+DEFINE_SCRUB_FBLOCK_ERROR_EVENT(xchk_fblock_preen);
#ifdef CONFIG_XFS_QUOTA
DECLARE_EVENT_CLASS(xchk_dqiter_class,
@@ -475,7 +561,7 @@ TRACE_EVENT(xchk_btree_op_error,
__entry->dev = sc->mp->m_super->s_dev;
__entry->type = sc->sm->sm_type;
- __assign_str(name, cur->bc_ops->name);
+ __assign_str(name);
__entry->level = level;
__entry->agno = XFS_FSB_TO_AGNO(cur->bc_mp, fsbno);
__entry->bno = XFS_FSB_TO_AGBNO(cur->bc_mp, fsbno);
@@ -518,7 +604,7 @@ TRACE_EVENT(xchk_ifork_btree_op_error,
__entry->ino = sc->ip->i_ino;
__entry->whichfork = cur->bc_ino.whichfork;
__entry->type = sc->sm->sm_type;
- __assign_str(name, cur->bc_ops->name);
+ __assign_str(name);
__entry->level = level;
__entry->ptr = cur->bc_levels[level].ptr;
__entry->agno = XFS_FSB_TO_AGNO(cur->bc_mp, fsbno);
@@ -558,7 +644,7 @@ TRACE_EVENT(xchk_btree_error,
xfs_fsblock_t fsbno = xchk_btree_cur_fsbno(cur, level);
__entry->dev = sc->mp->m_super->s_dev;
__entry->type = sc->sm->sm_type;
- __assign_str(name, cur->bc_ops->name);
+ __assign_str(name);
__entry->level = level;
__entry->agno = XFS_FSB_TO_AGNO(cur->bc_mp, fsbno);
__entry->bno = XFS_FSB_TO_AGBNO(cur->bc_mp, fsbno);
@@ -598,7 +684,7 @@ TRACE_EVENT(xchk_ifork_btree_error,
__entry->ino = sc->ip->i_ino;
__entry->whichfork = cur->bc_ino.whichfork;
__entry->type = sc->sm->sm_type;
- __assign_str(name, cur->bc_ops->name);
+ __assign_str(name);
__entry->level = level;
__entry->agno = XFS_FSB_TO_AGNO(cur->bc_mp, fsbno);
__entry->bno = XFS_FSB_TO_AGBNO(cur->bc_mp, fsbno);
@@ -637,7 +723,7 @@ DECLARE_EVENT_CLASS(xchk_sbtree_class,
__entry->dev = sc->mp->m_super->s_dev;
__entry->type = sc->sm->sm_type;
- __assign_str(name, cur->bc_ops->name);
+ __assign_str(name);
__entry->agno = XFS_FSB_TO_AGNO(cur->bc_mp, fsbno);
__entry->bno = XFS_FSB_TO_AGBNO(cur->bc_mp, fsbno);
__entry->level = level;
@@ -947,6 +1033,7 @@ DEFINE_XFILE_EVENT(xfile_store);
DEFINE_XFILE_EVENT(xfile_seek_data);
DEFINE_XFILE_EVENT(xfile_get_folio);
DEFINE_XFILE_EVENT(xfile_put_folio);
+DEFINE_XFILE_EVENT(xfile_discard);
TRACE_EVENT(xfarray_create,
TP_PROTO(struct xfarray *xfa, unsigned long long required_capacity),
@@ -1300,7 +1387,7 @@ TRACE_EVENT(xchk_iscan_iget_batch,
__entry->unavail)
);
-TRACE_EVENT(xchk_iscan_iget_retry_wait,
+DECLARE_EVENT_CLASS(xchk_iscan_retry_wait_class,
TP_PROTO(struct xchk_iscan *iscan),
TP_ARGS(iscan),
TP_STRUCT__entry(
@@ -1326,7 +1413,13 @@ TRACE_EVENT(xchk_iscan_iget_retry_wait,
__entry->remaining,
__entry->iget_timeout,
__entry->retry_delay)
-);
+)
+#define DEFINE_ISCAN_RETRY_WAIT_EVENT(name) \
+DEFINE_EVENT(xchk_iscan_retry_wait_class, name, \
+ TP_PROTO(struct xchk_iscan *iscan), \
+ TP_ARGS(iscan))
+DEFINE_ISCAN_RETRY_WAIT_EVENT(xchk_iscan_iget_retry_wait);
+DEFINE_ISCAN_RETRY_WAIT_EVENT(xchk_iscan_agi_retry_wait);
TRACE_EVENT(xchk_nlinks_collect_dirent,
TP_PROTO(struct xfs_mount *mp, struct xfs_inode *dp,
@@ -1354,6 +1447,33 @@ TRACE_EVENT(xchk_nlinks_collect_dirent,
__get_str(name))
);
+TRACE_EVENT(xchk_nlinks_collect_pptr,
+ TP_PROTO(struct xfs_mount *mp, struct xfs_inode *dp,
+ const struct xfs_name *name,
+ const struct xfs_parent_rec *pptr),
+ TP_ARGS(mp, dp, name, pptr),
+ TP_STRUCT__entry(
+ __field(dev_t, dev)
+ __field(xfs_ino_t, dir)
+ __field(xfs_ino_t, ino)
+ __field(unsigned int, namelen)
+ __dynamic_array(char, name, name->len)
+ ),
+ TP_fast_assign(
+ __entry->dev = mp->m_super->s_dev;
+ __entry->dir = dp->i_ino;
+ __entry->ino = be64_to_cpu(pptr->p_ino);
+ __entry->namelen = name->len;
+ memcpy(__get_str(name), name->name, name->len);
+ ),
+ TP_printk("dev %d:%d dir 0x%llx -> ino 0x%llx name '%.*s'",
+ MAJOR(__entry->dev), MINOR(__entry->dev),
+ __entry->dir,
+ __entry->ino,
+ __entry->namelen,
+ __get_str(name))
+);
+
TRACE_EVENT(xchk_nlinks_collect_metafile,
TP_PROTO(struct xfs_mount *mp, xfs_ino_t ino),
TP_ARGS(mp, ino),
@@ -1502,6 +1622,300 @@ DEFINE_EVENT(xchk_nlinks_diff_class, name, \
TP_ARGS(mp, ip, live))
DEFINE_SCRUB_NLINKS_DIFF_EVENT(xchk_nlinks_compare_inode);
+DECLARE_EVENT_CLASS(xchk_pptr_class,
+ TP_PROTO(struct xfs_inode *ip, const struct xfs_name *name,
+ xfs_ino_t far_ino),
+ TP_ARGS(ip, name, far_ino),
+ TP_STRUCT__entry(
+ __field(dev_t, dev)
+ __field(xfs_ino_t, ino)
+ __field(unsigned int, namelen)
+ __dynamic_array(char, name, name->len)
+ __field(xfs_ino_t, far_ino)
+ ),
+ TP_fast_assign(
+ __entry->dev = ip->i_mount->m_super->s_dev;
+ __entry->ino = ip->i_ino;
+ __entry->namelen = name->len;
+ memcpy(__get_str(name), name, name->len);
+ __entry->far_ino = far_ino;
+ ),
+ TP_printk("dev %d:%d ino 0x%llx name '%.*s' far_ino 0x%llx",
+ MAJOR(__entry->dev), MINOR(__entry->dev),
+ __entry->ino,
+ __entry->namelen,
+ __get_str(name),
+ __entry->far_ino)
+)
+#define DEFINE_XCHK_PPTR_EVENT(name) \
+DEFINE_EVENT(xchk_pptr_class, name, \
+ TP_PROTO(struct xfs_inode *ip, const struct xfs_name *name, \
+ xfs_ino_t far_ino), \
+ TP_ARGS(ip, name, far_ino))
+DEFINE_XCHK_PPTR_EVENT(xchk_dir_defer);
+DEFINE_XCHK_PPTR_EVENT(xchk_dir_slowpath);
+DEFINE_XCHK_PPTR_EVENT(xchk_dir_ultraslowpath);
+DEFINE_XCHK_PPTR_EVENT(xchk_parent_defer);
+DEFINE_XCHK_PPTR_EVENT(xchk_parent_slowpath);
+DEFINE_XCHK_PPTR_EVENT(xchk_parent_ultraslowpath);
+
+DECLARE_EVENT_CLASS(xchk_dirtree_class,
+ TP_PROTO(struct xfs_scrub *sc, struct xfs_inode *ip,
+ unsigned int path_nr, const struct xfs_name *name,
+ const struct xfs_parent_rec *pptr),
+ TP_ARGS(sc, ip, path_nr, name, pptr),
+ TP_STRUCT__entry(
+ __field(dev_t, dev)
+ __field(unsigned int, path_nr)
+ __field(xfs_ino_t, child_ino)
+ __field(unsigned int, child_gen)
+ __field(xfs_ino_t, parent_ino)
+ __field(unsigned int, parent_gen)
+ __field(unsigned int, namelen)
+ __dynamic_array(char, name, name->len)
+ ),
+ TP_fast_assign(
+ __entry->dev = sc->mp->m_super->s_dev;
+ __entry->path_nr = path_nr;
+ __entry->child_ino = ip->i_ino;
+ __entry->child_gen = VFS_I(ip)->i_generation;
+ __entry->parent_ino = be64_to_cpu(pptr->p_ino);
+ __entry->parent_gen = be32_to_cpu(pptr->p_gen);
+ __entry->namelen = name->len;
+ memcpy(__get_str(name), name->name, name->len);
+ ),
+ TP_printk("dev %d:%d path %u child_ino 0x%llx child_gen 0x%x parent_ino 0x%llx parent_gen 0x%x name '%.*s'",
+ MAJOR(__entry->dev), MINOR(__entry->dev),
+ __entry->path_nr,
+ __entry->child_ino,
+ __entry->child_gen,
+ __entry->parent_ino,
+ __entry->parent_gen,
+ __entry->namelen,
+ __get_str(name))
+);
+#define DEFINE_XCHK_DIRTREE_EVENT(name) \
+DEFINE_EVENT(xchk_dirtree_class, name, \
+ TP_PROTO(struct xfs_scrub *sc, struct xfs_inode *ip, \
+ unsigned int path_nr, const struct xfs_name *name, \
+ const struct xfs_parent_rec *pptr), \
+ TP_ARGS(sc, ip, path_nr, name, pptr))
+DEFINE_XCHK_DIRTREE_EVENT(xchk_dirtree_create_path);
+DEFINE_XCHK_DIRTREE_EVENT(xchk_dirpath_walk_upwards);
+
+DECLARE_EVENT_CLASS(xchk_dirpath_class,
+ TP_PROTO(struct xfs_scrub *sc, struct xfs_inode *ip,
+ unsigned int path_nr, unsigned int step_nr,
+ const struct xfs_name *name,
+ const struct xfs_parent_rec *pptr),
+ TP_ARGS(sc, ip, path_nr, step_nr, name, pptr),
+ TP_STRUCT__entry(
+ __field(dev_t, dev)
+ __field(unsigned int, path_nr)
+ __field(unsigned int, step_nr)
+ __field(xfs_ino_t, child_ino)
+ __field(unsigned int, child_gen)
+ __field(xfs_ino_t, parent_ino)
+ __field(unsigned int, parent_gen)
+ __field(unsigned int, namelen)
+ __dynamic_array(char, name, name->len)
+ ),
+ TP_fast_assign(
+ __entry->dev = sc->mp->m_super->s_dev;
+ __entry->path_nr = path_nr;
+ __entry->step_nr = step_nr;
+ __entry->child_ino = ip->i_ino;
+ __entry->child_gen = VFS_I(ip)->i_generation;
+ __entry->parent_ino = be64_to_cpu(pptr->p_ino);
+ __entry->parent_gen = be32_to_cpu(pptr->p_gen);
+ __entry->namelen = name->len;
+ memcpy(__get_str(name), name->name, name->len);
+ ),
+ TP_printk("dev %d:%d path %u step %u child_ino 0x%llx child_gen 0x%x parent_ino 0x%llx parent_gen 0x%x name '%.*s'",
+ MAJOR(__entry->dev), MINOR(__entry->dev),
+ __entry->path_nr,
+ __entry->step_nr,
+ __entry->child_ino,
+ __entry->child_gen,
+ __entry->parent_ino,
+ __entry->parent_gen,
+ __entry->namelen,
+ __get_str(name))
+);
+#define DEFINE_XCHK_DIRPATH_EVENT(name) \
+DEFINE_EVENT(xchk_dirpath_class, name, \
+ TP_PROTO(struct xfs_scrub *sc, struct xfs_inode *ip, \
+ unsigned int path_nr, unsigned int step_nr, \
+ const struct xfs_name *name, \
+ const struct xfs_parent_rec *pptr), \
+ TP_ARGS(sc, ip, path_nr, step_nr, name, pptr))
+DEFINE_XCHK_DIRPATH_EVENT(xchk_dirpath_disappeared);
+DEFINE_XCHK_DIRPATH_EVENT(xchk_dirpath_badgen);
+DEFINE_XCHK_DIRPATH_EVENT(xchk_dirpath_nondir_parent);
+DEFINE_XCHK_DIRPATH_EVENT(xchk_dirpath_unlinked_parent);
+DEFINE_XCHK_DIRPATH_EVENT(xchk_dirpath_found_next_step);
+
+TRACE_DEFINE_ENUM(XCHK_DIRPATH_SCANNING);
+TRACE_DEFINE_ENUM(XCHK_DIRPATH_DELETE);
+TRACE_DEFINE_ENUM(XCHK_DIRPATH_CORRUPT);
+TRACE_DEFINE_ENUM(XCHK_DIRPATH_LOOP);
+TRACE_DEFINE_ENUM(XCHK_DIRPATH_STALE);
+TRACE_DEFINE_ENUM(XCHK_DIRPATH_OK);
+TRACE_DEFINE_ENUM(XREP_DIRPATH_DELETING);
+TRACE_DEFINE_ENUM(XREP_DIRPATH_DELETED);
+TRACE_DEFINE_ENUM(XREP_DIRPATH_ADOPTING);
+TRACE_DEFINE_ENUM(XREP_DIRPATH_ADOPTED);
+
+#define XCHK_DIRPATH_OUTCOME_STRINGS \
+ { XCHK_DIRPATH_SCANNING, "scanning" }, \
+ { XCHK_DIRPATH_DELETE, "delete" }, \
+ { XCHK_DIRPATH_CORRUPT, "corrupt" }, \
+ { XCHK_DIRPATH_LOOP, "loop" }, \
+ { XCHK_DIRPATH_STALE, "stale" }, \
+ { XCHK_DIRPATH_OK, "ok" }, \
+ { XREP_DIRPATH_DELETING, "deleting" }, \
+ { XREP_DIRPATH_DELETED, "deleted" }, \
+ { XREP_DIRPATH_ADOPTING, "adopting" }, \
+ { XREP_DIRPATH_ADOPTED, "adopted" }
+
+DECLARE_EVENT_CLASS(xchk_dirpath_outcome_class,
+ TP_PROTO(struct xfs_scrub *sc, unsigned long long path_nr,
+ unsigned int nr_steps, \
+ unsigned int outcome),
+ TP_ARGS(sc, path_nr, nr_steps, outcome),
+ TP_STRUCT__entry(
+ __field(dev_t, dev)
+ __field(unsigned long long, path_nr)
+ __field(unsigned int, nr_steps)
+ __field(unsigned int, outcome)
+ ),
+ TP_fast_assign(
+ __entry->dev = sc->mp->m_super->s_dev;
+ __entry->path_nr = path_nr;
+ __entry->nr_steps = nr_steps;
+ __entry->outcome = outcome;
+ ),
+ TP_printk("dev %d:%d path %llu steps %u outcome %s",
+ MAJOR(__entry->dev), MINOR(__entry->dev),
+ __entry->path_nr,
+ __entry->nr_steps,
+ __print_symbolic(__entry->outcome, XCHK_DIRPATH_OUTCOME_STRINGS))
+);
+#define DEFINE_XCHK_DIRPATH_OUTCOME_EVENT(name) \
+DEFINE_EVENT(xchk_dirpath_outcome_class, name, \
+ TP_PROTO(struct xfs_scrub *sc, unsigned long long path_nr, \
+ unsigned int nr_steps, \
+ unsigned int outcome), \
+ TP_ARGS(sc, path_nr, nr_steps, outcome))
+DEFINE_XCHK_DIRPATH_OUTCOME_EVENT(xchk_dirpath_set_outcome);
+DEFINE_XCHK_DIRPATH_OUTCOME_EVENT(xchk_dirpath_evaluate_path);
+
+DECLARE_EVENT_CLASS(xchk_dirtree_evaluate_class,
+ TP_PROTO(const struct xchk_dirtree *dl,
+ const struct xchk_dirtree_outcomes *oc),
+ TP_ARGS(dl, oc),
+ TP_STRUCT__entry(
+ __field(dev_t, dev)
+ __field(xfs_ino_t, ino)
+ __field(xfs_ino_t, rootino)
+ __field(unsigned int, nr_paths)
+ __field(unsigned int, bad)
+ __field(unsigned int, suspect)
+ __field(unsigned int, good)
+ __field(bool, needs_adoption)
+ ),
+ TP_fast_assign(
+ __entry->dev = dl->sc->mp->m_super->s_dev;
+ __entry->ino = dl->sc->ip->i_ino;
+ __entry->rootino = dl->root_ino;
+ __entry->nr_paths = dl->nr_paths;
+ __entry->bad = oc->bad;
+ __entry->suspect = oc->suspect;
+ __entry->good = oc->good;
+ __entry->needs_adoption = oc->needs_adoption ? 1 : 0;
+ ),
+ TP_printk("dev %d:%d ino 0x%llx rootino 0x%llx nr_paths %u bad %u suspect %u good %u adopt? %d",
+ MAJOR(__entry->dev), MINOR(__entry->dev),
+ __entry->ino,
+ __entry->rootino,
+ __entry->nr_paths,
+ __entry->bad,
+ __entry->suspect,
+ __entry->good,
+ __entry->needs_adoption)
+);
+#define DEFINE_XCHK_DIRTREE_EVALUATE_EVENT(name) \
+DEFINE_EVENT(xchk_dirtree_evaluate_class, name, \
+ TP_PROTO(const struct xchk_dirtree *dl, \
+ const struct xchk_dirtree_outcomes *oc), \
+ TP_ARGS(dl, oc))
+DEFINE_XCHK_DIRTREE_EVALUATE_EVENT(xchk_dirtree_evaluate);
+
+TRACE_EVENT(xchk_dirpath_changed,
+ TP_PROTO(struct xfs_scrub *sc, unsigned int path_nr,
+ unsigned int step_nr, const struct xfs_inode *dp,
+ const struct xfs_inode *ip, const struct xfs_name *xname),
+ TP_ARGS(sc, path_nr, step_nr, dp, ip, xname),
+ TP_STRUCT__entry(
+ __field(dev_t, dev)
+ __field(unsigned int, path_nr)
+ __field(unsigned int, step_nr)
+ __field(xfs_ino_t, child_ino)
+ __field(xfs_ino_t, parent_ino)
+ __field(unsigned int, namelen)
+ __dynamic_array(char, name, xname->len)
+ ),
+ TP_fast_assign(
+ __entry->dev = sc->mp->m_super->s_dev;
+ __entry->path_nr = path_nr;
+ __entry->step_nr = step_nr;
+ __entry->child_ino = ip->i_ino;
+ __entry->parent_ino = dp->i_ino;
+ __entry->namelen = xname->len;
+ memcpy(__get_str(name), xname->name, xname->len);
+ ),
+ TP_printk("dev %d:%d path %u step %u child_ino 0x%llx parent_ino 0x%llx name '%.*s'",
+ MAJOR(__entry->dev), MINOR(__entry->dev),
+ __entry->path_nr,
+ __entry->step_nr,
+ __entry->child_ino,
+ __entry->parent_ino,
+ __entry->namelen,
+ __get_str(name))
+);
+
+TRACE_EVENT(xchk_dirtree_live_update,
+ TP_PROTO(struct xfs_scrub *sc, const struct xfs_inode *dp,
+ int action, const struct xfs_inode *ip, int delta,
+ const struct xfs_name *xname),
+ TP_ARGS(sc, dp, action, ip, delta, xname),
+ TP_STRUCT__entry(
+ __field(dev_t, dev)
+ __field(xfs_ino_t, parent_ino)
+ __field(int, action)
+ __field(xfs_ino_t, child_ino)
+ __field(int, delta)
+ __field(unsigned int, namelen)
+ __dynamic_array(char, name, xname->len)
+ ),
+ TP_fast_assign(
+ __entry->dev = sc->mp->m_super->s_dev;
+ __entry->parent_ino = dp->i_ino;
+ __entry->action = action;
+ __entry->child_ino = ip->i_ino;
+ __entry->delta = delta;
+ __entry->namelen = xname->len;
+ memcpy(__get_str(name), xname->name, xname->len);
+ ),
+ TP_printk("dev %d:%d parent_ino 0x%llx child_ino 0x%llx nlink_delta %d name '%.*s'",
+ MAJOR(__entry->dev), MINOR(__entry->dev),
+ __entry->parent_ino,
+ __entry->child_ino,
+ __entry->delta,
+ __entry->namelen,
+ __get_str(name))
+);
+
/* repair tracepoints */
#if IS_ENABLED(CONFIG_XFS_ONLINE_REPAIR)
@@ -1533,6 +1947,7 @@ DEFINE_EVENT(xrep_extent_class, name, \
DEFINE_REPAIR_EXTENT_EVENT(xreap_dispose_unmap_extent);
DEFINE_REPAIR_EXTENT_EVENT(xreap_dispose_free_extent);
DEFINE_REPAIR_EXTENT_EVENT(xreap_agextent_binval);
+DEFINE_REPAIR_EXTENT_EVENT(xreap_bmapi_binval);
DEFINE_REPAIR_EXTENT_EVENT(xrep_agfl_insert);
DECLARE_EVENT_CLASS(xrep_reap_find_class,
@@ -1566,6 +1981,7 @@ DEFINE_EVENT(xrep_reap_find_class, name, \
bool crosslinked), \
TP_ARGS(pag, agbno, len, crosslinked))
DEFINE_REPAIR_REAP_FIND_EVENT(xreap_agextent_select);
+DEFINE_REPAIR_REAP_FIND_EVENT(xreap_bmapi_select);
DECLARE_EVENT_CLASS(xrep_rmap_class,
TP_PROTO(struct xfs_mount *mp, xfs_agnumber_t agno,
@@ -2273,6 +2689,891 @@ TRACE_EVENT(xrep_rmap_live_update,
__entry->flags)
);
+TRACE_EVENT(xrep_tempfile_create,
+ TP_PROTO(struct xfs_scrub *sc),
+ TP_ARGS(sc),
+ TP_STRUCT__entry(
+ __field(dev_t, dev)
+ __field(xfs_ino_t, ino)
+ __field(unsigned int, type)
+ __field(xfs_agnumber_t, agno)
+ __field(xfs_ino_t, inum)
+ __field(unsigned int, gen)
+ __field(unsigned int, flags)
+ __field(xfs_ino_t, temp_inum)
+ ),
+ TP_fast_assign(
+ __entry->dev = sc->mp->m_super->s_dev;
+ __entry->ino = sc->file ? XFS_I(file_inode(sc->file))->i_ino : 0;
+ __entry->type = sc->sm->sm_type;
+ __entry->agno = sc->sm->sm_agno;
+ __entry->inum = sc->sm->sm_ino;
+ __entry->gen = sc->sm->sm_gen;
+ __entry->flags = sc->sm->sm_flags;
+ __entry->temp_inum = sc->tempip->i_ino;
+ ),
+ TP_printk("dev %d:%d ino 0x%llx type %s inum 0x%llx gen 0x%x flags 0x%x temp_inum 0x%llx",
+ MAJOR(__entry->dev), MINOR(__entry->dev),
+ __entry->ino,
+ __print_symbolic(__entry->type, XFS_SCRUB_TYPE_STRINGS),
+ __entry->inum,
+ __entry->gen,
+ __entry->flags,
+ __entry->temp_inum)
+);
+
+DECLARE_EVENT_CLASS(xrep_tempfile_class,
+ TP_PROTO(struct xfs_scrub *sc, int whichfork,
+ struct xfs_bmbt_irec *irec),
+ TP_ARGS(sc, whichfork, irec),
+ TP_STRUCT__entry(
+ __field(dev_t, dev)
+ __field(xfs_ino_t, ino)
+ __field(int, whichfork)
+ __field(xfs_fileoff_t, lblk)
+ __field(xfs_filblks_t, len)
+ __field(xfs_fsblock_t, pblk)
+ __field(int, state)
+ ),
+ TP_fast_assign(
+ __entry->dev = sc->mp->m_super->s_dev;
+ __entry->ino = sc->tempip->i_ino;
+ __entry->whichfork = whichfork;
+ __entry->lblk = irec->br_startoff;
+ __entry->len = irec->br_blockcount;
+ __entry->pblk = irec->br_startblock;
+ __entry->state = irec->br_state;
+ ),
+ TP_printk("dev %d:%d ino 0x%llx whichfork %s fileoff 0x%llx fsbcount 0x%llx startblock 0x%llx state %d",
+ MAJOR(__entry->dev), MINOR(__entry->dev),
+ __entry->ino,
+ __print_symbolic(__entry->whichfork, XFS_WHICHFORK_STRINGS),
+ __entry->lblk,
+ __entry->len,
+ __entry->pblk,
+ __entry->state)
+);
+#define DEFINE_XREP_TEMPFILE_EVENT(name) \
+DEFINE_EVENT(xrep_tempfile_class, name, \
+ TP_PROTO(struct xfs_scrub *sc, int whichfork, \
+ struct xfs_bmbt_irec *irec), \
+ TP_ARGS(sc, whichfork, irec))
+DEFINE_XREP_TEMPFILE_EVENT(xrep_tempfile_prealloc);
+DEFINE_XREP_TEMPFILE_EVENT(xrep_tempfile_copyin);
+
+TRACE_EVENT(xreap_ifork_extent,
+ TP_PROTO(struct xfs_scrub *sc, struct xfs_inode *ip, int whichfork,
+ const struct xfs_bmbt_irec *irec),
+ TP_ARGS(sc, ip, whichfork, irec),
+ TP_STRUCT__entry(
+ __field(dev_t, dev)
+ __field(xfs_ino_t, ino)
+ __field(int, whichfork)
+ __field(xfs_fileoff_t, fileoff)
+ __field(xfs_filblks_t, len)
+ __field(xfs_agnumber_t, agno)
+ __field(xfs_agblock_t, agbno)
+ __field(int, state)
+ ),
+ TP_fast_assign(
+ __entry->dev = sc->mp->m_super->s_dev;
+ __entry->ino = ip->i_ino;
+ __entry->whichfork = whichfork;
+ __entry->fileoff = irec->br_startoff;
+ __entry->len = irec->br_blockcount;
+ __entry->agno = XFS_FSB_TO_AGNO(sc->mp, irec->br_startblock);
+ __entry->agbno = XFS_FSB_TO_AGBNO(sc->mp, irec->br_startblock);
+ __entry->state = irec->br_state;
+ ),
+ TP_printk("dev %d:%d ip 0x%llx whichfork %s agno 0x%x agbno 0x%x fileoff 0x%llx fsbcount 0x%llx state 0x%x",
+ MAJOR(__entry->dev), MINOR(__entry->dev),
+ __entry->ino,
+ __print_symbolic(__entry->whichfork, XFS_WHICHFORK_STRINGS),
+ __entry->agno,
+ __entry->agbno,
+ __entry->fileoff,
+ __entry->len,
+ __entry->state)
+);
+
+TRACE_EVENT(xreap_bmapi_binval_scan,
+ TP_PROTO(struct xfs_scrub *sc, const struct xfs_bmbt_irec *irec,
+ xfs_extlen_t scan_blocks),
+ TP_ARGS(sc, irec, scan_blocks),
+ TP_STRUCT__entry(
+ __field(dev_t, dev)
+ __field(xfs_filblks_t, len)
+ __field(xfs_agnumber_t, agno)
+ __field(xfs_agblock_t, agbno)
+ __field(xfs_extlen_t, scan_blocks)
+ ),
+ TP_fast_assign(
+ __entry->dev = sc->mp->m_super->s_dev;
+ __entry->len = irec->br_blockcount;
+ __entry->agno = XFS_FSB_TO_AGNO(sc->mp, irec->br_startblock);
+ __entry->agbno = XFS_FSB_TO_AGBNO(sc->mp, irec->br_startblock);
+ __entry->scan_blocks = scan_blocks;
+ ),
+ TP_printk("dev %d:%d agno 0x%x agbno 0x%x fsbcount 0x%llx scan_blocks 0x%x",
+ MAJOR(__entry->dev), MINOR(__entry->dev),
+ __entry->agno,
+ __entry->agbno,
+ __entry->len,
+ __entry->scan_blocks)
+);
+
+TRACE_EVENT(xrep_xattr_recover_leafblock,
+ TP_PROTO(struct xfs_inode *ip, xfs_dablk_t dabno, uint16_t magic),
+ TP_ARGS(ip, dabno, magic),
+ TP_STRUCT__entry(
+ __field(dev_t, dev)
+ __field(xfs_ino_t, ino)
+ __field(xfs_dablk_t, dabno)
+ __field(uint16_t, magic)
+ ),
+ TP_fast_assign(
+ __entry->dev = ip->i_mount->m_super->s_dev;
+ __entry->ino = ip->i_ino;
+ __entry->dabno = dabno;
+ __entry->magic = magic;
+ ),
+ TP_printk("dev %d:%d ino 0x%llx dablk 0x%x magic 0x%x",
+ MAJOR(__entry->dev), MINOR(__entry->dev),
+ __entry->ino,
+ __entry->dabno,
+ __entry->magic)
+);
+
+DECLARE_EVENT_CLASS(xrep_xattr_salvage_class,
+ TP_PROTO(struct xfs_inode *ip, unsigned int flags, char *name,
+ unsigned int namelen, unsigned int valuelen),
+ TP_ARGS(ip, flags, name, namelen, valuelen),
+ TP_STRUCT__entry(
+ __field(dev_t, dev)
+ __field(xfs_ino_t, ino)
+ __field(unsigned int, flags)
+ __field(unsigned int, namelen)
+ __dynamic_array(char, name, namelen)
+ __field(unsigned int, valuelen)
+ ),
+ TP_fast_assign(
+ __entry->dev = ip->i_mount->m_super->s_dev;
+ __entry->ino = ip->i_ino;
+ __entry->flags = flags;
+ __entry->namelen = namelen;
+ memcpy(__get_str(name), name, namelen);
+ __entry->valuelen = valuelen;
+ ),
+ TP_printk("dev %d:%d ino 0x%llx flags %s name '%.*s' valuelen 0x%x",
+ MAJOR(__entry->dev), MINOR(__entry->dev),
+ __entry->ino,
+ __print_flags(__entry->flags, "|", XFS_ATTR_NAMESPACE_STR),
+ __entry->namelen,
+ __get_str(name),
+ __entry->valuelen)
+);
+#define DEFINE_XREP_XATTR_SALVAGE_EVENT(name) \
+DEFINE_EVENT(xrep_xattr_salvage_class, name, \
+ TP_PROTO(struct xfs_inode *ip, unsigned int flags, char *name, \
+ unsigned int namelen, unsigned int valuelen), \
+ TP_ARGS(ip, flags, name, namelen, valuelen))
+DEFINE_XREP_XATTR_SALVAGE_EVENT(xrep_xattr_salvage_rec);
+DEFINE_XREP_XATTR_SALVAGE_EVENT(xrep_xattr_insert_rec);
+DEFINE_XREP_XATTR_SALVAGE_EVENT(xrep_parent_stash_xattr);
+DEFINE_XREP_XATTR_SALVAGE_EVENT(xrep_parent_insert_xattr);
+
+DECLARE_EVENT_CLASS(xrep_pptr_salvage_class,
+ TP_PROTO(struct xfs_inode *ip, unsigned int flags, const void *name,
+ unsigned int namelen, const void *value, unsigned int valuelen),
+ TP_ARGS(ip, flags, name, namelen, value, valuelen),
+ TP_STRUCT__entry(
+ __field(dev_t, dev)
+ __field(xfs_ino_t, ino)
+ __field(xfs_ino_t, parent_ino)
+ __field(unsigned int, parent_gen)
+ __field(unsigned int, namelen)
+ __dynamic_array(char, name, namelen)
+ ),
+ TP_fast_assign(
+ const struct xfs_parent_rec *rec = value;
+
+ __entry->dev = ip->i_mount->m_super->s_dev;
+ __entry->ino = ip->i_ino;
+ __entry->parent_ino = be64_to_cpu(rec->p_ino);
+ __entry->parent_gen = be32_to_cpu(rec->p_gen);
+ __entry->namelen = namelen;
+ memcpy(__get_str(name), name, namelen);
+ ),
+ TP_printk("dev %d:%d ino 0x%llx parent_ino 0x%llx parent_gen 0x%x name '%.*s'",
+ MAJOR(__entry->dev), MINOR(__entry->dev),
+ __entry->ino,
+ __entry->parent_ino,
+ __entry->parent_gen,
+ __entry->namelen,
+ __get_str(name))
+)
+#define DEFINE_XREP_PPTR_SALVAGE_EVENT(name) \
+DEFINE_EVENT(xrep_pptr_salvage_class, name, \
+ TP_PROTO(struct xfs_inode *ip, unsigned int flags, const void *name, \
+ unsigned int namelen, const void *value, unsigned int valuelen), \
+ TP_ARGS(ip, flags, name, namelen, value, valuelen))
+DEFINE_XREP_PPTR_SALVAGE_EVENT(xrep_xattr_salvage_pptr);
+DEFINE_XREP_PPTR_SALVAGE_EVENT(xrep_xattr_insert_pptr);
+
+TRACE_EVENT(xrep_xattr_class,
+ TP_PROTO(struct xfs_inode *ip, struct xfs_inode *arg_ip),
+ TP_ARGS(ip, arg_ip),
+ TP_STRUCT__entry(
+ __field(dev_t, dev)
+ __field(xfs_ino_t, ino)
+ __field(xfs_ino_t, src_ino)
+ ),
+ TP_fast_assign(
+ __entry->dev = ip->i_mount->m_super->s_dev;
+ __entry->ino = ip->i_ino;
+ __entry->src_ino = arg_ip->i_ino;
+ ),
+ TP_printk("dev %d:%d ino 0x%llx src 0x%llx",
+ MAJOR(__entry->dev), MINOR(__entry->dev),
+ __entry->ino,
+ __entry->src_ino)
+)
+#define DEFINE_XREP_XATTR_EVENT(name) \
+DEFINE_EVENT(xrep_xattr_class, name, \
+ TP_PROTO(struct xfs_inode *ip, struct xfs_inode *arg_ip), \
+ TP_ARGS(ip, arg_ip))
+DEFINE_XREP_XATTR_EVENT(xrep_xattr_rebuild_tree);
+DEFINE_XREP_XATTR_EVENT(xrep_xattr_reset_fork);
+DEFINE_XREP_XATTR_EVENT(xrep_xattr_full_reset);
+
+DECLARE_EVENT_CLASS(xrep_xattr_pptr_scan_class,
+ TP_PROTO(struct xfs_inode *ip, const struct xfs_inode *dp,
+ const struct xfs_name *name),
+ TP_ARGS(ip, dp, name),
+ TP_STRUCT__entry(
+ __field(dev_t, dev)
+ __field(xfs_ino_t, ino)
+ __field(xfs_ino_t, parent_ino)
+ __field(unsigned int, parent_gen)
+ __field(unsigned int, namelen)
+ __dynamic_array(char, name, name->len)
+ ),
+ TP_fast_assign(
+ __entry->dev = ip->i_mount->m_super->s_dev;
+ __entry->ino = ip->i_ino;
+ __entry->parent_ino = dp->i_ino;
+ __entry->parent_gen = VFS_IC(dp)->i_generation;
+ __entry->namelen = name->len;
+ memcpy(__get_str(name), name->name, name->len);
+ ),
+ TP_printk("dev %d:%d ino 0x%llx parent_ino 0x%llx parent_gen 0x%x name '%.*s'",
+ MAJOR(__entry->dev), MINOR(__entry->dev),
+ __entry->ino,
+ __entry->parent_ino,
+ __entry->parent_gen,
+ __entry->namelen,
+ __get_str(name))
+)
+#define DEFINE_XREP_XATTR_PPTR_SCAN_EVENT(name) \
+DEFINE_EVENT(xrep_xattr_pptr_scan_class, name, \
+ TP_PROTO(struct xfs_inode *ip, const struct xfs_inode *dp, \
+ const struct xfs_name *name), \
+ TP_ARGS(ip, dp, name))
+DEFINE_XREP_XATTR_PPTR_SCAN_EVENT(xrep_xattr_stash_parentadd);
+DEFINE_XREP_XATTR_PPTR_SCAN_EVENT(xrep_xattr_stash_parentremove);
+
+TRACE_EVENT(xrep_dir_recover_dirblock,
+ TP_PROTO(struct xfs_inode *dp, xfs_dablk_t dabno, uint32_t magic,
+ uint32_t magic_guess),
+ TP_ARGS(dp, dabno, magic, magic_guess),
+ TP_STRUCT__entry(
+ __field(dev_t, dev)
+ __field(xfs_ino_t, dir_ino)
+ __field(xfs_dablk_t, dabno)
+ __field(uint32_t, magic)
+ __field(uint32_t, magic_guess)
+ ),
+ TP_fast_assign(
+ __entry->dev = dp->i_mount->m_super->s_dev;
+ __entry->dir_ino = dp->i_ino;
+ __entry->dabno = dabno;
+ __entry->magic = magic;
+ __entry->magic_guess = magic_guess;
+ ),
+ TP_printk("dev %d:%d dir 0x%llx dablk 0x%x magic 0x%x magic_guess 0x%x",
+ MAJOR(__entry->dev), MINOR(__entry->dev),
+ __entry->dir_ino,
+ __entry->dabno,
+ __entry->magic,
+ __entry->magic_guess)
+);
+
+DECLARE_EVENT_CLASS(xrep_dir_class,
+ TP_PROTO(struct xfs_inode *dp, xfs_ino_t parent_ino),
+ TP_ARGS(dp, parent_ino),
+ TP_STRUCT__entry(
+ __field(dev_t, dev)
+ __field(xfs_ino_t, dir_ino)
+ __field(xfs_ino_t, parent_ino)
+ ),
+ TP_fast_assign(
+ __entry->dev = dp->i_mount->m_super->s_dev;
+ __entry->dir_ino = dp->i_ino;
+ __entry->parent_ino = parent_ino;
+ ),
+ TP_printk("dev %d:%d dir 0x%llx parent 0x%llx",
+ MAJOR(__entry->dev), MINOR(__entry->dev),
+ __entry->dir_ino,
+ __entry->parent_ino)
+)
+#define DEFINE_XREP_DIR_EVENT(name) \
+DEFINE_EVENT(xrep_dir_class, name, \
+ TP_PROTO(struct xfs_inode *dp, xfs_ino_t parent_ino), \
+ TP_ARGS(dp, parent_ino))
+DEFINE_XREP_DIR_EVENT(xrep_dir_rebuild_tree);
+DEFINE_XREP_DIR_EVENT(xrep_dir_reset_fork);
+DEFINE_XREP_DIR_EVENT(xrep_parent_reset_dotdot);
+
+DECLARE_EVENT_CLASS(xrep_dirent_class,
+ TP_PROTO(struct xfs_inode *dp, const struct xfs_name *name,
+ xfs_ino_t ino),
+ TP_ARGS(dp, name, ino),
+ TP_STRUCT__entry(
+ __field(dev_t, dev)
+ __field(xfs_ino_t, dir_ino)
+ __field(unsigned int, namelen)
+ __dynamic_array(char, name, name->len)
+ __field(xfs_ino_t, ino)
+ __field(uint8_t, ftype)
+ ),
+ TP_fast_assign(
+ __entry->dev = dp->i_mount->m_super->s_dev;
+ __entry->dir_ino = dp->i_ino;
+ __entry->namelen = name->len;
+ memcpy(__get_str(name), name->name, name->len);
+ __entry->ino = ino;
+ __entry->ftype = name->type;
+ ),
+ TP_printk("dev %d:%d dir 0x%llx ftype %s name '%.*s' ino 0x%llx",
+ MAJOR(__entry->dev), MINOR(__entry->dev),
+ __entry->dir_ino,
+ __print_symbolic(__entry->ftype, XFS_DIR3_FTYPE_STR),
+ __entry->namelen,
+ __get_str(name),
+ __entry->ino)
+)
+#define DEFINE_XREP_DIRENT_EVENT(name) \
+DEFINE_EVENT(xrep_dirent_class, name, \
+ TP_PROTO(struct xfs_inode *dp, const struct xfs_name *name, \
+ xfs_ino_t ino), \
+ TP_ARGS(dp, name, ino))
+DEFINE_XREP_DIRENT_EVENT(xrep_dir_salvage_entry);
+DEFINE_XREP_DIRENT_EVENT(xrep_dir_stash_createname);
+DEFINE_XREP_DIRENT_EVENT(xrep_dir_replay_createname);
+DEFINE_XREP_DIRENT_EVENT(xrep_adoption_reparent);
+DEFINE_XREP_DIRENT_EVENT(xrep_dir_stash_removename);
+DEFINE_XREP_DIRENT_EVENT(xrep_dir_replay_removename);
+
+DECLARE_EVENT_CLASS(xrep_adoption_class,
+ TP_PROTO(struct xfs_inode *dp, struct xfs_inode *ip, bool moved),
+ TP_ARGS(dp, ip, moved),
+ TP_STRUCT__entry(
+ __field(dev_t, dev)
+ __field(xfs_ino_t, dir_ino)
+ __field(xfs_ino_t, child_ino)
+ __field(bool, moved)
+ ),
+ TP_fast_assign(
+ __entry->dev = dp->i_mount->m_super->s_dev;
+ __entry->dir_ino = dp->i_ino;
+ __entry->child_ino = ip->i_ino;
+ __entry->moved = moved;
+ ),
+ TP_printk("dev %d:%d dir 0x%llx child 0x%llx moved? %d",
+ MAJOR(__entry->dev), MINOR(__entry->dev),
+ __entry->dir_ino,
+ __entry->child_ino,
+ __entry->moved)
+);
+#define DEFINE_XREP_ADOPTION_EVENT(name) \
+DEFINE_EVENT(xrep_adoption_class, name, \
+ TP_PROTO(struct xfs_inode *dp, struct xfs_inode *ip, bool moved), \
+ TP_ARGS(dp, ip, moved))
+DEFINE_XREP_ADOPTION_EVENT(xrep_adoption_trans_roll);
+
+DECLARE_EVENT_CLASS(xrep_parent_salvage_class,
+ TP_PROTO(struct xfs_inode *dp, xfs_ino_t ino),
+ TP_ARGS(dp, ino),
+ TP_STRUCT__entry(
+ __field(dev_t, dev)
+ __field(xfs_ino_t, dir_ino)
+ __field(xfs_ino_t, ino)
+ ),
+ TP_fast_assign(
+ __entry->dev = dp->i_mount->m_super->s_dev;
+ __entry->dir_ino = dp->i_ino;
+ __entry->ino = ino;
+ ),
+ TP_printk("dev %d:%d dir 0x%llx parent 0x%llx",
+ MAJOR(__entry->dev), MINOR(__entry->dev),
+ __entry->dir_ino,
+ __entry->ino)
+)
+#define DEFINE_XREP_PARENT_SALVAGE_EVENT(name) \
+DEFINE_EVENT(xrep_parent_salvage_class, name, \
+ TP_PROTO(struct xfs_inode *dp, xfs_ino_t ino), \
+ TP_ARGS(dp, ino))
+DEFINE_XREP_PARENT_SALVAGE_EVENT(xrep_dir_salvaged_parent);
+DEFINE_XREP_PARENT_SALVAGE_EVENT(xrep_findparent_dirent);
+DEFINE_XREP_PARENT_SALVAGE_EVENT(xrep_findparent_from_dcache);
+
+DECLARE_EVENT_CLASS(xrep_pptr_class,
+ TP_PROTO(struct xfs_inode *ip, const struct xfs_name *name,
+ const struct xfs_parent_rec *pptr),
+ TP_ARGS(ip, name, pptr),
+ TP_STRUCT__entry(
+ __field(dev_t, dev)
+ __field(xfs_ino_t, ino)
+ __field(xfs_ino_t, parent_ino)
+ __field(unsigned int, parent_gen)
+ __field(unsigned int, namelen)
+ __dynamic_array(char, name, name->len)
+ ),
+ TP_fast_assign(
+ __entry->dev = ip->i_mount->m_super->s_dev;
+ __entry->ino = ip->i_ino;
+ __entry->parent_ino = be64_to_cpu(pptr->p_ino);
+ __entry->parent_gen = be32_to_cpu(pptr->p_gen);
+ __entry->namelen = name->len;
+ memcpy(__get_str(name), name->name, name->len);
+ ),
+ TP_printk("dev %d:%d ino 0x%llx parent_ino 0x%llx parent_gen 0x%x name '%.*s'",
+ MAJOR(__entry->dev), MINOR(__entry->dev),
+ __entry->ino,
+ __entry->parent_ino,
+ __entry->parent_gen,
+ __entry->namelen,
+ __get_str(name))
+)
+#define DEFINE_XREP_PPTR_EVENT(name) \
+DEFINE_EVENT(xrep_pptr_class, name, \
+ TP_PROTO(struct xfs_inode *ip, const struct xfs_name *name, \
+ const struct xfs_parent_rec *pptr), \
+ TP_ARGS(ip, name, pptr))
+DEFINE_XREP_PPTR_EVENT(xrep_xattr_replay_parentadd);
+DEFINE_XREP_PPTR_EVENT(xrep_xattr_replay_parentremove);
+DEFINE_XREP_PPTR_EVENT(xrep_parent_replay_parentadd);
+DEFINE_XREP_PPTR_EVENT(xrep_parent_replay_parentremove);
+
+DECLARE_EVENT_CLASS(xrep_pptr_scan_class,
+ TP_PROTO(struct xfs_inode *ip, const struct xfs_inode *dp,
+ const struct xfs_name *name),
+ TP_ARGS(ip, dp, name),
+ TP_STRUCT__entry(
+ __field(dev_t, dev)
+ __field(xfs_ino_t, ino)
+ __field(xfs_ino_t, parent_ino)
+ __field(unsigned int, parent_gen)
+ __field(unsigned int, namelen)
+ __dynamic_array(char, name, name->len)
+ ),
+ TP_fast_assign(
+ __entry->dev = ip->i_mount->m_super->s_dev;
+ __entry->ino = ip->i_ino;
+ __entry->parent_ino = dp->i_ino;
+ __entry->parent_gen = VFS_IC(dp)->i_generation;
+ __entry->namelen = name->len;
+ memcpy(__get_str(name), name->name, name->len);
+ ),
+ TP_printk("dev %d:%d ino 0x%llx parent_ino 0x%llx parent_gen 0x%x name '%.*s'",
+ MAJOR(__entry->dev), MINOR(__entry->dev),
+ __entry->ino,
+ __entry->parent_ino,
+ __entry->parent_gen,
+ __entry->namelen,
+ __get_str(name))
+)
+#define DEFINE_XREP_PPTR_SCAN_EVENT(name) \
+DEFINE_EVENT(xrep_pptr_scan_class, name, \
+ TP_PROTO(struct xfs_inode *ip, const struct xfs_inode *dp, \
+ const struct xfs_name *name), \
+ TP_ARGS(ip, dp, name))
+DEFINE_XREP_PPTR_SCAN_EVENT(xrep_parent_stash_parentadd);
+DEFINE_XREP_PPTR_SCAN_EVENT(xrep_parent_stash_parentremove);
+
+TRACE_EVENT(xrep_nlinks_set_record,
+ TP_PROTO(struct xfs_mount *mp, xfs_ino_t ino,
+ const struct xchk_nlink *obs),
+ TP_ARGS(mp, ino, obs),
+ TP_STRUCT__entry(
+ __field(dev_t, dev)
+ __field(xfs_ino_t, ino)
+ __field(xfs_nlink_t, parents)
+ __field(xfs_nlink_t, backrefs)
+ __field(xfs_nlink_t, children)
+ ),
+ TP_fast_assign(
+ __entry->dev = mp->m_super->s_dev;
+ __entry->ino = ino;
+ __entry->parents = obs->parents;
+ __entry->backrefs = obs->backrefs;
+ __entry->children = obs->children;
+ ),
+ TP_printk("dev %d:%d ino 0x%llx parents %u backrefs %u children %u",
+ MAJOR(__entry->dev), MINOR(__entry->dev),
+ __entry->ino,
+ __entry->parents,
+ __entry->backrefs,
+ __entry->children)
+);
+
+DECLARE_EVENT_CLASS(xrep_dentry_class,
+ TP_PROTO(struct xfs_mount *mp, const struct dentry *dentry),
+ TP_ARGS(mp, dentry),
+ TP_STRUCT__entry(
+ __field(dev_t, dev)
+ __field(unsigned int, flags)
+ __field(unsigned long, ino)
+ __field(bool, positive)
+ __field(unsigned long, parent_ino)
+ __field(unsigned int, namelen)
+ __dynamic_array(char, name, dentry->d_name.len)
+ ),
+ TP_fast_assign(
+ __entry->dev = mp->m_super->s_dev;
+ __entry->flags = dentry->d_flags;
+ __entry->positive = d_is_positive(dentry);
+ if (dentry->d_parent && d_inode(dentry->d_parent))
+ __entry->parent_ino = d_inode(dentry->d_parent)->i_ino;
+ else
+ __entry->parent_ino = -1UL;
+ __entry->ino = d_inode(dentry) ? d_inode(dentry)->i_ino : 0;
+ __entry->namelen = dentry->d_name.len;
+ memcpy(__get_str(name), dentry->d_name.name, dentry->d_name.len);
+ ),
+ TP_printk("dev %d:%d flags 0x%x positive? %d parent_ino 0x%lx ino 0x%lx name '%.*s'",
+ MAJOR(__entry->dev), MINOR(__entry->dev),
+ __entry->flags,
+ __entry->positive,
+ __entry->parent_ino,
+ __entry->ino,
+ __entry->namelen,
+ __get_str(name))
+);
+#define DEFINE_REPAIR_DENTRY_EVENT(name) \
+DEFINE_EVENT(xrep_dentry_class, name, \
+ TP_PROTO(struct xfs_mount *mp, const struct dentry *dentry), \
+ TP_ARGS(mp, dentry))
+DEFINE_REPAIR_DENTRY_EVENT(xrep_adoption_check_child);
+DEFINE_REPAIR_DENTRY_EVENT(xrep_adoption_invalidate_child);
+DEFINE_REPAIR_DENTRY_EVENT(xrep_dirtree_delete_child);
+
+TRACE_EVENT(xrep_symlink_salvage_target,
+ TP_PROTO(struct xfs_inode *ip, char *target, unsigned int targetlen),
+ TP_ARGS(ip, target, targetlen),
+ TP_STRUCT__entry(
+ __field(dev_t, dev)
+ __field(xfs_ino_t, ino)
+ __field(unsigned int, targetlen)
+ __dynamic_array(char, target, targetlen + 1)
+ ),
+ TP_fast_assign(
+ __entry->dev = ip->i_mount->m_super->s_dev;
+ __entry->ino = ip->i_ino;
+ __entry->targetlen = targetlen;
+ memcpy(__get_str(target), target, targetlen);
+ __get_str(target)[targetlen] = 0;
+ ),
+ TP_printk("dev %d:%d ip 0x%llx target '%.*s'",
+ MAJOR(__entry->dev), MINOR(__entry->dev),
+ __entry->ino,
+ __entry->targetlen,
+ __get_str(target))
+);
+
+DECLARE_EVENT_CLASS(xrep_symlink_class,
+ TP_PROTO(struct xfs_inode *ip),
+ TP_ARGS(ip),
+ TP_STRUCT__entry(
+ __field(dev_t, dev)
+ __field(xfs_ino_t, ino)
+ ),
+ TP_fast_assign(
+ __entry->dev = ip->i_mount->m_super->s_dev;
+ __entry->ino = ip->i_ino;
+ ),
+ TP_printk("dev %d:%d ip 0x%llx",
+ MAJOR(__entry->dev), MINOR(__entry->dev),
+ __entry->ino)
+);
+
+#define DEFINE_XREP_SYMLINK_EVENT(name) \
+DEFINE_EVENT(xrep_symlink_class, name, \
+ TP_PROTO(struct xfs_inode *ip), \
+ TP_ARGS(ip))
+DEFINE_XREP_SYMLINK_EVENT(xrep_symlink_rebuild);
+DEFINE_XREP_SYMLINK_EVENT(xrep_symlink_reset_fork);
+
+TRACE_EVENT(xrep_iunlink_visit,
+ TP_PROTO(struct xfs_perag *pag, unsigned int bucket,
+ xfs_agino_t bucket_agino, struct xfs_inode *ip),
+ TP_ARGS(pag, bucket, bucket_agino, ip),
+ TP_STRUCT__entry(
+ __field(dev_t, dev)
+ __field(xfs_agnumber_t, agno)
+ __field(xfs_agino_t, agino)
+ __field(unsigned int, bucket)
+ __field(xfs_agino_t, bucket_agino)
+ __field(xfs_agino_t, prev_agino)
+ __field(xfs_agino_t, next_agino)
+ ),
+ TP_fast_assign(
+ __entry->dev = pag->pag_mount->m_super->s_dev;
+ __entry->agno = pag->pag_agno;
+ __entry->agino = XFS_INO_TO_AGINO(pag->pag_mount, ip->i_ino);
+ __entry->bucket = bucket;
+ __entry->bucket_agino = bucket_agino;
+ __entry->prev_agino = ip->i_prev_unlinked;
+ __entry->next_agino = ip->i_next_unlinked;
+ ),
+ TP_printk("dev %d:%d agno 0x%x bucket %u agino 0x%x bucket_agino 0x%x prev_agino 0x%x next_agino 0x%x",
+ MAJOR(__entry->dev), MINOR(__entry->dev),
+ __entry->agno,
+ __entry->bucket,
+ __entry->agino,
+ __entry->bucket_agino,
+ __entry->prev_agino,
+ __entry->next_agino)
+);
+
+TRACE_EVENT(xrep_iunlink_reload_next,
+ TP_PROTO(struct xfs_inode *ip, xfs_agino_t prev_agino),
+ TP_ARGS(ip, prev_agino),
+ TP_STRUCT__entry(
+ __field(dev_t, dev)
+ __field(xfs_agnumber_t, agno)
+ __field(xfs_agino_t, agino)
+ __field(xfs_agino_t, old_prev_agino)
+ __field(xfs_agino_t, prev_agino)
+ __field(xfs_agino_t, next_agino)
+ __field(unsigned int, nlink)
+ ),
+ TP_fast_assign(
+ __entry->dev = ip->i_mount->m_super->s_dev;
+ __entry->agno = XFS_INO_TO_AGNO(ip->i_mount, ip->i_ino);
+ __entry->agino = XFS_INO_TO_AGINO(ip->i_mount, ip->i_ino);
+ __entry->old_prev_agino = ip->i_prev_unlinked;
+ __entry->prev_agino = prev_agino;
+ __entry->next_agino = ip->i_next_unlinked;
+ __entry->nlink = VFS_I(ip)->i_nlink;
+ ),
+ TP_printk("dev %d:%d agno 0x%x bucket %u agino 0x%x nlink %u old_prev_agino %u prev_agino 0x%x next_agino 0x%x",
+ MAJOR(__entry->dev), MINOR(__entry->dev),
+ __entry->agno,
+ __entry->agino % XFS_AGI_UNLINKED_BUCKETS,
+ __entry->agino,
+ __entry->nlink,
+ __entry->old_prev_agino,
+ __entry->prev_agino,
+ __entry->next_agino)
+);
+
+TRACE_EVENT(xrep_iunlink_reload_ondisk,
+ TP_PROTO(struct xfs_inode *ip),
+ TP_ARGS(ip),
+ TP_STRUCT__entry(
+ __field(dev_t, dev)
+ __field(xfs_agnumber_t, agno)
+ __field(xfs_agino_t, agino)
+ __field(unsigned int, nlink)
+ __field(xfs_agino_t, next_agino)
+ ),
+ TP_fast_assign(
+ __entry->dev = ip->i_mount->m_super->s_dev;
+ __entry->agno = XFS_INO_TO_AGNO(ip->i_mount, ip->i_ino);
+ __entry->agino = XFS_INO_TO_AGINO(ip->i_mount, ip->i_ino);
+ __entry->nlink = VFS_I(ip)->i_nlink;
+ __entry->next_agino = ip->i_next_unlinked;
+ ),
+ TP_printk("dev %d:%d agno 0x%x bucket %u agino 0x%x nlink %u next_agino 0x%x",
+ MAJOR(__entry->dev), MINOR(__entry->dev),
+ __entry->agno,
+ __entry->agino % XFS_AGI_UNLINKED_BUCKETS,
+ __entry->agino,
+ __entry->nlink,
+ __entry->next_agino)
+);
+
+TRACE_EVENT(xrep_iunlink_walk_ondisk_bucket,
+ TP_PROTO(struct xfs_perag *pag, unsigned int bucket,
+ xfs_agino_t prev_agino, xfs_agino_t next_agino),
+ TP_ARGS(pag, bucket, prev_agino, next_agino),
+ TP_STRUCT__entry(
+ __field(dev_t, dev)
+ __field(xfs_agnumber_t, agno)
+ __field(unsigned int, bucket)
+ __field(xfs_agino_t, prev_agino)
+ __field(xfs_agino_t, next_agino)
+ ),
+ TP_fast_assign(
+ __entry->dev = pag->pag_mount->m_super->s_dev;
+ __entry->agno = pag->pag_agno;
+ __entry->bucket = bucket;
+ __entry->prev_agino = prev_agino;
+ __entry->next_agino = next_agino;
+ ),
+ TP_printk("dev %d:%d agno 0x%x bucket %u prev_agino 0x%x next_agino 0x%x",
+ MAJOR(__entry->dev), MINOR(__entry->dev),
+ __entry->agno,
+ __entry->bucket,
+ __entry->prev_agino,
+ __entry->next_agino)
+);
+
+DECLARE_EVENT_CLASS(xrep_iunlink_resolve_class,
+ TP_PROTO(struct xfs_perag *pag, unsigned int bucket,
+ xfs_agino_t prev_agino, xfs_agino_t next_agino),
+ TP_ARGS(pag, bucket, prev_agino, next_agino),
+ TP_STRUCT__entry(
+ __field(dev_t, dev)
+ __field(xfs_agnumber_t, agno)
+ __field(unsigned int, bucket)
+ __field(xfs_agino_t, prev_agino)
+ __field(xfs_agino_t, next_agino)
+ ),
+ TP_fast_assign(
+ __entry->dev = pag->pag_mount->m_super->s_dev;
+ __entry->agno = pag->pag_agno;
+ __entry->bucket = bucket;
+ __entry->prev_agino = prev_agino;
+ __entry->next_agino = next_agino;
+ ),
+ TP_printk("dev %d:%d agno 0x%x bucket %u prev_agino 0x%x next_agino 0x%x",
+ MAJOR(__entry->dev), MINOR(__entry->dev),
+ __entry->agno,
+ __entry->bucket,
+ __entry->prev_agino,
+ __entry->next_agino)
+);
+#define DEFINE_REPAIR_IUNLINK_RESOLVE_EVENT(name) \
+DEFINE_EVENT(xrep_iunlink_resolve_class, name, \
+ TP_PROTO(struct xfs_perag *pag, unsigned int bucket, \
+ xfs_agino_t prev_agino, xfs_agino_t next_agino), \
+ TP_ARGS(pag, bucket, prev_agino, next_agino))
+DEFINE_REPAIR_IUNLINK_RESOLVE_EVENT(xrep_iunlink_resolve_uncached);
+DEFINE_REPAIR_IUNLINK_RESOLVE_EVENT(xrep_iunlink_resolve_wronglist);
+DEFINE_REPAIR_IUNLINK_RESOLVE_EVENT(xrep_iunlink_resolve_nolist);
+DEFINE_REPAIR_IUNLINK_RESOLVE_EVENT(xrep_iunlink_resolve_ok);
+
+TRACE_EVENT(xrep_iunlink_relink_next,
+ TP_PROTO(struct xfs_inode *ip, xfs_agino_t next_agino),
+ TP_ARGS(ip, next_agino),
+ TP_STRUCT__entry(
+ __field(dev_t, dev)
+ __field(xfs_agnumber_t, agno)
+ __field(xfs_agino_t, agino)
+ __field(xfs_agino_t, next_agino)
+ __field(xfs_agino_t, new_next_agino)
+ ),
+ TP_fast_assign(
+ __entry->dev = ip->i_mount->m_super->s_dev;
+ __entry->agno = XFS_INO_TO_AGNO(ip->i_mount, ip->i_ino);
+ __entry->agino = XFS_INO_TO_AGINO(ip->i_mount, ip->i_ino);
+ __entry->next_agino = ip->i_next_unlinked;
+ __entry->new_next_agino = next_agino;
+ ),
+ TP_printk("dev %d:%d agno 0x%x bucket %u agino 0x%x next_agino 0x%x -> 0x%x",
+ MAJOR(__entry->dev), MINOR(__entry->dev),
+ __entry->agno,
+ __entry->agino % XFS_AGI_UNLINKED_BUCKETS,
+ __entry->agino,
+ __entry->next_agino,
+ __entry->new_next_agino)
+);
+
+TRACE_EVENT(xrep_iunlink_relink_prev,
+ TP_PROTO(struct xfs_inode *ip, xfs_agino_t prev_agino),
+ TP_ARGS(ip, prev_agino),
+ TP_STRUCT__entry(
+ __field(dev_t, dev)
+ __field(xfs_agnumber_t, agno)
+ __field(xfs_agino_t, agino)
+ __field(xfs_agino_t, prev_agino)
+ __field(xfs_agino_t, new_prev_agino)
+ ),
+ TP_fast_assign(
+ __entry->dev = ip->i_mount->m_super->s_dev;
+ __entry->agno = XFS_INO_TO_AGNO(ip->i_mount, ip->i_ino);
+ __entry->agino = XFS_INO_TO_AGINO(ip->i_mount, ip->i_ino);
+ __entry->prev_agino = ip->i_prev_unlinked;
+ __entry->new_prev_agino = prev_agino;
+ ),
+ TP_printk("dev %d:%d agno 0x%x bucket %u agino 0x%x prev_agino 0x%x -> 0x%x",
+ MAJOR(__entry->dev), MINOR(__entry->dev),
+ __entry->agno,
+ __entry->agino % XFS_AGI_UNLINKED_BUCKETS,
+ __entry->agino,
+ __entry->prev_agino,
+ __entry->new_prev_agino)
+);
+
+TRACE_EVENT(xrep_iunlink_add_to_bucket,
+ TP_PROTO(struct xfs_perag *pag, unsigned int bucket,
+ xfs_agino_t agino, xfs_agino_t curr_head),
+ TP_ARGS(pag, bucket, agino, curr_head),
+ TP_STRUCT__entry(
+ __field(dev_t, dev)
+ __field(xfs_agnumber_t, agno)
+ __field(unsigned int, bucket)
+ __field(xfs_agino_t, agino)
+ __field(xfs_agino_t, next_agino)
+ ),
+ TP_fast_assign(
+ __entry->dev = pag->pag_mount->m_super->s_dev;
+ __entry->agno = pag->pag_agno;
+ __entry->bucket = bucket;
+ __entry->agino = agino;
+ __entry->next_agino = curr_head;
+ ),
+ TP_printk("dev %d:%d agno 0x%x bucket %u agino 0x%x next_agino 0x%x",
+ MAJOR(__entry->dev), MINOR(__entry->dev),
+ __entry->agno,
+ __entry->bucket,
+ __entry->agino,
+ __entry->next_agino)
+);
+
+TRACE_EVENT(xrep_iunlink_commit_bucket,
+ TP_PROTO(struct xfs_perag *pag, unsigned int bucket,
+ xfs_agino_t old_agino, xfs_agino_t agino),
+ TP_ARGS(pag, bucket, old_agino, agino),
+ TP_STRUCT__entry(
+ __field(dev_t, dev)
+ __field(xfs_agnumber_t, agno)
+ __field(unsigned int, bucket)
+ __field(xfs_agino_t, old_agino)
+ __field(xfs_agino_t, agino)
+ ),
+ TP_fast_assign(
+ __entry->dev = pag->pag_mount->m_super->s_dev;
+ __entry->agno = pag->pag_agno;
+ __entry->bucket = bucket;
+ __entry->old_agino = old_agino;
+ __entry->agino = agino;
+ ),
+ TP_printk("dev %d:%d agno 0x%x bucket %u agino 0x%x -> 0x%x",
+ MAJOR(__entry->dev), MINOR(__entry->dev),
+ __entry->agno,
+ __entry->bucket,
+ __entry->old_agino,
+ __entry->agino)
+);
+
+DEFINE_XCHK_DIRPATH_OUTCOME_EVENT(xrep_dirpath_set_outcome);
+DEFINE_XCHK_DIRTREE_EVENT(xrep_dirtree_delete_path);
+DEFINE_XCHK_DIRTREE_EVENT(xrep_dirtree_create_adoption);
+DEFINE_XCHK_DIRTREE_EVALUATE_EVENT(xrep_dirtree_decided_fate);
+
#endif /* IS_ENABLED(CONFIG_XFS_ONLINE_REPAIR) */
#endif /* _TRACE_XFS_SCRUB_TRACE_H */
diff --git a/fs/xfs/scrub/xfarray.c b/fs/xfs/scrub/xfarray.c
index 17c982a482..cdd13ed9c5 100644
--- a/fs/xfs/scrub/xfarray.c
+++ b/fs/xfs/scrub/xfarray.c
@@ -7,9 +7,9 @@
#include "xfs_fs.h"
#include "xfs_shared.h"
#include "xfs_format.h"
+#include "scrub/scrub.h"
#include "scrub/xfile.h"
#include "scrub/xfarray.h"
-#include "scrub/scrub.h"
#include "scrub/trace.h"
/*
@@ -486,6 +486,9 @@ xfarray_sortinfo_alloc(
xfarray_sortinfo_lo(si)[0] = 0;
xfarray_sortinfo_hi(si)[0] = array->nr - 1;
+ si->relax = INIT_XCHK_RELAX;
+ if (flags & XFARRAY_SORT_KILLABLE)
+ si->relax.interruptible = false;
trace_xfarray_sort(si, nr_bytes);
*infop = si;
@@ -503,10 +506,7 @@ xfarray_sort_terminated(
* few seconds so that we don't run afoul of the soft lockup watchdog
* or RCU stall detector.
*/
- cond_resched();
-
- if ((si->flags & XFARRAY_SORT_KILLABLE) &&
- fatal_signal_pending(current)) {
+ if (xchk_maybe_relax(&si->relax)) {
if (*error == 0)
*error = -EINTR;
return true;
@@ -822,12 +822,14 @@ xfarray_sort_scan(
/* Grab the first folio that backs this array element. */
if (!si->folio) {
+ struct folio *folio;
loff_t next_pos;
- si->folio = xfile_get_folio(si->array->xfile, idx_pos,
+ folio = xfile_get_folio(si->array->xfile, idx_pos,
si->array->obj_size, XFILE_ALLOC);
- if (IS_ERR(si->folio))
- return PTR_ERR(si->folio);
+ if (IS_ERR(folio))
+ return PTR_ERR(folio);
+ si->folio = folio;
si->first_folio_idx = xfarray_idx(si->array,
folio_pos(si->folio) + si->array->obj_size - 1);
@@ -1048,6 +1050,24 @@ xfarray_sort(
out_free:
trace_xfarray_sort_stats(si, error);
+ xfarray_sort_scan_done(si);
kvfree(si);
return error;
}
+
+/* How many bytes is this array consuming? */
+unsigned long long
+xfarray_bytes(
+ struct xfarray *array)
+{
+ return xfile_bytes(array->xfile);
+}
+
+/* Empty the entire array. */
+void
+xfarray_truncate(
+ struct xfarray *array)
+{
+ xfile_discard(array->xfile, 0, MAX_LFS_FILESIZE);
+ array->nr = 0;
+}
diff --git a/fs/xfs/scrub/xfarray.h b/fs/xfs/scrub/xfarray.h
index acb2f94c56..5eeeeed13a 100644
--- a/fs/xfs/scrub/xfarray.h
+++ b/fs/xfs/scrub/xfarray.h
@@ -8,6 +8,7 @@
/* xfile array index type, along with cursor initialization */
typedef uint64_t xfarray_idx_t;
+#define XFARRAY_NULLIDX ((__force xfarray_idx_t)-1ULL)
#define XFARRAY_CURSOR_INIT ((__force xfarray_idx_t)0)
/* Iterate each index of an xfile array. */
@@ -44,6 +45,8 @@ int xfarray_unset(struct xfarray *array, xfarray_idx_t idx);
int xfarray_store(struct xfarray *array, xfarray_idx_t idx, const void *ptr);
int xfarray_store_anywhere(struct xfarray *array, const void *ptr);
bool xfarray_element_is_null(struct xfarray *array, const void *ptr);
+void xfarray_truncate(struct xfarray *array);
+unsigned long long xfarray_bytes(struct xfarray *array);
/*
* Load an array element, but zero the buffer if there's no data because we
@@ -124,6 +127,9 @@ struct xfarray_sortinfo {
/* XFARRAY_SORT_* flags; see below. */
unsigned int flags;
+ /* next time we want to cond_resched() */
+ struct xchk_relax relax;
+
/* Cache a folio here for faster scanning for pivots */
struct folio *folio;
diff --git a/fs/xfs/scrub/xfblob.c b/fs/xfs/scrub/xfblob.c
new file mode 100644
index 0000000000..6ef2a9637f
--- /dev/null
+++ b/fs/xfs/scrub/xfblob.c
@@ -0,0 +1,168 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Copyright (c) 2021-2024 Oracle. All Rights Reserved.
+ * Author: Darrick J. Wong <djwong@kernel.org>
+ */
+#include "xfs.h"
+#include "xfs_fs.h"
+#include "xfs_shared.h"
+#include "xfs_format.h"
+#include "scrub/scrub.h"
+#include "scrub/xfile.h"
+#include "scrub/xfarray.h"
+#include "scrub/xfblob.h"
+
+/*
+ * XFS Blob Storage
+ * ================
+ * Stores and retrieves blobs using an xfile. Objects are appended to the file
+ * and the offset is returned as a magic cookie for retrieval.
+ */
+
+#define XB_KEY_MAGIC 0xABAADDAD
+struct xb_key {
+ uint32_t xb_magic; /* XB_KEY_MAGIC */
+ uint32_t xb_size; /* size of the blob, in bytes */
+ loff_t xb_offset; /* byte offset of this key */
+ /* blob comes after here */
+} __packed;
+
+/* Initialize a blob storage object. */
+int
+xfblob_create(
+ const char *description,
+ struct xfblob **blobp)
+{
+ struct xfblob *blob;
+ struct xfile *xfile;
+ int error;
+
+ error = xfile_create(description, 0, &xfile);
+ if (error)
+ return error;
+
+ blob = kmalloc(sizeof(struct xfblob), XCHK_GFP_FLAGS);
+ if (!blob) {
+ error = -ENOMEM;
+ goto out_xfile;
+ }
+
+ blob->xfile = xfile;
+ blob->last_offset = PAGE_SIZE;
+
+ *blobp = blob;
+ return 0;
+
+out_xfile:
+ xfile_destroy(xfile);
+ return error;
+}
+
+/* Destroy a blob storage object. */
+void
+xfblob_destroy(
+ struct xfblob *blob)
+{
+ xfile_destroy(blob->xfile);
+ kfree(blob);
+}
+
+/* Retrieve a blob. */
+int
+xfblob_load(
+ struct xfblob *blob,
+ xfblob_cookie cookie,
+ void *ptr,
+ uint32_t size)
+{
+ struct xb_key key;
+ int error;
+
+ error = xfile_load(blob->xfile, &key, sizeof(key), cookie);
+ if (error)
+ return error;
+
+ if (key.xb_magic != XB_KEY_MAGIC || key.xb_offset != cookie) {
+ ASSERT(0);
+ return -ENODATA;
+ }
+ if (size < key.xb_size) {
+ ASSERT(0);
+ return -EFBIG;
+ }
+
+ return xfile_load(blob->xfile, ptr, key.xb_size,
+ cookie + sizeof(key));
+}
+
+/* Store a blob. */
+int
+xfblob_store(
+ struct xfblob *blob,
+ xfblob_cookie *cookie,
+ const void *ptr,
+ uint32_t size)
+{
+ struct xb_key key = {
+ .xb_offset = blob->last_offset,
+ .xb_magic = XB_KEY_MAGIC,
+ .xb_size = size,
+ };
+ loff_t pos = blob->last_offset;
+ int error;
+
+ error = xfile_store(blob->xfile, &key, sizeof(key), pos);
+ if (error)
+ return error;
+
+ pos += sizeof(key);
+ error = xfile_store(blob->xfile, ptr, size, pos);
+ if (error)
+ goto out_err;
+
+ *cookie = blob->last_offset;
+ blob->last_offset += sizeof(key) + size;
+ return 0;
+out_err:
+ xfile_discard(blob->xfile, blob->last_offset, sizeof(key));
+ return error;
+}
+
+/* Free a blob. */
+int
+xfblob_free(
+ struct xfblob *blob,
+ xfblob_cookie cookie)
+{
+ struct xb_key key;
+ int error;
+
+ error = xfile_load(blob->xfile, &key, sizeof(key), cookie);
+ if (error)
+ return error;
+
+ if (key.xb_magic != XB_KEY_MAGIC || key.xb_offset != cookie) {
+ ASSERT(0);
+ return -ENODATA;
+ }
+
+ xfile_discard(blob->xfile, cookie, sizeof(key) + key.xb_size);
+ return 0;
+}
+
+/* How many bytes is this blob storage object consuming? */
+unsigned long long
+xfblob_bytes(
+ struct xfblob *blob)
+{
+ return xfile_bytes(blob->xfile);
+}
+
+/* Drop all the blobs. */
+void
+xfblob_truncate(
+ struct xfblob *blob)
+{
+ xfile_discard(blob->xfile, PAGE_SIZE, MAX_LFS_FILESIZE - PAGE_SIZE);
+ blob->last_offset = PAGE_SIZE;
+}
diff --git a/fs/xfs/scrub/xfblob.h b/fs/xfs/scrub/xfblob.h
new file mode 100644
index 0000000000..ae78322613
--- /dev/null
+++ b/fs/xfs/scrub/xfblob.h
@@ -0,0 +1,50 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * Copyright (c) 2021-2024 Oracle. All Rights Reserved.
+ * Author: Darrick J. Wong <djwong@kernel.org>
+ */
+#ifndef __XFS_SCRUB_XFBLOB_H__
+#define __XFS_SCRUB_XFBLOB_H__
+
+struct xfblob {
+ struct xfile *xfile;
+ loff_t last_offset;
+};
+
+typedef loff_t xfblob_cookie;
+
+int xfblob_create(const char *descr, struct xfblob **blobp);
+void xfblob_destroy(struct xfblob *blob);
+int xfblob_load(struct xfblob *blob, xfblob_cookie cookie, void *ptr,
+ uint32_t size);
+int xfblob_store(struct xfblob *blob, xfblob_cookie *cookie, const void *ptr,
+ uint32_t size);
+int xfblob_free(struct xfblob *blob, xfblob_cookie cookie);
+unsigned long long xfblob_bytes(struct xfblob *blob);
+void xfblob_truncate(struct xfblob *blob);
+
+static inline int
+xfblob_storename(
+ struct xfblob *blob,
+ xfblob_cookie *cookie,
+ const struct xfs_name *xname)
+{
+ return xfblob_store(blob, cookie, xname->name, xname->len);
+}
+
+static inline int
+xfblob_loadname(
+ struct xfblob *blob,
+ xfblob_cookie cookie,
+ struct xfs_name *xname,
+ uint32_t size)
+{
+ int ret = xfblob_load(blob, cookie, (void *)xname->name, size);
+ if (ret)
+ return ret;
+
+ xname->len = size;
+ return 0;
+}
+
+#endif /* __XFS_SCRUB_XFBLOB_H__ */
diff --git a/fs/xfs/scrub/xfile.c b/fs/xfs/scrub/xfile.c
index 8cdd863db5..d848222f80 100644
--- a/fs/xfs/scrub/xfile.c
+++ b/fs/xfs/scrub/xfile.c
@@ -10,9 +10,9 @@
#include "xfs_log_format.h"
#include "xfs_trans_resv.h"
#include "xfs_mount.h"
+#include "scrub/scrub.h"
#include "scrub/xfile.h"
#include "scrub/xfarray.h"
-#include "scrub/scrub.h"
#include "scrub/trace.h"
#include <linux/shmem_fs.h>
@@ -310,3 +310,15 @@ xfile_put_folio(
folio_unlock(folio);
folio_put(folio);
}
+
+/* Discard the page cache that's backing a range of the xfile. */
+void
+xfile_discard(
+ struct xfile *xf,
+ loff_t pos,
+ u64 count)
+{
+ trace_xfile_discard(xf, pos, count);
+
+ shmem_truncate_range(file_inode(xf->file), pos, pos + count - 1);
+}
diff --git a/fs/xfs/scrub/xfile.h b/fs/xfs/scrub/xfile.h
index 76d78dba7e..cc2cc1714c 100644
--- a/fs/xfs/scrub/xfile.h
+++ b/fs/xfs/scrub/xfile.h
@@ -17,6 +17,7 @@ int xfile_load(struct xfile *xf, void *buf, size_t count, loff_t pos);
int xfile_store(struct xfile *xf, const void *buf, size_t count,
loff_t pos);
+void xfile_discard(struct xfile *xf, loff_t pos, u64 count);
loff_t xfile_seek_data(struct xfile *xf, loff_t pos);
#define XFILE_MAX_FOLIO_SIZE (PAGE_SIZE << MAX_PAGECACHE_ORDER)
@@ -26,4 +27,9 @@ struct folio *xfile_get_folio(struct xfile *xf, loff_t offset, size_t len,
unsigned int flags);
void xfile_put_folio(struct xfile *xf, struct folio *folio);
+static inline unsigned long long xfile_bytes(struct xfile *xf)
+{
+ return file_inode(xf->file)->i_blocks << SECTOR_SHIFT;
+}
+
#endif /* __XFS_SCRUB_XFILE_H__ */
diff --git a/fs/xfs/scrub/xfs_scrub.h b/fs/xfs/scrub/xfs_scrub.h
index a39befa743..f17173b83e 100644
--- a/fs/xfs/scrub/xfs_scrub.h
+++ b/fs/xfs/scrub/xfs_scrub.h
@@ -7,9 +7,11 @@
#define __XFS_SCRUB_H__
#ifndef CONFIG_XFS_ONLINE_SCRUB
-# define xfs_scrub_metadata(file, sm) (-ENOTTY)
+# define xfs_ioc_scrub_metadata(f, a) (-ENOTTY)
+# define xfs_ioc_scrubv_metadata(f, a) (-ENOTTY)
#else
-int xfs_scrub_metadata(struct file *file, struct xfs_scrub_metadata *sm);
+int xfs_ioc_scrub_metadata(struct file *file, void __user *arg);
+int xfs_ioc_scrubv_metadata(struct file *file, void __user *arg);
#endif /* CONFIG_XFS_ONLINE_SCRUB */
#endif /* __XFS_SCRUB_H__ */