summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorDarrick J. Wong <djwong@kernel.org>2021-09-01 10:45:53 -0700
committerDarrick J. Wong <djwong@kernel.org>2021-09-17 18:54:52 -0700
commit98618b35d753c64477255a188350520959926dcc (patch)
tree38716c3d6eb1fa47a45e25ca8fc8b47a488df707
parent6040652832b38a0b1116af890578a38648116812 (diff)
xfs: zap broken inode forks
Determine if inode fork damage is responsible for the inode being unable to pass the ifork verifiers in xfs_iget and zap the fork contents if this is true. Once this is done the fork will be empty but we'll be able to construct an in-core inode, and a subsequent call to the inode fork repair ioctl will search the rmapbt to rebuild the records that were in the fork. Signed-off-by: Darrick J. Wong <djwong@kernel.org>
-rw-r--r--fs/xfs/libxfs/xfs_attr_leaf.c32
-rw-r--r--fs/xfs/libxfs/xfs_attr_leaf.h2
-rw-r--r--fs/xfs/libxfs/xfs_bmap.c22
-rw-r--r--fs/xfs/libxfs/xfs_bmap.h2
-rw-r--r--fs/xfs/scrub/inode_repair.c608
-rw-r--r--fs/xfs/scrub/trace.h42
6 files changed, 687 insertions, 21 deletions
diff --git a/fs/xfs/libxfs/xfs_attr_leaf.c b/fs/xfs/libxfs/xfs_attr_leaf.c
index e1d11e314228..ece88f1b3605 100644
--- a/fs/xfs/libxfs/xfs_attr_leaf.c
+++ b/fs/xfs/libxfs/xfs_attr_leaf.c
@@ -1009,23 +1009,16 @@ xfs_attr_shortform_allfit(
return xfs_attr_shortform_bytesfit(dp, bytes);
}
-/* Verify the consistency of an inline attribute fork. */
+/* Verify the consistency of a raw inline attribute fork. */
xfs_failaddr_t
-xfs_attr_shortform_verify(
- struct xfs_inode *ip)
+xfs_attr_shortform_verify_struct(
+ struct xfs_attr_shortform *sfp,
+ size_t size)
{
- struct xfs_attr_shortform *sfp;
struct xfs_attr_sf_entry *sfep;
struct xfs_attr_sf_entry *next_sfep;
char *endp;
- struct xfs_ifork *ifp;
int i;
- int64_t size;
-
- ASSERT(ip->i_afp->if_format == XFS_DINODE_FMT_LOCAL);
- ifp = XFS_IFORK_PTR(ip, XFS_ATTR_FORK);
- sfp = (struct xfs_attr_shortform *)ifp->if_u1.if_data;
- size = ifp->if_bytes;
/*
* Give up if the attribute is way too short.
@@ -1085,6 +1078,23 @@ xfs_attr_shortform_verify(
return NULL;
}
+/* Verify the consistency of an inline attribute fork. */
+xfs_failaddr_t
+xfs_attr_shortform_verify(
+ struct xfs_inode *ip)
+{
+ struct xfs_attr_shortform *sfp;
+ struct xfs_ifork *ifp;
+ int64_t size;
+
+ ASSERT(ip->i_afp->if_format == XFS_DINODE_FMT_LOCAL);
+ ifp = XFS_IFORK_PTR(ip, XFS_ATTR_FORK);
+ sfp = (struct xfs_attr_shortform *)ifp->if_u1.if_data;
+ size = ifp->if_bytes;
+
+ return xfs_attr_shortform_verify_struct(sfp, size);
+}
+
/*
* Convert a leaf attribute list to shortform attribute list
*/
diff --git a/fs/xfs/libxfs/xfs_attr_leaf.h b/fs/xfs/libxfs/xfs_attr_leaf.h
index efa757f1e912..f32a635b1e1a 100644
--- a/fs/xfs/libxfs/xfs_attr_leaf.h
+++ b/fs/xfs/libxfs/xfs_attr_leaf.h
@@ -57,6 +57,8 @@ int xfs_attr_sf_findname(struct xfs_da_args *args,
unsigned int *basep);
int xfs_attr_shortform_allfit(struct xfs_buf *bp, struct xfs_inode *dp);
int xfs_attr_shortform_bytesfit(struct xfs_inode *dp, int bytes);
+xfs_failaddr_t xfs_attr_shortform_verify_struct(struct xfs_attr_shortform *sfp,
+ size_t size);
xfs_failaddr_t xfs_attr_shortform_verify(struct xfs_inode *ip);
void xfs_attr_fork_remove(struct xfs_inode *ip, struct xfs_trans *tp);
diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c
index 447aa3829ed8..3bc784bc83f7 100644
--- a/fs/xfs/libxfs/xfs_bmap.c
+++ b/fs/xfs/libxfs/xfs_bmap.c
@@ -6255,19 +6255,18 @@ xfs_bmap_finish_one(
return error;
}
-/* Check that an inode's extent does not have invalid flags or bad ranges. */
+/* Check that an extent does not have invalid flags or bad ranges. */
xfs_failaddr_t
-xfs_bmap_validate_extent(
- struct xfs_inode *ip,
+xfs_bmap_validate_extent_raw(
+ struct xfs_mount *mp,
+ bool rtfile,
int whichfork,
struct xfs_bmbt_irec *irec)
{
- struct xfs_mount *mp = ip->i_mount;
-
if (!xfs_verify_fileext(mp, irec->br_startoff, irec->br_blockcount))
return __this_address;
- if (XFS_IS_REALTIME_INODE(ip) && whichfork == XFS_DATA_FORK) {
+ if (rtfile && whichfork == XFS_DATA_FORK) {
if (!xfs_verify_rtext(mp, irec->br_startblock,
irec->br_blockcount))
return __this_address;
@@ -6280,3 +6279,14 @@ xfs_bmap_validate_extent(
return __this_address;
return NULL;
}
+
+/* Check that an inode's extent does not have invalid flags or bad ranges. */
+xfs_failaddr_t
+xfs_bmap_validate_extent(
+ struct xfs_inode *ip,
+ int whichfork,
+ struct xfs_bmbt_irec *irec)
+{
+ return xfs_bmap_validate_extent_raw(ip->i_mount,
+ XFS_IS_REALTIME_INODE(ip), whichfork, irec);
+}
diff --git a/fs/xfs/libxfs/xfs_bmap.h b/fs/xfs/libxfs/xfs_bmap.h
index 67641f669918..e8b0ef0aa17d 100644
--- a/fs/xfs/libxfs/xfs_bmap.h
+++ b/fs/xfs/libxfs/xfs_bmap.h
@@ -283,6 +283,8 @@ static inline int xfs_bmap_fork_to_state(int whichfork)
}
}
+xfs_failaddr_t xfs_bmap_validate_extent_raw(struct xfs_mount *mp, bool rtfile,
+ int whichfork, struct xfs_bmbt_irec *irec);
xfs_failaddr_t xfs_bmap_validate_extent(struct xfs_inode *ip, int whichfork,
struct xfs_bmbt_irec *irec);
diff --git a/fs/xfs/scrub/inode_repair.c b/fs/xfs/scrub/inode_repair.c
index 080767ef4a48..63f5c68b8444 100644
--- a/fs/xfs/scrub/inode_repair.c
+++ b/fs/xfs/scrub/inode_repair.c
@@ -22,12 +22,18 @@
#include "xfs_ialloc.h"
#include "xfs_da_format.h"
#include "xfs_reflink.h"
+#include "xfs_alloc.h"
#include "xfs_rmap.h"
+#include "xfs_rmap_btree.h"
#include "xfs_bmap.h"
+#include "xfs_bmap_btree.h"
#include "xfs_bmap_util.h"
#include "xfs_dir2.h"
#include "xfs_dir2_priv.h"
#include "xfs_quota_defs.h"
+#include "xfs_attr_leaf.h"
+#include "xfs_log_priv.h"
+#include "xfs_ag.h"
#include "scrub/xfs_scrub.h"
#include "scrub/scrub.h"
#include "scrub/common.h"
@@ -47,6 +53,33 @@
* fix things on live incore inodes.
*/
+/* Blocks and extents associated with an inode, according to rmap records. */
+struct xrep_dinode_stats {
+ struct xfs_scrub *sc;
+
+ /* Blocks in use on the data device by data extents or bmbt blocks. */
+ xfs_rfsblock_t data_blocks;
+
+ /* Blocks in use on the rt device. */
+ xfs_rfsblock_t rt_blocks;
+
+ /* Blocks in use by the attr fork. */
+ xfs_rfsblock_t attr_blocks;
+
+ /* Number of data device extents for the data fork. */
+ xfs_extnum_t data_extents;
+
+ /*
+ * Number of realtime device extents for the data fork. If
+ * data_extents and rt_extents indicate that the data fork has extents
+ * on both devices, we'll just back away slowly.
+ */
+ xfs_extnum_t rt_extents;
+
+ /* Number of (data device) extents for the attr fork. */
+ xfs_aextnum_t attr_extents;
+};
+
/* Make sure this buffer can pass the inode buffer verifier. */
STATIC void
xrep_dinode_buf(
@@ -141,7 +174,8 @@ xrep_dinode_mode(
STATIC void
xrep_dinode_flags(
struct xfs_scrub *sc,
- struct xfs_dinode *dip)
+ struct xfs_dinode *dip,
+ bool isrt)
{
struct xfs_mount *mp = sc->mp;
uint64_t flags2;
@@ -154,6 +188,11 @@ xrep_dinode_flags(
flags = be16_to_cpu(dip->di_flags);
flags2 = be64_to_cpu(dip->di_flags2);
+ if (isrt)
+ flags |= XFS_DIFLAG_REALTIME;
+ else
+ flags &= ~XFS_DIFLAG_REALTIME;
+
if (xfs_has_reflink(mp) && S_ISREG(mode))
flags2 |= XFS_DIFLAG2_REFLINK;
else
@@ -302,20 +341,580 @@ xrep_dinode_extsize_hints(
}
}
+/* Count extents and blocks for an inode given an rmap. */
+STATIC int
+xrep_dinode_walk_rmap(
+ struct xfs_btree_cur *cur,
+ const struct xfs_rmap_irec *rec,
+ void *priv)
+{
+ struct xrep_dinode_stats *dis = priv;
+ int error = 0;
+
+ if (xchk_should_terminate(dis->sc, &error))
+ return error;
+
+ /* We only care about this inode. */
+ if (rec->rm_owner != dis->sc->sm->sm_ino)
+ return 0;
+
+ if (rec->rm_flags & XFS_RMAP_ATTR_FORK) {
+ dis->attr_blocks += rec->rm_blockcount;
+ if (!(rec->rm_flags & XFS_RMAP_BMBT_BLOCK))
+ dis->attr_extents++;
+
+ return 0;
+ }
+
+ dis->data_blocks += rec->rm_blockcount;
+ if (!(rec->rm_flags & XFS_RMAP_BMBT_BLOCK))
+ dis->data_extents++;
+
+ return 0;
+}
+
+/* Count extents and blocks for an inode from all AG rmap data. */
+STATIC int
+xrep_dinode_count_ag_rmaps(
+ struct xrep_dinode_stats *dis,
+ struct xfs_perag *pag)
+{
+ struct xfs_btree_cur *cur;
+ struct xfs_buf *agf;
+ int error;
+
+ error = xfs_alloc_read_agf(dis->sc->mp, dis->sc->tp, pag->pag_agno, 0,
+ &agf);
+ if (error)
+ return error;
+
+ cur = xfs_rmapbt_init_cursor(dis->sc->mp, dis->sc->tp, agf, pag);
+ error = xfs_rmap_query_all(cur, xrep_dinode_walk_rmap, dis);
+ xfs_btree_del_cursor(cur, error);
+ xfs_trans_brelse(dis->sc->tp, agf);
+ return error;
+}
+
+/* Count extents and blocks for a given inode from all rmap data. */
+STATIC int
+xrep_dinode_count_rmaps(
+ struct xrep_dinode_stats *dis)
+{
+ struct xfs_perag *pag;
+ xfs_agnumber_t agno;
+ int error;
+
+ if (!xfs_has_rmapbt(dis->sc->mp) || xfs_has_realtime(dis->sc->mp))
+ return -EOPNOTSUPP;
+
+ for_each_perag(dis->sc->mp, agno, pag) {
+ error = xrep_dinode_count_ag_rmaps(dis, pag);
+ if (error) {
+ xfs_perag_put(pag);
+ return error;
+ }
+ }
+
+ /* Can't have extents on both the rt and the data device. */
+ if (dis->data_extents && dis->rt_extents)
+ return -EFSCORRUPTED;
+
+ trace_xrep_dinode_count_rmaps(dis->sc,
+ dis->data_blocks, dis->rt_blocks, dis->attr_blocks,
+ dis->data_extents, dis->rt_extents, dis->attr_extents);
+ return 0;
+}
+
+/* Return true if this extents-format ifork looks like garbage. */
+STATIC bool
+xrep_dinode_bad_extents_fork(
+ struct xfs_scrub *sc,
+ struct xfs_dinode *dip,
+ int dfork_size,
+ int whichfork)
+{
+ struct xfs_bmbt_irec new;
+ struct xfs_bmbt_rec *dp;
+ bool isrt;
+ int i;
+ int nex;
+ int fork_size;
+
+ nex = XFS_DFORK_NEXTENTS(dip, whichfork);
+ fork_size = nex * sizeof(struct xfs_bmbt_rec);
+ if (fork_size < 0 || fork_size > dfork_size)
+ return true;
+ if (whichfork == XFS_ATTR_FORK && nex > ((uint16_t)-1U))
+ return true;
+ dp = XFS_DFORK_PTR(dip, whichfork);
+
+ isrt = dip->di_flags & cpu_to_be16(XFS_DIFLAG_REALTIME);
+ for (i = 0; i < nex; i++, dp++) {
+ xfs_failaddr_t fa;
+
+ xfs_bmbt_disk_get_all(dp, &new);
+ fa = xfs_bmap_validate_extent_raw(sc->mp, isrt, whichfork,
+ &new);
+ if (fa)
+ return true;
+ }
+
+ return false;
+}
+
+/* Return true if this btree-format ifork looks like garbage. */
+STATIC bool
+xrep_dinode_bad_btree_fork(
+ struct xfs_scrub *sc,
+ struct xfs_dinode *dip,
+ int dfork_size,
+ int whichfork)
+{
+ struct xfs_bmdr_block *dfp;
+ int nrecs;
+ int level;
+
+ if (XFS_DFORK_NEXTENTS(dip, whichfork) <=
+ dfork_size / sizeof(struct xfs_bmbt_rec))
+ return true;
+
+ if (dfork_size < sizeof(struct xfs_bmdr_block))
+ return true;
+
+ dfp = XFS_DFORK_PTR(dip, whichfork);
+ nrecs = be16_to_cpu(dfp->bb_numrecs);
+ level = be16_to_cpu(dfp->bb_level);
+
+ if (nrecs == 0 || XFS_BMDR_SPACE_CALC(nrecs) > dfork_size)
+ return true;
+ if (level == 0 || level >= XFS_BM_MAXLEVELS(sc->mp, whichfork))
+ return true;
+ return false;
+}
+
+/*
+ * Check the data fork for things that will fail the ifork verifiers or the
+ * ifork formatters.
+ */
+STATIC bool
+xrep_dinode_check_dfork(
+ struct xfs_scrub *sc,
+ struct xfs_dinode *dip,
+ uint16_t mode)
+{
+ uint64_t size;
+ unsigned int fmt;
+ int dfork_size;
+
+ fmt = XFS_DFORK_FORMAT(dip, XFS_DATA_FORK);
+ size = be64_to_cpu(dip->di_size);
+ switch (mode & S_IFMT) {
+ case S_IFIFO:
+ case S_IFCHR:
+ case S_IFBLK:
+ case S_IFSOCK:
+ if (fmt != XFS_DINODE_FMT_DEV)
+ return true;
+ break;
+ case S_IFREG:
+ if (fmt == XFS_DINODE_FMT_LOCAL)
+ return true;
+ fallthrough;
+ case S_IFLNK:
+ case S_IFDIR:
+ switch (fmt) {
+ case XFS_DINODE_FMT_LOCAL:
+ case XFS_DINODE_FMT_EXTENTS:
+ case XFS_DINODE_FMT_BTREE:
+ break;
+ default:
+ return true;
+ }
+ break;
+ default:
+ return true;
+ }
+ dfork_size = XFS_DFORK_SIZE(dip, sc->mp, XFS_DATA_FORK);
+ switch (fmt) {
+ case XFS_DINODE_FMT_DEV:
+ break;
+ case XFS_DINODE_FMT_LOCAL:
+ if (size > dfork_size)
+ return true;
+ break;
+ case XFS_DINODE_FMT_EXTENTS:
+ if (xrep_dinode_bad_extents_fork(sc, dip, dfork_size,
+ XFS_DATA_FORK))
+ return true;
+ break;
+ case XFS_DINODE_FMT_BTREE:
+ if (xrep_dinode_bad_btree_fork(sc, dip, dfork_size,
+ XFS_DATA_FORK))
+ return true;
+ break;
+ default:
+ return true;
+ }
+
+ return false;
+}
+
+/* Reset the data fork to something sane. */
+STATIC void
+xrep_dinode_zap_dfork(
+ struct xfs_scrub *sc,
+ struct xfs_dinode *dip,
+ uint16_t mode,
+ struct xrep_dinode_stats *dis)
+{
+ trace_xrep_dinode_zap_dfork(sc, dip);
+
+ dip->di_nextents = 0;
+
+ /* Special files always get reset to DEV */
+ switch (mode & S_IFMT) {
+ case S_IFIFO:
+ case S_IFCHR:
+ case S_IFBLK:
+ case S_IFSOCK:
+ dip->di_format = XFS_DINODE_FMT_DEV;
+ dip->di_size = 0;
+ return;
+ }
+
+ /*
+ * If we have data extents, reset to an empty map and hope the user
+ * will run the bmapbtd checker next.
+ */
+ if (dis->data_extents || dis->rt_extents || S_ISREG(mode)) {
+ dip->di_format = XFS_DINODE_FMT_EXTENTS;
+ return;
+ }
+
+ /* Otherwise, reset the local format to the minimum. */
+ switch (mode & S_IFMT) {
+ case S_IFLNK:
+ xrep_dinode_zap_symlink(sc, dip);
+ break;
+ case S_IFDIR:
+ xrep_dinode_zap_dir(sc, dip);
+ break;
+ }
+}
+
+/*
+ * Check the attr fork for things that will fail the ifork verifiers or the
+ * ifork formatters.
+ */
+STATIC bool
+xrep_dinode_check_afork(
+ struct xfs_scrub *sc,
+ struct xfs_dinode *dip)
+{
+ struct xfs_attr_shortform *sfp;
+ int size;
+
+ if (XFS_DFORK_BOFF(dip) == 0)
+ return dip->di_aformat != XFS_DINODE_FMT_EXTENTS ||
+ dip->di_anextents != 0;
+
+ size = XFS_DFORK_SIZE(dip, sc->mp, XFS_ATTR_FORK);
+ switch (XFS_DFORK_FORMAT(dip, XFS_ATTR_FORK)) {
+ case XFS_DINODE_FMT_LOCAL:
+ sfp = XFS_DFORK_PTR(dip, XFS_ATTR_FORK);
+ return xfs_attr_shortform_verify_struct(sfp, size) != NULL;
+ case XFS_DINODE_FMT_EXTENTS:
+ if (xrep_dinode_bad_extents_fork(sc, dip, size, XFS_ATTR_FORK))
+ return true;
+ break;
+ case XFS_DINODE_FMT_BTREE:
+ if (xrep_dinode_bad_btree_fork(sc, dip, size, XFS_ATTR_FORK))
+ return true;
+ break;
+ default:
+ return true;
+ }
+
+ return false;
+}
+
+/*
+ * Reset the attr fork to empty. Since the attr fork could have contained
+ * ACLs, make the file readable only by root.
+ */
+STATIC void
+xrep_dinode_zap_afork(
+ struct xfs_scrub *sc,
+ struct xfs_dinode *dip,
+ uint16_t mode,
+ struct xrep_dinode_stats *dis)
+{
+ trace_xrep_dinode_zap_afork(sc, dip);
+
+ dip->di_aformat = XFS_DINODE_FMT_EXTENTS;
+ dip->di_anextents = 0;
+
+ dip->di_forkoff = 0;
+ dip->di_mode = cpu_to_be16(mode & ~0777);
+ dip->di_uid = 0;
+ dip->di_gid = 0;
+}
+
+/* Make sure the fork offset is a sensible value. */
+STATIC void
+xrep_dinode_ensure_forkoff(
+ struct xfs_scrub *sc,
+ struct xfs_dinode *dip,
+ uint16_t mode,
+ struct xrep_dinode_stats *dis)
+{
+ struct xfs_bmdr_block *bmdr;
+ size_t bmdr_minsz = XFS_BMDR_SPACE_CALC(1);
+ unsigned int lit_sz = XFS_LITINO(sc->mp);
+ unsigned int afork_min, dfork_min;
+
+ trace_xrep_dinode_ensure_forkoff(sc, dip);
+
+ /*
+ * Before calling this function, xrep_dinode_core ensured that both
+ * forks actually fit inside their respective literal areas. If this
+ * was not the case, the fork was reset to FMT_EXTENTS with zero
+ * records. If the rmapbt scan found attr or data fork blocks, this
+ * will be noted in the dinode_stats, and we must leave enough room
+ * for the bmap repair code to reconstruct the mapping structure.
+ *
+ * First, compute the minimum space required for the attr fork.
+ */
+ switch (dip->di_aformat) {
+ case XFS_DINODE_FMT_LOCAL:
+ /*
+ * If we still have a shortform xattr structure at all, that
+ * means the attr fork area was exactly large enough to fit
+ * the sf structure.
+ */
+ afork_min = XFS_DFORK_SIZE(dip, sc->mp, XFS_ATTR_FORK);
+ break;
+ case XFS_DINODE_FMT_EXTENTS:
+ if (dip->di_anextents) {
+ /*
+ * We must maintain sufficient space to hold the entire
+ * extent map array in the data fork. Note that we
+ * previously zapped the fork if it had no chance of
+ * fitting in the inode.
+ */
+ afork_min = sizeof(struct xfs_bmbt_rec) *
+ be16_to_cpu(dip->di_anextents);
+ } else if (dis->attr_extents > 0) {
+ /*
+ * The attr fork thinks it has zero extents, but we
+ * found some xattr extents. We need to leave enough
+ * empty space here so that the incore attr fork will
+ * get created (and hence trigger the attr fork bmap
+ * repairer).
+ */
+ afork_min = bmdr_minsz;
+ } else {
+ /* No extents on disk or found in rmapbt. */
+ afork_min = 0;
+ }
+ break;
+ case XFS_DINODE_FMT_BTREE:
+ /* Must have space for btree header and key/pointers. */
+ bmdr = XFS_DFORK_PTR(dip, XFS_ATTR_FORK);
+ afork_min = XFS_BMAP_BROOT_SPACE(sc->mp, bmdr);
+ break;
+ default:
+ /* We should never see any other formats. */
+ afork_min = 0;
+ break;
+ }
+
+ /* Compute the minimum space required for the data fork. */
+ switch (dip->di_format) {
+ case XFS_DINODE_FMT_DEV:
+ dfork_min = sizeof(__be32);
+ break;
+ case XFS_DINODE_FMT_UUID:
+ dfork_min = sizeof(uuid_t);
+ break;
+ case XFS_DINODE_FMT_LOCAL:
+ /*
+ * If we still have a shortform data fork at all, that means
+ * the data fork area was large enough to fit whatever was in
+ * there.
+ */
+ dfork_min = be64_to_cpu(dip->di_size);
+ break;
+ case XFS_DINODE_FMT_EXTENTS:
+ if (dip->di_nextents) {
+ /*
+ * We must maintain sufficient space to hold the entire
+ * extent map array in the data fork. Note that we
+ * previously zapped the fork if it had no chance of
+ * fitting in the inode.
+ */
+ dfork_min = sizeof(struct xfs_bmbt_rec) *
+ be32_to_cpu(dip->di_nextents);
+ } else if (dis->data_extents > 0 || dis->rt_extents > 0) {
+ /*
+ * The data fork thinks it has zero extents, but we
+ * found some data extents. We need to leave enough
+ * empty space here so that the the data fork bmap
+ * repair will recover the mappings.
+ */
+ dfork_min = bmdr_minsz;
+ } else {
+ /* No extents on disk or found in rmapbt. */
+ dfork_min = 0;
+ }
+ break;
+ case XFS_DINODE_FMT_BTREE:
+ /* Must have space for btree header and key/pointers. */
+ bmdr = XFS_DFORK_PTR(dip, XFS_DATA_FORK);
+ dfork_min = XFS_BMAP_BROOT_SPACE(sc->mp, bmdr);
+ break;
+ default:
+ dfork_min = 0;
+ break;
+ }
+
+ /*
+ * Round all values up to the nearest 8 bytes, because that is the
+ * precision of di_forkoff.
+ */
+ afork_min = roundup(afork_min, 8);
+ dfork_min = roundup(dfork_min, 8);
+ bmdr_minsz = roundup(bmdr_minsz, 8);
+
+ ASSERT(dfork_min <= lit_sz);
+ ASSERT(afork_min <= lit_sz);
+
+ /*
+ * If the data fork was zapped and we don't have enough space for the
+ * recovery fork, move the attr fork up.
+ */
+ if (dip->di_format == XFS_DINODE_FMT_EXTENTS &&
+ dip->di_nextents == 0 &&
+ (dis->data_extents > 0 || dis->rt_extents > 0) &&
+ bmdr_minsz > XFS_DFORK_DSIZE(dip, sc->mp)) {
+ if (bmdr_minsz + afork_min > lit_sz) {
+ /*
+ * The attr for and the stub fork we need to recover
+ * the data fork won't both fit. Zap the attr fork.
+ */
+ xrep_dinode_zap_afork(sc, dip, mode, dis);
+ afork_min = bmdr_minsz;
+ } else {
+ void *before, *after;
+
+ /* Otherwise, just slide the attr fork up. */
+ before = XFS_DFORK_APTR(dip);
+ dip->di_forkoff = bmdr_minsz >> 3;
+ after = XFS_DFORK_APTR(dip);
+ memmove(after, before, XFS_DFORK_ASIZE(dip, sc->mp));
+ }
+ }
+
+ /*
+ * If the attr fork was zapped and we don't have enough space for the
+ * recovery fork, move the attr fork down.
+ */
+ if (dip->di_aformat == XFS_DINODE_FMT_EXTENTS &&
+ dip->di_anextents == 0 &&
+ dis->attr_extents > 0 &&
+ bmdr_minsz > XFS_DFORK_ASIZE(dip, sc->mp)) {
+ if (dip->di_format == XFS_DINODE_FMT_BTREE) {
+ /*
+ * If the data fork is in btree format then we can't
+ * adjust forkoff because that runs the risk of
+ * violating the extents/btree format transition rules.
+ */
+ } else if (bmdr_minsz + dfork_min > lit_sz) {
+ /*
+ * If we can't move the attr fork, too bad, we lose the
+ * attr fork and leak its blocks.
+ */
+ xrep_dinode_zap_afork(sc, dip, mode, dis);
+ } else {
+ /*
+ * Otherwise, just slide the attr fork down. The attr
+ * fork is empty, so we don't have any old contents to
+ * move here.
+ */
+ dip->di_forkoff = (lit_sz - bmdr_minsz) >> 3;
+ }
+ }
+}
+
+/*
+ * Zap the data/attr forks if we spot anything that isn't going to pass the
+ * ifork verifiers or the ifork formatters, because we need to get the inode
+ * into good enough shape that the higher level repair functions can run.
+ */
+STATIC void
+xrep_dinode_zap_forks(
+ struct xfs_scrub *sc,
+ struct xfs_dinode *dip,
+ struct xrep_dinode_stats *dis)
+{
+ uint16_t mode;
+ bool zap_datafork = false;
+ bool zap_attrfork = false;
+
+ trace_xrep_dinode_zap_forks(sc, dip);
+
+ mode = be16_to_cpu(dip->di_mode);
+
+ /* Inode counters don't make sense? */
+ if (be32_to_cpu(dip->di_nextents) > be64_to_cpu(dip->di_nblocks))
+ zap_datafork = true;
+ if (be16_to_cpu(dip->di_anextents) > be64_to_cpu(dip->di_nblocks))
+ zap_attrfork = true;
+ if (be32_to_cpu(dip->di_nextents) + be16_to_cpu(dip->di_anextents) >
+ be64_to_cpu(dip->di_nblocks))
+ zap_datafork = zap_attrfork = true;
+
+ if (!zap_datafork)
+ zap_datafork = xrep_dinode_check_dfork(sc, dip, mode);
+ if (!zap_attrfork)
+ zap_attrfork = xrep_dinode_check_afork(sc, dip);
+
+ /* Zap whatever's bad. */
+ if (zap_attrfork)
+ xrep_dinode_zap_afork(sc, dip, mode, dis);
+ if (zap_datafork)
+ xrep_dinode_zap_dfork(sc, dip, mode, dis);
+ xrep_dinode_ensure_forkoff(sc, dip, mode, dis);
+ dip->di_nblocks = 0;
+ if (!zap_attrfork)
+ be64_add_cpu(&dip->di_nblocks, dis->attr_blocks);
+ if (!zap_datafork) {
+ be64_add_cpu(&dip->di_nblocks, dis->data_blocks);
+ be64_add_cpu(&dip->di_nblocks, dis->rt_blocks);
+ }
+}
+
/* Inode didn't pass verifiers, so fix the raw buffer and retry iget. */
STATIC int
xrep_dinode_core(
struct xfs_scrub *sc)
{
+ struct xrep_dinode_stats dis = {
+ .sc = sc,
+ };
struct xfs_imap imap;
struct xfs_buf *bp;
struct xfs_dinode *dip;
- xfs_ino_t ino;
+ xfs_ino_t ino = sc->sm->sm_ino;
bool inuse;
int error;
+ /* Figure out what this inode had mapped in both forks. */
+ error = xrep_dinode_count_rmaps(&dis);
+ if (error)
+ return error;
+
/* Map & read inode. */
- ino = sc->sm->sm_ino;
error = xfs_imap(sc->mp, sc->tp, ino, &imap, XFS_IGET_UNTRUSTED);
if (error)
return error;
@@ -340,9 +939,10 @@ xrep_dinode_core(
dip = xfs_buf_offset(bp, imap.im_boffset);
xrep_dinode_header(sc, dip);
xrep_dinode_mode(sc, dip);
- xrep_dinode_flags(sc, dip);
+ xrep_dinode_flags(sc, dip, dis.rt_extents > 0);
xrep_dinode_size(sc, dip);
xrep_dinode_extsize_hints(sc, dip);
+ xrep_dinode_zap_forks(sc, dip, &dis);
/* Write out the inode... */
trace_xrep_dinode_fixed(sc, dip);
diff --git a/fs/xfs/scrub/trace.h b/fs/xfs/scrub/trace.h
index 6fbb852990f0..86051920ac49 100644
--- a/fs/xfs/scrub/trace.h
+++ b/fs/xfs/scrub/trace.h
@@ -1180,6 +1180,10 @@ DEFINE_REPAIR_DINODE_EVENT(xrep_dinode_extsize_hints);
DEFINE_REPAIR_DINODE_EVENT(xrep_dinode_zap_symlink);
DEFINE_REPAIR_DINODE_EVENT(xrep_dinode_zap_dir);
DEFINE_REPAIR_DINODE_EVENT(xrep_dinode_fixed);
+DEFINE_REPAIR_DINODE_EVENT(xrep_dinode_zap_forks);
+DEFINE_REPAIR_DINODE_EVENT(xrep_dinode_zap_dfork);
+DEFINE_REPAIR_DINODE_EVENT(xrep_dinode_zap_afork);
+DEFINE_REPAIR_DINODE_EVENT(xrep_dinode_ensure_forkoff);
DECLARE_EVENT_CLASS(xrep_inode_class,
TP_PROTO(struct xfs_scrub *sc),
@@ -1239,6 +1243,44 @@ DEFINE_REPAIR_INODE_EVENT(xrep_inode_sfdir_size);
DEFINE_REPAIR_INODE_EVENT(xrep_inode_size);
DEFINE_REPAIR_INODE_EVENT(xrep_inode_fixed);
+TRACE_EVENT(xrep_dinode_count_rmaps,
+ TP_PROTO(struct xfs_scrub *sc, xfs_rfsblock_t data_blocks,
+ xfs_rfsblock_t rt_blocks, xfs_rfsblock_t attr_blocks,
+ xfs_extnum_t data_extents, xfs_extnum_t rt_extents,
+ xfs_aextnum_t attr_extents),
+ TP_ARGS(sc, data_blocks, rt_blocks, attr_blocks, data_extents,
+ rt_extents, attr_extents),
+ TP_STRUCT__entry(
+ __field(dev_t, dev)
+ __field(xfs_ino_t, ino)
+ __field(xfs_rfsblock_t, data_blocks)
+ __field(xfs_rfsblock_t, rt_blocks)
+ __field(xfs_rfsblock_t, attr_blocks)
+ __field(xfs_extnum_t, data_extents)
+ __field(xfs_extnum_t, rt_extents)
+ __field(xfs_aextnum_t, attr_extents)
+ ),
+ TP_fast_assign(
+ __entry->dev = sc->mp->m_super->s_dev;
+ __entry->ino = sc->sm->sm_ino;
+ __entry->data_blocks = data_blocks;
+ __entry->rt_blocks = rt_blocks;
+ __entry->attr_blocks = attr_blocks;
+ __entry->data_extents = data_extents;
+ __entry->rt_extents = rt_extents;
+ __entry->attr_extents = attr_extents;
+ ),
+ TP_printk("dev %d:%d ino 0x%llx dblocks 0x%llx rtblocks 0x%llx ablocks 0x%llx dextents %u rtextents %u aextents %u",
+ MAJOR(__entry->dev), MINOR(__entry->dev),
+ __entry->ino,
+ __entry->data_blocks,
+ __entry->rt_blocks,
+ __entry->attr_blocks,
+ __entry->data_extents,
+ __entry->rt_extents,
+ __entry->attr_extents)
+);
+
#endif /* IS_ENABLED(CONFIG_XFS_ONLINE_REPAIR) */
#endif /* _TRACE_XFS_SCRUB_TRACE_H */