aboutsummaryrefslogtreecommitdiff
diff options
context:
space:
mode:
-rw-r--r--fs/xfs/Makefile1
-rw-r--r--fs/xfs/libxfs/xfs_attr_leaf.c13
-rw-r--r--fs/xfs/libxfs/xfs_attr_leaf.h3
-rw-r--r--fs/xfs/libxfs/xfs_bmap.c22
-rw-r--r--fs/xfs/libxfs/xfs_bmap.h2
-rw-r--r--fs/xfs/libxfs/xfs_dir2_priv.h3
-rw-r--r--fs/xfs/libxfs/xfs_dir2_sf.c13
-rw-r--r--fs/xfs/libxfs/xfs_format.h2
-rw-r--r--fs/xfs/libxfs/xfs_health.h10
-rw-r--r--fs/xfs/libxfs/xfs_inode_fork.c33
-rw-r--r--fs/xfs/libxfs/xfs_shared.h2
-rw-r--r--fs/xfs/libxfs/xfs_symlink_remote.c8
-rw-r--r--fs/xfs/scrub/bmap.c144
-rw-r--r--fs/xfs/scrub/common.c28
-rw-r--r--fs/xfs/scrub/common.h8
-rw-r--r--fs/xfs/scrub/dir.c42
-rw-r--r--fs/xfs/scrub/health.c32
-rw-r--r--fs/xfs/scrub/health.h2
-rw-r--r--fs/xfs/scrub/inode.c16
-rw-r--r--fs/xfs/scrub/inode_repair.c1525
-rw-r--r--fs/xfs/scrub/parent.c17
-rw-r--r--fs/xfs/scrub/repair.c57
-rw-r--r--fs/xfs/scrub/repair.h29
-rw-r--r--fs/xfs/scrub/rtbitmap.c4
-rw-r--r--fs/xfs/scrub/rtsummary.c4
-rw-r--r--fs/xfs/scrub/scrub.c2
-rw-r--r--fs/xfs/scrub/symlink.c20
-rw-r--r--fs/xfs/scrub/trace.h171
-rw-r--r--fs/xfs/xfs_dir2_readdir.c3
-rw-r--r--fs/xfs/xfs_health.c8
-rw-r--r--fs/xfs/xfs_inode.c35
-rw-r--r--fs/xfs/xfs_inode.h2
-rw-r--r--fs/xfs/xfs_symlink.c3
-rw-r--r--fs/xfs/xfs_xattr.c6
34 files changed, 2185 insertions, 85 deletions
diff --git a/fs/xfs/Makefile b/fs/xfs/Makefile
index 7e1df6fdaaad..561ab59b9422 100644
--- a/fs/xfs/Makefile
+++ b/fs/xfs/Makefile
@@ -184,6 +184,7 @@ xfs-y += $(addprefix scrub/, \
agheader_repair.o \
alloc_repair.o \
ialloc_repair.o \
+ inode_repair.o \
newbt.o \
reap.o \
refcount_repair.o \
diff --git a/fs/xfs/libxfs/xfs_attr_leaf.c b/fs/xfs/libxfs/xfs_attr_leaf.c
index 654e17e6610d..5d1ab4978f32 100644
--- a/fs/xfs/libxfs/xfs_attr_leaf.c
+++ b/fs/xfs/libxfs/xfs_attr_leaf.c
@@ -1040,23 +1040,16 @@ 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)
+ 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_af.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.
diff --git a/fs/xfs/libxfs/xfs_attr_leaf.h b/fs/xfs/libxfs/xfs_attr_leaf.h
index 368f4d9fa1d5..ce6743463c86 100644
--- a/fs/xfs/libxfs/xfs_attr_leaf.h
+++ b/fs/xfs/libxfs/xfs_attr_leaf.h
@@ -56,7 +56,8 @@ 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 xfs_inode *ip);
+xfs_failaddr_t xfs_attr_shortform_verify(struct xfs_attr_shortform *sfp,
+ size_t size);
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 e308d2f44a3c..a073ca877ced 100644
--- a/fs/xfs/libxfs/xfs_bmap.c
+++ b/fs/xfs/libxfs/xfs_bmap.c
@@ -6168,19 +6168,18 @@ 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_rtbext(mp, irec->br_startblock,
irec->br_blockcount))
return __this_address;
@@ -6210,3 +6209,14 @@ xfs_bmap_intent_destroy_cache(void)
kmem_cache_destroy(xfs_bmap_intent_cache);
xfs_bmap_intent_cache = 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 e33470e39728..8518324db285 100644
--- a/fs/xfs/libxfs/xfs_bmap.h
+++ b/fs/xfs/libxfs/xfs_bmap.h
@@ -263,6 +263,8 @@ static inline uint32_t 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);
int xfs_bmap_complain_bad_rec(struct xfs_inode *ip, int whichfork,
diff --git a/fs/xfs/libxfs/xfs_dir2_priv.h b/fs/xfs/libxfs/xfs_dir2_priv.h
index 7404a9ff1a92..1db2e60ba827 100644
--- a/fs/xfs/libxfs/xfs_dir2_priv.h
+++ b/fs/xfs/libxfs/xfs_dir2_priv.h
@@ -175,7 +175,8 @@ extern int xfs_dir2_sf_create(struct xfs_da_args *args, xfs_ino_t pino);
extern int xfs_dir2_sf_lookup(struct xfs_da_args *args);
extern int xfs_dir2_sf_removename(struct xfs_da_args *args);
extern int xfs_dir2_sf_replace(struct xfs_da_args *args);
-extern xfs_failaddr_t xfs_dir2_sf_verify(struct xfs_inode *ip);
+xfs_failaddr_t xfs_dir2_sf_verify(struct xfs_mount *mp,
+ struct xfs_dir2_sf_hdr *sfp, int64_t size);
int xfs_dir2_sf_entsize(struct xfs_mount *mp,
struct xfs_dir2_sf_hdr *hdr, int len);
void xfs_dir2_sf_put_ino(struct xfs_mount *mp, struct xfs_dir2_sf_hdr *hdr,
diff --git a/fs/xfs/libxfs/xfs_dir2_sf.c b/fs/xfs/libxfs/xfs_dir2_sf.c
index 8cd37e6e9d38..870ef1d1ebe4 100644
--- a/fs/xfs/libxfs/xfs_dir2_sf.c
+++ b/fs/xfs/libxfs/xfs_dir2_sf.c
@@ -707,11 +707,10 @@ xfs_dir2_sf_check(
/* Verify the consistency of an inline directory. */
xfs_failaddr_t
xfs_dir2_sf_verify(
- struct xfs_inode *ip)
+ struct xfs_mount *mp,
+ struct xfs_dir2_sf_hdr *sfp,
+ int64_t size)
{
- struct xfs_mount *mp = ip->i_mount;
- struct xfs_ifork *ifp = xfs_ifork_ptr(ip, XFS_DATA_FORK);
- struct xfs_dir2_sf_hdr *sfp;
struct xfs_dir2_sf_entry *sfep;
struct xfs_dir2_sf_entry *next_sfep;
char *endp;
@@ -719,15 +718,9 @@ xfs_dir2_sf_verify(
int i;
int i8count;
int offset;
- int64_t size;
int error;
uint8_t filetype;
- ASSERT(ifp->if_format == XFS_DINODE_FMT_LOCAL);
-
- sfp = (struct xfs_dir2_sf_hdr *)ifp->if_u1.if_data;
- size = ifp->if_bytes;
-
/*
* Give up if the directory is way too short.
*/
diff --git a/fs/xfs/libxfs/xfs_format.h b/fs/xfs/libxfs/xfs_format.h
index 9a88aba1589f..f16974126ff9 100644
--- a/fs/xfs/libxfs/xfs_format.h
+++ b/fs/xfs/libxfs/xfs_format.h
@@ -1008,7 +1008,7 @@ enum xfs_dinode_fmt {
* Return pointers to the data or attribute forks.
*/
#define XFS_DFORK_DPTR(dip) \
- ((char *)dip + xfs_dinode_size(dip->di_version))
+ ((void *)dip + xfs_dinode_size(dip->di_version))
#define XFS_DFORK_APTR(dip) \
(XFS_DFORK_DPTR(dip) + XFS_DFORK_BOFF(dip))
#define XFS_DFORK_PTR(dip,w) \
diff --git a/fs/xfs/libxfs/xfs_health.h b/fs/xfs/libxfs/xfs_health.h
index 99e796256c5d..6296993ff8f3 100644
--- a/fs/xfs/libxfs/xfs_health.h
+++ b/fs/xfs/libxfs/xfs_health.h
@@ -68,6 +68,11 @@ struct xfs_fsop_geom;
#define XFS_SICK_INO_SYMLINK (1 << 6) /* symbolic link remote target */
#define XFS_SICK_INO_PARENT (1 << 7) /* parent pointers */
+#define XFS_SICK_INO_BMBTD_ZAPPED (1 << 8) /* data fork erased */
+#define XFS_SICK_INO_BMBTA_ZAPPED (1 << 9) /* attr fork erased */
+#define XFS_SICK_INO_DIR_ZAPPED (1 << 10) /* directory erased */
+#define XFS_SICK_INO_SYMLINK_ZAPPED (1 << 11) /* symlink erased */
+
/* Primary evidence of health problems in a given group. */
#define XFS_SICK_FS_PRIMARY (XFS_SICK_FS_COUNTERS | \
XFS_SICK_FS_UQUOTA | \
@@ -97,6 +102,11 @@ struct xfs_fsop_geom;
XFS_SICK_INO_SYMLINK | \
XFS_SICK_INO_PARENT)
+#define XFS_SICK_INO_ZAPPED (XFS_SICK_INO_BMBTD_ZAPPED | \
+ XFS_SICK_INO_BMBTA_ZAPPED | \
+ XFS_SICK_INO_DIR_ZAPPED | \
+ XFS_SICK_INO_SYMLINK_ZAPPED)
+
/* These functions must be provided by the xfs implementation. */
void xfs_fs_mark_sick(struct xfs_mount *mp, unsigned int mask);
diff --git a/fs/xfs/libxfs/xfs_inode_fork.c b/fs/xfs/libxfs/xfs_inode_fork.c
index 5a2e7ddfa76d..dad8ea832c20 100644
--- a/fs/xfs/libxfs/xfs_inode_fork.c
+++ b/fs/xfs/libxfs/xfs_inode_fork.c
@@ -702,12 +702,22 @@ xfs_ifork_verify_local_data(
xfs_failaddr_t fa = NULL;
switch (VFS_I(ip)->i_mode & S_IFMT) {
- case S_IFDIR:
- fa = xfs_dir2_sf_verify(ip);
+ case S_IFDIR: {
+ struct xfs_mount *mp = ip->i_mount;
+ struct xfs_ifork *ifp = xfs_ifork_ptr(ip, XFS_DATA_FORK);
+ struct xfs_dir2_sf_hdr *sfp;
+
+ sfp = (struct xfs_dir2_sf_hdr *)ifp->if_u1.if_data;
+ fa = xfs_dir2_sf_verify(mp, sfp, ifp->if_bytes);
break;
- case S_IFLNK:
- fa = xfs_symlink_shortform_verify(ip);
+ }
+ case S_IFLNK: {
+ struct xfs_ifork *ifp = xfs_ifork_ptr(ip, XFS_DATA_FORK);
+
+ fa = xfs_symlink_shortform_verify(ifp->if_u1.if_data,
+ ifp->if_bytes);
break;
+ }
default:
break;
}
@@ -729,11 +739,20 @@ xfs_ifork_verify_local_attr(
struct xfs_ifork *ifp = &ip->i_af;
xfs_failaddr_t fa;
- if (!xfs_inode_has_attr_fork(ip))
+ if (!xfs_inode_has_attr_fork(ip)) {
fa = __this_address;
- else
- fa = xfs_attr_shortform_verify(ip);
+ } else {
+ struct xfs_attr_shortform *sfp;
+ struct xfs_ifork *ifp;
+ int64_t size;
+ ASSERT(ip->i_af.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;
+
+ fa = xfs_attr_shortform_verify(sfp, size);
+ }
if (fa) {
xfs_inode_verifier_error(ip, -EFSCORRUPTED, "attr fork",
ifp->if_u1.if_data, ifp->if_bytes, fa);
diff --git a/fs/xfs/libxfs/xfs_shared.h b/fs/xfs/libxfs/xfs_shared.h
index c4381388c0c1..4220d3584c1b 100644
--- a/fs/xfs/libxfs/xfs_shared.h
+++ b/fs/xfs/libxfs/xfs_shared.h
@@ -139,7 +139,7 @@ bool xfs_symlink_hdr_ok(xfs_ino_t ino, uint32_t offset,
uint32_t size, struct xfs_buf *bp);
void xfs_symlink_local_to_remote(struct xfs_trans *tp, struct xfs_buf *bp,
struct xfs_inode *ip, struct xfs_ifork *ifp);
-xfs_failaddr_t xfs_symlink_shortform_verify(struct xfs_inode *ip);
+xfs_failaddr_t xfs_symlink_shortform_verify(void *sfp, int64_t size);
/* Computed inode geometry for the filesystem. */
struct xfs_ino_geometry {
diff --git a/fs/xfs/libxfs/xfs_symlink_remote.c b/fs/xfs/libxfs/xfs_symlink_remote.c
index bdc777b9ec4a..3c96d1d617fb 100644
--- a/fs/xfs/libxfs/xfs_symlink_remote.c
+++ b/fs/xfs/libxfs/xfs_symlink_remote.c
@@ -202,15 +202,11 @@ xfs_symlink_local_to_remote(
*/
xfs_failaddr_t
xfs_symlink_shortform_verify(
- struct xfs_inode *ip)
+ void *sfp,
+ int64_t size)
{
- struct xfs_ifork *ifp = xfs_ifork_ptr(ip, XFS_DATA_FORK);
- char *sfp = (char *)ifp->if_u1.if_data;
- int size = ifp->if_bytes;
char *endp = sfp + size;
- ASSERT(ifp->if_format == XFS_DINODE_FMT_LOCAL);
-
/*
* Zero length symlinks should never occur in memory as they are
* never allowed to exist on disk.
diff --git a/fs/xfs/scrub/bmap.c b/fs/xfs/scrub/bmap.c
index 06d8c1996a33..8175e8c17c14 100644
--- a/fs/xfs/scrub/bmap.c
+++ b/fs/xfs/scrub/bmap.c
@@ -19,9 +19,11 @@
#include "xfs_bmap_btree.h"
#include "xfs_rmap.h"
#include "xfs_rmap_btree.h"
+#include "xfs_health.h"
#include "scrub/scrub.h"
#include "scrub/common.h"
#include "scrub/btree.h"
+#include "scrub/health.h"
#include "xfs_ag.h"
/* Set us up with an inode's bmap. */
@@ -78,6 +80,10 @@ xchk_setup_inode_bmap(
if (error)
goto out;
+ error = xchk_ino_dqattach(sc);
+ if (error)
+ goto out;
+
xchk_ilock(sc, XFS_ILOCK_EXCL);
out:
/* scrub teardown will unlock and release the inode */
@@ -633,6 +639,82 @@ xchk_bmap_check_ag_rmaps(
}
/*
+ * Decide if we want to scan the reverse mappings to determine if the attr
+ * fork /really/ has zero space mappings.
+ */
+STATIC bool
+xchk_bmap_check_empty_attrfork(
+ struct xfs_inode *ip)
+{
+ struct xfs_ifork *ifp = &ip->i_af;
+
+ /*
+ * If the dinode repair found a bad attr fork, it will reset the fork
+ * to extents format with zero records and wait for the this scrubber
+ * to reconstruct the block mappings. If the fork is not in this
+ * state, then the fork cannot have been zapped.
+ */
+ if (ifp->if_format != XFS_DINODE_FMT_EXTENTS || ifp->if_nextents != 0)
+ return false;
+
+ /*
+ * Files can have an attr fork in EXTENTS format with zero records for
+ * several reasons:
+ *
+ * a) an attr set created a fork but ran out of space
+ * b) attr replace deleted an old attr but failed during the set step
+ * c) the data fork was in btree format when all attrs were deleted, so
+ * the fork was left in place
+ * d) the inode repair code zapped the fork
+ *
+ * Only in case (d) do we want to scan the rmapbt to see if we need to
+ * rebuild the attr fork. The fork zap code clears all DAC permission
+ * bits and zeroes the uid and gid, so avoid the scan if any of those
+ * three conditions are not met.
+ */
+ if ((VFS_I(ip)->i_mode & 0777) != 0)
+ return false;
+ if (!uid_eq(VFS_I(ip)->i_uid, GLOBAL_ROOT_UID))
+ return false;
+ if (!gid_eq(VFS_I(ip)->i_gid, GLOBAL_ROOT_GID))
+ return false;
+
+ return true;
+}
+
+/*
+ * Decide if we want to scan the reverse mappings to determine if the data
+ * fork /really/ has zero space mappings.
+ */
+STATIC bool
+xchk_bmap_check_empty_datafork(
+ struct xfs_inode *ip)
+{
+ struct xfs_ifork *ifp = &ip->i_df;
+
+ /* Don't support realtime rmap checks yet. */
+ if (XFS_IS_REALTIME_INODE(ip))
+ return false;
+
+ /*
+ * If the dinode repair found a bad data fork, it will reset the fork
+ * to extents format with zero records and wait for the this scrubber
+ * to reconstruct the block mappings. If the fork is not in this
+ * state, then the fork cannot have been zapped.
+ */
+ if (ifp->if_format != XFS_DINODE_FMT_EXTENTS || ifp->if_nextents != 0)
+ return false;
+
+ /*
+ * If we encounter an empty data fork along with evidence that the fork
+ * might not really be empty, we need to scan the reverse mappings to
+ * decide if we're going to rebuild the fork. Data forks with nonzero
+ * file size are scanned.
+ */
+ return i_size_read(VFS_I(ip)) != 0;
+}
+
+/*
* Decide if we want to walk every rmap btree in the fs to make sure that each
* rmap for this file fork has corresponding bmbt entries.
*/
@@ -641,7 +723,6 @@ xchk_bmap_want_check_rmaps(
struct xchk_bmap_info *info)
{
struct xfs_scrub *sc = info->sc;
- struct xfs_ifork *ifp;
if (!xfs_has_rmapbt(sc->mp))
return false;
@@ -650,28 +731,10 @@ xchk_bmap_want_check_rmaps(
if (sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT)
return false;
- /* Don't support realtime rmap checks yet. */
- if (info->is_rt)
- return false;
-
- /*
- * The inode repair code zaps broken inode forks by resetting them back
- * to EXTENTS format and zero extent records. If we encounter a fork
- * in this state along with evidence that the fork isn't supposed to be
- * empty, we need to scan the reverse mappings to decide if we're going
- * to rebuild the fork. Data forks with nonzero file size are scanned.
- * xattr forks are never empty of content, so they are always scanned.
- */
- ifp = xfs_ifork_ptr(sc->ip, info->whichfork);
- if (ifp->if_format == XFS_DINODE_FMT_EXTENTS && ifp->if_nextents == 0) {
- if (info->whichfork == XFS_DATA_FORK &&
- i_size_read(VFS_I(sc->ip)) == 0)
- return false;
-
- return true;
- }
+ if (info->whichfork == XFS_ATTR_FORK)
+ return xchk_bmap_check_empty_attrfork(sc->ip);
- return false;
+ return xchk_bmap_check_empty_datafork(sc->ip);
}
/* Make sure each rmap has a corresponding bmbt entry. */
@@ -939,7 +1002,20 @@ int
xchk_bmap_data(
struct xfs_scrub *sc)
{
- return xchk_bmap(sc, XFS_DATA_FORK);
+ int error;
+
+ if (xchk_file_looks_zapped(sc, XFS_SICK_INO_BMBTD_ZAPPED)) {
+ xchk_ino_set_corrupt(sc, sc->ip->i_ino);
+ return 0;
+ }
+
+ error = xchk_bmap(sc, XFS_DATA_FORK);
+ if (error)
+ return error;
+
+ /* If the data fork is clean, it is clearly not zapped. */
+ xchk_mark_healthy_if_clean(sc, XFS_SICK_INO_BMBTD_ZAPPED);
+ return 0;
}
/* Scrub an inode's attr fork. */
@@ -947,7 +1023,27 @@ int
xchk_bmap_attr(
struct xfs_scrub *sc)
{
- return xchk_bmap(sc, XFS_ATTR_FORK);
+ int error;
+
+ /*
+ * If the attr fork has been zapped, it's possible that forkoff was
+ * reset to zero and hence sc->ip->i_afp is NULL. We don't want the
+ * NULL ifp check in xchk_bmap to conclude that the attr fork is ok,
+ * so short circuit that logic by setting the corruption flag and
+ * returning immediately.
+ */
+ if (xchk_file_looks_zapped(sc, XFS_SICK_INO_BMBTA_ZAPPED)) {
+ xchk_ino_set_corrupt(sc, sc->ip->i_ino);
+ return 0;
+ }
+
+ error = xchk_bmap(sc, XFS_ATTR_FORK);
+ if (error)
+ return error;
+
+ /* If the attr fork is clean, it is clearly not zapped. */
+ xchk_mark_healthy_if_clean(sc, XFS_SICK_INO_BMBTA_ZAPPED);
+ return 0;
}
/* Scrub an inode's CoW fork. */
diff --git a/fs/xfs/scrub/common.c b/fs/xfs/scrub/common.c
index e0d6d8c9f640..81f2b96bb5a7 100644
--- a/fs/xfs/scrub/common.c
+++ b/fs/xfs/scrub/common.c
@@ -25,6 +25,7 @@
#include "xfs_trans_priv.h"
#include "xfs_da_format.h"
#include "xfs_da_btree.h"
+#include "xfs_dir2_priv.h"
#include "xfs_attr.h"
#include "xfs_reflink.h"
#include "xfs_ag.h"
@@ -819,6 +820,26 @@ again:
return 0;
}
+#ifdef CONFIG_XFS_QUOTA
+/*
+ * Try to attach dquots to this inode if we think we might want to repair it.
+ * Callers must not hold any ILOCKs. If the dquots are broken and cannot be
+ * attached, a quotacheck will be scheduled.
+ */
+int
+xchk_ino_dqattach(
+ struct xfs_scrub *sc)
+{
+ ASSERT(sc->tp != NULL);
+ ASSERT(sc->ip != NULL);
+
+ if (!xchk_could_repair(sc))
+ return 0;
+
+ return xrep_ino_dqattach(sc);
+}
+#endif
+
/* Install an inode that we opened by handle for scrubbing. */
int
xchk_install_handle_inode(
@@ -1030,6 +1051,11 @@ xchk_setup_inode_contents(
error = xchk_trans_alloc(sc, resblks);
if (error)
goto out;
+
+ error = xchk_ino_dqattach(sc);
+ if (error)
+ goto out;
+
xchk_ilock(sc, XFS_ILOCK_EXCL);
out:
/* scrub teardown will unlock and release the inode for us */
@@ -1135,6 +1161,7 @@ xchk_metadata_inode_subtype(
unsigned int scrub_type)
{
__u32 smtype = sc->sm->sm_type;
+ unsigned int sick_mask = sc->sick_mask;
int error;
sc->sm->sm_type = scrub_type;
@@ -1152,6 +1179,7 @@ xchk_metadata_inode_subtype(
break;
}
+ sc->sick_mask = sick_mask;
sc->sm->sm_type = smtype;
return error;
}
diff --git a/fs/xfs/scrub/common.h b/fs/xfs/scrub/common.h
index c31be570e7d8..ec5755266259 100644
--- a/fs/xfs/scrub/common.h
+++ b/fs/xfs/scrub/common.h
@@ -103,9 +103,15 @@ xchk_setup_rtsummary(struct xfs_scrub *sc)
}
#endif
#ifdef CONFIG_XFS_QUOTA
+int xchk_ino_dqattach(struct xfs_scrub *sc);
int xchk_setup_quota(struct xfs_scrub *sc);
#else
static inline int
+xchk_ino_dqattach(struct xfs_scrub *sc)
+{
+ return 0;
+}
+static inline int
xchk_setup_quota(struct xfs_scrub *sc)
{
return -ENOENT;
@@ -192,6 +198,8 @@ static inline bool xchk_skip_xref(struct xfs_scrub_metadata *sm)
XFS_SCRUB_OFLAG_XCORRUPT);
}
+bool xchk_dir_looks_zapped(struct xfs_inode *dp);
+
#ifdef CONFIG_XFS_ONLINE_REPAIR
/* Decide if a repair is required. */
static inline bool xchk_needs_repair(const struct xfs_scrub_metadata *sm)
diff --git a/fs/xfs/scrub/dir.c b/fs/xfs/scrub/dir.c
index 0b491784b759..d86ab51af928 100644
--- a/fs/xfs/scrub/dir.c
+++ b/fs/xfs/scrub/dir.c
@@ -15,10 +15,12 @@
#include "xfs_icache.h"
#include "xfs_dir2.h"
#include "xfs_dir2_priv.h"
+#include "xfs_health.h"
#include "scrub/scrub.h"
#include "scrub/common.h"
#include "scrub/dabtree.h"
#include "scrub/readdir.h"
+#include "scrub/health.h"
/* Set us up to scrub directories. */
int
@@ -760,6 +762,11 @@ xchk_directory(
if (!S_ISDIR(VFS_I(sc->ip)->i_mode))
return -ENOENT;
+ if (xchk_file_looks_zapped(sc, XFS_SICK_INO_DIR_ZAPPED)) {
+ xchk_fblock_set_corrupt(sc, XFS_DATA_FORK, 0);
+ return 0;
+ }
+
/* Plausible size? */
if (sc->ip->i_disk_size < xfs_dir2_sf_hdr_size(0)) {
xchk_ino_set_corrupt(sc, sc->ip->i_ino);
@@ -784,7 +791,36 @@ xchk_directory(
/* Look up every name in this directory by hash. */
error = xchk_dir_walk(sc, sc->ip, xchk_dir_actor, NULL);
- if (error == -ECANCELED)
- error = 0;
- return error;
+ if (error && error != -ECANCELED)
+ return error;
+
+ /* If the dir is clean, it is clearly not zapped. */
+ xchk_mark_healthy_if_clean(sc, XFS_SICK_INO_DIR_ZAPPED);
+ return 0;
+}
+
+/*
+ * Decide if this directory has been zapped to satisfy the inode and ifork
+ * verifiers. Checking and repairing should be postponed until the directory
+ * is fixed.
+ */
+bool
+xchk_dir_looks_zapped(
+ struct xfs_inode *dp)
+{
+ /* Repair zapped this dir's data fork a short time ago */
+ if (xfs_ifork_zapped(dp, XFS_DATA_FORK))
+ return true;
+
+ /*
+ * If the dinode repair found a bad data fork, it will reset the fork
+ * to extents format with zero records and wait for the bmapbtd
+ * scrubber to reconstruct the block mappings. Directories always
+ * contain some content, so this is a clear sign of a zapped directory.
+ * The state checked by xfs_ifork_zapped is not persisted, so this is
+ * the secondary strategy if repairs are interrupted by a crash or an
+ * unmount.
+ */
+ return dp->i_df.if_format == XFS_DINODE_FMT_EXTENTS &&
+ dp->i_df.if_nextents == 0;
}
diff --git a/fs/xfs/scrub/health.c b/fs/xfs/scrub/health.c
index 5e2b09ed6e29..df716da11226 100644
--- a/fs/xfs/scrub/health.c
+++ b/fs/xfs/scrub/health.c
@@ -118,6 +118,38 @@ xchk_health_mask_for_scrub_type(
}
/*
+ * If the scrub state is clean, add @mask to the scrub sick mask to clear
+ * additional sick flags from the metadata object's sick state.
+ */
+void
+xchk_mark_healthy_if_clean(
+ struct xfs_scrub *sc,
+ unsigned int mask)
+{
+ if (!(sc->sm->sm_flags & (XFS_SCRUB_OFLAG_CORRUPT |
+ XFS_SCRUB_OFLAG_XCORRUPT)))
+ sc->sick_mask |= mask;
+}
+
+/*
+ * If we're scrubbing a piece of file metadata for the first time, does it look
+ * like it has been zapped? Skip the check if we just repaired the metadata
+ * and are revalidating it.
+ */
+bool
+xchk_file_looks_zapped(
+ struct xfs_scrub *sc,
+ unsigned int mask)
+{
+ ASSERT((mask & ~XFS_SICK_INO_ZAPPED) == 0);
+
+ if (sc->flags & XREP_ALREADY_FIXED)
+ return false;
+
+ return xfs_inode_has_sickness(sc->ip, mask);
+}
+
+/*
* Update filesystem health assessments based on what we found and did.
*
* If the scrubber finds errors, we mark sick whatever's mentioned in
diff --git a/fs/xfs/scrub/health.h b/fs/xfs/scrub/health.h
index 66a273f8585b..a731b2467399 100644
--- a/fs/xfs/scrub/health.h
+++ b/fs/xfs/scrub/health.h
@@ -10,5 +10,7 @@ unsigned int xchk_health_mask_for_scrub_type(__u32 scrub_type);
void xchk_update_health(struct xfs_scrub *sc);
bool xchk_ag_btree_healthy_enough(struct xfs_scrub *sc, struct xfs_perag *pag,
xfs_btnum_t btnum);
+void xchk_mark_healthy_if_clean(struct xfs_scrub *sc, unsigned int mask);
+bool xchk_file_looks_zapped(struct xfs_scrub *sc, unsigned int mask);
#endif /* __XFS_SCRUB_HEALTH_H__ */
diff --git a/fs/xfs/scrub/inode.c b/fs/xfs/scrub/inode.c
index b7a93380a1ab..6e2fe2d6250b 100644
--- a/fs/xfs/scrub/inode.c
+++ b/fs/xfs/scrub/inode.c
@@ -25,6 +25,7 @@
#include "scrub/common.h"
#include "scrub/btree.h"
#include "scrub/trace.h"
+#include "scrub/repair.h"
/* Prepare the attached inode for scrubbing. */
static inline int
@@ -39,6 +40,10 @@ xchk_prepare_iscrub(
if (error)
return error;
+ error = xchk_ino_dqattach(sc);
+ if (error)
+ return error;
+
xchk_ilock(sc, XFS_ILOCK_EXCL);
return 0;
}
@@ -181,8 +186,11 @@ xchk_setup_inode(
* saying the inode is allocated and the icache being unable to load
* the inode until we can flag the corruption in xchk_inode. The
* scrub function has to note the corruption, since we're not really
- * supposed to do that from the setup function.
+ * supposed to do that from the setup function. Save the mapping to
+ * make repairs to the ondisk inode buffer.
*/
+ if (xchk_could_repair(sc))
+ xrep_setup_inode(sc, &imap);
return 0;
out_cancel:
@@ -338,6 +346,10 @@ xchk_inode_flags2(
if (xfs_dinode_has_bigtime(dip) && !xfs_has_bigtime(mp))
goto bad;
+ /* no large extent counts without the filesystem feature */
+ if ((flags2 & XFS_DIFLAG2_NREXT64) && !xfs_has_large_extent_counts(mp))
+ goto bad;
+
return;
bad:
xchk_ino_set_corrupt(sc, ino);
@@ -548,7 +560,7 @@ xchk_dinode(
}
/* di_forkoff */
- if (XFS_DFORK_APTR(dip) >= (char *)dip + mp->m_sb.sb_inodesize)
+ if (XFS_DFORK_BOFF(dip) >= mp->m_sb.sb_inodesize)
xchk_ino_set_corrupt(sc, ino);
if (naextents != 0 && dip->di_forkoff == 0)
xchk_ino_set_corrupt(sc, ino);
diff --git a/fs/xfs/scrub/inode_repair.c b/fs/xfs/scrub/inode_repair.c
new file mode 100644
index 000000000000..66949cc3d7cc
--- /dev/null
+++ b/fs/xfs/scrub/inode_repair.c
@@ -0,0 +1,1525 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Copyright (C) 2018-2023 Oracle. All Rights Reserved.
+ * Author: Darrick J. Wong <[email protected]>
+ */
+#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_icache.h"
+#include "xfs_inode_buf.h"
+#include "xfs_inode_fork.h"
+#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_quota.h"
+#include "xfs_ag.h"
+#include "xfs_rtbitmap.h"
+#include "xfs_attr_leaf.h"
+#include "xfs_log_priv.h"
+#include "xfs_health.h"
+#include "scrub/xfs_scrub.h"
+#include "scrub/scrub.h"
+#include "scrub/common.h"
+#include "scrub/btree.h"
+#include "scrub/trace.h"
+#include "scrub/repair.h"
+
+/*
+ * Inode Record Repair
+ * ===================
+ *
+ * Roughly speaking, inode problems can be classified based on whether or not
+ * they trip the dinode verifiers. If those trip, then we won't be able to
+ * xfs_iget ourselves the inode.
+ *
+ * Therefore, the xrep_dinode_* functions fix anything that will cause the
+ * inode buffer verifier or the dinode verifier. The xrep_inode_* functions
+ * fix things on live incore inodes. The inode repair functions make decisions
+ * with security and usability implications when reviving a file:
+ *
+ * - Files with zero di_mode or a garbage di_mode are converted to regular file
+ * that only root can read. This file may not actually contain user data,
+ * if the file was not previously a regular file. Setuid and setgid bits
+ * are cleared.
+ *
+ * - Zero-size directories can be truncated to look empty. It is necessary to
+ * run the bmapbtd and directory repair functions to fully rebuild the
+ * directory.
+ *
+ * - Zero-size symbolic link targets can be truncated to '?'. It is necessary
+ * to run the bmapbtd and symlink repair functions to salvage the symlink.
+ *
+ * - Invalid extent size hints will be removed.
+ *
+ * - Quotacheck will be scheduled if we repaired an inode that was so badly
+ * damaged that the ondisk inode had to be rebuilt.
+ *
+ * - Invalid user, group, or project IDs (aka -1U) will be reset to zero.
+ * Setuid and setgid bits are cleared.
+ *
+ * - Data and attr forks are reset to extents format with zero extents if the
+ * fork data is inconsistent. It is necessary to run the bmapbtd or bmapbta
+ * repair functions to recover the space mapping.
+ *
+ * - ACLs will not be recovered if the attr fork is zapped or the extended
+ * attribute structure itself requires salvaging.
+ *
+ * - If the attr fork is zapped, the user and group ids are reset to root and
+ * the setuid and setgid bits are removed.
+ */
+
+/*
+ * All the information we need to repair the ondisk inode if we can't iget the
+ * incore inode. We don't allocate this buffer unless we're going to perform
+ * a repair to the ondisk inode cluster buffer.
+ */
+struct xrep_inode {
+ /* Inode mapping that we saved from the initial lookup attempt. */
+ struct xfs_imap imap;
+
+ 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;
+
+ /* Sick state to set after zapping parts of the inode. */
+ unsigned int ino_sick_mask;
+
+ /* Must we remove all access from this file? */
+ bool zap_acls;
+};
+
+/*
+ * Setup function for inode repair. @imap contains the ondisk inode mapping
+ * information so that we can correct the ondisk inode cluster buffer if
+ * necessary to make iget work.
+ */
+int
+xrep_setup_inode(
+ struct xfs_scrub *sc,
+ const struct xfs_imap *imap)
+{
+ struct xrep_inode *ri;
+
+ sc->buf = kzalloc(sizeof(struct xrep_inode), XCHK_GFP_FLAGS);
+ if (!sc->buf)
+ return -ENOMEM;
+
+ ri = sc->buf;
+ memcpy(&ri->imap, imap, sizeof(struct xfs_imap));
+ ri->sc = sc;
+ return 0;
+}
+
+/*
+ * Make sure this ondisk inode can pass the inode buffer verifier. This is
+ * not the same as the dinode verifier.
+ */
+STATIC void
+xrep_dinode_buf_core(
+ struct xfs_scrub *sc,
+ struct xfs_buf *bp,
+ unsigned int ioffset)
+{
+ struct xfs_dinode *dip = xfs_buf_offset(bp, ioffset);
+ struct xfs_trans *tp = sc->tp;
+ struct xfs_mount *mp = sc->mp;
+ xfs_agino_t agino;
+ bool crc_ok = false;
+ bool magic_ok = false;
+ bool unlinked_ok = false;
+
+ agino = be32_to_cpu(dip->di_next_unlinked);
+
+ if (xfs_verify_agino_or_null(bp->b_pag, agino))
+ unlinked_ok = true;
+
+ if (dip->di_magic == cpu_to_be16(XFS_DINODE_MAGIC) &&
+ xfs_dinode_good_version(mp, dip->di_version))
+ magic_ok = true;
+
+ if (xfs_verify_cksum((char *)dip, mp->m_sb.sb_inodesize,
+ XFS_DINODE_CRC_OFF))
+ crc_ok = true;
+
+ if (magic_ok && unlinked_ok && crc_ok)
+ return;
+
+ if (!magic_ok) {
+ dip->di_magic = cpu_to_be16(XFS_DINODE_MAGIC);
+ dip->di_version = 3;
+ }
+ if (!unlinked_ok)
+ dip->di_next_unlinked = cpu_to_be32(NULLAGINO);
+ xfs_dinode_calc_crc(mp, dip);
+ xfs_trans_buf_set_type(tp, bp, XFS_BLFT_DINO_BUF);
+ xfs_trans_log_buf(tp, bp, ioffset,
+ ioffset + sizeof(struct xfs_dinode) - 1);
+}
+
+/* Make sure this inode cluster buffer can pass the inode buffer verifier. */
+STATIC void
+xrep_dinode_buf(
+ struct xfs_scrub *sc,
+ struct xfs_buf *bp)
+{
+ struct xfs_mount *mp = sc->mp;
+ int i;
+ int ni;
+
+ ni = XFS_BB_TO_FSB(mp, bp->b_length) * mp->m_sb.sb_inopblock;
+ for (i = 0; i < ni; i++)
+ xrep_dinode_buf_core(sc, bp, i << mp->m_sb.sb_inodelog);
+}
+
+/* Reinitialize things that never change in an inode. */
+STATIC void
+xrep_dinode_header(
+ struct xfs_scrub *sc,
+ struct xfs_dinode *dip)
+{
+ trace_xrep_dinode_header(sc, dip);
+
+ dip->di_magic = cpu_to_be16(XFS_DINODE_MAGIC);
+ if (!xfs_dinode_good_version(sc->mp, dip->di_version))
+ dip->di_version = 3;
+ dip->di_ino = cpu_to_be64(sc->sm->sm_ino);
+ uuid_copy(&dip->di_uuid, &sc->mp->m_sb.sb_meta_uuid);
+ dip->di_gen = cpu_to_be32(sc->sm->sm_gen);
+}
+
+/* Turn di_mode into /something/ recognizable. */
+STATIC void
+xrep_dinode_mode(
+ struct xrep_inode *ri,
+ struct xfs_dinode *dip)
+{
+ struct xfs_scrub *sc = ri->sc;
+ uint16_t mode = be16_to_cpu(dip->di_mode);
+
+ trace_xrep_dinode_mode(sc, dip);
+
+ if (mode == 0 || xfs_mode_to_ftype(mode) != XFS_DIR3_FT_UNKNOWN)
+ return;
+
+ /* bad mode, so we set it to a file that only root can read */
+ mode = S_IFREG;
+ dip->di_mode = cpu_to_be16(mode);
+ dip->di_uid = 0;
+ dip->di_gid = 0;
+ ri->zap_acls = true;
+}
+
+/* Fix any conflicting flags that the verifiers complain about. */
+STATIC void
+xrep_dinode_flags(
+ struct xfs_scrub *sc,
+ struct xfs_dinode *dip,
+ bool isrt)
+{
+ struct xfs_mount *mp = sc->mp;
+ uint64_t flags2 = be64_to_cpu(dip->di_flags2);
+ uint16_t flags = be16_to_cpu(dip->di_flags);
+ uint16_t mode = be16_to_cpu(dip->di_mode);
+
+ trace_xrep_dinode_flags(sc, dip);
+
+ if (isrt)
+ flags |= XFS_DIFLAG_REALTIME;
+ else
+ flags &= ~XFS_DIFLAG_REALTIME;
+
+ /*
+ * For regular files on a reflink filesystem, set the REFLINK flag to
+ * protect shared extents. A later stage will actually check those
+ * extents and clear the flag if possible.
+ */
+ if (xfs_has_reflink(mp) && S_ISREG(mode))
+ flags2 |= XFS_DIFLAG2_REFLINK;
+ else
+ flags2 &= ~(XFS_DIFLAG2_REFLINK | XFS_DIFLAG2_COWEXTSIZE);
+ if (flags & XFS_DIFLAG_REALTIME)
+ flags2 &= ~XFS_DIFLAG2_REFLINK;
+ if (!xfs_has_bigtime(mp))
+ flags2 &= ~XFS_DIFLAG2_BIGTIME;
+ if (!xfs_has_large_extent_counts(mp))
+ flags2 &= ~XFS_DIFLAG2_NREXT64;
+ if (flags2 & XFS_DIFLAG2_NREXT64)
+ dip->di_nrext64_pad = 0;
+ else if (dip->di_version >= 3)
+ dip->di_v3_pad = 0;
+ dip->di_flags = cpu_to_be16(flags);
+ dip->di_flags2 = cpu_to_be64(flags2);
+}
+
+/*
+ * Blow out symlink; now it points nowhere. We don't have to worry about
+ * incore state because this inode is failing the verifiers.
+ */
+STATIC void
+xrep_dinode_zap_symlink(
+ struct xrep_inode *ri,
+ struct xfs_dinode *dip)
+{
+ struct xfs_scrub *sc = ri->sc;
+ char *p;
+
+ trace_xrep_dinode_zap_symlink(sc, dip);
+
+ dip->di_format = XFS_DINODE_FMT_LOCAL;
+ dip->di_size = cpu_to_be64(1);
+ p = XFS_DFORK_PTR(dip, XFS_DATA_FORK);
+ *p = '?';
+ ri->ino_sick_mask |= XFS_SICK_INO_SYMLINK_ZAPPED;
+}
+
+/*
+ * Blow out dir, make the parent point to the root. In the future repair will
+ * reconstruct this directory for us. Note that there's no in-core directory
+ * inode because the sf verifier tripped, so we don't have to worry about the
+ * dentry cache.
+ */
+STATIC void
+xrep_dinode_zap_dir(
+ struct xrep_inode *ri,
+ struct xfs_dinode *dip)
+{
+ struct xfs_scrub *sc = ri->sc;
+ struct xfs_mount *mp = sc->mp;
+ struct xfs_dir2_sf_hdr *sfp;
+ int i8count;
+
+ trace_xrep_dinode_zap_dir(sc, dip);
+
+ dip->di_format = XFS_DINODE_FMT_LOCAL;
+ i8count = mp->m_sb.sb_rootino > XFS_DIR2_MAX_SHORT_INUM;
+ sfp = XFS_DFORK_PTR(dip, XFS_DATA_FORK);
+ sfp->count = 0;
+ sfp->i8count = i8count;
+ xfs_dir2_sf_put_parent_ino(sfp, mp->m_sb.sb_rootino);
+ dip->di_size = cpu_to_be64(xfs_dir2_sf_hdr_size(i8count));
+ ri->ino_sick_mask |= XFS_SICK_INO_DIR_ZAPPED;
+}
+
+/* Make sure we don't have a garbage file size. */
+STATIC void
+xrep_dinode_size(
+ struct xrep_inode *ri,
+ struct xfs_dinode *dip)
+{
+ struct xfs_scrub *sc = ri->sc;
+ uint64_t size = be64_to_cpu(dip->di_size);
+ uint16_t mode = be16_to_cpu(dip->di_mode);
+
+ trace_xrep_dinode_size(sc, dip);
+
+ switch (mode & S_IFMT) {
+ case S_IFIFO:
+ case S_IFCHR:
+ case S_IFBLK:
+ case S_IFSOCK:
+ /* di_size can't be nonzero for special files */
+ dip->di_size = 0;
+ break;
+ case S_IFREG:
+ /* Regular files can't be larger than 2^63-1 bytes. */
+ dip->di_size = cpu_to_be64(size & ~(1ULL << 63));
+ break;
+ case S_IFLNK:
+ /*
+ * Truncate ridiculously oversized symlinks. If the size is
+ * zero, reset it to point to the current directory. Both of
+ * these conditions trigger dinode verifier errors, so there
+ * is no in-core state to reset.
+ */
+ if (size > XFS_SYMLINK_MAXLEN)
+ dip->di_size = cpu_to_be64(XFS_SYMLINK_MAXLEN);
+ else if (size == 0)
+ xrep_dinode_zap_symlink(ri, dip);
+ break;
+ case S_IFDIR:
+ /*
+ * Directories can't have a size larger than 32G. If the size
+ * is zero, reset it to an empty directory. Both of these
+ * conditions trigger dinode verifier errors, so there is no
+ * in-core state to reset.
+ */
+ if (size > XFS_DIR2_SPACE_SIZE)
+ dip->di_size = cpu_to_be64(XFS_DIR2_SPACE_SIZE);
+ else if (size == 0)
+ xrep_dinode_zap_dir(ri, dip);
+ break;
+ }
+}
+
+/* Fix extent size hints. */
+STATIC void
+xrep_dinode_extsize_hints(
+ struct xfs_scrub *sc,
+ struct xfs_dinode *dip)
+{
+ struct xfs_mount *mp = sc->mp;
+ uint64_t flags2 = be64_to_cpu(dip->di_flags2);
+ uint16_t flags = be16_to_cpu(dip->di_flags);
+ uint16_t mode = be16_to_cpu(dip->di_mode);
+
+ xfs_failaddr_t fa;
+
+ trace_xrep_dinode_extsize_hints(sc, dip);
+
+ fa = xfs_inode_validate_extsize(mp, be32_to_cpu(dip->di_extsize),
+ mode, flags);
+ if (fa) {
+ dip->di_extsize = 0;
+ dip->di_flags &= ~cpu_to_be16(XFS_DIFLAG_EXTSIZE |
+ XFS_DIFLAG_EXTSZINHERIT);
+ }
+
+ if (dip->di_version < 3)
+ return;
+
+ fa = xfs_inode_validate_cowextsize(mp, be32_to_cpu(dip->di_cowextsize),
+ mode, flags, flags2);
+ if (fa) {
+ dip->di_cowextsize = 0;
+ dip->di_flags2 &= ~cpu_to_be64(XFS_DIFLAG2_COWEXTSIZE);
+ }
+}
+
+/* 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_inode *ri = priv;
+ int error = 0;
+
+ if (xchk_should_terminate(ri->sc, &error))
+ return error;
+
+ /* We only care about this inode. */
+ if (rec->rm_owner != ri->sc->sm->sm_ino)
+ return 0;
+
+ if (rec->rm_flags & XFS_RMAP_ATTR_FORK) {
+ ri->attr_blocks += rec->rm_blockcount;
+ if (!(rec->rm_flags & XFS_RMAP_BMBT_BLOCK))
+ ri->attr_extents++;
+
+ return 0;
+ }
+
+ ri->data_blocks += rec->rm_blockcount;
+ if (!(rec->rm_flags & XFS_RMAP_BMBT_BLOCK))
+ ri->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_inode *ri,
+ struct xfs_perag *pag)
+{
+ struct xfs_btree_cur *cur;
+ struct xfs_buf *agf;
+ int error;
+
+ error = xfs_alloc_read_agf(pag, ri->sc->tp, 0, &agf);
+ if (error)
+ return error;
+
+ cur = xfs_rmapbt_init_cursor(ri->sc->mp, ri->sc->tp, agf, pag);
+ error = xfs_rmap_query_all(cur, xrep_dinode_walk_rmap, ri);
+ xfs_btree_del_cursor(cur, error);
+ xfs_trans_brelse(ri->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_inode *ri)
+{
+ struct xfs_perag *pag;
+ xfs_agnumber_t agno;
+ int error;
+
+ if (!xfs_has_rmapbt(ri->sc->mp) || xfs_has_realtime(ri->sc->mp))
+ return -EOPNOTSUPP;
+
+ for_each_perag(ri->sc->mp, agno, pag) {
+ error = xrep_dinode_count_ag_rmaps(ri, pag);
+ if (error) {
+ xfs_perag_rele(pag);
+ return error;
+ }
+ }
+
+ /* Can't have extents on both the rt and the data device. */
+ if (ri->data_extents && ri->rt_extents)
+ return -EFSCORRUPTED;
+
+ trace_xrep_dinode_count_rmaps(ri->sc,
+ ri->data_blocks, ri->rt_blocks, ri->attr_blocks,
+ ri->data_extents, ri->rt_extents, ri->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,
+ unsigned int dfork_size,
+ int whichfork)
+{
+ struct xfs_bmbt_irec new;
+ struct xfs_bmbt_rec *dp;
+ xfs_extnum_t nex;
+ bool isrt;
+ unsigned int i;
+
+ nex = xfs_dfork_nextents(dip, whichfork);
+ if (nex > dfork_size / sizeof(struct xfs_bmbt_rec))
+ 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_bmbt_fork(
+ struct xfs_scrub *sc,
+ struct xfs_dinode *dip,
+ unsigned int dfork_size,
+ int whichfork)
+{
+ struct xfs_bmdr_block *dfp;
+ xfs_extnum_t nex;
+ unsigned int i;
+ unsigned int dmxr;
+ unsigned int nrecs;
+ unsigned int level;
+
+ nex = xfs_dfork_nextents(dip, whichfork);
+ if (nex <= 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;
+
+ dmxr = xfs_bmdr_maxrecs(dfork_size, 0);
+ for (i = 1; i <= nrecs; i++) {
+ struct xfs_bmbt_key *fkp;
+ xfs_bmbt_ptr_t *fpp;
+ xfs_fileoff_t fileoff;
+ xfs_fsblock_t fsbno;
+
+ fkp = XFS_BMDR_KEY_ADDR(dfp, i);
+ fileoff = be64_to_cpu(fkp->br_startoff);
+ if (!xfs_verify_fileoff(sc->mp, fileoff))
+ return true;
+
+ fpp = XFS_BMDR_PTR_ADDR(dfp, i, dmxr);
+ fsbno = be64_to_cpu(*fpp);
+ if (!xfs_verify_fsbno(sc->mp, fsbno))
+ 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)
+{
+ void *dfork_ptr;
+ int64_t data_size;
+ unsigned int fmt;
+ unsigned int dfork_size;
+
+ /*
+ * Verifier functions take signed int64_t, so check for bogus negative
+ * values first.
+ */
+ data_size = be64_to_cpu(dip->di_size);
+ if (data_size < 0)
+ return true;
+
+ fmt = XFS_DFORK_FORMAT(dip, XFS_DATA_FORK);
+ 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);
+ dfork_ptr = XFS_DFORK_PTR(dip, XFS_DATA_FORK);
+
+ switch (fmt) {
+ case XFS_DINODE_FMT_DEV:
+ break;
+ case XFS_DINODE_FMT_LOCAL:
+ /* dir/symlink structure cannot be larger than the fork */
+ if (data_size > dfork_size)
+ return true;
+ /* directory structure must pass verification. */
+ if (S_ISDIR(mode) &&
+ xfs_dir2_sf_verify(sc->mp, dfork_ptr, data_size) != NULL)
+ return true;
+ /* symlink structure must pass verification. */
+ if (S_ISLNK(mode) &&
+ xfs_symlink_shortform_verify(dfork_ptr, data_size) != NULL)
+ 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_bmbt_fork(sc, dip, dfork_size,
+ XFS_DATA_FORK))
+ return true;
+ break;
+ default:
+ return true;
+ }
+
+ return false;
+}
+
+static void
+xrep_dinode_set_data_nextents(
+ struct xfs_dinode *dip,
+ xfs_extnum_t nextents)
+{
+ if (xfs_dinode_has_large_extent_counts(dip))
+ dip->di_big_nextents = cpu_to_be64(nextents);
+ else
+ dip->di_nextents = cpu_to_be32(nextents);
+}
+
+static void
+xrep_dinode_set_attr_nextents(
+ struct xfs_dinode *dip,
+ xfs_extnum_t nextents)
+{
+ if (xfs_dinode_has_large_extent_counts(dip))
+ dip->di_big_anextents = cpu_to_be32(nextents);
+ else
+ dip->di_anextents = cpu_to_be16(nextents);
+}
+
+/* Reset the data fork to something sane. */
+STATIC void
+xrep_dinode_zap_dfork(
+ struct xrep_inode *ri,
+ struct xfs_dinode *dip,
+ uint16_t mode)
+{
+ struct xfs_scrub *sc = ri->sc;
+
+ trace_xrep_dinode_zap_dfork(sc, dip);
+
+ ri->ino_sick_mask |= XFS_SICK_INO_BMBTD_ZAPPED;
+
+ xrep_dinode_set_data_nextents(dip, 0);
+ ri->data_blocks = 0;
+ ri->rt_blocks = 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 (ri->data_extents || ri->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(ri, dip);
+ break;
+ case S_IFDIR:
+ xrep_dinode_zap_dir(ri, 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 *afork_ptr;
+ size_t attr_size;
+ unsigned int afork_size;
+
+ if (XFS_DFORK_BOFF(dip) == 0)
+ return dip->di_aformat != XFS_DINODE_FMT_EXTENTS ||
+ xfs_dfork_attr_extents(dip) != 0;
+
+ afork_size = XFS_DFORK_SIZE(dip, sc->mp, XFS_ATTR_FORK);
+ afork_ptr = XFS_DFORK_PTR(dip, XFS_ATTR_FORK);
+
+ switch (XFS_DFORK_FORMAT(dip, XFS_ATTR_FORK)) {
+ case XFS_DINODE_FMT_LOCAL:
+ /* Fork has to be large enough to extract the xattr size. */
+ if (afork_size < sizeof(struct xfs_attr_sf_hdr))
+ return true;
+
+ /* xattr structure cannot be larger than the fork */
+ attr_size = be16_to_cpu(afork_ptr->hdr.totsize);
+ if (attr_size > afork_size)
+ return true;
+
+ /* xattr structure must pass verification. */
+ return xfs_attr_shortform_verify(afork_ptr, attr_size) != NULL;
+ case XFS_DINODE_FMT_EXTENTS:
+ if (xrep_dinode_bad_extents_fork(sc, dip, afork_size,
+ XFS_ATTR_FORK))
+ return true;
+ break;
+ case XFS_DINODE_FMT_BTREE:
+ if (xrep_dinode_bad_bmbt_fork(sc, dip, afork_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 xrep_inode *ri,
+ struct xfs_dinode *dip,
+ uint16_t mode)
+{
+ struct xfs_scrub *sc = ri->sc;
+
+ trace_xrep_dinode_zap_afork(sc, dip);
+
+ ri->ino_sick_mask |= XFS_SICK_INO_BMBTA_ZAPPED;
+
+ dip->di_aformat = XFS_DINODE_FMT_EXTENTS;
+ xrep_dinode_set_attr_nextents(dip, 0);
+ ri->attr_blocks = 0;
+
+ /*
+ * If the data fork is in btree format, removing the attr fork entirely
+ * might cause verifier failures if the next level down in the bmbt
+ * could now fit in the data fork area.
+ */
+ if (dip->di_format != XFS_DINODE_FMT_BTREE)
+ 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 xrep_inode *ri,
+ struct xfs_dinode *dip,
+ uint16_t mode)
+{
+ struct xfs_bmdr_block *bmdr;
+ struct xfs_scrub *sc = ri->sc;
+ xfs_extnum_t attr_extents, data_extents;
+ 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:
+ attr_extents = xfs_dfork_attr_extents(dip);
+ if (attr_extents) {
+ /*
+ * 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) * attr_extents;
+ } else if (ri->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:
+ data_extents = xfs_dfork_data_extents(dip);
+ if (data_extents) {
+ /*
+ * 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) * data_extents;
+ } else if (ri->data_extents > 0 || ri->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 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 &&
+ xfs_dfork_data_extents(dip) == 0 &&
+ (ri->data_extents > 0 || ri->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(ri, dip, mode);
+ 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 &&
+ xfs_dfork_attr_extents(dip) == 0 &&
+ ri->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(ri, dip, mode);
+ } 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 xrep_inode *ri,
+ struct xfs_dinode *dip)
+{
+ struct xfs_scrub *sc = ri->sc;
+ xfs_extnum_t data_extents;
+ xfs_extnum_t attr_extents;
+ xfs_filblks_t nblocks;
+ uint16_t mode;
+ bool zap_datafork = false;
+ bool zap_attrfork = ri->zap_acls;
+
+ trace_xrep_dinode_zap_forks(sc, dip);
+
+ mode = be16_to_cpu(dip->di_mode);
+
+ data_extents = xfs_dfork_data_extents(dip);
+ attr_extents = xfs_dfork_attr_extents(dip);
+ nblocks = be64_to_cpu(dip->di_nblocks);
+
+ /* Inode counters don't make sense? */
+ if (data_extents > nblocks)
+ zap_datafork = true;
+ if (attr_extents > nblocks)
+ zap_attrfork = true;
+ if (data_extents + attr_extents > 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(ri, dip, mode);
+ if (zap_datafork)
+ xrep_dinode_zap_dfork(ri, dip, mode);
+ xrep_dinode_ensure_forkoff(ri, dip, mode);
+
+ /*
+ * Zero di_nblocks if we don't have any extents at all to satisfy the
+ * buffer verifier.
+ */
+ data_extents = xfs_dfork_data_extents(dip);
+ attr_extents = xfs_dfork_attr_extents(dip);
+ if (data_extents + attr_extents == 0)
+ dip->di_nblocks = 0;
+}
+
+/* Inode didn't pass dinode verifiers, so fix the raw buffer and retry iget. */
+STATIC int
+xrep_dinode_core(
+ struct xrep_inode *ri)
+{
+ struct xfs_scrub *sc = ri->sc;
+ struct xfs_buf *bp;
+ struct xfs_dinode *dip;
+ xfs_ino_t ino = sc->sm->sm_ino;
+ int error;
+ int iget_error;
+
+ /* Figure out what this inode had mapped in both forks. */
+ error = xrep_dinode_count_rmaps(ri);
+ if (error)
+ return error;
+
+ /* Read the inode cluster buffer. */
+ error = xfs_trans_read_buf(sc->mp, sc->tp, sc->mp->m_ddev_targp,
+ ri->imap.im_blkno, ri->imap.im_len, XBF_UNMAPPED, &bp,
+ NULL);
+ if (error)
+ return error;
+
+ /* Make sure we can pass the inode buffer verifier. */
+ xrep_dinode_buf(sc, bp);
+ bp->b_ops = &xfs_inode_buf_ops;
+
+ /* Fix everything the verifier will complain about. */
+ dip = xfs_buf_offset(bp, ri->imap.im_boffset);
+ xrep_dinode_header(sc, dip);
+ xrep_dinode_mode(ri, dip);
+ xrep_dinode_flags(sc, dip, ri->rt_extents > 0);
+ xrep_dinode_size(ri, dip);
+ xrep_dinode_extsize_hints(sc, dip);
+ xrep_dinode_zap_forks(ri, dip);
+
+ /* Write out the inode. */
+ trace_xrep_dinode_fixed(sc, dip);
+ xfs_dinode_calc_crc(sc->mp, dip);
+ xfs_trans_buf_set_type(sc->tp, bp, XFS_BLFT_DINO_BUF);
+ xfs_trans_log_buf(sc->tp, bp, ri->imap.im_boffset,
+ ri->imap.im_boffset + sc->mp->m_sb.sb_inodesize - 1);
+
+ /*
+ * In theory, we've fixed the ondisk inode record enough that we should
+ * be able to load the inode into the cache. Try to iget that inode
+ * now while we hold the AGI and the inode cluster buffer and take the
+ * IOLOCK so that we can continue with repairs without anyone else
+ * accessing the inode. If iget fails, we still need to commit the
+ * changes.
+ */
+ iget_error = xchk_iget(sc, ino, &sc->ip);
+ if (!iget_error)
+ xchk_ilock(sc, XFS_IOLOCK_EXCL);
+
+ /*
+ * Commit the inode cluster buffer updates and drop the AGI buffer that
+ * we've been holding since scrub setup. From here on out, repairs
+ * deal only with the cached inode.
+ */
+ error = xrep_trans_commit(sc);
+ if (error)
+ return error;
+
+ if (iget_error)
+ return iget_error;
+
+ error = xchk_trans_alloc(sc, 0);
+ if (error)
+ return error;
+
+ error = xrep_ino_dqattach(sc);
+ if (error)
+ return error;
+
+ xchk_ilock(sc, XFS_ILOCK_EXCL);
+ if (ri->ino_sick_mask)
+ xfs_inode_mark_sick(sc->ip, ri->ino_sick_mask);
+ return 0;
+}
+
+/* Fix everything xfs_dinode_verify cares about. */
+STATIC int
+xrep_dinode_problems(
+ struct xrep_inode *ri)
+{
+ struct xfs_scrub *sc = ri->sc;
+ int error;
+
+ error = xrep_dinode_core(ri);
+ if (error)
+ return error;
+
+ /* We had to fix a totally busted inode, schedule quotacheck. */
+ if (XFS_IS_UQUOTA_ON(sc->mp))
+ xrep_force_quotacheck(sc, XFS_DQTYPE_USER);
+ if (XFS_IS_GQUOTA_ON(sc->mp))
+ xrep_force_quotacheck(sc, XFS_DQTYPE_GROUP);
+ if (XFS_IS_PQUOTA_ON(sc->mp))
+ xrep_force_quotacheck(sc, XFS_DQTYPE_PROJ);
+
+ return 0;
+}
+
+/*
+ * Fix problems that the verifiers don't care about. In general these are
+ * errors that don't cause problems elsewhere in the kernel that we can easily
+ * detect, so we don't check them all that rigorously.
+ */
+
+/* Make sure block and extent counts are ok. */
+STATIC int
+xrep_inode_blockcounts(
+ struct xfs_scrub *sc)
+{
+ struct xfs_ifork *ifp;
+ xfs_filblks_t count;
+ xfs_filblks_t acount;
+ xfs_extnum_t nextents;
+ int error;
+
+ trace_xrep_inode_blockcounts(sc);
+
+ /* Set data fork counters from the data fork mappings. */
+ error = xfs_bmap_count_blocks(sc->tp, sc->ip, XFS_DATA_FORK,
+ &nextents, &count);
+ if (error)
+ return error;
+ if (xfs_is_reflink_inode(sc->ip)) {
+ /*
+ * data fork blockcount can exceed physical storage if a user
+ * reflinks the same block over and over again.
+ */
+ ;
+ } else if (XFS_IS_REALTIME_INODE(sc->ip)) {
+ if (count >= sc->mp->m_sb.sb_rblocks)
+ return -EFSCORRUPTED;
+ } else {
+ if (count >= sc->mp->m_sb.sb_dblocks)
+ return -EFSCORRUPTED;
+ }
+ error = xrep_ino_ensure_extent_count(sc, XFS_DATA_FORK, nextents);
+ if (error)
+ return error;
+ sc->ip->i_df.if_nextents = nextents;
+
+ /* Set attr fork counters from the attr fork mappings. */
+ ifp = xfs_ifork_ptr(sc->ip, XFS_ATTR_FORK);
+ if (ifp) {
+ error = xfs_bmap_count_blocks(sc->tp, sc->ip, XFS_ATTR_FORK,
+ &nextents, &acount);
+ if (error)
+ return error;
+ if (count >= sc->mp->m_sb.sb_dblocks)
+ return -EFSCORRUPTED;
+ error = xrep_ino_ensure_extent_count(sc, XFS_ATTR_FORK,
+ nextents);
+ if (error)
+ return error;
+ ifp->if_nextents = nextents;
+ } else {
+ acount = 0;
+ }
+
+ sc->ip->i_nblocks = count + acount;
+ return 0;
+}
+
+/* Check for invalid uid/gid/prid. */
+STATIC void
+xrep_inode_ids(
+ struct xfs_scrub *sc)
+{
+ bool dirty = false;
+
+ trace_xrep_inode_ids(sc);
+
+ if (!uid_valid(VFS_I(sc->ip)->i_uid)) {
+ i_uid_write(VFS_I(sc->ip), 0);
+ dirty = true;
+ if (XFS_IS_UQUOTA_ON(sc->mp))
+ xrep_force_quotacheck(sc, XFS_DQTYPE_USER);
+ }
+
+ if (!gid_valid(VFS_I(sc->ip)->i_gid)) {
+ i_gid_write(VFS_I(sc->ip), 0);
+ dirty = true;
+ if (XFS_IS_GQUOTA_ON(sc->mp))
+ xrep_force_quotacheck(sc, XFS_DQTYPE_GROUP);
+ }
+
+ if (sc->ip->i_projid == -1U) {
+ sc->ip->i_projid = 0;
+ dirty = true;
+ if (XFS_IS_PQUOTA_ON(sc->mp))
+ xrep_force_quotacheck(sc, XFS_DQTYPE_PROJ);
+ }
+
+ /* strip setuid/setgid if we touched any of the ids */
+ if (dirty)
+ VFS_I(sc->ip)->i_mode &= ~(S_ISUID | S_ISGID);
+}
+
+static inline void
+xrep_clamp_timestamp(
+ struct xfs_inode *ip,
+ struct timespec64 *ts)
+{
+ ts->tv_nsec = clamp_t(long, ts->tv_nsec, 0, NSEC_PER_SEC);
+ *ts = timestamp_truncate(*ts, VFS_I(ip));
+}
+
+/* Nanosecond counters can't have more than 1 billion. */
+STATIC void
+xrep_inode_timestamps(
+ struct xfs_inode *ip)
+{
+ struct timespec64 tstamp;
+ struct inode *inode = VFS_I(ip);
+
+ tstamp = inode_get_atime(inode);
+ xrep_clamp_timestamp(ip, &tstamp);
+ inode_set_atime_to_ts(inode, tstamp);
+
+ tstamp = inode_get_mtime(inode);
+ xrep_clamp_timestamp(ip, &tstamp);
+ inode_set_mtime_to_ts(inode, tstamp);
+
+ tstamp = inode_get_ctime(inode);
+ xrep_clamp_timestamp(ip, &tstamp);
+ inode_set_ctime_to_ts(inode, tstamp);
+
+ xrep_clamp_timestamp(ip, &ip->i_crtime);
+}
+
+/* Fix inode flags that don't make sense together. */
+STATIC void
+xrep_inode_flags(
+ struct xfs_scrub *sc)
+{
+ uint16_t mode;
+
+ trace_xrep_inode_flags(sc);
+
+ mode = VFS_I(sc->ip)->i_mode;
+
+ /* Clear junk flags */
+ if (sc->ip->i_diflags & ~XFS_DIFLAG_ANY)
+ sc->ip->i_diflags &= ~XFS_DIFLAG_ANY;
+
+ /* NEWRTBM only applies to realtime bitmaps */
+ if (sc->ip->i_ino == sc->mp->m_sb.sb_rbmino)
+ sc->ip->i_diflags |= XFS_DIFLAG_NEWRTBM;
+ else
+ sc->ip->i_diflags &= ~XFS_DIFLAG_NEWRTBM;
+
+ /* These only make sense for directories. */
+ if (!S_ISDIR(mode))
+ sc->ip->i_diflags &= ~(XFS_DIFLAG_RTINHERIT |
+ XFS_DIFLAG_EXTSZINHERIT |
+ XFS_DIFLAG_PROJINHERIT |
+ XFS_DIFLAG_NOSYMLINKS);
+
+ /* These only make sense for files. */
+ if (!S_ISREG(mode))
+ sc->ip->i_diflags &= ~(XFS_DIFLAG_REALTIME |
+ XFS_DIFLAG_EXTSIZE);
+
+ /* These only make sense for non-rt files. */
+ if (sc->ip->i_diflags & XFS_DIFLAG_REALTIME)
+ sc->ip->i_diflags &= ~XFS_DIFLAG_FILESTREAM;
+
+ /* Immutable and append only? Drop the append. */
+ if ((sc->ip->i_diflags & XFS_DIFLAG_IMMUTABLE) &&
+ (sc->ip->i_diflags & XFS_DIFLAG_APPEND))
+ sc->ip->i_diflags &= ~XFS_DIFLAG_APPEND;
+
+ /* Clear junk flags. */
+ if (sc->ip->i_diflags2 & ~XFS_DIFLAG2_ANY)
+ sc->ip->i_diflags2 &= ~XFS_DIFLAG2_ANY;
+
+ /* No reflink flag unless we support it and it's a file. */
+ if (!xfs_has_reflink(sc->mp) || !S_ISREG(mode))
+ sc->ip->i_diflags2 &= ~XFS_DIFLAG2_REFLINK;
+
+ /* DAX only applies to files and dirs. */
+ if (!(S_ISREG(mode) || S_ISDIR(mode)))
+ sc->ip->i_diflags2 &= ~XFS_DIFLAG2_DAX;
+
+ /* No reflink files on the realtime device. */
+ if (sc->ip->i_diflags & XFS_DIFLAG_REALTIME)
+ sc->ip->i_diflags2 &= ~XFS_DIFLAG2_REFLINK;
+}
+
+/*
+ * Fix size problems with block/node format directories. If we fail to find
+ * the extent list, just bail out and let the bmapbtd repair functions clean
+ * up that mess.
+ */
+STATIC void
+xrep_inode_blockdir_size(
+ struct xfs_scrub *sc)
+{
+ struct xfs_iext_cursor icur;
+ struct xfs_bmbt_irec got;
+ struct xfs_ifork *ifp;
+ xfs_fileoff_t off;
+ int error;
+
+ trace_xrep_inode_blockdir_size(sc);
+
+ error = xfs_iread_extents(sc->tp, sc->ip, XFS_DATA_FORK);
+ if (error)
+ return;
+
+ /* Find the last block before 32G; this is the dir size. */
+ ifp = xfs_ifork_ptr(sc->ip, XFS_DATA_FORK);
+ off = XFS_B_TO_FSB(sc->mp, XFS_DIR2_SPACE_SIZE);
+ if (!xfs_iext_lookup_extent_before(sc->ip, ifp, &off, &icur, &got)) {
+ /* zero-extents directory? */
+ return;
+ }
+
+ off = got.br_startoff + got.br_blockcount;
+ sc->ip->i_disk_size = min_t(loff_t, XFS_DIR2_SPACE_SIZE,
+ XFS_FSB_TO_B(sc->mp, off));
+}
+
+/* Fix size problems with short format directories. */
+STATIC void
+xrep_inode_sfdir_size(
+ struct xfs_scrub *sc)
+{
+ struct xfs_ifork *ifp;
+
+ trace_xrep_inode_sfdir_size(sc);
+
+ ifp = xfs_ifork_ptr(sc->ip, XFS_DATA_FORK);
+ sc->ip->i_disk_size = ifp->if_bytes;
+}
+
+/*
+ * Fix any irregularities in a directory inode's size now that we can iterate
+ * extent maps and access other regular inode data.
+ */
+STATIC void
+xrep_inode_dir_size(
+ struct xfs_scrub *sc)
+{
+ trace_xrep_inode_dir_size(sc);
+
+ switch (sc->ip->i_df.if_format) {
+ case XFS_DINODE_FMT_EXTENTS:
+ case XFS_DINODE_FMT_BTREE:
+ xrep_inode_blockdir_size(sc);
+ break;
+ case XFS_DINODE_FMT_LOCAL:
+ xrep_inode_sfdir_size(sc);
+ break;
+ }
+}
+
+/* Fix extent size hint problems. */
+STATIC void
+xrep_inode_extsize(
+ struct xfs_scrub *sc)
+{
+ /* Fix misaligned extent size hints on a directory. */
+ if ((sc->ip->i_diflags & XFS_DIFLAG_RTINHERIT) &&
+ (sc->ip->i_diflags & XFS_DIFLAG_EXTSZINHERIT) &&
+ xfs_extlen_to_rtxmod(sc->mp, sc->ip->i_extsize) > 0) {
+ sc->ip->i_extsize = 0;
+ sc->ip->i_diflags &= ~XFS_DIFLAG_EXTSZINHERIT;
+ }
+}
+
+/* Fix any irregularities in an inode that the verifiers don't catch. */
+STATIC int
+xrep_inode_problems(
+ struct xfs_scrub *sc)
+{
+ int error;
+
+ error = xrep_inode_blockcounts(sc);
+ if (error)
+ return error;
+ xrep_inode_timestamps(sc->ip);
+ xrep_inode_flags(sc);
+ xrep_inode_ids(sc);
+ /*
+ * We can now do a better job fixing the size of a directory now that
+ * we can scan the data fork extents than we could in xrep_dinode_size.
+ */
+ if (S_ISDIR(VFS_I(sc->ip)->i_mode))
+ xrep_inode_dir_size(sc);
+ xrep_inode_extsize(sc);
+
+ trace_xrep_inode_fixed(sc);
+ xfs_trans_log_inode(sc->tp, sc->ip, XFS_ILOG_CORE);
+ return xrep_roll_trans(sc);
+}
+
+/* Repair an inode's fields. */
+int
+xrep_inode(
+ struct xfs_scrub *sc)
+{
+ int error = 0;
+
+ /*
+ * No inode? That means we failed the _iget verifiers. Repair all
+ * the things that the inode verifiers care about, then retry _iget.
+ */
+ if (!sc->ip) {
+ struct xrep_inode *ri = sc->buf;
+
+ ASSERT(ri != NULL);
+
+ error = xrep_dinode_problems(ri);
+ if (error)
+ return error;
+
+ /* By this point we had better have a working incore inode. */
+ if (!sc->ip)
+ return -EFSCORRUPTED;
+ }
+
+ xfs_trans_ijoin(sc->tp, sc->ip, 0);
+
+ /* If we found corruption of any kind, try to fix it. */
+ if ((sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT) ||
+ (sc->sm->sm_flags & XFS_SCRUB_OFLAG_XCORRUPT)) {
+ error = xrep_inode_problems(sc);
+ if (error)
+ return error;
+ }
+
+ /* See if we can clear the reflink flag. */
+ if (xfs_is_reflink_inode(sc->ip)) {
+ error = xfs_reflink_clear_inode_flag(sc->ip, &sc->tp);
+ if (error)
+ return error;
+ }
+
+ return xrep_defer_finish(sc);
+}
diff --git a/fs/xfs/scrub/parent.c b/fs/xfs/scrub/parent.c
index e6155d86f791..7db873672146 100644
--- a/fs/xfs/scrub/parent.c
+++ b/fs/xfs/scrub/parent.c
@@ -156,6 +156,16 @@ xchk_parent_validate(
goto out_rele;
}
+ /*
+ * We cannot yet validate this parent pointer if the directory looks as
+ * though it has been zapped by the inode record repair code.
+ */
+ if (xchk_dir_looks_zapped(dp)) {
+ error = -EBUSY;
+ xchk_set_incomplete(sc);
+ goto out_unlock;
+ }
+
/* Look for a directory entry in the parent pointing to the child. */
error = xchk_dir_walk(sc, dp, xchk_parent_actor, &spc);
if (!xchk_fblock_xref_process_error(sc, XFS_DATA_FORK, 0, &error))
@@ -217,6 +227,13 @@ xchk_parent(
*/
error = xchk_parent_validate(sc, parent_ino);
} while (error == -EAGAIN);
+ if (error == -EBUSY) {
+ /*
+ * We could not scan a directory, so we marked the check
+ * incomplete. No further error return is necessary.
+ */
+ return 0;
+ }
return error;
}
diff --git a/fs/xfs/scrub/repair.c b/fs/xfs/scrub/repair.c
index a604f0cea8c1..25392dea326d 100644
--- a/fs/xfs/scrub/repair.c
+++ b/fs/xfs/scrub/repair.c
@@ -176,6 +176,16 @@ xrep_roll_ag_trans(
return 0;
}
+/* Roll the scrub transaction, holding the primary metadata locked. */
+int
+xrep_roll_trans(
+ struct xfs_scrub *sc)
+{
+ if (!sc->ip)
+ return xrep_roll_ag_trans(sc);
+ return xfs_trans_roll_inode(&sc->tp, sc->ip);
+}
+
/* Finish all deferred work attached to the repair transaction. */
int
xrep_defer_finish(
@@ -673,6 +683,7 @@ xrep_find_ag_btree_roots(
return error;
}
+#ifdef CONFIG_XFS_QUOTA
/* Force a quotacheck the next time we mount. */
void
xrep_force_quotacheck(
@@ -699,10 +710,10 @@ xrep_force_quotacheck(
*
* This function ensures that the appropriate dquots are attached to an inode.
* We cannot allow the dquot code to allocate an on-disk dquot block here
- * because we're already in transaction context with the inode locked. The
- * on-disk dquot should already exist anyway. If the quota code signals
- * corruption or missing quota information, schedule quotacheck, which will
- * repair corruptions in the quota metadata.
+ * because we're already in transaction context. The on-disk dquot should
+ * already exist anyway. If the quota code signals corruption or missing quota
+ * information, schedule quotacheck, which will repair corruptions in the quota
+ * metadata.
*/
int
xrep_ino_dqattach(
@@ -710,7 +721,10 @@ xrep_ino_dqattach(
{
int error;
- error = xfs_qm_dqattach_locked(sc->ip, false);
+ ASSERT(sc->tp != NULL);
+ ASSERT(sc->ip != NULL);
+
+ error = xfs_qm_dqattach(sc->ip);
switch (error) {
case -EFSBADCRC:
case -EFSCORRUPTED:
@@ -734,6 +748,39 @@ xrep_ino_dqattach(
return error;
}
+#endif /* CONFIG_XFS_QUOTA */
+
+/*
+ * Ensure that the inode being repaired is ready to handle a certain number of
+ * extents, or return EFSCORRUPTED. Caller must hold the ILOCK of the inode
+ * being repaired and have joined it to the scrub transaction.
+ */
+int
+xrep_ino_ensure_extent_count(
+ struct xfs_scrub *sc,
+ int whichfork,
+ xfs_extnum_t nextents)
+{
+ xfs_extnum_t max_extents;
+ bool inode_has_nrext64;
+
+ inode_has_nrext64 = xfs_inode_has_large_extent_counts(sc->ip);
+ max_extents = xfs_iext_max_nextents(inode_has_nrext64, whichfork);
+ if (nextents <= max_extents)
+ return 0;
+ if (inode_has_nrext64)
+ return -EFSCORRUPTED;
+ if (!xfs_has_large_extent_counts(sc->mp))
+ return -EFSCORRUPTED;
+
+ max_extents = xfs_iext_max_nextents(true, whichfork);
+ if (nextents > max_extents)
+ return -EFSCORRUPTED;
+
+ sc->ip->i_diflags2 |= XFS_DIFLAG2_NREXT64;
+ xfs_trans_log_inode(sc->tp, sc->ip, XFS_ILOG_CORE);
+ return 0;
+}
/*
* Initialize all the btree cursors for an AG repair except for the btree that
diff --git a/fs/xfs/scrub/repair.h b/fs/xfs/scrub/repair.h
index cc7ea3942729..a513b84f5330 100644
--- a/fs/xfs/scrub/repair.h
+++ b/fs/xfs/scrub/repair.h
@@ -30,11 +30,22 @@ static inline int xrep_notsupported(struct xfs_scrub *sc)
int xrep_attempt(struct xfs_scrub *sc, struct xchk_stats_run *run);
void xrep_failure(struct xfs_mount *mp);
int xrep_roll_ag_trans(struct xfs_scrub *sc);
+int xrep_roll_trans(struct xfs_scrub *sc);
int xrep_defer_finish(struct xfs_scrub *sc);
bool xrep_ag_has_space(struct xfs_perag *pag, xfs_extlen_t nr_blocks,
enum xfs_ag_resv_type type);
xfs_extlen_t xrep_calc_ag_resblks(struct xfs_scrub *sc);
+static inline int
+xrep_trans_commit(
+ struct xfs_scrub *sc)
+{
+ int error = xfs_trans_commit(sc->tp);
+
+ sc->tp = NULL;
+ return error;
+}
+
struct xbitmap;
struct xagb_bitmap;
@@ -57,13 +68,25 @@ struct xrep_find_ag_btree {
int xrep_find_ag_btree_roots(struct xfs_scrub *sc, struct xfs_buf *agf_bp,
struct xrep_find_ag_btree *btree_info, struct xfs_buf *agfl_bp);
+
+#ifdef CONFIG_XFS_QUOTA
void xrep_force_quotacheck(struct xfs_scrub *sc, xfs_dqtype_t type);
int xrep_ino_dqattach(struct xfs_scrub *sc);
+#else
+# define xrep_force_quotacheck(sc, type) ((void)0)
+# define xrep_ino_dqattach(sc) (0)
+#endif /* CONFIG_XFS_QUOTA */
+
+int xrep_ino_ensure_extent_count(struct xfs_scrub *sc, int whichfork,
+ xfs_extnum_t nextents);
int xrep_reset_perag_resv(struct xfs_scrub *sc);
/* Repair setup functions */
int xrep_setup_ag_allocbt(struct xfs_scrub *sc);
+struct xfs_imap;
+int xrep_setup_inode(struct xfs_scrub *sc, const struct xfs_imap *imap);
+
void xrep_ag_btcur_init(struct xfs_scrub *sc, struct xchk_ag *sa);
/* Metadata revalidators */
@@ -81,12 +104,15 @@ int xrep_agi(struct xfs_scrub *sc);
int xrep_allocbt(struct xfs_scrub *sc);
int xrep_iallocbt(struct xfs_scrub *sc);
int xrep_refcountbt(struct xfs_scrub *sc);
+int xrep_inode(struct xfs_scrub *sc);
int xrep_reinit_pagf(struct xfs_scrub *sc);
int xrep_reinit_pagi(struct xfs_scrub *sc);
#else
+#define xrep_ino_dqattach(sc) (0)
+
static inline int
xrep_attempt(
struct xfs_scrub *sc,
@@ -124,6 +150,8 @@ xrep_setup_nothing(
}
#define xrep_setup_ag_allocbt xrep_setup_nothing
+#define xrep_setup_inode(sc, imap) ((void)0)
+
#define xrep_revalidate_allocbt (NULL)
#define xrep_revalidate_iallocbt (NULL)
@@ -135,6 +163,7 @@ xrep_setup_nothing(
#define xrep_allocbt xrep_notsupported
#define xrep_iallocbt xrep_notsupported
#define xrep_refcountbt xrep_notsupported
+#define xrep_inode xrep_notsupported
#endif /* CONFIG_XFS_ONLINE_REPAIR */
diff --git a/fs/xfs/scrub/rtbitmap.c b/fs/xfs/scrub/rtbitmap.c
index 41a1d89ae8e6..d509a08d3fc3 100644
--- a/fs/xfs/scrub/rtbitmap.c
+++ b/fs/xfs/scrub/rtbitmap.c
@@ -32,6 +32,10 @@ xchk_setup_rtbitmap(
if (error)
return error;
+ error = xchk_ino_dqattach(sc);
+ if (error)
+ return error;
+
xchk_ilock(sc, XFS_ILOCK_EXCL | XFS_ILOCK_RTBITMAP);
return 0;
}
diff --git a/fs/xfs/scrub/rtsummary.c b/fs/xfs/scrub/rtsummary.c
index 8b15c47408d0..f94800a029f3 100644
--- a/fs/xfs/scrub/rtsummary.c
+++ b/fs/xfs/scrub/rtsummary.c
@@ -63,6 +63,10 @@ xchk_setup_rtsummary(
if (error)
return error;
+ error = xchk_ino_dqattach(sc);
+ if (error)
+ return error;
+
/*
* Locking order requires us to take the rtbitmap first. We must be
* careful to unlock it ourselves when we are done with the rtbitmap
diff --git a/fs/xfs/scrub/scrub.c b/fs/xfs/scrub/scrub.c
index 6ff4dc57095f..7e903a0fde6c 100644
--- a/fs/xfs/scrub/scrub.c
+++ b/fs/xfs/scrub/scrub.c
@@ -282,7 +282,7 @@ static const struct xchk_meta_ops meta_scrub_ops[] = {
.type = ST_INODE,
.setup = xchk_setup_inode,
.scrub = xchk_inode,
- .repair = xrep_notsupported,
+ .repair = xrep_inode,
},
[XFS_SCRUB_TYPE_BMBTD] = { /* inode data fork */
.type = ST_INODE,
diff --git a/fs/xfs/scrub/symlink.c b/fs/xfs/scrub/symlink.c
index 38708fb9a5d7..60643d791d4a 100644
--- a/fs/xfs/scrub/symlink.c
+++ b/fs/xfs/scrub/symlink.c
@@ -12,8 +12,10 @@
#include "xfs_log_format.h"
#include "xfs_inode.h"
#include "xfs_symlink.h"
+#include "xfs_health.h"
#include "scrub/scrub.h"
#include "scrub/common.h"
+#include "scrub/health.h"
/* Set us up to scrub a symbolic link. */
int
@@ -41,13 +43,19 @@ xchk_symlink(
if (!S_ISLNK(VFS_I(ip)->i_mode))
return -ENOENT;
+
+ if (xchk_file_looks_zapped(sc, XFS_SICK_INO_SYMLINK_ZAPPED)) {
+ xchk_fblock_set_corrupt(sc, XFS_DATA_FORK, 0);
+ return 0;
+ }
+
ifp = xfs_ifork_ptr(ip, XFS_DATA_FORK);
len = ip->i_disk_size;
/* Plausible size? */
if (len > XFS_SYMLINK_MAXLEN || len <= 0) {
xchk_fblock_set_corrupt(sc, XFS_DATA_FORK, 0);
- goto out;
+ return 0;
}
/* Inline symlink? */
@@ -55,15 +63,17 @@ xchk_symlink(
if (len > xfs_inode_data_fork_size(ip) ||
len > strnlen(ifp->if_u1.if_data, xfs_inode_data_fork_size(ip)))
xchk_fblock_set_corrupt(sc, XFS_DATA_FORK, 0);
- goto out;
+ return 0;
}
/* Remote symlink; must read the contents. */
error = xfs_readlink_bmap_ilocked(sc->ip, sc->buf);
if (!xchk_fblock_process_error(sc, XFS_DATA_FORK, 0, &error))
- goto out;
+ return error;
if (strnlen(sc->buf, XFS_SYMLINK_MAXLEN) < len)
xchk_fblock_set_corrupt(sc, XFS_DATA_FORK, 0);
-out:
- return error;
+
+ /* If a remote symlink is clean, it is clearly not zapped. */
+ xchk_mark_healthy_if_clean(sc, XFS_SICK_INO_SYMLINK_ZAPPED);
+ return 0;
}
diff --git a/fs/xfs/scrub/trace.h b/fs/xfs/scrub/trace.h
index 3f7af4430951..120faa4dce2d 100644
--- a/fs/xfs/scrub/trace.h
+++ b/fs/xfs/scrub/trace.h
@@ -1393,6 +1393,177 @@ DEFINE_NEWBT_EXTENT_EVENT(xrep_newbt_alloc_file_blocks);
DEFINE_NEWBT_EXTENT_EVENT(xrep_newbt_free_blocks);
DEFINE_NEWBT_EXTENT_EVENT(xrep_newbt_claim_block);
+DECLARE_EVENT_CLASS(xrep_dinode_class,
+ TP_PROTO(struct xfs_scrub *sc, struct xfs_dinode *dip),
+ TP_ARGS(sc, dip),
+ TP_STRUCT__entry(
+ __field(dev_t, dev)
+ __field(xfs_ino_t, ino)
+ __field(uint16_t, mode)
+ __field(uint8_t, version)
+ __field(uint8_t, format)
+ __field(uint32_t, uid)
+ __field(uint32_t, gid)
+ __field(uint64_t, size)
+ __field(uint64_t, nblocks)
+ __field(uint32_t, extsize)
+ __field(uint32_t, nextents)
+ __field(uint16_t, anextents)
+ __field(uint8_t, forkoff)
+ __field(uint8_t, aformat)
+ __field(uint16_t, flags)
+ __field(uint32_t, gen)
+ __field(uint64_t, flags2)
+ __field(uint32_t, cowextsize)
+ ),
+ TP_fast_assign(
+ __entry->dev = sc->mp->m_super->s_dev;
+ __entry->ino = sc->sm->sm_ino;
+ __entry->mode = be16_to_cpu(dip->di_mode);
+ __entry->version = dip->di_version;
+ __entry->format = dip->di_format;
+ __entry->uid = be32_to_cpu(dip->di_uid);
+ __entry->gid = be32_to_cpu(dip->di_gid);
+ __entry->size = be64_to_cpu(dip->di_size);
+ __entry->nblocks = be64_to_cpu(dip->di_nblocks);
+ __entry->extsize = be32_to_cpu(dip->di_extsize);
+ __entry->nextents = be32_to_cpu(dip->di_nextents);
+ __entry->anextents = be16_to_cpu(dip->di_anextents);
+ __entry->forkoff = dip->di_forkoff;
+ __entry->aformat = dip->di_aformat;
+ __entry->flags = be16_to_cpu(dip->di_flags);
+ __entry->gen = be32_to_cpu(dip->di_gen);
+ __entry->flags2 = be64_to_cpu(dip->di_flags2);
+ __entry->cowextsize = be32_to_cpu(dip->di_cowextsize);
+ ),
+ TP_printk("dev %d:%d ino 0x%llx mode 0x%x version %u format %u uid %u gid %u disize 0x%llx nblocks 0x%llx extsize %u nextents %u anextents %u forkoff 0x%x aformat %u flags 0x%x gen 0x%x flags2 0x%llx cowextsize %u",
+ MAJOR(__entry->dev), MINOR(__entry->dev),
+ __entry->ino,
+ __entry->mode,
+ __entry->version,
+ __entry->format,
+ __entry->uid,
+ __entry->gid,
+ __entry->size,
+ __entry->nblocks,
+ __entry->extsize,
+ __entry->nextents,
+ __entry->anextents,
+ __entry->forkoff,
+ __entry->aformat,
+ __entry->flags,
+ __entry->gen,
+ __entry->flags2,
+ __entry->cowextsize)
+)
+
+#define DEFINE_REPAIR_DINODE_EVENT(name) \
+DEFINE_EVENT(xrep_dinode_class, name, \
+ TP_PROTO(struct xfs_scrub *sc, struct xfs_dinode *dip), \
+ TP_ARGS(sc, dip))
+DEFINE_REPAIR_DINODE_EVENT(xrep_dinode_header);
+DEFINE_REPAIR_DINODE_EVENT(xrep_dinode_mode);
+DEFINE_REPAIR_DINODE_EVENT(xrep_dinode_flags);
+DEFINE_REPAIR_DINODE_EVENT(xrep_dinode_size);
+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),
+ TP_ARGS(sc),
+ TP_STRUCT__entry(
+ __field(dev_t, dev)
+ __field(xfs_ino_t, ino)
+ __field(xfs_fsize_t, size)
+ __field(xfs_rfsblock_t, nblocks)
+ __field(uint16_t, flags)
+ __field(uint64_t, flags2)
+ __field(uint32_t, nextents)
+ __field(uint8_t, format)
+ __field(uint32_t, anextents)
+ __field(uint8_t, aformat)
+ ),
+ TP_fast_assign(
+ __entry->dev = sc->mp->m_super->s_dev;
+ __entry->ino = sc->sm->sm_ino;
+ __entry->size = sc->ip->i_disk_size;
+ __entry->nblocks = sc->ip->i_nblocks;
+ __entry->flags = sc->ip->i_diflags;
+ __entry->flags2 = sc->ip->i_diflags2;
+ __entry->nextents = sc->ip->i_df.if_nextents;
+ __entry->format = sc->ip->i_df.if_format;
+ __entry->anextents = sc->ip->i_af.if_nextents;
+ __entry->aformat = sc->ip->i_af.if_format;
+ ),
+ TP_printk("dev %d:%d ino 0x%llx disize 0x%llx nblocks 0x%llx flags 0x%x flags2 0x%llx nextents %u format %u anextents %u aformat %u",
+ MAJOR(__entry->dev), MINOR(__entry->dev),
+ __entry->ino,
+ __entry->size,
+ __entry->nblocks,
+ __entry->flags,
+ __entry->flags2,
+ __entry->nextents,
+ __entry->format,
+ __entry->anextents,
+ __entry->aformat)
+)
+
+#define DEFINE_REPAIR_INODE_EVENT(name) \
+DEFINE_EVENT(xrep_inode_class, name, \
+ TP_PROTO(struct xfs_scrub *sc), \
+ TP_ARGS(sc))
+DEFINE_REPAIR_INODE_EVENT(xrep_inode_blockcounts);
+DEFINE_REPAIR_INODE_EVENT(xrep_inode_ids);
+DEFINE_REPAIR_INODE_EVENT(xrep_inode_flags);
+DEFINE_REPAIR_INODE_EVENT(xrep_inode_blockdir_size);
+DEFINE_REPAIR_INODE_EVENT(xrep_inode_sfdir_size);
+DEFINE_REPAIR_INODE_EVENT(xrep_inode_dir_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 %llu rtextents %llu 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 */
diff --git a/fs/xfs/xfs_dir2_readdir.c b/fs/xfs/xfs_dir2_readdir.c
index 9f3ceb461515..57f42c2af0a3 100644
--- a/fs/xfs/xfs_dir2_readdir.c
+++ b/fs/xfs/xfs_dir2_readdir.c
@@ -18,6 +18,7 @@
#include "xfs_bmap.h"
#include "xfs_trans.h"
#include "xfs_error.h"
+#include "xfs_health.h"
/*
* Directory file type support functions
@@ -519,6 +520,8 @@ xfs_readdir(
if (xfs_is_shutdown(dp->i_mount))
return -EIO;
+ if (xfs_ifork_zapped(dp, XFS_DATA_FORK))
+ return -EIO;
ASSERT(S_ISDIR(VFS_I(dp)->i_mode));
ASSERT(xfs_isilocked(dp, XFS_IOLOCK_SHARED | XFS_IOLOCK_EXCL));
diff --git a/fs/xfs/xfs_health.c b/fs/xfs/xfs_health.c
index 72a075bb2c10..9a57afee9338 100644
--- a/fs/xfs/xfs_health.c
+++ b/fs/xfs/xfs_health.c
@@ -222,7 +222,7 @@ xfs_inode_mark_sick(
struct xfs_inode *ip,
unsigned int mask)
{
- ASSERT(!(mask & ~XFS_SICK_INO_PRIMARY));
+ ASSERT(!(mask & ~(XFS_SICK_INO_PRIMARY | XFS_SICK_INO_ZAPPED)));
trace_xfs_inode_mark_sick(ip, mask);
spin_lock(&ip->i_flags_lock);
@@ -246,7 +246,7 @@ xfs_inode_mark_healthy(
struct xfs_inode *ip,
unsigned int mask)
{
- ASSERT(!(mask & ~XFS_SICK_INO_PRIMARY));
+ ASSERT(!(mask & ~(XFS_SICK_INO_PRIMARY | XFS_SICK_INO_ZAPPED)));
trace_xfs_inode_mark_healthy(ip, mask);
spin_lock(&ip->i_flags_lock);
@@ -369,6 +369,10 @@ static const struct ioctl_sick_map ino_map[] = {
{ XFS_SICK_INO_XATTR, XFS_BS_SICK_XATTR },
{ XFS_SICK_INO_SYMLINK, XFS_BS_SICK_SYMLINK },
{ XFS_SICK_INO_PARENT, XFS_BS_SICK_PARENT },
+ { XFS_SICK_INO_BMBTD_ZAPPED, XFS_BS_SICK_BMBTD },
+ { XFS_SICK_INO_BMBTA_ZAPPED, XFS_BS_SICK_BMBTA },
+ { XFS_SICK_INO_DIR_ZAPPED, XFS_BS_SICK_DIR },
+ { XFS_SICK_INO_SYMLINK_ZAPPED, XFS_BS_SICK_SYMLINK },
{ 0, 0 },
};
diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c
index c0f1c89786c2..ea6b277485a4 100644
--- a/fs/xfs/xfs_inode.c
+++ b/fs/xfs/xfs_inode.c
@@ -37,6 +37,7 @@
#include "xfs_reflink.h"
#include "xfs_ag.h"
#include "xfs_log_priv.h"
+#include "xfs_health.h"
struct kmem_cache *xfs_inode_cache;
@@ -661,6 +662,8 @@ xfs_lookup(
if (xfs_is_shutdown(dp->i_mount))
return -EIO;
+ if (xfs_ifork_zapped(dp, XFS_DATA_FORK))
+ return -EIO;
error = xfs_dir_lookup(NULL, dp, name, &inum, ci_name);
if (error)
@@ -978,6 +981,8 @@ xfs_create(
if (xfs_is_shutdown(mp))
return -EIO;
+ if (xfs_ifork_zapped(dp, XFS_DATA_FORK))
+ return -EIO;
prid = xfs_get_initial_prid(dp);
@@ -1217,6 +1222,8 @@ xfs_link(
if (xfs_is_shutdown(mp))
return -EIO;
+ if (xfs_ifork_zapped(tdp, XFS_DATA_FORK))
+ return -EIO;
error = xfs_qm_dqattach(sip);
if (error)
@@ -2506,6 +2513,8 @@ xfs_remove(
if (xfs_is_shutdown(mp))
return -EIO;
+ if (xfs_ifork_zapped(dp, XFS_DATA_FORK))
+ return -EIO;
error = xfs_qm_dqattach(dp);
if (error)
@@ -3758,3 +3767,29 @@ xfs_inode_reload_unlinked(
return error;
}
+
+/* Has this inode fork been zapped by repair? */
+bool
+xfs_ifork_zapped(
+ const struct xfs_inode *ip,
+ int whichfork)
+{
+ unsigned int datamask = 0;
+
+ switch (whichfork) {
+ case XFS_DATA_FORK:
+ switch (ip->i_vnode.i_mode & S_IFMT) {
+ case S_IFDIR:
+ datamask = XFS_SICK_INO_DIR_ZAPPED;
+ break;
+ case S_IFLNK:
+ datamask = XFS_SICK_INO_SYMLINK_ZAPPED;
+ break;
+ }
+ return ip->i_sick & (XFS_SICK_INO_BMBTD_ZAPPED | datamask);
+ case XFS_ATTR_FORK:
+ return ip->i_sick & XFS_SICK_INO_BMBTA_ZAPPED;
+ default:
+ return false;
+ }
+}
diff --git a/fs/xfs/xfs_inode.h b/fs/xfs/xfs_inode.h
index 3beb470f1892..97f63bacd4c2 100644
--- a/fs/xfs/xfs_inode.h
+++ b/fs/xfs/xfs_inode.h
@@ -622,4 +622,6 @@ xfs_inode_unlinked_incomplete(
int xfs_inode_reload_unlinked_bucket(struct xfs_trans *tp, struct xfs_inode *ip);
int xfs_inode_reload_unlinked(struct xfs_inode *ip);
+bool xfs_ifork_zapped(const struct xfs_inode *ip, int whichfork);
+
#endif /* __XFS_INODE_H__ */
diff --git a/fs/xfs/xfs_symlink.c b/fs/xfs/xfs_symlink.c
index 85e433df6a3f..7c713727f7fd 100644
--- a/fs/xfs/xfs_symlink.c
+++ b/fs/xfs/xfs_symlink.c
@@ -23,6 +23,7 @@
#include "xfs_trans.h"
#include "xfs_ialloc.h"
#include "xfs_error.h"
+#include "xfs_health.h"
/* ----- Kernel only functions below ----- */
int
@@ -108,6 +109,8 @@ xfs_readlink(
if (xfs_is_shutdown(mp))
return -EIO;
+ if (xfs_ifork_zapped(ip, XFS_DATA_FORK))
+ return -EIO;
xfs_ilock(ip, XFS_ILOCK_SHARED);
diff --git a/fs/xfs/xfs_xattr.c b/fs/xfs/xfs_xattr.c
index 987843f84d03..364104e1b38a 100644
--- a/fs/xfs/xfs_xattr.c
+++ b/fs/xfs/xfs_xattr.c
@@ -136,6 +136,9 @@ xfs_xattr_get(const struct xattr_handler *handler, struct dentry *unused,
};
int error;
+ if (xfs_ifork_zapped(XFS_I(inode), XFS_ATTR_FORK))
+ return -EIO;
+
error = xfs_attr_get(&args);
if (error)
return error;
@@ -294,6 +297,9 @@ xfs_vn_listxattr(
struct inode *inode = d_inode(dentry);
int error;
+ if (xfs_ifork_zapped(XFS_I(inode), XFS_ATTR_FORK))
+ return -EIO;
+
/*
* First read the regular on-disk attributes.
*/