@@ -172,6 +172,19 @@ config XFS_ONLINE_SCRUB_STATS
If unsure, say N.
+config XFS_ONLINE_SCRUB_WHINE
+ bool "XFS online metadata verbose logging by default"
+ default y
+ depends on XFS_ONLINE_SCRUB
+ help
+ If you say Y here, the kernel will by default log the outcomes of all
+ scrub and repair operations, as well as any corruptions found. This
+ may slow down scrub due to printk logging overhead timers.
+
+ This value can be changed by editing /sys/fs/xfs/debug/scrub_whine
+
+ If unsure, say N.
+
choice
prompt "XFS hook implementation"
depends on XFS_FS && XFS_LIVE_HOOKS && XFS_ONLINE_SCRUB
@@ -11,6 +11,8 @@
#include "xfs_mount.h"
#include "xfs_inode.h"
#include "xfs_btree.h"
+#include "xfs_log_format.h"
+#include "xfs_ag.h"
#include "scrub/scrub.h"
#include "scrub/common.h"
#include "scrub/btree.h"
@@ -18,6 +20,62 @@
/* btree scrubbing */
+/* Figure out which block the btree cursor was pointing to. */
+static inline xfs_fsblock_t
+xchk_btree_cur_fsbno(
+ struct xfs_btree_cur *cur,
+ int level)
+{
+ if (level < cur->bc_nlevels && cur->bc_levels[level].bp)
+ return XFS_DADDR_TO_FSB(cur->bc_mp,
+ xfs_buf_daddr(cur->bc_levels[level].bp));
+ else if (level == cur->bc_nlevels - 1 &&
+ (cur->bc_flags & XFS_BTREE_ROOT_IN_INODE))
+ return XFS_INO_TO_FSB(cur->bc_mp, cur->bc_ino.ip->i_ino);
+ else if (!(cur->bc_flags & XFS_BTREE_LONG_PTRS))
+ return XFS_AGB_TO_FSB(cur->bc_mp, cur->bc_ag.pag->pag_agno, 0);
+ return NULLFSBLOCK;
+}
+
+static inline void
+process_error_whine(
+ struct xfs_scrub *sc,
+ struct xfs_btree_cur *cur,
+ int level,
+ int *error,
+ __u32 errflag,
+ void *ret_ip)
+{
+ xfs_fsblock_t fsbno = xchk_btree_cur_fsbno(cur, level);
+
+ if (cur->bc_flags & XFS_BTREE_ROOT_IN_INODE) {
+ xchk_whine(sc->mp, "ino 0x%llx fork %d type %s btnum %d level %d ptr %d agno 0x%x agbno 0x%x error %d errflag 0x%x ret_ip %pS",
+ cur->bc_ino.ip->i_ino,
+ cur->bc_ino.whichfork,
+ xchk_type_string(sc->sm->sm_type),
+ cur->bc_btnum,
+ level,
+ cur->bc_levels[level].ptr,
+ XFS_FSB_TO_AGNO(cur->bc_mp, fsbno),
+ XFS_FSB_TO_AGBNO(cur->bc_mp, fsbno),
+ *error,
+ errflag,
+ ret_ip);
+ return;
+ }
+
+ xchk_whine(sc->mp, "type %s btnum %d level %d ptr %d agno 0x%x agbno 0x%x error %d errflag 0x%x ret_ip %pS",
+ xchk_type_string(sc->sm->sm_type),
+ cur->bc_btnum,
+ level,
+ cur->bc_levels[level].ptr,
+ XFS_FSB_TO_AGNO(cur->bc_mp, fsbno),
+ XFS_FSB_TO_AGBNO(cur->bc_mp, fsbno),
+ *error,
+ errflag,
+ ret_ip);
+}
+
/*
* Check for btree operation errors. See the section about handling
* operational errors in common.c.
@@ -44,9 +102,13 @@ __xchk_btree_process_error(
case -EFSCORRUPTED:
/* Note the badness but don't abort. */
sc->sm->sm_flags |= errflag;
+ process_error_whine(sc, cur, level, error, errflag, ret_ip);
*error = 0;
fallthrough;
default:
+ if (*error)
+ process_error_whine(sc, cur, level, error, errflag,
+ ret_ip);
if (cur->bc_flags & XFS_BTREE_ROOT_IN_INODE)
trace_xchk_ifork_btree_op_error(sc, cur, level,
*error, ret_ip);
@@ -92,11 +154,37 @@ __xchk_btree_set_corrupt(
sc->sm->sm_flags |= errflag;
if (cur->bc_flags & XFS_BTREE_ROOT_IN_INODE)
+ {
+ xfs_fsblock_t fsbno = xchk_btree_cur_fsbno(cur, level);
+ xchk_whine(sc->mp, "ino 0x%llx fork %d type %s btnum %d level %d ptr %d agno 0x%x agbno 0x%x errflag 0x%x ret_ip %pS",
+ cur->bc_ino.ip->i_ino,
+ cur->bc_ino.whichfork,
+ xchk_type_string(sc->sm->sm_type),
+ cur->bc_btnum,
+ level,
+ cur->bc_levels[level].ptr,
+ XFS_FSB_TO_AGNO(cur->bc_mp, fsbno),
+ XFS_FSB_TO_AGBNO(cur->bc_mp, fsbno),
+ errflag,
+ ret_ip);
trace_xchk_ifork_btree_error(sc, cur, level,
ret_ip);
+ }
else
+ {
+ xfs_fsblock_t fsbno = xchk_btree_cur_fsbno(cur, level);
+ xchk_whine(sc->mp, "type %s btnum %d level %d ptr %d agno 0x%x agbno 0x%x errflag 0x%x ret_ip %pS",
+ xchk_type_string(sc->sm->sm_type),
+ cur->bc_btnum,
+ level,
+ cur->bc_levels[level].ptr,
+ XFS_FSB_TO_AGNO(cur->bc_mp, fsbno),
+ XFS_FSB_TO_AGBNO(cur->bc_mp, fsbno),
+ errflag,
+ ret_ip);
trace_xchk_btree_error(sc, cur, level,
ret_ip);
+ }
}
void
@@ -105,9 +105,23 @@ __xchk_process_error(
case -EFSCORRUPTED:
/* Note the badness but don't abort. */
sc->sm->sm_flags |= errflag;
+ xchk_whine(sc->mp, "type %s agno 0x%x agbno 0x%x error %d errflag 0x%x ret_ip %pS",
+ xchk_type_string(sc->sm->sm_type),
+ agno,
+ bno,
+ *error,
+ errflag,
+ ret_ip);
*error = 0;
fallthrough;
default:
+ if (*error)
+ xchk_whine(sc->mp, "type %s agno 0x%x agbno 0x%x error %d ret_ip %pS",
+ xchk_type_string(sc->sm->sm_type),
+ agno,
+ bno,
+ *error,
+ ret_ip);
trace_xchk_op_error(sc, agno, bno, *error, ret_ip);
break;
}
@@ -190,9 +204,25 @@ __xchk_fblock_process_error(
case -EFSCORRUPTED:
/* Note the badness but don't abort. */
sc->sm->sm_flags |= errflag;
+ xchk_whine(sc->mp, "ino 0x%llx fork %d type %s offset %llu error %d errflag 0x%x ret_ip %pS",
+ sc->ip->i_ino,
+ whichfork,
+ xchk_type_string(sc->sm->sm_type),
+ offset,
+ *error,
+ errflag,
+ ret_ip);
*error = 0;
fallthrough;
default:
+ if (*error)
+ xchk_whine(sc->mp, "ino 0x%llx fork %d type %s offset %llu error %d ret_ip %pS",
+ sc->ip->i_ino,
+ whichfork,
+ xchk_type_string(sc->sm->sm_type),
+ offset,
+ *error,
+ ret_ip);
trace_xchk_file_op_error(sc, whichfork, offset, *error,
ret_ip);
break;
@@ -264,6 +294,8 @@ xchk_set_corrupt(
struct xfs_scrub *sc)
{
sc->sm->sm_flags |= XFS_SCRUB_OFLAG_CORRUPT;
+ xchk_whine(sc->mp, "type %s ret_ip %pS", xchk_type_string(sc->sm->sm_type),
+ __return_address);
trace_xchk_fs_error(sc, 0, __return_address);
}
@@ -275,6 +307,11 @@ xchk_block_set_corrupt(
{
sc->sm->sm_flags |= XFS_SCRUB_OFLAG_CORRUPT;
trace_xchk_block_error(sc, xfs_buf_daddr(bp), __return_address);
+ xchk_whine(sc->mp, "type %s agno 0x%x agbno 0x%x ret_ip %pS",
+ xchk_type_string(sc->sm->sm_type),
+ xfs_daddr_to_agno(sc->mp, xfs_buf_daddr(bp)),
+ xfs_daddr_to_agbno(sc->mp, xfs_buf_daddr(bp)),
+ __return_address);
}
#ifdef CONFIG_XFS_QUOTA
@@ -286,6 +323,8 @@ xchk_qcheck_set_corrupt(
xfs_dqid_t id)
{
sc->sm->sm_flags |= XFS_SCRUB_OFLAG_CORRUPT;
+ xchk_whine(sc->mp, "type %s dqtype %u id %u ret_ip %pS",
+ xchk_type_string(sc->sm->sm_type), dqtype, id, __return_address);
trace_xchk_qcheck_error(sc, dqtype, id, __return_address);
}
#endif /* CONFIG_XFS_QUOTA */
@@ -298,6 +337,11 @@ xchk_block_xref_set_corrupt(
{
sc->sm->sm_flags |= XFS_SCRUB_OFLAG_XCORRUPT;
trace_xchk_block_error(sc, xfs_buf_daddr(bp), __return_address);
+ xchk_whine(sc->mp, "type %s agno 0x%x agbno 0x%x ret_ip %pS",
+ xchk_type_string(sc->sm->sm_type),
+ xfs_daddr_to_agno(sc->mp, xfs_buf_daddr(bp)),
+ xfs_daddr_to_agbno(sc->mp, xfs_buf_daddr(bp)),
+ __return_address);
}
/*
@@ -311,6 +355,8 @@ xchk_ino_set_corrupt(
xfs_ino_t ino)
{
sc->sm->sm_flags |= XFS_SCRUB_OFLAG_CORRUPT;
+ xchk_whine(sc->mp, "ino 0x%llx type %s ret_ip %pS",
+ ino, xchk_type_string(sc->sm->sm_type), __return_address);
trace_xchk_ino_error(sc, ino, __return_address);
}
@@ -321,6 +367,8 @@ xchk_ino_xref_set_corrupt(
xfs_ino_t ino)
{
sc->sm->sm_flags |= XFS_SCRUB_OFLAG_XCORRUPT;
+ xchk_whine(sc->mp, "ino 0x%llx type %s ret_ip %pS",
+ ino, xchk_type_string(sc->sm->sm_type), __return_address);
trace_xchk_ino_error(sc, ino, __return_address);
}
@@ -332,6 +380,12 @@ xchk_fblock_set_corrupt(
xfs_fileoff_t offset)
{
sc->sm->sm_flags |= XFS_SCRUB_OFLAG_CORRUPT;
+ xchk_whine(sc->mp, "ino 0x%llx fork %d type %s offset %llu ret_ip %pS",
+ sc->ip->i_ino,
+ whichfork,
+ xchk_type_string(sc->sm->sm_type),
+ offset,
+ __return_address);
trace_xchk_fblock_error(sc, whichfork, offset, __return_address);
}
@@ -343,6 +397,12 @@ xchk_fblock_xref_set_corrupt(
xfs_fileoff_t offset)
{
sc->sm->sm_flags |= XFS_SCRUB_OFLAG_XCORRUPT;
+ xchk_whine(sc->mp, "ino 0x%llx fork %d type %s offset %llu ret_ip %pS",
+ sc->ip->i_ino,
+ whichfork,
+ xchk_type_string(sc->sm->sm_type),
+ offset,
+ __return_address);
trace_xchk_fblock_error(sc, whichfork, offset, __return_address);
}
@@ -356,6 +416,8 @@ xchk_ino_set_warning(
xfs_ino_t ino)
{
sc->sm->sm_flags |= XFS_SCRUB_OFLAG_WARNING;
+ xchk_whine(sc->mp, "ino 0x%llx type %s ret_ip %pS",
+ ino, xchk_type_string(sc->sm->sm_type), __return_address);
trace_xchk_ino_warning(sc, ino, __return_address);
}
@@ -367,6 +429,12 @@ xchk_fblock_set_warning(
xfs_fileoff_t offset)
{
sc->sm->sm_flags |= XFS_SCRUB_OFLAG_WARNING;
+ xchk_whine(sc->mp, "ino 0x%llx fork %d type %s offset %llu ret_ip %pS",
+ sc->ip->i_ino,
+ whichfork,
+ xchk_type_string(sc->sm->sm_type),
+ offset,
+ __return_address);
trace_xchk_fblock_warning(sc, whichfork, offset, __return_address);
}
@@ -1312,6 +1380,10 @@ xchk_iget_for_scrubbing(
out_cancel:
xchk_trans_cancel(sc);
out_error:
+ xchk_whine(mp, "type %s agno 0x%x agbno 0x%x error %d ret_ip %pS",
+ xchk_type_string(sc->sm->sm_type), agno,
+ XFS_INO_TO_AGBNO(mp, sc->sm->sm_ino), error,
+ __return_address);
trace_xchk_op_error(sc, agno, XFS_INO_TO_AGBNO(mp, sc->sm->sm_ino),
error, __return_address);
return error;
@@ -1453,6 +1525,10 @@ xchk_should_check_xref(
}
sc->sm->sm_flags |= XFS_SCRUB_OFLAG_XFAIL;
+ xchk_whine(sc->mp, "type %s xref error %d ret_ip %pS",
+ xchk_type_string(sc->sm->sm_type),
+ *error,
+ __return_address);
trace_xchk_xref_error(sc, *error, __return_address);
/*
@@ -1484,6 +1560,11 @@ xchk_buffer_recheck(
return;
sc->sm->sm_flags |= XFS_SCRUB_OFLAG_CORRUPT;
trace_xchk_block_error(sc, xfs_buf_daddr(bp), fa);
+ xchk_whine(sc->mp, "type %s agno 0x%x agbno 0x%x ret_ip %pS",
+ xchk_type_string(sc->sm->sm_type),
+ xfs_daddr_to_agno(sc->mp, xfs_buf_daddr(bp)),
+ xfs_daddr_to_agbno(sc->mp, xfs_buf_daddr(bp)),
+ fa);
}
static inline int
@@ -1793,3 +1874,29 @@ xchk_inode_count_blocks(
*count = btblocks - 1;
return 0;
}
+
+/* Complain about failures... */
+void
+xchk_whine(
+ const struct xfs_mount *mp,
+ const char *fmt,
+ ...)
+{
+ struct va_format vaf;
+ va_list args;
+
+ if (!xfs_globals.scrub_whine)
+ return;
+
+ va_start(args, fmt);
+
+ vaf.fmt = fmt;
+ vaf.va = &args;
+
+ printk(KERN_INFO "XFS (%s) %pS: %pV\n", mp->m_super->s_id,
+ __return_address, &vaf);
+ va_end(args);
+
+ if (xfs_error_level >= XFS_ERRLEVEL_HIGH)
+ xfs_stack_trace();
+}
@@ -188,6 +188,7 @@ bool xchk_ilock_nowait(struct xfs_scrub *sc, unsigned int ilock_flags);
void xchk_iunlock(struct xfs_scrub *sc, unsigned int ilock_flags);
void xchk_buffer_recheck(struct xfs_scrub *sc, struct xfs_buf *bp);
+void xchk_whine(const struct xfs_mount *mp, const char *fmt, ...);
/*
* Grab the inode at @inum. The caller must have created a scrub transaction
@@ -47,9 +47,26 @@ xchk_da_process_error(
case -EFSCORRUPTED:
/* Note the badness but don't abort. */
sc->sm->sm_flags |= XFS_SCRUB_OFLAG_CORRUPT;
+ xchk_whine(sc->mp, "ino 0x%llx fork %d type %s dablk 0x%llx error %d ret_ip %pS",
+ sc->ip->i_ino,
+ ds->dargs.whichfork,
+ xchk_type_string(sc->sm->sm_type),
+ xfs_dir2_da_to_db(ds->dargs.geo,
+ ds->state->path.blk[level].blkno),
+ *error,
+ __return_address);
*error = 0;
fallthrough;
default:
+ if (*error)
+ xchk_whine(sc->mp, "ino 0x%llx fork %d type %s dablk 0x%llx error %d ret_ip %pS",
+ sc->ip->i_ino,
+ ds->dargs.whichfork,
+ xchk_type_string(sc->sm->sm_type),
+ xfs_dir2_da_to_db(ds->dargs.geo,
+ ds->state->path.blk[level].blkno),
+ *error,
+ __return_address);
trace_xchk_file_op_error(sc, ds->dargs.whichfork,
xfs_dir2_da_to_db(ds->dargs.geo,
ds->state->path.blk[level].blkno),
@@ -72,6 +89,13 @@ xchk_da_set_corrupt(
sc->sm->sm_flags |= XFS_SCRUB_OFLAG_CORRUPT;
+ xchk_whine(sc->mp, "ino 0x%llx fork %d type %s dablk 0x%llx ret_ip %pS",
+ sc->ip->i_ino,
+ ds->dargs.whichfork,
+ xchk_type_string(sc->sm->sm_type),
+ xfs_dir2_da_to_db(ds->dargs.geo,
+ ds->state->path.blk[level].blkno),
+ __return_address);
trace_xchk_fblock_error(sc, ds->dargs.whichfork,
xfs_dir2_da_to_db(ds->dargs.geo,
ds->state->path.blk[level].blkno),
@@ -217,6 +217,10 @@ xchk_setup_inode(
out_cancel:
xchk_trans_cancel(sc);
out_error:
+ xchk_whine(mp, "type %s agno 0x%x agbno 0x%x error %d ret_ip %pS",
+ xchk_type_string(sc->sm->sm_type), agno,
+ XFS_INO_TO_AGBNO(mp, sc->sm->sm_ino), error,
+ __return_address);
trace_xchk_op_error(sc, agno, XFS_INO_TO_AGBNO(mp, sc->sm->sm_ino),
error, __return_address);
return error;
@@ -632,6 +632,45 @@ xchk_scrub_create_subord(
return sub;
}
+static inline void
+repair_outcomes(struct xfs_scrub *sc, int error)
+{
+ struct xfs_scrub_metadata *sm = sc->sm;
+ const char *wut = NULL;
+
+ if (!xfs_globals.scrub_whine)
+ return;
+
+ if (sc->flags & XREP_ALREADY_FIXED) {
+ wut = "*** REPAIR SUCCESS";
+ error = 0;
+ } else if (error == -EBUSY) {
+ wut = "??? FILESYSTEM BUSY";
+ } else if (error == -EAGAIN) {
+ wut = "??? REPAIR DEFERRED";
+ } else if (error == -ECANCELED) {
+ wut = "??? REPAIR CANCELLED";
+ } else if (error == -EINTR) {
+ wut = "??? REPAIR INTERRUPTED";
+ } else if (error != -EOPNOTSUPP && error != -ENOENT) {
+ wut = "!!! REPAIR FAILED";
+ xfs_info(sc->mp,
+"%s ino 0x%llx type %s agno 0x%x inum 0x%llx gen 0x%x flags 0x%x error %d",
+ wut, XFS_I(file_inode(sc->file))->i_ino,
+ xchk_type_string(sm->sm_type), sm->sm_agno,
+ sm->sm_ino, sm->sm_gen, sm->sm_flags, error);
+ return;
+ } else {
+ return;
+ }
+
+ xfs_info_ratelimited(sc->mp,
+"%s ino 0x%llx type %s agno 0x%x inum 0x%llx gen 0x%x flags 0x%x error %d",
+ wut, XFS_I(file_inode(sc->file))->i_ino,
+ xchk_type_string(sm->sm_type), sm->sm_agno, sm->sm_ino,
+ sm->sm_gen, sm->sm_flags, error);
+}
+
/* Dispatch metadata scrubbing. */
int
xfs_scrub_metadata(
@@ -729,6 +768,7 @@ xfs_scrub_metadata(
* already tried to fix it, then attempt a repair.
*/
error = xrep_attempt(sc, &run);
+ repair_outcomes(sc, error);
if (error == -EAGAIN) {
/*
* Either the repair function succeeded or it couldn't
@@ -69,3 +69,25 @@ xfbtree_ino(
*/
#define CREATE_TRACE_POINTS
#include "scrub/trace.h"
+
+/* xchk_whine stuff */
+struct xchk_tstr {
+ unsigned int type;
+ const char *tag;
+};
+
+static const struct xchk_tstr xchk_tstr_tags[] = { XFS_SCRUB_TYPE_STRINGS };
+
+const char *
+xchk_type_string(
+ unsigned int type)
+{
+ unsigned int i;
+
+ for (i = 0; i < ARRAY_SIZE(xchk_tstr_tags); i++) {
+ if (xchk_tstr_tags[i].type == type)
+ return xchk_tstr_tags[i].tag;
+ }
+
+ return "???";
+}
@@ -127,6 +127,8 @@ TRACE_DEFINE_ENUM(XFS_SCRUB_TYPE_RTREFCBT);
{ XFS_SCRUB_TYPE_RTRMAPBT, "rtrmapbt" }, \
{ XFS_SCRUB_TYPE_RTREFCBT, "rtrefcountbt" }
+const char *xchk_type_string(unsigned int type);
+
#define XFS_SCRUB_FLAG_STRINGS \
{ XFS_SCRUB_IFLAG_REPAIR, "repair" }, \
{ XFS_SCRUB_OFLAG_CORRUPT, "corrupt" }, \
@@ -44,6 +44,11 @@ struct xfs_globals xfs_globals = {
.pwork_threads = -1, /* automatic thread detection */
.larp = false, /* log attribute replay */
#endif
+#ifdef CONFIG_XFS_ONLINE_SCRUB_WHINE
+ .scrub_whine = true,
+#else
+ .scrub_whine = false,
+#endif
/*
* Leave this many record slots empty when bulk loading btrees. By
@@ -91,6 +91,7 @@ struct xfs_globals {
int mount_delay; /* mount setup delay (secs) */
bool bug_on_assert; /* BUG() the kernel on assert failure */
bool always_cow; /* use COW fork for all overwrites */
+ bool scrub_whine; /* noisier output from scrub */
};
extern struct xfs_globals xfs_globals;
@@ -262,6 +262,37 @@ larp_show(
XFS_SYSFS_ATTR_RW(larp);
#endif /* DEBUG */
+/* Logging of the outcomes of everything that scrub does */
+STATIC ssize_t
+scrub_whine_store(
+ struct kobject *kobject,
+ const char *buf,
+ size_t count)
+{
+ int ret;
+ int val;
+
+ ret = kstrtoint(buf, 0, &val);
+ if (ret)
+ return ret;
+
+ if (val < -1 || val > num_possible_cpus())
+ return -EINVAL;
+
+ xfs_globals.scrub_whine = val;
+
+ return count;
+}
+
+STATIC ssize_t
+scrub_whine_show(
+ struct kobject *kobject,
+ char *buf)
+{
+ return sysfs_emit(buf, "%d\n", xfs_globals.scrub_whine);
+}
+XFS_SYSFS_ATTR_RW(scrub_whine);
+
STATIC ssize_t
bload_leaf_slack_store(
struct kobject *kobject,
@@ -323,6 +354,7 @@ static struct attribute *xfs_dbg_attrs[] = {
ATTR_LIST(pwork_threads),
ATTR_LIST(larp),
#endif
+ ATTR_LIST(scrub_whine),
ATTR_LIST(bload_leaf_slack),
ATTR_LIST(bload_node_slack),
NULL,