xfs: add online scrub for superblock counters

Teach online scrub how to check the filesystem summary counters.  We use
the incore delalloc block counter along with the incore AG headers to
compute expected values for fdblocks, icount, and ifree, and then check
that the percpu counter is within a certain threshold of the expected
value.  This is done to avoid having to freeze or otherwise lock the
filesystem, which means that we're only checking that the counters are
fairly close, not that they're exactly correct.
Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
Reviewed-by: Dave Chinner <dchinner@redhat.com>
Reviewed-by: Brian Foster <bfoster@redhat.com>

fs/xfs/Makefile

@@ -143,6 +143,7 @@ xfs-y				+= $(addprefix scrub/, \
 				   common.o \
 				   dabtree.o \
 				   dir.o \
+				   fscounters.o \
 				   health.o \
 				   ialloc.o \
 				   inode.o \

fs/xfs/libxfs/xfs_fs.h

@@ -578,9 +578,10 @@ struct xfs_scrub_metadata {
 #define XFS_SCRUB_TYPE_UQUOTA	21	/* user quotas */
 #define XFS_SCRUB_TYPE_GQUOTA	22	/* group quotas */
 #define XFS_SCRUB_TYPE_PQUOTA	23	/* project quotas */
+#define XFS_SCRUB_TYPE_FSCOUNTERS 24	/* fs summary counters */
 
 /* Number of scrub subcommands. */
-#define XFS_SCRUB_TYPE_NR	24
+#define XFS_SCRUB_TYPE_NR	25
 
 /* i: Repair this metadata. */
 #define XFS_SCRUB_IFLAG_REPAIR		(1 << 0)

fs/xfs/libxfs/xfs_types.c

@@ -185,7 +185,7 @@ xfs_verify_rtbno(
 }
 
 /* Calculate the range of valid icount values. */
-static void
+void
 xfs_icount_range(
 	struct xfs_mount	*mp,
 	unsigned long long	*min,

fs/xfs/libxfs/xfs_types.h

@@ -191,5 +191,7 @@ bool xfs_verify_dir_ino(struct xfs_mount *mp, xfs_ino_t ino);
 bool xfs_verify_rtbno(struct xfs_mount *mp, xfs_rtblock_t rtbno);
 bool xfs_verify_icount(struct xfs_mount *mp, unsigned long long icount);
 bool xfs_verify_dablk(struct xfs_mount *mp, xfs_fileoff_t off);
+void xfs_icount_range(struct xfs_mount *mp, unsigned long long *min,
+		unsigned long long *max);
 
 #endif	/* __XFS_TYPES_H__ */

fs/xfs/scrub/common.c

@@ -209,6 +209,15 @@ xchk_ino_set_preen(
 	trace_xchk_ino_preen(sc, ino, __return_address);
 }
 
+/* Record something being wrong with the filesystem primary superblock. */
+void
+xchk_set_corrupt(
+	struct xfs_scrub	*sc)
+{
+	sc->sm->sm_flags |= XFS_SCRUB_OFLAG_CORRUPT;
+	trace_xchk_fs_error(sc, 0, __return_address);
+}
+
 /* Record a corrupt block. */
 void
 xchk_block_set_corrupt(

fs/xfs/scrub/common.h

@@ -39,6 +39,7 @@ void xchk_block_set_preen(struct xfs_scrub *sc,
 		struct xfs_buf *bp);
 void xchk_ino_set_preen(struct xfs_scrub *sc, xfs_ino_t ino);
 
+void xchk_set_corrupt(struct xfs_scrub *sc);
 void xchk_block_set_corrupt(struct xfs_scrub *sc,
 		struct xfs_buf *bp);
 void xchk_ino_set_corrupt(struct xfs_scrub *sc, xfs_ino_t ino);
@@ -105,6 +106,7 @@ xchk_setup_quota(struct xfs_scrub *sc, struct xfs_inode *ip)
 	return -ENOENT;
 }
 #endif
+int xchk_setup_fscounters(struct xfs_scrub *sc, struct xfs_inode *ip);
 
 void xchk_ag_free(struct xfs_scrub *sc, struct xchk_ag *sa);
 int xchk_ag_init(struct xfs_scrub *sc, xfs_agnumber_t agno,

fs/xfs/scrub/health.c

@@ -109,6 +109,7 @@ static const struct xchk_health_map type_to_health_flag[XFS_SCRUB_TYPE_NR] = {
 	[XFS_SCRUB_TYPE_UQUOTA]		= { XHG_FS,  XFS_SICK_FS_UQUOTA },
 	[XFS_SCRUB_TYPE_GQUOTA]		= { XHG_FS,  XFS_SICK_FS_GQUOTA },
 	[XFS_SCRUB_TYPE_PQUOTA]		= { XHG_FS,  XFS_SICK_FS_PQUOTA },
+	[XFS_SCRUB_TYPE_FSCOUNTERS]	= { XHG_FS,  XFS_SICK_FS_COUNTERS },
 };
 
 /* Return the health status mask for this scrub type. */

fs/xfs/scrub/scrub.c

@@ -352,6 +352,12 @@ static const struct xchk_meta_ops meta_scrub_ops[] = {
 		.scrub	= xchk_quota,
 		.repair	= xrep_notsupported,
 	},
+	[XFS_SCRUB_TYPE_FSCOUNTERS] = {	/* fs summary counters */
+		.type	= ST_FS,
+		.setup	= xchk_setup_fscounters,
+		.scrub	= xchk_fscounters,
+		.repair	= xrep_notsupported,
+	},
 };
 
 /* This isn't a stable feature, warn once per day. */

fs/xfs/scrub/scrub.h

@@ -127,6 +127,7 @@ xchk_quota(struct xfs_scrub *sc)
 	return -ENOENT;
 }
 #endif
+int xchk_fscounters(struct xfs_scrub *sc);
 
 /* cross-referencing helpers */
 void xchk_xref_is_used_space(struct xfs_scrub *sc, xfs_agblock_t agbno,
@@ -152,4 +153,12 @@ void xchk_xref_is_used_rt_space(struct xfs_scrub *sc, xfs_rtblock_t rtbno,
 # define xchk_xref_is_used_rt_space(sc, rtbno, len) do { } while (0)
 #endif
 
+struct xchk_fscounters {
+	uint64_t		icount;
+	uint64_t		ifree;
+	uint64_t		fdblocks;
+	unsigned long long	icount_min;
+	unsigned long long	icount_max;
+};
+
 #endif	/* __XFS_SCRUB_SCRUB_H__ */

fs/xfs/scrub/trace.h

@@ -50,6 +50,7 @@ TRACE_DEFINE_ENUM(XFS_SCRUB_TYPE_RTSUM);
 TRACE_DEFINE_ENUM(XFS_SCRUB_TYPE_UQUOTA);
 TRACE_DEFINE_ENUM(XFS_SCRUB_TYPE_GQUOTA);
 TRACE_DEFINE_ENUM(XFS_SCRUB_TYPE_PQUOTA);
+TRACE_DEFINE_ENUM(XFS_SCRUB_TYPE_FSCOUNTERS);
 
 #define XFS_SCRUB_TYPE_STRINGS \
 	{ XFS_SCRUB_TYPE_PROBE,		"probe" }, \
@@ -75,7 +76,8 @@ TRACE_DEFINE_ENUM(XFS_SCRUB_TYPE_PQUOTA);
 	{ XFS_SCRUB_TYPE_RTSUM,		"rtsummary" }, \
 	{ XFS_SCRUB_TYPE_UQUOTA,	"usrquota" }, \
 	{ XFS_SCRUB_TYPE_GQUOTA,	"grpquota" }, \
-	{ XFS_SCRUB_TYPE_PQUOTA,	"prjquota" }
+	{ XFS_SCRUB_TYPE_PQUOTA,	"prjquota" }, \
+	{ XFS_SCRUB_TYPE_FSCOUNTERS,	"fscounters" }
 
 DECLARE_EVENT_CLASS(xchk_class,
 	TP_PROTO(struct xfs_inode *ip, struct xfs_scrub_metadata *sm,
@@ -223,6 +225,7 @@ DEFINE_EVENT(xchk_block_error_class, name, \
 		 void *ret_ip), \
 	TP_ARGS(sc, daddr, ret_ip))
 
+DEFINE_SCRUB_BLOCK_ERROR_EVENT(xchk_fs_error);
 DEFINE_SCRUB_BLOCK_ERROR_EVENT(xchk_block_error);
 DEFINE_SCRUB_BLOCK_ERROR_EVENT(xchk_block_preen);
 
@@ -590,6 +593,64 @@ TRACE_EVENT(xchk_iallocbt_check_cluster,
 		  __entry->cluster_ino)
 )
 
+TRACE_EVENT(xchk_fscounters_calc,
+	TP_PROTO(struct xfs_mount *mp, uint64_t icount, uint64_t ifree,
+		 uint64_t fdblocks, uint64_t delalloc),
+	TP_ARGS(mp, icount, ifree, fdblocks, delalloc),
+	TP_STRUCT__entry(
+		__field(dev_t, dev)
+		__field(int64_t, icount_sb)
+		__field(uint64_t, icount_calculated)
+		__field(int64_t, ifree_sb)
+		__field(uint64_t, ifree_calculated)
+		__field(int64_t, fdblocks_sb)
+		__field(uint64_t, fdblocks_calculated)
+		__field(uint64_t, delalloc)
+	),
+	TP_fast_assign(
+		__entry->dev = mp->m_super->s_dev;
+		__entry->icount_sb = mp->m_sb.sb_icount;
+		__entry->icount_calculated = icount;
+		__entry->ifree_sb = mp->m_sb.sb_ifree;
+		__entry->ifree_calculated = ifree;
+		__entry->fdblocks_sb = mp->m_sb.sb_fdblocks;
+		__entry->fdblocks_calculated = fdblocks;
+		__entry->delalloc = delalloc;
+	),
+	TP_printk("dev %d:%d icount %lld:%llu ifree %lld::%llu fdblocks %lld::%llu delalloc %llu",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  __entry->icount_sb,
+		  __entry->icount_calculated,
+		  __entry->ifree_sb,
+		  __entry->ifree_calculated,
+		  __entry->fdblocks_sb,
+		  __entry->fdblocks_calculated,
+		  __entry->delalloc)
+)
+
+TRACE_EVENT(xchk_fscounters_within_range,
+	TP_PROTO(struct xfs_mount *mp, uint64_t expected, int64_t curr_value,
+		 int64_t old_value),
+	TP_ARGS(mp, expected, curr_value, old_value),
+	TP_STRUCT__entry(
+		__field(dev_t, dev)
+		__field(uint64_t, expected)
+		__field(int64_t, curr_value)
+		__field(int64_t, old_value)
+	),
+	TP_fast_assign(
+		__entry->dev = mp->m_super->s_dev;
+		__entry->expected = expected;
+		__entry->curr_value = curr_value;
+		__entry->old_value = old_value;
+	),
+	TP_printk("dev %d:%d expected %llu curr_value %lld old_value %lld",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  __entry->expected,
+		  __entry->curr_value,
+		  __entry->old_value)
+)
+
 /* repair tracepoints */
 #if IS_ENABLED(CONFIG_XFS_ONLINE_REPAIR)