Merge tag 'repair-quotacheck-6.9_2024-02-23' of https://git.kernel.org/pub/scm/linux/kernel/git/djwong/xfs-linux into xfs-6.9-mergeC

xfs: online repair of quota counters

This series uses the inode scanner and live update hook functionality
introduced in the last patchset to implement quotacheck on a live
filesystem.  The quotacheck scrubber builds an incore copy of the
dquot resource usage counters and compares it to the live dquots to
report discrepancies.

If the user chooses to repair the quota counters, the repair function
visits each incore dquot to update the counts from the live information.
The live update hooks are key to keeping the incore copy up to date.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
Signed-off-by: Chandan Babu R <chandanbabu@kernel.org>

* tag 'repair-quotacheck-6.9_2024-02-23' of https://git.kernel.org/pub/scm/linux/kernel/git/djwong/xfs-linux:
  xfs: repair dquots based on live quotacheck results
  xfs: repair cannot update the summary counters when logging quota flags
  xfs: track quota updates during live quotacheck
  xfs: implement live quotacheck inode scan
  xfs: create a sparse load xfarray function
  xfs: create a helper to count per-device inode block usage
  xfs: create a xchk_trans_alloc_empty helper for scrub
  xfs: report the health of quota counts

Author: Chandan Babu R

fs/xfs/Makefile

@@ -180,6 +180,7 @@ xfs-$(CONFIG_XFS_RT)		+= $(addprefix scrub/, \
 xfs-$(CONFIG_XFS_QUOTA)		+= $(addprefix scrub/, \
 				   dqiterate.o \
 				   quota.o \
+				   quotacheck.o \
 				   )
 
 # online repair
@@ -203,6 +204,7 @@ xfs-$(CONFIG_XFS_RT)		+= $(addprefix scrub/, \
 
 xfs-$(CONFIG_XFS_QUOTA)		+= $(addprefix scrub/, \
 				   quota_repair.o \
+				   quotacheck_repair.o \
 				   )
 endif
 endif

fs/xfs/libxfs/xfs_fs.h

@@ -195,6 +195,7 @@ struct xfs_fsop_geom {
 #define XFS_FSOP_GEOM_SICK_PQUOTA	(1 << 3)  /* project quota */
 #define XFS_FSOP_GEOM_SICK_RT_BITMAP	(1 << 4)  /* realtime bitmap */
 #define XFS_FSOP_GEOM_SICK_RT_SUMMARY	(1 << 5)  /* realtime summary */
+#define XFS_FSOP_GEOM_SICK_QUOTACHECK	(1 << 6)  /* quota counts */
 
 /* Output for XFS_FS_COUNTS */
 typedef struct xfs_fsop_counts {
@@ -709,9 +710,10 @@ struct xfs_scrub_metadata {
 #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 */
+#define XFS_SCRUB_TYPE_QUOTACHECK 25	/* quota counters */
 
 /* Number of scrub subcommands. */
-#define XFS_SCRUB_TYPE_NR	25
+#define XFS_SCRUB_TYPE_NR	26
 
 /* i: Repair this metadata. */
 #define XFS_SCRUB_IFLAG_REPAIR		(1u << 0)

fs/xfs/libxfs/xfs_health.h

@@ -41,6 +41,7 @@ struct xfs_fsop_geom;
 #define XFS_SICK_FS_UQUOTA	(1 << 1)  /* user quota */
 #define XFS_SICK_FS_GQUOTA	(1 << 2)  /* group quota */
 #define XFS_SICK_FS_PQUOTA	(1 << 3)  /* project quota */
+#define XFS_SICK_FS_QUOTACHECK	(1 << 4)  /* quota counts */
 
 /* Observable health issues for realtime volume metadata. */
 #define XFS_SICK_RT_BITMAP	(1 << 0)  /* realtime bitmap */
@@ -77,7 +78,8 @@ struct xfs_fsop_geom;
 #define XFS_SICK_FS_PRIMARY	(XFS_SICK_FS_COUNTERS | \
 				 XFS_SICK_FS_UQUOTA | \
 				 XFS_SICK_FS_GQUOTA | \
-				 XFS_SICK_FS_PQUOTA)
+				 XFS_SICK_FS_PQUOTA | \
+				 XFS_SICK_FS_QUOTACHECK)
 
 #define XFS_SICK_RT_PRIMARY	(XFS_SICK_RT_BITMAP | \
 				 XFS_SICK_RT_SUMMARY)

fs/xfs/scrub/common.c

@@ -29,6 +29,8 @@
 #include "xfs_attr.h"
 #include "xfs_reflink.h"
 #include "xfs_ag.h"
+#include "xfs_error.h"
+#include "xfs_quota.h"
 #include "scrub/scrub.h"
 #include "scrub/common.h"
 #include "scrub/trace.h"
@@ -82,15 +84,23 @@ __xchk_process_error(
 				sc->ip ? sc->ip : XFS_I(file_inode(sc->file)),
 				sc->sm, *error);
 		break;
+	case -ECANCELED:
+		/*
+		 * ECANCELED here means that the caller set one of the scrub
+		 * outcome flags (corrupt, xfail, xcorrupt) and wants to exit
+		 * quickly.  Set error to zero and do not continue.
+		 */
+		trace_xchk_op_error(sc, agno, bno, *error, ret_ip);
+		*error = 0;
+		break;
 	case -EFSBADCRC:
 	case -EFSCORRUPTED:
 		/* Note the badness but don't abort. */
 		sc->sm->sm_flags |= errflag;
 		*error = 0;
 		fallthrough;
 	default:
-		trace_xchk_op_error(sc, agno, bno, *error,
-				ret_ip);
+		trace_xchk_op_error(sc, agno, bno, *error, ret_ip);
 		break;
 	}
 	return false;
@@ -136,6 +146,16 @@ __xchk_fblock_process_error(
 		/* Used to restart an op with deadlock avoidance. */
 		trace_xchk_deadlock_retry(sc->ip, sc->sm, *error);
 		break;
+	case -ECANCELED:
+		/*
+		 * ECANCELED here means that the caller set one of the scrub
+		 * outcome flags (corrupt, xfail, xcorrupt) and wants to exit
+		 * quickly.  Set error to zero and do not continue.
+		 */
+		trace_xchk_file_op_error(sc, whichfork, offset, *error,
+				ret_ip);
+		*error = 0;
+		break;
 	case -EFSBADCRC:
 	case -EFSCORRUPTED:
 		/* Note the badness but don't abort. */
@@ -227,6 +247,19 @@ xchk_block_set_corrupt(
 	trace_xchk_block_error(sc, xfs_buf_daddr(bp), __return_address);
 }
 
+#ifdef CONFIG_XFS_QUOTA
+/* Record a corrupt quota counter. */
+void
+xchk_qcheck_set_corrupt(
+	struct xfs_scrub	*sc,
+	unsigned int		dqtype,
+	xfs_dqid_t		id)
+{
+	sc->sm->sm_flags |= XFS_SCRUB_OFLAG_CORRUPT;
+	trace_xchk_qcheck_error(sc, dqtype, id, __return_address);
+}
+#endif
+
 /* Record a corruption while cross-referencing. */
 void
 xchk_block_xref_set_corrupt(
@@ -653,6 +686,13 @@ xchk_trans_cancel(
 	sc->tp = NULL;
 }
 
+int
+xchk_trans_alloc_empty(
+	struct xfs_scrub	*sc)
+{
+	return xfs_trans_alloc_empty(sc->mp, &sc->tp);
+}
+
 /*
  * Grab an empty transaction so that we can re-grab locked buffers if
  * one of our btrees turns out to be cyclic.
@@ -672,7 +712,7 @@ xchk_trans_alloc(
 		return xfs_trans_alloc(sc->mp, &M_RES(sc->mp)->tr_itruncate,
 				resblks, 0, 0, &sc->tp);
 
-	return xfs_trans_alloc_empty(sc->mp, &sc->tp);
+	return xchk_trans_alloc_empty(sc);
 }
 
 /* Set us up with a transaction and an empty context. */
@@ -1259,6 +1299,9 @@ xchk_fsgates_enable(
 	if (scrub_fsgates & XCHK_FSGATES_DRAIN)
 		xfs_drain_wait_enable();
 
+	if (scrub_fsgates & XCHK_FSGATES_QUOTA)
+		xfs_dqtrx_hook_enable();
+
 	sc->flags |= scrub_fsgates;
 }
 

fs/xfs/scrub/common.h

@@ -32,6 +32,7 @@ xchk_should_terminate(
 }
 
 int xchk_trans_alloc(struct xfs_scrub *sc, uint resblks);
+int xchk_trans_alloc_empty(struct xfs_scrub *sc);
 void xchk_trans_cancel(struct xfs_scrub *sc);
 
 bool xchk_process_error(struct xfs_scrub *sc, xfs_agnumber_t agno,
@@ -54,6 +55,10 @@ void xchk_block_set_corrupt(struct xfs_scrub *sc,
 void xchk_ino_set_corrupt(struct xfs_scrub *sc, xfs_ino_t ino);
 void xchk_fblock_set_corrupt(struct xfs_scrub *sc, int whichfork,
 		xfs_fileoff_t offset);
+#ifdef CONFIG_XFS_QUOTA
+void xchk_qcheck_set_corrupt(struct xfs_scrub *sc, unsigned int dqtype,
+		xfs_dqid_t id);
+#endif
 
 void xchk_block_xref_set_corrupt(struct xfs_scrub *sc,
 		struct xfs_buf *bp);
@@ -105,6 +110,7 @@ xchk_setup_rtsummary(struct xfs_scrub *sc)
 #ifdef CONFIG_XFS_QUOTA
 int xchk_ino_dqattach(struct xfs_scrub *sc);
 int xchk_setup_quota(struct xfs_scrub *sc);
+int xchk_setup_quotacheck(struct xfs_scrub *sc);
 #else
 static inline int
 xchk_ino_dqattach(struct xfs_scrub *sc)
@@ -116,6 +122,11 @@ xchk_setup_quota(struct xfs_scrub *sc)
 {
 	return -ENOENT;
 }
+static inline int
+xchk_setup_quotacheck(struct xfs_scrub *sc)
+{
+	return -ENOENT;
+}
 #endif
 int xchk_setup_fscounters(struct xfs_scrub *sc);
 

fs/xfs/scrub/fscounters.c

@@ -242,7 +242,7 @@ xchk_setup_fscounters(
 			return error;
 	}
 
-	return xfs_trans_alloc_empty(sc->mp, &sc->tp);
+	return xchk_trans_alloc_empty(sc);
 }
 
 /*

fs/xfs/scrub/health.c

@@ -105,6 +105,7 @@ static const struct xchk_health_map type_to_health_flag[XFS_SCRUB_TYPE_NR] = {
 	[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 },
+	[XFS_SCRUB_TYPE_QUOTACHECK]	= { XHG_FS,  XFS_SICK_FS_QUOTACHECK },
 };
 
 /* Return the health status mask for this scrub type. */