xfs: reap large AG metadata extents when possible

When we're freeing extents that have been set in a bitmap, break the
bitmap extent into multiple sub-extents organized by fate, and reap the
extents.  This enables us to dispose of old resources more efficiently
than doing them block by block.

While we're at it, rename the reaping functions to make it clear that
they're reaping per-AG extents.
Signed-off-by: Darrick J. Wong <djwong@kernel.org>
Reviewed-by: Dave Chinner <dchinner@redhat.com>

fs/xfs/scrub/agheader_repair.c

@@ -775,7 +775,7 @@ xrep_agfl(
 		goto err;
 
 	/* Dump any AGFL overflow. */
-	error = xrep_reap_extents(sc, &agfl_extents, &XFS_RMAP_OINFO_AG,
+	error = xrep_reap_ag_metadata(sc, &agfl_extents, &XFS_RMAP_OINFO_AG,
 			XFS_AG_RESV_AGFL);
 err:
 	xbitmap_destroy(&agfl_extents);

fs/xfs/scrub/bitmap.c

@@ -385,43 +385,6 @@ xbitmap_walk(
 	return error;
 }
 
-struct xbitmap_walk_bits {
-	xbitmap_walk_bits_fn	fn;
-	void			*priv;
-};
-
-/* Walk all the bits in a run. */
-static int
-xbitmap_walk_bits_in_run(
-	uint64_t			start,
-	uint64_t			len,
-	void				*priv)
-{
-	struct xbitmap_walk_bits	*wb = priv;
-	uint64_t			i;
-	int				error = 0;
-
-	for (i = start; i < start + len; i++) {
-		error = wb->fn(i, wb->priv);
-		if (error)
-			break;
-	}
-
-	return error;
-}
-
-/* Call a function for every set bit in this bitmap. */
-int
-xbitmap_walk_bits(
-	struct xbitmap			*bitmap,
-	xbitmap_walk_bits_fn		fn,
-	void				*priv)
-{
-	struct xbitmap_walk_bits	wb = {.fn = fn, .priv = priv};
-
-	return xbitmap_walk(bitmap, xbitmap_walk_bits_in_run, &wb);
-}
-
 /* Does this bitmap have no bits set at all? */
 bool
 xbitmap_empty(

fs/xfs/scrub/bitmap.h

@@ -33,10 +33,6 @@ typedef int (*xbitmap_walk_fn)(uint64_t start, uint64_t len, void *priv);
 int xbitmap_walk(struct xbitmap *bitmap, xbitmap_walk_fn fn,
 		void *priv);
 
-typedef int (*xbitmap_walk_bits_fn)(uint64_t bit, void *priv);
-int xbitmap_walk_bits(struct xbitmap *bitmap, xbitmap_walk_bits_fn fn,
-		void *priv);
-
 bool xbitmap_empty(struct xbitmap *bitmap);
 bool xbitmap_test(struct xbitmap *bitmap, uint64_t start, uint64_t *len);
 

fs/xfs/scrub/reap.h

@@ -6,7 +6,7 @@
 #ifndef __XFS_SCRUB_REAP_H__
 #define __XFS_SCRUB_REAP_H__
 
-int xrep_reap_extents(struct xfs_scrub *sc, struct xbitmap *bitmap,
+int xrep_reap_ag_metadata(struct xfs_scrub *sc, struct xbitmap *bitmap,
 		const struct xfs_owner_info *oinfo,
 		enum xfs_ag_resv_type type);
 

fs/xfs/scrub/repair.c

@@ -26,6 +26,7 @@
 #include "xfs_ag_resv.h"
 #include "xfs_quota.h"
 #include "xfs_qm.h"
+#include "xfs_defer.h"
 #include "scrub/scrub.h"
 #include "scrub/common.h"
 #include "scrub/trace.h"
@@ -166,6 +167,56 @@ xrep_roll_ag_trans(
 	return 0;
 }
 
+/* Finish all deferred work attached to the repair transaction. */
+int
+xrep_defer_finish(
+	struct xfs_scrub	*sc)
+{
+	int			error;
+
+	/*
+	 * Keep the AG header buffers locked while we complete deferred work
+	 * items.  Ensure that both AG buffers are dirty and held when we roll
+	 * the transaction so that they move forward in the log without losing
+	 * the bli (and hence the bli type) when the transaction commits.
+	 *
+	 * Normal code would never hold clean buffers across a roll, but repair
+	 * needs both buffers to maintain a total lock on the AG.
+	 */
+	if (sc->sa.agi_bp) {
+		xfs_ialloc_log_agi(sc->tp, sc->sa.agi_bp, XFS_AGI_MAGICNUM);
+		xfs_trans_bhold(sc->tp, sc->sa.agi_bp);
+	}
+
+	if (sc->sa.agf_bp) {
+		xfs_alloc_log_agf(sc->tp, sc->sa.agf_bp, XFS_AGF_MAGICNUM);
+		xfs_trans_bhold(sc->tp, sc->sa.agf_bp);
+	}
+
+	/*
+	 * Finish all deferred work items.  We still hold the AG header buffers
+	 * locked regardless of whether or not that succeeds.  On failure, the
+	 * buffers will be released during teardown on our way out of the
+	 * kernel.  If successful, join the buffers to the new transaction
+	 * and move on.
+	 */
+	error = xfs_defer_finish(&sc->tp);
+	if (error)
+		return error;
+
+	/*
+	 * Release the hold that we set above because defer_finish won't do
+	 * that for us.  The defer roll code redirties held buffers after each
+	 * roll, so the AG header buffers should be ready for logging.
+	 */
+	if (sc->sa.agi_bp)
+		xfs_trans_bhold_release(sc->tp, sc->sa.agi_bp);
+	if (sc->sa.agf_bp)
+		xfs_trans_bhold_release(sc->tp, sc->sa.agf_bp);
+
+	return 0;
+}
+
 /*
  * Does the given AG have enough space to rebuild a btree?  Neither AG
  * reservation can be critical, and we must have enough space (factoring

fs/xfs/scrub/repair.h

@@ -15,11 +15,20 @@ static inline int xrep_notsupported(struct xfs_scrub *sc)
 
 #ifdef CONFIG_XFS_ONLINE_REPAIR
 
+/*
+ * This is the maximum number of deferred extent freeing item extents (EFIs)
+ * that we'll attach to a transaction without rolling the transaction to avoid
+ * overrunning a tr_itruncate reservation.
+ */
+#define XREP_MAX_ITRUNCATE_EFIS	(128)
+
+
 /* Repair helpers */
 
 int xrep_attempt(struct xfs_scrub *sc);
 void xrep_failure(struct xfs_mount *mp);
 int xrep_roll_ag_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);

fs/xfs/scrub/trace.h

@@ -753,10 +753,43 @@ DECLARE_EVENT_CLASS(xrep_extent_class,
 DEFINE_EVENT(xrep_extent_class, name, \
 	TP_PROTO(struct xfs_perag *pag, xfs_agblock_t agbno, xfs_extlen_t len), \
 	TP_ARGS(pag, agbno, len))
-DEFINE_REPAIR_EXTENT_EVENT(xrep_dispose_unmap_extent);
-DEFINE_REPAIR_EXTENT_EVENT(xrep_dispose_free_extent);
+DEFINE_REPAIR_EXTENT_EVENT(xreap_dispose_unmap_extent);
+DEFINE_REPAIR_EXTENT_EVENT(xreap_dispose_free_extent);
+DEFINE_REPAIR_EXTENT_EVENT(xreap_agextent_binval);
 DEFINE_REPAIR_EXTENT_EVENT(xrep_agfl_insert);
 
+DECLARE_EVENT_CLASS(xrep_reap_find_class,
+	TP_PROTO(struct xfs_perag *pag, xfs_agblock_t agbno, xfs_extlen_t len,
+		bool crosslinked),
+	TP_ARGS(pag, agbno, len, crosslinked),
+	TP_STRUCT__entry(
+		__field(dev_t, dev)
+		__field(xfs_agnumber_t, agno)
+		__field(xfs_agblock_t, agbno)
+		__field(xfs_extlen_t, len)
+		__field(bool, crosslinked)
+	),
+	TP_fast_assign(
+		__entry->dev = pag->pag_mount->m_super->s_dev;
+		__entry->agno = pag->pag_agno;
+		__entry->agbno = agbno;
+		__entry->len = len;
+		__entry->crosslinked = crosslinked;
+	),
+	TP_printk("dev %d:%d agno 0x%x agbno 0x%x fsbcount 0x%x crosslinked %d",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  __entry->agno,
+		  __entry->agbno,
+		  __entry->len,
+		  __entry->crosslinked ? 1 : 0)
+);
+#define DEFINE_REPAIR_REAP_FIND_EVENT(name) \
+DEFINE_EVENT(xrep_reap_find_class, name, \
+	TP_PROTO(struct xfs_perag *pag, xfs_agblock_t agbno, xfs_extlen_t len, \
+		 bool crosslinked), \
+	TP_ARGS(pag, agbno, len, crosslinked))
+DEFINE_REPAIR_REAP_FIND_EVENT(xreap_agextent_select);
+
 DECLARE_EVENT_CLASS(xrep_rmap_class,
 	TP_PROTO(struct xfs_mount *mp, xfs_agnumber_t agno,
 		 xfs_agblock_t agbno, xfs_extlen_t len,