Merge tag 'scrub-drain-intents-6.4_2023-04-11' of...

Merge tag 'scrub-drain-intents-6.4_2023-04-11' of git://git.kernel.org/pub/scm/linux/kernel/git/djwong/xfs-linux into guilt/xfs-for-next

xfs: drain deferred work items when scrubbing [v24.5]

The design doc for XFS online fsck contains a long discussion of the
eventual consistency models in use for XFS metadata.  In that chapter,
we note that it is possible for scrub to collide with a chain of
deferred space metadata updates, and proposes a lightweight solution:
The use of a pending-intents counter so that scrub can wait for the
system to drain all chains.

This patchset implements that scrub drain.  The first patch implements
the basic mechanism, and the subsequent patches reduce the runtime
overhead by converting the implementation to use sloppy counters and
introducing jump labels to avoid walking into scrub hooks when it isn't
running.  This last paradigm repeats elsewhere in this megaseries.

v23.1: make intent items take an active ref to the perag structure and
       document why we bump and drop the intent counts when we do
Signed-off-by: Darrick J. Wong <djwong@kernel.org>
Signed-off-by: Dave Chinner <david@fromorbit.com>

fs/xfs/Kconfig

@@ -93,10 +93,15 @@ config XFS_RT
 
 	  If unsure, say N.
 
+config XFS_DRAIN_INTENTS
+	bool
+	select JUMP_LABEL if HAVE_ARCH_JUMP_LABEL
+
 config XFS_ONLINE_SCRUB
 	bool "XFS online metadata check support"
 	default n
 	depends on XFS_FS
+	select XFS_DRAIN_INTENTS
 	help
 	  If you say Y here you will be able to check metadata on a
 	  mounted XFS filesystem.  This feature is intended to reduce

fs/xfs/Makefile

@@ -136,6 +136,8 @@ ifeq ($(CONFIG_MEMORY_FAILURE),y)
 xfs-$(CONFIG_FS_DAX)		+= xfs_notify_failure.o
 endif
 
+xfs-$(CONFIG_XFS_DRAIN_INTENTS)	+= xfs_drain.o
+
 # online scrub/repair
 ifeq ($(CONFIG_XFS_ONLINE_SCRUB),y)
 

fs/xfs/libxfs/xfs_ag.c

@@ -260,6 +260,7 @@ xfs_free_perag(
 		spin_unlock(&mp->m_perag_lock);
 		ASSERT(pag);
 		XFS_IS_CORRUPT(pag->pag_mount, atomic_read(&pag->pag_ref) != 0);
+		xfs_defer_drain_free(&pag->pag_intents_drain);
 
 		cancel_delayed_work_sync(&pag->pag_blockgc_work);
 		xfs_buf_hash_destroy(pag);
@@ -385,6 +386,7 @@ xfs_initialize_perag(
 		spin_lock_init(&pag->pag_state_lock);
 		INIT_DELAYED_WORK(&pag->pag_blockgc_work, xfs_blockgc_worker);
 		INIT_RADIX_TREE(&pag->pag_ici_root, GFP_ATOMIC);
+		xfs_defer_drain_init(&pag->pag_intents_drain);
 		init_waitqueue_head(&pag->pagb_wait);
 		init_waitqueue_head(&pag->pag_active_wq);
 		pag->pagb_count = 0;
@@ -421,6 +423,7 @@ xfs_initialize_perag(
 	return 0;
 
 out_remove_pag:
+	xfs_defer_drain_free(&pag->pag_intents_drain);
 	radix_tree_delete(&mp->m_perag_tree, index);
 out_free_pag:
 	kmem_free(pag);
@@ -431,6 +434,7 @@ xfs_initialize_perag(
 		if (!pag)
 			break;
 		xfs_buf_hash_destroy(pag);
+		xfs_defer_drain_free(&pag->pag_intents_drain);
 		kmem_free(pag);
 	}
 	return error;

fs/xfs/libxfs/xfs_ag.h

@@ -101,6 +101,14 @@ struct xfs_perag {
 	/* background prealloc block trimming */
 	struct delayed_work	pag_blockgc_work;
 
+	/*
+	 * We use xfs_drain to track the number of deferred log intent items
+	 * that have been queued (but not yet processed) so that waiters (e.g.
+	 * scrub) will not lock resources when other threads are in the middle
+	 * of processing a chain of intent items only to find momentary
+	 * inconsistencies.
+	 */
+	struct xfs_defer_drain	pag_intents_drain;
 #endif /* __KERNEL__ */
 };
 

fs/xfs/libxfs/xfs_defer.c

@@ -397,6 +397,7 @@ xfs_defer_cancel_list(
 		list_for_each_safe(pwi, n, &dfp->dfp_work) {
 			list_del(pwi);
 			dfp->dfp_count--;
+			trace_xfs_defer_cancel_item(mp, dfp, pwi);
 			ops->cancel_item(pwi);
 		}
 		ASSERT(dfp->dfp_count == 0);
@@ -476,6 +477,7 @@ xfs_defer_finish_one(
 	list_for_each_safe(li, n, &dfp->dfp_work) {
 		list_del(li);
 		dfp->dfp_count--;
+		trace_xfs_defer_finish_item(tp->t_mountp, dfp, li);
 		error = ops->finish_item(tp, dfp->dfp_done, li, &state);
 		if (error == -EAGAIN) {
 			int		ret;
@@ -623,7 +625,7 @@ xfs_defer_add(
 	struct list_head		*li)
 {
 	struct xfs_defer_pending	*dfp = NULL;
-	const struct xfs_defer_op_type	*ops;
+	const struct xfs_defer_op_type	*ops = defer_op_types[type];
 
 	ASSERT(tp->t_flags & XFS_TRANS_PERM_LOG_RES);
 	BUILD_BUG_ON(ARRAY_SIZE(defer_op_types) != XFS_DEFER_OPS_TYPE_MAX);
@@ -636,7 +638,6 @@ xfs_defer_add(
 	if (!list_empty(&tp->t_dfops)) {
 		dfp = list_last_entry(&tp->t_dfops,
 				struct xfs_defer_pending, dfp_list);
-		ops = defer_op_types[dfp->dfp_type];
 		if (dfp->dfp_type != type ||
 		    (ops->max_items && dfp->dfp_count >= ops->max_items))
 			dfp = NULL;
@@ -653,6 +654,7 @@ xfs_defer_add(
 	}
 
 	list_add_tail(li, &dfp->dfp_work);
+	trace_xfs_defer_add_item(tp->t_mountp, dfp, li);
 	dfp->dfp_count++;
 }
 

fs/xfs/scrub/agheader.c

@@ -18,6 +18,15 @@
 #include "scrub/scrub.h"
 #include "scrub/common.h"
 
+int
+xchk_setup_agheader(
+	struct xfs_scrub	*sc)
+{
+	if (xchk_need_intent_drain(sc))
+		xchk_fsgates_enable(sc, XCHK_FSGATES_DRAIN);
+	return xchk_setup_fs(sc);
+}
+
 /* Superblock */
 
 /* Cross-reference with the other btrees. */

fs/xfs/scrub/alloc.c

@@ -24,6 +24,9 @@ int
 xchk_setup_ag_allocbt(
 	struct xfs_scrub	*sc)
 {
+	if (xchk_need_intent_drain(sc))
+		xchk_fsgates_enable(sc, XCHK_FSGATES_DRAIN);
+
 	return xchk_setup_ag_btree(sc, false);
 }
 

fs/xfs/scrub/bmap.c

@@ -31,6 +31,9 @@ xchk_setup_inode_bmap(
 {
 	int			error;
 
+	if (xchk_need_intent_drain(sc))
+		xchk_fsgates_enable(sc, XCHK_FSGATES_DRAIN);
+
 	error = xchk_get_inode(sc);
 	if (error)
 		goto out;

fs/xfs/scrub/btree.c

@@ -36,6 +36,7 @@ __xchk_btree_process_error(
 
 	switch (*error) {
 	case -EDEADLOCK:
+	case -ECHRNG:
 		/* Used to restart an op with deadlock avoidance. */
 		trace_xchk_deadlock_retry(sc->ip, sc->sm, *error);
 		break;

fs/xfs/scrub/common.c

@@ -75,6 +75,7 @@ __xchk_process_error(
 	case 0:
 		return true;
 	case -EDEADLOCK:
+	case -ECHRNG:
 		/* Used to restart an op with deadlock avoidance. */
 		trace_xchk_deadlock_retry(
 				sc->ip ? sc->ip : XFS_I(file_inode(sc->file)),
@@ -130,6 +131,7 @@ __xchk_fblock_process_error(
 	case 0:
 		return true;
 	case -EDEADLOCK:
+	case -ECHRNG:
 		/* Used to restart an op with deadlock avoidance. */
 		trace_xchk_deadlock_retry(sc->ip, sc->sm, *error);
 		break;
@@ -396,26 +398,19 @@ want_ag_read_header_failure(
 }
 
 /*
- * Grab the perag structure and all the headers for an AG.
+ * Grab the AG header buffers for the attached perag structure.
  *
  * The headers should be released by xchk_ag_free, but as a fail safe we attach
  * all the buffers we grab to the scrub transaction so they'll all be freed
- * when we cancel it.  Returns ENOENT if we can't grab the perag structure.
+ * when we cancel it.
  */
-int
-xchk_ag_read_headers(
+static inline int
+xchk_perag_read_headers(
 	struct xfs_scrub	*sc,
-	xfs_agnumber_t		agno,
 	struct xchk_ag		*sa)
 {
-	struct xfs_mount	*mp = sc->mp;
 	int			error;
 
-	ASSERT(!sa->pag);
-	sa->pag = xfs_perag_get(mp, agno);
-	if (!sa->pag)
-		return -ENOENT;
-
 	error = xfs_ialloc_read_agi(sa->pag, sc->tp, &sa->agi_bp);
 	if (error && want_ag_read_header_failure(sc, XFS_SCRUB_TYPE_AGI))
 		return error;
@@ -427,6 +422,104 @@ xchk_ag_read_headers(
 	return 0;
 }
 
+/*
+ * Grab the AG headers for the attached perag structure and wait for pending
+ * intents to drain.
+ */
+static int
+xchk_perag_drain_and_lock(
+	struct xfs_scrub	*sc)
+{
+	struct xchk_ag		*sa = &sc->sa;
+	int			error = 0;
+
+	ASSERT(sa->pag != NULL);
+	ASSERT(sa->agi_bp == NULL);
+	ASSERT(sa->agf_bp == NULL);
+
+	do {
+		if (xchk_should_terminate(sc, &error))
+			return error;
+
+		error = xchk_perag_read_headers(sc, sa);
+		if (error)
+			return error;
+
+		/*
+		 * If we've grabbed an inode for scrubbing then we assume that
+		 * holding its ILOCK will suffice to coordinate with any intent
+		 * chains involving this inode.
+		 */
+		if (sc->ip)
+			return 0;
+
+		/*
+		 * Decide if this AG is quiet enough for all metadata to be
+		 * consistent with each other.  XFS allows the AG header buffer
+		 * locks to cycle across transaction rolls while processing
+		 * chains of deferred ops, which means that there could be
+		 * other threads in the middle of processing a chain of
+		 * deferred ops.  For regular operations we are careful about
+		 * ordering operations to prevent collisions between threads
+		 * (which is why we don't need a per-AG lock), but scrub and
+		 * repair have to serialize against chained operations.
+		 *
+		 * We just locked all the AG headers buffers; now take a look
+		 * to see if there are any intents in progress.  If there are,
+		 * drop the AG headers and wait for the intents to drain.
+		 * Since we hold all the AG header locks for the duration of
+		 * the scrub, this is the only time we have to sample the
+		 * intents counter; any threads increasing it after this point
+		 * can't possibly be in the middle of a chain of AG metadata
+		 * updates.
+		 *
+		 * Obviously, this should be slanted against scrub and in favor
+		 * of runtime threads.
+		 */
+		if (!xfs_perag_intent_busy(sa->pag))
+			return 0;
+
+		if (sa->agf_bp) {
+			xfs_trans_brelse(sc->tp, sa->agf_bp);
+			sa->agf_bp = NULL;
+		}
+
+		if (sa->agi_bp) {
+			xfs_trans_brelse(sc->tp, sa->agi_bp);
+			sa->agi_bp = NULL;
+		}
+
+		if (!(sc->flags & XCHK_FSGATES_DRAIN))
+			return -ECHRNG;
+		error = xfs_perag_intent_drain(sa->pag);
+		if (error == -ERESTARTSYS)
+			error = -EINTR;
+	} while (!error);
+
+	return error;
+}
+
+/*
+ * Grab the per-AG structure, grab all AG header buffers, and wait until there
+ * aren't any pending intents.  Returns -ENOENT if we can't grab the perag
+ * structure.
+ */
+int
+xchk_ag_read_headers(
+	struct xfs_scrub	*sc,
+	xfs_agnumber_t		agno,
+	struct xchk_ag		*sa)
+{
+	struct xfs_mount	*mp = sc->mp;
+
+	ASSERT(!sa->pag);
+	sa->pag = xfs_perag_get(mp, agno);
+	if (!sa->pag)
+		return -ENOENT;
+
+	return xchk_perag_drain_and_lock(sc);
+}
+
 /* Release all the AG btree cursors. */
 void
 xchk_ag_btcur_free(
@@ -916,3 +1009,25 @@ xchk_start_reaping(
 	}
 	sc->flags &= ~XCHK_REAPING_DISABLED;
 }
+
+/*
+ * Enable filesystem hooks (i.e. runtime code patching) before starting a scrub
+ * operation.  Callers must not hold any locks that intersect with the CPU
+ * hotplug lock (e.g. writeback locks) because code patching must halt the CPUs
+ * to change kernel code.
+ */
+void
+xchk_fsgates_enable(
+	struct xfs_scrub	*sc,
+	unsigned int		scrub_fsgates)
+{
+	ASSERT(!(scrub_fsgates & ~XCHK_FSGATES_ALL));
+	ASSERT(!(sc->flags & scrub_fsgates));
+
+	trace_xchk_fsgates_enable(sc, scrub_fsgates);
+
+	if (scrub_fsgates & XCHK_FSGATES_DRAIN)
+		xfs_drain_wait_enable();
+
+	sc->flags |= scrub_fsgates;
+}

fs/xfs/scrub/common.h

@@ -72,6 +72,7 @@ bool xchk_should_check_xref(struct xfs_scrub *sc, int *error,
 			   struct xfs_btree_cur **curpp);
 
 /* Setup functions */
+int xchk_setup_agheader(struct xfs_scrub *sc);
 int xchk_setup_fs(struct xfs_scrub *sc);
 int xchk_setup_ag_allocbt(struct xfs_scrub *sc);
 int xchk_setup_ag_iallocbt(struct xfs_scrub *sc);
@@ -151,4 +152,18 @@ int xchk_ilock_inverted(struct xfs_inode *ip, uint lock_mode);
 void xchk_stop_reaping(struct xfs_scrub *sc);
 void xchk_start_reaping(struct xfs_scrub *sc);
 
+/*
+ * Setting up a hook to wait for intents to drain is costly -- we have to take
+ * the CPU hotplug lock and force an i-cache flush on all CPUs once to set it
+ * up, and again to tear it down.  These costs add up quickly, so we only want
+ * to enable the drain waiter if the drain actually detected a conflict with
+ * running intent chains.
+ */
+static inline bool xchk_need_intent_drain(struct xfs_scrub *sc)
+{
+	return sc->flags & XCHK_NEED_DRAIN;
+}
+
+void xchk_fsgates_enable(struct xfs_scrub *sc, unsigned int scrub_fshooks);
+
 #endif	/* __XFS_SCRUB_COMMON_H__ */

fs/xfs/scrub/dabtree.c

@@ -39,6 +39,7 @@ xchk_da_process_error(
 
 	switch (*error) {
 	case -EDEADLOCK:
+	case -ECHRNG:
 		/* Used to restart an op with deadlock avoidance. */
 		trace_xchk_deadlock_retry(sc->ip, sc->sm, *error);
 		break;

fs/xfs/scrub/fscounters.c

@@ -130,6 +130,13 @@ xchk_setup_fscounters(
 	struct xchk_fscounters	*fsc;
 	int			error;
 
+	/*
+	 * If the AGF doesn't track btreeblks, we have to lock the AGF to count
+	 * btree block usage by walking the actual btrees.
+	 */
+	if (!xfs_has_lazysbcount(sc->mp))
+		xchk_fsgates_enable(sc, XCHK_FSGATES_DRAIN);
+
 	sc->buf = kzalloc(sizeof(struct xchk_fscounters), XCHK_GFP_FLAGS);
 	if (!sc->buf)
 		return -ENOMEM;

fs/xfs/scrub/health.c

@@ -7,6 +7,8 @@
 #include "xfs_fs.h"
 #include "xfs_shared.h"
 #include "xfs_format.h"
+#include "xfs_trans_resv.h"
+#include "xfs_mount.h"
 #include "xfs_btree.h"
 #include "xfs_trans_resv.h"
 #include "xfs_mount.h"

fs/xfs/scrub/ialloc.c

@@ -32,6 +32,8 @@ int
 xchk_setup_ag_iallocbt(
 	struct xfs_scrub	*sc)
 {
+	if (xchk_need_intent_drain(sc))
+		xchk_fsgates_enable(sc, XCHK_FSGATES_DRAIN);
 	return xchk_setup_ag_btree(sc, sc->flags & XCHK_TRY_HARDER);
 }
 

fs/xfs/scrub/inode.c

@@ -32,6 +32,9 @@ xchk_setup_inode(
 {
 	int			error;
 
+	if (xchk_need_intent_drain(sc))
+		xchk_fsgates_enable(sc, XCHK_FSGATES_DRAIN);
+
 	/*
 	 * Try to get the inode.  If the verifiers fail, we try again
 	 * in raw mode.

fs/xfs/scrub/quota.c

@@ -53,6 +53,9 @@ xchk_setup_quota(
 	if (!xfs_this_quota_on(sc->mp, dqtype))
 		return -ENOENT;
 
+	if (xchk_need_intent_drain(sc))
+		xchk_fsgates_enable(sc, XCHK_FSGATES_DRAIN);
+
 	error = xchk_setup_fs(sc);
 	if (error)
 		return error;

fs/xfs/scrub/refcount.c

@@ -7,12 +7,15 @@
 #include "xfs_fs.h"
 #include "xfs_shared.h"
 #include "xfs_format.h"
+#include "xfs_trans_resv.h"
+#include "xfs_mount.h"
 #include "xfs_btree.h"
 #include "xfs_rmap.h"
 #include "xfs_refcount.h"
 #include "scrub/scrub.h"
 #include "scrub/common.h"
 #include "scrub/btree.h"
+#include "scrub/trace.h"
 #include "xfs_trans_resv.h"
 #include "xfs_mount.h"
 #include "xfs_ag.h"
@@ -24,6 +27,8 @@ int
 xchk_setup_ag_refcountbt(
 	struct xfs_scrub	*sc)
 {
+	if (xchk_need_intent_drain(sc))
+		xchk_fsgates_enable(sc, XCHK_FSGATES_DRAIN);
 	return xchk_setup_ag_btree(sc, false);
 }
 
@@ -300,8 +305,10 @@ xchk_refcountbt_xref_rmap(
 		goto out_free;
 
 	xchk_refcountbt_process_rmap_fragments(&refchk);
-	if (irec->rc_refcount != refchk.seen)
+	if (irec->rc_refcount != refchk.seen) {
+		trace_xchk_refcount_incorrect(sc->sa.pag, irec, refchk.seen);
 		xchk_btree_xref_set_corrupt(sc, sc->sa.rmap_cur, 0);
+	}
 
 out_free:
 	list_for_each_entry_safe(frag, n, &refchk.fragments, list) {

fs/xfs/scrub/repair.c

@@ -60,6 +60,9 @@ xrep_attempt(
 		sc->sm->sm_flags &= ~XFS_SCRUB_FLAGS_OUT;
 		sc->flags |= XREP_ALREADY_FIXED;
 		return -EAGAIN;
+	case -ECHRNG:
+		sc->flags |= XCHK_NEED_DRAIN;
+		return -EAGAIN;
 	case -EDEADLOCK:
 		/* Tell the caller to try again having grabbed all the locks. */
 		if (!(sc->flags & XCHK_TRY_HARDER)) {

fs/xfs/scrub/rmap.c

@@ -24,6 +24,9 @@ int
 xchk_setup_ag_rmapbt(
 	struct xfs_scrub	*sc)
 {
+	if (xchk_need_intent_drain(sc))
+		xchk_fsgates_enable(sc, XCHK_FSGATES_DRAIN);
+
 	return xchk_setup_ag_btree(sc, false);
 }
 

fs/xfs/scrub/scrub.c

@@ -145,6 +145,21 @@ xchk_probe(
 
 /* Scrub setup and teardown */
 
+static inline void
+xchk_fsgates_disable(
+	struct xfs_scrub	*sc)
+{
+	if (!(sc->flags & XCHK_FSGATES_ALL))
+		return;
+
+	trace_xchk_fsgates_disable(sc, sc->flags & XCHK_FSGATES_ALL);
+
+	if (sc->flags & XCHK_FSGATES_DRAIN)
+		xfs_drain_wait_disable();
+
+	sc->flags &= ~XCHK_FSGATES_ALL;
+}
+
 /* Free all the resources and finish the transactions. */
 STATIC int
 xchk_teardown(
@@ -177,6 +192,8 @@ xchk_teardown(
 		kvfree(sc->buf);
 		sc->buf = NULL;
 	}
+
+	xchk_fsgates_disable(sc);
 	return error;
 }
 
@@ -191,25 +208,25 @@ static const struct xchk_meta_ops meta_scrub_ops[] = {
 	},
 	[XFS_SCRUB_TYPE_SB] = {		/* superblock */
 		.type	= ST_PERAG,
-		.setup	= xchk_setup_fs,
+		.setup	= xchk_setup_agheader,
 		.scrub	= xchk_superblock,
 		.repair	= xrep_superblock,
 	},
 	[XFS_SCRUB_TYPE_AGF] = {	/* agf */
 		.type	= ST_PERAG,
-		.setup	= xchk_setup_fs,
+		.setup	= xchk_setup_agheader,
 		.scrub	= xchk_agf,
 		.repair	= xrep_agf,
 	},
 	[XFS_SCRUB_TYPE_AGFL]= {	/* agfl */
 		.type	= ST_PERAG,
-		.setup	= xchk_setup_fs,
+		.setup	= xchk_setup_agheader,
 		.scrub	= xchk_agfl,
 		.repair	= xrep_agfl,
 	},
 	[XFS_SCRUB_TYPE_AGI] = {	/* agi */
 		.type	= ST_PERAG,
-		.setup	= xchk_setup_fs,
+		.setup	= xchk_setup_agheader,
 		.scrub	= xchk_agi,
 		.repair	= xrep_agi,
 	},
@@ -491,23 +508,20 @@ xfs_scrub_metadata(
 
 	/* Set up for the operation. */
 	error = sc->ops->setup(sc);
+	if (error == -EDEADLOCK && !(sc->flags & XCHK_TRY_HARDER))
+		goto try_harder;
+	if (error == -ECHRNG && !(sc->flags & XCHK_NEED_DRAIN))
+		goto need_drain;
 	if (error)
 		goto out_teardown;
 
 	/* Scrub for errors. */
 	error = sc->ops->scrub(sc);
-	if (!(sc->flags & XCHK_TRY_HARDER) && error == -EDEADLOCK) {
-		/*
-		 * Scrubbers return -EDEADLOCK to mean 'try harder'.
-		 * Tear down everything we hold, then set up again with
-		 * preparation for worst-case scenarios.
-		 */
-		error = xchk_teardown(sc, 0);
-		if (error)
-			goto out_sc;
-		sc->flags |= XCHK_TRY_HARDER;
-		goto retry_op;
-	} else if (error || (sm->sm_flags & XFS_SCRUB_OFLAG_INCOMPLETE))
+	if (error == -EDEADLOCK && !(sc->flags & XCHK_TRY_HARDER))
+		goto try_harder;
+	if (error == -ECHRNG && !(sc->flags & XCHK_NEED_DRAIN))
+		goto need_drain;
+	if (error || (sm->sm_flags & XFS_SCRUB_OFLAG_INCOMPLETE))
 		goto out_teardown;
 
 	xchk_update_health(sc);
@@ -565,4 +579,21 @@ xfs_scrub_metadata(
 		error = 0;
 	}
 	return error;
+need_drain:
+	error = xchk_teardown(sc, 0);
+	if (error)
+		goto out_sc;
+	sc->flags |= XCHK_NEED_DRAIN;
+	goto retry_op;
+try_harder:
+	/*
+	 * Scrubbers return -EDEADLOCK to mean 'try harder'.  Tear down
+	 * everything we hold, then set up again with preparation for
+	 * worst-case scenarios.
+	 */
+	error = xchk_teardown(sc, 0);
+	if (error)
+		goto out_sc;
+	sc->flags |= XCHK_TRY_HARDER;
+	goto retry_op;
 }

fs/xfs/scrub/scrub.h

@@ -96,9 +96,19 @@ struct xfs_scrub {
 
 /* XCHK state flags grow up from zero, XREP state flags grown down from 2^31 */
 #define XCHK_TRY_HARDER		(1 << 0)  /* can't get resources, try again */
-#define XCHK_REAPING_DISABLED	(1 << 2)  /* background block reaping paused */
+#define XCHK_REAPING_DISABLED	(1 << 1)  /* background block reaping paused */
+#define XCHK_FSGATES_DRAIN	(1 << 2)  /* defer ops draining enabled */
+#define XCHK_NEED_DRAIN		(1 << 3)  /* scrub needs to drain defer ops */
 #define XREP_ALREADY_FIXED	(1 << 31) /* checking our repair work */
 
+/*
+ * The XCHK_FSGATES* flags reflect functionality in the main filesystem that
+ * are only enabled for this particular online fsck.  When not in use, the
+ * features are gated off via dynamic code patching, which is why the state
+ * must be enabled during scrub setup and can only be torn down afterwards.
+ */
+#define XCHK_FSGATES_ALL	(XCHK_FSGATES_DRAIN)
+
 /* Metadata scrubbers */
 int xchk_tester(struct xfs_scrub *sc);
 int xchk_superblock(struct xfs_scrub *sc);

fs/xfs/scrub/trace.h

@@ -30,6 +30,9 @@ TRACE_DEFINE_ENUM(XFS_BTNUM_FINOi);
 TRACE_DEFINE_ENUM(XFS_BTNUM_RMAPi);
 TRACE_DEFINE_ENUM(XFS_BTNUM_REFCi);
 
+TRACE_DEFINE_ENUM(XFS_REFC_DOMAIN_SHARED);
+TRACE_DEFINE_ENUM(XFS_REFC_DOMAIN_COW);
+
 TRACE_DEFINE_ENUM(XFS_SCRUB_TYPE_PROBE);
 TRACE_DEFINE_ENUM(XFS_SCRUB_TYPE_SB);
 TRACE_DEFINE_ENUM(XFS_SCRUB_TYPE_AGF);
@@ -93,6 +96,13 @@ TRACE_DEFINE_ENUM(XFS_SCRUB_TYPE_FSCOUNTERS);
 	{ XFS_SCRUB_OFLAG_WARNING,		"warning" }, \
 	{ XFS_SCRUB_OFLAG_NO_REPAIR_NEEDED,	"norepair" }
 
+#define XFS_SCRUB_STATE_STRINGS \
+	{ XCHK_TRY_HARDER,			"try_harder" }, \
+	{ XCHK_REAPING_DISABLED,		"reaping_disabled" }, \
+	{ XCHK_FSGATES_DRAIN,			"fsgates_drain" }, \
+	{ XCHK_NEED_DRAIN,			"need_drain" }, \
+	{ XREP_ALREADY_FIXED,			"already_fixed" }
+
 DECLARE_EVENT_CLASS(xchk_class,
 	TP_PROTO(struct xfs_inode *ip, struct xfs_scrub_metadata *sm,
 		 int error),
@@ -139,6 +149,33 @@ DEFINE_SCRUB_EVENT(xchk_deadlock_retry);
 DEFINE_SCRUB_EVENT(xrep_attempt);
 DEFINE_SCRUB_EVENT(xrep_done);
 
+DECLARE_EVENT_CLASS(xchk_fsgate_class,
+	TP_PROTO(struct xfs_scrub *sc, unsigned int fsgate_flags),
+	TP_ARGS(sc, fsgate_flags),
+	TP_STRUCT__entry(
+		__field(dev_t, dev)
+		__field(unsigned int, type)
+		__field(unsigned int, fsgate_flags)
+	),
+	TP_fast_assign(
+		__entry->dev = sc->mp->m_super->s_dev;
+		__entry->type = sc->sm->sm_type;
+		__entry->fsgate_flags = fsgate_flags;
+	),
+	TP_printk("dev %d:%d type %s fsgates '%s'",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  __print_symbolic(__entry->type, XFS_SCRUB_TYPE_STRINGS),
+		  __print_flags(__entry->fsgate_flags, "|", XFS_SCRUB_STATE_STRINGS))
+)
+
+#define DEFINE_SCRUB_FSHOOK_EVENT(name) \
+DEFINE_EVENT(xchk_fsgate_class, name, \
+	TP_PROTO(struct xfs_scrub *sc, unsigned int fsgates_flags), \
+	TP_ARGS(sc, fsgates_flags))
+
+DEFINE_SCRUB_FSHOOK_EVENT(xchk_fsgates_enable);
+DEFINE_SCRUB_FSHOOK_EVENT(xchk_fsgates_disable);
+
 TRACE_EVENT(xchk_op_error,
 	TP_PROTO(struct xfs_scrub *sc, xfs_agnumber_t agno,
 		 xfs_agblock_t bno, int error, void *ret_ip),
@@ -657,6 +694,38 @@ TRACE_EVENT(xchk_fscounters_within_range,
 		  __entry->old_value)
 )
 
+TRACE_EVENT(xchk_refcount_incorrect,
+	TP_PROTO(struct xfs_perag *pag, const struct xfs_refcount_irec *irec,
+		 xfs_nlink_t seen),
+	TP_ARGS(pag, irec, seen),
+	TP_STRUCT__entry(
+		__field(dev_t, dev)
+		__field(xfs_agnumber_t, agno)
+		__field(enum xfs_refc_domain, domain)
+		__field(xfs_agblock_t, startblock)
+		__field(xfs_extlen_t, blockcount)
+		__field(xfs_nlink_t, refcount)
+		__field(xfs_nlink_t, seen)
+	),
+	TP_fast_assign(
+		__entry->dev = pag->pag_mount->m_super->s_dev;
+		__entry->agno = pag->pag_agno;
+		__entry->domain = irec->rc_domain;
+		__entry->startblock = irec->rc_startblock;
+		__entry->blockcount = irec->rc_blockcount;
+		__entry->refcount = irec->rc_refcount;
+		__entry->seen = seen;
+	),
+	TP_printk("dev %d:%d agno 0x%x dom %s agbno 0x%x fsbcount 0x%x refcount %u seen %u",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  __entry->agno,
+		  __print_symbolic(__entry->domain, XFS_REFC_DOMAIN_STRINGS),
+		  __entry->startblock,
+		  __entry->blockcount,
+		  __entry->refcount,
+		  __entry->seen)
+)
+
 /* repair tracepoints */
 #if IS_ENABLED(CONFIG_XFS_ONLINE_REPAIR)
 

fs/xfs/xfs_bmap_item.c

@@ -373,7 +373,15 @@ xfs_bmap_update_get_group(
 	xfs_agnumber_t		agno;
 
 	agno = XFS_FSB_TO_AGNO(mp, bi->bi_bmap.br_startblock);
-	bi->bi_pag = xfs_perag_get(mp, agno);
+
+	/*
+	 * Bump the intent count on behalf of the deferred rmap and refcount
+	 * intent items that that we can queue when we finish this bmap work.
+	 * This new intent item will bump the intent count before the bmap
+	 * intent drops the intent count, ensuring that the intent count
+	 * remains nonzero across the transaction roll.
+	 */
+	bi->bi_pag = xfs_perag_intent_get(mp, agno);
 }
 
 /* Release a passive AG ref after finishing mapping work. */
@@ -381,7 +389,7 @@ static inline void
 xfs_bmap_update_put_group(
 	struct xfs_bmap_intent	*bi)
 {
-	xfs_perag_put(bi->bi_pag);
+	xfs_perag_intent_put(bi->bi_pag);
 }
 
 /* Process a deferred rmap update. */

fs/xfs/xfs_drain.c

+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Copyright (C) 2022-2023 Oracle.  All Rights Reserved.
+ * Author: Darrick J. Wong <djwong@kernel.org>
+ */
+#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_ag.h"
+#include "xfs_trace.h"
+
+/*
+ * Use a static key here to reduce the overhead of xfs_drain_rele.  If the
+ * compiler supports jump labels, the static branch will be replaced by a nop
+ * sled when there are no xfs_drain_wait callers.  Online fsck is currently
+ * the only caller, so this is a reasonable tradeoff.
+ *
+ * Note: Patching the kernel code requires taking the cpu hotplug lock.  Other
+ * parts of the kernel allocate memory with that lock held, which means that
+ * XFS callers cannot hold any locks that might be used by memory reclaim or
+ * writeback when calling the static_branch_{inc,dec} functions.
+ */
+static DEFINE_STATIC_KEY_FALSE(xfs_drain_waiter_gate);
+
+void
+xfs_drain_wait_disable(void)
+{
+	static_branch_dec(&xfs_drain_waiter_gate);
+}
+
+void
+xfs_drain_wait_enable(void)
+{
+	static_branch_inc(&xfs_drain_waiter_gate);
+}
+
+void
+xfs_defer_drain_init(
+	struct xfs_defer_drain	*dr)
+{
+	atomic_set(&dr->dr_count, 0);
+	init_waitqueue_head(&dr->dr_waiters);
+}
+
+void
+xfs_defer_drain_free(struct xfs_defer_drain	*dr)
+{
+	ASSERT(atomic_read(&dr->dr_count) == 0);
+}
+
+/* Increase the pending intent count. */
+static inline void xfs_defer_drain_grab(struct xfs_defer_drain *dr)
+{
+	atomic_inc(&dr->dr_count);
+}
+
+static inline bool has_waiters(struct wait_queue_head *wq_head)
+{
+	/*
+	 * This memory barrier is paired with the one in set_current_state on
+	 * the waiting side.
+	 */
+	smp_mb__after_atomic();
+	return waitqueue_active(wq_head);
+}
+
+/* Decrease the pending intent count, and wake any waiters, if appropriate. */
+static inline void xfs_defer_drain_rele(struct xfs_defer_drain *dr)
+{
+	if (atomic_dec_and_test(&dr->dr_count) &&
+	    static_branch_unlikely(&xfs_drain_waiter_gate) &&
+	    has_waiters(&dr->dr_waiters))
+		wake_up(&dr->dr_waiters);
+}
+
+/* Are there intents pending? */
+static inline bool xfs_defer_drain_busy(struct xfs_defer_drain *dr)
+{
+	return atomic_read(&dr->dr_count) > 0;
+}
+
+/*
+ * Wait for the pending intent count for a drain to hit zero.
+ *
+ * Callers must not hold any locks that would prevent intents from being
+ * finished.
+ */
+static inline int xfs_defer_drain_wait(struct xfs_defer_drain *dr)
+{
+	return wait_event_killable(dr->dr_waiters, !xfs_defer_drain_busy(dr));
+}
+
+/*
+ * Get a passive reference to an AG and declare an intent to update its
+ * metadata.
+ */
+struct xfs_perag *
+xfs_perag_intent_get(
+	struct xfs_mount	*mp,
+	xfs_agnumber_t		agno)
+{
+	struct xfs_perag	*pag;
+
+	pag = xfs_perag_get(mp, agno);
+	if (!pag)
+		return NULL;
+
+	xfs_perag_intent_hold(pag);
+	return pag;
+}
+
+/*
+ * Release our intent to update this AG's metadata, and then release our
+ * passive ref to the AG.
+ */
+void
+xfs_perag_intent_put(
+	struct xfs_perag	*pag)
+{
+	xfs_perag_intent_rele(pag);
+	xfs_perag_put(pag);
+}
+
+/*
+ * Declare an intent to update AG metadata.  Other threads that need exclusive
+ * access can decide to back off if they see declared intentions.
+ */
+void
+xfs_perag_intent_hold(
+	struct xfs_perag	*pag)
+{
+	trace_xfs_perag_intent_hold(pag, __return_address);
+	xfs_defer_drain_grab(&pag->pag_intents_drain);
+}
+
+/* Release our intent to update this AG's metadata. */
+void
+xfs_perag_intent_rele(
+	struct xfs_perag	*pag)
+{
+	trace_xfs_perag_intent_rele(pag, __return_address);
+	xfs_defer_drain_rele(&pag->pag_intents_drain);
+}
+
+/*
+ * Wait for the intent update count for this AG to hit zero.
+ * Callers must not hold any AG header buffers.
+ */
+int
+xfs_perag_intent_drain(
+	struct xfs_perag	*pag)
+{
+	trace_xfs_perag_wait_intents(pag, __return_address);
+	return xfs_defer_drain_wait(&pag->pag_intents_drain);
+}
+
+/* Has anyone declared an intent to update this AG? */
+bool
+xfs_perag_intent_busy(
+	struct xfs_perag	*pag)
+{
+	return xfs_defer_drain_busy(&pag->pag_intents_drain);
+}

fs/xfs/xfs_drain.h

+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Copyright (C) 2022-2023 Oracle.  All Rights Reserved.
+ * Author: Darrick J. Wong <djwong@kernel.org>
+ */
+#ifndef XFS_DRAIN_H_
+#define XFS_DRAIN_H_
+
+struct xfs_perag;
+
+#ifdef CONFIG_XFS_DRAIN_INTENTS
+/*
+ * Passive drain mechanism.  This data structure tracks a count of some items
+ * and contains a waitqueue for callers who would like to wake up when the
+ * count hits zero.
+ */
+struct xfs_defer_drain {
+	/* Number of items pending in some part of the filesystem. */
+	atomic_t		dr_count;
+
+	/* Queue to wait for dri_count to go to zero */
+	struct wait_queue_head	dr_waiters;
+};
+
+void xfs_defer_drain_init(struct xfs_defer_drain *dr);
+void xfs_defer_drain_free(struct xfs_defer_drain *dr);
+
+void xfs_drain_wait_disable(void);
+void xfs_drain_wait_enable(void);
+
+/*
+ * Deferred Work Intent Drains
+ * ===========================
+ *
+ * When a writer thread executes a chain of log intent items, the AG header
+ * buffer locks will cycle during a transaction roll to get from one intent
+ * item to the next in a chain.  Although scrub takes all AG header buffer
+ * locks, this isn't sufficient to guard against scrub checking an AG while
+ * that writer thread is in the middle of finishing a chain because there's no
+ * higher level locking primitive guarding allocation groups.
+ *
+ * When there's a collision, cross-referencing between data structures (e.g.
+ * rmapbt and refcountbt) yields false corruption events; if repair is running,
+ * this results in incorrect repairs, which is catastrophic.
+ *
+ * The solution is to the perag structure the count of active intents and make
+ * scrub wait until it has both AG header buffer locks and the intent counter
+ * reaches zero.  It is therefore critical that deferred work threads hold the
+ * AGI or AGF buffers when decrementing the intent counter.
+ *
+ * Given a list of deferred work items, the deferred work manager will complete
+ * a work item and all the sub-items that the parent item creates before moving
+ * on to the next work item in the list.  This is also true for all levels of
+ * sub-items.  Writer threads are permitted to queue multiple work items
+ * targetting the same AG, so a deferred work item (such as a BUI) that creates
+ * sub-items (such as RUIs) must bump the intent counter and maintain it until
+ * the sub-items can themselves bump the intent counter.
+ *
+ * Therefore, the intent count tracks entire lifetimes of deferred work items.
+ * All functions that create work items must increment the intent counter as
+ * soon as the item is added to the transaction and cannot drop the counter
+ * until the item is finished or cancelled.
+ */
+struct xfs_perag *xfs_perag_intent_get(struct xfs_mount *mp,
+		xfs_agnumber_t agno);
+void xfs_perag_intent_put(struct xfs_perag *pag);
+
+void xfs_perag_intent_hold(struct xfs_perag *pag);
+void xfs_perag_intent_rele(struct xfs_perag *pag);
+
+int xfs_perag_intent_drain(struct xfs_perag *pag);
+bool xfs_perag_intent_busy(struct xfs_perag *pag);
+#else
+struct xfs_defer_drain { /* empty */ };
+
+#define xfs_defer_drain_free(dr)		((void)0)
+#define xfs_defer_drain_init(dr)		((void)0)
+
+#define xfs_perag_intent_get(mp, agno)		xfs_perag_get((mp), (agno))
+#define xfs_perag_intent_put(pag)		xfs_perag_put(pag)
+
+static inline void xfs_perag_intent_hold(struct xfs_perag *pag) { }
+static inline void xfs_perag_intent_rele(struct xfs_perag *pag) { }
+
+#endif /* CONFIG_XFS_DRAIN_INTENTS */
+
+#endif /* XFS_DRAIN_H_ */

fs/xfs/xfs_extfree_item.c

@@ -469,7 +469,7 @@ xfs_extent_free_get_group(
 	xfs_agnumber_t			agno;
 
 	agno = XFS_FSB_TO_AGNO(mp, xefi->xefi_startblock);
-	xefi->xefi_pag = xfs_perag_get(mp, agno);
+	xefi->xefi_pag = xfs_perag_intent_get(mp, agno);
 }
 
 /* Release a passive AG ref after some freeing work. */
@@ -477,7 +477,7 @@ static inline void
 xfs_extent_free_put_group(
 	struct xfs_extent_free_item	*xefi)
 {
-	xfs_perag_put(xefi->xefi_pag);
+	xfs_perag_intent_put(xefi->xefi_pag);
 }
 
 /* Process a free extent. */

fs/xfs/xfs_linux.h

@@ -80,6 +80,7 @@ typedef __u32			xfs_nlink_t;
 #include "xfs_cksum.h"
 #include "xfs_buf.h"
 #include "xfs_message.h"
+#include "xfs_drain.h"
 
 #ifdef __BIG_ENDIAN
 #define XFS_NATIVE_HOST 1

fs/xfs/xfs_refcount_item.c

@@ -374,7 +374,7 @@ xfs_refcount_update_get_group(
 	xfs_agnumber_t			agno;
 
 	agno = XFS_FSB_TO_AGNO(mp, ri->ri_startblock);
-	ri->ri_pag = xfs_perag_get(mp, agno);
+	ri->ri_pag = xfs_perag_intent_get(mp, agno);
 }
 
 /* Release a passive AG ref after finishing refcounting work. */
@@ -382,7 +382,7 @@ static inline void
 xfs_refcount_update_put_group(
 	struct xfs_refcount_intent	*ri)
 {
-	xfs_perag_put(ri->ri_pag);
+	xfs_perag_intent_put(ri->ri_pag);
 }
 
 /* Process a deferred refcount update. */

fs/xfs/xfs_rmap_item.c

@@ -399,7 +399,7 @@ xfs_rmap_update_get_group(
 	xfs_agnumber_t		agno;
 
 	agno = XFS_FSB_TO_AGNO(mp, ri->ri_bmap.br_startblock);
-	ri->ri_pag = xfs_perag_get(mp, agno);
+	ri->ri_pag = xfs_perag_intent_get(mp, agno);
 }
 
 /* Release a passive AG ref after finishing rmapping work. */
@@ -407,7 +407,7 @@ static inline void
 xfs_rmap_update_put_group(
 	struct xfs_rmap_intent	*ri)
 {
-	xfs_perag_put(ri->ri_pag);
+	xfs_perag_intent_put(ri->ri_pag);
 }
 
 /* Process a deferred rmap update. */

fs/xfs/xfs_trace.h

@@ -2687,6 +2687,44 @@ DEFINE_BMAP_FREE_DEFERRED_EVENT(xfs_bmap_free_deferred);
 DEFINE_BMAP_FREE_DEFERRED_EVENT(xfs_agfl_free_defer);
 DEFINE_BMAP_FREE_DEFERRED_EVENT(xfs_agfl_free_deferred);
 
+DECLARE_EVENT_CLASS(xfs_defer_pending_item_class,
+	TP_PROTO(struct xfs_mount *mp, struct xfs_defer_pending *dfp,
+		 void *item),
+	TP_ARGS(mp, dfp, item),
+	TP_STRUCT__entry(
+		__field(dev_t, dev)
+		__field(int, type)
+		__field(void *, intent)
+		__field(void *, item)
+		__field(char, committed)
+		__field(int, nr)
+	),
+	TP_fast_assign(
+		__entry->dev = mp ? mp->m_super->s_dev : 0;
+		__entry->type = dfp->dfp_type;
+		__entry->intent = dfp->dfp_intent;
+		__entry->item = item;
+		__entry->committed = dfp->dfp_done != NULL;
+		__entry->nr = dfp->dfp_count;
+	),
+	TP_printk("dev %d:%d optype %d intent %p item %p committed %d nr %d",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  __entry->type,
+		  __entry->intent,
+		  __entry->item,
+		  __entry->committed,
+		  __entry->nr)
+)
+#define DEFINE_DEFER_PENDING_ITEM_EVENT(name) \
+DEFINE_EVENT(xfs_defer_pending_item_class, name, \
+	TP_PROTO(struct xfs_mount *mp, struct xfs_defer_pending *dfp, \
+		 void *item), \
+	TP_ARGS(mp, dfp, item))
+
+DEFINE_DEFER_PENDING_ITEM_EVENT(xfs_defer_add_item);
+DEFINE_DEFER_PENDING_ITEM_EVENT(xfs_defer_cancel_item);
+DEFINE_DEFER_PENDING_ITEM_EVENT(xfs_defer_finish_item);
+
 /* rmap tracepoints */
 DECLARE_EVENT_CLASS(xfs_rmap_class,
 	TP_PROTO(struct xfs_mount *mp, xfs_agnumber_t agno,
@@ -4326,6 +4364,39 @@ TRACE_EVENT(xfs_force_shutdown,
 		__entry->line_num)
 );
 
+#ifdef CONFIG_XFS_DRAIN_INTENTS
+DECLARE_EVENT_CLASS(xfs_perag_intents_class,
+	TP_PROTO(struct xfs_perag *pag, void *caller_ip),
+	TP_ARGS(pag, caller_ip),
+	TP_STRUCT__entry(
+		__field(dev_t, dev)
+		__field(xfs_agnumber_t, agno)
+		__field(long, nr_intents)
+		__field(void *, caller_ip)
+	),
+	TP_fast_assign(
+		__entry->dev = pag->pag_mount->m_super->s_dev;
+		__entry->agno = pag->pag_agno;
+		__entry->nr_intents = atomic_read(&pag->pag_intents_drain.dr_count);
+		__entry->caller_ip = caller_ip;
+	),
+	TP_printk("dev %d:%d agno 0x%x intents %ld caller %pS",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  __entry->agno,
+		  __entry->nr_intents,
+		  __entry->caller_ip)
+);
+
+#define DEFINE_PERAG_INTENTS_EVENT(name)	\
+DEFINE_EVENT(xfs_perag_intents_class, name,					\
+	TP_PROTO(struct xfs_perag *pag, void *caller_ip), \
+	TP_ARGS(pag, caller_ip))
+DEFINE_PERAG_INTENTS_EVENT(xfs_perag_intent_hold);
+DEFINE_PERAG_INTENTS_EVENT(xfs_perag_intent_rele);
+DEFINE_PERAG_INTENTS_EVENT(xfs_perag_wait_intents);
+
+#endif /* CONFIG_XFS_DRAIN_INTENTS */
+
 #endif /* _TRACE_XFS_H */
 
 #undef TRACE_INCLUDE_PATH