xfs: allow queued AG intents to drain before scrubbing

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.

Fix this by adding 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.

One quirk of the drain code is that deferred bmap updates also bump and
drop the intent counter.  A fundamental decision made during the design
phase of the reverse mapping feature is that updates to the rmapbt
records are always made by the same code that updates the primary
metadata.  In other words, callers of bmapi functions expect that the
bmapi functions will queue deferred rmap updates.

Some parts of the reflink code queue deferred refcount (CUI) and bmap
(BUI) updates in the same head transaction, but the deferred work
manager completely finishes the CUI before the BUI work is started.  As
a result, the CUI drops the intent count long before the deferred rmap
(RUI) update even has a chance to bump the intent count.  The only way
to keep the intent count elevated between the CUI and RUI is for the BUI
to bump the counter until the RUI has been created.

A second quirk of the intent drain code is that deferred work items must
increment the intent counter as soon as the work item is added to the
transaction.  When a BUI completes and queues an RUI, the RUI must
increment the counter before the BUI decrements it.  The only way to
accomplish this is to require that the counter be bumped as soon as the
deferred work item is created in memory.

In the next patches we'll improve on this facility, but this patch
provides the basic functionality.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
Reviewed-by: Dave Chinner <dchinner@redhat.com>

16 files changed, 438 insertions, 21 deletions

diff --git a/fs/xfs/Kconfig b/fs/xfs/Kconfig
index 9fac5ea8d0e4..ab24e683b440 100644
--- a/fs/xfs/Kconfig
+++ b/fs/xfs/Kconfig
@@ -93,10 +93,14 @@ config XFS_RT
 
 	  If unsure, say N.
 
+config XFS_DRAIN_INTENTS
+	bool
+
 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
diff --git a/fs/xfs/Makefile b/fs/xfs/Makefile
index 92d88dc3c9f7..3bdbc838c4d1 100644
--- a/fs/xfs/Makefile
+++ b/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)
 
diff --git a/fs/xfs/libxfs/xfs_ag.c b/fs/xfs/libxfs/xfs_ag.c
index 2d8910046ed9..1b078bbbf225 100644
--- a/fs/xfs/libxfs/xfs_ag.c
+++ b/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 @@ out_unwind_new_pags:
 		if (!pag)
 			break;
 		xfs_buf_hash_destroy(pag);
+		xfs_defer_drain_free(&pag->pag_intents_drain);
 		kmem_free(pag);
 	}
 	return error;
diff --git a/fs/xfs/libxfs/xfs_ag.h b/fs/xfs/libxfs/xfs_ag.h
index 8092eaba977d..2e0aef87d633 100644
--- a/fs/xfs/libxfs/xfs_ag.h
+++ b/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__ */
 };
 
diff --git a/fs/xfs/libxfs/xfs_defer.c b/fs/xfs/libxfs/xfs_defer.c
index 5a321b783398..bcfb6a4203cd 100644
--- a/fs/xfs/libxfs/xfs_defer.c
+++ b/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++;
 }
 
diff --git a/fs/xfs/scrub/common.c b/fs/xfs/scrub/common.c
index 597e6aca8628..2a496d1699a3 100644
--- a/fs/xfs/scrub/common.c
+++ b/fs/xfs/scrub/common.c
@@ -396,26 +396,19 @@ 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 +420,102 @@ 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;
+		}
+
+		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(
diff --git a/fs/xfs/scrub/health.c b/fs/xfs/scrub/health.c
index 66e99b0f6049..d2b2a1cb6533 100644
--- a/fs/xfs/scrub/health.c
+++ b/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"
diff --git a/fs/xfs/scrub/refcount.c b/fs/xfs/scrub/refcount.c
index aaad13b1871f..756066f3dea2 100644
--- a/fs/xfs/scrub/refcount.c
+++ b/fs/xfs/scrub/refcount.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_rmap.h"
 #include "xfs_refcount.h"
diff --git a/fs/xfs/xfs_bmap_item.c b/fs/xfs/xfs_bmap_item.c
index 8f0f33d07d2c..7551c3ec4ea5 100644
--- a/fs/xfs/xfs_bmap_item.c
+++ b/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. */
diff --git a/fs/xfs/xfs_drain.c b/fs/xfs/xfs_drain.c
new file mode 100644
index 000000000000..b431abdf0af1
--- /dev/null
+++ b/fs/xfs/xfs_drain.c
@@ -0,0 +1,140 @@
+// 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"
+
+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) &&
+	    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);
+}
diff --git a/fs/xfs/xfs_drain.h b/fs/xfs/xfs_drain.h
new file mode 100644
index 000000000000..9b16df3cc7dc
--- /dev/null
+++ b/fs/xfs/xfs_drain.h
@@ -0,0 +1,84 @@
+// 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);
+
+/*
+ * 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_ */
diff --git a/fs/xfs/xfs_extfree_item.c b/fs/xfs/xfs_extfree_item.c
index 38b66fcfddc8..f9e36b810663 100644
--- a/fs/xfs/xfs_extfree_item.c
+++ b/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. */
diff --git a/fs/xfs/xfs_linux.h b/fs/xfs/xfs_linux.h
index e88f18f85e4b..74dcb05069e8 100644
--- a/fs/xfs/xfs_linux.h
+++ b/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
diff --git a/fs/xfs/xfs_refcount_item.c b/fs/xfs/xfs_refcount_item.c
index 7edee9590ed6..edd8587658d5 100644
--- a/fs/xfs/xfs_refcount_item.c
+++ b/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. */
diff --git a/fs/xfs/xfs_rmap_item.c b/fs/xfs/xfs_rmap_item.c
index 739ddbd04a17..520c7ebdfed8 100644
--- a/fs/xfs/xfs_rmap_item.c
+++ b/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. */
diff --git a/fs/xfs/xfs_trace.h b/fs/xfs/xfs_trace.h
index db09bb771765..cd4ca5b1fcb0 100644
--- a/fs/xfs/xfs_trace.h
+++ b/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