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>

1 files changed, 71 insertions, 0 deletions

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