[Devel] [RFC PATCH vz9 v6 58/62] dm-ploop: fix locking and improve error handling when submitting pios

[Alexander Atanasov]

The difference between hlist_unhashed_lockless and hlist_unhashed
is that _lockless version uses READ_ONCE to do the check.
Since it is used without locks we must switch to the _lockless variant.

Also make locking clusters and adding to inflight_pios return result
so we can track if they failed and where.

https://virtuozzo.atlassian.net/browse/VSTOR-91821
Signed-off-by: Alexander Atanasov <alexander.atanasov at virtuozzo.com>
---
 drivers/md/dm-ploop-map.c | 70 ++++++++++++++++++++++++++++++---------
 1 file changed, 54 insertions(+), 16 deletions(-)

diff --git a/drivers/md/dm-ploop-map.c b/drivers/md/dm-ploop-map.c
index 55ed95e39601..a03e1af3fd87 100644
--- a/drivers/md/dm-ploop-map.c
+++ b/drivers/md/dm-ploop-map.c
@@ -496,17 +496,32 @@ static void ploop_dec_nr_inflight(struct ploop *ploop, struct pio *pio)
 	}
 }
 
-static void ploop_link_pio(struct hlist_head head[], struct pio *pio,
+static int ploop_link_pio(struct hlist_head head[], struct pio *pio,
 		     u32 clu, bool exclusive)
 {
 	struct hlist_head *slot = ploop_htable_slot(head, clu);
+	struct ploop *ploop = pio->ploop;
+
+	if (exclusive) {
+		struct pio *pe = ploop_find_pio(head, clu);
+
+		if (pe == pio)
+			return 1;
 
-	if (exclusive)
-		WARN_ON_ONCE(ploop_find_pio(head, clu) != NULL);
+		WARN_ON_ONCE(pe != NULL);
 
-	BUG_ON(!hlist_unhashed(&pio->hlist_node));
+		if (pe)
+			PL_ERR("clu:%u already exclusively locked\n", clu);
+	}
+
+	if (!hlist_unhashed_lockless(&pio->hlist_node)) {
+		PL_ERR("already hashed clu:%u e:%d\n", clu, exclusive);
+		WARN_ON_ONCE(1);
+		return 0;
+	}
 	hlist_add_head(&pio->hlist_node, slot);
 	pio->clu = clu;
+	return 1;
 }
 
 /*
@@ -514,45 +529,55 @@ static void ploop_link_pio(struct hlist_head head[], struct pio *pio,
  * or from exclusive_bios_rbtree. BIOs from endio_list are requeued
  * to deferred_list.
  */
-static void ploop_unlink_pio(struct ploop *ploop, struct pio *pio,
+static int ploop_unlink_pio(struct ploop *ploop, struct pio *pio,
 		       struct list_head *pio_list)
 {
-	BUG_ON(hlist_unhashed(&pio->hlist_node));
+	if (hlist_unhashed_lockless(&pio->hlist_node)) {
+		WARN_ON_ONCE(1);
+		return 0;
+	}
 
 	hlist_del_init(&pio->hlist_node);
 	list_splice_tail_init(&pio->endio_list, pio_list);
+	return 1;
 }
 
-static void ploop_add_cluster_lk(struct ploop *ploop, struct pio *pio, u32 clu)
+static int ploop_add_cluster_lk(struct ploop *ploop, struct pio *pio, u32 clu)
 {
 	unsigned long flags;
+	int ret;
 
 	spin_lock_irqsave(&ploop->deferred_lock, flags);
-	ploop_link_pio(ploop->exclusive_pios, pio, clu, true);
+	ret = ploop_link_pio(ploop->exclusive_pios, pio, clu, true);
 	spin_unlock_irqrestore(&ploop->deferred_lock, flags);
+	return ret;
 }
 
-static void ploop_del_cluster_lk(struct ploop *ploop, struct pio *pio)
+static int ploop_del_cluster_lk(struct ploop *ploop, struct pio *pio)
 {
 	LIST_HEAD(pio_list);
 	unsigned long flags;
+	int ret;
 
 	spin_lock_irqsave(&ploop->deferred_lock, flags);
-	ploop_unlink_pio(ploop, pio, &pio_list);
+	ret = ploop_unlink_pio(ploop, pio, &pio_list);
 	spin_unlock_irqrestore(&ploop->deferred_lock, flags);
 
 	if (!list_empty(&pio_list))
 		ploop_dispatch_pios(ploop, NULL, &pio_list);
+	return ret;
 }
 
-static void ploop_link_submitting_pio(struct ploop *ploop, struct pio *pio,
+static int ploop_link_submitting_pio(struct ploop *ploop, struct pio *pio,
 				      u32 clu)
 {
 	unsigned long flags;
+	int ret;
 
 	spin_lock_irqsave(&ploop->inflight_lock, flags);
-	ploop_link_pio(ploop->inflight_pios, pio, clu, false);
+	ret = ploop_link_pio(ploop->inflight_pios, pio, clu, false);
 	spin_unlock_irqrestore(&ploop->inflight_lock, flags);
+	return ret;
 }
 
 static void ploop_unlink_completed_pio(struct ploop *ploop, struct pio *pio)
@@ -560,7 +585,7 @@ static void ploop_unlink_completed_pio(struct ploop *ploop, struct pio *pio)
 	LIST_HEAD(pio_list);
 	unsigned long flags;
 
-	if (hlist_unhashed(&pio->hlist_node))
+	if (hlist_unhashed_lockless(&pio->hlist_node))
 		return;
 
 	spin_lock_irqsave(&ploop->inflight_lock, flags);
@@ -705,7 +730,8 @@ static int ploop_handle_discard_pio(struct ploop *ploop, struct pio *pio,
 		return 0;
 	}
 
-	ploop_add_cluster_lk(ploop, pio, clu);
+	if (!ploop_add_cluster_lk(ploop, pio, clu))
+		PL_ERR("dis clu %d already locked\n", clu);
 	pio->wants_discard_index_cleanup = true;
 
 punch_hole:
@@ -1419,7 +1445,8 @@ static int ploop_submit_cluster_cow(struct ploop *ploop, unsigned int level,
 	cow->aux_pio = aux_pio;
 	cow->cow_pio = cow_pio;
 
-	ploop_add_cluster_lk(ploop, cow_pio, clu);
+	if (!ploop_add_cluster_lk(ploop, cow_pio, clu))
+		PL_ERR("cowclu %d already locked\n", clu);
 
 	/* Stage #0: read secondary delta full clu */
 	ploop_map_and_submit_rw(ploop, dst_clu, aux_pio, level);
@@ -1699,8 +1726,19 @@ static int ploop_process_one_deferred_bio(struct ploop *ploop, struct pio *pio)
 						      &dst_clu, pio);
 	if (!ret)
 		goto executed;
+
 queue:		/* pio needs to go to the queue */
-	ploop_link_submitting_pio(ploop, pio, clu);
+	if (!ploop_link_submitting_pio(ploop, pio, clu)) {
+		PL_ERR("link submitting pio failed\n");
+		/* Pio is put into endio_list */
+		if (ploop_postpone_if_cluster_locked(ploop, pio, clu)) {
+			goto handled;
+		} else {
+			PL_ERR("link submitting pio postpone failed\n");
+			WARN_ON_ONCE(1);
+			/* fail thru and run it anyway nothing */
+		}
+	}
 	ploop_map_and_submit_rw(ploop, dst_clu, pio, ploop_top_level(ploop));
 	// return 1;
 executed:	/* pio op started  */
-- 
2.43.0