From 174364f6a8979655f71b04b6492657aec3762703 Mon Sep 17 00:00:00 2001
From: Damien Le Moal <damien.lemoal@wdc.com>
Date: Wed, 8 Jul 2020 09:20:22 +0900
Subject: [PATCH] dm zoned: Fix zone reclaim trigger
Git-commit: 174364f6a8979655f71b04b6492657aec3762703
Patch-mainline: v5.8-rc5
References: bsc#1175995, jsc#SLE-15608

Only triggering reclaim based on the percentage of unmapped cache
zones can fail to detect cases where reclaim is needed, e.g. if the
target has only 2 or 3 cache zones and only one unmapped cache zone,
the percentage of free cache zones is higher than
DMZ_RECLAIM_LOW_UNMAP_ZONES (30%) and reclaim does not trigger.

This problem, combined with the fact that dmz_schedule_reclaim() is
called from dmz_handle_bio() without the map lock held, leads to a
race between zone allocation and dmz_should_reclaim() result.
Depending on the workload applied, this race can lead to the write
path waiting forever for a free zone without reclaim being triggered.

Fix this by moving dmz_schedule_reclaim() inside dmz_alloc_zone()
under the map lock. This results in checking the need for zone reclaim
whenever a new data or buffer zone needs to be allocated.

Also fix dmz_reclaim_percentage() to always return 0 if the number of
unmapped cache (or random) zones is less than or equal to 1.

Suggested-by: Shin'ichiro Kawasaki <shinichiro.kawasaki@wdc.com>
Signed-off-by: Damien Le Moal <damien.lemoal@wdc.com>
Reviewed-by: Hannes Reinecke <hare@suse.de>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
Signed-off-by: Coly Li <colyli@suse.de>

---
 drivers/md/dm-zoned-metadata.c |  9 ++++++++-
 drivers/md/dm-zoned-reclaim.c  |  2 ++
 drivers/md/dm-zoned-target.c   | 10 +---------
 3 files changed, 11 insertions(+), 10 deletions(-)

diff --git a/drivers/md/dm-zoned-metadata.c b/drivers/md/dm-zoned-metadata.c
index 5cf6f5f552e0..b298fefb022e 100644
--- a/drivers/md/dm-zoned-metadata.c
+++ b/drivers/md/dm-zoned-metadata.c
@@ -2217,8 +2217,15 @@ struct dm_zone *dmz_alloc_zone(struct dmz_metadata *zmd, unsigned int dev_idx,
 {
 	struct list_head *list;
 	struct dm_zone *zone;
-	int i = 0;
+	int i;
+
+	/* Schedule reclaim to ensure free zones are available */
+	if (!(flags & DMZ_ALLOC_RECLAIM)) {
+		for (i = 0; i < zmd->nr_devs; i++)
+			dmz_schedule_reclaim(zmd->dev[i].reclaim);
+	}
 
+	i = 0;
 again:
 	if (flags & DMZ_ALLOC_CACHE)
 		list = &zmd->unmap_cache_list;
diff --git a/drivers/md/dm-zoned-reclaim.c b/drivers/md/dm-zoned-reclaim.c
index 7e0cc2d732cf..9c0ecc9568a4 100644
--- a/drivers/md/dm-zoned-reclaim.c
+++ b/drivers/md/dm-zoned-reclaim.c
@@ -456,6 +456,8 @@ static unsigned int dmz_reclaim_percentage(struct dmz_reclaim *zrc)
 		nr_zones = dmz_nr_rnd_zones(zmd, zrc->dev_idx);
 		nr_unmap = dmz_nr_unmap_rnd_zones(zmd, zrc->dev_idx);
 	}
+	if (nr_unmap <= 1)
+		return 0;
 	return nr_unmap * 100 / nr_zones;
 }
 
diff --git a/drivers/md/dm-zoned-target.c b/drivers/md/dm-zoned-target.c
index cf915009c306..42aa5139df7c 100644
--- a/drivers/md/dm-zoned-target.c
+++ b/drivers/md/dm-zoned-target.c
@@ -400,15 +400,7 @@ static void dmz_handle_bio(struct dmz_target *dmz, struct dm_chunk_work *cw,
 		dm_per_bio_data(bio, sizeof(struct dmz_bioctx));
 	struct dmz_metadata *zmd = dmz->metadata;
 	struct dm_zone *zone;
-	int i, ret;
-
-	/*
-	 * Write may trigger a zone allocation. So make sure the
-	 * allocation can succeed.
-	 */
-	if (bio_op(bio) == REQ_OP_WRITE)
-		for (i = 0; i < dmz->nr_ddevs; i++)
-			dmz_schedule_reclaim(dmz->dev[i].reclaim);
+	int ret;
 
 	dmz_lock_metadata(zmd);
 
-- 
2.26.2