[PATCH v7 08/28] block: Fake max open zones limit when there is no limit

[Damien Le Moal]

For a zoned block device that has no limit on the number of open zones
and no limit on the number of active zones, the zone write plug mempool
is created with a size of 128 zone write plugs. For such case, set the
device max_open_zones queue limit to this value to indicate to the user
the potential performance penalty that may happen when writing
simultaneously to more zones than the mempool size.

Signed-off-by: Damien Le Moal <dlem...@kernel.org>
Reviewed-by: Christoph Hellwig <h...@lst.de>
Reviewed-by: Hannes Reinecke <h...@suse.de>
Reviewed-by: Bart Van Assche <bvanass...@acm.org>
Tested-by: Hans Holmberg <hans.holmb...@wdc.com>
Tested-by: Dennis Maisenbacher <dennis.maisenbac...@wdc.com>
Reviewed-by: Martin K. Petersen <martin.peter...@oracle.com>
---
 block/blk-zoned.c | 41 +++++++++++++++++++++++++++++++++++------
 1 file changed, 35 insertions(+), 6 deletions(-)

diff --git a/block/blk-zoned.c b/block/blk-zoned.c
index fefcebd70445..4b21a1ec00d4 100644
--- a/block/blk-zoned.c
+++ b/block/blk-zoned.c
@@ -1503,6 +1503,38 @@ struct blk_revalidate_zone_args {
        sector_t        sector;
 };
 
+/*
+ * Update the disk zone resources information and device queue limits.
+ * The disk queue is frozen when this is executed.
+ */
+static int disk_update_zone_resources(struct gendisk *disk,
+                                     struct blk_revalidate_zone_args *args)
+{
+       struct request_queue *q = disk->queue;
+       struct queue_limits lim;
+
+       disk->nr_zones = args->nr_zones;
+       disk->zone_capacity = args->zone_capacity;
+       swap(disk->seq_zones_wlock, args->seq_zones_wlock);
+       swap(disk->conv_zones_bitmap, args->conv_zones_bitmap);
+
+       /*
+        * If the device has no limit on the maximum number of open and active
+        * zones, set its max open zone limit to the mempool size to indicate
+        * to the user that there is a potential performance impact due to
+        * dynamic zone write plug allocation when simultaneously writing to
+        * more zones than the size of the mempool.
+        */
+       if (disk->zone_wplugs_pool) {
+               lim = queue_limits_start_update(q);
+               if (!lim.max_open_zones && !lim.max_active_zones)
+                       lim.max_open_zones = disk->zone_wplugs_pool->min_nr;
+               return queue_limits_commit_update(q, &lim);
+       }
+
+       return 0;
+}
+
 /*
  * Helper function to check the validity of zones of a zoned block device.
  */
@@ -1703,17 +1735,14 @@ int blk_revalidate_disk_zones(struct gendisk *disk,
         */
        blk_mq_freeze_queue(q);
        if (ret > 0) {
-               disk->nr_zones = args.nr_zones;
-               disk->zone_capacity = args.zone_capacity;
-               swap(disk->seq_zones_wlock, args.seq_zones_wlock);
-               swap(disk->conv_zones_bitmap, args.conv_zones_bitmap);
+               ret = disk_update_zone_resources(disk, &args);
                if (update_driver_data)
                        update_driver_data(disk);
-               ret = 0;
        } else {
                pr_warn("%s: failed to revalidate zones\n", disk->disk_name);
-               disk_free_zone_resources(disk);
        }
+       if (ret)
+               disk_free_zone_resources(disk);
        blk_mq_unfreeze_queue(q);
 
        kfree(args.seq_zones_wlock);
-- 
2.44.0