scsi: core: Reallocate device's budget map on queue depth change

We currently use ->cmd_per_lun as initial queue depth for setting up the
budget_map. Martin Wilck reported that it is common for the queue_depth to
be subsequently updated in slave_configure() based on detected hardware
characteristics.

As a result, for some drivers, the static host template settings for
cmd_per_lun and can_queue won't actually get used in practice. And if the
default values are used to allocate the budget_map, memory may be consumed
unnecessarily.

Fix the issue by reallocating the budget_map after ->slave_configure()
returns. At that time the device queue_depth should accurately reflect what
the hardware needs.

Link: https://lore.kernel.org/r/20220127153733.409132-1-ming.lei@redhat.com
Cc: Bart Van Assche <bvanassche@acm.org>
Reported-by: Martin Wilck <martin.wilck@suse.com>
Suggested-by: Martin Wilck <martin.wilck@suse.com>
Tested-by: Martin Wilck <mwilck@suse.com>
Reviewed-by: Martin Wilck <mwilck@suse.com>
Reviewed-by: Bart Van Assche <bvanassche@acm.org>
Signed-off-by: Ming Lei <ming.lei@redhat.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>

1 files changed, 50 insertions, 5 deletions

diff --git a/drivers/scsi/scsi_scan.c b/drivers/scsi/scsi_scan.c
index 3520b9384428..f4e6c68ac99e 100644
--- a/drivers/scsi/scsi_scan.c
+++ b/drivers/scsi/scsi_scan.c
@@ -214,6 +214,48 @@ static void scsi_unlock_floptical(struct scsi_device *sdev,
 			 SCSI_TIMEOUT, 3, NULL);
 }
 
+static int scsi_realloc_sdev_budget_map(struct scsi_device *sdev,
+					unsigned int depth)
+{
+	int new_shift = sbitmap_calculate_shift(depth);
+	bool need_alloc = !sdev->budget_map.map;
+	bool need_free = false;
+	int ret;
+	struct sbitmap sb_backup;
+
+	/*
+	 * realloc if new shift is calculated, which is caused by setting
+	 * up one new default queue depth after calling ->slave_configure
+	 */
+	if (!need_alloc && new_shift != sdev->budget_map.shift)
+		need_alloc = need_free = true;
+
+	if (!need_alloc)
+		return 0;
+
+	/*
+	 * Request queue has to be frozen for reallocating budget map,
+	 * and here disk isn't added yet, so freezing is pretty fast
+	 */
+	if (need_free) {
+		blk_mq_freeze_queue(sdev->request_queue);
+		sb_backup = sdev->budget_map;
+	}
+	ret = sbitmap_init_node(&sdev->budget_map,
+				scsi_device_max_queue_depth(sdev),
+				new_shift, GFP_KERNEL,
+				sdev->request_queue->node, false, true);
+	if (need_free) {
+		if (ret)
+			sdev->budget_map = sb_backup;
+		else
+			sbitmap_free(&sb_backup);
+		ret = 0;
+		blk_mq_unfreeze_queue(sdev->request_queue);
+	}
+	return ret;
+}
+
 /**
  * scsi_alloc_sdev - allocate and setup a scsi_Device
  * @starget: which target to allocate a &scsi_device for
@@ -306,11 +348,7 @@ static struct scsi_device *scsi_alloc_sdev(struct scsi_target *starget,
 	 * default device queue depth to figure out sbitmap shift
 	 * since we use this queue depth most of times.
 	 */
-	if (sbitmap_init_node(&sdev->budget_map,
-				scsi_device_max_queue_depth(sdev),
-				sbitmap_calculate_shift(depth),
-				GFP_KERNEL, sdev->request_queue->node,
-				false, true)) {
+	if (scsi_realloc_sdev_budget_map(sdev, depth)) {
 		put_device(&starget->dev);
 		kfree(sdev);
 		goto out;
@@ -1017,6 +1055,13 @@ static int scsi_add_lun(struct scsi_device *sdev, unsigned char *inq_result,
 			}
 			return SCSI_SCAN_NO_RESPONSE;
 		}
+
+		/*
+		 * The queue_depth is often changed in ->slave_configure.
+		 * Set up budget map again since memory consumption of
+		 * the map depends on actual queue depth.
+		 */
+		scsi_realloc_sdev_budget_map(sdev, sdev->queue_depth);
 	}
 
 	if (sdev->scsi_level >= SCSI_3)