[PATCH v2] nvme: only reconfigure discard if necessary

[PATCH v2] nvme: only reconfigure discard if necessary

[Jens Axboe]

Currently nvme reconfigures discard for every disk revalidation. This
is problematic because any O_WRONLY or O_RDWR open will trigger a
partition scan through udev/systemd, and we will reconfigure discard.
This blows away any user settings, like discard_max_bytes.

Only re-configure the user settable settings if we need to.

Signed-off-by: Jens Axboe <axboe at kernel.dk>

---

diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index 9df4f71e58ca..25981b30a25d 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -1347,13 +1347,19 @@ static void nvme_set_chunk_size(struct nvme_ns *ns)
 	blk_queue_chunk_sectors(ns->queue, rounddown_pow_of_two(chunk_size));
 }
 
-static void nvme_config_discard(struct nvme_ctrl *ctrl,
-		unsigned stream_alignment, struct request_queue *queue)
+static void nvme_config_discard(struct nvme_ns *ns)
 {
+	struct nvme_ctrl *ctrl = ns->ctrl;
+	struct request_queue *queue = ns->queue;
 	u32 size = queue_logical_block_size(queue);
 
-	if (stream_alignment)
-		size *= stream_alignment;
+	if (!(ctrl->oncs & NVME_CTRL_ONCS_DSM)) {
+		blk_queue_flag_clear(QUEUE_FLAG_DISCARD, queue);
+		return;
+	}
+
+	if (ctrl->nr_streams && ns->sws && ns->sgs)
+		size *= ns->sws * ns->sgs;
 
 	BUILD_BUG_ON(PAGE_SIZE / sizeof(struct nvme_dsm_range) <
 			NVME_DSM_MAX_RANGES);
@@ -1361,6 +1367,10 @@ static void nvme_config_discard(struct nvme_ctrl *ctrl,
 	queue->limits.discard_alignment = 0;
 	queue->limits.discard_granularity = size;
 
+	/* If discard is already enabled, don't reset queue limits */
+	if (blk_queue_flag_test_and_set(QUEUE_FLAG_DISCARD, queue))
+		return;
+
 	blk_queue_max_discard_sectors(queue, UINT_MAX);
 	blk_queue_max_discard_segments(queue, NVME_DSM_MAX_RANGES);
 	blk_queue_flag_set(QUEUE_FLAG_DISCARD, queue);
@@ -1407,10 +1417,6 @@ static void nvme_update_disk_info(struct gendisk *disk,
 {
 	sector_t capacity = le64_to_cpup(&id->nsze) << (ns->lba_shift - 9);
 	unsigned short bs = 1 << ns->lba_shift;
-	unsigned stream_alignment = 0;
-
-	if (ns->ctrl->nr_streams && ns->sws && ns->sgs)
-		stream_alignment = ns->sws * ns->sgs;
 
 	blk_mq_freeze_queue(disk->queue);
 	blk_integrity_unregister(disk);
@@ -1424,10 +1430,9 @@ static void nvme_update_disk_info(struct gendisk *disk,
 		nvme_init_integrity(disk, ns->ms, ns->pi_type);
 	if (ns->ms && !nvme_ns_has_pi(ns) && !blk_get_integrity(disk))
 		capacity = 0;
-	set_capacity(disk, capacity);
 
-	if (ns->ctrl->oncs & NVME_CTRL_ONCS_DSM)
-		nvme_config_discard(ns->ctrl, stream_alignment, disk->queue);
+	set_capacity(disk, capacity);
+	nvme_config_discard(ns);
 	blk_mq_unfreeze_queue(disk->queue);
 }
 

-- 
Jens Axboe

[PATCH v2] nvme: only reconfigure discard if necessary

[Keith Busch]

On Wed, May 02, 2018@11:06:54AM -0600, Jens Axboe wrote:
> Currently nvme reconfigures discard for every disk revalidation. This
> is problematic because any O_WRONLY or O_RDWR open will trigger a
> partition scan through udev/systemd, and we will reconfigure discard.
> This blows away any user settings, like discard_max_bytes.
> 
> Only re-configure the user settable settings if we need to.
> 
> Signed-off-by: Jens Axboe <axboe at kernel.dk>

Thanks, applied to nvme-4.18 with a minor modification removing the
redundant QUEUE_FLAG_DISCARD flag set:
  
> +	/* If discard is already enabled, don't reset queue limits */
> +	if (blk_queue_flag_test_and_set(QUEUE_FLAG_DISCARD, queue))
> +		return;
> +
>  	blk_queue_max_discard_sectors(queue, UINT_MAX);
>  	blk_queue_max_discard_segments(queue, NVME_DSM_MAX_RANGES);
>  	blk_queue_flag_set(QUEUE_FLAG_DISCARD, queue);

-  	blk_queue_flag_set(QUEUE_FLAG_DISCARD, queue);