block: take io_opt and io_min into account for max_sectors

The soft max_sectors limit is normally capped by the hardware limits and
an arbitrary upper limit enforced by the kernel, but can be modified by
the user.  A few drivers want to increase this limit (nbd, rbd) or
adjust it up or down based on hardware capabilities (sd).

Change blk_validate_limits to default max_sectors to the optimal I/O
size, or upgrade it to the preferred minimal I/O size if that is
larger than the kernel default if no optimal I/O size is provided based
on the logic in the SD driver.

This keeps the existing kernel default for drivers that do not provide
an io_opt or very big io_min value, but picks a much more useful
default for those who provide these hints, and allows to remove the
hacks to set the user max_sectors limit in nbd, rbd and sd.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Bart Van Assche <bvanassche@acm.org>
Reviewed-by: Damien Le Moal <dlemoal@kernel.org>
Acked-by: Ilya Dryomov <idryomov@gmail.com>
Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com>
Link: https://lore.kernel.org/r/20240531074837.1648501-5-hch@lst.deSigned-off-by: Jens Axboe <axboe@kernel.dk>

block/blk-settings.c

@@ -153,6 +153,13 @@ static int blk_validate_limits(struct queue_limits *lim)
 		if (lim->max_user_sectors < PAGE_SIZE / SECTOR_SIZE)
 			return -EINVAL;
 		lim->max_sectors = min(max_hw_sectors, lim->max_user_sectors);
+	} else if (lim->io_opt) {
+		lim->max_sectors =
+			min(max_hw_sectors, lim->io_opt >> SECTOR_SHIFT);
+	} else if (lim->io_min &&
+		   lim->io_min > (BLK_DEF_MAX_SECTORS_CAP << SECTOR_SHIFT)) {
+		lim->max_sectors =
+			min(max_hw_sectors, lim->io_min >> SECTOR_SHIFT);
 	} else {
 		lim->max_sectors = min(max_hw_sectors, BLK_DEF_MAX_SECTORS_CAP);
 	}

drivers/block/nbd.c

@@ -1808,7 +1808,7 @@ static struct nbd_device *nbd_dev_add(int index, unsigned int refs)
 {
 	struct queue_limits lim = {
 		.max_hw_sectors		= 65536,
-		.max_user_sectors	= 256,
+		.io_opt			= 256 << SECTOR_SHIFT,
 		.max_segments		= USHRT_MAX,
 		.max_segment_size	= UINT_MAX,
 	};

drivers/block/rbd.c

@@ -4954,7 +4954,6 @@ static int rbd_init_disk(struct rbd_device *rbd_dev)
 	    rbd_dev->layout.object_size * rbd_dev->layout.stripe_count;
 	struct queue_limits lim = {
 		.max_hw_sectors		= objset_bytes >> SECTOR_SHIFT,
-		.max_user_sectors	= objset_bytes >> SECTOR_SHIFT,
 		.io_opt			= objset_bytes,
 		.io_min			= rbd_dev->opts->alloc_size,
 		.max_segments		= USHRT_MAX,

drivers/scsi/sd.c

@@ -3593,7 +3593,7 @@ static int sd_revalidate_disk(struct gendisk *disk)
 	struct request_queue *q = sdkp->disk->queue;
 	sector_t old_capacity = sdkp->capacity;
 	unsigned char *buffer;
-	unsigned int dev_max, rw_max;
+	unsigned int dev_max;
 
 	SCSI_LOG_HLQUEUE(3, sd_printk(KERN_INFO, sdkp,
 				      "sd_revalidate_disk\n"));
@@ -3675,34 +3675,15 @@ static int sd_revalidate_disk(struct gendisk *disk)
 	else
 		blk_queue_io_min(sdkp->disk->queue, 0);
 
-	if (sd_validate_opt_xfer_size(sdkp, dev_max)) {
-		q->limits.io_opt = logical_to_bytes(sdp, sdkp->opt_xfer_blocks);
-		rw_max = logical_to_sectors(sdp, sdkp->opt_xfer_blocks);
-	} else {
-		q->limits.io_opt = 0;
-		rw_max = min_not_zero(logical_to_sectors(sdp, dev_max),
-				      (sector_t)BLK_DEF_MAX_SECTORS_CAP);
-	}
-
 	/*
 	 * Limit default to SCSI host optimal sector limit if set. There may be
 	 * an impact on performance for when the size of a request exceeds this
 	 * host limit.
 	 */
-	rw_max = min_not_zero(rw_max, sdp->host->opt_sectors);
-
-	/* Do not exceed controller limit */
-	rw_max = min(rw_max, queue_max_hw_sectors(q));
-
-	/*
-	 * Only update max_sectors if previously unset or if the current value
-	 * exceeds the capabilities of the hardware.
-	 */
-	if (sdkp->first_scan ||
-	    q->limits.max_sectors > q->limits.max_dev_sectors ||
-	    q->limits.max_sectors > q->limits.max_hw_sectors) {
-		q->limits.max_sectors = rw_max;
-		q->limits.max_user_sectors = rw_max;
+	q->limits.io_opt = sdp->host->opt_sectors << SECTOR_SHIFT;
+	if (sd_validate_opt_xfer_size(sdkp, dev_max)) {
+		q->limits.io_opt = min_not_zero(q->limits.io_opt,
+				logical_to_bytes(sdp, sdkp->opt_xfer_blocks));
 	}
 
 	sdkp->first_scan = 0;