block: lift setting the readahead size into the block layer

Drivers shouldn't really mess with the readahead size, as that is a VM
concept.  Instead set it based on the optimal I/O size by lifting the
algorithm from the md driver when registering the disk.  Also set
bdi->io_pages there as well by applying the same scheme based on
max_sectors.  To ensure the limits work well for stacking drivers a
new helper is added to update the readahead limits from the block
limits, which is also called from disk_stack_limits.
Signed-off-by: NChristoph Hellwig <hch@lst.de>
Reviewed-by: NJohannes Thumshirn <johannes.thumshirn@wdc.com>
Reviewed-by: NJan Kara <jack@suse.cz>
Reviewed-by: NMike Snitzer <snitzer@redhat.com>
Reviewed-by: NMartin K. Petersen <martin.petersen@oracle.com>
Acked-by: NColy Li <colyli@suse.de>
Signed-off-by: NJens Axboe <axboe@kernel.dk>

block/blk-settings.c

@@ -372,6 +372,19 @@ void blk_queue_alignment_offset(struct request_queue *q, unsigned int offset)
 }
 EXPORT_SYMBOL(blk_queue_alignment_offset);
 
+void blk_queue_update_readahead(struct request_queue *q)
+{
+	/*
+	 * For read-ahead of large files to be effective, we need to read ahead
+	 * at least twice the optimal I/O size.
+	 */
+	q->backing_dev_info->ra_pages =
+		max(queue_io_opt(q) * 2 / PAGE_SIZE, VM_READAHEAD_PAGES);
+	q->backing_dev_info->io_pages =
+		queue_max_sectors(q) >> (PAGE_SHIFT - 9);
+}
+EXPORT_SYMBOL_GPL(blk_queue_update_readahead);
+
 /**
  * blk_limits_io_min - set minimum request size for a device
  * @limits: the queue limits
@@ -450,6 +463,8 @@ EXPORT_SYMBOL(blk_limits_io_opt);
 void blk_queue_io_opt(struct request_queue *q, unsigned int opt)
 {
 	blk_limits_io_opt(&q->limits, opt);
+	q->backing_dev_info->ra_pages =
+		max(queue_io_opt(q) * 2 / PAGE_SIZE, VM_READAHEAD_PAGES);
 }
 EXPORT_SYMBOL(blk_queue_io_opt);
 
@@ -631,8 +646,7 @@ void disk_stack_limits(struct gendisk *disk, struct block_device *bdev,
 		       top, bottom);
 	}
 
-	t->backing_dev_info->io_pages =
-		t->limits.max_sectors >> (PAGE_SHIFT - 9);
+	blk_queue_update_readahead(disk->queue);
 }
 EXPORT_SYMBOL(disk_stack_limits);
 

block/blk-sysfs.c

@@ -854,6 +854,8 @@ int blk_register_queue(struct gendisk *disk)
 		percpu_ref_switch_to_percpu(&q->q_usage_counter);
 	}
 
+	blk_queue_update_readahead(q);
+
 	ret = blk_trace_init_sysfs(dev);
 	if (ret)
 		return ret;

drivers/block/aoe/aoeblk.c

@@ -406,7 +406,6 @@ aoeblk_gdalloc(void *vp)
 	WARN_ON(d->gd);
 	WARN_ON(d->flags & DEVFL_UP);
 	blk_queue_max_hw_sectors(q, BLK_DEF_MAX_SECTORS);
-	q->backing_dev_info->ra_pages = SZ_2M / PAGE_SIZE;
 	blk_queue_io_opt(q, SZ_2M);
 	d->bufpool = mp;
 	d->blkq = gd->queue = q;

drivers/block/drbd/drbd_nl.c

@@ -1362,15 +1362,7 @@ static void drbd_setup_queue_param(struct drbd_device *device, struct drbd_backi
 
 	if (b) {
 		blk_stack_limits(&q->limits, &b->limits, 0);
-
-		if (q->backing_dev_info->ra_pages !=
-		    b->backing_dev_info->ra_pages) {
-			drbd_info(device, "Adjusting my ra_pages to backing device's (%lu -> %lu)\n",
-				 q->backing_dev_info->ra_pages,
-				 b->backing_dev_info->ra_pages);
-			q->backing_dev_info->ra_pages =
-						b->backing_dev_info->ra_pages;
-		}
+		blk_queue_update_readahead(q);
 	}
 	fixup_discard_if_not_supported(q);
 	fixup_write_zeroes(device, q);

drivers/md/bcache/super.c

@@ -1427,9 +1427,6 @@ static int cached_dev_init(struct cached_dev *dc, unsigned int block_size)
 	if (ret)
 		return ret;
 
-	dc->disk.disk->queue->backing_dev_info->ra_pages =
-		max(dc->disk.disk->queue->backing_dev_info->ra_pages,
-		    q->backing_dev_info->ra_pages);
 	blk_queue_io_opt(dc->disk.disk->queue,
 		max(queue_io_opt(dc->disk.disk->queue), queue_io_opt(q)));
 

drivers/md/dm-table.c

@@ -1925,8 +1925,7 @@ void dm_table_set_restrictions(struct dm_table *t, struct request_queue *q,
 	}
 #endif
 
-	/* Allow reads to exceed readahead limits */
-	q->backing_dev_info->io_pages = limits->max_sectors >> (PAGE_SHIFT - 9);
+	blk_queue_update_readahead(q);
 }
 
 unsigned int dm_table_get_num_targets(struct dm_table *t)

drivers/md/raid0.c

@@ -410,22 +410,6 @@ static int raid0_run(struct mddev *mddev)
 		 mdname(mddev),
 		 (unsigned long long)mddev->array_sectors);
 
-	if (mddev->queue) {
-		/* calculate the max read-ahead size.
-		 * For read-ahead of large files to be effective, we need to
-		 * readahead at least twice a whole stripe. i.e. number of devices
-		 * multiplied by chunk size times 2.
-		 * If an individual device has an ra_pages greater than the
-		 * chunk size, then we will not drive that device as hard as it
-		 * wants.  We consider this a configuration error: a larger
-		 * chunksize should be used in that case.
-		 */
-		int stripe = mddev->raid_disks *
-			(mddev->chunk_sectors << 9) / PAGE_SIZE;
-		if (mddev->queue->backing_dev_info->ra_pages < 2* stripe)
-			mddev->queue->backing_dev_info->ra_pages = 2* stripe;
-	}
-
 	dump_zones(mddev);
 
 	ret = md_integrity_register(mddev);

drivers/md/raid10.c

@@ -3873,19 +3873,6 @@ static int raid10_run(struct mddev *mddev)
 	mddev->resync_max_sectors = size;
 	set_bit(MD_FAILFAST_SUPPORTED, &mddev->flags);
 
-	if (mddev->queue) {
-		int stripe = conf->geo.raid_disks *
-			((mddev->chunk_sectors << 9) / PAGE_SIZE);
-
-		/* Calculate max read-ahead size.
-		 * We need to readahead at least twice a whole stripe....
-		 * maybe...
-		 */
-		stripe /= conf->geo.near_copies;
-		if (mddev->queue->backing_dev_info->ra_pages < 2 * stripe)
-			mddev->queue->backing_dev_info->ra_pages = 2 * stripe;
-	}
-
 	if (md_integrity_register(mddev))
 		goto out_free_conf;
 
@@ -4723,17 +4710,8 @@ static void end_reshape(struct r10conf *conf)
 	conf->reshape_safe = MaxSector;
 	spin_unlock_irq(&conf->device_lock);
 
-	/* read-ahead size must cover two whole stripes, which is
-	 * 2 * (datadisks) * chunksize where 'n' is the number of raid devices
-	 */
-	if (conf->mddev->queue) {
-		int stripe = conf->geo.raid_disks *
-			((conf->mddev->chunk_sectors << 9) / PAGE_SIZE);
-		stripe /= conf->geo.near_copies;
-		if (conf->mddev->queue->backing_dev_info->ra_pages < 2 * stripe)
-			conf->mddev->queue->backing_dev_info->ra_pages = 2 * stripe;
+	if (conf->mddev->queue)
 		raid10_set_io_opt(conf);
-	}
 	conf->fullsync = 0;
 }
 

drivers/md/raid5.c

@@ -7522,8 +7522,6 @@ static int raid5_run(struct mddev *mddev)
 		int data_disks = conf->previous_raid_disks - conf->max_degraded;
 		int stripe = data_disks *
 			((mddev->chunk_sectors << 9) / PAGE_SIZE);
-		if (mddev->queue->backing_dev_info->ra_pages < 2 * stripe)
-			mddev->queue->backing_dev_info->ra_pages = 2 * stripe;
 
 		chunk_size = mddev->chunk_sectors << 9;
 		blk_queue_io_min(mddev->queue, chunk_size);
@@ -8111,17 +8109,8 @@ static void end_reshape(struct r5conf *conf)
 		spin_unlock_irq(&conf->device_lock);
 		wake_up(&conf->wait_for_overlap);
 
-		/* read-ahead size must cover two whole stripes, which is
-		 * 2 * (datadisks) * chunksize where 'n' is the number of raid devices
-		 */
-		if (conf->mddev->queue) {
-			int data_disks = conf->raid_disks - conf->max_degraded;
-			int stripe = data_disks * ((conf->chunk_sectors << 9)
-						   / PAGE_SIZE);
-			if (conf->mddev->queue->backing_dev_info->ra_pages < 2 * stripe)
-				conf->mddev->queue->backing_dev_info->ra_pages = 2 * stripe;
+		if (conf->mddev->queue)
 			raid5_set_io_opt(conf);
-		}
 	}
 }
 

drivers/nvme/host/core.c

@@ -2147,6 +2147,7 @@ static int __nvme_revalidate_disk(struct gendisk *disk, struct nvme_id_ns *id)
 		nvme_update_disk_info(ns->head->disk, ns, id);
 		blk_stack_limits(&ns->head->disk->queue->limits,
 				 &ns->queue->limits, 0);
+		blk_queue_update_readahead(ns->head->disk->queue);
 		nvme_update_bdev_size(ns->head->disk);
 	}
 #endif

include/linux/blkdev.h

@@ -1140,6 +1140,7 @@ extern void blk_queue_max_zone_append_sectors(struct request_queue *q,
 extern void blk_queue_physical_block_size(struct request_queue *, unsigned int);
 extern void blk_queue_alignment_offset(struct request_queue *q,
 				       unsigned int alignment);
+void blk_queue_update_readahead(struct request_queue *q);
 extern void blk_limits_io_min(struct queue_limits *limits, unsigned int min);
 extern void blk_queue_io_min(struct request_queue *q, unsigned int min);
 extern void blk_limits_io_opt(struct queue_limits *limits, unsigned int opt);