block: loop: set discard granularity and alignment for block device backed loop

mainline inclusion
from mainline-v5.9-rc3
commit bcb21c8c
category: bugfix
bugzilla: NA
CVE: NA

-------------------------------------------------

In case of block device backend, if the backend supports write zeros, the
loop device will set queue flag of QUEUE_FLAG_DISCARD. However,
limits.discard_granularity isn't setup, and this way is wrong,
see the following description in Documentation/ABI/testing/sysfs-block:

	A discard_granularity of 0 means that the device does not support
	discard functionality.

Especially 9b15d109 ("block: improve discard bio alignment in
__blkdev_issue_discard()") starts to take q->limits.discard_granularity
for computing max discard sectors. And zero discard granularity may cause
kernel oops, or fail discard request even though the loop queue claims
discard support via QUEUE_FLAG_DISCARD.

Fix the issue by setup discard granularity and alignment.

Fixes: c52abf56 ("loop: Better discard support for block devices")
Signed-off-by: NMing Lei <ming.lei@redhat.com>
Reviewed-by: NChristoph Hellwig <hch@lst.de>
Acked-by: NColy Li <colyli@suse.de>
Cc: Hannes Reinecke <hare@suse.com>
Cc: Xiao Ni <xni@redhat.com>
Cc: Martin K. Petersen <martin.petersen@oracle.com>
Cc: Evan Green <evgreen@chromium.org>
Cc: Gwendal Grignou <gwendal@chromium.org>
Cc: Chaitanya Kulkarni <chaitanya.kulkarni@wdc.com>
Cc: Andrzej Pietrasiewicz <andrzej.p@collabora.com>
Cc: Christoph Hellwig <hch@lst.de>
Cc: <stable@vger.kernel.org>
Signed-off-by: NJens Axboe <axboe@kernel.dk>
Signed-off-by: NYang Yingliang <yangyingliang@huawei.com>
Reviewed-by: NYufen Yu <yuyufen@huawei.com>
Signed-off-by: NYang Yingliang <yangyingliang@huawei.com>

drivers/block/loop.c

@@ -864,6 +864,7 @@ static void loop_config_discard(struct loop_device *lo)
 	struct file *file = lo->lo_backing_file;
 	struct inode *inode = file->f_mapping->host;
 	struct request_queue *q = lo->lo_queue;
+	u32 granularity, max_discard_sectors;
 
 	/*
 	 * If the backing device is a block device, mirror its zeroing
@@ -876,11 +877,10 @@ static void loop_config_discard(struct loop_device *lo)
 		struct request_queue *backingq;
 
 		backingq = bdev_get_queue(inode->i_bdev);
-		blk_queue_max_discard_sectors(q,
-			backingq->limits.max_write_zeroes_sectors);
 
-		blk_queue_max_write_zeroes_sectors(q,
-			backingq->limits.max_write_zeroes_sectors);
+		max_discard_sectors = backingq->limits.max_write_zeroes_sectors;
+		granularity = backingq->limits.discard_granularity ?:
+			queue_physical_block_size(backingq);
 
 	/*
 	 * We use punch hole to reclaim the free space used by the
@@ -889,23 +889,26 @@ static void loop_config_discard(struct loop_device *lo)
 	 * useful information.
 	 */
 	} else if (!file->f_op->fallocate || lo->lo_encrypt_key_size) {
-		q->limits.discard_granularity = 0;
-		q->limits.discard_alignment = 0;
-		blk_queue_max_discard_sectors(q, 0);
-		blk_queue_max_write_zeroes_sectors(q, 0);
+		max_discard_sectors = 0;
+		granularity = 0;
 
 	} else {
-		q->limits.discard_granularity = inode->i_sb->s_blocksize;
-		q->limits.discard_alignment = 0;
-
-		blk_queue_max_discard_sectors(q, UINT_MAX >> 9);
-		blk_queue_max_write_zeroes_sectors(q, UINT_MAX >> 9);
+		max_discard_sectors = UINT_MAX >> 9;
+		granularity = inode->i_sb->s_blocksize;
 	}
 
-	if (q->limits.max_write_zeroes_sectors)
+	if (max_discard_sectors) {
+		q->limits.discard_granularity = granularity;
+		blk_queue_max_discard_sectors(q, max_discard_sectors);
+		blk_queue_max_write_zeroes_sectors(q, max_discard_sectors);
 		blk_queue_flag_set(QUEUE_FLAG_DISCARD, q);
-	else
+	} else {
+		q->limits.discard_granularity = 0;
+		blk_queue_max_discard_sectors(q, 0);
+		blk_queue_max_write_zeroes_sectors(q, 0);
 		blk_queue_flag_clear(QUEUE_FLAG_DISCARD, q);
+	}
+	q->limits.discard_alignment = 0;
 }
 
 static void loop_unprepare_queue(struct loop_device *lo)