[2/2] loop: Better discard support for block devices

Commit Message

Andrzej Pietrasiewicz March 17, 2020, 3:11 p.m. UTC

From: Evan Green <[e-mail]>

If the backing device for a loop device is a block device,
then mirror the "write zeroes" capabilities of the underlying
block device into the loop device. Copy this capability into both
max_write_zeroes_sectors and max_discard_sectors of the loop device.

The reason for this is that REQ_OP_DISCARD on a loop device translates
into blkdev_issue_zeroout(), rather than blkdev_issue_discard(). This
presents a consistent interface for loop devices (that discarded data
is zeroed), regardless of the backing device type of the loop device.
There should be no behavior change for loop devices backed by regular
files.

This change fixes blktest block/003, and removes an extraneous
error print in block/013 when testing on a loop device backed
by a block device that does not support discard.

Signed-off-by: Evan Green <[e-mail]>
[rebase onto v5.6-rc6]
Signed-off-by: Andrzej Pietrasiewicz <[e-mail]>

---

Changes in v5:
- Don't mirror discard if lo_encrypt_key_size is non-zero (Gwendal)

Changes in v4:
- Mirror blkdev's write_zeroes into loopdev's discard_sectors.

Changes in v3:
- Updated commit description

Changes in v2: None
---
 drivers/block/loop.c | 42 +++++++++++++++++++++++++++++++-----------
 1 file changed, 31 insertions(+), 11 deletions(-)

Patch

diff --git a/drivers/block/loop.c b/drivers/block/loop.c
index 87307454f768..8de3b2b098d3 100644
--- a/drivers/block/loop.c
+++ b/drivers/block/loop.c
@@ -427,11 +427,12 @@  static int lo_fallocate(struct loop_device *lo, struct request *rq, loff_t pos,
 	 * information.
 	 */
 	struct file *file = lo->lo_backing_file;
+	struct request_queue *q = lo->lo_queue;
 	int ret;
 
 	mode |= FALLOC_FL_KEEP_SIZE;
 
-	if ((!file->f_op->fallocate) || lo->lo_encrypt_key_size) {
+	if (!blk_queue_discard(q)) {
 		ret = -EOPNOTSUPP;
 		goto out;
 	}
@@ -867,28 +868,47 @@  static void loop_config_discard(struct loop_device *lo)
 	struct inode *inode = file->f_mapping->host;
 	struct request_queue *q = lo->lo_queue;
 
+
+	/*
+	 * If the backing device is a block device, mirror its zeroing
+	 * capability. REQ_OP_DISCARD translates to a zero-out even when backed
+	 * by block devices to keep consistent behavior with file-backed loop
+	 * devices.
+	 */
+	if (S_ISBLK(inode->i_mode) && !lo->lo_encrypt_key_size) {
+		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);
+
 	/*
 	 * We use punch hole to reclaim the free space used by the
 	 * image a.k.a. discard. However we do not support discard if
 	 * encryption is enabled, because it may give an attacker
 	 * useful information.
 	 */
-	if ((!file->f_op->fallocate) ||
-	    lo->lo_encrypt_key_size) {
+	} 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);
-		blk_queue_flag_clear(QUEUE_FLAG_DISCARD, q);
-		return;
-	}
 
-	q->limits.discard_granularity = inode->i_sb->s_blocksize;
-	q->limits.discard_alignment = 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);
+	}
 
-	blk_queue_max_discard_sectors(q, UINT_MAX >> 9);
-	blk_queue_max_write_zeroes_sectors(q, UINT_MAX >> 9);
-	blk_queue_flag_set(QUEUE_FLAG_DISCARD, q);
+	if (q->limits.max_write_zeroes_sectors)
+		blk_queue_flag_set(QUEUE_FLAG_DISCARD, q);
+	else
+		blk_queue_flag_clear(QUEUE_FLAG_DISCARD, q);
 }
 
 static void loop_unprepare_queue(struct loop_device *lo)