1 files changed, 59 insertions, 22 deletions

diff --git a/drivers/block/loop.c b/drivers/block/loop.c
index 61b2842b3f26..a1522cd580de 100644
--- a/drivers/block/loop.c
+++ b/drivers/block/loop.c
@@ -425,19 +425,22 @@ out_free_page:
 	return ret;
 }
 
-static int lo_discard(struct loop_device *lo, struct request *rq, loff_t pos)
+static int lo_fallocate(struct loop_device *lo, struct request *rq, loff_t pos,
+			int mode)
 {
 	/*
-	 * 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.
+	 * We use fallocate to manipulate the space mappings used by the image
+	 * a.k.a. discard/zerorange. However we do not support this if
+	 * encryption is enabled, because it may give an attacker useful
+	 * information.
 	 */
 	struct file *file = lo->lo_backing_file;
-	int mode = FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE;
+	struct request_queue *q = lo->lo_queue;
 	int ret;
 
-	if ((!file->f_op->fallocate) || lo->lo_encrypt_key_size) {
+	mode |= FALLOC_FL_KEEP_SIZE;
+
+	if (!blk_queue_discard(q)) {
 		ret = -EOPNOTSUPP;
 		goto out;
 	}
@@ -604,9 +607,17 @@ static int do_req_filebacked(struct loop_device *lo, struct request *rq)
 	switch (req_op(rq)) {
 	case REQ_OP_FLUSH:
 		return lo_req_flush(lo, rq);
-	case REQ_OP_DISCARD:
 	case REQ_OP_WRITE_ZEROES:
-		return lo_discard(lo, rq, pos);
+		/*
+		 * If the caller doesn't want deallocation, call zeroout to
+		 * write zeroes the range.  Otherwise, punch them out.
+		 */
+		return lo_fallocate(lo, rq, pos,
+			(rq->cmd_flags & REQ_NOUNMAP) ?
+				FALLOC_FL_ZERO_RANGE :
+				FALLOC_FL_PUNCH_HOLE);
+	case REQ_OP_DISCARD:
+		return lo_fallocate(lo, rq, pos, FALLOC_FL_PUNCH_HOLE);
 	case REQ_OP_WRITE:
 		if (lo->transfer)
 			return lo_write_transfer(lo, rq, pos);
@@ -878,6 +889,23 @@ 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
+	 * capability. Set the discard sectors to the block device's zeroing
+	 * capabilities because loop discards result in blkdev_issue_zeroout(),
+	 * not blkdev_issue_discard(). This maintains consistent behavior with
+	 * file-backed loop devices: discarded regions read back as zero.
+	 */
+	if (S_ISBLK(inode->i_mode) && !lo->lo_encrypt_key_size) {
+		struct request_queue *backingq;
+
+		backingq = bdev_get_queue(inode->i_bdev);
+
+		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
@@ -885,22 +913,27 @@ static void loop_config_discard(struct loop_device *lo)
 	 * 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) {
+		max_discard_sectors = 0;
+		granularity = 0;
+
+	} else {
+		max_discard_sectors = UINT_MAX >> 9;
+		granularity = inode->i_sb->s_blocksize;
+	}
+
+	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 {
 		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;
-
-	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);
 }
 
 static void loop_unprepare_queue(struct loop_device *lo)
@@ -1280,7 +1313,7 @@ loop_set_status(struct loop_device *lo, const struct loop_info64 *info)
 	if (lo->lo_offset != info->lo_offset ||
 	    lo->lo_sizelimit != info->lo_sizelimit) {
 		sync_blockdev(lo->lo_device);
-		kill_bdev(lo->lo_device);
+		invalidate_bdev(lo->lo_device);
 	}
 
 	/* I/O need to be drained during transfer transition */
@@ -1554,12 +1587,12 @@ static int loop_set_block_size(struct loop_device *lo, unsigned long arg)
 
 	if (lo->lo_queue->limits.logical_block_size != arg) {
 		sync_blockdev(lo->lo_device);
-		kill_bdev(lo->lo_device);
+		invalidate_bdev(lo->lo_device);
 	}
 
 	blk_mq_freeze_queue(lo->lo_queue);
 
-	/* kill_bdev should have truncated all the pages */
+	/* invalidate_bdev should have truncated all the pages */
 	if (lo->lo_queue->limits.logical_block_size != arg &&
 			lo->lo_device->bd_inode->i_mapping->nrpages) {
 		err = -EAGAIN;
@@ -2321,6 +2354,8 @@ static void __exit loop_exit(void)
 
 	range = max_loop ? max_loop << part_shift : 1UL << MINORBITS;
 
+	mutex_lock(&loop_ctl_mutex);
+
 	idr_for_each(&loop_index_idr, &loop_exit_cb, NULL);
 	idr_destroy(&loop_index_idr);
 
@@ -2328,6 +2363,8 @@ static void __exit loop_exit(void)
 	unregister_blkdev(LOOP_MAJOR, "loop");
 
 	misc_deregister(&loop_misc);
+
+	mutex_unlock(&loop_ctl_mutex);
 }
 
 module_init(loop_init);