1 files changed, 120 insertions, 149 deletions

diff --git a/drivers/block/loop.c b/drivers/block/loop.c
index 86cc3b19faae..db9b5164ccca 100644
--- a/drivers/block/loop.c
+++ b/drivers/block/loop.c
@@ -233,72 +233,6 @@ static void loop_set_size(struct loop_device *lo, loff_t size)
 		kobject_uevent(&disk_to_dev(lo->lo_disk)->kobj, KOBJ_CHANGE);
 }
 
-static int lo_write_bvec(struct file *file, struct bio_vec *bvec, loff_t *ppos)
-{
-	struct iov_iter i;
-	ssize_t bw;
-
-	iov_iter_bvec(&i, ITER_SOURCE, bvec, 1, bvec->bv_len);
-
-	bw = vfs_iter_write(file, &i, ppos, 0);
-
-	if (likely(bw ==  bvec->bv_len))
-		return 0;
-
-	printk_ratelimited(KERN_ERR
-		"loop: Write error at byte offset %llu, length %i.\n",
-		(unsigned long long)*ppos, bvec->bv_len);
-	if (bw >= 0)
-		bw = -EIO;
-	return bw;
-}
-
-static int lo_write_simple(struct loop_device *lo, struct request *rq,
-		loff_t pos)
-{
-	struct bio_vec bvec;
-	struct req_iterator iter;
-	int ret = 0;
-
-	rq_for_each_segment(bvec, rq, iter) {
-		ret = lo_write_bvec(lo->lo_backing_file, &bvec, &pos);
-		if (ret < 0)
-			break;
-		cond_resched();
-	}
-
-	return ret;
-}
-
-static int lo_read_simple(struct loop_device *lo, struct request *rq,
-		loff_t pos)
-{
-	struct bio_vec bvec;
-	struct req_iterator iter;
-	struct iov_iter i;
-	ssize_t len;
-
-	rq_for_each_segment(bvec, rq, iter) {
-		iov_iter_bvec(&i, ITER_DEST, &bvec, 1, bvec.bv_len);
-		len = vfs_iter_read(lo->lo_backing_file, &i, &pos, 0);
-		if (len < 0)
-			return len;
-
-		flush_dcache_page(bvec.bv_page);
-
-		if (len != bvec.bv_len) {
-			struct bio *bio;
-
-			__rq_for_each_bio(bio, rq)
-				zero_fill_bio(bio);
-			break;
-		}
-		cond_resched();
-	}
-
-	return 0;
-}
-
 static void loop_clear_limits(struct loop_device *lo, int mode)
 {
 	struct queue_limits lim = queue_limits_start_update(lo->lo_queue);
@@ -357,7 +291,7 @@ static void lo_complete_rq(struct request *rq)
 	struct loop_cmd *cmd = blk_mq_rq_to_pdu(rq);
 	blk_status_t ret = BLK_STS_OK;
 
-	if (!cmd->use_aio || cmd->ret < 0 || cmd->ret == blk_rq_bytes(rq) ||
+	if (cmd->ret < 0 || cmd->ret == blk_rq_bytes(rq) ||
 	    req_op(rq) != REQ_OP_READ) {
 		if (cmd->ret < 0)
 			ret = errno_to_blk_status(cmd->ret);
@@ -373,14 +307,13 @@ static void lo_complete_rq(struct request *rq)
 		cmd->ret = 0;
 		blk_mq_requeue_request(rq, true);
 	} else {
-		if (cmd->use_aio) {
-			struct bio *bio = rq->bio;
+		struct bio *bio = rq->bio;
 
-			while (bio) {
-				zero_fill_bio(bio);
-				bio = bio->bi_next;
-			}
+		while (bio) {
+			zero_fill_bio(bio);
+			bio = bio->bi_next;
 		}
+
 		ret = BLK_STS_IOERR;
 end_io:
 		blk_mq_end_request(rq, ret);
@@ -395,6 +328,8 @@ static void lo_rw_aio_do_completion(struct loop_cmd *cmd)
 		return;
 	kfree(cmd->bvec);
 	cmd->bvec = NULL;
+	if (req_op(rq) == REQ_OP_WRITE)
+		kiocb_end_write(&cmd->iocb);
 	if (likely(!blk_should_fake_timeout(rq->q)))
 		blk_mq_complete_request(rq);
 }
@@ -460,20 +395,26 @@ static int lo_rw_aio(struct loop_device *lo, struct loop_cmd *cmd,
 
 	cmd->iocb.ki_pos = pos;
 	cmd->iocb.ki_filp = file;
-	cmd->iocb.ki_complete = lo_rw_aio_complete;
-	cmd->iocb.ki_flags = IOCB_DIRECT;
-	cmd->iocb.ki_ioprio = IOPRIO_PRIO_VALUE(IOPRIO_CLASS_NONE, 0);
+	cmd->iocb.ki_ioprio = req_get_ioprio(rq);
+	if (cmd->use_aio) {
+		cmd->iocb.ki_complete = lo_rw_aio_complete;
+		cmd->iocb.ki_flags = IOCB_DIRECT;
+	} else {
+		cmd->iocb.ki_complete = NULL;
+		cmd->iocb.ki_flags = 0;
+	}
 
-	if (rw == ITER_SOURCE)
+	if (rw == ITER_SOURCE) {
+		kiocb_start_write(&cmd->iocb);
 		ret = file->f_op->write_iter(&cmd->iocb, &iter);
-	else
+	} else
 		ret = file->f_op->read_iter(&cmd->iocb, &iter);
 
 	lo_rw_aio_do_completion(cmd);
 
 	if (ret != -EIOCBQUEUED)
 		lo_rw_aio_complete(&cmd->iocb, ret);
-	return 0;
+	return -EIOCBQUEUED;
 }
 
 static int do_req_filebacked(struct loop_device *lo, struct request *rq)
@@ -481,15 +422,6 @@ static int do_req_filebacked(struct loop_device *lo, struct request *rq)
 	struct loop_cmd *cmd = blk_mq_rq_to_pdu(rq);
 	loff_t pos = ((loff_t) blk_rq_pos(rq) << 9) + lo->lo_offset;
 
-	/*
-	 * lo_write_simple and lo_read_simple should have been covered
-	 * by io submit style function like lo_rw_aio(), one blocker
-	 * is that lo_read_simple() need to call flush_dcache_page after
-	 * the page is written from kernel, and it isn't easy to handle
-	 * this in io submit style function which submits all segments
-	 * of the req at one time. And direct read IO doesn't need to
-	 * run flush_dcache_page().
-	 */
 	switch (req_op(rq)) {
 	case REQ_OP_FLUSH:
 		return lo_req_flush(lo, rq);
@@ -505,15 +437,9 @@ static int do_req_filebacked(struct loop_device *lo, struct request *rq)
 	case REQ_OP_DISCARD:
 		return lo_fallocate(lo, rq, pos, FALLOC_FL_PUNCH_HOLE);
 	case REQ_OP_WRITE:
-		if (cmd->use_aio)
-			return lo_rw_aio(lo, cmd, pos, ITER_SOURCE);
-		else
-			return lo_write_simple(lo, rq, pos);
+		return lo_rw_aio(lo, cmd, pos, ITER_SOURCE);
 	case REQ_OP_READ:
-		if (cmd->use_aio)
-			return lo_rw_aio(lo, cmd, pos, ITER_DEST);
-		else
-			return lo_read_simple(lo, rq, pos);
+		return lo_rw_aio(lo, cmd, pos, ITER_DEST);
 	default:
 		WARN_ON_ONCE(1);
 		return -EIO;
@@ -570,6 +496,25 @@ static int loop_validate_file(struct file *file, struct block_device *bdev)
 	return 0;
 }
 
+static void loop_assign_backing_file(struct loop_device *lo, struct file *file)
+{
+	lo->lo_backing_file = file;
+	lo->old_gfp_mask = mapping_gfp_mask(file->f_mapping);
+	mapping_set_gfp_mask(file->f_mapping,
+			lo->old_gfp_mask & ~(__GFP_IO | __GFP_FS));
+}
+
+static int loop_check_backing_file(struct file *file)
+{
+	if (!file->f_op->read_iter)
+		return -EINVAL;
+
+	if ((file->f_mode & FMODE_WRITE) && !file->f_op->write_iter)
+		return -EINVAL;
+
+	return 0;
+}
+
 /*
  * loop_change_fd switched the backing store of a loopback device to
  * a new file. This is useful for operating system installers to free up
@@ -590,6 +535,10 @@ static int loop_change_fd(struct loop_device *lo, struct block_device *bdev,
 	if (!file)
 		return -EBADF;
 
+	error = loop_check_backing_file(file);
+	if (error)
+		return error;
+
 	/* suppress uevents while reconfiguring the device */
 	dev_set_uevent_suppress(disk_to_dev(lo->lo_disk), 1);
 
@@ -622,10 +571,7 @@ static int loop_change_fd(struct loop_device *lo, struct block_device *bdev,
 	disk_force_media_change(lo->lo_disk);
 	blk_mq_freeze_queue(lo->lo_queue);
 	mapping_set_gfp_mask(old_file->f_mapping, lo->old_gfp_mask);
-	lo->lo_backing_file = file;
-	lo->old_gfp_mask = mapping_gfp_mask(file->f_mapping);
-	mapping_set_gfp_mask(file->f_mapping,
-			     lo->old_gfp_mask & ~(__GFP_IO|__GFP_FS));
+	loop_assign_backing_file(lo, file);
 	loop_update_dio(lo);
 	blk_mq_unfreeze_queue(lo->lo_queue);
 	partscan = lo->lo_flags & LO_FLAGS_PARTSCAN;
@@ -645,19 +591,20 @@ static int loop_change_fd(struct loop_device *lo, struct block_device *bdev,
 	 * dependency.
 	 */
 	fput(old_file);
+	dev_set_uevent_suppress(disk_to_dev(lo->lo_disk), 0);
 	if (partscan)
 		loop_reread_partitions(lo);
 
 	error = 0;
 done:
-	/* enable and uncork uevent now that we are done */
-	dev_set_uevent_suppress(disk_to_dev(lo->lo_disk), 0);
+	kobject_uevent(&disk_to_dev(lo->lo_disk)->kobj, KOBJ_CHANGE);
 	return error;
 
 out_err:
 	loop_global_unlock(lo, is_loop);
 out_putf:
 	fput(file);
+	dev_set_uevent_suppress(disk_to_dev(lo->lo_disk), 0);
 	goto done;
 }
 
@@ -770,12 +717,11 @@ static void loop_sysfs_exit(struct loop_device *lo)
 				   &loop_attribute_group);
 }
 
-static void loop_config_discard(struct loop_device *lo,
-		struct queue_limits *lim)
+static void loop_get_discard_config(struct loop_device *lo,
+				    u32 *granularity, u32 *max_discard_sectors)
 {
 	struct file *file = lo->lo_backing_file;
 	struct inode *inode = file->f_mapping->host;
-	u32 granularity = 0, max_discard_sectors = 0;
 	struct kstatfs sbuf;
 
 	/*
@@ -786,27 +732,19 @@ static void loop_config_discard(struct loop_device *lo,
 	 * file-backed loop devices: discarded regions read back as zero.
 	 */
 	if (S_ISBLK(inode->i_mode)) {
-		struct request_queue *backingq = bdev_get_queue(I_BDEV(inode));
+		struct block_device *bdev = I_BDEV(inode);
 
-		max_discard_sectors = backingq->limits.max_write_zeroes_sectors;
-		granularity = bdev_discard_granularity(I_BDEV(inode)) ?:
-			queue_physical_block_size(backingq);
+		*max_discard_sectors = bdev_write_zeroes_sectors(bdev);
+		*granularity = bdev_discard_granularity(bdev);
 
 	/*
 	 * We use punch hole to reclaim the free space used by the
 	 * image a.k.a. discard.
 	 */
 	} else if (file->f_op->fallocate && !vfs_statfs(&file->f_path, &sbuf)) {
-		max_discard_sectors = UINT_MAX >> 9;
-		granularity = sbuf.f_bsize;
+		*max_discard_sectors = UINT_MAX >> 9;
+		*granularity = sbuf.f_bsize;
 	}
-
-	lim->max_hw_discard_sectors = max_discard_sectors;
-	lim->max_write_zeroes_sectors = max_discard_sectors;
-	if (max_discard_sectors)
-		lim->discard_granularity = granularity;
-	else
-		lim->discard_granularity = 0;
 }
 
 struct loop_worker {
@@ -981,17 +919,18 @@ static unsigned int loop_default_blocksize(struct loop_device *lo,
 		struct block_device *backing_bdev)
 {
 	/* In case of direct I/O, match underlying block size */
-	if ((lo->lo_backing_file->f_flags & O_DIRECT) && backing_bdev)
+	if ((lo->lo_flags & LO_FLAGS_DIRECT_IO) && backing_bdev)
 		return bdev_logical_block_size(backing_bdev);
 	return SECTOR_SIZE;
 }
 
-static int loop_reconfigure_limits(struct loop_device *lo, unsigned int bsize)
+static void loop_update_limits(struct loop_device *lo, struct queue_limits *lim,
+		unsigned int bsize)
 {
 	struct file *file = lo->lo_backing_file;
 	struct inode *inode = file->f_mapping->host;
 	struct block_device *backing_bdev = NULL;
-	struct queue_limits lim;
+	u32 granularity = 0, max_discard_sectors = 0;
 
 	if (S_ISBLK(inode->i_mode))
 		backing_bdev = I_BDEV(inode);
@@ -1001,17 +940,22 @@ static int loop_reconfigure_limits(struct loop_device *lo, unsigned int bsize)
 	if (!bsize)
 		bsize = loop_default_blocksize(lo, backing_bdev);
 
-	lim = queue_limits_start_update(lo->lo_queue);
-	lim.logical_block_size = bsize;
-	lim.physical_block_size = bsize;
-	lim.io_min = bsize;
-	lim.features &= ~(BLK_FEAT_WRITE_CACHE | BLK_FEAT_ROTATIONAL);
+	loop_get_discard_config(lo, &granularity, &max_discard_sectors);
+
+	lim->logical_block_size = bsize;
+	lim->physical_block_size = bsize;
+	lim->io_min = bsize;
+	lim->features &= ~(BLK_FEAT_WRITE_CACHE | BLK_FEAT_ROTATIONAL);
 	if (file->f_op->fsync && !(lo->lo_flags & LO_FLAGS_READ_ONLY))
-		lim.features |= BLK_FEAT_WRITE_CACHE;
+		lim->features |= BLK_FEAT_WRITE_CACHE;
 	if (backing_bdev && !bdev_nonrot(backing_bdev))
-		lim.features |= BLK_FEAT_ROTATIONAL;
-	loop_config_discard(lo, &lim);
-	return queue_limits_commit_update(lo->lo_queue, &lim);
+		lim->features |= BLK_FEAT_ROTATIONAL;
+	lim->max_hw_discard_sectors = max_discard_sectors;
+	lim->max_write_zeroes_sectors = max_discard_sectors;
+	if (max_discard_sectors)
+		lim->discard_granularity = granularity;
+	else
+		lim->discard_granularity = 0;
 }
 
 static int loop_configure(struct loop_device *lo, blk_mode_t mode,
@@ -1019,7 +963,7 @@ static int loop_configure(struct loop_device *lo, blk_mode_t mode,
 			  const struct loop_config *config)
 {
 	struct file *file = fget(config->fd);
-	struct address_space *mapping;
+	struct queue_limits lim;
 	int error;
 	loff_t size;
 	bool partscan;
@@ -1027,6 +971,11 @@ static int loop_configure(struct loop_device *lo, blk_mode_t mode,
 
 	if (!file)
 		return -EBADF;
+
+	error = loop_check_backing_file(file);
+	if (error)
+		return error;
+
 	is_loop = is_loop_device(file);
 
 	/* This is safe, since we have a reference from open(). */
@@ -1054,8 +1003,6 @@ static int loop_configure(struct loop_device *lo, blk_mode_t mode,
 	if (error)
 		goto out_unlock;
 
-	mapping = file->f_mapping;
-
 	if ((config->info.lo_flags & ~LOOP_CONFIGURE_SETTABLE_FLAGS) != 0) {
 		error = -EINVAL;
 		goto out_unlock;
@@ -1087,11 +1034,11 @@ static int loop_configure(struct loop_device *lo, blk_mode_t mode,
 
 	lo->use_dio = lo->lo_flags & LO_FLAGS_DIRECT_IO;
 	lo->lo_device = bdev;
-	lo->lo_backing_file = file;
-	lo->old_gfp_mask = mapping_gfp_mask(mapping);
-	mapping_set_gfp_mask(mapping, lo->old_gfp_mask & ~(__GFP_IO|__GFP_FS));
+	loop_assign_backing_file(lo, file);
 
-	error = loop_reconfigure_limits(lo, config->block_size);
+	lim = queue_limits_start_update(lo->lo_queue);
+	loop_update_limits(lo, &lim, config->block_size);
+	error = queue_limits_commit_update(lo->lo_queue, &lim);
 	if (error)
 		goto out_unlock;
 
@@ -1111,8 +1058,8 @@ static int loop_configure(struct loop_device *lo, blk_mode_t mode,
 	if (partscan)
 		clear_bit(GD_SUPPRESS_PART_SCAN, &lo->lo_disk->state);
 
-	/* enable and uncork uevent now that we are done */
 	dev_set_uevent_suppress(disk_to_dev(lo->lo_disk), 0);
+	kobject_uevent(&disk_to_dev(lo->lo_disk)->kobj, KOBJ_CHANGE);
 
 	loop_global_unlock(lo, is_loop);
 	if (partscan)
@@ -1457,24 +1404,49 @@ static int loop_set_dio(struct loop_device *lo, unsigned long arg)
 	return error;
 }
 
-static int loop_set_block_size(struct loop_device *lo, unsigned long arg)
+static int loop_set_block_size(struct loop_device *lo, blk_mode_t mode,
+			       struct block_device *bdev, unsigned long arg)
 {
+	struct queue_limits lim;
 	int err = 0;
 
-	if (lo->lo_state != Lo_bound)
-		return -ENXIO;
+	/*
+	 * If we don't hold exclusive handle for the device, upgrade to it
+	 * here to avoid changing device under exclusive owner.
+	 */
+	if (!(mode & BLK_OPEN_EXCL)) {
+		err = bd_prepare_to_claim(bdev, loop_set_block_size, NULL);
+		if (err)
+			return err;
+	}
+
+	err = mutex_lock_killable(&lo->lo_mutex);
+	if (err)
+		goto abort_claim;
+
+	if (lo->lo_state != Lo_bound) {
+		err = -ENXIO;
+		goto unlock;
+	}
 
 	if (lo->lo_queue->limits.logical_block_size == arg)
-		return 0;
+		goto unlock;
 
 	sync_blockdev(lo->lo_device);
 	invalidate_bdev(lo->lo_device);
 
 	blk_mq_freeze_queue(lo->lo_queue);
-	err = loop_reconfigure_limits(lo, arg);
+	lim = queue_limits_start_update(lo->lo_queue);
+	loop_update_limits(lo, &lim, arg);
+	err = queue_limits_commit_update(lo->lo_queue, &lim);
 	loop_update_dio(lo);
 	blk_mq_unfreeze_queue(lo->lo_queue);
 
+unlock:
+	mutex_unlock(&lo->lo_mutex);
+abort_claim:
+	if (!(mode & BLK_OPEN_EXCL))
+		bd_abort_claiming(bdev, loop_set_block_size);
 	return err;
 }
 
@@ -1493,9 +1465,6 @@ static int lo_simple_ioctl(struct loop_device *lo, unsigned int cmd,
 	case LOOP_SET_DIRECT_IO:
 		err = loop_set_dio(lo, arg);
 		break;
-	case LOOP_SET_BLOCK_SIZE:
-		err = loop_set_block_size(lo, arg);
-		break;
 	default:
 		err = -EINVAL;
 	}
@@ -1550,9 +1519,12 @@ static int lo_ioctl(struct block_device *bdev, blk_mode_t mode,
 		break;
 	case LOOP_GET_STATUS64:
 		return loop_get_status64(lo, argp);
+	case LOOP_SET_BLOCK_SIZE:
+		if (!(mode & BLK_OPEN_WRITE) && !capable(CAP_SYS_ADMIN))
+			return -EPERM;
+		return loop_set_block_size(lo, mode, bdev, arg);
 	case LOOP_SET_CAPACITY:
 	case LOOP_SET_DIRECT_IO:
-	case LOOP_SET_BLOCK_SIZE:
 		if (!(mode & BLK_OPEN_WRITE) && !capable(CAP_SYS_ADMIN))
 			return -EPERM;
 		fallthrough;
@@ -1888,7 +1860,6 @@ static void loop_handle_cmd(struct loop_cmd *cmd)
 	struct loop_device *lo = rq->q->queuedata;
 	int ret = 0;
 	struct mem_cgroup *old_memcg = NULL;
-	const bool use_aio = cmd->use_aio;
 
 	if (write && (lo->lo_flags & LO_FLAGS_READ_ONLY)) {
 		ret = -EIO;
@@ -1918,7 +1889,7 @@ static void loop_handle_cmd(struct loop_cmd *cmd)
 	}
  failed:
 	/* complete non-aio request */
-	if (!use_aio || ret) {
+	if (ret != -EIOCBQUEUED) {
 		if (ret == -EOPNOTSUPP)
 			cmd->ret = ret;
 		else