1 files changed, 78 insertions, 106 deletions

diff --git a/drivers/block/loop.c b/drivers/block/loop.c
index 1153721bc7c2..78a7bb28defe 100644
--- a/drivers/block/loop.c
+++ b/drivers/block/loop.c
@@ -211,13 +211,10 @@ static void __loop_update_dio(struct loop_device *lo, bool dio)
 	if (lo->lo_state == Lo_bound)
 		blk_mq_freeze_queue(lo->lo_queue);
 	lo->use_dio = use_dio;
-	if (use_dio) {
-		blk_queue_flag_clear(QUEUE_FLAG_NOMERGES, lo->lo_queue);
+	if (use_dio)
 		lo->lo_flags |= LO_FLAGS_DIRECT_IO;
-	} else {
-		blk_queue_flag_set(QUEUE_FLAG_NOMERGES, lo->lo_queue);
+	else
 		lo->lo_flags &= ~LO_FLAGS_DIRECT_IO;
-	}
 	if (lo->lo_state == Lo_bound)
 		blk_mq_unfreeze_queue(lo->lo_queue);
 }
@@ -939,24 +936,6 @@ static void loop_free_idle_workers_timer(struct timer_list *timer)
 	return loop_free_idle_workers(lo, false);
 }
 
-static void loop_update_rotational(struct loop_device *lo)
-{
-	struct file *file = lo->lo_backing_file;
-	struct inode *file_inode = file->f_mapping->host;
-	struct block_device *file_bdev = file_inode->i_sb->s_bdev;
-	struct request_queue *q = lo->lo_queue;
-	bool nonrot = true;
-
-	/* not all filesystems (e.g. tmpfs) have a sb->s_bdev */
-	if (file_bdev)
-		nonrot = bdev_nonrot(file_bdev);
-
-	if (nonrot)
-		blk_queue_flag_set(QUEUE_FLAG_NONROT, q);
-	else
-		blk_queue_flag_clear(QUEUE_FLAG_NONROT, q);
-}
-
 /**
  * loop_set_status_from_info - configure device from loop_info
  * @lo: struct loop_device to configure
@@ -998,17 +977,40 @@ loop_set_status_from_info(struct loop_device *lo,
 	return 0;
 }
 
-static int loop_reconfigure_limits(struct loop_device *lo, unsigned short bsize,
-		bool update_discard_settings)
+static unsigned short 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)
+		return bdev_logical_block_size(backing_bdev);
+	return SECTOR_SIZE;
+}
+
+static int loop_reconfigure_limits(struct loop_device *lo, unsigned short 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;
 
+	if (S_ISBLK(inode->i_mode))
+		backing_bdev = I_BDEV(inode);
+	else if (inode->i_sb->s_bdev)
+		backing_bdev = inode->i_sb->s_bdev;
+
+	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;
-	if (update_discard_settings)
-		loop_config_discard(lo, &lim);
+	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;
+	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);
 }
 
@@ -1017,12 +1019,10 @@ static int loop_configure(struct loop_device *lo, blk_mode_t mode,
 			  const struct loop_config *config)
 {
 	struct file *file = fget(config->fd);
-	struct inode *inode;
 	struct address_space *mapping;
 	int error;
 	loff_t size;
 	bool partscan;
-	unsigned short bsize;
 	bool is_loop;
 
 	if (!file)
@@ -1055,19 +1055,12 @@ static int loop_configure(struct loop_device *lo, blk_mode_t mode,
 		goto out_unlock;
 
 	mapping = file->f_mapping;
-	inode = mapping->host;
 
 	if ((config->info.lo_flags & ~LOOP_CONFIGURE_SETTABLE_FLAGS) != 0) {
 		error = -EINVAL;
 		goto out_unlock;
 	}
 
-	if (config->block_size) {
-		error = blk_validate_block_size(config->block_size);
-		if (error)
-			goto out_unlock;
-	}
-
 	error = loop_set_status_from_info(lo, &config->info);
 	if (error)
 		goto out_unlock;
@@ -1098,22 +1091,10 @@ static int loop_configure(struct loop_device *lo, blk_mode_t mode,
 	lo->old_gfp_mask = mapping_gfp_mask(mapping);
 	mapping_set_gfp_mask(mapping, lo->old_gfp_mask & ~(__GFP_IO|__GFP_FS));
 
-	if (!(lo->lo_flags & LO_FLAGS_READ_ONLY) && file->f_op->fsync)
-		blk_queue_write_cache(lo->lo_queue, true, false);
-
-	if (config->block_size)
-		bsize = config->block_size;
-	else if ((lo->lo_backing_file->f_flags & O_DIRECT) && inode->i_sb->s_bdev)
-		/* In case of direct I/O, match underlying block size */
-		bsize = bdev_logical_block_size(inode->i_sb->s_bdev);
-	else
-		bsize = 512;
-
-	error = loop_reconfigure_limits(lo, bsize, true);
-	if (WARN_ON_ONCE(error))
+	error = loop_reconfigure_limits(lo, config->block_size);
+	if (error)
 		goto out_unlock;
 
-	loop_update_rotational(lo);
 	loop_update_dio(lo);
 	loop_sysfs_init(lo);
 
@@ -1154,22 +1135,12 @@ out_putf:
 	return error;
 }
 
-static void __loop_clr_fd(struct loop_device *lo, bool release)
+static void __loop_clr_fd(struct loop_device *lo)
 {
+	struct queue_limits lim;
 	struct file *filp;
 	gfp_t gfp = lo->old_gfp_mask;
 
-	if (test_bit(QUEUE_FLAG_WC, &lo->lo_queue->queue_flags))
-		blk_queue_write_cache(lo->lo_queue, false, false);
-
-	/*
-	 * Freeze the request queue when unbinding on a live file descriptor and
-	 * thus an open device.  When called from ->release we are guaranteed
-	 * that there is no I/O in progress already.
-	 */
-	if (!release)
-		blk_mq_freeze_queue(lo->lo_queue);
-
 	spin_lock_irq(&lo->lo_lock);
 	filp = lo->lo_backing_file;
 	lo->lo_backing_file = NULL;
@@ -1179,7 +1150,14 @@ static void __loop_clr_fd(struct loop_device *lo, bool release)
 	lo->lo_offset = 0;
 	lo->lo_sizelimit = 0;
 	memset(lo->lo_file_name, 0, LO_NAME_SIZE);
-	loop_reconfigure_limits(lo, 512, false);
+
+	/* reset the block size to the default */
+	lim = queue_limits_start_update(lo->lo_queue);
+	lim.logical_block_size = SECTOR_SIZE;
+	lim.physical_block_size = SECTOR_SIZE;
+	lim.io_min = SECTOR_SIZE;
+	queue_limits_commit_update(lo->lo_queue, &lim);
+
 	invalidate_disk(lo->lo_disk);
 	loop_sysfs_exit(lo);
 	/* let user-space know about this change */
@@ -1187,8 +1165,6 @@ static void __loop_clr_fd(struct loop_device *lo, bool release)
 	mapping_set_gfp_mask(filp->f_mapping, gfp);
 	/* This is safe: open() is still holding a reference. */
 	module_put(THIS_MODULE);
-	if (!release)
-		blk_mq_unfreeze_queue(lo->lo_queue);
 
 	disk_force_media_change(lo->lo_disk);
 
@@ -1203,11 +1179,7 @@ static void __loop_clr_fd(struct loop_device *lo, bool release)
 		 * must be at least one and it can only become zero when the
 		 * current holder is released.
 		 */
-		if (!release)
-			mutex_lock(&lo->lo_disk->open_mutex);
 		err = bdev_disk_changed(lo->lo_disk, false);
-		if (!release)
-			mutex_unlock(&lo->lo_disk->open_mutex);
 		if (err)
 			pr_warn("%s: partition scan of loop%d failed (rc=%d)\n",
 				__func__, lo->lo_number, err);
@@ -1256,24 +1228,16 @@ static int loop_clr_fd(struct loop_device *lo)
 		return -ENXIO;
 	}
 	/*
-	 * If we've explicitly asked to tear down the loop device,
-	 * and it has an elevated reference count, set it for auto-teardown when
-	 * the last reference goes away. This stops $!~#$@ udev from
-	 * preventing teardown because it decided that it needs to run blkid on
-	 * the loopback device whenever they appear. xfstests is notorious for
-	 * failing tests because blkid via udev races with a losetup
-	 * <dev>/do something like mkfs/losetup -d <dev> causing the losetup -d
-	 * command to fail with EBUSY.
+	 * Mark the device for removing the backing device on last close.
+	 * If we are the only opener, also switch the state to roundown here to
+	 * prevent new openers from coming in.
 	 */
-	if (disk_openers(lo->lo_disk) > 1) {
-		lo->lo_flags |= LO_FLAGS_AUTOCLEAR;
-		loop_global_unlock(lo, true);
-		return 0;
-	}
-	lo->lo_state = Lo_rundown;
+
+	lo->lo_flags |= LO_FLAGS_AUTOCLEAR;
+	if (disk_openers(lo->lo_disk) == 1)
+		lo->lo_state = Lo_rundown;
 	loop_global_unlock(lo, true);
 
-	__loop_clr_fd(lo, false);
 	return 0;
 }
 
@@ -1500,10 +1464,6 @@ static int loop_set_block_size(struct loop_device *lo, unsigned long arg)
 	if (lo->lo_state != Lo_bound)
 		return -ENXIO;
 
-	err = blk_validate_block_size(arg);
-	if (err)
-		return err;
-
 	if (lo->lo_queue->limits.logical_block_size == arg)
 		return 0;
 
@@ -1511,7 +1471,7 @@ static int loop_set_block_size(struct loop_device *lo, unsigned long arg)
 	invalidate_bdev(lo->lo_device);
 
 	blk_mq_freeze_queue(lo->lo_queue);
-	err = loop_reconfigure_limits(lo, arg, false);
+	err = loop_reconfigure_limits(lo, arg);
 	loop_update_dio(lo);
 	blk_mq_unfreeze_queue(lo->lo_queue);
 
@@ -1740,25 +1700,43 @@ static int lo_compat_ioctl(struct block_device *bdev, blk_mode_t mode,
 }
 #endif
 
+static int lo_open(struct gendisk *disk, blk_mode_t mode)
+{
+	struct loop_device *lo = disk->private_data;
+	int err;
+
+	err = mutex_lock_killable(&lo->lo_mutex);
+	if (err)
+		return err;
+
+	if (lo->lo_state == Lo_deleting || lo->lo_state == Lo_rundown)
+		err = -ENXIO;
+	mutex_unlock(&lo->lo_mutex);
+	return err;
+}
+
 static void lo_release(struct gendisk *disk)
 {
 	struct loop_device *lo = disk->private_data;
+	bool need_clear = false;
 
 	if (disk_openers(disk) > 0)
 		return;
+	/*
+	 * Clear the backing device information if this is the last close of
+	 * a device that's been marked for auto clear, or on which LOOP_CLR_FD
+	 * has been called.
+	 */
 
 	mutex_lock(&lo->lo_mutex);
-	if (lo->lo_state == Lo_bound && (lo->lo_flags & LO_FLAGS_AUTOCLEAR)) {
+	if (lo->lo_state == Lo_bound && (lo->lo_flags & LO_FLAGS_AUTOCLEAR))
 		lo->lo_state = Lo_rundown;
-		mutex_unlock(&lo->lo_mutex);
-		/*
-		 * In autoclear mode, stop the loop thread
-		 * and remove configuration after last close.
-		 */
-		__loop_clr_fd(lo, true);
-		return;
-	}
+
+	need_clear = (lo->lo_state == Lo_rundown);
 	mutex_unlock(&lo->lo_mutex);
+
+	if (need_clear)
+		__loop_clr_fd(lo);
 }
 
 static void lo_free_disk(struct gendisk *disk)
@@ -1775,6 +1753,7 @@ static void lo_free_disk(struct gendisk *disk)
 
 static const struct block_device_operations lo_fops = {
 	.owner =	THIS_MODULE,
+	.open =         lo_open,
 	.release =	lo_release,
 	.ioctl =	lo_ioctl,
 #ifdef CONFIG_COMPAT
@@ -1853,6 +1832,7 @@ static const struct kernel_param_ops loop_hw_qdepth_param_ops = {
 device_param_cb(hw_queue_depth, &loop_hw_qdepth_param_ops, &hw_queue_depth, 0444);
 MODULE_PARM_DESC(hw_queue_depth, "Queue depth for each hardware queue. Default: " __stringify(LOOP_DEFAULT_HW_Q_DEPTH));
 
+MODULE_DESCRIPTION("Loopback device support");
 MODULE_LICENSE("GPL");
 MODULE_ALIAS_BLOCKDEV_MAJOR(LOOP_MAJOR);
 
@@ -2060,14 +2040,6 @@ static int loop_add(int i)
 	lo->lo_queue = lo->lo_disk->queue;
 
 	/*
-	 * By default, we do buffer IO, so it doesn't make sense to enable
-	 * merge because the I/O submitted to backing file is handled page by
-	 * page. For directio mode, merge does help to dispatch bigger request
-	 * to underlayer disk. We will enable merge once directio is enabled.
-	 */
-	blk_queue_flag_set(QUEUE_FLAG_NOMERGES, lo->lo_queue);
-
-	/*
 	 * Disable partition scanning by default. The in-kernel partition
 	 * scanning can be requested individually per-device during its
 	 * setup. Userspace can always add and remove partitions from all