1 files changed, 66 insertions, 49 deletions

diff --git a/drivers/block/loop.c b/drivers/block/loop.c
index 01cbbfc4e9e2..3e636a75c83a 100644
--- a/drivers/block/loop.c
+++ b/drivers/block/loop.c
@@ -79,12 +79,14 @@
 #include <linux/ioprio.h>
 #include <linux/blk-cgroup.h>
 #include <linux/sched/mm.h>
+#include <linux/statfs.h>
 
 #include "loop.h"
 
 #include <linux/uaccess.h>
 
 #define LOOP_IDLE_WORKER_TIMEOUT (60 * HZ)
+#define LOOP_DEFAULT_HW_Q_DEPTH (128)
 
 static DEFINE_IDR(loop_index_idr);
 static DEFINE_MUTEX(loop_ctl_mutex);
@@ -308,12 +310,11 @@ static int lo_fallocate(struct loop_device *lo, struct request *rq, loff_t pos,
 	 * a.k.a. discard/zerorange.
 	 */
 	struct file *file = lo->lo_backing_file;
-	struct request_queue *q = lo->lo_queue;
 	int ret;
 
 	mode |= FALLOC_FL_KEEP_SIZE;
 
-	if (!blk_queue_discard(q)) {
+	if (!blk_queue_discard(lo->lo_queue)) {
 		ret = -EOPNOTSUPP;
 		goto out;
 	}
@@ -327,8 +328,7 @@ static int lo_fallocate(struct loop_device *lo, struct request *rq, loff_t pos,
 
 static int lo_req_flush(struct loop_device *lo, struct request *rq)
 {
-	struct file *file = lo->lo_backing_file;
-	int ret = vfs_fsync(file, 0);
+	int ret = vfs_fsync(lo->lo_backing_file, 0);
 	if (unlikely(ret && ret != -EINVAL))
 		ret = -EIO;
 
@@ -680,33 +680,33 @@ static ssize_t loop_attr_backing_file_show(struct loop_device *lo, char *buf)
 
 static ssize_t loop_attr_offset_show(struct loop_device *lo, char *buf)
 {
-	return sprintf(buf, "%llu\n", (unsigned long long)lo->lo_offset);
+	return sysfs_emit(buf, "%llu\n", (unsigned long long)lo->lo_offset);
 }
 
 static ssize_t loop_attr_sizelimit_show(struct loop_device *lo, char *buf)
 {
-	return sprintf(buf, "%llu\n", (unsigned long long)lo->lo_sizelimit);
+	return sysfs_emit(buf, "%llu\n", (unsigned long long)lo->lo_sizelimit);
 }
 
 static ssize_t loop_attr_autoclear_show(struct loop_device *lo, char *buf)
 {
 	int autoclear = (lo->lo_flags & LO_FLAGS_AUTOCLEAR);
 
-	return sprintf(buf, "%s\n", autoclear ? "1" : "0");
+	return sysfs_emit(buf, "%s\n", autoclear ? "1" : "0");
 }
 
 static ssize_t loop_attr_partscan_show(struct loop_device *lo, char *buf)
 {
 	int partscan = (lo->lo_flags & LO_FLAGS_PARTSCAN);
 
-	return sprintf(buf, "%s\n", partscan ? "1" : "0");
+	return sysfs_emit(buf, "%s\n", partscan ? "1" : "0");
 }
 
 static ssize_t loop_attr_dio_show(struct loop_device *lo, char *buf)
 {
 	int dio = (lo->lo_flags & LO_FLAGS_DIRECT_IO);
 
-	return sprintf(buf, "%s\n", dio ? "1" : "0");
+	return sysfs_emit(buf, "%s\n", dio ? "1" : "0");
 }
 
 LOOP_ATTR_RO(backing_file);
@@ -774,8 +774,13 @@ static void loop_config_discard(struct loop_device *lo)
 		granularity = 0;
 
 	} else {
+		struct kstatfs sbuf;
+
 		max_discard_sectors = UINT_MAX >> 9;
-		granularity = inode->i_sb->s_blocksize;
+		if (!vfs_statfs(&file->f_path, &sbuf))
+			granularity = sbuf.f_bsize;
+		else
+			max_discard_sectors = 0;
 	}
 
 	if (max_discard_sectors) {
@@ -1082,7 +1087,7 @@ out_putf:
 	return error;
 }
 
-static void __loop_clr_fd(struct loop_device *lo)
+static void __loop_clr_fd(struct loop_device *lo, bool release)
 {
 	struct file *filp;
 	gfp_t gfp = lo->old_gfp_mask;
@@ -1144,6 +1149,8 @@ static void __loop_clr_fd(struct loop_device *lo)
 	/* let user-space know about this change */
 	kobject_uevent(&disk_to_dev(lo->lo_disk)->kobj, KOBJ_CHANGE);
 	mapping_set_gfp_mask(filp->f_mapping, gfp);
+	/* This is safe: open() is still holding a reference. */
+	module_put(THIS_MODULE);
 	blk_mq_unfreeze_queue(lo->lo_queue);
 
 	disk_force_media_change(lo->lo_disk, DISK_EVENT_MEDIA_CHANGE);
@@ -1151,52 +1158,44 @@ static void __loop_clr_fd(struct loop_device *lo)
 	if (lo->lo_flags & LO_FLAGS_PARTSCAN) {
 		int err;
 
-		mutex_lock(&lo->lo_disk->open_mutex);
+		/*
+		 * open_mutex has been held already in release path, so don't
+		 * acquire it if this function is called in such case.
+		 *
+		 * If the reread partition isn't from release path, lo_refcnt
+		 * 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);
-		mutex_unlock(&lo->lo_disk->open_mutex);
+		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);
 		/* Device is gone, no point in returning error */
 	}
 
+	/*
+	 * lo->lo_state is set to Lo_unbound here after above partscan has
+	 * finished. There cannot be anybody else entering __loop_clr_fd() as
+	 * Lo_rundown state protects us from all the other places trying to
+	 * change the 'lo' device.
+	 */
 	lo->lo_flags = 0;
 	if (!part_shift)
 		lo->lo_disk->flags |= GENHD_FL_NO_PART;
-
-	fput(filp);
-}
-
-static void loop_rundown_completed(struct loop_device *lo)
-{
 	mutex_lock(&lo->lo_mutex);
 	lo->lo_state = Lo_unbound;
 	mutex_unlock(&lo->lo_mutex);
-	module_put(THIS_MODULE);
-}
 
-static void loop_rundown_workfn(struct work_struct *work)
-{
-	struct loop_device *lo = container_of(work, struct loop_device,
-					      rundown_work);
-	struct block_device *bdev = lo->lo_device;
-	struct gendisk *disk = lo->lo_disk;
-
-	__loop_clr_fd(lo);
-	kobject_put(&bdev->bd_device.kobj);
-	module_put(disk->fops->owner);
-	loop_rundown_completed(lo);
-}
-
-static void loop_schedule_rundown(struct loop_device *lo)
-{
-	struct block_device *bdev = lo->lo_device;
-	struct gendisk *disk = lo->lo_disk;
-
-	__module_get(disk->fops->owner);
-	kobject_get(&bdev->bd_device.kobj);
-	INIT_WORK(&lo->rundown_work, loop_rundown_workfn);
-	queue_work(system_long_wq, &lo->rundown_work);
+	/*
+	 * Need not hold lo_mutex to fput backing file. Calling fput holding
+	 * lo_mutex triggers a circular lock dependency possibility warning as
+	 * fput can take open_mutex which is usually taken before lo_mutex.
+	 */
+	fput(filp);
 }
 
 static int loop_clr_fd(struct loop_device *lo)
@@ -1228,8 +1227,7 @@ static int loop_clr_fd(struct loop_device *lo)
 	lo->lo_state = Lo_rundown;
 	mutex_unlock(&lo->lo_mutex);
 
-	__loop_clr_fd(lo);
-	loop_rundown_completed(lo);
+	__loop_clr_fd(lo, false);
 	return 0;
 }
 
@@ -1262,7 +1260,7 @@ loop_set_status(struct loop_device *lo, const struct loop_info64 *info)
 	if (size_changed && lo->lo_device->bd_inode->i_mapping->nrpages) {
 		/* If any pages were dirtied after invalidate_bdev(), try again */
 		err = -EAGAIN;
-		pr_warn("%s: loop%d (%s) has still dirty pages (nrpages=%lu)\n",
+		pr_warn("%s: loop%d (%s) still has dirty pages (nrpages=%lu)\n",
 			__func__, lo->lo_number, lo->lo_file_name,
 			lo->lo_device->bd_inode->i_mapping->nrpages);
 		goto out_unfreeze;
@@ -1482,7 +1480,7 @@ static int loop_set_block_size(struct loop_device *lo, unsigned long arg)
 	/* invalidate_bdev should have truncated all the pages */
 	if (lo->lo_device->bd_inode->i_mapping->nrpages) {
 		err = -EAGAIN;
-		pr_warn("%s: loop%d (%s) has still dirty pages (nrpages=%lu)\n",
+		pr_warn("%s: loop%d (%s) still has dirty pages (nrpages=%lu)\n",
 			__func__, lo->lo_number, lo->lo_file_name,
 			lo->lo_device->bd_inode->i_mapping->nrpages);
 		goto out_unfreeze;
@@ -1754,7 +1752,7 @@ static void lo_release(struct gendisk *disk, fmode_t mode)
 		 * In autoclear mode, stop the loop thread
 		 * and remove configuration after last close.
 		 */
-		loop_schedule_rundown(lo);
+		__loop_clr_fd(lo, true);
 		return;
 	} else if (lo->lo_state == Lo_bound) {
 		/*
@@ -1787,6 +1785,24 @@ module_param(max_loop, int, 0444);
 MODULE_PARM_DESC(max_loop, "Maximum number of loop devices");
 module_param(max_part, int, 0444);
 MODULE_PARM_DESC(max_part, "Maximum number of partitions per loop device");
+
+static int hw_queue_depth = LOOP_DEFAULT_HW_Q_DEPTH;
+
+static int loop_set_hw_queue_depth(const char *s, const struct kernel_param *p)
+{
+	int ret = kstrtoint(s, 10, &hw_queue_depth);
+
+	return (ret || (hw_queue_depth < 1)) ? -EINVAL : 0;
+}
+
+static const struct kernel_param_ops loop_hw_qdepth_param_ops = {
+	.set	= loop_set_hw_queue_depth,
+	.get	= param_get_int,
+};
+
+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: 128");
+
 MODULE_LICENSE("GPL");
 MODULE_ALIAS_BLOCKDEV_MAJOR(LOOP_MAJOR);
 
@@ -1981,7 +1997,7 @@ static int loop_add(int i)
 
 	lo->tag_set.ops = &loop_mq_ops;
 	lo->tag_set.nr_hw_queues = 1;
-	lo->tag_set.queue_depth = 128;
+	lo->tag_set.queue_depth = hw_queue_depth;
 	lo->tag_set.numa_node = NUMA_NO_NODE;
 	lo->tag_set.cmd_size = sizeof(struct loop_cmd);
 	lo->tag_set.flags = BLK_MQ_F_SHOULD_MERGE | BLK_MQ_F_STACKING |
@@ -2075,6 +2091,7 @@ static void loop_remove(struct loop_device *lo)
 	del_gendisk(lo->lo_disk);
 	blk_cleanup_disk(lo->lo_disk);
 	blk_mq_free_tag_set(&lo->tag_set);
+
 	mutex_lock(&loop_ctl_mutex);
 	idr_remove(&loop_index_idr, lo->lo_number);
 	mutex_unlock(&loop_ctl_mutex);