summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorGulam Mohamed <gulam.mohamed@oracle.com>2024-06-18 16:40:42 +0000
committerJens Axboe <axboe@kernel.dk>2024-06-27 16:10:32 -0600
commit18048c1af7836b8e31739d9eaefebc2bf76261f7 (patch)
tree9642d1873162f4c4143b38dfc9be59b0f5f200ce
parent63db4a1f795a19e4e12f036a12a5f61c48b03e5c (diff)
loop: Fix a race between loop detach and loop open
1. Userspace sends the command "losetup -d" which uses the open() call to open the device 2. Kernel receives the ioctl command "LOOP_CLR_FD" which calls the function loop_clr_fd() 3. If LOOP_CLR_FD is the first command received at the time, then the AUTOCLEAR flag is not set and deletion of the loop device proceeds ahead and scans the partitions (drop/add partitions) if (disk_openers(lo->lo_disk) > 1) { lo->lo_flags |= LO_FLAGS_AUTOCLEAR; loop_global_unlock(lo, true); return 0; } 4. Before scanning partitions, it will check to see if any partition of the loop device is currently opened 5. If any partition is opened, then it will return EBUSY: if (disk->open_partitions) return -EBUSY; 6. So, after receiving the "LOOP_CLR_FD" command and just before the above check for open_partitions, if any other command (like blkid) opens any partition of the loop device, then the partition scan will not proceed and EBUSY is returned as shown in above code 7. But in "__loop_clr_fd()", this EBUSY error is not propagated 8. We have noticed that this is causing the partitions of the loop to remain stale even after the loop device is detached resulting in the IO errors on the partitions Fix: Defer the detach of loop device to release function, which is called when the last close happens, by setting the lo_flags to LO_FLAGS_AUTOCLEAR at the time of detach i.e in loop_clr_fd() function. Test case involves the following two scripts: script1.sh: while [ 1 ]; do losetup -P -f /home/opt/looptest/test10.img blkid /dev/loop0p1 done script2.sh: while [ 1 ]; do losetup -d /dev/loop0 done Without fix, the following IO errors have been observed: kernel: __loop_clr_fd: partition scan of loop0 failed (rc=-16) kernel: I/O error, dev loop0, sector 20971392 op 0x0:(READ) flags 0x80700 phys_seg 1 prio class 0 kernel: I/O error, dev loop0, sector 108868 op 0x0:(READ) flags 0x0 phys_seg 1 prio class 0 kernel: Buffer I/O error on dev loop0p1, logical block 27201, async page read Signed-off-by: Gulam Mohamed <gulam.mohamed@oracle.com> Reviewed-by: Christoph Hellwig <hch@lst.de> Link: https://lore.kernel.org/r/20240618164042.343777-1-gulam.mohamed@oracle.com Signed-off-by: Jens Axboe <axboe@kernel.dk>
-rw-r--r--drivers/block/loop.c75
1 files changed, 36 insertions, 39 deletions
diff --git a/drivers/block/loop.c b/drivers/block/loop.c
index 86b5d956dc4e..cbda971d22b4 100644
--- a/drivers/block/loop.c
+++ b/drivers/block/loop.c
@@ -1123,20 +1123,12 @@ 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;
- /*
- * 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;
@@ -1161,8 +1153,6 @@ 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);
@@ -1177,11 +1167,7 @@ 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);
@@ -1230,24 +1216,16 @@ 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;
}
@@ -1714,25 +1692,43 @@ 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)
@@ -1749,6 +1745,7 @@ 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