[tip:locking/core] block, locking/lockdep: Assign a lock_class per gendisk used for wait_for_completion()

From: tip-bot for Byungchul Park
Date: Thu Oct 26 2017 - 05:36:08 EST


Commit-ID: e319e1fbd9d42420ab6eec0bfd75eb9ad7ca63b1
Gitweb: https://git.kernel.org/tip/e319e1fbd9d42420ab6eec0bfd75eb9ad7ca63b1
Author: Byungchul Park <byungchul.park@xxxxxxx>
AuthorDate: Wed, 25 Oct 2017 17:56:05 +0900
Committer: Ingo Molnar <mingo@xxxxxxxxxx>
CommitDate: Thu, 26 Oct 2017 07:54:17 +0200

block, locking/lockdep: Assign a lock_class per gendisk used for wait_for_completion()

Darrick posted the following warning and Dave Chinner analyzed it:

> ======================================================
> WARNING: possible circular locking dependency detected
> 4.14.0-rc1-fixes #1 Tainted: G W
> ------------------------------------------------------
> loop0/31693 is trying to acquire lock:
> (&(&ip->i_mmaplock)->mr_lock){++++}, at: [<ffffffffa00f1b0c>] xfs_ilock+0x23c/0x330 [xfs]
>
> but now in release context of a crosslock acquired at the following:
> ((complete)&ret.event){+.+.}, at: [<ffffffff81326c1f>] submit_bio_wait+0x7f/0xb0
>
> which lock already depends on the new lock.
>
> the existing dependency chain (in reverse order) is:
>
> -> #2 ((complete)&ret.event){+.+.}:
> lock_acquire+0xab/0x200
> wait_for_completion_io+0x4e/0x1a0
> submit_bio_wait+0x7f/0xb0
> blkdev_issue_zeroout+0x71/0xa0
> xfs_bmapi_convert_unwritten+0x11f/0x1d0 [xfs]
> xfs_bmapi_write+0x374/0x11f0 [xfs]
> xfs_iomap_write_direct+0x2ac/0x430 [xfs]
> xfs_file_iomap_begin+0x20d/0xd50 [xfs]
> iomap_apply+0x43/0xe0
> dax_iomap_rw+0x89/0xf0
> xfs_file_dax_write+0xcc/0x220 [xfs]
> xfs_file_write_iter+0xf0/0x130 [xfs]
> __vfs_write+0xd9/0x150
> vfs_write+0xc8/0x1c0
> SyS_write+0x45/0xa0
> entry_SYSCALL_64_fastpath+0x1f/0xbe
>
> -> #1 (&xfs_nondir_ilock_class){++++}:
> lock_acquire+0xab/0x200
> down_write_nested+0x4a/0xb0
> xfs_ilock+0x263/0x330 [xfs]
> xfs_setattr_size+0x152/0x370 [xfs]
> xfs_vn_setattr+0x6b/0x90 [xfs]
> notify_change+0x27d/0x3f0
> do_truncate+0x5b/0x90
> path_openat+0x237/0xa90
> do_filp_open+0x8a/0xf0
> do_sys_open+0x11c/0x1f0
> entry_SYSCALL_64_fastpath+0x1f/0xbe
>
> -> #0 (&(&ip->i_mmaplock)->mr_lock){++++}:
> up_write+0x1c/0x40
> xfs_iunlock+0x1d0/0x310 [xfs]
> xfs_file_fallocate+0x8a/0x310 [xfs]
> loop_queue_work+0xb7/0x8d0
> kthread_worker_fn+0xb9/0x1f0
>
> Chain exists of:
> &(&ip->i_mmaplock)->mr_lock --> &xfs_nondir_ilock_class --> (complete)&ret.event
>
> Possible unsafe locking scenario by crosslock:
>
> CPU0 CPU1
> ---- ----
> lock(&xfs_nondir_ilock_class);
> lock((complete)&ret.event);
> lock(&(&ip->i_mmaplock)->mr_lock);
> unlock((complete)&ret.event);
>
> *** DEADLOCK ***

The warning is a false positive, caused by the fact that all
wait_for_completion()s in submit_bio_wait() are waiting with the same
lock class.

However, some bios have nothing to do with others, for example in the case
of loop devices, there's no direct connection between the bios of an upper
device and the bios of a lower device(=loop device).

The safest way to assign different lock classes to different devices is
to do it for each gendisk. In other words, this patch assigns a
lockdep_map per gendisk and uses it when initializing completion in
submit_bio_wait().

Analyzed-by: Dave Chinner <david@xxxxxxxxxxxxx>
Reported-by: Darrick J. Wong <darrick.wong@xxxxxxxxxx>
Signed-off-by: Byungchul Park <byungchul.park@xxxxxxx>
Reviewed-by: Jens Axboe <axboe@xxxxxxxxx>
Cc: Linus Torvalds <torvalds@xxxxxxxxxxxxxxxxxxxx>
Cc: Peter Zijlstra <peterz@xxxxxxxxxxxxx>
Cc: Thomas Gleixner <tglx@xxxxxxxxxxxxx>
Cc: amir73il@xxxxxxxxx
Cc: axboe@xxxxxxxxx
Cc: david@xxxxxxxxxxxxx
Cc: hch@xxxxxxxxxxxxx
Cc: idryomov@xxxxxxxxx
Cc: johan@xxxxxxxxxx
Cc: johannes.berg@xxxxxxxxx
Cc: kernel-team@xxxxxxx
Cc: linux-block@xxxxxxxxxxxxxxx
Cc: linux-fsdevel@xxxxxxxxxxxxxxx
Cc: linux-mm@xxxxxxxxx
Cc: linux-xfs@xxxxxxxxxxxxxxx
Cc: oleg@xxxxxxxxxx
Cc: tj@xxxxxxxxxx
Link: http://lkml.kernel.org/r/1508921765-15396-10-git-send-email-byungchul.park@xxxxxxx
Signed-off-by: Ingo Molnar <mingo@xxxxxxxxxx>
---
block/bio.c | 2 +-
block/genhd.c | 10 ++--------
include/linux/genhd.h | 22 ++++++++++++++++++++--
3 files changed, 23 insertions(+), 11 deletions(-)

diff --git a/block/bio.c b/block/bio.c
index 5e901bf..cc60213 100644
--- a/block/bio.c
+++ b/block/bio.c
@@ -935,7 +935,7 @@ static void submit_bio_wait_endio(struct bio *bio)
*/
int submit_bio_wait(struct bio *bio)
{
- DECLARE_COMPLETION_ONSTACK(done);
+ DECLARE_COMPLETION_ONSTACK_MAP(done, bio->bi_disk->lockdep_map);

bio->bi_private = &done;
bio->bi_end_io = submit_bio_wait_endio;
diff --git a/block/genhd.c b/block/genhd.c
index dd305c6..630c0da 100644
--- a/block/genhd.c
+++ b/block/genhd.c
@@ -1354,13 +1354,7 @@ dev_t blk_lookup_devt(const char *name, int partno)
}
EXPORT_SYMBOL(blk_lookup_devt);

-struct gendisk *alloc_disk(int minors)
-{
- return alloc_disk_node(minors, NUMA_NO_NODE);
-}
-EXPORT_SYMBOL(alloc_disk);
-
-struct gendisk *alloc_disk_node(int minors, int node_id)
+struct gendisk *__alloc_disk_node(int minors, int node_id)
{
struct gendisk *disk;
struct disk_part_tbl *ptbl;
@@ -1411,7 +1405,7 @@ struct gendisk *alloc_disk_node(int minors, int node_id)
}
return disk;
}
-EXPORT_SYMBOL(alloc_disk_node);
+EXPORT_SYMBOL(__alloc_disk_node);

struct kobject *get_disk(struct gendisk *disk)
{
diff --git a/include/linux/genhd.h b/include/linux/genhd.h
index ea652bf..19d1871 100644
--- a/include/linux/genhd.h
+++ b/include/linux/genhd.h
@@ -206,6 +206,7 @@ struct gendisk {
#endif /* CONFIG_BLK_DEV_INTEGRITY */
int node_id;
struct badblocks *bb;
+ struct lockdep_map lockdep_map;
};

static inline struct gendisk *part_to_disk(struct hd_struct *part)
@@ -590,8 +591,7 @@ extern void __delete_partition(struct percpu_ref *);
extern void delete_partition(struct gendisk *, int);
extern void printk_all_partitions(void);

-extern struct gendisk *alloc_disk_node(int minors, int node_id);
-extern struct gendisk *alloc_disk(int minors);
+extern struct gendisk *__alloc_disk_node(int minors, int node_id);
extern struct kobject *get_disk(struct gendisk *disk);
extern void put_disk(struct gendisk *disk);
extern void blk_register_region(dev_t devt, unsigned long range,
@@ -615,6 +615,24 @@ extern ssize_t part_fail_store(struct device *dev,
const char *buf, size_t count);
#endif /* CONFIG_FAIL_MAKE_REQUEST */

+#define alloc_disk_node(minors, node_id) \
+({ \
+ static struct lock_class_key __key; \
+ const char *__name; \
+ struct gendisk *__disk; \
+ \
+ __name = "(gendisk_completion)"#minors"("#node_id")"; \
+ \
+ __disk = __alloc_disk_node(minors, node_id); \
+ \
+ if (__disk) \
+ lockdep_init_map(&__disk->lockdep_map, __name, &__key, 0); \
+ \
+ __disk; \
+})
+
+#define alloc_disk(minors) alloc_disk_node(minors, NUMA_NO_NODE)
+
static inline int hd_ref_init(struct hd_struct *part)
{
if (percpu_ref_init(&part->ref, __delete_partition, 0,