From: Hongyu Jin <hongyu.jin@xxxxxxxxxx>
[ Upstream commit 60b30050116c0351b90154044345c1b53ae1f323 ]
The root cause is the race as follows:
Thread #1 Thread #2(irq ctx)
z_erofs_runqueue()
struct z_erofs_decompressqueue io_A[];
submit bio A
z_erofs_decompress_kickoff(,,1)
z_erofs_decompressqueue_endio(bio A)
z_erofs_decompress_kickoff(,,-1)
spin_lock_irqsave()
atomic_add_return()
io_wait_event() -> pending_bios is already 0
[end of function]
wake_up_locked(io_A[]) // crash
Referenced backtrace in kernel 5.4:
[ 10.129422] Unable to handle kernel paging request at virtual address eb0454a4
[ 10.364157] CPU: 0 PID: 709 Comm: getprop Tainted: G WC O 5.4.147-ab09225 #1
[ 11.556325] [<c01b33b8>] (__wake_up_common) from [<c01b3300>] (__wake_up_locked+0x40/0x48)
[ 11.565487] [<c01b3300>] (__wake_up_locked) from [<c044c8d0>] (z_erofs_vle_unzip_kickoff+0x6c/0xc0)
[ 11.575438] [<c044c8d0>] (z_erofs_vle_unzip_kickoff) from [<c044c854>] (z_erofs_vle_read_endio+0x16c/0x17c)
[ 11.586082] [<c044c854>] (z_erofs_vle_read_endio) from [<c06a80e8>] (clone_endio+0xb4/0x1d0)
[ 11.595428] [<c06a80e8>] (clone_endio) from [<c04a1280>] (blk_update_request+0x150/0x4dc)
[ 11.604516] [<c04a1280>] (blk_update_request) from [<c06dea28>] (mmc_blk_cqe_complete_rq+0x144/0x15c)
[ 11.614640] [<c06dea28>] (mmc_blk_cqe_complete_rq) from [<c04a5d90>] (blk_done_softirq+0xb0/0xcc)
[ 11.624419] [<c04a5d90>] (blk_done_softirq) from [<c010242c>] (__do_softirq+0x184/0x56c)
[ 11.633419] [<c010242c>] (__do_softirq) from [<c01051e8>] (irq_exit+0xd4/0x138)
[ 11.641640] [<c01051e8>] (irq_exit) from [<c010c314>] (__handle_domain_irq+0x94/0xd0)
[ 11.650381] [<c010c314>] (__handle_domain_irq) from [<c04fde70>] (gic_handle_irq+0x50/0xd4)
[ 11.659641] [<c04fde70>] (gic_handle_irq) from [<c0101b70>] (__irq_svc+0x70/0xb0)
Signed-off-by: Hongyu Jin <hongyu.jin@xxxxxxxxxx>
Reviewed-by: Gao Xiang <hsiangkao@xxxxxxxxxxxxxxxxx>
Reviewed-by: Chao Yu <chao@xxxxxxxxxx>
Link: https://lore.kernel.org/r/20220401115527.4935-1-hongyu.jin.cn@xxxxxxxxx
Signed-off-by: Gao Xiang <hsiangkao@xxxxxxxxxxxxxxxxx>
Signed-off-by: Sasha Levin <sashal@xxxxxxxxxx>
---
fs/erofs/zdata.c | 12 ++++--------
fs/erofs/zdata.h | 2 +-
2 files changed, 5 insertions(+), 9 deletions(-)
diff --git a/fs/erofs/zdata.c b/fs/erofs/zdata.c
index 423bc1a61da5..a1b48bcafe63 100644
--- a/fs/erofs/zdata.c
+++ b/fs/erofs/zdata.c
@@ -1073,12 +1073,9 @@ static void z_erofs_decompress_kickoff(struct z_erofs_decompressqueue *io,
/* wake up the caller thread for sync decompression */
if (sync) {
- unsigned long flags;
-
- spin_lock_irqsave(&io->u.wait.lock, flags);
if (!atomic_add_return(bios, &io->pending_bios))
- wake_up_locked(&io->u.wait);
- spin_unlock_irqrestore(&io->u.wait.lock, flags);
+ complete(&io->u.done);
+
return;
}
@@ -1224,7 +1221,7 @@ jobqueue_init(struct super_block *sb,
} else {
fg_out:
q = fgq;
- init_waitqueue_head(&fgq->u.wait);
+ init_completion(&fgq->u.done);
atomic_set(&fgq->pending_bios, 0);
}
q->sb = sb;
@@ -1428,8 +1425,7 @@ static void z_erofs_runqueue(struct super_block *sb,
return;
/* wait until all bios are completed */
- io_wait_event(io[JQ_SUBMIT].u.wait,
- !atomic_read(&io[JQ_SUBMIT].pending_bios));
+ wait_for_completion_io(&io[JQ_SUBMIT].u.done);
/* handle synchronous decompress queue in the caller context */
z_erofs_decompress_queue(&io[JQ_SUBMIT], pagepool);
diff --git a/fs/erofs/zdata.h b/fs/erofs/zdata.h
index e043216b545f..800b11c53f57 100644
--- a/fs/erofs/zdata.h
+++ b/fs/erofs/zdata.h
@@ -97,7 +97,7 @@ struct z_erofs_decompressqueue {
z_erofs_next_pcluster_t head;
union {
- wait_queue_head_t wait;
+ struct completion done;
struct work_struct work;
} u;
};
--
2.35.1
