From b000145e9907809406d8164c3b2b8861d95aecd1 Mon Sep 17 00:00:00 2001
From: Jens Axboe <axboe@kernel.dk>
Date: Thu, 29 Sep 2022 10:57:05 -0600
Subject: [PATCH] io_uring/rw: defer fsnotify calls to task context
Git-commit: b000145e9907809406d8164c3b2b8861d95aecd1
Patch-mainline: v6.1-rc1
References: git-fixes

We can't call these off the kiocb completion as that might be off
soft/hard irq context. Defer the calls to when we process the
task_work for this request. That avoids valid complaints like:

stack backtrace:
CPU: 1 PID: 0 Comm: swapper/1 Not tainted 6.0.0-rc6-syzkaller-00321-g105a36f3694e #0
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 08/26/2022
Call Trace:
 <IRQ>
 __dump_stack lib/dump_stack.c:88 [inline]
 dump_stack_lvl+0xcd/0x134 lib/dump_stack.c:106
 print_usage_bug kernel/locking/lockdep.c:3961 [inline]
 valid_state kernel/locking/lockdep.c:3973 [inline]
 mark_lock_irq kernel/locking/lockdep.c:4176 [inline]
 mark_lock.part.0.cold+0x18/0xd8 kernel/locking/lockdep.c:4632
 mark_lock kernel/locking/lockdep.c:4596 [inline]
 mark_usage kernel/locking/lockdep.c:4527 [inline]
 __lock_acquire+0x11d9/0x56d0 kernel/locking/lockdep.c:5007
 lock_acquire kernel/locking/lockdep.c:5666 [inline]
 lock_acquire+0x1ab/0x570 kernel/locking/lockdep.c:5631
 __fs_reclaim_acquire mm/page_alloc.c:4674 [inline]
 fs_reclaim_acquire+0x115/0x160 mm/page_alloc.c:4688
 might_alloc include/linux/sched/mm.h:271 [inline]
 slab_pre_alloc_hook mm/slab.h:700 [inline]
 slab_alloc mm/slab.c:3278 [inline]
 __kmem_cache_alloc_lru mm/slab.c:3471 [inline]
 kmem_cache_alloc+0x39/0x520 mm/slab.c:3491
 fanotify_alloc_fid_event fs/notify/fanotify/fanotify.c:580 [inline]
 fanotify_alloc_event fs/notify/fanotify/fanotify.c:813 [inline]
 fanotify_handle_event+0x1130/0x3f40 fs/notify/fanotify/fanotify.c:948
 send_to_group fs/notify/fsnotify.c:360 [inline]
 fsnotify+0xafb/0x1680 fs/notify/fsnotify.c:570
 __fsnotify_parent+0x62f/0xa60 fs/notify/fsnotify.c:230
 fsnotify_parent include/linux/fsnotify.h:77 [inline]
 fsnotify_file include/linux/fsnotify.h:99 [inline]
 fsnotify_access include/linux/fsnotify.h:309 [inline]
 __io_complete_rw_common+0x485/0x720 io_uring/rw.c:195
 io_complete_rw+0x1a/0x1f0 io_uring/rw.c:228
 iomap_dio_complete_work fs/iomap/direct-io.c:144 [inline]
 iomap_dio_bio_end_io+0x438/0x5e0 fs/iomap/direct-io.c:178
 bio_endio+0x5f9/0x780 block/bio.c:1564
 req_bio_endio block/blk-mq.c:695 [inline]
 blk_update_request+0x3fc/0x1300 block/blk-mq.c:825
 scsi_end_request+0x7a/0x9a0 drivers/scsi/scsi_lib.c:541
 scsi_io_completion+0x173/0x1f70 drivers/scsi/scsi_lib.c:971
 scsi_complete+0x122/0x3b0 drivers/scsi/scsi_lib.c:1438
 blk_complete_reqs+0xad/0xe0 block/blk-mq.c:1022
 __do_softirq+0x1d3/0x9c6 kernel/softirq.c:571
 invoke_softirq kernel/softirq.c:445 [inline]
 __irq_exit_rcu+0x123/0x180 kernel/softirq.c:650
 irq_exit_rcu+0x5/0x20 kernel/softirq.c:662
 common_interrupt+0xa9/0xc0 arch/x86/kernel/irq.c:240

Fixes: f63cf5192fe3 ("io_uring: ensure that fsnotify is always called")
Link: https://lore.kernel.org/all/20220929135627.ykivmdks2w5vzrwg@quack3/
Reported-by: syzbot+dfcc5f4da15868df7d4d@syzkaller.appspotmail.com
Reported-by: Jan Kara <jack@suse.cz>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Signed-off-by: Gabriel Krisman Bertazi <krisman@suse.de>
---
 fs/io_uring.c |   20 +++++++++++++-------
 1 file changed, 13 insertions(+), 7 deletions(-)

--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -3397,12 +3397,6 @@ static bool io_rw_should_reissue(struct
 
 static bool __io_complete_rw_common(struct io_kiocb *req, long res)
 {
-	if (req->rw.kiocb.ki_flags & IOCB_WRITE) {
-		kiocb_end_write(req);
-		fsnotify_modify(req->file);
-	} else {
-		fsnotify_access(req->file);
-	}
 	if (unlikely(res != req->cqe.res)) {
 		if ((res == -EAGAIN || res == -EOPNOTSUPP) &&
 		    io_rw_should_reissue(req)) {
@@ -3428,6 +3422,18 @@ static inline void io_req_task_complete(
 	}
 }
 
+static void io_req_rw_complete(struct io_kiocb *req, bool *locked)
+{
+	if (req->rw.kiocb.ki_flags & IOCB_WRITE) {
+		kiocb_end_write(req);
+		fsnotify_modify(req->file);
+	} else {
+		fsnotify_access(req->file);
+	}
+
+	io_req_task_complete(req, locked);
+}
+
 static void __io_complete_rw(struct io_kiocb *req, long res,
 			     unsigned int issue_flags)
 {
@@ -3444,7 +3450,7 @@ static void io_complete_rw(struct kiocb
 	if (__io_complete_rw_common(req, res))
 		return;
 	req->cqe.res = res;
-	req->io_task_work.func = io_req_task_complete;
+	req->io_task_work.func = io_req_rw_complete;
 	io_req_task_prio_work_add(req);
 }