io_uring/rw: fix missing NOWAIT check for O_DIRECT start write

When io_uring starts a write, it'll call kiocb_start_write() to bump the
super block rwsem, preventing any freezes from happening while that
write is in-flight. The freeze side will grab that rwsem for writing,
excluding any new writers from happening and waiting for existing writes
to finish. But io_uring unconditionally uses kiocb_start_write(), which
will block if someone is currently attempting to freeze the mount point.
This causes a deadlock where freeze is waiting for previous writes to
complete, but the previous writes cannot complete, as the task that is
supposed to complete them is blocked waiting on starting a new write.
This results in the following stuck trace showing that dependency with
the write blocked starting a new write:

task:fio             state:D stack:0     pid:886   tgid:886   ppid:876
Call trace:
 __switch_to+0x1d8/0x348
 __schedule+0x8e8/0x2248
 schedule+0x110/0x3f0
 percpu_rwsem_wait+0x1e8/0x3f8
 __percpu_down_read+0xe8/0x500
 io_write+0xbb8/0xff8
 io_issue_sqe+0x10c/0x1020
 io_submit_sqes+0x614/0x2110
 __arm64_sys_io_uring_enter+0x524/0x1038
 invoke_syscall+0x74/0x268
 el0_svc_common.constprop.0+0x160/0x238
 do_el0_svc+0x44/0x60
 el0_svc+0x44/0xb0
 el0t_64_sync_handler+0x118/0x128
 el0t_64_sync+0x168/0x170
INFO: task fsfreeze:7364 blocked for more than 15 seconds.
      Not tainted 6.12.0-rc5-00063-g76aaf945701c #7963

with the attempting freezer stuck trying to grab the rwsem:

task:fsfreeze        state:D stack:0     pid:7364  tgid:7364  ppid:995
Call trace:
 __switch_to+0x1d8/0x348
 __schedule+0x8e8/0x2248
 schedule+0x110/0x3f0
 percpu_down_write+0x2b0/0x680
 freeze_super+0x248/0x8a8
 do_vfs_ioctl+0x149c/0x1b18
 __arm64_sys_ioctl+0xd0/0x1a0
 invoke_syscall+0x74/0x268
 el0_svc_common.constprop.0+0x160/0x238
 do_el0_svc+0x44/0x60
 el0_svc+0x44/0xb0
 el0t_64_sync_handler+0x118/0x128
 el0t_64_sync+0x168/0x170

Fix this by having the io_uring side honor IOCB_NOWAIT, and only attempt a
blocking grab of the super block rwsem if it isn't set. For normal issue
where IOCB_NOWAIT would always be set, this returns -EAGAIN which will
have io_uring core issue a blocking attempt of the write. That will in
turn also get completions run, ensuring forward progress.

Since freezing requires CAP_SYS_ADMIN in the first place, this isn't
something that can be triggered by a regular user.

Cc: [email protected] # 5.10+
Reported-by: Peter Mann <[email protected]>
Link: https://lore.kernel.org/io-uring/[email protected]
Signed-off-by: Jens Axboe <[email protected]>

Author: axboe

io_uring/rw.c

@@ -1014,6 +1014,25 @@ int io_read_mshot(struct io_kiocb *req, unsigned int issue_flags)
 	return IOU_OK;
 }
 
+static bool io_kiocb_start_write(struct io_kiocb *req, struct kiocb *kiocb)
+{
+	struct inode *inode;
+	bool ret;
+
+	if (!(req->flags & REQ_F_ISREG))
+		return true;
+	if (!(kiocb->ki_flags & IOCB_NOWAIT)) {
+		kiocb_start_write(kiocb);
+		return true;
+	}
+
+	inode = file_inode(kiocb->ki_filp);
+	ret = sb_start_write_trylock(inode->i_sb);
+	if (ret)
+		__sb_writers_release(inode->i_sb, SB_FREEZE_WRITE);
+	return ret;
+}
+
 int io_write(struct io_kiocb *req, unsigned int issue_flags)
 {
 	bool force_nonblock = issue_flags & IO_URING_F_NONBLOCK;
@@ -1051,8 +1070,8 @@ int io_write(struct io_kiocb *req, unsigned int issue_flags)
 	if (unlikely(ret))
 		return ret;
 
-	if (req->flags & REQ_F_ISREG)
-		kiocb_start_write(kiocb);
+	if (unlikely(!io_kiocb_start_write(req, kiocb)))
+		return -EAGAIN;
 	kiocb->ki_flags |= IOCB_WRITE;
 
 	if (likely(req->file->f_op->write_iter))