[PATCH v2 2/2] io_uring: don't retry with truncated iter

[Pavel Begunkov]

[   74.211232] BUG: KASAN: stack-out-of-bounds in iov_iter_revert+0x809/0x900
[   74.212778] Read of size 8 at addr ffff888025dc78b8 by task
syz-executor.0/828
[   74.214756] CPU: 0 PID: 828 Comm: syz-executor.0 Not tainted
5.14.0-rc3-next-20210730 #1
[   74.216525] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996),
BIOS rel-1.14.0-0-g155821a1990b-prebuilt.qemu.org 04/01/2014
[   74.219033] Call Trace:
[   74.219683]  dump_stack_lvl+0x8b/0xb3
[   74.220706]  print_address_description.constprop.0+0x1f/0x140
[   74.224226]  kasan_report.cold+0x7f/0x11b
[   74.226085]  iov_iter_revert+0x809/0x900
[   74.227960]  io_write+0x57d/0xe40
[   74.232647]  io_issue_sqe+0x4da/0x6a80
[   74.242578]  __io_queue_sqe+0x1ac/0xe60
[   74.245358]  io_submit_sqes+0x3f6e/0x76a0
[   74.248207]  __do_sys_io_uring_enter+0x90c/0x1a20
[   74.257167]  do_syscall_64+0x3b/0x90
[   74.257984]  entry_SYSCALL_64_after_hwframe+0x44/0xae

old_size = iov_iter_count();
...
iov_iter_revert(old_size - iov_iter_count());

If iov_iter_revert() is done base on the initial size as above, and the
iter is truncated and not reexpanded in the middle, it miscalculates
borders causing problems. This trace is due to no one reexpanding after
generic_write_checks().

Avoid reverting truncated iterators, so io_uring would fail requests
with EAGAIN instead of retrying them.

Cc: stable@xxxxxxxxxxxxxxx
Reported-by: Palash Oswal <oswalpalash@xxxxxxxxx>
Reported-by: Sudip Mukherjee <sudipm.mukherjee@xxxxxxxxx>
Reported-and-tested-by: syzbot+9671693590ef5aad8953@xxxxxxxxxxxxxxxxxxxxxxxxx
Suggested-by: Jens Axboe <axboe@xxxxxxxxx>
Signed-off-by: Pavel Begunkov <asml.silence@xxxxxxxxx>
---
 fs/io_uring.c | 16 ++++++++++++++++
 1 file changed, 16 insertions(+)

diff --git a/fs/io_uring.c b/fs/io_uring.c
index efd818419014..2e168051262d 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -2462,6 +2462,16 @@ static void kiocb_end_write(struct io_kiocb *req)
 	}
 }
 
+static inline bool io_check_truncated(struct iov_iter *i, size_t len)
+{
+	if (unlikely(i->truncated)) {
+		if (iov_iter_count(i) != len)
+			return false;
+		i->truncated = false;
+	}
+	return true;
+}
+
 #ifdef CONFIG_BLOCK
 static bool io_resubmit_prep(struct io_kiocb *req)
 {
@@ -2469,6 +2479,8 @@ static bool io_resubmit_prep(struct io_kiocb *req)
 
 	if (!rw)
 		return !io_req_prep_async(req);
+	if (!io_check_truncated(&rw->iter, req->result))
+		return false;
 	/* may have left rw->iter inconsistent on -EIOCBQUEUED */
 	iov_iter_revert(&rw->iter, req->result - iov_iter_count(&rw->iter));
 	return true;
@@ -3328,6 +3340,8 @@ static int io_read(struct io_kiocb *req, unsigned int issue_flags)
 		/* no retry on NONBLOCK nor RWF_NOWAIT */
 		if (req->flags & REQ_F_NOWAIT)
 			goto done;
+		if (!io_check_truncated(iter, io_size))
+			goto done;
 		/* some cases will consume bytes even on error returns */
 		iov_iter_revert(iter, io_size - iov_iter_count(iter));
 		ret = 0;
@@ -3467,6 +3481,8 @@ static int io_write(struct io_kiocb *req, unsigned int issue_flags)
 		kiocb_done(kiocb, ret2, issue_flags);
 	} else {
 copy_iov:
+		if (!io_check_truncated(iter, io_size))
+			goto done;
 		/* some cases will consume bytes even on error returns */
 		iov_iter_revert(iter, io_size - iov_iter_count(iter));
 		ret = io_setup_async_rw(req, iovec, inline_vecs, iter, false);
-- 
2.32.0