[PATCH v2] io_uring: fix IOPOLL with passthrough I/O

[Jens Axboe <axboe@kernel.dk>]

A previous commit improving IOPOLL made an incorrect assumption that
task_work isn't used with IOPOLL. This can cause crashes when doing
passthrough I/O on nvme, where queueing the completion task_work will
trample on the same memory that holds the completed list of requests.

Fix it up by shuffling the members around, so we're not sharing any
parts that end up getting used in this path.

Fixes: 3c7d76d6128a ("io_uring: IOPOLL polling improvements")
Reported-by: Yi Zhang <yi.zhang@redhat.com>
Link: https://lore.kernel.org/linux-block/CAHj4cs_SLPj9v9w5MgfzHKy+983enPx3ZQY2kMuMJ1202DBefw@mail.gmail.com/
Cc: Ming Lei <ming.lei@redhat.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>

---

v2: ensure ->iopoll_start is read before doing actual polling

diff --git a/include/linux/io_uring_types.h b/include/linux/io_uring_types.h
index e4c804f99c30..211686ad89fd 100644
--- a/include/linux/io_uring_types.h
+++ b/include/linux/io_uring_types.h
@@ -713,13 +713,10 @@ struct io_kiocb {
 	atomic_t			refs;
 	bool				cancel_seq_set;
 
-	/*
-	 * IOPOLL doesn't use task_work, so use the ->iopoll_node list
-	 * entry to manage pending iopoll requests.
-	 */
 	union {
 		struct io_task_work	io_task_work;
-		struct list_head	iopoll_node;
+		/* For IOPOLL setup queues, with hybrid polling */
+		u64                     iopoll_start;
 	};
 
 	union {
@@ -728,8 +725,8 @@ struct io_kiocb {
 		 * poll
 		 */
 		struct hlist_node	hash_node;
-		/* For IOPOLL setup queues, with hybrid polling */
-		u64                     iopoll_start;
+		/* IOPOLL completion handling */
+		struct list_head	iopoll_node;
 		/* for private io_kiocb freeing */
 		struct rcu_head		rcu_head;
 	};
diff --git a/io_uring/rw.c b/io_uring/rw.c
index 307f1f39d9f3..c33c533a267e 100644
--- a/io_uring/rw.c
+++ b/io_uring/rw.c
@@ -1296,12 +1296,13 @@ static int io_uring_hybrid_poll(struct io_kiocb *req,
 				struct io_comp_batch *iob, unsigned int poll_flags)
 {
 	struct io_ring_ctx *ctx = req->ctx;
-	u64 runtime, sleep_time;
+	u64 runtime, sleep_time, iopoll_start;
 	int ret;
 
+	iopoll_start = READ_ONCE(req->iopoll_start);
 	sleep_time = io_hybrid_iopoll_delay(ctx, req);
 	ret = io_uring_classic_poll(req, iob, poll_flags);
-	runtime = ktime_get_ns() - req->iopoll_start - sleep_time;
+	runtime = ktime_get_ns() - iopoll_start - sleep_time;
 
 	/*
 	 * Use minimum sleep time if we're polling devices with different
-- 
Jens Axboe