Skip to contentSkip to conversation

io_uring: flush timeouts that should already have expired

PATCH In review Marcelo Diop-Gonzalez 2 participants 3 messages Dec 18, 2020

Subsystems (2)
lore
Share & tools
lore
#0 lore raw

PATCH 1/1 io_uring: flush timeouts that should already have expired

Right now io_flush_timeouts() checks if the current number of events is equal to ->timeout.target_seq, but this will miss some timeouts if there have been more than 1 event added since the last time they were flushed (possible in io_submit_flush_completions(), for example). The test below hangs before this change (unless you run with

$ ./a.out ~/somefile 1)
int main(int argc, char **argv) {
	if (argc < 2)
		return 1;

	int fd = open(argv[1], O_RDONLY);
	if (fd < 0) {
		perror("open");
		return 1;
	}

	struct io_uring ring;
	io_uring_queue_init(4, &ring, 0);

	struct io_uring_sqe *sqe = io_uring_get_sqe(&ring);

	struct __kernel_timespec ts = { .tv_sec = 9999999 };
	io_uring_prep_timeout(sqe, &ts, 1, 0);
	sqe->user_data = 123;
	int ret = io_uring_submit(&ring);
	if (ret < 0) {
		fprintf(stderr, "submit(timeout_sqe): %d\n", ret);
		return 1;
	}

	int n = 2;
	if (argc > 2)
		n = atoi(argv[2]);

	char buf;
	for (int i = 0; i < n; i++) {
		sqe = io_uring_get_sqe(&ring);
		if (!sqe) {
			fprintf(stderr, "too many\n");
			exit(1);
		}
		io_uring_prep_read(sqe, fd, &buf, 1, 0);
	}
	ret = io_uring_submit(&ring);
	if (ret < 0) {
		fprintf(stderr, "submit(read_sqe): %d\n", ret);
		exit(1);
	}

	struct io_uring_cqe *cqe;
	for (int i = 0; i < n+1; i++) {
		struct io_uring_cqe *cqe;
		int ret = io_uring_wait_cqe(&ring, &cqe);
		if (ret < 0) {
			fprintf(stderr, "wait_cqe(): %d\n", ret);
			return 1;
		}
		if (cqe->user_data == 123)
			printf("timeout found\n");
		io_uring_cqe_seen(&ring, cqe);
	}
}
---
 fs/io_uring.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)
fs/io_uring.c +1 -1
index b74957856e68..ae7244f8e842 100644
@@ -1639,7 +1639,7 @@ static void io_flush_timeouts(struct io_ring_ctx *ctx)
 
 		if (io_is_timeout_noseq(req))
 			break;
-		if (req->timeout.target_seq != ctx->cached_cq_tail
+		if (req->timeout.target_seq > ctx->cached_cq_tail
 					- atomic_read(&ctx->cq_timeouts))
 			break;
 
Signature · 1 line
2.20.1
#1 lore raw
Quoted 7 lines · Marcelo Diop-Gonzalez

Right now io_flush_timeouts() checks if the current number of events is equal to ->timeout.target_seq, but this will miss some timeouts if there have been more than 1 event added since the last time they were flushed (possible in io_submit_flush_completions(), for example). The test below hangs before this change (unless you run with

$ ./a.out ~/somefile 1)

[...]

Quoted 11 lines
---
 fs/io_uring.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)
fs/io_uring.c +0 -0
index b74957856e68..ae7244f8e842 100644

fs/io_uring.c static void io_flush_timeouts(struct io_ring_ctx *ctx) · line 1642

Quoted 5 lines
fs/io_uring.c +1 -1
@@ -1639,7 +1639,7 @@ static void io_flush_timeouts(struct io_ring_ctx *ctx)
 
 		if (io_is_timeout_noseq(req))
 			break;
-		if (req->timeout.target_seq != ctx->cached_cq_tail
+		if (req->timeout.target_seq > ctx->cached_cq_tail

There was an pretty old patch for probably that problem, which got lost... Please consider that target_seq and others are u32 and may easily overflow, you can't do comparisons as freely. It would be great to finally fix it, but that can be a bit harder to do.

Quoted 4 lines
fs/io_uring.c +0 -0
 					- atomic_read(&ctx->cq_timeouts))
 			break;
 
Signature · 1 line
Pavel Begunkov
#2 lore raw
Quoted 22 lines · Pavel Begunkov
Quoted 7 lines · Marcelo Diop-Gonzalez

Right now io_flush_timeouts() checks if the current number of events is equal to ->timeout.target_seq, but this will miss some timeouts if there have been more than 1 event added since the last time they were flushed (possible in io_submit_flush_completions(), for example). The test below hangs before this change (unless you run with

$ ./a.out ~/somefile 1)

[...]

Quoted 12 lines
---
 fs/io_uring.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)
fs/io_uring.c +0 -0
index b74957856e68..ae7244f8e842 100644
@@ -1639,7 +1639,7 @@ static void io_flush_timeouts(struct io_ring_ctx *ctx)
 
Quoted 9 lines

fs/io_uring.c static void io_flush_timeouts(struct io_ring_ctx *ctx) · line 1642

Quoted 4 lines
fs/io_uring.c +1 -1
              if (io_is_timeout_noseq(req))
                      break;
-             if (req->timeout.target_seq != ctx->cached_cq_tail
+             if (req->timeout.target_seq > ctx->cached_cq_tail

There was an pretty old patch for probably that problem, which got lost... Please consider that target_seq and others are u32 and may easily overflow, you can't do comparisons as freely. It would be great to finally fix it, but that can be a bit harder to do.

Ahh whoops! Good point, didn't think of that.

-Marcelo

Quoted 8 lines

fs/io_uring.c static void io_flush_timeouts(struct io_ring_ctx *ctx) · line 1645

Quoted 5 lines
fs/io_uring.c +0 -0
                                      - atomic_read(&ctx->cq_timeouts))
                      break;
 

--
Pavel Begunkov