Re: [PATCH] io_uring/cmd_net: prevent infinite retry loop on unextractable timestamp skb

[Bui Viet Dung <dungvn2345@gmail.com>]

On Thu, Oct 8, 2026 at 3:43 PM Pavel Begunkov <asml.silence@gmail.com> wrote:
> Sounds fine since there are only timestamp skbs in this list, do
> you have a test case?

Hi Pavel,

Thanks for the review.

The issue was spotted during code inspection of the error handling path
in io_uring_cmd_timestamp(): specifically when skb_get_tx_timestamp() returns
a negative error (e.g. -ENOENT due to missing PHC bindings with
SOF_TIMESTAMPING_BIND_PHC or unavailable timestamp data). Since the
multishot apoll remains armed on EPOLLERR and the unhandled skb is spliced
back onto the head of sk_error_queue, it immediately re-triggers the command
in a tight busy-loop.

Below is a standalone test program demonstrating the TX_TIMESTAMP command
setup and execution with CQE32:

--- test_ts_cmd.c ---
#define _GNU_SOURCE
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <unistd.h>
#include <sys/socket.h>
#include <netinet/in.h>
#include <arpa/inet.h>
#include <linux/net_tstamp.h>
#include <linux/io_uring.h>
#include <sys/syscall.h>
#include <sys/mman.h>

#define IORING_OP_URING_CMD 46
#define SOCKET_URING_OP_TX_TIMESTAMP 4
#define IORING_SETUP_CQE32 (1U << 11)
#define SOF_TIMESTAMPING_OPT_TSONLY (1 << 11)

int main(void)
{
	int s, r_sock, ring_fd, val;
	struct sockaddr_in r_sin;
	socklen_t r_len = sizeof(r_sin);
	struct io_uring_params p;
	void *sq_ptr, *cq_ptr;
	struct io_uring_sqe *sqes;
	struct io_uring_cqe *cqes;
	unsigned *sq_tail, *sq_array, *cq_head, *cq_tail;
	char dummy = 'A';

	/* Receiver socket */
	r_sock = socket(AF_INET, SOCK_DGRAM, 0);
	memset(&r_sin, 0, sizeof(r_sin));
	r_sin.sin_family = AF_INET;
	r_sin.sin_addr.s_addr = htonl(INADDR_LOOPBACK);
	bind(r_sock, (struct sockaddr *)&r_sin, sizeof(r_sin));
	getsockname(r_sock, (struct sockaddr *)&r_sin, &r_len);

	/* Sender socket with TX software timestamp */
	s = socket(AF_INET, SOCK_DGRAM, 0);
	val = SOF_TIMESTAMPING_SOFTWARE | SOF_TIMESTAMPING_TX_SOFTWARE |
	      SOF_TIMESTAMPING_OPT_ID | SOF_TIMESTAMPING_OPT_TSONLY;
	setsockopt(s, SOL_SOCKET, SO_TIMESTAMPING, &val, sizeof(val));

	/* Send packet to queue timestamp skb into sk_error_queue */
	sendto(s, &dummy, sizeof(dummy), 0, (struct sockaddr *)&r_sin, sizeof(r_sin));
	usleep(10000);

	/* Initialize io_uring with CQE32 */
	memset(&p, 0, sizeof(p));
	p.flags = IORING_SETUP_CQE32;
	ring_fd = syscall(__NR_io_uring_setup, 4, &p);
	if (ring_fd < 0)
		return 1;

	sq_ptr = mmap(NULL, p.sq_off.array + p.sq_entries * sizeof(unsigned),
		      PROT_READ | PROT_WRITE, MAP_SHARED | MAP_POPULATE,
		      ring_fd, IORING_OFF_SQ_RING);
	sqes = mmap(NULL, p.sq_entries * sizeof(struct io_uring_sqe),
		    PROT_READ | PROT_WRITE, MAP_SHARED | MAP_POPULATE,
		    ring_fd, IORING_OFF_SQES);
	cq_ptr = mmap(NULL, p.cq_off.cqes + p.cq_entries * 2 * sizeof(struct io_uring_cqe),
		      PROT_READ | PROT_WRITE, MAP_SHARED | MAP_POPULATE,
		      ring_fd, IORING_OFF_CQ_RING);

	sq_tail = (unsigned *)(sq_ptr + p.sq_off.tail);
	sq_array = (unsigned *)(sq_ptr + p.sq_off.array);
	cq_head = (unsigned *)(cq_ptr + p.cq_off.head);
	cq_tail = (unsigned *)(cq_ptr + p.cq_off.tail);

	memset(&sqes[0], 0, sizeof(struct io_uring_sqe));
	sqes[0].opcode = IORING_OP_URING_CMD;
	sqes[0].fd = s;
	sqes[0].cmd_op = SOCKET_URING_OP_TX_TIMESTAMP;

	sq_array[0] = 0;
	*sq_tail = 1;

	/* Submit command and wait for CQE */
	syscall(__NR_io_uring_enter, ring_fd, 1, 1, 1, NULL, 0);

	close(ring_fd);
	close(s);
	close(r_sock);
	return 0;
}
---

If desired, I can format this into a test case for liburing under
test/timestamp.c.

Thanks,
Bui Viet Dung