linux

mirror of https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git synced 2026-08-28 08:44:29 -04:00

Files

Oleg Nesterov f1cebdec97 pipe: only enable the extra wake_up(rd_wait) for EPOLLET consumers

pipe_poll() unconditionally sets ->poll_usage on the first call, forcing
anon_pipe_write() to wake up readers on every write even if the pipe was
not empty.

The reason is that some legacy epoll(EPOLLET) users depend on historical
per-write wakeups, see commit 3a34b13a88 ("pipe: make pipe writes always
wake up readers").

Test-case:

	#include <unistd.h>
	#include <sys/epoll.h>
	#include <assert.h>

	int main(void)
	{
		int pfd[2], efd;
		struct epoll_event evt = { .events = EPOLLIN | EPOLLET };

		pipe(pfd);
		efd = epoll_create1(0);
		epoll_ctl(efd, EPOLL_CTL_ADD, pfd[0], &evt);

		for (int i = 0; i < 2; ++i) {
			write(pfd[1], "", 1);
			assert(epoll_wait(efd, &evt, 1, 0) == 1);
		}

		return 0;
	}

it fails if WRITE_ONCE(poll_usage, true) is removed from pipe_poll().
However, without EPOLLET in .events, it does not need the extra wakeup
and succeeds even if write() is called only once before the main loop.

Currently io_uring without (unsupported) IORING_POLL_ADD_LEVEL always
sets EPOLLET, and in IORING_POLL_ADD_MULTI mode it depends on per-write
wakeups the same way:

	#include <unistd.h>
	#include <sys/mman.h>
	#include <sys/epoll.h>
	#include <sys/syscall.h>
	#include <linux/io_uring.h>
	#include <assert.h>

	int main(void)
	{
		struct io_uring_params p = {};
		int fd, pfd[2];

		pipe(pfd);

		fd = syscall(SYS_io_uring_setup, 2, &p);
		assert(fd >= 0);

		void *ring = mmap(0, p.cq_off.cqes + p.cq_entries * sizeof(struct io_uring_cqe),
				  PROT_READ | PROT_WRITE, MAP_SHARED, fd, IORING_OFF_SQ_RING);
		assert(ring != MAP_FAILED);
		*(unsigned *)(ring + p.sq_off.tail) = 1;

		struct io_uring_sqe *sqes = mmap(0, p.sq_entries * sizeof(*sqes),
				  PROT_READ | PROT_WRITE, MAP_SHARED, fd, IORING_OFF_SQES);
		assert(sqes != MAP_FAILED);
		sqes[0].opcode = IORING_OP_POLL_ADD;
		sqes[0].fd = pfd[0];
		sqes[0].len = IORING_POLL_ADD_MULTI;
		sqes[0].poll32_events = EPOLLIN;

		syscall(SYS_io_uring_enter, fd, 1, 0, 0, 0, 0);

		unsigned *cq_head = ring + p.cq_off.head;
		unsigned *cq_tail = ring + p.cq_off.tail;
		for (int i = 0; i < 2; ++i) {
			write(pfd[1], "", 1);
			syscall(SYS_io_uring_enter, fd, 0, 0, IORING_ENTER_GETEVENTS, 0, 0);
			assert(*cq_tail == ++*cq_head);
		}

		return 0;
	}

the 2nd assert() in the main loop fails without ->poll_usage == true.

Rename ->poll_usage to ->pseudo_edgetrigger to make the purpose clearer,
update the comments, and change pipe_poll() to set ->pseudo_edgetrigger
only if wait->_key & EPOLLET is true. This check should catch both users,
and this way poll/select and epoll without EPOLLET users will not pay for
the extra wakeup.

Signed-off-by: Oleg Nesterov <oleg@redhat.com>
Link: https://patch.msgid.link/anCNoW-x0bcB2ggg@redhat.com
Signed-off-by: Christian Brauner (Amutable) <brauner@kernel.org>

2026-08-12 11:36:41 +02:00