[PATCH 7/7] eventpoll: add method for configuring minimum wait on epoll context

[Jens Axboe]

Add support for EPOLL_CTL_MIN_WAIT, which can be used to define a
minimum reap time for an epoll context.

Basic test case:

struct d {
        int p1, p2;
};

static void *fn(void *data)
{
        struct d *d = data;
        char b = 0x89;

	/* Generate 2 events 20 msec apart */
        usleep(10000);
        write(d->p1, &b, sizeof(b));
        usleep(10000);
        write(d->p2, &b, sizeof(b));

        return NULL;
}

int main(int argc, char *argv[])
{
        struct epoll_event ev, events[2];
        pthread_t thread;
        int p1[2], p2[2];
        struct d d;
        int efd, ret;

        efd = epoll_create1(0);
        if (efd < 0) {
                perror("epoll_create");
                return 1;
        }

        if (pipe(p1) < 0) {
                perror("pipe");
                return 1;
        }
        if (pipe(p2) < 0) {
                perror("pipe");
                return 1;
        }

        ev.events = EPOLLIN;
        ev.data.fd = p1[0];
        if (epoll_ctl(efd, EPOLL_CTL_ADD, p1[0], &ev) < 0) {
                perror("epoll add");
                return 1;
        }
        ev.events = EPOLLIN;
        ev.data.fd = p2[0];
        if (epoll_ctl(efd, EPOLL_CTL_ADD, p2[0], &ev) < 0) {
                perror("epoll add");
                return 1;
        }

	/* always wait 200 msec for events */
        ev.data.u64 = 200000;
        if (epoll_ctl(efd, EPOLL_CTL_MIN_WAIT, -1, &ev) < 0) {
                perror("epoll add set timeout");
                return 1;
        }

        d.p1 = p1[1];
        d.p2 = p2[1];
        pthread_create(&thread, NULL, fn, &d);

	/* expect to get 2 events here rather than just 1 */
        ret = epoll_wait(efd, events, 2, -1);
        printf("epoll_wait=%d\n", ret);

        return 0;
}

If EPOLL_CTL_MIN_WAIT is used with a timeout of 0, it is a no-op, and
acts the same as if it wasn't called to begin with. Only a non-zero
usec delay value will result in a wait time being applied for reaping
events.

Signed-off-by: Jens Axboe <axboe@xxxxxxxxx>
---
 fs/eventpoll.c                 | 13 ++++++++++++-
 include/linux/eventpoll.h      |  2 +-
 include/uapi/linux/eventpoll.h |  1 +
 3 files changed, 14 insertions(+), 2 deletions(-)

diff --git a/fs/eventpoll.c b/fs/eventpoll.c
index daa9885d9c2b..ec7ffce8265a 100644
--- a/fs/eventpoll.c
+++ b/fs/eventpoll.c
@@ -2183,6 +2183,17 @@ int do_epoll_ctl(int epfd, int op, int fd, struct epoll_event *epds,
 	 */
 	ep = f.file->private_data;
 
+	/*
+	 * Handle EPOLL_CTL_MIN_WAIT upfront as we don't need to care about
+	 * the fd being passed in.
+	 */
+	if (op == EPOLL_CTL_MIN_WAIT) {
+		/* return old value */
+		error = ep->min_wait_ts;
+		ep->min_wait_ts = epds->data;
+		goto error_fput;
+	}
+
 	/* Get the "struct file *" for the target file */
 	tf = fdget(fd);
 	if (!tf.file)
@@ -2315,7 +2326,7 @@ SYSCALL_DEFINE4(epoll_ctl, int, epfd, int, op, int, fd,
 {
 	struct epoll_event epds;
 
-	if (ep_op_has_event(op) &&
+	if ((ep_op_has_event(op) || op == EPOLL_CTL_MIN_WAIT) &&
 	    copy_from_user(&epds, event, sizeof(struct epoll_event)))
 		return -EFAULT;
 
diff --git a/include/linux/eventpoll.h b/include/linux/eventpoll.h
index 3337745d81bd..cbef635cb7e4 100644
--- a/include/linux/eventpoll.h
+++ b/include/linux/eventpoll.h
@@ -59,7 +59,7 @@ int do_epoll_ctl(int epfd, int op, int fd, struct epoll_event *epds,
 /* Tells if the epoll_ctl(2) operation needs an event copy from userspace */
 static inline int ep_op_has_event(int op)
 {
-	return op != EPOLL_CTL_DEL;
+	return op != EPOLL_CTL_DEL && op != EPOLL_CTL_MIN_WAIT;
 }
 
 #else
diff --git a/include/uapi/linux/eventpoll.h b/include/uapi/linux/eventpoll.h
index 8a3432d0f0dc..81ecb1ca36e0 100644
--- a/include/uapi/linux/eventpoll.h
+++ b/include/uapi/linux/eventpoll.h
@@ -26,6 +26,7 @@
 #define EPOLL_CTL_ADD 1
 #define EPOLL_CTL_DEL 2
 #define EPOLL_CTL_MOD 3
+#define EPOLL_CTL_MIN_WAIT	4
 
 /* Epoll event masks */
 #define EPOLLIN		(__force __poll_t)0x00000001
-- 
2.35.1