eventpoll: support busy poll per epoll instance

Allow busy polling on a per-epoll context basis. The per-epoll context
usec timeout value is preferred, but the pre-existing system wide sysctl
value is still supported if it specified.

busy_poll_usecs is a u32, but in a follow up patch the ioctl provided to
the user only allows setting a value from 0 to S32_MAX.

Signed-off-by: Joe Damato <jdamato@fastly.com>
Acked-by: Stanislav Fomichev <sdf@google.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

1 files changed, 39 insertions, 5 deletions

diff --git a/fs/eventpoll.c b/fs/eventpoll.c
index 3534d36a1474..401f865eced9 100644
--- a/fs/eventpoll.c
+++ b/fs/eventpoll.c
@@ -227,6 +227,8 @@ struct eventpoll {
 #ifdef CONFIG_NET_RX_BUSY_POLL
 	/* used to track busy poll napi_id */
 	unsigned int napi_id;
+	/* busy poll timeout */
+	u32 busy_poll_usecs;
 #endif
 
 #ifdef CONFIG_DEBUG_LOCK_ALLOC
@@ -387,11 +389,41 @@ static inline int ep_events_available(struct eventpoll *ep)
 }
 
 #ifdef CONFIG_NET_RX_BUSY_POLL
+/**
+ * busy_loop_ep_timeout - check if busy poll has timed out. The timeout value
+ * from the epoll instance ep is preferred, but if it is not set fallback to
+ * the system-wide global via busy_loop_timeout.
+ *
+ * @start_time: The start time used to compute the remaining time until timeout.
+ * @ep: Pointer to the eventpoll context.
+ *
+ * Return: true if the timeout has expired, false otherwise.
+ */
+static bool busy_loop_ep_timeout(unsigned long start_time,
+				 struct eventpoll *ep)
+{
+	unsigned long bp_usec = READ_ONCE(ep->busy_poll_usecs);
+
+	if (bp_usec) {
+		unsigned long end_time = start_time + bp_usec;
+		unsigned long now = busy_loop_current_time();
+
+		return time_after(now, end_time);
+	} else {
+		return busy_loop_timeout(start_time);
+	}
+}
+
+static bool ep_busy_loop_on(struct eventpoll *ep)
+{
+	return !!ep->busy_poll_usecs || net_busy_loop_on();
+}
+
 static bool ep_busy_loop_end(void *p, unsigned long start_time)
 {
 	struct eventpoll *ep = p;
 
-	return ep_events_available(ep) || busy_loop_timeout(start_time);
+	return ep_events_available(ep) || busy_loop_ep_timeout(start_time, ep);
 }
 
 /*
@@ -404,7 +436,7 @@ static bool ep_busy_loop(struct eventpoll *ep, int nonblock)
 {
 	unsigned int napi_id = READ_ONCE(ep->napi_id);
 
-	if ((napi_id >= MIN_NAPI_ID) && net_busy_loop_on()) {
+	if (napi_id >= MIN_NAPI_ID && ep_busy_loop_on(ep)) {
 		napi_busy_loop(napi_id, nonblock ? NULL : ep_busy_loop_end, ep, false,
 			       BUSY_POLL_BUDGET);
 		if (ep_events_available(ep))
@@ -425,12 +457,12 @@ static bool ep_busy_loop(struct eventpoll *ep, int nonblock)
  */
 static inline void ep_set_busy_poll_napi_id(struct epitem *epi)
 {
-	struct eventpoll *ep;
+	struct eventpoll *ep = epi->ep;
 	unsigned int napi_id;
 	struct socket *sock;
 	struct sock *sk;
 
-	if (!net_busy_loop_on())
+	if (!ep_busy_loop_on(ep))
 		return;
 
 	sock = sock_from_file(epi->ffd.file);
@@ -442,7 +474,6 @@ static inline void ep_set_busy_poll_napi_id(struct epitem *epi)
 		return;
 
 	napi_id = READ_ONCE(sk->sk_napi_id);
-	ep = epi->ep;
 
 	/* Non-NAPI IDs can be rejected
 	 *	or
@@ -2058,6 +2089,9 @@ static int do_epoll_create(int flags)
 		error = PTR_ERR(file);
 		goto out_free_fd;
 	}
+#ifdef CONFIG_NET_RX_BUSY_POLL
+	ep->busy_poll_usecs = 0;
+#endif
 	ep->file = file;
 	fd_install(fd, file);
 	return fd;