[net-next,v7,3/4] eventpoll: Add per-epoll prefer busy poll option

Commit Message

Joe Damato Feb. 9, 2024, 9:15 p.m. UTC

When using epoll-based busy poll, the prefer_busy_poll option is hardcoded
to false. Users may want to enable prefer_busy_poll to be used in
conjunction with gro_flush_timeout and defer_hard_irqs_count to keep device
IRQs masked.

Other busy poll methods allow enabling or disabling prefer busy poll via
SO_PREFER_BUSY_POLL, but epoll-based busy polling uses a hardcoded value.

Fix this edge case by adding support for a per-epoll context
prefer_busy_poll option. The default is false, as it was hardcoded before
this change.

Signed-off-by: Joe Damato <[e-mail]>
Acked-by: Stanislav Fomichev <[e-mail]>
Reviewed-by: Jakub Kicinski <[e-mail]>
Reviewed-by: Eric Dumazet <[e-mail]>
---
 fs/eventpoll.c | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

Patch

diff --git a/fs/eventpoll.c b/fs/eventpoll.c
index ed83ae33dd45..1b8d01af0c2c 100644
--- a/fs/eventpoll.c
+++ b/fs/eventpoll.c
@@ -231,6 +231,7 @@  struct eventpoll {
 	u32 busy_poll_usecs;
 	/* busy poll packet budget */
 	u16 busy_poll_budget;
+	bool prefer_busy_poll;
 #endif
 
 #ifdef CONFIG_DEBUG_LOCK_ALLOC
@@ -438,13 +439,14 @@  static bool ep_busy_loop(struct eventpoll *ep, int nonblock)
 {
 	unsigned int napi_id = READ_ONCE(ep->napi_id);
 	u16 budget = READ_ONCE(ep->busy_poll_budget);
+	bool prefer_busy_poll = READ_ONCE(ep->prefer_busy_poll);
 
 	if (!budget)
 		budget = BUSY_POLL_BUDGET;
 
 	if (napi_id >= MIN_NAPI_ID && ep_busy_loop_on(ep)) {
-		napi_busy_loop(napi_id, nonblock ? NULL : ep_busy_loop_end, ep, false,
-			       budget);
+		napi_busy_loop(napi_id, nonblock ? NULL : ep_busy_loop_end,
+			       ep, prefer_busy_poll, budget);
 		if (ep_events_available(ep))
 			return true;
 		/*
@@ -2098,6 +2100,7 @@  static int do_epoll_create(int flags)
 #ifdef CONFIG_NET_RX_BUSY_POLL
 	ep->busy_poll_usecs = 0;
 	ep->busy_poll_budget = 0;
+	ep->prefer_busy_poll = false;
 #endif
 	ep->file = file;
 	fd_install(fd, file);