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 <[email protected]>
Acked-by: Stanislav Fomichev <[email protected]>
Reviewed-by: Jakub Kicinski <[email protected]>
Reviewed-by: Eric Dumazet <[email protected]>
---
fs/eventpoll.c | 7 +++++--
1 file changed, 5 insertions(+), 2 deletions(-)
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);
--
2.25.1