From: Martin Karsten <mkarsten@uwaterloo.ca>

When NAPI_F_PREFER_BUSY_POLL is set during busy_poll_stop and the
irq_suspend_timeout is nonzero, this timeout is used to defer softirq
scheduling, potentially longer than gro_flush_timeout. This can be used
to effectively suspend softirq processing during the time it takes for
an application to process data and return to the next busy-poll.

The call to napi->poll in busy_poll_stop might lead to an invocation of
napi_complete_done, but the prefer-busy flag is still set at that time,
so the same logic is used to defer softirq scheduling for
irq_suspend_timeout.

Signed-off-by: Martin Karsten <mkarsten@uwaterloo.ca>
Co-developed-by: Joe Damato <jdamato@fastly.com>
Signed-off-by: Joe Damato <jdamato@fastly.com>
Tested-by: Joe Damato <jdamato@fastly.com>
Tested-by: Martin Karsten <mkarsten@uwaterloo.ca>
Acked-by: Stanislav Fomichev <sdf@fomichev.me>
Reviewed-by: Sridhar Samudrala <sridhar.samudrala@intel.com>
---
 v3:
   - Removed reference to non-existent sysfs parameter from commit
     message. No functional/code changes.

 net/core/dev.c | 17 +++++++++++++----
 1 file changed, 13 insertions(+), 4 deletions(-)

diff --git a/net/core/dev.c b/net/core/dev.c
index 4d910872963f..51d88f758e2e 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -6239,7 +6239,12 @@ bool napi_complete_done(struct napi_struct *n, int work_done)
 			timeout = napi_get_gro_flush_timeout(n);
 		n->defer_hard_irqs_count = napi_get_defer_hard_irqs(n);
 	}
-	if (n->defer_hard_irqs_count > 0) {
+	if (napi_prefer_busy_poll(n)) {
+		timeout = napi_get_irq_suspend_timeout(n);
+		if (timeout)
+			ret = false;
+	}
+	if (ret && n->defer_hard_irqs_count > 0) {
 		n->defer_hard_irqs_count--;
 		timeout = napi_get_gro_flush_timeout(n);
 		if (timeout)
@@ -6375,9 +6380,13 @@ static void busy_poll_stop(struct napi_struct *napi, void *have_poll_lock,
 	bpf_net_ctx = bpf_net_ctx_set(&__bpf_net_ctx);
 
 	if (flags & NAPI_F_PREFER_BUSY_POLL) {
-		napi->defer_hard_irqs_count = napi_get_defer_hard_irqs(napi);
-		timeout = napi_get_gro_flush_timeout(napi);
-		if (napi->defer_hard_irqs_count && timeout) {
+		timeout = napi_get_irq_suspend_timeout(napi);
+		if (!timeout) {
+			napi->defer_hard_irqs_count = napi_get_defer_hard_irqs(napi);
+			if (napi->defer_hard_irqs_count)
+				timeout = napi_get_gro_flush_timeout(napi);
+		}
+		if (timeout) {
 			hrtimer_start(&napi->timer, ns_to_ktime(timeout), HRTIMER_MODE_REL_PINNED);
 			skip_schedule = true;
 		}
-- 
2.25.1