drivers/net/intel: use napi_complete_done()

As per Eric Dumazet's previous patches:
(see commit (24d2e4a50737) - tg3: use napi_complete_done())

Quoting verbatim:
Using napi_complete_done() instead of napi_complete() allows
us to use /sys/class/net/ethX/gro_flush_timeout

GRO layer can aggregate more packets if the flush is delayed a bit,
without having to set too big coalescing parameters that impact
latencies.
</end quote>

Tested
configuration: low latency via ethtool -C ethx adaptive-rx off
				rx-usecs 10 adaptive-tx off tx-usecs 15
workload: streaming rx using netperf TCP_MAERTS

igb:
MIGRATED TCP MAERTS TEST from 0.0.0.0 (0.0.0.0) port 0 AF_INET to 10.0.0.1 () port 0 AF_INET : demo
...
Interim result:  941.48 10^6bits/s over 1.000 seconds ending at 1440193171.589

Alignment      Offset         Bytes    Bytes       Recvs   Bytes    Sends
Local  Remote  Local  Remote  Xfered   Per                 Per
Recv   Send    Recv   Send             Recv (avg)          Send (avg)
    8       8      0       0 1176930056  1475.36    797726   16384.00  71905

MIGRATED TCP MAERTS TEST from 0.0.0.0 (0.0.0.0) port 0 AF_INET to 10.0.0.1 () port 0 AF_INET : demo
...
Interim result:  941.49 10^6bits/s over 0.997 seconds ending at 1440193142.763

Alignment      Offset         Bytes    Bytes       Recvs   Bytes    Sends
Local  Remote  Local  Remote  Xfered   Per                 Per
Recv   Send    Recv   Send             Recv (avg)          Send (avg)
    8       8      0       0 1175182320  50476.00     23282   16384.00  71816

i40e:
Hard to test because the traffic is incoming so fast (24Gb/s) that GRO
always receives 87kB, even at the highest interrupt rate.

Other drivers were only compile tested.

Signed-off-by: Jesse Brandeburg <jesse.brandeburg@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>

1 files changed, 12 insertions, 9 deletions

diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_main.c b/drivers/net/ethernet/intel/fm10k/fm10k_main.c
index 537d81a6d738..e76a44cf330c 100644
--- a/drivers/net/ethernet/intel/fm10k/fm10k_main.c
+++ b/drivers/net/ethernet/intel/fm10k/fm10k_main.c
@@ -593,9 +593,9 @@ static void fm10k_receive_skb(struct fm10k_q_vector *q_vector,
 	napi_gro_receive(&q_vector->napi, skb);
 }
 
-static bool fm10k_clean_rx_irq(struct fm10k_q_vector *q_vector,
-			       struct fm10k_ring *rx_ring,
-			       int budget)
+static int fm10k_clean_rx_irq(struct fm10k_q_vector *q_vector,
+			      struct fm10k_ring *rx_ring,
+			      int budget)
 {
 	struct sk_buff *skb = rx_ring->skb;
 	unsigned int total_bytes = 0, total_packets = 0;
@@ -662,7 +662,7 @@ static bool fm10k_clean_rx_irq(struct fm10k_q_vector *q_vector,
 	q_vector->rx.total_packets += total_packets;
 	q_vector->rx.total_bytes += total_bytes;
 
-	return total_packets < budget;
+	return total_packets;
 }
 
 #define VXLAN_HLEN (sizeof(struct udphdr) + 8)
@@ -1422,7 +1422,7 @@ static int fm10k_poll(struct napi_struct *napi, int budget)
 	struct fm10k_q_vector *q_vector =
 			       container_of(napi, struct fm10k_q_vector, napi);
 	struct fm10k_ring *ring;
-	int per_ring_budget;
+	int per_ring_budget, work_done = 0;
 	bool clean_complete = true;
 
 	fm10k_for_each_ring(ring, q_vector->tx)
@@ -1436,16 +1436,19 @@ static int fm10k_poll(struct napi_struct *napi, int budget)
 	else
 		per_ring_budget = budget;
 
-	fm10k_for_each_ring(ring, q_vector->rx)
-		clean_complete &= fm10k_clean_rx_irq(q_vector, ring,
-						     per_ring_budget);
+	fm10k_for_each_ring(ring, q_vector->rx) {
+		int work = fm10k_clean_rx_irq(q_vector, ring, per_ring_budget);
+
+		work_done += work;
+		clean_complete &= !!(work < per_ring_budget);
+	}
 
 	/* If all work not completed, return budget and keep polling */
 	if (!clean_complete)
 		return budget;
 
 	/* all work done, exit the polling mode */
-	napi_complete(napi);
+	napi_complete_done(napi, work_done);
 
 	/* re-enable the q_vector */
 	fm10k_qv_enable(q_vector);