diff mbox series

[5.4,086/129] net: core: use listified Rx for GRO_NORMAL in napi_gro_receive()

Message ID 20200908152234.000867723@linuxfoundation.org
State New
Headers show
Series None | expand

Commit Message

Greg Kroah-Hartman Sept. 8, 2020, 3:25 p.m. UTC 
From: Alexander Lobakin <alobakin@dlink.ru>

commit 6570bc79c0dfff0f228b7afd2de720fb4e84d61d upstream.

Commit 323ebb61e32b4 ("net: use listified RX for handling GRO_NORMAL
skbs") made use of listified skb processing for the users of
napi_gro_frags().
The same technique can be used in a way more common napi_gro_receive()
to speed up non-merged (GRO_NORMAL) skbs for a wide range of drivers
including gro_cells and mac80211 users.
This slightly changes the return value in cases where skb is being
dropped by the core stack, but it seems to have no impact on related
drivers' functionality.
gro_normal_batch is left untouched as it's very individual for every
single system configuration and might be tuned in manual order to
achieve an optimal performance.

Signed-off-by: Alexander Lobakin <alobakin@dlink.ru>
Acked-by: Edward Cree <ecree@solarflare.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Hyunsoon Kim <h10.kim@samsung.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

---
 net/core/dev.c |    9 +++++----
 1 file changed, 5 insertions(+), 4 deletions(-)

Comments

Edward Cree Sept. 8, 2020, 9:35 p.m. UTC | #1 
On 08/09/2020 16:25, Greg Kroah-Hartman wrote:
> From: Alexander Lobakin <alobakin@dlink.ru>
>
> commit 6570bc79c0dfff0f228b7afd2de720fb4e84d61d upstream.
>
> Commit 323ebb61e32b4 ("net: use listified RX for handling GRO_NORMAL
> skbs") made use of listified skb processing for the users of
> napi_gro_frags().
> The same technique can be used in a way more common napi_gro_receive()
> to speed up non-merged (GRO_NORMAL) skbs for a wide range of drivers
> including gro_cells and mac80211 users.
> This slightly changes the return value in cases where skb is being
> dropped by the core stack, but it seems to have no impact on related
> drivers' functionality.
> gro_normal_batch is left untouched as it's very individual for every
> single system configuration and might be tuned in manual order to
> achieve an optimal performance.
>
> Signed-off-by: Alexander Lobakin <alobakin@dlink.ru>
> Acked-by: Edward Cree <ecree@solarflare.com>
> Signed-off-by: David S. Miller <davem@davemloft.net>
> Signed-off-by: Hyunsoon Kim <h10.kim@samsung.com>
> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
I'm not quite sure why this is stable material(it's a performance
 enhancement, rather than a fix).  But if you do want to take it,
 make sure you've also got
c80794323e82 ("net: Fix packet reordering caused by GRO and listified RX cooperation")
b167191e2a85 ("net: wireless: intel: iwlwifi: fix GRO_NORMAL packet stalling")
 in your tree, particularly the latter as without it this commit
 triggers a severe regression in iwlwifi.

-ed
diff mbox series

Patch

--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -5602,12 +5602,13 @@  static void napi_skb_free_stolen_head(st
 	kmem_cache_free(skbuff_head_cache, skb);
 }
 
-static gro_result_t napi_skb_finish(gro_result_t ret, struct sk_buff *skb)
+static gro_result_t napi_skb_finish(struct napi_struct *napi,
+				    struct sk_buff *skb,
+				    gro_result_t ret)
 {
 	switch (ret) {
 	case GRO_NORMAL:
-		if (netif_receive_skb_internal(skb))
-			ret = GRO_DROP;
+		gro_normal_one(napi, skb);
 		break;
 
 	case GRO_DROP:
@@ -5639,7 +5640,7 @@  gro_result_t napi_gro_receive(struct nap
 
 	skb_gro_reset_offset(skb);
 
-	ret = napi_skb_finish(dev_gro_receive(napi, skb), skb);
+	ret = napi_skb_finish(napi, skb, dev_gro_receive(napi, skb));
 	trace_napi_gro_receive_exit(ret);
 
 	return ret;