net: gro: do not keep too many GRO packets in napi->rx_list

Commit c807943 ("net: Fix packet reordering caused by GRO and
listified RX cooperation") had the unfortunate effect of adding
latencies in common workloads.

Before the patch, GRO packets were immediately passed to
upper stacks.

After the patch, we can accumulate quite a lot of GRO
packets (depdending on NAPI budget).

My fix is counting in napi->rx_count number of segments
instead of number of logical packets.

Fixes: c807943 ("net: Fix packet reordering caused by GRO and listified RX cooperation")
Signed-off-by: Eric Dumazet <[email protected]>
Bisected-by: John Sperbeck <[email protected]>
Tested-by: Jian Yang <[email protected]>
Cc: Maxim Mikityanskiy <[email protected]>
Reviewed-by: Saeed Mahameed <[email protected]>
Reviewed-by: Edward Cree <[email protected]>
Reviewed-by: Alexander Lobakin <[email protected]>
Link: https://lore.kernel.org/r/[email protected]
Signed-off-by: Jakub Kicinski <[email protected]>

Author: edumazet

net/core/dev.c

@@ -5735,10 +5735,11 @@ static void gro_normal_list(struct napi_struct *napi)
 /* Queue one GRO_NORMAL SKB up for list processing. If batch size exceeded,
  * pass the whole batch up to the stack.
  */
-static void gro_normal_one(struct napi_struct *napi, struct sk_buff *skb)
+static void gro_normal_one(struct napi_struct *napi, struct sk_buff *skb, int segs)
 {
 	list_add_tail(&skb->list, &napi->rx_list);
-	if (++napi->rx_count >= gro_normal_batch)
+	napi->rx_count += segs;
+	if (napi->rx_count >= gro_normal_batch)
 		gro_normal_list(napi);
 }
 
@@ -5777,7 +5778,7 @@ static int napi_gro_complete(struct napi_struct *napi, struct sk_buff *skb)
 	}
 
 out:
-	gro_normal_one(napi, skb);
+	gro_normal_one(napi, skb, NAPI_GRO_CB(skb)->count);
 	return NET_RX_SUCCESS;
 }
 
@@ -6067,7 +6068,7 @@ static gro_result_t napi_skb_finish(struct napi_struct *napi,
 {
 	switch (ret) {
 	case GRO_NORMAL:
-		gro_normal_one(napi, skb);
+		gro_normal_one(napi, skb, 1);
 		break;
 
 	case GRO_DROP:
@@ -6155,7 +6156,7 @@ static gro_result_t napi_frags_finish(struct napi_struct *napi,
 		__skb_push(skb, ETH_HLEN);
 		skb->protocol = eth_type_trans(skb, skb->dev);
 		if (ret == GRO_NORMAL)
-			gro_normal_one(napi, skb);
+			gro_normal_one(napi, skb, 1);
 		break;
 
 	case GRO_DROP: