[PATCH v2 net-next 3/3] skbuff: recycle GRO_MERGED_FREE skbs into NAPI skb cache

[Alexander Lobakin]

Instead of immediate freeing, recycle GRO_MERGED_FREE skbs into
NAPI skb cache. This is safe, because napi_gro_receive() and
napi_gro_frags() are called only inside NAPI softirq context.
As many drivers call napi_alloc_skb()/napi_get_frags() on their
receive path, this becomes especially useful.

Signed-off-by: Alexander Lobakin <alobakin@xxxxx>
---
 include/linux/skbuff.h |  1 +
 net/core/dev.c         |  9 +--------
 net/core/skbuff.c      | 12 +++++++++---
 3 files changed, 11 insertions(+), 11 deletions(-)

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 7a057b1f1eb8..507f1598e446 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -2888,6 +2888,7 @@ void napi_consume_skb(struct sk_buff *skb, int budget);
 
 void __kfree_skb_flush(void);
 void __kfree_skb_defer(struct sk_buff *skb);
+void napi_skb_free_stolen_head(struct sk_buff *skb);
 
 /**
  * __dev_alloc_pages - allocate page for network Rx
diff --git a/net/core/dev.c b/net/core/dev.c
index e4d77c8abe76..c28f0d601378 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -6054,13 +6054,6 @@ struct packet_offload *gro_find_complete_by_type(__be16 type)
 }
 EXPORT_SYMBOL(gro_find_complete_by_type);
 
-static void napi_skb_free_stolen_head(struct sk_buff *skb)
-{
-	skb_dst_drop(skb);
-	skb_ext_put(skb);
-	kmem_cache_free(skbuff_head_cache, skb);
-}
-
 static gro_result_t napi_skb_finish(struct napi_struct *napi,
 				    struct sk_buff *skb,
 				    gro_result_t ret)
@@ -6074,7 +6067,7 @@ static gro_result_t napi_skb_finish(struct napi_struct *napi,
 		if (NAPI_GRO_CB(skb)->free == NAPI_GRO_FREE_STOLEN_HEAD)
 			napi_skb_free_stolen_head(skb);
 		else
-			__kfree_skb(skb);
+			__kfree_skb_defer(skb);
 		break;
 
 	case GRO_HELD:
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index f42a3a04b918..bf6f92f1f4c7 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -902,9 +902,6 @@ static void napi_skb_cache_put(struct sk_buff *skb)
 {
 	struct napi_alloc_cache *nc = this_cpu_ptr(&napi_alloc_cache);
 
-	/* drop skb->head and call any destructors for packet */
-	skb_release_all(skb);
-
 	nc->skb_cache[nc->skb_count++] = skb;
 
 	if (unlikely(nc->skb_count == NAPI_SKB_CACHE_SIZE)) {
@@ -916,6 +913,14 @@ static void napi_skb_cache_put(struct sk_buff *skb)
 
 void __kfree_skb_defer(struct sk_buff *skb)
 {
+	skb_release_all(skb);
+	napi_skb_cache_put(skb);
+}
+
+void napi_skb_free_stolen_head(struct sk_buff *skb)
+{
+	skb_dst_drop(skb);
+	skb_ext_put(skb);
 	napi_skb_cache_put(skb);
 }
 
@@ -941,6 +946,7 @@ void napi_consume_skb(struct sk_buff *skb, int budget)
 		return;
 	}
 
+	skb_release_all(skb);
 	napi_skb_cache_put(skb);
 }
 EXPORT_SYMBOL(napi_consume_skb);
-- 
2.30.0