[PATCH v6 net-next 11/11] skbuff: queue NAPI_MERGED_FREE skbs into NAPI cache instead of freeing

[Alexander Lobakin]

napi_frags_finish() and napi_skb_finish() can only be called inside
NAPI Rx context, so we can feed NAPI cache with skbuff_heads that
got NAPI_MERGED_FREE verdict instead of immediate freeing.
Replace __kfree_skb() with __kfree_skb_defer() in napi_skb_finish()
and move napi_skb_free_stolen_head() to skbuff.c, so it can drop skbs
to NAPI cache.
As many drivers call napi_alloc_skb()/napi_get_frags() on their
receive path, this becomes especially useful.

Signed-off-by: Alexander Lobakin <aloba...@pm.me>
---
 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 906122eac82a..6d0a33d1c0db 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -2921,6 +2921,7 @@ static inline struct sk_buff *napi_alloc_skb(struct 
napi_struct *napi,
 }
 void napi_consume_skb(struct sk_buff *skb, int budget);
 
+void napi_skb_free_stolen_head(struct sk_buff *skb);
 void __kfree_skb_defer(struct sk_buff *skb);
 
 /**
diff --git a/net/core/dev.c b/net/core/dev.c
index 631807c196ad..ea9b46318d23 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -6095,13 +6095,6 @@ 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)
@@ -6115,7 +6108,7 @@ 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 875e1a453f7e..545a472273a5 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -916,9 +916,6 @@ static void napi_skb_cache_put(struct sk_buff *skb)
        struct napi_alloc_cache *nc = this_cpu_ptr(&napi_alloc_cache);
        u32 i;
 
-       /* drop skb->head and call any destructors for packet */
-       skb_release_all(skb);
-
        kasan_poison_object_data(skbuff_head_cache, skb);
        nc->skb_cache[nc->skb_count++] = skb;
 
@@ -935,6 +932,14 @@ 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);
 }
 
@@ -960,6 +965,7 @@ 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);
-- 
2.30.1