netdev - [PATCH v2 net-next 2/3] skbuff: (re)use NAPI skb cache on allocation path

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-ID: <20210113133635.39402-2-alobakin@pm.me>
Date:   Wed, 13 Jan 2021 13:37:13 +0000
From:   Alexander Lobakin <alobakin@...me>
To:     "David S. Miller" <davem@...emloft.net>,
        Jakub Kicinski <kuba@...nel.org>
Cc:     Eric Dumazet <edumazet@...gle.com>,
        Edward Cree <ecree.xilinx@...il.com>,
        Jonathan Lemon <jonathan.lemon@...il.com>,
        Willem de Bruijn <willemb@...gle.com>,
        Miaohe Lin <linmiaohe@...wei.com>,
        Alexander Lobakin <alobakin@...me>,
        Steffen Klassert <steffen.klassert@...unet.com>,
        Guillaume Nault <gnault@...hat.com>,
        Yadu Kishore <kyk.segfault@...il.com>,
        Al Viro <viro@...iv.linux.org.uk>, netdev@...r.kernel.org,
        linux-kernel@...r.kernel.org
Subject: [PATCH v2 net-next 2/3] skbuff: (re)use NAPI skb cache on allocation path

Instead of calling kmem_cache_alloc() every time when building a NAPI
skb, (re)use skbuff_heads from napi_alloc_cache.skb_cache. Previously
this cache was only used for bulk-freeing skbuff_heads consumed via
napi_consume_skb() or __kfree_skb_defer().

Typical path is:
 - skb is queued for freeing from driver or stack, its skbuff_head
   goes into the cache instead of immediate freeing;
 - driver or stack requests NAPI skb allocation, an skbuff_head is
   taken from the cache instead of allocation.

Corner cases:
 - if it's empty on skb allocation, bulk-allocate the first half;
 - if it's full on skb consuming, bulk-wipe the second half.

Also try to balance its size after completing network softirqs
(__kfree_skb_flush()).

prefetchw() on CONFIG_SLUB is dropped since it makes no sense anymore.

Suggested-by: Edward Cree <ecree.xilinx@...il.com>
Signed-off-by: Alexander Lobakin <alobakin@...me>
---
 net/core/skbuff.c | 54 ++++++++++++++++++++++++++++++-----------------
 1 file changed, 35 insertions(+), 19 deletions(-)

diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index dc3300dc2ac4..f42a3a04b918 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -364,6 +364,7 @@ struct sk_buff *build_skb_around(struct sk_buff *skb,
 EXPORT_SYMBOL(build_skb_around);
 
 #define NAPI_SKB_CACHE_SIZE	64
+#define NAPI_SKB_CACHE_HALF	(NAPI_SKB_CACHE_SIZE / 2)
 
 struct napi_alloc_cache {
 	struct page_frag_cache page;
@@ -487,7 +488,15 @@ EXPORT_SYMBOL(__netdev_alloc_skb);
 
 static struct sk_buff *napi_skb_cache_get(struct napi_alloc_cache *nc)
 {
-	return kmem_cache_alloc(skbuff_head_cache, GFP_ATOMIC);
+	if (unlikely(!nc->skb_count))
+		nc->skb_count = kmem_cache_alloc_bulk(skbuff_head_cache,
+						      GFP_ATOMIC,
+						      NAPI_SKB_CACHE_HALF,
+						      nc->skb_cache);
+	if (unlikely(!nc->skb_count))
+		return NULL;
+
+	return nc->skb_cache[--nc->skb_count];
 }
 
 /**
@@ -867,40 +876,47 @@ void __consume_stateless_skb(struct sk_buff *skb)
 void __kfree_skb_flush(void)
 {
 	struct napi_alloc_cache *nc = this_cpu_ptr(&napi_alloc_cache);
+	size_t count;
+	void **ptr;
+
+	if (unlikely(nc->skb_count == NAPI_SKB_CACHE_HALF))
+		return;
+
+	if (nc->skb_count > NAPI_SKB_CACHE_HALF) {
+		count = nc->skb_count - NAPI_SKB_CACHE_HALF;
+		ptr = nc->skb_cache + NAPI_SKB_CACHE_HALF;
 
-	/* flush skb_cache if containing objects */
-	if (nc->skb_count) {
-		kmem_cache_free_bulk(skbuff_head_cache, nc->skb_count,
-				     nc->skb_cache);
-		nc->skb_count = 0;
+		kmem_cache_free_bulk(skbuff_head_cache, count, ptr);
+		nc->skb_count = NAPI_SKB_CACHE_HALF;
+	} else {
+		count = NAPI_SKB_CACHE_HALF - nc->skb_count;
+		ptr = nc->skb_cache + nc->skb_count;
+
+		nc->skb_count += kmem_cache_alloc_bulk(skbuff_head_cache,
+						       GFP_ATOMIC, count,
+						       ptr);
 	}
 }
 
-static inline void _kfree_skb_defer(struct sk_buff *skb)
+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);
 
-	/* record skb to CPU local list */
 	nc->skb_cache[nc->skb_count++] = skb;
 
-#ifdef CONFIG_SLUB
-	/* SLUB writes into objects when freeing */
-	prefetchw(skb);
-#endif
-
-	/* flush skb_cache if it is filled */
 	if (unlikely(nc->skb_count == NAPI_SKB_CACHE_SIZE)) {
-		kmem_cache_free_bulk(skbuff_head_cache, NAPI_SKB_CACHE_SIZE,
-				     nc->skb_cache);
-		nc->skb_count = 0;
+		kmem_cache_free_bulk(skbuff_head_cache, NAPI_SKB_CACHE_HALF,
+				     nc->skb_cache + NAPI_SKB_CACHE_HALF);
+		nc->skb_count = NAPI_SKB_CACHE_HALF;
 	}
 }
+
 void __kfree_skb_defer(struct sk_buff *skb)
 {
-	_kfree_skb_defer(skb);
+	napi_skb_cache_put(skb);
 }
 
 void napi_consume_skb(struct sk_buff *skb, int budget)
@@ -925,7 +941,7 @@ void napi_consume_skb(struct sk_buff *skb, int budget)
 		return;
 	}
 
-	_kfree_skb_defer(skb);
+	napi_skb_cache_put(skb);
 }
 EXPORT_SYMBOL(napi_consume_skb);
 
-- 
2.30.0