Merge branch 'bulk-cpumap-redirect'

Jesper Dangaard Brouer says:

====================
This patchset utilize a number of different kernel bulk APIs for optimizing
the performance for the XDP cpumap redirect feature.

Benchmark details are available here:
 https://github.com/xdp-project/xdp-project/blob/master/areas/cpumap/cpumap03-optimizations.org

Performance measurements can be considered micro benchmarks, as they measure
dropping packets at different stages in the network stack.
Summary based on above:

Baseline benchmarks
- baseline-redirect: UdpNoPorts: 3,180,074
- baseline-redirect: iptables-raw drop: 6,193,534

Patch1: bpf: cpumap use ptr_ring_consume_batched
- redirect: UdpNoPorts: 3,327,729
- redirect: iptables-raw drop: 6,321,540

Patch2: net: core: introduce build_skb_around
- redirect: UdpNoPorts: 3,221,303
- redirect: iptables-raw drop: 6,320,066

Patch3: bpf: cpumap do bulk allocation of SKBs
- redirect: UdpNoPorts: 3,290,563
- redirect: iptables-raw drop: 6,650,112

Patch4: bpf: cpumap memory prefetchw optimizations for struct page
- redirect: UdpNoPorts: 3,520,250
- redirect: iptables-raw drop: 7,649,604

In this V2 submission I have chosen drop the SKB-list patch using
netif_receive_skb_list() as it was not showing a performance improvement for
these micro benchmarks.
====================

Signed-off-by: Alexei Starovoitov <ast@kernel.org>

1 files changed, 52 insertions, 19 deletions

diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 9901f5322852..087622298d77 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -258,6 +258,33 @@ nodata:
 }
 EXPORT_SYMBOL(__alloc_skb);
 
+/* Caller must provide SKB that is memset cleared */
+static struct sk_buff *__build_skb_around(struct sk_buff *skb,
+					  void *data, unsigned int frag_size)
+{
+	struct skb_shared_info *shinfo;
+	unsigned int size = frag_size ? : ksize(data);
+
+	size -= SKB_DATA_ALIGN(sizeof(struct skb_shared_info));
+
+	/* Assumes caller memset cleared SKB */
+	skb->truesize = SKB_TRUESIZE(size);
+	refcount_set(&skb->users, 1);
+	skb->head = data;
+	skb->data = data;
+	skb_reset_tail_pointer(skb);
+	skb->end = skb->tail + size;
+	skb->mac_header = (typeof(skb->mac_header))~0U;
+	skb->transport_header = (typeof(skb->transport_header))~0U;
+
+	/* make sure we initialize shinfo sequentially */
+	shinfo = skb_shinfo(skb);
+	memset(shinfo, 0, offsetof(struct skb_shared_info, dataref));
+	atomic_set(&shinfo->dataref, 1);
+
+	return skb;
+}
+
 /**
  * __build_skb - build a network buffer
  * @data: data buffer provided by caller
@@ -279,32 +306,15 @@ EXPORT_SYMBOL(__alloc_skb);
  */
 struct sk_buff *__build_skb(void *data, unsigned int frag_size)
 {
-	struct skb_shared_info *shinfo;
 	struct sk_buff *skb;
-	unsigned int size = frag_size ? : ksize(data);
 
 	skb = kmem_cache_alloc(skbuff_head_cache, GFP_ATOMIC);
-	if (!skb)
+	if (unlikely(!skb))
 		return NULL;
 
-	size -= SKB_DATA_ALIGN(sizeof(struct skb_shared_info));
-
 	memset(skb, 0, offsetof(struct sk_buff, tail));
-	skb->truesize = SKB_TRUESIZE(size);
-	refcount_set(&skb->users, 1);
-	skb->head = data;
-	skb->data = data;
-	skb_reset_tail_pointer(skb);
-	skb->end = skb->tail + size;
-	skb->mac_header = (typeof(skb->mac_header))~0U;
-	skb->transport_header = (typeof(skb->transport_header))~0U;
 
-	/* make sure we initialize shinfo sequentially */
-	shinfo = skb_shinfo(skb);
-	memset(shinfo, 0, offsetof(struct skb_shared_info, dataref));
-	atomic_set(&shinfo->dataref, 1);
-
-	return skb;
+	return __build_skb_around(skb, data, frag_size);
 }
 
 /* build_skb() is wrapper over __build_skb(), that specifically
@@ -325,6 +335,29 @@ struct sk_buff *build_skb(void *data, unsigned int frag_size)
 }
 EXPORT_SYMBOL(build_skb);
 
+/**
+ * build_skb_around - build a network buffer around provided skb
+ * @skb: sk_buff provide by caller, must be memset cleared
+ * @data: data buffer provided by caller
+ * @frag_size: size of data, or 0 if head was kmalloced
+ */
+struct sk_buff *build_skb_around(struct sk_buff *skb,
+				 void *data, unsigned int frag_size)
+{
+	if (unlikely(!skb))
+		return NULL;
+
+	skb = __build_skb_around(skb, data, frag_size);
+
+	if (skb && frag_size) {
+		skb->head_frag = 1;
+		if (page_is_pfmemalloc(virt_to_head_page(data)))
+			skb->pfmemalloc = 1;
+	}
+	return skb;
+}
+EXPORT_SYMBOL(build_skb_around);
+
 #define NAPI_SKB_CACHE_SIZE	64
 
 struct napi_alloc_cache {