[NET]: Implement SKB fast cloning.

Protocols that make extensive use of SKB cloning,
for example TCP, eat at least 2 allocations per
packet sent as a result.

To cut the kmalloc() count in half, we implement
a pre-allocation scheme wherein we allocate
2 sk_buff objects in advance, then use a simple
reference count to free up the memory at the
correct time.

Based upon an initial patch by Thomas Graf and
suggestions from Herbert Xu.

Signed-off-by: David S. Miller <davem@davemloft.net>

2 files changed, 24 insertions, 4 deletions

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index db10335e4192..42edce6abe23 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -162,6 +162,13 @@ struct skb_timeval {
         u32     off_usec;
 };
 
+
+enum {
+        SKB_FCLONE_UNAVAILABLE,
+        SKB_FCLONE_ORIG,
+        SKB_FCLONE_CLONE,
+};
+
 /** 
  *      struct sk_buff - socket buffer
  *      @next: Next buffer in list
@@ -255,7 +262,8 @@ struct sk_buff {
                                 ip_summed:2,
                                 nohdr:1,
                                 nfctinfo:3;
-        __u8                    pkt_type;
+        __u8                    pkt_type:3,
+                                fclone:2;
         __be16                  protocol;
 
         void                    (*destructor)(struct sk_buff *skb);
@@ -295,8 +303,20 @@ struct sk_buff {
 #include <asm/system.h>
 
 extern void            __kfree_skb(struct sk_buff *skb);
-extern struct sk_buff *alloc_skb(unsigned int size,
-                                 unsigned int __nocast priority);
+extern struct sk_buff *__alloc_skb(unsigned int size,
+                                   unsigned int __nocast priority, int fclone);
+static inline struct sk_buff *alloc_skb(unsigned int size,
+                                        unsigned int __nocast priority)
+{
+        return __alloc_skb(size, priority, 0);
+}
+
+static inline struct sk_buff *alloc_skb_fclone(unsigned int size,
+                                               unsigned int __nocast priority)
+{
+        return __alloc_skb(size, priority, 1);
+}
+
 extern struct sk_buff *alloc_skb_from_cache(kmem_cache_t *cp,
                                             unsigned int size,
                                             unsigned int __nocast priority);
diff --git a/include/net/sock.h b/include/net/sock.h
index 14183883e8e6..d57aece9492c 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -1200,7 +1200,7 @@ static inline struct sk_buff *sk_stream_alloc_pskb(struct sock *sk,
         int hdr_len;
 
         hdr_len = SKB_DATA_ALIGN(sk->sk_prot->max_header);
-        skb = alloc_skb(size + hdr_len, gfp);
+        skb = alloc_skb_fclone(size + hdr_len, gfp);
         if (skb) {
                 skb->truesize += mem;
                 if (sk->sk_forward_alloc >= (int)skb->truesize ||