net: Pull out core bits of __netdev_alloc_skb and add __napi_alloc_skb

This change pulls the core functionality out of __netdev_alloc_skb and
places them in a new function named __alloc_rx_skb.  The reason for doing
this is to make these bits accessible to a new function __napi_alloc_skb.
In addition __alloc_rx_skb now has a new flags value that is used to
determine which page frag pool to allocate from.  If the SKB_ALLOC_NAPI
flag is set then the NAPI pool is used.  The advantage of this is that we
do not have to use local_irq_save/restore when accessing the NAPI pool from
NAPI context.

In my test setup I saw at least 11ns of savings using the napi_alloc_skb
function versus the netdev_alloc_skb function, most of this being due to
the fact that we didn't have to call local_irq_save/restore.

The main use case for napi_alloc_skb would be for things such as copybreak
or page fragment based receive paths where an skb is allocated after the
data has been received instead of before.

Signed-off-by: Alexander Duyck <alexander.h.duyck@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

1 files changed, 9 insertions, 0 deletions

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 736cc99f3f6c..85ab7d72b54c 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -151,6 +151,7 @@ struct net_device;
 struct scatterlist;
 struct pipe_inode_info;
 struct iov_iter;
+struct napi_struct;
 
 #if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE)
 struct nf_conntrack {
@@ -673,6 +674,7 @@ struct sk_buff {
 
 #define SKB_ALLOC_FCLONE        0x01
 #define SKB_ALLOC_RX            0x02
+#define SKB_ALLOC_NAPI          0x04
 
 /* Returns true if the skb was allocated from PFMEMALLOC reserves */
 static inline bool skb_pfmemalloc(const struct sk_buff *skb)
@@ -2165,6 +2167,13 @@ static inline struct sk_buff *netdev_alloc_skb_ip_align(struct net_device *dev,
 }
 
 void *napi_alloc_frag(unsigned int fragsz);
+struct sk_buff *__napi_alloc_skb(struct napi_struct *napi,
+                                 unsigned int length, gfp_t gfp_mask);
+static inline struct sk_buff *napi_alloc_skb(struct napi_struct *napi,
+                                             unsigned int length)
+{
+        return __napi_alloc_skb(napi, length, GFP_ATOMIC);
+}
 
 /**
  * __dev_alloc_pages - allocate page for network Rx