net: TX_RING and packet mmap

New packet socket feature that makes packet socket more efficient for
transmission.

- It reduces number of system call through a PACKET_TX_RING mechanism,
  based on PACKET_RX_RING (Circular buffer allocated in kernel space
  which is mmapped from user space).

- It minimizes CPU copy using fragmented SKB (almost zero copy).

Signed-off-by: Johann Baudy <johann.baudy@gnu-log.net>
Signed-off-by: David S. Miller <davem@davemloft.net>

2 files changed, 18 insertions, 5 deletions

diff --git a/include/linux/if_packet.h b/include/linux/if_packet.h
index 18db0668065a..5b2badeb9497 100644
--- a/include/linux/if_packet.h
+++ b/include/linux/if_packet.h
@@ -46,6 +46,8 @@ struct sockaddr_ll
 #define PACKET_VERSION                  10
 #define PACKET_HDRLEN                   11
 #define PACKET_RESERVE                  12
+#define PACKET_TX_RING                  13
+#define PACKET_LOSS                     14
 
 struct tpacket_stats
 {
@@ -63,14 +65,22 @@ struct tpacket_auxdata
         __u16           tp_vlan_tci;
 };
 
+/* Rx ring - header status */
+#define TP_STATUS_KERNEL        0x0
+#define TP_STATUS_USER          0x1
+#define TP_STATUS_COPY          0x2
+#define TP_STATUS_LOSING        0x4
+#define TP_STATUS_CSUMNOTREADY  0x8
+
+/* Tx ring - header status */
+#define TP_STATUS_AVAILABLE     0x0
+#define TP_STATUS_SEND_REQUEST  0x1
+#define TP_STATUS_SENDING       0x2
+#define TP_STATUS_WRONG_FORMAT  0x4
+
 struct tpacket_hdr
 {
         unsigned long   tp_status;
-#define TP_STATUS_KERNEL        0
-#define TP_STATUS_USER          1
-#define TP_STATUS_COPY          2
-#define TP_STATUS_LOSING        4
-#define TP_STATUS_CSUMNOTREADY  8
         unsigned int    tp_len;
         unsigned int    tp_snaplen;
         unsigned short  tp_mac;
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 1b5c3d298f43..aff494ba6a31 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -203,6 +203,9 @@ struct skb_shared_info {
 #ifdef CONFIG_HAS_DMA
         dma_addr_t      dma_maps[MAX_SKB_FRAGS + 1];
 #endif
+        /* Intermediate layers must ensure that destructor_arg
+         * remains valid until skb destructor */
+        void *          destructor_arg;
 };
 
 /* We divide dataref into two halves.  The higher 16 bits hold references