net: packet: add randomized fanout scheduler

We currently allow for different fanout scheduling policies in pf_packet
such as scheduling by skb's rxhash, round-robin, by cpu, and rollover.
Also allow for a random, equidistributed selection of the socket from the
fanout process group.

Signed-off-by: Daniel Borkmann <dborkman@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

diff --git a/include/uapi/linux/if_packet.h b/include/uapi/linux/if_packet.h
index b950c02030c0a7776227e83caf050fa32391d7a8..dbf06667394b1185fb1dc769a5da198636164a45 100644 (file)
--- a/include/uapi/linux/if_packet.h
+++ b/include/uapi/linux/if_packet.h
@@ -56,6 +56,7 @@ struct sockaddr_ll {
 #define PACKET_FANOUT_LB               1
 #define PACKET_FANOUT_CPU              2
 #define PACKET_FANOUT_ROLLOVER         3
+#define PACKET_FANOUT_RND              4
 #define PACKET_FANOUT_FLAG_ROLLOVER    0x1000
 #define PACKET_FANOUT_FLAG_DEFRAG      0x8000
 

diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index 1fdf9ab91c3fad327c4cd14bd67ed328fde93be7..bee9bfdc8d056cd771b0b726eaa6e706df1f0d82 100644 (file)
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -88,7 +88,7 @@
 #include <linux/virtio_net.h>
 #include <linux/errqueue.h>
 #include <linux/net_tstamp.h>
-
+#include <linux/reciprocal_div.h>
 #ifdef CONFIG_INET
 #include <net/inet_common.h>
 #endif
@@ -1158,6 +1158,13 @@ static unsigned int fanout_demux_cpu(struct packet_fanout *f,
        return smp_processor_id() % num;
 }
 
+static unsigned int fanout_demux_rnd(struct packet_fanout *f,
+                                    struct sk_buff *skb,
+                                    unsigned int num)
+{
+       return reciprocal_divide(prandom_u32(), num);
+}
+
 static unsigned int fanout_demux_rollover(struct packet_fanout *f,
                                          struct sk_buff *skb,
                                          unsigned int idx, unsigned int skip,
@@ -1215,6 +1222,9 @@ static int packet_rcv_fanout(struct sk_buff *skb, struct net_device *dev,
        case PACKET_FANOUT_CPU:
                idx = fanout_demux_cpu(f, skb, num);
                break;
+       case PACKET_FANOUT_RND:
+               idx = fanout_demux_rnd(f, skb, num);
+               break;
        case PACKET_FANOUT_ROLLOVER:
                idx = fanout_demux_rollover(f, skb, 0, (unsigned int) -1, num);
                break;
@@ -1284,6 +1294,7 @@ static int fanout_add(struct sock *sk, u16 id, u16 type_flags)
        case PACKET_FANOUT_HASH:
        case PACKET_FANOUT_LB:
        case PACKET_FANOUT_CPU:
+       case PACKET_FANOUT_RND:
                break;
        default:
                return -EINVAL;