netfilter: xt_NFQUEUE: queue balancing support

Adds support for specifying a range of queues instead of a single queue
id. Flows will be distributed across the given range.

This is useful for multicore systems: Instead of having a single
application read packets from a queue, start multiple
instances on queues x, x+1, .. x+n. Each instance can process
flows independently.

Packets for the same connection are put into the same queue.

Signed-off-by: Holger Eitzenberger <heitzenberger@astaro.com>
Signed-off-by: Florian Westphal <fwestphal@astaro.com>
Signed-off-by: Patrick McHardy <kaber@trash.net>

2 files changed, 98 insertions, 0 deletions

diff --git a/include/linux/netfilter/xt_NFQUEUE.h b/include/linux/netfilter/xt_NFQUEUE.h
index 982a89f78272..2584f4a777de 100644
--- a/include/linux/netfilter/xt_NFQUEUE.h
+++ b/include/linux/netfilter/xt_NFQUEUE.h
@@ -15,4 +15,9 @@ struct xt_NFQ_info {
         __u16 queuenum;
 };
 
+struct xt_NFQ_info_v1 {
+        __u16 queuenum;
+        __u16 queues_total;
+};
+
 #endif /* _XT_NFQ_TARGET_H */
diff --git a/net/netfilter/xt_NFQUEUE.c b/net/netfilter/xt_NFQUEUE.c
index 6e0f84d4d058..498b45101df7 100644
--- a/net/netfilter/xt_NFQUEUE.c
+++ b/net/netfilter/xt_NFQUEUE.c
@@ -11,6 +11,10 @@
 #include <linux/module.h>
 #include <linux/skbuff.h>
 
+#include <linux/ip.h>
+#include <linux/ipv6.h>
+#include <linux/jhash.h>
+
 #include <linux/netfilter.h>
 #include <linux/netfilter_arp.h>
 #include <linux/netfilter/x_tables.h>
@@ -23,6 +27,8 @@ MODULE_ALIAS("ipt_NFQUEUE");
 MODULE_ALIAS("ip6t_NFQUEUE");
 MODULE_ALIAS("arpt_NFQUEUE");
 
+static u32 jhash_initval __read_mostly;
+
 static unsigned int
 nfqueue_tg(struct sk_buff *skb, const struct xt_target_param *par)
 {
@@ -31,6 +37,72 @@ nfqueue_tg(struct sk_buff *skb, const struct xt_target_param *par)
         return NF_QUEUE_NR(tinfo->queuenum);
 }
 
+static u32 hash_v4(const struct sk_buff *skb)
+{
+        const struct iphdr *iph = ip_hdr(skb);
+        u32 ipaddr;
+
+        /* packets in either direction go into same queue */
+        ipaddr = iph->saddr ^ iph->daddr;
+
+        return jhash_2words(ipaddr, iph->protocol, jhash_initval);
+}
+
+static unsigned int
+nfqueue_tg4_v1(struct sk_buff *skb, const struct xt_target_param *par)
+{
+        const struct xt_NFQ_info_v1 *info = par->targinfo;
+        u32 queue = info->queuenum;
+
+        if (info->queues_total > 1)
+                queue = hash_v4(skb) % info->queues_total + queue;
+        return NF_QUEUE_NR(queue);
+}
+
+#if defined(CONFIG_IP6_NF_IPTABLES) || defined(CONFIG_IP6_NF_IPTABLES_MODULE)
+static u32 hash_v6(const struct sk_buff *skb)
+{
+        const struct ipv6hdr *ip6h = ipv6_hdr(skb);
+        u32 addr[4];
+
+        addr[0] = ip6h->saddr.s6_addr32[0] ^ ip6h->daddr.s6_addr32[0];
+        addr[1] = ip6h->saddr.s6_addr32[1] ^ ip6h->daddr.s6_addr32[1];
+        addr[2] = ip6h->saddr.s6_addr32[2] ^ ip6h->daddr.s6_addr32[2];
+        addr[3] = ip6h->saddr.s6_addr32[3] ^ ip6h->daddr.s6_addr32[3];
+
+        return jhash2(addr, ARRAY_SIZE(addr), jhash_initval);
+}
+
+static unsigned int
+nfqueue_tg6_v1(struct sk_buff *skb, const struct xt_target_param *par)
+{
+        const struct xt_NFQ_info_v1 *info = par->targinfo;
+        u32 queue = info->queuenum;
+
+        if (info->queues_total > 1)
+                queue = hash_v6(skb) % info->queues_total + queue;
+        return NF_QUEUE_NR(queue);
+}
+#endif
+
+static bool nfqueue_tg_v1_check(const struct xt_tgchk_param *par)
+{
+        const struct xt_NFQ_info_v1 *info = par->targinfo;
+        u32 maxid;
+
+        if (info->queues_total == 0) {
+                pr_err("NFQUEUE: number of total queues is 0\n");
+                return false;
+        }
+        maxid = info->queues_total - 1 + info->queuenum;
+        if (maxid > 0xffff) {
+                pr_err("NFQUEUE: number of queues (%u) out of range (got %u)\n",
+                       info->queues_total, maxid);
+                return false;
+        }
+        return true;
+}
+
 static struct xt_target nfqueue_tg_reg[] __read_mostly = {
         {
                 .name           = "NFQUEUE",
@@ -39,10 +111,31 @@ static struct xt_target nfqueue_tg_reg[] __read_mostly = {
                 .targetsize     = sizeof(struct xt_NFQ_info),
                 .me             = THIS_MODULE,
         },
+        {
+                .name           = "NFQUEUE",
+                .revision       = 1,
+                .family         = NFPROTO_IPV4,
+                .checkentry     = nfqueue_tg_v1_check,
+                .target         = nfqueue_tg4_v1,
+                .targetsize     = sizeof(struct xt_NFQ_info_v1),
+                .me             = THIS_MODULE,
+        },
+#if defined(CONFIG_IP6_NF_IPTABLES) || defined(CONFIG_IP6_NF_IPTABLES_MODULE)
+        {
+                .name           = "NFQUEUE",
+                .revision       = 1,
+                .family         = NFPROTO_IPV6,
+                .checkentry     = nfqueue_tg_v1_check,
+                .target         = nfqueue_tg6_v1,
+                .targetsize     = sizeof(struct xt_NFQ_info_v1),
+                .me             = THIS_MODULE,
+        },
+#endif
 };
 
 static int __init nfqueue_tg_init(void)
 {
+        get_random_bytes(&jhash_initval, sizeof(jhash_initval));
         return xt_register_targets(nfqueue_tg_reg, ARRAY_SIZE(nfqueue_tg_reg));
 }