netfilter: nft_counter: convert it to use per-cpu counters

This patch converts the existing seqlock to per-cpu counters.

Suggested-by: Eric Dumazet <eric.dumazet@gmail.com>
Suggested-by: Patrick McHardy <kaber@trash.net>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>

diff --git a/net/netfilter/nft_counter.c b/net/netfilter/nft_counter.c
index 1759123..1067fb4 100644 (file)
--- a/net/netfilter/nft_counter.c
+++ b/net/netfilter/nft_counter.c
@@ -18,39 +18,59 @@
 #include <net/netfilter/nf_tables.h>
 
 struct nft_counter {
-       seqlock_t       lock;
        u64             bytes;
        u64             packets;
 };
 
+struct nft_counter_percpu {
+       struct nft_counter      counter;
+       struct u64_stats_sync   syncp;
+};
+
+struct nft_counter_percpu_priv {
+       struct nft_counter_percpu __percpu *counter;
+};
+
 static void nft_counter_eval(const struct nft_expr *expr,
                             struct nft_regs *regs,
                             const struct nft_pktinfo *pkt)
 {
-       struct nft_counter *priv = nft_expr_priv(expr);
-
-       write_seqlock_bh(&priv->lock);
-       priv->bytes += pkt->skb->len;
-       priv->packets++;
-       write_sequnlock_bh(&priv->lock);
+       struct nft_counter_percpu_priv *priv = nft_expr_priv(expr);
+       struct nft_counter_percpu *this_cpu;
+
+       local_bh_disable();
+       this_cpu = this_cpu_ptr(priv->counter);
+       u64_stats_update_begin(&this_cpu->syncp);
+       this_cpu->counter.bytes += pkt->skb->len;
+       this_cpu->counter.packets++;
+       u64_stats_update_end(&this_cpu->syncp);
+       local_bh_enable();
 }
 
 static int nft_counter_dump(struct sk_buff *skb, const struct nft_expr *expr)
 {
-       struct nft_counter *priv = nft_expr_priv(expr);
+       struct nft_counter_percpu_priv *priv = nft_expr_priv(expr);
+       struct nft_counter_percpu *cpu_stats;
+       struct nft_counter total;
+       u64 bytes, packets;
        unsigned int seq;
-       u64 bytes;
-       u64 packets;
-
-       do {
-               seq = read_seqbegin(&priv->lock);
-               bytes   = priv->bytes;
-               packets = priv->packets;
-       } while (read_seqretry(&priv->lock, seq));
-
-       if (nla_put_be64(skb, NFTA_COUNTER_BYTES, cpu_to_be64(bytes)))
-               goto nla_put_failure;
-       if (nla_put_be64(skb, NFTA_COUNTER_PACKETS, cpu_to_be64(packets)))
+       int cpu;
+
+       memset(&total, 0, sizeof(total));
+       for_each_possible_cpu(cpu) {
+               cpu_stats = per_cpu_ptr(priv->counter, cpu);
+               do {
+                       seq     = u64_stats_fetch_begin_irq(&cpu_stats->syncp);
+                       bytes   = cpu_stats->counter.bytes;
+                       packets = cpu_stats->counter.packets;
+               } while (u64_stats_fetch_retry_irq(&cpu_stats->syncp, seq));
+
+               total.packets += packets;
+               total.bytes += bytes;
+       }
+
+       if (nla_put_be64(skb, NFTA_COUNTER_BYTES, cpu_to_be64(total.bytes)) ||
+           nla_put_be64(skb, NFTA_COUNTER_PACKETS, cpu_to_be64(total.packets)))
                goto nla_put_failure;
        return 0;
 
@@ -67,23 +87,44 @@ static int nft_counter_init(const struct nft_ctx *ctx,
                            const struct nft_expr *expr,
                            const struct nlattr * const tb[])
 {
-       struct nft_counter *priv = nft_expr_priv(expr);
+       struct nft_counter_percpu_priv *priv = nft_expr_priv(expr);
+       struct nft_counter_percpu __percpu *cpu_stats;
+       struct nft_counter_percpu *this_cpu;
+
+       cpu_stats = netdev_alloc_pcpu_stats(struct nft_counter_percpu);
+       if (cpu_stats == NULL)
+               return ENOMEM;
+
+       preempt_disable();
+       this_cpu = this_cpu_ptr(cpu_stats);
+       if (tb[NFTA_COUNTER_PACKETS]) {
+               this_cpu->counter.packets =
+                       be64_to_cpu(nla_get_be64(tb[NFTA_COUNTER_PACKETS]));
+       }
+       if (tb[NFTA_COUNTER_BYTES]) {
+               this_cpu->counter.bytes =
+                       be64_to_cpu(nla_get_be64(tb[NFTA_COUNTER_BYTES]));
+       }
+       preempt_enable();
+       priv->counter = cpu_stats;
+       return 0;
+}
 
-       if (tb[NFTA_COUNTER_PACKETS])
-               priv->packets = be64_to_cpu(nla_get_be64(tb[NFTA_COUNTER_PACKETS]));
-       if (tb[NFTA_COUNTER_BYTES])
-               priv->bytes = be64_to_cpu(nla_get_be64(tb[NFTA_COUNTER_BYTES]));
+static void nft_counter_destroy(const struct nft_ctx *ctx,
+                               const struct nft_expr *expr)
+{
+       struct nft_counter_percpu_priv *priv = nft_expr_priv(expr);
 
-       seqlock_init(&priv->lock);
-       return 0;
+       free_percpu(priv->counter);
 }
 
 static struct nft_expr_type nft_counter_type;
 static const struct nft_expr_ops nft_counter_ops = {
        .type           = &nft_counter_type,
-       .size           = NFT_EXPR_SIZE(sizeof(struct nft_counter)),
+       .size           = NFT_EXPR_SIZE(sizeof(struct nft_counter_percpu_priv)),
        .eval           = nft_counter_eval,
        .init           = nft_counter_init,
+       .destroy        = nft_counter_destroy,
        .dump           = nft_counter_dump,
 };