From mboxrd@z Thu Jan 1 00:00:00 1970 From: John Fastabend Subject: [net-next PATCH 09/12] net: sched: make cls_u32 per cpu Date: Fri, 12 Sep 2014 20:08:47 -0700 Message-ID: <20140913030845.6249.5623.stgit@nitbit.x32> References: <20140913025925.6249.12537.stgit@nitbit.x32> Mime-Version: 1.0 Content-Type: text/plain; charset="utf-8" Content-Transfer-Encoding: 7bit Cc: netdev@vger.kernel.org, paulmck@linux.vnet.ibm.com, brouer@redhat.com To: xiyou.wangcong@gmail.com, davem@davemloft.net, eric.dumazet@gmail.com, jhs@mojatatu.com Return-path: Received: from mail-ob0-f178.google.com ([209.85.214.178]:60825 "EHLO mail-ob0-f178.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751289AbaIMDJI (ORCPT ); Fri, 12 Sep 2014 23:09:08 -0400 Received: by mail-ob0-f178.google.com with SMTP id va2so1088589obc.23 for ; Fri, 12 Sep 2014 20:09:08 -0700 (PDT) In-Reply-To: <20140913025925.6249.12537.stgit@nitbit.x32> Sender: netdev-owner@vger.kernel.org List-ID: This uses per cpu counters in cls_u32 in preparation to convert over to rcu. Signed-off-by: John Fastabend Acked-by: Eric Dumazet --- net/sched/cls_u32.c | 75 ++++++++++++++++++++++++++++++++++++++++----------- 1 file changed, 59 insertions(+), 16 deletions(-) diff --git a/net/sched/cls_u32.c b/net/sched/cls_u32.c index 70c0be8..f3227d7 100644 --- a/net/sched/cls_u32.c +++ b/net/sched/cls_u32.c @@ -55,10 +55,12 @@ struct tc_u_knode { struct tcf_result res; struct tc_u_hnode *ht_down; #ifdef CONFIG_CLS_U32_PERF - struct tc_u32_pcnt *pf; + struct tc_u32_pcnt __percpu *pf; #endif #ifdef CONFIG_CLS_U32_MARK - struct tc_u32_mark mark; + u32 val; + u32 mask; + u32 __percpu *pcpu_success; #endif struct tc_u32_sel sel; }; @@ -115,16 +117,16 @@ next_knode: struct tc_u32_key *key = n->sel.keys; #ifdef CONFIG_CLS_U32_PERF - n->pf->rcnt += 1; + __this_cpu_inc(n->pf->rcnt); j = 0; #endif #ifdef CONFIG_CLS_U32_MARK - if ((skb->mark & n->mark.mask) != n->mark.val) { + if ((skb->mark & n->mask) != n->val) { n = n->next; goto next_knode; } else { - n->mark.success++; + __this_cpu_inc(*n->pcpu_success); } #endif @@ -143,7 +145,7 @@ next_knode: goto next_knode; } #ifdef CONFIG_CLS_U32_PERF - n->pf->kcnts[j] += 1; + __this_cpu_inc(n->pf->kcnts[j]); j++; #endif } @@ -159,7 +161,7 @@ check_terminal: } #endif #ifdef CONFIG_CLS_U32_PERF - n->pf->rhit += 1; + __this_cpu_inc(n->pf->rhit); #endif r = tcf_exts_exec(skb, &n->exts, res); if (r < 0) { @@ -342,7 +344,7 @@ static int u32_destroy_key(struct tcf_proto *tp, struct tc_u_knode *n) if (n->ht_down) n->ht_down->refcnt--; #ifdef CONFIG_CLS_U32_PERF - kfree(n->pf); + free_percpu(n->pf); #endif kfree(n); return 0; @@ -564,6 +566,9 @@ static int u32_change(struct net *net, struct sk_buff *in_skb, struct nlattr *tb[TCA_U32_MAX + 1]; u32 htid; int err; +#ifdef CONFIG_CLS_U32_PERF + size_t size; +#endif if (opt == NULL) return handle ? -EINVAL : 0; @@ -642,8 +647,9 @@ static int u32_change(struct net *net, struct sk_buff *in_skb, return -ENOBUFS; #ifdef CONFIG_CLS_U32_PERF - n->pf = kzalloc(sizeof(struct tc_u32_pcnt) + s->nkeys*sizeof(u64), GFP_KERNEL); - if (n->pf == NULL) { + size = sizeof(struct tc_u32_pcnt) + s->nkeys * sizeof(u64); + n->pf = __alloc_percpu(size, __alignof__(struct tc_u32_pcnt)); + if (!n->pf) { kfree(n); return -ENOBUFS; } @@ -656,12 +662,14 @@ static int u32_change(struct net *net, struct sk_buff *in_skb, tcf_exts_init(&n->exts, TCA_U32_ACT, TCA_U32_POLICE); #ifdef CONFIG_CLS_U32_MARK + n->pcpu_success = alloc_percpu(u32); + if (tb[TCA_U32_MARK]) { struct tc_u32_mark *mark; mark = nla_data(tb[TCA_U32_MARK]); - memcpy(&n->mark, mark, sizeof(struct tc_u32_mark)); - n->mark.success = 0; + n->val = mark->val; + n->mask = mark->mask; } #endif @@ -745,6 +753,11 @@ static int u32_dump(struct net *net, struct tcf_proto *tp, unsigned long fh, if (nla_put_u32(skb, TCA_U32_DIVISOR, divisor)) goto nla_put_failure; } else { +#ifdef CONFIG_CLS_U32_PERF + struct tc_u32_pcnt *gpf; +#endif + int cpu; + if (nla_put(skb, TCA_U32_SEL, sizeof(n->sel) + n->sel.nkeys*sizeof(struct tc_u32_key), &n->sel)) @@ -762,9 +775,20 @@ static int u32_dump(struct net *net, struct tcf_proto *tp, unsigned long fh, goto nla_put_failure; #ifdef CONFIG_CLS_U32_MARK - if ((n->mark.val || n->mark.mask) && - nla_put(skb, TCA_U32_MARK, sizeof(n->mark), &n->mark)) - goto nla_put_failure; + if ((n->val || n->mask)) { + struct tc_u32_mark mark = {.val = n->val, + .mask = n->mask, + .success = 0}; + + for_each_possible_cpu(cpu) { + __u32 cnt = *per_cpu_ptr(n->pcpu_success, cpu); + + mark.success += cnt; + } + + if (nla_put(skb, TCA_U32_MARK, sizeof(mark), &mark)) + goto nla_put_failure; + } #endif if (tcf_exts_dump(skb, &n->exts) < 0) @@ -779,10 +803,29 @@ static int u32_dump(struct net *net, struct tcf_proto *tp, unsigned long fh, } #endif #ifdef CONFIG_CLS_U32_PERF + gpf = kzalloc(sizeof(struct tc_u32_pcnt) + + n->sel.nkeys * sizeof(u64), + GFP_KERNEL); + if (!gpf) + goto nla_put_failure; + + for_each_possible_cpu(cpu) { + int i; + struct tc_u32_pcnt *pf = per_cpu_ptr(n->pf, cpu); + + gpf->rcnt += pf->rcnt; + gpf->rhit += pf->rhit; + for (i = 0; i < n->sel.nkeys; i++) + gpf->kcnts[i] += pf->kcnts[i]; + } + if (nla_put(skb, TCA_U32_PCNT, sizeof(struct tc_u32_pcnt) + n->sel.nkeys*sizeof(u64), - n->pf)) + gpf)) { + kfree(gpf); goto nla_put_failure; + } + kfree(gpf); #endif }