net/sched: act_police: fix race condition on state variables

after 'police' configuration parameters were converted to use RCU instead
of spinlock, the state variables used to compute the traffic rate (namely
'tcfp_toks', 'tcfp_ptoks' and 'tcfp_t_c') are erroneously read/updated in
the traffic path without any protection.

Use a dedicated spinlock to avoid race conditions on these variables, and
ensure proper cache-line alignment. In this way, 'police' is still faster
than what we observed when 'tcf_lock' was used in the traffic path _ i.e.
reverting commit 2d550dbad83c ("net/sched: act_police: don't use spinlock
in the data path"). Moreover, we preserve the throughput improvement that
was obtained after 'police' started using per-cpu counters, when 'avrate'
is used instead of 'rate'.

Changes since v1 (thanks to Eric Dumazet):
- call ktime_get_ns() before acquiring the lock in the traffic path
- use a dedicated spinlock instead of tcf_lock
- improve cache-line usage

Fixes: 2d550dbad83c ("net/sched: act_police: don't use spinlock in the data path")
Reported-and-suggested-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: Davide Caratti <dcaratti@redhat.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>

diff --git a/net/sched/act_police.c b/net/sched/act_police.c
index 052855d..ee4665a 100644 (file)
--- a/net/sched/act_police.c
+++ b/net/sched/act_police.c
@@ -27,10 +27,7 @@ struct tcf_police_params {
        u32                     tcfp_ewma_rate;
        s64                     tcfp_burst;
        u32                     tcfp_mtu;
-       s64                     tcfp_toks;
-       s64                     tcfp_ptoks;
        s64                     tcfp_mtu_ptoks;
-       s64                     tcfp_t_c;
        struct psched_ratecfg   rate;
        bool                    rate_present;
        struct psched_ratecfg   peak;
@@ -41,6 +38,11 @@ struct tcf_police_params {
 struct tcf_police {
        struct tc_action        common;
        struct tcf_police_params __rcu *params;
+
+       spinlock_t              tcfp_lock ____cacheline_aligned_in_smp;
+       s64                     tcfp_toks;
+       s64                     tcfp_ptoks;
+       s64                     tcfp_t_c;
 };
 
 #define to_police(pc) ((struct tcf_police *)pc)
@@ -186,12 +188,9 @@ static int tcf_police_init(struct net *net, struct nlattr *nla,
        }
 
        new->tcfp_burst = PSCHED_TICKS2NS(parm->burst);
-       new->tcfp_toks = new->tcfp_burst;
-       if (new->peak_present) {
+       if (new->peak_present)
                new->tcfp_mtu_ptoks = (s64)psched_l2t_ns(&new->peak,
                                                         new->tcfp_mtu);
-               new->tcfp_ptoks = new->tcfp_mtu_ptoks;
-       }
 
        if (tb[TCA_POLICE_AVRATE])
                new->tcfp_ewma_rate = nla_get_u32(tb[TCA_POLICE_AVRATE]);
@@ -207,7 +206,12 @@ static int tcf_police_init(struct net *net, struct nlattr *nla,
        }
 
        spin_lock_bh(&police->tcf_lock);
-       new->tcfp_t_c = ktime_get_ns();
+       spin_lock_bh(&police->tcfp_lock);
+       police->tcfp_t_c = ktime_get_ns();
+       police->tcfp_toks = new->tcfp_burst;
+       if (new->peak_present)
+               police->tcfp_ptoks = new->tcfp_mtu_ptoks;
+       spin_unlock_bh(&police->tcfp_lock);
        police->tcf_action = parm->action;
        rcu_swap_protected(police->params,
                           new,
@@ -257,25 +261,28 @@ static int tcf_police_act(struct sk_buff *skb, const struct tc_action *a,
                }
 
                now = ktime_get_ns();
-               toks = min_t(s64, now - p->tcfp_t_c, p->tcfp_burst);
+               spin_lock_bh(&police->tcfp_lock);
+               toks = min_t(s64, now - police->tcfp_t_c, p->tcfp_burst);
                if (p->peak_present) {
-                       ptoks = toks + p->tcfp_ptoks;
+                       ptoks = toks + police->tcfp_ptoks;
                        if (ptoks > p->tcfp_mtu_ptoks)
                                ptoks = p->tcfp_mtu_ptoks;
                        ptoks -= (s64)psched_l2t_ns(&p->peak,
                                                    qdisc_pkt_len(skb));
                }
-               toks += p->tcfp_toks;
+               toks += police->tcfp_toks;
                if (toks > p->tcfp_burst)
                        toks = p->tcfp_burst;
                toks -= (s64)psched_l2t_ns(&p->rate, qdisc_pkt_len(skb));
                if ((toks|ptoks) >= 0) {
-                       p->tcfp_t_c = now;
-                       p->tcfp_toks = toks;
-                       p->tcfp_ptoks = ptoks;
+                       police->tcfp_t_c = now;
+                       police->tcfp_toks = toks;
+                       police->tcfp_ptoks = ptoks;
+                       spin_unlock_bh(&police->tcfp_lock);
                        ret = p->tcfp_result;
                        goto inc_drops;
                }
+               spin_unlock_bh(&police->tcfp_lock);
        }
 
 inc_overlimits: