summaryrefslogtreecommitdiffstats
path: root/net/sched
diff options
context:
space:
mode:
Diffstat (limited to 'net/sched')
-rw-r--r--net/sched/act_api.c44
-rw-r--r--net/sched/act_bpf.c2
-rw-r--r--net/sched/act_connmark.c3
-rw-r--r--net/sched/act_csum.c3
-rw-r--r--net/sched/act_gact.c44
-rw-r--r--net/sched/act_ipt.c2
-rw-r--r--net/sched/act_mirred.c58
-rw-r--r--net/sched/act_nat.c3
-rw-r--r--net/sched/act_pedit.c3
-rw-r--r--net/sched/act_simple.c3
-rw-r--r--net/sched/act_skbedit.c3
-rw-r--r--net/sched/act_vlan.c3
-rw-r--r--net/sched/cls_cgroup.c23
-rw-r--r--net/sched/sch_qfq.c1
14 files changed, 108 insertions, 87 deletions
diff --git a/net/sched/act_api.c b/net/sched/act_api.c
index af427a3..074a32f 100644
--- a/net/sched/act_api.c
+++ b/net/sched/act_api.c
@@ -27,6 +27,15 @@
#include <net/act_api.h>
#include <net/netlink.h>
+static void free_tcf(struct rcu_head *head)
+{
+ struct tcf_common *p = container_of(head, struct tcf_common, tcfc_rcu);
+
+ free_percpu(p->cpu_bstats);
+ free_percpu(p->cpu_qstats);
+ kfree(p);
+}
+
void tcf_hash_destroy(struct tc_action *a)
{
struct tcf_common *p = a->priv;
@@ -41,7 +50,7 @@ void tcf_hash_destroy(struct tc_action *a)
* gen_estimator est_timer() might access p->tcfc_lock
* or bstats, wait a RCU grace period before freeing p
*/
- kfree_rcu(p, tcfc_rcu);
+ call_rcu(&p->tcfc_rcu, free_tcf);
}
EXPORT_SYMBOL(tcf_hash_destroy);
@@ -230,15 +239,16 @@ void tcf_hash_cleanup(struct tc_action *a, struct nlattr *est)
if (est)
gen_kill_estimator(&pc->tcfc_bstats,
&pc->tcfc_rate_est);
- kfree_rcu(pc, tcfc_rcu);
+ call_rcu(&pc->tcfc_rcu, free_tcf);
}
EXPORT_SYMBOL(tcf_hash_cleanup);
int tcf_hash_create(u32 index, struct nlattr *est, struct tc_action *a,
- int size, int bind)
+ int size, int bind, bool cpustats)
{
struct tcf_hashinfo *hinfo = a->ops->hinfo;
struct tcf_common *p = kzalloc(size, GFP_KERNEL);
+ int err = -ENOMEM;
if (unlikely(!p))
return -ENOMEM;
@@ -246,18 +256,32 @@ int tcf_hash_create(u32 index, struct nlattr *est, struct tc_action *a,
if (bind)
p->tcfc_bindcnt = 1;
+ if (cpustats) {
+ p->cpu_bstats = netdev_alloc_pcpu_stats(struct gnet_stats_basic_cpu);
+ if (!p->cpu_bstats) {
+err1:
+ kfree(p);
+ return err;
+ }
+ p->cpu_qstats = alloc_percpu(struct gnet_stats_queue);
+ if (!p->cpu_qstats) {
+err2:
+ free_percpu(p->cpu_bstats);
+ goto err1;
+ }
+ }
spin_lock_init(&p->tcfc_lock);
INIT_HLIST_NODE(&p->tcfc_head);
p->tcfc_index = index ? index : tcf_hash_new_index(hinfo);
p->tcfc_tm.install = jiffies;
p->tcfc_tm.lastuse = jiffies;
if (est) {
- int err = gen_new_estimator(&p->tcfc_bstats, NULL,
- &p->tcfc_rate_est,
- &p->tcfc_lock, est);
+ err = gen_new_estimator(&p->tcfc_bstats, p->cpu_bstats,
+ &p->tcfc_rate_est,
+ &p->tcfc_lock, est);
if (err) {
- kfree(p);
- return err;
+ free_percpu(p->cpu_qstats);
+ goto err2;
}
}
@@ -615,10 +639,10 @@ int tcf_action_copy_stats(struct sk_buff *skb, struct tc_action *a,
if (err < 0)
goto errout;
- if (gnet_stats_copy_basic(&d, NULL, &p->tcfc_bstats) < 0 ||
+ if (gnet_stats_copy_basic(&d, p->cpu_bstats, &p->tcfc_bstats) < 0 ||
gnet_stats_copy_rate_est(&d, &p->tcfc_bstats,
&p->tcfc_rate_est) < 0 ||
- gnet_stats_copy_queue(&d, NULL,
+ gnet_stats_copy_queue(&d, p->cpu_qstats,
&p->tcfc_qstats,
p->tcfc_qstats.qlen) < 0)
goto errout;
diff --git a/net/sched/act_bpf.c b/net/sched/act_bpf.c
index 1df7828..e9e923a 100644
--- a/net/sched/act_bpf.c
+++ b/net/sched/act_bpf.c
@@ -281,7 +281,7 @@ static int tcf_bpf_init(struct net *net, struct nlattr *nla,
if (!tcf_hash_check(parm->index, act, bind)) {
ret = tcf_hash_create(parm->index, est, act,
- sizeof(*prog), bind);
+ sizeof(*prog), bind, false);
if (ret < 0)
goto destroy_fp;
diff --git a/net/sched/act_connmark.c b/net/sched/act_connmark.c
index 295d14b..f2b5402 100644
--- a/net/sched/act_connmark.c
+++ b/net/sched/act_connmark.c
@@ -108,7 +108,8 @@ static int tcf_connmark_init(struct net *net, struct nlattr *nla,
parm = nla_data(tb[TCA_CONNMARK_PARMS]);
if (!tcf_hash_check(parm->index, a, bind)) {
- ret = tcf_hash_create(parm->index, est, a, sizeof(*ci), bind);
+ ret = tcf_hash_create(parm->index, est, a, sizeof(*ci),
+ bind, false);
if (ret)
return ret;
diff --git a/net/sched/act_csum.c b/net/sched/act_csum.c
index 4cd5cf1..b07c535 100644
--- a/net/sched/act_csum.c
+++ b/net/sched/act_csum.c
@@ -62,7 +62,8 @@ static int tcf_csum_init(struct net *n, struct nlattr *nla, struct nlattr *est,
parm = nla_data(tb[TCA_CSUM_PARMS]);
if (!tcf_hash_check(parm->index, a, bind)) {
- ret = tcf_hash_create(parm->index, est, a, sizeof(*p), bind);
+ ret = tcf_hash_create(parm->index, est, a, sizeof(*p),
+ bind, false);
if (ret)
return ret;
ret = ACT_P_CREATED;
diff --git a/net/sched/act_gact.c b/net/sched/act_gact.c
index 7fffc22..5c1b051 100644
--- a/net/sched/act_gact.c
+++ b/net/sched/act_gact.c
@@ -28,14 +28,18 @@
#ifdef CONFIG_GACT_PROB
static int gact_net_rand(struct tcf_gact *gact)
{
- if (!gact->tcfg_pval || prandom_u32() % gact->tcfg_pval)
+ smp_rmb(); /* coupled with smp_wmb() in tcf_gact_init() */
+ if (prandom_u32() % gact->tcfg_pval)
return gact->tcf_action;
return gact->tcfg_paction;
}
static int gact_determ(struct tcf_gact *gact)
{
- if (!gact->tcfg_pval || gact->tcf_bstats.packets % gact->tcfg_pval)
+ u32 pack = atomic_inc_return(&gact->packets);
+
+ smp_rmb(); /* coupled with smp_wmb() in tcf_gact_init() */
+ if (pack % gact->tcfg_pval)
return gact->tcf_action;
return gact->tcfg_paction;
}
@@ -85,7 +89,8 @@ static int tcf_gact_init(struct net *net, struct nlattr *nla,
#endif
if (!tcf_hash_check(parm->index, a, bind)) {
- ret = tcf_hash_create(parm->index, est, a, sizeof(*gact), bind);
+ ret = tcf_hash_create(parm->index, est, a, sizeof(*gact),
+ bind, true);
if (ret)
return ret;
ret = ACT_P_CREATED;
@@ -99,16 +104,19 @@ static int tcf_gact_init(struct net *net, struct nlattr *nla,
gact = to_gact(a);
- spin_lock_bh(&gact->tcf_lock);
+ ASSERT_RTNL();
gact->tcf_action = parm->action;
#ifdef CONFIG_GACT_PROB
if (p_parm) {
gact->tcfg_paction = p_parm->paction;
- gact->tcfg_pval = p_parm->pval;
+ gact->tcfg_pval = max_t(u16, 1, p_parm->pval);
+ /* Make sure tcfg_pval is written before tcfg_ptype
+ * coupled with smp_rmb() in gact_net_rand() & gact_determ()
+ */
+ smp_wmb();
gact->tcfg_ptype = p_parm->ptype;
}
#endif
- spin_unlock_bh(&gact->tcf_lock);
if (ret == ACT_P_CREATED)
tcf_hash_insert(a);
return ret;
@@ -118,23 +126,21 @@ static int tcf_gact(struct sk_buff *skb, const struct tc_action *a,
struct tcf_result *res)
{
struct tcf_gact *gact = a->priv;
- int action = TC_ACT_SHOT;
+ int action = READ_ONCE(gact->tcf_action);
- spin_lock(&gact->tcf_lock);
#ifdef CONFIG_GACT_PROB
- if (gact->tcfg_ptype)
- action = gact_rand[gact->tcfg_ptype](gact);
- else
- action = gact->tcf_action;
-#else
- action = gact->tcf_action;
+ {
+ u32 ptype = READ_ONCE(gact->tcfg_ptype);
+
+ if (ptype)
+ action = gact_rand[ptype](gact);
+ }
#endif
- gact->tcf_bstats.bytes += qdisc_pkt_len(skb);
- gact->tcf_bstats.packets++;
+ bstats_cpu_update(this_cpu_ptr(gact->common.cpu_bstats), skb);
if (action == TC_ACT_SHOT)
- gact->tcf_qstats.drops++;
- gact->tcf_tm.lastuse = jiffies;
- spin_unlock(&gact->tcf_lock);
+ qstats_drop_inc(this_cpu_ptr(gact->common.cpu_qstats));
+
+ tcf_lastuse_update(&gact->tcf_tm);
return action;
}
diff --git a/net/sched/act_ipt.c b/net/sched/act_ipt.c
index cbc8dd7..99c9cc1 100644
--- a/net/sched/act_ipt.c
+++ b/net/sched/act_ipt.c
@@ -114,7 +114,7 @@ static int tcf_ipt_init(struct net *net, struct nlattr *nla, struct nlattr *est,
index = nla_get_u32(tb[TCA_IPT_INDEX]);
if (!tcf_hash_check(index, a, bind) ) {
- ret = tcf_hash_create(index, est, a, sizeof(*ipt), bind);
+ ret = tcf_hash_create(index, est, a, sizeof(*ipt), bind, false);
if (ret)
return ret;
ret = ACT_P_CREATED;
diff --git a/net/sched/act_mirred.c b/net/sched/act_mirred.c
index a42a3b2..19cd890 100644
--- a/net/sched/act_mirred.c
+++ b/net/sched/act_mirred.c
@@ -35,9 +35,11 @@ static LIST_HEAD(mirred_list);
static void tcf_mirred_release(struct tc_action *a, int bind)
{
struct tcf_mirred *m = to_mirred(a);
+ struct net_device *dev = rcu_dereference_protected(m->tcfm_dev, 1);
+
list_del(&m->tcfm_list);
- if (m->tcfm_dev)
- dev_put(m->tcfm_dev);
+ if (dev)
+ dev_put(dev);
}
static const struct nla_policy mirred_policy[TCA_MIRRED_MAX + 1] = {
@@ -93,7 +95,8 @@ static int tcf_mirred_init(struct net *net, struct nlattr *nla,
if (!tcf_hash_check(parm->index, a, bind)) {
if (dev == NULL)
return -EINVAL;
- ret = tcf_hash_create(parm->index, est, a, sizeof(*m), bind);
+ ret = tcf_hash_create(parm->index, est, a, sizeof(*m),
+ bind, true);
if (ret)
return ret;
ret = ACT_P_CREATED;
@@ -105,18 +108,18 @@ static int tcf_mirred_init(struct net *net, struct nlattr *nla,
}
m = to_mirred(a);
- spin_lock_bh(&m->tcf_lock);
+ ASSERT_RTNL();
m->tcf_action = parm->action;
m->tcfm_eaction = parm->eaction;
if (dev != NULL) {
m->tcfm_ifindex = parm->ifindex;
if (ret != ACT_P_CREATED)
- dev_put(m->tcfm_dev);
+ dev_put(rcu_dereference_protected(m->tcfm_dev, 1));
dev_hold(dev);
- m->tcfm_dev = dev;
+ rcu_assign_pointer(m->tcfm_dev, dev);
m->tcfm_ok_push = ok_push;
}
- spin_unlock_bh(&m->tcf_lock);
+
if (ret == ACT_P_CREATED) {
list_add(&m->tcfm_list, &mirred_list);
tcf_hash_insert(a);
@@ -131,20 +134,22 @@ static int tcf_mirred(struct sk_buff *skb, const struct tc_action *a,
struct tcf_mirred *m = a->priv;
struct net_device *dev;
struct sk_buff *skb2;
+ int retval, err;
u32 at;
- int retval, err = 1;
- spin_lock(&m->tcf_lock);
- m->tcf_tm.lastuse = jiffies;
- bstats_update(&m->tcf_bstats, skb);
+ tcf_lastuse_update(&m->tcf_tm);
+
+ bstats_cpu_update(this_cpu_ptr(m->common.cpu_bstats), skb);
- dev = m->tcfm_dev;
- if (!dev) {
- printk_once(KERN_NOTICE "tc mirred: target device is gone\n");
+ rcu_read_lock();
+ retval = READ_ONCE(m->tcf_action);
+ dev = rcu_dereference(m->tcfm_dev);
+ if (unlikely(!dev)) {
+ pr_notice_once("tc mirred: target device is gone\n");
goto out;
}
- if (!(dev->flags & IFF_UP)) {
+ if (unlikely(!(dev->flags & IFF_UP))) {
net_notice_ratelimited("tc mirred to Houston: device %s is down\n",
dev->name);
goto out;
@@ -152,7 +157,7 @@ static int tcf_mirred(struct sk_buff *skb, const struct tc_action *a,
at = G_TC_AT(skb->tc_verd);
skb2 = skb_clone(skb, GFP_ATOMIC);
- if (skb2 == NULL)
+ if (!skb2)
goto out;
if (!(at & AT_EGRESS)) {
@@ -168,16 +173,13 @@ static int tcf_mirred(struct sk_buff *skb, const struct tc_action *a,
skb2->dev = dev;
err = dev_queue_xmit(skb2);
-out:
if (err) {
- m->tcf_qstats.overlimits++;
+out:
+ qstats_overlimit_inc(this_cpu_ptr(m->common.cpu_qstats));
if (m->tcfm_eaction != TCA_EGRESS_MIRROR)
retval = TC_ACT_SHOT;
- else
- retval = m->tcf_action;
- } else
- retval = m->tcf_action;
- spin_unlock(&m->tcf_lock);
+ }
+ rcu_read_unlock();
return retval;
}
@@ -216,14 +218,16 @@ static int mirred_device_event(struct notifier_block *unused,
struct net_device *dev = netdev_notifier_info_to_dev(ptr);
struct tcf_mirred *m;
+ ASSERT_RTNL();
if (event == NETDEV_UNREGISTER)
list_for_each_entry(m, &mirred_list, tcfm_list) {
- spin_lock_bh(&m->tcf_lock);
- if (m->tcfm_dev == dev) {
+ if (rcu_access_pointer(m->tcfm_dev) == dev) {
dev_put(dev);
- m->tcfm_dev = NULL;
+ /* Note : no rcu grace period necessary, as
+ * net_device are already rcu protected.
+ */
+ RCU_INIT_POINTER(m->tcfm_dev, NULL);
}
- spin_unlock_bh(&m->tcf_lock);
}
return NOTIFY_DONE;
diff --git a/net/sched/act_nat.c b/net/sched/act_nat.c
index 270a030..5be0b3c 100644
--- a/net/sched/act_nat.c
+++ b/net/sched/act_nat.c
@@ -55,7 +55,8 @@ static int tcf_nat_init(struct net *net, struct nlattr *nla, struct nlattr *est,
parm = nla_data(tb[TCA_NAT_PARMS]);
if (!tcf_hash_check(parm->index, a, bind)) {
- ret = tcf_hash_create(parm->index, est, a, sizeof(*p), bind);
+ ret = tcf_hash_create(parm->index, est, a, sizeof(*p),
+ bind, false);
if (ret)
return ret;
ret = ACT_P_CREATED;
diff --git a/net/sched/act_pedit.c b/net/sched/act_pedit.c
index 17e6d66..ce8676a 100644
--- a/net/sched/act_pedit.c
+++ b/net/sched/act_pedit.c
@@ -57,7 +57,8 @@ static int tcf_pedit_init(struct net *net, struct nlattr *nla,
if (!tcf_hash_check(parm->index, a, bind)) {
if (!parm->nkeys)
return -EINVAL;
- ret = tcf_hash_create(parm->index, est, a, sizeof(*p), bind);
+ ret = tcf_hash_create(parm->index, est, a, sizeof(*p),
+ bind, false);
if (ret)
return ret;
p = to_pedit(a);
diff --git a/net/sched/act_simple.c b/net/sched/act_simple.c
index 6a8d948..d6b708d 100644
--- a/net/sched/act_simple.c
+++ b/net/sched/act_simple.c
@@ -103,7 +103,8 @@ static int tcf_simp_init(struct net *net, struct nlattr *nla,
defdata = nla_data(tb[TCA_DEF_DATA]);
if (!tcf_hash_check(parm->index, a, bind)) {
- ret = tcf_hash_create(parm->index, est, a, sizeof(*d), bind);
+ ret = tcf_hash_create(parm->index, est, a, sizeof(*d),
+ bind, false);
if (ret)
return ret;
diff --git a/net/sched/act_skbedit.c b/net/sched/act_skbedit.c
index fcfeeaf..6751b5f 100644
--- a/net/sched/act_skbedit.c
+++ b/net/sched/act_skbedit.c
@@ -99,7 +99,8 @@ static int tcf_skbedit_init(struct net *net, struct nlattr *nla,
parm = nla_data(tb[TCA_SKBEDIT_PARMS]);
if (!tcf_hash_check(parm->index, a, bind)) {
- ret = tcf_hash_create(parm->index, est, a, sizeof(*d), bind);
+ ret = tcf_hash_create(parm->index, est, a, sizeof(*d),
+ bind, false);
if (ret)
return ret;
diff --git a/net/sched/act_vlan.c b/net/sched/act_vlan.c
index d735ecf..796785e 100644
--- a/net/sched/act_vlan.c
+++ b/net/sched/act_vlan.c
@@ -116,7 +116,8 @@ static int tcf_vlan_init(struct net *net, struct nlattr *nla,
action = parm->v_action;
if (!tcf_hash_check(parm->index, a, bind)) {
- ret = tcf_hash_create(parm->index, est, a, sizeof(*v), bind);
+ ret = tcf_hash_create(parm->index, est, a, sizeof(*v),
+ bind, false);
if (ret)
return ret;
diff --git a/net/sched/cls_cgroup.c b/net/sched/cls_cgroup.c
index ea611b21..4c85bd3 100644
--- a/net/sched/cls_cgroup.c
+++ b/net/sched/cls_cgroup.c
@@ -30,35 +30,16 @@ static int cls_cgroup_classify(struct sk_buff *skb, const struct tcf_proto *tp,
struct tcf_result *res)
{
struct cls_cgroup_head *head = rcu_dereference_bh(tp->root);
- u32 classid;
-
- classid = task_cls_state(current)->classid;
-
- /*
- * Due to the nature of the classifier it is required to ignore all
- * packets originating from softirq context as accessing `current'
- * would lead to false results.
- *
- * This test assumes that all callers of dev_queue_xmit() explicitely
- * disable bh. Knowing this, it is possible to detect softirq based
- * calls by looking at the number of nested bh disable calls because
- * softirqs always disables bh.
- */
- if (in_serving_softirq()) {
- /* If there is an sk_classid we'll use that. */
- if (!skb->sk)
- return -1;
- classid = skb->sk->sk_classid;
- }
+ u32 classid = task_get_classid(skb);
if (!classid)
return -1;
-
if (!tcf_em_tree_match(skb, &head->ematches, NULL))
return -1;
res->classid = classid;
res->class = 0;
+
return tcf_exts_exec(skb, &head->exts, res);
}
diff --git a/net/sched/sch_qfq.c b/net/sched/sch_qfq.c
index b8d73bc..ffaeea6 100644
--- a/net/sched/sch_qfq.c
+++ b/net/sched/sch_qfq.c
@@ -186,7 +186,6 @@ struct qfq_sched {
u64 oldV, V; /* Precise virtual times. */
struct qfq_aggregate *in_serv_agg; /* Aggregate being served. */
- u32 num_active_agg; /* Num. of active aggregates */
u32 wsum; /* weight sum */
u32 iwsum; /* inverse weight sum */
OpenPOWER on IntegriCloud