| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-ID: <20140310170837.3011.21600.stgit@nitbit.x32>
Date: Mon, 10 Mar 2014 10:08:38 -0700
From: John Fastabend <john.fastabend@...il.com>
To: xiyou.wangcong@...il.com, jhs@...atatu.com
Cc: netdev@...r.kernel.org, davem@...emloft.net
Subject: [RCU PATCH 13/14] net: sched: make bstats per cpu and estimator RCU
safe
In order to run qdisc's without locking statistics and estimators
need to be handled correctly.
To resolve bstats make the statistics per cpu. And because this is
only needed for qdiscs that are running without locks which is not
the case for most qdiscs in the near future only create percpu
stats when qdiscs set the TCQ_F_LLQDISC flag.
Next because estimators use the bstats to calculate packets per
second and bytes per second the estimator code paths are updated
to use the per cpu statistics.
After this if qdiscs use the _percpu routines to update stats
and set the TCQ_F_LLQDISC they can be made safe to run without
locking. Any qdisc that sets the flag needs to ensure that the
data structures it owns are safe to run without locks and
additionally currently all the skb list routines run without
locking so those would need to be updated in a future patch.
Signed-off-by: John Fastabend <john.r.fastabend@...el.com>
---
include/net/gen_stats.h | 16 +++++++++++
include/net/sch_generic.h | 40 ++++++++++++++++++++++++++--
net/core/gen_estimator.c | 62 +++++++++++++++++++++++++++++++++-----------
net/core/gen_stats.c | 41 ++++++++++++++++++++++++++++-
net/netfilter/xt_RATEEST.c | 4 +--
net/sched/act_api.c | 8 +++---
net/sched/act_police.c | 4 +--
net/sched/sch_api.c | 51 +++++++++++++++++++++++++++++++-----
net/sched/sch_cbq.c | 8 +++---
net/sched/sch_drr.c | 8 +++---
net/sched/sch_generic.c | 12 ++++++++-
net/sched/sch_hfsc.c | 13 +++++----
net/sched/sch_htb.c | 8 +++---
net/sched/sch_ingress.c | 2 +
net/sched/sch_mq.c | 8 +++---
net/sched/sch_mqprio.c | 12 ++++-----
net/sched/sch_multiq.c | 2 +
net/sched/sch_prio.c | 2 +
net/sched/sch_qfq.c | 12 +++++----
19 files changed, 241 insertions(+), 72 deletions(-)
diff --git a/include/net/gen_stats.h b/include/net/gen_stats.h
index ea4271d..dec4312 100644
--- a/include/net/gen_stats.h
+++ b/include/net/gen_stats.h
@@ -6,6 +6,11 @@
#include <linux/rtnetlink.h>
#include <linux/pkt_sched.h>
+struct gnet_stats_basic_cpu {
+ struct gnet_stats_basic_packed bstats;
+ struct u64_stats_sync syncp;
+};
+
struct gnet_dump {
spinlock_t * lock;
struct sk_buff * skb;
@@ -26,10 +31,17 @@ int gnet_stats_start_copy_compat(struct sk_buff *skb, int type,
int tc_stats_type, int xstats_type,
spinlock_t *lock, struct gnet_dump *d);
+int gnet_stats_copy_basic_cpu(struct gnet_dump *d,
+ struct gnet_stats_basic_cpu *b);
+void __gnet_stats_copy_basic_cpu(struct gnet_stats_basic_packed *bstats,
+ struct gnet_stats_basic_cpu *b);
int gnet_stats_copy_basic(struct gnet_dump *d,
struct gnet_stats_basic_packed *b);
+void __gnet_stats_copy_basic(struct gnet_stats_basic_packed *bstats,
+ struct gnet_stats_basic_packed *b);
int gnet_stats_copy_rate_est(struct gnet_dump *d,
const struct gnet_stats_basic_packed *b,
+ const struct gnet_stats_basic_cpu *cpu_b,
struct gnet_stats_rate_est64 *r);
int gnet_stats_copy_queue(struct gnet_dump *d, struct gnet_stats_queue *q);
int gnet_stats_copy_app(struct gnet_dump *d, void *st, int len);
@@ -37,13 +49,17 @@ int gnet_stats_copy_app(struct gnet_dump *d, void *st, int len);
int gnet_stats_finish_copy(struct gnet_dump *d);
int gen_new_estimator(struct gnet_stats_basic_packed *bstats,
+ struct gnet_stats_basic_cpu *cpu_bstats,
struct gnet_stats_rate_est64 *rate_est,
spinlock_t *stats_lock, struct nlattr *opt);
void gen_kill_estimator(struct gnet_stats_basic_packed *bstats,
+ struct gnet_stats_basic_cpu *cpu_bstats,
struct gnet_stats_rate_est64 *rate_est);
int gen_replace_estimator(struct gnet_stats_basic_packed *bstats,
+ struct gnet_stats_basic_cpu *cpu_bstats,
struct gnet_stats_rate_est64 *rate_est,
spinlock_t *stats_lock, struct nlattr *opt);
bool gen_estimator_active(const struct gnet_stats_basic_packed *bstats,
+ const struct gnet_stats_basic_cpu *cpu_bstats,
const struct gnet_stats_rate_est64 *rate_est);
#endif
diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h
index 20553c7..1a55e19 100644
--- a/include/net/sch_generic.h
+++ b/include/net/sch_generic.h
@@ -6,6 +6,7 @@
#include <linux/rcupdate.h>
#include <linux/pkt_sched.h>
#include <linux/pkt_cls.h>
+#include <linux/percpu.h>
#include <net/gen_stats.h>
#include <net/rtnetlink.h>
@@ -57,6 +58,9 @@ struct Qdisc {
* Its true for MQ/MQPRIO slaves, or non
* multiqueue device.
*/
+#define TCQ_F_LLQDISC 0x20 /* lockless qdiscs can run without using
+ * the qdisc lock to serialize skbs.
+ */
#define TCQ_F_WARN_NONWC (1 << 16)
u32 limit;
const struct Qdisc_ops *ops;
@@ -83,7 +87,10 @@ struct Qdisc {
*/
unsigned long state;
struct sk_buff_head q;
- struct gnet_stats_basic_packed bstats;
+ union {
+ struct gnet_stats_basic_packed bstats;
+ struct gnet_stats_basic_cpu __percpu *cpu_bstats;
+ } bstats_qdisc;
unsigned int __state;
struct gnet_stats_queue qstats;
struct rcu_head rcu_head;
@@ -494,7 +501,6 @@ static inline int qdisc_enqueue_root(struct sk_buff *skb, struct Qdisc *sch)
return qdisc_enqueue(skb, sch) & NET_XMIT_MASK;
}
-
static inline void bstats_update(struct gnet_stats_basic_packed *bstats,
const struct sk_buff *skb)
{
@@ -502,10 +508,38 @@ static inline void bstats_update(struct gnet_stats_basic_packed *bstats,
bstats->packets += skb_is_gso(skb) ? skb_shinfo(skb)->gso_segs : 1;
}
+static inline void qdisc_bstats_update_cpu(struct Qdisc *sch,
+ const struct sk_buff *skb)
+{
+ struct gnet_stats_basic_cpu *bstats =
+ this_cpu_ptr(sch->bstats_qdisc.cpu_bstats);
+
+ u64_stats_update_begin(&bstats->syncp);
+ bstats_update(&bstats->bstats, skb);
+ u64_stats_update_end(&bstats->syncp);
+}
+
static inline void qdisc_bstats_update(struct Qdisc *sch,
const struct sk_buff *skb)
{
- bstats_update(&sch->bstats, skb);
+ bstats_update(&sch->bstats_qdisc.bstats, skb);
+}
+
+static inline bool qdisc_is_lockless(struct Qdisc *q)
+{
+ return q->flags & TCQ_F_LLQDISC;
+}
+
+static inline int
+qdisc_bstats_copy_qdisc(struct gnet_dump *d, struct Qdisc *q)
+{
+ int err;
+
+ if (qdisc_is_lockless(q))
+ err = gnet_stats_copy_basic_cpu(d, q->bstats_qdisc.cpu_bstats);
+ else
+ err = gnet_stats_copy_basic(d, &q->bstats_qdisc.bstats);
+ return err;
}
static inline int __qdisc_enqueue_tail(struct sk_buff *skb, struct Qdisc *sch,
diff --git a/net/core/gen_estimator.c b/net/core/gen_estimator.c
index 6b5b6e7..d1c6283 100644
--- a/net/core/gen_estimator.c
+++ b/net/core/gen_estimator.c
@@ -91,6 +91,8 @@ struct gen_estimator
u32 avpps;
struct rcu_head e_rcu;
struct rb_node node;
+ struct gnet_stats_basic_cpu __percpu *cpu_bstats;
+ struct rcu_head head;
};
struct gen_estimator_head
@@ -122,11 +124,21 @@ static void est_timer(unsigned long arg)
spin_lock(e->stats_lock);
read_lock(&est_lock);
- if (e->bstats == NULL)
+
+ if (e->bstats == NULL && e->cpu_bstats == NULL)
goto skip;
- nbytes = e->bstats->bytes;
- npackets = e->bstats->packets;
+ if (e->cpu_bstats) {
+ struct gnet_stats_basic_packed b = {0};
+
+ __gnet_stats_copy_basic_cpu(&b, e->cpu_bstats);
+ nbytes = b.bytes;
+ npackets = b.packets;
+ } else {
+ nbytes = e->bstats->bytes;
+ npackets = e->bstats->packets;
+ }
+
brate = (nbytes - e->last_bytes)<<(7 - idx);
e->last_bytes = nbytes;
e->avbps += (brate >> e->ewma_log) - (e->avbps >> e->ewma_log);
@@ -146,6 +158,11 @@ skip:
rcu_read_unlock();
}
+static void *gen_get_bstats(struct gen_estimator *est)
+{
+ return est->cpu_bstats ? est->cpu_bstats : est->bstats;
+}
+
static void gen_add_node(struct gen_estimator *est)
{
struct rb_node **p = &est_root.rb_node, *parent = NULL;
@@ -156,7 +173,7 @@ static void gen_add_node(struct gen_estimator *est)
parent = *p;
e = rb_entry(parent, struct gen_estimator, node);
- if (est->bstats > e->bstats)
+ if (gen_get_bstats(est) > gen_get_bstats(e))
p = &parent->rb_right;
else
p = &parent->rb_left;
@@ -167,18 +184,20 @@ static void gen_add_node(struct gen_estimator *est)
static
struct gen_estimator *gen_find_node(const struct gnet_stats_basic_packed *bstats,
+ const struct gnet_stats_basic_cpu *cpu_bstats,
const struct gnet_stats_rate_est64 *rate_est)
{
struct rb_node *p = est_root.rb_node;
+ void *b = bstats ? bstats : cpu_bstats;
while (p) {
struct gen_estimator *e;
e = rb_entry(p, struct gen_estimator, node);
- if (bstats > e->bstats)
+ if (b > gen_get_bstats(e))
p = p->rb_right;
- else if (bstats < e->bstats || rate_est != e->rate_est)
+ else if (b < gen_get_bstats(e) || rate_est != e->rate_est)
p = p->rb_left;
else
return e;
@@ -203,6 +222,7 @@ struct gen_estimator *gen_find_node(const struct gnet_stats_basic_packed *bstats
*
*/
int gen_new_estimator(struct gnet_stats_basic_packed *bstats,
+ struct gnet_stats_basic_cpu *cpu_bstats,
struct gnet_stats_rate_est64 *rate_est,
spinlock_t *stats_lock,
struct nlattr *opt)
@@ -221,14 +241,24 @@ int gen_new_estimator(struct gnet_stats_basic_packed *bstats,
if (est == NULL)
return -ENOBUFS;
+ if (cpu_bstats) {
+ struct gnet_stats_basic_packed b = {0};
+
+ est->cpu_bstats = cpu_bstats;
+ __gnet_stats_copy_basic_cpu(&b, cpu_bstats);
+ est->last_bytes = b.bytes;
+ est->last_packets = b.packets;
+ } else {
+ est->bstats = bstats;
+ est->last_bytes = bstats->bytes;
+ est->last_packets = bstats->packets;
+ }
+
idx = parm->interval + 2;
- est->bstats = bstats;
est->rate_est = rate_est;
est->stats_lock = stats_lock;
est->ewma_log = parm->ewma_log;
- est->last_bytes = bstats->bytes;
est->avbps = rate_est->bps<<5;
- est->last_packets = bstats->packets;
est->avpps = rate_est->pps<<10;
spin_lock_bh(&est_tree_lock);
@@ -258,16 +288,16 @@ EXPORT_SYMBOL(gen_new_estimator);
* Note : Caller should respect an RCU grace period before freeing stats_lock
*/
void gen_kill_estimator(struct gnet_stats_basic_packed *bstats,
+ struct gnet_stats_basic_cpu *cpu_bstats,
struct gnet_stats_rate_est64 *rate_est)
{
struct gen_estimator *e;
spin_lock_bh(&est_tree_lock);
- while ((e = gen_find_node(bstats, rate_est))) {
+ while ((e = gen_find_node(bstats, cpu_bstats, rate_est))) {
rb_erase(&e->node, &est_root);
-
write_lock(&est_lock);
- e->bstats = NULL;
+ e->bstats = NULL; /* since we dropped est_lock elsewhere this needs to move behind grace period? */
write_unlock(&est_lock);
list_del_rcu(&e->list);
@@ -290,11 +320,12 @@ EXPORT_SYMBOL(gen_kill_estimator);
* Returns 0 on success or a negative error code.
*/
int gen_replace_estimator(struct gnet_stats_basic_packed *bstats,
+ struct gnet_stats_basic_cpu *cpu_bstats,
struct gnet_stats_rate_est64 *rate_est,
spinlock_t *stats_lock, struct nlattr *opt)
{
- gen_kill_estimator(bstats, rate_est);
- return gen_new_estimator(bstats, rate_est, stats_lock, opt);
+ gen_kill_estimator(bstats, cpu_bstats, rate_est);
+ return gen_new_estimator(bstats, cpu_bstats, rate_est, stats_lock, opt);
}
EXPORT_SYMBOL(gen_replace_estimator);
@@ -306,6 +337,7 @@ EXPORT_SYMBOL(gen_replace_estimator);
* Returns true if estimator is active, and false if not.
*/
bool gen_estimator_active(const struct gnet_stats_basic_packed *bstats,
+ const struct gnet_stats_basic_cpu *cpu_bstats,
const struct gnet_stats_rate_est64 *rate_est)
{
bool res;
@@ -313,7 +345,7 @@ bool gen_estimator_active(const struct gnet_stats_basic_packed *bstats,
ASSERT_RTNL();
spin_lock_bh(&est_tree_lock);
- res = gen_find_node(bstats, rate_est) != NULL;
+ res = gen_find_node(bstats, cpu_bstats, rate_est) != NULL;
spin_unlock_bh(&est_tree_lock);
return res;
diff --git a/net/core/gen_stats.c b/net/core/gen_stats.c
index 9d3d9e7..29881da 100644
--- a/net/core/gen_stats.c
+++ b/net/core/gen_stats.c
@@ -128,6 +128,44 @@ gnet_stats_copy_basic(struct gnet_dump *d, struct gnet_stats_basic_packed *b)
}
EXPORT_SYMBOL(gnet_stats_copy_basic);
+void
+__gnet_stats_copy_basic(struct gnet_stats_basic_packed *bstats,
+ struct gnet_stats_basic_packed *b)
+{
+ bstats->bytes = b->bytes;
+ bstats->packets = b->packets;
+}
+EXPORT_SYMBOL(__gnet_stats_copy_basic);
+
+void
+__gnet_stats_copy_basic_cpu(struct gnet_stats_basic_packed *bstats,
+ struct gnet_stats_basic_cpu *b)
+{
+ int i;
+
+ for_each_possible_cpu(i) {
+ struct gnet_stats_basic_cpu *bcpu = per_cpu_ptr(b, i);
+ unsigned int start;
+
+ do {
+ start = u64_stats_fetch_begin_bh(&bcpu->syncp);
+ bstats->bytes += bcpu->bstats.bytes;
+ bstats->packets += bcpu->bstats.packets;
+ } while (u64_stats_fetch_retry_bh(&bcpu->syncp, start));
+ }
+}
+EXPORT_SYMBOL(__gnet_stats_copy_basic_cpu);
+
+int
+gnet_stats_copy_basic_cpu(struct gnet_dump *d, struct gnet_stats_basic_cpu *b)
+{
+ struct gnet_stats_basic_packed bstats = {0};
+
+ __gnet_stats_copy_basic_cpu(&bstats, b);
+ return gnet_stats_copy_basic(d, &bstats);
+}
+EXPORT_SYMBOL(gnet_stats_copy_basic_cpu);
+
/**
* gnet_stats_copy_rate_est - copy rate estimator statistics into statistics TLV
* @d: dumping handle
@@ -143,12 +181,13 @@ EXPORT_SYMBOL(gnet_stats_copy_basic);
int
gnet_stats_copy_rate_est(struct gnet_dump *d,
const struct gnet_stats_basic_packed *b,
+ const struct gnet_stats_basic_cpu *cpu_b,
struct gnet_stats_rate_est64 *r)
{
struct gnet_stats_rate_est est;
int res;
- if (b && !gen_estimator_active(b, r))
+ if ((b || cpu_b) && !gen_estimator_active(b, cpu_b, r))
return 0;
est.bps = min_t(u64, UINT_MAX, r->bps);
diff --git a/net/netfilter/xt_RATEEST.c b/net/netfilter/xt_RATEEST.c
index 370adf6..02e2532 100644
--- a/net/netfilter/xt_RATEEST.c
+++ b/net/netfilter/xt_RATEEST.c
@@ -64,7 +64,7 @@ void xt_rateest_put(struct xt_rateest *est)
mutex_lock(&xt_rateest_mutex);
if (--est->refcnt == 0) {
hlist_del(&est->list);
- gen_kill_estimator(&est->bstats, &est->rstats);
+ gen_kill_estimator(&est->bstats, NULL, &est->rstats);
/*
* gen_estimator est_timer() might access est->lock or bstats,
* wait a RCU grace period before freeing 'est'
@@ -136,7 +136,7 @@ static int xt_rateest_tg_checkentry(const struct xt_tgchk_param *par)
cfg.est.interval = info->interval;
cfg.est.ewma_log = info->ewma_log;
- ret = gen_new_estimator(&est->bstats, &est->rstats,
+ ret = gen_new_estimator(&est->bstats, NULL, &est->rstats,
&est->lock, &cfg.opt);
if (ret < 0)
goto err2;
diff --git a/net/sched/act_api.c b/net/sched/act_api.c
index d73a546..1e297bc 100644
--- a/net/sched/act_api.c
+++ b/net/sched/act_api.c
@@ -35,7 +35,7 @@ void tcf_hash_destroy(struct tc_action *a)
spin_lock_bh(&hinfo->lock);
hlist_del(&p->tcfc_head);
spin_unlock_bh(&hinfo->lock);
- gen_kill_estimator(&p->tcfc_bstats,
+ gen_kill_estimator(&p->tcfc_bstats, NULL,
&p->tcfc_rate_est);
/*
* gen_estimator est_timer() might access p->tcfc_lock
@@ -228,7 +228,7 @@ void tcf_hash_cleanup(struct tc_action *a, struct nlattr *est)
{
struct tcf_common *pc = a->priv;
if (est)
- gen_kill_estimator(&pc->tcfc_bstats,
+ gen_kill_estimator(&pc->tcfc_bstats, NULL,
&pc->tcfc_rate_est);
kfree_rcu(pc, tcfc_rcu);
}
@@ -252,7 +252,7 @@ int tcf_hash_create(u32 index, struct nlattr *est, struct tc_action *a,
p->tcfc_tm.install = jiffies;
p->tcfc_tm.lastuse = jiffies;
if (est) {
- int err = gen_new_estimator(&p->tcfc_bstats, &p->tcfc_rate_est,
+ int err = gen_new_estimator(&p->tcfc_bstats, NULL, &p->tcfc_rate_est,
&p->tcfc_lock, est);
if (err) {
kfree(p);
@@ -620,7 +620,7 @@ int tcf_action_copy_stats(struct sk_buff *skb, struct tc_action *a,
goto errout;
if (gnet_stats_copy_basic(&d, &p->tcfc_bstats) < 0 ||
- gnet_stats_copy_rate_est(&d, &p->tcfc_bstats,
+ gnet_stats_copy_rate_est(&d, &p->tcfc_bstats, NULL,
&p->tcfc_rate_est) < 0 ||
gnet_stats_copy_queue(&d, &p->tcfc_qstats) < 0)
goto errout;
diff --git a/net/sched/act_police.c b/net/sched/act_police.c
index 0566e46..18e6c83 100644
--- a/net/sched/act_police.c
+++ b/net/sched/act_police.c
@@ -178,14 +178,14 @@ override:
spin_lock_bh(&police->tcf_lock);
if (est) {
- err = gen_replace_estimator(&police->tcf_bstats,
+ err = gen_replace_estimator(&police->tcf_bstats, NULL,
&police->tcf_rate_est,
&police->tcf_lock, est);
if (err)
goto failure_unlock;
} else if (tb[TCA_POLICE_AVRATE] &&
(ret == ACT_P_CREATED ||
- !gen_estimator_active(&police->tcf_bstats,
+ !gen_estimator_active(&police->tcf_bstats, NULL,
&police->tcf_rate_est))) {
err = -EINVAL;
goto failure_unlock;
diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c
index 774f61c..8419d01 100644
--- a/net/sched/sch_api.c
+++ b/net/sched/sch_api.c
@@ -941,6 +941,13 @@ qdisc_create(struct net_device *dev, struct netdev_queue *dev_queue,
sch->handle = handle;
if (!ops->init || (err = ops->init(sch, tca[TCA_OPTIONS])) == 0) {
+ if (qdisc_is_lockless(sch)) {
+ sch->bstats_qdisc.cpu_bstats =
+ alloc_percpu(struct gnet_stats_basic_cpu);
+ if (!sch->bstats_qdisc.cpu_bstats)
+ goto err_out4;
+ }
+
if (tca[TCA_STAB]) {
stab = qdisc_get_stab(tca[TCA_STAB]);
if (IS_ERR(stab)) {
@@ -963,8 +970,18 @@ qdisc_create(struct net_device *dev, struct netdev_queue *dev_queue,
else
root_lock = qdisc_lock(sch);
- err = gen_new_estimator(&sch->bstats, &sch->rate_est,
- root_lock, tca[TCA_RATE]);
+ if (qdisc_is_lockless(sch))
+ err = gen_new_estimator(NULL,
+ sch->bstats_qdisc.cpu_bstats,
+ &sch->rate_est,
+ root_lock,
+ tca[TCA_RATE]);
+ else
+ err = gen_new_estimator(&sch->bstats_qdisc.bstats,
+ NULL,
+ &sch->rate_est,
+ root_lock,
+ tca[TCA_RATE]);
if (err)
goto err_out4;
}
@@ -1021,9 +1038,11 @@ static int qdisc_change(struct Qdisc *sch, struct nlattr **tca)
because change can't be undone. */
if (sch->flags & TCQ_F_MQROOT)
goto out;
- gen_replace_estimator(&sch->bstats, &sch->rate_est,
- qdisc_root_sleeping_lock(sch),
- tca[TCA_RATE]);
+ gen_replace_estimator(&sch->bstats_qdisc.bstats,
+ sch->bstats_qdisc.cpu_bstats,
+ &sch->rate_est,
+ qdisc_root_sleeping_lock(sch),
+ tca[TCA_RATE]);
}
out:
return 0;
@@ -1302,6 +1321,7 @@ static int tc_fill_qdisc(struct sk_buff *skb, struct Qdisc *q, u32 clid,
unsigned char *b = skb_tail_pointer(skb);
struct gnet_dump d;
struct qdisc_size_table *stab;
+ int err;
nlh = nlmsg_put(skb, portid, seq, event, sizeof(*tcm), flags);
if (!nlh)
@@ -1331,10 +1351,25 @@ static int tc_fill_qdisc(struct sk_buff *skb, struct Qdisc *q, u32 clid,
if (q->ops->dump_stats && q->ops->dump_stats(q, &d) < 0)
goto nla_put_failure;
- if (gnet_stats_copy_basic(&d, &q->bstats) < 0 ||
- gnet_stats_copy_rate_est(&d, &q->bstats, &q->rate_est) < 0 ||
+ if (qdisc_is_lockless(q)) {
+ err = gnet_stats_copy_basic_cpu(&d, q->bstats_qdisc.cpu_bstats);
+ if (err < 0)
+ goto nla_put_failure;
+ err = gnet_stats_copy_rate_est(&d, NULL,
+ q->bstats_qdisc.cpu_bstats,
+ &q->rate_est);
+ } else {
+ err = gnet_stats_copy_basic(&d, &q->bstats_qdisc.bstats);
+ if (err < 0)
+ goto nla_put_failure;
+ err = gnet_stats_copy_rate_est(&d,
+ &q->bstats_qdisc.bstats, NULL,
+ &q->rate_est);
+ }
+
+ if (err < 0 ||
gnet_stats_copy_queue(&d, &q->qstats) < 0)
- goto nla_put_failure;
+ goto nla_put_failure;
if (gnet_stats_finish_copy(&d) < 0)
goto nla_put_failure;
diff --git a/net/sched/sch_cbq.c b/net/sched/sch_cbq.c
index 61a51d0..4777431 100644
--- a/net/sched/sch_cbq.c
+++ b/net/sched/sch_cbq.c
@@ -1625,7 +1625,7 @@ cbq_dump_class_stats(struct Qdisc *sch, unsigned long arg,
cl->xstats.undertime = cl->undertime - q->now;
if (gnet_stats_copy_basic(d, &cl->bstats) < 0 ||
- gnet_stats_copy_rate_est(d, &cl->bstats, &cl->rate_est) < 0 ||
+ gnet_stats_copy_rate_est(d, &cl->bstats, NULL, &cl->rate_est) < 0 ||
gnet_stats_copy_queue(d, &cl->qstats) < 0)
return -1;
@@ -1697,7 +1697,7 @@ static void cbq_destroy_class(struct Qdisc *sch, struct cbq_class *cl)
qdisc_destroy(cl->q);
qdisc_put_rtab(cl->R_tab);
- gen_kill_estimator(&cl->bstats, &cl->rate_est);
+ gen_kill_estimator(&cl->bstats, NULL, &cl->rate_est);
if (cl != &q->link)
kfree(cl);
}
@@ -1788,7 +1788,7 @@ cbq_change_class(struct Qdisc *sch, u32 classid, u32 parentid, struct nlattr **t
}
if (tca[TCA_RATE]) {
- err = gen_replace_estimator(&cl->bstats, &cl->rate_est,
+ err = gen_replace_estimator(&cl->bstats, NULL, &cl->rate_est,
qdisc_root_sleeping_lock(sch),
tca[TCA_RATE]);
if (err) {
@@ -1881,7 +1881,7 @@ cbq_change_class(struct Qdisc *sch, u32 classid, u32 parentid, struct nlattr **t
goto failure;
if (tca[TCA_RATE]) {
- err = gen_new_estimator(&cl->bstats, &cl->rate_est,
+ err = gen_new_estimator(&cl->bstats, NULL, &cl->rate_est,
qdisc_root_sleeping_lock(sch),
tca[TCA_RATE]);
if (err) {
diff --git a/net/sched/sch_drr.c b/net/sched/sch_drr.c
index 899026f..894d9c4 100644
--- a/net/sched/sch_drr.c
+++ b/net/sched/sch_drr.c
@@ -88,7 +88,7 @@ static int drr_change_class(struct Qdisc *sch, u32 classid, u32 parentid,
if (cl != NULL) {
if (tca[TCA_RATE]) {
- err = gen_replace_estimator(&cl->bstats, &cl->rate_est,
+ err = gen_replace_estimator(&cl->bstats, NULL, &cl->rate_est,
qdisc_root_sleeping_lock(sch),
tca[TCA_RATE]);
if (err)
@@ -116,7 +116,7 @@ static int drr_change_class(struct Qdisc *sch, u32 classid, u32 parentid,
cl->qdisc = &noop_qdisc;
if (tca[TCA_RATE]) {
- err = gen_replace_estimator(&cl->bstats, &cl->rate_est,
+ err = gen_replace_estimator(&cl->bstats, NULL, &cl->rate_est,
qdisc_root_sleeping_lock(sch),
tca[TCA_RATE]);
if (err) {
@@ -138,7 +138,7 @@ static int drr_change_class(struct Qdisc *sch, u32 classid, u32 parentid,
static void drr_destroy_class(struct Qdisc *sch, struct drr_class *cl)
{
- gen_kill_estimator(&cl->bstats, &cl->rate_est);
+ gen_kill_estimator(&cl->bstats, NULL, &cl->rate_est);
qdisc_destroy(cl->qdisc);
kfree(cl);
}
@@ -282,7 +282,7 @@ static int drr_dump_class_stats(struct Qdisc *sch, unsigned long arg,
}
if (gnet_stats_copy_basic(d, &cl->bstats) < 0 ||
- gnet_stats_copy_rate_est(d, &cl->bstats, &cl->rate_est) < 0 ||
+ gnet_stats_copy_rate_est(d, &cl->bstats, NULL, &cl->rate_est) < 0 ||
gnet_stats_copy_queue(d, &cl->qdisc->qstats) < 0)
return -1;
diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c
index 9327edb..8542610 100644
--- a/net/sched/sch_generic.c
+++ b/net/sched/sch_generic.c
@@ -625,6 +625,9 @@ static void qdisc_rcu_free(struct rcu_head *head)
{
struct Qdisc *qdisc = container_of(head, struct Qdisc, rcu_head);
+ if (qdisc_is_lockless(qdisc))
+ free_percpu(qdisc->bstats_qdisc.cpu_bstats);
+
kfree((char *) qdisc - qdisc->padded);
}
@@ -641,7 +644,13 @@ void qdisc_destroy(struct Qdisc *qdisc)
qdisc_put_stab(rtnl_dereference(qdisc->stab));
#endif
- gen_kill_estimator(&qdisc->bstats, &qdisc->rate_est);
+ if (qdisc_is_lockless(qdisc))
+ gen_kill_estimator(NULL, qdisc->bstats_qdisc.cpu_bstats,
+ &qdisc->rate_est);
+ else
+ gen_kill_estimator(&qdisc->bstats_qdisc.bstats, NULL,
+ &qdisc->rate_est);
+
if (ops->reset)
ops->reset(qdisc);
if (ops->destroy)
@@ -651,6 +660,7 @@ void qdisc_destroy(struct Qdisc *qdisc)
dev_put(qdisc_dev(qdisc));
kfree_skb(qdisc->gso_skb);
+
/*
* gen_estimator est_timer() might access qdisc->q.lock,
* wait a RCU grace period before freeing qdisc.
diff --git a/net/sched/sch_hfsc.c b/net/sched/sch_hfsc.c
index 0a7650f..bc972f0 100644
--- a/net/sched/sch_hfsc.c
+++ b/net/sched/sch_hfsc.c
@@ -1014,9 +1014,10 @@ hfsc_change_class(struct Qdisc *sch, u32 classid, u32 parentid,
cur_time = psched_get_time();
if (tca[TCA_RATE]) {
- err = gen_replace_estimator(&cl->bstats, &cl->rate_est,
- qdisc_root_sleeping_lock(sch),
- tca[TCA_RATE]);
+ err = gen_replace_estimator(&cl->bstats, NULL,
+ &cl->rate_est,
+ qdisc_root_sleeping_lock(sch),
+ tca[TCA_RATE]);
if (err)
return err;
}
@@ -1063,7 +1064,7 @@ hfsc_change_class(struct Qdisc *sch, u32 classid, u32 parentid,
return -ENOBUFS;
if (tca[TCA_RATE]) {
- err = gen_new_estimator(&cl->bstats, &cl->rate_est,
+ err = gen_new_estimator(&cl->bstats, NULL, &cl->rate_est,
qdisc_root_sleeping_lock(sch),
tca[TCA_RATE]);
if (err) {
@@ -1115,7 +1116,7 @@ hfsc_destroy_class(struct Qdisc *sch, struct hfsc_class *cl)
fl = rtnl_dereference(cl->filter_list);
tcf_destroy_chain(&fl);
qdisc_destroy(cl->qdisc);
- gen_kill_estimator(&cl->bstats, &cl->rate_est);
+ gen_kill_estimator(&cl->bstats, NULL, &cl->rate_est);
if (cl != &q->root)
kfree(cl);
}
@@ -1378,7 +1379,7 @@ hfsc_dump_class_stats(struct Qdisc *sch, unsigned long arg,
xstats.rtwork = cl->cl_cumul;
if (gnet_stats_copy_basic(d, &cl->bstats) < 0 ||
- gnet_stats_copy_rate_est(d, &cl->bstats, &cl->rate_est) < 0 ||
+ gnet_stats_copy_rate_est(d, &cl->bstats, NULL, &cl->rate_est) < 0 ||
gnet_stats_copy_queue(d, &cl->qstats) < 0)
return -1;
diff --git a/net/sched/sch_htb.c b/net/sched/sch_htb.c
index 2c2a6aa..4af81f2 100644
--- a/net/sched/sch_htb.c
+++ b/net/sched/sch_htb.c
@@ -1145,7 +1145,7 @@ htb_dump_class_stats(struct Qdisc *sch, unsigned long arg, struct gnet_dump *d)
cl->xstats.ctokens = PSCHED_NS2TICKS(cl->ctokens);
if (gnet_stats_copy_basic(d, &cl->bstats) < 0 ||
- gnet_stats_copy_rate_est(d, NULL, &cl->rate_est) < 0 ||
+ gnet_stats_copy_rate_est(d, NULL, NULL, &cl->rate_est) < 0 ||
gnet_stats_copy_queue(d, &cl->qstats) < 0)
return -1;
@@ -1237,7 +1237,7 @@ static void htb_destroy_class(struct Qdisc *sch, struct htb_class *cl)
WARN_ON(!cl->un.leaf.q);
qdisc_destroy(cl->un.leaf.q);
}
- gen_kill_estimator(&cl->bstats, &cl->rate_est);
+ gen_kill_estimator(&cl->bstats, NULL, &cl->rate_est);
fl = rtnl_dereference(cl->filter_list);
tcf_destroy_chain(&fl);
kfree(cl);
@@ -1409,7 +1409,7 @@ static int htb_change_class(struct Qdisc *sch, u32 classid,
goto failure;
if (htb_rate_est || tca[TCA_RATE]) {
- err = gen_new_estimator(&cl->bstats, &cl->rate_est,
+ err = gen_new_estimator(&cl->bstats, NULL, &cl->rate_est,
qdisc_root_sleeping_lock(sch),
tca[TCA_RATE] ? : &est.nla);
if (err) {
@@ -1471,7 +1471,7 @@ static int htb_change_class(struct Qdisc *sch, u32 classid,
parent->children++;
} else {
if (tca[TCA_RATE]) {
- err = gen_replace_estimator(&cl->bstats, &cl->rate_est,
+ err = gen_replace_estimator(&cl->bstats, NULL, &cl->rate_est,
qdisc_root_sleeping_lock(sch),
tca[TCA_RATE]);
if (err)
diff --git a/net/sched/sch_ingress.c b/net/sched/sch_ingress.c
index f7c80d3..86cc5ce 100644
--- a/net/sched/sch_ingress.c
+++ b/net/sched/sch_ingress.c
@@ -64,7 +64,7 @@ static int ingress_enqueue(struct sk_buff *skb, struct Qdisc *sch)
result = tc_classify(skb, fl, &res);
- qdisc_bstats_update(sch, skb);
+ qdisc_bstats_update_cpu(sch, skb);
switch (result) {
case TC_ACT_SHOT:
result = TC_ACT_SHOT;
diff --git a/net/sched/sch_mq.c b/net/sched/sch_mq.c
index a8b2864..ca7109c 100644
--- a/net/sched/sch_mq.c
+++ b/net/sched/sch_mq.c
@@ -103,15 +103,15 @@ static int mq_dump(struct Qdisc *sch, struct sk_buff *skb)
unsigned int ntx;
sch->q.qlen = 0;
- memset(&sch->bstats, 0, sizeof(sch->bstats));
+ memset(&sch->bstats_qdisc.bstats, 0, sizeof(sch->bstats_qdisc));
memset(&sch->qstats, 0, sizeof(sch->qstats));
for (ntx = 0; ntx < dev->num_tx_queues; ntx++) {
qdisc = netdev_get_tx_queue(dev, ntx)->qdisc_sleeping;
spin_lock_bh(qdisc_lock(qdisc));
sch->q.qlen += qdisc->q.qlen;
- sch->bstats.bytes += qdisc->bstats.bytes;
- sch->bstats.packets += qdisc->bstats.packets;
+ sch->bstats_qdisc.bstats.bytes += qdisc->bstats_qdisc.bstats.bytes;
+ sch->bstats_qdisc.bstats.packets += qdisc->bstats_qdisc.bstats.packets;
sch->qstats.qlen += qdisc->qstats.qlen;
sch->qstats.backlog += qdisc->qstats.backlog;
sch->qstats.drops += qdisc->qstats.drops;
@@ -201,7 +201,7 @@ static int mq_dump_class_stats(struct Qdisc *sch, unsigned long cl,
sch = dev_queue->qdisc_sleeping;
sch->qstats.qlen = sch->q.qlen;
- if (gnet_stats_copy_basic(d, &sch->bstats) < 0 ||
+ if (gnet_stats_copy_basic(d, &sch->bstats_qdisc.bstats) < 0 ||
gnet_stats_copy_queue(d, &sch->qstats) < 0)
return -1;
return 0;
diff --git a/net/sched/sch_mqprio.c b/net/sched/sch_mqprio.c
index e1b112f..89337c8 100644
--- a/net/sched/sch_mqprio.c
+++ b/net/sched/sch_mqprio.c
@@ -227,15 +227,15 @@ static int mqprio_dump(struct Qdisc *sch, struct sk_buff *skb)
unsigned int i;
sch->q.qlen = 0;
- memset(&sch->bstats, 0, sizeof(sch->bstats));
+ memset(&sch->bstats_qdisc.bstats, 0, sizeof(sch->bstats_qdisc.bstats));
memset(&sch->qstats, 0, sizeof(sch->qstats));
for (i = 0; i < dev->num_tx_queues; i++) {
qdisc = rtnl_dereference(netdev_get_tx_queue(dev, i)->qdisc);
spin_lock_bh(qdisc_lock(qdisc));
sch->q.qlen += qdisc->q.qlen;
- sch->bstats.bytes += qdisc->bstats.bytes;
- sch->bstats.packets += qdisc->bstats.packets;
+ sch->bstats_qdisc.bstats.bytes += qdisc->bstats_qdisc.bstats.bytes;
+ sch->bstats_qdisc.bstats.packets += qdisc->bstats_qdisc.bstats.packets;
sch->qstats.qlen += qdisc->qstats.qlen;
sch->qstats.backlog += qdisc->qstats.backlog;
sch->qstats.drops += qdisc->qstats.drops;
@@ -342,8 +342,8 @@ static int mqprio_dump_class_stats(struct Qdisc *sch, unsigned long cl,
for (i = tc.offset; i < tc.offset + tc.count; i++) {
qdisc = rtnl_dereference(netdev_get_tx_queue(dev, i)->qdisc);
spin_lock_bh(qdisc_lock(qdisc));
- bstats.bytes += qdisc->bstats.bytes;
- bstats.packets += qdisc->bstats.packets;
+ bstats.bytes += qdisc->bstats_qdisc.bstats.bytes;
+ bstats.packets += qdisc->bstats_qdisc.bstats.packets;
qstats.qlen += qdisc->qstats.qlen;
qstats.backlog += qdisc->qstats.backlog;
qstats.drops += qdisc->qstats.drops;
@@ -361,7 +361,7 @@ static int mqprio_dump_class_stats(struct Qdisc *sch, unsigned long cl,
sch = dev_queue->qdisc_sleeping;
sch->qstats.qlen = sch->q.qlen;
- if (gnet_stats_copy_basic(d, &sch->bstats) < 0 ||
+ if (gnet_stats_copy_basic(d, &sch->bstats_qdisc.bstats) < 0 ||
gnet_stats_copy_queue(d, &sch->qstats) < 0)
return -1;
}
diff --git a/net/sched/sch_multiq.c b/net/sched/sch_multiq.c
index 169d637..73e8b2b 100644
--- a/net/sched/sch_multiq.c
+++ b/net/sched/sch_multiq.c
@@ -362,7 +362,7 @@ static int multiq_dump_class_stats(struct Qdisc *sch, unsigned long cl,
cl_q = q->queues[cl - 1];
cl_q->qstats.qlen = cl_q->q.qlen;
- if (gnet_stats_copy_basic(d, &cl_q->bstats) < 0 ||
+ if (gnet_stats_copy_basic(d, &cl_q->bstats_qdisc.bstats) < 0 ||
gnet_stats_copy_queue(d, &cl_q->qstats) < 0)
return -1;
diff --git a/net/sched/sch_prio.c b/net/sched/sch_prio.c
index 43aa35d..1ae5d5b 100644
--- a/net/sched/sch_prio.c
+++ b/net/sched/sch_prio.c
@@ -326,7 +326,7 @@ static int prio_dump_class_stats(struct Qdisc *sch, unsigned long cl,
cl_q = q->queues[cl - 1];
cl_q->qstats.qlen = cl_q->q.qlen;
- if (gnet_stats_copy_basic(d, &cl_q->bstats) < 0 ||
+ if (gnet_stats_copy_basic(d, &cl_q->bstats_qdisc.bstats) < 0 ||
gnet_stats_copy_queue(d, &cl_q->qstats) < 0)
return -1;
diff --git a/net/sched/sch_qfq.c b/net/sched/sch_qfq.c
index cee5618..1cc4978 100644
--- a/net/sched/sch_qfq.c
+++ b/net/sched/sch_qfq.c
@@ -459,7 +459,8 @@ static int qfq_change_class(struct Qdisc *sch, u32 classid, u32 parentid,
if (cl != NULL) { /* modify existing class */
if (tca[TCA_RATE]) {
- err = gen_replace_estimator(&cl->bstats, &cl->rate_est,
+ err = gen_replace_estimator(&cl->bstats, NULL,
+ &cl->rate_est,
qdisc_root_sleeping_lock(sch),
tca[TCA_RATE]);
if (err)
@@ -484,7 +485,8 @@ static int qfq_change_class(struct Qdisc *sch, u32 classid, u32 parentid,
cl->qdisc = &noop_qdisc;
if (tca[TCA_RATE]) {
- err = gen_new_estimator(&cl->bstats, &cl->rate_est,
+ err = gen_new_estimator(&cl->bstats, NULL,
+ &cl->rate_est,
qdisc_root_sleeping_lock(sch),
tca[TCA_RATE]);
if (err)
@@ -505,7 +507,7 @@ set_change_agg:
new_agg = kzalloc(sizeof(*new_agg), GFP_KERNEL);
if (new_agg == NULL) {
err = -ENOBUFS;
- gen_kill_estimator(&cl->bstats, &cl->rate_est);
+ gen_kill_estimator(&cl->bstats, NULL, &cl->rate_est);
goto destroy_class;
}
sch_tree_lock(sch);
@@ -530,7 +532,7 @@ static void qfq_destroy_class(struct Qdisc *sch, struct qfq_class *cl)
struct qfq_sched *q = qdisc_priv(sch);
qfq_rm_from_agg(q, cl);
- gen_kill_estimator(&cl->bstats, &cl->rate_est);
+ gen_kill_estimator(&cl->bstats, NULL, &cl->rate_est);
qdisc_destroy(cl->qdisc);
kfree(cl);
}
@@ -667,7 +669,7 @@ static int qfq_dump_class_stats(struct Qdisc *sch, unsigned long arg,
xstats.lmax = cl->agg->lmax;
if (gnet_stats_copy_basic(d, &cl->bstats) < 0 ||
- gnet_stats_copy_rate_est(d, &cl->bstats, &cl->rate_est) < 0 ||
+ gnet_stats_copy_rate_est(d, &cl->bstats, NULL, &cl->rate_est) < 0 ||
gnet_stats_copy_queue(d, &cl->qdisc->qstats) < 0)
return -1;
--
To unsubscribe from this list: send the line "unsubscribe netdev" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Powered by blists - more mailing lists