From: John Fastabend <john.fastabend@gmail.com>
To: xiyou.wangcong@gmail.com, davem@davemloft.net,
eric.dumazet@gmail.com, jhs@mojatatu.com
Cc: netdev@vger.kernel.org, paulmck@linux.vnet.ibm.com, brouer@redhat.com
Subject: [net-next PATCH v3 02/15] net: rcu-ify tcf_proto
Date: Mon, 08 Sep 2014 22:54:38 -0700 [thread overview]
Message-ID: <20140909055437.2071.86430.stgit@nitbit.x32> (raw)
In-Reply-To: <20140909055221.2071.99671.stgit@nitbit.x32>
rcu'ify tcf_proto this allows calling tc_classify() without holding
any locks. Updaters are protected by RTNL.
This patch prepares the core net_sched infrastracture for running
the classifier/action chains without holding the qdisc lock however
it does nothing to ensure cls_xxx and act_xxx types also work without
locking. Additional patches are required to address the fall out.
Signed-off-by: John Fastabend <john.r.fastabend@intel.com>
---
include/net/sch_generic.h | 9 +++++----
net/sched/cls_api.c | 30 +++++++++++++++---------------
net/sched/sch_api.c | 10 +++++-----
net/sched/sch_atm.c | 22 +++++++++++++---------
net/sched/sch_cbq.c | 13 +++++++++----
net/sched/sch_choke.c | 17 ++++++++++++-----
net/sched/sch_drr.c | 9 ++++++---
net/sched/sch_dsmark.c | 9 +++++----
net/sched/sch_fq_codel.c | 11 +++++++----
net/sched/sch_hfsc.c | 8 ++++----
net/sched/sch_htb.c | 15 ++++++++-------
net/sched/sch_ingress.c | 8 +++++---
net/sched/sch_multiq.c | 8 +++++---
net/sched/sch_prio.c | 11 +++++++----
net/sched/sch_qfq.c | 9 ++++++---
net/sched/sch_sfb.c | 15 +++++++++------
net/sched/sch_sfq.c | 11 +++++++----
17 files changed, 128 insertions(+), 87 deletions(-)
diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h
index 19b1b36..be000bb 100644
--- a/include/net/sch_generic.h
+++ b/include/net/sch_generic.h
@@ -143,7 +143,7 @@ struct Qdisc_class_ops {
void (*walk)(struct Qdisc *, struct qdisc_walker * arg);
/* Filter manipulation */
- struct tcf_proto ** (*tcf_chain)(struct Qdisc *, unsigned long);
+ struct tcf_proto __rcu ** (*tcf_chain)(struct Qdisc *, unsigned long);
unsigned long (*bind_tcf)(struct Qdisc *, unsigned long,
u32 classid);
void (*unbind_tcf)(struct Qdisc *, unsigned long);
@@ -212,8 +212,8 @@ struct tcf_proto_ops {
struct tcf_proto {
/* Fast access part */
- struct tcf_proto *next;
- void *root;
+ struct tcf_proto __rcu *next;
+ void __rcu *root;
int (*classify)(struct sk_buff *,
const struct tcf_proto *,
struct tcf_result *);
@@ -225,6 +225,7 @@ struct tcf_proto {
struct Qdisc *q;
void *data;
const struct tcf_proto_ops *ops;
+ struct rcu_head rcu;
};
struct qdisc_skb_cb {
@@ -378,7 +379,7 @@ struct Qdisc *qdisc_create_dflt(struct netdev_queue *dev_queue,
void __qdisc_calculate_pkt_len(struct sk_buff *skb,
const struct qdisc_size_table *stab);
void tcf_destroy(struct tcf_proto *tp);
-void tcf_destroy_chain(struct tcf_proto **fl);
+void tcf_destroy_chain(struct tcf_proto __rcu **fl);
/* Reset all TX qdiscs greater then index of a device. */
static inline void qdisc_reset_all_tx_gt(struct net_device *dev, unsigned int i)
diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c
index c28b0d3..e3d3c48 100644
--- a/net/sched/cls_api.c
+++ b/net/sched/cls_api.c
@@ -117,7 +117,6 @@ static int tc_ctl_tfilter(struct sk_buff *skb, struct nlmsghdr *n)
{
struct net *net = sock_net(skb->sk);
struct nlattr *tca[TCA_MAX + 1];
- spinlock_t *root_lock;
struct tcmsg *t;
u32 protocol;
u32 prio;
@@ -125,7 +124,8 @@ static int tc_ctl_tfilter(struct sk_buff *skb, struct nlmsghdr *n)
u32 parent;
struct net_device *dev;
struct Qdisc *q;
- struct tcf_proto **back, **chain;
+ struct tcf_proto __rcu **back;
+ struct tcf_proto __rcu **chain;
struct tcf_proto *tp;
const struct tcf_proto_ops *tp_ops;
const struct Qdisc_class_ops *cops;
@@ -197,7 +197,9 @@ replay:
goto errout;
/* Check the chain for existence of proto-tcf with this priority */
- for (back = chain; (tp = *back) != NULL; back = &tp->next) {
+ for (back = chain;
+ (tp = rtnl_dereference(*back)) != NULL;
+ back = &tp->next) {
if (tp->prio >= prio) {
if (tp->prio == prio) {
if (!nprio ||
@@ -209,8 +211,6 @@ replay:
}
}
- root_lock = qdisc_root_sleeping_lock(q);
-
if (tp == NULL) {
/* Proto-tcf does not exist, create new one */
@@ -259,7 +259,8 @@ replay:
}
tp->ops = tp_ops;
tp->protocol = protocol;
- tp->prio = nprio ? : TC_H_MAJ(tcf_auto_prio(*back));
+ tp->prio = nprio ? :
+ TC_H_MAJ(tcf_auto_prio(rtnl_dereference(*back)));
tp->q = q;
tp->classify = tp_ops->classify;
tp->classid = parent;
@@ -280,9 +281,9 @@ replay:
if (fh == 0) {
if (n->nlmsg_type == RTM_DELTFILTER && t->tcm_handle == 0) {
- spin_lock_bh(root_lock);
- *back = tp->next;
- spin_unlock_bh(root_lock);
+ struct tcf_proto *next = rtnl_dereference(tp->next);
+
+ rcu_assign_pointer(*back, next);
tfilter_notify(net, skb, n, tp, fh, RTM_DELTFILTER);
tcf_destroy(tp);
@@ -322,10 +323,8 @@ replay:
n->nlmsg_flags & NLM_F_CREATE ? TCA_ACT_NOREPLACE : TCA_ACT_REPLACE);
if (err == 0) {
if (tp_created) {
- spin_lock_bh(root_lock);
- tp->next = *back;
- *back = tp;
- spin_unlock_bh(root_lock);
+ rcu_assign_pointer(tp->next, rtnl_dereference(*back));
+ rcu_assign_pointer(*back, tp);
}
tfilter_notify(net, skb, n, tp, fh, RTM_NEWTFILTER);
} else {
@@ -420,7 +419,7 @@ static int tc_dump_tfilter(struct sk_buff *skb, struct netlink_callback *cb)
int s_t;
struct net_device *dev;
struct Qdisc *q;
- struct tcf_proto *tp, **chain;
+ struct tcf_proto *tp, __rcu **chain;
struct tcmsg *tcm = nlmsg_data(cb->nlh);
unsigned long cl = 0;
const struct Qdisc_class_ops *cops;
@@ -454,7 +453,8 @@ static int tc_dump_tfilter(struct sk_buff *skb, struct netlink_callback *cb)
s_t = cb->args[0];
- for (tp = *chain, t = 0; tp; tp = tp->next, t++) {
+ for (tp = rtnl_dereference(*chain), t = 0;
+ tp; tp = rtnl_dereference(tp->next), t++) {
if (t < s_t)
continue;
if (TC_H_MAJ(tcm->tcm_info) &&
diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c
index 58bed75..7c57867 100644
--- a/net/sched/sch_api.c
+++ b/net/sched/sch_api.c
@@ -1781,7 +1781,7 @@ int tc_classify_compat(struct sk_buff *skb, const struct tcf_proto *tp,
__be16 protocol = skb->protocol;
int err;
- for (; tp; tp = tp->next) {
+ for (; tp; tp = rcu_dereference_bh(tp->next)) {
if (tp->protocol != protocol &&
tp->protocol != htons(ETH_P_ALL))
continue;
@@ -1833,15 +1833,15 @@ void tcf_destroy(struct tcf_proto *tp)
{
tp->ops->destroy(tp);
module_put(tp->ops->owner);
- kfree(tp);
+ kfree_rcu(tp, rcu);
}
-void tcf_destroy_chain(struct tcf_proto **fl)
+void tcf_destroy_chain(struct tcf_proto __rcu **fl)
{
struct tcf_proto *tp;
- while ((tp = *fl) != NULL) {
- *fl = tp->next;
+ while ((tp = rtnl_dereference(*fl)) != NULL) {
+ rcu_assign_pointer(*fl, tp->next);
tcf_destroy(tp);
}
}
diff --git a/net/sched/sch_atm.c b/net/sched/sch_atm.c
index 8449b33..9140bb0 100644
--- a/net/sched/sch_atm.c
+++ b/net/sched/sch_atm.c
@@ -41,7 +41,7 @@
struct atm_flow_data {
struct Qdisc *q; /* FIFO, TBF, etc. */
- struct tcf_proto *filter_list;
+ struct tcf_proto __rcu *filter_list;
struct atm_vcc *vcc; /* VCC; NULL if VCC is closed */
void (*old_pop)(struct atm_vcc *vcc,
struct sk_buff *skb); /* chaining */
@@ -142,7 +142,9 @@ static void atm_tc_put(struct Qdisc *sch, unsigned long cl)
list_del_init(&flow->list);
pr_debug("atm_tc_put: qdisc %p\n", flow->q);
qdisc_destroy(flow->q);
+
tcf_destroy_chain(&flow->filter_list);
+
if (flow->sock) {
pr_debug("atm_tc_put: f_count %ld\n",
file_count(flow->sock->file));
@@ -273,7 +275,7 @@ static int atm_tc_change(struct Qdisc *sch, u32 classid, u32 parent,
error = -ENOBUFS;
goto err_out;
}
- flow->filter_list = NULL;
+ RCU_INIT_POINTER(flow->filter_list, NULL);
flow->q = qdisc_create_dflt(sch->dev_queue, &pfifo_qdisc_ops, classid);
if (!flow->q)
flow->q = &noop_qdisc;
@@ -311,7 +313,7 @@ static int atm_tc_delete(struct Qdisc *sch, unsigned long arg)
pr_debug("atm_tc_delete(sch %p,[qdisc %p],flow %p)\n", sch, p, flow);
if (list_empty(&flow->list))
return -EINVAL;
- if (flow->filter_list || flow == &p->link)
+ if (rtnl_dereference(flow->filter_list) || flow == &p->link)
return -EBUSY;
/*
* Reference count must be 2: one for "keepalive" (set at class
@@ -345,7 +347,8 @@ static void atm_tc_walk(struct Qdisc *sch, struct qdisc_walker *walker)
}
}
-static struct tcf_proto **atm_tc_find_tcf(struct Qdisc *sch, unsigned long cl)
+static struct tcf_proto __rcu **atm_tc_find_tcf(struct Qdisc *sch,
+ unsigned long cl)
{
struct atm_qdisc_data *p = qdisc_priv(sch);
struct atm_flow_data *flow = (struct atm_flow_data *)cl;
@@ -369,11 +372,12 @@ static int atm_tc_enqueue(struct sk_buff *skb, struct Qdisc *sch)
flow = NULL;
if (TC_H_MAJ(skb->priority) != sch->handle ||
!(flow = (struct atm_flow_data *)atm_tc_get(sch, skb->priority))) {
+ struct tcf_proto *fl;
+
list_for_each_entry(flow, &p->flows, list) {
- if (flow->filter_list) {
- result = tc_classify_compat(skb,
- flow->filter_list,
- &res);
+ fl = rcu_dereference_bh(flow->filter_list);
+ if (fl) {
+ result = tc_classify_compat(skb, fl, &res);
if (result < 0)
continue;
flow = (struct atm_flow_data *)res.class;
@@ -544,7 +548,7 @@ static int atm_tc_init(struct Qdisc *sch, struct nlattr *opt)
if (!p->link.q)
p->link.q = &noop_qdisc;
pr_debug("atm_tc_init: link (%p) qdisc %p\n", &p->link, p->link.q);
- p->link.filter_list = NULL;
+ RCU_INIT_POINTER(p->link.filter_list, NULL);
p->link.vcc = NULL;
p->link.sock = NULL;
p->link.classid = sch->handle;
diff --git a/net/sched/sch_cbq.c b/net/sched/sch_cbq.c
index 762a04b..80231d9 100644
--- a/net/sched/sch_cbq.c
+++ b/net/sched/sch_cbq.c
@@ -133,7 +133,7 @@ struct cbq_class {
struct gnet_stats_rate_est64 rate_est;
struct tc_cbq_xstats xstats;
- struct tcf_proto *filter_list;
+ struct tcf_proto __rcu *filter_list;
int refcnt;
int filters;
@@ -221,6 +221,7 @@ cbq_classify(struct sk_buff *skb, struct Qdisc *sch, int *qerr)
struct cbq_class **defmap;
struct cbq_class *cl = NULL;
u32 prio = skb->priority;
+ struct tcf_proto *fl;
struct tcf_result res;
/*
@@ -233,13 +234,15 @@ cbq_classify(struct sk_buff *skb, struct Qdisc *sch, int *qerr)
*qerr = NET_XMIT_SUCCESS | __NET_XMIT_BYPASS;
for (;;) {
int result = 0;
+
defmap = head->defaults;
+ fl = rcu_dereference_bh(head->filter_list);
/*
* Step 2+n. Apply classifier.
*/
- if (!head->filter_list ||
- (result = tc_classify_compat(skb, head->filter_list, &res)) < 0)
+ result = tc_classify_compat(skb, fl, &res);
+ if (!fl || result < 0)
goto fallback;
cl = (void *)res.class;
@@ -1667,6 +1670,7 @@ static void cbq_destroy_class(struct Qdisc *sch, struct cbq_class *cl)
WARN_ON(cl->filters);
tcf_destroy_chain(&cl->filter_list);
+
qdisc_destroy(cl->q);
qdisc_put_rtab(cl->R_tab);
gen_kill_estimator(&cl->bstats, &cl->rate_est);
@@ -1954,7 +1958,8 @@ static int cbq_delete(struct Qdisc *sch, unsigned long arg)
return 0;
}
-static struct tcf_proto **cbq_find_tcf(struct Qdisc *sch, unsigned long arg)
+static struct tcf_proto __rcu **cbq_find_tcf(struct Qdisc *sch,
+ unsigned long arg)
{
struct cbq_sched_data *q = qdisc_priv(sch);
struct cbq_class *cl = (struct cbq_class *)arg;
diff --git a/net/sched/sch_choke.c b/net/sched/sch_choke.c
index ed30e43..4b52b70 100644
--- a/net/sched/sch_choke.c
+++ b/net/sched/sch_choke.c
@@ -57,7 +57,7 @@ struct choke_sched_data {
/* Variables */
struct red_vars vars;
- struct tcf_proto *filter_list;
+ struct tcf_proto __rcu *filter_list;
struct {
u32 prob_drop; /* Early probability drops */
u32 prob_mark; /* Early probability marks */
@@ -193,9 +193,11 @@ static bool choke_classify(struct sk_buff *skb,
{
struct choke_sched_data *q = qdisc_priv(sch);
struct tcf_result res;
+ struct tcf_proto *fl;
int result;
- result = tc_classify(skb, q->filter_list, &res);
+ fl = rcu_dereference_bh(q->filter_list);
+ result = tc_classify(skb, fl, &res);
if (result >= 0) {
#ifdef CONFIG_NET_CLS_ACT
switch (result) {
@@ -244,12 +246,14 @@ static bool choke_match_random(const struct choke_sched_data *q,
unsigned int *pidx)
{
struct sk_buff *oskb;
+ struct tcf_proto *fl;
if (q->head == q->tail)
return false;
oskb = choke_peek_random(q, pidx);
- if (q->filter_list)
+ fl = rcu_dereference_bh(q->filter_list);
+ if (fl)
return choke_get_classid(nskb) == choke_get_classid(oskb);
return choke_match_flow(oskb, nskb);
@@ -259,9 +263,11 @@ static int choke_enqueue(struct sk_buff *skb, struct Qdisc *sch)
{
struct choke_sched_data *q = qdisc_priv(sch);
const struct red_parms *p = &q->parms;
+ struct tcf_proto *fl;
int ret = NET_XMIT_SUCCESS | __NET_XMIT_BYPASS;
- if (q->filter_list) {
+ fl = rcu_dereference_bh(q->filter_list);
+ if (fl) {
/* If using external classifiers, get result and record it. */
if (!choke_classify(skb, sch, &ret))
goto other_drop; /* Packet was eaten by filter */
@@ -554,7 +560,8 @@ static unsigned long choke_bind(struct Qdisc *sch, unsigned long parent,
return 0;
}
-static struct tcf_proto **choke_find_tcf(struct Qdisc *sch, unsigned long cl)
+static struct tcf_proto __rcu **choke_find_tcf(struct Qdisc *sch,
+ unsigned long cl)
{
struct choke_sched_data *q = qdisc_priv(sch);
diff --git a/net/sched/sch_drr.c b/net/sched/sch_drr.c
index 7bbbfe1..d8b5ccf 100644
--- a/net/sched/sch_drr.c
+++ b/net/sched/sch_drr.c
@@ -35,7 +35,7 @@ struct drr_class {
struct drr_sched {
struct list_head active;
- struct tcf_proto *filter_list;
+ struct tcf_proto __rcu *filter_list;
struct Qdisc_class_hash clhash;
};
@@ -184,7 +184,8 @@ static void drr_put_class(struct Qdisc *sch, unsigned long arg)
drr_destroy_class(sch, cl);
}
-static struct tcf_proto **drr_tcf_chain(struct Qdisc *sch, unsigned long cl)
+static struct tcf_proto __rcu **drr_tcf_chain(struct Qdisc *sch,
+ unsigned long cl)
{
struct drr_sched *q = qdisc_priv(sch);
@@ -319,6 +320,7 @@ static struct drr_class *drr_classify(struct sk_buff *skb, struct Qdisc *sch,
struct drr_sched *q = qdisc_priv(sch);
struct drr_class *cl;
struct tcf_result res;
+ struct tcf_proto *fl;
int result;
if (TC_H_MAJ(skb->priority ^ sch->handle) == 0) {
@@ -328,7 +330,8 @@ static struct drr_class *drr_classify(struct sk_buff *skb, struct Qdisc *sch,
}
*qerr = NET_XMIT_SUCCESS | __NET_XMIT_BYPASS;
- result = tc_classify(skb, q->filter_list, &res);
+ fl = rcu_dereference_bh(q->filter_list);
+ result = tc_classify(skb, fl, &res);
if (result >= 0) {
#ifdef CONFIG_NET_CLS_ACT
switch (result) {
diff --git a/net/sched/sch_dsmark.c b/net/sched/sch_dsmark.c
index 49d6ef3..485e456 100644
--- a/net/sched/sch_dsmark.c
+++ b/net/sched/sch_dsmark.c
@@ -37,7 +37,7 @@
struct dsmark_qdisc_data {
struct Qdisc *q;
- struct tcf_proto *filter_list;
+ struct tcf_proto __rcu *filter_list;
u8 *mask; /* "owns" the array */
u8 *value;
u16 indices;
@@ -186,8 +186,8 @@ ignore:
}
}
-static inline struct tcf_proto **dsmark_find_tcf(struct Qdisc *sch,
- unsigned long cl)
+static inline struct tcf_proto __rcu **dsmark_find_tcf(struct Qdisc *sch,
+ unsigned long cl)
{
struct dsmark_qdisc_data *p = qdisc_priv(sch);
return &p->filter_list;
@@ -229,7 +229,8 @@ static int dsmark_enqueue(struct sk_buff *skb, struct Qdisc *sch)
skb->tc_index = TC_H_MIN(skb->priority);
else {
struct tcf_result res;
- int result = tc_classify(skb, p->filter_list, &res);
+ struct tcf_proto *fl = rcu_dereference_bh(p->filter_list);
+ int result = tc_classify(skb, fl, &res);
pr_debug("result %d class 0x%04x\n", result, res.classid);
diff --git a/net/sched/sch_fq_codel.c b/net/sched/sch_fq_codel.c
index cc56c8b..105cf55 100644
--- a/net/sched/sch_fq_codel.c
+++ b/net/sched/sch_fq_codel.c
@@ -52,7 +52,7 @@ struct fq_codel_flow {
}; /* please try to keep this structure <= 64 bytes */
struct fq_codel_sched_data {
- struct tcf_proto *filter_list; /* optional external classifier */
+ struct tcf_proto __rcu *filter_list; /* optional external classifier */
struct fq_codel_flow *flows; /* Flows table [flows_cnt] */
u32 *backlogs; /* backlog table [flows_cnt] */
u32 flows_cnt; /* number of flows */
@@ -85,6 +85,7 @@ static unsigned int fq_codel_classify(struct sk_buff *skb, struct Qdisc *sch,
int *qerr)
{
struct fq_codel_sched_data *q = qdisc_priv(sch);
+ struct tcf_proto *filter;
struct tcf_result res;
int result;
@@ -93,11 +94,12 @@ static unsigned int fq_codel_classify(struct sk_buff *skb, struct Qdisc *sch,
TC_H_MIN(skb->priority) <= q->flows_cnt)
return TC_H_MIN(skb->priority);
- if (!q->filter_list)
+ filter = rcu_dereference(q->filter_list);
+ if (!filter)
return fq_codel_hash(q, skb) + 1;
*qerr = NET_XMIT_SUCCESS | __NET_XMIT_BYPASS;
- result = tc_classify(skb, q->filter_list, &res);
+ result = tc_classify(skb, filter, &res);
if (result >= 0) {
#ifdef CONFIG_NET_CLS_ACT
switch (result) {
@@ -496,7 +498,8 @@ static void fq_codel_put(struct Qdisc *q, unsigned long cl)
{
}
-static struct tcf_proto **fq_codel_find_tcf(struct Qdisc *sch, unsigned long cl)
+static struct tcf_proto __rcu **fq_codel_find_tcf(struct Qdisc *sch,
+ unsigned long cl)
{
struct fq_codel_sched_data *q = qdisc_priv(sch);
diff --git a/net/sched/sch_hfsc.c b/net/sched/sch_hfsc.c
index ec8aeaa..04b0de4 100644
--- a/net/sched/sch_hfsc.c
+++ b/net/sched/sch_hfsc.c
@@ -116,7 +116,7 @@ struct hfsc_class {
struct gnet_stats_queue qstats;
struct gnet_stats_rate_est64 rate_est;
unsigned int level; /* class level in hierarchy */
- struct tcf_proto *filter_list; /* filter list */
+ struct tcf_proto __rcu *filter_list; /* filter list */
unsigned int filter_cnt; /* filter count */
struct hfsc_sched *sched; /* scheduler data */
@@ -1161,7 +1161,7 @@ hfsc_classify(struct sk_buff *skb, struct Qdisc *sch, int *qerr)
*qerr = NET_XMIT_SUCCESS | __NET_XMIT_BYPASS;
head = &q->root;
- tcf = q->root.filter_list;
+ tcf = rcu_dereference_bh(q->root.filter_list);
while (tcf && (result = tc_classify(skb, tcf, &res)) >= 0) {
#ifdef CONFIG_NET_CLS_ACT
switch (result) {
@@ -1185,7 +1185,7 @@ hfsc_classify(struct sk_buff *skb, struct Qdisc *sch, int *qerr)
return cl; /* hit leaf class */
/* apply inner filter chain */
- tcf = cl->filter_list;
+ tcf = rcu_dereference_bh(cl->filter_list);
head = cl;
}
@@ -1285,7 +1285,7 @@ hfsc_unbind_tcf(struct Qdisc *sch, unsigned long arg)
cl->filter_cnt--;
}
-static struct tcf_proto **
+static struct tcf_proto __rcu **
hfsc_tcf_chain(struct Qdisc *sch, unsigned long arg)
{
struct hfsc_sched *q = qdisc_priv(sch);
diff --git a/net/sched/sch_htb.c b/net/sched/sch_htb.c
index aea942c..6d16b9b 100644
--- a/net/sched/sch_htb.c
+++ b/net/sched/sch_htb.c
@@ -103,7 +103,7 @@ struct htb_class {
u32 prio; /* these two are used only by leaves... */
int quantum; /* but stored for parent-to-leaf return */
- struct tcf_proto *filter_list; /* class attached filters */
+ struct tcf_proto __rcu *filter_list; /* class attached filters */
int filter_cnt;
int refcnt; /* usage count of this class */
@@ -153,7 +153,7 @@ struct htb_sched {
int rate2quantum; /* quant = rate / rate2quantum */
/* filters for qdisc itself */
- struct tcf_proto *filter_list;
+ struct tcf_proto __rcu *filter_list;
#define HTB_WARN_TOOMANYEVENTS 0x1
unsigned int warned; /* only one warning */
@@ -223,9 +223,9 @@ static struct htb_class *htb_classify(struct sk_buff *skb, struct Qdisc *sch,
if (cl->level == 0)
return cl;
/* Start with inner filter chain if a non-leaf class is selected */
- tcf = cl->filter_list;
+ tcf = rcu_dereference_bh(cl->filter_list);
} else {
- tcf = q->filter_list;
+ tcf = rcu_dereference_bh(q->filter_list);
}
*qerr = NET_XMIT_SUCCESS | __NET_XMIT_BYPASS;
@@ -251,7 +251,7 @@ static struct htb_class *htb_classify(struct sk_buff *skb, struct Qdisc *sch,
return cl; /* we hit leaf; return it */
/* we have got inner class; apply inner filter chain */
- tcf = cl->filter_list;
+ tcf = rcu_dereference_bh(cl->filter_list);
}
/* classification failed; try to use default class */
cl = htb_find(TC_H_MAKE(TC_H_MAJ(sch->handle), q->defcls), sch);
@@ -1519,11 +1519,12 @@ failure:
return err;
}
-static struct tcf_proto **htb_find_tcf(struct Qdisc *sch, unsigned long arg)
+static struct tcf_proto __rcu **htb_find_tcf(struct Qdisc *sch,
+ unsigned long arg)
{
struct htb_sched *q = qdisc_priv(sch);
struct htb_class *cl = (struct htb_class *)arg;
- struct tcf_proto **fl = cl ? &cl->filter_list : &q->filter_list;
+ struct tcf_proto __rcu **fl = cl ? &cl->filter_list : &q->filter_list;
return fl;
}
diff --git a/net/sched/sch_ingress.c b/net/sched/sch_ingress.c
index 62871c1..b351125 100644
--- a/net/sched/sch_ingress.c
+++ b/net/sched/sch_ingress.c
@@ -17,7 +17,7 @@
struct ingress_qdisc_data {
- struct tcf_proto *filter_list;
+ struct tcf_proto __rcu *filter_list;
};
/* ------------------------- Class/flow operations ------------------------- */
@@ -46,7 +46,8 @@ static void ingress_walk(struct Qdisc *sch, struct qdisc_walker *walker)
{
}
-static struct tcf_proto **ingress_find_tcf(struct Qdisc *sch, unsigned long cl)
+static struct tcf_proto __rcu **ingress_find_tcf(struct Qdisc *sch,
+ unsigned long cl)
{
struct ingress_qdisc_data *p = qdisc_priv(sch);
@@ -59,9 +60,10 @@ static int ingress_enqueue(struct sk_buff *skb, struct Qdisc *sch)
{
struct ingress_qdisc_data *p = qdisc_priv(sch);
struct tcf_result res;
+ struct tcf_proto *fl = rcu_dereference_bh(p->filter_list);
int result;
- result = tc_classify(skb, p->filter_list, &res);
+ result = tc_classify(skb, fl, &res);
qdisc_bstats_update(sch, skb);
switch (result) {
diff --git a/net/sched/sch_multiq.c b/net/sched/sch_multiq.c
index afb050a..c0466c1 100644
--- a/net/sched/sch_multiq.c
+++ b/net/sched/sch_multiq.c
@@ -31,7 +31,7 @@ struct multiq_sched_data {
u16 bands;
u16 max_bands;
u16 curband;
- struct tcf_proto *filter_list;
+ struct tcf_proto __rcu *filter_list;
struct Qdisc **queues;
};
@@ -42,10 +42,11 @@ multiq_classify(struct sk_buff *skb, struct Qdisc *sch, int *qerr)
struct multiq_sched_data *q = qdisc_priv(sch);
u32 band;
struct tcf_result res;
+ struct tcf_proto *fl = rcu_dereference_bh(q->filter_list);
int err;
*qerr = NET_XMIT_SUCCESS | __NET_XMIT_BYPASS;
- err = tc_classify(skb, q->filter_list, &res);
+ err = tc_classify(skb, fl, &res);
#ifdef CONFIG_NET_CLS_ACT
switch (err) {
case TC_ACT_STOLEN:
@@ -388,7 +389,8 @@ static void multiq_walk(struct Qdisc *sch, struct qdisc_walker *arg)
}
}
-static struct tcf_proto **multiq_find_tcf(struct Qdisc *sch, unsigned long cl)
+static struct tcf_proto __rcu **multiq_find_tcf(struct Qdisc *sch,
+ unsigned long cl)
{
struct multiq_sched_data *q = qdisc_priv(sch);
diff --git a/net/sched/sch_prio.c b/net/sched/sch_prio.c
index 79359b6..03ef99e 100644
--- a/net/sched/sch_prio.c
+++ b/net/sched/sch_prio.c
@@ -24,7 +24,7 @@
struct prio_sched_data {
int bands;
- struct tcf_proto *filter_list;
+ struct tcf_proto __rcu *filter_list;
u8 prio2band[TC_PRIO_MAX+1];
struct Qdisc *queues[TCQ_PRIO_BANDS];
};
@@ -36,11 +36,13 @@ prio_classify(struct sk_buff *skb, struct Qdisc *sch, int *qerr)
struct prio_sched_data *q = qdisc_priv(sch);
u32 band = skb->priority;
struct tcf_result res;
+ struct tcf_proto *fl;
int err;
*qerr = NET_XMIT_SUCCESS | __NET_XMIT_BYPASS;
if (TC_H_MAJ(skb->priority) != sch->handle) {
- err = tc_classify(skb, q->filter_list, &res);
+ fl = rcu_dereference_bh(q->filter_list);
+ err = tc_classify(skb, fl, &res);
#ifdef CONFIG_NET_CLS_ACT
switch (err) {
case TC_ACT_STOLEN:
@@ -50,7 +52,7 @@ prio_classify(struct sk_buff *skb, struct Qdisc *sch, int *qerr)
return NULL;
}
#endif
- if (!q->filter_list || err < 0) {
+ if (!fl || err < 0) {
if (TC_H_MAJ(band))
band = 0;
return q->queues[q->prio2band[band & TC_PRIO_MAX]];
@@ -351,7 +353,8 @@ static void prio_walk(struct Qdisc *sch, struct qdisc_walker *arg)
}
}
-static struct tcf_proto **prio_find_tcf(struct Qdisc *sch, unsigned long cl)
+static struct tcf_proto __rcu **prio_find_tcf(struct Qdisc *sch,
+ unsigned long cl)
{
struct prio_sched_data *q = qdisc_priv(sch);
diff --git a/net/sched/sch_qfq.c b/net/sched/sch_qfq.c
index 8056fb4..602ea01 100644
--- a/net/sched/sch_qfq.c
+++ b/net/sched/sch_qfq.c
@@ -181,7 +181,7 @@ struct qfq_group {
};
struct qfq_sched {
- struct tcf_proto *filter_list;
+ struct tcf_proto __rcu *filter_list;
struct Qdisc_class_hash clhash;
u64 oldV, V; /* Precise virtual times. */
@@ -576,7 +576,8 @@ static void qfq_put_class(struct Qdisc *sch, unsigned long arg)
qfq_destroy_class(sch, cl);
}
-static struct tcf_proto **qfq_tcf_chain(struct Qdisc *sch, unsigned long cl)
+static struct tcf_proto __rcu **qfq_tcf_chain(struct Qdisc *sch,
+ unsigned long cl)
{
struct qfq_sched *q = qdisc_priv(sch);
@@ -704,6 +705,7 @@ static struct qfq_class *qfq_classify(struct sk_buff *skb, struct Qdisc *sch,
struct qfq_sched *q = qdisc_priv(sch);
struct qfq_class *cl;
struct tcf_result res;
+ struct tcf_proto *fl;
int result;
if (TC_H_MAJ(skb->priority ^ sch->handle) == 0) {
@@ -714,7 +716,8 @@ static struct qfq_class *qfq_classify(struct sk_buff *skb, struct Qdisc *sch,
}
*qerr = NET_XMIT_SUCCESS | __NET_XMIT_BYPASS;
- result = tc_classify(skb, q->filter_list, &res);
+ fl = rcu_dereference_bh(q->filter_list);
+ result = tc_classify(skb, fl, &res);
if (result >= 0) {
#ifdef CONFIG_NET_CLS_ACT
switch (result) {
diff --git a/net/sched/sch_sfb.c b/net/sched/sch_sfb.c
index 9b0f709..1562fb2 100644
--- a/net/sched/sch_sfb.c
+++ b/net/sched/sch_sfb.c
@@ -55,7 +55,7 @@ struct sfb_bins {
struct sfb_sched_data {
struct Qdisc *qdisc;
- struct tcf_proto *filter_list;
+ struct tcf_proto __rcu *filter_list;
unsigned long rehash_interval;
unsigned long warmup_time; /* double buffering warmup time in jiffies */
u32 max;
@@ -253,13 +253,13 @@ static bool sfb_rate_limit(struct sk_buff *skb, struct sfb_sched_data *q)
return false;
}
-static bool sfb_classify(struct sk_buff *skb, struct sfb_sched_data *q,
+static bool sfb_classify(struct sk_buff *skb, struct tcf_proto *fl,
int *qerr, u32 *salt)
{
struct tcf_result res;
int result;
- result = tc_classify(skb, q->filter_list, &res);
+ result = tc_classify(skb, fl, &res);
if (result >= 0) {
#ifdef CONFIG_NET_CLS_ACT
switch (result) {
@@ -281,6 +281,7 @@ static int sfb_enqueue(struct sk_buff *skb, struct Qdisc *sch)
struct sfb_sched_data *q = qdisc_priv(sch);
struct Qdisc *child = q->qdisc;
+ struct tcf_proto *fl;
int i;
u32 p_min = ~0;
u32 minqlen = ~0;
@@ -306,9 +307,10 @@ static int sfb_enqueue(struct sk_buff *skb, struct Qdisc *sch)
}
}
- if (q->filter_list) {
+ fl = rcu_dereference_bh(q->filter_list);
+ if (fl) {
/* If using external classifiers, get result and record it. */
- if (!sfb_classify(skb, q, &ret, &salt))
+ if (!sfb_classify(skb, fl, &ret, &salt))
goto other_drop;
keys.src = salt;
keys.dst = 0;
@@ -660,7 +662,8 @@ static void sfb_walk(struct Qdisc *sch, struct qdisc_walker *walker)
}
}
-static struct tcf_proto **sfb_find_tcf(struct Qdisc *sch, unsigned long cl)
+static struct tcf_proto __rcu **sfb_find_tcf(struct Qdisc *sch,
+ unsigned long cl)
{
struct sfb_sched_data *q = qdisc_priv(sch);
diff --git a/net/sched/sch_sfq.c b/net/sched/sch_sfq.c
index 1af2f73..0bededd 100644
--- a/net/sched/sch_sfq.c
+++ b/net/sched/sch_sfq.c
@@ -125,7 +125,7 @@ struct sfq_sched_data {
u8 cur_depth; /* depth of longest slot */
u8 flags;
unsigned short scaled_quantum; /* SFQ_ALLOT_SIZE(quantum) */
- struct tcf_proto *filter_list;
+ struct tcf_proto __rcu *filter_list;
sfq_index *ht; /* Hash table ('divisor' slots) */
struct sfq_slot *slots; /* Flows table ('maxflows' entries) */
@@ -187,6 +187,7 @@ static unsigned int sfq_classify(struct sk_buff *skb, struct Qdisc *sch,
{
struct sfq_sched_data *q = qdisc_priv(sch);
struct tcf_result res;
+ struct tcf_proto *fl;
int result;
if (TC_H_MAJ(skb->priority) == sch->handle &&
@@ -194,13 +195,14 @@ static unsigned int sfq_classify(struct sk_buff *skb, struct Qdisc *sch,
TC_H_MIN(skb->priority) <= q->divisor)
return TC_H_MIN(skb->priority);
- if (!q->filter_list) {
+ fl = rcu_dereference_bh(q->filter_list);
+ if (!fl) {
skb_flow_dissect(skb, &sfq_skb_cb(skb)->keys);
return sfq_hash(q, skb) + 1;
}
*qerr = NET_XMIT_SUCCESS | __NET_XMIT_BYPASS;
- result = tc_classify(skb, q->filter_list, &res);
+ result = tc_classify(skb, fl, &res);
if (result >= 0) {
#ifdef CONFIG_NET_CLS_ACT
switch (result) {
@@ -841,7 +843,8 @@ static void sfq_put(struct Qdisc *q, unsigned long cl)
{
}
-static struct tcf_proto **sfq_find_tcf(struct Qdisc *sch, unsigned long cl)
+static struct tcf_proto __rcu **sfq_find_tcf(struct Qdisc *sch,
+ unsigned long cl)
{
struct sfq_sched_data *q = qdisc_priv(sch);
next prev parent reply other threads:[~2014-09-09 5:55 UTC|newest]
Thread overview: 34+ messages / expand[flat|nested] mbox.gz Atom feed top
2014-09-09 5:53 [net-next PATCH v3 00/15] net/sched use rcu filters John Fastabend
2014-09-09 5:54 ` [net-next PATCH v3 01/15] net: qdisc: use rcu prefix and silence sparse warnings John Fastabend
2014-09-09 12:05 ` Eric Dumazet
2014-09-09 5:54 ` John Fastabend [this message]
2014-09-09 12:20 ` [net-next PATCH v3 02/15] net: rcu-ify tcf_proto Eric Dumazet
2014-09-09 15:15 ` John Fastabend
2014-09-09 15:20 ` Eric Dumazet
2014-09-09 5:55 ` [net-next PATCH v3 03/15] net: sched: cls_basic use RCU John Fastabend
2014-09-09 12:29 ` Eric Dumazet
2014-09-09 5:55 ` [net-next PATCH v3 04/15] net: sched: cls_cgroup " John Fastabend
2014-09-09 12:34 ` Eric Dumazet
2014-09-09 5:56 ` [net-next PATCH v3 05/15] net: sched: cls_flow " John Fastabend
2014-09-09 12:41 ` Eric Dumazet
2014-09-09 16:09 ` John Fastabend
2014-09-09 16:20 ` Eric Dumazet
2014-09-09 5:56 ` [net-next PATCH v3 06/15] net: sched: fw " John Fastabend
2014-09-09 12:48 ` Eric Dumazet
2014-09-09 5:57 ` [net-next PATCH v3 07/15] net: sched: RCU cls_route John Fastabend
2014-09-09 12:59 ` Eric Dumazet
2014-09-09 16:24 ` John Fastabend
2014-09-09 5:57 ` [net-next PATCH v3 08/15] net: sched: RCU cls_tcindex John Fastabend
2014-09-09 5:58 ` [net-next PATCH v3 09/15] net: sched: make cls_u32 lockless John Fastabend
2014-09-09 13:20 ` Eric Dumazet
2014-09-09 16:35 ` John Fastabend
2014-09-09 18:02 ` Cong Wang
2014-09-10 4:53 ` John Fastabend
2014-09-09 5:58 ` [net-next PATCH v3 10/15] net: sched: rcu'ify cls_rsvp John Fastabend
2014-09-09 13:27 ` Eric Dumazet
2014-09-09 16:46 ` John Fastabend
2014-09-09 5:59 ` [net-next PATCH v3 11/15] net: sched: rcu'ify cls_bpf John Fastabend
2014-09-09 5:59 ` [net-next PATCH v3 12/15] net: sched: make tc_action safe to walk under RCU John Fastabend
2014-09-09 6:00 ` [net-next PATCH v3 13/15] net: sched: make bstats per cpu and estimator RCU safe John Fastabend
2014-09-09 6:00 ` [net-next PATCH v3 14/15] net: sched: make qstats per cpu John Fastabend
2014-09-09 6:01 ` [net-next PATCH v3 15/15] net: sched: drop ingress qdisc lock John Fastabend
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20140909055437.2071.86430.stgit@nitbit.x32 \
--to=john.fastabend@gmail.com \
--cc=brouer@redhat.com \
--cc=davem@davemloft.net \
--cc=eric.dumazet@gmail.com \
--cc=jhs@mojatatu.com \
--cc=netdev@vger.kernel.org \
--cc=paulmck@linux.vnet.ibm.com \
--cc=xiyou.wangcong@gmail.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.