All of lore.kernel.org
 help / color / mirror / Atom feed
From: John Fastabend <john.fastabend@gmail.com>
To: xiyou.wangcong@gmail.com, jhs@mojatatu.com, eric.dumazet@gmail.com
Cc: netdev@vger.kernel.org, davem@davemloft.net
Subject: [RFC PATCH 02/12] net: rcu-ify tcf_proto
Date: Fri, 10 Jan 2014 01:37:35 -0800	[thread overview]
Message-ID: <20140110093733.7193.41632.stgit@nitbit.x32> (raw)
In-Reply-To: <20140110092041.7193.5952.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 |    5 +++--
 net/sched/cls_api.c       |   29 ++++++++++++++---------------
 net/sched/sch_api.c       |    6 +++---
 net/sched/sch_atm.c       |   30 +++++++++++++++++++-----------
 net/sched/sch_cbq.c       |   21 +++++++++++++++------
 net/sched/sch_choke.c     |   18 +++++++++++++-----
 net/sched/sch_drr.c       |   10 +++++++---
 net/sched/sch_dsmark.c    |    8 +++++---
 net/sched/sch_fq_codel.c  |   11 +++++++----
 net/sched/sch_hfsc.c      |   17 +++++++++++------
 net/sched/sch_htb.c       |   23 +++++++++++++++--------
 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, 151 insertions(+), 89 deletions(-)

diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h
index 3e10a2a..11b878b 100644
--- a/include/net/sch_generic.h
+++ b/include/net/sch_generic.h
@@ -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 {
diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c
index 12e882e..86c3678 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;
@@ -196,7 +196,9 @@ 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 ||
@@ -208,8 +210,6 @@ replay:
 		}
 	}
 
-	root_lock = qdisc_root_sleeping_lock(q);
-
 	if (tp == NULL) {
 		/* Proto-tcf does not exist, create new one */
 
@@ -258,7 +258,7 @@ 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;
@@ -279,9 +279,9 @@ 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);
@@ -320,10 +320,8 @@ replay:
 	err = tp->ops->change(net, skb, tp, cl, t->tcm_handle, tca, &fh);
 	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 {
@@ -417,7 +415,7 @@ 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;
@@ -451,7 +449,8 @@ 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 1313145..774f61c 100644
--- a/net/sched/sch_api.c
+++ b/net/sched/sch_api.c
@@ -1778,7 +1778,7 @@ 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;
@@ -1830,7 +1830,7 @@ 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)
@@ -1838,7 +1838,7 @@ void tcf_destroy_chain(struct tcf_proto **fl)
 	struct tcf_proto *tp;
 
 	while ((tp = *fl) != NULL) {
-		*fl = tp->next;
+		*fl = rtnl_dereference(tp->next);
 		tcf_destroy(tp);
 	}
 }
diff --git a/net/sched/sch_atm.c b/net/sched/sch_atm.c
index 1f9c314..a4953c6 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 */
@@ -134,6 +134,7 @@ static void atm_tc_put(struct Qdisc *sch, unsigned long cl)
 {
 	struct atm_qdisc_data *p = qdisc_priv(sch);
 	struct atm_flow_data *flow = (struct atm_flow_data *)cl;
+	struct tcf_proto *fl;
 
 	pr_debug("atm_tc_put(sch %p,[qdisc %p],flow %p)\n", sch, p, flow);
 	if (--flow->ref)
@@ -142,7 +143,10 @@ 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);
+
+	fl = rtnl_dereference(flow->filter_list);
+	tcf_destroy_chain(&fl);
+
 	if (flow->sock) {
 		pr_debug("atm_tc_put: f_count %ld\n",
 			file_count(flow->sock->file));
@@ -273,7 +277,7 @@ static int atm_tc_change(struct Qdisc *sch, u32 classid, u32 parent,
 		error = -ENOBUFS;
 		goto err_out;
 	}
-	flow->filter_list = NULL;
+	rcu_assign_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 +315,7 @@ 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
@@ -369,11 +373,12 @@ 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 +549,7 @@ 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_assign_pointer(p->link.filter_list, NULL);
 	p->link.vcc = NULL;
 	p->link.sock = NULL;
 	p->link.classid = sch->handle;
@@ -568,10 +573,13 @@ static void atm_tc_destroy(struct Qdisc *sch)
 {
 	struct atm_qdisc_data *p = qdisc_priv(sch);
 	struct atm_flow_data *flow, *tmp;
+	struct tcf_proto *fl;
 
 	pr_debug("atm_tc_destroy(sch %p,[qdisc %p])\n", sch, p);
-	list_for_each_entry(flow, &p->flows, list)
-		tcf_destroy_chain(&flow->filter_list);
+	list_for_each_entry(flow, &p->flows, list) {
+		fl = rtnl_dereference(flow->filter_list);
+		tcf_destroy_chain(&fl);
+	}
 
 	list_for_each_entry_safe(flow, tmp, &p->flows, list) {
 		if (flow->ref > 1)
diff --git a/net/sched/sch_cbq.c b/net/sched/sch_cbq.c
index 2f80d01..61a51d0 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;
@@ -222,6 +222,7 @@ 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;
 
 	/*
@@ -234,13 +235,15 @@ 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;
@@ -1685,10 +1688,13 @@ static unsigned long cbq_get(struct Qdisc *sch, u32 classid)
 static void cbq_destroy_class(struct Qdisc *sch, struct cbq_class *cl)
 {
 	struct cbq_sched_data *q = qdisc_priv(sch);
+	struct tcf_proto *fl;
 
 	WARN_ON(cl->filters);
 
-	tcf_destroy_chain(&cl->filter_list);
+	fl = rtnl_dereference(cl->filter_list);
+	tcf_destroy_chain(&fl);
+
 	qdisc_destroy(cl->q);
 	qdisc_put_rtab(cl->R_tab);
 	gen_kill_estimator(&cl->bstats, &cl->rate_est);
@@ -1701,6 +1707,7 @@ static void cbq_destroy(struct Qdisc *sch)
 	struct cbq_sched_data *q = qdisc_priv(sch);
 	struct hlist_node *next;
 	struct cbq_class *cl;
+	struct tcf_proto *fl;
 	unsigned int h;
 
 #ifdef CONFIG_NET_CLS_ACT
@@ -1712,8 +1719,10 @@ static void cbq_destroy(struct Qdisc *sch)
 	 * be bound to classes which have been destroyed already. --TGR '04
 	 */
 	for (h = 0; h < q->clhash.hashsize; h++) {
-		hlist_for_each_entry(cl, &q->clhash.hash[h], common.hnode)
-			tcf_destroy_chain(&cl->filter_list);
+		hlist_for_each_entry(cl, &q->clhash.hash[h], common.hnode) {
+			fl = rtnl_dereference(cl->filter_list);
+			tcf_destroy_chain(&fl);
+		}
 	}
 	for (h = 0; h < q->clhash.hashsize; h++) {
 		hlist_for_each_entry_safe(cl, next, &q->clhash.hash[h],
diff --git a/net/sched/sch_choke.c b/net/sched/sch_choke.c
index ddd73cb..60eb0e5 100644
--- a/net/sched/sch_choke.c
+++ b/net/sched/sch_choke.c
@@ -58,7 +58,7 @@ 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 */
@@ -200,9 +200,11 @@ 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) {
@@ -251,12 +253,14 @@ 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);
@@ -266,9 +270,11 @@ 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 */
@@ -541,8 +547,10 @@ static int choke_dump_stats(struct Qdisc *sch, struct gnet_dump *d)
 static void choke_destroy(struct Qdisc *sch)
 {
 	struct choke_sched_data *q = qdisc_priv(sch);
+	struct tcf_proto *fl;
 
-	tcf_destroy_chain(&q->filter_list);
+	fl = rtnl_dereference(q->filter_list);
+	tcf_destroy_chain(&fl);
 	choke_free(q->tab);
 }
 
diff --git a/net/sched/sch_drr.c b/net/sched/sch_drr.c
index 8302717..899026f 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;
 };
 
@@ -319,6 +319,7 @@ 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 +329,8 @@ 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) {
@@ -467,9 +469,11 @@ static void drr_destroy_qdisc(struct Qdisc *sch)
 	struct drr_sched *q = qdisc_priv(sch);
 	struct drr_class *cl;
 	struct hlist_node *next;
+	struct tcf_proto *fl;
 	unsigned int i;
 
-	tcf_destroy_chain(&q->filter_list);
+	fl = rtnl_dereference(q->filter_list);
+	tcf_destroy_chain(&fl);
 
 	for (i = 0; i < q->clhash.hashsize; i++) {
 		hlist_for_each_entry_safe(cl, next, &q->clhash.hash[i],
diff --git a/net/sched/sch_dsmark.c b/net/sched/sch_dsmark.c
index 49d6ef3..6b84bd4 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;
@@ -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);
 
@@ -404,10 +405,11 @@ static void dsmark_reset(struct Qdisc *sch)
 static void dsmark_destroy(struct Qdisc *sch)
 {
 	struct dsmark_qdisc_data *p = qdisc_priv(sch);
+	struct tcf_proto *fl = rtnl_dereference(p->filter_list);
 
 	pr_debug("%s(sch %p,[qdisc %p])\n", __func__, sch, p);
 
-	tcf_destroy_chain(&p->filter_list);
+	tcf_destroy_chain(&fl);
 	qdisc_destroy(p->q);
 	kfree(p->mask);
 }
diff --git a/net/sched/sch_fq_codel.c b/net/sched/sch_fq_codel.c
index 5578628..bc47789 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 */
@@ -84,6 +84,7 @@ 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;
 
@@ -92,11 +93,12 @@ 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) {
@@ -376,8 +378,9 @@ static void fq_codel_free(void *addr)
 static void fq_codel_destroy(struct Qdisc *sch)
 {
 	struct fq_codel_sched_data *q = qdisc_priv(sch);
+	struct tcf_proto *filter = rtnl_dereference(q->filter_list);
 
-	tcf_destroy_chain(&q->filter_list);
+	tcf_destroy_chain(&filter);
 	fq_codel_free(q->backlogs);
 	fq_codel_free(q->flows);
 }
diff --git a/net/sched/sch_hfsc.c b/net/sched/sch_hfsc.c
index c407561..0a7650f 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 */
@@ -1110,8 +1110,10 @@ static void
 hfsc_destroy_class(struct Qdisc *sch, struct hfsc_class *cl)
 {
 	struct hfsc_sched *q = qdisc_priv(sch);
+	struct tcf_proto *fl;
 
-	tcf_destroy_chain(&cl->filter_list);
+	fl = rtnl_dereference(cl->filter_list);
+	tcf_destroy_chain(&fl);
 	qdisc_destroy(cl->qdisc);
 	gen_kill_estimator(&cl->bstats, &cl->rate_est);
 	if (cl != &q->root)
@@ -1161,7 +1163,7 @@ 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 +1187,7 @@ 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;
 	}
 
@@ -1540,11 +1542,14 @@ hfsc_destroy_qdisc(struct Qdisc *sch)
 	struct hfsc_sched *q = qdisc_priv(sch);
 	struct hlist_node *next;
 	struct hfsc_class *cl;
+	struct tcf_proto *fl;
 	unsigned int i;
 
 	for (i = 0; i < q->clhash.hashsize; i++) {
-		hlist_for_each_entry(cl, &q->clhash.hash[i], cl_common.hnode)
-			tcf_destroy_chain(&cl->filter_list);
+		hlist_for_each_entry(cl, &q->clhash.hash[i], cl_common.hnode) {
+			fl = rtnl_dereference(cl->filter_list);
+			tcf_destroy_chain(&fl);
+		}
 	}
 	for (i = 0; i < q->clhash.hashsize; i++) {
 		hlist_for_each_entry_safe(cl, next, &q->clhash.hash[i],
diff --git a/net/sched/sch_htb.c b/net/sched/sch_htb.c
index 0db5a6e..86df75c 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 */
@@ -223,7 +223,7 @@ static struct htb_class *htb_classify(struct sk_buff *skb, struct Qdisc *sch,
 		return cl;
 
 	*qerr = NET_XMIT_SUCCESS | __NET_XMIT_BYPASS;
-	tcf = q->filter_list;
+	tcf = rcu_dereference_bh(q->filter_list);
 	while (tcf && (result = tc_classify(skb, tcf, &res)) >= 0) {
 #ifdef CONFIG_NET_CLS_ACT
 		switch (result) {
@@ -246,7 +246,7 @@ 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);
@@ -1230,12 +1230,15 @@ static void htb_parent_to_leaf(struct htb_sched *q, struct htb_class *cl,
 
 static void htb_destroy_class(struct Qdisc *sch, struct htb_class *cl)
 {
+	struct tcf_proto *fl;
+
 	if (!cl->level) {
 		WARN_ON(!cl->un.leaf.q);
 		qdisc_destroy(cl->un.leaf.q);
 	}
 	gen_kill_estimator(&cl->bstats, &cl->rate_est);
-	tcf_destroy_chain(&cl->filter_list);
+	fl = rtnl_dereference(cl->filter_list);
+	tcf_destroy_chain(&fl);
 	kfree(cl);
 }
 
@@ -1244,6 +1247,7 @@ static void htb_destroy(struct Qdisc *sch)
 	struct htb_sched *q = qdisc_priv(sch);
 	struct hlist_node *next;
 	struct htb_class *cl;
+	struct tcf_proto *fl;
 	unsigned int i;
 
 	cancel_work_sync(&q->work);
@@ -1253,11 +1257,14 @@ static void htb_destroy(struct Qdisc *sch)
 	 * because filter need its target class alive to be able to call
 	 * unbind_filter on it (without Oops).
 	 */
-	tcf_destroy_chain(&q->filter_list);
+	fl = rtnl_dereference(q->filter_list);
+	tcf_destroy_chain(&fl);
 
 	for (i = 0; i < q->clhash.hashsize; i++) {
-		hlist_for_each_entry(cl, &q->clhash.hash[i], common.hnode)
-			tcf_destroy_chain(&cl->filter_list);
+		hlist_for_each_entry(cl, &q->clhash.hash[i], common.hnode) {
+			fl = rtnl_dereference(cl->filter_list);
+			tcf_destroy_chain(&fl);
+		}
 	}
 	for (i = 0; i < q->clhash.hashsize; i++) {
 		hlist_for_each_entry_safe(cl, next, &q->clhash.hash[i],
diff --git a/net/sched/sch_ingress.c b/net/sched/sch_ingress.c
index bce1665..f7c80d3 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 ------------------------- */
@@ -59,9 +59,10 @@ 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) {
@@ -89,8 +90,9 @@ static int ingress_enqueue(struct sk_buff *skb, struct Qdisc *sch)
 static void ingress_destroy(struct Qdisc *sch)
 {
 	struct ingress_qdisc_data *p = qdisc_priv(sch);
+	struct tcf_proto *fl = rtnl_dereference(p->filter_list);
 
-	tcf_destroy_chain(&p->filter_list);
+	tcf_destroy_chain(&fl);
 }
 
 static int ingress_dump(struct Qdisc *sch, struct sk_buff *skb)
diff --git a/net/sched/sch_multiq.c b/net/sched/sch_multiq.c
index afb050a..169d637 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:
@@ -188,8 +189,9 @@ multiq_destroy(struct Qdisc *sch)
 {
 	int band;
 	struct multiq_sched_data *q = qdisc_priv(sch);
+	struct tcf_proto *fl = rtnl_dereference(q->filter_list);
 
-	tcf_destroy_chain(&q->filter_list);
+	tcf_destroy_chain(&fl);
 	for (band = 0; band < q->bands; band++)
 		qdisc_destroy(q->queues[band]);
 
diff --git a/net/sched/sch_prio.c b/net/sched/sch_prio.c
index 79359b6..43aa35d 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]];
@@ -157,8 +159,9 @@ prio_destroy(struct Qdisc *sch)
 {
 	int prio;
 	struct prio_sched_data *q = qdisc_priv(sch);
+	struct tcf_proto *fl = rtnl_dereference(q->filter_list);
 
-	tcf_destroy_chain(&q->filter_list);
+	tcf_destroy_chain(&fl);
 	for (prio = 0; prio < q->bands; prio++)
 		qdisc_destroy(q->queues[prio]);
 }
diff --git a/net/sched/sch_qfq.c b/net/sched/sch_qfq.c
index 8056fb4..cee5618 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. */
@@ -704,6 +704,7 @@ 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 +715,8 @@ 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) {
@@ -1524,9 +1526,10 @@ static void qfq_destroy_qdisc(struct Qdisc *sch)
 	struct qfq_sched *q = qdisc_priv(sch);
 	struct qfq_class *cl;
 	struct hlist_node *next;
+	struct tcf_proto *fl = rtnl_dereference(q->filter_list);
 	unsigned int i;
 
-	tcf_destroy_chain(&q->filter_list);
+	tcf_destroy_chain(&fl);
 
 	for (i = 0; i < q->clhash.hashsize; i++) {
 		hlist_for_each_entry_safe(cl, next, &q->clhash.hash[i],
diff --git a/net/sched/sch_sfb.c b/net/sched/sch_sfb.c
index 30ea467..a4f1d6c 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;
@@ -465,8 +467,9 @@ static void sfb_reset(struct Qdisc *sch)
 static void sfb_destroy(struct Qdisc *sch)
 {
 	struct sfb_sched_data *q = qdisc_priv(sch);
+	struct tcf_proto *fl = rtnl_dereference(q->filter_list);
 
-	tcf_destroy_chain(&q->filter_list);
+	tcf_destroy_chain(&fl);
 	qdisc_destroy(q->qdisc);
 }
 
diff --git a/net/sched/sch_sfq.c b/net/sched/sch_sfq.c
index 76f01e0..da24df01 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) {
@@ -727,8 +729,9 @@ static void sfq_free(void *addr)
 static void sfq_destroy(struct Qdisc *sch)
 {
 	struct sfq_sched_data *q = qdisc_priv(sch);
+	struct tcf_proto *fl = rtnl_dereference(q->filter_list);
 
-	tcf_destroy_chain(&q->filter_list);
+	tcf_destroy_chain(&fl);
 	q->perturb_period = 0;
 	del_timer_sync(&q->perturb_timer);
 	sfq_free(q->ht);

  parent reply	other threads:[~2014-01-10  9:37 UTC|newest]

Thread overview: 20+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2014-01-10  9:36 [RFC PATCH 00/12] RCU'ify the net:sched classifier chains John Fastabend
2014-01-10  9:37 ` [RFC PATCH 01/12] net: qdisc: use rcu prefix and silence sparse warnings John Fastabend
2014-01-10  9:37 ` John Fastabend [this message]
2014-01-10  9:38 ` [RFC PATCH 03/12] net: sched: cls_basic use RCU John Fastabend
2014-01-10  9:38 ` [RFC PATCH 04/12] net: sched: cls_cgroup " John Fastabend
2014-01-10  9:39 ` [RFC PATCH 05/12] net: sched: cls_flow " John Fastabend
2014-01-10  9:39 ` [RFC PATCH 06/12] net: sched: fw " John Fastabend
2014-01-10  9:41 ` [RFC PATCH 07/12] net: sched: RCU cls_route John Fastabend
2014-01-10  9:42 ` [RFC PATCH 08/12] net: sched: RCU cls_tcindex John Fastabend
2014-01-10  9:42 ` [RFC PATCH 09/12] net: sched: make cls_u32 lockless John Fastabend
2014-01-10  9:43 ` [RFC PATCH 10/12] net: sched: rcu'ify cls_rsvp John Fastabend
2014-01-10  9:43 ` [RFC PATCH 11/12] net: make cls_bpf rcu safe John Fastabend
2014-01-10  9:44 ` [RFC PATCH 12/12] net: sched: make tc_action safe to walk under RCU John Fastabend
2014-01-11 19:43 ` [RFC PATCH 00/12] RCU'ify the net:sched classifier chains Cong Wang
2014-01-11 23:33   ` John Fastabend
2014-04-24 23:51     ` Cong Wang
2014-04-30 16:36       ` John Fastabend
2014-01-12 13:28 ` Jamal Hadi Salim
2014-01-12 13:57   ` Jamal Hadi Salim
2014-01-12 14:18     ` Jamal Hadi Salim

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=20140110093733.7193.41632.stgit@nitbit.x32 \
    --to=john.fastabend@gmail.com \
    --cc=davem@davemloft.net \
    --cc=eric.dumazet@gmail.com \
    --cc=jhs@mojatatu.com \
    --cc=netdev@vger.kernel.org \
    --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.