Patchwork pkt_sched: gen_kill_estimator() rcu fixes

login
register
mail settings
Submitter Eric Dumazet
Date June 9, 2010, 9:56 a.m.
Message ID <1276077416.2442.97.camel@edumazet-laptop>
Download mbox | patch
Permalink /patch/55066/
State Superseded
Delegated to: David Miller
Headers show

Comments

Eric Dumazet - June 9, 2010, 9:56 a.m.
Oops, I missed  kfree() deletion in  :


>  static void tcf_police_destroy(struct tcf_police *p)
>  {
>  	unsigned int h = tcf_hash(p->tcf_index, POL_TAB_MASK);
> @@ -113,6 +118,7 @@ static void tcf_police_destroy(struct tcf_police *p)
>  				qdisc_put_rtab(p->tcfp_R_tab);
>  			if (p->tcfp_P_tab)
>  				qdisc_put_rtab(p->tcfp_P_tab);
> +			call_rcu(&p->tcf_rcu, tcf_police_free_rcu);
>  			kfree(p);
>  			return;

Updated patch follows :

[PATCH] pkt_sched: gen_kill_estimator() rcu fixes

gen_kill_estimator() API is a bit misleading, since caller
should make sure an RCU grace period is respected before
freeing stats_lock.

This was partially addressed in commit 5d944c640b4 
(gen_estimator: deadlock fix), but same problem exist for all
gen_kill_estimator() users, if lock they use is not already rcu
protected.

A code review shows xt_RATEEST.c, act_api.c, act_police.c have this
problem. Other are ok because they use qdisc lock.

Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
---
 include/net/act_api.h              |    2 ++
 include/net/netfilter/xt_rateest.h |    1 +
 net/core/gen_estimator.c           |    1 +
 net/netfilter/xt_RATEEST.c         |    8 +++++++-
 net/sched/act_api.c                |    7 ++++++-
 net/sched/act_police.c             |    8 +++++++-
 6 files changed, 24 insertions(+), 3 deletions(-)



--
To unsubscribe from this list: send the line "unsubscribe netdev" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Jarek Poplawski - June 9, 2010, 10:41 a.m.
On Wed, Jun 09, 2010 at 11:56:56AM +0200, Eric Dumazet wrote:
...
> Updated patch follows :
> 
> [PATCH] pkt_sched: gen_kill_estimator() rcu fixes
> 
> gen_kill_estimator() API is a bit misleading, since caller

I'd call it incomplete or simply buggy. Plus a tiny note below.

> should make sure an RCU grace period is respected before
> freeing stats_lock.
> 
> This was partially addressed in commit 5d944c640b4 
> (gen_estimator: deadlock fix), but same problem exist for all
> gen_kill_estimator() users, if lock they use is not already rcu
> protected.
> 
> A code review shows xt_RATEEST.c, act_api.c, act_police.c have this
> problem. Other are ok because they use qdisc lock.
> 
> Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
> ---
...
> diff --git a/net/netfilter/xt_RATEEST.c b/net/netfilter/xt_RATEEST.c
> index 69c01e1..096b18b 100644
> --- a/net/netfilter/xt_RATEEST.c
> +++ b/net/netfilter/xt_RATEEST.c
> @@ -60,13 +60,18 @@ struct xt_rateest *xt_rateest_lookup(const char *name)
>  }
>  EXPORT_SYMBOL_GPL(xt_rateest_lookup);
>  
> +static void xt_rateeset_free_rcu(struct rcu_head *head)
> +{
> +	kfree(container_of(head, struct xt_rateest, rcu));
> +}
> +
>  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);
> -		kfree(est);
> +		call_rcu(&est->rcu, xt_rateeset_free_rcu);

Spelling suggestion: xt_rateest_free_rcu?

Since it's only 3 places I'd consider adding little comments,
who needs this call_rcu (like in qdisc_destroy).

Anyway this patch looks OK to me.

Jarek P.
--
To unsubscribe from this list: send the line "unsubscribe netdev" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

Patch

diff --git a/include/net/act_api.h b/include/net/act_api.h
index c05fd71..bab385f 100644
--- a/include/net/act_api.h
+++ b/include/net/act_api.h
@@ -20,6 +20,7 @@  struct tcf_common {
 	struct gnet_stats_queue		tcfc_qstats;
 	struct gnet_stats_rate_est	tcfc_rate_est;
 	spinlock_t			tcfc_lock;
+	struct rcu_head			tcfc_rcu;
 };
 #define tcf_next	common.tcfc_next
 #define tcf_index	common.tcfc_index
@@ -32,6 +33,7 @@  struct tcf_common {
 #define tcf_qstats	common.tcfc_qstats
 #define tcf_rate_est	common.tcfc_rate_est
 #define tcf_lock	common.tcfc_lock
+#define tcf_rcu		common.tcfc_rcu
 
 struct tcf_police {
 	struct tcf_common	common;
diff --git a/include/net/netfilter/xt_rateest.h b/include/net/netfilter/xt_rateest.h
index ddbf37e..5e14277 100644
--- a/include/net/netfilter/xt_rateest.h
+++ b/include/net/netfilter/xt_rateest.h
@@ -9,6 +9,7 @@  struct xt_rateest {
 	struct gnet_estimator		params;
 	struct gnet_stats_rate_est	rstats;
 	struct gnet_stats_basic_packed	bstats;
+	struct rcu_head			rcu;
 };
 
 extern struct xt_rateest *xt_rateest_lookup(const char *name);
diff --git a/net/core/gen_estimator.c b/net/core/gen_estimator.c
index 785e527..9fbe7f7 100644
--- a/net/core/gen_estimator.c
+++ b/net/core/gen_estimator.c
@@ -263,6 +263,7 @@  static void __gen_kill_estimator(struct rcu_head *head)
  *
  * Removes the rate estimator specified by &bstats and &rate_est.
  *
+ * 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_rate_est *rate_est)
diff --git a/net/netfilter/xt_RATEEST.c b/net/netfilter/xt_RATEEST.c
index 69c01e1..096b18b 100644
--- a/net/netfilter/xt_RATEEST.c
+++ b/net/netfilter/xt_RATEEST.c
@@ -60,13 +60,18 @@  struct xt_rateest *xt_rateest_lookup(const char *name)
 }
 EXPORT_SYMBOL_GPL(xt_rateest_lookup);
 
+static void xt_rateeset_free_rcu(struct rcu_head *head)
+{
+	kfree(container_of(head, struct xt_rateest, rcu));
+}
+
 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);
-		kfree(est);
+		call_rcu(&est->rcu, xt_rateeset_free_rcu);
 	}
 	mutex_unlock(&xt_rateest_mutex);
 }
@@ -179,6 +184,7 @@  static int __init xt_rateest_tg_init(void)
 static void __exit xt_rateest_tg_fini(void)
 {
 	xt_unregister_target(&xt_rateest_tg_reg);
+	rcu_barrier(); /* Wait for completion of call_rcu()'s */
 }
 
 
diff --git a/net/sched/act_api.c b/net/sched/act_api.c
index 972378f..0e6fd2b 100644
--- a/net/sched/act_api.c
+++ b/net/sched/act_api.c
@@ -26,6 +26,11 @@ 
 #include <net/act_api.h>
 #include <net/netlink.h>
 
+static void tcf_common_free_rcu(struct rcu_head *head)
+{
+	kfree(container_of(head, struct tcf_common, tcfc_rcu));
+}
+
 void tcf_hash_destroy(struct tcf_common *p, struct tcf_hashinfo *hinfo)
 {
 	unsigned int h = tcf_hash(p->tcfc_index, hinfo->hmask);
@@ -38,7 +43,7 @@  void tcf_hash_destroy(struct tcf_common *p, struct tcf_hashinfo *hinfo)
 			write_unlock_bh(hinfo->lock);
 			gen_kill_estimator(&p->tcfc_bstats,
 					   &p->tcfc_rate_est);
-			kfree(p);
+			call_rcu(&p->tcfc_rcu, tcf_common_free_rcu);
 			return;
 		}
 	}
diff --git a/net/sched/act_police.c b/net/sched/act_police.c
index 654f73d..04929ce 100644
--- a/net/sched/act_police.c
+++ b/net/sched/act_police.c
@@ -97,6 +97,11 @@  nla_put_failure:
 	goto done;
 }
 
+static void tcf_police_free_rcu(struct rcu_head *head)
+{
+	kfree(container_of(head, struct tcf_police, tcf_rcu));
+}
+
 static void tcf_police_destroy(struct tcf_police *p)
 {
 	unsigned int h = tcf_hash(p->tcf_index, POL_TAB_MASK);
@@ -113,7 +118,7 @@  static void tcf_police_destroy(struct tcf_police *p)
 				qdisc_put_rtab(p->tcfp_R_tab);
 			if (p->tcfp_P_tab)
 				qdisc_put_rtab(p->tcfp_P_tab);
-			kfree(p);
+			call_rcu(&p->tcf_rcu, tcf_police_free_rcu);
 			return;
 		}
 	}
@@ -397,6 +402,7 @@  static void __exit
 police_cleanup_module(void)
 {
 	tcf_unregister_action(&act_police_ops);
+	rcu_barrier(); /* Wait for completion of call_rcu()'s */
 }
 
 module_init(police_init_module);