From 50317fce2cc70a2bbbc4b42c31bbad510382a53c Mon Sep 17 00:00:00 2001 From: Cong Wang Date: Fri, 27 Oct 2017 22:08:56 -0700 Subject: net_sched: avoid matching qdisc with zero handle Davide found the following script triggers a NULL pointer dereference: ip l a name eth0 type dummy tc q a dev eth0 parent :1 handle 1: htb This is because for a freshly created netdevice noop_qdisc is attached and when passing 'parent :1', kernel actually tries to match the major handle which is 0 and noop_qdisc has handle 0 so is matched by mistake. Commit 69012ae425d7 tries to fix a similar bug but still misses this case. Handle 0 is not a valid one, should be just skipped. In fact, kernel uses it as TC_H_UNSPEC. Fixes: 69012ae425d7 ("net: sched: fix handling of singleton qdiscs with qdisc_hash") Fixes: 59cc1f61f09c ("net: sched:convert qdisc linked list to hashtable") Reported-by: Davide Caratti Cc: Jiri Kosina Cc: Eric Dumazet Cc: Jamal Hadi Salim Signed-off-by: Cong Wang Signed-off-by: David S. Miller --- net/sched/sch_api.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'net/sched') diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c index c6deb74e3d2f..22bc6fc48311 100644 --- a/net/sched/sch_api.c +++ b/net/sched/sch_api.c @@ -301,6 +301,8 @@ struct Qdisc *qdisc_lookup(struct net_device *dev, u32 handle) { struct Qdisc *q; + if (!handle) + return NULL; q = qdisc_match_from_root(dev->qdisc, handle); if (q) goto out; -- cgit v1.2.3 From 7aa0045dadb6ef37485ea9f2a7d28278ca588b51 Mon Sep 17 00:00:00 2001 From: Cong Wang Date: Thu, 26 Oct 2017 18:24:28 -0700 Subject: net_sched: introduce a workqueue for RCU callbacks of tc filter This patch introduces a dedicated workqueue for tc filters so that each tc filter's RCU callback could defer their action destroy work to this workqueue. The helper tcf_queue_work() is introduced for them to use. Because we hold RTNL lock when calling tcf_block_put(), we can not simply flush works inside it, therefore we have to defer it again to this workqueue and make sure all flying RCU callbacks have already queued their work before this one, in other words, to ensure this is the last one to execute to prevent any use-after-free. On the other hand, this makes tcf_block_put() ugly and harder to understand. Since David and Eric strongly dislike adding synchronize_rcu(), this is probably the only solution that could make everyone happy. Please also see the code comments below. Reported-by: Chris Mi Cc: Daniel Borkmann Cc: Jiri Pirko Cc: John Fastabend Cc: Jamal Hadi Salim Cc: "Paul E. McKenney" Signed-off-by: Cong Wang Signed-off-by: David S. Miller --- net/sched/cls_api.c | 68 +++++++++++++++++++++++++++++++++++++++-------------- 1 file changed, 51 insertions(+), 17 deletions(-) (limited to 'net/sched') diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c index 0b2219adf520..045d13679ad6 100644 --- a/net/sched/cls_api.c +++ b/net/sched/cls_api.c @@ -77,6 +77,8 @@ out: } EXPORT_SYMBOL(register_tcf_proto_ops); +static struct workqueue_struct *tc_filter_wq; + int unregister_tcf_proto_ops(struct tcf_proto_ops *ops) { struct tcf_proto_ops *t; @@ -86,6 +88,7 @@ int unregister_tcf_proto_ops(struct tcf_proto_ops *ops) * tcf_proto_ops's destroy() handler. */ rcu_barrier(); + flush_workqueue(tc_filter_wq); write_lock(&cls_mod_lock); list_for_each_entry(t, &tcf_proto_base, head) { @@ -100,6 +103,12 @@ int unregister_tcf_proto_ops(struct tcf_proto_ops *ops) } EXPORT_SYMBOL(unregister_tcf_proto_ops); +bool tcf_queue_work(struct work_struct *work) +{ + return queue_work(tc_filter_wq, work); +} +EXPORT_SYMBOL(tcf_queue_work); + /* Select new prio value from the range, managed by kernel. */ static inline u32 tcf_auto_prio(struct tcf_proto *tp) @@ -266,23 +275,30 @@ err_chain_create: } EXPORT_SYMBOL(tcf_block_get); -void tcf_block_put(struct tcf_block *block) +static void tcf_block_put_final(struct work_struct *work) { + struct tcf_block *block = container_of(work, struct tcf_block, work); struct tcf_chain *chain, *tmp; - if (!block) - return; - - /* XXX: Standalone actions are not allowed to jump to any chain, and - * bound actions should be all removed after flushing. However, - * filters are destroyed in RCU callbacks, we have to hold the chains - * first, otherwise we would always race with RCU callbacks on this list - * without proper locking. - */ + /* At this point, all the chains should have refcnt == 1. */ + rtnl_lock(); + list_for_each_entry_safe(chain, tmp, &block->chain_list, list) + tcf_chain_put(chain); + rtnl_unlock(); + kfree(block); +} - /* Wait for existing RCU callbacks to cool down. */ - rcu_barrier(); +/* XXX: Standalone actions are not allowed to jump to any chain, and bound + * actions should be all removed after flushing. However, filters are destroyed + * in RCU callbacks, we have to hold the chains first, otherwise we would + * always race with RCU callbacks on this list without proper locking. + */ +static void tcf_block_put_deferred(struct work_struct *work) +{ + struct tcf_block *block = container_of(work, struct tcf_block, work); + struct tcf_chain *chain; + rtnl_lock(); /* Hold a refcnt for all chains, except 0, in case they are gone. */ list_for_each_entry(chain, &block->chain_list, list) if (chain->index) @@ -292,13 +308,27 @@ void tcf_block_put(struct tcf_block *block) list_for_each_entry(chain, &block->chain_list, list) tcf_chain_flush(chain); - /* Wait for RCU callbacks to release the reference count. */ + INIT_WORK(&block->work, tcf_block_put_final); + /* Wait for RCU callbacks to release the reference count and make + * sure their works have been queued before this. + */ rcu_barrier(); + tcf_queue_work(&block->work); + rtnl_unlock(); +} - /* At this point, all the chains should have refcnt == 1. */ - list_for_each_entry_safe(chain, tmp, &block->chain_list, list) - tcf_chain_put(chain); - kfree(block); +void tcf_block_put(struct tcf_block *block) +{ + if (!block) + return; + + INIT_WORK(&block->work, tcf_block_put_deferred); + /* Wait for existing RCU callbacks to cool down, make sure their works + * have been queued before this. We can not flush pending works here + * because we are holding the RTNL lock. + */ + rcu_barrier(); + tcf_queue_work(&block->work); } EXPORT_SYMBOL(tcf_block_put); @@ -1030,6 +1060,10 @@ EXPORT_SYMBOL(tcf_exts_get_dev); static int __init tc_filter_init(void) { + tc_filter_wq = alloc_ordered_workqueue("tc_filter_workqueue", 0); + if (!tc_filter_wq) + return -ENOMEM; + rtnl_register(PF_UNSPEC, RTM_NEWTFILTER, tc_ctl_tfilter, NULL, 0); rtnl_register(PF_UNSPEC, RTM_DELTFILTER, tc_ctl_tfilter, NULL, 0); rtnl_register(PF_UNSPEC, RTM_GETTFILTER, tc_ctl_tfilter, -- cgit v1.2.3 From c96a48385d53089ee9977dd0bce82a9493984484 Mon Sep 17 00:00:00 2001 From: Cong Wang Date: Thu, 26 Oct 2017 18:24:29 -0700 Subject: net_sched: use tcf_queue_work() in basic filter Defer the tcf_exts_destroy() in RCU callback to tc filter workqueue and get RTNL lock. Reported-by: Chris Mi Cc: Daniel Borkmann Cc: Jiri Pirko Cc: John Fastabend Cc: Jamal Hadi Salim Cc: "Paul E. McKenney" Signed-off-by: Cong Wang Signed-off-by: David S. Miller --- net/sched/cls_basic.c | 20 +++++++++++++++++--- 1 file changed, 17 insertions(+), 3 deletions(-) (limited to 'net/sched') diff --git a/net/sched/cls_basic.c b/net/sched/cls_basic.c index d89ebafd2239..f177649a2419 100644 --- a/net/sched/cls_basic.c +++ b/net/sched/cls_basic.c @@ -34,7 +34,10 @@ struct basic_filter { struct tcf_result res; struct tcf_proto *tp; struct list_head link; - struct rcu_head rcu; + union { + struct work_struct work; + struct rcu_head rcu; + }; }; static int basic_classify(struct sk_buff *skb, const struct tcf_proto *tp, @@ -82,15 +85,26 @@ static int basic_init(struct tcf_proto *tp) return 0; } -static void basic_delete_filter(struct rcu_head *head) +static void basic_delete_filter_work(struct work_struct *work) { - struct basic_filter *f = container_of(head, struct basic_filter, rcu); + struct basic_filter *f = container_of(work, struct basic_filter, work); + rtnl_lock(); tcf_exts_destroy(&f->exts); tcf_em_tree_destroy(&f->ematches); + rtnl_unlock(); + kfree(f); } +static void basic_delete_filter(struct rcu_head *head) +{ + struct basic_filter *f = container_of(head, struct basic_filter, rcu); + + INIT_WORK(&f->work, basic_delete_filter_work); + tcf_queue_work(&f->work); +} + static void basic_destroy(struct tcf_proto *tp) { struct basic_head *head = rtnl_dereference(tp->root); -- cgit v1.2.3 From e910af676b565ecc16bcd6c896ecb68157396ecc Mon Sep 17 00:00:00 2001 From: Cong Wang Date: Thu, 26 Oct 2017 18:24:30 -0700 Subject: net_sched: use tcf_queue_work() in bpf filter Defer the tcf_exts_destroy() in RCU callback to tc filter workqueue and get RTNL lock. Reported-by: Chris Mi Cc: Daniel Borkmann Cc: Jiri Pirko Cc: John Fastabend Cc: Jamal Hadi Salim Cc: "Paul E. McKenney" Signed-off-by: Cong Wang Signed-off-by: David S. Miller --- net/sched/cls_bpf.c | 19 +++++++++++++++++-- 1 file changed, 17 insertions(+), 2 deletions(-) (limited to 'net/sched') diff --git a/net/sched/cls_bpf.c b/net/sched/cls_bpf.c index 520c5027646a..037a3ae86829 100644 --- a/net/sched/cls_bpf.c +++ b/net/sched/cls_bpf.c @@ -49,7 +49,10 @@ struct cls_bpf_prog { struct sock_filter *bpf_ops; const char *bpf_name; struct tcf_proto *tp; - struct rcu_head rcu; + union { + struct work_struct work; + struct rcu_head rcu; + }; }; static const struct nla_policy bpf_policy[TCA_BPF_MAX + 1] = { @@ -257,9 +260,21 @@ static void __cls_bpf_delete_prog(struct cls_bpf_prog *prog) kfree(prog); } +static void cls_bpf_delete_prog_work(struct work_struct *work) +{ + struct cls_bpf_prog *prog = container_of(work, struct cls_bpf_prog, work); + + rtnl_lock(); + __cls_bpf_delete_prog(prog); + rtnl_unlock(); +} + static void cls_bpf_delete_prog_rcu(struct rcu_head *rcu) { - __cls_bpf_delete_prog(container_of(rcu, struct cls_bpf_prog, rcu)); + struct cls_bpf_prog *prog = container_of(rcu, struct cls_bpf_prog, rcu); + + INIT_WORK(&prog->work, cls_bpf_delete_prog_work); + tcf_queue_work(&prog->work); } static void __cls_bpf_delete(struct tcf_proto *tp, struct cls_bpf_prog *prog) -- cgit v1.2.3 From b1b5b04fdb6da262aef37ef83b9f2e41326720ef Mon Sep 17 00:00:00 2001 From: Cong Wang Date: Thu, 26 Oct 2017 18:24:31 -0700 Subject: net_sched: use tcf_queue_work() in cgroup filter Defer the tcf_exts_destroy() in RCU callback to tc filter workqueue and get RTNL lock. Reported-by: Chris Mi Cc: Daniel Borkmann Cc: Jiri Pirko Cc: John Fastabend Cc: Jamal Hadi Salim Cc: "Paul E. McKenney" Signed-off-by: Cong Wang Signed-off-by: David S. Miller --- net/sched/cls_cgroup.c | 22 ++++++++++++++++++---- 1 file changed, 18 insertions(+), 4 deletions(-) (limited to 'net/sched') diff --git a/net/sched/cls_cgroup.c b/net/sched/cls_cgroup.c index d48452f87975..a97e069bee89 100644 --- a/net/sched/cls_cgroup.c +++ b/net/sched/cls_cgroup.c @@ -23,7 +23,10 @@ struct cls_cgroup_head { struct tcf_exts exts; struct tcf_ematch_tree ematches; struct tcf_proto *tp; - struct rcu_head rcu; + union { + struct work_struct work; + struct rcu_head rcu; + }; }; static int cls_cgroup_classify(struct sk_buff *skb, const struct tcf_proto *tp, @@ -57,15 +60,26 @@ static const struct nla_policy cgroup_policy[TCA_CGROUP_MAX + 1] = { [TCA_CGROUP_EMATCHES] = { .type = NLA_NESTED }, }; +static void cls_cgroup_destroy_work(struct work_struct *work) +{ + struct cls_cgroup_head *head = container_of(work, + struct cls_cgroup_head, + work); + rtnl_lock(); + tcf_exts_destroy(&head->exts); + tcf_em_tree_destroy(&head->ematches); + kfree(head); + rtnl_unlock(); +} + static void cls_cgroup_destroy_rcu(struct rcu_head *root) { struct cls_cgroup_head *head = container_of(root, struct cls_cgroup_head, rcu); - tcf_exts_destroy(&head->exts); - tcf_em_tree_destroy(&head->ematches); - kfree(head); + INIT_WORK(&head->work, cls_cgroup_destroy_work); + tcf_queue_work(&head->work); } static int cls_cgroup_change(struct net *net, struct sk_buff *in_skb, -- cgit v1.2.3 From 94cdb47566b799649e996e1fb9de2a503dada763 Mon Sep 17 00:00:00 2001 From: Cong Wang Date: Thu, 26 Oct 2017 18:24:32 -0700 Subject: net_sched: use tcf_queue_work() in flow filter Defer the tcf_exts_destroy() in RCU callback to tc filter workqueue and get RTNL lock. Reported-by: Chris Mi Cc: Daniel Borkmann Cc: Jiri Pirko Cc: John Fastabend Cc: Jamal Hadi Salim Cc: "Paul E. McKenney" Signed-off-by: Cong Wang Signed-off-by: David S. Miller --- net/sched/cls_flow.c | 19 ++++++++++++++++--- 1 file changed, 16 insertions(+), 3 deletions(-) (limited to 'net/sched') diff --git a/net/sched/cls_flow.c b/net/sched/cls_flow.c index 2a3a60ec5b86..67f3a2af6aab 100644 --- a/net/sched/cls_flow.c +++ b/net/sched/cls_flow.c @@ -57,7 +57,10 @@ struct flow_filter { u32 divisor; u32 baseclass; u32 hashrnd; - struct rcu_head rcu; + union { + struct work_struct work; + struct rcu_head rcu; + }; }; static inline u32 addr_fold(void *addr) @@ -369,14 +372,24 @@ static const struct nla_policy flow_policy[TCA_FLOW_MAX + 1] = { [TCA_FLOW_PERTURB] = { .type = NLA_U32 }, }; -static void flow_destroy_filter(struct rcu_head *head) +static void flow_destroy_filter_work(struct work_struct *work) { - struct flow_filter *f = container_of(head, struct flow_filter, rcu); + struct flow_filter *f = container_of(work, struct flow_filter, work); + rtnl_lock(); del_timer_sync(&f->perturb_timer); tcf_exts_destroy(&f->exts); tcf_em_tree_destroy(&f->ematches); kfree(f); + rtnl_unlock(); +} + +static void flow_destroy_filter(struct rcu_head *head) +{ + struct flow_filter *f = container_of(head, struct flow_filter, rcu); + + INIT_WORK(&f->work, flow_destroy_filter_work); + tcf_queue_work(&f->work); } static int flow_change(struct net *net, struct sk_buff *in_skb, -- cgit v1.2.3 From 0552c8afa077889b4704ef5ee88b03063ad45023 Mon Sep 17 00:00:00 2001 From: Cong Wang Date: Thu, 26 Oct 2017 18:24:33 -0700 Subject: net_sched: use tcf_queue_work() in flower filter Defer the tcf_exts_destroy() in RCU callback to tc filter workqueue and get RTNL lock. Reported-by: Chris Mi Cc: Daniel Borkmann Cc: Jiri Pirko Cc: John Fastabend Cc: Jamal Hadi Salim Cc: "Paul E. McKenney" Signed-off-by: Cong Wang Signed-off-by: David S. Miller --- net/sched/cls_flower.c | 19 ++++++++++++++++--- 1 file changed, 16 insertions(+), 3 deletions(-) (limited to 'net/sched') diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c index b480d7c792ba..5b5722c8b32c 100644 --- a/net/sched/cls_flower.c +++ b/net/sched/cls_flower.c @@ -87,7 +87,10 @@ struct cls_fl_filter { struct list_head list; u32 handle; u32 flags; - struct rcu_head rcu; + union { + struct work_struct work; + struct rcu_head rcu; + }; struct net_device *hw_dev; }; @@ -215,12 +218,22 @@ static int fl_init(struct tcf_proto *tp) return 0; } -static void fl_destroy_filter(struct rcu_head *head) +static void fl_destroy_filter_work(struct work_struct *work) { - struct cls_fl_filter *f = container_of(head, struct cls_fl_filter, rcu); + struct cls_fl_filter *f = container_of(work, struct cls_fl_filter, work); + rtnl_lock(); tcf_exts_destroy(&f->exts); kfree(f); + rtnl_unlock(); +} + +static void fl_destroy_filter(struct rcu_head *head) +{ + struct cls_fl_filter *f = container_of(head, struct cls_fl_filter, rcu); + + INIT_WORK(&f->work, fl_destroy_filter_work); + tcf_queue_work(&f->work); } static void fl_hw_destroy_filter(struct tcf_proto *tp, struct cls_fl_filter *f) -- cgit v1.2.3 From e071dff2a6beeccb6f9744f9a0251ab773ca2ab8 Mon Sep 17 00:00:00 2001 From: Cong Wang Date: Thu, 26 Oct 2017 18:24:34 -0700 Subject: net_sched: use tcf_queue_work() in fw filter Defer the tcf_exts_destroy() in RCU callback to tc filter workqueue and get RTNL lock. Reported-by: Chris Mi Cc: Daniel Borkmann Cc: Jiri Pirko Cc: John Fastabend Cc: Jamal Hadi Salim Cc: "Paul E. McKenney" Signed-off-by: Cong Wang Signed-off-by: David S. Miller --- net/sched/cls_fw.c | 19 ++++++++++++++++--- 1 file changed, 16 insertions(+), 3 deletions(-) (limited to 'net/sched') diff --git a/net/sched/cls_fw.c b/net/sched/cls_fw.c index 941245ad07fd..99183b8621ec 100644 --- a/net/sched/cls_fw.c +++ b/net/sched/cls_fw.c @@ -46,7 +46,10 @@ struct fw_filter { #endif /* CONFIG_NET_CLS_IND */ struct tcf_exts exts; struct tcf_proto *tp; - struct rcu_head rcu; + union { + struct work_struct work; + struct rcu_head rcu; + }; }; static u32 fw_hash(u32 handle) @@ -119,12 +122,22 @@ static int fw_init(struct tcf_proto *tp) return 0; } -static void fw_delete_filter(struct rcu_head *head) +static void fw_delete_filter_work(struct work_struct *work) { - struct fw_filter *f = container_of(head, struct fw_filter, rcu); + struct fw_filter *f = container_of(work, struct fw_filter, work); + rtnl_lock(); tcf_exts_destroy(&f->exts); kfree(f); + rtnl_unlock(); +} + +static void fw_delete_filter(struct rcu_head *head) +{ + struct fw_filter *f = container_of(head, struct fw_filter, rcu); + + INIT_WORK(&f->work, fw_delete_filter_work); + tcf_queue_work(&f->work); } static void fw_destroy(struct tcf_proto *tp) -- cgit v1.2.3 From df2735ee8e6ca202a8630f237b59401a25193be1 Mon Sep 17 00:00:00 2001 From: Cong Wang Date: Thu, 26 Oct 2017 18:24:35 -0700 Subject: net_sched: use tcf_queue_work() in matchall filter Defer the tcf_exts_destroy() in RCU callback to tc filter workqueue and get RTNL lock. Reported-by: Chris Mi Cc: Daniel Borkmann Cc: Jiri Pirko Cc: John Fastabend Cc: Jamal Hadi Salim Cc: "Paul E. McKenney" Signed-off-by: Cong Wang Signed-off-by: David S. Miller --- net/sched/cls_matchall.c | 19 ++++++++++++++++--- 1 file changed, 16 insertions(+), 3 deletions(-) (limited to 'net/sched') diff --git a/net/sched/cls_matchall.c b/net/sched/cls_matchall.c index eeac606c95ab..c33f711b9019 100644 --- a/net/sched/cls_matchall.c +++ b/net/sched/cls_matchall.c @@ -21,7 +21,10 @@ struct cls_mall_head { struct tcf_result res; u32 handle; u32 flags; - struct rcu_head rcu; + union { + struct work_struct work; + struct rcu_head rcu; + }; }; static int mall_classify(struct sk_buff *skb, const struct tcf_proto *tp, @@ -41,13 +44,23 @@ static int mall_init(struct tcf_proto *tp) return 0; } +static void mall_destroy_work(struct work_struct *work) +{ + struct cls_mall_head *head = container_of(work, struct cls_mall_head, + work); + rtnl_lock(); + tcf_exts_destroy(&head->exts); + kfree(head); + rtnl_unlock(); +} + static void mall_destroy_rcu(struct rcu_head *rcu) { struct cls_mall_head *head = container_of(rcu, struct cls_mall_head, rcu); - tcf_exts_destroy(&head->exts); - kfree(head); + INIT_WORK(&head->work, mall_destroy_work); + tcf_queue_work(&head->work); } static int mall_replace_hw_filter(struct tcf_proto *tp, -- cgit v1.2.3 From c0d378ef1266546a39f2df00a56ff1f74166a2b7 Mon Sep 17 00:00:00 2001 From: Cong Wang Date: Thu, 26 Oct 2017 18:24:36 -0700 Subject: net_sched: use tcf_queue_work() in u32 filter Defer the tcf_exts_destroy() in RCU callback to tc filter workqueue and get RTNL lock. Reported-by: Chris Mi Cc: Daniel Borkmann Cc: Jiri Pirko Cc: John Fastabend Cc: Jamal Hadi Salim Cc: "Paul E. McKenney" Signed-off-by: Cong Wang Signed-off-by: David S. Miller --- net/sched/cls_u32.c | 29 ++++++++++++++++++++++++++--- 1 file changed, 26 insertions(+), 3 deletions(-) (limited to 'net/sched') diff --git a/net/sched/cls_u32.c b/net/sched/cls_u32.c index 10b8d851fc6b..dadd1b344497 100644 --- a/net/sched/cls_u32.c +++ b/net/sched/cls_u32.c @@ -68,7 +68,10 @@ struct tc_u_knode { u32 __percpu *pcpu_success; #endif struct tcf_proto *tp; - struct rcu_head rcu; + union { + struct work_struct work; + struct rcu_head rcu; + }; /* The 'sel' field MUST be the last field in structure to allow for * tc_u32_keys allocated at end of structure. */ @@ -418,11 +421,21 @@ static int u32_destroy_key(struct tcf_proto *tp, struct tc_u_knode *n, * this the u32_delete_key_rcu variant does not free the percpu * statistics. */ +static void u32_delete_key_work(struct work_struct *work) +{ + struct tc_u_knode *key = container_of(work, struct tc_u_knode, work); + + rtnl_lock(); + u32_destroy_key(key->tp, key, false); + rtnl_unlock(); +} + static void u32_delete_key_rcu(struct rcu_head *rcu) { struct tc_u_knode *key = container_of(rcu, struct tc_u_knode, rcu); - u32_destroy_key(key->tp, key, false); + INIT_WORK(&key->work, u32_delete_key_work); + tcf_queue_work(&key->work); } /* u32_delete_key_freepf_rcu is the rcu callback variant @@ -432,11 +445,21 @@ static void u32_delete_key_rcu(struct rcu_head *rcu) * for the variant that should be used with keys return from * u32_init_knode() */ +static void u32_delete_key_freepf_work(struct work_struct *work) +{ + struct tc_u_knode *key = container_of(work, struct tc_u_knode, work); + + rtnl_lock(); + u32_destroy_key(key->tp, key, true); + rtnl_unlock(); +} + static void u32_delete_key_freepf_rcu(struct rcu_head *rcu) { struct tc_u_knode *key = container_of(rcu, struct tc_u_knode, rcu); - u32_destroy_key(key->tp, key, true); + INIT_WORK(&key->work, u32_delete_key_freepf_work); + tcf_queue_work(&key->work); } static int u32_delete_key(struct tcf_proto *tp, struct tc_u_knode *key) -- cgit v1.2.3 From c2f3f31d402be4849b06282c3a5278f2865c9fcc Mon Sep 17 00:00:00 2001 From: Cong Wang Date: Thu, 26 Oct 2017 18:24:37 -0700 Subject: net_sched: use tcf_queue_work() in route filter Defer the tcf_exts_destroy() in RCU callback to tc filter workqueue and get RTNL lock. Reported-by: Chris Mi Cc: Daniel Borkmann Cc: Jiri Pirko Cc: John Fastabend Cc: Jamal Hadi Salim Cc: "Paul E. McKenney" Signed-off-by: Cong Wang Signed-off-by: David S. Miller --- net/sched/cls_route.c | 19 ++++++++++++++++--- 1 file changed, 16 insertions(+), 3 deletions(-) (limited to 'net/sched') diff --git a/net/sched/cls_route.c b/net/sched/cls_route.c index 9ddde65915d2..4b14ccd8b8f2 100644 --- a/net/sched/cls_route.c +++ b/net/sched/cls_route.c @@ -57,7 +57,10 @@ struct route4_filter { u32 handle; struct route4_bucket *bkt; struct tcf_proto *tp; - struct rcu_head rcu; + union { + struct work_struct work; + struct rcu_head rcu; + }; }; #define ROUTE4_FAILURE ((struct route4_filter *)(-1L)) @@ -254,12 +257,22 @@ static int route4_init(struct tcf_proto *tp) return 0; } -static void route4_delete_filter(struct rcu_head *head) +static void route4_delete_filter_work(struct work_struct *work) { - struct route4_filter *f = container_of(head, struct route4_filter, rcu); + struct route4_filter *f = container_of(work, struct route4_filter, work); + rtnl_lock(); tcf_exts_destroy(&f->exts); kfree(f); + rtnl_unlock(); +} + +static void route4_delete_filter(struct rcu_head *head) +{ + struct route4_filter *f = container_of(head, struct route4_filter, rcu); + + INIT_WORK(&f->work, route4_delete_filter_work); + tcf_queue_work(&f->work); } static void route4_destroy(struct tcf_proto *tp) -- cgit v1.2.3 From d4f84a41dc615c166555cd332b0235bf6b9bcb4a Mon Sep 17 00:00:00 2001 From: Cong Wang Date: Thu, 26 Oct 2017 18:24:38 -0700 Subject: net_sched: use tcf_queue_work() in rsvp filter Defer the tcf_exts_destroy() in RCU callback to tc filter workqueue and get RTNL lock. Reported-by: Chris Mi Cc: Daniel Borkmann Cc: Jiri Pirko Cc: John Fastabend Cc: Jamal Hadi Salim Cc: "Paul E. McKenney" Signed-off-by: Cong Wang Signed-off-by: David S. Miller --- net/sched/cls_rsvp.h | 19 ++++++++++++++++--- 1 file changed, 16 insertions(+), 3 deletions(-) (limited to 'net/sched') diff --git a/net/sched/cls_rsvp.h b/net/sched/cls_rsvp.h index b1f6ed48bc72..bdbc541787f8 100644 --- a/net/sched/cls_rsvp.h +++ b/net/sched/cls_rsvp.h @@ -97,7 +97,10 @@ struct rsvp_filter { u32 handle; struct rsvp_session *sess; - struct rcu_head rcu; + union { + struct work_struct work; + struct rcu_head rcu; + }; }; static inline unsigned int hash_dst(__be32 *dst, u8 protocol, u8 tunnelid) @@ -282,12 +285,22 @@ static int rsvp_init(struct tcf_proto *tp) return -ENOBUFS; } -static void rsvp_delete_filter_rcu(struct rcu_head *head) +static void rsvp_delete_filter_work(struct work_struct *work) { - struct rsvp_filter *f = container_of(head, struct rsvp_filter, rcu); + struct rsvp_filter *f = container_of(work, struct rsvp_filter, work); + rtnl_lock(); tcf_exts_destroy(&f->exts); kfree(f); + rtnl_unlock(); +} + +static void rsvp_delete_filter_rcu(struct rcu_head *head) +{ + struct rsvp_filter *f = container_of(head, struct rsvp_filter, rcu); + + INIT_WORK(&f->work, rsvp_delete_filter_work); + tcf_queue_work(&f->work); } static void rsvp_delete_filter(struct tcf_proto *tp, struct rsvp_filter *f) -- cgit v1.2.3 From 27ce4f05e2abbe2d3ec7434e456619a5178cd3bd Mon Sep 17 00:00:00 2001 From: Cong Wang Date: Thu, 26 Oct 2017 18:24:39 -0700 Subject: net_sched: use tcf_queue_work() in tcindex filter Defer the tcf_exts_destroy() in RCU callback to tc filter workqueue and get RTNL lock. Reported-by: Chris Mi Cc: Daniel Borkmann Cc: Jiri Pirko Cc: John Fastabend Cc: Jamal Hadi Salim Cc: "Paul E. McKenney" Signed-off-by: Cong Wang Signed-off-by: David S. Miller --- net/sched/cls_tcindex.c | 38 +++++++++++++++++++++++++++++++++----- 1 file changed, 33 insertions(+), 5 deletions(-) (limited to 'net/sched') diff --git a/net/sched/cls_tcindex.c b/net/sched/cls_tcindex.c index 14a7e08b2fa9..beaa95e09c25 100644 --- a/net/sched/cls_tcindex.c +++ b/net/sched/cls_tcindex.c @@ -27,14 +27,20 @@ struct tcindex_filter_result { struct tcf_exts exts; struct tcf_result res; - struct rcu_head rcu; + union { + struct work_struct work; + struct rcu_head rcu; + }; }; struct tcindex_filter { u16 key; struct tcindex_filter_result result; struct tcindex_filter __rcu *next; - struct rcu_head rcu; + union { + struct work_struct work; + struct rcu_head rcu; + }; }; @@ -133,12 +139,34 @@ static int tcindex_init(struct tcf_proto *tp) return 0; } +static void tcindex_destroy_rexts_work(struct work_struct *work) +{ + struct tcindex_filter_result *r; + + r = container_of(work, struct tcindex_filter_result, work); + rtnl_lock(); + tcf_exts_destroy(&r->exts); + rtnl_unlock(); +} + static void tcindex_destroy_rexts(struct rcu_head *head) { struct tcindex_filter_result *r; r = container_of(head, struct tcindex_filter_result, rcu); - tcf_exts_destroy(&r->exts); + INIT_WORK(&r->work, tcindex_destroy_rexts_work); + tcf_queue_work(&r->work); +} + +static void tcindex_destroy_fexts_work(struct work_struct *work) +{ + struct tcindex_filter *f = container_of(work, struct tcindex_filter, + work); + + rtnl_lock(); + tcf_exts_destroy(&f->result.exts); + kfree(f); + rtnl_unlock(); } static void tcindex_destroy_fexts(struct rcu_head *head) @@ -146,8 +174,8 @@ static void tcindex_destroy_fexts(struct rcu_head *head) struct tcindex_filter *f = container_of(head, struct tcindex_filter, rcu); - tcf_exts_destroy(&f->result.exts); - kfree(f); + INIT_WORK(&f->work, tcindex_destroy_fexts_work); + tcf_queue_work(&f->work); } static int tcindex_delete(struct tcf_proto *tp, void *arg, bool *last) -- cgit v1.2.3 From 2d132eba1d972ea6c0e47286e4c821b4a3c5b84d Mon Sep 17 00:00:00 2001 From: Cong Wang Date: Thu, 26 Oct 2017 18:24:40 -0700 Subject: net_sched: add rtnl assertion to tcf_exts_destroy() After previous patches, it is now safe to claim that tcf_exts_destroy() is always called with RTNL lock. Cc: Daniel Borkmann Cc: Jiri Pirko Cc: John Fastabend Cc: Jamal Hadi Salim Cc: "Paul E. McKenney" Signed-off-by: Cong Wang Signed-off-by: David S. Miller --- net/sched/cls_api.c | 1 + 1 file changed, 1 insertion(+) (limited to 'net/sched') diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c index 045d13679ad6..231181c602ed 100644 --- a/net/sched/cls_api.c +++ b/net/sched/cls_api.c @@ -909,6 +909,7 @@ void tcf_exts_destroy(struct tcf_exts *exts) #ifdef CONFIG_NET_CLS_ACT LIST_HEAD(actions); + ASSERT_RTNL(); tcf_exts_to_list(exts, &actions); tcf_action_destroy(&actions, TCA_ACT_UNBIND); kfree(exts->actions); -- cgit v1.2.3 From 46e235c15ca44f34cb79f4dbec909b8c51999dc1 Mon Sep 17 00:00:00 2001 From: Cong Wang Date: Thu, 26 Oct 2017 18:24:41 -0700 Subject: net_sched: fix call_rcu() race on act_sample module removal Similar to commit c78e1746d3ad ("net: sched: fix call_rcu() race on classifier module unloads"), we need to wait for flying RCU callback tcf_sample_cleanup_rcu(). Cc: Yotam Gigi Cc: Daniel Borkmann Cc: Jiri Pirko Cc: Jamal Hadi Salim Cc: "Paul E. McKenney" Signed-off-by: Cong Wang Signed-off-by: David S. Miller --- net/sched/act_sample.c | 1 + 1 file changed, 1 insertion(+) (limited to 'net/sched') diff --git a/net/sched/act_sample.c b/net/sched/act_sample.c index ec986ae52808..a9f9a2ccc664 100644 --- a/net/sched/act_sample.c +++ b/net/sched/act_sample.c @@ -264,6 +264,7 @@ static int __init sample_init_module(void) static void __exit sample_cleanup_module(void) { + rcu_barrier(); tcf_unregister_action(&act_sample_ops, &sample_net_ops); } -- cgit v1.2.3