* [PATCH net-next v4 17/17] net: sched: unlock rules update API
From: Vlad Buslov @ 2019-02-11 8:55 UTC (permalink / raw)
To: netdev; +Cc: jhs, xiyou.wangcong, jiri, davem, ast, daniel, Vlad Buslov
In-Reply-To: <20190211085548.7190-1-vladbu@mellanox.com>
Register netlink protocol handlers for message types RTM_NEWTFILTER,
RTM_DELTFILTER, RTM_GETTFILTER as unlocked. Set rtnl_held variable that
tracks rtnl mutex state to be false by default.
Introduce tcf_proto_is_unlocked() helper that is used to check
tcf_proto_ops->flag to determine if ops can be called without taking rtnl
lock. Manually lookup Qdisc, class and block in rule update handlers.
Verify that both Qdisc ops and proto ops are unlocked before using any of
their callbacks, and obtain rtnl lock otherwise.
Signed-off-by: Vlad Buslov <vladbu@mellanox.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
---
net/sched/cls_api.c | 131 +++++++++++++++++++++++++++++++++++++++++++++-------
1 file changed, 114 insertions(+), 17 deletions(-)
diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c
index 5f9373ee47ce..266fcb34fefe 100644
--- a/net/sched/cls_api.c
+++ b/net/sched/cls_api.c
@@ -163,6 +163,23 @@ static inline u32 tcf_auto_prio(struct tcf_proto *tp)
return TC_H_MAJ(first);
}
+static bool tcf_proto_is_unlocked(const char *kind)
+{
+ const struct tcf_proto_ops *ops;
+ bool ret;
+
+ ops = tcf_proto_lookup_ops(kind, false, NULL);
+ /* On error return false to take rtnl lock. Proto lookup/create
+ * functions will perform lookup again and properly handle errors.
+ */
+ if (IS_ERR(ops))
+ return false;
+
+ ret = !!(ops->flags & TCF_PROTO_OPS_DOIT_UNLOCKED);
+ module_put(ops->owner);
+ return ret;
+}
+
static struct tcf_proto *tcf_proto_create(const char *kind, u32 protocol,
u32 prio, struct tcf_chain *chain,
bool rtnl_held,
@@ -1312,8 +1329,12 @@ static void tcf_block_release(struct Qdisc *q, struct tcf_block *block,
if (!IS_ERR_OR_NULL(block))
tcf_block_refcnt_put(block, rtnl_held);
- if (q)
- qdisc_put(q);
+ if (q) {
+ if (rtnl_held)
+ qdisc_put(q);
+ else
+ qdisc_put_unlocked(q);
+ }
}
struct tcf_block_owner_item {
@@ -1966,7 +1987,7 @@ static int tc_new_tfilter(struct sk_buff *skb, struct nlmsghdr *n,
void *fh;
int err;
int tp_created;
- bool rtnl_held = true;
+ bool rtnl_held = false;
if (!netlink_ns_capable(skb, net->user_ns, CAP_NET_ADMIN))
return -EPERM;
@@ -1985,6 +2006,7 @@ static int tc_new_tfilter(struct sk_buff *skb, struct nlmsghdr *n,
parent = t->tcm_parent;
tp = NULL;
cl = 0;
+ block = NULL;
if (prio == 0) {
/* If no priority is provided by the user,
@@ -2001,8 +2023,27 @@ static int tc_new_tfilter(struct sk_buff *skb, struct nlmsghdr *n,
/* Find head of filter chain. */
- block = tcf_block_find(net, &q, &parent, &cl,
- t->tcm_ifindex, t->tcm_block_index, extack);
+ err = __tcf_qdisc_find(net, &q, &parent, t->tcm_ifindex, false, extack);
+ if (err)
+ return err;
+
+ /* Take rtnl mutex if rtnl_held was set to true on previous iteration,
+ * block is shared (no qdisc found), qdisc is not unlocked, classifier
+ * type is not specified, classifier is not unlocked.
+ */
+ if (rtnl_held ||
+ (q && !(q->ops->cl_ops->flags & QDISC_CLASS_OPS_DOIT_UNLOCKED)) ||
+ !tca[TCA_KIND] || !tcf_proto_is_unlocked(nla_data(tca[TCA_KIND]))) {
+ rtnl_held = true;
+ rtnl_lock();
+ }
+
+ err = __tcf_qdisc_cl_find(q, parent, &cl, t->tcm_ifindex, extack);
+ if (err)
+ goto errout;
+
+ block = __tcf_block_find(net, q, cl, t->tcm_ifindex, t->tcm_block_index,
+ extack);
if (IS_ERR(block)) {
err = PTR_ERR(block);
goto errout;
@@ -2123,9 +2164,18 @@ static int tc_new_tfilter(struct sk_buff *skb, struct nlmsghdr *n,
tcf_chain_put(chain);
}
tcf_block_release(q, block, rtnl_held);
- if (err == -EAGAIN)
+
+ if (rtnl_held)
+ rtnl_unlock();
+
+ if (err == -EAGAIN) {
+ /* Take rtnl lock in case EAGAIN is caused by concurrent flush
+ * of target chain.
+ */
+ rtnl_held = true;
/* Replay the request. */
goto replay;
+ }
return err;
errout_locked:
@@ -2146,12 +2196,12 @@ static int tc_del_tfilter(struct sk_buff *skb, struct nlmsghdr *n,
struct Qdisc *q = NULL;
struct tcf_chain_info chain_info;
struct tcf_chain *chain = NULL;
- struct tcf_block *block;
+ struct tcf_block *block = NULL;
struct tcf_proto *tp = NULL;
unsigned long cl = 0;
void *fh = NULL;
int err;
- bool rtnl_held = true;
+ bool rtnl_held = false;
if (!netlink_ns_capable(skb, net->user_ns, CAP_NET_ADMIN))
return -EPERM;
@@ -2172,8 +2222,27 @@ static int tc_del_tfilter(struct sk_buff *skb, struct nlmsghdr *n,
/* Find head of filter chain. */
- block = tcf_block_find(net, &q, &parent, &cl,
- t->tcm_ifindex, t->tcm_block_index, extack);
+ err = __tcf_qdisc_find(net, &q, &parent, t->tcm_ifindex, false, extack);
+ if (err)
+ return err;
+
+ /* Take rtnl mutex if flushing whole chain, block is shared (no qdisc
+ * found), qdisc is not unlocked, classifier type is not specified,
+ * classifier is not unlocked.
+ */
+ if (!prio ||
+ (q && !(q->ops->cl_ops->flags & QDISC_CLASS_OPS_DOIT_UNLOCKED)) ||
+ !tca[TCA_KIND] || !tcf_proto_is_unlocked(nla_data(tca[TCA_KIND]))) {
+ rtnl_held = true;
+ rtnl_lock();
+ }
+
+ err = __tcf_qdisc_cl_find(q, parent, &cl, t->tcm_ifindex, extack);
+ if (err)
+ goto errout;
+
+ block = __tcf_block_find(net, q, cl, t->tcm_ifindex, t->tcm_block_index,
+ extack);
if (IS_ERR(block)) {
err = PTR_ERR(block);
goto errout;
@@ -2255,6 +2324,10 @@ static int tc_del_tfilter(struct sk_buff *skb, struct nlmsghdr *n,
tcf_chain_put(chain);
}
tcf_block_release(q, block, rtnl_held);
+
+ if (rtnl_held)
+ rtnl_unlock();
+
return err;
errout_locked:
@@ -2275,12 +2348,12 @@ static int tc_get_tfilter(struct sk_buff *skb, struct nlmsghdr *n,
struct Qdisc *q = NULL;
struct tcf_chain_info chain_info;
struct tcf_chain *chain = NULL;
- struct tcf_block *block;
+ struct tcf_block *block = NULL;
struct tcf_proto *tp = NULL;
unsigned long cl = 0;
void *fh = NULL;
int err;
- bool rtnl_held = true;
+ bool rtnl_held = false;
err = nlmsg_parse(n, sizeof(*t), tca, TCA_MAX, rtm_tca_policy, extack);
if (err < 0)
@@ -2298,8 +2371,26 @@ static int tc_get_tfilter(struct sk_buff *skb, struct nlmsghdr *n,
/* Find head of filter chain. */
- block = tcf_block_find(net, &q, &parent, &cl,
- t->tcm_ifindex, t->tcm_block_index, extack);
+ err = __tcf_qdisc_find(net, &q, &parent, t->tcm_ifindex, false, extack);
+ if (err)
+ return err;
+
+ /* Take rtnl mutex if block is shared (no qdisc found), qdisc is not
+ * unlocked, classifier type is not specified, classifier is not
+ * unlocked.
+ */
+ if ((q && !(q->ops->cl_ops->flags & QDISC_CLASS_OPS_DOIT_UNLOCKED)) ||
+ !tca[TCA_KIND] || !tcf_proto_is_unlocked(nla_data(tca[TCA_KIND]))) {
+ rtnl_held = true;
+ rtnl_lock();
+ }
+
+ err = __tcf_qdisc_cl_find(q, parent, &cl, t->tcm_ifindex, extack);
+ if (err)
+ goto errout;
+
+ block = __tcf_block_find(net, q, cl, t->tcm_ifindex, t->tcm_block_index,
+ extack);
if (IS_ERR(block)) {
err = PTR_ERR(block);
goto errout;
@@ -2352,6 +2443,10 @@ static int tc_get_tfilter(struct sk_buff *skb, struct nlmsghdr *n,
tcf_chain_put(chain);
}
tcf_block_release(q, block, rtnl_held);
+
+ if (rtnl_held)
+ rtnl_unlock();
+
return err;
}
@@ -3214,10 +3309,12 @@ static int __init tc_filter_init(void)
if (err)
goto err_rhash_setup_block_ht;
- rtnl_register(PF_UNSPEC, RTM_NEWTFILTER, tc_new_tfilter, NULL, 0);
- rtnl_register(PF_UNSPEC, RTM_DELTFILTER, tc_del_tfilter, NULL, 0);
+ rtnl_register(PF_UNSPEC, RTM_NEWTFILTER, tc_new_tfilter, NULL,
+ RTNL_FLAG_DOIT_UNLOCKED);
+ rtnl_register(PF_UNSPEC, RTM_DELTFILTER, tc_del_tfilter, NULL,
+ RTNL_FLAG_DOIT_UNLOCKED);
rtnl_register(PF_UNSPEC, RTM_GETTFILTER, tc_get_tfilter,
- tc_dump_tfilter, 0);
+ tc_dump_tfilter, RTNL_FLAG_DOIT_UNLOCKED);
rtnl_register(PF_UNSPEC, RTM_NEWCHAIN, tc_ctl_chain, NULL, 0);
rtnl_register(PF_UNSPEC, RTM_DELCHAIN, tc_ctl_chain, NULL, 0);
rtnl_register(PF_UNSPEC, RTM_GETCHAIN, tc_ctl_chain,
--
2.13.6
^ permalink raw reply related
* [PATCH net-next v4 12/17] net: sched: track rtnl lock status when validating extensions
From: Vlad Buslov @ 2019-02-11 8:55 UTC (permalink / raw)
To: netdev; +Cc: jhs, xiyou.wangcong, jiri, davem, ast, daniel, Vlad Buslov
In-Reply-To: <20190211085548.7190-1-vladbu@mellanox.com>
Actions API is already updated to not rely on rtnl lock for
synchronization. However, it need to be provided with rtnl status when
called from classifiers API in order to be able to correctly release the
lock when loading kernel module.
Extend extension validation function with 'rtnl_held' flag which is passed
to actions API. Add new 'rtnl_held' parameter to tcf_exts_validate() in cls
API. No classifier is currently updated to support unlocked execution, so
pass hardcoded 'true' flag parameter value.
Signed-off-by: Vlad Buslov <vladbu@mellanox.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
---
include/net/pkt_cls.h | 2 +-
net/sched/cls_api.c | 9 +++++----
net/sched/cls_basic.c | 2 +-
net/sched/cls_bpf.c | 3 ++-
net/sched/cls_cgroup.c | 2 +-
net/sched/cls_flow.c | 2 +-
net/sched/cls_flower.c | 3 ++-
net/sched/cls_fw.c | 2 +-
net/sched/cls_matchall.c | 3 ++-
net/sched/cls_route.c | 2 +-
net/sched/cls_rsvp.h | 3 ++-
net/sched/cls_tcindex.c | 2 +-
net/sched/cls_u32.c | 2 +-
13 files changed, 21 insertions(+), 16 deletions(-)
diff --git a/include/net/pkt_cls.h b/include/net/pkt_cls.h
index e5dafa5ee1b2..0e3b61016931 100644
--- a/include/net/pkt_cls.h
+++ b/include/net/pkt_cls.h
@@ -416,7 +416,7 @@ tcf_exts_exec(struct sk_buff *skb, struct tcf_exts *exts,
int tcf_exts_validate(struct net *net, struct tcf_proto *tp,
struct nlattr **tb, struct nlattr *rate_tlv,
- struct tcf_exts *exts, bool ovr,
+ struct tcf_exts *exts, bool ovr, bool rtnl_held,
struct netlink_ext_ack *extack);
void tcf_exts_destroy(struct tcf_exts *exts);
void tcf_exts_change(struct tcf_exts *dst, struct tcf_exts *src);
diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c
index 3038a82f6591..a3e715d34efb 100644
--- a/net/sched/cls_api.c
+++ b/net/sched/cls_api.c
@@ -2841,7 +2841,7 @@ EXPORT_SYMBOL(tcf_exts_destroy);
int tcf_exts_validate(struct net *net, struct tcf_proto *tp, struct nlattr **tb,
struct nlattr *rate_tlv, struct tcf_exts *exts, bool ovr,
- struct netlink_ext_ack *extack)
+ bool rtnl_held, struct netlink_ext_ack *extack)
{
#ifdef CONFIG_NET_CLS_ACT
{
@@ -2851,7 +2851,8 @@ int tcf_exts_validate(struct net *net, struct tcf_proto *tp, struct nlattr **tb,
if (exts->police && tb[exts->police]) {
act = tcf_action_init_1(net, tp, tb[exts->police],
rate_tlv, "police", ovr,
- TCA_ACT_BIND, true, extack);
+ TCA_ACT_BIND, rtnl_held,
+ extack);
if (IS_ERR(act))
return PTR_ERR(act);
@@ -2863,8 +2864,8 @@ int tcf_exts_validate(struct net *net, struct tcf_proto *tp, struct nlattr **tb,
err = tcf_action_init(net, tp, tb[exts->action],
rate_tlv, NULL, ovr, TCA_ACT_BIND,
- exts->actions, &attr_size, true,
- extack);
+ exts->actions, &attr_size,
+ rtnl_held, extack);
if (err < 0)
return err;
exts->nr_actions = err;
diff --git a/net/sched/cls_basic.c b/net/sched/cls_basic.c
index 4a57fec6f306..eaf9c02fe792 100644
--- a/net/sched/cls_basic.c
+++ b/net/sched/cls_basic.c
@@ -153,7 +153,7 @@ static int basic_set_parms(struct net *net, struct tcf_proto *tp,
{
int err;
- err = tcf_exts_validate(net, tp, tb, est, &f->exts, ovr, extack);
+ err = tcf_exts_validate(net, tp, tb, est, &f->exts, ovr, true, extack);
if (err < 0)
return err;
diff --git a/net/sched/cls_bpf.c b/net/sched/cls_bpf.c
index a95cb240a606..656b3423ad35 100644
--- a/net/sched/cls_bpf.c
+++ b/net/sched/cls_bpf.c
@@ -417,7 +417,8 @@ static int cls_bpf_set_parms(struct net *net, struct tcf_proto *tp,
if ((!is_bpf && !is_ebpf) || (is_bpf && is_ebpf))
return -EINVAL;
- ret = tcf_exts_validate(net, tp, tb, est, &prog->exts, ovr, extack);
+ ret = tcf_exts_validate(net, tp, tb, est, &prog->exts, ovr, true,
+ extack);
if (ret < 0)
return ret;
diff --git a/net/sched/cls_cgroup.c b/net/sched/cls_cgroup.c
index 3bc01bdde165..663ee1c6d606 100644
--- a/net/sched/cls_cgroup.c
+++ b/net/sched/cls_cgroup.c
@@ -110,7 +110,7 @@ static int cls_cgroup_change(struct net *net, struct sk_buff *in_skb,
goto errout;
err = tcf_exts_validate(net, tp, tb, tca[TCA_RATE], &new->exts, ovr,
- extack);
+ true, extack);
if (err < 0)
goto errout;
diff --git a/net/sched/cls_flow.c b/net/sched/cls_flow.c
index 2bb043cd436b..39a6407d4832 100644
--- a/net/sched/cls_flow.c
+++ b/net/sched/cls_flow.c
@@ -445,7 +445,7 @@ static int flow_change(struct net *net, struct sk_buff *in_skb,
goto err2;
err = tcf_exts_validate(net, tp, tb, tca[TCA_RATE], &fnew->exts, ovr,
- extack);
+ true, extack);
if (err < 0)
goto err2;
diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c
index c5d1db3a3db7..d187bda602fa 100644
--- a/net/sched/cls_flower.c
+++ b/net/sched/cls_flower.c
@@ -1272,7 +1272,8 @@ static int fl_set_parms(struct net *net, struct tcf_proto *tp,
{
int err;
- err = tcf_exts_validate(net, tp, tb, est, &f->exts, ovr, extack);
+ err = tcf_exts_validate(net, tp, tb, est, &f->exts, ovr, true,
+ extack);
if (err < 0)
return err;
diff --git a/net/sched/cls_fw.c b/net/sched/cls_fw.c
index 29eeeaf3ea44..c8173ebb69f2 100644
--- a/net/sched/cls_fw.c
+++ b/net/sched/cls_fw.c
@@ -217,7 +217,7 @@ static int fw_set_parms(struct net *net, struct tcf_proto *tp,
int err;
err = tcf_exts_validate(net, tp, tb, tca[TCA_RATE], &f->exts, ovr,
- extack);
+ true, extack);
if (err < 0)
return err;
diff --git a/net/sched/cls_matchall.c b/net/sched/cls_matchall.c
index a1b803fd372e..8848a147c4bf 100644
--- a/net/sched/cls_matchall.c
+++ b/net/sched/cls_matchall.c
@@ -145,7 +145,8 @@ static int mall_set_parms(struct net *net, struct tcf_proto *tp,
{
int err;
- err = tcf_exts_validate(net, tp, tb, est, &head->exts, ovr, extack);
+ err = tcf_exts_validate(net, tp, tb, est, &head->exts, ovr, true,
+ extack);
if (err < 0)
return err;
diff --git a/net/sched/cls_route.c b/net/sched/cls_route.c
index 0404aa5fa7cb..44b26038c4c4 100644
--- a/net/sched/cls_route.c
+++ b/net/sched/cls_route.c
@@ -393,7 +393,7 @@ static int route4_set_parms(struct net *net, struct tcf_proto *tp,
struct route4_bucket *b;
int err;
- err = tcf_exts_validate(net, tp, tb, est, &f->exts, ovr, extack);
+ err = tcf_exts_validate(net, tp, tb, est, &f->exts, ovr, true, extack);
if (err < 0)
return err;
diff --git a/net/sched/cls_rsvp.h b/net/sched/cls_rsvp.h
index e9ccf7daea7d..9dd9530e6a52 100644
--- a/net/sched/cls_rsvp.h
+++ b/net/sched/cls_rsvp.h
@@ -502,7 +502,8 @@ static int rsvp_change(struct net *net, struct sk_buff *in_skb,
err = tcf_exts_init(&e, TCA_RSVP_ACT, TCA_RSVP_POLICE);
if (err < 0)
return err;
- err = tcf_exts_validate(net, tp, tb, tca[TCA_RATE], &e, ovr, extack);
+ err = tcf_exts_validate(net, tp, tb, tca[TCA_RATE], &e, ovr, true,
+ extack);
if (err < 0)
goto errout2;
diff --git a/net/sched/cls_tcindex.c b/net/sched/cls_tcindex.c
index 9ccc93f257db..b7dc667b6ec0 100644
--- a/net/sched/cls_tcindex.c
+++ b/net/sched/cls_tcindex.c
@@ -314,7 +314,7 @@ tcindex_set_parms(struct net *net, struct tcf_proto *tp, unsigned long base,
err = tcf_exts_init(&e, TCA_TCINDEX_ACT, TCA_TCINDEX_POLICE);
if (err < 0)
return err;
- err = tcf_exts_validate(net, tp, tb, est, &e, ovr, extack);
+ err = tcf_exts_validate(net, tp, tb, est, &e, ovr, true, extack);
if (err < 0)
goto errout;
diff --git a/net/sched/cls_u32.c b/net/sched/cls_u32.c
index dcea21004604..e891f30d42e9 100644
--- a/net/sched/cls_u32.c
+++ b/net/sched/cls_u32.c
@@ -726,7 +726,7 @@ static int u32_set_parms(struct net *net, struct tcf_proto *tp,
{
int err;
- err = tcf_exts_validate(net, tp, tb, est, &n->exts, ovr, extack);
+ err = tcf_exts_validate(net, tp, tb, est, &n->exts, ovr, true, extack);
if (err < 0)
return err;
--
2.13.6
^ permalink raw reply related
* [PATCH net-next v4 15/17] net: sched: add flags to Qdisc class ops struct
From: Vlad Buslov @ 2019-02-11 8:55 UTC (permalink / raw)
To: netdev; +Cc: jhs, xiyou.wangcong, jiri, davem, ast, daniel, Vlad Buslov
In-Reply-To: <20190211085548.7190-1-vladbu@mellanox.com>
Extend Qdisc_class_ops with flags. Create enum to hold possible class ops
flag values. Add first class ops flags value QDISC_CLASS_OPS_DOIT_UNLOCKED
to indicate that class ops functions can be called without taking rtnl
lock.
Signed-off-by: Vlad Buslov <vladbu@mellanox.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
---
include/net/sch_generic.h | 8 ++++++++
1 file changed, 8 insertions(+)
diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h
index 365801c2a4f5..e50b729f8691 100644
--- a/include/net/sch_generic.h
+++ b/include/net/sch_generic.h
@@ -179,6 +179,7 @@ static inline int qdisc_avail_bulklimit(const struct netdev_queue *txq)
}
struct Qdisc_class_ops {
+ unsigned int flags;
/* Child qdisc manipulation */
struct netdev_queue * (*select_queue)(struct Qdisc *, struct tcmsg *);
int (*graft)(struct Qdisc *, unsigned long cl,
@@ -210,6 +211,13 @@ struct Qdisc_class_ops {
struct gnet_dump *);
};
+/* Qdisc_class_ops flag values */
+
+/* Implements API that doesn't require rtnl lock */
+enum qdisc_class_ops_flags {
+ QDISC_CLASS_OPS_DOIT_UNLOCKED = 1,
+};
+
struct Qdisc_ops {
struct Qdisc_ops *next;
const struct Qdisc_class_ops *cl_ops;
--
2.13.6
^ permalink raw reply related
* [PATCH net-next v4 06/17] net: sched: protect chain template accesses with block lock
From: Vlad Buslov @ 2019-02-11 8:55 UTC (permalink / raw)
To: netdev; +Cc: jhs, xiyou.wangcong, jiri, davem, ast, daniel, Vlad Buslov
In-Reply-To: <20190211085548.7190-1-vladbu@mellanox.com>
When cls API is called without protection of rtnl lock, parallel
modification of chain is possible, which means that chain template can be
changed concurrently in certain circumstances. For example, when chain is
'deleted' by new user-space chain API, the chain might continue to be used
if it is referenced by actions, and can be 're-created' again by user. In
such case same chain structure is reused and its template is changed. To
protect from described scenario, cache chain template while holding block
lock. Introduce standalone tc_chain_notify_delete() function that works
with cached template values, instead of chains themselves.
Signed-off-by: Vlad Buslov <vladbu@mellanox.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
---
net/sched/cls_api.c | 73 +++++++++++++++++++++++++++++++++++++++++------------
1 file changed, 57 insertions(+), 16 deletions(-)
diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c
index 8e2ac785f6fd..0dcce8b0c7b4 100644
--- a/net/sched/cls_api.c
+++ b/net/sched/cls_api.c
@@ -371,14 +371,22 @@ struct tcf_chain *tcf_chain_get_by_act(struct tcf_block *block, u32 chain_index)
}
EXPORT_SYMBOL(tcf_chain_get_by_act);
-static void tc_chain_tmplt_del(struct tcf_chain *chain);
+static void tc_chain_tmplt_del(const struct tcf_proto_ops *tmplt_ops,
+ void *tmplt_priv);
+static int tc_chain_notify_delete(const struct tcf_proto_ops *tmplt_ops,
+ void *tmplt_priv, u32 chain_index,
+ struct tcf_block *block, struct sk_buff *oskb,
+ u32 seq, u16 flags, bool unicast);
static void __tcf_chain_put(struct tcf_chain *chain, bool by_act,
bool explicitly_created)
{
struct tcf_block *block = chain->block;
+ const struct tcf_proto_ops *tmplt_ops;
bool is_last, free_block = false;
unsigned int refcnt;
+ void *tmplt_priv;
+ u32 chain_index;
mutex_lock(&block->lock);
if (explicitly_created) {
@@ -398,16 +406,21 @@ static void __tcf_chain_put(struct tcf_chain *chain, bool by_act,
*/
refcnt = --chain->refcnt;
is_last = refcnt - chain->action_refcnt == 0;
+ tmplt_ops = chain->tmplt_ops;
+ tmplt_priv = chain->tmplt_priv;
+ chain_index = chain->index;
+
if (refcnt == 0)
free_block = tcf_chain_detach(chain);
mutex_unlock(&block->lock);
/* The last dropped non-action reference will trigger notification. */
if (is_last && !by_act)
- tc_chain_notify(chain, NULL, 0, 0, RTM_DELCHAIN, false);
+ tc_chain_notify_delete(tmplt_ops, tmplt_priv, chain_index,
+ block, NULL, 0, 0, false);
if (refcnt == 0) {
- tc_chain_tmplt_del(chain);
+ tc_chain_tmplt_del(tmplt_ops, tmplt_priv);
tcf_chain_destroy(chain, free_block);
}
}
@@ -2155,8 +2168,10 @@ static int tc_dump_tfilter(struct sk_buff *skb, struct netlink_callback *cb)
return skb->len;
}
-static int tc_chain_fill_node(struct tcf_chain *chain, struct net *net,
- struct sk_buff *skb, struct tcf_block *block,
+static int tc_chain_fill_node(const struct tcf_proto_ops *tmplt_ops,
+ void *tmplt_priv, u32 chain_index,
+ struct net *net, struct sk_buff *skb,
+ struct tcf_block *block,
u32 portid, u32 seq, u16 flags, int event)
{
unsigned char *b = skb_tail_pointer(skb);
@@ -2165,8 +2180,8 @@ static int tc_chain_fill_node(struct tcf_chain *chain, struct net *net,
struct tcmsg *tcm;
void *priv;
- ops = chain->tmplt_ops;
- priv = chain->tmplt_priv;
+ ops = tmplt_ops;
+ priv = tmplt_priv;
nlh = nlmsg_put(skb, portid, seq, event, sizeof(*tcm), flags);
if (!nlh)
@@ -2184,7 +2199,7 @@ static int tc_chain_fill_node(struct tcf_chain *chain, struct net *net,
tcm->tcm_block_index = block->index;
}
- if (nla_put_u32(skb, TCA_CHAIN, chain->index))
+ if (nla_put_u32(skb, TCA_CHAIN, chain_index))
goto nla_put_failure;
if (ops) {
@@ -2215,7 +2230,8 @@ static int tc_chain_notify(struct tcf_chain *chain, struct sk_buff *oskb,
if (!skb)
return -ENOBUFS;
- if (tc_chain_fill_node(chain, net, skb, block, portid,
+ if (tc_chain_fill_node(chain->tmplt_ops, chain->tmplt_priv,
+ chain->index, net, skb, block, portid,
seq, flags, event) <= 0) {
kfree_skb(skb);
return -EINVAL;
@@ -2227,6 +2243,31 @@ static int tc_chain_notify(struct tcf_chain *chain, struct sk_buff *oskb,
return rtnetlink_send(skb, net, portid, RTNLGRP_TC, flags & NLM_F_ECHO);
}
+static int tc_chain_notify_delete(const struct tcf_proto_ops *tmplt_ops,
+ void *tmplt_priv, u32 chain_index,
+ struct tcf_block *block, struct sk_buff *oskb,
+ u32 seq, u16 flags, bool unicast)
+{
+ u32 portid = oskb ? NETLINK_CB(oskb).portid : 0;
+ struct net *net = block->net;
+ struct sk_buff *skb;
+
+ skb = alloc_skb(NLMSG_GOODSIZE, GFP_KERNEL);
+ if (!skb)
+ return -ENOBUFS;
+
+ if (tc_chain_fill_node(tmplt_ops, tmplt_priv, chain_index, net, skb,
+ block, portid, seq, flags, RTM_DELCHAIN) <= 0) {
+ kfree_skb(skb);
+ return -EINVAL;
+ }
+
+ if (unicast)
+ return netlink_unicast(net->rtnl, skb, portid, MSG_DONTWAIT);
+
+ return rtnetlink_send(skb, net, portid, RTNLGRP_TC, flags & NLM_F_ECHO);
+}
+
static int tc_chain_tmplt_add(struct tcf_chain *chain, struct net *net,
struct nlattr **tca,
struct netlink_ext_ack *extack)
@@ -2256,16 +2297,15 @@ static int tc_chain_tmplt_add(struct tcf_chain *chain, struct net *net,
return 0;
}
-static void tc_chain_tmplt_del(struct tcf_chain *chain)
+static void tc_chain_tmplt_del(const struct tcf_proto_ops *tmplt_ops,
+ void *tmplt_priv)
{
- const struct tcf_proto_ops *ops = chain->tmplt_ops;
-
/* If template ops are set, no work to do for us. */
- if (!ops)
+ if (!tmplt_ops)
return;
- ops->tmplt_destroy(chain->tmplt_priv);
- module_put(ops->owner);
+ tmplt_ops->tmplt_destroy(tmplt_priv);
+ module_put(tmplt_ops->owner);
}
/* Add/delete/get a chain */
@@ -2486,7 +2526,8 @@ static int tc_dump_chain(struct sk_buff *skb, struct netlink_callback *cb)
index++;
continue;
}
- err = tc_chain_fill_node(chain, net, skb, block,
+ err = tc_chain_fill_node(chain->tmplt_ops, chain->tmplt_priv,
+ chain->index, net, skb, block,
NETLINK_CB(cb->skb).portid,
cb->nlh->nlmsg_seq, NLM_F_MULTI,
RTM_NEWCHAIN);
--
2.13.6
^ permalink raw reply related
* [PATCH net-next v4 00/17] Refactor classifier API to work with chain/classifiers without rtnl lock
From: Vlad Buslov @ 2019-02-11 8:55 UTC (permalink / raw)
To: netdev; +Cc: jhs, xiyou.wangcong, jiri, davem, ast, daniel, Vlad Buslov
Currently, all netlink protocol handlers for updating rules, actions and
qdiscs are protected with single global rtnl lock which removes any
possibility for parallelism. This patch set is a third step to remove
rtnl lock dependency from TC rules update path.
Recently, new rtnl registration flag RTNL_FLAG_DOIT_UNLOCKED was added.
Handlers registered with this flag are called without RTNL taken. End
goal is to have rule update handlers(RTM_NEWTFILTER, RTM_DELTFILTER,
etc.) to be registered with UNLOCKED flag to allow parallel execution.
However, there is no intention to completely remove or split rtnl lock
itself. This patch set addresses specific problems in implementation of
classifiers API that prevent its control path from being executed
concurrently, and completes refactoring of cls API rules update handlers
by removing rtnl lock dependency from code that handles chains and
classifiers. Rules update handlers are registered with
RTNL_FLAG_DOIT_UNLOCKED flag.
This patch set substitutes global rtnl lock dependency on rules update
path in cls API by extending its data structures with following locks:
- tcf_block with 'lock' mutex. It is used to protect block state and
life-time management fields of chains on the block (chain->refcnt,
chain->action_refcnt, chain->explicitly crated, etc.).
- tcf_chain with 'filter_chain_lock' mutex, that is used to protect list
of classifier instances attached to chain. chain0->filter_chain_lock
serializes calls to head change callbacks and allows them to rely on
filter_chain_lock for serialization instead of rtnl lock.
- tcf_proto with 'lock' spinlock that is intended to be used to
synchronize access to classifiers that support unlocked execution.
Classifiers are extended with reference counting to accommodate parallel
access by unlocked cls API. Classifier ops structure is extended with
additional 'put' function to allow reference counting of filters and
intended to be used by classifiers that implement rtnl-unlocked API.
Users of classifiers and individual filter instances are modified to
always hold reference while working with them.
Classifiers that support unlocked execution still need to know the
status of rtnl lock, so their API is extended with additional
'rtnl_held' argument that is used to indicate that caller holds rtnl
lock. Cls API propagates rtnl lock status across its helper functions
and passes it to classifier.
Changes from V3 to V4:
- Patch 1:
- Extract code that manages chain 'explicitly_created' flag into
standalone patch.
- Patch 2 - new.
Changes from V2 to V3:
- Change block->lock and chain->filter_chain_lock type to mutex. This
removes the need for async miniqp refactoring and allows calling
sleeping functions while holding the block->lock and
chain->filter_chain_lock locks.
- Previous patch 1 - async miniqp is no longer needed, remove the patch.
- Patch 1:
- Change block->lock type to mutex.
- Implement tcf_block_destroy() helper function that destroys
block->lock mutex before deallocating the block.
- Revert GFP_KERNEL->GFP_ATOMIC memory allocation flags of tcf_chain
which is no longer needed after block->lock type change.
- Patch 6:
- Change chain->filter_chain_lock type to mutex.
- Assume chain0->filter_chain_lock synchronizations instead of rtnl
lock in mini_qdisc_pair_swap() function that is called from head
change callback of ingress Qdisc. With filter_chain_lock type
changed to mutex it is now possible to call sleeping function while
holding it, so it is now used instead of async implementation from
previous versions of this patch set.
- Patch 7:
- Add local tp_next var to tcf_chain_flush() and use it to store
tp->next pointer dereferenced with rcu_dereference_protected() to
satisfy kbuild test robot.
- Reset tp pointer to NULL at the beginning of tc_new_tfilter() to
prevent its uninitialized usage in error handling code. This code
was already implemented in patch 10, but must be in patch 8 to
preserve code bisectability.
- Put parent chain in tcf_proto_destroy(). In previous version this
code was implemented in patch 1 which was removed in V3.
Changes from V1 to V2:
- Patch 1:
- Use smp_store_release() instead of xchg() for setting
miniqp->tp_head.
- Move Qdisc deallocation to tc_proto_wq ordered workqueue that is
used to destroy tcf proto instances. This is necessary to ensure
that Qdisc is destroyed after all instances of chain/proto that it
contains in order to prevent use-after-free error in
tc_chain_notify_delete().
- Cache parent net device ifindex in block to prevent use-after-free
of dev queue in tc_chain_notify_delete().
- Patch 2:
- Use lockdep_assert_held() instead of spin_is_locked() for assertion.
- Use 'free_block' argument in tcf_chain_destroy() instead of checking
block's reference count and chain_list for second time.
- Patch 7:
- Refactor tcf_chain0_head_change_cb_add() to not take block->lock and
chain0->filter_chain_lock in correct order.
- Patch 10:
- Always set 'tp_created' flag when creating tp to prevent releasing
the chain twice when tp with same priority was inserted
concurrently.
- Patch 11:
- Add additional check to prevent creation of new proto instance when
parent chain is being flushed to reduce CPU usage.
- Don't call tcf_chain_delete_empty() if tp insertion failed.
- Patch 16 - new.
- Patch 17:
- Refactor to only lock take rtnl lock once (at the beginning of rule
update handlers).
- Always release rtnl mutex in the same function that locked it.
Remove unlock code from tcf_block_release().
Github:
[https://github.com/vbuslov/linux/tree/cls_api_rtnl_lock_remove_for_cong_v4]
Vlad Buslov (17):
net: sched: protect block state with mutex
net: sched: protect chain->explicitly_created with block->lock
net: sched: refactor tc_ctl_chain() to use block->lock
net: sched: protect block->chain0 with block->lock
net: sched: traverse chains in block with tcf_get_next_chain()
net: sched: protect chain template accesses with block lock
net: sched: protect filter_chain list with filter_chain_lock mutex
net: sched: introduce reference counting for tcf_proto
net: sched: traverse classifiers in chain with tcf_get_next_proto()
net: sched: refactor tp insert/delete for concurrent execution
net: sched: prevent insertion of new classifiers during chain flush
net: sched: track rtnl lock status when validating extensions
net: sched: extend proto ops with 'put' callback
net: sched: extend proto ops to support unlocked classifiers
net: sched: add flags to Qdisc class ops struct
net: sched: refactor tcf_block_find() into standalone functions
net: sched: unlock rules update API
include/net/pkt_cls.h | 6 +-
include/net/sch_generic.h | 68 ++-
net/sched/cls_api.c | 1214 ++++++++++++++++++++++++++++++++++-----------
net/sched/cls_basic.c | 14 +-
net/sched/cls_bpf.c | 15 +-
net/sched/cls_cgroup.c | 13 +-
net/sched/cls_flow.c | 15 +-
net/sched/cls_flower.c | 16 +-
net/sched/cls_fw.c | 15 +-
net/sched/cls_matchall.c | 16 +-
net/sched/cls_route.c | 14 +-
net/sched/cls_rsvp.h | 16 +-
net/sched/cls_tcindex.c | 17 +-
net/sched/cls_u32.c | 14 +-
net/sched/sch_api.c | 10 +-
net/sched/sch_generic.c | 6 +-
16 files changed, 1103 insertions(+), 366 deletions(-)
--
2.13.6
^ permalink raw reply
* [PATCH net-next v4 05/17] net: sched: traverse chains in block with tcf_get_next_chain()
From: Vlad Buslov @ 2019-02-11 8:55 UTC (permalink / raw)
To: netdev; +Cc: jhs, xiyou.wangcong, jiri, davem, ast, daniel, Vlad Buslov
In-Reply-To: <20190211085548.7190-1-vladbu@mellanox.com>
All users of block->chain_list rely on rtnl lock and assume that no new
chains are added when traversing the list. Use tcf_get_next_chain() to
traverse chain list without relying on rtnl mutex. This function iterates
over chains by taking reference to current iterator chain only and doesn't
assume external synchronization of chain list.
Don't take reference to all chains in block when flushing and use
tcf_get_next_chain() to safely iterate over chain list instead. Remove
tcf_block_put_all_chains() that is no longer used.
Signed-off-by: Vlad Buslov <vladbu@mellanox.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
---
include/net/pkt_cls.h | 2 ++
net/sched/cls_api.c | 96 +++++++++++++++++++++++++++++++++++++--------------
net/sched/sch_api.c | 4 ++-
3 files changed, 76 insertions(+), 26 deletions(-)
diff --git a/include/net/pkt_cls.h b/include/net/pkt_cls.h
index cb8be396a11f..38bee7dd21d1 100644
--- a/include/net/pkt_cls.h
+++ b/include/net/pkt_cls.h
@@ -44,6 +44,8 @@ bool tcf_queue_work(struct rcu_work *rwork, work_func_t func);
struct tcf_chain *tcf_chain_get_by_act(struct tcf_block *block,
u32 chain_index);
void tcf_chain_put_by_act(struct tcf_chain *chain);
+struct tcf_chain *tcf_get_next_chain(struct tcf_block *block,
+ struct tcf_chain *chain);
void tcf_block_netif_keep_dst(struct tcf_block *block);
int tcf_block_get(struct tcf_block **p_block,
struct tcf_proto __rcu **p_filter_chain, struct Qdisc *q,
diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c
index 869ae44d7631..8e2ac785f6fd 100644
--- a/net/sched/cls_api.c
+++ b/net/sched/cls_api.c
@@ -883,28 +883,62 @@ static struct tcf_block *tcf_block_refcnt_get(struct net *net, u32 block_index)
return block;
}
-static void tcf_block_flush_all_chains(struct tcf_block *block)
+static struct tcf_chain *
+__tcf_get_next_chain(struct tcf_block *block, struct tcf_chain *chain)
{
- struct tcf_chain *chain;
+ mutex_lock(&block->lock);
+ if (chain)
+ chain = list_is_last(&chain->list, &block->chain_list) ?
+ NULL : list_next_entry(chain, list);
+ else
+ chain = list_first_entry_or_null(&block->chain_list,
+ struct tcf_chain, list);
- /* Hold a refcnt for all chains, so that they don't disappear
- * while we are iterating.
- */
- list_for_each_entry(chain, &block->chain_list, list)
+ /* skip all action-only chains */
+ while (chain && tcf_chain_held_by_acts_only(chain))
+ chain = list_is_last(&chain->list, &block->chain_list) ?
+ NULL : list_next_entry(chain, list);
+
+ if (chain)
tcf_chain_hold(chain);
+ mutex_unlock(&block->lock);
- list_for_each_entry(chain, &block->chain_list, list)
- tcf_chain_flush(chain);
+ return chain;
}
-static void tcf_block_put_all_chains(struct tcf_block *block)
+/* Function to be used by all clients that want to iterate over all chains on
+ * block. It properly obtains block->lock and takes reference to chain before
+ * returning it. Users of this function must be tolerant to concurrent chain
+ * insertion/deletion or ensure that no concurrent chain modification is
+ * possible. Note that all netlink dump callbacks cannot guarantee to provide
+ * consistent dump because rtnl lock is released each time skb is filled with
+ * data and sent to user-space.
+ */
+
+struct tcf_chain *
+tcf_get_next_chain(struct tcf_block *block, struct tcf_chain *chain)
{
- struct tcf_chain *chain, *tmp;
+ struct tcf_chain *chain_next = __tcf_get_next_chain(block, chain);
- /* At this point, all the chains should have refcnt >= 1. */
- list_for_each_entry_safe(chain, tmp, &block->chain_list, list) {
- tcf_chain_put_explicitly_created(chain);
+ if (chain)
tcf_chain_put(chain);
+
+ return chain_next;
+}
+EXPORT_SYMBOL(tcf_get_next_chain);
+
+static void tcf_block_flush_all_chains(struct tcf_block *block)
+{
+ struct tcf_chain *chain;
+
+ /* Last reference to block. At this point chains cannot be added or
+ * removed concurrently.
+ */
+ for (chain = tcf_get_next_chain(block, NULL);
+ chain;
+ chain = tcf_get_next_chain(block, chain)) {
+ tcf_chain_put_explicitly_created(chain);
+ tcf_chain_flush(chain);
}
}
@@ -923,8 +957,6 @@ static void __tcf_block_put(struct tcf_block *block, struct Qdisc *q,
mutex_unlock(&block->lock);
if (tcf_block_shared(block))
tcf_block_remove(block, block->net);
- if (!free_block)
- tcf_block_flush_all_chains(block);
if (q)
tcf_block_offload_unbind(block, q, ei);
@@ -932,7 +964,7 @@ static void __tcf_block_put(struct tcf_block *block, struct Qdisc *q,
if (free_block)
tcf_block_destroy(block);
else
- tcf_block_put_all_chains(block);
+ tcf_block_flush_all_chains(block);
} else if (q) {
tcf_block_offload_unbind(block, q, ei);
}
@@ -1266,11 +1298,15 @@ tcf_block_playback_offloads(struct tcf_block *block, tc_setup_cb_t *cb,
void *cb_priv, bool add, bool offload_in_use,
struct netlink_ext_ack *extack)
{
- struct tcf_chain *chain;
+ struct tcf_chain *chain, *chain_prev;
struct tcf_proto *tp;
int err;
- list_for_each_entry(chain, &block->chain_list, list) {
+ for (chain = __tcf_get_next_chain(block, NULL);
+ chain;
+ chain_prev = chain,
+ chain = __tcf_get_next_chain(block, chain),
+ tcf_chain_put(chain_prev)) {
for (tp = rtnl_dereference(chain->filter_chain); tp;
tp = rtnl_dereference(tp->next)) {
if (tp->ops->reoffload) {
@@ -1289,6 +1325,7 @@ tcf_block_playback_offloads(struct tcf_block *block, tc_setup_cb_t *cb,
return 0;
err_playback_remove:
+ tcf_chain_put(chain);
tcf_block_playback_offloads(block, cb, cb_priv, false, offload_in_use,
extack);
return err;
@@ -2023,11 +2060,11 @@ static bool tcf_chain_dump(struct tcf_chain *chain, struct Qdisc *q, u32 parent,
/* called with RTNL */
static int tc_dump_tfilter(struct sk_buff *skb, struct netlink_callback *cb)
{
+ struct tcf_chain *chain, *chain_prev;
struct net *net = sock_net(skb->sk);
struct nlattr *tca[TCA_MAX + 1];
struct Qdisc *q = NULL;
struct tcf_block *block;
- struct tcf_chain *chain;
struct tcmsg *tcm = nlmsg_data(cb->nlh);
long index_start;
long index;
@@ -2091,12 +2128,17 @@ static int tc_dump_tfilter(struct sk_buff *skb, struct netlink_callback *cb)
index_start = cb->args[0];
index = 0;
- list_for_each_entry(chain, &block->chain_list, list) {
+ for (chain = __tcf_get_next_chain(block, NULL);
+ chain;
+ chain_prev = chain,
+ chain = __tcf_get_next_chain(block, chain),
+ tcf_chain_put(chain_prev)) {
if (tca[TCA_CHAIN] &&
nla_get_u32(tca[TCA_CHAIN]) != chain->index)
continue;
if (!tcf_chain_dump(chain, q, parent, skb, cb,
index_start, &index)) {
+ tcf_chain_put(chain);
err = -EMSGSIZE;
break;
}
@@ -2364,11 +2406,11 @@ static int tc_ctl_chain(struct sk_buff *skb, struct nlmsghdr *n,
/* called with RTNL */
static int tc_dump_chain(struct sk_buff *skb, struct netlink_callback *cb)
{
+ struct tcf_chain *chain, *chain_prev;
struct net *net = sock_net(skb->sk);
struct nlattr *tca[TCA_MAX + 1];
struct Qdisc *q = NULL;
struct tcf_block *block;
- struct tcf_chain *chain;
struct tcmsg *tcm = nlmsg_data(cb->nlh);
long index_start;
long index;
@@ -2432,7 +2474,11 @@ static int tc_dump_chain(struct sk_buff *skb, struct netlink_callback *cb)
index_start = cb->args[0];
index = 0;
- list_for_each_entry(chain, &block->chain_list, list) {
+ for (chain = __tcf_get_next_chain(block, NULL);
+ chain;
+ chain_prev = chain,
+ chain = __tcf_get_next_chain(block, chain),
+ tcf_chain_put(chain_prev)) {
if ((tca[TCA_CHAIN] &&
nla_get_u32(tca[TCA_CHAIN]) != chain->index))
continue;
@@ -2440,14 +2486,14 @@ static int tc_dump_chain(struct sk_buff *skb, struct netlink_callback *cb)
index++;
continue;
}
- if (tcf_chain_held_by_acts_only(chain))
- continue;
err = tc_chain_fill_node(chain, net, skb, block,
NETLINK_CB(cb->skb).portid,
cb->nlh->nlmsg_seq, NLM_F_MULTI,
RTM_NEWCHAIN);
- if (err <= 0)
+ if (err <= 0) {
+ tcf_chain_put(chain);
break;
+ }
index++;
}
diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c
index 03e26e8d0ec9..80058abc729f 100644
--- a/net/sched/sch_api.c
+++ b/net/sched/sch_api.c
@@ -1909,7 +1909,9 @@ static void tc_bind_tclass(struct Qdisc *q, u32 portid, u32 clid,
block = cops->tcf_block(q, cl, NULL);
if (!block)
return;
- list_for_each_entry(chain, &block->chain_list, list) {
+ for (chain = tcf_get_next_chain(block, NULL);
+ chain;
+ chain = tcf_get_next_chain(block, chain)) {
struct tcf_proto *tp;
for (tp = rtnl_dereference(chain->filter_chain);
--
2.13.6
^ permalink raw reply related
* [PATCH net-next v4 07/17] net: sched: protect filter_chain list with filter_chain_lock mutex
From: Vlad Buslov @ 2019-02-11 8:55 UTC (permalink / raw)
To: netdev; +Cc: jhs, xiyou.wangcong, jiri, davem, ast, daniel, Vlad Buslov
In-Reply-To: <20190211085548.7190-1-vladbu@mellanox.com>
Extend tcf_chain with new filter_chain_lock mutex. Always lock the chain
when accessing filter_chain list, instead of relying on rtnl lock.
Dereference filter_chain with tcf_chain_dereference() lockdep macro to
verify that all users of chain_list have the lock taken.
Rearrange tp insert/remove code in tc_new_tfilter/tc_del_tfilter to execute
all necessary code while holding chain lock in order to prevent
invalidation of chain_info structure by potential concurrent change. This
also serializes calls to tcf_chain0_head_change(), which allows head change
callbacks to rely on filter_chain_lock for synchronization instead of rtnl
mutex.
Signed-off-by: Vlad Buslov <vladbu@mellanox.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
---
include/net/sch_generic.h | 17 +++++++
net/sched/cls_api.c | 111 +++++++++++++++++++++++++++++++++-------------
net/sched/sch_generic.c | 6 ++-
3 files changed, 101 insertions(+), 33 deletions(-)
diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h
index 31b8ea66a47d..85993d7efee6 100644
--- a/include/net/sch_generic.h
+++ b/include/net/sch_generic.h
@@ -341,6 +341,8 @@ struct qdisc_skb_cb {
typedef void tcf_chain_head_change_t(struct tcf_proto *tp_head, void *priv);
struct tcf_chain {
+ /* Protects filter_chain. */
+ struct mutex filter_chain_lock;
struct tcf_proto __rcu *filter_chain;
struct list_head list;
struct tcf_block *block;
@@ -374,6 +376,21 @@ struct tcf_block {
struct rcu_head rcu;
};
+#ifdef CONFIG_PROVE_LOCKING
+static inline bool lockdep_tcf_chain_is_locked(struct tcf_chain *chain)
+{
+ return lockdep_is_held(&chain->filter_chain_lock);
+}
+#else
+static inline bool lockdep_tcf_chain_is_locked(struct tcf_block *chain)
+{
+ return true;
+}
+#endif /* #ifdef CONFIG_PROVE_LOCKING */
+
+#define tcf_chain_dereference(p, chain) \
+ rcu_dereference_protected(p, lockdep_tcf_chain_is_locked(chain))
+
static inline void tcf_block_offload_inc(struct tcf_block *block, u32 *flags)
{
if (*flags & TCA_CLS_FLAGS_IN_HW)
diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c
index 0dcce8b0c7b4..3fce30ae9a9b 100644
--- a/net/sched/cls_api.c
+++ b/net/sched/cls_api.c
@@ -221,6 +221,7 @@ static struct tcf_chain *tcf_chain_create(struct tcf_block *block,
if (!chain)
return NULL;
list_add_tail(&chain->list, &block->chain_list);
+ mutex_init(&chain->filter_chain_lock);
chain->block = block;
chain->index = chain_index;
chain->refcnt = 1;
@@ -280,6 +281,7 @@ static void tcf_chain_destroy(struct tcf_chain *chain, bool free_block)
{
struct tcf_block *block = chain->block;
+ mutex_destroy(&chain->filter_chain_lock);
kfree(chain);
if (free_block)
tcf_block_destroy(block);
@@ -443,9 +445,13 @@ static void tcf_chain_put_explicitly_created(struct tcf_chain *chain)
static void tcf_chain_flush(struct tcf_chain *chain)
{
- struct tcf_proto *tp = rtnl_dereference(chain->filter_chain);
+ struct tcf_proto *tp;
+ mutex_lock(&chain->filter_chain_lock);
+ tp = tcf_chain_dereference(chain->filter_chain, chain);
tcf_chain0_head_change(chain, NULL);
+ mutex_unlock(&chain->filter_chain_lock);
+
while (tp) {
RCU_INIT_POINTER(chain->filter_chain, tp->next);
tcf_proto_destroy(tp, NULL);
@@ -785,11 +791,29 @@ tcf_chain0_head_change_cb_add(struct tcf_block *block,
mutex_lock(&block->lock);
chain0 = block->chain0.chain;
- if (chain0 && chain0->filter_chain)
- tcf_chain_head_change_item(item, chain0->filter_chain);
- list_add(&item->list, &block->chain0.filter_chain_list);
+ if (chain0)
+ tcf_chain_hold(chain0);
+ else
+ list_add(&item->list, &block->chain0.filter_chain_list);
mutex_unlock(&block->lock);
+ if (chain0) {
+ struct tcf_proto *tp_head;
+
+ mutex_lock(&chain0->filter_chain_lock);
+
+ tp_head = tcf_chain_dereference(chain0->filter_chain, chain0);
+ if (tp_head)
+ tcf_chain_head_change_item(item, tp_head);
+
+ mutex_lock(&block->lock);
+ list_add(&item->list, &block->chain0.filter_chain_list);
+ mutex_unlock(&block->lock);
+
+ mutex_unlock(&chain0->filter_chain_lock);
+ tcf_chain_put(chain0);
+ }
+
return 0;
}
@@ -1464,9 +1488,10 @@ struct tcf_chain_info {
struct tcf_proto __rcu *next;
};
-static struct tcf_proto *tcf_chain_tp_prev(struct tcf_chain_info *chain_info)
+static struct tcf_proto *tcf_chain_tp_prev(struct tcf_chain *chain,
+ struct tcf_chain_info *chain_info)
{
- return rtnl_dereference(*chain_info->pprev);
+ return tcf_chain_dereference(*chain_info->pprev, chain);
}
static void tcf_chain_tp_insert(struct tcf_chain *chain,
@@ -1475,7 +1500,7 @@ static void tcf_chain_tp_insert(struct tcf_chain *chain,
{
if (*chain_info->pprev == chain->filter_chain)
tcf_chain0_head_change(chain, tp);
- RCU_INIT_POINTER(tp->next, tcf_chain_tp_prev(chain_info));
+ RCU_INIT_POINTER(tp->next, tcf_chain_tp_prev(chain, chain_info));
rcu_assign_pointer(*chain_info->pprev, tp);
tcf_chain_hold(chain);
}
@@ -1484,7 +1509,7 @@ static void tcf_chain_tp_remove(struct tcf_chain *chain,
struct tcf_chain_info *chain_info,
struct tcf_proto *tp)
{
- struct tcf_proto *next = rtnl_dereference(chain_info->next);
+ struct tcf_proto *next = tcf_chain_dereference(chain_info->next, chain);
if (tp == chain->filter_chain)
tcf_chain0_head_change(chain, next);
@@ -1502,7 +1527,8 @@ static struct tcf_proto *tcf_chain_tp_find(struct tcf_chain *chain,
/* Check the chain for existence of proto-tcf with this priority */
for (pprev = &chain->filter_chain;
- (tp = rtnl_dereference(*pprev)); pprev = &tp->next) {
+ (tp = tcf_chain_dereference(*pprev, chain));
+ pprev = &tp->next) {
if (tp->prio >= prio) {
if (tp->prio == prio) {
if (prio_allocate ||
@@ -1710,12 +1736,13 @@ static int tc_new_tfilter(struct sk_buff *skb, struct nlmsghdr *n,
goto errout;
}
+ mutex_lock(&chain->filter_chain_lock);
tp = tcf_chain_tp_find(chain, &chain_info, protocol,
prio, prio_allocate);
if (IS_ERR(tp)) {
NL_SET_ERR_MSG(extack, "Filter with specified priority/protocol not found");
err = PTR_ERR(tp);
- goto errout;
+ goto errout_locked;
}
if (tp == NULL) {
@@ -1724,29 +1751,37 @@ static int tc_new_tfilter(struct sk_buff *skb, struct nlmsghdr *n,
if (tca[TCA_KIND] == NULL || !protocol) {
NL_SET_ERR_MSG(extack, "Filter kind and protocol must be specified");
err = -EINVAL;
- goto errout;
+ goto errout_locked;
}
if (!(n->nlmsg_flags & NLM_F_CREATE)) {
NL_SET_ERR_MSG(extack, "Need both RTM_NEWTFILTER and NLM_F_CREATE to create a new filter");
err = -ENOENT;
- goto errout;
+ goto errout_locked;
}
if (prio_allocate)
- prio = tcf_auto_prio(tcf_chain_tp_prev(&chain_info));
+ prio = tcf_auto_prio(tcf_chain_tp_prev(chain,
+ &chain_info));
+ mutex_unlock(&chain->filter_chain_lock);
tp = tcf_proto_create(nla_data(tca[TCA_KIND]),
protocol, prio, chain, extack);
if (IS_ERR(tp)) {
err = PTR_ERR(tp);
goto errout;
}
+
+ mutex_lock(&chain->filter_chain_lock);
+ tcf_chain_tp_insert(chain, &chain_info, tp);
+ mutex_unlock(&chain->filter_chain_lock);
tp_created = 1;
} else if (tca[TCA_KIND] && nla_strcmp(tca[TCA_KIND], tp->ops->kind)) {
NL_SET_ERR_MSG(extack, "Specified filter kind does not match existing one");
err = -EINVAL;
- goto errout;
+ goto errout_locked;
+ } else {
+ mutex_unlock(&chain->filter_chain_lock);
}
fh = tp->ops->get(tp, t->tcm_handle);
@@ -1772,15 +1807,11 @@ static int tc_new_tfilter(struct sk_buff *skb, struct nlmsghdr *n,
err = tp->ops->change(net, skb, tp, cl, t->tcm_handle, tca, &fh,
n->nlmsg_flags & NLM_F_CREATE ? TCA_ACT_NOREPLACE : TCA_ACT_REPLACE,
extack);
- if (err == 0) {
- if (tp_created)
- tcf_chain_tp_insert(chain, &chain_info, tp);
+ if (err == 0)
tfilter_notify(net, skb, n, tp, block, q, parent, fh,
RTM_NEWTFILTER, false);
- } else {
- if (tp_created)
- tcf_proto_destroy(tp, NULL);
- }
+ else if (tp_created)
+ tcf_proto_destroy(tp, NULL);
errout:
if (chain)
@@ -1790,6 +1821,10 @@ static int tc_new_tfilter(struct sk_buff *skb, struct nlmsghdr *n,
/* Replay the request. */
goto replay;
return err;
+
+errout_locked:
+ mutex_unlock(&chain->filter_chain_lock);
+ goto errout;
}
static int tc_del_tfilter(struct sk_buff *skb, struct nlmsghdr *n,
@@ -1865,31 +1900,34 @@ static int tc_del_tfilter(struct sk_buff *skb, struct nlmsghdr *n,
goto errout;
}
+ mutex_lock(&chain->filter_chain_lock);
tp = tcf_chain_tp_find(chain, &chain_info, protocol,
prio, false);
if (!tp || IS_ERR(tp)) {
NL_SET_ERR_MSG(extack, "Filter with specified priority/protocol not found");
err = tp ? PTR_ERR(tp) : -ENOENT;
- goto errout;
+ goto errout_locked;
} else if (tca[TCA_KIND] && nla_strcmp(tca[TCA_KIND], tp->ops->kind)) {
NL_SET_ERR_MSG(extack, "Specified filter kind does not match existing one");
err = -EINVAL;
+ goto errout_locked;
+ } else if (t->tcm_handle == 0) {
+ tcf_chain_tp_remove(chain, &chain_info, tp);
+ mutex_unlock(&chain->filter_chain_lock);
+
+ tfilter_notify(net, skb, n, tp, block, q, parent, fh,
+ RTM_DELTFILTER, false);
+ tcf_proto_destroy(tp, extack);
+ err = 0;
goto errout;
}
+ mutex_unlock(&chain->filter_chain_lock);
fh = tp->ops->get(tp, t->tcm_handle);
if (!fh) {
- if (t->tcm_handle == 0) {
- tcf_chain_tp_remove(chain, &chain_info, tp);
- tfilter_notify(net, skb, n, tp, block, q, parent, fh,
- RTM_DELTFILTER, false);
- tcf_proto_destroy(tp, extack);
- err = 0;
- } else {
- NL_SET_ERR_MSG(extack, "Specified filter handle not found");
- err = -ENOENT;
- }
+ NL_SET_ERR_MSG(extack, "Specified filter handle not found");
+ err = -ENOENT;
} else {
bool last;
@@ -1899,7 +1937,10 @@ static int tc_del_tfilter(struct sk_buff *skb, struct nlmsghdr *n,
if (err)
goto errout;
if (last) {
+ mutex_lock(&chain->filter_chain_lock);
tcf_chain_tp_remove(chain, &chain_info, tp);
+ mutex_unlock(&chain->filter_chain_lock);
+
tcf_proto_destroy(tp, extack);
}
}
@@ -1909,6 +1950,10 @@ static int tc_del_tfilter(struct sk_buff *skb, struct nlmsghdr *n,
tcf_chain_put(chain);
tcf_block_release(q, block);
return err;
+
+errout_locked:
+ mutex_unlock(&chain->filter_chain_lock);
+ goto errout;
}
static int tc_get_tfilter(struct sk_buff *skb, struct nlmsghdr *n,
@@ -1966,8 +2011,10 @@ static int tc_get_tfilter(struct sk_buff *skb, struct nlmsghdr *n,
goto errout;
}
+ mutex_lock(&chain->filter_chain_lock);
tp = tcf_chain_tp_find(chain, &chain_info, protocol,
prio, false);
+ mutex_unlock(&chain->filter_chain_lock);
if (!tp || IS_ERR(tp)) {
NL_SET_ERR_MSG(extack, "Filter with specified priority/protocol not found");
err = tp ? PTR_ERR(tp) : -ENOENT;
diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c
index 66ba2ce2320f..e24568f9246c 100644
--- a/net/sched/sch_generic.c
+++ b/net/sched/sch_generic.c
@@ -1366,7 +1366,11 @@ static void mini_qdisc_rcu_func(struct rcu_head *head)
void mini_qdisc_pair_swap(struct mini_Qdisc_pair *miniqp,
struct tcf_proto *tp_head)
{
- struct mini_Qdisc *miniq_old = rtnl_dereference(*miniqp->p_miniq);
+ /* Protected with chain0->filter_chain_lock.
+ * Can't access chain directly because tp_head can be NULL.
+ */
+ struct mini_Qdisc *miniq_old =
+ rcu_dereference_protected(*miniqp->p_miniq, 1);
struct mini_Qdisc *miniq;
if (!tp_head) {
--
2.13.6
^ permalink raw reply related
* [PATCH net-next v4 11/17] net: sched: prevent insertion of new classifiers during chain flush
From: Vlad Buslov @ 2019-02-11 8:55 UTC (permalink / raw)
To: netdev; +Cc: jhs, xiyou.wangcong, jiri, davem, ast, daniel, Vlad Buslov
In-Reply-To: <20190211085548.7190-1-vladbu@mellanox.com>
Extend tcf_chain with 'flushing' flag. Use the flag to prevent insertion of
new classifier instances when chain flushing is in progress in order to
prevent resource leak when tcf_proto is created by unlocked users
concurrently.
Return EAGAIN error from tcf_chain_tp_insert_unique() to restart
tc_new_tfilter() and lookup the chain/proto again.
Signed-off-by: Vlad Buslov <vladbu@mellanox.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
---
include/net/sch_generic.h | 1 +
net/sched/cls_api.c | 35 +++++++++++++++++++++++++++++------
2 files changed, 30 insertions(+), 6 deletions(-)
diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h
index 083e566fc380..e8cf36ed3e87 100644
--- a/include/net/sch_generic.h
+++ b/include/net/sch_generic.h
@@ -356,6 +356,7 @@ struct tcf_chain {
unsigned int refcnt;
unsigned int action_refcnt;
bool explicitly_created;
+ bool flushing;
const struct tcf_proto_ops *tmplt_ops;
void *tmplt_priv;
};
diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c
index c6452e3bfc6a..3038a82f6591 100644
--- a/net/sched/cls_api.c
+++ b/net/sched/cls_api.c
@@ -477,9 +477,12 @@ static void __tcf_chain_put(struct tcf_chain *chain, bool by_act,
mutex_unlock(&block->lock);
/* The last dropped non-action reference will trigger notification. */
- if (is_last && !by_act)
+ if (is_last && !by_act) {
tc_chain_notify_delete(tmplt_ops, tmplt_priv, chain_index,
block, NULL, 0, 0, false);
+ /* Last reference to chain, no need to lock. */
+ chain->flushing = false;
+ }
if (refcnt == 0) {
tc_chain_tmplt_del(tmplt_ops, tmplt_priv);
@@ -511,6 +514,7 @@ static void tcf_chain_flush(struct tcf_chain *chain)
tp = tcf_chain_dereference(chain->filter_chain, chain);
RCU_INIT_POINTER(chain->filter_chain, NULL);
tcf_chain0_head_change(chain, NULL);
+ chain->flushing = true;
mutex_unlock(&chain->filter_chain_lock);
while (tp) {
@@ -1610,15 +1614,20 @@ static struct tcf_proto *tcf_chain_tp_prev(struct tcf_chain *chain,
return tcf_chain_dereference(*chain_info->pprev, chain);
}
-static void tcf_chain_tp_insert(struct tcf_chain *chain,
- struct tcf_chain_info *chain_info,
- struct tcf_proto *tp)
+static int tcf_chain_tp_insert(struct tcf_chain *chain,
+ struct tcf_chain_info *chain_info,
+ struct tcf_proto *tp)
{
+ if (chain->flushing)
+ return -EAGAIN;
+
if (*chain_info->pprev == chain->filter_chain)
tcf_chain0_head_change(chain, tp);
tcf_proto_get(tp);
RCU_INIT_POINTER(tp->next, tcf_chain_tp_prev(chain, chain_info));
rcu_assign_pointer(*chain_info->pprev, tp);
+
+ return 0;
}
static void tcf_chain_tp_remove(struct tcf_chain *chain,
@@ -1649,18 +1658,22 @@ static struct tcf_proto *tcf_chain_tp_insert_unique(struct tcf_chain *chain,
{
struct tcf_chain_info chain_info;
struct tcf_proto *tp;
+ int err = 0;
mutex_lock(&chain->filter_chain_lock);
tp = tcf_chain_tp_find(chain, &chain_info,
protocol, prio, false);
if (!tp)
- tcf_chain_tp_insert(chain, &chain_info, tp_new);
+ err = tcf_chain_tp_insert(chain, &chain_info, tp_new);
mutex_unlock(&chain->filter_chain_lock);
if (tp) {
tcf_proto_destroy(tp_new, NULL);
tp_new = tp;
+ } else if (err) {
+ tcf_proto_destroy(tp_new, NULL);
+ tp_new = ERR_PTR(err);
}
return tp_new;
@@ -1943,6 +1956,11 @@ static int tc_new_tfilter(struct sk_buff *skb, struct nlmsghdr *n,
if (tp == NULL) {
struct tcf_proto *tp_new = NULL;
+ if (chain->flushing) {
+ err = -EAGAIN;
+ goto errout_locked;
+ }
+
/* Proto-tcf does not exist, create new one */
if (tca[TCA_KIND] == NULL || !protocol) {
@@ -1966,11 +1984,15 @@ static int tc_new_tfilter(struct sk_buff *skb, struct nlmsghdr *n,
protocol, prio, chain, extack);
if (IS_ERR(tp_new)) {
err = PTR_ERR(tp_new);
- goto errout;
+ goto errout_tp;
}
tp_created = 1;
tp = tcf_chain_tp_insert_unique(chain, tp_new, protocol, prio);
+ if (IS_ERR(tp)) {
+ err = PTR_ERR(tp);
+ goto errout_tp;
+ }
} else {
mutex_unlock(&chain->filter_chain_lock);
}
@@ -2011,6 +2033,7 @@ static int tc_new_tfilter(struct sk_buff *skb, struct nlmsghdr *n,
errout:
if (err && tp_created)
tcf_chain_tp_delete_empty(chain, tp, NULL);
+errout_tp:
if (chain) {
if (tp && !IS_ERR(tp))
tcf_proto_put(tp, NULL);
--
2.13.6
^ permalink raw reply related
* [PATCH net-next v4 01/17] net: sched: protect block state with mutex
From: Vlad Buslov @ 2019-02-11 8:55 UTC (permalink / raw)
To: netdev; +Cc: jhs, xiyou.wangcong, jiri, davem, ast, daniel, Vlad Buslov
In-Reply-To: <20190211085548.7190-1-vladbu@mellanox.com>
Currently, tcf_block doesn't use any synchronization mechanisms to protect
critical sections that manage lifetime of its chains. block->chain_list and
multiple variables in tcf_chain that control its lifetime assume external
synchronization provided by global rtnl lock. Converting chain reference
counting to atomic reference counters is not possible because cls API uses
multiple counters and flags to control chain lifetime, so all of them must
be synchronized in chain get/put code.
Use single per-block lock to protect block data and manage lifetime of all
chains on the block. Always take block->lock when accessing chain_list.
Chain get and put modify chain lifetime-management data and parent block's
chain_list, so take the lock in these functions. Verify block->lock state
with assertions in functions that expect to be called with the lock taken
and are called from multiple places. Take block->lock when accessing
filter_chain_list.
In order to allow parallel update of rules on single block, move all calls
to classifiers outside of critical sections protected by new block->lock.
Rearrange chain get and put functions code to only access protected chain
data while holding block lock:
- Rearrange code to only access chain reference counter and chain action
reference counter while holding block lock.
- Extract code that requires block->lock from tcf_chain_destroy() into
standalone tcf_chain_destroy() function that is called by
__tcf_chain_put() in same critical section that changes chain reference
counters.
Signed-off-by: Vlad Buslov <vladbu@mellanox.com>
---
Changes from V3 to V4:
- Extract code that manages chain 'explicitly_created' flag into
standalone patch.
include/net/sch_generic.h | 5 +++
net/sched/cls_api.c | 84 +++++++++++++++++++++++++++++++++++++++--------
2 files changed, 76 insertions(+), 13 deletions(-)
diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h
index 7a4957599874..31b8ea66a47d 100644
--- a/include/net/sch_generic.h
+++ b/include/net/sch_generic.h
@@ -12,6 +12,7 @@
#include <linux/list.h>
#include <linux/refcount.h>
#include <linux/workqueue.h>
+#include <linux/mutex.h>
#include <net/gen_stats.h>
#include <net/rtnetlink.h>
@@ -352,6 +353,10 @@ struct tcf_chain {
};
struct tcf_block {
+ /* Lock protects tcf_block and lifetime-management data of chains
+ * attached to the block (refcnt, action_refcnt, explicitly_created).
+ */
+ struct mutex lock;
struct list_head chain_list;
u32 index; /* block index for shared blocks */
refcount_t refcnt;
diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c
index 02cf6d2fa0e1..806e7158a7e8 100644
--- a/net/sched/cls_api.c
+++ b/net/sched/cls_api.c
@@ -201,6 +201,9 @@ static void tcf_proto_destroy(struct tcf_proto *tp,
kfree_rcu(tp, rcu);
}
+#define ASSERT_BLOCK_LOCKED(block) \
+ lockdep_assert_held(&(block)->lock)
+
struct tcf_filter_chain_list_item {
struct list_head list;
tcf_chain_head_change_t *chain_head_change;
@@ -212,6 +215,8 @@ static struct tcf_chain *tcf_chain_create(struct tcf_block *block,
{
struct tcf_chain *chain;
+ ASSERT_BLOCK_LOCKED(block);
+
chain = kzalloc(sizeof(*chain), GFP_KERNEL);
if (!chain)
return NULL;
@@ -243,25 +248,51 @@ static void tcf_chain0_head_change(struct tcf_chain *chain,
tcf_chain_head_change_item(item, tp_head);
}
-static void tcf_chain_destroy(struct tcf_chain *chain)
+/* Returns true if block can be safely freed. */
+
+static bool tcf_chain_detach(struct tcf_chain *chain)
{
struct tcf_block *block = chain->block;
+ ASSERT_BLOCK_LOCKED(block);
+
list_del(&chain->list);
if (!chain->index)
block->chain0.chain = NULL;
+
+ if (list_empty(&block->chain_list) &&
+ refcount_read(&block->refcnt) == 0)
+ return true;
+
+ return false;
+}
+
+static void tcf_block_destroy(struct tcf_block *block)
+{
+ mutex_destroy(&block->lock);
+ kfree_rcu(block, rcu);
+}
+
+static void tcf_chain_destroy(struct tcf_chain *chain, bool free_block)
+{
+ struct tcf_block *block = chain->block;
+
kfree(chain);
- if (list_empty(&block->chain_list) && !refcount_read(&block->refcnt))
- kfree_rcu(block, rcu);
+ if (free_block)
+ tcf_block_destroy(block);
}
static void tcf_chain_hold(struct tcf_chain *chain)
{
+ ASSERT_BLOCK_LOCKED(chain->block);
+
++chain->refcnt;
}
static bool tcf_chain_held_by_acts_only(struct tcf_chain *chain)
{
+ ASSERT_BLOCK_LOCKED(chain->block);
+
/* In case all the references are action references, this
* chain should not be shown to the user.
*/
@@ -273,6 +304,8 @@ static struct tcf_chain *tcf_chain_lookup(struct tcf_block *block,
{
struct tcf_chain *chain;
+ ASSERT_BLOCK_LOCKED(block);
+
list_for_each_entry(chain, &block->chain_list, list) {
if (chain->index == chain_index)
return chain;
@@ -287,31 +320,40 @@ static struct tcf_chain *__tcf_chain_get(struct tcf_block *block,
u32 chain_index, bool create,
bool by_act)
{
- struct tcf_chain *chain = tcf_chain_lookup(block, chain_index);
+ struct tcf_chain *chain = NULL;
+ bool is_first_reference;
+ mutex_lock(&block->lock);
+ chain = tcf_chain_lookup(block, chain_index);
if (chain) {
tcf_chain_hold(chain);
} else {
if (!create)
- return NULL;
+ goto errout;
chain = tcf_chain_create(block, chain_index);
if (!chain)
- return NULL;
+ goto errout;
}
if (by_act)
++chain->action_refcnt;
+ is_first_reference = chain->refcnt - chain->action_refcnt == 1;
+ mutex_unlock(&block->lock);
/* Send notification only in case we got the first
* non-action reference. Until then, the chain acts only as
* a placeholder for actions pointing to it and user ought
* not know about them.
*/
- if (chain->refcnt - chain->action_refcnt == 1 && !by_act)
+ if (is_first_reference && !by_act)
tc_chain_notify(chain, NULL, 0, NLM_F_CREATE | NLM_F_EXCL,
RTM_NEWCHAIN, false);
return chain;
+
+errout:
+ mutex_unlock(&block->lock);
+ return chain;
}
static struct tcf_chain *tcf_chain_get(struct tcf_block *block, u32 chain_index,
@@ -330,17 +372,31 @@ static void tc_chain_tmplt_del(struct tcf_chain *chain);
static void __tcf_chain_put(struct tcf_chain *chain, bool by_act)
{
+ struct tcf_block *block = chain->block;
+ bool is_last, free_block = false;
+ unsigned int refcnt;
+
+ mutex_lock(&block->lock);
if (by_act)
chain->action_refcnt--;
- chain->refcnt--;
+
+ /* tc_chain_notify_delete can't be called while holding block lock.
+ * However, when block is unlocked chain can be changed concurrently, so
+ * save these to temporary variables.
+ */
+ refcnt = --chain->refcnt;
+ is_last = refcnt - chain->action_refcnt == 0;
+ if (refcnt == 0)
+ free_block = tcf_chain_detach(chain);
+ mutex_unlock(&block->lock);
/* The last dropped non-action reference will trigger notification. */
- if (chain->refcnt - chain->action_refcnt == 0 && !by_act)
+ if (is_last && !by_act)
tc_chain_notify(chain, NULL, 0, 0, RTM_DELCHAIN, false);
- if (chain->refcnt == 0) {
+ if (refcnt == 0) {
tc_chain_tmplt_del(chain);
- tcf_chain_destroy(chain);
+ tcf_chain_destroy(chain, free_block);
}
}
@@ -772,6 +828,7 @@ static struct tcf_block *tcf_block_create(struct net *net, struct Qdisc *q,
NL_SET_ERR_MSG(extack, "Memory allocation for block failed");
return ERR_PTR(-ENOMEM);
}
+ mutex_init(&block->lock);
INIT_LIST_HEAD(&block->chain_list);
INIT_LIST_HEAD(&block->cb_list);
INIT_LIST_HEAD(&block->owner_list);
@@ -835,7 +892,7 @@ static void tcf_block_put_all_chains(struct tcf_block *block)
static void __tcf_block_put(struct tcf_block *block, struct Qdisc *q,
struct tcf_block_ext_info *ei)
{
- if (refcount_dec_and_test(&block->refcnt)) {
+ if (refcount_dec_and_mutex_lock(&block->refcnt, &block->lock)) {
/* Flushing/putting all chains will cause the block to be
* deallocated when last chain is freed. However, if chain_list
* is empty, block has to be manually deallocated. After block
@@ -844,6 +901,7 @@ static void __tcf_block_put(struct tcf_block *block, struct Qdisc *q,
*/
bool free_block = list_empty(&block->chain_list);
+ mutex_unlock(&block->lock);
if (tcf_block_shared(block))
tcf_block_remove(block, block->net);
if (!free_block)
@@ -853,7 +911,7 @@ static void __tcf_block_put(struct tcf_block *block, struct Qdisc *q,
tcf_block_offload_unbind(block, q, ei);
if (free_block)
- kfree_rcu(block, rcu);
+ tcf_block_destroy(block);
else
tcf_block_put_all_chains(block);
} else if (q) {
--
2.13.6
^ permalink raw reply related
* [PATCH net-next v4 14/17] net: sched: extend proto ops to support unlocked classifiers
From: Vlad Buslov @ 2019-02-11 8:55 UTC (permalink / raw)
To: netdev; +Cc: jhs, xiyou.wangcong, jiri, davem, ast, daniel, Vlad Buslov
In-Reply-To: <20190211085548.7190-1-vladbu@mellanox.com>
Add 'rtnl_held' flag to tcf proto change, delete, destroy, dump, walk
functions to track rtnl lock status. Extend users of these function in cls
API to propagate rtnl lock status to them. This allows classifiers to
obtain rtnl lock when necessary and to pass rtnl lock status to extensions
and driver offload callbacks.
Add flags field to tcf proto ops. Add flag value to indicate that
classifier doesn't require rtnl lock.
Signed-off-by: Vlad Buslov <vladbu@mellanox.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
---
include/net/pkt_cls.h | 2 +-
include/net/sch_generic.h | 17 +++--
net/sched/cls_api.c | 168 +++++++++++++++++++++++++---------------------
net/sched/cls_basic.c | 12 ++--
net/sched/cls_bpf.c | 12 ++--
net/sched/cls_cgroup.c | 11 +--
net/sched/cls_flow.c | 13 ++--
net/sched/cls_flower.c | 13 ++--
net/sched/cls_fw.c | 13 ++--
net/sched/cls_matchall.c | 13 ++--
net/sched/cls_route.c | 12 ++--
net/sched/cls_rsvp.h | 13 ++--
net/sched/cls_tcindex.c | 15 +++--
net/sched/cls_u32.c | 12 ++--
net/sched/sch_api.c | 6 +-
15 files changed, 191 insertions(+), 141 deletions(-)
diff --git a/include/net/pkt_cls.h b/include/net/pkt_cls.h
index 0e3b61016931..6a530bef9253 100644
--- a/include/net/pkt_cls.h
+++ b/include/net/pkt_cls.h
@@ -47,7 +47,7 @@ void tcf_chain_put_by_act(struct tcf_chain *chain);
struct tcf_chain *tcf_get_next_chain(struct tcf_block *block,
struct tcf_chain *chain);
struct tcf_proto *tcf_get_next_proto(struct tcf_chain *chain,
- struct tcf_proto *tp);
+ struct tcf_proto *tp, bool rtnl_held);
void tcf_block_netif_keep_dst(struct tcf_block *block);
int tcf_block_get(struct tcf_block **p_block,
struct tcf_proto __rcu **p_filter_chain, struct Qdisc *q,
diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h
index 410dda80ca62..365801c2a4f5 100644
--- a/include/net/sch_generic.h
+++ b/include/net/sch_generic.h
@@ -273,7 +273,7 @@ struct tcf_proto_ops {
const struct tcf_proto *,
struct tcf_result *);
int (*init)(struct tcf_proto*);
- void (*destroy)(struct tcf_proto *tp,
+ void (*destroy)(struct tcf_proto *tp, bool rtnl_held,
struct netlink_ext_ack *extack);
void* (*get)(struct tcf_proto*, u32 handle);
@@ -281,12 +281,13 @@ struct tcf_proto_ops {
int (*change)(struct net *net, struct sk_buff *,
struct tcf_proto*, unsigned long,
u32 handle, struct nlattr **,
- void **, bool,
+ void **, bool, bool,
struct netlink_ext_ack *);
int (*delete)(struct tcf_proto *tp, void *arg,
- bool *last,
+ bool *last, bool rtnl_held,
struct netlink_ext_ack *);
- void (*walk)(struct tcf_proto*, struct tcf_walker *arg);
+ void (*walk)(struct tcf_proto *tp,
+ struct tcf_walker *arg, bool rtnl_held);
int (*reoffload)(struct tcf_proto *tp, bool add,
tc_setup_cb_t *cb, void *cb_priv,
struct netlink_ext_ack *extack);
@@ -299,12 +300,18 @@ struct tcf_proto_ops {
/* rtnetlink specific */
int (*dump)(struct net*, struct tcf_proto*, void *,
- struct sk_buff *skb, struct tcmsg*);
+ struct sk_buff *skb, struct tcmsg*,
+ bool);
int (*tmplt_dump)(struct sk_buff *skb,
struct net *net,
void *tmplt_priv);
struct module *owner;
+ int flags;
+};
+
+enum tcf_proto_ops_flags {
+ TCF_PROTO_OPS_DOIT_UNLOCKED = 1,
};
struct tcf_proto {
diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c
index 8fe38aa180cf..e8ed461e94af 100644
--- a/net/sched/cls_api.c
+++ b/net/sched/cls_api.c
@@ -69,7 +69,8 @@ static const struct tcf_proto_ops *__tcf_proto_lookup_ops(const char *kind)
}
static const struct tcf_proto_ops *
-tcf_proto_lookup_ops(const char *kind, struct netlink_ext_ack *extack)
+tcf_proto_lookup_ops(const char *kind, bool rtnl_held,
+ struct netlink_ext_ack *extack)
{
const struct tcf_proto_ops *ops;
@@ -77,9 +78,11 @@ tcf_proto_lookup_ops(const char *kind, struct netlink_ext_ack *extack)
if (ops)
return ops;
#ifdef CONFIG_MODULES
- rtnl_unlock();
+ if (rtnl_held)
+ rtnl_unlock();
request_module("cls_%s", kind);
- rtnl_lock();
+ if (rtnl_held)
+ rtnl_lock();
ops = __tcf_proto_lookup_ops(kind);
/* We dropped the RTNL semaphore in order to perform
* the module load. So, even if we succeeded in loading
@@ -162,6 +165,7 @@ static inline u32 tcf_auto_prio(struct tcf_proto *tp)
static struct tcf_proto *tcf_proto_create(const char *kind, u32 protocol,
u32 prio, struct tcf_chain *chain,
+ bool rtnl_held,
struct netlink_ext_ack *extack)
{
struct tcf_proto *tp;
@@ -171,7 +175,7 @@ static struct tcf_proto *tcf_proto_create(const char *kind, u32 protocol,
if (!tp)
return ERR_PTR(-ENOBUFS);
- tp->ops = tcf_proto_lookup_ops(kind, extack);
+ tp->ops = tcf_proto_lookup_ops(kind, rtnl_held, extack);
if (IS_ERR(tp->ops)) {
err = PTR_ERR(tp->ops);
goto errout;
@@ -202,20 +206,20 @@ static void tcf_proto_get(struct tcf_proto *tp)
static void tcf_chain_put(struct tcf_chain *chain);
-static void tcf_proto_destroy(struct tcf_proto *tp,
+static void tcf_proto_destroy(struct tcf_proto *tp, bool rtnl_held,
struct netlink_ext_ack *extack)
{
- tp->ops->destroy(tp, extack);
+ tp->ops->destroy(tp, rtnl_held, extack);
tcf_chain_put(tp->chain);
module_put(tp->ops->owner);
kfree_rcu(tp, rcu);
}
-static void tcf_proto_put(struct tcf_proto *tp,
+static void tcf_proto_put(struct tcf_proto *tp, bool rtnl_held,
struct netlink_ext_ack *extack)
{
if (refcount_dec_and_test(&tp->refcnt))
- tcf_proto_destroy(tp, extack);
+ tcf_proto_destroy(tp, rtnl_held, extack);
}
static int walker_noop(struct tcf_proto *tp, void *d, struct tcf_walker *arg)
@@ -223,21 +227,21 @@ static int walker_noop(struct tcf_proto *tp, void *d, struct tcf_walker *arg)
return -1;
}
-static bool tcf_proto_is_empty(struct tcf_proto *tp)
+static bool tcf_proto_is_empty(struct tcf_proto *tp, bool rtnl_held)
{
struct tcf_walker walker = { .fn = walker_noop, };
if (tp->ops->walk) {
- tp->ops->walk(tp, &walker);
+ tp->ops->walk(tp, &walker, rtnl_held);
return !walker.stop;
}
return true;
}
-static bool tcf_proto_check_delete(struct tcf_proto *tp)
+static bool tcf_proto_check_delete(struct tcf_proto *tp, bool rtnl_held)
{
spin_lock(&tp->lock);
- if (tcf_proto_is_empty(tp))
+ if (tcf_proto_is_empty(tp, rtnl_held))
tp->deleting = true;
spin_unlock(&tp->lock);
return tp->deleting;
@@ -506,7 +510,7 @@ static void tcf_chain_put_explicitly_created(struct tcf_chain *chain)
__tcf_chain_put(chain, false, true);
}
-static void tcf_chain_flush(struct tcf_chain *chain)
+static void tcf_chain_flush(struct tcf_chain *chain, bool rtnl_held)
{
struct tcf_proto *tp, *tp_next;
@@ -519,7 +523,7 @@ static void tcf_chain_flush(struct tcf_chain *chain)
while (tp) {
tp_next = rcu_dereference_protected(tp->next, 1);
- tcf_proto_put(tp, NULL);
+ tcf_proto_put(tp, rtnl_held, NULL);
tp = tp_next;
}
}
@@ -1070,18 +1074,19 @@ __tcf_get_next_proto(struct tcf_chain *chain, struct tcf_proto *tp)
*/
struct tcf_proto *
-tcf_get_next_proto(struct tcf_chain *chain, struct tcf_proto *tp)
+tcf_get_next_proto(struct tcf_chain *chain, struct tcf_proto *tp,
+ bool rtnl_held)
{
struct tcf_proto *tp_next = __tcf_get_next_proto(chain, tp);
if (tp)
- tcf_proto_put(tp, NULL);
+ tcf_proto_put(tp, rtnl_held, NULL);
return tp_next;
}
EXPORT_SYMBOL(tcf_get_next_proto);
-static void tcf_block_flush_all_chains(struct tcf_block *block)
+static void tcf_block_flush_all_chains(struct tcf_block *block, bool rtnl_held)
{
struct tcf_chain *chain;
@@ -1092,12 +1097,12 @@ static void tcf_block_flush_all_chains(struct tcf_block *block)
chain;
chain = tcf_get_next_chain(block, chain)) {
tcf_chain_put_explicitly_created(chain);
- tcf_chain_flush(chain);
+ tcf_chain_flush(chain, rtnl_held);
}
}
static void __tcf_block_put(struct tcf_block *block, struct Qdisc *q,
- struct tcf_block_ext_info *ei)
+ struct tcf_block_ext_info *ei, bool rtnl_held)
{
if (refcount_dec_and_mutex_lock(&block->refcnt, &block->lock)) {
/* Flushing/putting all chains will cause the block to be
@@ -1118,15 +1123,15 @@ static void __tcf_block_put(struct tcf_block *block, struct Qdisc *q,
if (free_block)
tcf_block_destroy(block);
else
- tcf_block_flush_all_chains(block);
+ tcf_block_flush_all_chains(block, rtnl_held);
} else if (q) {
tcf_block_offload_unbind(block, q, ei);
}
}
-static void tcf_block_refcnt_put(struct tcf_block *block)
+static void tcf_block_refcnt_put(struct tcf_block *block, bool rtnl_held)
{
- __tcf_block_put(block, NULL, NULL);
+ __tcf_block_put(block, NULL, NULL, rtnl_held);
}
/* Find tcf block.
@@ -1244,10 +1249,11 @@ static struct tcf_block *tcf_block_find(struct net *net, struct Qdisc **q,
return ERR_PTR(err);
}
-static void tcf_block_release(struct Qdisc *q, struct tcf_block *block)
+static void tcf_block_release(struct Qdisc *q, struct tcf_block *block,
+ bool rtnl_held)
{
if (!IS_ERR_OR_NULL(block))
- tcf_block_refcnt_put(block);
+ tcf_block_refcnt_put(block, rtnl_held);
if (q)
qdisc_put(q);
@@ -1358,7 +1364,7 @@ int tcf_block_get_ext(struct tcf_block **p_block, struct Qdisc *q,
tcf_block_owner_del(block, q, ei->binder_type);
err_block_owner_add:
err_block_insert:
- tcf_block_refcnt_put(block);
+ tcf_block_refcnt_put(block, true);
return err;
}
EXPORT_SYMBOL(tcf_block_get_ext);
@@ -1395,7 +1401,7 @@ void tcf_block_put_ext(struct tcf_block *block, struct Qdisc *q,
tcf_chain0_head_change_cb_del(block, ei);
tcf_block_owner_del(block, q, ei->binder_type);
- __tcf_block_put(block, q, ei);
+ __tcf_block_put(block, q, ei, true);
}
EXPORT_SYMBOL(tcf_block_put_ext);
@@ -1464,7 +1470,7 @@ tcf_block_playback_offloads(struct tcf_block *block, tc_setup_cb_t *cb,
for (tp = __tcf_get_next_proto(chain, NULL); tp;
tp_prev = tp,
tp = __tcf_get_next_proto(chain, tp),
- tcf_proto_put(tp_prev, NULL)) {
+ tcf_proto_put(tp_prev, true, NULL)) {
if (tp->ops->reoffload) {
err = tp->ops->reoffload(tp, add, cb, cb_priv,
extack);
@@ -1481,7 +1487,7 @@ tcf_block_playback_offloads(struct tcf_block *block, tc_setup_cb_t *cb,
return 0;
err_playback_remove:
- tcf_proto_put(tp, NULL);
+ tcf_proto_put(tp, true, NULL);
tcf_chain_put(chain);
tcf_block_playback_offloads(block, cb, cb_priv, false, offload_in_use,
extack);
@@ -1654,7 +1660,8 @@ static struct tcf_proto *tcf_chain_tp_find(struct tcf_chain *chain,
static struct tcf_proto *tcf_chain_tp_insert_unique(struct tcf_chain *chain,
struct tcf_proto *tp_new,
- u32 protocol, u32 prio)
+ u32 protocol, u32 prio,
+ bool rtnl_held)
{
struct tcf_chain_info chain_info;
struct tcf_proto *tp;
@@ -1669,10 +1676,10 @@ static struct tcf_proto *tcf_chain_tp_insert_unique(struct tcf_chain *chain,
mutex_unlock(&chain->filter_chain_lock);
if (tp) {
- tcf_proto_destroy(tp_new, NULL);
+ tcf_proto_destroy(tp_new, rtnl_held, NULL);
tp_new = tp;
} else if (err) {
- tcf_proto_destroy(tp_new, NULL);
+ tcf_proto_destroy(tp_new, rtnl_held, NULL);
tp_new = ERR_PTR(err);
}
@@ -1680,7 +1687,7 @@ static struct tcf_proto *tcf_chain_tp_insert_unique(struct tcf_chain *chain,
}
static void tcf_chain_tp_delete_empty(struct tcf_chain *chain,
- struct tcf_proto *tp,
+ struct tcf_proto *tp, bool rtnl_held,
struct netlink_ext_ack *extack)
{
struct tcf_chain_info chain_info;
@@ -1705,7 +1712,7 @@ static void tcf_chain_tp_delete_empty(struct tcf_chain *chain,
* concurrently.
* Mark tp for deletion if it is empty.
*/
- if (!tp_iter || !tcf_proto_check_delete(tp)) {
+ if (!tp_iter || !tcf_proto_check_delete(tp, rtnl_held)) {
mutex_unlock(&chain->filter_chain_lock);
return;
}
@@ -1716,7 +1723,7 @@ static void tcf_chain_tp_delete_empty(struct tcf_chain *chain,
RCU_INIT_POINTER(*chain_info.pprev, next);
mutex_unlock(&chain->filter_chain_lock);
- tcf_proto_put(tp, extack);
+ tcf_proto_put(tp, rtnl_held, extack);
}
static struct tcf_proto *tcf_chain_tp_find(struct tcf_chain *chain,
@@ -1755,7 +1762,8 @@ static struct tcf_proto *tcf_chain_tp_find(struct tcf_chain *chain,
static int tcf_fill_node(struct net *net, struct sk_buff *skb,
struct tcf_proto *tp, struct tcf_block *block,
struct Qdisc *q, u32 parent, void *fh,
- u32 portid, u32 seq, u16 flags, int event)
+ u32 portid, u32 seq, u16 flags, int event,
+ bool rtnl_held)
{
struct tcmsg *tcm;
struct nlmsghdr *nlh;
@@ -1783,7 +1791,8 @@ static int tcf_fill_node(struct net *net, struct sk_buff *skb,
if (!fh) {
tcm->tcm_handle = 0;
} else {
- if (tp->ops->dump && tp->ops->dump(net, tp, fh, skb, tcm) < 0)
+ if (tp->ops->dump &&
+ tp->ops->dump(net, tp, fh, skb, tcm, rtnl_held) < 0)
goto nla_put_failure;
}
nlh->nlmsg_len = skb_tail_pointer(skb) - b;
@@ -1798,7 +1807,8 @@ static int tcf_fill_node(struct net *net, struct sk_buff *skb,
static int tfilter_notify(struct net *net, struct sk_buff *oskb,
struct nlmsghdr *n, struct tcf_proto *tp,
struct tcf_block *block, struct Qdisc *q,
- u32 parent, void *fh, int event, bool unicast)
+ u32 parent, void *fh, int event, bool unicast,
+ bool rtnl_held)
{
struct sk_buff *skb;
u32 portid = oskb ? NETLINK_CB(oskb).portid : 0;
@@ -1808,7 +1818,8 @@ static int tfilter_notify(struct net *net, struct sk_buff *oskb,
return -ENOBUFS;
if (tcf_fill_node(net, skb, tp, block, q, parent, fh, portid,
- n->nlmsg_seq, n->nlmsg_flags, event) <= 0) {
+ n->nlmsg_seq, n->nlmsg_flags, event,
+ rtnl_held) <= 0) {
kfree_skb(skb);
return -EINVAL;
}
@@ -1824,7 +1835,7 @@ static int tfilter_del_notify(struct net *net, struct sk_buff *oskb,
struct nlmsghdr *n, struct tcf_proto *tp,
struct tcf_block *block, struct Qdisc *q,
u32 parent, void *fh, bool unicast, bool *last,
- struct netlink_ext_ack *extack)
+ bool rtnl_held, struct netlink_ext_ack *extack)
{
struct sk_buff *skb;
u32 portid = oskb ? NETLINK_CB(oskb).portid : 0;
@@ -1835,13 +1846,14 @@ static int tfilter_del_notify(struct net *net, struct sk_buff *oskb,
return -ENOBUFS;
if (tcf_fill_node(net, skb, tp, block, q, parent, fh, portid,
- n->nlmsg_seq, n->nlmsg_flags, RTM_DELTFILTER) <= 0) {
+ n->nlmsg_seq, n->nlmsg_flags, RTM_DELTFILTER,
+ rtnl_held) <= 0) {
NL_SET_ERR_MSG(extack, "Failed to build del event notification");
kfree_skb(skb);
return -EINVAL;
}
- err = tp->ops->delete(tp, fh, last, extack);
+ err = tp->ops->delete(tp, fh, last, rtnl_held, extack);
if (err) {
kfree_skb(skb);
return err;
@@ -1860,14 +1872,15 @@ static int tfilter_del_notify(struct net *net, struct sk_buff *oskb,
static void tfilter_notify_chain(struct net *net, struct sk_buff *oskb,
struct tcf_block *block, struct Qdisc *q,
u32 parent, struct nlmsghdr *n,
- struct tcf_chain *chain, int event)
+ struct tcf_chain *chain, int event,
+ bool rtnl_held)
{
struct tcf_proto *tp;
- for (tp = tcf_get_next_proto(chain, NULL);
- tp; tp = tcf_get_next_proto(chain, tp))
+ for (tp = tcf_get_next_proto(chain, NULL, rtnl_held);
+ tp; tp = tcf_get_next_proto(chain, tp, rtnl_held))
tfilter_notify(net, oskb, n, tp, block,
- q, parent, NULL, event, false);
+ q, parent, NULL, event, false, rtnl_held);
}
static void tfilter_put(struct tcf_proto *tp, void *fh)
@@ -1896,6 +1909,7 @@ static int tc_new_tfilter(struct sk_buff *skb, struct nlmsghdr *n,
void *fh;
int err;
int tp_created;
+ bool rtnl_held = true;
if (!netlink_ns_capable(skb, net->user_ns, CAP_NET_ADMIN))
return -EPERM;
@@ -1987,14 +2001,16 @@ static int tc_new_tfilter(struct sk_buff *skb, struct nlmsghdr *n,
mutex_unlock(&chain->filter_chain_lock);
tp_new = tcf_proto_create(nla_data(tca[TCA_KIND]),
- protocol, prio, chain, extack);
+ protocol, prio, chain, rtnl_held,
+ extack);
if (IS_ERR(tp_new)) {
err = PTR_ERR(tp_new);
goto errout_tp;
}
tp_created = 1;
- tp = tcf_chain_tp_insert_unique(chain, tp_new, protocol, prio);
+ tp = tcf_chain_tp_insert_unique(chain, tp_new, protocol, prio,
+ rtnl_held);
if (IS_ERR(tp)) {
err = PTR_ERR(tp);
goto errout_tp;
@@ -2032,24 +2048,24 @@ static int tc_new_tfilter(struct sk_buff *skb, struct nlmsghdr *n,
err = tp->ops->change(net, skb, tp, cl, t->tcm_handle, tca, &fh,
n->nlmsg_flags & NLM_F_CREATE ? TCA_ACT_NOREPLACE : TCA_ACT_REPLACE,
- extack);
+ rtnl_held, extack);
if (err == 0) {
tfilter_notify(net, skb, n, tp, block, q, parent, fh,
- RTM_NEWTFILTER, false);
+ RTM_NEWTFILTER, false, rtnl_held);
tfilter_put(tp, fh);
}
errout:
if (err && tp_created)
- tcf_chain_tp_delete_empty(chain, tp, NULL);
+ tcf_chain_tp_delete_empty(chain, tp, rtnl_held, NULL);
errout_tp:
if (chain) {
if (tp && !IS_ERR(tp))
- tcf_proto_put(tp, NULL);
+ tcf_proto_put(tp, rtnl_held, NULL);
if (!tp_created)
tcf_chain_put(chain);
}
- tcf_block_release(q, block);
+ tcf_block_release(q, block, rtnl_held);
if (err == -EAGAIN)
/* Replay the request. */
goto replay;
@@ -2078,6 +2094,7 @@ static int tc_del_tfilter(struct sk_buff *skb, struct nlmsghdr *n,
unsigned long cl = 0;
void *fh = NULL;
int err;
+ bool rtnl_held = true;
if (!netlink_ns_capable(skb, net->user_ns, CAP_NET_ADMIN))
return -EPERM;
@@ -2127,8 +2144,8 @@ static int tc_del_tfilter(struct sk_buff *skb, struct nlmsghdr *n,
if (prio == 0) {
tfilter_notify_chain(net, skb, block, q, parent, n,
- chain, RTM_DELTFILTER);
- tcf_chain_flush(chain);
+ chain, RTM_DELTFILTER, rtnl_held);
+ tcf_chain_flush(chain, rtnl_held);
err = 0;
goto errout;
}
@@ -2148,9 +2165,9 @@ static int tc_del_tfilter(struct sk_buff *skb, struct nlmsghdr *n,
tcf_chain_tp_remove(chain, &chain_info, tp);
mutex_unlock(&chain->filter_chain_lock);
- tcf_proto_put(tp, NULL);
+ tcf_proto_put(tp, rtnl_held, NULL);
tfilter_notify(net, skb, n, tp, block, q, parent, fh,
- RTM_DELTFILTER, false);
+ RTM_DELTFILTER, false, rtnl_held);
err = 0;
goto errout;
}
@@ -2166,20 +2183,21 @@ static int tc_del_tfilter(struct sk_buff *skb, struct nlmsghdr *n,
err = tfilter_del_notify(net, skb, n, tp, block,
q, parent, fh, false, &last,
- extack);
+ rtnl_held, extack);
+
if (err)
goto errout;
if (last)
- tcf_chain_tp_delete_empty(chain, tp, extack);
+ tcf_chain_tp_delete_empty(chain, tp, rtnl_held, extack);
}
errout:
if (chain) {
if (tp && !IS_ERR(tp))
- tcf_proto_put(tp, NULL);
+ tcf_proto_put(tp, rtnl_held, NULL);
tcf_chain_put(chain);
}
- tcf_block_release(q, block);
+ tcf_block_release(q, block, rtnl_held);
return err;
errout_locked:
@@ -2205,6 +2223,7 @@ static int tc_get_tfilter(struct sk_buff *skb, struct nlmsghdr *n,
unsigned long cl = 0;
void *fh = NULL;
int err;
+ bool rtnl_held = true;
err = nlmsg_parse(n, sizeof(*t), tca, TCA_MAX, rtm_tca_policy, extack);
if (err < 0)
@@ -2263,7 +2282,7 @@ static int tc_get_tfilter(struct sk_buff *skb, struct nlmsghdr *n,
err = -ENOENT;
} else {
err = tfilter_notify(net, skb, n, tp, block, q, parent,
- fh, RTM_NEWTFILTER, true);
+ fh, RTM_NEWTFILTER, true, rtnl_held);
if (err < 0)
NL_SET_ERR_MSG(extack, "Failed to send filter notify message");
}
@@ -2272,10 +2291,10 @@ static int tc_get_tfilter(struct sk_buff *skb, struct nlmsghdr *n,
errout:
if (chain) {
if (tp && !IS_ERR(tp))
- tcf_proto_put(tp, NULL);
+ tcf_proto_put(tp, rtnl_held, NULL);
tcf_chain_put(chain);
}
- tcf_block_release(q, block);
+ tcf_block_release(q, block, rtnl_held);
return err;
}
@@ -2296,7 +2315,7 @@ static int tcf_node_dump(struct tcf_proto *tp, void *n, struct tcf_walker *arg)
return tcf_fill_node(net, a->skb, tp, a->block, a->q, a->parent,
n, NETLINK_CB(a->cb->skb).portid,
a->cb->nlh->nlmsg_seq, NLM_F_MULTI,
- RTM_NEWTFILTER);
+ RTM_NEWTFILTER, true);
}
static bool tcf_chain_dump(struct tcf_chain *chain, struct Qdisc *q, u32 parent,
@@ -2313,7 +2332,7 @@ static bool tcf_chain_dump(struct tcf_chain *chain, struct Qdisc *q, u32 parent,
tp;
tp_prev = tp,
tp = __tcf_get_next_proto(chain, tp),
- tcf_proto_put(tp_prev, NULL),
+ tcf_proto_put(tp_prev, true, NULL),
(*p_index)++) {
if (*p_index < index_start)
continue;
@@ -2330,9 +2349,8 @@ static bool tcf_chain_dump(struct tcf_chain *chain, struct Qdisc *q, u32 parent,
if (tcf_fill_node(net, skb, tp, block, q, parent, NULL,
NETLINK_CB(cb->skb).portid,
cb->nlh->nlmsg_seq, NLM_F_MULTI,
- RTM_NEWTFILTER) <= 0)
+ RTM_NEWTFILTER, true) <= 0)
goto errout;
-
cb->args[1] = 1;
}
if (!tp->ops->walk)
@@ -2347,7 +2365,7 @@ static bool tcf_chain_dump(struct tcf_chain *chain, struct Qdisc *q, u32 parent,
arg.w.skip = cb->args[1] - 1;
arg.w.count = 0;
arg.w.cookie = cb->args[2];
- tp->ops->walk(tp, &arg.w);
+ tp->ops->walk(tp, &arg.w, true);
cb->args[2] = arg.w.cookie;
cb->args[1] = arg.w.count + 1;
if (arg.w.stop)
@@ -2356,7 +2374,7 @@ static bool tcf_chain_dump(struct tcf_chain *chain, struct Qdisc *q, u32 parent,
return true;
errout:
- tcf_proto_put(tp, NULL);
+ tcf_proto_put(tp, true, NULL);
return false;
}
@@ -2448,7 +2466,7 @@ static int tc_dump_tfilter(struct sk_buff *skb, struct netlink_callback *cb)
}
if (tcm->tcm_ifindex == TCM_IFINDEX_MAGIC_BLOCK)
- tcf_block_refcnt_put(block);
+ tcf_block_refcnt_put(block, true);
cb->args[0] = index;
out:
@@ -2569,7 +2587,7 @@ static int tc_chain_tmplt_add(struct tcf_chain *chain, struct net *net,
if (!tca[TCA_KIND])
return 0;
- ops = tcf_proto_lookup_ops(nla_data(tca[TCA_KIND]), extack);
+ ops = tcf_proto_lookup_ops(nla_data(tca[TCA_KIND]), true, extack);
if (IS_ERR(ops))
return PTR_ERR(ops);
if (!ops->tmplt_create || !ops->tmplt_destroy || !ops->tmplt_dump) {
@@ -2699,9 +2717,9 @@ static int tc_ctl_chain(struct sk_buff *skb, struct nlmsghdr *n,
break;
case RTM_DELCHAIN:
tfilter_notify_chain(net, skb, block, q, parent, n,
- chain, RTM_DELTFILTER);
+ chain, RTM_DELTFILTER, true);
/* Flush the chain first as the user requested chain removal. */
- tcf_chain_flush(chain);
+ tcf_chain_flush(chain, true);
/* In case the chain was successfully deleted, put a reference
* to the chain previously taken during addition.
*/
@@ -2722,7 +2740,7 @@ static int tc_ctl_chain(struct sk_buff *skb, struct nlmsghdr *n,
errout:
tcf_chain_put(chain);
errout_block:
- tcf_block_release(q, block);
+ tcf_block_release(q, block, true);
if (err == -EAGAIN)
/* Replay the request. */
goto replay;
@@ -2829,7 +2847,7 @@ static int tc_dump_chain(struct sk_buff *skb, struct netlink_callback *cb)
}
if (tcm->tcm_ifindex == TCM_IFINDEX_MAGIC_BLOCK)
- tcf_block_refcnt_put(block);
+ tcf_block_refcnt_put(block, true);
cb->args[0] = index;
out:
diff --git a/net/sched/cls_basic.c b/net/sched/cls_basic.c
index eaf9c02fe792..2383f449d2bc 100644
--- a/net/sched/cls_basic.c
+++ b/net/sched/cls_basic.c
@@ -107,7 +107,8 @@ static void basic_delete_filter_work(struct work_struct *work)
rtnl_unlock();
}
-static void basic_destroy(struct tcf_proto *tp, struct netlink_ext_ack *extack)
+static void basic_destroy(struct tcf_proto *tp, bool rtnl_held,
+ struct netlink_ext_ack *extack)
{
struct basic_head *head = rtnl_dereference(tp->root);
struct basic_filter *f, *n;
@@ -126,7 +127,7 @@ static void basic_destroy(struct tcf_proto *tp, struct netlink_ext_ack *extack)
}
static int basic_delete(struct tcf_proto *tp, void *arg, bool *last,
- struct netlink_ext_ack *extack)
+ bool rtnl_held, struct netlink_ext_ack *extack)
{
struct basic_head *head = rtnl_dereference(tp->root);
struct basic_filter *f = arg;
@@ -173,7 +174,7 @@ static int basic_set_parms(struct net *net, struct tcf_proto *tp,
static int basic_change(struct net *net, struct sk_buff *in_skb,
struct tcf_proto *tp, unsigned long base, u32 handle,
struct nlattr **tca, void **arg, bool ovr,
- struct netlink_ext_ack *extack)
+ bool rtnl_held, struct netlink_ext_ack *extack)
{
int err;
struct basic_head *head = rtnl_dereference(tp->root);
@@ -247,7 +248,8 @@ static int basic_change(struct net *net, struct sk_buff *in_skb,
return err;
}
-static void basic_walk(struct tcf_proto *tp, struct tcf_walker *arg)
+static void basic_walk(struct tcf_proto *tp, struct tcf_walker *arg,
+ bool rtnl_held)
{
struct basic_head *head = rtnl_dereference(tp->root);
struct basic_filter *f;
@@ -274,7 +276,7 @@ static void basic_bind_class(void *fh, u32 classid, unsigned long cl)
}
static int basic_dump(struct net *net, struct tcf_proto *tp, void *fh,
- struct sk_buff *skb, struct tcmsg *t)
+ struct sk_buff *skb, struct tcmsg *t, bool rtnl_held)
{
struct tc_basic_pcnt gpf = {};
struct basic_filter *f = fh;
diff --git a/net/sched/cls_bpf.c b/net/sched/cls_bpf.c
index 656b3423ad35..062350c6621c 100644
--- a/net/sched/cls_bpf.c
+++ b/net/sched/cls_bpf.c
@@ -298,7 +298,7 @@ static void __cls_bpf_delete(struct tcf_proto *tp, struct cls_bpf_prog *prog,
}
static int cls_bpf_delete(struct tcf_proto *tp, void *arg, bool *last,
- struct netlink_ext_ack *extack)
+ bool rtnl_held, struct netlink_ext_ack *extack)
{
struct cls_bpf_head *head = rtnl_dereference(tp->root);
@@ -307,7 +307,7 @@ static int cls_bpf_delete(struct tcf_proto *tp, void *arg, bool *last,
return 0;
}
-static void cls_bpf_destroy(struct tcf_proto *tp,
+static void cls_bpf_destroy(struct tcf_proto *tp, bool rtnl_held,
struct netlink_ext_ack *extack)
{
struct cls_bpf_head *head = rtnl_dereference(tp->root);
@@ -456,7 +456,8 @@ static int cls_bpf_set_parms(struct net *net, struct tcf_proto *tp,
static int cls_bpf_change(struct net *net, struct sk_buff *in_skb,
struct tcf_proto *tp, unsigned long base,
u32 handle, struct nlattr **tca,
- void **arg, bool ovr, struct netlink_ext_ack *extack)
+ void **arg, bool ovr, bool rtnl_held,
+ struct netlink_ext_ack *extack)
{
struct cls_bpf_head *head = rtnl_dereference(tp->root);
struct cls_bpf_prog *oldprog = *arg;
@@ -576,7 +577,7 @@ static int cls_bpf_dump_ebpf_info(const struct cls_bpf_prog *prog,
}
static int cls_bpf_dump(struct net *net, struct tcf_proto *tp, void *fh,
- struct sk_buff *skb, struct tcmsg *tm)
+ struct sk_buff *skb, struct tcmsg *tm, bool rtnl_held)
{
struct cls_bpf_prog *prog = fh;
struct nlattr *nest;
@@ -636,7 +637,8 @@ static void cls_bpf_bind_class(void *fh, u32 classid, unsigned long cl)
prog->res.class = cl;
}
-static void cls_bpf_walk(struct tcf_proto *tp, struct tcf_walker *arg)
+static void cls_bpf_walk(struct tcf_proto *tp, struct tcf_walker *arg,
+ bool rtnl_held)
{
struct cls_bpf_head *head = rtnl_dereference(tp->root);
struct cls_bpf_prog *prog;
diff --git a/net/sched/cls_cgroup.c b/net/sched/cls_cgroup.c
index 663ee1c6d606..1cef3b416094 100644
--- a/net/sched/cls_cgroup.c
+++ b/net/sched/cls_cgroup.c
@@ -78,7 +78,7 @@ static void cls_cgroup_destroy_work(struct work_struct *work)
static int cls_cgroup_change(struct net *net, struct sk_buff *in_skb,
struct tcf_proto *tp, unsigned long base,
u32 handle, struct nlattr **tca,
- void **arg, bool ovr,
+ void **arg, bool ovr, bool rtnl_held,
struct netlink_ext_ack *extack)
{
struct nlattr *tb[TCA_CGROUP_MAX + 1];
@@ -130,7 +130,7 @@ static int cls_cgroup_change(struct net *net, struct sk_buff *in_skb,
return err;
}
-static void cls_cgroup_destroy(struct tcf_proto *tp,
+static void cls_cgroup_destroy(struct tcf_proto *tp, bool rtnl_held,
struct netlink_ext_ack *extack)
{
struct cls_cgroup_head *head = rtnl_dereference(tp->root);
@@ -145,12 +145,13 @@ static void cls_cgroup_destroy(struct tcf_proto *tp,
}
static int cls_cgroup_delete(struct tcf_proto *tp, void *arg, bool *last,
- struct netlink_ext_ack *extack)
+ bool rtnl_held, struct netlink_ext_ack *extack)
{
return -EOPNOTSUPP;
}
-static void cls_cgroup_walk(struct tcf_proto *tp, struct tcf_walker *arg)
+static void cls_cgroup_walk(struct tcf_proto *tp, struct tcf_walker *arg,
+ bool rtnl_held)
{
struct cls_cgroup_head *head = rtnl_dereference(tp->root);
@@ -166,7 +167,7 @@ static void cls_cgroup_walk(struct tcf_proto *tp, struct tcf_walker *arg)
}
static int cls_cgroup_dump(struct net *net, struct tcf_proto *tp, void *fh,
- struct sk_buff *skb, struct tcmsg *t)
+ struct sk_buff *skb, struct tcmsg *t, bool rtnl_held)
{
struct cls_cgroup_head *head = rtnl_dereference(tp->root);
struct nlattr *nest;
diff --git a/net/sched/cls_flow.c b/net/sched/cls_flow.c
index 39a6407d4832..204e2edae8d5 100644
--- a/net/sched/cls_flow.c
+++ b/net/sched/cls_flow.c
@@ -391,7 +391,8 @@ static void flow_destroy_filter_work(struct work_struct *work)
static int flow_change(struct net *net, struct sk_buff *in_skb,
struct tcf_proto *tp, unsigned long base,
u32 handle, struct nlattr **tca,
- void **arg, bool ovr, struct netlink_ext_ack *extack)
+ void **arg, bool ovr, bool rtnl_held,
+ struct netlink_ext_ack *extack)
{
struct flow_head *head = rtnl_dereference(tp->root);
struct flow_filter *fold, *fnew;
@@ -566,7 +567,7 @@ static int flow_change(struct net *net, struct sk_buff *in_skb,
}
static int flow_delete(struct tcf_proto *tp, void *arg, bool *last,
- struct netlink_ext_ack *extack)
+ bool rtnl_held, struct netlink_ext_ack *extack)
{
struct flow_head *head = rtnl_dereference(tp->root);
struct flow_filter *f = arg;
@@ -590,7 +591,8 @@ static int flow_init(struct tcf_proto *tp)
return 0;
}
-static void flow_destroy(struct tcf_proto *tp, struct netlink_ext_ack *extack)
+static void flow_destroy(struct tcf_proto *tp, bool rtnl_held,
+ struct netlink_ext_ack *extack)
{
struct flow_head *head = rtnl_dereference(tp->root);
struct flow_filter *f, *next;
@@ -617,7 +619,7 @@ static void *flow_get(struct tcf_proto *tp, u32 handle)
}
static int flow_dump(struct net *net, struct tcf_proto *tp, void *fh,
- struct sk_buff *skb, struct tcmsg *t)
+ struct sk_buff *skb, struct tcmsg *t, bool rtnl_held)
{
struct flow_filter *f = fh;
struct nlattr *nest;
@@ -677,7 +679,8 @@ static int flow_dump(struct net *net, struct tcf_proto *tp, void *fh,
return -1;
}
-static void flow_walk(struct tcf_proto *tp, struct tcf_walker *arg)
+static void flow_walk(struct tcf_proto *tp, struct tcf_walker *arg,
+ bool rtnl_held)
{
struct flow_head *head = rtnl_dereference(tp->root);
struct flow_filter *f;
diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c
index d187bda602fa..5663f2b35de0 100644
--- a/net/sched/cls_flower.c
+++ b/net/sched/cls_flower.c
@@ -465,7 +465,8 @@ static void fl_destroy_sleepable(struct work_struct *work)
module_put(THIS_MODULE);
}
-static void fl_destroy(struct tcf_proto *tp, struct netlink_ext_ack *extack)
+static void fl_destroy(struct tcf_proto *tp, bool rtnl_held,
+ struct netlink_ext_ack *extack)
{
struct cls_fl_head *head = rtnl_dereference(tp->root);
struct fl_flow_mask *mask, *next_mask;
@@ -1300,7 +1301,8 @@ static int fl_set_parms(struct net *net, struct tcf_proto *tp,
static int fl_change(struct net *net, struct sk_buff *in_skb,
struct tcf_proto *tp, unsigned long base,
u32 handle, struct nlattr **tca,
- void **arg, bool ovr, struct netlink_ext_ack *extack)
+ void **arg, bool ovr, bool rtnl_held,
+ struct netlink_ext_ack *extack)
{
struct cls_fl_head *head = rtnl_dereference(tp->root);
struct cls_fl_filter *fold = *arg;
@@ -1433,7 +1435,7 @@ static int fl_change(struct net *net, struct sk_buff *in_skb,
}
static int fl_delete(struct tcf_proto *tp, void *arg, bool *last,
- struct netlink_ext_ack *extack)
+ bool rtnl_held, struct netlink_ext_ack *extack)
{
struct cls_fl_head *head = rtnl_dereference(tp->root);
struct cls_fl_filter *f = arg;
@@ -1445,7 +1447,8 @@ static int fl_delete(struct tcf_proto *tp, void *arg, bool *last,
return 0;
}
-static void fl_walk(struct tcf_proto *tp, struct tcf_walker *arg)
+static void fl_walk(struct tcf_proto *tp, struct tcf_walker *arg,
+ bool rtnl_held)
{
struct cls_fl_head *head = rtnl_dereference(tp->root);
struct cls_fl_filter *f;
@@ -2040,7 +2043,7 @@ static int fl_dump_key(struct sk_buff *skb, struct net *net,
}
static int fl_dump(struct net *net, struct tcf_proto *tp, void *fh,
- struct sk_buff *skb, struct tcmsg *t)
+ struct sk_buff *skb, struct tcmsg *t, bool rtnl_held)
{
struct cls_fl_filter *f = fh;
struct nlattr *nest;
diff --git a/net/sched/cls_fw.c b/net/sched/cls_fw.c
index c8173ebb69f2..317151bae73b 100644
--- a/net/sched/cls_fw.c
+++ b/net/sched/cls_fw.c
@@ -139,7 +139,8 @@ static void fw_delete_filter_work(struct work_struct *work)
rtnl_unlock();
}
-static void fw_destroy(struct tcf_proto *tp, struct netlink_ext_ack *extack)
+static void fw_destroy(struct tcf_proto *tp, bool rtnl_held,
+ struct netlink_ext_ack *extack)
{
struct fw_head *head = rtnl_dereference(tp->root);
struct fw_filter *f;
@@ -163,7 +164,7 @@ static void fw_destroy(struct tcf_proto *tp, struct netlink_ext_ack *extack)
}
static int fw_delete(struct tcf_proto *tp, void *arg, bool *last,
- struct netlink_ext_ack *extack)
+ bool rtnl_held, struct netlink_ext_ack *extack)
{
struct fw_head *head = rtnl_dereference(tp->root);
struct fw_filter *f = arg;
@@ -250,7 +251,8 @@ static int fw_set_parms(struct net *net, struct tcf_proto *tp,
static int fw_change(struct net *net, struct sk_buff *in_skb,
struct tcf_proto *tp, unsigned long base,
u32 handle, struct nlattr **tca, void **arg,
- bool ovr, struct netlink_ext_ack *extack)
+ bool ovr, bool rtnl_held,
+ struct netlink_ext_ack *extack)
{
struct fw_head *head = rtnl_dereference(tp->root);
struct fw_filter *f = *arg;
@@ -354,7 +356,8 @@ static int fw_change(struct net *net, struct sk_buff *in_skb,
return err;
}
-static void fw_walk(struct tcf_proto *tp, struct tcf_walker *arg)
+static void fw_walk(struct tcf_proto *tp, struct tcf_walker *arg,
+ bool rtnl_held)
{
struct fw_head *head = rtnl_dereference(tp->root);
int h;
@@ -384,7 +387,7 @@ static void fw_walk(struct tcf_proto *tp, struct tcf_walker *arg)
}
static int fw_dump(struct net *net, struct tcf_proto *tp, void *fh,
- struct sk_buff *skb, struct tcmsg *t)
+ struct sk_buff *skb, struct tcmsg *t, bool rtnl_held)
{
struct fw_head *head = rtnl_dereference(tp->root);
struct fw_filter *f = fh;
diff --git a/net/sched/cls_matchall.c b/net/sched/cls_matchall.c
index 8848a147c4bf..a37137430e61 100644
--- a/net/sched/cls_matchall.c
+++ b/net/sched/cls_matchall.c
@@ -109,7 +109,8 @@ static int mall_replace_hw_filter(struct tcf_proto *tp,
return 0;
}
-static void mall_destroy(struct tcf_proto *tp, struct netlink_ext_ack *extack)
+static void mall_destroy(struct tcf_proto *tp, bool rtnl_held,
+ struct netlink_ext_ack *extack)
{
struct cls_mall_head *head = rtnl_dereference(tp->root);
@@ -160,7 +161,8 @@ static int mall_set_parms(struct net *net, struct tcf_proto *tp,
static int mall_change(struct net *net, struct sk_buff *in_skb,
struct tcf_proto *tp, unsigned long base,
u32 handle, struct nlattr **tca,
- void **arg, bool ovr, struct netlink_ext_ack *extack)
+ void **arg, bool ovr, bool rtnl_held,
+ struct netlink_ext_ack *extack)
{
struct cls_mall_head *head = rtnl_dereference(tp->root);
struct nlattr *tb[TCA_MATCHALL_MAX + 1];
@@ -233,12 +235,13 @@ static int mall_change(struct net *net, struct sk_buff *in_skb,
}
static int mall_delete(struct tcf_proto *tp, void *arg, bool *last,
- struct netlink_ext_ack *extack)
+ bool rtnl_held, struct netlink_ext_ack *extack)
{
return -EOPNOTSUPP;
}
-static void mall_walk(struct tcf_proto *tp, struct tcf_walker *arg)
+static void mall_walk(struct tcf_proto *tp, struct tcf_walker *arg,
+ bool rtnl_held)
{
struct cls_mall_head *head = rtnl_dereference(tp->root);
@@ -280,7 +283,7 @@ static int mall_reoffload(struct tcf_proto *tp, bool add, tc_setup_cb_t *cb,
}
static int mall_dump(struct net *net, struct tcf_proto *tp, void *fh,
- struct sk_buff *skb, struct tcmsg *t)
+ struct sk_buff *skb, struct tcmsg *t, bool rtnl_held)
{
struct tc_matchall_pcnt gpf = {};
struct cls_mall_head *head = fh;
diff --git a/net/sched/cls_route.c b/net/sched/cls_route.c
index 44b26038c4c4..e590c3a2999d 100644
--- a/net/sched/cls_route.c
+++ b/net/sched/cls_route.c
@@ -276,7 +276,8 @@ static void route4_queue_work(struct route4_filter *f)
tcf_queue_work(&f->rwork, route4_delete_filter_work);
}
-static void route4_destroy(struct tcf_proto *tp, struct netlink_ext_ack *extack)
+static void route4_destroy(struct tcf_proto *tp, bool rtnl_held,
+ struct netlink_ext_ack *extack)
{
struct route4_head *head = rtnl_dereference(tp->root);
int h1, h2;
@@ -312,7 +313,7 @@ static void route4_destroy(struct tcf_proto *tp, struct netlink_ext_ack *extack)
}
static int route4_delete(struct tcf_proto *tp, void *arg, bool *last,
- struct netlink_ext_ack *extack)
+ bool rtnl_held, struct netlink_ext_ack *extack)
{
struct route4_head *head = rtnl_dereference(tp->root);
struct route4_filter *f = arg;
@@ -468,7 +469,7 @@ static int route4_set_parms(struct net *net, struct tcf_proto *tp,
static int route4_change(struct net *net, struct sk_buff *in_skb,
struct tcf_proto *tp, unsigned long base, u32 handle,
struct nlattr **tca, void **arg, bool ovr,
- struct netlink_ext_ack *extack)
+ bool rtnl_held, struct netlink_ext_ack *extack)
{
struct route4_head *head = rtnl_dereference(tp->root);
struct route4_filter __rcu **fp;
@@ -560,7 +561,8 @@ static int route4_change(struct net *net, struct sk_buff *in_skb,
return err;
}
-static void route4_walk(struct tcf_proto *tp, struct tcf_walker *arg)
+static void route4_walk(struct tcf_proto *tp, struct tcf_walker *arg,
+ bool rtnl_held)
{
struct route4_head *head = rtnl_dereference(tp->root);
unsigned int h, h1;
@@ -597,7 +599,7 @@ static void route4_walk(struct tcf_proto *tp, struct tcf_walker *arg)
}
static int route4_dump(struct net *net, struct tcf_proto *tp, void *fh,
- struct sk_buff *skb, struct tcmsg *t)
+ struct sk_buff *skb, struct tcmsg *t, bool rtnl_held)
{
struct route4_filter *f = fh;
struct nlattr *nest;
diff --git a/net/sched/cls_rsvp.h b/net/sched/cls_rsvp.h
index 9dd9530e6a52..4d3836178fa5 100644
--- a/net/sched/cls_rsvp.h
+++ b/net/sched/cls_rsvp.h
@@ -312,7 +312,8 @@ static void rsvp_delete_filter(struct tcf_proto *tp, struct rsvp_filter *f)
__rsvp_delete_filter(f);
}
-static void rsvp_destroy(struct tcf_proto *tp, struct netlink_ext_ack *extack)
+static void rsvp_destroy(struct tcf_proto *tp, bool rtnl_held,
+ struct netlink_ext_ack *extack)
{
struct rsvp_head *data = rtnl_dereference(tp->root);
int h1, h2;
@@ -341,7 +342,7 @@ static void rsvp_destroy(struct tcf_proto *tp, struct netlink_ext_ack *extack)
}
static int rsvp_delete(struct tcf_proto *tp, void *arg, bool *last,
- struct netlink_ext_ack *extack)
+ bool rtnl_held, struct netlink_ext_ack *extack)
{
struct rsvp_head *head = rtnl_dereference(tp->root);
struct rsvp_filter *nfp, *f = arg;
@@ -477,7 +478,8 @@ static int rsvp_change(struct net *net, struct sk_buff *in_skb,
struct tcf_proto *tp, unsigned long base,
u32 handle,
struct nlattr **tca,
- void **arg, bool ovr, struct netlink_ext_ack *extack)
+ void **arg, bool ovr, bool rtnl_held,
+ struct netlink_ext_ack *extack)
{
struct rsvp_head *data = rtnl_dereference(tp->root);
struct rsvp_filter *f, *nfp;
@@ -655,7 +657,8 @@ static int rsvp_change(struct net *net, struct sk_buff *in_skb,
return err;
}
-static void rsvp_walk(struct tcf_proto *tp, struct tcf_walker *arg)
+static void rsvp_walk(struct tcf_proto *tp, struct tcf_walker *arg,
+ bool rtnl_held)
{
struct rsvp_head *head = rtnl_dereference(tp->root);
unsigned int h, h1;
@@ -689,7 +692,7 @@ static void rsvp_walk(struct tcf_proto *tp, struct tcf_walker *arg)
}
static int rsvp_dump(struct net *net, struct tcf_proto *tp, void *fh,
- struct sk_buff *skb, struct tcmsg *t)
+ struct sk_buff *skb, struct tcmsg *t, bool rtnl_held)
{
struct rsvp_filter *f = fh;
struct rsvp_session *s;
diff --git a/net/sched/cls_tcindex.c b/net/sched/cls_tcindex.c
index b7dc667b6ec0..14d6b4058045 100644
--- a/net/sched/cls_tcindex.c
+++ b/net/sched/cls_tcindex.c
@@ -173,7 +173,7 @@ static void tcindex_destroy_fexts_work(struct work_struct *work)
}
static int tcindex_delete(struct tcf_proto *tp, void *arg, bool *last,
- struct netlink_ext_ack *extack)
+ bool rtnl_held, struct netlink_ext_ack *extack)
{
struct tcindex_data *p = rtnl_dereference(tp->root);
struct tcindex_filter_result *r = arg;
@@ -226,7 +226,7 @@ static int tcindex_destroy_element(struct tcf_proto *tp,
{
bool last;
- return tcindex_delete(tp, arg, &last, NULL);
+ return tcindex_delete(tp, arg, &last, false, NULL);
}
static void __tcindex_destroy(struct rcu_head *head)
@@ -499,7 +499,7 @@ static int
tcindex_change(struct net *net, struct sk_buff *in_skb,
struct tcf_proto *tp, unsigned long base, u32 handle,
struct nlattr **tca, void **arg, bool ovr,
- struct netlink_ext_ack *extack)
+ bool rtnl_held, struct netlink_ext_ack *extack)
{
struct nlattr *opt = tca[TCA_OPTIONS];
struct nlattr *tb[TCA_TCINDEX_MAX + 1];
@@ -522,7 +522,8 @@ tcindex_change(struct net *net, struct sk_buff *in_skb,
tca[TCA_RATE], ovr, extack);
}
-static void tcindex_walk(struct tcf_proto *tp, struct tcf_walker *walker)
+static void tcindex_walk(struct tcf_proto *tp, struct tcf_walker *walker,
+ bool rtnl_held)
{
struct tcindex_data *p = rtnl_dereference(tp->root);
struct tcindex_filter *f, *next;
@@ -558,7 +559,7 @@ static void tcindex_walk(struct tcf_proto *tp, struct tcf_walker *walker)
}
}
-static void tcindex_destroy(struct tcf_proto *tp,
+static void tcindex_destroy(struct tcf_proto *tp, bool rtnl_held,
struct netlink_ext_ack *extack)
{
struct tcindex_data *p = rtnl_dereference(tp->root);
@@ -568,14 +569,14 @@ static void tcindex_destroy(struct tcf_proto *tp,
walker.count = 0;
walker.skip = 0;
walker.fn = tcindex_destroy_element;
- tcindex_walk(tp, &walker);
+ tcindex_walk(tp, &walker, true);
call_rcu(&p->rcu, __tcindex_destroy);
}
static int tcindex_dump(struct net *net, struct tcf_proto *tp, void *fh,
- struct sk_buff *skb, struct tcmsg *t)
+ struct sk_buff *skb, struct tcmsg *t, bool rtnl_held)
{
struct tcindex_data *p = rtnl_dereference(tp->root);
struct tcindex_filter_result *r = fh;
diff --git a/net/sched/cls_u32.c b/net/sched/cls_u32.c
index e891f30d42e9..27d29c04dcc9 100644
--- a/net/sched/cls_u32.c
+++ b/net/sched/cls_u32.c
@@ -629,7 +629,8 @@ static int u32_destroy_hnode(struct tcf_proto *tp, struct tc_u_hnode *ht,
return -ENOENT;
}
-static void u32_destroy(struct tcf_proto *tp, struct netlink_ext_ack *extack)
+static void u32_destroy(struct tcf_proto *tp, bool rtnl_held,
+ struct netlink_ext_ack *extack)
{
struct tc_u_common *tp_c = tp->data;
struct tc_u_hnode *root_ht = rtnl_dereference(tp->root);
@@ -663,7 +664,7 @@ static void u32_destroy(struct tcf_proto *tp, struct netlink_ext_ack *extack)
}
static int u32_delete(struct tcf_proto *tp, void *arg, bool *last,
- struct netlink_ext_ack *extack)
+ bool rtnl_held, struct netlink_ext_ack *extack)
{
struct tc_u_hnode *ht = arg;
struct tc_u_common *tp_c = tp->data;
@@ -858,7 +859,7 @@ static struct tc_u_knode *u32_init_knode(struct tcf_proto *tp,
static int u32_change(struct net *net, struct sk_buff *in_skb,
struct tcf_proto *tp, unsigned long base, u32 handle,
- struct nlattr **tca, void **arg, bool ovr,
+ struct nlattr **tca, void **arg, bool ovr, bool rtnl_held,
struct netlink_ext_ack *extack)
{
struct tc_u_common *tp_c = tp->data;
@@ -1123,7 +1124,8 @@ static int u32_change(struct net *net, struct sk_buff *in_skb,
return err;
}
-static void u32_walk(struct tcf_proto *tp, struct tcf_walker *arg)
+static void u32_walk(struct tcf_proto *tp, struct tcf_walker *arg,
+ bool rtnl_held)
{
struct tc_u_common *tp_c = tp->data;
struct tc_u_hnode *ht;
@@ -1281,7 +1283,7 @@ static void u32_bind_class(void *fh, u32 classid, unsigned long cl)
}
static int u32_dump(struct net *net, struct tcf_proto *tp, void *fh,
- struct sk_buff *skb, struct tcmsg *t)
+ struct sk_buff *skb, struct tcmsg *t, bool rtnl_held)
{
struct tc_u_knode *n = fh;
struct tc_u_hnode *ht_up, *ht_down;
diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c
index 9a530cad2759..2283924fb56d 100644
--- a/net/sched/sch_api.c
+++ b/net/sched/sch_api.c
@@ -1914,14 +1914,14 @@ static void tc_bind_tclass(struct Qdisc *q, u32 portid, u32 clid,
chain = tcf_get_next_chain(block, chain)) {
struct tcf_proto *tp;
- for (tp = tcf_get_next_proto(chain, NULL);
- tp; tp = tcf_get_next_proto(chain, tp)) {
+ for (tp = tcf_get_next_proto(chain, NULL, true);
+ tp; tp = tcf_get_next_proto(chain, tp, true)) {
struct tcf_bind_args arg = {};
arg.w.fn = tcf_node_bind;
arg.classid = clid;
arg.cl = new_cl;
- tp->ops->walk(tp, &arg.w);
+ tp->ops->walk(tp, &arg.w, true);
}
}
}
--
2.13.6
^ permalink raw reply related
* [PATCH net-next v4 16/17] net: sched: refactor tcf_block_find() into standalone functions
From: Vlad Buslov @ 2019-02-11 8:55 UTC (permalink / raw)
To: netdev; +Cc: jhs, xiyou.wangcong, jiri, davem, ast, daniel, Vlad Buslov
In-Reply-To: <20190211085548.7190-1-vladbu@mellanox.com>
Refactor tcf_block_find() code into three standalone functions:
- __tcf_qdisc_find() to lookup Qdisc and increment its reference counter.
- __tcf_qdisc_cl_find() to lookup class.
- __tcf_block_find() to lookup block and increment its reference counter.
This change is necessary to allow netlink tc rule update handlers to call
these functions directly in order to conditionally take rtnl lock
according to Qdisc class ops flags before calling any of class ops
functions.
Signed-off-by: Vlad Buslov <vladbu@mellanox.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
---
net/sched/cls_api.c | 241 ++++++++++++++++++++++++++++++++--------------------
1 file changed, 149 insertions(+), 92 deletions(-)
diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c
index e8ed461e94af..5f9373ee47ce 100644
--- a/net/sched/cls_api.c
+++ b/net/sched/cls_api.c
@@ -1101,6 +1101,142 @@ static void tcf_block_flush_all_chains(struct tcf_block *block, bool rtnl_held)
}
}
+/* Lookup Qdisc and increments its reference counter.
+ * Set parent, if necessary.
+ */
+
+static int __tcf_qdisc_find(struct net *net, struct Qdisc **q,
+ u32 *parent, int ifindex, bool rtnl_held,
+ struct netlink_ext_ack *extack)
+{
+ const struct Qdisc_class_ops *cops;
+ struct net_device *dev;
+ int err = 0;
+
+ if (ifindex == TCM_IFINDEX_MAGIC_BLOCK)
+ return 0;
+
+ rcu_read_lock();
+
+ /* Find link */
+ dev = dev_get_by_index_rcu(net, ifindex);
+ if (!dev) {
+ rcu_read_unlock();
+ return -ENODEV;
+ }
+
+ /* Find qdisc */
+ if (!*parent) {
+ *q = dev->qdisc;
+ *parent = (*q)->handle;
+ } else {
+ *q = qdisc_lookup_rcu(dev, TC_H_MAJ(*parent));
+ if (!*q) {
+ NL_SET_ERR_MSG(extack, "Parent Qdisc doesn't exists");
+ err = -EINVAL;
+ goto errout_rcu;
+ }
+ }
+
+ *q = qdisc_refcount_inc_nz(*q);
+ if (!*q) {
+ NL_SET_ERR_MSG(extack, "Parent Qdisc doesn't exists");
+ err = -EINVAL;
+ goto errout_rcu;
+ }
+
+ /* Is it classful? */
+ cops = (*q)->ops->cl_ops;
+ if (!cops) {
+ NL_SET_ERR_MSG(extack, "Qdisc not classful");
+ err = -EINVAL;
+ goto errout_qdisc;
+ }
+
+ if (!cops->tcf_block) {
+ NL_SET_ERR_MSG(extack, "Class doesn't support blocks");
+ err = -EOPNOTSUPP;
+ goto errout_qdisc;
+ }
+
+errout_rcu:
+ /* At this point we know that qdisc is not noop_qdisc,
+ * which means that qdisc holds a reference to net_device
+ * and we hold a reference to qdisc, so it is safe to release
+ * rcu read lock.
+ */
+ rcu_read_unlock();
+ return err;
+
+errout_qdisc:
+ rcu_read_unlock();
+
+ if (rtnl_held)
+ qdisc_put(*q);
+ else
+ qdisc_put_unlocked(*q);
+ *q = NULL;
+
+ return err;
+}
+
+static int __tcf_qdisc_cl_find(struct Qdisc *q, u32 parent, unsigned long *cl,
+ int ifindex, struct netlink_ext_ack *extack)
+{
+ if (ifindex == TCM_IFINDEX_MAGIC_BLOCK)
+ return 0;
+
+ /* Do we search for filter, attached to class? */
+ if (TC_H_MIN(parent)) {
+ const struct Qdisc_class_ops *cops = q->ops->cl_ops;
+
+ *cl = cops->find(q, parent);
+ if (*cl == 0) {
+ NL_SET_ERR_MSG(extack, "Specified class doesn't exist");
+ return -ENOENT;
+ }
+ }
+
+ return 0;
+}
+
+static struct tcf_block *__tcf_block_find(struct net *net, struct Qdisc *q,
+ unsigned long cl, int ifindex,
+ u32 block_index,
+ struct netlink_ext_ack *extack)
+{
+ struct tcf_block *block;
+
+ if (ifindex == TCM_IFINDEX_MAGIC_BLOCK) {
+ block = tcf_block_refcnt_get(net, block_index);
+ if (!block) {
+ NL_SET_ERR_MSG(extack, "Block of given index was not found");
+ return ERR_PTR(-EINVAL);
+ }
+ } else {
+ const struct Qdisc_class_ops *cops = q->ops->cl_ops;
+
+ block = cops->tcf_block(q, cl, extack);
+ if (!block)
+ return ERR_PTR(-EINVAL);
+
+ if (tcf_block_shared(block)) {
+ NL_SET_ERR_MSG(extack, "This filter block is shared. Please use the block index to manipulate the filters");
+ return ERR_PTR(-EOPNOTSUPP);
+ }
+
+ /* Always take reference to block in order to support execution
+ * of rules update path of cls API without rtnl lock. Caller
+ * must release block when it is finished using it. 'if' block
+ * of this conditional obtain reference to block by calling
+ * tcf_block_refcnt_get().
+ */
+ refcount_inc(&block->refcnt);
+ }
+
+ return block;
+}
+
static void __tcf_block_put(struct tcf_block *block, struct Qdisc *q,
struct tcf_block_ext_info *ei, bool rtnl_held)
{
@@ -1146,106 +1282,27 @@ static struct tcf_block *tcf_block_find(struct net *net, struct Qdisc **q,
struct tcf_block *block;
int err = 0;
- if (ifindex == TCM_IFINDEX_MAGIC_BLOCK) {
- block = tcf_block_refcnt_get(net, block_index);
- if (!block) {
- NL_SET_ERR_MSG(extack, "Block of given index was not found");
- return ERR_PTR(-EINVAL);
- }
- } else {
- const struct Qdisc_class_ops *cops;
- struct net_device *dev;
-
- rcu_read_lock();
-
- /* Find link */
- dev = dev_get_by_index_rcu(net, ifindex);
- if (!dev) {
- rcu_read_unlock();
- return ERR_PTR(-ENODEV);
- }
-
- /* Find qdisc */
- if (!*parent) {
- *q = dev->qdisc;
- *parent = (*q)->handle;
- } else {
- *q = qdisc_lookup_rcu(dev, TC_H_MAJ(*parent));
- if (!*q) {
- NL_SET_ERR_MSG(extack, "Parent Qdisc doesn't exists");
- err = -EINVAL;
- goto errout_rcu;
- }
- }
-
- *q = qdisc_refcount_inc_nz(*q);
- if (!*q) {
- NL_SET_ERR_MSG(extack, "Parent Qdisc doesn't exists");
- err = -EINVAL;
- goto errout_rcu;
- }
-
- /* Is it classful? */
- cops = (*q)->ops->cl_ops;
- if (!cops) {
- NL_SET_ERR_MSG(extack, "Qdisc not classful");
- err = -EINVAL;
- goto errout_rcu;
- }
-
- if (!cops->tcf_block) {
- NL_SET_ERR_MSG(extack, "Class doesn't support blocks");
- err = -EOPNOTSUPP;
- goto errout_rcu;
- }
-
- /* At this point we know that qdisc is not noop_qdisc,
- * which means that qdisc holds a reference to net_device
- * and we hold a reference to qdisc, so it is safe to release
- * rcu read lock.
- */
- rcu_read_unlock();
+ ASSERT_RTNL();
- /* Do we search for filter, attached to class? */
- if (TC_H_MIN(*parent)) {
- *cl = cops->find(*q, *parent);
- if (*cl == 0) {
- NL_SET_ERR_MSG(extack, "Specified class doesn't exist");
- err = -ENOENT;
- goto errout_qdisc;
- }
- }
+ err = __tcf_qdisc_find(net, q, parent, ifindex, true, extack);
+ if (err)
+ goto errout;
- /* And the last stroke */
- block = cops->tcf_block(*q, *cl, extack);
- if (!block) {
- err = -EINVAL;
- goto errout_qdisc;
- }
- if (tcf_block_shared(block)) {
- NL_SET_ERR_MSG(extack, "This filter block is shared. Please use the block index to manipulate the filters");
- err = -EOPNOTSUPP;
- goto errout_qdisc;
- }
+ err = __tcf_qdisc_cl_find(*q, *parent, cl, ifindex, extack);
+ if (err)
+ goto errout_qdisc;
- /* Always take reference to block in order to support execution
- * of rules update path of cls API without rtnl lock. Caller
- * must release block when it is finished using it. 'if' block
- * of this conditional obtain reference to block by calling
- * tcf_block_refcnt_get().
- */
- refcount_inc(&block->refcnt);
- }
+ block = __tcf_block_find(net, *q, *cl, ifindex, block_index, extack);
+ if (IS_ERR(block))
+ goto errout_qdisc;
return block;
-errout_rcu:
- rcu_read_unlock();
errout_qdisc:
- if (*q) {
+ if (*q)
qdisc_put(*q);
- *q = NULL;
- }
+errout:
+ *q = NULL;
return ERR_PTR(err);
}
--
2.13.6
^ permalink raw reply related
* [PATCH net-next v4 10/17] net: sched: refactor tp insert/delete for concurrent execution
From: Vlad Buslov @ 2019-02-11 8:55 UTC (permalink / raw)
To: netdev; +Cc: jhs, xiyou.wangcong, jiri, davem, ast, daniel, Vlad Buslov
In-Reply-To: <20190211085548.7190-1-vladbu@mellanox.com>
Implement unique insertion function to atomically attach tcf_proto to chain
after verifying that no other tcf proto with specified priority exists.
Implement delete function that verifies that tp is actually empty before
deleting it. Use these functions to refactor cls API to account for
concurrent tp and rule update instead of relying on rtnl lock. Add new
'deleting' flag to tcf proto. Use it to restart search when iterating over
tp's on chain to prevent accessing potentially inval tp->next pointer.
Extend tcf proto with spinlock that is intended to be used to protect its
data from concurrent modification instead of relying on rtnl mutex. Use it
to protect 'deleting' flag. Add lockdep macros to validate that lock is
held when accessing protected fields.
Signed-off-by: Vlad Buslov <vladbu@mellanox.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
---
include/net/sch_generic.h | 18 +++++
net/sched/cls_api.c | 177 +++++++++++++++++++++++++++++++++++++++-------
2 files changed, 170 insertions(+), 25 deletions(-)
diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h
index 4372c08fc4d9..083e566fc380 100644
--- a/include/net/sch_generic.h
+++ b/include/net/sch_generic.h
@@ -322,6 +322,11 @@ struct tcf_proto {
void *data;
const struct tcf_proto_ops *ops;
struct tcf_chain *chain;
+ /* Lock protects tcf_proto shared state and can be used by unlocked
+ * classifiers to protect their private data.
+ */
+ spinlock_t lock;
+ bool deleting;
refcount_t refcnt;
struct rcu_head rcu;
};
@@ -382,16 +387,29 @@ static inline bool lockdep_tcf_chain_is_locked(struct tcf_chain *chain)
{
return lockdep_is_held(&chain->filter_chain_lock);
}
+
+static inline bool lockdep_tcf_proto_is_locked(struct tcf_proto *tp)
+{
+ return lockdep_is_held(&tp->lock);
+}
#else
static inline bool lockdep_tcf_chain_is_locked(struct tcf_block *chain)
{
return true;
}
+
+static inline bool lockdep_tcf_proto_is_locked(struct tcf_proto *tp)
+{
+ return true;
+}
#endif /* #ifdef CONFIG_PROVE_LOCKING */
#define tcf_chain_dereference(p, chain) \
rcu_dereference_protected(p, lockdep_tcf_chain_is_locked(chain))
+#define tcf_proto_dereference(p, tp) \
+ rcu_dereference_protected(p, lockdep_tcf_proto_is_locked(tp))
+
static inline void tcf_block_offload_inc(struct tcf_block *block, u32 *flags)
{
if (*flags & TCA_CLS_FLAGS_IN_HW)
diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c
index dca8a3bee9c2..c6452e3bfc6a 100644
--- a/net/sched/cls_api.c
+++ b/net/sched/cls_api.c
@@ -180,6 +180,7 @@ static struct tcf_proto *tcf_proto_create(const char *kind, u32 protocol,
tp->protocol = protocol;
tp->prio = prio;
tp->chain = chain;
+ spin_lock_init(&tp->lock);
refcount_set(&tp->refcnt, 1);
err = tp->ops->init(tp);
@@ -217,6 +218,49 @@ static void tcf_proto_put(struct tcf_proto *tp,
tcf_proto_destroy(tp, extack);
}
+static int walker_noop(struct tcf_proto *tp, void *d, struct tcf_walker *arg)
+{
+ return -1;
+}
+
+static bool tcf_proto_is_empty(struct tcf_proto *tp)
+{
+ struct tcf_walker walker = { .fn = walker_noop, };
+
+ if (tp->ops->walk) {
+ tp->ops->walk(tp, &walker);
+ return !walker.stop;
+ }
+ return true;
+}
+
+static bool tcf_proto_check_delete(struct tcf_proto *tp)
+{
+ spin_lock(&tp->lock);
+ if (tcf_proto_is_empty(tp))
+ tp->deleting = true;
+ spin_unlock(&tp->lock);
+ return tp->deleting;
+}
+
+static void tcf_proto_mark_delete(struct tcf_proto *tp)
+{
+ spin_lock(&tp->lock);
+ tp->deleting = true;
+ spin_unlock(&tp->lock);
+}
+
+static bool tcf_proto_is_deleting(struct tcf_proto *tp)
+{
+ bool deleting;
+
+ spin_lock(&tp->lock);
+ deleting = tp->deleting;
+ spin_unlock(&tp->lock);
+
+ return deleting;
+}
+
#define ASSERT_BLOCK_LOCKED(block) \
lockdep_assert_held(&(block)->lock)
@@ -983,13 +1027,27 @@ EXPORT_SYMBOL(tcf_get_next_chain);
static struct tcf_proto *
__tcf_get_next_proto(struct tcf_chain *chain, struct tcf_proto *tp)
{
+ u32 prio = 0;
+
ASSERT_RTNL();
mutex_lock(&chain->filter_chain_lock);
- if (!tp)
+ if (!tp) {
tp = tcf_chain_dereference(chain->filter_chain, chain);
- else
+ } else if (tcf_proto_is_deleting(tp)) {
+ /* 'deleting' flag is set and chain->filter_chain_lock was
+ * unlocked, which means next pointer could be invalid. Restart
+ * search.
+ */
+ prio = tp->prio + 1;
+ tp = tcf_chain_dereference(chain->filter_chain, chain);
+
+ for (; tp; tp = tcf_chain_dereference(tp->next, chain))
+ if (!tp->deleting && tp->prio >= prio)
+ break;
+ } else {
tp = tcf_chain_dereference(tp->next, chain);
+ }
if (tp)
tcf_proto_get(tp);
@@ -1569,6 +1627,7 @@ static void tcf_chain_tp_remove(struct tcf_chain *chain,
{
struct tcf_proto *next = tcf_chain_dereference(chain_info->next, chain);
+ tcf_proto_mark_delete(tp);
if (tp == chain->filter_chain)
tcf_chain0_head_change(chain, next);
RCU_INIT_POINTER(*chain_info->pprev, next);
@@ -1577,6 +1636,79 @@ static void tcf_chain_tp_remove(struct tcf_chain *chain,
static struct tcf_proto *tcf_chain_tp_find(struct tcf_chain *chain,
struct tcf_chain_info *chain_info,
u32 protocol, u32 prio,
+ bool prio_allocate);
+
+/* Try to insert new proto.
+ * If proto with specified priority already exists, free new proto
+ * and return existing one.
+ */
+
+static struct tcf_proto *tcf_chain_tp_insert_unique(struct tcf_chain *chain,
+ struct tcf_proto *tp_new,
+ u32 protocol, u32 prio)
+{
+ struct tcf_chain_info chain_info;
+ struct tcf_proto *tp;
+
+ mutex_lock(&chain->filter_chain_lock);
+
+ tp = tcf_chain_tp_find(chain, &chain_info,
+ protocol, prio, false);
+ if (!tp)
+ tcf_chain_tp_insert(chain, &chain_info, tp_new);
+ mutex_unlock(&chain->filter_chain_lock);
+
+ if (tp) {
+ tcf_proto_destroy(tp_new, NULL);
+ tp_new = tp;
+ }
+
+ return tp_new;
+}
+
+static void tcf_chain_tp_delete_empty(struct tcf_chain *chain,
+ struct tcf_proto *tp,
+ struct netlink_ext_ack *extack)
+{
+ struct tcf_chain_info chain_info;
+ struct tcf_proto *tp_iter;
+ struct tcf_proto **pprev;
+ struct tcf_proto *next;
+
+ mutex_lock(&chain->filter_chain_lock);
+
+ /* Atomically find and remove tp from chain. */
+ for (pprev = &chain->filter_chain;
+ (tp_iter = tcf_chain_dereference(*pprev, chain));
+ pprev = &tp_iter->next) {
+ if (tp_iter == tp) {
+ chain_info.pprev = pprev;
+ chain_info.next = tp_iter->next;
+ WARN_ON(tp_iter->deleting);
+ break;
+ }
+ }
+ /* Verify that tp still exists and no new filters were inserted
+ * concurrently.
+ * Mark tp for deletion if it is empty.
+ */
+ if (!tp_iter || !tcf_proto_check_delete(tp)) {
+ mutex_unlock(&chain->filter_chain_lock);
+ return;
+ }
+
+ next = tcf_chain_dereference(chain_info.next, chain);
+ if (tp == chain->filter_chain)
+ tcf_chain0_head_change(chain, next);
+ RCU_INIT_POINTER(*chain_info.pprev, next);
+ mutex_unlock(&chain->filter_chain_lock);
+
+ tcf_proto_put(tp, extack);
+}
+
+static struct tcf_proto *tcf_chain_tp_find(struct tcf_chain *chain,
+ struct tcf_chain_info *chain_info,
+ u32 protocol, u32 prio,
bool prio_allocate)
{
struct tcf_proto **pprev;
@@ -1809,6 +1941,8 @@ static int tc_new_tfilter(struct sk_buff *skb, struct nlmsghdr *n,
}
if (tp == NULL) {
+ struct tcf_proto *tp_new = NULL;
+
/* Proto-tcf does not exist, create new one */
if (tca[TCA_KIND] == NULL || !protocol) {
@@ -1828,25 +1962,25 @@ static int tc_new_tfilter(struct sk_buff *skb, struct nlmsghdr *n,
&chain_info));
mutex_unlock(&chain->filter_chain_lock);
- tp = tcf_proto_create(nla_data(tca[TCA_KIND]),
- protocol, prio, chain, extack);
- if (IS_ERR(tp)) {
- err = PTR_ERR(tp);
+ tp_new = tcf_proto_create(nla_data(tca[TCA_KIND]),
+ protocol, prio, chain, extack);
+ if (IS_ERR(tp_new)) {
+ err = PTR_ERR(tp_new);
goto errout;
}
- mutex_lock(&chain->filter_chain_lock);
- tcf_chain_tp_insert(chain, &chain_info, tp);
- mutex_unlock(&chain->filter_chain_lock);
tp_created = 1;
- } else if (tca[TCA_KIND] && nla_strcmp(tca[TCA_KIND], tp->ops->kind)) {
- NL_SET_ERR_MSG(extack, "Specified filter kind does not match existing one");
- err = -EINVAL;
- goto errout_locked;
+ tp = tcf_chain_tp_insert_unique(chain, tp_new, protocol, prio);
} else {
mutex_unlock(&chain->filter_chain_lock);
}
+ if (tca[TCA_KIND] && nla_strcmp(tca[TCA_KIND], tp->ops->kind)) {
+ NL_SET_ERR_MSG(extack, "Specified filter kind does not match existing one");
+ err = -EINVAL;
+ goto errout;
+ }
+
fh = tp->ops->get(tp, t->tcm_handle);
if (!fh) {
@@ -1873,12 +2007,10 @@ static int tc_new_tfilter(struct sk_buff *skb, struct nlmsghdr *n,
if (err == 0)
tfilter_notify(net, skb, n, tp, block, q, parent, fh,
RTM_NEWTFILTER, false);
- else if (tp_created)
- tcf_proto_destroy(tp, NULL);
errout:
- if (chain)
- tcf_chain_put(chain);
+ if (err && tp_created)
+ tcf_chain_tp_delete_empty(chain, tp, NULL);
if (chain) {
if (tp && !IS_ERR(tp))
tcf_proto_put(tp, NULL);
@@ -1984,9 +2116,9 @@ static int tc_del_tfilter(struct sk_buff *skb, struct nlmsghdr *n,
tcf_chain_tp_remove(chain, &chain_info, tp);
mutex_unlock(&chain->filter_chain_lock);
+ tcf_proto_put(tp, NULL);
tfilter_notify(net, skb, n, tp, block, q, parent, fh,
RTM_DELTFILTER, false);
- tcf_proto_destroy(tp, extack);
err = 0;
goto errout;
}
@@ -2005,13 +2137,8 @@ static int tc_del_tfilter(struct sk_buff *skb, struct nlmsghdr *n,
extack);
if (err)
goto errout;
- if (last) {
- mutex_lock(&chain->filter_chain_lock);
- tcf_chain_tp_remove(chain, &chain_info, tp);
- mutex_unlock(&chain->filter_chain_lock);
-
- tcf_proto_destroy(tp, extack);
- }
+ if (last)
+ tcf_chain_tp_delete_empty(chain, tp, extack);
}
errout:
--
2.13.6
^ permalink raw reply related
* [PATCH net-next v4 03/17] net: sched: refactor tc_ctl_chain() to use block->lock
From: Vlad Buslov @ 2019-02-11 8:55 UTC (permalink / raw)
To: netdev; +Cc: jhs, xiyou.wangcong, jiri, davem, ast, daniel, Vlad Buslov
In-Reply-To: <20190211085548.7190-1-vladbu@mellanox.com>
In order to remove dependency on rtnl lock, modify chain API to use
block->lock to protect chain from concurrent modification. Rearrange
tc_ctl_chain() code to call tcf_chain_hold() while holding block->lock to
prevent concurrent chain removal.
Signed-off-by: Vlad Buslov <vladbu@mellanox.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
---
net/sched/cls_api.c | 36 +++++++++++++++++++++++++-----------
1 file changed, 25 insertions(+), 11 deletions(-)
diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c
index 2ebf8e53038a..b5db0f79db14 100644
--- a/net/sched/cls_api.c
+++ b/net/sched/cls_api.c
@@ -2255,6 +2255,8 @@ static int tc_ctl_chain(struct sk_buff *skb, struct nlmsghdr *n,
err = -EINVAL;
goto errout_block;
}
+
+ mutex_lock(&block->lock);
chain = tcf_chain_lookup(block, chain_index);
if (n->nlmsg_type == RTM_NEWCHAIN) {
if (chain) {
@@ -2266,41 +2268,49 @@ static int tc_ctl_chain(struct sk_buff *skb, struct nlmsghdr *n,
} else {
NL_SET_ERR_MSG(extack, "Filter chain already exists");
err = -EEXIST;
- goto errout_block;
+ goto errout_block_locked;
}
} else {
if (!(n->nlmsg_flags & NLM_F_CREATE)) {
NL_SET_ERR_MSG(extack, "Need both RTM_NEWCHAIN and NLM_F_CREATE to create a new chain");
err = -ENOENT;
- goto errout_block;
+ goto errout_block_locked;
}
chain = tcf_chain_create(block, chain_index);
if (!chain) {
NL_SET_ERR_MSG(extack, "Failed to create filter chain");
err = -ENOMEM;
- goto errout_block;
+ goto errout_block_locked;
}
}
} else {
if (!chain || tcf_chain_held_by_acts_only(chain)) {
NL_SET_ERR_MSG(extack, "Cannot find specified filter chain");
err = -EINVAL;
- goto errout_block;
+ goto errout_block_locked;
}
tcf_chain_hold(chain);
}
+ if (n->nlmsg_type == RTM_NEWCHAIN) {
+ /* Modifying chain requires holding parent block lock. In case
+ * the chain was successfully added, take a reference to the
+ * chain. This ensures that an empty chain does not disappear at
+ * the end of this function.
+ */
+ tcf_chain_hold(chain);
+ chain->explicitly_created = true;
+ }
+ mutex_unlock(&block->lock);
+
switch (n->nlmsg_type) {
case RTM_NEWCHAIN:
err = tc_chain_tmplt_add(chain, net, tca, extack);
- if (err)
+ if (err) {
+ tcf_chain_put_explicitly_created(chain);
goto errout;
- /* In case the chain was successfully added, take a reference
- * to the chain. This ensures that an empty chain
- * does not disappear at the end of this function.
- */
- tcf_chain_hold(chain);
- chain->explicitly_created = true;
+ }
+
tc_chain_notify(chain, NULL, 0, NLM_F_CREATE | NLM_F_EXCL,
RTM_NEWCHAIN, false);
break;
@@ -2334,6 +2344,10 @@ static int tc_ctl_chain(struct sk_buff *skb, struct nlmsghdr *n,
/* Replay the request. */
goto replay;
return err;
+
+errout_block_locked:
+ mutex_unlock(&block->lock);
+ goto errout_block;
}
/* called with RTNL */
--
2.13.6
^ permalink raw reply related
* [PATCH net-next v4 13/17] net: sched: extend proto ops with 'put' callback
From: Vlad Buslov @ 2019-02-11 8:55 UTC (permalink / raw)
To: netdev; +Cc: jhs, xiyou.wangcong, jiri, davem, ast, daniel, Vlad Buslov
In-Reply-To: <20190211085548.7190-1-vladbu@mellanox.com>
Add optional tp->ops->put() API to be implemented for filter reference
counting. This new function is called by cls API to release filter
reference for filters returned by tp->ops->change() or tp->ops->get()
functions. Implement tfilter_put() helper to call tp->ops->put() only for
classifiers that implement it.
Signed-off-by: Vlad Buslov <vladbu@mellanox.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
---
include/net/sch_generic.h | 1 +
net/sched/cls_api.c | 12 +++++++++++-
2 files changed, 12 insertions(+), 1 deletion(-)
diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h
index e8cf36ed3e87..410dda80ca62 100644
--- a/include/net/sch_generic.h
+++ b/include/net/sch_generic.h
@@ -277,6 +277,7 @@ struct tcf_proto_ops {
struct netlink_ext_ack *extack);
void* (*get)(struct tcf_proto*, u32 handle);
+ void (*put)(struct tcf_proto *tp, void *f);
int (*change)(struct net *net, struct sk_buff *,
struct tcf_proto*, unsigned long,
u32 handle, struct nlattr **,
diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c
index a3e715d34efb..8fe38aa180cf 100644
--- a/net/sched/cls_api.c
+++ b/net/sched/cls_api.c
@@ -1870,6 +1870,12 @@ static void tfilter_notify_chain(struct net *net, struct sk_buff *oskb,
q, parent, NULL, event, false);
}
+static void tfilter_put(struct tcf_proto *tp, void *fh)
+{
+ if (tp->ops->put && fh)
+ tp->ops->put(tp, fh);
+}
+
static int tc_new_tfilter(struct sk_buff *skb, struct nlmsghdr *n,
struct netlink_ext_ack *extack)
{
@@ -2012,6 +2018,7 @@ static int tc_new_tfilter(struct sk_buff *skb, struct nlmsghdr *n,
goto errout;
}
} else if (n->nlmsg_flags & NLM_F_EXCL) {
+ tfilter_put(tp, fh);
NL_SET_ERR_MSG(extack, "Filter already exists");
err = -EEXIST;
goto errout;
@@ -2026,9 +2033,11 @@ static int tc_new_tfilter(struct sk_buff *skb, struct nlmsghdr *n,
err = tp->ops->change(net, skb, tp, cl, t->tcm_handle, tca, &fh,
n->nlmsg_flags & NLM_F_CREATE ? TCA_ACT_NOREPLACE : TCA_ACT_REPLACE,
extack);
- if (err == 0)
+ if (err == 0) {
tfilter_notify(net, skb, n, tp, block, q, parent, fh,
RTM_NEWTFILTER, false);
+ tfilter_put(tp, fh);
+ }
errout:
if (err && tp_created)
@@ -2259,6 +2268,7 @@ static int tc_get_tfilter(struct sk_buff *skb, struct nlmsghdr *n,
NL_SET_ERR_MSG(extack, "Failed to send filter notify message");
}
+ tfilter_put(tp, fh);
errout:
if (chain) {
if (tp && !IS_ERR(tp))
--
2.13.6
^ permalink raw reply related
* Re: [RFC, PATCH] net: page_pool: Don't use page->private to store dma_addr_t
From: Tariq Toukan @ 2019-02-11 8:53 UTC (permalink / raw)
To: Ilias Apalodimas, Matthew Wilcox
Cc: David Miller, brouer@redhat.com, toke@redhat.com,
netdev@vger.kernel.org, mgorman@techsingularity.net,
linux-mm@kvack.org
In-Reply-To: <20190207214237.GA10676@Iliass-MBP.lan>
On 2/7/2019 11:42 PM, Ilias Apalodimas wrote:
> Hi Matthew,
>
> On Thu, Feb 07, 2019 at 01:34:00PM -0800, Matthew Wilcox wrote:
>> On Thu, Feb 07, 2019 at 01:25:19PM -0800, David Miller wrote:
>>> From: Ilias Apalodimas <ilias.apalodimas@linaro.org>
>>> Date: Thu, 7 Feb 2019 17:20:34 +0200
>>>
>>>> Well updating struct page is the final goal, hence the comment. I am mostly
>>>> looking for opinions here since we are trying to store dma addresses which are
>>>> irrelevant to pages. Having dma_addr_t definitions in mm-related headers is a
>>>> bit controversial isn't it ? If we can add that, then yes the code would look
>>>> better
>>>
>>> I fundamentally disagree.
>>>
>>> One of the core operations performed on a page is mapping it so that a device
>>> and use it.
>>>
>>> Why have ancillary data structure support for this all over the place, rather
>>> than in the common spot which is the page.
>>>
>>> A page really is not just a 'mm' structure, it is a system structure.
>>
>> +1
>>
>> The fundamental point of computing is to do I/O.
> Ok, great that should sort it out then.
> I'll use your proposal and base the patch on that.
>
> Thanks for taking the time with this
>
> /Ilias
>
Hi,
It's great to use the struct page to store its dma mapping, but I am
worried about extensibility.
page_pool is evolving, and it would need several more per-page fields.
One of them would be pageref_bias, a planned optimization to reduce the
number of the costly atomic pageref operations (and replace existing
code in several drivers).
I would replace this dma field with a pointer to an extensible struct,
that would contain the dma mapping (and other stuff in the near future).
This pointer fits perfectly with the existing unsigned long private;
they can share the memory, for both 32- and 64-bits systems.
The only downside is one more pointer de-reference. This should be perf
tested.
However, when introducing the page refcnt bias optimization into
page_pool, I believe the perf gain would be guaranteed.
Regards,
Tariq
^ permalink raw reply
* [Resend PATCH] mt76: change the return type of mt76_dma_attach()
From: Ryder Lee @ 2019-02-11 8:48 UTC (permalink / raw)
To: Lorenzo Bianconi, Felix Fietkau, Kalle Valo
Cc: Roy Luo, linux-wireless, linux-kernel, netdev, linux-mediatek,
Ryder Lee
There is no need to return 0 in mt76_dma_attach(), so switch it to void.
Signed-off-by: Ryder Lee <ryder.lee@mediatek.com>
---
drivers/net/wireless/mediatek/mt76/dma.c | 3 +--
drivers/net/wireless/mediatek/mt76/dma.h | 2 +-
2 files changed, 2 insertions(+), 3 deletions(-)
diff --git a/drivers/net/wireless/mediatek/mt76/dma.c b/drivers/net/wireless/mediatek/mt76/dma.c
index e2ba263..d934d72 100644
--- a/drivers/net/wireless/mediatek/mt76/dma.c
+++ b/drivers/net/wireless/mediatek/mt76/dma.c
@@ -522,10 +522,9 @@ int mt76_dma_tx_queue_skb(struct mt76_dev *dev, struct mt76_queue *q,
.kick = mt76_dma_kick_queue,
};
-int mt76_dma_attach(struct mt76_dev *dev)
+void mt76_dma_attach(struct mt76_dev *dev)
{
dev->queue_ops = &mt76_dma_ops;
- return 0;
}
EXPORT_SYMBOL_GPL(mt76_dma_attach);
diff --git a/drivers/net/wireless/mediatek/mt76/dma.h b/drivers/net/wireless/mediatek/mt76/dma.h
index 357cc35..e3292df 100644
--- a/drivers/net/wireless/mediatek/mt76/dma.h
+++ b/drivers/net/wireless/mediatek/mt76/dma.h
@@ -54,7 +54,7 @@ enum mt76_mcu_evt_type {
EVT_EVENT_DFS_DETECT_RSP,
};
-int mt76_dma_attach(struct mt76_dev *dev);
+void mt76_dma_attach(struct mt76_dev *dev);
void mt76_dma_cleanup(struct mt76_dev *dev);
#endif
--
1.9.1
^ permalink raw reply related
* Re: [PATCH] mt76: change the retun type of mt76_dma_attach()
From: Ryder Lee @ 2019-02-11 8:48 UTC (permalink / raw)
To: Sergei Shtylyov
Cc: Lorenzo Bianconi, Felix Fietkau, Kalle Valo, netdev,
linux-mediatek, linux-wireless, Roy Luo, linux-kernel
In-Reply-To: <f65c85c2-ef47-d141-d78e-db2a138a1daf@cogentembedded.com>
On Mon, 2019-02-11 at 11:38 +0300, Sergei Shtylyov wrote:
> Hello!
>
> On 11.02.2019 5:13, Ryder Lee wrote:
>
> > There is no need to retun 0 in mt76_dma_attach(), so switch it to void.
> ^ r missing :-)
> >
> > Signed-off-by: Ryder Lee <ryder.lee@mediatek.com>
> [...]
>
> MBR, Sergei
>
I will resend a new one.
Thanks
Ryder
^ permalink raw reply
* Re: [PATCH] mt76: change the retun type of mt76_dma_attach()
From: Sergei Shtylyov @ 2019-02-11 8:38 UTC (permalink / raw)
To: Ryder Lee, Lorenzo Bianconi, Felix Fietkau, Kalle Valo
Cc: Roy Luo, linux-wireless, linux-kernel, netdev, linux-mediatek
In-Reply-To: <228fdddb9ca96e8ce861e324eb9039722cf18f49.1549850911.git.ryder.lee@mediatek.com>
Hello!
On 11.02.2019 5:13, Ryder Lee wrote:
> There is no need to retun 0 in mt76_dma_attach(), so switch it to void.
^ r missing :-)
>
> Signed-off-by: Ryder Lee <ryder.lee@mediatek.com>
[...]
MBR, Sergei
^ permalink raw reply
* Re: [RFC PATCH] perf, bpf: Retain kernel executable code in memory to aid Intel PT tracing
From: Adrian Hunter @ 2019-02-11 8:24 UTC (permalink / raw)
To: Alexei Starovoitov
Cc: Ingo Molnar, Peter Zijlstra, Andi Kleen, Alexander Shishkin,
Arnaldo Carvalho de Melo, Jiri Olsa, Song Liu, Daniel Borkmann,
Alexei Starovoitov, linux-kernel, netdev
In-Reply-To: <20190211081840.j3vhyp3cffftb6m2@ast-mbp>
On 11/02/19 10:18 AM, Alexei Starovoitov wrote:
> On Mon, Feb 11, 2019 at 09:54:01AM +0200, Adrian Hunter wrote:
>>
>> Which is not really a real use-case.
> ..
>>> perf analysis with PT becomes inaccurate and main goal
>>> of retaining accurate instruction info is not achieved.
>>
>> For the majority of real use-cases, yes it is.
>
> In our fleet not a single server is using Intel PT, yet you're
> proposing to penalize all of them with shrinker-based JIT freeing?
I already responded to that.
> There is no negotiation here.
Apart from Peter and Ingo already having indicated a different approach is
preferred, why not? Shouldn't maintainers provide technical reasons.
^ permalink raw reply
* Re: [PATCH net-next 0/2] Revert wake_on_lan devlink parameter
From: Vasundhara Volam @ 2019-02-11 8:21 UTC (permalink / raw)
To: David Miller; +Cc: michael.chan@broadcom.com, Jiri Pirko, Netdev
In-Reply-To: <20190210.233503.1063032485031175825.davem@davemloft.net>
On Mon, Feb 11, 2019 at 1:05 PM David Miller <davem@davemloft.net> wrote:
>
> From: Vasundhara Volam <vasundhara-v.volam@broadcom.com>
> Date: Mon, 11 Feb 2019 10:09:23 +0530
>
> > On Sat, Feb 9, 2019 at 12:37 PM David Miller <davem@davemloft.net> wrote:
> >>
> >> From: Vasundhara Volam <vasundhara-v.volam@broadcom.com>
> >> Date: Fri, 8 Feb 2019 14:43:08 +0530
> >>
> >> > As per discussion with Jakub Kicinski and Michal Kubecek,
> >> > this will be better addressed by soon-too-come ethtool netlink
> >> > API with additional indication that given WoL configuration request
> >> > is supposed to be persisted.
> >> >
> >> > Retain bnxt_en code for devlink port param table registration.
> >> > There will be follow up patches to add some devlink port params
> >> > for bnxt_en driver.
> >>
> >> Please fix the kbuild robot reported build failure and repost.
> > David, second patch in this patchset has already taken care of all
> > this failures.
> > Could you please apply both patches together?
>
> You cannot break bisection like this.
>
> If they cannot be separated, resubmit the change as one patch.
Okay. I will resubmit as one patch. Thank you David.
^ permalink raw reply
* Re: [RFC PATCH] perf, bpf: Retain kernel executable code in memory to aid Intel PT tracing
From: Alexei Starovoitov @ 2019-02-11 8:18 UTC (permalink / raw)
To: Adrian Hunter
Cc: Ingo Molnar, Peter Zijlstra, Andi Kleen, Alexander Shishkin,
Arnaldo Carvalho de Melo, Jiri Olsa, Song Liu, Daniel Borkmann,
Alexei Starovoitov, linux-kernel, netdev
In-Reply-To: <85ebb8e5-97a0-801a-8d5f-bc09a72047bb@intel.com>
On Mon, Feb 11, 2019 at 09:54:01AM +0200, Adrian Hunter wrote:
>
> Which is not really a real use-case.
..
> > perf analysis with PT becomes inaccurate and main goal
> > of retaining accurate instruction info is not achieved.
>
> For the majority of real use-cases, yes it is.
In our fleet not a single server is using Intel PT, yet you're
proposing to penalize all of them with shrinker-based JIT freeing?
There is no negotiation here.
NACK
^ permalink raw reply
* Re: [RFC PATCH] perf, bpf: Retain kernel executable code in memory to aid Intel PT tracing
From: Adrian Hunter @ 2019-02-11 7:54 UTC (permalink / raw)
To: Alexei Starovoitov
Cc: Ingo Molnar, Peter Zijlstra, Andi Kleen, Alexander Shishkin,
Arnaldo Carvalho de Melo, Jiri Olsa, Song Liu, Daniel Borkmann,
Alexei Starovoitov, linux-kernel, netdev
In-Reply-To: <20190208232924.bpdjuaqufndigtd4@ast-mbp>
On 9/02/19 1:29 AM, Alexei Starovoitov wrote:
> On Thu, Feb 07, 2019 at 01:19:01PM +0200, Adrian Hunter wrote:
>> Subject to memory pressure and other limits, retain executable code, such
>> as JIT-compiled bpf, in memory instead of freeing it immediately it is no
>> longer needed for execution.
>>
>> While perf is primarily aimed at statistical analysis, tools like Intel
>> PT can aim to provide a trace of exactly what happened. As such, corner
>> cases that can be overlooked statistically need to be addressed. For
>> example, there is a gap where JIT-compiled bpf can be freed from memory
>> before a tracer has a chance to read it out through the bpf syscall.
>> While that can be ignored statistically, it contributes to a death by
>> 1000 cuts for tracers attempting to assemble exactly what happened. This is
>> a bit gratuitous given that retaining the executable code is relatively
>> simple, and the amount of memory involved relatively small. The retained
>> executable code is then available in memory images such as /proc/kcore.
>>
>> This facility could perhaps be extended also to init sections.
>>
>> Note that this patch is compile tested only and, at present, is missing
>> the ability to retain symbols.
>>
>> Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
>> ---
>> arch/x86/Kconfig.cpu | 1 +
>> include/linux/filter.h | 4 +
>> include/linux/xc_retain.h | 49 ++++++++++
>> init/Kconfig | 6 ++
>> kernel/Makefile | 1 +
>> kernel/bpf/core.c | 44 ++++++++-
>> kernel/xc_retain.c | 183 +++++++++++++++++++++++++++++++++++++
>> net/core/sysctl_net_core.c | 62 +++++++++++++
>> 8 files changed, 349 insertions(+), 1 deletion(-)
>> create mode 100644 include/linux/xc_retain.h
>> create mode 100644 kernel/xc_retain.c
>>
>> diff --git a/arch/x86/Kconfig.cpu b/arch/x86/Kconfig.cpu
>> index 6adce15268bd..21dcd064c272 100644
>> --- a/arch/x86/Kconfig.cpu
>> +++ b/arch/x86/Kconfig.cpu
>> @@ -389,6 +389,7 @@ menuconfig PROCESSOR_SELECT
>> config CPU_SUP_INTEL
>> default y
>> bool "Support Intel processors" if PROCESSOR_SELECT
>> + select XC_RETAIN if PERF_EVENTS && BPF_JIT
>> ---help---
>> This enables detection, tunings and quirks for Intel processors
>>
>> diff --git a/include/linux/filter.h b/include/linux/filter.h
>> index d531d4250bff..40b9f601e18f 100644
>> --- a/include/linux/filter.h
>> +++ b/include/linux/filter.h
>> @@ -851,6 +851,10 @@ extern int bpf_jit_enable;
>> extern int bpf_jit_harden;
>> extern int bpf_jit_kallsyms;
>> extern long bpf_jit_limit;
>> +extern unsigned int bpf_jit_retain_min;
>> +extern unsigned int bpf_jit_retain_max;
>> +
>> +void bpf_jit_retain_update_sz(void);
>>
>> typedef void (*bpf_jit_fill_hole_t)(void *area, unsigned int size);
>>
>> diff --git a/include/linux/xc_retain.h b/include/linux/xc_retain.h
>> new file mode 100644
>> index 000000000000..e79dc138bab8
>> --- /dev/null
>> +++ b/include/linux/xc_retain.h
>> @@ -0,0 +1,49 @@
>> +/* SPDX-License-Identifier: GPL-2.0 */
>> +/*
>> + * Copyright (C) 2019 Intel Corporation.
>> + */
>> +#ifndef _LINUX_XC_RETAIN_H
>> +#define _LINUX_XC_RETAIN_H
>> +
>> +#include <linux/list.h>
>> +#include <linux/shrinker.h>
>> +#include <linux/spinlock.h>
>> +
>> +struct xc_retain_ops {
>> + void (*free)(void *addr);
>> +};
>> +
>> +struct xc_retain {
>> + struct list_head list;
>> + struct list_head items;
>> + const struct xc_retain_ops ops;
>> + unsigned int min_pages;
>> + unsigned int max_pages;
>> + unsigned int current_pages;
>> + unsigned int item_cnt;
>> + spinlock_t lock;
>> + struct shrinker shrinker;
>> +};
>> +
>> +#ifdef CONFIG_XC_RETAIN
>> +int xc_retain_register(struct xc_retain *xr);
>> +void xc_retain_binary(struct xc_retain *xr, void *addr, unsigned int pages);
>> +void xc_retain_set_min_pages(struct xc_retain *xr, unsigned int min_pages);
>> +void xc_retain_set_max_pages(struct xc_retain *xr, unsigned int max_pages);
>> +#else
>> +static inline int xc_retain_register(struct xc_retain *xr)
>> +{
>> + return 0;
>> +}
>> +static inline void xc_retain_binary(struct xc_retain *xr, void *addr,
>> + unsigned int pages)
>> +{
>> + xr->ops.free(addr);
>> +}
>> +static inline void xc_retain_set_max_pages(struct xc_retain *xr,
>> + unsigned int max_pages)
>> +{
>> +}
>> +#endif
>> +
>> +#endif
>> diff --git a/init/Kconfig b/init/Kconfig
>> index c9386a365eea..954c288cabdc 100644
>> --- a/init/Kconfig
>> +++ b/init/Kconfig
>> @@ -1550,6 +1550,12 @@ config EMBEDDED
>> an embedded system so certain expert options are available
>> for configuration.
>>
>> +config XC_RETAIN
>> + bool
>> + help
>> + Retain kernel executable code (e.g. jitted BPF) in memory after it
>> + would normally be freed.
>> +
>> config HAVE_PERF_EVENTS
>> bool
>> help
>> diff --git a/kernel/Makefile b/kernel/Makefile
>> index 6aa7543bcdb2..5df40e2a934e 100644
>> --- a/kernel/Makefile
>> +++ b/kernel/Makefile
>> @@ -98,6 +98,7 @@ obj-$(CONFIG_TRACEPOINTS) += trace/
>> obj-$(CONFIG_IRQ_WORK) += irq_work.o
>> obj-$(CONFIG_CPU_PM) += cpu_pm.o
>> obj-$(CONFIG_BPF) += bpf/
>> +obj-$(CONFIG_XC_RETAIN) += xc_retain.o
>>
>> obj-$(CONFIG_PERF_EVENTS) += events/
>>
>> diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
>> index 19c49313c709..7fd235d235c2 100644
>> --- a/kernel/bpf/core.c
>> +++ b/kernel/bpf/core.c
>> @@ -34,6 +34,7 @@
>> #include <linux/kallsyms.h>
>> #include <linux/rcupdate.h>
>> #include <linux/perf_event.h>
>> +#include <linux/xc_retain.h>
>>
>> #include <asm/unaligned.h>
>>
>> @@ -480,6 +481,10 @@ int bpf_jit_enable __read_mostly = IS_BUILTIN(CONFIG_BPF_JIT_ALWAYS_ON);
>> int bpf_jit_harden __read_mostly;
>> int bpf_jit_kallsyms __read_mostly;
>> long bpf_jit_limit __read_mostly;
>> +#define BPF_JIT_RETAIN_MIN 0
>> +#define BPF_JIT_RETAIN_MAX 16
>> +unsigned int bpf_jit_retain_min __read_mostly = BPF_JIT_RETAIN_MIN;
>> +unsigned int bpf_jit_retain_max __read_mostly = BPF_JIT_RETAIN_MAX;
>>
>> static __always_inline void
>> bpf_get_prog_addr_region(const struct bpf_prog *prog,
>> @@ -795,6 +800,43 @@ void bpf_jit_binary_free(struct bpf_binary_header *hdr)
>> bpf_jit_uncharge_modmem(pages);
>> }
>>
>> +#ifdef CONFIG_XC_RETAIN
>> +static struct xc_retain bpf_jit_retain = {
>> + .min_pages = BPF_JIT_RETAIN_MIN,
>> + .max_pages = BPF_JIT_RETAIN_MAX,
>> + .ops = {
>> + .free = module_memfree,
>> + },
>> +};
>> +
>> +void bpf_jit_retain_update_sz(void)
>> +{
>> + xc_retain_set_min_pages(&bpf_jit_retain, bpf_jit_retain_min);
>> + xc_retain_set_max_pages(&bpf_jit_retain, bpf_jit_retain_max);
>> +}
>> +
>> +static int __init bpf_jit_retain_init(void)
>> +{
>> + return xc_retain_register(&bpf_jit_retain);
>> +}
>> +subsys_initcall(bpf_jit_retain_init);
>> +
>> +static void bpf_jit_binary_retain(struct bpf_prog *fp,
>> + struct bpf_binary_header *hdr)
>> +{
>> + u32 pages = hdr->pages;
>> +
>> + xc_retain_binary(&bpf_jit_retain, hdr, pages);
>> + bpf_jit_uncharge_modmem(pages);
>> +}
>> +#else
>> +static void bpf_jit_binary_retain(struct bpf_prog *fp,
>> + struct bpf_binary_header *hdr)
>> +{
>> + return bpf_jit_binary_free(hdr);
>> +}
>> +#endif
>
> I'm strongly against this approach.
Thanks for commenting, but Peter wrote that he prefers this option:
https://lkml.kernel.org/r/20190109101808.GG1900@hirez.programming.kicks-ass.net
> I understand that it's under CONFIG, but changing kernel
> into garbage collection nightmare even under config
> or sysctl is not an option.
> In many cases bpf progs are loaded/unloaded a lot.
> Consider CI test system that runs tests 24/7.
> bpf progs are loaded/unloaded in huge numbers.
Which is not really a real use-case.
For PT, the data recorded is generally too large (e.g. 100MB per cpu per second)
to record continuously. But there is a "snapshot" mode that just captures
the PT data that is currently buffered. In that case we want to have a
kernel image that reflects what was running for the last small period of
time.
> Such system will suffer non deterministic test and
> performance results due to shrinkers.
The default was 16 pages, after that everything gets freed immediately.
That is assuming you don't turn it off for test purposes. That would
not have an effect on your tests.
Also, why would copying it out of memory be less intrusive that keeping it
in memory. Copying every bpf jit to disk for every load would be much more
intrusive.
> perf analysis with PT becomes inaccurate and main goal
> of retaining accurate instruction info is not achieved.
For the majority of real use-cases, yes it is.
> bpf_jit_retain_min/max tunables is not an option either.
> Please see how perf record is handling bpf prog/unload.
> What stops you from doing the same for PT?
Opens the door for the bpf program to be unloaded before it is copied out.
All the corner cases where it is not possible to get accurate decoding start
to add up.
^ permalink raw reply
* [PATCH net-next 1/1] flow_offload: Fix flow action infrastructure
From: Eli Britstein @ 2019-02-11 7:52 UTC (permalink / raw)
To: netdev
Cc: Roi Dayan, Pablo Neira Ayuso, Jiri Pirko, Saeed Mahameed,
Eli Britstein
Implementation of macro "flow_action_for_each" introduced in
commit e3ab786b42535 ("flow_offload: add flow action infrastructure")
and used in commit 738678817573c ("drivers: net: use flow action
infrastructure") iterated the first item twice and did not reach the
last one. Fix it.
Fixes: e3ab786b42535 ("flow_offload: add flow action infrastructure")
Fixes: 738678817573c ("drivers: net: use flow action infrastructure")
Signed-off-by: Eli Britstein <elibr@mellanox.com>
Reviewed-by: Roi Dayan <roid@mellanox.com>
---
include/net/flow_offload.h | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/include/net/flow_offload.h b/include/net/flow_offload.h
index 23166caa0da5..a307ccb18015 100644
--- a/include/net/flow_offload.h
+++ b/include/net/flow_offload.h
@@ -171,7 +171,7 @@ static inline bool flow_action_has_entries(const struct flow_action *action)
}
#define flow_action_for_each(__i, __act, __actions) \
- for (__i = 0, __act = &(__actions)->entries[0]; __i < (__actions)->num_entries; __act = &(__actions)->entries[__i++])
+ for (__i = 0, __act = &(__actions)->entries[0]; __i < (__actions)->num_entries; __act = &(__actions)->entries[++__i])
struct flow_rule {
struct flow_match match;
--
2.14.5
^ permalink raw reply related
* Re: [PATCH bpf-next v4 0/2] libbpf: adding AF_XDP support
From: Magnus Karlsson @ 2019-02-11 7:52 UTC (permalink / raw)
To: Jean-Mickael Guerin
Cc: Magnus Karlsson, Björn Töpel, ast, Daniel Borkmann,
Network Development, Jakub Kicinski, Björn Töpel,
Zhang, Qi Z, Jesper Dangaard Brouer, xiaolong.ye
In-Reply-To: <CAP2kokD9aSryMBDjt+ip=1NFronXrMfY59b6DauTT59kWHLwcw@mail.gmail.com>
On Mon, Feb 11, 2019 at 7:34 AM Jean-Mickael Guerin <jmg@6wind.com> wrote:
>
> Hi Magnus,
>
> > * In a future release, I am planning on adding a higher level data
> > plane interface too. This will be based around recvmsg and sendmsg
> > with the use of struct iovec for batching, without the user having
> > to know anything about the underlying four rings of an AF_XDP
> > socket. There will be one semantic difference though from the
> > standard recvmsg and that is that the kernel will fill in the iovecs
> > instead of the application. But the rest should be the same as the
> > libc versions so that application writers feel at home.
>
> You might consider recvmmsg() and sendmmsg() (bulk of multi segments packets?)
Exactly :-). Spot on.
/Magnus
> Jean-Mickael
^ permalink raw reply
* Re: [PATCH net-next v2 00/10] net: phy: Add support for 2.5GBASET PHYs
From: Maxime Chevallier @ 2019-02-11 7:46 UTC (permalink / raw)
To: Heiner Kallweit
Cc: davem, Andrew Lunn, netdev, linux-kernel, Florian Fainelli,
Russell King, linux-arm-kernel, Antoine Tenart, thomas.petazzoni,
gregory.clement, miquel.raynal, nadavh, stefanc, mw
In-Reply-To: <81c340ea-54b0-1abf-94af-b8dc4ee83e3a@gmail.com>
Hello Heiner,
>Hi Maxime,
>
>Andrew and me are working on Aquantia PHY support and he handed over
>to me a patch series which includes parts of the first version of your
>series. Having said that I'm especially interested in your patches
>5 and 6. Because your series is somewhat bigger and there are a few
>review comments, preparing the next round may take time.
>
>I'd propose that you extract generic patches being submission-ready
>and split the patch series into two. I think the following patches
>would be candidates for the first series: 2, 3, 5, 6
>(provided they have no dependency on the other patches)
>Based on that both of us can go on with our work.
Sure, I'll sent that shortly. Thanks for the help,
Maxime
^ permalink raw reply
page: next (older) | prev (newer) | latest
- recent:[subjects (threaded)|topics (new)|topics (active)]
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox