From 843e79d05addd8eb06992cd6dfafc7b9d53f2bc8 Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@mellanox.com>
Date: Wed, 11 Oct 2017 09:41:07 +0200
Subject: net: sched: make tc_action_ops->get_dev return dev and avoid passing
net
Return dev directly, NULL if not possible. That is enough.
Makes no sense to pass struct net * to get_dev op, as there is only one
net possible, the one the action was created in. So just store it in
mirred priv and use directly.
Rename the mirred op callback function.
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
net/sched/cls_api.c | 6 ++----
1 file changed, 2 insertions(+), 4 deletions(-)
(limited to 'net/sched/cls_api.c')
diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c
index 0b2219a..450873b 100644
--- a/net/sched/cls_api.c
+++ b/net/sched/cls_api.c
@@ -1016,10 +1016,8 @@ int tcf_exts_get_dev(struct net_device *dev, struct tcf_exts *exts,
tcf_exts_to_list(exts, &actions);
list_for_each_entry(a, &actions, list) {
- if (a->ops->get_dev) {
- a->ops->get_dev(a, dev_net(dev), hw_dev);
- break;
- }
+ if (a->ops->get_dev)
+ *hw_dev = a->ops->get_dev(a);
}
if (*hw_dev)
return 0;
--
cgit v1.1
From b3f55bdda8df55a563005e00b1b71212d8546541 Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@mellanox.com>
Date: Wed, 11 Oct 2017 09:41:08 +0200
Subject: net: sched: introduce per-egress action device callbacks
Introduce infrastructure that allows drivers to register callbacks that
are called whenever tc would offload inserted rule and specified device
acts as tc action egress device.
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
net/sched/cls_api.c | 30 ++++++++++++++++++++++++++++++
1 file changed, 30 insertions(+)
(limited to 'net/sched/cls_api.c')
diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c
index 450873b..99f9432 100644
--- a/net/sched/cls_api.c
+++ b/net/sched/cls_api.c
@@ -1026,6 +1026,36 @@ int tcf_exts_get_dev(struct net_device *dev, struct tcf_exts *exts,
}
EXPORT_SYMBOL(tcf_exts_get_dev);
+int tcf_exts_egdev_cb_call(struct tcf_exts *exts, enum tc_setup_type type,
+ void *type_data, bool err_stop)
+{
+ int ok_count = 0;
+#ifdef CONFIG_NET_CLS_ACT
+ const struct tc_action *a;
+ struct net_device *dev;
+ LIST_HEAD(actions);
+ int ret;
+
+ if (!tcf_exts_has_actions(exts))
+ return 0;
+
+ tcf_exts_to_list(exts, &actions);
+ list_for_each_entry(a, &actions, list) {
+ if (!a->ops->get_dev)
+ continue;
+ dev = a->ops->get_dev(a);
+ if (!dev || !tc_can_offload(dev))
+ continue;
+ ret = tc_setup_cb_egdev_call(dev, type, type_data, err_stop);
+ if (ret < 0)
+ return ret;
+ ok_count += ret;
+ }
+#endif
+ return ok_count;
+}
+EXPORT_SYMBOL(tcf_exts_egdev_cb_call);
+
static int __init tc_filter_init(void)
{
rtnl_register(PF_UNSPEC, RTM_NEWTFILTER, tc_ctl_tfilter, NULL, 0);
--
cgit v1.1
From 717503b9cf57c0bb7ea4d3a9f5699c9a04adf988 Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@mellanox.com>
Date: Wed, 11 Oct 2017 09:41:09 +0200
Subject: net: sched: convert cls_flower->egress_dev users to tc_setup_cb_egdev
infra
The only user of cls_flower->egress_dev is mlx5. So do the conversion
there alongside with the code originating the call in cls_flower
function fl_hw_replace_filter to the newly introduced egress device
callback infrastucture.
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
net/sched/cls_api.c | 13 ++++++++++---
1 file changed, 10 insertions(+), 3 deletions(-)
(limited to 'net/sched/cls_api.c')
diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c
index 99f9432..51994a2 100644
--- a/net/sched/cls_api.c
+++ b/net/sched/cls_api.c
@@ -1026,8 +1026,9 @@ int tcf_exts_get_dev(struct net_device *dev, struct tcf_exts *exts,
}
EXPORT_SYMBOL(tcf_exts_get_dev);
-int tcf_exts_egdev_cb_call(struct tcf_exts *exts, enum tc_setup_type type,
- void *type_data, bool err_stop)
+static int tc_exts_setup_cb_egdev_call(struct tcf_exts *exts,
+ enum tc_setup_type type,
+ void *type_data, bool err_stop)
{
int ok_count = 0;
#ifdef CONFIG_NET_CLS_ACT
@@ -1054,7 +1055,13 @@ int tcf_exts_egdev_cb_call(struct tcf_exts *exts, enum tc_setup_type type,
#endif
return ok_count;
}
-EXPORT_SYMBOL(tcf_exts_egdev_cb_call);
+
+int tc_setup_cb_call(struct tcf_exts *exts, enum tc_setup_type type,
+ void *type_data, bool err_stop)
+{
+ return tc_exts_setup_cb_egdev_call(exts, type, type_data, err_stop);
+}
+EXPORT_SYMBOL(tc_setup_cb_call);
static int __init tc_filter_init(void)
{
--
cgit v1.1
From 7578d7b45ed870b13a8ace57e32feaed623c2a94 Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@mellanox.com>
Date: Wed, 11 Oct 2017 09:41:10 +0200
Subject: net: sched: remove unused tcf_exts_get_dev helper and
cls_flower->egress_dev
The helper and the struct field ares no longer used by any code,
so remove them.
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
net/sched/cls_api.c | 22 ----------------------
1 file changed, 22 deletions(-)
(limited to 'net/sched/cls_api.c')
diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c
index 51994a2..2977b8a 100644
--- a/net/sched/cls_api.c
+++ b/net/sched/cls_api.c
@@ -1004,28 +1004,6 @@ int tcf_exts_dump_stats(struct sk_buff *skb, struct tcf_exts *exts)
}
EXPORT_SYMBOL(tcf_exts_dump_stats);
-int tcf_exts_get_dev(struct net_device *dev, struct tcf_exts *exts,
- struct net_device **hw_dev)
-{
-#ifdef CONFIG_NET_CLS_ACT
- const struct tc_action *a;
- LIST_HEAD(actions);
-
- if (!tcf_exts_has_actions(exts))
- return -EINVAL;
-
- tcf_exts_to_list(exts, &actions);
- list_for_each_entry(a, &actions, list) {
- if (a->ops->get_dev)
- *hw_dev = a->ops->get_dev(a);
- }
- if (*hw_dev)
- return 0;
-#endif
- return -EOPNOTSUPP;
-}
-EXPORT_SYMBOL(tcf_exts_get_dev);
-
static int tc_exts_setup_cb_egdev_call(struct tcf_exts *exts,
enum tc_setup_type type,
void *type_data, bool err_stop)
--
cgit v1.1
From 69d78ef25c7b0058674145500efb12255738ba8a Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@mellanox.com>
Date: Fri, 13 Oct 2017 14:00:57 +0200
Subject: net: sched: store Qdisc pointer in struct block
Prepare for removal of tp->q and store Qdisc pointer in the block
structure.
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
net/sched/cls_api.c | 3 ++-
1 file changed, 2 insertions(+), 1 deletion(-)
(limited to 'net/sched/cls_api.c')
diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c
index 2977b8a..f7d3f1f 100644
--- a/net/sched/cls_api.c
+++ b/net/sched/cls_api.c
@@ -241,7 +241,7 @@ tcf_chain_filter_chain_ptr_set(struct tcf_chain *chain,
}
int tcf_block_get(struct tcf_block **p_block,
- struct tcf_proto __rcu **p_filter_chain)
+ struct tcf_proto __rcu **p_filter_chain, struct Qdisc *q)
{
struct tcf_block *block = kzalloc(sizeof(*block), GFP_KERNEL);
struct tcf_chain *chain;
@@ -257,6 +257,7 @@ int tcf_block_get(struct tcf_block **p_block,
goto err_chain_create;
}
tcf_chain_filter_chain_ptr_set(chain, p_filter_chain);
+ block->q = q;
*p_block = block;
return 0;
--
cgit v1.1
From 855319becbcffec6988a4e781a861b69a71c5b58 Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@mellanox.com>
Date: Fri, 13 Oct 2017 14:00:58 +0200
Subject: net: sched: store net pointer in block and introduce qdisc_net helper
Store net pointer in the block structure. Along the way, introduce
qdisc_net helper which allows to easily obtain net pointer for
qdisc instance.
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
net/sched/cls_api.c | 1 +
1 file changed, 1 insertion(+)
(limited to 'net/sched/cls_api.c')
diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c
index f7d3f1f..856003c 100644
--- a/net/sched/cls_api.c
+++ b/net/sched/cls_api.c
@@ -257,6 +257,7 @@ int tcf_block_get(struct tcf_block **p_block,
goto err_chain_create;
}
tcf_chain_filter_chain_ptr_set(chain, p_filter_chain);
+ block->net = qdisc_net(q);
block->q = q;
*p_block = block;
return 0;
--
cgit v1.1
From a10fa20101ae48fed2102f8e84d98f5aac2e5c40 Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@mellanox.com>
Date: Fri, 13 Oct 2017 14:01:05 +0200
Subject: net: sched: propagate q and parent from caller down to tcf_fill_node
The callers have this info, they will pass it down to tcf_fill_node.
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
net/sched/cls_api.c | 55 ++++++++++++++++++++++++++++++++++-------------------
1 file changed, 35 insertions(+), 20 deletions(-)
(limited to 'net/sched/cls_api.c')
diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c
index 856003c..2e8e87f 100644
--- a/net/sched/cls_api.c
+++ b/net/sched/cls_api.c
@@ -420,8 +420,8 @@ 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, void *fh, u32 portid,
- u32 seq, u16 flags, int event)
+ struct tcf_proto *tp, struct Qdisc *q, u32 parent,
+ void *fh, u32 portid, u32 seq, u16 flags, int event)
{
struct tcmsg *tcm;
struct nlmsghdr *nlh;
@@ -434,8 +434,8 @@ static int tcf_fill_node(struct net *net, struct sk_buff *skb,
tcm->tcm_family = AF_UNSPEC;
tcm->tcm__pad1 = 0;
tcm->tcm__pad2 = 0;
- tcm->tcm_ifindex = qdisc_dev(tp->q)->ifindex;
- tcm->tcm_parent = tp->classid;
+ tcm->tcm_ifindex = qdisc_dev(q)->ifindex;
+ tcm->tcm_parent = parent;
tcm->tcm_info = TC_H_MAKE(tp->prio, tp->protocol);
if (nla_put_string(skb, TCA_KIND, tp->ops->kind))
goto nla_put_failure;
@@ -458,6 +458,7 @@ nla_put_failure:
static int tfilter_notify(struct net *net, struct sk_buff *oskb,
struct nlmsghdr *n, struct tcf_proto *tp,
+ struct Qdisc *q, u32 parent,
void *fh, int event, bool unicast)
{
struct sk_buff *skb;
@@ -467,7 +468,7 @@ static int tfilter_notify(struct net *net, struct sk_buff *oskb,
if (!skb)
return -ENOBUFS;
- if (tcf_fill_node(net, skb, tp, fh, portid, n->nlmsg_seq,
+ if (tcf_fill_node(net, skb, tp, q, parent, fh, portid, n->nlmsg_seq,
n->nlmsg_flags, event) <= 0) {
kfree_skb(skb);
return -EINVAL;
@@ -482,6 +483,7 @@ static int tfilter_notify(struct net *net, struct sk_buff *oskb,
static int tfilter_del_notify(struct net *net, struct sk_buff *oskb,
struct nlmsghdr *n, struct tcf_proto *tp,
+ struct Qdisc *q, u32 parent,
void *fh, bool unicast, bool *last)
{
struct sk_buff *skb;
@@ -492,7 +494,7 @@ static int tfilter_del_notify(struct net *net, struct sk_buff *oskb,
if (!skb)
return -ENOBUFS;
- if (tcf_fill_node(net, skb, tp, fh, portid, n->nlmsg_seq,
+ if (tcf_fill_node(net, skb, tp, q, parent, fh, portid, n->nlmsg_seq,
n->nlmsg_flags, RTM_DELTFILTER) <= 0) {
kfree_skb(skb);
return -EINVAL;
@@ -512,6 +514,7 @@ 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 Qdisc *q, u32 parent,
struct nlmsghdr *n,
struct tcf_chain *chain, int event)
{
@@ -519,7 +522,7 @@ static void tfilter_notify_chain(struct net *net, struct sk_buff *oskb,
for (tp = rtnl_dereference(chain->filter_chain);
tp; tp = rtnl_dereference(tp->next))
- tfilter_notify(net, oskb, n, tp, 0, event, false);
+ tfilter_notify(net, oskb, n, tp, q, parent, 0, event, false);
}
/* Add/change/delete/get a filter node */
@@ -638,7 +641,8 @@ replay:
}
if (n->nlmsg_type == RTM_DELTFILTER && prio == 0) {
- tfilter_notify_chain(net, skb, n, chain, RTM_DELTFILTER);
+ tfilter_notify_chain(net, skb, q, parent, n,
+ chain, RTM_DELTFILTER);
tcf_chain_flush(chain);
err = 0;
goto errout;
@@ -685,7 +689,7 @@ replay:
if (!fh) {
if (n->nlmsg_type == RTM_DELTFILTER && t->tcm_handle == 0) {
tcf_chain_tp_remove(chain, &chain_info, tp);
- tfilter_notify(net, skb, n, tp, fh,
+ tfilter_notify(net, skb, n, tp, q, parent, fh,
RTM_DELTFILTER, false);
tcf_proto_destroy(tp);
err = 0;
@@ -710,8 +714,8 @@ replay:
}
break;
case RTM_DELTFILTER:
- err = tfilter_del_notify(net, skb, n, tp, fh, false,
- &last);
+ err = tfilter_del_notify(net, skb, n, tp, q, parent,
+ fh, false, &last);
if (err)
goto errout;
if (last) {
@@ -720,7 +724,7 @@ replay:
}
goto errout;
case RTM_GETTFILTER:
- err = tfilter_notify(net, skb, n, tp, fh,
+ err = tfilter_notify(net, skb, n, tp, q, parent, fh,
RTM_NEWTFILTER, true);
goto errout;
default:
@@ -734,7 +738,8 @@ replay:
if (err == 0) {
if (tp_created)
tcf_chain_tp_insert(chain, &chain_info, tp);
- tfilter_notify(net, skb, n, tp, fh, RTM_NEWTFILTER, false);
+ tfilter_notify(net, skb, n, tp, q, parent, fh,
+ RTM_NEWTFILTER, false);
} else {
if (tp_created)
tcf_proto_destroy(tp);
@@ -753,6 +758,8 @@ struct tcf_dump_args {
struct tcf_walker w;
struct sk_buff *skb;
struct netlink_callback *cb;
+ struct Qdisc *q;
+ u32 parent;
};
static int tcf_node_dump(struct tcf_proto *tp, void *n, struct tcf_walker *arg)
@@ -760,13 +767,14 @@ static int tcf_node_dump(struct tcf_proto *tp, void *n, struct tcf_walker *arg)
struct tcf_dump_args *a = (void *)arg;
struct net *net = sock_net(a->skb->sk);
- return tcf_fill_node(net, a->skb, tp, n, NETLINK_CB(a->cb->skb).portid,
+ return tcf_fill_node(net, a->skb, tp, a->q, a->parent,
+ n, NETLINK_CB(a->cb->skb).portid,
a->cb->nlh->nlmsg_seq, NLM_F_MULTI,
RTM_NEWTFILTER);
}
-static bool tcf_chain_dump(struct tcf_chain *chain, struct sk_buff *skb,
- struct netlink_callback *cb,
+static bool tcf_chain_dump(struct tcf_chain *chain, struct Qdisc *q, u32 parent,
+ struct sk_buff *skb, struct netlink_callback *cb,
long index_start, long *p_index)
{
struct net *net = sock_net(skb->sk);
@@ -788,7 +796,7 @@ static bool tcf_chain_dump(struct tcf_chain *chain, struct sk_buff *skb,
memset(&cb->args[1], 0,
sizeof(cb->args) - sizeof(cb->args[0]));
if (cb->args[1] == 0) {
- if (tcf_fill_node(net, skb, tp, 0,
+ if (tcf_fill_node(net, skb, tp, q, parent, 0,
NETLINK_CB(cb->skb).portid,
cb->nlh->nlmsg_seq, NLM_F_MULTI,
RTM_NEWTFILTER) <= 0)
@@ -801,6 +809,8 @@ static bool tcf_chain_dump(struct tcf_chain *chain, struct sk_buff *skb,
arg.w.fn = tcf_node_dump;
arg.skb = skb;
arg.cb = cb;
+ arg.q = q;
+ arg.parent = parent;
arg.w.stop = 0;
arg.w.skip = cb->args[1] - 1;
arg.w.count = 0;
@@ -826,6 +836,7 @@ static int tc_dump_tfilter(struct sk_buff *skb, struct netlink_callback *cb)
const struct Qdisc_class_ops *cops;
long index_start;
long index;
+ u32 parent;
int err;
if (nlmsg_len(cb->nlh) < sizeof(*tcm))
@@ -839,10 +850,13 @@ static int tc_dump_tfilter(struct sk_buff *skb, struct netlink_callback *cb)
if (!dev)
return skb->len;
- if (!tcm->tcm_parent)
+ parent = tcm->tcm_parent;
+ if (!parent) {
q = dev->qdisc;
- else
+ parent = q->handle;
+ } else {
q = qdisc_lookup(dev, TC_H_MAJ(tcm->tcm_parent));
+ }
if (!q)
goto out;
cops = q->ops->cl_ops;
@@ -866,7 +880,8 @@ static int tc_dump_tfilter(struct sk_buff *skb, struct netlink_callback *cb)
if (tca[TCA_CHAIN] &&
nla_get_u32(tca[TCA_CHAIN]) != chain->index)
continue;
- if (!tcf_chain_dump(chain, skb, cb, index_start, &index))
+ if (!tcf_chain_dump(chain, q, parent, skb, cb,
+ index_start, &index))
break;
}
--
cgit v1.1
From 8c4083b30e56fc71b0e94c26374b32d95d5ea461 Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@mellanox.com>
Date: Thu, 19 Oct 2017 15:50:29 +0200
Subject: net: sched: add block bind/unbind notif. and extended block_get/put
Introduce new type of ndo_setup_tc message to propage binding/unbinding
of a block to driver. Call this ndo whenever qdisc gets/puts a block.
Alongside with this, there's need to propagate binder type from qdisc
code down to the notifier. So introduce extended variants of
block_get/put in order to pass this info.
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
net/sched/cls_api.c | 56 ++++++++++++++++++++++++++++++++++++++++++++++++++---
1 file changed, 53 insertions(+), 3 deletions(-)
(limited to 'net/sched/cls_api.c')
diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c
index 2e8e87f..92dce26 100644
--- a/net/sched/cls_api.c
+++ b/net/sched/cls_api.c
@@ -240,8 +240,36 @@ tcf_chain_filter_chain_ptr_set(struct tcf_chain *chain,
chain->p_filter_chain = p_filter_chain;
}
-int tcf_block_get(struct tcf_block **p_block,
- struct tcf_proto __rcu **p_filter_chain, struct Qdisc *q)
+static void tcf_block_offload_cmd(struct tcf_block *block, struct Qdisc *q,
+ struct tcf_block_ext_info *ei,
+ enum tc_block_command command)
+{
+ struct net_device *dev = q->dev_queue->dev;
+ struct tc_block_offload bo = {};
+
+ if (!tc_can_offload(dev))
+ return;
+ bo.command = command;
+ bo.binder_type = ei->binder_type;
+ bo.block = block;
+ dev->netdev_ops->ndo_setup_tc(dev, TC_SETUP_BLOCK, &bo);
+}
+
+static void tcf_block_offload_bind(struct tcf_block *block, struct Qdisc *q,
+ struct tcf_block_ext_info *ei)
+{
+ tcf_block_offload_cmd(block, q, ei, TC_BLOCK_BIND);
+}
+
+static void tcf_block_offload_unbind(struct tcf_block *block, struct Qdisc *q,
+ struct tcf_block_ext_info *ei)
+{
+ tcf_block_offload_cmd(block, q, ei, TC_BLOCK_UNBIND);
+}
+
+int tcf_block_get_ext(struct tcf_block **p_block,
+ struct tcf_proto __rcu **p_filter_chain, struct Qdisc *q,
+ struct tcf_block_ext_info *ei)
{
struct tcf_block *block = kzalloc(sizeof(*block), GFP_KERNEL);
struct tcf_chain *chain;
@@ -259,6 +287,7 @@ int tcf_block_get(struct tcf_block **p_block,
tcf_chain_filter_chain_ptr_set(chain, p_filter_chain);
block->net = qdisc_net(q);
block->q = q;
+ tcf_block_offload_bind(block, q, ei);
*p_block = block;
return 0;
@@ -266,15 +295,28 @@ err_chain_create:
kfree(block);
return err;
}
+EXPORT_SYMBOL(tcf_block_get_ext);
+
+int tcf_block_get(struct tcf_block **p_block,
+ struct tcf_proto __rcu **p_filter_chain, struct Qdisc *q)
+{
+ struct tcf_block_ext_info ei = {0, };
+
+ return tcf_block_get_ext(p_block, p_filter_chain, q, &ei);
+}
EXPORT_SYMBOL(tcf_block_get);
-void tcf_block_put(struct tcf_block *block)
+void tcf_block_put_ext(struct tcf_block *block,
+ struct tcf_proto __rcu **p_filter_chain, struct Qdisc *q,
+ struct tcf_block_ext_info *ei)
{
struct tcf_chain *chain, *tmp;
if (!block)
return;
+ tcf_block_offload_unbind(block, q, ei);
+
/* XXX: Standalone actions are not allowed to jump to any chain, and
* bound actions should be all removed after flushing. However,
* filters are destroyed in RCU callbacks, we have to hold the chains
@@ -302,6 +344,14 @@ void tcf_block_put(struct tcf_block *block)
tcf_chain_put(chain);
kfree(block);
}
+EXPORT_SYMBOL(tcf_block_put_ext);
+
+void tcf_block_put(struct tcf_block *block)
+{
+ struct tcf_block_ext_info ei = {0, };
+
+ tcf_block_put_ext(block, NULL, block->q, &ei);
+}
EXPORT_SYMBOL(tcf_block_put);
/* Main classifier routine: scans classifier chain attached
--
cgit v1.1
From acb674428c3d57bccbe3f4a1a7a009f6d73e9f41 Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@mellanox.com>
Date: Thu, 19 Oct 2017 15:50:31 +0200
Subject: net: sched: introduce per-block callbacks
Introduce infrastructure that allows drivers to register callbacks that
are called whenever tc would offload inserted rule for a specific block.
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
net/sched/cls_api.c | 105 ++++++++++++++++++++++++++++++++++++++++++++++++++++
1 file changed, 105 insertions(+)
(limited to 'net/sched/cls_api.c')
diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c
index 92dce26..b16c79c 100644
--- a/net/sched/cls_api.c
+++ b/net/sched/cls_api.c
@@ -278,6 +278,8 @@ int tcf_block_get_ext(struct tcf_block **p_block,
if (!block)
return -ENOMEM;
INIT_LIST_HEAD(&block->chain_list);
+ INIT_LIST_HEAD(&block->cb_list);
+
/* Create chain 0 by default, it has to be always present. */
chain = tcf_chain_create(block, 0);
if (!chain) {
@@ -354,6 +356,109 @@ void tcf_block_put(struct tcf_block *block)
}
EXPORT_SYMBOL(tcf_block_put);
+struct tcf_block_cb {
+ struct list_head list;
+ tc_setup_cb_t *cb;
+ void *cb_ident;
+ void *cb_priv;
+ unsigned int refcnt;
+};
+
+void *tcf_block_cb_priv(struct tcf_block_cb *block_cb)
+{
+ return block_cb->cb_priv;
+}
+EXPORT_SYMBOL(tcf_block_cb_priv);
+
+struct tcf_block_cb *tcf_block_cb_lookup(struct tcf_block *block,
+ tc_setup_cb_t *cb, void *cb_ident)
+{ struct tcf_block_cb *block_cb;
+
+ list_for_each_entry(block_cb, &block->cb_list, list)
+ if (block_cb->cb == cb && block_cb->cb_ident == cb_ident)
+ return block_cb;
+ return NULL;
+}
+EXPORT_SYMBOL(tcf_block_cb_lookup);
+
+void tcf_block_cb_incref(struct tcf_block_cb *block_cb)
+{
+ block_cb->refcnt++;
+}
+EXPORT_SYMBOL(tcf_block_cb_incref);
+
+unsigned int tcf_block_cb_decref(struct tcf_block_cb *block_cb)
+{
+ return --block_cb->refcnt;
+}
+EXPORT_SYMBOL(tcf_block_cb_decref);
+
+struct tcf_block_cb *__tcf_block_cb_register(struct tcf_block *block,
+ tc_setup_cb_t *cb, void *cb_ident,
+ void *cb_priv)
+{
+ struct tcf_block_cb *block_cb;
+
+ block_cb = kzalloc(sizeof(*block_cb), GFP_KERNEL);
+ if (!block_cb)
+ return NULL;
+ block_cb->cb = cb;
+ block_cb->cb_ident = cb_ident;
+ block_cb->cb_priv = cb_priv;
+ list_add(&block_cb->list, &block->cb_list);
+ return block_cb;
+}
+EXPORT_SYMBOL(__tcf_block_cb_register);
+
+int tcf_block_cb_register(struct tcf_block *block,
+ tc_setup_cb_t *cb, void *cb_ident,
+ void *cb_priv)
+{
+ struct tcf_block_cb *block_cb;
+
+ block_cb = __tcf_block_cb_register(block, cb, cb_ident, cb_priv);
+ return block_cb ? 0 : -ENOMEM;
+}
+EXPORT_SYMBOL(tcf_block_cb_register);
+
+void __tcf_block_cb_unregister(struct tcf_block_cb *block_cb)
+{
+ list_del(&block_cb->list);
+ kfree(block_cb);
+}
+EXPORT_SYMBOL(__tcf_block_cb_unregister);
+
+void tcf_block_cb_unregister(struct tcf_block *block,
+ tc_setup_cb_t *cb, void *cb_ident)
+{
+ struct tcf_block_cb *block_cb;
+
+ block_cb = tcf_block_cb_lookup(block, cb, cb_ident);
+ if (!block_cb)
+ return;
+ __tcf_block_cb_unregister(block_cb);
+}
+EXPORT_SYMBOL(tcf_block_cb_unregister);
+
+static int tcf_block_cb_call(struct tcf_block *block, enum tc_setup_type type,
+ void *type_data, bool err_stop)
+{
+ struct tcf_block_cb *block_cb;
+ int ok_count = 0;
+ int err;
+
+ list_for_each_entry(block_cb, &block->cb_list, list) {
+ err = block_cb->cb(type, type_data, block_cb->cb_priv);
+ if (err) {
+ if (err_stop)
+ return err;
+ } else {
+ ok_count++;
+ }
+ }
+ return ok_count;
+}
+
/* Main classifier routine: scans classifier chain attached
* to this qdisc, (optionally) tests for protocol and asks
* specific classifiers.
--
cgit v1.1
From 208c0f4b5237f1d6611b2c679a8022d6901577d6 Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@mellanox.com>
Date: Thu, 19 Oct 2017 15:50:32 +0200
Subject: net: sched: use tc_setup_cb_call to call per-block callbacks
Extend the tc_setup_cb_call entrypoint function originally used only for
action egress devices callbacks to call per-block callbacks as well.
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
net/sched/cls_api.c | 21 ++++++++++++++++++---
1 file changed, 18 insertions(+), 3 deletions(-)
(limited to 'net/sched/cls_api.c')
diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c
index b16c79c..cdfdc24 100644
--- a/net/sched/cls_api.c
+++ b/net/sched/cls_api.c
@@ -1206,10 +1206,25 @@ static int tc_exts_setup_cb_egdev_call(struct tcf_exts *exts,
return ok_count;
}
-int tc_setup_cb_call(struct tcf_exts *exts, enum tc_setup_type type,
- void *type_data, bool err_stop)
+int tc_setup_cb_call(struct tcf_block *block, struct tcf_exts *exts,
+ enum tc_setup_type type, void *type_data, bool err_stop)
{
- return tc_exts_setup_cb_egdev_call(exts, type, type_data, err_stop);
+ int ok_count;
+ int ret;
+
+ ret = tcf_block_cb_call(block, type, type_data, err_stop);
+ if (ret < 0)
+ return ret;
+ ok_count = ret;
+
+ if (!exts)
+ return ok_count;
+ ret = tc_exts_setup_cb_egdev_call(exts, type, type_data, err_stop);
+ if (ret < 0)
+ return ret;
+ ok_count += ret;
+
+ return ok_count;
}
EXPORT_SYMBOL(tc_setup_cb_call);
--
cgit v1.1
From 9d452cebd7d69e9eb22b4c0482fdbb6fc762167f Mon Sep 17 00:00:00 2001
From: Or Gerlitz <ogerlitz@mellanox.com>
Date: Tue, 24 Oct 2017 08:58:02 +0300
Subject: net/sched: Fix actions list corruption when adding offloaded tc flows
Prior to commit b3f55bdda8df, the networking core doesn't wire an in-place
actions list the when the low level driver is called to offload the flow,
but all low level drivers do that (call tcf_exts_to_list()) in their
offloading "add" logic.
Now, the in-place list is set in the core which goes over the list in a loop,
but also by the hw driver when their offloading code is invoked indirectly:
cls_xxx add flow -> tc_setup_cb_call -> tc_exts_setup_cb_egdev_call -> hw driver
which messes up the core list instance upon driver return. Fix that by avoiding
in-place list on the net core code that deals with adding flows.
Fixes: b3f55bdda8df ('net: sched: introduce per-egress action device callbacks')
Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
net/sched/cls_api.c | 7 +++----
1 file changed, 3 insertions(+), 4 deletions(-)
(limited to 'net/sched/cls_api.c')
diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c
index cdfdc24..0e96cda 100644
--- a/net/sched/cls_api.c
+++ b/net/sched/cls_api.c
@@ -1184,14 +1184,13 @@ static int tc_exts_setup_cb_egdev_call(struct tcf_exts *exts,
#ifdef CONFIG_NET_CLS_ACT
const struct tc_action *a;
struct net_device *dev;
- LIST_HEAD(actions);
- int ret;
+ int i, ret;
if (!tcf_exts_has_actions(exts))
return 0;
- tcf_exts_to_list(exts, &actions);
- list_for_each_entry(a, &actions, list) {
+ for (i = 0; i < exts->nr_actions; i++) {
+ a = exts->actions[i];
if (!a->ops->get_dev)
continue;
dev = a->ops->get_dev(a);
--
cgit v1.1
From 44ae12a768b7212976a362c590075716a77e8f28 Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@mellanox.com>
Date: Wed, 1 Nov 2017 11:47:39 +0100
Subject: net: sched: move the can_offload check from binding phase to rule
insertion phase
This restores the original behaviour before the block callbacks were
introduced. Allow the drivers to do binding of block always, no matter
if the NETIF_F_HW_TC feature is on or off. Move the check to the block
callback which is called for rule insertion.
Reported-by: Alexander Duyck <alexander.duyck@gmail.com>
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
net/sched/cls_api.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
(limited to 'net/sched/cls_api.c')
diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c
index 2c03fcb..15e3216 100644
--- a/net/sched/cls_api.c
+++ b/net/sched/cls_api.c
@@ -256,7 +256,7 @@ static void tcf_block_offload_cmd(struct tcf_block *block, struct Qdisc *q,
struct net_device *dev = q->dev_queue->dev;
struct tc_block_offload bo = {};
- if (!tc_can_offload(dev))
+ if (!dev->netdev_ops->ndo_setup_tc)
return;
bo.command = command;
bo.binder_type = ei->binder_type;
--
cgit v1.1
From 7612fb0387d6ffcfc3173527466fe3f596657c58 Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@mellanox.com>
Date: Wed, 1 Nov 2017 11:47:40 +0100
Subject: net: sched: remove tc_can_offload check from egdev call
Since the only user, mlx5 driver does the check in
mlx5e_setup_tc_block_cb, no need to check here.
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
net/sched/cls_api.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
(limited to 'net/sched/cls_api.c')
diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c
index 15e3216..a26c690 100644
--- a/net/sched/cls_api.c
+++ b/net/sched/cls_api.c
@@ -1206,7 +1206,7 @@ static int tc_exts_setup_cb_egdev_call(struct tcf_exts *exts,
if (!a->ops->get_dev)
continue;
dev = a->ops->get_dev(a);
- if (!dev || !tc_can_offload(dev))
+ if (!dev)
continue;
ret = tc_setup_cb_egdev_call(dev, type, type_data, err_stop);
if (ret < 0)
--
cgit v1.1
From 4bb1b116b7f37a64c08d28213a2e6f87fcef2d8b Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@mellanox.com>
Date: Thu, 2 Nov 2017 15:07:01 +0100
Subject: net: sched: move block offload unbind after all chains are flushed
Currently, the offload unbind is done before the chains are flushed.
That causes driver to unregister block callback before it can get all
the callback calls done during flush, leaving the offloaded tps inside
the HW. So fix the order to prevent this situation and restore the
original behaviour.
Reported-by: Alexander Duyck <alexander.duyck@gmail.com>
Reported-by: Jakub Kicinski <kubakici@wp.pl>
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
net/sched/cls_api.c | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
(limited to 'net/sched/cls_api.c')
diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c
index a26c690..3364347 100644
--- a/net/sched/cls_api.c
+++ b/net/sched/cls_api.c
@@ -343,11 +343,11 @@ void tcf_block_put_ext(struct tcf_block *block,
if (!block)
return;
- tcf_block_offload_unbind(block, q, ei);
-
list_for_each_entry_safe(chain, tmp, &block->chain_list, list)
tcf_chain_flush(chain);
+ tcf_block_offload_unbind(block, q, ei);
+
INIT_WORK(&block->work, tcf_block_put_final);
/* Wait for existing RCU callbacks to cool down, make sure their works
* have been queued before this. We can not flush pending works here
--
cgit v1.1
From 8f918d3ff4a1283a1693afe2b4c8e1844674ca15 Mon Sep 17 00:00:00 2001
From: Cong Wang <xiyou.wangcong@gmail.com>
Date: Thu, 2 Nov 2017 17:32:08 -0700
Subject: net_sched: check NULL in tcf_block_put()
Callers of tcf_block_put() could pass NULL so
we can't use block->q before checking if block is
NULL or not.
tcf_block_put_ext() callers are fine, it is always
non-NULL.
Fixes: 8c4083b30e56 ("net: sched: add block bind/unbind notif. and extended block_get/put")
Reported-by: Dave Taht <dave.taht@gmail.com>
Cc: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Reviewed-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
net/sched/cls_api.c | 5 ++---
1 file changed, 2 insertions(+), 3 deletions(-)
(limited to 'net/sched/cls_api.c')
diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c
index 3364347..8d1885a 100644
--- a/net/sched/cls_api.c
+++ b/net/sched/cls_api.c
@@ -340,9 +340,6 @@ void tcf_block_put_ext(struct tcf_block *block,
{
struct tcf_chain *chain, *tmp;
- if (!block)
- return;
-
list_for_each_entry_safe(chain, tmp, &block->chain_list, list)
tcf_chain_flush(chain);
@@ -362,6 +359,8 @@ void tcf_block_put(struct tcf_block *block)
{
struct tcf_block_ext_info ei = {0, };
+ if (!block)
+ return;
tcf_block_put_ext(block, NULL, block->q, &ei);
}
--
cgit v1.1
From c7eb7d7230509ec862d4144f7a831f995bc5d028 Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@mellanox.com>
Date: Fri, 3 Nov 2017 11:46:24 +0100
Subject: net: sched: introduce chain_head_change callback
Add a callback that is to be called whenever head of the chain changes.
Also provide a callback for the default case when the caller gets a
block using non-extended getter.
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
net/sched/cls_api.c | 54 +++++++++++++++++++++++++++++++----------------------
1 file changed, 32 insertions(+), 22 deletions(-)
(limited to 'net/sched/cls_api.c')
diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c
index 8d1885a..206e19f 100644
--- a/net/sched/cls_api.c
+++ b/net/sched/cls_api.c
@@ -195,12 +195,19 @@ static struct tcf_chain *tcf_chain_create(struct tcf_block *block,
return chain;
}
+static void tcf_chain_head_change(struct tcf_chain *chain,
+ struct tcf_proto *tp_head)
+{
+ if (chain->chain_head_change)
+ chain->chain_head_change(tp_head,
+ chain->chain_head_change_priv);
+}
+
static void tcf_chain_flush(struct tcf_chain *chain)
{
struct tcf_proto *tp;
- if (chain->p_filter_chain)
- RCU_INIT_POINTER(*chain->p_filter_chain, NULL);
+ tcf_chain_head_change(chain, NULL);
while ((tp = rtnl_dereference(chain->filter_chain)) != NULL) {
RCU_INIT_POINTER(chain->filter_chain, tp->next);
tcf_chain_put(chain);
@@ -242,13 +249,6 @@ void tcf_chain_put(struct tcf_chain *chain)
}
EXPORT_SYMBOL(tcf_chain_put);
-static void
-tcf_chain_filter_chain_ptr_set(struct tcf_chain *chain,
- struct tcf_proto __rcu **p_filter_chain)
-{
- chain->p_filter_chain = p_filter_chain;
-}
-
static void tcf_block_offload_cmd(struct tcf_block *block, struct Qdisc *q,
struct tcf_block_ext_info *ei,
enum tc_block_command command)
@@ -276,8 +276,7 @@ static void tcf_block_offload_unbind(struct tcf_block *block, struct Qdisc *q,
tcf_block_offload_cmd(block, q, ei, TC_BLOCK_UNBIND);
}
-int tcf_block_get_ext(struct tcf_block **p_block,
- struct tcf_proto __rcu **p_filter_chain, struct Qdisc *q,
+int tcf_block_get_ext(struct tcf_block **p_block, struct Qdisc *q,
struct tcf_block_ext_info *ei)
{
struct tcf_block *block = kzalloc(sizeof(*block), GFP_KERNEL);
@@ -295,7 +294,9 @@ int tcf_block_get_ext(struct tcf_block **p_block,
err = -ENOMEM;
goto err_chain_create;
}
- tcf_chain_filter_chain_ptr_set(chain, p_filter_chain);
+ WARN_ON(!ei->chain_head_change);
+ chain->chain_head_change = ei->chain_head_change;
+ chain->chain_head_change_priv = ei->chain_head_change_priv;
block->net = qdisc_net(q);
block->q = q;
tcf_block_offload_bind(block, q, ei);
@@ -308,12 +309,23 @@ err_chain_create:
}
EXPORT_SYMBOL(tcf_block_get_ext);
+static void tcf_chain_head_change_dflt(struct tcf_proto *tp_head, void *priv)
+{
+ struct tcf_proto __rcu **p_filter_chain = priv;
+
+ rcu_assign_pointer(*p_filter_chain, tp_head);
+}
+
int tcf_block_get(struct tcf_block **p_block,
struct tcf_proto __rcu **p_filter_chain, struct Qdisc *q)
{
- struct tcf_block_ext_info ei = {0, };
+ struct tcf_block_ext_info ei = {
+ .chain_head_change = tcf_chain_head_change_dflt,
+ .chain_head_change_priv = p_filter_chain,
+ };
- return tcf_block_get_ext(p_block, p_filter_chain, q, &ei);
+ WARN_ON(!p_filter_chain);
+ return tcf_block_get_ext(p_block, q, &ei);
}
EXPORT_SYMBOL(tcf_block_get);
@@ -334,8 +346,7 @@ static void tcf_block_put_final(struct work_struct *work)
* actions should be all removed after flushing. However, filters are now
* destroyed in tc filter workqueue with RTNL lock, they can not race here.
*/
-void tcf_block_put_ext(struct tcf_block *block,
- struct tcf_proto __rcu **p_filter_chain, struct Qdisc *q,
+void tcf_block_put_ext(struct tcf_block *block, struct Qdisc *q,
struct tcf_block_ext_info *ei)
{
struct tcf_chain *chain, *tmp;
@@ -361,7 +372,7 @@ void tcf_block_put(struct tcf_block *block)
if (!block)
return;
- tcf_block_put_ext(block, NULL, block->q, &ei);
+ tcf_block_put_ext(block, block->q, &ei);
}
EXPORT_SYMBOL(tcf_block_put);
@@ -537,9 +548,8 @@ static void tcf_chain_tp_insert(struct tcf_chain *chain,
struct tcf_chain_info *chain_info,
struct tcf_proto *tp)
{
- if (chain->p_filter_chain &&
- *chain_info->pprev == chain->filter_chain)
- rcu_assign_pointer(*chain->p_filter_chain, tp);
+ if (*chain_info->pprev == chain->filter_chain)
+ tcf_chain_head_change(chain, tp);
RCU_INIT_POINTER(tp->next, tcf_chain_tp_prev(chain_info));
rcu_assign_pointer(*chain_info->pprev, tp);
tcf_chain_hold(chain);
@@ -551,8 +561,8 @@ static void tcf_chain_tp_remove(struct tcf_chain *chain,
{
struct tcf_proto *next = rtnl_dereference(chain_info->next);
- if (chain->p_filter_chain && tp == chain->filter_chain)
- RCU_INIT_POINTER(*chain->p_filter_chain, next);
+ if (tp == chain->filter_chain)
+ tcf_chain_head_change(chain, next);
RCU_INIT_POINTER(*chain_info->pprev, next);
tcf_chain_put(chain);
}
--
cgit v1.1