net/flower: Introduce hardware offload support
This patch is based on a patch made by John Fastabend.
It adds support for offloading cls_flower.
when NETIF_F_HW_TC is on:
flags = 0 => Rule will be processed twice - by hardware, and if
still relevant, by software.
flags = SKIP_HW => Rull will be processed by software only
If hardware fail/not capabale to apply the rule, operation will NOT
fail. Filter will be processed by SW only.
Acked-by: Jiri Pirko <jiri@mellanox.com>
Suggested-by: John Fastabend <john.r.fastabend@intel.com>
Signed-off-by: Amir Vadai <amir@vadai.me>
Signed-off-by: David S. Miller <davem@davemloft.net>
diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c
index 95b0212..25d8766 100644
--- a/net/sched/cls_flower.c
+++ b/net/sched/cls_flower.c
@@ -165,6 +165,51 @@
kfree(f);
}
+static void fl_hw_destroy_filter(struct tcf_proto *tp, u64 cookie)
+{
+ struct net_device *dev = tp->q->dev_queue->dev;
+ struct tc_cls_flower_offload offload = {0};
+ struct tc_to_netdev tc;
+
+ if (!tc_should_offload(dev, 0))
+ return;
+
+ offload.command = TC_CLSFLOWER_DESTROY;
+ offload.cookie = cookie;
+
+ tc.type = TC_SETUP_CLSFLOWER;
+ tc.cls_flower = &offload;
+
+ dev->netdev_ops->ndo_setup_tc(dev, tp->q->handle, tp->protocol, &tc);
+}
+
+static void fl_hw_replace_filter(struct tcf_proto *tp,
+ struct flow_dissector *dissector,
+ struct fl_flow_key *mask,
+ struct fl_flow_key *key,
+ struct tcf_exts *actions,
+ u64 cookie, u32 flags)
+{
+ struct net_device *dev = tp->q->dev_queue->dev;
+ struct tc_cls_flower_offload offload = {0};
+ struct tc_to_netdev tc;
+
+ if (!tc_should_offload(dev, flags))
+ return;
+
+ offload.command = TC_CLSFLOWER_REPLACE;
+ offload.cookie = cookie;
+ offload.dissector = dissector;
+ offload.mask = mask;
+ offload.key = key;
+ offload.exts = actions;
+
+ tc.type = TC_SETUP_CLSFLOWER;
+ tc.cls_flower = &offload;
+
+ dev->netdev_ops->ndo_setup_tc(dev, tp->q->handle, tp->protocol, &tc);
+}
+
static bool fl_destroy(struct tcf_proto *tp, bool force)
{
struct cls_fl_head *head = rtnl_dereference(tp->root);
@@ -174,6 +219,7 @@
return false;
list_for_each_entry_safe(f, next, &head->filters, list) {
+ fl_hw_destroy_filter(tp, (u64)f);
list_del_rcu(&f->list);
call_rcu(&f->rcu, fl_destroy_filter);
}
@@ -459,6 +505,7 @@
struct cls_fl_filter *fnew;
struct nlattr *tb[TCA_FLOWER_MAX + 1];
struct fl_flow_mask mask = {};
+ u32 flags = 0;
int err;
if (!tca[TCA_OPTIONS])
@@ -486,6 +533,9 @@
}
fnew->handle = handle;
+ if (tb[TCA_FLOWER_FLAGS])
+ flags = nla_get_u32(tb[TCA_FLOWER_FLAGS]);
+
err = fl_set_parms(net, tp, fnew, &mask, base, tb, tca[TCA_RATE], ovr);
if (err)
goto errout;
@@ -498,9 +548,20 @@
head->ht_params);
if (err)
goto errout;
- if (fold)
+
+ fl_hw_replace_filter(tp,
+ &head->dissector,
+ &mask.key,
+ &fnew->key,
+ &fnew->exts,
+ (u64)fnew,
+ flags);
+
+ if (fold) {
rhashtable_remove_fast(&head->ht, &fold->ht_node,
head->ht_params);
+ fl_hw_destroy_filter(tp, (u64)fold);
+ }
*arg = (unsigned long) fnew;
@@ -527,6 +588,7 @@
rhashtable_remove_fast(&head->ht, &f->ht_node,
head->ht_params);
list_del_rcu(&f->list);
+ fl_hw_destroy_filter(tp, (u64)f);
tcf_unbind_filter(tp, &f->res);
call_rcu(&f->rcu, fl_destroy_filter);
return 0;