net/sched: cls_api: Support hardware miss to tc action
Subsystems (6)
v9 cover net/sched: cls_api: Support hardware miss to tc action
Hi,
This series adds support for hardware miss to instruct tc to continue execution in a specific tc action instance on a filter's action list. The mlx5 driver patch (besides the refactors) shows its usage instead of using just chain restore.
Currently a filter's action list must be executed all together or not at all as driver are only able to tell tc to continue executing from a specific tc chain, and not a specific filter/action.
This is troublesome with regards to action CT, where new connections should be sent to software (via tc chain restore), and established connections can be handled in hardware.
Checking for new connections is done when executing the ct action in hardware (by checking the packet's tuple against known established tuples). But if there is a packet modification (pedit) action before action CT and the checked tuple is a new connection, hardware will need to revert the previous packet modifications before sending it back to software so it can re-match the same tc filter in software and re-execute its CT action.
The following is an example configuration of stateless nat on mlx5 driver that isn't supported before this patchet:
#Setup corrosponding mlx5 VFs in namespaces
$ ip netns add ns0 $ ip netns add ns1 $ ip link set dev enp8s0f0v0 netns ns0 $ ip netns exec ns0 ifconfig enp8s0f0v0 1.1.1.1/24 up $ ip link set dev enp8s0f0v1 netns ns1 $ ip netns exec ns1 ifconfig enp8s0f0v1 1.1.1.2/24 up
#Setup tc arp and ct rules on mxl5 VF representors
$ tc qdisc add dev enp8s0f0_0 ingress $ tc qdisc add dev enp8s0f0_1 ingress $ ifconfig enp8s0f0_0 up $ ifconfig enp8s0f0_1 up
#Original side
$ tc filter add dev enp8s0f0_0 ingress chain 0 proto ip flower \
ct_state -trk ip_proto tcp dst_port 8888 \
action pedit ex munge tcp dport set 5001 pipe \
action csum ip tcp pipe \
action ct pipe \
action goto chain 1
$ tc filter add dev enp8s0f0_0 ingress chain 1 proto ip flower \
ct_state +trk+est \
action mirred egress redirect dev enp8s0f0_1
$ tc filter add dev enp8s0f0_0 ingress chain 1 proto ip flower \
ct_state +trk+new \
action ct commit pipe \
action mirred egress redirect dev enp8s0f0_1
$ tc filter add dev enp8s0f0_0 ingress chain 0 proto arp flower \
action mirred egress redirect dev enp8s0f0_1#Reply side
$ tc filter add dev enp8s0f0_1 ingress chain 0 proto arp flower \
action mirred egress redirect dev enp8s0f0_0
$ tc filter add dev enp8s0f0_1 ingress chain 0 proto ip flower \
ct_state -trk ip_proto tcp \
action ct pipe \
action pedit ex munge tcp sport set 8888 pipe \
action csum ip tcp pipe \
action mirred egress redirect dev enp8s0f0_0#Run traffic
$ ip netns exec ns1 iperf -s -p 5001& $ sleep 2 #wait for iperf to fully open $ ip netns exec ns0 iperf -c 1.1.1.2 -p 8888
#dump tc filter stats on enp8s0f0_0 chain 0 rule and see hardware packets:
$ tc -s filter show dev enp8s0f0_0 ingress chain 0 proto ip | grep "hardware.*pkt"
Sent hardware 9310116832 bytes 6149672 pkt
Sent hardware 9310116832 bytes 6149672 pkt
Sent hardware 9310116832 bytes 6149672 pktA new connection executing the first filter in hardware will first rewrite the dst port to the new port, and then the ct action is executed, because this is a new connection, hardware will need to be send this back to software, on chain 0, to execute the first filter again in software. The dst port needs to be reverted otherwise it won't re-match the old dst port in the first filter. Because of that, currently mlx5 driver will reject offloading the above action ct rule.
This series adds supports partial offload of a filter's action list, and letting tc software continue processing in the specific action instance where hardware left off (in the above case after the "action pedit ex munge tcp dport... of the first rule") allowing support for scenarios such as the above.
Changelog:
v1->v2:
Fixed compilation without CONFIG_NET_CLS
Cover letter re-write
v2->v3:
Unlock spin_lock on error in cls flower filter handle refactor Cover letter
v3->v4:
Silence warning by clang
v4->v5:
Cover letter example
Removed ifdef as much as possible by using inline stubs
v5->v6:
Removed new inlines in cls_api.c (bot complained in patchwork) Added reviewed-by/ack - Thanks!
v6->v7:
Removed WARN_ON from pkt path (leon)
Removed unnecessary return in void func
v7->v8:
Removed #if IS_ENABLED on skb ext adding Kconfig changes Complex variable init in seperate lines if,else if, else if ---> switch case
v8->v9:
Removed even more IS_ENABLED because of Kconfig
Paul Blakey (7):
net/sched: cls_api: Support hardware miss to tc action net/sched: flower: Move filter handle initialization earlier net/sched: flower: Support hardware miss to tc action net/mlx5: Kconfig: Make tc offload depend on tc skb extension net/mlx5: Refactor tc miss handling to a single function net/mlx5e: Rename CHAIN_TO_REG to MAPPED_OBJ_TO_REG net/mlx5e: TC, Set CT miss to the specific ct action instance
.../net/ethernet/mellanox/mlx5/core/Kconfig | 4 +- .../ethernet/mellanox/mlx5/core/en/rep/tc.c | 225 ++------------ .../mellanox/mlx5/core/en/tc/sample.c | 2 +- .../ethernet/mellanox/mlx5/core/en/tc_ct.c | 39 +-- .../ethernet/mellanox/mlx5/core/en/tc_ct.h | 2 + .../net/ethernet/mellanox/mlx5/core/en_rx.c | 4 +- .../net/ethernet/mellanox/mlx5/core/en_tc.c | 280 ++++++++++++++++-- .../net/ethernet/mellanox/mlx5/core/en_tc.h | 23 +- .../net/ethernet/mellanox/mlx5/core/eswitch.h | 2 + .../mellanox/mlx5/core/lib/fs_chains.c | 14 +- include/linux/skbuff.h | 6 +- include/net/flow_offload.h | 1 + include/net/pkt_cls.h | 34 ++- include/net/sch_generic.h | 2 + net/openvswitch/flow.c | 3 +- net/sched/act_api.c | 2 +- net/sched/cls_api.c | 213 ++++++++++++- net/sched/cls_flower.c | 73 +++-- 18 files changed, 602 insertions(+), 327 deletions(-)
Signature · 1 line
2.30.1
PATCH v9 1/7 net/sched: cls_api: Support hardware miss to tc action
For drivers to support partial offload of a filter's action list, add support for action miss to specify an action instance to continue from in sw.
CT action in particular can't be fully offloaded, as new connections need to be handled in software. This imposes other limitations on the actions that can be offloaded together with the CT action, such as packet modifications.
Assign each action on a filter's action list a unique miss_cookie which drivers can then use to fill action_miss part of the tc skb extension. On getting back this miss_cookie, find the action instance with relevant cookie and continue classifying from there.
--- include/linux/skbuff.h | 6 +- include/net/flow_offload.h | 1 + include/net/pkt_cls.h | 34 +++--- include/net/sch_generic.h | 2 + net/openvswitch/flow.c | 3 +- net/sched/act_api.c | 2 +- net/sched/cls_api.c | 213 +++++++++++++++++++++++++++++++++++-- 7 files changed, 234 insertions(+), 27 deletions(-)
include/linux/skbuff.h +5 -1
@@ -311,12 +311,16 @@ struct nf_bridge_info {* and read by ovs to recirc_id. */ struct tc_skb_ext { -__u32 chain; +union { +u64 act_miss_cookie; +__u32 chain; + };__u16 mru;__u16 zone;u8 post_ct:1 ;u8 post_ct_snat:1 ;u8 post_ct_dnat:1 ; +u8 act_miss:1 ;/* Set if act_miss_cookie is used */ };#endif
include/net/flow_offload.h +1 -0
@@ -228,6 +228,7 @@ void flow_action_cookie_destroy(struct flow_action_cookie *cookie);struct flow_action_entry {enum flow_action_id id;u32 hw_index; +u64 miss_cookie;enum flow_action_hw_stats hw_stats;action_destr destructor;void *destructor_priv;
include/net/pkt_cls.h +20 -14
@@ -59,6 +59,8 @@ int tcf_block_get_ext(struct tcf_block **p_block, struct Qdisc *q,void tcf_block_put (struct tcf_block *block);void tcf_block_put_ext (struct tcf_block *block,struct Qdisc *q,struct tcf_block_ext_info *ei); +int tcf_exts_init_ex (struct tcf_exts *exts,struct net *net,int action, +int police,struct tcf_proto *tp,u32 handle,bool used_action_miss);static inline bool tcf_block_shared (struct tcf_block *block) {
@@ -229,6 +231,7 @@ struct tcf_exts {struct tc_action **actions;struct net *net;netns_tracker ns_tracker; +struct tcf_exts_miss_cookie_node *miss_cookie_node;#endif /* Map to export classifier specific extension TLV types to the * generic extensions API. Unsupported extensions must be set to 0.
@@ -240,21 +243,11 @@ struct tcf_exts {static inline int tcf_exts_init (struct tcf_exts *exts,struct net *net,int action,int police) { -#ifdef CONFIG_NET_CLS_ACT - exts->type =0 ; - exts->nr_actions =0 ; -/* Note: we do not own yet a reference on net. -* This reference might be taken later from tcf_exts_get_net(). -*/ - exts->net = net; - exts->actions =kcalloc (TCA_ACT_MAX_PRIO ,sizeof (struct tc_action *), -GFP_KERNEL ); -if (!exts->actions) -return -ENOMEM ; +#ifdef CONFIG_NET_CLS +return tcf_exts_init_ex (exts, net, action, police,NULL ,0 , false); +#else +return -EOPNOTSUPP ;#endif - exts->action = action; - exts->police = police; -return 0 ; }/* Return false if the netns is being destroyed in cleanup_net(). Callers
@@ -353,6 +346,18 @@ tcf_exts_exec(struct sk_buff *skb, struct tcf_exts *exts,return TC_ACT_OK ; } +static inline int +tcf_exts_exec_ex (struct sk_buff *skb,struct tcf_exts *exts,int act_index, +struct tcf_result *res) +{ +#ifdef CONFIG_NET_CLS_ACT +return tcf_action_exec (skb, exts->actions + act_index, + exts->nr_actions - act_index, res); +#else +return TC_ACT_OK ; +#endif +} + int tcf_exts_validate(struct net *net, struct tcf_proto *tp, struct nlattr **tb, struct nlattr *rate_tlv, struct tcf_exts *exts, u32 flags,
@@ -577,6 +582,7 @@ int tc_setup_offload_action(struct flow_action *flow_action,void tc_cleanup_offload_action (struct flow_action *flow_action);int tc_setup_action (struct flow_action *flow_action,struct tc_action *actions[], +u32 miss_cookie_base,struct netlink_ext_ack *extack); int tc_setup_cb_call(struct tcf_block *block, enum tc_setup_type type,
include/net/sch_generic.h +2 -0
@@ -369,6 +369,8 @@ struct tcf_proto_ops {struct nlattr **tca, struct netlink_ext_ack *extack);void (*tmplt_destroy)(void *tmplt_priv); +struct tcf_exts * (*get_exts)(const struct tcf_proto *tp, +u32 handle);/* rtnetlink specific */ int (*dump)(struct net*, struct tcf_proto*, void *,
net/openvswitch/flow.c +2 -1
@@ -1038,7 +1038,8 @@ int ovs_flow_key_extract(const struct ip_tunnel_info *tun_info,#if IS_ENABLED (CONFIG_NET_TC_SKB_EXT )if (tc_skb_ext_tc_enabled ()) { tc_ext =skb_ext_find (skb,TC_SKB_EXT ); - key->recirc_id = tc_ext ? tc_ext->chain :0 ; + key->recirc_id = tc_ext && !tc_ext->act_miss ? + tc_ext->chain :0 ;OVS_CB (skb)->mru = tc_ext ? tc_ext->mru :0 ; post_ct = tc_ext ? tc_ext->post_ct : false; post_ct_snat = post_ct ? tc_ext->post_ct_snat : false;
net/sched/act_api.c +1 -1
@@ -272,7 +272,7 @@ static int tcf_action_offload_add_ex(struct tc_action *action,if (err) goto fl_err; - err =tc_setup_action (&fl_action->action, actions, extack); + err =tc_setup_action (&fl_action->action, actions,0 , extack);if (err) {NL_SET_ERR_MSG_MOD (extack,"Failed to setup tc actions for offload" );
net/sched/cls_api.c +203 -10
305 lines not on this page · raw message
Signature · 1 line
2.30.1
Quoted 55 lines · Paul Blakey
For drivers to support partial offload of a filter's action list, add support for action miss to specify an action instance to continue from in sw.
CT action in particular can't be fully offloaded, as new connections need to be handled in software. This imposes other limitations on the actions that can be offloaded together with the CT action, such as packet modifications.
Assign each action on a filter's action list a unique
miss_cookiewhich drivers can then use to fillaction_misspart of the tc skb extension. On getting back thismiss_cookie, find the action instance with relevant cookie and continue classifying from there.Signed-off-by Paul Blakey <[email protected]>Reviewed-by Jiri Pirko <[email protected]>Reviewed-by Simon Horman <[email protected]>Acked-by Jamal Hadi Salim <[email protected]>--- include/linux/skbuff.h | 6 +- include/net/flow_offload.h | 1 + include/net/pkt_cls.h | 34 +++--- include/net/sch_generic.h | 2 + net/openvswitch/flow.c | 3 +- net/sched/act_api.c | 2 +- net/sched/cls_api.c | 213 +++++++++++++++++++++++++++++++++++-- 7 files changed, 234 insertions(+), 27 deletions(-)include/linux/skbuff.h +5
-1@@ -311,12 +311,16 @@ struct nf_bridge_info {* and read by ovs to recirc_id. */ struct tc_skb_ext { -__u32 chain; +union { +u64 act_miss_cookie; +__u32 chain; + };__u16 mru;__u16 zone;u8 post_ct:1 ;u8 post_ct_snat:1 ;u8 post_ct_dnat:1 ; +u8 act_miss:1 ;/* Set if act_miss_cookie is used */ };#endif include/net/flow_offload.h +0
-0
include/net/flow_offload.h void flow_action_cookie_destroy(struct flow_action_cookie *cookie); · line 231
Quoted 4 lines
include/net/flow_offload.h +1
-0@@ -228,6 +228,7 @@ void flow_action_cookie_destroy(struct flow_action_cookie *cookie);struct flow_action_entry {enum flow_action_id id;u32 hw_index; +u64 miss_cookie;
The per-action stats patchset is adding a cookie for the actions as well, and exactly on this struct:
@@ -228,6 +228,7 @@ struct flow_action_cookie *flow_action_cookie_create(void *data,
struct flow_action_entry {
enum flow_action_id id;
u32 hw_index;
+ unsigned long act_cookie;
enum flow_action_hw_stats hw_stats;
action_destr destructor;
void *destructor_priv;There, it is a simple value: the act pointer itself. Here, it is already more complex. Can them be merged into only one maybe?
If not, perhaps act_cookie should be renamed to stats_cookie then.
Quoted 153 lines
include/net/flow_offload.h +0
-0enum flow_action_hw_stats hw_stats;action_destr destructor;void *destructor_priv;include/net/pkt_cls.h +20
-14@@ -59,6 +59,8 @@ int tcf_block_get_ext(struct tcf_block **p_block, struct Qdisc *q,void tcf_block_put (struct tcf_block *block);void tcf_block_put_ext (struct tcf_block *block,struct Qdisc *q,struct tcf_block_ext_info *ei); +int tcf_exts_init_ex (struct tcf_exts *exts,struct net *net,int action, +int police,struct tcf_proto *tp,u32 handle,bool used_action_miss);static inline bool tcf_block_shared (struct tcf_block *block) {@@ -229,6 +231,7 @@ struct tcf_exts {struct tc_action **actions;struct net *net;netns_tracker ns_tracker; +struct tcf_exts_miss_cookie_node *miss_cookie_node;#endif /* Map to export classifier specific extension TLV types to the * generic extensions API. Unsupported extensions must be set to 0. @@ -240,21 +243,11 @@ struct tcf_exts {static inline int tcf_exts_init (struct tcf_exts *exts,struct net *net,int action,int police) { -#ifdef CONFIG_NET_CLS_ACT - exts->type =0 ; - exts->nr_actions =0 ; -/* Note: we do not own yet a reference on net. -* This reference might be taken later from tcf_exts_get_net(). -*/ - exts->net = net; - exts->actions =kcalloc (TCA_ACT_MAX_PRIO ,sizeof (struct tc_action *), -GFP_KERNEL ); -if (!exts->actions) -return -ENOMEM ; +#ifdef CONFIG_NET_CLS +return tcf_exts_init_ex (exts, net, action, police,NULL ,0 , false); +#else +return -EOPNOTSUPP ;#endif - exts->action = action; - exts->police = police; -return 0 ; }/* Return false if the netns is being destroyed in cleanup_net(). Callers @@ -353,6 +346,18 @@ tcf_exts_exec(struct sk_buff *skb, struct tcf_exts *exts,return TC_ACT_OK ; } +static inline int +tcf_exts_exec_ex (struct sk_buff *skb,struct tcf_exts *exts,int act_index, +struct tcf_result *res) +{ +#ifdef CONFIG_NET_CLS_ACT +return tcf_action_exec (skb, exts->actions + act_index, + exts->nr_actions - act_index, res); +#else +return TC_ACT_OK ; +#endif +} + int tcf_exts_validate(struct net *net, struct tcf_proto *tp, struct nlattr **tb, struct nlattr *rate_tlv, struct tcf_exts *exts, u32 flags,@@ -577,6 +582,7 @@ int tc_setup_offload_action(struct flow_action *flow_action,void tc_cleanup_offload_action (struct flow_action *flow_action);int tc_setup_action (struct flow_action *flow_action,struct tc_action *actions[], +u32 miss_cookie_base,struct netlink_ext_ack *extack); int tc_setup_cb_call(struct tcf_block *block, enum tc_setup_type type,include/net/sch_generic.h +2
-0@@ -369,6 +369,8 @@ struct tcf_proto_ops {struct nlattr **tca, struct netlink_ext_ack *extack);void (*tmplt_destroy)(void *tmplt_priv); +struct tcf_exts * (*get_exts)(const struct tcf_proto *tp, +u32 handle);/* rtnetlink specific */ int (*dump)(struct net*, struct tcf_proto*, void *,net/openvswitch/flow.c +2
-1@@ -1038,7 +1038,8 @@ int ovs_flow_key_extract(const struct ip_tunnel_info *tun_info,#if IS_ENABLED (CONFIG_NET_TC_SKB_EXT )if (tc_skb_ext_tc_enabled ()) { tc_ext =skb_ext_find (skb,TC_SKB_EXT ); - key->recirc_id = tc_ext ? tc_ext->chain :0 ; + key->recirc_id = tc_ext && !tc_ext->act_miss ? + tc_ext->chain :0 ;OVS_CB (skb)->mru = tc_ext ? tc_ext->mru :0 ; post_ct = tc_ext ? tc_ext->post_ct : false; post_ct_snat = post_ct ? tc_ext->post_ct_snat : false;net/sched/act_api.c +1
-1@@ -272,7 +272,7 @@ static int tcf_action_offload_add_ex(struct tc_action *action,if (err) goto fl_err; - err =tc_setup_action (&fl_action->action, actions, extack); + err =tc_setup_action (&fl_action->action, actions,0 , extack);if (err) {NL_SET_ERR_MSG_MOD (extack,"Failed to setup tc actions for offload" );net/sched/cls_api.c +21
-0@@ -22,6 +22,7 @@#include <linux/idr.h> #include <linux/jhash.h> #include <linux/rculist.h> +#include <linux/rhashtable.h> #include <net/net_namespace.h> #include <net/sock.h> #include <net/netlink.h> @@ -50,6 +51,109 @@ static LIST_HEAD(tcf_proto_base);/* Protects list of registered TC modules. It is pure SMP lock. */ static DEFINE_RWLOCK (cls_mod_lock); +static struct xarray tcf_exts_miss_cookies_xa; +struct tcf_exts_miss_cookie_node { +const struct tcf_chain *chain; +const struct tcf_proto *tp; +const struct tcf_exts *exts; +u32 chain_index; +u32 tp_prio; +u32 handle; +u32 miss_cookie_base; +struct rcu_head rcu; +}; + +/* Each tc action entry cookie will be comprised of 32bit miss_cookie_base + +* action index in the exts tc actions array. +*/ +union tcf_exts_miss_cookie { +struct { +u32 miss_cookie_base; +u32 act_index; + };
net/sched/cls_api.c static LIST_HEAD(tcf_proto_base); · line 83
Quoted 10 lines
net/sched/cls_api.c +10
-0+u64 miss_cookie; +}; + +#if IS_ENABLED (CONFIG_NET_TC_SKB_EXT ) +static int +tcf_exts_miss_cookie_base_alloc (struct tcf_exts *exts,struct tcf_proto *tp, +u32 handle) +{ +struct tcf_exts_miss_cookie_node *n; +static u32 next;
What protects this static variable from concurrent access?
Quoted 149 lines
net/sched/cls_api.c +108
-6+int err; + +if (WARN_ON (!handle || !tp->ops->get_exts)) +return -EINVAL ; + + n =kzalloc (sizeof (*n),GFP_KERNEL ); +if (!n) +return -ENOMEM ; + + n->chain_index = tp->chain->index; + n->chain = tp->chain; + n->tp_prio = tp->prio; + n->tp = tp; + n->exts = exts; + n->handle = handle; + + err =xa_alloc_cyclic (&tcf_exts_miss_cookies_xa, &n->miss_cookie_base, + n, xa_limit_32b, &next,GFP_KERNEL ); +if (err) + goto err_xa_alloc; + + exts->miss_cookie_node = n; +return 0 ; + +err_xa_alloc: +kfree (n); +return err; +} + +static void tcf_exts_miss_cookie_base_destroy (struct tcf_exts *exts) +{ +struct tcf_exts_miss_cookie_node *n; + +if (!exts->miss_cookie_node) +return ; + + n = exts->miss_cookie_node; +xa_erase (&tcf_exts_miss_cookies_xa, n->miss_cookie_base); +kfree_rcu (n, rcu); +} + +static struct tcf_exts_miss_cookie_node * +tcf_exts_miss_cookie_lookup (u64 miss_cookie,int *act_index) +{ +union tcf_exts_miss_cookie mc = { .miss_cookie = miss_cookie, }; + + *act_index = mc.act_index; +return xa_load (&tcf_exts_miss_cookies_xa, mc.miss_cookie_base); +} +#else /* IS_ENABLED(CONFIG_NET_TC_SKB_EXT) */ +static int +tcf_exts_miss_cookie_base_alloc (struct tcf_exts *exts,struct tcf_proto *tp, +u32 handle) +{ +return 0 ; +} + +static void tcf_exts_miss_cookie_base_destroy (struct tcf_exts *exts) +{ +} +#endif /* IS_ENABLED(CONFIG_NET_TC_SKB_EXT) */ + +static u64 tcf_exts_miss_cookie_get (u32 miss_cookie_base,int act_index) +{ +union tcf_exts_miss_cookie mc = { .act_index = act_index, }; + +if (!miss_cookie_base) +return 0 ; + + mc.miss_cookie_base = miss_cookie_base; +return mc.miss_cookie; +} +#ifdef CONFIG_NET_CLS_ACT DEFINE_STATIC_KEY_FALSE (tc_skb_ext_tc);EXPORT_SYMBOL (tc_skb_ext_tc);@@ -1549,6 +1653,8 @@ static inline int __tcf_classify(struct sk_buff *skb,const struct tcf_proto *orig_tp, struct tcf_result *res, bool compat_mode, + struct tcf_exts_miss_cookie_node *n, + int act_index, u32 *last_executed_chain) { #ifdef CONFIG_NET_CLS_ACT@@ -1560,13 +1666,36 @@ static inline int __tcf_classify(struct sk_buff *skb,#endif for (; tp; tp =rcu_dereference_bh (tp->next)) {__be16 protocol =skb_protocol (skb, false); -int err; +int err =0 ; -if (tp->protocol != protocol && - tp->protocol !=htons (ETH_P_ALL )) -continue ; +if (n) { +struct tcf_exts *exts; + +if (n->tp_prio != tp->prio) +continue ; + +/* We re-lookup the tp and chain based on index instead +* of having hard refs and locks to them, so do a sanity +* check if any of tp,chain,exts was replaced by the +* time we got here with a cookie from hardware. +*/ +if (unlikely (n->tp != tp || n->tp->chain != n->chain || + !tp->ops->get_exts)) +return TC_ACT_SHOT ; + + exts = tp->ops->get_exts (tp, n->handle); +if (unlikely (!exts || n->exts != exts)) +return TC_ACT_SHOT ; - err =tc_classify (skb, tp, res); + n =NULL ; + err =tcf_exts_exec_ex (skb, exts, act_index, res); + }else { +if (tp->protocol != protocol && + tp->protocol !=htons (ETH_P_ALL )) +continue ; + + err =tc_classify (skb, tp, res); + }#ifdef CONFIG_NET_CLS_ACT if (unlikely (err ==TC_ACT_RECLASSIFY && !compat_mode)) { first_tp = orig_tp;@@ -1582,6 +1711,9 @@ static inline int __tcf_classify(struct sk_buff *skb,return err; } +if (unlikely (n)) +return TC_ACT_SHOT ; +return TC_ACT_UNSPEC ;/* signal: continue lookup */ #ifdef CONFIG_NET_CLS_ACT reset:@@ -1606,21 +1738,33 @@ int tcf_classify(struct sk_buff *skb,#if !IS_ENABLED (CONFIG_NET_TC_SKB_EXT )u32 last_executed_chain =0 ; -return __tcf_classify (skb, tp, tp, res, compat_mode, +return __tcf_classify (skb, tp, tp, res, compat_mode,NULL ,0 , &last_executed_chain);#else u32 last_executed_chain = tp ? tp->chain->index :0 ; +struct tcf_exts_miss_cookie_node *n =NULL ;const struct tcf_proto *orig_tp = tp;struct tc_skb_ext *ext;
net/sched/cls_api.c int tcf_classify(struct sk_buff *skb, · line 1756
Quoted 10 lines
net/sched/cls_api.c +3
-1+int act_index =0 ;int ret;if (block) { ext =skb_ext_find (skb,TC_SKB_EXT ); -if (ext && ext->chain) { +if (ext && (ext->chain || ext->act_miss)) {struct tcf_chain *fchain; +u32 chain = ext->chain;
IMHO it would be nice to avoid this assignment here, because there is nothing above saying that the union value can be read as a chain. For C, yes, it is okay. The worry is about ensuring that whatever is reading it, is reading what it is expecting it to be. Perhaps just declare it here, and then:
net/sched/cls_api.c int tcf_classify(struct sk_buff *skb, · line 1765
Quoted 10 lines
net/sched/cls_api.c +8
-1- fchain =tcf_chain_lookup_rcu (block, ext->chain); +if (ext->act_miss) { + n =tcf_exts_miss_cookie_lookup (ext->act_miss_cookie, + &act_index); +if (!n) +return TC_ACT_SHOT ; + + chain = n->chain_index; + }
else {
chain = ext->chain;
}Quoted 109 lines
net/sched/cls_api.c +53
-2+ + fchain =tcf_chain_lookup_rcu (block, chain);if (!fchain)return TC_ACT_SHOT ;@@ -1632,7 +1776,7 @@ int tcf_classify(struct sk_buff *skb, } } - ret =__tcf_classify (skb, tp, orig_tp, res, compat_mode, + ret =__tcf_classify (skb, tp, orig_tp, res, compat_mode, n, act_index, &last_executed_chain);if (tc_skb_ext_tc_enabled ()) {@@ -3056,9 +3200,48 @@ static int tc_dump_chain(struct sk_buff *skb, struct netlink_callback *cb)return skb->len; } +int tcf_exts_init_ex (struct tcf_exts *exts,struct net *net,int action, +int police,struct tcf_proto *tp,u32 handle, +bool use_action_miss) +{ +int err =0 ; + +#ifdef CONFIG_NET_CLS_ACT + exts->type =0 ; + exts->nr_actions =0 ; +/* Note: we do not own yet a reference on net. +* This reference might be taken later from tcf_exts_get_net(). +*/ + exts->net = net; + exts->actions =kcalloc (TCA_ACT_MAX_PRIO ,sizeof (struct tc_action *), +GFP_KERNEL ); +if (!exts->actions) +return -ENOMEM ; +#endif + + exts->action = action; + exts->police = police; + +if (!use_action_miss) +return 0 ; + + err =tcf_exts_miss_cookie_base_alloc (exts, tp, handle); +if (err) + goto err_miss_alloc; + +return 0 ; + +err_miss_alloc: +tcf_exts_destroy (exts); +return err; +} +EXPORT_SYMBOL (tcf_exts_init_ex); +void tcf_exts_destroy (struct tcf_exts *exts) {#ifdef CONFIG_NET_CLS_ACT +tcf_exts_miss_cookie_base_destroy (exts); +if (exts->actions) {tcf_action_destroy (exts->actions,TCA_ACT_UNBIND );kfree (exts->actions);@@ -3547,6 +3730,7 @@ static int tc_setup_offload_act(struct tc_action *act,int tc_setup_action (struct flow_action *flow_action,struct tc_action *actions[], +u32 miss_cookie_base,struct netlink_ext_ack *extack) {int i, j, k, index, err =0 ;@@ -3577,6 +3761,8 @@ int tc_setup_action(struct flow_action *flow_action,for (k =0 ; k < index ; k++) { entry[k].hw_stats =tc_act_hw_stats (act->hw_stats); entry[k].hw_index = act->tcfa_index; + entry[k].miss_cookie = +tcf_exts_miss_cookie_get (miss_cookie_base, i); } j += index;@@ -3599,10 +3785,15 @@ int tc_setup_offload_action(struct flow_action *flow_action, struct netlink_ext_ack *extack) {#ifdef CONFIG_NET_CLS_ACT +u32 miss_cookie_base; +if (!exts)return 0 ; -return tc_setup_action (flow_action, exts->actions, extack); + miss_cookie_base = exts->miss_cookie_node ? + exts->miss_cookie_node->miss_cookie_base :0 ; +return tc_setup_action (flow_action, exts->actions, miss_cookie_base, + extack);#else return 0 ;#endif @@ -3770,6 +3961,8 @@ static int __init tc_filter_init(void)if (err) goto err_register_pernet_subsys; +xa_init_flags (&tcf_exts_miss_cookies_xa,XA_FLAGS_ALLOC1 ); +rtnl_register (PF_UNSPEC ,RTM_NEWTFILTER , tc_new_tfilter,NULL ,RTNL_FLAG_DOIT_UNLOCKED ); rtnl_register(PF_UNSPEC, RTM_DELTFILTER, tc_del_tfilter, NULL,Signature · 1 line
2.30.1
Quoted 73 lines · Marcelo Ricardo Leitner
Quoted 55 lines · Paul Blakey
For drivers to support partial offload of a filter's action list, add support for action miss to specify an action instance to continue from in sw.
CT action in particular can't be fully offloaded, as new connections need to be handled in software. This imposes other limitations on the actions that can be offloaded together with the CT action, such as packet modifications.
Assign each action on a filter's action list a unique
miss_cookiewhich drivers can then use to fillaction_misspart of the tc skb extension. On getting back thismiss_cookie, find the action instance with relevant cookie and continue classifying from there.Signed-off-by Paul Blakey <[email protected]>Reviewed-by Jiri Pirko <[email protected]>Reviewed-by Simon Horman <[email protected]>Acked-by Jamal Hadi Salim <[email protected]>--- include/linux/skbuff.h | 6 +- include/net/flow_offload.h | 1 + include/net/pkt_cls.h | 34 +++--- include/net/sch_generic.h | 2 + net/openvswitch/flow.c | 3 +- net/sched/act_api.c | 2 +- net/sched/cls_api.c | 213 +++++++++++++++++++++++++++++++++++-- 7 files changed, 234 insertions(+), 27 deletions(-)include/linux/skbuff.h +5
-1@@ -311,12 +311,16 @@ struct nf_bridge_info {* and read by ovs to recirc_id. */ struct tc_skb_ext { -__u32 chain; +union { +u64 act_miss_cookie; +__u32 chain; + };__u16 mru;__u16 zone;u8 post_ct:1 ;u8 post_ct_snat:1 ;u8 post_ct_dnat:1 ; +u8 act_miss:1 ;/* Set if act_miss_cookie is used */ };#endif include/net/flow_offload.h +0
-0include/net/flow_offload.h void flow_action_cookie_destroy(struct flow_action_cookie *cookie); · line 231
Quoted 4 lines
include/net/flow_offload.h +1
-0@@ -228,6 +228,7 @@ void flow_action_cookie_destroy(struct flow_action_cookie *cookie);struct flow_action_entry {enum flow_action_id id;u32 hw_index; +u64 miss_cookie;The per-action stats patchset is adding a cookie for the actions as well, and exactly on this struct:
include/net/flow_offload.h +1
-0@@ -228,6 +228,7 @@ struct flow_action_cookie *flow_action_cookie_create(void *data,struct flow_action_entry {enum flow_action_id id;u32 hw_index; +unsigned long act_cookie;enum flow_action_hw_stats hw_stats;action_destr destructor;void *destructor_priv;
Quoted 3 lines
There, it is a simple value: the act pointer itself. Here, it is already more complex. Can them be merged into only one maybe?
If not, perhapsact_cookieshould be renamed tostats_cookiethen.
I don't think it can be shared, actions can be shared between multiple filters, while the miss cookie would be different for each used instance (takes the filter in to account).
So I'll rename it.
Quoted 158 lines
Quoted 158 lines
include/net/flow_offload.h +0
-0enum flow_action_hw_stats hw_stats;action_destr destructor;void *destructor_priv;include/net/pkt_cls.h +20
-14@@ -59,6 +59,8 @@ int tcf_block_get_ext(struct tcf_block **p_block, struct Qdisc *q,void tcf_block_put (struct tcf_block *block);void tcf_block_put_ext (struct tcf_block *block,struct Qdisc *q,struct tcf_block_ext_info *ei); +int tcf_exts_init_ex (struct tcf_exts *exts,struct net *net,int action, +int police,struct tcf_proto *tp,u32 handle,bool used_action_miss);static inline bool tcf_block_shared (struct tcf_block *block) {@@ -229,6 +231,7 @@ struct tcf_exts {struct tc_action **actions;struct net *net;netns_tracker ns_tracker; +struct tcf_exts_miss_cookie_node *miss_cookie_node;#endif /* Map to export classifier specific extension TLV types to the * generic extensions API. Unsupported extensions must be set to 0. @@ -240,21 +243,11 @@ struct tcf_exts {static inline int tcf_exts_init (struct tcf_exts *exts,struct net *net,int action,int police) { -#ifdef CONFIG_NET_CLS_ACT - exts->type =0 ; - exts->nr_actions =0 ; -/* Note: we do not own yet a reference on net. -* This reference might be taken later from tcf_exts_get_net(). -*/ - exts->net = net; - exts->actions =kcalloc (TCA_ACT_MAX_PRIO ,sizeof (struct tc_action *), -GFP_KERNEL ); -if (!exts->actions) -return -ENOMEM ; +#ifdef CONFIG_NET_CLS +return tcf_exts_init_ex (exts, net, action, police,NULL ,0 , false); +#else +return -EOPNOTSUPP ;#endif - exts->action = action; - exts->police = police; -return 0 ; }/* Return false if the netns is being destroyed in cleanup_net(). Callers @@ -353,6 +346,18 @@ tcf_exts_exec(struct sk_buff *skb, struct tcf_exts *exts,return TC_ACT_OK ; } +static inline int +tcf_exts_exec_ex (struct sk_buff *skb,struct tcf_exts *exts,int act_index, +struct tcf_result *res) +{ +#ifdef CONFIG_NET_CLS_ACT +return tcf_action_exec (skb, exts->actions + act_index, + exts->nr_actions - act_index, res); +#else +return TC_ACT_OK ; +#endif +} + int tcf_exts_validate(struct net *net, struct tcf_proto *tp, struct nlattr **tb, struct nlattr *rate_tlv, struct tcf_exts *exts, u32 flags,@@ -577,6 +582,7 @@ int tc_setup_offload_action(struct flow_action *flow_action,void tc_cleanup_offload_action (struct flow_action *flow_action);int tc_setup_action (struct flow_action *flow_action,struct tc_action *actions[], +u32 miss_cookie_base,struct netlink_ext_ack *extack); int tc_setup_cb_call(struct tcf_block *block, enum tc_setup_type type,include/net/sch_generic.h +2
-0@@ -369,6 +369,8 @@ struct tcf_proto_ops {struct nlattr **tca, struct netlink_ext_ack *extack);void (*tmplt_destroy)(void *tmplt_priv); +struct tcf_exts * (*get_exts)(const struct tcf_proto *tp, +u32 handle);/* rtnetlink specific */ int (*dump)(struct net*, struct tcf_proto*, void *,net/openvswitch/flow.c +2
-1@@ -1038,7 +1038,8 @@ int ovs_flow_key_extract(const struct ip_tunnel_info *tun_info,#if IS_ENABLED (CONFIG_NET_TC_SKB_EXT )if (tc_skb_ext_tc_enabled ()) { tc_ext =skb_ext_find (skb,TC_SKB_EXT ); - key->recirc_id = tc_ext ? tc_ext->chain :0 ; + key->recirc_id = tc_ext && !tc_ext->act_miss ? + tc_ext->chain :0 ;OVS_CB (skb)->mru = tc_ext ? tc_ext->mru :0 ; post_ct = tc_ext ? tc_ext->post_ct : false; post_ct_snat = post_ct ? tc_ext->post_ct_snat : false;net/sched/act_api.c +1
-1@@ -272,7 +272,7 @@ static int tcf_action_offload_add_ex(struct tc_action *action,if (err) goto fl_err; - err =tc_setup_action (&fl_action->action, actions, extack); + err =tc_setup_action (&fl_action->action, actions,0 , extack);if (err) {NL_SET_ERR_MSG_MOD (extack,"Failed to setup tc actions for offload" );net/sched/cls_api.c +25
-0@@ -22,6 +22,7 @@#include <linux/idr.h> #include <linux/jhash.h> #include <linux/rculist.h> +#include <linux/rhashtable.h> #include <net/net_namespace.h> #include <net/sock.h> #include <net/netlink.h> @@ -50,6 +51,109 @@ static LIST_HEAD(tcf_proto_base);/* Protects list of registered TC modules. It is pure SMP lock. */ static DEFINE_RWLOCK (cls_mod_lock); +static struct xarray tcf_exts_miss_cookies_xa; +struct tcf_exts_miss_cookie_node { +const struct tcf_chain *chain; +const struct tcf_proto *tp; +const struct tcf_exts *exts; +u32 chain_index; +u32 tp_prio; +u32 handle; +u32 miss_cookie_base; +struct rcu_head rcu; +}; + +/* Each tc action entry cookie will be comprised of 32bit miss_cookie_base + +* action index in the exts tc actions array. +*/ +union tcf_exts_miss_cookie { +struct { +u32 miss_cookie_base; +u32 act_index; + }; +u64 miss_cookie; +}; + +#if IS_ENABLED (CONFIG_NET_TC_SKB_EXT )
Quoted 8 lines
net/sched/cls_api.c static LIST_HEAD(tcf_proto_base); · line 83
Quoted 6 lines
net/sched/cls_api.c +6
-0+static int +tcf_exts_miss_cookie_base_alloc (struct tcf_exts *exts,struct tcf_proto *tp, +u32 handle) +{ +struct tcf_exts_miss_cookie_node *n; +static u32 next;What protects this static variable from concurrent access?
Nothing, but it acts as a suggestion for xa_alloc, so I don't think syncronzation is needed here.
Quoted 156 lines
Quoted 156 lines
net/sched/cls_api.c +109
-6+int err; + +if (WARN_ON (!handle || !tp->ops->get_exts)) +return -EINVAL ; + + n =kzalloc (sizeof (*n),GFP_KERNEL ); +if (!n) +return -ENOMEM ; + + n->chain_index = tp->chain->index; + n->chain = tp->chain; + n->tp_prio = tp->prio; + n->tp = tp; + n->exts = exts; + n->handle = handle; + + err =xa_alloc_cyclic (&tcf_exts_miss_cookies_xa, &n->miss_cookie_base, + n, xa_limit_32b, &next,GFP_KERNEL ); +if (err) + goto err_xa_alloc; + + exts->miss_cookie_node = n; +return 0 ; + +err_xa_alloc: +kfree (n); +return err; +} + +static void tcf_exts_miss_cookie_base_destroy (struct tcf_exts *exts) +{ +struct tcf_exts_miss_cookie_node *n; + +if (!exts->miss_cookie_node) +return ; + + n = exts->miss_cookie_node; +xa_erase (&tcf_exts_miss_cookies_xa, n->miss_cookie_base); +kfree_rcu (n, rcu); +} + +static struct tcf_exts_miss_cookie_node * +tcf_exts_miss_cookie_lookup (u64 miss_cookie,int *act_index) +{ +union tcf_exts_miss_cookie mc = { .miss_cookie = miss_cookie, }; + + *act_index = mc.act_index; +return xa_load (&tcf_exts_miss_cookies_xa, mc.miss_cookie_base); +} +#else /* IS_ENABLED(CONFIG_NET_TC_SKB_EXT) */ +static int +tcf_exts_miss_cookie_base_alloc (struct tcf_exts *exts,struct tcf_proto *tp, +u32 handle) +{ +return 0 ; +} + +static void tcf_exts_miss_cookie_base_destroy (struct tcf_exts *exts) +{ +} +#endif /* IS_ENABLED(CONFIG_NET_TC_SKB_EXT) */ + +static u64 tcf_exts_miss_cookie_get (u32 miss_cookie_base,int act_index) +{ +union tcf_exts_miss_cookie mc = { .act_index = act_index, }; + +if (!miss_cookie_base) +return 0 ; + + mc.miss_cookie_base = miss_cookie_base; +return mc.miss_cookie; +} +#ifdef CONFIG_NET_CLS_ACT DEFINE_STATIC_KEY_FALSE (tc_skb_ext_tc);EXPORT_SYMBOL (tc_skb_ext_tc);@@ -1549,6 +1653,8 @@ static inline int __tcf_classify(struct sk_buff *skb,const struct tcf_proto *orig_tp, struct tcf_result *res, bool compat_mode, + struct tcf_exts_miss_cookie_node *n, + int act_index, u32 *last_executed_chain) { #ifdef CONFIG_NET_CLS_ACT@@ -1560,13 +1666,36 @@ static inline int __tcf_classify(struct sk_buff *skb,#endif for (; tp; tp =rcu_dereference_bh (tp->next)) {__be16 protocol =skb_protocol (skb, false); -int err; +int err =0 ; -if (tp->protocol != protocol && - tp->protocol !=htons (ETH_P_ALL )) -continue ; +if (n) { +struct tcf_exts *exts; + +if (n->tp_prio != tp->prio) +continue ; + +/* We re-lookup the tp and chain based on index instead +* of having hard refs and locks to them, so do a sanity +* check if any of tp,chain,exts was replaced by the +* time we got here with a cookie from hardware. +*/ +if (unlikely (n->tp != tp || n->tp->chain != n->chain || + !tp->ops->get_exts)) +return TC_ACT_SHOT ; + + exts = tp->ops->get_exts (tp, n->handle); +if (unlikely (!exts || n->exts != exts)) +return TC_ACT_SHOT ; - err =tc_classify (skb, tp, res); + n =NULL ; + err =tcf_exts_exec_ex (skb, exts, act_index, res); + }else { +if (tp->protocol != protocol && + tp->protocol !=htons (ETH_P_ALL )) +continue ; + + err =tc_classify (skb, tp, res); + }#ifdef CONFIG_NET_CLS_ACT if (unlikely (err ==TC_ACT_RECLASSIFY && !compat_mode)) { first_tp = orig_tp;@@ -1582,6 +1711,9 @@ static inline int __tcf_classify(struct sk_buff *skb,return err; } +if (unlikely (n)) +return TC_ACT_SHOT ; +return TC_ACT_UNSPEC ;/* signal: continue lookup */ #ifdef CONFIG_NET_CLS_ACT reset:@@ -1606,21 +1738,33 @@ int tcf_classify(struct sk_buff *skb,#if !IS_ENABLED (CONFIG_NET_TC_SKB_EXT )u32 last_executed_chain =0 ; -return __tcf_classify (skb, tp, tp, res, compat_mode, +return __tcf_classify (skb, tp, tp, res, compat_mode,NULL ,0 , &last_executed_chain);#else u32 last_executed_chain = tp ? tp->chain->index :0 ; +struct tcf_exts_miss_cookie_node *n =NULL ;const struct tcf_proto *orig_tp = tp;struct tc_skb_ext *ext; +int act_index =0 ;int ret;if (block) { ext =skb_ext_find (skb,TC_SKB_EXT );
Quoted 10 lines
net/sched/cls_api.c int tcf_classify(struct sk_buff *skb, · line 1756
Quoted 4 lines
net/sched/cls_api.c +2
-1-if (ext && ext->chain) { +if (ext && (ext->chain || ext->act_miss)) {struct tcf_chain *fchain; +u32 chain = ext->chain;IMHO it would be nice to avoid this assignment here, because there is nothing above saying that the union value can be read as a chain. For C, yes, it is okay. The worry is about ensuring that whatever is reading it, is reading what it is expecting it to be. Perhaps just declare it here, and then:
Right, not nice, will fix.
Quoted 125 lines
net/sched/cls_api.c int tcf_classify(struct sk_buff *skb, · line 1765
Quoted 11 lines
net/sched/cls_api.c +8
-1- fchain =tcf_chain_lookup_rcu (block, ext->chain); +if (ext->act_miss) { + n =tcf_exts_miss_cookie_lookup (ext->act_miss_cookie, + &act_index); +if (!n) +return TC_ACT_SHOT ; + + chain = n->chain_index; + }else { chain = ext->chain; }Quoted 109 lines
net/sched/cls_api.c +53
-2+ + fchain =tcf_chain_lookup_rcu (block, chain);if (!fchain)return TC_ACT_SHOT ;@@ -1632,7 +1776,7 @@ int tcf_classify(struct sk_buff *skb, } } - ret =__tcf_classify (skb, tp, orig_tp, res, compat_mode, + ret =__tcf_classify (skb, tp, orig_tp, res, compat_mode, n, act_index, &last_executed_chain);if (tc_skb_ext_tc_enabled ()) {@@ -3056,9 +3200,48 @@ static int tc_dump_chain(struct sk_buff *skb, struct netlink_callback *cb)return skb->len; } +int tcf_exts_init_ex (struct tcf_exts *exts,struct net *net,int action, +int police,struct tcf_proto *tp,u32 handle, +bool use_action_miss) +{ +int err =0 ; + +#ifdef CONFIG_NET_CLS_ACT + exts->type =0 ; + exts->nr_actions =0 ; +/* Note: we do not own yet a reference on net. +* This reference might be taken later from tcf_exts_get_net(). +*/ + exts->net = net; + exts->actions =kcalloc (TCA_ACT_MAX_PRIO ,sizeof (struct tc_action *), +GFP_KERNEL ); +if (!exts->actions) +return -ENOMEM ; +#endif + + exts->action = action; + exts->police = police; + +if (!use_action_miss) +return 0 ; + + err =tcf_exts_miss_cookie_base_alloc (exts, tp, handle); +if (err) + goto err_miss_alloc; + +return 0 ; + +err_miss_alloc: +tcf_exts_destroy (exts); +return err; +} +EXPORT_SYMBOL (tcf_exts_init_ex); +void tcf_exts_destroy (struct tcf_exts *exts) {#ifdef CONFIG_NET_CLS_ACT +tcf_exts_miss_cookie_base_destroy (exts); +if (exts->actions) {tcf_action_destroy (exts->actions,TCA_ACT_UNBIND );kfree (exts->actions);@@ -3547,6 +3730,7 @@ static int tc_setup_offload_act(struct tc_action *act,int tc_setup_action (struct flow_action *flow_action,struct tc_action *actions[], +u32 miss_cookie_base,struct netlink_ext_ack *extack) {int i, j, k, index, err =0 ;@@ -3577,6 +3761,8 @@ int tc_setup_action(struct flow_action *flow_action,for (k =0 ; k < index ; k++) { entry[k].hw_stats =tc_act_hw_stats (act->hw_stats); entry[k].hw_index = act->tcfa_index; + entry[k].miss_cookie = +tcf_exts_miss_cookie_get (miss_cookie_base, i); } j += index;@@ -3599,10 +3785,15 @@ int tc_setup_offload_action(struct flow_action *flow_action, struct netlink_ext_ack *extack) {#ifdef CONFIG_NET_CLS_ACT +u32 miss_cookie_base; +if (!exts)return 0 ; -return tc_setup_action (flow_action, exts->actions, extack); + miss_cookie_base = exts->miss_cookie_node ? + exts->miss_cookie_node->miss_cookie_base :0 ; +return tc_setup_action (flow_action, exts->actions, miss_cookie_base, + extack);#else return 0 ;#endif @@ -3770,6 +3961,8 @@ static int __init tc_filter_init(void)if (err) goto err_register_pernet_subsys; +xa_init_flags (&tcf_exts_miss_cookies_xa,XA_FLAGS_ALLOC1 ); +rtnl_register (PF_UNSPEC ,RTM_NEWTFILTER , tc_new_tfilter,NULL ,RTNL_FLAG_DOIT_UNLOCKED ); rtnl_register(PF_UNSPEC, RTM_DELTFILTER, tc_del_tfilter, NULL,Signature · 1 line
2.30.1
Quoted 75 lines · Paul Blakey
Quoted 72 lines · Marcelo Ricardo Leitner
Quoted 54 lines · Paul Blakey
For drivers to support partial offload of a filter's action list, add support for action miss to specify an action instance to continue from in sw.
CT action in particular can't be fully offloaded, as new connections need to be handled in software. This imposes other limitations on the actions that can be offloaded together with the CT action, such as packet modifications.
Assign each action on a filter's action list a unique
miss_cookiewhich drivers can then use to fillaction_misspart of the tc skb extension. On getting back thismiss_cookie, find the action instance with relevant cookie and continue classifying from there.Signed-off-by Paul Blakey <[email protected]>Reviewed-by Jiri Pirko <[email protected]>Reviewed-by Simon Horman <[email protected]>Acked-by Jamal Hadi Salim <[email protected]>--- include/linux/skbuff.h | 6 +- include/net/flow_offload.h | 1 + include/net/pkt_cls.h | 34 +++--- include/net/sch_generic.h | 2 + net/openvswitch/flow.c | 3 +- net/sched/act_api.c | 2 +- net/sched/cls_api.c | 213 +++++++++++++++++++++++++++++++++++-- 7 files changed, 234 insertions(+), 27 deletions(-)include/linux/skbuff.h +5
-1@@ -311,12 +311,16 @@ struct nf_bridge_info {* and read by ovs to recirc_id. */ struct tc_skb_ext { -__u32 chain; +union { +u64 act_miss_cookie; +__u32 chain; + };__u16 mru;__u16 zone;u8 post_ct:1 ;u8 post_ct_snat:1 ;u8 post_ct_dnat:1 ; +u8 act_miss:1 ;/* Set if act_miss_cookie is used */ };#endif include/net/flow_offload.h +0
-0include/net/flow_offload.h void flow_action_cookie_destroy(struct flow_action_cookie *cookie); · line 231
Quoted 4 lines
include/net/flow_offload.h +1
-0@@ -228,6 +228,7 @@ void flow_action_cookie_destroy(struct flow_action_cookie *cookie);struct flow_action_entry {enum flow_action_id id;u32 hw_index; +u64 miss_cookie;The per-action stats patchset is adding a cookie for the actions as well, and exactly on this struct:
include/net/flow_offload.h +1
-0@@ -228,6 +228,7 @@ struct flow_action_cookie *flow_action_cookie_create(void *data,struct flow_action_entry {enum flow_action_id id;u32 hw_index; +unsigned long act_cookie;enum flow_action_hw_stats hw_stats;action_destr destructor;void *destructor_priv;
Quoted 7 lines
Quoted 3 lines
There, it is a simple value: the act pointer itself. Here, it is already more complex. Can them be merged into only one maybe?
If not, perhapsact_cookieshould be renamed tostats_cookiethen.I don't think it can be shared, actions can be shared between multiple filters, while the miss cookie would be different for each used instance (takes the filter in to account).
Good point. So it would at best be a masked value that part A works for the miss here and part B for the stats, which is pretty much what the two cookies are giving, just without having to do bit gymnasics, yes.
Quoted 447 lines
So I'll rename it.
Quoted 151 lines
Quoted 151 lines
include/net/flow_offload.h +0
-0enum flow_action_hw_stats hw_stats;action_destr destructor;void *destructor_priv;include/net/pkt_cls.h +20
-14@@ -59,6 +59,8 @@ int tcf_block_get_ext(struct tcf_block **p_block, struct Qdisc *q,void tcf_block_put (struct tcf_block *block);void tcf_block_put_ext (struct tcf_block *block,struct Qdisc *q,struct tcf_block_ext_info *ei); +int tcf_exts_init_ex (struct tcf_exts *exts,struct net *net,int action, +int police,struct tcf_proto *tp,u32 handle,bool used_action_miss);static inline bool tcf_block_shared (struct tcf_block *block) {@@ -229,6 +231,7 @@ struct tcf_exts {struct tc_action **actions;struct net *net;netns_tracker ns_tracker; +struct tcf_exts_miss_cookie_node *miss_cookie_node;#endif /* Map to export classifier specific extension TLV types to the * generic extensions API. Unsupported extensions must be set to 0. @@ -240,21 +243,11 @@ struct tcf_exts {static inline int tcf_exts_init (struct tcf_exts *exts,struct net *net,int action,int police) { -#ifdef CONFIG_NET_CLS_ACT - exts->type =0 ; - exts->nr_actions =0 ; -/* Note: we do not own yet a reference on net. -* This reference might be taken later from tcf_exts_get_net(). -*/ - exts->net = net; - exts->actions =kcalloc (TCA_ACT_MAX_PRIO ,sizeof (struct tc_action *), -GFP_KERNEL ); -if (!exts->actions) -return -ENOMEM ; +#ifdef CONFIG_NET_CLS +return tcf_exts_init_ex (exts, net, action, police,NULL ,0 , false); +#else +return -EOPNOTSUPP ;#endif - exts->action = action; - exts->police = police; -return 0 ; }/* Return false if the netns is being destroyed in cleanup_net(). Callers @@ -353,6 +346,18 @@ tcf_exts_exec(struct sk_buff *skb, struct tcf_exts *exts,return TC_ACT_OK ; } +static inline int +tcf_exts_exec_ex (struct sk_buff *skb,struct tcf_exts *exts,int act_index, +struct tcf_result *res) +{ +#ifdef CONFIG_NET_CLS_ACT +return tcf_action_exec (skb, exts->actions + act_index, + exts->nr_actions - act_index, res); +#else +return TC_ACT_OK ; +#endif +} + int tcf_exts_validate(struct net *net, struct tcf_proto *tp, struct nlattr **tb, struct nlattr *rate_tlv, struct tcf_exts *exts, u32 flags,@@ -577,6 +582,7 @@ int tc_setup_offload_action(struct flow_action *flow_action,void tc_cleanup_offload_action (struct flow_action *flow_action);int tc_setup_action (struct flow_action *flow_action,struct tc_action *actions[], +u32 miss_cookie_base,struct netlink_ext_ack *extack); int tc_setup_cb_call(struct tcf_block *block, enum tc_setup_type type,include/net/sch_generic.h +2
-0@@ -369,6 +369,8 @@ struct tcf_proto_ops {struct nlattr **tca, struct netlink_ext_ack *extack);void (*tmplt_destroy)(void *tmplt_priv); +struct tcf_exts * (*get_exts)(const struct tcf_proto *tp, +u32 handle);/* rtnetlink specific */ int (*dump)(struct net*, struct tcf_proto*, void *,net/openvswitch/flow.c +2
-1@@ -1038,7 +1038,8 @@ int ovs_flow_key_extract(const struct ip_tunnel_info *tun_info,#if IS_ENABLED (CONFIG_NET_TC_SKB_EXT )if (tc_skb_ext_tc_enabled ()) { tc_ext =skb_ext_find (skb,TC_SKB_EXT ); - key->recirc_id = tc_ext ? tc_ext->chain :0 ; + key->recirc_id = tc_ext && !tc_ext->act_miss ? + tc_ext->chain :0 ;OVS_CB (skb)->mru = tc_ext ? tc_ext->mru :0 ; post_ct = tc_ext ? tc_ext->post_ct : false; post_ct_snat = post_ct ? tc_ext->post_ct_snat : false;net/sched/act_api.c +1
-1@@ -272,7 +272,7 @@ static int tcf_action_offload_add_ex(struct tc_action *action,if (err) goto fl_err; - err =tc_setup_action (&fl_action->action, actions, extack); + err =tc_setup_action (&fl_action->action, actions,0 , extack);if (err) {NL_SET_ERR_MSG_MOD (extack,"Failed to setup tc actions for offload" );net/sched/cls_api.c +25
-0@@ -22,6 +22,7 @@#include <linux/idr.h> #include <linux/jhash.h> #include <linux/rculist.h> +#include <linux/rhashtable.h> #include <net/net_namespace.h> #include <net/sock.h> #include <net/netlink.h> @@ -50,6 +51,109 @@ static LIST_HEAD(tcf_proto_base);/* Protects list of registered TC modules. It is pure SMP lock. */ static DEFINE_RWLOCK (cls_mod_lock); +static struct xarray tcf_exts_miss_cookies_xa; +struct tcf_exts_miss_cookie_node { +const struct tcf_chain *chain; +const struct tcf_proto *tp; +const struct tcf_exts *exts; +u32 chain_index; +u32 tp_prio; +u32 handle; +u32 miss_cookie_base; +struct rcu_head rcu; +}; + +/* Each tc action entry cookie will be comprised of 32bit miss_cookie_base + +* action index in the exts tc actions array. +*/ +union tcf_exts_miss_cookie { +struct { +u32 miss_cookie_base; +u32 act_index; + }; +u64 miss_cookie; +}; + +#if IS_ENABLED (CONFIG_NET_TC_SKB_EXT )Quoted 8 lines
net/sched/cls_api.c static LIST_HEAD(tcf_proto_base); · line 83
Quoted 6 lines
net/sched/cls_api.c +6
-0+static int +tcf_exts_miss_cookie_base_alloc (struct tcf_exts *exts,struct tcf_proto *tp, +u32 handle) +{ +struct tcf_exts_miss_cookie_node *n; +static u32 next;What protects this static variable from concurrent access?
Nothing, but it acts as a suggestion for
xa_alloc, so I don't think syncronzation is needed here.Quoted 152 lines
Quoted 152 lines
net/sched/cls_api.c +110
-7+int err; + +if (WARN_ON (!handle || !tp->ops->get_exts)) +return -EINVAL ; + + n =kzalloc (sizeof (*n),GFP_KERNEL ); +if (!n) +return -ENOMEM ; + + n->chain_index = tp->chain->index; + n->chain = tp->chain; + n->tp_prio = tp->prio; + n->tp = tp; + n->exts = exts; + n->handle = handle; + + err =xa_alloc_cyclic (&tcf_exts_miss_cookies_xa, &n->miss_cookie_base, + n, xa_limit_32b, &next,GFP_KERNEL ); +if (err) + goto err_xa_alloc; + + exts->miss_cookie_node = n; +return 0 ; + +err_xa_alloc: +kfree (n); +return err; +} + +static void tcf_exts_miss_cookie_base_destroy (struct tcf_exts *exts) +{ +struct tcf_exts_miss_cookie_node *n; + +if (!exts->miss_cookie_node) +return ; + + n = exts->miss_cookie_node; +xa_erase (&tcf_exts_miss_cookies_xa, n->miss_cookie_base); +kfree_rcu (n, rcu); +} + +static struct tcf_exts_miss_cookie_node * +tcf_exts_miss_cookie_lookup (u64 miss_cookie,int *act_index) +{ +union tcf_exts_miss_cookie mc = { .miss_cookie = miss_cookie, }; + + *act_index = mc.act_index; +return xa_load (&tcf_exts_miss_cookies_xa, mc.miss_cookie_base); +} +#else /* IS_ENABLED(CONFIG_NET_TC_SKB_EXT) */ +static int +tcf_exts_miss_cookie_base_alloc (struct tcf_exts *exts,struct tcf_proto *tp, +u32 handle) +{ +return 0 ; +} + +static void tcf_exts_miss_cookie_base_destroy (struct tcf_exts *exts) +{ +} +#endif /* IS_ENABLED(CONFIG_NET_TC_SKB_EXT) */ + +static u64 tcf_exts_miss_cookie_get (u32 miss_cookie_base,int act_index) +{ +union tcf_exts_miss_cookie mc = { .act_index = act_index, }; + +if (!miss_cookie_base) +return 0 ; + + mc.miss_cookie_base = miss_cookie_base; +return mc.miss_cookie; +} +#ifdef CONFIG_NET_CLS_ACT DEFINE_STATIC_KEY_FALSE (tc_skb_ext_tc);EXPORT_SYMBOL (tc_skb_ext_tc);@@ -1549,6 +1653,8 @@ static inline int __tcf_classify(struct sk_buff *skb,const struct tcf_proto *orig_tp, struct tcf_result *res, bool compat_mode, + struct tcf_exts_miss_cookie_node *n, + int act_index, u32 *last_executed_chain) { #ifdef CONFIG_NET_CLS_ACT@@ -1560,13 +1666,36 @@ static inline int __tcf_classify(struct sk_buff *skb,#endif for (; tp; tp =rcu_dereference_bh (tp->next)) {__be16 protocol =skb_protocol (skb, false); -int err; +int err =0 ; -if (tp->protocol != protocol && - tp->protocol !=htons (ETH_P_ALL )) -continue ; +if (n) { +struct tcf_exts *exts; + +if (n->tp_prio != tp->prio) +continue ; + +/* We re-lookup the tp and chain based on index instead +* of having hard refs and locks to them, so do a sanity +* check if any of tp,chain,exts was replaced by the +* time we got here with a cookie from hardware. +*/ +if (unlikely (n->tp != tp || n->tp->chain != n->chain || + !tp->ops->get_exts)) +return TC_ACT_SHOT ; + + exts = tp->ops->get_exts (tp, n->handle); +if (unlikely (!exts || n->exts != exts)) +return TC_ACT_SHOT ; - err =tc_classify (skb, tp, res); + n =NULL ; + err =tcf_exts_exec_ex (skb, exts, act_index, res); + }else { +if (tp->protocol != protocol && + tp->protocol !=htons (ETH_P_ALL )) +continue ; + + err =tc_classify (skb, tp, res); + }#ifdef CONFIG_NET_CLS_ACT if (unlikely (err ==TC_ACT_RECLASSIFY && !compat_mode)) { first_tp = orig_tp;@@ -1582,6 +1711,9 @@ static inline int __tcf_classify(struct sk_buff *skb,return err; } +if (unlikely (n)) +return TC_ACT_SHOT ; +return TC_ACT_UNSPEC ;/* signal: continue lookup */ #ifdef CONFIG_NET_CLS_ACT reset:@@ -1606,21 +1738,33 @@ int tcf_classify(struct sk_buff *skb,#if !IS_ENABLED (CONFIG_NET_TC_SKB_EXT )u32 last_executed_chain =0 ; -return __tcf_classify (skb, tp, tp, res, compat_mode, +return __tcf_classify (skb, tp, tp, res, compat_mode,NULL ,0 , &last_executed_chain);#else u32 last_executed_chain = tp ? tp->chain->index :0 ; +struct tcf_exts_miss_cookie_node *n =NULL ;const struct tcf_proto *orig_tp = tp;struct tc_skb_ext *ext; +int act_index =0 ;int ret;if (block) { ext =skb_ext_find (skb,TC_SKB_EXT ); -if (ext && ext->chain) { +if (ext && (ext->chain || ext->act_miss)) {Quoted 8 lines
net/sched/cls_api.c int tcf_classify(struct sk_buff *skb, · line 1756
Quoted 2 lines
net/sched/cls_api.c +1
-0struct tcf_chain *fchain; +u32 chain = ext->chain;IMHO it would be nice to avoid this assignment here, because there is nothing above saying that the union value can be read as a chain. For C, yes, it is okay. The worry is about ensuring that whatever is reading it, is reading what it is expecting it to be. Perhaps just declare it here, and then:
Right, not nice, will fix.
Quoted 116 lines
net/sched/cls_api.c int tcf_classify(struct sk_buff *skb, · line 1765
Quoted 10 lines
net/sched/cls_api.c +8
-1- fchain =tcf_chain_lookup_rcu (block, ext->chain); +if (ext->act_miss) { + n =tcf_exts_miss_cookie_lookup (ext->act_miss_cookie, + &act_index); +if (!n) +return TC_ACT_SHOT ; + + chain = n->chain_index; + }else { chain = ext->chain; }Quoted 101 lines
net/sched/cls_api.c +53
-2+ + fchain =tcf_chain_lookup_rcu (block, chain);if (!fchain)return TC_ACT_SHOT ;@@ -1632,7 +1776,7 @@ int tcf_classify(struct sk_buff *skb, } } - ret =__tcf_classify (skb, tp, orig_tp, res, compat_mode, + ret =__tcf_classify (skb, tp, orig_tp, res, compat_mode, n, act_index, &last_executed_chain);if (tc_skb_ext_tc_enabled ()) {@@ -3056,9 +3200,48 @@ static int tc_dump_chain(struct sk_buff *skb, struct netlink_callback *cb)return skb->len; } +int tcf_exts_init_ex (struct tcf_exts *exts,struct net *net,int action, +int police,struct tcf_proto *tp,u32 handle, +bool use_action_miss) +{ +int err =0 ; + +#ifdef CONFIG_NET_CLS_ACT + exts->type =0 ; + exts->nr_actions =0 ; +/* Note: we do not own yet a reference on net. +* This reference might be taken later from tcf_exts_get_net(). +*/ + exts->net = net; + exts->actions =kcalloc (TCA_ACT_MAX_PRIO ,sizeof (struct tc_action *), +GFP_KERNEL ); +if (!exts->actions) +return -ENOMEM ; +#endif + + exts->action = action; + exts->police = police; + +if (!use_action_miss) +return 0 ; + + err =tcf_exts_miss_cookie_base_alloc (exts, tp, handle); +if (err) + goto err_miss_alloc; + +return 0 ; + +err_miss_alloc: +tcf_exts_destroy (exts); +return err; +} +EXPORT_SYMBOL (tcf_exts_init_ex); +void tcf_exts_destroy (struct tcf_exts *exts) {#ifdef CONFIG_NET_CLS_ACT +tcf_exts_miss_cookie_base_destroy (exts); +if (exts->actions) {tcf_action_destroy (exts->actions,TCA_ACT_UNBIND );kfree (exts->actions);@@ -3547,6 +3730,7 @@ static int tc_setup_offload_act(struct tc_action *act,int tc_setup_action (struct flow_action *flow_action,struct tc_action *actions[], +u32 miss_cookie_base,struct netlink_ext_ack *extack) {int i, j, k, index, err =0 ;@@ -3577,6 +3761,8 @@ int tc_setup_action(struct flow_action *flow_action,for (k =0 ; k < index ; k++) { entry[k].hw_stats =tc_act_hw_stats (act->hw_stats); entry[k].hw_index = act->tcfa_index; + entry[k].miss_cookie = +tcf_exts_miss_cookie_get (miss_cookie_base, i); } j += index;@@ -3599,10 +3785,15 @@ int tc_setup_offload_action(struct flow_action *flow_action, struct netlink_ext_ack *extack) {#ifdef CONFIG_NET_CLS_ACT +u32 miss_cookie_base; +if (!exts)return 0 ; -return tc_setup_action (flow_action, exts->actions, extack); + miss_cookie_base = exts->miss_cookie_node ? + exts->miss_cookie_node->miss_cookie_base :0 ; +return tc_setup_action (flow_action, exts->actions, miss_cookie_base, + extack);#else return 0 ;#endif @@ -3770,6 +3961,8 @@ static int __init tc_filter_init(void)if (err) goto err_register_pernet_subsys; +xa_init_flags (&tcf_exts_miss_cookies_xa,XA_FLAGS_ALLOC1 ); +rtnl_register (PF_UNSPEC ,RTM_NEWTFILTER , tc_new_tfilter,NULL ,RTNL_FLAG_DOIT_UNLOCKED ); rtnl_register(PF_UNSPEC, RTM_DELTFILTER, tc_del_tfilter, NULL,Signature · 1 line
2.30.1
Quoted 80 lines · Marcelo Ricardo Leitner
Quoted 73 lines · Paul Blakey
Quoted 71 lines · Marcelo Ricardo Leitner
Quoted 54 lines · Paul Blakey
For drivers to support partial offload of a filter's action list, add support for action miss to specify an action instance to continue from in sw.
CT action in particular can't be fully offloaded, as new connections need to be handled in software. This imposes other limitations on the actions that can be offloaded together with the CT action, such as packet modifications.
Assign each action on a filter's action list a unique
miss_cookiewhich drivers can then use to fillaction_misspart of the tc skb extension. On getting back thismiss_cookie, find the action instance with relevant cookie and continue classifying from there.Signed-off-by Paul Blakey <[email protected]>Reviewed-by Jiri Pirko <[email protected]>Reviewed-by Simon Horman <[email protected]>Acked-by Jamal Hadi Salim <[email protected]>--- include/linux/skbuff.h | 6 +- include/net/flow_offload.h | 1 + include/net/pkt_cls.h | 34 +++--- include/net/sch_generic.h | 2 + net/openvswitch/flow.c | 3 +- net/sched/act_api.c | 2 +- net/sched/cls_api.c | 213 +++++++++++++++++++++++++++++++++++-- 7 files changed, 234 insertions(+), 27 deletions(-)include/linux/skbuff.h +5
-1@@ -311,12 +311,16 @@ struct nf_bridge_info {* and read by ovs to recirc_id. */ struct tc_skb_ext { -__u32 chain; +union { +u64 act_miss_cookie; +__u32 chain; + };__u16 mru;__u16 zone;u8 post_ct:1 ;u8 post_ct_snat:1 ;u8 post_ct_dnat:1 ; +u8 act_miss:1 ;/* Set if act_miss_cookie is used */ };#endif include/net/flow_offload.h +0
-0include/net/flow_offload.h void flow_action_cookie_destroy(struct flow_action_cookie *cookie); · line 231
Quoted 4 lines
include/net/flow_offload.h +1
-0@@ -228,6 +228,7 @@ void flow_action_cookie_destroy(struct flow_action_cookie *cookie);struct flow_action_entry {enum flow_action_id id;u32 hw_index; +u64 miss_cookie;The per-action stats patchset is adding a cookie for the actions as well, and exactly on this struct:
include/net/flow_offload.h +1
-0@@ -228,6 +228,7 @@ struct flow_action_cookie *flow_action_cookie_create(void *data,struct flow_action_entry {enum flow_action_id id;u32 hw_index; +unsigned long act_cookie;enum flow_action_hw_stats hw_stats;action_destr destructor;void *destructor_priv;Quoted 6 lines
Quoted 3 lines
There, it is a simple value: the act pointer itself. Here, it is already more complex. Can them be merged into only one maybe?
If not, perhapsact_cookieshould be renamed tostats_cookiethen.I don't think it can be shared, actions can be shared between multiple filters, while the miss cookie would be different for each used instance (takes the filter in to account).
Quoted 4 lines
Good point. So it would at best be a masked value that part A works for the miss here and part B for the stats, which is pretty much what the two cookies are giving, just without having to do bit gymnasics, yes.
act cookie is using 64 bits (to store the pointer and void a mapping), and I'm using at least
32bits, so there is not simple type that will contain both.
So I'll rename the act_cookie to stats_cookie once I rebase.
Quoted 84 lines · Paul Blakey
Quoted 79 lines · Marcelo Ricardo Leitner
Quoted 72 lines · Paul Blakey
Quoted 71 lines · Marcelo Ricardo Leitner
Quoted 54 lines · Paul Blakey
For drivers to support partial offload of a filter's action list, add support for action miss to specify an action instance to continue from in sw.
CT action in particular can't be fully offloaded, as new connections need to be handled in software. This imposes other limitations on the actions that can be offloaded together with the CT action, such as packet modifications.
Assign each action on a filter's action list a unique
miss_cookiewhich drivers can then use to fillaction_misspart of the tc skb extension. On getting back thismiss_cookie, find the action instance with relevant cookie and continue classifying from there.Signed-off-by Paul Blakey <[email protected]>Reviewed-by Jiri Pirko <[email protected]>Reviewed-by Simon Horman <[email protected]>Acked-by Jamal Hadi Salim <[email protected]>--- include/linux/skbuff.h | 6 +- include/net/flow_offload.h | 1 + include/net/pkt_cls.h | 34 +++--- include/net/sch_generic.h | 2 + net/openvswitch/flow.c | 3 +- net/sched/act_api.c | 2 +- net/sched/cls_api.c | 213 +++++++++++++++++++++++++++++++++++-- 7 files changed, 234 insertions(+), 27 deletions(-)include/linux/skbuff.h +5
-1@@ -311,12 +311,16 @@ struct nf_bridge_info {* and read by ovs to recirc_id. */ struct tc_skb_ext { -__u32 chain; +union { +u64 act_miss_cookie; +__u32 chain; + };__u16 mru;__u16 zone;u8 post_ct:1 ;u8 post_ct_snat:1 ;u8 post_ct_dnat:1 ; +u8 act_miss:1 ;/* Set if act_miss_cookie is used */ };#endif include/net/flow_offload.h +0
-0include/net/flow_offload.h void flow_action_cookie_destroy(struct flow_action_cookie *cookie); · line 231
Quoted 4 lines
include/net/flow_offload.h +1
-0@@ -228,6 +228,7 @@ void flow_action_cookie_destroy(struct flow_action_cookie *cookie);struct flow_action_entry {enum flow_action_id id;u32 hw_index; +u64 miss_cookie;The per-action stats patchset is adding a cookie for the actions as well, and exactly on this struct:
include/net/flow_offload.h +1
-0@@ -228,6 +228,7 @@ struct flow_action_cookie *flow_action_cookie_create(void *data,struct flow_action_entry {enum flow_action_id id;u32 hw_index; +unsigned long act_cookie;enum flow_action_hw_stats hw_stats;action_destr destructor;void *destructor_priv;Quoted 6 lines
Quoted 3 lines
There, it is a simple value: the act pointer itself. Here, it is already more complex. Can them be merged into only one maybe?
If not, perhapsact_cookieshould be renamed tostats_cookiethen.I don't think it can be shared, actions can be shared between multiple filters, while the miss cookie would be different for each used instance (takes the filter in to account).
Quoted 4 lines
Good point. So it would at best be a masked value that part A works for the miss here and part B for the stats, which is pretty much what the two cookies are giving, just without having to do bit gymnasics, yes.
Quoted 6 lines
act cookie is using 64 bits (to store the pointer and void a mapping), and I'm using at least
32bits, so there is not simple type that will contain both.
So I'll rename the
act_cookietostats_cookieonce I rebase.
The current act_cookie uniquely identifies the action instance.
I think it might be used in other use cases and not just for stats.
Actually, I think the current naming scheme of act_cookie and miss_cookie makes sense.
Quoted 86 lines · Oz Shlomo
Quoted 84 lines · Paul Blakey
Quoted 83 lines · Marcelo Ricardo Leitner
Quoted 72 lines · Paul Blakey
Quoted 71 lines · Marcelo Ricardo Leitner
Quoted 54 lines · Paul Blakey
For drivers to support partial offload of a filter's action list, add support for action miss to specify an action instance to continue from in sw.
CT action in particular can't be fully offloaded, as new connections need to be handled in software. This imposes other limitations on the actions that can be offloaded together with the CT action, such as packet modifications.
Assign each action on a filter's action list a unique
miss_cookiewhich drivers can then use to fillaction_misspart of the tc skb extension. On getting back thismiss_cookie, find the action instance with relevant cookie and continue classifying from there.Signed-off-by Paul Blakey <[email protected]>Reviewed-by Jiri Pirko <[email protected]>Reviewed-by Simon Horman <[email protected]>Acked-by Jamal Hadi Salim <[email protected]>--- include/linux/skbuff.h | 6 +- include/net/flow_offload.h | 1 + include/net/pkt_cls.h | 34 +++--- include/net/sch_generic.h | 2 + net/openvswitch/flow.c | 3 +- net/sched/act_api.c | 2 +- net/sched/cls_api.c | 213 +++++++++++++++++++++++++++++++++++-- 7 files changed, 234 insertions(+), 27 deletions(-)include/linux/skbuff.h +5
-1@@ -311,12 +311,16 @@ struct nf_bridge_info {* and read by ovs to recirc_id. */ struct tc_skb_ext { -__u32 chain; +union { +u64 act_miss_cookie; +__u32 chain; + };__u16 mru;__u16 zone;u8 post_ct:1 ;u8 post_ct_snat:1 ;u8 post_ct_dnat:1 ; +u8 act_miss:1 ;/* Set if act_miss_cookie is used */ };#endif include/net/flow_offload.h +0
-0include/net/flow_offload.h void flow_action_cookie_destroy(struct flow_action_cookie *cookie); · line 231
Quoted 4 lines
include/net/flow_offload.h +1
-0@@ -228,6 +228,7 @@ void flow_action_cookie_destroy(struct flow_action_cookie *cookie);struct flow_action_entry {enum flow_action_id id;u32 hw_index; +u64 miss_cookie;The per-action stats patchset is adding a cookie for the actions as well, and exactly on this struct:
include/net/flow_offload.h +1
-0@@ -228,6 +228,7 @@ struct flow_action_cookie *flow_action_cookie_create(void *data,struct flow_action_entry {enum flow_action_id id;u32 hw_index; +unsigned long act_cookie;enum flow_action_hw_stats hw_stats;action_destr destructor;void *destructor_priv;Quoted 6 lines
Quoted 3 lines
There, it is a simple value: the act pointer itself. Here, it is already more complex. Can them be merged into only one maybe?
If not, perhapsact_cookieshould be renamed tostats_cookiethen.I don't think it can be shared, actions can be shared between multiple filters, while the miss cookie would be different for each used instance (takes the filter in to account).
Good point. So it would at best be a masked value that part A works for the miss here and part B for the stats, which is pretty much what the two cookies are giving, just without having to do bit gymnasics, yes.
Quoted 8 lines
Quoted 6 lines
act cookie is using 64 bits (to store the pointer and void a mapping), and I'm using at least
32bits, so there is not simple type that will contain both.
So I'll rename the
act_cookietostats_cookieonce I rebase.The current
act_cookieuniquely identifies the action instance.
While miss_cookie also uniquely identifies the action, within a filter list. Or, miss_cookie uniquely identifies an action configuration.
Quoted 1 line
I think it might be used in other use cases and not just for stats.
I don't disagree.
Quoted 3 lines
Actually, I think the current naming scheme of
act_cookieandmiss_cookiemakes sense.
act_cookie is actually already used (and differently) in tc_action itself here:1045ba77a596 ("net sched actions: Add support for user cookies")
With this, IMO it is tough to know which one takes precedence where.
Then perhaps,act_cookie here -> instance_cookiemiss_cookie -> config_cookie
Sorry for the bikeshedding, btw, but these cookies are getting confusing. We need them to taste nice :-}
Quoted 10 lines · Marcelo Ricardo Leitner
Quoted 2 lines · Oz Shlomo
Actually, I think the current naming scheme of
act_cookieandmiss_cookiemakes sense.Then perhaps,
act_cookiehere ->instance_cookiemiss_cookie->config_cookieSorry for the bikeshedding, btw, but these cookies are getting confusing. We need them to taste nice :-}
I'm with Oz, keep the current name for act_cookie.
(In my ideal world, it'd just be called cookie, and the existing
cookie in struct flow_action_entry would be renamed user_cookie. Because act_cookie is the same thing conceptually as flow_cls_offload.cookie. Though I wonder if that means it belongs in struct flow_offload_action instead?)
-ed
Quoted 14 lines · Edward Cree
Quoted 10 lines · Marcelo Ricardo Leitner
Quoted 2 lines · Oz Shlomo
Actually, I think the current naming scheme of
act_cookieandmiss_cookiemakes sense.Then perhaps,
act_cookiehere ->instance_cookiemiss_cookie->config_cookieSorry for the bikeshedding, btw, but these cookies are getting confusing. We need them to taste nice :-}
I'm with Oz, keep the current name for
act_cookie.
Quoted 7 lines
(In my ideal world, it'd just be called cookie, and the existing
cookie in structflow_action_entrywould be renameduser_cookie. Becauseact_cookieis the same thing conceptually as flow_cls_offload.cookie. Though I wonder if that means it belongs in structflow_offload_actioninstead?)-ed
Ok so I want to add this patch to the series:
From 326938812758dbd2591b221452708504911ca419 Mon Sep 17 00:00:00 2001
From: Paul Blakey <[email protected]>
Date: Wed, 15 Feb 2023 10:57:40 +0200
Subject: [PATCH] net: sched: Rename user cookie and act cookie
struct tc_action->act_cookie is a user defined cookie, and the related struct flow_action_entry->act_cookie is used as an handle similar to struct flow_cls_offload->cookie.
Rename tc_action->act_cookie to user_cookie, and flow_action_entry->act_cookie to cookie so their names would better fit their usage.
Issue: 3226890
---
drivers/net/ethernet/mellanox/mlx5/core/en_tc.c +1 -1
@@ -4180,7 +4180,7 @@ parse_state->actions |= attr->action;if (!tc_act->stats_action) - attr->tc_act_cookies[attr->tc_act_cookies_count++] = act->act_cookie; + attr->tc_act_cookies[attr->tc_act_cookies_count++] = act->cookie;/* Split attr for multi table act if not the last act. */ if (jump_state.jump_target ||
include/net/act_api.h +1 -1
@@ -39,7 +39,7 @@struct gnet_stats_basic_sync __percpu *cpu_bstats;struct gnet_stats_basic_sync __percpu *cpu_bstats_hw;struct gnet_stats_queue __percpu *cpu_qstats; -struct tc_cookie __rcu *act_cookie; +struct tc_cookie __rcu *user_cookie;struct tcf_chain __rcu *goto_chain;u32 tcfa_flags;u8 hw_stats;
include/net/flow_offload.h +2 -2
@@ -228,7 +228,7 @@struct flow_action_entry {enum flow_action_id id;u32 hw_index; -unsigned long act_cookie; +unsigned long cookie;enum flow_action_hw_stats hw_stats;action_destr destructor;void *destructor_priv;
@@ -321,7 +321,7 @@u16 sid; } pppoe; }; -struct flow_action_cookie *cookie;/* user defined action cookie */ +struct flow_action_cookie *user_cookie;/* user defined action cookie */ };struct flow_action {
net/sched/act_api.c +13 -13
@@ -125,7 +125,7 @@free_percpu (p->cpu_bstats_hw);free_percpu (p->cpu_qstats); -tcf_set_action_cookie (&p->act_cookie,NULL ); +tcf_set_action_cookie (&p->user_cookie,NULL );if (chain)tcf_chain_put_by_act (chain);
@@ -431,14 +431,14 @@static size_t tcf_action_shared_attrs_size (const struct tc_action *act) { -struct tc_cookie *act_cookie; +struct tc_cookie *user_cookie;u32 cookie_len =0 ;rcu_read_lock (); - act_cookie =rcu_dereference (act->act_cookie); + user_cookie =rcu_dereference (act->user_cookie); -if (act_cookie) - cookie_len =nla_total_size (act_cookie->len); +if (user_cookie) + cookie_len =nla_total_size (user_cookie->len);rcu_read_unlock ();return nla_total_size (0 )/* action number nested */
@@ -488,7 +488,7 @@ goto nla_put_failure;rcu_read_lock (); - cookie =rcu_dereference (a->act_cookie); + cookie =rcu_dereference (a->user_cookie);if (cookie) {if (nla_put (skb,TCA_ACT_COOKIE , cookie->len, cookie->data)) {rcu_read_unlock ();
@@ -1362,9 +1362,9 @@ {bool police = flags &TCA_ACT_FLAGS_POLICE ;struct nla_bitfield32 userflags = {0 ,0 }; +struct tc_cookie *user_cookie =NULL ;u8 hw_stats =TCA_ACT_HW_STATS_ANY ;struct nlattr *tb[TCA_ACT_MAX +1 ]; -struct tc_cookie *cookie =NULL ;struct tc_action *a;int err;
@@ -1375,8 +1375,8 @@if (err <0 )return ERR_PTR (err);if (tb[TCA_ACT_COOKIE ]) { - cookie =nla_memdup_cookie (tb); -if (!cookie) { + user_cookie =nla_memdup_cookie (tb); +if (!user_cookie) {NL_SET_ERR_MSG (extack,"No memory to generate TC cookie" ); err = -ENOMEM ; goto err_out;
@@ -1402,7 +1402,7 @@ *init_res = err;if (!police && tb[TCA_ACT_COOKIE ]) -tcf_set_action_cookie (&a->act_cookie, cookie); +tcf_set_action_cookie (&a->user_cookie, user_cookie);if (!police) a->hw_stats = hw_stats;
@@ -1410,9 +1410,9 @@return a; err_out: -if (cookie) { -kfree (cookie->data); -kfree (cookie); +if (user_cookie) { +kfree (user_cookie->data); +kfree (user_cookie); }return ERR_PTR (err); }
net/sched/cls_api.c +14 -14
@@ -3490,28 +3490,28 @@ }EXPORT_SYMBOL (tc_setup_cb_reoffload); -static int tcf_act_get_cookie (struct flow_action_entry *entry, -const struct tc_action *act) +static int tcf_act_get_user_cookie (struct flow_action_entry *entry, +const struct tc_action *act) { -struct tc_cookie *cookie; +struct tc_cookie *user_cookie;int err =0 ;rcu_read_lock (); - cookie =rcu_dereference (act->act_cookie); -if (cookie) { - entry->cookie =flow_action_cookie_create (cookie->data, - cookie->len, -GFP_ATOMIC ); -if (!entry->cookie) + user_cookie =rcu_dereference (act->user_cookie); +if (user_cookie) { + entry->user_cookie =flow_action_cookie_create (user_cookie->data, + user_cookie->len, +GFP_ATOMIC ); +if (!entry->user_cookie) err = -ENOMEM ; }rcu_read_unlock ();return err; } -static void tcf_act_put_cookie (struct flow_action_entry *entry) +static void tcf_act_put_user_cookie (struct flow_action_entry *entry) { -flow_action_cookie_destroy (entry->cookie); +flow_action_cookie_destroy (entry->user_cookie); }void tc_cleanup_offload_action (struct flow_action *flow_action)
@@ -3520,7 +3520,7 @@int i;flow_action_for_each (i, entry, flow_action) { -tcf_act_put_cookie (entry); +tcf_act_put_user_cookie (entry);if (entry->destructor) entry->destructor (entry->destructor_priv); }
@@ -3565,7 +3565,7 @@ entry = &flow_action->entries[j];spin_lock_bh (&act->tcfa_lock); - err =tcf_act_get_cookie (entry, act); + err =tcf_act_get_user_cookie (entry, act);if (err) goto err_out_locked;
@@ -3577,7 +3577,7 @@for (k =0 ; k < index ; k++) { entry[k].hw_stats =tc_act_hw_stats (act->hw_stats); entry[k].hw_index = act->tcfa_index; - entry[k].act_cookie = (unsigned long )act; + entry[k].cookie = (unsigned long )act; } j += index;
Quoted 36 lines · Paul Blakey
Quoted 14 lines · Edward Cree
Quoted 10 lines · Marcelo Ricardo Leitner
Quoted 2 lines · Oz Shlomo
Actually, I think the current naming scheme of
act_cookieandmiss_cookiemakes sense.Then perhaps,
act_cookiehere ->instance_cookiemiss_cookie->config_cookieSorry for the bikeshedding, btw, but these cookies are getting confusing. We need them to taste nice :-}
I'm with Oz, keep the current name for
act_cookie.Quoted 7 lines
(In my ideal world, it'd just be called cookie, and the existing
cookie in structflow_action_entrywould be renameduser_cookie. Becauseact_cookieis the same thing conceptually as flow_cls_offload.cookie. Though I wonder if that means it belongs in structflow_offload_actioninstead?)-ed
Ok so I want to add this patch to the series:
From
326938812758dbd2591b221452708504911ca419Mon Sep 17 00:00:00 2001
From: Paul Blakey <[email protected]>
Date: Wed, 15 Feb 2023 10:57:40 +0200
Subject: [PATCH] net: sched: Rename user cookie and act cookie
Quoted 7 lines
struct
tc_action->act_cookieis a user defined cookie, and the related structflow_action_entry->act_cookieis used as an handle similar to structflow_cls_offload->cookie.Rename
tc_action->act_cookietouser_cookie, andflow_action_entry->act_cookieto cookie so their names would better fit their usage.
Makes sense. This helps a lot already.
(I didn't review the patch carefully yet, but it seems good) Thanks!
PATCH v9 2/7 net/sched: flower: Move filter handle initialization earlier
In reply to Paul BlakeyTo support miss to action during hardware offload the filter's handle is needed when setting up the actions (tcf_exts_init()), and before offloading.
Move filter handle initialization earlier.
--- net/sched/cls_flower.c | 62 ++++++++++++++++++++++++------------------ 1 file changed, 35 insertions(+), 27 deletions(-)
net/sched/cls_flower.c +35 -27
@@ -2192,10 +2192,6 @@ static int fl_change(struct net *net, struct sk_buff *in_skb,INIT_LIST_HEAD (&fnew->hw_list);refcount_set (&fnew->refcnt,1 ); - err =tcf_exts_init (&fnew->exts, net,TCA_FLOWER_ACT ,0 ); -if (err <0 ) - goto errout; -if (tb[TCA_FLOWER_FLAGS ]) { fnew->flags =nla_get_u32 (tb[TCA_FLOWER_FLAGS ]);
@@ -2205,15 +2201,45 @@ static int fl_change(struct net *net, struct sk_buff *in_skb, } } +if (!fold) { +spin_lock (&tp->lock); +if (!handle) { + handle =1 ; + err =idr_alloc_u32 (&head->handle_idr, fnew, &handle, +INT_MAX ,GFP_ATOMIC ); + }else { + err =idr_alloc_u32 (&head->handle_idr, fnew, &handle, + handle,GFP_ATOMIC ); + +/* Filter with specified handle was concurrently +* inserted after initial check in cls_api. This is not +* necessarily an error if NLM_F_EXCL is not set in +* message flags. Returning EAGAIN will cause cls_api to +* try to update concurrently inserted rule. +*/ +if (err == -ENOSPC ) + err = -EAGAIN ; + } +spin_unlock (&tp->lock); + +if (err) + goto errout; + } + fnew->handle = handle; + + err =tcf_exts_init (&fnew->exts, net,TCA_FLOWER_ACT ,0 ); +if (err <0 ) + goto errout_idr; + err =fl_set_parms (net, tp, fnew, mask, base, tb, tca[TCA_RATE ], tp->chain->tmplt_priv, flags, fnew->flags, extack);if (err) - goto errout; + goto errout_idr; err =fl_check_assign_mask (head, fnew, fold, mask);if (err) - goto errout; + goto errout_idr; err =fl_ht_insert_unique (fnew, fold, &in_ht);if (err)
@@ -2279,29 +2305,9 @@ static int fl_change(struct net *net, struct sk_buff *in_skb,refcount_dec (&fold->refcnt);__fl_put (fold); }else { -if (handle) { -/* user specifies a handle and it doesn't exist */ - err =idr_alloc_u32 (&head->handle_idr, fnew, &handle, - handle,GFP_ATOMIC ); - -/* Filter with specified handle was concurrently -* inserted after initial check in cls_api. This is not -* necessarily an error if NLM_F_EXCL is not set in -* message flags. Returning EAGAIN will cause cls_api to -* try to update concurrently inserted rule. -*/ -if (err == -ENOSPC ) - err = -EAGAIN ; - }else { - handle =1 ; - err =idr_alloc_u32 (&head->handle_idr, fnew, &handle, -INT_MAX ,GFP_ATOMIC ); - } -if (err) - goto errout_hw; +idr_replace (&head->handle_idr, fnew, fnew->handle);refcount_inc (&fnew->refcnt); - fnew->handle = handle;list_add_tail_rcu (&fnew->list, &fnew->mask->filters);spin_unlock (&tp->lock); }
@@ -2324,6 +2330,8 @@ static int fl_change(struct net *net, struct sk_buff *in_skb, fnew->mask->filter_ht_params); errout_mask:fl_mask_put (head, fnew->mask); +errout_idr: +idr_remove (&head->handle_idr, fnew->handle); errout:__fl_put (fnew); errout_tb:
Signature · 1 line
2.30.1
PATCH v9 3/7 net/sched: flower: Support hardware miss to tc action
In reply to Paul BlakeyTo support hardware miss to tc action in actions on the flower classifier, implement the required getting of filter actions, and setup filter exts (actions) miss by giving it the filter's handle and actions.
--- net/sched/cls_flower.c | 13 ++++++++++++- 1 file changed, 12 insertions(+), 1 deletion(-)
net/sched/cls_flower.c +12 -1
@@ -534,6 +534,15 @@ static struct cls_fl_filter *__fl_get(struct cls_fl_head *head, u32 handle)return f; } +static struct tcf_exts *fl_get_exts (const struct tcf_proto *tp,u32 handle) +{ +struct cls_fl_head *head =rcu_dereference_bh (tp->root); +struct cls_fl_filter *f; + + f =idr_find (&head->handle_idr, handle); +return f ? &f->exts :NULL ; +} +static int __fl_delete (struct tcf_proto *tp,struct cls_fl_filter *f,bool *last,bool rtnl_held,struct netlink_ext_ack *extack)
@@ -2227,7 +2236,8 @@ static int fl_change(struct net *net, struct sk_buff *in_skb, } fnew->handle = handle; - err =tcf_exts_init (&fnew->exts, net,TCA_FLOWER_ACT ,0 ); + err =tcf_exts_init_ex (&fnew->exts, net,TCA_FLOWER_ACT ,0 , tp, handle, + !tc_skip_hw (fnew->flags));if (err <0 ) goto errout_idr;
@@ -3449,6 +3459,7 @@ static struct tcf_proto_ops cls_fl_ops __read_mostly = { .tmplt_create = fl_tmplt_create, .tmplt_destroy = fl_tmplt_destroy, .tmplt_dump = fl_tmplt_dump, + .get_exts = fl_get_exts, .owner = THIS_MODULE, .flags = TCF_PROTO_OPS_DOIT_UNLOCKED, };
Signature · 1 line
2.30.1
PATCH v9 4/7 net/mlx5: Kconfig: Make tc offload depend on tc skb extension
In reply to Paul BlakeyTc skb extension is a basic requirement for using tc offload to support correct restoration on action miss.
Depend on it.
--- drivers/net/ethernet/mellanox/mlx5/core/Kconfig | 4 ++-- drivers/net/ethernet/mellanox/mlx5/core/en/rep/tc.c | 2 -- drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c | 7 ------- drivers/net/ethernet/mellanox/mlx5/core/en_tc.c | 2 -- drivers/net/ethernet/mellanox/mlx5/core/en_tc.h | 2 -- 5 files changed, 2 insertions(+), 15 deletions(-)
drivers/net/ethernet/mellanox/mlx5/core/Kconfig +2 -2
@@ -85,7 +85,7 @@ config MLX5_BRIDGE config MLX5_CLS_ACT bool "MLX5 TC classifier action support" - depends on MLX5_ESWITCH && NET_CLS_ACT + depends on MLX5_ESWITCH && NET_CLS_ACT && NET_TC_SKB_EXT default y help mlx5 ConnectX offloads support for TC classifier action (NET_CLS_ACT),
@@ -100,7 +100,7 @@ config MLX5_CLS_ACT config MLX5_TC_CT bool "MLX5 TC connection tracking offload support" - depends on MLX5_CLS_ACT && NF_FLOW_TABLE && NET_ACT_CT && NET_TC_SKB_EXT + depends on MLX5_CLS_ACT && NF_FLOW_TABLE && NET_ACT_CT default y help Say Y here if you want to support offloading connection tracking rules
drivers/net/ethernet/mellanox/mlx5/core/en/rep/tc.c +0 -2
@@ -762,7 +762,6 @@ static bool mlx5e_restore_skb_chain(struct sk_buff *skb, u32 chain, u32 reg_c1,struct mlx5e_priv *priv =netdev_priv (skb->dev);u32 tunnel_id = (reg_c1 >>ESW_TUN_OFFSET ) &TUNNEL_ID_MASK ; -#if IS_ENABLED (CONFIG_NET_TC_SKB_EXT )if (chain) {struct mlx5_rep_uplink_priv *uplink_priv;struct mlx5e_rep_priv *uplink_rpriv;
@@ -784,7 +783,6 @@ static bool mlx5e_restore_skb_chain(struct sk_buff *skb, u32 chain, u32 reg_c1, zone_restore_id))return false; } -#endif /* CONFIG_NET_TC_SKB_EXT */ return mlx5e_restore_tunnel (priv, skb, tc_priv, tunnel_id); }
drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c +0 -7
@@ -2078,13 +2078,6 @@ mlx5_tc_ct_init_check_support(struct mlx5e_priv *priv,const char *err_msg =NULL ;int err =0 ; -#if !IS_ENABLED (CONFIG_NET_TC_SKB_EXT ) -/* cannot restore chain ID on HW miss */ - - err_msg ="tc skb extension missing" ; - err = -EOPNOTSUPP ; - goto out_err; -#endif if (IS_ERR_OR_NULL (post_act)) {/* Ignore_flow_level support isn't supported by default for VFs and so post_act * won't be supported. Skip showing error msg.
drivers/net/ethernet/mellanox/mlx5/core/en_tc.c +0 -2
@@ -5565,7 +5565,6 @@ int mlx5e_setup_tc_block_cb(enum tc_setup_type type, void *type_data,bool mlx5e_tc_update_skb (struct mlx5_cqe64 *cqe,struct sk_buff *skb) { -#if IS_ENABLED (CONFIG_NET_TC_SKB_EXT )u32 chain =0 , chain_tag, reg_b, zone_restore_id;struct mlx5e_priv *priv =netdev_priv (skb->dev);struct mlx5_mapped_obj mapped_obj;
@@ -5603,7 +5602,6 @@ bool mlx5e_tc_update_skb(struct mlx5_cqe64 *cqe,netdev_dbg (priv->netdev,"Invalid mapped object type: %d\n" , mapped_obj.type);return false; } -#endif /* CONFIG_NET_TC_SKB_EXT */ return true; }
drivers/net/ethernet/mellanox/mlx5/core/en_tc.h +0 -2
@@ -370,7 +370,6 @@ struct mlx5e_tc_table *mlx5e_tc_table_alloc(void);void mlx5e_tc_table_free (struct mlx5e_tc_table *tc);static inline bool mlx5e_cqe_regb_chain (struct mlx5_cqe64 *cqe) { -#if IS_ENABLED (CONFIG_NET_TC_SKB_EXT )u32 chain, reg_b; reg_b =be32_to_cpu (cqe->ft_metadata);
@@ -381,7 +380,6 @@ static inline bool mlx5e_cqe_regb_chain(struct mlx5_cqe64 *cqe) chain = reg_b &MLX5E_TC_TABLE_CHAIN_TAG_MASK ;if (chain)return true; -#endif return false; }
Signature · 1 line
2.30.1
Re: [PATCH net-next v9 4/7] net/mlx5: Kconfig: Make tc offload depend on tc skb extension
Quoted 2 lines · Paul Blakey
Tc skb extension is a basic requirement for using tc offload to support correct restoration on action miss.
Btw, this is great. There was at least 1 report on ovn upstream because the person didn't know skb extensions had to be manually enabled.
PATCH v9 5/7 net/mlx5: Refactor tc miss handling to a single function
In reply to Paul BlakeyMove tc miss handling code to en_tc.c, and remove
duplicate code.
--- .../ethernet/mellanox/mlx5/core/en/rep/tc.c | 223 ++---------------- .../net/ethernet/mellanox/mlx5/core/en_rx.c | 4 +- .../net/ethernet/mellanox/mlx5/core/en_tc.c | 220 +++++++++++++++-- .../net/ethernet/mellanox/mlx5/core/en_tc.h | 11 +- 4 files changed, 231 insertions(+), 227 deletions(-)
drivers/net/ethernet/mellanox/mlx5/core/en/rep/tc.c +23 -200
@@ -1,7 +1,6 @@// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB /* Copyright (c) 2020 Mellanox Technologies. */ -#include <net/dst_metadata.h> #include <linux/netdevice.h> #include <linux/if_macvlan.h> #include <linux/list.h>
@@ -665,230 +664,54 @@ void mlx5e_rep_tc_netdevice_event_unregister(struct mlx5e_rep_priv *rpriv) mlx5e_rep_indr_block_unbind); } -static bool mlx5e_restore_tunnel (struct mlx5e_priv *priv,struct sk_buff *skb, -struct mlx5e_tc_update_priv *tc_priv, -u32 tunnel_id) -{ -struct mlx5_eswitch *esw = priv->mdev->priv.eswitch; -struct tunnel_match_enc_opts enc_opts = {}; -struct mlx5_rep_uplink_priv *uplink_priv; -struct mlx5e_rep_priv *uplink_rpriv; -struct metadata_dst *tun_dst; -struct tunnel_match_key key; -u32 tun_id, enc_opts_id; -struct net_device *dev; -int err; - - enc_opts_id = tunnel_id &ENC_OPTS_BITS_MASK ; - tun_id = tunnel_id >>ENC_OPTS_BITS ; - -if (!tun_id) -return true; - - uplink_rpriv =mlx5_eswitch_get_uplink_priv (esw,REP_ETH ); - uplink_priv = &uplink_rpriv->uplink_priv; - - err =mapping_find (uplink_priv->tunnel_mapping, tun_id, &key); -if (err) { -netdev_dbg (priv->netdev, -"Couldn't find tunnel for tun_id: %d, err: %d\n" , - tun_id, err); -return false; - } - -if (enc_opts_id) { - err =mapping_find (uplink_priv->tunnel_enc_opts_mapping, - enc_opts_id, &enc_opts); -if (err) { -netdev_dbg (priv->netdev, -"Couldn't find tunnel (opts) for tun_id: %d, err: %d\n" , - enc_opts_id, err); -return false; - } - } - -if (key.enc_control.addr_type ==FLOW_DISSECTOR_KEY_IPV4_ADDRS ) { - tun_dst =__ip_tun_set_dst (key.enc_ipv4.src, key.enc_ipv4.dst, - key.enc_ip.tos, key.enc_ip.ttl, - key.enc_tp.dst,TUNNEL_KEY , -key32_to_tunnel_id (key.enc_key_id.keyid), - enc_opts.key.len); - }else if (key.enc_control.addr_type ==FLOW_DISSECTOR_KEY_IPV6_ADDRS ) { - tun_dst =__ipv6_tun_set_dst (&key.enc_ipv6.src, &key.enc_ipv6.dst, - key.enc_ip.tos, key.enc_ip.ttl, - key.enc_tp.dst,0 ,TUNNEL_KEY , -key32_to_tunnel_id (key.enc_key_id.keyid), - enc_opts.key.len); - }else { -netdev_dbg (priv->netdev, -"Couldn't restore tunnel, unsupported addr_type: %d\n" , - key.enc_control.addr_type); -return false; - } - -if (!tun_dst) { -netdev_dbg (priv->netdev,"Couldn't restore tunnel, no tun_dst\n" ); -return false; - } - - tun_dst->u.tun_info.key.tp_src = key.enc_tp.src; - -if (enc_opts.key.len) -ip_tunnel_info_opts_set (&tun_dst->u.tun_info, - enc_opts.key.data, - enc_opts.key.len, - enc_opts.key.dst_opt_type); - -skb_dst_set (skb, (struct dst_entry *)tun_dst); - dev =dev_get_by_index (&init_net, key.filter_ifindex); -if (!dev) { -netdev_dbg (priv->netdev, -"Couldn't find tunnel device with ifindex: %d\n" , - key.filter_ifindex); -return false; - } - -/* Set fwd_dev so we do dev_put() after datapath */ - tc_priv->fwd_dev = dev; - - skb->dev = dev; - -return true; -} - -static bool mlx5e_restore_skb_chain (struct sk_buff *skb,u32 chain,u32 reg_c1, -struct mlx5e_tc_update_priv *tc_priv) -{ -struct mlx5e_priv *priv =netdev_priv (skb->dev); -u32 tunnel_id = (reg_c1 >>ESW_TUN_OFFSET ) &TUNNEL_ID_MASK ; - -if (chain) { -struct mlx5_rep_uplink_priv *uplink_priv; -struct mlx5e_rep_priv *uplink_rpriv; -struct tc_skb_ext *tc_skb_ext; -struct mlx5_eswitch *esw; -u32 zone_restore_id; - - tc_skb_ext =tc_skb_ext_alloc (skb); -if (!tc_skb_ext) { -WARN_ON (1 ); -return false; - } - tc_skb_ext->chain = chain; - zone_restore_id = reg_c1 &ESW_ZONE_ID_MASK ; - esw = priv->mdev->priv.eswitch; - uplink_rpriv =mlx5_eswitch_get_uplink_priv (esw,REP_ETH ); - uplink_priv = &uplink_rpriv->uplink_priv; -if (!mlx5e_tc_ct_restore_flow (uplink_priv->ct_priv, skb, - zone_restore_id)) -return false; - } - -return mlx5e_restore_tunnel (priv, skb, tc_priv, tunnel_id); -} - -static void mlx5_rep_tc_post_napi_receive (struct mlx5e_tc_update_priv *tc_priv) -{ -if (tc_priv->fwd_dev) -dev_put (tc_priv->fwd_dev); -} - -static void mlx5e_restore_skb_sample (struct mlx5e_priv *priv,struct sk_buff *skb, -struct mlx5_mapped_obj *mapped_obj, -struct mlx5e_tc_update_priv *tc_priv) -{ -if (!mlx5e_restore_tunnel (priv, skb, tc_priv, mapped_obj->sample.tunnel_id)) { -netdev_dbg (priv->netdev, -"Failed to restore tunnel info for sampled packet\n" ); -return ; - } -mlx5e_tc_sample_skb (skb, mapped_obj); -mlx5_rep_tc_post_napi_receive (tc_priv); -} - -static bool mlx5e_restore_skb_int_port (struct mlx5e_priv *priv,struct sk_buff *skb, -struct mlx5_mapped_obj *mapped_obj, -struct mlx5e_tc_update_priv *tc_priv, -bool *forward_tx, -u32 reg_c1) -{ -u32 tunnel_id = (reg_c1 >>ESW_TUN_OFFSET ) &TUNNEL_ID_MASK ; -struct mlx5_eswitch *esw = priv->mdev->priv.eswitch; -struct mlx5_rep_uplink_priv *uplink_priv; -struct mlx5e_rep_priv *uplink_rpriv; - -/* Tunnel restore takes precedence over int port restore */ -if (tunnel_id) -return mlx5e_restore_tunnel (priv, skb, tc_priv, tunnel_id); - - uplink_rpriv =mlx5_eswitch_get_uplink_priv (esw,REP_ETH ); - uplink_priv = &uplink_rpriv->uplink_priv; - -if (mlx5e_tc_int_port_dev_fwd (uplink_priv->int_port_priv, skb, - mapped_obj->int_port_metadata, forward_tx)) { -/* Set fwd_dev for future dev_put */ - tc_priv->fwd_dev = skb->dev; - -return true; - } - -return false; -} -void mlx5e_rep_tc_receive (struct mlx5_cqe64 *cqe,struct mlx5e_rq *rq,struct sk_buff *skb) { -u32 reg_c1 =be32_to_cpu (cqe->ft_metadata); +u32 reg_c0, reg_c1, zone_restore_id, tunnel_id;struct mlx5e_tc_update_priv tc_priv = {}; -struct mlx5_mapped_obj mapped_obj; +struct mlx5_rep_uplink_priv *uplink_priv; +struct mlx5e_rep_priv *uplink_rpriv; +struct mlx5_tc_ct_priv *ct_priv; +struct mapping_ctx *mapping_ctx;struct mlx5_eswitch *esw; -bool forward_tx = false;struct mlx5e_priv *priv; -u32 reg_c0; -int err; reg_c0 = (be32_to_cpu (cqe->sop_drop_qpn) &MLX5E_TC_FLOW_ID_MASK );if (!reg_c0 || reg_c0 ==MLX5_FS_DEFAULT_FLOW_TAG ) goto forward; -/* If reg_c0 is not equal to the default flow tag then skb->mark +/* If mapped_obj_id is not equal to the default flow tag then skb->mark * is not supported and must be reset back to 0. */ skb->mark =0 ; priv =netdev_priv (skb->dev); esw = priv->mdev->priv.eswitch; - err =mapping_find (esw->offloads.reg_c0_obj_pool, reg_c0, &mapped_obj); -if (err) { -netdev_dbg (priv->netdev, -"Couldn't find mapped object for reg_c0: %d, err: %d\n" , - reg_c0, err); - goto free_skb; - } + mapping_ctx = esw->offloads.reg_c0_obj_pool; + reg_c1 =be32_to_cpu (cqe->ft_metadata); + zone_restore_id = reg_c1 &ESW_ZONE_ID_MASK ; + tunnel_id = (reg_c1 >>ESW_TUN_OFFSET ) &TUNNEL_ID_MASK ; -if (mapped_obj.type ==MLX5_MAPPED_OBJ_CHAIN ) { -if (!mlx5e_restore_skb_chain (skb, mapped_obj.chain, reg_c1, &tc_priv) && - !mlx5_ipsec_is_rx_flow (cqe)) - goto free_skb; - }else if (mapped_obj.type ==MLX5_MAPPED_OBJ_SAMPLE ) { -mlx5e_restore_skb_sample (priv, skb, &mapped_obj, &tc_priv); - goto free_skb; - }else if (mapped_obj.type ==MLX5_MAPPED_OBJ_INT_PORT_METADATA ) { -if (!mlx5e_restore_skb_int_port (priv, skb, &mapped_obj, &tc_priv, - &forward_tx, reg_c1)) - goto free_skb; - }else { -netdev_dbg (priv->netdev,"Invalid mapped object type: %d\n" , mapped_obj.type); + uplink_rpriv =mlx5_eswitch_get_uplink_priv (esw,REP_ETH ); + uplink_priv = &uplink_rpriv->uplink_priv; + ct_priv = uplink_priv->ct_priv; + +if (!mlx5_ipsec_is_rx_flow (cqe) && + !mlx5e_tc_update_skb (cqe, skb, mapping_ctx, reg_c0, ct_priv, zone_restore_id, tunnel_id, + &tc_priv)) goto free_skb; - } forward: -if (forward_tx) +if (tc_priv.skb_done) + goto free_skb; + +if (tc_priv.forward_tx)dev_queue_xmit (skb);else napi_gro_receive (rq->cq.napi, skb); -mlx5_rep_tc_post_napi_receive (&tc_priv); +if (tc_priv.fwd_dev) +dev_put (tc_priv.fwd_dev);return ;
drivers/net/ethernet/mellanox/mlx5/core/en_rx.c +2 -2
@@ -1792,7 +1792,7 @@ static void mlx5e_handle_rx_cqe(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe)mlx5e_complete_rx_cqe (rq, cqe, cqe_bcnt, skb);if (mlx5e_cqe_regb_chain (cqe)) -if (!mlx5e_tc_update_skb (cqe, skb)) { +if (!mlx5e_tc_update_skb_nic (cqe, skb)) {dev_kfree_skb_any (skb); goto free_wqe; }
@@ -2259,7 +2259,7 @@ static void mlx5e_handle_rx_cqe_mpwrq(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqmlx5e_complete_rx_cqe (rq, cqe, cqe_bcnt, skb);if (mlx5e_cqe_regb_chain (cqe)) -if (!mlx5e_tc_update_skb (cqe, skb)) { +if (!mlx5e_tc_update_skb_nic (cqe, skb)) {dev_kfree_skb_any (skb); goto mpwrq_cqe_out; }
drivers/net/ethernet/mellanox/mlx5/core/en_tc.c +197 -23
249 lines not on this page · raw message
drivers/net/ethernet/mellanox/mlx5/core/en_tc.h +9 -2
@@ -59,6 +59,8 @@ int mlx5e_tc_num_filters(struct mlx5e_priv *priv, unsigned long flags);struct mlx5e_tc_update_priv {struct net_device *fwd_dev; +bool skb_done; +bool forward_tx; };struct mlx5_nic_flow_attr {
@@ -384,14 +386,19 @@ static inline bool mlx5e_cqe_regb_chain(struct mlx5_cqe64 *cqe) return false; } -bool mlx5e_tc_update_skb (struct mlx5_cqe64 *cqe,struct sk_buff *skb); +bool mlx5e_tc_update_skb_nic (struct mlx5_cqe64 *cqe,struct sk_buff *skb); +bool mlx5e_tc_update_skb (struct mlx5_cqe64 *cqe,struct sk_buff *skb, +struct mapping_ctx *mapping_ctx,u32 mapped_obj_id, +struct mlx5_tc_ct_priv *ct_priv, +u32 zone_restore_id,u32 tunnel_id, +struct mlx5e_tc_update_priv *tc_priv);#else /* CONFIG_MLX5_CLS_ACT */ static inline struct mlx5e_tc_table *mlx5e_tc_table_alloc (void ) {return NULL ; }static inline void mlx5e_tc_table_free (struct mlx5e_tc_table *tc) {}static inline bool mlx5e_cqe_regb_chain (struct mlx5_cqe64 *cqe) {return false; }static inline bool -mlx5e_tc_update_skb (struct mlx5_cqe64 *cqe,struct sk_buff *skb) +mlx5e_tc_update_skb_nic (struct mlx5_cqe64 *cqe,struct sk_buff *skb) {return true; }#endif
Signature · 1 line
2.30.1
PATCH v9 6/7 net/mlx5e: Rename CHAIN_TO_REG to MAPPED_OBJ_TO_REG
In reply to Paul BlakeyThis reg usage is always a mapped object, not necessarily containing chain info.
Rename to properly convey what it stores. This patch doesn't change any functionality.
--- .../net/ethernet/mellanox/mlx5/core/en/tc/sample.c | 2 +- drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c | 2 +- drivers/net/ethernet/mellanox/mlx5/core/en_tc.c | 6 +++--- drivers/net/ethernet/mellanox/mlx5/core/en_tc.h | 4 ++-- .../ethernet/mellanox/mlx5/core/lib/fs_chains.c | 14 +++++++------- 5 files changed, 14 insertions(+), 14 deletions(-)
drivers/net/ethernet/mellanox/mlx5/core/en/tc/sample.c +1 -1
@@ -237,7 +237,7 @@ sample_modify_hdr_get(struct mlx5_core_dev *mdev, u32 obj_id,int err; err =mlx5e_tc_match_to_reg_set (mdev, mod_acts,MLX5_FLOW_NAMESPACE_FDB , -CHAIN_TO_REG , obj_id); +MAPPED_OBJ_TO_REG , obj_id);if (err) goto err_set_regc0;
drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c +1 -1
@@ -1875,7 +1875,7 @@ __mlx5_tc_ct_flow_offload(struct mlx5_tc_ct_priv *ct_priv, ct_flow->chain_mapping = chain_mapping; err =mlx5e_tc_match_to_reg_set (priv->mdev, pre_mod_acts, ct_priv->ns_type, -CHAIN_TO_REG , chain_mapping); +MAPPED_OBJ_TO_REG , chain_mapping);if (err) {ct_dbg ("Failed to set chain register mapping" ); goto err_mapping;
drivers/net/ethernet/mellanox/mlx5/core/en_tc.c +3 -3
@@ -105,7 +105,7 @@ struct mlx5e_tc_table { };struct mlx5e_tc_attr_to_reg_mapping mlx5e_tc_attr_to_reg_mappings[] = { - [CHAIN_TO_REG ] = { + [MAPPED_OBJ_TO_REG ] = { .mfield =MLX5_ACTION_IN_FIELD_METADATA_REG_C_0 , .moffset =0 , .mlen =16 ,
@@ -132,7 +132,7 @@ struct mlx5e_tc_attr_to_reg_mapping mlx5e_tc_attr_to_reg_mappings[] = {* into reg_b that is passed to SW since we don't * jump between steering domains. */ - [NIC_CHAIN_TO_REG] = { + [NIC_MAPPED_OBJ_TO_REG] = { .mfield = MLX5_ACTION_IN_FIELD_METADATA_REG_B, .moffset = 0, .mlen = 16,
@@ -1585,7 +1585,7 @@ mlx5e_tc_offload_to_slow_path(struct mlx5_eswitch *esw, goto err_get_chain; err =mlx5e_tc_match_to_reg_set (esw->dev, &mod_acts,MLX5_FLOW_NAMESPACE_FDB , -CHAIN_TO_REG , chain_mapping); +MAPPED_OBJ_TO_REG , chain_mapping);if (err) goto err_reg_set;
drivers/net/ethernet/mellanox/mlx5/core/en_tc.h +2 -2
@@ -229,7 +229,7 @@ void mlx5e_tc_update_neigh_used_value(struct mlx5e_neigh_hash_entry *nhe);void mlx5e_tc_reoffload_flows_work (struct work_struct *work);enum mlx5e_tc_attr_to_reg { -CHAIN_TO_REG , +MAPPED_OBJ_TO_REG ,VPORT_TO_REG ,TUNNEL_TO_REG ,CTSTATE_TO_REG ,
@@ -238,7 +238,7 @@ enum mlx5e_tc_attr_to_reg {MARK_TO_REG ,LABELS_TO_REG ,FTEID_TO_REG , -NIC_CHAIN_TO_REG , +NIC_MAPPED_OBJ_TO_REG ,NIC_ZONE_RESTORE_TO_REG , PACKET_COLOR_TO_REG, };
drivers/net/ethernet/mellanox/mlx5/core/lib/fs_chains.c +7 -7
@@ -214,7 +214,7 @@ create_chain_restore(struct fs_chain *chain)struct mlx5_eswitch *esw = chain->chains->dev->priv.eswitch;u8 modact[MLX5_UN_SZ_BYTES (set_add_copy_action_in_auto)] = {};struct mlx5_fs_chains *chains = chain->chains; -enum mlx5e_tc_attr_to_reg chain_to_reg; +enum mlx5e_tc_attr_to_reg mapped_obj_to_reg;struct mlx5_modify_hdr *mod_hdr;u32 index;int err;
@@ -242,7 +242,7 @@ create_chain_restore(struct fs_chain *chain) chain->id = index;if (chains->ns ==MLX5_FLOW_NAMESPACE_FDB ) { - chain_to_reg =CHAIN_TO_REG ; + mapped_obj_to_reg =MAPPED_OBJ_TO_REG ; chain->restore_rule =esw_add_restore_rule (esw, chain->id);if (IS_ERR (chain->restore_rule)) { err =PTR_ERR (chain->restore_rule);
@@ -253,7 +253,7 @@ create_chain_restore(struct fs_chain *chain)* since we write the metadata to reg_b * that is passed to SW directly. */ - chain_to_reg =NIC_CHAIN_TO_REG ; + mapped_obj_to_reg =NIC_MAPPED_OBJ_TO_REG ; }else { err = -EINVAL ; goto err_rule;
@@ -261,12 +261,12 @@ create_chain_restore(struct fs_chain *chain)MLX5_SET (set_action_in, modact, action_type,MLX5_ACTION_TYPE_SET );MLX5_SET (set_action_in, modact, field, - mlx5e_tc_attr_to_reg_mappings[chain_to_reg].mfield); + mlx5e_tc_attr_to_reg_mappings[mapped_obj_to_reg].mfield);MLX5_SET (set_action_in, modact, offset, - mlx5e_tc_attr_to_reg_mappings[chain_to_reg].moffset); + mlx5e_tc_attr_to_reg_mappings[mapped_obj_to_reg].moffset);MLX5_SET (set_action_in, modact, length, - mlx5e_tc_attr_to_reg_mappings[chain_to_reg].mlen ==32 ? -0 : mlx5e_tc_attr_to_reg_mappings[chain_to_reg].mlen); + mlx5e_tc_attr_to_reg_mappings[mapped_obj_to_reg].mlen ==32 ? +0 : mlx5e_tc_attr_to_reg_mappings[mapped_obj_to_reg].mlen);MLX5_SET (set_action_in, modact, data, chain->id); mod_hdr =mlx5_modify_header_alloc (chains->dev, chains->ns,1 , modact);
Signature · 1 line
2.30.1
PATCH v9 7/7 net/mlx5e: TC, Set CT miss to the specific ct action instance
In reply to Paul BlakeyCurrently, CT misses restore the missed chain on the tc skb extension so tc will continue from the relevant chain. Instead, restore the CT action's miss cookie on the extension, which will instruct tc to continue from the this specific CT action instance on the relevant filter's action list.
Map the CT action's miss_cookie to a new miss object (ACT_MISS), and use this miss mapping instead of the current chain miss object (CHAIN_MISS) for CT action misses.
To restore this new miss mapping value, add a RX restore rule for each such mapping value.
--- .../ethernet/mellanox/mlx5/core/en/tc_ct.c | 32 +++++----- .../ethernet/mellanox/mlx5/core/en/tc_ct.h | 2 + .../net/ethernet/mellanox/mlx5/core/en_tc.c | 64 +++++++++++++++++-- .../net/ethernet/mellanox/mlx5/core/en_tc.h | 6 ++ .../net/ethernet/mellanox/mlx5/core/eswitch.h | 2 + 5 files changed, 82 insertions(+), 24 deletions(-)
drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c +15 -17
@@ -59,6 +59,7 @@ struct mlx5_tc_ct_debugfs {struct mlx5_tc_ct_priv {struct mlx5_core_dev *dev; +struct mlx5e_priv *priv;const struct net_device *netdev;struct mod_hdr_tbl *mod_hdr_tbl;struct xarray tuple_ids;
@@ -85,7 +86,6 @@ struct mlx5_ct_flow {struct mlx5_flow_attr *pre_ct_attr;struct mlx5_flow_handle *pre_ct_rule;struct mlx5_ct_ft *ft; -u32 chain_mapping; };struct mlx5_ct_zone_rule {
@@ -1445,6 +1445,7 @@ mlx5_tc_ct_parse_action(struct mlx5_tc_ct_priv *priv, attr->ct_attr.zone = act->ct.zone; attr->ct_attr.ct_action = act->ct.action; attr->ct_attr.nf_ft = act->ct.flow_table; + attr->ct_attr.act_miss_cookie = act->miss_cookie;return 0 ; }
@@ -1782,7 +1783,7 @@ mlx5_tc_ct_del_ft_cb(struct mlx5_tc_ct_priv *ct_priv, struct mlx5_ct_ft *ft)* + ft prio (tc chain) + * + original match + * +---------------------+ -* | set chain miss mapping +* | set act_miss_cookie mapping * | set fte_id * | set tunnel_id * | do decap
@@ -1827,7 +1828,7 @@ __mlx5_tc_ct_flow_offload(struct mlx5_tc_ct_priv *ct_priv,struct mlx5_flow_attr *pre_ct_attr;struct mlx5_modify_hdr *mod_hdr;struct mlx5_ct_flow *ct_flow; -int chain_mapping =0 , err; +int act_miss_mapping =0 , err;struct mlx5_ct_ft *ft;u16 zone;
@@ -1862,22 +1863,18 @@ __mlx5_tc_ct_flow_offload(struct mlx5_tc_ct_priv *ct_priv, pre_ct_attr->action |=MLX5_FLOW_CONTEXT_ACTION_FWD_DEST |MLX5_FLOW_CONTEXT_ACTION_MOD_HDR ; -/* Write chain miss tag for miss in ct table as we -* don't go though all prios of this chain as normal tc rules -* miss. -*/ - err =mlx5_chains_get_chain_mapping (ct_priv->chains, attr->chain, - &chain_mapping); + err =mlx5e_tc_action_miss_mapping_get (ct_priv->priv, attr, attr->ct_attr.act_miss_cookie, + &act_miss_mapping);if (err) { -ct_dbg ("Failed to get chain register mapping for chain" ); - goto err_get_chain; +ct_dbg ("Failed to get register mapping for act miss" ); + goto err_get_act_miss; } - ct_flow->chain_mapping = chain_mapping; + attr->ct_attr.act_miss_mapping = act_miss_mapping; err =mlx5e_tc_match_to_reg_set (priv->mdev, pre_mod_acts, ct_priv->ns_type, -MAPPED_OBJ_TO_REG , chain_mapping); +MAPPED_OBJ_TO_REG , act_miss_mapping);if (err) { -ct_dbg ("Failed to set chain register mapping" ); +ct_dbg ("Failed to set act miss register mapping" ); goto err_mapping; }
@@ -1941,8 +1938,8 @@ __mlx5_tc_ct_flow_offload(struct mlx5_tc_ct_priv *ct_priv,mlx5_modify_header_dealloc (priv->mdev, pre_ct_attr->modify_hdr); err_mapping:mlx5e_mod_hdr_dealloc (pre_mod_acts); -mlx5_chains_put_chain_mapping (ct_priv->chains, ct_flow->chain_mapping); -err_get_chain: +mlx5e_tc_action_miss_mapping_put (ct_priv->priv, attr, act_miss_mapping); +err_get_act_miss:kfree (ct_flow->pre_ct_attr); err_alloc_pre:mlx5_tc_ct_del_ft_cb (ct_priv, ft);
@@ -1981,7 +1978,7 @@ __mlx5_tc_ct_delete_flow(struct mlx5_tc_ct_priv *ct_priv,mlx5_tc_rule_delete (priv, ct_flow->pre_ct_rule, pre_ct_attr);mlx5_modify_header_dealloc (priv->mdev, pre_ct_attr->modify_hdr); -mlx5_chains_put_chain_mapping (ct_priv->chains, ct_flow->chain_mapping); +mlx5e_tc_action_miss_mapping_put (ct_priv->priv, attr, attr->ct_attr.act_miss_mapping);mlx5_tc_ct_del_ft_cb (ct_priv, ct_flow->ft);kfree (ct_flow->pre_ct_attr);
@@ -2154,6 +2151,7 @@ mlx5_tc_ct_init(struct mlx5e_priv *priv, struct mlx5_fs_chains *chains, }spin_lock_init (&ct_priv->ht_lock); + ct_priv->priv = priv; ct_priv->ns_type = ns_type; ct_priv->chains = chains; ct_priv->netdev = priv->netdev;
drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.h +2 -0
@@ -28,6 +28,8 @@ struct mlx5_ct_attr {struct mlx5_ct_flow *ct_flow;struct nf_flowtable *nf_ft;u32 ct_labels_id; +u32 act_miss_mapping; +u64 act_miss_cookie; };#define zone_to_reg_ct {\
drivers/net/ethernet/mellanox/mlx5/core/en_tc.c +57 -7
95 lines not on this page · raw message
drivers/net/ethernet/mellanox/mlx5/core/en_tc.h +6 -0
@@ -101,6 +101,7 @@ struct mlx5_flow_attr {struct mlx5_flow_attr *branch_true;struct mlx5_flow_attr *branch_false;struct mlx5_flow_attr *jumping_attr; +struct mlx5_flow_handle *act_id_restore_rule;/* keep this union last */ union { DECLARE_FLEX_ARRAY(struct mlx5_esw_flow_attr, esw_attr);
@@ -402,4 +403,9 @@ mlx5e_tc_update_skb_nic(struct mlx5_cqe64 *cqe, struct sk_buff *skb) {return true; }#endif +int mlx5e_tc_action_miss_mapping_get (struct mlx5e_priv *priv,struct mlx5_flow_attr *attr, +u64 act_miss_cookie,u32 *act_miss_mapping); +void mlx5e_tc_action_miss_mapping_put (struct mlx5e_priv *priv,struct mlx5_flow_attr *attr, +u32 act_miss_mapping); +#endif /* __MLX5_EN_TC_H__ */
drivers/net/ethernet/mellanox/mlx5/core/eswitch.h +2 -0
@@ -52,12 +52,14 @@ enum mlx5_mapped_obj_type { MLX5_MAPPED_OBJ_CHAIN,MLX5_MAPPED_OBJ_SAMPLE ,MLX5_MAPPED_OBJ_INT_PORT_METADATA , + MLX5_MAPPED_OBJ_ACT_MISS, }; struct mlx5_mapped_obj { enum mlx5_mapped_obj_type type; union { u32 chain; + u64 act_miss_cookie; struct { u32 group_id; u32 rate;
Signature · 1 line
2.30.1
Hi,
Quoted 70 lines · Paul Blakey
Hi,
This series adds support for hardware miss to instruct tc to continue execution in a specific tc action instance on a filter's action list. The mlx5 driver patch (besides the refactors) shows its usage instead of using just chain restore.
Currently a filter's action list must be executed all together or not at all as driver are only able to tell tc to continue executing from a specific tc chain, and not a specific filter/action.
This is troublesome with regards to action CT, where new connections should be sent to software (via tc chain restore), and established connections can be handled in hardware.
Checking for new connections is done when executing the ct action in hardware (by checking the packet's tuple against known established tuples). But if there is a packet modification (pedit) action before action CT and the checked tuple is a new connection, hardware will need to revert the previous packet modifications before sending it back to software so it can re-match the same tc filter in software and re-execute its CT action.
The following is an example configuration of stateless nat on mlx5 driver that isn't supported before this patchet:
#Setup corrosponding mlx5 VFs in namespaces
$ ip netns add ns0 $ ip netns add ns1 $ ip link set dev enp8s0f0v0 netns ns0 $ ip netns exec ns0 ifconfig enp8s0f0v0 1.1.1.1/24 up $ ip link set dev enp8s0f0v1 netns ns1 $ ip netns exec ns1 ifconfig enp8s0f0v1 1.1.1.2/24 up#Setup tc arp and ct rules on mxl5 VF representors
$ tc qdisc add dev enp8s0f0_0 ingress $ tc qdisc add dev enp8s0f0_1 ingress $ ifconfig enp8s0f0_0 up $ ifconfig enp8s0f0_1 up#Original side
$ tc filter add dev enp8s0f0_0 ingress chain 0 proto ip flower \ ct_state -trk ip_proto tcp dst_port 8888 \ action pedit ex munge tcp dport set 5001 pipe \ action csum ip tcp pipe \ action ct pipe \ action goto chain 1 $ tc filter add dev enp8s0f0_0 ingress chain 1 proto ip flower \ ct_state +trk+est \ action mirred egress redirect dev enp8s0f0_1 $ tc filter add dev enp8s0f0_0 ingress chain 1 proto ip flower \ ct_state +trk+new \ action ct commit pipe \ action mirred egress redirect dev enp8s0f0_1 $ tc filter add dev enp8s0f0_0 ingress chain 0 proto arp flower \ action mirred egress redirect dev enp8s0f0_1#Reply side
$ tc filter add dev enp8s0f0_1 ingress chain 0 proto arp flower \ action mirred egress redirect dev enp8s0f0_0 $ tc filter add dev enp8s0f0_1 ingress chain 0 proto ip flower \ ct_state -trk ip_proto tcp \ action ct pipe \ action pedit ex munge tcp sport set 8888 pipe \ action csum ip tcp pipe \ action mirred egress redirect dev enp8s0f0_0#Run traffic
$ ip netns exec ns1 iperf -s -p 5001& $ sleep 2 #wait for iperf to fully open $ ip netns exec ns0 iperf -c 1.1.1.2 -p 8888
Quoted 5 lines
#dump tc filter stats on
enp8s0f0_0chain 0 rule and see hardware packets:$ tc -s filter show dev enp8s0f0_0 ingress chain 0 proto ip | grep "hardware.*pkt" Sent hardware 9310116832 bytes 6149672 pkt Sent hardware 9310116832 bytes 6149672 pkt Sent hardware 9310116832 bytes 6149672 pkt
I see Jamal had asked about stats on the other version, but then no dependency was set. I think we _must_ have a dependency of this patchet on the per-action stats one. Otherwise the stats above will get messy. Without the per-action stats, the last one is replicated to the other actions. But then, will hw count the packet that it did only the first action? I don't see how it would, and then for the all but first one the packet will be accounted twice.
With this said, it would be nice to provide a sample of how the sw and hw stats would look like _after_ this patchset as well.
Btw I'll add my Reviewed-by tag to the per-action stats one in a few.
Quoted 10 lines
A new connection executing the first filter in hardware will first rewrite the dst port to the new port, and then the ct action is executed, because this is a new connection, hardware will need to be send this back to software, on chain 0, to execute the first filter again in software. The dst port needs to be reverted otherwise it won't re-match the old dst port in the first filter. Because of that, currently mlx5 driver will reject offloading the above action ct rule.
This series adds supports partial offload of a filter's action list,
We should avoid this terminology as is, as it can create confusion. It is not that it is offloading action 1 and not action 2. Instead, it is adding support to a more fine grained miss to sw. Perhaps "support for partially executing in hw".
Quoted 68 lines
and letting tc software continue processing in the specific action instance where hardware left off (in the above case after the "action pedit ex munge tcp dport... of the first rule") allowing support for scenarios such as the above.
Changelog:
v1->v2:
Fixed compilation withoutCONFIG_NET_CLS
Cover letter re-write
v2->v3:
Unlockspin_lockon error in cls flower filter handle refactor Cover letter
v3->v4:
Silence warning by clang
v4->v5:
Cover letter example
Removed ifdef as much as possible by using inline stubs
v5->v6:
Removed new inlines incls_api.c(bot complained in patchwork) Added reviewed-by/ack - Thanks!
v6->v7:
RemovedWARN_ONfrom pkt path (leon)
Removed unnecessary return in void func
v7->v8:
Removed #ifIS_ENABLEDon skb ext addingKconfigchanges Complex variable init in seperate lines if,else if, else if ---> switch case
v8->v9:
Removed even moreIS_ENABLEDbecause ofKconfigPaul Blakey (7):
net/sched:cls_api: Support hardware miss to tc action net/sched: flower: Move filter handle initialization earlier net/sched: flower: Support hardware miss to tc action net/mlx5:Kconfig: Make tc offload depend on tc skb extension net/mlx5: Refactor tc miss handling to a single function net/mlx5e: RenameCHAIN_TO_REGtoMAPPED_OBJ_TO_REGnet/mlx5e: TC, Set CT miss to the specific ct action instance.../net/ethernet/mellanox/mlx5/core/Kconfig | 4 +- .../ethernet/mellanox/mlx5/core/en/rep/tc.c | 225 ++------------ .../mellanox/mlx5/core/en/tc/sample.c | 2 +- .../ethernet/mellanox/mlx5/core/en/tc_ct.c | 39 +-- .../ethernet/mellanox/mlx5/core/en/tc_ct.h | 2 + .../net/ethernet/mellanox/mlx5/core/en_rx.c | 4 +- .../net/ethernet/mellanox/mlx5/core/en_tc.c | 280 ++++++++++++++++-- .../net/ethernet/mellanox/mlx5/core/en_tc.h | 23 +- .../net/ethernet/mellanox/mlx5/core/eswitch.h | 2 + .../mellanox/mlx5/core/lib/fs_chains.c | 14 +- include/linux/skbuff.h | 6 +- include/net/flow_offload.h | 1 + include/net/pkt_cls.h | 34 ++- include/net/sch_generic.h | 2 + net/openvswitch/flow.c | 3 +- net/sched/act_api.c | 2 +- net/sched/cls_api.c | 213 ++++++++++++- net/sched/cls_flower.c | 73 +++-- 18 files changed, 602 insertions(+), 327 deletions(-)Signature · 1 line
2.30.1
Quoted 87 lines · Marcelo Ricardo Leitner
Hi,
Quoted 70 lines · Paul Blakey
Hi,
This series adds support for hardware miss to instruct tc to continue execution in a specific tc action instance on a filter's action list. The mlx5 driver patch (besides the refactors) shows its usage instead of using just chain restore.
Currently a filter's action list must be executed all together or not at all as driver are only able to tell tc to continue executing from a specific tc chain, and not a specific filter/action.
This is troublesome with regards to action CT, where new connections should be sent to software (via tc chain restore), and established connections can be handled in hardware.
Checking for new connections is done when executing the ct action in hardware (by checking the packet's tuple against known established tuples). But if there is a packet modification (pedit) action before action CT and the checked tuple is a new connection, hardware will need to revert the previous packet modifications before sending it back to software so it can re-match the same tc filter in software and re-execute its CT action.
The following is an example configuration of stateless nat on mlx5 driver that isn't supported before this patchet:
#Setup corrosponding mlx5 VFs in namespaces
$ ip netns add ns0 $ ip netns add ns1 $ ip link set dev enp8s0f0v0 netns ns0 $ ip netns exec ns0 ifconfig enp8s0f0v0 1.1.1.1/24 up $ ip link set dev enp8s0f0v1 netns ns1 $ ip netns exec ns1 ifconfig enp8s0f0v1 1.1.1.2/24 up#Setup tc arp and ct rules on mxl5 VF representors
$ tc qdisc add dev enp8s0f0_0 ingress $ tc qdisc add dev enp8s0f0_1 ingress $ ifconfig enp8s0f0_0 up $ ifconfig enp8s0f0_1 up#Original side $ tc filter add dev enp8s0f0_0 ingress chain 0 proto ip flower \ ct_state -trk ip_proto tcp dst_port 8888 \ action pedit ex munge tcp dport set 5001 pipe \ action csum ip tcp pipe \ action ct pipe \ action goto chain 1 $ tc filter add dev enp8s0f0_0 ingress chain 1 proto ip flower \ ct_state +trk+est \ action mirred egress redirect dev enp8s0f0_1 $ tc filter add dev enp8s0f0_0 ingress chain 1 proto ip flower \ ct_state +trk+new \ action ct commit pipe \ action mirred egress redirect dev enp8s0f0_1 $ tc filter add dev enp8s0f0_0 ingress chain 0 proto arp flower \ action mirred egress redirect dev enp8s0f0_1 #Reply side $ tc filter add dev enp8s0f0_1 ingress chain 0 proto arp flower \ action mirred egress redirect dev enp8s0f0_0 $ tc filter add dev enp8s0f0_1 ingress chain 0 proto ip flower \ ct_state -trk ip_proto tcp \ action ct pipe \ action pedit ex munge tcp sport set 8888 pipe \ action csum ip tcp pipe \ action mirred egress redirect dev enp8s0f0_0#Run traffic
$ ip netns exec ns1 iperf -s -p 5001& $ sleep 2 #wait for iperf to fully open $ ip netns exec ns0 iperf -c 1.1.1.2 -p 8888Quoted 5 lines
#dump tc filter stats on
enp8s0f0_0chain 0 rule and see hardware packets:$ tc -s filter show dev enp8s0f0_0 ingress chain 0 proto ip | grep "hardware.*pkt" Sent hardware 9310116832 bytes 6149672 pkt Sent hardware 9310116832 bytes 6149672 pkt Sent hardware 9310116832 bytes 6149672 pktI see Jamal had asked about stats on the other version, but then no dependency was set. I think we _must_ have a dependency of this patchet on the per-action stats one. Otherwise the stats above will get messy. Without the per-action stats, the last one is replicated to the other actions. But then, will hw count the packet that it did only the first action? I don't see how it would, and then for the all but first one the packet will be accounted twice.
Quoted 4 lines
With this said, it would be nice to provide a sample of how the sw and hw stats would look like _after_ this patchset as well.
Btw I'll add my Reviewed-by tag to the per-action stats one in a few.
This patchset actually doesn't need to rely on the per actions stats because the driver is still reordering the action list so CT will be first and the example in cover letter will be rejected because it can't be reordered. Then we are still doing all (CT and the rest) or nothing.
But we wanted to confirm the API before committing the rest of the driver patches since its has a lot of refactors so we split it to two series - API, then only MLX5 DRIVER. This is just the API with a bare minimal driver change to just use the API. From tc user perspective nothing changed here.
So do we first continue with this (after i fix your suggestions), and then we'll submit the rest, or should I rebase on the per action stats, add even more mlx5 patches here which are mostly not relevant, since I think we are ok with the API changes.
Quoted 85 lines
Quoted 11 lines
A new connection executing the first filter in hardware will first rewrite the dst port to the new port, and then the ct action is executed, because this is a new connection, hardware will need to be send this back to software, on chain 0, to execute the first filter again in software. The dst port needs to be reverted otherwise it won't re-match the old dst port in the first filter. Because of that, currently mlx5 driver will reject offloading the above action ct rule.
This series adds supports partial offload of a filter's action list,
We should avoid this terminology as is, as it can create confusion. It is not that it is offloading action 1 and not action 2. Instead, it is adding support to a more fine grained miss to sw. Perhaps "support for partially executing in hw".
Quoted 68 lines
and letting tc software continue processing in the specific action instance where hardware left off (in the above case after the "action pedit ex munge tcp dport... of the first rule") allowing support for scenarios such as the above.
Changelog:
v1->v2:
Fixed compilation withoutCONFIG_NET_CLS
Cover letter re-write
v2->v3:
Unlockspin_lockon error in cls flower filter handle refactor Cover letter
v3->v4:
Silence warning by clang
v4->v5:
Cover letter example
Removed ifdef as much as possible by using inline stubs
v5->v6:
Removed new inlines incls_api.c(bot complained in patchwork) Added reviewed-by/ack - Thanks!
v6->v7:
RemovedWARN_ONfrom pkt path (leon)
Removed unnecessary return in void func
v7->v8:
Removed #ifIS_ENABLEDon skb ext addingKconfigchanges Complex variable init in seperate lines if,else if, else if ---> switch case
v8->v9:
Removed even moreIS_ENABLEDbecause ofKconfigPaul Blakey (7):
net/sched:cls_api: Support hardware miss to tc action net/sched: flower: Move filter handle initialization earlier net/sched: flower: Support hardware miss to tc action net/mlx5:Kconfig: Make tc offload depend on tc skb extension net/mlx5: Refactor tc miss handling to a single function net/mlx5e: RenameCHAIN_TO_REGtoMAPPED_OBJ_TO_REGnet/mlx5e: TC, Set CT miss to the specific ct action instance.../net/ethernet/mellanox/mlx5/core/Kconfig | 4 +- .../ethernet/mellanox/mlx5/core/en/rep/tc.c | 225 ++------------ .../mellanox/mlx5/core/en/tc/sample.c | 2 +- .../ethernet/mellanox/mlx5/core/en/tc_ct.c | 39 +-- .../ethernet/mellanox/mlx5/core/en/tc_ct.h | 2 + .../net/ethernet/mellanox/mlx5/core/en_rx.c | 4 +- .../net/ethernet/mellanox/mlx5/core/en_tc.c | 280 ++++++++++++++++-- .../net/ethernet/mellanox/mlx5/core/en_tc.h | 23 +- .../net/ethernet/mellanox/mlx5/core/eswitch.h | 2 + .../mellanox/mlx5/core/lib/fs_chains.c | 14 +- include/linux/skbuff.h | 6 +- include/net/flow_offload.h | 1 + include/net/pkt_cls.h | 34 ++- include/net/sch_generic.h | 2 + net/openvswitch/flow.c | 3 +- net/sched/act_api.c | 2 +- net/sched/cls_api.c | 213 ++++++++++++- net/sched/cls_flower.c | 73 +++-- 18 files changed, 602 insertions(+), 327 deletions(-)Signature · 1 line
2.30.1
Quoted 93 lines · Paul Blakey
Quoted 90 lines · Marcelo Ricardo Leitner
Hi,
Quoted 70 lines · Paul Blakey
Hi,
This series adds support for hardware miss to instruct tc to continue execution in a specific tc action instance on a filter's action list. The mlx5 driver patch (besides the refactors) shows its usage instead of using just chain restore.
Currently a filter's action list must be executed all together or not at all as driver are only able to tell tc to continue executing from a specific tc chain, and not a specific filter/action.
This is troublesome with regards to action CT, where new connections should be sent to software (via tc chain restore), and established connections can be handled in hardware.
Checking for new connections is done when executing the ct action in hardware (by checking the packet's tuple against known established tuples). But if there is a packet modification (pedit) action before action CT and the checked tuple is a new connection, hardware will need to revert the previous packet modifications before sending it back to software so it can re-match the same tc filter in software and re-execute its CT action.
The following is an example configuration of stateless nat on mlx5 driver that isn't supported before this patchet:
#Setup corrosponding mlx5 VFs in namespaces
$ ip netns add ns0 $ ip netns add ns1 $ ip link set dev enp8s0f0v0 netns ns0 $ ip netns exec ns0 ifconfig enp8s0f0v0 1.1.1.1/24 up $ ip link set dev enp8s0f0v1 netns ns1 $ ip netns exec ns1 ifconfig enp8s0f0v1 1.1.1.2/24 up#Setup tc arp and ct rules on mxl5 VF representors
$ tc qdisc add dev enp8s0f0_0 ingress $ tc qdisc add dev enp8s0f0_1 ingress $ ifconfig enp8s0f0_0 up $ ifconfig enp8s0f0_1 up#Original side $ tc filter add dev enp8s0f0_0 ingress chain 0 proto ip flower \ ct_state -trk ip_proto tcp dst_port 8888 \ action pedit ex munge tcp dport set 5001 pipe \ action csum ip tcp pipe \ action ct pipe \ action goto chain 1 $ tc filter add dev enp8s0f0_0 ingress chain 1 proto ip flower \ ct_state +trk+est \ action mirred egress redirect dev enp8s0f0_1 $ tc filter add dev enp8s0f0_0 ingress chain 1 proto ip flower \ ct_state +trk+new \ action ct commit pipe \ action mirred egress redirect dev enp8s0f0_1 $ tc filter add dev enp8s0f0_0 ingress chain 0 proto arp flower \ action mirred egress redirect dev enp8s0f0_1 #Reply side $ tc filter add dev enp8s0f0_1 ingress chain 0 proto arp flower \ action mirred egress redirect dev enp8s0f0_0 $ tc filter add dev enp8s0f0_1 ingress chain 0 proto ip flower \ ct_state -trk ip_proto tcp \ action ct pipe \ action pedit ex munge tcp sport set 8888 pipe \ action csum ip tcp pipe \ action mirred egress redirect dev enp8s0f0_0#Run traffic
$ ip netns exec ns1 iperf -s -p 5001& $ sleep 2 #wait for iperf to fully open $ ip netns exec ns0 iperf -c 1.1.1.2 -p 8888Quoted 5 lines
#dump tc filter stats on
enp8s0f0_0chain 0 rule and see hardware packets:$ tc -s filter show dev enp8s0f0_0 ingress chain 0 proto ip | grep "hardware.*pkt" Sent hardware 9310116832 bytes 6149672 pkt Sent hardware 9310116832 bytes 6149672 pkt Sent hardware 9310116832 bytes 6149672 pktI see Jamal had asked about stats on the other version, but then no dependency was set. I think we _must_ have a dependency of this patchet on the per-action stats one. Otherwise the stats above will get messy. Without the per-action stats, the last one is replicated to the other actions. But then, will hw count the packet that it did only the first action? I don't see how it would, and then for the all but first one the packet will be accounted twice.
With this said, it would be nice to provide a sample of how the sw and hw stats would look like _after_ this patchset as well.
Quoted 7 lines
Quoted 1 line
Btw I'll add my Reviewed-by tag to the per-action stats one in a few.
This patchset actually doesn't need to rely on the per actions stats because the driver is still reordering the action list so CT will be first and the example in cover letter will be rejected because it can't be reordered. Then we are still doing all (CT and the rest) or nothing.
Ah right. I thought the driver patches here were undoing the reordering already.
Quoted 8 lines
But we wanted to confirm the API before committing the rest of the driver patches since its has a lot of refactors so we split it to two series - API, then only MLX5 DRIVER. This is just the API with a bare minimal driver change to just use the API. From tc user perspective nothing changed here.
So do we first continue with this (after i fix your suggestions), and then we'll submit the rest, or should I rebase on the per action stats, add even
Well, the two patchsets will certainly create conflicts when adding the cookie. Not sure if the maintainers can accomodate it.
Quoted 89 lines
more mlx5 patches here which are mostly not relevant, since I think we are ok with the API changes.
Quoted 85 lines
Quoted 11 lines
A new connection executing the first filter in hardware will first rewrite the dst port to the new port, and then the ct action is executed, because this is a new connection, hardware will need to be send this back to software, on chain 0, to execute the first filter again in software. The dst port needs to be reverted otherwise it won't re-match the old dst port in the first filter. Because of that, currently mlx5 driver will reject offloading the above action ct rule.
This series adds supports partial offload of a filter's action list,
We should avoid this terminology as is, as it can create confusion. It is not that it is offloading action 1 and not action 2. Instead, it is adding support to a more fine grained miss to sw. Perhaps "support for partially executing in hw".
Quoted 68 lines
and letting tc software continue processing in the specific action instance where hardware left off (in the above case after the "action pedit ex munge tcp dport... of the first rule") allowing support for scenarios such as the above.
Changelog:
v1->v2:
Fixed compilation withoutCONFIG_NET_CLS
Cover letter re-write
v2->v3:
Unlockspin_lockon error in cls flower filter handle refactor Cover letter
v3->v4:
Silence warning by clang
v4->v5:
Cover letter example
Removed ifdef as much as possible by using inline stubs
v5->v6:
Removed new inlines incls_api.c(bot complained in patchwork) Added reviewed-by/ack - Thanks!
v6->v7:
RemovedWARN_ONfrom pkt path (leon)
Removed unnecessary return in void func
v7->v8:
Removed #ifIS_ENABLEDon skb ext addingKconfigchanges Complex variable init in seperate lines if,else if, else if ---> switch case
v8->v9:
Removed even moreIS_ENABLEDbecause ofKconfigPaul Blakey (7):
net/sched:cls_api: Support hardware miss to tc action net/sched: flower: Move filter handle initialization earlier net/sched: flower: Support hardware miss to tc action net/mlx5:Kconfig: Make tc offload depend on tc skb extension net/mlx5: Refactor tc miss handling to a single function net/mlx5e: RenameCHAIN_TO_REGtoMAPPED_OBJ_TO_REGnet/mlx5e: TC, Set CT miss to the specific ct action instance.../net/ethernet/mellanox/mlx5/core/Kconfig | 4 +- .../ethernet/mellanox/mlx5/core/en/rep/tc.c | 225 ++------------ .../mellanox/mlx5/core/en/tc/sample.c | 2 +- .../ethernet/mellanox/mlx5/core/en/tc_ct.c | 39 +-- .../ethernet/mellanox/mlx5/core/en/tc_ct.h | 2 + .../net/ethernet/mellanox/mlx5/core/en_rx.c | 4 +- .../net/ethernet/mellanox/mlx5/core/en_tc.c | 280 ++++++++++++++++-- .../net/ethernet/mellanox/mlx5/core/en_tc.h | 23 +- .../net/ethernet/mellanox/mlx5/core/eswitch.h | 2 + .../mellanox/mlx5/core/lib/fs_chains.c | 14 +- include/linux/skbuff.h | 6 +- include/net/flow_offload.h | 1 + include/net/pkt_cls.h | 34 ++- include/net/sch_generic.h | 2 + net/openvswitch/flow.c | 3 +- net/sched/act_api.c | 2 +- net/sched/cls_api.c | 213 ++++++++++++- net/sched/cls_flower.c | 73 +++-- 18 files changed, 602 insertions(+), 327 deletions(-)Signature · 1 line
2.30.1