| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-ID: <ygnhim12qxxy.fsf@nvidia.com>
Date: Thu, 22 Jul 2021 16:29:13 +0300
From: Vlad Buslov <vladbu@...dia.com>
To: Simon Horman <simon.horman@...igine.com>
CC: David Miller <davem@...emloft.net>,
Jakub Kicinski <kuba@...nel.org>,
Jamal Hadi Salim <jhs@...atatu.com>,
Cong Wang <xiyou.wangcong@...il.com>,
Jiri Pirko <jiri@...lanox.com>, <netdev@...r.kernel.org>,
<oss-drivers@...igine.com>,
Baowen Zheng <baowen.zheng@...igine.com>,
"Louis Peens" <louis.peens@...igine.com>
Subject: Re: [PATCH net-next 1/3] flow_offload: allow user to offload tc
action to net device
On Thu 22 Jul 2021 at 12:19, Simon Horman <simon.horman@...igine.com> wrote:
> From: Baowen Zheng <baowen.zheng@...igine.com>
>
> Use flow_indr_dev_register/flow_indr_dev_setup_offload to
> offload tc action.
>
> We offload the tc action mainly for ovs meter configuration.
> Make some basic changes for different vendors to return EOPNOTSUPP.
>
> We need to call tc_cleanup_flow_action to clean up tc action entry since
> in tc_setup_action, some actions may hold dev refcnt, especially the mirror
> action.
>
> As per review from the RFC, the kernel test robot will fail to run, so
> we add CONFIG_NET_CLS_ACT control for the action offload.
>
> Signed-off-by: Baowen Zheng <baowen.zheng@...igine.com>
> Signed-off-by: Louis Peens <louis.peens@...igine.com>
> Signed-off-by: Simon Horman <simon.horman@...igine.com>
> ---
> drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c | 2 +-
> .../ethernet/mellanox/mlx5/core/en/rep/tc.c | 3 ++
> .../ethernet/netronome/nfp/flower/offload.c | 3 ++
> include/linux/netdevice.h | 1 +
> include/net/flow_offload.h | 15 ++++++++
> include/net/pkt_cls.h | 15 ++++++++
> net/core/flow_offload.c | 26 +++++++++++++-
> net/sched/act_api.c | 33 +++++++++++++++++
> net/sched/cls_api.c | 36 ++++++++++++++++---
> 9 files changed, 128 insertions(+), 6 deletions(-)
>
> diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c
> index 5e4429b14b8c..edbbf7b4df77 100644
> --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c
> +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c
> @@ -1951,7 +1951,7 @@ static int bnxt_tc_setup_indr_cb(struct net_device *netdev, struct Qdisc *sch, v
> void *data,
> void (*cleanup)(struct flow_block_cb *block_cb))
> {
> - if (!bnxt_is_netdev_indr_offload(netdev))
> + if (!netdev || !bnxt_is_netdev_indr_offload(netdev))
> return -EOPNOTSUPP;
>
> switch (type) {
> diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/rep/tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en/rep/tc.c
> index 059799e4f483..111daacc4cc3 100644
> --- a/drivers/net/ethernet/mellanox/mlx5/core/en/rep/tc.c
> +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/rep/tc.c
> @@ -486,6 +486,9 @@ int mlx5e_rep_indr_setup_cb(struct net_device *netdev, struct Qdisc *sch, void *
> void *data,
> void (*cleanup)(struct flow_block_cb *block_cb))
> {
> + if (!netdev)
> + return -EOPNOTSUPP;
> +
> switch (type) {
> case TC_SETUP_BLOCK:
> return mlx5e_rep_indr_setup_block(netdev, sch, cb_priv, type_data,
> diff --git a/drivers/net/ethernet/netronome/nfp/flower/offload.c b/drivers/net/ethernet/netronome/nfp/flower/offload.c
> index 2406d33356ad..88bbc86347b4 100644
> --- a/drivers/net/ethernet/netronome/nfp/flower/offload.c
> +++ b/drivers/net/ethernet/netronome/nfp/flower/offload.c
> @@ -1869,6 +1869,9 @@ nfp_flower_indr_setup_tc_cb(struct net_device *netdev, struct Qdisc *sch, void *
> void *data,
> void (*cleanup)(struct flow_block_cb *block_cb))
> {
> + if (!netdev)
> + return -EOPNOTSUPP;
> +
> if (!nfp_fl_is_netdev_to_offload(netdev))
> return -EOPNOTSUPP;
>
> diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
> index 42f6f866d5f3..b138219baf6f 100644
> --- a/include/linux/netdevice.h
> +++ b/include/linux/netdevice.h
> @@ -923,6 +923,7 @@ enum tc_setup_type {
> TC_SETUP_QDISC_TBF,
> TC_SETUP_QDISC_FIFO,
> TC_SETUP_QDISC_HTB,
> + TC_SETUP_ACT,
> };
>
> /* These structures hold the attributes of bpf state that are being passed
> diff --git a/include/net/flow_offload.h b/include/net/flow_offload.h
> index 69c9eabf8325..26644596fd54 100644
> --- a/include/net/flow_offload.h
> +++ b/include/net/flow_offload.h
> @@ -553,6 +553,21 @@ struct flow_cls_offload {
> u32 classid;
> };
>
> +enum flow_act_command {
> + FLOW_ACT_REPLACE,
> + FLOW_ACT_DESTROY,
> + FLOW_ACT_STATS,
> +};
> +
> +struct flow_offload_action {
> + struct netlink_ext_ack *extack;
> + enum flow_act_command command;
> + struct flow_stats stats;
> + struct flow_action action;
> +};
> +
> +struct flow_offload_action *flow_action_alloc(unsigned int num_actions);
> +
> static inline struct flow_rule *
> flow_cls_offload_flow_rule(struct flow_cls_offload *flow_cmd)
> {
> diff --git a/include/net/pkt_cls.h b/include/net/pkt_cls.h
> index ec7823921bd2..cd4cf6b10f5d 100644
> --- a/include/net/pkt_cls.h
> +++ b/include/net/pkt_cls.h
> @@ -266,6 +266,9 @@ static inline void tcf_exts_put_net(struct tcf_exts *exts)
> for (; 0; (void)(i), (void)(a), (void)(exts))
> #endif
>
> +#define tcf_act_for_each_action(i, a, actions) \
> + for (i = 0; i < TCA_ACT_MAX_PRIO && ((a) = actions[i]); i++)
> +
> static inline void
> tcf_exts_stats_update(const struct tcf_exts *exts,
> u64 bytes, u64 packets, u64 drops, u64 lastuse,
> @@ -536,8 +539,19 @@ tcf_match_indev(struct sk_buff *skb, int ifindex)
> return ifindex == skb->skb_iif;
> }
>
> +#ifdef CONFIG_NET_CLS_ACT
> int tc_setup_flow_action(struct flow_action *flow_action,
> const struct tcf_exts *exts);
> +#else
> +static inline int tc_setup_flow_action(struct flow_action *flow_action,
> + const struct tcf_exts *exts)
> +{
> + return 0;
> +}
> +#endif
> +
> +int tc_setup_action(struct flow_action *flow_action,
> + struct tc_action *actions[]);
> void tc_cleanup_flow_action(struct flow_action *flow_action);
>
> int tc_setup_cb_call(struct tcf_block *block, enum tc_setup_type type,
> @@ -558,6 +572,7 @@ int tc_setup_cb_reoffload(struct tcf_block *block, struct tcf_proto *tp,
> enum tc_setup_type type, void *type_data,
> void *cb_priv, u32 *flags, unsigned int *in_hw_count);
> unsigned int tcf_exts_num_actions(struct tcf_exts *exts);
> +unsigned int tcf_act_num_actions(struct tc_action *actions[]);
>
> #ifdef CONFIG_NET_CLS_ACT
> int tcf_qevent_init(struct tcf_qevent *qe, struct Qdisc *sch,
> diff --git a/net/core/flow_offload.c b/net/core/flow_offload.c
> index 715b67f6c62f..0fa2f75cc9b3 100644
> --- a/net/core/flow_offload.c
> +++ b/net/core/flow_offload.c
> @@ -27,6 +27,27 @@ struct flow_rule *flow_rule_alloc(unsigned int num_actions)
> }
> EXPORT_SYMBOL(flow_rule_alloc);
>
> +struct flow_offload_action *flow_action_alloc(unsigned int num_actions)
> +{
> + struct flow_offload_action *fl_action;
> + int i;
> +
> + fl_action = kzalloc(struct_size(fl_action, action.entries, num_actions),
> + GFP_KERNEL);
> + if (!fl_action)
> + return NULL;
> +
> + fl_action->action.num_entries = num_actions;
> + /* Pre-fill each action hw_stats with DONT_CARE.
> + * Caller can override this if it wants stats for a given action.
> + */
> + for (i = 0; i < num_actions; i++)
> + fl_action->action.entries[i].hw_stats = FLOW_ACTION_HW_STATS_DONT_CARE;
> +
> + return fl_action;
> +}
> +EXPORT_SYMBOL(flow_action_alloc);
> +
> #define FLOW_DISSECTOR_MATCH(__rule, __type, __out) \
> const struct flow_match *__m = &(__rule)->match; \
> struct flow_dissector *__d = (__m)->dissector; \
> @@ -476,6 +497,9 @@ int flow_indr_dev_setup_offload(struct net_device *dev, struct Qdisc *sch,
>
> mutex_unlock(&flow_indr_block_lock);
>
> - return list_empty(&bo->cb_list) ? -EOPNOTSUPP : 0;
> + if (bo)
> + return list_empty(&bo->cb_list) ? -EOPNOTSUPP : 0;
> + else
> + return 0;
> }
> EXPORT_SYMBOL(flow_indr_dev_setup_offload);
> diff --git a/net/sched/act_api.c b/net/sched/act_api.c
> index 998a2374f7ae..185f17ea60d5 100644
> --- a/net/sched/act_api.c
> +++ b/net/sched/act_api.c
> @@ -1060,6 +1060,36 @@ struct tc_action *tcf_action_init_1(struct net *net, struct tcf_proto *tp,
> return ERR_PTR(err);
> }
>
> +/* offload the tc command after inserted */
> +int tcf_action_offload_cmd(struct tc_action *actions[],
> + struct netlink_ext_ack *extack)
> +{
> + struct flow_offload_action *fl_act;
> + int err = 0;
> +
> + fl_act = flow_action_alloc(tcf_act_num_actions(actions));
> + if (!fl_act)
> + return -ENOMEM;
> +
> + fl_act->extack = extack;
> + err = tc_setup_action(&fl_act->action, actions);
> + if (err) {
> + NL_SET_ERR_MSG_MOD(extack,
> + "Failed to setup tc actions for offload\n");
> + goto err_out;
> + }
> + fl_act->command = FLOW_ACT_REPLACE;
> +
> + flow_indr_dev_setup_offload(NULL, NULL, TC_SETUP_ACT, fl_act, NULL, NULL);
> +
> + tc_cleanup_flow_action(&fl_act->action);
> +
> +err_out:
> + kfree(fl_act);
> + return err;
> +}
> +EXPORT_SYMBOL(tcf_action_offload_cmd);
> +
> /* Returns numbers of initialized actions or negative error. */
>
> int tcf_action_init(struct net *net, struct tcf_proto *tp, struct nlattr *nla,
> @@ -1514,6 +1544,9 @@ static int tcf_action_add(struct net *net, struct nlattr *nla,
> return ret;
> ret = tcf_add_notify(net, n, actions, portid, attr_size, extack);
>
> + /* offload actions to hardware if possible */
> + tcf_action_offload_cmd(actions, extack);
> +
I think this has already been suggested for RFC, but some sort of
visibility for offload status of action would be extremely welcome.
Perhaps "IN_HW" flag and counter, similar to what we have for offloaded
filters.
> /* only put existing actions */
> for (i = 0; i < TCA_ACT_MAX_PRIO; i++)
> if (init_res[i] == ACT_P_CREATED)
> diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c
> index c8cb59a11098..9b9770dab5e8 100644
> --- a/net/sched/cls_api.c
> +++ b/net/sched/cls_api.c
> @@ -3544,8 +3544,8 @@ static enum flow_action_hw_stats tc_act_hw_stats(u8 hw_stats)
> return hw_stats;
> }
>
> -int tc_setup_flow_action(struct flow_action *flow_action,
> - const struct tcf_exts *exts)
> +int tc_setup_action(struct flow_action *flow_action,
> + struct tc_action *actions[])
> {
> struct tc_action *act;
> int i, j, k, err = 0;
> @@ -3554,11 +3554,11 @@ int tc_setup_flow_action(struct flow_action *flow_action,
> BUILD_BUG_ON(TCA_ACT_HW_STATS_IMMEDIATE != FLOW_ACTION_HW_STATS_IMMEDIATE);
> BUILD_BUG_ON(TCA_ACT_HW_STATS_DELAYED != FLOW_ACTION_HW_STATS_DELAYED);
>
> - if (!exts)
> + if (!actions)
> return 0;
>
> j = 0;
> - tcf_exts_for_each_action(i, act, exts) {
> + tcf_act_for_each_action(i, act, actions) {
> struct flow_action_entry *entry;
>
> entry = &flow_action->entries[j];
> @@ -3725,7 +3725,19 @@ int tc_setup_flow_action(struct flow_action *flow_action,
> spin_unlock_bh(&act->tcfa_lock);
> goto err_out;
> }
> +EXPORT_SYMBOL(tc_setup_action);
> +
> +#ifdef CONFIG_NET_CLS_ACT
> +int tc_setup_flow_action(struct flow_action *flow_action,
> + const struct tcf_exts *exts)
> +{
> + if (!exts)
> + return 0;
> +
> + return tc_setup_action(flow_action, exts->actions);
> +}
> EXPORT_SYMBOL(tc_setup_flow_action);
> +#endif
>
> unsigned int tcf_exts_num_actions(struct tcf_exts *exts)
> {
> @@ -3743,6 +3755,22 @@ unsigned int tcf_exts_num_actions(struct tcf_exts *exts)
> }
> EXPORT_SYMBOL(tcf_exts_num_actions);
>
> +unsigned int tcf_act_num_actions(struct tc_action *actions[])
> +{
> + unsigned int num_acts = 0;
> + struct tc_action *act;
> + int i;
> +
> + tcf_act_for_each_action(i, act, actions) {
> + if (is_tcf_pedit(act))
> + num_acts += tcf_pedit_nkeys(act);
> + else
> + num_acts++;
> + }
> + return num_acts;
> +}
> +EXPORT_SYMBOL(tcf_act_num_actions);
> +
> #ifdef CONFIG_NET_CLS_ACT
> static int tcf_qevent_parse_block_index(struct nlattr *block_index_attr,
> u32 *p_block_index,
Powered by blists - more mailing lists