diff options
Diffstat (limited to 'net/sched')
49 files changed, 446 insertions, 209 deletions
diff --git a/net/sched/Kconfig b/net/sched/Kconfig index 84badf00647e..a3b37d88800e 100644 --- a/net/sched/Kconfig +++ b/net/sched/Kconfig @@ -468,6 +468,9 @@ choice config DEFAULT_FQ_CODEL bool "Fair Queue Controlled Delay" if NET_SCH_FQ_CODEL + config DEFAULT_FQ_PIE + bool "Flow Queue Proportional Integral controller Enhanced" if NET_SCH_FQ_PIE + config DEFAULT_SFQ bool "Stochastic Fair Queue" if NET_SCH_SFQ @@ -480,6 +483,7 @@ config DEFAULT_NET_SCH default "pfifo_fast" if DEFAULT_PFIFO_FAST default "fq" if DEFAULT_FQ default "fq_codel" if DEFAULT_FQ_CODEL + default "fq_pie" if DEFAULT_FQ_PIE default "sfq" if DEFAULT_SFQ default "pfifo_fast" endif diff --git a/net/sched/act_api.c b/net/sched/act_api.c index 8ac7eb0a8309..063d8aaf2900 100644 --- a/net/sched/act_api.c +++ b/net/sched/act_api.c @@ -1059,14 +1059,13 @@ err: return err; } -void tcf_action_update_stats(struct tc_action *a, u64 bytes, u32 packets, - bool drop, bool hw) +void tcf_action_update_stats(struct tc_action *a, u64 bytes, u64 packets, + u64 drops, bool hw) { if (a->cpu_bstats) { _bstats_cpu_update(this_cpu_ptr(a->cpu_bstats), bytes, packets); - if (drop) - this_cpu_ptr(a->cpu_qstats)->drops += packets; + this_cpu_ptr(a->cpu_qstats)->drops += drops; if (hw) _bstats_cpu_update(this_cpu_ptr(a->cpu_bstats_hw), @@ -1075,8 +1074,7 @@ void tcf_action_update_stats(struct tc_action *a, u64 bytes, u32 packets, } _bstats_update(&a->tcfa_bstats, bytes, packets); - if (drop) - a->tcfa_qstats.drops += packets; + a->tcfa_qstats.drops += drops; if (hw) _bstats_update(&a->tcfa_bstats_hw, bytes, packets); } @@ -1475,7 +1473,7 @@ static int tc_ctl_action(struct sk_buff *skb, struct nlmsghdr *n, { struct net *net = sock_net(skb->sk); struct nlattr *tca[TCA_ROOT_MAX + 1]; - u32 portid = skb ? NETLINK_CB(skb).portid : 0; + u32 portid = NETLINK_CB(skb).portid; int ret = 0, ovr = 0; if ((n->nlmsg_type != RTM_GETACTION) && diff --git a/net/sched/act_ct.c b/net/sched/act_ct.c index e9f3576cbf71..1b9c6d4a1b6b 100644 --- a/net/sched/act_ct.c +++ b/net/sched/act_ct.c @@ -1450,12 +1450,12 @@ static int tcf_ct_search(struct net *net, struct tc_action **a, u32 index) return tcf_idr_search(tn, a, index); } -static void tcf_stats_update(struct tc_action *a, u64 bytes, u32 packets, - u64 lastuse, bool hw) +static void tcf_stats_update(struct tc_action *a, u64 bytes, u64 packets, + u64 drops, u64 lastuse, bool hw) { struct tcf_ct *c = to_ct(a); - tcf_action_update_stats(a, bytes, packets, false, hw); + tcf_action_update_stats(a, bytes, packets, drops, hw); c->tcf_tm.lastuse = max_t(u64, c->tcf_tm.lastuse, lastuse); } diff --git a/net/sched/act_gact.c b/net/sched/act_gact.c index 416065772719..410e3bbfb9ca 100644 --- a/net/sched/act_gact.c +++ b/net/sched/act_gact.c @@ -171,14 +171,15 @@ static int tcf_gact_act(struct sk_buff *skb, const struct tc_action *a, return action; } -static void tcf_gact_stats_update(struct tc_action *a, u64 bytes, u32 packets, - u64 lastuse, bool hw) +static void tcf_gact_stats_update(struct tc_action *a, u64 bytes, u64 packets, + u64 drops, u64 lastuse, bool hw) { struct tcf_gact *gact = to_gact(a); int action = READ_ONCE(gact->tcf_action); struct tcf_t *tm = &gact->tcf_tm; - tcf_action_update_stats(a, bytes, packets, action == TC_ACT_SHOT, hw); + tcf_action_update_stats(a, bytes, packets, + action == TC_ACT_SHOT ? packets : drops, hw); tm->lastuse = max_t(u64, tm->lastuse, lastuse); } diff --git a/net/sched/act_gate.c b/net/sched/act_gate.c index 9c628591f452..1fb8d428d2c1 100644 --- a/net/sched/act_gate.c +++ b/net/sched/act_gate.c @@ -32,7 +32,7 @@ static ktime_t gate_get_time(struct tcf_gate *gact) return KTIME_MAX; } -static int gate_get_start_time(struct tcf_gate *gact, ktime_t *start) +static void gate_get_start_time(struct tcf_gate *gact, ktime_t *start) { struct tcf_gate_params *param = &gact->param; ktime_t now, base, cycle; @@ -43,18 +43,13 @@ static int gate_get_start_time(struct tcf_gate *gact, ktime_t *start) if (ktime_after(base, now)) { *start = base; - return 0; + return; } cycle = param->tcfg_cycletime; - /* cycle time should not be zero */ - if (!cycle) - return -EFAULT; - n = div64_u64(ktime_sub_ns(now, base), cycle); *start = ktime_add_ns(base, (n + 1) * cycle); - return 0; } static void gate_start_timer(struct tcf_gate *gact, ktime_t start) @@ -277,6 +272,27 @@ release_list: return err; } +static void gate_setup_timer(struct tcf_gate *gact, u64 basetime, + enum tk_offsets tko, s32 clockid, + bool do_init) +{ + if (!do_init) { + if (basetime == gact->param.tcfg_basetime && + tko == gact->tk_offset && + clockid == gact->param.tcfg_clockid) + return; + + spin_unlock_bh(&gact->tcf_lock); + hrtimer_cancel(&gact->hitimer); + spin_lock_bh(&gact->tcf_lock); + } + gact->param.tcfg_basetime = basetime; + gact->param.tcfg_clockid = clockid; + gact->tk_offset = tko; + hrtimer_init(&gact->hitimer, clockid, HRTIMER_MODE_ABS_SOFT); + gact->hitimer.function = gate_timer_func; +} + static int tcf_gate_init(struct net *net, struct nlattr *nla, struct nlattr *est, struct tc_action **a, int ovr, int bind, bool rtnl_held, @@ -287,12 +303,12 @@ static int tcf_gate_init(struct net *net, struct nlattr *nla, enum tk_offsets tk_offset = TK_OFFS_TAI; struct nlattr *tb[TCA_GATE_MAX + 1]; struct tcf_chain *goto_ch = NULL; + u64 cycletime = 0, basetime = 0; struct tcf_gate_params *p; s32 clockid = CLOCK_TAI; struct tcf_gate *gact; struct tc_gate *parm; int ret = 0, err; - u64 basetime = 0; u32 gflags = 0; s32 prio = -1; ktime_t start; @@ -308,6 +324,27 @@ static int tcf_gate_init(struct net *net, struct nlattr *nla, if (!tb[TCA_GATE_PARMS]) return -EINVAL; + if (tb[TCA_GATE_CLOCKID]) { + clockid = nla_get_s32(tb[TCA_GATE_CLOCKID]); + switch (clockid) { + case CLOCK_REALTIME: + tk_offset = TK_OFFS_REAL; + break; + case CLOCK_MONOTONIC: + tk_offset = TK_OFFS_MAX; + break; + case CLOCK_BOOTTIME: + tk_offset = TK_OFFS_BOOT; + break; + case CLOCK_TAI: + tk_offset = TK_OFFS_TAI; + break; + default: + NL_SET_ERR_MSG(extack, "Invalid 'clockid'"); + return -EINVAL; + } + } + parm = nla_data(tb[TCA_GATE_PARMS]); index = parm->index; @@ -331,10 +368,6 @@ static int tcf_gate_init(struct net *net, struct nlattr *nla, tcf_idr_release(*a, bind); return -EEXIST; } - if (ret == ACT_P_CREATED) { - to_gate(*a)->param.tcfg_clockid = -1; - INIT_LIST_HEAD(&(to_gate(*a)->param.entries)); - } if (tb[TCA_GATE_PRIORITY]) prio = nla_get_s32(tb[TCA_GATE_PRIORITY]); @@ -345,41 +378,19 @@ static int tcf_gate_init(struct net *net, struct nlattr *nla, if (tb[TCA_GATE_FLAGS]) gflags = nla_get_u32(tb[TCA_GATE_FLAGS]); - if (tb[TCA_GATE_CLOCKID]) { - clockid = nla_get_s32(tb[TCA_GATE_CLOCKID]); - switch (clockid) { - case CLOCK_REALTIME: - tk_offset = TK_OFFS_REAL; - break; - case CLOCK_MONOTONIC: - tk_offset = TK_OFFS_MAX; - break; - case CLOCK_BOOTTIME: - tk_offset = TK_OFFS_BOOT; - break; - case CLOCK_TAI: - tk_offset = TK_OFFS_TAI; - break; - default: - NL_SET_ERR_MSG(extack, "Invalid 'clockid'"); - goto release_idr; - } - } + gact = to_gate(*a); + if (ret == ACT_P_CREATED) + INIT_LIST_HEAD(&gact->param.entries); err = tcf_action_check_ctrlact(parm->action, tp, &goto_ch, extack); if (err < 0) goto release_idr; - gact = to_gate(*a); - spin_lock_bh(&gact->tcf_lock); p = &gact->param; - if (tb[TCA_GATE_CYCLE_TIME]) { - p->tcfg_cycletime = nla_get_u64(tb[TCA_GATE_CYCLE_TIME]); - if (!p->tcfg_cycletime_ext) - goto chain_put; - } + if (tb[TCA_GATE_CYCLE_TIME]) + cycletime = nla_get_u64(tb[TCA_GATE_CYCLE_TIME]); if (tb[TCA_GATE_ENTRY_LIST]) { err = parse_gate_list(tb[TCA_GATE_ENTRY_LIST], p, extack); @@ -387,35 +398,29 @@ static int tcf_gate_init(struct net *net, struct nlattr *nla, goto chain_put; } - if (!p->tcfg_cycletime) { + if (!cycletime) { struct tcfg_gate_entry *entry; ktime_t cycle = 0; list_for_each_entry(entry, &p->entries, list) cycle = ktime_add_ns(cycle, entry->interval); - p->tcfg_cycletime = cycle; + cycletime = cycle; + if (!cycletime) { + err = -EINVAL; + goto chain_put; + } } + p->tcfg_cycletime = cycletime; if (tb[TCA_GATE_CYCLE_TIME_EXT]) p->tcfg_cycletime_ext = nla_get_u64(tb[TCA_GATE_CYCLE_TIME_EXT]); + gate_setup_timer(gact, basetime, tk_offset, clockid, + ret == ACT_P_CREATED); p->tcfg_priority = prio; - p->tcfg_basetime = basetime; - p->tcfg_clockid = clockid; p->tcfg_flags = gflags; - - gact->tk_offset = tk_offset; - hrtimer_init(&gact->hitimer, clockid, HRTIMER_MODE_ABS_SOFT); - gact->hitimer.function = gate_timer_func; - - err = gate_get_start_time(gact, &start); - if (err < 0) { - NL_SET_ERR_MSG(extack, - "Internal error: failed get start time"); - release_entry_list(&p->entries); - goto chain_put; - } + gate_get_start_time(gact, &start); gact->current_close_time = start; gact->current_gate_status = GATE_ACT_GATE_OPEN | GATE_ACT_PENDING; @@ -443,6 +448,13 @@ chain_put: if (goto_ch) tcf_chain_put_by_act(goto_ch); release_idr: + /* action is not inserted in any list: it's safe to init hitimer + * without taking tcf_lock. + */ + if (ret == ACT_P_CREATED) + gate_setup_timer(gact, gact->param.tcfg_basetime, + gact->tk_offset, gact->param.tcfg_clockid, + true); tcf_idr_release(*a, bind); return err; } @@ -453,9 +465,7 @@ static void tcf_gate_cleanup(struct tc_action *a) struct tcf_gate_params *p; p = &gact->param; - if (p->tcfg_clockid != -1) - hrtimer_cancel(&gact->hitimer); - + hrtimer_cancel(&gact->hitimer); release_entry_list(&p->entries); } @@ -568,13 +578,13 @@ static int tcf_gate_walker(struct net *net, struct sk_buff *skb, return tcf_generic_walker(tn, skb, cb, type, ops, extack); } -static void tcf_gate_stats_update(struct tc_action *a, u64 bytes, u32 packets, - u64 lastuse, bool hw) +static void tcf_gate_stats_update(struct tc_action *a, u64 bytes, u64 packets, + u64 drops, u64 lastuse, bool hw) { struct tcf_gate *gact = to_gate(a); struct tcf_t *tm = &gact->tcf_tm; - tcf_action_update_stats(a, bytes, packets, false, hw); + tcf_action_update_stats(a, bytes, packets, drops, hw); tm->lastuse = max_t(u64, tm->lastuse, lastuse); } diff --git a/net/sched/act_mirred.c b/net/sched/act_mirred.c index 83dd82fc9f40..b2705318993b 100644 --- a/net/sched/act_mirred.c +++ b/net/sched/act_mirred.c @@ -312,13 +312,13 @@ out: return retval; } -static void tcf_stats_update(struct tc_action *a, u64 bytes, u32 packets, - u64 lastuse, bool hw) +static void tcf_stats_update(struct tc_action *a, u64 bytes, u64 packets, + u64 drops, u64 lastuse, bool hw) { struct tcf_mirred *m = to_mirred(a); struct tcf_t *tm = &m->tcf_tm; - tcf_action_update_stats(a, bytes, packets, false, hw); + tcf_action_update_stats(a, bytes, packets, drops, hw); tm->lastuse = max_t(u64, tm->lastuse, lastuse); } diff --git a/net/sched/act_pedit.c b/net/sched/act_pedit.c index d41d6200d9de..66986db062ed 100644 --- a/net/sched/act_pedit.c +++ b/net/sched/act_pedit.c @@ -409,13 +409,13 @@ done: return p->tcf_action; } -static void tcf_pedit_stats_update(struct tc_action *a, u64 bytes, u32 packets, - u64 lastuse, bool hw) +static void tcf_pedit_stats_update(struct tc_action *a, u64 bytes, u64 packets, + u64 drops, u64 lastuse, bool hw) { struct tcf_pedit *d = to_pedit(a); struct tcf_t *tm = &d->tcf_tm; - tcf_action_update_stats(a, bytes, packets, false, hw); + tcf_action_update_stats(a, bytes, packets, drops, hw); tm->lastuse = max_t(u64, tm->lastuse, lastuse); } diff --git a/net/sched/act_police.c b/net/sched/act_police.c index 8b7a0ac96c51..0b431d493768 100644 --- a/net/sched/act_police.c +++ b/net/sched/act_police.c @@ -288,13 +288,13 @@ static void tcf_police_cleanup(struct tc_action *a) } static void tcf_police_stats_update(struct tc_action *a, - u64 bytes, u32 packets, + u64 bytes, u64 packets, u64 drops, u64 lastuse, bool hw) { struct tcf_police *police = to_police(a); struct tcf_t *tm = &police->tcf_tm; - tcf_action_update_stats(a, bytes, packets, false, hw); + tcf_action_update_stats(a, bytes, packets, drops, hw); tm->lastuse = max_t(u64, tm->lastuse, lastuse); } diff --git a/net/sched/act_skbedit.c b/net/sched/act_skbedit.c index b125b2be4467..361b863e0634 100644 --- a/net/sched/act_skbedit.c +++ b/net/sched/act_skbedit.c @@ -74,12 +74,13 @@ err: } static void tcf_skbedit_stats_update(struct tc_action *a, u64 bytes, - u32 packets, u64 lastuse, bool hw) + u64 packets, u64 drops, + u64 lastuse, bool hw) { struct tcf_skbedit *d = to_skbedit(a); struct tcf_t *tm = &d->tcf_tm; - tcf_action_update_stats(a, bytes, packets, false, hw); + tcf_action_update_stats(a, bytes, packets, drops, hw); tm->lastuse = max_t(u64, tm->lastuse, lastuse); } diff --git a/net/sched/act_vlan.c b/net/sched/act_vlan.c index c91d3958fcbb..a5ff9f68ab02 100644 --- a/net/sched/act_vlan.c +++ b/net/sched/act_vlan.c @@ -302,13 +302,13 @@ static int tcf_vlan_walker(struct net *net, struct sk_buff *skb, return tcf_generic_walker(tn, skb, cb, type, ops, extack); } -static void tcf_vlan_stats_update(struct tc_action *a, u64 bytes, u32 packets, - u64 lastuse, bool hw) +static void tcf_vlan_stats_update(struct tc_action *a, u64 bytes, u64 packets, + u64 drops, u64 lastuse, bool hw) { struct tcf_vlan *v = to_vlan(a); struct tcf_t *tm = &v->tcf_tm; - tcf_action_update_stats(a, bytes, packets, false, hw); + tcf_action_update_stats(a, bytes, packets, drops, hw); tm->lastuse = max_t(u64, tm->lastuse, lastuse); } diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c index a00a203b2ef5..e9e119ea6813 100644 --- a/net/sched/cls_api.c +++ b/net/sched/cls_api.c @@ -652,6 +652,7 @@ static void tc_block_indr_cleanup(struct flow_block_cb *block_cb) &block->flow_block, tcf_block_shared(block), &extack); down_write(&block->cb_lock); + list_del(&block_cb->driver_list); list_move(&block_cb->list, &bo.cb_list); up_write(&block->cb_lock); rtnl_lock(); @@ -671,25 +672,29 @@ static int tcf_block_offload_cmd(struct tcf_block *block, struct netlink_ext_ack *extack) { struct flow_block_offload bo = {}; - int err; tcf_block_offload_init(&bo, dev, command, ei->binder_type, &block->flow_block, tcf_block_shared(block), extack); - if (dev->netdev_ops->ndo_setup_tc) + if (dev->netdev_ops->ndo_setup_tc) { + int err; + err = dev->netdev_ops->ndo_setup_tc(dev, TC_SETUP_BLOCK, &bo); - else - err = flow_indr_dev_setup_offload(dev, TC_SETUP_BLOCK, block, - &bo, tc_block_indr_cleanup); + if (err < 0) { + if (err != -EOPNOTSUPP) + NL_SET_ERR_MSG(extack, "Driver ndo_setup_tc failed"); + return err; + } - if (err < 0) { - if (err != -EOPNOTSUPP) - NL_SET_ERR_MSG(extack, "Driver ndo_setup_tc failed"); - return err; + return tcf_block_setup(block, &bo); } - return tcf_block_setup(block, &bo); + flow_indr_dev_setup_offload(dev, TC_SETUP_BLOCK, block, &bo, + tc_block_indr_cleanup); + tcf_block_setup(block, &bo); + + return -EOPNOTSUPP; } static int tcf_block_offload_bind(struct tcf_block *block, struct Qdisc *q, @@ -3655,9 +3660,11 @@ int tc_setup_flow_action(struct flow_action *flow_action, tcf_sample_get_group(entry, act); } else if (is_tcf_police(act)) { entry->id = FLOW_ACTION_POLICE; - entry->police.burst = tcf_police_tcfp_burst(act); + entry->police.burst = tcf_police_burst(act); entry->police.rate_bytes_ps = tcf_police_rate_bytes_ps(act); + entry->police.mtu = tcf_police_tcfp_mtu(act); + entry->police.index = act->tcfa_index; } else if (is_tcf_ct(act)) { entry->id = FLOW_ACTION_CT; entry->ct.action = tcf_ct_action(act); @@ -3741,6 +3748,125 @@ unsigned int tcf_exts_num_actions(struct tcf_exts *exts) } EXPORT_SYMBOL(tcf_exts_num_actions); +#ifdef CONFIG_NET_CLS_ACT +static int tcf_qevent_parse_block_index(struct nlattr *block_index_attr, + u32 *p_block_index, + struct netlink_ext_ack *extack) +{ + *p_block_index = nla_get_u32(block_index_attr); + if (!*p_block_index) { + NL_SET_ERR_MSG(extack, "Block number may not be zero"); + return -EINVAL; + } + + return 0; +} + +int tcf_qevent_init(struct tcf_qevent *qe, struct Qdisc *sch, + enum flow_block_binder_type binder_type, + struct nlattr *block_index_attr, + struct netlink_ext_ack *extack) +{ + u32 block_index; + int err; + + if (!block_index_attr) + return 0; + + err = tcf_qevent_parse_block_index(block_index_attr, &block_index, extack); + if (err) + return err; + + if (!block_index) + return 0; + + qe->info.binder_type = binder_type; + qe->info.chain_head_change = tcf_chain_head_change_dflt; + qe->info.chain_head_change_priv = &qe->filter_chain; + qe->info.block_index = block_index; + + return tcf_block_get_ext(&qe->block, sch, &qe->info, extack); +} +EXPORT_SYMBOL(tcf_qevent_init); + +void tcf_qevent_destroy(struct tcf_qevent *qe, struct Qdisc *sch) +{ + if (qe->info.block_index) + tcf_block_put_ext(qe->block, sch, &qe->info); +} +EXPORT_SYMBOL(tcf_qevent_destroy); + +int tcf_qevent_validate_change(struct tcf_qevent *qe, struct nlattr *block_index_attr, + struct netlink_ext_ack *extack) +{ + u32 block_index; + int err; + + if (!block_index_attr) + return 0; + + err = tcf_qevent_parse_block_index(block_index_attr, &block_index, extack); + if (err) + return err; + + /* Bounce newly-configured block or change in block. */ + if (block_index != qe->info.block_index) { + NL_SET_ERR_MSG(extack, "Change of blocks is not supported"); + return -EINVAL; + } + + return 0; +} +EXPORT_SYMBOL(tcf_qevent_validate_change); + +struct sk_buff *tcf_qevent_handle(struct tcf_qevent *qe, struct Qdisc *sch, struct sk_buff *skb, + spinlock_t *root_lock, struct sk_buff **to_free, int *ret) +{ + struct tcf_result cl_res; + struct tcf_proto *fl; + + if (!qe->info.block_index) + return skb; + + fl = rcu_dereference_bh(qe->filter_chain); + + if (root_lock) + spin_unlock(root_lock); + + switch (tcf_classify(skb, fl, &cl_res, false)) { + case TC_ACT_SHOT: + qdisc_qstats_drop(sch); + __qdisc_drop(skb, to_free); + *ret = __NET_XMIT_BYPASS; + return NULL; + case TC_ACT_STOLEN: + case TC_ACT_QUEUED: + case TC_ACT_TRAP: + __qdisc_drop(skb, to_free); + *ret = __NET_XMIT_STOLEN; + return NULL; + case TC_ACT_REDIRECT: + skb_do_redirect(skb); + *ret = __NET_XMIT_STOLEN; + return NULL; + } + + if (root_lock) + spin_lock(root_lock); + + return skb; +} +EXPORT_SYMBOL(tcf_qevent_handle); + +int tcf_qevent_dump(struct sk_buff *skb, int attr_name, struct tcf_qevent *qe) +{ + if (!qe->info.block_index) + return 0; + return nla_put_u32(skb, attr_name, qe->info.block_index); +} +EXPORT_SYMBOL(tcf_qevent_dump); +#endif + static __net_init int tcf_net_init(struct net *net) { struct tcf_net *tn = net_generic(net, tcf_net_id); diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c index b2da37286082..391971672d54 100644 --- a/net/sched/cls_flower.c +++ b/net/sched/cls_flower.c @@ -491,6 +491,7 @@ static void fl_hw_update_stats(struct tcf_proto *tp, struct cls_fl_filter *f, tcf_exts_stats_update(&f->exts, cls_flower.stats.bytes, cls_flower.stats.pkts, + cls_flower.stats.drops, cls_flower.stats.lastused, cls_flower.stats.used_hw_stats, cls_flower.stats.used_hw_stats_valid); diff --git a/net/sched/cls_matchall.c b/net/sched/cls_matchall.c index 8d39dbcf1746..cafb84480bab 100644 --- a/net/sched/cls_matchall.c +++ b/net/sched/cls_matchall.c @@ -338,7 +338,8 @@ static void mall_stats_hw_filter(struct tcf_proto *tp, tc_setup_cb_call(block, TC_SETUP_CLSMATCHALL, &cls_mall, false, true); tcf_exts_stats_update(&head->exts, cls_mall.stats.bytes, - cls_mall.stats.pkts, cls_mall.stats.lastused, + cls_mall.stats.pkts, cls_mall.stats.drops, + cls_mall.stats.lastused, cls_mall.stats.used_hw_stats, cls_mall.stats.used_hw_stats_valid); } diff --git a/net/sched/cls_tcindex.c b/net/sched/cls_tcindex.c index 61e95029c18f..78bec347b8b6 100644 --- a/net/sched/cls_tcindex.c +++ b/net/sched/cls_tcindex.c @@ -533,7 +533,7 @@ tcindex_change(struct net *net, struct sk_buff *in_skb, pr_debug("tcindex_change(tp %p,handle 0x%08x,tca %p,arg %p),opt %p," "p %p,r %p,*arg %p\n", - tp, handle, tca, arg, opt, p, r, arg ? *arg : NULL); + tp, handle, tca, arg, opt, p, r, *arg); if (!opt) return 0; diff --git a/net/sched/cls_u32.c b/net/sched/cls_u32.c index e15ff335953d..771b068f8254 100644 --- a/net/sched/cls_u32.c +++ b/net/sched/cls_u32.c @@ -796,9 +796,7 @@ static struct tc_u_knode *u32_init_knode(struct net *net, struct tcf_proto *tp, struct tc_u32_sel *s = &n->sel; struct tc_u_knode *new; - new = kzalloc(sizeof(*n) + s->nkeys*sizeof(struct tc_u32_key), - GFP_KERNEL); - + new = kzalloc(struct_size(new, sel.keys, s->nkeys), GFP_KERNEL); if (!new) return NULL; diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c index 9a3449b56bd6..11ebba60da3b 100644 --- a/net/sched/sch_api.c +++ b/net/sched/sch_api.c @@ -1093,8 +1093,7 @@ skip: int err; /* Only support running class lockless if parent is lockless */ - if (new && (new->flags & TCQ_F_NOLOCK) && - parent && !(parent->flags & TCQ_F_NOLOCK)) + if (new && (new->flags & TCQ_F_NOLOCK) && !(parent->flags & TCQ_F_NOLOCK)) qdisc_clear_nolock(new); if (!cops || !cops->graft) diff --git a/net/sched/sch_atm.c b/net/sched/sch_atm.c index ee12ca9f55b4..fb6b16c4e46d 100644 --- a/net/sched/sch_atm.c +++ b/net/sched/sch_atm.c @@ -374,7 +374,7 @@ static struct tcf_block *atm_tc_tcf_block(struct Qdisc *sch, unsigned long cl, /* --------------------------- Qdisc operations ---------------------------- */ -static int atm_tc_enqueue(struct sk_buff *skb, struct Qdisc *sch, +static int atm_tc_enqueue(struct sk_buff *skb, struct Qdisc *sch, spinlock_t *root_lock, struct sk_buff **to_free) { struct atm_qdisc_data *p = qdisc_priv(sch); @@ -432,7 +432,7 @@ done: #endif } - ret = qdisc_enqueue(skb, flow->q, to_free); + ret = qdisc_enqueue(skb, flow->q, root_lock, to_free); if (ret != NET_XMIT_SUCCESS) { drop: __maybe_unused if (net_xmit_drop_count(ret)) { diff --git a/net/sched/sch_blackhole.c b/net/sched/sch_blackhole.c index a7f7667ae984..187644657c4f 100644 --- a/net/sched/sch_blackhole.c +++ b/net/sched/sch_blackhole.c @@ -13,7 +13,7 @@ #include <linux/skbuff.h> #include <net/pkt_sched.h> -static int blackhole_enqueue(struct sk_buff *skb, struct Qdisc *sch, +static int blackhole_enqueue(struct sk_buff *skb, struct Qdisc *sch, spinlock_t *root_lock, struct sk_buff **to_free) { qdisc_drop(skb, sch, to_free); diff --git a/net/sched/sch_cake.c b/net/sched/sch_cake.c index 60f8ae578819..e9c502dd29a2 100644 --- a/net/sched/sch_cake.c +++ b/net/sched/sch_cake.c @@ -312,8 +312,8 @@ static const u8 precedence[] = { }; static const u8 diffserv8[] = { - 2, 5, 1, 2, 4, 2, 2, 2, - 0, 2, 1, 2, 1, 2, 1, 2, + 2, 0, 1, 2, 4, 2, 2, 2, + 1, 2, 1, 2, 1, 2, 1, 2, 5, 2, 4, 2, 4, 2, 4, 2, 3, 2, 3, 2, 3, 2, 3, 2, 6, 2, 3, 2, 3, 2, 3, 2, @@ -323,7 +323,7 @@ static const u8 diffserv8[] = { }; static const u8 diffserv4[] = { - 0, 2, 0, 0, 2, 0, 0, 0, + 0, 1, 0, 0, 2, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 2, 0, 2, 0, 2, 0, 2, 0, 2, 0, 2, 0, 2, 0, 2, 0, @@ -334,7 +334,7 @@ static const u8 diffserv4[] = { }; static const u8 diffserv3[] = { - 0, 0, 0, 0, 2, 0, 0, 0, + 0, 1, 0, 0, 2, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, @@ -1551,32 +1551,51 @@ static unsigned int cake_drop(struct Qdisc *sch, struct sk_buff **to_free) return idx + (tin << 16); } -static u8 cake_handle_diffserv(struct sk_buff *skb, u16 wash) +static u8 cake_handle_diffserv(struct sk_buff *skb, bool wash) { - int wlen = skb_network_offset(skb); + const int offset = skb_network_offset(skb); + u16 *buf, buf_; u8 dscp; switch (tc_skb_protocol(skb)) { case htons(ETH_P_IP): - wlen += sizeof(struct iphdr); - if (!pskb_may_pull(skb, wlen) || - skb_try_make_writable(skb, wlen)) + buf = skb_header_pointer(skb, offset, sizeof(buf_), &buf_); + if (unlikely(!buf)) return 0; - dscp = ipv4_get_dsfield(ip_hdr(skb)) >> 2; - if (wash && dscp) + /* ToS is in the second byte of iphdr */ + dscp = ipv4_get_dsfield((struct iphdr *)buf) >> 2; + + if (wash && dscp) { + const int wlen = offset + sizeof(struct iphdr); + + if (!pskb_may_pull(skb, wlen) || + skb_try_make_writable(skb, wlen)) + return 0; + ipv4_change_dsfield(ip_hdr(skb), INET_ECN_MASK, 0); + } + return dscp; case htons(ETH_P_IPV6): - wlen += sizeof(struct ipv6hdr); - if (!pskb_may_pull(skb, wlen) || - skb_try_make_writable(skb, wlen)) + buf = skb_header_pointer(skb, offset, sizeof(buf_), &buf_); + if (unlikely(!buf)) return 0; - dscp = ipv6_get_dsfield(ipv6_hdr(skb)) >> 2; - if (wash && dscp) + /* Traffic class is in the first and second bytes of ipv6hdr */ + dscp = ipv6_get_dsfield((struct ipv6hdr *)buf) >> 2; + + if (wash && dscp) { + const int wlen = offset + sizeof(struct ipv6hdr); + + if (!pskb_may_pull(skb, wlen) || + skb_try_make_writable(skb, wlen)) + return 0; + ipv6_change_dsfield(ipv6_hdr(skb), INET_ECN_MASK, 0); + } + return dscp; case htons(ETH_P_ARP): @@ -1593,14 +1612,17 @@ static struct cake_tin_data *cake_select_tin(struct Qdisc *sch, { struct cake_sched_data *q = qdisc_priv(sch); u32 tin, mark; + bool wash; u8 dscp; /* Tin selection: Default to diffserv-based selection, allow overriding - * using firewall marks or skb->priority. + * using firewall marks or skb->priority. Call DSCP parsing early if + * wash is enabled, otherwise defer to below to skip unneeded parsing. */ - dscp = cake_handle_diffserv(skb, - q->rate_flags & CAKE_FLAG_WASH); mark = (skb->mark & q->fwmark_mask) >> q->fwmark_shft; + wash = !!(q->rate_flags & CAKE_FLAG_WASH); + if (wash) + dscp = cake_handle_diffserv(skb, wash); if (q->tin_mode == CAKE_DIFFSERV_BESTEFFORT) tin = 0; @@ -1614,6 +1636,8 @@ static struct cake_tin_data *cake_select_tin(struct Qdisc *sch, tin = q->tin_order[TC_H_MIN(skb->priority) - 1]; else { + if (!wash) + dscp = cake_handle_diffserv(skb, wash); tin = q->tin_index[dscp]; if (unlikely(tin >= q->tin_cnt)) @@ -1663,7 +1687,7 @@ hash: static void cake_reconfigure(struct Qdisc *sch); -static s32 cake_enqueue(struct sk_buff *skb, struct Qdisc *sch, +static s32 cake_enqueue(struct sk_buff *skb, struct Qdisc *sch, spinlock_t *root_lock, struct sk_buff **to_free) { struct cake_sched_data *q = qdisc_priv(sch); @@ -2691,7 +2715,7 @@ static int cake_init(struct Qdisc *sch, struct nlattr *opt, qdisc_watchdog_init(&q->watchdog, sch); if (opt) { - int err = cake_change(sch, opt, extack); + err = cake_change(sch, opt, extack); if (err) return err; @@ -3008,7 +3032,7 @@ static int cake_dump_class_stats(struct Qdisc *sch, unsigned long cl, PUT_STAT_S32(BLUE_TIMER_US, ktime_to_us( ktime_sub(now, - flow->cvars.blue_timer))); + flow->cvars.blue_timer))); } if (flow->cvars.dropping) { PUT_STAT_S32(DROP_NEXT_US, diff --git a/net/sched/sch_cbq.c b/net/sched/sch_cbq.c index 39b427dc7512..052d4a1af69a 100644 --- a/net/sched/sch_cbq.c +++ b/net/sched/sch_cbq.c @@ -356,7 +356,7 @@ cbq_mark_toplevel(struct cbq_sched_data *q, struct cbq_class *cl) } static int -cbq_enqueue(struct sk_buff *skb, struct Qdisc *sch, +cbq_enqueue(struct sk_buff *skb, struct Qdisc *sch, spinlock_t *root_lock, struct sk_buff **to_free) { struct cbq_sched_data *q = qdisc_priv(sch); @@ -373,7 +373,7 @@ cbq_enqueue(struct sk_buff *skb, struct Qdisc *sch, return ret; } - ret = qdisc_enqueue(skb, cl->q, to_free); + ret = qdisc_enqueue(skb, cl->q, root_lock, to_free); if (ret == NET_XMIT_SUCCESS) { sch->q.qlen++; cbq_mark_toplevel(q, cl); diff --git a/net/sched/sch_cbs.c b/net/sched/sch_cbs.c index 2eaac2ff380f..7af15ebe07f7 100644 --- a/net/sched/sch_cbs.c +++ b/net/sched/sch_cbs.c @@ -77,7 +77,7 @@ struct cbs_sched_data { s64 sendslope; /* in bytes/s */ s64 idleslope; /* in bytes/s */ struct qdisc_watchdog watchdog; - int (*enqueue)(struct sk_buff *skb, struct Qdisc *sch, + int (*enqueue)(struct sk_buff *skb, struct Qdisc *sch, spinlock_t *root_lock, struct sk_buff **to_free); struct sk_buff *(*dequeue)(struct Qdisc *sch); struct Qdisc *qdisc; @@ -85,13 +85,13 @@ struct cbs_sched_data { }; static int cbs_child_enqueue(struct sk_buff *skb, struct Qdisc *sch, - struct Qdisc *child, + struct Qdisc *child, spinlock_t *root_lock, struct sk_buff **to_free) { unsigned int len = qdisc_pkt_len(skb); int err; - err = child->ops->enqueue(skb, child, to_free); + err = child->ops->enqueue(skb, child, root_lock, to_free); if (err != NET_XMIT_SUCCESS) return err; @@ -101,16 +101,16 @@ static int cbs_child_enqueue(struct sk_buff *skb, struct Qdisc *sch, return NET_XMIT_SUCCESS; } -static int cbs_enqueue_offload(struct sk_buff *skb, struct Qdisc *sch, +static int cbs_enqueue_offload(struct sk_buff *skb, struct Qdisc *sch, spinlock_t *root_lock, struct sk_buff **to_free) { struct cbs_sched_data *q = qdisc_priv(sch); struct Qdisc *qdisc = q->qdisc; - return cbs_child_enqueue(skb, sch, qdisc, to_free); + return cbs_child_enqueue(skb, sch, qdisc, root_lock, to_free); } -static int cbs_enqueue_soft(struct sk_buff *skb, struct Qdisc *sch, +static int cbs_enqueue_soft(struct sk_buff *skb, struct Qdisc *sch, spinlock_t *root_lock, struct sk_buff **to_free) { struct cbs_sched_data *q = qdisc_priv(sch); @@ -124,15 +124,15 @@ static int cbs_enqueue_soft(struct sk_buff *skb, struct Qdisc *sch, q->last = ktime_get_ns(); } - return cbs_child_enqueue(skb, sch, qdisc, to_free); + return cbs_child_enqueue(skb, sch, qdisc, root_lock, to_free); } -static int cbs_enqueue(struct sk_buff *skb, struct Qdisc *sch, +static int cbs_enqueue(struct sk_buff *skb, struct Qdisc *sch, spinlock_t *root_lock, struct sk_buff **to_free) { struct cbs_sched_data *q = qdisc_priv(sch); - return q->enqueue(skb, sch, to_free); + return q->enqueue(skb, sch, root_lock, to_free); } /* timediff is in ns, slope is in bytes/s */ diff --git a/net/sched/sch_choke.c b/net/sched/sch_choke.c index bd618b00d319..baf3faee31aa 100644 --- a/net/sched/sch_choke.c +++ b/net/sched/sch_choke.c @@ -210,7 +210,7 @@ static bool choke_match_random(const struct choke_sched_data *q, return choke_match_flow(oskb, nskb); } -static int choke_enqueue(struct sk_buff *skb, struct Qdisc *sch, +static int choke_enqueue(struct sk_buff *skb, struct Qdisc *sch, spinlock_t *root_lock, struct sk_buff **to_free) { struct choke_sched_data *q = qdisc_priv(sch); diff --git a/net/sched/sch_codel.c b/net/sched/sch_codel.c index 30169b3adbbb..1d94837abdd8 100644 --- a/net/sched/sch_codel.c +++ b/net/sched/sch_codel.c @@ -108,7 +108,7 @@ static struct sk_buff *codel_qdisc_dequeue(struct Qdisc *sch) return skb; } -static int codel_qdisc_enqueue(struct sk_buff *skb, struct Qdisc *sch, +static int codel_qdisc_enqueue(struct sk_buff *skb, struct Qdisc *sch, spinlock_t *root_lock, struct sk_buff **to_free) { struct codel_sched_data *q; diff --git a/net/sched/sch_drr.c b/net/sched/sch_drr.c index 07a2b0b35495..0d5c9a8ec61d 100644 --- a/net/sched/sch_drr.c +++ b/net/sched/sch_drr.c @@ -337,7 +337,7 @@ static struct drr_class *drr_classify(struct sk_buff *skb, struct Qdisc *sch, return NULL; } -static int drr_enqueue(struct sk_buff *skb, struct Qdisc *sch, +static int drr_enqueue(struct sk_buff *skb, struct Qdisc *sch, spinlock_t *root_lock, struct sk_buff **to_free) { unsigned int len = qdisc_pkt_len(skb); @@ -355,7 +355,7 @@ static int drr_enqueue(struct sk_buff *skb, struct Qdisc *sch, } first = !cl->qdisc->q.qlen; - err = qdisc_enqueue(skb, cl->qdisc, to_free); + err = qdisc_enqueue(skb, cl->qdisc, root_lock, to_free); if (unlikely(err != NET_XMIT_SUCCESS)) { if (net_xmit_drop_count(err)) { cl->qstats.drops++; diff --git a/net/sched/sch_dsmark.c b/net/sched/sch_dsmark.c index 05605b30bef3..fbe49fffcdbb 100644 --- a/net/sched/sch_dsmark.c +++ b/net/sched/sch_dsmark.c @@ -198,7 +198,7 @@ static struct tcf_block *dsmark_tcf_block(struct Qdisc *sch, unsigned long cl, /* --------------------------- Qdisc operations ---------------------------- */ -static int dsmark_enqueue(struct sk_buff *skb, struct Qdisc *sch, +static int dsmark_enqueue(struct sk_buff *skb, struct Qdisc *sch, spinlock_t *root_lock, struct sk_buff **to_free) { unsigned int len = qdisc_pkt_len(skb); @@ -267,7 +267,7 @@ static int dsmark_enqueue(struct sk_buff *skb, struct Qdisc *sch, } } - err = qdisc_enqueue(skb, p->q, to_free); + err = qdisc_enqueue(skb, p->q, root_lock, to_free); if (err != NET_XMIT_SUCCESS) { if (net_xmit_drop_count(err)) qdisc_qstats_drop(sch); diff --git a/net/sched/sch_etf.c b/net/sched/sch_etf.c index c48f91075b5c..7a7c50a68115 100644 --- a/net/sched/sch_etf.c +++ b/net/sched/sch_etf.c @@ -160,7 +160,7 @@ static void report_sock_error(struct sk_buff *skb, u32 err, u8 code) } static int etf_enqueue_timesortedlist(struct sk_buff *nskb, struct Qdisc *sch, - struct sk_buff **to_free) + spinlock_t *root_lock, struct sk_buff **to_free) { struct etf_sched_data *q = qdisc_priv(sch); struct rb_node **p = &q->head.rb_root.rb_node, *parent = NULL; diff --git a/net/sched/sch_ets.c b/net/sched/sch_ets.c index a87e9159338c..373dc5855d4e 100644 --- a/net/sched/sch_ets.c +++ b/net/sched/sch_ets.c @@ -415,7 +415,7 @@ static struct ets_class *ets_classify(struct sk_buff *skb, struct Qdisc *sch, return &q->classes[band]; } -static int ets_qdisc_enqueue(struct sk_buff *skb, struct Qdisc *sch, +static int ets_qdisc_enqueue(struct sk_buff *skb, struct Qdisc *sch, spinlock_t *root_lock, struct sk_buff **to_free) { unsigned int len = qdisc_pkt_len(skb); @@ -433,7 +433,7 @@ static int ets_qdisc_enqueue(struct sk_buff *skb, struct Qdisc *sch, } first = !cl->qdisc->q.qlen; - err = qdisc_enqueue(skb, cl->qdisc, to_free); + err = qdisc_enqueue(skb, cl->qdisc, root_lock, to_free); if (unlikely(err != NET_XMIT_SUCCESS)) { if (net_xmit_drop_count(err)) { cl->qstats.drops++; diff --git a/net/sched/sch_fifo.c b/net/sched/sch_fifo.c index a579a4131d22..b4da5b624ad8 100644 --- a/net/sched/sch_fifo.c +++ b/net/sched/sch_fifo.c @@ -16,7 +16,7 @@ /* 1 band FIFO pseudo-"scheduler" */ -static int bfifo_enqueue(struct sk_buff *skb, struct Qdisc *sch, +static int bfifo_enqueue(struct sk_buff *skb, struct Qdisc *sch, spinlock_t *root_lock, struct sk_buff **to_free) { if (likely(sch->qstats.backlog + qdisc_pkt_len(skb) <= sch->limit)) @@ -25,7 +25,7 @@ static int bfifo_enqueue(struct sk_buff *skb, struct Qdisc *sch, return qdisc_drop(skb, sch, to_free); } -static int pfifo_enqueue(struct sk_buff *skb, struct Qdisc *sch, +static int pfifo_enqueue(struct sk_buff *skb, struct Qdisc *sch, spinlock_t *root_lock, struct sk_buff **to_free) { if (likely(sch->q.qlen < sch->limit)) @@ -34,7 +34,7 @@ static int pfifo_enqueue(struct sk_buff *skb, struct Qdisc *sch, return qdisc_drop(skb, sch, to_free); } -static int pfifo_tail_enqueue(struct sk_buff *skb, struct Qdisc *sch, +static int pfifo_tail_enqueue(struct sk_buff *skb, struct Qdisc *sch, spinlock_t *root_lock, struct sk_buff **to_free) { unsigned int prev_backlog; diff --git a/net/sched/sch_fq.c b/net/sched/sch_fq.c index 8f06a808c59a..a90d745c41e0 100644 --- a/net/sched/sch_fq.c +++ b/net/sched/sch_fq.c @@ -439,7 +439,7 @@ static bool fq_packet_beyond_horizon(const struct sk_buff *skb, return unlikely((s64)skb->tstamp > (s64)(q->ktime_cache + q->horizon)); } -static int fq_enqueue(struct sk_buff *skb, struct Qdisc *sch, +static int fq_enqueue(struct sk_buff *skb, struct Qdisc *sch, spinlock_t *root_lock, struct sk_buff **to_free) { struct fq_sched_data *q = qdisc_priv(sch); @@ -1075,3 +1075,4 @@ module_init(fq_module_init) module_exit(fq_module_exit) MODULE_AUTHOR("Eric Dumazet"); MODULE_LICENSE("GPL"); +MODULE_DESCRIPTION("Fair Queue Packet Scheduler"); diff --git a/net/sched/sch_fq_codel.c b/net/sched/sch_fq_codel.c index 436160be9c18..6bf979f95509 100644 --- a/net/sched/sch_fq_codel.c +++ b/net/sched/sch_fq_codel.c @@ -181,7 +181,7 @@ static unsigned int fq_codel_drop(struct Qdisc *sch, unsigned int max_packets, return idx; } -static int fq_codel_enqueue(struct sk_buff *skb, struct Qdisc *sch, +static int fq_codel_enqueue(struct sk_buff *skb, struct Qdisc *sch, spinlock_t *root_lock, struct sk_buff **to_free) { struct fq_codel_sched_data *q = qdisc_priv(sch); @@ -721,3 +721,4 @@ module_init(fq_codel_module_init) module_exit(fq_codel_module_exit) MODULE_AUTHOR("Eric Dumazet"); MODULE_LICENSE("GPL"); +MODULE_DESCRIPTION("Fair Queue CoDel discipline"); diff --git a/net/sched/sch_fq_pie.c b/net/sched/sch_fq_pie.c index fb760cee824e..a27a250ab8f9 100644 --- a/net/sched/sch_fq_pie.c +++ b/net/sched/sch_fq_pie.c @@ -125,7 +125,7 @@ static inline void flow_queue_add(struct fq_pie_flow *flow, skb->next = NULL; } -static int fq_pie_qdisc_enqueue(struct sk_buff *skb, struct Qdisc *sch, +static int fq_pie_qdisc_enqueue(struct sk_buff *skb, struct Qdisc *sch, spinlock_t *root_lock, struct sk_buff **to_free) { struct fq_pie_sched_data *q = qdisc_priv(sch); diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c index 265a61d011df..715cde1df9e4 100644 --- a/net/sched/sch_generic.c +++ b/net/sched/sch_generic.c @@ -520,7 +520,7 @@ EXPORT_SYMBOL(netif_carrier_off); cheaper. */ -static int noop_enqueue(struct sk_buff *skb, struct Qdisc *qdisc, +static int noop_enqueue(struct sk_buff *skb, struct Qdisc *qdisc, spinlock_t *root_lock, struct sk_buff **to_free) { __qdisc_drop(skb, to_free); @@ -614,7 +614,7 @@ static inline struct skb_array *band2list(struct pfifo_fast_priv *priv, return &priv->q[band]; } -static int pfifo_fast_enqueue(struct sk_buff *skb, struct Qdisc *qdisc, +static int pfifo_fast_enqueue(struct sk_buff *skb, struct Qdisc *qdisc, spinlock_t *root_lock, struct sk_buff **to_free) { int band = prio2band[skb->priority & TC_PRIO_MAX]; diff --git a/net/sched/sch_gred.c b/net/sched/sch_gred.c index 8599c6f31b05..7d67c6cd6605 100644 --- a/net/sched/sch_gred.c +++ b/net/sched/sch_gred.c @@ -161,7 +161,7 @@ static bool gred_per_vq_red_flags_used(struct gred_sched *table) return false; } -static int gred_enqueue(struct sk_buff *skb, struct Qdisc *sch, +static int gred_enqueue(struct sk_buff *skb, struct Qdisc *sch, spinlock_t *root_lock, struct sk_buff **to_free) { struct gred_sched_data *q = NULL; diff --git a/net/sched/sch_hfsc.c b/net/sched/sch_hfsc.c index 433f2190960f..7f6670044f0a 100644 --- a/net/sched/sch_hfsc.c +++ b/net/sched/sch_hfsc.c @@ -1528,8 +1528,8 @@ hfsc_dump_qdisc(struct Qdisc *sch, struct sk_buff *skb) return -1; } -static int -hfsc_enqueue(struct sk_buff *skb, struct Qdisc *sch, struct sk_buff **to_free) +static int hfsc_enqueue(struct sk_buff *skb, struct Qdisc *sch, spinlock_t *root_lock, + struct sk_buff **to_free) { unsigned int len = qdisc_pkt_len(skb); struct hfsc_class *cl; @@ -1545,7 +1545,7 @@ hfsc_enqueue(struct sk_buff *skb, struct Qdisc *sch, struct sk_buff **to_free) } first = !cl->qdisc->q.qlen; - err = qdisc_enqueue(skb, cl->qdisc, to_free); + err = qdisc_enqueue(skb, cl->qdisc, root_lock, to_free); if (unlikely(err != NET_XMIT_SUCCESS)) { if (net_xmit_drop_count(err)) { cl->qstats.drops++; diff --git a/net/sched/sch_hhf.c b/net/sched/sch_hhf.c index be35f03b657b..ddc6bf1d85d0 100644 --- a/net/sched/sch_hhf.c +++ b/net/sched/sch_hhf.c @@ -368,7 +368,7 @@ static unsigned int hhf_drop(struct Qdisc *sch, struct sk_buff **to_free) return bucket - q->buckets; } -static int hhf_enqueue(struct sk_buff *skb, struct Qdisc *sch, +static int hhf_enqueue(struct sk_buff *skb, struct Qdisc *sch, spinlock_t *root_lock, struct sk_buff **to_free) { struct hhf_sched_data *q = qdisc_priv(sch); @@ -721,3 +721,4 @@ module_exit(hhf_module_exit) MODULE_AUTHOR("Terry Lam"); MODULE_AUTHOR("Nandita Dukkipati"); MODULE_LICENSE("GPL"); +MODULE_DESCRIPTION("Heavy-Hitter Filter (HHF)"); diff --git a/net/sched/sch_htb.c b/net/sched/sch_htb.c index 8184c87da8be..52fc513688b1 100644 --- a/net/sched/sch_htb.c +++ b/net/sched/sch_htb.c @@ -576,7 +576,7 @@ static inline void htb_deactivate(struct htb_sched *q, struct htb_class *cl) cl->prio_activity = 0; } -static int htb_enqueue(struct sk_buff *skb, struct Qdisc *sch, +static int htb_enqueue(struct sk_buff *skb, struct Qdisc *sch, spinlock_t *root_lock, struct sk_buff **to_free) { int uninitialized_var(ret); @@ -599,7 +599,7 @@ static int htb_enqueue(struct sk_buff *skb, struct Qdisc *sch, __qdisc_drop(skb, to_free); return ret; #endif - } else if ((ret = qdisc_enqueue(skb, cl->leaf.q, + } else if ((ret = qdisc_enqueue(skb, cl->leaf.q, root_lock, to_free)) != NET_XMIT_SUCCESS) { if (net_xmit_drop_count(ret)) { qdisc_qstats_drop(sch); diff --git a/net/sched/sch_multiq.c b/net/sched/sch_multiq.c index 1330ad224931..648611f5c105 100644 --- a/net/sched/sch_multiq.c +++ b/net/sched/sch_multiq.c @@ -57,7 +57,7 @@ multiq_classify(struct sk_buff *skb, struct Qdisc *sch, int *qerr) } static int -multiq_enqueue(struct sk_buff *skb, struct Qdisc *sch, +multiq_enqueue(struct sk_buff *skb, struct Qdisc *sch, spinlock_t *root_lock, struct sk_buff **to_free) { struct Qdisc *qdisc; @@ -74,7 +74,7 @@ multiq_enqueue(struct sk_buff *skb, struct Qdisc *sch, } #endif - ret = qdisc_enqueue(skb, qdisc, to_free); + ret = qdisc_enqueue(skb, qdisc, root_lock, to_free); if (ret == NET_XMIT_SUCCESS) { sch->q.qlen++; return NET_XMIT_SUCCESS; diff --git a/net/sched/sch_netem.c b/net/sched/sch_netem.c index 84f82771cdf5..8fb17483a34f 100644 --- a/net/sched/sch_netem.c +++ b/net/sched/sch_netem.c @@ -431,7 +431,7 @@ static struct sk_buff *netem_segment(struct sk_buff *skb, struct Qdisc *sch, * NET_XMIT_DROP: queue length didn't change. * NET_XMIT_SUCCESS: one skb was queued. */ -static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch, +static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch, spinlock_t *root_lock, struct sk_buff **to_free) { struct netem_sched_data *q = qdisc_priv(sch); @@ -480,7 +480,7 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch, u32 dupsave = q->duplicate; /* prevent duplicating a dup... */ q->duplicate = 0; - rootq->enqueue(skb2, rootq, to_free); + rootq->enqueue(skb2, rootq, root_lock, to_free); q->duplicate = dupsave; rc_drop = NET_XMIT_SUCCESS; } @@ -604,7 +604,7 @@ finish_segs: skb_mark_not_on_list(segs); qdisc_skb_cb(segs)->pkt_len = segs->len; last_len = segs->len; - rc = qdisc_enqueue(segs, sch, to_free); + rc = qdisc_enqueue(segs, sch, root_lock, to_free); if (rc != NET_XMIT_SUCCESS) { if (net_xmit_drop_count(rc)) qdisc_qstats_drop(sch); @@ -720,7 +720,7 @@ deliver: struct sk_buff *to_free = NULL; int err; - err = qdisc_enqueue(skb, q->qdisc, &to_free); + err = qdisc_enqueue(skb, q->qdisc, NULL, &to_free); kfree_skb_list(to_free); if (err != NET_XMIT_SUCCESS && net_xmit_drop_count(err)) { diff --git a/net/sched/sch_pie.c b/net/sched/sch_pie.c index c65077f0c0f3..b305313b64e3 100644 --- a/net/sched/sch_pie.c +++ b/net/sched/sch_pie.c @@ -82,7 +82,7 @@ bool pie_drop_early(struct Qdisc *sch, struct pie_params *params, } EXPORT_SYMBOL_GPL(pie_drop_early); -static int pie_qdisc_enqueue(struct sk_buff *skb, struct Qdisc *sch, +static int pie_qdisc_enqueue(struct sk_buff *skb, struct Qdisc *sch, spinlock_t *root_lock, struct sk_buff **to_free) { struct pie_sched_data *q = qdisc_priv(sch); diff --git a/net/sched/sch_plug.c b/net/sched/sch_plug.c index cbc2ebca4548..e5f8b4769b4d 100644 --- a/net/sched/sch_plug.c +++ b/net/sched/sch_plug.c @@ -84,7 +84,7 @@ struct plug_sched_data { u32 pkts_to_release; }; -static int plug_enqueue(struct sk_buff *skb, struct Qdisc *sch, +static int plug_enqueue(struct sk_buff *skb, struct Qdisc *sch, spinlock_t *root_lock, struct sk_buff **to_free) { struct plug_sched_data *q = qdisc_priv(sch); diff --git a/net/sched/sch_prio.c b/net/sched/sch_prio.c index 647941702f9f..a3e187f2603c 100644 --- a/net/sched/sch_prio.c +++ b/net/sched/sch_prio.c @@ -65,8 +65,8 @@ prio_classify(struct sk_buff *skb, struct Qdisc *sch, int *qerr) return q->queues[band]; } -static int -prio_enqueue(struct sk_buff *skb, struct Qdisc *sch, struct sk_buff **to_free) +static int prio_enqueue(struct sk_buff *skb, struct Qdisc *sch, spinlock_t *root_lock, + struct sk_buff **to_free) { unsigned int len = qdisc_pkt_len(skb); struct Qdisc *qdisc; @@ -83,7 +83,7 @@ prio_enqueue(struct sk_buff *skb, struct Qdisc *sch, struct sk_buff **to_free) } #endif - ret = qdisc_enqueue(skb, qdisc, to_free); + ret = qdisc_enqueue(skb, qdisc, root_lock, to_free); if (ret == NET_XMIT_SUCCESS) { sch->qstats.backlog += len; sch->q.qlen++; diff --git a/net/sched/sch_qfq.c b/net/sched/sch_qfq.c index 0b05ac7c848e..ede854516825 100644 --- a/net/sched/sch_qfq.c +++ b/net/sched/sch_qfq.c @@ -1194,7 +1194,7 @@ static struct qfq_aggregate *qfq_choose_next_agg(struct qfq_sched *q) return agg; } -static int qfq_enqueue(struct sk_buff *skb, struct Qdisc *sch, +static int qfq_enqueue(struct sk_buff *skb, struct Qdisc *sch, spinlock_t *root_lock, struct sk_buff **to_free) { unsigned int len = qdisc_pkt_len(skb), gso_segs; @@ -1225,7 +1225,7 @@ static int qfq_enqueue(struct sk_buff *skb, struct Qdisc *sch, gso_segs = skb_is_gso(skb) ? skb_shinfo(skb)->gso_segs : 1; first = !cl->qdisc->q.qlen; - err = qdisc_enqueue(skb, cl->qdisc, to_free); + err = qdisc_enqueue(skb, cl->qdisc, root_lock, to_free); if (unlikely(err != NET_XMIT_SUCCESS)) { pr_debug("qfq_enqueue: enqueue failed %d\n", err); if (net_xmit_drop_count(err)) { diff --git a/net/sched/sch_red.c b/net/sched/sch_red.c index 555a1b9e467f..de2be4d04ed6 100644 --- a/net/sched/sch_red.c +++ b/net/sched/sch_red.c @@ -46,6 +46,8 @@ struct red_sched_data { struct red_vars vars; struct red_stats stats; struct Qdisc *qdisc; + struct tcf_qevent qe_early_drop; + struct tcf_qevent qe_mark; }; #define TC_RED_SUPPORTED_FLAGS (TC_RED_HISTORIC_FLAGS | TC_RED_NODROP) @@ -65,7 +67,7 @@ static int red_use_nodrop(struct red_sched_data *q) return q->flags & TC_RED_NODROP; } -static int red_enqueue(struct sk_buff *skb, struct Qdisc *sch, +static int red_enqueue(struct sk_buff *skb, struct Qdisc *sch, spinlock_t *root_lock, struct sk_buff **to_free) { struct red_sched_data *q = qdisc_priv(sch); @@ -92,6 +94,9 @@ static int red_enqueue(struct sk_buff *skb, struct Qdisc *sch, if (INET_ECN_set_ce(skb)) { q->stats.prob_mark++; + skb = tcf_qevent_handle(&q->qe_mark, sch, skb, root_lock, to_free, &ret); + if (!skb) + return NET_XMIT_CN | ret; } else if (!red_use_nodrop(q)) { q->stats.prob_drop++; goto congestion_drop; @@ -109,6 +114,9 @@ static int red_enqueue(struct sk_buff *skb, struct Qdisc *sch, if (INET_ECN_set_ce(skb)) { q->stats.forced_mark++; + skb = tcf_qevent_handle(&q->qe_mark, sch, skb, root_lock, to_free, &ret); + if (!skb) + return NET_XMIT_CN | ret; } else if (!red_use_nodrop(q)) { q->stats.forced_drop++; goto congestion_drop; @@ -118,7 +126,7 @@ static int red_enqueue(struct sk_buff *skb, struct Qdisc *sch, break; } - ret = qdisc_enqueue(skb, child, to_free); + ret = qdisc_enqueue(skb, child, root_lock, to_free); if (likely(ret == NET_XMIT_SUCCESS)) { qdisc_qstats_backlog_inc(sch, skb); sch->q.qlen++; @@ -129,6 +137,10 @@ static int red_enqueue(struct sk_buff *skb, struct Qdisc *sch, return ret; congestion_drop: + skb = tcf_qevent_handle(&q->qe_early_drop, sch, skb, root_lock, to_free, &ret); + if (!skb) + return NET_XMIT_CN | ret; + qdisc_drop(skb, sch, to_free); return NET_XMIT_CN; } @@ -202,6 +214,8 @@ static void red_destroy(struct Qdisc *sch) { struct red_sched_data *q = qdisc_priv(sch); + tcf_qevent_destroy(&q->qe_mark, sch); + tcf_qevent_destroy(&q->qe_early_drop, sch); del_timer_sync(&q->adapt_timer); red_offload(sch, false); qdisc_put(q->qdisc); @@ -213,14 +227,15 @@ static const struct nla_policy red_policy[TCA_RED_MAX + 1] = { [TCA_RED_STAB] = { .len = RED_STAB_SIZE }, [TCA_RED_MAX_P] = { .type = NLA_U32 }, [TCA_RED_FLAGS] = NLA_POLICY_BITFIELD32(TC_RED_SUPPORTED_FLAGS), + [TCA_RED_EARLY_DROP_BLOCK] = { .type = NLA_U32 }, + [TCA_RED_MARK_BLOCK] = { .type = NLA_U32 }, }; -static int red_change(struct Qdisc *sch, struct nlattr *opt, - struct netlink_ext_ack *extack) +static int __red_change(struct Qdisc *sch, struct nlattr **tb, + struct netlink_ext_ack *extack) { struct Qdisc *old_child = NULL, *child = NULL; struct red_sched_data *q = qdisc_priv(sch); - struct nlattr *tb[TCA_RED_MAX + 1]; struct nla_bitfield32 flags_bf; struct tc_red_qopt *ctl; unsigned char userbits; @@ -228,14 +243,6 @@ static int red_change(struct Qdisc *sch, struct nlattr *opt, int err; u32 max_P; - if (opt == NULL) - return -EINVAL; - - err = nla_parse_nested_deprecated(tb, TCA_RED_MAX, opt, red_policy, - NULL); - if (err < 0) - return err; - if (tb[TCA_RED_PARMS] == NULL || tb[TCA_RED_STAB] == NULL) return -EINVAL; @@ -323,11 +330,74 @@ static int red_init(struct Qdisc *sch, struct nlattr *opt, struct netlink_ext_ack *extack) { struct red_sched_data *q = qdisc_priv(sch); + struct nlattr *tb[TCA_RED_MAX + 1]; + int err; + + if (!opt) + return -EINVAL; + + err = nla_parse_nested_deprecated(tb, TCA_RED_MAX, opt, red_policy, + extack); + if (err < 0) + return err; q->qdisc = &noop_qdisc; q->sch = sch; timer_setup(&q->adapt_timer, red_adaptative_timer, 0); - return red_change(sch, opt, extack); + + err = __red_change(sch, tb, extack); + if (err) + return err; + + err = tcf_qevent_init(&q->qe_early_drop, sch, + FLOW_BLOCK_BINDER_TYPE_RED_EARLY_DROP, + tb[TCA_RED_EARLY_DROP_BLOCK], extack); + if (err) + goto err_early_drop_init; + + err = tcf_qevent_init(&q->qe_mark, sch, + FLOW_BLOCK_BINDER_TYPE_RED_MARK, + tb[TCA_RED_MARK_BLOCK], extack); + if (err) + goto err_mark_init; + + return 0; + +err_mark_init: + tcf_qevent_destroy(&q->qe_early_drop, sch); +err_early_drop_init: + del_timer_sync(&q->adapt_timer); + red_offload(sch, false); + qdisc_put(q->qdisc); + return err; +} + +static int red_change(struct Qdisc *sch, struct nlattr *opt, + struct netlink_ext_ack *extack) +{ + struct red_sched_data *q = qdisc_priv(sch); + struct nlattr *tb[TCA_RED_MAX + 1]; + int err; + + if (!opt) + return -EINVAL; + + err = nla_parse_nested_deprecated(tb, TCA_RED_MAX, opt, red_policy, + extack); + if (err < 0) + return err; + + err = tcf_qevent_validate_change(&q->qe_early_drop, + tb[TCA_RED_EARLY_DROP_BLOCK], extack); + if (err) + return err; + + err = tcf_qevent_validate_change(&q->qe_mark, + tb[TCA_RED_MARK_BLOCK], extack); + if (err) + return err; + + return __red_change(sch, tb, extack); } static int red_dump_offload_stats(struct Qdisc *sch) @@ -371,7 +441,9 @@ static int red_dump(struct Qdisc *sch, struct sk_buff *skb) if (nla_put(skb, TCA_RED_PARMS, sizeof(opt), &opt) || nla_put_u32(skb, TCA_RED_MAX_P, q->parms.max_P) || nla_put_bitfield32(skb, TCA_RED_FLAGS, - q->flags, TC_RED_SUPPORTED_FLAGS)) + q->flags, TC_RED_SUPPORTED_FLAGS) || + tcf_qevent_dump(skb, TCA_RED_MARK_BLOCK, &q->qe_mark) || + tcf_qevent_dump(skb, TCA_RED_EARLY_DROP_BLOCK, &q->qe_early_drop)) goto nla_put_failure; return nla_nest_end(skb, opts); diff --git a/net/sched/sch_sfb.c b/net/sched/sch_sfb.c index 4074c50ac3d7..d2a6e78262bb 100644 --- a/net/sched/sch_sfb.c +++ b/net/sched/sch_sfb.c @@ -276,7 +276,7 @@ static bool sfb_classify(struct sk_buff *skb, struct tcf_proto *fl, return false; } -static int sfb_enqueue(struct sk_buff *skb, struct Qdisc *sch, +static int sfb_enqueue(struct sk_buff *skb, struct Qdisc *sch, spinlock_t *root_lock, struct sk_buff **to_free) { @@ -399,7 +399,7 @@ static int sfb_enqueue(struct sk_buff *skb, struct Qdisc *sch, } enqueue: - ret = qdisc_enqueue(skb, child, to_free); + ret = qdisc_enqueue(skb, child, root_lock, to_free); if (likely(ret == NET_XMIT_SUCCESS)) { qdisc_qstats_backlog_inc(sch, skb); sch->q.qlen++; diff --git a/net/sched/sch_sfq.c b/net/sched/sch_sfq.c index 5a6def5e4e6d..46cdefd69e44 100644 --- a/net/sched/sch_sfq.c +++ b/net/sched/sch_sfq.c @@ -343,7 +343,7 @@ static int sfq_headdrop(const struct sfq_sched_data *q) } static int -sfq_enqueue(struct sk_buff *skb, struct Qdisc *sch, struct sk_buff **to_free) +sfq_enqueue(struct sk_buff *skb, struct Qdisc *sch, spinlock_t *root_lock, struct sk_buff **to_free) { struct sfq_sched_data *q = qdisc_priv(sch); unsigned int hash, dropped; diff --git a/net/sched/sch_skbprio.c b/net/sched/sch_skbprio.c index 7a5e4c454715..f75f237c4436 100644 --- a/net/sched/sch_skbprio.c +++ b/net/sched/sch_skbprio.c @@ -65,7 +65,7 @@ static u16 calc_new_low_prio(const struct skbprio_sched_data *q) return SKBPRIO_MAX_PRIORITY - 1; } -static int skbprio_enqueue(struct sk_buff *skb, struct Qdisc *sch, +static int skbprio_enqueue(struct sk_buff *skb, struct Qdisc *sch, spinlock_t *root_lock, struct sk_buff **to_free) { const unsigned int max_priority = SKBPRIO_MAX_PRIORITY - 1; diff --git a/net/sched/sch_taprio.c b/net/sched/sch_taprio.c index b1eb12d33b9a..daef2ff60a98 100644 --- a/net/sched/sch_taprio.c +++ b/net/sched/sch_taprio.c @@ -410,7 +410,7 @@ done: return txtime; } -static int taprio_enqueue(struct sk_buff *skb, struct Qdisc *sch, +static int taprio_enqueue(struct sk_buff *skb, struct Qdisc *sch, spinlock_t *root_lock, struct sk_buff **to_free) { struct taprio_sched *q = qdisc_priv(sch); @@ -435,7 +435,7 @@ static int taprio_enqueue(struct sk_buff *skb, struct Qdisc *sch, qdisc_qstats_backlog_inc(sch, skb); sch->q.qlen++; - return qdisc_enqueue(skb, child, to_free); + return qdisc_enqueue(skb, child, root_lock, to_free); } static struct sk_buff *taprio_peek_soft(struct Qdisc *sch) @@ -1108,11 +1108,10 @@ static void setup_txtime(struct taprio_sched *q, static struct tc_taprio_qopt_offload *taprio_offload_alloc(int num_entries) { - size_t size = sizeof(struct tc_taprio_sched_entry) * num_entries + - sizeof(struct __tc_taprio_qopt_offload); struct __tc_taprio_qopt_offload *__offload; - __offload = kzalloc(size, GFP_KERNEL); + __offload = kzalloc(struct_size(__offload, offload.entries, num_entries), + GFP_KERNEL); if (!__offload) return NULL; diff --git a/net/sched/sch_tbf.c b/net/sched/sch_tbf.c index 78e79029dc63..c3eb5cdb83a8 100644 --- a/net/sched/sch_tbf.c +++ b/net/sched/sch_tbf.c @@ -187,7 +187,7 @@ static int tbf_offload_dump(struct Qdisc *sch) /* GSO packet is too big, segment it so that tbf can transmit * each segment in time */ -static int tbf_segment(struct sk_buff *skb, struct Qdisc *sch, +static int tbf_segment(struct sk_buff *skb, struct Qdisc *sch, spinlock_t *root_lock, struct sk_buff **to_free) { struct tbf_sched_data *q = qdisc_priv(sch); @@ -206,7 +206,7 @@ static int tbf_segment(struct sk_buff *skb, struct Qdisc *sch, skb_mark_not_on_list(segs); qdisc_skb_cb(segs)->pkt_len = segs->len; len += segs->len; - ret = qdisc_enqueue(segs, q->qdisc, to_free); + ret = qdisc_enqueue(segs, q->qdisc, root_lock, to_free); if (ret != NET_XMIT_SUCCESS) { if (net_xmit_drop_count(ret)) qdisc_qstats_drop(sch); @@ -221,7 +221,7 @@ static int tbf_segment(struct sk_buff *skb, struct Qdisc *sch, return nb > 0 ? NET_XMIT_SUCCESS : NET_XMIT_DROP; } -static int tbf_enqueue(struct sk_buff *skb, struct Qdisc *sch, +static int tbf_enqueue(struct sk_buff *skb, struct Qdisc *sch, spinlock_t *root_lock, struct sk_buff **to_free) { struct tbf_sched_data *q = qdisc_priv(sch); @@ -231,10 +231,10 @@ static int tbf_enqueue(struct sk_buff *skb, struct Qdisc *sch, if (qdisc_pkt_len(skb) > q->max_size) { if (skb_is_gso(skb) && skb_gso_validate_mac_len(skb, q->max_size)) - return tbf_segment(skb, sch, to_free); + return tbf_segment(skb, sch, root_lock, to_free); return qdisc_drop(skb, sch, to_free); } - ret = qdisc_enqueue(skb, q->qdisc, to_free); + ret = qdisc_enqueue(skb, q->qdisc, root_lock, to_free); if (ret != NET_XMIT_SUCCESS) { if (net_xmit_drop_count(ret)) qdisc_qstats_drop(sch); diff --git a/net/sched/sch_teql.c b/net/sched/sch_teql.c index 689ef6f3ded8..511964653476 100644 --- a/net/sched/sch_teql.c +++ b/net/sched/sch_teql.c @@ -72,8 +72,8 @@ struct teql_sched_data { /* "teql*" qdisc routines */ -static int -teql_enqueue(struct sk_buff *skb, struct Qdisc *sch, struct sk_buff **to_free) +static int teql_enqueue(struct sk_buff *skb, struct Qdisc *sch, spinlock_t *root_lock, + struct sk_buff **to_free) { struct net_device *dev = qdisc_dev(sch); struct teql_sched_data *q = qdisc_priv(sch); |