diff options
Diffstat (limited to 'net/sched')
47 files changed, 3183 insertions, 907 deletions
diff --git a/net/sched/Kconfig b/net/sched/Kconfig index f04d4a484d5..a7a5583d4f6 100644 --- a/net/sched/Kconfig +++ b/net/sched/Kconfig @@ -126,6 +126,17 @@ config NET_SCH_RED To compile this code as a module, choose M here: the module will be called sch_red. +config NET_SCH_SFB + tristate "Stochastic Fair Blue (SFB)" + ---help--- + Say Y here if you want to use the Stochastic Fair Blue (SFB) + packet scheduling algorithm. + + See the top of <file:net/sched/sch_sfb.c> for more details. + + To compile this code as a module, choose M here: the + module will be called sch_sfb. + config NET_SCH_SFQ tristate "Stochastic Fairness Queueing (SFQ)" ---help--- @@ -205,6 +216,29 @@ config NET_SCH_DRR If unsure, say N. +config NET_SCH_MQPRIO + tristate "Multi-queue priority scheduler (MQPRIO)" + help + Say Y here if you want to use the Multi-queue Priority scheduler. + This scheduler allows QOS to be offloaded on NICs that have support + for offloading QOS schedulers. + + To compile this driver as a module, choose M here: the module will + be called sch_mqprio. + + If unsure, say N. + +config NET_SCH_CHOKE + tristate "CHOose and Keep responsive flow scheduler (CHOKE)" + help + Say Y here if you want to use the CHOKe packet scheduler (CHOose + and Keep for responsive flows, CHOose and Kill for unresponsive + flows). This is a variation of RED which trys to penalize flows + that monopolize the queue. + + To compile this code as a module, choose M here: the + module will be called sch_choke. + config NET_SCH_INGRESS tristate "Ingress Qdisc" depends on NET_CLS_ACT @@ -243,7 +277,7 @@ config NET_CLS_TCINDEX config NET_CLS_ROUTE4 tristate "Routing decision (ROUTE)" - select NET_CLS_ROUTE + select IP_ROUTE_CLASSID select NET_CLS ---help--- If you say Y here, you will be able to classify packets @@ -252,9 +286,6 @@ config NET_CLS_ROUTE4 To compile this code as a module, choose M here: the module will be called cls_route. -config NET_CLS_ROUTE - bool - config NET_CLS_FW tristate "Netfilter mark (FW)" select NET_CLS diff --git a/net/sched/Makefile b/net/sched/Makefile index 960f5dba630..2e77b8dba22 100644 --- a/net/sched/Makefile +++ b/net/sched/Makefile @@ -24,6 +24,7 @@ obj-$(CONFIG_NET_SCH_RED) += sch_red.o obj-$(CONFIG_NET_SCH_GRED) += sch_gred.o obj-$(CONFIG_NET_SCH_INGRESS) += sch_ingress.o obj-$(CONFIG_NET_SCH_DSMARK) += sch_dsmark.o +obj-$(CONFIG_NET_SCH_SFB) += sch_sfb.o obj-$(CONFIG_NET_SCH_SFQ) += sch_sfq.o obj-$(CONFIG_NET_SCH_TBF) += sch_tbf.o obj-$(CONFIG_NET_SCH_TEQL) += sch_teql.o @@ -32,6 +33,9 @@ obj-$(CONFIG_NET_SCH_MULTIQ) += sch_multiq.o obj-$(CONFIG_NET_SCH_ATM) += sch_atm.o obj-$(CONFIG_NET_SCH_NETEM) += sch_netem.o obj-$(CONFIG_NET_SCH_DRR) += sch_drr.o +obj-$(CONFIG_NET_SCH_MQPRIO) += sch_mqprio.o +obj-$(CONFIG_NET_SCH_CHOKE) += sch_choke.o + obj-$(CONFIG_NET_CLS_U32) += cls_u32.o obj-$(CONFIG_NET_CLS_ROUTE4) += cls_route.o obj-$(CONFIG_NET_CLS_FW) += cls_fw.o diff --git a/net/sched/act_api.c b/net/sched/act_api.c index 23b25f89e7e..15873e14cb5 100644 --- a/net/sched/act_api.c +++ b/net/sched/act_api.c @@ -78,7 +78,7 @@ static int tcf_dump_walker(struct sk_buff *skb, struct netlink_callback *cb, struct tc_action *a, struct tcf_hashinfo *hinfo) { struct tcf_common *p; - int err = 0, index = -1,i = 0, s_i = 0, n_i = 0; + int err = 0, index = -1, i = 0, s_i = 0, n_i = 0; struct nlattr *nest; read_lock_bh(hinfo->lock); @@ -126,7 +126,7 @@ static int tcf_del_walker(struct sk_buff *skb, struct tc_action *a, { struct tcf_common *p, *s_p; struct nlattr *nest; - int i= 0, n_i = 0; + int i = 0, n_i = 0; nest = nla_nest_start(skb, a->order); if (nest == NULL) @@ -138,7 +138,7 @@ static int tcf_del_walker(struct sk_buff *skb, struct tc_action *a, while (p != NULL) { s_p = p->tcfc_next; if (ACT_P_DELETED == tcf_hash_release(p, 0, hinfo)) - module_put(a->ops->owner); + module_put(a->ops->owner); n_i++; p = s_p; } @@ -447,7 +447,8 @@ tcf_action_dump_1(struct sk_buff *skb, struct tc_action *a, int bind, int ref) nest = nla_nest_start(skb, TCA_OPTIONS); if (nest == NULL) goto nla_put_failure; - if ((err = tcf_action_dump_old(skb, a, bind, ref)) > 0) { + err = tcf_action_dump_old(skb, a, bind, ref); + if (err > 0) { nla_nest_end(skb, nest); return err; } @@ -491,7 +492,7 @@ struct tc_action *tcf_action_init_1(struct nlattr *nla, struct nlattr *est, struct tc_action *a; struct tc_action_ops *a_o; char act_name[IFNAMSIZ]; - struct nlattr *tb[TCA_ACT_MAX+1]; + struct nlattr *tb[TCA_ACT_MAX + 1]; struct nlattr *kind; int err; @@ -549,9 +550,9 @@ struct tc_action *tcf_action_init_1(struct nlattr *nla, struct nlattr *est, goto err_free; /* module count goes up only when brand new policy is created - if it exists and is only bound to in a_o->init() then - ACT_P_CREATED is not returned (a zero is). - */ + * if it exists and is only bound to in a_o->init() then + * ACT_P_CREATED is not returned (a zero is). + */ if (err != ACT_P_CREATED) module_put(a_o->owner); a->ops = a_o; @@ -569,7 +570,7 @@ err_out: struct tc_action *tcf_action_init(struct nlattr *nla, struct nlattr *est, char *name, int ovr, int bind) { - struct nlattr *tb[TCA_ACT_MAX_PRIO+1]; + struct nlattr *tb[TCA_ACT_MAX_PRIO + 1]; struct tc_action *head = NULL, *act, *act_prev = NULL; int err; int i; @@ -697,7 +698,7 @@ act_get_notify(struct net *net, u32 pid, struct nlmsghdr *n, static struct tc_action * tcf_action_get_1(struct nlattr *nla, struct nlmsghdr *n, u32 pid) { - struct nlattr *tb[TCA_ACT_MAX+1]; + struct nlattr *tb[TCA_ACT_MAX + 1]; struct tc_action *a; int index; int err; @@ -770,7 +771,7 @@ static int tca_action_flush(struct net *net, struct nlattr *nla, struct tcamsg *t; struct netlink_callback dcb; struct nlattr *nest; - struct nlattr *tb[TCA_ACT_MAX+1]; + struct nlattr *tb[TCA_ACT_MAX + 1]; struct nlattr *kind; struct tc_action *a = create_a(0); int err = -ENOMEM; @@ -821,7 +822,8 @@ static int tca_action_flush(struct net *net, struct nlattr *nla, nlh->nlmsg_flags |= NLM_F_ROOT; module_put(a->ops->owner); kfree(a); - err = rtnetlink_send(skb, net, pid, RTNLGRP_TC, n->nlmsg_flags&NLM_F_ECHO); + err = rtnetlink_send(skb, net, pid, RTNLGRP_TC, + n->nlmsg_flags & NLM_F_ECHO); if (err > 0) return 0; @@ -842,14 +844,14 @@ tca_action_gd(struct net *net, struct nlattr *nla, struct nlmsghdr *n, u32 pid, int event) { int i, ret; - struct nlattr *tb[TCA_ACT_MAX_PRIO+1]; + struct nlattr *tb[TCA_ACT_MAX_PRIO + 1]; struct tc_action *head = NULL, *act, *act_prev = NULL; ret = nla_parse_nested(tb, TCA_ACT_MAX_PRIO, nla, NULL); if (ret < 0) return ret; - if (event == RTM_DELACTION && n->nlmsg_flags&NLM_F_ROOT) { + if (event == RTM_DELACTION && n->nlmsg_flags & NLM_F_ROOT) { if (tb[1] != NULL) return tca_action_flush(net, tb[1], n, pid); else @@ -892,7 +894,7 @@ tca_action_gd(struct net *net, struct nlattr *nla, struct nlmsghdr *n, /* now do the delete */ tcf_action_destroy(head, 0); ret = rtnetlink_send(skb, net, pid, RTNLGRP_TC, - n->nlmsg_flags&NLM_F_ECHO); + n->nlmsg_flags & NLM_F_ECHO); if (ret > 0) return 0; return ret; @@ -936,7 +938,7 @@ static int tcf_add_notify(struct net *net, struct tc_action *a, nlh->nlmsg_len = skb_tail_pointer(skb) - b; NETLINK_CB(skb).dst_group = RTNLGRP_TC; - err = rtnetlink_send(skb, net, pid, RTNLGRP_TC, flags&NLM_F_ECHO); + err = rtnetlink_send(skb, net, pid, RTNLGRP_TC, flags & NLM_F_ECHO); if (err > 0) err = 0; return err; @@ -967,7 +969,7 @@ tcf_action_add(struct net *net, struct nlattr *nla, struct nlmsghdr *n, /* dump then free all the actions after update; inserted policy * stays intact - * */ + */ ret = tcf_add_notify(net, act, pid, seq, RTM_NEWACTION, n->nlmsg_flags); for (a = act; a; a = act) { act = a->next; @@ -993,8 +995,7 @@ static int tc_ctl_action(struct sk_buff *skb, struct nlmsghdr *n, void *arg) return -EINVAL; } - /* n->nlmsg_flags&NLM_F_CREATE - * */ + /* n->nlmsg_flags & NLM_F_CREATE */ switch (n->nlmsg_type) { case RTM_NEWACTION: /* we are going to assume all other flags @@ -1003,7 +1004,7 @@ static int tc_ctl_action(struct sk_buff *skb, struct nlmsghdr *n, void *arg) * but since we want avoid ambiguity (eg when flags * is zero) then just set this */ - if (n->nlmsg_flags&NLM_F_REPLACE) + if (n->nlmsg_flags & NLM_F_REPLACE) ovr = 1; replay: ret = tcf_action_add(net, tca[TCA_ACT_TAB], n, pid, ovr); @@ -1028,7 +1029,7 @@ replay: static struct nlattr * find_dump_kind(const struct nlmsghdr *n) { - struct nlattr *tb1, *tb2[TCA_ACT_MAX+1]; + struct nlattr *tb1, *tb2[TCA_ACT_MAX + 1]; struct nlattr *tb[TCA_ACT_MAX_PRIO + 1]; struct nlattr *nla[TCAA_MAX + 1]; struct nlattr *kind; @@ -1071,9 +1072,8 @@ tc_dump_action(struct sk_buff *skb, struct netlink_callback *cb) } a_o = tc_lookup_action(kind); - if (a_o == NULL) { + if (a_o == NULL) return 0; - } memset(&a, 0, sizeof(struct tc_action)); a.ops = a_o; diff --git a/net/sched/act_csum.c b/net/sched/act_csum.c index 83ddfc07e45..6cdf9abe475 100644 --- a/net/sched/act_csum.c +++ b/net/sched/act_csum.c @@ -63,7 +63,7 @@ static int tcf_csum_init(struct nlattr *nla, struct nlattr *est, if (nla == NULL) return -EINVAL; - err = nla_parse_nested(tb, TCA_CSUM_MAX, nla,csum_policy); + err = nla_parse_nested(tb, TCA_CSUM_MAX, nla, csum_policy); if (err < 0) return err; diff --git a/net/sched/act_gact.c b/net/sched/act_gact.c index c2ed90a4c0b..2b4ab4b05ce 100644 --- a/net/sched/act_gact.c +++ b/net/sched/act_gact.c @@ -50,7 +50,7 @@ static int gact_determ(struct tcf_gact *gact) } typedef int (*g_rand)(struct tcf_gact *gact); -static g_rand gact_rand[MAX_RAND]= { NULL, gact_net_rand, gact_determ }; +static g_rand gact_rand[MAX_RAND] = { NULL, gact_net_rand, gact_determ }; #endif /* CONFIG_GACT_PROB */ static const struct nla_policy gact_policy[TCA_GACT_MAX + 1] = { @@ -89,7 +89,7 @@ static int tcf_gact_init(struct nlattr *nla, struct nlattr *est, pc = tcf_hash_create(parm->index, est, a, sizeof(*gact), bind, &gact_idx_gen, &gact_hash_info); if (IS_ERR(pc)) - return PTR_ERR(pc); + return PTR_ERR(pc); ret = ACT_P_CREATED; } else { if (!ovr) { @@ -205,9 +205,9 @@ MODULE_LICENSE("GPL"); static int __init gact_init_module(void) { #ifdef CONFIG_GACT_PROB - printk(KERN_INFO "GACT probability on\n"); + pr_info("GACT probability on\n"); #else - printk(KERN_INFO "GACT probability NOT on\n"); + pr_info("GACT probability NOT on\n"); #endif return tcf_register_action(&act_gact_ops); } diff --git a/net/sched/act_ipt.c b/net/sched/act_ipt.c index c2a7c20e81c..9fc211a1b20 100644 --- a/net/sched/act_ipt.c +++ b/net/sched/act_ipt.c @@ -138,7 +138,7 @@ static int tcf_ipt_init(struct nlattr *nla, struct nlattr *est, pc = tcf_hash_create(index, est, a, sizeof(*ipt), bind, &ipt_idx_gen, &ipt_hash_info); if (IS_ERR(pc)) - return PTR_ERR(pc); + return PTR_ERR(pc); ret = ACT_P_CREATED; } else { if (!ovr) { @@ -162,7 +162,8 @@ static int tcf_ipt_init(struct nlattr *nla, struct nlattr *est, if (unlikely(!t)) goto err2; - if ((err = ipt_init_target(t, tname, hook)) < 0) + err = ipt_init_target(t, tname, hook); + if (err < 0) goto err3; spin_lock_bh(&ipt->tcf_lock); @@ -212,8 +213,9 @@ static int tcf_ipt(struct sk_buff *skb, struct tc_action *a, bstats_update(&ipt->tcf_bstats, skb); /* yes, we have to worry about both in and out dev - worry later - danger - this API seems to have changed - from earlier kernels */ + * worry later - danger - this API seems to have changed + * from earlier kernels + */ par.in = skb->dev; par.out = NULL; par.hooknum = ipt->tcfi_hook; @@ -253,9 +255,9 @@ static int tcf_ipt_dump(struct sk_buff *skb, struct tc_action *a, int bind, int struct tc_cnt c; /* for simple targets kernel size == user size - ** user name = target name - ** for foolproof you need to not assume this - */ + * user name = target name + * for foolproof you need to not assume this + */ t = kmemdup(ipt->tcfi_t, ipt->tcfi_t->u.user.target_size, GFP_ATOMIC); if (unlikely(!t)) diff --git a/net/sched/act_mirred.c b/net/sched/act_mirred.c index d765067e99d..961386e2f2c 100644 --- a/net/sched/act_mirred.c +++ b/net/sched/act_mirred.c @@ -41,13 +41,13 @@ static struct tcf_hashinfo mirred_hash_info = { .lock = &mirred_lock, }; -static inline int tcf_mirred_release(struct tcf_mirred *m, int bind) +static int tcf_mirred_release(struct tcf_mirred *m, int bind) { if (m) { if (bind) m->tcf_bindcnt--; m->tcf_refcnt--; - if(!m->tcf_bindcnt && m->tcf_refcnt <= 0) { + if (!m->tcf_bindcnt && m->tcf_refcnt <= 0) { list_del(&m->tcfm_list); if (m->tcfm_dev) dev_put(m->tcfm_dev); diff --git a/net/sched/act_nat.c b/net/sched/act_nat.c index 178a4bd7b7c..762b027650a 100644 --- a/net/sched/act_nat.c +++ b/net/sched/act_nat.c @@ -69,7 +69,7 @@ static int tcf_nat_init(struct nlattr *nla, struct nlattr *est, pc = tcf_hash_create(parm->index, est, a, sizeof(*p), bind, &nat_idx_gen, &nat_hash_info); if (IS_ERR(pc)) - return PTR_ERR(pc); + return PTR_ERR(pc); p = to_tcf_nat(pc); ret = ACT_P_CREATED; } else { diff --git a/net/sched/act_pedit.c b/net/sched/act_pedit.c index 445bef716f7..50c7c06c019 100644 --- a/net/sched/act_pedit.c +++ b/net/sched/act_pedit.c @@ -70,7 +70,7 @@ static int tcf_pedit_init(struct nlattr *nla, struct nlattr *est, pc = tcf_hash_create(parm->index, est, a, sizeof(*p), bind, &pedit_idx_gen, &pedit_hash_info); if (IS_ERR(pc)) - return PTR_ERR(pc); + return PTR_ERR(pc); p = to_pedit(pc); keys = kmalloc(ksize, GFP_KERNEL); if (keys == NULL) { @@ -127,11 +127,9 @@ static int tcf_pedit(struct sk_buff *skb, struct tc_action *a, int i, munged = 0; unsigned int off; - if (skb_cloned(skb)) { - if (pskb_expand_head(skb, 0, 0, GFP_ATOMIC)) { - return p->tcf_action; - } - } + if (skb_cloned(skb) && + pskb_expand_head(skb, 0, 0, GFP_ATOMIC)) + return p->tcf_action; off = skb_network_offset(skb); diff --git a/net/sched/act_police.c b/net/sched/act_police.c index e2f08b1e2e5..8a1630774fd 100644 --- a/net/sched/act_police.c +++ b/net/sched/act_police.c @@ -22,8 +22,8 @@ #include <net/act_api.h> #include <net/netlink.h> -#define L2T(p,L) qdisc_l2t((p)->tcfp_R_tab, L) -#define L2T_P(p,L) qdisc_l2t((p)->tcfp_P_tab, L) +#define L2T(p, L) qdisc_l2t((p)->tcfp_R_tab, L) +#define L2T_P(p, L) qdisc_l2t((p)->tcfp_P_tab, L) #define POL_TAB_MASK 15 static struct tcf_common *tcf_police_ht[POL_TAB_MASK + 1]; @@ -37,8 +37,7 @@ static struct tcf_hashinfo police_hash_info = { }; /* old policer structure from before tc actions */ -struct tc_police_compat -{ +struct tc_police_compat { u32 index; int action; u32 limit; @@ -139,7 +138,7 @@ static const struct nla_policy police_policy[TCA_POLICE_MAX + 1] = { static int tcf_act_police_locate(struct nlattr *nla, struct nlattr *est, struct tc_action *a, int ovr, int bind) { - unsigned h; + unsigned int h; int ret = 0, err; struct nlattr *tb[TCA_POLICE_MAX + 1]; struct tc_police *parm; diff --git a/net/sched/act_simple.c b/net/sched/act_simple.c index 7287cff7af3..a34a22de60b 100644 --- a/net/sched/act_simple.c +++ b/net/sched/act_simple.c @@ -47,7 +47,7 @@ static int tcf_simp(struct sk_buff *skb, struct tc_action *a, struct tcf_result /* print policy string followed by _ then packet count * Example if this was the 3rd packet and the string was "hello" * then it would look like "hello_3" (without quotes) - **/ + */ pr_info("simple: %s_%d\n", (char *)d->tcfd_defdata, d->tcf_bstats.packets); spin_unlock(&d->tcf_lock); @@ -125,7 +125,7 @@ static int tcf_simp_init(struct nlattr *nla, struct nlattr *est, pc = tcf_hash_create(parm->index, est, a, sizeof(*d), bind, &simp_idx_gen, &simp_hash_info); if (IS_ERR(pc)) - return PTR_ERR(pc); + return PTR_ERR(pc); d = to_defact(pc); ret = alloc_defdata(d, defdata); @@ -149,7 +149,7 @@ static int tcf_simp_init(struct nlattr *nla, struct nlattr *est, return ret; } -static inline int tcf_simp_cleanup(struct tc_action *a, int bind) +static int tcf_simp_cleanup(struct tc_action *a, int bind) { struct tcf_defact *d = a->priv; @@ -158,8 +158,8 @@ static inline int tcf_simp_cleanup(struct tc_action *a, int bind) return 0; } -static inline int tcf_simp_dump(struct sk_buff *skb, struct tc_action *a, - int bind, int ref) +static int tcf_simp_dump(struct sk_buff *skb, struct tc_action *a, + int bind, int ref) { unsigned char *b = skb_tail_pointer(skb); struct tcf_defact *d = a->priv; diff --git a/net/sched/act_skbedit.c b/net/sched/act_skbedit.c index 836f5fee9e5..5f6f0c7c390 100644 --- a/net/sched/act_skbedit.c +++ b/net/sched/act_skbedit.c @@ -113,7 +113,7 @@ static int tcf_skbedit_init(struct nlattr *nla, struct nlattr *est, pc = tcf_hash_create(parm->index, est, a, sizeof(*d), bind, &skbedit_idx_gen, &skbedit_hash_info); if (IS_ERR(pc)) - return PTR_ERR(pc); + return PTR_ERR(pc); d = to_skbedit(pc); ret = ACT_P_CREATED; @@ -144,7 +144,7 @@ static int tcf_skbedit_init(struct nlattr *nla, struct nlattr *est, return ret; } -static inline int tcf_skbedit_cleanup(struct tc_action *a, int bind) +static int tcf_skbedit_cleanup(struct tc_action *a, int bind) { struct tcf_skbedit *d = a->priv; @@ -153,8 +153,8 @@ static inline int tcf_skbedit_cleanup(struct tc_action *a, int bind) return 0; } -static inline int tcf_skbedit_dump(struct sk_buff *skb, struct tc_action *a, - int bind, int ref) +static int tcf_skbedit_dump(struct sk_buff *skb, struct tc_action *a, + int bind, int ref) { unsigned char *b = skb_tail_pointer(skb); struct tcf_skbedit *d = a->priv; diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c index 5fd0c28ef79..bb2c523f815 100644 --- a/net/sched/cls_api.c +++ b/net/sched/cls_api.c @@ -85,7 +85,7 @@ int unregister_tcf_proto_ops(struct tcf_proto_ops *ops) int rc = -ENOENT; write_lock(&cls_mod_lock); - for (tp = &tcf_proto_base; (t=*tp) != NULL; tp = &t->next) + for (tp = &tcf_proto_base; (t = *tp) != NULL; tp = &t->next) if (t == ops) break; @@ -111,7 +111,7 @@ static inline u32 tcf_auto_prio(struct tcf_proto *tp) u32 first = TC_H_MAKE(0xC0000000U, 0U); if (tp) - first = tp->prio-1; + first = tp->prio - 1; return first; } @@ -149,7 +149,8 @@ replay: if (prio == 0) { /* If no priority is given, user wants we allocated it. */ - if (n->nlmsg_type != RTM_NEWTFILTER || !(n->nlmsg_flags&NLM_F_CREATE)) + if (n->nlmsg_type != RTM_NEWTFILTER || + !(n->nlmsg_flags & NLM_F_CREATE)) return -ENOENT; prio = TC_H_MAKE(0x80000000U, 0U); } @@ -176,7 +177,8 @@ replay: } /* Is it classful? */ - if ((cops = q->ops->cl_ops) == NULL) + cops = q->ops->cl_ops; + if (!cops) return -EINVAL; if (cops->tcf_chain == NULL) @@ -196,10 +198,11 @@ replay: goto errout; /* Check the chain for existence of proto-tcf with this priority */ - for (back = chain; (tp=*back) != NULL; back = &tp->next) { + for (back = chain; (tp = *back) != NULL; back = &tp->next) { if (tp->prio >= prio) { if (tp->prio == prio) { - if (!nprio || (tp->protocol != protocol && protocol)) + if (!nprio || + (tp->protocol != protocol && protocol)) goto errout; } else tp = NULL; @@ -216,7 +219,8 @@ replay: goto errout; err = -ENOENT; - if (n->nlmsg_type != RTM_NEWTFILTER || !(n->nlmsg_flags&NLM_F_CREATE)) + if (n->nlmsg_type != RTM_NEWTFILTER || + !(n->nlmsg_flags & NLM_F_CREATE)) goto errout; @@ -420,7 +424,8 @@ static int tc_dump_tfilter(struct sk_buff *skb, struct netlink_callback *cb) if (cb->nlh->nlmsg_len < NLMSG_LENGTH(sizeof(*tcm))) return skb->len; - if ((dev = __dev_get_by_index(net, tcm->tcm_ifindex)) == NULL) + dev = __dev_get_by_index(net, tcm->tcm_ifindex); + if (!dev) return skb->len; if (!tcm->tcm_parent) @@ -429,7 +434,8 @@ static int tc_dump_tfilter(struct sk_buff *skb, struct netlink_callback *cb) q = qdisc_lookup(dev, TC_H_MAJ(tcm->tcm_parent)); if (!q) goto out; - if ((cops = q->ops->cl_ops) == NULL) + cops = q->ops->cl_ops; + if (!cops) goto errout; if (cops->tcf_chain == NULL) goto errout; @@ -444,8 +450,9 @@ static int tc_dump_tfilter(struct sk_buff *skb, struct netlink_callback *cb) s_t = cb->args[0]; - for (tp=*chain, t=0; tp; tp = tp->next, t++) { - if (t < s_t) continue; + for (tp = *chain, t = 0; tp; tp = tp->next, t++) { + if (t < s_t) + continue; if (TC_H_MAJ(tcm->tcm_info) && TC_H_MAJ(tcm->tcm_info) != tp->prio) continue; @@ -468,10 +475,10 @@ static int tc_dump_tfilter(struct sk_buff *skb, struct netlink_callback *cb) arg.skb = skb; arg.cb = cb; arg.w.stop = 0; - arg.w.skip = cb->args[1]-1; + arg.w.skip = cb->args[1] - 1; arg.w.count = 0; tp->ops->walk(tp, &arg.w); - cb->args[1] = arg.w.count+1; + cb->args[1] = arg.w.count + 1; if (arg.w.stop) break; } diff --git a/net/sched/cls_basic.c b/net/sched/cls_basic.c index f23d9155b1e..8be8872dd57 100644 --- a/net/sched/cls_basic.c +++ b/net/sched/cls_basic.c @@ -21,14 +21,12 @@ #include <net/act_api.h> #include <net/pkt_cls.h> -struct basic_head -{ +struct basic_head { u32 hgenerator; struct list_head flist; }; -struct basic_filter -{ +struct basic_filter { u32 handle; struct tcf_exts exts; struct tcf_ematch_tree ematches; @@ -92,8 +90,7 @@ static int basic_init(struct tcf_proto *tp) return 0; } -static inline void basic_delete_filter(struct tcf_proto *tp, - struct basic_filter *f) +static void basic_delete_filter(struct tcf_proto *tp, struct basic_filter *f) { tcf_unbind_filter(tp, &f->res); tcf_exts_destroy(tp, &f->exts); @@ -135,9 +132,9 @@ static const struct nla_policy basic_policy[TCA_BASIC_MAX + 1] = { [TCA_BASIC_EMATCHES] = { .type = NLA_NESTED }, }; -static inline int basic_set_parms(struct tcf_proto *tp, struct basic_filter *f, - unsigned long base, struct nlattr **tb, - struct nlattr *est) +static int basic_set_parms(struct tcf_proto *tp, struct basic_filter *f, + unsigned long base, struct nlattr **tb, + struct nlattr *est) { int err = -EINVAL; struct tcf_exts e; @@ -203,7 +200,7 @@ static int basic_change(struct tcf_proto *tp, unsigned long base, u32 handle, } while (--i > 0 && basic_get(tp, head->hgenerator)); if (i <= 0) { - printk(KERN_ERR "Insufficient number of handles\n"); + pr_err("Insufficient number of handles\n"); goto errout; } diff --git a/net/sched/cls_cgroup.c b/net/sched/cls_cgroup.c index d49c40fb7e0..32a335194ca 100644 --- a/net/sched/cls_cgroup.c +++ b/net/sched/cls_cgroup.c @@ -56,7 +56,8 @@ static struct cgroup_subsys_state *cgrp_create(struct cgroup_subsys *ss, { struct cgroup_cls_state *cs; - if (!(cs = kzalloc(sizeof(*cs), GFP_KERNEL))) + cs = kzalloc(sizeof(*cs), GFP_KERNEL); + if (!cs) return ERR_PTR(-ENOMEM); if (cgrp->parent) @@ -94,8 +95,7 @@ static int cgrp_populate(struct cgroup_subsys *ss, struct cgroup *cgrp) return cgroup_add_files(cgrp, ss, ss_files, ARRAY_SIZE(ss_files)); } -struct cls_cgroup_head -{ +struct cls_cgroup_head { u32 handle; struct tcf_exts exts; struct tcf_ematch_tree ematches; @@ -166,7 +166,7 @@ static int cls_cgroup_change(struct tcf_proto *tp, unsigned long base, u32 handle, struct nlattr **tca, unsigned long *arg) { - struct nlattr *tb[TCA_CGROUP_MAX+1]; + struct nlattr *tb[TCA_CGROUP_MAX + 1]; struct cls_cgroup_head *head = tp->root; struct tcf_ematch_tree t; struct tcf_exts e; diff --git a/net/sched/cls_flow.c b/net/sched/cls_flow.c index 5b271a18bc3..8ec01391d98 100644 --- a/net/sched/cls_flow.c +++ b/net/sched/cls_flow.c @@ -121,7 +121,7 @@ static u32 flow_get_proto_src(struct sk_buff *skb) if (!pskb_network_may_pull(skb, sizeof(*iph))) break; iph = ip_hdr(skb); - if (iph->frag_off & htons(IP_MF|IP_OFFSET)) + if (iph->frag_off & htons(IP_MF | IP_OFFSET)) break; poff = proto_ports_offset(iph->protocol); if (poff >= 0 && @@ -163,7 +163,7 @@ static u32 flow_get_proto_dst(struct sk_buff *skb) if (!pskb_network_may_pull(skb, sizeof(*iph))) break; iph = ip_hdr(skb); - if (iph->frag_off & htons(IP_MF|IP_OFFSET)) + if (iph->frag_off & htons(IP_MF | IP_OFFSET)) break; poff = proto_ports_offset(iph->protocol); if (poff >= 0 && @@ -276,7 +276,7 @@ fallback: static u32 flow_get_rtclassid(const struct sk_buff *skb) { -#ifdef CONFIG_NET_CLS_ROUTE +#ifdef CONFIG_IP_ROUTE_CLASSID if (skb_dst(skb)) return skb_dst(skb)->tclassid; #endif diff --git a/net/sched/cls_fw.c b/net/sched/cls_fw.c index 93b0a7b6f9b..26e7bc4ffb7 100644 --- a/net/sched/cls_fw.c +++ b/net/sched/cls_fw.c @@ -31,14 +31,12 @@ #define HTSIZE (PAGE_SIZE/sizeof(struct fw_filter *)) -struct fw_head -{ +struct fw_head { struct fw_filter *ht[HTSIZE]; u32 mask; }; -struct fw_filter -{ +struct fw_filter { struct fw_filter *next; u32 id; struct tcf_result res; @@ -53,7 +51,7 @@ static const struct tcf_ext_map fw_ext_map = { .police = TCA_FW_POLICE }; -static __inline__ int fw_hash(u32 handle) +static inline int fw_hash(u32 handle) { if (HTSIZE == 4096) return ((handle >> 24) & 0xFFF) ^ @@ -82,14 +80,14 @@ static __inline__ int fw_hash(u32 handle) static int fw_classify(struct sk_buff *skb, struct tcf_proto *tp, struct tcf_result *res) { - struct fw_head *head = (struct fw_head*)tp->root; + struct fw_head *head = (struct fw_head *)tp->root; struct fw_filter *f; int r; u32 id = skb->mark; if (head != NULL) { id &= head->mask; - for (f=head->ht[fw_hash(id)]; f; f=f->next) { + for (f = head->ht[fw_hash(id)]; f; f = f->next) { if (f->id == id) { *res = f->res; #ifdef CONFIG_NET_CLS_IND @@ -105,7 +103,8 @@ static int fw_classify(struct sk_buff *skb, struct tcf_proto *tp, } } else { /* old method */ - if (id && (TC_H_MAJ(id) == 0 || !(TC_H_MAJ(id^tp->q->handle)))) { + if (id && (TC_H_MAJ(id) == 0 || + !(TC_H_MAJ(id ^ tp->q->handle)))) { res->classid = id; res->class = 0; return 0; @@ -117,13 +116,13 @@ static int fw_classify(struct sk_buff *skb, struct tcf_proto *tp, static unsigned long fw_get(struct tcf_proto *tp, u32 handle) { - struct fw_head *head = (struct fw_head*)tp->root; + struct fw_head *head = (struct fw_head *)tp->root; struct fw_filter *f; if (head == NULL) return 0; - for (f=head->ht[fw_hash(handle)]; f; f=f->next) { + for (f = head->ht[fw_hash(handle)]; f; f = f->next) { if (f->id == handle) return (unsigned long)f; } @@ -139,8 +138,7 @@ static int fw_init(struct tcf_proto *tp) return 0; } -static inline void -fw_delete_filter(struct tcf_proto *tp, struct fw_filter *f) +static void fw_delete_filter(struct tcf_proto *tp, struct fw_filter *f) { tcf_unbind_filter(tp, &f->res); tcf_exts_destroy(tp, &f->exts); @@ -156,8 +154,8 @@ static void fw_destroy(struct tcf_proto *tp) if (head == NULL) return; - for (h=0; h<HTSIZE; h++) { - while ((f=head->ht[h]) != NULL) { + for (h = 0; h < HTSIZE; h++) { + while ((f = head->ht[h]) != NULL) { head->ht[h] = f->next; fw_delete_filter(tp, f); } @@ -167,14 +165,14 @@ static void fw_destroy(struct tcf_proto *tp) static int fw_delete(struct tcf_proto *tp, unsigned long arg) { - struct fw_head *head = (struct fw_head*)tp->root; - struct fw_filter *f = (struct fw_filter*)arg; + struct fw_head *head = (struct fw_head *)tp->root; + struct fw_filter *f = (struct fw_filter *)arg; struct fw_filter **fp; if (head == NULL || f == NULL) goto out; - for (fp=&head->ht[fw_hash(f->id)]; *fp; fp = &(*fp)->next) { + for (fp = &head->ht[fw_hash(f->id)]; *fp; fp = &(*fp)->next) { if (*fp == f) { tcf_tree_lock(tp); *fp = f->next; @@ -240,7 +238,7 @@ static int fw_change(struct tcf_proto *tp, unsigned long base, struct nlattr **tca, unsigned long *arg) { - struct fw_head *head = (struct fw_head*)tp->root; + struct fw_head *head = (struct fw_head *)tp->root; struct fw_filter *f = (struct fw_filter *) *arg; struct nlattr *opt = tca[TCA_OPTIONS]; struct nlattr *tb[TCA_FW_MAX + 1]; @@ -302,7 +300,7 @@ errout: static void fw_walk(struct tcf_proto *tp, struct tcf_walker *arg) { - struct fw_head *head = (struct fw_head*)tp->root; + struct fw_head *head = (struct fw_head *)tp->root; int h; if (head == NULL) @@ -332,7 +330,7 @@ static int fw_dump(struct tcf_proto *tp, unsigned long fh, struct sk_buff *skb, struct tcmsg *t) { struct fw_head *head = (struct fw_head *)tp->root; - struct fw_filter *f = (struct fw_filter*)fh; + struct fw_filter *f = (struct fw_filter *)fh; unsigned char *b = skb_tail_pointer(skb); struct nlattr *nest; diff --git a/net/sched/cls_route.c b/net/sched/cls_route.c index 694dcd85dec..d580cdfca09 100644 --- a/net/sched/cls_route.c +++ b/net/sched/cls_route.c @@ -23,34 +23,30 @@ #include <net/pkt_cls.h> /* - 1. For now we assume that route tags < 256. - It allows to use direct table lookups, instead of hash tables. - 2. For now we assume that "from TAG" and "fromdev DEV" statements - are mutually exclusive. - 3. "to TAG from ANY" has higher priority, than "to ANY from XXX" + * 1. For now we assume that route tags < 256. + * It allows to use direct table lookups, instead of hash tables. + * 2. For now we assume that "from TAG" and "fromdev DEV" statements + * are mutually exclusive. + * 3. "to TAG from ANY" has higher priority, than "to ANY from XXX" */ -struct route4_fastmap -{ +struct route4_fastmap { struct route4_filter *filter; u32 id; int iif; }; -struct route4_head -{ +struct route4_head { struct route4_fastmap fastmap[16]; - struct route4_bucket *table[256+1]; + struct route4_bucket *table[256 + 1]; }; -struct route4_bucket -{ +struct route4_bucket { /* 16 FROM buckets + 16 IIF buckets + 1 wildcard bucket */ - struct route4_filter *ht[16+16+1]; + struct route4_filter *ht[16 + 16 + 1]; }; -struct route4_filter -{ +struct route4_filter { struct route4_filter *next; u32 id; int iif; @@ -61,20 +57,20 @@ struct route4_filter struct route4_bucket *bkt; }; -#define ROUTE4_FAILURE ((struct route4_filter*)(-1L)) +#define ROUTE4_FAILURE ((struct route4_filter *)(-1L)) static const struct tcf_ext_map route_ext_map = { .police = TCA_ROUTE4_POLICE, .action = TCA_ROUTE4_ACT }; -static __inline__ int route4_fastmap_hash(u32 id, int iif) +static inline int route4_fastmap_hash(u32 id, int iif) { - return id&0xF; + return id & 0xF; } -static inline -void route4_reset_fastmap(struct Qdisc *q, struct route4_head *head, u32 id) +static void +route4_reset_fastmap(struct Qdisc *q, struct route4_head *head, u32 id) { spinlock_t *root_lock = qdisc_root_sleeping_lock(q); @@ -83,32 +79,33 @@ void route4_reset_fastmap(struct Qdisc *q, struct route4_head *head, u32 id) spin_unlock_bh(root_lock); } -static inline void +static void route4_set_fastmap(struct route4_head *head, u32 id, int iif, struct route4_filter *f) { int h = route4_fastmap_hash(id, iif); + head->fastmap[h].id = id; head->fastmap[h].iif = iif; head->fastmap[h].filter = f; } -static __inline__ int route4_hash_to(u32 id) +static inline int route4_hash_to(u32 id) { - return id&0xFF; + return id & 0xFF; } -static __inline__ int route4_hash_from(u32 id) +static inline int route4_hash_from(u32 id) { - return (id>>16)&0xF; + return (id >> 16) & 0xF; } -static __inline__ int route4_hash_iif(int iif) +static inline int route4_hash_iif(int iif) { - return 16 + ((iif>>16)&0xF); + return 16 + ((iif >> 16) & 0xF); } -static __inline__ int route4_hash_wild(void) +static inline int route4_hash_wild(void) { return 32; } @@ -131,21 +128,22 @@ static __inline__ int route4_hash_wild(void) static int route4_classify(struct sk_buff *skb, struct tcf_proto *tp, struct tcf_result *res) { - struct route4_head *head = (struct route4_head*)tp->root; + struct route4_head *head = (struct route4_head *)tp->root; struct dst_entry *dst; struct route4_bucket *b; struct route4_filter *f; u32 id, h; int iif, dont_cache = 0; - if ((dst = skb_dst(skb)) == NULL) + dst = skb_dst(skb); + if (!dst) goto failure; id = dst->tclassid; if (head == NULL) goto old_method; - iif = ((struct rtable*)dst)->fl.iif; + iif = ((struct rtable *)dst)->fl.iif; h = route4_fastmap_hash(id, iif); if (id == head->fastmap[h].id && @@ -161,7 +159,8 @@ static int route4_classify(struct sk_buff *skb, struct tcf_proto *tp, h = route4_hash_to(id); restart: - if ((b = head->table[h]) != NULL) { + b = head->table[h]; + if (b) { for (f = b->ht[route4_hash_from(id)]; f; f = f->next) if (f->id == id) ROUTE4_APPLY_RESULT(); @@ -197,8 +196,9 @@ old_method: static inline u32 to_hash(u32 id) { - u32 h = id&0xFF; - if (id&0x8000) + u32 h = id & 0xFF; + + if (id & 0x8000) h += 256; return h; } @@ -211,17 +211,17 @@ static inline u32 from_hash(u32 id) if (!(id & 0x8000)) { if (id > 255) return 256; - return id&0xF; + return id & 0xF; } - return 16 + (id&0xF); + return 16 + (id & 0xF); } static unsigned long route4_get(struct tcf_proto *tp, u32 handle) { - struct route4_head *head = (struct route4_head*)tp->root; + struct route4_head *head = (struct route4_head *)tp->root; struct route4_bucket *b; struct route4_filter *f; - unsigned h1, h2; + unsigned int h1, h2; if (!head) return 0; @@ -230,11 +230,12 @@ static unsigned long route4_get(struct tcf_proto *tp, u32 handle) if (h1 > 256) return 0; - h2 = from_hash(handle>>16); + h2 = from_hash(handle >> 16); if (h2 > 32) return 0; - if ((b = head->table[h1]) != NULL) { + b = head->table[h1]; + if (b) { for (f = b->ht[h2]; f; f = f->next) if (f->handle == handle) return (unsigned long)f; @@ -251,7 +252,7 @@ static int route4_init(struct tcf_proto *tp) return 0; } -static inline void +static void route4_delete_filter(struct tcf_proto *tp, struct route4_filter *f) { tcf_unbind_filter(tp, &f->res); @@ -267,11 +268,12 @@ static void route4_destroy(struct tcf_proto *tp) if (head == NULL) return; - for (h1=0; h1<=256; h1++) { + for (h1 = 0; h1 <= 256; h1++) { struct route4_bucket *b; - if ((b = head->table[h1]) != NULL) { - for (h2=0; h2<=32; h2++) { + b = head->table[h1]; + if (b) { + for (h2 = 0; h2 <= 32; h2++) { struct route4_filter *f; while ((f = b->ht[h2]) != NULL) { @@ -287,9 +289,9 @@ static void route4_destroy(struct tcf_proto *tp) static int route4_delete(struct tcf_proto *tp, unsigned long arg) { - struct route4_head *head = (struct route4_head*)tp->root; - struct route4_filter **fp, *f = (struct route4_filter*)arg; - unsigned h = 0; + struct route4_head *head = (struct route4_head *)tp->root; + struct route4_filter **fp, *f = (struct route4_filter *)arg; + unsigned int h = 0; struct route4_bucket *b; int i; @@ -299,7 +301,7 @@ static int route4_delete(struct tcf_proto *tp, unsigned long arg) h = f->handle; b = f->bkt; - for (fp = &b->ht[from_hash(h>>16)]; *fp; fp = &(*fp)->next) { + for (fp = &b->ht[from_hash(h >> 16)]; *fp; fp = &(*fp)->next) { if (*fp == f) { tcf_tree_lock(tp); *fp = f->next; @@ -310,7 +312,7 @@ static int route4_delete(struct tcf_proto *tp, unsigned long arg) /* Strip tree */ - for (i=0; i<=32; i++) + for (i = 0; i <= 32; i++) if (b->ht[i]) return 0; @@ -380,7 +382,8 @@ static int route4_set_parms(struct tcf_proto *tp, unsigned long base, } h1 = to_hash(nhandle); - if ((b = head->table[h1]) == NULL) { + b = head->table[h1]; + if (!b) { err = -ENOBUFS; b = kzalloc(sizeof(struct route4_bucket), GFP_KERNEL); if (b == NULL) @@ -391,6 +394,7 @@ static int route4_set_parms(struct tcf_proto *tp, unsigned long base, tcf_tree_unlock(tp); } else { unsigned int h2 = from_hash(nhandle >> 16); + err = -EEXIST; for (fp = b->ht[h2]; fp; fp = fp->next) if (fp->handle == f->handle) @@ -444,7 +448,8 @@ static int route4_change(struct tcf_proto *tp, unsigned long base, if (err < 0) return err; - if ((f = (struct route4_filter*)*arg) != NULL) { + f = (struct route4_filter *)*arg; + if (f) { if (f->handle != handle && handle) return -EINVAL; @@ -481,7 +486,7 @@ static int route4_change(struct tcf_proto *tp, unsigned long base, reinsert: h = from_hash(f->handle >> 16); - for (fp = &f->bkt->ht[h]; (f1=*fp) != NULL; fp = &f1->next) + for (fp = &f->bkt->ht[h]; (f1 = *fp) != NULL; fp = &f1->next) if (f->handle < f1->handle) break; @@ -492,7 +497,8 @@ reinsert: if (old_handle && f->handle != old_handle) { th = to_hash(old_handle); h = from_hash(old_handle >> 16); - if ((b = head->table[th]) != NULL) { + b = head->table[th]; + if (b) { for (fp = &b->ht[h]; *fp; fp = &(*fp)->next) { if (*fp == f) { *fp = f->next; @@ -515,7 +521,7 @@ errout: static void route4_walk(struct tcf_proto *tp, struct tcf_walker *arg) { struct route4_head *head = tp->root; - unsigned h, h1; + unsigned int h, h1; if (head == NULL) arg->stop = 1; @@ -549,7 +555,7 @@ static void route4_walk(struct tcf_proto *tp, struct tcf_walker *arg) static int route4_dump(struct tcf_proto *tp, unsigned long fh, struct sk_buff *skb, struct tcmsg *t) { - struct route4_filter *f = (struct route4_filter*)fh; + struct route4_filter *f = (struct route4_filter *)fh; unsigned char *b = skb_tail_pointer(skb); struct nlattr *nest; u32 id; @@ -563,15 +569,15 @@ static int route4_dump(struct tcf_proto *tp, unsigned long fh, if (nest == NULL) goto nla_put_failure; - if (!(f->handle&0x8000)) { - id = f->id&0xFF; + if (!(f->handle & 0x8000)) { + id = f->id & 0xFF; NLA_PUT_U32(skb, TCA_ROUTE4_TO, id); } - if (f->handle&0x80000000) { - if ((f->handle>>16) != 0xFFFF) + if (f->handle & 0x80000000) { + if ((f->handle >> 16) != 0xFFFF) NLA_PUT_U32(skb, TCA_ROUTE4_IIF, f->iif); } else { - id = f->id>>16; + id = f->id >> 16; NLA_PUT_U32(skb, TCA_ROUTE4_FROM, id); } if (f->res.classid) diff --git a/net/sched/cls_rsvp.h b/net/sched/cls_rsvp.h index 425a1790b04..402c44b241a 100644 --- a/net/sched/cls_rsvp.h +++ b/net/sched/cls_rsvp.h @@ -66,28 +66,25 @@ powerful classification engine. */ -struct rsvp_head -{ +struct rsvp_head { u32 tmap[256/32]; u32 hgenerator; u8 tgenerator; struct rsvp_session *ht[256]; }; -struct rsvp_session -{ +struct rsvp_session { struct rsvp_session *next; __be32 dst[RSVP_DST_LEN]; struct tc_rsvp_gpi dpi; u8 protocol; u8 tunnelid; /* 16 (src,sport) hash slots, and one wildcard source slot */ - struct rsvp_filter *ht[16+1]; + struct rsvp_filter *ht[16 + 1]; }; -struct rsvp_filter -{ +struct rsvp_filter { struct rsvp_filter *next; __be32 src[RSVP_DST_LEN]; struct tc_rsvp_gpi spi; @@ -100,17 +97,19 @@ struct rsvp_filter struct rsvp_session *sess; }; -static __inline__ unsigned hash_dst(__be32 *dst, u8 protocol, u8 tunnelid) +static inline unsigned int hash_dst(__be32 *dst, u8 protocol, u8 tunnelid) { - unsigned h = (__force __u32)dst[RSVP_DST_LEN-1]; + unsigned int h = (__force __u32)dst[RSVP_DST_LEN - 1]; + h ^= h>>16; h ^= h>>8; return (h ^ protocol ^ tunnelid) & 0xFF; } -static __inline__ unsigned hash_src(__be32 *src) +static inline unsigned int hash_src(__be32 *src) { - unsigned h = (__force __u32)src[RSVP_DST_LEN-1]; + unsigned int h = (__force __u32)src[RSVP_DST_LEN-1]; + h ^= h>>16; h ^= h>>8; h ^= h>>4; @@ -134,10 +133,10 @@ static struct tcf_ext_map rsvp_ext_map = { static int rsvp_classify(struct sk_buff *skb, struct tcf_proto *tp, struct tcf_result *res) { - struct rsvp_session **sht = ((struct rsvp_head*)tp->root)->ht; + struct rsvp_session **sht = ((struct rsvp_head *)tp->root)->ht; struct rsvp_session *s; struct rsvp_filter *f; - unsigned h1, h2; + unsigned int h1, h2; __be32 *dst, *src; u8 protocol; u8 tunnelid = 0; @@ -162,13 +161,13 @@ restart: src = &nhptr->saddr.s6_addr32[0]; dst = &nhptr->daddr.s6_addr32[0]; protocol = nhptr->nexthdr; - xprt = ((u8*)nhptr) + sizeof(struct ipv6hdr); + xprt = ((u8 *)nhptr) + sizeof(struct ipv6hdr); #else src = &nhptr->saddr; dst = &nhptr->daddr; protocol = nhptr->protocol; - xprt = ((u8*)nhptr) + (nhptr->ihl<<2); - if (nhptr->frag_off & htons(IP_MF|IP_OFFSET)) + xprt = ((u8 *)nhptr) + (nhptr->ihl<<2); + if (nhptr->frag_off & htons(IP_MF | IP_OFFSET)) return -1; #endif @@ -176,10 +175,10 @@ restart: h2 = hash_src(src); for (s = sht[h1]; s; s = s->next) { - if (dst[RSVP_DST_LEN-1] == s->dst[RSVP_DST_LEN-1] && + if (dst[RSVP_DST_LEN-1] == s->dst[RSVP_DST_LEN - 1] && protocol == s->protocol && !(s->dpi.mask & - (*(u32*)(xprt+s->dpi.offset)^s->dpi.key)) && + (*(u32 *)(xprt + s->dpi.offset) ^ s->dpi.key)) && #if RSVP_DST_LEN == 4 dst[0] == s->dst[0] && dst[1] == s->dst[1] && @@ -188,8 +187,8 @@ restart: tunnelid == s->tunnelid) { for (f = s->ht[h2]; f; f = f->next) { - if (src[RSVP_DST_LEN-1] == f->src[RSVP_DST_LEN-1] && - !(f->spi.mask & (*(u32*)(xprt+f->spi.offset)^f->spi.key)) + if (src[RSVP_DST_LEN-1] == f->src[RSVP_DST_LEN - 1] && + !(f->spi.mask & (*(u32 *)(xprt + f->spi.offset) ^ f->spi.key)) #if RSVP_DST_LEN == 4 && src[0] == f->src[0] && @@ -205,7 +204,7 @@ matched: return 0; tunnelid = f->res.classid; - nhptr = (void*)(xprt + f->tunnelhdr - sizeof(*nhptr)); + nhptr = (void *)(xprt + f->tunnelhdr - sizeof(*nhptr)); goto restart; } } @@ -224,11 +223,11 @@ matched: static unsigned long rsvp_get(struct tcf_proto *tp, u32 handle) { - struct rsvp_session **sht = ((struct rsvp_head*)tp->root)->ht; + struct rsvp_session **sht = ((struct rsvp_head *)tp->root)->ht; struct rsvp_session *s; struct rsvp_filter *f; - unsigned h1 = handle&0xFF; - unsigned h2 = (handle>>8)&0xFF; + unsigned int h1 = handle & 0xFF; + unsigned int h2 = (handle >> 8) & 0xFF; if (h2 > 16) return 0; @@ -258,7 +257,7 @@ static int rsvp_init(struct tcf_proto *tp) return -ENOBUFS; } -static inline void +static void rsvp_delete_filter(struct tcf_proto *tp, struct rsvp_filter *f) { tcf_unbind_filter(tp, &f->res); @@ -277,13 +276,13 @@ static void rsvp_destroy(struct tcf_proto *tp) sht = data->ht; - for (h1=0; h1<256; h1++) { + for (h1 = 0; h1 < 256; h1++) { struct rsvp_session *s; while ((s = sht[h1]) != NULL) { sht[h1] = s->next; - for (h2=0; h2<=16; h2++) { + for (h2 = 0; h2 <= 16; h2++) { struct rsvp_filter *f; while ((f = s->ht[h2]) != NULL) { @@ -299,13 +298,13 @@ static void rsvp_destroy(struct tcf_proto *tp) static int rsvp_delete(struct tcf_proto *tp, unsigned long arg) { - struct rsvp_filter **fp, *f = (struct rsvp_filter*)arg; - unsigned h = f->handle; + struct rsvp_filter **fp, *f = (struct rsvp_filter *)arg; + unsigned int h = f->handle; struct rsvp_session **sp; struct rsvp_session *s = f->sess; int i; - for (fp = &s->ht[(h>>8)&0xFF]; *fp; fp = &(*fp)->next) { + for (fp = &s->ht[(h >> 8) & 0xFF]; *fp; fp = &(*fp)->next) { if (*fp == f) { tcf_tree_lock(tp); *fp = f->next; @@ -314,12 +313,12 @@ static int rsvp_delete(struct tcf_proto *tp, unsigned long arg) /* Strip tree */ - for (i=0; i<=16; i++) + for (i = 0; i <= 16; i++) if (s->ht[i]) return 0; /* OK, session has no flows */ - for (sp = &((struct rsvp_head*)tp->root)->ht[h&0xFF]; + for (sp = &((struct rsvp_head *)tp->root)->ht[h & 0xFF]; *sp; sp = &(*sp)->next) { if (*sp == s) { tcf_tree_lock(tp); @@ -337,13 +336,14 @@ static int rsvp_delete(struct tcf_proto *tp, unsigned long arg) return 0; } -static unsigned gen_handle(struct tcf_proto *tp, unsigned salt) +static unsigned int gen_handle(struct tcf_proto *tp, unsigned salt) { struct rsvp_head *data = tp->root; int i = 0xFFFF; while (i-- > 0) { u32 h; + if ((data->hgenerator += 0x10000) == 0) data->hgenerator = 0x10000; h = data->hgenerator|salt; @@ -355,10 +355,10 @@ static unsigned gen_handle(struct tcf_proto *tp, unsigned salt) static int tunnel_bts(struct rsvp_head *data) { - int n = data->tgenerator>>5; - u32 b = 1<<(data->tgenerator&0x1F); + int n = data->tgenerator >> 5; + u32 b = 1 << (data->tgenerator & 0x1F); - if (data->tmap[n]&b) + if (data->tmap[n] & b) return 0; data->tmap[n] |= b; return 1; @@ -372,10 +372,10 @@ static void tunnel_recycle(struct rsvp_head *data) memset(tmap, 0, sizeof(tmap)); - for (h1=0; h1<256; h1++) { + for (h1 = 0; h1 < 256; h1++) { struct rsvp_session *s; for (s = sht[h1]; s; s = s->next) { - for (h2=0; h2<=16; h2++) { + for (h2 = 0; h2 <= 16; h2++) { struct rsvp_filter *f; for (f = s->ht[h2]; f; f = f->next) { @@ -395,8 +395,8 @@ static u32 gen_tunnel(struct rsvp_head *data) { int i, k; - for (k=0; k<2; k++) { - for (i=255; i>0; i--) { + for (k = 0; k < 2; k++) { + for (i = 255; i > 0; i--) { if (++data->tgenerator == 0) data->tgenerator = 1; if (tunnel_bts(data)) @@ -428,7 +428,7 @@ static int rsvp_change(struct tcf_proto *tp, unsigned long base, struct nlattr *opt = tca[TCA_OPTIONS-1]; struct nlattr *tb[TCA_RSVP_MAX + 1]; struct tcf_exts e; - unsigned h1, h2; + unsigned int h1, h2; __be32 *dst; int err; @@ -443,7 +443,8 @@ static int rsvp_change(struct tcf_proto *tp, unsigned long base, if (err < 0) return err; - if ((f = (struct rsvp_filter*)*arg) != NULL) { + f = (struct rsvp_filter *)*arg; + if (f) { /* Node exists: adjust only classid */ if (f->handle != handle && handle) @@ -500,7 +501,7 @@ static int rsvp_change(struct tcf_proto *tp, unsigned long base, goto errout; } - for (sp = &data->ht[h1]; (s=*sp) != NULL; sp = &s->next) { + for (sp = &data->ht[h1]; (s = *sp) != NULL; sp = &s->next) { if (dst[RSVP_DST_LEN-1] == s->dst[RSVP_DST_LEN-1] && pinfo && pinfo->protocol == s->protocol && memcmp(&pinfo->dpi, &s->dpi, sizeof(s->dpi)) == 0 && @@ -523,7 +524,7 @@ insert: tcf_exts_change(tp, &f->exts, &e); for (fp = &s->ht[h2]; *fp; fp = &(*fp)->next) - if (((*fp)->spi.mask&f->spi.mask) != f->spi.mask) + if (((*fp)->spi.mask & f->spi.mask) != f->spi.mask) break; f->next = *fp; wmb(); @@ -567,7 +568,7 @@ errout2: static void rsvp_walk(struct tcf_proto *tp, struct tcf_walker *arg) { struct rsvp_head *head = tp->root; - unsigned h, h1; + unsigned int h, h1; if (arg->stop) return; @@ -598,7 +599,7 @@ static void rsvp_walk(struct tcf_proto *tp, struct tcf_walker *arg) static int rsvp_dump(struct tcf_proto *tp, unsigned long fh, struct sk_buff *skb, struct tcmsg *t) { - struct rsvp_filter *f = (struct rsvp_filter*)fh; + struct rsvp_filter *f = (struct rsvp_filter *)fh; struct rsvp_session *s; unsigned char *b = skb_tail_pointer(skb); struct nlattr *nest; @@ -624,7 +625,7 @@ static int rsvp_dump(struct tcf_proto *tp, unsigned long fh, NLA_PUT(skb, TCA_RSVP_PINFO, sizeof(pinfo), &pinfo); if (f->res.classid) NLA_PUT_U32(skb, TCA_RSVP_CLASSID, f->res.classid); - if (((f->handle>>8)&0xFF) != 16) + if (((f->handle >> 8) & 0xFF) != 16) NLA_PUT(skb, TCA_RSVP_SRC, sizeof(f->src), f->src); if (tcf_exts_dump(skb, &f->exts, &rsvp_ext_map) < 0) diff --git a/net/sched/cls_tcindex.c b/net/sched/cls_tcindex.c index 20ef330bb91..36667fa6423 100644 --- a/net/sched/cls_tcindex.c +++ b/net/sched/cls_tcindex.c @@ -249,7 +249,7 @@ tcindex_set_parms(struct tcf_proto *tp, unsigned long base, u32 handle, * of the hashing index is below the threshold. */ if ((cp.mask >> cp.shift) < PERFECT_HASH_THRESHOLD) - cp.hash = (cp.mask >> cp.shift)+1; + cp.hash = (cp.mask >> cp.shift) + 1; else cp.hash = DEFAULT_HASH_SIZE; } diff --git a/net/sched/cls_u32.c b/net/sched/cls_u32.c index b0c2a82178a..3b93fc0c895 100644 --- a/net/sched/cls_u32.c +++ b/net/sched/cls_u32.c @@ -42,8 +42,7 @@ #include <net/act_api.h> #include <net/pkt_cls.h> -struct tc_u_knode -{ +struct tc_u_knode { struct tc_u_knode *next; u32 handle; struct tc_u_hnode *ht_up; @@ -63,19 +62,17 @@ struct tc_u_knode struct tc_u32_sel sel; }; -struct tc_u_hnode -{ +struct tc_u_hnode { struct tc_u_hnode *next; u32 handle; u32 prio; struct tc_u_common *tp_c; int refcnt; - unsigned divisor; + unsigned int divisor; struct tc_u_knode *ht[1]; }; -struct tc_u_common -{ +struct tc_u_common { struct tc_u_hnode *hlist; struct Qdisc *q; int refcnt; @@ -87,9 +84,11 @@ static const struct tcf_ext_map u32_ext_map = { .police = TCA_U32_POLICE }; -static __inline__ unsigned u32_hash_fold(__be32 key, struct tc_u32_sel *sel, u8 fshift) +static inline unsigned int u32_hash_fold(__be32 key, + const struct tc_u32_sel *sel, + u8 fshift) { - unsigned h = ntohl(key & sel->hmask)>>fshift; + unsigned int h = ntohl(key & sel->hmask) >> fshift; return h; } @@ -101,7 +100,7 @@ static int u32_classify(struct sk_buff *skb, struct tcf_proto *tp, struct tcf_re unsigned int off; } stack[TC_U32_MAXDEPTH]; - struct tc_u_hnode *ht = (struct tc_u_hnode*)tp->root; + struct tc_u_hnode *ht = (struct tc_u_hnode *)tp->root; unsigned int off = skb_network_offset(skb); struct tc_u_knode *n; int sdepth = 0; @@ -120,7 +119,7 @@ next_knode: struct tc_u32_key *key = n->sel.keys; #ifdef CONFIG_CLS_U32_PERF - n->pf->rcnt +=1; + n->pf->rcnt += 1; j = 0; #endif @@ -133,14 +132,14 @@ next_knode: } #endif - for (i = n->sel.nkeys; i>0; i--, key++) { + for (i = n->sel.nkeys; i > 0; i--, key++) { int toff = off + key->off + (off2 & key->offmask); - __be32 *data, _data; + __be32 *data, hdata; if (skb_headroom(skb) + toff > INT_MAX) goto out; - data = skb_header_pointer(skb, toff, 4, &_data); + data = skb_header_pointer(skb, toff, 4, &hdata); if (!data) goto out; if ((*data ^ key->val) & key->mask) { @@ -148,13 +147,13 @@ next_knode: goto next_knode; } #ifdef CONFIG_CLS_U32_PERF - n->pf->kcnts[j] +=1; + n->pf->kcnts[j] += 1; j++; #endif } if (n->ht_down == NULL) { check_terminal: - if (n->sel.flags&TC_U32_TERMINAL) { + if (n->sel.flags & TC_U32_TERMINAL) { *res = n->res; #ifdef CONFIG_NET_CLS_IND @@ -164,7 +163,7 @@ check_terminal: } #endif #ifdef CONFIG_CLS_U32_PERF - n->pf->rhit +=1; + n->pf->rhit += 1; #endif r = tcf_exts_exec(skb, &n->exts, res); if (r < 0) { @@ -188,26 +187,26 @@ check_terminal: ht = n->ht_down; sel = 0; if (ht->divisor) { - __be32 *data, _data; + __be32 *data, hdata; data = skb_header_pointer(skb, off + n->sel.hoff, 4, - &_data); + &hdata); if (!data) goto out; sel = ht->divisor & u32_hash_fold(*data, &n->sel, n->fshift); } - if (!(n->sel.flags&(TC_U32_VAROFFSET|TC_U32_OFFSET|TC_U32_EAT))) + if (!(n->sel.flags & (TC_U32_VAROFFSET | TC_U32_OFFSET | TC_U32_EAT))) goto next_ht; - if (n->sel.flags&(TC_U32_OFFSET|TC_U32_VAROFFSET)) { + if (n->sel.flags & (TC_U32_OFFSET | TC_U32_VAROFFSET)) { off2 = n->sel.off + 3; if (n->sel.flags & TC_U32_VAROFFSET) { - __be16 *data, _data; + __be16 *data, hdata; data = skb_header_pointer(skb, off + n->sel.offoff, - 2, &_data); + 2, &hdata); if (!data) goto out; off2 += ntohs(n->sel.offmask & *data) >> @@ -215,7 +214,7 @@ check_terminal: } off2 &= ~3; } - if (n->sel.flags&TC_U32_EAT) { + if (n->sel.flags & TC_U32_EAT) { off += off2; off2 = 0; } @@ -236,11 +235,11 @@ out: deadloop: if (net_ratelimit()) - printk(KERN_WARNING "cls_u32: dead loop\n"); + pr_warning("cls_u32: dead loop\n"); return -1; } -static __inline__ struct tc_u_hnode * +static struct tc_u_hnode * u32_lookup_ht(struct tc_u_common *tp_c, u32 handle) { struct tc_u_hnode *ht; @@ -252,10 +251,10 @@ u32_lookup_ht(struct tc_u_common *tp_c, u32 handle) return ht; } -static __inline__ struct tc_u_knode * +static struct tc_u_knode * u32_lookup_key(struct tc_u_hnode *ht, u32 handle) { - unsigned sel; + unsigned int sel; struct tc_u_knode *n = NULL; sel = TC_U32_HASH(handle); @@ -300,7 +299,7 @@ static u32 gen_new_htid(struct tc_u_common *tp_c) do { if (++tp_c->hgenerator == 0x7FF) tp_c->hgenerator = 1; - } while (--i>0 && u32_lookup_ht(tp_c, (tp_c->hgenerator|0x800)<<20)); + } while (--i > 0 && u32_lookup_ht(tp_c, (tp_c->hgenerator|0x800)<<20)); return i > 0 ? (tp_c->hgenerator|0x800)<<20 : 0; } @@ -378,9 +377,9 @@ static int u32_delete_key(struct tcf_proto *tp, struct tc_u_knode* key) static void u32_clear_hnode(struct tcf_proto *tp, struct tc_u_hnode *ht) { struct tc_u_knode *n; - unsigned h; + unsigned int h; - for (h=0; h<=ht->divisor; h++) { + for (h = 0; h <= ht->divisor; h++) { while ((n = ht->ht[h]) != NULL) { ht->ht[h] = n->next; @@ -446,13 +445,13 @@ static void u32_destroy(struct tcf_proto *tp) static int u32_delete(struct tcf_proto *tp, unsigned long arg) { - struct tc_u_hnode *ht = (struct tc_u_hnode*)arg; + struct tc_u_hnode *ht = (struct tc_u_hnode *)arg; if (ht == NULL) return 0; if (TC_U32_KEY(ht->handle)) - return u32_delete_key(tp, (struct tc_u_knode*)ht); + return u32_delete_key(tp, (struct tc_u_knode *)ht); if (tp->root == ht) return -EINVAL; @@ -470,14 +469,14 @@ static int u32_delete(struct tcf_proto *tp, unsigned long arg) static u32 gen_new_kid(struct tc_u_hnode *ht, u32 handle) { struct tc_u_knode *n; - unsigned i = 0x7FF; + unsigned int i = 0x7FF; - for (n=ht->ht[TC_U32_HASH(handle)]; n; n = n->next) + for (n = ht->ht[TC_U32_HASH(handle)]; n; n = n->next) if (i < TC_U32_NODE(n->handle)) i = TC_U32_NODE(n->handle); i++; - return handle|(i>0xFFF ? 0xFFF : i); + return handle | (i > 0xFFF ? 0xFFF : i); } static const struct nla_policy u32_policy[TCA_U32_MAX + 1] = { @@ -566,7 +565,8 @@ static int u32_change(struct tcf_proto *tp, unsigned long base, u32 handle, if (err < 0) return err; - if ((n = (struct tc_u_knode*)*arg) != NULL) { + n = (struct tc_u_knode *)*arg; + if (n) { if (TC_U32_KEY(n->handle) == 0) return -EINVAL; @@ -574,7 +574,7 @@ static int u32_change(struct tcf_proto *tp, unsigned long base, u32 handle, } if (tb[TCA_U32_DIVISOR]) { - unsigned divisor = nla_get_u32(tb[TCA_U32_DIVISOR]); + unsigned int divisor = nla_get_u32(tb[TCA_U32_DIVISOR]); if (--divisor > 0x100) return -EINVAL; @@ -585,7 +585,7 @@ static int u32_change(struct tcf_proto *tp, unsigned long base, u32 handle, if (handle == 0) return -ENOMEM; } - ht = kzalloc(sizeof(*ht) + divisor*sizeof(void*), GFP_KERNEL); + ht = kzalloc(sizeof(*ht) + divisor*sizeof(void *), GFP_KERNEL); if (ht == NULL) return -ENOBUFS; ht->tp_c = tp_c; @@ -683,7 +683,7 @@ static void u32_walk(struct tcf_proto *tp, struct tcf_walker *arg) struct tc_u_common *tp_c = tp->data; struct tc_u_hnode *ht; struct tc_u_knode *n; - unsigned h; + unsigned int h; if (arg->stop) return; @@ -717,7 +717,7 @@ static void u32_walk(struct tcf_proto *tp, struct tcf_walker *arg) static int u32_dump(struct tcf_proto *tp, unsigned long fh, struct sk_buff *skb, struct tcmsg *t) { - struct tc_u_knode *n = (struct tc_u_knode*)fh; + struct tc_u_knode *n = (struct tc_u_knode *)fh; struct nlattr *nest; if (n == NULL) @@ -730,8 +730,9 @@ static int u32_dump(struct tcf_proto *tp, unsigned long fh, goto nla_put_failure; if (TC_U32_KEY(n->handle) == 0) { - struct tc_u_hnode *ht = (struct tc_u_hnode*)fh; - u32 divisor = ht->divisor+1; + struct tc_u_hnode *ht = (struct tc_u_hnode *)fh; + u32 divisor = ht->divisor + 1; + NLA_PUT_U32(skb, TCA_U32_DIVISOR, divisor); } else { NLA_PUT(skb, TCA_U32_SEL, @@ -755,7 +756,7 @@ static int u32_dump(struct tcf_proto *tp, unsigned long fh, goto nla_put_failure; #ifdef CONFIG_NET_CLS_IND - if(strlen(n->indev)) + if (strlen(n->indev)) NLA_PUT_STRING(skb, TCA_U32_INDEV, n->indev); #endif #ifdef CONFIG_CLS_U32_PERF diff --git a/net/sched/em_cmp.c b/net/sched/em_cmp.c index bc450397487..1c8360a2752 100644 --- a/net/sched/em_cmp.c +++ b/net/sched/em_cmp.c @@ -33,40 +33,41 @@ static int em_cmp_match(struct sk_buff *skb, struct tcf_ematch *em, return 0; switch (cmp->align) { - case TCF_EM_ALIGN_U8: - val = *ptr; - break; + case TCF_EM_ALIGN_U8: + val = *ptr; + break; - case TCF_EM_ALIGN_U16: - val = get_unaligned_be16(ptr); + case TCF_EM_ALIGN_U16: + val = get_unaligned_be16(ptr); - if (cmp_needs_transformation(cmp)) - val = be16_to_cpu(val); - break; + if (cmp_needs_transformation(cmp)) + val = be16_to_cpu(val); + break; - case TCF_EM_ALIGN_U32: - /* Worth checking boundries? The branching seems - * to get worse. Visit again. */ - val = get_unaligned_be32(ptr); + case TCF_EM_ALIGN_U32: + /* Worth checking boundries? The branching seems + * to get worse. Visit again. + */ + val = get_unaligned_be32(ptr); - if (cmp_needs_transformation(cmp)) - val = be32_to_cpu(val); - break; + if (cmp_needs_transformation(cmp)) + val = be32_to_cpu(val); + break; - default: - return 0; + default: + return 0; } if (cmp->mask) val &= cmp->mask; switch (cmp->opnd) { - case TCF_EM_OPND_EQ: - return val == cmp->val; - case TCF_EM_OPND_LT: - return val < cmp->val; - case TCF_EM_OPND_GT: - return val > cmp->val; + case TCF_EM_OPND_EQ: + return val == cmp->val; + case TCF_EM_OPND_LT: + return val < cmp->val; + case TCF_EM_OPND_GT: + return val > cmp->val; } return 0; diff --git a/net/sched/em_meta.c b/net/sched/em_meta.c index 34da5e29ea1..e5e17478267 100644 --- a/net/sched/em_meta.c +++ b/net/sched/em_meta.c @@ -73,21 +73,18 @@ #include <net/pkt_cls.h> #include <net/sock.h> -struct meta_obj -{ +struct meta_obj { unsigned long value; unsigned int len; }; -struct meta_value -{ +struct meta_value { struct tcf_meta_val hdr; unsigned long val; unsigned int len; }; -struct meta_match -{ +struct meta_match { struct meta_value lvalue; struct meta_value rvalue; }; @@ -255,7 +252,7 @@ META_COLLECTOR(int_rtclassid) if (unlikely(skb_dst(skb) == NULL)) *err = -1; else -#ifdef CONFIG_NET_CLS_ROUTE +#ifdef CONFIG_IP_ROUTE_CLASSID dst->value = skb_dst(skb)->tclassid; #else dst->value = 0; @@ -404,7 +401,7 @@ META_COLLECTOR(int_sk_sndbuf) META_COLLECTOR(int_sk_alloc) { SKIP_NONLOCAL(skb); - dst->value = skb->sk->sk_allocation; + dst->value = (__force int) skb->sk->sk_allocation; } META_COLLECTOR(int_sk_route_caps) @@ -483,8 +480,7 @@ META_COLLECTOR(int_sk_write_pend) * Meta value collectors assignment table **************************************************************************/ -struct meta_ops -{ +struct meta_ops { void (*get)(struct sk_buff *, struct tcf_pkt_info *, struct meta_value *, struct meta_obj *, int *); }; @@ -494,7 +490,7 @@ struct meta_ops /* Meta value operations table listing all meta value collectors and * assigns them to a type and meta id. */ -static struct meta_ops __meta_ops[TCF_META_TYPE_MAX+1][TCF_META_ID_MAX+1] = { +static struct meta_ops __meta_ops[TCF_META_TYPE_MAX + 1][TCF_META_ID_MAX + 1] = { [TCF_META_TYPE_VAR] = { [META_ID(DEV)] = META_FUNC(var_dev), [META_ID(SK_BOUND_IF)] = META_FUNC(var_sk_bound_if), @@ -550,7 +546,7 @@ static struct meta_ops __meta_ops[TCF_META_TYPE_MAX+1][TCF_META_ID_MAX+1] = { } }; -static inline struct meta_ops * meta_ops(struct meta_value *val) +static inline struct meta_ops *meta_ops(struct meta_value *val) { return &__meta_ops[meta_type(val)][meta_id(val)]; } @@ -649,9 +645,8 @@ static int meta_int_dump(struct sk_buff *skb, struct meta_value *v, int tlv) { if (v->len == sizeof(unsigned long)) NLA_PUT(skb, tlv, sizeof(unsigned long), &v->val); - else if (v->len == sizeof(u32)) { + else if (v->len == sizeof(u32)) NLA_PUT_U32(skb, tlv, v->val); - } return 0; @@ -663,8 +658,7 @@ nla_put_failure: * Type specific operations table **************************************************************************/ -struct meta_type_ops -{ +struct meta_type_ops { void (*destroy)(struct meta_value *); int (*compare)(struct meta_obj *, struct meta_obj *); int (*change)(struct meta_value *, struct nlattr *); @@ -672,7 +666,7 @@ struct meta_type_ops int (*dump)(struct sk_buff *, struct meta_value *, int); }; -static struct meta_type_ops __meta_type_ops[TCF_META_TYPE_MAX+1] = { +static struct meta_type_ops __meta_type_ops[TCF_META_TYPE_MAX + 1] = { [TCF_META_TYPE_VAR] = { .destroy = meta_var_destroy, .compare = meta_var_compare, @@ -688,7 +682,7 @@ static struct meta_type_ops __meta_type_ops[TCF_META_TYPE_MAX+1] = { } }; -static inline struct meta_type_ops * meta_type_ops(struct meta_value *v) +static inline struct meta_type_ops *meta_type_ops(struct meta_value *v) { return &__meta_type_ops[meta_type(v)]; } @@ -713,7 +707,7 @@ static int meta_get(struct sk_buff *skb, struct tcf_pkt_info *info, return err; if (meta_type_ops(v)->apply_extras) - meta_type_ops(v)->apply_extras(v, dst); + meta_type_ops(v)->apply_extras(v, dst); return 0; } @@ -732,12 +726,12 @@ static int em_meta_match(struct sk_buff *skb, struct tcf_ematch *m, r = meta_type_ops(&meta->lvalue)->compare(&l_value, &r_value); switch (meta->lvalue.hdr.op) { - case TCF_EM_OPND_EQ: - return !r; - case TCF_EM_OPND_LT: - return r < 0; - case TCF_EM_OPND_GT: - return r > 0; + case TCF_EM_OPND_EQ: + return !r; + case TCF_EM_OPND_LT: + return r < 0; + case TCF_EM_OPND_GT: + return r > 0; } return 0; @@ -771,7 +765,7 @@ static inline int meta_change_data(struct meta_value *dst, struct nlattr *nla) static inline int meta_is_supported(struct meta_value *val) { - return (!meta_id(val) || meta_ops(val)->get); + return !meta_id(val) || meta_ops(val)->get; } static const struct nla_policy meta_policy[TCA_EM_META_MAX + 1] = { diff --git a/net/sched/em_nbyte.c b/net/sched/em_nbyte.c index 1a4176aee6e..a3bed07a008 100644 --- a/net/sched/em_nbyte.c +++ b/net/sched/em_nbyte.c @@ -18,8 +18,7 @@ #include <linux/tc_ematch/tc_em_nbyte.h> #include <net/pkt_cls.h> -struct nbyte_data -{ +struct nbyte_data { struct tcf_em_nbyte hdr; char pattern[0]; }; diff --git a/net/sched/em_text.c b/net/sched/em_text.c index ea8f566e720..15d353d2e4b 100644 --- a/net/sched/em_text.c +++ b/net/sched/em_text.c @@ -19,8 +19,7 @@ #include <linux/tc_ematch/tc_em_text.h> #include <net/pkt_cls.h> -struct text_match -{ +struct text_match { u16 from_offset; u16 to_offset; u8 from_layer; diff --git a/net/sched/em_u32.c b/net/sched/em_u32.c index 953f1479f7d..797bdb88c01 100644 --- a/net/sched/em_u32.c +++ b/net/sched/em_u32.c @@ -35,7 +35,7 @@ static int em_u32_match(struct sk_buff *skb, struct tcf_ematch *em, if (!tcf_valid_offset(skb, ptr, sizeof(u32))) return 0; - return !(((*(__be32*) ptr) ^ key->val) & key->mask); + return !(((*(__be32 *) ptr) ^ key->val) & key->mask); } static struct tcf_ematch_ops em_u32_ops = { diff --git a/net/sched/ematch.c b/net/sched/ematch.c index 5e37da961f8..88d93eb9250 100644 --- a/net/sched/ematch.c +++ b/net/sched/ematch.c @@ -93,7 +93,7 @@ static LIST_HEAD(ematch_ops); static DEFINE_RWLOCK(ematch_mod_lock); -static inline struct tcf_ematch_ops * tcf_em_lookup(u16 kind) +static struct tcf_ematch_ops *tcf_em_lookup(u16 kind) { struct tcf_ematch_ops *e = NULL; @@ -163,8 +163,8 @@ void tcf_em_unregister(struct tcf_ematch_ops *ops) } EXPORT_SYMBOL(tcf_em_unregister); -static inline struct tcf_ematch * tcf_em_get_match(struct tcf_ematch_tree *tree, - int index) +static inline struct tcf_ematch *tcf_em_get_match(struct tcf_ematch_tree *tree, + int index) { return &tree->matches[index]; } @@ -184,7 +184,8 @@ static int tcf_em_validate(struct tcf_proto *tp, if (em_hdr->kind == TCF_EM_CONTAINER) { /* Special ematch called "container", carries an index - * referencing an external ematch sequence. */ + * referencing an external ematch sequence. + */ u32 ref; if (data_len < sizeof(ref)) @@ -195,7 +196,8 @@ static int tcf_em_validate(struct tcf_proto *tp, goto errout; /* We do not allow backward jumps to avoid loops and jumps - * to our own position are of course illegal. */ + * to our own position are of course illegal. + */ if (ref <= idx) goto errout; @@ -208,7 +210,8 @@ static int tcf_em_validate(struct tcf_proto *tp, * which automatically releases the reference again, therefore * the module MUST not be given back under any circumstances * here. Be aware, the destroy function assumes that the - * module is held if the ops field is non zero. */ + * module is held if the ops field is non zero. + */ em->ops = tcf_em_lookup(em_hdr->kind); if (em->ops == NULL) { @@ -221,7 +224,8 @@ static int tcf_em_validate(struct tcf_proto *tp, if (em->ops) { /* We dropped the RTNL mutex in order to * perform the module load. Tell the caller - * to replay the request. */ + * to replay the request. + */ module_put(em->ops->owner); err = -EAGAIN; } @@ -230,7 +234,8 @@ static int tcf_em_validate(struct tcf_proto *tp, } /* ematch module provides expected length of data, so we - * can do a basic sanity check. */ + * can do a basic sanity check. + */ if (em->ops->datalen && data_len < em->ops->datalen) goto errout; @@ -246,7 +251,8 @@ static int tcf_em_validate(struct tcf_proto *tp, * TCF_EM_SIMPLE may be specified stating that the * data only consists of a u32 integer and the module * does not expected a memory reference but rather - * the value carried. */ + * the value carried. + */ if (em_hdr->flags & TCF_EM_SIMPLE) { if (data_len < sizeof(u32)) goto errout; @@ -334,7 +340,8 @@ int tcf_em_tree_validate(struct tcf_proto *tp, struct nlattr *nla, * The array of rt attributes is parsed in the order as they are * provided, their type must be incremental from 1 to n. Even * if it does not serve any real purpose, a failure of sticking - * to this policy will result in parsing failure. */ + * to this policy will result in parsing failure. + */ for (idx = 0; nla_ok(rt_match, list_len); idx++) { err = -EINVAL; @@ -359,7 +366,8 @@ int tcf_em_tree_validate(struct tcf_proto *tp, struct nlattr *nla, /* Check if the number of matches provided by userspace actually * complies with the array of matches. The number was used for * the validation of references and a mismatch could lead to - * undefined references during the matching process. */ + * undefined references during the matching process. + */ if (idx != tree_hdr->nmatches) { err = -EINVAL; goto errout_abort; @@ -449,7 +457,7 @@ int tcf_em_tree_dump(struct sk_buff *skb, struct tcf_ematch_tree *tree, int tlv) .flags = em->flags }; - NLA_PUT(skb, i+1, sizeof(em_hdr), &em_hdr); + NLA_PUT(skb, i + 1, sizeof(em_hdr), &em_hdr); if (em->ops && em->ops->dump) { if (em->ops->dump(skb, em) < 0) @@ -478,6 +486,7 @@ static inline int tcf_em_match(struct sk_buff *skb, struct tcf_ematch *em, struct tcf_pkt_info *info) { int r = em->ops->match(skb, em, info); + return tcf_em_is_inverted(em) ? !r : r; } @@ -527,8 +536,8 @@ pop_stack: stack_overflow: if (net_ratelimit()) - printk(KERN_WARNING "tc ematch: local stack overflow," - " increase NET_EMATCH_STACK\n"); + pr_warning("tc ematch: local stack overflow," + " increase NET_EMATCH_STACK\n"); return -1; } EXPORT_SYMBOL(__tcf_em_tree_match); diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c index b22ca2d1ceb..7490f3f2db8 100644 --- a/net/sched/sch_api.c +++ b/net/sched/sch_api.c @@ -187,7 +187,7 @@ int unregister_qdisc(struct Qdisc_ops *qops) int err = -ENOENT; write_lock(&qdisc_mod_lock); - for (qp = &qdisc_base; (q=*qp)!=NULL; qp = &q->next) + for (qp = &qdisc_base; (q = *qp) != NULL; qp = &q->next) if (q == qops) break; if (q) { @@ -321,7 +321,9 @@ void qdisc_put_rtab(struct qdisc_rate_table *tab) if (!tab || --tab->refcnt) return; - for (rtabp = &qdisc_rtab_list; (rtab=*rtabp) != NULL; rtabp = &rtab->next) { + for (rtabp = &qdisc_rtab_list; + (rtab = *rtabp) != NULL; + rtabp = &rtab->next) { if (rtab == tab) { *rtabp = rtab->next; kfree(rtab); @@ -396,6 +398,11 @@ static struct qdisc_size_table *qdisc_get_stab(struct nlattr *opt) return stab; } +static void stab_kfree_rcu(struct rcu_head *head) +{ + kfree(container_of(head, struct qdisc_size_table, rcu)); +} + void qdisc_put_stab(struct qdisc_size_table *tab) { if (!tab) @@ -405,7 +412,7 @@ void qdisc_put_stab(struct qdisc_size_table *tab) if (--tab->refcnt == 0) { list_del(&tab->list); - kfree(tab); + call_rcu_bh(&tab->rcu, stab_kfree_rcu); } spin_unlock(&qdisc_stab_lock); @@ -428,7 +435,7 @@ nla_put_failure: return -1; } -void qdisc_calculate_pkt_len(struct sk_buff *skb, struct qdisc_size_table *stab) +void __qdisc_calculate_pkt_len(struct sk_buff *skb, const struct qdisc_size_table *stab) { int pkt_len, slot; @@ -454,14 +461,13 @@ out: pkt_len = 1; qdisc_skb_cb(skb)->pkt_len = pkt_len; } -EXPORT_SYMBOL(qdisc_calculate_pkt_len); +EXPORT_SYMBOL(__qdisc_calculate_pkt_len); void qdisc_warn_nonwc(char *txt, struct Qdisc *qdisc) { if (!(qdisc->flags & TCQ_F_WARN_NONWC)) { - printk(KERN_WARNING - "%s: %s qdisc %X: is non-work-conserving?\n", - txt, qdisc->ops->id, qdisc->handle >> 16); + pr_warn("%s: %s qdisc %X: is non-work-conserving?\n", + txt, qdisc->ops->id, qdisc->handle >> 16); qdisc->flags |= TCQ_F_WARN_NONWC; } } @@ -472,7 +478,7 @@ static enum hrtimer_restart qdisc_watchdog(struct hrtimer *timer) struct qdisc_watchdog *wd = container_of(timer, struct qdisc_watchdog, timer); - wd->qdisc->flags &= ~TCQ_F_THROTTLED; + qdisc_unthrottled(wd->qdisc); __netif_schedule(qdisc_root(wd->qdisc)); return HRTIMER_NORESTART; @@ -494,7 +500,7 @@ void qdisc_watchdog_schedule(struct qdisc_watchdog *wd, psched_time_t expires) &qdisc_root_sleeping(wd->qdisc)->state)) return; - wd->qdisc->flags |= TCQ_F_THROTTLED; + qdisc_throttled(wd->qdisc); time = ktime_set(0, 0); time = ktime_add_ns(time, PSCHED_TICKS2NS(expires)); hrtimer_start(&wd->timer, time, HRTIMER_MODE_ABS); @@ -504,7 +510,7 @@ EXPORT_SYMBOL(qdisc_watchdog_schedule); void qdisc_watchdog_cancel(struct qdisc_watchdog *wd) { hrtimer_cancel(&wd->timer); - wd->qdisc->flags &= ~TCQ_F_THROTTLED; + qdisc_unthrottled(wd->qdisc); } EXPORT_SYMBOL(qdisc_watchdog_cancel); @@ -625,7 +631,7 @@ static u32 qdisc_alloc_handle(struct net_device *dev) autohandle = TC_H_MAKE(0x80000000U, 0); } while (qdisc_lookup(dev, autohandle) && --i > 0); - return i>0 ? autohandle : 0; + return i > 0 ? autohandle : 0; } void qdisc_tree_decrease_qlen(struct Qdisc *sch, unsigned int n) @@ -834,7 +840,7 @@ qdisc_create(struct net_device *dev, struct netdev_queue *dev_queue, err = PTR_ERR(stab); goto err_out4; } - sch->stab = stab; + rcu_assign_pointer(sch->stab, stab); } if (tca[TCA_RATE]) { spinlock_t *root_lock; @@ -874,7 +880,7 @@ err_out4: * Any broken qdiscs that would require a ops->reset() here? * The qdisc was never in action so it shouldn't be necessary. */ - qdisc_put_stab(sch->stab); + qdisc_put_stab(rtnl_dereference(sch->stab)); if (ops->destroy) ops->destroy(sch); goto err_out3; @@ -882,7 +888,7 @@ err_out4: static int qdisc_change(struct Qdisc *sch, struct nlattr **tca) { - struct qdisc_size_table *stab = NULL; + struct qdisc_size_table *ostab, *stab = NULL; int err = 0; if (tca[TCA_OPTIONS]) { @@ -899,8 +905,9 @@ static int qdisc_change(struct Qdisc *sch, struct nlattr **tca) return PTR_ERR(stab); } - qdisc_put_stab(sch->stab); - sch->stab = stab; + ostab = rtnl_dereference(sch->stab); + rcu_assign_pointer(sch->stab, stab); + qdisc_put_stab(ostab); if (tca[TCA_RATE]) { /* NB: ignores errors from replace_estimator @@ -915,9 +922,8 @@ out: return 0; } -struct check_loop_arg -{ - struct qdisc_walker w; +struct check_loop_arg { + struct qdisc_walker w; struct Qdisc *p; int depth; }; @@ -970,7 +976,8 @@ static int tc_get_qdisc(struct sk_buff *skb, struct nlmsghdr *n, void *arg) struct Qdisc *p = NULL; int err; - if ((dev = __dev_get_by_index(net, tcm->tcm_ifindex)) == NULL) + dev = __dev_get_by_index(net, tcm->tcm_ifindex); + if (!dev) return -ENODEV; err = nlmsg_parse(n, sizeof(*tcm), tca, TCA_MAX, NULL); @@ -980,12 +987,12 @@ static int tc_get_qdisc(struct sk_buff *skb, struct nlmsghdr *n, void *arg) if (clid) { if (clid != TC_H_ROOT) { if (TC_H_MAJ(clid) != TC_H_MAJ(TC_H_INGRESS)) { - if ((p = qdisc_lookup(dev, TC_H_MAJ(clid))) == NULL) + p = qdisc_lookup(dev, TC_H_MAJ(clid)); + if (!p) return -ENOENT; q = qdisc_leaf(p, clid); - } else { /* ingress */ - if (dev_ingress_queue(dev)) - q = dev_ingress_queue(dev)->qdisc_sleeping; + } else if (dev_ingress_queue(dev)) { + q = dev_ingress_queue(dev)->qdisc_sleeping; } } else { q = dev->qdisc; @@ -996,7 +1003,8 @@ static int tc_get_qdisc(struct sk_buff *skb, struct nlmsghdr *n, void *arg) if (tcm->tcm_handle && q->handle != tcm->tcm_handle) return -EINVAL; } else { - if ((q = qdisc_lookup(dev, tcm->tcm_handle)) == NULL) + q = qdisc_lookup(dev, tcm->tcm_handle); + if (!q) return -ENOENT; } @@ -1008,7 +1016,8 @@ static int tc_get_qdisc(struct sk_buff *skb, struct nlmsghdr *n, void *arg) return -EINVAL; if (q->handle == 0) return -ENOENT; - if ((err = qdisc_graft(dev, p, skb, n, clid, NULL, q)) != 0) + err = qdisc_graft(dev, p, skb, n, clid, NULL, q); + if (err != 0) return err; } else { qdisc_notify(net, skb, n, clid, NULL, q); @@ -1017,7 +1026,7 @@ static int tc_get_qdisc(struct sk_buff *skb, struct nlmsghdr *n, void *arg) } /* - Create/change qdisc. + * Create/change qdisc. */ static int tc_modify_qdisc(struct sk_buff *skb, struct nlmsghdr *n, void *arg) @@ -1036,7 +1045,8 @@ replay: clid = tcm->tcm_parent; q = p = NULL; - if ((dev = __dev_get_by_index(net, tcm->tcm_ifindex)) == NULL) + dev = __dev_get_by_index(net, tcm->tcm_ifindex); + if (!dev) return -ENODEV; err = nlmsg_parse(n, sizeof(*tcm), tca, TCA_MAX, NULL); @@ -1046,12 +1056,12 @@ replay: if (clid) { if (clid != TC_H_ROOT) { if (clid != TC_H_INGRESS) { - if ((p = qdisc_lookup(dev, TC_H_MAJ(clid))) == NULL) + p = qdisc_lookup(dev, TC_H_MAJ(clid)); + if (!p) return -ENOENT; q = qdisc_leaf(p, clid); - } else { /* ingress */ - if (dev_ingress_queue_create(dev)) - q = dev_ingress_queue(dev)->qdisc_sleeping; + } else if (dev_ingress_queue_create(dev)) { + q = dev_ingress_queue(dev)->qdisc_sleeping; } } else { q = dev->qdisc; @@ -1063,13 +1073,14 @@ replay: if (!q || !tcm->tcm_handle || q->handle != tcm->tcm_handle) { if (tcm->tcm_handle) { - if (q && !(n->nlmsg_flags&NLM_F_REPLACE)) + if (q && !(n->nlmsg_flags & NLM_F_REPLACE)) return -EEXIST; if (TC_H_MIN(tcm->tcm_handle)) return -EINVAL; - if ((q = qdisc_lookup(dev, tcm->tcm_handle)) == NULL) + q = qdisc_lookup(dev, tcm->tcm_handle); + if (!q) goto create_n_graft; - if (n->nlmsg_flags&NLM_F_EXCL) + if (n->nlmsg_flags & NLM_F_EXCL) return -EEXIST; if (tca[TCA_KIND] && nla_strcmp(tca[TCA_KIND], q->ops->id)) return -EINVAL; @@ -1079,7 +1090,7 @@ replay: atomic_inc(&q->refcnt); goto graft; } else { - if (q == NULL) + if (!q) goto create_n_graft; /* This magic test requires explanation. @@ -1101,9 +1112,9 @@ replay: * For now we select create/graft, if * user gave KIND, which does not match existing. */ - if ((n->nlmsg_flags&NLM_F_CREATE) && - (n->nlmsg_flags&NLM_F_REPLACE) && - ((n->nlmsg_flags&NLM_F_EXCL) || + if ((n->nlmsg_flags & NLM_F_CREATE) && + (n->nlmsg_flags & NLM_F_REPLACE) && + ((n->nlmsg_flags & NLM_F_EXCL) || (tca[TCA_KIND] && nla_strcmp(tca[TCA_KIND], q->ops->id)))) goto create_n_graft; @@ -1118,7 +1129,7 @@ replay: /* Change qdisc parameters */ if (q == NULL) return -ENOENT; - if (n->nlmsg_flags&NLM_F_EXCL) + if (n->nlmsg_flags & NLM_F_EXCL) return -EEXIST; if (tca[TCA_KIND] && nla_strcmp(tca[TCA_KIND], q->ops->id)) return -EINVAL; @@ -1128,7 +1139,7 @@ replay: return err; create_n_graft: - if (!(n->nlmsg_flags&NLM_F_CREATE)) + if (!(n->nlmsg_flags & NLM_F_CREATE)) return -ENOENT; if (clid == TC_H_INGRESS) { if (dev_ingress_queue(dev)) @@ -1175,6 +1186,7 @@ static int tc_fill_qdisc(struct sk_buff *skb, struct Qdisc *q, u32 clid, struct nlmsghdr *nlh; unsigned char *b = skb_tail_pointer(skb); struct gnet_dump d; + struct qdisc_size_table *stab; nlh = NLMSG_NEW(skb, pid, seq, event, sizeof(*tcm), flags); tcm = NLMSG_DATA(nlh); @@ -1190,7 +1202,8 @@ static int tc_fill_qdisc(struct sk_buff *skb, struct Qdisc *q, u32 clid, goto nla_put_failure; q->qstats.qlen = q->q.qlen; - if (q->stab && qdisc_dump_stab(skb, q->stab) < 0) + stab = rtnl_dereference(q->stab); + if (stab && qdisc_dump_stab(skb, stab) < 0) goto nla_put_failure; if (gnet_stats_start_copy_compat(skb, TCA_STATS2, TCA_STATS, TCA_XSTATS, @@ -1234,16 +1247,19 @@ static int qdisc_notify(struct net *net, struct sk_buff *oskb, return -ENOBUFS; if (old && !tc_qdisc_dump_ignore(old)) { - if (tc_fill_qdisc(skb, old, clid, pid, n->nlmsg_seq, 0, RTM_DELQDISC) < 0) + if (tc_fill_qdisc(skb, old, clid, pid, n->nlmsg_seq, + 0, RTM_DELQDISC) < 0) goto err_out; } if (new && !tc_qdisc_dump_ignore(new)) { - if (tc_fill_qdisc(skb, new, clid, pid, n->nlmsg_seq, old ? NLM_F_REPLACE : 0, RTM_NEWQDISC) < 0) + if (tc_fill_qdisc(skb, new, clid, pid, n->nlmsg_seq, + old ? NLM_F_REPLACE : 0, RTM_NEWQDISC) < 0) goto err_out; } if (skb->len) - return rtnetlink_send(skb, net, pid, RTNLGRP_TC, n->nlmsg_flags&NLM_F_ECHO); + return rtnetlink_send(skb, net, pid, RTNLGRP_TC, + n->nlmsg_flags & NLM_F_ECHO); err_out: kfree_skb(skb); @@ -1275,7 +1291,7 @@ static int tc_dump_qdisc_root(struct Qdisc *root, struct sk_buff *skb, q_idx++; continue; } - if (!tc_qdisc_dump_ignore(q) && + if (!tc_qdisc_dump_ignore(q) && tc_fill_qdisc(skb, q, q->parent, NETLINK_CB(cb->skb).pid, cb->nlh->nlmsg_seq, NLM_F_MULTI, RTM_NEWQDISC) <= 0) goto done; @@ -1356,7 +1372,8 @@ static int tc_ctl_tclass(struct sk_buff *skb, struct nlmsghdr *n, void *arg) u32 qid = TC_H_MAJ(clid); int err; - if ((dev = __dev_get_by_index(net, tcm->tcm_ifindex)) == NULL) + dev = __dev_get_by_index(net, tcm->tcm_ifindex); + if (!dev) return -ENODEV; err = nlmsg_parse(n, sizeof(*tcm), tca, TCA_MAX, NULL); @@ -1391,9 +1408,9 @@ static int tc_ctl_tclass(struct sk_buff *skb, struct nlmsghdr *n, void *arg) qid = dev->qdisc->handle; /* Now qid is genuine qdisc handle consistent - both with parent and child. - - TC_H_MAJ(pid) still may be unspecified, complete it now. + * both with parent and child. + * + * TC_H_MAJ(pid) still may be unspecified, complete it now. */ if (pid) pid = TC_H_MAKE(qid, pid); @@ -1403,7 +1420,8 @@ static int tc_ctl_tclass(struct sk_buff *skb, struct nlmsghdr *n, void *arg) } /* OK. Locate qdisc */ - if ((q = qdisc_lookup(dev, qid)) == NULL) + q = qdisc_lookup(dev, qid); + if (!q) return -ENOENT; /* An check that it supports classes */ @@ -1423,13 +1441,14 @@ static int tc_ctl_tclass(struct sk_buff *skb, struct nlmsghdr *n, void *arg) if (cl == 0) { err = -ENOENT; - if (n->nlmsg_type != RTM_NEWTCLASS || !(n->nlmsg_flags&NLM_F_CREATE)) + if (n->nlmsg_type != RTM_NEWTCLASS || + !(n->nlmsg_flags & NLM_F_CREATE)) goto out; } else { switch (n->nlmsg_type) { case RTM_NEWTCLASS: err = -EEXIST; - if (n->nlmsg_flags&NLM_F_EXCL) + if (n->nlmsg_flags & NLM_F_EXCL) goto out; break; case RTM_DELTCLASS: @@ -1521,14 +1540,14 @@ static int tclass_notify(struct net *net, struct sk_buff *oskb, return -EINVAL; } - return rtnetlink_send(skb, net, pid, RTNLGRP_TC, n->nlmsg_flags&NLM_F_ECHO); + return rtnetlink_send(skb, net, pid, RTNLGRP_TC, + n->nlmsg_flags & NLM_F_ECHO); } -struct qdisc_dump_args -{ - struct qdisc_walker w; - struct sk_buff *skb; - struct netlink_callback *cb; +struct qdisc_dump_args { + struct qdisc_walker w; + struct sk_buff *skb; + struct netlink_callback *cb; }; static int qdisc_class_dump(struct Qdisc *q, unsigned long cl, struct qdisc_walker *arg) @@ -1590,7 +1609,7 @@ static int tc_dump_tclass_root(struct Qdisc *root, struct sk_buff *skb, static int tc_dump_tclass(struct sk_buff *skb, struct netlink_callback *cb) { - struct tcmsg *tcm = (struct tcmsg*)NLMSG_DATA(cb->nlh); + struct tcmsg *tcm = (struct tcmsg *)NLMSG_DATA(cb->nlh); struct net *net = sock_net(skb->sk); struct netdev_queue *dev_queue; struct net_device *dev; @@ -1598,7 +1617,8 @@ static int tc_dump_tclass(struct sk_buff *skb, struct netlink_callback *cb) if (cb->nlh->nlmsg_len < NLMSG_LENGTH(sizeof(*tcm))) return 0; - if ((dev = dev_get_by_index(net, tcm->tcm_ifindex)) == NULL) + dev = dev_get_by_index(net, tcm->tcm_ifindex); + if (!dev) return 0; s_t = cb->args[0]; @@ -1621,19 +1641,22 @@ done: } /* Main classifier routine: scans classifier chain attached - to this qdisc, (optionally) tests for protocol and asks - specific classifiers. + * to this qdisc, (optionally) tests for protocol and asks + * specific classifiers. */ int tc_classify_compat(struct sk_buff *skb, struct tcf_proto *tp, struct tcf_result *res) { __be16 protocol = skb->protocol; - int err = 0; + int err; for (; tp; tp = tp->next) { - if ((tp->protocol == protocol || - tp->protocol == htons(ETH_P_ALL)) && - (err = tp->classify(skb, tp, res)) >= 0) { + if (tp->protocol != protocol && + tp->protocol != htons(ETH_P_ALL)) + continue; + err = tp->classify(skb, tp, res); + + if (err >= 0) { #ifdef CONFIG_NET_CLS_ACT if (err != TC_ACT_RECLASSIFY && skb->tc_verd) skb->tc_verd = SET_TC_VERD(skb->tc_verd, 0); @@ -1649,12 +1672,12 @@ int tc_classify(struct sk_buff *skb, struct tcf_proto *tp, struct tcf_result *res) { int err = 0; - __be16 protocol; #ifdef CONFIG_NET_CLS_ACT + __be16 protocol; struct tcf_proto *otp = tp; reclassify: -#endif protocol = skb->protocol; +#endif err = tc_classify_compat(skb, tp, res); #ifdef CONFIG_NET_CLS_ACT @@ -1664,11 +1687,11 @@ reclassify: if (verd++ >= MAX_REC_LOOP) { if (net_ratelimit()) - printk(KERN_NOTICE - "%s: packet reclassify loop" + pr_notice("%s: packet reclassify loop" " rule prio %u protocol %02x\n", - tp->q->ops->id, - tp->prio & 0xffff, ntohs(tp->protocol)); + tp->q->ops->id, + tp->prio & 0xffff, + ntohs(tp->protocol)); return TC_ACT_SHOT; } skb->tc_verd = SET_TC_VERD(skb->tc_verd, verd); @@ -1761,7 +1784,7 @@ static int __init pktsched_init(void) err = register_pernet_subsys(&psched_net_ops); if (err) { - printk(KERN_ERR "pktsched_init: " + pr_err("pktsched_init: " "cannot initialize per netns operations\n"); return err; } diff --git a/net/sched/sch_atm.c b/net/sched/sch_atm.c index 943d733409d..3f08158b868 100644 --- a/net/sched/sch_atm.c +++ b/net/sched/sch_atm.c @@ -319,7 +319,7 @@ static int atm_tc_delete(struct Qdisc *sch, unsigned long arg) * creation), and one for the reference held when calling delete. */ if (flow->ref < 2) { - printk(KERN_ERR "atm_tc_delete: flow->ref == %d\n", flow->ref); + pr_err("atm_tc_delete: flow->ref == %d\n", flow->ref); return -EINVAL; } if (flow->ref > 2) @@ -384,12 +384,12 @@ static int atm_tc_enqueue(struct sk_buff *skb, struct Qdisc *sch) } } flow = NULL; - done: - ; +done: + ; } - if (!flow) + if (!flow) { flow = &p->link; - else { + } else { if (flow->vcc) ATM_SKB(skb)->atm_options = flow->vcc->atm_options; /*@@@ looks good ... but it's not supposed to work :-) */ @@ -576,8 +576,7 @@ static void atm_tc_destroy(struct Qdisc *sch) list_for_each_entry_safe(flow, tmp, &p->flows, list) { if (flow->ref > 1) - printk(KERN_ERR "atm_destroy: %p->ref = %d\n", flow, - flow->ref); + pr_err("atm_destroy: %p->ref = %d\n", flow, flow->ref); atm_tc_put(sch, (unsigned long)flow); } tasklet_kill(&p->task); @@ -616,9 +615,8 @@ static int atm_tc_dump_class(struct Qdisc *sch, unsigned long cl, } if (flow->excess) NLA_PUT_U32(skb, TCA_ATM_EXCESS, flow->classid); - else { + else NLA_PUT_U32(skb, TCA_ATM_EXCESS, 0); - } nla_nest_end(skb, nest); return skb->len; diff --git a/net/sched/sch_cbq.c b/net/sched/sch_cbq.c index 5f63ec58942..24d94c097b3 100644 --- a/net/sched/sch_cbq.c +++ b/net/sched/sch_cbq.c @@ -72,8 +72,7 @@ struct cbq_sched_data; -struct cbq_class -{ +struct cbq_class { struct Qdisc_class_common common; struct cbq_class *next_alive; /* next class with backlog in this priority band */ @@ -139,19 +138,18 @@ struct cbq_class int refcnt; int filters; - struct cbq_class *defaults[TC_PRIO_MAX+1]; + struct cbq_class *defaults[TC_PRIO_MAX + 1]; }; -struct cbq_sched_data -{ +struct cbq_sched_data { struct Qdisc_class_hash clhash; /* Hash table of all classes */ - int nclasses[TC_CBQ_MAXPRIO+1]; - unsigned quanta[TC_CBQ_MAXPRIO+1]; + int nclasses[TC_CBQ_MAXPRIO + 1]; + unsigned int quanta[TC_CBQ_MAXPRIO + 1]; struct cbq_class link; - unsigned activemask; - struct cbq_class *active[TC_CBQ_MAXPRIO+1]; /* List of all classes + unsigned int activemask; + struct cbq_class *active[TC_CBQ_MAXPRIO + 1]; /* List of all classes with backlog */ #ifdef CONFIG_NET_CLS_ACT @@ -162,7 +160,7 @@ struct cbq_sched_data int tx_len; psched_time_t now; /* Cached timestamp */ psched_time_t now_rt; /* Cached real time */ - unsigned pmask; + unsigned int pmask; struct hrtimer delay_timer; struct qdisc_watchdog watchdog; /* Watchdog timer, @@ -175,9 +173,9 @@ struct cbq_sched_data }; -#define L2T(cl,len) qdisc_l2t((cl)->R_tab,len) +#define L2T(cl, len) qdisc_l2t((cl)->R_tab, len) -static __inline__ struct cbq_class * +static inline struct cbq_class * cbq_class_lookup(struct cbq_sched_data *q, u32 classid) { struct Qdisc_class_common *clc; @@ -193,25 +191,27 @@ cbq_class_lookup(struct cbq_sched_data *q, u32 classid) static struct cbq_class * cbq_reclassify(struct sk_buff *skb, struct cbq_class *this) { - struct cbq_class *cl, *new; + struct cbq_class *cl; - for (cl = this->tparent; cl; cl = cl->tparent) - if ((new = cl->defaults[TC_PRIO_BESTEFFORT]) != NULL && new != this) - return new; + for (cl = this->tparent; cl; cl = cl->tparent) { + struct cbq_class *new = cl->defaults[TC_PRIO_BESTEFFORT]; + if (new != NULL && new != this) + return new; + } return NULL; } #endif /* Classify packet. The procedure is pretty complicated, but - it allows us to combine link sharing and priority scheduling - transparently. - - Namely, you can put link sharing rules (f.e. route based) at root of CBQ, - so that it resolves to split nodes. Then packets are classified - by logical priority, or a more specific classifier may be attached - to the split node. + * it allows us to combine link sharing and priority scheduling + * transparently. + * + * Namely, you can put link sharing rules (f.e. route based) at root of CBQ, + * so that it resolves to split nodes. Then packets are classified + * by logical priority, or a more specific classifier may be attached + * to the split node. */ static struct cbq_class * @@ -227,7 +227,7 @@ cbq_classify(struct sk_buff *skb, struct Qdisc *sch, int *qerr) /* * Step 1. If skb->priority points to one of our classes, use it. */ - if (TC_H_MAJ(prio^sch->handle) == 0 && + if (TC_H_MAJ(prio ^ sch->handle) == 0 && (cl = cbq_class_lookup(q, prio)) != NULL) return cl; @@ -243,10 +243,11 @@ cbq_classify(struct sk_buff *skb, struct Qdisc *sch, int *qerr) (result = tc_classify_compat(skb, head->filter_list, &res)) < 0) goto fallback; - if ((cl = (void*)res.class) == NULL) { + cl = (void *)res.class; + if (!cl) { if (TC_H_MAJ(res.classid)) cl = cbq_class_lookup(q, res.classid); - else if ((cl = defmap[res.classid&TC_PRIO_MAX]) == NULL) + else if ((cl = defmap[res.classid & TC_PRIO_MAX]) == NULL) cl = defmap[TC_PRIO_BESTEFFORT]; if (cl == NULL || cl->level >= head->level) @@ -282,7 +283,7 @@ fallback: * Step 4. No success... */ if (TC_H_MAJ(prio) == 0 && - !(cl = head->defaults[prio&TC_PRIO_MAX]) && + !(cl = head->defaults[prio & TC_PRIO_MAX]) && !(cl = head->defaults[TC_PRIO_BESTEFFORT])) return head; @@ -290,12 +291,12 @@ fallback: } /* - A packet has just been enqueued on the empty class. - cbq_activate_class adds it to the tail of active class list - of its priority band. + * A packet has just been enqueued on the empty class. + * cbq_activate_class adds it to the tail of active class list + * of its priority band. */ -static __inline__ void cbq_activate_class(struct cbq_class *cl) +static inline void cbq_activate_class(struct cbq_class *cl) { struct cbq_sched_data *q = qdisc_priv(cl->qdisc); int prio = cl->cpriority; @@ -314,9 +315,9 @@ static __inline__ void cbq_activate_class(struct cbq_class *cl) } /* - Unlink class from active chain. - Note that this same procedure is done directly in cbq_dequeue* - during round-robin procedure. + * Unlink class from active chain. + * Note that this same procedure is done directly in cbq_dequeue* + * during round-robin procedure. */ static void cbq_deactivate_class(struct cbq_class *this) @@ -350,7 +351,7 @@ cbq_mark_toplevel(struct cbq_sched_data *q, struct cbq_class *cl) { int toplevel = q->toplevel; - if (toplevel > cl->level && !(cl->q->flags&TCQ_F_THROTTLED)) { + if (toplevel > cl->level && !(qdisc_is_throttled(cl->q))) { psched_time_t now; psched_tdiff_t incr; @@ -363,7 +364,7 @@ cbq_mark_toplevel(struct cbq_sched_data *q, struct cbq_class *cl) q->toplevel = cl->level; return; } - } while ((cl=cl->borrow) != NULL && toplevel > cl->level); + } while ((cl = cl->borrow) != NULL && toplevel > cl->level); } } @@ -417,11 +418,11 @@ static void cbq_ovl_classic(struct cbq_class *cl) delay += cl->offtime; /* - Class goes to sleep, so that it will have no - chance to work avgidle. Let's forgive it 8) - - BTW cbq-2.0 has a crap in this - place, apparently they forgot to shift it by cl->ewma_log. + * Class goes to sleep, so that it will have no + * chance to work avgidle. Let's forgive it 8) + * + * BTW cbq-2.0 has a crap in this + * place, apparently they forgot to shift it by cl->ewma_log. */ if (cl->avgidle < 0) delay -= (-cl->avgidle) - ((-cl->avgidle) >> cl->ewma_log); @@ -438,8 +439,8 @@ static void cbq_ovl_classic(struct cbq_class *cl) q->wd_expires = delay; /* Dirty work! We must schedule wakeups based on - real available rate, rather than leaf rate, - which may be tiny (even zero). + * real available rate, rather than leaf rate, + * which may be tiny (even zero). */ if (q->toplevel == TC_CBQ_MAXLEVEL) { struct cbq_class *b; @@ -459,7 +460,7 @@ static void cbq_ovl_classic(struct cbq_class *cl) } /* TC_CBQ_OVL_RCLASSIC: penalize by offtime classes in hierarchy, when - they go overlimit + * they go overlimit */ static void cbq_ovl_rclassic(struct cbq_class *cl) @@ -594,7 +595,7 @@ static enum hrtimer_restart cbq_undelay(struct hrtimer *timer) struct Qdisc *sch = q->watchdog.qdisc; psched_time_t now; psched_tdiff_t delay = 0; - unsigned pmask; + unsigned int pmask; now = psched_get_time(); @@ -623,7 +624,7 @@ static enum hrtimer_restart cbq_undelay(struct hrtimer *timer) hrtimer_start(&q->delay_timer, time, HRTIMER_MODE_ABS); } - sch->flags &= ~TCQ_F_THROTTLED; + qdisc_unthrottled(sch); __netif_schedule(qdisc_root(sch)); return HRTIMER_NORESTART; } @@ -663,15 +664,15 @@ static int cbq_reshape_fail(struct sk_buff *skb, struct Qdisc *child) #endif /* - It is mission critical procedure. - - We "regenerate" toplevel cutoff, if transmitting class - has backlog and it is not regulated. It is not part of - original CBQ description, but looks more reasonable. - Probably, it is wrong. This question needs further investigation. -*/ + * It is mission critical procedure. + * + * We "regenerate" toplevel cutoff, if transmitting class + * has backlog and it is not regulated. It is not part of + * original CBQ description, but looks more reasonable. + * Probably, it is wrong. This question needs further investigation. + */ -static __inline__ void +static inline void cbq_update_toplevel(struct cbq_sched_data *q, struct cbq_class *cl, struct cbq_class *borrowed) { @@ -682,7 +683,7 @@ cbq_update_toplevel(struct cbq_sched_data *q, struct cbq_class *cl, q->toplevel = borrowed->level; return; } - } while ((borrowed=borrowed->borrow) != NULL); + } while ((borrowed = borrowed->borrow) != NULL); } #if 0 /* It is not necessary now. Uncommenting it @@ -710,10 +711,10 @@ cbq_update(struct cbq_sched_data *q) cl->bstats.bytes += len; /* - (now - last) is total time between packet right edges. - (last_pktlen/rate) is "virtual" busy time, so that - - idle = (now - last) - last_pktlen/rate + * (now - last) is total time between packet right edges. + * (last_pktlen/rate) is "virtual" busy time, so that + * + * idle = (now - last) - last_pktlen/rate */ idle = q->now - cl->last; @@ -723,9 +724,9 @@ cbq_update(struct cbq_sched_data *q) idle -= L2T(cl, len); /* true_avgidle := (1-W)*true_avgidle + W*idle, - where W=2^{-ewma_log}. But cl->avgidle is scaled: - cl->avgidle == true_avgidle/W, - hence: + * where W=2^{-ewma_log}. But cl->avgidle is scaled: + * cl->avgidle == true_avgidle/W, + * hence: */ avgidle += idle - (avgidle>>cl->ewma_log); } @@ -739,22 +740,22 @@ cbq_update(struct cbq_sched_data *q) cl->avgidle = avgidle; /* Calculate expected time, when this class - will be allowed to send. - It will occur, when: - (1-W)*true_avgidle + W*delay = 0, i.e. - idle = (1/W - 1)*(-true_avgidle) - or - idle = (1 - W)*(-cl->avgidle); + * will be allowed to send. + * It will occur, when: + * (1-W)*true_avgidle + W*delay = 0, i.e. + * idle = (1/W - 1)*(-true_avgidle) + * or + * idle = (1 - W)*(-cl->avgidle); */ idle = (-avgidle) - ((-avgidle) >> cl->ewma_log); /* - That is not all. - To maintain the rate allocated to the class, - we add to undertime virtual clock, - necessary to complete transmitted packet. - (len/phys_bandwidth has been already passed - to the moment of cbq_update) + * That is not all. + * To maintain the rate allocated to the class, + * we add to undertime virtual clock, + * necessary to complete transmitted packet. + * (len/phys_bandwidth has been already passed + * to the moment of cbq_update) */ idle -= L2T(&q->link, len); @@ -776,7 +777,7 @@ cbq_update(struct cbq_sched_data *q) cbq_update_toplevel(q, this, q->tx_borrowed); } -static __inline__ struct cbq_class * +static inline struct cbq_class * cbq_under_limit(struct cbq_class *cl) { struct cbq_sched_data *q = qdisc_priv(cl->qdisc); @@ -792,16 +793,17 @@ cbq_under_limit(struct cbq_class *cl) do { /* It is very suspicious place. Now overlimit - action is generated for not bounded classes - only if link is completely congested. - Though it is in agree with ancestor-only paradigm, - it looks very stupid. Particularly, - it means that this chunk of code will either - never be called or result in strong amplification - of burstiness. Dangerous, silly, and, however, - no another solution exists. + * action is generated for not bounded classes + * only if link is completely congested. + * Though it is in agree with ancestor-only paradigm, + * it looks very stupid. Particularly, + * it means that this chunk of code will either + * never be called or result in strong amplification + * of burstiness. Dangerous, silly, and, however, + * no another solution exists. */ - if ((cl = cl->borrow) == NULL) { + cl = cl->borrow; + if (!cl) { this_cl->qstats.overlimits++; this_cl->overlimit(this_cl); return NULL; @@ -814,7 +816,7 @@ cbq_under_limit(struct cbq_class *cl) return cl; } -static __inline__ struct sk_buff * +static inline struct sk_buff * cbq_dequeue_prio(struct Qdisc *sch, int prio) { struct cbq_sched_data *q = qdisc_priv(sch); @@ -838,7 +840,7 @@ cbq_dequeue_prio(struct Qdisc *sch, int prio) if (cl->deficit <= 0) { /* Class exhausted its allotment per - this round. Switch to the next one. + * this round. Switch to the next one. */ deficit = 1; cl->deficit += cl->quantum; @@ -848,8 +850,8 @@ cbq_dequeue_prio(struct Qdisc *sch, int prio) skb = cl->q->dequeue(cl->q); /* Class did not give us any skb :-( - It could occur even if cl->q->q.qlen != 0 - f.e. if cl->q == "tbf" + * It could occur even if cl->q->q.qlen != 0 + * f.e. if cl->q == "tbf" */ if (skb == NULL) goto skip_class; @@ -878,7 +880,7 @@ cbq_dequeue_prio(struct Qdisc *sch, int prio) skip_class: if (cl->q->q.qlen == 0 || prio != cl->cpriority) { /* Class is empty or penalized. - Unlink it from active chain. + * Unlink it from active chain. */ cl_prev->next_alive = cl->next_alive; cl->next_alive = NULL; @@ -917,14 +919,14 @@ next_class: return NULL; } -static __inline__ struct sk_buff * +static inline struct sk_buff * cbq_dequeue_1(struct Qdisc *sch) { struct cbq_sched_data *q = qdisc_priv(sch); struct sk_buff *skb; - unsigned activemask; + unsigned int activemask; - activemask = q->activemask&0xFF; + activemask = q->activemask & 0xFF; while (activemask) { int prio = ffz(~activemask); activemask &= ~(1<<prio); @@ -949,11 +951,11 @@ cbq_dequeue(struct Qdisc *sch) if (q->tx_class) { psched_tdiff_t incr2; /* Time integrator. We calculate EOS time - by adding expected packet transmission time. - If real time is greater, we warp artificial clock, - so that: - - cbq_time = max(real_time, work); + * by adding expected packet transmission time. + * If real time is greater, we warp artificial clock, + * so that: + * + * cbq_time = max(real_time, work); */ incr2 = L2T(&q->link, q->tx_len); q->now += incr2; @@ -971,27 +973,27 @@ cbq_dequeue(struct Qdisc *sch) if (skb) { qdisc_bstats_update(sch, skb); sch->q.qlen--; - sch->flags &= ~TCQ_F_THROTTLED; + qdisc_unthrottled(sch); return skb; } /* All the classes are overlimit. - - It is possible, if: - - 1. Scheduler is empty. - 2. Toplevel cutoff inhibited borrowing. - 3. Root class is overlimit. - - Reset 2d and 3d conditions and retry. - - Note, that NS and cbq-2.0 are buggy, peeking - an arbitrary class is appropriate for ancestor-only - sharing, but not for toplevel algorithm. - - Our version is better, but slower, because it requires - two passes, but it is unavoidable with top-level sharing. - */ + * + * It is possible, if: + * + * 1. Scheduler is empty. + * 2. Toplevel cutoff inhibited borrowing. + * 3. Root class is overlimit. + * + * Reset 2d and 3d conditions and retry. + * + * Note, that NS and cbq-2.0 are buggy, peeking + * an arbitrary class is appropriate for ancestor-only + * sharing, but not for toplevel algorithm. + * + * Our version is better, but slower, because it requires + * two passes, but it is unavoidable with top-level sharing. + */ if (q->toplevel == TC_CBQ_MAXLEVEL && q->link.undertime == PSCHED_PASTPERFECT) @@ -1002,7 +1004,8 @@ cbq_dequeue(struct Qdisc *sch) } /* No packets in scheduler or nobody wants to give them to us :-( - Sigh... start watchdog timer in the last case. */ + * Sigh... start watchdog timer in the last case. + */ if (sch->q.qlen) { sch->qstats.overlimits++; @@ -1024,13 +1027,14 @@ static void cbq_adjust_levels(struct cbq_class *this) int level = 0; struct cbq_class *cl; - if ((cl = this->children) != NULL) { + cl = this->children; + if (cl) { do { if (cl->level > level) level = cl->level; } while ((cl = cl->sibling) != this->children); } - this->level = level+1; + this->level = level + 1; } while ((this = this->tparent) != NULL); } @@ -1046,14 +1050,15 @@ static void cbq_normalize_quanta(struct cbq_sched_data *q, int prio) for (h = 0; h < q->clhash.hashsize; h++) { hlist_for_each_entry(cl, n, &q->clhash.hash[h], common.hnode) { /* BUGGGG... Beware! This expression suffer of - arithmetic overflows! + * arithmetic overflows! */ if (cl->priority == prio) { cl->quantum = (cl->weight*cl->allot*q->nclasses[prio])/ q->quanta[prio]; } if (cl->quantum <= 0 || cl->quantum>32*qdisc_dev(cl->qdisc)->mtu) { - printk(KERN_WARNING "CBQ: class %08x has bad quantum==%ld, repaired.\n", cl->common.classid, cl->quantum); + pr_warning("CBQ: class %08x has bad quantum==%ld, repaired.\n", + cl->common.classid, cl->quantum); cl->quantum = qdisc_dev(cl->qdisc)->mtu/2 + 1; } } @@ -1064,18 +1069,18 @@ static void cbq_sync_defmap(struct cbq_class *cl) { struct cbq_sched_data *q = qdisc_priv(cl->qdisc); struct cbq_class *split = cl->split; - unsigned h; + unsigned int h; int i; if (split == NULL) return; - for (i=0; i<=TC_PRIO_MAX; i++) { - if (split->defaults[i] == cl && !(cl->defmap&(1<<i))) + for (i = 0; i <= TC_PRIO_MAX; i++) { + if (split->defaults[i] == cl && !(cl->defmap & (1<<i))) split->defaults[i] = NULL; } - for (i=0; i<=TC_PRIO_MAX; i++) { + for (i = 0; i <= TC_PRIO_MAX; i++) { int level = split->level; if (split->defaults[i]) @@ -1088,7 +1093,7 @@ static void cbq_sync_defmap(struct cbq_class *cl) hlist_for_each_entry(c, n, &q->clhash.hash[h], common.hnode) { if (c->split == split && c->level < level && - c->defmap&(1<<i)) { + c->defmap & (1<<i)) { split->defaults[i] = c; level = c->level; } @@ -1102,7 +1107,8 @@ static void cbq_change_defmap(struct cbq_class *cl, u32 splitid, u32 def, u32 ma struct cbq_class *split = NULL; if (splitid == 0) { - if ((split = cl->split) == NULL) + split = cl->split; + if (!split) return; splitid = split->common.classid; } @@ -1120,9 +1126,9 @@ static void cbq_change_defmap(struct cbq_class *cl, u32 splitid, u32 def, u32 ma cl->defmap = 0; cbq_sync_defmap(cl); cl->split = split; - cl->defmap = def&mask; + cl->defmap = def & mask; } else - cl->defmap = (cl->defmap&~mask)|(def&mask); + cl->defmap = (cl->defmap & ~mask) | (def & mask); cbq_sync_defmap(cl); } @@ -1135,7 +1141,7 @@ static void cbq_unlink_class(struct cbq_class *this) qdisc_class_hash_remove(&q->clhash, &this->common); if (this->tparent) { - clp=&this->sibling; + clp = &this->sibling; cl = *clp; do { if (cl == this) { @@ -1174,7 +1180,7 @@ static void cbq_link_class(struct cbq_class *this) } } -static unsigned int cbq_drop(struct Qdisc* sch) +static unsigned int cbq_drop(struct Qdisc *sch) { struct cbq_sched_data *q = qdisc_priv(sch); struct cbq_class *cl, *cl_head; @@ -1182,7 +1188,8 @@ static unsigned int cbq_drop(struct Qdisc* sch) unsigned int len; for (prio = TC_CBQ_MAXPRIO; prio >= 0; prio--) { - if ((cl_head = q->active[prio]) == NULL) + cl_head = q->active[prio]; + if (!cl_head) continue; cl = cl_head; @@ -1199,13 +1206,13 @@ static unsigned int cbq_drop(struct Qdisc* sch) } static void -cbq_reset(struct Qdisc* sch) +cbq_reset(struct Qdisc *sch) { struct cbq_sched_data *q = qdisc_priv(sch); struct cbq_class *cl; struct hlist_node *n; int prio; - unsigned h; + unsigned int h; q->activemask = 0; q->pmask = 0; @@ -1237,21 +1244,21 @@ cbq_reset(struct Qdisc* sch) static int cbq_set_lss(struct cbq_class *cl, struct tc_cbq_lssopt *lss) { - if (lss->change&TCF_CBQ_LSS_FLAGS) { - cl->share = (lss->flags&TCF_CBQ_LSS_ISOLATED) ? NULL : cl->tparent; - cl->borrow = (lss->flags&TCF_CBQ_LSS_BOUNDED) ? NULL : cl->tparent; + if (lss->change & TCF_CBQ_LSS_FLAGS) { + cl->share = (lss->flags & TCF_CBQ_LSS_ISOLATED) ? NULL : cl->tparent; + cl->borrow = (lss->flags & TCF_CBQ_LSS_BOUNDED) ? NULL : cl->tparent; } - if (lss->change&TCF_CBQ_LSS_EWMA) + if (lss->change & TCF_CBQ_LSS_EWMA) cl->ewma_log = lss->ewma_log; - if (lss->change&TCF_CBQ_LSS_AVPKT) + if (lss->change & TCF_CBQ_LSS_AVPKT) cl->avpkt = lss->avpkt; - if (lss->change&TCF_CBQ_LSS_MINIDLE) + if (lss->change & TCF_CBQ_LSS_MINIDLE) cl->minidle = -(long)lss->minidle; - if (lss->change&TCF_CBQ_LSS_MAXIDLE) { + if (lss->change & TCF_CBQ_LSS_MAXIDLE) { cl->maxidle = lss->maxidle; cl->avgidle = lss->maxidle; } - if (lss->change&TCF_CBQ_LSS_OFFTIME) + if (lss->change & TCF_CBQ_LSS_OFFTIME) cl->offtime = lss->offtime; return 0; } @@ -1279,10 +1286,10 @@ static int cbq_set_wrr(struct cbq_class *cl, struct tc_cbq_wrropt *wrr) if (wrr->weight) cl->weight = wrr->weight; if (wrr->priority) { - cl->priority = wrr->priority-1; + cl->priority = wrr->priority - 1; cl->cpriority = cl->priority; if (cl->priority >= cl->priority2) - cl->priority2 = TC_CBQ_MAXPRIO-1; + cl->priority2 = TC_CBQ_MAXPRIO - 1; } cbq_addprio(q, cl); @@ -1299,10 +1306,10 @@ static int cbq_set_overlimit(struct cbq_class *cl, struct tc_cbq_ovl *ovl) cl->overlimit = cbq_ovl_delay; break; case TC_CBQ_OVL_LOWPRIO: - if (ovl->priority2-1 >= TC_CBQ_MAXPRIO || - ovl->priority2-1 <= cl->priority) + if (ovl->priority2 - 1 >= TC_CBQ_MAXPRIO || + ovl->priority2 - 1 <= cl->priority) return -EINVAL; - cl->priority2 = ovl->priority2-1; + cl->priority2 = ovl->priority2 - 1; cl->overlimit = cbq_ovl_lowprio; break; case TC_CBQ_OVL_DROP: @@ -1381,9 +1388,9 @@ static int cbq_init(struct Qdisc *sch, struct nlattr *opt) if (!q->link.q) q->link.q = &noop_qdisc; - q->link.priority = TC_CBQ_MAXPRIO-1; - q->link.priority2 = TC_CBQ_MAXPRIO-1; - q->link.cpriority = TC_CBQ_MAXPRIO-1; + q->link.priority = TC_CBQ_MAXPRIO - 1; + q->link.priority2 = TC_CBQ_MAXPRIO - 1; + q->link.cpriority = TC_CBQ_MAXPRIO - 1; q->link.ovl_strategy = TC_CBQ_OVL_CLASSIC; q->link.overlimit = cbq_ovl_classic; q->link.allot = psched_mtu(qdisc_dev(sch)); @@ -1414,7 +1421,7 @@ put_rtab: return err; } -static __inline__ int cbq_dump_rate(struct sk_buff *skb, struct cbq_class *cl) +static int cbq_dump_rate(struct sk_buff *skb, struct cbq_class *cl) { unsigned char *b = skb_tail_pointer(skb); @@ -1426,7 +1433,7 @@ nla_put_failure: return -1; } -static __inline__ int cbq_dump_lss(struct sk_buff *skb, struct cbq_class *cl) +static int cbq_dump_lss(struct sk_buff *skb, struct cbq_class *cl) { unsigned char *b = skb_tail_pointer(skb); struct tc_cbq_lssopt opt; @@ -1451,15 +1458,15 @@ nla_put_failure: return -1; } -static __inline__ int cbq_dump_wrr(struct sk_buff *skb, struct cbq_class *cl) +static int cbq_dump_wrr(struct sk_buff *skb, struct cbq_class *cl) { unsigned char *b = skb_tail_pointer(skb); struct tc_cbq_wrropt opt; opt.flags = 0; opt.allot = cl->allot; - opt.priority = cl->priority+1; - opt.cpriority = cl->cpriority+1; + opt.priority = cl->priority + 1; + opt.cpriority = cl->cpriority + 1; opt.weight = cl->weight; NLA_PUT(skb, TCA_CBQ_WRROPT, sizeof(opt), &opt); return skb->len; @@ -1469,13 +1476,13 @@ nla_put_failure: return -1; } -static __inline__ int cbq_dump_ovl(struct sk_buff *skb, struct cbq_class *cl) +static int cbq_dump_ovl(struct sk_buff *skb, struct cbq_class *cl) { unsigned char *b = skb_tail_pointer(skb); struct tc_cbq_ovl opt; opt.strategy = cl->ovl_strategy; - opt.priority2 = cl->priority2+1; + opt.priority2 = cl->priority2 + 1; opt.pad = 0; opt.penalty = cl->penalty; NLA_PUT(skb, TCA_CBQ_OVL_STRATEGY, sizeof(opt), &opt); @@ -1486,7 +1493,7 @@ nla_put_failure: return -1; } -static __inline__ int cbq_dump_fopt(struct sk_buff *skb, struct cbq_class *cl) +static int cbq_dump_fopt(struct sk_buff *skb, struct cbq_class *cl) { unsigned char *b = skb_tail_pointer(skb); struct tc_cbq_fopt opt; @@ -1505,7 +1512,7 @@ nla_put_failure: } #ifdef CONFIG_NET_CLS_ACT -static __inline__ int cbq_dump_police(struct sk_buff *skb, struct cbq_class *cl) +static int cbq_dump_police(struct sk_buff *skb, struct cbq_class *cl) { unsigned char *b = skb_tail_pointer(skb); struct tc_cbq_police opt; @@ -1569,7 +1576,7 @@ static int cbq_dump_class(struct Qdisc *sch, unsigned long arg, struct sk_buff *skb, struct tcmsg *tcm) { - struct cbq_class *cl = (struct cbq_class*)arg; + struct cbq_class *cl = (struct cbq_class *)arg; struct nlattr *nest; if (cl->tparent) @@ -1597,7 +1604,7 @@ cbq_dump_class_stats(struct Qdisc *sch, unsigned long arg, struct gnet_dump *d) { struct cbq_sched_data *q = qdisc_priv(sch); - struct cbq_class *cl = (struct cbq_class*)arg; + struct cbq_class *cl = (struct cbq_class *)arg; cl->qstats.qlen = cl->q->q.qlen; cl->xstats.avgidle = cl->avgidle; @@ -1617,7 +1624,7 @@ cbq_dump_class_stats(struct Qdisc *sch, unsigned long arg, static int cbq_graft(struct Qdisc *sch, unsigned long arg, struct Qdisc *new, struct Qdisc **old) { - struct cbq_class *cl = (struct cbq_class*)arg; + struct cbq_class *cl = (struct cbq_class *)arg; if (new == NULL) { new = qdisc_create_dflt(sch->dev_queue, @@ -1640,10 +1647,9 @@ static int cbq_graft(struct Qdisc *sch, unsigned long arg, struct Qdisc *new, return 0; } -static struct Qdisc * -cbq_leaf(struct Qdisc *sch, unsigned long arg) +static struct Qdisc *cbq_leaf(struct Qdisc *sch, unsigned long arg) { - struct cbq_class *cl = (struct cbq_class*)arg; + struct cbq_class *cl = (struct cbq_class *)arg; return cl->q; } @@ -1682,13 +1688,12 @@ static void cbq_destroy_class(struct Qdisc *sch, struct cbq_class *cl) kfree(cl); } -static void -cbq_destroy(struct Qdisc* sch) +static void cbq_destroy(struct Qdisc *sch) { struct cbq_sched_data *q = qdisc_priv(sch); struct hlist_node *n, *next; struct cbq_class *cl; - unsigned h; + unsigned int h; #ifdef CONFIG_NET_CLS_ACT q->rx_class = NULL; @@ -1712,7 +1717,7 @@ cbq_destroy(struct Qdisc* sch) static void cbq_put(struct Qdisc *sch, unsigned long arg) { - struct cbq_class *cl = (struct cbq_class*)arg; + struct cbq_class *cl = (struct cbq_class *)arg; if (--cl->refcnt == 0) { #ifdef CONFIG_NET_CLS_ACT @@ -1735,7 +1740,7 @@ cbq_change_class(struct Qdisc *sch, u32 classid, u32 parentid, struct nlattr **t { int err; struct cbq_sched_data *q = qdisc_priv(sch); - struct cbq_class *cl = (struct cbq_class*)*arg; + struct cbq_class *cl = (struct cbq_class *)*arg; struct nlattr *opt = tca[TCA_OPTIONS]; struct nlattr *tb[TCA_CBQ_MAX + 1]; struct cbq_class *parent; @@ -1827,13 +1832,14 @@ cbq_change_class(struct Qdisc *sch, u32 classid, u32 parentid, struct nlattr **t if (classid) { err = -EINVAL; - if (TC_H_MAJ(classid^sch->handle) || cbq_class_lookup(q, classid)) + if (TC_H_MAJ(classid ^ sch->handle) || + cbq_class_lookup(q, classid)) goto failure; } else { int i; - classid = TC_H_MAKE(sch->handle,0x8000); + classid = TC_H_MAKE(sch->handle, 0x8000); - for (i=0; i<0x8000; i++) { + for (i = 0; i < 0x8000; i++) { if (++q->hgenerator >= 0x8000) q->hgenerator = 1; if (cbq_class_lookup(q, classid|q->hgenerator) == NULL) @@ -1890,11 +1896,11 @@ cbq_change_class(struct Qdisc *sch, u32 classid, u32 parentid, struct nlattr **t cl->minidle = -0x7FFFFFFF; cbq_set_lss(cl, nla_data(tb[TCA_CBQ_LSSOPT])); cbq_set_wrr(cl, nla_data(tb[TCA_CBQ_WRROPT])); - if (cl->ewma_log==0) + if (cl->ewma_log == 0) cl->ewma_log = q->link.ewma_log; - if (cl->maxidle==0) + if (cl->maxidle == 0) cl->maxidle = q->link.maxidle; - if (cl->avpkt==0) + if (cl->avpkt == 0) cl->avpkt = q->link.avpkt; cl->overlimit = cbq_ovl_classic; if (tb[TCA_CBQ_OVL_STRATEGY]) @@ -1920,7 +1926,7 @@ failure: static int cbq_delete(struct Qdisc *sch, unsigned long arg) { struct cbq_sched_data *q = qdisc_priv(sch); - struct cbq_class *cl = (struct cbq_class*)arg; + struct cbq_class *cl = (struct cbq_class *)arg; unsigned int qlen; if (cl->filters || cl->children || cl == &q->link) @@ -1978,7 +1984,7 @@ static unsigned long cbq_bind_filter(struct Qdisc *sch, unsigned long parent, u32 classid) { struct cbq_sched_data *q = qdisc_priv(sch); - struct cbq_class *p = (struct cbq_class*)parent; + struct cbq_class *p = (struct cbq_class *)parent; struct cbq_class *cl = cbq_class_lookup(q, classid); if (cl) { @@ -1992,7 +1998,7 @@ static unsigned long cbq_bind_filter(struct Qdisc *sch, unsigned long parent, static void cbq_unbind_filter(struct Qdisc *sch, unsigned long arg) { - struct cbq_class *cl = (struct cbq_class*)arg; + struct cbq_class *cl = (struct cbq_class *)arg; cl->filters--; } @@ -2002,7 +2008,7 @@ static void cbq_walk(struct Qdisc *sch, struct qdisc_walker *arg) struct cbq_sched_data *q = qdisc_priv(sch); struct cbq_class *cl; struct hlist_node *n; - unsigned h; + unsigned int h; if (arg->stop) return; diff --git a/net/sched/sch_choke.c b/net/sched/sch_choke.c new file mode 100644 index 00000000000..06afbaeb4c8 --- /dev/null +++ b/net/sched/sch_choke.c @@ -0,0 +1,688 @@ +/* + * net/sched/sch_choke.c CHOKE scheduler + * + * Copyright (c) 2011 Stephen Hemminger <shemminger@vyatta.com> + * Copyright (c) 2011 Eric Dumazet <eric.dumazet@gmail.com> + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * version 2 as published by the Free Software Foundation. + * + */ + +#include <linux/module.h> +#include <linux/types.h> +#include <linux/kernel.h> +#include <linux/skbuff.h> +#include <linux/reciprocal_div.h> +#include <linux/vmalloc.h> +#include <net/pkt_sched.h> +#include <net/inet_ecn.h> +#include <net/red.h> +#include <linux/ip.h> +#include <net/ip.h> +#include <linux/ipv6.h> +#include <net/ipv6.h> + +/* + CHOKe stateless AQM for fair bandwidth allocation + ================================================= + + CHOKe (CHOose and Keep for responsive flows, CHOose and Kill for + unresponsive flows) is a variant of RED that penalizes misbehaving flows but + maintains no flow state. The difference from RED is an additional step + during the enqueuing process. If average queue size is over the + low threshold (qmin), a packet is chosen at random from the queue. + If both the new and chosen packet are from the same flow, both + are dropped. Unlike RED, CHOKe is not really a "classful" qdisc because it + needs to access packets in queue randomly. It has a minimal class + interface to allow overriding the builtin flow classifier with + filters. + + Source: + R. Pan, B. Prabhakar, and K. Psounis, "CHOKe, A Stateless + Active Queue Management Scheme for Approximating Fair Bandwidth Allocation", + IEEE INFOCOM, 2000. + + A. Tang, J. Wang, S. Low, "Understanding CHOKe: Throughput and Spatial + Characteristics", IEEE/ACM Transactions on Networking, 2004 + + */ + +/* Upper bound on size of sk_buff table (packets) */ +#define CHOKE_MAX_QUEUE (128*1024 - 1) + +struct choke_sched_data { +/* Parameters */ + u32 limit; + unsigned char flags; + + struct red_parms parms; + +/* Variables */ + struct tcf_proto *filter_list; + struct { + u32 prob_drop; /* Early probability drops */ + u32 prob_mark; /* Early probability marks */ + u32 forced_drop; /* Forced drops, qavg > max_thresh */ + u32 forced_mark; /* Forced marks, qavg > max_thresh */ + u32 pdrop; /* Drops due to queue limits */ + u32 other; /* Drops due to drop() calls */ + u32 matched; /* Drops to flow match */ + } stats; + + unsigned int head; + unsigned int tail; + + unsigned int tab_mask; /* size - 1 */ + + struct sk_buff **tab; +}; + +/* deliver a random number between 0 and N - 1 */ +static u32 random_N(unsigned int N) +{ + return reciprocal_divide(random32(), N); +} + +/* number of elements in queue including holes */ +static unsigned int choke_len(const struct choke_sched_data *q) +{ + return (q->tail - q->head) & q->tab_mask; +} + +/* Is ECN parameter configured */ +static int use_ecn(const struct choke_sched_data *q) +{ + return q->flags & TC_RED_ECN; +} + +/* Should packets over max just be dropped (versus marked) */ +static int use_harddrop(const struct choke_sched_data *q) +{ + return q->flags & TC_RED_HARDDROP; +} + +/* Move head pointer forward to skip over holes */ +static void choke_zap_head_holes(struct choke_sched_data *q) +{ + do { + q->head = (q->head + 1) & q->tab_mask; + if (q->head == q->tail) + break; + } while (q->tab[q->head] == NULL); +} + +/* Move tail pointer backwards to reuse holes */ +static void choke_zap_tail_holes(struct choke_sched_data *q) +{ + do { + q->tail = (q->tail - 1) & q->tab_mask; + if (q->head == q->tail) + break; + } while (q->tab[q->tail] == NULL); +} + +/* Drop packet from queue array by creating a "hole" */ +static void choke_drop_by_idx(struct Qdisc *sch, unsigned int idx) +{ + struct choke_sched_data *q = qdisc_priv(sch); + struct sk_buff *skb = q->tab[idx]; + + q->tab[idx] = NULL; + + if (idx == q->head) + choke_zap_head_holes(q); + if (idx == q->tail) + choke_zap_tail_holes(q); + + sch->qstats.backlog -= qdisc_pkt_len(skb); + qdisc_drop(skb, sch); + qdisc_tree_decrease_qlen(sch, 1); + --sch->q.qlen; +} + +/* + * Compare flow of two packets + * Returns true only if source and destination address and port match. + * false for special cases + */ +static bool choke_match_flow(struct sk_buff *skb1, + struct sk_buff *skb2) +{ + int off1, off2, poff; + const u32 *ports1, *ports2; + u8 ip_proto; + __u32 hash1; + + if (skb1->protocol != skb2->protocol) + return false; + + /* Use hash value as quick check + * Assumes that __skb_get_rxhash makes IP header and ports linear + */ + hash1 = skb_get_rxhash(skb1); + if (!hash1 || hash1 != skb_get_rxhash(skb2)) + return false; + + /* Probably match, but be sure to avoid hash collisions */ + off1 = skb_network_offset(skb1); + off2 = skb_network_offset(skb2); + + switch (skb1->protocol) { + case __constant_htons(ETH_P_IP): { + const struct iphdr *ip1, *ip2; + + ip1 = (const struct iphdr *) (skb1->data + off1); + ip2 = (const struct iphdr *) (skb2->data + off2); + + ip_proto = ip1->protocol; + if (ip_proto != ip2->protocol || + ip1->saddr != ip2->saddr || ip1->daddr != ip2->daddr) + return false; + + if ((ip1->frag_off | ip2->frag_off) & htons(IP_MF | IP_OFFSET)) + ip_proto = 0; + off1 += ip1->ihl * 4; + off2 += ip2->ihl * 4; + break; + } + + case __constant_htons(ETH_P_IPV6): { + const struct ipv6hdr *ip1, *ip2; + + ip1 = (const struct ipv6hdr *) (skb1->data + off1); + ip2 = (const struct ipv6hdr *) (skb2->data + off2); + + ip_proto = ip1->nexthdr; + if (ip_proto != ip2->nexthdr || + ipv6_addr_cmp(&ip1->saddr, &ip2->saddr) || + ipv6_addr_cmp(&ip1->daddr, &ip2->daddr)) + return false; + off1 += 40; + off2 += 40; + } + + default: /* Maybe compare MAC header here? */ + return false; + } + + poff = proto_ports_offset(ip_proto); + if (poff < 0) + return true; + + off1 += poff; + off2 += poff; + + ports1 = (__force u32 *)(skb1->data + off1); + ports2 = (__force u32 *)(skb2->data + off2); + return *ports1 == *ports2; +} + +struct choke_skb_cb { + u16 classid; +}; + +static inline struct choke_skb_cb *choke_skb_cb(const struct sk_buff *skb) +{ + BUILD_BUG_ON(sizeof(skb->cb) < + sizeof(struct qdisc_skb_cb) + sizeof(struct choke_skb_cb)); + return (struct choke_skb_cb *)qdisc_skb_cb(skb)->data; +} + +static inline void choke_set_classid(struct sk_buff *skb, u16 classid) +{ + choke_skb_cb(skb)->classid = classid; +} + +static u16 choke_get_classid(const struct sk_buff *skb) +{ + return choke_skb_cb(skb)->classid; +} + +/* + * Classify flow using either: + * 1. pre-existing classification result in skb + * 2. fast internal classification + * 3. use TC filter based classification + */ +static bool choke_classify(struct sk_buff *skb, + struct Qdisc *sch, int *qerr) + +{ + struct choke_sched_data *q = qdisc_priv(sch); + struct tcf_result res; + int result; + + result = tc_classify(skb, q->filter_list, &res); + if (result >= 0) { +#ifdef CONFIG_NET_CLS_ACT + switch (result) { + case TC_ACT_STOLEN: + case TC_ACT_QUEUED: + *qerr = NET_XMIT_SUCCESS | __NET_XMIT_STOLEN; + case TC_ACT_SHOT: + return false; + } +#endif + choke_set_classid(skb, TC_H_MIN(res.classid)); + return true; + } + + return false; +} + +/* + * Select a packet at random from queue + * HACK: since queue can have holes from previous deletion; retry several + * times to find a random skb but then just give up and return the head + * Will return NULL if queue is empty (q->head == q->tail) + */ +static struct sk_buff *choke_peek_random(const struct choke_sched_data *q, + unsigned int *pidx) +{ + struct sk_buff *skb; + int retrys = 3; + + do { + *pidx = (q->head + random_N(choke_len(q))) & q->tab_mask; + skb = q->tab[*pidx]; + if (skb) + return skb; + } while (--retrys > 0); + + return q->tab[*pidx = q->head]; +} + +/* + * Compare new packet with random packet in queue + * returns true if matched and sets *pidx + */ +static bool choke_match_random(const struct choke_sched_data *q, + struct sk_buff *nskb, + unsigned int *pidx) +{ + struct sk_buff *oskb; + + if (q->head == q->tail) + return false; + + oskb = choke_peek_random(q, pidx); + if (q->filter_list) + return choke_get_classid(nskb) == choke_get_classid(oskb); + + return choke_match_flow(oskb, nskb); +} + +static int choke_enqueue(struct sk_buff *skb, struct Qdisc *sch) +{ + struct choke_sched_data *q = qdisc_priv(sch); + struct red_parms *p = &q->parms; + int ret = NET_XMIT_SUCCESS | __NET_XMIT_BYPASS; + + if (q->filter_list) { + /* If using external classifiers, get result and record it. */ + if (!choke_classify(skb, sch, &ret)) + goto other_drop; /* Packet was eaten by filter */ + } + + /* Compute average queue usage (see RED) */ + p->qavg = red_calc_qavg(p, sch->q.qlen); + if (red_is_idling(p)) + red_end_of_idle_period(p); + + /* Is queue small? */ + if (p->qavg <= p->qth_min) + p->qcount = -1; + else { + unsigned int idx; + + /* Draw a packet at random from queue and compare flow */ + if (choke_match_random(q, skb, &idx)) { + q->stats.matched++; + choke_drop_by_idx(sch, idx); + goto congestion_drop; + } + + /* Queue is large, always mark/drop */ + if (p->qavg > p->qth_max) { + p->qcount = -1; + + sch->qstats.overlimits++; + if (use_harddrop(q) || !use_ecn(q) || + !INET_ECN_set_ce(skb)) { + q->stats.forced_drop++; + goto congestion_drop; + } + + q->stats.forced_mark++; + } else if (++p->qcount) { + if (red_mark_probability(p, p->qavg)) { + p->qcount = 0; + p->qR = red_random(p); + + sch->qstats.overlimits++; + if (!use_ecn(q) || !INET_ECN_set_ce(skb)) { + q->stats.prob_drop++; + goto congestion_drop; + } + + q->stats.prob_mark++; + } + } else + p->qR = red_random(p); + } + + /* Admit new packet */ + if (sch->q.qlen < q->limit) { + q->tab[q->tail] = skb; + q->tail = (q->tail + 1) & q->tab_mask; + ++sch->q.qlen; + sch->qstats.backlog += qdisc_pkt_len(skb); + return NET_XMIT_SUCCESS; + } + + q->stats.pdrop++; + sch->qstats.drops++; + kfree_skb(skb); + return NET_XMIT_DROP; + + congestion_drop: + qdisc_drop(skb, sch); + return NET_XMIT_CN; + + other_drop: + if (ret & __NET_XMIT_BYPASS) + sch->qstats.drops++; + kfree_skb(skb); + return ret; +} + +static struct sk_buff *choke_dequeue(struct Qdisc *sch) +{ + struct choke_sched_data *q = qdisc_priv(sch); + struct sk_buff *skb; + + if (q->head == q->tail) { + if (!red_is_idling(&q->parms)) + red_start_of_idle_period(&q->parms); + return NULL; + } + + skb = q->tab[q->head]; + q->tab[q->head] = NULL; + choke_zap_head_holes(q); + --sch->q.qlen; + sch->qstats.backlog -= qdisc_pkt_len(skb); + qdisc_bstats_update(sch, skb); + + return skb; +} + +static unsigned int choke_drop(struct Qdisc *sch) +{ + struct choke_sched_data *q = qdisc_priv(sch); + unsigned int len; + + len = qdisc_queue_drop(sch); + if (len > 0) + q->stats.other++; + else { + if (!red_is_idling(&q->parms)) + red_start_of_idle_period(&q->parms); + } + + return len; +} + +static void choke_reset(struct Qdisc *sch) +{ + struct choke_sched_data *q = qdisc_priv(sch); + + red_restart(&q->parms); +} + +static const struct nla_policy choke_policy[TCA_CHOKE_MAX + 1] = { + [TCA_CHOKE_PARMS] = { .len = sizeof(struct tc_red_qopt) }, + [TCA_CHOKE_STAB] = { .len = RED_STAB_SIZE }, +}; + + +static void choke_free(void *addr) +{ + if (addr) { + if (is_vmalloc_addr(addr)) + vfree(addr); + else + kfree(addr); + } +} + +static int choke_change(struct Qdisc *sch, struct nlattr *opt) +{ + struct choke_sched_data *q = qdisc_priv(sch); + struct nlattr *tb[TCA_CHOKE_MAX + 1]; + const struct tc_red_qopt *ctl; + int err; + struct sk_buff **old = NULL; + unsigned int mask; + + if (opt == NULL) + return -EINVAL; + + err = nla_parse_nested(tb, TCA_CHOKE_MAX, opt, choke_policy); + if (err < 0) + return err; + + if (tb[TCA_CHOKE_PARMS] == NULL || + tb[TCA_CHOKE_STAB] == NULL) + return -EINVAL; + + ctl = nla_data(tb[TCA_CHOKE_PARMS]); + + if (ctl->limit > CHOKE_MAX_QUEUE) + return -EINVAL; + + mask = roundup_pow_of_two(ctl->limit + 1) - 1; + if (mask != q->tab_mask) { + struct sk_buff **ntab; + + ntab = kcalloc(mask + 1, sizeof(struct sk_buff *), GFP_KERNEL); + if (!ntab) + ntab = vzalloc((mask + 1) * sizeof(struct sk_buff *)); + if (!ntab) + return -ENOMEM; + + sch_tree_lock(sch); + old = q->tab; + if (old) { + unsigned int oqlen = sch->q.qlen, tail = 0; + + while (q->head != q->tail) { + struct sk_buff *skb = q->tab[q->head]; + + q->head = (q->head + 1) & q->tab_mask; + if (!skb) + continue; + if (tail < mask) { + ntab[tail++] = skb; + continue; + } + sch->qstats.backlog -= qdisc_pkt_len(skb); + --sch->q.qlen; + qdisc_drop(skb, sch); + } + qdisc_tree_decrease_qlen(sch, oqlen - sch->q.qlen); + q->head = 0; + q->tail = tail; + } + + q->tab_mask = mask; + q->tab = ntab; + } else + sch_tree_lock(sch); + + q->flags = ctl->flags; + q->limit = ctl->limit; + + red_set_parms(&q->parms, ctl->qth_min, ctl->qth_max, ctl->Wlog, + ctl->Plog, ctl->Scell_log, + nla_data(tb[TCA_CHOKE_STAB])); + + if (q->head == q->tail) + red_end_of_idle_period(&q->parms); + + sch_tree_unlock(sch); + choke_free(old); + return 0; +} + +static int choke_init(struct Qdisc *sch, struct nlattr *opt) +{ + return choke_change(sch, opt); +} + +static int choke_dump(struct Qdisc *sch, struct sk_buff *skb) +{ + struct choke_sched_data *q = qdisc_priv(sch); + struct nlattr *opts = NULL; + struct tc_red_qopt opt = { + .limit = q->limit, + .flags = q->flags, + .qth_min = q->parms.qth_min >> q->parms.Wlog, + .qth_max = q->parms.qth_max >> q->parms.Wlog, + .Wlog = q->parms.Wlog, + .Plog = q->parms.Plog, + .Scell_log = q->parms.Scell_log, + }; + + opts = nla_nest_start(skb, TCA_OPTIONS); + if (opts == NULL) + goto nla_put_failure; + + NLA_PUT(skb, TCA_CHOKE_PARMS, sizeof(opt), &opt); + return nla_nest_end(skb, opts); + +nla_put_failure: + nla_nest_cancel(skb, opts); + return -EMSGSIZE; +} + +static int choke_dump_stats(struct Qdisc *sch, struct gnet_dump *d) +{ + struct choke_sched_data *q = qdisc_priv(sch); + struct tc_choke_xstats st = { + .early = q->stats.prob_drop + q->stats.forced_drop, + .marked = q->stats.prob_mark + q->stats.forced_mark, + .pdrop = q->stats.pdrop, + .other = q->stats.other, + .matched = q->stats.matched, + }; + + return gnet_stats_copy_app(d, &st, sizeof(st)); +} + +static void choke_destroy(struct Qdisc *sch) +{ + struct choke_sched_data *q = qdisc_priv(sch); + + tcf_destroy_chain(&q->filter_list); + choke_free(q->tab); +} + +static struct Qdisc *choke_leaf(struct Qdisc *sch, unsigned long arg) +{ + return NULL; +} + +static unsigned long choke_get(struct Qdisc *sch, u32 classid) +{ + return 0; +} + +static void choke_put(struct Qdisc *q, unsigned long cl) +{ +} + +static unsigned long choke_bind(struct Qdisc *sch, unsigned long parent, + u32 classid) +{ + return 0; +} + +static struct tcf_proto **choke_find_tcf(struct Qdisc *sch, unsigned long cl) +{ + struct choke_sched_data *q = qdisc_priv(sch); + + if (cl) + return NULL; + return &q->filter_list; +} + +static int choke_dump_class(struct Qdisc *sch, unsigned long cl, + struct sk_buff *skb, struct tcmsg *tcm) +{ + tcm->tcm_handle |= TC_H_MIN(cl); + return 0; +} + +static void choke_walk(struct Qdisc *sch, struct qdisc_walker *arg) +{ + if (!arg->stop) { + if (arg->fn(sch, 1, arg) < 0) { + arg->stop = 1; + return; + } + arg->count++; + } +} + +static const struct Qdisc_class_ops choke_class_ops = { + .leaf = choke_leaf, + .get = choke_get, + .put = choke_put, + .tcf_chain = choke_find_tcf, + .bind_tcf = choke_bind, + .unbind_tcf = choke_put, + .dump = choke_dump_class, + .walk = choke_walk, +}; + +static struct sk_buff *choke_peek_head(struct Qdisc *sch) +{ + struct choke_sched_data *q = qdisc_priv(sch); + + return (q->head != q->tail) ? q->tab[q->head] : NULL; +} + +static struct Qdisc_ops choke_qdisc_ops __read_mostly = { + .id = "choke", + .priv_size = sizeof(struct choke_sched_data), + + .enqueue = choke_enqueue, + .dequeue = choke_dequeue, + .peek = choke_peek_head, + .drop = choke_drop, + .init = choke_init, + .destroy = choke_destroy, + .reset = choke_reset, + .change = choke_change, + .dump = choke_dump, + .dump_stats = choke_dump_stats, + .owner = THIS_MODULE, +}; + +static int __init choke_module_init(void) +{ + return register_qdisc(&choke_qdisc_ops); +} + +static void __exit choke_module_exit(void) +{ + unregister_qdisc(&choke_qdisc_ops); +} + +module_init(choke_module_init) +module_exit(choke_module_exit) + +MODULE_LICENSE("GPL"); diff --git a/net/sched/sch_dsmark.c b/net/sched/sch_dsmark.c index 0f7bf3fdfea..2c790204d04 100644 --- a/net/sched/sch_dsmark.c +++ b/net/sched/sch_dsmark.c @@ -137,10 +137,10 @@ static int dsmark_change(struct Qdisc *sch, u32 classid, u32 parent, mask = nla_get_u8(tb[TCA_DSMARK_MASK]); if (tb[TCA_DSMARK_VALUE]) - p->value[*arg-1] = nla_get_u8(tb[TCA_DSMARK_VALUE]); + p->value[*arg - 1] = nla_get_u8(tb[TCA_DSMARK_VALUE]); if (tb[TCA_DSMARK_MASK]) - p->mask[*arg-1] = mask; + p->mask[*arg - 1] = mask; err = 0; @@ -155,8 +155,8 @@ static int dsmark_delete(struct Qdisc *sch, unsigned long arg) if (!dsmark_valid_index(p, arg)) return -EINVAL; - p->mask[arg-1] = 0xff; - p->value[arg-1] = 0; + p->mask[arg - 1] = 0xff; + p->value[arg - 1] = 0; return 0; } @@ -175,7 +175,7 @@ static void dsmark_walk(struct Qdisc *sch, struct qdisc_walker *walker) if (p->mask[i] == 0xff && !p->value[i]) goto ignore; if (walker->count >= walker->skip) { - if (walker->fn(sch, i+1, walker) < 0) { + if (walker->fn(sch, i + 1, walker) < 0) { walker->stop = 1; break; } @@ -304,9 +304,8 @@ static struct sk_buff *dsmark_dequeue(struct Qdisc *sch) * and don't need yet another qdisc as a bypass. */ if (p->mask[index] != 0xff || p->value[index]) - printk(KERN_WARNING - "dsmark_dequeue: unsupported protocol %d\n", - ntohs(skb->protocol)); + pr_warning("dsmark_dequeue: unsupported protocol %d\n", + ntohs(skb->protocol)); break; } @@ -424,14 +423,14 @@ static int dsmark_dump_class(struct Qdisc *sch, unsigned long cl, if (!dsmark_valid_index(p, cl)) return -EINVAL; - tcm->tcm_handle = TC_H_MAKE(TC_H_MAJ(sch->handle), cl-1); + tcm->tcm_handle = TC_H_MAKE(TC_H_MAJ(sch->handle), cl - 1); tcm->tcm_info = p->q->handle; opts = nla_nest_start(skb, TCA_OPTIONS); if (opts == NULL) goto nla_put_failure; - NLA_PUT_U8(skb, TCA_DSMARK_MASK, p->mask[cl-1]); - NLA_PUT_U8(skb, TCA_DSMARK_VALUE, p->value[cl-1]); + NLA_PUT_U8(skb, TCA_DSMARK_MASK, p->mask[cl - 1]); + NLA_PUT_U8(skb, TCA_DSMARK_VALUE, p->value[cl - 1]); return nla_nest_end(skb, opts); diff --git a/net/sched/sch_fifo.c b/net/sched/sch_fifo.c index d468b479aa9..66effe2da8e 100644 --- a/net/sched/sch_fifo.c +++ b/net/sched/sch_fifo.c @@ -19,36 +19,25 @@ /* 1 band FIFO pseudo-"scheduler" */ -struct fifo_sched_data +static int bfifo_enqueue(struct sk_buff *skb, struct Qdisc *sch) { - u32 limit; -}; - -static int bfifo_enqueue(struct sk_buff *skb, struct Qdisc* sch) -{ - struct fifo_sched_data *q = qdisc_priv(sch); - - if (likely(sch->qstats.backlog + qdisc_pkt_len(skb) <= q->limit)) + if (likely(sch->qstats.backlog + qdisc_pkt_len(skb) <= sch->limit)) return qdisc_enqueue_tail(skb, sch); return qdisc_reshape_fail(skb, sch); } -static int pfifo_enqueue(struct sk_buff *skb, struct Qdisc* sch) +static int pfifo_enqueue(struct sk_buff *skb, struct Qdisc *sch) { - struct fifo_sched_data *q = qdisc_priv(sch); - - if (likely(skb_queue_len(&sch->q) < q->limit)) + if (likely(skb_queue_len(&sch->q) < sch->limit)) return qdisc_enqueue_tail(skb, sch); return qdisc_reshape_fail(skb, sch); } -static int pfifo_tail_enqueue(struct sk_buff *skb, struct Qdisc* sch) +static int pfifo_tail_enqueue(struct sk_buff *skb, struct Qdisc *sch) { - struct fifo_sched_data *q = qdisc_priv(sch); - - if (likely(skb_queue_len(&sch->q) < q->limit)) + if (likely(skb_queue_len(&sch->q) < sch->limit)) return qdisc_enqueue_tail(skb, sch); /* queue full, remove one skb to fulfill the limit */ @@ -61,31 +50,40 @@ static int pfifo_tail_enqueue(struct sk_buff *skb, struct Qdisc* sch) static int fifo_init(struct Qdisc *sch, struct nlattr *opt) { - struct fifo_sched_data *q = qdisc_priv(sch); + bool bypass; + bool is_bfifo = sch->ops == &bfifo_qdisc_ops; if (opt == NULL) { u32 limit = qdisc_dev(sch)->tx_queue_len ? : 1; - if (sch->ops == &bfifo_qdisc_ops) + if (is_bfifo) limit *= psched_mtu(qdisc_dev(sch)); - q->limit = limit; + sch->limit = limit; } else { struct tc_fifo_qopt *ctl = nla_data(opt); if (nla_len(opt) < sizeof(*ctl)) return -EINVAL; - q->limit = ctl->limit; + sch->limit = ctl->limit; } + if (is_bfifo) + bypass = sch->limit >= psched_mtu(qdisc_dev(sch)); + else + bypass = sch->limit >= 1; + + if (bypass) + sch->flags |= TCQ_F_CAN_BYPASS; + else + sch->flags &= ~TCQ_F_CAN_BYPASS; return 0; } static int fifo_dump(struct Qdisc *sch, struct sk_buff *skb) { - struct fifo_sched_data *q = qdisc_priv(sch); - struct tc_fifo_qopt opt = { .limit = q->limit }; + struct tc_fifo_qopt opt = { .limit = sch->limit }; NLA_PUT(skb, TCA_OPTIONS, sizeof(opt), &opt); return skb->len; @@ -96,7 +94,7 @@ nla_put_failure: struct Qdisc_ops pfifo_qdisc_ops __read_mostly = { .id = "pfifo", - .priv_size = sizeof(struct fifo_sched_data), + .priv_size = 0, .enqueue = pfifo_enqueue, .dequeue = qdisc_dequeue_head, .peek = qdisc_peek_head, @@ -111,7 +109,7 @@ EXPORT_SYMBOL(pfifo_qdisc_ops); struct Qdisc_ops bfifo_qdisc_ops __read_mostly = { .id = "bfifo", - .priv_size = sizeof(struct fifo_sched_data), + .priv_size = 0, .enqueue = bfifo_enqueue, .dequeue = qdisc_dequeue_head, .peek = qdisc_peek_head, @@ -126,7 +124,7 @@ EXPORT_SYMBOL(bfifo_qdisc_ops); struct Qdisc_ops pfifo_head_drop_qdisc_ops __read_mostly = { .id = "pfifo_head_drop", - .priv_size = sizeof(struct fifo_sched_data), + .priv_size = 0, .enqueue = pfifo_tail_enqueue, .dequeue = qdisc_dequeue_head, .peek = qdisc_peek_head, diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c index 1bc698039ae..c84b65920d1 100644 --- a/net/sched/sch_generic.c +++ b/net/sched/sch_generic.c @@ -87,8 +87,8 @@ static inline int handle_dev_cpu_collision(struct sk_buff *skb, */ kfree_skb(skb); if (net_ratelimit()) - printk(KERN_WARNING "Dead loop on netdevice %s, " - "fix it urgently!\n", dev_queue->dev->name); + pr_warning("Dead loop on netdevice %s, fix it urgently!\n", + dev_queue->dev->name); ret = qdisc_qlen(q); } else { /* @@ -137,8 +137,8 @@ int sch_direct_xmit(struct sk_buff *skb, struct Qdisc *q, } else { /* Driver returned NETDEV_TX_BUSY - requeue skb */ if (unlikely (ret != NETDEV_TX_BUSY && net_ratelimit())) - printk(KERN_WARNING "BUG %s code %d qlen %d\n", - dev->name, ret, q->q.qlen); + pr_warning("BUG %s code %d qlen %d\n", + dev->name, ret, q->q.qlen); ret = dev_requeue_skb(skb, q); } @@ -412,8 +412,9 @@ static struct Qdisc noqueue_qdisc = { }; -static const u8 prio2band[TC_PRIO_MAX+1] = - { 1, 2, 2, 2, 1, 2, 0, 0 , 1, 1, 1, 1, 1, 1, 1, 1 }; +static const u8 prio2band[TC_PRIO_MAX + 1] = { + 1, 2, 2, 2, 1, 2, 0, 0 , 1, 1, 1, 1, 1, 1, 1, 1 +}; /* 3-band FIFO queue: old style, but should be a bit faster than generic prio+fifo combination. @@ -445,7 +446,7 @@ static inline struct sk_buff_head *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) { if (skb_queue_len(&qdisc->q) < qdisc_dev(qdisc)->tx_queue_len) { int band = prio2band[skb->priority & TC_PRIO_MAX]; @@ -460,7 +461,7 @@ static int pfifo_fast_enqueue(struct sk_buff *skb, struct Qdisc* qdisc) return qdisc_drop(skb, qdisc); } -static struct sk_buff *pfifo_fast_dequeue(struct Qdisc* qdisc) +static struct sk_buff *pfifo_fast_dequeue(struct Qdisc *qdisc) { struct pfifo_fast_priv *priv = qdisc_priv(qdisc); int band = bitmap2band[priv->bitmap]; @@ -479,7 +480,7 @@ static struct sk_buff *pfifo_fast_dequeue(struct Qdisc* qdisc) return NULL; } -static struct sk_buff *pfifo_fast_peek(struct Qdisc* qdisc) +static struct sk_buff *pfifo_fast_peek(struct Qdisc *qdisc) { struct pfifo_fast_priv *priv = qdisc_priv(qdisc); int band = bitmap2band[priv->bitmap]; @@ -493,7 +494,7 @@ static struct sk_buff *pfifo_fast_peek(struct Qdisc* qdisc) return NULL; } -static void pfifo_fast_reset(struct Qdisc* qdisc) +static void pfifo_fast_reset(struct Qdisc *qdisc) { int prio; struct pfifo_fast_priv *priv = qdisc_priv(qdisc); @@ -510,7 +511,7 @@ static int pfifo_fast_dump(struct Qdisc *qdisc, struct sk_buff *skb) { struct tc_prio_qopt opt = { .bands = PFIFO_FAST_BANDS }; - memcpy(&opt.priomap, prio2band, TC_PRIO_MAX+1); + memcpy(&opt.priomap, prio2band, TC_PRIO_MAX + 1); NLA_PUT(skb, TCA_OPTIONS, sizeof(opt), &opt); return skb->len; @@ -526,6 +527,8 @@ static int pfifo_fast_init(struct Qdisc *qdisc, struct nlattr *opt) for (prio = 0; prio < PFIFO_FAST_BANDS; prio++) skb_queue_head_init(band2list(priv, prio)); + /* Can by-pass the queue discipline */ + qdisc->flags |= TCQ_F_CAN_BYPASS; return 0; } @@ -540,27 +543,32 @@ struct Qdisc_ops pfifo_fast_ops __read_mostly = { .dump = pfifo_fast_dump, .owner = THIS_MODULE, }; +EXPORT_SYMBOL(pfifo_fast_ops); struct Qdisc *qdisc_alloc(struct netdev_queue *dev_queue, struct Qdisc_ops *ops) { void *p; struct Qdisc *sch; - unsigned int size; + unsigned int size = QDISC_ALIGN(sizeof(*sch)) + ops->priv_size; int err = -ENOBUFS; - /* ensure that the Qdisc and the private data are 64-byte aligned */ - size = QDISC_ALIGN(sizeof(*sch)); - size += ops->priv_size + (QDISC_ALIGNTO - 1); - p = kzalloc_node(size, GFP_KERNEL, netdev_queue_numa_node_read(dev_queue)); if (!p) goto errout; sch = (struct Qdisc *) QDISC_ALIGN((unsigned long) p); - sch->padded = (char *) sch - (char *) p; - + /* if we got non aligned memory, ask more and do alignment ourself */ + if (sch != p) { + kfree(p); + p = kzalloc_node(size + QDISC_ALIGNTO - 1, GFP_KERNEL, + netdev_queue_numa_node_read(dev_queue)); + if (!p) + goto errout; + sch = (struct Qdisc *) QDISC_ALIGN((unsigned long) p); + sch->padded = (char *) sch - (char *) p; + } INIT_LIST_HEAD(&sch->list); skb_queue_head_init(&sch->q); spin_lock_init(&sch->busylock); @@ -630,7 +638,7 @@ void qdisc_destroy(struct Qdisc *qdisc) #ifdef CONFIG_NET_SCHED qdisc_list_del(qdisc); - qdisc_put_stab(qdisc->stab); + qdisc_put_stab(rtnl_dereference(qdisc->stab)); #endif gen_kill_estimator(&qdisc->bstats, &qdisc->rate_est); if (ops->reset) @@ -674,25 +682,21 @@ struct Qdisc *dev_graft_qdisc(struct netdev_queue *dev_queue, return oqdisc; } +EXPORT_SYMBOL(dev_graft_qdisc); static void attach_one_default_qdisc(struct net_device *dev, struct netdev_queue *dev_queue, void *_unused) { - struct Qdisc *qdisc; + struct Qdisc *qdisc = &noqueue_qdisc; if (dev->tx_queue_len) { qdisc = qdisc_create_dflt(dev_queue, &pfifo_fast_ops, TC_H_ROOT); if (!qdisc) { - printk(KERN_INFO "%s: activation failed\n", dev->name); + netdev_info(dev, "activation failed\n"); return; } - - /* Can by-pass the queue discipline for default qdisc */ - qdisc->flags |= TCQ_F_CAN_BYPASS; - } else { - qdisc = &noqueue_qdisc; } dev_queue->qdisc_sleeping = qdisc; } @@ -761,6 +765,7 @@ void dev_activate(struct net_device *dev) dev_watchdog_up(dev); } } +EXPORT_SYMBOL(dev_activate); static void dev_deactivate_queue(struct net_device *dev, struct netdev_queue *dev_queue, @@ -841,6 +846,7 @@ void dev_deactivate(struct net_device *dev) dev_deactivate_many(&single); list_del(&single); } +EXPORT_SYMBOL(dev_deactivate); static void dev_init_scheduler_queue(struct net_device *dev, struct netdev_queue *dev_queue, diff --git a/net/sched/sch_gred.c b/net/sched/sch_gred.c index 51dcc2aa5c9..b9493a09a87 100644 --- a/net/sched/sch_gred.c +++ b/net/sched/sch_gred.c @@ -32,8 +32,7 @@ struct gred_sched_data; struct gred_sched; -struct gred_sched_data -{ +struct gred_sched_data { u32 limit; /* HARD maximal queue length */ u32 DP; /* the drop pramaters */ u32 bytesin; /* bytes seen on virtualQ so far*/ @@ -50,8 +49,7 @@ enum { GRED_RIO_MODE, }; -struct gred_sched -{ +struct gred_sched { struct gred_sched_data *tab[MAX_DPs]; unsigned long flags; u32 red_flags; @@ -150,17 +148,18 @@ static inline int gred_use_harddrop(struct gred_sched *t) return t->red_flags & TC_RED_HARDDROP; } -static int gred_enqueue(struct sk_buff *skb, struct Qdisc* sch) +static int gred_enqueue(struct sk_buff *skb, struct Qdisc *sch) { - struct gred_sched_data *q=NULL; - struct gred_sched *t= qdisc_priv(sch); + struct gred_sched_data *q = NULL; + struct gred_sched *t = qdisc_priv(sch); unsigned long qavg = 0; u16 dp = tc_index_to_dp(skb); - if (dp >= t->DPs || (q = t->tab[dp]) == NULL) { + if (dp >= t->DPs || (q = t->tab[dp]) == NULL) { dp = t->def; - if ((q = t->tab[dp]) == NULL) { + q = t->tab[dp]; + if (!q) { /* Pass through packets not assigned to a DP * if no default DP has been configured. This * allows for DP flows to be left untouched. @@ -183,7 +182,7 @@ static int gred_enqueue(struct sk_buff *skb, struct Qdisc* sch) for (i = 0; i < t->DPs; i++) { if (t->tab[i] && t->tab[i]->prio < q->prio && !red_is_idling(&t->tab[i]->parms)) - qavg +=t->tab[i]->parms.qavg; + qavg += t->tab[i]->parms.qavg; } } @@ -203,28 +202,28 @@ static int gred_enqueue(struct sk_buff *skb, struct Qdisc* sch) gred_store_wred_set(t, q); switch (red_action(&q->parms, q->parms.qavg + qavg)) { - case RED_DONT_MARK: - break; - - case RED_PROB_MARK: - sch->qstats.overlimits++; - if (!gred_use_ecn(t) || !INET_ECN_set_ce(skb)) { - q->stats.prob_drop++; - goto congestion_drop; - } - - q->stats.prob_mark++; - break; - - case RED_HARD_MARK: - sch->qstats.overlimits++; - if (gred_use_harddrop(t) || !gred_use_ecn(t) || - !INET_ECN_set_ce(skb)) { - q->stats.forced_drop++; - goto congestion_drop; - } - q->stats.forced_mark++; - break; + case RED_DONT_MARK: + break; + + case RED_PROB_MARK: + sch->qstats.overlimits++; + if (!gred_use_ecn(t) || !INET_ECN_set_ce(skb)) { + q->stats.prob_drop++; + goto congestion_drop; + } + + q->stats.prob_mark++; + break; + + case RED_HARD_MARK: + sch->qstats.overlimits++; + if (gred_use_harddrop(t) || !gred_use_ecn(t) || + !INET_ECN_set_ce(skb)) { + q->stats.forced_drop++; + goto congestion_drop; + } + q->stats.forced_mark++; + break; } if (q->backlog + qdisc_pkt_len(skb) <= q->limit) { @@ -241,7 +240,7 @@ congestion_drop: return NET_XMIT_CN; } -static struct sk_buff *gred_dequeue(struct Qdisc* sch) +static struct sk_buff *gred_dequeue(struct Qdisc *sch) { struct sk_buff *skb; struct gred_sched *t = qdisc_priv(sch); @@ -254,9 +253,9 @@ static struct sk_buff *gred_dequeue(struct Qdisc* sch) if (dp >= t->DPs || (q = t->tab[dp]) == NULL) { if (net_ratelimit()) - printk(KERN_WARNING "GRED: Unable to relocate " - "VQ 0x%x after dequeue, screwing up " - "backlog.\n", tc_index_to_dp(skb)); + pr_warning("GRED: Unable to relocate VQ 0x%x " + "after dequeue, screwing up " + "backlog.\n", tc_index_to_dp(skb)); } else { q->backlog -= qdisc_pkt_len(skb); @@ -273,7 +272,7 @@ static struct sk_buff *gred_dequeue(struct Qdisc* sch) return NULL; } -static unsigned int gred_drop(struct Qdisc* sch) +static unsigned int gred_drop(struct Qdisc *sch) { struct sk_buff *skb; struct gred_sched *t = qdisc_priv(sch); @@ -286,9 +285,9 @@ static unsigned int gred_drop(struct Qdisc* sch) if (dp >= t->DPs || (q = t->tab[dp]) == NULL) { if (net_ratelimit()) - printk(KERN_WARNING "GRED: Unable to relocate " - "VQ 0x%x while dropping, screwing up " - "backlog.\n", tc_index_to_dp(skb)); + pr_warning("GRED: Unable to relocate VQ 0x%x " + "while dropping, screwing up " + "backlog.\n", tc_index_to_dp(skb)); } else { q->backlog -= len; q->stats.other++; @@ -308,7 +307,7 @@ static unsigned int gred_drop(struct Qdisc* sch) } -static void gred_reset(struct Qdisc* sch) +static void gred_reset(struct Qdisc *sch) { int i; struct gred_sched *t = qdisc_priv(sch); @@ -369,8 +368,8 @@ static inline int gred_change_table_def(struct Qdisc *sch, struct nlattr *dps) for (i = table->DPs; i < MAX_DPs; i++) { if (table->tab[i]) { - printk(KERN_WARNING "GRED: Warning: Destroying " - "shadowed VQ 0x%x\n", i); + pr_warning("GRED: Warning: Destroying " + "shadowed VQ 0x%x\n", i); gred_destroy_vq(table->tab[i]); table->tab[i] = NULL; } diff --git a/net/sched/sch_hfsc.c b/net/sched/sch_hfsc.c index 14a799de1c3..6488e642565 100644 --- a/net/sched/sch_hfsc.c +++ b/net/sched/sch_hfsc.c @@ -81,8 +81,7 @@ * that are expensive on 32-bit architectures. */ -struct internal_sc -{ +struct internal_sc { u64 sm1; /* scaled slope of the 1st segment */ u64 ism1; /* scaled inverse-slope of the 1st segment */ u64 dx; /* the x-projection of the 1st segment */ @@ -92,8 +91,7 @@ struct internal_sc }; /* runtime service curve */ -struct runtime_sc -{ +struct runtime_sc { u64 x; /* current starting position on x-axis */ u64 y; /* current starting position on y-axis */ u64 sm1; /* scaled slope of the 1st segment */ @@ -104,15 +102,13 @@ struct runtime_sc u64 ism2; /* scaled inverse-slope of the 2nd segment */ }; -enum hfsc_class_flags -{ +enum hfsc_class_flags { HFSC_RSC = 0x1, HFSC_FSC = 0x2, HFSC_USC = 0x4 }; -struct hfsc_class -{ +struct hfsc_class { struct Qdisc_class_common cl_common; unsigned int refcnt; /* usage count */ @@ -140,8 +136,8 @@ struct hfsc_class u64 cl_cumul; /* cumulative work in bytes done by real-time criteria */ - u64 cl_d; /* deadline*/ - u64 cl_e; /* eligible time */ + u64 cl_d; /* deadline*/ + u64 cl_e; /* eligible time */ u64 cl_vt; /* virtual time */ u64 cl_f; /* time when this class will fit for link-sharing, max(myf, cfmin) */ @@ -176,8 +172,7 @@ struct hfsc_class unsigned long cl_nactive; /* number of active children */ }; -struct hfsc_sched -{ +struct hfsc_sched { u16 defcls; /* default class id */ struct hfsc_class root; /* root class */ struct Qdisc_class_hash clhash; /* class hash */ @@ -693,7 +688,7 @@ init_vf(struct hfsc_class *cl, unsigned int len) if (go_active) { n = rb_last(&cl->cl_parent->vt_tree); if (n != NULL) { - max_cl = rb_entry(n, struct hfsc_class,vt_node); + max_cl = rb_entry(n, struct hfsc_class, vt_node); /* * set vt to the average of the min and max * classes. if the parent's period didn't @@ -1177,8 +1172,10 @@ hfsc_classify(struct sk_buff *skb, struct Qdisc *sch, int *qerr) return NULL; } #endif - if ((cl = (struct hfsc_class *)res.class) == NULL) { - if ((cl = hfsc_find_class(res.classid, sch)) == NULL) + cl = (struct hfsc_class *)res.class; + if (!cl) { + cl = hfsc_find_class(res.classid, sch); + if (!cl) break; /* filter selected invalid classid */ if (cl->level >= head->level) break; /* filter may only point downwards */ @@ -1316,7 +1313,7 @@ hfsc_dump_sc(struct sk_buff *skb, int attr, struct internal_sc *sc) return -1; } -static inline int +static int hfsc_dump_curves(struct sk_buff *skb, struct hfsc_class *cl) { if ((cl->cl_flags & HFSC_RSC) && @@ -1420,7 +1417,8 @@ hfsc_schedule_watchdog(struct Qdisc *sch) struct hfsc_class *cl; u64 next_time = 0; - if ((cl = eltree_get_minel(q)) != NULL) + cl = eltree_get_minel(q); + if (cl) next_time = cl->cl_e; if (q->root.cl_cfmin != 0) { if (next_time == 0 || next_time > q->root.cl_cfmin) @@ -1625,7 +1623,8 @@ hfsc_dequeue(struct Qdisc *sch) * find the class with the minimum deadline among * the eligible classes. */ - if ((cl = eltree_get_mindl(q, cur_time)) != NULL) { + cl = eltree_get_mindl(q, cur_time); + if (cl) { realtime = 1; } else { /* @@ -1664,7 +1663,7 @@ hfsc_dequeue(struct Qdisc *sch) set_passive(cl); } - sch->flags &= ~TCQ_F_THROTTLED; + qdisc_unthrottled(sch); qdisc_bstats_update(sch, skb); sch->q.qlen--; diff --git a/net/sched/sch_htb.c b/net/sched/sch_htb.c index fc12fe6f559..e1429a85091 100644 --- a/net/sched/sch_htb.c +++ b/net/sched/sch_htb.c @@ -99,9 +99,10 @@ struct htb_class { struct rb_root feed[TC_HTB_NUMPRIO]; /* feed trees */ struct rb_node *ptr[TC_HTB_NUMPRIO]; /* current class ptr */ /* When class changes from state 1->2 and disconnects from - parent's feed then we lost ptr value and start from the - first child again. Here we store classid of the - last valid ptr (used when ptr is NULL). */ + * parent's feed then we lost ptr value and start from the + * first child again. Here we store classid of the + * last valid ptr (used when ptr is NULL). + */ u32 last_ptr_id[TC_HTB_NUMPRIO]; } inner; } un; @@ -185,7 +186,7 @@ static inline struct htb_class *htb_find(u32 handle, struct Qdisc *sch) * have no valid leaf we try to use MAJOR:default leaf. It still unsuccessfull * then finish and return direct queue. */ -#define HTB_DIRECT (struct htb_class*)-1 +#define HTB_DIRECT ((struct htb_class *)-1L) static struct htb_class *htb_classify(struct sk_buff *skb, struct Qdisc *sch, int *qerr) @@ -197,11 +198,13 @@ static struct htb_class *htb_classify(struct sk_buff *skb, struct Qdisc *sch, int result; /* allow to select class by setting skb->priority to valid classid; - note that nfmark can be used too by attaching filter fw with no - rules in it */ + * note that nfmark can be used too by attaching filter fw with no + * rules in it + */ if (skb->priority == sch->handle) return HTB_DIRECT; /* X:0 (direct flow) selected */ - if ((cl = htb_find(skb->priority, sch)) != NULL && cl->level == 0) + cl = htb_find(skb->priority, sch); + if (cl && cl->level == 0) return cl; *qerr = NET_XMIT_SUCCESS | __NET_XMIT_BYPASS; @@ -216,10 +219,12 @@ static struct htb_class *htb_classify(struct sk_buff *skb, struct Qdisc *sch, return NULL; } #endif - if ((cl = (void *)res.class) == NULL) { + cl = (void *)res.class; + if (!cl) { if (res.classid == sch->handle) return HTB_DIRECT; /* X:0 (direct flow) */ - if ((cl = htb_find(res.classid, sch)) == NULL) + cl = htb_find(res.classid, sch); + if (!cl) break; /* filter selected invalid classid */ } if (!cl->level) @@ -378,7 +383,8 @@ static void htb_activate_prios(struct htb_sched *q, struct htb_class *cl) if (p->un.inner.feed[prio].rb_node) /* parent already has its feed in use so that - reset bit in mask as parent is already ok */ + * reset bit in mask as parent is already ok + */ mask &= ~(1 << prio); htb_add_to_id_tree(p->un.inner.feed + prio, cl, prio); @@ -413,8 +419,9 @@ static void htb_deactivate_prios(struct htb_sched *q, struct htb_class *cl) if (p->un.inner.ptr[prio] == cl->node + prio) { /* we are removing child which is pointed to from - parent feed - forget the pointer but remember - classid */ + * parent feed - forget the pointer but remember + * classid + */ p->un.inner.last_ptr_id[prio] = cl->common.classid; p->un.inner.ptr[prio] = NULL; } @@ -663,8 +670,9 @@ static psched_time_t htb_do_events(struct htb_sched *q, int level, unsigned long start) { /* don't run for longer than 2 jiffies; 2 is used instead of - 1 to simplify things when jiffy is going to be incremented - too soon */ + * 1 to simplify things when jiffy is going to be incremented + * too soon + */ unsigned long stop_at = start + 2; while (time_before(jiffies, stop_at)) { struct htb_class *cl; @@ -687,7 +695,7 @@ static psched_time_t htb_do_events(struct htb_sched *q, int level, /* too much load - let's continue after a break for scheduling */ if (!(q->warned & HTB_WARN_TOOMANYEVENTS)) { - printk(KERN_WARNING "htb: too many events!\n"); + pr_warning("htb: too many events!\n"); q->warned |= HTB_WARN_TOOMANYEVENTS; } @@ -695,7 +703,8 @@ static psched_time_t htb_do_events(struct htb_sched *q, int level, } /* Returns class->node+prio from id-tree where classe's id is >= id. NULL - is no such one exists. */ + * is no such one exists. + */ static struct rb_node *htb_id_find_next_upper(int prio, struct rb_node *n, u32 id) { @@ -739,12 +748,14 @@ static struct htb_class *htb_lookup_leaf(struct rb_root *tree, int prio, for (i = 0; i < 65535; i++) { if (!*sp->pptr && *sp->pid) { /* ptr was invalidated but id is valid - try to recover - the original or next ptr */ + * the original or next ptr + */ *sp->pptr = htb_id_find_next_upper(prio, sp->root, *sp->pid); } *sp->pid = 0; /* ptr is valid now so that remove this hint as it - can become out of date quickly */ + * can become out of date quickly + */ if (!*sp->pptr) { /* we are at right end; rewind & go up */ *sp->pptr = sp->root; while ((*sp->pptr)->rb_left) @@ -772,7 +783,8 @@ static struct htb_class *htb_lookup_leaf(struct rb_root *tree, int prio, } /* dequeues packet at given priority and level; call only if - you are sure that there is active class at prio/level */ + * you are sure that there is active class at prio/level + */ static struct sk_buff *htb_dequeue_tree(struct htb_sched *q, int prio, int level) { @@ -789,9 +801,10 @@ next: return NULL; /* class can be empty - it is unlikely but can be true if leaf - qdisc drops packets in enqueue routine or if someone used - graft operation on the leaf since last dequeue; - simply deactivate and skip such class */ + * qdisc drops packets in enqueue routine or if someone used + * graft operation on the leaf since last dequeue; + * simply deactivate and skip such class + */ if (unlikely(cl->un.leaf.q->q.qlen == 0)) { struct htb_class *next; htb_deactivate(q, cl); @@ -831,7 +844,8 @@ next: ptr[0]) + prio); } /* this used to be after charge_class but this constelation - gives us slightly better performance */ + * gives us slightly better performance + */ if (!cl->un.leaf.q->q.qlen) htb_deactivate(q, cl); htb_charge_class(q, cl, level, skb); @@ -852,7 +866,7 @@ static struct sk_buff *htb_dequeue(struct Qdisc *sch) if (skb != NULL) { ok: qdisc_bstats_update(sch, skb); - sch->flags &= ~TCQ_F_THROTTLED; + qdisc_unthrottled(sch); sch->q.qlen--; return skb; } @@ -883,6 +897,7 @@ ok: m = ~q->row_mask[level]; while (m != (int)(-1)) { int prio = ffz(m); + m |= 1 << prio; skb = htb_dequeue_tree(q, prio, level); if (likely(skb != NULL)) @@ -987,13 +1002,12 @@ static int htb_init(struct Qdisc *sch, struct nlattr *opt) return err; if (tb[TCA_HTB_INIT] == NULL) { - printk(KERN_ERR "HTB: hey probably you have bad tc tool ?\n"); + pr_err("HTB: hey probably you have bad tc tool ?\n"); return -EINVAL; } gopt = nla_data(tb[TCA_HTB_INIT]); if (gopt->version != HTB_VER >> 16) { - printk(KERN_ERR - "HTB: need tc/htb version %d (minor is %d), you have %d\n", + pr_err("HTB: need tc/htb version %d (minor is %d), you have %d\n", HTB_VER >> 16, HTB_VER & 0xffff, gopt->version); return -EINVAL; } @@ -1206,9 +1220,10 @@ static void htb_destroy(struct Qdisc *sch) cancel_work_sync(&q->work); qdisc_watchdog_cancel(&q->watchdog); /* This line used to be after htb_destroy_class call below - and surprisingly it worked in 2.4. But it must precede it - because filter need its target class alive to be able to call - unbind_filter on it (without Oops). */ + * and surprisingly it worked in 2.4. But it must precede it + * because filter need its target class alive to be able to call + * unbind_filter on it (without Oops). + */ tcf_destroy_chain(&q->filter_list); for (i = 0; i < q->clhash.hashsize; i++) { @@ -1342,11 +1357,12 @@ static int htb_change_class(struct Qdisc *sch, u32 classid, /* check maximal depth */ if (parent && parent->parent && parent->parent->level < 2) { - printk(KERN_ERR "htb: tree is too deep\n"); + pr_err("htb: tree is too deep\n"); goto failure; } err = -ENOBUFS; - if ((cl = kzalloc(sizeof(*cl), GFP_KERNEL)) == NULL) + cl = kzalloc(sizeof(*cl), GFP_KERNEL); + if (!cl) goto failure; err = gen_new_estimator(&cl->bstats, &cl->rate_est, @@ -1366,8 +1382,9 @@ static int htb_change_class(struct Qdisc *sch, u32 classid, RB_CLEAR_NODE(&cl->node[prio]); /* create leaf qdisc early because it uses kmalloc(GFP_KERNEL) - so that can't be used inside of sch_tree_lock - -- thanks to Karlis Peisenieks */ + * so that can't be used inside of sch_tree_lock + * -- thanks to Karlis Peisenieks + */ new_q = qdisc_create_dflt(sch->dev_queue, &pfifo_qdisc_ops, classid); sch_tree_lock(sch); @@ -1419,17 +1436,18 @@ static int htb_change_class(struct Qdisc *sch, u32 classid, } /* it used to be a nasty bug here, we have to check that node - is really leaf before changing cl->un.leaf ! */ + * is really leaf before changing cl->un.leaf ! + */ if (!cl->level) { cl->quantum = rtab->rate.rate / q->rate2quantum; if (!hopt->quantum && cl->quantum < 1000) { - printk(KERN_WARNING + pr_warning( "HTB: quantum of class %X is small. Consider r2q change.\n", cl->common.classid); cl->quantum = 1000; } if (!hopt->quantum && cl->quantum > 200000) { - printk(KERN_WARNING + pr_warning( "HTB: quantum of class %X is big. Consider r2q change.\n", cl->common.classid); cl->quantum = 200000; @@ -1478,13 +1496,13 @@ static unsigned long htb_bind_filter(struct Qdisc *sch, unsigned long parent, struct htb_class *cl = htb_find(classid, sch); /*if (cl && !cl->level) return 0; - The line above used to be there to prevent attaching filters to - leaves. But at least tc_index filter uses this just to get class - for other reasons so that we have to allow for it. - ---- - 19.6.2002 As Werner explained it is ok - bind filter is just - another way to "lock" the class - unlike "get" this lock can - be broken by class during destroy IIUC. + * The line above used to be there to prevent attaching filters to + * leaves. But at least tc_index filter uses this just to get class + * for other reasons so that we have to allow for it. + * ---- + * 19.6.2002 As Werner explained it is ok - bind filter is just + * another way to "lock" the class - unlike "get" this lock can + * be broken by class during destroy IIUC. */ if (cl) cl->filter_cnt++; diff --git a/net/sched/sch_mq.c b/net/sched/sch_mq.c index ecc302f4d2a..ec5cbc84896 100644 --- a/net/sched/sch_mq.c +++ b/net/sched/sch_mq.c @@ -61,7 +61,6 @@ static int mq_init(struct Qdisc *sch, struct nlattr *opt) TC_H_MIN(ntx + 1))); if (qdisc == NULL) goto err; - qdisc->flags |= TCQ_F_CAN_BYPASS; priv->qdiscs[ntx] = qdisc; } diff --git a/net/sched/sch_mqprio.c b/net/sched/sch_mqprio.c new file mode 100644 index 00000000000..ea17cbed29e --- /dev/null +++ b/net/sched/sch_mqprio.c @@ -0,0 +1,418 @@ +/* + * net/sched/sch_mqprio.c + * + * Copyright (c) 2010 John Fastabend <john.r.fastabend@intel.com> + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * version 2 as published by the Free Software Foundation. + */ + +#include <linux/types.h> +#include <linux/slab.h> +#include <linux/kernel.h> +#include <linux/string.h> +#include <linux/errno.h> +#include <linux/skbuff.h> +#include <net/netlink.h> +#include <net/pkt_sched.h> +#include <net/sch_generic.h> + +struct mqprio_sched { + struct Qdisc **qdiscs; + int hw_owned; +}; + +static void mqprio_destroy(struct Qdisc *sch) +{ + struct net_device *dev = qdisc_dev(sch); + struct mqprio_sched *priv = qdisc_priv(sch); + unsigned int ntx; + + if (priv->qdiscs) { + for (ntx = 0; + ntx < dev->num_tx_queues && priv->qdiscs[ntx]; + ntx++) + qdisc_destroy(priv->qdiscs[ntx]); + kfree(priv->qdiscs); + } + + if (priv->hw_owned && dev->netdev_ops->ndo_setup_tc) + dev->netdev_ops->ndo_setup_tc(dev, 0); + else + netdev_set_num_tc(dev, 0); +} + +static int mqprio_parse_opt(struct net_device *dev, struct tc_mqprio_qopt *qopt) +{ + int i, j; + + /* Verify num_tc is not out of max range */ + if (qopt->num_tc > TC_MAX_QUEUE) + return -EINVAL; + + /* Verify priority mapping uses valid tcs */ + for (i = 0; i < TC_BITMASK + 1; i++) { + if (qopt->prio_tc_map[i] >= qopt->num_tc) + return -EINVAL; + } + + /* net_device does not support requested operation */ + if (qopt->hw && !dev->netdev_ops->ndo_setup_tc) + return -EINVAL; + + /* if hw owned qcount and qoffset are taken from LLD so + * no reason to verify them here + */ + if (qopt->hw) + return 0; + + for (i = 0; i < qopt->num_tc; i++) { + unsigned int last = qopt->offset[i] + qopt->count[i]; + + /* Verify the queue count is in tx range being equal to the + * real_num_tx_queues indicates the last queue is in use. + */ + if (qopt->offset[i] >= dev->real_num_tx_queues || + !qopt->count[i] || + last > dev->real_num_tx_queues) + return -EINVAL; + + /* Verify that the offset and counts do not overlap */ + for (j = i + 1; j < qopt->num_tc; j++) { + if (last > qopt->offset[j]) + return -EINVAL; + } + } + + return 0; +} + +static int mqprio_init(struct Qdisc *sch, struct nlattr *opt) +{ + struct net_device *dev = qdisc_dev(sch); + struct mqprio_sched *priv = qdisc_priv(sch); + struct netdev_queue *dev_queue; + struct Qdisc *qdisc; + int i, err = -EOPNOTSUPP; + struct tc_mqprio_qopt *qopt = NULL; + + BUILD_BUG_ON(TC_MAX_QUEUE != TC_QOPT_MAX_QUEUE); + BUILD_BUG_ON(TC_BITMASK != TC_QOPT_BITMASK); + + if (sch->parent != TC_H_ROOT) + return -EOPNOTSUPP; + + if (!netif_is_multiqueue(dev)) + return -EOPNOTSUPP; + + if (nla_len(opt) < sizeof(*qopt)) + return -EINVAL; + + qopt = nla_data(opt); + if (mqprio_parse_opt(dev, qopt)) + return -EINVAL; + + /* pre-allocate qdisc, attachment can't fail */ + priv->qdiscs = kcalloc(dev->num_tx_queues, sizeof(priv->qdiscs[0]), + GFP_KERNEL); + if (priv->qdiscs == NULL) { + err = -ENOMEM; + goto err; + } + + for (i = 0; i < dev->num_tx_queues; i++) { + dev_queue = netdev_get_tx_queue(dev, i); + qdisc = qdisc_create_dflt(dev_queue, &pfifo_fast_ops, + TC_H_MAKE(TC_H_MAJ(sch->handle), + TC_H_MIN(i + 1))); + if (qdisc == NULL) { + err = -ENOMEM; + goto err; + } + priv->qdiscs[i] = qdisc; + } + + /* If the mqprio options indicate that hardware should own + * the queue mapping then run ndo_setup_tc otherwise use the + * supplied and verified mapping + */ + if (qopt->hw) { + priv->hw_owned = 1; + err = dev->netdev_ops->ndo_setup_tc(dev, qopt->num_tc); + if (err) + goto err; + } else { + netdev_set_num_tc(dev, qopt->num_tc); + for (i = 0; i < qopt->num_tc; i++) + netdev_set_tc_queue(dev, i, + qopt->count[i], qopt->offset[i]); + } + + /* Always use supplied priority mappings */ + for (i = 0; i < TC_BITMASK + 1; i++) + netdev_set_prio_tc_map(dev, i, qopt->prio_tc_map[i]); + + sch->flags |= TCQ_F_MQROOT; + return 0; + +err: + mqprio_destroy(sch); + return err; +} + +static void mqprio_attach(struct Qdisc *sch) +{ + struct net_device *dev = qdisc_dev(sch); + struct mqprio_sched *priv = qdisc_priv(sch); + struct Qdisc *qdisc; + unsigned int ntx; + + /* Attach underlying qdisc */ + for (ntx = 0; ntx < dev->num_tx_queues; ntx++) { + qdisc = priv->qdiscs[ntx]; + qdisc = dev_graft_qdisc(qdisc->dev_queue, qdisc); + if (qdisc) + qdisc_destroy(qdisc); + } + kfree(priv->qdiscs); + priv->qdiscs = NULL; +} + +static struct netdev_queue *mqprio_queue_get(struct Qdisc *sch, + unsigned long cl) +{ + struct net_device *dev = qdisc_dev(sch); + unsigned long ntx = cl - 1 - netdev_get_num_tc(dev); + + if (ntx >= dev->num_tx_queues) + return NULL; + return netdev_get_tx_queue(dev, ntx); +} + +static int mqprio_graft(struct Qdisc *sch, unsigned long cl, struct Qdisc *new, + struct Qdisc **old) +{ + struct net_device *dev = qdisc_dev(sch); + struct netdev_queue *dev_queue = mqprio_queue_get(sch, cl); + + if (!dev_queue) + return -EINVAL; + + if (dev->flags & IFF_UP) + dev_deactivate(dev); + + *old = dev_graft_qdisc(dev_queue, new); + + if (dev->flags & IFF_UP) + dev_activate(dev); + + return 0; +} + +static int mqprio_dump(struct Qdisc *sch, struct sk_buff *skb) +{ + struct net_device *dev = qdisc_dev(sch); + struct mqprio_sched *priv = qdisc_priv(sch); + unsigned char *b = skb_tail_pointer(skb); + struct tc_mqprio_qopt opt = { 0 }; + struct Qdisc *qdisc; + unsigned int i; + + sch->q.qlen = 0; + memset(&sch->bstats, 0, sizeof(sch->bstats)); + memset(&sch->qstats, 0, sizeof(sch->qstats)); + + for (i = 0; i < dev->num_tx_queues; i++) { + qdisc = netdev_get_tx_queue(dev, i)->qdisc; + spin_lock_bh(qdisc_lock(qdisc)); + sch->q.qlen += qdisc->q.qlen; + sch->bstats.bytes += qdisc->bstats.bytes; + sch->bstats.packets += qdisc->bstats.packets; + sch->qstats.qlen += qdisc->qstats.qlen; + sch->qstats.backlog += qdisc->qstats.backlog; + sch->qstats.drops += qdisc->qstats.drops; + sch->qstats.requeues += qdisc->qstats.requeues; + sch->qstats.overlimits += qdisc->qstats.overlimits; + spin_unlock_bh(qdisc_lock(qdisc)); + } + + opt.num_tc = netdev_get_num_tc(dev); + memcpy(opt.prio_tc_map, dev->prio_tc_map, sizeof(opt.prio_tc_map)); + opt.hw = priv->hw_owned; + + for (i = 0; i < netdev_get_num_tc(dev); i++) { + opt.count[i] = dev->tc_to_txq[i].count; + opt.offset[i] = dev->tc_to_txq[i].offset; + } + + NLA_PUT(skb, TCA_OPTIONS, sizeof(opt), &opt); + + return skb->len; +nla_put_failure: + nlmsg_trim(skb, b); + return -1; +} + +static struct Qdisc *mqprio_leaf(struct Qdisc *sch, unsigned long cl) +{ + struct netdev_queue *dev_queue = mqprio_queue_get(sch, cl); + + if (!dev_queue) + return NULL; + + return dev_queue->qdisc_sleeping; +} + +static unsigned long mqprio_get(struct Qdisc *sch, u32 classid) +{ + struct net_device *dev = qdisc_dev(sch); + unsigned int ntx = TC_H_MIN(classid); + + if (ntx > dev->num_tx_queues + netdev_get_num_tc(dev)) + return 0; + return ntx; +} + +static void mqprio_put(struct Qdisc *sch, unsigned long cl) +{ +} + +static int mqprio_dump_class(struct Qdisc *sch, unsigned long cl, + struct sk_buff *skb, struct tcmsg *tcm) +{ + struct net_device *dev = qdisc_dev(sch); + + if (cl <= netdev_get_num_tc(dev)) { + tcm->tcm_parent = TC_H_ROOT; + tcm->tcm_info = 0; + } else { + int i; + struct netdev_queue *dev_queue; + + dev_queue = mqprio_queue_get(sch, cl); + tcm->tcm_parent = 0; + for (i = 0; i < netdev_get_num_tc(dev); i++) { + struct netdev_tc_txq tc = dev->tc_to_txq[i]; + int q_idx = cl - netdev_get_num_tc(dev); + + if (q_idx > tc.offset && + q_idx <= tc.offset + tc.count) { + tcm->tcm_parent = + TC_H_MAKE(TC_H_MAJ(sch->handle), + TC_H_MIN(i + 1)); + break; + } + } + tcm->tcm_info = dev_queue->qdisc_sleeping->handle; + } + tcm->tcm_handle |= TC_H_MIN(cl); + return 0; +} + +static int mqprio_dump_class_stats(struct Qdisc *sch, unsigned long cl, + struct gnet_dump *d) + __releases(d->lock) + __acquires(d->lock) +{ + struct net_device *dev = qdisc_dev(sch); + + if (cl <= netdev_get_num_tc(dev)) { + int i; + struct Qdisc *qdisc; + struct gnet_stats_queue qstats = {0}; + struct gnet_stats_basic_packed bstats = {0}; + struct netdev_tc_txq tc = dev->tc_to_txq[cl - 1]; + + /* Drop lock here it will be reclaimed before touching + * statistics this is required because the d->lock we + * hold here is the look on dev_queue->qdisc_sleeping + * also acquired below. + */ + spin_unlock_bh(d->lock); + + for (i = tc.offset; i < tc.offset + tc.count; i++) { + qdisc = netdev_get_tx_queue(dev, i)->qdisc; + spin_lock_bh(qdisc_lock(qdisc)); + bstats.bytes += qdisc->bstats.bytes; + bstats.packets += qdisc->bstats.packets; + qstats.qlen += qdisc->qstats.qlen; + qstats.backlog += qdisc->qstats.backlog; + qstats.drops += qdisc->qstats.drops; + qstats.requeues += qdisc->qstats.requeues; + qstats.overlimits += qdisc->qstats.overlimits; + spin_unlock_bh(qdisc_lock(qdisc)); + } + /* Reclaim root sleeping lock before completing stats */ + spin_lock_bh(d->lock); + if (gnet_stats_copy_basic(d, &bstats) < 0 || + gnet_stats_copy_queue(d, &qstats) < 0) + return -1; + } else { + struct netdev_queue *dev_queue = mqprio_queue_get(sch, cl); + + sch = dev_queue->qdisc_sleeping; + sch->qstats.qlen = sch->q.qlen; + if (gnet_stats_copy_basic(d, &sch->bstats) < 0 || + gnet_stats_copy_queue(d, &sch->qstats) < 0) + return -1; + } + return 0; +} + +static void mqprio_walk(struct Qdisc *sch, struct qdisc_walker *arg) +{ + struct net_device *dev = qdisc_dev(sch); + unsigned long ntx; + + if (arg->stop) + return; + + /* Walk hierarchy with a virtual class per tc */ + arg->count = arg->skip; + for (ntx = arg->skip; + ntx < dev->num_tx_queues + netdev_get_num_tc(dev); + ntx++) { + if (arg->fn(sch, ntx + 1, arg) < 0) { + arg->stop = 1; + break; + } + arg->count++; + } +} + +static const struct Qdisc_class_ops mqprio_class_ops = { + .graft = mqprio_graft, + .leaf = mqprio_leaf, + .get = mqprio_get, + .put = mqprio_put, + .walk = mqprio_walk, + .dump = mqprio_dump_class, + .dump_stats = mqprio_dump_class_stats, +}; + +static struct Qdisc_ops mqprio_qdisc_ops __read_mostly = { + .cl_ops = &mqprio_class_ops, + .id = "mqprio", + .priv_size = sizeof(struct mqprio_sched), + .init = mqprio_init, + .destroy = mqprio_destroy, + .attach = mqprio_attach, + .dump = mqprio_dump, + .owner = THIS_MODULE, +}; + +static int __init mqprio_module_init(void) +{ + return register_qdisc(&mqprio_qdisc_ops); +} + +static void __exit mqprio_module_exit(void) +{ + unregister_qdisc(&mqprio_qdisc_ops); +} + +module_init(mqprio_module_init); +module_exit(mqprio_module_exit); + +MODULE_LICENSE("GPL"); diff --git a/net/sched/sch_multiq.c b/net/sched/sch_multiq.c index 436a2e75b32..edc1950e0e7 100644 --- a/net/sched/sch_multiq.c +++ b/net/sched/sch_multiq.c @@ -156,7 +156,7 @@ static unsigned int multiq_drop(struct Qdisc *sch) unsigned int len; struct Qdisc *qdisc; - for (band = q->bands-1; band >= 0; band--) { + for (band = q->bands - 1; band >= 0; band--) { qdisc = q->queues[band]; if (qdisc->ops->drop) { len = qdisc->ops->drop(qdisc); @@ -265,7 +265,7 @@ static int multiq_init(struct Qdisc *sch, struct nlattr *opt) for (i = 0; i < q->max_bands; i++) q->queues[i] = &noop_qdisc; - err = multiq_tune(sch,opt); + err = multiq_tune(sch, opt); if (err) kfree(q->queues); @@ -346,7 +346,7 @@ static int multiq_dump_class(struct Qdisc *sch, unsigned long cl, struct multiq_sched_data *q = qdisc_priv(sch); tcm->tcm_handle |= TC_H_MIN(cl); - tcm->tcm_info = q->queues[cl-1]->handle; + tcm->tcm_info = q->queues[cl - 1]->handle; return 0; } @@ -378,7 +378,7 @@ static void multiq_walk(struct Qdisc *sch, struct qdisc_walker *arg) arg->count++; continue; } - if (arg->fn(sch, band+1, arg) < 0) { + if (arg->fn(sch, band + 1, arg) < 0) { arg->stop = 1; break; } diff --git a/net/sched/sch_netem.c b/net/sched/sch_netem.c index 6a3006b38dc..edbbf7ad662 100644 --- a/net/sched/sch_netem.c +++ b/net/sched/sch_netem.c @@ -19,12 +19,13 @@ #include <linux/kernel.h> #include <linux/errno.h> #include <linux/skbuff.h> +#include <linux/vmalloc.h> #include <linux/rtnetlink.h> #include <net/netlink.h> #include <net/pkt_sched.h> -#define VERSION "1.2" +#define VERSION "1.3" /* Network Emulation Queuing algorithm. ==================================== @@ -47,6 +48,20 @@ layering other disciplines. It does not need to do bandwidth control either since that can be handled by using token bucket or other rate control. + + Correlated Loss Generator models + + Added generation of correlated loss according to the + "Gilbert-Elliot" model, a 4-state markov model. + + References: + [1] NetemCLG Home http://netgroup.uniroma2.it/NetemCLG + [2] S. Salsano, F. Ludovici, A. Ordine, "Definition of a general + and intuitive loss model for packet networks and its implementation + in the Netem module in the Linux kernel", available in [1] + + Authors: Stefano Salsano <stefano.salsano at uniroma2.it + Fabio Ludovici <fabio.ludovici at yahoo.it> */ struct netem_sched_data { @@ -73,6 +88,26 @@ struct netem_sched_data { u32 size; s16 table[0]; } *delay_dist; + + enum { + CLG_RANDOM, + CLG_4_STATES, + CLG_GILB_ELL, + } loss_model; + + /* Correlated Loss Generation models */ + struct clgstate { + /* state of the Markov chain */ + u8 state; + + /* 4-states and Gilbert-Elliot models */ + u32 a1; /* p13 for 4-states or p for GE */ + u32 a2; /* p31 for 4-states or r for GE */ + u32 a3; /* p32 for 4-states or h for GE */ + u32 a4; /* p14 for 4-states or 1-k for GE */ + u32 a5; /* p23 used only in 4-states */ + } clg; + }; /* Time stamp put into socket buffer control block */ @@ -115,6 +150,122 @@ static u32 get_crandom(struct crndstate *state) return answer; } +/* loss_4state - 4-state model loss generator + * Generates losses according to the 4-state Markov chain adopted in + * the GI (General and Intuitive) loss model. + */ +static bool loss_4state(struct netem_sched_data *q) +{ + struct clgstate *clg = &q->clg; + u32 rnd = net_random(); + + /* + * Makes a comparision between rnd and the transition + * probabilities outgoing from the current state, then decides the + * next state and if the next packet has to be transmitted or lost. + * The four states correspond to: + * 1 => successfully transmitted packets within a gap period + * 4 => isolated losses within a gap period + * 3 => lost packets within a burst period + * 2 => successfully transmitted packets within a burst period + */ + switch (clg->state) { + case 1: + if (rnd < clg->a4) { + clg->state = 4; + return true; + } else if (clg->a4 < rnd && rnd < clg->a1) { + clg->state = 3; + return true; + } else if (clg->a1 < rnd) + clg->state = 1; + + break; + case 2: + if (rnd < clg->a5) { + clg->state = 3; + return true; + } else + clg->state = 2; + + break; + case 3: + if (rnd < clg->a3) + clg->state = 2; + else if (clg->a3 < rnd && rnd < clg->a2 + clg->a3) { + clg->state = 1; + return true; + } else if (clg->a2 + clg->a3 < rnd) { + clg->state = 3; + return true; + } + break; + case 4: + clg->state = 1; + break; + } + + return false; +} + +/* loss_gilb_ell - Gilbert-Elliot model loss generator + * Generates losses according to the Gilbert-Elliot loss model or + * its special cases (Gilbert or Simple Gilbert) + * + * Makes a comparision between random number and the transition + * probabilities outgoing from the current state, then decides the + * next state. A second random number is extracted and the comparision + * with the loss probability of the current state decides if the next + * packet will be transmitted or lost. + */ +static bool loss_gilb_ell(struct netem_sched_data *q) +{ + struct clgstate *clg = &q->clg; + + switch (clg->state) { + case 1: + if (net_random() < clg->a1) + clg->state = 2; + if (net_random() < clg->a4) + return true; + case 2: + if (net_random() < clg->a2) + clg->state = 1; + if (clg->a3 > net_random()) + return true; + } + + return false; +} + +static bool loss_event(struct netem_sched_data *q) +{ + switch (q->loss_model) { + case CLG_RANDOM: + /* Random packet drop 0 => none, ~0 => all */ + return q->loss && q->loss >= get_crandom(&q->loss_cor); + + case CLG_4_STATES: + /* 4state loss model algorithm (used also for GI model) + * Extracts a value from the markov 4 state loss generator, + * if it is 1 drops a packet and if needed writes the event in + * the kernel logs + */ + return loss_4state(q); + + case CLG_GILB_ELL: + /* Gilbert-Elliot loss model algorithm + * Extracts a value from the Gilbert-Elliot loss generator, + * if it is 1 drops a packet and if needed writes the event in + * the kernel logs + */ + return loss_gilb_ell(q); + } + + return false; /* not reached */ +} + + /* tabledist - return a pseudo-randomly distributed value with mean mu and * std deviation sigma. Uses table lookup to approximate the desired * distribution, and a uniformly-distributed pseudo-random source. @@ -161,14 +312,12 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch) int ret; int count = 1; - pr_debug("netem_enqueue skb=%p\n", skb); - /* Random duplication */ if (q->duplicate && q->duplicate >= get_crandom(&q->dup_cor)) ++count; - /* Random packet drop 0 => none, ~0 => all */ - if (q->loss && q->loss >= get_crandom(&q->loss_cor)) + /* Drop packet? */ + if (loss_event(q)) --count; if (count == 0) { @@ -211,8 +360,8 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch) } cb = netem_skb_cb(skb); - if (q->gap == 0 || /* not doing reordering */ - q->counter < q->gap || /* inside last reordering gap */ + if (q->gap == 0 || /* not doing reordering */ + q->counter < q->gap || /* inside last reordering gap */ q->reorder < get_crandom(&q->reorder_cor)) { psched_time_t now; psched_tdiff_t delay; @@ -238,17 +387,18 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch) ret = NET_XMIT_SUCCESS; } - if (likely(ret == NET_XMIT_SUCCESS)) { - sch->q.qlen++; - } else if (net_xmit_drop_count(ret)) { - sch->qstats.drops++; + if (ret != NET_XMIT_SUCCESS) { + if (net_xmit_drop_count(ret)) { + sch->qstats.drops++; + return ret; + } } - pr_debug("netem: enqueue ret %d\n", ret); - return ret; + sch->q.qlen++; + return NET_XMIT_SUCCESS; } -static unsigned int netem_drop(struct Qdisc* sch) +static unsigned int netem_drop(struct Qdisc *sch) { struct netem_sched_data *q = qdisc_priv(sch); unsigned int len = 0; @@ -265,7 +415,7 @@ static struct sk_buff *netem_dequeue(struct Qdisc *sch) struct netem_sched_data *q = qdisc_priv(sch); struct sk_buff *skb; - if (sch->flags & TCQ_F_THROTTLED) + if (qdisc_is_throttled(sch)) return NULL; skb = q->qdisc->ops->peek(q->qdisc); @@ -287,9 +437,10 @@ static struct sk_buff *netem_dequeue(struct Qdisc *sch) if (G_TC_FROM(skb->tc_verd) & AT_INGRESS) skb->tstamp.tv64 = 0; #endif - pr_debug("netem_dequeue: return skb=%p\n", skb); - qdisc_bstats_update(sch, skb); + sch->q.qlen--; + qdisc_unthrottled(sch); + qdisc_bstats_update(sch, skb); return skb; } @@ -308,6 +459,16 @@ static void netem_reset(struct Qdisc *sch) qdisc_watchdog_cancel(&q->watchdog); } +static void dist_free(struct disttable *d) +{ + if (d) { + if (is_vmalloc_addr(d)) + vfree(d); + else + kfree(d); + } +} + /* * Distribution data is a variable size payload containing * signed 16 bit values. @@ -315,16 +476,20 @@ static void netem_reset(struct Qdisc *sch) static int get_dist_table(struct Qdisc *sch, const struct nlattr *attr) { struct netem_sched_data *q = qdisc_priv(sch); - unsigned long n = nla_len(attr)/sizeof(__s16); + size_t n = nla_len(attr)/sizeof(__s16); const __s16 *data = nla_data(attr); spinlock_t *root_lock; struct disttable *d; int i; + size_t s; - if (n > 65536) + if (n > NETEM_DIST_MAX) return -EINVAL; - d = kmalloc(sizeof(*d) + n*sizeof(d->table[0]), GFP_KERNEL); + s = sizeof(struct disttable) + n * sizeof(s16); + d = kmalloc(s, GFP_KERNEL); + if (!d) + d = vmalloc(s); if (!d) return -ENOMEM; @@ -335,7 +500,7 @@ static int get_dist_table(struct Qdisc *sch, const struct nlattr *attr) root_lock = qdisc_root_sleeping_lock(sch); spin_lock_bh(root_lock); - kfree(q->delay_dist); + dist_free(q->delay_dist); q->delay_dist = d; spin_unlock_bh(root_lock); return 0; @@ -369,10 +534,66 @@ static void get_corrupt(struct Qdisc *sch, const struct nlattr *attr) init_crandom(&q->corrupt_cor, r->correlation); } +static int get_loss_clg(struct Qdisc *sch, const struct nlattr *attr) +{ + struct netem_sched_data *q = qdisc_priv(sch); + const struct nlattr *la; + int rem; + + nla_for_each_nested(la, attr, rem) { + u16 type = nla_type(la); + + switch(type) { + case NETEM_LOSS_GI: { + const struct tc_netem_gimodel *gi = nla_data(la); + + if (nla_len(la) != sizeof(struct tc_netem_gimodel)) { + pr_info("netem: incorrect gi model size\n"); + return -EINVAL; + } + + q->loss_model = CLG_4_STATES; + + q->clg.state = 1; + q->clg.a1 = gi->p13; + q->clg.a2 = gi->p31; + q->clg.a3 = gi->p32; + q->clg.a4 = gi->p14; + q->clg.a5 = gi->p23; + break; + } + + case NETEM_LOSS_GE: { + const struct tc_netem_gemodel *ge = nla_data(la); + + if (nla_len(la) != sizeof(struct tc_netem_gemodel)) { + pr_info("netem: incorrect gi model size\n"); + return -EINVAL; + } + + q->loss_model = CLG_GILB_ELL; + q->clg.state = 1; + q->clg.a1 = ge->p; + q->clg.a2 = ge->r; + q->clg.a3 = ge->h; + q->clg.a4 = ge->k1; + break; + } + + default: + pr_info("netem: unknown loss type %u\n", type); + return -EINVAL; + } + } + + return 0; +} + static const struct nla_policy netem_policy[TCA_NETEM_MAX + 1] = { [TCA_NETEM_CORR] = { .len = sizeof(struct tc_netem_corr) }, [TCA_NETEM_REORDER] = { .len = sizeof(struct tc_netem_reorder) }, [TCA_NETEM_CORRUPT] = { .len = sizeof(struct tc_netem_corrupt) }, + [TCA_NETEM_LOSS] = { .type = NLA_NESTED }, }; static int parse_attr(struct nlattr *tb[], int maxtype, struct nlattr *nla, @@ -380,11 +601,15 @@ static int parse_attr(struct nlattr *tb[], int maxtype, struct nlattr *nla, { int nested_len = nla_len(nla) - NLA_ALIGN(len); - if (nested_len < 0) + if (nested_len < 0) { + pr_info("netem: invalid attributes len %d\n", nested_len); return -EINVAL; + } + if (nested_len >= nla_attr_size(0)) return nla_parse(tb, maxtype, nla_data(nla) + NLA_ALIGN(len), nested_len, policy); + memset(tb, 0, sizeof(struct nlattr *) * (maxtype + 1)); return 0; } @@ -407,7 +632,7 @@ static int netem_change(struct Qdisc *sch, struct nlattr *opt) ret = fifo_set_limit(q->qdisc, qopt->limit); if (ret) { - pr_debug("netem: can't set fifo limit\n"); + pr_info("netem: can't set fifo limit\n"); return ret; } @@ -440,7 +665,11 @@ static int netem_change(struct Qdisc *sch, struct nlattr *opt) if (tb[TCA_NETEM_CORRUPT]) get_corrupt(sch, tb[TCA_NETEM_CORRUPT]); - return 0; + q->loss_model = CLG_RANDOM; + if (tb[TCA_NETEM_LOSS]) + ret = get_loss_clg(sch, tb[TCA_NETEM_LOSS]); + + return ret; } /* @@ -535,16 +764,17 @@ static int netem_init(struct Qdisc *sch, struct nlattr *opt) qdisc_watchdog_init(&q->watchdog, sch); + q->loss_model = CLG_RANDOM; q->qdisc = qdisc_create_dflt(sch->dev_queue, &tfifo_qdisc_ops, TC_H_MAKE(sch->handle, 1)); if (!q->qdisc) { - pr_debug("netem: qdisc create failed\n"); + pr_notice("netem: qdisc create tfifo qdisc failed\n"); return -ENOMEM; } ret = netem_change(sch, opt); if (ret) { - pr_debug("netem: change failed\n"); + pr_info("netem: change failed\n"); qdisc_destroy(q->qdisc); } return ret; @@ -556,14 +786,61 @@ static void netem_destroy(struct Qdisc *sch) qdisc_watchdog_cancel(&q->watchdog); qdisc_destroy(q->qdisc); - kfree(q->delay_dist); + dist_free(q->delay_dist); +} + +static int dump_loss_model(const struct netem_sched_data *q, + struct sk_buff *skb) +{ + struct nlattr *nest; + + nest = nla_nest_start(skb, TCA_NETEM_LOSS); + if (nest == NULL) + goto nla_put_failure; + + switch (q->loss_model) { + case CLG_RANDOM: + /* legacy loss model */ + nla_nest_cancel(skb, nest); + return 0; /* no data */ + + case CLG_4_STATES: { + struct tc_netem_gimodel gi = { + .p13 = q->clg.a1, + .p31 = q->clg.a2, + .p32 = q->clg.a3, + .p14 = q->clg.a4, + .p23 = q->clg.a5, + }; + + NLA_PUT(skb, NETEM_LOSS_GI, sizeof(gi), &gi); + break; + } + case CLG_GILB_ELL: { + struct tc_netem_gemodel ge = { + .p = q->clg.a1, + .r = q->clg.a2, + .h = q->clg.a3, + .k1 = q->clg.a4, + }; + + NLA_PUT(skb, NETEM_LOSS_GE, sizeof(ge), &ge); + break; + } + } + + nla_nest_end(skb, nest); + return 0; + +nla_put_failure: + nla_nest_cancel(skb, nest); + return -1; } static int netem_dump(struct Qdisc *sch, struct sk_buff *skb) { const struct netem_sched_data *q = qdisc_priv(sch); - unsigned char *b = skb_tail_pointer(skb); - struct nlattr *nla = (struct nlattr *) b; + struct nlattr *nla = (struct nlattr *) skb_tail_pointer(skb); struct tc_netem_qopt qopt; struct tc_netem_corr cor; struct tc_netem_reorder reorder; @@ -590,17 +867,87 @@ static int netem_dump(struct Qdisc *sch, struct sk_buff *skb) corrupt.correlation = q->corrupt_cor.rho; NLA_PUT(skb, TCA_NETEM_CORRUPT, sizeof(corrupt), &corrupt); - nla->nla_len = skb_tail_pointer(skb) - b; + if (dump_loss_model(q, skb) != 0) + goto nla_put_failure; - return skb->len; + return nla_nest_end(skb, nla); nla_put_failure: - nlmsg_trim(skb, b); + nlmsg_trim(skb, nla); return -1; } +static int netem_dump_class(struct Qdisc *sch, unsigned long cl, + struct sk_buff *skb, struct tcmsg *tcm) +{ + struct netem_sched_data *q = qdisc_priv(sch); + + if (cl != 1) /* only one class */ + return -ENOENT; + + tcm->tcm_handle |= TC_H_MIN(1); + tcm->tcm_info = q->qdisc->handle; + + return 0; +} + +static int netem_graft(struct Qdisc *sch, unsigned long arg, struct Qdisc *new, + struct Qdisc **old) +{ + struct netem_sched_data *q = qdisc_priv(sch); + + if (new == NULL) + new = &noop_qdisc; + + sch_tree_lock(sch); + *old = q->qdisc; + q->qdisc = new; + qdisc_tree_decrease_qlen(*old, (*old)->q.qlen); + qdisc_reset(*old); + sch_tree_unlock(sch); + + return 0; +} + +static struct Qdisc *netem_leaf(struct Qdisc *sch, unsigned long arg) +{ + struct netem_sched_data *q = qdisc_priv(sch); + return q->qdisc; +} + +static unsigned long netem_get(struct Qdisc *sch, u32 classid) +{ + return 1; +} + +static void netem_put(struct Qdisc *sch, unsigned long arg) +{ +} + +static void netem_walk(struct Qdisc *sch, struct qdisc_walker *walker) +{ + if (!walker->stop) { + if (walker->count >= walker->skip) + if (walker->fn(sch, 1, walker) < 0) { + walker->stop = 1; + return; + } + walker->count++; + } +} + +static const struct Qdisc_class_ops netem_class_ops = { + .graft = netem_graft, + .leaf = netem_leaf, + .get = netem_get, + .put = netem_put, + .walk = netem_walk, + .dump = netem_dump_class, +}; + static struct Qdisc_ops netem_qdisc_ops __read_mostly = { .id = "netem", + .cl_ops = &netem_class_ops, .priv_size = sizeof(struct netem_sched_data), .enqueue = netem_enqueue, .dequeue = netem_dequeue, diff --git a/net/sched/sch_prio.c b/net/sched/sch_prio.c index fbd710d619b..2a318f2dc3e 100644 --- a/net/sched/sch_prio.c +++ b/net/sched/sch_prio.c @@ -22,8 +22,7 @@ #include <net/pkt_sched.h> -struct prio_sched_data -{ +struct prio_sched_data { int bands; struct tcf_proto *filter_list; u8 prio2band[TC_PRIO_MAX+1]; @@ -54,7 +53,7 @@ prio_classify(struct sk_buff *skb, struct Qdisc *sch, int *qerr) if (!q->filter_list || err < 0) { if (TC_H_MAJ(band)) band = 0; - return q->queues[q->prio2band[band&TC_PRIO_MAX]]; + return q->queues[q->prio2band[band & TC_PRIO_MAX]]; } band = res.classid; } @@ -106,7 +105,7 @@ static struct sk_buff *prio_peek(struct Qdisc *sch) return NULL; } -static struct sk_buff *prio_dequeue(struct Qdisc* sch) +static struct sk_buff *prio_dequeue(struct Qdisc *sch) { struct prio_sched_data *q = qdisc_priv(sch); int prio; @@ -124,7 +123,7 @@ static struct sk_buff *prio_dequeue(struct Qdisc* sch) } -static unsigned int prio_drop(struct Qdisc* sch) +static unsigned int prio_drop(struct Qdisc *sch) { struct prio_sched_data *q = qdisc_priv(sch); int prio; @@ -143,24 +142,24 @@ static unsigned int prio_drop(struct Qdisc* sch) static void -prio_reset(struct Qdisc* sch) +prio_reset(struct Qdisc *sch) { int prio; struct prio_sched_data *q = qdisc_priv(sch); - for (prio=0; prio<q->bands; prio++) + for (prio = 0; prio < q->bands; prio++) qdisc_reset(q->queues[prio]); sch->q.qlen = 0; } static void -prio_destroy(struct Qdisc* sch) +prio_destroy(struct Qdisc *sch) { int prio; struct prio_sched_data *q = qdisc_priv(sch); tcf_destroy_chain(&q->filter_list); - for (prio=0; prio<q->bands; prio++) + for (prio = 0; prio < q->bands; prio++) qdisc_destroy(q->queues[prio]); } @@ -177,7 +176,7 @@ static int prio_tune(struct Qdisc *sch, struct nlattr *opt) if (qopt->bands > TCQ_PRIO_BANDS || qopt->bands < 2) return -EINVAL; - for (i=0; i<=TC_PRIO_MAX; i++) { + for (i = 0; i <= TC_PRIO_MAX; i++) { if (qopt->priomap[i] >= qopt->bands) return -EINVAL; } @@ -186,7 +185,7 @@ static int prio_tune(struct Qdisc *sch, struct nlattr *opt) q->bands = qopt->bands; memcpy(q->prio2band, qopt->priomap, TC_PRIO_MAX+1); - for (i=q->bands; i<TCQ_PRIO_BANDS; i++) { + for (i = q->bands; i < TCQ_PRIO_BANDS; i++) { struct Qdisc *child = q->queues[i]; q->queues[i] = &noop_qdisc; if (child != &noop_qdisc) { @@ -196,9 +195,10 @@ static int prio_tune(struct Qdisc *sch, struct nlattr *opt) } sch_tree_unlock(sch); - for (i=0; i<q->bands; i++) { + for (i = 0; i < q->bands; i++) { if (q->queues[i] == &noop_qdisc) { struct Qdisc *child, *old; + child = qdisc_create_dflt(sch->dev_queue, &pfifo_qdisc_ops, TC_H_MAKE(sch->handle, i + 1)); @@ -224,7 +224,7 @@ static int prio_init(struct Qdisc *sch, struct nlattr *opt) struct prio_sched_data *q = qdisc_priv(sch); int i; - for (i=0; i<TCQ_PRIO_BANDS; i++) + for (i = 0; i < TCQ_PRIO_BANDS; i++) q->queues[i] = &noop_qdisc; if (opt == NULL) { @@ -232,7 +232,7 @@ static int prio_init(struct Qdisc *sch, struct nlattr *opt) } else { int err; - if ((err= prio_tune(sch, opt)) != 0) + if ((err = prio_tune(sch, opt)) != 0) return err; } return 0; @@ -245,7 +245,7 @@ static int prio_dump(struct Qdisc *sch, struct sk_buff *skb) struct tc_prio_qopt opt; opt.bands = q->bands; - memcpy(&opt.priomap, q->prio2band, TC_PRIO_MAX+1); + memcpy(&opt.priomap, q->prio2band, TC_PRIO_MAX + 1); NLA_PUT(skb, TCA_OPTIONS, sizeof(opt), &opt); @@ -342,7 +342,7 @@ static void prio_walk(struct Qdisc *sch, struct qdisc_walker *arg) arg->count++; continue; } - if (arg->fn(sch, prio+1, arg) < 0) { + if (arg->fn(sch, prio + 1, arg) < 0) { arg->stop = 1; break; } @@ -350,7 +350,7 @@ static void prio_walk(struct Qdisc *sch, struct qdisc_walker *arg) } } -static struct tcf_proto ** prio_find_tcf(struct Qdisc *sch, unsigned long cl) +static struct tcf_proto **prio_find_tcf(struct Qdisc *sch, unsigned long cl) { struct prio_sched_data *q = qdisc_priv(sch); diff --git a/net/sched/sch_red.c b/net/sched/sch_red.c index 9f98dbd32d4..6649463da1b 100644 --- a/net/sched/sch_red.c +++ b/net/sched/sch_red.c @@ -36,8 +36,7 @@ if RED works correctly. */ -struct red_sched_data -{ +struct red_sched_data { u32 limit; /* HARD maximal queue length */ unsigned char flags; struct red_parms parms; @@ -55,7 +54,7 @@ static inline int red_use_harddrop(struct red_sched_data *q) return q->flags & TC_RED_HARDDROP; } -static int red_enqueue(struct sk_buff *skb, struct Qdisc* sch) +static int red_enqueue(struct sk_buff *skb, struct Qdisc *sch) { struct red_sched_data *q = qdisc_priv(sch); struct Qdisc *child = q->qdisc; @@ -67,29 +66,29 @@ static int red_enqueue(struct sk_buff *skb, struct Qdisc* sch) red_end_of_idle_period(&q->parms); switch (red_action(&q->parms, q->parms.qavg)) { - case RED_DONT_MARK: - break; - - case RED_PROB_MARK: - sch->qstats.overlimits++; - if (!red_use_ecn(q) || !INET_ECN_set_ce(skb)) { - q->stats.prob_drop++; - goto congestion_drop; - } - - q->stats.prob_mark++; - break; - - case RED_HARD_MARK: - sch->qstats.overlimits++; - if (red_use_harddrop(q) || !red_use_ecn(q) || - !INET_ECN_set_ce(skb)) { - q->stats.forced_drop++; - goto congestion_drop; - } - - q->stats.forced_mark++; - break; + case RED_DONT_MARK: + break; + + case RED_PROB_MARK: + sch->qstats.overlimits++; + if (!red_use_ecn(q) || !INET_ECN_set_ce(skb)) { + q->stats.prob_drop++; + goto congestion_drop; + } + + q->stats.prob_mark++; + break; + + case RED_HARD_MARK: + sch->qstats.overlimits++; + if (red_use_harddrop(q) || !red_use_ecn(q) || + !INET_ECN_set_ce(skb)) { + q->stats.forced_drop++; + goto congestion_drop; + } + + q->stats.forced_mark++; + break; } ret = qdisc_enqueue(skb, child); @@ -106,7 +105,7 @@ congestion_drop: return NET_XMIT_CN; } -static struct sk_buff * red_dequeue(struct Qdisc* sch) +static struct sk_buff *red_dequeue(struct Qdisc *sch) { struct sk_buff *skb; struct red_sched_data *q = qdisc_priv(sch); @@ -123,7 +122,7 @@ static struct sk_buff * red_dequeue(struct Qdisc* sch) return skb; } -static struct sk_buff * red_peek(struct Qdisc* sch) +static struct sk_buff *red_peek(struct Qdisc *sch) { struct red_sched_data *q = qdisc_priv(sch); struct Qdisc *child = q->qdisc; @@ -131,7 +130,7 @@ static struct sk_buff * red_peek(struct Qdisc* sch) return child->ops->peek(child); } -static unsigned int red_drop(struct Qdisc* sch) +static unsigned int red_drop(struct Qdisc *sch) { struct red_sched_data *q = qdisc_priv(sch); struct Qdisc *child = q->qdisc; @@ -150,7 +149,7 @@ static unsigned int red_drop(struct Qdisc* sch) return 0; } -static void red_reset(struct Qdisc* sch) +static void red_reset(struct Qdisc *sch) { struct red_sched_data *q = qdisc_priv(sch); @@ -217,7 +216,7 @@ static int red_change(struct Qdisc *sch, struct nlattr *opt) return 0; } -static int red_init(struct Qdisc* sch, struct nlattr *opt) +static int red_init(struct Qdisc *sch, struct nlattr *opt) { struct red_sched_data *q = qdisc_priv(sch); diff --git a/net/sched/sch_sfb.c b/net/sched/sch_sfb.c new file mode 100644 index 00000000000..0a833d0c1f6 --- /dev/null +++ b/net/sched/sch_sfb.c @@ -0,0 +1,709 @@ +/* + * net/sched/sch_sfb.c Stochastic Fair Blue + * + * Copyright (c) 2008-2011 Juliusz Chroboczek <jch@pps.jussieu.fr> + * Copyright (c) 2011 Eric Dumazet <eric.dumazet@gmail.com> + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * version 2 as published by the Free Software Foundation. + * + * W. Feng, D. Kandlur, D. Saha, K. Shin. Blue: + * A New Class of Active Queue Management Algorithms. + * U. Michigan CSE-TR-387-99, April 1999. + * + * http://www.thefengs.com/wuchang/blue/CSE-TR-387-99.pdf + * + */ + +#include <linux/module.h> +#include <linux/types.h> +#include <linux/kernel.h> +#include <linux/errno.h> +#include <linux/skbuff.h> +#include <linux/random.h> +#include <linux/jhash.h> +#include <net/ip.h> +#include <net/pkt_sched.h> +#include <net/inet_ecn.h> + +/* + * SFB uses two B[l][n] : L x N arrays of bins (L levels, N bins per level) + * This implementation uses L = 8 and N = 16 + * This permits us to split one 32bit hash (provided per packet by rxhash or + * external classifier) into 8 subhashes of 4 bits. + */ +#define SFB_BUCKET_SHIFT 4 +#define SFB_NUMBUCKETS (1 << SFB_BUCKET_SHIFT) /* N bins per Level */ +#define SFB_BUCKET_MASK (SFB_NUMBUCKETS - 1) +#define SFB_LEVELS (32 / SFB_BUCKET_SHIFT) /* L */ + +/* SFB algo uses a virtual queue, named "bin" */ +struct sfb_bucket { + u16 qlen; /* length of virtual queue */ + u16 p_mark; /* marking probability */ +}; + +/* We use a double buffering right before hash change + * (Section 4.4 of SFB reference : moving hash functions) + */ +struct sfb_bins { + u32 perturbation; /* jhash perturbation */ + struct sfb_bucket bins[SFB_LEVELS][SFB_NUMBUCKETS]; +}; + +struct sfb_sched_data { + struct Qdisc *qdisc; + struct tcf_proto *filter_list; + unsigned long rehash_interval; + unsigned long warmup_time; /* double buffering warmup time in jiffies */ + u32 max; + u32 bin_size; /* maximum queue length per bin */ + u32 increment; /* d1 */ + u32 decrement; /* d2 */ + u32 limit; /* HARD maximal queue length */ + u32 penalty_rate; + u32 penalty_burst; + u32 tokens_avail; + unsigned long rehash_time; + unsigned long token_time; + + u8 slot; /* current active bins (0 or 1) */ + bool double_buffering; + struct sfb_bins bins[2]; + + struct { + u32 earlydrop; + u32 penaltydrop; + u32 bucketdrop; + u32 queuedrop; + u32 childdrop; /* drops in child qdisc */ + u32 marked; /* ECN mark */ + } stats; +}; + +/* + * Each queued skb might be hashed on one or two bins + * We store in skb_cb the two hash values. + * (A zero value means double buffering was not used) + */ +struct sfb_skb_cb { + u32 hashes[2]; +}; + +static inline struct sfb_skb_cb *sfb_skb_cb(const struct sk_buff *skb) +{ + BUILD_BUG_ON(sizeof(skb->cb) < + sizeof(struct qdisc_skb_cb) + sizeof(struct sfb_skb_cb)); + return (struct sfb_skb_cb *)qdisc_skb_cb(skb)->data; +} + +/* + * If using 'internal' SFB flow classifier, hash comes from skb rxhash + * If using external classifier, hash comes from the classid. + */ +static u32 sfb_hash(const struct sk_buff *skb, u32 slot) +{ + return sfb_skb_cb(skb)->hashes[slot]; +} + +/* Probabilities are coded as Q0.16 fixed-point values, + * with 0xFFFF representing 65535/65536 (almost 1.0) + * Addition and subtraction are saturating in [0, 65535] + */ +static u32 prob_plus(u32 p1, u32 p2) +{ + u32 res = p1 + p2; + + return min_t(u32, res, SFB_MAX_PROB); +} + +static u32 prob_minus(u32 p1, u32 p2) +{ + return p1 > p2 ? p1 - p2 : 0; +} + +static void increment_one_qlen(u32 sfbhash, u32 slot, struct sfb_sched_data *q) +{ + int i; + struct sfb_bucket *b = &q->bins[slot].bins[0][0]; + + for (i = 0; i < SFB_LEVELS; i++) { + u32 hash = sfbhash & SFB_BUCKET_MASK; + + sfbhash >>= SFB_BUCKET_SHIFT; + if (b[hash].qlen < 0xFFFF) + b[hash].qlen++; + b += SFB_NUMBUCKETS; /* next level */ + } +} + +static void increment_qlen(const struct sk_buff *skb, struct sfb_sched_data *q) +{ + u32 sfbhash; + + sfbhash = sfb_hash(skb, 0); + if (sfbhash) + increment_one_qlen(sfbhash, 0, q); + + sfbhash = sfb_hash(skb, 1); + if (sfbhash) + increment_one_qlen(sfbhash, 1, q); +} + +static void decrement_one_qlen(u32 sfbhash, u32 slot, + struct sfb_sched_data *q) +{ + int i; + struct sfb_bucket *b = &q->bins[slot].bins[0][0]; + + for (i = 0; i < SFB_LEVELS; i++) { + u32 hash = sfbhash & SFB_BUCKET_MASK; + + sfbhash >>= SFB_BUCKET_SHIFT; + if (b[hash].qlen > 0) + b[hash].qlen--; + b += SFB_NUMBUCKETS; /* next level */ + } +} + +static void decrement_qlen(const struct sk_buff *skb, struct sfb_sched_data *q) +{ + u32 sfbhash; + + sfbhash = sfb_hash(skb, 0); + if (sfbhash) + decrement_one_qlen(sfbhash, 0, q); + + sfbhash = sfb_hash(skb, 1); + if (sfbhash) + decrement_one_qlen(sfbhash, 1, q); +} + +static void decrement_prob(struct sfb_bucket *b, struct sfb_sched_data *q) +{ + b->p_mark = prob_minus(b->p_mark, q->decrement); +} + +static void increment_prob(struct sfb_bucket *b, struct sfb_sched_data *q) +{ + b->p_mark = prob_plus(b->p_mark, q->increment); +} + +static void sfb_zero_all_buckets(struct sfb_sched_data *q) +{ + memset(&q->bins, 0, sizeof(q->bins)); +} + +/* + * compute max qlen, max p_mark, and avg p_mark + */ +static u32 sfb_compute_qlen(u32 *prob_r, u32 *avgpm_r, const struct sfb_sched_data *q) +{ + int i; + u32 qlen = 0, prob = 0, totalpm = 0; + const struct sfb_bucket *b = &q->bins[q->slot].bins[0][0]; + + for (i = 0; i < SFB_LEVELS * SFB_NUMBUCKETS; i++) { + if (qlen < b->qlen) + qlen = b->qlen; + totalpm += b->p_mark; + if (prob < b->p_mark) + prob = b->p_mark; + b++; + } + *prob_r = prob; + *avgpm_r = totalpm / (SFB_LEVELS * SFB_NUMBUCKETS); + return qlen; +} + + +static void sfb_init_perturbation(u32 slot, struct sfb_sched_data *q) +{ + q->bins[slot].perturbation = net_random(); +} + +static void sfb_swap_slot(struct sfb_sched_data *q) +{ + sfb_init_perturbation(q->slot, q); + q->slot ^= 1; + q->double_buffering = false; +} + +/* Non elastic flows are allowed to use part of the bandwidth, expressed + * in "penalty_rate" packets per second, with "penalty_burst" burst + */ +static bool sfb_rate_limit(struct sk_buff *skb, struct sfb_sched_data *q) +{ + if (q->penalty_rate == 0 || q->penalty_burst == 0) + return true; + + if (q->tokens_avail < 1) { + unsigned long age = min(10UL * HZ, jiffies - q->token_time); + + q->tokens_avail = (age * q->penalty_rate) / HZ; + if (q->tokens_avail > q->penalty_burst) + q->tokens_avail = q->penalty_burst; + q->token_time = jiffies; + if (q->tokens_avail < 1) + return true; + } + + q->tokens_avail--; + return false; +} + +static bool sfb_classify(struct sk_buff *skb, struct sfb_sched_data *q, + int *qerr, u32 *salt) +{ + struct tcf_result res; + int result; + + result = tc_classify(skb, q->filter_list, &res); + if (result >= 0) { +#ifdef CONFIG_NET_CLS_ACT + switch (result) { + case TC_ACT_STOLEN: + case TC_ACT_QUEUED: + *qerr = NET_XMIT_SUCCESS | __NET_XMIT_STOLEN; + case TC_ACT_SHOT: + return false; + } +#endif + *salt = TC_H_MIN(res.classid); + return true; + } + return false; +} + +static int sfb_enqueue(struct sk_buff *skb, struct Qdisc *sch) +{ + + struct sfb_sched_data *q = qdisc_priv(sch); + struct Qdisc *child = q->qdisc; + int i; + u32 p_min = ~0; + u32 minqlen = ~0; + u32 r, slot, salt, sfbhash; + int ret = NET_XMIT_SUCCESS | __NET_XMIT_BYPASS; + + if (q->rehash_interval > 0) { + unsigned long limit = q->rehash_time + q->rehash_interval; + + if (unlikely(time_after(jiffies, limit))) { + sfb_swap_slot(q); + q->rehash_time = jiffies; + } else if (unlikely(!q->double_buffering && q->warmup_time > 0 && + time_after(jiffies, limit - q->warmup_time))) { + q->double_buffering = true; + } + } + + if (q->filter_list) { + /* If using external classifiers, get result and record it. */ + if (!sfb_classify(skb, q, &ret, &salt)) + goto other_drop; + } else { + salt = skb_get_rxhash(skb); + } + + slot = q->slot; + + sfbhash = jhash_1word(salt, q->bins[slot].perturbation); + if (!sfbhash) + sfbhash = 1; + sfb_skb_cb(skb)->hashes[slot] = sfbhash; + + for (i = 0; i < SFB_LEVELS; i++) { + u32 hash = sfbhash & SFB_BUCKET_MASK; + struct sfb_bucket *b = &q->bins[slot].bins[i][hash]; + + sfbhash >>= SFB_BUCKET_SHIFT; + if (b->qlen == 0) + decrement_prob(b, q); + else if (b->qlen >= q->bin_size) + increment_prob(b, q); + if (minqlen > b->qlen) + minqlen = b->qlen; + if (p_min > b->p_mark) + p_min = b->p_mark; + } + + slot ^= 1; + sfb_skb_cb(skb)->hashes[slot] = 0; + + if (unlikely(minqlen >= q->max || sch->q.qlen >= q->limit)) { + sch->qstats.overlimits++; + if (minqlen >= q->max) + q->stats.bucketdrop++; + else + q->stats.queuedrop++; + goto drop; + } + + if (unlikely(p_min >= SFB_MAX_PROB)) { + /* Inelastic flow */ + if (q->double_buffering) { + sfbhash = jhash_1word(salt, q->bins[slot].perturbation); + if (!sfbhash) + sfbhash = 1; + sfb_skb_cb(skb)->hashes[slot] = sfbhash; + + for (i = 0; i < SFB_LEVELS; i++) { + u32 hash = sfbhash & SFB_BUCKET_MASK; + struct sfb_bucket *b = &q->bins[slot].bins[i][hash]; + + sfbhash >>= SFB_BUCKET_SHIFT; + if (b->qlen == 0) + decrement_prob(b, q); + else if (b->qlen >= q->bin_size) + increment_prob(b, q); + } + } + if (sfb_rate_limit(skb, q)) { + sch->qstats.overlimits++; + q->stats.penaltydrop++; + goto drop; + } + goto enqueue; + } + + r = net_random() & SFB_MAX_PROB; + + if (unlikely(r < p_min)) { + if (unlikely(p_min > SFB_MAX_PROB / 2)) { + /* If we're marking that many packets, then either + * this flow is unresponsive, or we're badly congested. + * In either case, we want to start dropping packets. + */ + if (r < (p_min - SFB_MAX_PROB / 2) * 2) { + q->stats.earlydrop++; + goto drop; + } + } + if (INET_ECN_set_ce(skb)) { + q->stats.marked++; + } else { + q->stats.earlydrop++; + goto drop; + } + } + +enqueue: + ret = qdisc_enqueue(skb, child); + if (likely(ret == NET_XMIT_SUCCESS)) { + sch->q.qlen++; + increment_qlen(skb, q); + } else if (net_xmit_drop_count(ret)) { + q->stats.childdrop++; + sch->qstats.drops++; + } + return ret; + +drop: + qdisc_drop(skb, sch); + return NET_XMIT_CN; +other_drop: + if (ret & __NET_XMIT_BYPASS) + sch->qstats.drops++; + kfree_skb(skb); + return ret; +} + +static struct sk_buff *sfb_dequeue(struct Qdisc *sch) +{ + struct sfb_sched_data *q = qdisc_priv(sch); + struct Qdisc *child = q->qdisc; + struct sk_buff *skb; + + skb = child->dequeue(q->qdisc); + + if (skb) { + qdisc_bstats_update(sch, skb); + sch->q.qlen--; + decrement_qlen(skb, q); + } + + return skb; +} + +static struct sk_buff *sfb_peek(struct Qdisc *sch) +{ + struct sfb_sched_data *q = qdisc_priv(sch); + struct Qdisc *child = q->qdisc; + + return child->ops->peek(child); +} + +/* No sfb_drop -- impossible since the child doesn't return the dropped skb. */ + +static void sfb_reset(struct Qdisc *sch) +{ + struct sfb_sched_data *q = qdisc_priv(sch); + + qdisc_reset(q->qdisc); + sch->q.qlen = 0; + q->slot = 0; + q->double_buffering = false; + sfb_zero_all_buckets(q); + sfb_init_perturbation(0, q); +} + +static void sfb_destroy(struct Qdisc *sch) +{ + struct sfb_sched_data *q = qdisc_priv(sch); + + tcf_destroy_chain(&q->filter_list); + qdisc_destroy(q->qdisc); +} + +static const struct nla_policy sfb_policy[TCA_SFB_MAX + 1] = { + [TCA_SFB_PARMS] = { .len = sizeof(struct tc_sfb_qopt) }, +}; + +static const struct tc_sfb_qopt sfb_default_ops = { + .rehash_interval = 600 * MSEC_PER_SEC, + .warmup_time = 60 * MSEC_PER_SEC, + .limit = 0, + .max = 25, + .bin_size = 20, + .increment = (SFB_MAX_PROB + 500) / 1000, /* 0.1 % */ + .decrement = (SFB_MAX_PROB + 3000) / 6000, + .penalty_rate = 10, + .penalty_burst = 20, +}; + +static int sfb_change(struct Qdisc *sch, struct nlattr *opt) +{ + struct sfb_sched_data *q = qdisc_priv(sch); + struct Qdisc *child; + struct nlattr *tb[TCA_SFB_MAX + 1]; + const struct tc_sfb_qopt *ctl = &sfb_default_ops; + u32 limit; + int err; + + if (opt) { + err = nla_parse_nested(tb, TCA_SFB_MAX, opt, sfb_policy); + if (err < 0) + return -EINVAL; + + if (tb[TCA_SFB_PARMS] == NULL) + return -EINVAL; + + ctl = nla_data(tb[TCA_SFB_PARMS]); + } + + limit = ctl->limit; + if (limit == 0) + limit = max_t(u32, qdisc_dev(sch)->tx_queue_len, 1); + + child = fifo_create_dflt(sch, &pfifo_qdisc_ops, limit); + if (IS_ERR(child)) + return PTR_ERR(child); + + sch_tree_lock(sch); + + qdisc_tree_decrease_qlen(q->qdisc, q->qdisc->q.qlen); + qdisc_destroy(q->qdisc); + q->qdisc = child; + + q->rehash_interval = msecs_to_jiffies(ctl->rehash_interval); + q->warmup_time = msecs_to_jiffies(ctl->warmup_time); + q->rehash_time = jiffies; + q->limit = limit; + q->increment = ctl->increment; + q->decrement = ctl->decrement; + q->max = ctl->max; + q->bin_size = ctl->bin_size; + q->penalty_rate = ctl->penalty_rate; + q->penalty_burst = ctl->penalty_burst; + q->tokens_avail = ctl->penalty_burst; + q->token_time = jiffies; + + q->slot = 0; + q->double_buffering = false; + sfb_zero_all_buckets(q); + sfb_init_perturbation(0, q); + sfb_init_perturbation(1, q); + + sch_tree_unlock(sch); + + return 0; +} + +static int sfb_init(struct Qdisc *sch, struct nlattr *opt) +{ + struct sfb_sched_data *q = qdisc_priv(sch); + + q->qdisc = &noop_qdisc; + return sfb_change(sch, opt); +} + +static int sfb_dump(struct Qdisc *sch, struct sk_buff *skb) +{ + struct sfb_sched_data *q = qdisc_priv(sch); + struct nlattr *opts; + struct tc_sfb_qopt opt = { + .rehash_interval = jiffies_to_msecs(q->rehash_interval), + .warmup_time = jiffies_to_msecs(q->warmup_time), + .limit = q->limit, + .max = q->max, + .bin_size = q->bin_size, + .increment = q->increment, + .decrement = q->decrement, + .penalty_rate = q->penalty_rate, + .penalty_burst = q->penalty_burst, + }; + + sch->qstats.backlog = q->qdisc->qstats.backlog; + opts = nla_nest_start(skb, TCA_OPTIONS); + NLA_PUT(skb, TCA_SFB_PARMS, sizeof(opt), &opt); + return nla_nest_end(skb, opts); + +nla_put_failure: + nla_nest_cancel(skb, opts); + return -EMSGSIZE; +} + +static int sfb_dump_stats(struct Qdisc *sch, struct gnet_dump *d) +{ + struct sfb_sched_data *q = qdisc_priv(sch); + struct tc_sfb_xstats st = { + .earlydrop = q->stats.earlydrop, + .penaltydrop = q->stats.penaltydrop, + .bucketdrop = q->stats.bucketdrop, + .queuedrop = q->stats.queuedrop, + .childdrop = q->stats.childdrop, + .marked = q->stats.marked, + }; + + st.maxqlen = sfb_compute_qlen(&st.maxprob, &st.avgprob, q); + + return gnet_stats_copy_app(d, &st, sizeof(st)); +} + +static int sfb_dump_class(struct Qdisc *sch, unsigned long cl, + struct sk_buff *skb, struct tcmsg *tcm) +{ + return -ENOSYS; +} + +static int sfb_graft(struct Qdisc *sch, unsigned long arg, struct Qdisc *new, + struct Qdisc **old) +{ + struct sfb_sched_data *q = qdisc_priv(sch); + + if (new == NULL) + new = &noop_qdisc; + + sch_tree_lock(sch); + *old = q->qdisc; + q->qdisc = new; + qdisc_tree_decrease_qlen(*old, (*old)->q.qlen); + qdisc_reset(*old); + sch_tree_unlock(sch); + return 0; +} + +static struct Qdisc *sfb_leaf(struct Qdisc *sch, unsigned long arg) +{ + struct sfb_sched_data *q = qdisc_priv(sch); + + return q->qdisc; +} + +static unsigned long sfb_get(struct Qdisc *sch, u32 classid) +{ + return 1; +} + +static void sfb_put(struct Qdisc *sch, unsigned long arg) +{ +} + +static int sfb_change_class(struct Qdisc *sch, u32 classid, u32 parentid, + struct nlattr **tca, unsigned long *arg) +{ + return -ENOSYS; +} + +static int sfb_delete(struct Qdisc *sch, unsigned long cl) +{ + return -ENOSYS; +} + +static void sfb_walk(struct Qdisc *sch, struct qdisc_walker *walker) +{ + if (!walker->stop) { + if (walker->count >= walker->skip) + if (walker->fn(sch, 1, walker) < 0) { + walker->stop = 1; + return; + } + walker->count++; + } +} + +static struct tcf_proto **sfb_find_tcf(struct Qdisc *sch, unsigned long cl) +{ + struct sfb_sched_data *q = qdisc_priv(sch); + + if (cl) + return NULL; + return &q->filter_list; +} + +static unsigned long sfb_bind(struct Qdisc *sch, unsigned long parent, + u32 classid) +{ + return 0; +} + + +static const struct Qdisc_class_ops sfb_class_ops = { + .graft = sfb_graft, + .leaf = sfb_leaf, + .get = sfb_get, + .put = sfb_put, + .change = sfb_change_class, + .delete = sfb_delete, + .walk = sfb_walk, + .tcf_chain = sfb_find_tcf, + .bind_tcf = sfb_bind, + .unbind_tcf = sfb_put, + .dump = sfb_dump_class, +}; + +static struct Qdisc_ops sfb_qdisc_ops __read_mostly = { + .id = "sfb", + .priv_size = sizeof(struct sfb_sched_data), + .cl_ops = &sfb_class_ops, + .enqueue = sfb_enqueue, + .dequeue = sfb_dequeue, + .peek = sfb_peek, + .init = sfb_init, + .reset = sfb_reset, + .destroy = sfb_destroy, + .change = sfb_change, + .dump = sfb_dump, + .dump_stats = sfb_dump_stats, + .owner = THIS_MODULE, +}; + +static int __init sfb_module_init(void) +{ + return register_qdisc(&sfb_qdisc_ops); +} + +static void __exit sfb_module_exit(void) +{ + unregister_qdisc(&sfb_qdisc_ops); +} + +module_init(sfb_module_init) +module_exit(sfb_module_exit) + +MODULE_DESCRIPTION("Stochastic Fair Blue queue discipline"); +MODULE_AUTHOR("Juliusz Chroboczek"); +MODULE_AUTHOR("Eric Dumazet"); +MODULE_LICENSE("GPL"); diff --git a/net/sched/sch_sfq.c b/net/sched/sch_sfq.c index edea8cefec6..c2e628dfaac 100644 --- a/net/sched/sch_sfq.c +++ b/net/sched/sch_sfq.c @@ -21,6 +21,7 @@ #include <linux/skbuff.h> #include <linux/jhash.h> #include <linux/slab.h> +#include <linux/vmalloc.h> #include <net/ip.h> #include <net/netlink.h> #include <net/pkt_sched.h> @@ -76,7 +77,8 @@ #define SFQ_DEPTH 128 /* max number of packets per flow */ #define SFQ_SLOTS 128 /* max number of flows */ #define SFQ_EMPTY_SLOT 255 -#define SFQ_HASH_DIVISOR 1024 +#define SFQ_DEFAULT_HASH_DIVISOR 1024 + /* We use 16 bits to store allot, and want to handle packets up to 64K * Scale allot by 8 (1<<3) so that no overflow occurs. */ @@ -92,8 +94,7 @@ typedef unsigned char sfq_index; * while following values [SFQ_SLOTS ... SFQ_SLOTS + SFQ_DEPTH - 1] * are 'pointers' to dep[] array */ -struct sfq_head -{ +struct sfq_head { sfq_index next; sfq_index prev; }; @@ -108,13 +109,12 @@ struct sfq_slot { short allot; /* credit for this slot */ }; -struct sfq_sched_data -{ +struct sfq_sched_data { /* Parameters */ int perturb_period; - unsigned quantum; /* Allotment per round: MUST BE >= MTU */ + unsigned int quantum; /* Allotment per round: MUST BE >= MTU */ int limit; - + unsigned int divisor; /* number of slots in hash table */ /* Variables */ struct tcf_proto *filter_list; struct timer_list perturb_timer; @@ -122,7 +122,7 @@ struct sfq_sched_data sfq_index cur_depth; /* depth of longest slot */ unsigned short scaled_quantum; /* SFQ_ALLOT_SIZE(quantum) */ struct sfq_slot *tail; /* current slot in round */ - sfq_index ht[SFQ_HASH_DIVISOR]; /* Hash table */ + sfq_index *ht; /* Hash table (divisor slots) */ struct sfq_slot slots[SFQ_SLOTS]; struct sfq_head dep[SFQ_DEPTH]; /* Linked list of slots, indexed by depth */ }; @@ -137,12 +137,12 @@ static inline struct sfq_head *sfq_dep_head(struct sfq_sched_data *q, sfq_index return &q->dep[val - SFQ_SLOTS]; } -static __inline__ unsigned sfq_fold_hash(struct sfq_sched_data *q, u32 h, u32 h1) +static unsigned int sfq_fold_hash(struct sfq_sched_data *q, u32 h, u32 h1) { - return jhash_2words(h, h1, q->perturbation) & (SFQ_HASH_DIVISOR - 1); + return jhash_2words(h, h1, q->perturbation) & (q->divisor - 1); } -static unsigned sfq_hash(struct sfq_sched_data *q, struct sk_buff *skb) +static unsigned int sfq_hash(struct sfq_sched_data *q, struct sk_buff *skb) { u32 h, h2; @@ -157,13 +157,13 @@ static unsigned sfq_hash(struct sfq_sched_data *q, struct sk_buff *skb) iph = ip_hdr(skb); h = (__force u32)iph->daddr; h2 = (__force u32)iph->saddr ^ iph->protocol; - if (iph->frag_off & htons(IP_MF|IP_OFFSET)) + if (iph->frag_off & htons(IP_MF | IP_OFFSET)) break; poff = proto_ports_offset(iph->protocol); if (poff >= 0 && pskb_network_may_pull(skb, iph->ihl * 4 + 4 + poff)) { iph = ip_hdr(skb); - h2 ^= *(u32*)((void *)iph + iph->ihl * 4 + poff); + h2 ^= *(u32 *)((void *)iph + iph->ihl * 4 + poff); } break; } @@ -181,7 +181,7 @@ static unsigned sfq_hash(struct sfq_sched_data *q, struct sk_buff *skb) if (poff >= 0 && pskb_network_may_pull(skb, sizeof(*iph) + 4 + poff)) { iph = ipv6_hdr(skb); - h2 ^= *(u32*)((void *)iph + sizeof(*iph) + poff); + h2 ^= *(u32 *)((void *)iph + sizeof(*iph) + poff); } break; } @@ -203,7 +203,7 @@ static unsigned int sfq_classify(struct sk_buff *skb, struct Qdisc *sch, if (TC_H_MAJ(skb->priority) == sch->handle && TC_H_MIN(skb->priority) > 0 && - TC_H_MIN(skb->priority) <= SFQ_HASH_DIVISOR) + TC_H_MIN(skb->priority) <= q->divisor) return TC_H_MIN(skb->priority); if (!q->filter_list) @@ -221,7 +221,7 @@ static unsigned int sfq_classify(struct sk_buff *skb, struct Qdisc *sch, return 0; } #endif - if (TC_H_MIN(res.classid) <= SFQ_HASH_DIVISOR) + if (TC_H_MIN(res.classid) <= q->divisor) return TC_H_MIN(res.classid); } return 0; @@ -491,13 +491,18 @@ static int sfq_change(struct Qdisc *sch, struct nlattr *opt) if (opt->nla_len < nla_attr_size(sizeof(*ctl))) return -EINVAL; + if (ctl->divisor && + (!is_power_of_2(ctl->divisor) || ctl->divisor > 65536)) + return -EINVAL; + sch_tree_lock(sch); q->quantum = ctl->quantum ? : psched_mtu(qdisc_dev(sch)); q->scaled_quantum = SFQ_ALLOT_SIZE(q->quantum); q->perturb_period = ctl->perturb_period * HZ; if (ctl->limit) q->limit = min_t(u32, ctl->limit, SFQ_DEPTH - 1); - + if (ctl->divisor) + q->divisor = ctl->divisor; qlen = sch->q.qlen; while (sch->q.qlen > q->limit) sfq_drop(sch); @@ -515,15 +520,13 @@ static int sfq_change(struct Qdisc *sch, struct nlattr *opt) static int sfq_init(struct Qdisc *sch, struct nlattr *opt) { struct sfq_sched_data *q = qdisc_priv(sch); + size_t sz; int i; q->perturb_timer.function = sfq_perturbation; q->perturb_timer.data = (unsigned long)sch; init_timer_deferrable(&q->perturb_timer); - for (i = 0; i < SFQ_HASH_DIVISOR; i++) - q->ht[i] = SFQ_EMPTY_SLOT; - for (i = 0; i < SFQ_DEPTH; i++) { q->dep[i].next = i + SFQ_SLOTS; q->dep[i].prev = i + SFQ_SLOTS; @@ -532,6 +535,7 @@ static int sfq_init(struct Qdisc *sch, struct nlattr *opt) q->limit = SFQ_DEPTH - 1; q->cur_depth = 0; q->tail = NULL; + q->divisor = SFQ_DEFAULT_HASH_DIVISOR; if (opt == NULL) { q->quantum = psched_mtu(qdisc_dev(sch)); q->scaled_quantum = SFQ_ALLOT_SIZE(q->quantum); @@ -543,10 +547,23 @@ static int sfq_init(struct Qdisc *sch, struct nlattr *opt) return err; } + sz = sizeof(q->ht[0]) * q->divisor; + q->ht = kmalloc(sz, GFP_KERNEL); + if (!q->ht && sz > PAGE_SIZE) + q->ht = vmalloc(sz); + if (!q->ht) + return -ENOMEM; + for (i = 0; i < q->divisor; i++) + q->ht[i] = SFQ_EMPTY_SLOT; + for (i = 0; i < SFQ_SLOTS; i++) { slot_queue_init(&q->slots[i]); sfq_link(q, i); } + if (q->limit >= 1) + sch->flags |= TCQ_F_CAN_BYPASS; + else + sch->flags &= ~TCQ_F_CAN_BYPASS; return 0; } @@ -557,6 +574,10 @@ static void sfq_destroy(struct Qdisc *sch) tcf_destroy_chain(&q->filter_list); q->perturb_period = 0; del_timer_sync(&q->perturb_timer); + if (is_vmalloc_addr(q->ht)) + vfree(q->ht); + else + kfree(q->ht); } static int sfq_dump(struct Qdisc *sch, struct sk_buff *skb) @@ -569,7 +590,7 @@ static int sfq_dump(struct Qdisc *sch, struct sk_buff *skb) opt.perturb_period = q->perturb_period / HZ; opt.limit = q->limit; - opt.divisor = SFQ_HASH_DIVISOR; + opt.divisor = q->divisor; opt.flows = q->limit; NLA_PUT(skb, TCA_OPTIONS, sizeof(opt), &opt); @@ -594,6 +615,8 @@ static unsigned long sfq_get(struct Qdisc *sch, u32 classid) static unsigned long sfq_bind(struct Qdisc *sch, unsigned long parent, u32 classid) { + /* we cannot bypass queue discipline anymore */ + sch->flags &= ~TCQ_F_CAN_BYPASS; return 0; } @@ -647,7 +670,7 @@ static void sfq_walk(struct Qdisc *sch, struct qdisc_walker *arg) if (arg->stop) return; - for (i = 0; i < SFQ_HASH_DIVISOR; i++) { + for (i = 0; i < q->divisor; i++) { if (q->ht[i] == SFQ_EMPTY_SLOT || arg->count < arg->skip) { arg->count++; diff --git a/net/sched/sch_tbf.c b/net/sched/sch_tbf.c index e93165820c3..1dcfb5223a8 100644 --- a/net/sched/sch_tbf.c +++ b/net/sched/sch_tbf.c @@ -97,8 +97,7 @@ changed the limit is not effective anymore. */ -struct tbf_sched_data -{ +struct tbf_sched_data { /* Parameters */ u32 limit; /* Maximal length of backlog: bytes */ u32 buffer; /* Token bucket depth/rate: MUST BE >= MTU/B */ @@ -115,10 +114,10 @@ struct tbf_sched_data struct qdisc_watchdog watchdog; /* Watchdog timer */ }; -#define L2T(q,L) qdisc_l2t((q)->R_tab,L) -#define L2T_P(q,L) qdisc_l2t((q)->P_tab,L) +#define L2T(q, L) qdisc_l2t((q)->R_tab, L) +#define L2T_P(q, L) qdisc_l2t((q)->P_tab, L) -static int tbf_enqueue(struct sk_buff *skb, struct Qdisc* sch) +static int tbf_enqueue(struct sk_buff *skb, struct Qdisc *sch) { struct tbf_sched_data *q = qdisc_priv(sch); int ret; @@ -137,7 +136,7 @@ static int tbf_enqueue(struct sk_buff *skb, struct Qdisc* sch) return NET_XMIT_SUCCESS; } -static unsigned int tbf_drop(struct Qdisc* sch) +static unsigned int tbf_drop(struct Qdisc *sch) { struct tbf_sched_data *q = qdisc_priv(sch); unsigned int len = 0; @@ -149,7 +148,7 @@ static unsigned int tbf_drop(struct Qdisc* sch) return len; } -static struct sk_buff *tbf_dequeue(struct Qdisc* sch) +static struct sk_buff *tbf_dequeue(struct Qdisc *sch) { struct tbf_sched_data *q = qdisc_priv(sch); struct sk_buff *skb; @@ -185,7 +184,7 @@ static struct sk_buff *tbf_dequeue(struct Qdisc* sch) q->tokens = toks; q->ptokens = ptoks; sch->q.qlen--; - sch->flags &= ~TCQ_F_THROTTLED; + qdisc_unthrottled(sch); qdisc_bstats_update(sch, skb); return skb; } @@ -209,7 +208,7 @@ static struct sk_buff *tbf_dequeue(struct Qdisc* sch) return NULL; } -static void tbf_reset(struct Qdisc* sch) +static void tbf_reset(struct Qdisc *sch) { struct tbf_sched_data *q = qdisc_priv(sch); @@ -227,7 +226,7 @@ static const struct nla_policy tbf_policy[TCA_TBF_MAX + 1] = { [TCA_TBF_PTAB] = { .type = NLA_BINARY, .len = TC_RTAB_SIZE }, }; -static int tbf_change(struct Qdisc* sch, struct nlattr *opt) +static int tbf_change(struct Qdisc *sch, struct nlattr *opt) { int err; struct tbf_sched_data *q = qdisc_priv(sch); @@ -236,7 +235,7 @@ static int tbf_change(struct Qdisc* sch, struct nlattr *opt) struct qdisc_rate_table *rtab = NULL; struct qdisc_rate_table *ptab = NULL; struct Qdisc *child = NULL; - int max_size,n; + int max_size, n; err = nla_parse_nested(tb, TCA_TBF_PTAB, opt, tbf_policy); if (err < 0) @@ -259,15 +258,18 @@ static int tbf_change(struct Qdisc* sch, struct nlattr *opt) } for (n = 0; n < 256; n++) - if (rtab->data[n] > qopt->buffer) break; - max_size = (n << qopt->rate.cell_log)-1; + if (rtab->data[n] > qopt->buffer) + break; + max_size = (n << qopt->rate.cell_log) - 1; if (ptab) { int size; for (n = 0; n < 256; n++) - if (ptab->data[n] > qopt->mtu) break; - size = (n << qopt->peakrate.cell_log)-1; - if (size < max_size) max_size = size; + if (ptab->data[n] > qopt->mtu) + break; + size = (n << qopt->peakrate.cell_log) - 1; + if (size < max_size) + max_size = size; } if (max_size < 0) goto done; @@ -310,7 +312,7 @@ done: return err; } -static int tbf_init(struct Qdisc* sch, struct nlattr *opt) +static int tbf_init(struct Qdisc *sch, struct nlattr *opt) { struct tbf_sched_data *q = qdisc_priv(sch); @@ -422,8 +424,7 @@ static void tbf_walk(struct Qdisc *sch, struct qdisc_walker *walker) } } -static const struct Qdisc_class_ops tbf_class_ops = -{ +static const struct Qdisc_class_ops tbf_class_ops = { .graft = tbf_graft, .leaf = tbf_leaf, .get = tbf_get, diff --git a/net/sched/sch_teql.c b/net/sched/sch_teql.c index d84e7329660..45cd30098e3 100644 --- a/net/sched/sch_teql.c +++ b/net/sched/sch_teql.c @@ -53,8 +53,7 @@ which will not break load balancing, though native slave traffic will have the highest priority. */ -struct teql_master -{ +struct teql_master { struct Qdisc_ops qops; struct net_device *dev; struct Qdisc *slaves; @@ -65,22 +64,21 @@ struct teql_master unsigned long tx_dropped; }; -struct teql_sched_data -{ +struct teql_sched_data { struct Qdisc *next; struct teql_master *m; struct neighbour *ncache; struct sk_buff_head q; }; -#define NEXT_SLAVE(q) (((struct teql_sched_data*)qdisc_priv(q))->next) +#define NEXT_SLAVE(q) (((struct teql_sched_data *)qdisc_priv(q))->next) -#define FMASK (IFF_BROADCAST|IFF_POINTOPOINT) +#define FMASK (IFF_BROADCAST | IFF_POINTOPOINT) /* "teql*" qdisc routines */ static int -teql_enqueue(struct sk_buff *skb, struct Qdisc* sch) +teql_enqueue(struct sk_buff *skb, struct Qdisc *sch) { struct net_device *dev = qdisc_dev(sch); struct teql_sched_data *q = qdisc_priv(sch); @@ -96,7 +94,7 @@ teql_enqueue(struct sk_buff *skb, struct Qdisc* sch) } static struct sk_buff * -teql_dequeue(struct Qdisc* sch) +teql_dequeue(struct Qdisc *sch) { struct teql_sched_data *dat = qdisc_priv(sch); struct netdev_queue *dat_queue; @@ -118,13 +116,13 @@ teql_dequeue(struct Qdisc* sch) } static struct sk_buff * -teql_peek(struct Qdisc* sch) +teql_peek(struct Qdisc *sch) { /* teql is meant to be used as root qdisc */ return NULL; } -static __inline__ void +static inline void teql_neigh_release(struct neighbour *n) { if (n) @@ -132,7 +130,7 @@ teql_neigh_release(struct neighbour *n) } static void -teql_reset(struct Qdisc* sch) +teql_reset(struct Qdisc *sch) { struct teql_sched_data *dat = qdisc_priv(sch); @@ -142,13 +140,14 @@ teql_reset(struct Qdisc* sch) } static void -teql_destroy(struct Qdisc* sch) +teql_destroy(struct Qdisc *sch) { struct Qdisc *q, *prev; struct teql_sched_data *dat = qdisc_priv(sch); struct teql_master *master = dat->m; - if ((prev = master->slaves) != NULL) { + prev = master->slaves; + if (prev) { do { q = NEXT_SLAVE(prev); if (q == sch) { @@ -180,7 +179,7 @@ teql_destroy(struct Qdisc* sch) static int teql_qdisc_init(struct Qdisc *sch, struct nlattr *opt) { struct net_device *dev = qdisc_dev(sch); - struct teql_master *m = (struct teql_master*)sch->ops; + struct teql_master *m = (struct teql_master *)sch->ops; struct teql_sched_data *q = qdisc_priv(sch); if (dev->hard_header_len > m->dev->hard_header_len) @@ -291,7 +290,8 @@ restart: nores = 0; busy = 0; - if ((q = start) == NULL) + q = start; + if (!q) goto drop; do { @@ -356,10 +356,10 @@ drop: static int teql_master_open(struct net_device *dev) { - struct Qdisc * q; + struct Qdisc *q; struct teql_master *m = netdev_priv(dev); int mtu = 0xFFFE; - unsigned flags = IFF_NOARP|IFF_MULTICAST; + unsigned int flags = IFF_NOARP | IFF_MULTICAST; if (m->slaves == NULL) return -EUNATCH; @@ -427,7 +427,7 @@ static int teql_master_mtu(struct net_device *dev, int new_mtu) do { if (new_mtu > qdisc_dev(q)->mtu) return -EINVAL; - } while ((q=NEXT_SLAVE(q)) != m->slaves); + } while ((q = NEXT_SLAVE(q)) != m->slaves); } dev->mtu = new_mtu; |