diff options
Diffstat (limited to 'net/sched')
40 files changed, 714 insertions, 1235 deletions
diff --git a/net/sched/Kconfig b/net/sched/Kconfig index 475df8449be9..8a74cac0be8c 100644 --- a/net/sched/Kconfig +++ b/net/sched/Kconfig @@ -97,7 +97,7 @@ config NET_SCH_ATM select classes of this queuing discipline. Each class maps the flow(s) it is handling to a given virtual circuit. - See the top of <file:net/sched/sch_atm.c>) for more details. + See the top of <file:net/sched/sch_atm.c> for more details. To compile this code as a module, choose M here: the module will be called sch_atm. @@ -111,6 +111,17 @@ config NET_SCH_PRIO To compile this code as a module, choose M here: the module will be called sch_prio. +config NET_SCH_RR + tristate "Multi Band Round Robin Queuing (RR)" + select NET_SCH_PRIO + ---help--- + Say Y here if you want to use an n-band round robin packet + scheduler. + + The module uses sch_prio for its framework and is aliased as + sch_rr, so it will load sch_prio, although it is referred + to using sch_rr. + config NET_SCH_RED tristate "Random Early Detection (RED)" ---help--- @@ -126,7 +137,7 @@ config NET_SCH_SFQ tristate "Stochastic Fairness Queueing (SFQ)" ---help--- Say Y here if you want to use the Stochastic Fairness Queueing (SFQ) - packet scheduling algorithm . + packet scheduling algorithm. See the top of <file:net/sched/sch_sfq.c> for more details. @@ -275,7 +286,6 @@ config CLS_U32_MARK config NET_CLS_RSVP tristate "IPv4 Resource Reservation Protocol (RSVP)" select NET_CLS - select NET_ESTIMATOR ---help--- The Resource Reservation Protocol (RSVP) permits end systems to request a minimum and maximum data flow rate for a connection; this @@ -290,14 +300,13 @@ config NET_CLS_RSVP config NET_CLS_RSVP6 tristate "IPv6 Resource Reservation Protocol (RSVP6)" select NET_CLS - select NET_ESTIMATOR ---help--- The Resource Reservation Protocol (RSVP) permits end systems to request a minimum and maximum data flow rate for a connection; this is important for real time data such as streaming sound or video. Say Y here if you want to be able to classify outgoing packets based - on their RSVP requests and you are using the IPv6. + on their RSVP requests and you are using the IPv6 protocol. To compile this code as a module, choose M here: the module will be called cls_rsvp6. @@ -382,7 +391,6 @@ config NET_EMATCH_TEXT config NET_CLS_ACT bool "Actions" - select NET_ESTIMATOR ---help--- Say Y here if you want to use traffic control actions. Actions get attached to classifiers and are invoked after a successful @@ -464,13 +472,12 @@ config NET_ACT_SIMP config NET_CLS_POLICE bool "Traffic Policing (obsolete)" - depends on NET_CLS_ACT!=y - select NET_ESTIMATOR + select NET_CLS_ACT + select NET_ACT_POLICE ---help--- Say Y here if you want to do traffic policing, i.e. strict - bandwidth limiting. This option is obsoleted by the traffic - policer implemented as action, it stays here for compatibility - reasons. + bandwidth limiting. This option is obsolete and just selects + the option replacing it. It will be removed in the future. config NET_CLS_IND bool "Incoming device classification" @@ -480,14 +487,6 @@ config NET_CLS_IND classification based on the incoming device. This option is likely to disappear in favour of the metadata ematch. -config NET_ESTIMATOR - bool "Rate estimator" - ---help--- - Say Y here to allow using rate estimators to estimate the current - rate-of-flow for network devices, queues, etc. This module is - automatically selected if needed but can be selected manually for - statistical purposes. - endif # NET_SCHED endmenu diff --git a/net/sched/Makefile b/net/sched/Makefile index 020767a204d4..b67c36f65cf2 100644 --- a/net/sched/Makefile +++ b/net/sched/Makefile @@ -8,7 +8,6 @@ obj-$(CONFIG_NET_SCHED) += sch_api.o sch_blackhole.o obj-$(CONFIG_NET_CLS) += cls_api.o obj-$(CONFIG_NET_CLS_ACT) += act_api.o obj-$(CONFIG_NET_ACT_POLICE) += act_police.o -obj-$(CONFIG_NET_CLS_POLICE) += act_police.o obj-$(CONFIG_NET_ACT_GACT) += act_gact.o obj-$(CONFIG_NET_ACT_MIRRED) += act_mirred.o obj-$(CONFIG_NET_ACT_IPT) += act_ipt.o diff --git a/net/sched/act_api.c b/net/sched/act_api.c index 711dd26c95c3..72cdb0fade20 100644 --- a/net/sched/act_api.c +++ b/net/sched/act_api.c @@ -11,23 +11,13 @@ * */ -#include <asm/uaccess.h> -#include <asm/system.h> -#include <linux/bitops.h> #include <linux/types.h> #include <linux/kernel.h> #include <linux/string.h> -#include <linux/mm.h> -#include <linux/socket.h> -#include <linux/sockios.h> -#include <linux/in.h> #include <linux/errno.h> -#include <linux/interrupt.h> -#include <linux/netdevice.h> #include <linux/skbuff.h> #include <linux/init.h> #include <linux/kmod.h> -#include <net/sock.h> #include <net/sch_generic.h> #include <net/act_api.h> #include <net/netlink.h> @@ -42,10 +32,8 @@ void tcf_hash_destroy(struct tcf_common *p, struct tcf_hashinfo *hinfo) write_lock_bh(hinfo->lock); *p1p = p->tcfc_next; write_unlock_bh(hinfo->lock); -#ifdef CONFIG_NET_ESTIMATOR gen_kill_estimator(&p->tcfc_bstats, &p->tcfc_rate_est); -#endif kfree(p); return; } @@ -80,7 +68,7 @@ static int tcf_dump_walker(struct sk_buff *skb, struct netlink_callback *cb, int err = 0, index = -1,i = 0, s_i = 0, n_i = 0; struct rtattr *r ; - read_lock(hinfo->lock); + read_lock_bh(hinfo->lock); s_i = cb->args[0]; @@ -108,7 +96,7 @@ static int tcf_dump_walker(struct sk_buff *skb, struct netlink_callback *cb, } } done: - read_unlock(hinfo->lock); + read_unlock_bh(hinfo->lock); if (n_i) cb->args[0] += n_i; return n_i; @@ -168,13 +156,13 @@ struct tcf_common *tcf_hash_lookup(u32 index, struct tcf_hashinfo *hinfo) { struct tcf_common *p; - read_lock(hinfo->lock); + read_lock_bh(hinfo->lock); for (p = hinfo->htab[tcf_hash(index, hinfo->hmask)]; p; p = p->tcfc_next) { if (p->tcfc_index == index) break; } - read_unlock(hinfo->lock); + read_unlock_bh(hinfo->lock); return p; } @@ -232,15 +220,12 @@ struct tcf_common *tcf_hash_create(u32 index, struct rtattr *est, struct tc_acti p->tcfc_bindcnt = 1; spin_lock_init(&p->tcfc_lock); - p->tcfc_stats_lock = &p->tcfc_lock; p->tcfc_index = index ? index : tcf_hash_new_index(idx_gen, hinfo); p->tcfc_tm.install = jiffies; p->tcfc_tm.lastuse = jiffies; -#ifdef CONFIG_NET_ESTIMATOR if (est) gen_new_estimator(&p->tcfc_bstats, &p->tcfc_rate_est, - p->tcfc_stats_lock, est); -#endif + &p->tcfc_lock, est); a->priv = (void *) p; return p; } @@ -599,12 +584,12 @@ int tcf_action_copy_stats(struct sk_buff *skb, struct tc_action *a, if (compat_mode) { if (a->type == TCA_OLD_COMPAT) err = gnet_stats_start_copy_compat(skb, 0, - TCA_STATS, TCA_XSTATS, h->tcf_stats_lock, &d); + TCA_STATS, TCA_XSTATS, &h->tcf_lock, &d); else return 0; } else err = gnet_stats_start_copy(skb, TCA_ACT_STATS, - h->tcf_stats_lock, &d); + &h->tcf_lock, &d); if (err < 0) goto errout; @@ -614,9 +599,7 @@ int tcf_action_copy_stats(struct sk_buff *skb, struct tc_action *a, goto errout; if (gnet_stats_copy_basic(&d, &h->tcf_bstats) < 0 || -#ifdef CONFIG_NET_ESTIMATOR gnet_stats_copy_rate_est(&d, &h->tcf_rate_est) < 0 || -#endif gnet_stats_copy_queue(&d, &h->tcf_qstats) < 0) goto errout; diff --git a/net/sched/act_gact.c b/net/sched/act_gact.c index 7517f3791541..a9631e426d91 100644 --- a/net/sched/act_gact.c +++ b/net/sched/act_gact.c @@ -10,26 +10,15 @@ * */ -#include <asm/uaccess.h> -#include <asm/system.h> -#include <linux/bitops.h> #include <linux/types.h> #include <linux/kernel.h> #include <linux/string.h> -#include <linux/mm.h> -#include <linux/socket.h> -#include <linux/sockios.h> -#include <linux/in.h> #include <linux/errno.h> -#include <linux/interrupt.h> -#include <linux/netdevice.h> #include <linux/skbuff.h> #include <linux/rtnetlink.h> #include <linux/module.h> #include <linux/init.h> -#include <linux/proc_fs.h> #include <net/netlink.h> -#include <net/sock.h> #include <net/pkt_sched.h> #include <linux/tc_act/tc_gact.h> #include <net/tc_act/tc_gact.h> diff --git a/net/sched/act_ipt.c b/net/sched/act_ipt.c index 00b05f422d45..6b407ece953c 100644 --- a/net/sched/act_ipt.c +++ b/net/sched/act_ipt.c @@ -11,27 +11,15 @@ * Copyright: Jamal Hadi Salim (2002-4) */ -#include <asm/uaccess.h> -#include <asm/system.h> -#include <asm/bitops.h> #include <linux/types.h> #include <linux/kernel.h> #include <linux/string.h> -#include <linux/mm.h> -#include <linux/socket.h> -#include <linux/sockios.h> -#include <linux/in.h> #include <linux/errno.h> -#include <linux/interrupt.h> -#include <linux/netdevice.h> #include <linux/skbuff.h> #include <linux/rtnetlink.h> #include <linux/module.h> #include <linux/init.h> -#include <linux/proc_fs.h> -#include <linux/kmod.h> #include <net/netlink.h> -#include <net/sock.h> #include <net/pkt_sched.h> #include <linux/tc_act/tc_ipt.h> #include <net/tc_act/tc_ipt.h> diff --git a/net/sched/act_mirred.c b/net/sched/act_mirred.c index de21c92faaa2..579578944ae7 100644 --- a/net/sched/act_mirred.c +++ b/net/sched/act_mirred.c @@ -12,31 +12,19 @@ * */ -#include <asm/uaccess.h> -#include <asm/system.h> -#include <asm/bitops.h> #include <linux/types.h> #include <linux/kernel.h> #include <linux/string.h> -#include <linux/mm.h> -#include <linux/socket.h> -#include <linux/sockios.h> -#include <linux/in.h> #include <linux/errno.h> -#include <linux/interrupt.h> -#include <linux/netdevice.h> #include <linux/skbuff.h> #include <linux/rtnetlink.h> #include <linux/module.h> #include <linux/init.h> -#include <linux/proc_fs.h> #include <net/netlink.h> -#include <net/sock.h> #include <net/pkt_sched.h> #include <linux/tc_act/tc_mirred.h> #include <net/tc_act/tc_mirred.h> -#include <linux/etherdevice.h> #include <linux/if_arp.h> #define MIRRED_TAB_MASK 7 diff --git a/net/sched/act_pedit.c b/net/sched/act_pedit.c index 6f8684b5617e..b46fab5fb323 100644 --- a/net/sched/act_pedit.c +++ b/net/sched/act_pedit.c @@ -9,26 +9,15 @@ * Authors: Jamal Hadi Salim (2002-4) */ -#include <asm/uaccess.h> -#include <asm/system.h> -#include <asm/bitops.h> #include <linux/types.h> #include <linux/kernel.h> #include <linux/string.h> -#include <linux/mm.h> -#include <linux/socket.h> -#include <linux/sockios.h> -#include <linux/in.h> #include <linux/errno.h> -#include <linux/interrupt.h> -#include <linux/netdevice.h> #include <linux/skbuff.h> #include <linux/rtnetlink.h> #include <linux/module.h> #include <linux/init.h> -#include <linux/proc_fs.h> #include <net/netlink.h> -#include <net/sock.h> #include <net/pkt_sched.h> #include <linux/tc_act/tc_pedit.h> #include <net/tc_act/tc_pedit.h> diff --git a/net/sched/act_police.c b/net/sched/act_police.c index 616f465f407e..17f6f27e28a2 100644 --- a/net/sched/act_police.c +++ b/net/sched/act_police.c @@ -10,25 +10,14 @@ * J Hadi Salim (action changes) */ -#include <asm/uaccess.h> -#include <asm/system.h> -#include <linux/bitops.h> #include <linux/module.h> #include <linux/types.h> #include <linux/kernel.h> #include <linux/string.h> -#include <linux/mm.h> -#include <linux/socket.h> -#include <linux/sockios.h> -#include <linux/in.h> #include <linux/errno.h> -#include <linux/interrupt.h> -#include <linux/netdevice.h> #include <linux/skbuff.h> -#include <linux/module.h> #include <linux/rtnetlink.h> #include <linux/init.h> -#include <net/sock.h> #include <net/act_api.h> #include <net/netlink.h> @@ -60,7 +49,6 @@ struct tc_police_compat /* Each policer is serialized by its individual spinlock */ -#ifdef CONFIG_NET_CLS_ACT static int tcf_act_police_walker(struct sk_buff *skb, struct netlink_callback *cb, int type, struct tc_action *a) { @@ -68,7 +56,7 @@ static int tcf_act_police_walker(struct sk_buff *skb, struct netlink_callback *c int err = 0, index = -1, i = 0, s_i = 0, n_i = 0; struct rtattr *r; - read_lock(&police_lock); + read_lock_bh(&police_lock); s_i = cb->args[0]; @@ -97,7 +85,7 @@ static int tcf_act_police_walker(struct sk_buff *skb, struct netlink_callback *c } } done: - read_unlock(&police_lock); + read_unlock_bh(&police_lock); if (n_i) cb->args[0] += n_i; return n_i; @@ -106,9 +94,8 @@ rtattr_failure: nlmsg_trim(skb, r); goto done; } -#endif -void tcf_police_destroy(struct tcf_police *p) +static void tcf_police_destroy(struct tcf_police *p) { unsigned int h = tcf_hash(p->tcf_index, POL_TAB_MASK); struct tcf_common **p1p; @@ -118,10 +105,8 @@ void tcf_police_destroy(struct tcf_police *p) write_lock_bh(&police_lock); *p1p = p->tcf_next; write_unlock_bh(&police_lock); -#ifdef CONFIG_NET_ESTIMATOR gen_kill_estimator(&p->tcf_bstats, &p->tcf_rate_est); -#endif if (p->tcfp_R_tab) qdisc_put_rtab(p->tcfp_R_tab); if (p->tcfp_P_tab) @@ -133,7 +118,6 @@ void tcf_police_destroy(struct tcf_police *p) BUG_TRAP(0); } -#ifdef CONFIG_NET_CLS_ACT static int tcf_act_police_locate(struct rtattr *rta, struct rtattr *est, struct tc_action *a, int ovr, int bind) { @@ -185,7 +169,6 @@ static int tcf_act_police_locate(struct rtattr *rta, struct rtattr *est, ret = ACT_P_CREATED; police->tcf_refcnt = 1; spin_lock_init(&police->tcf_lock); - police->tcf_stats_lock = &police->tcf_lock; if (bind) police->tcf_bindcnt = 1; override: @@ -227,15 +210,13 @@ override: police->tcfp_ptoks = L2T_P(police, police->tcfp_mtu); police->tcf_action = parm->action; -#ifdef CONFIG_NET_ESTIMATOR if (tb[TCA_POLICE_AVRATE-1]) police->tcfp_ewma_rate = *(u32*)RTA_DATA(tb[TCA_POLICE_AVRATE-1]); if (est) gen_replace_estimator(&police->tcf_bstats, &police->tcf_rate_est, - police->tcf_stats_lock, est); -#endif + &police->tcf_lock, est); spin_unlock_bh(&police->tcf_lock); if (ret != ACT_P_CREATED) @@ -262,10 +243,19 @@ failure: static int tcf_act_police_cleanup(struct tc_action *a, int bind) { struct tcf_police *p = a->priv; + int ret = 0; + + if (p != NULL) { + if (bind) + p->tcf_bindcnt--; - if (p != NULL) - return tcf_police_release(p, bind); - return 0; + p->tcf_refcnt--; + if (p->tcf_refcnt <= 0 && !p->tcf_bindcnt) { + tcf_police_destroy(p); + ret = 1; + } + } + return ret; } static int tcf_act_police(struct sk_buff *skb, struct tc_action *a, @@ -281,14 +271,12 @@ static int tcf_act_police(struct sk_buff *skb, struct tc_action *a, police->tcf_bstats.bytes += skb->len; police->tcf_bstats.packets++; -#ifdef CONFIG_NET_ESTIMATOR if (police->tcfp_ewma_rate && police->tcf_rate_est.bps >= police->tcfp_ewma_rate) { police->tcf_qstats.overlimits++; spin_unlock(&police->tcf_lock); return police->tcf_action; } -#endif if (skb->len <= police->tcfp_mtu) { if (police->tcfp_R_tab == NULL) { @@ -348,10 +336,8 @@ tcf_act_police_dump(struct sk_buff *skb, struct tc_action *a, int bind, int ref) if (police->tcfp_result) RTA_PUT(skb, TCA_POLICE_RESULT, sizeof(int), &police->tcfp_result); -#ifdef CONFIG_NET_ESTIMATOR if (police->tcfp_ewma_rate) RTA_PUT(skb, TCA_POLICE_AVRATE, 4, &police->tcfp_ewma_rate); -#endif return skb->len; rtattr_failure: @@ -391,240 +377,3 @@ police_cleanup_module(void) module_init(police_init_module); module_exit(police_cleanup_module); - -#else /* CONFIG_NET_CLS_ACT */ - -static struct tcf_common *tcf_police_lookup(u32 index) -{ - struct tcf_hashinfo *hinfo = &police_hash_info; - struct tcf_common *p; - - read_lock(hinfo->lock); - for (p = hinfo->htab[tcf_hash(index, hinfo->hmask)]; p; - p = p->tcfc_next) { - if (p->tcfc_index == index) - break; - } - read_unlock(hinfo->lock); - - return p; -} - -static u32 tcf_police_new_index(void) -{ - u32 *idx_gen = &police_idx_gen; - u32 val = *idx_gen; - - do { - if (++val == 0) - val = 1; - } while (tcf_police_lookup(val)); - - return (*idx_gen = val); -} - -struct tcf_police *tcf_police_locate(struct rtattr *rta, struct rtattr *est) -{ - unsigned int h; - struct tcf_police *police; - struct rtattr *tb[TCA_POLICE_MAX]; - struct tc_police *parm; - int size; - - if (rtattr_parse_nested(tb, TCA_POLICE_MAX, rta) < 0) - return NULL; - - if (tb[TCA_POLICE_TBF-1] == NULL) - return NULL; - size = RTA_PAYLOAD(tb[TCA_POLICE_TBF-1]); - if (size != sizeof(*parm) && size != sizeof(struct tc_police_compat)) - return NULL; - - parm = RTA_DATA(tb[TCA_POLICE_TBF-1]); - - if (parm->index) { - struct tcf_common *pc; - - pc = tcf_police_lookup(parm->index); - if (pc) { - police = to_police(pc); - police->tcf_refcnt++; - return police; - } - } - police = kzalloc(sizeof(*police), GFP_KERNEL); - if (unlikely(!police)) - return NULL; - - police->tcf_refcnt = 1; - spin_lock_init(&police->tcf_lock); - police->tcf_stats_lock = &police->tcf_lock; - if (parm->rate.rate) { - police->tcfp_R_tab = - qdisc_get_rtab(&parm->rate, tb[TCA_POLICE_RATE-1]); - if (police->tcfp_R_tab == NULL) - goto failure; - if (parm->peakrate.rate) { - police->tcfp_P_tab = - qdisc_get_rtab(&parm->peakrate, - tb[TCA_POLICE_PEAKRATE-1]); - if (police->tcfp_P_tab == NULL) - goto failure; - } - } - if (tb[TCA_POLICE_RESULT-1]) { - if (RTA_PAYLOAD(tb[TCA_POLICE_RESULT-1]) != sizeof(u32)) - goto failure; - police->tcfp_result = *(u32*)RTA_DATA(tb[TCA_POLICE_RESULT-1]); - } -#ifdef CONFIG_NET_ESTIMATOR - if (tb[TCA_POLICE_AVRATE-1]) { - if (RTA_PAYLOAD(tb[TCA_POLICE_AVRATE-1]) != sizeof(u32)) - goto failure; - police->tcfp_ewma_rate = - *(u32*)RTA_DATA(tb[TCA_POLICE_AVRATE-1]); - } -#endif - police->tcfp_toks = police->tcfp_burst = parm->burst; - police->tcfp_mtu = parm->mtu; - if (police->tcfp_mtu == 0) { - police->tcfp_mtu = ~0; - if (police->tcfp_R_tab) - police->tcfp_mtu = 255<<police->tcfp_R_tab->rate.cell_log; - } - if (police->tcfp_P_tab) - police->tcfp_ptoks = L2T_P(police, police->tcfp_mtu); - police->tcfp_t_c = psched_get_time(); - police->tcf_index = parm->index ? parm->index : - tcf_police_new_index(); - police->tcf_action = parm->action; -#ifdef CONFIG_NET_ESTIMATOR - if (est) - gen_new_estimator(&police->tcf_bstats, &police->tcf_rate_est, - police->tcf_stats_lock, est); -#endif - h = tcf_hash(police->tcf_index, POL_TAB_MASK); - write_lock_bh(&police_lock); - police->tcf_next = tcf_police_ht[h]; - tcf_police_ht[h] = &police->common; - write_unlock_bh(&police_lock); - return police; - -failure: - if (police->tcfp_R_tab) - qdisc_put_rtab(police->tcfp_R_tab); - kfree(police); - return NULL; -} - -int tcf_police(struct sk_buff *skb, struct tcf_police *police) -{ - psched_time_t now; - long toks; - long ptoks = 0; - - spin_lock(&police->tcf_lock); - - police->tcf_bstats.bytes += skb->len; - police->tcf_bstats.packets++; - -#ifdef CONFIG_NET_ESTIMATOR - if (police->tcfp_ewma_rate && - police->tcf_rate_est.bps >= police->tcfp_ewma_rate) { - police->tcf_qstats.overlimits++; - spin_unlock(&police->tcf_lock); - return police->tcf_action; - } -#endif - if (skb->len <= police->tcfp_mtu) { - if (police->tcfp_R_tab == NULL) { - spin_unlock(&police->tcf_lock); - return police->tcfp_result; - } - - now = psched_get_time(); - toks = psched_tdiff_bounded(now, police->tcfp_t_c, - police->tcfp_burst); - if (police->tcfp_P_tab) { - ptoks = toks + police->tcfp_ptoks; - if (ptoks > (long)L2T_P(police, police->tcfp_mtu)) - ptoks = (long)L2T_P(police, police->tcfp_mtu); - ptoks -= L2T_P(police, skb->len); - } - toks += police->tcfp_toks; - if (toks > (long)police->tcfp_burst) - toks = police->tcfp_burst; - toks -= L2T(police, skb->len); - if ((toks|ptoks) >= 0) { - police->tcfp_t_c = now; - police->tcfp_toks = toks; - police->tcfp_ptoks = ptoks; - spin_unlock(&police->tcf_lock); - return police->tcfp_result; - } - } - - police->tcf_qstats.overlimits++; - spin_unlock(&police->tcf_lock); - return police->tcf_action; -} -EXPORT_SYMBOL(tcf_police); - -int tcf_police_dump(struct sk_buff *skb, struct tcf_police *police) -{ - unsigned char *b = skb_tail_pointer(skb); - struct tc_police opt; - - opt.index = police->tcf_index; - opt.action = police->tcf_action; - opt.mtu = police->tcfp_mtu; - opt.burst = police->tcfp_burst; - if (police->tcfp_R_tab) - opt.rate = police->tcfp_R_tab->rate; - else - memset(&opt.rate, 0, sizeof(opt.rate)); - if (police->tcfp_P_tab) - opt.peakrate = police->tcfp_P_tab->rate; - else - memset(&opt.peakrate, 0, sizeof(opt.peakrate)); - RTA_PUT(skb, TCA_POLICE_TBF, sizeof(opt), &opt); - if (police->tcfp_result) - RTA_PUT(skb, TCA_POLICE_RESULT, sizeof(int), - &police->tcfp_result); -#ifdef CONFIG_NET_ESTIMATOR - if (police->tcfp_ewma_rate) - RTA_PUT(skb, TCA_POLICE_AVRATE, 4, &police->tcfp_ewma_rate); -#endif - return skb->len; - -rtattr_failure: - nlmsg_trim(skb, b); - return -1; -} - -int tcf_police_dump_stats(struct sk_buff *skb, struct tcf_police *police) -{ - struct gnet_dump d; - - if (gnet_stats_start_copy_compat(skb, TCA_STATS2, TCA_STATS, - TCA_XSTATS, police->tcf_stats_lock, - &d) < 0) - goto errout; - - if (gnet_stats_copy_basic(&d, &police->tcf_bstats) < 0 || -#ifdef CONFIG_NET_ESTIMATOR - gnet_stats_copy_rate_est(&d, &police->tcf_rate_est) < 0 || -#endif - gnet_stats_copy_queue(&d, &police->tcf_qstats) < 0) - goto errout; - - if (gnet_stats_finish_copy(&d) < 0) - goto errout; - - return 0; - -errout: - return -1; -} - -#endif /* CONFIG_NET_CLS_ACT */ diff --git a/net/sched/act_simple.c b/net/sched/act_simple.c index 36e1edad5990..fb84ef33d14f 100644 --- a/net/sched/act_simple.c +++ b/net/sched/act_simple.c @@ -13,7 +13,6 @@ #include <linux/module.h> #include <linux/init.h> #include <linux/kernel.h> -#include <linux/netdevice.h> #include <linux/skbuff.h> #include <linux/rtnetlink.h> #include <net/netlink.h> diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c index ebf94edf0478..5f0fbca7393f 100644 --- a/net/sched/cls_api.c +++ b/net/sched/cls_api.c @@ -14,26 +14,16 @@ * */ -#include <asm/uaccess.h> -#include <asm/system.h> -#include <linux/bitops.h> #include <linux/module.h> #include <linux/types.h> #include <linux/kernel.h> #include <linux/string.h> -#include <linux/mm.h> -#include <linux/socket.h> -#include <linux/sockios.h> -#include <linux/in.h> #include <linux/errno.h> -#include <linux/interrupt.h> -#include <linux/netdevice.h> #include <linux/skbuff.h> #include <linux/init.h> #include <linux/kmod.h> #include <linux/netlink.h> #include <net/netlink.h> -#include <net/sock.h> #include <net/pkt_sched.h> #include <net/pkt_cls.h> @@ -468,11 +458,6 @@ tcf_exts_destroy(struct tcf_proto *tp, struct tcf_exts *exts) tcf_action_destroy(exts->action, TCA_ACT_UNBIND); exts->action = NULL; } -#elif defined CONFIG_NET_CLS_POLICE - if (exts->police) { - tcf_police_release(exts->police, TCA_ACT_UNBIND); - exts->police = NULL; - } #endif } @@ -506,17 +491,6 @@ tcf_exts_validate(struct tcf_proto *tp, struct rtattr **tb, exts->action = act; } } -#elif defined CONFIG_NET_CLS_POLICE - if (map->police && tb[map->police-1]) { - struct tcf_police *p; - - p = tcf_police_locate(tb[map->police-1], rate_tlv); - if (p == NULL) - return -EINVAL; - - exts->police = p; - } else if (map->action && tb[map->action-1]) - return -EOPNOTSUPP; #else if ((map->action && tb[map->action-1]) || (map->police && tb[map->police-1])) @@ -539,15 +513,6 @@ tcf_exts_change(struct tcf_proto *tp, struct tcf_exts *dst, if (act) tcf_action_destroy(act, TCA_ACT_UNBIND); } -#elif defined CONFIG_NET_CLS_POLICE - if (src->police) { - struct tcf_police *p; - tcf_tree_lock(tp); - p = xchg(&dst->police, src->police); - tcf_tree_unlock(tp); - if (p) - tcf_police_release(p, TCA_ACT_UNBIND); - } #endif } @@ -576,17 +541,6 @@ tcf_exts_dump(struct sk_buff *skb, struct tcf_exts *exts, p_rta->rta_len = skb_tail_pointer(skb) - (u8 *)p_rta; } } -#elif defined CONFIG_NET_CLS_POLICE - if (map->police && exts->police) { - struct rtattr *p_rta = (struct rtattr *)skb_tail_pointer(skb); - - RTA_PUT(skb, map->police, 0, NULL); - - if (tcf_police_dump(skb, exts->police) < 0) - goto rtattr_failure; - - p_rta->rta_len = skb_tail_pointer(skb) - (u8 *)p_rta; - } #endif return 0; rtattr_failure: __attribute__ ((unused)) @@ -601,10 +555,6 @@ tcf_exts_dump_stats(struct sk_buff *skb, struct tcf_exts *exts, if (exts->action) if (tcf_action_copy_stats(skb, exts->action, 1) < 0) goto rtattr_failure; -#elif defined CONFIG_NET_CLS_POLICE - if (exts->police) - if (tcf_police_dump_stats(skb, exts->police) < 0) - goto rtattr_failure; #endif return 0; rtattr_failure: __attribute__ ((unused)) diff --git a/net/sched/cls_basic.c b/net/sched/cls_basic.c index c885412d79d5..8dbcf2771a46 100644 --- a/net/sched/cls_basic.c +++ b/net/sched/cls_basic.c @@ -13,7 +13,6 @@ #include <linux/types.h> #include <linux/kernel.h> #include <linux/string.h> -#include <linux/mm.h> #include <linux/errno.h> #include <linux/rtnetlink.h> #include <linux/skbuff.h> diff --git a/net/sched/cls_fw.c b/net/sched/cls_fw.c index bbec4a0d4dcb..8adbd6a37d14 100644 --- a/net/sched/cls_fw.c +++ b/net/sched/cls_fw.c @@ -19,29 +19,12 @@ */ #include <linux/module.h> -#include <asm/uaccess.h> -#include <asm/system.h> -#include <linux/bitops.h> #include <linux/types.h> #include <linux/kernel.h> #include <linux/string.h> -#include <linux/mm.h> -#include <linux/socket.h> -#include <linux/sockios.h> -#include <linux/in.h> #include <linux/errno.h> -#include <linux/interrupt.h> -#include <linux/if_ether.h> -#include <linux/inet.h> -#include <linux/netdevice.h> -#include <linux/etherdevice.h> -#include <linux/notifier.h> -#include <linux/netfilter.h> -#include <net/ip.h> -#include <net/netlink.h> -#include <net/route.h> #include <linux/skbuff.h> -#include <net/sock.h> +#include <net/netlink.h> #include <net/act_api.h> #include <net/pkt_cls.h> diff --git a/net/sched/cls_route.c b/net/sched/cls_route.c index cc941d0ee3a5..0a8409c1d28a 100644 --- a/net/sched/cls_route.c +++ b/net/sched/cls_route.c @@ -10,28 +10,14 @@ */ #include <linux/module.h> -#include <asm/uaccess.h> -#include <asm/system.h> -#include <linux/bitops.h> #include <linux/types.h> #include <linux/kernel.h> #include <linux/string.h> -#include <linux/mm.h> -#include <linux/socket.h> -#include <linux/sockios.h> -#include <linux/in.h> #include <linux/errno.h> -#include <linux/interrupt.h> -#include <linux/if_ether.h> -#include <linux/inet.h> -#include <linux/netdevice.h> -#include <linux/etherdevice.h> -#include <linux/notifier.h> -#include <net/ip.h> -#include <net/netlink.h> -#include <net/route.h> #include <linux/skbuff.h> -#include <net/sock.h> +#include <net/dst.h> +#include <net/route.h> +#include <net/netlink.h> #include <net/act_api.h> #include <net/pkt_cls.h> diff --git a/net/sched/cls_rsvp.c b/net/sched/cls_rsvp.c index 0a683c07c648..cbb5e0d600f3 100644 --- a/net/sched/cls_rsvp.c +++ b/net/sched/cls_rsvp.c @@ -10,27 +10,12 @@ */ #include <linux/module.h> -#include <asm/uaccess.h> -#include <asm/system.h> -#include <linux/bitops.h> #include <linux/types.h> #include <linux/kernel.h> #include <linux/string.h> -#include <linux/mm.h> -#include <linux/socket.h> -#include <linux/sockios.h> -#include <linux/in.h> #include <linux/errno.h> -#include <linux/interrupt.h> -#include <linux/if_ether.h> -#include <linux/inet.h> -#include <linux/netdevice.h> -#include <linux/etherdevice.h> -#include <linux/notifier.h> -#include <net/ip.h> -#include <net/route.h> #include <linux/skbuff.h> -#include <net/sock.h> +#include <net/ip.h> #include <net/netlink.h> #include <net/act_api.h> #include <net/pkt_cls.h> diff --git a/net/sched/cls_rsvp6.c b/net/sched/cls_rsvp6.c index 93b6abed57db..dd08aea2aee5 100644 --- a/net/sched/cls_rsvp6.c +++ b/net/sched/cls_rsvp6.c @@ -10,28 +10,12 @@ */ #include <linux/module.h> -#include <asm/uaccess.h> -#include <asm/system.h> -#include <linux/bitops.h> #include <linux/types.h> #include <linux/kernel.h> #include <linux/string.h> -#include <linux/mm.h> -#include <linux/socket.h> -#include <linux/sockios.h> -#include <linux/in.h> #include <linux/errno.h> -#include <linux/interrupt.h> -#include <linux/if_ether.h> -#include <linux/inet.h> -#include <linux/netdevice.h> -#include <linux/etherdevice.h> -#include <linux/notifier.h> -#include <net/ip.h> #include <linux/ipv6.h> -#include <net/route.h> #include <linux/skbuff.h> -#include <net/sock.h> #include <net/act_api.h> #include <net/pkt_cls.h> #include <net/netlink.h> diff --git a/net/sched/cls_tcindex.c b/net/sched/cls_tcindex.c index 47ac0c556429..2314820a080a 100644 --- a/net/sched/cls_tcindex.c +++ b/net/sched/cls_tcindex.c @@ -9,12 +9,9 @@ #include <linux/kernel.h> #include <linux/skbuff.h> #include <linux/errno.h> -#include <linux/netdevice.h> -#include <net/ip.h> #include <net/act_api.h> #include <net/netlink.h> #include <net/pkt_cls.h> -#include <net/route.h> /* diff --git a/net/sched/cls_u32.c b/net/sched/cls_u32.c index c7a347bd6d70..d4d5d2f271d2 100644 --- a/net/sched/cls_u32.c +++ b/net/sched/cls_u32.c @@ -30,30 +30,14 @@ * nfmark match added by Catalin(ux aka Dino) BOIE <catab at umbrella.ro> */ -#include <asm/uaccess.h> -#include <asm/system.h> -#include <linux/bitops.h> #include <linux/module.h> #include <linux/types.h> #include <linux/kernel.h> #include <linux/string.h> -#include <linux/mm.h> -#include <linux/socket.h> -#include <linux/sockios.h> -#include <linux/in.h> #include <linux/errno.h> -#include <linux/interrupt.h> -#include <linux/if_ether.h> -#include <linux/inet.h> -#include <linux/netdevice.h> -#include <linux/etherdevice.h> -#include <linux/notifier.h> #include <linux/rtnetlink.h> -#include <net/ip.h> -#include <net/netlink.h> -#include <net/route.h> #include <linux/skbuff.h> -#include <net/sock.h> +#include <net/netlink.h> #include <net/act_api.h> #include <net/pkt_cls.h> @@ -518,7 +502,7 @@ static int u32_set_parms(struct tcf_proto *tp, unsigned long base, #ifdef CONFIG_NET_CLS_IND if (tb[TCA_U32_INDEV-1]) { - int err = tcf_change_indev(tp, n->indev, tb[TCA_U32_INDEV-1]); + err = tcf_change_indev(tp, n->indev, tb[TCA_U32_INDEV-1]); if (err < 0) goto errout; } @@ -798,9 +782,6 @@ static int __init init_u32(void) #ifdef CONFIG_CLS_U32_PERF printk(" Performance counters on\n"); #endif -#ifdef CONFIG_NET_CLS_POLICE - printk(" OLD policer on \n"); -#endif #ifdef CONFIG_NET_CLS_IND printk(" input device check on \n"); #endif diff --git a/net/sched/em_cmp.c b/net/sched/em_cmp.c index 8d6dacd81900..cc49c932641d 100644 --- a/net/sched/em_cmp.c +++ b/net/sched/em_cmp.c @@ -98,3 +98,4 @@ MODULE_LICENSE("GPL"); module_init(init_em_cmp); module_exit(exit_em_cmp); +MODULE_ALIAS_TCF_EMATCH(TCF_EM_CMP); diff --git a/net/sched/em_meta.c b/net/sched/em_meta.c index 60acf8cdb27b..650f09c8bd6a 100644 --- a/net/sched/em_meta.c +++ b/net/sched/em_meta.c @@ -848,3 +848,5 @@ MODULE_LICENSE("GPL"); module_init(init_em_meta); module_exit(exit_em_meta); + +MODULE_ALIAS_TCF_EMATCH(TCF_EM_META); diff --git a/net/sched/em_nbyte.c b/net/sched/em_nbyte.c index b4b36efce292..370a1b2ea317 100644 --- a/net/sched/em_nbyte.c +++ b/net/sched/em_nbyte.c @@ -76,3 +76,5 @@ MODULE_LICENSE("GPL"); module_init(init_em_nbyte); module_exit(exit_em_nbyte); + +MODULE_ALIAS_TCF_EMATCH(TCF_EM_NBYTE); diff --git a/net/sched/em_text.c b/net/sched/em_text.c index e8f46169449d..d5cd86efb7d0 100644 --- a/net/sched/em_text.c +++ b/net/sched/em_text.c @@ -150,3 +150,5 @@ MODULE_LICENSE("GPL"); module_init(init_em_text); module_exit(exit_em_text); + +MODULE_ALIAS_TCF_EMATCH(TCF_EM_TEXT); diff --git a/net/sched/em_u32.c b/net/sched/em_u32.c index 0a2a7fe08de3..112796e4a7c4 100644 --- a/net/sched/em_u32.c +++ b/net/sched/em_u32.c @@ -60,3 +60,5 @@ MODULE_LICENSE("GPL"); module_init(init_em_u32); module_exit(exit_em_u32); + +MODULE_ALIAS_TCF_EMATCH(TCF_EM_U32); diff --git a/net/sched/ematch.c b/net/sched/ematch.c index 63146d339d81..f3a104e323bd 100644 --- a/net/sched/ematch.c +++ b/net/sched/ematch.c @@ -84,9 +84,7 @@ #include <linux/module.h> #include <linux/types.h> #include <linux/kernel.h> -#include <linux/mm.h> #include <linux/errno.h> -#include <linux/interrupt.h> #include <linux/rtnetlink.h> #include <linux/skbuff.h> #include <net/pkt_cls.h> @@ -224,6 +222,19 @@ static int tcf_em_validate(struct tcf_proto *tp, if (em->ops == NULL) { err = -ENOENT; +#ifdef CONFIG_KMOD + __rtnl_unlock(); + request_module("ematch-kind-%u", em_hdr->kind); + rtnl_lock(); + em->ops = tcf_em_lookup(em_hdr->kind); + if (em->ops) { + /* We dropped the RTNL mutex in order to + * perform the module load. Tell the caller + * to replay the request. */ + module_put(em->ops->owner); + err = -EAGAIN; + } +#endif goto errout; } diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c index 7a6b0b7cc68a..dee0d5fb39c5 100644 --- a/net/sched/sch_api.c +++ b/net/sched/sch_api.c @@ -19,30 +19,18 @@ #include <linux/types.h> #include <linux/kernel.h> #include <linux/string.h> -#include <linux/mm.h> -#include <linux/socket.h> -#include <linux/sockios.h> -#include <linux/in.h> #include <linux/errno.h> -#include <linux/interrupt.h> -#include <linux/netdevice.h> #include <linux/skbuff.h> #include <linux/init.h> #include <linux/proc_fs.h> #include <linux/seq_file.h> #include <linux/kmod.h> #include <linux/list.h> -#include <linux/bitops.h> #include <linux/hrtimer.h> #include <net/netlink.h> -#include <net/sock.h> #include <net/pkt_sched.h> -#include <asm/processor.h> -#include <asm/uaccess.h> -#include <asm/system.h> - static int qdisc_notify(struct sk_buff *oskb, struct nlmsghdr *n, u32 clid, struct Qdisc *old, struct Qdisc *new); static int tclass_notify(struct sk_buff *oskb, struct nlmsghdr *n, @@ -392,6 +380,10 @@ void qdisc_tree_decrease_qlen(struct Qdisc *sch, unsigned int n) return; while ((parentid = sch->parent)) { sch = qdisc_lookup(sch->dev, TC_H_MAJ(parentid)); + if (sch == NULL) { + WARN_ON(parentid != TC_H_ROOT); + return; + } cops = sch->ops->cl_ops; if (cops->qlen_notify) { cl = cops->get(sch, parentid); @@ -432,8 +424,6 @@ static int qdisc_graft(struct net_device *dev, struct Qdisc *parent, unsigned long cl = cops->get(parent, classid); if (cl) { err = cops->graft(parent, cl, new, old); - if (new) - new->parent = classid; cops->put(parent, cl); } } @@ -448,7 +438,8 @@ static int qdisc_graft(struct net_device *dev, struct Qdisc *parent, */ static struct Qdisc * -qdisc_create(struct net_device *dev, u32 handle, struct rtattr **tca, int *errp) +qdisc_create(struct net_device *dev, u32 parent, u32 handle, + struct rtattr **tca, int *errp) { int err; struct rtattr *kind = tca[TCA_KIND-1]; @@ -494,6 +485,8 @@ qdisc_create(struct net_device *dev, u32 handle, struct rtattr **tca, int *errp) goto err_out2; } + sch->parent = parent; + if (handle == TC_H_INGRESS) { sch->flags |= TCQ_F_INGRESS; sch->stats_lock = &dev->ingress_lock; @@ -511,7 +504,6 @@ qdisc_create(struct net_device *dev, u32 handle, struct rtattr **tca, int *errp) sch->handle = handle; if (!ops->init || (err = ops->init(sch, tca[TCA_OPTIONS-1])) == 0) { -#ifdef CONFIG_NET_ESTIMATOR if (tca[TCA_RATE-1]) { err = gen_new_estimator(&sch->bstats, &sch->rate_est, sch->stats_lock, @@ -527,7 +519,6 @@ qdisc_create(struct net_device *dev, u32 handle, struct rtattr **tca, int *errp) goto err_out3; } } -#endif qdisc_lock_tree(dev); list_add_tail(&sch->list, &dev->qdisc_list); qdisc_unlock_tree(dev); @@ -555,11 +546,9 @@ static int qdisc_change(struct Qdisc *sch, struct rtattr **tca) if (err) return err; } -#ifdef CONFIG_NET_ESTIMATOR if (tca[TCA_RATE-1]) gen_replace_estimator(&sch->bstats, &sch->rate_est, sch->stats_lock, tca[TCA_RATE-1]); -#endif return 0; } @@ -774,9 +763,11 @@ create_n_graft: if (!(n->nlmsg_flags&NLM_F_CREATE)) return -ENOENT; if (clid == TC_H_INGRESS) - q = qdisc_create(dev, tcm->tcm_parent, tca, &err); + q = qdisc_create(dev, tcm->tcm_parent, tcm->tcm_parent, + tca, &err); else - q = qdisc_create(dev, tcm->tcm_handle, tca, &err); + q = qdisc_create(dev, tcm->tcm_parent, tcm->tcm_handle, + tca, &err); if (q == NULL) { if (err == -EAGAIN) goto replay; @@ -835,9 +826,7 @@ static int tc_fill_qdisc(struct sk_buff *skb, struct Qdisc *q, u32 clid, goto rtattr_failure; if (gnet_stats_copy_basic(&d, &q->bstats) < 0 || -#ifdef CONFIG_NET_ESTIMATOR gnet_stats_copy_rate_est(&d, &q->rate_est) < 0 || -#endif gnet_stats_copy_queue(&d, &q->qstats) < 0) goto rtattr_failure; @@ -1163,47 +1152,57 @@ static int tc_dump_tclass(struct sk_buff *skb, struct netlink_callback *cb) 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; + + for (; tp; tp = tp->next) { + if ((tp->protocol == protocol || + tp->protocol == htons(ETH_P_ALL)) && + (err = tp->classify(skb, tp, res)) >= 0) { +#ifdef CONFIG_NET_CLS_ACT + if (err != TC_ACT_RECLASSIFY && skb->tc_verd) + skb->tc_verd = SET_TC_VERD(skb->tc_verd, 0); +#endif + return err; + } + } + return -1; +} +EXPORT_SYMBOL(tc_classify_compat); + int tc_classify(struct sk_buff *skb, struct tcf_proto *tp, - struct tcf_result *res) + struct tcf_result *res) { int err = 0; - __be16 protocol = skb->protocol; + __be16 protocol; #ifdef CONFIG_NET_CLS_ACT struct tcf_proto *otp = tp; reclassify: #endif protocol = skb->protocol; - for ( ; tp; tp = tp->next) { - if ((tp->protocol == protocol || - tp->protocol == htons(ETH_P_ALL)) && - (err = tp->classify(skb, tp, res)) >= 0) { + err = tc_classify_compat(skb, tp, res); #ifdef CONFIG_NET_CLS_ACT - if ( TC_ACT_RECLASSIFY == err) { - __u32 verd = (__u32) G_TC_VERD(skb->tc_verd); - tp = otp; - - if (MAX_REC_LOOP < verd++) { - printk("rule prio %d protocol %02x reclassify is buggy packet dropped\n", - tp->prio&0xffff, ntohs(tp->protocol)); - return TC_ACT_SHOT; - } - skb->tc_verd = SET_TC_VERD(skb->tc_verd,verd); - goto reclassify; - } else { - if (skb->tc_verd) - skb->tc_verd = SET_TC_VERD(skb->tc_verd,0); - return err; - } -#else - - return err; -#endif + if (err == TC_ACT_RECLASSIFY) { + u32 verd = G_TC_VERD(skb->tc_verd); + tp = otp; + + if (verd++ >= MAX_REC_LOOP) { + printk("rule prio %u protocol %02x reclassify loop, " + "packet dropped\n", + tp->prio&0xffff, ntohs(tp->protocol)); + return TC_ACT_SHOT; } - + skb->tc_verd = SET_TC_VERD(skb->tc_verd, verd); + goto reclassify; } - return -1; +#endif + return err; } +EXPORT_SYMBOL(tc_classify); void tcf_destroy(struct tcf_proto *tp) { @@ -1270,4 +1269,3 @@ EXPORT_SYMBOL(qdisc_get_rtab); EXPORT_SYMBOL(qdisc_put_rtab); EXPORT_SYMBOL(register_qdisc); EXPORT_SYMBOL(unregister_qdisc); -EXPORT_SYMBOL(tc_classify); diff --git a/net/sched/sch_atm.c b/net/sched/sch_atm.c index d1c383fca82c..ddc4f2c54379 100644 --- a/net/sched/sch_atm.c +++ b/net/sched/sch_atm.c @@ -2,24 +2,19 @@ /* Written 1998-2000 by Werner Almesberger, EPFL ICA */ - #include <linux/module.h> #include <linux/init.h> #include <linux/string.h> #include <linux/errno.h> #include <linux/skbuff.h> -#include <linux/interrupt.h> #include <linux/atmdev.h> #include <linux/atmclip.h> -#include <linux/netdevice.h> #include <linux/rtnetlink.h> -#include <linux/file.h> /* for fput */ +#include <linux/file.h> /* for fput */ #include <net/netlink.h> #include <net/pkt_sched.h> -#include <net/sock.h> - -extern struct socket *sockfd_lookup(int fd, int *err); /* @@@ fix this */ +extern struct socket *sockfd_lookup(int fd, int *err); /* @@@ fix this */ #if 0 /* control */ #define DPRINTK(format,args...) printk(KERN_DEBUG format,##args) @@ -33,7 +28,6 @@ extern struct socket *sockfd_lookup(int fd, int *err); /* @@@ fix this */ #define D2PRINTK(format,args...) #endif - /* * The ATM queuing discipline provides a framework for invoking classifiers * (aka "filters"), which in turn select classes of this queuing discipline. @@ -55,23 +49,21 @@ extern struct socket *sockfd_lookup(int fd, int *err); /* @@@ fix this */ * - should lock the flow while there is data in the queue (?) */ - #define PRIV(sch) qdisc_priv(sch) #define VCC2FLOW(vcc) ((struct atm_flow_data *) ((vcc)->user_back)) - struct atm_flow_data { - struct Qdisc *q; /* FIFO, TBF, etc. */ + struct Qdisc *q; /* FIFO, TBF, etc. */ struct tcf_proto *filter_list; - struct atm_vcc *vcc; /* VCC; NULL if VCC is closed */ - void (*old_pop)(struct atm_vcc *vcc,struct sk_buff *skb); /* chaining */ + struct atm_vcc *vcc; /* VCC; NULL if VCC is closed */ + void (*old_pop)(struct atm_vcc *vcc, + struct sk_buff * skb); /* chaining */ struct atm_qdisc_data *parent; /* parent qdisc */ struct socket *sock; /* for closing */ u32 classid; /* x:y type ID */ int ref; /* reference count */ struct gnet_stats_basic bstats; struct gnet_stats_queue qstats; - spinlock_t *stats_lock; struct atm_flow_data *next; struct atm_flow_data *excess; /* flow for excess traffic; NULL to set CLP instead */ @@ -86,76 +78,74 @@ struct atm_qdisc_data { struct tasklet_struct task; /* requeue tasklet */ }; - /* ------------------------- Class/flow operations ------------------------- */ - -static int find_flow(struct atm_qdisc_data *qdisc,struct atm_flow_data *flow) +static int find_flow(struct atm_qdisc_data *qdisc, struct atm_flow_data *flow) { struct atm_flow_data *walk; - DPRINTK("find_flow(qdisc %p,flow %p)\n",qdisc,flow); + DPRINTK("find_flow(qdisc %p,flow %p)\n", qdisc, flow); for (walk = qdisc->flows; walk; walk = walk->next) - if (walk == flow) return 1; + if (walk == flow) + return 1; DPRINTK("find_flow: not found\n"); return 0; } - -static __inline__ struct atm_flow_data *lookup_flow(struct Qdisc *sch, - u32 classid) +static inline struct atm_flow_data *lookup_flow(struct Qdisc *sch, u32 classid) { struct atm_qdisc_data *p = PRIV(sch); struct atm_flow_data *flow; for (flow = p->flows; flow; flow = flow->next) - if (flow->classid == classid) break; + if (flow->classid == classid) + break; return flow; } - -static int atm_tc_graft(struct Qdisc *sch,unsigned long arg, - struct Qdisc *new,struct Qdisc **old) +static int atm_tc_graft(struct Qdisc *sch, unsigned long arg, + struct Qdisc *new, struct Qdisc **old) { struct atm_qdisc_data *p = PRIV(sch); - struct atm_flow_data *flow = (struct atm_flow_data *) arg; - - DPRINTK("atm_tc_graft(sch %p,[qdisc %p],flow %p,new %p,old %p)\n",sch, - p,flow,new,old); - if (!find_flow(p,flow)) return -EINVAL; - if (!new) new = &noop_qdisc; - *old = xchg(&flow->q,new); - if (*old) qdisc_reset(*old); + struct atm_flow_data *flow = (struct atm_flow_data *)arg; + + DPRINTK("atm_tc_graft(sch %p,[qdisc %p],flow %p,new %p,old %p)\n", + sch, p, flow, new, old); + if (!find_flow(p, flow)) + return -EINVAL; + if (!new) + new = &noop_qdisc; + *old = xchg(&flow->q, new); + if (*old) + qdisc_reset(*old); return 0; } - -static struct Qdisc *atm_tc_leaf(struct Qdisc *sch,unsigned long cl) +static struct Qdisc *atm_tc_leaf(struct Qdisc *sch, unsigned long cl) { - struct atm_flow_data *flow = (struct atm_flow_data *) cl; + struct atm_flow_data *flow = (struct atm_flow_data *)cl; - DPRINTK("atm_tc_leaf(sch %p,flow %p)\n",sch,flow); + DPRINTK("atm_tc_leaf(sch %p,flow %p)\n", sch, flow); return flow ? flow->q : NULL; } - -static unsigned long atm_tc_get(struct Qdisc *sch,u32 classid) +static unsigned long atm_tc_get(struct Qdisc *sch, u32 classid) { - struct atm_qdisc_data *p __attribute__((unused)) = PRIV(sch); + struct atm_qdisc_data *p __maybe_unused = PRIV(sch); struct atm_flow_data *flow; - DPRINTK("atm_tc_get(sch %p,[qdisc %p],classid %x)\n",sch,p,classid); - flow = lookup_flow(sch,classid); - if (flow) flow->ref++; - DPRINTK("atm_tc_get: flow %p\n",flow); - return (unsigned long) flow; + DPRINTK("atm_tc_get(sch %p,[qdisc %p],classid %x)\n", sch, p, classid); + flow = lookup_flow(sch, classid); + if (flow) + flow->ref++; + DPRINTK("atm_tc_get: flow %p\n", flow); + return (unsigned long)flow; } - static unsigned long atm_tc_bind_filter(struct Qdisc *sch, - unsigned long parent, u32 classid) + unsigned long parent, u32 classid) { - return atm_tc_get(sch,classid); + return atm_tc_get(sch, classid); } /* @@ -163,72 +153,75 @@ static unsigned long atm_tc_bind_filter(struct Qdisc *sch, * requested (atm_tc_destroy, etc.). The assumption here is that we never drop * anything that still seems to be in use. */ - static void atm_tc_put(struct Qdisc *sch, unsigned long cl) { struct atm_qdisc_data *p = PRIV(sch); - struct atm_flow_data *flow = (struct atm_flow_data *) cl; + struct atm_flow_data *flow = (struct atm_flow_data *)cl; struct atm_flow_data **prev; - DPRINTK("atm_tc_put(sch %p,[qdisc %p],flow %p)\n",sch,p,flow); - if (--flow->ref) return; + DPRINTK("atm_tc_put(sch %p,[qdisc %p],flow %p)\n", sch, p, flow); + if (--flow->ref) + return; DPRINTK("atm_tc_put: destroying\n"); for (prev = &p->flows; *prev; prev = &(*prev)->next) - if (*prev == flow) break; + if (*prev == flow) + break; if (!*prev) { - printk(KERN_CRIT "atm_tc_put: class %p not found\n",flow); + printk(KERN_CRIT "atm_tc_put: class %p not found\n", flow); return; } *prev = flow->next; - DPRINTK("atm_tc_put: qdisc %p\n",flow->q); + DPRINTK("atm_tc_put: qdisc %p\n", flow->q); qdisc_destroy(flow->q); tcf_destroy_chain(flow->filter_list); if (flow->sock) { DPRINTK("atm_tc_put: f_count %d\n", - file_count(flow->sock->file)); + file_count(flow->sock->file)); flow->vcc->pop = flow->old_pop; sockfd_put(flow->sock); } - if (flow->excess) atm_tc_put(sch,(unsigned long) flow->excess); - if (flow != &p->link) kfree(flow); + if (flow->excess) + atm_tc_put(sch, (unsigned long)flow->excess); + if (flow != &p->link) + kfree(flow); /* * If flow == &p->link, the qdisc no longer works at this point and * needs to be removed. (By the caller of atm_tc_put.) */ } - -static void sch_atm_pop(struct atm_vcc *vcc,struct sk_buff *skb) +static void sch_atm_pop(struct atm_vcc *vcc, struct sk_buff *skb) { struct atm_qdisc_data *p = VCC2FLOW(vcc)->parent; - D2PRINTK("sch_atm_pop(vcc %p,skb %p,[qdisc %p])\n",vcc,skb,p); - VCC2FLOW(vcc)->old_pop(vcc,skb); + D2PRINTK("sch_atm_pop(vcc %p,skb %p,[qdisc %p])\n", vcc, skb, p); + VCC2FLOW(vcc)->old_pop(vcc, skb); tasklet_schedule(&p->task); } static const u8 llc_oui_ip[] = { - 0xaa, /* DSAP: non-ISO */ - 0xaa, /* SSAP: non-ISO */ - 0x03, /* Ctrl: Unnumbered Information Command PDU */ - 0x00, /* OUI: EtherType */ + 0xaa, /* DSAP: non-ISO */ + 0xaa, /* SSAP: non-ISO */ + 0x03, /* Ctrl: Unnumbered Information Command PDU */ + 0x00, /* OUI: EtherType */ 0x00, 0x00, - 0x08, 0x00 }; /* Ethertype IP (0800) */ + 0x08, 0x00 +}; /* Ethertype IP (0800) */ static int atm_tc_change(struct Qdisc *sch, u32 classid, u32 parent, - struct rtattr **tca, unsigned long *arg) + struct rtattr **tca, unsigned long *arg) { struct atm_qdisc_data *p = PRIV(sch); - struct atm_flow_data *flow = (struct atm_flow_data *) *arg; + struct atm_flow_data *flow = (struct atm_flow_data *)*arg; struct atm_flow_data *excess = NULL; - struct rtattr *opt = tca[TCA_OPTIONS-1]; + struct rtattr *opt = tca[TCA_OPTIONS - 1]; struct rtattr *tb[TCA_ATM_MAX]; struct socket *sock; - int fd,error,hdr_len; + int fd, error, hdr_len; void *hdr; DPRINTK("atm_tc_change(sch %p,[qdisc %p],classid %x,parent %x," - "flow %p,opt %p)\n",sch,p,classid,parent,flow,opt); + "flow %p,opt %p)\n", sch, p, classid, parent, flow, opt); /* * The concept of parents doesn't apply for this qdisc. */ @@ -241,33 +234,36 @@ static int atm_tc_change(struct Qdisc *sch, u32 classid, u32 parent, * class needs to be removed and a new one added. (This may be changed * later.) */ - if (flow) return -EBUSY; + if (flow) + return -EBUSY; if (opt == NULL || rtattr_parse_nested(tb, TCA_ATM_MAX, opt)) return -EINVAL; - if (!tb[TCA_ATM_FD-1] || RTA_PAYLOAD(tb[TCA_ATM_FD-1]) < sizeof(fd)) + if (!tb[TCA_ATM_FD - 1] || RTA_PAYLOAD(tb[TCA_ATM_FD - 1]) < sizeof(fd)) return -EINVAL; - fd = *(int *) RTA_DATA(tb[TCA_ATM_FD-1]); - DPRINTK("atm_tc_change: fd %d\n",fd); - if (tb[TCA_ATM_HDR-1]) { - hdr_len = RTA_PAYLOAD(tb[TCA_ATM_HDR-1]); - hdr = RTA_DATA(tb[TCA_ATM_HDR-1]); - } - else { + fd = *(int *)RTA_DATA(tb[TCA_ATM_FD - 1]); + DPRINTK("atm_tc_change: fd %d\n", fd); + if (tb[TCA_ATM_HDR - 1]) { + hdr_len = RTA_PAYLOAD(tb[TCA_ATM_HDR - 1]); + hdr = RTA_DATA(tb[TCA_ATM_HDR - 1]); + } else { hdr_len = RFC1483LLC_LEN; - hdr = NULL; /* default LLC/SNAP for IP */ + hdr = NULL; /* default LLC/SNAP for IP */ } - if (!tb[TCA_ATM_EXCESS-1]) excess = NULL; + if (!tb[TCA_ATM_EXCESS - 1]) + excess = NULL; else { - if (RTA_PAYLOAD(tb[TCA_ATM_EXCESS-1]) != sizeof(u32)) + if (RTA_PAYLOAD(tb[TCA_ATM_EXCESS - 1]) != sizeof(u32)) return -EINVAL; - excess = (struct atm_flow_data *) atm_tc_get(sch, - *(u32 *) RTA_DATA(tb[TCA_ATM_EXCESS-1])); - if (!excess) return -ENOENT; + excess = (struct atm_flow_data *) + atm_tc_get(sch, *(u32 *)RTA_DATA(tb[TCA_ATM_EXCESS - 1])); + if (!excess) + return -ENOENT; } DPRINTK("atm_tc_change: type %d, payload %d, hdr_len %d\n", - opt->rta_type,RTA_PAYLOAD(opt),hdr_len); - if (!(sock = sockfd_lookup(fd,&error))) return error; /* f_count++ */ - DPRINTK("atm_tc_change: f_count %d\n",file_count(sock->file)); + opt->rta_type, RTA_PAYLOAD(opt), hdr_len); + if (!(sock = sockfd_lookup(fd, &error))) + return error; /* f_count++ */ + DPRINTK("atm_tc_change: f_count %d\n", file_count(sock->file)); if (sock->ops->family != PF_ATMSVC && sock->ops->family != PF_ATMPVC) { error = -EPROTOTYPE; goto err_out; @@ -280,37 +276,36 @@ static int atm_tc_change(struct Qdisc *sch, u32 classid, u32 parent, error = -EINVAL; goto err_out; } - if (find_flow(p,flow)) { + if (find_flow(p, flow)) { error = -EEXIST; goto err_out; } - } - else { + } else { int i; unsigned long cl; for (i = 1; i < 0x8000; i++) { - classid = TC_H_MAKE(sch->handle,0x8000 | i); - if (!(cl = atm_tc_get(sch,classid))) break; - atm_tc_put(sch,cl); + classid = TC_H_MAKE(sch->handle, 0x8000 | i); + if (!(cl = atm_tc_get(sch, classid))) + break; + atm_tc_put(sch, cl); } } - DPRINTK("atm_tc_change: new id %x\n",classid); - flow = kmalloc(sizeof(struct atm_flow_data)+hdr_len,GFP_KERNEL); - DPRINTK("atm_tc_change: flow %p\n",flow); + DPRINTK("atm_tc_change: new id %x\n", classid); + flow = kzalloc(sizeof(struct atm_flow_data) + hdr_len, GFP_KERNEL); + DPRINTK("atm_tc_change: flow %p\n", flow); if (!flow) { error = -ENOBUFS; goto err_out; } - memset(flow,0,sizeof(*flow)); flow->filter_list = NULL; - if (!(flow->q = qdisc_create_dflt(sch->dev,&pfifo_qdisc_ops,classid))) + if (!(flow->q = qdisc_create_dflt(sch->dev, &pfifo_qdisc_ops, classid))) flow->q = &noop_qdisc; - DPRINTK("atm_tc_change: qdisc %p\n",flow->q); + DPRINTK("atm_tc_change: qdisc %p\n", flow->q); flow->sock = sock; - flow->vcc = ATM_SD(sock); /* speedup */ + flow->vcc = ATM_SD(sock); /* speedup */ flow->vcc->user_back = flow; - DPRINTK("atm_tc_change: vcc %p\n",flow->vcc); + DPRINTK("atm_tc_change: vcc %p\n", flow->vcc); flow->old_pop = flow->vcc->pop; flow->parent = p; flow->vcc->pop = sch_atm_pop; @@ -321,50 +316,53 @@ static int atm_tc_change(struct Qdisc *sch, u32 classid, u32 parent, p->link.next = flow; flow->hdr_len = hdr_len; if (hdr) - memcpy(flow->hdr,hdr,hdr_len); + memcpy(flow->hdr, hdr, hdr_len); else - memcpy(flow->hdr,llc_oui_ip,sizeof(llc_oui_ip)); - *arg = (unsigned long) flow; + memcpy(flow->hdr, llc_oui_ip, sizeof(llc_oui_ip)); + *arg = (unsigned long)flow; return 0; err_out: - if (excess) atm_tc_put(sch,(unsigned long) excess); + if (excess) + atm_tc_put(sch, (unsigned long)excess); sockfd_put(sock); return error; } - -static int atm_tc_delete(struct Qdisc *sch,unsigned long arg) +static int atm_tc_delete(struct Qdisc *sch, unsigned long arg) { struct atm_qdisc_data *p = PRIV(sch); - struct atm_flow_data *flow = (struct atm_flow_data *) arg; + struct atm_flow_data *flow = (struct atm_flow_data *)arg; - DPRINTK("atm_tc_delete(sch %p,[qdisc %p],flow %p)\n",sch,p,flow); - if (!find_flow(PRIV(sch),flow)) return -EINVAL; - if (flow->filter_list || flow == &p->link) return -EBUSY; + DPRINTK("atm_tc_delete(sch %p,[qdisc %p],flow %p)\n", sch, p, flow); + if (!find_flow(PRIV(sch), flow)) + return -EINVAL; + if (flow->filter_list || flow == &p->link) + return -EBUSY; /* * Reference count must be 2: one for "keepalive" (set at class * 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); + printk(KERN_ERR "atm_tc_delete: flow->ref == %d\n", flow->ref); return -EINVAL; } - if (flow->ref > 2) return -EBUSY; /* catch references via excess, etc.*/ - atm_tc_put(sch,arg); + if (flow->ref > 2) + return -EBUSY; /* catch references via excess, etc. */ + atm_tc_put(sch, arg); return 0; } - -static void atm_tc_walk(struct Qdisc *sch,struct qdisc_walker *walker) +static void atm_tc_walk(struct Qdisc *sch, struct qdisc_walker *walker) { struct atm_qdisc_data *p = PRIV(sch); struct atm_flow_data *flow; - DPRINTK("atm_tc_walk(sch %p,[qdisc %p],walker %p)\n",sch,p,walker); - if (walker->stop) return; + DPRINTK("atm_tc_walk(sch %p,[qdisc %p],walker %p)\n", sch, p, walker); + if (walker->stop) + return; for (flow = p->flows; flow; flow = flow->next) { if (walker->count >= walker->skip) - if (walker->fn(sch,(unsigned long) flow,walker) < 0) { + if (walker->fn(sch, (unsigned long)flow, walker) < 0) { walker->stop = 1; break; } @@ -372,73 +370,71 @@ static void atm_tc_walk(struct Qdisc *sch,struct qdisc_walker *walker) } } - -static struct tcf_proto **atm_tc_find_tcf(struct Qdisc *sch,unsigned long cl) +static struct tcf_proto **atm_tc_find_tcf(struct Qdisc *sch, unsigned long cl) { struct atm_qdisc_data *p = PRIV(sch); - struct atm_flow_data *flow = (struct atm_flow_data *) cl; + struct atm_flow_data *flow = (struct atm_flow_data *)cl; - DPRINTK("atm_tc_find_tcf(sch %p,[qdisc %p],flow %p)\n",sch,p,flow); + DPRINTK("atm_tc_find_tcf(sch %p,[qdisc %p],flow %p)\n", sch, p, flow); return flow ? &flow->filter_list : &p->link.filter_list; } - /* --------------------------- Qdisc operations ---------------------------- */ - -static int atm_tc_enqueue(struct sk_buff *skb,struct Qdisc *sch) +static int atm_tc_enqueue(struct sk_buff *skb, struct Qdisc *sch) { struct atm_qdisc_data *p = PRIV(sch); - struct atm_flow_data *flow = NULL ; /* @@@ */ + struct atm_flow_data *flow = NULL; /* @@@ */ struct tcf_result res; int result; int ret = NET_XMIT_POLICED; - D2PRINTK("atm_tc_enqueue(skb %p,sch %p,[qdisc %p])\n",skb,sch,p); - result = TC_POLICE_OK; /* be nice to gcc */ + D2PRINTK("atm_tc_enqueue(skb %p,sch %p,[qdisc %p])\n", skb, sch, p); + result = TC_POLICE_OK; /* be nice to gcc */ if (TC_H_MAJ(skb->priority) != sch->handle || - !(flow = (struct atm_flow_data *) atm_tc_get(sch,skb->priority))) + !(flow = (struct atm_flow_data *)atm_tc_get(sch, skb->priority))) for (flow = p->flows; flow; flow = flow->next) if (flow->filter_list) { - result = tc_classify(skb,flow->filter_list, - &res); - if (result < 0) continue; - flow = (struct atm_flow_data *) res.class; - if (!flow) flow = lookup_flow(sch,res.classid); + result = tc_classify_compat(skb, + flow->filter_list, + &res); + if (result < 0) + continue; + flow = (struct atm_flow_data *)res.class; + if (!flow) + flow = lookup_flow(sch, res.classid); break; } - if (!flow) flow = &p->link; + if (!flow) + flow = &p->link; else { if (flow->vcc) ATM_SKB(skb)->atm_options = flow->vcc->atm_options; - /*@@@ looks good ... but it's not supposed to work :-)*/ -#ifdef CONFIG_NET_CLS_POLICE + /*@@@ looks good ... but it's not supposed to work :-) */ +#ifdef CONFIG_NET_CLS_ACT switch (result) { - case TC_POLICE_SHOT: - kfree_skb(skb); - break; - case TC_POLICE_RECLASSIFY: - if (flow->excess) flow = flow->excess; - else { - ATM_SKB(skb)->atm_options |= - ATM_ATMOPT_CLP; - break; - } - /* fall through */ - case TC_POLICE_OK: - /* fall through */ - default: - break; + case TC_ACT_QUEUED: + case TC_ACT_STOLEN: + kfree_skb(skb); + return NET_XMIT_SUCCESS; + case TC_ACT_SHOT: + kfree_skb(skb); + goto drop; + case TC_POLICE_RECLASSIFY: + if (flow->excess) + flow = flow->excess; + else + ATM_SKB(skb)->atm_options |= ATM_ATMOPT_CLP; + break; } #endif } - if ( -#ifdef CONFIG_NET_CLS_POLICE - result == TC_POLICE_SHOT || -#endif - (ret = flow->q->enqueue(skb,flow->q)) != 0) { + + if ((ret = flow->q->enqueue(skb, flow->q)) != 0) { +drop: __maybe_unused sch->qstats.drops++; - if (flow) flow->qstats.drops++; + if (flow) + flow->qstats.drops++; return ret; } sch->bstats.bytes += skb->len; @@ -462,7 +458,6 @@ static int atm_tc_enqueue(struct sk_buff *skb,struct Qdisc *sch) return NET_XMIT_BYPASS; } - /* * Dequeue packets and send them over ATM. Note that we quite deliberately * avoid checking net_device's flow control here, simply because sch_atm @@ -470,167 +465,163 @@ static int atm_tc_enqueue(struct sk_buff *skb,struct Qdisc *sch) * non-ATM interfaces. */ - static void sch_atm_dequeue(unsigned long data) { - struct Qdisc *sch = (struct Qdisc *) data; + struct Qdisc *sch = (struct Qdisc *)data; struct atm_qdisc_data *p = PRIV(sch); struct atm_flow_data *flow; struct sk_buff *skb; - D2PRINTK("sch_atm_dequeue(sch %p,[qdisc %p])\n",sch,p); + D2PRINTK("sch_atm_dequeue(sch %p,[qdisc %p])\n", sch, p); for (flow = p->link.next; flow; flow = flow->next) /* * If traffic is properly shaped, this won't generate nasty * little bursts. Otherwise, it may ... (but that's okay) */ while ((skb = flow->q->dequeue(flow->q))) { - if (!atm_may_send(flow->vcc,skb->truesize)) { - (void) flow->q->ops->requeue(skb,flow->q); + if (!atm_may_send(flow->vcc, skb->truesize)) { + (void)flow->q->ops->requeue(skb, flow->q); break; } - D2PRINTK("atm_tc_dequeue: sending on class %p\n",flow); + D2PRINTK("atm_tc_dequeue: sending on class %p\n", flow); /* remove any LL header somebody else has attached */ skb_pull(skb, skb_network_offset(skb)); if (skb_headroom(skb) < flow->hdr_len) { struct sk_buff *new; - new = skb_realloc_headroom(skb,flow->hdr_len); + new = skb_realloc_headroom(skb, flow->hdr_len); dev_kfree_skb(skb); - if (!new) continue; + if (!new) + continue; skb = new; } D2PRINTK("sch_atm_dequeue: ip %p, data %p\n", skb_network_header(skb), skb->data); ATM_SKB(skb)->vcc = flow->vcc; - memcpy(skb_push(skb,flow->hdr_len),flow->hdr, - flow->hdr_len); + memcpy(skb_push(skb, flow->hdr_len), flow->hdr, + flow->hdr_len); atomic_add(skb->truesize, &sk_atm(flow->vcc)->sk_wmem_alloc); /* atm.atm_options are already set by atm_tc_enqueue */ - (void) flow->vcc->send(flow->vcc,skb); + flow->vcc->send(flow->vcc, skb); } } - static struct sk_buff *atm_tc_dequeue(struct Qdisc *sch) { struct atm_qdisc_data *p = PRIV(sch); struct sk_buff *skb; - D2PRINTK("atm_tc_dequeue(sch %p,[qdisc %p])\n",sch,p); + D2PRINTK("atm_tc_dequeue(sch %p,[qdisc %p])\n", sch, p); tasklet_schedule(&p->task); skb = p->link.q->dequeue(p->link.q); - if (skb) sch->q.qlen--; + if (skb) + sch->q.qlen--; return skb; } - -static int atm_tc_requeue(struct sk_buff *skb,struct Qdisc *sch) +static int atm_tc_requeue(struct sk_buff *skb, struct Qdisc *sch) { struct atm_qdisc_data *p = PRIV(sch); int ret; - D2PRINTK("atm_tc_requeue(skb %p,sch %p,[qdisc %p])\n",skb,sch,p); - ret = p->link.q->ops->requeue(skb,p->link.q); + D2PRINTK("atm_tc_requeue(skb %p,sch %p,[qdisc %p])\n", skb, sch, p); + ret = p->link.q->ops->requeue(skb, p->link.q); if (!ret) { - sch->q.qlen++; - sch->qstats.requeues++; - } else { + sch->q.qlen++; + sch->qstats.requeues++; + } else { sch->qstats.drops++; p->link.qstats.drops++; } return ret; } - static unsigned int atm_tc_drop(struct Qdisc *sch) { struct atm_qdisc_data *p = PRIV(sch); struct atm_flow_data *flow; unsigned int len; - DPRINTK("atm_tc_drop(sch %p,[qdisc %p])\n",sch,p); + DPRINTK("atm_tc_drop(sch %p,[qdisc %p])\n", sch, p); for (flow = p->flows; flow; flow = flow->next) if (flow->q->ops->drop && (len = flow->q->ops->drop(flow->q))) return len; return 0; } - -static int atm_tc_init(struct Qdisc *sch,struct rtattr *opt) +static int atm_tc_init(struct Qdisc *sch, struct rtattr *opt) { struct atm_qdisc_data *p = PRIV(sch); - DPRINTK("atm_tc_init(sch %p,[qdisc %p],opt %p)\n",sch,p,opt); + DPRINTK("atm_tc_init(sch %p,[qdisc %p],opt %p)\n", sch, p, opt); p->flows = &p->link; - if(!(p->link.q = qdisc_create_dflt(sch->dev,&pfifo_qdisc_ops, - sch->handle))) + if (!(p->link.q = qdisc_create_dflt(sch->dev, &pfifo_qdisc_ops, + sch->handle))) p->link.q = &noop_qdisc; - DPRINTK("atm_tc_init: link (%p) qdisc %p\n",&p->link,p->link.q); + DPRINTK("atm_tc_init: link (%p) qdisc %p\n", &p->link, p->link.q); p->link.filter_list = NULL; p->link.vcc = NULL; p->link.sock = NULL; p->link.classid = sch->handle; p->link.ref = 1; p->link.next = NULL; - tasklet_init(&p->task,sch_atm_dequeue,(unsigned long) sch); + tasklet_init(&p->task, sch_atm_dequeue, (unsigned long)sch); return 0; } - static void atm_tc_reset(struct Qdisc *sch) { struct atm_qdisc_data *p = PRIV(sch); struct atm_flow_data *flow; - DPRINTK("atm_tc_reset(sch %p,[qdisc %p])\n",sch,p); - for (flow = p->flows; flow; flow = flow->next) qdisc_reset(flow->q); + DPRINTK("atm_tc_reset(sch %p,[qdisc %p])\n", sch, p); + for (flow = p->flows; flow; flow = flow->next) + qdisc_reset(flow->q); sch->q.qlen = 0; } - static void atm_tc_destroy(struct Qdisc *sch) { struct atm_qdisc_data *p = PRIV(sch); struct atm_flow_data *flow; - DPRINTK("atm_tc_destroy(sch %p,[qdisc %p])\n",sch,p); + DPRINTK("atm_tc_destroy(sch %p,[qdisc %p])\n", sch, p); /* races ? */ while ((flow = p->flows)) { tcf_destroy_chain(flow->filter_list); flow->filter_list = NULL; if (flow->ref > 1) - printk(KERN_ERR "atm_destroy: %p->ref = %d\n",flow, - flow->ref); - atm_tc_put(sch,(unsigned long) flow); + printk(KERN_ERR "atm_destroy: %p->ref = %d\n", flow, + flow->ref); + atm_tc_put(sch, (unsigned long)flow); if (p->flows == flow) { printk(KERN_ERR "atm_destroy: putting flow %p didn't " - "kill it\n",flow); - p->flows = flow->next; /* brute force */ + "kill it\n", flow); + p->flows = flow->next; /* brute force */ break; } } tasklet_kill(&p->task); } - static int atm_tc_dump_class(struct Qdisc *sch, unsigned long cl, - struct sk_buff *skb, struct tcmsg *tcm) + struct sk_buff *skb, struct tcmsg *tcm) { struct atm_qdisc_data *p = PRIV(sch); - struct atm_flow_data *flow = (struct atm_flow_data *) cl; + struct atm_flow_data *flow = (struct atm_flow_data *)cl; unsigned char *b = skb_tail_pointer(skb); struct rtattr *rta; DPRINTK("atm_tc_dump_class(sch %p,[qdisc %p],flow %p,skb %p,tcm %p)\n", - sch,p,flow,skb,tcm); - if (!find_flow(p,flow)) return -EINVAL; + sch, p, flow, skb, tcm); + if (!find_flow(p, flow)) + return -EINVAL; tcm->tcm_handle = flow->classid; tcm->tcm_info = flow->q->handle; - rta = (struct rtattr *) b; - RTA_PUT(skb,TCA_OPTIONS,0,NULL); - RTA_PUT(skb,TCA_ATM_HDR,flow->hdr_len,flow->hdr); + rta = (struct rtattr *)b; + RTA_PUT(skb, TCA_OPTIONS, 0, NULL); + RTA_PUT(skb, TCA_ATM_HDR, flow->hdr_len, flow->hdr); if (flow->vcc) { struct sockaddr_atmpvc pvc; int state; @@ -639,16 +630,16 @@ static int atm_tc_dump_class(struct Qdisc *sch, unsigned long cl, pvc.sap_addr.itf = flow->vcc->dev ? flow->vcc->dev->number : -1; pvc.sap_addr.vpi = flow->vcc->vpi; pvc.sap_addr.vci = flow->vcc->vci; - RTA_PUT(skb,TCA_ATM_ADDR,sizeof(pvc),&pvc); + RTA_PUT(skb, TCA_ATM_ADDR, sizeof(pvc), &pvc); state = ATM_VF2VS(flow->vcc->flags); - RTA_PUT(skb,TCA_ATM_STATE,sizeof(state),&state); + RTA_PUT(skb, TCA_ATM_STATE, sizeof(state), &state); } if (flow->excess) - RTA_PUT(skb,TCA_ATM_EXCESS,sizeof(u32),&flow->classid); + RTA_PUT(skb, TCA_ATM_EXCESS, sizeof(u32), &flow->classid); else { static u32 zero; - RTA_PUT(skb,TCA_ATM_EXCESS,sizeof(zero),&zero); + RTA_PUT(skb, TCA_ATM_EXCESS, sizeof(zero), &zero); } rta->rta_len = skb_tail_pointer(skb) - b; return skb->len; @@ -659,9 +650,9 @@ rtattr_failure: } static int atm_tc_dump_class_stats(struct Qdisc *sch, unsigned long arg, - struct gnet_dump *d) + struct gnet_dump *d) { - struct atm_flow_data *flow = (struct atm_flow_data *) arg; + struct atm_flow_data *flow = (struct atm_flow_data *)arg; flow->qstats.qlen = flow->q->q.qlen; @@ -678,38 +669,35 @@ static int atm_tc_dump(struct Qdisc *sch, struct sk_buff *skb) } static struct Qdisc_class_ops atm_class_ops = { - .graft = atm_tc_graft, - .leaf = atm_tc_leaf, - .get = atm_tc_get, - .put = atm_tc_put, - .change = atm_tc_change, - .delete = atm_tc_delete, - .walk = atm_tc_walk, - .tcf_chain = atm_tc_find_tcf, - .bind_tcf = atm_tc_bind_filter, - .unbind_tcf = atm_tc_put, - .dump = atm_tc_dump_class, - .dump_stats = atm_tc_dump_class_stats, + .graft = atm_tc_graft, + .leaf = atm_tc_leaf, + .get = atm_tc_get, + .put = atm_tc_put, + .change = atm_tc_change, + .delete = atm_tc_delete, + .walk = atm_tc_walk, + .tcf_chain = atm_tc_find_tcf, + .bind_tcf = atm_tc_bind_filter, + .unbind_tcf = atm_tc_put, + .dump = atm_tc_dump_class, + .dump_stats = atm_tc_dump_class_stats, }; static struct Qdisc_ops atm_qdisc_ops = { - .next = NULL, - .cl_ops = &atm_class_ops, - .id = "atm", - .priv_size = sizeof(struct atm_qdisc_data), - .enqueue = atm_tc_enqueue, - .dequeue = atm_tc_dequeue, - .requeue = atm_tc_requeue, - .drop = atm_tc_drop, - .init = atm_tc_init, - .reset = atm_tc_reset, - .destroy = atm_tc_destroy, - .change = NULL, - .dump = atm_tc_dump, - .owner = THIS_MODULE, + .cl_ops = &atm_class_ops, + .id = "atm", + .priv_size = sizeof(struct atm_qdisc_data), + .enqueue = atm_tc_enqueue, + .dequeue = atm_tc_dequeue, + .requeue = atm_tc_requeue, + .drop = atm_tc_drop, + .init = atm_tc_init, + .reset = atm_tc_reset, + .destroy = atm_tc_destroy, + .dump = atm_tc_dump, + .owner = THIS_MODULE, }; - static int __init atm_init(void) { return register_qdisc(&atm_qdisc_ops); diff --git a/net/sched/sch_blackhole.c b/net/sched/sch_blackhole.c index cb0c456aa349..f914fc43a124 100644 --- a/net/sched/sch_blackhole.c +++ b/net/sched/sch_blackhole.c @@ -14,7 +14,6 @@ #include <linux/module.h> #include <linux/types.h> #include <linux/kernel.h> -#include <linux/netdevice.h> #include <linux/skbuff.h> #include <net/pkt_sched.h> diff --git a/net/sched/sch_cbq.c b/net/sched/sch_cbq.c index ee2d5967d109..cbef3bbfc20f 100644 --- a/net/sched/sch_cbq.c +++ b/net/sched/sch_cbq.c @@ -11,28 +11,12 @@ */ #include <linux/module.h> -#include <asm/uaccess.h> -#include <asm/system.h> -#include <linux/bitops.h> #include <linux/types.h> #include <linux/kernel.h> #include <linux/string.h> -#include <linux/mm.h> -#include <linux/socket.h> -#include <linux/sockios.h> -#include <linux/in.h> #include <linux/errno.h> -#include <linux/interrupt.h> -#include <linux/if_ether.h> -#include <linux/inet.h> -#include <linux/netdevice.h> -#include <linux/etherdevice.h> -#include <linux/notifier.h> -#include <net/ip.h> -#include <net/netlink.h> -#include <net/route.h> #include <linux/skbuff.h> -#include <net/sock.h> +#include <net/netlink.h> #include <net/pkt_sched.h> @@ -98,7 +82,7 @@ struct cbq_class unsigned char priority2; /* priority to be used after overlimit */ unsigned char ewma_log; /* time constant for idle time calculation */ unsigned char ovl_strategy; -#ifdef CONFIG_NET_CLS_POLICE +#ifdef CONFIG_NET_CLS_ACT unsigned char police; #endif @@ -148,7 +132,6 @@ struct cbq_class struct gnet_stats_basic bstats; struct gnet_stats_queue qstats; struct gnet_stats_rate_est rate_est; - spinlock_t *stats_lock; struct tc_cbq_xstats xstats; struct tcf_proto *filter_list; @@ -171,7 +154,7 @@ struct cbq_sched_data struct cbq_class *active[TC_CBQ_MAXPRIO+1]; /* List of all classes with backlog */ -#ifdef CONFIG_NET_CLS_POLICE +#ifdef CONFIG_NET_CLS_ACT struct cbq_class *rx_class; #endif struct cbq_class *tx_class; @@ -213,7 +196,7 @@ cbq_class_lookup(struct cbq_sched_data *q, u32 classid) return NULL; } -#ifdef CONFIG_NET_CLS_POLICE +#ifdef CONFIG_NET_CLS_ACT static struct cbq_class * cbq_reclassify(struct sk_buff *skb, struct cbq_class *this) @@ -264,7 +247,8 @@ cbq_classify(struct sk_buff *skb, struct Qdisc *sch, int *qerr) /* * Step 2+n. Apply classifier. */ - if (!head->filter_list || (result = tc_classify(skb, head->filter_list, &res)) < 0) + if (!head->filter_list || + (result = tc_classify_compat(skb, head->filter_list, &res)) < 0) goto fallback; if ((cl = (void*)res.class) == NULL) { @@ -284,15 +268,8 @@ cbq_classify(struct sk_buff *skb, struct Qdisc *sch, int *qerr) *qerr = NET_XMIT_SUCCESS; case TC_ACT_SHOT: return NULL; - } -#elif defined(CONFIG_NET_CLS_POLICE) - switch (result) { - case TC_POLICE_RECLASSIFY: + case TC_ACT_RECLASSIFY: return cbq_reclassify(skb, cl); - case TC_POLICE_SHOT: - return NULL; - default: - break; } #endif if (cl->level == 0) @@ -403,10 +380,10 @@ cbq_enqueue(struct sk_buff *skb, struct Qdisc *sch) { struct cbq_sched_data *q = qdisc_priv(sch); int len = skb->len; - int ret; + int uninitialized_var(ret); struct cbq_class *cl = cbq_classify(skb, sch, &ret); -#ifdef CONFIG_NET_CLS_POLICE +#ifdef CONFIG_NET_CLS_ACT q->rx_class = cl; #endif if (cl == NULL) { @@ -416,7 +393,7 @@ cbq_enqueue(struct sk_buff *skb, struct Qdisc *sch) return ret; } -#ifdef CONFIG_NET_CLS_POLICE +#ifdef CONFIG_NET_CLS_ACT cl->q->__parent = sch; #endif if ((ret = cl->q->enqueue(skb, cl->q)) == NET_XMIT_SUCCESS) { @@ -451,7 +428,7 @@ cbq_requeue(struct sk_buff *skb, struct Qdisc *sch) cbq_mark_toplevel(q, cl); -#ifdef CONFIG_NET_CLS_POLICE +#ifdef CONFIG_NET_CLS_ACT q->rx_class = cl; cl->q->__parent = sch; #endif @@ -686,9 +663,7 @@ static enum hrtimer_restart cbq_undelay(struct hrtimer *timer) return HRTIMER_NORESTART; } - -#ifdef CONFIG_NET_CLS_POLICE - +#ifdef CONFIG_NET_CLS_ACT static int cbq_reshape_fail(struct sk_buff *skb, struct Qdisc *child) { int len = skb->len; @@ -1381,7 +1356,7 @@ static int cbq_set_overlimit(struct cbq_class *cl, struct tc_cbq_ovl *ovl) return 0; } -#ifdef CONFIG_NET_CLS_POLICE +#ifdef CONFIG_NET_CLS_ACT static int cbq_set_police(struct cbq_class *cl, struct tc_cbq_police *p) { cl->police = p->police; @@ -1442,7 +1417,6 @@ static int cbq_init(struct Qdisc *sch, struct rtattr *opt) q->link.ewma_log = TC_CBQ_DEF_EWMA; q->link.avpkt = q->link.allot/2; q->link.minidle = -0x7FFFFFFF; - q->link.stats_lock = &sch->dev->queue_lock; qdisc_watchdog_init(&q->watchdog, sch); hrtimer_init(&q->delay_timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS); @@ -1550,7 +1524,7 @@ rtattr_failure: return -1; } -#ifdef CONFIG_NET_CLS_POLICE +#ifdef CONFIG_NET_CLS_ACT static __inline__ int cbq_dump_police(struct sk_buff *skb, struct cbq_class *cl) { unsigned char *b = skb_tail_pointer(skb); @@ -1576,7 +1550,7 @@ static int cbq_dump_attr(struct sk_buff *skb, struct cbq_class *cl) cbq_dump_rate(skb, cl) < 0 || cbq_dump_wrr(skb, cl) < 0 || cbq_dump_ovl(skb, cl) < 0 || -#ifdef CONFIG_NET_CLS_POLICE +#ifdef CONFIG_NET_CLS_ACT cbq_dump_police(skb, cl) < 0 || #endif cbq_dump_fopt(skb, cl) < 0) @@ -1653,9 +1627,7 @@ cbq_dump_class_stats(struct Qdisc *sch, unsigned long arg, cl->xstats.undertime = cl->undertime - q->now; if (gnet_stats_copy_basic(d, &cl->bstats) < 0 || -#ifdef CONFIG_NET_ESTIMATOR gnet_stats_copy_rate_est(d, &cl->rate_est) < 0 || -#endif gnet_stats_copy_queue(d, &cl->qstats) < 0) return -1; @@ -1673,7 +1645,7 @@ static int cbq_graft(struct Qdisc *sch, unsigned long arg, struct Qdisc *new, cl->classid)) == NULL) return -ENOBUFS; } else { -#ifdef CONFIG_NET_CLS_POLICE +#ifdef CONFIG_NET_CLS_ACT if (cl->police == TC_POLICE_RECLASSIFY) new->reshape_fail = cbq_reshape_fail; #endif @@ -1726,9 +1698,7 @@ static void cbq_destroy_class(struct Qdisc *sch, struct cbq_class *cl) tcf_destroy_chain(cl->filter_list); qdisc_destroy(cl->q); qdisc_put_rtab(cl->R_tab); -#ifdef CONFIG_NET_ESTIMATOR gen_kill_estimator(&cl->bstats, &cl->rate_est); -#endif if (cl != &q->link) kfree(cl); } @@ -1740,7 +1710,7 @@ cbq_destroy(struct Qdisc* sch) struct cbq_class *cl; unsigned h; -#ifdef CONFIG_NET_CLS_POLICE +#ifdef CONFIG_NET_CLS_ACT q->rx_class = NULL; #endif /* @@ -1769,7 +1739,7 @@ static void cbq_put(struct Qdisc *sch, unsigned long arg) struct cbq_class *cl = (struct cbq_class*)arg; if (--cl->refcnt == 0) { -#ifdef CONFIG_NET_CLS_POLICE +#ifdef CONFIG_NET_CLS_ACT struct cbq_sched_data *q = qdisc_priv(sch); spin_lock_bh(&sch->dev->queue_lock); @@ -1817,7 +1787,7 @@ cbq_change_class(struct Qdisc *sch, u32 classid, u32 parentid, struct rtattr **t RTA_PAYLOAD(tb[TCA_CBQ_WRROPT-1]) < sizeof(struct tc_cbq_wrropt)) return -EINVAL; -#ifdef CONFIG_NET_CLS_POLICE +#ifdef CONFIG_NET_CLS_ACT if (tb[TCA_CBQ_POLICE-1] && RTA_PAYLOAD(tb[TCA_CBQ_POLICE-1]) < sizeof(struct tc_cbq_police)) return -EINVAL; @@ -1860,7 +1830,7 @@ cbq_change_class(struct Qdisc *sch, u32 classid, u32 parentid, struct rtattr **t if (tb[TCA_CBQ_OVL_STRATEGY-1]) cbq_set_overlimit(cl, RTA_DATA(tb[TCA_CBQ_OVL_STRATEGY-1])); -#ifdef CONFIG_NET_CLS_POLICE +#ifdef CONFIG_NET_CLS_ACT if (tb[TCA_CBQ_POLICE-1]) cbq_set_police(cl, RTA_DATA(tb[TCA_CBQ_POLICE-1])); #endif @@ -1873,11 +1843,10 @@ cbq_change_class(struct Qdisc *sch, u32 classid, u32 parentid, struct rtattr **t sch_tree_unlock(sch); -#ifdef CONFIG_NET_ESTIMATOR if (tca[TCA_RATE-1]) gen_replace_estimator(&cl->bstats, &cl->rate_est, - cl->stats_lock, tca[TCA_RATE-1]); -#endif + &sch->dev->queue_lock, + tca[TCA_RATE-1]); return 0; } @@ -1935,7 +1904,6 @@ cbq_change_class(struct Qdisc *sch, u32 classid, u32 parentid, struct rtattr **t cl->allot = parent->allot; cl->quantum = cl->allot; cl->weight = cl->R_tab->rate.rate; - cl->stats_lock = &sch->dev->queue_lock; sch_tree_lock(sch); cbq_link_class(cl); @@ -1955,7 +1923,7 @@ cbq_change_class(struct Qdisc *sch, u32 classid, u32 parentid, struct rtattr **t cl->overlimit = cbq_ovl_classic; if (tb[TCA_CBQ_OVL_STRATEGY-1]) cbq_set_overlimit(cl, RTA_DATA(tb[TCA_CBQ_OVL_STRATEGY-1])); -#ifdef CONFIG_NET_CLS_POLICE +#ifdef CONFIG_NET_CLS_ACT if (tb[TCA_CBQ_POLICE-1]) cbq_set_police(cl, RTA_DATA(tb[TCA_CBQ_POLICE-1])); #endif @@ -1963,11 +1931,9 @@ cbq_change_class(struct Qdisc *sch, u32 classid, u32 parentid, struct rtattr **t cbq_set_fopt(cl, RTA_DATA(tb[TCA_CBQ_FOPT-1])); sch_tree_unlock(sch); -#ifdef CONFIG_NET_ESTIMATOR if (tca[TCA_RATE-1]) gen_new_estimator(&cl->bstats, &cl->rate_est, - cl->stats_lock, tca[TCA_RATE-1]); -#endif + &sch->dev->queue_lock, tca[TCA_RATE-1]); *arg = (unsigned long)cl; return 0; @@ -2001,7 +1967,7 @@ static int cbq_delete(struct Qdisc *sch, unsigned long arg) q->tx_class = NULL; q->tx_borrowed = NULL; } -#ifdef CONFIG_NET_CLS_POLICE +#ifdef CONFIG_NET_CLS_ACT if (q->rx_class == cl) q->rx_class = NULL; #endif diff --git a/net/sched/sch_dsmark.c b/net/sched/sch_dsmark.c index 3c6fd181263f..60f89199e3da 100644 --- a/net/sched/sch_dsmark.c +++ b/net/sched/sch_dsmark.c @@ -9,7 +9,6 @@ #include <linux/string.h> #include <linux/errno.h> #include <linux/skbuff.h> -#include <linux/netdevice.h> /* for pkt_sched */ #include <linux/rtnetlink.h> #include <net/pkt_sched.h> #include <net/dsfield.h> @@ -238,25 +237,23 @@ static int dsmark_enqueue(struct sk_buff *skb,struct Qdisc *sch) D2PRINTK("result %d class 0x%04x\n", result, res.classid); switch (result) { -#ifdef CONFIG_NET_CLS_POLICE - case TC_POLICE_SHOT: - kfree_skb(skb); - sch->qstats.drops++; - return NET_XMIT_POLICED; -#if 0 - case TC_POLICE_RECLASSIFY: - /* FIXME: what to do here ??? */ +#ifdef CONFIG_NET_CLS_ACT + case TC_ACT_QUEUED: + case TC_ACT_STOLEN: + kfree_skb(skb); + return NET_XMIT_SUCCESS; + case TC_ACT_SHOT: + kfree_skb(skb); + sch->qstats.drops++; + return NET_XMIT_BYPASS; #endif -#endif - case TC_POLICE_OK: - skb->tc_index = TC_H_MIN(res.classid); - break; - case TC_POLICE_UNSPEC: - /* fall through */ - default: - if (p->default_index != NO_DEFAULT_INDEX) - skb->tc_index = p->default_index; - break; + case TC_ACT_OK: + skb->tc_index = TC_H_MIN(res.classid); + break; + default: + if (p->default_index != NO_DEFAULT_INDEX) + skb->tc_index = p->default_index; + break; } } diff --git a/net/sched/sch_fifo.c b/net/sched/sch_fifo.c index c2689f4ba8de..c264308f17c1 100644 --- a/net/sched/sch_fifo.c +++ b/net/sched/sch_fifo.c @@ -13,7 +13,6 @@ #include <linux/types.h> #include <linux/kernel.h> #include <linux/errno.h> -#include <linux/netdevice.h> #include <linux/skbuff.h> #include <net/pkt_sched.h> diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c index f4d34480a093..c81649cf0b9e 100644 --- a/net/sched/sch_generic.c +++ b/net/sched/sch_generic.c @@ -11,27 +11,19 @@ * - Ingress support */ -#include <asm/uaccess.h> -#include <asm/system.h> #include <linux/bitops.h> #include <linux/module.h> #include <linux/types.h> #include <linux/kernel.h> #include <linux/sched.h> #include <linux/string.h> -#include <linux/mm.h> -#include <linux/socket.h> -#include <linux/sockios.h> -#include <linux/in.h> #include <linux/errno.h> -#include <linux/interrupt.h> #include <linux/netdevice.h> #include <linux/skbuff.h> #include <linux/rtnetlink.h> #include <linux/init.h> #include <linux/rcupdate.h> #include <linux/list.h> -#include <net/sock.h> #include <net/pkt_sched.h> /* Main transmission queue. */ @@ -59,122 +51,143 @@ void qdisc_unlock_tree(struct net_device *dev) spin_unlock_bh(&dev->queue_lock); } -/* - dev->queue_lock serializes queue accesses for this device - AND dev->qdisc pointer itself. +static inline int qdisc_qlen(struct Qdisc *q) +{ + return q->q.qlen; +} - netif_tx_lock serializes accesses to device driver. +static inline int dev_requeue_skb(struct sk_buff *skb, struct net_device *dev, + struct Qdisc *q) +{ + if (unlikely(skb->next)) + dev->gso_skb = skb; + else + q->ops->requeue(skb, q); - dev->queue_lock and netif_tx_lock are mutually exclusive, - if one is grabbed, another must be free. - */ + netif_schedule(dev); + return 0; +} +static inline struct sk_buff *dev_dequeue_skb(struct net_device *dev, + struct Qdisc *q) +{ + struct sk_buff *skb; -/* Kick device. + if ((skb = dev->gso_skb)) + dev->gso_skb = NULL; + else + skb = q->dequeue(q); - Returns: 0 - queue is empty or throttled. - >0 - queue is not empty. + return skb; +} - NOTE: Called under dev->queue_lock with locally disabled BH. -*/ +static inline int handle_dev_cpu_collision(struct sk_buff *skb, + struct net_device *dev, + struct Qdisc *q) +{ + int ret; + if (unlikely(dev->xmit_lock_owner == smp_processor_id())) { + /* + * Same CPU holding the lock. It may be a transient + * configuration error, when hard_start_xmit() recurses. We + * detect it by checking xmit owner and drop the packet when + * deadloop is detected. Return OK to try the next skb. + */ + kfree_skb(skb); + if (net_ratelimit()) + printk(KERN_WARNING "Dead loop on netdevice %s, " + "fix it urgently!\n", dev->name); + ret = qdisc_qlen(q); + } else { + /* + * Another cpu is holding lock, requeue & delay xmits for + * some time. + */ + __get_cpu_var(netdev_rx_stat).cpu_collision++; + ret = dev_requeue_skb(skb, dev, q); + } + + return ret; +} + +/* + * NOTE: Called under dev->queue_lock with locally disabled BH. + * + * __LINK_STATE_QDISC_RUNNING guarantees only one CPU can process this + * device at a time. dev->queue_lock serializes queue accesses for + * this device AND dev->qdisc pointer itself. + * + * netif_tx_lock serializes accesses to device driver. + * + * dev->queue_lock and netif_tx_lock are mutually exclusive, + * if one is grabbed, another must be free. + * + * Note, that this procedure can be called by a watchdog timer + * + * Returns to the caller: + * 0 - queue is empty or throttled. + * >0 - queue is not empty. + * + */ static inline int qdisc_restart(struct net_device *dev) { struct Qdisc *q = dev->qdisc; struct sk_buff *skb; + unsigned lockless; + int ret; /* Dequeue packet */ - if (((skb = dev->gso_skb)) || ((skb = q->dequeue(q)))) { - unsigned nolock = (dev->features & NETIF_F_LLTX); + if (unlikely((skb = dev_dequeue_skb(dev, q)) == NULL)) + return 0; + + /* + * When the driver has LLTX set, it does its own locking in + * start_xmit. These checks are worth it because even uncongested + * locks can be quite expensive. The driver can do a trylock, as + * is being done here; in case of lock contention it should return + * NETDEV_TX_LOCKED and the packet will be requeued. + */ + lockless = (dev->features & NETIF_F_LLTX); - dev->gso_skb = NULL; + if (!lockless && !netif_tx_trylock(dev)) { + /* Another CPU grabbed the driver tx lock */ + return handle_dev_cpu_collision(skb, dev, q); + } - /* - * When the driver has LLTX set it does its own locking - * in start_xmit. No need to add additional overhead by - * locking again. These checks are worth it because - * even uncongested locks can be quite expensive. - * The driver can do trylock like here too, in case - * of lock congestion it should return -1 and the packet - * will be requeued. - */ - if (!nolock) { - if (!netif_tx_trylock(dev)) { - collision: - /* So, someone grabbed the driver. */ - - /* It may be transient configuration error, - when hard_start_xmit() recurses. We detect - it by checking xmit owner and drop the - packet when deadloop is detected. - */ - if (dev->xmit_lock_owner == smp_processor_id()) { - kfree_skb(skb); - if (net_ratelimit()) - printk(KERN_DEBUG "Dead loop on netdevice %s, fix it urgently!\n", dev->name); - goto out; - } - __get_cpu_var(netdev_rx_stat).cpu_collision++; - goto requeue; - } - } + /* And release queue */ + spin_unlock(&dev->queue_lock); - { - /* And release queue */ - spin_unlock(&dev->queue_lock); - - if (!netif_queue_stopped(dev)) { - int ret; - - ret = dev_hard_start_xmit(skb, dev); - if (ret == NETDEV_TX_OK) { - if (!nolock) { - netif_tx_unlock(dev); - } - spin_lock(&dev->queue_lock); - q = dev->qdisc; - goto out; - } - if (ret == NETDEV_TX_LOCKED && nolock) { - spin_lock(&dev->queue_lock); - q = dev->qdisc; - goto collision; - } - } + ret = dev_hard_start_xmit(skb, dev); - /* NETDEV_TX_BUSY - we need to requeue */ - /* Release the driver */ - if (!nolock) { - netif_tx_unlock(dev); - } - spin_lock(&dev->queue_lock); - q = dev->qdisc; - } + if (!lockless) + netif_tx_unlock(dev); - /* Device kicked us out :( - This is possible in three cases: + spin_lock(&dev->queue_lock); + q = dev->qdisc; - 0. driver is locked - 1. fastroute is enabled - 2. device cannot determine busy state - before start of transmission (f.e. dialout) - 3. device is buggy (ppp) - */ + switch (ret) { + case NETDEV_TX_OK: + /* Driver sent out skb successfully */ + ret = qdisc_qlen(q); + break; -requeue: - if (unlikely(q == &noop_qdisc)) - kfree_skb(skb); - else if (skb->next) - dev->gso_skb = skb; - else - q->ops->requeue(skb, q); - netif_schedule(dev); + case NETDEV_TX_LOCKED: + /* Driver try lock failed */ + ret = handle_dev_cpu_collision(skb, dev, q); + break; + + default: + /* 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); + + ret = dev_requeue_skb(skb, dev, q); + break; } - return 0; -out: - BUG_ON((int) q->q.qlen < 0); - return q->q.qlen; + return ret; } void __qdisc_run(struct net_device *dev) @@ -493,9 +506,7 @@ void qdisc_destroy(struct Qdisc *qdisc) return; list_del(&qdisc->list); -#ifdef CONFIG_NET_ESTIMATOR gen_kill_estimator(&qdisc->bstats, &qdisc->rate_est); -#endif if (ops->reset) ops->reset(qdisc); if (ops->destroy) diff --git a/net/sched/sch_gred.c b/net/sched/sch_gred.c index fa1b4fe7a5fd..3cc6dda02e2e 100644 --- a/net/sched/sch_gred.c +++ b/net/sched/sch_gred.c @@ -21,7 +21,6 @@ #include <linux/module.h> #include <linux/types.h> #include <linux/kernel.h> -#include <linux/netdevice.h> #include <linux/skbuff.h> #include <net/pkt_sched.h> #include <net/red.h> diff --git a/net/sched/sch_hfsc.c b/net/sched/sch_hfsc.c index 9d124c4ee3a7..55e7e4530f43 100644 --- a/net/sched/sch_hfsc.c +++ b/net/sched/sch_hfsc.c @@ -53,7 +53,6 @@ #include <linux/module.h> #include <linux/types.h> #include <linux/errno.h> -#include <linux/jiffies.h> #include <linux/compiler.h> #include <linux/spinlock.h> #include <linux/skbuff.h> @@ -62,13 +61,11 @@ #include <linux/list.h> #include <linux/rbtree.h> #include <linux/init.h> -#include <linux/netdevice.h> #include <linux/rtnetlink.h> #include <linux/pkt_sched.h> #include <net/netlink.h> #include <net/pkt_sched.h> #include <net/pkt_cls.h> -#include <asm/system.h> #include <asm/div64.h> /* @@ -122,7 +119,6 @@ struct hfsc_class struct gnet_stats_basic bstats; struct gnet_stats_queue qstats; struct gnet_stats_rate_est rate_est; - spinlock_t *stats_lock; unsigned int level; /* class level in hierarchy */ struct tcf_proto *filter_list; /* filter list */ unsigned int filter_cnt; /* filter count */ @@ -1054,11 +1050,10 @@ hfsc_change_class(struct Qdisc *sch, u32 classid, u32 parentid, } sch_tree_unlock(sch); -#ifdef CONFIG_NET_ESTIMATOR if (tca[TCA_RATE-1]) gen_replace_estimator(&cl->bstats, &cl->rate_est, - cl->stats_lock, tca[TCA_RATE-1]); -#endif + &sch->dev->queue_lock, + tca[TCA_RATE-1]); return 0; } @@ -1098,7 +1093,6 @@ hfsc_change_class(struct Qdisc *sch, u32 classid, u32 parentid, cl->qdisc = qdisc_create_dflt(sch->dev, &pfifo_qdisc_ops, classid); if (cl->qdisc == NULL) cl->qdisc = &noop_qdisc; - cl->stats_lock = &sch->dev->queue_lock; INIT_LIST_HEAD(&cl->children); cl->vt_tree = RB_ROOT; cl->cf_tree = RB_ROOT; @@ -1112,11 +1106,9 @@ hfsc_change_class(struct Qdisc *sch, u32 classid, u32 parentid, cl->cl_pcvtoff = parent->cl_cvtoff; sch_tree_unlock(sch); -#ifdef CONFIG_NET_ESTIMATOR if (tca[TCA_RATE-1]) gen_new_estimator(&cl->bstats, &cl->rate_est, - cl->stats_lock, tca[TCA_RATE-1]); -#endif + &sch->dev->queue_lock, tca[TCA_RATE-1]); *arg = (unsigned long)cl; return 0; } @@ -1128,9 +1120,7 @@ hfsc_destroy_class(struct Qdisc *sch, struct hfsc_class *cl) tcf_destroy_chain(cl->filter_list); qdisc_destroy(cl->qdisc); -#ifdef CONFIG_NET_ESTIMATOR gen_kill_estimator(&cl->bstats, &cl->rate_est); -#endif if (cl != &q->root) kfree(cl); } @@ -1184,9 +1174,6 @@ hfsc_classify(struct sk_buff *skb, struct Qdisc *sch, int *qerr) case TC_ACT_SHOT: return NULL; } -#elif defined(CONFIG_NET_CLS_POLICE) - if (result == TC_POLICE_SHOT) - return NULL; #endif if ((cl = (struct hfsc_class *)res.class) == NULL) { if ((cl = hfsc_find_class(res.classid, sch)) == NULL) @@ -1384,9 +1371,7 @@ hfsc_dump_class_stats(struct Qdisc *sch, unsigned long arg, xstats.rtwork = cl->cl_cumul; if (gnet_stats_copy_basic(d, &cl->bstats) < 0 || -#ifdef CONFIG_NET_ESTIMATOR gnet_stats_copy_rate_est(d, &cl->rate_est) < 0 || -#endif gnet_stats_copy_queue(d, &cl->qstats) < 0) return -1; @@ -1448,8 +1433,6 @@ hfsc_init_qdisc(struct Qdisc *sch, struct rtattr *opt) return -EINVAL; qopt = RTA_DATA(opt); - sch->stats_lock = &sch->dev->queue_lock; - q->defcls = qopt->defcls; for (i = 0; i < HFSC_HSIZE; i++) INIT_LIST_HEAD(&q->clhash[i]); @@ -1464,7 +1447,6 @@ hfsc_init_qdisc(struct Qdisc *sch, struct rtattr *opt) sch->handle); if (q->root.qdisc == NULL) q->root.qdisc = &noop_qdisc; - q->root.stats_lock = &sch->dev->queue_lock; INIT_LIST_HEAD(&q->root.children); q->root.vt_tree = RB_ROOT; q->root.cf_tree = RB_ROOT; diff --git a/net/sched/sch_htb.c b/net/sched/sch_htb.c index 035788c5b7f8..246a2f9765f1 100644 --- a/net/sched/sch_htb.c +++ b/net/sched/sch_htb.c @@ -28,32 +28,16 @@ * $Id: sch_htb.c,v 1.25 2003/12/07 11:08:25 devik Exp devik $ */ #include <linux/module.h> -#include <asm/uaccess.h> -#include <asm/system.h> -#include <linux/bitops.h> #include <linux/types.h> #include <linux/kernel.h> #include <linux/string.h> -#include <linux/mm.h> -#include <linux/socket.h> -#include <linux/sockios.h> -#include <linux/in.h> #include <linux/errno.h> -#include <linux/interrupt.h> -#include <linux/if_ether.h> -#include <linux/inet.h> -#include <linux/netdevice.h> -#include <linux/etherdevice.h> -#include <linux/notifier.h> -#include <net/ip.h> -#include <net/route.h> #include <linux/skbuff.h> #include <linux/list.h> #include <linux/compiler.h> +#include <linux/rbtree.h> #include <net/netlink.h> -#include <net/sock.h> #include <net/pkt_sched.h> -#include <linux/rbtree.h> /* HTB algorithm. Author: devik@cdi.cz @@ -69,8 +53,6 @@ */ #define HTB_HSIZE 16 /* classid hash size */ -#define HTB_EWMAC 2 /* rate average over HTB_EWMAC*HTB_HSIZE sec */ -#define HTB_RATECM 1 /* whether to use rate computer */ #define HTB_HYSTERESIS 1 /* whether to use mode hysteresis for speedup */ #define HTB_VER 0x30011 /* major must be matched with number suplied by TC as version */ @@ -95,12 +77,6 @@ struct htb_class { struct tc_htb_xstats xstats; /* our special stats */ int refcnt; /* usage count of this class */ -#ifdef HTB_RATECM - /* rate measurement counters */ - unsigned long rate_bytes, sum_bytes; - unsigned long rate_packets, sum_packets; -#endif - /* topology */ int level; /* our level (see above) */ struct htb_class *parent; /* parent class */ @@ -153,15 +129,12 @@ struct htb_class { /* of un.leaf originals should be done. */ }; -/* TODO: maybe compute rate when size is too large .. or drop ? */ static inline long L2T(struct htb_class *cl, struct qdisc_rate_table *rate, int size) { int slot = size >> rate->rate.cell_log; - if (slot > 255) { - cl->xstats.giants++; - slot = 255; - } + if (slot > 255) + return (rate->data[255]*(slot >> 8) + rate->data[slot & 0xFF]); return rate->data[slot]; } @@ -194,10 +167,6 @@ struct htb_sched { int rate2quantum; /* quant = rate / rate2quantum */ psched_time_t now; /* cached dequeue time */ struct qdisc_watchdog watchdog; -#ifdef HTB_RATECM - struct timer_list rttim; /* rate computer timer */ - int recmp_bucket; /* which hash bucket to recompute next */ -#endif /* non shaped skbs; let them go directly thru */ struct sk_buff_head direct_queue; @@ -280,9 +249,6 @@ static struct htb_class *htb_classify(struct sk_buff *skb, struct Qdisc *sch, case TC_ACT_SHOT: return NULL; } -#elif defined(CONFIG_NET_CLS_POLICE) - if (result == TC_POLICE_SHOT) - return HTB_DIRECT; #endif if ((cl = (void *)res.class) == NULL) { if (res.classid == sch->handle) @@ -634,13 +600,14 @@ static int htb_enqueue(struct sk_buff *skb, struct Qdisc *sch) cl->qstats.drops++; return NET_XMIT_DROP; } else { - cl->bstats.packets++; + cl->bstats.packets += + skb_is_gso(skb)?skb_shinfo(skb)->gso_segs:1; cl->bstats.bytes += skb->len; htb_activate(q, cl); } sch->q.qlen++; - sch->bstats.packets++; + sch->bstats.packets += skb_is_gso(skb)?skb_shinfo(skb)->gso_segs:1; sch->bstats.bytes += skb->len; return NET_XMIT_SUCCESS; } @@ -677,34 +644,6 @@ static int htb_requeue(struct sk_buff *skb, struct Qdisc *sch) return NET_XMIT_SUCCESS; } -#ifdef HTB_RATECM -#define RT_GEN(D,R) R+=D-(R/HTB_EWMAC);D=0 -static void htb_rate_timer(unsigned long arg) -{ - struct Qdisc *sch = (struct Qdisc *)arg; - struct htb_sched *q = qdisc_priv(sch); - struct hlist_node *p; - struct htb_class *cl; - - - /* lock queue so that we can muck with it */ - spin_lock_bh(&sch->dev->queue_lock); - - q->rttim.expires = jiffies + HZ; - add_timer(&q->rttim); - - /* scan and recompute one bucket at time */ - if (++q->recmp_bucket >= HTB_HSIZE) - q->recmp_bucket = 0; - - hlist_for_each_entry(cl,p, q->hash + q->recmp_bucket, hlist) { - RT_GEN(cl->sum_bytes, cl->rate_bytes); - RT_GEN(cl->sum_packets, cl->rate_packets); - } - spin_unlock_bh(&sch->dev->queue_lock); -} -#endif - /** * htb_charge_class - charges amount "bytes" to leaf and ancestors * @@ -717,8 +656,9 @@ static void htb_rate_timer(unsigned long arg) * In such case we remove class from event queue first. */ static void htb_charge_class(struct htb_sched *q, struct htb_class *cl, - int level, int bytes) + int level, struct sk_buff *skb) { + int bytes = skb->len; long toks, diff; enum htb_cmode old_mode; @@ -750,16 +690,12 @@ static void htb_charge_class(struct htb_sched *q, struct htb_class *cl, if (cl->cmode != HTB_CAN_SEND) htb_add_to_wait_tree(q, cl, diff); } -#ifdef HTB_RATECM - /* update rate counters */ - cl->sum_bytes += bytes; - cl->sum_packets++; -#endif /* update byte stats except for leaves which are already updated */ if (cl->level) { cl->bstats.bytes += bytes; - cl->bstats.packets++; + cl->bstats.packets += skb_is_gso(skb)? + skb_shinfo(skb)->gso_segs:1; } cl = cl->parent; } @@ -943,7 +879,7 @@ next: gives us slightly better performance */ if (!cl->un.leaf.q->q.qlen) htb_deactivate(q, cl); - htb_charge_class(q, cl, level, skb->len); + htb_charge_class(q, cl, level, skb); } return skb; } @@ -1095,13 +1031,6 @@ static int htb_init(struct Qdisc *sch, struct rtattr *opt) if (q->direct_qlen < 2) /* some devices have zero tx_queue_len */ q->direct_qlen = 2; -#ifdef HTB_RATECM - init_timer(&q->rttim); - q->rttim.function = htb_rate_timer; - q->rttim.data = (unsigned long)sch; - q->rttim.expires = jiffies + HZ; - add_timer(&q->rttim); -#endif if ((q->rate2quantum = gopt->rate2quantum) < 1) q->rate2quantum = 1; q->defcls = gopt->defcls; @@ -1175,11 +1104,6 @@ htb_dump_class_stats(struct Qdisc *sch, unsigned long arg, struct gnet_dump *d) { struct htb_class *cl = (struct htb_class *)arg; -#ifdef HTB_RATECM - cl->rate_est.bps = cl->rate_bytes / (HTB_EWMAC * HTB_HSIZE); - cl->rate_est.pps = cl->rate_packets / (HTB_EWMAC * HTB_HSIZE); -#endif - if (!cl->level && cl->un.leaf.q) cl->qstats.qlen = cl->un.leaf.q->q.qlen; cl->xstats.tokens = cl->tokens; @@ -1277,6 +1201,7 @@ static void htb_destroy_class(struct Qdisc *sch, struct htb_class *cl) BUG_TRAP(cl->un.leaf.q); qdisc_destroy(cl->un.leaf.q); } + gen_kill_estimator(&cl->bstats, &cl->rate_est); qdisc_put_rtab(cl->rate); qdisc_put_rtab(cl->ceil); @@ -1305,9 +1230,6 @@ static void htb_destroy(struct Qdisc *sch) struct htb_sched *q = qdisc_priv(sch); qdisc_watchdog_cancel(&q->watchdog); -#ifdef HTB_RATECM - del_timer_sync(&q->rttim); -#endif /* 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 @@ -1403,6 +1325,20 @@ static int htb_change_class(struct Qdisc *sch, u32 classid, if (!cl) { /* new class */ struct Qdisc *new_q; int prio; + struct { + struct rtattr rta; + struct gnet_estimator opt; + } est = { + .rta = { + .rta_len = RTA_LENGTH(sizeof(est.opt)), + .rta_type = TCA_RATE, + }, + .opt = { + /* 4s interval, 16s averaging constant */ + .interval = 2, + .ewma_log = 2, + }, + }; /* check for valid classid */ if (!classid || TC_H_MAJ(classid ^ sch->handle) @@ -1418,6 +1354,9 @@ static int htb_change_class(struct Qdisc *sch, u32 classid, if ((cl = kzalloc(sizeof(*cl), GFP_KERNEL)) == NULL) goto failure; + gen_new_estimator(&cl->bstats, &cl->rate_est, + &sch->dev->queue_lock, + tca[TCA_RATE-1] ? : &est.rta); cl->refcnt = 1; INIT_LIST_HEAD(&cl->sibling); INIT_HLIST_NODE(&cl->hlist); @@ -1469,8 +1408,13 @@ static int htb_change_class(struct Qdisc *sch, u32 classid, hlist_add_head(&cl->hlist, q->hash + htb_hash(classid)); list_add_tail(&cl->sibling, parent ? &parent->children : &q->root); - } else + } else { + if (tca[TCA_RATE-1]) + gen_replace_estimator(&cl->bstats, &cl->rate_est, + &sch->dev->queue_lock, + tca[TCA_RATE-1]); sch_tree_lock(sch); + } /* it used to be a nasty bug here, we have to check that node is really leaf before changing cl->un.leaf ! */ diff --git a/net/sched/sch_ingress.c b/net/sched/sch_ingress.c index f8b9f1cdf738..2d32fd27496e 100644 --- a/net/sched/sch_ingress.c +++ b/net/sched/sch_ingress.c @@ -9,21 +9,14 @@ #include <linux/module.h> #include <linux/types.h> +#include <linux/list.h> #include <linux/skbuff.h> -#include <linux/netdevice.h> #include <linux/rtnetlink.h> #include <linux/netfilter_ipv4.h> #include <linux/netfilter_ipv6.h> #include <linux/netfilter.h> -#include <linux/smp.h> #include <net/netlink.h> #include <net/pkt_sched.h> -#include <asm/byteorder.h> -#include <asm/uaccess.h> -#include <linux/kmod.h> -#include <linux/stat.h> -#include <linux/interrupt.h> -#include <linux/list.h> #undef DEBUG_INGRESS @@ -165,37 +158,17 @@ static int ingress_enqueue(struct sk_buff *skb,struct Qdisc *sch) break; case TC_ACT_RECLASSIFY: case TC_ACT_OK: - case TC_ACT_UNSPEC: - default: skb->tc_index = TC_H_MIN(res.classid); + default: result = TC_ACT_OK; break; } -/* backward compat */ -#else -#ifdef CONFIG_NET_CLS_POLICE - switch (result) { - case TC_POLICE_SHOT: - result = NF_DROP; - sch->qstats.drops++; - break; - case TC_POLICE_RECLASSIFY: /* DSCP remarking here ? */ - case TC_POLICE_OK: - case TC_POLICE_UNSPEC: - default: - sch->bstats.packets++; - sch->bstats.bytes += skb->len; - result = NF_ACCEPT; - break; - } - #else D2PRINTK("Overriding result to ACCEPT\n"); result = NF_ACCEPT; sch->bstats.packets++; sch->bstats.bytes += skb->len; #endif -#endif return result; } diff --git a/net/sched/sch_netem.c b/net/sched/sch_netem.c index 5d9d8bc9cc3a..9e5e87e81f00 100644 --- a/net/sched/sch_netem.c +++ b/net/sched/sch_netem.c @@ -14,11 +14,9 @@ */ #include <linux/module.h> -#include <linux/bitops.h> #include <linux/types.h> #include <linux/kernel.h> #include <linux/errno.h> -#include <linux/netdevice.h> #include <linux/skbuff.h> #include <linux/rtnetlink.h> diff --git a/net/sched/sch_prio.c b/net/sched/sch_prio.c index 6d7542c26e47..abd82fc3ec60 100644 --- a/net/sched/sch_prio.c +++ b/net/sched/sch_prio.c @@ -12,37 +12,23 @@ */ #include <linux/module.h> -#include <asm/uaccess.h> -#include <asm/system.h> -#include <linux/bitops.h> #include <linux/types.h> #include <linux/kernel.h> #include <linux/string.h> -#include <linux/mm.h> -#include <linux/socket.h> -#include <linux/sockios.h> -#include <linux/in.h> #include <linux/errno.h> -#include <linux/interrupt.h> -#include <linux/if_ether.h> -#include <linux/inet.h> -#include <linux/netdevice.h> -#include <linux/etherdevice.h> -#include <linux/notifier.h> -#include <net/ip.h> -#include <net/route.h> #include <linux/skbuff.h> #include <net/netlink.h> -#include <net/sock.h> #include <net/pkt_sched.h> struct prio_sched_data { int bands; + int curband; /* for round-robin */ struct tcf_proto *filter_list; u8 prio2band[TC_PRIO_MAX+1]; struct Qdisc *queues[TCQ_PRIO_BANDS]; + int mq; }; @@ -52,32 +38,34 @@ prio_classify(struct sk_buff *skb, struct Qdisc *sch, int *qerr) struct prio_sched_data *q = qdisc_priv(sch); u32 band = skb->priority; struct tcf_result res; + int err; *qerr = NET_XMIT_BYPASS; if (TC_H_MAJ(skb->priority) != sch->handle) { + err = tc_classify(skb, q->filter_list, &res); #ifdef CONFIG_NET_CLS_ACT - switch (tc_classify(skb, q->filter_list, &res)) { + switch (err) { case TC_ACT_STOLEN: case TC_ACT_QUEUED: *qerr = NET_XMIT_SUCCESS; case TC_ACT_SHOT: return NULL; } - - if (!q->filter_list ) { -#else - if (!q->filter_list || tc_classify(skb, q->filter_list, &res)) { #endif + if (!q->filter_list || err < 0) { if (TC_H_MAJ(band)) band = 0; - return q->queues[q->prio2band[band&TC_PRIO_MAX]]; + band = q->prio2band[band&TC_PRIO_MAX]; + goto out; } band = res.classid; } band = TC_H_MIN(band) - 1; if (band >= q->bands) - return q->queues[q->prio2band[0]]; - + band = q->prio2band[0]; +out: + if (q->mq) + skb_set_queue_mapping(skb, band); return q->queues[band]; } @@ -144,17 +132,58 @@ prio_dequeue(struct Qdisc* sch) struct Qdisc *qdisc; for (prio = 0; prio < q->bands; prio++) { - qdisc = q->queues[prio]; - skb = qdisc->dequeue(qdisc); - if (skb) { - sch->q.qlen--; - return skb; + /* Check if the target subqueue is available before + * pulling an skb. This way we avoid excessive requeues + * for slower queues. + */ + if (!netif_subqueue_stopped(sch->dev, (q->mq ? prio : 0))) { + qdisc = q->queues[prio]; + skb = qdisc->dequeue(qdisc); + if (skb) { + sch->q.qlen--; + return skb; + } } } return NULL; } +static struct sk_buff *rr_dequeue(struct Qdisc* sch) +{ + struct sk_buff *skb; + struct prio_sched_data *q = qdisc_priv(sch); + struct Qdisc *qdisc; + int bandcount; + + /* Only take one pass through the queues. If nothing is available, + * return nothing. + */ + for (bandcount = 0; bandcount < q->bands; bandcount++) { + /* Check if the target subqueue is available before + * pulling an skb. This way we avoid excessive requeues + * for slower queues. If the queue is stopped, try the + * next queue. + */ + if (!netif_subqueue_stopped(sch->dev, + (q->mq ? q->curband : 0))) { + qdisc = q->queues[q->curband]; + skb = qdisc->dequeue(qdisc); + if (skb) { + sch->q.qlen--; + q->curband++; + if (q->curband >= q->bands) + q->curband = 0; + return skb; + } + } + q->curband++; + if (q->curband >= q->bands) + q->curband = 0; + } + return NULL; +} + static unsigned int prio_drop(struct Qdisc* sch) { struct prio_sched_data *q = qdisc_priv(sch); @@ -198,21 +227,43 @@ prio_destroy(struct Qdisc* sch) static int prio_tune(struct Qdisc *sch, struct rtattr *opt) { struct prio_sched_data *q = qdisc_priv(sch); - struct tc_prio_qopt *qopt = RTA_DATA(opt); + struct tc_prio_qopt *qopt; + struct rtattr *tb[TCA_PRIO_MAX]; int i; - if (opt->rta_len < RTA_LENGTH(sizeof(*qopt))) + if (rtattr_parse_nested_compat(tb, TCA_PRIO_MAX, opt, qopt, + sizeof(*qopt))) return -EINVAL; - if (qopt->bands > TCQ_PRIO_BANDS || qopt->bands < 2) + q->bands = qopt->bands; + /* If we're multiqueue, make sure the number of incoming bands + * matches the number of queues on the device we're associating with. + * If the number of bands requested is zero, then set q->bands to + * dev->egress_subqueue_count. Also, the root qdisc must be the + * only one that is enabled for multiqueue, since it's the only one + * that interacts with the underlying device. + */ + q->mq = RTA_GET_FLAG(tb[TCA_PRIO_MQ - 1]); + if (q->mq) { + if (sch->parent != TC_H_ROOT) + return -EINVAL; + if (netif_is_multiqueue(sch->dev)) { + if (q->bands == 0) + q->bands = sch->dev->egress_subqueue_count; + else if (q->bands != sch->dev->egress_subqueue_count) + return -EINVAL; + } else + return -EOPNOTSUPP; + } + + if (q->bands > TCQ_PRIO_BANDS || q->bands < 2) return -EINVAL; for (i=0; i<=TC_PRIO_MAX; i++) { - if (qopt->priomap[i] >= qopt->bands) + if (qopt->priomap[i] >= q->bands) return -EINVAL; } sch_tree_lock(sch); - q->bands = qopt->bands; memcpy(q->prio2band, qopt->priomap, TC_PRIO_MAX+1); for (i=q->bands; i<TCQ_PRIO_BANDS; i++) { @@ -268,11 +319,17 @@ static int prio_dump(struct Qdisc *sch, struct sk_buff *skb) { struct prio_sched_data *q = qdisc_priv(sch); unsigned char *b = skb_tail_pointer(skb); + struct rtattr *nest; struct tc_prio_qopt opt; opt.bands = q->bands; memcpy(&opt.priomap, q->prio2band, TC_PRIO_MAX+1); - RTA_PUT(skb, TCA_OPTIONS, sizeof(opt), &opt); + + nest = RTA_NEST_COMPAT(skb, TCA_OPTIONS, sizeof(opt), &opt); + if (q->mq) + RTA_PUT_FLAG(skb, TCA_PRIO_MQ); + RTA_NEST_COMPAT_END(skb, nest); + return skb->len; rtattr_failure: @@ -443,17 +500,44 @@ static struct Qdisc_ops prio_qdisc_ops = { .owner = THIS_MODULE, }; +static struct Qdisc_ops rr_qdisc_ops = { + .next = NULL, + .cl_ops = &prio_class_ops, + .id = "rr", + .priv_size = sizeof(struct prio_sched_data), + .enqueue = prio_enqueue, + .dequeue = rr_dequeue, + .requeue = prio_requeue, + .drop = prio_drop, + .init = prio_init, + .reset = prio_reset, + .destroy = prio_destroy, + .change = prio_tune, + .dump = prio_dump, + .owner = THIS_MODULE, +}; + static int __init prio_module_init(void) { - return register_qdisc(&prio_qdisc_ops); + int err; + + err = register_qdisc(&prio_qdisc_ops); + if (err < 0) + return err; + err = register_qdisc(&rr_qdisc_ops); + if (err < 0) + unregister_qdisc(&prio_qdisc_ops); + return err; } static void __exit prio_module_exit(void) { unregister_qdisc(&prio_qdisc_ops); + unregister_qdisc(&rr_qdisc_ops); } module_init(prio_module_init) module_exit(prio_module_exit) MODULE_LICENSE("GPL"); +MODULE_ALIAS("sch_rr"); diff --git a/net/sched/sch_red.c b/net/sched/sch_red.c index 00db53eb8159..9b95fefb70f4 100644 --- a/net/sched/sch_red.c +++ b/net/sched/sch_red.c @@ -17,7 +17,6 @@ #include <linux/module.h> #include <linux/types.h> #include <linux/kernel.h> -#include <linux/netdevice.h> #include <linux/skbuff.h> #include <net/pkt_sched.h> #include <net/inet_ecn.h> diff --git a/net/sched/sch_sfq.c b/net/sched/sch_sfq.c index 96dfdf78d32c..b542c875e154 100644 --- a/net/sched/sch_sfq.c +++ b/net/sched/sch_sfq.c @@ -10,31 +10,18 @@ */ #include <linux/module.h> -#include <asm/uaccess.h> -#include <asm/system.h> -#include <linux/bitops.h> #include <linux/types.h> #include <linux/kernel.h> #include <linux/jiffies.h> #include <linux/string.h> -#include <linux/mm.h> -#include <linux/socket.h> -#include <linux/sockios.h> #include <linux/in.h> #include <linux/errno.h> -#include <linux/interrupt.h> -#include <linux/if_ether.h> -#include <linux/inet.h> -#include <linux/netdevice.h> -#include <linux/etherdevice.h> -#include <linux/notifier.h> #include <linux/init.h> -#include <net/ip.h> -#include <net/netlink.h> #include <linux/ipv6.h> -#include <net/route.h> #include <linux/skbuff.h> -#include <net/sock.h> +#include <linux/jhash.h> +#include <net/ip.h> +#include <net/netlink.h> #include <net/pkt_sched.h> @@ -109,7 +96,7 @@ struct sfq_sched_data /* Variables */ struct timer_list perturb_timer; - int perturbation; + u32 perturbation; sfq_index tail; /* Index of current slot in round */ sfq_index max_depth; /* Maximal depth */ @@ -123,12 +110,7 @@ struct sfq_sched_data static __inline__ unsigned sfq_fold_hash(struct sfq_sched_data *q, u32 h, u32 h1) { - int pert = q->perturbation; - - /* Have we any rotation primitives? If not, WHY? */ - h ^= (h1<<pert) ^ (h1>>(0x1F - pert)); - h ^= h>>10; - return h & 0x3FF; + return jhash_2words(h, h1, q->perturbation) & (SFQ_HASH_DIVISOR - 1); } static unsigned sfq_hash(struct sfq_sched_data *q, struct sk_buff *skb) @@ -270,6 +252,13 @@ sfq_enqueue(struct sk_buff *skb, struct Qdisc* sch) q->ht[hash] = x = q->dep[SFQ_DEPTH].next; q->hash[x] = hash; } + /* If selected queue has length q->limit, this means that + * all another queues are empty and that we do simple tail drop, + * i.e. drop _this_ packet. + */ + if (q->qs[x].qlen >= q->limit) + return qdisc_drop(skb, sch); + sch->qstats.backlog += skb->len; __skb_queue_tail(&q->qs[x], skb); sfq_inc(q, x); @@ -284,7 +273,7 @@ sfq_enqueue(struct sk_buff *skb, struct Qdisc* sch) q->tail = x; } } - if (++sch->q.qlen < q->limit-1) { + if (++sch->q.qlen <= q->limit) { sch->bstats.bytes += skb->len; sch->bstats.packets++; return 0; @@ -308,6 +297,19 @@ sfq_requeue(struct sk_buff *skb, struct Qdisc* sch) } sch->qstats.backlog += skb->len; __skb_queue_head(&q->qs[x], skb); + /* If selected queue has length q->limit+1, this means that + * all another queues are empty and we do simple tail drop. + * This packet is still requeued at head of queue, tail packet + * is dropped. + */ + if (q->qs[x].qlen > q->limit) { + skb = q->qs[x].prev; + __skb_unlink(skb, &q->qs[x]); + sch->qstats.drops++; + sch->qstats.backlog -= skb->len; + kfree_skb(skb); + return NET_XMIT_CN; + } sfq_inc(q, x); if (q->qs[x].qlen == 1) { /* The flow is new */ if (q->tail == SFQ_DEPTH) { /* It is the first flow */ @@ -320,7 +322,7 @@ sfq_requeue(struct sk_buff *skb, struct Qdisc* sch) q->tail = x; } } - if (++sch->q.qlen < q->limit - 1) { + if (++sch->q.qlen <= q->limit) { sch->qstats.requeues++; return 0; } @@ -384,12 +386,10 @@ static void sfq_perturbation(unsigned long arg) struct Qdisc *sch = (struct Qdisc*)arg; struct sfq_sched_data *q = qdisc_priv(sch); - q->perturbation = net_random()&0x1F; + get_random_bytes(&q->perturbation, 4); - if (q->perturb_period) { - q->perturb_timer.expires = jiffies + q->perturb_period; - add_timer(&q->perturb_timer); - } + if (q->perturb_period) + mod_timer(&q->perturb_timer, jiffies + q->perturb_period); } static int sfq_change(struct Qdisc *sch, struct rtattr *opt) @@ -405,17 +405,17 @@ static int sfq_change(struct Qdisc *sch, struct rtattr *opt) q->quantum = ctl->quantum ? : psched_mtu(sch->dev); q->perturb_period = ctl->perturb_period*HZ; if (ctl->limit) - q->limit = min_t(u32, ctl->limit, SFQ_DEPTH); + q->limit = min_t(u32, ctl->limit, SFQ_DEPTH - 1); qlen = sch->q.qlen; - while (sch->q.qlen >= q->limit-1) + while (sch->q.qlen > q->limit) sfq_drop(sch); qdisc_tree_decrease_qlen(sch, qlen - sch->q.qlen); del_timer(&q->perturb_timer); if (q->perturb_period) { - q->perturb_timer.expires = jiffies + q->perturb_period; - add_timer(&q->perturb_timer); + mod_timer(&q->perturb_timer, jiffies + q->perturb_period); + get_random_bytes(&q->perturbation, 4); } sch_tree_unlock(sch); return 0; @@ -437,12 +437,13 @@ static int sfq_init(struct Qdisc *sch, struct rtattr *opt) q->dep[i+SFQ_DEPTH].next = i+SFQ_DEPTH; q->dep[i+SFQ_DEPTH].prev = i+SFQ_DEPTH; } - q->limit = SFQ_DEPTH; + q->limit = SFQ_DEPTH - 1; q->max_depth = 0; q->tail = SFQ_DEPTH; if (opt == NULL) { q->quantum = psched_mtu(sch->dev); q->perturb_period = 0; + get_random_bytes(&q->perturbation, 4); } else { int err = sfq_change(sch, opt); if (err) diff --git a/net/sched/sch_tbf.c b/net/sched/sch_tbf.c index 53862953baaf..8c2639af4c6a 100644 --- a/net/sched/sch_tbf.c +++ b/net/sched/sch_tbf.c @@ -13,29 +13,12 @@ */ #include <linux/module.h> -#include <asm/uaccess.h> -#include <asm/system.h> -#include <linux/bitops.h> #include <linux/types.h> #include <linux/kernel.h> -#include <linux/jiffies.h> #include <linux/string.h> -#include <linux/mm.h> -#include <linux/socket.h> -#include <linux/sockios.h> -#include <linux/in.h> #include <linux/errno.h> -#include <linux/interrupt.h> -#include <linux/if_ether.h> -#include <linux/inet.h> -#include <linux/netdevice.h> -#include <linux/etherdevice.h> -#include <linux/notifier.h> -#include <net/ip.h> -#include <net/netlink.h> -#include <net/route.h> #include <linux/skbuff.h> -#include <net/sock.h> +#include <net/netlink.h> #include <net/pkt_sched.h> @@ -142,7 +125,7 @@ static int tbf_enqueue(struct sk_buff *skb, struct Qdisc* sch) if (skb->len > q->max_size) { sch->qstats.drops++; -#ifdef CONFIG_NET_CLS_POLICE +#ifdef CONFIG_NET_CLS_ACT if (sch->reshape_fail == NULL || sch->reshape_fail(skb, sch)) #endif kfree_skb(skb); diff --git a/net/sched/sch_teql.c b/net/sched/sch_teql.c index f05ad9a30b4c..0968184ea6be 100644 --- a/net/sched/sch_teql.c +++ b/net/sched/sch_teql.c @@ -9,30 +9,17 @@ */ #include <linux/module.h> -#include <asm/uaccess.h> -#include <asm/system.h> -#include <linux/bitops.h> #include <linux/types.h> #include <linux/kernel.h> #include <linux/string.h> -#include <linux/mm.h> -#include <linux/socket.h> -#include <linux/sockios.h> -#include <linux/in.h> #include <linux/errno.h> -#include <linux/interrupt.h> #include <linux/if_arp.h> -#include <linux/if_ether.h> -#include <linux/inet.h> #include <linux/netdevice.h> -#include <linux/etherdevice.h> -#include <linux/notifier.h> #include <linux/init.h> -#include <net/ip.h> -#include <net/route.h> #include <linux/skbuff.h> #include <linux/moduleparam.h> -#include <net/sock.h> +#include <net/dst.h> +#include <net/neighbour.h> #include <net/pkt_sched.h> /* @@ -225,7 +212,6 @@ static int teql_qdisc_init(struct Qdisc *sch, struct rtattr *opt) return 0; } -/* "teql*" netdevice routines */ static int __teql_resolve(struct sk_buff *skb, struct sk_buff *skb_res, struct net_device *dev) @@ -277,6 +263,7 @@ static int teql_master_xmit(struct sk_buff *skb, struct net_device *dev) int busy; int nores; int len = skb->len; + int subq = skb->queue_mapping; struct sk_buff *skb_res = NULL; start = master->slaves; @@ -293,7 +280,9 @@ restart: if (slave->qdisc_sleeping != q) continue; - if (netif_queue_stopped(slave) || ! netif_running(slave)) { + if (netif_queue_stopped(slave) || + netif_subqueue_stopped(slave, subq) || + !netif_running(slave)) { busy = 1; continue; } @@ -302,6 +291,7 @@ restart: case 0: if (netif_tx_trylock(slave)) { if (!netif_queue_stopped(slave) && + !netif_subqueue_stopped(slave, subq) && slave->hard_start_xmit(skb, slave) == 0) { netif_tx_unlock(slave); master->slaves = NEXT_SLAVE(q); |