diff options
Diffstat (limited to 'net/sched')
-rw-r--r-- | net/sched/Kconfig | 50 | ||||
-rw-r--r-- | net/sched/Makefile | 3 | ||||
-rw-r--r-- | net/sched/act_api.c | 21 | ||||
-rw-r--r-- | net/sched/cls_api.c | 7 | ||||
-rw-r--r-- | net/sched/cls_rsvp.h | 1 | ||||
-rw-r--r-- | net/sched/em_meta.c | 68 | ||||
-rw-r--r-- | net/sched/em_text.c | 154 | ||||
-rw-r--r-- | net/sched/sch_api.c | 75 | ||||
-rw-r--r-- | net/sched/sch_blackhole.c | 54 | ||||
-rw-r--r-- | net/sched/sch_cbq.c | 3 | ||||
-rw-r--r-- | net/sched/sch_dsmark.c | 357 | ||||
-rw-r--r-- | net/sched/sch_fifo.c | 152 | ||||
-rw-r--r-- | net/sched/sch_generic.c | 122 | ||||
-rw-r--r-- | net/sched/sch_red.c | 2 |
14 files changed, 605 insertions, 464 deletions
diff --git a/net/sched/Kconfig b/net/sched/Kconfig index b22c9beb604d..59d3e71f8b85 100644 --- a/net/sched/Kconfig +++ b/net/sched/Kconfig @@ -1,6 +1,43 @@ # # Traffic control configuration. # + +menuconfig NET_SCHED + bool "QoS and/or fair queueing" + ---help--- + When the kernel has several packets to send out over a network + device, it has to decide which ones to send first, which ones to + delay, and which ones to drop. This is the job of the packet + scheduler, and several different algorithms for how to do this + "fairly" have been proposed. + + If you say N here, you will get the standard packet scheduler, which + is a FIFO (first come, first served). If you say Y here, you will be + able to choose from among several alternative algorithms which can + then be attached to different network devices. This is useful for + example if some of your network devices are real time devices that + need a certain minimum data flow rate, or if you need to limit the + maximum data flow rate for traffic which matches specified criteria. + This code is considered to be experimental. + + To administer these schedulers, you'll need the user-level utilities + from the package iproute2+tc at <ftp://ftp.tux.org/pub/net/ip-routing/>. + That package also contains some documentation; for more, check out + <http://snafu.freedom.org/linux2.2/iproute-notes.html>. + + This Quality of Service (QoS) support will enable you to use + Differentiated Services (diffserv) and Resource Reservation Protocol + (RSVP) on your Linux router if you also say Y to "QoS support", + "Packet classifier API" and to some classifiers below. Documentation + and software is at <http://diffserv.sourceforge.net/>. + + If you say Y here and to "/proc file system" below, you will be able + to read status information about packet schedulers from the file + /proc/net/psched. + + The available schedulers are listed in the following questions; you + can say Y to as many as you like. If unsure, say N now. + choice prompt "Packet scheduler clock source" depends on NET_SCHED @@ -449,6 +486,19 @@ config NET_EMATCH_META To compile this code as a module, choose M here: the module will be called em_meta. +config NET_EMATCH_TEXT + tristate "Textsearch" + depends on NET_EMATCH + select TEXTSEARCH + select TEXTSEARCH_KMP + select TEXTSEARCH_FSM + ---help--- + Say Y here if you want to be ablt to classify packets based on + textsearch comparisons. + + To compile this code as a module, choose M here: the + module will be called em_text. + config NET_CLS_ACT bool "Packet ACTION" depends on EXPERIMENTAL && NET_CLS && NET_QOS diff --git a/net/sched/Makefile b/net/sched/Makefile index eb3fe583eba8..e48d0d456b3e 100644 --- a/net/sched/Makefile +++ b/net/sched/Makefile @@ -4,7 +4,7 @@ obj-y := sch_generic.o -obj-$(CONFIG_NET_SCHED) += sch_api.o sch_fifo.o +obj-$(CONFIG_NET_SCHED) += sch_api.o sch_fifo.o sch_blackhole.o obj-$(CONFIG_NET_CLS) += cls_api.o obj-$(CONFIG_NET_CLS_ACT) += act_api.o obj-$(CONFIG_NET_ACT_POLICE) += police.o @@ -40,3 +40,4 @@ obj-$(CONFIG_NET_EMATCH_CMP) += em_cmp.o obj-$(CONFIG_NET_EMATCH_NBYTE) += em_nbyte.o obj-$(CONFIG_NET_EMATCH_U32) += em_u32.o obj-$(CONFIG_NET_EMATCH_META) += em_meta.o +obj-$(CONFIG_NET_EMATCH_TEXT) += em_text.o diff --git a/net/sched/act_api.c b/net/sched/act_api.c index 914c85ff8fe6..249c61936ea0 100644 --- a/net/sched/act_api.c +++ b/net/sched/act_api.c @@ -428,17 +428,19 @@ errout: static int tca_get_fill(struct sk_buff *skb, struct tc_action *a, u32 pid, u32 seq, - unsigned flags, int event, int bind, int ref) + u16 flags, int event, int bind, int ref) { struct tcamsg *t; struct nlmsghdr *nlh; unsigned char *b = skb->tail; struct rtattr *x; - nlh = NLMSG_PUT(skb, pid, seq, event, sizeof(*t)); - nlh->nlmsg_flags = flags; + nlh = NLMSG_NEW(skb, pid, seq, event, sizeof(*t), flags); + t = NLMSG_DATA(nlh); t->tca_family = AF_UNSPEC; + t->tca__pad1 = 0; + t->tca__pad2 = 0; x = (struct rtattr*) skb->tail; RTA_PUT(skb, TCA_ACT_TAB, 0, NULL); @@ -580,6 +582,8 @@ static int tca_action_flush(struct rtattr *rta, struct nlmsghdr *n, u32 pid) nlh = NLMSG_PUT(skb, pid, n->nlmsg_seq, RTM_DELACTION, sizeof(*t)); t = NLMSG_DATA(nlh); t->tca_family = AF_UNSPEC; + t->tca__pad1 = 0; + t->tca__pad2 = 0; x = (struct rtattr *) skb->tail; RTA_PUT(skb, TCA_ACT_TAB, 0, NULL); @@ -669,7 +673,7 @@ err: } static int tcf_add_notify(struct tc_action *a, u32 pid, u32 seq, int event, - unsigned flags) + u16 flags) { struct tcamsg *t; struct nlmsghdr *nlh; @@ -684,11 +688,12 @@ static int tcf_add_notify(struct tc_action *a, u32 pid, u32 seq, int event, b = (unsigned char *)skb->tail; - nlh = NLMSG_PUT(skb, pid, seq, event, sizeof(*t)); - nlh->nlmsg_flags = flags; + nlh = NLMSG_NEW(skb, pid, seq, event, sizeof(*t), flags); t = NLMSG_DATA(nlh); t->tca_family = AF_UNSPEC; - + t->tca__pad1 = 0; + t->tca__pad2 = 0; + x = (struct rtattr*) skb->tail; RTA_PUT(skb, TCA_ACT_TAB, 0, NULL); @@ -843,6 +848,8 @@ tc_dump_action(struct sk_buff *skb, struct netlink_callback *cb) cb->nlh->nlmsg_type, sizeof(*t)); t = NLMSG_DATA(nlh); t->tca_family = AF_UNSPEC; + t->tca__pad1 = 0; + t->tca__pad2 = 0; x = (struct rtattr *) skb->tail; RTA_PUT(skb, TCA_ACT_TAB, 0, NULL); diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c index 56e66c3fe0fa..3b5714ef4d1a 100644 --- a/net/sched/cls_api.c +++ b/net/sched/cls_api.c @@ -322,16 +322,17 @@ errout: static int tcf_fill_node(struct sk_buff *skb, struct tcf_proto *tp, unsigned long fh, - u32 pid, u32 seq, unsigned flags, int event) + u32 pid, u32 seq, u16 flags, int event) { struct tcmsg *tcm; struct nlmsghdr *nlh; unsigned char *b = skb->tail; - nlh = NLMSG_PUT(skb, pid, seq, event, sizeof(*tcm)); - nlh->nlmsg_flags = flags; + nlh = NLMSG_NEW(skb, pid, seq, event, sizeof(*tcm), flags); tcm = NLMSG_DATA(nlh); tcm->tcm_family = AF_UNSPEC; + tcm->tcm__pad1 = 0; + tcm->tcm__pad1 = 0; tcm->tcm_ifindex = tp->q->dev->ifindex; tcm->tcm_parent = tp->classid; tcm->tcm_info = TC_H_MAKE(tp->prio, tp->protocol); diff --git a/net/sched/cls_rsvp.h b/net/sched/cls_rsvp.h index 232fb9196810..006168d69376 100644 --- a/net/sched/cls_rsvp.h +++ b/net/sched/cls_rsvp.h @@ -618,6 +618,7 @@ static int rsvp_dump(struct tcf_proto *tp, unsigned long fh, pinfo.protocol = s->protocol; pinfo.tunnelid = s->tunnelid; pinfo.tunnelhdr = f->tunnelhdr; + pinfo.pad = 0; RTA_PUT(skb, TCA_RSVP_PINFO, sizeof(pinfo), &pinfo); if (f->res.classid) RTA_PUT(skb, TCA_RSVP_CLASSID, 4, &f->res.classid); diff --git a/net/sched/em_meta.c b/net/sched/em_meta.c index 48bb23c2a35a..00eae5f9a01a 100644 --- a/net/sched/em_meta.c +++ b/net/sched/em_meta.c @@ -27,17 +27,17 @@ * lvalue rvalue * +-----------+ +-----------+ * | type: INT | | type: INT | - * def | id: INDEV | | id: VALUE | + * def | id: DEV | | id: VALUE | * | data: | | data: 3 | * +-----------+ +-----------+ * | | - * ---> meta_ops[INT][INDEV](...) | + * ---> meta_ops[INT][DEV](...) | * | | * ----------- | * V V * +-----------+ +-----------+ * | type: INT | | type: INT | - * obj | id: INDEV | | id: VALUE | + * obj | id: DEV | | id: VALUE | * | data: 2 |<--data got filled out | data: 3 | * +-----------+ +-----------+ * | | @@ -170,26 +170,6 @@ META_COLLECTOR(var_dev) *err = var_dev(skb->dev, dst); } -META_COLLECTOR(int_indev) -{ - *err = int_dev(skb->input_dev, dst); -} - -META_COLLECTOR(var_indev) -{ - *err = var_dev(skb->input_dev, dst); -} - -META_COLLECTOR(int_realdev) -{ - *err = int_dev(skb->real_dev, dst); -} - -META_COLLECTOR(var_realdev) -{ - *err = var_dev(skb->real_dev, dst); -} - /************************************************************************** * skb attributes **************************************************************************/ @@ -205,11 +185,6 @@ META_COLLECTOR(int_protocol) dst->value = skb->protocol; } -META_COLLECTOR(int_security) -{ - dst->value = skb->security; -} - META_COLLECTOR(int_pkttype) { dst->value = skb->pkt_type; @@ -234,12 +209,14 @@ META_COLLECTOR(int_maclen) * Netfilter **************************************************************************/ -#ifdef CONFIG_NETFILTER META_COLLECTOR(int_nfmark) { +#ifdef CONFIG_NETFILTER dst->value = skb->nfmark; -} +#else + dst->value = 0; #endif +} /************************************************************************** * Traffic Control @@ -250,31 +227,21 @@ META_COLLECTOR(int_tcindex) dst->value = skb->tc_index; } -#ifdef CONFIG_NET_CLS_ACT -META_COLLECTOR(int_tcverd) -{ - dst->value = skb->tc_verd; -} - -META_COLLECTOR(int_tcclassid) -{ - dst->value = skb->tc_classid; -} -#endif - /************************************************************************** * Routing **************************************************************************/ -#ifdef CONFIG_NET_CLS_ROUTE META_COLLECTOR(int_rtclassid) { if (unlikely(skb->dst == NULL)) *err = -1; else +#ifdef CONFIG_NET_CLS_ROUTE dst->value = skb->dst->tclassid; -} +#else + dst->value = 0; #endif +} META_COLLECTOR(int_rtiif) { @@ -510,8 +477,6 @@ struct meta_ops static struct meta_ops __meta_ops[TCF_META_TYPE_MAX+1][TCF_META_ID_MAX+1] = { [TCF_META_TYPE_VAR] = { [META_ID(DEV)] = META_FUNC(var_dev), - [META_ID(INDEV)] = META_FUNC(var_indev), - [META_ID(REALDEV)] = META_FUNC(var_realdev), [META_ID(SK_BOUND_IF)] = META_FUNC(var_sk_bound_if), }, [TCF_META_TYPE_INT] = { @@ -520,26 +485,15 @@ static struct meta_ops __meta_ops[TCF_META_TYPE_MAX+1][TCF_META_ID_MAX+1] = { [META_ID(LOADAVG_1)] = META_FUNC(int_loadavg_1), [META_ID(LOADAVG_2)] = META_FUNC(int_loadavg_2), [META_ID(DEV)] = META_FUNC(int_dev), - [META_ID(INDEV)] = META_FUNC(int_indev), - [META_ID(REALDEV)] = META_FUNC(int_realdev), [META_ID(PRIORITY)] = META_FUNC(int_priority), [META_ID(PROTOCOL)] = META_FUNC(int_protocol), - [META_ID(SECURITY)] = META_FUNC(int_security), [META_ID(PKTTYPE)] = META_FUNC(int_pkttype), [META_ID(PKTLEN)] = META_FUNC(int_pktlen), [META_ID(DATALEN)] = META_FUNC(int_datalen), [META_ID(MACLEN)] = META_FUNC(int_maclen), -#ifdef CONFIG_NETFILTER [META_ID(NFMARK)] = META_FUNC(int_nfmark), -#endif [META_ID(TCINDEX)] = META_FUNC(int_tcindex), -#ifdef CONFIG_NET_CLS_ACT - [META_ID(TCVERDICT)] = META_FUNC(int_tcverd), - [META_ID(TCCLASSID)] = META_FUNC(int_tcclassid), -#endif -#ifdef CONFIG_NET_CLS_ROUTE [META_ID(RTCLASSID)] = META_FUNC(int_rtclassid), -#endif [META_ID(RTIIF)] = META_FUNC(int_rtiif), [META_ID(SK_FAMILY)] = META_FUNC(int_sk_family), [META_ID(SK_STATE)] = META_FUNC(int_sk_state), diff --git a/net/sched/em_text.c b/net/sched/em_text.c new file mode 100644 index 000000000000..77beabc91fa3 --- /dev/null +++ b/net/sched/em_text.c @@ -0,0 +1,154 @@ +/* + * net/sched/em_text.c Textsearch ematch + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + * + * Authors: Thomas Graf <tgraf@suug.ch> + */ + +#include <linux/config.h> +#include <linux/module.h> +#include <linux/types.h> +#include <linux/kernel.h> +#include <linux/sched.h> +#include <linux/string.h> +#include <linux/skbuff.h> +#include <linux/textsearch.h> +#include <linux/tc_ematch/tc_em_text.h> +#include <net/pkt_cls.h> + +struct text_match +{ + u16 from_offset; + u16 to_offset; + u8 from_layer; + u8 to_layer; + struct ts_config *config; +}; + +#define EM_TEXT_PRIV(m) ((struct text_match *) (m)->data) + +static int em_text_match(struct sk_buff *skb, struct tcf_ematch *m, + struct tcf_pkt_info *info) +{ + struct text_match *tm = EM_TEXT_PRIV(m); + int from, to; + struct ts_state state; + + from = tcf_get_base_ptr(skb, tm->from_layer) - skb->data; + from += tm->from_offset; + + to = tcf_get_base_ptr(skb, tm->to_layer) - skb->data; + to += tm->to_offset; + + return skb_find_text(skb, from, to, tm->config, &state) != UINT_MAX; +} + +static int em_text_change(struct tcf_proto *tp, void *data, int len, + struct tcf_ematch *m) +{ + struct text_match *tm; + struct tcf_em_text *conf = data; + struct ts_config *ts_conf; + int flags = 0; + + if (len < sizeof(*conf) || len < (sizeof(*conf) + conf->pattern_len)) + return -EINVAL; + + if (conf->from_layer > conf->to_layer) + return -EINVAL; + + if (conf->from_layer == conf->to_layer && + conf->from_offset > conf->to_offset) + return -EINVAL; + +retry: + ts_conf = textsearch_prepare(conf->algo, (u8 *) conf + sizeof(*conf), + conf->pattern_len, GFP_KERNEL, flags); + + if (flags & TS_AUTOLOAD) + rtnl_lock(); + + if (IS_ERR(ts_conf)) { + if (PTR_ERR(ts_conf) == -ENOENT && !(flags & TS_AUTOLOAD)) { + rtnl_unlock(); + flags |= TS_AUTOLOAD; + goto retry; + } else + return PTR_ERR(ts_conf); + } else if (flags & TS_AUTOLOAD) { + textsearch_destroy(ts_conf); + return -EAGAIN; + } + + tm = kmalloc(sizeof(*tm), GFP_KERNEL); + if (tm == NULL) { + textsearch_destroy(ts_conf); + return -ENOBUFS; + } + + tm->from_offset = conf->from_offset; + tm->to_offset = conf->to_offset; + tm->from_layer = conf->from_layer; + tm->to_layer = conf->to_layer; + tm->config = ts_conf; + + m->datalen = sizeof(*tm); + m->data = (unsigned long) tm; + + return 0; +} + +static void em_text_destroy(struct tcf_proto *tp, struct tcf_ematch *m) +{ + textsearch_destroy(EM_TEXT_PRIV(m)->config); +} + +static int em_text_dump(struct sk_buff *skb, struct tcf_ematch *m) +{ + struct text_match *tm = EM_TEXT_PRIV(m); + struct tcf_em_text conf; + + strncpy(conf.algo, tm->config->ops->name, sizeof(conf.algo) - 1); + conf.from_offset = tm->from_offset; + conf.to_offset = tm->to_offset; + conf.from_layer = tm->from_layer; + conf.to_layer = tm->to_layer; + conf.pattern_len = textsearch_get_pattern_len(tm->config); + conf.pad = 0; + + RTA_PUT_NOHDR(skb, sizeof(conf), &conf); + RTA_APPEND(skb, conf.pattern_len, textsearch_get_pattern(tm->config)); + return 0; + +rtattr_failure: + return -1; +} + +static struct tcf_ematch_ops em_text_ops = { + .kind = TCF_EM_TEXT, + .change = em_text_change, + .match = em_text_match, + .destroy = em_text_destroy, + .dump = em_text_dump, + .owner = THIS_MODULE, + .link = LIST_HEAD_INIT(em_text_ops.link) +}; + +static int __init init_em_text(void) +{ + return tcf_em_register(&em_text_ops); +} + +static void __exit exit_em_text(void) +{ + tcf_em_unregister(&em_text_ops); +} + +MODULE_LICENSE("GPL"); + +module_init(init_em_text); +module_exit(exit_em_text); diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c index 07977f8f2679..b9a069af4a02 100644 --- a/net/sched/sch_api.c +++ b/net/sched/sch_api.c @@ -399,10 +399,8 @@ qdisc_create(struct net_device *dev, u32 handle, struct rtattr **tca, int *errp) { int err; struct rtattr *kind = tca[TCA_KIND-1]; - void *p = NULL; struct Qdisc *sch; struct Qdisc_ops *ops; - int size; ops = qdisc_lookup_ops(kind); #ifdef CONFIG_KMOD @@ -437,64 +435,55 @@ qdisc_create(struct net_device *dev, u32 handle, struct rtattr **tca, int *errp) if (ops == NULL) goto err_out; - /* ensure that the Qdisc and the private data are 32-byte aligned */ - size = ((sizeof(*sch) + QDISC_ALIGN_CONST) & ~QDISC_ALIGN_CONST); - size += ops->priv_size + QDISC_ALIGN_CONST; - - p = kmalloc(size, GFP_KERNEL); - err = -ENOBUFS; - if (!p) + sch = qdisc_alloc(dev, ops); + if (IS_ERR(sch)) { + err = PTR_ERR(sch); goto err_out2; - memset(p, 0, size); - sch = (struct Qdisc *)(((unsigned long)p + QDISC_ALIGN_CONST) - & ~QDISC_ALIGN_CONST); - sch->padded = (char *)sch - (char *)p; - - INIT_LIST_HEAD(&sch->list); - skb_queue_head_init(&sch->q); + } - if (handle == TC_H_INGRESS) + if (handle == TC_H_INGRESS) { sch->flags |= TCQ_F_INGRESS; - - sch->ops = ops; - sch->enqueue = ops->enqueue; - sch->dequeue = ops->dequeue; - sch->dev = dev; - dev_hold(dev); - atomic_set(&sch->refcnt, 1); - sch->stats_lock = &dev->queue_lock; - if (handle == 0) { + handle = TC_H_MAKE(TC_H_INGRESS, 0); + } else if (handle == 0) { handle = qdisc_alloc_handle(dev); err = -ENOMEM; if (handle == 0) goto err_out3; } - if (handle == TC_H_INGRESS) - sch->handle =TC_H_MAKE(TC_H_INGRESS, 0); - else - sch->handle = handle; + 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, + tca[TCA_RATE-1]); + if (err) { + /* + * Any broken qdiscs that would require + * a ops->reset() here? The qdisc was never + * in action so it shouldn't be necessary. + */ + if (ops->destroy) + ops->destroy(sch); + goto err_out3; + } + } +#endif qdisc_lock_tree(dev); list_add_tail(&sch->list, &dev->qdisc_list); qdisc_unlock_tree(dev); -#ifdef CONFIG_NET_ESTIMATOR - if (tca[TCA_RATE-1]) - gen_new_estimator(&sch->bstats, &sch->rate_est, - sch->stats_lock, tca[TCA_RATE-1]); -#endif return sch; } err_out3: dev_put(dev); + kfree((char *) sch - sch->padded); err_out2: module_put(ops->owner); err_out: *errp = err; - if (p) - kfree(p); return NULL; } @@ -760,17 +749,18 @@ graft: } static int tc_fill_qdisc(struct sk_buff *skb, struct Qdisc *q, u32 clid, - u32 pid, u32 seq, unsigned flags, int event) + u32 pid, u32 seq, u16 flags, int event) { struct tcmsg *tcm; struct nlmsghdr *nlh; unsigned char *b = skb->tail; struct gnet_dump d; - nlh = NLMSG_PUT(skb, pid, seq, event, sizeof(*tcm)); - nlh->nlmsg_flags = flags; + nlh = NLMSG_NEW(skb, pid, seq, event, sizeof(*tcm), flags); tcm = NLMSG_DATA(nlh); tcm->tcm_family = AF_UNSPEC; + tcm->tcm__pad1 = 0; + tcm->tcm__pad2 = 0; tcm->tcm_ifindex = q->dev->ifindex; tcm->tcm_parent = clid; tcm->tcm_handle = q->handle; @@ -997,7 +987,7 @@ out: static int tc_fill_tclass(struct sk_buff *skb, struct Qdisc *q, unsigned long cl, - u32 pid, u32 seq, unsigned flags, int event) + u32 pid, u32 seq, u16 flags, int event) { struct tcmsg *tcm; struct nlmsghdr *nlh; @@ -1005,8 +995,7 @@ static int tc_fill_tclass(struct sk_buff *skb, struct Qdisc *q, struct gnet_dump d; struct Qdisc_class_ops *cl_ops = q->ops->cl_ops; - nlh = NLMSG_PUT(skb, pid, seq, event, sizeof(*tcm)); - nlh->nlmsg_flags = flags; + nlh = NLMSG_NEW(skb, pid, seq, event, sizeof(*tcm), flags); tcm = NLMSG_DATA(nlh); tcm->tcm_family = AF_UNSPEC; tcm->tcm_ifindex = q->dev->ifindex; diff --git a/net/sched/sch_blackhole.c b/net/sched/sch_blackhole.c new file mode 100644 index 000000000000..81f0b8346d17 --- /dev/null +++ b/net/sched/sch_blackhole.c @@ -0,0 +1,54 @@ +/* + * net/sched/sch_blackhole.c Black hole queue + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + * + * Authors: Thomas Graf <tgraf@suug.ch> + * + * Note: Quantum tunneling is not supported. + */ + +#include <linux/config.h> +#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> + +static int blackhole_enqueue(struct sk_buff *skb, struct Qdisc *sch) +{ + qdisc_drop(skb, sch); + return NET_XMIT_SUCCESS; +} + +static struct sk_buff *blackhole_dequeue(struct Qdisc *sch) +{ + return NULL; +} + +static struct Qdisc_ops blackhole_qdisc_ops = { + .id = "blackhole", + .priv_size = 0, + .enqueue = blackhole_enqueue, + .dequeue = blackhole_dequeue, + .owner = THIS_MODULE, +}; + +static int __init blackhole_module_init(void) +{ + return register_qdisc(&blackhole_qdisc_ops); +} + +static void __exit blackhole_module_exit(void) +{ + unregister_qdisc(&blackhole_qdisc_ops); +} + +module_init(blackhole_module_init) +module_exit(blackhole_module_exit) + +MODULE_LICENSE("GPL"); diff --git a/net/sched/sch_cbq.c b/net/sched/sch_cbq.c index d43e3b8cbf6a..09453f997d8c 100644 --- a/net/sched/sch_cbq.c +++ b/net/sched/sch_cbq.c @@ -1528,6 +1528,7 @@ static __inline__ int cbq_dump_ovl(struct sk_buff *skb, struct cbq_class *cl) opt.strategy = cl->ovl_strategy; opt.priority2 = cl->priority2+1; + opt.pad = 0; opt.penalty = (cl->penalty*1000)/HZ; RTA_PUT(skb, TCA_CBQ_OVL_STRATEGY, sizeof(opt), &opt); return skb->len; @@ -1563,6 +1564,8 @@ static __inline__ int cbq_dump_police(struct sk_buff *skb, struct cbq_class *cl) if (cl->police) { opt.police = cl->police; + opt.__res1 = 0; + opt.__res2 = 0; RTA_PUT(skb, TCA_CBQ_POLICE, sizeof(opt), &opt); } return skb->len; diff --git a/net/sched/sch_dsmark.c b/net/sched/sch_dsmark.c index d8bd2a569c7c..13e0e7b3856b 100644 --- a/net/sched/sch_dsmark.c +++ b/net/sched/sch_dsmark.c @@ -31,7 +31,7 @@ #endif -#define PRIV(sch) qdisc_priv(sch) +#define PRIV(sch) ((struct dsmark_qdisc_data *) qdisc_priv(sch)) /* @@ -55,24 +55,38 @@ struct dsmark_qdisc_data { struct Qdisc *q; struct tcf_proto *filter_list; - __u8 *mask; /* "owns" the array */ - __u8 *value; - __u16 indices; - __u32 default_index; /* index range is 0...0xffff */ + u8 *mask; /* "owns" the array */ + u8 *value; + u16 indices; + u32 default_index; /* index range is 0...0xffff */ int set_tc_index; }; +static inline int dsmark_valid_indices(u16 indices) +{ + while (indices != 1) { + if (indices & 1) + return 0; + indices >>= 1; + } + + return 1; +} -/* ------------------------- Class/flow operations ------------------------- */ +static inline int dsmark_valid_index(struct dsmark_qdisc_data *p, u16 index) +{ + return (index <= p->indices && index > 0); +} +/* ------------------------- Class/flow operations ------------------------- */ -static int dsmark_graft(struct Qdisc *sch,unsigned long arg, - struct Qdisc *new,struct Qdisc **old) +static int dsmark_graft(struct Qdisc *sch, unsigned long arg, + struct Qdisc *new, struct Qdisc **old) { struct dsmark_qdisc_data *p = PRIV(sch); - DPRINTK("dsmark_graft(sch %p,[qdisc %p],new %p,old %p)\n",sch,p,new, - old); + DPRINTK("dsmark_graft(sch %p,[qdisc %p],new %p,old %p)\n", + sch, p, new, old); if (new == NULL) { new = qdisc_create_dflt(sch->dev, &pfifo_qdisc_ops); @@ -81,91 +95,95 @@ static int dsmark_graft(struct Qdisc *sch,unsigned long arg, } sch_tree_lock(sch); - *old = xchg(&p->q,new); - if (*old) - qdisc_reset(*old); + *old = xchg(&p->q, new); + qdisc_reset(*old); sch->q.qlen = 0; - sch_tree_unlock(sch); /* @@@ move up ? */ + sch_tree_unlock(sch); + return 0; } - static struct Qdisc *dsmark_leaf(struct Qdisc *sch, unsigned long arg) { - struct dsmark_qdisc_data *p = PRIV(sch); - - return p->q; + return PRIV(sch)->q; } - -static unsigned long dsmark_get(struct Qdisc *sch,u32 classid) +static unsigned long dsmark_get(struct Qdisc *sch, u32 classid) { - struct dsmark_qdisc_data *p __attribute__((unused)) = PRIV(sch); + DPRINTK("dsmark_get(sch %p,[qdisc %p],classid %x)\n", + sch, PRIV(sch), classid); - DPRINTK("dsmark_get(sch %p,[qdisc %p],classid %x)\n",sch,p,classid); - return TC_H_MIN(classid)+1; + return TC_H_MIN(classid) + 1; } - static unsigned long dsmark_bind_filter(struct Qdisc *sch, - unsigned long parent, u32 classid) + unsigned long parent, u32 classid) { - return dsmark_get(sch,classid); + return dsmark_get(sch, classid); } - static void dsmark_put(struct Qdisc *sch, unsigned long cl) { } - static int dsmark_change(struct Qdisc *sch, u32 classid, u32 parent, - struct rtattr **tca, unsigned long *arg) + struct rtattr **tca, unsigned long *arg) { struct dsmark_qdisc_data *p = PRIV(sch); struct rtattr *opt = tca[TCA_OPTIONS-1]; struct rtattr *tb[TCA_DSMARK_MAX]; + int err = -EINVAL; + u8 mask = 0; DPRINTK("dsmark_change(sch %p,[qdisc %p],classid %x,parent %x)," - "arg 0x%lx\n",sch,p,classid,parent,*arg); - if (*arg > p->indices) - return -ENOENT; - if (!opt || rtattr_parse_nested(tb, TCA_DSMARK_MAX, opt)) - return -EINVAL; - if (tb[TCA_DSMARK_MASK-1]) { - if (!RTA_PAYLOAD(tb[TCA_DSMARK_MASK-1])) - return -EINVAL; - p->mask[*arg-1] = *(__u8 *) RTA_DATA(tb[TCA_DSMARK_MASK-1]); - } - if (tb[TCA_DSMARK_VALUE-1]) { - if (!RTA_PAYLOAD(tb[TCA_DSMARK_VALUE-1])) - return -EINVAL; - p->value[*arg-1] = *(__u8 *) RTA_DATA(tb[TCA_DSMARK_VALUE-1]); + "arg 0x%lx\n", sch, p, classid, parent, *arg); + + if (!dsmark_valid_index(p, *arg)) { + err = -ENOENT; + goto rtattr_failure; } - return 0; -} + if (!opt || rtattr_parse_nested(tb, TCA_DSMARK_MAX, opt)) + goto rtattr_failure; + + if (tb[TCA_DSMARK_MASK-1]) + mask = RTA_GET_U8(tb[TCA_DSMARK_MASK-1]); + + if (tb[TCA_DSMARK_VALUE-1]) + p->value[*arg-1] = RTA_GET_U8(tb[TCA_DSMARK_VALUE-1]); + + if (tb[TCA_DSMARK_MASK-1]) + p->mask[*arg-1] = mask; + + err = 0; -static int dsmark_delete(struct Qdisc *sch,unsigned long arg) +rtattr_failure: + return err; +} + +static int dsmark_delete(struct Qdisc *sch, unsigned long arg) { struct dsmark_qdisc_data *p = PRIV(sch); - if (!arg || arg > p->indices) + if (!dsmark_valid_index(p, arg)) return -EINVAL; + p->mask[arg-1] = 0xff; p->value[arg-1] = 0; + return 0; } - static void dsmark_walk(struct Qdisc *sch,struct qdisc_walker *walker) { struct dsmark_qdisc_data *p = PRIV(sch); int i; - DPRINTK("dsmark_walk(sch %p,[qdisc %p],walker %p)\n",sch,p,walker); + DPRINTK("dsmark_walk(sch %p,[qdisc %p],walker %p)\n", sch, p, walker); + if (walker->stop) return; + for (i = 0; i < p->indices; i++) { if (p->mask[i] == 0xff && !p->value[i]) goto ignore; @@ -180,26 +198,20 @@ ignore: } } - static struct tcf_proto **dsmark_find_tcf(struct Qdisc *sch,unsigned long cl) { - struct dsmark_qdisc_data *p = PRIV(sch); - - return &p->filter_list; + return &PRIV(sch)->filter_list; } - /* --------------------------- Qdisc operations ---------------------------- */ - static int dsmark_enqueue(struct sk_buff *skb,struct Qdisc *sch) { struct dsmark_qdisc_data *p = PRIV(sch); - struct tcf_result res; - int result; - int ret = NET_XMIT_POLICED; + int err; + + D2PRINTK("dsmark_enqueue(skb %p,sch %p,[qdisc %p])\n", skb, sch, p); - D2PRINTK("dsmark_enqueue(skb %p,sch %p,[qdisc %p])\n",skb,sch,p); if (p->set_tc_index) { /* FIXME: Safe with non-linear skbs? --RR */ switch (skb->protocol) { @@ -216,17 +228,21 @@ static int dsmark_enqueue(struct sk_buff *skb,struct Qdisc *sch) break; }; } - result = TC_POLICE_OK; /* be nice to gcc */ - if (TC_H_MAJ(skb->priority) == sch->handle) { + + if (TC_H_MAJ(skb->priority) == sch->handle) skb->tc_index = TC_H_MIN(skb->priority); - } else { - result = tc_classify(skb,p->filter_list,&res); - D2PRINTK("result %d class 0x%04x\n",result,res.classid); + else { + struct tcf_result res; + int result = tc_classify(skb, p->filter_list, &res); + + D2PRINTK("result %d class 0x%04x\n", result, res.classid); + switch (result) { #ifdef CONFIG_NET_CLS_POLICE case TC_POLICE_SHOT: kfree_skb(skb); - break; + sch->qstats.drops++; + return NET_XMIT_POLICED; #if 0 case TC_POLICE_RECLASSIFY: /* FIXME: what to do here ??? */ @@ -243,43 +259,45 @@ static int dsmark_enqueue(struct sk_buff *skb,struct Qdisc *sch) break; }; } - if ( -#ifdef CONFIG_NET_CLS_POLICE - result == TC_POLICE_SHOT || -#endif - ((ret = p->q->enqueue(skb,p->q)) != 0)) { + err = p->q->enqueue(skb,p->q); + if (err != NET_XMIT_SUCCESS) { sch->qstats.drops++; - return ret; + return err; } + sch->bstats.bytes += skb->len; sch->bstats.packets++; sch->q.qlen++; - return ret; -} + return NET_XMIT_SUCCESS; +} static struct sk_buff *dsmark_dequeue(struct Qdisc *sch) { struct dsmark_qdisc_data *p = PRIV(sch); struct sk_buff *skb; - int index; + u32 index; + + D2PRINTK("dsmark_dequeue(sch %p,[qdisc %p])\n", sch, p); - D2PRINTK("dsmark_dequeue(sch %p,[qdisc %p])\n",sch,p); skb = p->q->ops->dequeue(p->q); - if (!skb) + if (skb == NULL) return NULL; + sch->q.qlen--; - index = skb->tc_index & (p->indices-1); - D2PRINTK("index %d->%d\n",skb->tc_index,index); + + index = skb->tc_index & (p->indices - 1); + D2PRINTK("index %d->%d\n", skb->tc_index, index); + switch (skb->protocol) { case __constant_htons(ETH_P_IP): - ipv4_change_dsfield(skb->nh.iph, - p->mask[index],p->value[index]); + ipv4_change_dsfield(skb->nh.iph, p->mask[index], + p->value[index]); break; case __constant_htons(ETH_P_IPV6): - ipv6_change_dsfield(skb->nh.ipv6h, - p->mask[index],p->value[index]); + ipv6_change_dsfield(skb->nh.ipv6h, p->mask[index], + p->value[index]); break; default: /* @@ -293,152 +311,162 @@ static struct sk_buff *dsmark_dequeue(struct Qdisc *sch) htons(skb->protocol)); break; }; + return skb; } - static int dsmark_requeue(struct sk_buff *skb,struct Qdisc *sch) { - int ret; struct dsmark_qdisc_data *p = PRIV(sch); + int err; - D2PRINTK("dsmark_requeue(skb %p,sch %p,[qdisc %p])\n",skb,sch,p); - if ((ret = p->q->ops->requeue(skb, p->q)) == 0) { - sch->q.qlen++; - sch->qstats.requeues++; - return 0; + D2PRINTK("dsmark_requeue(skb %p,sch %p,[qdisc %p])\n", skb, sch, p); + + err = p->q->ops->requeue(skb, p->q); + if (err != NET_XMIT_SUCCESS) { + sch->qstats.drops++; + return err; } - sch->qstats.drops++; - return ret; -} + sch->q.qlen++; + sch->qstats.requeues++; + + return NET_XMIT_SUCCESS; +} static unsigned int dsmark_drop(struct Qdisc *sch) { struct dsmark_qdisc_data *p = PRIV(sch); unsigned int len; - DPRINTK("dsmark_reset(sch %p,[qdisc %p])\n",sch,p); - if (!p->q->ops->drop) - return 0; - if (!(len = p->q->ops->drop(p->q))) + DPRINTK("dsmark_reset(sch %p,[qdisc %p])\n", sch, p); + + if (p->q->ops->drop == NULL) return 0; - sch->q.qlen--; + + len = p->q->ops->drop(p->q); + if (len) + sch->q.qlen--; + return len; } - -static int dsmark_init(struct Qdisc *sch,struct rtattr *opt) +static int dsmark_init(struct Qdisc *sch, struct rtattr *opt) { struct dsmark_qdisc_data *p = PRIV(sch); struct rtattr *tb[TCA_DSMARK_MAX]; - __u16 tmp; - - DPRINTK("dsmark_init(sch %p,[qdisc %p],opt %p)\n",sch,p,opt); - if (!opt || - rtattr_parse(tb,TCA_DSMARK_MAX,RTA_DATA(opt),RTA_PAYLOAD(opt)) < 0 || - !tb[TCA_DSMARK_INDICES-1] || - RTA_PAYLOAD(tb[TCA_DSMARK_INDICES-1]) < sizeof(__u16)) - return -EINVAL; - p->indices = *(__u16 *) RTA_DATA(tb[TCA_DSMARK_INDICES-1]); - if (!p->indices) - return -EINVAL; - for (tmp = p->indices; tmp != 1; tmp >>= 1) { - if (tmp & 1) - return -EINVAL; - } - p->default_index = NO_DEFAULT_INDEX; - if (tb[TCA_DSMARK_DEFAULT_INDEX-1]) { - if (RTA_PAYLOAD(tb[TCA_DSMARK_DEFAULT_INDEX-1]) < sizeof(__u16)) - return -EINVAL; - p->default_index = - *(__u16 *) RTA_DATA(tb[TCA_DSMARK_DEFAULT_INDEX-1]); + int err = -EINVAL; + u32 default_index = NO_DEFAULT_INDEX; + u16 indices; + u8 *mask; + + DPRINTK("dsmark_init(sch %p,[qdisc %p],opt %p)\n", sch, p, opt); + + if (!opt || rtattr_parse_nested(tb, TCA_DSMARK_MAX, opt) < 0) + goto errout; + + indices = RTA_GET_U16(tb[TCA_DSMARK_INDICES-1]); + if (!indices || !dsmark_valid_indices(indices)) + goto errout; + + if (tb[TCA_DSMARK_DEFAULT_INDEX-1]) + default_index = RTA_GET_U16(tb[TCA_DSMARK_DEFAULT_INDEX-1]); + + mask = kmalloc(indices * 2, GFP_KERNEL); + if (mask == NULL) { + err = -ENOMEM; + goto errout; } - p->set_tc_index = !!tb[TCA_DSMARK_SET_TC_INDEX-1]; - p->mask = kmalloc(p->indices*2,GFP_KERNEL); - if (!p->mask) - return -ENOMEM; - p->value = p->mask+p->indices; - memset(p->mask,0xff,p->indices); - memset(p->value,0,p->indices); - if (!(p->q = qdisc_create_dflt(sch->dev, &pfifo_qdisc_ops))) + + p->mask = mask; + memset(p->mask, 0xff, indices); + + p->value = p->mask + indices; + memset(p->value, 0, indices); + + p->indices = indices; + p->default_index = default_index; + p->set_tc_index = RTA_GET_FLAG(tb[TCA_DSMARK_SET_TC_INDEX-1]); + + p->q = qdisc_create_dflt(sch->dev, &pfifo_qdisc_ops); + if (p->q == NULL) p->q = &noop_qdisc; - DPRINTK("dsmark_init: qdisc %p\n",&p->q); - return 0; -} + DPRINTK("dsmark_init: qdisc %p\n", p->q); + + err = 0; +errout: +rtattr_failure: + return err; +} static void dsmark_reset(struct Qdisc *sch) { struct dsmark_qdisc_data *p = PRIV(sch); - DPRINTK("dsmark_reset(sch %p,[qdisc %p])\n",sch,p); + DPRINTK("dsmark_reset(sch %p,[qdisc %p])\n", sch, p); qdisc_reset(p->q); sch->q.qlen = 0; } - static void dsmark_destroy(struct Qdisc *sch) { struct dsmark_qdisc_data *p = PRIV(sch); struct tcf_proto *tp; - DPRINTK("dsmark_destroy(sch %p,[qdisc %p])\n",sch,p); + DPRINTK("dsmark_destroy(sch %p,[qdisc %p])\n", sch, p); + while (p->filter_list) { tp = p->filter_list; p->filter_list = tp->next; tcf_destroy(tp); } + qdisc_destroy(p->q); kfree(p->mask); } - static int dsmark_dump_class(struct Qdisc *sch, unsigned long cl, - struct sk_buff *skb, struct tcmsg *tcm) + struct sk_buff *skb, struct tcmsg *tcm) { struct dsmark_qdisc_data *p = PRIV(sch); - unsigned char *b = skb->tail; - struct rtattr *rta; + struct rtattr *opts = NULL; + + DPRINTK("dsmark_dump_class(sch %p,[qdisc %p],class %ld\n", sch, p, cl); - DPRINTK("dsmark_dump_class(sch %p,[qdisc %p],class %ld\n",sch,p,cl); - if (!cl || cl > p->indices) + if (!dsmark_valid_index(p, cl)) return -EINVAL; - tcm->tcm_handle = TC_H_MAKE(TC_H_MAJ(sch->handle),cl-1); - rta = (struct rtattr *) b; - RTA_PUT(skb,TCA_OPTIONS,0,NULL); - RTA_PUT(skb,TCA_DSMARK_MASK,1,&p->mask[cl-1]); - RTA_PUT(skb,TCA_DSMARK_VALUE,1,&p->value[cl-1]); - rta->rta_len = skb->tail-b; - return skb->len; + + tcm->tcm_handle = TC_H_MAKE(TC_H_MAJ(sch->handle), cl-1); + + opts = RTA_NEST(skb, TCA_OPTIONS); + RTA_PUT_U8(skb,TCA_DSMARK_MASK, p->mask[cl-1]); + RTA_PUT_U8(skb,TCA_DSMARK_VALUE, p->value[cl-1]); + + return RTA_NEST_END(skb, opts); rtattr_failure: - skb_trim(skb,b-skb->data); - return -1; + return RTA_NEST_CANCEL(skb, opts); } static int dsmark_dump(struct Qdisc *sch, struct sk_buff *skb) { struct dsmark_qdisc_data *p = PRIV(sch); - unsigned char *b = skb->tail; - struct rtattr *rta; + struct rtattr *opts = NULL; - rta = (struct rtattr *) b; - RTA_PUT(skb,TCA_OPTIONS,0,NULL); - RTA_PUT(skb,TCA_DSMARK_INDICES,sizeof(__u16),&p->indices); - if (p->default_index != NO_DEFAULT_INDEX) { - __u16 tmp = p->default_index; + opts = RTA_NEST(skb, TCA_OPTIONS); + RTA_PUT_U16(skb, TCA_DSMARK_INDICES, p->indices); + + if (p->default_index != NO_DEFAULT_INDEX) + RTA_PUT_U16(skb, TCA_DSMARK_DEFAULT_INDEX, p->default_index); - RTA_PUT(skb,TCA_DSMARK_DEFAULT_INDEX, sizeof(__u16), &tmp); - } if (p->set_tc_index) - RTA_PUT(skb, TCA_DSMARK_SET_TC_INDEX, 0, NULL); - rta->rta_len = skb->tail-b; - return skb->len; + RTA_PUT_FLAG(skb, TCA_DSMARK_SET_TC_INDEX); + + return RTA_NEST_END(skb, opts); rtattr_failure: - skb_trim(skb,b-skb->data); - return -1; + return RTA_NEST_CANCEL(skb, opts); } static struct Qdisc_class_ops dsmark_class_ops = { @@ -476,10 +504,13 @@ static int __init dsmark_module_init(void) { return register_qdisc(&dsmark_qdisc_ops); } + static void __exit dsmark_module_exit(void) { unregister_qdisc(&dsmark_qdisc_ops); } + module_init(dsmark_module_init) module_exit(dsmark_module_exit) + MODULE_LICENSE("GPL"); diff --git a/net/sched/sch_fifo.c b/net/sched/sch_fifo.c index 4888305c96da..033083bf0e74 100644 --- a/net/sched/sch_fifo.c +++ b/net/sched/sch_fifo.c @@ -11,131 +11,38 @@ #include <linux/config.h> #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/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/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/pkt_sched.h> /* 1 band FIFO pseudo-"scheduler" */ struct fifo_sched_data { - unsigned limit; + u32 limit; }; -static int -bfifo_enqueue(struct sk_buff *skb, struct Qdisc* sch) +static int bfifo_enqueue(struct sk_buff *skb, struct Qdisc* sch) { struct fifo_sched_data *q = qdisc_priv(sch); - if (sch->qstats.backlog + skb->len <= q->limit) { - __skb_queue_tail(&sch->q, skb); - sch->qstats.backlog += skb->len; - sch->bstats.bytes += skb->len; - sch->bstats.packets++; - return 0; - } - sch->qstats.drops++; -#ifdef CONFIG_NET_CLS_POLICE - if (sch->reshape_fail==NULL || sch->reshape_fail(skb, sch)) -#endif - kfree_skb(skb); - return NET_XMIT_DROP; -} - -static int -bfifo_requeue(struct sk_buff *skb, struct Qdisc* sch) -{ - __skb_queue_head(&sch->q, skb); - sch->qstats.backlog += skb->len; - sch->qstats.requeues++; - return 0; -} - -static struct sk_buff * -bfifo_dequeue(struct Qdisc* sch) -{ - struct sk_buff *skb; + if (likely(sch->qstats.backlog + skb->len <= q->limit)) + return qdisc_enqueue_tail(skb, sch); - skb = __skb_dequeue(&sch->q); - if (skb) - sch->qstats.backlog -= skb->len; - return skb; + return qdisc_reshape_fail(skb, sch); } -static unsigned int -fifo_drop(struct Qdisc* sch) -{ - struct sk_buff *skb; - - skb = __skb_dequeue_tail(&sch->q); - if (skb) { - unsigned int len = skb->len; - sch->qstats.backlog -= len; - kfree_skb(skb); - return len; - } - return 0; -} - -static void -fifo_reset(struct Qdisc* sch) -{ - skb_queue_purge(&sch->q); - sch->qstats.backlog = 0; -} - -static int -pfifo_enqueue(struct sk_buff *skb, struct Qdisc* sch) +static int pfifo_enqueue(struct sk_buff *skb, struct Qdisc* sch) { struct fifo_sched_data *q = qdisc_priv(sch); - if (sch->q.qlen < q->limit) { - __skb_queue_tail(&sch->q, skb); - sch->bstats.bytes += skb->len; - sch->bstats.packets++; - return 0; - } - sch->qstats.drops++; -#ifdef CONFIG_NET_CLS_POLICE - if (sch->reshape_fail==NULL || sch->reshape_fail(skb, sch)) -#endif - kfree_skb(skb); - return NET_XMIT_DROP; -} - -static int -pfifo_requeue(struct sk_buff *skb, struct Qdisc* sch) -{ - __skb_queue_head(&sch->q, skb); - sch->qstats.requeues++; - return 0; -} - + if (likely(skb_queue_len(&sch->q) < q->limit)) + return qdisc_enqueue_tail(skb, sch); -static struct sk_buff * -pfifo_dequeue(struct Qdisc* sch) -{ - return __skb_dequeue(&sch->q); + return qdisc_reshape_fail(skb, sch); } static int fifo_init(struct Qdisc *sch, struct rtattr *opt) @@ -143,66 +50,59 @@ static int fifo_init(struct Qdisc *sch, struct rtattr *opt) struct fifo_sched_data *q = qdisc_priv(sch); if (opt == NULL) { - unsigned int limit = sch->dev->tx_queue_len ? : 1; + u32 limit = sch->dev->tx_queue_len ? : 1; if (sch->ops == &bfifo_qdisc_ops) - q->limit = limit*sch->dev->mtu; - else - q->limit = limit; + limit *= sch->dev->mtu; + + q->limit = limit; } else { struct tc_fifo_qopt *ctl = RTA_DATA(opt); - if (opt->rta_len < RTA_LENGTH(sizeof(*ctl))) + + if (RTA_PAYLOAD(opt) < sizeof(*ctl)) return -EINVAL; + q->limit = ctl->limit; } + return 0; } static int fifo_dump(struct Qdisc *sch, struct sk_buff *skb) { struct fifo_sched_data *q = qdisc_priv(sch); - unsigned char *b = skb->tail; - struct tc_fifo_qopt opt; + struct tc_fifo_qopt opt = { .limit = q->limit }; - opt.limit = q->limit; RTA_PUT(skb, TCA_OPTIONS, sizeof(opt), &opt); - return skb->len; rtattr_failure: - skb_trim(skb, b - skb->data); return -1; } struct Qdisc_ops pfifo_qdisc_ops = { - .next = NULL, - .cl_ops = NULL, .id = "pfifo", .priv_size = sizeof(struct fifo_sched_data), .enqueue = pfifo_enqueue, - .dequeue = pfifo_dequeue, - .requeue = pfifo_requeue, - .drop = fifo_drop, + .dequeue = qdisc_dequeue_head, + .requeue = qdisc_requeue, + .drop = qdisc_queue_drop, .init = fifo_init, - .reset = fifo_reset, - .destroy = NULL, + .reset = qdisc_reset_queue, .change = fifo_init, .dump = fifo_dump, .owner = THIS_MODULE, }; struct Qdisc_ops bfifo_qdisc_ops = { - .next = NULL, - .cl_ops = NULL, .id = "bfifo", .priv_size = sizeof(struct fifo_sched_data), .enqueue = bfifo_enqueue, - .dequeue = bfifo_dequeue, - .requeue = bfifo_requeue, - .drop = fifo_drop, + .dequeue = qdisc_dequeue_head, + .requeue = qdisc_requeue, + .drop = qdisc_queue_drop, .init = fifo_init, - .reset = fifo_reset, - .destroy = NULL, + .reset = qdisc_reset_queue, .change = fifo_init, .dump = fifo_dump, .owner = THIS_MODULE, diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c index 87e48a4e1051..8edefd5d095d 100644 --- a/net/sched/sch_generic.c +++ b/net/sched/sch_generic.c @@ -243,31 +243,27 @@ static void dev_watchdog_down(struct net_device *dev) cheaper. */ -static int -noop_enqueue(struct sk_buff *skb, struct Qdisc * qdisc) +static int noop_enqueue(struct sk_buff *skb, struct Qdisc * qdisc) { kfree_skb(skb); return NET_XMIT_CN; } -static struct sk_buff * -noop_dequeue(struct Qdisc * qdisc) +static struct sk_buff *noop_dequeue(struct Qdisc * qdisc) { return NULL; } -static int -noop_requeue(struct sk_buff *skb, struct Qdisc* qdisc) +static int noop_requeue(struct sk_buff *skb, struct Qdisc* qdisc) { if (net_ratelimit()) - printk(KERN_DEBUG "%s deferred output. It is buggy.\n", skb->dev->name); + printk(KERN_DEBUG "%s deferred output. It is buggy.\n", + skb->dev->name); kfree_skb(skb); return NET_XMIT_CN; } struct Qdisc_ops noop_qdisc_ops = { - .next = NULL, - .cl_ops = NULL, .id = "noop", .priv_size = 0, .enqueue = noop_enqueue, @@ -285,8 +281,6 @@ struct Qdisc noop_qdisc = { }; static struct Qdisc_ops noqueue_qdisc_ops = { - .next = NULL, - .cl_ops = NULL, .id = "noqueue", .priv_size = 0, .enqueue = noop_enqueue, @@ -311,97 +305,86 @@ static const u8 prio2band[TC_PRIO_MAX+1] = generic prio+fifo combination. */ -static int -pfifo_fast_enqueue(struct sk_buff *skb, struct Qdisc* qdisc) +#define PFIFO_FAST_BANDS 3 + +static inline struct sk_buff_head *prio2list(struct sk_buff *skb, + struct Qdisc *qdisc) { struct sk_buff_head *list = qdisc_priv(qdisc); + return list + prio2band[skb->priority & TC_PRIO_MAX]; +} - list += prio2band[skb->priority&TC_PRIO_MAX]; +static int pfifo_fast_enqueue(struct sk_buff *skb, struct Qdisc* qdisc) +{ + struct sk_buff_head *list = prio2list(skb, qdisc); - if (list->qlen < qdisc->dev->tx_queue_len) { - __skb_queue_tail(list, skb); + if (skb_queue_len(list) < qdisc->dev->tx_queue_len) { qdisc->q.qlen++; - qdisc->bstats.bytes += skb->len; - qdisc->bstats.packets++; - return 0; + return __qdisc_enqueue_tail(skb, qdisc, list); } - qdisc->qstats.drops++; - kfree_skb(skb); - return NET_XMIT_DROP; + + return qdisc_drop(skb, qdisc); } -static struct sk_buff * -pfifo_fast_dequeue(struct Qdisc* qdisc) +static struct sk_buff *pfifo_fast_dequeue(struct Qdisc* qdisc) { int prio; struct sk_buff_head *list = qdisc_priv(qdisc); - struct sk_buff *skb; - for (prio = 0; prio < 3; prio++, list++) { - skb = __skb_dequeue(list); - if (skb) { + for (prio = 0; prio < PFIFO_FAST_BANDS; prio++) { + if (!skb_queue_empty(list + prio)) { qdisc->q.qlen--; - return skb; + return __qdisc_dequeue_head(qdisc, list + prio); } } + return NULL; } -static int -pfifo_fast_requeue(struct sk_buff *skb, struct Qdisc* qdisc) +static int pfifo_fast_requeue(struct sk_buff *skb, struct Qdisc* qdisc) { - struct sk_buff_head *list = qdisc_priv(qdisc); - - list += prio2band[skb->priority&TC_PRIO_MAX]; - - __skb_queue_head(list, skb); qdisc->q.qlen++; - qdisc->qstats.requeues++; - return 0; + return __qdisc_requeue(skb, qdisc, prio2list(skb, qdisc)); } -static void -pfifo_fast_reset(struct Qdisc* qdisc) +static void pfifo_fast_reset(struct Qdisc* qdisc) { int prio; struct sk_buff_head *list = qdisc_priv(qdisc); - for (prio=0; prio < 3; prio++) - skb_queue_purge(list+prio); + for (prio = 0; prio < PFIFO_FAST_BANDS; prio++) + __qdisc_reset_queue(qdisc, list + prio); + + qdisc->qstats.backlog = 0; qdisc->q.qlen = 0; } static int pfifo_fast_dump(struct Qdisc *qdisc, struct sk_buff *skb) { - unsigned char *b = skb->tail; - struct tc_prio_qopt opt; + struct tc_prio_qopt opt = { .bands = PFIFO_FAST_BANDS }; - opt.bands = 3; memcpy(&opt.priomap, prio2band, TC_PRIO_MAX+1); RTA_PUT(skb, TCA_OPTIONS, sizeof(opt), &opt); return skb->len; rtattr_failure: - skb_trim(skb, b - skb->data); return -1; } static int pfifo_fast_init(struct Qdisc *qdisc, struct rtattr *opt) { - int i; + int prio; struct sk_buff_head *list = qdisc_priv(qdisc); - for (i=0; i<3; i++) - skb_queue_head_init(list+i); + for (prio = 0; prio < PFIFO_FAST_BANDS; prio++) + skb_queue_head_init(list + prio); return 0; } static struct Qdisc_ops pfifo_fast_ops = { - .next = NULL, - .cl_ops = NULL, .id = "pfifo_fast", - .priv_size = 3 * sizeof(struct sk_buff_head), + .priv_size = PFIFO_FAST_BANDS * sizeof(struct sk_buff_head), .enqueue = pfifo_fast_enqueue, .dequeue = pfifo_fast_dequeue, .requeue = pfifo_fast_requeue, @@ -411,24 +394,23 @@ static struct Qdisc_ops pfifo_fast_ops = { .owner = THIS_MODULE, }; -struct Qdisc * qdisc_create_dflt(struct net_device *dev, struct Qdisc_ops *ops) +struct Qdisc *qdisc_alloc(struct net_device *dev, struct Qdisc_ops *ops) { void *p; struct Qdisc *sch; - int size; + unsigned int size; + int err = -ENOBUFS; /* ensure that the Qdisc and the private data are 32-byte aligned */ - size = ((sizeof(*sch) + QDISC_ALIGN_CONST) & ~QDISC_ALIGN_CONST); - size += ops->priv_size + QDISC_ALIGN_CONST; + size = QDISC_ALIGN(sizeof(*sch)); + size += ops->priv_size + (QDISC_ALIGNTO - 1); p = kmalloc(size, GFP_KERNEL); if (!p) - return NULL; + goto errout; memset(p, 0, size); - - sch = (struct Qdisc *)(((unsigned long)p + QDISC_ALIGN_CONST) - & ~QDISC_ALIGN_CONST); - sch->padded = (char *)sch - (char *)p; + sch = (struct Qdisc *) QDISC_ALIGN((unsigned long) p); + sch->padded = (char *) sch - (char *) p; INIT_LIST_HEAD(&sch->list); skb_queue_head_init(&sch->q); @@ -439,11 +421,24 @@ struct Qdisc * qdisc_create_dflt(struct net_device *dev, struct Qdisc_ops *ops) dev_hold(dev); sch->stats_lock = &dev->queue_lock; atomic_set(&sch->refcnt, 1); + + return sch; +errout: + return ERR_PTR(-err); +} + +struct Qdisc * qdisc_create_dflt(struct net_device *dev, struct Qdisc_ops *ops) +{ + struct Qdisc *sch; + + sch = qdisc_alloc(dev, ops); + if (IS_ERR(sch)) + goto errout; + if (!ops->init || ops->init(sch, NULL) == 0) return sch; - dev_put(dev); - kfree(p); +errout: return NULL; } @@ -607,6 +602,7 @@ EXPORT_SYMBOL(__netdev_watchdog_up); EXPORT_SYMBOL(noop_qdisc); EXPORT_SYMBOL(noop_qdisc_ops); EXPORT_SYMBOL(qdisc_create_dflt); +EXPORT_SYMBOL(qdisc_alloc); EXPORT_SYMBOL(qdisc_destroy); EXPORT_SYMBOL(qdisc_reset); EXPORT_SYMBOL(qdisc_restart); diff --git a/net/sched/sch_red.c b/net/sched/sch_red.c index 664d0e47374f..7845d045eec4 100644 --- a/net/sched/sch_red.c +++ b/net/sched/sch_red.c @@ -385,7 +385,7 @@ static int red_change(struct Qdisc *sch, struct rtattr *opt) memcpy(q->Stab, RTA_DATA(tb[TCA_RED_STAB-1]), 256); q->qcount = -1; - if (skb_queue_len(&sch->q) == 0) + if (skb_queue_empty(&sch->q)) PSCHED_SET_PASTPERFECT(q->qidlestart); sch_tree_unlock(sch); return 0; |