linux/net/sched/cls_api.c

615 lines
14 KiB
C
Raw Normal View History

/*
* net/sched/cls_api.c Packet classifier API.
*
* 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: Alexey Kuznetsov, <kuznet@ms2.inr.ac.ru>
*
* Changes:
*
* Eduardo J. Blanco <ejbs@netlabs.com.uy> :990222: kmod support
*
*/
#include <linux/module.h>
#include <linux/types.h>
#include <linux/kernel.h>
#include <linux/string.h>
#include <linux/errno.h>
#include <linux/skbuff.h>
#include <linux/init.h>
#include <linux/kmod.h>
#include <linux/netlink.h>
#include <linux/err.h>
include cleanup: Update gfp.h and slab.h includes to prepare for breaking implicit slab.h inclusion from percpu.h percpu.h is included by sched.h and module.h and thus ends up being included when building most .c files. percpu.h includes slab.h which in turn includes gfp.h making everything defined by the two files universally available and complicating inclusion dependencies. percpu.h -> slab.h dependency is about to be removed. Prepare for this change by updating users of gfp and slab facilities include those headers directly instead of assuming availability. As this conversion needs to touch large number of source files, the following script is used as the basis of conversion. http://userweb.kernel.org/~tj/misc/slabh-sweep.py The script does the followings. * Scan files for gfp and slab usages and update includes such that only the necessary includes are there. ie. if only gfp is used, gfp.h, if slab is used, slab.h. * When the script inserts a new include, it looks at the include blocks and try to put the new include such that its order conforms to its surrounding. It's put in the include block which contains core kernel includes, in the same order that the rest are ordered - alphabetical, Christmas tree, rev-Xmas-tree or at the end if there doesn't seem to be any matching order. * If the script can't find a place to put a new include (mostly because the file doesn't have fitting include block), it prints out an error message indicating which .h file needs to be added to the file. The conversion was done in the following steps. 1. The initial automatic conversion of all .c files updated slightly over 4000 files, deleting around 700 includes and adding ~480 gfp.h and ~3000 slab.h inclusions. The script emitted errors for ~400 files. 2. Each error was manually checked. Some didn't need the inclusion, some needed manual addition while adding it to implementation .h or embedding .c file was more appropriate for others. This step added inclusions to around 150 files. 3. The script was run again and the output was compared to the edits from #2 to make sure no file was left behind. 4. Several build tests were done and a couple of problems were fixed. e.g. lib/decompress_*.c used malloc/free() wrappers around slab APIs requiring slab.h to be added manually. 5. The script was run on all .h files but without automatically editing them as sprinkling gfp.h and slab.h inclusions around .h files could easily lead to inclusion dependency hell. Most gfp.h inclusion directives were ignored as stuff from gfp.h was usually wildly available and often used in preprocessor macros. Each slab.h inclusion directive was examined and added manually as necessary. 6. percpu.h was updated not to include slab.h. 7. Build test were done on the following configurations and failures were fixed. CONFIG_GCOV_KERNEL was turned off for all tests (as my distributed build env didn't work with gcov compiles) and a few more options had to be turned off depending on archs to make things build (like ipr on powerpc/64 which failed due to missing writeq). * x86 and x86_64 UP and SMP allmodconfig and a custom test config. * powerpc and powerpc64 SMP allmodconfig * sparc and sparc64 SMP allmodconfig * ia64 SMP allmodconfig * s390 SMP allmodconfig * alpha SMP allmodconfig * um on x86_64 SMP allmodconfig 8. percpu.h modifications were reverted so that it could be applied as a separate patch and serve as bisection point. Given the fact that I had only a couple of failures from tests on step 6, I'm fairly confident about the coverage of this conversion patch. If there is a breakage, it's likely to be something in one of the arch headers which should be easily discoverable easily on most builds of the specific arch. Signed-off-by: Tejun Heo <tj@kernel.org> Guess-its-ok-by: Christoph Lameter <cl@linux-foundation.org> Cc: Ingo Molnar <mingo@redhat.com> Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
2010-03-24 08:04:11 +00:00
#include <linux/slab.h>
#include <net/net_namespace.h>
#include <net/sock.h>
#include <net/netlink.h>
#include <net/pkt_sched.h>
#include <net/pkt_cls.h>
/* The list of all installed classifier types */
static struct tcf_proto_ops *tcf_proto_base __read_mostly;
/* Protects list of registered TC modules. It is pure SMP lock. */
static DEFINE_RWLOCK(cls_mod_lock);
/* Find classifier type by string name */
static struct tcf_proto_ops *tcf_proto_lookup_ops(struct nlattr *kind)
{
struct tcf_proto_ops *t = NULL;
if (kind) {
read_lock(&cls_mod_lock);
for (t = tcf_proto_base; t; t = t->next) {
if (nla_strcmp(kind, t->kind) == 0) {
if (!try_module_get(t->owner))
t = NULL;
break;
}
}
read_unlock(&cls_mod_lock);
}
return t;
}
/* Register(unregister) new classifier type */
int register_tcf_proto_ops(struct tcf_proto_ops *ops)
{
struct tcf_proto_ops *t, **tp;
int rc = -EEXIST;
write_lock(&cls_mod_lock);
for (tp = &tcf_proto_base; (t = *tp) != NULL; tp = &t->next)
if (!strcmp(ops->kind, t->kind))
goto out;
ops->next = NULL;
*tp = ops;
rc = 0;
out:
write_unlock(&cls_mod_lock);
return rc;
}
EXPORT_SYMBOL(register_tcf_proto_ops);
int unregister_tcf_proto_ops(struct tcf_proto_ops *ops)
{
struct tcf_proto_ops *t, **tp;
int rc = -ENOENT;
write_lock(&cls_mod_lock);
for (tp = &tcf_proto_base; (t=*tp) != NULL; tp = &t->next)
if (t == ops)
break;
if (!t)
goto out;
*tp = t->next;
rc = 0;
out:
write_unlock(&cls_mod_lock);
return rc;
}
EXPORT_SYMBOL(unregister_tcf_proto_ops);
static int tfilter_notify(struct net *net, struct sk_buff *oskb,
struct nlmsghdr *n, struct tcf_proto *tp,
unsigned long fh, int event);
/* Select new prio value from the range, managed by kernel. */
static inline u32 tcf_auto_prio(struct tcf_proto *tp)
{
u32 first = TC_H_MAKE(0xC0000000U, 0U);
if (tp)
first = tp->prio-1;
return first;
}
/* Add/change/delete/get a filter node */
static int tc_ctl_tfilter(struct sk_buff *skb, struct nlmsghdr *n, void *arg)
{
struct net *net = sock_net(skb->sk);
struct nlattr *tca[TCA_MAX + 1];
spinlock_t *root_lock;
struct tcmsg *t;
u32 protocol;
u32 prio;
u32 nprio;
u32 parent;
struct net_device *dev;
struct Qdisc *q;
struct tcf_proto **back, **chain;
struct tcf_proto *tp;
struct tcf_proto_ops *tp_ops;
const struct Qdisc_class_ops *cops;
unsigned long cl;
unsigned long fh;
int err;
int tp_created = 0;
replay:
t = NLMSG_DATA(n);
protocol = TC_H_MIN(t->tcm_info);
prio = TC_H_MAJ(t->tcm_info);
nprio = prio;
parent = t->tcm_parent;
cl = 0;
if (prio == 0) {
/* If no priority is given, user wants we allocated it. */
if (n->nlmsg_type != RTM_NEWTFILTER || !(n->nlmsg_flags&NLM_F_CREATE))
return -ENOENT;
prio = TC_H_MAKE(0x80000000U, 0U);
}
/* Find head of filter chain. */
/* Find link */
dev = __dev_get_by_index(net, t->tcm_ifindex);
if (dev == NULL)
return -ENODEV;
err = nlmsg_parse(n, sizeof(*t), tca, TCA_MAX, NULL);
if (err < 0)
return err;
/* Find qdisc */
if (!parent) {
q = dev->qdisc;
parent = q->handle;
} else {
q = qdisc_lookup(dev, TC_H_MAJ(t->tcm_parent));
if (q == NULL)
return -EINVAL;
}
/* Is it classful? */
if ((cops = q->ops->cl_ops) == NULL)
return -EINVAL;
if (cops->tcf_chain == NULL)
return -EOPNOTSUPP;
/* Do we search for filter, attached to class? */
if (TC_H_MIN(parent)) {
cl = cops->get(q, parent);
if (cl == 0)
return -ENOENT;
}
/* And the last stroke */
chain = cops->tcf_chain(q, cl);
err = -EINVAL;
if (chain == NULL)
goto errout;
/* Check the chain for existence of proto-tcf with this priority */
for (back = chain; (tp=*back) != NULL; back = &tp->next) {
if (tp->prio >= prio) {
if (tp->prio == prio) {
if (!nprio || (tp->protocol != protocol && protocol))
goto errout;
} else
tp = NULL;
break;
}
}
root_lock = qdisc_root_sleeping_lock(q);
if (tp == NULL) {
/* Proto-tcf does not exist, create new one */
if (tca[TCA_KIND] == NULL || !protocol)
goto errout;
err = -ENOENT;
if (n->nlmsg_type != RTM_NEWTFILTER || !(n->nlmsg_flags&NLM_F_CREATE))
goto errout;
/* Create new proto tcf */
err = -ENOBUFS;
tp = kzalloc(sizeof(*tp), GFP_KERNEL);
if (tp == NULL)
goto errout;
err = -ENOENT;
tp_ops = tcf_proto_lookup_ops(tca[TCA_KIND]);
if (tp_ops == NULL) {
#ifdef CONFIG_MODULES
struct nlattr *kind = tca[TCA_KIND];
char name[IFNAMSIZ];
if (kind != NULL &&
nla_strlcpy(name, kind, IFNAMSIZ) < IFNAMSIZ) {
rtnl_unlock();
request_module("cls_%s", name);
rtnl_lock();
tp_ops = tcf_proto_lookup_ops(kind);
/* We dropped the RTNL semaphore in order to
* perform the module load. So, even if we
* succeeded in loading the module we have to
* replay the request. We indicate this using
* -EAGAIN.
*/
if (tp_ops != NULL) {
module_put(tp_ops->owner);
err = -EAGAIN;
}
}
#endif
kfree(tp);
goto errout;
}
tp->ops = tp_ops;
tp->protocol = protocol;
tp->prio = nprio ? : TC_H_MAJ(tcf_auto_prio(*back));
tp->q = q;
tp->classify = tp_ops->classify;
tp->classid = parent;
err = tp_ops->init(tp);
if (err != 0) {
module_put(tp_ops->owner);
kfree(tp);
goto errout;
}
tp_created = 1;
} else if (tca[TCA_KIND] && nla_strcmp(tca[TCA_KIND], tp->ops->kind))
goto errout;
fh = tp->ops->get(tp, t->tcm_handle);
if (fh == 0) {
if (n->nlmsg_type == RTM_DELTFILTER && t->tcm_handle == 0) {
spin_lock_bh(root_lock);
*back = tp->next;
spin_unlock_bh(root_lock);
tfilter_notify(net, skb, n, tp, fh, RTM_DELTFILTER);
tcf_destroy(tp);
err = 0;
goto errout;
}
err = -ENOENT;
if (n->nlmsg_type != RTM_NEWTFILTER ||
!(n->nlmsg_flags & NLM_F_CREATE))
goto errout;
} else {
switch (n->nlmsg_type) {
case RTM_NEWTFILTER:
err = -EEXIST;
if (n->nlmsg_flags & NLM_F_EXCL) {
if (tp_created)
tcf_destroy(tp);
goto errout;
}
break;
case RTM_DELTFILTER:
err = tp->ops->delete(tp, fh);
if (err == 0)
tfilter_notify(net, skb, n, tp, fh, RTM_DELTFILTER);
goto errout;
case RTM_GETTFILTER:
err = tfilter_notify(net, skb, n, tp, fh, RTM_NEWTFILTER);
goto errout;
default:
err = -EINVAL;
goto errout;
}
}
err = tp->ops->change(tp, cl, t->tcm_handle, tca, &fh);
if (err == 0) {
if (tp_created) {
spin_lock_bh(root_lock);
tp->next = *back;
*back = tp;
spin_unlock_bh(root_lock);
}
tfilter_notify(net, skb, n, tp, fh, RTM_NEWTFILTER);
} else {
if (tp_created)
tcf_destroy(tp);
}
errout:
if (cl)
cops->put(q, cl);
if (err == -EAGAIN)
/* Replay the request. */
goto replay;
return err;
}
static int tcf_fill_node(struct sk_buff *skb, struct tcf_proto *tp,
unsigned long fh, u32 pid, u32 seq, u16 flags, int event)
{
struct tcmsg *tcm;
struct nlmsghdr *nlh;
unsigned char *b = skb_tail_pointer(skb);
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 = qdisc_dev(tp->q)->ifindex;
tcm->tcm_parent = tp->classid;
tcm->tcm_info = TC_H_MAKE(tp->prio, tp->protocol);
NLA_PUT_STRING(skb, TCA_KIND, tp->ops->kind);
tcm->tcm_handle = fh;
if (RTM_DELTFILTER != event) {
tcm->tcm_handle = 0;
if (tp->ops->dump && tp->ops->dump(tp, fh, skb, tcm) < 0)
goto nla_put_failure;
}
nlh->nlmsg_len = skb_tail_pointer(skb) - b;
return skb->len;
nlmsg_failure:
nla_put_failure:
nlmsg_trim(skb, b);
return -1;
}
static int tfilter_notify(struct net *net, struct sk_buff *oskb,
struct nlmsghdr *n, struct tcf_proto *tp,
unsigned long fh, int event)
{
struct sk_buff *skb;
u32 pid = oskb ? NETLINK_CB(oskb).pid : 0;
skb = alloc_skb(NLMSG_GOODSIZE, GFP_KERNEL);
if (!skb)
return -ENOBUFS;
if (tcf_fill_node(skb, tp, fh, pid, n->nlmsg_seq, 0, event) <= 0) {
kfree_skb(skb);
return -EINVAL;
}
return rtnetlink_send(skb, net, pid, RTNLGRP_TC,
n->nlmsg_flags & NLM_F_ECHO);
}
struct tcf_dump_args {
struct tcf_walker w;
struct sk_buff *skb;
struct netlink_callback *cb;
};
static int tcf_node_dump(struct tcf_proto *tp, unsigned long n,
struct tcf_walker *arg)
{
struct tcf_dump_args *a = (void *)arg;
return tcf_fill_node(a->skb, tp, n, NETLINK_CB(a->cb->skb).pid,
a->cb->nlh->nlmsg_seq, NLM_F_MULTI, RTM_NEWTFILTER);
}
/* called with RTNL */
static int tc_dump_tfilter(struct sk_buff *skb, struct netlink_callback *cb)
{
struct net *net = sock_net(skb->sk);
int t;
int s_t;
struct net_device *dev;
struct Qdisc *q;
struct tcf_proto *tp, **chain;
struct tcmsg *tcm = (struct tcmsg *)NLMSG_DATA(cb->nlh);
unsigned long cl = 0;
const struct Qdisc_class_ops *cops;
struct tcf_dump_args arg;
if (cb->nlh->nlmsg_len < NLMSG_LENGTH(sizeof(*tcm)))
return skb->len;
if ((dev = __dev_get_by_index(net, tcm->tcm_ifindex)) == NULL)
return skb->len;
if (!tcm->tcm_parent)
q = dev->qdisc;
else
q = qdisc_lookup(dev, TC_H_MAJ(tcm->tcm_parent));
if (!q)
goto out;
if ((cops = q->ops->cl_ops) == NULL)
goto errout;
if (cops->tcf_chain == NULL)
goto errout;
if (TC_H_MIN(tcm->tcm_parent)) {
cl = cops->get(q, tcm->tcm_parent);
if (cl == 0)
goto errout;
}
chain = cops->tcf_chain(q, cl);
if (chain == NULL)
goto errout;
s_t = cb->args[0];
for (tp=*chain, t=0; tp; tp = tp->next, t++) {
if (t < s_t) continue;
if (TC_H_MAJ(tcm->tcm_info) &&
TC_H_MAJ(tcm->tcm_info) != tp->prio)
continue;
if (TC_H_MIN(tcm->tcm_info) &&
TC_H_MIN(tcm->tcm_info) != tp->protocol)
continue;
if (t > s_t)
memset(&cb->args[1], 0, sizeof(cb->args)-sizeof(cb->args[0]));
if (cb->args[1] == 0) {
if (tcf_fill_node(skb, tp, 0, NETLINK_CB(cb->skb).pid,
cb->nlh->nlmsg_seq, NLM_F_MULTI,
RTM_NEWTFILTER) <= 0)
break;
cb->args[1] = 1;
}
if (tp->ops->walk == NULL)
continue;
arg.w.fn = tcf_node_dump;
arg.skb = skb;
arg.cb = cb;
arg.w.stop = 0;
arg.w.skip = cb->args[1]-1;
arg.w.count = 0;
tp->ops->walk(tp, &arg.w);
cb->args[1] = arg.w.count+1;
if (arg.w.stop)
break;
}
cb->args[0] = t;
errout:
if (cl)
cops->put(q, cl);
out:
return skb->len;
}
void tcf_exts_destroy(struct tcf_proto *tp, struct tcf_exts *exts)
{
#ifdef CONFIG_NET_CLS_ACT
if (exts->action) {
tcf_action_destroy(exts->action, TCA_ACT_UNBIND);
exts->action = NULL;
}
#endif
}
EXPORT_SYMBOL(tcf_exts_destroy);
int tcf_exts_validate(struct tcf_proto *tp, struct nlattr **tb,
struct nlattr *rate_tlv, struct tcf_exts *exts,
const struct tcf_ext_map *map)
{
memset(exts, 0, sizeof(*exts));
#ifdef CONFIG_NET_CLS_ACT
{
struct tc_action *act;
if (map->police && tb[map->police]) {
act = tcf_action_init_1(tb[map->police], rate_tlv,
"police", TCA_ACT_NOREPLACE,
TCA_ACT_BIND);
if (IS_ERR(act))
return PTR_ERR(act);
act->type = TCA_OLD_COMPAT;
exts->action = act;
} else if (map->action && tb[map->action]) {
act = tcf_action_init(tb[map->action], rate_tlv, NULL,
TCA_ACT_NOREPLACE, TCA_ACT_BIND);
if (IS_ERR(act))
return PTR_ERR(act);
exts->action = act;
}
}
#else
if ((map->action && tb[map->action]) ||
(map->police && tb[map->police]))
return -EOPNOTSUPP;
#endif
return 0;
}
EXPORT_SYMBOL(tcf_exts_validate);
void tcf_exts_change(struct tcf_proto *tp, struct tcf_exts *dst,
struct tcf_exts *src)
{
#ifdef CONFIG_NET_CLS_ACT
if (src->action) {
struct tc_action *act;
tcf_tree_lock(tp);
act = dst->action;
dst->action = src->action;
tcf_tree_unlock(tp);
if (act)
tcf_action_destroy(act, TCA_ACT_UNBIND);
}
#endif
}
EXPORT_SYMBOL(tcf_exts_change);
int tcf_exts_dump(struct sk_buff *skb, struct tcf_exts *exts,
const struct tcf_ext_map *map)
{
#ifdef CONFIG_NET_CLS_ACT
if (map->action && exts->action) {
/*
* again for backward compatible mode - we want
* to work with both old and new modes of entering
* tc data even if iproute2 was newer - jhs
*/
struct nlattr *nest;
if (exts->action->type != TCA_OLD_COMPAT) {
nest = nla_nest_start(skb, map->action);
if (nest == NULL)
goto nla_put_failure;
if (tcf_action_dump(skb, exts->action, 0, 0) < 0)
goto nla_put_failure;
nla_nest_end(skb, nest);
} else if (map->police) {
nest = nla_nest_start(skb, map->police);
if (nest == NULL)
goto nla_put_failure;
if (tcf_action_dump_old(skb, exts->action, 0, 0) < 0)
goto nla_put_failure;
nla_nest_end(skb, nest);
}
}
#endif
return 0;
nla_put_failure: __attribute__ ((unused))
return -1;
}
EXPORT_SYMBOL(tcf_exts_dump);
int tcf_exts_dump_stats(struct sk_buff *skb, struct tcf_exts *exts,
const struct tcf_ext_map *map)
{
#ifdef CONFIG_NET_CLS_ACT
if (exts->action)
if (tcf_action_copy_stats(skb, exts->action, 1) < 0)
goto nla_put_failure;
#endif
return 0;
nla_put_failure: __attribute__ ((unused))
return -1;
}
EXPORT_SYMBOL(tcf_exts_dump_stats);
static int __init tc_filter_init(void)
{
rtnl_register(PF_UNSPEC, RTM_NEWTFILTER, tc_ctl_tfilter, NULL);
rtnl_register(PF_UNSPEC, RTM_DELTFILTER, tc_ctl_tfilter, NULL);
rtnl_register(PF_UNSPEC, RTM_GETTFILTER, tc_ctl_tfilter,
tc_dump_tfilter);
return 0;
}
subsys_initcall(tc_filter_init);