linux-sg2042/net/sched/act_api.c

1127 lines
24 KiB
C
Raw Normal View History

/*
* net/sched/act_api.c Packet action 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.
*
* Author: Jamal Hadi Salim
*
*
*/
#include <linux/types.h>
#include <linux/kernel.h>
#include <linux/string.h>
#include <linux/errno.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 16:04:11 +08:00
#include <linux/slab.h>
#include <linux/skbuff.h>
#include <linux/init.h>
#include <linux/kmod.h>
#include <linux/err.h>
#include <net/net_namespace.h>
#include <net/sock.h>
#include <net/sch_generic.h>
#include <net/act_api.h>
#include <net/netlink.h>
void tcf_hash_destroy(struct tcf_common *p, struct tcf_hashinfo *hinfo)
{
unsigned int h = tcf_hash(p->tcfc_index, hinfo->hmask);
struct tcf_common **p1p;
for (p1p = &hinfo->htab[h]; *p1p; p1p = &(*p1p)->tcfc_next) {
if (*p1p == p) {
write_lock_bh(hinfo->lock);
*p1p = p->tcfc_next;
write_unlock_bh(hinfo->lock);
gen_kill_estimator(&p->tcfc_bstats,
&p->tcfc_rate_est);
/*
* gen_estimator est_timer() might access p->tcfc_lock
* or bstats, wait a RCU grace period before freeing p
*/
kfree_rcu(p, tcfc_rcu);
return;
}
}
WARN_ON(1);
}
EXPORT_SYMBOL(tcf_hash_destroy);
int tcf_hash_release(struct tcf_common *p, int bind,
struct tcf_hashinfo *hinfo)
{
int ret = 0;
if (p) {
if (bind)
p->tcfc_bindcnt--;
p->tcfc_refcnt--;
if (p->tcfc_bindcnt <= 0 && p->tcfc_refcnt <= 0) {
tcf_hash_destroy(p, hinfo);
ret = 1;
}
}
return ret;
}
EXPORT_SYMBOL(tcf_hash_release);
static int tcf_dump_walker(struct sk_buff *skb, struct netlink_callback *cb,
struct tc_action *a, struct tcf_hashinfo *hinfo)
{
struct tcf_common *p;
int err = 0, index = -1, i = 0, s_i = 0, n_i = 0;
struct nlattr *nest;
read_lock_bh(hinfo->lock);
s_i = cb->args[0];
for (i = 0; i < (hinfo->hmask + 1); i++) {
p = hinfo->htab[tcf_hash(i, hinfo->hmask)];
for (; p; p = p->tcfc_next) {
index++;
if (index < s_i)
continue;
a->priv = p;
a->order = n_i;
nest = nla_nest_start(skb, a->order);
if (nest == NULL)
goto nla_put_failure;
err = tcf_action_dump_1(skb, a, 0, 0);
if (err < 0) {
index--;
nlmsg_trim(skb, nest);
goto done;
}
nla_nest_end(skb, nest);
n_i++;
if (n_i >= TCA_ACT_MAX_PRIO)
goto done;
}
}
done:
read_unlock_bh(hinfo->lock);
if (n_i)
cb->args[0] += n_i;
return n_i;
nla_put_failure:
nla_nest_cancel(skb, nest);
goto done;
}
static int tcf_del_walker(struct sk_buff *skb, struct tc_action *a,
struct tcf_hashinfo *hinfo)
{
struct tcf_common *p, *s_p;
struct nlattr *nest;
int i = 0, n_i = 0;
nest = nla_nest_start(skb, a->order);
if (nest == NULL)
goto nla_put_failure;
NLA_PUT_STRING(skb, TCA_KIND, a->ops->kind);
for (i = 0; i < (hinfo->hmask + 1); i++) {
p = hinfo->htab[tcf_hash(i, hinfo->hmask)];
while (p != NULL) {
s_p = p->tcfc_next;
if (ACT_P_DELETED == tcf_hash_release(p, 0, hinfo))
module_put(a->ops->owner);
n_i++;
p = s_p;
}
}
NLA_PUT_U32(skb, TCA_FCNT, n_i);
nla_nest_end(skb, nest);
return n_i;
nla_put_failure:
nla_nest_cancel(skb, nest);
return -EINVAL;
}
int tcf_generic_walker(struct sk_buff *skb, struct netlink_callback *cb,
int type, struct tc_action *a)
{
struct tcf_hashinfo *hinfo = a->ops->hinfo;
if (type == RTM_DELACTION) {
return tcf_del_walker(skb, a, hinfo);
} else if (type == RTM_GETACTION) {
return tcf_dump_walker(skb, cb, a, hinfo);
} else {
WARN(1, "tcf_generic_walker: unknown action %d\n", type);
return -EINVAL;
}
}
EXPORT_SYMBOL(tcf_generic_walker);
struct tcf_common *tcf_hash_lookup(u32 index, struct tcf_hashinfo *hinfo)
{
struct tcf_common *p;
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_bh(hinfo->lock);
return p;
}
EXPORT_SYMBOL(tcf_hash_lookup);
u32 tcf_hash_new_index(u32 *idx_gen, struct tcf_hashinfo *hinfo)
{
u32 val = *idx_gen;
do {
if (++val == 0)
val = 1;
} while (tcf_hash_lookup(val, hinfo));
return (*idx_gen = val);
}
EXPORT_SYMBOL(tcf_hash_new_index);
int tcf_hash_search(struct tc_action *a, u32 index)
{
struct tcf_hashinfo *hinfo = a->ops->hinfo;
struct tcf_common *p = tcf_hash_lookup(index, hinfo);
if (p) {
a->priv = p;
return 1;
}
return 0;
}
EXPORT_SYMBOL(tcf_hash_search);
struct tcf_common *tcf_hash_check(u32 index, struct tc_action *a, int bind,
struct tcf_hashinfo *hinfo)
{
struct tcf_common *p = NULL;
if (index && (p = tcf_hash_lookup(index, hinfo)) != NULL) {
if (bind)
p->tcfc_bindcnt++;
p->tcfc_refcnt++;
a->priv = p;
}
return p;
}
EXPORT_SYMBOL(tcf_hash_check);
struct tcf_common *tcf_hash_create(u32 index, struct nlattr *est,
struct tc_action *a, int size, int bind,
u32 *idx_gen, struct tcf_hashinfo *hinfo)
{
struct tcf_common *p = kzalloc(size, GFP_KERNEL);
if (unlikely(!p))
return ERR_PTR(-ENOMEM);
p->tcfc_refcnt = 1;
if (bind)
p->tcfc_bindcnt = 1;
spin_lock_init(&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;
if (est) {
int err = gen_new_estimator(&p->tcfc_bstats, &p->tcfc_rate_est,
&p->tcfc_lock, est);
if (err) {
kfree(p);
return ERR_PTR(err);
}
}
a->priv = (void *) p;
return p;
}
EXPORT_SYMBOL(tcf_hash_create);
void tcf_hash_insert(struct tcf_common *p, struct tcf_hashinfo *hinfo)
{
unsigned int h = tcf_hash(p->tcfc_index, hinfo->hmask);
write_lock_bh(hinfo->lock);
p->tcfc_next = hinfo->htab[h];
hinfo->htab[h] = p;
write_unlock_bh(hinfo->lock);
}
EXPORT_SYMBOL(tcf_hash_insert);
static struct tc_action_ops *act_base = NULL;
static DEFINE_RWLOCK(act_mod_lock);
int tcf_register_action(struct tc_action_ops *act)
{
struct tc_action_ops *a, **ap;
write_lock(&act_mod_lock);
for (ap = &act_base; (a = *ap) != NULL; ap = &a->next) {
if (act->type == a->type || (strcmp(act->kind, a->kind) == 0)) {
write_unlock(&act_mod_lock);
return -EEXIST;
}
}
act->next = NULL;
*ap = act;
write_unlock(&act_mod_lock);
return 0;
}
EXPORT_SYMBOL(tcf_register_action);
int tcf_unregister_action(struct tc_action_ops *act)
{
struct tc_action_ops *a, **ap;
int err = -ENOENT;
write_lock(&act_mod_lock);
for (ap = &act_base; (a = *ap) != NULL; ap = &a->next)
if (a == act)
break;
if (a) {
*ap = a->next;
a->next = NULL;
err = 0;
}
write_unlock(&act_mod_lock);
return err;
}
EXPORT_SYMBOL(tcf_unregister_action);
/* lookup by name */
static struct tc_action_ops *tc_lookup_action_n(char *kind)
{
struct tc_action_ops *a = NULL;
if (kind) {
read_lock(&act_mod_lock);
for (a = act_base; a; a = a->next) {
if (strcmp(kind, a->kind) == 0) {
if (!try_module_get(a->owner)) {
read_unlock(&act_mod_lock);
return NULL;
}
break;
}
}
read_unlock(&act_mod_lock);
}
return a;
}
/* lookup by nlattr */
static struct tc_action_ops *tc_lookup_action(struct nlattr *kind)
{
struct tc_action_ops *a = NULL;
if (kind) {
read_lock(&act_mod_lock);
for (a = act_base; a; a = a->next) {
if (nla_strcmp(kind, a->kind) == 0) {
if (!try_module_get(a->owner)) {
read_unlock(&act_mod_lock);
return NULL;
}
break;
}
}
read_unlock(&act_mod_lock);
}
return a;
}
#if 0
/* lookup by id */
static struct tc_action_ops *tc_lookup_action_id(u32 type)
{
struct tc_action_ops *a = NULL;
if (type) {
read_lock(&act_mod_lock);
for (a = act_base; a; a = a->next) {
if (a->type == type) {
if (!try_module_get(a->owner)) {
read_unlock(&act_mod_lock);
return NULL;
}
break;
}
}
read_unlock(&act_mod_lock);
}
return a;
}
#endif
int tcf_action_exec(struct sk_buff *skb, const struct tc_action *act,
struct tcf_result *res)
{
const struct tc_action *a;
int ret = -1;
if (skb->tc_verd & TC_NCLS) {
skb->tc_verd = CLR_TC_NCLS(skb->tc_verd);
ret = TC_ACT_OK;
goto exec_done;
}
while ((a = act) != NULL) {
repeat:
if (a->ops && a->ops->act) {
ret = a->ops->act(skb, a, res);
if (TC_MUNGED & skb->tc_verd) {
/* copied already, allow trampling */
skb->tc_verd = SET_TC_OK2MUNGE(skb->tc_verd);
skb->tc_verd = CLR_TC_MUNGED(skb->tc_verd);
}
if (ret == TC_ACT_REPEAT)
goto repeat; /* we need a ttl - JHS */
if (ret != TC_ACT_PIPE)
goto exec_done;
}
act = a->next;
}
exec_done:
return ret;
}
EXPORT_SYMBOL(tcf_action_exec);
void tcf_action_destroy(struct tc_action *act, int bind)
{
struct tc_action *a;
for (a = act; a; a = act) {
if (a->ops && a->ops->cleanup) {
if (a->ops->cleanup(a, bind) == ACT_P_DELETED)
module_put(a->ops->owner);
act = act->next;
kfree(a);
} else {
/*FIXME: Remove later - catch insertion bugs*/
WARN(1, "tcf_action_destroy: BUG? destroying NULL ops\n");
act = act->next;
kfree(a);
}
}
}
int
tcf_action_dump_old(struct sk_buff *skb, struct tc_action *a, int bind, int ref)
{
int err = -EINVAL;
if (a->ops == NULL || a->ops->dump == NULL)
return err;
return a->ops->dump(skb, a, bind, ref);
}
int
tcf_action_dump_1(struct sk_buff *skb, struct tc_action *a, int bind, int ref)
{
int err = -EINVAL;
unsigned char *b = skb_tail_pointer(skb);
struct nlattr *nest;
if (a->ops == NULL || a->ops->dump == NULL)
return err;
NLA_PUT_STRING(skb, TCA_KIND, a->ops->kind);
if (tcf_action_copy_stats(skb, a, 0))
goto nla_put_failure;
nest = nla_nest_start(skb, TCA_OPTIONS);
if (nest == NULL)
goto nla_put_failure;
err = tcf_action_dump_old(skb, a, bind, ref);
if (err > 0) {
nla_nest_end(skb, nest);
return err;
}
nla_put_failure:
nlmsg_trim(skb, b);
return -1;
}
EXPORT_SYMBOL(tcf_action_dump_1);
int
tcf_action_dump(struct sk_buff *skb, struct tc_action *act, int bind, int ref)
{
struct tc_action *a;
int err = -EINVAL;
struct nlattr *nest;
while ((a = act) != NULL) {
act = a->next;
nest = nla_nest_start(skb, a->order);
if (nest == NULL)
goto nla_put_failure;
err = tcf_action_dump_1(skb, a, bind, ref);
if (err < 0)
goto errout;
nla_nest_end(skb, nest);
}
return 0;
nla_put_failure:
err = -EINVAL;
errout:
nla_nest_cancel(skb, nest);
return err;
}
struct tc_action *tcf_action_init_1(struct nlattr *nla, struct nlattr *est,
char *name, int ovr, int bind)
{
struct tc_action *a;
struct tc_action_ops *a_o;
char act_name[IFNAMSIZ];
struct nlattr *tb[TCA_ACT_MAX + 1];
struct nlattr *kind;
int err;
if (name == NULL) {
err = nla_parse_nested(tb, TCA_ACT_MAX, nla, NULL);
if (err < 0)
goto err_out;
err = -EINVAL;
kind = tb[TCA_ACT_KIND];
if (kind == NULL)
goto err_out;
if (nla_strlcpy(act_name, kind, IFNAMSIZ) >= IFNAMSIZ)
goto err_out;
} else {
err = -EINVAL;
if (strlcpy(act_name, name, IFNAMSIZ) >= IFNAMSIZ)
goto err_out;
}
a_o = tc_lookup_action_n(act_name);
if (a_o == NULL) {
#ifdef CONFIG_MODULES
rtnl_unlock();
request_module("act_%s", act_name);
rtnl_lock();
a_o = tc_lookup_action_n(act_name);
/* We dropped the RTNL semaphore in order to
* perform the module load. So, even if we
* succeeded in loading the module we have to
* tell the caller to replay the request. We
* indicate this using -EAGAIN.
*/
if (a_o != NULL) {
err = -EAGAIN;
goto err_mod;
}
#endif
err = -ENOENT;
goto err_out;
}
err = -ENOMEM;
a = kzalloc(sizeof(*a), GFP_KERNEL);
if (a == NULL)
goto err_mod;
/* backward compatibility for policer */
if (name == NULL)
err = a_o->init(tb[TCA_ACT_OPTIONS], est, a, ovr, bind);
else
err = a_o->init(nla, est, a, ovr, bind);
if (err < 0)
goto err_free;
/* module count goes up only when brand new policy is created
* if it exists and is only bound to in a_o->init() then
* ACT_P_CREATED is not returned (a zero is).
*/
if (err != ACT_P_CREATED)
module_put(a_o->owner);
a->ops = a_o;
return a;
err_free:
kfree(a);
err_mod:
module_put(a_o->owner);
err_out:
return ERR_PTR(err);
}
struct tc_action *tcf_action_init(struct nlattr *nla, struct nlattr *est,
char *name, int ovr, int bind)
{
struct nlattr *tb[TCA_ACT_MAX_PRIO + 1];
struct tc_action *head = NULL, *act, *act_prev = NULL;
int err;
int i;
err = nla_parse_nested(tb, TCA_ACT_MAX_PRIO, nla, NULL);
if (err < 0)
return ERR_PTR(err);
for (i = 1; i <= TCA_ACT_MAX_PRIO && tb[i]; i++) {
act = tcf_action_init_1(tb[i], est, name, ovr, bind);
if (IS_ERR(act))
goto err;
act->order = i;
if (head == NULL)
head = act;
else
act_prev->next = act;
act_prev = act;
}
return head;
err:
if (head != NULL)
tcf_action_destroy(head, bind);
return act;
}
int tcf_action_copy_stats(struct sk_buff *skb, struct tc_action *a,
int compat_mode)
{
int err = 0;
struct gnet_dump d;
struct tcf_act_hdr *h = a->priv;
if (h == NULL)
goto errout;
/* compat_mode being true specifies a call that is supposed
* to add additional backward compatibility statistic TLVs.
*/
if (compat_mode) {
if (a->type == TCA_OLD_COMPAT)
err = gnet_stats_start_copy_compat(skb, 0,
TCA_STATS, TCA_XSTATS, &h->tcf_lock, &d);
else
return 0;
} else
err = gnet_stats_start_copy(skb, TCA_ACT_STATS,
&h->tcf_lock, &d);
if (err < 0)
goto errout;
if (a->ops != NULL && a->ops->get_stats != NULL)
if (a->ops->get_stats(skb, a) < 0)
goto errout;
if (gnet_stats_copy_basic(&d, &h->tcf_bstats) < 0 ||
pkt_sched: gen_estimator: Dont report fake rate estimators Jarek Poplawski a écrit : > > > Hmm... So you made me to do some "real" work here, and guess what?: > there is one serious checkpatch warning! ;-) Plus, this new parameter > should be added to the function description. Otherwise: > Signed-off-by: Jarek Poplawski <jarkao2@gmail.com> > > Thanks, > Jarek P. > > PS: I guess full "Don't" would show we really mean it... Okay :) Here is the last round, before the night ! Thanks again [RFC] pkt_sched: gen_estimator: Don't report fake rate estimators We currently send TCA_STATS_RATE_EST elements to netlink users, even if no estimator is running. # tc -s -d qdisc qdisc pfifo_fast 0: dev eth0 root bands 3 priomap 1 2 2 2 1 2 0 0 1 1 1 1 1 1 1 1 Sent 112833764978 bytes 1495081739 pkt (dropped 0, overlimits 0 requeues 0) rate 0bit 0pps backlog 0b 0p requeues 0 User has no way to tell if the "rate 0bit 0pps" is a real estimation, or a fake one (because no estimator is active) After this patch, tc command output is : $ tc -s -d qdisc qdisc pfifo_fast 0: dev eth0 root bands 3 priomap 1 2 2 2 1 2 0 0 1 1 1 1 1 1 1 1 Sent 561075 bytes 1196 pkt (dropped 0, overlimits 0 requeues 0) backlog 0b 0p requeues 0 We add a parameter to gnet_stats_copy_rate_est() function so that it can use gen_estimator_active(bstats, r), as suggested by Jarek. This parameter can be NULL if check is not necessary, (htb for example has a mandatory rate estimator) Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com> Signed-off-by: Jarek Poplawski <jarkao2@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2009-10-02 18:32:18 +08:00
gnet_stats_copy_rate_est(&d, &h->tcf_bstats,
&h->tcf_rate_est) < 0 ||
gnet_stats_copy_queue(&d, &h->tcf_qstats) < 0)
goto errout;
if (gnet_stats_finish_copy(&d) < 0)
goto errout;
return 0;
errout:
return -1;
}
static int
tca_get_fill(struct sk_buff *skb, struct tc_action *a, u32 pid, u32 seq,
u16 flags, int event, int bind, int ref)
{
struct tcamsg *t;
struct nlmsghdr *nlh;
unsigned char *b = skb_tail_pointer(skb);
struct nlattr *nest;
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;
nest = nla_nest_start(skb, TCA_ACT_TAB);
if (nest == NULL)
goto nla_put_failure;
if (tcf_action_dump(skb, a, bind, ref) < 0)
goto nla_put_failure;
nla_nest_end(skb, nest);
nlh->nlmsg_len = skb_tail_pointer(skb) - b;
return skb->len;
nla_put_failure:
nlmsg_failure:
nlmsg_trim(skb, b);
return -1;
}
static int
act_get_notify(struct net *net, u32 pid, struct nlmsghdr *n,
struct tc_action *a, int event)
{
struct sk_buff *skb;
skb = alloc_skb(NLMSG_GOODSIZE, GFP_KERNEL);
if (!skb)
return -ENOBUFS;
if (tca_get_fill(skb, a, pid, n->nlmsg_seq, 0, event, 0, 0) <= 0) {
kfree_skb(skb);
return -EINVAL;
}
return rtnl_unicast(skb, net, pid);
}
static struct tc_action *
tcf_action_get_1(struct nlattr *nla, struct nlmsghdr *n, u32 pid)
{
struct nlattr *tb[TCA_ACT_MAX + 1];
struct tc_action *a;
int index;
int err;
err = nla_parse_nested(tb, TCA_ACT_MAX, nla, NULL);
if (err < 0)
goto err_out;
err = -EINVAL;
if (tb[TCA_ACT_INDEX] == NULL ||
nla_len(tb[TCA_ACT_INDEX]) < sizeof(index))
goto err_out;
index = nla_get_u32(tb[TCA_ACT_INDEX]);
err = -ENOMEM;
a = kzalloc(sizeof(struct tc_action), GFP_KERNEL);
if (a == NULL)
goto err_out;
err = -EINVAL;
a->ops = tc_lookup_action(tb[TCA_ACT_KIND]);
if (a->ops == NULL)
goto err_free;
if (a->ops->lookup == NULL)
goto err_mod;
err = -ENOENT;
if (a->ops->lookup(a, index) == 0)
goto err_mod;
module_put(a->ops->owner);
return a;
err_mod:
module_put(a->ops->owner);
err_free:
kfree(a);
err_out:
return ERR_PTR(err);
}
static void cleanup_a(struct tc_action *act)
{
struct tc_action *a;
for (a = act; a; a = act) {
act = a->next;
kfree(a);
}
}
static struct tc_action *create_a(int i)
{
struct tc_action *act;
act = kzalloc(sizeof(*act), GFP_KERNEL);
if (act == NULL) {
pr_debug("create_a: failed to alloc!\n");
return NULL;
}
act->order = i;
return act;
}
static int tca_action_flush(struct net *net, struct nlattr *nla,
struct nlmsghdr *n, u32 pid)
{
struct sk_buff *skb;
unsigned char *b;
struct nlmsghdr *nlh;
struct tcamsg *t;
struct netlink_callback dcb;
struct nlattr *nest;
struct nlattr *tb[TCA_ACT_MAX + 1];
struct nlattr *kind;
struct tc_action *a = create_a(0);
int err = -ENOMEM;
if (a == NULL) {
pr_debug("tca_action_flush: couldnt create tc_action\n");
return err;
}
skb = alloc_skb(NLMSG_GOODSIZE, GFP_KERNEL);
if (!skb) {
pr_debug("tca_action_flush: failed skb alloc\n");
kfree(a);
return err;
}
b = skb_tail_pointer(skb);
err = nla_parse_nested(tb, TCA_ACT_MAX, nla, NULL);
if (err < 0)
goto err_out;
err = -EINVAL;
kind = tb[TCA_ACT_KIND];
a->ops = tc_lookup_action(kind);
if (a->ops == NULL)
goto err_out;
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;
nest = nla_nest_start(skb, TCA_ACT_TAB);
if (nest == NULL)
goto nla_put_failure;
err = a->ops->walk(skb, &dcb, RTM_DELACTION, a);
if (err < 0)
goto nla_put_failure;
if (err == 0)
goto noflush_out;
nla_nest_end(skb, nest);
nlh->nlmsg_len = skb_tail_pointer(skb) - b;
nlh->nlmsg_flags |= NLM_F_ROOT;
module_put(a->ops->owner);
kfree(a);
err = rtnetlink_send(skb, net, pid, RTNLGRP_TC,
n->nlmsg_flags & NLM_F_ECHO);
if (err > 0)
return 0;
return err;
nla_put_failure:
nlmsg_failure:
module_put(a->ops->owner);
err_out:
noflush_out:
kfree_skb(skb);
kfree(a);
return err;
}
static int
tca_action_gd(struct net *net, struct nlattr *nla, struct nlmsghdr *n,
u32 pid, int event)
{
int i, ret;
struct nlattr *tb[TCA_ACT_MAX_PRIO + 1];
struct tc_action *head = NULL, *act, *act_prev = NULL;
ret = nla_parse_nested(tb, TCA_ACT_MAX_PRIO, nla, NULL);
if (ret < 0)
return ret;
if (event == RTM_DELACTION && n->nlmsg_flags & NLM_F_ROOT) {
if (tb[1] != NULL)
return tca_action_flush(net, tb[1], n, pid);
else
return -EINVAL;
}
for (i = 1; i <= TCA_ACT_MAX_PRIO && tb[i]; i++) {
act = tcf_action_get_1(tb[i], n, pid);
if (IS_ERR(act)) {
ret = PTR_ERR(act);
goto err;
}
act->order = i;
if (head == NULL)
head = act;
else
act_prev->next = act;
act_prev = act;
}
if (event == RTM_GETACTION)
ret = act_get_notify(net, pid, n, head, event);
else { /* delete */
struct sk_buff *skb;
skb = alloc_skb(NLMSG_GOODSIZE, GFP_KERNEL);
if (!skb) {
ret = -ENOBUFS;
goto err;
}
if (tca_get_fill(skb, head, pid, n->nlmsg_seq, 0, event,
0, 1) <= 0) {
kfree_skb(skb);
ret = -EINVAL;
goto err;
}
/* now do the delete */
tcf_action_destroy(head, 0);
ret = rtnetlink_send(skb, net, pid, RTNLGRP_TC,
n->nlmsg_flags & NLM_F_ECHO);
if (ret > 0)
return 0;
return ret;
}
err:
cleanup_a(head);
return ret;
}
static int tcf_add_notify(struct net *net, struct tc_action *a,
u32 pid, u32 seq, int event, u16 flags)
{
struct tcamsg *t;
struct nlmsghdr *nlh;
struct sk_buff *skb;
struct nlattr *nest;
unsigned char *b;
int err = 0;
skb = alloc_skb(NLMSG_GOODSIZE, GFP_KERNEL);
if (!skb)
return -ENOBUFS;
b = skb_tail_pointer(skb);
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;
nest = nla_nest_start(skb, TCA_ACT_TAB);
if (nest == NULL)
goto nla_put_failure;
if (tcf_action_dump(skb, a, 0, 0) < 0)
goto nla_put_failure;
nla_nest_end(skb, nest);
nlh->nlmsg_len = skb_tail_pointer(skb) - b;
NETLINK_CB(skb).dst_group = RTNLGRP_TC;
err = rtnetlink_send(skb, net, pid, RTNLGRP_TC, flags & NLM_F_ECHO);
if (err > 0)
err = 0;
return err;
nla_put_failure:
nlmsg_failure:
kfree_skb(skb);
return -1;
}
static int
tcf_action_add(struct net *net, struct nlattr *nla, struct nlmsghdr *n,
u32 pid, int ovr)
{
int ret = 0;
struct tc_action *act;
struct tc_action *a;
u32 seq = n->nlmsg_seq;
act = tcf_action_init(nla, NULL, NULL, ovr, 0);
if (act == NULL)
goto done;
if (IS_ERR(act)) {
ret = PTR_ERR(act);
goto done;
}
/* dump then free all the actions after update; inserted policy
* stays intact
*/
ret = tcf_add_notify(net, act, pid, seq, RTM_NEWACTION, n->nlmsg_flags);
for (a = act; a; a = act) {
act = a->next;
kfree(a);
}
done:
return ret;
}
static int tc_ctl_action(struct sk_buff *skb, struct nlmsghdr *n, void *arg)
{
struct net *net = sock_net(skb->sk);
struct nlattr *tca[TCA_ACT_MAX + 1];
u32 pid = skb ? NETLINK_CB(skb).pid : 0;
int ret = 0, ovr = 0;
ret = nlmsg_parse(n, sizeof(struct tcamsg), tca, TCA_ACT_MAX, NULL);
if (ret < 0)
return ret;
if (tca[TCA_ACT_TAB] == NULL) {
pr_notice("tc_ctl_action: received NO action attribs\n");
return -EINVAL;
}
/* n->nlmsg_flags & NLM_F_CREATE */
switch (n->nlmsg_type) {
case RTM_NEWACTION:
/* we are going to assume all other flags
* imply create only if it doesn't exist
* Note that CREATE | EXCL implies that
* but since we want avoid ambiguity (eg when flags
* is zero) then just set this
*/
if (n->nlmsg_flags & NLM_F_REPLACE)
ovr = 1;
replay:
ret = tcf_action_add(net, tca[TCA_ACT_TAB], n, pid, ovr);
if (ret == -EAGAIN)
goto replay;
break;
case RTM_DELACTION:
ret = tca_action_gd(net, tca[TCA_ACT_TAB], n,
pid, RTM_DELACTION);
break;
case RTM_GETACTION:
ret = tca_action_gd(net, tca[TCA_ACT_TAB], n,
pid, RTM_GETACTION);
break;
default:
BUG();
}
return ret;
}
static struct nlattr *
find_dump_kind(const struct nlmsghdr *n)
{
struct nlattr *tb1, *tb2[TCA_ACT_MAX + 1];
struct nlattr *tb[TCA_ACT_MAX_PRIO + 1];
struct nlattr *nla[TCAA_MAX + 1];
struct nlattr *kind;
if (nlmsg_parse(n, sizeof(struct tcamsg), nla, TCAA_MAX, NULL) < 0)
return NULL;
tb1 = nla[TCA_ACT_TAB];
if (tb1 == NULL)
return NULL;
if (nla_parse(tb, TCA_ACT_MAX_PRIO, nla_data(tb1),
NLMSG_ALIGN(nla_len(tb1)), NULL) < 0)
return NULL;
if (tb[1] == NULL)
return NULL;
if (nla_parse(tb2, TCA_ACT_MAX, nla_data(tb[1]),
nla_len(tb[1]), NULL) < 0)
return NULL;
kind = tb2[TCA_ACT_KIND];
return kind;
}
static int
tc_dump_action(struct sk_buff *skb, struct netlink_callback *cb)
{
struct nlmsghdr *nlh;
unsigned char *b = skb_tail_pointer(skb);
struct nlattr *nest;
struct tc_action_ops *a_o;
struct tc_action a;
int ret = 0;
struct tcamsg *t = (struct tcamsg *) NLMSG_DATA(cb->nlh);
struct nlattr *kind = find_dump_kind(cb->nlh);
if (kind == NULL) {
pr_info("tc_dump_action: action bad kind\n");
return 0;
}
a_o = tc_lookup_action(kind);
if (a_o == NULL)
return 0;
memset(&a, 0, sizeof(struct tc_action));
a.ops = a_o;
if (a_o->walk == NULL) {
WARN(1, "tc_dump_action: %s !capable of dumping table\n",
a_o->kind);
goto nla_put_failure;
}
nlh = NLMSG_PUT(skb, NETLINK_CB(cb->skb).pid, cb->nlh->nlmsg_seq,
cb->nlh->nlmsg_type, sizeof(*t));
t = NLMSG_DATA(nlh);
t->tca_family = AF_UNSPEC;
t->tca__pad1 = 0;
t->tca__pad2 = 0;
nest = nla_nest_start(skb, TCA_ACT_TAB);
if (nest == NULL)
goto nla_put_failure;
ret = a_o->walk(skb, cb, RTM_GETACTION, &a);
if (ret < 0)
goto nla_put_failure;
if (ret > 0) {
nla_nest_end(skb, nest);
ret = skb->len;
} else
nla_nest_cancel(skb, nest);
nlh->nlmsg_len = skb_tail_pointer(skb) - b;
if (NETLINK_CB(cb->skb).pid && ret)
nlh->nlmsg_flags |= NLM_F_MULTI;
module_put(a_o->owner);
return skb->len;
nla_put_failure:
nlmsg_failure:
module_put(a_o->owner);
nlmsg_trim(skb, b);
return skb->len;
}
static int __init tc_action_init(void)
{
rtnl_register(PF_UNSPEC, RTM_NEWACTION, tc_ctl_action, NULL, NULL);
rtnl_register(PF_UNSPEC, RTM_DELACTION, tc_ctl_action, NULL, NULL);
rtnl_register(PF_UNSPEC, RTM_GETACTION, tc_ctl_action, tc_dump_action,
NULL);
return 0;
}
subsys_initcall(tc_action_init);