linux/net/sched/cls_fw.c

457 lines
9.6 KiB
C
Raw Normal View History

// SPDX-License-Identifier: GPL-2.0-or-later
/*
* net/sched/cls_fw.c Classifier mapping ipchains' fwmark to traffic class.
*
* Authors: Alexey Kuznetsov, <kuznet@ms2.inr.ac.ru>
*
* Changes:
* Karlis Peisenieks <karlis@mt.lv> : 990415 : fw_walk off by one
* Karlis Peisenieks <karlis@mt.lv> : 990415 : fw_delete killed all the filter (and kernel).
* Alex <alex@pilotsoft.com> : 2004xxyy: Added Action extension
*/
#include <linux/module.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/types.h>
#include <linux/kernel.h>
#include <linux/string.h>
#include <linux/errno.h>
#include <linux/skbuff.h>
#include <net/netlink.h>
#include <net/act_api.h>
#include <net/pkt_cls.h>
#include <net/sch_generic.h>
#define HTSIZE 256
struct fw_head {
u32 mask;
struct fw_filter __rcu *ht[HTSIZE];
struct rcu_head rcu;
};
struct fw_filter {
struct fw_filter __rcu *next;
u32 id;
struct tcf_result res;
int ifindex;
struct tcf_exts exts;
struct tcf_proto *tp;
struct rcu_work rwork;
};
static u32 fw_hash(u32 handle)
{
handle ^= (handle >> 16);
handle ^= (handle >> 8);
return handle % HTSIZE;
}
static int fw_classify(struct sk_buff *skb, const struct tcf_proto *tp,
struct tcf_result *res)
{
struct fw_head *head = rcu_dereference_bh(tp->root);
struct fw_filter *f;
int r;
u32 id = skb->mark;
if (head != NULL) {
id &= head->mask;
for (f = rcu_dereference_bh(head->ht[fw_hash(id)]); f;
f = rcu_dereference_bh(f->next)) {
if (f->id == id) {
*res = f->res;
if (!tcf_match_indev(skb, f->ifindex))
continue;
r = tcf_exts_exec(skb, &f->exts, res);
if (r < 0)
continue;
return r;
}
}
} else {
struct Qdisc *q = tcf_block_q(tp->chain->block);
/* Old method: classify the packet using its skb mark. */
if (id && (TC_H_MAJ(id) == 0 ||
!(TC_H_MAJ(id ^ q->handle)))) {
res->classid = id;
res->class = 0;
return 0;
}
}
return -1;
}
static void *fw_get(struct tcf_proto *tp, u32 handle)
{
struct fw_head *head = rtnl_dereference(tp->root);
struct fw_filter *f;
if (head == NULL)
return NULL;
f = rtnl_dereference(head->ht[fw_hash(handle)]);
for (; f; f = rtnl_dereference(f->next)) {
if (f->id == handle)
return f;
}
return NULL;
}
static int fw_init(struct tcf_proto *tp)
{
/* We don't allocate fw_head here, because in the old method
* we don't need it at all.
*/
return 0;
}
static void __fw_delete_filter(struct fw_filter *f)
{
tcf_exts_destroy(&f->exts);
tcf_exts_put_net(&f->exts);
kfree(f);
}
static void fw_delete_filter_work(struct work_struct *work)
{
struct fw_filter *f = container_of(to_rcu_work(work),
struct fw_filter,
rwork);
rtnl_lock();
__fw_delete_filter(f);
rtnl_unlock();
}
static void fw_destroy(struct tcf_proto *tp, bool rtnl_held,
struct netlink_ext_ack *extack)
{
struct fw_head *head = rtnl_dereference(tp->root);
struct fw_filter *f;
int h;
if (head == NULL)
return;
for (h = 0; h < HTSIZE; h++) {
while ((f = rtnl_dereference(head->ht[h])) != NULL) {
RCU_INIT_POINTER(head->ht[h],
rtnl_dereference(f->next));
tcf_unbind_filter(tp, &f->res);
if (tcf_exts_get_net(&f->exts))
tcf_queue_work(&f->rwork, fw_delete_filter_work);
else
__fw_delete_filter(f);
}
}
kfree_rcu(head, rcu);
}
static int fw_delete(struct tcf_proto *tp, void *arg, bool *last,
bool rtnl_held, struct netlink_ext_ack *extack)
{
struct fw_head *head = rtnl_dereference(tp->root);
struct fw_filter *f = arg;
struct fw_filter __rcu **fp;
struct fw_filter *pfp;
int ret = -EINVAL;
int h;
if (head == NULL || f == NULL)
goto out;
fp = &head->ht[fw_hash(f->id)];
for (pfp = rtnl_dereference(*fp); pfp;
fp = &pfp->next, pfp = rtnl_dereference(*fp)) {
if (pfp == f) {
RCU_INIT_POINTER(*fp, rtnl_dereference(f->next));
tcf_unbind_filter(tp, &f->res);
tcf_exts_get_net(&f->exts);
tcf_queue_work(&f->rwork, fw_delete_filter_work);
ret = 0;
break;
}
}
*last = true;
for (h = 0; h < HTSIZE; h++) {
if (rcu_access_pointer(head->ht[h])) {
*last = false;
break;
}
}
out:
return ret;
}
static const struct nla_policy fw_policy[TCA_FW_MAX + 1] = {
[TCA_FW_CLASSID] = { .type = NLA_U32 },
[TCA_FW_INDEV] = { .type = NLA_STRING, .len = IFNAMSIZ },
[TCA_FW_MASK] = { .type = NLA_U32 },
};
static int fw_set_parms(struct net *net, struct tcf_proto *tp,
struct fw_filter *f, struct nlattr **tb,
struct nlattr **tca, unsigned long base, bool ovr,
struct netlink_ext_ack *extack)
{
struct fw_head *head = rtnl_dereference(tp->root);
u32 mask;
int err;
err = tcf_exts_validate(net, tp, tb, tca[TCA_RATE], &f->exts, ovr,
true, extack);
if (err < 0)
return err;
if (tb[TCA_FW_CLASSID]) {
f->res.classid = nla_get_u32(tb[TCA_FW_CLASSID]);
tcf_bind_filter(tp, &f->res, base);
}
if (tb[TCA_FW_INDEV]) {
int ret;
ret = tcf_change_indev(net, tb[TCA_FW_INDEV], extack);
if (ret < 0)
return ret;
f->ifindex = ret;
}
err = -EINVAL;
if (tb[TCA_FW_MASK]) {
mask = nla_get_u32(tb[TCA_FW_MASK]);
if (mask != head->mask)
return err;
} else if (head->mask != 0xFFFFFFFF)
return err;
return 0;
}
static int fw_change(struct net *net, struct sk_buff *in_skb,
struct tcf_proto *tp, unsigned long base,
u32 handle, struct nlattr **tca, void **arg,
bool ovr, bool rtnl_held,
struct netlink_ext_ack *extack)
{
struct fw_head *head = rtnl_dereference(tp->root);
struct fw_filter *f = *arg;
struct nlattr *opt = tca[TCA_OPTIONS];
struct nlattr *tb[TCA_FW_MAX + 1];
int err;
if (!opt)
return handle ? -EINVAL : 0; /* Succeed if it is old method. */
netlink: make validation more configurable for future strictness We currently have two levels of strict validation: 1) liberal (default) - undefined (type >= max) & NLA_UNSPEC attributes accepted - attribute length >= expected accepted - garbage at end of message accepted 2) strict (opt-in) - NLA_UNSPEC attributes accepted - attribute length >= expected accepted Split out parsing strictness into four different options: * TRAILING - check that there's no trailing data after parsing attributes (in message or nested) * MAXTYPE - reject attrs > max known type * UNSPEC - reject attributes with NLA_UNSPEC policy entries * STRICT_ATTRS - strictly validate attribute size The default for future things should be *everything*. The current *_strict() is a combination of TRAILING and MAXTYPE, and is renamed to _deprecated_strict(). The current regular parsing has none of this, and is renamed to *_parse_deprecated(). Additionally it allows us to selectively set one of the new flags even on old policies. Notably, the UNSPEC flag could be useful in this case, since it can be arranged (by filling in the policy) to not be an incompatible userspace ABI change, but would then going forward prevent forgetting attribute entries. Similar can apply to the POLICY flag. We end up with the following renames: * nla_parse -> nla_parse_deprecated * nla_parse_strict -> nla_parse_deprecated_strict * nlmsg_parse -> nlmsg_parse_deprecated * nlmsg_parse_strict -> nlmsg_parse_deprecated_strict * nla_parse_nested -> nla_parse_nested_deprecated * nla_validate_nested -> nla_validate_nested_deprecated Using spatch, of course: @@ expression TB, MAX, HEAD, LEN, POL, EXT; @@ -nla_parse(TB, MAX, HEAD, LEN, POL, EXT) +nla_parse_deprecated(TB, MAX, HEAD, LEN, POL, EXT) @@ expression NLH, HDRLEN, TB, MAX, POL, EXT; @@ -nlmsg_parse(NLH, HDRLEN, TB, MAX, POL, EXT) +nlmsg_parse_deprecated(NLH, HDRLEN, TB, MAX, POL, EXT) @@ expression NLH, HDRLEN, TB, MAX, POL, EXT; @@ -nlmsg_parse_strict(NLH, HDRLEN, TB, MAX, POL, EXT) +nlmsg_parse_deprecated_strict(NLH, HDRLEN, TB, MAX, POL, EXT) @@ expression TB, MAX, NLA, POL, EXT; @@ -nla_parse_nested(TB, MAX, NLA, POL, EXT) +nla_parse_nested_deprecated(TB, MAX, NLA, POL, EXT) @@ expression START, MAX, POL, EXT; @@ -nla_validate_nested(START, MAX, POL, EXT) +nla_validate_nested_deprecated(START, MAX, POL, EXT) @@ expression NLH, HDRLEN, MAX, POL, EXT; @@ -nlmsg_validate(NLH, HDRLEN, MAX, POL, EXT) +nlmsg_validate_deprecated(NLH, HDRLEN, MAX, POL, EXT) For this patch, don't actually add the strict, non-renamed versions yet so that it breaks compile if I get it wrong. Also, while at it, make nla_validate and nla_parse go down to a common __nla_validate_parse() function to avoid code duplication. Ultimately, this allows us to have very strict validation for every new caller of nla_parse()/nlmsg_parse() etc as re-introduced in the next patch, while existing things will continue to work as is. In effect then, this adds fully strict validation for any new command. Signed-off-by: Johannes Berg <johannes.berg@intel.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-04-26 20:07:28 +08:00
err = nla_parse_nested_deprecated(tb, TCA_FW_MAX, opt, fw_policy,
NULL);
if (err < 0)
return err;
if (f) {
struct fw_filter *pfp, *fnew;
struct fw_filter __rcu **fp;
if (f->id != handle && handle)
return -EINVAL;
fnew = kzalloc(sizeof(struct fw_filter), GFP_KERNEL);
if (!fnew)
return -ENOBUFS;
fnew->id = f->id;
fnew->res = f->res;
fnew->ifindex = f->ifindex;
fnew->tp = f->tp;
err = tcf_exts_init(&fnew->exts, net, TCA_FW_ACT,
TCA_FW_POLICE);
if (err < 0) {
kfree(fnew);
return err;
}
err = fw_set_parms(net, tp, fnew, tb, tca, base, ovr, extack);
if (err < 0) {
tcf_exts_destroy(&fnew->exts);
kfree(fnew);
return err;
}
fp = &head->ht[fw_hash(fnew->id)];
for (pfp = rtnl_dereference(*fp); pfp;
fp = &pfp->next, pfp = rtnl_dereference(*fp))
if (pfp == f)
break;
RCU_INIT_POINTER(fnew->next, rtnl_dereference(pfp->next));
rcu_assign_pointer(*fp, fnew);
tcf_unbind_filter(tp, &f->res);
tcf_exts_get_net(&f->exts);
tcf_queue_work(&f->rwork, fw_delete_filter_work);
*arg = fnew;
return err;
}
if (!handle)
return -EINVAL;
if (!head) {
u32 mask = 0xFFFFFFFF;
if (tb[TCA_FW_MASK])
mask = nla_get_u32(tb[TCA_FW_MASK]);
head = kzalloc(sizeof(*head), GFP_KERNEL);
if (!head)
return -ENOBUFS;
head->mask = mask;
rcu_assign_pointer(tp->root, head);
}
f = kzalloc(sizeof(struct fw_filter), GFP_KERNEL);
if (f == NULL)
return -ENOBUFS;
err = tcf_exts_init(&f->exts, net, TCA_FW_ACT, TCA_FW_POLICE);
if (err < 0)
goto errout;
f->id = handle;
f->tp = tp;
err = fw_set_parms(net, tp, f, tb, tca, base, ovr, extack);
if (err < 0)
goto errout;
RCU_INIT_POINTER(f->next, head->ht[fw_hash(handle)]);
rcu_assign_pointer(head->ht[fw_hash(handle)], f);
*arg = f;
return 0;
errout:
tcf_exts_destroy(&f->exts);
kfree(f);
return err;
}
static void fw_walk(struct tcf_proto *tp, struct tcf_walker *arg,
bool rtnl_held)
{
struct fw_head *head = rtnl_dereference(tp->root);
int h;
if (head == NULL)
arg->stop = 1;
if (arg->stop)
return;
for (h = 0; h < HTSIZE; h++) {
struct fw_filter *f;
for (f = rtnl_dereference(head->ht[h]); f;
f = rtnl_dereference(f->next)) {
if (arg->count < arg->skip) {
arg->count++;
continue;
}
if (arg->fn(tp, f, arg) < 0) {
arg->stop = 1;
return;
}
arg->count++;
}
}
}
static int fw_dump(struct net *net, struct tcf_proto *tp, void *fh,
struct sk_buff *skb, struct tcmsg *t, bool rtnl_held)
{
struct fw_head *head = rtnl_dereference(tp->root);
struct fw_filter *f = fh;
struct nlattr *nest;
if (f == NULL)
return skb->len;
t->tcm_handle = f->id;
if (!f->res.classid && !tcf_exts_has_actions(&f->exts))
return skb->len;
nest = nla_nest_start_noflag(skb, TCA_OPTIONS);
if (nest == NULL)
goto nla_put_failure;
if (f->res.classid &&
nla_put_u32(skb, TCA_FW_CLASSID, f->res.classid))
goto nla_put_failure;
if (f->ifindex) {
struct net_device *dev;
dev = __dev_get_by_index(net, f->ifindex);
if (dev && nla_put_string(skb, TCA_FW_INDEV, dev->name))
goto nla_put_failure;
}
if (head->mask != 0xFFFFFFFF &&
nla_put_u32(skb, TCA_FW_MASK, head->mask))
goto nla_put_failure;
if (tcf_exts_dump(skb, &f->exts) < 0)
goto nla_put_failure;
nla_nest_end(skb, nest);
if (tcf_exts_dump_stats(skb, &f->exts) < 0)
goto nla_put_failure;
return skb->len;
nla_put_failure:
nla_nest_cancel(skb, nest);
return -1;
}
static void fw_bind_class(void *fh, u32 classid, unsigned long cl)
{
struct fw_filter *f = fh;
if (f && f->res.classid == classid)
f->res.class = cl;
}
static struct tcf_proto_ops cls_fw_ops __read_mostly = {
.kind = "fw",
.classify = fw_classify,
.init = fw_init,
.destroy = fw_destroy,
.get = fw_get,
.change = fw_change,
.delete = fw_delete,
.walk = fw_walk,
.dump = fw_dump,
.bind_class = fw_bind_class,
.owner = THIS_MODULE,
};
static int __init init_fw(void)
{
return register_tcf_proto_ops(&cls_fw_ops);
}
static void __exit exit_fw(void)
{
unregister_tcf_proto_ops(&cls_fw_ops);
}
module_init(init_fw)
module_exit(exit_fw)
MODULE_LICENSE("GPL");