linux/net/sched/cls_route.c

679 lines
14 KiB
C
Raw Normal View History

// SPDX-License-Identifier: GPL-2.0-or-later
/*
* net/sched/cls_route.c ROUTE4 classifier.
*
* Authors: Alexey Kuznetsov, <kuznet@ms2.inr.ac.ru>
*/
#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/dst.h>
#include <net/route.h>
#include <net/netlink.h>
#include <net/act_api.h>
#include <net/pkt_cls.h>
/*
* 1. For now we assume that route tags < 256.
* It allows to use direct table lookups, instead of hash tables.
* 2. For now we assume that "from TAG" and "fromdev DEV" statements
* are mutually exclusive.
* 3. "to TAG from ANY" has higher priority, than "to ANY from XXX"
*/
struct route4_fastmap {
struct route4_filter *filter;
u32 id;
int iif;
};
struct route4_head {
struct route4_fastmap fastmap[16];
struct route4_bucket __rcu *table[256 + 1];
struct rcu_head rcu;
};
struct route4_bucket {
/* 16 FROM buckets + 16 IIF buckets + 1 wildcard bucket */
struct route4_filter __rcu *ht[16 + 16 + 1];
struct rcu_head rcu;
};
struct route4_filter {
struct route4_filter __rcu *next;
u32 id;
int iif;
struct tcf_result res;
struct tcf_exts exts;
u32 handle;
struct route4_bucket *bkt;
struct tcf_proto *tp;
struct rcu_work rwork;
};
#define ROUTE4_FAILURE ((struct route4_filter *)(-1L))
static inline int route4_fastmap_hash(u32 id, int iif)
{
return id & 0xF;
}
static DEFINE_SPINLOCK(fastmap_lock);
static void
route4_reset_fastmap(struct route4_head *head)
{
spin_lock_bh(&fastmap_lock);
memset(head->fastmap, 0, sizeof(head->fastmap));
spin_unlock_bh(&fastmap_lock);
}
static void
route4_set_fastmap(struct route4_head *head, u32 id, int iif,
struct route4_filter *f)
{
int h = route4_fastmap_hash(id, iif);
/* fastmap updates must look atomic to aling id, iff, filter */
spin_lock_bh(&fastmap_lock);
head->fastmap[h].id = id;
head->fastmap[h].iif = iif;
head->fastmap[h].filter = f;
spin_unlock_bh(&fastmap_lock);
}
static inline int route4_hash_to(u32 id)
{
return id & 0xFF;
}
static inline int route4_hash_from(u32 id)
{
return (id >> 16) & 0xF;
}
static inline int route4_hash_iif(int iif)
{
return 16 + ((iif >> 16) & 0xF);
}
static inline int route4_hash_wild(void)
{
return 32;
}
#define ROUTE4_APPLY_RESULT() \
{ \
*res = f->res; \
if (tcf_exts_has_actions(&f->exts)) { \
int r = tcf_exts_exec(skb, &f->exts, res); \
if (r < 0) { \
dont_cache = 1; \
continue; \
} \
return r; \
} else if (!dont_cache) \
route4_set_fastmap(head, id, iif, f); \
return 0; \
}
static int route4_classify(struct sk_buff *skb, const struct tcf_proto *tp,
struct tcf_result *res)
{
struct route4_head *head = rcu_dereference_bh(tp->root);
struct dst_entry *dst;
struct route4_bucket *b;
struct route4_filter *f;
u32 id, h;
int iif, dont_cache = 0;
dst = skb_dst(skb);
if (!dst)
goto failure;
id = dst->tclassid;
iif = inet_iif(skb);
h = route4_fastmap_hash(id, iif);
spin_lock(&fastmap_lock);
if (id == head->fastmap[h].id &&
iif == head->fastmap[h].iif &&
(f = head->fastmap[h].filter) != NULL) {
if (f == ROUTE4_FAILURE) {
spin_unlock(&fastmap_lock);
goto failure;
}
*res = f->res;
spin_unlock(&fastmap_lock);
return 0;
}
spin_unlock(&fastmap_lock);
h = route4_hash_to(id);
restart:
b = rcu_dereference_bh(head->table[h]);
if (b) {
for (f = rcu_dereference_bh(b->ht[route4_hash_from(id)]);
f;
f = rcu_dereference_bh(f->next))
if (f->id == id)
ROUTE4_APPLY_RESULT();
for (f = rcu_dereference_bh(b->ht[route4_hash_iif(iif)]);
f;
f = rcu_dereference_bh(f->next))
if (f->iif == iif)
ROUTE4_APPLY_RESULT();
for (f = rcu_dereference_bh(b->ht[route4_hash_wild()]);
f;
f = rcu_dereference_bh(f->next))
ROUTE4_APPLY_RESULT();
}
if (h < 256) {
h = 256;
id &= ~0xFFFF;
goto restart;
}
if (!dont_cache)
route4_set_fastmap(head, id, iif, ROUTE4_FAILURE);
failure:
return -1;
}
static inline u32 to_hash(u32 id)
{
u32 h = id & 0xFF;
if (id & 0x8000)
h += 256;
return h;
}
static inline u32 from_hash(u32 id)
{
id &= 0xFFFF;
if (id == 0xFFFF)
return 32;
if (!(id & 0x8000)) {
if (id > 255)
return 256;
return id & 0xF;
}
return 16 + (id & 0xF);
}
static void *route4_get(struct tcf_proto *tp, u32 handle)
{
struct route4_head *head = rtnl_dereference(tp->root);
struct route4_bucket *b;
struct route4_filter *f;
unsigned int h1, h2;
h1 = to_hash(handle);
if (h1 > 256)
return NULL;
h2 = from_hash(handle >> 16);
if (h2 > 32)
return NULL;
b = rtnl_dereference(head->table[h1]);
if (b) {
for (f = rtnl_dereference(b->ht[h2]);
f;
f = rtnl_dereference(f->next))
if (f->handle == handle)
return f;
}
return NULL;
}
static int route4_init(struct tcf_proto *tp)
{
struct route4_head *head;
head = kzalloc(sizeof(struct route4_head), GFP_KERNEL);
if (head == NULL)
return -ENOBUFS;
rcu_assign_pointer(tp->root, head);
return 0;
}
static void __route4_delete_filter(struct route4_filter *f)
{
tcf_exts_destroy(&f->exts);
tcf_exts_put_net(&f->exts);
kfree(f);
}
static void route4_delete_filter_work(struct work_struct *work)
{
struct route4_filter *f = container_of(to_rcu_work(work),
struct route4_filter,
rwork);
rtnl_lock();
__route4_delete_filter(f);
rtnl_unlock();
}
static void route4_queue_work(struct route4_filter *f)
{
tcf_queue_work(&f->rwork, route4_delete_filter_work);
}
static void route4_destroy(struct tcf_proto *tp, bool rtnl_held,
struct netlink_ext_ack *extack)
{
struct route4_head *head = rtnl_dereference(tp->root);
int h1, h2;
if (head == NULL)
return;
for (h1 = 0; h1 <= 256; h1++) {
struct route4_bucket *b;
b = rtnl_dereference(head->table[h1]);
if (b) {
for (h2 = 0; h2 <= 32; h2++) {
struct route4_filter *f;
while ((f = rtnl_dereference(b->ht[h2])) != NULL) {
struct route4_filter *next;
next = rtnl_dereference(f->next);
RCU_INIT_POINTER(b->ht[h2], next);
tcf_unbind_filter(tp, &f->res);
if (tcf_exts_get_net(&f->exts))
route4_queue_work(f);
else
__route4_delete_filter(f);
}
}
RCU_INIT_POINTER(head->table[h1], NULL);
kfree_rcu(b, rcu);
}
}
kfree_rcu(head, rcu);
}
static int route4_delete(struct tcf_proto *tp, void *arg, bool *last,
bool rtnl_held, struct netlink_ext_ack *extack)
{
struct route4_head *head = rtnl_dereference(tp->root);
struct route4_filter *f = arg;
struct route4_filter __rcu **fp;
struct route4_filter *nf;
struct route4_bucket *b;
unsigned int h = 0;
int i, h1;
if (!head || !f)
return -EINVAL;
h = f->handle;
b = f->bkt;
fp = &b->ht[from_hash(h >> 16)];
for (nf = rtnl_dereference(*fp); nf;
fp = &nf->next, nf = rtnl_dereference(*fp)) {
if (nf == f) {
/* unlink it */
RCU_INIT_POINTER(*fp, rtnl_dereference(f->next));
/* Remove any fastmap lookups that might ref filter
* notice we unlink'd the filter so we can't get it
* back in the fastmap.
*/
route4_reset_fastmap(head);
/* Delete it */
tcf_unbind_filter(tp, &f->res);
tcf_exts_get_net(&f->exts);
tcf_queue_work(&f->rwork, route4_delete_filter_work);
/* Strip RTNL protected tree */
for (i = 0; i <= 32; i++) {
struct route4_filter *rt;
rt = rtnl_dereference(b->ht[i]);
if (rt)
goto out;
}
/* OK, session has no flows */
RCU_INIT_POINTER(head->table[to_hash(h)], NULL);
kfree_rcu(b, rcu);
break;
}
}
out:
*last = true;
for (h1 = 0; h1 <= 256; h1++) {
if (rcu_access_pointer(head->table[h1])) {
*last = false;
break;
}
}
return 0;
}
static const struct nla_policy route4_policy[TCA_ROUTE4_MAX + 1] = {
[TCA_ROUTE4_CLASSID] = { .type = NLA_U32 },
[TCA_ROUTE4_TO] = { .type = NLA_U32 },
[TCA_ROUTE4_FROM] = { .type = NLA_U32 },
[TCA_ROUTE4_IIF] = { .type = NLA_U32 },
};
static int route4_set_parms(struct net *net, struct tcf_proto *tp,
unsigned long base, struct route4_filter *f,
u32 handle, struct route4_head *head,
struct nlattr **tb, struct nlattr *est, int new,
bool ovr, struct netlink_ext_ack *extack)
{
u32 id = 0, to = 0, nhandle = 0x8000;
struct route4_filter *fp;
unsigned int h1;
struct route4_bucket *b;
int err;
err = tcf_exts_validate(net, tp, tb, est, &f->exts, ovr, true, extack);
if (err < 0)
return err;
if (tb[TCA_ROUTE4_TO]) {
if (new && handle & 0x8000)
return -EINVAL;
to = nla_get_u32(tb[TCA_ROUTE4_TO]);
if (to > 0xFF)
return -EINVAL;
nhandle = to;
}
if (tb[TCA_ROUTE4_FROM]) {
if (tb[TCA_ROUTE4_IIF])
return -EINVAL;
id = nla_get_u32(tb[TCA_ROUTE4_FROM]);
if (id > 0xFF)
return -EINVAL;
nhandle |= id << 16;
} else if (tb[TCA_ROUTE4_IIF]) {
id = nla_get_u32(tb[TCA_ROUTE4_IIF]);
if (id > 0x7FFF)
return -EINVAL;
nhandle |= (id | 0x8000) << 16;
} else
nhandle |= 0xFFFF << 16;
if (handle && new) {
nhandle |= handle & 0x7F00;
if (nhandle != handle)
return -EINVAL;
}
h1 = to_hash(nhandle);
b = rtnl_dereference(head->table[h1]);
if (!b) {
b = kzalloc(sizeof(struct route4_bucket), GFP_KERNEL);
if (b == NULL)
return -ENOBUFS;
rcu_assign_pointer(head->table[h1], b);
} else {
unsigned int h2 = from_hash(nhandle >> 16);
for (fp = rtnl_dereference(b->ht[h2]);
fp;
fp = rtnl_dereference(fp->next))
if (fp->handle == f->handle)
return -EEXIST;
}
if (tb[TCA_ROUTE4_TO])
f->id = to;
if (tb[TCA_ROUTE4_FROM])
f->id = to | id<<16;
else if (tb[TCA_ROUTE4_IIF])
f->iif = id;
f->handle = nhandle;
f->bkt = b;
f->tp = tp;
if (tb[TCA_ROUTE4_CLASSID]) {
f->res.classid = nla_get_u32(tb[TCA_ROUTE4_CLASSID]);
tcf_bind_filter(tp, &f->res, base);
}
return 0;
}
static int route4_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 route4_head *head = rtnl_dereference(tp->root);
struct route4_filter __rcu **fp;
struct route4_filter *fold, *f1, *pfp, *f = NULL;
struct route4_bucket *b;
struct nlattr *opt = tca[TCA_OPTIONS];
struct nlattr *tb[TCA_ROUTE4_MAX + 1];
unsigned int h, th;
int err;
bool new = true;
if (opt == NULL)
return handle ? -EINVAL : 0;
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_ROUTE4_MAX, opt,
route4_policy, NULL);
if (err < 0)
return err;
fold = *arg;
if (fold && handle && fold->handle != handle)
return -EINVAL;
err = -ENOBUFS;
f = kzalloc(sizeof(struct route4_filter), GFP_KERNEL);
if (!f)
goto errout;
err = tcf_exts_init(&f->exts, net, TCA_ROUTE4_ACT, TCA_ROUTE4_POLICE);
if (err < 0)
goto errout;
if (fold) {
f->id = fold->id;
f->iif = fold->iif;
f->res = fold->res;
f->handle = fold->handle;
f->tp = fold->tp;
f->bkt = fold->bkt;
new = false;
}
err = route4_set_parms(net, tp, base, f, handle, head, tb,
tca[TCA_RATE], new, ovr, extack);
if (err < 0)
goto errout;
h = from_hash(f->handle >> 16);
fp = &f->bkt->ht[h];
for (pfp = rtnl_dereference(*fp);
(f1 = rtnl_dereference(*fp)) != NULL;
fp = &f1->next)
if (f->handle < f1->handle)
break;
tcf_block_netif_keep_dst(tp->chain->block);
rcu_assign_pointer(f->next, f1);
rcu_assign_pointer(*fp, f);
if (fold && fold->handle && f->handle != fold->handle) {
th = to_hash(fold->handle);
h = from_hash(fold->handle >> 16);
b = rtnl_dereference(head->table[th]);
if (b) {
fp = &b->ht[h];
for (pfp = rtnl_dereference(*fp); pfp;
fp = &pfp->next, pfp = rtnl_dereference(*fp)) {
if (pfp == f) {
*fp = f->next;
break;
}
}
}
}
route4_reset_fastmap(head);
*arg = f;
if (fold) {
tcf_unbind_filter(tp, &fold->res);
tcf_exts_get_net(&fold->exts);
tcf_queue_work(&fold->rwork, route4_delete_filter_work);
}
return 0;
errout:
if (f)
tcf_exts_destroy(&f->exts);
kfree(f);
return err;
}
static void route4_walk(struct tcf_proto *tp, struct tcf_walker *arg,
bool rtnl_held)
{
struct route4_head *head = rtnl_dereference(tp->root);
unsigned int h, h1;
if (head == NULL || arg->stop)
return;
for (h = 0; h <= 256; h++) {
struct route4_bucket *b = rtnl_dereference(head->table[h]);
if (b) {
for (h1 = 0; h1 <= 32; h1++) {
struct route4_filter *f;
for (f = rtnl_dereference(b->ht[h1]);
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 route4_dump(struct net *net, struct tcf_proto *tp, void *fh,
struct sk_buff *skb, struct tcmsg *t, bool rtnl_held)
{
struct route4_filter *f = fh;
struct nlattr *nest;
u32 id;
if (f == NULL)
return skb->len;
t->tcm_handle = f->handle;
nest = nla_nest_start_noflag(skb, TCA_OPTIONS);
if (nest == NULL)
goto nla_put_failure;
if (!(f->handle & 0x8000)) {
id = f->id & 0xFF;
if (nla_put_u32(skb, TCA_ROUTE4_TO, id))
goto nla_put_failure;
}
if (f->handle & 0x80000000) {
if ((f->handle >> 16) != 0xFFFF &&
nla_put_u32(skb, TCA_ROUTE4_IIF, f->iif))
goto nla_put_failure;
} else {
id = f->id >> 16;
if (nla_put_u32(skb, TCA_ROUTE4_FROM, id))
goto nla_put_failure;
}
if (f->res.classid &&
nla_put_u32(skb, TCA_ROUTE4_CLASSID, f->res.classid))
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 route4_bind_class(void *fh, u32 classid, unsigned long cl)
{
struct route4_filter *f = fh;
if (f && f->res.classid == classid)
f->res.class = cl;
}
static struct tcf_proto_ops cls_route4_ops __read_mostly = {
.kind = "route",
.classify = route4_classify,
.init = route4_init,
.destroy = route4_destroy,
.get = route4_get,
.change = route4_change,
.delete = route4_delete,
.walk = route4_walk,
.dump = route4_dump,
.bind_class = route4_bind_class,
.owner = THIS_MODULE,
};
static int __init init_route4(void)
{
return register_tcf_proto_ops(&cls_route4_ops);
}
static void __exit exit_route4(void)
{
unregister_tcf_proto_ops(&cls_route4_ops);
}
module_init(init_route4)
module_exit(exit_route4)
MODULE_LICENSE("GPL");