linux-sg2042/net/sched/cls_u32.c

838 lines
17 KiB
C
Raw Normal View History

/*
* net/sched/cls_u32.c Ugly (or Universal) 32bit key Packet Classifier.
*
* 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>
*
* The filters are packed to hash tables of key nodes
* with a set of 32bit key/mask pairs at every node.
* Nodes reference next level hash tables etc.
*
* This scheme is the best universal classifier I managed to
* invent; it is not super-fast, but it is not slow (provided you
* program it correctly), and general enough. And its relative
* speed grows as the number of rules becomes larger.
*
* It seems that it represents the best middle point between
* speed and manageability both by human and by machine.
*
* It is especially useful for link sharing combined with QoS;
* pure RSVP doesn't need such a general approach and can use
* much simpler (and faster) schemes, sort of cls_rsvp.c.
*
* JHS: We should remove the CONFIG_NET_CLS_IND from here
* eventually when the meta match extension is made available
*
* nfmark match added by Catalin(ux aka Dino) BOIE <catab at umbrella.ro>
*/
#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/rtnetlink.h>
#include <linux/skbuff.h>
net_sched: avoid generating same handle for u32 filters When kernel generates a handle for a u32 filter, it tries to start from the max in the bucket. So when we have a filter with the max (fff) handle, it will cause kernel always generates the same handle for new filters. This can be shown by the following command: tc qdisc add dev eth0 ingress tc filter add dev eth0 parent ffff: protocol ip pref 770 handle 800::fff u32 match ip protocol 1 0xff tc filter add dev eth0 parent ffff: protocol ip pref 770 u32 match ip protocol 1 0xff ... we will get some u32 filters with same handle: # tc filter show dev eth0 parent ffff: filter protocol ip pref 770 u32 filter protocol ip pref 770 u32 fh 800: ht divisor 1 filter protocol ip pref 770 u32 fh 800::fff order 4095 key ht 800 bkt 0 match 00010000/00ff0000 at 8 filter protocol ip pref 770 u32 fh 800::fff order 4095 key ht 800 bkt 0 match 00010000/00ff0000 at 8 filter protocol ip pref 770 u32 fh 800::fff order 4095 key ht 800 bkt 0 match 00010000/00ff0000 at 8 filter protocol ip pref 770 u32 fh 800::fff order 4095 key ht 800 bkt 0 match 00010000/00ff0000 at 8 handles should be unique. This patch fixes it by looking up a bitmap, so that can guarantee the handle is as unique as possible. For compatibility, we still start from 0x800. Cc: "David S. Miller" <davem@davemloft.net> Signed-off-by: Cong Wang <cwang@twopensource.com> Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com> Signed-off-by: Jamal Hadi Salim <jhs@mojatatu.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-07-18 08:34:53 +08:00
#include <linux/bitmap.h>
#include <net/netlink.h>
#include <net/act_api.h>
#include <net/pkt_cls.h>
struct tc_u_knode {
struct tc_u_knode *next;
u32 handle;
struct tc_u_hnode *ht_up;
struct tcf_exts exts;
#ifdef CONFIG_NET_CLS_IND
int ifindex;
#endif
u8 fshift;
struct tcf_result res;
struct tc_u_hnode *ht_down;
#ifdef CONFIG_CLS_U32_PERF
struct tc_u32_pcnt *pf;
#endif
#ifdef CONFIG_CLS_U32_MARK
struct tc_u32_mark mark;
#endif
struct tc_u32_sel sel;
};
struct tc_u_hnode {
struct tc_u_hnode *next;
u32 handle;
u32 prio;
struct tc_u_common *tp_c;
int refcnt;
unsigned int divisor;
struct tc_u_knode *ht[1];
};
struct tc_u_common {
struct tc_u_hnode *hlist;
struct Qdisc *q;
int refcnt;
u32 hgenerator;
};
static inline unsigned int u32_hash_fold(__be32 key,
const struct tc_u32_sel *sel,
u8 fshift)
{
unsigned int h = ntohl(key & sel->hmask) >> fshift;
return h;
}
static int u32_classify(struct sk_buff *skb, const struct tcf_proto *tp, struct tcf_result *res)
{
struct {
struct tc_u_knode *knode;
unsigned int off;
} stack[TC_U32_MAXDEPTH];
struct tc_u_hnode *ht = tp->root;
unsigned int off = skb_network_offset(skb);
struct tc_u_knode *n;
int sdepth = 0;
int off2 = 0;
int sel = 0;
#ifdef CONFIG_CLS_U32_PERF
int j;
#endif
int i, r;
next_ht:
n = ht->ht[sel];
next_knode:
if (n) {
struct tc_u32_key *key = n->sel.keys;
#ifdef CONFIG_CLS_U32_PERF
n->pf->rcnt += 1;
j = 0;
#endif
#ifdef CONFIG_CLS_U32_MARK
if ((skb->mark & n->mark.mask) != n->mark.val) {
n = n->next;
goto next_knode;
} else {
n->mark.success++;
}
#endif
for (i = n->sel.nkeys; i > 0; i--, key++) {
int toff = off + key->off + (off2 & key->offmask);
__be32 *data, hdata;
if (skb_headroom(skb) + toff > INT_MAX)
goto out;
data = skb_header_pointer(skb, toff, 4, &hdata);
if (!data)
goto out;
if ((*data ^ key->val) & key->mask) {
n = n->next;
goto next_knode;
}
#ifdef CONFIG_CLS_U32_PERF
n->pf->kcnts[j] += 1;
j++;
#endif
}
if (n->ht_down == NULL) {
check_terminal:
if (n->sel.flags & TC_U32_TERMINAL) {
*res = n->res;
#ifdef CONFIG_NET_CLS_IND
if (!tcf_match_indev(skb, n->ifindex)) {
n = n->next;
goto next_knode;
}
#endif
#ifdef CONFIG_CLS_U32_PERF
n->pf->rhit += 1;
#endif
r = tcf_exts_exec(skb, &n->exts, res);
if (r < 0) {
n = n->next;
goto next_knode;
}
return r;
}
n = n->next;
goto next_knode;
}
/* PUSH */
if (sdepth >= TC_U32_MAXDEPTH)
goto deadloop;
stack[sdepth].knode = n;
stack[sdepth].off = off;
sdepth++;
ht = n->ht_down;
sel = 0;
if (ht->divisor) {
__be32 *data, hdata;
data = skb_header_pointer(skb, off + n->sel.hoff, 4,
&hdata);
if (!data)
goto out;
sel = ht->divisor & u32_hash_fold(*data, &n->sel,
n->fshift);
}
if (!(n->sel.flags & (TC_U32_VAROFFSET | TC_U32_OFFSET | TC_U32_EAT)))
goto next_ht;
if (n->sel.flags & (TC_U32_OFFSET | TC_U32_VAROFFSET)) {
off2 = n->sel.off + 3;
if (n->sel.flags & TC_U32_VAROFFSET) {
__be16 *data, hdata;
data = skb_header_pointer(skb,
off + n->sel.offoff,
2, &hdata);
if (!data)
goto out;
off2 += ntohs(n->sel.offmask & *data) >>
n->sel.offshift;
}
off2 &= ~3;
}
if (n->sel.flags & TC_U32_EAT) {
off += off2;
off2 = 0;
}
if (off < skb->len)
goto next_ht;
}
/* POP */
if (sdepth--) {
n = stack[sdepth].knode;
ht = n->ht_up;
off = stack[sdepth].off;
goto check_terminal;
}
out:
return -1;
deadloop:
net_warn_ratelimited("cls_u32: dead loop\n");
return -1;
}
static struct tc_u_hnode *
u32_lookup_ht(struct tc_u_common *tp_c, u32 handle)
{
struct tc_u_hnode *ht;
for (ht = tp_c->hlist; ht; ht = ht->next)
if (ht->handle == handle)
break;
return ht;
}
static struct tc_u_knode *
u32_lookup_key(struct tc_u_hnode *ht, u32 handle)
{
unsigned int sel;
struct tc_u_knode *n = NULL;
sel = TC_U32_HASH(handle);
if (sel > ht->divisor)
goto out;
for (n = ht->ht[sel]; n; n = n->next)
if (n->handle == handle)
break;
out:
return n;
}
static unsigned long u32_get(struct tcf_proto *tp, u32 handle)
{
struct tc_u_hnode *ht;
struct tc_u_common *tp_c = tp->data;
if (TC_U32_HTID(handle) == TC_U32_ROOT)
ht = tp->root;
else
ht = u32_lookup_ht(tp_c, TC_U32_HTID(handle));
if (!ht)
return 0;
if (TC_U32_KEY(handle) == 0)
return (unsigned long)ht;
return (unsigned long)u32_lookup_key(ht, handle);
}
static void u32_put(struct tcf_proto *tp, unsigned long f)
{
}
static u32 gen_new_htid(struct tc_u_common *tp_c)
{
int i = 0x800;
do {
if (++tp_c->hgenerator == 0x7FF)
tp_c->hgenerator = 1;
} while (--i > 0 && u32_lookup_ht(tp_c, (tp_c->hgenerator|0x800)<<20));
return i > 0 ? (tp_c->hgenerator|0x800)<<20 : 0;
}
static int u32_init(struct tcf_proto *tp)
{
struct tc_u_hnode *root_ht;
struct tc_u_common *tp_c;
tp_c = tp->q->u32_node;
root_ht = kzalloc(sizeof(*root_ht), GFP_KERNEL);
if (root_ht == NULL)
return -ENOBUFS;
root_ht->divisor = 0;
root_ht->refcnt++;
root_ht->handle = tp_c ? gen_new_htid(tp_c) : 0x80000000;
root_ht->prio = tp->prio;
if (tp_c == NULL) {
tp_c = kzalloc(sizeof(*tp_c), GFP_KERNEL);
if (tp_c == NULL) {
kfree(root_ht);
return -ENOBUFS;
}
tp_c->q = tp->q;
tp->q->u32_node = tp_c;
}
tp_c->refcnt++;
root_ht->next = tp_c->hlist;
tp_c->hlist = root_ht;
root_ht->tp_c = tp_c;
tp->root = root_ht;
tp->data = tp_c;
return 0;
}
static int u32_destroy_key(struct tcf_proto *tp, struct tc_u_knode *n)
{
tcf_unbind_filter(tp, &n->res);
tcf_exts_destroy(tp, &n->exts);
if (n->ht_down)
n->ht_down->refcnt--;
#ifdef CONFIG_CLS_U32_PERF
kfree(n->pf);
#endif
kfree(n);
return 0;
}
static int u32_delete_key(struct tcf_proto *tp, struct tc_u_knode *key)
{
struct tc_u_knode **kp;
struct tc_u_hnode *ht = key->ht_up;
if (ht) {
for (kp = &ht->ht[TC_U32_HASH(key->handle)]; *kp; kp = &(*kp)->next) {
if (*kp == key) {
tcf_tree_lock(tp);
*kp = key->next;
tcf_tree_unlock(tp);
u32_destroy_key(tp, key);
return 0;
}
}
}
WARN_ON(1);
return 0;
}
static void u32_clear_hnode(struct tcf_proto *tp, struct tc_u_hnode *ht)
{
struct tc_u_knode *n;
unsigned int h;
for (h = 0; h <= ht->divisor; h++) {
while ((n = ht->ht[h]) != NULL) {
ht->ht[h] = n->next;
u32_destroy_key(tp, n);
}
}
}
static int u32_destroy_hnode(struct tcf_proto *tp, struct tc_u_hnode *ht)
{
struct tc_u_common *tp_c = tp->data;
struct tc_u_hnode **hn;
WARN_ON(ht->refcnt);
u32_clear_hnode(tp, ht);
for (hn = &tp_c->hlist; *hn; hn = &(*hn)->next) {
if (*hn == ht) {
*hn = ht->next;
kfree(ht);
return 0;
}
}
WARN_ON(1);
return -ENOENT;
}
static void u32_destroy(struct tcf_proto *tp)
{
struct tc_u_common *tp_c = tp->data;
struct tc_u_hnode *root_ht = tp->root;
WARN_ON(root_ht == NULL);
if (root_ht && --root_ht->refcnt == 0)
u32_destroy_hnode(tp, root_ht);
if (--tp_c->refcnt == 0) {
struct tc_u_hnode *ht;
tp->q->u32_node = NULL;
for (ht = tp_c->hlist; ht; ht = ht->next) {
ht->refcnt--;
u32_clear_hnode(tp, ht);
}
while ((ht = tp_c->hlist) != NULL) {
tp_c->hlist = ht->next;
WARN_ON(ht->refcnt != 0);
kfree(ht);
}
kfree(tp_c);
}
tp->data = NULL;
}
static int u32_delete(struct tcf_proto *tp, unsigned long arg)
{
struct tc_u_hnode *ht = (struct tc_u_hnode *)arg;
if (ht == NULL)
return 0;
if (TC_U32_KEY(ht->handle))
return u32_delete_key(tp, (struct tc_u_knode *)ht);
if (tp->root == ht)
return -EINVAL;
if (ht->refcnt == 1) {
ht->refcnt--;
u32_destroy_hnode(tp, ht);
} else {
return -EBUSY;
}
return 0;
}
net_sched: avoid generating same handle for u32 filters When kernel generates a handle for a u32 filter, it tries to start from the max in the bucket. So when we have a filter with the max (fff) handle, it will cause kernel always generates the same handle for new filters. This can be shown by the following command: tc qdisc add dev eth0 ingress tc filter add dev eth0 parent ffff: protocol ip pref 770 handle 800::fff u32 match ip protocol 1 0xff tc filter add dev eth0 parent ffff: protocol ip pref 770 u32 match ip protocol 1 0xff ... we will get some u32 filters with same handle: # tc filter show dev eth0 parent ffff: filter protocol ip pref 770 u32 filter protocol ip pref 770 u32 fh 800: ht divisor 1 filter protocol ip pref 770 u32 fh 800::fff order 4095 key ht 800 bkt 0 match 00010000/00ff0000 at 8 filter protocol ip pref 770 u32 fh 800::fff order 4095 key ht 800 bkt 0 match 00010000/00ff0000 at 8 filter protocol ip pref 770 u32 fh 800::fff order 4095 key ht 800 bkt 0 match 00010000/00ff0000 at 8 filter protocol ip pref 770 u32 fh 800::fff order 4095 key ht 800 bkt 0 match 00010000/00ff0000 at 8 handles should be unique. This patch fixes it by looking up a bitmap, so that can guarantee the handle is as unique as possible. For compatibility, we still start from 0x800. Cc: "David S. Miller" <davem@davemloft.net> Signed-off-by: Cong Wang <cwang@twopensource.com> Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com> Signed-off-by: Jamal Hadi Salim <jhs@mojatatu.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-07-18 08:34:53 +08:00
#define NR_U32_NODE (1<<12)
static u32 gen_new_kid(struct tc_u_hnode *ht, u32 handle)
{
struct tc_u_knode *n;
net_sched: avoid generating same handle for u32 filters When kernel generates a handle for a u32 filter, it tries to start from the max in the bucket. So when we have a filter with the max (fff) handle, it will cause kernel always generates the same handle for new filters. This can be shown by the following command: tc qdisc add dev eth0 ingress tc filter add dev eth0 parent ffff: protocol ip pref 770 handle 800::fff u32 match ip protocol 1 0xff tc filter add dev eth0 parent ffff: protocol ip pref 770 u32 match ip protocol 1 0xff ... we will get some u32 filters with same handle: # tc filter show dev eth0 parent ffff: filter protocol ip pref 770 u32 filter protocol ip pref 770 u32 fh 800: ht divisor 1 filter protocol ip pref 770 u32 fh 800::fff order 4095 key ht 800 bkt 0 match 00010000/00ff0000 at 8 filter protocol ip pref 770 u32 fh 800::fff order 4095 key ht 800 bkt 0 match 00010000/00ff0000 at 8 filter protocol ip pref 770 u32 fh 800::fff order 4095 key ht 800 bkt 0 match 00010000/00ff0000 at 8 filter protocol ip pref 770 u32 fh 800::fff order 4095 key ht 800 bkt 0 match 00010000/00ff0000 at 8 handles should be unique. This patch fixes it by looking up a bitmap, so that can guarantee the handle is as unique as possible. For compatibility, we still start from 0x800. Cc: "David S. Miller" <davem@davemloft.net> Signed-off-by: Cong Wang <cwang@twopensource.com> Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com> Signed-off-by: Jamal Hadi Salim <jhs@mojatatu.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-07-18 08:34:53 +08:00
unsigned long i;
unsigned long *bitmap = kzalloc(BITS_TO_LONGS(NR_U32_NODE) * sizeof(unsigned long),
GFP_KERNEL);
if (!bitmap)
return handle | 0xFFF;
for (n = ht->ht[TC_U32_HASH(handle)]; n; n = n->next)
net_sched: avoid generating same handle for u32 filters When kernel generates a handle for a u32 filter, it tries to start from the max in the bucket. So when we have a filter with the max (fff) handle, it will cause kernel always generates the same handle for new filters. This can be shown by the following command: tc qdisc add dev eth0 ingress tc filter add dev eth0 parent ffff: protocol ip pref 770 handle 800::fff u32 match ip protocol 1 0xff tc filter add dev eth0 parent ffff: protocol ip pref 770 u32 match ip protocol 1 0xff ... we will get some u32 filters with same handle: # tc filter show dev eth0 parent ffff: filter protocol ip pref 770 u32 filter protocol ip pref 770 u32 fh 800: ht divisor 1 filter protocol ip pref 770 u32 fh 800::fff order 4095 key ht 800 bkt 0 match 00010000/00ff0000 at 8 filter protocol ip pref 770 u32 fh 800::fff order 4095 key ht 800 bkt 0 match 00010000/00ff0000 at 8 filter protocol ip pref 770 u32 fh 800::fff order 4095 key ht 800 bkt 0 match 00010000/00ff0000 at 8 filter protocol ip pref 770 u32 fh 800::fff order 4095 key ht 800 bkt 0 match 00010000/00ff0000 at 8 handles should be unique. This patch fixes it by looking up a bitmap, so that can guarantee the handle is as unique as possible. For compatibility, we still start from 0x800. Cc: "David S. Miller" <davem@davemloft.net> Signed-off-by: Cong Wang <cwang@twopensource.com> Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com> Signed-off-by: Jamal Hadi Salim <jhs@mojatatu.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-07-18 08:34:53 +08:00
set_bit(TC_U32_NODE(n->handle), bitmap);
net_sched: avoid generating same handle for u32 filters When kernel generates a handle for a u32 filter, it tries to start from the max in the bucket. So when we have a filter with the max (fff) handle, it will cause kernel always generates the same handle for new filters. This can be shown by the following command: tc qdisc add dev eth0 ingress tc filter add dev eth0 parent ffff: protocol ip pref 770 handle 800::fff u32 match ip protocol 1 0xff tc filter add dev eth0 parent ffff: protocol ip pref 770 u32 match ip protocol 1 0xff ... we will get some u32 filters with same handle: # tc filter show dev eth0 parent ffff: filter protocol ip pref 770 u32 filter protocol ip pref 770 u32 fh 800: ht divisor 1 filter protocol ip pref 770 u32 fh 800::fff order 4095 key ht 800 bkt 0 match 00010000/00ff0000 at 8 filter protocol ip pref 770 u32 fh 800::fff order 4095 key ht 800 bkt 0 match 00010000/00ff0000 at 8 filter protocol ip pref 770 u32 fh 800::fff order 4095 key ht 800 bkt 0 match 00010000/00ff0000 at 8 filter protocol ip pref 770 u32 fh 800::fff order 4095 key ht 800 bkt 0 match 00010000/00ff0000 at 8 handles should be unique. This patch fixes it by looking up a bitmap, so that can guarantee the handle is as unique as possible. For compatibility, we still start from 0x800. Cc: "David S. Miller" <davem@davemloft.net> Signed-off-by: Cong Wang <cwang@twopensource.com> Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com> Signed-off-by: Jamal Hadi Salim <jhs@mojatatu.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-07-18 08:34:53 +08:00
i = find_next_zero_bit(bitmap, NR_U32_NODE, 0x800);
if (i >= NR_U32_NODE)
i = find_next_zero_bit(bitmap, NR_U32_NODE, 1);
kfree(bitmap);
return handle | (i >= NR_U32_NODE ? 0xFFF : i);
}
static const struct nla_policy u32_policy[TCA_U32_MAX + 1] = {
[TCA_U32_CLASSID] = { .type = NLA_U32 },
[TCA_U32_HASH] = { .type = NLA_U32 },
[TCA_U32_LINK] = { .type = NLA_U32 },
[TCA_U32_DIVISOR] = { .type = NLA_U32 },
[TCA_U32_SEL] = { .len = sizeof(struct tc_u32_sel) },
[TCA_U32_INDEV] = { .type = NLA_STRING, .len = IFNAMSIZ },
[TCA_U32_MARK] = { .len = sizeof(struct tc_u32_mark) },
};
static int u32_set_parms(struct net *net, struct tcf_proto *tp,
unsigned long base, struct tc_u_hnode *ht,
struct tc_u_knode *n, struct nlattr **tb,
struct nlattr *est, bool ovr)
{
int err;
struct tcf_exts e;
tcf_exts_init(&e, TCA_U32_ACT, TCA_U32_POLICE);
err = tcf_exts_validate(net, tp, tb, est, &e, ovr);
if (err < 0)
return err;
err = -EINVAL;
if (tb[TCA_U32_LINK]) {
u32 handle = nla_get_u32(tb[TCA_U32_LINK]);
struct tc_u_hnode *ht_down = NULL, *ht_old;
if (TC_U32_KEY(handle))
goto errout;
if (handle) {
ht_down = u32_lookup_ht(ht->tp_c, handle);
if (ht_down == NULL)
goto errout;
ht_down->refcnt++;
}
tcf_tree_lock(tp);
ht_old = n->ht_down;
n->ht_down = ht_down;
tcf_tree_unlock(tp);
if (ht_old)
ht_old->refcnt--;
}
if (tb[TCA_U32_CLASSID]) {
n->res.classid = nla_get_u32(tb[TCA_U32_CLASSID]);
tcf_bind_filter(tp, &n->res, base);
}
#ifdef CONFIG_NET_CLS_IND
if (tb[TCA_U32_INDEV]) {
int ret;
ret = tcf_change_indev(net, tb[TCA_U32_INDEV]);
if (ret < 0)
goto errout;
n->ifindex = ret;
}
#endif
tcf_exts_change(tp, &n->exts, &e);
return 0;
errout:
tcf_exts_destroy(tp, &e);
return err;
}
static int u32_change(struct net *net, struct sk_buff *in_skb,
struct tcf_proto *tp, unsigned long base, u32 handle,
struct nlattr **tca,
unsigned long *arg, bool ovr)
{
struct tc_u_common *tp_c = tp->data;
struct tc_u_hnode *ht;
struct tc_u_knode *n;
struct tc_u32_sel *s;
struct nlattr *opt = tca[TCA_OPTIONS];
struct nlattr *tb[TCA_U32_MAX + 1];
u32 htid;
int err;
if (opt == NULL)
return handle ? -EINVAL : 0;
err = nla_parse_nested(tb, TCA_U32_MAX, opt, u32_policy);
if (err < 0)
return err;
n = (struct tc_u_knode *)*arg;
if (n) {
if (TC_U32_KEY(n->handle) == 0)
return -EINVAL;
return u32_set_parms(net, tp, base, n->ht_up, n, tb,
tca[TCA_RATE], ovr);
}
if (tb[TCA_U32_DIVISOR]) {
unsigned int divisor = nla_get_u32(tb[TCA_U32_DIVISOR]);
if (--divisor > 0x100)
return -EINVAL;
if (TC_U32_KEY(handle))
return -EINVAL;
if (handle == 0) {
handle = gen_new_htid(tp->data);
if (handle == 0)
return -ENOMEM;
}
ht = kzalloc(sizeof(*ht) + divisor*sizeof(void *), GFP_KERNEL);
if (ht == NULL)
return -ENOBUFS;
ht->tp_c = tp_c;
ht->refcnt = 1;
ht->divisor = divisor;
ht->handle = handle;
ht->prio = tp->prio;
ht->next = tp_c->hlist;
tp_c->hlist = ht;
*arg = (unsigned long)ht;
return 0;
}
if (tb[TCA_U32_HASH]) {
htid = nla_get_u32(tb[TCA_U32_HASH]);
if (TC_U32_HTID(htid) == TC_U32_ROOT) {
ht = tp->root;
htid = ht->handle;
} else {
ht = u32_lookup_ht(tp->data, TC_U32_HTID(htid));
if (ht == NULL)
return -EINVAL;
}
} else {
ht = tp->root;
htid = ht->handle;
}
if (ht->divisor < TC_U32_HASH(htid))
return -EINVAL;
if (handle) {
if (TC_U32_HTID(handle) && TC_U32_HTID(handle^htid))
return -EINVAL;
handle = htid | TC_U32_NODE(handle);
} else
handle = gen_new_kid(ht, htid);
if (tb[TCA_U32_SEL] == NULL)
return -EINVAL;
s = nla_data(tb[TCA_U32_SEL]);
n = kzalloc(sizeof(*n) + s->nkeys*sizeof(struct tc_u32_key), GFP_KERNEL);
if (n == NULL)
return -ENOBUFS;
#ifdef CONFIG_CLS_U32_PERF
n->pf = kzalloc(sizeof(struct tc_u32_pcnt) + s->nkeys*sizeof(u64), GFP_KERNEL);
if (n->pf == NULL) {
kfree(n);
return -ENOBUFS;
}
#endif
memcpy(&n->sel, s, sizeof(*s) + s->nkeys*sizeof(struct tc_u32_key));
n->ht_up = ht;
n->handle = handle;
n->fshift = s->hmask ? ffs(ntohl(s->hmask)) - 1 : 0;
tcf_exts_init(&n->exts, TCA_U32_ACT, TCA_U32_POLICE);
#ifdef CONFIG_CLS_U32_MARK
if (tb[TCA_U32_MARK]) {
struct tc_u32_mark *mark;
mark = nla_data(tb[TCA_U32_MARK]);
memcpy(&n->mark, mark, sizeof(struct tc_u32_mark));
n->mark.success = 0;
}
#endif
err = u32_set_parms(net, tp, base, ht, n, tb, tca[TCA_RATE], ovr);
if (err == 0) {
struct tc_u_knode **ins;
for (ins = &ht->ht[TC_U32_HASH(handle)]; *ins; ins = &(*ins)->next)
if (TC_U32_NODE(handle) < TC_U32_NODE((*ins)->handle))
break;
n->next = *ins;
tcf_tree_lock(tp);
*ins = n;
tcf_tree_unlock(tp);
*arg = (unsigned long)n;
return 0;
}
#ifdef CONFIG_CLS_U32_PERF
kfree(n->pf);
#endif
kfree(n);
return err;
}
static void u32_walk(struct tcf_proto *tp, struct tcf_walker *arg)
{
struct tc_u_common *tp_c = tp->data;
struct tc_u_hnode *ht;
struct tc_u_knode *n;
unsigned int h;
if (arg->stop)
return;
for (ht = tp_c->hlist; ht; ht = ht->next) {
if (ht->prio != tp->prio)
continue;
if (arg->count >= arg->skip) {
if (arg->fn(tp, (unsigned long)ht, arg) < 0) {
arg->stop = 1;
return;
}
}
arg->count++;
for (h = 0; h <= ht->divisor; h++) {
for (n = ht->ht[h]; n; n = n->next) {
if (arg->count < arg->skip) {
arg->count++;
continue;
}
if (arg->fn(tp, (unsigned long)n, arg) < 0) {
arg->stop = 1;
return;
}
arg->count++;
}
}
}
}
static int u32_dump(struct net *net, struct tcf_proto *tp, unsigned long fh,
struct sk_buff *skb, struct tcmsg *t)
{
struct tc_u_knode *n = (struct tc_u_knode *)fh;
struct nlattr *nest;
if (n == NULL)
return skb->len;
t->tcm_handle = n->handle;
nest = nla_nest_start(skb, TCA_OPTIONS);
if (nest == NULL)
goto nla_put_failure;
if (TC_U32_KEY(n->handle) == 0) {
struct tc_u_hnode *ht = (struct tc_u_hnode *)fh;
u32 divisor = ht->divisor + 1;
if (nla_put_u32(skb, TCA_U32_DIVISOR, divisor))
goto nla_put_failure;
} else {
if (nla_put(skb, TCA_U32_SEL,
sizeof(n->sel) + n->sel.nkeys*sizeof(struct tc_u32_key),
&n->sel))
goto nla_put_failure;
if (n->ht_up) {
u32 htid = n->handle & 0xFFFFF000;
if (nla_put_u32(skb, TCA_U32_HASH, htid))
goto nla_put_failure;
}
if (n->res.classid &&
nla_put_u32(skb, TCA_U32_CLASSID, n->res.classid))
goto nla_put_failure;
if (n->ht_down &&
nla_put_u32(skb, TCA_U32_LINK, n->ht_down->handle))
goto nla_put_failure;
#ifdef CONFIG_CLS_U32_MARK
if ((n->mark.val || n->mark.mask) &&
nla_put(skb, TCA_U32_MARK, sizeof(n->mark), &n->mark))
goto nla_put_failure;
#endif
if (tcf_exts_dump(skb, &n->exts) < 0)
goto nla_put_failure;
#ifdef CONFIG_NET_CLS_IND
if (n->ifindex) {
struct net_device *dev;
dev = __dev_get_by_index(net, n->ifindex);
if (dev && nla_put_string(skb, TCA_U32_INDEV, dev->name))
goto nla_put_failure;
}
#endif
#ifdef CONFIG_CLS_U32_PERF
if (nla_put(skb, TCA_U32_PCNT,
sizeof(struct tc_u32_pcnt) + n->sel.nkeys*sizeof(u64),
n->pf))
goto nla_put_failure;
#endif
}
nla_nest_end(skb, nest);
if (TC_U32_KEY(n->handle))
if (tcf_exts_dump_stats(skb, &n->exts) < 0)
goto nla_put_failure;
return skb->len;
nla_put_failure:
nla_nest_cancel(skb, nest);
return -1;
}
static struct tcf_proto_ops cls_u32_ops __read_mostly = {
.kind = "u32",
.classify = u32_classify,
.init = u32_init,
.destroy = u32_destroy,
.get = u32_get,
.put = u32_put,
.change = u32_change,
.delete = u32_delete,
.walk = u32_walk,
.dump = u32_dump,
.owner = THIS_MODULE,
};
static int __init init_u32(void)
{
pr_info("u32 classifier\n");
#ifdef CONFIG_CLS_U32_PERF
pr_info(" Performance counters on\n");
#endif
#ifdef CONFIG_NET_CLS_IND
pr_info(" input device check on\n");
#endif
#ifdef CONFIG_NET_CLS_ACT
pr_info(" Actions configured\n");
#endif
return register_tcf_proto_ops(&cls_u32_ops);
}
static void __exit exit_u32(void)
{
unregister_tcf_proto_ops(&cls_u32_ops);
}
module_init(init_u32)
module_exit(exit_u32)
MODULE_LICENSE("GPL");