2016-09-12 18:13:09 -06:00
|
|
|
/*
|
|
|
|
* net/sched/act_skbmod.c skb data modifier
|
|
|
|
*
|
|
|
|
* Copyright (c) 2016 Jamal Hadi Salim <jhs@mojatatu.com>
|
|
|
|
*
|
|
|
|
* 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.
|
|
|
|
*/
|
|
|
|
|
|
|
|
#include <linux/module.h>
|
|
|
|
#include <linux/init.h>
|
|
|
|
#include <linux/kernel.h>
|
|
|
|
#include <linux/skbuff.h>
|
|
|
|
#include <linux/rtnetlink.h>
|
|
|
|
#include <net/netlink.h>
|
|
|
|
#include <net/pkt_sched.h>
|
|
|
|
|
|
|
|
#include <linux/tc_act/tc_skbmod.h>
|
|
|
|
#include <net/tc_act/tc_skbmod.h>
|
|
|
|
|
|
|
|
#define SKBMOD_TAB_MASK 15
|
|
|
|
|
netns: make struct pernet_operations::id unsigned int
Make struct pernet_operations::id unsigned.
There are 2 reasons to do so:
1)
This field is really an index into an zero based array and
thus is unsigned entity. Using negative value is out-of-bound
access by definition.
2)
On x86_64 unsigned 32-bit data which are mixed with pointers
via array indexing or offsets added or subtracted to pointers
are preffered to signed 32-bit data.
"int" being used as an array index needs to be sign-extended
to 64-bit before being used.
void f(long *p, int i)
{
g(p[i]);
}
roughly translates to
movsx rsi, esi
mov rdi, [rsi+...]
call g
MOVSX is 3 byte instruction which isn't necessary if the variable is
unsigned because x86_64 is zero extending by default.
Now, there is net_generic() function which, you guessed it right, uses
"int" as an array index:
static inline void *net_generic(const struct net *net, int id)
{
...
ptr = ng->ptr[id - 1];
...
}
And this function is used a lot, so those sign extensions add up.
Patch snipes ~1730 bytes on allyesconfig kernel (without all junk
messing with code generation):
add/remove: 0/0 grow/shrink: 70/598 up/down: 396/-2126 (-1730)
Unfortunately some functions actually grow bigger.
This is a semmingly random artefact of code generation with register
allocator being used differently. gcc decides that some variable
needs to live in new r8+ registers and every access now requires REX
prefix. Or it is shifted into r12, so [r12+0] addressing mode has to be
used which is longer than [r8]
However, overall balance is in negative direction:
add/remove: 0/0 grow/shrink: 70/598 up/down: 396/-2126 (-1730)
function old new delta
nfsd4_lock 3886 3959 +73
tipc_link_build_proto_msg 1096 1140 +44
mac80211_hwsim_new_radio 2776 2808 +32
tipc_mon_rcv 1032 1058 +26
svcauth_gss_legacy_init 1413 1429 +16
tipc_bcbase_select_primary 379 392 +13
nfsd4_exchange_id 1247 1260 +13
nfsd4_setclientid_confirm 782 793 +11
...
put_client_renew_locked 494 480 -14
ip_set_sockfn_get 730 716 -14
geneve_sock_add 829 813 -16
nfsd4_sequence_done 721 703 -18
nlmclnt_lookup_host 708 686 -22
nfsd4_lockt 1085 1063 -22
nfs_get_client 1077 1050 -27
tcf_bpf_init 1106 1076 -30
nfsd4_encode_fattr 5997 5930 -67
Total: Before=154856051, After=154854321, chg -0.00%
Signed-off-by: Alexey Dobriyan <adobriyan@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2016-11-16 18:58:21 -07:00
|
|
|
static unsigned int skbmod_net_id;
|
2016-09-12 18:13:09 -06:00
|
|
|
static struct tc_action_ops act_skbmod_ops;
|
|
|
|
|
|
|
|
#define MAX_EDIT_LEN ETH_HLEN
|
|
|
|
static int tcf_skbmod_run(struct sk_buff *skb, const struct tc_action *a,
|
|
|
|
struct tcf_result *res)
|
|
|
|
{
|
|
|
|
struct tcf_skbmod *d = to_skbmod(a);
|
|
|
|
int action;
|
|
|
|
struct tcf_skbmod_params *p;
|
|
|
|
u64 flags;
|
|
|
|
int err;
|
|
|
|
|
|
|
|
tcf_lastuse_update(&d->tcf_tm);
|
|
|
|
bstats_cpu_update(this_cpu_ptr(d->common.cpu_bstats), skb);
|
|
|
|
|
|
|
|
/* XXX: if you are going to edit more fields beyond ethernet header
|
|
|
|
* (example when you add IP header replacement or vlan swap)
|
|
|
|
* then MAX_EDIT_LEN needs to change appropriately
|
|
|
|
*/
|
|
|
|
err = skb_ensure_writable(skb, MAX_EDIT_LEN);
|
|
|
|
if (unlikely(err)) { /* best policy is to drop on the floor */
|
|
|
|
qstats_overlimit_inc(this_cpu_ptr(d->common.cpu_qstats));
|
|
|
|
return TC_ACT_SHOT;
|
|
|
|
}
|
|
|
|
|
|
|
|
rcu_read_lock();
|
|
|
|
action = READ_ONCE(d->tcf_action);
|
|
|
|
if (unlikely(action == TC_ACT_SHOT)) {
|
|
|
|
qstats_overlimit_inc(this_cpu_ptr(d->common.cpu_qstats));
|
|
|
|
rcu_read_unlock();
|
|
|
|
return action;
|
|
|
|
}
|
|
|
|
|
|
|
|
p = rcu_dereference(d->skbmod_p);
|
|
|
|
flags = p->flags;
|
|
|
|
if (flags & SKBMOD_F_DMAC)
|
|
|
|
ether_addr_copy(eth_hdr(skb)->h_dest, p->eth_dst);
|
|
|
|
if (flags & SKBMOD_F_SMAC)
|
|
|
|
ether_addr_copy(eth_hdr(skb)->h_source, p->eth_src);
|
|
|
|
if (flags & SKBMOD_F_ETYPE)
|
|
|
|
eth_hdr(skb)->h_proto = p->eth_type;
|
|
|
|
rcu_read_unlock();
|
|
|
|
|
|
|
|
if (flags & SKBMOD_F_SWAPMAC) {
|
|
|
|
u16 tmpaddr[ETH_ALEN / 2]; /* ether_addr_copy() requirement */
|
|
|
|
/*XXX: I am sure we can come up with more efficient swapping*/
|
|
|
|
ether_addr_copy((u8 *)tmpaddr, eth_hdr(skb)->h_dest);
|
|
|
|
ether_addr_copy(eth_hdr(skb)->h_dest, eth_hdr(skb)->h_source);
|
|
|
|
ether_addr_copy(eth_hdr(skb)->h_source, (u8 *)tmpaddr);
|
|
|
|
}
|
|
|
|
|
|
|
|
return action;
|
|
|
|
}
|
|
|
|
|
|
|
|
static const struct nla_policy skbmod_policy[TCA_SKBMOD_MAX + 1] = {
|
|
|
|
[TCA_SKBMOD_PARMS] = { .len = sizeof(struct tc_skbmod) },
|
|
|
|
[TCA_SKBMOD_DMAC] = { .len = ETH_ALEN },
|
|
|
|
[TCA_SKBMOD_SMAC] = { .len = ETH_ALEN },
|
|
|
|
[TCA_SKBMOD_ETYPE] = { .type = NLA_U16 },
|
|
|
|
};
|
|
|
|
|
|
|
|
static int tcf_skbmod_init(struct net *net, struct nlattr *nla,
|
|
|
|
struct nlattr *est, struct tc_action **a,
|
|
|
|
int ovr, int bind)
|
|
|
|
{
|
|
|
|
struct tc_action_net *tn = net_generic(net, skbmod_net_id);
|
|
|
|
struct nlattr *tb[TCA_SKBMOD_MAX + 1];
|
|
|
|
struct tcf_skbmod_params *p, *p_old;
|
|
|
|
struct tc_skbmod *parm;
|
|
|
|
struct tcf_skbmod *d;
|
|
|
|
bool exists = false;
|
|
|
|
u8 *daddr = NULL;
|
|
|
|
u8 *saddr = NULL;
|
|
|
|
u16 eth_type = 0;
|
|
|
|
u32 lflags = 0;
|
|
|
|
int ret = 0, err;
|
|
|
|
|
|
|
|
if (!nla)
|
|
|
|
return -EINVAL;
|
|
|
|
|
|
|
|
err = nla_parse_nested(tb, TCA_SKBMOD_MAX, nla, skbmod_policy);
|
|
|
|
if (err < 0)
|
|
|
|
return err;
|
|
|
|
|
|
|
|
if (!tb[TCA_SKBMOD_PARMS])
|
|
|
|
return -EINVAL;
|
|
|
|
|
|
|
|
if (tb[TCA_SKBMOD_DMAC]) {
|
|
|
|
daddr = nla_data(tb[TCA_SKBMOD_DMAC]);
|
|
|
|
lflags |= SKBMOD_F_DMAC;
|
|
|
|
}
|
|
|
|
|
|
|
|
if (tb[TCA_SKBMOD_SMAC]) {
|
|
|
|
saddr = nla_data(tb[TCA_SKBMOD_SMAC]);
|
|
|
|
lflags |= SKBMOD_F_SMAC;
|
|
|
|
}
|
|
|
|
|
|
|
|
if (tb[TCA_SKBMOD_ETYPE]) {
|
|
|
|
eth_type = nla_get_u16(tb[TCA_SKBMOD_ETYPE]);
|
|
|
|
lflags |= SKBMOD_F_ETYPE;
|
|
|
|
}
|
|
|
|
|
|
|
|
parm = nla_data(tb[TCA_SKBMOD_PARMS]);
|
|
|
|
if (parm->flags & SKBMOD_F_SWAPMAC)
|
|
|
|
lflags = SKBMOD_F_SWAPMAC;
|
|
|
|
|
|
|
|
exists = tcf_hash_check(tn, parm->index, a, bind);
|
|
|
|
if (exists && bind)
|
|
|
|
return 0;
|
|
|
|
|
|
|
|
if (!lflags)
|
|
|
|
return -EINVAL;
|
|
|
|
|
|
|
|
if (!exists) {
|
|
|
|
ret = tcf_hash_create(tn, parm->index, est, a,
|
|
|
|
&act_skbmod_ops, bind, true);
|
|
|
|
if (ret)
|
|
|
|
return ret;
|
|
|
|
|
|
|
|
ret = ACT_P_CREATED;
|
|
|
|
} else {
|
|
|
|
tcf_hash_release(*a, bind);
|
|
|
|
if (!ovr)
|
|
|
|
return -EEXIST;
|
|
|
|
}
|
|
|
|
|
|
|
|
d = to_skbmod(*a);
|
|
|
|
|
|
|
|
ASSERT_RTNL();
|
|
|
|
p = kzalloc(sizeof(struct tcf_skbmod_params), GFP_KERNEL);
|
|
|
|
if (unlikely(!p)) {
|
|
|
|
if (ovr)
|
|
|
|
tcf_hash_release(*a, bind);
|
|
|
|
return -ENOMEM;
|
|
|
|
}
|
|
|
|
|
|
|
|
p->flags = lflags;
|
|
|
|
d->tcf_action = parm->action;
|
|
|
|
|
|
|
|
p_old = rtnl_dereference(d->skbmod_p);
|
|
|
|
|
|
|
|
if (ovr)
|
|
|
|
spin_lock_bh(&d->tcf_lock);
|
|
|
|
|
|
|
|
if (lflags & SKBMOD_F_DMAC)
|
|
|
|
ether_addr_copy(p->eth_dst, daddr);
|
|
|
|
if (lflags & SKBMOD_F_SMAC)
|
|
|
|
ether_addr_copy(p->eth_src, saddr);
|
|
|
|
if (lflags & SKBMOD_F_ETYPE)
|
|
|
|
p->eth_type = htons(eth_type);
|
|
|
|
|
|
|
|
rcu_assign_pointer(d->skbmod_p, p);
|
|
|
|
if (ovr)
|
|
|
|
spin_unlock_bh(&d->tcf_lock);
|
|
|
|
|
|
|
|
if (p_old)
|
|
|
|
kfree_rcu(p_old, rcu);
|
|
|
|
|
|
|
|
if (ret == ACT_P_CREATED)
|
|
|
|
tcf_hash_insert(tn, *a);
|
|
|
|
return ret;
|
|
|
|
}
|
|
|
|
|
|
|
|
static void tcf_skbmod_cleanup(struct tc_action *a, int bind)
|
|
|
|
{
|
|
|
|
struct tcf_skbmod *d = to_skbmod(a);
|
|
|
|
struct tcf_skbmod_params *p;
|
|
|
|
|
|
|
|
p = rcu_dereference_protected(d->skbmod_p, 1);
|
|
|
|
kfree_rcu(p, rcu);
|
|
|
|
}
|
|
|
|
|
|
|
|
static int tcf_skbmod_dump(struct sk_buff *skb, struct tc_action *a,
|
|
|
|
int bind, int ref)
|
|
|
|
{
|
|
|
|
struct tcf_skbmod *d = to_skbmod(a);
|
|
|
|
unsigned char *b = skb_tail_pointer(skb);
|
|
|
|
struct tcf_skbmod_params *p = rtnl_dereference(d->skbmod_p);
|
|
|
|
struct tc_skbmod opt = {
|
|
|
|
.index = d->tcf_index,
|
|
|
|
.refcnt = d->tcf_refcnt - ref,
|
|
|
|
.bindcnt = d->tcf_bindcnt - bind,
|
|
|
|
.action = d->tcf_action,
|
|
|
|
};
|
|
|
|
struct tcf_t t;
|
|
|
|
|
|
|
|
opt.flags = p->flags;
|
|
|
|
if (nla_put(skb, TCA_SKBMOD_PARMS, sizeof(opt), &opt))
|
|
|
|
goto nla_put_failure;
|
|
|
|
if ((p->flags & SKBMOD_F_DMAC) &&
|
|
|
|
nla_put(skb, TCA_SKBMOD_DMAC, ETH_ALEN, p->eth_dst))
|
|
|
|
goto nla_put_failure;
|
|
|
|
if ((p->flags & SKBMOD_F_SMAC) &&
|
|
|
|
nla_put(skb, TCA_SKBMOD_SMAC, ETH_ALEN, p->eth_src))
|
|
|
|
goto nla_put_failure;
|
|
|
|
if ((p->flags & SKBMOD_F_ETYPE) &&
|
|
|
|
nla_put_u16(skb, TCA_SKBMOD_ETYPE, ntohs(p->eth_type)))
|
|
|
|
goto nla_put_failure;
|
|
|
|
|
|
|
|
tcf_tm_dump(&t, &d->tcf_tm);
|
|
|
|
if (nla_put_64bit(skb, TCA_SKBMOD_TM, sizeof(t), &t, TCA_SKBMOD_PAD))
|
|
|
|
goto nla_put_failure;
|
|
|
|
|
|
|
|
return skb->len;
|
|
|
|
nla_put_failure:
|
|
|
|
rcu_read_unlock();
|
|
|
|
nlmsg_trim(skb, b);
|
|
|
|
return -1;
|
|
|
|
}
|
|
|
|
|
|
|
|
static int tcf_skbmod_walker(struct net *net, struct sk_buff *skb,
|
|
|
|
struct netlink_callback *cb, int type,
|
|
|
|
const struct tc_action_ops *ops)
|
|
|
|
{
|
|
|
|
struct tc_action_net *tn = net_generic(net, skbmod_net_id);
|
|
|
|
|
|
|
|
return tcf_generic_walker(tn, skb, cb, type, ops);
|
|
|
|
}
|
|
|
|
|
|
|
|
static int tcf_skbmod_search(struct net *net, struct tc_action **a, u32 index)
|
|
|
|
{
|
|
|
|
struct tc_action_net *tn = net_generic(net, skbmod_net_id);
|
|
|
|
|
|
|
|
return tcf_hash_search(tn, a, index);
|
|
|
|
}
|
|
|
|
|
|
|
|
static struct tc_action_ops act_skbmod_ops = {
|
|
|
|
.kind = "skbmod",
|
|
|
|
.type = TCA_ACT_SKBMOD,
|
|
|
|
.owner = THIS_MODULE,
|
|
|
|
.act = tcf_skbmod_run,
|
|
|
|
.dump = tcf_skbmod_dump,
|
|
|
|
.init = tcf_skbmod_init,
|
|
|
|
.cleanup = tcf_skbmod_cleanup,
|
|
|
|
.walk = tcf_skbmod_walker,
|
|
|
|
.lookup = tcf_skbmod_search,
|
|
|
|
.size = sizeof(struct tcf_skbmod),
|
|
|
|
};
|
|
|
|
|
|
|
|
static __net_init int skbmod_init_net(struct net *net)
|
|
|
|
{
|
|
|
|
struct tc_action_net *tn = net_generic(net, skbmod_net_id);
|
|
|
|
|
|
|
|
return tc_action_net_init(tn, &act_skbmod_ops, SKBMOD_TAB_MASK);
|
|
|
|
}
|
|
|
|
|
|
|
|
static void __net_exit skbmod_exit_net(struct net *net)
|
|
|
|
{
|
|
|
|
struct tc_action_net *tn = net_generic(net, skbmod_net_id);
|
|
|
|
|
|
|
|
tc_action_net_exit(tn);
|
|
|
|
}
|
|
|
|
|
|
|
|
static struct pernet_operations skbmod_net_ops = {
|
|
|
|
.init = skbmod_init_net,
|
|
|
|
.exit = skbmod_exit_net,
|
|
|
|
.id = &skbmod_net_id,
|
|
|
|
.size = sizeof(struct tc_action_net),
|
|
|
|
};
|
|
|
|
|
|
|
|
MODULE_AUTHOR("Jamal Hadi Salim, <jhs@mojatatu.com>");
|
|
|
|
MODULE_DESCRIPTION("SKB data mod-ing");
|
|
|
|
MODULE_LICENSE("GPL");
|
|
|
|
|
|
|
|
static int __init skbmod_init_module(void)
|
|
|
|
{
|
|
|
|
return tcf_register_action(&act_skbmod_ops, &skbmod_net_ops);
|
|
|
|
}
|
|
|
|
|
|
|
|
static void __exit skbmod_cleanup_module(void)
|
|
|
|
{
|
|
|
|
tcf_unregister_action(&act_skbmod_ops, &skbmod_net_ops);
|
|
|
|
}
|
|
|
|
|
|
|
|
module_init(skbmod_init_module);
|
|
|
|
module_exit(skbmod_cleanup_module);
|