linux/net/sched/act_skbmod.c

309 lines
7.8 KiB
C
Raw Normal View History

/*
* 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>
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>
2016-11-17 09:58:21 +08:00
static unsigned int skbmod_net_id;
static struct tc_action_ops act_skbmod_ops;
#define MAX_EDIT_LEN ETH_HLEN
static int tcf_skbmod_act(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 */
goto drop;
action = READ_ONCE(d->tcf_action);
if (unlikely(action == TC_ACT_SHOT))
goto drop;
p = rcu_dereference_bh(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;
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;
drop:
qstats_overlimit_inc(this_cpu_ptr(d->common.cpu_qstats));
return TC_ACT_SHOT;
}
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, bool rtnl_held,
struct netlink_ext_ack *extack)
{
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, NULL);
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;
err = tcf_idr_check_alloc(tn, &parm->index, a, bind);
if (err < 0)
return err;
exists = err;
if (exists && bind)
return 0;
if (!lflags) {
if (exists)
tcf_idr_release(*a, bind);
else
tcf_idr_cleanup(tn, parm->index);
return -EINVAL;
}
if (!exists) {
ret = tcf_idr_create(tn, parm->index, est, a,
&act_skbmod_ops, bind, true);
if (ret) {
tcf_idr_cleanup(tn, parm->index);
return ret;
}
ret = ACT_P_CREATED;
} else if (!ovr) {
tcf_idr_release(*a, bind);
return -EEXIST;
}
d = to_skbmod(*a);
p = kzalloc(sizeof(struct tcf_skbmod_params), GFP_KERNEL);
if (unlikely(!p)) {
tcf_idr_release(*a, bind);
return -ENOMEM;
}
p->flags = lflags;
d->tcf_action = parm->action;
if (ovr)
spin_lock_bh(&d->tcf_lock);
/* Protected by tcf_lock if overwriting existing action. */
p_old = rcu_dereference_protected(d->skbmod_p, 1);
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_idr_insert(tn, *a);
return ret;
}
static void tcf_skbmod_cleanup(struct tc_action *a)
{
struct tcf_skbmod *d = to_skbmod(a);
struct tcf_skbmod_params *p;
p = rcu_dereference_protected(d->skbmod_p, 1);
net/sched: fix NULL dereference on the error path of tcf_skbmod_init() when the following command # tc action replace action skbmod swap mac index 100 is run for the first time, and tcf_skbmod_init() fails to allocate struct tcf_skbmod_params, tcf_skbmod_cleanup() calls kfree_rcu(NULL), thus causing the following error: BUG: unable to handle kernel NULL pointer dereference at 0000000000000008 IP: __call_rcu+0x23/0x2b0 PGD 8000000034057067 P4D 8000000034057067 PUD 74937067 PMD 0 Oops: 0002 [#1] SMP PTI Modules linked in: act_skbmod(E) psample ip6table_filter ip6_tables iptable_filter binfmt_misc ext4 snd_hda_codec_generic snd_hda_intel snd_hda_codec crct10dif_pclmul mbcache jbd2 crc32_pclmul snd_hda_core ghash_clmulni_intel snd_hwdep pcbc snd_seq snd_seq_device snd_pcm aesni_intel snd_timer crypto_simd glue_helper snd cryptd virtio_balloon joydev soundcore pcspkr i2c_piix4 nfsd auth_rpcgss nfs_acl lockd grace sunrpc ip_tables xfs libcrc32c ata_generic pata_acpi qxl drm_kms_helper syscopyarea sysfillrect sysimgblt fb_sys_fops ttm drm virtio_console virtio_net virtio_blk ata_piix libata crc32c_intel virtio_pci serio_raw virtio_ring virtio i2c_core floppy dm_mirror dm_region_hash dm_log dm_mod [last unloaded: act_skbmod] CPU: 3 PID: 3144 Comm: tc Tainted: G E 4.16.0-rc4.act_vlan.orig+ #403 Hardware name: Red Hat KVM, BIOS 0.5.1 01/01/2011 RIP: 0010:__call_rcu+0x23/0x2b0 RSP: 0018:ffffbd2e403e7798 EFLAGS: 00010246 RAX: ffffffffc0872080 RBX: ffff981d34bff780 RCX: 00000000ffffffff RDX: ffffffff922a5f00 RSI: 0000000000000000 RDI: 0000000000000000 RBP: 0000000000000000 R08: 0000000000000001 R09: 000000000000021f R10: 000000003d003000 R11: 0000000000aaaaaa R12: 0000000000000000 R13: ffffffff922a5f00 R14: 0000000000000001 R15: ffff981d3b698c2c FS: 00007f3678292740(0000) GS:ffff981d3fd80000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000000000008 CR3: 000000007c57a006 CR4: 00000000001606e0 Call Trace: __tcf_idr_release+0x79/0xf0 tcf_skbmod_init+0x1d1/0x210 [act_skbmod] tcf_action_init_1+0x2cc/0x430 tcf_action_init+0xd3/0x1b0 tc_ctl_action+0x18b/0x240 rtnetlink_rcv_msg+0x29c/0x310 ? _cond_resched+0x15/0x30 ? __kmalloc_node_track_caller+0x1b9/0x270 ? rtnl_calcit.isra.28+0x100/0x100 netlink_rcv_skb+0xd2/0x110 netlink_unicast+0x17c/0x230 netlink_sendmsg+0x2cd/0x3c0 sock_sendmsg+0x30/0x40 ___sys_sendmsg+0x27a/0x290 ? filemap_map_pages+0x34a/0x3a0 ? __handle_mm_fault+0xbfd/0xe20 __sys_sendmsg+0x51/0x90 do_syscall_64+0x6e/0x1a0 entry_SYSCALL_64_after_hwframe+0x3d/0xa2 RIP: 0033:0x7f36776a3ba0 RSP: 002b:00007fff4703b618 EFLAGS: 00000246 ORIG_RAX: 000000000000002e RAX: ffffffffffffffda RBX: 00007fff4703b740 RCX: 00007f36776a3ba0 RDX: 0000000000000000 RSI: 00007fff4703b690 RDI: 0000000000000003 RBP: 000000005aaaba36 R08: 0000000000000002 R09: 0000000000000000 R10: 00007fff4703b0a0 R11: 0000000000000246 R12: 0000000000000000 R13: 00007fff4703b754 R14: 0000000000000001 R15: 0000000000669f60 Code: 5d e9 42 da ff ff 66 90 0f 1f 44 00 00 41 57 41 56 41 55 49 89 d5 41 54 55 48 89 fd 53 48 83 ec 08 40 f6 c7 07 0f 85 19 02 00 00 <48> 89 75 08 48 c7 45 00 00 00 00 00 9c 58 0f 1f 44 00 00 49 89 RIP: __call_rcu+0x23/0x2b0 RSP: ffffbd2e403e7798 CR2: 0000000000000008 Fix it in tcf_skbmod_cleanup(), ensuring that kfree_rcu(p, ...) is called only when p is not NULL. Fixes: 86da71b57383 ("net_sched: Introduce skbmod action") Signed-off-by: Davide Caratti <dcaratti@redhat.com> Acked-by: Jiri Pirko <jiri@mellanox.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-03-16 07:00:57 +08:00
if (p)
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;
struct tc_skbmod opt = {
.index = d->tcf_index,
.refcnt = refcount_read(&d->tcf_refcnt) - ref,
.bindcnt = atomic_read(&d->tcf_bindcnt) - bind,
};
struct tcf_t t;
spin_lock_bh(&d->tcf_lock);
opt.action = d->tcf_action;
p = rcu_dereference_protected(d->skbmod_p,
lockdep_is_held(&d->tcf_lock));
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;
spin_unlock_bh(&d->tcf_lock);
return skb->len;
nla_put_failure:
spin_unlock_bh(&d->tcf_lock);
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 netlink_ext_ack *extack)
{
struct tc_action_net *tn = net_generic(net, skbmod_net_id);
return tcf_generic_walker(tn, skb, cb, type, ops, extack);
}
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_idr_search(tn, a, index);
}
static struct tc_action_ops act_skbmod_ops = {
.kind = "skbmod",
.type = TCA_ACT_SKBMOD,
.owner = THIS_MODULE,
.act = tcf_skbmod_act,
.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);
}
static void __net_exit skbmod_exit_net(struct list_head *net_list)
{
tc_action_net_exit(net_list, skbmod_net_id);
}
static struct pernet_operations skbmod_net_ops = {
.init = skbmod_init_net,
.exit_batch = 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);