linux/net/sched/act_vlan.c

336 lines
7.9 KiB
C
Raw Normal View History

/*
* Copyright (c) 2014 Jiri Pirko <jiri@resnulli.us>
*
* 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 <linux/if_vlan.h>
#include <net/netlink.h>
#include <net/pkt_sched.h>
#include <linux/tc_act/tc_vlan.h>
#include <net/tc_act/tc_vlan.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 vlan_net_id;
static struct tc_action_ops act_vlan_ops;
static int tcf_vlan(struct sk_buff *skb, const struct tc_action *a,
struct tcf_result *res)
{
struct tcf_vlan *v = to_vlan(a);
struct tcf_vlan_params *p;
int action;
int err;
u16 tci;
tcf_lastuse_update(&v->tcf_tm);
bstats_cpu_update(this_cpu_ptr(v->common.cpu_bstats), skb);
/* Ensure 'data' points at mac_header prior calling vlan manipulating
* functions.
*/
if (skb_at_tc_ingress(skb))
skb_push_rcsum(skb, skb->mac_len);
rcu_read_lock();
action = READ_ONCE(v->tcf_action);
p = rcu_dereference(v->vlan_p);
switch (p->tcfv_action) {
case TCA_VLAN_ACT_POP:
err = skb_vlan_pop(skb);
if (err)
goto drop;
break;
case TCA_VLAN_ACT_PUSH:
err = skb_vlan_push(skb, p->tcfv_push_proto, p->tcfv_push_vid |
(p->tcfv_push_prio << VLAN_PRIO_SHIFT));
if (err)
goto drop;
break;
case TCA_VLAN_ACT_MODIFY:
/* No-op if no vlan tag (either hw-accel or in-payload) */
if (!skb_vlan_tagged(skb))
goto unlock;
/* extract existing tag (and guarantee no hw-accel tag) */
if (skb_vlan_tag_present(skb)) {
tci = skb_vlan_tag_get(skb);
skb->vlan_tci = 0;
} else {
/* in-payload vlan tag, pop it */
err = __skb_vlan_pop(skb, &tci);
if (err)
goto drop;
}
/* replace the vid */
tci = (tci & ~VLAN_VID_MASK) | p->tcfv_push_vid;
/* replace prio bits, if tcfv_push_prio specified */
if (p->tcfv_push_prio) {
tci &= ~VLAN_PRIO_MASK;
tci |= p->tcfv_push_prio << VLAN_PRIO_SHIFT;
}
/* put updated tci as hwaccel tag */
__vlan_hwaccel_put_tag(skb, p->tcfv_push_proto, tci);
break;
default:
BUG();
}
goto unlock;
drop:
action = TC_ACT_SHOT;
qstats_drop_inc(this_cpu_ptr(v->common.cpu_qstats));
unlock:
rcu_read_unlock();
if (skb_at_tc_ingress(skb))
skb_pull_rcsum(skb, skb->mac_len);
return action;
}
static const struct nla_policy vlan_policy[TCA_VLAN_MAX + 1] = {
[TCA_VLAN_PARMS] = { .len = sizeof(struct tc_vlan) },
[TCA_VLAN_PUSH_VLAN_ID] = { .type = NLA_U16 },
[TCA_VLAN_PUSH_VLAN_PROTOCOL] = { .type = NLA_U16 },
[TCA_VLAN_PUSH_VLAN_PRIORITY] = { .type = NLA_U8 },
};
static int tcf_vlan_init(struct net *net, struct nlattr *nla,
struct nlattr *est, struct tc_action **a,
int ovr, int bind, struct netlink_ext_ack *extack)
{
struct tc_action_net *tn = net_generic(net, vlan_net_id);
struct nlattr *tb[TCA_VLAN_MAX + 1];
struct tcf_vlan_params *p, *p_old;
struct tc_vlan *parm;
struct tcf_vlan *v;
int action;
__be16 push_vid = 0;
__be16 push_proto = 0;
u8 push_prio = 0;
bool exists = false;
int ret = 0, err;
if (!nla)
return -EINVAL;
err = nla_parse_nested(tb, TCA_VLAN_MAX, nla, vlan_policy, NULL);
if (err < 0)
return err;
if (!tb[TCA_VLAN_PARMS])
return -EINVAL;
parm = nla_data(tb[TCA_VLAN_PARMS]);
exists = tcf_idr_check(tn, parm->index, a, bind);
if (exists && bind)
return 0;
switch (parm->v_action) {
case TCA_VLAN_ACT_POP:
break;
case TCA_VLAN_ACT_PUSH:
case TCA_VLAN_ACT_MODIFY:
if (!tb[TCA_VLAN_PUSH_VLAN_ID]) {
if (exists)
tcf_idr_release(*a, bind);
return -EINVAL;
}
push_vid = nla_get_u16(tb[TCA_VLAN_PUSH_VLAN_ID]);
if (push_vid >= VLAN_VID_MASK) {
if (exists)
tcf_idr_release(*a, bind);
return -ERANGE;
}
if (tb[TCA_VLAN_PUSH_VLAN_PROTOCOL]) {
push_proto = nla_get_be16(tb[TCA_VLAN_PUSH_VLAN_PROTOCOL]);
switch (push_proto) {
case htons(ETH_P_8021Q):
case htons(ETH_P_8021AD):
break;
default:
return -EPROTONOSUPPORT;
}
} else {
push_proto = htons(ETH_P_8021Q);
}
if (tb[TCA_VLAN_PUSH_VLAN_PRIORITY])
push_prio = nla_get_u8(tb[TCA_VLAN_PUSH_VLAN_PRIORITY]);
break;
default:
if (exists)
tcf_idr_release(*a, bind);
return -EINVAL;
}
action = parm->v_action;
if (!exists) {
ret = tcf_idr_create(tn, parm->index, est, a,
&act_vlan_ops, bind, true);
if (ret)
return ret;
ret = ACT_P_CREATED;
} else {
tcf_idr_release(*a, bind);
if (!ovr)
return -EEXIST;
}
v = to_vlan(*a);
ASSERT_RTNL();
p = kzalloc(sizeof(*p), GFP_KERNEL);
if (!p) {
net/sched: fix idr leak in the error path of tcf_vlan_init() tcf_vlan_init() can fail after the idr has been successfully reserved. When this happens, every subsequent attempt to configure vlan rules using the same idr value will systematically fail with -ENOSPC, unless the first attempt was done using the 'replace' keyword. # tc action add action vlan pop index 100 RTNETLINK answers: Cannot allocate memory We have an error talking to the kernel # tc action add action vlan pop index 100 RTNETLINK answers: No space left on device We have an error talking to the kernel # tc action add action vlan pop index 100 RTNETLINK answers: No space left on device We have an error talking to the kernel ... Fix this in tcf_vlan_init(), ensuring that tcf_idr_release() is called on the error path when the idr has been reserved, but not yet inserted. Also, don't test 'ovr' in the error path, to avoid a 'replace' failure implicitly become a 'delete' that leaks refcount in act_vlan module: # rmmod act_vlan; modprobe act_vlan # tc action add action vlan push id 5 index 100 # tc action replace action vlan push id 7 index 100 RTNETLINK answers: Cannot allocate memory We have an error talking to the kernel # tc action list action vlan # # rmmod act_vlan rmmod: ERROR: Module act_vlan is in use Fixes: 4c5b9d9642c8 ("act_vlan: VLAN action rewrite to use RCU lock/unlock and update") Fixes: 65a206c01e8e ("net/sched: Change act_api and act_xxx modules to use IDR") Acked-by: Jamal Hadi Salim <jhs@mojatatu.com> Signed-off-by: Davide Caratti <dcaratti@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-03-19 22:31:27 +08:00
if (ret == ACT_P_CREATED)
tcf_idr_release(*a, bind);
return -ENOMEM;
}
v->tcf_action = parm->action;
p_old = rtnl_dereference(v->vlan_p);
p->tcfv_action = action;
p->tcfv_push_vid = push_vid;
p->tcfv_push_prio = push_prio;
p->tcfv_push_proto = push_proto;
rcu_assign_pointer(v->vlan_p, p);
if (p_old)
kfree_rcu(p_old, rcu);
if (ret == ACT_P_CREATED)
tcf_idr_insert(tn, *a);
return ret;
}
static void tcf_vlan_cleanup(struct tc_action *a)
{
struct tcf_vlan *v = to_vlan(a);
struct tcf_vlan_params *p;
p = rcu_dereference_protected(v->vlan_p, 1);
net/sched: fix NULL dereference in the error path of tcf_vlan_init() when the following command # tc actions replace action vlan pop index 100 is run for the first time, and tcf_vlan_init() fails allocating struct tcf_vlan_params, tcf_vlan_cleanup() calls kfree_rcu(NULL, ...). This causes the following error: BUG: unable to handle kernel NULL pointer dereference at 0000000000000018 IP: __call_rcu+0x23/0x2b0 PGD 80000000760a2067 P4D 80000000760a2067 PUD 742c1067 PMD 0 Oops: 0002 [#1] SMP PTI Modules linked in: act_vlan(E) ip6table_filter ip6_tables iptable_filter binfmt_misc ext4 snd_hda_codec_generic snd_hda_intel mbcache snd_hda_codec jbd2 snd_hda_core crct10dif_pclmul crc32_pclmul ghash_clmulni_intel pcbc snd_hwdep snd_seq snd_seq_device snd_pcm aesni_intel crypto_simd snd_timer glue_helper snd cryptd joydev soundcore virtio_balloon 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_blk virtio_net ata_piix crc32c_intel libata virtio_pci i2c_core virtio_ring serio_raw virtio floppy dm_mirror dm_region_hash dm_log dm_mod [last unloaded: act_vlan] CPU: 3 PID: 3119 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:ffffaac3005fb798 EFLAGS: 00010246 RAX: ffffffffc0704080 RBX: ffff97f2b4bbe900 RCX: 00000000ffffffff RDX: ffffffffabca5f00 RSI: 0000000000000010 RDI: 0000000000000010 RBP: 0000000000000010 R08: 0000000000000001 R09: 0000000000000044 R10: 00000000fd003000 R11: ffff97f2faab5b91 R12: 0000000000000000 R13: ffffffffabca5f00 R14: ffff97f2fb80202c R15: 00000000fffffff4 FS: 00007f68f75b4740(0000) GS:ffff97f2ffd80000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000000000018 CR3: 0000000072b52001 CR4: 00000000001606e0 Call Trace: __tcf_idr_release+0x79/0xf0 tcf_vlan_init+0x168/0x270 [act_vlan] 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: 0033:0x7f68f69c5ba0 RSP: 002b:00007fffd79c1118 EFLAGS: 00000246 ORIG_RAX: 000000000000002e RAX: ffffffffffffffda RBX: 00007fffd79c1240 RCX: 00007f68f69c5ba0 RDX: 0000000000000000 RSI: 00007fffd79c1190 RDI: 0000000000000003 RBP: 000000005aaa708e R08: 0000000000000002 R09: 0000000000000000 R10: 00007fffd79c0ba0 R11: 0000000000000246 R12: 0000000000000000 R13: 00007fffd79c1254 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: ffffaac3005fb798 CR2: 0000000000000018 fix this in tcf_vlan_cleanup(), ensuring that kfree_rcu(p, ...) is called only when p is not NULL. Fixes: 4c5b9d9642c8 ("act_vlan: VLAN action rewrite to use RCU lock/unlock and update") Acked-by: Jiri Pirko <jiri@mellanox.com> Acked-by: Manish Kurup <manish.kurup@verizon.com> Signed-off-by: Davide Caratti <dcaratti@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-03-16 07:00:53 +08:00
if (p)
kfree_rcu(p, rcu);
}
static int tcf_vlan_dump(struct sk_buff *skb, struct tc_action *a,
int bind, int ref)
{
unsigned char *b = skb_tail_pointer(skb);
struct tcf_vlan *v = to_vlan(a);
struct tcf_vlan_params *p = rtnl_dereference(v->vlan_p);
struct tc_vlan opt = {
.index = v->tcf_index,
.refcnt = v->tcf_refcnt - ref,
.bindcnt = v->tcf_bindcnt - bind,
.action = v->tcf_action,
.v_action = p->tcfv_action,
};
struct tcf_t t;
if (nla_put(skb, TCA_VLAN_PARMS, sizeof(opt), &opt))
goto nla_put_failure;
if ((p->tcfv_action == TCA_VLAN_ACT_PUSH ||
p->tcfv_action == TCA_VLAN_ACT_MODIFY) &&
(nla_put_u16(skb, TCA_VLAN_PUSH_VLAN_ID, p->tcfv_push_vid) ||
nla_put_be16(skb, TCA_VLAN_PUSH_VLAN_PROTOCOL,
p->tcfv_push_proto) ||
(nla_put_u8(skb, TCA_VLAN_PUSH_VLAN_PRIORITY,
p->tcfv_push_prio))))
goto nla_put_failure;
tcf_tm_dump(&t, &v->tcf_tm);
if (nla_put_64bit(skb, TCA_VLAN_TM, sizeof(t), &t, TCA_VLAN_PAD))
goto nla_put_failure;
return skb->len;
nla_put_failure:
nlmsg_trim(skb, b);
return -1;
}
static int tcf_vlan_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, vlan_net_id);
return tcf_generic_walker(tn, skb, cb, type, ops, extack);
}
static int tcf_vlan_search(struct net *net, struct tc_action **a, u32 index,
struct netlink_ext_ack *extack)
{
struct tc_action_net *tn = net_generic(net, vlan_net_id);
return tcf_idr_search(tn, a, index);
}
static struct tc_action_ops act_vlan_ops = {
.kind = "vlan",
.type = TCA_ACT_VLAN,
.owner = THIS_MODULE,
.act = tcf_vlan,
.dump = tcf_vlan_dump,
.init = tcf_vlan_init,
.cleanup = tcf_vlan_cleanup,
.walk = tcf_vlan_walker,
.lookup = tcf_vlan_search,
.size = sizeof(struct tcf_vlan),
};
static __net_init int vlan_init_net(struct net *net)
{
struct tc_action_net *tn = net_generic(net, vlan_net_id);
return tc_action_net_init(tn, &act_vlan_ops);
}
static void __net_exit vlan_exit_net(struct list_head *net_list)
{
tc_action_net_exit(net_list, vlan_net_id);
}
static struct pernet_operations vlan_net_ops = {
.init = vlan_init_net,
.exit_batch = vlan_exit_net,
.id = &vlan_net_id,
.size = sizeof(struct tc_action_net),
.async = true,
};
static int __init vlan_init_module(void)
{
return tcf_register_action(&act_vlan_ops, &vlan_net_ops);
}
static void __exit vlan_cleanup_module(void)
{
tcf_unregister_action(&act_vlan_ops, &vlan_net_ops);
}
module_init(vlan_init_module);
module_exit(vlan_cleanup_module);
MODULE_AUTHOR("Jiri Pirko <jiri@resnulli.us>");
MODULE_DESCRIPTION("vlan manipulation actions");
MODULE_LICENSE("GPL v2");