linux_dsm_epyc7002/net/sched/act_skbedit.c

358 lines
9.6 KiB
C
Raw Normal View History

/*
* Copyright (c) 2008, Intel Corporation.
*
* This program is free software; you can redistribute it and/or modify it
* under the terms and conditions of the GNU General Public License,
* version 2, as published by the Free Software Foundation.
*
* This program is distributed in the hope it will be useful, but WITHOUT
* ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
* FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
* more details.
*
* You should have received a copy of the GNU General Public License along with
* this program; if not, see <http://www.gnu.org/licenses/>.
*
* Author: Alexander Duyck <alexander.h.duyck@intel.com>
*/
#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 <net/ip.h>
#include <net/ipv6.h>
#include <net/dsfield.h>
#include <linux/tc_act/tc_skbedit.h>
#include <net/tc_act/tc_skbedit.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 08:58:21 +07:00
static unsigned int skbedit_net_id;
static struct tc_action_ops act_skbedit_ops;
static int tcf_skbedit_act(struct sk_buff *skb, const struct tc_action *a,
struct tcf_result *res)
{
struct tcf_skbedit *d = to_skbedit(a);
struct tcf_skbedit_params *params;
int action;
tcf_lastuse_update(&d->tcf_tm);
bstats_cpu_update(this_cpu_ptr(d->common.cpu_bstats), skb);
params = rcu_dereference_bh(d->params);
action = READ_ONCE(d->tcf_action);
if (params->flags & SKBEDIT_F_PRIORITY)
skb->priority = params->priority;
if (params->flags & SKBEDIT_F_INHERITDSFIELD) {
int wlen = skb_network_offset(skb);
switch (tc_skb_protocol(skb)) {
case htons(ETH_P_IP):
wlen += sizeof(struct iphdr);
if (!pskb_may_pull(skb, wlen))
goto err;
skb->priority = ipv4_get_dsfield(ip_hdr(skb)) >> 2;
break;
case htons(ETH_P_IPV6):
wlen += sizeof(struct ipv6hdr);
if (!pskb_may_pull(skb, wlen))
goto err;
skb->priority = ipv6_get_dsfield(ipv6_hdr(skb)) >> 2;
break;
}
}
if (params->flags & SKBEDIT_F_QUEUE_MAPPING &&
skb->dev->real_num_tx_queues > params->queue_mapping)
skb_set_queue_mapping(skb, params->queue_mapping);
if (params->flags & SKBEDIT_F_MARK) {
skb->mark &= ~params->mask;
skb->mark |= params->mark & params->mask;
}
if (params->flags & SKBEDIT_F_PTYPE)
skb->pkt_type = params->ptype;
return action;
err:
qstats_drop_inc(this_cpu_ptr(d->common.cpu_qstats));
return TC_ACT_SHOT;
}
static const struct nla_policy skbedit_policy[TCA_SKBEDIT_MAX + 1] = {
[TCA_SKBEDIT_PARMS] = { .len = sizeof(struct tc_skbedit) },
[TCA_SKBEDIT_PRIORITY] = { .len = sizeof(u32) },
[TCA_SKBEDIT_QUEUE_MAPPING] = { .len = sizeof(u16) },
[TCA_SKBEDIT_MARK] = { .len = sizeof(u32) },
[TCA_SKBEDIT_PTYPE] = { .len = sizeof(u16) },
[TCA_SKBEDIT_MASK] = { .len = sizeof(u32) },
[TCA_SKBEDIT_FLAGS] = { .len = sizeof(u64) },
};
static int tcf_skbedit_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, skbedit_net_id);
struct tcf_skbedit_params *params_old, *params_new;
struct nlattr *tb[TCA_SKBEDIT_MAX + 1];
struct tc_skbedit *parm;
struct tcf_skbedit *d;
u32 flags = 0, *priority = NULL, *mark = NULL, *mask = NULL;
u16 *queue_mapping = NULL, *ptype = NULL;
bool exists = false;
int ret = 0, err;
if (nla == NULL)
return -EINVAL;
err = nla_parse_nested(tb, TCA_SKBEDIT_MAX, nla, skbedit_policy, NULL);
if (err < 0)
return err;
if (tb[TCA_SKBEDIT_PARMS] == NULL)
return -EINVAL;
if (tb[TCA_SKBEDIT_PRIORITY] != NULL) {
flags |= SKBEDIT_F_PRIORITY;
priority = nla_data(tb[TCA_SKBEDIT_PRIORITY]);
}
if (tb[TCA_SKBEDIT_QUEUE_MAPPING] != NULL) {
flags |= SKBEDIT_F_QUEUE_MAPPING;
queue_mapping = nla_data(tb[TCA_SKBEDIT_QUEUE_MAPPING]);
}
if (tb[TCA_SKBEDIT_PTYPE] != NULL) {
ptype = nla_data(tb[TCA_SKBEDIT_PTYPE]);
if (!skb_pkt_type_ok(*ptype))
return -EINVAL;
flags |= SKBEDIT_F_PTYPE;
}
if (tb[TCA_SKBEDIT_MARK] != NULL) {
flags |= SKBEDIT_F_MARK;
mark = nla_data(tb[TCA_SKBEDIT_MARK]);
}
if (tb[TCA_SKBEDIT_MASK] != NULL) {
flags |= SKBEDIT_F_MASK;
mask = nla_data(tb[TCA_SKBEDIT_MASK]);
}
if (tb[TCA_SKBEDIT_FLAGS] != NULL) {
u64 *pure_flags = nla_data(tb[TCA_SKBEDIT_FLAGS]);
if (*pure_flags & SKBEDIT_F_INHERITDSFIELD)
flags |= SKBEDIT_F_INHERITDSFIELD;
}
parm = nla_data(tb[TCA_SKBEDIT_PARMS]);
err = tcf_idr_check_alloc(tn, &parm->index, a, bind);
if (err < 0)
return err;
exists = err;
if (exists && bind)
return 0;
if (!flags) {
net sched actions: fix invalid pointer dereferencing if skbedit flags missing When application fails to pass flags in netlink TLV for a new skbedit action, the kernel results in the following oops: [ 8.307732] BUG: unable to handle kernel paging request at 0000000000021130 [ 8.309167] PGD 80000000193d1067 P4D 80000000193d1067 PUD 180e0067 PMD 0 [ 8.310595] Oops: 0000 [#1] SMP PTI [ 8.311334] Modules linked in: kvm_intel kvm irqbypass crct10dif_pclmul crc32_pclmul ghash_clmulni_intel pcbc aesni_intel aes_x86_64 crypto_simd cryptd glue_helper serio_raw [ 8.314190] CPU: 1 PID: 397 Comm: tc Not tainted 4.17.0-rc3+ #357 [ 8.315252] RIP: 0010:__tcf_idr_release+0x33/0x140 [ 8.316203] RSP: 0018:ffffa0718038f840 EFLAGS: 00010246 [ 8.317123] RAX: 0000000000000001 RBX: 0000000000021100 RCX: 0000000000000000 [ 8.319831] RDX: 0000000000000000 RSI: 0000000000000000 RDI: 0000000000021100 [ 8.321181] RBP: 0000000000000000 R08: 000000000004adf8 R09: 0000000000000122 [ 8.322645] R10: 0000000000000000 R11: ffffffff9e5b01ed R12: 0000000000000000 [ 8.324157] R13: ffffffff9e0d3cc0 R14: 0000000000000000 R15: 0000000000000000 [ 8.325590] FS: 00007f591292e700(0000) GS:ffff8fcf5bc40000(0000) knlGS:0000000000000000 [ 8.327001] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 8.327987] CR2: 0000000000021130 CR3: 00000000180e6004 CR4: 00000000001606a0 [ 8.329289] Call Trace: [ 8.329735] tcf_skbedit_init+0xa7/0xb0 [ 8.330423] tcf_action_init_1+0x362/0x410 [ 8.331139] ? try_to_wake_up+0x44/0x430 [ 8.331817] tcf_action_init+0x103/0x190 [ 8.332511] tc_ctl_action+0x11a/0x220 [ 8.333174] rtnetlink_rcv_msg+0x23d/0x2e0 [ 8.333902] ? _cond_resched+0x16/0x40 [ 8.334569] ? __kmalloc_node_track_caller+0x5b/0x2c0 [ 8.335440] ? rtnl_calcit.isra.31+0xf0/0xf0 [ 8.336178] netlink_rcv_skb+0xdb/0x110 [ 8.336855] netlink_unicast+0x167/0x220 [ 8.337550] netlink_sendmsg+0x2a7/0x390 [ 8.338258] sock_sendmsg+0x30/0x40 [ 8.338865] ___sys_sendmsg+0x2c5/0x2e0 [ 8.339531] ? pagecache_get_page+0x27/0x210 [ 8.340271] ? filemap_fault+0xa2/0x630 [ 8.340943] ? page_add_file_rmap+0x108/0x200 [ 8.341732] ? alloc_set_pte+0x2aa/0x530 [ 8.342573] ? finish_fault+0x4e/0x70 [ 8.343332] ? __handle_mm_fault+0xbc1/0x10d0 [ 8.344337] ? __sys_sendmsg+0x53/0x80 [ 8.345040] __sys_sendmsg+0x53/0x80 [ 8.345678] do_syscall_64+0x4f/0x100 [ 8.346339] entry_SYSCALL_64_after_hwframe+0x44/0xa9 [ 8.347206] RIP: 0033:0x7f591191da67 [ 8.347831] RSP: 002b:00007fff745abd48 EFLAGS: 00000246 ORIG_RAX: 000000000000002e [ 8.349179] RAX: ffffffffffffffda RBX: 00007fff745abe70 RCX: 00007f591191da67 [ 8.350431] RDX: 0000000000000000 RSI: 00007fff745abdc0 RDI: 0000000000000003 [ 8.351659] RBP: 000000005af35251 R08: 0000000000000001 R09: 0000000000000000 [ 8.352922] R10: 00000000000005f1 R11: 0000000000000246 R12: 0000000000000000 [ 8.354183] R13: 00007fff745afed0 R14: 0000000000000001 R15: 00000000006767c0 [ 8.355400] Code: 41 89 d4 53 89 f5 48 89 fb e8 aa 20 fd ff 85 c0 0f 84 ed 00 00 00 48 85 db 0f 84 cf 00 00 00 40 84 ed 0f 85 cd 00 00 00 45 84 e4 <8b> 53 30 74 0d 85 d2 b8 ff ff ff ff 0f 8f b3 00 00 00 8b 43 2c [ 8.358699] RIP: __tcf_idr_release+0x33/0x140 RSP: ffffa0718038f840 [ 8.359770] CR2: 0000000000021130 [ 8.360438] ---[ end trace 60c66be45dfc14f0 ]--- The caller calls action's ->init() and passes pointer to "struct tc_action *a", which later may be initialized to point at the existing action, otherwise "struct tc_action *a" is still invalid, and therefore dereferencing it is an error as happens in tcf_idr_release, where refcnt is decremented. So in case of missing flags tcf_idr_release must be called only for existing actions. v2: - prepare patch for net tree Fixes: 5e1567aeb7fe ("net sched: skbedit action fix late binding") Signed-off-by: Roman Mashak <mrv@mojatatu.com> Acked-by: Cong Wang <xiyou.wangcong@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-05-11 21:55:09 +07:00
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_skbedit_ops, bind, true);
if (ret) {
tcf_idr_cleanup(tn, parm->index);
return ret;
}
d = to_skbedit(*a);
ret = ACT_P_CREATED;
} else {
d = to_skbedit(*a);
if (!ovr) {
tcf_idr_release(*a, bind);
return -EEXIST;
}
}
ASSERT_RTNL();
params_new = kzalloc(sizeof(*params_new), GFP_KERNEL);
if (unlikely(!params_new)) {
if (ret == ACT_P_CREATED)
tcf_idr_release(*a, bind);
return -ENOMEM;
}
params_new->flags = flags;
if (flags & SKBEDIT_F_PRIORITY)
params_new->priority = *priority;
if (flags & SKBEDIT_F_QUEUE_MAPPING)
params_new->queue_mapping = *queue_mapping;
if (flags & SKBEDIT_F_MARK)
params_new->mark = *mark;
if (flags & SKBEDIT_F_PTYPE)
params_new->ptype = *ptype;
/* default behaviour is to use all the bits */
params_new->mask = 0xffffffff;
if (flags & SKBEDIT_F_MASK)
params_new->mask = *mask;
d->tcf_action = parm->action;
params_old = rtnl_dereference(d->params);
rcu_assign_pointer(d->params, params_new);
if (params_old)
kfree_rcu(params_old, rcu);
if (ret == ACT_P_CREATED)
tcf_idr_insert(tn, *a);
return ret;
}
static int tcf_skbedit_dump(struct sk_buff *skb, struct tc_action *a,
int bind, int ref)
{
unsigned char *b = skb_tail_pointer(skb);
struct tcf_skbedit *d = to_skbedit(a);
struct tcf_skbedit_params *params;
struct tc_skbedit opt = {
.index = d->tcf_index,
.refcnt = refcount_read(&d->tcf_refcnt) - ref,
.bindcnt = atomic_read(&d->tcf_bindcnt) - bind,
.action = d->tcf_action,
};
u64 pure_flags = 0;
struct tcf_t t;
params = rtnl_dereference(d->params);
if (nla_put(skb, TCA_SKBEDIT_PARMS, sizeof(opt), &opt))
goto nla_put_failure;
if ((params->flags & SKBEDIT_F_PRIORITY) &&
nla_put_u32(skb, TCA_SKBEDIT_PRIORITY, params->priority))
goto nla_put_failure;
if ((params->flags & SKBEDIT_F_QUEUE_MAPPING) &&
nla_put_u16(skb, TCA_SKBEDIT_QUEUE_MAPPING, params->queue_mapping))
goto nla_put_failure;
if ((params->flags & SKBEDIT_F_MARK) &&
nla_put_u32(skb, TCA_SKBEDIT_MARK, params->mark))
goto nla_put_failure;
if ((params->flags & SKBEDIT_F_PTYPE) &&
nla_put_u16(skb, TCA_SKBEDIT_PTYPE, params->ptype))
goto nla_put_failure;
if ((params->flags & SKBEDIT_F_MASK) &&
nla_put_u32(skb, TCA_SKBEDIT_MASK, params->mask))
goto nla_put_failure;
if (params->flags & SKBEDIT_F_INHERITDSFIELD)
pure_flags |= SKBEDIT_F_INHERITDSFIELD;
if (pure_flags != 0 &&
nla_put(skb, TCA_SKBEDIT_FLAGS, sizeof(pure_flags), &pure_flags))
goto nla_put_failure;
tcf_tm_dump(&t, &d->tcf_tm);
if (nla_put_64bit(skb, TCA_SKBEDIT_TM, sizeof(t), &t, TCA_SKBEDIT_PAD))
goto nla_put_failure;
return skb->len;
nla_put_failure:
nlmsg_trim(skb, b);
return -1;
}
static void tcf_skbedit_cleanup(struct tc_action *a)
{
struct tcf_skbedit *d = to_skbedit(a);
struct tcf_skbedit_params *params;
params = rcu_dereference_protected(d->params, 1);
if (params)
kfree_rcu(params, rcu);
}
static int tcf_skbedit_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, skbedit_net_id);
return tcf_generic_walker(tn, skb, cb, type, ops, extack);
}
static int tcf_skbedit_search(struct net *net, struct tc_action **a, u32 index,
struct netlink_ext_ack *extack)
{
struct tc_action_net *tn = net_generic(net, skbedit_net_id);
return tcf_idr_search(tn, a, index);
}
static int tcf_skbedit_delete(struct net *net, u32 index)
{
struct tc_action_net *tn = net_generic(net, skbedit_net_id);
return tcf_idr_delete_index(tn, index);
}
static struct tc_action_ops act_skbedit_ops = {
.kind = "skbedit",
.type = TCA_ACT_SKBEDIT,
.owner = THIS_MODULE,
.act = tcf_skbedit_act,
.dump = tcf_skbedit_dump,
.init = tcf_skbedit_init,
.cleanup = tcf_skbedit_cleanup,
.walk = tcf_skbedit_walker,
.lookup = tcf_skbedit_search,
.delete = tcf_skbedit_delete,
.size = sizeof(struct tcf_skbedit),
};
static __net_init int skbedit_init_net(struct net *net)
{
struct tc_action_net *tn = net_generic(net, skbedit_net_id);
return tc_action_net_init(tn, &act_skbedit_ops);
}
static void __net_exit skbedit_exit_net(struct list_head *net_list)
{
tc_action_net_exit(net_list, skbedit_net_id);
}
static struct pernet_operations skbedit_net_ops = {
.init = skbedit_init_net,
.exit_batch = skbedit_exit_net,
.id = &skbedit_net_id,
.size = sizeof(struct tc_action_net),
};
MODULE_AUTHOR("Alexander Duyck, <alexander.h.duyck@intel.com>");
MODULE_DESCRIPTION("SKB Editing");
MODULE_LICENSE("GPL");
static int __init skbedit_init_module(void)
{
return tcf_register_action(&act_skbedit_ops, &skbedit_net_ops);
}
static void __exit skbedit_cleanup_module(void)
{
tcf_unregister_action(&act_skbedit_ops, &skbedit_net_ops);
}
module_init(skbedit_init_module);
module_exit(skbedit_cleanup_module);