mirror of
https://mirrors.bfsu.edu.cn/git/linux.git
synced 2024-11-16 08:44:21 +08:00
0a889b9404
a recursive lock warning [1] can be observed with the following script, # $TC actions add action ife encode allow prio pass index 42 IFE type 0xED3E # $TC actions replace action ife encode allow tcindex pass index 42 in case the kernel was unable to run the last command (e.g. because of the impossibility to load 'act_meta_skbtcindex'). For a similar reason, the kernel can leak idr in the error path of tcf_ife_init(), because tcf_idr_release() is not called after successful idr reservation: # $TC actions add action ife encode allow tcindex index 47 IFE type 0xED3E RTNETLINK answers: No such file or directory We have an error talking to the kernel # $TC actions add action ife encode allow tcindex index 47 IFE type 0xED3E RTNETLINK answers: No space left on device We have an error talking to the kernel # $TC actions add action ife encode use mark 7 type 0xfefe pass index 47 IFE type 0xFEFE RTNETLINK answers: No space left on device We have an error talking to the kernel Since tcfa_lock is already taken when the action is being edited, a call to tcf_idr_release() wrongly makes tcf_idr_cleanup() take the same lock again. On the other hand, tcf_idr_release() needs to be called in the error path of tcf_ife_init(), to undo the last tcf_idr_create() invocation. Fix both problems in tcf_ife_init(). Since the cleanup() routine can now be called when ife->params is NULL, also add a NULL pointer check to avoid calling kfree_rcu(NULL, rcu). [1] ============================================ WARNING: possible recursive locking detected 4.17.0-rc4.kasan+ #417 Tainted: G E -------------------------------------------- tc/3932 is trying to acquire lock: 000000005097c9a6 (&(&p->tcfa_lock)->rlock){+...}, at: tcf_ife_cleanup+0x19/0x80 [act_ife] but task is already holding lock: 000000005097c9a6 (&(&p->tcfa_lock)->rlock){+...}, at: tcf_ife_init+0xf6d/0x13c0 [act_ife] other info that might help us debug this: Possible unsafe locking scenario: CPU0 ---- lock(&(&p->tcfa_lock)->rlock); lock(&(&p->tcfa_lock)->rlock); *** DEADLOCK *** May be due to missing lock nesting notation 2 locks held by tc/3932: #0: 000000007ca8e990 (rtnl_mutex){+.+.}, at: tcf_ife_init+0xf61/0x13c0 [act_ife] #1: 000000005097c9a6 (&(&p->tcfa_lock)->rlock){+...}, at: tcf_ife_init+0xf6d/0x13c0 [act_ife] stack backtrace: CPU: 3 PID: 3932 Comm: tc Tainted: G E 4.17.0-rc4.kasan+ #417 Hardware name: Red Hat KVM, BIOS 0.5.1 01/01/2011 Call Trace: dump_stack+0x9a/0xeb __lock_acquire+0xf43/0x34a0 ? debug_check_no_locks_freed+0x2b0/0x2b0 ? debug_check_no_locks_freed+0x2b0/0x2b0 ? debug_check_no_locks_freed+0x2b0/0x2b0 ? __mutex_lock+0x62f/0x1240 ? kvm_sched_clock_read+0x1a/0x30 ? sched_clock+0x5/0x10 ? sched_clock_cpu+0x18/0x170 ? find_held_lock+0x39/0x1d0 ? lock_acquire+0x10b/0x330 lock_acquire+0x10b/0x330 ? tcf_ife_cleanup+0x19/0x80 [act_ife] _raw_spin_lock_bh+0x38/0x70 ? tcf_ife_cleanup+0x19/0x80 [act_ife] tcf_ife_cleanup+0x19/0x80 [act_ife] __tcf_idr_release+0xff/0x350 tcf_ife_init+0xdde/0x13c0 [act_ife] ? ife_exit_net+0x290/0x290 [act_ife] ? __lock_is_held+0xb4/0x140 tcf_action_init_1+0x67b/0xad0 ? tcf_action_dump_old+0xa0/0xa0 ? sched_clock+0x5/0x10 ? sched_clock_cpu+0x18/0x170 ? kvm_sched_clock_read+0x1a/0x30 ? sched_clock+0x5/0x10 ? sched_clock_cpu+0x18/0x170 ? memset+0x1f/0x40 tcf_action_init+0x30f/0x590 ? tcf_action_init_1+0xad0/0xad0 ? memset+0x1f/0x40 tc_ctl_action+0x48e/0x5e0 ? mutex_lock_io_nested+0x1160/0x1160 ? tca_action_gd+0x990/0x990 ? sched_clock+0x5/0x10 ? find_held_lock+0x39/0x1d0 rtnetlink_rcv_msg+0x4da/0x990 ? validate_linkmsg+0x680/0x680 ? sched_clock_cpu+0x18/0x170 ? find_held_lock+0x39/0x1d0 netlink_rcv_skb+0x127/0x350 ? validate_linkmsg+0x680/0x680 ? netlink_ack+0x970/0x970 ? __kmalloc_node_track_caller+0x304/0x3a0 netlink_unicast+0x40f/0x5d0 ? netlink_attachskb+0x580/0x580 ? _copy_from_iter_full+0x187/0x760 ? import_iovec+0x90/0x390 netlink_sendmsg+0x67f/0xb50 ? netlink_unicast+0x5d0/0x5d0 ? copy_msghdr_from_user+0x206/0x340 ? netlink_unicast+0x5d0/0x5d0 sock_sendmsg+0xb3/0xf0 ___sys_sendmsg+0x60a/0x8b0 ? copy_msghdr_from_user+0x340/0x340 ? lock_downgrade+0x5e0/0x5e0 ? tty_write_lock+0x18/0x50 ? kvm_sched_clock_read+0x1a/0x30 ? sched_clock+0x5/0x10 ? sched_clock_cpu+0x18/0x170 ? find_held_lock+0x39/0x1d0 ? lock_downgrade+0x5e0/0x5e0 ? lock_acquire+0x10b/0x330 ? __audit_syscall_entry+0x316/0x690 ? current_kernel_time64+0x6b/0xd0 ? __fget_light+0x55/0x1f0 ? __sys_sendmsg+0xd2/0x170 __sys_sendmsg+0xd2/0x170 ? __ia32_sys_shutdown+0x70/0x70 ? syscall_trace_enter+0x57a/0xd60 ? rcu_read_lock_sched_held+0xdc/0x110 ? __bpf_trace_sys_enter+0x10/0x10 ? do_syscall_64+0x22/0x480 do_syscall_64+0xa5/0x480 entry_SYSCALL_64_after_hwframe+0x49/0xbe RIP: 0033:0x7fd646988ba0 RSP: 002b:00007fffc9fab3c8 EFLAGS: 00000246 ORIG_RAX: 000000000000002e RAX: ffffffffffffffda RBX: 00007fffc9fab4f0 RCX: 00007fd646988ba0 RDX: 0000000000000000 RSI: 00007fffc9fab440 RDI: 0000000000000003 RBP: 000000005b28c8b3 R08: 0000000000000002 R09: 0000000000000000 R10: 00007fffc9faae20 R11: 0000000000000246 R12: 0000000000000000 R13: 00007fffc9fab504 R14: 0000000000000001 R15: 000000000066c100 Fixes:4e8c861550
("net sched: net sched: ife action fix late binding") Fixes:ef6980b6be
("introduce IFE action") Signed-off-by: Davide Caratti <dcaratti@redhat.com> Acked-by: Cong Wang <xiyou.wangcong@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
895 lines
20 KiB
C
895 lines
20 KiB
C
/*
|
|
* net/sched/ife.c Inter-FE action based on ForCES WG InterFE LFB
|
|
*
|
|
* Refer to:
|
|
* draft-ietf-forces-interfelfb-03
|
|
* and
|
|
* netdev01 paper:
|
|
* "Distributing Linux Traffic Control Classifier-Action
|
|
* Subsystem"
|
|
* Authors: Jamal Hadi Salim and Damascene M. Joachimpillai
|
|
*
|
|
* 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.
|
|
*
|
|
* copyright Jamal Hadi Salim (2015)
|
|
*
|
|
*/
|
|
|
|
#include <linux/types.h>
|
|
#include <linux/kernel.h>
|
|
#include <linux/string.h>
|
|
#include <linux/errno.h>
|
|
#include <linux/skbuff.h>
|
|
#include <linux/rtnetlink.h>
|
|
#include <linux/module.h>
|
|
#include <linux/init.h>
|
|
#include <net/net_namespace.h>
|
|
#include <net/netlink.h>
|
|
#include <net/pkt_sched.h>
|
|
#include <uapi/linux/tc_act/tc_ife.h>
|
|
#include <net/tc_act/tc_ife.h>
|
|
#include <linux/etherdevice.h>
|
|
#include <net/ife.h>
|
|
|
|
static unsigned int ife_net_id;
|
|
static int max_metacnt = IFE_META_MAX + 1;
|
|
static struct tc_action_ops act_ife_ops;
|
|
|
|
static const struct nla_policy ife_policy[TCA_IFE_MAX + 1] = {
|
|
[TCA_IFE_PARMS] = { .len = sizeof(struct tc_ife)},
|
|
[TCA_IFE_DMAC] = { .len = ETH_ALEN},
|
|
[TCA_IFE_SMAC] = { .len = ETH_ALEN},
|
|
[TCA_IFE_TYPE] = { .type = NLA_U16},
|
|
};
|
|
|
|
int ife_encode_meta_u16(u16 metaval, void *skbdata, struct tcf_meta_info *mi)
|
|
{
|
|
u16 edata = 0;
|
|
|
|
if (mi->metaval)
|
|
edata = *(u16 *)mi->metaval;
|
|
else if (metaval)
|
|
edata = metaval;
|
|
|
|
if (!edata) /* will not encode */
|
|
return 0;
|
|
|
|
edata = htons(edata);
|
|
return ife_tlv_meta_encode(skbdata, mi->metaid, 2, &edata);
|
|
}
|
|
EXPORT_SYMBOL_GPL(ife_encode_meta_u16);
|
|
|
|
int ife_get_meta_u32(struct sk_buff *skb, struct tcf_meta_info *mi)
|
|
{
|
|
if (mi->metaval)
|
|
return nla_put_u32(skb, mi->metaid, *(u32 *)mi->metaval);
|
|
else
|
|
return nla_put(skb, mi->metaid, 0, NULL);
|
|
}
|
|
EXPORT_SYMBOL_GPL(ife_get_meta_u32);
|
|
|
|
int ife_check_meta_u32(u32 metaval, struct tcf_meta_info *mi)
|
|
{
|
|
if (metaval || mi->metaval)
|
|
return 8; /* T+L+V == 2+2+4 */
|
|
|
|
return 0;
|
|
}
|
|
EXPORT_SYMBOL_GPL(ife_check_meta_u32);
|
|
|
|
int ife_check_meta_u16(u16 metaval, struct tcf_meta_info *mi)
|
|
{
|
|
if (metaval || mi->metaval)
|
|
return 8; /* T+L+(V) == 2+2+(2+2bytepad) */
|
|
|
|
return 0;
|
|
}
|
|
EXPORT_SYMBOL_GPL(ife_check_meta_u16);
|
|
|
|
int ife_encode_meta_u32(u32 metaval, void *skbdata, struct tcf_meta_info *mi)
|
|
{
|
|
u32 edata = metaval;
|
|
|
|
if (mi->metaval)
|
|
edata = *(u32 *)mi->metaval;
|
|
else if (metaval)
|
|
edata = metaval;
|
|
|
|
if (!edata) /* will not encode */
|
|
return 0;
|
|
|
|
edata = htonl(edata);
|
|
return ife_tlv_meta_encode(skbdata, mi->metaid, 4, &edata);
|
|
}
|
|
EXPORT_SYMBOL_GPL(ife_encode_meta_u32);
|
|
|
|
int ife_get_meta_u16(struct sk_buff *skb, struct tcf_meta_info *mi)
|
|
{
|
|
if (mi->metaval)
|
|
return nla_put_u16(skb, mi->metaid, *(u16 *)mi->metaval);
|
|
else
|
|
return nla_put(skb, mi->metaid, 0, NULL);
|
|
}
|
|
EXPORT_SYMBOL_GPL(ife_get_meta_u16);
|
|
|
|
int ife_alloc_meta_u32(struct tcf_meta_info *mi, void *metaval, gfp_t gfp)
|
|
{
|
|
mi->metaval = kmemdup(metaval, sizeof(u32), gfp);
|
|
if (!mi->metaval)
|
|
return -ENOMEM;
|
|
|
|
return 0;
|
|
}
|
|
EXPORT_SYMBOL_GPL(ife_alloc_meta_u32);
|
|
|
|
int ife_alloc_meta_u16(struct tcf_meta_info *mi, void *metaval, gfp_t gfp)
|
|
{
|
|
mi->metaval = kmemdup(metaval, sizeof(u16), gfp);
|
|
if (!mi->metaval)
|
|
return -ENOMEM;
|
|
|
|
return 0;
|
|
}
|
|
EXPORT_SYMBOL_GPL(ife_alloc_meta_u16);
|
|
|
|
void ife_release_meta_gen(struct tcf_meta_info *mi)
|
|
{
|
|
kfree(mi->metaval);
|
|
}
|
|
EXPORT_SYMBOL_GPL(ife_release_meta_gen);
|
|
|
|
int ife_validate_meta_u32(void *val, int len)
|
|
{
|
|
if (len == sizeof(u32))
|
|
return 0;
|
|
|
|
return -EINVAL;
|
|
}
|
|
EXPORT_SYMBOL_GPL(ife_validate_meta_u32);
|
|
|
|
int ife_validate_meta_u16(void *val, int len)
|
|
{
|
|
/* length will not include padding */
|
|
if (len == sizeof(u16))
|
|
return 0;
|
|
|
|
return -EINVAL;
|
|
}
|
|
EXPORT_SYMBOL_GPL(ife_validate_meta_u16);
|
|
|
|
static LIST_HEAD(ifeoplist);
|
|
static DEFINE_RWLOCK(ife_mod_lock);
|
|
|
|
static struct tcf_meta_ops *find_ife_oplist(u16 metaid)
|
|
{
|
|
struct tcf_meta_ops *o;
|
|
|
|
read_lock(&ife_mod_lock);
|
|
list_for_each_entry(o, &ifeoplist, list) {
|
|
if (o->metaid == metaid) {
|
|
if (!try_module_get(o->owner))
|
|
o = NULL;
|
|
read_unlock(&ife_mod_lock);
|
|
return o;
|
|
}
|
|
}
|
|
read_unlock(&ife_mod_lock);
|
|
|
|
return NULL;
|
|
}
|
|
|
|
int register_ife_op(struct tcf_meta_ops *mops)
|
|
{
|
|
struct tcf_meta_ops *m;
|
|
|
|
if (!mops->metaid || !mops->metatype || !mops->name ||
|
|
!mops->check_presence || !mops->encode || !mops->decode ||
|
|
!mops->get || !mops->alloc)
|
|
return -EINVAL;
|
|
|
|
write_lock(&ife_mod_lock);
|
|
|
|
list_for_each_entry(m, &ifeoplist, list) {
|
|
if (m->metaid == mops->metaid ||
|
|
(strcmp(mops->name, m->name) == 0)) {
|
|
write_unlock(&ife_mod_lock);
|
|
return -EEXIST;
|
|
}
|
|
}
|
|
|
|
if (!mops->release)
|
|
mops->release = ife_release_meta_gen;
|
|
|
|
list_add_tail(&mops->list, &ifeoplist);
|
|
write_unlock(&ife_mod_lock);
|
|
return 0;
|
|
}
|
|
EXPORT_SYMBOL_GPL(unregister_ife_op);
|
|
|
|
int unregister_ife_op(struct tcf_meta_ops *mops)
|
|
{
|
|
struct tcf_meta_ops *m;
|
|
int err = -ENOENT;
|
|
|
|
write_lock(&ife_mod_lock);
|
|
list_for_each_entry(m, &ifeoplist, list) {
|
|
if (m->metaid == mops->metaid) {
|
|
list_del(&mops->list);
|
|
err = 0;
|
|
break;
|
|
}
|
|
}
|
|
write_unlock(&ife_mod_lock);
|
|
|
|
return err;
|
|
}
|
|
EXPORT_SYMBOL_GPL(register_ife_op);
|
|
|
|
static int ife_validate_metatype(struct tcf_meta_ops *ops, void *val, int len)
|
|
{
|
|
int ret = 0;
|
|
/* XXX: unfortunately cant use nla_policy at this point
|
|
* because a length of 0 is valid in the case of
|
|
* "allow". "use" semantics do enforce for proper
|
|
* length and i couldve use nla_policy but it makes it hard
|
|
* to use it just for that..
|
|
*/
|
|
if (ops->validate)
|
|
return ops->validate(val, len);
|
|
|
|
if (ops->metatype == NLA_U32)
|
|
ret = ife_validate_meta_u32(val, len);
|
|
else if (ops->metatype == NLA_U16)
|
|
ret = ife_validate_meta_u16(val, len);
|
|
|
|
return ret;
|
|
}
|
|
|
|
#ifdef CONFIG_MODULES
|
|
static const char *ife_meta_id2name(u32 metaid)
|
|
{
|
|
switch (metaid) {
|
|
case IFE_META_SKBMARK:
|
|
return "skbmark";
|
|
case IFE_META_PRIO:
|
|
return "skbprio";
|
|
case IFE_META_TCINDEX:
|
|
return "tcindex";
|
|
default:
|
|
return "unknown";
|
|
}
|
|
}
|
|
#endif
|
|
|
|
/* called when adding new meta information
|
|
* under ife->tcf_lock for existing action
|
|
*/
|
|
static int load_metaops_and_vet(struct tcf_ife_info *ife, u32 metaid,
|
|
void *val, int len, bool exists)
|
|
{
|
|
struct tcf_meta_ops *ops = find_ife_oplist(metaid);
|
|
int ret = 0;
|
|
|
|
if (!ops) {
|
|
ret = -ENOENT;
|
|
#ifdef CONFIG_MODULES
|
|
if (exists)
|
|
spin_unlock_bh(&ife->tcf_lock);
|
|
rtnl_unlock();
|
|
request_module("ife-meta-%s", ife_meta_id2name(metaid));
|
|
rtnl_lock();
|
|
if (exists)
|
|
spin_lock_bh(&ife->tcf_lock);
|
|
ops = find_ife_oplist(metaid);
|
|
#endif
|
|
}
|
|
|
|
if (ops) {
|
|
ret = 0;
|
|
if (len)
|
|
ret = ife_validate_metatype(ops, val, len);
|
|
|
|
module_put(ops->owner);
|
|
}
|
|
|
|
return ret;
|
|
}
|
|
|
|
/* called when adding new meta information
|
|
* under ife->tcf_lock for existing action
|
|
*/
|
|
static int add_metainfo(struct tcf_ife_info *ife, u32 metaid, void *metaval,
|
|
int len, bool atomic)
|
|
{
|
|
struct tcf_meta_info *mi = NULL;
|
|
struct tcf_meta_ops *ops = find_ife_oplist(metaid);
|
|
int ret = 0;
|
|
|
|
if (!ops)
|
|
return -ENOENT;
|
|
|
|
mi = kzalloc(sizeof(*mi), atomic ? GFP_ATOMIC : GFP_KERNEL);
|
|
if (!mi) {
|
|
/*put back what find_ife_oplist took */
|
|
module_put(ops->owner);
|
|
return -ENOMEM;
|
|
}
|
|
|
|
mi->metaid = metaid;
|
|
mi->ops = ops;
|
|
if (len > 0) {
|
|
ret = ops->alloc(mi, metaval, atomic ? GFP_ATOMIC : GFP_KERNEL);
|
|
if (ret != 0) {
|
|
kfree(mi);
|
|
module_put(ops->owner);
|
|
return ret;
|
|
}
|
|
}
|
|
|
|
list_add_tail(&mi->metalist, &ife->metalist);
|
|
|
|
return ret;
|
|
}
|
|
|
|
static int use_all_metadata(struct tcf_ife_info *ife)
|
|
{
|
|
struct tcf_meta_ops *o;
|
|
int rc = 0;
|
|
int installed = 0;
|
|
|
|
read_lock(&ife_mod_lock);
|
|
list_for_each_entry(o, &ifeoplist, list) {
|
|
rc = add_metainfo(ife, o->metaid, NULL, 0, true);
|
|
if (rc == 0)
|
|
installed += 1;
|
|
}
|
|
read_unlock(&ife_mod_lock);
|
|
|
|
if (installed)
|
|
return 0;
|
|
else
|
|
return -EINVAL;
|
|
}
|
|
|
|
static int dump_metalist(struct sk_buff *skb, struct tcf_ife_info *ife)
|
|
{
|
|
struct tcf_meta_info *e;
|
|
struct nlattr *nest;
|
|
unsigned char *b = skb_tail_pointer(skb);
|
|
int total_encoded = 0;
|
|
|
|
/*can only happen on decode */
|
|
if (list_empty(&ife->metalist))
|
|
return 0;
|
|
|
|
nest = nla_nest_start(skb, TCA_IFE_METALST);
|
|
if (!nest)
|
|
goto out_nlmsg_trim;
|
|
|
|
list_for_each_entry(e, &ife->metalist, metalist) {
|
|
if (!e->ops->get(skb, e))
|
|
total_encoded += 1;
|
|
}
|
|
|
|
if (!total_encoded)
|
|
goto out_nlmsg_trim;
|
|
|
|
nla_nest_end(skb, nest);
|
|
|
|
return 0;
|
|
|
|
out_nlmsg_trim:
|
|
nlmsg_trim(skb, b);
|
|
return -1;
|
|
}
|
|
|
|
/* under ife->tcf_lock */
|
|
static void _tcf_ife_cleanup(struct tc_action *a)
|
|
{
|
|
struct tcf_ife_info *ife = to_ife(a);
|
|
struct tcf_meta_info *e, *n;
|
|
|
|
list_for_each_entry_safe(e, n, &ife->metalist, metalist) {
|
|
module_put(e->ops->owner);
|
|
list_del(&e->metalist);
|
|
if (e->metaval) {
|
|
if (e->ops->release)
|
|
e->ops->release(e);
|
|
else
|
|
kfree(e->metaval);
|
|
}
|
|
kfree(e);
|
|
}
|
|
}
|
|
|
|
static void tcf_ife_cleanup(struct tc_action *a)
|
|
{
|
|
struct tcf_ife_info *ife = to_ife(a);
|
|
struct tcf_ife_params *p;
|
|
|
|
spin_lock_bh(&ife->tcf_lock);
|
|
_tcf_ife_cleanup(a);
|
|
spin_unlock_bh(&ife->tcf_lock);
|
|
|
|
p = rcu_dereference_protected(ife->params, 1);
|
|
if (p)
|
|
kfree_rcu(p, rcu);
|
|
}
|
|
|
|
/* under ife->tcf_lock for existing action */
|
|
static int populate_metalist(struct tcf_ife_info *ife, struct nlattr **tb,
|
|
bool exists)
|
|
{
|
|
int len = 0;
|
|
int rc = 0;
|
|
int i = 0;
|
|
void *val;
|
|
|
|
for (i = 1; i < max_metacnt; i++) {
|
|
if (tb[i]) {
|
|
val = nla_data(tb[i]);
|
|
len = nla_len(tb[i]);
|
|
|
|
rc = load_metaops_and_vet(ife, i, val, len, exists);
|
|
if (rc != 0)
|
|
return rc;
|
|
|
|
rc = add_metainfo(ife, i, val, len, exists);
|
|
if (rc)
|
|
return rc;
|
|
}
|
|
}
|
|
|
|
return rc;
|
|
}
|
|
|
|
static int tcf_ife_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, ife_net_id);
|
|
struct nlattr *tb[TCA_IFE_MAX + 1];
|
|
struct nlattr *tb2[IFE_META_MAX + 1];
|
|
struct tcf_ife_params *p, *p_old;
|
|
struct tcf_ife_info *ife;
|
|
u16 ife_type = ETH_P_IFE;
|
|
struct tc_ife *parm;
|
|
u8 *daddr = NULL;
|
|
u8 *saddr = NULL;
|
|
bool exists = false;
|
|
int ret = 0;
|
|
int err;
|
|
|
|
err = nla_parse_nested(tb, TCA_IFE_MAX, nla, ife_policy, NULL);
|
|
if (err < 0)
|
|
return err;
|
|
|
|
if (!tb[TCA_IFE_PARMS])
|
|
return -EINVAL;
|
|
|
|
parm = nla_data(tb[TCA_IFE_PARMS]);
|
|
|
|
/* IFE_DECODE is 0 and indicates the opposite of IFE_ENCODE because
|
|
* they cannot run as the same time. Check on all other values which
|
|
* are not supported right now.
|
|
*/
|
|
if (parm->flags & ~IFE_ENCODE)
|
|
return -EINVAL;
|
|
|
|
p = kzalloc(sizeof(*p), GFP_KERNEL);
|
|
if (!p)
|
|
return -ENOMEM;
|
|
|
|
exists = tcf_idr_check(tn, parm->index, a, bind);
|
|
if (exists && bind) {
|
|
kfree(p);
|
|
return 0;
|
|
}
|
|
|
|
if (!exists) {
|
|
ret = tcf_idr_create(tn, parm->index, est, a, &act_ife_ops,
|
|
bind, true);
|
|
if (ret) {
|
|
kfree(p);
|
|
return ret;
|
|
}
|
|
ret = ACT_P_CREATED;
|
|
} else {
|
|
tcf_idr_release(*a, bind);
|
|
if (!ovr) {
|
|
kfree(p);
|
|
return -EEXIST;
|
|
}
|
|
}
|
|
|
|
ife = to_ife(*a);
|
|
p->flags = parm->flags;
|
|
|
|
if (parm->flags & IFE_ENCODE) {
|
|
if (tb[TCA_IFE_TYPE])
|
|
ife_type = nla_get_u16(tb[TCA_IFE_TYPE]);
|
|
if (tb[TCA_IFE_DMAC])
|
|
daddr = nla_data(tb[TCA_IFE_DMAC]);
|
|
if (tb[TCA_IFE_SMAC])
|
|
saddr = nla_data(tb[TCA_IFE_SMAC]);
|
|
}
|
|
|
|
ife->tcf_action = parm->action;
|
|
|
|
if (parm->flags & IFE_ENCODE) {
|
|
if (daddr)
|
|
ether_addr_copy(p->eth_dst, daddr);
|
|
else
|
|
eth_zero_addr(p->eth_dst);
|
|
|
|
if (saddr)
|
|
ether_addr_copy(p->eth_src, saddr);
|
|
else
|
|
eth_zero_addr(p->eth_src);
|
|
|
|
p->eth_type = ife_type;
|
|
}
|
|
|
|
if (exists)
|
|
spin_lock_bh(&ife->tcf_lock);
|
|
|
|
if (ret == ACT_P_CREATED)
|
|
INIT_LIST_HEAD(&ife->metalist);
|
|
|
|
if (tb[TCA_IFE_METALST]) {
|
|
err = nla_parse_nested(tb2, IFE_META_MAX, tb[TCA_IFE_METALST],
|
|
NULL, NULL);
|
|
if (err) {
|
|
metadata_parse_err:
|
|
if (ret == ACT_P_CREATED)
|
|
tcf_idr_release(*a, bind);
|
|
|
|
if (exists)
|
|
spin_unlock_bh(&ife->tcf_lock);
|
|
kfree(p);
|
|
return err;
|
|
}
|
|
|
|
err = populate_metalist(ife, tb2, exists);
|
|
if (err)
|
|
goto metadata_parse_err;
|
|
|
|
} else {
|
|
/* if no passed metadata allow list or passed allow-all
|
|
* then here we process by adding as many supported metadatum
|
|
* as we can. You better have at least one else we are
|
|
* going to bail out
|
|
*/
|
|
err = use_all_metadata(ife);
|
|
if (err) {
|
|
if (ret == ACT_P_CREATED)
|
|
tcf_idr_release(*a, bind);
|
|
|
|
if (exists)
|
|
spin_unlock_bh(&ife->tcf_lock);
|
|
kfree(p);
|
|
return err;
|
|
}
|
|
}
|
|
|
|
if (exists)
|
|
spin_unlock_bh(&ife->tcf_lock);
|
|
|
|
p_old = rtnl_dereference(ife->params);
|
|
rcu_assign_pointer(ife->params, p);
|
|
if (p_old)
|
|
kfree_rcu(p_old, rcu);
|
|
|
|
if (ret == ACT_P_CREATED)
|
|
tcf_idr_insert(tn, *a);
|
|
|
|
return ret;
|
|
}
|
|
|
|
static int tcf_ife_dump(struct sk_buff *skb, struct tc_action *a, int bind,
|
|
int ref)
|
|
{
|
|
unsigned char *b = skb_tail_pointer(skb);
|
|
struct tcf_ife_info *ife = to_ife(a);
|
|
struct tcf_ife_params *p = rtnl_dereference(ife->params);
|
|
struct tc_ife opt = {
|
|
.index = ife->tcf_index,
|
|
.refcnt = ife->tcf_refcnt - ref,
|
|
.bindcnt = ife->tcf_bindcnt - bind,
|
|
.action = ife->tcf_action,
|
|
.flags = p->flags,
|
|
};
|
|
struct tcf_t t;
|
|
|
|
if (nla_put(skb, TCA_IFE_PARMS, sizeof(opt), &opt))
|
|
goto nla_put_failure;
|
|
|
|
tcf_tm_dump(&t, &ife->tcf_tm);
|
|
if (nla_put_64bit(skb, TCA_IFE_TM, sizeof(t), &t, TCA_IFE_PAD))
|
|
goto nla_put_failure;
|
|
|
|
if (!is_zero_ether_addr(p->eth_dst)) {
|
|
if (nla_put(skb, TCA_IFE_DMAC, ETH_ALEN, p->eth_dst))
|
|
goto nla_put_failure;
|
|
}
|
|
|
|
if (!is_zero_ether_addr(p->eth_src)) {
|
|
if (nla_put(skb, TCA_IFE_SMAC, ETH_ALEN, p->eth_src))
|
|
goto nla_put_failure;
|
|
}
|
|
|
|
if (nla_put(skb, TCA_IFE_TYPE, 2, &p->eth_type))
|
|
goto nla_put_failure;
|
|
|
|
if (dump_metalist(skb, ife)) {
|
|
/*ignore failure to dump metalist */
|
|
pr_info("Failed to dump metalist\n");
|
|
}
|
|
|
|
return skb->len;
|
|
|
|
nla_put_failure:
|
|
nlmsg_trim(skb, b);
|
|
return -1;
|
|
}
|
|
|
|
static int find_decode_metaid(struct sk_buff *skb, struct tcf_ife_info *ife,
|
|
u16 metaid, u16 mlen, void *mdata)
|
|
{
|
|
struct tcf_meta_info *e;
|
|
|
|
/* XXX: use hash to speed up */
|
|
list_for_each_entry(e, &ife->metalist, metalist) {
|
|
if (metaid == e->metaid) {
|
|
if (e->ops) {
|
|
/* We check for decode presence already */
|
|
return e->ops->decode(skb, mdata, mlen);
|
|
}
|
|
}
|
|
}
|
|
|
|
return -ENOENT;
|
|
}
|
|
|
|
static int tcf_ife_decode(struct sk_buff *skb, const struct tc_action *a,
|
|
struct tcf_result *res)
|
|
{
|
|
struct tcf_ife_info *ife = to_ife(a);
|
|
int action = ife->tcf_action;
|
|
u8 *ifehdr_end;
|
|
u8 *tlv_data;
|
|
u16 metalen;
|
|
|
|
bstats_cpu_update(this_cpu_ptr(ife->common.cpu_bstats), skb);
|
|
tcf_lastuse_update(&ife->tcf_tm);
|
|
|
|
if (skb_at_tc_ingress(skb))
|
|
skb_push(skb, skb->dev->hard_header_len);
|
|
|
|
tlv_data = ife_decode(skb, &metalen);
|
|
if (unlikely(!tlv_data)) {
|
|
qstats_drop_inc(this_cpu_ptr(ife->common.cpu_qstats));
|
|
return TC_ACT_SHOT;
|
|
}
|
|
|
|
ifehdr_end = tlv_data + metalen;
|
|
for (; tlv_data < ifehdr_end; tlv_data = ife_tlv_meta_next(tlv_data)) {
|
|
u8 *curr_data;
|
|
u16 mtype;
|
|
u16 dlen;
|
|
|
|
curr_data = ife_tlv_meta_decode(tlv_data, ifehdr_end, &mtype,
|
|
&dlen, NULL);
|
|
if (!curr_data) {
|
|
qstats_drop_inc(this_cpu_ptr(ife->common.cpu_qstats));
|
|
return TC_ACT_SHOT;
|
|
}
|
|
|
|
if (find_decode_metaid(skb, ife, mtype, dlen, curr_data)) {
|
|
/* abuse overlimits to count when we receive metadata
|
|
* but dont have an ops for it
|
|
*/
|
|
pr_info_ratelimited("Unknown metaid %d dlen %d\n",
|
|
mtype, dlen);
|
|
qstats_overlimit_inc(this_cpu_ptr(ife->common.cpu_qstats));
|
|
}
|
|
}
|
|
|
|
if (WARN_ON(tlv_data != ifehdr_end)) {
|
|
qstats_drop_inc(this_cpu_ptr(ife->common.cpu_qstats));
|
|
return TC_ACT_SHOT;
|
|
}
|
|
|
|
skb->protocol = eth_type_trans(skb, skb->dev);
|
|
skb_reset_network_header(skb);
|
|
|
|
return action;
|
|
}
|
|
|
|
/*XXX: check if we can do this at install time instead of current
|
|
* send data path
|
|
**/
|
|
static int ife_get_sz(struct sk_buff *skb, struct tcf_ife_info *ife)
|
|
{
|
|
struct tcf_meta_info *e, *n;
|
|
int tot_run_sz = 0, run_sz = 0;
|
|
|
|
list_for_each_entry_safe(e, n, &ife->metalist, metalist) {
|
|
if (e->ops->check_presence) {
|
|
run_sz = e->ops->check_presence(skb, e);
|
|
tot_run_sz += run_sz;
|
|
}
|
|
}
|
|
|
|
return tot_run_sz;
|
|
}
|
|
|
|
static int tcf_ife_encode(struct sk_buff *skb, const struct tc_action *a,
|
|
struct tcf_result *res, struct tcf_ife_params *p)
|
|
{
|
|
struct tcf_ife_info *ife = to_ife(a);
|
|
int action = ife->tcf_action;
|
|
struct ethhdr *oethh; /* outer ether header */
|
|
struct tcf_meta_info *e;
|
|
/*
|
|
OUTERHDR:TOTMETALEN:{TLVHDR:Metadatum:TLVHDR..}:ORIGDATA
|
|
where ORIGDATA = original ethernet header ...
|
|
*/
|
|
u16 metalen = ife_get_sz(skb, ife);
|
|
int hdrm = metalen + skb->dev->hard_header_len + IFE_METAHDRLEN;
|
|
unsigned int skboff = 0;
|
|
int new_len = skb->len + hdrm;
|
|
bool exceed_mtu = false;
|
|
void *ife_meta;
|
|
int err = 0;
|
|
|
|
if (!skb_at_tc_ingress(skb)) {
|
|
if (new_len > skb->dev->mtu)
|
|
exceed_mtu = true;
|
|
}
|
|
|
|
bstats_cpu_update(this_cpu_ptr(ife->common.cpu_bstats), skb);
|
|
tcf_lastuse_update(&ife->tcf_tm);
|
|
|
|
if (!metalen) { /* no metadata to send */
|
|
/* abuse overlimits to count when we allow packet
|
|
* with no metadata
|
|
*/
|
|
qstats_overlimit_inc(this_cpu_ptr(ife->common.cpu_qstats));
|
|
return action;
|
|
}
|
|
/* could be stupid policy setup or mtu config
|
|
* so lets be conservative.. */
|
|
if ((action == TC_ACT_SHOT) || exceed_mtu) {
|
|
qstats_drop_inc(this_cpu_ptr(ife->common.cpu_qstats));
|
|
return TC_ACT_SHOT;
|
|
}
|
|
|
|
if (skb_at_tc_ingress(skb))
|
|
skb_push(skb, skb->dev->hard_header_len);
|
|
|
|
ife_meta = ife_encode(skb, metalen);
|
|
|
|
spin_lock(&ife->tcf_lock);
|
|
|
|
/* XXX: we dont have a clever way of telling encode to
|
|
* not repeat some of the computations that are done by
|
|
* ops->presence_check...
|
|
*/
|
|
list_for_each_entry(e, &ife->metalist, metalist) {
|
|
if (e->ops->encode) {
|
|
err = e->ops->encode(skb, (void *)(ife_meta + skboff),
|
|
e);
|
|
}
|
|
if (err < 0) {
|
|
/* too corrupt to keep around if overwritten */
|
|
spin_unlock(&ife->tcf_lock);
|
|
qstats_drop_inc(this_cpu_ptr(ife->common.cpu_qstats));
|
|
return TC_ACT_SHOT;
|
|
}
|
|
skboff += err;
|
|
}
|
|
spin_unlock(&ife->tcf_lock);
|
|
oethh = (struct ethhdr *)skb->data;
|
|
|
|
if (!is_zero_ether_addr(p->eth_src))
|
|
ether_addr_copy(oethh->h_source, p->eth_src);
|
|
if (!is_zero_ether_addr(p->eth_dst))
|
|
ether_addr_copy(oethh->h_dest, p->eth_dst);
|
|
oethh->h_proto = htons(p->eth_type);
|
|
|
|
if (skb_at_tc_ingress(skb))
|
|
skb_pull(skb, skb->dev->hard_header_len);
|
|
|
|
return action;
|
|
}
|
|
|
|
static int tcf_ife_act(struct sk_buff *skb, const struct tc_action *a,
|
|
struct tcf_result *res)
|
|
{
|
|
struct tcf_ife_info *ife = to_ife(a);
|
|
struct tcf_ife_params *p;
|
|
int ret;
|
|
|
|
rcu_read_lock();
|
|
p = rcu_dereference(ife->params);
|
|
if (p->flags & IFE_ENCODE) {
|
|
ret = tcf_ife_encode(skb, a, res, p);
|
|
rcu_read_unlock();
|
|
return ret;
|
|
}
|
|
rcu_read_unlock();
|
|
|
|
return tcf_ife_decode(skb, a, res);
|
|
}
|
|
|
|
static int tcf_ife_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, ife_net_id);
|
|
|
|
return tcf_generic_walker(tn, skb, cb, type, ops, extack);
|
|
}
|
|
|
|
static int tcf_ife_search(struct net *net, struct tc_action **a, u32 index,
|
|
struct netlink_ext_ack *extack)
|
|
{
|
|
struct tc_action_net *tn = net_generic(net, ife_net_id);
|
|
|
|
return tcf_idr_search(tn, a, index);
|
|
}
|
|
|
|
static struct tc_action_ops act_ife_ops = {
|
|
.kind = "ife",
|
|
.type = TCA_ACT_IFE,
|
|
.owner = THIS_MODULE,
|
|
.act = tcf_ife_act,
|
|
.dump = tcf_ife_dump,
|
|
.cleanup = tcf_ife_cleanup,
|
|
.init = tcf_ife_init,
|
|
.walk = tcf_ife_walker,
|
|
.lookup = tcf_ife_search,
|
|
.size = sizeof(struct tcf_ife_info),
|
|
};
|
|
|
|
static __net_init int ife_init_net(struct net *net)
|
|
{
|
|
struct tc_action_net *tn = net_generic(net, ife_net_id);
|
|
|
|
return tc_action_net_init(tn, &act_ife_ops);
|
|
}
|
|
|
|
static void __net_exit ife_exit_net(struct list_head *net_list)
|
|
{
|
|
tc_action_net_exit(net_list, ife_net_id);
|
|
}
|
|
|
|
static struct pernet_operations ife_net_ops = {
|
|
.init = ife_init_net,
|
|
.exit_batch = ife_exit_net,
|
|
.id = &ife_net_id,
|
|
.size = sizeof(struct tc_action_net),
|
|
};
|
|
|
|
static int __init ife_init_module(void)
|
|
{
|
|
return tcf_register_action(&act_ife_ops, &ife_net_ops);
|
|
}
|
|
|
|
static void __exit ife_cleanup_module(void)
|
|
{
|
|
tcf_unregister_action(&act_ife_ops, &ife_net_ops);
|
|
}
|
|
|
|
module_init(ife_init_module);
|
|
module_exit(ife_cleanup_module);
|
|
|
|
MODULE_AUTHOR("Jamal Hadi Salim(2015)");
|
|
MODULE_DESCRIPTION("Inter-FE LFB action");
|
|
MODULE_LICENSE("GPL");
|