linux-stable/net/sched/act_mirred.c

386 lines
9.4 KiB
C
Raw Normal View History

/*
* net/sched/act_mirred.c packet mirroring and redirect actions
*
* 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.
*
* Authors: Jamal Hadi Salim (2002-4)
*
* TODO: Add ingress support (and socket redirect support)
*
*/
#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 cleanup: Update gfp.h and slab.h includes to prepare for breaking implicit slab.h inclusion from percpu.h percpu.h is included by sched.h and module.h and thus ends up being included when building most .c files. percpu.h includes slab.h which in turn includes gfp.h making everything defined by the two files universally available and complicating inclusion dependencies. percpu.h -> slab.h dependency is about to be removed. Prepare for this change by updating users of gfp and slab facilities include those headers directly instead of assuming availability. As this conversion needs to touch large number of source files, the following script is used as the basis of conversion. http://userweb.kernel.org/~tj/misc/slabh-sweep.py The script does the followings. * Scan files for gfp and slab usages and update includes such that only the necessary includes are there. ie. if only gfp is used, gfp.h, if slab is used, slab.h. * When the script inserts a new include, it looks at the include blocks and try to put the new include such that its order conforms to its surrounding. It's put in the include block which contains core kernel includes, in the same order that the rest are ordered - alphabetical, Christmas tree, rev-Xmas-tree or at the end if there doesn't seem to be any matching order. * If the script can't find a place to put a new include (mostly because the file doesn't have fitting include block), it prints out an error message indicating which .h file needs to be added to the file. The conversion was done in the following steps. 1. The initial automatic conversion of all .c files updated slightly over 4000 files, deleting around 700 includes and adding ~480 gfp.h and ~3000 slab.h inclusions. The script emitted errors for ~400 files. 2. Each error was manually checked. Some didn't need the inclusion, some needed manual addition while adding it to implementation .h or embedding .c file was more appropriate for others. This step added inclusions to around 150 files. 3. The script was run again and the output was compared to the edits from #2 to make sure no file was left behind. 4. Several build tests were done and a couple of problems were fixed. e.g. lib/decompress_*.c used malloc/free() wrappers around slab APIs requiring slab.h to be added manually. 5. The script was run on all .h files but without automatically editing them as sprinkling gfp.h and slab.h inclusions around .h files could easily lead to inclusion dependency hell. Most gfp.h inclusion directives were ignored as stuff from gfp.h was usually wildly available and often used in preprocessor macros. Each slab.h inclusion directive was examined and added manually as necessary. 6. percpu.h was updated not to include slab.h. 7. Build test were done on the following configurations and failures were fixed. CONFIG_GCOV_KERNEL was turned off for all tests (as my distributed build env didn't work with gcov compiles) and a few more options had to be turned off depending on archs to make things build (like ipr on powerpc/64 which failed due to missing writeq). * x86 and x86_64 UP and SMP allmodconfig and a custom test config. * powerpc and powerpc64 SMP allmodconfig * sparc and sparc64 SMP allmodconfig * ia64 SMP allmodconfig * s390 SMP allmodconfig * alpha SMP allmodconfig * um on x86_64 SMP allmodconfig 8. percpu.h modifications were reverted so that it could be applied as a separate patch and serve as bisection point. Given the fact that I had only a couple of failures from tests on step 6, I'm fairly confident about the coverage of this conversion patch. If there is a breakage, it's likely to be something in one of the arch headers which should be easily discoverable easily on most builds of the specific arch. Signed-off-by: Tejun Heo <tj@kernel.org> Guess-its-ok-by: Christoph Lameter <cl@linux-foundation.org> Cc: Ingo Molnar <mingo@redhat.com> Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
2010-03-24 08:04:11 +00:00
#include <linux/gfp.h>
#include <linux/if_arp.h>
[NET]: Make the device list and device lookups per namespace. This patch makes most of the generic device layer network namespace safe. This patch makes dev_base_head a network namespace variable, and then it picks up a few associated variables. The functions: dev_getbyhwaddr dev_getfirsthwbytype dev_get_by_flags dev_get_by_name __dev_get_by_name dev_get_by_index __dev_get_by_index dev_ioctl dev_ethtool dev_load wireless_process_ioctl were modified to take a network namespace argument, and deal with it. vlan_ioctl_set and brioctl_set were modified so their hooks will receive a network namespace argument. So basically anthing in the core of the network stack that was affected to by the change of dev_base was modified to handle multiple network namespaces. The rest of the network stack was simply modified to explicitly use &init_net the initial network namespace. This can be fixed when those components of the network stack are modified to handle multiple network namespaces. For now the ifindex generator is left global. Fundametally ifindex numbers are per namespace, or else we will have corner case problems with migration when we get that far. At the same time there are assumptions in the network stack that the ifindex of a network device won't change. Making the ifindex number global seems a good compromise until the network stack can cope with ifindex changes when you change namespaces, and the like. Signed-off-by: Eric W. Biederman <ebiederm@xmission.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2007-09-17 18:56:21 +00:00
#include <net/net_namespace.h>
#include <net/netlink.h>
#include <net/pkt_sched.h>
#include <linux/tc_act/tc_mirred.h>
#include <net/tc_act/tc_mirred.h>
#include <linux/if_arp.h>
#define MIRRED_TAB_MASK 7
static LIST_HEAD(mirred_list);
static DEFINE_SPINLOCK(mirred_list_lock);
static bool tcf_mirred_is_act_redirect(int action)
{
return action == TCA_EGRESS_REDIR || action == TCA_INGRESS_REDIR;
}
static u32 tcf_mirred_act_direction(int action)
{
switch (action) {
case TCA_EGRESS_REDIR:
case TCA_EGRESS_MIRROR:
return AT_EGRESS;
case TCA_INGRESS_REDIR:
case TCA_INGRESS_MIRROR:
return AT_INGRESS;
default:
BUG();
}
}
static void tcf_mirred_release(struct tc_action *a, int bind)
{
struct tcf_mirred *m = to_mirred(a);
net_sched: close another race condition in tcf_mirred_release() We saw the following extra refcount release on veth device: kernel: [7957821.463992] unregister_netdevice: waiting for mesos50284 to become free. Usage count = -1 Since we heavily use mirred action to redirect packets to veth, I think this is caused by the following race condition: CPU0: tcf_mirred_release(): (in RCU callback) struct net_device *dev = rcu_dereference_protected(m->tcfm_dev, 1); CPU1: mirred_device_event(): spin_lock_bh(&mirred_list_lock); list_for_each_entry(m, &mirred_list, tcfm_list) { if (rcu_access_pointer(m->tcfm_dev) == dev) { dev_put(dev); /* Note : no rcu grace period necessary, as * net_device are already rcu protected. */ RCU_INIT_POINTER(m->tcfm_dev, NULL); } } spin_unlock_bh(&mirred_list_lock); CPU0: tcf_mirred_release(): spin_lock_bh(&mirred_list_lock); list_del(&m->tcfm_list); spin_unlock_bh(&mirred_list_lock); if (dev) // <======== Stil refers to the old m->tcfm_dev dev_put(dev); // <======== dev_put() is called on it again The action init code path is good because it is impossible to modify an action that is being removed. So, fix this by moving everything under the spinlock. Fixes: 2ee22a90c7af ("net_sched: act_mirred: remove spinlock in fast path") Fixes: 6bd00b850635 ("act_mirred: fix a race condition on mirred_list") Cc: Jamal Hadi Salim <jhs@mojatatu.com> Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com> Acked-by: Jamal Hadi Salim <jhs@mojatatu.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-05-16 22:11:18 +00:00
struct net_device *dev;
/* We could be called either in a RCU callback or with RTNL lock held. */
spin_lock_bh(&mirred_list_lock);
list_del(&m->tcfm_list);
net_sched: close another race condition in tcf_mirred_release() We saw the following extra refcount release on veth device: kernel: [7957821.463992] unregister_netdevice: waiting for mesos50284 to become free. Usage count = -1 Since we heavily use mirred action to redirect packets to veth, I think this is caused by the following race condition: CPU0: tcf_mirred_release(): (in RCU callback) struct net_device *dev = rcu_dereference_protected(m->tcfm_dev, 1); CPU1: mirred_device_event(): spin_lock_bh(&mirred_list_lock); list_for_each_entry(m, &mirred_list, tcfm_list) { if (rcu_access_pointer(m->tcfm_dev) == dev) { dev_put(dev); /* Note : no rcu grace period necessary, as * net_device are already rcu protected. */ RCU_INIT_POINTER(m->tcfm_dev, NULL); } } spin_unlock_bh(&mirred_list_lock); CPU0: tcf_mirred_release(): spin_lock_bh(&mirred_list_lock); list_del(&m->tcfm_list); spin_unlock_bh(&mirred_list_lock); if (dev) // <======== Stil refers to the old m->tcfm_dev dev_put(dev); // <======== dev_put() is called on it again The action init code path is good because it is impossible to modify an action that is being removed. So, fix this by moving everything under the spinlock. Fixes: 2ee22a90c7af ("net_sched: act_mirred: remove spinlock in fast path") Fixes: 6bd00b850635 ("act_mirred: fix a race condition on mirred_list") Cc: Jamal Hadi Salim <jhs@mojatatu.com> Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com> Acked-by: Jamal Hadi Salim <jhs@mojatatu.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-05-16 22:11:18 +00:00
dev = rcu_dereference_protected(m->tcfm_dev, 1);
if (dev)
dev_put(dev);
net_sched: close another race condition in tcf_mirred_release() We saw the following extra refcount release on veth device: kernel: [7957821.463992] unregister_netdevice: waiting for mesos50284 to become free. Usage count = -1 Since we heavily use mirred action to redirect packets to veth, I think this is caused by the following race condition: CPU0: tcf_mirred_release(): (in RCU callback) struct net_device *dev = rcu_dereference_protected(m->tcfm_dev, 1); CPU1: mirred_device_event(): spin_lock_bh(&mirred_list_lock); list_for_each_entry(m, &mirred_list, tcfm_list) { if (rcu_access_pointer(m->tcfm_dev) == dev) { dev_put(dev); /* Note : no rcu grace period necessary, as * net_device are already rcu protected. */ RCU_INIT_POINTER(m->tcfm_dev, NULL); } } spin_unlock_bh(&mirred_list_lock); CPU0: tcf_mirred_release(): spin_lock_bh(&mirred_list_lock); list_del(&m->tcfm_list); spin_unlock_bh(&mirred_list_lock); if (dev) // <======== Stil refers to the old m->tcfm_dev dev_put(dev); // <======== dev_put() is called on it again The action init code path is good because it is impossible to modify an action that is being removed. So, fix this by moving everything under the spinlock. Fixes: 2ee22a90c7af ("net_sched: act_mirred: remove spinlock in fast path") Fixes: 6bd00b850635 ("act_mirred: fix a race condition on mirred_list") Cc: Jamal Hadi Salim <jhs@mojatatu.com> Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com> Acked-by: Jamal Hadi Salim <jhs@mojatatu.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-05-16 22:11:18 +00:00
spin_unlock_bh(&mirred_list_lock);
}
static const struct nla_policy mirred_policy[TCA_MIRRED_MAX + 1] = {
[TCA_MIRRED_PARMS] = { .len = sizeof(struct tc_mirred) },
};
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 01:58:21 +00:00
static unsigned int mirred_net_id;
static struct tc_action_ops act_mirred_ops;
static int tcf_mirred_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, mirred_net_id);
struct nlattr *tb[TCA_MIRRED_MAX + 1];
bool mac_header_xmit = false;
struct tc_mirred *parm;
struct tcf_mirred *m;
struct net_device *dev;
bool exists = false;
int ret;
if (nla == NULL)
return -EINVAL;
ret = nla_parse_nested(tb, TCA_MIRRED_MAX, nla, mirred_policy);
if (ret < 0)
return ret;
if (tb[TCA_MIRRED_PARMS] == NULL)
return -EINVAL;
parm = nla_data(tb[TCA_MIRRED_PARMS]);
exists = tcf_hash_check(tn, parm->index, a, bind);
if (exists && bind)
return 0;
switch (parm->eaction) {
case TCA_EGRESS_MIRROR:
case TCA_EGRESS_REDIR:
case TCA_INGRESS_REDIR:
case TCA_INGRESS_MIRROR:
break;
default:
if (exists)
tcf_hash_release(*a, bind);
return -EINVAL;
}
if (parm->ifindex) {
dev = __dev_get_by_index(net, parm->ifindex);
if (dev == NULL) {
if (exists)
tcf_hash_release(*a, bind);
return -ENODEV;
}
mac_header_xmit = dev_is_mac_header_xmit(dev);
} else {
dev = NULL;
}
if (!exists) {
if (dev == NULL)
return -EINVAL;
ret = tcf_hash_create(tn, parm->index, est, a,
&act_mirred_ops, bind, true);
if (ret)
return ret;
ret = ACT_P_CREATED;
} else {
tcf_hash_release(*a, bind);
if (!ovr)
return -EEXIST;
}
m = to_mirred(*a);
ASSERT_RTNL();
m->tcf_action = parm->action;
m->tcfm_eaction = parm->eaction;
if (dev != NULL) {
m->tcfm_ifindex = parm->ifindex;
if (ret != ACT_P_CREATED)
dev_put(rcu_dereference_protected(m->tcfm_dev, 1));
dev_hold(dev);
rcu_assign_pointer(m->tcfm_dev, dev);
m->tcfm_mac_header_xmit = mac_header_xmit;
}
if (ret == ACT_P_CREATED) {
spin_lock_bh(&mirred_list_lock);
list_add(&m->tcfm_list, &mirred_list);
spin_unlock_bh(&mirred_list_lock);
tcf_hash_insert(tn, *a);
}
return ret;
}
static int tcf_mirred(struct sk_buff *skb, const struct tc_action *a,
struct tcf_result *res)
{
struct tcf_mirred *m = to_mirred(a);
bool m_mac_header_xmit;
struct net_device *dev;
struct sk_buff *skb2;
int retval, err = 0;
int m_eaction;
int mac_len;
tcf_lastuse_update(&m->tcf_tm);
bstats_cpu_update(this_cpu_ptr(m->common.cpu_bstats), skb);
rcu_read_lock();
m_mac_header_xmit = READ_ONCE(m->tcfm_mac_header_xmit);
m_eaction = READ_ONCE(m->tcfm_eaction);
retval = READ_ONCE(m->tcf_action);
dev = rcu_dereference(m->tcfm_dev);
if (unlikely(!dev)) {
pr_notice_once("tc mirred: target device is gone\n");
goto out;
}
if (unlikely(!(dev->flags & IFF_UP))) {
net_notice_ratelimited("tc mirred to Houston: device %s is down\n",
dev->name);
goto out;
}
skb2 = skb_clone(skb, GFP_ATOMIC);
if (!skb2)
goto out;
/* If action's target direction differs than filter's direction,
* and devices expect a mac header on xmit, then mac push/pull is
* needed.
*/
if (skb->tc_at != tcf_mirred_act_direction(m_eaction) &&
m_mac_header_xmit) {
if (!skb_at_tc_ingress(skb)) {
/* caught at egress, act ingress: pull mac */
mac_len = skb_network_header(skb) - skb_mac_header(skb);
skb_pull_rcsum(skb2, mac_len);
} else {
/* caught at ingress, act egress: push mac */
skb_push_rcsum(skb2, skb->mac_len);
}
}
/* mirror is always swallowed */
if (tcf_mirred_is_act_redirect(m_eaction))
skb2->tc_from = skb2->tc_at;
skb2->skb_iif = skb->dev->ifindex;
skb2->dev = dev;
if (tcf_mirred_act_direction(m_eaction) & AT_EGRESS)
err = dev_queue_xmit(skb2);
else
err = netif_receive_skb(skb2);
if (err) {
out:
qstats_overlimit_inc(this_cpu_ptr(m->common.cpu_qstats));
if (tcf_mirred_is_act_redirect(m_eaction))
retval = TC_ACT_SHOT;
}
rcu_read_unlock();
return retval;
}
static void tcf_stats_update(struct tc_action *a, u64 bytes, u32 packets,
u64 lastuse)
{
struct tcf_mirred *m = to_mirred(a);
struct tcf_t *tm = &m->tcf_tm;
_bstats_cpu_update(this_cpu_ptr(a->cpu_bstats), bytes, packets);
tm->lastuse = lastuse;
}
static int tcf_mirred_dump(struct sk_buff *skb, struct tc_action *a, int bind,
int ref)
{
unsigned char *b = skb_tail_pointer(skb);
struct tcf_mirred *m = to_mirred(a);
struct tc_mirred opt = {
.index = m->tcf_index,
.action = m->tcf_action,
.refcnt = m->tcf_refcnt - ref,
.bindcnt = m->tcf_bindcnt - bind,
.eaction = m->tcfm_eaction,
.ifindex = m->tcfm_ifindex,
};
struct tcf_t t;
if (nla_put(skb, TCA_MIRRED_PARMS, sizeof(opt), &opt))
goto nla_put_failure;
tcf_tm_dump(&t, &m->tcf_tm);
if (nla_put_64bit(skb, TCA_MIRRED_TM, sizeof(t), &t, TCA_MIRRED_PAD))
goto nla_put_failure;
return skb->len;
nla_put_failure:
nlmsg_trim(skb, b);
return -1;
}
static int tcf_mirred_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, mirred_net_id);
return tcf_generic_walker(tn, skb, cb, type, ops);
}
static int tcf_mirred_search(struct net *net, struct tc_action **a, u32 index)
{
struct tc_action_net *tn = net_generic(net, mirred_net_id);
return tcf_hash_search(tn, a, index);
}
static int mirred_device_event(struct notifier_block *unused,
unsigned long event, void *ptr)
{
struct net_device *dev = netdev_notifier_info_to_dev(ptr);
struct tcf_mirred *m;
ASSERT_RTNL();
if (event == NETDEV_UNREGISTER) {
spin_lock_bh(&mirred_list_lock);
list_for_each_entry(m, &mirred_list, tcfm_list) {
if (rcu_access_pointer(m->tcfm_dev) == dev) {
dev_put(dev);
/* Note : no rcu grace period necessary, as
* net_device are already rcu protected.
*/
RCU_INIT_POINTER(m->tcfm_dev, NULL);
}
}
spin_unlock_bh(&mirred_list_lock);
}
return NOTIFY_DONE;
}
static struct notifier_block mirred_device_notifier = {
.notifier_call = mirred_device_event,
};
static int tcf_mirred_device(const struct tc_action *a, struct net *net,
struct net_device **mirred_dev)
{
int ifindex = tcf_mirred_ifindex(a);
*mirred_dev = __dev_get_by_index(net, ifindex);
if (!*mirred_dev)
return -EINVAL;
return 0;
}
static struct tc_action_ops act_mirred_ops = {
.kind = "mirred",
.type = TCA_ACT_MIRRED,
.owner = THIS_MODULE,
.act = tcf_mirred,
.stats_update = tcf_stats_update,
.dump = tcf_mirred_dump,
.cleanup = tcf_mirred_release,
.init = tcf_mirred_init,
.walk = tcf_mirred_walker,
.lookup = tcf_mirred_search,
.size = sizeof(struct tcf_mirred),
.get_dev = tcf_mirred_device,
};
static __net_init int mirred_init_net(struct net *net)
{
struct tc_action_net *tn = net_generic(net, mirred_net_id);
return tc_action_net_init(tn, &act_mirred_ops, MIRRED_TAB_MASK);
}
static void __net_exit mirred_exit_net(struct net *net)
{
struct tc_action_net *tn = net_generic(net, mirred_net_id);
tc_action_net_exit(tn);
}
static struct pernet_operations mirred_net_ops = {
.init = mirred_init_net,
.exit = mirred_exit_net,
.id = &mirred_net_id,
.size = sizeof(struct tc_action_net),
};
MODULE_AUTHOR("Jamal Hadi Salim(2002)");
MODULE_DESCRIPTION("Device Mirror/redirect actions");
MODULE_LICENSE("GPL");
static int __init mirred_init_module(void)
{
int err = register_netdevice_notifier(&mirred_device_notifier);
if (err)
return err;
pr_info("Mirror/redirect action on\n");
return tcf_register_action(&act_mirred_ops, &mirred_net_ops);
}
static void __exit mirred_cleanup_module(void)
{
tcf_unregister_action(&act_mirred_ops, &mirred_net_ops);
unregister_netdevice_notifier(&mirred_device_notifier);
}
module_init(mirred_init_module);
module_exit(mirred_cleanup_module);