linux/net/sched/cls_flower.c

1061 lines
30 KiB
C
Raw Normal View History

/*
* net/sched/cls_flower.c Flower classifier
*
* Copyright (c) 2015 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/kernel.h>
#include <linux/init.h>
#include <linux/module.h>
#include <linux/rhashtable.h>
net, sched: respect rcu grace period on cls destruction Roi reported a crash in flower where tp->root was NULL in ->classify() callbacks. Reason is that in ->destroy() tp->root is set to NULL via RCU_INIT_POINTER(). It's problematic for some of the classifiers, because this doesn't respect RCU grace period for them, and as a result, still outstanding readers from tc_classify() will try to blindly dereference a NULL tp->root. The tp->root object is strictly private to the classifier implementation and holds internal data the core such as tc_ctl_tfilter() doesn't know about. Within some classifiers, such as cls_bpf, cls_basic, etc, tp->root is only checked for NULL in ->get() callback, but nowhere else. This is misleading and seemed to be copied from old classifier code that was not cleaned up properly. For example, d3fa76ee6b4a ("[NET_SCHED]: cls_basic: fix NULL pointer dereference") moved tp->root initialization into ->init() routine, where before it was part of ->change(), so ->get() had to deal with tp->root being NULL back then, so that was indeed a valid case, after d3fa76ee6b4a, not really anymore. We used to set tp->root to NULL long ago in ->destroy(), see 47a1a1d4be29 ("pkt_sched: remove unnecessary xchg() in packet classifiers"); but the NULLifying was reintroduced with the RCUification, but it's not correct for every classifier implementation. In the cases that are fixed here with one exception of cls_cgroup, tp->root object is allocated and initialized inside ->init() callback, which is always performed at a point in time after we allocate a new tp, which means tp and thus tp->root was not globally visible in the tp chain yet (see tc_ctl_tfilter()). Also, on destruction tp->root is strictly kfree_rcu()'ed in ->destroy() handler, same for the tp which is kfree_rcu()'ed right when we return from ->destroy() in tcf_destroy(). This means, the head object's lifetime for such classifiers is always tied to the tp lifetime. The RCU callback invocation for the two kfree_rcu() could be out of order, but that's fine since both are independent. Dropping the RCU_INIT_POINTER(tp->root, NULL) for these classifiers here means that 1) we don't need a useless NULL check in fast-path and, 2) that outstanding readers of that tp in tc_classify() can still execute under respect with RCU grace period as it is actually expected. Things that haven't been touched here: cls_fw and cls_route. They each handle tp->root being NULL in ->classify() path for historic reasons, so their ->destroy() implementation can stay as is. If someone actually cares, they could get cleaned up at some point to avoid the test in fast path. cls_u32 doesn't set tp->root to NULL. For cls_rsvp, I just added a !head should anyone actually be using/testing it, so it at least aligns with cls_fw and cls_route. For cls_flower we additionally need to defer rhashtable destruction (to a sleepable context) after RCU grace period as concurrent readers might still access it. (Note that in this case we need to hold module reference to keep work callback address intact, since we only wait on module unload for all call_rcu()s to finish.) This fixes one race to bring RCU grace period guarantees back. Next step as worked on by Cong however is to fix 1e052be69d04 ("net_sched: destroy proto tp when all filters are gone") to get the order of unlinking the tp in tc_ctl_tfilter() for the RTM_DELTFILTER case right by moving RCU_INIT_POINTER() before tcf_destroy() and let the notification for removal be done through the prior ->delete() callback. Both are independant issues. Once we have that right, we can then clean tp->root up for a number of classifiers by not making them RCU pointers, which requires a new callback (->uninit) that is triggered from tp's RCU callback, where we just kfree() tp->root from there. Fixes: 1f947bf151e9 ("net: sched: rcu'ify cls_bpf") Fixes: 9888faefe132 ("net: sched: cls_basic use RCU") Fixes: 70da9f0bf999 ("net: sched: cls_flow use RCU") Fixes: 77b9900ef53a ("tc: introduce Flower classifier") Fixes: bf3994d2ed31 ("net/sched: introduce Match-all classifier") Fixes: 952313bd6258 ("net: sched: cls_cgroup use RCU") Reported-by: Roi Dayan <roid@mellanox.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Cc: Cong Wang <xiyou.wangcong@gmail.com> Cc: John Fastabend <john.fastabend@gmail.com> Cc: Roi Dayan <roid@mellanox.com> Cc: Jiri Pirko <jiri@mellanox.com> Acked-by: John Fastabend <john.r.fastabend@intel.com> Acked-by: Cong Wang <xiyou.wangcong@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-11-27 00:18:01 +00:00
#include <linux/workqueue.h>
#include <linux/if_ether.h>
#include <linux/in6.h>
#include <linux/ip.h>
#include <net/sch_generic.h>
#include <net/pkt_cls.h>
#include <net/ip.h>
#include <net/flow_dissector.h>
#include <net/dst.h>
#include <net/dst_metadata.h>
struct fl_flow_key {
int indev_ifindex;
struct flow_dissector_key_control control;
struct flow_dissector_key_control enc_control;
struct flow_dissector_key_basic basic;
struct flow_dissector_key_eth_addrs eth;
struct flow_dissector_key_vlan vlan;
union {
struct flow_dissector_key_ipv4_addrs ipv4;
struct flow_dissector_key_ipv6_addrs ipv6;
};
struct flow_dissector_key_ports tp;
struct flow_dissector_key_keyid enc_key_id;
union {
struct flow_dissector_key_ipv4_addrs enc_ipv4;
struct flow_dissector_key_ipv6_addrs enc_ipv6;
};
struct flow_dissector_key_ports enc_tp;
} __aligned(BITS_PER_LONG / 8); /* Ensure that we can do comparisons as longs. */
struct fl_flow_mask_range {
unsigned short int start;
unsigned short int end;
};
struct fl_flow_mask {
struct fl_flow_key key;
struct fl_flow_mask_range range;
struct rcu_head rcu;
};
struct cls_fl_head {
struct rhashtable ht;
struct fl_flow_mask mask;
struct flow_dissector dissector;
u32 hgen;
bool mask_assigned;
struct list_head filters;
struct rhashtable_params ht_params;
net, sched: respect rcu grace period on cls destruction Roi reported a crash in flower where tp->root was NULL in ->classify() callbacks. Reason is that in ->destroy() tp->root is set to NULL via RCU_INIT_POINTER(). It's problematic for some of the classifiers, because this doesn't respect RCU grace period for them, and as a result, still outstanding readers from tc_classify() will try to blindly dereference a NULL tp->root. The tp->root object is strictly private to the classifier implementation and holds internal data the core such as tc_ctl_tfilter() doesn't know about. Within some classifiers, such as cls_bpf, cls_basic, etc, tp->root is only checked for NULL in ->get() callback, but nowhere else. This is misleading and seemed to be copied from old classifier code that was not cleaned up properly. For example, d3fa76ee6b4a ("[NET_SCHED]: cls_basic: fix NULL pointer dereference") moved tp->root initialization into ->init() routine, where before it was part of ->change(), so ->get() had to deal with tp->root being NULL back then, so that was indeed a valid case, after d3fa76ee6b4a, not really anymore. We used to set tp->root to NULL long ago in ->destroy(), see 47a1a1d4be29 ("pkt_sched: remove unnecessary xchg() in packet classifiers"); but the NULLifying was reintroduced with the RCUification, but it's not correct for every classifier implementation. In the cases that are fixed here with one exception of cls_cgroup, tp->root object is allocated and initialized inside ->init() callback, which is always performed at a point in time after we allocate a new tp, which means tp and thus tp->root was not globally visible in the tp chain yet (see tc_ctl_tfilter()). Also, on destruction tp->root is strictly kfree_rcu()'ed in ->destroy() handler, same for the tp which is kfree_rcu()'ed right when we return from ->destroy() in tcf_destroy(). This means, the head object's lifetime for such classifiers is always tied to the tp lifetime. The RCU callback invocation for the two kfree_rcu() could be out of order, but that's fine since both are independent. Dropping the RCU_INIT_POINTER(tp->root, NULL) for these classifiers here means that 1) we don't need a useless NULL check in fast-path and, 2) that outstanding readers of that tp in tc_classify() can still execute under respect with RCU grace period as it is actually expected. Things that haven't been touched here: cls_fw and cls_route. They each handle tp->root being NULL in ->classify() path for historic reasons, so their ->destroy() implementation can stay as is. If someone actually cares, they could get cleaned up at some point to avoid the test in fast path. cls_u32 doesn't set tp->root to NULL. For cls_rsvp, I just added a !head should anyone actually be using/testing it, so it at least aligns with cls_fw and cls_route. For cls_flower we additionally need to defer rhashtable destruction (to a sleepable context) after RCU grace period as concurrent readers might still access it. (Note that in this case we need to hold module reference to keep work callback address intact, since we only wait on module unload for all call_rcu()s to finish.) This fixes one race to bring RCU grace period guarantees back. Next step as worked on by Cong however is to fix 1e052be69d04 ("net_sched: destroy proto tp when all filters are gone") to get the order of unlinking the tp in tc_ctl_tfilter() for the RTM_DELTFILTER case right by moving RCU_INIT_POINTER() before tcf_destroy() and let the notification for removal be done through the prior ->delete() callback. Both are independant issues. Once we have that right, we can then clean tp->root up for a number of classifiers by not making them RCU pointers, which requires a new callback (->uninit) that is triggered from tp's RCU callback, where we just kfree() tp->root from there. Fixes: 1f947bf151e9 ("net: sched: rcu'ify cls_bpf") Fixes: 9888faefe132 ("net: sched: cls_basic use RCU") Fixes: 70da9f0bf999 ("net: sched: cls_flow use RCU") Fixes: 77b9900ef53a ("tc: introduce Flower classifier") Fixes: bf3994d2ed31 ("net/sched: introduce Match-all classifier") Fixes: 952313bd6258 ("net: sched: cls_cgroup use RCU") Reported-by: Roi Dayan <roid@mellanox.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Cc: Cong Wang <xiyou.wangcong@gmail.com> Cc: John Fastabend <john.fastabend@gmail.com> Cc: Roi Dayan <roid@mellanox.com> Cc: Jiri Pirko <jiri@mellanox.com> Acked-by: John Fastabend <john.r.fastabend@intel.com> Acked-by: Cong Wang <xiyou.wangcong@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-11-27 00:18:01 +00:00
union {
struct work_struct work;
struct rcu_head rcu;
};
};
struct cls_fl_filter {
struct rhash_head ht_node;
struct fl_flow_key mkey;
struct tcf_exts exts;
struct tcf_result res;
struct fl_flow_key key;
struct list_head list;
u32 handle;
u32 flags;
struct rcu_head rcu;
struct tc_to_netdev tc;
struct net_device *hw_dev;
};
static unsigned short int fl_mask_range(const struct fl_flow_mask *mask)
{
return mask->range.end - mask->range.start;
}
static void fl_mask_update_range(struct fl_flow_mask *mask)
{
const u8 *bytes = (const u8 *) &mask->key;
size_t size = sizeof(mask->key);
size_t i, first = 0, last = size - 1;
for (i = 0; i < sizeof(mask->key); i++) {
if (bytes[i]) {
if (!first && i)
first = i;
last = i;
}
}
mask->range.start = rounddown(first, sizeof(long));
mask->range.end = roundup(last + 1, sizeof(long));
}
static void *fl_key_get_start(struct fl_flow_key *key,
const struct fl_flow_mask *mask)
{
return (u8 *) key + mask->range.start;
}
static void fl_set_masked_key(struct fl_flow_key *mkey, struct fl_flow_key *key,
struct fl_flow_mask *mask)
{
const long *lkey = fl_key_get_start(key, mask);
const long *lmask = fl_key_get_start(&mask->key, mask);
long *lmkey = fl_key_get_start(mkey, mask);
int i;
for (i = 0; i < fl_mask_range(mask); i += sizeof(long))
*lmkey++ = *lkey++ & *lmask++;
}
static void fl_clear_masked_range(struct fl_flow_key *key,
struct fl_flow_mask *mask)
{
memset(fl_key_get_start(key, mask), 0, fl_mask_range(mask));
}
static int fl_classify(struct sk_buff *skb, const struct tcf_proto *tp,
struct tcf_result *res)
{
struct cls_fl_head *head = rcu_dereference_bh(tp->root);
struct cls_fl_filter *f;
struct fl_flow_key skb_key;
struct fl_flow_key skb_mkey;
struct ip_tunnel_info *info;
if (!atomic_read(&head->ht.nelems))
return -1;
fl_clear_masked_range(&skb_key, &head->mask);
info = skb_tunnel_info(skb);
if (info) {
struct ip_tunnel_key *key = &info->key;
switch (ip_tunnel_info_af(info)) {
case AF_INET:
skb_key.enc_ipv4.src = key->u.ipv4.src;
skb_key.enc_ipv4.dst = key->u.ipv4.dst;
break;
case AF_INET6:
skb_key.enc_ipv6.src = key->u.ipv6.src;
skb_key.enc_ipv6.dst = key->u.ipv6.dst;
break;
}
skb_key.enc_key_id.keyid = tunnel_id_to_key32(key->tun_id);
skb_key.enc_tp.src = key->tp_src;
skb_key.enc_tp.dst = key->tp_dst;
}
skb_key.indev_ifindex = skb->skb_iif;
/* skb_flow_dissect() does not set n_proto in case an unknown protocol,
* so do it rather here.
*/
skb_key.basic.n_proto = skb->protocol;
skb_flow_dissect(skb, &head->dissector, &skb_key, 0);
fl_set_masked_key(&skb_mkey, &skb_key, &head->mask);
f = rhashtable_lookup_fast(&head->ht,
fl_key_get_start(&skb_mkey, &head->mask),
head->ht_params);
if (f && !tc_skip_sw(f->flags)) {
*res = f->res;
return tcf_exts_exec(skb, &f->exts, res);
}
return -1;
}
static int fl_init(struct tcf_proto *tp)
{
struct cls_fl_head *head;
head = kzalloc(sizeof(*head), GFP_KERNEL);
if (!head)
return -ENOBUFS;
INIT_LIST_HEAD_RCU(&head->filters);
rcu_assign_pointer(tp->root, head);
return 0;
}
static void fl_destroy_filter(struct rcu_head *head)
{
struct cls_fl_filter *f = container_of(head, struct cls_fl_filter, rcu);
tcf_exts_destroy(&f->exts);
kfree(f);
}
static void fl_hw_destroy_filter(struct tcf_proto *tp, struct cls_fl_filter *f)
{
struct tc_cls_flower_offload offload = {0};
struct net_device *dev = f->hw_dev;
struct tc_to_netdev *tc = &f->tc;
if (!tc_can_offload(dev, tp))
return;
offload.command = TC_CLSFLOWER_DESTROY;
offload.cookie = (unsigned long)f;
tc->type = TC_SETUP_CLSFLOWER;
tc->cls_flower = &offload;
dev->netdev_ops->ndo_setup_tc(dev, tp->q->handle, tp->protocol, tc);
}
static int fl_hw_replace_filter(struct tcf_proto *tp,
struct flow_dissector *dissector,
struct fl_flow_key *mask,
struct cls_fl_filter *f)
{
struct net_device *dev = tp->q->dev_queue->dev;
struct tc_cls_flower_offload offload = {0};
struct tc_to_netdev *tc = &f->tc;
int err;
if (!tc_can_offload(dev, tp)) {
if (tcf_exts_get_dev(dev, &f->exts, &f->hw_dev))
return tc_skip_sw(f->flags) ? -EINVAL : 0;
dev = f->hw_dev;
tc->egress_dev = true;
} else {
f->hw_dev = dev;
}
offload.command = TC_CLSFLOWER_REPLACE;
offload.cookie = (unsigned long)f;
offload.dissector = dissector;
offload.mask = mask;
offload.key = &f->key;
offload.exts = &f->exts;
tc->type = TC_SETUP_CLSFLOWER;
tc->cls_flower = &offload;
err = dev->netdev_ops->ndo_setup_tc(dev, tp->q->handle, tp->protocol,
tc);
if (tc_skip_sw(f->flags))
return err;
return 0;
}
static void fl_hw_update_stats(struct tcf_proto *tp, struct cls_fl_filter *f)
{
struct tc_cls_flower_offload offload = {0};
struct net_device *dev = f->hw_dev;
struct tc_to_netdev *tc = &f->tc;
if (!tc_can_offload(dev, tp))
return;
offload.command = TC_CLSFLOWER_STATS;
offload.cookie = (unsigned long)f;
offload.exts = &f->exts;
tc->type = TC_SETUP_CLSFLOWER;
tc->cls_flower = &offload;
dev->netdev_ops->ndo_setup_tc(dev, tp->q->handle, tp->protocol, tc);
}
static void __fl_delete(struct tcf_proto *tp, struct cls_fl_filter *f)
{
list_del_rcu(&f->list);
if (!tc_skip_hw(f->flags))
fl_hw_destroy_filter(tp, f);
tcf_unbind_filter(tp, &f->res);
call_rcu(&f->rcu, fl_destroy_filter);
}
net, sched: respect rcu grace period on cls destruction Roi reported a crash in flower where tp->root was NULL in ->classify() callbacks. Reason is that in ->destroy() tp->root is set to NULL via RCU_INIT_POINTER(). It's problematic for some of the classifiers, because this doesn't respect RCU grace period for them, and as a result, still outstanding readers from tc_classify() will try to blindly dereference a NULL tp->root. The tp->root object is strictly private to the classifier implementation and holds internal data the core such as tc_ctl_tfilter() doesn't know about. Within some classifiers, such as cls_bpf, cls_basic, etc, tp->root is only checked for NULL in ->get() callback, but nowhere else. This is misleading and seemed to be copied from old classifier code that was not cleaned up properly. For example, d3fa76ee6b4a ("[NET_SCHED]: cls_basic: fix NULL pointer dereference") moved tp->root initialization into ->init() routine, where before it was part of ->change(), so ->get() had to deal with tp->root being NULL back then, so that was indeed a valid case, after d3fa76ee6b4a, not really anymore. We used to set tp->root to NULL long ago in ->destroy(), see 47a1a1d4be29 ("pkt_sched: remove unnecessary xchg() in packet classifiers"); but the NULLifying was reintroduced with the RCUification, but it's not correct for every classifier implementation. In the cases that are fixed here with one exception of cls_cgroup, tp->root object is allocated and initialized inside ->init() callback, which is always performed at a point in time after we allocate a new tp, which means tp and thus tp->root was not globally visible in the tp chain yet (see tc_ctl_tfilter()). Also, on destruction tp->root is strictly kfree_rcu()'ed in ->destroy() handler, same for the tp which is kfree_rcu()'ed right when we return from ->destroy() in tcf_destroy(). This means, the head object's lifetime for such classifiers is always tied to the tp lifetime. The RCU callback invocation for the two kfree_rcu() could be out of order, but that's fine since both are independent. Dropping the RCU_INIT_POINTER(tp->root, NULL) for these classifiers here means that 1) we don't need a useless NULL check in fast-path and, 2) that outstanding readers of that tp in tc_classify() can still execute under respect with RCU grace period as it is actually expected. Things that haven't been touched here: cls_fw and cls_route. They each handle tp->root being NULL in ->classify() path for historic reasons, so their ->destroy() implementation can stay as is. If someone actually cares, they could get cleaned up at some point to avoid the test in fast path. cls_u32 doesn't set tp->root to NULL. For cls_rsvp, I just added a !head should anyone actually be using/testing it, so it at least aligns with cls_fw and cls_route. For cls_flower we additionally need to defer rhashtable destruction (to a sleepable context) after RCU grace period as concurrent readers might still access it. (Note that in this case we need to hold module reference to keep work callback address intact, since we only wait on module unload for all call_rcu()s to finish.) This fixes one race to bring RCU grace period guarantees back. Next step as worked on by Cong however is to fix 1e052be69d04 ("net_sched: destroy proto tp when all filters are gone") to get the order of unlinking the tp in tc_ctl_tfilter() for the RTM_DELTFILTER case right by moving RCU_INIT_POINTER() before tcf_destroy() and let the notification for removal be done through the prior ->delete() callback. Both are independant issues. Once we have that right, we can then clean tp->root up for a number of classifiers by not making them RCU pointers, which requires a new callback (->uninit) that is triggered from tp's RCU callback, where we just kfree() tp->root from there. Fixes: 1f947bf151e9 ("net: sched: rcu'ify cls_bpf") Fixes: 9888faefe132 ("net: sched: cls_basic use RCU") Fixes: 70da9f0bf999 ("net: sched: cls_flow use RCU") Fixes: 77b9900ef53a ("tc: introduce Flower classifier") Fixes: bf3994d2ed31 ("net/sched: introduce Match-all classifier") Fixes: 952313bd6258 ("net: sched: cls_cgroup use RCU") Reported-by: Roi Dayan <roid@mellanox.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Cc: Cong Wang <xiyou.wangcong@gmail.com> Cc: John Fastabend <john.fastabend@gmail.com> Cc: Roi Dayan <roid@mellanox.com> Cc: Jiri Pirko <jiri@mellanox.com> Acked-by: John Fastabend <john.r.fastabend@intel.com> Acked-by: Cong Wang <xiyou.wangcong@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-11-27 00:18:01 +00:00
static void fl_destroy_sleepable(struct work_struct *work)
{
struct cls_fl_head *head = container_of(work, struct cls_fl_head,
work);
if (head->mask_assigned)
rhashtable_destroy(&head->ht);
kfree(head);
module_put(THIS_MODULE);
}
static void fl_destroy_rcu(struct rcu_head *rcu)
{
struct cls_fl_head *head = container_of(rcu, struct cls_fl_head, rcu);
INIT_WORK(&head->work, fl_destroy_sleepable);
schedule_work(&head->work);
}
static bool fl_destroy(struct tcf_proto *tp, bool force)
{
struct cls_fl_head *head = rtnl_dereference(tp->root);
struct cls_fl_filter *f, *next;
if (!force && !list_empty(&head->filters))
return false;
list_for_each_entry_safe(f, next, &head->filters, list)
__fl_delete(tp, f);
net, sched: respect rcu grace period on cls destruction Roi reported a crash in flower where tp->root was NULL in ->classify() callbacks. Reason is that in ->destroy() tp->root is set to NULL via RCU_INIT_POINTER(). It's problematic for some of the classifiers, because this doesn't respect RCU grace period for them, and as a result, still outstanding readers from tc_classify() will try to blindly dereference a NULL tp->root. The tp->root object is strictly private to the classifier implementation and holds internal data the core such as tc_ctl_tfilter() doesn't know about. Within some classifiers, such as cls_bpf, cls_basic, etc, tp->root is only checked for NULL in ->get() callback, but nowhere else. This is misleading and seemed to be copied from old classifier code that was not cleaned up properly. For example, d3fa76ee6b4a ("[NET_SCHED]: cls_basic: fix NULL pointer dereference") moved tp->root initialization into ->init() routine, where before it was part of ->change(), so ->get() had to deal with tp->root being NULL back then, so that was indeed a valid case, after d3fa76ee6b4a, not really anymore. We used to set tp->root to NULL long ago in ->destroy(), see 47a1a1d4be29 ("pkt_sched: remove unnecessary xchg() in packet classifiers"); but the NULLifying was reintroduced with the RCUification, but it's not correct for every classifier implementation. In the cases that are fixed here with one exception of cls_cgroup, tp->root object is allocated and initialized inside ->init() callback, which is always performed at a point in time after we allocate a new tp, which means tp and thus tp->root was not globally visible in the tp chain yet (see tc_ctl_tfilter()). Also, on destruction tp->root is strictly kfree_rcu()'ed in ->destroy() handler, same for the tp which is kfree_rcu()'ed right when we return from ->destroy() in tcf_destroy(). This means, the head object's lifetime for such classifiers is always tied to the tp lifetime. The RCU callback invocation for the two kfree_rcu() could be out of order, but that's fine since both are independent. Dropping the RCU_INIT_POINTER(tp->root, NULL) for these classifiers here means that 1) we don't need a useless NULL check in fast-path and, 2) that outstanding readers of that tp in tc_classify() can still execute under respect with RCU grace period as it is actually expected. Things that haven't been touched here: cls_fw and cls_route. They each handle tp->root being NULL in ->classify() path for historic reasons, so their ->destroy() implementation can stay as is. If someone actually cares, they could get cleaned up at some point to avoid the test in fast path. cls_u32 doesn't set tp->root to NULL. For cls_rsvp, I just added a !head should anyone actually be using/testing it, so it at least aligns with cls_fw and cls_route. For cls_flower we additionally need to defer rhashtable destruction (to a sleepable context) after RCU grace period as concurrent readers might still access it. (Note that in this case we need to hold module reference to keep work callback address intact, since we only wait on module unload for all call_rcu()s to finish.) This fixes one race to bring RCU grace period guarantees back. Next step as worked on by Cong however is to fix 1e052be69d04 ("net_sched: destroy proto tp when all filters are gone") to get the order of unlinking the tp in tc_ctl_tfilter() for the RTM_DELTFILTER case right by moving RCU_INIT_POINTER() before tcf_destroy() and let the notification for removal be done through the prior ->delete() callback. Both are independant issues. Once we have that right, we can then clean tp->root up for a number of classifiers by not making them RCU pointers, which requires a new callback (->uninit) that is triggered from tp's RCU callback, where we just kfree() tp->root from there. Fixes: 1f947bf151e9 ("net: sched: rcu'ify cls_bpf") Fixes: 9888faefe132 ("net: sched: cls_basic use RCU") Fixes: 70da9f0bf999 ("net: sched: cls_flow use RCU") Fixes: 77b9900ef53a ("tc: introduce Flower classifier") Fixes: bf3994d2ed31 ("net/sched: introduce Match-all classifier") Fixes: 952313bd6258 ("net: sched: cls_cgroup use RCU") Reported-by: Roi Dayan <roid@mellanox.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Cc: Cong Wang <xiyou.wangcong@gmail.com> Cc: John Fastabend <john.fastabend@gmail.com> Cc: Roi Dayan <roid@mellanox.com> Cc: Jiri Pirko <jiri@mellanox.com> Acked-by: John Fastabend <john.r.fastabend@intel.com> Acked-by: Cong Wang <xiyou.wangcong@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-11-27 00:18:01 +00:00
__module_get(THIS_MODULE);
call_rcu(&head->rcu, fl_destroy_rcu);
return true;
}
static unsigned long fl_get(struct tcf_proto *tp, u32 handle)
{
struct cls_fl_head *head = rtnl_dereference(tp->root);
struct cls_fl_filter *f;
list_for_each_entry(f, &head->filters, list)
if (f->handle == handle)
return (unsigned long) f;
return 0;
}
static const struct nla_policy fl_policy[TCA_FLOWER_MAX + 1] = {
[TCA_FLOWER_UNSPEC] = { .type = NLA_UNSPEC },
[TCA_FLOWER_CLASSID] = { .type = NLA_U32 },
[TCA_FLOWER_INDEV] = { .type = NLA_STRING,
.len = IFNAMSIZ },
[TCA_FLOWER_KEY_ETH_DST] = { .len = ETH_ALEN },
[TCA_FLOWER_KEY_ETH_DST_MASK] = { .len = ETH_ALEN },
[TCA_FLOWER_KEY_ETH_SRC] = { .len = ETH_ALEN },
[TCA_FLOWER_KEY_ETH_SRC_MASK] = { .len = ETH_ALEN },
[TCA_FLOWER_KEY_ETH_TYPE] = { .type = NLA_U16 },
[TCA_FLOWER_KEY_IP_PROTO] = { .type = NLA_U8 },
[TCA_FLOWER_KEY_IPV4_SRC] = { .type = NLA_U32 },
[TCA_FLOWER_KEY_IPV4_SRC_MASK] = { .type = NLA_U32 },
[TCA_FLOWER_KEY_IPV4_DST] = { .type = NLA_U32 },
[TCA_FLOWER_KEY_IPV4_DST_MASK] = { .type = NLA_U32 },
[TCA_FLOWER_KEY_IPV6_SRC] = { .len = sizeof(struct in6_addr) },
[TCA_FLOWER_KEY_IPV6_SRC_MASK] = { .len = sizeof(struct in6_addr) },
[TCA_FLOWER_KEY_IPV6_DST] = { .len = sizeof(struct in6_addr) },
[TCA_FLOWER_KEY_IPV6_DST_MASK] = { .len = sizeof(struct in6_addr) },
[TCA_FLOWER_KEY_TCP_SRC] = { .type = NLA_U16 },
[TCA_FLOWER_KEY_TCP_DST] = { .type = NLA_U16 },
[TCA_FLOWER_KEY_UDP_SRC] = { .type = NLA_U16 },
[TCA_FLOWER_KEY_UDP_DST] = { .type = NLA_U16 },
[TCA_FLOWER_KEY_VLAN_ID] = { .type = NLA_U16 },
[TCA_FLOWER_KEY_VLAN_PRIO] = { .type = NLA_U8 },
[TCA_FLOWER_KEY_VLAN_ETH_TYPE] = { .type = NLA_U16 },
[TCA_FLOWER_KEY_ENC_KEY_ID] = { .type = NLA_U32 },
[TCA_FLOWER_KEY_ENC_IPV4_SRC] = { .type = NLA_U32 },
[TCA_FLOWER_KEY_ENC_IPV4_SRC_MASK] = { .type = NLA_U32 },
[TCA_FLOWER_KEY_ENC_IPV4_DST] = { .type = NLA_U32 },
[TCA_FLOWER_KEY_ENC_IPV4_DST_MASK] = { .type = NLA_U32 },
[TCA_FLOWER_KEY_ENC_IPV6_SRC] = { .len = sizeof(struct in6_addr) },
[TCA_FLOWER_KEY_ENC_IPV6_SRC_MASK] = { .len = sizeof(struct in6_addr) },
[TCA_FLOWER_KEY_ENC_IPV6_DST] = { .len = sizeof(struct in6_addr) },
[TCA_FLOWER_KEY_ENC_IPV6_DST_MASK] = { .len = sizeof(struct in6_addr) },
[TCA_FLOWER_KEY_TCP_SRC_MASK] = { .type = NLA_U16 },
[TCA_FLOWER_KEY_TCP_DST_MASK] = { .type = NLA_U16 },
[TCA_FLOWER_KEY_UDP_SRC_MASK] = { .type = NLA_U16 },
[TCA_FLOWER_KEY_UDP_DST_MASK] = { .type = NLA_U16 },
[TCA_FLOWER_KEY_SCTP_SRC_MASK] = { .type = NLA_U16 },
[TCA_FLOWER_KEY_SCTP_DST_MASK] = { .type = NLA_U16 },
[TCA_FLOWER_KEY_SCTP_SRC] = { .type = NLA_U16 },
[TCA_FLOWER_KEY_SCTP_DST] = { .type = NLA_U16 },
[TCA_FLOWER_KEY_ENC_UDP_SRC_PORT] = { .type = NLA_U16 },
[TCA_FLOWER_KEY_ENC_UDP_SRC_PORT_MASK] = { .type = NLA_U16 },
[TCA_FLOWER_KEY_ENC_UDP_DST_PORT] = { .type = NLA_U16 },
[TCA_FLOWER_KEY_ENC_UDP_DST_PORT_MASK] = { .type = NLA_U16 },
};
static void fl_set_key_val(struct nlattr **tb,
void *val, int val_type,
void *mask, int mask_type, int len)
{
if (!tb[val_type])
return;
memcpy(val, nla_data(tb[val_type]), len);
if (mask_type == TCA_FLOWER_UNSPEC || !tb[mask_type])
memset(mask, 0xff, len);
else
memcpy(mask, nla_data(tb[mask_type]), len);
}
static void fl_set_key_vlan(struct nlattr **tb,
struct flow_dissector_key_vlan *key_val,
struct flow_dissector_key_vlan *key_mask)
{
#define VLAN_PRIORITY_MASK 0x7
if (tb[TCA_FLOWER_KEY_VLAN_ID]) {
key_val->vlan_id =
nla_get_u16(tb[TCA_FLOWER_KEY_VLAN_ID]) & VLAN_VID_MASK;
key_mask->vlan_id = VLAN_VID_MASK;
}
if (tb[TCA_FLOWER_KEY_VLAN_PRIO]) {
key_val->vlan_priority =
nla_get_u8(tb[TCA_FLOWER_KEY_VLAN_PRIO]) &
VLAN_PRIORITY_MASK;
key_mask->vlan_priority = VLAN_PRIORITY_MASK;
}
}
static int fl_set_key(struct net *net, struct nlattr **tb,
struct fl_flow_key *key, struct fl_flow_key *mask)
{
__be16 ethertype;
#ifdef CONFIG_NET_CLS_IND
if (tb[TCA_FLOWER_INDEV]) {
int err = tcf_change_indev(net, tb[TCA_FLOWER_INDEV]);
if (err < 0)
return err;
key->indev_ifindex = err;
mask->indev_ifindex = 0xffffffff;
}
#endif
fl_set_key_val(tb, key->eth.dst, TCA_FLOWER_KEY_ETH_DST,
mask->eth.dst, TCA_FLOWER_KEY_ETH_DST_MASK,
sizeof(key->eth.dst));
fl_set_key_val(tb, key->eth.src, TCA_FLOWER_KEY_ETH_SRC,
mask->eth.src, TCA_FLOWER_KEY_ETH_SRC_MASK,
sizeof(key->eth.src));
if (tb[TCA_FLOWER_KEY_ETH_TYPE]) {
ethertype = nla_get_be16(tb[TCA_FLOWER_KEY_ETH_TYPE]);
if (ethertype == htons(ETH_P_8021Q)) {
fl_set_key_vlan(tb, &key->vlan, &mask->vlan);
fl_set_key_val(tb, &key->basic.n_proto,
TCA_FLOWER_KEY_VLAN_ETH_TYPE,
&mask->basic.n_proto, TCA_FLOWER_UNSPEC,
sizeof(key->basic.n_proto));
} else {
key->basic.n_proto = ethertype;
mask->basic.n_proto = cpu_to_be16(~0);
}
}
if (key->basic.n_proto == htons(ETH_P_IP) ||
key->basic.n_proto == htons(ETH_P_IPV6)) {
fl_set_key_val(tb, &key->basic.ip_proto, TCA_FLOWER_KEY_IP_PROTO,
&mask->basic.ip_proto, TCA_FLOWER_UNSPEC,
sizeof(key->basic.ip_proto));
}
if (tb[TCA_FLOWER_KEY_IPV4_SRC] || tb[TCA_FLOWER_KEY_IPV4_DST]) {
key->control.addr_type = FLOW_DISSECTOR_KEY_IPV4_ADDRS;
fl_set_key_val(tb, &key->ipv4.src, TCA_FLOWER_KEY_IPV4_SRC,
&mask->ipv4.src, TCA_FLOWER_KEY_IPV4_SRC_MASK,
sizeof(key->ipv4.src));
fl_set_key_val(tb, &key->ipv4.dst, TCA_FLOWER_KEY_IPV4_DST,
&mask->ipv4.dst, TCA_FLOWER_KEY_IPV4_DST_MASK,
sizeof(key->ipv4.dst));
} else if (tb[TCA_FLOWER_KEY_IPV6_SRC] || tb[TCA_FLOWER_KEY_IPV6_DST]) {
key->control.addr_type = FLOW_DISSECTOR_KEY_IPV6_ADDRS;
fl_set_key_val(tb, &key->ipv6.src, TCA_FLOWER_KEY_IPV6_SRC,
&mask->ipv6.src, TCA_FLOWER_KEY_IPV6_SRC_MASK,
sizeof(key->ipv6.src));
fl_set_key_val(tb, &key->ipv6.dst, TCA_FLOWER_KEY_IPV6_DST,
&mask->ipv6.dst, TCA_FLOWER_KEY_IPV6_DST_MASK,
sizeof(key->ipv6.dst));
}
if (key->basic.ip_proto == IPPROTO_TCP) {
fl_set_key_val(tb, &key->tp.src, TCA_FLOWER_KEY_TCP_SRC,
&mask->tp.src, TCA_FLOWER_KEY_TCP_SRC_MASK,
sizeof(key->tp.src));
fl_set_key_val(tb, &key->tp.dst, TCA_FLOWER_KEY_TCP_DST,
&mask->tp.dst, TCA_FLOWER_KEY_TCP_DST_MASK,
sizeof(key->tp.dst));
} else if (key->basic.ip_proto == IPPROTO_UDP) {
fl_set_key_val(tb, &key->tp.src, TCA_FLOWER_KEY_UDP_SRC,
&mask->tp.src, TCA_FLOWER_KEY_UDP_SRC_MASK,
sizeof(key->tp.src));
fl_set_key_val(tb, &key->tp.dst, TCA_FLOWER_KEY_UDP_DST,
&mask->tp.dst, TCA_FLOWER_KEY_UDP_DST_MASK,
sizeof(key->tp.dst));
} else if (key->basic.ip_proto == IPPROTO_SCTP) {
fl_set_key_val(tb, &key->tp.src, TCA_FLOWER_KEY_SCTP_SRC,
&mask->tp.src, TCA_FLOWER_KEY_SCTP_SRC_MASK,
sizeof(key->tp.src));
fl_set_key_val(tb, &key->tp.dst, TCA_FLOWER_KEY_SCTP_DST,
&mask->tp.dst, TCA_FLOWER_KEY_SCTP_DST_MASK,
sizeof(key->tp.dst));
}
if (tb[TCA_FLOWER_KEY_ENC_IPV4_SRC] ||
tb[TCA_FLOWER_KEY_ENC_IPV4_DST]) {
key->enc_control.addr_type = FLOW_DISSECTOR_KEY_IPV4_ADDRS;
fl_set_key_val(tb, &key->enc_ipv4.src,
TCA_FLOWER_KEY_ENC_IPV4_SRC,
&mask->enc_ipv4.src,
TCA_FLOWER_KEY_ENC_IPV4_SRC_MASK,
sizeof(key->enc_ipv4.src));
fl_set_key_val(tb, &key->enc_ipv4.dst,
TCA_FLOWER_KEY_ENC_IPV4_DST,
&mask->enc_ipv4.dst,
TCA_FLOWER_KEY_ENC_IPV4_DST_MASK,
sizeof(key->enc_ipv4.dst));
}
if (tb[TCA_FLOWER_KEY_ENC_IPV6_SRC] ||
tb[TCA_FLOWER_KEY_ENC_IPV6_DST]) {
key->enc_control.addr_type = FLOW_DISSECTOR_KEY_IPV6_ADDRS;
fl_set_key_val(tb, &key->enc_ipv6.src,
TCA_FLOWER_KEY_ENC_IPV6_SRC,
&mask->enc_ipv6.src,
TCA_FLOWER_KEY_ENC_IPV6_SRC_MASK,
sizeof(key->enc_ipv6.src));
fl_set_key_val(tb, &key->enc_ipv6.dst,
TCA_FLOWER_KEY_ENC_IPV6_DST,
&mask->enc_ipv6.dst,
TCA_FLOWER_KEY_ENC_IPV6_DST_MASK,
sizeof(key->enc_ipv6.dst));
}
fl_set_key_val(tb, &key->enc_key_id.keyid, TCA_FLOWER_KEY_ENC_KEY_ID,
&mask->enc_key_id.keyid, TCA_FLOWER_UNSPEC,
sizeof(key->enc_key_id.keyid));
fl_set_key_val(tb, &key->enc_tp.src, TCA_FLOWER_KEY_ENC_UDP_SRC_PORT,
&mask->enc_tp.src, TCA_FLOWER_KEY_ENC_UDP_SRC_PORT_MASK,
sizeof(key->enc_tp.src));
fl_set_key_val(tb, &key->enc_tp.dst, TCA_FLOWER_KEY_ENC_UDP_DST_PORT,
&mask->enc_tp.dst, TCA_FLOWER_KEY_ENC_UDP_DST_PORT_MASK,
sizeof(key->enc_tp.dst));
return 0;
}
static bool fl_mask_eq(struct fl_flow_mask *mask1,
struct fl_flow_mask *mask2)
{
const long *lmask1 = fl_key_get_start(&mask1->key, mask1);
const long *lmask2 = fl_key_get_start(&mask2->key, mask2);
return !memcmp(&mask1->range, &mask2->range, sizeof(mask1->range)) &&
!memcmp(lmask1, lmask2, fl_mask_range(mask1));
}
static const struct rhashtable_params fl_ht_params = {
.key_offset = offsetof(struct cls_fl_filter, mkey), /* base offset */
.head_offset = offsetof(struct cls_fl_filter, ht_node),
.automatic_shrinking = true,
};
static int fl_init_hashtable(struct cls_fl_head *head,
struct fl_flow_mask *mask)
{
head->ht_params = fl_ht_params;
head->ht_params.key_len = fl_mask_range(mask);
head->ht_params.key_offset += mask->range.start;
return rhashtable_init(&head->ht, &head->ht_params);
}
#define FL_KEY_MEMBER_OFFSET(member) offsetof(struct fl_flow_key, member)
#define FL_KEY_MEMBER_SIZE(member) (sizeof(((struct fl_flow_key *) 0)->member))
#define FL_KEY_IS_MASKED(mask, member) \
memchr_inv(((char *)mask) + FL_KEY_MEMBER_OFFSET(member), \
0, FL_KEY_MEMBER_SIZE(member)) \
#define FL_KEY_SET(keys, cnt, id, member) \
do { \
keys[cnt].key_id = id; \
keys[cnt].offset = FL_KEY_MEMBER_OFFSET(member); \
cnt++; \
} while(0);
#define FL_KEY_SET_IF_MASKED(mask, keys, cnt, id, member) \
do { \
if (FL_KEY_IS_MASKED(mask, member)) \
FL_KEY_SET(keys, cnt, id, member); \
} while(0);
static void fl_init_dissector(struct cls_fl_head *head,
struct fl_flow_mask *mask)
{
struct flow_dissector_key keys[FLOW_DISSECTOR_KEY_MAX];
size_t cnt = 0;
FL_KEY_SET(keys, cnt, FLOW_DISSECTOR_KEY_CONTROL, control);
FL_KEY_SET(keys, cnt, FLOW_DISSECTOR_KEY_BASIC, basic);
FL_KEY_SET_IF_MASKED(&mask->key, keys, cnt,
FLOW_DISSECTOR_KEY_ETH_ADDRS, eth);
FL_KEY_SET_IF_MASKED(&mask->key, keys, cnt,
FLOW_DISSECTOR_KEY_IPV4_ADDRS, ipv4);
FL_KEY_SET_IF_MASKED(&mask->key, keys, cnt,
FLOW_DISSECTOR_KEY_IPV6_ADDRS, ipv6);
FL_KEY_SET_IF_MASKED(&mask->key, keys, cnt,
FLOW_DISSECTOR_KEY_PORTS, tp);
FL_KEY_SET_IF_MASKED(&mask->key, keys, cnt,
FLOW_DISSECTOR_KEY_VLAN, vlan);
FL_KEY_SET_IF_MASKED(&mask->key, keys, cnt,
FLOW_DISSECTOR_KEY_ENC_KEYID, enc_key_id);
FL_KEY_SET_IF_MASKED(&mask->key, keys, cnt,
FLOW_DISSECTOR_KEY_ENC_IPV4_ADDRS, enc_ipv4);
FL_KEY_SET_IF_MASKED(&mask->key, keys, cnt,
FLOW_DISSECTOR_KEY_ENC_IPV6_ADDRS, enc_ipv6);
if (FL_KEY_IS_MASKED(&mask->key, enc_ipv4) ||
FL_KEY_IS_MASKED(&mask->key, enc_ipv6))
FL_KEY_SET(keys, cnt, FLOW_DISSECTOR_KEY_ENC_CONTROL,
enc_control);
FL_KEY_SET_IF_MASKED(&mask->key, keys, cnt,
FLOW_DISSECTOR_KEY_ENC_PORTS, enc_tp);
skb_flow_dissector_init(&head->dissector, keys, cnt);
}
static int fl_check_assign_mask(struct cls_fl_head *head,
struct fl_flow_mask *mask)
{
int err;
if (head->mask_assigned) {
if (!fl_mask_eq(&head->mask, mask))
return -EINVAL;
else
return 0;
}
/* Mask is not assigned yet. So assign it and init hashtable
* according to that.
*/
err = fl_init_hashtable(head, mask);
if (err)
return err;
memcpy(&head->mask, mask, sizeof(head->mask));
head->mask_assigned = true;
fl_init_dissector(head, mask);
return 0;
}
static int fl_set_parms(struct net *net, struct tcf_proto *tp,
struct cls_fl_filter *f, struct fl_flow_mask *mask,
unsigned long base, struct nlattr **tb,
struct nlattr *est, bool ovr)
{
struct tcf_exts e;
int err;
err = tcf_exts_init(&e, TCA_FLOWER_ACT, 0);
if (err < 0)
return err;
err = tcf_exts_validate(net, tp, tb, est, &e, ovr);
if (err < 0)
goto errout;
if (tb[TCA_FLOWER_CLASSID]) {
f->res.classid = nla_get_u32(tb[TCA_FLOWER_CLASSID]);
tcf_bind_filter(tp, &f->res, base);
}
err = fl_set_key(net, tb, &f->key, &mask->key);
if (err)
goto errout;
fl_mask_update_range(mask);
fl_set_masked_key(&f->mkey, &f->key, mask);
tcf_exts_change(tp, &f->exts, &e);
return 0;
errout:
tcf_exts_destroy(&e);
return err;
}
static u32 fl_grab_new_handle(struct tcf_proto *tp,
struct cls_fl_head *head)
{
unsigned int i = 0x80000000;
u32 handle;
do {
if (++head->hgen == 0x7FFFFFFF)
head->hgen = 1;
} while (--i > 0 && fl_get(tp, head->hgen));
if (unlikely(i == 0)) {
pr_err("Insufficient number of handles\n");
handle = 0;
} else {
handle = head->hgen;
}
return handle;
}
static int fl_change(struct net *net, struct sk_buff *in_skb,
struct tcf_proto *tp, unsigned long base,
u32 handle, struct nlattr **tca,
unsigned long *arg, bool ovr)
{
struct cls_fl_head *head = rtnl_dereference(tp->root);
struct cls_fl_filter *fold = (struct cls_fl_filter *) *arg;
struct cls_fl_filter *fnew;
struct nlattr *tb[TCA_FLOWER_MAX + 1];
struct fl_flow_mask mask = {};
int err;
if (!tca[TCA_OPTIONS])
return -EINVAL;
err = nla_parse_nested(tb, TCA_FLOWER_MAX, tca[TCA_OPTIONS], fl_policy);
if (err < 0)
return err;
if (fold && handle && fold->handle != handle)
return -EINVAL;
fnew = kzalloc(sizeof(*fnew), GFP_KERNEL);
if (!fnew)
return -ENOBUFS;
err = tcf_exts_init(&fnew->exts, TCA_FLOWER_ACT, 0);
if (err < 0)
goto errout;
if (!handle) {
handle = fl_grab_new_handle(tp, head);
if (!handle) {
err = -EINVAL;
goto errout;
}
}
fnew->handle = handle;
if (tb[TCA_FLOWER_FLAGS]) {
fnew->flags = nla_get_u32(tb[TCA_FLOWER_FLAGS]);
if (!tc_flags_valid(fnew->flags)) {
err = -EINVAL;
goto errout;
}
}
err = fl_set_parms(net, tp, fnew, &mask, base, tb, tca[TCA_RATE], ovr);
if (err)
goto errout;
err = fl_check_assign_mask(head, &mask);
if (err)
goto errout;
if (!tc_skip_sw(fnew->flags)) {
err = rhashtable_insert_fast(&head->ht, &fnew->ht_node,
head->ht_params);
if (err)
goto errout;
}
if (!tc_skip_hw(fnew->flags)) {
err = fl_hw_replace_filter(tp,
&head->dissector,
&mask.key,
fnew);
if (err)
goto errout;
}
if (fold) {
if (!tc_skip_sw(fold->flags))
rhashtable_remove_fast(&head->ht, &fold->ht_node,
head->ht_params);
if (!tc_skip_hw(fold->flags))
fl_hw_destroy_filter(tp, fold);
}
*arg = (unsigned long) fnew;
if (fold) {
list_replace_rcu(&fold->list, &fnew->list);
tcf_unbind_filter(tp, &fold->res);
call_rcu(&fold->rcu, fl_destroy_filter);
} else {
list_add_tail_rcu(&fnew->list, &head->filters);
}
return 0;
errout:
tcf_exts_destroy(&fnew->exts);
kfree(fnew);
return err;
}
static int fl_delete(struct tcf_proto *tp, unsigned long arg)
{
struct cls_fl_head *head = rtnl_dereference(tp->root);
struct cls_fl_filter *f = (struct cls_fl_filter *) arg;
if (!tc_skip_sw(f->flags))
rhashtable_remove_fast(&head->ht, &f->ht_node,
head->ht_params);
__fl_delete(tp, f);
return 0;
}
static void fl_walk(struct tcf_proto *tp, struct tcf_walker *arg)
{
struct cls_fl_head *head = rtnl_dereference(tp->root);
struct cls_fl_filter *f;
list_for_each_entry_rcu(f, &head->filters, list) {
if (arg->count < arg->skip)
goto skip;
if (arg->fn(tp, (unsigned long) f, arg) < 0) {
arg->stop = 1;
break;
}
skip:
arg->count++;
}
}
static int fl_dump_key_val(struct sk_buff *skb,
void *val, int val_type,
void *mask, int mask_type, int len)
{
int err;
if (!memchr_inv(mask, 0, len))
return 0;
err = nla_put(skb, val_type, len, val);
if (err)
return err;
if (mask_type != TCA_FLOWER_UNSPEC) {
err = nla_put(skb, mask_type, len, mask);
if (err)
return err;
}
return 0;
}
static int fl_dump_key_vlan(struct sk_buff *skb,
struct flow_dissector_key_vlan *vlan_key,
struct flow_dissector_key_vlan *vlan_mask)
{
int err;
if (!memchr_inv(vlan_mask, 0, sizeof(*vlan_mask)))
return 0;
if (vlan_mask->vlan_id) {
err = nla_put_u16(skb, TCA_FLOWER_KEY_VLAN_ID,
vlan_key->vlan_id);
if (err)
return err;
}
if (vlan_mask->vlan_priority) {
err = nla_put_u8(skb, TCA_FLOWER_KEY_VLAN_PRIO,
vlan_key->vlan_priority);
if (err)
return err;
}
return 0;
}
static int fl_dump(struct net *net, struct tcf_proto *tp, unsigned long fh,
struct sk_buff *skb, struct tcmsg *t)
{
struct cls_fl_head *head = rtnl_dereference(tp->root);
struct cls_fl_filter *f = (struct cls_fl_filter *) fh;
struct nlattr *nest;
struct fl_flow_key *key, *mask;
if (!f)
return skb->len;
t->tcm_handle = f->handle;
nest = nla_nest_start(skb, TCA_OPTIONS);
if (!nest)
goto nla_put_failure;
if (f->res.classid &&
nla_put_u32(skb, TCA_FLOWER_CLASSID, f->res.classid))
goto nla_put_failure;
key = &f->key;
mask = &head->mask.key;
if (mask->indev_ifindex) {
struct net_device *dev;
dev = __dev_get_by_index(net, key->indev_ifindex);
if (dev && nla_put_string(skb, TCA_FLOWER_INDEV, dev->name))
goto nla_put_failure;
}
if (!tc_skip_hw(f->flags))
fl_hw_update_stats(tp, f);
if (fl_dump_key_val(skb, key->eth.dst, TCA_FLOWER_KEY_ETH_DST,
mask->eth.dst, TCA_FLOWER_KEY_ETH_DST_MASK,
sizeof(key->eth.dst)) ||
fl_dump_key_val(skb, key->eth.src, TCA_FLOWER_KEY_ETH_SRC,
mask->eth.src, TCA_FLOWER_KEY_ETH_SRC_MASK,
sizeof(key->eth.src)) ||
fl_dump_key_val(skb, &key->basic.n_proto, TCA_FLOWER_KEY_ETH_TYPE,
&mask->basic.n_proto, TCA_FLOWER_UNSPEC,
sizeof(key->basic.n_proto)))
goto nla_put_failure;
if (fl_dump_key_vlan(skb, &key->vlan, &mask->vlan))
goto nla_put_failure;
if ((key->basic.n_proto == htons(ETH_P_IP) ||
key->basic.n_proto == htons(ETH_P_IPV6)) &&
fl_dump_key_val(skb, &key->basic.ip_proto, TCA_FLOWER_KEY_IP_PROTO,
&mask->basic.ip_proto, TCA_FLOWER_UNSPEC,
sizeof(key->basic.ip_proto)))
goto nla_put_failure;
if (key->control.addr_type == FLOW_DISSECTOR_KEY_IPV4_ADDRS &&
(fl_dump_key_val(skb, &key->ipv4.src, TCA_FLOWER_KEY_IPV4_SRC,
&mask->ipv4.src, TCA_FLOWER_KEY_IPV4_SRC_MASK,
sizeof(key->ipv4.src)) ||
fl_dump_key_val(skb, &key->ipv4.dst, TCA_FLOWER_KEY_IPV4_DST,
&mask->ipv4.dst, TCA_FLOWER_KEY_IPV4_DST_MASK,
sizeof(key->ipv4.dst))))
goto nla_put_failure;
else if (key->control.addr_type == FLOW_DISSECTOR_KEY_IPV6_ADDRS &&
(fl_dump_key_val(skb, &key->ipv6.src, TCA_FLOWER_KEY_IPV6_SRC,
&mask->ipv6.src, TCA_FLOWER_KEY_IPV6_SRC_MASK,
sizeof(key->ipv6.src)) ||
fl_dump_key_val(skb, &key->ipv6.dst, TCA_FLOWER_KEY_IPV6_DST,
&mask->ipv6.dst, TCA_FLOWER_KEY_IPV6_DST_MASK,
sizeof(key->ipv6.dst))))
goto nla_put_failure;
if (key->basic.ip_proto == IPPROTO_TCP &&
(fl_dump_key_val(skb, &key->tp.src, TCA_FLOWER_KEY_TCP_SRC,
&mask->tp.src, TCA_FLOWER_KEY_TCP_SRC_MASK,
sizeof(key->tp.src)) ||
fl_dump_key_val(skb, &key->tp.dst, TCA_FLOWER_KEY_TCP_DST,
&mask->tp.dst, TCA_FLOWER_KEY_TCP_DST_MASK,
sizeof(key->tp.dst))))
goto nla_put_failure;
else if (key->basic.ip_proto == IPPROTO_UDP &&
(fl_dump_key_val(skb, &key->tp.src, TCA_FLOWER_KEY_UDP_SRC,
&mask->tp.src, TCA_FLOWER_KEY_UDP_SRC_MASK,
sizeof(key->tp.src)) ||
fl_dump_key_val(skb, &key->tp.dst, TCA_FLOWER_KEY_UDP_DST,
&mask->tp.dst, TCA_FLOWER_KEY_UDP_DST_MASK,
sizeof(key->tp.dst))))
goto nla_put_failure;
else if (key->basic.ip_proto == IPPROTO_SCTP &&
(fl_dump_key_val(skb, &key->tp.src, TCA_FLOWER_KEY_SCTP_SRC,
&mask->tp.src, TCA_FLOWER_KEY_SCTP_SRC_MASK,
sizeof(key->tp.src)) ||
fl_dump_key_val(skb, &key->tp.dst, TCA_FLOWER_KEY_SCTP_DST,
&mask->tp.dst, TCA_FLOWER_KEY_SCTP_DST_MASK,
sizeof(key->tp.dst))))
goto nla_put_failure;
if (key->enc_control.addr_type == FLOW_DISSECTOR_KEY_IPV4_ADDRS &&
(fl_dump_key_val(skb, &key->enc_ipv4.src,
TCA_FLOWER_KEY_ENC_IPV4_SRC, &mask->enc_ipv4.src,
TCA_FLOWER_KEY_ENC_IPV4_SRC_MASK,
sizeof(key->enc_ipv4.src)) ||
fl_dump_key_val(skb, &key->enc_ipv4.dst,
TCA_FLOWER_KEY_ENC_IPV4_DST, &mask->enc_ipv4.dst,
TCA_FLOWER_KEY_ENC_IPV4_DST_MASK,
sizeof(key->enc_ipv4.dst))))
goto nla_put_failure;
else if (key->enc_control.addr_type == FLOW_DISSECTOR_KEY_IPV6_ADDRS &&
(fl_dump_key_val(skb, &key->enc_ipv6.src,
TCA_FLOWER_KEY_ENC_IPV6_SRC, &mask->enc_ipv6.src,
TCA_FLOWER_KEY_ENC_IPV6_SRC_MASK,
sizeof(key->enc_ipv6.src)) ||
fl_dump_key_val(skb, &key->enc_ipv6.dst,
TCA_FLOWER_KEY_ENC_IPV6_DST,
&mask->enc_ipv6.dst,
TCA_FLOWER_KEY_ENC_IPV6_DST_MASK,
sizeof(key->enc_ipv6.dst))))
goto nla_put_failure;
if (fl_dump_key_val(skb, &key->enc_key_id, TCA_FLOWER_KEY_ENC_KEY_ID,
&mask->enc_key_id, TCA_FLOWER_UNSPEC,
sizeof(key->enc_key_id)) ||
fl_dump_key_val(skb, &key->enc_tp.src,
TCA_FLOWER_KEY_ENC_UDP_SRC_PORT,
&mask->enc_tp.src,
TCA_FLOWER_KEY_ENC_UDP_SRC_PORT_MASK,
sizeof(key->enc_tp.src)) ||
fl_dump_key_val(skb, &key->enc_tp.dst,
TCA_FLOWER_KEY_ENC_UDP_DST_PORT,
&mask->enc_tp.dst,
TCA_FLOWER_KEY_ENC_UDP_DST_PORT_MASK,
sizeof(key->enc_tp.dst)))
goto nla_put_failure;
nla_put_u32(skb, TCA_FLOWER_FLAGS, f->flags);
if (tcf_exts_dump(skb, &f->exts))
goto nla_put_failure;
nla_nest_end(skb, nest);
if (tcf_exts_dump_stats(skb, &f->exts) < 0)
goto nla_put_failure;
return skb->len;
nla_put_failure:
nla_nest_cancel(skb, nest);
return -1;
}
static struct tcf_proto_ops cls_fl_ops __read_mostly = {
.kind = "flower",
.classify = fl_classify,
.init = fl_init,
.destroy = fl_destroy,
.get = fl_get,
.change = fl_change,
.delete = fl_delete,
.walk = fl_walk,
.dump = fl_dump,
.owner = THIS_MODULE,
};
static int __init cls_fl_init(void)
{
return register_tcf_proto_ops(&cls_fl_ops);
}
static void __exit cls_fl_exit(void)
{
unregister_tcf_proto_ops(&cls_fl_ops);
}
module_init(cls_fl_init);
module_exit(cls_fl_exit);
MODULE_AUTHOR("Jiri Pirko <jiri@resnulli.us>");
MODULE_DESCRIPTION("Flower classifier");
MODULE_LICENSE("GPL v2");