linux/net/sched/cls_cgroup.c

221 lines
4.9 KiB
C
Raw Normal View History

/*
* net/sched/cls_cgroup.c Control Group Classifier
*
* 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: Thomas Graf <tgraf@suug.ch>
*/
#include <linux/module.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 16:04:11 +08:00
#include <linux/slab.h>
#include <linux/skbuff.h>
cls_cgroup: Store classid in struct sock Up until now cls_cgroup has relied on fetching the classid out of the current executing thread. This runs into trouble when a packet processing is delayed in which case it may execute out of another thread's context. Furthermore, even when a packet is not delayed we may fail to classify it if soft IRQs have been disabled, because this scenario is indistinguishable from one where a packet unrelated to the current thread is processed by a real soft IRQ. In fact, the current semantics is inherently broken, as a single skb may be constructed out of the writes of two different tasks. A different manifestation of this problem is when the TCP stack transmits in response of an incoming ACK. This is currently unclassified. As we already have a concept of packet ownership for accounting purposes in the skb->sk pointer, this is a natural place to store the classid in a persistent manner. This patch adds the cls_cgroup classid in struct sock, filling up an existing hole on 64-bit :) The value is set at socket creation time. So all sockets created via socket(2) automatically gains the ID of the thread creating it. Whenever another process touches the socket by either reading or writing to it, we will change the socket classid to that of the process if it has a valid (non-zero) classid. For sockets created on inbound connections through accept(2), we inherit the classid of the original listening socket through sk_clone, possibly preceding the actual accept(2) call. In order to minimise risks, I have not made this the authoritative classid. For now it is only used as a backup when we execute with soft IRQs disabled. Once we're completely happy with its semantics we can use it as the sole classid. Footnote: I have rearranged the error path on cls_group module creation. If we didn't do this, then there is a window where someone could create a tc rule using cls_group before the cgroup subsystem has been registered. Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au> Signed-off-by: David S. Miller <davem@davemloft.net>
2010-05-24 15:12:34 +08:00
#include <linux/rcupdate.h>
#include <net/rtnetlink.h>
#include <net/pkt_cls.h>
cls_cgroup: Store classid in struct sock Up until now cls_cgroup has relied on fetching the classid out of the current executing thread. This runs into trouble when a packet processing is delayed in which case it may execute out of another thread's context. Furthermore, even when a packet is not delayed we may fail to classify it if soft IRQs have been disabled, because this scenario is indistinguishable from one where a packet unrelated to the current thread is processed by a real soft IRQ. In fact, the current semantics is inherently broken, as a single skb may be constructed out of the writes of two different tasks. A different manifestation of this problem is when the TCP stack transmits in response of an incoming ACK. This is currently unclassified. As we already have a concept of packet ownership for accounting purposes in the skb->sk pointer, this is a natural place to store the classid in a persistent manner. This patch adds the cls_cgroup classid in struct sock, filling up an existing hole on 64-bit :) The value is set at socket creation time. So all sockets created via socket(2) automatically gains the ID of the thread creating it. Whenever another process touches the socket by either reading or writing to it, we will change the socket classid to that of the process if it has a valid (non-zero) classid. For sockets created on inbound connections through accept(2), we inherit the classid of the original listening socket through sk_clone, possibly preceding the actual accept(2) call. In order to minimise risks, I have not made this the authoritative classid. For now it is only used as a backup when we execute with soft IRQs disabled. Once we're completely happy with its semantics we can use it as the sole classid. Footnote: I have rearranged the error path on cls_group module creation. If we didn't do this, then there is a window where someone could create a tc rule using cls_group before the cgroup subsystem has been registered. Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au> Signed-off-by: David S. Miller <davem@davemloft.net>
2010-05-24 15:12:34 +08:00
#include <net/sock.h>
#include <net/cls_cgroup.h>
struct cls_cgroup_head {
u32 handle;
struct tcf_exts exts;
struct tcf_ematch_tree ematches;
struct tcf_proto *tp;
struct rcu_head rcu;
};
static int cls_cgroup_classify(struct sk_buff *skb, const struct tcf_proto *tp,
struct tcf_result *res)
{
struct cls_cgroup_head *head = rcu_dereference_bh(tp->root);
u32 classid = task_get_classid(skb);
if (!classid)
return -1;
if (!tcf_em_tree_match(skb, &head->ematches, NULL))
return -1;
res->classid = classid;
res->class = 0;
return tcf_exts_exec(skb, &head->exts, res);
}
static unsigned long cls_cgroup_get(struct tcf_proto *tp, u32 handle)
{
return 0UL;
}
static int cls_cgroup_init(struct tcf_proto *tp)
{
return 0;
}
static const struct nla_policy cgroup_policy[TCA_CGROUP_MAX + 1] = {
[TCA_CGROUP_EMATCHES] = { .type = NLA_NESTED },
};
static void cls_cgroup_destroy_rcu(struct rcu_head *root)
{
struct cls_cgroup_head *head = container_of(root,
struct cls_cgroup_head,
rcu);
tcf_exts_destroy(&head->exts);
tcf_em_tree_destroy(&head->ematches);
kfree(head);
}
static int cls_cgroup_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 nlattr *tb[TCA_CGROUP_MAX + 1];
struct cls_cgroup_head *head = rtnl_dereference(tp->root);
struct cls_cgroup_head *new;
struct tcf_ematch_tree t;
struct tcf_exts e;
int err;
if (!tca[TCA_OPTIONS])
return -EINVAL;
if (!head && !handle)
return -EINVAL;
if (head && handle != head->handle)
return -ENOENT;
new = kzalloc(sizeof(*head), GFP_KERNEL);
if (!new)
return -ENOBUFS;
err = tcf_exts_init(&new->exts, TCA_CGROUP_ACT, TCA_CGROUP_POLICE);
if (err < 0)
goto errout;
new->handle = handle;
new->tp = tp;
err = nla_parse_nested(tb, TCA_CGROUP_MAX, tca[TCA_OPTIONS],
cgroup_policy, NULL);
if (err < 0)
goto errout;
err = tcf_exts_init(&e, TCA_CGROUP_ACT, TCA_CGROUP_POLICE);
if (err < 0)
goto errout;
err = tcf_exts_validate(net, tp, tb, tca[TCA_RATE], &e, ovr);
if (err < 0) {
tcf_exts_destroy(&e);
goto errout;
}
err = tcf_em_tree_validate(tp, tb[TCA_CGROUP_EMATCHES], &t);
if (err < 0) {
tcf_exts_destroy(&e);
goto errout;
}
tcf_exts_change(tp, &new->exts, &e);
tcf_em_tree_change(tp, &new->ematches, &t);
rcu_assign_pointer(tp->root, new);
if (head)
call_rcu(&head->rcu, cls_cgroup_destroy_rcu);
return 0;
errout:
tcf_exts_destroy(&new->exts);
kfree(new);
return err;
}
static bool cls_cgroup_destroy(struct tcf_proto *tp, bool force)
{
struct cls_cgroup_head *head = rtnl_dereference(tp->root);
if (!force)
return false;
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 08:18:01 +08:00
/* Head can still be NULL due to cls_cgroup_init(). */
if (head)
call_rcu(&head->rcu, cls_cgroup_destroy_rcu);
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 08:18:01 +08:00
return true;
}
static int cls_cgroup_delete(struct tcf_proto *tp, unsigned long arg)
{
return -EOPNOTSUPP;
}
static void cls_cgroup_walk(struct tcf_proto *tp, struct tcf_walker *arg)
{
struct cls_cgroup_head *head = rtnl_dereference(tp->root);
if (arg->count < arg->skip)
goto skip;
if (arg->fn(tp, (unsigned long) head, arg) < 0) {
arg->stop = 1;
return;
}
skip:
arg->count++;
}
static int cls_cgroup_dump(struct net *net, struct tcf_proto *tp, unsigned long fh,
struct sk_buff *skb, struct tcmsg *t)
{
struct cls_cgroup_head *head = rtnl_dereference(tp->root);
struct nlattr *nest;
t->tcm_handle = head->handle;
nest = nla_nest_start(skb, TCA_OPTIONS);
if (nest == NULL)
goto nla_put_failure;
if (tcf_exts_dump(skb, &head->exts) < 0 ||
tcf_em_tree_dump(skb, &head->ematches, TCA_CGROUP_EMATCHES) < 0)
goto nla_put_failure;
nla_nest_end(skb, nest);
if (tcf_exts_dump_stats(skb, &head->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_cgroup_ops __read_mostly = {
.kind = "cgroup",
.init = cls_cgroup_init,
.change = cls_cgroup_change,
.classify = cls_cgroup_classify,
.destroy = cls_cgroup_destroy,
.get = cls_cgroup_get,
.delete = cls_cgroup_delete,
.walk = cls_cgroup_walk,
.dump = cls_cgroup_dump,
.owner = THIS_MODULE,
};
static int __init init_cgroup_cls(void)
{
return register_tcf_proto_ops(&cls_cgroup_ops);
}
static void __exit exit_cgroup_cls(void)
{
unregister_tcf_proto_ops(&cls_cgroup_ops);
}
module_init(init_cgroup_cls);
module_exit(exit_cgroup_cls);
MODULE_LICENSE("GPL");