linux_dsm_epyc7002/net/sched/act_api.c

1755 lines
41 KiB
C
Raw Normal View History

/*
* net/sched/act_api.c Packet action API.
*
* 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.
*
* Author: Jamal Hadi Salim
*
*
*/
#include <linux/types.h>
#include <linux/kernel.h>
#include <linux/string.h>
#include <linux/errno.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 15:04:11 +07:00
#include <linux/slab.h>
#include <linux/skbuff.h>
#include <linux/init.h>
#include <linux/kmod.h>
#include <linux/err.h>
#include <linux/module.h>
#include <linux/rhashtable.h>
#include <linux/list.h>
#include <net/net_namespace.h>
#include <net/sock.h>
#include <net/sch_generic.h>
#include <net/pkt_cls.h>
#include <net/act_api.h>
#include <net/netlink.h>
static int tcf_action_goto_chain_init(struct tc_action *a, struct tcf_proto *tp)
{
u32 chain_index = a->tcfa_action & TC_ACT_EXT_VAL_MASK;
if (!tp)
return -EINVAL;
a->goto_chain = tcf_chain_get_by_act(tp->chain->block, chain_index);
if (!a->goto_chain)
return -ENOMEM;
return 0;
}
static void tcf_action_goto_chain_fini(struct tc_action *a)
{
tcf_chain_put_by_act(a->goto_chain);
}
static void tcf_action_goto_chain_exec(const struct tc_action *a,
struct tcf_result *res)
{
const struct tcf_chain *chain = a->goto_chain;
res->goto_tp = rcu_dereference_bh(chain->filter_chain);
}
static void tcf_free_cookie_rcu(struct rcu_head *p)
{
struct tc_cookie *cookie = container_of(p, struct tc_cookie, rcu);
kfree(cookie->data);
kfree(cookie);
}
static void tcf_set_action_cookie(struct tc_cookie __rcu **old_cookie,
struct tc_cookie *new_cookie)
{
struct tc_cookie *old;
old = xchg((__force struct tc_cookie **)old_cookie, new_cookie);
if (old)
call_rcu(&old->rcu, tcf_free_cookie_rcu);
}
/* XXX: For standalone actions, we don't need a RCU grace period either, because
* actions are always connected to filters and filters are already destroyed in
* RCU callbacks, so after a RCU grace period actions are already disconnected
* from filters. Readers later can not find us.
*/
static void free_tcf(struct tc_action *p)
{
free_percpu(p->cpu_bstats);
free_percpu(p->cpu_bstats_hw);
free_percpu(p->cpu_qstats);
tcf_set_action_cookie(&p->act_cookie, NULL);
if (p->goto_chain)
tcf_action_goto_chain_fini(p);
kfree(p);
}
static void tcf_action_cleanup(struct tc_action *p)
{
if (p->ops->cleanup)
p->ops->cleanup(p);
gen_kill_estimator(&p->tcfa_rate_est);
free_tcf(p);
}
static int __tcf_action_put(struct tc_action *p, bool bind)
{
struct tcf_idrinfo *idrinfo = p->idrinfo;
if (refcount_dec_and_mutex_lock(&p->tcfa_refcnt, &idrinfo->lock)) {
if (bind)
atomic_dec(&p->tcfa_bindcnt);
idr_remove(&idrinfo->action_idr, p->tcfa_index);
mutex_unlock(&idrinfo->lock);
tcf_action_cleanup(p);
return 1;
}
if (bind)
atomic_dec(&p->tcfa_bindcnt);
return 0;
}
int __tcf_idr_release(struct tc_action *p, bool bind, bool strict)
{
int ret = 0;
/* Release with strict==1 and bind==0 is only called through act API
* interface (classifiers always bind). Only case when action with
* positive reference count and zero bind count can exist is when it was
* also created with act API (unbinding last classifier will destroy the
* action if it was created by classifier). So only case when bind count
* can be changed after initial check is when unbound action is
* destroyed by act API while classifier binds to action with same id
* concurrently. This result either creation of new action(same behavior
* as before), or reusing existing action if concurrent process
* increments reference count before action is deleted. Both scenarios
* are acceptable.
*/
if (p) {
if (!bind && strict && atomic_read(&p->tcfa_bindcnt) > 0)
return -EPERM;
if (__tcf_action_put(p, bind))
ret = ACT_P_DELETED;
}
net: sched: fix refcount imbalance in actions Since commit 55334a5db5cd ("net_sched: act: refuse to remove bound action outside"), we end up with a wrong reference count for a tc action. Test case 1: FOO="1,6 0 0 4294967295," BAR="1,6 0 0 4294967294," tc filter add dev foo parent 1: bpf bytecode "$FOO" flowid 1:1 \ action bpf bytecode "$FOO" tc actions show action bpf action order 0: bpf bytecode '1,6 0 0 4294967295' default-action pipe index 1 ref 1 bind 1 tc actions replace action bpf bytecode "$BAR" index 1 tc actions show action bpf action order 0: bpf bytecode '1,6 0 0 4294967294' default-action pipe index 1 ref 2 bind 1 tc actions replace action bpf bytecode "$FOO" index 1 tc actions show action bpf action order 0: bpf bytecode '1,6 0 0 4294967295' default-action pipe index 1 ref 3 bind 1 Test case 2: FOO="1,6 0 0 4294967295," tc filter add dev foo parent 1: bpf bytecode "$FOO" flowid 1:1 action ok tc actions show action gact action order 0: gact action pass random type none pass val 0 index 1 ref 1 bind 1 tc actions add action drop index 1 RTNETLINK answers: File exists [...] tc actions show action gact action order 0: gact action pass random type none pass val 0 index 1 ref 2 bind 1 tc actions add action drop index 1 RTNETLINK answers: File exists [...] tc actions show action gact action order 0: gact action pass random type none pass val 0 index 1 ref 3 bind 1 What happens is that in tcf_hash_check(), we check tcf_common for a given index and increase tcfc_refcnt and conditionally tcfc_bindcnt when we've found an existing action. Now there are the following cases: 1) We do a late binding of an action. In that case, we leave the tcfc_refcnt/tcfc_bindcnt increased and are done with the ->init() handler. This is correctly handeled. 2) We replace the given action, or we try to add one without replacing and find out that the action at a specific index already exists (thus, we go out with error in that case). In case of 2), we have to undo the reference count increase from tcf_hash_check() in the tcf_hash_check() function. Currently, we fail to do so because of the 'tcfc_bindcnt > 0' check which bails out early with an -EPERM error. Now, while commit 55334a5db5cd prevents 'tc actions del action ...' on an already classifier-bound action to drop the reference count (which could then become negative, wrap around etc), this restriction only accounts for invocations outside a specific action's ->init() handler. One possible solution would be to add a flag thus we possibly trigger the -EPERM ony in situations where it is indeed relevant. After the patch, above test cases have correct reference count again. Fixes: 55334a5db5cd ("net_sched: act: refuse to remove bound action outside") Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Reviewed-by: Cong Wang <cwang@twopensource.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-07-30 04:35:25 +07:00
return ret;
}
EXPORT_SYMBOL(__tcf_idr_release);
static size_t tcf_action_shared_attrs_size(const struct tc_action *act)
{
struct tc_cookie *act_cookie;
u32 cookie_len = 0;
rcu_read_lock();
act_cookie = rcu_dereference(act->act_cookie);
if (act_cookie)
cookie_len = nla_total_size(act_cookie->len);
rcu_read_unlock();
return nla_total_size(0) /* action number nested */
+ nla_total_size(IFNAMSIZ) /* TCA_ACT_KIND */
+ cookie_len /* TCA_ACT_COOKIE */
+ nla_total_size(0) /* TCA_ACT_STATS nested */
/* TCA_STATS_BASIC */
+ nla_total_size_64bit(sizeof(struct gnet_stats_basic))
/* TCA_STATS_QUEUE */
+ nla_total_size_64bit(sizeof(struct gnet_stats_queue))
+ nla_total_size(0) /* TCA_OPTIONS nested */
+ nla_total_size(sizeof(struct tcf_t)); /* TCA_GACT_TM */
}
static size_t tcf_action_full_attrs_size(size_t sz)
{
return NLMSG_HDRLEN /* struct nlmsghdr */
+ sizeof(struct tcamsg)
+ nla_total_size(0) /* TCA_ACT_TAB nested */
+ sz;
}
static size_t tcf_action_fill_size(const struct tc_action *act)
{
size_t sz = tcf_action_shared_attrs_size(act);
if (act->ops->get_fill_size)
return act->ops->get_fill_size(act) + sz;
return sz;
}
static int tcf_dump_walker(struct tcf_idrinfo *idrinfo, struct sk_buff *skb,
struct netlink_callback *cb)
{
int err = 0, index = -1, s_i = 0, n_i = 0;
net sched actions: dump more than TCA_ACT_MAX_PRIO actions per batch When you dump hundreds of thousands of actions, getting only 32 per dump batch even when the socket buffer and memory allocations allow is inefficient. With this change, the user will get as many as possibly fitting within the given constraints available to the kernel. The top level action TLV space is extended. An attribute TCA_ROOT_FLAGS is used to carry flags; flag TCA_FLAG_LARGE_DUMP_ON is set by the user indicating the user is capable of processing these large dumps. Older user space which doesnt set this flag doesnt get the large (than 32) batches. The kernel uses the TCA_ROOT_COUNT attribute to tell the user how many actions are put in a single batch. As such user space app knows how long to iterate (independent of the type of action being dumped) instead of hardcoded maximum of 32 thus maintaining backward compat. Some results dumping 1.5M actions below: first an unpatched tc which doesnt understand these features... prompt$ time -p tc actions ls action gact | grep index | wc -l 1500000 real 1388.43 user 2.07 sys 1386.79 Now lets see a patched tc which sets the correct flags when requesting a dump: prompt$ time -p updatedtc actions ls action gact | grep index | wc -l 1500000 real 178.13 user 2.02 sys 176.96 That is about 8x performance improvement for tc app which sets its receive buffer to about 32K. Signed-off-by: Jamal Hadi Salim <jhs@mojatatu.com> Reviewed-by: Jiri Pirko <jiri@mellanox.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-07-31 00:24:51 +07:00
u32 act_flags = cb->args[2];
net sched actions: add time filter for action dumping This patch adds support for filtering based on time since last used. When we are dumping a large number of actions it is useful to have the option of filtering based on when the action was last used to reduce the amount of data crossing to user space. With this patch the user space app sets the TCA_ROOT_TIME_DELTA attribute with the value in milliseconds with "time of interest since now". The kernel converts this to jiffies and does the filtering comparison matching entries that have seen activity since then and returns them to user space. Old kernels and old tc continue to work in legacy mode since they dont specify this attribute. Some example (we have 400 actions bound to 400 filters); at installation time. Using updated when tc setting the time of interest to 120 seconds earlier (we see 400 actions): prompt$ hackedtc actions ls action gact since 120000| grep index | wc -l 400 go get some coffee and wait for > 120 seconds and try again: prompt$ hackedtc actions ls action gact since 120000 | grep index | wc -l 0 Lets see a filter bound to one of these actions: .... filter pref 10 u32 filter pref 10 u32 fh 800: ht divisor 1 filter pref 10 u32 fh 800::800 order 2048 key ht 800 bkt 0 flowid 1:10 (rule hit 2 success 1) match 7f000002/ffffffff at 12 (success 1 ) action order 1: gact action pass random type none pass val 0 index 23 ref 2 bind 1 installed 1145 sec used 802 sec Action statistics: Sent 84 bytes 1 pkt (dropped 0, overlimits 0 requeues 0) backlog 0b 0p requeues 0 .... that coffee took long, no? It was good. Now lets ping -c 1 127.0.0.2, then run the actions again: prompt$ hackedtc actions ls action gact since 120 | grep index | wc -l 1 More details please: prompt$ hackedtc -s actions ls action gact since 120000 action order 0: gact action pass random type none pass val 0 index 23 ref 2 bind 1 installed 1270 sec used 30 sec Action statistics: Sent 168 bytes 2 pkt (dropped 0, overlimits 0 requeues 0) backlog 0b 0p requeues 0 And the filter? filter pref 10 u32 filter pref 10 u32 fh 800: ht divisor 1 filter pref 10 u32 fh 800::800 order 2048 key ht 800 bkt 0 flowid 1:10 (rule hit 4 success 2) match 7f000002/ffffffff at 12 (success 2 ) action order 1: gact action pass random type none pass val 0 index 23 ref 2 bind 1 installed 1324 sec used 84 sec Action statistics: Sent 168 bytes 2 pkt (dropped 0, overlimits 0 requeues 0) backlog 0b 0p requeues 0 Signed-off-by: Jamal Hadi Salim <jhs@mojatatu.com> Reviewed-by: Jiri Pirko <jiri@mellanox.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-07-31 00:24:52 +07:00
unsigned long jiffy_since = cb->args[3];
struct nlattr *nest;
struct idr *idr = &idrinfo->action_idr;
struct tc_action *p;
unsigned long id = 1;
mutex_lock(&idrinfo->lock);
s_i = cb->args[0];
idr_for_each_entry_ul(idr, p, id) {
index++;
if (index < s_i)
continue;
if (jiffy_since &&
time_after(jiffy_since,
(unsigned long)p->tcfa_tm.lastuse))
continue;
nest = nla_nest_start(skb, n_i);
net sched actions: fix dumping which requires several messages to user space Fixes a bug in the tcf_dump_walker function that can cause some actions to not be reported when dumping a large number of actions. This issue became more aggrevated when cookies feature was added. In particular this issue is manifest when large cookie values are assigned to the actions and when enough actions are created that the resulting table must be dumped in multiple batches. The number of actions returned in each batch is limited by the total number of actions and the memory buffer size. With small cookies the numeric limit is reached before the buffer size limit, which avoids the code path triggering this bug. When large cookies are used buffer fills before the numeric limit, and the erroneous code path is hit. For example after creating 32 csum actions with the cookie aaaabbbbccccdddd $ tc actions ls action csum total acts 26 action order 0: csum (tcp) action continue index 1 ref 1 bind 0 cookie aaaabbbbccccdddd ..... action order 25: csum (tcp) action continue index 26 ref 1 bind 0 cookie aaaabbbbccccdddd total acts 6 action order 0: csum (tcp) action continue index 28 ref 1 bind 0 cookie aaaabbbbccccdddd ...... action order 5: csum (tcp) action continue index 32 ref 1 bind 0 cookie aaaabbbbccccdddd Note that the action with index 27 is omitted from the report. Fixes: 4b3550ef530c ("[NET_SCHED]: Use nla_nest_start/nla_nest_end")" Signed-off-by: Craig Dillabaugh <cdillaba@mojatatu.com> Acked-by: Jamal Hadi Salim <jhs@mojatatu.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-03-27 01:58:32 +07:00
if (!nest) {
index--;
goto nla_put_failure;
net sched actions: fix dumping which requires several messages to user space Fixes a bug in the tcf_dump_walker function that can cause some actions to not be reported when dumping a large number of actions. This issue became more aggrevated when cookies feature was added. In particular this issue is manifest when large cookie values are assigned to the actions and when enough actions are created that the resulting table must be dumped in multiple batches. The number of actions returned in each batch is limited by the total number of actions and the memory buffer size. With small cookies the numeric limit is reached before the buffer size limit, which avoids the code path triggering this bug. When large cookies are used buffer fills before the numeric limit, and the erroneous code path is hit. For example after creating 32 csum actions with the cookie aaaabbbbccccdddd $ tc actions ls action csum total acts 26 action order 0: csum (tcp) action continue index 1 ref 1 bind 0 cookie aaaabbbbccccdddd ..... action order 25: csum (tcp) action continue index 26 ref 1 bind 0 cookie aaaabbbbccccdddd total acts 6 action order 0: csum (tcp) action continue index 28 ref 1 bind 0 cookie aaaabbbbccccdddd ...... action order 5: csum (tcp) action continue index 32 ref 1 bind 0 cookie aaaabbbbccccdddd Note that the action with index 27 is omitted from the report. Fixes: 4b3550ef530c ("[NET_SCHED]: Use nla_nest_start/nla_nest_end")" Signed-off-by: Craig Dillabaugh <cdillaba@mojatatu.com> Acked-by: Jamal Hadi Salim <jhs@mojatatu.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-03-27 01:58:32 +07:00
}
err = tcf_action_dump_1(skb, p, 0, 0);
if (err < 0) {
index--;
nlmsg_trim(skb, nest);
goto done;
}
nla_nest_end(skb, nest);
n_i++;
if (!(act_flags & TCA_FLAG_LARGE_DUMP_ON) &&
n_i >= TCA_ACT_MAX_PRIO)
goto done;
}
done:
net sched actions: add time filter for action dumping This patch adds support for filtering based on time since last used. When we are dumping a large number of actions it is useful to have the option of filtering based on when the action was last used to reduce the amount of data crossing to user space. With this patch the user space app sets the TCA_ROOT_TIME_DELTA attribute with the value in milliseconds with "time of interest since now". The kernel converts this to jiffies and does the filtering comparison matching entries that have seen activity since then and returns them to user space. Old kernels and old tc continue to work in legacy mode since they dont specify this attribute. Some example (we have 400 actions bound to 400 filters); at installation time. Using updated when tc setting the time of interest to 120 seconds earlier (we see 400 actions): prompt$ hackedtc actions ls action gact since 120000| grep index | wc -l 400 go get some coffee and wait for > 120 seconds and try again: prompt$ hackedtc actions ls action gact since 120000 | grep index | wc -l 0 Lets see a filter bound to one of these actions: .... filter pref 10 u32 filter pref 10 u32 fh 800: ht divisor 1 filter pref 10 u32 fh 800::800 order 2048 key ht 800 bkt 0 flowid 1:10 (rule hit 2 success 1) match 7f000002/ffffffff at 12 (success 1 ) action order 1: gact action pass random type none pass val 0 index 23 ref 2 bind 1 installed 1145 sec used 802 sec Action statistics: Sent 84 bytes 1 pkt (dropped 0, overlimits 0 requeues 0) backlog 0b 0p requeues 0 .... that coffee took long, no? It was good. Now lets ping -c 1 127.0.0.2, then run the actions again: prompt$ hackedtc actions ls action gact since 120 | grep index | wc -l 1 More details please: prompt$ hackedtc -s actions ls action gact since 120000 action order 0: gact action pass random type none pass val 0 index 23 ref 2 bind 1 installed 1270 sec used 30 sec Action statistics: Sent 168 bytes 2 pkt (dropped 0, overlimits 0 requeues 0) backlog 0b 0p requeues 0 And the filter? filter pref 10 u32 filter pref 10 u32 fh 800: ht divisor 1 filter pref 10 u32 fh 800::800 order 2048 key ht 800 bkt 0 flowid 1:10 (rule hit 4 success 2) match 7f000002/ffffffff at 12 (success 2 ) action order 1: gact action pass random type none pass val 0 index 23 ref 2 bind 1 installed 1324 sec used 84 sec Action statistics: Sent 168 bytes 2 pkt (dropped 0, overlimits 0 requeues 0) backlog 0b 0p requeues 0 Signed-off-by: Jamal Hadi Salim <jhs@mojatatu.com> Reviewed-by: Jiri Pirko <jiri@mellanox.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-07-31 00:24:52 +07:00
if (index >= 0)
cb->args[0] = index + 1;
mutex_unlock(&idrinfo->lock);
net sched actions: dump more than TCA_ACT_MAX_PRIO actions per batch When you dump hundreds of thousands of actions, getting only 32 per dump batch even when the socket buffer and memory allocations allow is inefficient. With this change, the user will get as many as possibly fitting within the given constraints available to the kernel. The top level action TLV space is extended. An attribute TCA_ROOT_FLAGS is used to carry flags; flag TCA_FLAG_LARGE_DUMP_ON is set by the user indicating the user is capable of processing these large dumps. Older user space which doesnt set this flag doesnt get the large (than 32) batches. The kernel uses the TCA_ROOT_COUNT attribute to tell the user how many actions are put in a single batch. As such user space app knows how long to iterate (independent of the type of action being dumped) instead of hardcoded maximum of 32 thus maintaining backward compat. Some results dumping 1.5M actions below: first an unpatched tc which doesnt understand these features... prompt$ time -p tc actions ls action gact | grep index | wc -l 1500000 real 1388.43 user 2.07 sys 1386.79 Now lets see a patched tc which sets the correct flags when requesting a dump: prompt$ time -p updatedtc actions ls action gact | grep index | wc -l 1500000 real 178.13 user 2.02 sys 176.96 That is about 8x performance improvement for tc app which sets its receive buffer to about 32K. Signed-off-by: Jamal Hadi Salim <jhs@mojatatu.com> Reviewed-by: Jiri Pirko <jiri@mellanox.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-07-31 00:24:51 +07:00
if (n_i) {
if (act_flags & TCA_FLAG_LARGE_DUMP_ON)
cb->args[1] = n_i;
}
return n_i;
nla_put_failure:
nla_nest_cancel(skb, nest);
goto done;
}
static int tcf_idr_release_unsafe(struct tc_action *p)
{
if (atomic_read(&p->tcfa_bindcnt) > 0)
return -EPERM;
if (refcount_dec_and_test(&p->tcfa_refcnt)) {
idr_remove(&p->idrinfo->action_idr, p->tcfa_index);
tcf_action_cleanup(p);
return ACT_P_DELETED;
}
return 0;
}
static int tcf_del_walker(struct tcf_idrinfo *idrinfo, struct sk_buff *skb,
const struct tc_action_ops *ops)
{
struct nlattr *nest;
int n_i = 0;
int ret = -EINVAL;
struct idr *idr = &idrinfo->action_idr;
struct tc_action *p;
unsigned long id = 1;
nest = nla_nest_start(skb, 0);
if (nest == NULL)
goto nla_put_failure;
if (nla_put_string(skb, TCA_KIND, ops->kind))
goto nla_put_failure;
mutex_lock(&idrinfo->lock);
idr_for_each_entry_ul(idr, p, id) {
ret = tcf_idr_release_unsafe(p);
if (ret == ACT_P_DELETED) {
module_put(ops->owner);
n_i++;
} else if (ret < 0) {
mutex_unlock(&idrinfo->lock);
goto nla_put_failure;
}
}
mutex_unlock(&idrinfo->lock);
if (nla_put_u32(skb, TCA_FCNT, n_i))
goto nla_put_failure;
nla_nest_end(skb, nest);
return n_i;
nla_put_failure:
nla_nest_cancel(skb, nest);
return ret;
}
int tcf_generic_walker(struct tc_action_net *tn, struct sk_buff *skb,
struct netlink_callback *cb, int type,
const struct tc_action_ops *ops,
struct netlink_ext_ack *extack)
{
struct tcf_idrinfo *idrinfo = tn->idrinfo;
if (type == RTM_DELACTION) {
return tcf_del_walker(idrinfo, skb, ops);
} else if (type == RTM_GETACTION) {
return tcf_dump_walker(idrinfo, skb, cb);
} else {
WARN(1, "tcf_generic_walker: unknown command %d\n", type);
NL_SET_ERR_MSG(extack, "tcf_generic_walker: unknown command");
return -EINVAL;
}
}
EXPORT_SYMBOL(tcf_generic_walker);
int tcf_idr_search(struct tc_action_net *tn, struct tc_action **a, u32 index)
{
struct tcf_idrinfo *idrinfo = tn->idrinfo;
struct tc_action *p;
mutex_lock(&idrinfo->lock);
p = idr_find(&idrinfo->action_idr, index);
if (IS_ERR(p))
p = NULL;
else if (p)
refcount_inc(&p->tcfa_refcnt);
mutex_unlock(&idrinfo->lock);
if (p) {
*a = p;
return true;
}
return false;
}
EXPORT_SYMBOL(tcf_idr_search);
static int tcf_idr_delete_index(struct tcf_idrinfo *idrinfo, u32 index)
{
struct tc_action *p;
int ret = 0;
mutex_lock(&idrinfo->lock);
p = idr_find(&idrinfo->action_idr, index);
if (!p) {
mutex_unlock(&idrinfo->lock);
return -ENOENT;
}
if (!atomic_read(&p->tcfa_bindcnt)) {
if (refcount_dec_and_test(&p->tcfa_refcnt)) {
struct module *owner = p->ops->owner;
WARN_ON(p != idr_remove(&idrinfo->action_idr,
p->tcfa_index));
mutex_unlock(&idrinfo->lock);
tcf_action_cleanup(p);
module_put(owner);
return 0;
}
ret = 0;
} else {
ret = -EPERM;
}
mutex_unlock(&idrinfo->lock);
return ret;
}
int tcf_idr_create(struct tc_action_net *tn, u32 index, struct nlattr *est,
struct tc_action **a, const struct tc_action_ops *ops,
int bind, bool cpustats)
{
struct tc_action *p = kzalloc(ops->size, GFP_KERNEL);
struct tcf_idrinfo *idrinfo = tn->idrinfo;
int err = -ENOMEM;
if (unlikely(!p))
return -ENOMEM;
refcount_set(&p->tcfa_refcnt, 1);
if (bind)
atomic_set(&p->tcfa_bindcnt, 1);
if (cpustats) {
p->cpu_bstats = netdev_alloc_pcpu_stats(struct gnet_stats_basic_cpu);
if (!p->cpu_bstats)
goto err1;
p->cpu_bstats_hw = netdev_alloc_pcpu_stats(struct gnet_stats_basic_cpu);
if (!p->cpu_bstats_hw)
goto err2;
p->cpu_qstats = alloc_percpu(struct gnet_stats_queue);
if (!p->cpu_qstats)
goto err3;
}
spin_lock_init(&p->tcfa_lock);
p->tcfa_index = index;
p->tcfa_tm.install = jiffies;
p->tcfa_tm.lastuse = jiffies;
p->tcfa_tm.firstuse = 0;
if (est) {
err = gen_new_estimator(&p->tcfa_bstats, p->cpu_bstats,
&p->tcfa_rate_est,
&p->tcfa_lock, NULL, est);
if (err)
goto err4;
}
p->idrinfo = idrinfo;
p->ops = ops;
*a = p;
return 0;
err4:
free_percpu(p->cpu_qstats);
err3:
free_percpu(p->cpu_bstats_hw);
err2:
free_percpu(p->cpu_bstats);
err1:
kfree(p);
return err;
}
EXPORT_SYMBOL(tcf_idr_create);
void tcf_idr_insert(struct tc_action_net *tn, struct tc_action *a)
{
struct tcf_idrinfo *idrinfo = tn->idrinfo;
mutex_lock(&idrinfo->lock);
/* Replace ERR_PTR(-EBUSY) allocated by tcf_idr_check_alloc */
WARN_ON(!IS_ERR(idr_replace(&idrinfo->action_idr, a, a->tcfa_index)));
mutex_unlock(&idrinfo->lock);
}
EXPORT_SYMBOL(tcf_idr_insert);
/* Cleanup idr index that was allocated but not initialized. */
void tcf_idr_cleanup(struct tc_action_net *tn, u32 index)
{
struct tcf_idrinfo *idrinfo = tn->idrinfo;
mutex_lock(&idrinfo->lock);
/* Remove ERR_PTR(-EBUSY) allocated by tcf_idr_check_alloc */
WARN_ON(!IS_ERR(idr_remove(&idrinfo->action_idr, index)));
mutex_unlock(&idrinfo->lock);
}
EXPORT_SYMBOL(tcf_idr_cleanup);
/* Check if action with specified index exists. If actions is found, increments
* its reference and bind counters, and return 1. Otherwise insert temporary
* error pointer (to prevent concurrent users from inserting actions with same
* index) and return 0.
*/
int tcf_idr_check_alloc(struct tc_action_net *tn, u32 *index,
struct tc_action **a, int bind)
{
struct tcf_idrinfo *idrinfo = tn->idrinfo;
struct tc_action *p;
int ret;
again:
mutex_lock(&idrinfo->lock);
if (*index) {
p = idr_find(&idrinfo->action_idr, *index);
if (IS_ERR(p)) {
/* This means that another process allocated
* index but did not assign the pointer yet.
*/
mutex_unlock(&idrinfo->lock);
goto again;
}
if (p) {
refcount_inc(&p->tcfa_refcnt);
if (bind)
atomic_inc(&p->tcfa_bindcnt);
*a = p;
ret = 1;
} else {
*a = NULL;
ret = idr_alloc_u32(&idrinfo->action_idr, NULL, index,
*index, GFP_KERNEL);
if (!ret)
idr_replace(&idrinfo->action_idr,
ERR_PTR(-EBUSY), *index);
}
} else {
*index = 1;
*a = NULL;
ret = idr_alloc_u32(&idrinfo->action_idr, NULL, index,
UINT_MAX, GFP_KERNEL);
if (!ret)
idr_replace(&idrinfo->action_idr, ERR_PTR(-EBUSY),
*index);
}
mutex_unlock(&idrinfo->lock);
return ret;
}
EXPORT_SYMBOL(tcf_idr_check_alloc);
void tcf_idrinfo_destroy(const struct tc_action_ops *ops,
struct tcf_idrinfo *idrinfo)
{
struct idr *idr = &idrinfo->action_idr;
struct tc_action *p;
int ret;
unsigned long id = 1;
idr_for_each_entry_ul(idr, p, id) {
ret = __tcf_idr_release(p, false, true);
if (ret == ACT_P_DELETED)
module_put(ops->owner);
else if (ret < 0)
return;
}
idr_destroy(&idrinfo->action_idr);
}
EXPORT_SYMBOL(tcf_idrinfo_destroy);
static LIST_HEAD(act_base);
static DEFINE_RWLOCK(act_mod_lock);
int tcf_register_action(struct tc_action_ops *act,
struct pernet_operations *ops)
{
struct tc_action_ops *a;
int ret;
if (!act->act || !act->dump || !act->init || !act->walk || !act->lookup)
return -EINVAL;
/* We have to register pernet ops before making the action ops visible,
* otherwise tcf_action_init_1() could get a partially initialized
* netns.
*/
ret = register_pernet_subsys(ops);
if (ret)
return ret;
write_lock(&act_mod_lock);
list_for_each_entry(a, &act_base, head) {
if (act->type == a->type || (strcmp(act->kind, a->kind) == 0)) {
write_unlock(&act_mod_lock);
unregister_pernet_subsys(ops);
return -EEXIST;
}
}
list_add_tail(&act->head, &act_base);
write_unlock(&act_mod_lock);
return 0;
}
EXPORT_SYMBOL(tcf_register_action);
int tcf_unregister_action(struct tc_action_ops *act,
struct pernet_operations *ops)
{
struct tc_action_ops *a;
int err = -ENOENT;
write_lock(&act_mod_lock);
list_for_each_entry(a, &act_base, head) {
if (a == act) {
list_del(&act->head);
err = 0;
break;
}
}
write_unlock(&act_mod_lock);
if (!err)
unregister_pernet_subsys(ops);
return err;
}
EXPORT_SYMBOL(tcf_unregister_action);
/* lookup by name */
static struct tc_action_ops *tc_lookup_action_n(char *kind)
{
struct tc_action_ops *a, *res = NULL;
if (kind) {
read_lock(&act_mod_lock);
list_for_each_entry(a, &act_base, head) {
if (strcmp(kind, a->kind) == 0) {
if (try_module_get(a->owner))
res = a;
break;
}
}
read_unlock(&act_mod_lock);
}
return res;
}
/* lookup by nlattr */
static struct tc_action_ops *tc_lookup_action(struct nlattr *kind)
{
struct tc_action_ops *a, *res = NULL;
if (kind) {
read_lock(&act_mod_lock);
list_for_each_entry(a, &act_base, head) {
if (nla_strcmp(kind, a->kind) == 0) {
if (try_module_get(a->owner))
res = a;
break;
}
}
read_unlock(&act_mod_lock);
}
return res;
}
net sched actions: Complete the JUMPX opcode per discussion at netconf/netdev: When we have an action that is capable of branching (example a policer), we can achieve a continuation of the action graph by programming a "continue" where we find an exact replica of the same filter rule with a lower priority and the remainder of the action graph. When you have 100s of thousands of filters which require such a feature it gets very inefficient to do two lookups. This patch completes a leftover feature of action codes. Its time has come. Example below where a user labels packets with a different skbmark on ingress of a port depending on whether they have/not exceeded the configured rate. This mark is then used to make further decisions on some egress port. #rate control, very low so we can easily see the effect sudo $TC actions add action police rate 1kbit burst 90k \ conform-exceed pipe/jump 2 index 10 # skbedit index 11 will be used if the user conforms sudo $TC actions add action skbedit mark 11 ok index 11 # skbedit index 12 will be used if the user does not conform sudo $TC actions add action skbedit mark 12 ok index 12 #lets bind the user .. sudo $TC filter add dev $ETH parent ffff: protocol ip prio 8 u32 \ match ip dst 127.0.0.8/32 flowid 1:10 \ action police index 10 \ action skbedit index 11 \ action skbedit index 12 #run a ping -f and see what happens.. # jhs@foobar:~$ sudo $TC -s filter ls dev $ETH parent ffff: protocol ip filter pref 8 u32 filter pref 8 u32 fh 800: ht divisor 1 filter pref 8 u32 fh 800::800 order 2048 key ht 800 bkt 0 flowid 1:10 (rule hit 2800 success 1005) match 7f000008/ffffffff at 16 (success 1005 ) action order 1: police 0xa rate 1Kbit burst 23440b mtu 2Kb action pipe/jump 2 overhead 0b ref 2 bind 1 installed 207 sec used 122 sec Action statistics: Sent 84420 bytes 1005 pkt (dropped 0, overlimits 721 requeues 0) backlog 0b 0p requeues 0 action order 2: skbedit mark 11 pass index 11 ref 2 bind 1 installed 204 sec used 122 sec Action statistics: Sent 60564 bytes 721 pkt (dropped 0, overlimits 0 requeues 0) backlog 0b 0p requeues 0 action order 3: skbedit mark 12 pass index 12 ref 2 bind 1 installed 201 sec used 122 sec Action statistics: Sent 23856 bytes 284 pkt (dropped 0, overlimits 0 requeues 0) backlog 0b 0p requeues 0 Not bad, about 28% non-conforming packets.. Signed-off-by: Jamal Hadi Salim <jhs@mojatatu.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-04-24 00:17:28 +07:00
/*TCA_ACT_MAX_PRIO is 32, there count upto 32 */
#define TCA_ACT_MAX_PRIO_MASK 0x1FF
int tcf_action_exec(struct sk_buff *skb, struct tc_action **actions,
int nr_actions, struct tcf_result *res)
{
net sched actions: Complete the JUMPX opcode per discussion at netconf/netdev: When we have an action that is capable of branching (example a policer), we can achieve a continuation of the action graph by programming a "continue" where we find an exact replica of the same filter rule with a lower priority and the remainder of the action graph. When you have 100s of thousands of filters which require such a feature it gets very inefficient to do two lookups. This patch completes a leftover feature of action codes. Its time has come. Example below where a user labels packets with a different skbmark on ingress of a port depending on whether they have/not exceeded the configured rate. This mark is then used to make further decisions on some egress port. #rate control, very low so we can easily see the effect sudo $TC actions add action police rate 1kbit burst 90k \ conform-exceed pipe/jump 2 index 10 # skbedit index 11 will be used if the user conforms sudo $TC actions add action skbedit mark 11 ok index 11 # skbedit index 12 will be used if the user does not conform sudo $TC actions add action skbedit mark 12 ok index 12 #lets bind the user .. sudo $TC filter add dev $ETH parent ffff: protocol ip prio 8 u32 \ match ip dst 127.0.0.8/32 flowid 1:10 \ action police index 10 \ action skbedit index 11 \ action skbedit index 12 #run a ping -f and see what happens.. # jhs@foobar:~$ sudo $TC -s filter ls dev $ETH parent ffff: protocol ip filter pref 8 u32 filter pref 8 u32 fh 800: ht divisor 1 filter pref 8 u32 fh 800::800 order 2048 key ht 800 bkt 0 flowid 1:10 (rule hit 2800 success 1005) match 7f000008/ffffffff at 16 (success 1005 ) action order 1: police 0xa rate 1Kbit burst 23440b mtu 2Kb action pipe/jump 2 overhead 0b ref 2 bind 1 installed 207 sec used 122 sec Action statistics: Sent 84420 bytes 1005 pkt (dropped 0, overlimits 721 requeues 0) backlog 0b 0p requeues 0 action order 2: skbedit mark 11 pass index 11 ref 2 bind 1 installed 204 sec used 122 sec Action statistics: Sent 60564 bytes 721 pkt (dropped 0, overlimits 0 requeues 0) backlog 0b 0p requeues 0 action order 3: skbedit mark 12 pass index 12 ref 2 bind 1 installed 201 sec used 122 sec Action statistics: Sent 23856 bytes 284 pkt (dropped 0, overlimits 0 requeues 0) backlog 0b 0p requeues 0 Not bad, about 28% non-conforming packets.. Signed-off-by: Jamal Hadi Salim <jhs@mojatatu.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-04-24 00:17:28 +07:00
u32 jmp_prgcnt = 0;
u32 jmp_ttl = TCA_ACT_MAX_PRIO; /*matches actions per filter */
int i;
int ret = TC_ACT_OK;
if (skb_skip_tc_classify(skb))
return TC_ACT_OK;
net sched actions: Complete the JUMPX opcode per discussion at netconf/netdev: When we have an action that is capable of branching (example a policer), we can achieve a continuation of the action graph by programming a "continue" where we find an exact replica of the same filter rule with a lower priority and the remainder of the action graph. When you have 100s of thousands of filters which require such a feature it gets very inefficient to do two lookups. This patch completes a leftover feature of action codes. Its time has come. Example below where a user labels packets with a different skbmark on ingress of a port depending on whether they have/not exceeded the configured rate. This mark is then used to make further decisions on some egress port. #rate control, very low so we can easily see the effect sudo $TC actions add action police rate 1kbit burst 90k \ conform-exceed pipe/jump 2 index 10 # skbedit index 11 will be used if the user conforms sudo $TC actions add action skbedit mark 11 ok index 11 # skbedit index 12 will be used if the user does not conform sudo $TC actions add action skbedit mark 12 ok index 12 #lets bind the user .. sudo $TC filter add dev $ETH parent ffff: protocol ip prio 8 u32 \ match ip dst 127.0.0.8/32 flowid 1:10 \ action police index 10 \ action skbedit index 11 \ action skbedit index 12 #run a ping -f and see what happens.. # jhs@foobar:~$ sudo $TC -s filter ls dev $ETH parent ffff: protocol ip filter pref 8 u32 filter pref 8 u32 fh 800: ht divisor 1 filter pref 8 u32 fh 800::800 order 2048 key ht 800 bkt 0 flowid 1:10 (rule hit 2800 success 1005) match 7f000008/ffffffff at 16 (success 1005 ) action order 1: police 0xa rate 1Kbit burst 23440b mtu 2Kb action pipe/jump 2 overhead 0b ref 2 bind 1 installed 207 sec used 122 sec Action statistics: Sent 84420 bytes 1005 pkt (dropped 0, overlimits 721 requeues 0) backlog 0b 0p requeues 0 action order 2: skbedit mark 11 pass index 11 ref 2 bind 1 installed 204 sec used 122 sec Action statistics: Sent 60564 bytes 721 pkt (dropped 0, overlimits 0 requeues 0) backlog 0b 0p requeues 0 action order 3: skbedit mark 12 pass index 12 ref 2 bind 1 installed 201 sec used 122 sec Action statistics: Sent 23856 bytes 284 pkt (dropped 0, overlimits 0 requeues 0) backlog 0b 0p requeues 0 Not bad, about 28% non-conforming packets.. Signed-off-by: Jamal Hadi Salim <jhs@mojatatu.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-04-24 00:17:28 +07:00
restart_act_graph:
for (i = 0; i < nr_actions; i++) {
const struct tc_action *a = actions[i];
net sched actions: Complete the JUMPX opcode per discussion at netconf/netdev: When we have an action that is capable of branching (example a policer), we can achieve a continuation of the action graph by programming a "continue" where we find an exact replica of the same filter rule with a lower priority and the remainder of the action graph. When you have 100s of thousands of filters which require such a feature it gets very inefficient to do two lookups. This patch completes a leftover feature of action codes. Its time has come. Example below where a user labels packets with a different skbmark on ingress of a port depending on whether they have/not exceeded the configured rate. This mark is then used to make further decisions on some egress port. #rate control, very low so we can easily see the effect sudo $TC actions add action police rate 1kbit burst 90k \ conform-exceed pipe/jump 2 index 10 # skbedit index 11 will be used if the user conforms sudo $TC actions add action skbedit mark 11 ok index 11 # skbedit index 12 will be used if the user does not conform sudo $TC actions add action skbedit mark 12 ok index 12 #lets bind the user .. sudo $TC filter add dev $ETH parent ffff: protocol ip prio 8 u32 \ match ip dst 127.0.0.8/32 flowid 1:10 \ action police index 10 \ action skbedit index 11 \ action skbedit index 12 #run a ping -f and see what happens.. # jhs@foobar:~$ sudo $TC -s filter ls dev $ETH parent ffff: protocol ip filter pref 8 u32 filter pref 8 u32 fh 800: ht divisor 1 filter pref 8 u32 fh 800::800 order 2048 key ht 800 bkt 0 flowid 1:10 (rule hit 2800 success 1005) match 7f000008/ffffffff at 16 (success 1005 ) action order 1: police 0xa rate 1Kbit burst 23440b mtu 2Kb action pipe/jump 2 overhead 0b ref 2 bind 1 installed 207 sec used 122 sec Action statistics: Sent 84420 bytes 1005 pkt (dropped 0, overlimits 721 requeues 0) backlog 0b 0p requeues 0 action order 2: skbedit mark 11 pass index 11 ref 2 bind 1 installed 204 sec used 122 sec Action statistics: Sent 60564 bytes 721 pkt (dropped 0, overlimits 0 requeues 0) backlog 0b 0p requeues 0 action order 3: skbedit mark 12 pass index 12 ref 2 bind 1 installed 201 sec used 122 sec Action statistics: Sent 23856 bytes 284 pkt (dropped 0, overlimits 0 requeues 0) backlog 0b 0p requeues 0 Not bad, about 28% non-conforming packets.. Signed-off-by: Jamal Hadi Salim <jhs@mojatatu.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-04-24 00:17:28 +07:00
if (jmp_prgcnt > 0) {
jmp_prgcnt -= 1;
continue;
}
repeat:
ret = a->ops->act(skb, a, res);
if (ret == TC_ACT_REPEAT)
goto repeat; /* we need a ttl - JHS */
net sched actions: Complete the JUMPX opcode per discussion at netconf/netdev: When we have an action that is capable of branching (example a policer), we can achieve a continuation of the action graph by programming a "continue" where we find an exact replica of the same filter rule with a lower priority and the remainder of the action graph. When you have 100s of thousands of filters which require such a feature it gets very inefficient to do two lookups. This patch completes a leftover feature of action codes. Its time has come. Example below where a user labels packets with a different skbmark on ingress of a port depending on whether they have/not exceeded the configured rate. This mark is then used to make further decisions on some egress port. #rate control, very low so we can easily see the effect sudo $TC actions add action police rate 1kbit burst 90k \ conform-exceed pipe/jump 2 index 10 # skbedit index 11 will be used if the user conforms sudo $TC actions add action skbedit mark 11 ok index 11 # skbedit index 12 will be used if the user does not conform sudo $TC actions add action skbedit mark 12 ok index 12 #lets bind the user .. sudo $TC filter add dev $ETH parent ffff: protocol ip prio 8 u32 \ match ip dst 127.0.0.8/32 flowid 1:10 \ action police index 10 \ action skbedit index 11 \ action skbedit index 12 #run a ping -f and see what happens.. # jhs@foobar:~$ sudo $TC -s filter ls dev $ETH parent ffff: protocol ip filter pref 8 u32 filter pref 8 u32 fh 800: ht divisor 1 filter pref 8 u32 fh 800::800 order 2048 key ht 800 bkt 0 flowid 1:10 (rule hit 2800 success 1005) match 7f000008/ffffffff at 16 (success 1005 ) action order 1: police 0xa rate 1Kbit burst 23440b mtu 2Kb action pipe/jump 2 overhead 0b ref 2 bind 1 installed 207 sec used 122 sec Action statistics: Sent 84420 bytes 1005 pkt (dropped 0, overlimits 721 requeues 0) backlog 0b 0p requeues 0 action order 2: skbedit mark 11 pass index 11 ref 2 bind 1 installed 204 sec used 122 sec Action statistics: Sent 60564 bytes 721 pkt (dropped 0, overlimits 0 requeues 0) backlog 0b 0p requeues 0 action order 3: skbedit mark 12 pass index 12 ref 2 bind 1 installed 201 sec used 122 sec Action statistics: Sent 23856 bytes 284 pkt (dropped 0, overlimits 0 requeues 0) backlog 0b 0p requeues 0 Not bad, about 28% non-conforming packets.. Signed-off-by: Jamal Hadi Salim <jhs@mojatatu.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-04-24 00:17:28 +07:00
if (TC_ACT_EXT_CMP(ret, TC_ACT_JUMP)) {
net sched actions: Complete the JUMPX opcode per discussion at netconf/netdev: When we have an action that is capable of branching (example a policer), we can achieve a continuation of the action graph by programming a "continue" where we find an exact replica of the same filter rule with a lower priority and the remainder of the action graph. When you have 100s of thousands of filters which require such a feature it gets very inefficient to do two lookups. This patch completes a leftover feature of action codes. Its time has come. Example below where a user labels packets with a different skbmark on ingress of a port depending on whether they have/not exceeded the configured rate. This mark is then used to make further decisions on some egress port. #rate control, very low so we can easily see the effect sudo $TC actions add action police rate 1kbit burst 90k \ conform-exceed pipe/jump 2 index 10 # skbedit index 11 will be used if the user conforms sudo $TC actions add action skbedit mark 11 ok index 11 # skbedit index 12 will be used if the user does not conform sudo $TC actions add action skbedit mark 12 ok index 12 #lets bind the user .. sudo $TC filter add dev $ETH parent ffff: protocol ip prio 8 u32 \ match ip dst 127.0.0.8/32 flowid 1:10 \ action police index 10 \ action skbedit index 11 \ action skbedit index 12 #run a ping -f and see what happens.. # jhs@foobar:~$ sudo $TC -s filter ls dev $ETH parent ffff: protocol ip filter pref 8 u32 filter pref 8 u32 fh 800: ht divisor 1 filter pref 8 u32 fh 800::800 order 2048 key ht 800 bkt 0 flowid 1:10 (rule hit 2800 success 1005) match 7f000008/ffffffff at 16 (success 1005 ) action order 1: police 0xa rate 1Kbit burst 23440b mtu 2Kb action pipe/jump 2 overhead 0b ref 2 bind 1 installed 207 sec used 122 sec Action statistics: Sent 84420 bytes 1005 pkt (dropped 0, overlimits 721 requeues 0) backlog 0b 0p requeues 0 action order 2: skbedit mark 11 pass index 11 ref 2 bind 1 installed 204 sec used 122 sec Action statistics: Sent 60564 bytes 721 pkt (dropped 0, overlimits 0 requeues 0) backlog 0b 0p requeues 0 action order 3: skbedit mark 12 pass index 12 ref 2 bind 1 installed 201 sec used 122 sec Action statistics: Sent 23856 bytes 284 pkt (dropped 0, overlimits 0 requeues 0) backlog 0b 0p requeues 0 Not bad, about 28% non-conforming packets.. Signed-off-by: Jamal Hadi Salim <jhs@mojatatu.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-04-24 00:17:28 +07:00
jmp_prgcnt = ret & TCA_ACT_MAX_PRIO_MASK;
if (!jmp_prgcnt || (jmp_prgcnt > nr_actions)) {
/* faulty opcode, stop pipeline */
return TC_ACT_OK;
} else {
jmp_ttl -= 1;
if (jmp_ttl > 0)
goto restart_act_graph;
else /* faulty graph, stop pipeline */
return TC_ACT_OK;
}
} else if (TC_ACT_EXT_CMP(ret, TC_ACT_GOTO_CHAIN)) {
tcf_action_goto_chain_exec(a, res);
net sched actions: Complete the JUMPX opcode per discussion at netconf/netdev: When we have an action that is capable of branching (example a policer), we can achieve a continuation of the action graph by programming a "continue" where we find an exact replica of the same filter rule with a lower priority and the remainder of the action graph. When you have 100s of thousands of filters which require such a feature it gets very inefficient to do two lookups. This patch completes a leftover feature of action codes. Its time has come. Example below where a user labels packets with a different skbmark on ingress of a port depending on whether they have/not exceeded the configured rate. This mark is then used to make further decisions on some egress port. #rate control, very low so we can easily see the effect sudo $TC actions add action police rate 1kbit burst 90k \ conform-exceed pipe/jump 2 index 10 # skbedit index 11 will be used if the user conforms sudo $TC actions add action skbedit mark 11 ok index 11 # skbedit index 12 will be used if the user does not conform sudo $TC actions add action skbedit mark 12 ok index 12 #lets bind the user .. sudo $TC filter add dev $ETH parent ffff: protocol ip prio 8 u32 \ match ip dst 127.0.0.8/32 flowid 1:10 \ action police index 10 \ action skbedit index 11 \ action skbedit index 12 #run a ping -f and see what happens.. # jhs@foobar:~$ sudo $TC -s filter ls dev $ETH parent ffff: protocol ip filter pref 8 u32 filter pref 8 u32 fh 800: ht divisor 1 filter pref 8 u32 fh 800::800 order 2048 key ht 800 bkt 0 flowid 1:10 (rule hit 2800 success 1005) match 7f000008/ffffffff at 16 (success 1005 ) action order 1: police 0xa rate 1Kbit burst 23440b mtu 2Kb action pipe/jump 2 overhead 0b ref 2 bind 1 installed 207 sec used 122 sec Action statistics: Sent 84420 bytes 1005 pkt (dropped 0, overlimits 721 requeues 0) backlog 0b 0p requeues 0 action order 2: skbedit mark 11 pass index 11 ref 2 bind 1 installed 204 sec used 122 sec Action statistics: Sent 60564 bytes 721 pkt (dropped 0, overlimits 0 requeues 0) backlog 0b 0p requeues 0 action order 3: skbedit mark 12 pass index 12 ref 2 bind 1 installed 201 sec used 122 sec Action statistics: Sent 23856 bytes 284 pkt (dropped 0, overlimits 0 requeues 0) backlog 0b 0p requeues 0 Not bad, about 28% non-conforming packets.. Signed-off-by: Jamal Hadi Salim <jhs@mojatatu.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-04-24 00:17:28 +07:00
}
if (ret != TC_ACT_PIPE)
break;
}
net sched actions: Complete the JUMPX opcode per discussion at netconf/netdev: When we have an action that is capable of branching (example a policer), we can achieve a continuation of the action graph by programming a "continue" where we find an exact replica of the same filter rule with a lower priority and the remainder of the action graph. When you have 100s of thousands of filters which require such a feature it gets very inefficient to do two lookups. This patch completes a leftover feature of action codes. Its time has come. Example below where a user labels packets with a different skbmark on ingress of a port depending on whether they have/not exceeded the configured rate. This mark is then used to make further decisions on some egress port. #rate control, very low so we can easily see the effect sudo $TC actions add action police rate 1kbit burst 90k \ conform-exceed pipe/jump 2 index 10 # skbedit index 11 will be used if the user conforms sudo $TC actions add action skbedit mark 11 ok index 11 # skbedit index 12 will be used if the user does not conform sudo $TC actions add action skbedit mark 12 ok index 12 #lets bind the user .. sudo $TC filter add dev $ETH parent ffff: protocol ip prio 8 u32 \ match ip dst 127.0.0.8/32 flowid 1:10 \ action police index 10 \ action skbedit index 11 \ action skbedit index 12 #run a ping -f and see what happens.. # jhs@foobar:~$ sudo $TC -s filter ls dev $ETH parent ffff: protocol ip filter pref 8 u32 filter pref 8 u32 fh 800: ht divisor 1 filter pref 8 u32 fh 800::800 order 2048 key ht 800 bkt 0 flowid 1:10 (rule hit 2800 success 1005) match 7f000008/ffffffff at 16 (success 1005 ) action order 1: police 0xa rate 1Kbit burst 23440b mtu 2Kb action pipe/jump 2 overhead 0b ref 2 bind 1 installed 207 sec used 122 sec Action statistics: Sent 84420 bytes 1005 pkt (dropped 0, overlimits 721 requeues 0) backlog 0b 0p requeues 0 action order 2: skbedit mark 11 pass index 11 ref 2 bind 1 installed 204 sec used 122 sec Action statistics: Sent 60564 bytes 721 pkt (dropped 0, overlimits 0 requeues 0) backlog 0b 0p requeues 0 action order 3: skbedit mark 12 pass index 12 ref 2 bind 1 installed 201 sec used 122 sec Action statistics: Sent 23856 bytes 284 pkt (dropped 0, overlimits 0 requeues 0) backlog 0b 0p requeues 0 Not bad, about 28% non-conforming packets.. Signed-off-by: Jamal Hadi Salim <jhs@mojatatu.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-04-24 00:17:28 +07:00
return ret;
}
EXPORT_SYMBOL(tcf_action_exec);
int tcf_action_destroy(struct tc_action *actions[], int bind)
{
const struct tc_action_ops *ops;
struct tc_action *a;
int ret = 0, i;
for (i = 0; i < TCA_ACT_MAX_PRIO && actions[i]; i++) {
a = actions[i];
actions[i] = NULL;
ops = a->ops;
ret = __tcf_idr_release(a, bind, true);
if (ret == ACT_P_DELETED)
module_put(ops->owner);
else if (ret < 0)
return ret;
}
return ret;
}
static int tcf_action_destroy_1(struct tc_action *a, int bind)
{
struct tc_action *actions[] = { a, NULL };
return tcf_action_destroy(actions, bind);
}
static int tcf_action_put(struct tc_action *p)
{
return __tcf_action_put(p, false);
}
/* Put all actions in this array, skip those NULL's. */
static void tcf_action_put_many(struct tc_action *actions[])
{
int i;
for (i = 0; i < TCA_ACT_MAX_PRIO; i++) {
struct tc_action *a = actions[i];
const struct tc_action_ops *ops;
if (!a)
continue;
ops = a->ops;
if (tcf_action_put(a))
module_put(ops->owner);
}
}
int
tcf_action_dump_old(struct sk_buff *skb, struct tc_action *a, int bind, int ref)
{
return a->ops->dump(skb, a, bind, ref);
}
int
tcf_action_dump_1(struct sk_buff *skb, struct tc_action *a, int bind, int ref)
{
int err = -EINVAL;
unsigned char *b = skb_tail_pointer(skb);
struct nlattr *nest;
struct tc_cookie *cookie;
if (nla_put_string(skb, TCA_KIND, a->ops->kind))
goto nla_put_failure;
if (tcf_action_copy_stats(skb, a, 0))
goto nla_put_failure;
rcu_read_lock();
cookie = rcu_dereference(a->act_cookie);
if (cookie) {
if (nla_put(skb, TCA_ACT_COOKIE, cookie->len, cookie->data)) {
rcu_read_unlock();
goto nla_put_failure;
}
}
rcu_read_unlock();
nest = nla_nest_start(skb, TCA_OPTIONS);
if (nest == NULL)
goto nla_put_failure;
err = tcf_action_dump_old(skb, a, bind, ref);
if (err > 0) {
nla_nest_end(skb, nest);
return err;
}
nla_put_failure:
nlmsg_trim(skb, b);
return -1;
}
EXPORT_SYMBOL(tcf_action_dump_1);
int tcf_action_dump(struct sk_buff *skb, struct tc_action *actions[],
int bind, int ref)
{
struct tc_action *a;
int err = -EINVAL, i;
struct nlattr *nest;
for (i = 0; i < TCA_ACT_MAX_PRIO && actions[i]; i++) {
a = actions[i];
nest = nla_nest_start(skb, a->order);
if (nest == NULL)
goto nla_put_failure;
err = tcf_action_dump_1(skb, a, bind, ref);
if (err < 0)
goto errout;
nla_nest_end(skb, nest);
}
return 0;
nla_put_failure:
err = -EINVAL;
errout:
nla_nest_cancel(skb, nest);
return err;
}
static struct tc_cookie *nla_memdup_cookie(struct nlattr **tb)
{
struct tc_cookie *c = kzalloc(sizeof(*c), GFP_KERNEL);
if (!c)
return NULL;
c->data = nla_memdup(tb[TCA_ACT_COOKIE], GFP_KERNEL);
if (!c->data) {
kfree(c);
return NULL;
}
c->len = nla_len(tb[TCA_ACT_COOKIE]);
return c;
}
static bool tcf_action_valid(int action)
{
int opcode = TC_ACT_EXT_OPCODE(action);
if (!opcode)
return action <= TC_ACT_VALUE_MAX;
return opcode <= TC_ACT_EXT_OPCODE_MAX || action == TC_ACT_UNSPEC;
}
struct tc_action *tcf_action_init_1(struct net *net, struct tcf_proto *tp,
struct nlattr *nla, struct nlattr *est,
char *name, int ovr, int bind,
bool rtnl_held,
struct netlink_ext_ack *extack)
{
struct tc_action *a;
struct tc_action_ops *a_o;
struct tc_cookie *cookie = NULL;
char act_name[IFNAMSIZ];
struct nlattr *tb[TCA_ACT_MAX + 1];
struct nlattr *kind;
int err;
if (name == NULL) {
err = nla_parse_nested(tb, TCA_ACT_MAX, nla, NULL, extack);
if (err < 0)
goto err_out;
err = -EINVAL;
kind = tb[TCA_ACT_KIND];
if (!kind) {
NL_SET_ERR_MSG(extack, "TC action kind must be specified");
goto err_out;
}
if (nla_strlcpy(act_name, kind, IFNAMSIZ) >= IFNAMSIZ) {
NL_SET_ERR_MSG(extack, "TC action name too long");
goto err_out;
}
if (tb[TCA_ACT_COOKIE]) {
int cklen = nla_len(tb[TCA_ACT_COOKIE]);
if (cklen > TC_COOKIE_MAX_SIZE) {
NL_SET_ERR_MSG(extack, "TC cookie size above the maximum");
goto err_out;
}
cookie = nla_memdup_cookie(tb);
if (!cookie) {
NL_SET_ERR_MSG(extack, "No memory to generate TC cookie");
err = -ENOMEM;
goto err_out;
}
}
} else {
if (strlcpy(act_name, name, IFNAMSIZ) >= IFNAMSIZ) {
NL_SET_ERR_MSG(extack, "TC action name too long");
err = -EINVAL;
goto err_out;
}
}
a_o = tc_lookup_action_n(act_name);
if (a_o == NULL) {
#ifdef CONFIG_MODULES
if (rtnl_held)
rtnl_unlock();
request_module("act_%s", act_name);
if (rtnl_held)
rtnl_lock();
a_o = tc_lookup_action_n(act_name);
/* We dropped the RTNL semaphore in order to
* perform the module load. So, even if we
* succeeded in loading the module we have to
* tell the caller to replay the request. We
* indicate this using -EAGAIN.
*/
if (a_o != NULL) {
err = -EAGAIN;
goto err_mod;
}
#endif
NL_SET_ERR_MSG(extack, "Failed to load TC action module");
err = -ENOENT;
goto err_out;
}
/* backward compatibility for policer */
if (name == NULL)
err = a_o->init(net, tb[TCA_ACT_OPTIONS], est, &a, ovr, bind,
rtnl_held, extack);
else
err = a_o->init(net, nla, est, &a, ovr, bind, rtnl_held,
extack);
if (err < 0)
goto err_mod;
if (!name && tb[TCA_ACT_COOKIE])
tcf_set_action_cookie(&a->act_cookie, cookie);
/* module count goes up only when brand new policy is created
* if it exists and is only bound to in a_o->init() then
* ACT_P_CREATED is not returned (a zero is).
*/
if (err != ACT_P_CREATED)
module_put(a_o->owner);
if (TC_ACT_EXT_CMP(a->tcfa_action, TC_ACT_GOTO_CHAIN)) {
err = tcf_action_goto_chain_init(a, tp);
if (err) {
tcf_action_destroy_1(a, bind);
NL_SET_ERR_MSG(extack, "Failed to init TC action chain");
return ERR_PTR(err);
}
}
if (!tcf_action_valid(a->tcfa_action)) {
tcf_action_destroy_1(a, bind);
NL_SET_ERR_MSG(extack, "Invalid control action value");
return ERR_PTR(-EINVAL);
}
return a;
err_mod:
module_put(a_o->owner);
err_out:
if (cookie) {
kfree(cookie->data);
kfree(cookie);
}
return ERR_PTR(err);
}
/* Returns numbers of initialized actions or negative error. */
int tcf_action_init(struct net *net, struct tcf_proto *tp, struct nlattr *nla,
struct nlattr *est, char *name, int ovr, int bind,
struct tc_action *actions[], size_t *attr_size,
bool rtnl_held, struct netlink_ext_ack *extack)
{
struct nlattr *tb[TCA_ACT_MAX_PRIO + 1];
struct tc_action *act;
size_t sz = 0;
int err;
int i;
err = nla_parse_nested(tb, TCA_ACT_MAX_PRIO, nla, NULL, extack);
if (err < 0)
return err;
for (i = 1; i <= TCA_ACT_MAX_PRIO && tb[i]; i++) {
act = tcf_action_init_1(net, tp, tb[i], est, name, ovr, bind,
rtnl_held, extack);
if (IS_ERR(act)) {
err = PTR_ERR(act);
goto err;
}
act->order = i;
sz += tcf_action_fill_size(act);
/* Start from index 0 */
actions[i - 1] = act;
}
*attr_size = tcf_action_full_attrs_size(sz);
return i - 1;
err:
tcf_action_destroy(actions, bind);
return err;
}
int tcf_action_copy_stats(struct sk_buff *skb, struct tc_action *p,
int compat_mode)
{
int err = 0;
struct gnet_dump d;
if (p == NULL)
goto errout;
/* compat_mode being true specifies a call that is supposed
* to add additional backward compatibility statistic TLVs.
*/
if (compat_mode) {
if (p->type == TCA_OLD_COMPAT)
err = gnet_stats_start_copy_compat(skb, 0,
TCA_STATS,
TCA_XSTATS,
&p->tcfa_lock, &d,
TCA_PAD);
else
return 0;
} else
err = gnet_stats_start_copy(skb, TCA_ACT_STATS,
&p->tcfa_lock, &d, TCA_ACT_PAD);
if (err < 0)
goto errout;
if (gnet_stats_copy_basic(NULL, &d, p->cpu_bstats, &p->tcfa_bstats) < 0 ||
gnet_stats_copy_basic_hw(NULL, &d, p->cpu_bstats_hw,
&p->tcfa_bstats_hw) < 0 ||
gnet_stats_copy_rate_est(&d, &p->tcfa_rate_est) < 0 ||
gnet_stats_copy_queue(&d, p->cpu_qstats,
&p->tcfa_qstats,
p->tcfa_qstats.qlen) < 0)
goto errout;
if (gnet_stats_finish_copy(&d) < 0)
goto errout;
return 0;
errout:
return -1;
}
static int tca_get_fill(struct sk_buff *skb, struct tc_action *actions[],
u32 portid, u32 seq, u16 flags, int event, int bind,
int ref)
{
struct tcamsg *t;
struct nlmsghdr *nlh;
unsigned char *b = skb_tail_pointer(skb);
struct nlattr *nest;
nlh = nlmsg_put(skb, portid, seq, event, sizeof(*t), flags);
if (!nlh)
goto out_nlmsg_trim;
t = nlmsg_data(nlh);
t->tca_family = AF_UNSPEC;
t->tca__pad1 = 0;
t->tca__pad2 = 0;
nest = nla_nest_start(skb, TCA_ACT_TAB);
if (!nest)
goto out_nlmsg_trim;
if (tcf_action_dump(skb, actions, bind, ref) < 0)
goto out_nlmsg_trim;
nla_nest_end(skb, nest);
nlh->nlmsg_len = skb_tail_pointer(skb) - b;
return skb->len;
out_nlmsg_trim:
nlmsg_trim(skb, b);
return -1;
}
static int
tcf_get_notify(struct net *net, u32 portid, struct nlmsghdr *n,
struct tc_action *actions[], int event,
struct netlink_ext_ack *extack)
{
struct sk_buff *skb;
skb = alloc_skb(NLMSG_GOODSIZE, GFP_KERNEL);
if (!skb)
return -ENOBUFS;
if (tca_get_fill(skb, actions, portid, n->nlmsg_seq, 0, event,
0, 1) <= 0) {
NL_SET_ERR_MSG(extack, "Failed to fill netlink attributes while adding TC action");
kfree_skb(skb);
return -EINVAL;
}
return rtnl_unicast(skb, net, portid);
}
static struct tc_action *tcf_action_get_1(struct net *net, struct nlattr *nla,
struct nlmsghdr *n, u32 portid,
struct netlink_ext_ack *extack)
{
struct nlattr *tb[TCA_ACT_MAX + 1];
const struct tc_action_ops *ops;
struct tc_action *a;
int index;
int err;
err = nla_parse_nested(tb, TCA_ACT_MAX, nla, NULL, extack);
if (err < 0)
goto err_out;
err = -EINVAL;
if (tb[TCA_ACT_INDEX] == NULL ||
nla_len(tb[TCA_ACT_INDEX]) < sizeof(index)) {
NL_SET_ERR_MSG(extack, "Invalid TC action index value");
goto err_out;
}
index = nla_get_u32(tb[TCA_ACT_INDEX]);
err = -EINVAL;
ops = tc_lookup_action(tb[TCA_ACT_KIND]);
if (!ops) { /* could happen in batch of actions */
NL_SET_ERR_MSG(extack, "Specified TC action kind not found");
goto err_out;
}
err = -ENOENT;
if (ops->lookup(net, &a, index) == 0) {
NL_SET_ERR_MSG(extack, "TC action with specified index not found");
goto err_mod;
}
module_put(ops->owner);
return a;
err_mod:
module_put(ops->owner);
err_out:
return ERR_PTR(err);
}
static int tca_action_flush(struct net *net, struct nlattr *nla,
struct nlmsghdr *n, u32 portid,
struct netlink_ext_ack *extack)
{
struct sk_buff *skb;
unsigned char *b;
struct nlmsghdr *nlh;
struct tcamsg *t;
struct netlink_callback dcb;
struct nlattr *nest;
struct nlattr *tb[TCA_ACT_MAX + 1];
const struct tc_action_ops *ops;
struct nlattr *kind;
int err = -ENOMEM;
skb = alloc_skb(NLMSG_GOODSIZE, GFP_KERNEL);
if (!skb)
return err;
b = skb_tail_pointer(skb);
err = nla_parse_nested(tb, TCA_ACT_MAX, nla, NULL, extack);
if (err < 0)
goto err_out;
err = -EINVAL;
kind = tb[TCA_ACT_KIND];
ops = tc_lookup_action(kind);
if (!ops) { /*some idjot trying to flush unknown action */
NL_SET_ERR_MSG(extack, "Cannot flush unknown TC action");
goto err_out;
}
nlh = nlmsg_put(skb, portid, n->nlmsg_seq, RTM_DELACTION,
sizeof(*t), 0);
if (!nlh) {
NL_SET_ERR_MSG(extack, "Failed to create TC action flush notification");
goto out_module_put;
}
t = nlmsg_data(nlh);
t->tca_family = AF_UNSPEC;
t->tca__pad1 = 0;
t->tca__pad2 = 0;
nest = nla_nest_start(skb, TCA_ACT_TAB);
if (!nest) {
NL_SET_ERR_MSG(extack, "Failed to add new netlink message");
goto out_module_put;
}
err = ops->walk(net, skb, &dcb, RTM_DELACTION, ops, extack);
if (err <= 0) {
nla_nest_cancel(skb, nest);
goto out_module_put;
}
nla_nest_end(skb, nest);
nlh->nlmsg_len = skb_tail_pointer(skb) - b;
nlh->nlmsg_flags |= NLM_F_ROOT;
module_put(ops->owner);
err = rtnetlink_send(skb, net, portid, RTNLGRP_TC,
n->nlmsg_flags & NLM_F_ECHO);
if (err > 0)
return 0;
if (err < 0)
NL_SET_ERR_MSG(extack, "Failed to send TC action flush notification");
return err;
out_module_put:
module_put(ops->owner);
err_out:
kfree_skb(skb);
return err;
}
static int tcf_action_delete(struct net *net, struct tc_action *actions[])
{
int i;
for (i = 0; i < TCA_ACT_MAX_PRIO && actions[i]; i++) {
struct tc_action *a = actions[i];
const struct tc_action_ops *ops = a->ops;
/* Actions can be deleted concurrently so we must save their
* type and id to search again after reference is released.
*/
struct tcf_idrinfo *idrinfo = a->idrinfo;
u32 act_index = a->tcfa_index;
net: sched: null actions array pointer before releasing action Currently, tcf_action_delete() nulls actions array pointer after putting and deleting it. However, if tcf_idr_delete_index() returns an error, pointer to action is not set to null. That results it being released second time in error handling code of tca_action_gd(). Kasan error: [ 807.367755] ================================================================== [ 807.375844] BUG: KASAN: use-after-free in tc_setup_cb_call+0x14e/0x250 [ 807.382763] Read of size 8 at addr ffff88033e636000 by task tc/2732 [ 807.391289] CPU: 0 PID: 2732 Comm: tc Tainted: G W 4.19.0-rc1+ #799 [ 807.399542] Hardware name: Supermicro SYS-2028TP-DECR/X10DRT-P, BIOS 2.0b 03/30/2017 [ 807.407948] Call Trace: [ 807.410763] dump_stack+0x92/0xeb [ 807.414456] print_address_description+0x70/0x360 [ 807.419549] kasan_report+0x14d/0x300 [ 807.423582] ? tc_setup_cb_call+0x14e/0x250 [ 807.428150] tc_setup_cb_call+0x14e/0x250 [ 807.432539] ? nla_put+0x65/0xe0 [ 807.436146] fl_dump+0x394/0x3f0 [cls_flower] [ 807.440890] ? fl_tmplt_dump+0x140/0x140 [cls_flower] [ 807.446327] ? lock_downgrade+0x320/0x320 [ 807.450702] ? lock_acquire+0xe2/0x220 [ 807.454819] ? is_bpf_text_address+0x5/0x140 [ 807.459475] ? memcpy+0x34/0x50 [ 807.462980] ? nla_put+0x65/0xe0 [ 807.466582] tcf_fill_node+0x341/0x430 [ 807.470717] ? tcf_block_put+0xe0/0xe0 [ 807.474859] tcf_node_dump+0xdb/0xf0 [ 807.478821] fl_walk+0x8e/0x170 [cls_flower] [ 807.483474] tcf_chain_dump+0x35a/0x4d0 [ 807.487703] ? tfilter_notify+0x170/0x170 [ 807.492091] ? tcf_fill_node+0x430/0x430 [ 807.496411] tc_dump_tfilter+0x362/0x3f0 [ 807.500712] ? tc_del_tfilter+0x850/0x850 [ 807.505104] ? kasan_unpoison_shadow+0x30/0x40 [ 807.509940] ? __mutex_unlock_slowpath+0xcf/0x410 [ 807.515031] netlink_dump+0x263/0x4f0 [ 807.519077] __netlink_dump_start+0x2a0/0x300 [ 807.523817] ? tc_del_tfilter+0x850/0x850 [ 807.528198] rtnetlink_rcv_msg+0x46a/0x6d0 [ 807.532671] ? rtnl_fdb_del+0x3f0/0x3f0 [ 807.536878] ? tc_del_tfilter+0x850/0x850 [ 807.541280] netlink_rcv_skb+0x18d/0x200 [ 807.545570] ? rtnl_fdb_del+0x3f0/0x3f0 [ 807.549773] ? netlink_ack+0x500/0x500 [ 807.553913] netlink_unicast+0x2d0/0x370 [ 807.558212] ? netlink_attachskb+0x340/0x340 [ 807.562855] ? _copy_from_iter_full+0xe9/0x3e0 [ 807.567677] ? import_iovec+0x11e/0x1c0 [ 807.571890] netlink_sendmsg+0x3b9/0x6a0 [ 807.576192] ? netlink_unicast+0x370/0x370 [ 807.580684] ? netlink_unicast+0x370/0x370 [ 807.585154] sock_sendmsg+0x6b/0x80 [ 807.589015] ___sys_sendmsg+0x4a1/0x520 [ 807.593230] ? copy_msghdr_from_user+0x210/0x210 [ 807.598232] ? do_wp_page+0x174/0x880 [ 807.602276] ? __handle_mm_fault+0x749/0x1c10 [ 807.607021] ? __handle_mm_fault+0x1046/0x1c10 [ 807.611849] ? __pmd_alloc+0x320/0x320 [ 807.615973] ? check_chain_key+0x140/0x1f0 [ 807.620450] ? check_chain_key+0x140/0x1f0 [ 807.624929] ? __fget_light+0xbc/0xd0 [ 807.628970] ? __sys_sendmsg+0xd7/0x150 [ 807.633172] __sys_sendmsg+0xd7/0x150 [ 807.637201] ? __ia32_sys_shutdown+0x30/0x30 [ 807.641846] ? up_read+0x53/0x90 [ 807.645442] ? __do_page_fault+0x484/0x780 [ 807.649949] ? do_syscall_64+0x1e/0x2c0 [ 807.654164] do_syscall_64+0x72/0x2c0 [ 807.658198] entry_SYSCALL_64_after_hwframe+0x49/0xbe [ 807.663625] RIP: 0033:0x7f42e9870150 [ 807.667568] Code: 8b 15 3c 7d 2b 00 f7 d8 64 89 02 48 c7 c0 ff ff ff ff eb cd 66 0f 1f 44 00 00 83 3d b9 d5 2b 00 00 75 10 b8 2e 00 00 00 0f 05 <48> 3d 01 f0 ff ff 73 31 c3 48 83 ec 08 e8 be cd 00 00 48 89 04 24 [ 807.687328] RSP: 002b:00007ffdbf595b58 EFLAGS: 00000246 ORIG_RAX: 000000000000002e [ 807.695564] RAX: ffffffffffffffda RBX: 0000000000000000 RCX: 00007f42e9870150 [ 807.703083] RDX: 0000000000000000 RSI: 00007ffdbf595b80 RDI: 0000000000000003 [ 807.710605] RBP: 00007ffdbf599d90 R08: 0000000000679bc0 R09: 000000000000000f [ 807.718127] R10: 00000000000005e7 R11: 0000000000000246 R12: 00007ffdbf599d88 [ 807.725651] R13: 0000000000000000 R14: 0000000000000000 R15: 0000000000000000 [ 807.735048] Allocated by task 2687: [ 807.738902] kasan_kmalloc+0xa0/0xd0 [ 807.742852] __kmalloc+0x118/0x2d0 [ 807.746615] tcf_idr_create+0x44/0x320 [ 807.750738] tcf_nat_init+0x41e/0x530 [act_nat] [ 807.755638] tcf_action_init_1+0x4e0/0x650 [ 807.760104] tcf_action_init+0x1ce/0x2d0 [ 807.764395] tcf_exts_validate+0x1d8/0x200 [ 807.768861] fl_change+0x55a/0x26b4 [cls_flower] [ 807.773845] tc_new_tfilter+0x748/0xa20 [ 807.778051] rtnetlink_rcv_msg+0x56a/0x6d0 [ 807.782517] netlink_rcv_skb+0x18d/0x200 [ 807.786804] netlink_unicast+0x2d0/0x370 [ 807.791095] netlink_sendmsg+0x3b9/0x6a0 [ 807.795387] sock_sendmsg+0x6b/0x80 [ 807.799240] ___sys_sendmsg+0x4a1/0x520 [ 807.803445] __sys_sendmsg+0xd7/0x150 [ 807.807473] do_syscall_64+0x72/0x2c0 [ 807.811506] entry_SYSCALL_64_after_hwframe+0x49/0xbe [ 807.818776] Freed by task 2728: [ 807.822283] __kasan_slab_free+0x122/0x180 [ 807.826752] kfree+0xf4/0x2f0 [ 807.830080] __tcf_action_put+0x5a/0xb0 [ 807.834281] tcf_action_put_many+0x46/0x70 [ 807.838747] tca_action_gd+0x232/0xc40 [ 807.842862] tc_ctl_action+0x215/0x230 [ 807.846977] rtnetlink_rcv_msg+0x56a/0x6d0 [ 807.851444] netlink_rcv_skb+0x18d/0x200 [ 807.855731] netlink_unicast+0x2d0/0x370 [ 807.860021] netlink_sendmsg+0x3b9/0x6a0 [ 807.864312] sock_sendmsg+0x6b/0x80 [ 807.868166] ___sys_sendmsg+0x4a1/0x520 [ 807.872372] __sys_sendmsg+0xd7/0x150 [ 807.876401] do_syscall_64+0x72/0x2c0 [ 807.880431] entry_SYSCALL_64_after_hwframe+0x49/0xbe [ 807.887704] The buggy address belongs to the object at ffff88033e636000 which belongs to the cache kmalloc-256 of size 256 [ 807.900909] The buggy address is located 0 bytes inside of 256-byte region [ffff88033e636000, ffff88033e636100) [ 807.913155] The buggy address belongs to the page: [ 807.918322] page:ffffea000cf98d80 count:1 mapcount:0 mapping:ffff88036f80ee00 index:0x0 compound_mapcount: 0 [ 807.928831] flags: 0x5fff8000008100(slab|head) [ 807.933647] raw: 005fff8000008100 ffffea000db44f00 0000000400000004 ffff88036f80ee00 [ 807.942050] raw: 0000000000000000 0000000080190019 00000001ffffffff 0000000000000000 [ 807.950456] page dumped because: kasan: bad access detected [ 807.958240] Memory state around the buggy address: [ 807.963405] ffff88033e635f00: fc fc fc fc fb fb fb fb fb fb fb fc fc fc fc fb [ 807.971288] ffff88033e635f80: fb fb fb fb fb fb fc fc fc fc fc fc fc fc fc fc [ 807.979166] >ffff88033e636000: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb [ 807.994882] ^ [ 807.998477] ffff88033e636080: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb [ 808.006352] ffff88033e636100: fc fc fc fc fc fc fc fc fb fb fb fb fb fb fb fb [ 808.014230] ================================================================== [ 808.022108] Disabling lock debugging due to kernel taint Fixes: edfaf94fa705 ("net_sched: improve and refactor tcf_action_put_many()") Signed-off-by: Vlad Buslov <vladbu@mellanox.com> Acked-by: Cong Wang <xiyou.wangcong@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-09-03 14:04:55 +07:00
actions[i] = NULL;
if (tcf_action_put(a)) {
/* last reference, action was deleted concurrently */
module_put(ops->owner);
} else {
int ret;
/* now do the delete */
ret = tcf_idr_delete_index(idrinfo, act_index);
if (ret < 0)
return ret;
}
}
return 0;
}
static int
tcf_del_notify(struct net *net, struct nlmsghdr *n, struct tc_action *actions[],
u32 portid, size_t attr_size, struct netlink_ext_ack *extack)
{
int ret;
struct sk_buff *skb;
skb = alloc_skb(attr_size <= NLMSG_GOODSIZE ? NLMSG_GOODSIZE : attr_size,
GFP_KERNEL);
if (!skb)
return -ENOBUFS;
if (tca_get_fill(skb, actions, portid, n->nlmsg_seq, 0, RTM_DELACTION,
0, 2) <= 0) {
NL_SET_ERR_MSG(extack, "Failed to fill netlink TC action attributes");
kfree_skb(skb);
return -EINVAL;
}
/* now do the delete */
ret = tcf_action_delete(net, actions);
if (ret < 0) {
NL_SET_ERR_MSG(extack, "Failed to delete TC action");
kfree_skb(skb);
return ret;
}
ret = rtnetlink_send(skb, net, portid, RTNLGRP_TC,
n->nlmsg_flags & NLM_F_ECHO);
if (ret > 0)
return 0;
return ret;
}
static int
tca_action_gd(struct net *net, struct nlattr *nla, struct nlmsghdr *n,
u32 portid, int event, struct netlink_ext_ack *extack)
{
int i, ret;
struct nlattr *tb[TCA_ACT_MAX_PRIO + 1];
struct tc_action *act;
size_t attr_size = 0;
struct tc_action *actions[TCA_ACT_MAX_PRIO] = {};
ret = nla_parse_nested(tb, TCA_ACT_MAX_PRIO, nla, NULL, extack);
if (ret < 0)
return ret;
if (event == RTM_DELACTION && n->nlmsg_flags & NLM_F_ROOT) {
if (tb[1])
return tca_action_flush(net, tb[1], n, portid, extack);
NL_SET_ERR_MSG(extack, "Invalid netlink attributes while flushing TC action");
return -EINVAL;
}
for (i = 1; i <= TCA_ACT_MAX_PRIO && tb[i]; i++) {
act = tcf_action_get_1(net, tb[i], n, portid, extack);
if (IS_ERR(act)) {
ret = PTR_ERR(act);
goto err;
}
act->order = i;
attr_size += tcf_action_fill_size(act);
actions[i - 1] = act;
}
attr_size = tcf_action_full_attrs_size(attr_size);
if (event == RTM_GETACTION)
ret = tcf_get_notify(net, portid, n, actions, event, extack);
else { /* delete */
ret = tcf_del_notify(net, n, actions, portid, attr_size, extack);
if (ret)
goto err;
return 0;
}
err:
tcf_action_put_many(actions);
return ret;
}
static int
tcf_add_notify(struct net *net, struct nlmsghdr *n, struct tc_action *actions[],
u32 portid, size_t attr_size, struct netlink_ext_ack *extack)
{
struct sk_buff *skb;
int err = 0;
skb = alloc_skb(attr_size <= NLMSG_GOODSIZE ? NLMSG_GOODSIZE : attr_size,
GFP_KERNEL);
if (!skb)
return -ENOBUFS;
if (tca_get_fill(skb, actions, portid, n->nlmsg_seq, n->nlmsg_flags,
RTM_NEWACTION, 0, 0) <= 0) {
NL_SET_ERR_MSG(extack, "Failed to fill netlink attributes while adding TC action");
kfree_skb(skb);
return -EINVAL;
}
err = rtnetlink_send(skb, net, portid, RTNLGRP_TC,
n->nlmsg_flags & NLM_F_ECHO);
if (err > 0)
err = 0;
return err;
}
static int tcf_action_add(struct net *net, struct nlattr *nla,
struct nlmsghdr *n, u32 portid, int ovr,
struct netlink_ext_ack *extack)
{
size_t attr_size = 0;
int ret = 0;
struct tc_action *actions[TCA_ACT_MAX_PRIO] = {};
ret = tcf_action_init(net, NULL, nla, NULL, NULL, ovr, 0, actions,
&attr_size, true, extack);
if (ret < 0)
return ret;
ret = tcf_add_notify(net, n, actions, portid, attr_size, extack);
if (ovr)
tcf_action_put_many(actions);
return ret;
}
net sched actions: dump more than TCA_ACT_MAX_PRIO actions per batch When you dump hundreds of thousands of actions, getting only 32 per dump batch even when the socket buffer and memory allocations allow is inefficient. With this change, the user will get as many as possibly fitting within the given constraints available to the kernel. The top level action TLV space is extended. An attribute TCA_ROOT_FLAGS is used to carry flags; flag TCA_FLAG_LARGE_DUMP_ON is set by the user indicating the user is capable of processing these large dumps. Older user space which doesnt set this flag doesnt get the large (than 32) batches. The kernel uses the TCA_ROOT_COUNT attribute to tell the user how many actions are put in a single batch. As such user space app knows how long to iterate (independent of the type of action being dumped) instead of hardcoded maximum of 32 thus maintaining backward compat. Some results dumping 1.5M actions below: first an unpatched tc which doesnt understand these features... prompt$ time -p tc actions ls action gact | grep index | wc -l 1500000 real 1388.43 user 2.07 sys 1386.79 Now lets see a patched tc which sets the correct flags when requesting a dump: prompt$ time -p updatedtc actions ls action gact | grep index | wc -l 1500000 real 178.13 user 2.02 sys 176.96 That is about 8x performance improvement for tc app which sets its receive buffer to about 32K. Signed-off-by: Jamal Hadi Salim <jhs@mojatatu.com> Reviewed-by: Jiri Pirko <jiri@mellanox.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-07-31 00:24:51 +07:00
static u32 tcaa_root_flags_allowed = TCA_FLAG_LARGE_DUMP_ON;
static const struct nla_policy tcaa_policy[TCA_ROOT_MAX + 1] = {
[TCA_ROOT_FLAGS] = { .type = NLA_BITFIELD32,
.validation_data = &tcaa_root_flags_allowed },
net sched actions: add time filter for action dumping This patch adds support for filtering based on time since last used. When we are dumping a large number of actions it is useful to have the option of filtering based on when the action was last used to reduce the amount of data crossing to user space. With this patch the user space app sets the TCA_ROOT_TIME_DELTA attribute with the value in milliseconds with "time of interest since now". The kernel converts this to jiffies and does the filtering comparison matching entries that have seen activity since then and returns them to user space. Old kernels and old tc continue to work in legacy mode since they dont specify this attribute. Some example (we have 400 actions bound to 400 filters); at installation time. Using updated when tc setting the time of interest to 120 seconds earlier (we see 400 actions): prompt$ hackedtc actions ls action gact since 120000| grep index | wc -l 400 go get some coffee and wait for > 120 seconds and try again: prompt$ hackedtc actions ls action gact since 120000 | grep index | wc -l 0 Lets see a filter bound to one of these actions: .... filter pref 10 u32 filter pref 10 u32 fh 800: ht divisor 1 filter pref 10 u32 fh 800::800 order 2048 key ht 800 bkt 0 flowid 1:10 (rule hit 2 success 1) match 7f000002/ffffffff at 12 (success 1 ) action order 1: gact action pass random type none pass val 0 index 23 ref 2 bind 1 installed 1145 sec used 802 sec Action statistics: Sent 84 bytes 1 pkt (dropped 0, overlimits 0 requeues 0) backlog 0b 0p requeues 0 .... that coffee took long, no? It was good. Now lets ping -c 1 127.0.0.2, then run the actions again: prompt$ hackedtc actions ls action gact since 120 | grep index | wc -l 1 More details please: prompt$ hackedtc -s actions ls action gact since 120000 action order 0: gact action pass random type none pass val 0 index 23 ref 2 bind 1 installed 1270 sec used 30 sec Action statistics: Sent 168 bytes 2 pkt (dropped 0, overlimits 0 requeues 0) backlog 0b 0p requeues 0 And the filter? filter pref 10 u32 filter pref 10 u32 fh 800: ht divisor 1 filter pref 10 u32 fh 800::800 order 2048 key ht 800 bkt 0 flowid 1:10 (rule hit 4 success 2) match 7f000002/ffffffff at 12 (success 2 ) action order 1: gact action pass random type none pass val 0 index 23 ref 2 bind 1 installed 1324 sec used 84 sec Action statistics: Sent 168 bytes 2 pkt (dropped 0, overlimits 0 requeues 0) backlog 0b 0p requeues 0 Signed-off-by: Jamal Hadi Salim <jhs@mojatatu.com> Reviewed-by: Jiri Pirko <jiri@mellanox.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-07-31 00:24:52 +07:00
[TCA_ROOT_TIME_DELTA] = { .type = NLA_U32 },
net sched actions: dump more than TCA_ACT_MAX_PRIO actions per batch When you dump hundreds of thousands of actions, getting only 32 per dump batch even when the socket buffer and memory allocations allow is inefficient. With this change, the user will get as many as possibly fitting within the given constraints available to the kernel. The top level action TLV space is extended. An attribute TCA_ROOT_FLAGS is used to carry flags; flag TCA_FLAG_LARGE_DUMP_ON is set by the user indicating the user is capable of processing these large dumps. Older user space which doesnt set this flag doesnt get the large (than 32) batches. The kernel uses the TCA_ROOT_COUNT attribute to tell the user how many actions are put in a single batch. As such user space app knows how long to iterate (independent of the type of action being dumped) instead of hardcoded maximum of 32 thus maintaining backward compat. Some results dumping 1.5M actions below: first an unpatched tc which doesnt understand these features... prompt$ time -p tc actions ls action gact | grep index | wc -l 1500000 real 1388.43 user 2.07 sys 1386.79 Now lets see a patched tc which sets the correct flags when requesting a dump: prompt$ time -p updatedtc actions ls action gact | grep index | wc -l 1500000 real 178.13 user 2.02 sys 176.96 That is about 8x performance improvement for tc app which sets its receive buffer to about 32K. Signed-off-by: Jamal Hadi Salim <jhs@mojatatu.com> Reviewed-by: Jiri Pirko <jiri@mellanox.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-07-31 00:24:51 +07:00
};
static int tc_ctl_action(struct sk_buff *skb, struct nlmsghdr *n,
struct netlink_ext_ack *extack)
{
struct net *net = sock_net(skb->sk);
net sched actions: dump more than TCA_ACT_MAX_PRIO actions per batch When you dump hundreds of thousands of actions, getting only 32 per dump batch even when the socket buffer and memory allocations allow is inefficient. With this change, the user will get as many as possibly fitting within the given constraints available to the kernel. The top level action TLV space is extended. An attribute TCA_ROOT_FLAGS is used to carry flags; flag TCA_FLAG_LARGE_DUMP_ON is set by the user indicating the user is capable of processing these large dumps. Older user space which doesnt set this flag doesnt get the large (than 32) batches. The kernel uses the TCA_ROOT_COUNT attribute to tell the user how many actions are put in a single batch. As such user space app knows how long to iterate (independent of the type of action being dumped) instead of hardcoded maximum of 32 thus maintaining backward compat. Some results dumping 1.5M actions below: first an unpatched tc which doesnt understand these features... prompt$ time -p tc actions ls action gact | grep index | wc -l 1500000 real 1388.43 user 2.07 sys 1386.79 Now lets see a patched tc which sets the correct flags when requesting a dump: prompt$ time -p updatedtc actions ls action gact | grep index | wc -l 1500000 real 178.13 user 2.02 sys 176.96 That is about 8x performance improvement for tc app which sets its receive buffer to about 32K. Signed-off-by: Jamal Hadi Salim <jhs@mojatatu.com> Reviewed-by: Jiri Pirko <jiri@mellanox.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-07-31 00:24:51 +07:00
struct nlattr *tca[TCA_ROOT_MAX + 1];
u32 portid = skb ? NETLINK_CB(skb).portid : 0;
int ret = 0, ovr = 0;
if ((n->nlmsg_type != RTM_GETACTION) &&
!netlink_capable(skb, CAP_NET_ADMIN))
return -EPERM;
net sched actions: dump more than TCA_ACT_MAX_PRIO actions per batch When you dump hundreds of thousands of actions, getting only 32 per dump batch even when the socket buffer and memory allocations allow is inefficient. With this change, the user will get as many as possibly fitting within the given constraints available to the kernel. The top level action TLV space is extended. An attribute TCA_ROOT_FLAGS is used to carry flags; flag TCA_FLAG_LARGE_DUMP_ON is set by the user indicating the user is capable of processing these large dumps. Older user space which doesnt set this flag doesnt get the large (than 32) batches. The kernel uses the TCA_ROOT_COUNT attribute to tell the user how many actions are put in a single batch. As such user space app knows how long to iterate (independent of the type of action being dumped) instead of hardcoded maximum of 32 thus maintaining backward compat. Some results dumping 1.5M actions below: first an unpatched tc which doesnt understand these features... prompt$ time -p tc actions ls action gact | grep index | wc -l 1500000 real 1388.43 user 2.07 sys 1386.79 Now lets see a patched tc which sets the correct flags when requesting a dump: prompt$ time -p updatedtc actions ls action gact | grep index | wc -l 1500000 real 178.13 user 2.02 sys 176.96 That is about 8x performance improvement for tc app which sets its receive buffer to about 32K. Signed-off-by: Jamal Hadi Salim <jhs@mojatatu.com> Reviewed-by: Jiri Pirko <jiri@mellanox.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-07-31 00:24:51 +07:00
ret = nlmsg_parse(n, sizeof(struct tcamsg), tca, TCA_ROOT_MAX, NULL,
extack);
if (ret < 0)
return ret;
if (tca[TCA_ACT_TAB] == NULL) {
NL_SET_ERR_MSG(extack, "Netlink action attributes missing");
return -EINVAL;
}
/* n->nlmsg_flags & NLM_F_CREATE */
switch (n->nlmsg_type) {
case RTM_NEWACTION:
/* we are going to assume all other flags
* imply create only if it doesn't exist
* Note that CREATE | EXCL implies that
* but since we want avoid ambiguity (eg when flags
* is zero) then just set this
*/
if (n->nlmsg_flags & NLM_F_REPLACE)
ovr = 1;
replay:
ret = tcf_action_add(net, tca[TCA_ACT_TAB], n, portid, ovr,
extack);
if (ret == -EAGAIN)
goto replay;
break;
case RTM_DELACTION:
ret = tca_action_gd(net, tca[TCA_ACT_TAB], n,
portid, RTM_DELACTION, extack);
break;
case RTM_GETACTION:
ret = tca_action_gd(net, tca[TCA_ACT_TAB], n,
portid, RTM_GETACTION, extack);
break;
default:
BUG();
}
return ret;
}
net sched actions: dump more than TCA_ACT_MAX_PRIO actions per batch When you dump hundreds of thousands of actions, getting only 32 per dump batch even when the socket buffer and memory allocations allow is inefficient. With this change, the user will get as many as possibly fitting within the given constraints available to the kernel. The top level action TLV space is extended. An attribute TCA_ROOT_FLAGS is used to carry flags; flag TCA_FLAG_LARGE_DUMP_ON is set by the user indicating the user is capable of processing these large dumps. Older user space which doesnt set this flag doesnt get the large (than 32) batches. The kernel uses the TCA_ROOT_COUNT attribute to tell the user how many actions are put in a single batch. As such user space app knows how long to iterate (independent of the type of action being dumped) instead of hardcoded maximum of 32 thus maintaining backward compat. Some results dumping 1.5M actions below: first an unpatched tc which doesnt understand these features... prompt$ time -p tc actions ls action gact | grep index | wc -l 1500000 real 1388.43 user 2.07 sys 1386.79 Now lets see a patched tc which sets the correct flags when requesting a dump: prompt$ time -p updatedtc actions ls action gact | grep index | wc -l 1500000 real 178.13 user 2.02 sys 176.96 That is about 8x performance improvement for tc app which sets its receive buffer to about 32K. Signed-off-by: Jamal Hadi Salim <jhs@mojatatu.com> Reviewed-by: Jiri Pirko <jiri@mellanox.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-07-31 00:24:51 +07:00
static struct nlattr *find_dump_kind(struct nlattr **nla)
{
struct nlattr *tb1, *tb2[TCA_ACT_MAX + 1];
struct nlattr *tb[TCA_ACT_MAX_PRIO + 1];
struct nlattr *kind;
tb1 = nla[TCA_ACT_TAB];
if (tb1 == NULL)
return NULL;
if (nla_parse(tb, TCA_ACT_MAX_PRIO, nla_data(tb1),
NLMSG_ALIGN(nla_len(tb1)), NULL, NULL) < 0)
return NULL;
if (tb[1] == NULL)
return NULL;
if (nla_parse_nested(tb2, TCA_ACT_MAX, tb[1], NULL, NULL) < 0)
return NULL;
kind = tb2[TCA_ACT_KIND];
return kind;
}
static int tc_dump_action(struct sk_buff *skb, struct netlink_callback *cb)
{
struct net *net = sock_net(skb->sk);
struct nlmsghdr *nlh;
unsigned char *b = skb_tail_pointer(skb);
struct nlattr *nest;
struct tc_action_ops *a_o;
int ret = 0;
struct tcamsg *t = (struct tcamsg *) nlmsg_data(cb->nlh);
net sched actions: dump more than TCA_ACT_MAX_PRIO actions per batch When you dump hundreds of thousands of actions, getting only 32 per dump batch even when the socket buffer and memory allocations allow is inefficient. With this change, the user will get as many as possibly fitting within the given constraints available to the kernel. The top level action TLV space is extended. An attribute TCA_ROOT_FLAGS is used to carry flags; flag TCA_FLAG_LARGE_DUMP_ON is set by the user indicating the user is capable of processing these large dumps. Older user space which doesnt set this flag doesnt get the large (than 32) batches. The kernel uses the TCA_ROOT_COUNT attribute to tell the user how many actions are put in a single batch. As such user space app knows how long to iterate (independent of the type of action being dumped) instead of hardcoded maximum of 32 thus maintaining backward compat. Some results dumping 1.5M actions below: first an unpatched tc which doesnt understand these features... prompt$ time -p tc actions ls action gact | grep index | wc -l 1500000 real 1388.43 user 2.07 sys 1386.79 Now lets see a patched tc which sets the correct flags when requesting a dump: prompt$ time -p updatedtc actions ls action gact | grep index | wc -l 1500000 real 178.13 user 2.02 sys 176.96 That is about 8x performance improvement for tc app which sets its receive buffer to about 32K. Signed-off-by: Jamal Hadi Salim <jhs@mojatatu.com> Reviewed-by: Jiri Pirko <jiri@mellanox.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-07-31 00:24:51 +07:00
struct nlattr *tb[TCA_ROOT_MAX + 1];
struct nlattr *count_attr = NULL;
net sched actions: add time filter for action dumping This patch adds support for filtering based on time since last used. When we are dumping a large number of actions it is useful to have the option of filtering based on when the action was last used to reduce the amount of data crossing to user space. With this patch the user space app sets the TCA_ROOT_TIME_DELTA attribute with the value in milliseconds with "time of interest since now". The kernel converts this to jiffies and does the filtering comparison matching entries that have seen activity since then and returns them to user space. Old kernels and old tc continue to work in legacy mode since they dont specify this attribute. Some example (we have 400 actions bound to 400 filters); at installation time. Using updated when tc setting the time of interest to 120 seconds earlier (we see 400 actions): prompt$ hackedtc actions ls action gact since 120000| grep index | wc -l 400 go get some coffee and wait for > 120 seconds and try again: prompt$ hackedtc actions ls action gact since 120000 | grep index | wc -l 0 Lets see a filter bound to one of these actions: .... filter pref 10 u32 filter pref 10 u32 fh 800: ht divisor 1 filter pref 10 u32 fh 800::800 order 2048 key ht 800 bkt 0 flowid 1:10 (rule hit 2 success 1) match 7f000002/ffffffff at 12 (success 1 ) action order 1: gact action pass random type none pass val 0 index 23 ref 2 bind 1 installed 1145 sec used 802 sec Action statistics: Sent 84 bytes 1 pkt (dropped 0, overlimits 0 requeues 0) backlog 0b 0p requeues 0 .... that coffee took long, no? It was good. Now lets ping -c 1 127.0.0.2, then run the actions again: prompt$ hackedtc actions ls action gact since 120 | grep index | wc -l 1 More details please: prompt$ hackedtc -s actions ls action gact since 120000 action order 0: gact action pass random type none pass val 0 index 23 ref 2 bind 1 installed 1270 sec used 30 sec Action statistics: Sent 168 bytes 2 pkt (dropped 0, overlimits 0 requeues 0) backlog 0b 0p requeues 0 And the filter? filter pref 10 u32 filter pref 10 u32 fh 800: ht divisor 1 filter pref 10 u32 fh 800::800 order 2048 key ht 800 bkt 0 flowid 1:10 (rule hit 4 success 2) match 7f000002/ffffffff at 12 (success 2 ) action order 1: gact action pass random type none pass val 0 index 23 ref 2 bind 1 installed 1324 sec used 84 sec Action statistics: Sent 168 bytes 2 pkt (dropped 0, overlimits 0 requeues 0) backlog 0b 0p requeues 0 Signed-off-by: Jamal Hadi Salim <jhs@mojatatu.com> Reviewed-by: Jiri Pirko <jiri@mellanox.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-07-31 00:24:52 +07:00
unsigned long jiffy_since = 0;
net sched actions: dump more than TCA_ACT_MAX_PRIO actions per batch When you dump hundreds of thousands of actions, getting only 32 per dump batch even when the socket buffer and memory allocations allow is inefficient. With this change, the user will get as many as possibly fitting within the given constraints available to the kernel. The top level action TLV space is extended. An attribute TCA_ROOT_FLAGS is used to carry flags; flag TCA_FLAG_LARGE_DUMP_ON is set by the user indicating the user is capable of processing these large dumps. Older user space which doesnt set this flag doesnt get the large (than 32) batches. The kernel uses the TCA_ROOT_COUNT attribute to tell the user how many actions are put in a single batch. As such user space app knows how long to iterate (independent of the type of action being dumped) instead of hardcoded maximum of 32 thus maintaining backward compat. Some results dumping 1.5M actions below: first an unpatched tc which doesnt understand these features... prompt$ time -p tc actions ls action gact | grep index | wc -l 1500000 real 1388.43 user 2.07 sys 1386.79 Now lets see a patched tc which sets the correct flags when requesting a dump: prompt$ time -p updatedtc actions ls action gact | grep index | wc -l 1500000 real 178.13 user 2.02 sys 176.96 That is about 8x performance improvement for tc app which sets its receive buffer to about 32K. Signed-off-by: Jamal Hadi Salim <jhs@mojatatu.com> Reviewed-by: Jiri Pirko <jiri@mellanox.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-07-31 00:24:51 +07:00
struct nlattr *kind = NULL;
struct nla_bitfield32 bf;
net sched actions: add time filter for action dumping This patch adds support for filtering based on time since last used. When we are dumping a large number of actions it is useful to have the option of filtering based on when the action was last used to reduce the amount of data crossing to user space. With this patch the user space app sets the TCA_ROOT_TIME_DELTA attribute with the value in milliseconds with "time of interest since now". The kernel converts this to jiffies and does the filtering comparison matching entries that have seen activity since then and returns them to user space. Old kernels and old tc continue to work in legacy mode since they dont specify this attribute. Some example (we have 400 actions bound to 400 filters); at installation time. Using updated when tc setting the time of interest to 120 seconds earlier (we see 400 actions): prompt$ hackedtc actions ls action gact since 120000| grep index | wc -l 400 go get some coffee and wait for > 120 seconds and try again: prompt$ hackedtc actions ls action gact since 120000 | grep index | wc -l 0 Lets see a filter bound to one of these actions: .... filter pref 10 u32 filter pref 10 u32 fh 800: ht divisor 1 filter pref 10 u32 fh 800::800 order 2048 key ht 800 bkt 0 flowid 1:10 (rule hit 2 success 1) match 7f000002/ffffffff at 12 (success 1 ) action order 1: gact action pass random type none pass val 0 index 23 ref 2 bind 1 installed 1145 sec used 802 sec Action statistics: Sent 84 bytes 1 pkt (dropped 0, overlimits 0 requeues 0) backlog 0b 0p requeues 0 .... that coffee took long, no? It was good. Now lets ping -c 1 127.0.0.2, then run the actions again: prompt$ hackedtc actions ls action gact since 120 | grep index | wc -l 1 More details please: prompt$ hackedtc -s actions ls action gact since 120000 action order 0: gact action pass random type none pass val 0 index 23 ref 2 bind 1 installed 1270 sec used 30 sec Action statistics: Sent 168 bytes 2 pkt (dropped 0, overlimits 0 requeues 0) backlog 0b 0p requeues 0 And the filter? filter pref 10 u32 filter pref 10 u32 fh 800: ht divisor 1 filter pref 10 u32 fh 800::800 order 2048 key ht 800 bkt 0 flowid 1:10 (rule hit 4 success 2) match 7f000002/ffffffff at 12 (success 2 ) action order 1: gact action pass random type none pass val 0 index 23 ref 2 bind 1 installed 1324 sec used 84 sec Action statistics: Sent 168 bytes 2 pkt (dropped 0, overlimits 0 requeues 0) backlog 0b 0p requeues 0 Signed-off-by: Jamal Hadi Salim <jhs@mojatatu.com> Reviewed-by: Jiri Pirko <jiri@mellanox.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-07-31 00:24:52 +07:00
u32 msecs_since = 0;
net sched actions: dump more than TCA_ACT_MAX_PRIO actions per batch When you dump hundreds of thousands of actions, getting only 32 per dump batch even when the socket buffer and memory allocations allow is inefficient. With this change, the user will get as many as possibly fitting within the given constraints available to the kernel. The top level action TLV space is extended. An attribute TCA_ROOT_FLAGS is used to carry flags; flag TCA_FLAG_LARGE_DUMP_ON is set by the user indicating the user is capable of processing these large dumps. Older user space which doesnt set this flag doesnt get the large (than 32) batches. The kernel uses the TCA_ROOT_COUNT attribute to tell the user how many actions are put in a single batch. As such user space app knows how long to iterate (independent of the type of action being dumped) instead of hardcoded maximum of 32 thus maintaining backward compat. Some results dumping 1.5M actions below: first an unpatched tc which doesnt understand these features... prompt$ time -p tc actions ls action gact | grep index | wc -l 1500000 real 1388.43 user 2.07 sys 1386.79 Now lets see a patched tc which sets the correct flags when requesting a dump: prompt$ time -p updatedtc actions ls action gact | grep index | wc -l 1500000 real 178.13 user 2.02 sys 176.96 That is about 8x performance improvement for tc app which sets its receive buffer to about 32K. Signed-off-by: Jamal Hadi Salim <jhs@mojatatu.com> Reviewed-by: Jiri Pirko <jiri@mellanox.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-07-31 00:24:51 +07:00
u32 act_count = 0;
ret = nlmsg_parse(cb->nlh, sizeof(struct tcamsg), tb, TCA_ROOT_MAX,
tcaa_policy, cb->extack);
net sched actions: dump more than TCA_ACT_MAX_PRIO actions per batch When you dump hundreds of thousands of actions, getting only 32 per dump batch even when the socket buffer and memory allocations allow is inefficient. With this change, the user will get as many as possibly fitting within the given constraints available to the kernel. The top level action TLV space is extended. An attribute TCA_ROOT_FLAGS is used to carry flags; flag TCA_FLAG_LARGE_DUMP_ON is set by the user indicating the user is capable of processing these large dumps. Older user space which doesnt set this flag doesnt get the large (than 32) batches. The kernel uses the TCA_ROOT_COUNT attribute to tell the user how many actions are put in a single batch. As such user space app knows how long to iterate (independent of the type of action being dumped) instead of hardcoded maximum of 32 thus maintaining backward compat. Some results dumping 1.5M actions below: first an unpatched tc which doesnt understand these features... prompt$ time -p tc actions ls action gact | grep index | wc -l 1500000 real 1388.43 user 2.07 sys 1386.79 Now lets see a patched tc which sets the correct flags when requesting a dump: prompt$ time -p updatedtc actions ls action gact | grep index | wc -l 1500000 real 178.13 user 2.02 sys 176.96 That is about 8x performance improvement for tc app which sets its receive buffer to about 32K. Signed-off-by: Jamal Hadi Salim <jhs@mojatatu.com> Reviewed-by: Jiri Pirko <jiri@mellanox.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-07-31 00:24:51 +07:00
if (ret < 0)
return ret;
net sched actions: dump more than TCA_ACT_MAX_PRIO actions per batch When you dump hundreds of thousands of actions, getting only 32 per dump batch even when the socket buffer and memory allocations allow is inefficient. With this change, the user will get as many as possibly fitting within the given constraints available to the kernel. The top level action TLV space is extended. An attribute TCA_ROOT_FLAGS is used to carry flags; flag TCA_FLAG_LARGE_DUMP_ON is set by the user indicating the user is capable of processing these large dumps. Older user space which doesnt set this flag doesnt get the large (than 32) batches. The kernel uses the TCA_ROOT_COUNT attribute to tell the user how many actions are put in a single batch. As such user space app knows how long to iterate (independent of the type of action being dumped) instead of hardcoded maximum of 32 thus maintaining backward compat. Some results dumping 1.5M actions below: first an unpatched tc which doesnt understand these features... prompt$ time -p tc actions ls action gact | grep index | wc -l 1500000 real 1388.43 user 2.07 sys 1386.79 Now lets see a patched tc which sets the correct flags when requesting a dump: prompt$ time -p updatedtc actions ls action gact | grep index | wc -l 1500000 real 178.13 user 2.02 sys 176.96 That is about 8x performance improvement for tc app which sets its receive buffer to about 32K. Signed-off-by: Jamal Hadi Salim <jhs@mojatatu.com> Reviewed-by: Jiri Pirko <jiri@mellanox.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-07-31 00:24:51 +07:00
kind = find_dump_kind(tb);
if (kind == NULL) {
pr_info("tc_dump_action: action bad kind\n");
return 0;
}
a_o = tc_lookup_action(kind);
if (a_o == NULL)
return 0;
net sched actions: dump more than TCA_ACT_MAX_PRIO actions per batch When you dump hundreds of thousands of actions, getting only 32 per dump batch even when the socket buffer and memory allocations allow is inefficient. With this change, the user will get as many as possibly fitting within the given constraints available to the kernel. The top level action TLV space is extended. An attribute TCA_ROOT_FLAGS is used to carry flags; flag TCA_FLAG_LARGE_DUMP_ON is set by the user indicating the user is capable of processing these large dumps. Older user space which doesnt set this flag doesnt get the large (than 32) batches. The kernel uses the TCA_ROOT_COUNT attribute to tell the user how many actions are put in a single batch. As such user space app knows how long to iterate (independent of the type of action being dumped) instead of hardcoded maximum of 32 thus maintaining backward compat. Some results dumping 1.5M actions below: first an unpatched tc which doesnt understand these features... prompt$ time -p tc actions ls action gact | grep index | wc -l 1500000 real 1388.43 user 2.07 sys 1386.79 Now lets see a patched tc which sets the correct flags when requesting a dump: prompt$ time -p updatedtc actions ls action gact | grep index | wc -l 1500000 real 178.13 user 2.02 sys 176.96 That is about 8x performance improvement for tc app which sets its receive buffer to about 32K. Signed-off-by: Jamal Hadi Salim <jhs@mojatatu.com> Reviewed-by: Jiri Pirko <jiri@mellanox.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-07-31 00:24:51 +07:00
cb->args[2] = 0;
if (tb[TCA_ROOT_FLAGS]) {
bf = nla_get_bitfield32(tb[TCA_ROOT_FLAGS]);
cb->args[2] = bf.value;
}
net sched actions: add time filter for action dumping This patch adds support for filtering based on time since last used. When we are dumping a large number of actions it is useful to have the option of filtering based on when the action was last used to reduce the amount of data crossing to user space. With this patch the user space app sets the TCA_ROOT_TIME_DELTA attribute with the value in milliseconds with "time of interest since now". The kernel converts this to jiffies and does the filtering comparison matching entries that have seen activity since then and returns them to user space. Old kernels and old tc continue to work in legacy mode since they dont specify this attribute. Some example (we have 400 actions bound to 400 filters); at installation time. Using updated when tc setting the time of interest to 120 seconds earlier (we see 400 actions): prompt$ hackedtc actions ls action gact since 120000| grep index | wc -l 400 go get some coffee and wait for > 120 seconds and try again: prompt$ hackedtc actions ls action gact since 120000 | grep index | wc -l 0 Lets see a filter bound to one of these actions: .... filter pref 10 u32 filter pref 10 u32 fh 800: ht divisor 1 filter pref 10 u32 fh 800::800 order 2048 key ht 800 bkt 0 flowid 1:10 (rule hit 2 success 1) match 7f000002/ffffffff at 12 (success 1 ) action order 1: gact action pass random type none pass val 0 index 23 ref 2 bind 1 installed 1145 sec used 802 sec Action statistics: Sent 84 bytes 1 pkt (dropped 0, overlimits 0 requeues 0) backlog 0b 0p requeues 0 .... that coffee took long, no? It was good. Now lets ping -c 1 127.0.0.2, then run the actions again: prompt$ hackedtc actions ls action gact since 120 | grep index | wc -l 1 More details please: prompt$ hackedtc -s actions ls action gact since 120000 action order 0: gact action pass random type none pass val 0 index 23 ref 2 bind 1 installed 1270 sec used 30 sec Action statistics: Sent 168 bytes 2 pkt (dropped 0, overlimits 0 requeues 0) backlog 0b 0p requeues 0 And the filter? filter pref 10 u32 filter pref 10 u32 fh 800: ht divisor 1 filter pref 10 u32 fh 800::800 order 2048 key ht 800 bkt 0 flowid 1:10 (rule hit 4 success 2) match 7f000002/ffffffff at 12 (success 2 ) action order 1: gact action pass random type none pass val 0 index 23 ref 2 bind 1 installed 1324 sec used 84 sec Action statistics: Sent 168 bytes 2 pkt (dropped 0, overlimits 0 requeues 0) backlog 0b 0p requeues 0 Signed-off-by: Jamal Hadi Salim <jhs@mojatatu.com> Reviewed-by: Jiri Pirko <jiri@mellanox.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-07-31 00:24:52 +07:00
if (tb[TCA_ROOT_TIME_DELTA]) {
msecs_since = nla_get_u32(tb[TCA_ROOT_TIME_DELTA]);
}
nlh = nlmsg_put(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq,
cb->nlh->nlmsg_type, sizeof(*t), 0);
if (!nlh)
goto out_module_put;
net sched actions: dump more than TCA_ACT_MAX_PRIO actions per batch When you dump hundreds of thousands of actions, getting only 32 per dump batch even when the socket buffer and memory allocations allow is inefficient. With this change, the user will get as many as possibly fitting within the given constraints available to the kernel. The top level action TLV space is extended. An attribute TCA_ROOT_FLAGS is used to carry flags; flag TCA_FLAG_LARGE_DUMP_ON is set by the user indicating the user is capable of processing these large dumps. Older user space which doesnt set this flag doesnt get the large (than 32) batches. The kernel uses the TCA_ROOT_COUNT attribute to tell the user how many actions are put in a single batch. As such user space app knows how long to iterate (independent of the type of action being dumped) instead of hardcoded maximum of 32 thus maintaining backward compat. Some results dumping 1.5M actions below: first an unpatched tc which doesnt understand these features... prompt$ time -p tc actions ls action gact | grep index | wc -l 1500000 real 1388.43 user 2.07 sys 1386.79 Now lets see a patched tc which sets the correct flags when requesting a dump: prompt$ time -p updatedtc actions ls action gact | grep index | wc -l 1500000 real 178.13 user 2.02 sys 176.96 That is about 8x performance improvement for tc app which sets its receive buffer to about 32K. Signed-off-by: Jamal Hadi Salim <jhs@mojatatu.com> Reviewed-by: Jiri Pirko <jiri@mellanox.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-07-31 00:24:51 +07:00
net sched actions: add time filter for action dumping This patch adds support for filtering based on time since last used. When we are dumping a large number of actions it is useful to have the option of filtering based on when the action was last used to reduce the amount of data crossing to user space. With this patch the user space app sets the TCA_ROOT_TIME_DELTA attribute with the value in milliseconds with "time of interest since now". The kernel converts this to jiffies and does the filtering comparison matching entries that have seen activity since then and returns them to user space. Old kernels and old tc continue to work in legacy mode since they dont specify this attribute. Some example (we have 400 actions bound to 400 filters); at installation time. Using updated when tc setting the time of interest to 120 seconds earlier (we see 400 actions): prompt$ hackedtc actions ls action gact since 120000| grep index | wc -l 400 go get some coffee and wait for > 120 seconds and try again: prompt$ hackedtc actions ls action gact since 120000 | grep index | wc -l 0 Lets see a filter bound to one of these actions: .... filter pref 10 u32 filter pref 10 u32 fh 800: ht divisor 1 filter pref 10 u32 fh 800::800 order 2048 key ht 800 bkt 0 flowid 1:10 (rule hit 2 success 1) match 7f000002/ffffffff at 12 (success 1 ) action order 1: gact action pass random type none pass val 0 index 23 ref 2 bind 1 installed 1145 sec used 802 sec Action statistics: Sent 84 bytes 1 pkt (dropped 0, overlimits 0 requeues 0) backlog 0b 0p requeues 0 .... that coffee took long, no? It was good. Now lets ping -c 1 127.0.0.2, then run the actions again: prompt$ hackedtc actions ls action gact since 120 | grep index | wc -l 1 More details please: prompt$ hackedtc -s actions ls action gact since 120000 action order 0: gact action pass random type none pass val 0 index 23 ref 2 bind 1 installed 1270 sec used 30 sec Action statistics: Sent 168 bytes 2 pkt (dropped 0, overlimits 0 requeues 0) backlog 0b 0p requeues 0 And the filter? filter pref 10 u32 filter pref 10 u32 fh 800: ht divisor 1 filter pref 10 u32 fh 800::800 order 2048 key ht 800 bkt 0 flowid 1:10 (rule hit 4 success 2) match 7f000002/ffffffff at 12 (success 2 ) action order 1: gact action pass random type none pass val 0 index 23 ref 2 bind 1 installed 1324 sec used 84 sec Action statistics: Sent 168 bytes 2 pkt (dropped 0, overlimits 0 requeues 0) backlog 0b 0p requeues 0 Signed-off-by: Jamal Hadi Salim <jhs@mojatatu.com> Reviewed-by: Jiri Pirko <jiri@mellanox.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-07-31 00:24:52 +07:00
if (msecs_since)
jiffy_since = jiffies - msecs_to_jiffies(msecs_since);
t = nlmsg_data(nlh);
t->tca_family = AF_UNSPEC;
t->tca__pad1 = 0;
t->tca__pad2 = 0;
net sched actions: add time filter for action dumping This patch adds support for filtering based on time since last used. When we are dumping a large number of actions it is useful to have the option of filtering based on when the action was last used to reduce the amount of data crossing to user space. With this patch the user space app sets the TCA_ROOT_TIME_DELTA attribute with the value in milliseconds with "time of interest since now". The kernel converts this to jiffies and does the filtering comparison matching entries that have seen activity since then and returns them to user space. Old kernels and old tc continue to work in legacy mode since they dont specify this attribute. Some example (we have 400 actions bound to 400 filters); at installation time. Using updated when tc setting the time of interest to 120 seconds earlier (we see 400 actions): prompt$ hackedtc actions ls action gact since 120000| grep index | wc -l 400 go get some coffee and wait for > 120 seconds and try again: prompt$ hackedtc actions ls action gact since 120000 | grep index | wc -l 0 Lets see a filter bound to one of these actions: .... filter pref 10 u32 filter pref 10 u32 fh 800: ht divisor 1 filter pref 10 u32 fh 800::800 order 2048 key ht 800 bkt 0 flowid 1:10 (rule hit 2 success 1) match 7f000002/ffffffff at 12 (success 1 ) action order 1: gact action pass random type none pass val 0 index 23 ref 2 bind 1 installed 1145 sec used 802 sec Action statistics: Sent 84 bytes 1 pkt (dropped 0, overlimits 0 requeues 0) backlog 0b 0p requeues 0 .... that coffee took long, no? It was good. Now lets ping -c 1 127.0.0.2, then run the actions again: prompt$ hackedtc actions ls action gact since 120 | grep index | wc -l 1 More details please: prompt$ hackedtc -s actions ls action gact since 120000 action order 0: gact action pass random type none pass val 0 index 23 ref 2 bind 1 installed 1270 sec used 30 sec Action statistics: Sent 168 bytes 2 pkt (dropped 0, overlimits 0 requeues 0) backlog 0b 0p requeues 0 And the filter? filter pref 10 u32 filter pref 10 u32 fh 800: ht divisor 1 filter pref 10 u32 fh 800::800 order 2048 key ht 800 bkt 0 flowid 1:10 (rule hit 4 success 2) match 7f000002/ffffffff at 12 (success 2 ) action order 1: gact action pass random type none pass val 0 index 23 ref 2 bind 1 installed 1324 sec used 84 sec Action statistics: Sent 168 bytes 2 pkt (dropped 0, overlimits 0 requeues 0) backlog 0b 0p requeues 0 Signed-off-by: Jamal Hadi Salim <jhs@mojatatu.com> Reviewed-by: Jiri Pirko <jiri@mellanox.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-07-31 00:24:52 +07:00
cb->args[3] = jiffy_since;
net sched actions: dump more than TCA_ACT_MAX_PRIO actions per batch When you dump hundreds of thousands of actions, getting only 32 per dump batch even when the socket buffer and memory allocations allow is inefficient. With this change, the user will get as many as possibly fitting within the given constraints available to the kernel. The top level action TLV space is extended. An attribute TCA_ROOT_FLAGS is used to carry flags; flag TCA_FLAG_LARGE_DUMP_ON is set by the user indicating the user is capable of processing these large dumps. Older user space which doesnt set this flag doesnt get the large (than 32) batches. The kernel uses the TCA_ROOT_COUNT attribute to tell the user how many actions are put in a single batch. As such user space app knows how long to iterate (independent of the type of action being dumped) instead of hardcoded maximum of 32 thus maintaining backward compat. Some results dumping 1.5M actions below: first an unpatched tc which doesnt understand these features... prompt$ time -p tc actions ls action gact | grep index | wc -l 1500000 real 1388.43 user 2.07 sys 1386.79 Now lets see a patched tc which sets the correct flags when requesting a dump: prompt$ time -p updatedtc actions ls action gact | grep index | wc -l 1500000 real 178.13 user 2.02 sys 176.96 That is about 8x performance improvement for tc app which sets its receive buffer to about 32K. Signed-off-by: Jamal Hadi Salim <jhs@mojatatu.com> Reviewed-by: Jiri Pirko <jiri@mellanox.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-07-31 00:24:51 +07:00
count_attr = nla_reserve(skb, TCA_ROOT_COUNT, sizeof(u32));
if (!count_attr)
goto out_module_put;
nest = nla_nest_start(skb, TCA_ACT_TAB);
if (nest == NULL)
goto out_module_put;
ret = a_o->walk(net, skb, cb, RTM_GETACTION, a_o, NULL);
if (ret < 0)
goto out_module_put;
if (ret > 0) {
nla_nest_end(skb, nest);
ret = skb->len;
net sched actions: dump more than TCA_ACT_MAX_PRIO actions per batch When you dump hundreds of thousands of actions, getting only 32 per dump batch even when the socket buffer and memory allocations allow is inefficient. With this change, the user will get as many as possibly fitting within the given constraints available to the kernel. The top level action TLV space is extended. An attribute TCA_ROOT_FLAGS is used to carry flags; flag TCA_FLAG_LARGE_DUMP_ON is set by the user indicating the user is capable of processing these large dumps. Older user space which doesnt set this flag doesnt get the large (than 32) batches. The kernel uses the TCA_ROOT_COUNT attribute to tell the user how many actions are put in a single batch. As such user space app knows how long to iterate (independent of the type of action being dumped) instead of hardcoded maximum of 32 thus maintaining backward compat. Some results dumping 1.5M actions below: first an unpatched tc which doesnt understand these features... prompt$ time -p tc actions ls action gact | grep index | wc -l 1500000 real 1388.43 user 2.07 sys 1386.79 Now lets see a patched tc which sets the correct flags when requesting a dump: prompt$ time -p updatedtc actions ls action gact | grep index | wc -l 1500000 real 178.13 user 2.02 sys 176.96 That is about 8x performance improvement for tc app which sets its receive buffer to about 32K. Signed-off-by: Jamal Hadi Salim <jhs@mojatatu.com> Reviewed-by: Jiri Pirko <jiri@mellanox.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-07-31 00:24:51 +07:00
act_count = cb->args[1];
memcpy(nla_data(count_attr), &act_count, sizeof(u32));
cb->args[1] = 0;
} else
nlmsg_trim(skb, b);
nlh->nlmsg_len = skb_tail_pointer(skb) - b;
if (NETLINK_CB(cb->skb).portid && ret)
nlh->nlmsg_flags |= NLM_F_MULTI;
module_put(a_o->owner);
return skb->len;
out_module_put:
module_put(a_o->owner);
nlmsg_trim(skb, b);
return skb->len;
}
struct tcf_action_net {
struct rhashtable egdev_ht;
};
static unsigned int tcf_action_net_id;
struct tcf_action_egdev_cb {
struct list_head list;
tc_setup_cb_t *cb;
void *cb_priv;
};
struct tcf_action_egdev {
struct rhash_head ht_node;
const struct net_device *dev;
unsigned int refcnt;
struct list_head cb_list;
};
static const struct rhashtable_params tcf_action_egdev_ht_params = {
.key_offset = offsetof(struct tcf_action_egdev, dev),
.head_offset = offsetof(struct tcf_action_egdev, ht_node),
.key_len = sizeof(const struct net_device *),
};
static struct tcf_action_egdev *
tcf_action_egdev_lookup(const struct net_device *dev)
{
struct net *net = dev_net(dev);
struct tcf_action_net *tan = net_generic(net, tcf_action_net_id);
return rhashtable_lookup_fast(&tan->egdev_ht, &dev,
tcf_action_egdev_ht_params);
}
static struct tcf_action_egdev *
tcf_action_egdev_get(const struct net_device *dev)
{
struct tcf_action_egdev *egdev;
struct tcf_action_net *tan;
egdev = tcf_action_egdev_lookup(dev);
if (egdev)
goto inc_ref;
egdev = kzalloc(sizeof(*egdev), GFP_KERNEL);
if (!egdev)
return NULL;
INIT_LIST_HEAD(&egdev->cb_list);
egdev->dev = dev;
tan = net_generic(dev_net(dev), tcf_action_net_id);
rhashtable_insert_fast(&tan->egdev_ht, &egdev->ht_node,
tcf_action_egdev_ht_params);
inc_ref:
egdev->refcnt++;
return egdev;
}
static void tcf_action_egdev_put(struct tcf_action_egdev *egdev)
{
struct tcf_action_net *tan;
if (--egdev->refcnt)
return;
tan = net_generic(dev_net(egdev->dev), tcf_action_net_id);
rhashtable_remove_fast(&tan->egdev_ht, &egdev->ht_node,
tcf_action_egdev_ht_params);
kfree(egdev);
}
static struct tcf_action_egdev_cb *
tcf_action_egdev_cb_lookup(struct tcf_action_egdev *egdev,
tc_setup_cb_t *cb, void *cb_priv)
{
struct tcf_action_egdev_cb *egdev_cb;
list_for_each_entry(egdev_cb, &egdev->cb_list, list)
if (egdev_cb->cb == cb && egdev_cb->cb_priv == cb_priv)
return egdev_cb;
return NULL;
}
static int tcf_action_egdev_cb_call(struct tcf_action_egdev *egdev,
enum tc_setup_type type,
void *type_data, bool err_stop)
{
struct tcf_action_egdev_cb *egdev_cb;
int ok_count = 0;
int err;
list_for_each_entry(egdev_cb, &egdev->cb_list, list) {
err = egdev_cb->cb(type, type_data, egdev_cb->cb_priv);
if (err) {
if (err_stop)
return err;
} else {
ok_count++;
}
}
return ok_count;
}
static int tcf_action_egdev_cb_add(struct tcf_action_egdev *egdev,
tc_setup_cb_t *cb, void *cb_priv)
{
struct tcf_action_egdev_cb *egdev_cb;
egdev_cb = tcf_action_egdev_cb_lookup(egdev, cb, cb_priv);
if (WARN_ON(egdev_cb))
return -EEXIST;
egdev_cb = kzalloc(sizeof(*egdev_cb), GFP_KERNEL);
if (!egdev_cb)
return -ENOMEM;
egdev_cb->cb = cb;
egdev_cb->cb_priv = cb_priv;
list_add(&egdev_cb->list, &egdev->cb_list);
return 0;
}
static void tcf_action_egdev_cb_del(struct tcf_action_egdev *egdev,
tc_setup_cb_t *cb, void *cb_priv)
{
struct tcf_action_egdev_cb *egdev_cb;
egdev_cb = tcf_action_egdev_cb_lookup(egdev, cb, cb_priv);
if (WARN_ON(!egdev_cb))
return;
list_del(&egdev_cb->list);
kfree(egdev_cb);
}
static int __tc_setup_cb_egdev_register(const struct net_device *dev,
tc_setup_cb_t *cb, void *cb_priv)
{
struct tcf_action_egdev *egdev = tcf_action_egdev_get(dev);
int err;
if (!egdev)
return -ENOMEM;
err = tcf_action_egdev_cb_add(egdev, cb, cb_priv);
if (err)
goto err_cb_add;
return 0;
err_cb_add:
tcf_action_egdev_put(egdev);
return err;
}
int tc_setup_cb_egdev_register(const struct net_device *dev,
tc_setup_cb_t *cb, void *cb_priv)
{
int err;
rtnl_lock();
err = __tc_setup_cb_egdev_register(dev, cb, cb_priv);
rtnl_unlock();
return err;
}
EXPORT_SYMBOL_GPL(tc_setup_cb_egdev_register);
static void __tc_setup_cb_egdev_unregister(const struct net_device *dev,
tc_setup_cb_t *cb, void *cb_priv)
{
struct tcf_action_egdev *egdev = tcf_action_egdev_lookup(dev);
if (WARN_ON(!egdev))
return;
tcf_action_egdev_cb_del(egdev, cb, cb_priv);
tcf_action_egdev_put(egdev);
}
void tc_setup_cb_egdev_unregister(const struct net_device *dev,
tc_setup_cb_t *cb, void *cb_priv)
{
rtnl_lock();
__tc_setup_cb_egdev_unregister(dev, cb, cb_priv);
rtnl_unlock();
}
EXPORT_SYMBOL_GPL(tc_setup_cb_egdev_unregister);
int tc_setup_cb_egdev_call(const struct net_device *dev,
enum tc_setup_type type, void *type_data,
bool err_stop)
{
struct tcf_action_egdev *egdev = tcf_action_egdev_lookup(dev);
if (!egdev)
return 0;
return tcf_action_egdev_cb_call(egdev, type, type_data, err_stop);
}
EXPORT_SYMBOL_GPL(tc_setup_cb_egdev_call);
static __net_init int tcf_action_net_init(struct net *net)
{
struct tcf_action_net *tan = net_generic(net, tcf_action_net_id);
return rhashtable_init(&tan->egdev_ht, &tcf_action_egdev_ht_params);
}
static void __net_exit tcf_action_net_exit(struct net *net)
{
struct tcf_action_net *tan = net_generic(net, tcf_action_net_id);
rhashtable_destroy(&tan->egdev_ht);
}
static struct pernet_operations tcf_action_net_ops = {
.init = tcf_action_net_init,
.exit = tcf_action_net_exit,
.id = &tcf_action_net_id,
.size = sizeof(struct tcf_action_net),
};
static int __init tc_action_init(void)
{
int err;
err = register_pernet_subsys(&tcf_action_net_ops);
if (err)
return err;
rtnl_register(PF_UNSPEC, RTM_NEWACTION, tc_ctl_action, NULL, 0);
rtnl_register(PF_UNSPEC, RTM_DELACTION, tc_ctl_action, NULL, 0);
rtnl_register(PF_UNSPEC, RTM_GETACTION, tc_ctl_action, tc_dump_action,
0);
return 0;
}
subsys_initcall(tc_action_init);