2019-05-27 14:55:01 +08:00
|
|
|
// SPDX-License-Identifier: GPL-2.0-or-later
|
2005-04-17 06:20:36 +08:00
|
|
|
/*
|
2014-11-06 03:51:51 +08:00
|
|
|
* net/sched/act_police.c Input police filter
|
2005-04-17 06:20:36 +08:00
|
|
|
*
|
|
|
|
* Authors: Alexey Kuznetsov, <kuznet@ms2.inr.ac.ru>
|
|
|
|
* J Hadi Salim (action changes)
|
|
|
|
*/
|
|
|
|
|
|
|
|
#include <linux/module.h>
|
|
|
|
#include <linux/types.h>
|
|
|
|
#include <linux/kernel.h>
|
|
|
|
#include <linux/string.h>
|
|
|
|
#include <linux/errno.h>
|
|
|
|
#include <linux/skbuff.h>
|
|
|
|
#include <linux/rtnetlink.h>
|
|
|
|
#include <linux/init.h>
|
include cleanup: Update gfp.h and slab.h includes to prepare for breaking implicit slab.h inclusion from percpu.h
percpu.h is included by sched.h and module.h and thus ends up being
included when building most .c files. percpu.h includes slab.h which
in turn includes gfp.h making everything defined by the two files
universally available and complicating inclusion dependencies.
percpu.h -> slab.h dependency is about to be removed. Prepare for
this change by updating users of gfp and slab facilities include those
headers directly instead of assuming availability. As this conversion
needs to touch large number of source files, the following script is
used as the basis of conversion.
http://userweb.kernel.org/~tj/misc/slabh-sweep.py
The script does the followings.
* Scan files for gfp and slab usages and update includes such that
only the necessary includes are there. ie. if only gfp is used,
gfp.h, if slab is used, slab.h.
* When the script inserts a new include, it looks at the include
blocks and try to put the new include such that its order conforms
to its surrounding. It's put in the include block which contains
core kernel includes, in the same order that the rest are ordered -
alphabetical, Christmas tree, rev-Xmas-tree or at the end if there
doesn't seem to be any matching order.
* If the script can't find a place to put a new include (mostly
because the file doesn't have fitting include block), it prints out
an error message indicating which .h file needs to be added to the
file.
The conversion was done in the following steps.
1. The initial automatic conversion of all .c files updated slightly
over 4000 files, deleting around 700 includes and adding ~480 gfp.h
and ~3000 slab.h inclusions. The script emitted errors for ~400
files.
2. Each error was manually checked. Some didn't need the inclusion,
some needed manual addition while adding it to implementation .h or
embedding .c file was more appropriate for others. This step added
inclusions to around 150 files.
3. The script was run again and the output was compared to the edits
from #2 to make sure no file was left behind.
4. Several build tests were done and a couple of problems were fixed.
e.g. lib/decompress_*.c used malloc/free() wrappers around slab
APIs requiring slab.h to be added manually.
5. The script was run on all .h files but without automatically
editing them as sprinkling gfp.h and slab.h inclusions around .h
files could easily lead to inclusion dependency hell. Most gfp.h
inclusion directives were ignored as stuff from gfp.h was usually
wildly available and often used in preprocessor macros. Each
slab.h inclusion directive was examined and added manually as
necessary.
6. percpu.h was updated not to include slab.h.
7. Build test were done on the following configurations and failures
were fixed. CONFIG_GCOV_KERNEL was turned off for all tests (as my
distributed build env didn't work with gcov compiles) and a few
more options had to be turned off depending on archs to make things
build (like ipr on powerpc/64 which failed due to missing writeq).
* x86 and x86_64 UP and SMP allmodconfig and a custom test config.
* powerpc and powerpc64 SMP allmodconfig
* sparc and sparc64 SMP allmodconfig
* ia64 SMP allmodconfig
* s390 SMP allmodconfig
* alpha SMP allmodconfig
* um on x86_64 SMP allmodconfig
8. percpu.h modifications were reverted so that it could be applied as
a separate patch and serve as bisection point.
Given the fact that I had only a couple of failures from tests on step
6, I'm fairly confident about the coverage of this conversion patch.
If there is a breakage, it's likely to be something in one of the arch
headers which should be easily discoverable easily on most builds of
the specific arch.
Signed-off-by: Tejun Heo <tj@kernel.org>
Guess-its-ok-by: Christoph Lameter <cl@linux-foundation.org>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
2010-03-24 16:04:11 +08:00
|
|
|
#include <linux/slab.h>
|
2005-04-17 06:20:36 +08:00
|
|
|
#include <net/act_api.h>
|
2007-03-26 14:06:12 +08:00
|
|
|
#include <net/netlink.h>
|
2019-03-20 22:00:08 +08:00
|
|
|
#include <net/pkt_cls.h>
|
2019-05-04 19:46:21 +08:00
|
|
|
#include <net/tc_act/tc_police.h>
|
2006-12-01 11:54:05 +08:00
|
|
|
|
2006-08-22 14:54:55 +08:00
|
|
|
/* Each policer is serialized by its individual spinlock */
|
2005-04-17 06:20:36 +08:00
|
|
|
|
netns: make struct pernet_operations::id unsigned int
Make struct pernet_operations::id unsigned.
There are 2 reasons to do so:
1)
This field is really an index into an zero based array and
thus is unsigned entity. Using negative value is out-of-bound
access by definition.
2)
On x86_64 unsigned 32-bit data which are mixed with pointers
via array indexing or offsets added or subtracted to pointers
are preffered to signed 32-bit data.
"int" being used as an array index needs to be sign-extended
to 64-bit before being used.
void f(long *p, int i)
{
g(p[i]);
}
roughly translates to
movsx rsi, esi
mov rdi, [rsi+...]
call g
MOVSX is 3 byte instruction which isn't necessary if the variable is
unsigned because x86_64 is zero extending by default.
Now, there is net_generic() function which, you guessed it right, uses
"int" as an array index:
static inline void *net_generic(const struct net *net, int id)
{
...
ptr = ng->ptr[id - 1];
...
}
And this function is used a lot, so those sign extensions add up.
Patch snipes ~1730 bytes on allyesconfig kernel (without all junk
messing with code generation):
add/remove: 0/0 grow/shrink: 70/598 up/down: 396/-2126 (-1730)
Unfortunately some functions actually grow bigger.
This is a semmingly random artefact of code generation with register
allocator being used differently. gcc decides that some variable
needs to live in new r8+ registers and every access now requires REX
prefix. Or it is shifted into r12, so [r12+0] addressing mode has to be
used which is longer than [r8]
However, overall balance is in negative direction:
add/remove: 0/0 grow/shrink: 70/598 up/down: 396/-2126 (-1730)
function old new delta
nfsd4_lock 3886 3959 +73
tipc_link_build_proto_msg 1096 1140 +44
mac80211_hwsim_new_radio 2776 2808 +32
tipc_mon_rcv 1032 1058 +26
svcauth_gss_legacy_init 1413 1429 +16
tipc_bcbase_select_primary 379 392 +13
nfsd4_exchange_id 1247 1260 +13
nfsd4_setclientid_confirm 782 793 +11
...
put_client_renew_locked 494 480 -14
ip_set_sockfn_get 730 716 -14
geneve_sock_add 829 813 -16
nfsd4_sequence_done 721 703 -18
nlmclnt_lookup_host 708 686 -22
nfsd4_lockt 1085 1063 -22
nfs_get_client 1077 1050 -27
tcf_bpf_init 1106 1076 -30
nfsd4_encode_fattr 5997 5930 -67
Total: Before=154856051, After=154854321, chg -0.00%
Signed-off-by: Alexey Dobriyan <adobriyan@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2016-11-17 09:58:21 +08:00
|
|
|
static unsigned int police_net_id;
|
2016-07-26 07:09:41 +08:00
|
|
|
static struct tc_action_ops act_police_ops;
|
2016-02-23 07:57:53 +08:00
|
|
|
|
2018-08-12 21:34:56 +08:00
|
|
|
static int tcf_police_walker(struct net *net, struct sk_buff *skb,
|
2016-02-23 07:57:53 +08:00
|
|
|
struct netlink_callback *cb, int type,
|
2018-02-15 23:54:58 +08:00
|
|
|
const struct tc_action_ops *ops,
|
|
|
|
struct netlink_ext_ack *extack)
|
2005-04-17 06:20:36 +08:00
|
|
|
{
|
2016-02-23 07:57:53 +08:00
|
|
|
struct tc_action_net *tn = net_generic(net, police_net_id);
|
2005-04-17 06:20:36 +08:00
|
|
|
|
2018-02-15 23:54:59 +08:00
|
|
|
return tcf_generic_walker(tn, skb, cb, type, ops, extack);
|
2005-04-17 06:20:36 +08:00
|
|
|
}
|
|
|
|
|
2008-01-24 12:36:30 +08:00
|
|
|
static const struct nla_policy police_policy[TCA_POLICE_MAX + 1] = {
|
|
|
|
[TCA_POLICE_RATE] = { .len = TC_RTAB_SIZE },
|
|
|
|
[TCA_POLICE_PEAKRATE] = { .len = TC_RTAB_SIZE },
|
|
|
|
[TCA_POLICE_AVRATE] = { .type = NLA_U32 },
|
|
|
|
[TCA_POLICE_RESULT] = { .type = NLA_U32 },
|
2019-09-04 23:03:43 +08:00
|
|
|
[TCA_POLICE_RATE64] = { .type = NLA_U64 },
|
|
|
|
[TCA_POLICE_PEAKRATE64] = { .type = NLA_U64 },
|
2021-03-12 22:08:31 +08:00
|
|
|
[TCA_POLICE_PKTRATE64] = { .type = NLA_U64, .min = 1 },
|
|
|
|
[TCA_POLICE_PKTBURST64] = { .type = NLA_U64, .min = 1 },
|
2008-01-24 12:36:30 +08:00
|
|
|
};
|
|
|
|
|
2018-08-12 21:34:56 +08:00
|
|
|
static int tcf_police_init(struct net *net, struct nlattr *nla,
|
2016-07-26 07:09:41 +08:00
|
|
|
struct nlattr *est, struct tc_action **a,
|
2019-10-30 22:09:05 +08:00
|
|
|
struct tcf_proto *tp, u32 flags,
|
2018-02-15 23:54:56 +08:00
|
|
|
struct netlink_ext_ack *extack)
|
2005-04-17 06:20:36 +08:00
|
|
|
{
|
2018-11-29 01:43:42 +08:00
|
|
|
int ret = 0, tcfp_result = TC_ACT_OK, err, size;
|
2021-07-30 07:12:14 +08:00
|
|
|
bool bind = flags & TCA_ACT_FLAGS_BIND;
|
2008-01-23 14:11:50 +08:00
|
|
|
struct nlattr *tb[TCA_POLICE_MAX + 1];
|
2019-03-20 22:00:08 +08:00
|
|
|
struct tcf_chain *goto_ch = NULL;
|
2005-04-17 06:20:36 +08:00
|
|
|
struct tc_police *parm;
|
2006-08-22 14:54:55 +08:00
|
|
|
struct tcf_police *police;
|
2005-04-17 06:20:36 +08:00
|
|
|
struct qdisc_rate_table *R_tab = NULL, *P_tab = NULL;
|
2016-02-23 07:57:53 +08:00
|
|
|
struct tc_action_net *tn = net_generic(net, police_net_id);
|
2018-09-14 01:29:13 +08:00
|
|
|
struct tcf_police_params *new;
|
2016-08-14 13:35:01 +08:00
|
|
|
bool exists = false;
|
2019-08-01 21:02:51 +08:00
|
|
|
u32 index;
|
2019-09-04 23:03:43 +08:00
|
|
|
u64 rate64, prate64;
|
2021-03-12 22:08:31 +08:00
|
|
|
u64 pps, ppsburst;
|
2005-04-17 06:20:36 +08:00
|
|
|
|
2008-01-24 12:33:32 +08:00
|
|
|
if (nla == NULL)
|
2005-04-17 06:20:36 +08:00
|
|
|
return -EINVAL;
|
|
|
|
|
netlink: make validation more configurable for future strictness
We currently have two levels of strict validation:
1) liberal (default)
- undefined (type >= max) & NLA_UNSPEC attributes accepted
- attribute length >= expected accepted
- garbage at end of message accepted
2) strict (opt-in)
- NLA_UNSPEC attributes accepted
- attribute length >= expected accepted
Split out parsing strictness into four different options:
* TRAILING - check that there's no trailing data after parsing
attributes (in message or nested)
* MAXTYPE - reject attrs > max known type
* UNSPEC - reject attributes with NLA_UNSPEC policy entries
* STRICT_ATTRS - strictly validate attribute size
The default for future things should be *everything*.
The current *_strict() is a combination of TRAILING and MAXTYPE,
and is renamed to _deprecated_strict().
The current regular parsing has none of this, and is renamed to
*_parse_deprecated().
Additionally it allows us to selectively set one of the new flags
even on old policies. Notably, the UNSPEC flag could be useful in
this case, since it can be arranged (by filling in the policy) to
not be an incompatible userspace ABI change, but would then going
forward prevent forgetting attribute entries. Similar can apply
to the POLICY flag.
We end up with the following renames:
* nla_parse -> nla_parse_deprecated
* nla_parse_strict -> nla_parse_deprecated_strict
* nlmsg_parse -> nlmsg_parse_deprecated
* nlmsg_parse_strict -> nlmsg_parse_deprecated_strict
* nla_parse_nested -> nla_parse_nested_deprecated
* nla_validate_nested -> nla_validate_nested_deprecated
Using spatch, of course:
@@
expression TB, MAX, HEAD, LEN, POL, EXT;
@@
-nla_parse(TB, MAX, HEAD, LEN, POL, EXT)
+nla_parse_deprecated(TB, MAX, HEAD, LEN, POL, EXT)
@@
expression NLH, HDRLEN, TB, MAX, POL, EXT;
@@
-nlmsg_parse(NLH, HDRLEN, TB, MAX, POL, EXT)
+nlmsg_parse_deprecated(NLH, HDRLEN, TB, MAX, POL, EXT)
@@
expression NLH, HDRLEN, TB, MAX, POL, EXT;
@@
-nlmsg_parse_strict(NLH, HDRLEN, TB, MAX, POL, EXT)
+nlmsg_parse_deprecated_strict(NLH, HDRLEN, TB, MAX, POL, EXT)
@@
expression TB, MAX, NLA, POL, EXT;
@@
-nla_parse_nested(TB, MAX, NLA, POL, EXT)
+nla_parse_nested_deprecated(TB, MAX, NLA, POL, EXT)
@@
expression START, MAX, POL, EXT;
@@
-nla_validate_nested(START, MAX, POL, EXT)
+nla_validate_nested_deprecated(START, MAX, POL, EXT)
@@
expression NLH, HDRLEN, MAX, POL, EXT;
@@
-nlmsg_validate(NLH, HDRLEN, MAX, POL, EXT)
+nlmsg_validate_deprecated(NLH, HDRLEN, MAX, POL, EXT)
For this patch, don't actually add the strict, non-renamed versions
yet so that it breaks compile if I get it wrong.
Also, while at it, make nla_validate and nla_parse go down to a
common __nla_validate_parse() function to avoid code duplication.
Ultimately, this allows us to have very strict validation for every
new caller of nla_parse()/nlmsg_parse() etc as re-introduced in the
next patch, while existing things will continue to work as is.
In effect then, this adds fully strict validation for any new command.
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2019-04-26 20:07:28 +08:00
|
|
|
err = nla_parse_nested_deprecated(tb, TCA_POLICE_MAX, nla,
|
|
|
|
police_policy, NULL);
|
2008-01-24 12:33:32 +08:00
|
|
|
if (err < 0)
|
|
|
|
return err;
|
|
|
|
|
2008-01-23 14:11:50 +08:00
|
|
|
if (tb[TCA_POLICE_TBF] == NULL)
|
2006-12-01 11:54:05 +08:00
|
|
|
return -EINVAL;
|
2008-01-23 14:11:50 +08:00
|
|
|
size = nla_len(tb[TCA_POLICE_TBF]);
|
2006-12-01 11:54:05 +08:00
|
|
|
if (size != sizeof(*parm) && size != sizeof(struct tc_police_compat))
|
2005-04-17 06:20:36 +08:00
|
|
|
return -EINVAL;
|
2016-08-14 13:35:01 +08:00
|
|
|
|
2008-01-23 14:11:50 +08:00
|
|
|
parm = nla_data(tb[TCA_POLICE_TBF]);
|
2019-08-01 21:02:51 +08:00
|
|
|
index = parm->index;
|
|
|
|
err = tcf_idr_check_alloc(tn, &index, a, bind);
|
2018-07-05 22:24:32 +08:00
|
|
|
if (err < 0)
|
|
|
|
return err;
|
|
|
|
exists = err;
|
2016-08-14 13:35:01 +08:00
|
|
|
if (exists && bind)
|
|
|
|
return 0;
|
2005-04-17 06:20:36 +08:00
|
|
|
|
2016-08-14 13:35:01 +08:00
|
|
|
if (!exists) {
|
2019-08-01 21:02:51 +08:00
|
|
|
ret = tcf_idr_create(tn, index, NULL, a,
|
2019-10-30 22:09:06 +08:00
|
|
|
&act_police_ops, bind, true, 0);
|
2018-07-05 22:24:32 +08:00
|
|
|
if (ret) {
|
2019-08-01 21:02:51 +08:00
|
|
|
tcf_idr_cleanup(tn, index);
|
2016-06-07 00:54:30 +08:00
|
|
|
return ret;
|
2018-07-05 22:24:32 +08:00
|
|
|
}
|
2016-06-07 00:54:30 +08:00
|
|
|
ret = ACT_P_CREATED;
|
2018-11-22 01:23:53 +08:00
|
|
|
spin_lock_init(&(to_police(*a)->tcfp_lock));
|
2021-07-30 07:12:14 +08:00
|
|
|
} else if (!(flags & TCA_ACT_FLAGS_REPLACE)) {
|
2017-08-30 14:31:59 +08:00
|
|
|
tcf_idr_release(*a, bind);
|
2018-07-05 22:24:30 +08:00
|
|
|
return -EEXIST;
|
2005-04-17 06:20:36 +08:00
|
|
|
}
|
2019-03-20 22:00:08 +08:00
|
|
|
err = tcf_action_check_ctrlact(parm->action, tp, &goto_ch, extack);
|
|
|
|
if (err < 0)
|
|
|
|
goto release_idr;
|
2005-04-17 06:20:36 +08:00
|
|
|
|
2016-07-26 07:09:41 +08:00
|
|
|
police = to_police(*a);
|
2005-04-17 06:20:36 +08:00
|
|
|
if (parm->rate.rate) {
|
|
|
|
err = -ENOMEM;
|
2017-12-21 01:35:18 +08:00
|
|
|
R_tab = qdisc_get_rtab(&parm->rate, tb[TCA_POLICE_RATE], NULL);
|
2005-04-17 06:20:36 +08:00
|
|
|
if (R_tab == NULL)
|
|
|
|
goto failure;
|
2008-11-26 13:14:06 +08:00
|
|
|
|
2005-04-17 06:20:36 +08:00
|
|
|
if (parm->peakrate.rate) {
|
|
|
|
P_tab = qdisc_get_rtab(&parm->peakrate,
|
2017-12-21 01:35:18 +08:00
|
|
|
tb[TCA_POLICE_PEAKRATE], NULL);
|
2008-11-26 13:13:31 +08:00
|
|
|
if (P_tab == NULL)
|
2005-04-17 06:20:36 +08:00
|
|
|
goto failure;
|
|
|
|
}
|
|
|
|
}
|
2008-11-26 13:13:31 +08:00
|
|
|
|
|
|
|
if (est) {
|
2018-09-14 01:29:12 +08:00
|
|
|
err = gen_replace_estimator(&police->tcf_bstats,
|
|
|
|
police->common.cpu_bstats,
|
2008-11-26 13:13:31 +08:00
|
|
|
&police->tcf_rate_est,
|
2016-06-07 00:37:16 +08:00
|
|
|
&police->tcf_lock,
|
net: sched: Remove Qdisc::running sequence counter
The Qdisc::running sequence counter has two uses:
1. Reliably reading qdisc's tc statistics while the qdisc is running
(a seqcount read/retry loop at gnet_stats_add_basic()).
2. As a flag, indicating whether the qdisc in question is running
(without any retry loops).
For the first usage, the Qdisc::running sequence counter write section,
qdisc_run_begin() => qdisc_run_end(), covers a much wider area than what
is actually needed: the raw qdisc's bstats update. A u64_stats sync
point was thus introduced (in previous commits) inside the bstats
structure itself. A local u64_stats write section is then started and
stopped for the bstats updates.
Use that u64_stats sync point mechanism for the bstats read/retry loop
at gnet_stats_add_basic().
For the second qdisc->running usage, a __QDISC_STATE_RUNNING bit flag,
accessed with atomic bitops, is sufficient. Using a bit flag instead of
a sequence counter at qdisc_run_begin/end() and qdisc_is_running() leads
to the SMP barriers implicitly added through raw_read_seqcount() and
write_seqcount_begin/end() getting removed. All call sites have been
surveyed though, and no required ordering was identified.
Now that the qdisc->running sequence counter is no longer used, remove
it.
Note, using u64_stats implies no sequence counter protection for 64-bit
architectures. This can lead to the qdisc tc statistics "packets" vs.
"bytes" values getting out of sync on rare occasions. The individual
values will still be valid.
Signed-off-by: Ahmed S. Darwish <a.darwish@linutronix.de>
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
2021-10-16 16:49:10 +08:00
|
|
|
false, est);
|
2008-11-26 13:13:31 +08:00
|
|
|
if (err)
|
2017-06-14 04:36:24 +08:00
|
|
|
goto failure;
|
2009-03-05 09:38:10 +08:00
|
|
|
} else if (tb[TCA_POLICE_AVRATE] &&
|
|
|
|
(ret == ACT_P_CREATED ||
|
2016-12-05 01:48:16 +08:00
|
|
|
!gen_estimator_active(&police->tcf_rate_est))) {
|
2009-03-05 09:38:10 +08:00
|
|
|
err = -EINVAL;
|
2017-06-14 04:36:24 +08:00
|
|
|
goto failure;
|
2008-11-26 13:13:31 +08:00
|
|
|
}
|
|
|
|
|
2018-11-29 01:43:42 +08:00
|
|
|
if (tb[TCA_POLICE_RESULT]) {
|
|
|
|
tcfp_result = nla_get_u32(tb[TCA_POLICE_RESULT]);
|
|
|
|
if (TC_ACT_EXT_CMP(tcfp_result, TC_ACT_GOTO_CHAIN)) {
|
|
|
|
NL_SET_ERR_MSG(extack,
|
|
|
|
"goto chain not allowed on fallback");
|
|
|
|
err = -EINVAL;
|
|
|
|
goto failure;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2021-03-12 22:08:31 +08:00
|
|
|
if ((tb[TCA_POLICE_PKTRATE64] && !tb[TCA_POLICE_PKTBURST64]) ||
|
|
|
|
(!tb[TCA_POLICE_PKTRATE64] && tb[TCA_POLICE_PKTBURST64])) {
|
|
|
|
NL_SET_ERR_MSG(extack,
|
|
|
|
"Both or neither packet-per-second burst and rate must be provided");
|
|
|
|
err = -EINVAL;
|
|
|
|
goto failure;
|
|
|
|
}
|
|
|
|
|
|
|
|
if (tb[TCA_POLICE_PKTRATE64] && R_tab) {
|
|
|
|
NL_SET_ERR_MSG(extack,
|
|
|
|
"packet-per-second and byte-per-second rate limits not allowed in same action");
|
|
|
|
err = -EINVAL;
|
|
|
|
goto failure;
|
|
|
|
}
|
|
|
|
|
2018-09-14 01:29:13 +08:00
|
|
|
new = kzalloc(sizeof(*new), GFP_KERNEL);
|
|
|
|
if (unlikely(!new)) {
|
|
|
|
err = -ENOMEM;
|
|
|
|
goto failure;
|
|
|
|
}
|
|
|
|
|
2008-11-26 13:13:31 +08:00
|
|
|
/* No failure allowed after this point */
|
2018-11-29 01:43:42 +08:00
|
|
|
new->tcfp_result = tcfp_result;
|
2018-09-14 01:29:13 +08:00
|
|
|
new->tcfp_mtu = parm->mtu;
|
|
|
|
if (!new->tcfp_mtu) {
|
|
|
|
new->tcfp_mtu = ~0;
|
2013-02-12 08:12:07 +08:00
|
|
|
if (R_tab)
|
2018-09-14 01:29:13 +08:00
|
|
|
new->tcfp_mtu = 255 << R_tab->rate.cell_log;
|
2013-02-12 08:12:07 +08:00
|
|
|
}
|
|
|
|
if (R_tab) {
|
2018-09-14 01:29:13 +08:00
|
|
|
new->rate_present = true;
|
2019-09-04 23:03:43 +08:00
|
|
|
rate64 = tb[TCA_POLICE_RATE64] ?
|
|
|
|
nla_get_u64(tb[TCA_POLICE_RATE64]) : 0;
|
|
|
|
psched_ratecfg_precompute(&new->rate, &R_tab->rate, rate64);
|
2013-02-12 08:12:07 +08:00
|
|
|
qdisc_put_rtab(R_tab);
|
|
|
|
} else {
|
2018-09-14 01:29:13 +08:00
|
|
|
new->rate_present = false;
|
2005-04-17 06:20:36 +08:00
|
|
|
}
|
2013-02-12 08:12:07 +08:00
|
|
|
if (P_tab) {
|
2018-09-14 01:29:13 +08:00
|
|
|
new->peak_present = true;
|
2019-09-04 23:03:43 +08:00
|
|
|
prate64 = tb[TCA_POLICE_PEAKRATE64] ?
|
|
|
|
nla_get_u64(tb[TCA_POLICE_PEAKRATE64]) : 0;
|
|
|
|
psched_ratecfg_precompute(&new->peak, &P_tab->rate, prate64);
|
2013-02-12 08:12:07 +08:00
|
|
|
qdisc_put_rtab(P_tab);
|
|
|
|
} else {
|
2018-09-14 01:29:13 +08:00
|
|
|
new->peak_present = false;
|
2005-04-17 06:20:36 +08:00
|
|
|
}
|
|
|
|
|
2018-09-14 01:29:13 +08:00
|
|
|
new->tcfp_burst = PSCHED_TICKS2NS(parm->burst);
|
2018-11-21 05:18:44 +08:00
|
|
|
if (new->peak_present)
|
2018-09-14 01:29:13 +08:00
|
|
|
new->tcfp_mtu_ptoks = (s64)psched_l2t_ns(&new->peak,
|
|
|
|
new->tcfp_mtu);
|
2005-04-17 06:20:36 +08:00
|
|
|
|
2008-01-23 14:11:50 +08:00
|
|
|
if (tb[TCA_POLICE_AVRATE])
|
2018-09-14 01:29:13 +08:00
|
|
|
new->tcfp_ewma_rate = nla_get_u32(tb[TCA_POLICE_AVRATE]);
|
2005-04-17 06:20:36 +08:00
|
|
|
|
2021-03-12 22:08:31 +08:00
|
|
|
if (tb[TCA_POLICE_PKTRATE64]) {
|
|
|
|
pps = nla_get_u64(tb[TCA_POLICE_PKTRATE64]);
|
|
|
|
ppsburst = nla_get_u64(tb[TCA_POLICE_PKTBURST64]);
|
|
|
|
new->pps_present = true;
|
|
|
|
new->tcfp_pkt_burst = PSCHED_TICKS2NS(ppsburst);
|
|
|
|
psched_ppscfg_precompute(&new->ppsrate, pps);
|
|
|
|
}
|
|
|
|
|
2018-09-14 01:29:13 +08:00
|
|
|
spin_lock_bh(&police->tcf_lock);
|
2018-11-21 05:18:44 +08:00
|
|
|
spin_lock_bh(&police->tcfp_lock);
|
|
|
|
police->tcfp_t_c = ktime_get_ns();
|
|
|
|
police->tcfp_toks = new->tcfp_burst;
|
|
|
|
if (new->peak_present)
|
|
|
|
police->tcfp_ptoks = new->tcfp_mtu_ptoks;
|
|
|
|
spin_unlock_bh(&police->tcfp_lock);
|
2019-03-20 22:00:08 +08:00
|
|
|
goto_ch = tcf_action_set_ctrlact(*a, parm->action, goto_ch);
|
2019-09-24 07:09:18 +08:00
|
|
|
new = rcu_replace_pointer(police->params,
|
|
|
|
new,
|
|
|
|
lockdep_is_held(&police->tcf_lock));
|
2006-08-22 14:54:55 +08:00
|
|
|
spin_unlock_bh(&police->tcf_lock);
|
2005-04-17 06:20:36 +08:00
|
|
|
|
2019-03-20 22:00:08 +08:00
|
|
|
if (goto_ch)
|
|
|
|
tcf_chain_put_by_act(goto_ch);
|
2018-09-14 01:29:13 +08:00
|
|
|
if (new)
|
|
|
|
kfree_rcu(new, rcu);
|
2005-04-17 06:20:36 +08:00
|
|
|
|
|
|
|
return ret;
|
|
|
|
|
|
|
|
failure:
|
2013-12-17 15:29:16 +08:00
|
|
|
qdisc_put_rtab(P_tab);
|
|
|
|
qdisc_put_rtab(R_tab);
|
2019-03-20 22:00:08 +08:00
|
|
|
if (goto_ch)
|
|
|
|
tcf_chain_put_by_act(goto_ch);
|
|
|
|
release_idr:
|
2018-07-05 22:24:30 +08:00
|
|
|
tcf_idr_release(*a, bind);
|
2005-04-17 06:20:36 +08:00
|
|
|
return err;
|
|
|
|
}
|
|
|
|
|
2018-08-12 21:34:56 +08:00
|
|
|
static int tcf_police_act(struct sk_buff *skb, const struct tc_action *a,
|
2007-02-09 22:25:16 +08:00
|
|
|
struct tcf_result *res)
|
2005-04-17 06:20:36 +08:00
|
|
|
{
|
2016-07-26 07:09:41 +08:00
|
|
|
struct tcf_police *police = to_police(a);
|
2021-03-12 22:08:31 +08:00
|
|
|
s64 now, toks, ppstoks = 0, ptoks = 0;
|
2018-09-14 01:29:13 +08:00
|
|
|
struct tcf_police_params *p;
|
2018-09-14 01:29:12 +08:00
|
|
|
int ret;
|
2005-04-17 06:20:36 +08:00
|
|
|
|
2016-05-24 09:07:20 +08:00
|
|
|
tcf_lastuse_update(&police->tcf_tm);
|
2021-10-16 16:49:09 +08:00
|
|
|
bstats_update(this_cpu_ptr(police->common.cpu_bstats), skb);
|
2005-04-17 06:20:36 +08:00
|
|
|
|
2018-09-14 01:29:13 +08:00
|
|
|
ret = READ_ONCE(police->tcf_action);
|
|
|
|
p = rcu_dereference_bh(police->params);
|
|
|
|
|
|
|
|
if (p->tcfp_ewma_rate) {
|
2016-12-05 01:48:16 +08:00
|
|
|
struct gnet_stats_rate_est64 sample;
|
|
|
|
|
|
|
|
if (!gen_estimator_read(&police->tcf_rate_est, &sample) ||
|
2018-09-14 01:29:13 +08:00
|
|
|
sample.bps >= p->tcfp_ewma_rate)
|
2018-09-14 01:29:12 +08:00
|
|
|
goto inc_overlimits;
|
2005-04-17 06:20:36 +08:00
|
|
|
}
|
|
|
|
|
2018-09-14 01:29:13 +08:00
|
|
|
if (qdisc_pkt_len(skb) <= p->tcfp_mtu) {
|
2021-03-12 22:08:31 +08:00
|
|
|
if (!p->rate_present && !p->pps_present) {
|
2018-09-14 01:29:13 +08:00
|
|
|
ret = p->tcfp_result;
|
|
|
|
goto end;
|
2005-04-17 06:20:36 +08:00
|
|
|
}
|
|
|
|
|
2014-08-23 09:32:09 +08:00
|
|
|
now = ktime_get_ns();
|
2018-11-21 05:18:44 +08:00
|
|
|
spin_lock_bh(&police->tcfp_lock);
|
|
|
|
toks = min_t(s64, now - police->tcfp_t_c, p->tcfp_burst);
|
2018-09-14 01:29:13 +08:00
|
|
|
if (p->peak_present) {
|
2018-11-21 05:18:44 +08:00
|
|
|
ptoks = toks + police->tcfp_ptoks;
|
2018-09-14 01:29:13 +08:00
|
|
|
if (ptoks > p->tcfp_mtu_ptoks)
|
|
|
|
ptoks = p->tcfp_mtu_ptoks;
|
|
|
|
ptoks -= (s64)psched_l2t_ns(&p->peak,
|
|
|
|
qdisc_pkt_len(skb));
|
2005-04-17 06:20:36 +08:00
|
|
|
}
|
2021-03-12 22:08:31 +08:00
|
|
|
if (p->rate_present) {
|
|
|
|
toks += police->tcfp_toks;
|
|
|
|
if (toks > p->tcfp_burst)
|
|
|
|
toks = p->tcfp_burst;
|
|
|
|
toks -= (s64)psched_l2t_ns(&p->rate, qdisc_pkt_len(skb));
|
|
|
|
} else if (p->pps_present) {
|
|
|
|
ppstoks = min_t(s64, now - police->tcfp_t_c, p->tcfp_pkt_burst);
|
|
|
|
ppstoks += police->tcfp_pkttoks;
|
|
|
|
if (ppstoks > p->tcfp_pkt_burst)
|
|
|
|
ppstoks = p->tcfp_pkt_burst;
|
|
|
|
ppstoks -= (s64)psched_pkt2t_ns(&p->ppsrate, 1);
|
|
|
|
}
|
|
|
|
if ((toks | ptoks | ppstoks) >= 0) {
|
2018-11-21 05:18:44 +08:00
|
|
|
police->tcfp_t_c = now;
|
|
|
|
police->tcfp_toks = toks;
|
|
|
|
police->tcfp_ptoks = ptoks;
|
2021-03-12 22:08:31 +08:00
|
|
|
police->tcfp_pkttoks = ppstoks;
|
2018-11-21 05:18:44 +08:00
|
|
|
spin_unlock_bh(&police->tcfp_lock);
|
2018-09-14 01:29:13 +08:00
|
|
|
ret = p->tcfp_result;
|
2018-09-14 01:29:12 +08:00
|
|
|
goto inc_drops;
|
2005-04-17 06:20:36 +08:00
|
|
|
}
|
2018-11-21 05:18:44 +08:00
|
|
|
spin_unlock_bh(&police->tcfp_lock);
|
2005-04-17 06:20:36 +08:00
|
|
|
}
|
2018-09-14 01:29:12 +08:00
|
|
|
|
|
|
|
inc_overlimits:
|
|
|
|
qstats_overlimit_inc(this_cpu_ptr(police->common.cpu_qstats));
|
|
|
|
inc_drops:
|
|
|
|
if (ret == TC_ACT_SHOT)
|
|
|
|
qstats_drop_inc(this_cpu_ptr(police->common.cpu_qstats));
|
2018-09-14 01:29:13 +08:00
|
|
|
end:
|
2018-09-14 01:29:12 +08:00
|
|
|
return ret;
|
2005-04-17 06:20:36 +08:00
|
|
|
}
|
|
|
|
|
2018-09-14 01:29:13 +08:00
|
|
|
static void tcf_police_cleanup(struct tc_action *a)
|
|
|
|
{
|
|
|
|
struct tcf_police *police = to_police(a);
|
|
|
|
struct tcf_police_params *p;
|
|
|
|
|
|
|
|
p = rcu_dereference_protected(police->params, 1);
|
|
|
|
if (p)
|
|
|
|
kfree_rcu(p, rcu);
|
|
|
|
}
|
|
|
|
|
2019-05-04 19:46:24 +08:00
|
|
|
static void tcf_police_stats_update(struct tc_action *a,
|
2020-06-19 14:01:07 +08:00
|
|
|
u64 bytes, u64 packets, u64 drops,
|
2019-05-04 19:46:24 +08:00
|
|
|
u64 lastuse, bool hw)
|
|
|
|
{
|
|
|
|
struct tcf_police *police = to_police(a);
|
|
|
|
struct tcf_t *tm = &police->tcf_tm;
|
|
|
|
|
2020-06-19 14:01:07 +08:00
|
|
|
tcf_action_update_stats(a, bytes, packets, drops, hw);
|
2019-05-04 19:46:24 +08:00
|
|
|
tm->lastuse = max_t(u64, tm->lastuse, lastuse);
|
|
|
|
}
|
|
|
|
|
2018-08-12 21:34:56 +08:00
|
|
|
static int tcf_police_dump(struct sk_buff *skb, struct tc_action *a,
|
2016-09-18 20:45:33 +08:00
|
|
|
int bind, int ref)
|
2005-04-17 06:20:36 +08:00
|
|
|
{
|
2007-04-20 11:29:13 +08:00
|
|
|
unsigned char *b = skb_tail_pointer(skb);
|
2016-07-26 07:09:41 +08:00
|
|
|
struct tcf_police *police = to_police(a);
|
2018-09-14 01:29:13 +08:00
|
|
|
struct tcf_police_params *p;
|
2010-08-31 21:21:42 +08:00
|
|
|
struct tc_police opt = {
|
|
|
|
.index = police->tcf_index,
|
2018-07-05 22:24:24 +08:00
|
|
|
.refcnt = refcount_read(&police->tcf_refcnt) - ref,
|
|
|
|
.bindcnt = atomic_read(&police->tcf_bindcnt) - bind,
|
2010-08-31 21:21:42 +08:00
|
|
|
};
|
2016-05-24 09:07:20 +08:00
|
|
|
struct tcf_t t;
|
2010-08-31 21:21:42 +08:00
|
|
|
|
2018-08-11 01:51:55 +08:00
|
|
|
spin_lock_bh(&police->tcf_lock);
|
|
|
|
opt.action = police->tcf_action;
|
2018-09-14 01:29:13 +08:00
|
|
|
p = rcu_dereference_protected(police->params,
|
|
|
|
lockdep_is_held(&police->tcf_lock));
|
|
|
|
opt.mtu = p->tcfp_mtu;
|
|
|
|
opt.burst = PSCHED_NS2TICKS(p->tcfp_burst);
|
2019-09-04 23:03:43 +08:00
|
|
|
if (p->rate_present) {
|
2018-09-14 01:29:13 +08:00
|
|
|
psched_ratecfg_getrate(&opt.rate, &p->rate);
|
2019-09-04 23:03:43 +08:00
|
|
|
if ((police->params->rate.rate_bytes_ps >= (1ULL << 32)) &&
|
|
|
|
nla_put_u64_64bit(skb, TCA_POLICE_RATE64,
|
|
|
|
police->params->rate.rate_bytes_ps,
|
|
|
|
TCA_POLICE_PAD))
|
|
|
|
goto nla_put_failure;
|
|
|
|
}
|
|
|
|
if (p->peak_present) {
|
2018-09-14 01:29:13 +08:00
|
|
|
psched_ratecfg_getrate(&opt.peakrate, &p->peak);
|
2019-09-04 23:03:43 +08:00
|
|
|
if ((police->params->peak.rate_bytes_ps >= (1ULL << 32)) &&
|
|
|
|
nla_put_u64_64bit(skb, TCA_POLICE_PEAKRATE64,
|
|
|
|
police->params->peak.rate_bytes_ps,
|
|
|
|
TCA_POLICE_PAD))
|
|
|
|
goto nla_put_failure;
|
|
|
|
}
|
2021-03-12 22:08:31 +08:00
|
|
|
if (p->pps_present) {
|
|
|
|
if (nla_put_u64_64bit(skb, TCA_POLICE_PKTRATE64,
|
|
|
|
police->params->ppsrate.rate_pkts_ps,
|
|
|
|
TCA_POLICE_PAD))
|
|
|
|
goto nla_put_failure;
|
|
|
|
if (nla_put_u64_64bit(skb, TCA_POLICE_PKTBURST64,
|
|
|
|
PSCHED_NS2TICKS(p->tcfp_pkt_burst),
|
|
|
|
TCA_POLICE_PAD))
|
|
|
|
goto nla_put_failure;
|
|
|
|
}
|
2012-03-29 17:11:39 +08:00
|
|
|
if (nla_put(skb, TCA_POLICE_TBF, sizeof(opt), &opt))
|
|
|
|
goto nla_put_failure;
|
2018-09-14 01:29:13 +08:00
|
|
|
if (p->tcfp_result &&
|
|
|
|
nla_put_u32(skb, TCA_POLICE_RESULT, p->tcfp_result))
|
2012-03-29 17:11:39 +08:00
|
|
|
goto nla_put_failure;
|
2018-09-14 01:29:13 +08:00
|
|
|
if (p->tcfp_ewma_rate &&
|
|
|
|
nla_put_u32(skb, TCA_POLICE_AVRATE, p->tcfp_ewma_rate))
|
2012-03-29 17:11:39 +08:00
|
|
|
goto nla_put_failure;
|
2016-05-24 09:07:20 +08:00
|
|
|
|
2019-10-20 00:49:32 +08:00
|
|
|
tcf_tm_dump(&t, &police->tcf_tm);
|
2016-05-24 09:07:20 +08:00
|
|
|
if (nla_put_64bit(skb, TCA_POLICE_TM, sizeof(t), &t, TCA_POLICE_PAD))
|
|
|
|
goto nla_put_failure;
|
2018-08-11 01:51:55 +08:00
|
|
|
spin_unlock_bh(&police->tcf_lock);
|
2016-05-24 09:07:20 +08:00
|
|
|
|
2005-04-17 06:20:36 +08:00
|
|
|
return skb->len;
|
|
|
|
|
2008-01-23 14:11:50 +08:00
|
|
|
nla_put_failure:
|
2018-08-11 01:51:55 +08:00
|
|
|
spin_unlock_bh(&police->tcf_lock);
|
2007-03-26 14:06:12 +08:00
|
|
|
nlmsg_trim(skb, b);
|
2005-04-17 06:20:36 +08:00
|
|
|
return -1;
|
|
|
|
}
|
|
|
|
|
2018-08-30 01:15:35 +08:00
|
|
|
static int tcf_police_search(struct net *net, struct tc_action **a, u32 index)
|
2016-02-23 07:57:53 +08:00
|
|
|
{
|
|
|
|
struct tc_action_net *tn = net_generic(net, police_net_id);
|
|
|
|
|
2017-08-30 14:31:59 +08:00
|
|
|
return tcf_idr_search(tn, a, index);
|
2016-02-23 07:57:53 +08:00
|
|
|
}
|
|
|
|
|
2005-04-17 06:20:36 +08:00
|
|
|
MODULE_AUTHOR("Alexey Kuznetsov");
|
|
|
|
MODULE_DESCRIPTION("Policing actions");
|
|
|
|
MODULE_LICENSE("GPL");
|
|
|
|
|
|
|
|
static struct tc_action_ops act_police_ops = {
|
|
|
|
.kind = "police",
|
2019-02-10 20:25:00 +08:00
|
|
|
.id = TCA_ID_POLICE,
|
2005-04-17 06:20:36 +08:00
|
|
|
.owner = THIS_MODULE,
|
2019-05-04 19:46:24 +08:00
|
|
|
.stats_update = tcf_police_stats_update,
|
2018-08-12 21:34:56 +08:00
|
|
|
.act = tcf_police_act,
|
|
|
|
.dump = tcf_police_dump,
|
|
|
|
.init = tcf_police_init,
|
|
|
|
.walk = tcf_police_walker,
|
2016-02-23 07:57:53 +08:00
|
|
|
.lookup = tcf_police_search,
|
2018-09-14 01:29:13 +08:00
|
|
|
.cleanup = tcf_police_cleanup,
|
2016-07-26 07:09:41 +08:00
|
|
|
.size = sizeof(struct tcf_police),
|
2016-02-23 07:57:53 +08:00
|
|
|
};
|
|
|
|
|
|
|
|
static __net_init int police_init_net(struct net *net)
|
|
|
|
{
|
|
|
|
struct tc_action_net *tn = net_generic(net, police_net_id);
|
|
|
|
|
2019-08-26 01:01:32 +08:00
|
|
|
return tc_action_net_init(net, tn, &act_police_ops);
|
2016-02-23 07:57:53 +08:00
|
|
|
}
|
|
|
|
|
2017-12-12 07:35:03 +08:00
|
|
|
static void __net_exit police_exit_net(struct list_head *net_list)
|
2016-02-23 07:57:53 +08:00
|
|
|
{
|
2017-12-12 07:35:03 +08:00
|
|
|
tc_action_net_exit(net_list, police_net_id);
|
2016-02-23 07:57:53 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
static struct pernet_operations police_net_ops = {
|
|
|
|
.init = police_init_net,
|
2017-12-12 07:35:03 +08:00
|
|
|
.exit_batch = police_exit_net,
|
2016-02-23 07:57:53 +08:00
|
|
|
.id = &police_net_id,
|
|
|
|
.size = sizeof(struct tc_action_net),
|
2005-04-17 06:20:36 +08:00
|
|
|
};
|
|
|
|
|
2016-09-18 20:45:33 +08:00
|
|
|
static int __init police_init_module(void)
|
2005-04-17 06:20:36 +08:00
|
|
|
{
|
2016-02-23 07:57:53 +08:00
|
|
|
return tcf_register_action(&act_police_ops, &police_net_ops);
|
2005-04-17 06:20:36 +08:00
|
|
|
}
|
|
|
|
|
2016-09-18 20:45:33 +08:00
|
|
|
static void __exit police_cleanup_module(void)
|
2005-04-17 06:20:36 +08:00
|
|
|
{
|
2016-02-23 07:57:53 +08:00
|
|
|
tcf_unregister_action(&act_police_ops, &police_net_ops);
|
2005-04-17 06:20:36 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
module_init(police_init_module);
|
|
|
|
module_exit(police_cleanup_module);
|