2019-05-19 20:08:20 +08:00
|
|
|
// SPDX-License-Identifier: GPL-2.0-only
|
2005-04-17 06:20:36 +08:00
|
|
|
/* net/sched/sch_dsmark.c - Differentiated Services field marker */
|
|
|
|
|
|
|
|
|
|
/* Written 1998-2000 by Werner Almesberger, EPFL ICA */
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
#include <linux/module.h>
|
|
|
|
|
#include <linux/init.h>
|
include cleanup: Update gfp.h and slab.h includes to prepare for breaking implicit slab.h inclusion from percpu.h
percpu.h is included by sched.h and module.h and thus ends up being
included when building most .c files. percpu.h includes slab.h which
in turn includes gfp.h making everything defined by the two files
universally available and complicating inclusion dependencies.
percpu.h -> slab.h dependency is about to be removed. Prepare for
this change by updating users of gfp and slab facilities include those
headers directly instead of assuming availability. As this conversion
needs to touch large number of source files, the following script is
used as the basis of conversion.
http://userweb.kernel.org/~tj/misc/slabh-sweep.py
The script does the followings.
* Scan files for gfp and slab usages and update includes such that
only the necessary includes are there. ie. if only gfp is used,
gfp.h, if slab is used, slab.h.
* When the script inserts a new include, it looks at the include
blocks and try to put the new include such that its order conforms
to its surrounding. It's put in the include block which contains
core kernel includes, in the same order that the rest are ordered -
alphabetical, Christmas tree, rev-Xmas-tree or at the end if there
doesn't seem to be any matching order.
* If the script can't find a place to put a new include (mostly
because the file doesn't have fitting include block), it prints out
an error message indicating which .h file needs to be added to the
file.
The conversion was done in the following steps.
1. The initial automatic conversion of all .c files updated slightly
over 4000 files, deleting around 700 includes and adding ~480 gfp.h
and ~3000 slab.h inclusions. The script emitted errors for ~400
files.
2. Each error was manually checked. Some didn't need the inclusion,
some needed manual addition while adding it to implementation .h or
embedding .c file was more appropriate for others. This step added
inclusions to around 150 files.
3. The script was run again and the output was compared to the edits
from #2 to make sure no file was left behind.
4. Several build tests were done and a couple of problems were fixed.
e.g. lib/decompress_*.c used malloc/free() wrappers around slab
APIs requiring slab.h to be added manually.
5. The script was run on all .h files but without automatically
editing them as sprinkling gfp.h and slab.h inclusions around .h
files could easily lead to inclusion dependency hell. Most gfp.h
inclusion directives were ignored as stuff from gfp.h was usually
wildly available and often used in preprocessor macros. Each
slab.h inclusion directive was examined and added manually as
necessary.
6. percpu.h was updated not to include slab.h.
7. Build test were done on the following configurations and failures
were fixed. CONFIG_GCOV_KERNEL was turned off for all tests (as my
distributed build env didn't work with gcov compiles) and a few
more options had to be turned off depending on archs to make things
build (like ipr on powerpc/64 which failed due to missing writeq).
* x86 and x86_64 UP and SMP allmodconfig and a custom test config.
* powerpc and powerpc64 SMP allmodconfig
* sparc and sparc64 SMP allmodconfig
* ia64 SMP allmodconfig
* s390 SMP allmodconfig
* alpha SMP allmodconfig
* um on x86_64 SMP allmodconfig
8. percpu.h modifications were reverted so that it could be applied as
a separate patch and serve as bisection point.
Given the fact that I had only a couple of failures from tests on step
6, I'm fairly confident about the coverage of this conversion patch.
If there is a breakage, it's likely to be something in one of the arch
headers which should be easily discoverable easily on most builds of
the specific arch.
Signed-off-by: Tejun Heo <tj@kernel.org>
Guess-its-ok-by: Christoph Lameter <cl@linux-foundation.org>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
2010-03-24 16:04:11 +08:00
|
|
|
#include <linux/slab.h>
|
2005-04-17 06:20:36 +08:00
|
|
|
#include <linux/types.h>
|
|
|
|
|
#include <linux/string.h>
|
|
|
|
|
#include <linux/errno.h>
|
|
|
|
|
#include <linux/skbuff.h>
|
|
|
|
|
#include <linux/rtnetlink.h>
|
2008-01-21 18:21:45 +08:00
|
|
|
#include <linux/bitops.h>
|
2005-04-17 06:20:36 +08:00
|
|
|
#include <net/pkt_sched.h>
|
2017-02-09 21:38:56 +08:00
|
|
|
#include <net/pkt_cls.h>
|
2005-04-17 06:20:36 +08:00
|
|
|
#include <net/dsfield.h>
|
|
|
|
|
#include <net/inet_ecn.h>
|
|
|
|
|
#include <asm/byteorder.h>
|
|
|
|
|
|
|
|
|
|
/*
|
|
|
|
|
* classid class marking
|
|
|
|
|
* ------- ----- -------
|
|
|
|
|
* n/a 0 n/a
|
|
|
|
|
* x:0 1 use entry [0]
|
|
|
|
|
* ... ... ...
|
|
|
|
|
* x:y y>0 y+1 use entry [y]
|
|
|
|
|
* ... ... ...
|
|
|
|
|
* x:indices-1 indices use entry [indices-1]
|
|
|
|
|
* ... ... ...
|
|
|
|
|
* x:y y+1 use entry [y & (indices-1)]
|
|
|
|
|
* ... ... ...
|
|
|
|
|
* 0xffff 0x10000 use entry [indices-1]
|
|
|
|
|
*/
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
#define NO_DEFAULT_INDEX (1 << 16)
|
|
|
|
|
|
2015-09-18 07:37:13 +08:00
|
|
|
struct mask_value {
|
|
|
|
|
u8 mask;
|
|
|
|
|
u8 value;
|
|
|
|
|
};
|
|
|
|
|
|
2005-04-17 06:20:36 +08:00
|
|
|
struct dsmark_qdisc_data {
|
|
|
|
|
struct Qdisc *q;
|
2014-09-13 11:05:27 +08:00
|
|
|
struct tcf_proto __rcu *filter_list;
|
2017-05-17 17:07:55 +08:00
|
|
|
struct tcf_block *block;
|
2015-09-18 07:37:13 +08:00
|
|
|
struct mask_value *mv;
|
2005-06-19 13:53:29 +08:00
|
|
|
u16 indices;
|
2015-09-18 07:37:13 +08:00
|
|
|
u8 set_tc_index;
|
2005-06-19 13:53:29 +08:00
|
|
|
u32 default_index; /* index range is 0...0xffff */
|
2015-09-18 07:37:13 +08:00
|
|
|
#define DSMARK_EMBEDDED_SZ 16
|
|
|
|
|
struct mask_value embedded[DSMARK_EMBEDDED_SZ];
|
2005-04-17 06:20:36 +08:00
|
|
|
};
|
|
|
|
|
|
2005-06-19 13:52:54 +08:00
|
|
|
static inline int dsmark_valid_index(struct dsmark_qdisc_data *p, u16 index)
|
|
|
|
|
{
|
2013-12-10 20:55:29 +08:00
|
|
|
return index <= p->indices && index > 0;
|
2005-06-19 13:52:54 +08:00
|
|
|
}
|
2005-04-17 06:20:36 +08:00
|
|
|
|
|
|
|
|
/* ------------------------- Class/flow operations ------------------------- */
|
|
|
|
|
|
2005-06-19 13:53:29 +08:00
|
|
|
static int dsmark_graft(struct Qdisc *sch, unsigned long arg,
|
2017-12-21 01:35:17 +08:00
|
|
|
struct Qdisc *new, struct Qdisc **old,
|
|
|
|
|
struct netlink_ext_ack *extack)
|
2005-04-17 06:20:36 +08:00
|
|
|
{
|
2008-01-21 16:50:09 +08:00
|
|
|
struct dsmark_qdisc_data *p = qdisc_priv(sch);
|
2005-04-17 06:20:36 +08:00
|
|
|
|
2013-12-23 17:39:00 +08:00
|
|
|
pr_debug("%s(sch %p,[qdisc %p],new %p,old %p)\n",
|
|
|
|
|
__func__, sch, p, new, old);
|
2005-06-01 06:16:52 +08:00
|
|
|
|
|
|
|
|
if (new == NULL) {
|
2010-10-16 21:04:08 +08:00
|
|
|
new = qdisc_create_dflt(sch->dev_queue, &pfifo_qdisc_ops,
|
2017-12-21 01:35:21 +08:00
|
|
|
sch->handle, NULL);
|
2005-06-01 06:16:52 +08:00
|
|
|
if (new == NULL)
|
|
|
|
|
new = &noop_qdisc;
|
|
|
|
|
}
|
|
|
|
|
|
2016-02-26 06:55:00 +08:00
|
|
|
*old = qdisc_replace(sch, new, &p->q);
|
2007-02-09 22:25:16 +08:00
|
|
|
return 0;
|
2005-04-17 06:20:36 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
|
|
static struct Qdisc *dsmark_leaf(struct Qdisc *sch, unsigned long arg)
|
|
|
|
|
{
|
2008-01-21 16:50:09 +08:00
|
|
|
struct dsmark_qdisc_data *p = qdisc_priv(sch);
|
|
|
|
|
return p->q;
|
2005-04-17 06:20:36 +08:00
|
|
|
}
|
|
|
|
|
|
net_sched: remove tc class reference counting
For TC classes, their ->get() and ->put() are always paired, and the
reference counting is completely useless, because:
1) For class modification and dumping paths, we already hold RTNL lock,
so all of these ->get(),->change(),->put() are atomic.
2) For filter bindiing/unbinding, we use other reference counter than
this one, and they should have RTNL lock too.
3) For ->qlen_notify(), it is special because it is called on ->enqueue()
path, but we already hold qdisc tree lock there, and we hold this
tree lock when graft or delete the class too, so it should not be gone
or changed until we release the tree lock.
Therefore, this patch removes ->get() and ->put(), but:
1) Adds a new ->find() to find the pointer to a class by classid, no
refcnt.
2) Move the original class destroy upon the last refcnt into ->delete(),
right after releasing tree lock. This is fine because the class is
already removed from hash when holding the lock.
For those who also use ->put() as ->unbind(), just rename them to reflect
this change.
Cc: Jamal Hadi Salim <jhs@mojatatu.com>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
Acked-by: Jamal Hadi Salim <jhs@mojatatu.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2017-08-25 07:51:29 +08:00
|
|
|
static unsigned long dsmark_find(struct Qdisc *sch, u32 classid)
|
2005-04-17 06:20:36 +08:00
|
|
|
{
|
2005-06-19 13:53:29 +08:00
|
|
|
return TC_H_MIN(classid) + 1;
|
2005-04-17 06:20:36 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
|
|
static unsigned long dsmark_bind_filter(struct Qdisc *sch,
|
2005-06-19 13:53:29 +08:00
|
|
|
unsigned long parent, u32 classid)
|
2005-04-17 06:20:36 +08:00
|
|
|
{
|
net_sched: remove tc class reference counting
For TC classes, their ->get() and ->put() are always paired, and the
reference counting is completely useless, because:
1) For class modification and dumping paths, we already hold RTNL lock,
so all of these ->get(),->change(),->put() are atomic.
2) For filter bindiing/unbinding, we use other reference counter than
this one, and they should have RTNL lock too.
3) For ->qlen_notify(), it is special because it is called on ->enqueue()
path, but we already hold qdisc tree lock there, and we hold this
tree lock when graft or delete the class too, so it should not be gone
or changed until we release the tree lock.
Therefore, this patch removes ->get() and ->put(), but:
1) Adds a new ->find() to find the pointer to a class by classid, no
refcnt.
2) Move the original class destroy upon the last refcnt into ->delete(),
right after releasing tree lock. This is fine because the class is
already removed from hash when holding the lock.
For those who also use ->put() as ->unbind(), just rename them to reflect
this change.
Cc: Jamal Hadi Salim <jhs@mojatatu.com>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
Acked-by: Jamal Hadi Salim <jhs@mojatatu.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2017-08-25 07:51:29 +08:00
|
|
|
pr_debug("%s(sch %p,[qdisc %p],classid %x)\n",
|
|
|
|
|
__func__, sch, qdisc_priv(sch), classid);
|
|
|
|
|
|
|
|
|
|
return dsmark_find(sch, classid);
|
2005-04-17 06:20:36 +08:00
|
|
|
}
|
|
|
|
|
|
net_sched: remove tc class reference counting
For TC classes, their ->get() and ->put() are always paired, and the
reference counting is completely useless, because:
1) For class modification and dumping paths, we already hold RTNL lock,
so all of these ->get(),->change(),->put() are atomic.
2) For filter bindiing/unbinding, we use other reference counter than
this one, and they should have RTNL lock too.
3) For ->qlen_notify(), it is special because it is called on ->enqueue()
path, but we already hold qdisc tree lock there, and we hold this
tree lock when graft or delete the class too, so it should not be gone
or changed until we release the tree lock.
Therefore, this patch removes ->get() and ->put(), but:
1) Adds a new ->find() to find the pointer to a class by classid, no
refcnt.
2) Move the original class destroy upon the last refcnt into ->delete(),
right after releasing tree lock. This is fine because the class is
already removed from hash when holding the lock.
For those who also use ->put() as ->unbind(), just rename them to reflect
this change.
Cc: Jamal Hadi Salim <jhs@mojatatu.com>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
Acked-by: Jamal Hadi Salim <jhs@mojatatu.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2017-08-25 07:51:29 +08:00
|
|
|
static void dsmark_unbind_filter(struct Qdisc *sch, unsigned long cl)
|
2005-04-17 06:20:36 +08:00
|
|
|
{
|
|
|
|
|
}
|
|
|
|
|
|
2008-01-24 12:35:39 +08:00
|
|
|
static const struct nla_policy dsmark_policy[TCA_DSMARK_MAX + 1] = {
|
|
|
|
|
[TCA_DSMARK_INDICES] = { .type = NLA_U16 },
|
|
|
|
|
[TCA_DSMARK_DEFAULT_INDEX] = { .type = NLA_U16 },
|
|
|
|
|
[TCA_DSMARK_SET_TC_INDEX] = { .type = NLA_FLAG },
|
|
|
|
|
[TCA_DSMARK_MASK] = { .type = NLA_U8 },
|
|
|
|
|
[TCA_DSMARK_VALUE] = { .type = NLA_U8 },
|
|
|
|
|
};
|
|
|
|
|
|
2005-04-17 06:20:36 +08:00
|
|
|
static int dsmark_change(struct Qdisc *sch, u32 classid, u32 parent,
|
2017-12-21 01:35:15 +08:00
|
|
|
struct nlattr **tca, unsigned long *arg,
|
|
|
|
|
struct netlink_ext_ack *extack)
|
2005-04-17 06:20:36 +08:00
|
|
|
{
|
2008-01-21 16:50:09 +08:00
|
|
|
struct dsmark_qdisc_data *p = qdisc_priv(sch);
|
2008-01-23 14:11:17 +08:00
|
|
|
struct nlattr *opt = tca[TCA_OPTIONS];
|
|
|
|
|
struct nlattr *tb[TCA_DSMARK_MAX + 1];
|
2005-06-19 13:52:54 +08:00
|
|
|
int err = -EINVAL;
|
2005-04-17 06:20:36 +08:00
|
|
|
|
2013-12-23 17:39:00 +08:00
|
|
|
pr_debug("%s(sch %p,[qdisc %p],classid %x,parent %x), arg 0x%lx\n",
|
|
|
|
|
__func__, sch, p, classid, parent, *arg);
|
2005-06-19 13:52:54 +08:00
|
|
|
|
|
|
|
|
if (!dsmark_valid_index(p, *arg)) {
|
|
|
|
|
err = -ENOENT;
|
2008-01-23 14:11:17 +08:00
|
|
|
goto errout;
|
2005-04-17 06:20:36 +08:00
|
|
|
}
|
|
|
|
|
|
2008-01-24 12:33:32 +08:00
|
|
|
if (!opt)
|
2008-01-23 14:11:17 +08:00
|
|
|
goto errout;
|
2005-06-19 13:52:54 +08:00
|
|
|
|
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_DSMARK_MAX, opt,
|
|
|
|
|
dsmark_policy, NULL);
|
2008-01-24 12:33:32 +08:00
|
|
|
if (err < 0)
|
2008-01-24 12:35:39 +08:00
|
|
|
goto errout;
|
2008-01-24 12:33:32 +08:00
|
|
|
|
2008-01-24 12:35:39 +08:00
|
|
|
if (tb[TCA_DSMARK_VALUE])
|
2015-09-18 07:37:13 +08:00
|
|
|
p->mv[*arg - 1].value = nla_get_u8(tb[TCA_DSMARK_VALUE]);
|
2007-02-09 22:25:16 +08:00
|
|
|
|
2008-01-23 14:11:17 +08:00
|
|
|
if (tb[TCA_DSMARK_MASK])
|
2015-09-18 07:37:13 +08:00
|
|
|
p->mv[*arg - 1].mask = nla_get_u8(tb[TCA_DSMARK_MASK]);
|
2005-06-19 13:52:54 +08:00
|
|
|
|
|
|
|
|
err = 0;
|
|
|
|
|
|
2008-01-23 14:11:17 +08:00
|
|
|
errout:
|
2005-06-19 13:52:54 +08:00
|
|
|
return err;
|
|
|
|
|
}
|
2005-04-17 06:20:36 +08:00
|
|
|
|
2021-01-19 20:08:12 +08:00
|
|
|
static int dsmark_delete(struct Qdisc *sch, unsigned long arg,
|
|
|
|
|
struct netlink_ext_ack *extack)
|
2005-04-17 06:20:36 +08:00
|
|
|
{
|
2008-01-21 16:50:09 +08:00
|
|
|
struct dsmark_qdisc_data *p = qdisc_priv(sch);
|
2005-04-17 06:20:36 +08:00
|
|
|
|
2005-06-19 13:53:29 +08:00
|
|
|
if (!dsmark_valid_index(p, arg))
|
2005-04-17 06:20:36 +08:00
|
|
|
return -EINVAL;
|
2007-02-09 22:25:16 +08:00
|
|
|
|
2015-09-18 07:37:13 +08:00
|
|
|
p->mv[arg - 1].mask = 0xff;
|
|
|
|
|
p->mv[arg - 1].value = 0;
|
2005-06-19 13:53:29 +08:00
|
|
|
|
2005-04-17 06:20:36 +08:00
|
|
|
return 0;
|
|
|
|
|
}
|
|
|
|
|
|
2008-01-21 18:24:21 +08:00
|
|
|
static void dsmark_walk(struct Qdisc *sch, struct qdisc_walker *walker)
|
2005-04-17 06:20:36 +08:00
|
|
|
{
|
2008-01-21 16:50:09 +08:00
|
|
|
struct dsmark_qdisc_data *p = qdisc_priv(sch);
|
2005-04-17 06:20:36 +08:00
|
|
|
int i;
|
|
|
|
|
|
2013-12-23 17:39:00 +08:00
|
|
|
pr_debug("%s(sch %p,[qdisc %p],walker %p)\n",
|
|
|
|
|
__func__, sch, p, walker);
|
2005-06-19 13:53:29 +08:00
|
|
|
|
2005-04-17 06:20:36 +08:00
|
|
|
if (walker->stop)
|
|
|
|
|
return;
|
2005-06-19 13:53:29 +08:00
|
|
|
|
2005-04-17 06:20:36 +08:00
|
|
|
for (i = 0; i < p->indices; i++) {
|
2015-09-18 07:37:13 +08:00
|
|
|
if (p->mv[i].mask == 0xff && !p->mv[i].value)
|
2005-06-01 06:15:58 +08:00
|
|
|
goto ignore;
|
2005-04-17 06:20:36 +08:00
|
|
|
if (walker->count >= walker->skip) {
|
2011-01-20 03:26:56 +08:00
|
|
|
if (walker->fn(sch, i + 1, walker) < 0) {
|
2005-04-17 06:20:36 +08:00
|
|
|
walker->stop = 1;
|
|
|
|
|
break;
|
|
|
|
|
}
|
|
|
|
|
}
|
2007-02-09 22:25:16 +08:00
|
|
|
ignore:
|
2005-06-01 06:15:58 +08:00
|
|
|
walker->count++;
|
2007-02-09 22:25:16 +08:00
|
|
|
}
|
2005-04-17 06:20:36 +08:00
|
|
|
}
|
|
|
|
|
|
2017-12-21 01:35:16 +08:00
|
|
|
static struct tcf_block *dsmark_tcf_block(struct Qdisc *sch, unsigned long cl,
|
|
|
|
|
struct netlink_ext_ack *extack)
|
2005-04-17 06:20:36 +08:00
|
|
|
{
|
2008-01-21 16:50:09 +08:00
|
|
|
struct dsmark_qdisc_data *p = qdisc_priv(sch);
|
2017-05-17 17:07:55 +08:00
|
|
|
|
|
|
|
|
return p->block;
|
2005-04-17 06:20:36 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
|
|
/* --------------------------- Qdisc operations ---------------------------- */
|
|
|
|
|
|
2016-06-22 14:16:49 +08:00
|
|
|
static int dsmark_enqueue(struct sk_buff *skb, struct Qdisc *sch,
|
|
|
|
|
struct sk_buff **to_free)
|
2005-04-17 06:20:36 +08:00
|
|
|
{
|
2019-01-10 00:09:42 +08:00
|
|
|
unsigned int len = qdisc_pkt_len(skb);
|
2008-01-21 16:50:09 +08:00
|
|
|
struct dsmark_qdisc_data *p = qdisc_priv(sch);
|
2005-06-19 13:53:29 +08:00
|
|
|
int err;
|
|
|
|
|
|
2013-12-23 17:39:00 +08:00
|
|
|
pr_debug("%s(skb %p,sch %p,[qdisc %p])\n", __func__, skb, sch, p);
|
2005-04-17 06:20:36 +08:00
|
|
|
|
|
|
|
|
if (p->set_tc_index) {
|
2017-03-17 23:05:28 +08:00
|
|
|
int wlen = skb_network_offset(skb);
|
|
|
|
|
|
sched: consistently handle layer3 header accesses in the presence of VLANs
There are a couple of places in net/sched/ that check skb->protocol and act
on the value there. However, in the presence of VLAN tags, the value stored
in skb->protocol can be inconsistent based on whether VLAN acceleration is
enabled. The commit quoted in the Fixes tag below fixed the users of
skb->protocol to use a helper that will always see the VLAN ethertype.
However, most of the callers don't actually handle the VLAN ethertype, but
expect to find the IP header type in the protocol field. This means that
things like changing the ECN field, or parsing diffserv values, stops
working if there's a VLAN tag, or if there are multiple nested VLAN
tags (QinQ).
To fix this, change the helper to take an argument that indicates whether
the caller wants to skip the VLAN tags or not. When skipping VLAN tags, we
make sure to skip all of them, so behaviour is consistent even in QinQ
mode.
To make the helper usable from the ECN code, move it to if_vlan.h instead
of pkt_sched.h.
v3:
- Remove empty lines
- Move vlan variable definitions inside loop in skb_protocol()
- Also use skb_protocol() helper in IP{,6}_ECN_decapsulate() and
bpf_skb_ecn_set_ce()
v2:
- Use eth_type_vlan() helper in skb_protocol()
- Also fix code that reads skb->protocol directly
- Change a couple of 'if/else if' statements to switch constructs to avoid
calling the helper twice
Reported-by: Ilya Ponetayev <i.ponetaev@ndmsystems.com>
Fixes: d8b9605d2697 ("net: sched: fix skb->protocol use in case of accelerated vlan path")
Signed-off-by: Toke Høiland-Jørgensen <toke@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2020-07-04 04:26:43 +08:00
|
|
|
switch (skb_protocol(skb, true)) {
|
2008-09-21 13:20:49 +08:00
|
|
|
case htons(ETH_P_IP):
|
2017-03-17 23:05:28 +08:00
|
|
|
wlen += sizeof(struct iphdr);
|
|
|
|
|
if (!pskb_may_pull(skb, wlen) ||
|
|
|
|
|
skb_try_make_writable(skb, wlen))
|
2008-01-21 18:24:21 +08:00
|
|
|
goto drop;
|
2008-01-21 18:23:49 +08:00
|
|
|
|
2008-01-21 18:24:21 +08:00
|
|
|
skb->tc_index = ipv4_get_dsfield(ip_hdr(skb))
|
|
|
|
|
& ~INET_ECN_MASK;
|
|
|
|
|
break;
|
2008-01-21 18:23:49 +08:00
|
|
|
|
2008-09-21 13:20:49 +08:00
|
|
|
case htons(ETH_P_IPV6):
|
2017-03-17 23:05:28 +08:00
|
|
|
wlen += sizeof(struct ipv6hdr);
|
|
|
|
|
if (!pskb_may_pull(skb, wlen) ||
|
|
|
|
|
skb_try_make_writable(skb, wlen))
|
2008-01-21 18:24:21 +08:00
|
|
|
goto drop;
|
2008-01-21 18:23:49 +08:00
|
|
|
|
2008-01-21 18:24:21 +08:00
|
|
|
skb->tc_index = ipv6_get_dsfield(ipv6_hdr(skb))
|
|
|
|
|
& ~INET_ECN_MASK;
|
|
|
|
|
break;
|
|
|
|
|
default:
|
|
|
|
|
skb->tc_index = 0;
|
|
|
|
|
break;
|
2007-04-21 08:09:22 +08:00
|
|
|
}
|
2005-04-17 06:20:36 +08:00
|
|
|
}
|
2005-06-19 13:53:29 +08:00
|
|
|
|
|
|
|
|
if (TC_H_MAJ(skb->priority) == sch->handle)
|
2005-04-17 06:20:36 +08:00
|
|
|
skb->tc_index = TC_H_MIN(skb->priority);
|
2005-06-19 13:53:29 +08:00
|
|
|
else {
|
|
|
|
|
struct tcf_result res;
|
2014-09-13 11:05:27 +08:00
|
|
|
struct tcf_proto *fl = rcu_dereference_bh(p->filter_list);
|
2021-07-29 02:08:00 +08:00
|
|
|
int result = tcf_classify(skb, NULL, fl, &res, false);
|
2005-06-19 13:53:29 +08:00
|
|
|
|
2008-01-21 16:50:09 +08:00
|
|
|
pr_debug("result %d class 0x%04x\n", result, res.classid);
|
2005-06-19 13:53:29 +08:00
|
|
|
|
2005-04-17 06:20:36 +08:00
|
|
|
switch (result) {
|
2007-07-15 15:02:10 +08:00
|
|
|
#ifdef CONFIG_NET_CLS_ACT
|
|
|
|
|
case TC_ACT_QUEUED:
|
|
|
|
|
case TC_ACT_STOLEN:
|
2017-06-06 20:12:02 +08:00
|
|
|
case TC_ACT_TRAP:
|
2016-06-22 14:16:49 +08:00
|
|
|
__qdisc_drop(skb, to_free);
|
2008-08-05 13:31:03 +08:00
|
|
|
return NET_XMIT_SUCCESS | __NET_XMIT_STOLEN;
|
2008-01-21 18:23:49 +08:00
|
|
|
|
2007-07-15 15:02:10 +08:00
|
|
|
case TC_ACT_SHOT:
|
2008-01-21 18:23:49 +08:00
|
|
|
goto drop;
|
2005-04-17 06:20:36 +08:00
|
|
|
#endif
|
2007-07-15 15:03:05 +08:00
|
|
|
case TC_ACT_OK:
|
2007-07-15 15:02:10 +08:00
|
|
|
skb->tc_index = TC_H_MIN(res.classid);
|
|
|
|
|
break;
|
2008-01-21 18:23:49 +08:00
|
|
|
|
2007-07-15 15:02:10 +08:00
|
|
|
default:
|
|
|
|
|
if (p->default_index != NO_DEFAULT_INDEX)
|
|
|
|
|
skb->tc_index = p->default_index;
|
|
|
|
|
break;
|
2007-04-21 08:09:22 +08:00
|
|
|
}
|
2005-04-17 06:20:36 +08:00
|
|
|
}
|
|
|
|
|
|
2016-06-22 14:16:49 +08:00
|
|
|
err = qdisc_enqueue(skb, p->q, to_free);
|
2005-06-19 13:53:29 +08:00
|
|
|
if (err != NET_XMIT_SUCCESS) {
|
2008-08-05 13:31:03 +08:00
|
|
|
if (net_xmit_drop_count(err))
|
2014-09-29 02:53:29 +08:00
|
|
|
qdisc_qstats_drop(sch);
|
2005-06-19 13:53:29 +08:00
|
|
|
return err;
|
2005-04-17 06:20:36 +08:00
|
|
|
}
|
2005-06-19 13:53:29 +08:00
|
|
|
|
2019-01-10 00:09:42 +08:00
|
|
|
sch->qstats.backlog += len;
|
2005-04-17 06:20:36 +08:00
|
|
|
sch->q.qlen++;
|
|
|
|
|
|
2005-06-19 13:53:29 +08:00
|
|
|
return NET_XMIT_SUCCESS;
|
2008-01-21 18:23:49 +08:00
|
|
|
|
|
|
|
|
drop:
|
2016-06-22 14:16:49 +08:00
|
|
|
qdisc_drop(skb, sch, to_free);
|
2008-08-05 13:39:11 +08:00
|
|
|
return NET_XMIT_SUCCESS | __NET_XMIT_BYPASS;
|
2005-06-19 13:53:29 +08:00
|
|
|
}
|
2005-04-17 06:20:36 +08:00
|
|
|
|
|
|
|
|
static struct sk_buff *dsmark_dequeue(struct Qdisc *sch)
|
|
|
|
|
{
|
2008-01-21 16:50:09 +08:00
|
|
|
struct dsmark_qdisc_data *p = qdisc_priv(sch);
|
2005-04-17 06:20:36 +08:00
|
|
|
struct sk_buff *skb;
|
2005-06-19 13:53:29 +08:00
|
|
|
u32 index;
|
|
|
|
|
|
2013-12-23 17:39:00 +08:00
|
|
|
pr_debug("%s(sch %p,[qdisc %p])\n", __func__, sch, p);
|
2005-04-17 06:20:36 +08:00
|
|
|
|
2016-03-07 12:07:57 +08:00
|
|
|
skb = qdisc_dequeue_peeked(p->q);
|
2005-06-19 13:53:29 +08:00
|
|
|
if (skb == NULL)
|
2005-04-17 06:20:36 +08:00
|
|
|
return NULL;
|
2005-06-19 13:53:29 +08:00
|
|
|
|
2011-01-21 15:31:33 +08:00
|
|
|
qdisc_bstats_update(sch, skb);
|
2016-02-26 06:55:03 +08:00
|
|
|
qdisc_qstats_backlog_dec(sch, skb);
|
2005-04-17 06:20:36 +08:00
|
|
|
sch->q.qlen--;
|
2005-06-19 13:53:29 +08:00
|
|
|
|
|
|
|
|
index = skb->tc_index & (p->indices - 1);
|
2008-01-21 16:50:09 +08:00
|
|
|
pr_debug("index %d->%d\n", skb->tc_index, index);
|
2005-06-19 13:53:29 +08:00
|
|
|
|
sched: consistently handle layer3 header accesses in the presence of VLANs
There are a couple of places in net/sched/ that check skb->protocol and act
on the value there. However, in the presence of VLAN tags, the value stored
in skb->protocol can be inconsistent based on whether VLAN acceleration is
enabled. The commit quoted in the Fixes tag below fixed the users of
skb->protocol to use a helper that will always see the VLAN ethertype.
However, most of the callers don't actually handle the VLAN ethertype, but
expect to find the IP header type in the protocol field. This means that
things like changing the ECN field, or parsing diffserv values, stops
working if there's a VLAN tag, or if there are multiple nested VLAN
tags (QinQ).
To fix this, change the helper to take an argument that indicates whether
the caller wants to skip the VLAN tags or not. When skipping VLAN tags, we
make sure to skip all of them, so behaviour is consistent even in QinQ
mode.
To make the helper usable from the ECN code, move it to if_vlan.h instead
of pkt_sched.h.
v3:
- Remove empty lines
- Move vlan variable definitions inside loop in skb_protocol()
- Also use skb_protocol() helper in IP{,6}_ECN_decapsulate() and
bpf_skb_ecn_set_ce()
v2:
- Use eth_type_vlan() helper in skb_protocol()
- Also fix code that reads skb->protocol directly
- Change a couple of 'if/else if' statements to switch constructs to avoid
calling the helper twice
Reported-by: Ilya Ponetayev <i.ponetaev@ndmsystems.com>
Fixes: d8b9605d2697 ("net: sched: fix skb->protocol use in case of accelerated vlan path")
Signed-off-by: Toke Høiland-Jørgensen <toke@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2020-07-04 04:26:43 +08:00
|
|
|
switch (skb_protocol(skb, true)) {
|
2008-09-21 13:20:49 +08:00
|
|
|
case htons(ETH_P_IP):
|
2015-09-18 07:37:13 +08:00
|
|
|
ipv4_change_dsfield(ip_hdr(skb), p->mv[index].mask,
|
|
|
|
|
p->mv[index].value);
|
2005-04-17 06:20:36 +08:00
|
|
|
break;
|
2008-09-21 13:20:49 +08:00
|
|
|
case htons(ETH_P_IPV6):
|
2015-09-18 07:37:13 +08:00
|
|
|
ipv6_change_dsfield(ipv6_hdr(skb), p->mv[index].mask,
|
|
|
|
|
p->mv[index].value);
|
2005-04-17 06:20:36 +08:00
|
|
|
break;
|
2008-01-21 18:24:21 +08:00
|
|
|
default:
|
|
|
|
|
/*
|
|
|
|
|
* Only complain if a change was actually attempted.
|
|
|
|
|
* This way, we can send non-IP traffic through dsmark
|
|
|
|
|
* and don't need yet another qdisc as a bypass.
|
|
|
|
|
*/
|
2015-09-18 07:37:13 +08:00
|
|
|
if (p->mv[index].mask != 0xff || p->mv[index].value)
|
2013-12-23 17:39:00 +08:00
|
|
|
pr_warn("%s: unsupported protocol %d\n",
|
sched: consistently handle layer3 header accesses in the presence of VLANs
There are a couple of places in net/sched/ that check skb->protocol and act
on the value there. However, in the presence of VLAN tags, the value stored
in skb->protocol can be inconsistent based on whether VLAN acceleration is
enabled. The commit quoted in the Fixes tag below fixed the users of
skb->protocol to use a helper that will always see the VLAN ethertype.
However, most of the callers don't actually handle the VLAN ethertype, but
expect to find the IP header type in the protocol field. This means that
things like changing the ECN field, or parsing diffserv values, stops
working if there's a VLAN tag, or if there are multiple nested VLAN
tags (QinQ).
To fix this, change the helper to take an argument that indicates whether
the caller wants to skip the VLAN tags or not. When skipping VLAN tags, we
make sure to skip all of them, so behaviour is consistent even in QinQ
mode.
To make the helper usable from the ECN code, move it to if_vlan.h instead
of pkt_sched.h.
v3:
- Remove empty lines
- Move vlan variable definitions inside loop in skb_protocol()
- Also use skb_protocol() helper in IP{,6}_ECN_decapsulate() and
bpf_skb_ecn_set_ce()
v2:
- Use eth_type_vlan() helper in skb_protocol()
- Also fix code that reads skb->protocol directly
- Change a couple of 'if/else if' statements to switch constructs to avoid
calling the helper twice
Reported-by: Ilya Ponetayev <i.ponetaev@ndmsystems.com>
Fixes: d8b9605d2697 ("net: sched: fix skb->protocol use in case of accelerated vlan path")
Signed-off-by: Toke Høiland-Jørgensen <toke@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2020-07-04 04:26:43 +08:00
|
|
|
__func__, ntohs(skb_protocol(skb, true)));
|
2008-01-21 18:24:21 +08:00
|
|
|
break;
|
2007-04-21 08:09:22 +08:00
|
|
|
}
|
2005-06-19 13:53:29 +08:00
|
|
|
|
2005-04-17 06:20:36 +08:00
|
|
|
return skb;
|
|
|
|
|
}
|
|
|
|
|
|
2008-10-31 15:45:55 +08:00
|
|
|
static struct sk_buff *dsmark_peek(struct Qdisc *sch)
|
|
|
|
|
{
|
|
|
|
|
struct dsmark_qdisc_data *p = qdisc_priv(sch);
|
|
|
|
|
|
2013-12-23 17:39:00 +08:00
|
|
|
pr_debug("%s(sch %p,[qdisc %p])\n", __func__, sch, p);
|
2008-10-31 15:45:55 +08:00
|
|
|
|
|
|
|
|
return p->q->ops->peek(p->q);
|
|
|
|
|
}
|
|
|
|
|
|
2017-12-21 01:35:13 +08:00
|
|
|
static int dsmark_init(struct Qdisc *sch, struct nlattr *opt,
|
|
|
|
|
struct netlink_ext_ack *extack)
|
2005-04-17 06:20:36 +08:00
|
|
|
{
|
2008-01-21 16:50:09 +08:00
|
|
|
struct dsmark_qdisc_data *p = qdisc_priv(sch);
|
2008-01-23 14:11:17 +08:00
|
|
|
struct nlattr *tb[TCA_DSMARK_MAX + 1];
|
2017-05-18 04:03:16 +08:00
|
|
|
int err = -EINVAL;
|
2005-06-19 13:52:54 +08:00
|
|
|
u32 default_index = NO_DEFAULT_INDEX;
|
|
|
|
|
u16 indices;
|
2015-09-18 07:37:13 +08:00
|
|
|
int i;
|
2005-06-19 13:52:54 +08:00
|
|
|
|
2013-12-23 17:39:00 +08:00
|
|
|
pr_debug("%s(sch %p,[qdisc %p],opt %p)\n", __func__, sch, p, opt);
|
2005-06-19 13:52:54 +08:00
|
|
|
|
2008-01-24 12:33:32 +08:00
|
|
|
if (!opt)
|
|
|
|
|
goto errout;
|
|
|
|
|
|
2017-12-21 01:35:19 +08:00
|
|
|
err = tcf_block_get(&p->block, &p->filter_list, sch, extack);
|
2017-05-17 17:07:55 +08:00
|
|
|
if (err)
|
|
|
|
|
return err;
|
|
|
|
|
|
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_DSMARK_MAX, opt,
|
|
|
|
|
dsmark_policy, NULL);
|
2008-01-24 12:33:32 +08:00
|
|
|
if (err < 0)
|
2005-06-19 13:52:54 +08:00
|
|
|
goto errout;
|
|
|
|
|
|
2008-01-24 12:33:32 +08:00
|
|
|
err = -EINVAL;
|
2019-10-05 01:34:45 +08:00
|
|
|
if (!tb[TCA_DSMARK_INDICES])
|
|
|
|
|
goto errout;
|
2008-01-23 14:11:17 +08:00
|
|
|
indices = nla_get_u16(tb[TCA_DSMARK_INDICES]);
|
2008-01-21 18:21:45 +08:00
|
|
|
|
|
|
|
|
if (hweight32(indices) != 1)
|
2005-06-19 13:52:54 +08:00
|
|
|
goto errout;
|
|
|
|
|
|
2008-01-24 12:35:39 +08:00
|
|
|
if (tb[TCA_DSMARK_DEFAULT_INDEX])
|
2008-01-23 14:11:17 +08:00
|
|
|
default_index = nla_get_u16(tb[TCA_DSMARK_DEFAULT_INDEX]);
|
2005-06-19 13:52:54 +08:00
|
|
|
|
2015-09-18 07:37:13 +08:00
|
|
|
if (indices <= DSMARK_EMBEDDED_SZ)
|
|
|
|
|
p->mv = p->embedded;
|
|
|
|
|
else
|
|
|
|
|
p->mv = kmalloc_array(indices, sizeof(*p->mv), GFP_KERNEL);
|
|
|
|
|
if (!p->mv) {
|
2005-06-19 13:52:54 +08:00
|
|
|
err = -ENOMEM;
|
|
|
|
|
goto errout;
|
2005-04-17 06:20:36 +08:00
|
|
|
}
|
2015-09-18 07:37:13 +08:00
|
|
|
for (i = 0; i < indices; i++) {
|
|
|
|
|
p->mv[i].mask = 0xff;
|
|
|
|
|
p->mv[i].value = 0;
|
|
|
|
|
}
|
2005-06-19 13:52:54 +08:00
|
|
|
p->indices = indices;
|
|
|
|
|
p->default_index = default_index;
|
2008-01-23 14:11:17 +08:00
|
|
|
p->set_tc_index = nla_get_flag(tb[TCA_DSMARK_SET_TC_INDEX]);
|
2005-06-19 13:52:54 +08:00
|
|
|
|
2017-12-21 01:35:21 +08:00
|
|
|
p->q = qdisc_create_dflt(sch->dev_queue, &pfifo_qdisc_ops, sch->handle,
|
|
|
|
|
NULL);
|
2005-06-19 13:52:54 +08:00
|
|
|
if (p->q == NULL)
|
2005-04-17 06:20:36 +08:00
|
|
|
p->q = &noop_qdisc;
|
2017-03-08 23:03:32 +08:00
|
|
|
else
|
|
|
|
|
qdisc_hash_add(p->q, true);
|
2005-06-19 13:52:54 +08:00
|
|
|
|
2013-12-23 17:39:00 +08:00
|
|
|
pr_debug("%s: qdisc %p\n", __func__, p->q);
|
2005-06-19 13:52:54 +08:00
|
|
|
|
|
|
|
|
err = 0;
|
|
|
|
|
errout:
|
|
|
|
|
return err;
|
2005-04-17 06:20:36 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
|
|
static void dsmark_reset(struct Qdisc *sch)
|
|
|
|
|
{
|
2008-01-21 16:50:09 +08:00
|
|
|
struct dsmark_qdisc_data *p = qdisc_priv(sch);
|
2005-04-17 06:20:36 +08:00
|
|
|
|
2013-12-23 17:39:00 +08:00
|
|
|
pr_debug("%s(sch %p,[qdisc %p])\n", __func__, sch, p);
|
2021-05-23 22:38:53 +08:00
|
|
|
if (p->q)
|
|
|
|
|
qdisc_reset(p->q);
|
2016-02-26 06:55:03 +08:00
|
|
|
sch->qstats.backlog = 0;
|
2005-04-17 06:20:36 +08:00
|
|
|
sch->q.qlen = 0;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
static void dsmark_destroy(struct Qdisc *sch)
|
|
|
|
|
{
|
2008-01-21 16:50:09 +08:00
|
|
|
struct dsmark_qdisc_data *p = qdisc_priv(sch);
|
2005-04-17 06:20:36 +08:00
|
|
|
|
2013-12-23 17:39:00 +08:00
|
|
|
pr_debug("%s(sch %p,[qdisc %p])\n", __func__, sch, p);
|
2005-06-19 13:53:29 +08:00
|
|
|
|
2017-05-17 17:07:55 +08:00
|
|
|
tcf_block_put(p->block);
|
2018-09-25 00:22:50 +08:00
|
|
|
qdisc_put(p->q);
|
2015-09-18 07:37:13 +08:00
|
|
|
if (p->mv != p->embedded)
|
|
|
|
|
kfree(p->mv);
|
2005-04-17 06:20:36 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
|
|
static int dsmark_dump_class(struct Qdisc *sch, unsigned long cl,
|
2005-06-19 13:53:12 +08:00
|
|
|
struct sk_buff *skb, struct tcmsg *tcm)
|
2005-04-17 06:20:36 +08:00
|
|
|
{
|
2008-01-21 16:50:09 +08:00
|
|
|
struct dsmark_qdisc_data *p = qdisc_priv(sch);
|
2008-01-23 14:11:17 +08:00
|
|
|
struct nlattr *opts = NULL;
|
2005-04-17 06:20:36 +08:00
|
|
|
|
2013-12-23 17:39:00 +08:00
|
|
|
pr_debug("%s(sch %p,[qdisc %p],class %ld\n", __func__, sch, p, cl);
|
2005-06-19 13:53:12 +08:00
|
|
|
|
|
|
|
|
if (!dsmark_valid_index(p, cl))
|
2005-04-17 06:20:36 +08:00
|
|
|
return -EINVAL;
|
2005-06-19 13:53:12 +08:00
|
|
|
|
2011-01-20 03:26:56 +08:00
|
|
|
tcm->tcm_handle = TC_H_MAKE(TC_H_MAJ(sch->handle), cl - 1);
|
2006-03-21 11:01:06 +08:00
|
|
|
tcm->tcm_info = p->q->handle;
|
2005-06-19 13:53:12 +08:00
|
|
|
|
2019-04-26 17:13:06 +08:00
|
|
|
opts = nla_nest_start_noflag(skb, TCA_OPTIONS);
|
2008-01-23 14:11:17 +08:00
|
|
|
if (opts == NULL)
|
|
|
|
|
goto nla_put_failure;
|
2015-09-18 07:37:13 +08:00
|
|
|
if (nla_put_u8(skb, TCA_DSMARK_MASK, p->mv[cl - 1].mask) ||
|
|
|
|
|
nla_put_u8(skb, TCA_DSMARK_VALUE, p->mv[cl - 1].value))
|
2012-03-29 17:11:39 +08:00
|
|
|
goto nla_put_failure;
|
2005-06-19 13:53:12 +08:00
|
|
|
|
2008-01-23 14:11:17 +08:00
|
|
|
return nla_nest_end(skb, opts);
|
2005-04-17 06:20:36 +08:00
|
|
|
|
2008-01-23 14:11:17 +08:00
|
|
|
nla_put_failure:
|
2008-06-04 07:36:54 +08:00
|
|
|
nla_nest_cancel(skb, opts);
|
|
|
|
|
return -EMSGSIZE;
|
2005-04-17 06:20:36 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
|
|
static int dsmark_dump(struct Qdisc *sch, struct sk_buff *skb)
|
|
|
|
|
{
|
2008-01-21 16:50:09 +08:00
|
|
|
struct dsmark_qdisc_data *p = qdisc_priv(sch);
|
2008-01-23 14:11:17 +08:00
|
|
|
struct nlattr *opts = NULL;
|
2005-04-17 06:20:36 +08:00
|
|
|
|
2019-04-26 17:13:06 +08:00
|
|
|
opts = nla_nest_start_noflag(skb, TCA_OPTIONS);
|
2008-01-23 14:11:17 +08:00
|
|
|
if (opts == NULL)
|
|
|
|
|
goto nla_put_failure;
|
2012-03-29 17:11:39 +08:00
|
|
|
if (nla_put_u16(skb, TCA_DSMARK_INDICES, p->indices))
|
|
|
|
|
goto nla_put_failure;
|
2005-06-19 13:53:12 +08:00
|
|
|
|
2012-03-29 17:11:39 +08:00
|
|
|
if (p->default_index != NO_DEFAULT_INDEX &&
|
|
|
|
|
nla_put_u16(skb, TCA_DSMARK_DEFAULT_INDEX, p->default_index))
|
|
|
|
|
goto nla_put_failure;
|
2005-04-17 06:20:36 +08:00
|
|
|
|
2012-03-29 17:11:39 +08:00
|
|
|
if (p->set_tc_index &&
|
|
|
|
|
nla_put_flag(skb, TCA_DSMARK_SET_TC_INDEX))
|
|
|
|
|
goto nla_put_failure;
|
2005-06-19 13:53:12 +08:00
|
|
|
|
2008-01-23 14:11:17 +08:00
|
|
|
return nla_nest_end(skb, opts);
|
2005-04-17 06:20:36 +08:00
|
|
|
|
2008-01-23 14:11:17 +08:00
|
|
|
nla_put_failure:
|
2008-06-04 07:36:54 +08:00
|
|
|
nla_nest_cancel(skb, opts);
|
|
|
|
|
return -EMSGSIZE;
|
2005-04-17 06:20:36 +08:00
|
|
|
}
|
|
|
|
|
|
2007-11-14 17:44:41 +08:00
|
|
|
static const struct Qdisc_class_ops dsmark_class_ops = {
|
2005-04-17 06:20:36 +08:00
|
|
|
.graft = dsmark_graft,
|
|
|
|
|
.leaf = dsmark_leaf,
|
net_sched: remove tc class reference counting
For TC classes, their ->get() and ->put() are always paired, and the
reference counting is completely useless, because:
1) For class modification and dumping paths, we already hold RTNL lock,
so all of these ->get(),->change(),->put() are atomic.
2) For filter bindiing/unbinding, we use other reference counter than
this one, and they should have RTNL lock too.
3) For ->qlen_notify(), it is special because it is called on ->enqueue()
path, but we already hold qdisc tree lock there, and we hold this
tree lock when graft or delete the class too, so it should not be gone
or changed until we release the tree lock.
Therefore, this patch removes ->get() and ->put(), but:
1) Adds a new ->find() to find the pointer to a class by classid, no
refcnt.
2) Move the original class destroy upon the last refcnt into ->delete(),
right after releasing tree lock. This is fine because the class is
already removed from hash when holding the lock.
For those who also use ->put() as ->unbind(), just rename them to reflect
this change.
Cc: Jamal Hadi Salim <jhs@mojatatu.com>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
Acked-by: Jamal Hadi Salim <jhs@mojatatu.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2017-08-25 07:51:29 +08:00
|
|
|
.find = dsmark_find,
|
2005-04-17 06:20:36 +08:00
|
|
|
.change = dsmark_change,
|
|
|
|
|
.delete = dsmark_delete,
|
|
|
|
|
.walk = dsmark_walk,
|
2017-05-17 17:07:55 +08:00
|
|
|
.tcf_block = dsmark_tcf_block,
|
2005-04-17 06:20:36 +08:00
|
|
|
.bind_tcf = dsmark_bind_filter,
|
net_sched: remove tc class reference counting
For TC classes, their ->get() and ->put() are always paired, and the
reference counting is completely useless, because:
1) For class modification and dumping paths, we already hold RTNL lock,
so all of these ->get(),->change(),->put() are atomic.
2) For filter bindiing/unbinding, we use other reference counter than
this one, and they should have RTNL lock too.
3) For ->qlen_notify(), it is special because it is called on ->enqueue()
path, but we already hold qdisc tree lock there, and we hold this
tree lock when graft or delete the class too, so it should not be gone
or changed until we release the tree lock.
Therefore, this patch removes ->get() and ->put(), but:
1) Adds a new ->find() to find the pointer to a class by classid, no
refcnt.
2) Move the original class destroy upon the last refcnt into ->delete(),
right after releasing tree lock. This is fine because the class is
already removed from hash when holding the lock.
For those who also use ->put() as ->unbind(), just rename them to reflect
this change.
Cc: Jamal Hadi Salim <jhs@mojatatu.com>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
Acked-by: Jamal Hadi Salim <jhs@mojatatu.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2017-08-25 07:51:29 +08:00
|
|
|
.unbind_tcf = dsmark_unbind_filter,
|
2005-04-17 06:20:36 +08:00
|
|
|
.dump = dsmark_dump_class,
|
|
|
|
|
};
|
|
|
|
|
|
2007-11-14 17:44:41 +08:00
|
|
|
static struct Qdisc_ops dsmark_qdisc_ops __read_mostly = {
|
2005-04-17 06:20:36 +08:00
|
|
|
.next = NULL,
|
|
|
|
|
.cl_ops = &dsmark_class_ops,
|
|
|
|
|
.id = "dsmark",
|
|
|
|
|
.priv_size = sizeof(struct dsmark_qdisc_data),
|
|
|
|
|
.enqueue = dsmark_enqueue,
|
|
|
|
|
.dequeue = dsmark_dequeue,
|
2008-10-31 15:45:55 +08:00
|
|
|
.peek = dsmark_peek,
|
2005-04-17 06:20:36 +08:00
|
|
|
.init = dsmark_init,
|
|
|
|
|
.reset = dsmark_reset,
|
|
|
|
|
.destroy = dsmark_destroy,
|
|
|
|
|
.change = NULL,
|
|
|
|
|
.dump = dsmark_dump,
|
|
|
|
|
.owner = THIS_MODULE,
|
|
|
|
|
};
|
|
|
|
|
|
|
|
|
|
static int __init dsmark_module_init(void)
|
|
|
|
|
{
|
|
|
|
|
return register_qdisc(&dsmark_qdisc_ops);
|
|
|
|
|
}
|
2005-06-19 13:53:29 +08:00
|
|
|
|
2007-02-09 22:25:16 +08:00
|
|
|
static void __exit dsmark_module_exit(void)
|
2005-04-17 06:20:36 +08:00
|
|
|
{
|
|
|
|
|
unregister_qdisc(&dsmark_qdisc_ops);
|
|
|
|
|
}
|
2005-06-19 13:53:29 +08:00
|
|
|
|
2005-04-17 06:20:36 +08:00
|
|
|
module_init(dsmark_module_init)
|
|
|
|
|
module_exit(dsmark_module_exit)
|
2005-06-19 13:53:29 +08:00
|
|
|
|
2005-04-17 06:20:36 +08:00
|
|
|
MODULE_LICENSE("GPL");
|