2019-05-29 01:10:04 +08:00
|
|
|
// SPDX-License-Identifier: GPL-2.0-only
|
2008-09-13 07:29:34 +08:00
|
|
|
/*
|
|
|
|
* Copyright (c) 2008, Intel Corporation.
|
|
|
|
*
|
|
|
|
* Author: Alexander Duyck <alexander.h.duyck@intel.com>
|
|
|
|
*/
|
|
|
|
|
|
|
|
#include <linux/module.h>
|
include cleanup: Update gfp.h and slab.h includes to prepare for breaking implicit slab.h inclusion from percpu.h
percpu.h is included by sched.h and module.h and thus ends up being
included when building most .c files. percpu.h includes slab.h which
in turn includes gfp.h making everything defined by the two files
universally available and complicating inclusion dependencies.
percpu.h -> slab.h dependency is about to be removed. Prepare for
this change by updating users of gfp and slab facilities include those
headers directly instead of assuming availability. As this conversion
needs to touch large number of source files, the following script is
used as the basis of conversion.
http://userweb.kernel.org/~tj/misc/slabh-sweep.py
The script does the followings.
* Scan files for gfp and slab usages and update includes such that
only the necessary includes are there. ie. if only gfp is used,
gfp.h, if slab is used, slab.h.
* When the script inserts a new include, it looks at the include
blocks and try to put the new include such that its order conforms
to its surrounding. It's put in the include block which contains
core kernel includes, in the same order that the rest are ordered -
alphabetical, Christmas tree, rev-Xmas-tree or at the end if there
doesn't seem to be any matching order.
* If the script can't find a place to put a new include (mostly
because the file doesn't have fitting include block), it prints out
an error message indicating which .h file needs to be added to the
file.
The conversion was done in the following steps.
1. The initial automatic conversion of all .c files updated slightly
over 4000 files, deleting around 700 includes and adding ~480 gfp.h
and ~3000 slab.h inclusions. The script emitted errors for ~400
files.
2. Each error was manually checked. Some didn't need the inclusion,
some needed manual addition while adding it to implementation .h or
embedding .c file was more appropriate for others. This step added
inclusions to around 150 files.
3. The script was run again and the output was compared to the edits
from #2 to make sure no file was left behind.
4. Several build tests were done and a couple of problems were fixed.
e.g. lib/decompress_*.c used malloc/free() wrappers around slab
APIs requiring slab.h to be added manually.
5. The script was run on all .h files but without automatically
editing them as sprinkling gfp.h and slab.h inclusions around .h
files could easily lead to inclusion dependency hell. Most gfp.h
inclusion directives were ignored as stuff from gfp.h was usually
wildly available and often used in preprocessor macros. Each
slab.h inclusion directive was examined and added manually as
necessary.
6. percpu.h was updated not to include slab.h.
7. Build test were done on the following configurations and failures
were fixed. CONFIG_GCOV_KERNEL was turned off for all tests (as my
distributed build env didn't work with gcov compiles) and a few
more options had to be turned off depending on archs to make things
build (like ipr on powerpc/64 which failed due to missing writeq).
* x86 and x86_64 UP and SMP allmodconfig and a custom test config.
* powerpc and powerpc64 SMP allmodconfig
* sparc and sparc64 SMP allmodconfig
* ia64 SMP allmodconfig
* s390 SMP allmodconfig
* alpha SMP allmodconfig
* um on x86_64 SMP allmodconfig
8. percpu.h modifications were reverted so that it could be applied as
a separate patch and serve as bisection point.
Given the fact that I had only a couple of failures from tests on step
6, I'm fairly confident about the coverage of this conversion patch.
If there is a breakage, it's likely to be something in one of the arch
headers which should be easily discoverable easily on most builds of
the specific arch.
Signed-off-by: Tejun Heo <tj@kernel.org>
Guess-its-ok-by: Christoph Lameter <cl@linux-foundation.org>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
2010-03-24 16:04:11 +08:00
|
|
|
#include <linux/slab.h>
|
2008-09-13 07:29:34 +08:00
|
|
|
#include <linux/types.h>
|
|
|
|
#include <linux/kernel.h>
|
|
|
|
#include <linux/string.h>
|
|
|
|
#include <linux/errno.h>
|
|
|
|
#include <linux/skbuff.h>
|
|
|
|
#include <net/netlink.h>
|
|
|
|
#include <net/pkt_sched.h>
|
2017-02-09 21:38:56 +08:00
|
|
|
#include <net/pkt_cls.h>
|
2008-09-13 07:29:34 +08:00
|
|
|
|
|
|
|
struct multiq_sched_data {
|
|
|
|
u16 bands;
|
|
|
|
u16 max_bands;
|
|
|
|
u16 curband;
|
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;
|
2008-09-13 07:29:34 +08:00
|
|
|
struct Qdisc **queues;
|
|
|
|
};
|
|
|
|
|
|
|
|
|
|
|
|
static struct Qdisc *
|
|
|
|
multiq_classify(struct sk_buff *skb, struct Qdisc *sch, int *qerr)
|
|
|
|
{
|
|
|
|
struct multiq_sched_data *q = qdisc_priv(sch);
|
|
|
|
u32 band;
|
|
|
|
struct tcf_result res;
|
2014-09-13 11:05:27 +08:00
|
|
|
struct tcf_proto *fl = rcu_dereference_bh(q->filter_list);
|
2008-09-13 07:29:34 +08:00
|
|
|
int err;
|
|
|
|
|
|
|
|
*qerr = NET_XMIT_SUCCESS | __NET_XMIT_BYPASS;
|
2021-07-29 02:08:00 +08:00
|
|
|
err = tcf_classify(skb, NULL, fl, &res, false);
|
2008-09-13 07:29:34 +08:00
|
|
|
#ifdef CONFIG_NET_CLS_ACT
|
|
|
|
switch (err) {
|
|
|
|
case TC_ACT_STOLEN:
|
|
|
|
case TC_ACT_QUEUED:
|
2017-06-06 20:12:02 +08:00
|
|
|
case TC_ACT_TRAP:
|
2008-09-13 07:29:34 +08:00
|
|
|
*qerr = NET_XMIT_SUCCESS | __NET_XMIT_STOLEN;
|
2020-07-08 01:21:38 +08:00
|
|
|
fallthrough;
|
2008-09-13 07:29:34 +08:00
|
|
|
case TC_ACT_SHOT:
|
|
|
|
return NULL;
|
|
|
|
}
|
|
|
|
#endif
|
|
|
|
band = skb_get_queue_mapping(skb);
|
|
|
|
|
|
|
|
if (band >= q->bands)
|
|
|
|
return q->queues[0];
|
|
|
|
|
|
|
|
return q->queues[band];
|
|
|
|
}
|
|
|
|
|
|
|
|
static int
|
2020-07-15 01:03:08 +08:00
|
|
|
multiq_enqueue(struct sk_buff *skb, struct Qdisc *sch,
|
2016-06-22 14:16:49 +08:00
|
|
|
struct sk_buff **to_free)
|
2008-09-13 07:29:34 +08:00
|
|
|
{
|
|
|
|
struct Qdisc *qdisc;
|
|
|
|
int ret;
|
|
|
|
|
|
|
|
qdisc = multiq_classify(skb, sch, &ret);
|
|
|
|
#ifdef CONFIG_NET_CLS_ACT
|
|
|
|
if (qdisc == NULL) {
|
|
|
|
|
|
|
|
if (ret & __NET_XMIT_BYPASS)
|
2014-09-29 02:53:29 +08:00
|
|
|
qdisc_qstats_drop(sch);
|
2016-06-22 14:16:49 +08:00
|
|
|
__qdisc_drop(skb, to_free);
|
2008-09-13 07:29:34 +08:00
|
|
|
return ret;
|
|
|
|
}
|
|
|
|
#endif
|
|
|
|
|
2020-07-15 01:03:08 +08:00
|
|
|
ret = qdisc_enqueue(skb, qdisc, to_free);
|
2008-09-13 07:29:34 +08:00
|
|
|
if (ret == NET_XMIT_SUCCESS) {
|
|
|
|
sch->q.qlen++;
|
|
|
|
return NET_XMIT_SUCCESS;
|
|
|
|
}
|
|
|
|
if (net_xmit_drop_count(ret))
|
2014-09-29 02:53:29 +08:00
|
|
|
qdisc_qstats_drop(sch);
|
2008-09-13 07:29:34 +08:00
|
|
|
return ret;
|
|
|
|
}
|
|
|
|
|
|
|
|
static struct sk_buff *multiq_dequeue(struct Qdisc *sch)
|
|
|
|
{
|
|
|
|
struct multiq_sched_data *q = qdisc_priv(sch);
|
|
|
|
struct Qdisc *qdisc;
|
|
|
|
struct sk_buff *skb;
|
|
|
|
int band;
|
|
|
|
|
|
|
|
for (band = 0; band < q->bands; band++) {
|
|
|
|
/* cycle through bands to ensure fairness */
|
|
|
|
q->curband++;
|
|
|
|
if (q->curband >= q->bands)
|
|
|
|
q->curband = 0;
|
|
|
|
|
|
|
|
/* Check that target subqueue is available before
|
2008-11-14 14:56:30 +08:00
|
|
|
* pulling an skb to avoid head-of-line blocking.
|
2008-09-13 07:29:34 +08:00
|
|
|
*/
|
2011-11-29 00:32:44 +08:00
|
|
|
if (!netif_xmit_stopped(
|
|
|
|
netdev_get_tx_queue(qdisc_dev(sch), q->curband))) {
|
2008-09-13 07:29:34 +08:00
|
|
|
qdisc = q->queues[q->curband];
|
|
|
|
skb = qdisc->dequeue(qdisc);
|
|
|
|
if (skb) {
|
2011-01-21 15:31:33 +08:00
|
|
|
qdisc_bstats_update(sch, skb);
|
2008-09-13 07:29:34 +08:00
|
|
|
sch->q.qlen--;
|
|
|
|
return skb;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
}
|
|
|
|
return NULL;
|
|
|
|
|
|
|
|
}
|
|
|
|
|
2008-10-31 15:45:55 +08:00
|
|
|
static struct sk_buff *multiq_peek(struct Qdisc *sch)
|
|
|
|
{
|
|
|
|
struct multiq_sched_data *q = qdisc_priv(sch);
|
|
|
|
unsigned int curband = q->curband;
|
|
|
|
struct Qdisc *qdisc;
|
|
|
|
struct sk_buff *skb;
|
|
|
|
int band;
|
|
|
|
|
|
|
|
for (band = 0; band < q->bands; band++) {
|
|
|
|
/* cycle through bands to ensure fairness */
|
|
|
|
curband++;
|
|
|
|
if (curband >= q->bands)
|
|
|
|
curband = 0;
|
|
|
|
|
|
|
|
/* Check that target subqueue is available before
|
2008-11-14 14:56:30 +08:00
|
|
|
* pulling an skb to avoid head-of-line blocking.
|
2008-10-31 15:45:55 +08:00
|
|
|
*/
|
2011-11-29 00:32:44 +08:00
|
|
|
if (!netif_xmit_stopped(
|
|
|
|
netdev_get_tx_queue(qdisc_dev(sch), curband))) {
|
2008-10-31 15:45:55 +08:00
|
|
|
qdisc = q->queues[curband];
|
|
|
|
skb = qdisc->ops->peek(qdisc);
|
|
|
|
if (skb)
|
|
|
|
return skb;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
return NULL;
|
|
|
|
|
|
|
|
}
|
|
|
|
|
2008-09-13 07:29:34 +08:00
|
|
|
static void
|
|
|
|
multiq_reset(struct Qdisc *sch)
|
|
|
|
{
|
|
|
|
u16 band;
|
|
|
|
struct multiq_sched_data *q = qdisc_priv(sch);
|
|
|
|
|
|
|
|
for (band = 0; band < q->bands; band++)
|
|
|
|
qdisc_reset(q->queues[band]);
|
|
|
|
sch->q.qlen = 0;
|
|
|
|
q->curband = 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
static void
|
|
|
|
multiq_destroy(struct Qdisc *sch)
|
|
|
|
{
|
|
|
|
int band;
|
|
|
|
struct multiq_sched_data *q = qdisc_priv(sch);
|
|
|
|
|
2017-05-17 17:07:55 +08:00
|
|
|
tcf_block_put(q->block);
|
2008-09-13 07:29:34 +08:00
|
|
|
for (band = 0; band < q->bands; band++)
|
2018-09-25 00:22:50 +08:00
|
|
|
qdisc_put(q->queues[band]);
|
2008-09-13 07:29:34 +08:00
|
|
|
|
|
|
|
kfree(q->queues);
|
|
|
|
}
|
|
|
|
|
2017-12-21 01:35:14 +08:00
|
|
|
static int multiq_tune(struct Qdisc *sch, struct nlattr *opt,
|
|
|
|
struct netlink_ext_ack *extack)
|
2008-09-13 07:29:34 +08:00
|
|
|
{
|
|
|
|
struct multiq_sched_data *q = qdisc_priv(sch);
|
|
|
|
struct tc_multiq_qopt *qopt;
|
2019-09-24 23:51:17 +08:00
|
|
|
struct Qdisc **removed;
|
|
|
|
int i, n_removed = 0;
|
2008-09-13 07:29:34 +08:00
|
|
|
|
|
|
|
if (!netif_is_multiqueue(qdisc_dev(sch)))
|
2009-02-10 16:11:21 +08:00
|
|
|
return -EOPNOTSUPP;
|
2008-09-13 07:29:34 +08:00
|
|
|
if (nla_len(opt) < sizeof(*qopt))
|
|
|
|
return -EINVAL;
|
|
|
|
|
|
|
|
qopt = nla_data(opt);
|
|
|
|
|
|
|
|
qopt->bands = qdisc_dev(sch)->real_num_tx_queues;
|
|
|
|
|
2019-09-24 23:51:17 +08:00
|
|
|
removed = kmalloc(sizeof(*removed) * (q->max_bands - q->bands),
|
|
|
|
GFP_KERNEL);
|
|
|
|
if (!removed)
|
|
|
|
return -ENOMEM;
|
|
|
|
|
2008-09-13 07:29:34 +08:00
|
|
|
sch_tree_lock(sch);
|
|
|
|
q->bands = qopt->bands;
|
|
|
|
for (i = q->bands; i < q->max_bands; i++) {
|
2008-09-13 08:57:23 +08:00
|
|
|
if (q->queues[i] != &noop_qdisc) {
|
2008-11-20 20:11:36 +08:00
|
|
|
struct Qdisc *child = q->queues[i];
|
2019-03-28 23:53:13 +08:00
|
|
|
|
2008-11-20 20:11:36 +08:00
|
|
|
q->queues[i] = &noop_qdisc;
|
2019-09-24 23:51:17 +08:00
|
|
|
qdisc_purge_queue(child);
|
|
|
|
removed[n_removed++] = child;
|
2008-09-13 07:29:34 +08:00
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
sch_tree_unlock(sch);
|
|
|
|
|
2019-09-24 23:51:17 +08:00
|
|
|
for (i = 0; i < n_removed; i++)
|
|
|
|
qdisc_put(removed[i]);
|
|
|
|
kfree(removed);
|
|
|
|
|
2008-09-13 07:29:34 +08:00
|
|
|
for (i = 0; i < q->bands; i++) {
|
|
|
|
if (q->queues[i] == &noop_qdisc) {
|
2008-11-20 20:11:36 +08:00
|
|
|
struct Qdisc *child, *old;
|
2010-10-16 21:04:08 +08:00
|
|
|
child = qdisc_create_dflt(sch->dev_queue,
|
2008-09-13 07:29:34 +08:00
|
|
|
&pfifo_qdisc_ops,
|
|
|
|
TC_H_MAKE(sch->handle,
|
2017-12-21 01:35:21 +08:00
|
|
|
i + 1), extack);
|
2008-09-13 07:29:34 +08:00
|
|
|
if (child) {
|
|
|
|
sch_tree_lock(sch);
|
2008-11-20 20:11:36 +08:00
|
|
|
old = q->queues[i];
|
|
|
|
q->queues[i] = child;
|
2017-03-08 23:03:32 +08:00
|
|
|
if (child != &noop_qdisc)
|
|
|
|
qdisc_hash_add(child, true);
|
2008-09-13 07:29:34 +08:00
|
|
|
|
2019-09-24 23:51:17 +08:00
|
|
|
if (old != &noop_qdisc)
|
|
|
|
qdisc_purge_queue(old);
|
2008-09-13 07:29:34 +08:00
|
|
|
sch_tree_unlock(sch);
|
2019-09-24 23:51:17 +08:00
|
|
|
qdisc_put(old);
|
2008-09-13 07:29:34 +08:00
|
|
|
}
|
|
|
|
}
|
|
|
|
}
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
2017-12-21 01:35:13 +08:00
|
|
|
static int multiq_init(struct Qdisc *sch, struct nlattr *opt,
|
|
|
|
struct netlink_ext_ack *extack)
|
2008-09-13 07:29:34 +08:00
|
|
|
{
|
|
|
|
struct multiq_sched_data *q = qdisc_priv(sch);
|
2008-09-13 08:57:23 +08:00
|
|
|
int i, err;
|
2008-09-13 07:29:34 +08:00
|
|
|
|
|
|
|
q->queues = NULL;
|
|
|
|
|
2017-12-21 01:35:11 +08:00
|
|
|
if (!opt)
|
2008-09-13 07:29:34 +08:00
|
|
|
return -EINVAL;
|
|
|
|
|
2017-12-21 01:35:19 +08:00
|
|
|
err = tcf_block_get(&q->block, &q->filter_list, sch, extack);
|
2017-05-17 17:07:55 +08:00
|
|
|
if (err)
|
|
|
|
return err;
|
|
|
|
|
2008-09-13 07:29:34 +08:00
|
|
|
q->max_bands = qdisc_dev(sch)->num_tx_queues;
|
|
|
|
|
|
|
|
q->queues = kcalloc(q->max_bands, sizeof(struct Qdisc *), GFP_KERNEL);
|
|
|
|
if (!q->queues)
|
|
|
|
return -ENOBUFS;
|
|
|
|
for (i = 0; i < q->max_bands; i++)
|
|
|
|
q->queues[i] = &noop_qdisc;
|
|
|
|
|
2017-12-21 01:35:14 +08:00
|
|
|
return multiq_tune(sch, opt, extack);
|
2008-09-13 07:29:34 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
static int multiq_dump(struct Qdisc *sch, struct sk_buff *skb)
|
|
|
|
{
|
|
|
|
struct multiq_sched_data *q = qdisc_priv(sch);
|
|
|
|
unsigned char *b = skb_tail_pointer(skb);
|
|
|
|
struct tc_multiq_qopt opt;
|
|
|
|
|
|
|
|
opt.bands = q->bands;
|
|
|
|
opt.max_bands = q->max_bands;
|
|
|
|
|
2012-03-29 17:11:39 +08:00
|
|
|
if (nla_put(skb, TCA_OPTIONS, sizeof(opt), &opt))
|
|
|
|
goto nla_put_failure;
|
2008-09-13 07:29:34 +08:00
|
|
|
|
|
|
|
return skb->len;
|
|
|
|
|
|
|
|
nla_put_failure:
|
|
|
|
nlmsg_trim(skb, b);
|
|
|
|
return -1;
|
|
|
|
}
|
|
|
|
|
|
|
|
static int multiq_graft(struct Qdisc *sch, unsigned long arg, struct Qdisc *new,
|
2017-12-21 01:35:17 +08:00
|
|
|
struct Qdisc **old, struct netlink_ext_ack *extack)
|
2008-09-13 07:29:34 +08:00
|
|
|
{
|
|
|
|
struct multiq_sched_data *q = qdisc_priv(sch);
|
|
|
|
unsigned long band = arg - 1;
|
|
|
|
|
|
|
|
if (new == NULL)
|
|
|
|
new = &noop_qdisc;
|
|
|
|
|
2016-02-26 06:55:00 +08:00
|
|
|
*old = qdisc_replace(sch, new, &q->queues[band]);
|
2008-09-13 07:29:34 +08:00
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
static struct Qdisc *
|
|
|
|
multiq_leaf(struct Qdisc *sch, unsigned long arg)
|
|
|
|
{
|
|
|
|
struct multiq_sched_data *q = qdisc_priv(sch);
|
|
|
|
unsigned long band = arg - 1;
|
|
|
|
|
|
|
|
return q->queues[band];
|
|
|
|
}
|
|
|
|
|
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 multiq_find(struct Qdisc *sch, u32 classid)
|
2008-09-13 07:29:34 +08:00
|
|
|
{
|
|
|
|
struct multiq_sched_data *q = qdisc_priv(sch);
|
|
|
|
unsigned long band = TC_H_MIN(classid);
|
|
|
|
|
|
|
|
if (band - 1 >= q->bands)
|
|
|
|
return 0;
|
|
|
|
return band;
|
|
|
|
}
|
|
|
|
|
|
|
|
static unsigned long multiq_bind(struct Qdisc *sch, unsigned long parent,
|
|
|
|
u32 classid)
|
|
|
|
{
|
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
|
|
|
return multiq_find(sch, classid);
|
2008-09-13 07:29:34 +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 multiq_unbind(struct Qdisc *q, unsigned long cl)
|
2008-09-13 07:29:34 +08:00
|
|
|
{
|
|
|
|
}
|
|
|
|
|
|
|
|
static int multiq_dump_class(struct Qdisc *sch, unsigned long cl,
|
|
|
|
struct sk_buff *skb, struct tcmsg *tcm)
|
|
|
|
{
|
|
|
|
struct multiq_sched_data *q = qdisc_priv(sch);
|
|
|
|
|
|
|
|
tcm->tcm_handle |= TC_H_MIN(cl);
|
2011-01-20 03:26:56 +08:00
|
|
|
tcm->tcm_info = q->queues[cl - 1]->handle;
|
2008-09-13 07:29:34 +08:00
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
static int multiq_dump_class_stats(struct Qdisc *sch, unsigned long cl,
|
|
|
|
struct gnet_dump *d)
|
|
|
|
{
|
|
|
|
struct multiq_sched_data *q = qdisc_priv(sch);
|
|
|
|
struct Qdisc *cl_q;
|
|
|
|
|
|
|
|
cl_q = q->queues[cl - 1];
|
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
|
|
|
if (gnet_stats_copy_basic(d, cl_q->cpu_bstats, &cl_q->bstats, true) < 0 ||
|
2019-03-28 23:53:12 +08:00
|
|
|
qdisc_qstats_copy(d, cl_q) < 0)
|
2008-09-13 07:29:34 +08:00
|
|
|
return -1;
|
|
|
|
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
static void multiq_walk(struct Qdisc *sch, struct qdisc_walker *arg)
|
|
|
|
{
|
|
|
|
struct multiq_sched_data *q = qdisc_priv(sch);
|
|
|
|
int band;
|
|
|
|
|
|
|
|
if (arg->stop)
|
|
|
|
return;
|
|
|
|
|
|
|
|
for (band = 0; band < q->bands; band++) {
|
|
|
|
if (arg->count < arg->skip) {
|
|
|
|
arg->count++;
|
|
|
|
continue;
|
|
|
|
}
|
2011-01-20 03:26:56 +08:00
|
|
|
if (arg->fn(sch, band + 1, arg) < 0) {
|
2008-09-13 07:29:34 +08:00
|
|
|
arg->stop = 1;
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
arg->count++;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2017-12-21 01:35:16 +08:00
|
|
|
static struct tcf_block *multiq_tcf_block(struct Qdisc *sch, unsigned long cl,
|
|
|
|
struct netlink_ext_ack *extack)
|
2008-09-13 07:29:34 +08:00
|
|
|
{
|
|
|
|
struct multiq_sched_data *q = qdisc_priv(sch);
|
|
|
|
|
|
|
|
if (cl)
|
|
|
|
return NULL;
|
2017-05-17 17:07:55 +08:00
|
|
|
return q->block;
|
2008-09-13 07:29:34 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
static const struct Qdisc_class_ops multiq_class_ops = {
|
|
|
|
.graft = multiq_graft,
|
|
|
|
.leaf = multiq_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 = multiq_find,
|
2008-09-13 07:29:34 +08:00
|
|
|
.walk = multiq_walk,
|
2017-05-17 17:07:55 +08:00
|
|
|
.tcf_block = multiq_tcf_block,
|
2008-09-13 07:29:34 +08:00
|
|
|
.bind_tcf = multiq_bind,
|
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 = multiq_unbind,
|
2008-09-13 07:29:34 +08:00
|
|
|
.dump = multiq_dump_class,
|
|
|
|
.dump_stats = multiq_dump_class_stats,
|
|
|
|
};
|
|
|
|
|
|
|
|
static struct Qdisc_ops multiq_qdisc_ops __read_mostly = {
|
|
|
|
.next = NULL,
|
|
|
|
.cl_ops = &multiq_class_ops,
|
|
|
|
.id = "multiq",
|
|
|
|
.priv_size = sizeof(struct multiq_sched_data),
|
|
|
|
.enqueue = multiq_enqueue,
|
|
|
|
.dequeue = multiq_dequeue,
|
2008-10-31 15:45:55 +08:00
|
|
|
.peek = multiq_peek,
|
2008-09-13 07:29:34 +08:00
|
|
|
.init = multiq_init,
|
|
|
|
.reset = multiq_reset,
|
|
|
|
.destroy = multiq_destroy,
|
|
|
|
.change = multiq_tune,
|
|
|
|
.dump = multiq_dump,
|
|
|
|
.owner = THIS_MODULE,
|
|
|
|
};
|
|
|
|
|
|
|
|
static int __init multiq_module_init(void)
|
|
|
|
{
|
|
|
|
return register_qdisc(&multiq_qdisc_ops);
|
|
|
|
}
|
|
|
|
|
|
|
|
static void __exit multiq_module_exit(void)
|
|
|
|
{
|
|
|
|
unregister_qdisc(&multiq_qdisc_ops);
|
|
|
|
}
|
|
|
|
|
|
|
|
module_init(multiq_module_init)
|
|
|
|
module_exit(multiq_module_exit)
|
|
|
|
|
|
|
|
MODULE_LICENSE("GPL");
|