linux/net/sched/sch_drr.c

530 lines
11 KiB
C
Raw Normal View History

/*
* net/sched/sch_drr.c Deficit Round Robin scheduler
*
* Copyright (c) 2008 Patrick McHardy <kaber@trash.net>
*
* This program is free software; you can redistribute it and/or
* modify it under the terms of the GNU General Public License
* version 2 as published by the Free Software Foundation.
*/
#include <linux/module.h>
include cleanup: Update gfp.h and slab.h includes to prepare for breaking implicit slab.h inclusion from percpu.h percpu.h is included by sched.h and module.h and thus ends up being included when building most .c files. percpu.h includes slab.h which in turn includes gfp.h making everything defined by the two files universally available and complicating inclusion dependencies. percpu.h -> slab.h dependency is about to be removed. Prepare for this change by updating users of gfp and slab facilities include those headers directly instead of assuming availability. As this conversion needs to touch large number of source files, the following script is used as the basis of conversion. http://userweb.kernel.org/~tj/misc/slabh-sweep.py The script does the followings. * Scan files for gfp and slab usages and update includes such that only the necessary includes are there. ie. if only gfp is used, gfp.h, if slab is used, slab.h. * When the script inserts a new include, it looks at the include blocks and try to put the new include such that its order conforms to its surrounding. It's put in the include block which contains core kernel includes, in the same order that the rest are ordered - alphabetical, Christmas tree, rev-Xmas-tree or at the end if there doesn't seem to be any matching order. * If the script can't find a place to put a new include (mostly because the file doesn't have fitting include block), it prints out an error message indicating which .h file needs to be added to the file. The conversion was done in the following steps. 1. The initial automatic conversion of all .c files updated slightly over 4000 files, deleting around 700 includes and adding ~480 gfp.h and ~3000 slab.h inclusions. The script emitted errors for ~400 files. 2. Each error was manually checked. Some didn't need the inclusion, some needed manual addition while adding it to implementation .h or embedding .c file was more appropriate for others. This step added inclusions to around 150 files. 3. The script was run again and the output was compared to the edits from #2 to make sure no file was left behind. 4. Several build tests were done and a couple of problems were fixed. e.g. lib/decompress_*.c used malloc/free() wrappers around slab APIs requiring slab.h to be added manually. 5. The script was run on all .h files but without automatically editing them as sprinkling gfp.h and slab.h inclusions around .h files could easily lead to inclusion dependency hell. Most gfp.h inclusion directives were ignored as stuff from gfp.h was usually wildly available and often used in preprocessor macros. Each slab.h inclusion directive was examined and added manually as necessary. 6. percpu.h was updated not to include slab.h. 7. Build test were done on the following configurations and failures were fixed. CONFIG_GCOV_KERNEL was turned off for all tests (as my distributed build env didn't work with gcov compiles) and a few more options had to be turned off depending on archs to make things build (like ipr on powerpc/64 which failed due to missing writeq). * x86 and x86_64 UP and SMP allmodconfig and a custom test config. * powerpc and powerpc64 SMP allmodconfig * sparc and sparc64 SMP allmodconfig * ia64 SMP allmodconfig * s390 SMP allmodconfig * alpha SMP allmodconfig * um on x86_64 SMP allmodconfig 8. percpu.h modifications were reverted so that it could be applied as a separate patch and serve as bisection point. Given the fact that I had only a couple of failures from tests on step 6, I'm fairly confident about the coverage of this conversion patch. If there is a breakage, it's likely to be something in one of the arch headers which should be easily discoverable easily on most builds of the specific arch. Signed-off-by: Tejun Heo <tj@kernel.org> Guess-its-ok-by: Christoph Lameter <cl@linux-foundation.org> Cc: Ingo Molnar <mingo@redhat.com> Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
2010-03-24 16:04:11 +08:00
#include <linux/slab.h>
#include <linux/init.h>
#include <linux/errno.h>
#include <linux/netdevice.h>
#include <linux/pkt_sched.h>
#include <net/sch_generic.h>
#include <net/pkt_sched.h>
#include <net/pkt_cls.h>
struct drr_class {
struct Qdisc_class_common common;
unsigned int refcnt;
unsigned int filter_cnt;
struct gnet_stats_basic_packed bstats;
struct gnet_stats_queue qstats;
struct gnet_stats_rate_est rate_est;
struct list_head alist;
struct Qdisc *qdisc;
u32 quantum;
u32 deficit;
};
struct drr_sched {
struct list_head active;
struct tcf_proto *filter_list;
struct Qdisc_class_hash clhash;
};
static struct drr_class *drr_find_class(struct Qdisc *sch, u32 classid)
{
struct drr_sched *q = qdisc_priv(sch);
struct Qdisc_class_common *clc;
clc = qdisc_class_find(&q->clhash, classid);
if (clc == NULL)
return NULL;
return container_of(clc, struct drr_class, common);
}
static void drr_purge_queue(struct drr_class *cl)
{
unsigned int len = cl->qdisc->q.qlen;
qdisc_reset(cl->qdisc);
qdisc_tree_decrease_qlen(cl->qdisc, len);
}
static const struct nla_policy drr_policy[TCA_DRR_MAX + 1] = {
[TCA_DRR_QUANTUM] = { .type = NLA_U32 },
};
static int drr_change_class(struct Qdisc *sch, u32 classid, u32 parentid,
struct nlattr **tca, unsigned long *arg)
{
struct drr_sched *q = qdisc_priv(sch);
struct drr_class *cl = (struct drr_class *)*arg;
struct nlattr *opt = tca[TCA_OPTIONS];
struct nlattr *tb[TCA_DRR_MAX + 1];
u32 quantum;
int err;
if (!opt)
return -EINVAL;
err = nla_parse_nested(tb, TCA_DRR_MAX, opt, drr_policy);
if (err < 0)
return err;
if (tb[TCA_DRR_QUANTUM]) {
quantum = nla_get_u32(tb[TCA_DRR_QUANTUM]);
if (quantum == 0)
return -EINVAL;
} else
quantum = psched_mtu(qdisc_dev(sch));
if (cl != NULL) {
if (tca[TCA_RATE]) {
err = gen_replace_estimator(&cl->bstats, &cl->rate_est,
qdisc_root_sleeping_lock(sch),
tca[TCA_RATE]);
if (err)
return err;
}
sch_tree_lock(sch);
if (tb[TCA_DRR_QUANTUM])
cl->quantum = quantum;
sch_tree_unlock(sch);
return 0;
}
cl = kzalloc(sizeof(struct drr_class), GFP_KERNEL);
if (cl == NULL)
return -ENOBUFS;
cl->refcnt = 1;
cl->common.classid = classid;
cl->quantum = quantum;
cl->qdisc = qdisc_create_dflt(qdisc_dev(sch), sch->dev_queue,
&pfifo_qdisc_ops, classid);
if (cl->qdisc == NULL)
cl->qdisc = &noop_qdisc;
if (tca[TCA_RATE]) {
err = gen_replace_estimator(&cl->bstats, &cl->rate_est,
qdisc_root_sleeping_lock(sch),
tca[TCA_RATE]);
if (err) {
qdisc_destroy(cl->qdisc);
kfree(cl);
return err;
}
}
sch_tree_lock(sch);
qdisc_class_hash_insert(&q->clhash, &cl->common);
sch_tree_unlock(sch);
qdisc_class_hash_grow(sch, &q->clhash);
*arg = (unsigned long)cl;
return 0;
}
static void drr_destroy_class(struct Qdisc *sch, struct drr_class *cl)
{
gen_kill_estimator(&cl->bstats, &cl->rate_est);
qdisc_destroy(cl->qdisc);
kfree(cl);
}
static int drr_delete_class(struct Qdisc *sch, unsigned long arg)
{
struct drr_sched *q = qdisc_priv(sch);
struct drr_class *cl = (struct drr_class *)arg;
if (cl->filter_cnt > 0)
return -EBUSY;
sch_tree_lock(sch);
drr_purge_queue(cl);
qdisc_class_hash_remove(&q->clhash, &cl->common);
BUG_ON(--cl->refcnt == 0);
/*
* This shouldn't happen: we "hold" one cops->get() when called
* from tc_ctl_tclass; the destroy method is done from cops->put().
*/
sch_tree_unlock(sch);
return 0;
}
static unsigned long drr_get_class(struct Qdisc *sch, u32 classid)
{
struct drr_class *cl = drr_find_class(sch, classid);
if (cl != NULL)
cl->refcnt++;
return (unsigned long)cl;
}
static void drr_put_class(struct Qdisc *sch, unsigned long arg)
{
struct drr_class *cl = (struct drr_class *)arg;
if (--cl->refcnt == 0)
drr_destroy_class(sch, cl);
}
static struct tcf_proto **drr_tcf_chain(struct Qdisc *sch, unsigned long cl)
{
struct drr_sched *q = qdisc_priv(sch);
if (cl)
return NULL;
return &q->filter_list;
}
static unsigned long drr_bind_tcf(struct Qdisc *sch, unsigned long parent,
u32 classid)
{
struct drr_class *cl = drr_find_class(sch, classid);
if (cl != NULL)
cl->filter_cnt++;
return (unsigned long)cl;
}
static void drr_unbind_tcf(struct Qdisc *sch, unsigned long arg)
{
struct drr_class *cl = (struct drr_class *)arg;
cl->filter_cnt--;
}
static int drr_graft_class(struct Qdisc *sch, unsigned long arg,
struct Qdisc *new, struct Qdisc **old)
{
struct drr_class *cl = (struct drr_class *)arg;
if (new == NULL) {
new = qdisc_create_dflt(qdisc_dev(sch), sch->dev_queue,
&pfifo_qdisc_ops, cl->common.classid);
if (new == NULL)
new = &noop_qdisc;
}
sch_tree_lock(sch);
drr_purge_queue(cl);
*old = cl->qdisc;
cl->qdisc = new;
sch_tree_unlock(sch);
return 0;
}
static struct Qdisc *drr_class_leaf(struct Qdisc *sch, unsigned long arg)
{
struct drr_class *cl = (struct drr_class *)arg;
return cl->qdisc;
}
static void drr_qlen_notify(struct Qdisc *csh, unsigned long arg)
{
struct drr_class *cl = (struct drr_class *)arg;
if (cl->qdisc->q.qlen == 0)
list_del(&cl->alist);
}
static int drr_dump_class(struct Qdisc *sch, unsigned long arg,
struct sk_buff *skb, struct tcmsg *tcm)
{
struct drr_class *cl = (struct drr_class *)arg;
struct nlattr *nest;
tcm->tcm_parent = TC_H_ROOT;
tcm->tcm_handle = cl->common.classid;
tcm->tcm_info = cl->qdisc->handle;
nest = nla_nest_start(skb, TCA_OPTIONS);
if (nest == NULL)
goto nla_put_failure;
NLA_PUT_U32(skb, TCA_DRR_QUANTUM, cl->quantum);
return nla_nest_end(skb, nest);
nla_put_failure:
nla_nest_cancel(skb, nest);
return -EMSGSIZE;
}
static int drr_dump_class_stats(struct Qdisc *sch, unsigned long arg,
struct gnet_dump *d)
{
struct drr_class *cl = (struct drr_class *)arg;
struct tc_drr_stats xstats;
memset(&xstats, 0, sizeof(xstats));
if (cl->qdisc->q.qlen) {
xstats.deficit = cl->deficit;
cl->qdisc->qstats.qlen = cl->qdisc->q.qlen;
}
if (gnet_stats_copy_basic(d, &cl->bstats) < 0 ||
pkt_sched: gen_estimator: Dont report fake rate estimators Jarek Poplawski a écrit : > > > Hmm... So you made me to do some "real" work here, and guess what?: > there is one serious checkpatch warning! ;-) Plus, this new parameter > should be added to the function description. Otherwise: > Signed-off-by: Jarek Poplawski <jarkao2@gmail.com> > > Thanks, > Jarek P. > > PS: I guess full "Don't" would show we really mean it... Okay :) Here is the last round, before the night ! Thanks again [RFC] pkt_sched: gen_estimator: Don't report fake rate estimators We currently send TCA_STATS_RATE_EST elements to netlink users, even if no estimator is running. # tc -s -d qdisc qdisc pfifo_fast 0: dev eth0 root bands 3 priomap 1 2 2 2 1 2 0 0 1 1 1 1 1 1 1 1 Sent 112833764978 bytes 1495081739 pkt (dropped 0, overlimits 0 requeues 0) rate 0bit 0pps backlog 0b 0p requeues 0 User has no way to tell if the "rate 0bit 0pps" is a real estimation, or a fake one (because no estimator is active) After this patch, tc command output is : $ tc -s -d qdisc qdisc pfifo_fast 0: dev eth0 root bands 3 priomap 1 2 2 2 1 2 0 0 1 1 1 1 1 1 1 1 Sent 561075 bytes 1196 pkt (dropped 0, overlimits 0 requeues 0) backlog 0b 0p requeues 0 We add a parameter to gnet_stats_copy_rate_est() function so that it can use gen_estimator_active(bstats, r), as suggested by Jarek. This parameter can be NULL if check is not necessary, (htb for example has a mandatory rate estimator) Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com> Signed-off-by: Jarek Poplawski <jarkao2@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2009-10-02 18:32:18 +08:00
gnet_stats_copy_rate_est(d, &cl->bstats, &cl->rate_est) < 0 ||
gnet_stats_copy_queue(d, &cl->qdisc->qstats) < 0)
return -1;
return gnet_stats_copy_app(d, &xstats, sizeof(xstats));
}
static void drr_walk(struct Qdisc *sch, struct qdisc_walker *arg)
{
struct drr_sched *q = qdisc_priv(sch);
struct drr_class *cl;
struct hlist_node *n;
unsigned int i;
if (arg->stop)
return;
for (i = 0; i < q->clhash.hashsize; i++) {
hlist_for_each_entry(cl, n, &q->clhash.hash[i], common.hnode) {
if (arg->count < arg->skip) {
arg->count++;
continue;
}
if (arg->fn(sch, (unsigned long)cl, arg) < 0) {
arg->stop = 1;
return;
}
arg->count++;
}
}
}
static struct drr_class *drr_classify(struct sk_buff *skb, struct Qdisc *sch,
int *qerr)
{
struct drr_sched *q = qdisc_priv(sch);
struct drr_class *cl;
struct tcf_result res;
int result;
if (TC_H_MAJ(skb->priority ^ sch->handle) == 0) {
cl = drr_find_class(sch, skb->priority);
if (cl != NULL)
return cl;
}
*qerr = NET_XMIT_SUCCESS | __NET_XMIT_BYPASS;
result = tc_classify(skb, q->filter_list, &res);
if (result >= 0) {
#ifdef CONFIG_NET_CLS_ACT
switch (result) {
case TC_ACT_QUEUED:
case TC_ACT_STOLEN:
*qerr = NET_XMIT_SUCCESS | __NET_XMIT_STOLEN;
case TC_ACT_SHOT:
return NULL;
}
#endif
cl = (struct drr_class *)res.class;
if (cl == NULL)
cl = drr_find_class(sch, res.classid);
return cl;
}
return NULL;
}
static int drr_enqueue(struct sk_buff *skb, struct Qdisc *sch)
{
struct drr_sched *q = qdisc_priv(sch);
struct drr_class *cl;
unsigned int len;
int err;
cl = drr_classify(skb, sch, &err);
if (cl == NULL) {
if (err & __NET_XMIT_BYPASS)
sch->qstats.drops++;
kfree_skb(skb);
return err;
}
len = qdisc_pkt_len(skb);
err = qdisc_enqueue(skb, cl->qdisc);
if (unlikely(err != NET_XMIT_SUCCESS)) {
if (net_xmit_drop_count(err)) {
cl->qstats.drops++;
sch->qstats.drops++;
}
return err;
}
if (cl->qdisc->q.qlen == 1) {
list_add_tail(&cl->alist, &q->active);
cl->deficit = cl->quantum;
}
cl->bstats.packets++;
cl->bstats.bytes += len;
sch->bstats.packets++;
sch->bstats.bytes += len;
sch->q.qlen++;
return err;
}
static struct sk_buff *drr_dequeue(struct Qdisc *sch)
{
struct drr_sched *q = qdisc_priv(sch);
struct drr_class *cl;
struct sk_buff *skb;
unsigned int len;
if (list_empty(&q->active))
goto out;
while (1) {
cl = list_first_entry(&q->active, struct drr_class, alist);
skb = cl->qdisc->ops->peek(cl->qdisc);
if (skb == NULL)
goto out;
len = qdisc_pkt_len(skb);
if (len <= cl->deficit) {
cl->deficit -= len;
skb = qdisc_dequeue_peeked(cl->qdisc);
if (cl->qdisc->q.qlen == 0)
list_del(&cl->alist);
sch->q.qlen--;
return skb;
}
cl->deficit += cl->quantum;
list_move_tail(&cl->alist, &q->active);
}
out:
return NULL;
}
static unsigned int drr_drop(struct Qdisc *sch)
{
struct drr_sched *q = qdisc_priv(sch);
struct drr_class *cl;
unsigned int len;
list_for_each_entry(cl, &q->active, alist) {
if (cl->qdisc->ops->drop) {
len = cl->qdisc->ops->drop(cl->qdisc);
if (len > 0) {
sch->q.qlen--;
if (cl->qdisc->q.qlen == 0)
list_del(&cl->alist);
return len;
}
}
}
return 0;
}
static int drr_init_qdisc(struct Qdisc *sch, struct nlattr *opt)
{
struct drr_sched *q = qdisc_priv(sch);
int err;
err = qdisc_class_hash_init(&q->clhash);
if (err < 0)
return err;
INIT_LIST_HEAD(&q->active);
return 0;
}
static void drr_reset_qdisc(struct Qdisc *sch)
{
struct drr_sched *q = qdisc_priv(sch);
struct drr_class *cl;
struct hlist_node *n;
unsigned int i;
for (i = 0; i < q->clhash.hashsize; i++) {
hlist_for_each_entry(cl, n, &q->clhash.hash[i], common.hnode) {
if (cl->qdisc->q.qlen)
list_del(&cl->alist);
qdisc_reset(cl->qdisc);
}
}
sch->q.qlen = 0;
}
static void drr_destroy_qdisc(struct Qdisc *sch)
{
struct drr_sched *q = qdisc_priv(sch);
struct drr_class *cl;
struct hlist_node *n, *next;
unsigned int i;
tcf_destroy_chain(&q->filter_list);
for (i = 0; i < q->clhash.hashsize; i++) {
hlist_for_each_entry_safe(cl, n, next, &q->clhash.hash[i],
common.hnode)
drr_destroy_class(sch, cl);
}
qdisc_class_hash_destroy(&q->clhash);
}
static const struct Qdisc_class_ops drr_class_ops = {
.change = drr_change_class,
.delete = drr_delete_class,
.get = drr_get_class,
.put = drr_put_class,
.tcf_chain = drr_tcf_chain,
.bind_tcf = drr_bind_tcf,
.unbind_tcf = drr_unbind_tcf,
.graft = drr_graft_class,
.leaf = drr_class_leaf,
.qlen_notify = drr_qlen_notify,
.dump = drr_dump_class,
.dump_stats = drr_dump_class_stats,
.walk = drr_walk,
};
static struct Qdisc_ops drr_qdisc_ops __read_mostly = {
.cl_ops = &drr_class_ops,
.id = "drr",
.priv_size = sizeof(struct drr_sched),
.enqueue = drr_enqueue,
.dequeue = drr_dequeue,
.peek = qdisc_peek_dequeued,
.drop = drr_drop,
.init = drr_init_qdisc,
.reset = drr_reset_qdisc,
.destroy = drr_destroy_qdisc,
.owner = THIS_MODULE,
};
static int __init drr_init(void)
{
return register_qdisc(&drr_qdisc_ops);
}
static void __exit drr_exit(void)
{
unregister_qdisc(&drr_qdisc_ops);
}
module_init(drr_init);
module_exit(drr_exit);
MODULE_LICENSE("GPL");