linux_dsm_epyc7002/net/sched/sch_prio.c

400 lines
8.3 KiB
C
Raw Normal View History

/*
* net/sched/sch_prio.c Simple 3-band priority "scheduler".
*
* This program is free software; you can redistribute it and/or
* modify it under the terms of the GNU General Public License
* as published by the Free Software Foundation; either version
* 2 of the License, or (at your option) any later version.
*
* Authors: Alexey Kuznetsov, <kuznet@ms2.inr.ac.ru>
* Fixes: 19990609: J Hadi Salim <hadi@nortelnetworks.com>:
* Init -- EINVAL when opt undefined
*/
#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 15:04:11 +07:00
#include <linux/slab.h>
#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>
struct prio_sched_data {
int bands;
struct tcf_proto __rcu *filter_list;
u8 prio2band[TC_PRIO_MAX+1];
struct Qdisc *queues[TCQ_PRIO_BANDS];
};
static struct Qdisc *
prio_classify(struct sk_buff *skb, struct Qdisc *sch, int *qerr)
{
struct prio_sched_data *q = qdisc_priv(sch);
u32 band = skb->priority;
struct tcf_result res;
struct tcf_proto *fl;
int err;
*qerr = NET_XMIT_SUCCESS | __NET_XMIT_BYPASS;
if (TC_H_MAJ(skb->priority) != sch->handle) {
fl = rcu_dereference_bh(q->filter_list);
err = tc_classify(skb, fl, &res, false);
#ifdef CONFIG_NET_CLS_ACT
switch (err) {
case TC_ACT_STOLEN:
case TC_ACT_QUEUED:
*qerr = NET_XMIT_SUCCESS | __NET_XMIT_STOLEN;
case TC_ACT_SHOT:
return NULL;
}
#endif
if (!fl || err < 0) {
if (TC_H_MAJ(band))
band = 0;
return q->queues[q->prio2band[band & TC_PRIO_MAX]];
}
band = res.classid;
}
band = TC_H_MIN(band) - 1;
if (band >= q->bands)
return q->queues[q->prio2band[0]];
return q->queues[band];
}
static int
prio_enqueue(struct sk_buff *skb, struct Qdisc *sch)
{
struct Qdisc *qdisc;
int ret;
qdisc = prio_classify(skb, sch, &ret);
#ifdef CONFIG_NET_CLS_ACT
if (qdisc == NULL) {
if (ret & __NET_XMIT_BYPASS)
qdisc_qstats_drop(sch);
kfree_skb(skb);
return ret;
}
#endif
ret = qdisc_enqueue(skb, qdisc);
if (ret == NET_XMIT_SUCCESS) {
qdisc_qstats_backlog_inc(sch, skb);
sch->q.qlen++;
return NET_XMIT_SUCCESS;
}
if (net_xmit_drop_count(ret))
qdisc_qstats_drop(sch);
return ret;
}
static struct sk_buff *prio_peek(struct Qdisc *sch)
{
struct prio_sched_data *q = qdisc_priv(sch);
int prio;
for (prio = 0; prio < q->bands; prio++) {
struct Qdisc *qdisc = q->queues[prio];
struct sk_buff *skb = qdisc->ops->peek(qdisc);
if (skb)
return skb;
}
return NULL;
}
static struct sk_buff *prio_dequeue(struct Qdisc *sch)
{
struct prio_sched_data *q = qdisc_priv(sch);
int prio;
for (prio = 0; prio < q->bands; prio++) {
struct Qdisc *qdisc = q->queues[prio];
struct sk_buff *skb = qdisc_dequeue_peeked(qdisc);
if (skb) {
qdisc_bstats_update(sch, skb);
qdisc_qstats_backlog_dec(sch, skb);
sch->q.qlen--;
return skb;
}
}
return NULL;
}
static unsigned int prio_drop(struct Qdisc *sch)
{
struct prio_sched_data *q = qdisc_priv(sch);
int prio;
unsigned int len;
struct Qdisc *qdisc;
for (prio = q->bands-1; prio >= 0; prio--) {
qdisc = q->queues[prio];
if (qdisc->ops->drop && (len = qdisc->ops->drop(qdisc)) != 0) {
sch->qstats.backlog -= len;
sch->q.qlen--;
return len;
}
}
return 0;
}
static void
prio_reset(struct Qdisc *sch)
{
int prio;
struct prio_sched_data *q = qdisc_priv(sch);
for (prio = 0; prio < q->bands; prio++)
qdisc_reset(q->queues[prio]);
sch->qstats.backlog = 0;
sch->q.qlen = 0;
}
static void
prio_destroy(struct Qdisc *sch)
{
int prio;
struct prio_sched_data *q = qdisc_priv(sch);
tcf_destroy_chain(&q->filter_list);
for (prio = 0; prio < q->bands; prio++)
qdisc_destroy(q->queues[prio]);
}
static int prio_tune(struct Qdisc *sch, struct nlattr *opt)
{
struct prio_sched_data *q = qdisc_priv(sch);
struct tc_prio_qopt *qopt;
int i;
if (nla_len(opt) < sizeof(*qopt))
return -EINVAL;
qopt = nla_data(opt);
if (qopt->bands > TCQ_PRIO_BANDS || qopt->bands < 2)
return -EINVAL;
for (i = 0; i <= TC_PRIO_MAX; i++) {
if (qopt->priomap[i] >= qopt->bands)
return -EINVAL;
}
sch_tree_lock(sch);
q->bands = qopt->bands;
memcpy(q->prio2band, qopt->priomap, TC_PRIO_MAX+1);
for (i = q->bands; i < TCQ_PRIO_BANDS; i++) {
struct Qdisc *child = q->queues[i];
q->queues[i] = &noop_qdisc;
if (child != &noop_qdisc) {
qdisc_tree_reduce_backlog(child, child->q.qlen, child->qstats.backlog);
qdisc_destroy(child);
}
}
sch_tree_unlock(sch);
for (i = 0; i < q->bands; i++) {
struct Qdisc *child;
if (q->queues[i] != &noop_qdisc)
continue;
child = qdisc_create_dflt(sch->dev_queue, &pfifo_qdisc_ops,
TC_H_MAKE(sch->handle, i + 1));
if (!child)
return -ENOMEM;
sch_tree_lock(sch);
q->queues[i] = child;
sch_tree_unlock(sch);
}
return 0;
}
static int prio_init(struct Qdisc *sch, struct nlattr *opt)
{
struct prio_sched_data *q = qdisc_priv(sch);
int i;
for (i = 0; i < TCQ_PRIO_BANDS; i++)
q->queues[i] = &noop_qdisc;
if (opt == NULL) {
return -EINVAL;
} else {
int err;
if ((err = prio_tune(sch, opt)) != 0)
return err;
}
return 0;
}
static int prio_dump(struct Qdisc *sch, struct sk_buff *skb)
{
struct prio_sched_data *q = qdisc_priv(sch);
unsigned char *b = skb_tail_pointer(skb);
struct tc_prio_qopt opt;
opt.bands = q->bands;
memcpy(&opt.priomap, q->prio2band, TC_PRIO_MAX + 1);
if (nla_put(skb, TCA_OPTIONS, sizeof(opt), &opt))
goto nla_put_failure;
return skb->len;
nla_put_failure:
nlmsg_trim(skb, b);
return -1;
}
static int prio_graft(struct Qdisc *sch, unsigned long arg, struct Qdisc *new,
struct Qdisc **old)
{
struct prio_sched_data *q = qdisc_priv(sch);
unsigned long band = arg - 1;
if (new == NULL)
new = &noop_qdisc;
*old = qdisc_replace(sch, new, &q->queues[band]);
return 0;
}
static struct Qdisc *
prio_leaf(struct Qdisc *sch, unsigned long arg)
{
struct prio_sched_data *q = qdisc_priv(sch);
unsigned long band = arg - 1;
return q->queues[band];
}
static unsigned long prio_get(struct Qdisc *sch, u32 classid)
{
struct prio_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 prio_bind(struct Qdisc *sch, unsigned long parent, u32 classid)
{
return prio_get(sch, classid);
}
static void prio_put(struct Qdisc *q, unsigned long cl)
{
}
static int prio_dump_class(struct Qdisc *sch, unsigned long cl, struct sk_buff *skb,
struct tcmsg *tcm)
{
struct prio_sched_data *q = qdisc_priv(sch);
tcm->tcm_handle |= TC_H_MIN(cl);
tcm->tcm_info = q->queues[cl-1]->handle;
return 0;
}
static int prio_dump_class_stats(struct Qdisc *sch, unsigned long cl,
struct gnet_dump *d)
{
struct prio_sched_data *q = qdisc_priv(sch);
struct Qdisc *cl_q;
cl_q = q->queues[cl - 1];
if (gnet_stats_copy_basic(d, NULL, &cl_q->bstats) < 0 ||
gnet_stats_copy_queue(d, NULL, &cl_q->qstats, cl_q->q.qlen) < 0)
return -1;
return 0;
}
static void prio_walk(struct Qdisc *sch, struct qdisc_walker *arg)
{
struct prio_sched_data *q = qdisc_priv(sch);
int prio;
if (arg->stop)
return;
for (prio = 0; prio < q->bands; prio++) {
if (arg->count < arg->skip) {
arg->count++;
continue;
}
if (arg->fn(sch, prio + 1, arg) < 0) {
arg->stop = 1;
break;
}
arg->count++;
}
}
static struct tcf_proto __rcu **prio_find_tcf(struct Qdisc *sch,
unsigned long cl)
{
struct prio_sched_data *q = qdisc_priv(sch);
if (cl)
return NULL;
return &q->filter_list;
}
static const struct Qdisc_class_ops prio_class_ops = {
.graft = prio_graft,
.leaf = prio_leaf,
.get = prio_get,
.put = prio_put,
.walk = prio_walk,
.tcf_chain = prio_find_tcf,
.bind_tcf = prio_bind,
.unbind_tcf = prio_put,
.dump = prio_dump_class,
.dump_stats = prio_dump_class_stats,
};
static struct Qdisc_ops prio_qdisc_ops __read_mostly = {
.next = NULL,
.cl_ops = &prio_class_ops,
.id = "prio",
.priv_size = sizeof(struct prio_sched_data),
.enqueue = prio_enqueue,
.dequeue = prio_dequeue,
.peek = prio_peek,
.drop = prio_drop,
.init = prio_init,
.reset = prio_reset,
.destroy = prio_destroy,
.change = prio_tune,
.dump = prio_dump,
.owner = THIS_MODULE,
};
static int __init prio_module_init(void)
{
return register_qdisc(&prio_qdisc_ops);
}
static void __exit prio_module_exit(void)
{
unregister_qdisc(&prio_qdisc_ops);
}
module_init(prio_module_init)
module_exit(prio_module_exit)
MODULE_LICENSE("GPL");