| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Date: Thu, 19 Dec 2019 18:20:58 +0300
From: Kirill Tkhai <ktkhai@...tuozzo.com>
To: Steven Rostedt <rostedt@...dmis.org>,
Peter Zijlstra <peterz@...radead.org>
Cc: mingo@...hat.com, juri.lelli@...hat.com,
vincent.guittot@...aro.org, dietmar.eggemann@....com,
bsegall@...gle.com, mgorman@...e.de, linux-kernel@...r.kernel.org
Subject: [PATCH v2] sched: Micro optimization in pick_next_task() and in
check_preempt_curr()
From: Kirill Tkhai <ktkhai@...tuozzo.com>
This introduces an optimization based on xxx_sched_class addresses
in two hot scheduler functions: pick_next_task() and check_preempt_curr().
After this patch, it will be possible to compare pointers to sched classes
to check, which of them has a higher priority, instead of current iterations
using for_each_class().
One more result of the patch is that size of object file becomes a little
less (excluding added BUG_ON(), which goes in __init section):
$size kernel/sched/core.o
text data bss dec hex filename
before: 66446 18957 676 86079 1503f kernel/sched/core.o
after: 66398 18957 676 86031 1500f kernel/sched/core.o
SCHED_DATA improvements guaranteeing order of sched classes are made
by Steven Rostedt <rostedt@...dmis.org>
Signed-off-by: Kirill Tkhai <ktkhai@...tuozzo.com>
v2: Steven's data sections ordering. Hunk with comment in Makefile is removed.
---
include/asm-generic/vmlinux.lds.h | 8 ++++++++
kernel/sched/core.c | 24 +++++++++---------------
kernel/sched/deadline.c | 3 ++-
kernel/sched/fair.c | 3 ++-
kernel/sched/idle.c | 3 ++-
kernel/sched/rt.c | 3 ++-
kernel/sched/stop_task.c | 3 ++-
7 files changed, 27 insertions(+), 20 deletions(-)
diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h
index e00f41aa8ec4..ff12a422ff19 100644
--- a/include/asm-generic/vmlinux.lds.h
+++ b/include/asm-generic/vmlinux.lds.h
@@ -108,6 +108,13 @@
#define SBSS_MAIN .sbss
#endif
+#define SCHED_DATA \
+ *(__idle_sched_class) \
+ *(__fair_sched_class) \
+ *(__rt_sched_class) \
+ *(__dl_sched_class) \
+ *(__stop_sched_class)
+
/*
* Align to a 32 byte boundary equal to the
* alignment gcc 4.5 uses for a struct
@@ -308,6 +315,7 @@
#define DATA_DATA \
*(.xiptext) \
*(DATA_MAIN) \
+ SCHED_DATA \
*(.ref.data) \
*(.data..shared_aligned) /* percpu related */ \
MEM_KEEP(init.data*) \
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 15508c202bf5..befdd7158b27 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -1416,20 +1416,10 @@ static inline void check_class_changed(struct rq *rq, struct task_struct *p,
void check_preempt_curr(struct rq *rq, struct task_struct *p, int flags)
{
- const struct sched_class *class;
-
- if (p->sched_class == rq->curr->sched_class) {
+ if (p->sched_class == rq->curr->sched_class)
rq->curr->sched_class->check_preempt_curr(rq, p, flags);
- } else {
- for_each_class(class) {
- if (class == rq->curr->sched_class)
- break;
- if (class == p->sched_class) {
- resched_curr(rq);
- break;
- }
- }
- }
+ else if (p->sched_class > rq->curr->sched_class)
+ resched_curr(rq);
/*
* A queue event has occurred, and we're going to schedule. In
@@ -3914,8 +3904,7 @@ pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
* higher scheduling class, because otherwise those loose the
* opportunity to pull in more work from other CPUs.
*/
- if (likely((prev->sched_class == &idle_sched_class ||
- prev->sched_class == &fair_sched_class) &&
+ if (likely(prev->sched_class <= &fair_sched_class &&
rq->nr_running == rq->cfs.h_nr_running)) {
p = pick_next_task_fair(rq, prev, rf);
@@ -6569,6 +6558,11 @@ void __init sched_init(void)
unsigned long ptr = 0;
int i;
+ BUG_ON(&idle_sched_class > &fair_sched_class ||
+ &fair_sched_class > &rt_sched_class ||
+ &rt_sched_class > &dl_sched_class ||
+ &dl_sched_class > &stop_sched_class);
+
wait_bit_init();
#ifdef CONFIG_FAIR_GROUP_SCHED
diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index 43323f875cb9..5abdbe569f93 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -2428,7 +2428,8 @@ static void prio_changed_dl(struct rq *rq, struct task_struct *p,
}
}
-const struct sched_class dl_sched_class = {
+const struct sched_class dl_sched_class
+ __attribute__((section("__dl_sched_class"))) = {
.next = &rt_sched_class,
.enqueue_task = enqueue_task_dl,
.dequeue_task = dequeue_task_dl,
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 8da0222924cf..9379b3804582 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -10760,7 +10760,8 @@ static unsigned int get_rr_interval_fair(struct rq *rq, struct task_struct *task
/*
* All the scheduling class methods:
*/
-const struct sched_class fair_sched_class = {
+const struct sched_class fair_sched_class
+ __attribute__((section("__fair_sched_class"))) = {
.next = &idle_sched_class,
.enqueue_task = enqueue_task_fair,
.dequeue_task = dequeue_task_fair,
diff --git a/kernel/sched/idle.c b/kernel/sched/idle.c
index ffa959e91227..700a9c826f0e 100644
--- a/kernel/sched/idle.c
+++ b/kernel/sched/idle.c
@@ -454,7 +454,8 @@ static void update_curr_idle(struct rq *rq)
/*
* Simple, special scheduling class for the per-CPU idle tasks:
*/
-const struct sched_class idle_sched_class = {
+const struct sched_class idle_sched_class
+ __attribute__((section("__idle_sched_class"))) = {
/* .next is NULL */
/* no enqueue/yield_task for idle tasks */
diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c
index e591d40fd645..5d3f9bcddaeb 100644
--- a/kernel/sched/rt.c
+++ b/kernel/sched/rt.c
@@ -2354,7 +2354,8 @@ static unsigned int get_rr_interval_rt(struct rq *rq, struct task_struct *task)
return 0;
}
-const struct sched_class rt_sched_class = {
+const struct sched_class rt_sched_class
+ __attribute__((section("__rt_sched_class"))) = {
.next = &fair_sched_class,
.enqueue_task = enqueue_task_rt,
.dequeue_task = dequeue_task_rt,
diff --git a/kernel/sched/stop_task.c b/kernel/sched/stop_task.c
index 4c9e9975684f..03bc7530ff75 100644
--- a/kernel/sched/stop_task.c
+++ b/kernel/sched/stop_task.c
@@ -115,7 +115,8 @@ static void update_curr_stop(struct rq *rq)
/*
* Simple, special scheduling class for the per-CPU stop tasks:
*/
-const struct sched_class stop_sched_class = {
+const struct sched_class stop_sched_class
+ __attribute__((section("__stop_sched_class"))) = {
.next = &dl_sched_class,
.enqueue_task = enqueue_task_stop,
Powered by blists - more mailing lists