| 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
| ||
|
Message-ID: <20240804024047.100355-5-tj@kernel.org>
Date: Sat, 3 Aug 2024 16:40:11 -1000
From: Tejun Heo <tj@...nel.org>
To: void@...ifault.com,
peterz@...radead.org
Cc: linux-kernel@...r.kernel.org,
kernel-team@...a.com,
mingo@...hat.com,
Tejun Heo <tj@...nel.org>
Subject: [PATCH 4/6] sched_ext: Simplify UP support by enabling sched_class->balance() in UP
On SMP, SCX performs dispatch from sched_class->balance(). As balance() was
not available in UP, it instead called the internal balance function from
put_prev_task_scx() and pick_next_task_scx() to emulate the effect, which is
rather nasty.
Enabling sched_class->balance() on UP shouldn't cause any meaningful
overhead. Enable balance() on UP and drop the ugly workaround.
Signed-off-by: Tejun Heo <tj@...nel.org>
Suggested-by: Peter Zijlstra <peterz@...radead.org>
---
kernel/sched/core.c | 4 +---
kernel/sched/ext.c | 41 +----------------------------------------
kernel/sched/sched.h | 2 +-
3 files changed, 3 insertions(+), 44 deletions(-)
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 0532b27fd9af..d2ccc2c4b4d3 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -5826,7 +5826,6 @@ static inline void schedule_debug(struct task_struct *prev, bool preempt)
static void put_prev_task_balance(struct rq *rq, struct task_struct *prev,
struct rq_flags *rf)
{
-#ifdef CONFIG_SMP
const struct sched_class *start_class = prev->sched_class;
const struct sched_class *class;
@@ -5849,10 +5848,9 @@ static void put_prev_task_balance(struct rq *rq, struct task_struct *prev,
* a runnable task of @class priority or higher.
*/
for_active_class_range(class, start_class, &idle_sched_class) {
- if (class->balance(rq, prev, rf))
+ if (class->balance && class->balance(rq, prev, rf))
break;
}
-#endif
put_prev_task(rq, prev);
}
diff --git a/kernel/sched/ext.c b/kernel/sched/ext.c
index 48f8f57f5954..09f394bb4889 100644
--- a/kernel/sched/ext.c
+++ b/kernel/sched/ext.c
@@ -2616,7 +2616,6 @@ static int balance_one(struct rq *rq, struct task_struct *prev, bool local)
return has_tasks;
}
-#ifdef CONFIG_SMP
static int balance_scx(struct rq *rq, struct task_struct *prev,
struct rq_flags *rf)
{
@@ -2650,7 +2649,6 @@ static int balance_scx(struct rq *rq, struct task_struct *prev,
return ret;
}
-#endif
static void set_next_task_scx(struct rq *rq, struct task_struct *p, bool first)
{
@@ -2719,37 +2717,6 @@ static void process_ddsp_deferred_locals(struct rq *rq)
static void put_prev_task_scx(struct rq *rq, struct task_struct *p)
{
-#ifndef CONFIG_SMP
- /*
- * UP workaround.
- *
- * Because SCX may transfer tasks across CPUs during dispatch, dispatch
- * is performed from its balance operation which isn't called in UP.
- * Let's work around by calling it from the operations which come right
- * after.
- *
- * 1. If the prev task is on SCX, pick_next_task() calls
- * .put_prev_task() right after. As .put_prev_task() is also called
- * from other places, we need to distinguish the calls which can be
- * done by looking at the previous task's state - if still queued or
- * dequeued with %SCX_DEQ_SLEEP, the caller must be pick_next_task().
- * This case is handled here.
- *
- * 2. If the prev task is not on SCX, the first following call into SCX
- * will be .pick_next_task(), which is covered by calling
- * balance_scx() from pick_next_task_scx().
- *
- * Note that we can't merge the first case into the second as
- * balance_scx() must be called before the previous SCX task goes
- * through put_prev_task_scx().
- *
- * @rq is pinned and can't be unlocked. As UP doesn't transfer tasks
- * around, balance_one() doesn't need to.
- */
- if (p->scx.flags & (SCX_TASK_QUEUED | SCX_TASK_DEQD_FOR_SLEEP))
- balance_one(rq, p, true);
-#endif
-
update_curr_scx(rq);
/* see dequeue_task_scx() on why we skip when !QUEUED */
@@ -2807,12 +2774,6 @@ static struct task_struct *pick_next_task_scx(struct rq *rq)
{
struct task_struct *p;
-#ifndef CONFIG_SMP
- /* UP workaround - see the comment at the head of put_prev_task_scx() */
- if (unlikely(rq->curr->sched_class != &ext_sched_class))
- balance_one(rq, rq->curr, true);
-#endif
-
p = first_local_task(rq);
if (!p)
return NULL;
@@ -3673,6 +3634,7 @@ DEFINE_SCHED_CLASS(ext) = {
.wakeup_preempt = wakeup_preempt_scx,
+ .balance = balance_scx,
.pick_next_task = pick_next_task_scx,
.put_prev_task = put_prev_task_scx,
@@ -3681,7 +3643,6 @@ DEFINE_SCHED_CLASS(ext) = {
.switch_class = switch_class_scx,
#ifdef CONFIG_SMP
- .balance = balance_scx,
.select_task_rq = select_task_rq_scx,
.task_woken = task_woken_scx,
.set_cpus_allowed = set_cpus_allowed_scx,
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 42b4d1428c2c..9b88a46d3fce 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -2357,6 +2357,7 @@ struct sched_class {
void (*wakeup_preempt)(struct rq *rq, struct task_struct *p, int flags);
+ int (*balance)(struct rq *rq, struct task_struct *prev, struct rq_flags *rf);
struct task_struct *(*pick_next_task)(struct rq *rq);
void (*put_prev_task)(struct rq *rq, struct task_struct *p);
@@ -2365,7 +2366,6 @@ struct sched_class {
void (*switch_class)(struct rq *rq, struct task_struct *next);
#ifdef CONFIG_SMP
- int (*balance)(struct rq *rq, struct task_struct *prev, struct rq_flags *rf);
int (*select_task_rq)(struct task_struct *p, int task_cpu, int flags);
struct task_struct * (*pick_task)(struct rq *rq);
--
2.46.0
Powered by blists - more mailing lists