LKML Archive on lore.kernel.org
 help / color / Atom feed
From: "tip-bot2 for Peter Zijlstra" <tip-bot2@linutronix.de>
To: linux-tip-commits@vger.kernel.org
Cc: "Peter Zijlstra (Intel)" <peterz@infradead.org>,
	Don Hiatt <dhiatt@digitalocean.com>,
	Hongyu Ning <hongyu.ning@linux.intel.com>,
	Vincent Guittot <vincent.guittot@linaro.org>,
	x86@kernel.org, linux-kernel@vger.kernel.org
Subject: [tip: sched/core] sched: Optimize rq_lockp() usage
Date: Wed, 12 May 2021 10:28:26 -0000
Message-ID: <162081530619.29796.11256820252103924811.tip-bot2@tip-bot2> (raw)
In-Reply-To: <20210422123308.316696988@infradead.org>

The following commit has been merged into the sched/core branch of tip:

Commit-ID:     9ef7e7e33bcdb57be1afb28884053c28b5f05240
Gitweb:        https://git.kernel.org/tip/9ef7e7e33bcdb57be1afb28884053c28b5f05240
Author:        Peter Zijlstra <peterz@infradead.org>
AuthorDate:    Wed, 03 Mar 2021 16:45:41 +01:00
Committer:     Peter Zijlstra <peterz@infradead.org>
CommitterDate: Wed, 12 May 2021 11:43:27 +02:00

sched: Optimize rq_lockp() usage

rq_lockp() includes a static_branch(), which is asm-goto, which is
asm volatile which defeats regular CSE. This means that:

	if (!static_branch(&foo))
		return simple;

	if (static_branch(&foo) && cond)
		return complex;

Doesn't fold and we get horrible code. Introduce __rq_lockp() without
the static_branch() on.

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Tested-by: Don Hiatt <dhiatt@digitalocean.com>
Tested-by: Hongyu Ning <hongyu.ning@linux.intel.com>
Tested-by: Vincent Guittot <vincent.guittot@linaro.org>
Link: https://lkml.kernel.org/r/20210422123308.316696988@infradead.org
---
 kernel/sched/core.c     | 16 ++++++++--------
 kernel/sched/deadline.c |  4 ++--
 kernel/sched/fair.c     |  2 +-
 kernel/sched/sched.h    | 33 +++++++++++++++++++++++++--------
 4 files changed, 36 insertions(+), 19 deletions(-)

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 384b793..42c1c88 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -300,9 +300,9 @@ void raw_spin_rq_lock_nested(struct rq *rq, int subclass)
 	}
 
 	for (;;) {
-		lock = rq_lockp(rq);
+		lock = __rq_lockp(rq);
 		raw_spin_lock_nested(lock, subclass);
-		if (likely(lock == rq_lockp(rq))) {
+		if (likely(lock == __rq_lockp(rq))) {
 			/* preempt_count *MUST* be > 1 */
 			preempt_enable_no_resched();
 			return;
@@ -325,9 +325,9 @@ bool raw_spin_rq_trylock(struct rq *rq)
 	}
 
 	for (;;) {
-		lock = rq_lockp(rq);
+		lock = __rq_lockp(rq);
 		ret = raw_spin_trylock(lock);
-		if (!ret || (likely(lock == rq_lockp(rq)))) {
+		if (!ret || (likely(lock == __rq_lockp(rq)))) {
 			preempt_enable();
 			return ret;
 		}
@@ -352,7 +352,7 @@ void double_rq_lock(struct rq *rq1, struct rq *rq2)
 		swap(rq1, rq2);
 
 	raw_spin_rq_lock(rq1);
-	if (rq_lockp(rq1) == rq_lockp(rq2))
+	if (__rq_lockp(rq1) == __rq_lockp(rq2))
 		return;
 
 	raw_spin_rq_lock_nested(rq2, SINGLE_DEPTH_NESTING);
@@ -2622,7 +2622,7 @@ void set_task_cpu(struct task_struct *p, unsigned int new_cpu)
 	 * task_rq_lock().
 	 */
 	WARN_ON_ONCE(debug_locks && !(lockdep_is_held(&p->pi_lock) ||
-				      lockdep_is_held(rq_lockp(task_rq(p)))));
+				      lockdep_is_held(__rq_lockp(task_rq(p)))));
 #endif
 	/*
 	 * Clearly, migrating tasks to offline CPUs is a fairly daft thing.
@@ -4248,7 +4248,7 @@ prepare_lock_switch(struct rq *rq, struct task_struct *next, struct rq_flags *rf
 	 * do an early lockdep release here:
 	 */
 	rq_unpin_lock(rq, rf);
-	spin_release(&rq_lockp(rq)->dep_map, _THIS_IP_);
+	spin_release(&__rq_lockp(rq)->dep_map, _THIS_IP_);
 #ifdef CONFIG_DEBUG_SPINLOCK
 	/* this is a valid case when another task releases the spinlock */
 	rq_lockp(rq)->owner = next;
@@ -4262,7 +4262,7 @@ static inline void finish_lock_switch(struct rq *rq)
 	 * fix up the runqueue lock - which gets 'carried over' from
 	 * prev into current:
 	 */
-	spin_acquire(&rq_lockp(rq)->dep_map, 0, 0, _THIS_IP_);
+	spin_acquire(&__rq_lockp(rq)->dep_map, 0, 0, _THIS_IP_);
 	__balance_callbacks(rq);
 	raw_spin_rq_unlock_irq(rq);
 }
diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index 6e99b8b..fb0eb9a 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -1097,9 +1097,9 @@ static enum hrtimer_restart dl_task_timer(struct hrtimer *timer)
 		 * If the runqueue is no longer available, migrate the
 		 * task elsewhere. This necessarily changes rq.
 		 */
-		lockdep_unpin_lock(rq_lockp(rq), rf.cookie);
+		lockdep_unpin_lock(__rq_lockp(rq), rf.cookie);
 		rq = dl_task_offline_migration(rq, p);
-		rf.cookie = lockdep_pin_lock(rq_lockp(rq));
+		rf.cookie = lockdep_pin_lock(__rq_lockp(rq));
 		update_rq_clock(rq);
 
 		/*
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index e50bd75..18960d0 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -1107,7 +1107,7 @@ struct numa_group {
 static struct numa_group *deref_task_numa_group(struct task_struct *p)
 {
 	return rcu_dereference_check(p->numa_group, p == current ||
-		(lockdep_is_held(rq_lockp(task_rq(p))) && !READ_ONCE(p->on_cpu)));
+		(lockdep_is_held(__rq_lockp(task_rq(p))) && !READ_ONCE(p->on_cpu)));
 }
 
 static struct numa_group *deref_curr_numa_group(struct task_struct *p)
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 29418b8..ca30af3 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -1133,6 +1133,10 @@ static inline bool sched_core_disabled(void)
 	return !static_branch_unlikely(&__sched_core_enabled);
 }
 
+/*
+ * Be careful with this function; not for general use. The return value isn't
+ * stable unless you actually hold a relevant rq->__lock.
+ */
 static inline raw_spinlock_t *rq_lockp(struct rq *rq)
 {
 	if (sched_core_enabled(rq))
@@ -1141,6 +1145,14 @@ static inline raw_spinlock_t *rq_lockp(struct rq *rq)
 	return &rq->__lock;
 }
 
+static inline raw_spinlock_t *__rq_lockp(struct rq *rq)
+{
+	if (rq->core_enabled)
+		return &rq->core->__lock;
+
+	return &rq->__lock;
+}
+
 #else /* !CONFIG_SCHED_CORE */
 
 static inline bool sched_core_enabled(struct rq *rq)
@@ -1158,11 +1170,16 @@ static inline raw_spinlock_t *rq_lockp(struct rq *rq)
 	return &rq->__lock;
 }
 
+static inline raw_spinlock_t *__rq_lockp(struct rq *rq)
+{
+	return &rq->__lock;
+}
+
 #endif /* CONFIG_SCHED_CORE */
 
 static inline void lockdep_assert_rq_held(struct rq *rq)
 {
-	lockdep_assert_held(rq_lockp(rq));
+	lockdep_assert_held(__rq_lockp(rq));
 }
 
 extern void raw_spin_rq_lock_nested(struct rq *rq, int subclass);
@@ -1346,7 +1363,7 @@ extern struct callback_head balance_push_callback;
  */
 static inline void rq_pin_lock(struct rq *rq, struct rq_flags *rf)
 {
-	rf->cookie = lockdep_pin_lock(rq_lockp(rq));
+	rf->cookie = lockdep_pin_lock(__rq_lockp(rq));
 
 #ifdef CONFIG_SCHED_DEBUG
 	rq->clock_update_flags &= (RQCF_REQ_SKIP|RQCF_ACT_SKIP);
@@ -1364,12 +1381,12 @@ static inline void rq_unpin_lock(struct rq *rq, struct rq_flags *rf)
 		rf->clock_update_flags = RQCF_UPDATED;
 #endif
 
-	lockdep_unpin_lock(rq_lockp(rq), rf->cookie);
+	lockdep_unpin_lock(__rq_lockp(rq), rf->cookie);
 }
 
 static inline void rq_repin_lock(struct rq *rq, struct rq_flags *rf)
 {
-	lockdep_repin_lock(rq_lockp(rq), rf->cookie);
+	lockdep_repin_lock(__rq_lockp(rq), rf->cookie);
 
 #ifdef CONFIG_SCHED_DEBUG
 	/*
@@ -2338,7 +2355,7 @@ static inline int _double_lock_balance(struct rq *this_rq, struct rq *busiest)
 	__acquires(busiest->lock)
 	__acquires(this_rq->lock)
 {
-	if (rq_lockp(this_rq) == rq_lockp(busiest))
+	if (__rq_lockp(this_rq) == __rq_lockp(busiest))
 		return 0;
 
 	if (likely(raw_spin_rq_trylock(busiest)))
@@ -2370,9 +2387,9 @@ static inline int double_lock_balance(struct rq *this_rq, struct rq *busiest)
 static inline void double_unlock_balance(struct rq *this_rq, struct rq *busiest)
 	__releases(busiest->lock)
 {
-	if (rq_lockp(this_rq) != rq_lockp(busiest))
+	if (__rq_lockp(this_rq) != __rq_lockp(busiest))
 		raw_spin_rq_unlock(busiest);
-	lock_set_subclass(&rq_lockp(this_rq)->dep_map, 0, _RET_IP_);
+	lock_set_subclass(&__rq_lockp(this_rq)->dep_map, 0, _RET_IP_);
 }
 
 static inline void double_lock(spinlock_t *l1, spinlock_t *l2)
@@ -2412,7 +2429,7 @@ static inline void double_rq_unlock(struct rq *rq1, struct rq *rq2)
 	__releases(rq1->lock)
 	__releases(rq2->lock)
 {
-	if (rq_lockp(rq1) != rq_lockp(rq2))
+	if (__rq_lockp(rq1) != __rq_lockp(rq2))
 		raw_spin_rq_unlock(rq2);
 	else
 		__release(rq2->lock);

  reply index

Thread overview: 92+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-04-22 12:04 [PATCH 00/19] sched: Core Scheduling Peter Zijlstra
2021-04-22 12:05 ` [PATCH 01/19] sched/fair: Add a few assertions Peter Zijlstra
2021-05-12 10:28   ` [tip: sched/core] " tip-bot2 for Peter Zijlstra
2021-05-13  8:56     ` Ning, Hongyu
2021-04-22 12:05 ` [PATCH 02/19] sched: Provide raw_spin_rq_*lock*() helpers Peter Zijlstra
2021-05-12 10:28   ` [tip: sched/core] " tip-bot2 for Peter Zijlstra
2021-04-22 12:05 ` [PATCH 03/19] sched: Wrap rq::lock access Peter Zijlstra
2021-05-12 10:28   ` [tip: sched/core] " tip-bot2 for Peter Zijlstra
2021-04-22 12:05 ` [PATCH 04/19] sched: Prepare for Core-wide rq->lock Peter Zijlstra
2021-04-24  1:22   ` Josh Don
2021-04-26  8:31     ` Peter Zijlstra
2021-04-26 22:21       ` Josh Don
2021-04-27 17:10         ` Don Hiatt
2021-04-27 23:35           ` Josh Don
2021-04-28  1:03             ` Aubrey Li
2021-04-28  6:05               ` Aubrey Li
2021-04-28 10:57                 ` Aubrey Li
2021-04-28 16:41                   ` Don Hiatt
2021-04-29 20:48                     ` Josh Don
2021-04-29 21:09                       ` Don Hiatt
2021-04-29 23:22                         ` Josh Don
2021-04-30 16:18                           ` Don Hiatt
2021-04-30  8:26                         ` Aubrey Li
2021-04-28 16:04             ` Don Hiatt
2021-04-27 23:30         ` Josh Don
2021-04-28  9:13           ` Peter Zijlstra
2021-04-28 10:35             ` Aubrey Li
2021-04-28 11:03               ` Peter Zijlstra
2021-04-28 14:18                 ` Paul E. McKenney
2021-04-29 20:11             ` Josh Don
2021-05-03 19:17               ` Peter Zijlstra
2021-04-28  7:13         ` Peter Zijlstra
2021-04-28  6:02   ` Aubrey Li
2021-04-29  8:03   ` Aubrey Li
2021-04-29 20:39     ` Josh Don
2021-04-30  8:20       ` Aubrey Li
2021-04-30  8:48         ` Josh Don
2021-04-30 14:15           ` Aubrey Li
2021-05-04  7:38       ` Peter Zijlstra
2021-05-05 16:20         ` Don Hiatt
2021-05-06 10:25           ` Peter Zijlstra
2021-05-07  9:50   ` [PATCH v2 " Peter Zijlstra
2021-05-08  8:07     ` Aubrey Li
2021-05-12  9:07       ` Peter Zijlstra
2021-04-22 12:05 ` [PATCH 05/19] sched: " Peter Zijlstra
2021-05-07  9:50   ` [PATCH v2 " Peter Zijlstra
2021-05-12 10:28     ` [tip: sched/core] " tip-bot2 for Peter Zijlstra
2021-04-22 12:05 ` [PATCH 06/19] sched: Optimize rq_lockp() usage Peter Zijlstra
2021-05-12 10:28   ` tip-bot2 for Peter Zijlstra [this message]
2021-04-22 12:05 ` [PATCH 07/19] sched: Allow sched_core_put() from atomic context Peter Zijlstra
2021-05-12 10:28   ` [tip: sched/core] " tip-bot2 for Peter Zijlstra
2021-04-22 12:05 ` [PATCH 08/19] sched: Introduce sched_class::pick_task() Peter Zijlstra
2021-05-12 10:28   ` [tip: sched/core] " tip-bot2 for Peter Zijlstra
2021-04-22 12:05 ` [PATCH 09/19] sched: Basic tracking of matching tasks Peter Zijlstra
2021-05-12 10:28   ` [tip: sched/core] " tip-bot2 for Peter Zijlstra
2021-04-22 12:05 ` [PATCH 10/19] sched: Add core wide task selection and scheduling Peter Zijlstra
2021-05-12 10:28   ` [tip: sched/core] " tip-bot2 for Peter Zijlstra
2021-04-22 12:05 ` [PATCH 11/19] sched/fair: Fix forced idle sibling starvation corner case Peter Zijlstra
2021-05-12 10:28   ` [tip: sched/core] " tip-bot2 for Vineeth Pillai
2021-04-22 12:05 ` [PATCH 12/19] sched: Fix priority inversion of cookied task with sibling Peter Zijlstra
2021-05-12 10:28   ` [tip: sched/core] " tip-bot2 for Joel Fernandes (Google)
2021-04-22 12:05 ` [PATCH 13/19] sched/fair: Snapshot the min_vruntime of CPUs on force idle Peter Zijlstra
2021-05-12 10:28   ` [tip: sched/core] " tip-bot2 for Joel Fernandes (Google)
2021-04-22 12:05 ` [PATCH 14/19] sched: Trivial forced-newidle balancer Peter Zijlstra
2021-05-12 10:28   ` [tip: sched/core] " tip-bot2 for Peter Zijlstra
2021-04-22 12:05 ` [PATCH 15/19] sched: Migration changes for core scheduling Peter Zijlstra
2021-05-12 10:28   ` [tip: sched/core] " tip-bot2 for Aubrey Li
2021-04-22 12:05 ` [PATCH 16/19] sched: Trivial core scheduling cookie management Peter Zijlstra
2021-05-12 10:28   ` [tip: sched/core] " tip-bot2 for Peter Zijlstra
2021-04-22 12:05 ` [PATCH 17/19] sched: Inherit task cookie on fork() Peter Zijlstra
2021-05-10 16:06   ` Joel Fernandes
2021-05-10 16:22     ` Chris Hyser
2021-05-10 20:47       ` Joel Fernandes
2021-05-10 21:38         ` Chris Hyser
2021-05-12  9:05           ` Peter Zijlstra
2021-05-12 20:20             ` Josh Don
2021-05-12 21:07               ` Don Hiatt
2021-05-12 10:28   ` [tip: sched/core] " tip-bot2 for Peter Zijlstra
2021-04-22 12:05 ` [PATCH 18/19] sched: prctl() core-scheduling interface Peter Zijlstra
2021-05-12 10:28   ` [tip: sched/core] " tip-bot2 for Chris Hyser
2021-06-14 23:36   ` [PATCH 18/19] " Josh Don
2021-06-15 11:31     ` Joel Fernandes
2021-04-22 12:05 ` [PATCH 19/19] kselftest: Add test for core sched prctl interface Peter Zijlstra
2021-05-12 10:28   ` [tip: sched/core] " tip-bot2 for Chris Hyser
2021-04-22 16:43 ` [PATCH 00/19] sched: Core Scheduling Don Hiatt
2021-04-22 17:29   ` Peter Zijlstra
2021-04-30  6:47 ` Ning, Hongyu
2021-05-06 10:29   ` Peter Zijlstra
2021-05-06 12:53     ` Ning, Hongyu
2021-05-07 18:02 ` Joel Fernandes
2021-05-10 16:16 ` Vincent Guittot
2021-05-11  7:00   ` Vincent Guittot

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=162081530619.29796.11256820252103924811.tip-bot2@tip-bot2 \
    --to=tip-bot2@linutronix.de \
    --cc=dhiatt@digitalocean.com \
    --cc=hongyu.ning@linux.intel.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-tip-commits@vger.kernel.org \
    --cc=peterz@infradead.org \
    --cc=vincent.guittot@linaro.org \
    --cc=x86@kernel.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link

LKML Archive on lore.kernel.org

Archives are clonable:
	git clone --mirror https://lore.kernel.org/lkml/0 lkml/git/0.git
	git clone --mirror https://lore.kernel.org/lkml/1 lkml/git/1.git
	git clone --mirror https://lore.kernel.org/lkml/2 lkml/git/2.git
	git clone --mirror https://lore.kernel.org/lkml/3 lkml/git/3.git
	git clone --mirror https://lore.kernel.org/lkml/4 lkml/git/4.git
	git clone --mirror https://lore.kernel.org/lkml/5 lkml/git/5.git
	git clone --mirror https://lore.kernel.org/lkml/6 lkml/git/6.git
	git clone --mirror https://lore.kernel.org/lkml/7 lkml/git/7.git
	git clone --mirror https://lore.kernel.org/lkml/8 lkml/git/8.git
	git clone --mirror https://lore.kernel.org/lkml/9 lkml/git/9.git
	git clone --mirror https://lore.kernel.org/lkml/10 lkml/git/10.git

	# If you have public-inbox 1.1+ installed, you may
	# initialize and index your mirror using the following commands:
	public-inbox-init -V2 lkml lkml/ https://lore.kernel.org/lkml \
		linux-kernel@vger.kernel.org
	public-inbox-index lkml

Example config snippet for mirrors

Newsgroup available over NNTP:
	nntp://nntp.lore.kernel.org/org.kernel.vger.linux-kernel


AGPL code for this site: git clone https://public-inbox.org/public-inbox.git