LKML Archive on lore.kernel.org
help / color / mirror / Atom feed
From: Thomas Gleixner <tglx@linutronix.de>
To: LKML <linux-kernel@vger.kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>,
	Ingo Molnar <mingo@kernel.org>,
	Juri Lelli <juri.lelli@redhat.com>,
	Steven Rostedt <rostedt@goodmis.org>,
	Daniel Bristot de Oliveira <bristot@redhat.com>,
	Will Deacon <will@kernel.org>, Waiman Long <longman@redhat.com>,
	Boqun Feng <boqun.feng@gmail.com>,
	Sebastian Andrzej Siewior <bigeasy@linutronix.de>,
	Davidlohr Bueso <dave@stgolabs.net>,
	Mike Galbraith <efault@gmx.de>
Subject: [patch V4 05/68] sched: Rework the __schedule() preempt argument
Date: Wed, 11 Aug 2021 14:22:36 +0200 (CEST)	[thread overview]
Message-ID: <20210811121414.423888208@linutronix.de> (raw)
In-Reply-To: <20210811120348.855823694@linutronix.de>

From: Thomas Gleixner <tglx@linutronix.de>

PREEMPT_RT needs to hand a special state into __schedule() when a task
blocks on a 'sleeping' spin/rwlock. This is required to handle
rcu_note_context_switch() correctly without having special casing in the
RCU code. From an RCU point of view the blocking on the sleeping spinlock
is equivalent to preemption because the task might be in a read side
critical section.

schedule_debug() also has a check which would trigger with the !preempt
case, but that could be handled differently.

To avoid adding another argument and extra checks which cannot be optimized
out by the compiler the following solution has been chosen:

 - Replace the boolean 'preempt' argument with an unsigned integer
   'sched_mode' argument and define constants to hand in:
   (0 == No preemption, 1 = preemption).

 - Add two masks to apply on that mode one for the debug/rcu invocations
   and one for the actual scheduling decision.

   For a non RT kernel these masks are UINT_MAX, i.e. all bits are set
   which allows the compiler to optimize the AND operation out because it is
   not masking out anything. IOW, it's not different from the boolean.

   RT enabled kernels will define these masks separately.

No functional change.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
V2: Simplify the masking logic
---
 kernel/sched/core.c |   34 +++++++++++++++++++++++-----------
 1 file changed, 23 insertions(+), 11 deletions(-)
---
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -5820,6 +5820,18 @@ pick_next_task(struct rq *rq, struct tas
 #endif /* CONFIG_SCHED_CORE */
 
 /*
+ * Constants for the sched_mode argument of __schedule().
+ *
+ * The mode argument allows RT enabled kernels to differentiate a
+ * preemption from blocking on an 'sleeping' spin/rwlock. Note, that
+ * SM_MASK_PREEMPT for !RT has all bits set which allows the compiler to
+ * optimize the AND operation out and just check for zero.
+ */
+#define SM_NONE			0x0
+#define SM_PREEMPT		0x1
+#define SM_MASK_PREEMPT		(~0U)
+
+/*
  * __schedule() is the main scheduler function.
  *
  * The main means of driving the scheduler and thus entering this function are:
@@ -5858,7 +5870,7 @@ pick_next_task(struct rq *rq, struct tas
  *
  * WARNING: must be called with preemption disabled!
  */
-static void __sched notrace __schedule(bool preempt)
+static void __sched notrace __schedule(unsigned int sched_mode)
 {
 	struct task_struct *prev, *next;
 	unsigned long *switch_count;
@@ -5871,13 +5883,13 @@ static void __sched notrace __schedule(b
 	rq = cpu_rq(cpu);
 	prev = rq->curr;
 
-	schedule_debug(prev, preempt);
+	schedule_debug(prev, !!sched_mode);
 
 	if (sched_feat(HRTICK) || sched_feat(HRTICK_DL))
 		hrtick_clear(rq);
 
 	local_irq_disable();
-	rcu_note_context_switch(preempt);
+	rcu_note_context_switch(!!sched_mode);
 
 	/*
 	 * Make sure that signal_pending_state()->signal_pending() below
@@ -5911,7 +5923,7 @@ static void __sched notrace __schedule(b
 	 *  - ptrace_{,un}freeze_traced() can change ->state underneath us.
 	 */
 	prev_state = READ_ONCE(prev->__state);
-	if (!preempt && prev_state) {
+	if (!(sched_mode & SM_MASK_PREEMPT) && prev_state) {
 		if (signal_pending_state(prev_state, prev)) {
 			WRITE_ONCE(prev->__state, TASK_RUNNING);
 		} else {
@@ -5977,7 +5989,7 @@ static void __sched notrace __schedule(b
 		migrate_disable_switch(rq, prev);
 		psi_sched_switch(prev, next, !task_on_rq_queued(prev));
 
-		trace_sched_switch(preempt, prev, next);
+		trace_sched_switch(sched_mode & SM_MASK_PREEMPT, prev, next);
 
 		/* Also unlocks the rq: */
 		rq = context_switch(rq, prev, next, &rf);
@@ -5998,7 +6010,7 @@ void __noreturn do_task_dead(void)
 	/* Tell freezer to ignore us: */
 	current->flags |= PF_NOFREEZE;
 
-	__schedule(false);
+	__schedule(SM_NONE);
 	BUG();
 
 	/* Avoid "noreturn function does return" - but don't continue if BUG() is a NOP: */
@@ -6059,7 +6071,7 @@ asmlinkage __visible void __sched schedu
 	sched_submit_work(tsk);
 	do {
 		preempt_disable();
-		__schedule(false);
+		__schedule(SM_NONE);
 		sched_preempt_enable_no_resched();
 	} while (need_resched());
 	sched_update_worker(tsk);
@@ -6087,7 +6099,7 @@ void __sched schedule_idle(void)
 	 */
 	WARN_ON_ONCE(current->__state);
 	do {
-		__schedule(false);
+		__schedule(SM_NONE);
 	} while (need_resched());
 }
 
@@ -6140,7 +6152,7 @@ static void __sched notrace preempt_sche
 		 */
 		preempt_disable_notrace();
 		preempt_latency_start(1);
-		__schedule(true);
+		__schedule(SM_PREEMPT);
 		preempt_latency_stop(1);
 		preempt_enable_no_resched_notrace();
 
@@ -6219,7 +6231,7 @@ asmlinkage __visible void __sched notrac
 		 * an infinite recursion.
 		 */
 		prev_ctx = exception_enter();
-		__schedule(true);
+		__schedule(SM_PREEMPT);
 		exception_exit(prev_ctx);
 
 		preempt_latency_stop(1);
@@ -6368,7 +6380,7 @@ asmlinkage __visible void __sched preemp
 	do {
 		preempt_disable();
 		local_irq_enable();
-		__schedule(true);
+		__schedule(SM_PREEMPT);
 		local_irq_disable();
 		sched_preempt_enable_no_resched();
 	} while (need_resched());


  parent reply	other threads:[~2021-08-11 12:23 UTC|newest]

Thread overview: 70+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-08-11 12:22 [patch V4 00/68] locking, sched: The PREEMPT-RT locking infrastructure Thomas Gleixner
2021-08-11 12:22 ` [patch V4 01/68] sched: Split out the wakeup state check Thomas Gleixner
2021-08-11 12:22 ` [patch V4 02/68] sched: Introduce TASK_RTLOCK_WAIT Thomas Gleixner
2021-08-11 12:22 ` [patch V4 03/68] sched: Reorganize current::__state helpers Thomas Gleixner
2021-08-11 12:22 ` [patch V4 04/68] sched: Prepare for RT sleeping spin/rwlocks Thomas Gleixner
2021-08-11 12:22 ` Thomas Gleixner [this message]
2021-08-11 12:22 ` [patch V4 06/68] sched: Provide schedule point for RT locks Thomas Gleixner
2021-08-11 12:22 ` [patch V4 07/68] sched/wake_q: Provide WAKE_Q_HEAD_INITIALIZER Thomas Gleixner
2021-08-11 12:22 ` [patch V4 08/68] media/atomisp: Use lockdep instead of *mutex_is_locked() Thomas Gleixner
2021-08-11 12:22 ` [patch V4 09/68] rtmutex: Remove rt_mutex_is_locked() Thomas Gleixner
2021-08-11 12:22 ` [patch V4 10/68] rtmutex: Convert macros to inlines Thomas Gleixner
2021-08-11 12:22 ` [patch V4 11/68] rtmutex: Switch to try_cmpxchg() Thomas Gleixner
2021-08-11 12:22 ` [patch V4 12/68] rtmutex: Split API and implementation Thomas Gleixner
2021-08-11 12:22 ` [patch V4 13/68] rtmutex: Split out the inner parts of struct rtmutex Thomas Gleixner
2021-08-11 12:22 ` [patch V4 14/68] locking/rtmutex: Provide rt_mutex_slowlock_locked() Thomas Gleixner
2021-08-11 12:22 ` [patch V4 15/68] rtmutex: Provide rt_mutex_base_is_locked() Thomas Gleixner
2021-08-11 12:22 ` [patch V4 16/68] locking: Add base code for RT rw_semaphore and rwlock Thomas Gleixner
2021-08-11 12:22 ` [patch V4 17/68] locking/rwsem: Add rtmutex based R/W semaphore implementation Thomas Gleixner
2021-08-11 12:22 ` [patch V4 18/68] locking/rtmutex: Add wake_state to rt_mutex_waiter Thomas Gleixner
2021-08-11 12:22 ` [patch V4 19/68] locking/rtmutex: Provide rt_wake_q and helpers Thomas Gleixner
2021-08-11 12:22 ` [patch V4 20/68] locking/rtmutex: Use rt_mutex_wake_q_head Thomas Gleixner
2021-08-11 12:22 ` [patch V4 21/68] locking/rtmutex: Prepare RT rt_mutex_wake_q for RT locks Thomas Gleixner
2021-08-11 12:22 ` [patch V4 22/68] locking/rtmutex: Guard regular sleeping locks specific functions Thomas Gleixner
2021-08-11 12:22 ` [patch V4 23/68] locking/spinlock: Split the lock types header Thomas Gleixner
2021-08-11 12:23 ` [patch V4 24/68] locking/rtmutex: Prevent future include recursion hell Thomas Gleixner
2021-08-11 12:23 ` [patch V4 25/68] locking/lockdep: Reduce includes in debug_locks.h Thomas Gleixner
2021-08-11 12:23 ` [patch V4 26/68] rbtree: Split out the rbtree type definitions Thomas Gleixner
2021-08-11 12:23 ` [patch V4 27/68] locking/rtmutex: Include only rbtree types Thomas Gleixner
2021-08-11 12:23 ` [patch V4 28/68] locking/spinlock: Provide RT specific spinlock type Thomas Gleixner
2021-08-11 12:23 ` [patch V4 29/68] locking/spinlock: Provide RT variant header Thomas Gleixner
2021-08-11 12:23 ` [patch V4 30/68] locking/rtmutex: Provide the spin/rwlock core lock function Thomas Gleixner
2021-08-11 12:23 ` [patch V4 31/68] locking/spinlock: Provide RT variant Thomas Gleixner
2021-08-11 12:23 ` [patch V4 32/68] locking/rwlock: " Thomas Gleixner
2021-08-11 12:23 ` [patch V4 33/68] locking/rtmutex: Squash !RT tasks to DEFAULT_PRIO Thomas Gleixner
2021-08-11 12:23 ` [patch V4 34/68] locking/mutex: Consolidate core headers Thomas Gleixner
2021-08-11 12:23 ` [patch V4 35/68] locking/mutex: Move waiter to core header Thomas Gleixner
2021-08-11 12:23 ` [patch V4 36/68] locking/ww_mutex: Move ww_mutex declarations into ww_mutex.h Thomas Gleixner
2021-08-11 12:23 ` [patch V4 37/68] locking/mutex: Make mutex::wait_lock raw Thomas Gleixner
2021-08-11 12:23 ` [patch V4 38/68] locking/ww_mutex: Simplify lockdep annotation Thomas Gleixner
2021-08-11 12:23 ` [patch V4 39/68] locking/ww_mutex: Gather mutex_waiter initialization Thomas Gleixner
2021-08-11 12:23 ` [patch V4 40/68] locking/ww_mutex: Split up ww_mutex_unlock() Thomas Gleixner
2021-08-11 12:23 ` [patch V4 41/68] locking/ww_mutex: Split W/W implementation logic Thomas Gleixner
2021-08-11 12:23 ` [patch V4 42/68] locking/ww_mutex: Remove __sched annotation Thomas Gleixner
2021-08-11 12:23 ` [patch V4 43/68] locking/ww_mutex: Abstract waiter iteration Thomas Gleixner
2021-08-11 12:23 ` [patch V4 44/68] locking/ww_mutex: Abstract waiter enqueueing Thomas Gleixner
2021-08-11 12:23 ` [patch V4 45/68] locking/ww_mutex: Abstract mutex accessors Thomas Gleixner
2021-08-11 12:23 ` [patch V4 46/68] locking/ww_mutex: Abstract mutex types Thomas Gleixner
2021-08-11 12:23 ` [patch V4 47/68] locking/ww_mutex: Abstract internal lock access Thomas Gleixner
2021-08-11 12:23 ` [patch V4 48/68] locking/ww_mutex: Implement rt_mutex accessors Thomas Gleixner
2021-08-11 12:23 ` [patch V4 49/68] locking/ww_mutex: Add RT priority to W/W order Thomas Gleixner
2021-08-11 12:23 ` [patch V4 50/68] locking/ww_mutex: Add rt_mutex based lock type and accessors Thomas Gleixner
2021-08-11 12:23 ` [patch V4 51/68] locking/rtmutex: Extend the rtmutex core to support ww_mutex Thomas Gleixner
2021-08-11 12:23 ` [patch V4 52/68] locking/ww_mutex: Implement rtmutex based ww_mutex API functions Thomas Gleixner
2021-08-11 12:23 ` [patch V4 53/68] locking/rtmutex: Add mutex variant for RT Thomas Gleixner
2021-08-11 12:23 ` [patch V4 54/68] lib/test_lockup: Adapt to changed variables Thomas Gleixner
2021-08-11 12:23 ` [patch V4 55/68] futex: Validate waiter correctly in futex_proxy_trylock_atomic() Thomas Gleixner
2021-08-11 12:23 ` [patch V4 56/68] futex: Cleanup stale comments Thomas Gleixner
2021-08-11 12:23 ` [patch V4 57/68] futex: Clarify futex_requeue() PI handling Thomas Gleixner
2021-08-11 12:23 ` [patch V4 58/68] futex: Remove bogus condition for requeue PI Thomas Gleixner
2021-08-11 12:23 ` [patch V4 59/68] futex: Correct the number of requeued waiters for PI Thomas Gleixner
2021-08-11 12:23 ` [patch V4 60/68] futex: Restructure futex_requeue() Thomas Gleixner
2021-08-11 12:23 ` [patch V4 61/68] futex: Clarify comment in futex_requeue() Thomas Gleixner
2021-08-11 12:23 ` [patch V4 62/68] futex: Reorder sanity checks " Thomas Gleixner
2021-08-11 12:23 ` [patch V4 63/68] futex: Simplify handle_early_requeue_pi_wakeup() Thomas Gleixner
2021-08-11 12:23 ` [patch V4 64/68] futex: Prevent requeue_pi() lock nesting issue on RT Thomas Gleixner
2021-08-11 12:23 ` [patch V4 65/68] rtmutex: Prevent lockdep false positive with PI futexes Thomas Gleixner
2021-08-11 12:23 ` [patch V4 66/68] preempt: Adjust PREEMPT_LOCK_OFFSET for RT Thomas Gleixner
2021-08-11 12:23 ` [patch V4 67/68] locking/rtmutex: Implement equal priority lock stealing Thomas Gleixner
2021-08-11 12:23 ` [patch V4 68/68] locking/rtmutex: Add adaptive spinwait mechanism Thomas Gleixner
2021-08-13  8:05 ` [patch V4 69/68] locking/rt: Add missing __might_sleep() to spin/rwlocks Thomas Gleixner

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=20210811121414.423888208@linutronix.de \
    --to=tglx@linutronix.de \
    --cc=bigeasy@linutronix.de \
    --cc=boqun.feng@gmail.com \
    --cc=bristot@redhat.com \
    --cc=dave@stgolabs.net \
    --cc=efault@gmx.de \
    --cc=juri.lelli@redhat.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=longman@redhat.com \
    --cc=mingo@kernel.org \
    --cc=peterz@infradead.org \
    --cc=rostedt@goodmis.org \
    --cc=will@kernel.org \
    --subject='Re: [patch V4 05/68] sched: Rework the __schedule() preempt argument' \
    /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

This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).