Merge tag 'sched-core-2020-12-14' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull scheduler updates from Thomas Gleixner:

 - migrate_disable/enable() support which originates from the RT tree
   and is now a prerequisite for the new preemptible kmap_local() API
   which aims to replace kmap_atomic().

 - A fair amount of topology and NUMA related improvements

 - Improvements for the frequency invariant calculations

 - Enhanced robustness for the global CPU priority tracking and decision
   making

 - The usual small fixes and enhancements all over the place

* tag 'sched-core-2020-12-14' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (61 commits)
  sched/fair: Trivial correction of the newidle_balance() comment
  sched/fair: Clear SMT siblings after determining the core is not idle
  sched: Fix kernel-doc markup
  x86: Print ratio freq_max/freq_base used in frequency invariance calculations
  x86, sched: Use midpoint of max_boost and max_P for frequency invariance on AMD EPYC
  x86, sched: Calculate frequency invariance for AMD systems
  irq_work: Optimize irq_work_single()
  smp: Cleanup smp_call_function*()
  irq_work: Cleanup
  sched: Limit the amount of NUMA imbalance that can exist at fork time
  sched/numa: Allow a floating imbalance between NUMA nodes
  sched: Avoid unnecessary calculation of load imbalance at clone time
  sched/numa: Rename nr_running and break out the magic number
  sched: Make migrate_disable/enable() independent of RT
  sched/topology: Condition EAS enablement on FIE support
  arm64: Rebuild sched domains on invariance status changes
  sched/topology,schedutil: Wrap sched domains rebuild
  sched/uclamp: Allow to reset a task uclamp constraint value
  sched/core: Fix typos in comments
  Documentation: scheduler: fix information on arch SD flags, sched_domain and sched_debug
  ...

1 files changed, 25 insertions, 20 deletions

diff --git a/kernel/irq_work.c b/kernel/irq_work.c
index eca83965b631..e8da1e71583a 100644
--- a/kernel/irq_work.c
+++ b/kernel/irq_work.c
@@ -31,10 +31,10 @@ static bool irq_work_claim(struct irq_work *work)
 {
 	int oflags;
 
-	oflags = atomic_fetch_or(IRQ_WORK_CLAIMED | CSD_TYPE_IRQ_WORK, &work->flags);
+	oflags = atomic_fetch_or(IRQ_WORK_CLAIMED | CSD_TYPE_IRQ_WORK, &work->node.a_flags);
 	/*
 	 * If the work is already pending, no need to raise the IPI.
-	 * The pairing atomic_fetch_andnot() in irq_work_run() makes sure
+	 * The pairing smp_mb() in irq_work_single() makes sure
 	 * everything we did before is visible.
 	 */
 	if (oflags & IRQ_WORK_PENDING)
@@ -53,12 +53,12 @@ void __weak arch_irq_work_raise(void)
 static void __irq_work_queue_local(struct irq_work *work)
 {
 	/* If the work is "lazy", handle it from next tick if any */
-	if (atomic_read(&work->flags) & IRQ_WORK_LAZY) {
-		if (llist_add(&work->llnode, this_cpu_ptr(&lazy_list)) &&
+	if (atomic_read(&work->node.a_flags) & IRQ_WORK_LAZY) {
+		if (llist_add(&work->node.llist, this_cpu_ptr(&lazy_list)) &&
 		    tick_nohz_tick_stopped())
 			arch_irq_work_raise();
 	} else {
-		if (llist_add(&work->llnode, this_cpu_ptr(&raised_list)))
+		if (llist_add(&work->node.llist, this_cpu_ptr(&raised_list)))
 			arch_irq_work_raise();
 	}
 }
@@ -102,7 +102,7 @@ bool irq_work_queue_on(struct irq_work *work, int cpu)
 	if (cpu != smp_processor_id()) {
 		/* Arch remote IPI send/receive backend aren't NMI safe */
 		WARN_ON_ONCE(in_nmi());
-		__smp_call_single_queue(cpu, &work->llnode);
+		__smp_call_single_queue(cpu, &work->node.llist);
 	} else {
 		__irq_work_queue_local(work);
 	}
@@ -136,23 +136,28 @@ void irq_work_single(void *arg)
 	int flags;
 
 	/*
-	 * Clear the PENDING bit, after this point the @work
-	 * can be re-used.
-	 * Make it immediately visible so that other CPUs trying
-	 * to claim that work don't rely on us to handle their data
-	 * while we are in the middle of the func.
+	 * Clear the PENDING bit, after this point the @work can be re-used.
+	 * The PENDING bit acts as a lock, and we own it, so we can clear it
+	 * without atomic ops.
 	 */
-	flags = atomic_fetch_andnot(IRQ_WORK_PENDING, &work->flags);
+	flags = atomic_read(&work->node.a_flags);
+	flags &= ~IRQ_WORK_PENDING;
+	atomic_set(&work->node.a_flags, flags);
+
+	/*
+	 * See irq_work_claim().
+	 */
+	smp_mb();
 
-	lockdep_irq_work_enter(work);
+	lockdep_irq_work_enter(flags);
 	work->func(work);
-	lockdep_irq_work_exit(work);
+	lockdep_irq_work_exit(flags);
+
 	/*
-	 * Clear the BUSY bit and return to the free state if
-	 * no-one else claimed it meanwhile.
+	 * Clear the BUSY bit, if set, and return to the free state if no-one
+	 * else claimed it meanwhile.
 	 */
-	flags &= ~IRQ_WORK_PENDING;
-	(void)atomic_cmpxchg(&work->flags, flags, flags & ~IRQ_WORK_BUSY);
+	(void)atomic_cmpxchg(&work->node.a_flags, flags, flags & ~IRQ_WORK_BUSY);
 }
 
 static void irq_work_run_list(struct llist_head *list)
@@ -166,7 +171,7 @@ static void irq_work_run_list(struct llist_head *list)
 		return;
 
 	llnode = llist_del_all(list);
-	llist_for_each_entry_safe(work, tmp, llnode, llnode)
+	llist_for_each_entry_safe(work, tmp, llnode, node.llist)
 		irq_work_single(work);
 }
 
@@ -198,7 +203,7 @@ void irq_work_sync(struct irq_work *work)
 {
 	lockdep_assert_irqs_enabled();
 
-	while (atomic_read(&work->flags) & IRQ_WORK_BUSY)
+	while (irq_work_is_busy(work))
 		cpu_relax();
 }
 EXPORT_SYMBOL_GPL(irq_work_sync);