From c5105d764e0214bcc4c6d40d7ba231d01b2e9dda Mon Sep 17 00:00:00 2001
From: Zhenzhong Duan <zhenzhong.duan@oracle.com>
Date: Wed, 27 Nov 2019 16:37:28 +0800
Subject: sched/clock: Use static_branch_likely() with sched_clock_running

sched_clock_running is enabled early at bootup stage and never
disabled. So hint that to the compiler by using static_branch_likely()
rather than static_branch_unlikely().

The branch probability mis-annotation was introduced in the original
commit that converted the plain sched_clock_running flag to a static key:

  46457ea464f5 ("sched/clock: Use static key for sched_clock_running")

Steve further notes:

  | Looks like the confusion was the moving of the "!":
  |
  | -       if (unlikely(!sched_clock_running))
  | +       if (!static_branch_unlikely(&sched_clock_running))
  |
  | Where, it was unlikely that !sched_clock_running would be true, but
  | because the "!" was moved outside the "unlikely()" it makes the test
  | "likely()". That is, if we added an intermediate step, it would have
  | been:
  |
  |         if (!likely(sched_clock_running))
  |
  | which would have prevented the mistake that this patch fixes.

  [ mingo: Edited the changelog. ]

Signed-off-by: Zhenzhong Duan <zhenzhong.duan@oracle.com>
Reviewed-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: bsegall@google.com
Cc: dietmar.eggemann@arm.com
Cc: juri.lelli@redhat.com
Cc: mgorman@suse.de
Cc: vincent.guittot@linaro.org
Link: https://lkml.kernel.org/r/1574843848-26825-1-git-send-email-zhenzhong.duan@oracle.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 kernel/sched/clock.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/kernel/sched/clock.c b/kernel/sched/clock.c
index 1152259a4ca0..12bca64dff73 100644
--- a/kernel/sched/clock.c
+++ b/kernel/sched/clock.c
@@ -370,7 +370,7 @@ u64 sched_clock_cpu(int cpu)
 	if (sched_clock_stable())
 		return sched_clock() + __sched_clock_offset;
 
-	if (!static_branch_unlikely(&sched_clock_running))
+	if (!static_branch_likely(&sched_clock_running))
 		return sched_clock();
 
 	preempt_disable_notrace();
@@ -393,7 +393,7 @@ void sched_clock_tick(void)
 	if (sched_clock_stable())
 		return;
 
-	if (!static_branch_unlikely(&sched_clock_running))
+	if (!static_branch_likely(&sched_clock_running))
 		return;
 
 	lockdep_assert_irqs_disabled();
@@ -460,7 +460,7 @@ void __init sched_clock_init(void)
 
 u64 sched_clock_cpu(int cpu)
 {
-	if (!static_branch_unlikely(&sched_clock_running))
+	if (!static_branch_likely(&sched_clock_running))
 		return 0;
 
 	return sched_clock();
-- 
cgit v1.2.3-59-g8ed1b


From e7289c6de81c8e8991148e46c9ab43e2d23940f3 Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Tue, 15 Oct 2019 21:17:48 +0200
Subject: sched/rt, ARM: Use CONFIG_PREEMPTION

CONFIG_PREEMPTION is selected by CONFIG_PREEMPT and by CONFIG_PREEMPT_RT.
Both PREEMPT and PREEMPT_RT require the same functionality which today
depends on CONFIG_PREEMPT.

Switch the entry code, cache over to use CONFIG_PREEMPTION and add output
in show_stack() for PREEMPT_RT.

[bigeasy: +traps.c]

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Russell King <linux@armlinux.org.uk>
Cc: linux-arm-kernel@lists.infradead.org
Link: https://lore.kernel.org/r/20191015191821.11479-2-bigeasy@linutronix.de
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 arch/arm/include/asm/switch_to.h | 2 +-
 arch/arm/kernel/entry-armv.S     | 4 ++--
 arch/arm/kernel/traps.c          | 2 ++
 arch/arm/mm/cache-v7.S           | 4 ++--
 arch/arm/mm/cache-v7m.S          | 4 ++--
 5 files changed, 9 insertions(+), 7 deletions(-)

diff --git a/arch/arm/include/asm/switch_to.h b/arch/arm/include/asm/switch_to.h
index d3e937dcee4d..007d8fea7157 100644
--- a/arch/arm/include/asm/switch_to.h
+++ b/arch/arm/include/asm/switch_to.h
@@ -10,7 +10,7 @@
  * to ensure that the maintenance completes in case we migrate to another
  * CPU.
  */
-#if defined(CONFIG_PREEMPT) && defined(CONFIG_SMP) && defined(CONFIG_CPU_V7)
+#if defined(CONFIG_PREEMPTION) && defined(CONFIG_SMP) && defined(CONFIG_CPU_V7)
 #define __complete_pending_tlbi()	dsb(ish)
 #else
 #define __complete_pending_tlbi()
diff --git a/arch/arm/kernel/entry-armv.S b/arch/arm/kernel/entry-armv.S
index 858d4e541532..77f54830554c 100644
--- a/arch/arm/kernel/entry-armv.S
+++ b/arch/arm/kernel/entry-armv.S
@@ -211,7 +211,7 @@ __irq_svc:
 	svc_entry
 	irq_handler
 
-#ifdef CONFIG_PREEMPT
+#ifdef CONFIG_PREEMPTION
 	ldr	r8, [tsk, #TI_PREEMPT]		@ get preempt count
 	ldr	r0, [tsk, #TI_FLAGS]		@ get flags
 	teq	r8, #0				@ if preempt count != 0
@@ -226,7 +226,7 @@ ENDPROC(__irq_svc)
 
 	.ltorg
 
-#ifdef CONFIG_PREEMPT
+#ifdef CONFIG_PREEMPTION
 svc_preempt:
 	mov	r8, lr
 1:	bl	preempt_schedule_irq		@ irq en/disable is done inside
diff --git a/arch/arm/kernel/traps.c b/arch/arm/kernel/traps.c
index c053abd1fb53..abb7dd7e656f 100644
--- a/arch/arm/kernel/traps.c
+++ b/arch/arm/kernel/traps.c
@@ -248,6 +248,8 @@ void show_stack(struct task_struct *tsk, unsigned long *sp)
 
 #ifdef CONFIG_PREEMPT
 #define S_PREEMPT " PREEMPT"
+#elif defined(CONFIG_PREEMPT_RT)
+#define S_PREEMPT " PREEMPT_RT"
 #else
 #define S_PREEMPT ""
 #endif
diff --git a/arch/arm/mm/cache-v7.S b/arch/arm/mm/cache-v7.S
index 0ee8fc4b4672..dc8f152f3556 100644
--- a/arch/arm/mm/cache-v7.S
+++ b/arch/arm/mm/cache-v7.S
@@ -135,13 +135,13 @@ flush_levels:
 	and	r1, r1, #7			@ mask of the bits for current cache only
 	cmp	r1, #2				@ see what cache we have at this level
 	blt	skip				@ skip if no cache, or just i-cache
-#ifdef CONFIG_PREEMPT
+#ifdef CONFIG_PREEMPTION
 	save_and_disable_irqs_notrace r9	@ make cssr&csidr read atomic
 #endif
 	mcr	p15, 2, r10, c0, c0, 0		@ select current cache level in cssr
 	isb					@ isb to sych the new cssr&csidr
 	mrc	p15, 1, r1, c0, c0, 0		@ read the new csidr
-#ifdef CONFIG_PREEMPT
+#ifdef CONFIG_PREEMPTION
 	restore_irqs_notrace r9
 #endif
 	and	r2, r1, #7			@ extract the length of the cache lines
diff --git a/arch/arm/mm/cache-v7m.S b/arch/arm/mm/cache-v7m.S
index a0035c426ce6..1bc3a0a50753 100644
--- a/arch/arm/mm/cache-v7m.S
+++ b/arch/arm/mm/cache-v7m.S
@@ -183,13 +183,13 @@ flush_levels:
 	and	r1, r1, #7			@ mask of the bits for current cache only
 	cmp	r1, #2				@ see what cache we have at this level
 	blt	skip				@ skip if no cache, or just i-cache
-#ifdef CONFIG_PREEMPT
+#ifdef CONFIG_PREEMPTION
 	save_and_disable_irqs_notrace r9	@ make cssr&csidr read atomic
 #endif
 	write_csselr r10, r1			@ set current cache level
 	isb					@ isb to sych the new cssr&csidr
 	read_ccsidr r1				@ read the new csidr
-#ifdef CONFIG_PREEMPT
+#ifdef CONFIG_PREEMPTION
 	restore_irqs_notrace r9
 #endif
 	and	r2, r1, #7			@ extract the length of the cache lines
-- 
cgit v1.2.3-59-g8ed1b


From 7ef858dad9fa6cabfe3b78997c3114cd641de6e3 Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Tue, 15 Oct 2019 21:17:49 +0200
Subject: sched/rt, arm64: Use CONFIG_PREEMPTION

CONFIG_PREEMPTION is selected by CONFIG_PREEMPT and by CONFIG_PREEMPT_RT.
Both PREEMPT and PREEMPT_RT require the same functionality which today
depends on CONFIG_PREEMPT.

Switch the Kconfig dependency, entry code and preemption handling over
to use CONFIG_PREEMPTION. Add PREEMPT_RT output in show_stack().

[bigeasy: +traps.c, Kconfig]

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Will Deacon <will@kernel.org>
Cc: linux-arm-kernel@lists.infradead.org
Link: https://lore.kernel.org/r/20191015191821.11479-3-bigeasy@linutronix.de
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 arch/arm64/Kconfig                 | 52 +++++++++++++++++++-------------------
 arch/arm64/crypto/sha256-glue.c    |  2 +-
 arch/arm64/include/asm/assembler.h |  6 ++---
 arch/arm64/include/asm/preempt.h   |  4 +--
 arch/arm64/kernel/entry.S          |  2 +-
 arch/arm64/kernel/traps.c          |  3 +++
 6 files changed, 36 insertions(+), 33 deletions(-)

diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index b1b4476ddb83..3ab05857ca8f 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -34,32 +34,32 @@ config ARM64
 	select ARCH_HAS_TEARDOWN_DMA_OPS if IOMMU_SUPPORT
 	select ARCH_HAS_TICK_BROADCAST if GENERIC_CLOCKEVENTS_BROADCAST
 	select ARCH_HAVE_NMI_SAFE_CMPXCHG
-	select ARCH_INLINE_READ_LOCK if !PREEMPT
-	select ARCH_INLINE_READ_LOCK_BH if !PREEMPT
-	select ARCH_INLINE_READ_LOCK_IRQ if !PREEMPT
-	select ARCH_INLINE_READ_LOCK_IRQSAVE if !PREEMPT
-	select ARCH_INLINE_READ_UNLOCK if !PREEMPT
-	select ARCH_INLINE_READ_UNLOCK_BH if !PREEMPT
-	select ARCH_INLINE_READ_UNLOCK_IRQ if !PREEMPT
-	select ARCH_INLINE_READ_UNLOCK_IRQRESTORE if !PREEMPT
-	select ARCH_INLINE_WRITE_LOCK if !PREEMPT
-	select ARCH_INLINE_WRITE_LOCK_BH if !PREEMPT
-	select ARCH_INLINE_WRITE_LOCK_IRQ if !PREEMPT
-	select ARCH_INLINE_WRITE_LOCK_IRQSAVE if !PREEMPT
-	select ARCH_INLINE_WRITE_UNLOCK if !PREEMPT
-	select ARCH_INLINE_WRITE_UNLOCK_BH if !PREEMPT
-	select ARCH_INLINE_WRITE_UNLOCK_IRQ if !PREEMPT
-	select ARCH_INLINE_WRITE_UNLOCK_IRQRESTORE if !PREEMPT
-	select ARCH_INLINE_SPIN_TRYLOCK if !PREEMPT
-	select ARCH_INLINE_SPIN_TRYLOCK_BH if !PREEMPT
-	select ARCH_INLINE_SPIN_LOCK if !PREEMPT
-	select ARCH_INLINE_SPIN_LOCK_BH if !PREEMPT
-	select ARCH_INLINE_SPIN_LOCK_IRQ if !PREEMPT
-	select ARCH_INLINE_SPIN_LOCK_IRQSAVE if !PREEMPT
-	select ARCH_INLINE_SPIN_UNLOCK if !PREEMPT
-	select ARCH_INLINE_SPIN_UNLOCK_BH if !PREEMPT
-	select ARCH_INLINE_SPIN_UNLOCK_IRQ if !PREEMPT
-	select ARCH_INLINE_SPIN_UNLOCK_IRQRESTORE if !PREEMPT
+	select ARCH_INLINE_READ_LOCK if !PREEMPTION
+	select ARCH_INLINE_READ_LOCK_BH if !PREEMPTION
+	select ARCH_INLINE_READ_LOCK_IRQ if !PREEMPTION
+	select ARCH_INLINE_READ_LOCK_IRQSAVE if !PREEMPTION
+	select ARCH_INLINE_READ_UNLOCK if !PREEMPTION
+	select ARCH_INLINE_READ_UNLOCK_BH if !PREEMPTION
+	select ARCH_INLINE_READ_UNLOCK_IRQ if !PREEMPTION
+	select ARCH_INLINE_READ_UNLOCK_IRQRESTORE if !PREEMPTION
+	select ARCH_INLINE_WRITE_LOCK if !PREEMPTION
+	select ARCH_INLINE_WRITE_LOCK_BH if !PREEMPTION
+	select ARCH_INLINE_WRITE_LOCK_IRQ if !PREEMPTION
+	select ARCH_INLINE_WRITE_LOCK_IRQSAVE if !PREEMPTION
+	select ARCH_INLINE_WRITE_UNLOCK if !PREEMPTION
+	select ARCH_INLINE_WRITE_UNLOCK_BH if !PREEMPTION
+	select ARCH_INLINE_WRITE_UNLOCK_IRQ if !PREEMPTION
+	select ARCH_INLINE_WRITE_UNLOCK_IRQRESTORE if !PREEMPTION
+	select ARCH_INLINE_SPIN_TRYLOCK if !PREEMPTION
+	select ARCH_INLINE_SPIN_TRYLOCK_BH if !PREEMPTION
+	select ARCH_INLINE_SPIN_LOCK if !PREEMPTION
+	select ARCH_INLINE_SPIN_LOCK_BH if !PREEMPTION
+	select ARCH_INLINE_SPIN_LOCK_IRQ if !PREEMPTION
+	select ARCH_INLINE_SPIN_LOCK_IRQSAVE if !PREEMPTION
+	select ARCH_INLINE_SPIN_UNLOCK if !PREEMPTION
+	select ARCH_INLINE_SPIN_UNLOCK_BH if !PREEMPTION
+	select ARCH_INLINE_SPIN_UNLOCK_IRQ if !PREEMPTION
+	select ARCH_INLINE_SPIN_UNLOCK_IRQRESTORE if !PREEMPTION
 	select ARCH_KEEP_MEMBLOCK
 	select ARCH_USE_CMPXCHG_LOCKREF
 	select ARCH_USE_QUEUED_RWLOCKS
diff --git a/arch/arm64/crypto/sha256-glue.c b/arch/arm64/crypto/sha256-glue.c
index e273faca924f..999da59f03a9 100644
--- a/arch/arm64/crypto/sha256-glue.c
+++ b/arch/arm64/crypto/sha256-glue.c
@@ -97,7 +97,7 @@ static int sha256_update_neon(struct shash_desc *desc, const u8 *data,
 		 * input when running on a preemptible kernel, but process the
 		 * data block by block instead.
 		 */
-		if (IS_ENABLED(CONFIG_PREEMPT) &&
+		if (IS_ENABLED(CONFIG_PREEMPTION) &&
 		    chunk + sctx->count % SHA256_BLOCK_SIZE > SHA256_BLOCK_SIZE)
 			chunk = SHA256_BLOCK_SIZE -
 				sctx->count % SHA256_BLOCK_SIZE;
diff --git a/arch/arm64/include/asm/assembler.h b/arch/arm64/include/asm/assembler.h
index b8cf7c85ffa2..2cc0dd8bd9f7 100644
--- a/arch/arm64/include/asm/assembler.h
+++ b/arch/arm64/include/asm/assembler.h
@@ -699,8 +699,8 @@ USER(\label, ic	ivau, \tmp2)			// invalidate I line PoU
  * where <label> is optional, and marks the point where execution will resume
  * after a yield has been performed. If omitted, execution resumes right after
  * the endif_yield_neon invocation. Note that the entire sequence, including
- * the provided patchup code, will be omitted from the image if CONFIG_PREEMPT
- * is not defined.
+ * the provided patchup code, will be omitted from the image if
+ * CONFIG_PREEMPTION is not defined.
  *
  * As a convenience, in the case where no patchup code is required, the above
  * sequence may be abbreviated to
@@ -728,7 +728,7 @@ USER(\label, ic	ivau, \tmp2)			// invalidate I line PoU
 	.endm
 
 	.macro		if_will_cond_yield_neon
-#ifdef CONFIG_PREEMPT
+#ifdef CONFIG_PREEMPTION
 	get_current_task	x0
 	ldr		x0, [x0, #TSK_TI_PREEMPT]
 	sub		x0, x0, #PREEMPT_DISABLE_OFFSET
diff --git a/arch/arm64/include/asm/preempt.h b/arch/arm64/include/asm/preempt.h
index d49951647014..80e946b2abee 100644
--- a/arch/arm64/include/asm/preempt.h
+++ b/arch/arm64/include/asm/preempt.h
@@ -79,11 +79,11 @@ static inline bool should_resched(int preempt_offset)
 	return pc == preempt_offset;
 }
 
-#ifdef CONFIG_PREEMPT
+#ifdef CONFIG_PREEMPTION
 void preempt_schedule(void);
 #define __preempt_schedule() preempt_schedule()
 void preempt_schedule_notrace(void);
 #define __preempt_schedule_notrace() preempt_schedule_notrace()
-#endif /* CONFIG_PREEMPT */
+#endif /* CONFIG_PREEMPTION */
 
 #endif /* __ASM_PREEMPT_H */
diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S
index 583f71abbe98..6fcb62df2b71 100644
--- a/arch/arm64/kernel/entry.S
+++ b/arch/arm64/kernel/entry.S
@@ -604,7 +604,7 @@ el1_irq:
 
 	irq_handler
 
-#ifdef CONFIG_PREEMPT
+#ifdef CONFIG_PREEMPTION
 	ldr	x24, [tsk, #TSK_TI_PREEMPT]	// get preempt count
 alternative_if ARM64_HAS_IRQ_PRIO_MASKING
 	/*
diff --git a/arch/arm64/kernel/traps.c b/arch/arm64/kernel/traps.c
index 73caf35c2262..cf402be5c573 100644
--- a/arch/arm64/kernel/traps.c
+++ b/arch/arm64/kernel/traps.c
@@ -144,9 +144,12 @@ void show_stack(struct task_struct *tsk, unsigned long *sp)
 
 #ifdef CONFIG_PREEMPT
 #define S_PREEMPT " PREEMPT"
+#elif defined(CONFIG_PREEMPT_RT)
+#define S_PREEMPT " PREEMPT_RT"
 #else
 #define S_PREEMPT ""
 #endif
+
 #define S_SMP " SMP"
 
 static int __die(const char *str, int err, struct pt_regs *regs)
-- 
cgit v1.2.3-59-g8ed1b


From fdc5569eaba997852e0bfb57d11af496e4c1fa9a Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Thu, 24 Oct 2019 18:04:58 +0200
Subject: sched/rt, powerpc: Use CONFIG_PREEMPTION

CONFIG_PREEMPTION is selected by CONFIG_PREEMPT and by CONFIG_PREEMPT_RT.
Both PREEMPT and PREEMPT_RT require the same functionality which today
depends on CONFIG_PREEMPT.

Switch the entry code over to use CONFIG_PREEMPTION.

[bigeasy: +Kconfig]

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: Michael Ellerman <mpe@ellerman.id.au>
Cc: Christophe Leroy <christophe.leroy@c-s.fr>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: linuxppc-dev@lists.ozlabs.org
Link: https://lore.kernel.org/r/20191024160458.vlnf3wlcyjl2ich7@linutronix.de
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 arch/powerpc/Kconfig           | 2 +-
 arch/powerpc/kernel/entry_32.S | 4 ++--
 arch/powerpc/kernel/entry_64.S | 4 ++--
 3 files changed, 5 insertions(+), 5 deletions(-)

diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index e446bb5b3f8d..c781170e9923 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -106,7 +106,7 @@ config LOCKDEP_SUPPORT
 config GENERIC_LOCKBREAK
 	bool
 	default y
-	depends on SMP && PREEMPT
+	depends on SMP && PREEMPTION
 
 config GENERIC_HWEIGHT
 	bool
diff --git a/arch/powerpc/kernel/entry_32.S b/arch/powerpc/kernel/entry_32.S
index d60908ea37fb..e1a4c39b83b8 100644
--- a/arch/powerpc/kernel/entry_32.S
+++ b/arch/powerpc/kernel/entry_32.S
@@ -897,7 +897,7 @@ resume_kernel:
 	bne-	0b
 1:
 
-#ifdef CONFIG_PREEMPT
+#ifdef CONFIG_PREEMPTION
 	/* check current_thread_info->preempt_count */
 	lwz	r0,TI_PREEMPT(r2)
 	cmpwi	0,r0,0		/* if non-zero, just restore regs and return */
@@ -921,7 +921,7 @@ resume_kernel:
 	 */
 	bl	trace_hardirqs_on
 #endif
-#endif /* CONFIG_PREEMPT */
+#endif /* CONFIG_PREEMPTION */
 restore_kuap:
 	kuap_restore r1, r2, r9, r10, r0
 
diff --git a/arch/powerpc/kernel/entry_64.S b/arch/powerpc/kernel/entry_64.S
index 3fd3ef352e3f..a9a1d3cdb523 100644
--- a/arch/powerpc/kernel/entry_64.S
+++ b/arch/powerpc/kernel/entry_64.S
@@ -846,7 +846,7 @@ resume_kernel:
 	bne-	0b
 1:
 
-#ifdef CONFIG_PREEMPT
+#ifdef CONFIG_PREEMPTION
 	/* Check if we need to preempt */
 	andi.	r0,r4,_TIF_NEED_RESCHED
 	beq+	restore
@@ -877,7 +877,7 @@ resume_kernel:
 	li	r10,MSR_RI
 	mtmsrd	r10,1		  /* Update machine state */
 #endif /* CONFIG_PPC_BOOK3E */
-#endif /* CONFIG_PREEMPT */
+#endif /* CONFIG_PREEMPTION */
 
 	.globl	fast_exc_return_irq
 fast_exc_return_irq:
-- 
cgit v1.2.3-59-g8ed1b


From 916591722c7543570843b54d5896121146b498f5 Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Tue, 15 Oct 2019 21:17:51 +0200
Subject: sched/rt, ARC: Use CONFIG_PREEMPTION

CONFIG_PREEMPTION is selected by CONFIG_PREEMPT and by CONFIG_PREEMPT_RT.
Both PREEMPT and PREEMPT_RT require the same functionality which today
depends on CONFIG_PREEMPT.

Switch the entry code over to use CONFIG_PREEMPTION.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Vineet Gupta <vgupta@synopsys.com>
Cc: linux-snps-arc@lists.infradead.org
Link: https://lore.kernel.org/r/20191015191821.11479-5-bigeasy@linutronix.de
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 arch/arc/kernel/entry.S | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/arch/arc/kernel/entry.S b/arch/arc/kernel/entry.S
index 72be01270e24..1f6bb184a44d 100644
--- a/arch/arc/kernel/entry.S
+++ b/arch/arc/kernel/entry.S
@@ -337,11 +337,11 @@ resume_user_mode_begin:
 resume_kernel_mode:
 
 	; Disable Interrupts from this point on
-	; CONFIG_PREEMPT: This is a must for preempt_schedule_irq()
-	; !CONFIG_PREEMPT: To ensure restore_regs is intr safe
+	; CONFIG_PREEMPTION: This is a must for preempt_schedule_irq()
+	; !CONFIG_PREEMPTION: To ensure restore_regs is intr safe
 	IRQ_DISABLE	r9
 
-#ifdef CONFIG_PREEMPT
+#ifdef CONFIG_PREEMPTION
 
 	; Can't preempt if preemption disabled
 	GET_CURR_THR_INFO_FROM_SP   r10
-- 
cgit v1.2.3-59-g8ed1b


From 51466979c754d11e1e8da0e46a66218ffc7226ee Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Tue, 15 Oct 2019 21:17:52 +0200
Subject: sched/rt, c6x: Use CONFIG_PREEMPTION

CONFIG_PREEMPTION is selected by CONFIG_PREEMPT and by CONFIG_PREEMPT_RT.
Both PREEMPT and PREEMPT_RT require the same functionality which today
depends on CONFIG_PREEMPT.

Switch the entry code over to use CONFIG_PREEMPTION.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: Aurelien Jacquiot <jacquiot.aurelien@gmail.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mark Salter <msalter@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: linux-c6x-dev@linux-c6x.org
Link: https://lore.kernel.org/r/20191015191821.11479-6-bigeasy@linutronix.de
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 arch/c6x/kernel/entry.S | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/arch/c6x/kernel/entry.S b/arch/c6x/kernel/entry.S
index 4332a10aec6c..fb154d19625b 100644
--- a/arch/c6x/kernel/entry.S
+++ b/arch/c6x/kernel/entry.S
@@ -18,7 +18,7 @@
 #define DP	B14
 #define SP	B15
 
-#ifndef CONFIG_PREEMPT
+#ifndef CONFIG_PREEMPTION
 #define resume_kernel restore_all
 #endif
 
@@ -287,7 +287,7 @@ work_notifysig:
 	;; is a little bit different
 	;;
 ENTRY(ret_from_exception)
-#ifdef CONFIG_PREEMPT
+#ifdef CONFIG_PREEMPTION
 	MASK_INT B2
 #endif
 
@@ -557,7 +557,7 @@ ENDPROC(_nmi_handler)
 	;;
 	;; Jump to schedule() then return to ret_from_isr
 	;;
-#ifdef	CONFIG_PREEMPT
+#ifdef	CONFIG_PREEMPTION
 resume_kernel:
 	GET_THREAD_INFO A12
 	LDW	.D1T1	*+A12(THREAD_INFO_PREEMPT_COUNT),A1
@@ -582,7 +582,7 @@ preempt_schedule:
 	B	.S2	preempt_schedule_irq
 #endif
 	ADDKPC	.S2	preempt_schedule,B3,4
-#endif /* CONFIG_PREEMPT */
+#endif /* CONFIG_PREEMPTION */
 
 ENTRY(enable_exception)
 	DINT
-- 
cgit v1.2.3-59-g8ed1b


From 365a795a13326df11a5114d2b6067ca2a6d53364 Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Tue, 15 Oct 2019 21:17:53 +0200
Subject: sched/rt, csky: Use CONFIG_PREEMPTION

CONFIG_PREEMPTION is selected by CONFIG_PREEMPT and by CONFIG_PREEMPT_RT.
Both PREEMPT and PREEMPT_RT require the same functionality which today
depends on CONFIG_PREEMPT.

Switch the entry code over to use CONFIG_PREEMPTION.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: Guo Ren <guoren@kernel.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: https://lore.kernel.org/r/20191015191821.11479-7-bigeasy@linutronix.de
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 arch/csky/kernel/entry.S | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/arch/csky/kernel/entry.S b/arch/csky/kernel/entry.S
index a7a5b67df898..007706328000 100644
--- a/arch/csky/kernel/entry.S
+++ b/arch/csky/kernel/entry.S
@@ -277,7 +277,7 @@ ENTRY(csky_irq)
 	zero_fp
 	psrset	ee
 
-#ifdef CONFIG_PREEMPT
+#ifdef CONFIG_PREEMPTION
 	mov	r9, sp			/* Get current stack  pointer */
 	bmaski	r10, THREAD_SHIFT
 	andn	r9, r10			/* Get thread_info */
@@ -294,7 +294,7 @@ ENTRY(csky_irq)
 	mov	a0, sp
 	jbsr	csky_do_IRQ
 
-#ifdef CONFIG_PREEMPT
+#ifdef CONFIG_PREEMPTION
 	subi	r12, 1
 	stw	r12, (r9, TINFO_PREEMPT)
 	cmpnei	r12, 0
-- 
cgit v1.2.3-59-g8ed1b


From 7462b759b1c2fc3848fe54f71bf553f8f4e6d323 Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Tue, 15 Oct 2019 21:17:54 +0200
Subject: sched/rt, h8300: Use CONFIG_PREEMPTION

CONFIG_PREEMPTION is selected by CONFIG_PREEMPT and by CONFIG_PREEMPT_RT.
Both PREEMPT and PREEMPT_RT require the same functionality which today
depends on CONFIG_PREEMPT.

Switch the entry code over to use CONFIG_PREEMPTION.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Yoshinori Sato <ysato@users.sourceforge.jp>
Cc: uclinux-h8-devel@lists.sourceforge.jp
Link: https://lore.kernel.org/r/20191015191821.11479-8-bigeasy@linutronix.de
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 arch/h8300/kernel/entry.S | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/arch/h8300/kernel/entry.S b/arch/h8300/kernel/entry.S
index 4ade5f8299ba..c6e289b5f1f2 100644
--- a/arch/h8300/kernel/entry.S
+++ b/arch/h8300/kernel/entry.S
@@ -284,12 +284,12 @@ badsys:
 	mov.l	er0,@(LER0:16,sp)
 	bra	resume_userspace
 
-#if !defined(CONFIG_PREEMPT)
+#if !defined(CONFIG_PREEMPTION)
 #define resume_kernel restore_all
 #endif
 
 ret_from_exception:
-#if defined(CONFIG_PREEMPT)
+#if defined(CONFIG_PREEMPTION)
 	orc	#0xc0,ccr
 #endif
 ret_from_interrupt:
@@ -319,7 +319,7 @@ work_resched:
 restore_all:
 	RESTORE_ALL			/* Does RTE */
 
-#if defined(CONFIG_PREEMPT)
+#if defined(CONFIG_PREEMPTION)
 resume_kernel:
 	mov.l	@(TI_PRE_COUNT:16,er4),er0
 	bne	restore_all:8
-- 
cgit v1.2.3-59-g8ed1b


From 143cd41f50e0c074fbdb06c3ab75a45e3076b5a6 Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Tue, 15 Oct 2019 21:17:55 +0200
Subject: sched/rt, hexagon: Use CONFIG_PREEMPTION

CONFIG_PREEMPTION is selected by CONFIG_PREEMPT and by CONFIG_PREEMPT_RT.
Both PREEMPT and PREEMPT_RT require the same functionality which today
depends on CONFIG_PREEMPT.

Switch the entry code over to use CONFIG_PREEMPTION.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: Brian Cain <bcain@codeaurora.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: linux-hexagon@vger.kernel.org
Link: https://lore.kernel.org/r/20191015191821.11479-9-bigeasy@linutronix.de
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 arch/hexagon/kernel/vm_entry.S | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/arch/hexagon/kernel/vm_entry.S b/arch/hexagon/kernel/vm_entry.S
index 12242c27e2df..65a1ea0eed2f 100644
--- a/arch/hexagon/kernel/vm_entry.S
+++ b/arch/hexagon/kernel/vm_entry.S
@@ -265,12 +265,12 @@ event_dispatch:
 	 * should be in the designated register (usually R19)
 	 *
 	 * If we were in kernel mode, we don't need to check scheduler
-	 * or signals if CONFIG_PREEMPT is not set.  If set, then it has
+	 * or signals if CONFIG_PREEMPTION is not set.  If set, then it has
 	 * to jump to a need_resched kind of block.
-	 * BTW, CONFIG_PREEMPT is not supported yet.
+	 * BTW, CONFIG_PREEMPTION is not supported yet.
 	 */
 
-#ifdef CONFIG_PREEMPT
+#ifdef CONFIG_PREEMPTION
 	R0 = #VM_INT_DISABLE
 	trap1(#HVM_TRAP1_VMSETIE)
 #endif
-- 
cgit v1.2.3-59-g8ed1b


From b9b75e53b2fb040bc74a750fb27bbfa80059b3fe Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Tue, 15 Oct 2019 21:17:56 +0200
Subject: sched/rt, ia64: Use CONFIG_PREEMPTION

CONFIG_PREEMPTION is selected by CONFIG_PREEMPT and by CONFIG_PREEMPT_RT.
Both PREEMPT and PREEMPT_RT require the same functionality which today
depends on CONFIG_PREEMPT.

Switch the entry code and kprobes over to use CONFIG_PREEMPTION.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: Fenghua Yu <fenghua.yu@intel.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Tony Luck <tony.luck@intel.com>
Cc: linux-ia64@vger.kernel.org
Link: https://lore.kernel.org/r/20191015191821.11479-10-bigeasy@linutronix.de
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 arch/ia64/kernel/entry.S   | 12 ++++++------
 arch/ia64/kernel/kprobes.c |  2 +-
 2 files changed, 7 insertions(+), 7 deletions(-)

diff --git a/arch/ia64/kernel/entry.S b/arch/ia64/kernel/entry.S
index a9992be5718b..2ac926331500 100644
--- a/arch/ia64/kernel/entry.S
+++ b/arch/ia64/kernel/entry.S
@@ -670,12 +670,12 @@ GLOBAL_ENTRY(ia64_leave_syscall)
 	 *
 	 * p6 controls whether current_thread_info()->flags needs to be check for
 	 * extra work.  We always check for extra work when returning to user-level.
-	 * With CONFIG_PREEMPT, we also check for extra work when the preempt_count
+	 * With CONFIG_PREEMPTION, we also check for extra work when the preempt_count
 	 * is 0.  After extra work processing has been completed, execution
 	 * resumes at ia64_work_processed_syscall with p6 set to 1 if the extra-work-check
 	 * needs to be redone.
 	 */
-#ifdef CONFIG_PREEMPT
+#ifdef CONFIG_PREEMPTION
 	RSM_PSR_I(p0, r2, r18)			// disable interrupts
 	cmp.eq pLvSys,p0=r0,r0			// pLvSys=1: leave from syscall
 (pKStk) adds r20=TI_PRE_COUNT+IA64_TASK_SIZE,r13
@@ -685,7 +685,7 @@ GLOBAL_ENTRY(ia64_leave_syscall)
 (pUStk)	mov r21=0			// r21 <- 0
 	;;
 	cmp.eq p6,p0=r21,r0		// p6 <- pUStk || (preempt_count == 0)
-#else /* !CONFIG_PREEMPT */
+#else /* !CONFIG_PREEMPTION */
 	RSM_PSR_I(pUStk, r2, r18)
 	cmp.eq pLvSys,p0=r0,r0		// pLvSys=1: leave from syscall
 (pUStk)	cmp.eq.unc p6,p0=r0,r0		// p6 <- pUStk
@@ -814,12 +814,12 @@ GLOBAL_ENTRY(ia64_leave_kernel)
 	 *
 	 * p6 controls whether current_thread_info()->flags needs to be check for
 	 * extra work.  We always check for extra work when returning to user-level.
-	 * With CONFIG_PREEMPT, we also check for extra work when the preempt_count
+	 * With CONFIG_PREEMPTION, we also check for extra work when the preempt_count
 	 * is 0.  After extra work processing has been completed, execution
 	 * resumes at .work_processed_syscall with p6 set to 1 if the extra-work-check
 	 * needs to be redone.
 	 */
-#ifdef CONFIG_PREEMPT
+#ifdef CONFIG_PREEMPTION
 	RSM_PSR_I(p0, r17, r31)			// disable interrupts
 	cmp.eq p0,pLvSys=r0,r0			// pLvSys=0: leave from kernel
 (pKStk)	adds r20=TI_PRE_COUNT+IA64_TASK_SIZE,r13
@@ -1120,7 +1120,7 @@ skip_rbs_switch:
 
 	/*
 	 * On entry:
-	 *	r20 = &current->thread_info->pre_count (if CONFIG_PREEMPT)
+	 *	r20 = &current->thread_info->pre_count (if CONFIG_PREEMPTION)
 	 *	r31 = current->thread_info->flags
 	 * On exit:
 	 *	p6 = TRUE if work-pending-check needs to be redone
diff --git a/arch/ia64/kernel/kprobes.c b/arch/ia64/kernel/kprobes.c
index b8356edbde65..a6d6a0556f08 100644
--- a/arch/ia64/kernel/kprobes.c
+++ b/arch/ia64/kernel/kprobes.c
@@ -841,7 +841,7 @@ static int __kprobes pre_kprobes_handler(struct die_args *args)
 		return 1;
 	}
 
-#if !defined(CONFIG_PREEMPT)
+#if !defined(CONFIG_PREEMPTION)
 	if (p->ainsn.inst_flag == INST_FLAG_BOOSTABLE && !p->post_handler) {
 		/* Boost up -- we can execute copied instructions directly */
 		ia64_psr(regs)->ri = p->ainsn.slot;
-- 
cgit v1.2.3-59-g8ed1b


From 18803733bd67b8e8f608a0bbb491e1491dcce01e Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Tue, 15 Oct 2019 21:17:58 +0200
Subject: sched/rt, microblaze: Use CONFIG_PREEMPTION

CONFIG_PREEMPTION is selected by CONFIG_PREEMPT and by CONFIG_PREEMPT_RT.
Both PREEMPT and PREEMPT_RT require the same functionality which today
depends on CONFIG_PREEMPT.

Switch the entry code over to use CONFIG_PREEMPTION.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Michal Simek <monstr@monstr.eu>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: https://lore.kernel.org/r/20191015191821.11479-12-bigeasy@linutronix.de
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 arch/microblaze/kernel/entry.S | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/microblaze/kernel/entry.S b/arch/microblaze/kernel/entry.S
index de7083bd1d24..f6ded356394a 100644
--- a/arch/microblaze/kernel/entry.S
+++ b/arch/microblaze/kernel/entry.S
@@ -728,7 +728,7 @@ no_intr_resched:
 	bri	6f;
 /* MS: Return to kernel state. */
 2:
-#ifdef CONFIG_PREEMPT
+#ifdef CONFIG_PREEMPTION
 	lwi	r11, CURRENT_TASK, TS_THREAD_INFO;
 	/* MS: get preempt_count from thread info */
 	lwi	r5, r11, TI_PREEMPT_COUNT;
-- 
cgit v1.2.3-59-g8ed1b


From 098fa51b1d054fbc9ec1286a3c74231aebd6ff15 Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Tue, 15 Oct 2019 21:17:59 +0200
Subject: sched/rt, MIPS: Use CONFIG_PREEMPTION

CONFIG_PREEMPTION is selected by CONFIG_PREEMPT and by CONFIG_PREEMPT_RT.
Both PREEMPT and PREEMPT_RT require the same functionality which today
depends on CONFIG_PREEMPT.

Switch the entry code and assmebly macros over to use CONFIG_PREEMPTION.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: James Hogan <jhogan@kernel.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Paul Burton <paul.burton@mips.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Ralf Baechle <ralf@linux-mips.org>
Cc: linux-mips@vger.kernel.org
Link: https://lore.kernel.org/r/20191015191821.11479-13-bigeasy@linutronix.de
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 arch/mips/include/asm/asmmacro.h | 4 ++--
 arch/mips/kernel/entry.S         | 6 +++---
 2 files changed, 5 insertions(+), 5 deletions(-)

diff --git a/arch/mips/include/asm/asmmacro.h b/arch/mips/include/asm/asmmacro.h
index feb069cbf44e..655f40ddb6d1 100644
--- a/arch/mips/include/asm/asmmacro.h
+++ b/arch/mips/include/asm/asmmacro.h
@@ -63,7 +63,7 @@
 	.endm
 
 	.macro	local_irq_disable reg=t0
-#ifdef CONFIG_PREEMPT
+#ifdef CONFIG_PREEMPTION
 	lw      \reg, TI_PRE_COUNT($28)
 	addi    \reg, \reg, 1
 	sw      \reg, TI_PRE_COUNT($28)
@@ -73,7 +73,7 @@
 	xori	\reg, \reg, 1
 	mtc0	\reg, CP0_STATUS
 	irq_disable_hazard
-#ifdef CONFIG_PREEMPT
+#ifdef CONFIG_PREEMPTION
 	lw      \reg, TI_PRE_COUNT($28)
 	addi    \reg, \reg, -1
 	sw      \reg, TI_PRE_COUNT($28)
diff --git a/arch/mips/kernel/entry.S b/arch/mips/kernel/entry.S
index 5469d43b6966..4849a48afc0f 100644
--- a/arch/mips/kernel/entry.S
+++ b/arch/mips/kernel/entry.S
@@ -19,7 +19,7 @@
 #include <asm/thread_info.h>
 #include <asm/war.h>
 
-#ifndef CONFIG_PREEMPT
+#ifndef CONFIG_PREEMPTION
 #define resume_kernel	restore_all
 #else
 #define __ret_from_irq	ret_from_exception
@@ -27,7 +27,7 @@
 
 	.text
 	.align	5
-#ifndef CONFIG_PREEMPT
+#ifndef CONFIG_PREEMPTION
 FEXPORT(ret_from_exception)
 	local_irq_disable			# preempt stop
 	b	__ret_from_irq
@@ -53,7 +53,7 @@ resume_userspace:
 	bnez	t0, work_pending
 	j	restore_all
 
-#ifdef CONFIG_PREEMPT
+#ifdef CONFIG_PREEMPTION
 resume_kernel:
 	local_irq_disable
 	lw	t0, TI_PRE_COUNT($28)
-- 
cgit v1.2.3-59-g8ed1b


From 10c1537b32e7667842ccefbc2970153784837c27 Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Tue, 15 Oct 2019 21:18:00 +0200
Subject: sched/rt, nds32: Use CONFIG_PREEMPTION

CONFIG_PREEMPTION is selected by CONFIG_PREEMPT and by CONFIG_PREEMPT_RT.
Both PREEMPT and PREEMPT_RT require the same functionality which today
depends on CONFIG_PREEMPT.

Switch the ex-exit code over to use CONFIG_PREEMPTION.

[bigeasy: +Kconfig]

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: Greentime Hu <green.hu@gmail.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Vincent Chen <deanbo422@gmail.com>
Link: https://lore.kernel.org/r/20191015191821.11479-14-bigeasy@linutronix.de
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 arch/nds32/Kconfig          | 2 +-
 arch/nds32/kernel/ex-exit.S | 4 ++--
 2 files changed, 3 insertions(+), 3 deletions(-)

diff --git a/arch/nds32/Kconfig b/arch/nds32/Kconfig
index 12c06a833b7c..e30298e99e1b 100644
--- a/arch/nds32/Kconfig
+++ b/arch/nds32/Kconfig
@@ -62,7 +62,7 @@ config GENERIC_HWEIGHT
 
 config GENERIC_LOCKBREAK
 	def_bool y
-	depends on PREEMPT
+	depends on PREEMPTION
 
 config TRACE_IRQFLAGS_SUPPORT
 	def_bool y
diff --git a/arch/nds32/kernel/ex-exit.S b/arch/nds32/kernel/ex-exit.S
index 1df02a793364..6a2966c2d8c8 100644
--- a/arch/nds32/kernel/ex-exit.S
+++ b/arch/nds32/kernel/ex-exit.S
@@ -72,7 +72,7 @@
 	restore_user_regs_last
 	.endm
 
-#ifdef CONFIG_PREEMPT
+#ifdef CONFIG_PREEMPTION
 	.macro	preempt_stop
 	.endm
 #else
@@ -158,7 +158,7 @@ no_work_pending:
 /*
  * preemptive kernel
  */
-#ifdef CONFIG_PREEMPT
+#ifdef CONFIG_PREEMPTION
 resume_kernel:
 	gie_disable
 	lwi	$t0, [tsk+#TSK_TI_PREEMPT]
-- 
cgit v1.2.3-59-g8ed1b


From f0365eb50b04de91d0119619026865ba2a352a34 Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Tue, 15 Oct 2019 21:18:01 +0200
Subject: sched/rt, nios2: Use CONFIG_PREEMPTION

CONFIG_PREEMPTION is selected by CONFIG_PREEMPT and by CONFIG_PREEMPT_RT.
Both PREEMPT and PREEMPT_RT require the same functionality which today
depends on CONFIG_PREEMPT.

Switch the entry code over to use CONFIG_PREEMPTION.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: Ley Foon Tan <lftan@altera.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: nios2-dev@lists.rocketboards.org
Link: https://lore.kernel.org/r/20191015191821.11479-15-bigeasy@linutronix.de
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 arch/nios2/kernel/entry.S | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/nios2/kernel/entry.S b/arch/nios2/kernel/entry.S
index 1e515ccd698e..3d8d1d0bcb64 100644
--- a/arch/nios2/kernel/entry.S
+++ b/arch/nios2/kernel/entry.S
@@ -365,7 +365,7 @@ ENTRY(ret_from_interrupt)
 	ldw	r1, PT_ESTATUS(sp)	/* check if returning to kernel */
 	TSTBNZ	r1, r1, ESTATUS_EU, Luser_return
 
-#ifdef CONFIG_PREEMPT
+#ifdef CONFIG_PREEMPTION
 	GET_THREAD_INFO	r1
 	ldw	r4, TI_PREEMPT_COUNT(r1)
 	bne	r4, r0, restore_all
-- 
cgit v1.2.3-59-g8ed1b


From 09613e8320cda150717126ba88c0ddc38bfc0c68 Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Tue, 15 Oct 2019 21:18:02 +0200
Subject: sched/rt, parisc: Use CONFIG_PREEMPTION

CONFIG_PREEMPTION is selected by CONFIG_PREEMPT and by CONFIG_PREEMPT_RT.
Both PREEMPT and PREEMPT_RT require the same functionality which today
depends on CONFIG_PREEMPT.

Switch the entry code over to use CONFIG_PREEMPTION.

[bigeasy: +Kconfig]

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: Helge Deller <deller@gmx.de>
Cc: James E.J. Bottomley <James.Bottomley@HansenPartnership.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: linux-parisc@vger.kernel.org
Link: https://lore.kernel.org/r/20191015191821.11479-16-bigeasy@linutronix.de
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 arch/parisc/Kconfig        |  2 +-
 arch/parisc/kernel/entry.S | 10 +++++-----
 2 files changed, 6 insertions(+), 6 deletions(-)

diff --git a/arch/parisc/Kconfig b/arch/parisc/Kconfig
index b16237c95ea3..593e4014cef8 100644
--- a/arch/parisc/Kconfig
+++ b/arch/parisc/Kconfig
@@ -81,7 +81,7 @@ config STACK_GROWSUP
 config GENERIC_LOCKBREAK
 	bool
 	default y
-	depends on SMP && PREEMPT
+	depends on SMP && PREEMPTION
 
 config ARCH_HAS_ILOG2_U32
 	bool
diff --git a/arch/parisc/kernel/entry.S b/arch/parisc/kernel/entry.S
index b96d74496977..9a03e29c8733 100644
--- a/arch/parisc/kernel/entry.S
+++ b/arch/parisc/kernel/entry.S
@@ -940,14 +940,14 @@ intr_restore:
 	rfi
 	nop
 
-#ifndef CONFIG_PREEMPT
+#ifndef CONFIG_PREEMPTION
 # define intr_do_preempt	intr_restore
-#endif /* !CONFIG_PREEMPT */
+#endif /* !CONFIG_PREEMPTION */
 
 	.import schedule,code
 intr_do_resched:
 	/* Only call schedule on return to userspace. If we're returning
-	 * to kernel space, we may schedule if CONFIG_PREEMPT, otherwise
+	 * to kernel space, we may schedule if CONFIG_PREEMPTION, otherwise
 	 * we jump back to intr_restore.
 	 */
 	LDREG	PT_IASQ0(%r16), %r20
@@ -979,7 +979,7 @@ intr_do_resched:
 	 * and preempt_count is 0. otherwise, we continue on
 	 * our merry way back to the current running task.
 	 */
-#ifdef CONFIG_PREEMPT
+#ifdef CONFIG_PREEMPTION
 	.import preempt_schedule_irq,code
 intr_do_preempt:
 	rsm	PSW_SM_I, %r0		/* disable interrupts */
@@ -999,7 +999,7 @@ intr_do_preempt:
 	nop
 
 	b,n	intr_restore		/* ssm PSW_SM_I done by intr_restore */
-#endif /* CONFIG_PREEMPT */
+#endif /* CONFIG_PREEMPTION */
 
 	/*
 	 * External interrupts.
-- 
cgit v1.2.3-59-g8ed1b


From 29ff64929e6caf3a6df8e719aa5b9dc36e8e407a Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Tue, 15 Oct 2019 21:18:03 +0200
Subject: sched/rt, riscv: Use CONFIG_PREEMPTION

CONFIG_PREEMPTION is selected by CONFIG_PREEMPT and by CONFIG_PREEMPT_RT.
Both PREEMPT and PREEMPT_RT require the same functionality which today
depends on CONFIG_PREEMPT.

Switch the entry code over to use CONFIG_PREEMPTION.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: Paul Walmsley <paul.walmsley@sifive.com> # for arch/riscv
Cc: Albert Ou <aou@eecs.berkeley.edu>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Palmer Dabbelt <palmer@sifive.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: linux-riscv@lists.infradead.org
Link: https://lore.kernel.org/r/20191015191821.11479-17-bigeasy@linutronix.de
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 arch/riscv/kernel/entry.S | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/arch/riscv/kernel/entry.S b/arch/riscv/kernel/entry.S
index a1349ca64669..dd61bb247ce7 100644
--- a/arch/riscv/kernel/entry.S
+++ b/arch/riscv/kernel/entry.S
@@ -155,7 +155,7 @@ _save_context:
 	REG_L x2,  PT_SP(sp)
 	.endm
 
-#if !IS_ENABLED(CONFIG_PREEMPT)
+#if !IS_ENABLED(CONFIG_PREEMPTION)
 .set resume_kernel, restore_all
 #endif
 
@@ -304,7 +304,7 @@ restore_all:
 	sret
 #endif
 
-#if IS_ENABLED(CONFIG_PREEMPT)
+#if IS_ENABLED(CONFIG_PREEMPTION)
 resume_kernel:
 	REG_L s0, TASK_TI_PREEMPT_COUNT(tp)
 	bnez s0, restore_all
-- 
cgit v1.2.3-59-g8ed1b


From fa686453053b70a8a01b7517df8cfc5872f63196 Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Tue, 15 Oct 2019 21:18:04 +0200
Subject: sched/rt, s390: Use CONFIG_PREEMPTION

CONFIG_PREEMPTION is selected by CONFIG_PREEMPT and by CONFIG_PREEMPT_RT.
Both PREEMPT and PREEMPT_RT require the same functionality which today
depends on CONFIG_PREEMPT.

Switch the preemption and entry code over to use CONFIG_PREEMPTION. Add
PREEMPT_RT output to die().

[bigeasy: +Kconfig, dumpstack.c]

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: Christian Borntraeger <borntraeger@de.ibm.com>
Cc: Heiko Carstens <heiko.carstens@de.ibm.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Vasily Gorbik <gor@linux.ibm.com>
Cc: linux-s390@vger.kernel.org
Link: https://lore.kernel.org/r/20191015191821.11479-18-bigeasy@linutronix.de
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 arch/s390/Kconfig               | 2 +-
 arch/s390/include/asm/preempt.h | 4 ++--
 arch/s390/kernel/dumpstack.c    | 2 ++
 arch/s390/kernel/entry.S        | 2 +-
 4 files changed, 6 insertions(+), 4 deletions(-)

diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig
index d4051e88e625..62b10a301bd6 100644
--- a/arch/s390/Kconfig
+++ b/arch/s390/Kconfig
@@ -30,7 +30,7 @@ config GENERIC_BUG_RELATIVE_POINTERS
 	def_bool y
 
 config GENERIC_LOCKBREAK
-	def_bool y if PREEMPT
+	def_bool y if PREEMPTTION
 
 config PGSTE
 	def_bool y if KVM
diff --git a/arch/s390/include/asm/preempt.h b/arch/s390/include/asm/preempt.h
index b5ea9e14c017..6ede29907fbf 100644
--- a/arch/s390/include/asm/preempt.h
+++ b/arch/s390/include/asm/preempt.h
@@ -130,11 +130,11 @@ static inline bool should_resched(int preempt_offset)
 
 #endif /* CONFIG_HAVE_MARCH_Z196_FEATURES */
 
-#ifdef CONFIG_PREEMPT
+#ifdef CONFIG_PREEMPTION
 extern asmlinkage void preempt_schedule(void);
 #define __preempt_schedule() preempt_schedule()
 extern asmlinkage void preempt_schedule_notrace(void);
 #define __preempt_schedule_notrace() preempt_schedule_notrace()
-#endif /* CONFIG_PREEMPT */
+#endif /* CONFIG_PREEMPTION */
 
 #endif /* __ASM_PREEMPT_H */
diff --git a/arch/s390/kernel/dumpstack.c b/arch/s390/kernel/dumpstack.c
index d306fe04489a..2c122d8bab93 100644
--- a/arch/s390/kernel/dumpstack.c
+++ b/arch/s390/kernel/dumpstack.c
@@ -195,6 +195,8 @@ void die(struct pt_regs *regs, const char *str)
 	       regs->int_code >> 17, ++die_counter);
 #ifdef CONFIG_PREEMPT
 	pr_cont("PREEMPT ");
+#elif defined(CONFIG_PREEMPT_RT)
+	pr_cont("PREEMPT_RT ");
 #endif
 	pr_cont("SMP ");
 	if (debug_pagealloc_enabled())
diff --git a/arch/s390/kernel/entry.S b/arch/s390/kernel/entry.S
index 270d1d145761..9205add8481d 100644
--- a/arch/s390/kernel/entry.S
+++ b/arch/s390/kernel/entry.S
@@ -790,7 +790,7 @@ ENTRY(io_int_handler)
 .Lio_work:
 	tm	__PT_PSW+1(%r11),0x01	# returning to user ?
 	jo	.Lio_work_user		# yes -> do resched & signal
-#ifdef CONFIG_PREEMPT
+#ifdef CONFIG_PREEMPTION
 	# check for preemptive scheduling
 	icm	%r0,15,__LC_PREEMPT_COUNT
 	jnz	.Lio_restore		# preemption is disabled
-- 
cgit v1.2.3-59-g8ed1b


From 7be60ccbc59098f5251edae51bbf08e2d2226da0 Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Tue, 15 Oct 2019 21:18:05 +0200
Subject: sched/rt, sh: Use CONFIG_PREEMPTION

CONFIG_PREEMPTION is selected by CONFIG_PREEMPT and by CONFIG_PREEMPT_RT.
Both PREEMPT and PREEMPT_RT require the same functionality which today
depends on CONFIG_PREEMPT.

Switch the entry code over to use CONFIG_PREEMPTION.

[bigeasy: +Kconfig]

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Rich Felker <dalias@libc.org>
Cc: Yoshinori Sato <ysato@users.sourceforge.jp>
Cc: linux-sh@vger.kernel.org
Link: https://lore.kernel.org/r/20191015191821.11479-19-bigeasy@linutronix.de
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 arch/sh/Kconfig                | 2 +-
 arch/sh/kernel/cpu/sh5/entry.S | 4 ++--
 arch/sh/kernel/entry-common.S  | 4 ++--
 3 files changed, 5 insertions(+), 5 deletions(-)

diff --git a/arch/sh/Kconfig b/arch/sh/Kconfig
index f356ee674d89..9ece111b0254 100644
--- a/arch/sh/Kconfig
+++ b/arch/sh/Kconfig
@@ -108,7 +108,7 @@ config GENERIC_CALIBRATE_DELAY
 
 config GENERIC_LOCKBREAK
 	def_bool y
-	depends on SMP && PREEMPT
+	depends on SMP && PREEMPTION
 
 config ARCH_SUSPEND_POSSIBLE
 	def_bool n
diff --git a/arch/sh/kernel/cpu/sh5/entry.S b/arch/sh/kernel/cpu/sh5/entry.S
index de68ffdfffbf..81c8b64b977f 100644
--- a/arch/sh/kernel/cpu/sh5/entry.S
+++ b/arch/sh/kernel/cpu/sh5/entry.S
@@ -86,7 +86,7 @@
 	andi	r6, ~0xf0, r6;		\
 	putcon	r6, SR;
 
-#ifdef CONFIG_PREEMPT
+#ifdef CONFIG_PREEMPTION
 #  define preempt_stop()	CLI()
 #else
 #  define preempt_stop()
@@ -884,7 +884,7 @@ ret_from_exception:
 
 	/* Check softirqs */
 
-#ifdef CONFIG_PREEMPT
+#ifdef CONFIG_PREEMPTION
 	pta   ret_from_syscall, tr0
 	blink   tr0, ZERO
 
diff --git a/arch/sh/kernel/entry-common.S b/arch/sh/kernel/entry-common.S
index d31f66e82ce5..956a7a03b0c8 100644
--- a/arch/sh/kernel/entry-common.S
+++ b/arch/sh/kernel/entry-common.S
@@ -41,7 +41,7 @@
  */
 #include <asm/dwarf.h>
 
-#if defined(CONFIG_PREEMPT)
+#if defined(CONFIG_PREEMPTION)
 #  define preempt_stop()	cli ; TRACE_IRQS_OFF
 #else
 #  define preempt_stop()
@@ -84,7 +84,7 @@ ENTRY(ret_from_irq)
 	get_current_thread_info r8, r0
 	bt	resume_kernel	! Yes, it's from kernel, go back soon
 
-#ifdef CONFIG_PREEMPT
+#ifdef CONFIG_PREEMPTION
 	bra	resume_userspace
 	 nop
 ENTRY(resume_kernel)
-- 
cgit v1.2.3-59-g8ed1b


From 85a683d0a6895026b535bf40643687c626e376f3 Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Tue, 15 Oct 2019 21:18:06 +0200
Subject: sched/rt, sparc: Use CONFIG_PREEMPTION

CONFIG_PREEMPTION is selected by CONFIG_PREEMPT and by CONFIG_PREEMPT_RT.
Both PREEMPT and PREEMPT_RT require the same functionality which today
depends on CONFIG_PREEMPT.

Switch the trap code over to use CONFIG_PREEMPTION.

[bigeasy: +Kconfig]

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: David S. Miller <davem@davemloft.net>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: sparclinux@vger.kernel.org
Link: https://lore.kernel.org/r/20191015191821.11479-20-bigeasy@linutronix.de
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 arch/sparc/Kconfig           | 2 +-
 arch/sparc/kernel/rtrap_64.S | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/arch/sparc/Kconfig b/arch/sparc/Kconfig
index eb24cb1afc11..e8c3ea01c12f 100644
--- a/arch/sparc/Kconfig
+++ b/arch/sparc/Kconfig
@@ -277,7 +277,7 @@ config US3_MC
 config GENERIC_LOCKBREAK
 	bool
 	default y
-	depends on SPARC64 && SMP && PREEMPT
+	depends on SPARC64 && SMP && PREEMPTION
 
 config NUMA
 	bool "NUMA support"
diff --git a/arch/sparc/kernel/rtrap_64.S b/arch/sparc/kernel/rtrap_64.S
index 29aa34f11720..c5fd4b450d9b 100644
--- a/arch/sparc/kernel/rtrap_64.S
+++ b/arch/sparc/kernel/rtrap_64.S
@@ -310,7 +310,7 @@ kern_rtt_restore:
 		retry
 
 to_kernel:
-#ifdef CONFIG_PREEMPT
+#ifdef CONFIG_PREEMPTION
 		ldsw			[%g6 + TI_PRE_COUNT], %l5
 		brnz			%l5, kern_fpucheck
 		 ldx			[%g6 + TI_FLAGS], %l5
-- 
cgit v1.2.3-59-g8ed1b


From 6c5260d73d2b723f072c312eb80ef83711b4e166 Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Tue, 15 Oct 2019 21:18:07 +0200
Subject: sched/rt, xtensa: Use CONFIG_PREEMPTION

CONFIG_PREEMPTION is selected by CONFIG_PREEMPT and by CONFIG_PREEMPT_RT.
Both PREEMPT and PREEMPT_RT require the same functionality which today
depends on CONFIG_PREEMPT.

Switch the entry code over to use CONFIG_PREEMPTION. Add PREEMPT_RT
output to die().

[bigeasy: +traps.c]

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: Max Filippov <jcmvbkbc@gmail.com>
Cc: Chris Zankel <chris@zankel.net>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: linux-xtensa@linux-xtensa.org
Link: https://lore.kernel.org/r/20191015191821.11479-21-bigeasy@linutronix.de
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 arch/xtensa/kernel/entry.S | 2 +-
 arch/xtensa/kernel/traps.c | 7 +++++--
 2 files changed, 6 insertions(+), 3 deletions(-)

diff --git a/arch/xtensa/kernel/entry.S b/arch/xtensa/kernel/entry.S
index be897803834a..2c9e48566e48 100644
--- a/arch/xtensa/kernel/entry.S
+++ b/arch/xtensa/kernel/entry.S
@@ -520,7 +520,7 @@ common_exception_return:
 	call4	schedule	# void schedule (void)
 	j	1b
 
-#ifdef CONFIG_PREEMPT
+#ifdef CONFIG_PREEMPTION
 6:
 	_bbci.l	a4, TIF_NEED_RESCHED, 4f
 
diff --git a/arch/xtensa/kernel/traps.c b/arch/xtensa/kernel/traps.c
index 87bd68dd7687..0976e27b8d5d 100644
--- a/arch/xtensa/kernel/traps.c
+++ b/arch/xtensa/kernel/traps.c
@@ -519,12 +519,15 @@ DEFINE_SPINLOCK(die_lock);
 void die(const char * str, struct pt_regs * regs, long err)
 {
 	static int die_counter;
+	const char *pr = "";
+
+	if (IS_ENABLED(CONFIG_PREEMPTION))
+		pr = IS_ENABLED(CONFIG_PREEMPT_RT) ? " PREEMPT_RT" : " PREEMPT";
 
 	console_verbose();
 	spin_lock_irq(&die_lock);
 
-	pr_info("%s: sig: %ld [#%d]%s\n", str, err, ++die_counter,
-		IS_ENABLED(CONFIG_PREEMPT) ? " PREEMPT" : "");
+	pr_info("%s: sig: %ld [#%d]%s\n", str, err, ++die_counter, pr);
 	show_regs(regs);
 	if (!user_mode(regs))
 		show_stack(NULL, (unsigned long*)regs->areg[1]);
-- 
cgit v1.2.3-59-g8ed1b


From 2da2b32fd9346009e9acdb68c570ca8d3966aba7 Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Tue, 15 Oct 2019 21:18:08 +0200
Subject: sched/rt, net: Use CONFIG_PREEMPTION.patch

CONFIG_PREEMPTION is selected by CONFIG_PREEMPT and by CONFIG_PREEMPT_RT.
Both PREEMPT and PREEMPT_RT require the same functionality which today
depends on CONFIG_PREEMPT.

Update the comment to use CONFIG_PREEMPTION.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: David S. Miller <davem@davemloft.net>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: netdev@vger.kernel.org
Link: https://lore.kernel.org/r/20191015191821.11479-22-bigeasy@linutronix.de
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 net/core/dev.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/core/dev.c b/net/core/dev.c
index 46580b290450..de5f14bc639d 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -928,7 +928,7 @@ EXPORT_SYMBOL(dev_get_by_napi_id);
  *
  *	The use of raw_seqcount_begin() and cond_resched() before
  *	retrying is required as we want to give the writers a chance
- *	to complete when CONFIG_PREEMPT is not set.
+ *	to complete when CONFIG_PREEMPTION is not set.
  */
 int netdev_get_name(struct net *net, char *name, int ifindex)
 {
-- 
cgit v1.2.3-59-g8ed1b


From d4a3dcbc4727966a64a64d57e2b5106a138d426d Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Tue, 15 Oct 2019 21:18:09 +0200
Subject: sched/rt, xen: Use CONFIG_PREEMPTION

CONFIG_PREEMPTION is selected by CONFIG_PREEMPT and by CONFIG_PREEMPT_RT.
Both PREEMPT and PREEMPT_RT require the same functionality which today
depends on CONFIG_PREEMPT.

Switch the preempt anand xen-ops code over to use CONFIG_PREEMPTION.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Juergen Gross <jgross@suse.com>
Cc: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stefano Stabellini <sstabellini@kernel.org>
Cc: xen-devel@lists.xenproject.org
Link: https://lore.kernel.org/r/20191015191821.11479-23-bigeasy@linutronix.de
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 drivers/xen/preempt.c | 4 ++--
 include/xen/xen-ops.h | 4 ++--
 2 files changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/xen/preempt.c b/drivers/xen/preempt.c
index 8b9919c26095..70650b248de5 100644
--- a/drivers/xen/preempt.c
+++ b/drivers/xen/preempt.c
@@ -8,7 +8,7 @@
 #include <linux/sched.h>
 #include <xen/xen-ops.h>
 
-#ifndef CONFIG_PREEMPT
+#ifndef CONFIG_PREEMPTION
 
 /*
  * Some hypercalls issued by the toolstack can take many 10s of
@@ -37,4 +37,4 @@ asmlinkage __visible void xen_maybe_preempt_hcall(void)
 		__this_cpu_write(xen_in_preemptible_hcall, true);
 	}
 }
-#endif /* CONFIG_PREEMPT */
+#endif /* CONFIG_PREEMPTION */
diff --git a/include/xen/xen-ops.h b/include/xen/xen-ops.h
index d89969aa9942..095be1d66f31 100644
--- a/include/xen/xen-ops.h
+++ b/include/xen/xen-ops.h
@@ -215,7 +215,7 @@ bool xen_running_on_version_or_later(unsigned int major, unsigned int minor);
 void xen_efi_runtime_setup(void);
 
 
-#ifdef CONFIG_PREEMPT
+#ifdef CONFIG_PREEMPTION
 
 static inline void xen_preemptible_hcall_begin(void)
 {
@@ -239,6 +239,6 @@ static inline void xen_preemptible_hcall_end(void)
 	__this_cpu_write(xen_in_preemptible_hcall, false);
 }
 
-#endif /* CONFIG_PREEMPT */
+#endif /* CONFIG_PREEMPTION */
 
 #endif /* INCLUDE_XEN_OPS_H */
-- 
cgit v1.2.3-59-g8ed1b


From 2496396fcb44404ead24b578c583d5286886e857 Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Tue, 15 Oct 2019 21:18:10 +0200
Subject: sched/rt, fs: Use CONFIG_PREEMPTION
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

CONFIG_PREEMPTION is selected by CONFIG_PREEMPT and by CONFIG_PREEMPT_RT.
Both PREEMPT and PREEMPT_RT require the same functionality which today
depends on CONFIG_PREEMPT.

Switch the i_size() and part_nr_sects_…() code over to use
CONFIG_PREEMPTION. Update the comment for fsstack_copy_inode_size() also
to refer to CONFIG_PREEMPTION.

[bigeasy: +PREEMPT comments]

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: Alexander Viro <viro@zeniv.linux.org.uk>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: linux-fsdevel@vger.kernel.org
Link: https://lore.kernel.org/r/20191015191821.11479-24-bigeasy@linutronix.de
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 fs/stack.c            | 6 +++---
 include/linux/fs.h    | 4 ++--
 include/linux/genhd.h | 6 +++---
 3 files changed, 8 insertions(+), 8 deletions(-)

diff --git a/fs/stack.c b/fs/stack.c
index 4ef2c056269d..c9830924eb12 100644
--- a/fs/stack.c
+++ b/fs/stack.c
@@ -23,7 +23,7 @@ void fsstack_copy_inode_size(struct inode *dst, struct inode *src)
 
 	/*
 	 * But on 32-bit, we ought to make an effort to keep the two halves of
-	 * i_blocks in sync despite SMP or PREEMPT - though stat's
+	 * i_blocks in sync despite SMP or PREEMPTION - though stat's
 	 * generic_fillattr() doesn't bother, and we won't be applying quotas
 	 * (where i_blocks does become important) at the upper level.
 	 *
@@ -38,14 +38,14 @@ void fsstack_copy_inode_size(struct inode *dst, struct inode *src)
 		spin_unlock(&src->i_lock);
 
 	/*
-	 * If CONFIG_SMP or CONFIG_PREEMPT on 32-bit, it's vital for
+	 * If CONFIG_SMP or CONFIG_PREEMPTION on 32-bit, it's vital for
 	 * fsstack_copy_inode_size() to hold some lock around
 	 * i_size_write(), otherwise i_size_read() may spin forever (see
 	 * include/linux/fs.h).  We don't necessarily hold i_mutex when this
 	 * is called, so take i_lock for that case.
 	 *
 	 * And if on 32-bit, continue our effort to keep the two halves of
-	 * i_blocks in sync despite SMP or PREEMPT: use i_lock  for that case
+	 * i_blocks in sync despite SMP or PREEMPTION: use i_lock for that case
 	 * too, and do both at once by combining the tests.
 	 *
 	 * There is none of this locking overhead in the 64-bit case.
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 98e0349adb52..dddfcbb140a7 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -855,7 +855,7 @@ static inline loff_t i_size_read(const struct inode *inode)
 		i_size = inode->i_size;
 	} while (read_seqcount_retry(&inode->i_size_seqcount, seq));
 	return i_size;
-#elif BITS_PER_LONG==32 && defined(CONFIG_PREEMPT)
+#elif BITS_PER_LONG==32 && defined(CONFIG_PREEMPTION)
 	loff_t i_size;
 
 	preempt_disable();
@@ -880,7 +880,7 @@ static inline void i_size_write(struct inode *inode, loff_t i_size)
 	inode->i_size = i_size;
 	write_seqcount_end(&inode->i_size_seqcount);
 	preempt_enable();
-#elif BITS_PER_LONG==32 && defined(CONFIG_PREEMPT)
+#elif BITS_PER_LONG==32 && defined(CONFIG_PREEMPTION)
 	preempt_disable();
 	inode->i_size = i_size;
 	preempt_enable();
diff --git a/include/linux/genhd.h b/include/linux/genhd.h
index 8bb63027e4d6..a927829bb73a 100644
--- a/include/linux/genhd.h
+++ b/include/linux/genhd.h
@@ -718,7 +718,7 @@ static inline void hd_free_part(struct hd_struct *part)
  * accessor function.
  *
  * Code written along the lines of i_size_read() and i_size_write().
- * CONFIG_PREEMPT case optimizes the case of UP kernel with preemption
+ * CONFIG_PREEMPTION case optimizes the case of UP kernel with preemption
  * on.
  */
 static inline sector_t part_nr_sects_read(struct hd_struct *part)
@@ -731,7 +731,7 @@ static inline sector_t part_nr_sects_read(struct hd_struct *part)
 		nr_sects = part->nr_sects;
 	} while (read_seqcount_retry(&part->nr_sects_seq, seq));
 	return nr_sects;
-#elif BITS_PER_LONG==32 && defined(CONFIG_PREEMPT)
+#elif BITS_PER_LONG==32 && defined(CONFIG_PREEMPTION)
 	sector_t nr_sects;
 
 	preempt_disable();
@@ -754,7 +754,7 @@ static inline void part_nr_sects_write(struct hd_struct *part, sector_t size)
 	write_seqcount_begin(&part->nr_sects_seq);
 	part->nr_sects = size;
 	write_seqcount_end(&part->nr_sects_seq);
-#elif BITS_PER_LONG==32 && defined(CONFIG_PREEMPT)
+#elif BITS_PER_LONG==32 && defined(CONFIG_PREEMPTION)
 	preempt_disable();
 	part->nr_sects = size;
 	preempt_enable();
-- 
cgit v1.2.3-59-g8ed1b


From 94545870b14b5eb6d8a887fab845d1918f4f62ac Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Tue, 15 Oct 2019 21:18:11 +0200
Subject: sched/rt, btrfs: Use CONFIG_PREEMPTION
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

CONFIG_PREEMPTION is selected by CONFIG_PREEMPT and by CONFIG_PREEMPT_RT.
Both PREEMPT and PREEMPT_RT require the same functionality which today
depends on CONFIG_PREEMPT.

Switch the btrfs_device_set_…() macro over to use CONFIG_PREEMPTION.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: David Sterba <dsterba@suse.com>
Cc: Chris Mason <clm@fb.com>
Cc: Josef Bacik <josef@toxicpanda.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: linux-btrfs@vger.kernel.org
Link: https://lore.kernel.org/r/20191015191821.11479-25-bigeasy@linutronix.de
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 fs/btrfs/volumes.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/btrfs/volumes.h b/fs/btrfs/volumes.h
index fc1b564b9cfe..0ee5386926fa 100644
--- a/fs/btrfs/volumes.h
+++ b/fs/btrfs/volumes.h
@@ -168,7 +168,7 @@ btrfs_device_set_##name(struct btrfs_device *dev, u64 size)		\
 	write_seqcount_end(&dev->data_seqcount);			\
 	preempt_enable();						\
 }
-#elif BITS_PER_LONG==32 && defined(CONFIG_PREEMPT)
+#elif BITS_PER_LONG==32 && defined(CONFIG_PREEMPTION)
 #define BTRFS_DEVICE_GETSET_FUNCS(name)					\
 static inline u64							\
 btrfs_device_get_##name(const struct btrfs_device *dev)			\
-- 
cgit v1.2.3-59-g8ed1b


From 923717cbab900fb23b31f16fb31b1d86b09bf702 Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Tue, 15 Oct 2019 21:18:12 +0200
Subject: sched/rt, mm: Use CONFIG_PREEMPTION

CONFIG_PREEMPTION is selected by CONFIG_PREEMPT and by CONFIG_PREEMPT_RT.
Both PREEMPT and PREEMPT_RT require the same functionality which today
depends on CONFIG_PREEMPT.

Switch the pte_unmap_same() and SLUB code over to use CONFIG_PREEMPTION.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: Chistoph Lameter <cl@linux.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: David Rientjes <rientjes@google.com>
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Pekka Enberg <penberg@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: linux-mm@kvack.org
Link: https://lore.kernel.org/r/20191015191821.11479-26-bigeasy@linutronix.de
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 mm/memory.c |  2 +-
 mm/slub.c   | 12 ++++++------
 2 files changed, 7 insertions(+), 7 deletions(-)

diff --git a/mm/memory.c b/mm/memory.c
index 513c3ecc76ee..d56883c220f4 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -2151,7 +2151,7 @@ static inline int pte_unmap_same(struct mm_struct *mm, pmd_t *pmd,
 				pte_t *page_table, pte_t orig_pte)
 {
 	int same = 1;
-#if defined(CONFIG_SMP) || defined(CONFIG_PREEMPT)
+#if defined(CONFIG_SMP) || defined(CONFIG_PREEMPTION)
 	if (sizeof(pte_t) > sizeof(unsigned long)) {
 		spinlock_t *ptl = pte_lockptr(mm, pmd);
 		spin_lock(ptl);
diff --git a/mm/slub.c b/mm/slub.c
index d11389710b12..f7c66dc2ba0b 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -1964,7 +1964,7 @@ static void *get_partial(struct kmem_cache *s, gfp_t flags, int node,
 	return get_any_partial(s, flags, c);
 }
 
-#ifdef CONFIG_PREEMPT
+#ifdef CONFIG_PREEMPTION
 /*
  * Calculate the next globally unique transaction for disambiguiation
  * during cmpxchg. The transactions start with the cpu number and are then
@@ -2009,7 +2009,7 @@ static inline void note_cmpxchg_failure(const char *n,
 
 	pr_info("%s %s: cmpxchg redo ", n, s->name);
 
-#ifdef CONFIG_PREEMPT
+#ifdef CONFIG_PREEMPTION
 	if (tid_to_cpu(tid) != tid_to_cpu(actual_tid))
 		pr_warn("due to cpu change %d -> %d\n",
 			tid_to_cpu(tid), tid_to_cpu(actual_tid));
@@ -2637,7 +2637,7 @@ static void *__slab_alloc(struct kmem_cache *s, gfp_t gfpflags, int node,
 	unsigned long flags;
 
 	local_irq_save(flags);
-#ifdef CONFIG_PREEMPT
+#ifdef CONFIG_PREEMPTION
 	/*
 	 * We may have been preempted and rescheduled on a different
 	 * cpu before disabling interrupts. Need to reload cpu area
@@ -2691,13 +2691,13 @@ redo:
 	 * as we end up on the original cpu again when doing the cmpxchg.
 	 *
 	 * We should guarantee that tid and kmem_cache are retrieved on
-	 * the same cpu. It could be different if CONFIG_PREEMPT so we need
+	 * the same cpu. It could be different if CONFIG_PREEMPTION so we need
 	 * to check if it is matched or not.
 	 */
 	do {
 		tid = this_cpu_read(s->cpu_slab->tid);
 		c = raw_cpu_ptr(s->cpu_slab);
-	} while (IS_ENABLED(CONFIG_PREEMPT) &&
+	} while (IS_ENABLED(CONFIG_PREEMPTION) &&
 		 unlikely(tid != READ_ONCE(c->tid)));
 
 	/*
@@ -2971,7 +2971,7 @@ redo:
 	do {
 		tid = this_cpu_read(s->cpu_slab->tid);
 		c = raw_cpu_ptr(s->cpu_slab);
-	} while (IS_ENABLED(CONFIG_PREEMPT) &&
+	} while (IS_ENABLED(CONFIG_PREEMPTION) &&
 		 unlikely(tid != READ_ONCE(c->tid)));
 
 	/* Same with comment on barrier() in slab_alloc_node() */
-- 
cgit v1.2.3-59-g8ed1b


From 1b40cd56f3bcffcfedb43bc30bd431b52240fb3b Mon Sep 17 00:00:00 2001
From: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Date: Tue, 15 Oct 2019 21:18:18 +0200
Subject: sched/rt, locking: Use CONFIG_PREEMPTION

CONFIG_PREEMPTION is selected by CONFIG_PREEMPT and by CONFIG_PREEMPT_RT.
Both PREEMPT and PREEMPT_RT require the same functionality which today
depends on CONFIG_PREEMPT.

Switch the Kconfig dependency to use CONFIG_PREEMPTION.

Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Will Deacon <will@kernel.org>
Link: https://lore.kernel.org/r/20191015191821.11479-32-bigeasy@linutronix.de
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 kernel/Kconfig.locks | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

diff --git a/kernel/Kconfig.locks b/kernel/Kconfig.locks
index e0852dc333ac..3de8fd11873b 100644
--- a/kernel/Kconfig.locks
+++ b/kernel/Kconfig.locks
@@ -101,7 +101,7 @@ config UNINLINE_SPIN_UNLOCK
 # unlock and unlock_irq functions are inlined when:
 #   - DEBUG_SPINLOCK=n and ARCH_INLINE_*LOCK=y
 #  or
-#   - DEBUG_SPINLOCK=n and PREEMPT=n
+#   - DEBUG_SPINLOCK=n and PREEMPTION=n
 #
 # unlock_bh and unlock_irqrestore functions are inlined when:
 #   - DEBUG_SPINLOCK=n and ARCH_INLINE_*LOCK=y
@@ -139,7 +139,7 @@ config INLINE_SPIN_UNLOCK_BH
 
 config INLINE_SPIN_UNLOCK_IRQ
 	def_bool y
-	depends on !PREEMPT || ARCH_INLINE_SPIN_UNLOCK_IRQ
+	depends on !PREEMPTION || ARCH_INLINE_SPIN_UNLOCK_IRQ
 
 config INLINE_SPIN_UNLOCK_IRQRESTORE
 	def_bool y
@@ -168,7 +168,7 @@ config INLINE_READ_LOCK_IRQSAVE
 
 config INLINE_READ_UNLOCK
 	def_bool y
-	depends on !PREEMPT || ARCH_INLINE_READ_UNLOCK
+	depends on !PREEMPTION || ARCH_INLINE_READ_UNLOCK
 
 config INLINE_READ_UNLOCK_BH
 	def_bool y
@@ -176,7 +176,7 @@ config INLINE_READ_UNLOCK_BH
 
 config INLINE_READ_UNLOCK_IRQ
 	def_bool y
-	depends on !PREEMPT || ARCH_INLINE_READ_UNLOCK_IRQ
+	depends on !PREEMPTION || ARCH_INLINE_READ_UNLOCK_IRQ
 
 config INLINE_READ_UNLOCK_IRQRESTORE
 	def_bool y
@@ -205,7 +205,7 @@ config INLINE_WRITE_LOCK_IRQSAVE
 
 config INLINE_WRITE_UNLOCK
 	def_bool y
-	depends on !PREEMPT || ARCH_INLINE_WRITE_UNLOCK
+	depends on !PREEMPTION || ARCH_INLINE_WRITE_UNLOCK
 
 config INLINE_WRITE_UNLOCK_BH
 	def_bool y
@@ -213,7 +213,7 @@ config INLINE_WRITE_UNLOCK_BH
 
 config INLINE_WRITE_UNLOCK_IRQ
 	def_bool y
-	depends on !PREEMPT || ARCH_INLINE_WRITE_UNLOCK_IRQ
+	depends on !PREEMPTION || ARCH_INLINE_WRITE_UNLOCK_IRQ
 
 config INLINE_WRITE_UNLOCK_IRQRESTORE
 	def_bool y
-- 
cgit v1.2.3-59-g8ed1b


From 9f47286924f2f868760a528c14596370e32d86b4 Mon Sep 17 00:00:00 2001
From: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Date: Tue, 15 Oct 2019 21:18:19 +0200
Subject: sched/core: Use CONFIG_PREEMPTION

CONFIG_PREEMPTION is selected by CONFIG_PREEMPT and by CONFIG_PREEMPT_RT.
Both PREEMPT and PREEMPT_RT require the same functionality which today
depends on CONFIG_PREEMPT.

Let DEBUG_PREEMPT depend on CONFIG_PREEMPTION.

Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: https://lore.kernel.org/r/20191015191821.11479-33-bigeasy@linutronix.de
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 lib/Kconfig.debug | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug
index 2f6fb96405af..d03e2b1570ca 100644
--- a/lib/Kconfig.debug
+++ b/lib/Kconfig.debug
@@ -1051,7 +1051,7 @@ config DEBUG_TIMEKEEPING
 
 config DEBUG_PREEMPT
 	bool "Debug preemptible kernel"
-	depends on DEBUG_KERNEL && PREEMPT && TRACE_IRQFLAGS_SUPPORT
+	depends on DEBUG_KERNEL && PREEMPTION && TRACE_IRQFLAGS_SUPPORT
 	default y
 	help
 	  If you say Y here then the kernel will use a debug variant of the
-- 
cgit v1.2.3-59-g8ed1b


From 025f50f3866486a5278afa91f0d3b6b780141050 Mon Sep 17 00:00:00 2001
From: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Date: Tue, 15 Oct 2019 21:18:21 +0200
Subject: sched/rt, workqueue: Use PREEMPTION

CONFIG_PREEMPTION is selected by CONFIG_PREEMPT and by CONFIG_PREEMPT_RT.
Both PREEMPT and PREEMPT_RT require the same functionality which today
depends on CONFIG_PREEMPT.

Update the comment to use PREEMPTION because it is true for both
preemption models.

Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: Lai Jiangshan <jiangshanlai@gmail.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Tejun Heo <tj@kernel.org>
Link: https://lore.kernel.org/r/20191015191821.11479-35-bigeasy@linutronix.de
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 kernel/workqueue.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index bc88fd939f4e..bf57dc717b38 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -2280,7 +2280,7 @@ __acquires(&pool->lock)
 	}
 
 	/*
-	 * The following prevents a kworker from hogging CPU on !PREEMPT
+	 * The following prevents a kworker from hogging CPU on !PREEMPTION
 	 * kernels, where a requeueing work item waiting for something to
 	 * happen could deadlock with stop_machine as such work item could
 	 * indefinitely requeue itself while all other CPUs are trapped in
-- 
cgit v1.2.3-59-g8ed1b


From 7c2e8bbd87db661122e92d71a394dd7bb3ada4d3 Mon Sep 17 00:00:00 2001
From: Frederic Weisbecker <frederic@kernel.org>
Date: Tue, 3 Dec 2019 17:01:05 +0100
Subject: sched: Spare resched IPI when prio changes on a single fair task

The runqueue of a fair task being remotely reniced is going to get a
resched IPI in order to reassess which task should be the current
running on the CPU. However that evaluation is useless if the fair task
is running alone, in which case we can spare that IPI, preventing
nohz_full CPUs from being disturbed.

Reported-by: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Frederic Weisbecker <frederic@kernel.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Ingo Molnar <mingo@kernel.org>
Link: https://lkml.kernel.org/r/20191203160106.18806-2-frederic@kernel.org
---
 kernel/sched/fair.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 08a233e97a01..846f50bd0c0b 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -10322,6 +10322,9 @@ prio_changed_fair(struct rq *rq, struct task_struct *p, int oldprio)
 	if (!task_on_rq_queued(p))
 		return;
 
+	if (rq->cfs.nr_running == 1)
+		return;
+
 	/*
 	 * Reschedule if we are currently running on this runqueue and
 	 * our priority decreased, or if we are not currently running on
-- 
cgit v1.2.3-59-g8ed1b


From 5443a0be6121d557e12951537e10159e4c61035d Mon Sep 17 00:00:00 2001
From: Frederic Weisbecker <frederic@kernel.org>
Date: Tue, 3 Dec 2019 17:01:06 +0100
Subject: sched: Use fair:prio_changed() instead of ad-hoc implementation

set_user_nice() implements its own version of fair::prio_changed() and
therefore misses a specific optimization towards nohz_full CPUs that
avoid sending an resched IPI to a reniced task running alone. Use the
proper callback instead.

Reported-by: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Frederic Weisbecker <frederic@kernel.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Ingo Molnar <mingo@kernel.org>
Link: https://lkml.kernel.org/r/20191203160106.18806-3-frederic@kernel.org
---
 kernel/sched/core.c | 16 ++++++++--------
 1 file changed, 8 insertions(+), 8 deletions(-)

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 90e4b00ace89..15508c202bf5 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -4540,17 +4540,17 @@ void set_user_nice(struct task_struct *p, long nice)
 	p->prio = effective_prio(p);
 	delta = p->prio - old_prio;
 
-	if (queued) {
+	if (queued)
 		enqueue_task(rq, p, ENQUEUE_RESTORE | ENQUEUE_NOCLOCK);
-		/*
-		 * If the task increased its priority or is running and
-		 * lowered its priority, then reschedule its CPU:
-		 */
-		if (delta < 0 || (delta > 0 && task_running(rq, p)))
-			resched_curr(rq);
-	}
 	if (running)
 		set_next_task(rq, p);
+
+	/*
+	 * If the task increased its priority or is running and
+	 * lowered its priority, then reschedule its CPU:
+	 */
+	p->sched_class->prio_changed(rq, p, old_prio);
+
 out_unlock:
 	task_rq_unlock(rq, p, &rf);
 }
-- 
cgit v1.2.3-59-g8ed1b


From cde65194502778665c1b52afc5722cf7dbfaa399 Mon Sep 17 00:00:00 2001
From: Oleg Nesterov <oleg@redhat.com>
Date: Tue, 10 Dec 2019 20:19:03 +0100
Subject: sched/wait: fix ___wait_var_event(exclusive)

init_wait_var_entry() forgets to initialize wq_entry->flags.

Currently not a problem, we don't have wait_var_event_exclusive().

Signed-off-by: Oleg Nesterov <oleg@redhat.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Vincent Guittot <vincent.guittot@linaro.org>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Felipe Balbi <balbi@kernel.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Miklos Szeredi <miklos@szeredi.hu>
Cc: Juri Lelli <juri.lelli@redhat.com>
Link: https://lkml.kernel.org/r/20191210191902.GB14449@redhat.com
---
 kernel/sched/wait_bit.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/kernel/sched/wait_bit.c b/kernel/sched/wait_bit.c
index 45eba18a2898..02ce292b9bc0 100644
--- a/kernel/sched/wait_bit.c
+++ b/kernel/sched/wait_bit.c
@@ -179,6 +179,7 @@ void init_wait_var_entry(struct wait_bit_queue_entry *wbq_entry, void *var, int
 			.bit_nr = -1,
 		},
 		.wq_entry = {
+			.flags	 = flags,
 			.private = current,
 			.func	 = var_wake_function,
 			.entry	 = LIST_HEAD_INIT(wbq_entry->wq_entry.entry),
-- 
cgit v1.2.3-59-g8ed1b


From 45178ac0cea853fe0e405bf11e101bdebea57b15 Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Tue, 10 Dec 2019 09:34:54 +0100
Subject: cpu/hotplug, stop_machine: Fix stop_machine vs hotplug order

Paul reported a very sporadic, rcutorture induced, workqueue failure.
When the planets align, the workqueue rescuer's self-migrate fails and
then triggers a WARN for running a work on the wrong CPU.

Tejun then figured that set_cpus_allowed_ptr()'s stop_one_cpu() call
could be ignored! When stopper->enabled is false, stop_machine will
insta complete the work, without actually doing the work. Worse, it
will not WARN about this (we really should fix this).

It turns out there is a small window where a freshly online'ed CPU is
marked 'online' but doesn't yet have the stopper task running:

	BP				AP

	bringup_cpu()
	  __cpu_up(cpu, idle)	 -->	start_secondary()
					...
					cpu_startup_entry()
	  bringup_wait_for_ap()
	    wait_for_ap_thread() <--	  cpuhp_online_idle()
					  while (1)
					    do_idle()

					... available to run kthreads ...

	    stop_machine_unpark()
	      stopper->enable = true;

Close this by moving the stop_machine_unpark() into
cpuhp_online_idle(), such that the stopper thread is ready before we
start the idle loop and schedule.

Reported-by: "Paul E. McKenney" <paulmck@kernel.org>
Debugged-by: Tejun Heo <tj@kernel.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Tested-by: "Paul E. McKenney" <paulmck@kernel.org>
---
 kernel/cpu.c | 13 +++++++++----
 1 file changed, 9 insertions(+), 4 deletions(-)

diff --git a/kernel/cpu.c b/kernel/cpu.c
index a59cc980adad..e7f79674824d 100644
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -525,8 +525,7 @@ static int bringup_wait_for_ap(unsigned int cpu)
 	if (WARN_ON_ONCE((!cpu_online(cpu))))
 		return -ECANCELED;
 
-	/* Unpark the stopper thread and the hotplug thread of the target cpu */
-	stop_machine_unpark(cpu);
+	/* Unpark the hotplug thread of the target cpu */
 	kthread_unpark(st->thread);
 
 	/*
@@ -1089,8 +1088,8 @@ void notify_cpu_starting(unsigned int cpu)
 
 /*
  * Called from the idle task. Wake up the controlling task which brings the
- * stopper and the hotplug thread of the upcoming CPU up and then delegates
- * the rest of the online bringup to the hotplug thread.
+ * hotplug thread of the upcoming CPU up and then delegates the rest of the
+ * online bringup to the hotplug thread.
  */
 void cpuhp_online_idle(enum cpuhp_state state)
 {
@@ -1100,6 +1099,12 @@ void cpuhp_online_idle(enum cpuhp_state state)
 	if (state != CPUHP_AP_ONLINE_IDLE)
 		return;
 
+	/*
+	 * Unpart the stopper thread before we start the idle loop (and start
+	 * scheduling); this ensures the stopper task is always available.
+	 */
+	stop_machine_unpark(smp_processor_id());
+
 	st->state = CPUHP_AP_ONLINE_IDLE;
 	complete_ap_thread(st, true);
 }
-- 
cgit v1.2.3-59-g8ed1b


From 60588bfa223ff675b95f866249f90616613fbe31 Mon Sep 17 00:00:00 2001
From: Cheng Jian <cj.chengjian@huawei.com>
Date: Fri, 13 Dec 2019 10:45:30 +0800
Subject: sched/fair: Optimize select_idle_cpu

select_idle_cpu() will scan the LLC domain for idle CPUs,
it's always expensive. so the next commit :

	1ad3aaf3fcd2 ("sched/core: Implement new approach to scale select_idle_cpu()")

introduces a way to limit how many CPUs we scan.

But it consume some CPUs out of 'nr' that are not allowed
for the task and thus waste our attempts. The function
always return nr_cpumask_bits, and we can't find a CPU
which our task is allowed to run.

Cpumask may be too big, similar to select_idle_core(), use
per_cpu_ptr 'select_idle_mask' to prevent stack overflow.

Fixes: 1ad3aaf3fcd2 ("sched/core: Implement new approach to scale select_idle_cpu()")
Signed-off-by: Cheng Jian <cj.chengjian@huawei.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
Reviewed-by: Vincent Guittot <vincent.guittot@linaro.org>
Reviewed-by: Valentin Schneider <valentin.schneider@arm.com>
Link: https://lkml.kernel.org/r/20191213024530.28052-1-cj.chengjian@huawei.com
---
 kernel/sched/fair.c | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 846f50bd0c0b..280d54ccb4be 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -5828,6 +5828,7 @@ static inline int select_idle_smt(struct task_struct *p, int target)
  */
 static int select_idle_cpu(struct task_struct *p, struct sched_domain *sd, int target)
 {
+	struct cpumask *cpus = this_cpu_cpumask_var_ptr(select_idle_mask);
 	struct sched_domain *this_sd;
 	u64 avg_cost, avg_idle;
 	u64 time, cost;
@@ -5859,11 +5860,11 @@ static int select_idle_cpu(struct task_struct *p, struct sched_domain *sd, int t
 
 	time = cpu_clock(this);
 
-	for_each_cpu_wrap(cpu, sched_domain_span(sd), target) {
+	cpumask_and(cpus, sched_domain_span(sd), p->cpus_ptr);
+
+	for_each_cpu_wrap(cpu, cpus, target) {
 		if (!--nr)
 			return si_cpu;
-		if (!cpumask_test_cpu(cpu, p->cpus_ptr))
-			continue;
 		if (available_idle_cpu(cpu))
 			break;
 		if (si_cpu == -1 && sched_idle_cpu(cpu))
-- 
cgit v1.2.3-59-g8ed1b


From d040e0734fb3dedfe24c3d94f5a32b4812eca610 Mon Sep 17 00:00:00 2001
From: Peng Wang <rocking@linux.alibaba.com>
Date: Fri, 13 Dec 2019 11:45:40 +0800
Subject: schied/fair: Skip calculating @contrib without load

Because of the:

	if (!load)
		runnable = running = 0;

clause in ___update_load_sum(), all the actual users of @contrib in
accumulate_sum():

	if (load)
		sa->load_sum += load * contrib;
	if (runnable)
		sa->runnable_load_sum += runnable * contrib;
	if (running)
		sa->util_sum += contrib << SCHED_CAPACITY_SHIFT;

don't happen, and therefore we don't care what @contrib actually is and
calculating it is pointless.

If we count the times when @load equals zero and not as below:

	if (load) {
		load_is_not_zero_count++;
		contrib = __accumulate_pelt_segments(periods,
				1024 - sa->period_contrib,delta);
	} else
		load_is_zero_count++;

As we can see, load_is_zero_count is much bigger than
load_is_zero_count, and the gap is gradually widening:

	load_is_zero_count:            6016044 times
	load_is_not_zero_count:         244316 times
	19:50:43 up 1 min,  1 user,  load average: 0.09, 0.06, 0.02

	load_is_zero_count:            7956168 times
	load_is_not_zero_count:         261472 times
	19:51:42 up 2 min,  1 user,  load average: 0.03, 0.05, 0.01

	load_is_zero_count:           10199896 times
	load_is_not_zero_count:         278364 times
	19:52:51 up 3 min,  1 user,  load average: 0.06, 0.05, 0.01

	load_is_zero_count:           14333700 times
	load_is_not_zero_count:         318424 times
	19:54:53 up 5 min,  1 user,  load average: 0.01, 0.03, 0.00

Perhaps we can gain some performance advantage by saving these
unnecessary calculation.

Signed-off-by: Peng Wang <rocking@linux.alibaba.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Vincent Guittot < vincent.guittot@linaro.org>
Link: https://lkml.kernel.org/r/1576208740-35609-1-git-send-email-rocking@linux.alibaba.com
---
 kernel/sched/pelt.c | 20 +++++++++++++++++---
 1 file changed, 17 insertions(+), 3 deletions(-)

diff --git a/kernel/sched/pelt.c b/kernel/sched/pelt.c
index a96db50d40e0..bd006b79b360 100644
--- a/kernel/sched/pelt.c
+++ b/kernel/sched/pelt.c
@@ -129,8 +129,20 @@ accumulate_sum(u64 delta, struct sched_avg *sa,
 		 * Step 2
 		 */
 		delta %= 1024;
-		contrib = __accumulate_pelt_segments(periods,
-				1024 - sa->period_contrib, delta);
+		if (load) {
+			/*
+			 * This relies on the:
+			 *
+			 * if (!load)
+			 *	runnable = running = 0;
+			 *
+			 * clause from ___update_load_sum(); this results in
+			 * the below usage of @contrib to dissapear entirely,
+			 * so no point in calculating it.
+			 */
+			contrib = __accumulate_pelt_segments(periods,
+					1024 - sa->period_contrib, delta);
+		}
 	}
 	sa->period_contrib = delta;
 
@@ -205,7 +217,9 @@ ___update_load_sum(u64 now, struct sched_avg *sa,
 	 * This means that weight will be 0 but not running for a sched_entity
 	 * but also for a cfs_rq if the latter becomes idle. As an example,
 	 * this happens during idle_balance() which calls
-	 * update_blocked_averages()
+	 * update_blocked_averages().
+	 *
+	 * Also see the comment in accumulate_sum().
 	 */
 	if (!load)
 		runnable = running = 0;
-- 
cgit v1.2.3-59-g8ed1b


From a5e37de90e67ac1072a9a44bd0cec9f5e98ded08 Mon Sep 17 00:00:00 2001
From: Yangtao Li <tiny.windzz@gmail.com>
Date: Sat, 14 Dec 2019 19:51:07 +0000
Subject: stop_machine: remove try_stop_cpus helper

try_stop_cpus is not used after this:

commit c190c3b16c0f ("rcu: Switch synchronize_sched_expedited() to
stop_one_cpu()")

So remove it.

Signed-off-by: Yangtao Li <tiny.windzz@gmail.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20191214195107.26480-1-tiny.windzz@gmail.com
---
 include/linux/stop_machine.h |  7 -------
 kernel/stop_machine.c        | 30 ------------------------------
 2 files changed, 37 deletions(-)

diff --git a/include/linux/stop_machine.h b/include/linux/stop_machine.h
index f9a0c6189852..648298f877da 100644
--- a/include/linux/stop_machine.h
+++ b/include/linux/stop_machine.h
@@ -33,7 +33,6 @@ int stop_two_cpus(unsigned int cpu1, unsigned int cpu2, cpu_stop_fn_t fn, void *
 bool stop_one_cpu_nowait(unsigned int cpu, cpu_stop_fn_t fn, void *arg,
 			 struct cpu_stop_work *work_buf);
 int stop_cpus(const struct cpumask *cpumask, cpu_stop_fn_t fn, void *arg);
-int try_stop_cpus(const struct cpumask *cpumask, cpu_stop_fn_t fn, void *arg);
 void stop_machine_park(int cpu);
 void stop_machine_unpark(int cpu);
 void stop_machine_yield(const struct cpumask *cpumask);
@@ -90,12 +89,6 @@ static inline int stop_cpus(const struct cpumask *cpumask,
 	return -ENOENT;
 }
 
-static inline int try_stop_cpus(const struct cpumask *cpumask,
-				cpu_stop_fn_t fn, void *arg)
-{
-	return stop_cpus(cpumask, fn, arg);
-}
-
 #endif	/* CONFIG_SMP */
 
 /*
diff --git a/kernel/stop_machine.c b/kernel/stop_machine.c
index 1fe34a9fabc2..5d68ec4c4015 100644
--- a/kernel/stop_machine.c
+++ b/kernel/stop_machine.c
@@ -453,36 +453,6 @@ int stop_cpus(const struct cpumask *cpumask, cpu_stop_fn_t fn, void *arg)
 	return ret;
 }
 
-/**
- * try_stop_cpus - try to stop multiple cpus
- * @cpumask: cpus to stop
- * @fn: function to execute
- * @arg: argument to @fn
- *
- * Identical to stop_cpus() except that it fails with -EAGAIN if
- * someone else is already using the facility.
- *
- * CONTEXT:
- * Might sleep.
- *
- * RETURNS:
- * -EAGAIN if someone else is already stopping cpus, -ENOENT if
- * @fn(@arg) was not executed at all because all cpus in @cpumask were
- * offline; otherwise, 0 if all executions of @fn returned 0, any non
- * zero return value if any returned non zero.
- */
-int try_stop_cpus(const struct cpumask *cpumask, cpu_stop_fn_t fn, void *arg)
-{
-	int ret;
-
-	/* static works are used, process one request at a time */
-	if (!mutex_trylock(&stop_cpus_mutex))
-		return -EAGAIN;
-	ret = __stop_cpus(cpumask, fn, arg);
-	mutex_unlock(&stop_cpus_mutex);
-	return ret;
-}
-
 static int cpu_stop_should_run(unsigned int cpu)
 {
 	struct cpu_stopper *stopper = &per_cpu(cpu_stopper, cpu);
-- 
cgit v1.2.3-59-g8ed1b


From 53a23364b6b0c679a8ecfc48e74d652f18e3631f Mon Sep 17 00:00:00 2001
From: Qian Cai <cai@lca.pw>
Date: Thu, 19 Dec 2019 09:03:14 -0500
Subject: sched/core: Remove unused variable from set_user_nice()

This commit left behind an unused variable:

  5443a0be6121 ("sched: Use fair:prio_changed() instead of ad-hoc implementation") left behind an unused variable.

  kernel/sched/core.c: In function 'set_user_nice':
  kernel/sched/core.c:4507:16: warning: variable 'delta' set but not used
    int old_prio, delta;
                ^~~~~

Signed-off-by: Qian Cai <cai@lca.pw>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Fixes: 5443a0be6121 ("sched: Use fair:prio_changed() instead of ad-hoc implementation")
Link: https://lkml.kernel.org/r/20191219140314.1252-1-cai@lca.pw
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 kernel/sched/core.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 15508c202bf5..1f6c094520e0 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -4504,7 +4504,7 @@ static inline int rt_effective_prio(struct task_struct *p, int prio)
 void set_user_nice(struct task_struct *p, long nice)
 {
 	bool queued, running;
-	int old_prio, delta;
+	int old_prio;
 	struct rq_flags rf;
 	struct rq *rq;
 
@@ -4538,7 +4538,6 @@ void set_user_nice(struct task_struct *p, long nice)
 	set_load_weight(p, true);
 	old_prio = p->prio;
 	p->prio = effective_prio(p);
-	delta = p->prio - old_prio;
 
 	if (queued)
 		enqueue_task(rq, p, ENQUEUE_RESTORE | ENQUEUE_NOCLOCK);
-- 
cgit v1.2.3-59-g8ed1b


From 17346452b25b98acfb395d2a82ec2e4ad0cb7a01 Mon Sep 17 00:00:00 2001
From: Viresh Kumar <viresh.kumar@linaro.org>
Date: Thu, 14 Nov 2019 16:19:27 +0530
Subject: sched/fair: Make sched-idle CPU selection consistent throughout

There are instances where we keep searching for an idle CPU despite
already having a sched-idle CPU (in find_idlest_group_cpu(),
select_idle_smt() and select_idle_cpu() and then there are places where
we don't necessarily do that and return a sched-idle CPU as soon as we
find one (in select_idle_sibling()). This looks a bit inconsistent and
it may be worth having the same policy everywhere.

On the other hand, choosing a sched-idle CPU over a idle one shall be
beneficial from performance and power point of view as well, as we don't
need to get the CPU online from a deep idle state which wastes quite a
lot of time and energy and delays the scheduling of the newly woken up
task.

This patch tries to simplify code around sched-idle CPU selection and
make it consistent throughout.

Testing is done with the help of rt-app on hikey board (ARM64 octa-core,
2 clusters, 0-3 and 4-7). The cpufreq governor was set to performance to
avoid any side affects from CPU frequency. Following are the tests
performed:

Test 1: 1-cfs-task:

 A single SCHED_NORMAL task is pinned to CPU5 which runs for 2333 us
 out of 7777 us (so gives time for the cluster to go in deep idle
 state).

Test 2: 1-cfs-1-idle-task:

 A single SCHED_NORMAL task is pinned on CPU5 and single SCHED_IDLE
 task is pinned on CPU6 (to make sure cluster 1 doesn't go in deep idle
 state).

Test 3: 1-cfs-8-idle-task:

 A single SCHED_NORMAL task is pinned on CPU5 and eight SCHED_IDLE
 tasks are created which run forever (not pinned anywhere, so they run
 on all CPUs). Checked with kernelshark that as soon as NORMAL task
 sleeps, the SCHED_IDLE task starts running on CPU5.

And here are the results on mean latency (in us), using the "st" tool.

  $ st 1-cfs-task/rt-app-cfs_thread-0.log
  N       min     max     sum     mean    stddev
  642     90      592     197180  307.134 109.906

  $ st 1-cfs-1-idle-task/rt-app-cfs_thread-0.log
  N       min     max     sum     mean    stddev
  642     67      311     113850  177.336 41.4251

  $ st 1-cfs-8-idle-task/rt-app-cfs_thread-0.log
  N       min     max     sum     mean    stddev
  643     29      173     41364   64.3297 13.2344

The mean latency when we need to:

 - wakeup from deep idle state is 307 us.
 - wakeup from shallow idle state is 177 us.
 - preempt a SCHED_IDLE task is 64 us.

Signed-off-by: Viresh Kumar <viresh.kumar@linaro.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Vincent Guittot <vincent.guittot@linaro.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: https://lkml.kernel.org/r/b90cbcce608cef4e02a7bbfe178335f76d201bab.1573728344.git.viresh.kumar@linaro.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 kernel/sched/fair.c | 34 ++++++++++++----------------------
 1 file changed, 12 insertions(+), 22 deletions(-)

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 8da0222924cf..1f34fa9732d8 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -5588,7 +5588,7 @@ find_idlest_group_cpu(struct sched_group *group, struct task_struct *p, int this
 	unsigned int min_exit_latency = UINT_MAX;
 	u64 latest_idle_timestamp = 0;
 	int least_loaded_cpu = this_cpu;
-	int shallowest_idle_cpu = -1, si_cpu = -1;
+	int shallowest_idle_cpu = -1;
 	int i;
 
 	/* Check if we have any choice: */
@@ -5597,6 +5597,9 @@ find_idlest_group_cpu(struct sched_group *group, struct task_struct *p, int this
 
 	/* Traverse only the allowed CPUs */
 	for_each_cpu_and(i, sched_group_span(group), p->cpus_ptr) {
+		if (sched_idle_cpu(i))
+			return i;
+
 		if (available_idle_cpu(i)) {
 			struct rq *rq = cpu_rq(i);
 			struct cpuidle_state *idle = idle_get_state(rq);
@@ -5619,12 +5622,7 @@ find_idlest_group_cpu(struct sched_group *group, struct task_struct *p, int this
 				latest_idle_timestamp = rq->idle_stamp;
 				shallowest_idle_cpu = i;
 			}
-		} else if (shallowest_idle_cpu == -1 && si_cpu == -1) {
-			if (sched_idle_cpu(i)) {
-				si_cpu = i;
-				continue;
-			}
-
+		} else if (shallowest_idle_cpu == -1) {
 			load = cpu_load(cpu_rq(i));
 			if (load < min_load) {
 				min_load = load;
@@ -5633,11 +5631,7 @@ find_idlest_group_cpu(struct sched_group *group, struct task_struct *p, int this
 		}
 	}
 
-	if (shallowest_idle_cpu != -1)
-		return shallowest_idle_cpu;
-	if (si_cpu != -1)
-		return si_cpu;
-	return least_loaded_cpu;
+	return shallowest_idle_cpu != -1 ? shallowest_idle_cpu : least_loaded_cpu;
 }
 
 static inline int find_idlest_cpu(struct sched_domain *sd, struct task_struct *p,
@@ -5790,7 +5784,7 @@ static int select_idle_core(struct task_struct *p, struct sched_domain *sd, int
  */
 static int select_idle_smt(struct task_struct *p, int target)
 {
-	int cpu, si_cpu = -1;
+	int cpu;
 
 	if (!static_branch_likely(&sched_smt_present))
 		return -1;
@@ -5798,13 +5792,11 @@ static int select_idle_smt(struct task_struct *p, int target)
 	for_each_cpu(cpu, cpu_smt_mask(target)) {
 		if (!cpumask_test_cpu(cpu, p->cpus_ptr))
 			continue;
-		if (available_idle_cpu(cpu))
+		if (available_idle_cpu(cpu) || sched_idle_cpu(cpu))
 			return cpu;
-		if (si_cpu == -1 && sched_idle_cpu(cpu))
-			si_cpu = cpu;
 	}
 
-	return si_cpu;
+	return -1;
 }
 
 #else /* CONFIG_SCHED_SMT */
@@ -5834,7 +5826,7 @@ static int select_idle_cpu(struct task_struct *p, struct sched_domain *sd, int t
 	u64 time, cost;
 	s64 delta;
 	int this = smp_processor_id();
-	int cpu, nr = INT_MAX, si_cpu = -1;
+	int cpu, nr = INT_MAX;
 
 	this_sd = rcu_dereference(*this_cpu_ptr(&sd_llc));
 	if (!this_sd)
@@ -5864,11 +5856,9 @@ static int select_idle_cpu(struct task_struct *p, struct sched_domain *sd, int t
 
 	for_each_cpu_wrap(cpu, cpus, target) {
 		if (!--nr)
-			return si_cpu;
-		if (available_idle_cpu(cpu))
+			return -1;
+		if (available_idle_cpu(cpu) || sched_idle_cpu(cpu))
 			break;
-		if (si_cpu == -1 && sched_idle_cpu(cpu))
-			si_cpu = cpu;
 	}
 
 	time = cpu_clock(this) - time;
-- 
cgit v1.2.3-59-g8ed1b


From 59fe675248ffc37d4167e9ec6920a2f3d5ec67bb Mon Sep 17 00:00:00 2001
From: Valentin Schneider <valentin.schneider@arm.com>
Date: Wed, 11 Dec 2019 11:38:47 +0000
Subject: sched/uclamp: Remove uclamp_util()

The sole user of uclamp_util(), schedutil_cpu_util(), was made to use
uclamp_util_with() instead in commit:

  af24bde8df20 ("sched/uclamp: Add uclamp support to energy_compute()")

From then on, uclamp_util() has remained unused. Being a simple wrapper
around uclamp_util_with(), we can get rid of it and win back a few lines.

Tested-By: Dietmar Eggemann <dietmar.eggemann@arm.com>
Suggested-by: Dietmar Eggemann <dietmar.eggemann@arm.com>
Signed-off-by: Valentin Schneider <valentin.schneider@arm.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Dietmar Eggemann <dietmar.eggemann@arm.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: https://lkml.kernel.org/r/20191211113851.24241-2-valentin.schneider@arm.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 kernel/sched/sched.h | 9 ---------
 1 file changed, 9 deletions(-)

diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 280a3c735935..d9b24513d71d 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -2324,21 +2324,12 @@ unsigned int uclamp_util_with(struct rq *rq, unsigned int util,
 
 	return clamp(util, min_util, max_util);
 }
-
-static inline unsigned int uclamp_util(struct rq *rq, unsigned int util)
-{
-	return uclamp_util_with(rq, util, NULL);
-}
 #else /* CONFIG_UCLAMP_TASK */
 static inline unsigned int uclamp_util_with(struct rq *rq, unsigned int util,
 					    struct task_struct *p)
 {
 	return util;
 }
-static inline unsigned int uclamp_util(struct rq *rq, unsigned int util)
-{
-	return util;
-}
 #endif /* CONFIG_UCLAMP_TASK */
 
 #ifdef arch_scale_freq_capacity
-- 
cgit v1.2.3-59-g8ed1b


From 686516b55e98edf18c2a02d36aaaa6f4c0f6c39c Mon Sep 17 00:00:00 2001
From: Valentin Schneider <valentin.schneider@arm.com>
Date: Wed, 11 Dec 2019 11:38:48 +0000
Subject: sched/uclamp: Make uclamp util helpers use and return UL values

Vincent pointed out recently that the canonical type for utilization
values is 'unsigned long'. Internally uclamp uses 'unsigned int' values for
cache optimization, but this doesn't have to be exported to its users.

Make the uclamp helpers that deal with utilization use and return unsigned
long values.

Tested-By: Dietmar Eggemann <dietmar.eggemann@arm.com>
Signed-off-by: Valentin Schneider <valentin.schneider@arm.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Quentin Perret <qperret@google.com>
Reviewed-by: Vincent Guittot <vincent.guittot@linaro.org>
Reviewed-by: Dietmar Eggemann <dietmar.eggemann@arm.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: https://lkml.kernel.org/r/20191211113851.24241-3-valentin.schneider@arm.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 kernel/sched/core.c  |  6 +++---
 kernel/sched/sched.h | 14 +++++++-------
 2 files changed, 10 insertions(+), 10 deletions(-)

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 1f6c094520e0..e7b08d52db93 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -919,17 +919,17 @@ uclamp_eff_get(struct task_struct *p, enum uclamp_id clamp_id)
 	return uc_req;
 }
 
-unsigned int uclamp_eff_value(struct task_struct *p, enum uclamp_id clamp_id)
+unsigned long uclamp_eff_value(struct task_struct *p, enum uclamp_id clamp_id)
 {
 	struct uclamp_se uc_eff;
 
 	/* Task currently refcounted: use back-annotated (effective) value */
 	if (p->uclamp[clamp_id].active)
-		return p->uclamp[clamp_id].value;
+		return (unsigned long)p->uclamp[clamp_id].value;
 
 	uc_eff = uclamp_eff_get(p, clamp_id);
 
-	return uc_eff.value;
+	return (unsigned long)uc_eff.value;
 }
 
 /*
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index d9b24513d71d..b478474ea847 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -2300,14 +2300,14 @@ static inline void cpufreq_update_util(struct rq *rq, unsigned int flags) {}
 #endif /* CONFIG_CPU_FREQ */
 
 #ifdef CONFIG_UCLAMP_TASK
-unsigned int uclamp_eff_value(struct task_struct *p, enum uclamp_id clamp_id);
+unsigned long uclamp_eff_value(struct task_struct *p, enum uclamp_id clamp_id);
 
 static __always_inline
-unsigned int uclamp_util_with(struct rq *rq, unsigned int util,
-			      struct task_struct *p)
+unsigned long uclamp_util_with(struct rq *rq, unsigned long util,
+			       struct task_struct *p)
 {
-	unsigned int min_util = READ_ONCE(rq->uclamp[UCLAMP_MIN].value);
-	unsigned int max_util = READ_ONCE(rq->uclamp[UCLAMP_MAX].value);
+	unsigned long min_util = READ_ONCE(rq->uclamp[UCLAMP_MIN].value);
+	unsigned long max_util = READ_ONCE(rq->uclamp[UCLAMP_MAX].value);
 
 	if (p) {
 		min_util = max(min_util, uclamp_eff_value(p, UCLAMP_MIN));
@@ -2325,8 +2325,8 @@ unsigned int uclamp_util_with(struct rq *rq, unsigned int util,
 	return clamp(util, min_util, max_util);
 }
 #else /* CONFIG_UCLAMP_TASK */
-static inline unsigned int uclamp_util_with(struct rq *rq, unsigned int util,
-					    struct task_struct *p)
+static inline unsigned long uclamp_util_with(struct rq *rq, unsigned long util,
+					     struct task_struct *p)
 {
 	return util;
 }
-- 
cgit v1.2.3-59-g8ed1b


From d2b58a286e89824900d501db0be1d4f6aed474fc Mon Sep 17 00:00:00 2001
From: Valentin Schneider <valentin.schneider@arm.com>
Date: Wed, 11 Dec 2019 11:38:49 +0000
Subject: sched/uclamp: Rename uclamp_util_with() into uclamp_rq_util_with()

The current helper returns (CPU) rq utilization with uclamp restrictions
taken into account. A uclamp task utilization helper would be quite
helpful, but this requires some renaming.

Prepare the code for the introduction of a uclamp_task_util() by renaming
the existing uclamp_util_with() to uclamp_rq_util_with().

Tested-By: Dietmar Eggemann <dietmar.eggemann@arm.com>
Signed-off-by: Valentin Schneider <valentin.schneider@arm.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Quentin Perret <qperret@google.com>
Reviewed-by: Vincent Guittot <vincent.guittot@linaro.org>
Reviewed-by: Dietmar Eggemann <dietmar.eggemann@arm.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: https://lkml.kernel.org/r/20191211113851.24241-4-valentin.schneider@arm.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 kernel/sched/cpufreq_schedutil.c | 2 +-
 kernel/sched/sched.h             | 9 +++++----
 2 files changed, 6 insertions(+), 5 deletions(-)

diff --git a/kernel/sched/cpufreq_schedutil.c b/kernel/sched/cpufreq_schedutil.c
index 9b8916fd00a2..7fbaee24c824 100644
--- a/kernel/sched/cpufreq_schedutil.c
+++ b/kernel/sched/cpufreq_schedutil.c
@@ -238,7 +238,7 @@ unsigned long schedutil_cpu_util(int cpu, unsigned long util_cfs,
 	 */
 	util = util_cfs + cpu_util_rt(rq);
 	if (type == FREQUENCY_UTIL)
-		util = uclamp_util_with(rq, util, p);
+		util = uclamp_rq_util_with(rq, util, p);
 
 	dl_util = cpu_util_dl(rq);
 
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index b478474ea847..1a88dc8ad11b 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -2303,8 +2303,8 @@ static inline void cpufreq_update_util(struct rq *rq, unsigned int flags) {}
 unsigned long uclamp_eff_value(struct task_struct *p, enum uclamp_id clamp_id);
 
 static __always_inline
-unsigned long uclamp_util_with(struct rq *rq, unsigned long util,
-			       struct task_struct *p)
+unsigned long uclamp_rq_util_with(struct rq *rq, unsigned long util,
+				  struct task_struct *p)
 {
 	unsigned long min_util = READ_ONCE(rq->uclamp[UCLAMP_MIN].value);
 	unsigned long max_util = READ_ONCE(rq->uclamp[UCLAMP_MAX].value);
@@ -2325,8 +2325,9 @@ unsigned long uclamp_util_with(struct rq *rq, unsigned long util,
 	return clamp(util, min_util, max_util);
 }
 #else /* CONFIG_UCLAMP_TASK */
-static inline unsigned long uclamp_util_with(struct rq *rq, unsigned long util,
-					     struct task_struct *p)
+static inline
+unsigned long uclamp_rq_util_with(struct rq *rq, unsigned long util,
+				  struct task_struct *p)
 {
 	return util;
 }
-- 
cgit v1.2.3-59-g8ed1b


From a7008c07a568278ed2763436404752a98004c7ff Mon Sep 17 00:00:00 2001
From: Valentin Schneider <valentin.schneider@arm.com>
Date: Wed, 11 Dec 2019 11:38:50 +0000
Subject: sched/fair: Make task_fits_capacity() consider uclamp restrictions

task_fits_capacity() drives CPU selection at wakeup time, and is also used
to detect misfit tasks. Right now it does so by comparing task_util_est()
with a CPU's capacity, but doesn't take into account uclamp restrictions.

There's a few interesting uses that can come out of doing this. For
instance, a low uclamp.max value could prevent certain tasks from being
flagged as misfit tasks, so they could merrily remain on low-capacity CPUs.
Similarly, a high uclamp.min value would steer tasks towards high capacity
CPUs at wakeup (and, should that fail, later steered via misfit balancing),
so such "boosted" tasks would favor CPUs of higher capacity.

Introduce uclamp_task_util() and make task_fits_capacity() use it.

Tested-By: Dietmar Eggemann <dietmar.eggemann@arm.com>
Signed-off-by: Valentin Schneider <valentin.schneider@arm.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Quentin Perret <qperret@google.com>
Reviewed-by: Vincent Guittot <vincent.guittot@linaro.org>
Reviewed-by: Dietmar Eggemann <dietmar.eggemann@arm.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: https://lkml.kernel.org/r/20191211113851.24241-5-valentin.schneider@arm.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 kernel/sched/fair.c | 16 +++++++++++++++-
 1 file changed, 15 insertions(+), 1 deletion(-)

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 1f34fa9732d8..26c59bc5b2ed 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -3711,6 +3711,20 @@ static inline unsigned long task_util_est(struct task_struct *p)
 	return max(task_util(p), _task_util_est(p));
 }
 
+#ifdef CONFIG_UCLAMP_TASK
+static inline unsigned long uclamp_task_util(struct task_struct *p)
+{
+	return clamp(task_util_est(p),
+		     uclamp_eff_value(p, UCLAMP_MIN),
+		     uclamp_eff_value(p, UCLAMP_MAX));
+}
+#else
+static inline unsigned long uclamp_task_util(struct task_struct *p)
+{
+	return task_util_est(p);
+}
+#endif
+
 static inline void util_est_enqueue(struct cfs_rq *cfs_rq,
 				    struct task_struct *p)
 {
@@ -3822,7 +3836,7 @@ done:
 
 static inline int task_fits_capacity(struct task_struct *p, long capacity)
 {
-	return fits_capacity(task_util_est(p), capacity);
+	return fits_capacity(uclamp_task_util(p), capacity);
 }
 
 static inline void update_misfit_status(struct task_struct *p, struct rq *rq)
-- 
cgit v1.2.3-59-g8ed1b


From 1d42509e475cdc8542aa5b3e03a7e845244f4f57 Mon Sep 17 00:00:00 2001
From: Valentin Schneider <valentin.schneider@arm.com>
Date: Wed, 11 Dec 2019 11:38:51 +0000
Subject: sched/fair: Make EAS wakeup placement consider uclamp restrictions

task_fits_capacity() has just been made uclamp-aware, and
find_energy_efficient_cpu() needs to go through the same treatment.

Things are somewhat different here however - using the task max clamp isn't
sufficient. Consider the following setup:

  The target runqueue, rq:
    rq.cpu_capacity_orig = 512
    rq.cfs.avg.util_avg = 200
    rq.uclamp.max = 768 // the max p.uclamp.max of all enqueued p's is 768

  The waking task, p (not yet enqueued on rq):
    p.util_est = 600
    p.uclamp.max = 100

Now, consider the following code which doesn't use the rq clamps:

  util = uclamp_task_util(p);
  // Does the task fit in the spare CPU capacity?
  cpu = cpu_of(rq);
  fits_capacity(util, cpu_capacity(cpu) - cpu_util(cpu))

This would lead to:

  util = 100;
  fits_capacity(100, 512 - 200)

fits_capacity() would return true. However, enqueuing p on that CPU *will*
cause it to become overutilized since rq clamp values are max-aggregated,
so we'd remain with

  rq.uclamp.max = 768

which comes from the other tasks already enqueued on rq. Thus, we could
select a high enough frequency to reach beyond 0.8 * 512 utilization
(== overutilized) after enqueuing p on rq. What find_energy_efficient_cpu()
needs here is uclamp_rq_util_with() which lets us peek at the future
utilization landscape, including rq-wide uclamp values.

Make find_energy_efficient_cpu() use uclamp_rq_util_with() for its
fits_capacity() check. This is in line with what compute_energy() ends up
using for estimating utilization.

Tested-By: Dietmar Eggemann <dietmar.eggemann@arm.com>
Suggested-by: Quentin Perret <qperret@google.com>
Signed-off-by: Valentin Schneider <valentin.schneider@arm.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Vincent Guittot <vincent.guittot@linaro.org>
Reviewed-by: Dietmar Eggemann <dietmar.eggemann@arm.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: https://lkml.kernel.org/r/20191211113851.24241-6-valentin.schneider@arm.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 kernel/sched/fair.c | 12 ++++++++++--
 1 file changed, 10 insertions(+), 2 deletions(-)

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 26c59bc5b2ed..2d170b5da0e3 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -6273,9 +6273,18 @@ static int find_energy_efficient_cpu(struct task_struct *p, int prev_cpu)
 			if (!cpumask_test_cpu(cpu, p->cpus_ptr))
 				continue;
 
-			/* Skip CPUs that will be overutilized. */
 			util = cpu_util_next(cpu, p, cpu);
 			cpu_cap = capacity_of(cpu);
+			spare_cap = cpu_cap - util;
+
+			/*
+			 * Skip CPUs that cannot satisfy the capacity request.
+			 * IOW, placing the task there would make the CPU
+			 * overutilized. Take uclamp into account to see how
+			 * much capacity we can get out of the CPU; this is
+			 * aligned with schedutil_cpu_util().
+			 */
+			util = uclamp_rq_util_with(cpu_rq(cpu), util, p);
 			if (!fits_capacity(util, cpu_cap))
 				continue;
 
@@ -6290,7 +6299,6 @@ static int find_energy_efficient_cpu(struct task_struct *p, int prev_cpu)
 			 * Find the CPU with the maximum spare capacity in
 			 * the performance domain
 			 */
-			spare_cap = cpu_cap - util;
 			if (spare_cap > max_spare_cap) {
 				max_spare_cap = spare_cap;
 				max_spare_cap_cpu = cpu;
-- 
cgit v1.2.3-59-g8ed1b


From 804d402fb6f6487b825aae8cf42fda6426c62867 Mon Sep 17 00:00:00 2001
From: Qais Yousef <qais.yousef@arm.com>
Date: Wed, 9 Oct 2019 11:46:11 +0100
Subject: sched/rt: Make RT capacity-aware

Capacity Awareness refers to the fact that on heterogeneous systems
(like Arm big.LITTLE), the capacity of the CPUs is not uniform, hence
when placing tasks we need to be aware of this difference of CPU
capacities.

In such scenarios we want to ensure that the selected CPU has enough
capacity to meet the requirement of the running task. Enough capacity
means here that capacity_orig_of(cpu) >= task.requirement.

The definition of task.requirement is dependent on the scheduling class.

For CFS, utilization is used to select a CPU that has >= capacity value
than the cfs_task.util.

	capacity_orig_of(cpu) >= cfs_task.util

DL isn't capacity aware at the moment but can make use of the bandwidth
reservation to implement that in a similar manner CFS uses utilization.
The following patchset implements that:

https://lore.kernel.org/lkml/20190506044836.2914-1-luca.abeni@santannapisa.it/

	capacity_orig_of(cpu)/SCHED_CAPACITY >= dl_deadline/dl_runtime

For RT we don't have a per task utilization signal and we lack any
information in general about what performance requirement the RT task
needs. But with the introduction of uclamp, RT tasks can now control
that by setting uclamp_min to guarantee a minimum performance point.

ATM the uclamp value are only used for frequency selection; but on
heterogeneous systems this is not enough and we need to ensure that the
capacity of the CPU is >= uclamp_min. Which is what implemented here.

	capacity_orig_of(cpu) >= rt_task.uclamp_min

Note that by default uclamp.min is 1024, which means that RT tasks will
always be biased towards the big CPUs, which make for a better more
predictable behavior for the default case.

Must stress that the bias acts as a hint rather than a definite
placement strategy. For example, if all big cores are busy executing
other RT tasks we can't guarantee that a new RT task will be placed
there.

On non-heterogeneous systems the original behavior of RT should be
retained. Similarly if uclamp is not selected in the config.

[ mingo: Minor edits to comments. ]

Signed-off-by: Qais Yousef <qais.yousef@arm.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Dietmar Eggemann <dietmar.eggemann@arm.com>
Reviewed-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: https://lkml.kernel.org/r/20191009104611.15363-1-qais.yousef@arm.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 kernel/sched/cpupri.c | 25 ++++++++++++++--
 kernel/sched/cpupri.h |  4 ++-
 kernel/sched/rt.c     | 83 +++++++++++++++++++++++++++++++++++++++++----------
 3 files changed, 94 insertions(+), 18 deletions(-)

diff --git a/kernel/sched/cpupri.c b/kernel/sched/cpupri.c
index b7abca987d94..1a2719e1350a 100644
--- a/kernel/sched/cpupri.c
+++ b/kernel/sched/cpupri.c
@@ -46,6 +46,8 @@ static int convert_prio(int prio)
  * @cp: The cpupri context
  * @p: The task
  * @lowest_mask: A mask to fill in with selected CPUs (or NULL)
+ * @fitness_fn: A pointer to a function to do custom checks whether the CPU
+ *              fits a specific criteria so that we only return those CPUs.
  *
  * Note: This function returns the recommended CPUs as calculated during the
  * current invocation.  By the time the call returns, the CPUs may have in
@@ -57,7 +59,8 @@ static int convert_prio(int prio)
  * Return: (int)bool - CPUs were found
  */
 int cpupri_find(struct cpupri *cp, struct task_struct *p,
-		struct cpumask *lowest_mask)
+		struct cpumask *lowest_mask,
+		bool (*fitness_fn)(struct task_struct *p, int cpu))
 {
 	int idx = 0;
 	int task_pri = convert_prio(p->prio);
@@ -98,6 +101,8 @@ int cpupri_find(struct cpupri *cp, struct task_struct *p,
 			continue;
 
 		if (lowest_mask) {
+			int cpu;
+
 			cpumask_and(lowest_mask, p->cpus_ptr, vec->mask);
 
 			/*
@@ -108,7 +113,23 @@ int cpupri_find(struct cpupri *cp, struct task_struct *p,
 			 * condition, simply act as though we never hit this
 			 * priority level and continue on.
 			 */
-			if (cpumask_any(lowest_mask) >= nr_cpu_ids)
+			if (cpumask_empty(lowest_mask))
+				continue;
+
+			if (!fitness_fn)
+				return 1;
+
+			/* Ensure the capacity of the CPUs fit the task */
+			for_each_cpu(cpu, lowest_mask) {
+				if (!fitness_fn(p, cpu))
+					cpumask_clear_cpu(cpu, lowest_mask);
+			}
+
+			/*
+			 * If no CPU at the current priority can fit the task
+			 * continue looking
+			 */
+			if (cpumask_empty(lowest_mask))
 				continue;
 		}
 
diff --git a/kernel/sched/cpupri.h b/kernel/sched/cpupri.h
index 7dc20a3232e7..32dd520db11f 100644
--- a/kernel/sched/cpupri.h
+++ b/kernel/sched/cpupri.h
@@ -18,7 +18,9 @@ struct cpupri {
 };
 
 #ifdef CONFIG_SMP
-int  cpupri_find(struct cpupri *cp, struct task_struct *p, struct cpumask *lowest_mask);
+int  cpupri_find(struct cpupri *cp, struct task_struct *p,
+		 struct cpumask *lowest_mask,
+		 bool (*fitness_fn)(struct task_struct *p, int cpu));
 void cpupri_set(struct cpupri *cp, int cpu, int pri);
 int  cpupri_init(struct cpupri *cp);
 void cpupri_cleanup(struct cpupri *cp);
diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c
index e591d40fd645..4043abe45459 100644
--- a/kernel/sched/rt.c
+++ b/kernel/sched/rt.c
@@ -437,6 +437,45 @@ static inline int on_rt_rq(struct sched_rt_entity *rt_se)
 	return rt_se->on_rq;
 }
 
+#ifdef CONFIG_UCLAMP_TASK
+/*
+ * Verify the fitness of task @p to run on @cpu taking into account the uclamp
+ * settings.
+ *
+ * This check is only important for heterogeneous systems where uclamp_min value
+ * is higher than the capacity of a @cpu. For non-heterogeneous system this
+ * function will always return true.
+ *
+ * The function will return true if the capacity of the @cpu is >= the
+ * uclamp_min and false otherwise.
+ *
+ * Note that uclamp_min will be clamped to uclamp_max if uclamp_min
+ * > uclamp_max.
+ */
+static inline bool rt_task_fits_capacity(struct task_struct *p, int cpu)
+{
+	unsigned int min_cap;
+	unsigned int max_cap;
+	unsigned int cpu_cap;
+
+	/* Only heterogeneous systems can benefit from this check */
+	if (!static_branch_unlikely(&sched_asym_cpucapacity))
+		return true;
+
+	min_cap = uclamp_eff_value(p, UCLAMP_MIN);
+	max_cap = uclamp_eff_value(p, UCLAMP_MAX);
+
+	cpu_cap = capacity_orig_of(cpu);
+
+	return cpu_cap >= min(min_cap, max_cap);
+}
+#else
+static inline bool rt_task_fits_capacity(struct task_struct *p, int cpu)
+{
+	return true;
+}
+#endif
+
 #ifdef CONFIG_RT_GROUP_SCHED
 
 static inline u64 sched_rt_runtime(struct rt_rq *rt_rq)
@@ -1391,6 +1430,7 @@ select_task_rq_rt(struct task_struct *p, int cpu, int sd_flag, int flags)
 {
 	struct task_struct *curr;
 	struct rq *rq;
+	bool test;
 
 	/* For anything but wake ups, just return the task_cpu */
 	if (sd_flag != SD_BALANCE_WAKE && sd_flag != SD_BALANCE_FORK)
@@ -1422,10 +1462,16 @@ select_task_rq_rt(struct task_struct *p, int cpu, int sd_flag, int flags)
 	 *
 	 * This test is optimistic, if we get it wrong the load-balancer
 	 * will have to sort it out.
+	 *
+	 * We take into account the capacity of the CPU to ensure it fits the
+	 * requirement of the task - which is only important on heterogeneous
+	 * systems like big.LITTLE.
 	 */
-	if (curr && unlikely(rt_task(curr)) &&
-	    (curr->nr_cpus_allowed < 2 ||
-	     curr->prio <= p->prio)) {
+	test = curr &&
+	       unlikely(rt_task(curr)) &&
+	       (curr->nr_cpus_allowed < 2 || curr->prio <= p->prio);
+
+	if (test || !rt_task_fits_capacity(p, cpu)) {
 		int target = find_lowest_rq(p);
 
 		/*
@@ -1449,15 +1495,15 @@ static void check_preempt_equal_prio(struct rq *rq, struct task_struct *p)
 	 * let's hope p can move out.
 	 */
 	if (rq->curr->nr_cpus_allowed == 1 ||
-	    !cpupri_find(&rq->rd->cpupri, rq->curr, NULL))
+	    !cpupri_find(&rq->rd->cpupri, rq->curr, NULL, NULL))
 		return;
 
 	/*
 	 * p is migratable, so let's not schedule it and
 	 * see if it is pushed or pulled somewhere else.
 	 */
-	if (p->nr_cpus_allowed != 1
-	    && cpupri_find(&rq->rd->cpupri, p, NULL))
+	if (p->nr_cpus_allowed != 1 &&
+	    cpupri_find(&rq->rd->cpupri, p, NULL, NULL))
 		return;
 
 	/*
@@ -1601,7 +1647,8 @@ static void put_prev_task_rt(struct rq *rq, struct task_struct *p)
 static int pick_rt_task(struct rq *rq, struct task_struct *p, int cpu)
 {
 	if (!task_running(rq, p) &&
-	    cpumask_test_cpu(cpu, p->cpus_ptr))
+	    cpumask_test_cpu(cpu, p->cpus_ptr) &&
+	    rt_task_fits_capacity(p, cpu))
 		return 1;
 
 	return 0;
@@ -1643,7 +1690,8 @@ static int find_lowest_rq(struct task_struct *task)
 	if (task->nr_cpus_allowed == 1)
 		return -1; /* No other targets possible */
 
-	if (!cpupri_find(&task_rq(task)->rd->cpupri, task, lowest_mask))
+	if (!cpupri_find(&task_rq(task)->rd->cpupri, task, lowest_mask,
+			 rt_task_fits_capacity))
 		return -1; /* No targets found */
 
 	/*
@@ -2147,12 +2195,14 @@ skip:
  */
 static void task_woken_rt(struct rq *rq, struct task_struct *p)
 {
-	if (!task_running(rq, p) &&
-	    !test_tsk_need_resched(rq->curr) &&
-	    p->nr_cpus_allowed > 1 &&
-	    (dl_task(rq->curr) || rt_task(rq->curr)) &&
-	    (rq->curr->nr_cpus_allowed < 2 ||
-	     rq->curr->prio <= p->prio))
+	bool need_to_push = !task_running(rq, p) &&
+			    !test_tsk_need_resched(rq->curr) &&
+			    p->nr_cpus_allowed > 1 &&
+			    (dl_task(rq->curr) || rt_task(rq->curr)) &&
+			    (rq->curr->nr_cpus_allowed < 2 ||
+			     rq->curr->prio <= p->prio);
+
+	if (need_to_push || !rt_task_fits_capacity(p, cpu_of(rq)))
 		push_rt_tasks(rq);
 }
 
@@ -2224,7 +2274,10 @@ static void switched_to_rt(struct rq *rq, struct task_struct *p)
 	 */
 	if (task_on_rq_queued(p) && rq->curr != p) {
 #ifdef CONFIG_SMP
-		if (p->nr_cpus_allowed > 1 && rq->rt.overloaded)
+		bool need_to_push = rq->rt.overloaded ||
+				    !rt_task_fits_capacity(p, cpu_of(rq));
+
+		if (p->nr_cpus_allowed > 1 && need_to_push)
 			rt_queue_push_tasks(rq);
 #endif /* CONFIG_SMP */
 		if (p->prio < rq->curr->prio && cpu_online(cpu_of(rq)))
-- 
cgit v1.2.3-59-g8ed1b


From db5793c5993d265fe6644b6638fcb0758f6b5347 Mon Sep 17 00:00:00 2001
From: Jisheng Zhang <Jisheng.Zhang@synaptics.com>
Date: Wed, 18 Dec 2019 05:31:25 +0000
Subject: watchdog: Remove soft_lockup_hrtimer_cnt and related code

After commit 9cf57731b63e ("watchdog/softlockup: Replace "watchdog/%u"
threads with cpu_stop_work"), the percpu soft_lockup_hrtimer_cnt is
not used any more, so remove it and related code.

Signed-off-by: Jisheng Zhang <Jisheng.Zhang@synaptics.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20191218131720.4146aea2@xhacker.debian
---
 kernel/watchdog.c | 3 ---
 1 file changed, 3 deletions(-)

diff --git a/kernel/watchdog.c b/kernel/watchdog.c
index f41334ef0971..0621301ae8cf 100644
--- a/kernel/watchdog.c
+++ b/kernel/watchdog.c
@@ -173,7 +173,6 @@ static DEFINE_PER_CPU(struct hrtimer, watchdog_hrtimer);
 static DEFINE_PER_CPU(bool, softlockup_touch_sync);
 static DEFINE_PER_CPU(bool, soft_watchdog_warn);
 static DEFINE_PER_CPU(unsigned long, hrtimer_interrupts);
-static DEFINE_PER_CPU(unsigned long, soft_lockup_hrtimer_cnt);
 static DEFINE_PER_CPU(struct task_struct *, softlockup_task_ptr_saved);
 static DEFINE_PER_CPU(unsigned long, hrtimer_interrupts_saved);
 static unsigned long soft_lockup_nmi_warn;
@@ -350,8 +349,6 @@ static DEFINE_PER_CPU(struct cpu_stop_work, softlockup_stop_work);
  */
 static int softlockup_fn(void *data)
 {
-	__this_cpu_write(soft_lockup_hrtimer_cnt,
-			 __this_cpu_read(hrtimer_interrupts));
 	__touch_watchdog();
 	complete(this_cpu_ptr(&softlockup_completion));
 
-- 
cgit v1.2.3-59-g8ed1b


From 5f68eb19b5716f8cf3ccfa833cffd1522813b0e8 Mon Sep 17 00:00:00 2001
From: Vincent Guittot <vincent.guittot@linaro.org>
Date: Fri, 20 Dec 2019 12:04:53 +0100
Subject: sched/fair : Improve update_sd_pick_busiest for spare capacity case

Similarly to calculate_imbalance() and find_busiest_group(), using the
number of idle CPUs when there is only 1 CPU in the group is not efficient
because we can't make a difference between a CPU running 1 task and a CPU
running dozens of small tasks competing for the same CPU but not enough
to overload it. More generally speaking, we should use the number of
running tasks when there is the same number of idle CPUs in a group instead
of blindly select the 1st one.

When the groups have spare capacity and the same number of idle CPUs, we
compare the number of running tasks to select the busiest group.

Signed-off-by: Vincent Guittot <vincent.guittot@linaro.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/1576839893-26930-1-git-send-email-vincent.guittot@linaro.org
---
 kernel/sched/fair.c | 14 +++++++++-----
 1 file changed, 9 insertions(+), 5 deletions(-)

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 2d170b5da0e3..35c105759dfa 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -8181,14 +8181,18 @@ static bool update_sd_pick_busiest(struct lb_env *env,
 
 	case group_has_spare:
 		/*
-		 * Select not overloaded group with lowest number of
-		 * idle cpus. We could also compare the spare capacity
-		 * which is more stable but it can end up that the
-		 * group has less spare capacity but finally more idle
+		 * Select not overloaded group with lowest number of idle cpus
+		 * and highest number of running tasks. We could also compare
+		 * the spare capacity which is more stable but it can end up
+		 * that the group has less spare capacity but finally more idle
 		 * CPUs which means less opportunity to pull tasks.
 		 */
-		if (sgs->idle_cpus >= busiest->idle_cpus)
+		if (sgs->idle_cpus > busiest->idle_cpus)
 			return false;
+		else if ((sgs->idle_cpus == busiest->idle_cpus) &&
+			 (sgs->sum_nr_running <= busiest->sum_nr_running))
+			return false;
+
 		break;
 	}
 
-- 
cgit v1.2.3-59-g8ed1b


From 323af6deaf70f204880caf94678350802682e0dc Mon Sep 17 00:00:00 2001
From: Viresh Kumar <viresh.kumar@linaro.org>
Date: Wed, 8 Jan 2020 13:57:04 +0530
Subject: sched/fair: Load balance aggressively for SCHED_IDLE CPUs

The fair scheduler performs periodic load balance on every CPU to check
if it can pull some tasks from other busy CPUs. The duration of this
periodic load balance is set to sd->balance_interval for the idle CPUs
and is calculated by multiplying the sd->balance_interval with the
sd->busy_factor (set to 32 by default) for the busy CPUs. The
multiplication is done for busy CPUs to avoid doing load balance too
often and rather spend more time executing actual task. While that is
the right thing to do for the CPUs busy with SCHED_OTHER or SCHED_BATCH
tasks, it may not be the optimal thing for CPUs running only SCHED_IDLE
tasks.

With the recent enhancements in the fair scheduler around SCHED_IDLE
CPUs, we now prefer to enqueue a newly-woken task to a SCHED_IDLE
CPU instead of other busy or idle CPUs. The same reasoning should be
applied to the load balancer as well to make it migrate tasks more
aggressively to a SCHED_IDLE CPU, as that will reduce the scheduling
latency of the migrated (SCHED_OTHER) tasks.

This patch makes minimal changes to the fair scheduler to do the next
load balance soon after the last non SCHED_IDLE task is dequeued from a
runqueue, i.e. making the CPU SCHED_IDLE. Also the sd->busy_factor is
ignored while calculating the balance_interval for such CPUs. This is
done to avoid delaying the periodic load balance by few hundred
milliseconds for SCHED_IDLE CPUs.

This is tested on ARM64 Hikey620 platform (octa-core) with the help of
rt-app and it is verified, using kernel traces, that the newly
SCHED_IDLE CPU does load balancing shortly after it becomes SCHED_IDLE
and pulls tasks from other busy CPUs.

Signed-off-by: Viresh Kumar <viresh.kumar@linaro.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Vincent Guittot <vincent.guittot@linaro.org>
Link: https://lkml.kernel.org/r/e485827eb8fe7db0943d6f3f6e0f5a4a70272781.1578471925.git.viresh.kumar@linaro.org
---
 kernel/sched/fair.c | 32 +++++++++++++++++++++-----------
 1 file changed, 21 insertions(+), 11 deletions(-)

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 35c105759dfa..d292883694b7 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -5210,6 +5210,18 @@ static inline void update_overutilized_status(struct rq *rq)
 static inline void update_overutilized_status(struct rq *rq) { }
 #endif
 
+/* Runqueue only has SCHED_IDLE tasks enqueued */
+static int sched_idle_rq(struct rq *rq)
+{
+	return unlikely(rq->nr_running == rq->cfs.idle_h_nr_running &&
+			rq->nr_running);
+}
+
+static int sched_idle_cpu(int cpu)
+{
+	return sched_idle_rq(cpu_rq(cpu));
+}
+
 /*
  * The enqueue_task method is called before nr_running is
  * increased. Here we update the fair scheduling stats and
@@ -5324,6 +5336,7 @@ static void dequeue_task_fair(struct rq *rq, struct task_struct *p, int flags)
 	struct sched_entity *se = &p->se;
 	int task_sleep = flags & DEQUEUE_SLEEP;
 	int idle_h_nr_running = task_has_idle_policy(p);
+	bool was_sched_idle = sched_idle_rq(rq);
 
 	for_each_sched_entity(se) {
 		cfs_rq = cfs_rq_of(se);
@@ -5370,6 +5383,10 @@ static void dequeue_task_fair(struct rq *rq, struct task_struct *p, int flags)
 	if (!se)
 		sub_nr_running(rq, 1);
 
+	/* balance early to pull high priority tasks */
+	if (unlikely(!was_sched_idle && sched_idle_rq(rq)))
+		rq->next_balance = jiffies;
+
 	util_est_dequeue(&rq->cfs, p, task_sleep);
 	hrtick_update(rq);
 }
@@ -5392,15 +5409,6 @@ static struct {
 
 #endif /* CONFIG_NO_HZ_COMMON */
 
-/* CPU only has SCHED_IDLE tasks enqueued */
-static int sched_idle_cpu(int cpu)
-{
-	struct rq *rq = cpu_rq(cpu);
-
-	return unlikely(rq->nr_running == rq->cfs.idle_h_nr_running &&
-			rq->nr_running);
-}
-
 static unsigned long cpu_load(struct rq *rq)
 {
 	return cfs_rq_load_avg(&rq->cfs);
@@ -9546,6 +9554,7 @@ static void rebalance_domains(struct rq *rq, enum cpu_idle_type idle)
 {
 	int continue_balancing = 1;
 	int cpu = rq->cpu;
+	int busy = idle != CPU_IDLE && !sched_idle_cpu(cpu);
 	unsigned long interval;
 	struct sched_domain *sd;
 	/* Earliest time when we have to do rebalance again */
@@ -9582,7 +9591,7 @@ static void rebalance_domains(struct rq *rq, enum cpu_idle_type idle)
 			break;
 		}
 
-		interval = get_sd_balance_interval(sd, idle != CPU_IDLE);
+		interval = get_sd_balance_interval(sd, busy);
 
 		need_serialize = sd->flags & SD_SERIALIZE;
 		if (need_serialize) {
@@ -9598,9 +9607,10 @@ static void rebalance_domains(struct rq *rq, enum cpu_idle_type idle)
 				 * state even if we migrated tasks. Update it.
 				 */
 				idle = idle_cpu(cpu) ? CPU_IDLE : CPU_NOT_IDLE;
+				busy = idle != CPU_IDLE && !sched_idle_cpu(cpu);
 			}
 			sd->last_balance = jiffies;
-			interval = get_sd_balance_interval(sd, idle != CPU_IDLE);
+			interval = get_sd_balance_interval(sd, busy);
 		}
 		if (need_serialize)
 			spin_unlock(&balancing);
-- 
cgit v1.2.3-59-g8ed1b


From 7226017ad37a888915628e59a84a2d1e57b40707 Mon Sep 17 00:00:00 2001
From: Qais Yousef <qais.yousef@arm.com>
Date: Tue, 24 Dec 2019 11:54:04 +0000
Subject: sched/uclamp: Fix a bug in propagating uclamp value in new cgroups

When a new cgroup is created, the effective uclamp value wasn't updated
with a call to cpu_util_update_eff() that looks at the hierarchy and
update to the most restrictive values.

Fix it by ensuring to call cpu_util_update_eff() when a new cgroup
becomes online.

Without this change, the newly created cgroup uses the default
root_task_group uclamp values, which is 1024 for both uclamp_{min, max},
which will cause the rq to to be clamped to max, hence cause the
system to run at max frequency.

The problem was observed on Ubuntu server and was reproduced on Debian
and Buildroot rootfs.

By default, Ubuntu and Debian create a cpu controller cgroup hierarchy
and add all tasks to it - which creates enough noise to keep the rq
uclamp value at max most of the time. Imitating this behavior makes the
problem visible in Buildroot too which otherwise looks fine since it's a
minimal userspace.

Fixes: 0b60ba2dd342 ("sched/uclamp: Propagate parent clamps")
Reported-by: Doug Smythies <dsmythies@telus.net>
Signed-off-by: Qais Yousef <qais.yousef@arm.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Tested-by: Doug Smythies <dsmythies@telus.net>
Link: https://lore.kernel.org/lkml/000701d5b965$361b6c60$a2524520$@net/
---
 kernel/sched/core.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index e7b08d52db93..d0270b14c132 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -7099,6 +7099,12 @@ static int cpu_cgroup_css_online(struct cgroup_subsys_state *css)
 
 	if (parent)
 		sched_online_group(tg, parent);
+
+#ifdef CONFIG_UCLAMP_TASK_GROUP
+	/* Propagate the effective uclamp value for the new group */
+	cpu_util_update_eff(css);
+#endif
+
 	return 0;
 }
 
-- 
cgit v1.2.3-59-g8ed1b


From dcd6dffb0a75741471297724640733fa4e958d72 Mon Sep 17 00:00:00 2001
From: Li Guanglei <guanglei.li@unisoc.com>
Date: Wed, 25 Dec 2019 15:44:04 +0800
Subject: sched/core: Fix size of rq::uclamp initialization

rq::uclamp is an array of struct uclamp_rq, make sure we clear the
whole thing.

Fixes: 69842cba9ace ("sched/uclamp: Add CPU's clamp buckets refcountinga")
Signed-off-by: Li Guanglei <guanglei.li@unisoc.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Qais Yousef <qais.yousef@arm.com>
Link: https://lkml.kernel.org/r/1577259844-12677-1-git-send-email-guangleix.li@gmail.com
---
 kernel/sched/core.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index d0270b14c132..fc1dfc007604 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -1253,7 +1253,8 @@ static void __init init_uclamp(void)
 	mutex_init(&uclamp_mutex);
 
 	for_each_possible_cpu(cpu) {
-		memset(&cpu_rq(cpu)->uclamp, 0, sizeof(struct uclamp_rq));
+		memset(&cpu_rq(cpu)->uclamp, 0,
+				sizeof(struct uclamp_rq)*UCLAMP_CNT);
 		cpu_rq(cpu)->uclamp_flags = 0;
 	}
 
-- 
cgit v1.2.3-59-g8ed1b


From 02d4ac5885a18d326b500b94808f0956dcce2832 Mon Sep 17 00:00:00 2001
From: Wei Li <liwei391@huawei.com>
Date: Thu, 26 Dec 2019 16:52:24 +0800
Subject: sched/debug: Reset watchdog on all CPUs while processing sysrq-t

Lengthy output of sysrq-t may take a lot of time on slow serial console
with lots of processes and CPUs.

So we need to reset NMI-watchdog to avoid spurious lockup messages, and
we also reset softlockup watchdogs on all other CPUs since another CPU
might be blocked waiting for us to process an IPI or stop_machine.

Add to sysrq_sched_debug_show() as what we did in show_state_filter().

Signed-off-by: Wei Li <liwei391@huawei.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
Link: https://lkml.kernel.org/r/20191226085224.48942-1-liwei391@huawei.com
---
 kernel/sched/debug.c | 11 +++++++++--
 1 file changed, 9 insertions(+), 2 deletions(-)

diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c
index f7e4579e746c..879d3ccf3806 100644
--- a/kernel/sched/debug.c
+++ b/kernel/sched/debug.c
@@ -751,9 +751,16 @@ void sysrq_sched_debug_show(void)
 	int cpu;
 
 	sched_debug_header(NULL);
-	for_each_online_cpu(cpu)
+	for_each_online_cpu(cpu) {
+		/*
+		 * Need to reset softlockup watchdogs on all CPUs, because
+		 * another CPU might be blocked waiting for us to process
+		 * an IPI or stop_machine.
+		 */
+		touch_nmi_watchdog();
+		touch_all_softlockup_watchdogs();
 		print_cpu(NULL, cpu);
-
+	}
 }
 
 /*
-- 
cgit v1.2.3-59-g8ed1b


From 35f4cd96f5551dc1b2641159e7bb7bf91de6600f Mon Sep 17 00:00:00 2001
From: Yangtao Li <tiny.windzz@gmail.com>
Date: Sat, 28 Dec 2019 16:19:12 +0000
Subject: stop_machine: Make stop_cpus() static

The function stop_cpus() is only used internally by the
stop_machine for stop multiple cpus.

Make it static.

Signed-off-by: Yangtao Li <tiny.windzz@gmail.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20191228161912.24082-1-tiny.windzz@gmail.com
---
 include/linux/stop_machine.h | 9 ---------
 kernel/stop_machine.c        | 2 +-
 2 files changed, 1 insertion(+), 10 deletions(-)

diff --git a/include/linux/stop_machine.h b/include/linux/stop_machine.h
index 648298f877da..76d8b09384a7 100644
--- a/include/linux/stop_machine.h
+++ b/include/linux/stop_machine.h
@@ -32,7 +32,6 @@ int stop_one_cpu(unsigned int cpu, cpu_stop_fn_t fn, void *arg);
 int stop_two_cpus(unsigned int cpu1, unsigned int cpu2, cpu_stop_fn_t fn, void *arg);
 bool stop_one_cpu_nowait(unsigned int cpu, cpu_stop_fn_t fn, void *arg,
 			 struct cpu_stop_work *work_buf);
-int stop_cpus(const struct cpumask *cpumask, cpu_stop_fn_t fn, void *arg);
 void stop_machine_park(int cpu);
 void stop_machine_unpark(int cpu);
 void stop_machine_yield(const struct cpumask *cpumask);
@@ -81,14 +80,6 @@ static inline bool stop_one_cpu_nowait(unsigned int cpu,
 	return false;
 }
 
-static inline int stop_cpus(const struct cpumask *cpumask,
-			    cpu_stop_fn_t fn, void *arg)
-{
-	if (cpumask_test_cpu(raw_smp_processor_id(), cpumask))
-		return stop_one_cpu(raw_smp_processor_id(), fn, arg);
-	return -ENOENT;
-}
-
 #endif	/* CONFIG_SMP */
 
 /*
diff --git a/kernel/stop_machine.c b/kernel/stop_machine.c
index 5d68ec4c4015..865bb0228ab6 100644
--- a/kernel/stop_machine.c
+++ b/kernel/stop_machine.c
@@ -442,7 +442,7 @@ static int __stop_cpus(const struct cpumask *cpumask,
  * @cpumask were offline; otherwise, 0 if all executions of @fn
  * returned 0, any non zero return value if any returned non zero.
  */
-int stop_cpus(const struct cpumask *cpumask, cpu_stop_fn_t fn, void *arg)
+static int stop_cpus(const struct cpumask *cpumask, cpu_stop_fn_t fn, void *arg)
 {
 	int ret;
 
-- 
cgit v1.2.3-59-g8ed1b


From 9dec1b6949ae9509cdc3edb2d75fda39c9db9fa2 Mon Sep 17 00:00:00 2001
From: Alex Shi <alex.shi@linux.alibaba.com>
Date: Thu, 2 Jan 2020 18:07:52 +0800
Subject: sched/cputime: move rq parameter in irqtime_account_process_tick

Every time we call irqtime_account_process_tick() is in a interrupt,
Every caller will get and assign a parameter rq = this_rq(), This is
unnecessary and increase the code size a little bit. Move the rq getting
action to irqtime_account_process_tick internally is better.

             base               with this patch
cputime.o    578792 bytes        577888 bytes

Signed-off-by: Alex Shi <alex.shi@linux.alibaba.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/1577959674-255537-1-git-send-email-alex.shi@linux.alibaba.com
---
 kernel/sched/cputime.c | 15 ++++++---------
 1 file changed, 6 insertions(+), 9 deletions(-)

diff --git a/kernel/sched/cputime.c b/kernel/sched/cputime.c
index d43318a489f2..cff3e656566d 100644
--- a/kernel/sched/cputime.c
+++ b/kernel/sched/cputime.c
@@ -355,7 +355,7 @@ void thread_group_cputime(struct task_struct *tsk, struct task_cputime *times)
  * softirq as those do not count in task exec_runtime any more.
  */
 static void irqtime_account_process_tick(struct task_struct *p, int user_tick,
-					 struct rq *rq, int ticks)
+					 int ticks)
 {
 	u64 other, cputime = TICK_NSEC * ticks;
 
@@ -381,7 +381,7 @@ static void irqtime_account_process_tick(struct task_struct *p, int user_tick,
 		account_system_index_time(p, cputime, CPUTIME_SOFTIRQ);
 	} else if (user_tick) {
 		account_user_time(p, cputime);
-	} else if (p == rq->idle) {
+	} else if (p == this_rq()->idle) {
 		account_idle_time(cputime);
 	} else if (p->flags & PF_VCPU) { /* System time or guest time */
 		account_guest_time(p, cputime);
@@ -392,14 +392,12 @@ static void irqtime_account_process_tick(struct task_struct *p, int user_tick,
 
 static void irqtime_account_idle_ticks(int ticks)
 {
-	struct rq *rq = this_rq();
-
-	irqtime_account_process_tick(current, 0, rq, ticks);
+	irqtime_account_process_tick(current, 0, ticks);
 }
 #else /* CONFIG_IRQ_TIME_ACCOUNTING */
 static inline void irqtime_account_idle_ticks(int ticks) { }
 static inline void irqtime_account_process_tick(struct task_struct *p, int user_tick,
-						struct rq *rq, int nr_ticks) { }
+						int nr_ticks) { }
 #endif /* CONFIG_IRQ_TIME_ACCOUNTING */
 
 /*
@@ -473,13 +471,12 @@ void thread_group_cputime_adjusted(struct task_struct *p, u64 *ut, u64 *st)
 void account_process_tick(struct task_struct *p, int user_tick)
 {
 	u64 cputime, steal;
-	struct rq *rq = this_rq();
 
 	if (vtime_accounting_enabled_this_cpu())
 		return;
 
 	if (sched_clock_irqtime) {
-		irqtime_account_process_tick(p, user_tick, rq, 1);
+		irqtime_account_process_tick(p, user_tick, 1);
 		return;
 	}
 
@@ -493,7 +490,7 @@ void account_process_tick(struct task_struct *p, int user_tick)
 
 	if (user_tick)
 		account_user_time(p, cputime);
-	else if ((p != rq->idle) || (irq_count() != HARDIRQ_OFFSET))
+	else if ((p != this_rq()->idle) || (irq_count() != HARDIRQ_OFFSET))
 		account_system_time(p, HARDIRQ_OFFSET, cputime);
 	else
 		account_idle_time(cputime);
-- 
cgit v1.2.3-59-g8ed1b


From fe71bbb21ee14160f73f81b113d71145327a1c0d Mon Sep 17 00:00:00 2001
From: Peng Wang <rocking@linux.alibaba.com>
Date: Fri, 3 Jan 2020 19:44:00 +0800
Subject: sched/fair: calculate delta runnable load only when it's needed

Move the code of calculation for delta_sum/delta_avg to where
it is really needed to be done.

Signed-off-by: Peng Wang <rocking@linux.alibaba.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Vincent Guittot <vincent.guittot@linaro.org>
Link: https://lkml.kernel.org/r/20200103114400.17668-1-rocking@linux.alibaba.com
---
 kernel/sched/fair.c | 11 ++++++-----
 1 file changed, 6 insertions(+), 5 deletions(-)

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index d292883694b7..32c5421b6a25 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -3366,16 +3366,17 @@ update_tg_cfs_runnable(struct cfs_rq *cfs_rq, struct sched_entity *se, struct cf
 
 	runnable_load_sum = (s64)se_runnable(se) * runnable_sum;
 	runnable_load_avg = div_s64(runnable_load_sum, LOAD_AVG_MAX);
-	delta_sum = runnable_load_sum - se_weight(se) * se->avg.runnable_load_sum;
-	delta_avg = runnable_load_avg - se->avg.runnable_load_avg;
-
-	se->avg.runnable_load_sum = runnable_sum;
-	se->avg.runnable_load_avg = runnable_load_avg;
 
 	if (se->on_rq) {
+		delta_sum = runnable_load_sum -
+				se_weight(se) * se->avg.runnable_load_sum;
+		delta_avg = runnable_load_avg - se->avg.runnable_load_avg;
 		add_positive(&cfs_rq->avg.runnable_load_avg, delta_avg);
 		add_positive(&cfs_rq->avg.runnable_load_sum, delta_sum);
 	}
+
+	se->avg.runnable_load_sum = runnable_sum;
+	se->avg.runnable_load_avg = runnable_load_avg;
 }
 
 static inline void add_tg_cfs_propagate(struct cfs_rq *cfs_rq, long runnable_sum)
-- 
cgit v1.2.3-59-g8ed1b


From 4c58f57fa6e93318a0899f70d8b99fe6bac22ce8 Mon Sep 17 00:00:00 2001
From: Peng Liu <iwtbavbm@gmail.com>
Date: Sat, 4 Jan 2020 21:08:28 +0800
Subject: sched/fair: Fix sgc->{min,max}_capacity calculation for SD_OVERLAP

commit bf475ce0a3dd ("sched/fair: Add per-CPU min capacity to
sched_group_capacity") introduced per-cpu min_capacity.

commit e3d6d0cb66f2 ("sched/fair: Add sched_group per-CPU max capacity")
introduced per-cpu max_capacity.

In the SD_OVERLAP case, the local variable 'capacity' represents the sum
of CPU capacity of all CPUs in the first sched group (sg) of the sched
domain (sd).

It is erroneously used to calculate sg's min and max CPU capacity.
To fix this use capacity_of(cpu) instead of 'capacity'.

The code which achieves this via cpu_rq(cpu)->sd->groups->sgc->capacity
(for rq->sd != NULL) can be removed since it delivers the same value as
capacity_of(cpu) which is currently only used for the (!rq->sd) case
(see update_cpu_capacity()).
An sg of the lowest sd (rq->sd or sd->child == NULL) represents a single
CPU (and hence sg->sgc->capacity == capacity_of(cpu)).

Signed-off-by: Peng Liu <iwtbavbm@gmail.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Valentin Schneider <valentin.schneider@arm.com>
Link: https://lkml.kernel.org/r/20200104130828.GA7718@iZj6chx1xj0e0buvshuecpZ
---
 kernel/sched/fair.c | 26 ++++----------------------
 1 file changed, 4 insertions(+), 22 deletions(-)

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 32c5421b6a25..e84723c5c661 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -7802,29 +7802,11 @@ void update_group_capacity(struct sched_domain *sd, int cpu)
 		 */
 
 		for_each_cpu(cpu, sched_group_span(sdg)) {
-			struct sched_group_capacity *sgc;
-			struct rq *rq = cpu_rq(cpu);
+			unsigned long cpu_cap = capacity_of(cpu);
 
-			/*
-			 * build_sched_domains() -> init_sched_groups_capacity()
-			 * gets here before we've attached the domains to the
-			 * runqueues.
-			 *
-			 * Use capacity_of(), which is set irrespective of domains
-			 * in update_cpu_capacity().
-			 *
-			 * This avoids capacity from being 0 and
-			 * causing divide-by-zero issues on boot.
-			 */
-			if (unlikely(!rq->sd)) {
-				capacity += capacity_of(cpu);
-			} else {
-				sgc = rq->sd->groups->sgc;
-				capacity += sgc->capacity;
-			}
-
-			min_capacity = min(capacity, min_capacity);
-			max_capacity = max(capacity, max_capacity);
+			capacity += cpu_cap;
+			min_capacity = min(cpu_cap, min_capacity);
+			max_capacity = max(cpu_cap, max_capacity);
 		}
 	} else  {
 		/*
-- 
cgit v1.2.3-59-g8ed1b


From 3d817689a62cf71bbb290af18cd26cf9764f38fe Mon Sep 17 00:00:00 2001
From: Wang Long <w@laoqinren.net>
Date: Wed, 18 Dec 2019 20:38:18 +0800
Subject: sched/psi: create /proc/pressure and /proc/pressure/{io|memory|cpu}
 only when psi enabled

when CONFIG_PSI_DEFAULT_DISABLED set to N or the command line set psi=0,
I think we should not create /proc/pressure and
/proc/pressure/{io|memory|cpu}.

In the future, user maybe determine whether the psi feature is enabled by
checking the existence of the /proc/pressure dir or
/proc/pressure/{io|memory|cpu} files.

Signed-off-by: Wang Long <w@laoqinren.net>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Link: https://lkml.kernel.org/r/1576672698-32504-1-git-send-email-w@laoqinren.net
---
 kernel/sched/psi.c | 10 ++++++----
 1 file changed, 6 insertions(+), 4 deletions(-)

diff --git a/kernel/sched/psi.c b/kernel/sched/psi.c
index ce8f6748678a..db7b50bba3f1 100644
--- a/kernel/sched/psi.c
+++ b/kernel/sched/psi.c
@@ -1280,10 +1280,12 @@ static const struct file_operations psi_cpu_fops = {
 
 static int __init psi_proc_init(void)
 {
-	proc_mkdir("pressure", NULL);
-	proc_create("pressure/io", 0, NULL, &psi_io_fops);
-	proc_create("pressure/memory", 0, NULL, &psi_memory_fops);
-	proc_create("pressure/cpu", 0, NULL, &psi_cpu_fops);
+	if (psi_enable) {
+		proc_mkdir("pressure", NULL);
+		proc_create("pressure/io", 0, NULL, &psi_io_fops);
+		proc_create("pressure/memory", 0, NULL, &psi_memory_fops);
+		proc_create("pressure/cpu", 0, NULL, &psi_cpu_fops);
+	}
 	return 0;
 }
 module_init(psi_proc_init);
-- 
cgit v1.2.3-59-g8ed1b


From a4f9a0e51bbf89cb461b1985a1a570e6b87da3b5 Mon Sep 17 00:00:00 2001
From: Vincent Guittot <vincent.guittot@linaro.org>
Date: Wed, 15 Jan 2020 11:20:20 +0100
Subject: sched/fair: Remove redundant call to cpufreq_update_util()

With commit

  bef69dd87828 ("sched/cpufreq: Move the cfs_rq_util_change() call to cpufreq_update_util()")

update_load_avg() has become the central point for calling cpufreq
(not including the update of blocked load). This change helps to
simplify further the number of calls to cpufreq_update_util() and to
remove last redundant ones. With update_load_avg(), we are now sure
that cpufreq_update_util() will be called after every task attachment
to a cfs_rq and especially after propagating this event down to the
util_avg of the root cfs_rq, which is the level that is used by
cpufreq governors like schedutil to set the frequency of a CPU.

The SCHED_CPUFREQ_MIGRATION flag forces an early call to cpufreq when
the migration happens in a cgroup whereas util_avg of root cfs_rq is
not yet updated and this call is duplicated with the one that happens
immediately after when the migration event reaches the root cfs_rq.
The dedicated flag SCHED_CPUFREQ_MIGRATION is now useless and can be
removed. The interface of attach_entity_load_avg() can also be
simplified accordingly.

Signed-off-by: Vincent Guittot <vincent.guittot@linaro.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Link: https://lkml.kernel.org/r/1579083620-24943-1-git-send-email-vincent.guittot@linaro.org
---
 include/linux/sched/cpufreq.h |  1 -
 kernel/sched/fair.c           | 14 +++++++-------
 2 files changed, 7 insertions(+), 8 deletions(-)

diff --git a/include/linux/sched/cpufreq.h b/include/linux/sched/cpufreq.h
index cc6bcc1e96bc..3ed5aa18593f 100644
--- a/include/linux/sched/cpufreq.h
+++ b/include/linux/sched/cpufreq.h
@@ -9,7 +9,6 @@
  */
 
 #define SCHED_CPUFREQ_IOWAIT	(1U << 0)
-#define SCHED_CPUFREQ_MIGRATION	(1U << 1)
 
 #ifdef CONFIG_CPU_FREQ
 struct cpufreq_policy;
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index e84723c5c661..ebf50955fe8a 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -801,7 +801,7 @@ void post_init_entity_util_avg(struct task_struct *p)
 		 * For !fair tasks do:
 		 *
 		update_cfs_rq_load_avg(now, cfs_rq);
-		attach_entity_load_avg(cfs_rq, se, 0);
+		attach_entity_load_avg(cfs_rq, se);
 		switched_from_fair(rq, p);
 		 *
 		 * such that the next switched_to_fair() has the
@@ -3114,7 +3114,7 @@ static inline void cfs_rq_util_change(struct cfs_rq *cfs_rq, int flags)
 {
 	struct rq *rq = rq_of(cfs_rq);
 
-	if (&rq->cfs == cfs_rq || (flags & SCHED_CPUFREQ_MIGRATION)) {
+	if (&rq->cfs == cfs_rq) {
 		/*
 		 * There are a few boundary cases this might miss but it should
 		 * get called often enough that that should (hopefully) not be
@@ -3521,7 +3521,7 @@ update_cfs_rq_load_avg(u64 now, struct cfs_rq *cfs_rq)
  * Must call update_cfs_rq_load_avg() before this, since we rely on
  * cfs_rq->avg.last_update_time being current.
  */
-static void attach_entity_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
+static void attach_entity_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se)
 {
 	u32 divider = LOAD_AVG_MAX - 1024 + cfs_rq->avg.period_contrib;
 
@@ -3557,7 +3557,7 @@ static void attach_entity_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *s
 
 	add_tg_cfs_propagate(cfs_rq, se->avg.load_sum);
 
-	cfs_rq_util_change(cfs_rq, flags);
+	cfs_rq_util_change(cfs_rq, 0);
 
 	trace_pelt_cfs_tp(cfs_rq);
 }
@@ -3615,7 +3615,7 @@ static inline void update_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *s
 		 *
 		 * IOW we're enqueueing a task on a new CPU.
 		 */
-		attach_entity_load_avg(cfs_rq, se, SCHED_CPUFREQ_MIGRATION);
+		attach_entity_load_avg(cfs_rq, se);
 		update_tg_load_avg(cfs_rq, 0);
 
 	} else if (decayed) {
@@ -3872,7 +3872,7 @@ static inline void update_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *s
 static inline void remove_entity_load_avg(struct sched_entity *se) {}
 
 static inline void
-attach_entity_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags) {}
+attach_entity_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se) {}
 static inline void
 detach_entity_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se) {}
 
@@ -10436,7 +10436,7 @@ static void attach_entity_cfs_rq(struct sched_entity *se)
 
 	/* Synchronize entity with its cfs_rq */
 	update_load_avg(cfs_rq, se, sched_feat(ATTACH_AGE_LOAD) ? 0 : SKIP_AGE_LOAD);
-	attach_entity_load_avg(cfs_rq, se, 0);
+	attach_entity_load_avg(cfs_rq, se);
 	update_tg_load_avg(cfs_rq, false);
 	propagate_entity_cfs_rq(se);
 }
-- 
cgit v1.2.3-59-g8ed1b


From 3e0de271fff77abb933f1b69c213854c3eda9125 Mon Sep 17 00:00:00 2001
From: Hewenliang <hewenliang4@huawei.com>
Date: Thu, 9 Jan 2020 21:56:04 -0500
Subject: idle: fix spelling mistake "iterrupts" -> "interrupts"

There is a spelling misake in comments of cpuidle_idle_call. Fix it.

Signed-off-by: Hewenliang <hewenliang4@huawei.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
Link: https://lkml.kernel.org/r/20200110025604.34373-1-hewenliang4@huawei.com
---
 kernel/sched/idle.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/kernel/sched/idle.c b/kernel/sched/idle.c
index ffa959e91227..b743bf38f08f 100644
--- a/kernel/sched/idle.c
+++ b/kernel/sched/idle.c
@@ -158,7 +158,7 @@ static void cpuidle_idle_call(void)
 	/*
 	 * Suspend-to-idle ("s2idle") is a system state in which all user space
 	 * has been frozen, all I/O devices have been suspended and the only
-	 * activity happens here and in iterrupts (if any).  In that case bypass
+	 * activity happens here and in interrupts (if any). In that case bypass
 	 * the cpuidle governor and go stratight for the deepest idle state
 	 * available.  Possibly also suspend the local tick and the entire
 	 * timekeeping to prevent timer interrupts from kicking us out of idle
-- 
cgit v1.2.3-59-g8ed1b


From ccf74128d66ce937876184ad55db2e0276af08d3 Mon Sep 17 00:00:00 2001
From: Valentin Schneider <valentin.schneider@arm.com>
Date: Wed, 15 Jan 2020 16:09:15 +0000
Subject: sched/topology: Assert non-NUMA topology masks don't (partially)
 overlap
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

topology.c::get_group() relies on the assumption that non-NUMA domains do
not partially overlap. Zeng Tao pointed out in [1] that such topology
descriptions, while completely bogus, can end up being exposed to the
scheduler.

In his example (8 CPUs, 2-node system), we end up with:
  MC span for CPU3 == 3-7
  MC span for CPU4 == 4-7

The first pass through get_group(3, sdd@MC) will result in the following
sched_group list:

  3 -> 4 -> 5 -> 6 -> 7
  ^                  /
   `----------------'

And a later pass through get_group(4, sdd@MC) will "corrupt" that to:

  3 -> 4 -> 5 -> 6 -> 7
       ^             /
	`-----------'

which will completely break things like 'while (sg != sd->groups)' when
using CPU3's base sched_domain.

There already are some architecture-specific checks in place such as
x86/kernel/smpboot.c::topology.sane(), but this is something we can detect
in the core scheduler, so it seems worthwhile to do so.

Warn and abort the construction of the sched domains if such a broken
topology description is detected. Note that this is somewhat
expensive (O(t.c²), 't' non-NUMA topology levels and 'c' CPUs) and could be
gated under SCHED_DEBUG if deemed necessary.

Testing
=======

Dietmar managed to reproduce this using the following qemu incantation:

  $ qemu-system-aarch64 -kernel ./Image -hda ./qemu-image-aarch64.img \
  -append 'root=/dev/vda console=ttyAMA0 loglevel=8 sched_debug' -smp \
  cores=8 --nographic -m 512 -cpu cortex-a53 -machine virt -numa \
  node,cpus=0-2,nodeid=0 -numa node,cpus=3-7,nodeid=1

alongside the following drivers/base/arch_topology.c hack (AIUI wouldn't be
needed if '-smp cores=X, sockets=Y' would work with qemu):

8<---
@@ -465,6 +465,9 @@ void update_siblings_masks(unsigned int cpuid)
 		if (cpuid_topo->package_id != cpu_topo->package_id)
 			continue;

+		if ((cpu < 4 && cpuid > 3) || (cpu > 3 && cpuid < 4))
+			continue;
+
 		cpumask_set_cpu(cpuid, &cpu_topo->core_sibling);
 		cpumask_set_cpu(cpu, &cpuid_topo->core_sibling);

8<---

[1]: https://lkml.kernel.org/r/1577088979-8545-1-git-send-email-prime.zeng@hisilicon.com

Reported-by: Zeng Tao <prime.zeng@hisilicon.com>
Signed-off-by: Valentin Schneider <valentin.schneider@arm.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20200115160915.22575-1-valentin.schneider@arm.com
---
 kernel/sched/topology.c | 39 +++++++++++++++++++++++++++++++++++++++
 1 file changed, 39 insertions(+)

diff --git a/kernel/sched/topology.c b/kernel/sched/topology.c
index 6ec1e595b1d4..dfb64c08a407 100644
--- a/kernel/sched/topology.c
+++ b/kernel/sched/topology.c
@@ -1879,6 +1879,42 @@ static struct sched_domain *build_sched_domain(struct sched_domain_topology_leve
 	return sd;
 }
 
+/*
+ * Ensure topology masks are sane, i.e. there are no conflicts (overlaps) for
+ * any two given CPUs at this (non-NUMA) topology level.
+ */
+static bool topology_span_sane(struct sched_domain_topology_level *tl,
+			      const struct cpumask *cpu_map, int cpu)
+{
+	int i;
+
+	/* NUMA levels are allowed to overlap */
+	if (tl->flags & SDTL_OVERLAP)
+		return true;
+
+	/*
+	 * Non-NUMA levels cannot partially overlap - they must be either
+	 * completely equal or completely disjoint. Otherwise we can end up
+	 * breaking the sched_group lists - i.e. a later get_group() pass
+	 * breaks the linking done for an earlier span.
+	 */
+	for_each_cpu(i, cpu_map) {
+		if (i == cpu)
+			continue;
+		/*
+		 * We should 'and' all those masks with 'cpu_map' to exactly
+		 * match the topology we're about to build, but that can only
+		 * remove CPUs, which only lessens our ability to detect
+		 * overlaps
+		 */
+		if (!cpumask_equal(tl->mask(cpu), tl->mask(i)) &&
+		    cpumask_intersects(tl->mask(cpu), tl->mask(i)))
+			return false;
+	}
+
+	return true;
+}
+
 /*
  * Find the sched_domain_topology_level where all CPU capacities are visible
  * for all CPUs.
@@ -1975,6 +2011,9 @@ build_sched_domains(const struct cpumask *cpu_map, struct sched_domain_attr *att
 				has_asym = true;
 			}
 
+			if (WARN_ON(!topology_span_sane(tl, cpu_map, i)))
+				goto error;
+
 			sd = build_sched_domain(tl, cpu_map, attr, sd, dflags, i);
 
 			if (tl == sched_domain_topology)
-- 
cgit v1.2.3-59-g8ed1b


From afa70d941f663c69c9a64ec1021bbcfa82f0e54a Mon Sep 17 00:00:00 2001
From: Viresh Kumar <viresh.kumar@linaro.org>
Date: Mon, 20 Jan 2020 11:29:05 +0530
Subject: sched/fair: Define sched_idle_cpu() only for SMP configurations
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

sched_idle_cpu() isn't used for non SMP configuration and with a recent
change, we have started getting following warning:

  kernel/sched/fair.c:5221:12: warning: ‘sched_idle_cpu’ defined but not used [-Wunused-function]

Fix that by defining sched_idle_cpu() only for SMP configurations.

Fixes: 323af6deaf70 ("sched/fair: Load balance aggressively for SCHED_IDLE CPUs")
Reported-by: Stephen Rothwell <sfr@canb.auug.org.au>
Signed-off-by: Viresh Kumar <viresh.kumar@linaro.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Cc: Juri Lelli <juri.lelli@redhat.com>
Cc: Vincent Guittot <vincent.guittot@linaro.org>
Cc: Dietmar Eggemann <dietmar.eggemann@arm.com>
Link: https://lore.kernel.org/r/f0554f590687478b33914a4aff9f0e6a62886d44.1579499907.git.viresh.kumar@linaro.org
---
 kernel/sched/fair.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index ebf50955fe8a..fe4e0d775375 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -5218,10 +5218,12 @@ static int sched_idle_rq(struct rq *rq)
 			rq->nr_running);
 }
 
+#ifdef CONFIG_SMP
 static int sched_idle_cpu(int cpu)
 {
 	return sched_idle_rq(cpu_rq(cpu));
 }
+#endif
 
 /*
  * The enqueue_task method is called before nr_running is
-- 
cgit v1.2.3-59-g8ed1b