Merge tag 'locking-urgent-2020-08-30' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull locking fixes from Thomas Gleixner:
 "A set of fixes for lockdep, tracing and RCU:

   - Prevent recursion by using raw_cpu_* operations

   - Fixup the interrupt state in the cpu idle code to be consistent

   - Push rcu_idle_enter/exit() invocations deeper into the idle path so
     that the lock operations are inside the RCU watching sections

   - Move trace_cpu_idle() into generic code so it's called before RCU
     goes idle.

   - Handle raw_local_irq* vs. local_irq* operations correctly

   - Move the tracepoints out from under the lockdep recursion handling
     which turned out to be fragile and inconsistent"

* tag 'locking-urgent-2020-08-30' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  lockdep,trace: Expose tracepoints
  lockdep: Only trace IRQ edges
  mips: Implement arch_irqs_disabled()
  arm64: Implement arch_irqs_disabled()
  nds32: Implement arch_irqs_disabled()
  locking/lockdep: Cleanup
  x86/entry: Remove unused THUNKs
  cpuidle: Move trace_cpu_idle() into generic code
  cpuidle: Make CPUIDLE_FLAG_TLB_FLUSHED generic
  sched,idle,rcu: Push rcu_idle deeper into the idle path
  cpuidle: Fixup IRQ state
  lockdep: Use raw_cpu_*() for per-cpu variables

11 files changed, 23 insertions, 35 deletions

diff --git a/arch/arm/mach-omap2/pm34xx.c b/arch/arm/mach-omap2/pm34xx.c
index 6df395fff971..f5dfddf492e2 100644
--- a/arch/arm/mach-omap2/pm34xx.c
+++ b/arch/arm/mach-omap2/pm34xx.c
@@ -298,11 +298,7 @@ static void omap3_pm_idle(void)
 	if (omap_irq_pending())
 		return;
 
-	trace_cpu_idle_rcuidle(1, smp_processor_id());
-
 	omap_sram_idle();
-
-	trace_cpu_idle_rcuidle(PWR_EVENT_EXIT, smp_processor_id());
 }
 
 #ifdef CONFIG_SUSPEND
diff --git a/arch/arm64/include/asm/irqflags.h b/arch/arm64/include/asm/irqflags.h
index aa4b6521ef14..ff328e5bbb75 100644
--- a/arch/arm64/include/asm/irqflags.h
+++ b/arch/arm64/include/asm/irqflags.h
@@ -95,6 +95,11 @@ static inline int arch_irqs_disabled_flags(unsigned long flags)
 	return res;
 }
 
+static inline int arch_irqs_disabled(void)
+{
+	return arch_irqs_disabled_flags(arch_local_save_flags());
+}
+
 static inline unsigned long arch_local_irq_save(void)
 {
 	unsigned long flags;
diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c
index b63ce4c54cfe..f1804496b935 100644
--- a/arch/arm64/kernel/process.c
+++ b/arch/arm64/kernel/process.c
@@ -123,10 +123,8 @@ void arch_cpu_idle(void)
 	 * This should do all the clock switching and wait for interrupt
 	 * tricks
 	 */
-	trace_cpu_idle_rcuidle(1, smp_processor_id());
 	cpu_do_idle();
 	local_irq_enable();
-	trace_cpu_idle_rcuidle(PWR_EVENT_EXIT, smp_processor_id());
 }
 
 #ifdef CONFIG_HOTPLUG_CPU
diff --git a/arch/mips/include/asm/irqflags.h b/arch/mips/include/asm/irqflags.h
index 47a8ffc0b413..f5b8300f4573 100644
--- a/arch/mips/include/asm/irqflags.h
+++ b/arch/mips/include/asm/irqflags.h
@@ -137,6 +137,11 @@ static inline int arch_irqs_disabled_flags(unsigned long flags)
 	return !(flags & 1);
 }
 
+static inline int arch_irqs_disabled(void)
+{
+	return arch_irqs_disabled_flags(arch_local_save_flags());
+}
+
 #endif /* #ifndef __ASSEMBLY__ */
 
 /*
diff --git a/arch/nds32/include/asm/irqflags.h b/arch/nds32/include/asm/irqflags.h
index fb45ec46bb1b..51ef800bb301 100644
--- a/arch/nds32/include/asm/irqflags.h
+++ b/arch/nds32/include/asm/irqflags.h
@@ -34,3 +34,8 @@ static inline int arch_irqs_disabled_flags(unsigned long flags)
 {
 	return !flags;
 }
+
+static inline int arch_irqs_disabled(void)
+{
+	return arch_irqs_disabled_flags(arch_local_save_flags());
+}
diff --git a/arch/powerpc/include/asm/hw_irq.h b/arch/powerpc/include/asm/hw_irq.h
index 3a0db7b0b46e..35060be09073 100644
--- a/arch/powerpc/include/asm/hw_irq.h
+++ b/arch/powerpc/include/asm/hw_irq.h
@@ -200,17 +200,14 @@ static inline bool arch_irqs_disabled(void)
 #define powerpc_local_irq_pmu_save(flags)			\
 	 do {							\
 		raw_local_irq_pmu_save(flags);			\
-		trace_hardirqs_off();				\
+		if (!raw_irqs_disabled_flags(flags))		\
+			trace_hardirqs_off();			\
 	} while(0)
 #define powerpc_local_irq_pmu_restore(flags)			\
 	do {							\
-		if (raw_irqs_disabled_flags(flags)) {		\
-			raw_local_irq_pmu_restore(flags);	\
-			trace_hardirqs_off();			\
-		} else {					\
+		if (!raw_irqs_disabled_flags(flags))		\
 			trace_hardirqs_on();			\
-			raw_local_irq_pmu_restore(flags);	\
-		}						\
+		raw_local_irq_pmu_restore(flags);		\
 	} while(0)
 #else
 #define powerpc_local_irq_pmu_save(flags)			\
diff --git a/arch/s390/kernel/idle.c b/arch/s390/kernel/idle.c
index 88bb42ca5008..c73f50649e7e 100644
--- a/arch/s390/kernel/idle.c
+++ b/arch/s390/kernel/idle.c
@@ -33,14 +33,13 @@ void enabled_wait(void)
 		PSW_MASK_IO | PSW_MASK_EXT | PSW_MASK_MCHECK;
 	clear_cpu_flag(CIF_NOHZ_DELAY);
 
-	trace_cpu_idle_rcuidle(1, smp_processor_id());
 	local_irq_save(flags);
 	/* Call the assembler magic in entry.S */
 	psw_idle(idle, psw_mask);
 	local_irq_restore(flags);
-	trace_cpu_idle_rcuidle(PWR_EVENT_EXIT, smp_processor_id());
 
 	/* Account time spent with enabled wait psw loaded as idle time. */
+	/* XXX seqcount has tracepoints that require RCU */
 	write_seqcount_begin(&idle->seqcount);
 	idle_time = idle->clock_idle_exit - idle->clock_idle_enter;
 	idle->clock_idle_enter = idle->clock_idle_exit = 0ULL;
diff --git a/arch/x86/entry/thunk_32.S b/arch/x86/entry/thunk_32.S
index 3a07ce3ec70b..f1f96d4d8cd6 100644
--- a/arch/x86/entry/thunk_32.S
+++ b/arch/x86/entry/thunk_32.S
@@ -29,11 +29,6 @@ SYM_CODE_START_NOALIGN(\name)
 SYM_CODE_END(\name)
 	.endm
 
-#ifdef CONFIG_TRACE_IRQFLAGS
-	THUNK trace_hardirqs_on_thunk,trace_hardirqs_on_caller,1
-	THUNK trace_hardirqs_off_thunk,trace_hardirqs_off_caller,1
-#endif
-
 #ifdef CONFIG_PREEMPTION
 	THUNK preempt_schedule_thunk, preempt_schedule
 	THUNK preempt_schedule_notrace_thunk, preempt_schedule_notrace
diff --git a/arch/x86/include/asm/mmu.h b/arch/x86/include/asm/mmu.h
index 0a301ad0b02f..9257667d13c5 100644
--- a/arch/x86/include/asm/mmu.h
+++ b/arch/x86/include/asm/mmu.h
@@ -59,5 +59,6 @@ typedef struct {
 	}
 
 void leave_mm(int cpu);
+#define leave_mm leave_mm
 
 #endif /* _ASM_X86_MMU_H */
diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c
index 994d8393f2f7..13ce616cc7af 100644
--- a/arch/x86/kernel/process.c
+++ b/arch/x86/kernel/process.c
@@ -684,9 +684,7 @@ void arch_cpu_idle(void)
  */
 void __cpuidle default_idle(void)
 {
-	trace_cpu_idle_rcuidle(1, smp_processor_id());
 	safe_halt();
-	trace_cpu_idle_rcuidle(PWR_EVENT_EXIT, smp_processor_id());
 }
 #if defined(CONFIG_APM_MODULE) || defined(CONFIG_HALTPOLL_CPUIDLE_MODULE)
 EXPORT_SYMBOL(default_idle);
@@ -792,7 +790,6 @@ static int prefer_mwait_c1_over_halt(const struct cpuinfo_x86 *c)
 static __cpuidle void mwait_idle(void)
 {
 	if (!current_set_polling_and_test()) {
-		trace_cpu_idle_rcuidle(1, smp_processor_id());
 		if (this_cpu_has(X86_BUG_CLFLUSH_MONITOR)) {
 			mb(); /* quirk */
 			clflush((void *)&current_thread_info()->flags);
@@ -804,7 +801,6 @@ static __cpuidle void mwait_idle(void)
 			__sti_mwait(0, 0);
 		else
 			local_irq_enable();
-		trace_cpu_idle_rcuidle(PWR_EVENT_EXIT, smp_processor_id());
 	} else {
 		local_irq_enable();
 	}
diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c
index 1a3569b43aa5..0951b47e64c1 100644
--- a/arch/x86/mm/tlb.c
+++ b/arch/x86/mm/tlb.c
@@ -555,21 +555,12 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next,
 		this_cpu_write(cpu_tlbstate.ctxs[new_asid].tlb_gen, next_tlb_gen);
 		load_new_mm_cr3(next->pgd, new_asid, true);
 
-		/*
-		 * NB: This gets called via leave_mm() in the idle path
-		 * where RCU functions differently.  Tracing normally
-		 * uses RCU, so we need to use the _rcuidle variant.
-		 *
-		 * (There is no good reason for this.  The idle code should
-		 *  be rearranged to call this before rcu_idle_enter().)
-		 */
-		trace_tlb_flush_rcuidle(TLB_FLUSH_ON_TASK_SWITCH, TLB_FLUSH_ALL);
+		trace_tlb_flush(TLB_FLUSH_ON_TASK_SWITCH, TLB_FLUSH_ALL);
 	} else {
 		/* The new ASID is already up to date. */
 		load_new_mm_cr3(next->pgd, new_asid, false);
 
-		/* See above wrt _rcuidle. */
-		trace_tlb_flush_rcuidle(TLB_FLUSH_ON_TASK_SWITCH, 0);
+		trace_tlb_flush(TLB_FLUSH_ON_TASK_SWITCH, 0);
 	}
 
 	/* Make sure we write CR3 before loaded_mm. */