Merge tag 'locking-urgent-2020-11-29' of git://git.kernel.org/pub/scm…

…/linux/kernel/git/tip/tip

Pull locking fixes from Thomas Gleixner:
 "Two more places which invoke tracing from RCU disabled regions in the
  idle path.

  Similar to the entry path the low level idle functions have to be
  non-instrumentable"

* tag 'locking-urgent-2020-11-29' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  intel_idle: Fix intel_idle() vs tracing
  sched/idle: Fix arch_cpu_idle() vs tracing

arch/alpha/kernel/process.c

@@ -57,7 +57,7 @@ EXPORT_SYMBOL(pm_power_off);
 void arch_cpu_idle(void)
 {
 	wtint(0);
-	local_irq_enable();
+	raw_local_irq_enable();
 }
 
 void arch_cpu_idle_dead(void)

arch/arm/kernel/process.c

@@ -71,7 +71,7 @@ void arch_cpu_idle(void)
 		arm_pm_idle();
 	else
 		cpu_do_idle();
-	local_irq_enable();
+	raw_local_irq_enable();
 }
 
 void arch_cpu_idle_prepare(void)

arch/arm64/kernel/process.c

@@ -126,7 +126,7 @@ void arch_cpu_idle(void)
 	 * tricks
 	 */
 	cpu_do_idle();
-	local_irq_enable();
+	raw_local_irq_enable();
 }
 
 #ifdef CONFIG_HOTPLUG_CPU

arch/csky/kernel/process.c

@@ -102,6 +102,6 @@ void arch_cpu_idle(void)
 #ifdef CONFIG_CPU_PM_STOP
 	asm volatile("stop\n");
 #endif
-	local_irq_enable();
+	raw_local_irq_enable();
 }
 #endif

arch/h8300/kernel/process.c

@@ -57,7 +57,7 @@ asmlinkage void ret_from_kernel_thread(void);
  */
 void arch_cpu_idle(void)
 {
-	local_irq_enable();
+	raw_local_irq_enable();
 	__asm__("sleep");
 }
 

arch/hexagon/kernel/process.c

@@ -44,7 +44,7 @@ void arch_cpu_idle(void)
 {
 	__vmwait();
 	/*  interrupts wake us up, but irqs are still disabled */
-	local_irq_enable();
+	raw_local_irq_enable();
 }
 
 /*

arch/ia64/kernel/process.c

@@ -239,7 +239,7 @@ void arch_cpu_idle(void)
 	if (mark_idle)
 		(*mark_idle)(1);
 
-	safe_halt();
+	raw_safe_halt();
 
 	if (mark_idle)
 		(*mark_idle)(0);

arch/microblaze/kernel/process.c

@@ -149,5 +149,5 @@ int dump_fpu(struct pt_regs *regs, elf_fpregset_t *fpregs)
 
 void arch_cpu_idle(void)
 {
-       local_irq_enable();
+       raw_local_irq_enable();
 }

arch/mips/kernel/idle.c

@@ -33,19 +33,19 @@ static void __cpuidle r3081_wait(void)
 {
 	unsigned long cfg = read_c0_conf();
 	write_c0_conf(cfg | R30XX_CONF_HALT);
-	local_irq_enable();
+	raw_local_irq_enable();
 }
 
 static void __cpuidle r39xx_wait(void)
 {
 	if (!need_resched())
 		write_c0_conf(read_c0_conf() | TX39_CONF_HALT);
-	local_irq_enable();
+	raw_local_irq_enable();
 }
 
 void __cpuidle r4k_wait(void)
 {
-	local_irq_enable();
+	raw_local_irq_enable();
 	__r4k_wait();
 }
 
@@ -64,7 +64,7 @@ void __cpuidle r4k_wait_irqoff(void)
 		"	.set	arch=r4000	\n"
 		"	wait			\n"
 		"	.set	pop		\n");
-	local_irq_enable();
+	raw_local_irq_enable();
 }
 
 /*
@@ -84,7 +84,7 @@ static void __cpuidle rm7k_wait_irqoff(void)
 		"	wait						\n"
 		"	mtc0	$1, $12		# stalls until W stage	\n"
 		"	.set	pop					\n");
-	local_irq_enable();
+	raw_local_irq_enable();
 }
 
 /*
@@ -257,7 +257,7 @@ void arch_cpu_idle(void)
 	if (cpu_wait)
 		cpu_wait();
 	else
-		local_irq_enable();
+		raw_local_irq_enable();
 }
 
 #ifdef CONFIG_CPU_IDLE

arch/nios2/kernel/process.c

@@ -33,7 +33,7 @@ EXPORT_SYMBOL(pm_power_off);
 
 void arch_cpu_idle(void)
 {
-	local_irq_enable();
+	raw_local_irq_enable();
 }
 
 /*

arch/openrisc/kernel/process.c

@@ -79,7 +79,7 @@ void machine_power_off(void)
  */
 void arch_cpu_idle(void)
 {
-	local_irq_enable();
+	raw_local_irq_enable();
 	if (mfspr(SPR_UPR) & SPR_UPR_PMP)
 		mtspr(SPR_PMR, mfspr(SPR_PMR) | SPR_PMR_DME);
 }

arch/parisc/kernel/process.c

@@ -169,7 +169,7 @@ void __cpuidle arch_cpu_idle_dead(void)
 
 void __cpuidle arch_cpu_idle(void)
 {
-	local_irq_enable();
+	raw_local_irq_enable();
 
 	/* nop on real hardware, qemu will idle sleep. */
 	asm volatile("or %%r10,%%r10,%%r10\n":::);

arch/powerpc/kernel/idle.c

@@ -52,9 +52,9 @@ void arch_cpu_idle(void)
 		 * interrupts enabled, some don't.
 		 */
 		if (irqs_disabled())
-			local_irq_enable();
+			raw_local_irq_enable();
 	} else {
-		local_irq_enable();
+		raw_local_irq_enable();
 		/*
 		 * Go into low thread priority and possibly
 		 * low power mode.

arch/riscv/kernel/process.c

@@ -36,7 +36,7 @@ extern asmlinkage void ret_from_kernel_thread(void);
 void arch_cpu_idle(void)
 {
 	wait_for_interrupt();
-	local_irq_enable();
+	raw_local_irq_enable();
 }
 
 void show_regs(struct pt_regs *regs)

arch/s390/kernel/idle.c

@@ -33,10 +33,10 @@ void enabled_wait(void)
 		PSW_MASK_IO | PSW_MASK_EXT | PSW_MASK_MCHECK;
 	clear_cpu_flag(CIF_NOHZ_DELAY);
 
-	local_irq_save(flags);
+	raw_local_irq_save(flags);
 	/* Call the assembler magic in entry.S */
 	psw_idle(idle, psw_mask);
-	local_irq_restore(flags);
+	raw_local_irq_restore(flags);
 
 	/* Account time spent with enabled wait psw loaded as idle time. */
 	raw_write_seqcount_begin(&idle->seqcount);
@@ -123,7 +123,7 @@ void arch_cpu_idle_enter(void)
 void arch_cpu_idle(void)
 {
 	enabled_wait();
-	local_irq_enable();
+	raw_local_irq_enable();
 }
 
 void arch_cpu_idle_exit(void)

arch/sh/kernel/idle.c

@@ -22,7 +22,7 @@ static void (*sh_idle)(void);
 void default_idle(void)
 {
 	set_bl_bit();
-	local_irq_enable();
+	raw_local_irq_enable();
 	/* Isn't this racy ? */
 	cpu_sleep();
 	clear_bl_bit();

arch/sparc/kernel/leon_pmc.c

@@ -50,7 +50,7 @@ static void pmc_leon_idle_fixup(void)
 	register unsigned int address = (unsigned int)leon3_irqctrl_regs;
 
 	/* Interrupts need to be enabled to not hang the CPU */
-	local_irq_enable();
+	raw_local_irq_enable();
 
 	__asm__ __volatile__ (
 		"wr	%%g0, %%asr19\n"
@@ -66,7 +66,7 @@ static void pmc_leon_idle_fixup(void)
 static void pmc_leon_idle(void)
 {
 	/* Interrupts need to be enabled to not hang the CPU */
-	local_irq_enable();
+	raw_local_irq_enable();
 
 	/* For systems without power-down, this will be no-op */
 	__asm__ __volatile__ ("wr	%g0, %asr19\n\t");

arch/sparc/kernel/process_32.c

@@ -74,7 +74,7 @@ void arch_cpu_idle(void)
 {
 	if (sparc_idle)
 		(*sparc_idle)();
-	local_irq_enable();
+	raw_local_irq_enable();
 }
 
 /* XXX cli/sti -> local_irq_xxx here, check this works once SMP is fixed. */

arch/sparc/kernel/process_64.c

@@ -62,11 +62,11 @@ void arch_cpu_idle(void)
 {
 	if (tlb_type != hypervisor) {
 		touch_nmi_watchdog();
-		local_irq_enable();
+		raw_local_irq_enable();
 	} else {
 		unsigned long pstate;
 
-		local_irq_enable();
+		raw_local_irq_enable();
 
                 /* The sun4v sleeping code requires that we have PSTATE.IE cleared over
                  * the cpu sleep hypervisor call.

arch/um/kernel/process.c

@@ -217,7 +217,7 @@ void arch_cpu_idle(void)
 {
 	cpu_tasks[current_thread_info()->cpu].pid = os_getpid();
 	um_idle_sleep();
-	local_irq_enable();
+	raw_local_irq_enable();
 }
 
 int __cant_sleep(void) {

arch/x86/include/asm/mwait.h

@@ -88,8 +88,6 @@ static inline void __mwaitx(unsigned long eax, unsigned long ebx,
 
 static inline void __sti_mwait(unsigned long eax, unsigned long ecx)
 {
-	trace_hardirqs_on();
-
 	mds_idle_clear_cpu_buffers();
 	/* "mwait %eax, %ecx;" */
 	asm volatile("sti; .byte 0x0f, 0x01, 0xc9;"

arch/x86/kernel/process.c

@@ -685,7 +685,7 @@ void arch_cpu_idle(void)
  */
 void __cpuidle default_idle(void)
 {
-	safe_halt();
+	raw_safe_halt();
 }
 #if defined(CONFIG_APM_MODULE) || defined(CONFIG_HALTPOLL_CPUIDLE_MODULE)
 EXPORT_SYMBOL(default_idle);
@@ -736,6 +736,8 @@ void stop_this_cpu(void *dummy)
 /*
  * AMD Erratum 400 aware idle routine. We handle it the same way as C3 power
  * states (local apic timer and TSC stop).
+ *
+ * XXX this function is completely buggered vs RCU and tracing.
  */
 static void amd_e400_idle(void)
 {
@@ -757,9 +759,9 @@ static void amd_e400_idle(void)
 	 * The switch back from broadcast mode needs to be called with
 	 * interrupts disabled.
 	 */
-	local_irq_disable();
+	raw_local_irq_disable();
 	tick_broadcast_exit();
-	local_irq_enable();
+	raw_local_irq_enable();
 }
 
 /*
@@ -801,9 +803,9 @@ static __cpuidle void mwait_idle(void)
 		if (!need_resched())
 			__sti_mwait(0, 0);
 		else
-			local_irq_enable();
+			raw_local_irq_enable();
 	} else {
-		local_irq_enable();
+		raw_local_irq_enable();
 	}
 	__current_clr_polling();
 }

drivers/idle/intel_idle.c

@@ -126,26 +126,9 @@ static __cpuidle int intel_idle(struct cpuidle_device *dev,
 	struct cpuidle_state *state = &drv->states[index];
 	unsigned long eax = flg2MWAIT(state->flags);
 	unsigned long ecx = 1; /* break on interrupt flag */
-	bool tick;
-
-	if (!static_cpu_has(X86_FEATURE_ARAT)) {
-		/*
-		 * Switch over to one-shot tick broadcast if the target C-state
-		 * is deeper than C1.
-		 */
-		if ((eax >> MWAIT_SUBSTATE_SIZE) & MWAIT_CSTATE_MASK) {
-			tick = true;
-			tick_broadcast_enter();
-		} else {
-			tick = false;
-		}
-	}
 
 	mwait_idle_with_hints(eax, ecx);
 
-	if (!static_cpu_has(X86_FEATURE_ARAT) && tick)
-		tick_broadcast_exit();
-
 	return index;
 }
 
@@ -1227,6 +1210,20 @@ static bool __init intel_idle_acpi_cst_extract(void)
 	return false;
 }
 
+static bool __init intel_idle_state_needs_timer_stop(struct cpuidle_state *state)
+{
+	unsigned long eax = flg2MWAIT(state->flags);
+
+	if (boot_cpu_has(X86_FEATURE_ARAT))
+		return false;
+
+	/*
+	 * Switch over to one-shot tick broadcast if the target C-state
+	 * is deeper than C1.
+	 */
+	return !!((eax >> MWAIT_SUBSTATE_SIZE) & MWAIT_CSTATE_MASK);
+}
+
 static void __init intel_idle_init_cstates_acpi(struct cpuidle_driver *drv)
 {
 	int cstate, limit = min_t(int, CPUIDLE_STATE_MAX, acpi_state_table.count);
@@ -1269,6 +1266,9 @@ static void __init intel_idle_init_cstates_acpi(struct cpuidle_driver *drv)
 		if (disabled_states_mask & BIT(cstate))
 			state->flags |= CPUIDLE_FLAG_OFF;
 
+		if (intel_idle_state_needs_timer_stop(state))
+			state->flags |= CPUIDLE_FLAG_TIMER_STOP;
+
 		state->enter = intel_idle;
 		state->enter_s2idle = intel_idle_s2idle;
 	}
@@ -1507,6 +1507,9 @@ static void __init intel_idle_init_cstates_icpu(struct cpuidle_driver *drv)
 		     !(cpuidle_state_table[cstate].flags & CPUIDLE_FLAG_ALWAYS_ENABLE)))
 			drv->states[drv->state_count].flags |= CPUIDLE_FLAG_OFF;
 
+		if (intel_idle_state_needs_timer_stop(&drv->states[drv->state_count]))
+			drv->states[drv->state_count].flags |= CPUIDLE_FLAG_TIMER_STOP;
+
 		drv->state_count++;
 	}