Merge branch 'x86-idle-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull x86 idle updates from Ingo Molnar:
 "There were two bigger changes in this development cycle:

   - remove idle notifiers:

       32 files changed, 74 insertions(+), 803 deletions(-)

     These notifiers were of questionable value and the main usecase,
     the i7300 driver, was essentially unmaintained and can be removed,
     plus modern power management concepts don't need the callback - so
     use this golden opportunity and get rid of this opaque and fragile
     callback from a latency sensitive code path.

     (Len Brown, Thomas Gleixner)

   - improve the AMD Erratum 400 workaround that used high overhead MSR
     polling in the idle loop (Borisla Petkov, Thomas Gleixner)"

* 'x86-idle-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  x86: Remove empty idle.h header
  x86/amd: Simplify AMD E400 aware idle routine
  x86/amd: Check for the C1E bug post ACPI subsystem init
  x86/bugs: Separate AMD E400 erratum and C1E bug
  x86/cpufeature: Provide helper to set bugs bits
  x86/idle: Remove enter_idle(), exit_idle()
  x86: Remove x86_test_and_clear_bit_percpu()
  x86/idle: Remove is_idle flag
  x86/idle: Remove idle_notifier
  i7300_idle: Remove this driver

MAINTAINERS

@@ -6104,12 +6104,6 @@ S:	Maintained
 F:	Documentation/cdrom/ide-cd
 F:	drivers/ide/ide-cd*
 
-IDLE-I7300
-M:	Andy Henroid <andrew.d.henroid@intel.com>
-L:	linux-pm@vger.kernel.org
-S:	Supported
-F:	drivers/idle/i7300_idle.c
-
 IEEE 802.15.4 SUBSYSTEM
 M:	Alexander Aring <aar@pengutronix.de>
 M:	Stefan Schmidt <stefan@osg.samsung.com>

arch/x86/include/asm/acpi.h

@@ -94,7 +94,7 @@ static inline unsigned int acpi_processor_cstate_check(unsigned int max_cstate)
 	    boot_cpu_data.x86_model <= 0x05 &&
 	    boot_cpu_data.x86_mask < 0x0A)
 		return 1;
-	else if (amd_e400_c1e_detected)
+	else if (boot_cpu_has(X86_BUG_AMD_APIC_C1E))
 		return 1;
 	else
 		return max_cstate;

arch/x86/include/asm/apic.h

@@ -11,7 +11,6 @@
 #include <asm/fixmap.h>
 #include <asm/mpspec.h>
 #include <asm/msr.h>
-#include <asm/idle.h>
 
 #define ARCH_APICTIMER_STOPS_ON_C3	1
 
@@ -640,7 +639,6 @@ extern void irq_exit(void);
 static inline void entering_irq(void)
 {
 	irq_enter();
-	exit_idle();
 }
 
 static inline void entering_ack_irq(void)

arch/x86/include/asm/cpufeature.h

@@ -204,6 +204,7 @@ static __always_inline __pure bool _static_cpu_has(u16 bit)
 
 #define static_cpu_has_bug(bit)		static_cpu_has((bit))
 #define boot_cpu_has_bug(bit)		cpu_has_bug(&boot_cpu_data, (bit))
+#define boot_cpu_set_bug(bit)		set_cpu_cap(&boot_cpu_data, (bit))
 
 #define MAX_CPU_FEATURES		(NCAPINTS * 32)
 #define cpu_have_feature		boot_cpu_has

arch/x86/include/asm/cpufeatures.h

@@ -314,4 +314,6 @@
 #define X86_BUG_NULL_SEG	X86_BUG(10) /* Nulling a selector preserves the base */
 #define X86_BUG_SWAPGS_FENCE	X86_BUG(11) /* SWAPGS without input dep on GS */
 #define X86_BUG_MONITOR		X86_BUG(12) /* IPI required to wake up remote CPU */
+#define X86_BUG_AMD_E400	X86_BUG(13) /* CPU is among the affected by Erratum 400 */
+
 #endif /* _ASM_X86_CPUFEATURES_H */

arch/x86/include/asm/idle.h

-#ifndef _ASM_X86_IDLE_H
-#define _ASM_X86_IDLE_H
-
-#define IDLE_START 1
-#define IDLE_END 2
-
-struct notifier_block;
-void idle_notifier_register(struct notifier_block *n);
-void idle_notifier_unregister(struct notifier_block *n);
-
-#ifdef CONFIG_X86_64
-void enter_idle(void);
-void exit_idle(void);
-#else /* !CONFIG_X86_64 */
-static inline void enter_idle(void) { }
-static inline void exit_idle(void) { }
-static inline void __exit_idle(void) { }
-#endif /* CONFIG_X86_64 */
-
-void amd_e400_remove_cpu(int cpu);
-
-#endif /* _ASM_X86_IDLE_H */

arch/x86/include/asm/percpu.h

@@ -507,17 +507,6 @@ do {									\
 
 #endif
 
-/* This is not atomic against other CPUs -- CPU preemption needs to be off */
-#define x86_test_and_clear_bit_percpu(bit, var)				\
-({									\
-	bool old__;							\
-	asm volatile("btr %2,"__percpu_arg(1)"\n\t"			\
-		     CC_SET(c)						\
-		     : CC_OUT(c) (old__), "+m" (var)			\
-		     : "dIr" (bit));					\
-	old__;								\
-})
-
 static __always_inline bool x86_this_cpu_constant_test_bit(unsigned int nr,
                         const unsigned long __percpu *addr)
 {

arch/x86/include/asm/processor.h

@@ -633,10 +633,9 @@ static inline void sync_core(void)
 }
 
 extern void select_idle_routine(const struct cpuinfo_x86 *c);
-extern void init_amd_e400_c1e_mask(void);
+extern void amd_e400_c1e_apic_setup(void);
 
 extern unsigned long		boot_option_idle_override;
-extern bool			amd_e400_c1e_detected;
 
 enum idle_boot_override {IDLE_NO_OVERRIDE=0, IDLE_HALT, IDLE_NOMWAIT,
 			 IDLE_POLL};

arch/x86/kernel/apic/apic.c

@@ -48,7 +48,6 @@
 #include <asm/io_apic.h>
 #include <asm/desc.h>
 #include <asm/hpet.h>
-#include <asm/idle.h>
 #include <asm/mtrr.h>
 #include <asm/time.h>
 #include <asm/smp.h>
@@ -894,11 +893,13 @@ void __init setup_boot_APIC_clock(void)
 
 	/* Setup the lapic or request the broadcast */
 	setup_APIC_timer();
+	amd_e400_c1e_apic_setup();
 }
 
 void setup_secondary_APIC_clock(void)
 {
 	setup_APIC_timer();
+	amd_e400_c1e_apic_setup();
 }
 
 /*

arch/x86/kernel/apic/io_apic.c

@@ -48,7 +48,6 @@
 #include <linux/bootmem.h>
 
 #include <asm/irqdomain.h>
-#include <asm/idle.h>
 #include <asm/io.h>
 #include <asm/smp.h>
 #include <asm/cpu.h>

arch/x86/kernel/cpu/amd.c

@@ -20,6 +20,10 @@
 
 #include "cpu.h"
 
+static const int amd_erratum_383[];
+static const int amd_erratum_400[];
+static bool cpu_has_amd_erratum(struct cpuinfo_x86 *cpu, const int *erratum);
+
 /*
  * nodes_per_socket: Stores the number of nodes per socket.
  * Refer to Fam15h Models 00-0fh BKDG - CPUID Fn8000_001E_ECX
@@ -592,11 +596,16 @@ static void early_init_amd(struct cpuinfo_x86 *c)
 	/* F16h erratum 793, CVE-2013-6885 */
 	if (c->x86 == 0x16 && c->x86_model <= 0xf)
 		msr_set_bit(MSR_AMD64_LS_CFG, 15);
-}
 
-static const int amd_erratum_383[];
-static const int amd_erratum_400[];
-static bool cpu_has_amd_erratum(struct cpuinfo_x86 *cpu, const int *erratum);
+	/*
+	 * Check whether the machine is affected by erratum 400. This is
+	 * used to select the proper idle routine and to enable the check
+	 * whether the machine is affected in arch_post_acpi_init(), which
+	 * sets the X86_BUG_AMD_APIC_C1E bug depending on the MSR check.
+	 */
+	if (cpu_has_amd_erratum(c, amd_erratum_400))
+		set_cpu_bug(c, X86_BUG_AMD_E400);
+}
 
 static void init_amd_k8(struct cpuinfo_x86 *c)
 {
@@ -777,9 +786,6 @@ static void init_amd(struct cpuinfo_x86 *c)
 	if (c->x86 > 0x11)
 		set_cpu_cap(c, X86_FEATURE_ARAT);
 
-	if (cpu_has_amd_erratum(c, amd_erratum_400))
-		set_cpu_bug(c, X86_BUG_AMD_APIC_C1E);
-
 	rdmsr_safe(MSR_AMD64_PATCH_LEVEL, &c->microcode, &dummy);
 
 	/* 3DNow or LM implies PREFETCHW */

arch/x86/kernel/cpu/common.c

@@ -1172,7 +1172,6 @@ void enable_sep_cpu(void)
 void __init identify_boot_cpu(void)
 {
 	identify_cpu(&boot_cpu_data);
-	init_amd_e400_c1e_mask();
 #ifdef CONFIG_X86_32
 	sysenter_setup();
 	enable_sep_cpu();

arch/x86/kernel/cpu/mcheck/mce_amd.c

@@ -24,7 +24,6 @@
 
 #include <asm/amd_nb.h>
 #include <asm/apic.h>
-#include <asm/idle.h>
 #include <asm/mce.h>
 #include <asm/msr.h>
 #include <asm/trace/irq_vectors.h>

arch/x86/kernel/cpu/mcheck/therm_throt.c

@@ -26,7 +26,6 @@
 
 #include <asm/processor.h>
 #include <asm/apic.h>
-#include <asm/idle.h>
 #include <asm/mce.h>
 #include <asm/msr.h>
 #include <asm/trace/irq_vectors.h>

arch/x86/kernel/cpu/mcheck/threshold.c

@@ -6,7 +6,6 @@
 
 #include <asm/irq_vectors.h>
 #include <asm/apic.h>
-#include <asm/idle.h>
 #include <asm/mce.h>
 #include <asm/trace/irq_vectors.h>
 

arch/x86/kernel/cpu/mshyperv.c

@@ -25,7 +25,6 @@
 #include <asm/hyperv.h>
 #include <asm/mshyperv.h>
 #include <asm/desc.h>
-#include <asm/idle.h>
 #include <asm/irq_regs.h>
 #include <asm/i8259.h>
 #include <asm/apic.h>

arch/x86/kernel/irq.c

@@ -14,7 +14,6 @@
 #include <asm/apic.h>
 #include <asm/io_apic.h>
 #include <asm/irq.h>
-#include <asm/idle.h>
 #include <asm/mce.h>
 #include <asm/hw_irq.h>
 #include <asm/desc.h>

arch/x86/kernel/irq_64.c

@@ -16,7 +16,6 @@
 #include <linux/uaccess.h>
 #include <linux/smp.h>
 #include <asm/io_apic.h>
-#include <asm/idle.h>
 #include <asm/apic.h>
 
 int sysctl_panic_on_stackoverflow;

arch/x86/kernel/kvm.c

@@ -42,7 +42,6 @@
 #include <asm/traps.h>
 #include <asm/desc.h>
 #include <asm/tlbflush.h>
-#include <asm/idle.h>
 #include <asm/apic.h>
 #include <asm/apicdef.h>
 #include <asm/hypervisor.h>
@@ -267,13 +266,11 @@ do_async_page_fault(struct pt_regs *regs, unsigned long error_code)
 	case KVM_PV_REASON_PAGE_NOT_PRESENT:
 		/* page is swapped out by the host. */
 		prev_state = exception_enter();
-		exit_idle();
 		kvm_async_pf_task_wait((u32)read_cr2());
 		exception_exit(prev_state);
 		break;
 	case KVM_PV_REASON_PAGE_READY:
 		rcu_irq_enter();
-		exit_idle();
 		kvm_async_pf_task_wake((u32)read_cr2());
 		rcu_irq_exit();
 		break;

arch/x86/kernel/process.c

@@ -23,7 +23,6 @@
 #include <asm/cpu.h>
 #include <asm/apic.h>
 #include <asm/syscalls.h>
-#include <asm/idle.h>
 #include <asm/uaccess.h>
 #include <asm/mwait.h>
 #include <asm/fpu/internal.h>
@@ -65,23 +64,6 @@ __visible DEFINE_PER_CPU_SHARED_ALIGNED(struct tss_struct, cpu_tss) = {
 };
 EXPORT_PER_CPU_SYMBOL(cpu_tss);
 
-#ifdef CONFIG_X86_64
-static DEFINE_PER_CPU(unsigned char, is_idle);
-static ATOMIC_NOTIFIER_HEAD(idle_notifier);
-
-void idle_notifier_register(struct notifier_block *n)
-{
-	atomic_notifier_chain_register(&idle_notifier, n);
-}
-EXPORT_SYMBOL_GPL(idle_notifier_register);
-
-void idle_notifier_unregister(struct notifier_block *n)
-{
-	atomic_notifier_chain_unregister(&idle_notifier, n);
-}
-EXPORT_SYMBOL_GPL(idle_notifier_unregister);
-#endif
-
 /*
  * this gets called so that we can store lazy state into memory and copy the
  * current task into the new thread.
@@ -251,39 +233,9 @@ static inline void play_dead(void)
 }
 #endif
 
-#ifdef CONFIG_X86_64
-void enter_idle(void)
-{
-	this_cpu_write(is_idle, 1);
-	atomic_notifier_call_chain(&idle_notifier, IDLE_START, NULL);
-}
-
-static void __exit_idle(void)
-{
-	if (x86_test_and_clear_bit_percpu(0, is_idle) == 0)
-		return;
-	atomic_notifier_call_chain(&idle_notifier, IDLE_END, NULL);
-}
-
-/* Called from interrupts to signify idle end */
-void exit_idle(void)
-{
-	/* idle loop has pid 0 */
-	if (current->pid)
-		return;
-	__exit_idle();
-}
-#endif
-
 void arch_cpu_idle_enter(void)
 {
 	local_touch_nmi();
-	enter_idle();
-}
-
-void arch_cpu_idle_exit(void)
-{
-	__exit_idle();
 }
 
 void arch_cpu_idle_dead(void)
@@ -336,59 +288,33 @@ void stop_this_cpu(void *dummy)
 		halt();
 }
 
-bool amd_e400_c1e_detected;
-EXPORT_SYMBOL(amd_e400_c1e_detected);
-
-static cpumask_var_t amd_e400_c1e_mask;
-
-void amd_e400_remove_cpu(int cpu)
-{
-	if (amd_e400_c1e_mask != NULL)
-		cpumask_clear_cpu(cpu, amd_e400_c1e_mask);
-}
-
 /*
- * AMD Erratum 400 aware idle routine. We check for C1E active in the interrupt
- * pending message MSR. If we detect C1E, then we handle it the same
- * way as C3 power states (local apic timer and TSC stop)
+ * AMD Erratum 400 aware idle routine. We handle it the same way as C3 power
+ * states (local apic timer and TSC stop).
  */
 static void amd_e400_idle(void)
 {
-	if (!amd_e400_c1e_detected) {
-		u32 lo, hi;
-
-		rdmsr(MSR_K8_INT_PENDING_MSG, lo, hi);
-
-		if (lo & K8_INTP_C1E_ACTIVE_MASK) {
-			amd_e400_c1e_detected = true;
-			if (!boot_cpu_has(X86_FEATURE_NONSTOP_TSC))
-				mark_tsc_unstable("TSC halt in AMD C1E");
-			pr_info("System has AMD C1E enabled\n");
-		}
+	/*
+	 * We cannot use static_cpu_has_bug() here because X86_BUG_AMD_APIC_C1E
+	 * gets set after static_cpu_has() places have been converted via
+	 * alternatives.
+	 */
+	if (!boot_cpu_has_bug(X86_BUG_AMD_APIC_C1E)) {
+		default_idle();
+		return;
 	}
 
-	if (amd_e400_c1e_detected) {
-		int cpu = smp_processor_id();
-
-		if (!cpumask_test_cpu(cpu, amd_e400_c1e_mask)) {
-			cpumask_set_cpu(cpu, amd_e400_c1e_mask);
-			/* Force broadcast so ACPI can not interfere. */
-			tick_broadcast_force();
-			pr_info("Switch to broadcast mode on CPU%d\n", cpu);
-		}
 	tick_broadcast_enter();
 
 	default_idle();
 
 	/*
-		 * The switch back from broadcast mode needs to be
-		 * called with interrupts disabled.
+	 * The switch back from broadcast mode needs to be called with
+	 * interrupts disabled.
 	 */
 	local_irq_disable();
 	tick_broadcast_exit();
 	local_irq_enable();
-	} else
-		default_idle();
 }
 
 /*
@@ -448,8 +374,7 @@ void select_idle_routine(const struct cpuinfo_x86 *c)
 	if (x86_idle || boot_option_idle_override == IDLE_POLL)
 		return;
 
-	if (cpu_has_bug(c, X86_BUG_AMD_APIC_C1E)) {
-		/* E400: APIC timer interrupt does not wake up CPU from C1e */
+	if (boot_cpu_has_bug(X86_BUG_AMD_E400)) {
 		pr_info("using AMD E400 aware idle routine\n");
 		x86_idle = amd_e400_idle;
 	} else if (prefer_mwait_c1_over_halt(c)) {
@@ -459,11 +384,37 @@ void select_idle_routine(const struct cpuinfo_x86 *c)
 		x86_idle = default_idle;
 }
 
-void __init init_amd_e400_c1e_mask(void)
+void amd_e400_c1e_apic_setup(void)
+{
+	if (boot_cpu_has_bug(X86_BUG_AMD_APIC_C1E)) {
+		pr_info("Switch to broadcast mode on CPU%d\n", smp_processor_id());
+		local_irq_disable();
+		tick_broadcast_force();
+		local_irq_enable();
+	}
+}
+
+void __init arch_post_acpi_subsys_init(void)
 {
-	/* If we're using amd_e400_idle, we need to allocate amd_e400_c1e_mask. */
-	if (x86_idle == amd_e400_idle)
-		zalloc_cpumask_var(&amd_e400_c1e_mask, GFP_KERNEL);
+	u32 lo, hi;
+
+	if (!boot_cpu_has_bug(X86_BUG_AMD_E400))
+		return;
+
+	/*
+	 * AMD E400 detection needs to happen after ACPI has been enabled. If
+	 * the machine is affected K8_INTP_C1E_ACTIVE_MASK bits are set in
+	 * MSR_K8_INT_PENDING_MSG.
+	 */
+	rdmsr(MSR_K8_INT_PENDING_MSG, lo, hi);
+	if (!(lo & K8_INTP_C1E_ACTIVE_MASK))
+		return;
+
+	boot_cpu_set_bug(X86_BUG_AMD_APIC_C1E);
+
+	if (!boot_cpu_has(X86_FEATURE_NONSTOP_TSC))
+		mark_tsc_unstable("TSC halt in AMD C1E");
+	pr_info("System has AMD C1E enabled\n");
 }
 
 static int __init idle_setup(char *str)

arch/x86/kernel/process_32.c

@@ -49,7 +49,6 @@
 
 #include <asm/tlbflush.h>
 #include <asm/cpu.h>
-#include <asm/idle.h>
 #include <asm/syscalls.h>
 #include <asm/debugreg.h>
 #include <asm/switch_to.h>

arch/x86/kernel/process_64.c

@@ -44,7 +44,6 @@
 #include <asm/desc.h>
 #include <asm/proto.h>
 #include <asm/ia32.h>
-#include <asm/idle.h>
 #include <asm/syscalls.h>
 #include <asm/debugreg.h>
 #include <asm/switch_to.h>

arch/x86/kernel/smpboot.c

@@ -58,7 +58,6 @@
 #include <asm/desc.h>
 #include <asm/nmi.h>
 #include <asm/irq.h>
-#include <asm/idle.h>
 #include <asm/realmode.h>
 #include <asm/cpu.h>
 #include <asm/numa.h>
@@ -1596,7 +1595,6 @@ void play_dead_common(void)
 {
 	idle_task_exit();
 	reset_lazy_tlbstate();
-	amd_e400_remove_cpu(raw_smp_processor_id());
 
 	/* Ack it */
 	(void)cpu_report_death();

arch/x86/platform/uv/tlb_uv.c

@@ -19,7 +19,6 @@
 #include <asm/uv/uv_hub.h>
 #include <asm/uv/uv_bau.h>
 #include <asm/apic.h>
-#include <asm/idle.h>
 #include <asm/tsc.h>
 #include <asm/irq_vectors.h>
 #include <asm/timer.h>

drivers/acpi/processor_idle.c

@@ -141,7 +141,7 @@ static void lapic_timer_check_state(int state, struct acpi_processor *pr,
 	if (cpu_has(&cpu_data(pr->id), X86_FEATURE_ARAT))
 		return;
 
-	if (amd_e400_c1e_detected)
+	if (boot_cpu_has_bug(X86_BUG_AMD_APIC_C1E))
 		type = ACPI_STATE_C1;
 
 	/*

drivers/dma/ioat/registers.h

@@ -106,8 +106,6 @@
 #define IOAT_DMA_COMP_V1			0x0001	/* Compatibility with DMA version 1 */
 #define IOAT_DMA_COMP_V2			0x0002	/* Compatibility with DMA version 2 */
 
-/* IOAT1 define left for i7300_idle driver to not fail compiling */
-#define IOAT1_CHANSTS_OFFSET		0x04
 #define IOAT_CHANSTS_OFFSET		0x08	/* 64-bit Channel Status Register */
 #define IOAT_CHANSTS_COMPLETED_DESCRIPTOR_ADDR	(~0x3fULL)
 #define IOAT_CHANSTS_SOFT_ERR			0x10ULL

drivers/idle/Kconfig

@@ -8,20 +8,3 @@ config INTEL_IDLE
 	  native Intel hardware idle features.  The acpi_idle driver
 	  can be configured at the same time, in order to handle
 	  processors intel_idle does not support.
-
-menu "Memory power savings"
-depends on X86_64
-
-config I7300_IDLE_IOAT_CHANNEL
-	bool
-
-config I7300_IDLE
-	tristate "Intel chipset idle memory power saving driver"
-	select I7300_IDLE_IOAT_CHANNEL
-	help
-	  Enable memory power savings when idle with certain Intel server
-	  chipsets. The chipset must have I/O AT support, such as the
-	  Intel 7300. The power savings depends on the type and quantity of
-	  DRAM devices.
-
-endmenu

drivers/idle/Makefile

-obj-$(CONFIG_I7300_IDLE)			+= i7300_idle.o
 obj-$(CONFIG_INTEL_IDLE)			+= intel_idle.o
 

drivers/thermal/intel_powerclamp.c

@@ -56,7 +56,6 @@
 #include <asm/msr.h>
 #include <asm/mwait.h>
 #include <asm/cpu_device_id.h>
-#include <asm/idle.h>
 #include <asm/hardirq.h>
 
 #define MAX_TARGET_RATIO (50U)

drivers/xen/events/events_base.c

@@ -37,7 +37,6 @@
 #include <asm/desc.h>
 #include <asm/ptrace.h>
 #include <asm/irq.h>
-#include <asm/idle.h>
 #include <asm/io_apic.h>
 #include <asm/i8259.h>
 #include <asm/xen/pci.h>
@@ -1256,7 +1255,6 @@ void xen_evtchn_do_upcall(struct pt_regs *regs)
 
 	irq_enter();
 #ifdef CONFIG_X86
-	exit_idle();
 	inc_irq_stat(irq_hv_callback_count);
 #endif
 

init/main.c

@@ -448,6 +448,8 @@ void __init parse_early_param(void)
 	done = 1;
 }
 
+void __init __weak arch_post_acpi_subsys_init(void) { }
+
 void __init __weak smp_setup_processor_id(void)
 {
 }
@@ -649,6 +651,7 @@ asmlinkage __visible void __init start_kernel(void)
 	check_bugs();
 
 	acpi_subsystem_init();
+	arch_post_acpi_subsys_init();
 	sfi_init_late();
 
 	if (efi_enabled(EFI_RUNTIME_SERVICES)) {