Merge branch 'idle-release' of git://git.kernel.org/pub/scm/linux/kernel/git/lenb/linux-idle-2.6

* 'idle-release' of git://git.kernel.org/pub/scm/linux/kernel/git/lenb/linux-idle-2.6:
  x86 idle: deprecate mwait_idle() and "idle=mwait" cmdline param
  x86 idle: deprecate "no-hlt" cmdline param
  x86 idle APM: deprecate CONFIG_APM_CPU_IDLE
  x86 idle floppy: deprecate disable_hlt()
  x86 idle: EXPORT_SYMBOL(default_idle, pm_idle) only when APM demands it
  x86 idle: clarify AMD erratum 400 workaround
  idle governor: Avoid lock acquisition to read pm_qos before entering idle
  cpuidle: menu: fixed wrapping timers at 4.294 seconds

Documentation/feature-removal-schedule.txt

@@ -6,6 +6,42 @@ be removed from this file.
 
 ---------------------------
 
+What:	x86 floppy disable_hlt
+When:	2012
+Why:	ancient workaround of dubious utility clutters the
+	code used by everybody else.
+Who:	Len Brown <len.brown@intel.com>
+
+---------------------------
+
+What:	CONFIG_APM_CPU_IDLE, and its ability to call APM BIOS in idle
+When:	2012
+Why:	This optional sub-feature of APM is of dubious reliability,
+	and ancient APM laptops are likely better served by calling HLT.
+	Deleting CONFIG_APM_CPU_IDLE allows x86 to stop exporting
+	the pm_idle function pointer to modules.
+Who:	Len Brown <len.brown@intel.com>
+
+----------------------------
+
+What:	x86_32 "no-hlt" cmdline param
+When:	2012
+Why:	remove a branch from idle path, simplify code used by everybody.
+	This option disabled the use of HLT in idle and machine_halt()
+	for hardware that was flakey 15-years ago.  Today we have
+	"idle=poll" that removed HLT from idle, and so if such a machine
+	is still running the upstream kernel, "idle=poll" is likely sufficient.
+Who:	Len Brown <len.brown@intel.com>
+
+----------------------------
+
+What:	x86 "idle=mwait" cmdline param
+When:	2012
+Why:	simplify x86 idle code
+Who:	Len Brown <len.brown@intel.com>
+
+----------------------------
+
 What:	PRISM54
 When:	2.6.34
 

arch/x86/include/asm/acpi.h

@@ -139,7 +139,7 @@ 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 (c1e_detected)
+	else if (amd_e400_c1e_detected)
 		return 1;
 	else
 		return max_cstate;

arch/x86/include/asm/idle.h

@@ -16,6 +16,6 @@ static inline void enter_idle(void) { }
 static inline void exit_idle(void) { }
 #endif /* CONFIG_X86_64 */
 
-void c1e_remove_cpu(int cpu);
+void amd_e400_remove_cpu(int cpu);
 
 #endif /* _ASM_X86_IDLE_H */

arch/x86/include/asm/processor.h

@@ -754,10 +754,10 @@ static inline void __sti_mwait(unsigned long eax, unsigned long ecx)
 extern void mwait_idle_with_hints(unsigned long eax, unsigned long ecx);
 
 extern void select_idle_routine(const struct cpuinfo_x86 *c);
-extern void init_c1e_mask(void);
+extern void init_amd_e400_c1e_mask(void);
 
 extern unsigned long		boot_option_idle_override;
-extern bool			c1e_detected;
+extern bool			amd_e400_c1e_detected;
 
 enum idle_boot_override {IDLE_NO_OVERRIDE=0, IDLE_HALT, IDLE_NOMWAIT,
 			 IDLE_POLL, IDLE_FORCE_MWAIT};

arch/x86/kernel/apm_32.c

@@ -361,6 +361,7 @@ struct apm_user {
  * idle percentage above which bios idle calls are done
  */
 #ifdef CONFIG_APM_CPU_IDLE
+#warning deprecated CONFIG_APM_CPU_IDLE will be deleted in 2012
 #define DEFAULT_IDLE_THRESHOLD	95
 #else
 #define DEFAULT_IDLE_THRESHOLD	100
@@ -904,6 +905,7 @@ static void apm_cpu_idle(void)
 	unsigned int jiffies_since_last_check = jiffies - last_jiffies;
 	unsigned int bucket;
 
+	WARN_ONCE(1, "deprecated apm_cpu_idle will be deleted in 2012");
 recalc:
 	if (jiffies_since_last_check > IDLE_CALC_LIMIT) {
 		use_apm_idle = 0;

arch/x86/kernel/cpu/bugs.c

@@ -19,6 +19,7 @@
 
 static int __init no_halt(char *s)
 {
+	WARN_ONCE(1, "\"no-hlt\" is deprecated, please use \"idle=poll\"\n");
 	boot_cpu_data.hlt_works_ok = 0;
 	return 1;
 }

arch/x86/kernel/cpu/common.c

@@ -902,7 +902,7 @@ static void vgetcpu_set_mode(void)
 void __init identify_boot_cpu(void)
 {
 	identify_cpu(&boot_cpu_data);
-	init_c1e_mask();
+	init_amd_e400_c1e_mask();
 #ifdef CONFIG_X86_32
 	sysenter_setup();
 	enable_sep_cpu();

arch/x86/kernel/process.c

@@ -337,7 +337,9 @@ EXPORT_SYMBOL(boot_option_idle_override);
  * Powermanagement idle function, if any..
  */
 void (*pm_idle)(void);
+#if defined(CONFIG_APM_MODULE) && defined(CONFIG_APM_CPU_IDLE)
 EXPORT_SYMBOL(pm_idle);
+#endif
 
 #ifdef CONFIG_X86_32
 /*
@@ -397,7 +399,7 @@ void default_idle(void)
 		cpu_relax();
 	}
 }
-#ifdef CONFIG_APM_MODULE
+#if defined(CONFIG_APM_MODULE) && defined(CONFIG_APM_CPU_IDLE)
 EXPORT_SYMBOL(default_idle);
 #endif
 
@@ -535,45 +537,45 @@ int mwait_usable(const struct cpuinfo_x86 *c)
 	return (edx & MWAIT_EDX_C1);
 }
 
-bool c1e_detected;
+bool amd_e400_c1e_detected;
-EXPORT_SYMBOL(c1e_detected);
+EXPORT_SYMBOL(amd_e400_c1e_detected);
 
-static cpumask_var_t c1e_mask;
+static cpumask_var_t amd_e400_c1e_mask;
 
-void c1e_remove_cpu(int cpu)
+void amd_e400_remove_cpu(int cpu)
 {
-	if (c1e_mask != NULL)
+	if (amd_e400_c1e_mask != NULL)
-		cpumask_clear_cpu(cpu, c1e_mask);
+		cpumask_clear_cpu(cpu, amd_e400_c1e_mask);
 }
 
 /*
- * C1E aware idle routine. We check for C1E active in the interrupt
+ * 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)
  */
-static void c1e_idle(void)
+static void amd_e400_idle(void)
 {
 	if (need_resched())
 		return;
 
-	if (!c1e_detected) {
+	if (!amd_e400_c1e_detected) {
 		u32 lo, hi;
 
 		rdmsr(MSR_K8_INT_PENDING_MSG, lo, hi);
 
 		if (lo & K8_INTP_C1E_ACTIVE_MASK) {
-			c1e_detected = true;
+			amd_e400_c1e_detected = true;
 			if (!boot_cpu_has(X86_FEATURE_NONSTOP_TSC))
 				mark_tsc_unstable("TSC halt in AMD C1E");
 			printk(KERN_INFO "System has AMD C1E enabled\n");
 		}
 	}
 
-	if (c1e_detected) {
+	if (amd_e400_c1e_detected) {
 		int cpu = smp_processor_id();
 
-		if (!cpumask_test_cpu(cpu, c1e_mask)) {
+		if (!cpumask_test_cpu(cpu, amd_e400_c1e_mask)) {
-			cpumask_set_cpu(cpu, c1e_mask);
+			cpumask_set_cpu(cpu, amd_e400_c1e_mask);
 			/*
 			 * Force broadcast so ACPI can not interfere.
 			 */
@@ -616,17 +618,17 @@ void __cpuinit select_idle_routine(const struct cpuinfo_x86 *c)
 		pm_idle = mwait_idle;
 	} else if (cpu_has_amd_erratum(amd_erratum_400)) {
 		/* E400: APIC timer interrupt does not wake up CPU from C1e */
-		printk(KERN_INFO "using C1E aware idle routine\n");
+		printk(KERN_INFO "using AMD E400 aware idle routine\n");
-		pm_idle = c1e_idle;
+		pm_idle = amd_e400_idle;
 	} else
 		pm_idle = default_idle;
 }
 
-void __init init_c1e_mask(void)
+void __init init_amd_e400_c1e_mask(void)
 {
-	/* If we're using c1e_idle, we need to allocate c1e_mask. */
+	/* If we're using amd_e400_idle, we need to allocate amd_e400_c1e_mask. */
-	if (pm_idle == c1e_idle)
+	if (pm_idle == amd_e400_idle)
-		zalloc_cpumask_var(&c1e_mask, GFP_KERNEL);
+		zalloc_cpumask_var(&amd_e400_c1e_mask, GFP_KERNEL);
 }
 
 static int __init idle_setup(char *str)
@@ -640,6 +642,7 @@ static int __init idle_setup(char *str)
 		boot_option_idle_override = IDLE_POLL;
 	} else if (!strcmp(str, "mwait")) {
 		boot_option_idle_override = IDLE_FORCE_MWAIT;
+		WARN_ONCE(1, "\idle=mwait\" will be removed in 2012\"\n");
 	} else if (!strcmp(str, "halt")) {
 		/*
 		 * When the boot option of idle=halt is added, halt is

arch/x86/kernel/smpboot.c

@@ -1307,7 +1307,7 @@ void play_dead_common(void)
 {
 	idle_task_exit();
 	reset_lazy_tlbstate();
-	c1e_remove_cpu(raw_smp_processor_id());
+	amd_e400_remove_cpu(raw_smp_processor_id());
 
 	mb();
 	/* Ack it */

drivers/acpi/processor_idle.c

@@ -161,7 +161,7 @@ static void lapic_timer_check_state(int state, struct acpi_processor *pr,
 	if (cpu_has(&cpu_data(pr->id), X86_FEATURE_ARAT))
 		return;
 
-	if (c1e_detected)
+	if (amd_e400_c1e_detected)
 		type = ACPI_STATE_C1;
 
 	/*

drivers/block/floppy.c

@@ -1038,6 +1038,7 @@ static void floppy_disable_hlt(void)
 {
 	unsigned long flags;
 
+	WARN_ONCE(1, "floppy_disable_hlt() scheduled for removal in 2012");
 	spin_lock_irqsave(&floppy_hlt_lock, flags);
 	if (!hlt_disabled) {
 		hlt_disabled = 1;

drivers/cpuidle/governors/menu.c

@@ -237,6 +237,7 @@ static int menu_select(struct cpuidle_device *dev)
 	unsigned int power_usage = -1;
 	int i;
 	int multiplier;
+	struct timespec t;
 
 	if (data->needs_update) {
 		menu_update(dev);
@@ -251,8 +252,9 @@ static int menu_select(struct cpuidle_device *dev)
 		return 0;
 
 	/* determine the expected residency time, round up */
+	t = ktime_to_timespec(tick_nohz_get_sleep_length());
 	data->expected_us =
-	    DIV_ROUND_UP((u32)ktime_to_ns(tick_nohz_get_sleep_length()), 1000);
+		t.tv_sec * USEC_PER_SEC + t.tv_nsec / NSEC_PER_USEC;
 
 
 	data->bucket = which_bucket(data->expected_us);

include/linux/pm_qos_params.h

@@ -16,6 +16,10 @@
 #define PM_QOS_NUM_CLASSES 4
 #define PM_QOS_DEFAULT_VALUE -1
 
+#define PM_QOS_CPU_DMA_LAT_DEFAULT_VALUE	(2000 * USEC_PER_SEC)
+#define PM_QOS_NETWORK_LAT_DEFAULT_VALUE	(2000 * USEC_PER_SEC)
+#define PM_QOS_NETWORK_THROUGHPUT_DEFAULT_VALUE	0
+
 struct pm_qos_request_list {
 	struct plist_node list;
 	int pm_qos_class;

kernel/pm_qos_params.c

@@ -54,11 +54,17 @@ enum pm_qos_type {
 	PM_QOS_MIN		/* return the smallest value */
 };
 
+/*
+ * Note: The lockless read path depends on the CPU accessing
+ * target_value atomically.  Atomic access is only guaranteed on all CPU
+ * types linux supports for 32 bit quantites
+ */
 struct pm_qos_object {
 	struct plist_head requests;
 	struct blocking_notifier_head *notifiers;
 	struct miscdevice pm_qos_power_miscdev;
 	char *name;
+	s32 target_value;	/* Do not change to 64 bit */
 	s32 default_value;
 	enum pm_qos_type type;
 };
@@ -71,7 +77,8 @@ static struct pm_qos_object cpu_dma_pm_qos = {
 	.requests = PLIST_HEAD_INIT(cpu_dma_pm_qos.requests, pm_qos_lock),
 	.notifiers = &cpu_dma_lat_notifier,
 	.name = "cpu_dma_latency",
-	.default_value = 2000 * USEC_PER_SEC,
+	.target_value = PM_QOS_CPU_DMA_LAT_DEFAULT_VALUE,
+	.default_value = PM_QOS_CPU_DMA_LAT_DEFAULT_VALUE,
 	.type = PM_QOS_MIN,
 };
 
@@ -80,7 +87,8 @@ static struct pm_qos_object network_lat_pm_qos = {
 	.requests = PLIST_HEAD_INIT(network_lat_pm_qos.requests, pm_qos_lock),
 	.notifiers = &network_lat_notifier,
 	.name = "network_latency",
-	.default_value = 2000 * USEC_PER_SEC,
+	.target_value = PM_QOS_NETWORK_LAT_DEFAULT_VALUE,
+	.default_value = PM_QOS_NETWORK_LAT_DEFAULT_VALUE,
 	.type = PM_QOS_MIN
 };
 
@@ -90,7 +98,8 @@ static struct pm_qos_object network_throughput_pm_qos = {
 	.requests = PLIST_HEAD_INIT(network_throughput_pm_qos.requests, pm_qos_lock),
 	.notifiers = &network_throughput_notifier,
 	.name = "network_throughput",
-	.default_value = 0,
+	.target_value = PM_QOS_NETWORK_THROUGHPUT_DEFAULT_VALUE,
+	.default_value = PM_QOS_NETWORK_THROUGHPUT_DEFAULT_VALUE,
 	.type = PM_QOS_MAX,
 };
 
@@ -136,6 +145,16 @@ static inline int pm_qos_get_value(struct pm_qos_object *o)
 	}
 }
 
+static inline s32 pm_qos_read_value(struct pm_qos_object *o)
+{
+	return o->target_value;
+}
+
+static inline void pm_qos_set_value(struct pm_qos_object *o, s32 value)
+{
+	o->target_value = value;
+}
+
 static void update_target(struct pm_qos_object *o, struct plist_node *node,
 			  int del, int value)
 {
@@ -160,6 +179,7 @@ static void update_target(struct pm_qos_object *o, struct plist_node *node,
 		plist_add(node, &o->requests);
 	}
 	curr_value = pm_qos_get_value(o);
+	pm_qos_set_value(o, curr_value);
 	spin_unlock_irqrestore(&pm_qos_lock, flags);
 
 	if (prev_value != curr_value)
@@ -194,18 +214,11 @@ static int find_pm_qos_object_by_minor(int minor)
  * pm_qos_request - returns current system wide qos expectation
  * @pm_qos_class: identification of which qos value is requested
  *
- * This function returns the current target value in an atomic manner.
+ * This function returns the current target value.
  */
 int pm_qos_request(int pm_qos_class)
 {
-	unsigned long flags;
+	return pm_qos_read_value(pm_qos_array[pm_qos_class]);
-	int value;
-
-	spin_lock_irqsave(&pm_qos_lock, flags);
-	value = pm_qos_get_value(pm_qos_array[pm_qos_class]);
-	spin_unlock_irqrestore(&pm_qos_lock, flags);
-
-	return value;
 }
 EXPORT_SYMBOL_GPL(pm_qos_request);