Merge branch 'cpuidle' into next

12 files changed, 411 insertions, 87 deletions

diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index 7c93c7eb0e5..d66a47fde80 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -87,6 +87,10 @@ config ARCH_HAS_ILOG2_U64
 	bool
 	default y if 64BIT
 
+config ARCH_HAS_CPU_IDLE_WAIT
+	bool
+	default y
+
 config GENERIC_HWEIGHT
 	bool
 	default y
diff --git a/arch/powerpc/include/asm/processor.h b/arch/powerpc/include/asm/processor.h
index eb11a446720..b585bff1a02 100644
--- a/arch/powerpc/include/asm/processor.h
+++ b/arch/powerpc/include/asm/processor.h
@@ -382,6 +382,9 @@ static inline unsigned long get_clean_sp(struct pt_regs *regs, int is_32)
 }
 #endif
 
+extern unsigned long cpuidle_disable;
+enum idle_boot_override {IDLE_NO_OVERRIDE = 0, IDLE_POWERSAVE_OFF};
+
 #endif /* __KERNEL__ */
 #endif /* __ASSEMBLY__ */
 #endif /* _ASM_POWERPC_PROCESSOR_H */
diff --git a/arch/powerpc/include/asm/system.h b/arch/powerpc/include/asm/system.h
index e30a13d1ee7..f56a0a75d98 100644
--- a/arch/powerpc/include/asm/system.h
+++ b/arch/powerpc/include/asm/system.h
@@ -221,6 +221,15 @@ extern unsigned long klimit;
 extern void *zalloc_maybe_bootmem(size_t size, gfp_t mask);
 
 extern int powersave_nap;	/* set if nap mode can be used in idle loop */
+void cpu_idle_wait(void);
+
+#ifdef CONFIG_PSERIES_IDLE
+extern void update_smt_snooze_delay(int snooze);
+extern int pseries_notify_cpuidle_add_cpu(int cpu);
+#else
+static inline void update_smt_snooze_delay(int snooze) {}
+static inline int pseries_notify_cpuidle_add_cpu(int cpu) { return 0; }
+#endif
 
 /*
  * Atomic exchange
diff --git a/arch/powerpc/kernel/idle.c b/arch/powerpc/kernel/idle.c
index 39a2baa6ad5..8574b0e81ff 100644
--- a/arch/powerpc/kernel/idle.c
+++ b/arch/powerpc/kernel/idle.c
@@ -39,9 +39,13 @@
 #define cpu_should_die()	0
 #endif
 
+unsigned long cpuidle_disable = IDLE_NO_OVERRIDE;
+EXPORT_SYMBOL(cpuidle_disable);
+
 static int __init powersave_off(char *arg)
 {
 	ppc_md.power_save = NULL;
+	cpuidle_disable = IDLE_POWERSAVE_OFF;
 	return 0;
 }
 __setup("powersave=off", powersave_off);
@@ -102,6 +106,29 @@ void cpu_idle(void)
 	}
 }
 
+
+/*
+ * cpu_idle_wait - Used to ensure that all the CPUs come out of the old
+ * idle loop and start using the new idle loop.
+ * Required while changing idle handler on SMP systems.
+ * Caller must have changed idle handler to the new value before the call.
+ * This window may be larger on shared systems.
+ */
+void cpu_idle_wait(void)
+{
+	int cpu;
+	smp_mb();
+
+	/* kick all the CPUs so that they exit out of old idle routine */
+	get_online_cpus();
+	for_each_online_cpu(cpu) {
+		if (cpu != smp_processor_id())
+			smp_send_reschedule(cpu);
+	}
+	put_online_cpus();
+}
+EXPORT_SYMBOL_GPL(cpu_idle_wait);
+
 int powersave_nap;
 
 #ifdef CONFIG_SYSCTL
diff --git a/arch/powerpc/kernel/sysfs.c b/arch/powerpc/kernel/sysfs.c
index f579be55209..6fdf5ffe8c4 100644
--- a/arch/powerpc/kernel/sysfs.c
+++ b/arch/powerpc/kernel/sysfs.c
@@ -18,6 +18,7 @@
 #include <asm/machdep.h>
 #include <asm/smp.h>
 #include <asm/pmc.h>
+#include <asm/system.h>
 
 #include "cacheinfo.h"
 
@@ -51,6 +52,7 @@ static ssize_t store_smt_snooze_delay(struct sys_device *dev,
 		return -EINVAL;
 
 	per_cpu(smt_snooze_delay, cpu->sysdev.id) = snooze;
+	update_smt_snooze_delay(snooze);
 
 	return count;
 }
diff --git a/arch/powerpc/platforms/Kconfig b/arch/powerpc/platforms/Kconfig
index 3fe6d927ad7..31e1adeaa92 100644
--- a/arch/powerpc/platforms/Kconfig
+++ b/arch/powerpc/platforms/Kconfig
@@ -211,6 +211,12 @@ config PPC_PASEMI_CPUFREQ
 
 endmenu
 
+menu "CPUIdle driver"
+
+source "drivers/cpuidle/Kconfig"
+
+endmenu
+
 config PPC601_SYNC_FIX
 	bool "Workarounds for PPC601 bugs"
 	depends on 6xx && (PPC_PREP || PPC_PMAC)
diff --git a/arch/powerpc/platforms/pseries/Kconfig b/arch/powerpc/platforms/pseries/Kconfig
index c81f6bb9c10..ae7b6d41fed 100644
--- a/arch/powerpc/platforms/pseries/Kconfig
+++ b/arch/powerpc/platforms/pseries/Kconfig
@@ -120,3 +120,12 @@ config DTL
 	  which are accessible through a debugfs file.
 
 	  Say N if you are unsure.
+
+config PSERIES_IDLE
+	tristate "Cpuidle driver for pSeries platforms"
+	depends on CPU_IDLE
+	depends on PPC_PSERIES
+	default y
+	help
+	  Select this option to enable processor idle state management
+	  through cpuidle subsystem.
diff --git a/arch/powerpc/platforms/pseries/Makefile b/arch/powerpc/platforms/pseries/Makefile
index 3556e402cbf..236db46b407 100644
--- a/arch/powerpc/platforms/pseries/Makefile
+++ b/arch/powerpc/platforms/pseries/Makefile
@@ -22,6 +22,7 @@ obj-$(CONFIG_PHYP_DUMP)		+= phyp_dump.o
 obj-$(CONFIG_CMM)		+= cmm.o
 obj-$(CONFIG_DTL)		+= dtl.o
 obj-$(CONFIG_IO_EVENT_IRQ)	+= io_event_irq.o
+obj-$(CONFIG_PSERIES_IDLE)	+= processor_idle.o
 
 ifeq ($(CONFIG_PPC_PSERIES),y)
 obj-$(CONFIG_SUSPEND)		+= suspend.o
diff --git a/arch/powerpc/platforms/pseries/processor_idle.c b/arch/powerpc/platforms/pseries/processor_idle.c
new file mode 100644
index 00000000000..085fd3f45ad
--- /dev/null
+++ b/arch/powerpc/platforms/pseries/processor_idle.c
@@ -0,0 +1,329 @@
+/*
+ *  processor_idle - idle state cpuidle driver.
+ *  Adapted from drivers/idle/intel_idle.c and
+ *  drivers/acpi/processor_idle.c
+ *
+ */
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/moduleparam.h>
+#include <linux/cpuidle.h>
+#include <linux/cpu.h>
+
+#include <asm/paca.h>
+#include <asm/reg.h>
+#include <asm/system.h>
+#include <asm/machdep.h>
+#include <asm/firmware.h>
+
+#include "plpar_wrappers.h"
+#include "pseries.h"
+
+struct cpuidle_driver pseries_idle_driver = {
+	.name =		"pseries_idle",
+	.owner =	THIS_MODULE,
+};
+
+#define MAX_IDLE_STATE_COUNT	2
+
+static int max_idle_state = MAX_IDLE_STATE_COUNT - 1;
+static struct cpuidle_device __percpu *pseries_cpuidle_devices;
+static struct cpuidle_state *cpuidle_state_table;
+
+void update_smt_snooze_delay(int snooze)
+{
+	struct cpuidle_driver *drv = cpuidle_get_driver();
+	if (drv)
+		drv->states[0].target_residency = snooze;
+}
+
+static inline void idle_loop_prolog(unsigned long *in_purr, ktime_t *kt_before)
+{
+
+	*kt_before = ktime_get_real();
+	*in_purr = mfspr(SPRN_PURR);
+	/*
+	 * Indicate to the HV that we are idle. Now would be
+	 * a good time to find other work to dispatch.
+	 */
+	get_lppaca()->idle = 1;
+}
+
+static inline  s64 idle_loop_epilog(unsigned long in_purr, ktime_t kt_before)
+{
+	get_lppaca()->wait_state_cycles += mfspr(SPRN_PURR) - in_purr;
+	get_lppaca()->idle = 0;
+
+	return ktime_to_us(ktime_sub(ktime_get_real(), kt_before));
+}
+
+static int snooze_loop(struct cpuidle_device *dev,
+			struct cpuidle_driver *drv,
+			int index)
+{
+	unsigned long in_purr;
+	ktime_t kt_before;
+	unsigned long start_snooze;
+	long snooze = drv->states[0].target_residency;
+
+	idle_loop_prolog(&in_purr, &kt_before);
+
+	if (snooze) {
+		start_snooze = get_tb() + snooze * tb_ticks_per_usec;
+		local_irq_enable();
+		set_thread_flag(TIF_POLLING_NRFLAG);
+
+		while ((snooze < 0) || (get_tb() < start_snooze)) {
+			if (need_resched() || cpu_is_offline(dev->cpu))
+				goto out;
+			ppc64_runlatch_off();
+			HMT_low();
+			HMT_very_low();
+		}
+
+		HMT_medium();
+		clear_thread_flag(TIF_POLLING_NRFLAG);
+		smp_mb();
+		local_irq_disable();
+	}
+
+out:
+	HMT_medium();
+	dev->last_residency =
+		(int)idle_loop_epilog(in_purr, kt_before);
+	return index;
+}
+
+static int dedicated_cede_loop(struct cpuidle_device *dev,
+				struct cpuidle_driver *drv,
+				int index)
+{
+	unsigned long in_purr;
+	ktime_t kt_before;
+
+	idle_loop_prolog(&in_purr, &kt_before);
+	get_lppaca()->donate_dedicated_cpu = 1;
+
+	ppc64_runlatch_off();
+	HMT_medium();
+	cede_processor();
+
+	get_lppaca()->donate_dedicated_cpu = 0;
+	dev->last_residency =
+		(int)idle_loop_epilog(in_purr, kt_before);
+	return index;
+}
+
+static int shared_cede_loop(struct cpuidle_device *dev,
+			struct cpuidle_driver *drv,
+			int index)
+{
+	unsigned long in_purr;
+	ktime_t kt_before;
+
+	idle_loop_prolog(&in_purr, &kt_before);
+
+	/*
+	 * Yield the processor to the hypervisor.  We return if
+	 * an external interrupt occurs (which are driven prior
+	 * to returning here) or if a prod occurs from another
+	 * processor. When returning here, external interrupts
+	 * are enabled.
+	 */
+	cede_processor();
+
+	dev->last_residency =
+		(int)idle_loop_epilog(in_purr, kt_before);
+	return index;
+}
+
+/*
+ * States for dedicated partition case.
+ */
+static struct cpuidle_state dedicated_states[MAX_IDLE_STATE_COUNT] = {
+	{ /* Snooze */
+		.name = "snooze",
+		.desc = "snooze",
+		.flags = CPUIDLE_FLAG_TIME_VALID,
+		.exit_latency = 0,
+		.target_residency = 0,
+		.enter = &snooze_loop },
+	{ /* CEDE */
+		.name = "CEDE",
+		.desc = "CEDE",
+		.flags = CPUIDLE_FLAG_TIME_VALID,
+		.exit_latency = 1,
+		.target_residency = 10,
+		.enter = &dedicated_cede_loop },
+};
+
+/*
+ * States for shared partition case.
+ */
+static struct cpuidle_state shared_states[MAX_IDLE_STATE_COUNT] = {
+	{ /* Shared Cede */
+		.name = "Shared Cede",
+		.desc = "Shared Cede",
+		.flags = CPUIDLE_FLAG_TIME_VALID,
+		.exit_latency = 0,
+		.target_residency = 0,
+		.enter = &shared_cede_loop },
+};
+
+int pseries_notify_cpuidle_add_cpu(int cpu)
+{
+	struct cpuidle_device *dev =
+			per_cpu_ptr(pseries_cpuidle_devices, cpu);
+	if (dev && cpuidle_get_driver()) {
+		cpuidle_disable_device(dev);
+		cpuidle_enable_device(dev);
+	}
+	return 0;
+}
+
+/*
+ * pseries_cpuidle_driver_init()
+ */
+static int pseries_cpuidle_driver_init(void)
+{
+	int idle_state;
+	struct cpuidle_driver *drv = &pseries_idle_driver;
+
+	drv->state_count = 0;
+
+	for (idle_state = 0; idle_state < MAX_IDLE_STATE_COUNT; ++idle_state) {
+
+		if (idle_state > max_idle_state)
+			break;
+
+		/* is the state not enabled? */
+		if (cpuidle_state_table[idle_state].enter == NULL)
+			continue;
+
+		drv->states[drv->state_count] =	/* structure copy */
+			cpuidle_state_table[idle_state];
+
+		if (cpuidle_state_table == dedicated_states)
+			drv->states[drv->state_count].target_residency =
+				__get_cpu_var(smt_snooze_delay);
+
+		drv->state_count += 1;
+	}
+
+	return 0;
+}
+
+/* pseries_idle_devices_uninit(void)
+ * unregister cpuidle devices and de-allocate memory
+ */
+static void pseries_idle_devices_uninit(void)
+{
+	int i;
+	struct cpuidle_device *dev;
+
+	for_each_possible_cpu(i) {
+		dev = per_cpu_ptr(pseries_cpuidle_devices, i);
+		cpuidle_unregister_device(dev);
+	}
+
+	free_percpu(pseries_cpuidle_devices);
+	return;
+}
+
+/* pseries_idle_devices_init()
+ * allocate, initialize and register cpuidle device
+ */
+static int pseries_idle_devices_init(void)
+{
+	int i;
+	struct cpuidle_driver *drv = &pseries_idle_driver;
+	struct cpuidle_device *dev;
+
+	pseries_cpuidle_devices = alloc_percpu(struct cpuidle_device);
+	if (pseries_cpuidle_devices == NULL)
+		return -ENOMEM;
+
+	for_each_possible_cpu(i) {
+		dev = per_cpu_ptr(pseries_cpuidle_devices, i);
+		dev->state_count = drv->state_count;
+		dev->cpu = i;
+		if (cpuidle_register_device(dev)) {
+			printk(KERN_DEBUG \
+				"cpuidle_register_device %d failed!\n", i);
+			return -EIO;
+		}
+	}
+
+	return 0;
+}
+
+/*
+ * pseries_idle_probe()
+ * Choose state table for shared versus dedicated partition
+ */
+static int pseries_idle_probe(void)
+{
+
+	if (!firmware_has_feature(FW_FEATURE_SPLPAR))
+		return -ENODEV;
+
+	if (cpuidle_disable != IDLE_NO_OVERRIDE)
+		return -ENODEV;
+
+	if (max_idle_state == 0) {
+		printk(KERN_DEBUG "pseries processor idle disabled.\n");
+		return -EPERM;
+	}
+
+	if (get_lppaca()->shared_proc)
+		cpuidle_state_table = shared_states;
+	else
+		cpuidle_state_table = dedicated_states;
+
+	return 0;
+}
+
+static int __init pseries_processor_idle_init(void)
+{
+	int retval;
+
+	retval = pseries_idle_probe();
+	if (retval)
+		return retval;
+
+	pseries_cpuidle_driver_init();
+	retval = cpuidle_register_driver(&pseries_idle_driver);
+	if (retval) {
+		printk(KERN_DEBUG "Registration of pseries driver failed.\n");
+		return retval;
+	}
+
+	retval = pseries_idle_devices_init();
+	if (retval) {
+		pseries_idle_devices_uninit();
+		cpuidle_unregister_driver(&pseries_idle_driver);
+		return retval;
+	}
+
+	printk(KERN_DEBUG "pseries_idle_driver registered\n");
+
+	return 0;
+}
+
+static void __exit pseries_processor_idle_exit(void)
+{
+
+	pseries_idle_devices_uninit();
+	cpuidle_unregister_driver(&pseries_idle_driver);
+
+	return;
+}
+
+module_init(pseries_processor_idle_init);
+module_exit(pseries_processor_idle_exit);
+
+MODULE_AUTHOR("Deepthi Dharwar <deepthi@linux.vnet.ibm.com>");
+MODULE_DESCRIPTION("Cpuidle driver for POWER");
+MODULE_LICENSE("GPL");
diff --git a/arch/powerpc/platforms/pseries/pseries.h b/arch/powerpc/platforms/pseries/pseries.h
index 24c7162f11d..9a3dda07566 100644
--- a/arch/powerpc/platforms/pseries/pseries.h
+++ b/arch/powerpc/platforms/pseries/pseries.h
@@ -57,4 +57,7 @@ extern struct device_node *dlpar_configure_connector(u32);
 extern int dlpar_attach_node(struct device_node *);
 extern int dlpar_detach_node(struct device_node *);
 
+/* Snooze Delay, pseries_idle */
+DECLARE_PER_CPU(long, smt_snooze_delay);
+
 #endif /* _PSERIES_PSERIES_H */
diff --git a/arch/powerpc/platforms/pseries/setup.c b/arch/powerpc/platforms/pseries/setup.c
index 01df08dbc43..164839cb9fc 100644
--- a/arch/powerpc/platforms/pseries/setup.c
+++ b/arch/powerpc/platforms/pseries/setup.c
@@ -39,6 +39,7 @@
 #include <linux/irq.h>
 #include <linux/seq_file.h>
 #include <linux/root_dev.h>
+#include <linux/cpuidle.h>
 
 #include <asm/mmu.h>
 #include <asm/processor.h>
@@ -74,9 +75,6 @@ EXPORT_SYMBOL(CMO_PageSize);
 
 int fwnmi_active;  /* TRUE if an FWNMI handler is present */
 
-static void pseries_shared_idle_sleep(void);
-static void pseries_dedicated_idle_sleep(void);
-
 static struct device_node *pSeries_mpic_node;
 
 static void pSeries_show_cpuinfo(struct seq_file *m)
@@ -351,6 +349,21 @@ static int alloc_dispatch_log_kmem_cache(void)
 }
 early_initcall(alloc_dispatch_log_kmem_cache);
 
+static void pSeries_idle(void)
+{
+	/* This would call on the cpuidle framework, and the back-end pseries
+	 * driver to  go to idle states
+	 */
+	if (cpuidle_idle_call()) {
+		/* On error, execute default handler
+		 * to go into low thread priority and possibly
+		 * low power mode.
+		 */
+		HMT_low();
+		HMT_very_low();
+	}
+}
+
 static void __init pSeries_setup_arch(void)
 {
 	/* Discover PIC type and setup ppc_md accordingly */
@@ -373,18 +386,9 @@ static void __init pSeries_setup_arch(void)
 
 	pSeries_nvram_init();
 
-	/* Choose an idle loop */
 	if (firmware_has_feature(FW_FEATURE_SPLPAR)) {
 		vpa_init(boot_cpuid);
-		if (get_lppaca()->shared_proc) {
-			printk(KERN_DEBUG "Using shared processor idle loop\n");
-			ppc_md.power_save = pseries_shared_idle_sleep;
-		} else {
-			printk(KERN_DEBUG "Using dedicated idle loop\n");
-			ppc_md.power_save = pseries_dedicated_idle_sleep;
-		}
-	} else {
-		printk(KERN_DEBUG "Using default idle loop\n");
+		ppc_md.power_save = pSeries_idle;
 	}
 
 	if (firmware_has_feature(FW_FEATURE_LPAR))
@@ -585,80 +589,6 @@ static int __init pSeries_probe(void)
 	return 1;
 }
 
-
-DECLARE_PER_CPU(long, smt_snooze_delay);
-
-static void pseries_dedicated_idle_sleep(void)
-{ 
-	unsigned int cpu = smp_processor_id();
-	unsigned long start_snooze;
-	unsigned long in_purr, out_purr;
-	long snooze = __get_cpu_var(smt_snooze_delay);
-
-	/*
-	 * Indicate to the HV that we are idle. Now would be
-	 * a good time to find other work to dispatch.
-	 */
-	get_lppaca()->idle = 1;
-	get_lppaca()->donate_dedicated_cpu = 1;
-	in_purr = mfspr(SPRN_PURR);
-
-	/*
-	 * We come in with interrupts disabled, and need_resched()
-	 * has been checked recently.  If we should poll for a little
-	 * while, do so.
-	 */
-	if (snooze) {
-		start_snooze = get_tb() + snooze * tb_ticks_per_usec;
-		local_irq_enable();
-		set_thread_flag(TIF_POLLING_NRFLAG);
-
-		while ((snooze < 0) || (get_tb() < start_snooze)) {
-			if (need_resched() || cpu_is_offline(cpu))
-				goto out;
-			ppc64_runlatch_off();
-			HMT_low();
-			HMT_very_low();
-		}
-
-		HMT_medium();
-		clear_thread_flag(TIF_POLLING_NRFLAG);
-		smp_mb();
-		local_irq_disable();
-		if (need_resched() || cpu_is_offline(cpu))
-			goto out;
-	}
-
-	cede_processor();
-
-out:
-	HMT_medium();
-	out_purr = mfspr(SPRN_PURR);
-	get_lppaca()->wait_state_cycles += out_purr - in_purr;
-	get_lppaca()->donate_dedicated_cpu = 0;
-	get_lppaca()->idle = 0;
-}
-
-static void pseries_shared_idle_sleep(void)
-{
-	/*
-	 * Indicate to the HV that we are idle. Now would be
-	 * a good time to find other work to dispatch.
-	 */
-	get_lppaca()->idle = 1;
-
-	/*
-	 * Yield the processor to the hypervisor.  We return if
-	 * an external interrupt occurs (which are driven prior
-	 * to returning here) or if a prod occurs from another
-	 * processor. When returning here, external interrupts
-	 * are enabled.
-	 */
-	cede_processor();
-
-	get_lppaca()->idle = 0;
-}
-
 static int pSeries_pci_probe_mode(struct pci_bus *bus)
 {
 	if (firmware_has_feature(FW_FEATURE_LPAR))
diff --git a/arch/powerpc/platforms/pseries/smp.c b/arch/powerpc/platforms/pseries/smp.c
index 26e93fd4c62..bbc3c42f673 100644
--- a/arch/powerpc/platforms/pseries/smp.c
+++ b/arch/powerpc/platforms/pseries/smp.c
@@ -148,6 +148,7 @@ static void __devinit smp_xics_setup_cpu(int cpu)
 	set_cpu_current_state(cpu, CPU_STATE_ONLINE);
 	set_default_offline_state(cpu);
 #endif
+	pseries_notify_cpuidle_add_cpu(cpu);
 }
 
 static int __devinit smp_pSeries_kick_cpu(int nr)