Merge tag 'pm+acpi-3.15-rc1-3' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm

Pull more ACPI and power management fixes and updates from Rafael Wysocki:
 "This is PM and ACPI material that has emerged over the last two weeks
  and one fix for a CPU hotplug regression introduced by the recent CPU
  hotplug notifiers registration series.

  Included are intel_idle and turbostat updates from Len Brown (these
  have been in linux-next for quite some time), a new cpufreq driver for
  powernv (that might spend some more time in linux-next, but BenH was
  asking me so nicely to push it for 3.15 that I couldn't resist), some
  cpufreq fixes and cleanups (including fixes for some silly breakage in
  a couple of cpufreq drivers introduced during the 3.14 cycle),
  assorted ACPI cleanups, wakeup framework documentation fixes, a new
  sysfs attribute for cpuidle and a new command line argument for power
  domains diagnostics.

  Specifics:

   - Fix for a recently introduced CPU hotplug regression in ARM KVM
     from Ming Lei.

   - Fixes for breakage in the at32ap, loongson2_cpufreq, and unicore32
     cpufreq drivers introduced during the 3.14 cycle (-stable material)
     from Chen Gang and Viresh Kumar.

   - New powernv cpufreq driver from Vaidyanathan Srinivasan, with bits
     from Gautham R Shenoy and Srivatsa S Bhat.

   - Exynos cpufreq driver fix preventing it from being included into
     multiplatform builds that aren't supported by it from Sachin Kamat.

   - cpufreq cleanups related to the usage of the driver_data field in
     struct cpufreq_frequency_table from Viresh Kumar.

   - cpufreq ppc driver cleanup from Sachin Kamat.

   - Intel BayTrail support for intel_idle and ACPI idle from Len Brown.

   - Intel CPU model 54 (Atom N2000 series) support for intel_idle from
     Jan Kiszka.

   - intel_idle fix for Intel Ivy Town residency targets from Len Brown.

   - turbostat updates (Intel Broadwell support and output cleanups)
     from Len Brown.

   - New cpuidle sysfs attribute for exporting C-states' target
     residency information to user space from Daniel Lezcano.

   - New kernel command line argument to prevent power domains enabled
     by the bootloader from being turned off even if they are not in use
     (for diagnostics purposes) from Tushar Behera.

   - Fixes for wakeup sysfs attributes documentation from Geert
     Uytterhoeven.

   - New ACPI video blacklist entry for ThinkPad Helix from Stephen
     Chandler Paul.

   - Assorted ACPI cleanups and a Kconfig help update from Jonghwan
     Choi, Zhihui Zhang, Hanjun Guo"

* tag 'pm+acpi-3.15-rc1-3' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm: (28 commits)
  ACPI: Update the ACPI spec information in Kconfig
  arm, kvm: fix double lock on cpu_add_remove_lock
  cpuidle: sysfs: Export target residency information
  cpufreq: ppc: Remove duplicate inclusion of fsl_soc.h
  cpufreq: create another field .flags in cpufreq_frequency_table
  cpufreq: use kzalloc() to allocate memory for cpufreq_frequency_table
  cpufreq: don't print value of .driver_data from core
  cpufreq: ia64: don't set .driver_data to index
  cpufreq: powernv: Select CPUFreq related Kconfig options for powernv
  cpufreq: powernv: Use cpufreq_frequency_table.driver_data to store pstate ids
  cpufreq: powernv: cpufreq driver for powernv platform
  cpufreq: at32ap: don't declare local variable as static
  cpufreq: loongson2_cpufreq: don't declare local variable as static
  cpufreq: unicore32: fix typo issue for 'clk'
  cpufreq: exynos: Disable on multiplatform build
  PM / wakeup: Correct presence vs. emptiness of wakeup_* attributes
  PM / domains: Add pd_ignore_unused to keep power domains enabled
  ACPI / dock: Drop dock_device_ids[] table
  ACPI / video: Favor native backlight interface for ThinkPad Helix
  ACPI / thermal: Fix wrong variable usage in debug statement
  ...

Documentation/ABI/testing/sysfs-devices-power

@@ -83,8 +83,10 @@ Contact:	Rafael J. Wysocki <rjw@rjwysocki.net>
 Description:
 		The /sys/devices/.../wakeup_count attribute contains the number
 		of signaled wakeup events associated with the device.  This
-		attribute is read-only.  If the device is not enabled to wake up
+		attribute is read-only.  If the device is not capable to wake up
 		the system from sleep states, this attribute is not present.
+		If the device is not enabled to wake up the system from sleep
+		states, this attribute is empty.
 
 What:		/sys/devices/.../power/wakeup_active_count
 Date:		September 2010
@@ -93,8 +95,10 @@ Description:
 		The /sys/devices/.../wakeup_active_count attribute contains the
 		number of times the processing of wakeup events associated with
 		the device was completed (at the kernel level).  This attribute
-		is read-only.  If the device is not enabled to wake up the
-		system from sleep states, this attribute is not present.
+		is read-only.  If the device is not capable to wake up the
+		system from sleep states, this attribute is not present.  If
+		the device is not enabled to wake up the system from sleep
+		states, this attribute is empty.
 
 What:		/sys/devices/.../power/wakeup_abort_count
 Date:		February 2012
@@ -104,8 +108,9 @@ Description:
 		number of times the processing of a wakeup event associated with
 		the device might have aborted system transition into a sleep
 		state in progress.  This attribute is read-only.  If the device
-		is not enabled to wake up the system from sleep states, this
-		attribute is not present.
+		is not capable to wake up the system from sleep states, this
+		attribute is not present.  If the device is not enabled to wake
+		up the system from sleep states, this attribute is empty.
 
 What:		/sys/devices/.../power/wakeup_expire_count
 Date:		February 2012
@@ -114,8 +119,10 @@ Description:
 		The /sys/devices/.../wakeup_expire_count attribute contains the
 		number of times a wakeup event associated with the device has
 		been reported with a timeout that expired.  This attribute is
-		read-only.  If the device is not enabled to wake up the system
-		from sleep states, this attribute is not present.
+		read-only.  If the device is not capable to wake up the system
+		from sleep states, this attribute is not present.  If the
+		device is not enabled to wake up the system from sleep states,
+		this attribute is empty.
 
 What:		/sys/devices/.../power/wakeup_active
 Date:		September 2010
@@ -124,8 +131,10 @@ Description:
 		The /sys/devices/.../wakeup_active attribute contains either 1,
 		or 0, depending on whether or not a wakeup event associated with
 		the device is being processed (1).  This attribute is read-only.
-		If the device is not enabled to wake up the system from sleep
-		states, this attribute is not present.
+		If the device is not capable to wake up the system from sleep
+		states, this attribute is not present.  If the device is not
+		enabled to wake up the system from sleep states, this attribute
+		is empty.
 
 What:		/sys/devices/.../power/wakeup_total_time_ms
 Date:		September 2010
@@ -134,8 +143,9 @@ Description:
 		The /sys/devices/.../wakeup_total_time_ms attribute contains
 		the total time of processing wakeup events associated with the
 		device, in milliseconds.  This attribute is read-only.  If the
-		device is not enabled to wake up the system from sleep states,
-		this attribute is not present.
+		device is not capable to wake up the system from sleep states,
+		this attribute is not present.  If the device is not enabled to
+		wake up the system from sleep states, this attribute is empty.
 
 What:		/sys/devices/.../power/wakeup_max_time_ms
 Date:		September 2010
@@ -144,8 +154,10 @@ Description:
 		The /sys/devices/.../wakeup_max_time_ms attribute contains
 		the maximum time of processing a single wakeup event associated
 		with the device, in milliseconds.  This attribute is read-only.
-		If the device is not enabled to wake up the system from sleep
-		states, this attribute is not present.
+		If the device is not capable to wake up the system from sleep
+		states, this attribute is not present.  If the device is not
+		enabled to wake up the system from sleep states, this attribute
+		is empty.
 
 What:		/sys/devices/.../power/wakeup_last_time_ms
 Date:		September 2010
@@ -156,7 +168,8 @@ Description:
 		signaling the last wakeup event associated with the device, in
 		milliseconds.  This attribute is read-only.  If the device is
 		not enabled to wake up the system from sleep states, this
-		attribute is not present.
+		attribute is not present.  If the device is not enabled to wake
+		up the system from sleep states, this attribute is empty.
 
 What:		/sys/devices/.../power/wakeup_prevent_sleep_time_ms
 Date:		February 2012
@@ -165,9 +178,10 @@ Description:
 		The /sys/devices/.../wakeup_prevent_sleep_time_ms attribute
 		contains the total time the device has been preventing
 		opportunistic transitions to sleep states from occurring.
-		This attribute is read-only.  If the device is not enabled to
+		This attribute is read-only.  If the device is not capable to
 		wake up the system from sleep states, this attribute is not
-		present.
+		present.  If the device is not enabled to wake up the system
+		from sleep states, this attribute is empty.
 
 What:		/sys/devices/.../power/autosuspend_delay_ms
 Date:		September 2010

Documentation/kernel-parameters.txt

@@ -2563,6 +2563,13 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 
 	pcmv=		[HW,PCMCIA] BadgePAD 4
 
+	pd_ignore_unused
+			[PM]
+			Keep all power-domains already enabled by bootloader on,
+			even if no driver has claimed them. This is useful
+			for debug and development, but should not be
+			needed on a platform with proper driver support.
+
 	pd.		[PARIDE]
 			See Documentation/blockdev/paride.txt.
 

arch/mips/loongson/lemote-2f/clock.c

@@ -28,16 +28,16 @@ enum {
 };
 
 struct cpufreq_frequency_table loongson2_clockmod_table[] = {
-	{DC_RESV, CPUFREQ_ENTRY_INVALID},
-	{DC_ZERO, CPUFREQ_ENTRY_INVALID},
-	{DC_25PT, 0},
-	{DC_37PT, 0},
-	{DC_50PT, 0},
-	{DC_62PT, 0},
-	{DC_75PT, 0},
-	{DC_87PT, 0},
-	{DC_DISABLE, 0},
-	{DC_RESV, CPUFREQ_TABLE_END},
+	{0, DC_RESV, CPUFREQ_ENTRY_INVALID},
+	{0, DC_ZERO, CPUFREQ_ENTRY_INVALID},
+	{0, DC_25PT, 0},
+	{0, DC_37PT, 0},
+	{0, DC_50PT, 0},
+	{0, DC_62PT, 0},
+	{0, DC_75PT, 0},
+	{0, DC_87PT, 0},
+	{0, DC_DISABLE, 0},
+	{0, DC_RESV, CPUFREQ_TABLE_END},
 };
 EXPORT_SYMBOL_GPL(loongson2_clockmod_table);
 

arch/powerpc/configs/pseries_defconfig

@@ -306,3 +306,4 @@ CONFIG_KVM_BOOK3S_64=m
 CONFIG_KVM_BOOK3S_64_HV=y
 CONFIG_TRANSPARENT_HUGEPAGE=y
 CONFIG_TRANSPARENT_HUGEPAGE_ALWAYS=y
+CONFIG_CPU_FREQ_DEFAULT_GOV_ONDEMAND=y

arch/powerpc/configs/pseries_le_defconfig

@@ -301,3 +301,4 @@ CONFIG_CRYPTO_LZO=m
 # CONFIG_CRYPTO_ANSI_CPRNG is not set
 CONFIG_CRYPTO_DEV_NX=y
 CONFIG_CRYPTO_DEV_NX_ENCRYPT=m
+CONFIG_CPU_FREQ_DEFAULT_GOV_ONDEMAND=y

arch/powerpc/include/asm/reg.h

@@ -272,6 +272,10 @@
 #define SPRN_HSRR1	0x13B	/* Hypervisor Save/Restore 1 */
 #define SPRN_IC		0x350	/* Virtual Instruction Count */
 #define SPRN_VTB	0x351	/* Virtual Time Base */
+#define SPRN_PMICR	0x354   /* Power Management Idle Control Reg */
+#define SPRN_PMSR	0x355   /* Power Management Status Reg */
+#define SPRN_PMCR	0x374	/* Power Management Control Register */
+
 /* HFSCR and FSCR bit numbers are the same */
 #define FSCR_TAR_LG	8	/* Enable Target Address Register */
 #define FSCR_EBB_LG	7	/* Enable Event Based Branching */

arch/powerpc/platforms/powernv/Kconfig

@@ -11,6 +11,12 @@ config PPC_POWERNV
 	select PPC_UDBG_16550
 	select PPC_SCOM
 	select ARCH_RANDOM
+	select CPU_FREQ
+	select CPU_FREQ_GOV_PERFORMANCE
+	select CPU_FREQ_GOV_POWERSAVE
+	select CPU_FREQ_GOV_USERSPACE
+	select CPU_FREQ_GOV_ONDEMAND
+	select CPU_FREQ_GOV_CONSERVATIVE
 	default y
 
 config PPC_POWERNV_RTAS

arch/x86/kernel/acpi/cstate.c

@@ -87,7 +87,9 @@ static long acpi_processor_ffh_cstate_probe_cpu(void *_cx)
 	num_cstate_subtype = edx_part & MWAIT_SUBSTATE_MASK;
 
 	retval = 0;
-	if (num_cstate_subtype < (cx->address & MWAIT_SUBSTATE_MASK)) {
+	/* If the HW does not support any sub-states in this C-state */
+	if (num_cstate_subtype == 0) {
+		pr_warn(FW_BUG "ACPI MWAIT C-state 0x%x not supported by HW (0x%x)\n", cx->address, edx_part);
 		retval = -1;
 		goto out;
 	}

drivers/acpi/Kconfig

@@ -31,10 +31,14 @@ menuconfig ACPI
 	  ACPI CA, see:
 	  <http://acpica.org/>
 
-	  ACPI is an open industry specification co-developed by
-	  Hewlett-Packard, Intel, Microsoft, Phoenix, and Toshiba.
+	  ACPI is an open industry specification originally co-developed by
+	  Hewlett-Packard, Intel, Microsoft, Phoenix, and Toshiba. Currently,
+	  it is developed by the ACPI Specification Working Group (ASWG) under
+	  the UEFI Forum and any UEFI member can join the ASWG and contribute
+	  to the ACPI specification.
 	  The specification is available at:
 	  <http://www.acpi.info>
+	  <http://www.uefi.org/acpi/specs>
 
 if ACPI
 

drivers/acpi/dock.c

@@ -51,12 +51,6 @@ MODULE_PARM_DESC(immediate_undock, "1 (default) will cause the driver to "
 	" the driver to wait for userspace to write the undock sysfs file "
 	" before undocking");
 
-static const struct acpi_device_id dock_device_ids[] = {
-	{"LNXDOCK", 0},
-	{"", 0},
-};
-MODULE_DEVICE_TABLE(acpi, dock_device_ids);
-
 struct dock_station {
 	acpi_handle handle;
 	unsigned long last_dock_time;

drivers/acpi/osl.c

@@ -1219,10 +1219,9 @@ acpi_os_create_semaphore(u32 max_units, u32 initial_units, acpi_handle * handle)
 {
 	struct semaphore *sem = NULL;
 
-	sem = acpi_os_allocate(sizeof(struct semaphore));
+	sem = acpi_os_allocate_zeroed(sizeof(struct semaphore));
 	if (!sem)
 		return AE_NO_MEMORY;
-	memset(sem, 0, sizeof(struct semaphore));
 
 	sema_init(sem, initial_units);
 

drivers/acpi/thermal.c

@@ -344,7 +344,7 @@ static int acpi_thermal_trips_update(struct acpi_thermal *tz, int flag)
 			tz->trips.hot.flags.valid = 1;
 			ACPI_DEBUG_PRINT((ACPI_DB_INFO,
 					"Found hot threshold [%lu]\n",
-					tz->trips.critical.temperature));
+					tz->trips.hot.temperature));
 		}
 	}
 

drivers/acpi/utils.c

@@ -164,11 +164,10 @@ acpi_extract_package(union acpi_object *package,
 	 * Validate output buffer.
 	 */
 	if (buffer->length == ACPI_ALLOCATE_BUFFER) {
-		buffer->pointer = ACPI_ALLOCATE(size_required);
+		buffer->pointer = ACPI_ALLOCATE_ZEROED(size_required);
 		if (!buffer->pointer)
 			return AE_NO_MEMORY;
 		buffer->length = size_required;
-		memset(buffer->pointer, 0, size_required);
 	} else {
 		if (buffer->length < size_required) {
 			buffer->length = size_required;

drivers/acpi/video.c

@@ -487,6 +487,14 @@ static struct dmi_system_id video_dmi_table[] __initdata = {
 		DMI_MATCH(DMI_PRODUCT_VERSION, "Lenovo IdeaPad Yoga 13"),
 		},
 	},
+	{
+	.callback = video_set_use_native_backlight,
+	.ident = "Thinkpad Helix",
+	.matches = {
+		DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"),
+		DMI_MATCH(DMI_PRODUCT_VERSION, "ThinkPad Helix"),
+		},
+	},
 	{
 	 .callback = video_set_use_native_backlight,
 	 .ident = "Dell Inspiron 7520",

drivers/base/power/domain.c

@@ -705,6 +705,14 @@ static int pm_genpd_runtime_resume(struct device *dev)
 	return 0;
 }
 
+static bool pd_ignore_unused;
+static int __init pd_ignore_unused_setup(char *__unused)
+{
+	pd_ignore_unused = true;
+	return 1;
+}
+__setup("pd_ignore_unused", pd_ignore_unused_setup);
+
 /**
  * pm_genpd_poweroff_unused - Power off all PM domains with no devices in use.
  */
@@ -712,6 +720,11 @@ void pm_genpd_poweroff_unused(void)
 {
 	struct generic_pm_domain *genpd;
 
+	if (pd_ignore_unused) {
+		pr_warn("genpd: Not disabling unused power domains\n");
+		return;
+	}
+
 	mutex_lock(&gpd_list_lock);
 
 	list_for_each_entry(genpd, &gpd_list, gpd_list_node)

drivers/cpufreq/Kconfig.arm

@@ -30,7 +30,7 @@ config ARM_EXYNOS_CPUFREQ
 
 config ARM_EXYNOS4210_CPUFREQ
 	bool "SAMSUNG EXYNOS4210"
-	depends on CPU_EXYNOS4210
+	depends on CPU_EXYNOS4210 && !ARCH_MULTIPLATFORM
 	default y
 	select ARM_EXYNOS_CPUFREQ
 	help
@@ -41,7 +41,7 @@ config ARM_EXYNOS4210_CPUFREQ
 
 config ARM_EXYNOS4X12_CPUFREQ
 	bool "SAMSUNG EXYNOS4x12"
-	depends on (SOC_EXYNOS4212 || SOC_EXYNOS4412)
+	depends on (SOC_EXYNOS4212 || SOC_EXYNOS4412) && !ARCH_MULTIPLATFORM
 	default y
 	select ARM_EXYNOS_CPUFREQ
 	help
@@ -52,7 +52,7 @@ config ARM_EXYNOS4X12_CPUFREQ
 
 config ARM_EXYNOS5250_CPUFREQ
 	bool "SAMSUNG EXYNOS5250"
-	depends on SOC_EXYNOS5250
+	depends on SOC_EXYNOS5250 && !ARCH_MULTIPLATFORM
 	default y
 	select ARM_EXYNOS_CPUFREQ
 	help

drivers/cpufreq/Kconfig.powerpc

@@ -54,3 +54,11 @@ config PPC_PASEMI_CPUFREQ
 	help
 	  This adds the support for frequency switching on PA Semi
 	  PWRficient processors.
+
+config POWERNV_CPUFREQ
+       tristate "CPU frequency scaling for IBM POWERNV platform"
+       depends on PPC_POWERNV
+       default y
+       help
+	 This adds support for CPU frequency switching on IBM POWERNV
+	 platform

drivers/cpufreq/Makefile

@@ -86,6 +86,7 @@ obj-$(CONFIG_PPC_CORENET_CPUFREQ)   += ppc-corenet-cpufreq.o
 obj-$(CONFIG_CPU_FREQ_PMAC)		+= pmac32-cpufreq.o
 obj-$(CONFIG_CPU_FREQ_PMAC64)		+= pmac64-cpufreq.o
 obj-$(CONFIG_PPC_PASEMI_CPUFREQ)	+= pasemi-cpufreq.o
+obj-$(CONFIG_POWERNV_CPUFREQ)		+= powernv-cpufreq.o
 
 ##################################################################################
 # Other platform drivers

drivers/cpufreq/acpi-cpufreq.c

@@ -754,7 +754,7 @@ static int acpi_cpufreq_cpu_init(struct cpufreq_policy *policy)
 		goto err_unreg;
 	}
 
-	data->freq_table = kmalloc(sizeof(*data->freq_table) *
+	data->freq_table = kzalloc(sizeof(*data->freq_table) *
 		    (perf->state_count+1), GFP_KERNEL);
 	if (!data->freq_table) {
 		result = -ENOMEM;

drivers/cpufreq/at32ap-cpufreq.c

@@ -52,7 +52,7 @@ static int at32_set_target(struct cpufreq_policy *policy, unsigned int index)
 static int at32_cpufreq_driver_init(struct cpufreq_policy *policy)
 {
 	unsigned int frequency, rate, min_freq;
-	static struct clk *cpuclk;
+	struct clk *cpuclk;
 	int retval, steps, i;
 
 	if (policy->cpu != 0)

drivers/cpufreq/cris-artpec3-cpufreq.c

@@ -15,9 +15,9 @@ static struct notifier_block cris_sdram_freq_notifier_block = {
 };
 
 static struct cpufreq_frequency_table cris_freq_table[] = {
-	{0x01,	6000},
-	{0x02,	200000},
-	{0,	CPUFREQ_TABLE_END},
+	{0, 0x01, 6000},
+	{0, 0x02, 200000},
+	{0, 0, CPUFREQ_TABLE_END},
 };
 
 static unsigned int cris_freq_get_cpu_frequency(unsigned int cpu)

drivers/cpufreq/cris-etraxfs-cpufreq.c

@@ -15,9 +15,9 @@ static struct notifier_block cris_sdram_freq_notifier_block = {
 };
 
 static struct cpufreq_frequency_table cris_freq_table[] = {
-	{0x01, 6000},
-	{0x02, 200000},
-	{0, CPUFREQ_TABLE_END},
+	{0, 0x01, 6000},
+	{0, 0x02, 200000},
+	{0, 0, CPUFREQ_TABLE_END},
 };
 
 static unsigned int cris_freq_get_cpu_frequency(unsigned int cpu)

drivers/cpufreq/elanfreq.c

@@ -56,15 +56,15 @@ static struct s_elan_multiplier elan_multiplier[] = {
 };
 
 static struct cpufreq_frequency_table elanfreq_table[] = {
-	{0,	1000},
-	{1,	2000},
-	{2,	4000},
-	{3,	8000},
-	{4,	16000},
-	{5,	33000},
-	{6,	66000},
-	{7,	99000},
-	{0,	CPUFREQ_TABLE_END},
+	{0, 0,	1000},
+	{0, 1,	2000},
+	{0, 2,	4000},
+	{0, 3,	8000},
+	{0, 4,	16000},
+	{0, 5,	33000},
+	{0, 6,	66000},
+	{0, 7,	99000},
+	{0, 0,	CPUFREQ_TABLE_END},
 };
 
 

drivers/cpufreq/exynos4210-cpufreq.c

@@ -29,12 +29,12 @@ static unsigned int exynos4210_volt_table[] = {
 };
 
 static struct cpufreq_frequency_table exynos4210_freq_table[] = {
-	{L0, 1200 * 1000},
-	{L1, 1000 * 1000},
-	{L2,  800 * 1000},
-	{L3,  500 * 1000},
-	{L4,  200 * 1000},
-	{0, CPUFREQ_TABLE_END},
+	{0, L0, 1200 * 1000},
+	{0, L1, 1000 * 1000},
+	{0, L2,  800 * 1000},
+	{0, L3,  500 * 1000},
+	{0, L4,  200 * 1000},
+	{0, 0, CPUFREQ_TABLE_END},
 };
 
 static struct apll_freq apll_freq_4210[] = {

drivers/cpufreq/exynos4x12-cpufreq.c

@@ -30,21 +30,21 @@ static unsigned int exynos4x12_volt_table[] = {
 };
 
 static struct cpufreq_frequency_table exynos4x12_freq_table[] = {
-	{CPUFREQ_BOOST_FREQ, 1500 * 1000},
-	{L1, 1400 * 1000},
-	{L2, 1300 * 1000},
-	{L3, 1200 * 1000},
-	{L4, 1100 * 1000},
-	{L5, 1000 * 1000},
-	{L6,  900 * 1000},
-	{L7,  800 * 1000},
-	{L8,  700 * 1000},
-	{L9,  600 * 1000},
-	{L10, 500 * 1000},
-	{L11, 400 * 1000},
-	{L12, 300 * 1000},
-	{L13, 200 * 1000},
-	{0, CPUFREQ_TABLE_END},
+	{CPUFREQ_BOOST_FREQ, L0, 1500 * 1000},
+	{0, L1, 1400 * 1000},
+	{0, L2, 1300 * 1000},
+	{0, L3, 1200 * 1000},
+	{0, L4, 1100 * 1000},
+	{0, L5, 1000 * 1000},
+	{0, L6,  900 * 1000},
+	{0, L7,  800 * 1000},
+	{0, L8,  700 * 1000},
+	{0, L9,  600 * 1000},
+	{0, L10, 500 * 1000},
+	{0, L11, 400 * 1000},
+	{0, L12, 300 * 1000},
+	{0, L13, 200 * 1000},
+	{0, 0, CPUFREQ_TABLE_END},
 };
 
 static struct apll_freq *apll_freq_4x12;

drivers/cpufreq/exynos5250-cpufreq.c

@@ -34,23 +34,23 @@ static unsigned int exynos5250_volt_table[] = {
 };
 
 static struct cpufreq_frequency_table exynos5250_freq_table[] = {
-	{L0, 1700 * 1000},
-	{L1, 1600 * 1000},
-	{L2, 1500 * 1000},
-	{L3, 1400 * 1000},
-	{L4, 1300 * 1000},
-	{L5, 1200 * 1000},
-	{L6, 1100 * 1000},
-	{L7, 1000 * 1000},
-	{L8,  900 * 1000},
-	{L9,  800 * 1000},
-	{L10, 700 * 1000},
-	{L11, 600 * 1000},
-	{L12, 500 * 1000},
-	{L13, 400 * 1000},
-	{L14, 300 * 1000},
-	{L15, 200 * 1000},
-	{0, CPUFREQ_TABLE_END},
+	{0, L0, 1700 * 1000},
+	{0, L1, 1600 * 1000},
+	{0, L2, 1500 * 1000},
+	{0, L3, 1400 * 1000},
+	{0, L4, 1300 * 1000},
+	{0, L5, 1200 * 1000},
+	{0, L6, 1100 * 1000},
+	{0, L7, 1000 * 1000},
+	{0, L8,  900 * 1000},
+	{0, L9,  800 * 1000},
+	{0, L10, 700 * 1000},
+	{0, L11, 600 * 1000},
+	{0, L12, 500 * 1000},
+	{0, L13, 400 * 1000},
+	{0, L14, 300 * 1000},
+	{0, L15, 200 * 1000},
+	{0, 0, CPUFREQ_TABLE_END},
 };
 
 static struct apll_freq apll_freq_5250[] = {

drivers/cpufreq/freq_table.c

@@ -33,11 +33,10 @@ int cpufreq_frequency_table_cpuinfo(struct cpufreq_policy *policy,
 			continue;
 		}
 		if (!cpufreq_boost_enabled()
-		    && table[i].driver_data == CPUFREQ_BOOST_FREQ)
+		    && (table[i].flags & CPUFREQ_BOOST_FREQ))
 			continue;
 
-		pr_debug("table entry %u: %u kHz, %u driver_data\n",
-					i, freq, table[i].driver_data);
+		pr_debug("table entry %u: %u kHz\n", i, freq);
 		if (freq < min_freq)
 			min_freq = freq;
 		if (freq > max_freq)
@@ -175,8 +174,8 @@ int cpufreq_frequency_table_target(struct cpufreq_policy *policy,
 	} else
 		*index = optimal.driver_data;
 
-	pr_debug("target is %u (%u kHz, %u)\n", *index, table[*index].frequency,
-		table[*index].driver_data);
+	pr_debug("target index is %u, freq is:%u kHz\n", *index,
+		 table[*index].frequency);
 
 	return 0;
 }
@@ -230,7 +229,7 @@ static ssize_t show_available_freqs(struct cpufreq_policy *policy, char *buf,
 		 * show_boost = false and driver_data != BOOST freq
 		 * display NON BOOST freqs
 		 */
-		if (show_boost ^ (table[i].driver_data == CPUFREQ_BOOST_FREQ))
+		if (show_boost ^ (table[i].flags & CPUFREQ_BOOST_FREQ))
 			continue;
 
 		count += sprintf(&buf[count], "%d ", table[i].frequency);

drivers/cpufreq/ia64-acpi-cpufreq.c

@@ -254,7 +254,7 @@ acpi_cpufreq_cpu_init (
 	}
 
 	/* alloc freq_table */
-	data->freq_table = kmalloc(sizeof(*data->freq_table) *
+	data->freq_table = kzalloc(sizeof(*data->freq_table) *
 	                           (data->acpi_data.state_count + 1),
 	                           GFP_KERNEL);
 	if (!data->freq_table) {
@@ -275,7 +275,6 @@ acpi_cpufreq_cpu_init (
 	/* table init */
 	for (i = 0; i <= data->acpi_data.state_count; i++)
 	{
-		data->freq_table[i].driver_data = i;
 		if (i < data->acpi_data.state_count) {
 			data->freq_table[i].frequency =
 			      data->acpi_data.states[i].core_frequency * 1000;

drivers/cpufreq/kirkwood-cpufreq.c

@@ -43,9 +43,9 @@ static struct priv
  * table.
  */
 static struct cpufreq_frequency_table kirkwood_freq_table[] = {
-	{STATE_CPU_FREQ,	0}, /* CPU uses cpuclk */
-	{STATE_DDR_FREQ,	0}, /* CPU uses ddrclk */
-	{0,			CPUFREQ_TABLE_END},
+	{0, STATE_CPU_FREQ,	0}, /* CPU uses cpuclk */
+	{0, STATE_DDR_FREQ,	0}, /* CPU uses ddrclk */
+	{0, 0,			CPUFREQ_TABLE_END},
 };
 
 static unsigned int kirkwood_cpufreq_get_cpu_frequency(unsigned int cpu)

drivers/cpufreq/longhaul.c

@@ -475,7 +475,7 @@ static int longhaul_get_ranges(void)
 		return -EINVAL;
 	}
 
-	longhaul_table = kmalloc((numscales + 1) * sizeof(*longhaul_table),
+	longhaul_table = kzalloc((numscales + 1) * sizeof(*longhaul_table),
 			GFP_KERNEL);
 	if (!longhaul_table)
 		return -ENOMEM;

drivers/cpufreq/loongson2_cpufreq.c

@@ -69,7 +69,7 @@ static int loongson2_cpufreq_target(struct cpufreq_policy *policy,
 
 static int loongson2_cpufreq_cpu_init(struct cpufreq_policy *policy)
 {
-	static struct clk *cpuclk;
+	struct clk *cpuclk;
 	int i;
 	unsigned long rate;
 	int ret;

drivers/cpufreq/maple-cpufreq.c

@@ -59,9 +59,9 @@
 #define CPUFREQ_LOW                   1
 
 static struct cpufreq_frequency_table maple_cpu_freqs[] = {
-	{CPUFREQ_HIGH,		0},
-	{CPUFREQ_LOW,		0},
-	{0,			CPUFREQ_TABLE_END},
+	{0, CPUFREQ_HIGH,		0},
+	{0, CPUFREQ_LOW,		0},
+	{0, 0,				CPUFREQ_TABLE_END},
 };
 
 /* Power mode data is an array of the 32 bits PCR values to use for

drivers/cpufreq/p4-clockmod.c

@@ -92,16 +92,16 @@ static int cpufreq_p4_setdc(unsigned int cpu, unsigned int newstate)
 
 
 static struct cpufreq_frequency_table p4clockmod_table[] = {
-	{DC_RESV, CPUFREQ_ENTRY_INVALID},
-	{DC_DFLT, 0},
-	{DC_25PT, 0},
-	{DC_38PT, 0},
-	{DC_50PT, 0},
-	{DC_64PT, 0},
-	{DC_75PT, 0},
-	{DC_88PT, 0},
-	{DC_DISABLE, 0},
-	{DC_RESV, CPUFREQ_TABLE_END},
+	{0, DC_RESV, CPUFREQ_ENTRY_INVALID},
+	{0, DC_DFLT, 0},
+	{0, DC_25PT, 0},
+	{0, DC_38PT, 0},
+	{0, DC_50PT, 0},
+	{0, DC_64PT, 0},
+	{0, DC_75PT, 0},
+	{0, DC_88PT, 0},
+	{0, DC_DISABLE, 0},
+	{0, DC_RESV, CPUFREQ_TABLE_END},
 };
 
 

drivers/cpufreq/pasemi-cpufreq.c

@@ -60,12 +60,12 @@ static int current_astate;
 
 /* We support 5(A0-A4) power states excluding turbo(A5-A6) modes */
 static struct cpufreq_frequency_table pas_freqs[] = {
-	{0,	0},
-	{1,	0},
-	{2,	0},
-	{3,	0},
-	{4,	0},
-	{0,	CPUFREQ_TABLE_END},
+	{0, 0,	0},
+	{0, 1,	0},
+	{0, 2,	0},
+	{0, 3,	0},
+	{0, 4,	0},
+	{0, 0,	CPUFREQ_TABLE_END},
 };
 
 /*

drivers/cpufreq/pmac32-cpufreq.c

@@ -81,9 +81,9 @@ static int is_pmu_based;
 #define CPUFREQ_LOW                   1
 
 static struct cpufreq_frequency_table pmac_cpu_freqs[] = {
-	{CPUFREQ_HIGH, 		0},
-	{CPUFREQ_LOW,		0},
-	{0,			CPUFREQ_TABLE_END},
+	{0, CPUFREQ_HIGH,	0},
+	{0, CPUFREQ_LOW,	0},
+	{0, 0,			CPUFREQ_TABLE_END},
 };
 
 static inline void local_delay(unsigned long ms)

drivers/cpufreq/pmac64-cpufreq.c

@@ -65,9 +65,9 @@
 #define CPUFREQ_LOW                   1
 
 static struct cpufreq_frequency_table g5_cpu_freqs[] = {
-	{CPUFREQ_HIGH, 		0},
-	{CPUFREQ_LOW,		0},
-	{0,			CPUFREQ_TABLE_END},
+	{0, CPUFREQ_HIGH,	0},
+	{0, CPUFREQ_LOW,	0},
+	{0, 0,			CPUFREQ_TABLE_END},
 };
 
 /* Power mode data is an array of the 32 bits PCR values to use for

drivers/cpufreq/powernow-k6.c

@@ -37,15 +37,15 @@ MODULE_PARM_DESC(bus_frequency, "Bus frequency in kHz");
 
 /* Clock ratio multiplied by 10 - see table 27 in AMD#23446 */
 static struct cpufreq_frequency_table clock_ratio[] = {
-	{60,  /* 110 -> 6.0x */ 0},
-	{55,  /* 011 -> 5.5x */ 0},
-	{50,  /* 001 -> 5.0x */ 0},
-	{45,  /* 000 -> 4.5x */ 0},
-	{40,  /* 010 -> 4.0x */ 0},
-	{35,  /* 111 -> 3.5x */ 0},
-	{30,  /* 101 -> 3.0x */ 0},
-	{20,  /* 100 -> 2.0x */ 0},
-	{0, CPUFREQ_TABLE_END}
+	{0, 60,  /* 110 -> 6.0x */ 0},
+	{0, 55,  /* 011 -> 5.5x */ 0},
+	{0, 50,  /* 001 -> 5.0x */ 0},
+	{0, 45,  /* 000 -> 4.5x */ 0},
+	{0, 40,  /* 010 -> 4.0x */ 0},
+	{0, 35,  /* 111 -> 3.5x */ 0},
+	{0, 30,  /* 101 -> 3.0x */ 0},
+	{0, 20,  /* 100 -> 2.0x */ 0},
+	{0, 0, CPUFREQ_TABLE_END}
 };
 
 static const u8 index_to_register[8] = { 6, 3, 1, 0, 2, 7, 5, 4 };

drivers/cpufreq/powernow-k8.c

@@ -623,7 +623,7 @@ static int fill_powernow_table(struct powernow_k8_data *data,
 	if (check_pst_table(data, pst, maxvid))
 		return -EINVAL;
 
-	powernow_table = kmalloc((sizeof(*powernow_table)
+	powernow_table = kzalloc((sizeof(*powernow_table)
 		* (data->numps + 1)), GFP_KERNEL);
 	if (!powernow_table) {
 		printk(KERN_ERR PFX "powernow_table memory alloc failure\n");
@@ -793,7 +793,7 @@ static int powernow_k8_cpu_init_acpi(struct powernow_k8_data *data)
 	}
 
 	/* fill in data->powernow_table */
-	powernow_table = kmalloc((sizeof(*powernow_table)
+	powernow_table = kzalloc((sizeof(*powernow_table)
 		* (data->acpi_data.state_count + 1)), GFP_KERNEL);
 	if (!powernow_table) {
 		pr_debug("powernow_table memory alloc failure\n");
@@ -810,7 +810,6 @@ static int powernow_k8_cpu_init_acpi(struct powernow_k8_data *data)
 
 	powernow_table[data->acpi_data.state_count].frequency =
 		CPUFREQ_TABLE_END;
-	powernow_table[data->acpi_data.state_count].driver_data = 0;
 	data->powernow_table = powernow_table;
 
 	if (cpumask_first(cpu_core_mask(data->cpu)) == data->cpu)

drivers/cpufreq/powernv-cpufreq.c

@@ -0,0 +1,341 @@
+/*
+ * POWERNV cpufreq driver for the IBM POWER processors
+ *
+ * (C) Copyright IBM 2014
+ *
+ * Author: Vaidyanathan Srinivasan <svaidy at linux.vnet.ibm.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2, or (at your option)
+ * any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ */
+
+#define pr_fmt(fmt)	"powernv-cpufreq: " fmt
+
+#include <linux/kernel.h>
+#include <linux/sysfs.h>
+#include <linux/cpumask.h>
+#include <linux/module.h>
+#include <linux/cpufreq.h>
+#include <linux/smp.h>
+#include <linux/of.h>
+
+#include <asm/cputhreads.h>
+#include <asm/reg.h>
+
+#define POWERNV_MAX_PSTATES	256
+
+static struct cpufreq_frequency_table powernv_freqs[POWERNV_MAX_PSTATES+1];
+
+/*
+ * Note: The set of pstates consists of contiguous integers, the
+ * smallest of which is indicated by powernv_pstate_info.min, the
+ * largest of which is indicated by powernv_pstate_info.max.
+ *
+ * The nominal pstate is the highest non-turbo pstate in this
+ * platform. This is indicated by powernv_pstate_info.nominal.
+ */
+static struct powernv_pstate_info {
+	int min;
+	int max;
+	int nominal;
+	int nr_pstates;
+} powernv_pstate_info;
+
+/*
+ * Initialize the freq table based on data obtained
+ * from the firmware passed via device-tree
+ */
+static int init_powernv_pstates(void)
+{
+	struct device_node *power_mgt;
+	int i, pstate_min, pstate_max, pstate_nominal, nr_pstates = 0;
+	const __be32 *pstate_ids, *pstate_freqs;
+	u32 len_ids, len_freqs;
+
+	power_mgt = of_find_node_by_path("/ibm,opal/power-mgt");
+	if (!power_mgt) {
+		pr_warn("power-mgt node not found\n");
+		return -ENODEV;
+	}
+
+	if (of_property_read_u32(power_mgt, "ibm,pstate-min", &pstate_min)) {
+		pr_warn("ibm,pstate-min node not found\n");
+		return -ENODEV;
+	}
+
+	if (of_property_read_u32(power_mgt, "ibm,pstate-max", &pstate_max)) {
+		pr_warn("ibm,pstate-max node not found\n");
+		return -ENODEV;
+	}
+
+	if (of_property_read_u32(power_mgt, "ibm,pstate-nominal",
+				 &pstate_nominal)) {
+		pr_warn("ibm,pstate-nominal not found\n");
+		return -ENODEV;
+	}
+	pr_info("cpufreq pstate min %d nominal %d max %d\n", pstate_min,
+		pstate_nominal, pstate_max);
+
+	pstate_ids = of_get_property(power_mgt, "ibm,pstate-ids", &len_ids);
+	if (!pstate_ids) {
+		pr_warn("ibm,pstate-ids not found\n");
+		return -ENODEV;
+	}
+
+	pstate_freqs = of_get_property(power_mgt, "ibm,pstate-frequencies-mhz",
+				      &len_freqs);
+	if (!pstate_freqs) {
+		pr_warn("ibm,pstate-frequencies-mhz not found\n");
+		return -ENODEV;
+	}
+
+	WARN_ON(len_ids != len_freqs);
+	nr_pstates = min(len_ids, len_freqs) / sizeof(u32);
+	if (!nr_pstates) {
+		pr_warn("No PStates found\n");
+		return -ENODEV;
+	}
+
+	pr_debug("NR PStates %d\n", nr_pstates);
+	for (i = 0; i < nr_pstates; i++) {
+		u32 id = be32_to_cpu(pstate_ids[i]);
+		u32 freq = be32_to_cpu(pstate_freqs[i]);
+
+		pr_debug("PState id %d freq %d MHz\n", id, freq);
+		powernv_freqs[i].frequency = freq * 1000; /* kHz */
+		powernv_freqs[i].driver_data = id;
+	}
+	/* End of list marker entry */
+	powernv_freqs[i].frequency = CPUFREQ_TABLE_END;
+
+	powernv_pstate_info.min = pstate_min;
+	powernv_pstate_info.max = pstate_max;
+	powernv_pstate_info.nominal = pstate_nominal;
+	powernv_pstate_info.nr_pstates = nr_pstates;
+
+	return 0;
+}
+
+/* Returns the CPU frequency corresponding to the pstate_id. */
+static unsigned int pstate_id_to_freq(int pstate_id)
+{
+	int i;
+
+	i = powernv_pstate_info.max - pstate_id;
+	BUG_ON(i >= powernv_pstate_info.nr_pstates || i < 0);
+
+	return powernv_freqs[i].frequency;
+}
+
+/*
+ * cpuinfo_nominal_freq_show - Show the nominal CPU frequency as indicated by
+ * the firmware
+ */
+static ssize_t cpuinfo_nominal_freq_show(struct cpufreq_policy *policy,
+					char *buf)
+{
+	return sprintf(buf, "%u\n",
+		pstate_id_to_freq(powernv_pstate_info.nominal));
+}
+
+struct freq_attr cpufreq_freq_attr_cpuinfo_nominal_freq =
+	__ATTR_RO(cpuinfo_nominal_freq);
+
+static struct freq_attr *powernv_cpu_freq_attr[] = {
+	&cpufreq_freq_attr_scaling_available_freqs,
+	&cpufreq_freq_attr_cpuinfo_nominal_freq,
+	NULL,
+};
+
+/* Helper routines */
+
+/* Access helpers to power mgt SPR */
+
+static inline unsigned long get_pmspr(unsigned long sprn)
+{
+	switch (sprn) {
+	case SPRN_PMCR:
+		return mfspr(SPRN_PMCR);
+
+	case SPRN_PMICR:
+		return mfspr(SPRN_PMICR);
+
+	case SPRN_PMSR:
+		return mfspr(SPRN_PMSR);
+	}
+	BUG();
+}
+
+static inline void set_pmspr(unsigned long sprn, unsigned long val)
+{
+	switch (sprn) {
+	case SPRN_PMCR:
+		mtspr(SPRN_PMCR, val);
+		return;
+
+	case SPRN_PMICR:
+		mtspr(SPRN_PMICR, val);
+		return;
+	}
+	BUG();
+}
+
+/*
+ * Use objects of this type to query/update
+ * pstates on a remote CPU via smp_call_function.
+ */
+struct powernv_smp_call_data {
+	unsigned int freq;
+	int pstate_id;
+};
+
+/*
+ * powernv_read_cpu_freq: Reads the current frequency on this CPU.
+ *
+ * Called via smp_call_function.
+ *
+ * Note: The caller of the smp_call_function should pass an argument of
+ * the type 'struct powernv_smp_call_data *' along with this function.
+ *
+ * The current frequency on this CPU will be returned via
+ * ((struct powernv_smp_call_data *)arg)->freq;
+ */
+static void powernv_read_cpu_freq(void *arg)
+{
+	unsigned long pmspr_val;
+	s8 local_pstate_id;
+	struct powernv_smp_call_data *freq_data = arg;
+
+	pmspr_val = get_pmspr(SPRN_PMSR);
+
+	/*
+	 * The local pstate id corresponds bits 48..55 in the PMSR.
+	 * Note: Watch out for the sign!
+	 */
+	local_pstate_id = (pmspr_val >> 48) & 0xFF;
+	freq_data->pstate_id = local_pstate_id;
+	freq_data->freq = pstate_id_to_freq(freq_data->pstate_id);
+
+	pr_debug("cpu %d pmsr %016lX pstate_id %d frequency %d kHz\n",
+		raw_smp_processor_id(), pmspr_val, freq_data->pstate_id,
+		freq_data->freq);
+}
+
+/*
+ * powernv_cpufreq_get: Returns the CPU frequency as reported by the
+ * firmware for CPU 'cpu'. This value is reported through the sysfs
+ * file cpuinfo_cur_freq.
+ */
+unsigned int powernv_cpufreq_get(unsigned int cpu)
+{
+	struct powernv_smp_call_data freq_data;
+
+	smp_call_function_any(cpu_sibling_mask(cpu), powernv_read_cpu_freq,
+			&freq_data, 1);
+
+	return freq_data.freq;
+}
+
+/*
+ * set_pstate: Sets the pstate on this CPU.
+ *
+ * This is called via an smp_call_function.
+ *
+ * The caller must ensure that freq_data is of the type
+ * (struct powernv_smp_call_data *) and the pstate_id which needs to be set
+ * on this CPU should be present in freq_data->pstate_id.
+ */
+static void set_pstate(void *freq_data)
+{
+	unsigned long val;
+	unsigned long pstate_ul =
+		((struct powernv_smp_call_data *) freq_data)->pstate_id;
+
+	val = get_pmspr(SPRN_PMCR);
+	val = val & 0x0000FFFFFFFFFFFFULL;
+
+	pstate_ul = pstate_ul & 0xFF;
+
+	/* Set both global(bits 56..63) and local(bits 48..55) PStates */
+	val = val | (pstate_ul << 56) | (pstate_ul << 48);
+
+	pr_debug("Setting cpu %d pmcr to %016lX\n",
+			raw_smp_processor_id(), val);
+	set_pmspr(SPRN_PMCR, val);
+}
+
+/*
+ * powernv_cpufreq_target_index: Sets the frequency corresponding to
+ * the cpufreq table entry indexed by new_index on the cpus in the
+ * mask policy->cpus
+ */
+static int powernv_cpufreq_target_index(struct cpufreq_policy *policy,
+					unsigned int new_index)
+{
+	struct powernv_smp_call_data freq_data;
+
+	freq_data.pstate_id = powernv_freqs[new_index].driver_data;
+
+	/*
+	 * Use smp_call_function to send IPI and execute the
+	 * mtspr on target CPU.  We could do that without IPI
+	 * if current CPU is within policy->cpus (core)
+	 */
+	smp_call_function_any(policy->cpus, set_pstate, &freq_data, 1);
+
+	return 0;
+}
+
+static int powernv_cpufreq_cpu_init(struct cpufreq_policy *policy)
+{
+	int base, i;
+
+	base = cpu_first_thread_sibling(policy->cpu);
+
+	for (i = 0; i < threads_per_core; i++)
+		cpumask_set_cpu(base + i, policy->cpus);
+
+	return cpufreq_table_validate_and_show(policy, powernv_freqs);
+}
+
+static struct cpufreq_driver powernv_cpufreq_driver = {
+	.name		= "powernv-cpufreq",
+	.flags		= CPUFREQ_CONST_LOOPS,
+	.init		= powernv_cpufreq_cpu_init,
+	.verify		= cpufreq_generic_frequency_table_verify,
+	.target_index	= powernv_cpufreq_target_index,
+	.get		= powernv_cpufreq_get,
+	.attr		= powernv_cpu_freq_attr,
+};
+
+static int __init powernv_cpufreq_init(void)
+{
+	int rc = 0;
+
+	/* Discover pstates from device tree and init */
+	rc = init_powernv_pstates();
+	if (rc) {
+		pr_info("powernv-cpufreq disabled. System does not support PState control\n");
+		return rc;
+	}
+
+	return cpufreq_register_driver(&powernv_cpufreq_driver);
+}
+module_init(powernv_cpufreq_init);
+
+static void __exit powernv_cpufreq_exit(void)
+{
+	cpufreq_unregister_driver(&powernv_cpufreq_driver);
+}
+module_exit(powernv_cpufreq_exit);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Vaidyanathan Srinivasan <svaidy at linux.vnet.ibm.com>");

drivers/cpufreq/ppc-corenet-cpufreq.c

@@ -13,7 +13,6 @@
 #include <linux/clk.h>
 #include <linux/cpufreq.h>
 #include <linux/errno.h>
-#include <sysdev/fsl_soc.h>
 #include <linux/init.h>
 #include <linux/kernel.h>
 #include <linux/module.h>

drivers/cpufreq/ppc_cbe_cpufreq.c

@@ -32,15 +32,15 @@
 
 /* the CBE supports an 8 step frequency scaling */
 static struct cpufreq_frequency_table cbe_freqs[] = {
-	{1,	0},
-	{2,	0},
-	{3,	0},
-	{4,	0},
-	{5,	0},
-	{6,	0},
-	{8,	0},
-	{10,	0},
-	{0,	CPUFREQ_TABLE_END},
+	{0, 1,	0},
+	{0, 2,	0},
+	{0, 3,	0},
+	{0, 4,	0},
+	{0, 5,	0},
+	{0, 6,	0},
+	{0, 8,	0},
+	{0, 10,	0},
+	{0, 0,	CPUFREQ_TABLE_END},
 };
 
 /*

drivers/cpufreq/s3c2416-cpufreq.c

@@ -72,19 +72,19 @@ static struct s3c2416_dvfs s3c2416_dvfs_table[] = {
 #endif
 
 static struct cpufreq_frequency_table s3c2416_freq_table[] = {
-	{ SOURCE_HCLK, FREQ_DVS },
-	{ SOURCE_ARMDIV, 133333 },
-	{ SOURCE_ARMDIV, 266666 },
-	{ SOURCE_ARMDIV, 400000 },
-	{ 0, CPUFREQ_TABLE_END },
+	{ 0, SOURCE_HCLK, FREQ_DVS },
+	{ 0, SOURCE_ARMDIV, 133333 },
+	{ 0, SOURCE_ARMDIV, 266666 },
+	{ 0, SOURCE_ARMDIV, 400000 },
+	{ 0, 0, CPUFREQ_TABLE_END },
 };
 
 static struct cpufreq_frequency_table s3c2450_freq_table[] = {
-	{ SOURCE_HCLK, FREQ_DVS },
-	{ SOURCE_ARMDIV, 133500 },
-	{ SOURCE_ARMDIV, 267000 },
-	{ SOURCE_ARMDIV, 534000 },
-	{ 0, CPUFREQ_TABLE_END },
+	{ 0, SOURCE_HCLK, FREQ_DVS },
+	{ 0, SOURCE_ARMDIV, 133500 },
+	{ 0, SOURCE_ARMDIV, 267000 },
+	{ 0, SOURCE_ARMDIV, 534000 },
+	{ 0, 0, CPUFREQ_TABLE_END },
 };
 
 static unsigned int s3c2416_cpufreq_get_speed(unsigned int cpu)

drivers/cpufreq/s3c24xx-cpufreq.c

@@ -586,7 +586,7 @@ static int s3c_cpufreq_build_freq(void)
 	size = cpu_cur.info->calc_freqtable(&cpu_cur, NULL, 0);
 	size++;
 
-	ftab = kmalloc(sizeof(*ftab) * size, GFP_KERNEL);
+	ftab = kzalloc(sizeof(*ftab) * size, GFP_KERNEL);
 	if (!ftab) {
 		printk(KERN_ERR "%s: no memory for tables\n", __func__);
 		return -ENOMEM;
@@ -664,7 +664,7 @@ int __init s3c_plltab_register(struct cpufreq_frequency_table *plls,
 
 	size = sizeof(*vals) * (plls_no + 1);
 
-	vals = kmalloc(size, GFP_KERNEL);
+	vals = kzalloc(size, GFP_KERNEL);
 	if (vals) {
 		memcpy(vals, plls, size);
 		pll_reg = vals;

drivers/cpufreq/s3c64xx-cpufreq.c

@@ -37,19 +37,19 @@ static struct s3c64xx_dvfs s3c64xx_dvfs_table[] = {
 };
 
 static struct cpufreq_frequency_table s3c64xx_freq_table[] = {
-	{ 0,  66000 },
-	{ 0, 100000 },
-	{ 0, 133000 },
-	{ 1, 200000 },
-	{ 1, 222000 },
-	{ 1, 266000 },
-	{ 2, 333000 },
-	{ 2, 400000 },
-	{ 2, 532000 },
-	{ 2, 533000 },
-	{ 3, 667000 },
-	{ 4, 800000 },
-	{ 0, CPUFREQ_TABLE_END },
+	{ 0, 0,  66000 },
+	{ 0, 0, 100000 },
+	{ 0, 0, 133000 },
+	{ 0, 1, 200000 },
+	{ 0, 1, 222000 },
+	{ 0, 1, 266000 },
+	{ 0, 2, 333000 },
+	{ 0, 2, 400000 },
+	{ 0, 2, 532000 },
+	{ 0, 2, 533000 },
+	{ 0, 3, 667000 },
+	{ 0, 4, 800000 },
+	{ 0, 0, CPUFREQ_TABLE_END },
 };
 #endif
 

drivers/cpufreq/s5pv210-cpufreq.c

@@ -64,12 +64,12 @@ enum s5pv210_dmc_port {
 };
 
 static struct cpufreq_frequency_table s5pv210_freq_table[] = {
-	{L0, 1000*1000},
-	{L1, 800*1000},
-	{L2, 400*1000},
-	{L3, 200*1000},
-	{L4, 100*1000},
-	{0, CPUFREQ_TABLE_END},
+	{0, L0, 1000*1000},
+	{0, L1, 800*1000},
+	{0, L2, 400*1000},
+	{0, L3, 200*1000},
+	{0, L4, 100*1000},
+	{0, 0, CPUFREQ_TABLE_END},
 };
 
 static struct regulator *arm_regulator;

drivers/cpufreq/sc520_freq.c

@@ -33,9 +33,9 @@ static __u8 __iomem *cpuctl;
 #define PFX "sc520_freq: "
 
 static struct cpufreq_frequency_table sc520_freq_table[] = {
-	{0x01,	100000},
-	{0x02,	133000},
-	{0,	CPUFREQ_TABLE_END},
+	{0, 0x01,	100000},
+	{0, 0x02,	133000},
+	{0, 0,	CPUFREQ_TABLE_END},
 };
 
 static unsigned int sc520_freq_get_cpu_frequency(unsigned int cpu)

drivers/cpufreq/spear-cpufreq.c

@@ -195,18 +195,15 @@ static int spear_cpufreq_probe(struct platform_device *pdev)
 	cnt = prop->length / sizeof(u32);
 	val = prop->value;
 
-	freq_tbl = kmalloc(sizeof(*freq_tbl) * (cnt + 1), GFP_KERNEL);
+	freq_tbl = kzalloc(sizeof(*freq_tbl) * (cnt + 1), GFP_KERNEL);
 	if (!freq_tbl) {
 		ret = -ENOMEM;
 		goto out_put_node;
 	}
 
-	for (i = 0; i < cnt; i++) {
-		freq_tbl[i].driver_data = i;
+	for (i = 0; i < cnt; i++)
 		freq_tbl[i].frequency = be32_to_cpup(val++);
-	}
 
-	freq_tbl[i].driver_data = i;
 	freq_tbl[i].frequency = CPUFREQ_TABLE_END;
 
 	spear_cpufreq.freq_tbl = freq_tbl;

drivers/cpufreq/speedstep-ich.c

@@ -49,9 +49,9 @@ static u32 pmbase;
  * are in kHz for the time being.
  */
 static struct cpufreq_frequency_table speedstep_freqs[] = {
-	{SPEEDSTEP_HIGH,	0},
-	{SPEEDSTEP_LOW,		0},
-	{0,			CPUFREQ_TABLE_END},
+	{0, SPEEDSTEP_HIGH,	0},
+	{0, SPEEDSTEP_LOW,	0},
+	{0, 0,			CPUFREQ_TABLE_END},
 };
 
 

drivers/cpufreq/speedstep-smi.c

@@ -42,9 +42,9 @@ static enum speedstep_processor speedstep_processor;
  * are in kHz for the time being.
  */
 static struct cpufreq_frequency_table speedstep_freqs[] = {
-	{SPEEDSTEP_HIGH,	0},
-	{SPEEDSTEP_LOW,		0},
-	{0,			CPUFREQ_TABLE_END},
+	{0, SPEEDSTEP_HIGH,	0},
+	{0, SPEEDSTEP_LOW,	0},
+	{0, 0,			CPUFREQ_TABLE_END},
 };
 
 #define GET_SPEEDSTEP_OWNER 0

drivers/cpufreq/unicore2-cpufreq.c

@@ -45,7 +45,7 @@ static int ucv2_target(struct cpufreq_policy *policy,
 	freqs.new = target_freq;
 
 	cpufreq_freq_transition_begin(policy, &freqs);
-	ret = clk_set_rate(policy->mclk, target_freq * 1000);
+	ret = clk_set_rate(policy->clk, target_freq * 1000);
 	cpufreq_freq_transition_end(policy, &freqs, ret);
 
 	return ret;

drivers/cpuidle/sysfs.c

@@ -293,6 +293,7 @@ static ssize_t show_state_##_name(struct cpuidle_state *state, \
 }
 
 define_show_state_function(exit_latency)
+define_show_state_function(target_residency)
 define_show_state_function(power_usage)
 define_show_state_ull_function(usage)
 define_show_state_ull_function(time)
@@ -304,6 +305,7 @@ define_store_state_ull_function(disable)
 define_one_state_ro(name, show_state_name);
 define_one_state_ro(desc, show_state_desc);
 define_one_state_ro(latency, show_state_exit_latency);
+define_one_state_ro(residency, show_state_target_residency);
 define_one_state_ro(power, show_state_power_usage);
 define_one_state_ro(usage, show_state_usage);
 define_one_state_ro(time, show_state_time);
@@ -313,6 +315,7 @@ static struct attribute *cpuidle_state_default_attrs[] = {
 	&attr_name.attr,
 	&attr_desc.attr,
 	&attr_latency.attr,
+	&attr_residency.attr,
 	&attr_power.attr,
 	&attr_usage.attr,
 	&attr_time.attr,

drivers/idle/intel_idle.c

@@ -196,6 +196,53 @@ static struct cpuidle_state snb_cstates[] = {
 		.enter = NULL }
 };
 
+static struct cpuidle_state byt_cstates[] = {
+	{
+		.name = "C1-BYT",
+		.desc = "MWAIT 0x00",
+		.flags = MWAIT2flg(0x00) | CPUIDLE_FLAG_TIME_VALID,
+		.exit_latency = 1,
+		.target_residency = 1,
+		.enter = &intel_idle },
+	{
+		.name = "C1E-BYT",
+		.desc = "MWAIT 0x01",
+		.flags = MWAIT2flg(0x01) | CPUIDLE_FLAG_TIME_VALID,
+		.exit_latency = 15,
+		.target_residency = 30,
+		.enter = &intel_idle },
+	{
+		.name = "C6N-BYT",
+		.desc = "MWAIT 0x58",
+		.flags = MWAIT2flg(0x58) | CPUIDLE_FLAG_TIME_VALID | CPUIDLE_FLAG_TLB_FLUSHED,
+		.exit_latency = 40,
+		.target_residency = 275,
+		.enter = &intel_idle },
+	{
+		.name = "C6S-BYT",
+		.desc = "MWAIT 0x52",
+		.flags = MWAIT2flg(0x52) | CPUIDLE_FLAG_TIME_VALID | CPUIDLE_FLAG_TLB_FLUSHED,
+		.exit_latency = 140,
+		.target_residency = 560,
+		.enter = &intel_idle },
+	{
+		.name = "C7-BYT",
+		.desc = "MWAIT 0x60",
+		.flags = MWAIT2flg(0x60) | CPUIDLE_FLAG_TIME_VALID | CPUIDLE_FLAG_TLB_FLUSHED,
+		.exit_latency = 1200,
+		.target_residency = 1500,
+		.enter = &intel_idle },
+	{
+		.name = "C7S-BYT",
+		.desc = "MWAIT 0x64",
+		.flags = MWAIT2flg(0x64) | CPUIDLE_FLAG_TIME_VALID | CPUIDLE_FLAG_TLB_FLUSHED,
+		.exit_latency = 10000,
+		.target_residency = 20000,
+		.enter = &intel_idle },
+	{
+		.enter = NULL }
+};
+
 static struct cpuidle_state ivb_cstates[] = {
 	{
 		.name = "C1-IVB",
@@ -236,6 +283,105 @@ static struct cpuidle_state ivb_cstates[] = {
 		.enter = NULL }
 };
 
+static struct cpuidle_state ivt_cstates[] = {
+	{
+		.name = "C1-IVT",
+		.desc = "MWAIT 0x00",
+		.flags = MWAIT2flg(0x00) | CPUIDLE_FLAG_TIME_VALID,
+		.exit_latency = 1,
+		.target_residency = 1,
+		.enter = &intel_idle },
+	{
+		.name = "C1E-IVT",
+		.desc = "MWAIT 0x01",
+		.flags = MWAIT2flg(0x01) | CPUIDLE_FLAG_TIME_VALID,
+		.exit_latency = 10,
+		.target_residency = 80,
+		.enter = &intel_idle },
+	{
+		.name = "C3-IVT",
+		.desc = "MWAIT 0x10",
+		.flags = MWAIT2flg(0x10) | CPUIDLE_FLAG_TIME_VALID | CPUIDLE_FLAG_TLB_FLUSHED,
+		.exit_latency = 59,
+		.target_residency = 156,
+		.enter = &intel_idle },
+	{
+		.name = "C6-IVT",
+		.desc = "MWAIT 0x20",
+		.flags = MWAIT2flg(0x20) | CPUIDLE_FLAG_TIME_VALID | CPUIDLE_FLAG_TLB_FLUSHED,
+		.exit_latency = 82,
+		.target_residency = 300,
+		.enter = &intel_idle },
+	{
+		.enter = NULL }
+};
+
+static struct cpuidle_state ivt_cstates_4s[] = {
+	{
+		.name = "C1-IVT-4S",
+		.desc = "MWAIT 0x00",
+		.flags = MWAIT2flg(0x00) | CPUIDLE_FLAG_TIME_VALID,
+		.exit_latency = 1,
+		.target_residency = 1,
+		.enter = &intel_idle },
+	{
+		.name = "C1E-IVT-4S",
+		.desc = "MWAIT 0x01",
+		.flags = MWAIT2flg(0x01) | CPUIDLE_FLAG_TIME_VALID,
+		.exit_latency = 10,
+		.target_residency = 250,
+		.enter = &intel_idle },
+	{
+		.name = "C3-IVT-4S",
+		.desc = "MWAIT 0x10",
+		.flags = MWAIT2flg(0x10) | CPUIDLE_FLAG_TIME_VALID | CPUIDLE_FLAG_TLB_FLUSHED,
+		.exit_latency = 59,
+		.target_residency = 300,
+		.enter = &intel_idle },
+	{
+		.name = "C6-IVT-4S",
+		.desc = "MWAIT 0x20",
+		.flags = MWAIT2flg(0x20) | CPUIDLE_FLAG_TIME_VALID | CPUIDLE_FLAG_TLB_FLUSHED,
+		.exit_latency = 84,
+		.target_residency = 400,
+		.enter = &intel_idle },
+	{
+		.enter = NULL }
+};
+
+static struct cpuidle_state ivt_cstates_8s[] = {
+	{
+		.name = "C1-IVT-8S",
+		.desc = "MWAIT 0x00",
+		.flags = MWAIT2flg(0x00) | CPUIDLE_FLAG_TIME_VALID,
+		.exit_latency = 1,
+		.target_residency = 1,
+		.enter = &intel_idle },
+	{
+		.name = "C1E-IVT-8S",
+		.desc = "MWAIT 0x01",
+		.flags = MWAIT2flg(0x01) | CPUIDLE_FLAG_TIME_VALID,
+		.exit_latency = 10,
+		.target_residency = 500,
+		.enter = &intel_idle },
+	{
+		.name = "C3-IVT-8S",
+		.desc = "MWAIT 0x10",
+		.flags = MWAIT2flg(0x10) | CPUIDLE_FLAG_TIME_VALID | CPUIDLE_FLAG_TLB_FLUSHED,
+		.exit_latency = 59,
+		.target_residency = 600,
+		.enter = &intel_idle },
+	{
+		.name = "C6-IVT-8S",
+		.desc = "MWAIT 0x20",
+		.flags = MWAIT2flg(0x20) | CPUIDLE_FLAG_TIME_VALID | CPUIDLE_FLAG_TLB_FLUSHED,
+		.exit_latency = 88,
+		.target_residency = 700,
+		.enter = &intel_idle },
+	{
+		.enter = NULL }
+};
+
 static struct cpuidle_state hsw_cstates[] = {
 	{
 		.name = "C1-HSW",
@@ -464,11 +610,21 @@ static const struct idle_cpu idle_cpu_snb = {
 	.disable_promotion_to_c1e = true,
 };
 
+static const struct idle_cpu idle_cpu_byt = {
+	.state_table = byt_cstates,
+	.disable_promotion_to_c1e = true,
+};
+
 static const struct idle_cpu idle_cpu_ivb = {
 	.state_table = ivb_cstates,
 	.disable_promotion_to_c1e = true,
 };
 
+static const struct idle_cpu idle_cpu_ivt = {
+	.state_table = ivt_cstates,
+	.disable_promotion_to_c1e = true,
+};
+
 static const struct idle_cpu idle_cpu_hsw = {
 	.state_table = hsw_cstates,
 	.disable_promotion_to_c1e = true,
@@ -494,8 +650,10 @@ static const struct x86_cpu_id intel_idle_ids[] = {
 	ICPU(0x2f, idle_cpu_nehalem),
 	ICPU(0x2a, idle_cpu_snb),
 	ICPU(0x2d, idle_cpu_snb),
+	ICPU(0x36, idle_cpu_atom),
+	ICPU(0x37, idle_cpu_byt),
 	ICPU(0x3a, idle_cpu_ivb),
-	ICPU(0x3e, idle_cpu_ivb),
+	ICPU(0x3e, idle_cpu_ivt),
 	ICPU(0x3c, idle_cpu_hsw),
 	ICPU(0x3f, idle_cpu_hsw),
 	ICPU(0x45, idle_cpu_hsw),
@@ -572,6 +730,39 @@ static void intel_idle_cpuidle_devices_uninit(void)
 	free_percpu(intel_idle_cpuidle_devices);
 	return;
 }
+
+/*
+ * intel_idle_state_table_update()
+ *
+ * Update the default state_table for this CPU-id
+ *
+ * Currently used to access tuned IVT multi-socket targets
+ * Assumption: num_sockets == (max_package_num + 1)
+ */
+void intel_idle_state_table_update(void)
+{
+	/* IVT uses a different table for 1-2, 3-4, and > 4 sockets */
+	if (boot_cpu_data.x86_model == 0x3e) { /* IVT */
+		int cpu, package_num, num_sockets = 1;
+
+		for_each_online_cpu(cpu) {
+			package_num = topology_physical_package_id(cpu);
+			if (package_num + 1 > num_sockets) {
+				num_sockets = package_num + 1;
+
+				if (num_sockets > 4)
+					cpuidle_state_table = ivt_cstates_8s;
+					return;
+			}
+		}
+
+		if (num_sockets > 2)
+			cpuidle_state_table = ivt_cstates_4s;
+		/* else, 1 and 2 socket systems use default ivt_cstates */
+	}
+	return;
+}
+
 /*
  * intel_idle_cpuidle_driver_init()
  * allocate, initialize cpuidle_states
@@ -581,10 +772,12 @@ static int __init intel_idle_cpuidle_driver_init(void)
 	int cstate;
 	struct cpuidle_driver *drv = &intel_idle_driver;
 
+	intel_idle_state_table_update();
+
 	drv->state_count = 1;
 
 	for (cstate = 0; cstate < CPUIDLE_STATE_MAX; ++cstate) {
-		int num_substates, mwait_hint, mwait_cstate, mwait_substate;
+		int num_substates, mwait_hint, mwait_cstate;
 
 		if (cpuidle_state_table[cstate].enter == NULL)
 			break;
@@ -597,14 +790,13 @@ static int __init intel_idle_cpuidle_driver_init(void)
 
 		mwait_hint = flg2MWAIT(cpuidle_state_table[cstate].flags);
 		mwait_cstate = MWAIT_HINT2CSTATE(mwait_hint);
-		mwait_substate = MWAIT_HINT2SUBSTATE(mwait_hint);
 
-		/* does the state exist in CPUID.MWAIT? */
+		/* number of sub-states for this state in CPUID.MWAIT */
 		num_substates = (mwait_substates >> ((mwait_cstate + 1) * 4))
 					& MWAIT_SUBSTATE_MASK;
 
-		/* if sub-state in table is not enumerated by CPUID */
-		if ((mwait_substate + 1) > num_substates)
+		/* if NO sub-states for this state in CPUID, skip it */
+		if (num_substates == 0)
 			continue;
 
 		if (((mwait_cstate + 1) > 2) &&

include/linux/cpufreq.h

@@ -455,11 +455,14 @@ extern struct cpufreq_governor cpufreq_gov_conservative;
  *                     FREQUENCY TABLE HELPERS                       *
  *********************************************************************/
 
-#define CPUFREQ_ENTRY_INVALID ~0
-#define CPUFREQ_TABLE_END     ~1
-#define CPUFREQ_BOOST_FREQ    ~2
+/* Special Values of .frequency field */
+#define CPUFREQ_ENTRY_INVALID	~0
+#define CPUFREQ_TABLE_END	~1
+/* Special Values of .flags field */
+#define CPUFREQ_BOOST_FREQ	(1 << 0)
 
 struct cpufreq_frequency_table {
+	unsigned int	flags;
 	unsigned int	driver_data; /* driver specific data, not used by core */
 	unsigned int	frequency; /* kHz - doesn't need to be in ascending
 				    * order */

tools/power/x86/turbostat/turbostat.8

@@ -47,21 +47,22 @@ displays the statistics gathered since it was forked.
 .PP
 .SH FIELD DESCRIPTIONS
 .nf
-\fBpk\fP processor package number.
-\fBcor\fP processor core number.
+\fBPackage\fP processor package number.
+\fBCore\fP processor core number.
 \fBCPU\fP Linux CPU (logical processor) number.
 Note that multiple CPUs per core indicate support for Intel(R) Hyper-Threading Technology.
-\fB%c0\fP percent of the interval that the CPU retired instructions.
-\fBGHz\fP average clock rate while the CPU was in c0 state.
-\fBTSC\fP average GHz that the TSC ran during the entire interval.
-\fB%c1, %c3, %c6, %c7\fP show the percentage residency in hardware core idle states.
-\fBCTMP\fP Degrees Celsius reported by the per-core Digital Thermal Sensor.
-\fBPTMP\fP Degrees Celsius reported by the per-package Package Thermal Monitor.
-\fB%pc2, %pc3, %pc6, %pc7\fP percentage residency in hardware package idle states.
-\fBPkg_W\fP Watts consumed by the whole package.
-\fBCor_W\fP Watts consumed by the core part of the package.
-\fBGFX_W\fP Watts consumed by the Graphics part of the package -- available only on client processors.
-\fBRAM_W\fP Watts consumed by the DRAM DIMMS -- available only on server processors.
+\fBAVG_MHz\fP number of cycles executed divided by time elapsed.
+\fB%Buzy\fP percent of the interval that the CPU retired instructions, aka. % of time in "C0" state.
+\fBBzy_MHz\fP average clock rate while the CPU was busy (in "c0" state).
+\fBTSC_MHz\fP average MHz that the TSC ran during the entire interval.
+\fBCPU%c1, CPU%c3, CPU%c6, CPU%c7\fP show the percentage residency in hardware core idle states.
+\fBCoreTmp\fP Degrees Celsius reported by the per-core Digital Thermal Sensor.
+\fBPkgTtmp\fP Degrees Celsius reported by the per-package Package Thermal Monitor.
+\fBPkg%pc2, Pkg%pc3, Pkg%pc6, Pkg%pc7\fP percentage residency in hardware package idle states.
+\fBPkgWatt\fP Watts consumed by the whole package.
+\fBCorWatt\fP Watts consumed by the core part of the package.
+\fBGFXWatt\fP Watts consumed by the Graphics part of the package -- available only on client processors.
+\fBRAMWatt\fP Watts consumed by the DRAM DIMMS -- available only on server processors.
 \fBPKG_%\fP percent of the interval that RAPL throttling was active on the Package.
 \fBRAM_%\fP percent of the interval that RAPL throttling was active on DRAM.
 .fi
@@ -78,29 +79,17 @@ For Watts columns, the summary is a system total.
 Subsequent rows show per-CPU statistics.
 
 .nf
-[root@sandy]# ./turbostat
-cor CPU    %c0  GHz  TSC    %c1    %c3    %c6    %c7 CTMP PTMP   %pc2   %pc3   %pc6   %pc7  Pkg_W  Cor_W GFX_W
-          0.06 0.80 2.29   0.11   0.00   0.00  99.83   47   40   0.26   0.01   0.44  98.78   3.49   0.12  0.14
-  0   0   0.07 0.80 2.29   0.07   0.00   0.00  99.86   40   40   0.26   0.01   0.44  98.78   3.49   0.12  0.14
-  0   4   0.03 0.80 2.29   0.12
-  1   1   0.04 0.80 2.29   0.25   0.01   0.00  99.71   40
-  1   5   0.16 0.80 2.29   0.13
-  2   2   0.05 0.80 2.29   0.06   0.01   0.00  99.88   40
-  2   6   0.03 0.80 2.29   0.08
-  3   3   0.05 0.80 2.29   0.08   0.00   0.00  99.87   47
-  3   7   0.04 0.84 2.29   0.09
-.fi
-.SH SUMMARY EXAMPLE
-The "-s" option prints the column headers just once,
-and then the one line system summary for each sample interval.
-
-.nf
-[root@wsm]# turbostat -S
-   %c0  GHz  TSC    %c1    %c3    %c6 CTMP   %pc3   %pc6
-  1.40 2.81 3.38  10.78  43.47  44.35   42  13.67   2.09
-  1.34 2.90 3.38  11.48  58.96  28.23   41  19.89   0.15
-  1.55 2.72 3.38  26.73  37.66  34.07   42   2.53   2.80
-  1.37 2.83 3.38  16.95  60.05  21.63   42   5.76   0.20
+[root@ivy]# ./turbostat
+    Core     CPU Avg_MHz   %Busy Bzy_MHz TSC_MHz     SMI  CPU%c1  CPU%c3  CPU%c6  CPU%c7 CoreTmp  PkgTmp Pkg%pc2 Pkg%pc3 Pkg%pc6 Pkg%pc7 PkgWatt CorWatt GFXWatt 
+       -       -       6    0.36    1596    3492       0    0.59    0.01   99.04    0.00      23      24   23.82    0.01   72.47    0.00    6.40    1.01    0.00
+       0       0       9    0.58    1596    3492       0    0.28    0.01   99.13    0.00      23      24   23.82    0.01   72.47    0.00    6.40    1.01    0.00
+       0       4       1    0.07    1596    3492       0    0.79
+       1       1      10    0.65    1596    3492       0    0.59    0.00   98.76    0.00      23
+       1       5       5    0.28    1596    3492       0    0.95
+       2       2      10    0.66    1596    3492       0    0.41    0.01   98.92    0.00      23
+       2       6       2    0.10    1597    3492       0    0.97
+       3       3       3    0.20    1596    3492       0    0.44    0.00   99.37    0.00      23
+       3       7       5    0.31    1596    3492       0    0.33
 .fi
 .SH VERBOSE EXAMPLE
 The "-v" option adds verbosity to the output:
@@ -154,55 +143,35 @@ eg. Here a cycle soaker is run on 1 CPU (see %c0) for a few seconds
 until ^C while the other CPUs are mostly idle:
 
 .nf
-[root@x980 lenb]# ./turbostat cat /dev/zero > /dev/null
+root@ivy: turbostat cat /dev/zero > /dev/null
 ^C
-cor CPU    %c0  GHz  TSC    %c1    %c3    %c6   %pc3   %pc6
-          8.86 3.61 3.38  15.06  31.19  44.89   0.00   0.00
-  0   0   1.46 3.22 3.38  16.84  29.48  52.22   0.00   0.00
-  0   6   0.21 3.06 3.38  18.09
-  1   2   0.53 3.33 3.38   2.80  46.40  50.27
-  1   8   0.89 3.47 3.38   2.44
-  2   4   1.36 3.43 3.38   9.04  23.71  65.89
-  2  10   0.18 2.86 3.38  10.22
-  8   1   0.04 2.87 3.38  99.96   0.01   0.00
-  8   7  99.72 3.63 3.38   0.27
-  9   3   0.31 3.21 3.38   7.64  56.55  35.50
-  9   9   0.08 2.95 3.38   7.88
- 10   5   1.42 3.43 3.38   2.14  30.99  65.44
- 10  11   0.16 2.88 3.38   3.40
+    Core     CPU Avg_MHz   %Busy Bzy_MHz TSC_MHz     SMI  CPU%c1  CPU%c3  CPU%c6  CPU%c7 CoreTmp  PkgTmp Pkg%pc2 Pkg%pc3 Pkg%pc6 Pkg%pc7 PkgWatt CorWatt GFXWatt 
+       -       -     496   12.75    3886    3492       0   13.16    0.04   74.04    0.00      36      36    0.00    0.00    0.00    0.00   23.15   17.65    0.00
+       0       0      22    0.57    3830    3492       0    0.83    0.02   98.59    0.00      27      36    0.00    0.00    0.00    0.00   23.15   17.65    0.00
+       0       4       9    0.24    3829    3492       0    1.15
+       1       1       4    0.09    3783    3492       0   99.91    0.00    0.00    0.00      36
+       1       5    3880   99.82    3888    3492       0    0.18
+       2       2      17    0.44    3813    3492       0    0.77    0.04   98.75    0.00      28
+       2       6      12    0.32    3823    3492       0    0.89
+       3       3      16    0.43    3844    3492       0    0.63    0.11   98.84    0.00      30
+       3       7       4    0.11    3827    3492       0    0.94
+30.372243 sec
+
 .fi
-Above the cycle soaker drives cpu7 up its 3.6 GHz turbo limit
+Above the cycle soaker drives cpu5 up its 3.8 GHz turbo limit
 while the other processors are generally in various states of idle.
 
-Note that cpu1 and cpu7 are HT siblings within core8.
-As cpu7 is very busy, it prevents its sibling, cpu1,
+Note that cpu1 and cpu5 are HT siblings within core1.
+As cpu5 is very busy, it prevents its sibling, cpu1,
 from entering a c-state deeper than c1.
 
-Note that turbostat reports average GHz of 3.63, while
-the arithmetic average of the GHz column above is lower.
-This is a weighted average, where the weight is %c0.  ie. it is the total number of
-un-halted cycles elapsed per time divided by the number of CPUs.
-.SH SMI COUNTING EXAMPLE
-On Intel Nehalem and newer processors, MSR 0x34 is a System Management Mode Interrupt (SMI) counter.
-This counter is shown by default under the "SMI" column.
-.nf
-[root@x980 ~]# turbostat
-cor CPU    %c0  GHz  TSC SMI    %c1    %c3    %c6 CTMP   %pc3   %pc6
-          0.11 1.91 3.38   0   1.84   0.26  97.79   29   0.82  83.87
-  0   0   0.40 1.63 3.38   0  10.27   0.12  89.20   20   0.82  83.88
-  0   6   0.06 1.63 3.38   0  10.61
-  1   2   0.37 2.63 3.38   0   0.02   0.10  99.51   22
-  1   8   0.01 1.62 3.38   0   0.39
-  2   4   0.07 1.62 3.38   0   0.04   0.07  99.82   23
-  2  10   0.02 1.62 3.38   0   0.09
-  8   1   0.23 1.64 3.38   0   0.10   1.07  98.60   24
-  8   7   0.02 1.64 3.38   0   0.31
-  9   3   0.03 1.62 3.38   0   0.03   0.05  99.89   29
-  9   9   0.02 1.62 3.38   0   0.05
- 10   5   0.07 1.62 3.38   0   0.08   0.12  99.73   27
- 10  11   0.03 1.62 3.38   0   0.13
-^C
-.fi
+Note that the Avg_MHz column reflects the total number of cycles executed
+divided by the measurement interval.  If the %Busy column is 100%,
+then the processor was running at that speed the entire interval.
+The Avg_MHz multiplied by the %Busy results in the Bzy_MHz --
+which is the average frequency while the processor was executing --
+not including any non-busy idle time.
+
 .SH NOTES
 
 .B "turbostat "

tools/power/x86/turbostat/turbostat.c

@@ -56,7 +56,7 @@ unsigned int do_slm_cstates;
 unsigned int use_c1_residency_msr;
 unsigned int has_aperf;
 unsigned int has_epb;
-unsigned int units = 1000000000;	/* Ghz etc */
+unsigned int units = 1000000;	/* MHz etc */
 unsigned int genuine_intel;
 unsigned int has_invariant_tsc;
 unsigned int do_nehalem_platform_info;
@@ -264,88 +264,93 @@ int get_msr(int cpu, off_t offset, unsigned long long *msr)
 	return 0;
 }
 
+/*
+ * Example Format w/ field column widths:
+ *
+ * Package    Core     CPU Avg_MHz Bzy_MHz TSC_MHz     SMI   %Busy CPU_%c1 CPU_%c3 CPU_%c6 CPU_%c7 CoreTmp  PkgTmp Pkg%pc2 Pkg%pc3 Pkg%pc6 Pkg%pc7 PkgWatt CorWatt GFXWatt
+ * 1234567 1234567 1234567 1234567 1234567 1234567 1234567 1234567 1234567 1234567 1234567 1234567 1234567 1234567 1234567 1234567 1234567 1234567 1234567 1234567 1234567
+ */
+
 void print_header(void)
 {
 	if (show_pkg)
-		outp += sprintf(outp, "pk");
-	if (show_pkg)
-		outp += sprintf(outp, " ");
+		outp += sprintf(outp, "Package ");
 	if (show_core)
-		outp += sprintf(outp, "cor");
+		outp += sprintf(outp, "    Core ");
 	if (show_cpu)
-		outp += sprintf(outp, " CPU");
-	if (show_pkg || show_core || show_cpu)
-		outp += sprintf(outp, " ");
+		outp += sprintf(outp, "    CPU ");
+	if (has_aperf)
+		outp += sprintf(outp, "Avg_MHz ");
 	if (do_nhm_cstates)
-		outp += sprintf(outp, "   %%c0");
+		outp += sprintf(outp, "  %%Busy ");
 	if (has_aperf)
-		outp += sprintf(outp, "  GHz");
-	outp += sprintf(outp, "  TSC");
+		outp += sprintf(outp, "Bzy_MHz ");
+	outp += sprintf(outp, "TSC_MHz ");
 	if (do_smi)
-		outp += sprintf(outp, " SMI");
+		outp += sprintf(outp, "    SMI ");
 	if (extra_delta_offset32)
-		outp += sprintf(outp, "  count 0x%03X", extra_delta_offset32);
+		outp += sprintf(outp, " count 0x%03X ", extra_delta_offset32);
 	if (extra_delta_offset64)
-		outp += sprintf(outp, "  COUNT 0x%03X", extra_delta_offset64);
+		outp += sprintf(outp, " COUNT 0x%03X ", extra_delta_offset64);
 	if (extra_msr_offset32)
-		outp += sprintf(outp, "   MSR 0x%03X", extra_msr_offset32);
+		outp += sprintf(outp, "  MSR 0x%03X ", extra_msr_offset32);
 	if (extra_msr_offset64)
-		outp += sprintf(outp, "           MSR 0x%03X", extra_msr_offset64);
+		outp += sprintf(outp, "          MSR 0x%03X ", extra_msr_offset64);
 	if (do_nhm_cstates)
-		outp += sprintf(outp, "    %%c1");
+		outp += sprintf(outp, " CPU%%c1 ");
 	if (do_nhm_cstates && !do_slm_cstates)
-		outp += sprintf(outp, "    %%c3");
+		outp += sprintf(outp, " CPU%%c3 ");
 	if (do_nhm_cstates)
-		outp += sprintf(outp, "    %%c6");
+		outp += sprintf(outp, " CPU%%c6 ");
 	if (do_snb_cstates)
-		outp += sprintf(outp, "    %%c7");
+		outp += sprintf(outp, " CPU%%c7 ");
 
 	if (do_dts)
-		outp += sprintf(outp, " CTMP");
+		outp += sprintf(outp, "CoreTmp ");
 	if (do_ptm)
-		outp += sprintf(outp, " PTMP");
+		outp += sprintf(outp, " PkgTmp ");
 
 	if (do_snb_cstates)
-		outp += sprintf(outp, "   %%pc2");
+		outp += sprintf(outp, "Pkg%%pc2 ");
 	if (do_nhm_cstates && !do_slm_cstates)
-		outp += sprintf(outp, "   %%pc3");
+		outp += sprintf(outp, "Pkg%%pc3 ");
 	if (do_nhm_cstates && !do_slm_cstates)
-		outp += sprintf(outp, "   %%pc6");
+		outp += sprintf(outp, "Pkg%%pc6 ");
 	if (do_snb_cstates)
-		outp += sprintf(outp, "   %%pc7");
+		outp += sprintf(outp, "Pkg%%pc7 ");
 	if (do_c8_c9_c10) {
-		outp += sprintf(outp, "   %%pc8");
-		outp += sprintf(outp, "   %%pc9");
-		outp += sprintf(outp, "  %%pc10");
+		outp += sprintf(outp, "Pkg%%pc8 ");
+		outp += sprintf(outp, "Pkg%%pc9 ");
+		outp += sprintf(outp, "Pk%%pc10 ");
 	}
 
 	if (do_rapl && !rapl_joules) {
 		if (do_rapl & RAPL_PKG)
-			outp += sprintf(outp, "  Pkg_W");
+			outp += sprintf(outp, "PkgWatt ");
 		if (do_rapl & RAPL_CORES)
-			outp += sprintf(outp, "  Cor_W");
+			outp += sprintf(outp, "CorWatt ");
 		if (do_rapl & RAPL_GFX)
-			outp += sprintf(outp, " GFX_W");
+			outp += sprintf(outp, "GFXWatt ");
 		if (do_rapl & RAPL_DRAM)
-			outp += sprintf(outp, " RAM_W");
+			outp += sprintf(outp, "RAMWatt ");
 		if (do_rapl & RAPL_PKG_PERF_STATUS)
-			outp += sprintf(outp, " PKG_%%");
+			outp += sprintf(outp, "  PKG_%% ");
 		if (do_rapl & RAPL_DRAM_PERF_STATUS)
-			outp += sprintf(outp, " RAM_%%");
+			outp += sprintf(outp, "  RAM_%% ");
 	} else {
 		if (do_rapl & RAPL_PKG)
-			outp += sprintf(outp, "  Pkg_J");
+			outp += sprintf(outp, "  Pkg_J ");
 		if (do_rapl & RAPL_CORES)
-			outp += sprintf(outp, "  Cor_J");
+			outp += sprintf(outp, "  Cor_J ");
 		if (do_rapl & RAPL_GFX)
-			outp += sprintf(outp, " GFX_J");
+			outp += sprintf(outp, "  GFX_J ");
 		if (do_rapl & RAPL_DRAM)
-			outp += sprintf(outp, " RAM_W");
+			outp += sprintf(outp, "  RAM_W ");
 		if (do_rapl & RAPL_PKG_PERF_STATUS)
-			outp += sprintf(outp, " PKG_%%");
+			outp += sprintf(outp, "  PKG_%% ");
 		if (do_rapl & RAPL_DRAM_PERF_STATUS)
-			outp += sprintf(outp, " RAM_%%");
-		outp += sprintf(outp, " time");
+			outp += sprintf(outp, "  RAM_%% ");
+		outp += sprintf(outp, "  time ");
 
 	}
 	outp += sprintf(outp, "\n");
@@ -410,25 +415,12 @@ int dump_counters(struct thread_data *t, struct core_data *c,
 
 /*
  * column formatting convention & formats
- * package: "pk" 2 columns %2d
- * core: "cor" 3 columns %3d
- * CPU: "CPU" 3 columns %3d
- * Pkg_W: %6.2
- * Cor_W: %6.2
- * GFX_W: %5.2
- * RAM_W: %5.2
- * GHz: "GHz" 3 columns %3.2
- * TSC: "TSC" 3 columns %3.2
- * SMI: "SMI" 4 columns %4d
- * percentage " %pc3" %6.2
- * Perf Status percentage: %5.2
- * "CTMP" 4 columns %4d
  */
 int format_counters(struct thread_data *t, struct core_data *c,
 	struct pkg_data *p)
 {
 	double interval_float;
-	char *fmt5, *fmt6;
+	char *fmt8;
 
 	 /* if showing only 1st thread in core and this isn't one, bail out */
 	if (show_core_only && !(t->flags & CPU_IS_FIRST_THREAD_IN_CORE))
@@ -443,65 +435,52 @@ int format_counters(struct thread_data *t, struct core_data *c,
 	/* topo columns, print blanks on 1st (average) line */
 	if (t == &average.threads) {
 		if (show_pkg)
-			outp += sprintf(outp, "  ");
-		if (show_pkg && show_core)
-			outp += sprintf(outp, " ");
+			outp += sprintf(outp, "       -");
 		if (show_core)
-			outp += sprintf(outp, "   ");
+			outp += sprintf(outp, "       -");
 		if (show_cpu)
-			outp += sprintf(outp, " " "   ");
+			outp += sprintf(outp, "       -");
 	} else {
 		if (show_pkg) {
 			if (p)
-				outp += sprintf(outp, "%2d", p->package_id);
+				outp += sprintf(outp, "%8d", p->package_id);
 			else
-				outp += sprintf(outp, "  ");
+				outp += sprintf(outp, "       -");
 		}
-		if (show_pkg && show_core)
-			outp += sprintf(outp, " ");
 		if (show_core) {
 			if (c)
-				outp += sprintf(outp, "%3d", c->core_id);
+				outp += sprintf(outp, "%8d", c->core_id);
 			else
-				outp += sprintf(outp, "   ");
+				outp += sprintf(outp, "       -");
 		}
 		if (show_cpu)
-			outp += sprintf(outp, " %3d", t->cpu_id);
+			outp += sprintf(outp, "%8d", t->cpu_id);
 	}
+
+	/* AvgMHz */
+	if (has_aperf)
+		outp += sprintf(outp, "%8.0f",
+			1.0 / units * t->aperf / interval_float);
+
 	/* %c0 */
 	if (do_nhm_cstates) {
-		if (show_pkg || show_core || show_cpu)
-			outp += sprintf(outp, " ");
 		if (!skip_c0)
-			outp += sprintf(outp, "%6.2f", 100.0 * t->mperf/t->tsc);
+			outp += sprintf(outp, "%8.2f", 100.0 * t->mperf/t->tsc);
 		else
-			outp += sprintf(outp, "  ****");
+			outp += sprintf(outp, "********");
 	}
 
-	/* GHz */
-	if (has_aperf) {
-		if (!aperf_mperf_unstable) {
-			outp += sprintf(outp, " %3.2f",
-				1.0 * t->tsc / units * t->aperf /
-				t->mperf / interval_float);
-		} else {
-			if (t->aperf > t->tsc || t->mperf > t->tsc) {
-				outp += sprintf(outp, " ***");
-			} else {
-				outp += sprintf(outp, "%3.1f*",
-					1.0 * t->tsc /
-					units * t->aperf /
-					t->mperf / interval_float);
-			}
-		}
-	}
+	/* BzyMHz */
+	if (has_aperf)
+		outp += sprintf(outp, "%8.0f",
+			1.0 * t->tsc / units * t->aperf / t->mperf / interval_float);
 
 	/* TSC */
-	outp += sprintf(outp, "%5.2f", 1.0 * t->tsc/units/interval_float);
+	outp += sprintf(outp, "%8.0f", 1.0 * t->tsc/units/interval_float);
 
 	/* SMI */
 	if (do_smi)
-		outp += sprintf(outp, "%4d", t->smi_count);
+		outp += sprintf(outp, "%8d", t->smi_count);
 
 	/* delta */
 	if (extra_delta_offset32)
@@ -520,9 +499,9 @@ int format_counters(struct thread_data *t, struct core_data *c,
 
 	if (do_nhm_cstates) {
 		if (!skip_c1)
-			outp += sprintf(outp, " %6.2f", 100.0 * t->c1/t->tsc);
+			outp += sprintf(outp, "%8.2f", 100.0 * t->c1/t->tsc);
 		else
-			outp += sprintf(outp, "  ****");
+			outp += sprintf(outp, "********");
 	}
 
 	/* print per-core data only for 1st thread in core */
@@ -530,79 +509,76 @@ int format_counters(struct thread_data *t, struct core_data *c,
 		goto done;
 
 	if (do_nhm_cstates && !do_slm_cstates)
-		outp += sprintf(outp, " %6.2f", 100.0 * c->c3/t->tsc);
+		outp += sprintf(outp, "%8.2f", 100.0 * c->c3/t->tsc);
 	if (do_nhm_cstates)
-		outp += sprintf(outp, " %6.2f", 100.0 * c->c6/t->tsc);
+		outp += sprintf(outp, "%8.2f", 100.0 * c->c6/t->tsc);
 	if (do_snb_cstates)
-		outp += sprintf(outp, " %6.2f", 100.0 * c->c7/t->tsc);
+		outp += sprintf(outp, "%8.2f", 100.0 * c->c7/t->tsc);
 
 	if (do_dts)
-		outp += sprintf(outp, " %4d", c->core_temp_c);
+		outp += sprintf(outp, "%8d", c->core_temp_c);
 
 	/* print per-package data only for 1st core in package */
 	if (!(t->flags & CPU_IS_FIRST_CORE_IN_PACKAGE))
 		goto done;
 
 	if (do_ptm)
-		outp += sprintf(outp, " %4d", p->pkg_temp_c);
+		outp += sprintf(outp, "%8d", p->pkg_temp_c);
 
 	if (do_snb_cstates)
-		outp += sprintf(outp, " %6.2f", 100.0 * p->pc2/t->tsc);
+		outp += sprintf(outp, "%8.2f", 100.0 * p->pc2/t->tsc);
 	if (do_nhm_cstates && !do_slm_cstates)
-		outp += sprintf(outp, " %6.2f", 100.0 * p->pc3/t->tsc);
+		outp += sprintf(outp, "%8.2f", 100.0 * p->pc3/t->tsc);
 	if (do_nhm_cstates && !do_slm_cstates)
-		outp += sprintf(outp, " %6.2f", 100.0 * p->pc6/t->tsc);
+		outp += sprintf(outp, "%8.2f", 100.0 * p->pc6/t->tsc);
 	if (do_snb_cstates)
-		outp += sprintf(outp, " %6.2f", 100.0 * p->pc7/t->tsc);
+		outp += sprintf(outp, "%8.2f", 100.0 * p->pc7/t->tsc);
 	if (do_c8_c9_c10) {
-		outp += sprintf(outp, " %6.2f", 100.0 * p->pc8/t->tsc);
-		outp += sprintf(outp, " %6.2f", 100.0 * p->pc9/t->tsc);
-		outp += sprintf(outp, " %6.2f", 100.0 * p->pc10/t->tsc);
+		outp += sprintf(outp, "%8.2f", 100.0 * p->pc8/t->tsc);
+		outp += sprintf(outp, "%8.2f", 100.0 * p->pc9/t->tsc);
+		outp += sprintf(outp, "%8.2f", 100.0 * p->pc10/t->tsc);
 	}
 
 	/*
  	 * If measurement interval exceeds minimum RAPL Joule Counter range,
  	 * indicate that results are suspect by printing "**" in fraction place.
  	 */
-	if (interval_float < rapl_joule_counter_range) {
-		fmt5 = " %5.2f";
-		fmt6 = " %6.2f";
-	} else {
-		fmt5 = " %3.0f**";
-		fmt6 = " %4.0f**";
-	}
+	if (interval_float < rapl_joule_counter_range)
+		fmt8 = "%8.2f";
+	else
+		fmt8 = " %6.0f**";
 
 	if (do_rapl && !rapl_joules) {
 		if (do_rapl & RAPL_PKG)
-			outp += sprintf(outp, fmt6, p->energy_pkg * rapl_energy_units / interval_float);
+			outp += sprintf(outp, fmt8, p->energy_pkg * rapl_energy_units / interval_float);
 		if (do_rapl & RAPL_CORES)
-			outp += sprintf(outp, fmt6, p->energy_cores * rapl_energy_units / interval_float);
+			outp += sprintf(outp, fmt8, p->energy_cores * rapl_energy_units / interval_float);
 		if (do_rapl & RAPL_GFX)
-			outp += sprintf(outp, fmt5, p->energy_gfx * rapl_energy_units / interval_float);
+			outp += sprintf(outp, fmt8, p->energy_gfx * rapl_energy_units / interval_float);
 		if (do_rapl & RAPL_DRAM)
-			outp += sprintf(outp, fmt5, p->energy_dram * rapl_energy_units / interval_float);
+			outp += sprintf(outp, fmt8, p->energy_dram * rapl_energy_units / interval_float);
 		if (do_rapl & RAPL_PKG_PERF_STATUS)
-			outp += sprintf(outp, fmt5, 100.0 * p->rapl_pkg_perf_status * rapl_time_units / interval_float);
+			outp += sprintf(outp, fmt8, 100.0 * p->rapl_pkg_perf_status * rapl_time_units / interval_float);
 		if (do_rapl & RAPL_DRAM_PERF_STATUS)
-			outp += sprintf(outp, fmt5, 100.0 * p->rapl_dram_perf_status * rapl_time_units / interval_float);
+			outp += sprintf(outp, fmt8, 100.0 * p->rapl_dram_perf_status * rapl_time_units / interval_float);
 	} else {
 		if (do_rapl & RAPL_PKG)
-			outp += sprintf(outp, fmt6,
+			outp += sprintf(outp, fmt8,
 					p->energy_pkg * rapl_energy_units);
 		if (do_rapl & RAPL_CORES)
-			outp += sprintf(outp, fmt6,
+			outp += sprintf(outp, fmt8,
 					p->energy_cores * rapl_energy_units);
 		if (do_rapl & RAPL_GFX)
-			outp += sprintf(outp, fmt5,
+			outp += sprintf(outp, fmt8,
 					p->energy_gfx * rapl_energy_units);
 		if (do_rapl & RAPL_DRAM)
-			outp += sprintf(outp, fmt5,
+			outp += sprintf(outp, fmt8,
 					p->energy_dram * rapl_energy_units);
 		if (do_rapl & RAPL_PKG_PERF_STATUS)
-			outp += sprintf(outp, fmt5, 100.0 * p->rapl_pkg_perf_status * rapl_time_units / interval_float);
+			outp += sprintf(outp, fmt8, 100.0 * p->rapl_pkg_perf_status * rapl_time_units / interval_float);
 		if (do_rapl & RAPL_DRAM_PERF_STATUS)
-			outp += sprintf(outp, fmt5, 100.0 * p->rapl_dram_perf_status * rapl_time_units / interval_float);
-	outp += sprintf(outp, fmt5, interval_float);
+			outp += sprintf(outp, fmt8, 100.0 * p->rapl_dram_perf_status * rapl_time_units / interval_float);
+	outp += sprintf(outp, fmt8, interval_float);
 
 	}
 done:
@@ -1516,6 +1492,9 @@ int has_nehalem_turbo_ratio_limit(unsigned int family, unsigned int model)
 	case 0x46:	/* HSW */
 	case 0x37:	/* BYT */
 	case 0x4D:	/* AVN */
+	case 0x3D:	/* BDW */
+	case 0x4F:	/* BDX */
+	case 0x56:	/* BDX-DE */
 		return 1;
 	case 0x2E:	/* Nehalem-EX Xeon - Beckton */
 	case 0x2F:	/* Westmere-EX Xeon - Eagleton */
@@ -1629,9 +1608,12 @@ void rapl_probe(unsigned int family, unsigned int model)
 	case 0x3C:	/* HSW */
 	case 0x45:	/* HSW */
 	case 0x46:	/* HSW */
+	case 0x3D:	/* BDW */
 		do_rapl = RAPL_PKG | RAPL_CORES | RAPL_CORE_POLICY | RAPL_GFX | RAPL_PKG_POWER_INFO;
 		break;
 	case 0x3F:	/* HSX */
+	case 0x4F:	/* BDX */
+	case 0x56:	/* BDX-DE */
 		do_rapl = RAPL_PKG | RAPL_DRAM | RAPL_DRAM_PERF_STATUS | RAPL_PKG_PERF_STATUS | RAPL_PKG_POWER_INFO;
 		break;
 	case 0x2D:
@@ -1875,6 +1857,9 @@ int is_snb(unsigned int family, unsigned int model)
 	case 0x3F:	/* HSW */
 	case 0x45:	/* HSW */
 	case 0x46:	/* HSW */
+	case 0x3D:	/* BDW */
+	case 0x4F:	/* BDX */
+	case 0x56:	/* BDX-DE */
 		return 1;
 	}
 	return 0;
@@ -1886,7 +1871,8 @@ int has_c8_c9_c10(unsigned int family, unsigned int model)
 		return 0;
 
 	switch (model) {
-	case 0x45:
+	case 0x45:	/* HSW */
+	case 0x3D:	/* BDW */
 		return 1;
 	}
 	return 0;
@@ -2455,7 +2441,7 @@ int main(int argc, char **argv)
 	cmdline(argc, argv);
 
 	if (verbose)
-		fprintf(stderr, "turbostat v3.6 Dec 2, 2013"
+		fprintf(stderr, "turbostat v3.7 Feb 6, 2014"
 			" - Len Brown <lenb@kernel.org>\n");
 
 	turbostat_init();

virt/kvm/arm/arch_timer.c

@@ -277,7 +277,7 @@ int kvm_timer_hyp_init(void)
 
 	host_vtimer_irq = ppi;
 
-	err = register_cpu_notifier(&kvm_timer_cpu_nb);
+	err = __register_cpu_notifier(&kvm_timer_cpu_nb);
 	if (err) {
 		kvm_err("Cannot register timer CPU notifier\n");
 		goto out_free;

virt/kvm/arm/vgic.c

@@ -1496,7 +1496,7 @@ int kvm_vgic_hyp_init(void)
 		goto out;
 	}
 
-	ret = register_cpu_notifier(&vgic_cpu_nb);
+	ret = __register_cpu_notifier(&vgic_cpu_nb);
 	if (ret) {
 		kvm_err("Cannot register vgic CPU notifier\n");
 		goto out_free_irq;