[PATCH 0/7] cpuidle/powernv: Enable Fast-Sleep on PowerNV

[PATCH 0/7] cpuidle/powernv: Enable Fast-Sleep on PowerNV

[Preeti U Murthy]

This series is based on tip/timers/core ontop of commit
849401b66d305:tick: Fixup more fallout from hrtimer broadcast mode.

Fast sleep is one of the deep idle states on Power8 in which local timers of
CPUs stop. On PowerPC we do not have an external clock device which can
handle wakeup of such CPUs. Now that we have the support in the tick
broadcast framework for archs that do not sport such a device soon to go
upstream, add fast sleep as one of the idle states on PowerNV along with
related arch specific support.

The earlier versions of this patchset included support in the tick broadcast
framework for such idle states. Now that the support in the broadcast
framework has been pulled into tip separately, this series is posted
independently and as a new patchset altogether. This series depends in
particular on the following commits in tip/timers/core:

1.da7e6f45c3:time: Change the return type of clockevents_notify() to integer
2.ba8f20c2eb:cpuidle: Handle clockevents_notify(BROADCAST_ENTER) failure
3.5d1638acb9f62fa:tick: Introduce hrtimer based broadcast
4.f1689bb7abec8e2e6:time: Fixup fallout from recent clockevent/tick changes
5.849401b66d305f3feb75:Fixup more fallout from hrtimer broadcast mode

---

Preeti U Murthy (3):
      cpuidle/ppc: Split timer_interrupt() into timer handling and interrupt handling routines
      cpuidle/powernv: Add "Fast-Sleep" CPU idle state
      cpuidle/powernv: Parse device tree to setup idle states

Srivatsa S. Bhat (2):
      powerpc: Free up the slot of PPC_MSG_CALL_FUNC_SINGLE IPI message
      powerpc: Implement tick broadcast IPI as a fixed IPI message

Vaidyanathan Srinivasan (2):
      powernv/cpuidle: Add context management for Fast Sleep
      powermgt: Add OPAL call to resync timebase on wakeup


 arch/powerpc/Kconfig                           |    2 
 arch/powerpc/include/asm/opal.h                |    2 
 arch/powerpc/include/asm/processor.h           |    1 
 arch/powerpc/include/asm/smp.h                 |    2 
 arch/powerpc/include/asm/time.h                |    1 
 arch/powerpc/kernel/exceptions-64s.S           |   10 ++
 arch/powerpc/kernel/idle_power7.S              |   90 +++++++++++++++++----
 arch/powerpc/kernel/smp.c                      |   25 ++++--
 arch/powerpc/kernel/time.c                     |   90 +++++++++++++--------
 arch/powerpc/platforms/cell/interrupt.c        |    2 
 arch/powerpc/platforms/powernv/opal-wrappers.S |    1 
 arch/powerpc/platforms/ps3/smp.c               |    2 
 drivers/cpuidle/cpuidle-powernv.c              |  102 ++++++++++++++++++++++--
 13 files changed, 253 insertions(+), 77 deletions(-)

-- 
Signature

[PATCH 1/7] powerpc: Free up the slot of PPC_MSG_CALL_FUNC_SINGLE IPI message

[Preeti U Murthy]

From: Srivatsa S. Bhat <srivatsa.bhat@linux.vnet.ibm.com>

The IPI handlers for both PPC_MSG_CALL_FUNC and PPC_MSG_CALL_FUNC_SINGLE map
to a common implementation - generic_smp_call_function_single_interrupt(). So,
we can consolidate them and save one of the IPI message slots, (which are
precious on powerpc, since only 4 of those slots are available).

So, implement the functionality of PPC_MSG_CALL_FUNC_SINGLE using
PPC_MSG_CALL_FUNC itself and release its IPI message slot, so that it can be
used for something else in the future, if desired.

Signed-off-by: Srivatsa S. Bhat <srivatsa.bhat@linux.vnet.ibm.com>
Signed-off-by: Preeti U. Murthy <preeti@linux.vnet.ibm.com>
Acked-by: Geoff Levand <geoff@infradead.org> [For the PS3 part]
---

 arch/powerpc/include/asm/smp.h          |    2 +-
 arch/powerpc/kernel/smp.c               |   12 +++++-------
 arch/powerpc/platforms/cell/interrupt.c |    2 +-
 arch/powerpc/platforms/ps3/smp.c        |    2 +-
 4 files changed, 8 insertions(+), 10 deletions(-)

diff --git a/arch/powerpc/include/asm/smp.h b/arch/powerpc/include/asm/smp.h
index 084e080..9f7356b 100644
--- a/arch/powerpc/include/asm/smp.h
+++ b/arch/powerpc/include/asm/smp.h
@@ -120,7 +120,7 @@ extern int cpu_to_core_id(int cpu);
  * in /proc/interrupts will be wrong!!! --Troy */
 #define PPC_MSG_CALL_FUNCTION   0
 #define PPC_MSG_RESCHEDULE      1
-#define PPC_MSG_CALL_FUNC_SINGLE	2
+#define PPC_MSG_UNUSED		2
 #define PPC_MSG_DEBUGGER_BREAK  3
 
 /* for irq controllers that have dedicated ipis per message (4) */
diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c
index ac2621a..ee7d76b 100644
--- a/arch/powerpc/kernel/smp.c
+++ b/arch/powerpc/kernel/smp.c
@@ -145,9 +145,9 @@ static irqreturn_t reschedule_action(int irq, void *data)
 	return IRQ_HANDLED;
 }
 
-static irqreturn_t call_function_single_action(int irq, void *data)
+static irqreturn_t unused_action(int irq, void *data)
 {
-	generic_smp_call_function_single_interrupt();
+	/* This slot is unused and hence available for use, if needed */
 	return IRQ_HANDLED;
 }
 
@@ -168,14 +168,14 @@ static irqreturn_t debug_ipi_action(int irq, void *data)
 static irq_handler_t smp_ipi_action[] = {
 	[PPC_MSG_CALL_FUNCTION] =  call_function_action,
 	[PPC_MSG_RESCHEDULE] = reschedule_action,
-	[PPC_MSG_CALL_FUNC_SINGLE] = call_function_single_action,
+	[PPC_MSG_UNUSED] = unused_action,
 	[PPC_MSG_DEBUGGER_BREAK] = debug_ipi_action,
 };
 
 const char *smp_ipi_name[] = {
 	[PPC_MSG_CALL_FUNCTION] =  "ipi call function",
 	[PPC_MSG_RESCHEDULE] = "ipi reschedule",
-	[PPC_MSG_CALL_FUNC_SINGLE] = "ipi call function single",
+	[PPC_MSG_UNUSED] = "ipi unused",
 	[PPC_MSG_DEBUGGER_BREAK] = "ipi debugger",
 };
 
@@ -251,8 +251,6 @@ irqreturn_t smp_ipi_demux(void)
 			generic_smp_call_function_interrupt();
 		if (all & IPI_MESSAGE(PPC_MSG_RESCHEDULE))
 			scheduler_ipi();
-		if (all & IPI_MESSAGE(PPC_MSG_CALL_FUNC_SINGLE))
-			generic_smp_call_function_single_interrupt();
 		if (all & IPI_MESSAGE(PPC_MSG_DEBUGGER_BREAK))
 			debug_ipi_action(0, NULL);
 	} while (info->messages);
@@ -280,7 +278,7 @@ EXPORT_SYMBOL_GPL(smp_send_reschedule);
 
 void arch_send_call_function_single_ipi(int cpu)
 {
-	do_message_pass(cpu, PPC_MSG_CALL_FUNC_SINGLE);
+	do_message_pass(cpu, PPC_MSG_CALL_FUNCTION);
 }
 
 void arch_send_call_function_ipi_mask(const struct cpumask *mask)
diff --git a/arch/powerpc/platforms/cell/interrupt.c b/arch/powerpc/platforms/cell/interrupt.c
index 2d42f3b..adf3726 100644
--- a/arch/powerpc/platforms/cell/interrupt.c
+++ b/arch/powerpc/platforms/cell/interrupt.c
@@ -215,7 +215,7 @@ void iic_request_IPIs(void)
 {
 	iic_request_ipi(PPC_MSG_CALL_FUNCTION);
 	iic_request_ipi(PPC_MSG_RESCHEDULE);
-	iic_request_ipi(PPC_MSG_CALL_FUNC_SINGLE);
+	iic_request_ipi(PPC_MSG_UNUSED);
 	iic_request_ipi(PPC_MSG_DEBUGGER_BREAK);
 }
 
diff --git a/arch/powerpc/platforms/ps3/smp.c b/arch/powerpc/platforms/ps3/smp.c
index 4b35166..00d1a7c 100644
--- a/arch/powerpc/platforms/ps3/smp.c
+++ b/arch/powerpc/platforms/ps3/smp.c
@@ -76,7 +76,7 @@ static int __init ps3_smp_probe(void)
 
 		BUILD_BUG_ON(PPC_MSG_CALL_FUNCTION    != 0);
 		BUILD_BUG_ON(PPC_MSG_RESCHEDULE       != 1);
-		BUILD_BUG_ON(PPC_MSG_CALL_FUNC_SINGLE != 2);
+		BUILD_BUG_ON(PPC_MSG_UNUSED	      != 2);
 		BUILD_BUG_ON(PPC_MSG_DEBUGGER_BREAK   != 3);
 
 		for (i = 0; i < MSG_COUNT; i++) {

[PATCH 2/7] powerpc: Implement tick broadcast IPI as a fixed IPI message

[Preeti U Murthy]

From: Srivatsa S. Bhat <srivatsa.bhat@linux.vnet.ibm.com>

For scalability and performance reasons, we want the tick broadcast IPIs
to be handled as efficiently as possible. Fixed IPI messages
are one of the most efficient mechanisms available - they are faster than
the smp_call_function mechanism because the IPI handlers are fixed and hence
they don't involve costly operations such as adding IPI handlers to the target
CPU's function queue, acquiring locks for synchronization etc.

Luckily we have an unused IPI message slot, so use that to implement
tick broadcast IPIs efficiently.

Signed-off-by: Srivatsa S. Bhat <srivatsa.bhat@linux.vnet.ibm.com>
[Functions renamed to tick_broadcast* and Changelog modified by
 Preeti U. Murthy<preeti@linux.vnet.ibm.com>]
Signed-off-by: Preeti U. Murthy <preeti@linux.vnet.ibm.com>
Acked-by: Geoff Levand <geoff@infradead.org> [For the PS3 part]
---

 arch/powerpc/include/asm/smp.h          |    2 +-
 arch/powerpc/include/asm/time.h         |    1 +
 arch/powerpc/kernel/smp.c               |   21 +++++++++++++++++----
 arch/powerpc/kernel/time.c              |    5 +++++
 arch/powerpc/platforms/cell/interrupt.c |    2 +-
 arch/powerpc/platforms/ps3/smp.c        |    2 +-
 6 files changed, 26 insertions(+), 7 deletions(-)

diff --git a/arch/powerpc/include/asm/smp.h b/arch/powerpc/include/asm/smp.h
index 9f7356b..ff51046 100644
--- a/arch/powerpc/include/asm/smp.h
+++ b/arch/powerpc/include/asm/smp.h
@@ -120,7 +120,7 @@ extern int cpu_to_core_id(int cpu);
  * in /proc/interrupts will be wrong!!! --Troy */
 #define PPC_MSG_CALL_FUNCTION   0
 #define PPC_MSG_RESCHEDULE      1
-#define PPC_MSG_UNUSED		2
+#define PPC_MSG_TICK_BROADCAST	2
 #define PPC_MSG_DEBUGGER_BREAK  3
 
 /* for irq controllers that have dedicated ipis per message (4) */
diff --git a/arch/powerpc/include/asm/time.h b/arch/powerpc/include/asm/time.h
index c1f2676..1d428e6 100644
--- a/arch/powerpc/include/asm/time.h
+++ b/arch/powerpc/include/asm/time.h
@@ -28,6 +28,7 @@ extern struct clock_event_device decrementer_clockevent;
 struct rtc_time;
 extern void to_tm(int tim, struct rtc_time * tm);
 extern void GregorianDay(struct rtc_time *tm);
+extern void tick_broadcast_ipi_handler(void);
 
 extern void generic_calibrate_decr(void);
 
diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c
index ee7d76b..e2a4232 100644
--- a/arch/powerpc/kernel/smp.c
+++ b/arch/powerpc/kernel/smp.c
@@ -35,6 +35,7 @@
 #include <asm/ptrace.h>
 #include <linux/atomic.h>
 #include <asm/irq.h>
+#include <asm/hw_irq.h>
 #include <asm/page.h>
 #include <asm/pgtable.h>
 #include <asm/prom.h>
@@ -145,9 +146,9 @@ static irqreturn_t reschedule_action(int irq, void *data)
 	return IRQ_HANDLED;
 }
 
-static irqreturn_t unused_action(int irq, void *data)
+static irqreturn_t tick_broadcast_ipi_action(int irq, void *data)
 {
-	/* This slot is unused and hence available for use, if needed */
+	tick_broadcast_ipi_handler();
 	return IRQ_HANDLED;
 }
 
@@ -168,14 +169,14 @@ static irqreturn_t debug_ipi_action(int irq, void *data)
 static irq_handler_t smp_ipi_action[] = {
 	[PPC_MSG_CALL_FUNCTION] =  call_function_action,
 	[PPC_MSG_RESCHEDULE] = reschedule_action,
-	[PPC_MSG_UNUSED] = unused_action,
+	[PPC_MSG_TICK_BROADCAST] = tick_broadcast_ipi_action,
 	[PPC_MSG_DEBUGGER_BREAK] = debug_ipi_action,
 };
 
 const char *smp_ipi_name[] = {
 	[PPC_MSG_CALL_FUNCTION] =  "ipi call function",
 	[PPC_MSG_RESCHEDULE] = "ipi reschedule",
-	[PPC_MSG_UNUSED] = "ipi unused",
+	[PPC_MSG_TICK_BROADCAST] = "ipi tick-broadcast",
 	[PPC_MSG_DEBUGGER_BREAK] = "ipi debugger",
 };
 
@@ -251,6 +252,8 @@ irqreturn_t smp_ipi_demux(void)
 			generic_smp_call_function_interrupt();
 		if (all & IPI_MESSAGE(PPC_MSG_RESCHEDULE))
 			scheduler_ipi();
+		if (all & IPI_MESSAGE(PPC_MSG_TICK_BROADCAST))
+			tick_broadcast_ipi_handler();
 		if (all & IPI_MESSAGE(PPC_MSG_DEBUGGER_BREAK))
 			debug_ipi_action(0, NULL);
 	} while (info->messages);
@@ -289,6 +292,16 @@ void arch_send_call_function_ipi_mask(const struct cpumask *mask)
 		do_message_pass(cpu, PPC_MSG_CALL_FUNCTION);
 }
 
+#ifdef CONFIG_GENERIC_CLOCKEVENTS_BROADCAST
+void tick_broadcast(const struct cpumask *mask)
+{
+	unsigned int cpu;
+
+	for_each_cpu(cpu, mask)
+		do_message_pass(cpu, PPC_MSG_TICK_BROADCAST);
+}
+#endif
+
 #if defined(CONFIG_DEBUGGER) || defined(CONFIG_KEXEC)
 void smp_send_debugger_break(void)
 {
diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c
index b3dab20..3ff97db 100644
--- a/arch/powerpc/kernel/time.c
+++ b/arch/powerpc/kernel/time.c
@@ -825,6 +825,11 @@ static void decrementer_set_mode(enum clock_event_mode mode,
 		decrementer_set_next_event(DECREMENTER_MAX, dev);
 }
 
+/* Interrupt handler for the timer broadcast IPI */
+void tick_broadcast_ipi_handler(void)
+{
+}
+
 static void register_decrementer_clockevent(int cpu)
 {
 	struct clock_event_device *dec = &per_cpu(decrementers, cpu);
diff --git a/arch/powerpc/platforms/cell/interrupt.c b/arch/powerpc/platforms/cell/interrupt.c
index adf3726..8a106b4 100644
--- a/arch/powerpc/platforms/cell/interrupt.c
+++ b/arch/powerpc/platforms/cell/interrupt.c
@@ -215,7 +215,7 @@ void iic_request_IPIs(void)
 {
 	iic_request_ipi(PPC_MSG_CALL_FUNCTION);
 	iic_request_ipi(PPC_MSG_RESCHEDULE);
-	iic_request_ipi(PPC_MSG_UNUSED);
+	iic_request_ipi(PPC_MSG_TICK_BROADCAST);
 	iic_request_ipi(PPC_MSG_DEBUGGER_BREAK);
 }
 
diff --git a/arch/powerpc/platforms/ps3/smp.c b/arch/powerpc/platforms/ps3/smp.c
index 00d1a7c..b358bec 100644
--- a/arch/powerpc/platforms/ps3/smp.c
+++ b/arch/powerpc/platforms/ps3/smp.c
@@ -76,7 +76,7 @@ static int __init ps3_smp_probe(void)
 
 		BUILD_BUG_ON(PPC_MSG_CALL_FUNCTION    != 0);
 		BUILD_BUG_ON(PPC_MSG_RESCHEDULE       != 1);
-		BUILD_BUG_ON(PPC_MSG_UNUSED	      != 2);
+		BUILD_BUG_ON(PPC_MSG_TICK_BROADCAST   != 2);
 		BUILD_BUG_ON(PPC_MSG_DEBUGGER_BREAK   != 3);
 
 		for (i = 0; i < MSG_COUNT; i++) {

[PATCH 3/7] cpuidle/ppc: Split timer_interrupt() into timer handling and interrupt handling routines

[Preeti U Murthy]

Split timer_interrupt(), which is the local timer interrupt handler on ppc
into routines called during regular interrupt handling and __timer_interrupt(),
which takes care of running local timers and collecting time related stats.

This will enable callers interested only in running expired local timers to
directly call into __timer_interupt(). One of the use cases of this is the
tick broadcast IPI handling in which the sleeping CPUs need to handle the local
timers that have expired.

Signed-off-by: Preeti U Murthy <preeti@linux.vnet.ibm.com>
---

 arch/powerpc/kernel/time.c |   81 +++++++++++++++++++++++++-------------------
 1 file changed, 46 insertions(+), 35 deletions(-)

diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c
index 3ff97db..df2989b 100644
--- a/arch/powerpc/kernel/time.c
+++ b/arch/powerpc/kernel/time.c
@@ -478,6 +478,47 @@ void arch_irq_work_raise(void)
 
 #endif /* CONFIG_IRQ_WORK */
 
+void __timer_interrupt(void)
+{
+	struct pt_regs *regs = get_irq_regs();
+	u64 *next_tb = &__get_cpu_var(decrementers_next_tb);
+	struct clock_event_device *evt = &__get_cpu_var(decrementers);
+	u64 now;
+
+	trace_timer_interrupt_entry(regs);
+
+	if (test_irq_work_pending()) {
+		clear_irq_work_pending();
+		irq_work_run();
+	}
+
+	now = get_tb_or_rtc();
+	if (now >= *next_tb) {
+		*next_tb = ~(u64)0;
+		if (evt->event_handler)
+			evt->event_handler(evt);
+		__get_cpu_var(irq_stat).timer_irqs_event++;
+	} else {
+		now = *next_tb - now;
+		if (now <= DECREMENTER_MAX)
+			set_dec((int)now);
+		/* We may have raced with new irq work */
+		if (test_irq_work_pending())
+			set_dec(1);
+		__get_cpu_var(irq_stat).timer_irqs_others++;
+	}
+
+#ifdef CONFIG_PPC64
+	/* collect purr register values often, for accurate calculations */
+	if (firmware_has_feature(FW_FEATURE_SPLPAR)) {
+		struct cpu_usage *cu = &__get_cpu_var(cpu_usage_array);
+		cu->current_tb = mfspr(SPRN_PURR);
+	}
+#endif
+
+	trace_timer_interrupt_exit(regs);
+}
+
 /*
  * timer_interrupt - gets called when the decrementer overflows,
  * with interrupts disabled.
@@ -486,8 +527,6 @@ void timer_interrupt(struct pt_regs * regs)
 {
 	struct pt_regs *old_regs;
 	u64 *next_tb = &__get_cpu_var(decrementers_next_tb);
-	struct clock_event_device *evt = &__get_cpu_var(decrementers);
-	u64 now;
 
 	/* Ensure a positive value is written to the decrementer, or else
 	 * some CPUs will continue to take decrementer exceptions.
@@ -519,39 +558,7 @@ void timer_interrupt(struct pt_regs * regs)
 	old_regs = set_irq_regs(regs);
 	irq_enter();
 
-	trace_timer_interrupt_entry(regs);
-
-	if (test_irq_work_pending()) {
-		clear_irq_work_pending();
-		irq_work_run();
-	}
-
-	now = get_tb_or_rtc();
-	if (now >= *next_tb) {
-		*next_tb = ~(u64)0;
-		if (evt->event_handler)
-			evt->event_handler(evt);
-		__get_cpu_var(irq_stat).timer_irqs_event++;
-	} else {
-		now = *next_tb - now;
-		if (now <= DECREMENTER_MAX)
-			set_dec((int)now);
-		/* We may have raced with new irq work */
-		if (test_irq_work_pending())
-			set_dec(1);
-		__get_cpu_var(irq_stat).timer_irqs_others++;
-	}
-
-#ifdef CONFIG_PPC64
-	/* collect purr register values often, for accurate calculations */
-	if (firmware_has_feature(FW_FEATURE_SPLPAR)) {
-		struct cpu_usage *cu = &__get_cpu_var(cpu_usage_array);
-		cu->current_tb = mfspr(SPRN_PURR);
-	}
-#endif
-
-	trace_timer_interrupt_exit(regs);
-
+	__timer_interrupt();
 	irq_exit();
 	set_irq_regs(old_regs);
 }
@@ -828,6 +835,10 @@ static void decrementer_set_mode(enum clock_event_mode mode,
 /* Interrupt handler for the timer broadcast IPI */
 void tick_broadcast_ipi_handler(void)
 {
+	u64 *next_tb = &__get_cpu_var(decrementers_next_tb);
+
+	*next_tb = get_tb_or_rtc();
+	__timer_interrupt();
 }
 
 static void register_decrementer_clockevent(int cpu)

[PATCH 4/7] powernv/cpuidle: Add context management for Fast Sleep

[Preeti U Murthy]

From: Vaidyanathan Srinivasan <svaidy@linux.vnet.ibm.com>

Before adding Fast-Sleep into the cpuidle framework, some low level
support needs to be added to enable it. This includes saving and
restoring of certain registers at entry and exit time of this state
respectively just like we do in the NAP idle state.

Signed-off-by: Vaidyanathan Srinivasan <svaidy@linux.vnet.ibm.com>
[Changelog modified by Preeti U. Murthy <preeti@linux.vnet.ibm.com>]
Signed-off-by: Preeti U. Murthy <preeti@linux.vnet.ibm.com>
---

 arch/powerpc/include/asm/processor.h |    1 +
 arch/powerpc/kernel/exceptions-64s.S |   10 ++++-
 arch/powerpc/kernel/idle_power7.S    |   63 ++++++++++++++++++++++++----------
 3 files changed, 53 insertions(+), 21 deletions(-)

diff --git a/arch/powerpc/include/asm/processor.h b/arch/powerpc/include/asm/processor.h
index b62de43..d660dc3 100644
--- a/arch/powerpc/include/asm/processor.h
+++ b/arch/powerpc/include/asm/processor.h
@@ -450,6 +450,7 @@ enum idle_boot_override {IDLE_NO_OVERRIDE = 0, IDLE_POWERSAVE_OFF};
 
 extern int powersave_nap;	/* set if nap mode can be used in idle loop */
 extern void power7_nap(void);
+extern void power7_sleep(void);
 extern void flush_instruction_cache(void);
 extern void hard_reset_now(void);
 extern void poweroff_now(void);
diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S
index 38d5073..b01a9cb 100644
--- a/arch/powerpc/kernel/exceptions-64s.S
+++ b/arch/powerpc/kernel/exceptions-64s.S
@@ -121,9 +121,10 @@ BEGIN_FTR_SECTION
 	cmpwi	cr1,r13,2
 	/* Total loss of HV state is fatal, we could try to use the
 	 * PIR to locate a PACA, then use an emergency stack etc...
-	 * but for now, let's just stay stuck here
+	 * OPAL v3 based powernv platforms have new idle states
+	 * which fall in this catagory.
 	 */
-	bgt	cr1,.
+	bgt	cr1,8f
 	GET_PACA(r13)
 
 #ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
@@ -141,6 +142,11 @@ BEGIN_FTR_SECTION
 	beq	cr1,2f
 	b	.power7_wakeup_noloss
 2:	b	.power7_wakeup_loss
+
+	/* Fast Sleep wakeup on PowerNV */
+8:	GET_PACA(r13)
+	b 	.power7_wakeup_loss
+
 9:
 END_FTR_SECTION_IFSET(CPU_FTR_HVMODE | CPU_FTR_ARCH_206)
 #endif /* CONFIG_PPC_P7_NAP */
diff --git a/arch/powerpc/kernel/idle_power7.S b/arch/powerpc/kernel/idle_power7.S
index 3fdef0f..14f78be 100644
--- a/arch/powerpc/kernel/idle_power7.S
+++ b/arch/powerpc/kernel/idle_power7.S
@@ -20,17 +20,27 @@
 
 #undef DEBUG
 
-	.text
+/* Idle state entry routines */
 
-_GLOBAL(power7_idle)
-	/* Now check if user or arch enabled NAP mode */
-	LOAD_REG_ADDRBASE(r3,powersave_nap)
-	lwz	r4,ADDROFF(powersave_nap)(r3)
-	cmpwi	0,r4,0
-	beqlr
-	/* fall through */
+#define	IDLE_STATE_ENTER_SEQ(IDLE_INST)				\
+	/* Magic NAP/SLEEP/WINKLE mode enter sequence */	\
+	std	r0,0(r1);					\
+	ptesync;						\
+	ld	r0,0(r1);					\
+1:	cmp	cr0,r0,r0;					\
+	bne	1b;						\
+	IDLE_INST;						\
+	b	.
 
-_GLOBAL(power7_nap)
+	.text
+
+/*
+ * Pass requested state in r3:
+ * 	0 - nap
+ * 	1 - sleep
+ */
+_GLOBAL(power7_powersave_common)
+	/* Use r3 to pass state nap/sleep/winkle */
 	/* NAP is a state loss, we create a regs frame on the
 	 * stack, fill it up with the state we care about and
 	 * stick a pointer to it in PACAR1. We really only
@@ -79,8 +89,8 @@ _GLOBAL(power7_nap)
 	/* Continue saving state */
 	SAVE_GPR(2, r1)
 	SAVE_NVGPRS(r1)
-	mfcr	r3
-	std	r3,_CCR(r1)
+	mfcr	r4
+	std	r4,_CCR(r1)
 	std	r9,_MSR(r1)
 	std	r1,PACAR1(r13)
 
@@ -90,15 +100,30 @@ _GLOBAL(power7_enter_nap_mode)
 	li	r4,KVM_HWTHREAD_IN_NAP
 	stb	r4,HSTATE_HWTHREAD_STATE(r13)
 #endif
+	cmpwi	cr0,r3,1
+	beq	2f
+	IDLE_STATE_ENTER_SEQ(PPC_NAP)
+	/* No return */
+2:	IDLE_STATE_ENTER_SEQ(PPC_SLEEP)
+	/* No return */
 
-	/* Magic NAP mode enter sequence */
-	std	r0,0(r1)
-	ptesync
-	ld	r0,0(r1)
-1:	cmp	cr0,r0,r0
-	bne	1b
-	PPC_NAP
-	b	.
+_GLOBAL(power7_idle)
+	/* Now check if user or arch enabled NAP mode */
+	LOAD_REG_ADDRBASE(r3,powersave_nap)
+	lwz	r4,ADDROFF(powersave_nap)(r3)
+	cmpwi	0,r4,0
+	beqlr
+	/* fall through */
+
+_GLOBAL(power7_nap)
+	li	r3,0
+	b	power7_powersave_common
+	/* No return */
+
+_GLOBAL(power7_sleep)
+	li	r3,1
+	b	power7_powersave_common
+	/* No return */
 
 _GLOBAL(power7_wakeup_loss)
 	ld	r1,PACAR1(r13)

[PATCH 5/7] powermgt: Add OPAL call to resync timebase on wakeup

[Preeti U Murthy]

From: Vaidyanathan Srinivasan <svaidy@linux.vnet.ibm.com>

During "Fast-sleep" and deeper power savings state, decrementer and
timebase could be stopped making it out of sync with rest
of the cores in the system.

Add a firmware call to request platform to resync timebase
using low level platform methods.

Signed-off-by: Vaidyanathan Srinivasan <svaidy@linux.vnet.ibm.com>
Signed-off-by: Preeti U. Murthy <preeti@linux.vnet.ibm.com>
---

 arch/powerpc/include/asm/opal.h                |    2 ++
 arch/powerpc/kernel/exceptions-64s.S           |    2 +-
 arch/powerpc/kernel/idle_power7.S              |   27 ++++++++++++++++++++++++
 arch/powerpc/platforms/powernv/opal-wrappers.S |    1 +
 4 files changed, 31 insertions(+), 1 deletion(-)

diff --git a/arch/powerpc/include/asm/opal.h b/arch/powerpc/include/asm/opal.h
index 40157e2..c71c72e 100644
--- a/arch/powerpc/include/asm/opal.h
+++ b/arch/powerpc/include/asm/opal.h
@@ -154,6 +154,7 @@ extern int opal_enter_rtas(struct rtas_args *args,
 #define OPAL_FLASH_VALIDATE			76
 #define OPAL_FLASH_MANAGE			77
 #define OPAL_FLASH_UPDATE			78
+#define OPAL_RESYNC_TIMEBASE			79
 #define OPAL_GET_MSG				85
 #define OPAL_CHECK_ASYNC_COMPLETION		86
 #define OPAL_SYNC_HOST_REBOOT			87
@@ -865,6 +866,7 @@ extern void opal_flash_init(void);
 extern int opal_machine_check(struct pt_regs *regs);
 
 extern void opal_shutdown(void);
+extern int opal_resync_timebase(void);
 
 extern void opal_lpc_init(void);
 
diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S
index b01a9cb..9533d7a 100644
--- a/arch/powerpc/kernel/exceptions-64s.S
+++ b/arch/powerpc/kernel/exceptions-64s.S
@@ -145,7 +145,7 @@ BEGIN_FTR_SECTION
 
 	/* Fast Sleep wakeup on PowerNV */
 8:	GET_PACA(r13)
-	b 	.power7_wakeup_loss
+	b 	.power7_wakeup_tb_loss
 
 9:
 END_FTR_SECTION_IFSET(CPU_FTR_HVMODE | CPU_FTR_ARCH_206)
diff --git a/arch/powerpc/kernel/idle_power7.S b/arch/powerpc/kernel/idle_power7.S
index 14f78be..c3ab869 100644
--- a/arch/powerpc/kernel/idle_power7.S
+++ b/arch/powerpc/kernel/idle_power7.S
@@ -17,6 +17,7 @@
 #include <asm/ppc-opcode.h>
 #include <asm/hw_irq.h>
 #include <asm/kvm_book3s_asm.h>
+#include <asm/opal.h>
 
 #undef DEBUG
 
@@ -125,6 +126,32 @@ _GLOBAL(power7_sleep)
 	b	power7_powersave_common
 	/* No return */
 
+_GLOBAL(power7_wakeup_tb_loss)
+	ld	r2,PACATOC(r13);
+	ld	r1,PACAR1(r13)
+
+	/* Time base re-sync */
+	li	r0,OPAL_RESYNC_TIMEBASE
+	LOAD_REG_ADDR(r11,opal);
+	ld	r12,8(r11);
+	ld	r2,0(r11);
+	mtctr	r12
+	bctrl
+
+	/* TODO: Check r3 for failure */
+
+	REST_NVGPRS(r1)
+	REST_GPR(2, r1)
+	ld	r3,_CCR(r1)
+	ld	r4,_MSR(r1)
+	ld	r5,_NIP(r1)
+	addi	r1,r1,INT_FRAME_SIZE
+	mtcr	r3
+	mfspr	r3,SPRN_SRR1		/* Return SRR1 */
+	mtspr	SPRN_SRR1,r4
+	mtspr	SPRN_SRR0,r5
+	rfid
+
 _GLOBAL(power7_wakeup_loss)
 	ld	r1,PACAR1(r13)
 	REST_NVGPRS(r1)
diff --git a/arch/powerpc/platforms/powernv/opal-wrappers.S b/arch/powerpc/platforms/powernv/opal-wrappers.S
index 3e8829c..aab54b6 100644
--- a/arch/powerpc/platforms/powernv/opal-wrappers.S
+++ b/arch/powerpc/platforms/powernv/opal-wrappers.S
@@ -126,6 +126,7 @@ OPAL_CALL(opal_return_cpu,			OPAL_RETURN_CPU);
 OPAL_CALL(opal_validate_flash,			OPAL_FLASH_VALIDATE);
 OPAL_CALL(opal_manage_flash,			OPAL_FLASH_MANAGE);
 OPAL_CALL(opal_update_flash,			OPAL_FLASH_UPDATE);
+OPAL_CALL(opal_resync_timebase,			OPAL_RESYNC_TIMEBASE);
 OPAL_CALL(opal_get_msg,				OPAL_GET_MSG);
 OPAL_CALL(opal_check_completion,		OPAL_CHECK_ASYNC_COMPLETION);
 OPAL_CALL(opal_sync_host_reboot,		OPAL_SYNC_HOST_REBOOT);

[PATCH 6/7] cpuidle/powernv: Add "Fast-Sleep" CPU idle state

[Preeti U Murthy]

Fast sleep is one of the deep idle states on Power8 in which local timers of
CPUs stop. On PowerPC we do not have an external clock device which can
handle wakeup of such CPUs. Now that we have the support in the tick broadcast
framework for archs that do not sport such a device and the low level support
for fast sleep, enable it in the cpuidle framework on PowerNV.

Signed-off-by: Preeti U Murthy <preeti@linux.vnet.ibm.com>
---

 arch/powerpc/Kconfig              |    2 ++
 arch/powerpc/kernel/time.c        |    4 +++-
 drivers/cpuidle/cpuidle-powernv.c |   34 ++++++++++++++++++++++++++++++++++
 3 files changed, 39 insertions(+), 1 deletion(-)

diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index 957bf34..b841420 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -130,6 +130,8 @@ config PPC
 	select GENERIC_CMOS_UPDATE
 	select GENERIC_TIME_VSYSCALL_OLD
 	select GENERIC_CLOCKEVENTS
+	select GENERIC_CLOCKEVENTS_BROADCAST if SMP
+	select ARCH_HAS_TICK_BROADCAST if GENERIC_CLOCKEVENTS_BROADCAST
 	select GENERIC_STRNCPY_FROM_USER
 	select GENERIC_STRNLEN_USER
 	select HAVE_MOD_ARCH_SPECIFIC
diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c
index df2989b..122a580 100644
--- a/arch/powerpc/kernel/time.c
+++ b/arch/powerpc/kernel/time.c
@@ -42,6 +42,7 @@
 #include <linux/timex.h>
 #include <linux/kernel_stat.h>
 #include <linux/time.h>
+#include <linux/clockchips.h>
 #include <linux/init.h>
 #include <linux/profile.h>
 #include <linux/cpu.h>
@@ -106,7 +107,7 @@ struct clock_event_device decrementer_clockevent = {
 	.irq            = 0,
 	.set_next_event = decrementer_set_next_event,
 	.set_mode       = decrementer_set_mode,
-	.features       = CLOCK_EVT_FEAT_ONESHOT,
+	.features       = CLOCK_EVT_FEAT_ONESHOT | CLOCK_EVT_FEAT_C3STOP,
 };
 EXPORT_SYMBOL(decrementer_clockevent);
 
@@ -944,6 +945,7 @@ void __init time_init(void)
 	clocksource_init();
 
 	init_decrementer_clockevent();
+	tick_setup_hrtimer_broadcast();
 }
 
 
diff --git a/drivers/cpuidle/cpuidle-powernv.c b/drivers/cpuidle/cpuidle-powernv.c
index 78fd174..4fb97ce 100644
--- a/drivers/cpuidle/cpuidle-powernv.c
+++ b/drivers/cpuidle/cpuidle-powernv.c
@@ -11,6 +11,7 @@
 #include <linux/cpuidle.h>
 #include <linux/cpu.h>
 #include <linux/notifier.h>
+#include <linux/clockchips.h>
 
 #include <asm/machdep.h>
 #include <asm/firmware.h>
@@ -49,6 +50,32 @@ static int nap_loop(struct cpuidle_device *dev,
 	return index;
 }
 
+static int fastsleep_loop(struct cpuidle_device *dev,
+				struct cpuidle_driver *drv,
+				int index)
+{
+	unsigned long old_lpcr = mfspr(SPRN_LPCR);
+	unsigned long new_lpcr;
+
+	if (unlikely(system_state < SYSTEM_RUNNING))
+		return index;
+
+	new_lpcr = old_lpcr;
+	new_lpcr &= ~(LPCR_MER | LPCR_PECE); /* lpcr[mer] must be 0 */
+
+	/* exit powersave upon external interrupt, but not decrementer
+	 * interrupt.
+	 */
+	new_lpcr |= LPCR_PECE0;
+
+	mtspr(SPRN_LPCR, new_lpcr);
+	power7_sleep();
+
+	mtspr(SPRN_LPCR, old_lpcr);
+
+	return index;
+}
+
 /*
  * States for dedicated partition case.
  */
@@ -67,6 +94,13 @@ static struct cpuidle_state powernv_states[] = {
 		.exit_latency = 10,
 		.target_residency = 100,
 		.enter = &nap_loop },
+	 { /* Fastsleep */
+		.name = "fastsleep",
+		.desc = "fastsleep",
+		.flags = CPUIDLE_FLAG_TIME_VALID,
+		.exit_latency = 10,
+		.target_residency = 100,
+		.enter = &fastsleep_loop },
 };
 
 static int powernv_cpuidle_add_cpu_notifier(struct notifier_block *n,

[PATCH 7/7] cpuidle/powernv: Parse device tree to setup idle states

[Preeti U Murthy]

Add deep idle states such as nap and fast sleep to the cpuidle state table
only if they are discovered from the device tree during cpuidle initialization.

Signed-off-by: Preeti U Murthy <preeti@linux.vnet.ibm.com>
---

 drivers/cpuidle/cpuidle-powernv.c |   82 +++++++++++++++++++++++++++++--------
 1 file changed, 65 insertions(+), 17 deletions(-)

diff --git a/drivers/cpuidle/cpuidle-powernv.c b/drivers/cpuidle/cpuidle-powernv.c
index 4fb97ce..fdae1c4 100644
--- a/drivers/cpuidle/cpuidle-powernv.c
+++ b/drivers/cpuidle/cpuidle-powernv.c
@@ -12,10 +12,17 @@
 #include <linux/cpu.h>
 #include <linux/notifier.h>
 #include <linux/clockchips.h>
+#include <linux/of.h>
 
 #include <asm/machdep.h>
 #include <asm/firmware.h>
 
+/* Flags and constants used in PowerNV platform */
+
+#define MAX_POWERNV_IDLE_STATES	8
+#define IDLE_USE_INST_NAP	0x00010000 /* Use nap instruction */
+#define IDLE_USE_INST_SLEEP	0x00020000 /* Use sleep instruction */
+
 struct cpuidle_driver powernv_idle_driver = {
 	.name             = "powernv_idle",
 	.owner            = THIS_MODULE,
@@ -79,7 +86,7 @@ static int fastsleep_loop(struct cpuidle_device *dev,
 /*
  * States for dedicated partition case.
  */
-static struct cpuidle_state powernv_states[] = {
+static struct cpuidle_state powernv_states[MAX_POWERNV_IDLE_STATES] = {
 	{ /* Snooze */
 		.name = "snooze",
 		.desc = "snooze",
@@ -87,20 +94,6 @@ static struct cpuidle_state powernv_states[] = {
 		.exit_latency = 0,
 		.target_residency = 0,
 		.enter = &snooze_loop },
-	{ /* NAP */
-		.name = "NAP",
-		.desc = "NAP",
-		.flags = CPUIDLE_FLAG_TIME_VALID,
-		.exit_latency = 10,
-		.target_residency = 100,
-		.enter = &nap_loop },
-	 { /* Fastsleep */
-		.name = "fastsleep",
-		.desc = "fastsleep",
-		.flags = CPUIDLE_FLAG_TIME_VALID,
-		.exit_latency = 10,
-		.target_residency = 100,
-		.enter = &fastsleep_loop },
 };
 
 static int powernv_cpuidle_add_cpu_notifier(struct notifier_block *n,
@@ -161,19 +154,74 @@ static int powernv_cpuidle_driver_init(void)
 	return 0;
 }
 
+static int powernv_add_idle_states(void)
+{
+	struct device_node *power_mgt;
+	struct property *prop;
+	int nr_idle_states = 1; /* Snooze */
+	int dt_idle_states;
+	u32 *flags;
+	int i;
+
+	/* Currently we have snooze statically defined */
+
+	power_mgt = of_find_node_by_path("/ibm,opal/power-mgt");
+	if (!power_mgt) {
+		pr_warn("opal: PowerMgmt Node not found\n");
+		return nr_idle_states;
+	}
+
+	prop = of_find_property(power_mgt, "ibm,cpu-idle-state-flags", NULL);
+	if (!prop) {
+		pr_warn("DT-PowerMgmt: missing ibm,cpu-idle-state-flags\n");
+		return nr_idle_states;
+	}
+
+	dt_idle_states = prop->length / sizeof(u32);
+	flags = (u32 *) prop->value;
+
+	for (i = 0; i < dt_idle_states; i++) {
+
+		if (flags[i] & IDLE_USE_INST_NAP) {
+			/* Add NAP state */
+			strcpy(powernv_states[nr_idle_states].name, "Nap");
+			strcpy(powernv_states[nr_idle_states].desc, "Nap");
+			powernv_states[nr_idle_states].flags = CPUIDLE_FLAG_TIME_VALID;
+			powernv_states[nr_idle_states].exit_latency = 10;
+			powernv_states[nr_idle_states].target_residency = 100;
+			powernv_states[nr_idle_states].enter = &nap_loop;
+			nr_idle_states++;
+		}
+
+		if (flags[i] & IDLE_USE_INST_SLEEP) {
+			/* Add FASTSLEEP state */
+			strcpy(powernv_states[nr_idle_states].name, "FastSleep");
+			strcpy(powernv_states[nr_idle_states].desc, "FastSleep");
+			powernv_states[nr_idle_states].flags =
+				CPUIDLE_FLAG_TIME_VALID | CPUIDLE_FLAG_TIMER_STOP;
+			powernv_states[nr_idle_states].exit_latency = 300;
+			powernv_states[nr_idle_states].target_residency = 1000000;
+			powernv_states[nr_idle_states].enter = &fastsleep_loop;
+			nr_idle_states++;
+		}
+	}
+
+	return nr_idle_states;
+}
+
 /*
  * powernv_idle_probe()
  * Choose state table for shared versus dedicated partition
  */
 static int powernv_idle_probe(void)
 {
-
 	if (cpuidle_disable != IDLE_NO_OVERRIDE)
 		return -ENODEV;
 
 	if (firmware_has_feature(FW_FEATURE_OPALv3)) {
 		cpuidle_state_table = powernv_states;
-		max_idle_state = ARRAY_SIZE(powernv_states);
+		/* Device tree can indicate more idle states */
+		max_idle_state = powernv_add_idle_states();
  	} else
  		return -ENODEV;