Merge tag 'powerpc-3.19-2' of git://git.kernel.org/pub/scm/linux/kernel/git/mpe/linux

Pull second batch of powerpc updates from Michael Ellerman:
 "The highlight is the series that reworks the idle management on
  powernv, which allows us to use deeper idle states on those machines.

  There's the fix from Anton for the "BUG at kernel/smpboot.c:134!"
  problem.

  An i2c driver for powernv.  This is acked by Wolfram Sang, and he
  asked that we take it through the powerpc tree.

  A fix for audit from rgb at Red Hat, acked by Paul Moore who is one of
  the audit maintainers.

  A patch from Ben to export the symbol map of our OPAL firmware as a
  sysfs file, so that tools can use it.

  Also some CXL fixes, a couple of powerpc perf fixes, a fix for
  smt-enabled, and the patch to add __force to get_user() so we can use
  bitwise types"

* tag 'powerpc-3.19-2' of git://git.kernel.org/pub/scm/linux/kernel/git/mpe/linux:
  powerpc/powernv: Ignore smt-enabled on Power8 and later
  powerpc/uaccess: Allow get_user() with bitwise types
  powerpc/powernv: Expose OPAL firmware symbol map
  powernv/powerpc: Add winkle support for offline cpus
  powernv/cpuidle: Redesign idle states management
  powerpc/powernv: Enable Offline CPUs to enter deep idle states
  powerpc/powernv: Switch off MMU before entering nap/sleep/rvwinkle mode
  i2c: Driver to expose PowerNV platform i2c busses
  powerpc: add little endian flag to syscall_get_arch()
  power/perf/hv-24x7: Use kmem_cache_free() instead of kfree
  powerpc/perf/hv-24x7: Use per-cpu page buffer
  cxl: Unmap MMIO regions when detaching a context
  cxl: Add timeout to process element commands
  cxl: Change contexts_lock to a mutex to fix sleep while atomic bug
  powerpc: Secondary CPUs must set cpu_callin_map after setting active and online

20 files changed, 766 insertions, 78 deletions

diff --git a/arch/powerpc/include/asm/cpuidle.h b/arch/powerpc/include/asm/cpuidle.h
new file mode 100644
index 00000000000..d2f99ca1e3a
--- /dev/null
+++ b/arch/powerpc/include/asm/cpuidle.h
@@ -0,0 +1,20 @@
+#ifndef _ASM_POWERPC_CPUIDLE_H
+#define _ASM_POWERPC_CPUIDLE_H
+
+#ifdef CONFIG_PPC_POWERNV
+/* Used in powernv idle state management */
+#define PNV_THREAD_RUNNING              0
+#define PNV_THREAD_NAP                  1
+#define PNV_THREAD_SLEEP                2
+#define PNV_THREAD_WINKLE               3
+#define PNV_CORE_IDLE_LOCK_BIT          0x100
+#define PNV_CORE_IDLE_THREAD_BITS       0x0FF
+
+#ifndef __ASSEMBLY__
+extern u32 pnv_fastsleep_workaround_at_entry[];
+extern u32 pnv_fastsleep_workaround_at_exit[];
+#endif
+
+#endif
+
+#endif
diff --git a/arch/powerpc/include/asm/opal.h b/arch/powerpc/include/asm/opal.h
index 5cd8d2fddba..eb95b675109 100644
--- a/arch/powerpc/include/asm/opal.h
+++ b/arch/powerpc/include/asm/opal.h
@@ -56,6 +56,14 @@ struct opal_sg_list {
 #define OPAL_HARDWARE_FROZEN	-13
 #define OPAL_WRONG_STATE	-14
 #define OPAL_ASYNC_COMPLETION	-15
+#define OPAL_I2C_TIMEOUT	-17
+#define OPAL_I2C_INVALID_CMD	-18
+#define OPAL_I2C_LBUS_PARITY	-19
+#define OPAL_I2C_BKEND_OVERRUN	-20
+#define OPAL_I2C_BKEND_ACCESS	-21
+#define OPAL_I2C_ARBT_LOST	-22
+#define OPAL_I2C_NACK_RCVD	-23
+#define OPAL_I2C_STOP_ERR	-24
 
 /* API Tokens (in r0) */
 #define OPAL_INVALID_CALL			-1
@@ -152,12 +160,25 @@ struct opal_sg_list {
 #define OPAL_PCI_ERR_INJECT			96
 #define OPAL_PCI_EEH_FREEZE_SET			97
 #define OPAL_HANDLE_HMI				98
+#define OPAL_CONFIG_CPU_IDLE_STATE		99
+#define OPAL_SLW_SET_REG			100
 #define OPAL_REGISTER_DUMP_REGION		101
 #define OPAL_UNREGISTER_DUMP_REGION		102
 #define OPAL_WRITE_TPO				103
 #define OPAL_READ_TPO				104
 #define OPAL_IPMI_SEND				107
 #define OPAL_IPMI_RECV				108
+#define OPAL_I2C_REQUEST			109
+
+/* Device tree flags */
+
+/* Flags set in power-mgmt nodes in device tree if
+ * respective idle states are supported in the platform.
+ */
+#define OPAL_PM_NAP_ENABLED	0x00010000
+#define OPAL_PM_SLEEP_ENABLED	0x00020000
+#define OPAL_PM_WINKLE_ENABLED	0x00040000
+#define OPAL_PM_SLEEP_ENABLED_ER1	0x00080000
 
 #ifndef __ASSEMBLY__
 
@@ -712,6 +733,24 @@ typedef struct oppanel_line {
 	uint64_t 	line_len;
 } oppanel_line_t;
 
+/* OPAL I2C request */
+struct opal_i2c_request {
+	uint8_t	type;
+#define OPAL_I2C_RAW_READ	0
+#define OPAL_I2C_RAW_WRITE	1
+#define OPAL_I2C_SM_READ	2
+#define OPAL_I2C_SM_WRITE	3
+	uint8_t flags;
+#define OPAL_I2C_ADDR_10	0x01	/* Not supported yet */
+	uint8_t	subaddr_sz;		/* Max 4 */
+	uint8_t reserved;
+	__be16 addr;			/* 7 or 10 bit address */
+	__be16 reserved2;
+	__be32 subaddr;		/* Sub-address if any */
+	__be32 size;			/* Data size */
+	__be64 buffer_ra;		/* Buffer real address */
+};
+
 /* /sys/firmware/opal */
 extern struct kobject *opal_kobj;
 
@@ -876,11 +915,14 @@ int64_t opal_sensor_read(uint32_t sensor_hndl, int token, __be32 *sensor_data);
 int64_t opal_handle_hmi(void);
 int64_t opal_register_dump_region(uint32_t id, uint64_t start, uint64_t end);
 int64_t opal_unregister_dump_region(uint32_t id);
+int64_t opal_slw_set_reg(uint64_t cpu_pir, uint64_t sprn, uint64_t val);
 int64_t opal_pci_set_phb_cxl_mode(uint64_t phb_id, uint64_t mode, uint64_t pe_number);
 int64_t opal_ipmi_send(uint64_t interface, struct opal_ipmi_msg *msg,
 		uint64_t msg_len);
 int64_t opal_ipmi_recv(uint64_t interface, struct opal_ipmi_msg *msg,
 		uint64_t *msg_len);
+int64_t opal_i2c_request(uint64_t async_token, uint32_t bus_id,
+			 struct opal_i2c_request *oreq);
 
 /* Internal functions */
 extern int early_init_dt_scan_opal(unsigned long node, const char *uname,
diff --git a/arch/powerpc/include/asm/paca.h b/arch/powerpc/include/asm/paca.h
index 24a386cbb92..e5f22c6c4bf 100644
--- a/arch/powerpc/include/asm/paca.h
+++ b/arch/powerpc/include/asm/paca.h
@@ -152,6 +152,16 @@ struct paca_struct {
 	u64 tm_scratch;                 /* TM scratch area for reclaim */
 #endif
 
+#ifdef CONFIG_PPC_POWERNV
+	/* Per-core mask tracking idle threads and a lock bit-[L][TTTTTTTT] */
+	u32 *core_idle_state_ptr;
+	u8 thread_idle_state;		/* PNV_THREAD_RUNNING/NAP/SLEEP	*/
+	/* Mask to indicate thread id in core */
+	u8 thread_mask;
+	/* Mask to denote subcore sibling threads */
+	u8 subcore_sibling_mask;
+#endif
+
 #ifdef CONFIG_PPC_BOOK3S_64
 	/* Exclusive emergency stack pointer for machine check exception. */
 	void *mc_emergency_sp;
diff --git a/arch/powerpc/include/asm/ppc-opcode.h b/arch/powerpc/include/asm/ppc-opcode.h
index 1a5287759fc..03cd858a401 100644
--- a/arch/powerpc/include/asm/ppc-opcode.h
+++ b/arch/powerpc/include/asm/ppc-opcode.h
@@ -194,6 +194,7 @@
 
 #define PPC_INST_NAP			0x4c000364
 #define PPC_INST_SLEEP			0x4c0003a4
+#define PPC_INST_WINKLE			0x4c0003e4
 
 /* A2 specific instructions */
 #define PPC_INST_ERATWE			0x7c0001a6
@@ -375,6 +376,7 @@
 
 #define PPC_NAP			stringify_in_c(.long PPC_INST_NAP)
 #define PPC_SLEEP		stringify_in_c(.long PPC_INST_SLEEP)
+#define PPC_WINKLE		stringify_in_c(.long PPC_INST_WINKLE)
 
 /* BHRB instructions */
 #define PPC_CLRBHRB		stringify_in_c(.long PPC_INST_CLRBHRB)
diff --git a/arch/powerpc/include/asm/processor.h b/arch/powerpc/include/asm/processor.h
index 29c3798cf80..bf117d8fb45 100644
--- a/arch/powerpc/include/asm/processor.h
+++ b/arch/powerpc/include/asm/processor.h
@@ -452,7 +452,8 @@ 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 unsigned long power7_nap(int check_irq);
-extern void power7_sleep(void);
+extern unsigned long power7_sleep(void);
+extern unsigned long power7_winkle(void);
 extern void flush_instruction_cache(void);
 extern void hard_reset_now(void);
 extern void poweroff_now(void);
diff --git a/arch/powerpc/include/asm/reg.h b/arch/powerpc/include/asm/reg.h
index c998279bd85..1c874fb533b 100644
--- a/arch/powerpc/include/asm/reg.h
+++ b/arch/powerpc/include/asm/reg.h
@@ -118,8 +118,10 @@
 #define __MSR		(MSR_ME | MSR_RI | MSR_IR | MSR_DR | MSR_ISF |MSR_HV)
 #ifdef __BIG_ENDIAN__
 #define MSR_		__MSR
+#define MSR_IDLE	(MSR_ME | MSR_SF | MSR_HV)
 #else
 #define MSR_		(__MSR | MSR_LE)
+#define MSR_IDLE	(MSR_ME | MSR_SF | MSR_HV | MSR_LE)
 #endif
 #define MSR_KERNEL	(MSR_ | MSR_64BIT)
 #define MSR_USER32	(MSR_ | MSR_PR | MSR_EE)
@@ -371,6 +373,7 @@
 #define SPRN_DBAT7L	0x23F	/* Data BAT 7 Lower Register */
 #define SPRN_DBAT7U	0x23E	/* Data BAT 7 Upper Register */
 #define SPRN_PPR	0x380	/* SMT Thread status Register */
+#define SPRN_TSCR	0x399	/* Thread Switch Control Register */
 
 #define SPRN_DEC	0x016		/* Decrement Register */
 #define SPRN_DER	0x095		/* Debug Enable Regsiter */
@@ -728,6 +731,7 @@
 #define SPRN_BESCR	806	/* Branch event status and control register */
 #define   BESCR_GE	0x8000000000000000ULL /* Global Enable */
 #define SPRN_WORT	895	/* Workload optimization register - thread */
+#define SPRN_WORC	863	/* Workload optimization register - core */
 
 #define SPRN_PMC1	787
 #define SPRN_PMC2	788
diff --git a/arch/powerpc/include/asm/syscall.h b/arch/powerpc/include/asm/syscall.h
index 6240698fee9..ff21b7a2f0c 100644
--- a/arch/powerpc/include/asm/syscall.h
+++ b/arch/powerpc/include/asm/syscall.h
@@ -90,6 +90,10 @@ static inline void syscall_set_arguments(struct task_struct *task,
 
 static inline int syscall_get_arch(void)
 {
-	return is_32bit_task() ? AUDIT_ARCH_PPC : AUDIT_ARCH_PPC64;
+	int arch = is_32bit_task() ? AUDIT_ARCH_PPC : AUDIT_ARCH_PPC64;
+#ifdef __LITTLE_ENDIAN__
+	arch |= __AUDIT_ARCH_LE;
+#endif
+	return arch;
 }
 #endif	/* _ASM_SYSCALL_H */
diff --git a/arch/powerpc/include/asm/uaccess.h b/arch/powerpc/include/asm/uaccess.h
index 9485b43a7c0..a0c071d24e0 100644
--- a/arch/powerpc/include/asm/uaccess.h
+++ b/arch/powerpc/include/asm/uaccess.h
@@ -284,7 +284,7 @@ do {								\
 	if (!is_kernel_addr((unsigned long)__gu_addr))		\
 		might_fault();					\
 	__get_user_size(__gu_val, __gu_addr, (size), __gu_err);	\
-	(x) = (__typeof__(*(ptr)))__gu_val;			\
+	(x) = (__force __typeof__(*(ptr)))__gu_val;			\
 	__gu_err;						\
 })
 #endif /* __powerpc64__ */
@@ -297,7 +297,7 @@ do {								\
 	might_fault();							\
 	if (access_ok(VERIFY_READ, __gu_addr, (size)))			\
 		__get_user_size(__gu_val, __gu_addr, (size), __gu_err);	\
-	(x) = (__typeof__(*(ptr)))__gu_val;				\
+	(x) = (__force __typeof__(*(ptr)))__gu_val;				\
 	__gu_err;							\
 })
 
@@ -308,7 +308,7 @@ do {								\
 	const __typeof__(*(ptr)) __user *__gu_addr = (ptr);	\
 	__chk_user_ptr(ptr);					\
 	__get_user_size(__gu_val, __gu_addr, (size), __gu_err);	\
-	(x) = (__typeof__(*(ptr)))__gu_val;			\
+	(x) = (__force __typeof__(*(ptr)))__gu_val;			\
 	__gu_err;						\
 })
 
diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c
index 24d78e1871c..e624f964635 100644
--- a/arch/powerpc/kernel/asm-offsets.c
+++ b/arch/powerpc/kernel/asm-offsets.c
@@ -726,5 +726,16 @@ int main(void)
 					arch.timing_last_enter.tv32.tbl));
 #endif
 
+#ifdef CONFIG_PPC_POWERNV
+	DEFINE(PACA_CORE_IDLE_STATE_PTR,
+			offsetof(struct paca_struct, core_idle_state_ptr));
+	DEFINE(PACA_THREAD_IDLE_STATE,
+			offsetof(struct paca_struct, thread_idle_state));
+	DEFINE(PACA_THREAD_MASK,
+			offsetof(struct paca_struct, thread_mask));
+	DEFINE(PACA_SUBCORE_SIBLING_MASK,
+			offsetof(struct paca_struct, subcore_sibling_mask));
+#endif
+
 	return 0;
 }
diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S
index db08382e19f..c2df8150bd7 100644
--- a/arch/powerpc/kernel/exceptions-64s.S
+++ b/arch/powerpc/kernel/exceptions-64s.S
@@ -15,6 +15,7 @@
 #include <asm/hw_irq.h>
 #include <asm/exception-64s.h>
 #include <asm/ptrace.h>
+#include <asm/cpuidle.h>
 
 /*
  * We layout physical memory as follows:
@@ -101,23 +102,34 @@ system_reset_pSeries:
 #ifdef CONFIG_PPC_P7_NAP
 BEGIN_FTR_SECTION
 	/* Running native on arch 2.06 or later, check if we are
-	 * waking up from nap. We only handle no state loss and
-	 * supervisor state loss. We do -not- handle hypervisor
-	 * state loss at this time.
+	 * waking up from nap/sleep/winkle.
 	 */
 	mfspr	r13,SPRN_SRR1
 	rlwinm.	r13,r13,47-31,30,31
 	beq	9f
 
-	/* waking up from powersave (nap) state */
-	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...
-	 * OPAL v3 based powernv platforms have new idle states
-	 * which fall in this catagory.
+	cmpwi	cr3,r13,2
+
+	/*
+	 * Check if last bit of HSPGR0 is set. This indicates whether we are
+	 * waking up from winkle.
 	 */
-	bgt	cr1,8f
 	GET_PACA(r13)
+	clrldi	r5,r13,63
+	clrrdi	r13,r13,1
+	cmpwi	cr4,r5,1
+	mtspr	SPRN_HSPRG0,r13
+
+	lbz	r0,PACA_THREAD_IDLE_STATE(r13)
+	cmpwi   cr2,r0,PNV_THREAD_NAP
+	bgt     cr2,8f				/* Either sleep or Winkle */
+
+	/* Waking up from nap should not cause hypervisor state loss */
+	bgt	cr3,.
+
+	/* Waking up from nap */
+	li	r0,PNV_THREAD_RUNNING
+	stb	r0,PACA_THREAD_IDLE_STATE(r13)	/* Clear thread state */
 
 #ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
 	li	r0,KVM_HWTHREAD_IN_KERNEL
@@ -133,7 +145,7 @@ BEGIN_FTR_SECTION
 
 	/* Return SRR1 from power7_nap() */
 	mfspr	r3,SPRN_SRR1
-	beq	cr1,2f
+	beq	cr3,2f
 	b	power7_wakeup_noloss
 2:	b	power7_wakeup_loss
 
@@ -1382,6 +1394,7 @@ machine_check_handle_early:
 	MACHINE_CHECK_HANDLER_WINDUP
 	GET_PACA(r13)
 	ld	r1,PACAR1(r13)
+	li	r3,PNV_THREAD_NAP
 	b	power7_enter_nap_mode
 4:
 #endif
diff --git a/arch/powerpc/kernel/idle_power7.S b/arch/powerpc/kernel/idle_power7.S
index 18c0687e5ab..05adc8bbdef 100644
--- a/arch/powerpc/kernel/idle_power7.S
+++ b/arch/powerpc/kernel/idle_power7.S
@@ -18,9 +18,25 @@
 #include <asm/hw_irq.h>
 #include <asm/kvm_book3s_asm.h>
 #include <asm/opal.h>
+#include <asm/cpuidle.h>
+#include <asm/mmu-hash64.h>
 
 #undef DEBUG
 
+/*
+ * Use unused space in the interrupt stack to save and restore
+ * registers for winkle support.
+ */
+#define _SDR1	GPR3
+#define _RPR	GPR4
+#define _SPURR	GPR5
+#define _PURR	GPR6
+#define _TSCR	GPR7
+#define _DSCR	GPR8
+#define _AMOR	GPR9
+#define _WORT	GPR10
+#define _WORC	GPR11
+
 /* Idle state entry routines */
 
 #define	IDLE_STATE_ENTER_SEQ(IDLE_INST)				\
@@ -37,8 +53,7 @@
 
 /*
  * Pass requested state in r3:
- * 	0 - nap
- * 	1 - sleep
+ *	r3 - PNV_THREAD_NAP/SLEEP/WINKLE
  *
  * To check IRQ_HAPPENED in r4
  * 	0 - don't check
@@ -101,18 +116,105 @@ _GLOBAL(power7_powersave_common)
 	std	r9,_MSR(r1)
 	std	r1,PACAR1(r13)
 
-_GLOBAL(power7_enter_nap_mode)
+	/*
+	 * Go to real mode to do the nap, as required by the architecture.
+	 * Also, we need to be in real mode before setting hwthread_state,
+	 * because as soon as we do that, another thread can switch
+	 * the MMU context to the guest.
+	 */
+	LOAD_REG_IMMEDIATE(r5, MSR_IDLE)
+	li	r6, MSR_RI
+	andc	r6, r9, r6
+	LOAD_REG_ADDR(r7, power7_enter_nap_mode)
+	mtmsrd	r6, 1		/* clear RI before setting SRR0/1 */
+	mtspr	SPRN_SRR0, r7
+	mtspr	SPRN_SRR1, r5
+	rfid
+
+	.globl	power7_enter_nap_mode
+power7_enter_nap_mode:
 #ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
 	/* Tell KVM we're napping */
 	li	r4,KVM_HWTHREAD_IN_NAP
 	stb	r4,HSTATE_HWTHREAD_STATE(r13)
 #endif
-	cmpwi	cr0,r3,1
-	beq	2f
+	stb	r3,PACA_THREAD_IDLE_STATE(r13)
+	cmpwi	cr3,r3,PNV_THREAD_SLEEP
+	bge	cr3,2f
 	IDLE_STATE_ENTER_SEQ(PPC_NAP)
 	/* No return */
-2:	IDLE_STATE_ENTER_SEQ(PPC_SLEEP)
-	/* No return */
+2:
+	/* Sleep or winkle */
+	lbz	r7,PACA_THREAD_MASK(r13)
+	ld	r14,PACA_CORE_IDLE_STATE_PTR(r13)
+lwarx_loop1:
+	lwarx	r15,0,r14
+	andc	r15,r15,r7			/* Clear thread bit */
+
+	andi.	r15,r15,PNV_CORE_IDLE_THREAD_BITS
+
+/*
+ * If cr0 = 0, then current thread is the last thread of the core entering
+ * sleep. Last thread needs to execute the hardware bug workaround code if
+ * required by the platform.
+ * Make the workaround call unconditionally here. The below branch call is
+ * patched out when the idle states are discovered if the platform does not
+ * require it.
+ */
+.global pnv_fastsleep_workaround_at_entry
+pnv_fastsleep_workaround_at_entry:
+	beq	fastsleep_workaround_at_entry
+
+	stwcx.	r15,0,r14
+	bne-	lwarx_loop1
+	isync
+
+common_enter: /* common code for all the threads entering sleep or winkle */
+	bgt	cr3,enter_winkle
+	IDLE_STATE_ENTER_SEQ(PPC_SLEEP)
+
+fastsleep_workaround_at_entry:
+	ori	r15,r15,PNV_CORE_IDLE_LOCK_BIT
+	stwcx.	r15,0,r14
+	bne-	lwarx_loop1
+	isync
+
+	/* Fast sleep workaround */
+	li	r3,1
+	li	r4,1
+	li	r0,OPAL_CONFIG_CPU_IDLE_STATE
+	bl	opal_call_realmode
+
+	/* Clear Lock bit */
+	li	r0,0
+	lwsync
+	stw	r0,0(r14)
+	b	common_enter
+
+enter_winkle:
+	/*
+	 * Note all register i.e per-core, per-subcore or per-thread is saved
+	 * here since any thread in the core might wake up first
+	 */
+	mfspr	r3,SPRN_SDR1
+	std	r3,_SDR1(r1)
+	mfspr	r3,SPRN_RPR
+	std	r3,_RPR(r1)
+	mfspr	r3,SPRN_SPURR
+	std	r3,_SPURR(r1)
+	mfspr	r3,SPRN_PURR
+	std	r3,_PURR(r1)
+	mfspr	r3,SPRN_TSCR
+	std	r3,_TSCR(r1)
+	mfspr	r3,SPRN_DSCR
+	std	r3,_DSCR(r1)
+	mfspr	r3,SPRN_AMOR
+	std	r3,_AMOR(r1)
+	mfspr	r3,SPRN_WORT
+	std	r3,_WORT(r1)
+	mfspr	r3,SPRN_WORC
+	std	r3,_WORC(r1)
+	IDLE_STATE_ENTER_SEQ(PPC_WINKLE)
 
 _GLOBAL(power7_idle)
 	/* Now check if user or arch enabled NAP mode */
@@ -125,48 +227,21 @@ _GLOBAL(power7_idle)
 
 _GLOBAL(power7_nap)
 	mr	r4,r3
-	li	r3,0
+	li	r3,PNV_THREAD_NAP
 	b	power7_powersave_common
 	/* No return */
 
 _GLOBAL(power7_sleep)
-	li	r3,1
+	li	r3,PNV_THREAD_SLEEP
 	li	r4,1
 	b	power7_powersave_common
 	/* No return */
 
-/*
- * Make opal call in realmode. This is a generic function to be called
- * from realmode from reset vector. It handles endianess.
- *
- * r13 - paca pointer
- * r1  - stack pointer
- * r3  - opal token
- */
-opal_call_realmode:
-	mflr	r12
-	std	r12,_LINK(r1)
-	ld	r2,PACATOC(r13)
-	/* Set opal return address */
-	LOAD_REG_ADDR(r0,return_from_opal_call)
-	mtlr	r0
-	/* Handle endian-ness */
-	li	r0,MSR_LE
-	mfmsr	r12
-	andc	r12,r12,r0
-	mtspr	SPRN_HSRR1,r12
-	mr	r0,r3			/* Move opal token to r0 */
-	LOAD_REG_ADDR(r11,opal)
-	ld	r12,8(r11)
-	ld	r2,0(r11)
-	mtspr	SPRN_HSRR0,r12
-	hrfid
-
-return_from_opal_call:
-	FIXUP_ENDIAN
-	ld	r0,_LINK(r1)
-	mtlr	r0
-	blr
+_GLOBAL(power7_winkle)
+	li	r3,3
+	li	r4,1
+	b	power7_powersave_common
+	/* No return */
 
 #define CHECK_HMI_INTERRUPT						\
 	mfspr	r0,SPRN_SRR1;						\
@@ -181,7 +256,7 @@ ALT_FTR_SECTION_END_NESTED_IFSET(CPU_FTR_ARCH_207S, 66);		\
 	ld	r2,PACATOC(r13);					\
 	ld	r1,PACAR1(r13);						\
 	std	r3,ORIG_GPR3(r1);	/* Save original r3 */		\
-	li	r3,OPAL_HANDLE_HMI;	/* Pass opal token argument*/	\
+	li	r0,OPAL_HANDLE_HMI;	/* Pass opal token argument*/	\
 	bl	opal_call_realmode;					\
 	ld	r3,ORIG_GPR3(r1);	/* Restore original r3 */	\
 20:	nop;
@@ -190,16 +265,190 @@ ALT_FTR_SECTION_END_NESTED_IFSET(CPU_FTR_ARCH_207S, 66);		\
 _GLOBAL(power7_wakeup_tb_loss)
 	ld	r2,PACATOC(r13);
 	ld	r1,PACAR1(r13)
+	/*
+	 * Before entering any idle state, the NVGPRs are saved in the stack
+	 * and they are restored before switching to the process context. Hence
+	 * until they are restored, they are free to be used.
+	 *
+	 * Save SRR1 in a NVGPR as it might be clobbered in opal_call_realmode
+	 * (called in CHECK_HMI_INTERRUPT). SRR1 is required to determine the
+	 * wakeup reason if we branch to kvm_start_guest.
+	 */
 
+	mfspr	r16,SPRN_SRR1
 BEGIN_FTR_SECTION
 	CHECK_HMI_INTERRUPT
 END_FTR_SECTION_IFSET(CPU_FTR_HVMODE)
+
+	lbz	r7,PACA_THREAD_MASK(r13)
+	ld	r14,PACA_CORE_IDLE_STATE_PTR(r13)
+lwarx_loop2:
+	lwarx	r15,0,r14
+	andi.	r9,r15,PNV_CORE_IDLE_LOCK_BIT
+	/*
+	 * Lock bit is set in one of the 2 cases-
+	 * a. In the sleep/winkle enter path, the last thread is executing
+	 * fastsleep workaround code.
+	 * b. In the wake up path, another thread is executing fastsleep
+	 * workaround undo code or resyncing timebase or restoring context
+	 * In either case loop until the lock bit is cleared.
+	 */
+	bne	core_idle_lock_held
+
+	cmpwi	cr2,r15,0
+	lbz	r4,PACA_SUBCORE_SIBLING_MASK(r13)
+	and	r4,r4,r15
+	cmpwi	cr1,r4,0	/* Check if first in subcore */
+
+	/*
+	 * At this stage
+	 * cr1 - 0b0100 if first thread to wakeup in subcore
+	 * cr2 - 0b0100 if first thread to wakeup in core
+	 * cr3-  0b0010 if waking up from sleep or winkle
+	 * cr4 - 0b0100 if waking up from winkle
+	 */
+
+	or	r15,r15,r7		/* Set thread bit */
+
+	beq	cr1,first_thread_in_subcore
+
+	/* Not first thread in subcore to wake up */
+	stwcx.	r15,0,r14
+	bne-	lwarx_loop2
+	isync
+	b	common_exit
+
+core_idle_lock_held:
+	HMT_LOW
+core_idle_lock_loop:
+	lwz	r15,0(14)
+	andi.   r9,r15,PNV_CORE_IDLE_LOCK_BIT
+	bne	core_idle_lock_loop
+	HMT_MEDIUM
+	b	lwarx_loop2
+
+first_thread_in_subcore:
+	/* First thread in subcore to wakeup */
+	ori	r15,r15,PNV_CORE_IDLE_LOCK_BIT
+	stwcx.	r15,0,r14
+	bne-	lwarx_loop2
+	isync
+
+	/*
+	 * If waking up from sleep, subcore state is not lost. Hence
+	 * skip subcore state restore
+	 */
+	bne	cr4,subcore_state_restored
+
+	/* Restore per-subcore state */
+	ld      r4,_SDR1(r1)
+	mtspr   SPRN_SDR1,r4
+	ld      r4,_RPR(r1)
+	mtspr   SPRN_RPR,r4
+	ld	r4,_AMOR(r1)
+	mtspr	SPRN_AMOR,r4
+
+subcore_state_restored:
+	/*
+	 * Check if the thread is also the first thread in the core. If not,
+	 * skip to clear_lock.
+	 */
+	bne	cr2,clear_lock
+
+first_thread_in_core:
+
+	/*
+	 * First thread in the core waking up from fastsleep. It needs to
+	 * call the fastsleep workaround code if the platform requires it.
+	 * Call it unconditionally here. The below branch instruction will
+	 * be patched out when the idle states are discovered if platform
+	 * does not require workaround.
+	 */
+.global pnv_fastsleep_workaround_at_exit
+pnv_fastsleep_workaround_at_exit:
+	b	fastsleep_workaround_at_exit
+
+timebase_resync:
+	/* Do timebase resync if we are waking up from sleep. Use cr3 value
+	 * set in exceptions-64s.S */
+	ble	cr3,clear_lock
 	/* Time base re-sync */
-	li	r3,OPAL_RESYNC_TIMEBASE
+	li	r0,OPAL_RESYNC_TIMEBASE
 	bl	opal_call_realmode;
-
 	/* TODO: Check r3 for failure */
 
+	/*
+	 * If waking up from sleep, per core state is not lost, skip to
+	 * clear_lock.
+	 */
+	bne	cr4,clear_lock
+
+	/* Restore per core state */
+	ld	r4,_TSCR(r1)
+	mtspr	SPRN_TSCR,r4
+	ld	r4,_WORC(r1)
+	mtspr	SPRN_WORC,r4
+
+clear_lock:
+	andi.	r15,r15,PNV_CORE_IDLE_THREAD_BITS
+	lwsync
+	stw	r15,0(r14)
+
+common_exit:
+	/*
+	 * Common to all threads.
+	 *
+	 * If waking up from sleep, hypervisor state is not lost. Hence
+	 * skip hypervisor state restore.
+	 */
+	bne	cr4,hypervisor_state_restored
+
+	/* Waking up from winkle */
+
+	/* Restore per thread state */
+	bl	__restore_cpu_power8
+
+	/* Restore SLB  from PACA */
+	ld	r8,PACA_SLBSHADOWPTR(r13)
+
+	.rept	SLB_NUM_BOLTED
+	li	r3, SLBSHADOW_SAVEAREA
+	LDX_BE	r5, r8, r3
+	addi	r3, r3, 8
+	LDX_BE	r6, r8, r3
+	andis.	r7,r5,SLB_ESID_V@h
+	beq	1f
+	slbmte	r6,r5
+1:	addi	r8,r8,16
+	.endr
+
+	ld	r4,_SPURR(r1)
+	mtspr	SPRN_SPURR,r4
+	ld	r4,_PURR(r1)
+	mtspr	SPRN_PURR,r4
+	ld	r4,_DSCR(r1)
+	mtspr	SPRN_DSCR,r4
+	ld	r4,_WORT(r1)
+	mtspr	SPRN_WORT,r4
+
+hypervisor_state_restored:
+
+	li	r5,PNV_THREAD_RUNNING
+	stb     r5,PACA_THREAD_IDLE_STATE(r13)
+
+	mtspr	SPRN_SRR1,r16
+#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
+	li      r0,KVM_HWTHREAD_IN_KERNEL
+	stb     r0,HSTATE_HWTHREAD_STATE(r13)
+	/* Order setting hwthread_state vs. testing hwthread_req */
+	sync
+	lbz     r0,HSTATE_HWTHREAD_REQ(r13)
+	cmpwi   r0,0
+	beq     6f
+	b       kvm_start_guest
+6:
+#endif
+
 	REST_NVGPRS(r1)
 	REST_GPR(2, r1)
 	ld	r3,_CCR(r1)
@@ -212,6 +461,13 @@ END_FTR_SECTION_IFSET(CPU_FTR_HVMODE)
 	mtspr	SPRN_SRR0,r5
 	rfid
 
+fastsleep_workaround_at_exit:
+	li	r3,1
+	li	r4,0
+	li	r0,OPAL_CONFIG_CPU_IDLE_STATE
+	bl	opal_call_realmode
+	b	timebase_resync
+
 /*
  * R3 here contains the value that will be returned to the caller
  * of power7_nap.
diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c
index 8b2d2dc8ef1..8ec017cb444 100644
--- a/arch/powerpc/kernel/smp.c
+++ b/arch/powerpc/kernel/smp.c
@@ -700,7 +700,6 @@ void start_secondary(void *unused)
 	smp_store_cpu_info(cpu);
 	set_dec(tb_ticks_per_jiffy);
 	preempt_disable();
-	cpu_callin_map[cpu] = 1;
 
 	if (smp_ops->setup_cpu)
 		smp_ops->setup_cpu(cpu);
@@ -739,6 +738,14 @@ void start_secondary(void *unused)
 	notify_cpu_starting(cpu);
 	set_cpu_online(cpu, true);
 
+	/*
+	 * CPU must be marked active and online before we signal back to the
+	 * master, because the scheduler needs to see the cpu_online and
+	 * cpu_active bits set.
+	 */
+	smp_wmb();
+	cpu_callin_map[cpu] = 1;
+
 	local_irq_enable();
 
 	cpu_startup_entry(CPUHP_ONLINE);
diff --git a/arch/powerpc/perf/hv-24x7.c b/arch/powerpc/perf/hv-24x7.c
index dba34088da2..f162d0b8eea 100644
--- a/arch/powerpc/perf/hv-24x7.c
+++ b/arch/powerpc/perf/hv-24x7.c
@@ -177,7 +177,7 @@ static ssize_t _name##_show(struct device *dev,			\
 	}							\
 	ret = sprintf(buf, _fmt, _expr);			\
 e_free:								\
-	kfree(page);						\
+	kmem_cache_free(hv_page_cache, page);			\
 	return ret;						\
 }								\
 static DEVICE_ATTR_RO(_name)
@@ -217,11 +217,14 @@ static bool is_physical_domain(int domain)
 		domain == HV_24X7_PERF_DOMAIN_PHYSICAL_CORE;
 }
 
+DEFINE_PER_CPU(char, hv_24x7_reqb[4096]) __aligned(4096);
+DEFINE_PER_CPU(char, hv_24x7_resb[4096]) __aligned(4096);
+
 static unsigned long single_24x7_request(u8 domain, u32 offset, u16 ix,
 					 u16 lpar, u64 *res,
 					 bool success_expected)
 {
-	unsigned long ret = -ENOMEM;
+	unsigned long ret;
 
 	/*
 	 * request_buffer and result_buffer are not required to be 4k aligned,
@@ -243,13 +246,11 @@ static unsigned long single_24x7_request(u8 domain, u32 offset, u16 ix,
 	BUILD_BUG_ON(sizeof(*request_buffer) > 4096);
 	BUILD_BUG_ON(sizeof(*result_buffer) > 4096);
 
-	request_buffer = kmem_cache_zalloc(hv_page_cache, GFP_USER);
-	if (!request_buffer)
-		goto out;
+	request_buffer = (void *)get_cpu_var(hv_24x7_reqb);
+	result_buffer = (void *)get_cpu_var(hv_24x7_resb);
 
-	result_buffer = kmem_cache_zalloc(hv_page_cache, GFP_USER);
-	if (!result_buffer)
-		goto out_free_request_buffer;
+	memset(request_buffer, 0, 4096);
+	memset(result_buffer, 0, 4096);
 
 	*request_buffer = (struct reqb) {
 		.buf = {
@@ -278,15 +279,11 @@ static unsigned long single_24x7_request(u8 domain, u32 offset, u16 ix,
 				domain, offset, ix, lpar, ret, ret,
 				result_buffer->buf.detailed_rc,
 				result_buffer->buf.failing_request_ix);
-		goto out_free_result_buffer;
+		goto out;
 	}
 
 	*res = be64_to_cpu(result_buffer->result);
 
-out_free_result_buffer:
-	kfree(result_buffer);
-out_free_request_buffer:
-	kfree(request_buffer);
 out:
 	return ret;
 }
diff --git a/arch/powerpc/platforms/powernv/opal-wrappers.S b/arch/powerpc/platforms/powernv/opal-wrappers.S
index 0a299be588a..54eca8b3b28 100644
--- a/arch/powerpc/platforms/powernv/opal-wrappers.S
+++ b/arch/powerpc/platforms/powernv/opal-wrappers.S
@@ -158,6 +158,43 @@ opal_tracepoint_return:
 	blr
 #endif
 
+/*
+ * Make opal call in realmode. This is a generic function to be called
+ * from realmode. It handles endianness.
+ *
+ * r13 - paca pointer
+ * r1  - stack pointer
+ * r0  - opal token
+ */
+_GLOBAL(opal_call_realmode)
+	mflr	r12
+	std	r12,PPC_LR_STKOFF(r1)
+	ld	r2,PACATOC(r13)
+	/* Set opal return address */
+	LOAD_REG_ADDR(r12,return_from_opal_call)
+	mtlr	r12
+
+	mfmsr	r12
+#ifdef __LITTLE_ENDIAN__
+	/* Handle endian-ness */
+	li	r11,MSR_LE
+	andc	r12,r12,r11
+#endif
+	mtspr	SPRN_HSRR1,r12
+	LOAD_REG_ADDR(r11,opal)
+	ld	r12,8(r11)
+	ld	r2,0(r11)
+	mtspr	SPRN_HSRR0,r12
+	hrfid
+
+return_from_opal_call:
+#ifdef __LITTLE_ENDIAN__
+	FIXUP_ENDIAN
+#endif
+	ld	r12,PPC_LR_STKOFF(r1)
+	mtlr	r12
+	blr
+
 OPAL_CALL(opal_invalid_call,			OPAL_INVALID_CALL);
 OPAL_CALL(opal_console_write,			OPAL_CONSOLE_WRITE);
 OPAL_CALL(opal_console_read,			OPAL_CONSOLE_READ);
@@ -247,6 +284,7 @@ OPAL_CALL(opal_sensor_read,			OPAL_SENSOR_READ);
 OPAL_CALL(opal_get_param,			OPAL_GET_PARAM);
 OPAL_CALL(opal_set_param,			OPAL_SET_PARAM);
 OPAL_CALL(opal_handle_hmi,			OPAL_HANDLE_HMI);
+OPAL_CALL(opal_slw_set_reg,			OPAL_SLW_SET_REG);
 OPAL_CALL(opal_register_dump_region,		OPAL_REGISTER_DUMP_REGION);
 OPAL_CALL(opal_unregister_dump_region,		OPAL_UNREGISTER_DUMP_REGION);
 OPAL_CALL(opal_pci_set_phb_cxl_mode,		OPAL_PCI_SET_PHB_CXL_MODE);
@@ -254,3 +292,4 @@ OPAL_CALL(opal_tpo_write,			OPAL_WRITE_TPO);
 OPAL_CALL(opal_tpo_read,			OPAL_READ_TPO);
 OPAL_CALL(opal_ipmi_send,			OPAL_IPMI_SEND);
 OPAL_CALL(opal_ipmi_recv,			OPAL_IPMI_RECV);
+OPAL_CALL(opal_i2c_request,			OPAL_I2C_REQUEST);
diff --git a/arch/powerpc/platforms/powernv/opal.c b/arch/powerpc/platforms/powernv/opal.c
index cb0b6de79cd..f10b9ec8c1f 100644
--- a/arch/powerpc/platforms/powernv/opal.c
+++ b/arch/powerpc/platforms/powernv/opal.c
@@ -9,8 +9,9 @@
  * 2 of the License, or (at your option) any later version.
  */
 
-#undef DEBUG
+#define pr_fmt(fmt)	"opal: " fmt
 
+#include <linux/printk.h>
 #include <linux/types.h>
 #include <linux/of.h>
 #include <linux/of_fdt.h>
@@ -625,6 +626,39 @@ static int opal_sysfs_init(void)
 	return 0;
 }
 
+static ssize_t symbol_map_read(struct file *fp, struct kobject *kobj,
+			       struct bin_attribute *bin_attr,
+			       char *buf, loff_t off, size_t count)
+{
+	return memory_read_from_buffer(buf, count, &off, bin_attr->private,
+				       bin_attr->size);
+}
+
+static BIN_ATTR_RO(symbol_map, 0);
+
+static void opal_export_symmap(void)
+{
+	const __be64 *syms;
+	unsigned int size;
+	struct device_node *fw;
+	int rc;
+
+	fw = of_find_node_by_path("/ibm,opal/firmware");
+	if (!fw)
+		return;
+	syms = of_get_property(fw, "symbol-map", &size);
+	if (!syms || size != 2 * sizeof(__be64))
+		return;
+
+	/* Setup attributes */
+	bin_attr_symbol_map.private = __va(be64_to_cpu(syms[0]));
+	bin_attr_symbol_map.size = be64_to_cpu(syms[1]);
+
+	rc = sysfs_create_bin_file(opal_kobj, &bin_attr_symbol_map);
+	if (rc)
+		pr_warn("Error %d creating OPAL symbols file\n", rc);
+}
+
 static void __init opal_dump_region_init(void)
 {
 	void *addr;
@@ -653,6 +687,14 @@ static void opal_ipmi_init(struct device_node *opal_node)
 			of_platform_device_create(np, NULL, NULL);
 }
 
+static void opal_i2c_create_devs(void)
+{
+	struct device_node *np;
+
+	for_each_compatible_node(np, NULL, "ibm,opal-i2c")
+		of_platform_device_create(np, NULL, NULL);
+}
+
 static int __init opal_init(void)
 {
 	struct device_node *np, *consoles;
@@ -679,6 +721,9 @@ static int __init opal_init(void)
 		of_node_put(consoles);
 	}
 
+	/* Create i2c platform devices */
+	opal_i2c_create_devs();
+
 	/* Find all OPAL interrupts and request them */
 	irqs = of_get_property(opal_node, "opal-interrupts", &irqlen);
 	pr_debug("opal: Found %d interrupts reserved for OPAL\n",
@@ -702,6 +747,8 @@ static int __init opal_init(void)
 	/* Create "opal" kobject under /sys/firmware */
 	rc = opal_sysfs_init();
 	if (rc == 0) {
+		/* Export symbol map to userspace */
+		opal_export_symmap();
 		/* Setup dump region interface */
 		opal_dump_region_init();
 		/* Setup error log interface */
@@ -824,3 +871,4 @@ EXPORT_SYMBOL_GPL(opal_rtc_read);
 EXPORT_SYMBOL_GPL(opal_rtc_write);
 EXPORT_SYMBOL_GPL(opal_tpo_read);
 EXPORT_SYMBOL_GPL(opal_tpo_write);
+EXPORT_SYMBOL_GPL(opal_i2c_request);
diff --git a/arch/powerpc/platforms/powernv/powernv.h b/arch/powerpc/platforms/powernv/powernv.h
index 6c8e2d188cd..604c48e7879 100644
--- a/arch/powerpc/platforms/powernv/powernv.h
+++ b/arch/powerpc/platforms/powernv/powernv.h
@@ -29,6 +29,8 @@ static inline u64 pnv_pci_dma_get_required_mask(struct pci_dev *pdev)
 }
 #endif
 
+extern u32 pnv_get_supported_cpuidle_states(void);
+
 extern void pnv_lpc_init(void);
 
 bool cpu_core_split_required(void);
diff --git a/arch/powerpc/platforms/powernv/setup.c b/arch/powerpc/platforms/powernv/setup.c
index 30b1c3e298a..b700a329c31 100644
--- a/arch/powerpc/platforms/powernv/setup.c
+++ b/arch/powerpc/platforms/powernv/setup.c
@@ -36,8 +36,12 @@
 #include <asm/opal.h>
 #include <asm/kexec.h>
 #include <asm/smp.h>
+#include <asm/cputhreads.h>
+#include <asm/cpuidle.h>
+#include <asm/code-patching.h>
 
 #include "powernv.h"
+#include "subcore.h"
 
 static void __init pnv_setup_arch(void)
 {
@@ -288,6 +292,168 @@ static void __init pnv_setup_machdep_rtas(void)
 }
 #endif /* CONFIG_PPC_POWERNV_RTAS */
 
+static u32 supported_cpuidle_states;
+
+int pnv_save_sprs_for_winkle(void)
+{
+	int cpu;
+	int rc;
+
+	/*
+	 * hid0, hid1, hid4, hid5, hmeer and lpcr values are symmetric accross
+	 * all cpus at boot. Get these reg values of current cpu and use the
+	 * same accross all cpus.
+	 */
+	uint64_t lpcr_val = mfspr(SPRN_LPCR);
+	uint64_t hid0_val = mfspr(SPRN_HID0);
+	uint64_t hid1_val = mfspr(SPRN_HID1);
+	uint64_t hid4_val = mfspr(SPRN_HID4);
+	uint64_t hid5_val = mfspr(SPRN_HID5);
+	uint64_t hmeer_val = mfspr(SPRN_HMEER);
+
+	for_each_possible_cpu(cpu) {
+		uint64_t pir = get_hard_smp_processor_id(cpu);
+		uint64_t hsprg0_val = (uint64_t)&paca[cpu];
+
+		/*
+		 * HSPRG0 is used to store the cpu's pointer to paca. Hence last
+		 * 3 bits are guaranteed to be 0. Program slw to restore HSPRG0
+		 * with 63rd bit set, so that when a thread wakes up at 0x100 we
+		 * can use this bit to distinguish between fastsleep and
+		 * deep winkle.
+		 */
+		hsprg0_val |= 1;
+
+		rc = opal_slw_set_reg(pir, SPRN_HSPRG0, hsprg0_val);
+		if (rc != 0)
+			return rc;
+
+		rc = opal_slw_set_reg(pir, SPRN_LPCR, lpcr_val);
+		if (rc != 0)
+			return rc;
+
+		/* HIDs are per core registers */
+		if (cpu_thread_in_core(cpu) == 0) {
+
+			rc = opal_slw_set_reg(pir, SPRN_HMEER, hmeer_val);
+			if (rc != 0)
+				return rc;
+
+			rc = opal_slw_set_reg(pir, SPRN_HID0, hid0_val);
+			if (rc != 0)
+				return rc;
+
+			rc = opal_slw_set_reg(pir, SPRN_HID1, hid1_val);
+			if (rc != 0)
+				return rc;
+
+			rc = opal_slw_set_reg(pir, SPRN_HID4, hid4_val);
+			if (rc != 0)
+				return rc;
+
+			rc = opal_slw_set_reg(pir, SPRN_HID5, hid5_val);
+			if (rc != 0)
+				return rc;
+		}
+	}
+
+	return 0;
+}
+
+static void pnv_alloc_idle_core_states(void)
+{
+	int i, j;
+	int nr_cores = cpu_nr_cores();
+	u32 *core_idle_state;
+
+	/*
+	 * core_idle_state - First 8 bits track the idle state of each thread
+	 * of the core. The 8th bit is the lock bit. Initially all thread bits
+	 * are set. They are cleared when the thread enters deep idle state
+	 * like sleep and winkle. Initially the lock bit is cleared.
+	 * The lock bit has 2 purposes
+	 * a. While the first thread is restoring core state, it prevents
+	 * other threads in the core from switching to process context.
+	 * b. While the last thread in the core is saving the core state, it
+	 * prevents a different thread from waking up.
+	 */
+	for (i = 0; i < nr_cores; i++) {
+		int first_cpu = i * threads_per_core;
+		int node = cpu_to_node(first_cpu);
+
+		core_idle_state = kmalloc_node(sizeof(u32), GFP_KERNEL, node);
+		*core_idle_state = PNV_CORE_IDLE_THREAD_BITS;
+
+		for (j = 0; j < threads_per_core; j++) {
+			int cpu = first_cpu + j;
+
+			paca[cpu].core_idle_state_ptr = core_idle_state;
+			paca[cpu].thread_idle_state = PNV_THREAD_RUNNING;
+			paca[cpu].thread_mask = 1 << j;
+		}
+	}
+
+	update_subcore_sibling_mask();
+
+	if (supported_cpuidle_states & OPAL_PM_WINKLE_ENABLED)
+		pnv_save_sprs_for_winkle();
+}
+
+u32 pnv_get_supported_cpuidle_states(void)
+{
+	return supported_cpuidle_states;
+}
+EXPORT_SYMBOL_GPL(pnv_get_supported_cpuidle_states);
+
+static int __init pnv_init_idle_states(void)
+{
+	struct device_node *power_mgt;
+	int dt_idle_states;
+	const __be32 *idle_state_flags;
+	u32 len_flags, flags;
+	int i;
+
+	supported_cpuidle_states = 0;
+
+	if (cpuidle_disable != IDLE_NO_OVERRIDE)
+		return 0;
+
+	if (!firmware_has_feature(FW_FEATURE_OPALv3))
+		return 0;
+
+	power_mgt = of_find_node_by_path("/ibm,opal/power-mgt");
+	if (!power_mgt) {
+		pr_warn("opal: PowerMgmt Node not found\n");
+		return 0;
+	}
+
+	idle_state_flags = of_get_property(power_mgt,
+			"ibm,cpu-idle-state-flags", &len_flags);
+	if (!idle_state_flags) {
+		pr_warn("DT-PowerMgmt: missing ibm,cpu-idle-state-flags\n");
+		return 0;
+	}
+
+	dt_idle_states = len_flags / sizeof(u32);
+
+	for (i = 0; i < dt_idle_states; i++) {
+		flags = be32_to_cpu(idle_state_flags[i]);
+		supported_cpuidle_states |= flags;
+	}
+	if (!(supported_cpuidle_states & OPAL_PM_SLEEP_ENABLED_ER1)) {
+		patch_instruction(
+			(unsigned int *)pnv_fastsleep_workaround_at_entry,
+			PPC_INST_NOP);
+		patch_instruction(
+			(unsigned int *)pnv_fastsleep_workaround_at_exit,
+			PPC_INST_NOP);
+	}
+	pnv_alloc_idle_core_states();
+	return 0;
+}
+
+subsys_initcall(pnv_init_idle_states);
+
 static int __init pnv_probe(void)
 {
 	unsigned long root = of_get_flat_dt_root();
diff --git a/arch/powerpc/platforms/powernv/smp.c b/arch/powerpc/platforms/powernv/smp.c
index b716f666e48..fc34025ef82 100644
--- a/arch/powerpc/platforms/powernv/smp.c
+++ b/arch/powerpc/platforms/powernv/smp.c
@@ -150,6 +150,7 @@ static void pnv_smp_cpu_kill_self(void)
 {
 	unsigned int cpu;
 	unsigned long srr1;
+	u32 idle_states;
 
 	/* Standard hot unplug procedure */
 	local_irq_disable();
@@ -160,13 +161,23 @@ static void pnv_smp_cpu_kill_self(void)
 	generic_set_cpu_dead(cpu);
 	smp_wmb();
 
+	idle_states = pnv_get_supported_cpuidle_states();
 	/* We don't want to take decrementer interrupts while we are offline,
 	 * so clear LPCR:PECE1. We keep PECE2 enabled.
 	 */
 	mtspr(SPRN_LPCR, mfspr(SPRN_LPCR) & ~(u64)LPCR_PECE1);
 	while (!generic_check_cpu_restart(cpu)) {
+
 		ppc64_runlatch_off();
-		srr1 = power7_nap(1);
+
+		if (idle_states & OPAL_PM_WINKLE_ENABLED)
+			srr1 = power7_winkle();
+		else if ((idle_states & OPAL_PM_SLEEP_ENABLED) ||
+				(idle_states & OPAL_PM_SLEEP_ENABLED_ER1))
+			srr1 = power7_sleep();
+		else
+			srr1 = power7_nap(1);
+
 		ppc64_runlatch_on();
 
 		/*
@@ -198,13 +209,27 @@ static void pnv_smp_cpu_kill_self(void)
 
 #endif /* CONFIG_HOTPLUG_CPU */
 
+static int pnv_cpu_bootable(unsigned int nr)
+{
+	/*
+	 * Starting with POWER8, the subcore logic relies on all threads of a
+	 * core being booted so that they can participate in split mode
+	 * switches. So on those machines we ignore the smt_enabled_at_boot
+	 * setting (smt-enabled on the kernel command line).
+	 */
+	if (cpu_has_feature(CPU_FTR_ARCH_207S))
+		return 1;
+
+	return smp_generic_cpu_bootable(nr);
+}
+
 static struct smp_ops_t pnv_smp_ops = {
 	.message_pass	= smp_muxed_ipi_message_pass,
 	.cause_ipi	= NULL,	/* Filled at runtime by xics_smp_probe() */
 	.probe		= xics_smp_probe,
 	.kick_cpu	= pnv_smp_kick_cpu,
 	.setup_cpu	= pnv_smp_setup_cpu,
-	.cpu_bootable	= smp_generic_cpu_bootable,
+	.cpu_bootable	= pnv_cpu_bootable,
 #ifdef CONFIG_HOTPLUG_CPU
 	.cpu_disable	= pnv_smp_cpu_disable,
 	.cpu_die	= generic_cpu_die,
diff --git a/arch/powerpc/platforms/powernv/subcore.c b/arch/powerpc/platforms/powernv/subcore.c
index c87f96b79d1..f60f80ada90 100644
--- a/arch/powerpc/platforms/powernv/subcore.c
+++ b/arch/powerpc/platforms/powernv/subcore.c
@@ -160,6 +160,18 @@ static void wait_for_sync_step(int step)
 	mb();
 }
 
+static void update_hid_in_slw(u64 hid0)
+{
+	u64 idle_states = pnv_get_supported_cpuidle_states();
+
+	if (idle_states & OPAL_PM_WINKLE_ENABLED) {
+		/* OPAL call to patch slw with the new HID0 value */
+		u64 cpu_pir = hard_smp_processor_id();
+
+		opal_slw_set_reg(cpu_pir, SPRN_HID0, hid0);
+	}
+}
+
 static void unsplit_core(void)
 {
 	u64 hid0, mask;
@@ -179,6 +191,7 @@ static void unsplit_core(void)
 	hid0 = mfspr(SPRN_HID0);
 	hid0 &= ~HID0_POWER8_DYNLPARDIS;
 	mtspr(SPRN_HID0, hid0);
+	update_hid_in_slw(hid0);
 
 	while (mfspr(SPRN_HID0) & mask)
 		cpu_relax();
@@ -215,6 +228,7 @@ static void split_core(int new_mode)
 	hid0  = mfspr(SPRN_HID0);
 	hid0 |= HID0_POWER8_DYNLPARDIS | split_parms[i].value;
 	mtspr(SPRN_HID0, hid0);
+	update_hid_in_slw(hid0);
 
 	/* Wait for it to happen */
 	while (!(mfspr(SPRN_HID0) & split_parms[i].mask))
@@ -251,6 +265,25 @@ bool cpu_core_split_required(void)
 	return true;
 }
 
+void update_subcore_sibling_mask(void)
+{
+	int cpu;
+	/*
+	 * sibling mask for the first cpu. Left shift this by required bits
+	 * to get sibling mask for the rest of the cpus.
+	 */
+	int sibling_mask_first_cpu =  (1 << threads_per_subcore) - 1;
+
+	for_each_possible_cpu(cpu) {
+		int tid = cpu_thread_in_core(cpu);
+		int offset = (tid / threads_per_subcore) * threads_per_subcore;
+		int mask = sibling_mask_first_cpu << offset;
+
+		paca[cpu].subcore_sibling_mask = mask;
+
+	}
+}
+
 static int cpu_update_split_mode(void *data)
 {
 	int cpu, new_mode = *(int *)data;
@@ -284,6 +317,7 @@ static int cpu_update_split_mode(void *data)
 		/* Make the new mode public */
 		subcores_per_core = new_mode;
 		threads_per_subcore = threads_per_core / subcores_per_core;
+		update_subcore_sibling_mask();
 
 		/* Make sure the new mode is written before we exit */
 		mb();
diff --git a/arch/powerpc/platforms/powernv/subcore.h b/arch/powerpc/platforms/powernv/subcore.h
index 148abc91deb..84e02ae5289 100644
--- a/arch/powerpc/platforms/powernv/subcore.h
+++ b/arch/powerpc/platforms/powernv/subcore.h
@@ -14,5 +14,12 @@
 #define SYNC_STEP_FINISHED	3	/* Set by secondary when split/unsplit is done */
 
 #ifndef __ASSEMBLY__
+
+#ifdef CONFIG_SMP
 void split_core_secondary_loop(u8 *state);
-#endif
+extern void update_subcore_sibling_mask(void);
+#else
+static inline void update_subcore_sibling_mask(void) { };
+#endif /* CONFIG_SMP */
+
+#endif /* __ASSEMBLY__ */