[RFC PATCH v3] powerpc/64s: Move idle code to powernv C code

Nicholas Piggin npiggin at gmail.com
Tue Jul 31 23:42:04 AEST 2018


Reimplement Book3S idle code to C, in the powernv platform code.
Assembly stubs are used to save and restore the stack frame and
non-volatile GPRs before going to idle, but these are small and
mostly agnostic to microarchitecture implementation details.

The optimisation where EC=ESL=0 idle modes did not have to save
GPRs or mtmsrd L=0 is restored, because it's simple to do.

Idle wakeup no longer uses the ->cpu_restore call to reinit SPRs,
but saves and restores them all explicitly. This can easily be
extended to tracking the set of system-wide SPRs that do not have
to be saved each time.

Moving the HMI, SPR, OPAL, locking, etc. to C is the only real
way this stuff will cope with non-trivial new CPU implementation
details, firmware changes, etc., without becoming unmaintainable.

Since RFC v1:
- Now tested and working with POWER9 hash and radix.
- KVM support added. This took a bit of work to untangle and might
  still have some issues, but POWER9 seems to work including hash on
  radix with dependent threads mode.
- This snowballed a bit because of KVM and other details making it
  not feasible to leave POWER7/8 code alone. That's only half done
  at the moment.
- So far this trades about 800 lines of asm for 500 of C. With POWER7/8
  support done it might be another hundred or so lines of C.

Since RFC v2:
- Fixed deep state SLB reloading
- Now tested and working with POWER8.
- Accounted for most feedback.

Thanks,
Nick

---
 include/asm/book3s/64/mmu-hash.h |    1 
 include/asm/cpuidle.h            |   21 
 include/asm/paca.h               |   40 -
 include/asm/processor.h          |    9 
 include/asm/reg.h                |    7 
 kernel/asm-offsets.c             |   18 
 kernel/dt_cpu_ftrs.c             |   21 
 kernel/exceptions-64s.S          |   17 
 kernel/idle_book3s.S             |  998 +++------------------------------------
 kernel/setup-common.c            |    4 
 kvm/book3s_hv_rmhandlers.S       |   94 ++-
 mm/slb.c                         |   15 
 platforms/powernv/idle.c         |  839 ++++++++++++++++++++++++++------
 platforms/powernv/subcore.c      |    2 
 xmon/xmon.c                      |   25 
 15 files changed, 902 insertions(+), 1209 deletions(-)

diff --git a/arch/powerpc/include/asm/book3s/64/mmu-hash.h b/arch/powerpc/include/asm/book3s/64/mmu-hash.h
index 50ed64fba4ae..b68a4fe446d6 100644
--- a/arch/powerpc/include/asm/book3s/64/mmu-hash.h
+++ b/arch/powerpc/include/asm/book3s/64/mmu-hash.h
@@ -487,6 +487,7 @@ extern void hpte_init_native(void);
 
 extern void slb_initialize(void);
 extern void slb_flush_and_rebolt(void);
+extern void slb_shadow_reload(void);
 
 extern void slb_vmalloc_update(void);
 extern void slb_set_size(u16 size);
diff --git a/arch/powerpc/include/asm/cpuidle.h b/arch/powerpc/include/asm/cpuidle.h
index e210a83eb196..9b5c7ec908f2 100644
--- a/arch/powerpc/include/asm/cpuidle.h
+++ b/arch/powerpc/include/asm/cpuidle.h
@@ -27,10 +27,11 @@
  * the THREAD_WINKLE_BITS are set, which indicate which threads have not
  * yet woken from the winkle state.
  */
-#define PNV_CORE_IDLE_LOCK_BIT			0x10000000
+#define NR_PNV_CORE_IDLE_LOCK_BIT		28
+#define PNV_CORE_IDLE_LOCK_BIT			(1ULL << NR_PNV_CORE_IDLE_LOCK_BIT)
 
+#define PNV_CORE_IDLE_WINKLE_COUNT_SHIFT	16
 #define PNV_CORE_IDLE_WINKLE_COUNT		0x00010000
-#define PNV_CORE_IDLE_WINKLE_COUNT_ALL_BIT	0x00080000
 #define PNV_CORE_IDLE_WINKLE_COUNT_BITS		0x000F0000
 #define PNV_CORE_IDLE_THREAD_WINKLE_BITS_SHIFT	8
 #define PNV_CORE_IDLE_THREAD_WINKLE_BITS	0x0000FF00
@@ -68,22 +69,6 @@
 #define ERR_DEEP_STATE_ESL_MISMATCH	-2
 
 #ifndef __ASSEMBLY__
-/* Additional SPRs that need to be saved/restored during stop */
-struct stop_sprs {
-	u64 pid;
-	u64 ldbar;
-	u64 fscr;
-	u64 hfscr;
-	u64 mmcr1;
-	u64 mmcr2;
-	u64 mmcra;
-};
-
-extern u32 pnv_fastsleep_workaround_at_entry[];
-extern u32 pnv_fastsleep_workaround_at_exit[];
-
-extern u64 pnv_first_deep_stop_state;
-
 unsigned long pnv_cpu_offline(unsigned int cpu);
 int validate_psscr_val_mask(u64 *psscr_val, u64 *psscr_mask, u32 flags);
 static inline void report_invalid_psscr_val(u64 psscr_val, int err)
diff --git a/arch/powerpc/include/asm/paca.h b/arch/powerpc/include/asm/paca.h
index 4e9cede5a7e7..d2cee5ebaaa1 100644
--- a/arch/powerpc/include/asm/paca.h
+++ b/arch/powerpc/include/asm/paca.h
@@ -168,7 +168,6 @@ struct paca_struct {
 	u8 irq_happened;		/* irq happened while soft-disabled */
 	u8 io_sync;			/* writel() needs spin_unlock sync */
 	u8 irq_work_pending;		/* IRQ_WORK interrupt while soft-disable */
-	u8 nap_state_lost;		/* NV GPR values lost in power7_idle */
 #ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
 	u8 pmcregs_in_use;		/* pseries puts this in lppaca */
 #endif
@@ -178,23 +177,30 @@ struct paca_struct {
 #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;
-	/* Flag to request this thread not to stop */
-	atomic_t dont_stop;
-	/* The PSSCR value that the kernel requested before going to stop */
-	u64 requested_psscr;
+	/* PowerNV idle fields */
+	/* PNV_CORE_IDLE_* bits, all siblings work on thread 0 paca */
+	unsigned long idle_state;
+	union {
+		/* P7/P8 specific fields */
+		struct {
+			/* PNV_THREAD_RUNNING/NAP/SLEEP	*/
+			u8 thread_idle_state;
+			/* Mask to indicate thread id in core */
+			u8 thread_mask;
+			/* Mask to denote subcore sibling threads */
+			u8 subcore_sibling_mask;
+		};
 
-	/*
-	 * Save area for additional SPRs that need to be
-	 * saved/restored during cpuidle stop.
-	 */
-	struct stop_sprs stop_sprs;
+		/* P9 specific fields */
+		struct {
+#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
+			/* The PSSCR value that the kernel requested before going to stop */
+			u64 requested_psscr;
+			/* Flag to request this thread not to stop */
+			atomic_t dont_stop;
+#endif
+		};
+	};
 #endif
 
 #ifdef CONFIG_PPC_BOOK3S_64
diff --git a/arch/powerpc/include/asm/processor.h b/arch/powerpc/include/asm/processor.h
index 5debe337ea9d..1d241f4d8612 100644
--- a/arch/powerpc/include/asm/processor.h
+++ b/arch/powerpc/include/asm/processor.h
@@ -507,14 +507,17 @@ static inline unsigned long get_clean_sp(unsigned long sp, int is_32)
 }
 #endif
 
+/* asm stubs */
+extern unsigned long isa3_idle_stop_noloss(unsigned long psscr_val);
+extern unsigned long isa3_idle_stop_mayloss(unsigned long psscr_val);
+extern unsigned long isa206_idle_insn_mayloss(unsigned long type);
+
 extern unsigned long cpuidle_disable;
 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_idle_insn(unsigned long type); /* PNV_THREAD_NAP/etc*/
+
 extern void power7_idle_type(unsigned long type);
-extern unsigned long power9_idle_stop(unsigned long psscr_val);
-extern unsigned long power9_offline_stop(unsigned long psscr_val);
 extern void power9_idle_type(unsigned long stop_psscr_val,
 			      unsigned long stop_psscr_mask);
 
diff --git a/arch/powerpc/include/asm/reg.h b/arch/powerpc/include/asm/reg.h
index d85d000d05b5..76513a2a2192 100644
--- a/arch/powerpc/include/asm/reg.h
+++ b/arch/powerpc/include/asm/reg.h
@@ -753,10 +753,9 @@
 #define	  SRR1_WAKERESET	0x00100000 /* System reset */
 #define   SRR1_WAKEHDBELL	0x000c0000 /* Hypervisor doorbell on P8 */
 #define	  SRR1_WAKESTATE	0x00030000 /* Powersave exit mask [46:47] */
-#define	  SRR1_WS_DEEPEST	0x00030000 /* Some resources not maintained,
-					  * may not be recoverable */
-#define	  SRR1_WS_DEEPER	0x00020000 /* Some resources not maintained */
-#define	  SRR1_WS_DEEP		0x00010000 /* All resources maintained */
+#define	  SRR1_WS_HVLOSS	0x00030000 /* HV resources not maintained */
+#define	  SRR1_WS_GPRLOSS	0x00020000 /* GPRs not maintained */
+#define	  SRR1_WS_NOLOSS	0x00010000 /* All resources maintained */
 #define   SRR1_PROGTM		0x00200000 /* TM Bad Thing */
 #define   SRR1_PROGFPE		0x00100000 /* Floating Point Enabled */
 #define   SRR1_PROGILL		0x00080000 /* Illegal instruction */
diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c
index 89cf15566c4e..7834256585f1 100644
--- a/arch/powerpc/kernel/asm-offsets.c
+++ b/arch/powerpc/kernel/asm-offsets.c
@@ -256,7 +256,6 @@ int main(void)
 	OFFSET(ACCOUNT_USER_TIME, paca_struct, accounting.utime);
 	OFFSET(ACCOUNT_SYSTEM_TIME, paca_struct, accounting.stime);
 	OFFSET(PACA_TRAP_SAVE, paca_struct, trap_save);
-	OFFSET(PACA_NAPSTATELOST, paca_struct, nap_state_lost);
 	OFFSET(PACA_SPRG_VDSO, paca_struct, sprg_vdso);
 #else /* CONFIG_PPC64 */
 #ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE
@@ -761,23 +760,6 @@ int main(void)
 	OFFSET(VCPU_TIMING_LAST_ENTER_TBL, kvm_vcpu, arch.timing_last_enter.tv32.tbl);
 #endif
 
-#ifdef CONFIG_PPC_POWERNV
-	OFFSET(PACA_CORE_IDLE_STATE_PTR, paca_struct, core_idle_state_ptr);
-	OFFSET(PACA_THREAD_IDLE_STATE, paca_struct, thread_idle_state);
-	OFFSET(PACA_THREAD_MASK, paca_struct, thread_mask);
-	OFFSET(PACA_SUBCORE_SIBLING_MASK, paca_struct, subcore_sibling_mask);
-	OFFSET(PACA_REQ_PSSCR, paca_struct, requested_psscr);
-	OFFSET(PACA_DONT_STOP, paca_struct, dont_stop);
-#define STOP_SPR(x, f)	OFFSET(x, paca_struct, stop_sprs.f)
-	STOP_SPR(STOP_PID, pid);
-	STOP_SPR(STOP_LDBAR, ldbar);
-	STOP_SPR(STOP_FSCR, fscr);
-	STOP_SPR(STOP_HFSCR, hfscr);
-	STOP_SPR(STOP_MMCR1, mmcr1);
-	STOP_SPR(STOP_MMCR2, mmcr2);
-	STOP_SPR(STOP_MMCRA, mmcra);
-#endif
-
 	DEFINE(PPC_DBELL_SERVER, PPC_DBELL_SERVER);
 	DEFINE(PPC_DBELL_MSGTYPE, PPC_DBELL_MSGTYPE);
 
diff --git a/arch/powerpc/kernel/dt_cpu_ftrs.c b/arch/powerpc/kernel/dt_cpu_ftrs.c
index f432054234a4..d635d78facdc 100644
--- a/arch/powerpc/kernel/dt_cpu_ftrs.c
+++ b/arch/powerpc/kernel/dt_cpu_ftrs.c
@@ -71,7 +71,6 @@ static int hv_mode;
 
 static struct {
 	u64	lpcr;
-	u64	lpcr_clear;
 	u64	hfscr;
 	u64	fscr;
 } system_registers;
@@ -80,24 +79,7 @@ static void (*init_pmu_registers)(void);
 
 static void __restore_cpu_cpufeatures(void)
 {
-	u64 lpcr;
-
-	/*
-	 * LPCR is restored by the power on engine already. It can be changed
-	 * after early init e.g., by radix enable, and we have no unified API
-	 * for saving and restoring such SPRs.
-	 *
-	 * This ->restore hook should really be removed from idle and register
-	 * restore moved directly into the idle restore code, because this code
-	 * doesn't know how idle is implemented or what it needs restored here.
-	 *
-	 * The best we can do to accommodate secondary boot and idle restore
-	 * for now is "or" LPCR with existing.
-	 */
-	lpcr = mfspr(SPRN_LPCR);
-	lpcr |= system_registers.lpcr;
-	lpcr &= ~system_registers.lpcr_clear;
-	mtspr(SPRN_LPCR, lpcr);
+	mtspr(SPRN_LPCR, system_registers.lpcr);
 	if (hv_mode) {
 		mtspr(SPRN_LPID, 0);
 		mtspr(SPRN_HFSCR, system_registers.hfscr);
@@ -318,7 +300,6 @@ static int __init feat_enable_mmu_hash_v3(struct dt_cpu_feature *f)
 {
 	u64 lpcr;
 
-	system_registers.lpcr_clear |= (LPCR_ISL | LPCR_UPRT | LPCR_HR);
 	lpcr = mfspr(SPRN_LPCR);
 	lpcr &= ~(LPCR_ISL | LPCR_UPRT | LPCR_HR);
 	mtspr(SPRN_LPCR, lpcr);
diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S
index 76a14702cb9c..137f0f446472 100644
--- a/arch/powerpc/kernel/exceptions-64s.S
+++ b/arch/powerpc/kernel/exceptions-64s.S
@@ -135,8 +135,9 @@ TRAMP_KVM(PACA_EXNMI, 0x100)
 
 #ifdef CONFIG_PPC_P7_NAP
 EXC_COMMON_BEGIN(system_reset_idle_common)
-	mfspr	r12,SPRN_SRR1
-	b	pnv_powersave_wakeup
+	mfspr	r3,SPRN_SRR1
+	bltlr	cr3	/* no state loss, return to idle caller */
+	b	idle_return_gpr_loss
 #endif
 
 /*
@@ -415,17 +416,17 @@ EXC_COMMON_BEGIN(machine_check_idle_common)
 	 * Then decrement MCE nesting after finishing with the stack.
 	 */
 	ld	r3,_MSR(r1)
+	ld	r4,_LINK(r1)
 
 	lhz	r11,PACA_IN_MCE(r13)
 	subi	r11,r11,1
 	sth	r11,PACA_IN_MCE(r13)
 
-	/* Turn off the RI bit because SRR1 is used by idle wakeup code. */
-	/* Recoverability could be improved by reducing the use of SRR1. */
-	li	r11,0
-	mtmsrd	r11,1
-
-	b	pnv_powersave_wakeup_mce
+	mtlr	r4
+	rlwinm	r10,r3,47-31,30,31
+	cmpwi	cr3,r10,2
+	bltlr	cr3	/* no state loss, return to idle caller */
+	b	idle_return_gpr_loss
 #endif
 	/*
 	 * Handle machine check early in real mode. We come here with
diff --git a/arch/powerpc/kernel/idle_book3s.S b/arch/powerpc/kernel/idle_book3s.S
index 672ead80c702..618251b0dd1e 100644
--- a/arch/powerpc/kernel/idle_book3s.S
+++ b/arch/powerpc/kernel/idle_book3s.S
@@ -1,6 +1,7 @@
 /*
- *  This file contains idle entry/exit functions for POWER7,
- *  POWER8 and POWER9 CPUs.
+ *  This file contains general idle entry/exit functions. The platform / CPU
+ *  must call the correct save/restore functions and ensure SPRs are saved
+ *  and restored correctly, handle KVM, interrupts, etc.
  *
  *  This program is free software; you can redistribute it and/or
  *  modify it under the terms of the GNU General Public License
@@ -8,218 +9,69 @@
  *  2 of the License, or (at your option) any later version.
  */
 
-#include <linux/threads.h>
-#include <asm/processor.h>
-#include <asm/page.h>
-#include <asm/cputable.h>
-#include <asm/thread_info.h>
 #include <asm/ppc_asm.h>
 #include <asm/asm-offsets.h>
 #include <asm/ppc-opcode.h>
-#include <asm/hw_irq.h>
-#include <asm/kvm_book3s_asm.h>
-#include <asm/opal.h>
 #include <asm/cpuidle.h>
-#include <asm/exception-64s.h>
-#include <asm/book3s/64/mmu-hash.h>
-#include <asm/mmu.h>
-
-#undef DEBUG
-
-/*
- * Use unused space in the interrupt stack to save and restore
- * registers for winkle support.
- */
-#define _MMCR0	GPR0
-#define _SDR1	GPR3
-#define _PTCR	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
-#define _LPCR	GPR12
-
-#define PSSCR_EC_ESL_MASK_SHIFTED          (PSSCR_EC | PSSCR_ESL) >> 16
-
-	.text
 
 /*
- * Used by threads before entering deep idle states. Saves SPRs
- * in interrupt stack frame
- */
-save_sprs_to_stack:
-	/*
-	 * 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
-	 */
-BEGIN_FTR_SECTION
-	/*
-	 * Note - SDR1 is dropped in Power ISA v3. Hence not restoring
-	 * SDR1 here
-	 */
-	mfspr	r3,SPRN_PTCR
-	std	r3,_PTCR(r1)
-	mfspr	r3,SPRN_LPCR
-	std	r3,_LPCR(r1)
-FTR_SECTION_ELSE
-	mfspr	r3,SPRN_SDR1
-	std	r3,_SDR1(r1)
-ALT_FTR_SECTION_END_IFSET(CPU_FTR_ARCH_300)
-	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)
-/*
- * On POWER9, there are idle states such as stop4, invoked via cpuidle,
- * that lose hypervisor resources. In such cases, we need to save
- * additional SPRs before entering those idle states so that they can
- * be restored to their older values on wakeup from the idle state.
+ * Desired PSSCR in r3
+ *
+ * No state will be lost regardless of wakeup mechanism (interrupt or NIA).
+ * Interrupt driven wakeup may clobber volatiles, and should blr (with LR
+ * unchanged) to return to caller with r3 set according to caller's expected
+ * return code (for Book3S/64 that is SRR1).
  *
- * On POWER8, the only such deep idle state is winkle which is used
- * only in the context of CPU-Hotplug, where these additional SPRs are
- * reinitiazed to a sane value. Hence there is no need to save/restore
- * these SPRs.
+ * Caller is responsible for restoring SPRs, MSR, etc.
  */
-BEGIN_FTR_SECTION
-	blr
-END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_300)
-
-power9_save_additional_sprs:
-	mfspr	r3, SPRN_PID
-	mfspr	r4, SPRN_LDBAR
-	std	r3, STOP_PID(r13)
-	std	r4, STOP_LDBAR(r13)
-
-	mfspr	r3, SPRN_FSCR
-	mfspr	r4, SPRN_HFSCR
-	std	r3, STOP_FSCR(r13)
-	std	r4, STOP_HFSCR(r13)
-
-	mfspr	r3, SPRN_MMCRA
-	mfspr	r4, SPRN_MMCR0
-	std	r3, STOP_MMCRA(r13)
-	std	r4, _MMCR0(r1)
-
-	mfspr	r3, SPRN_MMCR1
-	mfspr	r4, SPRN_MMCR2
-	std	r3, STOP_MMCR1(r13)
-	std	r4, STOP_MMCR2(r13)
-	blr
-
-power9_restore_additional_sprs:
-	ld	r3,_LPCR(r1)
-	ld	r4, STOP_PID(r13)
-	mtspr	SPRN_LPCR,r3
-	mtspr	SPRN_PID, r4
-
-	ld	r3, STOP_LDBAR(r13)
-	ld	r4, STOP_FSCR(r13)
-	mtspr	SPRN_LDBAR, r3
-	mtspr	SPRN_FSCR, r4
-
-	ld	r3, STOP_HFSCR(r13)
-	ld	r4, STOP_MMCRA(r13)
-	mtspr	SPRN_HFSCR, r3
-	mtspr	SPRN_MMCRA, r4
-
-	ld	r3, _MMCR0(r1)
-	ld	r4, STOP_MMCR1(r13)
-	mtspr	SPRN_MMCR0, r3
-	mtspr	SPRN_MMCR1, r4
-
-	ld	r3, STOP_MMCR2(r13)
-	ld	r4, PACA_SPRG_VDSO(r13)
-	mtspr	SPRN_MMCR2, r3
-	mtspr	SPRN_SPRG3, r4
+_GLOBAL(isa3_idle_stop_noloss)
+	mtspr 	SPRN_PSSCR,r3
+	PPC_STOP
+	li	r3,0
 	blr
 
 /*
- * Used by threads when the lock bit of core_idle_state is set.
- * Threads will spin in HMT_LOW until the lock bit is cleared.
- * r14 - pointer to core_idle_state
- * r15 - used to load contents of core_idle_state
- * r9  - used as a temporary variable
+ * Desired PSSCR in r3
+ *
+ * GPRs may be lost, so they are saved here. Wakeup is by interrupt only.
+ * Wakeup can return to caller by calling isa3_idle_wake_gpr_loss with r3 set
+ * to return value.
+ *
+ * A wakeup without GPR loss may alterateively be handled as in
+ * isa3_idle_stop_noloss as an optimisation.
+ *
+ * Caller is responsible for restoring SPRs, MSR, etc.
  */
-
-core_idle_lock_held:
-	HMT_LOW
-3:	lwz	r15,0(r14)
-	andis.	r15,r15,PNV_CORE_IDLE_LOCK_BIT at h
-	bne	3b
-	HMT_MEDIUM
-	lwarx	r15,0,r14
-	andis.	r9,r15,PNV_CORE_IDLE_LOCK_BIT at h
-	bne-	core_idle_lock_held
-	blr
+_GLOBAL(isa3_idle_stop_mayloss)
+	mtspr 	SPRN_PSSCR,r3
+	std	r1,PACAR1(r13)
+	mflr	r4
+	mfcr	r5
+	/* use stack red zone rather than a new frame */
+	addi	r6,r1,-INT_FRAME_SIZE
+	SAVE_GPR(2, r6)
+	SAVE_NVGPRS(r6)
+	std	r4,_LINK(r6)
+	std	r5,_CCR(r6)
+	PPC_STOP
+	b	.	/* catch bugs */
 
 /*
- * Pass requested state in r3:
- *	r3 - PNV_THREAD_NAP/SLEEP/WINKLE in POWER8
- *	   - Requested PSSCR value in POWER9
+ * Desired return value in r3
  *
- * Address of idle handler to branch to in realmode in r4
+ * Idle wakeup can call this after calling isa3_idle_stop_loss to
+ * return to caller with r3 as return code.
  */
-pnv_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
-	 * need to save PC, some CR bits and the NV GPRs,
-	 * but for now an interrupt frame will do.
-	 */
-	mtctr	r4
-
-	mflr	r0
-	std	r0,16(r1)
-	stdu	r1,-INT_FRAME_SIZE(r1)
-	std	r0,_LINK(r1)
-	std	r0,_NIP(r1)
-
-	/* We haven't lost state ... yet */
-	li	r0,0
-	stb	r0,PACA_NAPSTATELOST(r13)
-
-	/* Continue saving state */
-	SAVE_GPR(2, r1)
-	SAVE_NVGPRS(r1)
-	mfcr	r5
-	std	r5,_CCR(r1)
-	std	r1,PACAR1(r13)
-
-BEGIN_FTR_SECTION
-	/*
-	 * POWER9 does not require real mode to stop, and presently does not
-	 * set hwthread_state for KVM (threads don't share MMU context), so
-	 * we can remain in virtual mode for this.
-	 */
-	bctr
-END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300)
-	/*
-	 * POWER8
-	 * 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(r7, MSR_IDLE)
-	mtmsrd	r7,0
-	bctr
+_GLOBAL(idle_return_gpr_loss)
+	ld	r1,PACAR1(r13)
+	addi	r6,r1,-INT_FRAME_SIZE
+	ld	r4,_LINK(r6)
+	ld	r5,_CCR(r6)
+	REST_NVGPRS(r6)
+	REST_GPR(2, r6)
+	mtlr	r4
+	mtcr	r5
+	blr
 
 /*
  * This is the sequence required to execute idle instructions, as
@@ -232,723 +84,53 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300)
 	ld	r0,0(r1);					\
 236:	cmpd	cr0,r0,r0;					\
 	bne	236b;						\
-	IDLE_INST;
-
-
-	.globl pnv_enter_arch207_idle_mode
-pnv_enter_arch207_idle_mode:
-#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
-	/* Tell KVM we're entering idle */
-	li	r4,KVM_HWTHREAD_IN_IDLE
-	/******************************************************/
-	/*  N O T E   W E L L    ! ! !    N O T E   W E L L   */
-	/* The following store to HSTATE_HWTHREAD_STATE(r13)  */
-	/* MUST occur in real mode, i.e. with the MMU off,    */
-	/* and the MMU must stay off until we clear this flag */
-	/* and test HSTATE_HWTHREAD_REQ(r13) in               */
-	/* pnv_powersave_wakeup in this file.                 */
-	/* The reason is that another thread can switch the   */
-	/* MMU to a guest context whenever this flag is set   */
-	/* to KVM_HWTHREAD_IN_IDLE, and if the MMU was on,    */
-	/* that would potentially cause this thread to start  */
-	/* executing instructions from guest memory in        */
-	/* hypervisor mode, leading to a host crash or data   */
-	/* corruption, or worse.                              */
-	/******************************************************/
-	stb	r4,HSTATE_HWTHREAD_STATE(r13)
-#endif
-	stb	r3,PACA_THREAD_IDLE_STATE(r13)
-	cmpwi	cr3,r3,PNV_THREAD_SLEEP
-	bge	cr3,2f
-	IDLE_STATE_ENTER_SEQ_NORET(PPC_NAP)
-	/* No return */
-2:
-	/* Sleep or winkle */
-	lbz	r7,PACA_THREAD_MASK(r13)
-	ld	r14,PACA_CORE_IDLE_STATE_PTR(r13)
-	li	r5,0
-	beq	cr3,3f
-	lis	r5,PNV_CORE_IDLE_WINKLE_COUNT at h
-3:
-lwarx_loop1:
-	lwarx	r15,0,r14
-
-	andis.	r9,r15,PNV_CORE_IDLE_LOCK_BIT at h
-	bnel-	core_idle_lock_held
-
-	add	r15,r15,r5			/* Add if winkle */
-	andc	r15,r15,r7			/* Clear thread bit */
-
-	andi.	r9,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_NORET(PPC_SLEEP)
-
-fastsleep_workaround_at_entry:
-	oris	r15,r15,PNV_CORE_IDLE_LOCK_BIT at h
-	stwcx.	r15,0,r14
-	bne-	lwarx_loop1
-	isync
+	IDLE_INST;						\
+	b	.	/* catch bugs */
 
-	/* Fast sleep workaround */
-	li	r3,1
-	li	r4,1
-	bl	opal_config_cpu_idle_state
-
-	/* Unlock */
-	xoris	r15,r15,PNV_CORE_IDLE_LOCK_BIT at h
-	lwsync
-	stw	r15,0(r14)
-	b	common_enter
-
-enter_winkle:
-	bl	save_sprs_to_stack
-
-	IDLE_STATE_ENTER_SEQ_NORET(PPC_WINKLE)
-
-/*
- * r3 - PSSCR value corresponding to the requested stop state.
- */
-power_enter_stop:
 /*
- * Check if we are executing the lite variant with ESL=EC=0
- */
-	andis.   r4,r3,PSSCR_EC_ESL_MASK_SHIFTED
-	clrldi   r3,r3,60 /* r3 = Bits[60:63] = Requested Level (RL) */
-	bne	 .Lhandle_esl_ec_set
-	PPC_STOP
-	li	r3,0  /* Since we didn't lose state, return 0 */
-	std	r3, PACA_REQ_PSSCR(r13)
-
-	/*
-	 * pnv_wakeup_noloss() expects r12 to contain the SRR1 value so
-	 * it can determine if the wakeup reason is an HMI in
-	 * CHECK_HMI_INTERRUPT.
-	 *
-	 * However, when we wakeup with ESL=0, SRR1 will not contain the wakeup
-	 * reason, so there is no point setting r12 to SRR1.
-	 *
-	 * Further, we clear r12 here, so that we don't accidentally enter the
-	 * HMI in pnv_wakeup_noloss() if the value of r12[42:45] == WAKE_HMI.
-	 */
-	li	r12, 0
-	b 	pnv_wakeup_noloss
-
-.Lhandle_esl_ec_set:
-BEGIN_FTR_SECTION
-	/*
-	 * POWER9 DD2.0 or earlier can incorrectly set PMAO when waking up after
-	 * a state-loss idle. Saving and restoring MMCR0 over idle is a
-	 * workaround.
-	 */
-	mfspr	r4,SPRN_MMCR0
-	std	r4,_MMCR0(r1)
-END_FTR_SECTION_IFCLR(CPU_FTR_POWER9_DD2_1)
-
-/*
- * Check if the requested state is a deep idle state.
- */
-	LOAD_REG_ADDRBASE(r5,pnv_first_deep_stop_state)
-	ld	r4,ADDROFF(pnv_first_deep_stop_state)(r5)
-	cmpd	r3,r4
-	bge	.Lhandle_deep_stop
-	PPC_STOP	/* Does not return (system reset interrupt) */
-
-.Lhandle_deep_stop:
-/*
- * Entering deep idle state.
- * Clear thread bit in PACA_CORE_IDLE_STATE, save SPRs to
- * stack and enter stop
- */
-	lbz     r7,PACA_THREAD_MASK(r13)
-	ld      r14,PACA_CORE_IDLE_STATE_PTR(r13)
-
-lwarx_loop_stop:
-	lwarx   r15,0,r14
-	andis.	r9,r15,PNV_CORE_IDLE_LOCK_BIT at h
-	bnel-	core_idle_lock_held
-	andc    r15,r15,r7                      /* Clear thread bit */
-
-	stwcx.  r15,0,r14
-	bne-    lwarx_loop_stop
-	isync
-
-	bl	save_sprs_to_stack
-
-	PPC_STOP	/* Does not return (system reset interrupt) */
-
-/*
- * Entered with MSR[EE]=0 and no soft-masked interrupts pending.
- * r3 contains desired idle state (PNV_THREAD_NAP/SLEEP/WINKLE).
- */
-_GLOBAL(power7_idle_insn)
-	/* Now check if user or arch enabled NAP mode */
-	LOAD_REG_ADDR(r4, pnv_enter_arch207_idle_mode)
-	b	pnv_powersave_common
-
-#define CHECK_HMI_INTERRUPT						\
-BEGIN_FTR_SECTION_NESTED(66);						\
-	rlwinm	r0,r12,45-31,0xf;  /* extract wake reason field (P8) */	\
-FTR_SECTION_ELSE_NESTED(66);						\
-	rlwinm	r0,r12,45-31,0xe;  /* P7 wake reason field is 3 bits */	\
-ALT_FTR_SECTION_END_NESTED_IFSET(CPU_FTR_ARCH_207S, 66);		\
-	cmpwi	r0,0xa;			/* Hypervisor maintenance ? */	\
-	bne+	20f;							\
-	/* Invoke opal call to handle hmi */				\
-	ld	r2,PACATOC(r13);					\
-	ld	r1,PACAR1(r13);						\
-	std	r3,ORIG_GPR3(r1);	/* Save original r3 */		\
-	li	r3,0;			/* NULL argument */		\
-	bl	hmi_exception_realmode;					\
-	nop;								\
-	ld	r3,ORIG_GPR3(r1);	/* Restore original r3 */	\
-20:	nop;
-
-/*
- * Entered with MSR[EE]=0 and no soft-masked interrupts pending.
- * r3 contains desired PSSCR register value.
+ * Desired instruction type in r3
  *
- * Offline (CPU unplug) case also must notify KVM that the CPU is
- * idle.
- */
-_GLOBAL(power9_offline_stop)
-#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
-	/*
-	 * Tell KVM we're entering idle.
-	 * This does not have to be done in real mode because the P9 MMU
-	 * is independent per-thread. Some steppings share radix/hash mode
-	 * between threads, but in that case KVM has a barrier sync in real
-	 * mode before and after switching between radix and hash.
-	 */
-	li	r4,KVM_HWTHREAD_IN_IDLE
-	stb	r4,HSTATE_HWTHREAD_STATE(r13)
-#endif
-	/* fall through */
-
-_GLOBAL(power9_idle_stop)
-	std	r3, PACA_REQ_PSSCR(r13)
-#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
-BEGIN_FTR_SECTION
-	sync
-	lwz	r5, PACA_DONT_STOP(r13)
-	cmpwi	r5, 0
-	bne	1f
-END_FTR_SECTION_IFSET(CPU_FTR_P9_TM_XER_SO_BUG)
-#endif
-	mtspr 	SPRN_PSSCR,r3
-	LOAD_REG_ADDR(r4,power_enter_stop)
-	b	pnv_powersave_common
-	/* No return */
-#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
-1:
-	/*
-	 * We get here when TM / thread reconfiguration bug workaround
-	 * code wants to get the CPU into SMT4 mode, and therefore
-	 * we are being asked not to stop.
-	 */
-	li	r3, 0
-	std	r3, PACA_REQ_PSSCR(r13)
-	blr		/* return 0 for wakeup cause / SRR1 value */
-#endif
-
-/*
- * Called from machine check handler for powersave wakeups.
- * Low level machine check processing has already been done. Now just
- * go through the wake up path to get everything in order.
+ * GPRs may be lost, so they are saved here. Wakeup is by interrupt only.
+ * Wakeup can return to caller by calling pnv_powersave_wakeup_gpr_loss
+ * with r3 set to return value.
  *
- * r3 - The original SRR1 value.
- * Original SRR[01] have been clobbered.
- * MSR_RI is clear.
- */
-.global pnv_powersave_wakeup_mce
-pnv_powersave_wakeup_mce:
-	/* Set cr3 for pnv_powersave_wakeup */
-	rlwinm	r11,r3,47-31,30,31
-	cmpwi	cr3,r11,2
-
-	/*
-	 * Now put the original SRR1 with SRR1_WAKEMCE_RESVD as the wake
-	 * reason into r12, which allows reuse of the system reset wakeup
-	 * code without being mistaken for another type of wakeup.
-	 */
-	oris	r12,r3,SRR1_WAKEMCE_RESVD at h
-
-	b	pnv_powersave_wakeup
-
-/*
- * Called from reset vector for powersave wakeups.
- * cr3 - set to gt if waking up with partial/complete hypervisor state loss
- * r12 - SRR1
- */
-.global pnv_powersave_wakeup
-pnv_powersave_wakeup:
-	ld	r2, PACATOC(r13)
-
-BEGIN_FTR_SECTION
-	bl	pnv_restore_hyp_resource_arch300
-FTR_SECTION_ELSE
-	bl	pnv_restore_hyp_resource_arch207
-ALT_FTR_SECTION_END_IFSET(CPU_FTR_ARCH_300)
-
-	li	r0,PNV_THREAD_RUNNING
-	stb	r0,PACA_THREAD_IDLE_STATE(r13)	/* Clear thread state */
-
-	mr	r3,r12
-
-#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
-	lbz	r0,HSTATE_HWTHREAD_STATE(r13)
-	cmpwi	r0,KVM_HWTHREAD_IN_KERNEL
-	beq	0f
-	li	r0,KVM_HWTHREAD_IN_KERNEL
-	stb	r0,HSTATE_HWTHREAD_STATE(r13)
-	/* Order setting hwthread_state vs. testing hwthread_req */
-	sync
-0:	lbz	r0,HSTATE_HWTHREAD_REQ(r13)
-	cmpwi	r0,0
-	beq	1f
-	b	kvm_start_guest
-1:
-#endif
-
-	/* Return SRR1 from power7_nap() */
-	blt	cr3,pnv_wakeup_noloss
-	b	pnv_wakeup_loss
-
-/*
- * Check whether we have woken up with hypervisor state loss.
- * If yes, restore hypervisor state and return back to link.
+ * A wakeup without GPR loss may alterateively be handled as in
+ * isa3_idle_stop_noloss as an optimisation.
  *
- * cr3 - set to gt if waking up with partial/complete hypervisor state loss
- */
-pnv_restore_hyp_resource_arch300:
-	/*
-	 * Workaround for POWER9, if we lost resources, the ERAT
-	 * might have been mixed up and needs flushing. We also need
-	 * to reload MMCR0 (see comment above). We also need to set
-	 * then clear bit 60 in MMCRA to ensure the PMU starts running.
-	 */
-	blt	cr3,1f
-BEGIN_FTR_SECTION
-	PPC_INVALIDATE_ERAT
-	ld	r1,PACAR1(r13)
-	ld	r4,_MMCR0(r1)
-	mtspr	SPRN_MMCR0,r4
-END_FTR_SECTION_IFCLR(CPU_FTR_POWER9_DD2_1)
-	mfspr	r4,SPRN_MMCRA
-	ori	r4,r4,(1 << (63-60))
-	mtspr	SPRN_MMCRA,r4
-	xori	r4,r4,(1 << (63-60))
-	mtspr	SPRN_MMCRA,r4
-1:
-	/*
-	 * POWER ISA 3. Use PSSCR to determine if we
-	 * are waking up from deep idle state
-	 */
-	LOAD_REG_ADDRBASE(r5,pnv_first_deep_stop_state)
-	ld	r4,ADDROFF(pnv_first_deep_stop_state)(r5)
-
-	/*
-	 * 0-3 bits correspond to Power-Saving Level Status
-	 * which indicates the idle state we are waking up from
-	 */
-	mfspr	r5, SPRN_PSSCR
-	rldicl  r5,r5,4,60
-	li	r0, 0		/* clear requested_psscr to say we're awake */
-	std	r0, PACA_REQ_PSSCR(r13)
-	cmpd	cr4,r5,r4
-	bge	cr4,pnv_wakeup_tb_loss /* returns to caller */
-
-	blr	/* Waking up without hypervisor state loss. */
-
-/* Same calling convention as arch300 */
-pnv_restore_hyp_resource_arch207:
-	/*
-	 * POWER ISA 2.07 or less.
-	 * Check if we slept with sleep or winkle.
-	 */
-	lbz	r4,PACA_THREAD_IDLE_STATE(r13)
-	cmpwi	cr2,r4,PNV_THREAD_NAP
-	bgt	cr2,pnv_wakeup_tb_loss	/* Either sleep or Winkle */
-
-	/*
-	 * We fall through here if PACA_THREAD_IDLE_STATE shows we are waking
-	 * up from nap. At this stage CR3 shouldn't contains 'gt' since that
-	 * indicates we are waking with hypervisor state loss from nap.
-	 */
-	bgt	cr3,.
-
-	blr	/* Waking up without hypervisor state loss */
-
-/*
- * Called if waking up from idle state which can cause either partial or
- * complete hyp state loss.
- * In POWER8, called if waking up from fastsleep or winkle
- * In POWER9, called if waking up from stop state >= pnv_first_deep_stop_state
- *
- * r13 - PACA
- * cr3 - gt if waking up with partial/complete hypervisor state loss
- *
- * If ISA300:
- * cr4 - gt or eq if waking up from complete hypervisor state loss.
+ * Caller is responsible for restoring SPRs, MSR, etc.
  *
- * If ISA207:
- * r4 - PACA_THREAD_IDLE_STATE
+ * ISA206/7 must call these in realmode, MMU disabled.
  */
-pnv_wakeup_tb_loss:
-	ld	r1,PACAR1(r13)
-	/*
-	 * Before entering any idle state, the NVGPRs are saved in the stack.
-	 * If there was a state loss, or PACA_NAPSTATELOST was set, then the
-	 * NVGPRs are restored. If we are here, it is likely that state is lost,
-	 * but not guaranteed -- neither ISA207 nor ISA300 tests to reach
-	 * here are the same as the test to restore NVGPRS:
-	 * PACA_THREAD_IDLE_STATE test for ISA207, PSSCR test for ISA300,
-	 * and SRR1 test for restoring NVGPRs.
-	 *
-	 * We are about to clobber NVGPRs now, so set NAPSTATELOST to
-	 * guarantee they will always be restored. This might be tightened
-	 * with careful reading of specs (particularly for ISA300) but this
-	 * is already a slow wakeup path and it's simpler to be safe.
-	 */
-	li	r0,1
-	stb	r0,PACA_NAPSTATELOST(r13)
-
-	/*
-	 *
-	 * Save SRR1 and LR in NVGPRs as they might be clobbered in
-	 * opal_call() (called in CHECK_HMI_INTERRUPT). SRR1 is required
-	 * to determine the wakeup reason if we branch to kvm_start_guest. LR
-	 * is required to return back to reset vector after hypervisor state
-	 * restore is complete.
-	 */
-	mr	r19,r12
-	mr	r18,r4
-	mflr	r17
-BEGIN_FTR_SECTION
-	CHECK_HMI_INTERRUPT
-END_FTR_SECTION_IFSET(CPU_FTR_HVMODE)
-
-	ld	r14,PACA_CORE_IDLE_STATE_PTR(r13)
-	lbz	r7,PACA_THREAD_MASK(r13)
-
-	/*
-	 * Take the core lock to synchronize against other threads.
-	 *
-	 * 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.
-	 */
-1:
-	lwarx	r15,0,r14
-	andis.	r9,r15,PNV_CORE_IDLE_LOCK_BIT at h
-	bnel-	core_idle_lock_held
-	oris	r15,r15,PNV_CORE_IDLE_LOCK_BIT at h
-	stwcx.	r15,0,r14
-	bne-	1b
-	isync
-
-	andi.	r9,r15,PNV_CORE_IDLE_THREAD_BITS
-	cmpwi	cr2,r9,0
-
-	/*
-	 * At this stage
-	 * cr2 - eq if first thread to wakeup in core
-	 * cr3-  gt if waking up with partial/complete hypervisor state loss
-	 * ISA300:
-	 * cr4 - gt or eq if waking up from complete hypervisor state loss.
-	 */
-
-BEGIN_FTR_SECTION
-	/*
-	 * Were we in winkle?
-	 * If yes, check if all threads were in winkle, decrement our
-	 * winkle count, set all thread winkle bits if all were in winkle.
-	 * Check if our thread has a winkle bit set, and set cr4 accordingly
-	 * (to match ISA300, above). Pseudo-code for core idle state
-	 * transitions for ISA207 is as follows (everything happens atomically
-	 * due to store conditional and/or lock bit):
-	 *
-	 * nap_idle() { }
-	 * nap_wake() { }
-	 *
-	 * sleep_idle()
-	 * {
-	 *	core_idle_state &= ~thread_in_core
-	 * }
-	 *
-	 * sleep_wake()
-	 * {
-	 *     bool first_in_core, first_in_subcore;
-	 *
-	 *     first_in_core = (core_idle_state & IDLE_THREAD_BITS) == 0;
-	 *     first_in_subcore = (core_idle_state & SUBCORE_SIBLING_MASK) == 0;
-	 *
-	 *     core_idle_state |= thread_in_core;
-	 * }
-	 *
-	 * winkle_idle()
-	 * {
-	 *	core_idle_state &= ~thread_in_core;
-	 *	core_idle_state += 1 << WINKLE_COUNT_SHIFT;
-	 * }
-	 *
-	 * winkle_wake()
-	 * {
-	 *     bool first_in_core, first_in_subcore, winkle_state_lost;
-	 *
-	 *     first_in_core = (core_idle_state & IDLE_THREAD_BITS) == 0;
-	 *     first_in_subcore = (core_idle_state & SUBCORE_SIBLING_MASK) == 0;
-	 *
-	 *     core_idle_state |= thread_in_core;
-	 *
-	 *     if ((core_idle_state & WINKLE_MASK) == (8 << WINKLE_COUNT_SIHFT))
-	 *         core_idle_state |= THREAD_WINKLE_BITS;
-	 *     core_idle_state -= 1 << WINKLE_COUNT_SHIFT;
-	 *
-	 *     winkle_state_lost = core_idle_state &
-	 *				(thread_in_core << WINKLE_THREAD_SHIFT);
-	 *     core_idle_state &= ~(thread_in_core << WINKLE_THREAD_SHIFT);
-	 * }
-	 *
-	 */
-	cmpwi	r18,PNV_THREAD_WINKLE
+_GLOBAL(isa206_idle_insn_mayloss)
+	std	r1,PACAR1(r13)
+	mflr	r4
+	mfcr	r5
+	/* use stack red zone rather than a new frame */
+	addi	r6,r1,-INT_FRAME_SIZE
+	SAVE_GPR(2, r6)
+	SAVE_NVGPRS(r6)
+	std	r4,_LINK(r6)
+	std	r5,_CCR(r6)
+	cmpwi	r3,PNV_THREAD_NAP
+	bne	1f
+	IDLE_STATE_ENTER_SEQ_NORET(PPC_NAP)
+1:	cmpwi	r3,PNV_THREAD_SLEEP
 	bne	2f
-	andis.	r9,r15,PNV_CORE_IDLE_WINKLE_COUNT_ALL_BIT at h
-	subis	r15,r15,PNV_CORE_IDLE_WINKLE_COUNT at h
-	beq	2f
-	ori	r15,r15,PNV_CORE_IDLE_THREAD_WINKLE_BITS /* all were winkle */
-2:
-	/* Shift thread bit to winkle mask, then test if this thread is set,
-	 * and remove it from the winkle bits */
-	slwi	r8,r7,8
-	and	r8,r8,r15
-	andc	r15,r15,r8
-	cmpwi	cr4,r8,1 /* cr4 will be gt if our bit is set, lt if not */
-
-	lbz	r4,PACA_SUBCORE_SIBLING_MASK(r13)
-	and	r4,r4,r15
-	cmpwi	r4,0	/* Check if first in subcore */
-
-	or	r15,r15,r7		/* Set thread bit */
-	beq	first_thread_in_subcore
-END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_300)
-
-	or	r15,r15,r7		/* Set thread bit */
-	beq	cr2,first_thread_in_core
-
-	/* Not first thread in core or subcore to wake up */
-	b	clear_lock
-
-first_thread_in_subcore:
-	/*
-	 * If waking up from sleep, subcore state is not lost. Hence
-	 * skip subcore state restore
-	 */
-	blt	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 any state which can cause
-	 * partial or complete hypervisor state loss. 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 if the platform does not have fastsleep or does not
-	 * require the workaround. Patching will be performed during the
-	 * discovery of idle-states.
-	 */
-.global pnv_fastsleep_workaround_at_exit
-pnv_fastsleep_workaround_at_exit:
-	b	fastsleep_workaround_at_exit
-
-timebase_resync:
-	/*
-	 * Use cr3 which indicates that we are waking up with atleast partial
-	 * hypervisor state loss to determine if TIMEBASE RESYNC is needed.
-	 */
-	ble	cr3,.Ltb_resynced
-	/* Time base re-sync */
-	bl	opal_resync_timebase;
-	/*
-	 * If waking up from sleep (POWER8), per core state
-	 * is not lost, skip to clear_lock.
-	 */
-.Ltb_resynced:
-	blt	cr4,clear_lock
-
-	/*
-	 * First thread in the core to wake up and its waking up with
-	 * complete hypervisor state loss. Restore per core hypervisor
-	 * state.
-	 */
-BEGIN_FTR_SECTION
-	ld	r4,_PTCR(r1)
-	mtspr	SPRN_PTCR,r4
-	ld	r4,_RPR(r1)
-	mtspr	SPRN_RPR,r4
-	ld	r4,_AMOR(r1)
-	mtspr	SPRN_AMOR,r4
-END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300)
-
-	ld	r4,_TSCR(r1)
-	mtspr	SPRN_TSCR,r4
-	ld	r4,_WORC(r1)
-	mtspr	SPRN_WORC,r4
-
-clear_lock:
-	xoris	r15,r15,PNV_CORE_IDLE_LOCK_BIT at h
-	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.
-	 */
-	blt	cr4,hypervisor_state_restored
-
-	/* Waking up from winkle */
-
-BEGIN_MMU_FTR_SECTION
-	b	no_segments
-END_MMU_FTR_SECTION_IFSET(MMU_FTR_TYPE_RADIX)
-	/* 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 at h
-	beq	1f
-	slbmte	r6,r5
-1:	addi	r8,r8,16
-	.endr
-no_segments:
-
-	/* Restore per thread state */
-
-	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
+	IDLE_STATE_ENTER_SEQ_NORET(PPC_SLEEP)
+	b	.	/* catch bugs */
+2:	IDLE_STATE_ENTER_SEQ_NORET(PPC_WINKLE)
+	b	.	/* catch bugs */
 
-	/* Call cur_cpu_spec->cpu_restore() */
-	LOAD_REG_ADDR(r4, cur_cpu_spec)
-	ld	r4,0(r4)
-	ld	r12,CPU_SPEC_RESTORE(r4)
-#ifdef PPC64_ELF_ABI_v1
-	ld	r12,0(r12)
+#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
+_GLOBAL(idle_kvm_start_guest)
+	std	r1,PACAR1(r13)
+	mflr	r4
+	mfcr	r5
+	/* use stack red zone rather than a new frame */
+	addi	r6,r1,-INT_FRAME_SIZE
+	SAVE_GPR(2, r6)
+	SAVE_NVGPRS(r6)
+	std	r4,_LINK(r6)
+	std	r5,_CCR(r6)
+	b	kvm_start_guest
 #endif
-	mtctr	r12
-	bctrl
-
-/*
- * On POWER9, we can come here on wakeup from a cpuidle stop state.
- * Hence restore the additional SPRs to the saved value.
- *
- * On POWER8, we come here only on winkle. Since winkle is used
- * only in the case of CPU-Hotplug, we don't need to restore
- * the additional SPRs.
- */
-BEGIN_FTR_SECTION
-	bl 	power9_restore_additional_sprs
-END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300)
-hypervisor_state_restored:
-
-	mr	r12,r19
-	mtlr	r17
-	blr		/* return to pnv_powersave_wakeup */
-
-fastsleep_workaround_at_exit:
-	li	r3,1
-	li	r4,0
-	bl	opal_config_cpu_idle_state
-	b	timebase_resync
-
-/*
- * R3 here contains the value that will be returned to the caller
- * of power7_nap.
- * R12 contains SRR1 for CHECK_HMI_INTERRUPT.
- */
-.global pnv_wakeup_loss
-pnv_wakeup_loss:
-	ld	r1,PACAR1(r13)
-BEGIN_FTR_SECTION
-	CHECK_HMI_INTERRUPT
-END_FTR_SECTION_IFSET(CPU_FTR_HVMODE)
-	REST_NVGPRS(r1)
-	REST_GPR(2, r1)
-	ld	r4,PACAKMSR(r13)
-	ld	r5,_LINK(r1)
-	ld	r6,_CCR(r1)
-	addi	r1,r1,INT_FRAME_SIZE
-	mtlr	r5
-	mtcr	r6
-	mtmsrd	r4
-	blr
-
-/*
- * R3 here contains the value that will be returned to the caller
- * of power7_nap.
- * R12 contains SRR1 for CHECK_HMI_INTERRUPT.
- */
-pnv_wakeup_noloss:
-	lbz	r0,PACA_NAPSTATELOST(r13)
-	cmpwi	r0,0
-	bne	pnv_wakeup_loss
-	ld	r1,PACAR1(r13)
-BEGIN_FTR_SECTION
-	CHECK_HMI_INTERRUPT
-END_FTR_SECTION_IFSET(CPU_FTR_HVMODE)
-	ld	r4,PACAKMSR(r13)
-	ld	r5,_NIP(r1)
-	ld	r6,_CCR(r1)
-	addi	r1,r1,INT_FRAME_SIZE
-	mtlr	r5
-	mtcr	r6
-	mtmsrd	r4
-	blr
diff --git a/arch/powerpc/kernel/setup-common.c b/arch/powerpc/kernel/setup-common.c
index 40b44bb53a4e..e089da156ef3 100644
--- a/arch/powerpc/kernel/setup-common.c
+++ b/arch/powerpc/kernel/setup-common.c
@@ -401,8 +401,8 @@ void __init check_for_initrd(void)
 
 #ifdef CONFIG_SMP
 
-int threads_per_core, threads_per_subcore, threads_shift;
-cpumask_t threads_core_mask;
+int threads_per_core, threads_per_subcore, threads_shift __read_mostly;
+cpumask_t threads_core_mask __read_mostly;
 EXPORT_SYMBOL_GPL(threads_per_core);
 EXPORT_SYMBOL_GPL(threads_per_subcore);
 EXPORT_SYMBOL_GPL(threads_shift);
diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
index 6e4554b273f1..90e260773aa4 100644
--- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S
+++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
@@ -32,6 +32,7 @@
 #include <asm/opal.h>
 #include <asm/xive-regs.h>
 #include <asm/thread_info.h>
+#include <asm/cpuidle.h>
 
 /* Sign-extend HDEC if not on POWER9 */
 #define EXTEND_HDEC(reg)			\
@@ -320,43 +321,32 @@ kvm_novcpu_exit:
 	b	kvmhv_switch_to_host
 
 /*
- * We come in here when wakened from nap mode.
- * Relocation is off and most register values are lost.
- * r13 points to the PACA.
+ * We come in here when wakened from Linux offline idle code.
+ * Relocation is off
  * r3 contains the SRR1 wakeup value, SRR1 is trashed.
  */
 	.globl	kvm_start_guest
 kvm_start_guest:
-	/* Set runlatch bit the minute you wake up from nap */
-	mfspr	r0, SPRN_CTRLF
-	ori 	r0, r0, 1
-	mtspr	SPRN_CTRLT, r0
-
 	/*
 	 * Could avoid this and pass it through in r3. For now,
 	 * code expects it to be in SRR1.
 	 */
 	mtspr	SPRN_SRR1,r3
 
-	ld	r2,PACATOC(r13)
-
 	li	r0,0
 	stb	r0,PACA_FTRACE_ENABLED(r13)
 
 	li	r0,KVM_HWTHREAD_IN_KVM
 	stb	r0,HSTATE_HWTHREAD_STATE(r13)
 
-	/* NV GPR values from power7_idle() will no longer be valid */
-	li	r0,1
-	stb	r0,PACA_NAPSTATELOST(r13)
-
-	/* were we napping due to cede? */
+	/* cede napping should not come through here */
 	lbz	r0,HSTATE_NAPPING(r13)
-	cmpwi	r0,NAPPING_CEDE
-	beq	kvm_end_cede
-	cmpwi	r0,NAPPING_NOVCPU
-	beq	kvm_novcpu_wakeup
+	twnei	r0,0
 
+/*
+ * We can come in at this point from KVM nap.
+ */
+do_start_guest:
 	ld	r1,PACAEMERGSP(r13)
 	subi	r1,r1,STACK_FRAME_OVERHEAD
 
@@ -467,19 +457,17 @@ kvm_no_guest:
 	lbz	r3, HSTATE_HWTHREAD_REQ(r13)
 	cmpwi	r3, 0
 	bne	54f
-/*
- * We jump to pnv_wakeup_loss, which will return to the caller
- * of power7_nap in the powernv cpu offline loop.  The value we
- * put in r3 becomes the return value for power7_nap. pnv_wakeup_loss
- * requires SRR1 in r12.
- */
+
+	/*
+	 * Jump to idle_return_gpr_loss, which returns to the
+	 * idle_kvm_start_guest caller.
+	 */
 	li	r3, LPCR_PECE0
 	mfspr	r4, SPRN_LPCR
 	rlwimi	r4, r3, 0, LPCR_PECE0 | LPCR_PECE1
 	mtspr	SPRN_LPCR, r4
 	li	r3, 0
-	mfspr	r12,SPRN_SRR1
-	b	pnv_wakeup_loss
+	b	idle_return_gpr_loss
 
 53:	HMT_LOW
 	ld	r5, HSTATE_KVM_VCORE(r13)
@@ -2648,6 +2636,7 @@ _GLOBAL(kvmppc_h_cede)		/* r3 = vcpu pointer, r11 = msr, r13 = paca */
  * switch occurs: SLB entries, PURR, SPURR, AMOR, UAMOR, AMR, SPRG0-3,
  * DAR, DSISR, DABR, DABRX, DSCR, PMCx, MMCRx, SIAR, SDAR.
  */
+#if 1
 	/* Save non-volatile GPRs */
 	std	r14, VCPU_GPR(R14)(r3)
 	std	r15, VCPU_GPR(R15)(r3)
@@ -2667,6 +2656,7 @@ _GLOBAL(kvmppc_h_cede)		/* r3 = vcpu pointer, r11 = msr, r13 = paca */
 	std	r29, VCPU_GPR(R29)(r3)
 	std	r30, VCPU_GPR(R30)(r3)
 	std	r31, VCPU_GPR(R31)(r3)
+#endif
 
 	/* save FP state */
 	bl	kvmppc_save_fp
@@ -2758,21 +2748,47 @@ BEGIN_FTR_SECTION
 	li	r4, LPCR_PECE_HVEE at higher
 	sldi	r4, r4, 32
 	or	r5, r5, r4
-END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300)
+FTR_SECTION_ELSE
+	li	r3, PNV_THREAD_NAP
+ALT_FTR_SECTION_END_IFSET(CPU_FTR_ARCH_300)
 	mtspr	SPRN_LPCR,r5
 	isync
-	li	r0, 0
-	std	r0, HSTATE_SCRATCH0(r13)
-	ptesync
-	ld	r0, HSTATE_SCRATCH0(r13)
-1:	cmpd	r0, r0
-	bne	1b
+
+	mr	r0, r1
+	ld	r1, PACAEMERGSP(r13)
+	subi	r1, r1, STACK_FRAME_OVERHEAD
+	std	r0, 0(r1)
+	ld	r0, PACAR1(r13)
+	std	r0, 8(r1)
+
 BEGIN_FTR_SECTION
-	nap
+	bl	isa3_idle_stop_mayloss
 FTR_SECTION_ELSE
-	PPC_STOP
-ALT_FTR_SECTION_END_IFCLR(CPU_FTR_ARCH_300)
-	b	.
+	bl	isa206_idle_insn_mayloss
+ALT_FTR_SECTION_END_IFSET(CPU_FTR_ARCH_300)
+
+	mfspr	r0, SPRN_CTRLF
+	ori	r0, r0, 1
+	mtspr	SPRN_CTRLT, r0
+
+	ld	r0, 8(r1)
+	std	r0, PACAR1(r13)
+	ld	r1, 0(r1)
+
+	mtspr	r3, SPRN_SRR1
+
+	li	r0, 0
+	stb	r0, PACA_FTRACE_ENABLED(r13)
+
+	li	r0, KVM_HWTHREAD_IN_KVM
+	stb	r0, HSTATE_HWTHREAD_STATE(r13)
+
+	lbz	r0, HSTATE_NAPPING(r13)
+	cmpwi	r0, NAPPING_CEDE
+	beq	kvm_end_cede
+	cmpwi	r0, NAPPING_NOVCPU
+	beq	kvm_novcpu_wakeup
+	b	do_start_guest
 
 33:	mr	r4, r3
 	li	r3, 0
@@ -2821,6 +2837,7 @@ END_FTR_SECTION(CPU_FTR_TM | CPU_FTR_P9_TM_HV_ASSIST, 0)
 	subf	r3, r7, r3
 	mtspr	SPRN_DEC, r3
 
+#if 1
 	/* Load NV GPRS */
 	ld	r14, VCPU_GPR(R14)(r4)
 	ld	r15, VCPU_GPR(R15)(r4)
@@ -2840,6 +2857,7 @@ END_FTR_SECTION(CPU_FTR_TM | CPU_FTR_P9_TM_HV_ASSIST, 0)
 	ld	r29, VCPU_GPR(R29)(r4)
 	ld	r30, VCPU_GPR(R30)(r4)
 	ld	r31, VCPU_GPR(R31)(r4)
+#endif
 
 	/* Check the wake reason in SRR1 to see why we got here */
 	bl	kvmppc_check_wake_reason
diff --git a/arch/powerpc/mm/slb.c b/arch/powerpc/mm/slb.c
index cb796724a6fc..1518beec3161 100644
--- a/arch/powerpc/mm/slb.c
+++ b/arch/powerpc/mm/slb.c
@@ -90,6 +90,21 @@ static inline void create_shadowed_slbe(unsigned long ea, int ssize,
 		     : "memory" );
 }
 
+void slb_shadow_reload(void)
+{
+	struct slb_shadow *p = get_slb_shadow();
+	enum slb_index index;
+
+	for (index = 0; index < SLB_NUM_BOLTED; index++) {
+		if (be64_to_cpu(p->save_area[index].esid) & SLB_ESID_V) {
+			asm volatile("slbmte  %0,%1" :
+			     : "r" (be64_to_cpu(p->save_area[index].vsid)),
+			       "r" (be64_to_cpu(p->save_area[index].esid)));
+		}
+	}
+	isync();
+}
+
 static void __slb_flush_and_rebolt(void)
 {
 	/* If you change this make sure you change SLB_NUM_BOLTED
diff --git a/arch/powerpc/platforms/powernv/idle.c b/arch/powerpc/platforms/powernv/idle.c
index 12f13acee1f6..bf85e86f1064 100644
--- a/arch/powerpc/platforms/powernv/idle.c
+++ b/arch/powerpc/platforms/powernv/idle.c
@@ -16,6 +16,7 @@
 #include <linux/device.h>
 #include <linux/cpu.h>
 
+#include <asm/asm-prototypes.h>
 #include <asm/firmware.h>
 #include <asm/machdep.h>
 #include <asm/opal.h>
@@ -35,7 +36,7 @@
 #define P9_STOP_SPR_MSR 2000
 #define P9_STOP_SPR_PSSCR      855
 
-static u32 supported_cpuidle_states;
+static u32 pm_flags_possible; /* OPAL_PM_ flags */
 
 /*
  * The default stop state that will be used by ppc_md.power_save
@@ -46,10 +47,10 @@ static u64 pnv_default_stop_mask;
 static bool default_stop_found;
 
 /*
- * First deep stop state. Used to figure out when to save/restore
- * hypervisor context.
+ * First stop state levels when HV and TB loss can occur.
  */
-u64 pnv_first_deep_stop_state = MAX_STOP_STATE;
+static u64 pnv_first_tb_loss_level = MAX_STOP_STATE + 1;
+static u64 pnv_first_hv_loss_level = MAX_STOP_STATE + 1;
 
 /*
  * psscr value and mask of the deepest stop idle state.
@@ -60,6 +61,8 @@ static u64 pnv_deepest_stop_psscr_mask;
 static u64 pnv_deepest_stop_flag;
 static bool deepest_stop_found;
 
+static unsigned long power7_offline_type;
+
 static int pnv_save_sprs_for_deep_states(void)
 {
 	int cpu;
@@ -70,12 +73,12 @@ static int pnv_save_sprs_for_deep_states(void)
 	 * all cpus at boot. Get these reg values of current cpu and use the
 	 * same across 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);
+	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);
 	uint64_t msr_val = MSR_IDLE;
 	uint64_t psscr_val = pnv_deepest_stop_psscr_val;
 
@@ -135,92 +138,9 @@ static int pnv_save_sprs_for_deep_states(void)
 	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 - The lower 8 bits track the idle state of
-	 * each thread of the core.
-	 *
-	 * The most significant bit is the lock bit.
-	 *
-	 * Initially all the bits corresponding to threads_per_core
-	 * are set. They are cleared when the thread enters deep idle
-	 * state like sleep and winkle/stop.
-	 *
-	 * Initially the lock bit is cleared.  The lock bit has 2
-	 * purposes:
-	 * 	a. While the first thread in the core waking up from
-	 * 	   idle 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);
-		size_t paca_ptr_array_size;
-
-		core_idle_state = kmalloc_node(sizeof(u32), GFP_KERNEL, node);
-		*core_idle_state = (1 << threads_per_core) - 1;
-		paca_ptr_array_size = (threads_per_core *
-				       sizeof(struct paca_struct *));
-
-		for (j = 0; j < threads_per_core; j++) {
-			int cpu = first_cpu + j;
-
-			paca_ptrs[cpu]->core_idle_state_ptr = core_idle_state;
-			paca_ptrs[cpu]->thread_idle_state = PNV_THREAD_RUNNING;
-			paca_ptrs[cpu]->thread_mask = 1 << j;
-		}
-	}
-
-	update_subcore_sibling_mask();
-
-	if (supported_cpuidle_states & OPAL_PM_LOSE_FULL_CONTEXT) {
-		int rc = pnv_save_sprs_for_deep_states();
-
-		if (likely(!rc))
-			return;
-
-		/*
-		 * The stop-api is unable to restore hypervisor
-		 * resources on wakeup from platform idle states which
-		 * lose full context. So disable such states.
-		 */
-		supported_cpuidle_states &= ~OPAL_PM_LOSE_FULL_CONTEXT;
-		pr_warn("cpuidle-powernv: Disabling idle states that lose full context\n");
-		pr_warn("cpuidle-powernv: Idle power-savings, CPU-Hotplug affected\n");
-
-		if (cpu_has_feature(CPU_FTR_ARCH_300) &&
-		    (pnv_deepest_stop_flag & OPAL_PM_LOSE_FULL_CONTEXT)) {
-			/*
-			 * Use the default stop state for CPU-Hotplug
-			 * if available.
-			 */
-			if (default_stop_found) {
-				pnv_deepest_stop_psscr_val =
-					pnv_default_stop_val;
-				pnv_deepest_stop_psscr_mask =
-					pnv_default_stop_mask;
-				pr_warn("cpuidle-powernv: Offlined CPUs will stop with psscr = 0x%016llx\n",
-					pnv_deepest_stop_psscr_val);
-			} else { /* Fallback to snooze loop for CPU-Hotplug */
-				deepest_stop_found = false;
-				pr_warn("cpuidle-powernv: Offlined CPUs will busy wait\n");
-			}
-		}
-	}
-}
-
 u32 pnv_get_supported_cpuidle_states(void)
 {
-	return supported_cpuidle_states;
+	return pm_flags_possible;
 }
 EXPORT_SYMBOL_GPL(pnv_get_supported_cpuidle_states);
 
@@ -236,6 +156,9 @@ static void pnv_fastsleep_workaround_apply(void *info)
 		*err = 1;
 }
 
+static bool power7_fastsleep_workaround_entry = true;
+static bool power7_fastsleep_workaround_exit = true;
+
 /*
  * Used to store fastsleep workaround state
  * 0 - Workaround applied/undone at fastsleep entry/exit path (Default)
@@ -275,13 +198,7 @@ static ssize_t store_fastsleep_workaround_applyonce(struct device *dev,
 	 * offlined, as last thread of the core entering fastsleep or deeper
 	 * state would have applied workaround.
 	 */
-	err = patch_instruction(
-		(unsigned int *)pnv_fastsleep_workaround_at_exit,
-		PPC_INST_NOP);
-	if (err) {
-		pr_err("fastsleep_workaround_applyonce change failed while patching pnv_fastsleep_workaround_at_exit");
-		goto fail;
-	}
+	power7_fastsleep_workaround_exit = false;
 
 	get_online_cpus();
 	primary_thread_mask = cpu_online_cores_map();
@@ -294,13 +211,7 @@ static ssize_t store_fastsleep_workaround_applyonce(struct device *dev,
 		goto fail;
 	}
 
-	err = patch_instruction(
-		(unsigned int *)pnv_fastsleep_workaround_at_entry,
-		PPC_INST_NOP);
-	if (err) {
-		pr_err("fastsleep_workaround_applyonce change failed while patching pnv_fastsleep_workaround_at_entry");
-		goto fail;
-	}
+	power7_fastsleep_workaround_entry = false;
 
 	fastsleep_workaround_applyonce = 1;
 
@@ -313,6 +224,308 @@ static DEVICE_ATTR(fastsleep_workaround_applyonce, 0600,
 			show_fastsleep_workaround_applyonce,
 			store_fastsleep_workaround_applyonce);
 
+static inline void atomic_start_thread_idle(void)
+{
+	int cpu = raw_smp_processor_id();
+	int first = cpu_first_thread_sibling(cpu);
+	int thread_nr = cpu_thread_in_core(cpu);
+	unsigned long *state = &paca_ptrs[first]->idle_state;
+
+	clear_bit(thread_nr, state);
+}
+
+static inline void atomic_stop_thread_idle(void)
+{
+	int cpu = raw_smp_processor_id();
+	int first = cpu_first_thread_sibling(cpu);
+	int thread_nr = cpu_thread_in_core(cpu);
+	unsigned long *state = &paca_ptrs[first]->idle_state;
+
+	set_bit(thread_nr, state);
+}
+
+static inline void atomic_lock_thread_idle(void)
+{
+	int cpu = raw_smp_processor_id();
+	int first = cpu_first_thread_sibling(cpu);
+	unsigned long *state = &paca_ptrs[first]->idle_state;
+
+	while (unlikely(test_and_set_bit_lock(NR_PNV_CORE_IDLE_LOCK_BIT, state)))
+		barrier();
+	isync();
+}
+
+static inline void atomic_unlock_and_stop_thread_idle(void)
+{
+	int cpu = raw_smp_processor_id();
+	int first = cpu_first_thread_sibling(cpu);
+	unsigned long thread = 1UL << cpu_thread_in_core(cpu);
+	unsigned long *state = &paca_ptrs[first]->idle_state;
+	u64 s = READ_ONCE(*state);
+	u64 new, tmp;
+
+	isync();
+
+	BUG_ON(!(s & PNV_CORE_IDLE_LOCK_BIT));
+	BUG_ON(s & thread);
+
+again:
+	new = (s | thread) & ~PNV_CORE_IDLE_LOCK_BIT;
+	tmp = cmpxchg(state, s, new);
+	if (unlikely(tmp != s)) {
+		s = tmp;
+		goto again;
+	}
+}
+
+static inline void atomic_unlock_thread_idle(void)
+{
+	int cpu = raw_smp_processor_id();
+	int first = cpu_first_thread_sibling(cpu);
+	unsigned long *state = &paca_ptrs[first]->idle_state;
+
+	BUG_ON(!test_bit(NR_PNV_CORE_IDLE_LOCK_BIT, state));
+	clear_bit_unlock(NR_PNV_CORE_IDLE_LOCK_BIT, state);
+}
+
+struct p7_sprs {
+	/* per core */
+	u64 tscr;
+	u64 worc;
+
+	/* per subcore */
+	u64 sdr1;
+	u64 rpr;
+	u64 amor;
+
+	/* per thread */
+	u64 lpcr;
+	u64 hfscr;
+	u64 fscr;
+	u64 purr;
+	u64 spurr;
+	u64 dscr;
+	u64 wort;
+
+	u64 mmcra;
+	u32 mmcr0;
+	u32 mmcr1;
+	u64 mmcr2;
+};
+
+static unsigned long power7_idle_insn(unsigned long type)
+{
+	int cpu = raw_smp_processor_id();
+	int first = cpu_first_thread_sibling(cpu);
+	unsigned long thread = 1UL << cpu_thread_in_core(cpu);
+	unsigned long *state = &paca_ptrs[first]->idle_state;
+	unsigned long srr1;
+	bool full_winkle;
+	struct p7_sprs sprs;
+	bool sprs_saved = false;
+	int rc;
+
+	memset(&sprs, 0, sizeof(sprs));
+
+	if (unlikely(type != PNV_THREAD_NAP)) {
+		atomic_lock_thread_idle();
+
+		BUG_ON(!(*state & thread));
+		*state &= ~thread;
+
+		if (power7_fastsleep_workaround_entry) {
+			if ((*state & ((1 << threads_per_core) - 1)) == 0) {
+				rc = opal_config_cpu_idle_state(
+						OPAL_CONFIG_IDLE_FASTSLEEP,
+						OPAL_CONFIG_IDLE_APPLY);
+				BUG_ON(rc);
+			}
+		}
+
+		if (type == PNV_THREAD_WINKLE) {
+			sprs.tscr	= mfspr(SPRN_TSCR);
+			sprs.worc	= mfspr(SPRN_WORC);
+
+			sprs.sdr1	= mfspr(SPRN_SDR1);
+			sprs.rpr	= mfspr(SPRN_RPR);
+			sprs.amor	= mfspr(SPRN_AMOR);
+
+			sprs.lpcr	= mfspr(SPRN_LPCR);
+			sprs.hfscr	= mfspr(SPRN_HFSCR);
+			sprs.fscr	= mfspr(SPRN_FSCR);
+			sprs.purr	= mfspr(SPRN_PURR);
+			sprs.spurr	= mfspr(SPRN_SPURR);
+			sprs.dscr	= mfspr(SPRN_DSCR);
+			sprs.wort	= mfspr(SPRN_WORT);
+
+			sprs.mmcra	= mfspr(SPRN_MMCRA);
+			sprs.mmcr0	= mfspr(SPRN_MMCR0);
+			sprs.mmcr1	= mfspr(SPRN_MMCR1);
+			sprs.mmcr2	= mfspr(SPRN_MMCR2);
+
+			sprs_saved = true;
+
+			/*
+			 * Increment winkle counter and set all winkle bits if
+			 * all threads are winkling. This allows wakeup side to
+			 * distinguish between fast sleep and winkle state
+			 * loss. Fast sleep still has to resync the timebase so
+			 * this may not be a really big win.
+			 */
+			*state += 1 << PNV_CORE_IDLE_WINKLE_COUNT_SHIFT;
+			if ((*state & PNV_CORE_IDLE_WINKLE_COUNT_BITS) >> PNV_CORE_IDLE_WINKLE_COUNT_SHIFT == threads_per_core)
+				*state |= PNV_CORE_IDLE_THREAD_WINKLE_BITS;
+			WARN_ON((*state & PNV_CORE_IDLE_WINKLE_COUNT_BITS) == 0);
+		}
+
+		atomic_unlock_thread_idle();
+	}
+
+	srr1 = isa206_idle_insn_mayloss(type);
+
+	WARN_ON_ONCE(!srr1);
+	WARN_ON_ONCE(mfmsr() & (MSR_IR|MSR_DR));
+
+	if (unlikely((srr1 & SRR1_WAKEMASK_P8) == SRR1_WAKEHMI))
+		hmi_exception_realmode(NULL);
+
+	if (likely((srr1 & SRR1_WAKESTATE) != SRR1_WS_HVLOSS)) {
+		if (unlikely(type != PNV_THREAD_NAP)) {
+			atomic_lock_thread_idle();
+			if (type == PNV_THREAD_WINKLE) {
+				WARN_ON((*state & PNV_CORE_IDLE_WINKLE_COUNT_BITS) == 0);
+				*state -= 1 << PNV_CORE_IDLE_WINKLE_COUNT_SHIFT;
+				*state &= ~(thread << PNV_CORE_IDLE_THREAD_WINKLE_BITS_SHIFT);
+			}
+			atomic_unlock_and_stop_thread_idle();
+		}
+		return srr1;
+	}
+
+	/* HV state loss */
+	BUG_ON(type == PNV_THREAD_NAP);
+
+	atomic_lock_thread_idle();
+
+	full_winkle = false;
+	if (type == PNV_THREAD_WINKLE) {
+		WARN_ON((*state & PNV_CORE_IDLE_WINKLE_COUNT_BITS) == 0);
+		*state -= 1 << PNV_CORE_IDLE_WINKLE_COUNT_SHIFT;
+		if (*state & (thread << PNV_CORE_IDLE_THREAD_WINKLE_BITS_SHIFT)) {
+			*state &= ~(thread << PNV_CORE_IDLE_THREAD_WINKLE_BITS_SHIFT);
+			full_winkle = true;
+			BUG_ON(!sprs_saved);
+		}
+	}
+
+	WARN_ON(*state & thread);
+
+	if ((*state & ((1 << threads_per_core) - 1)) != 0)
+		goto core_woken;
+
+	/* Per-core SPRs */
+	if (full_winkle) {
+		mtspr(SPRN_TSCR,	sprs.tscr);
+		mtspr(SPRN_WORC,	sprs.worc);
+	}
+
+	if (power7_fastsleep_workaround_exit) {
+		rc = opal_config_cpu_idle_state(OPAL_CONFIG_IDLE_FASTSLEEP,
+						OPAL_CONFIG_IDLE_UNDO);
+		BUG_ON(rc);
+	}
+
+	/* TB */
+	if (opal_resync_timebase() != OPAL_SUCCESS)
+		BUG();
+
+core_woken:
+	if (!full_winkle)
+		goto subcore_woken;
+
+	if ((*state & local_paca->subcore_sibling_mask) != 0)
+		goto subcore_woken;
+
+	/* Per-subcore SPRs */
+	mtspr(SPRN_SDR1,	sprs.sdr1);
+	mtspr(SPRN_RPR,		sprs.rpr);
+	mtspr(SPRN_AMOR,	sprs.amor);
+
+subcore_woken:
+	atomic_unlock_and_stop_thread_idle();
+
+	/* Fast sleep does not lose SPRs */
+	if (!full_winkle)
+		return srr1;
+
+	/* Per-thread SPRs */
+	mtspr(SPRN_LPCR,	sprs.lpcr);
+	mtspr(SPRN_HFSCR,	sprs.hfscr);
+	mtspr(SPRN_FSCR,	sprs.fscr);
+	mtspr(SPRN_PURR,	sprs.purr);
+	mtspr(SPRN_SPURR,	sprs.spurr);
+	mtspr(SPRN_DSCR,	sprs.dscr);
+	mtspr(SPRN_WORT,	sprs.wort);
+
+	mtspr(SPRN_MMCRA,	sprs.mmcra);
+	mtspr(SPRN_MMCR0,	sprs.mmcr0);
+	mtspr(SPRN_MMCR1,	sprs.mmcr1);
+	mtspr(SPRN_MMCR2,	sprs.mmcr2);
+
+	mtspr(SPRN_SPRG3,	local_paca->sprg_vdso);
+
+	slb_shadow_reload();
+
+	return srr1;
+}
+
+extern unsigned long idle_kvm_start_guest(unsigned long srr1);
+
+static unsigned long power7_offline(void)
+{
+	unsigned long srr1;
+
+	mtmsr(MSR_IDLE);
+
+#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
+	/* Tell KVM we're entering idle. */
+	/******************************************************/
+	/*  N O T E   W E L L    ! ! !    N O T E   W E L L   */
+	/* The following store to HSTATE_HWTHREAD_STATE(r13)  */
+	/* MUST occur in real mode, i.e. with the MMU off,    */
+	/* and the MMU must stay off until we clear this flag */
+	/* and test HSTATE_HWTHREAD_REQ(r13) in               */
+	/* pnv_powersave_wakeup in this file.                 */
+	/* The reason is that another thread can switch the   */
+	/* MMU to a guest context whenever this flag is set   */
+	/* to KVM_HWTHREAD_IN_IDLE, and if the MMU was on,    */
+	/* that would potentially cause this thread to start  */
+	/* executing instructions from guest memory in        */
+	/* hypervisor mode, leading to a host crash or data   */
+	/* corruption, or worse.                              */
+	/******************************************************/
+	local_paca->kvm_hstate.hwthread_state = KVM_HWTHREAD_IN_IDLE;
+#endif
+
+	__ppc64_runlatch_off();
+	srr1 = power7_idle_insn(power7_offline_type);
+	__ppc64_runlatch_on();
+
+#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
+	if (local_paca->kvm_hstate.hwthread_state != KVM_HWTHREAD_IN_KERNEL) {
+		local_paca->kvm_hstate.hwthread_state = KVM_HWTHREAD_IN_KERNEL;
+		/* Order setting hwthread_state vs. testing hwthread_req */
+		smp_mb();
+	}
+	if (local_paca->kvm_hstate.hwthread_req)
+		srr1 = idle_kvm_start_guest(srr1);
+#endif
+
+	mtmsr(MSR_KERNEL);
+
+	return srr1;
+}
+
 static unsigned long __power7_idle_type(unsigned long type)
 {
 	unsigned long srr1;
@@ -320,9 +533,11 @@ static unsigned long __power7_idle_type(unsigned long type)
 	if (!prep_irq_for_idle_irqsoff())
 		return 0;
 
+	mtmsr(MSR_IDLE);
 	__ppc64_runlatch_off();
 	srr1 = power7_idle_insn(type);
 	__ppc64_runlatch_on();
+	mtmsr(MSR_KERNEL);
 
 	fini_irq_for_idle_irqsoff();
 
@@ -345,6 +560,244 @@ void power7_idle(void)
 	power7_idle_type(PNV_THREAD_NAP);
 }
 
+struct p9_sprs {
+	/* per core */
+	u64 ptcr;
+	u64 rpr;
+	u64 tscr;
+	u64 ldbar;
+	u64 amor;
+
+	/* per thread */
+	u64 lpcr;
+	u64 hfscr;
+	u64 fscr;
+	u64 pid;
+	u64 purr;
+	u64 spurr;
+	u64 dscr;
+	u64 wort;
+
+	u64 mmcra;
+	u32 mmcr0;
+	u32 mmcr1;
+	u64 mmcr2;
+};
+
+static unsigned long power9_idle_stop(unsigned long psscr, bool mmu_on)
+{
+	int cpu = raw_smp_processor_id();
+	int first = cpu_first_thread_sibling(cpu);
+	unsigned long *state = &paca_ptrs[first]->idle_state;
+	unsigned long srr1;
+	unsigned long mmcr0 = 0;
+	struct p9_sprs sprs;
+	bool sprs_saved = false;
+
+	memset(&sprs, 0, sizeof(sprs));
+
+	if (!(psscr & (PSSCR_EC|PSSCR_ESL))) {
+		BUG_ON(!mmu_on);
+
+		/*
+		 * Wake synchronously. SRESET via xscom may still cause
+		 * a 0x100 powersave wakeup with SRR1 reason!
+		 */
+		srr1 = isa3_idle_stop_noloss(psscr);
+		if (likely(!srr1))
+			return 0;
+
+		/*
+		 * Registers not saved, can't recover!
+		 * This would be a hardware bug
+		 */
+		BUG_ON((srr1 & SRR1_WAKESTATE) != SRR1_WS_NOLOSS);
+
+		goto out;
+	}
+
+	/* EC=ESL=1 case */
+#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
+	if (cpu_has_feature(CPU_FTR_P9_TM_XER_SO_BUG)) {
+		local_paca->requested_psscr = psscr;
+		/* order setting requested_psscr vs testing dont_stop */
+		smp_mb();
+		if (atomic_read(&local_paca->dont_stop)) {
+			local_paca->requested_psscr = 0;
+			return 0;
+		}
+	}
+#endif
+
+	if (!cpu_has_feature(CPU_FTR_POWER9_DD2_1)) {
+		 /*
+		  * POWER9 DD2 can incorrectly set PMAO when waking up
+		  * after a state-loss idle. Saving and restoring MMCR0
+		  * over idle is a workaround.
+		  */
+		mmcr0		= mfspr(SPRN_MMCR0);
+	}
+	if ((psscr & PSSCR_RL_MASK) >= pnv_first_hv_loss_level) {
+		sprs.lpcr	= mfspr(SPRN_LPCR);
+		sprs.hfscr	= mfspr(SPRN_HFSCR);
+		sprs.fscr	= mfspr(SPRN_FSCR);
+		sprs.pid	= mfspr(SPRN_PID);
+		sprs.purr	= mfspr(SPRN_PURR);
+		sprs.spurr	= mfspr(SPRN_SPURR);
+		sprs.dscr	= mfspr(SPRN_DSCR);
+		sprs.wort	= mfspr(SPRN_WORT);
+
+		sprs.mmcra	= mfspr(SPRN_MMCRA);
+		sprs.mmcr0	= mfspr(SPRN_MMCR0);
+		sprs.mmcr1	= mfspr(SPRN_MMCR1);
+		sprs.mmcr2	= mfspr(SPRN_MMCR2);
+
+		sprs.ptcr	= mfspr(SPRN_PTCR);
+		sprs.rpr	= mfspr(SPRN_RPR);
+		sprs.tscr	= mfspr(SPRN_TSCR);
+		sprs.ldbar	= mfspr(SPRN_LDBAR);
+		sprs.amor	= mfspr(SPRN_AMOR);
+
+		sprs_saved = true;
+
+		atomic_start_thread_idle();
+	}
+
+	srr1 = isa3_idle_stop_mayloss(psscr);
+
+#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
+	local_paca->requested_psscr = 0;
+#endif
+
+	psscr = mfspr(SPRN_PSSCR);
+
+	WARN_ON_ONCE(!srr1);
+	WARN_ON_ONCE(mfmsr() & (MSR_IR|MSR_DR));
+
+	if ((srr1 & SRR1_WAKESTATE) != SRR1_WS_NOLOSS) {
+		unsigned long mmcra;
+
+		/*
+		 * Workaround for POWER9 DD2.0, if we lost resources, the ERAT
+		 * might have been corrupted and needs flushing. We also need
+		 * to reload MMCR0 (see mmcr0 comment above).
+		 */
+		if (!cpu_has_feature(CPU_FTR_POWER9_DD2_1)) {
+			asm volatile(PPC_INVALIDATE_ERAT);
+			mtspr(SPRN_MMCR0, mmcr0);
+		}
+
+		/*
+		 * DD2.2 and earlier need to set then clear bit 60 in MMCRA
+		 * to ensure the PMU starts running.
+		 */
+		mmcra = mfspr(SPRN_MMCRA);
+		mmcra |= PPC_BIT(60);
+		mtspr(SPRN_MMCRA, mmcra);
+		mmcra &= ~PPC_BIT(60);
+		mtspr(SPRN_MMCRA, mmcra);
+	}
+
+	if (unlikely((srr1 & SRR1_WAKEMASK_P8) == SRR1_WAKEHMI))
+		hmi_exception_realmode(NULL);
+
+	/*
+	 * On POWER9, SRR1 bits do not match exactly as expected.
+	 * SRR1_WS_GPRLOSS (10b) can also result in SPR loss, so
+	 * always test PSSCR if there is any state loss.
+	 */
+	if (likely((psscr & PSSCR_RL_MASK) < pnv_first_hv_loss_level)) {
+		if (sprs_saved)
+			atomic_stop_thread_idle();
+		goto out;
+	}
+
+	/* HV state loss */
+	BUG_ON(!sprs_saved);
+
+	atomic_lock_thread_idle();
+
+	if ((*state & ((1 << threads_per_core) - 1)) != 0)
+		goto core_woken;
+
+	/* Per-core SPRs */
+	mtspr(SPRN_PTCR,	sprs.ptcr);
+	mtspr(SPRN_RPR,		sprs.rpr);
+	mtspr(SPRN_TSCR,	sprs.tscr);
+	mtspr(SPRN_LDBAR,	sprs.ldbar);
+	mtspr(SPRN_AMOR,	sprs.amor);
+
+	if ((psscr & PSSCR_RL_MASK) >= pnv_first_tb_loss_level) {
+		/* TB loss */
+		if (opal_resync_timebase() != OPAL_SUCCESS)
+			BUG();
+	}
+
+core_woken:
+	atomic_unlock_and_stop_thread_idle();
+
+	/* Per-thread SPRs */
+	mtspr(SPRN_LPCR,	sprs.lpcr);
+	mtspr(SPRN_HFSCR,	sprs.hfscr);
+	mtspr(SPRN_FSCR,	sprs.fscr);
+	mtspr(SPRN_PID,		sprs.pid);
+	mtspr(SPRN_PURR,	sprs.purr);
+	mtspr(SPRN_SPURR,	sprs.spurr);
+	mtspr(SPRN_DSCR,	sprs.dscr);
+	mtspr(SPRN_WORT,	sprs.wort);
+
+	mtspr(SPRN_MMCRA,	sprs.mmcra);
+	mtspr(SPRN_MMCR0,	sprs.mmcr0);
+	mtspr(SPRN_MMCR1,	sprs.mmcr1);
+	mtspr(SPRN_MMCR2,	sprs.mmcr2);
+
+	mtspr(SPRN_SPRG3,	local_paca->sprg_vdso);
+
+	if (!radix_enabled())
+		slb_shadow_reload();
+
+out:
+	if (mmu_on)
+		mtmsr(MSR_KERNEL);
+
+	return srr1;
+}
+
+static unsigned long power9_offline_stop(unsigned long psscr)
+{
+	unsigned long srr1;
+
+#ifndef CONFIG_KVM_BOOK3S_HV_POSSIBLE
+	__ppc64_runlatch_off();
+	srr1 = power9_idle_stop(psscr, true);
+	__ppc64_runlatch_on();
+#else
+	/*
+	 * Tell KVM we're entering idle.
+	 * This does not have to be done in real mode because the P9 MMU
+	 * is independent per-thread. Some steppings share radix/hash mode
+	 * between threads, but in that case KVM has a barrier sync in real
+	 * mode before and after switching between radix and hash.
+	 */
+	local_paca->kvm_hstate.hwthread_state = KVM_HWTHREAD_IN_IDLE;
+
+	__ppc64_runlatch_off();
+	srr1 = power9_idle_stop(psscr, false);
+	__ppc64_runlatch_on();
+
+	if (local_paca->kvm_hstate.hwthread_state != KVM_HWTHREAD_IN_KERNEL) {
+		local_paca->kvm_hstate.hwthread_state = KVM_HWTHREAD_IN_KERNEL;
+		/* Order setting hwthread_state vs. testing hwthread_req */
+		smp_mb();
+	}
+	if (local_paca->kvm_hstate.hwthread_req)
+		srr1 = idle_kvm_start_guest(srr1);
+	mtmsr(MSR_KERNEL);
+#endif
+
+	return srr1;
+}
+
 static unsigned long __power9_idle_type(unsigned long stop_psscr_val,
 				      unsigned long stop_psscr_mask)
 {
@@ -358,7 +811,7 @@ static unsigned long __power9_idle_type(unsigned long stop_psscr_val,
 	psscr = (psscr & ~stop_psscr_mask) | stop_psscr_val;
 
 	__ppc64_runlatch_off();
-	srr1 = power9_idle_stop(psscr);
+	srr1 = power9_idle_stop(psscr, true);
 	__ppc64_runlatch_on();
 
 	fini_irq_for_idle_irqsoff();
@@ -407,7 +860,7 @@ void pnv_power9_force_smt4_catch(void)
 			atomic_inc(&paca_ptrs[cpu0+thr]->dont_stop);
 	}
 	/* order setting dont_stop vs testing requested_psscr */
-	mb();
+	smp_mb();
 	for (thr = 0; thr < threads_per_core; ++thr) {
 		if (!paca_ptrs[cpu0+thr]->requested_psscr)
 			++awake_threads;
@@ -466,7 +919,7 @@ static void pnv_program_cpu_hotplug_lpcr(unsigned int cpu, u64 lpcr_val)
 	 * Program the LPCR via stop-api only if the deepest stop state
 	 * can lose hypervisor context.
 	 */
-	if (supported_cpuidle_states & OPAL_PM_LOSE_FULL_CONTEXT)
+	if (pm_flags_possible & OPAL_PM_LOSE_FULL_CONTEXT)
 		opal_slw_set_reg(pir, SPRN_LPCR, lpcr_val);
 }
 
@@ -478,7 +931,6 @@ static void pnv_program_cpu_hotplug_lpcr(unsigned int cpu, u64 lpcr_val)
 unsigned long pnv_cpu_offline(unsigned int cpu)
 {
 	unsigned long srr1;
-	u32 idle_states = pnv_get_supported_cpuidle_states();
 	u64 lpcr_val;
 
 	/*
@@ -503,15 +955,8 @@ unsigned long pnv_cpu_offline(unsigned int cpu)
 		psscr = (psscr & ~pnv_deepest_stop_psscr_mask) |
 						pnv_deepest_stop_psscr_val;
 		srr1 = power9_offline_stop(psscr);
-
-	} else if ((idle_states & OPAL_PM_WINKLE_ENABLED) &&
-		   (idle_states & OPAL_PM_LOSE_FULL_CONTEXT)) {
-		srr1 = power7_idle_insn(PNV_THREAD_WINKLE);
-	} else if ((idle_states & OPAL_PM_SLEEP_ENABLED) ||
-		   (idle_states & OPAL_PM_SLEEP_ENABLED_ER1)) {
-		srr1 = power7_idle_insn(PNV_THREAD_SLEEP);
-	} else if (idle_states & OPAL_PM_NAP_ENABLED) {
-		srr1 = power7_idle_insn(PNV_THREAD_NAP);
+	} else if (cpu_has_feature(CPU_FTR_ARCH_206) && power7_offline_type) {
+		srr1 = power7_offline();
 	} else {
 		/* This is the fallback method. We emulate snooze */
 		while (!generic_check_cpu_restart(cpu)) {
@@ -623,7 +1068,8 @@ static int __init pnv_power9_idle_init(struct device_node *np, u32 *flags,
 	u64 *psscr_val = NULL;
 	u64 *psscr_mask = NULL;
 	u32 *residency_ns = NULL;
-	u64 max_residency_ns = 0;
+	u64 max_deep_residency_ns = 0;
+	u64 max_default_residency_ns = 0;
 	int rc = 0, i;
 
 	psscr_val = kcalloc(dt_idle_states, sizeof(*psscr_val), GFP_KERNEL);
@@ -661,26 +1107,32 @@ static int __init pnv_power9_idle_init(struct device_node *np, u32 *flags,
 	}
 
 	/*
-	 * Set pnv_first_deep_stop_state, pnv_deepest_stop_psscr_{val,mask},
-	 * and the pnv_default_stop_{val,mask}.
-	 *
-	 * pnv_first_deep_stop_state should be set to the first stop
-	 * level to cause hypervisor state loss.
-	 *
 	 * pnv_deepest_stop_{val,mask} should be set to values corresponding to
 	 * the deepest stop state.
 	 *
 	 * pnv_default_stop_{val,mask} should be set to values corresponding to
-	 * the shallowest (OPAL_PM_STOP_INST_FAST) loss-less stop state.
+	 * the deepest loss-less (OPAL_PM_STOP_INST_FAST) stop state.
 	 */
-	pnv_first_deep_stop_state = MAX_STOP_STATE;
+	pnv_first_tb_loss_level = MAX_STOP_STATE + 1;
+	pnv_first_hv_loss_level = MAX_STOP_STATE + 1;
 	for (i = 0; i < dt_idle_states; i++) {
 		int err;
 		u64 psscr_rl = psscr_val[i] & PSSCR_RL_MASK;
 
-		if ((flags[i] & OPAL_PM_LOSE_FULL_CONTEXT) &&
-		     (pnv_first_deep_stop_state > psscr_rl))
-			pnv_first_deep_stop_state = psscr_rl;
+		/*
+		 * Deep state idle entry/exit does not optimize states that
+		 * lose timebase but not other SPRs, it always restores all
+		 * SPRs for any HV loss level. POWER9 does not have any
+		 * states where this is applies.
+		 */
+		if ((flags[i] & (OPAL_PM_LOSE_FULL_CONTEXT |
+				 OPAL_PM_TIMEBASE_STOP)) &&
+		    (pnv_first_hv_loss_level > psscr_rl))
+			pnv_first_hv_loss_level = psscr_rl;
+
+		if ((flags[i] & OPAL_PM_TIMEBASE_STOP) &&
+		    (pnv_first_tb_loss_level > psscr_rl))
+			pnv_first_tb_loss_level = psscr_rl;
 
 		err = validate_psscr_val_mask(&psscr_val[i], &psscr_mask[i],
 					      flags[i]);
@@ -689,19 +1141,21 @@ static int __init pnv_power9_idle_init(struct device_node *np, u32 *flags,
 			continue;
 		}
 
-		if (max_residency_ns < residency_ns[i]) {
-			max_residency_ns = residency_ns[i];
+		if (max_deep_residency_ns < residency_ns[i]) {
+			max_deep_residency_ns = residency_ns[i];
 			pnv_deepest_stop_psscr_val = psscr_val[i];
 			pnv_deepest_stop_psscr_mask = psscr_mask[i];
 			pnv_deepest_stop_flag = flags[i];
 			deepest_stop_found = true;
 		}
 
-		if (!default_stop_found &&
+		if (max_default_residency_ns < residency_ns[i] &&
 		    (flags[i] & OPAL_PM_STOP_INST_FAST)) {
+			max_default_residency_ns = residency_ns[i];
 			pnv_default_stop_val = psscr_val[i];
 			pnv_default_stop_mask = psscr_mask[i];
 			default_stop_found = true;
+			WARN_ON(flags[i] & OPAL_PM_LOSE_FULL_CONTEXT);
 		}
 	}
 
@@ -721,15 +1175,48 @@ static int __init pnv_power9_idle_init(struct device_node *np, u32 *flags,
 			pnv_deepest_stop_psscr_mask);
 	}
 
-	pr_info("cpuidle-powernv: Requested Level (RL) value of first deep stop = 0x%llx\n",
-		pnv_first_deep_stop_state);
+	pr_info("cpuidle-powernv: First stop level that may lose SPRs = 0x%lld\n",
+		pnv_first_hv_loss_level);
+
+	pr_info("cpuidle-powernv: First stop level that may lose timebase = 0x%lld\n",
+		pnv_first_tb_loss_level);
 out:
 	kfree(psscr_val);
 	kfree(psscr_mask);
 	kfree(residency_ns);
+
 	return rc;
 }
 
+static void __init pnv_disable_deep_states(void)
+{
+	/*
+	 * The stop-api is unable to restore hypervisor
+	 * resources on wakeup from platform idle states which
+	 * lose full context. So disable such states.
+	 */
+	pm_flags_possible &= ~OPAL_PM_LOSE_FULL_CONTEXT;
+	pr_warn("cpuidle-powernv: Disabling idle states that lose full context\n");
+	pr_warn("cpuidle-powernv: Idle power-savings, CPU-Hotplug affected\n");
+
+	if (cpu_has_feature(CPU_FTR_ARCH_300) &&
+	    (pnv_deepest_stop_flag & OPAL_PM_LOSE_FULL_CONTEXT)) {
+		/*
+		 * Use the default stop state for CPU-Hotplug
+		 * if available.
+		 */
+		if (default_stop_found) {
+			pnv_deepest_stop_psscr_val = pnv_default_stop_val;
+			pnv_deepest_stop_psscr_mask = pnv_default_stop_mask;
+			pr_warn("cpuidle-powernv: Offlined CPUs will stop with psscr = 0x%016llx\n",
+				pnv_deepest_stop_psscr_val);
+		} else { /* Fallback to snooze loop for CPU-Hotplug */
+			deepest_stop_found = false;
+			pr_warn("cpuidle-powernv: Offlined CPUs will busy wait\n");
+		}
+	}
+}
+
 /*
  * Probe device tree for supported idle states
  */
@@ -766,42 +1253,78 @@ static void __init pnv_probe_idle_states(void)
 	}
 
 	for (i = 0; i < dt_idle_states; i++)
-		supported_cpuidle_states |= flags[i];
+		pm_flags_possible |= flags[i];
 
 out:
 	kfree(flags);
 }
+
 static int __init pnv_init_idle_states(void)
 {
+	int cpu;
 
-	supported_cpuidle_states = 0;
+	/* Set up PACA fields */
+	for_each_present_cpu(cpu) {
+		struct paca_struct *p = paca_ptrs[cpu];
+
+		p->idle_state = 0;
+		if (cpu == cpu_first_thread_sibling(cpu))
+			p->idle_state = (1 << threads_per_core) - 1;
+
+		if (!cpu_has_feature(CPU_FTR_ARCH_300)) {
+			/* P7/P8 nap */
+			p->thread_idle_state = PNV_THREAD_RUNNING;
+			p->thread_mask = 1 << cpu_thread_in_core(cpu);
+		} else {
+			/* P9 stop */
+#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
+			p->requested_psscr = 0;
+			atomic_set(&p->dont_stop, 0);
+#endif
+		}
+	}
+
+	pm_flags_possible = 0;
 
 	if (cpuidle_disable != IDLE_NO_OVERRIDE)
 		goto out;
 
 	pnv_probe_idle_states();
 
-	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);
-	} else {
-		/*
-		 * OPAL_PM_SLEEP_ENABLED_ER1 is set. It indicates that
-		 * workaround is needed to use fastsleep. Provide sysfs
-		 * control to choose how this workaround has to be applied.
-		 */
-		device_create_file(cpu_subsys.dev_root,
+	if (!cpu_has_feature(CPU_FTR_ARCH_300)) {
+		if (!(pm_flags_possible & OPAL_PM_SLEEP_ENABLED_ER1)) {
+			power7_fastsleep_workaround_entry = false;
+			power7_fastsleep_workaround_exit = false;
+		} else {
+			/*
+			 * OPAL_PM_SLEEP_ENABLED_ER1 is set. It indicates that
+			 * workaround is needed to use fastsleep. Provide sysfs
+			 * control to choose how this workaround has to be
+			 * applied.
+			 */
+			device_create_file(cpu_subsys.dev_root,
 				&dev_attr_fastsleep_workaround_applyonce);
-	}
+		}
 
-	pnv_alloc_idle_core_states();
+		update_subcore_sibling_mask();
+
+		if (pm_flags_possible & OPAL_PM_NAP_ENABLED) {
+			ppc_md.power_save = power7_idle;
+			power7_offline_type = PNV_THREAD_NAP;
+		}
 
-	if (supported_cpuidle_states & OPAL_PM_NAP_ENABLED)
-		ppc_md.power_save = power7_idle;
+		if ((pm_flags_possible & OPAL_PM_WINKLE_ENABLED) &&
+			   (pm_flags_possible & OPAL_PM_LOSE_FULL_CONTEXT))
+			power7_offline_type = PNV_THREAD_WINKLE;
+		else if ((pm_flags_possible & OPAL_PM_SLEEP_ENABLED) ||
+			   (pm_flags_possible & OPAL_PM_SLEEP_ENABLED_ER1))
+			power7_offline_type = PNV_THREAD_SLEEP;
+	}
+
+	if (pm_flags_possible & OPAL_PM_LOSE_FULL_CONTEXT) {
+		if (pnv_save_sprs_for_deep_states())
+			pnv_disable_deep_states();
+	}
 
 out:
 	return 0;
diff --git a/arch/powerpc/platforms/powernv/subcore.c b/arch/powerpc/platforms/powernv/subcore.c
index 45563004feda..1d7a9fd30dd1 100644
--- a/arch/powerpc/platforms/powernv/subcore.c
+++ b/arch/powerpc/platforms/powernv/subcore.c
@@ -183,7 +183,7 @@ static void unsplit_core(void)
 	cpu = smp_processor_id();
 	if (cpu_thread_in_core(cpu) != 0) {
 		while (mfspr(SPRN_HID0) & mask)
-			power7_idle_insn(PNV_THREAD_NAP);
+			power7_idle_type(PNV_THREAD_NAP);
 
 		per_cpu(split_state, cpu).step = SYNC_STEP_UNSPLIT;
 		return;
diff --git a/arch/powerpc/xmon/xmon.c b/arch/powerpc/xmon/xmon.c
index fdc43d5ccb42..4fcae8e8e741 100644
--- a/arch/powerpc/xmon/xmon.c
+++ b/arch/powerpc/xmon/xmon.c
@@ -2417,7 +2417,6 @@ static void dump_one_paca(int cpu)
 	DUMP(p, irq_happened, "%#-*x");
 	DUMP(p, io_sync, "%#-*x");
 	DUMP(p, irq_work_pending, "%#-*x");
-	DUMP(p, nap_state_lost, "%#-*x");
 	DUMP(p, sprg_vdso, "%#-*llx");
 
 #ifdef CONFIG_PPC_TRANSACTIONAL_MEM
@@ -2425,19 +2424,17 @@ static void dump_one_paca(int cpu)
 #endif
 
 #ifdef CONFIG_PPC_POWERNV
-	DUMP(p, core_idle_state_ptr, "%-*px");
-	DUMP(p, thread_idle_state, "%#-*x");
-	DUMP(p, thread_mask, "%#-*x");
-	DUMP(p, subcore_sibling_mask, "%#-*x");
-	DUMP(p, requested_psscr, "%#-*llx");
-	DUMP(p, stop_sprs.pid, "%#-*llx");
-	DUMP(p, stop_sprs.ldbar, "%#-*llx");
-	DUMP(p, stop_sprs.fscr, "%#-*llx");
-	DUMP(p, stop_sprs.hfscr, "%#-*llx");
-	DUMP(p, stop_sprs.mmcr1, "%#-*llx");
-	DUMP(p, stop_sprs.mmcr2, "%#-*llx");
-	DUMP(p, stop_sprs.mmcra, "%#-*llx");
-	DUMP(p, dont_stop.counter, "%#-*x");
+	DUMP(p, idle_state, "%#-*lx");
+	if (!cpu_has_feature(CPU_FTR_ARCH_300)) {
+		DUMP(p, thread_idle_state, "%#-*x");
+		DUMP(p, thread_mask, "%#-*x");
+		DUMP(p, subcore_sibling_mask, "%#-*x");
+	} else {
+#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
+		DUMP(p, requested_psscr, "%#-*llx");
+		DUMP(p, dont_stop.counter, "%#-*x");
+#endif
+	}
 #endif
 
 	DUMP(p, accounting.utime, "%#-*lx");


More information about the Linuxppc-dev mailing list