Merge branch 'topic/ppc-kvm' into next

Merge our topic branch shared with KVM. In particular this includes the
rewrite of the idle code into C.

7 files changed, 230 insertions, 988 deletions

diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c
index 60b82198de7c..8e02444e9d3d 100644
--- a/arch/powerpc/kernel/asm-offsets.c
+++ b/arch/powerpc/kernel/asm-offsets.c
@@ -271,7 +271,6 @@ 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
@@ -773,23 +772,6 @@ 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/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S
index bedd89438827..6b86055e5251 100644
--- a/arch/powerpc/kernel/exceptions-64s.S
+++ b/arch/powerpc/kernel/exceptions-64s.S
@@ -121,7 +121,9 @@ EXC_VIRT_NONE(0x4000, 0x100)
 	mfspr	r10,SPRN_SRR1 ;						\
 	rlwinm.	r10,r10,47-31,30,31 ;					\
 	beq-	1f ;							\
-	cmpwi	cr3,r10,2 ;						\
+	cmpwi	cr1,r10,2 ;						\
+	mfspr	r3,SPRN_SRR1 ;						\
+	bltlr	cr1 ;	/* no state loss, return to idle caller */	\
 	BRANCH_TO_C000(r10, system_reset_idle_common) ;			\
 1:									\
 	KVMTEST_PR(n) ;							\
@@ -145,8 +147,11 @@ 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
+	/*
+	 * This must be a direct branch (without linker branch stub) because
+	 * we can not use TOC at this point as r2 may not be restored yet.
+	 */
+	b	idle_return_gpr_loss
 #endif
 
 /*
@@ -429,17 +434,17 @@ 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	cr1,r10,2
+	bltlr	cr1	/* 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/hw_breakpoint.c b/arch/powerpc/kernel/hw_breakpoint.c
index fec8a6773119..da307dd93ee3 100644
--- a/arch/powerpc/kernel/hw_breakpoint.c
+++ b/arch/powerpc/kernel/hw_breakpoint.c
@@ -29,11 +29,15 @@
 #include <linux/kernel.h>
 #include <linux/sched.h>
 #include <linux/smp.h>
+#include <linux/debugfs.h>
+#include <linux/init.h>
 
 #include <asm/hw_breakpoint.h>
 #include <asm/processor.h>
 #include <asm/sstep.h>
 #include <asm/debug.h>
+#include <asm/debugfs.h>
+#include <asm/hvcall.h>
 #include <linux/uaccess.h>
 
 /*
@@ -174,7 +178,7 @@ int hw_breakpoint_arch_parse(struct perf_event *bp,
 	if (!ppc_breakpoint_available())
 		return -ENODEV;
 	length_max = 8; /* DABR */
-	if (cpu_has_feature(CPU_FTR_DAWR)) {
+	if (dawr_enabled()) {
 		length_max = 512 ; /* 64 doublewords */
 		/* DAWR region can't cross 512 boundary */
 		if ((attr->bp_addr >> 9) !=
@@ -376,3 +380,59 @@ void hw_breakpoint_pmu_read(struct perf_event *bp)
 {
 	/* TODO */
 }
+
+bool dawr_force_enable;
+EXPORT_SYMBOL_GPL(dawr_force_enable);
+
+static ssize_t dawr_write_file_bool(struct file *file,
+				    const char __user *user_buf,
+				    size_t count, loff_t *ppos)
+{
+	struct arch_hw_breakpoint null_brk = {0, 0, 0};
+	size_t rc;
+
+	/* Send error to user if they hypervisor won't allow us to write DAWR */
+	if ((!dawr_force_enable) &&
+	    (firmware_has_feature(FW_FEATURE_LPAR)) &&
+	    (set_dawr(&null_brk) != H_SUCCESS))
+		return -1;
+
+	rc = debugfs_write_file_bool(file, user_buf, count, ppos);
+	if (rc)
+		return rc;
+
+	/* If we are clearing, make sure all CPUs have the DAWR cleared */
+	if (!dawr_force_enable)
+		smp_call_function((smp_call_func_t)set_dawr, &null_brk, 0);
+
+	return rc;
+}
+
+static const struct file_operations dawr_enable_fops = {
+	.read =		debugfs_read_file_bool,
+	.write =	dawr_write_file_bool,
+	.open =		simple_open,
+	.llseek =	default_llseek,
+};
+
+static int __init dawr_force_setup(void)
+{
+	dawr_force_enable = false;
+
+	if (cpu_has_feature(CPU_FTR_DAWR)) {
+		/* Don't setup sysfs file for user control on P8 */
+		dawr_force_enable = true;
+		return 0;
+	}
+
+	if (PVR_VER(mfspr(SPRN_PVR)) == PVR_POWER9) {
+		/* Turn DAWR off by default, but allow admin to turn it on */
+		dawr_force_enable = false;
+		debugfs_create_file_unsafe("dawr_enable_dangerous", 0600,
+					   powerpc_debugfs_root,
+					   &dawr_force_enable,
+					   &dawr_enable_fops);
+	}
+	return 0;
+}
+arch_initcall(dawr_force_setup);
diff --git a/arch/powerpc/kernel/idle_book3s.S b/arch/powerpc/kernel/idle_book3s.S
index 4a860d3b9229..2dfbd5d5b932 100644
--- a/arch/powerpc/kernel/idle_book3s.S
+++ b/arch/powerpc/kernel/idle_book3s.S
@@ -1,995 +1,188 @@
 /*
- *  This file contains idle entry/exit functions for POWER7,
- *  POWER8 and POWER9 CPUs.
+ *  Copyright 2018, IBM Corporation.
  *
  *  This program is free software; you can redistribute it and/or
  *  modify it under the terms of the GNU General Public License
  *  as published by the Free Software Foundation; either version
  *  2 of the License, or (at your option) any later version.
+ *
+ *  This file contains general idle entry/exit functions to save
+ *  and restore stack and NVGPRs which allows C code to call idle
+ *  states that lose GPRs, and it will return transparently with
+ *  SRR1 wakeup reason return value.
+ *
+ *  The platform / CPU caller must ensure SPRs and any other non-GPR
+ *  state is saved and restored correctly, handle KVM, interrupts, etc.
  */
 
-#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>
-#include <asm/asm-compat.h>
-#include <asm/feature-fixups.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
  *
- * 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.
+ * No state will be lost regardless of wakeup mechanism (interrupt or NIA).
+ *
+ * An EC=0 type wakeup will return with a value of 0. SRESET wakeup (which can
+ * happen with xscom SRESET and possibly MCE) may clobber volatiles except LR,
+ * and must blr, to return to caller with r3 set according to caller's expected
+ * return code (for Book3S/64 that is SRR1).
  */
-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(isa300_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.
+ * The SRESET wakeup returns to this function's caller by calling
+ * idle_return_gpr_loss with r3 set to desired return value.
+ *
+ * A wakeup without GPR loss may alteratively be handled as in
+ * isa300_idle_stop_noloss and blr directly, as an optimisation.
+ *
+ * The caller is responsible for saving/restoring SPRs, MSR, timebase,
+ * etc.
  */
-
-core_idle_lock_held:
-	HMT_LOW
-3:	lwz	r15,0(r14)
-	andis.	r15,r15,PNV_CORE_IDLE_LOCK_BIT@h
-	bne	3b
-	HMT_MEDIUM
-	lwarx	r15,0,r14
-	andis.	r9,r15,PNV_CORE_IDLE_LOCK_BIT@h
-	bne-	core_idle_lock_held
-	blr
-
-/* Reuse some unused pt_regs slots for AMR/IAMR/UAMOR/UAMOR */
-#define PNV_POWERSAVE_AMR	_TRAP
-#define PNV_POWERSAVE_IAMR	_DAR
-#define PNV_POWERSAVE_UAMOR	_DSISR
-#define PNV_POWERSAVE_AMOR	RESULT
+_GLOBAL(isa300_idle_stop_mayloss)
+	mtspr 	SPRN_PSSCR,r3
+	std	r1,PACAR1(r13)
+	mflr	r4
+	mfcr	r5
+	/* use stack red zone rather than a new frame for saving regs */
+	std	r2,-8*0(r1)
+	std	r14,-8*1(r1)
+	std	r15,-8*2(r1)
+	std	r16,-8*3(r1)
+	std	r17,-8*4(r1)
+	std	r18,-8*5(r1)
+	std	r19,-8*6(r1)
+	std	r20,-8*7(r1)
+	std	r21,-8*8(r1)
+	std	r22,-8*9(r1)
+	std	r23,-8*10(r1)
+	std	r24,-8*11(r1)
+	std	r25,-8*12(r1)
+	std	r26,-8*13(r1)
+	std	r27,-8*14(r1)
+	std	r28,-8*15(r1)
+	std	r29,-8*16(r1)
+	std	r30,-8*17(r1)
+	std	r31,-8*18(r1)
+	std	r4,-8*19(r1)
+	std	r5,-8*20(r1)
+	/* 168 bytes */
+	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
+ *
+ * The idle wakeup SRESET interrupt can call this after calling
+ * to return to the idle sleep function caller with r3 as the return code.
  *
- * Address of idle handler to branch to in realmode in r4
+ * This must not be used if idle was entered via a _noloss function (use
+ * a simple blr instead).
  */
-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)
-
-BEGIN_FTR_SECTION
-	mfspr	r4, SPRN_AMR
-	mfspr	r5, SPRN_IAMR
-	mfspr	r6, SPRN_UAMOR
-	std	r4, PNV_POWERSAVE_AMR(r1)
-	std	r5, PNV_POWERSAVE_IAMR(r1)
-	std	r6, PNV_POWERSAVE_UAMOR(r1)
-BEGIN_FTR_SECTION_NESTED(42)
-	mfspr	r7, SPRN_AMOR
-	std	r7, PNV_POWERSAVE_AMOR(r1)
-END_FTR_SECTION_NESTED_IFSET(CPU_FTR_HVMODE, 42)
-END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
-
-	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)
+	ld	r4,-8*19(r1)
+	ld	r5,-8*20(r1)
+	mtlr	r4
+	mtcr	r5
+	/*
+	 * KVM nap requires r2 to be saved, rather than just restoring it
+	 * from PACATOC. This could be avoided for that less common case
+	 * if KVM saved its r2.
+	 */
+	ld	r2,-8*0(r1)
+	ld	r14,-8*1(r1)
+	ld	r15,-8*2(r1)
+	ld	r16,-8*3(r1)
+	ld	r17,-8*4(r1)
+	ld	r18,-8*5(r1)
+	ld	r19,-8*6(r1)
+	ld	r20,-8*7(r1)
+	ld	r21,-8*8(r1)
+	ld	r22,-8*9(r1)
+	ld	r23,-8*10(r1)
+	ld	r24,-8*11(r1)
+	ld	r25,-8*12(r1)
+	ld	r26,-8*13(r1)
+	ld	r27,-8*14(r1)
+	ld	r28,-8*15(r1)
+	ld	r29,-8*16(r1)
+	ld	r30,-8*17(r1)
+	ld	r31,-8*18(r1)
+	blr
 
 /*
  * This is the sequence required to execute idle instructions, as
  * specified in ISA v2.07 (and earlier). MSR[IR] and MSR[DR] must be 0.
+ *
+ * The 0(r1) slot is used to save r2 in isa206, so use that here.
  */
 #define IDLE_STATE_ENTER_SEQ_NORET(IDLE_INST)			\
 	/* Magic NAP/SLEEP/WINKLE mode enter sequence */	\
-	std	r0,0(r1);					\
+	std	r2,0(r1);					\
 	ptesync;						\
-	ld	r0,0(r1);					\
-236:	cmpd	cr0,r0,r0;					\
+	ld	r2,0(r1);					\
+236:	cmpd	cr0,r2,r2;					\
 	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@h
-3:
-lwarx_loop1:
-	lwarx	r15,0,r14
-
-	andis.	r9,r15,PNV_CORE_IDLE_LOCK_BIT@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@h
-	stwcx.	r15,0,r14
-	bne-	lwarx_loop1
-	isync
-
-	/* Fast sleep workaround */
-	li	r3,1
-	li	r4,1
-	bl	opal_config_cpu_idle_state
-
-	/* Unlock */
-	xoris	r15,r15,PNV_CORE_IDLE_LOCK_BIT@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@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.
- *
- * 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.
- *
- * 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@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
+	IDLE_INST;						\
+	b	.	/* catch bugs */
 
 /*
- * Check whether we have woken up with hypervisor state loss.
- * If yes, restore hypervisor state and return back to link.
+ * Desired instruction type in r3
  *
- * 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
+ * GPRs may be lost, so they are saved here. Wakeup is by interrupt only.
+ * The SRESET wakeup returns to this function's caller by calling
+ * idle_return_gpr_loss with r3 set to desired return value.
  *
- * r13 - PACA
- * cr3 - gt if waking up with partial/complete hypervisor state loss
+ * A wakeup without GPR loss may alteratively be handled as in
+ * isa300_idle_stop_noloss and blr directly, as an optimisation.
  *
- * If ISA300:
- * cr4 - gt or eq if waking up from complete hypervisor state loss.
+ * The caller is responsible for saving/restoring SPRs, MSR, timebase,
+ * etc.
  *
- * If ISA207:
- * r4 - PACA_THREAD_IDLE_STATE
+ * This must be called in real-mode (MSR_IDLE).
  */
-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@h
-	bnel-	core_idle_lock_held
-	oris	r15,r15,PNV_CORE_IDLE_LOCK_BIT@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 for saving regs */
+	std	r2,-8*0(r1)
+	std	r14,-8*1(r1)
+	std	r15,-8*2(r1)
+	std	r16,-8*3(r1)
+	std	r17,-8*4(r1)
+	std	r18,-8*5(r1)
+	std	r19,-8*6(r1)
+	std	r20,-8*7(r1)
+	std	r21,-8*8(r1)
+	std	r22,-8*9(r1)
+	std	r23,-8*10(r1)
+	std	r24,-8*11(r1)
+	std	r25,-8*12(r1)
+	std	r26,-8*13(r1)
+	std	r27,-8*14(r1)
+	std	r28,-8*15(r1)
+	std	r29,-8*16(r1)
+	std	r30,-8*17(r1)
+	std	r31,-8*18(r1)
+	std	r4,-8*19(r1)
+	std	r5,-8*20(r1)
+	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@h
-	subis	r15,r15,PNV_CORE_IDLE_WINKLE_COUNT@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@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@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
-
-	/* 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)
-#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)
-
-BEGIN_FTR_SECTION
-	/* These regs were saved in pnv_powersave_common() */
-	ld	r4, PNV_POWERSAVE_AMR(r1)
-	ld	r5, PNV_POWERSAVE_IAMR(r1)
-	ld	r6, PNV_POWERSAVE_UAMOR(r1)
-	mtspr	SPRN_AMR, r4
-	mtspr	SPRN_IAMR, r5
-	mtspr	SPRN_UAMOR, r6
-BEGIN_FTR_SECTION_NESTED(42)
-	ld	r7, PNV_POWERSAVE_AMOR(r1)
-	mtspr	SPRN_AMOR, r7
-END_FTR_SECTION_NESTED_IFSET(CPU_FTR_HVMODE, 42)
-	/*
-	 * We don't need an isync here after restoring IAMR because the upcoming
-	 * mtmsrd is execution synchronizing.
-	 */
-END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
-
-	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
+	IDLE_STATE_ENTER_SEQ_NORET(PPC_SLEEP)
+2:	IDLE_STATE_ENTER_SEQ_NORET(PPC_WINKLE)
 
-/*
- * 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/process.c b/arch/powerpc/kernel/process.c
index f7b2e3b3db28..64e1494d3a1d 100644
--- a/arch/powerpc/kernel/process.c
+++ b/arch/powerpc/kernel/process.c
@@ -67,6 +67,7 @@
 #include <asm/cpu_has_feature.h>
 #include <asm/asm-prototypes.h>
 #include <asm/stacktrace.h>
+#include <asm/hw_breakpoint.h>
 
 #include <linux/kprobes.h>
 #include <linux/kdebug.h>
@@ -784,7 +785,7 @@ static inline int set_dabr(struct arch_hw_breakpoint *brk)
 	return __set_dabr(dabr, dabrx);
 }
 
-static inline int set_dawr(struct arch_hw_breakpoint *brk)
+int set_dawr(struct arch_hw_breakpoint *brk)
 {
 	unsigned long dawr, dawrx, mrd;
 
@@ -816,7 +817,7 @@ void __set_breakpoint(struct arch_hw_breakpoint *brk)
 {
 	memcpy(this_cpu_ptr(&current_brk), brk, sizeof(*brk));
 
-	if (cpu_has_feature(CPU_FTR_DAWR))
+	if (dawr_enabled())
 		// Power8 or later
 		set_dawr(brk);
 	else if (!cpu_has_feature(CPU_FTR_ARCH_207S))
@@ -830,8 +831,8 @@ void __set_breakpoint(struct arch_hw_breakpoint *brk)
 /* Check if we have DAWR or DABR hardware */
 bool ppc_breakpoint_available(void)
 {
-	if (cpu_has_feature(CPU_FTR_DAWR))
-		return true; /* POWER8 DAWR */
+	if (dawr_enabled())
+		return true; /* POWER8 DAWR or POWER9 forced DAWR */
 	if (cpu_has_feature(CPU_FTR_ARCH_207S))
 		return false; /* POWER9 with DAWR disabled */
 	/* DABR: Everything but POWER8 and POWER9 */
diff --git a/arch/powerpc/kernel/ptrace.c b/arch/powerpc/kernel/ptrace.c
index d9ac7d94656e..684b0b315c32 100644
--- a/arch/powerpc/kernel/ptrace.c
+++ b/arch/powerpc/kernel/ptrace.c
@@ -43,6 +43,7 @@
 #include <asm/tm.h>
 #include <asm/asm-prototypes.h>
 #include <asm/debug.h>
+#include <asm/hw_breakpoint.h>
 
 #define CREATE_TRACE_POINTS
 #include <trace/events/syscalls.h>
@@ -3088,7 +3089,7 @@ long arch_ptrace(struct task_struct *child, long request,
 		dbginfo.sizeof_condition = 0;
 #ifdef CONFIG_HAVE_HW_BREAKPOINT
 		dbginfo.features = PPC_DEBUG_FEATURE_DATA_BP_RANGE;
-		if (cpu_has_feature(CPU_FTR_DAWR))
+		if (dawr_enabled())
 			dbginfo.features |= PPC_DEBUG_FEATURE_DATA_BP_DAWR;
 #else
 		dbginfo.features = 0;
diff --git a/arch/powerpc/kernel/setup-common.c b/arch/powerpc/kernel/setup-common.c
index 1729bf409562..70dc10aa0ccf 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);