Merge branch 'topic/ppc-kvm' into next

This merge's Nick's big P9 KVM series, original cover letter follows:

KVM: PPC: Book3S HV P9: entry/exit optimisations

This reduces radix guest full entry/exit latency on POWER9 and POWER10
by 2x.

Nested HV guests should see smaller improvements in their L1 entry/exit,
but this is also combined with most L0 speedups also applying to nested
entry. nginx localhost throughput test in a SMP nested guest is improved
about 10% (in a direct guest it doesn't change much because it uses XIVE
for IPIs) when L0 and L1 are patched.

It does this in several main ways:

- Rearrange code to optimise SPR accesses. Mainly, avoid scoreboard
  stalls.

- Test SPR values to avoid mtSPRs where possible. mtSPRs are expensive.

- Reduce mftb. mftb is expensive.

- Demand fault certain facilities to avoid saving and/or restoring them
  (at the cost of fault when they are used, but this is mitigated over
  a number of entries, like the facilities when context switching
  processes). PM, TM, and EBB so far.

- Defer some sequences that are made just in case a guest is interrupted
  in the middle of a critical section to the case where the guest is
  scheduled on a different CPU, rather than every time (at the cost of
  an extra IPI in this case). Namely the tlbsync sequence for radix with
  GTSE, which is very expensive.

- Reduce locking, barriers, atomics related to the vcpus-per-vcore > 1
  handling that the P9 path does not require.

Documentation/admin-guide/kernel-parameters.txt

@@ -4144,6 +4144,14 @@
 			Override pmtimer IOPort with a hex value.
 			e.g. pmtmr=0x508
 
+	pmu_override=	[PPC] Override the PMU.
+			This option takes over the PMU facility, so it is no
+			longer usable by perf. Setting this option starts the
+			PMU counters by setting MMCR0 to 0 (the FC bit is
+			cleared). If a number is given, then MMCR1 is set to
+			that number, otherwise (e.g., 'pmu_override=on'), MMCR1
+			remains 0.
+
 	pm_debug_messages	[SUSPEND,KNL]
 			Enable suspend/resume debug messages during boot up.
 

arch/powerpc/include/asm/asm-prototypes.h

@@ -141,11 +141,6 @@ static inline void kvmppc_restore_tm_hv(struct kvm_vcpu *vcpu, u64 msr,
 					bool preserve_nv) { }
 #endif /* CONFIG_PPC_TRANSACTIONAL_MEM */
 
-void kvmhv_save_host_pmu(void);
-void kvmhv_load_host_pmu(void);
-void kvmhv_save_guest_pmu(struct kvm_vcpu *vcpu, bool pmu_in_use);
-void kvmhv_load_guest_pmu(struct kvm_vcpu *vcpu);
-
 void kvmppc_p9_enter_guest(struct kvm_vcpu *vcpu);
 
 long kvmppc_h_set_dabr(struct kvm_vcpu *vcpu, unsigned long dabr);

arch/powerpc/include/asm/kvm_asm.h

@@ -79,6 +79,7 @@
 #define BOOK3S_INTERRUPT_FP_UNAVAIL	0x800
 #define BOOK3S_INTERRUPT_DECREMENTER	0x900
 #define BOOK3S_INTERRUPT_HV_DECREMENTER	0x980
+#define BOOK3S_INTERRUPT_NESTED_HV_DECREMENTER	0x1980
 #define BOOK3S_INTERRUPT_DOORBELL	0xa00
 #define BOOK3S_INTERRUPT_SYSCALL	0xc00
 #define BOOK3S_INTERRUPT_TRACE		0xd00

arch/powerpc/include/asm/kvm_book3s.h

@@ -406,6 +406,12 @@ static inline ulong kvmppc_get_fault_dar(struct kvm_vcpu *vcpu)
 	return vcpu->arch.fault_dar;
 }
 
+/* Expiry time of vcpu DEC relative to host TB */
+static inline u64 kvmppc_dec_expires_host_tb(struct kvm_vcpu *vcpu)
+{
+	return vcpu->arch.dec_expires - vcpu->arch.vcore->tb_offset;
+}
+
 static inline bool is_kvmppc_resume_guest(int r)
 {
 	return (r == RESUME_GUEST || r == RESUME_GUEST_NV);

arch/powerpc/include/asm/kvm_book3s_64.h

@@ -44,7 +44,6 @@ struct kvm_nested_guest {
 	struct mutex tlb_lock;		/* serialize page faults and tlbies */
 	struct kvm_nested_guest *next;
 	cpumask_t need_tlb_flush;
-	cpumask_t cpu_in_guest;
 	short prev_cpu[NR_CPUS];
 	u8 radix;			/* is this nested guest radix */
 };
@@ -154,7 +153,9 @@ static inline bool kvmhv_vcpu_is_radix(struct kvm_vcpu *vcpu)
 	return radix;
 }
 
-int kvmhv_vcpu_entry_p9(struct kvm_vcpu *vcpu, u64 time_limit, unsigned long lpcr);
+unsigned long kvmppc_msr_hard_disable_set_facilities(struct kvm_vcpu *vcpu, unsigned long msr);
+
+int kvmhv_vcpu_entry_p9(struct kvm_vcpu *vcpu, u64 time_limit, unsigned long lpcr, u64 *tb);
 
 #define KVM_DEFAULT_HPT_ORDER	24	/* 16MB HPT by default */
 #endif

arch/powerpc/include/asm/kvm_host.h

@@ -287,7 +287,6 @@ struct kvm_arch {
 	u32 online_vcores;
 	atomic_t hpte_mod_interest;
 	cpumask_t need_tlb_flush;
-	cpumask_t cpu_in_guest;
 	u8 radix;
 	u8 fwnmi_enabled;
 	u8 secure_guest;
@@ -579,6 +578,10 @@ struct kvm_vcpu_arch {
 	ulong cfar;
 	ulong ppr;
 	u32 pspb;
+	u8 load_ebb;
+#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+	u8 load_tm;
+#endif
 	ulong fscr;
 	ulong shadow_fscr;
 	ulong ebbhr;
@@ -741,7 +744,7 @@ struct kvm_vcpu_arch {
 
 	struct hrtimer dec_timer;
 	u64 dec_jiffies;
-	u64 dec_expires;
+	u64 dec_expires;	/* Relative to guest timebase. */
 	unsigned long pending_exceptions;
 	u8 ceded;
 	u8 prodded;

arch/powerpc/include/asm/kvm_ppc.h

@@ -552,8 +552,7 @@ extern void kvm_hv_vm_activated(void);
 extern void kvm_hv_vm_deactivated(void);
 extern bool kvm_hv_mode_active(void);
 
-extern void kvmppc_check_need_tlb_flush(struct kvm *kvm, int pcpu,
-					struct kvm_nested_guest *nested);
+extern void kvmppc_check_need_tlb_flush(struct kvm *kvm, int pcpu);
 
 #else
 static inline void __init kvm_cma_reserve(void)
@@ -760,6 +759,7 @@ void kvmppc_realmode_machine_check(struct kvm_vcpu *vcpu);
 void kvmppc_subcore_enter_guest(void);
 void kvmppc_subcore_exit_guest(void);
 long kvmppc_realmode_hmi_handler(void);
+long kvmppc_p9_realmode_hmi_handler(struct kvm_vcpu *vcpu);
 long kvmppc_h_enter(struct kvm_vcpu *vcpu, unsigned long flags,
                     long pte_index, unsigned long pteh, unsigned long ptel);
 long kvmppc_h_remove(struct kvm_vcpu *vcpu, unsigned long flags,

arch/powerpc/include/asm/switch_to.h

@@ -112,6 +112,9 @@ static inline void clear_task_ebb(struct task_struct *t)
 #endif
 }
 
+void kvmppc_save_user_regs(void);
+void kvmppc_save_current_sprs(void);
+
 extern int set_thread_tidr(struct task_struct *t);
 
 #endif /* _ASM_POWERPC_SWITCH_TO_H */

arch/powerpc/include/asm/time.h

@@ -18,6 +18,8 @@
 #include <asm/vdso/timebase.h>
 
 /* time.c */
+extern u64 decrementer_max;
+
 extern unsigned long tb_ticks_per_jiffy;
 extern unsigned long tb_ticks_per_usec;
 extern unsigned long tb_ticks_per_sec;
@@ -97,19 +99,16 @@ extern void div128_by_32(u64 dividend_high, u64 dividend_low,
 extern void secondary_cpu_time_init(void);
 extern void __init time_init(void);
 
-#ifdef CONFIG_PPC64
-static inline unsigned long test_irq_work_pending(void)
-{
-	unsigned long x;
+DECLARE_PER_CPU(u64, decrementers_next_tb);
 
-	asm volatile("lbz %0,%1(13)"
-		: "=r" (x)
-		: "i" (offsetof(struct paca_struct, irq_work_pending)));
-	return x;
+static inline u64 timer_get_next_tb(void)
+{
+	return __this_cpu_read(decrementers_next_tb);
 }
-#endif
 
-DECLARE_PER_CPU(u64, decrementers_next_tb);
+#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
+void timer_rearm_host_dec(u64 now);
+#endif
 
 /* Convert timebase ticks to nanoseconds */
 unsigned long long tb_to_ns(unsigned long long tb_ticks);

arch/powerpc/kernel/cpu_setup_power.c

@@ -109,7 +109,7 @@ static void init_PMU_HV_ISA207(void)
 static void init_PMU(void)
 {
 	mtspr(SPRN_MMCRA, 0);
-	mtspr(SPRN_MMCR0, 0);
+	mtspr(SPRN_MMCR0, MMCR0_FC);
 	mtspr(SPRN_MMCR1, 0);
 	mtspr(SPRN_MMCR2, 0);
 }
@@ -123,7 +123,7 @@ static void init_PMU_ISA31(void)
 {
 	mtspr(SPRN_MMCR3, 0);
 	mtspr(SPRN_MMCRA, MMCRA_BHRB_DISABLE);
-	mtspr(SPRN_MMCR0, MMCR0_PMCCEXT);
+	mtspr(SPRN_MMCR0, MMCR0_FC | MMCR0_PMCCEXT);
 }
 
 /*
@@ -137,6 +137,7 @@ void __setup_cpu_power7(unsigned long offset, struct cpu_spec *t)
 		return;
 
 	mtspr(SPRN_LPID, 0);
+	mtspr(SPRN_AMOR, ~0);
 	mtspr(SPRN_PCR, PCR_MASK);
 	init_LPCR_ISA206(mfspr(SPRN_LPCR), LPCR_LPES1 >> LPCR_LPES_SH);
 }
@@ -150,6 +151,7 @@ void __restore_cpu_power7(void)
 		return;
 
 	mtspr(SPRN_LPID, 0);
+	mtspr(SPRN_AMOR, ~0);
 	mtspr(SPRN_PCR, PCR_MASK);
 	init_LPCR_ISA206(mfspr(SPRN_LPCR), LPCR_LPES1 >> LPCR_LPES_SH);
 }
@@ -164,6 +166,7 @@ void __setup_cpu_power8(unsigned long offset, struct cpu_spec *t)
 		return;
 
 	mtspr(SPRN_LPID, 0);
+	mtspr(SPRN_AMOR, ~0);
 	mtspr(SPRN_PCR, PCR_MASK);
 	init_LPCR_ISA206(mfspr(SPRN_LPCR) | LPCR_PECEDH, 0); /* LPES = 0 */
 	init_HFSCR();
@@ -184,6 +187,7 @@ void __restore_cpu_power8(void)
 		return;
 
 	mtspr(SPRN_LPID, 0);
+	mtspr(SPRN_AMOR, ~0);
 	mtspr(SPRN_PCR, PCR_MASK);
 	init_LPCR_ISA206(mfspr(SPRN_LPCR) | LPCR_PECEDH, 0); /* LPES = 0 */
 	init_HFSCR();
@@ -202,6 +206,7 @@ void __setup_cpu_power9(unsigned long offset, struct cpu_spec *t)
 	mtspr(SPRN_PSSCR, 0);
 	mtspr(SPRN_LPID, 0);
 	mtspr(SPRN_PID, 0);
+	mtspr(SPRN_AMOR, ~0);
 	mtspr(SPRN_PCR, PCR_MASK);
 	init_LPCR_ISA300((mfspr(SPRN_LPCR) | LPCR_PECEDH | LPCR_PECE_HVEE |\
 			 LPCR_HVICE | LPCR_HEIC) & ~(LPCR_UPRT | LPCR_HR), 0);
@@ -223,6 +228,7 @@ void __restore_cpu_power9(void)
 	mtspr(SPRN_PSSCR, 0);
 	mtspr(SPRN_LPID, 0);
 	mtspr(SPRN_PID, 0);
+	mtspr(SPRN_AMOR, ~0);
 	mtspr(SPRN_PCR, PCR_MASK);
 	init_LPCR_ISA300((mfspr(SPRN_LPCR) | LPCR_PECEDH | LPCR_PECE_HVEE |\
 			 LPCR_HVICE | LPCR_HEIC) & ~(LPCR_UPRT | LPCR_HR), 0);
@@ -242,6 +248,7 @@ void __setup_cpu_power10(unsigned long offset, struct cpu_spec *t)
 	mtspr(SPRN_PSSCR, 0);
 	mtspr(SPRN_LPID, 0);
 	mtspr(SPRN_PID, 0);
+	mtspr(SPRN_AMOR, ~0);
 	mtspr(SPRN_PCR, PCR_MASK);
 	init_LPCR_ISA300((mfspr(SPRN_LPCR) | LPCR_PECEDH | LPCR_PECE_HVEE |\
 			 LPCR_HVICE | LPCR_HEIC) & ~(LPCR_UPRT | LPCR_HR), 0);
@@ -264,6 +271,7 @@ void __restore_cpu_power10(void)
 	mtspr(SPRN_PSSCR, 0);
 	mtspr(SPRN_LPID, 0);
 	mtspr(SPRN_PID, 0);
+	mtspr(SPRN_AMOR, ~0);
 	mtspr(SPRN_PCR, PCR_MASK);
 	init_LPCR_ISA300((mfspr(SPRN_LPCR) | LPCR_PECEDH | LPCR_PECE_HVEE |\
 			 LPCR_HVICE | LPCR_HEIC) & ~(LPCR_UPRT | LPCR_HR), 0);

arch/powerpc/kernel/dt_cpu_ftrs.c

@@ -80,6 +80,7 @@ static void __restore_cpu_cpufeatures(void)
 	mtspr(SPRN_LPCR, system_registers.lpcr);
 	if (hv_mode) {
 		mtspr(SPRN_LPID, 0);
+		mtspr(SPRN_AMOR, ~0);
 		mtspr(SPRN_HFSCR, system_registers.hfscr);
 		mtspr(SPRN_PCR, system_registers.pcr);
 	}
@@ -216,6 +217,7 @@ static int __init feat_enable_hv(struct dt_cpu_feature *f)
 	}
 
 	mtspr(SPRN_LPID, 0);
+	mtspr(SPRN_AMOR, ~0);
 
 	lpcr = mfspr(SPRN_LPCR);
 	lpcr &=  ~LPCR_LPES0; /* HV external interrupts */
@@ -351,7 +353,7 @@ static void init_pmu_power8(void)
 	}
 
 	mtspr(SPRN_MMCRA, 0);
-	mtspr(SPRN_MMCR0, 0);
+	mtspr(SPRN_MMCR0, MMCR0_FC);
 	mtspr(SPRN_MMCR1, 0);
 	mtspr(SPRN_MMCR2, 0);
 	mtspr(SPRN_MMCRS, 0);
@@ -390,7 +392,7 @@ static void init_pmu_power9(void)
 		mtspr(SPRN_MMCRC, 0);
 
 	mtspr(SPRN_MMCRA, 0);
-	mtspr(SPRN_MMCR0, 0);
+	mtspr(SPRN_MMCR0, MMCR0_FC);
 	mtspr(SPRN_MMCR1, 0);
 	mtspr(SPRN_MMCR2, 0);
 }
@@ -426,7 +428,7 @@ static void init_pmu_power10(void)
 
 	mtspr(SPRN_MMCR3, 0);
 	mtspr(SPRN_MMCRA, MMCRA_BHRB_DISABLE);
-	mtspr(SPRN_MMCR0, MMCR0_PMCCEXT);
+	mtspr(SPRN_MMCR0, MMCR0_FC | MMCR0_PMCCEXT);
 }
 
 static int __init feat_enable_pmu_power10(struct dt_cpu_feature *f)

arch/powerpc/kernel/process.c

@@ -1156,6 +1156,40 @@ static inline void save_sprs(struct thread_struct *t)
 #endif
 }
 
+#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
+void kvmppc_save_user_regs(void)
+{
+	unsigned long usermsr;
+
+	if (!current->thread.regs)
+		return;
+
+	usermsr = current->thread.regs->msr;
+
+	if (usermsr & MSR_FP)
+		save_fpu(current);
+
+	if (usermsr & MSR_VEC)
+		save_altivec(current);
+
+#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+	if (usermsr & MSR_TM) {
+		current->thread.tm_tfhar = mfspr(SPRN_TFHAR);
+		current->thread.tm_tfiar = mfspr(SPRN_TFIAR);
+		current->thread.tm_texasr = mfspr(SPRN_TEXASR);
+		current->thread.regs->msr &= ~MSR_TM;
+	}
+#endif
+}
+EXPORT_SYMBOL_GPL(kvmppc_save_user_regs);
+
+void kvmppc_save_current_sprs(void)
+{
+	save_sprs(&current->thread);
+}
+EXPORT_SYMBOL_GPL(kvmppc_save_current_sprs);
+#endif /* CONFIG_KVM_BOOK3S_HV_POSSIBLE */
+
 static inline void restore_sprs(struct thread_struct *old_thread,
 				struct thread_struct *new_thread)
 {

arch/powerpc/kernel/time.c

@@ -88,6 +88,7 @@ static struct clocksource clocksource_timebase = {
 
 #define DECREMENTER_DEFAULT_MAX 0x7FFFFFFF
 u64 decrementer_max = DECREMENTER_DEFAULT_MAX;
+EXPORT_SYMBOL_GPL(decrementer_max); /* for KVM HDEC */
 
 static int decrementer_set_next_event(unsigned long evt,
 				      struct clock_event_device *dev);
@@ -107,6 +108,7 @@ struct clock_event_device decrementer_clockevent = {
 EXPORT_SYMBOL(decrementer_clockevent);
 
 DEFINE_PER_CPU(u64, decrementers_next_tb);
+EXPORT_SYMBOL_GPL(decrementers_next_tb);
 static DEFINE_PER_CPU(struct clock_event_device, decrementers);
 
 #define XSEC_PER_SEC (1024*1024)
@@ -496,6 +498,16 @@ EXPORT_SYMBOL(profile_pc);
  * 64-bit uses a byte in the PACA, 32-bit uses a per-cpu variable...
  */
 #ifdef CONFIG_PPC64
+static inline unsigned long test_irq_work_pending(void)
+{
+	unsigned long x;
+
+	asm volatile("lbz %0,%1(13)"
+		: "=r" (x)
+		: "i" (offsetof(struct paca_struct, irq_work_pending)));
+	return x;
+}
+
 static inline void set_irq_work_pending_flag(void)
 {
 	asm volatile("stb %0,%1(13)" : :
@@ -539,13 +551,44 @@ void arch_irq_work_raise(void)
 	preempt_enable();
 }
 
+static void set_dec_or_work(u64 val)
+{
+	set_dec(val);
+	/* We may have raced with new irq work */
+	if (unlikely(test_irq_work_pending()))
+		set_dec(1);
+}
+
 #else  /* CONFIG_IRQ_WORK */
 
 #define test_irq_work_pending()	0
 #define clear_irq_work_pending()
 
+static void set_dec_or_work(u64 val)
+{
+	set_dec(val);
+}
 #endif /* CONFIG_IRQ_WORK */
 
+#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
+void timer_rearm_host_dec(u64 now)
+{
+	u64 *next_tb = this_cpu_ptr(&decrementers_next_tb);
+
+	WARN_ON_ONCE(!arch_irqs_disabled());
+	WARN_ON_ONCE(mfmsr() & MSR_EE);
+
+	if (now >= *next_tb) {
+		local_paca->irq_happened |= PACA_IRQ_DEC;
+	} else {
+		now = *next_tb - now;
+		if (now <= decrementer_max)
+			set_dec_or_work(now);
+	}
+}
+EXPORT_SYMBOL_GPL(timer_rearm_host_dec);
+#endif
+
 /*
  * timer_interrupt - gets called when the decrementer overflows,
  * with interrupts disabled.
@@ -606,10 +649,7 @@ DEFINE_INTERRUPT_HANDLER_ASYNC(timer_interrupt)
 	} else {
 		now = *next_tb - now;
 		if (now <= decrementer_max)
-			set_dec(now);
-		/* We may have raced with new irq work */
-		if (test_irq_work_pending())
-			set_dec(1);
+			set_dec_or_work(now);
 		__this_cpu_inc(irq_stat.timer_irqs_others);
 	}
 
@@ -843,11 +883,7 @@ static int decrementer_set_next_event(unsigned long evt,
 				      struct clock_event_device *dev)
 {
 	__this_cpu_write(decrementers_next_tb, get_tb() + evt);
-	set_dec(evt);
-
-	/* We may have raced with new irq work */
-	if (test_irq_work_pending())
-		set_dec(1);
+	set_dec_or_work(evt);
 
 	return 0;
 }

arch/powerpc/kvm/Kconfig

@@ -130,6 +130,21 @@ config KVM_BOOK3S_HV_EXIT_TIMING
 
 	  If unsure, say N.
 
+config KVM_BOOK3S_HV_NESTED_PMU_WORKAROUND
+	bool "Nested L0 host workaround for L1 KVM host PMU handling bug" if EXPERT
+	depends on KVM_BOOK3S_HV_POSSIBLE
+	default !EXPERT
+	help
+	  Old nested HV capable Linux guests have a bug where they don't
+	  reflect the PMU in-use status of their L2 guest to the L0 host
+	  while the L2 PMU registers are live. This can result in loss
+          of L2 PMU register state, causing perf to not work correctly in
+	  L2 guests.
+
+	  Selecting this option for the L0 host implements a workaround for
+	  those buggy L1s which saves the L2 state, at the cost of performance
+	  in all nested-capable guest entry/exit.
+
 config KVM_BOOKE_HV
 	bool
 

arch/powerpc/kvm/book3s_64_entry.S

@@ -374,11 +374,16 @@ END_MMU_FTR_SECTION_IFCLR(MMU_FTR_TYPE_RADIX)
 BEGIN_FTR_SECTION
 	mtspr	SPRN_DAWRX1,r10
 END_FTR_SECTION_IFSET(CPU_FTR_DAWR1)
-	mtspr	SPRN_PID,r10
 
 	/*
-	 * Switch to host MMU mode
+	 * Switch to host MMU mode (don't have the real host PID but we aren't
+	 * going back to userspace).
 	 */
+	hwsync
+	isync
+
+	mtspr	SPRN_PID,r10
+
 	ld	r10, HSTATE_KVM_VCPU(r13)
 	ld	r10, VCPU_KVM(r10)
 	lwz	r10, KVM_HOST_LPID(r10)
@@ -389,6 +394,8 @@ END_FTR_SECTION_IFSET(CPU_FTR_DAWR1)
 	ld	r10, KVM_HOST_LPCR(r10)
 	mtspr	SPRN_LPCR,r10
 
+	isync
+
 	/*
 	 * Set GUEST_MODE_NONE so the handler won't branch to KVM, and clear
 	 * MSR_RI in r12 ([H]SRR1) so the handler won't try to return.

arch/powerpc/kvm/book3s_64_mmu_radix.c

@@ -57,6 +57,8 @@ unsigned long __kvmhv_copy_tofrom_guest_radix(int lpid, int pid,
 
 	preempt_disable();
 
+	asm volatile("hwsync" ::: "memory");
+	isync();
 	/* switch the lpid first to avoid running host with unallocated pid */
 	old_lpid = mfspr(SPRN_LPID);
 	if (old_lpid != lpid)
@@ -75,6 +77,8 @@ unsigned long __kvmhv_copy_tofrom_guest_radix(int lpid, int pid,
 		ret = __copy_to_user_inatomic((void __user *)to, from, n);
 	pagefault_enable();
 
+	asm volatile("hwsync" ::: "memory");
+	isync();
 	/* switch the pid first to avoid running host with unallocated pid */
 	if (quadrant == 1 && pid != old_pid)
 		mtspr(SPRN_PID, old_pid);

arch/powerpc/kvm/book3s_hv.h

+// SPDX-License-Identifier: GPL-2.0-only
+
+/*
+ * Privileged (non-hypervisor) host registers to save.
+ */
+struct p9_host_os_sprs {
+	unsigned long iamr;
+	unsigned long amr;
+
+	unsigned int pmc1;
+	unsigned int pmc2;
+	unsigned int pmc3;
+	unsigned int pmc4;
+	unsigned int pmc5;
+	unsigned int pmc6;
+	unsigned long mmcr0;
+	unsigned long mmcr1;
+	unsigned long mmcr2;
+	unsigned long mmcr3;
+	unsigned long mmcra;
+	unsigned long siar;
+	unsigned long sier1;
+	unsigned long sier2;
+	unsigned long sier3;
+	unsigned long sdar;
+};
+
+static inline bool nesting_enabled(struct kvm *kvm)
+{
+	return kvm->arch.nested_enable && kvm_is_radix(kvm);
+}
+
+bool load_vcpu_state(struct kvm_vcpu *vcpu,
+			   struct p9_host_os_sprs *host_os_sprs);
+void store_vcpu_state(struct kvm_vcpu *vcpu);
+void save_p9_host_os_sprs(struct p9_host_os_sprs *host_os_sprs);
+void restore_p9_host_os_sprs(struct kvm_vcpu *vcpu,
+				    struct p9_host_os_sprs *host_os_sprs);
+void switch_pmu_to_guest(struct kvm_vcpu *vcpu,
+			    struct p9_host_os_sprs *host_os_sprs);
+void switch_pmu_to_host(struct kvm_vcpu *vcpu,
+			    struct p9_host_os_sprs *host_os_sprs);

arch/powerpc/kvm/book3s_hv_builtin.c

@@ -649,6 +649,8 @@ void kvmppc_guest_entry_inject_int(struct kvm_vcpu *vcpu)
 	int ext;
 	unsigned long lpcr;
 
+	WARN_ON_ONCE(cpu_has_feature(CPU_FTR_ARCH_300));
+
 	/* Insert EXTERNAL bit into LPCR at the MER bit position */
 	ext = (vcpu->arch.pending_exceptions >> BOOK3S_IRQPRIO_EXTERNAL) & 1;
 	lpcr = mfspr(SPRN_LPCR);
@@ -682,57 +684,23 @@ static void flush_guest_tlb(struct kvm *kvm)
 	unsigned long rb, set;
 
 	rb = PPC_BIT(52);	/* IS = 2 */
-	if (kvm_is_radix(kvm)) {
-		/* R=1 PRS=1 RIC=2 */
+	for (set = 0; set < kvm->arch.tlb_sets; ++set) {
+		/* R=0 PRS=0 RIC=0 */
 		asm volatile(PPC_TLBIEL(%0, %4, %3, %2, %1)
-			     : : "r" (rb), "i" (1), "i" (1), "i" (2),
+			     : : "r" (rb), "i" (0), "i" (0), "i" (0),
 			       "r" (0) : "memory");
-		for (set = 1; set < kvm->arch.tlb_sets; ++set) {
-			rb += PPC_BIT(51);	/* increment set number */
-			/* R=1 PRS=1 RIC=0 */
-			asm volatile(PPC_TLBIEL(%0, %4, %3, %2, %1)
-				     : : "r" (rb), "i" (1), "i" (1), "i" (0),
-				       "r" (0) : "memory");
-		}
-		asm volatile("ptesync": : :"memory");
-		asm volatile(PPC_RADIX_INVALIDATE_ERAT_GUEST : : :"memory");
-	} else {
-		for (set = 0; set < kvm->arch.tlb_sets; ++set) {
-			/* R=0 PRS=0 RIC=0 */
-			asm volatile(PPC_TLBIEL(%0, %4, %3, %2, %1)
-				     : : "r" (rb), "i" (0), "i" (0), "i" (0),
-				       "r" (0) : "memory");
-			rb += PPC_BIT(51);	/* increment set number */
-		}
-		asm volatile("ptesync": : :"memory");
-		asm volatile(PPC_ISA_3_0_INVALIDATE_ERAT : : :"memory");
+		rb += PPC_BIT(51);	/* increment set number */
 	}
+	asm volatile("ptesync": : :"memory");
 }
 
-void kvmppc_check_need_tlb_flush(struct kvm *kvm, int pcpu,
-				 struct kvm_nested_guest *nested)
+void kvmppc_check_need_tlb_flush(struct kvm *kvm, int pcpu)
 {
-	cpumask_t *need_tlb_flush;
-
-	/*
-	 * On POWER9, individual threads can come in here, but the
-	 * TLB is shared between the 4 threads in a core, hence
-	 * invalidating on one thread invalidates for all.
-	 * Thus we make all 4 threads use the same bit.
-	 */
-	if (cpu_has_feature(CPU_FTR_ARCH_300))
-		pcpu = cpu_first_tlb_thread_sibling(pcpu);
-
-	if (nested)
-		need_tlb_flush = &nested->need_tlb_flush;
-	else
-		need_tlb_flush = &kvm->arch.need_tlb_flush;
-
-	if (cpumask_test_cpu(pcpu, need_tlb_flush)) {
+	if (cpumask_test_cpu(pcpu, &kvm->arch.need_tlb_flush)) {
 		flush_guest_tlb(kvm);
 
 		/* Clear the bit after the TLB flush */
-		cpumask_clear_cpu(pcpu, need_tlb_flush);
+		cpumask_clear_cpu(pcpu, &kvm->arch.need_tlb_flush);
 	}
 }
 EXPORT_SYMBOL_GPL(kvmppc_check_need_tlb_flush);

arch/powerpc/kvm/book3s_hv_hmi.c

@@ -20,10 +20,15 @@ void wait_for_subcore_guest_exit(void)
 
 	/*
 	 * NULL bitmap pointer indicates that KVM module hasn't
-	 * been loaded yet and hence no guests are running.
+	 * been loaded yet and hence no guests are running, or running
+	 * on POWER9 or newer CPU.
+	 *
 	 * If no KVM is in use, no need to co-ordinate among threads
 	 * as all of them will always be in host and no one is going
 	 * to modify TB other than the opal hmi handler.
+	 *
+	 * POWER9 and newer don't need this synchronisation.
+	 *
 	 * Hence, just return from here.
 	 */
 	if (!local_paca->sibling_subcore_state)

arch/powerpc/kvm/book3s_hv_interrupts.S

@@ -104,7 +104,10 @@ END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_207S)
 	mtlr	r0
 	blr
 
-_GLOBAL(kvmhv_save_host_pmu)
+/*
+ * void kvmhv_save_host_pmu(void)
+ */
+kvmhv_save_host_pmu:
 BEGIN_FTR_SECTION
 	/* Work around P8 PMAE bug */
 	li	r3, -1
@@ -138,14 +141,6 @@ BEGIN_FTR_SECTION
 	std	r8, HSTATE_MMCR2(r13)
 	std	r9, HSTATE_SIER(r13)
 END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
-BEGIN_FTR_SECTION
-	mfspr	r5, SPRN_MMCR3
-	mfspr	r6, SPRN_SIER2
-	mfspr	r7, SPRN_SIER3
-	std	r5, HSTATE_MMCR3(r13)
-	std	r6, HSTATE_SIER2(r13)
-	std	r7, HSTATE_SIER3(r13)
-END_FTR_SECTION_IFSET(CPU_FTR_ARCH_31)
 	mfspr	r3, SPRN_PMC1
 	mfspr	r5, SPRN_PMC2
 	mfspr	r6, SPRN_PMC3

arch/powerpc/kvm/book3s_hv_nested.c

@@ -358,6 +358,7 @@ long kvmhv_enter_nested_guest(struct kvm_vcpu *vcpu)
 	/* convert TB values/offsets to host (L0) values */
 	hdec_exp = l2_hv.hdec_expiry - vc->tb_offset;
 	vc->tb_offset += l2_hv.tb_offset;
+	vcpu->arch.dec_expires += l2_hv.tb_offset;
 
 	/* set L1 state to L2 state */
 	vcpu->arch.nested = l2;
@@ -374,11 +375,6 @@ long kvmhv_enter_nested_guest(struct kvm_vcpu *vcpu)
 	vcpu->arch.ret = RESUME_GUEST;
 	vcpu->arch.trap = 0;
 	do {
-		if (mftb() >= hdec_exp) {
-			vcpu->arch.trap = BOOK3S_INTERRUPT_HV_DECREMENTER;
-			r = RESUME_HOST;
-			break;
-		}
 		r = kvmhv_run_single_vcpu(vcpu, hdec_exp, lpcr);
 	} while (is_kvmppc_resume_guest(r));
 
@@ -399,6 +395,8 @@ long kvmhv_enter_nested_guest(struct kvm_vcpu *vcpu)
 	if (l2_regs.msr & MSR_TS_MASK)
 		vcpu->arch.shregs.msr |= MSR_TS_S;
 	vc->tb_offset = saved_l1_hv.tb_offset;
+	/* XXX: is this always the same delta as saved_l1_hv.tb_offset? */
+	vcpu->arch.dec_expires -= l2_hv.tb_offset;
 	restore_hv_regs(vcpu, &saved_l1_hv);
 	vcpu->arch.purr += delta_purr;
 	vcpu->arch.spurr += delta_spurr;

arch/powerpc/kvm/book3s_hv_ras.c

@@ -136,6 +136,60 @@ void kvmppc_realmode_machine_check(struct kvm_vcpu *vcpu)
 	vcpu->arch.mce_evt = mce_evt;
 }
 
+
+long kvmppc_p9_realmode_hmi_handler(struct kvm_vcpu *vcpu)
+{
+	struct kvmppc_vcore *vc = vcpu->arch.vcore;
+	long ret = 0;
+
+	/*
+	 * Unapply and clear the offset first. That way, if the TB was not
+	 * resynced then it will remain in host-offset, and if it was resynced
+	 * then it is brought into host-offset. Then the tb offset is
+	 * re-applied before continuing with the KVM exit.
+	 *
+	 * This way, we don't need to actually know whether not OPAL resynced
+	 * the timebase or do any of the complicated dance that the P7/8
+	 * path requires.
+	 */
+	if (vc->tb_offset_applied) {
+		u64 new_tb = mftb() - vc->tb_offset_applied;
+		mtspr(SPRN_TBU40, new_tb);
+		if ((mftb() & 0xffffff) < (new_tb & 0xffffff)) {
+			new_tb += 0x1000000;
+			mtspr(SPRN_TBU40, new_tb);
+		}
+		vc->tb_offset_applied = 0;
+	}
+
+	local_paca->hmi_irqs++;
+
+	if (hmi_handle_debugtrig(NULL) >= 0) {
+		ret = 1;
+		goto out;
+	}
+
+	if (ppc_md.hmi_exception_early)
+		ppc_md.hmi_exception_early(NULL);
+
+out:
+	if (vc->tb_offset) {
+		u64 new_tb = mftb() + vc->tb_offset;
+		mtspr(SPRN_TBU40, new_tb);
+		if ((mftb() & 0xffffff) < (new_tb & 0xffffff)) {
+			new_tb += 0x1000000;
+			mtspr(SPRN_TBU40, new_tb);
+		}
+		vc->tb_offset_applied = vc->tb_offset;
+	}
+
+	return ret;
+}
+
+/*
+ * The following subcore HMI handling is all only for pre-POWER9 CPUs.
+ */
+
 /* Check if dynamic split is in force and return subcore size accordingly. */
 static inline int kvmppc_cur_subcore_size(void)
 {

arch/powerpc/kvm/book3s_hv_rm_mmu.c

@@ -55,12 +55,6 @@ static int global_invalidates(struct kvm *kvm)
 		smp_wmb();
 		cpumask_setall(&kvm->arch.need_tlb_flush);
 		cpu = local_paca->kvm_hstate.kvm_vcore->pcpu;
-		/*
-		 * On POWER9, threads are independent but the TLB is shared,
-		 * so use the bit for the first thread to represent the core.
-		 */
-		if (cpu_has_feature(CPU_FTR_ARCH_300))
-			cpu = cpu_first_tlb_thread_sibling(cpu);
 		cpumask_clear_cpu(cpu, &kvm->arch.need_tlb_flush);
 	}
 

arch/powerpc/kvm/book3s_hv_rmhandlers.S

@@ -778,17 +778,14 @@ END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_207S)
 	/* Restore AMR and UAMOR, set AMOR to all 1s */
 	ld	r5,VCPU_AMR(r4)
 	ld	r6,VCPU_UAMOR(r4)
-	li	r7,-1
 	mtspr	SPRN_AMR,r5
 	mtspr	SPRN_UAMOR,r6
-	mtspr	SPRN_AMOR,r7
 
-	/* Restore state of CTRL run bit; assume 1 on entry */
+	/* Restore state of CTRL run bit; the host currently has it set to 1 */
 	lwz	r5,VCPU_CTRL(r4)
 	andi.	r5,r5,1
 	bne	4f
-	mfspr	r6,SPRN_CTRLF
-	clrrdi	r6,r6,1
+	li	r6,0
 	mtspr	SPRN_CTRLT,r6
 4:
 	/* Secondary threads wait for primary to have done partition switch */
@@ -817,10 +814,6 @@ END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_207S)
 	 * Set the decrementer to the guest decrementer.
 	 */
 	ld	r8,VCPU_DEC_EXPIRES(r4)
-	/* r8 is a host timebase value here, convert to guest TB */
-	ld	r5,HSTATE_KVM_VCORE(r13)
-	ld	r6,VCORE_TB_OFFSET_APPL(r5)
-	add	r8,r8,r6
 	mftb	r7
 	subf	r3,r7,r8
 	mtspr	SPRN_DEC,r3
@@ -1195,9 +1188,6 @@ guest_bypass:
 	mftb	r6
 	extsw	r5,r5
 16:	add	r5,r5,r6
-	/* r5 is a guest timebase value here, convert to host TB */
-	ld	r4,VCORE_TB_OFFSET_APPL(r3)
-	subf	r5,r4,r5
 	std	r5,VCPU_DEC_EXPIRES(r9)
 
 	/* Increment exit count, poke other threads to exit */
@@ -1211,12 +1201,12 @@ guest_bypass:
 	stw	r0, VCPU_CPU(r9)
 	stw	r0, VCPU_THREAD_CPU(r9)
 
-	/* Save guest CTRL register, set runlatch to 1 */
+	/* Save guest CTRL register, set runlatch to 1 if it was clear */
 	mfspr	r6,SPRN_CTRLF
 	stw	r6,VCPU_CTRL(r9)
 	andi.	r0,r6,1
 	bne	4f
-	ori	r6,r6,1
+	li	r6,1
 	mtspr	SPRN_CTRLT,r6
 4:
 	/*
@@ -2163,9 +2153,6 @@ END_FTR_SECTION_IFCLR(CPU_FTR_TM)
 	/* save expiry time of guest decrementer */
 	add	r3, r3, r5
 	ld	r4, HSTATE_KVM_VCPU(r13)
-	ld	r5, HSTATE_KVM_VCORE(r13)
-	ld	r6, VCORE_TB_OFFSET_APPL(r5)
-	subf	r3, r6, r3	/* convert to host TB value */
 	std	r3, VCPU_DEC_EXPIRES(r4)
 
 #ifdef CONFIG_KVM_BOOK3S_HV_EXIT_TIMING
@@ -2186,8 +2173,7 @@ END_FTR_SECTION_IFCLR(CPU_FTR_TM)
 	 * Also clear the runlatch bit before napping.
 	 */
 kvm_do_nap:
-	mfspr	r0, SPRN_CTRLF
-	clrrdi	r0, r0, 1
+	li	r0,0
 	mtspr	SPRN_CTRLT, r0
 
 	li	r0,1
@@ -2206,8 +2192,7 @@ kvm_nap_sequence:		/* desired LPCR value in r5 */
 
 	bl	isa206_idle_insn_mayloss
 
-	mfspr	r0, SPRN_CTRLF
-	ori	r0, r0, 1
+	li	r0,1
 	mtspr	SPRN_CTRLT, r0
 
 	mtspr	SPRN_SRR1, r3
@@ -2264,9 +2249,6 @@ END_FTR_SECTION_IFCLR(CPU_FTR_TM)
 
 	/* Restore guest decrementer */
 	ld	r3, VCPU_DEC_EXPIRES(r4)
-	ld	r5, HSTATE_KVM_VCORE(r13)
-	ld	r6, VCORE_TB_OFFSET_APPL(r5)
-	add	r3, r3, r6	/* convert host TB to guest TB value */
 	mftb	r7
 	subf	r3, r7, r3
 	mtspr	SPRN_DEC, r3
@@ -2778,10 +2760,11 @@ kvmppc_msr_interrupt:
 	blr
 
 /*
+ * void kvmhv_load_guest_pmu(struct kvm_vcpu *vcpu)
+ *
  * Load up guest PMU state.  R3 points to the vcpu struct.
  */
-_GLOBAL(kvmhv_load_guest_pmu)
-EXPORT_SYMBOL_GPL(kvmhv_load_guest_pmu)
+kvmhv_load_guest_pmu:
 	mr	r4, r3
 	mflr	r0
 	li	r3, 1
@@ -2815,27 +2798,17 @@ END_FTR_SECTION_IFSET(CPU_FTR_PMAO_BUG)
 	mtspr	SPRN_MMCRA, r6
 	mtspr	SPRN_SIAR, r7
 	mtspr	SPRN_SDAR, r8
-BEGIN_FTR_SECTION
-	ld      r5, VCPU_MMCR + 24(r4)
-	ld      r6, VCPU_SIER + 8(r4)
-	ld      r7, VCPU_SIER + 16(r4)
-	mtspr   SPRN_MMCR3, r5
-	mtspr   SPRN_SIER2, r6
-	mtspr   SPRN_SIER3, r7
-END_FTR_SECTION_IFSET(CPU_FTR_ARCH_31)
 BEGIN_FTR_SECTION
 	ld	r5, VCPU_MMCR + 16(r4)
 	ld	r6, VCPU_SIER(r4)
 	mtspr	SPRN_MMCR2, r5
 	mtspr	SPRN_SIER, r6
-BEGIN_FTR_SECTION_NESTED(96)
 	lwz	r7, VCPU_PMC + 24(r4)
 	lwz	r8, VCPU_PMC + 28(r4)
 	ld	r9, VCPU_MMCRS(r4)
 	mtspr	SPRN_SPMC1, r7
 	mtspr	SPRN_SPMC2, r8
 	mtspr	SPRN_MMCRS, r9
-END_FTR_SECTION_NESTED(CPU_FTR_ARCH_300, 0, 96)
 END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
 	mtspr	SPRN_MMCR0, r3
 	isync
@@ -2843,10 +2816,11 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
 	blr
 
 /*
+ * void kvmhv_load_host_pmu(void)
+ *
  * Reload host PMU state saved in the PACA by kvmhv_save_host_pmu.
  */
-_GLOBAL(kvmhv_load_host_pmu)
-EXPORT_SYMBOL_GPL(kvmhv_load_host_pmu)
+kvmhv_load_host_pmu:
 	mflr	r0
 	lbz	r4, PACA_PMCINUSE(r13) /* is the host using the PMU? */
 	cmpwi	r4, 0
@@ -2884,25 +2858,18 @@ BEGIN_FTR_SECTION
 	mtspr	SPRN_MMCR2, r8
 	mtspr	SPRN_SIER, r9
 END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
-BEGIN_FTR_SECTION
-	ld      r5, HSTATE_MMCR3(r13)
-	ld      r6, HSTATE_SIER2(r13)
-	ld      r7, HSTATE_SIER3(r13)
-	mtspr   SPRN_MMCR3, r5
-	mtspr   SPRN_SIER2, r6
-	mtspr   SPRN_SIER3, r7
-END_FTR_SECTION_IFSET(CPU_FTR_ARCH_31)
 	mtspr	SPRN_MMCR0, r3
 	isync
 	mtlr	r0
 23:	blr
 
 /*
+ * void kvmhv_save_guest_pmu(struct kvm_vcpu *vcpu, bool pmu_in_use)
+ *
  * Save guest PMU state into the vcpu struct.
  * r3 = vcpu, r4 = full save flag (PMU in use flag set in VPA)
  */
-_GLOBAL(kvmhv_save_guest_pmu)
-EXPORT_SYMBOL_GPL(kvmhv_save_guest_pmu)
+kvmhv_save_guest_pmu:
 	mr	r9, r3
 	mr	r8, r4
 BEGIN_FTR_SECTION
@@ -2951,14 +2918,6 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
 BEGIN_FTR_SECTION
 	std	r10, VCPU_MMCR + 16(r9)
 END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
-BEGIN_FTR_SECTION
-	mfspr   r5, SPRN_MMCR3
-	mfspr   r6, SPRN_SIER2
-	mfspr   r7, SPRN_SIER3
-	std     r5, VCPU_MMCR + 24(r9)
-	std     r6, VCPU_SIER + 8(r9)
-	std     r7, VCPU_SIER + 16(r9)
-END_FTR_SECTION_IFSET(CPU_FTR_ARCH_31)
 	std	r7, VCPU_SIAR(r9)
 	std	r8, VCPU_SDAR(r9)
 	mfspr	r3, SPRN_PMC1
@@ -2976,7 +2935,6 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_31)
 BEGIN_FTR_SECTION
 	mfspr	r5, SPRN_SIER
 	std	r5, VCPU_SIER(r9)
-BEGIN_FTR_SECTION_NESTED(96)
 	mfspr	r6, SPRN_SPMC1
 	mfspr	r7, SPRN_SPMC2
 	mfspr	r8, SPRN_MMCRS
@@ -2985,7 +2943,6 @@ BEGIN_FTR_SECTION_NESTED(96)
 	std	r8, VCPU_MMCRS(r9)
 	lis	r4, 0x8000
 	mtspr	SPRN_MMCRS, r4
-END_FTR_SECTION_NESTED(CPU_FTR_ARCH_300, 0, 96)
 END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
 22:	blr
 

arch/powerpc/mm/book3s64/radix_pgtable.c

@@ -572,18 +572,6 @@ void __init radix__early_init_devtree(void)
 	return;
 }
 
-static void radix_init_amor(void)
-{
-	/*
-	* In HV mode, we init AMOR (Authority Mask Override Register) so that
-	* the hypervisor and guest can setup IAMR (Instruction Authority Mask
-	* Register), enable key 0 and set it to 1.
-	*
-	* AMOR = 0b1100 .... 0000 (Mask for key 0 is 11)
-	*/
-	mtspr(SPRN_AMOR, (3ul << 62));
-}
-
 void __init radix__early_init_mmu(void)
 {
 	unsigned long lpcr;
@@ -644,7 +632,6 @@ void __init radix__early_init_mmu(void)
 		lpcr = mfspr(SPRN_LPCR);
 		mtspr(SPRN_LPCR, lpcr | LPCR_UPRT | LPCR_HR);
 		radix_init_partition_table();
-		radix_init_amor();
 	} else {
 		radix_init_pseries();
 	}
@@ -668,8 +655,6 @@ void radix__early_init_mmu_secondary(void)
 
 		set_ptcr_when_no_uv(__pa(partition_tb) |
 				    (PATB_SIZE_SHIFT - 12));
-
-		radix_init_amor();
 	}
 
 	radix__switch_mmu_context(NULL, &init_mm);

arch/powerpc/perf/core-book3s.c

@@ -2419,8 +2419,24 @@ int register_power_pmu(struct power_pmu *pmu)
 }
 
 #ifdef CONFIG_PPC64
+static bool pmu_override = false;
+static unsigned long pmu_override_val;
+static void do_pmu_override(void *data)
+{
+	ppc_set_pmu_inuse(1);
+	if (pmu_override_val)
+		mtspr(SPRN_MMCR1, pmu_override_val);
+	mtspr(SPRN_MMCR0, mfspr(SPRN_MMCR0) & ~MMCR0_FC);
+}
+
 static int __init init_ppc64_pmu(void)
 {
+	if (cpu_has_feature(CPU_FTR_HVMODE) && pmu_override) {
+		pr_warn("disabling perf due to pmu_override= command line option.\n");
+		on_each_cpu(do_pmu_override, NULL, 1);
+		return 0;
+	}
+
 	/* run through all the pmu drivers one at a time */
 	if (!init_power5_pmu())
 		return 0;
@@ -2442,4 +2458,23 @@ static int __init init_ppc64_pmu(void)
 		return init_generic_compat_pmu();
 }
 early_initcall(init_ppc64_pmu);
+
+static int __init pmu_setup(char *str)
+{
+	unsigned long val;
+
+	if (!early_cpu_has_feature(CPU_FTR_HVMODE))
+		return 0;
+
+	pmu_override = true;
+
+	if (kstrtoul(str, 0, &val))
+		val = 0;
+
+	pmu_override_val = val;
+
+	return 1;
+}
+__setup("pmu_override=", pmu_setup);
+
 #endif

arch/powerpc/platforms/powernv/idle.c

@@ -306,8 +306,8 @@ struct p7_sprs {
 	/* per thread SPRs that get lost in shallow states */
 	u64 amr;
 	u64 iamr;
-	u64 amor;
 	u64 uamor;
+	/* amor is restored to constant ~0 */
 };
 
 static unsigned long power7_idle_insn(unsigned long type)
@@ -378,7 +378,6 @@ static unsigned long power7_idle_insn(unsigned long type)
 	if (cpu_has_feature(CPU_FTR_ARCH_207S)) {
 		sprs.amr	= mfspr(SPRN_AMR);
 		sprs.iamr	= mfspr(SPRN_IAMR);
-		sprs.amor	= mfspr(SPRN_AMOR);
 		sprs.uamor	= mfspr(SPRN_UAMOR);
 	}
 
@@ -397,7 +396,7 @@ static unsigned long power7_idle_insn(unsigned long type)
 			 */
 			mtspr(SPRN_AMR,		sprs.amr);
 			mtspr(SPRN_IAMR,	sprs.iamr);
-			mtspr(SPRN_AMOR,	sprs.amor);
+			mtspr(SPRN_AMOR,	~0);
 			mtspr(SPRN_UAMOR,	sprs.uamor);
 		}
 	}
@@ -589,7 +588,6 @@ struct p9_sprs {
 	u64 purr;
 	u64 spurr;
 	u64 dscr;
-	u64 wort;
 	u64 ciabr;
 
 	u64 mmcra;
@@ -687,7 +685,6 @@ static unsigned long power9_idle_stop(unsigned long psscr)
 
 	sprs.amr	= mfspr(SPRN_AMR);
 	sprs.iamr	= mfspr(SPRN_IAMR);
-	sprs.amor	= mfspr(SPRN_AMOR);
 	sprs.uamor	= mfspr(SPRN_UAMOR);
 
 	srr1 = isa300_idle_stop_mayloss(psscr);		/* go idle */
@@ -708,7 +705,7 @@ static unsigned long power9_idle_stop(unsigned long psscr)
 		 */
 		mtspr(SPRN_AMR,		sprs.amr);
 		mtspr(SPRN_IAMR,	sprs.iamr);
-		mtspr(SPRN_AMOR,	sprs.amor);
+		mtspr(SPRN_AMOR,	~0);
 		mtspr(SPRN_UAMOR,	sprs.uamor);
 
 		/*

arch/powerpc/xmon/xmon.c

@@ -2107,8 +2107,14 @@ static void dump_300_sprs(void)
 	if (!cpu_has_feature(CPU_FTR_ARCH_300))
 		return;
 
-	printf("pidr   = %.16lx  tidr  = %.16lx\n",
-		mfspr(SPRN_PID), mfspr(SPRN_TIDR));
+	if (cpu_has_feature(CPU_FTR_P9_TIDR)) {
+		printf("pidr   = %.16lx  tidr  = %.16lx\n",
+			mfspr(SPRN_PID), mfspr(SPRN_TIDR));
+	} else {
+		printf("pidr   = %.16lx\n",
+			mfspr(SPRN_PID));
+	}
+
 	printf("psscr  = %.16lx\n",
 		hv ? mfspr(SPRN_PSSCR) : mfspr(SPRN_PSSCR_PR));