KVM: PPC: Book3S HV: Extract PMU save/restore operations as C-callable functions

This pulls out the assembler code that is responsible for saving and
restoring the PMU state for the host and guest into separate functions
so they can be used from an alternate entry path.  The calling
convention is made compatible with C.
Reviewed-by: NDavid Gibson <david@gibson.dropbear.id.au>
Signed-off-by: NPaul Mackerras <paulus@ozlabs.org>
Reviewed-by: NMadhavan Srinivasan <maddy@linux.vnet.ibm.com>
Signed-off-by: NMichael Ellerman <mpe@ellerman.id.au>

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

@@ -150,4 +150,9 @@ extern s32 patch__memset_nocache, patch__memcpy_nocache;
 
 extern long flush_count_cache;
 
+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);
+
 #endif /* _ASM_POWERPC_ASM_PROTOTYPES_H */

arch/powerpc/kvm/book3s_hv_interrupts.S

@@ -64,52 +64,7 @@ BEGIN_FTR_SECTION
 END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_207S)
 
 	/* Save host PMU registers */
-BEGIN_FTR_SECTION
-	/* Work around P8 PMAE bug */
-	li	r3, -1
-	clrrdi	r3, r3, 10
-	mfspr	r8, SPRN_MMCR2
-	mtspr	SPRN_MMCR2, r3		/* freeze all counters using MMCR2 */
-	isync
-END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
-	li	r3, 1
-	sldi	r3, r3, 31		/* MMCR0_FC (freeze counters) bit */
-	mfspr	r7, SPRN_MMCR0		/* save MMCR0 */
-	mtspr	SPRN_MMCR0, r3		/* freeze all counters, disable interrupts */
-	mfspr	r6, SPRN_MMCRA
-	/* Clear MMCRA in order to disable SDAR updates */
-	li	r5, 0
-	mtspr	SPRN_MMCRA, r5
-	isync
-	lbz	r5, PACA_PMCINUSE(r13)	/* is the host using the PMU? */
-	cmpwi	r5, 0
-	beq	31f			/* skip if not */
-	mfspr	r5, SPRN_MMCR1
-	mfspr	r9, SPRN_SIAR
-	mfspr	r10, SPRN_SDAR
-	std	r7, HSTATE_MMCR0(r13)
-	std	r5, HSTATE_MMCR1(r13)
-	std	r6, HSTATE_MMCRA(r13)
-	std	r9, HSTATE_SIAR(r13)
-	std	r10, HSTATE_SDAR(r13)
-BEGIN_FTR_SECTION
-	mfspr	r9, SPRN_SIER
-	std	r8, HSTATE_MMCR2(r13)
-	std	r9, HSTATE_SIER(r13)
-END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
-	mfspr	r3, SPRN_PMC1
-	mfspr	r5, SPRN_PMC2
-	mfspr	r6, SPRN_PMC3
-	mfspr	r7, SPRN_PMC4
-	mfspr	r8, SPRN_PMC5
-	mfspr	r9, SPRN_PMC6
-	stw	r3, HSTATE_PMC1(r13)
-	stw	r5, HSTATE_PMC2(r13)
-	stw	r6, HSTATE_PMC3(r13)
-	stw	r7, HSTATE_PMC4(r13)
-	stw	r8, HSTATE_PMC5(r13)
-	stw	r9, HSTATE_PMC6(r13)
-31:
+	bl	kvmhv_save_host_pmu
 
 	/*
 	 * Put whatever is in the decrementer into the
@@ -161,3 +116,51 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300)
 	ld	r0, PPC_LR_STKOFF(r1)
 	mtlr	r0
 	blr
+
+_GLOBAL(kvmhv_save_host_pmu)
+BEGIN_FTR_SECTION
+	/* Work around P8 PMAE bug */
+	li	r3, -1
+	clrrdi	r3, r3, 10
+	mfspr	r8, SPRN_MMCR2
+	mtspr	SPRN_MMCR2, r3		/* freeze all counters using MMCR2 */
+	isync
+END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
+	li	r3, 1
+	sldi	r3, r3, 31		/* MMCR0_FC (freeze counters) bit */
+	mfspr	r7, SPRN_MMCR0		/* save MMCR0 */
+	mtspr	SPRN_MMCR0, r3		/* freeze all counters, disable interrupts */
+	mfspr	r6, SPRN_MMCRA
+	/* Clear MMCRA in order to disable SDAR updates */
+	li	r5, 0
+	mtspr	SPRN_MMCRA, r5
+	isync
+	lbz	r5, PACA_PMCINUSE(r13)	/* is the host using the PMU? */
+	cmpwi	r5, 0
+	beq	31f			/* skip if not */
+	mfspr	r5, SPRN_MMCR1
+	mfspr	r9, SPRN_SIAR
+	mfspr	r10, SPRN_SDAR
+	std	r7, HSTATE_MMCR0(r13)
+	std	r5, HSTATE_MMCR1(r13)
+	std	r6, HSTATE_MMCRA(r13)
+	std	r9, HSTATE_SIAR(r13)
+	std	r10, HSTATE_SDAR(r13)
+BEGIN_FTR_SECTION
+	mfspr	r9, SPRN_SIER
+	std	r8, HSTATE_MMCR2(r13)
+	std	r9, HSTATE_SIER(r13)
+END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
+	mfspr	r3, SPRN_PMC1
+	mfspr	r5, SPRN_PMC2
+	mfspr	r6, SPRN_PMC3
+	mfspr	r7, SPRN_PMC4
+	mfspr	r8, SPRN_PMC5
+	mfspr	r9, SPRN_PMC6
+	stw	r3, HSTATE_PMC1(r13)
+	stw	r5, HSTATE_PMC2(r13)
+	stw	r6, HSTATE_PMC3(r13)
+	stw	r7, HSTATE_PMC4(r13)
+	stw	r8, HSTATE_PMC5(r13)
+	stw	r9, HSTATE_PMC6(r13)
+31:	blr

arch/powerpc/kvm/book3s_hv_rmhandlers.S

@@ -28,6 +28,7 @@
 #include <asm/exception-64s.h>
 #include <asm/kvm_book3s_asm.h>
 #include <asm/book3s/64/mmu-hash.h>
+#include <asm/export.h>
 #include <asm/tm.h>
 #include <asm/opal.h>
 #include <asm/xive-regs.h>
@@ -113,45 +114,7 @@ END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_207S)
 	mtspr	SPRN_SPRG_VDSO_WRITE,r3
 
 	/* Reload the host's PMU registers */
-	lbz	r4, PACA_PMCINUSE(r13) /* is the host using the PMU? */
-	cmpwi	r4, 0
-	beq	23f			/* skip if not */
-BEGIN_FTR_SECTION
-	ld	r3, HSTATE_MMCR0(r13)
-	andi.	r4, r3, MMCR0_PMAO_SYNC | MMCR0_PMAO
-	cmpwi	r4, MMCR0_PMAO
-	beql	kvmppc_fix_pmao
-END_FTR_SECTION_IFSET(CPU_FTR_PMAO_BUG)
-	lwz	r3, HSTATE_PMC1(r13)
-	lwz	r4, HSTATE_PMC2(r13)
-	lwz	r5, HSTATE_PMC3(r13)
-	lwz	r6, HSTATE_PMC4(r13)
-	lwz	r8, HSTATE_PMC5(r13)
-	lwz	r9, HSTATE_PMC6(r13)
-	mtspr	SPRN_PMC1, r3
-	mtspr	SPRN_PMC2, r4
-	mtspr	SPRN_PMC3, r5
-	mtspr	SPRN_PMC4, r6
-	mtspr	SPRN_PMC5, r8
-	mtspr	SPRN_PMC6, r9
-	ld	r3, HSTATE_MMCR0(r13)
-	ld	r4, HSTATE_MMCR1(r13)
-	ld	r5, HSTATE_MMCRA(r13)
-	ld	r6, HSTATE_SIAR(r13)
-	ld	r7, HSTATE_SDAR(r13)
-	mtspr	SPRN_MMCR1, r4
-	mtspr	SPRN_MMCRA, r5
-	mtspr	SPRN_SIAR, r6
-	mtspr	SPRN_SDAR, r7
-BEGIN_FTR_SECTION
-	ld	r8, HSTATE_MMCR2(r13)
-	ld	r9, HSTATE_SIER(r13)
-	mtspr	SPRN_MMCR2, r8
-	mtspr	SPRN_SIER, r9
-END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
-	mtspr	SPRN_MMCR0, r3
-	isync
-23:
+	bl	kvmhv_load_host_pmu
 
 	/*
 	 * Reload DEC.  HDEC interrupts were disabled when
@@ -805,57 +768,12 @@ END_FTR_SECTION(CPU_FTR_TM | CPU_FTR_P9_TM_HV_ASSIST, 0)
 91:
 #endif
 
-	/* Load guest PMU registers */
-	/* R4 is live here (vcpu pointer) */
-	li	r3, 1
-	sldi	r3, r3, 31		/* MMCR0_FC (freeze counters) bit */
-	mtspr	SPRN_MMCR0, r3		/* freeze all counters, disable ints */
-	isync
-BEGIN_FTR_SECTION
-	ld	r3, VCPU_MMCR(r4)
-	andi.	r5, r3, MMCR0_PMAO_SYNC | MMCR0_PMAO
-	cmpwi	r5, MMCR0_PMAO
-	beql	kvmppc_fix_pmao
-END_FTR_SECTION_IFSET(CPU_FTR_PMAO_BUG)
-	lwz	r3, VCPU_PMC(r4)	/* always load up guest PMU registers */
-	lwz	r5, VCPU_PMC + 4(r4)	/* to prevent information leak */
-	lwz	r6, VCPU_PMC + 8(r4)
-	lwz	r7, VCPU_PMC + 12(r4)
-	lwz	r8, VCPU_PMC + 16(r4)
-	lwz	r9, VCPU_PMC + 20(r4)
-	mtspr	SPRN_PMC1, r3
-	mtspr	SPRN_PMC2, r5
-	mtspr	SPRN_PMC3, r6
-	mtspr	SPRN_PMC4, r7
-	mtspr	SPRN_PMC5, r8
-	mtspr	SPRN_PMC6, r9
-	ld	r3, VCPU_MMCR(r4)
-	ld	r5, VCPU_MMCR + 8(r4)
-	ld	r6, VCPU_MMCR + 16(r4)
-	ld	r7, VCPU_SIAR(r4)
-	ld	r8, VCPU_SDAR(r4)
-	mtspr	SPRN_MMCR1, r5
-	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(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_MMCR + 32(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
+	/* Load guest PMU registers; r4 = vcpu pointer here */
+	mr	r3, r4
+	bl	kvmhv_load_guest_pmu
 
 	/* Load up FP, VMX and VSX registers */
+	ld	r4, HSTATE_KVM_VCPU(r13)
 	bl	kvmppc_load_fp
 
 	ld	r14, VCPU_GPR(R14)(r4)
@@ -1766,83 +1684,12 @@ END_FTR_SECTION(CPU_FTR_TM | CPU_FTR_P9_TM_HV_ASSIST, 0)
 25:
 	/* Save PMU registers if requested */
 	/* r8 and cr0.eq are live here */
-BEGIN_FTR_SECTION
-	/*
-	 * POWER8 seems to have a hardware bug where setting
-	 * MMCR0[PMAE] along with MMCR0[PMC1CE] and/or MMCR0[PMCjCE]
-	 * when some counters are already negative doesn't seem
-	 * to cause a performance monitor alert (and hence interrupt).
-	 * The effect of this is that when saving the PMU state,
-	 * if there is no PMU alert pending when we read MMCR0
-	 * before freezing the counters, but one becomes pending
-	 * before we read the counters, we lose it.
-	 * To work around this, we need a way to freeze the counters
-	 * before reading MMCR0.  Normally, freezing the counters
-	 * is done by writing MMCR0 (to set MMCR0[FC]) which
-	 * unavoidably writes MMCR0[PMA0] as well.  On POWER8,
-	 * we can also freeze the counters using MMCR2, by writing
-	 * 1s to all the counter freeze condition bits (there are
-	 * 9 bits each for 6 counters).
-	 */
-	li	r3, -1			/* set all freeze bits */
-	clrrdi	r3, r3, 10
-	mfspr	r10, SPRN_MMCR2
-	mtspr	SPRN_MMCR2, r3
-	isync
-END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
-	li	r3, 1
-	sldi	r3, r3, 31		/* MMCR0_FC (freeze counters) bit */
-	mfspr	r4, SPRN_MMCR0		/* save MMCR0 */
-	mtspr	SPRN_MMCR0, r3		/* freeze all counters, disable ints */
-	mfspr	r6, SPRN_MMCRA
-	/* Clear MMCRA in order to disable SDAR updates */
-	li	r7, 0
-	mtspr	SPRN_MMCRA, r7
-	isync
+	mr	r3, r9
+	li	r4, 1
 	beq	21f			/* if no VPA, save PMU stuff anyway */
-	lbz	r7, LPPACA_PMCINUSE(r8)
-	cmpwi	r7, 0			/* did they ask for PMU stuff to be saved? */
-	bne	21f
-	std	r3, VCPU_MMCR(r9)	/* if not, set saved MMCR0 to FC */
-	b	22f
-21:	mfspr	r5, SPRN_MMCR1
-	mfspr	r7, SPRN_SIAR
-	mfspr	r8, SPRN_SDAR
-	std	r4, VCPU_MMCR(r9)
-	std	r5, VCPU_MMCR + 8(r9)
-	std	r6, VCPU_MMCR + 16(r9)
-BEGIN_FTR_SECTION
-	std	r10, VCPU_MMCR + 24(r9)
-END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
-	std	r7, VCPU_SIAR(r9)
-	std	r8, VCPU_SDAR(r9)
-	mfspr	r3, SPRN_PMC1
-	mfspr	r4, SPRN_PMC2
-	mfspr	r5, SPRN_PMC3
-	mfspr	r6, SPRN_PMC4
-	mfspr	r7, SPRN_PMC5
-	mfspr	r8, SPRN_PMC6
-	stw	r3, VCPU_PMC(r9)
-	stw	r4, VCPU_PMC + 4(r9)
-	stw	r5, VCPU_PMC + 8(r9)
-	stw	r6, VCPU_PMC + 12(r9)
-	stw	r7, VCPU_PMC + 16(r9)
-	stw	r8, VCPU_PMC + 20(r9)
-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
-	stw	r6, VCPU_PMC + 24(r9)
-	stw	r7, VCPU_PMC + 28(r9)
-	std	r8, VCPU_MMCR + 32(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:
+	lbz	r4, LPPACA_PMCINUSE(r8)
+21:	bl	kvmhv_save_guest_pmu
+	ld	r9, HSTATE_KVM_VCPU(r13)
 
 	/* Restore host values of some registers */
 BEGIN_FTR_SECTION
@@ -3387,6 +3234,194 @@ kvmppc_msr_interrupt:
 1:	rldimi	r11, r0, MSR_TS_S_LG, 63 - MSR_TS_T_LG
 	blr
 
+/*
+ * Load up guest PMU state.  R3 points to the vcpu struct.
+ */
+_GLOBAL(kvmhv_load_guest_pmu)
+EXPORT_SYMBOL_GPL(kvmhv_load_guest_pmu)
+	mr	r4, r3
+	mflr	r0
+	li	r3, 1
+	sldi	r3, r3, 31		/* MMCR0_FC (freeze counters) bit */
+	mtspr	SPRN_MMCR0, r3		/* freeze all counters, disable ints */
+	isync
+BEGIN_FTR_SECTION
+	ld	r3, VCPU_MMCR(r4)
+	andi.	r5, r3, MMCR0_PMAO_SYNC | MMCR0_PMAO
+	cmpwi	r5, MMCR0_PMAO
+	beql	kvmppc_fix_pmao
+END_FTR_SECTION_IFSET(CPU_FTR_PMAO_BUG)
+	lwz	r3, VCPU_PMC(r4)	/* always load up guest PMU registers */
+	lwz	r5, VCPU_PMC + 4(r4)	/* to prevent information leak */
+	lwz	r6, VCPU_PMC + 8(r4)
+	lwz	r7, VCPU_PMC + 12(r4)
+	lwz	r8, VCPU_PMC + 16(r4)
+	lwz	r9, VCPU_PMC + 20(r4)
+	mtspr	SPRN_PMC1, r3
+	mtspr	SPRN_PMC2, r5
+	mtspr	SPRN_PMC3, r6
+	mtspr	SPRN_PMC4, r7
+	mtspr	SPRN_PMC5, r8
+	mtspr	SPRN_PMC6, r9
+	ld	r3, VCPU_MMCR(r4)
+	ld	r5, VCPU_MMCR + 8(r4)
+	ld	r6, VCPU_MMCR + 16(r4)
+	ld	r7, VCPU_SIAR(r4)
+	ld	r8, VCPU_SDAR(r4)
+	mtspr	SPRN_MMCR1, r5
+	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(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_MMCR + 32(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
+	mtlr	r0
+	blr
+
+/*
+ * 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)
+	mflr	r0
+	lbz	r4, PACA_PMCINUSE(r13) /* is the host using the PMU? */
+	cmpwi	r4, 0
+	beq	23f			/* skip if not */
+BEGIN_FTR_SECTION
+	ld	r3, HSTATE_MMCR0(r13)
+	andi.	r4, r3, MMCR0_PMAO_SYNC | MMCR0_PMAO
+	cmpwi	r4, MMCR0_PMAO
+	beql	kvmppc_fix_pmao
+END_FTR_SECTION_IFSET(CPU_FTR_PMAO_BUG)
+	lwz	r3, HSTATE_PMC1(r13)
+	lwz	r4, HSTATE_PMC2(r13)
+	lwz	r5, HSTATE_PMC3(r13)
+	lwz	r6, HSTATE_PMC4(r13)
+	lwz	r8, HSTATE_PMC5(r13)
+	lwz	r9, HSTATE_PMC6(r13)
+	mtspr	SPRN_PMC1, r3
+	mtspr	SPRN_PMC2, r4
+	mtspr	SPRN_PMC3, r5
+	mtspr	SPRN_PMC4, r6
+	mtspr	SPRN_PMC5, r8
+	mtspr	SPRN_PMC6, r9
+	ld	r3, HSTATE_MMCR0(r13)
+	ld	r4, HSTATE_MMCR1(r13)
+	ld	r5, HSTATE_MMCRA(r13)
+	ld	r6, HSTATE_SIAR(r13)
+	ld	r7, HSTATE_SDAR(r13)
+	mtspr	SPRN_MMCR1, r4
+	mtspr	SPRN_MMCRA, r5
+	mtspr	SPRN_SIAR, r6
+	mtspr	SPRN_SDAR, r7
+BEGIN_FTR_SECTION
+	ld	r8, HSTATE_MMCR2(r13)
+	ld	r9, HSTATE_SIER(r13)
+	mtspr	SPRN_MMCR2, r8
+	mtspr	SPRN_SIER, r9
+END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
+	mtspr	SPRN_MMCR0, r3
+	isync
+	mtlr	r0
+23:	blr
+
+/*
+ * 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)
+	mr	r9, r3
+	mr	r8, r4
+BEGIN_FTR_SECTION
+	/*
+	 * POWER8 seems to have a hardware bug where setting
+	 * MMCR0[PMAE] along with MMCR0[PMC1CE] and/or MMCR0[PMCjCE]
+	 * when some counters are already negative doesn't seem
+	 * to cause a performance monitor alert (and hence interrupt).
+	 * The effect of this is that when saving the PMU state,
+	 * if there is no PMU alert pending when we read MMCR0
+	 * before freezing the counters, but one becomes pending
+	 * before we read the counters, we lose it.
+	 * To work around this, we need a way to freeze the counters
+	 * before reading MMCR0.  Normally, freezing the counters
+	 * is done by writing MMCR0 (to set MMCR0[FC]) which
+	 * unavoidably writes MMCR0[PMA0] as well.  On POWER8,
+	 * we can also freeze the counters using MMCR2, by writing
+	 * 1s to all the counter freeze condition bits (there are
+	 * 9 bits each for 6 counters).
+	 */
+	li	r3, -1			/* set all freeze bits */
+	clrrdi	r3, r3, 10
+	mfspr	r10, SPRN_MMCR2
+	mtspr	SPRN_MMCR2, r3
+	isync
+END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
+	li	r3, 1
+	sldi	r3, r3, 31		/* MMCR0_FC (freeze counters) bit */
+	mfspr	r4, SPRN_MMCR0		/* save MMCR0 */
+	mtspr	SPRN_MMCR0, r3		/* freeze all counters, disable ints */
+	mfspr	r6, SPRN_MMCRA
+	/* Clear MMCRA in order to disable SDAR updates */
+	li	r7, 0
+	mtspr	SPRN_MMCRA, r7
+	isync
+	cmpwi	r8, 0			/* did they ask for PMU stuff to be saved? */
+	bne	21f
+	std	r3, VCPU_MMCR(r9)	/* if not, set saved MMCR0 to FC */
+	b	22f
+21:	mfspr	r5, SPRN_MMCR1
+	mfspr	r7, SPRN_SIAR
+	mfspr	r8, SPRN_SDAR
+	std	r4, VCPU_MMCR(r9)
+	std	r5, VCPU_MMCR + 8(r9)
+	std	r6, VCPU_MMCR + 16(r9)
+BEGIN_FTR_SECTION
+	std	r10, VCPU_MMCR + 24(r9)
+END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
+	std	r7, VCPU_SIAR(r9)
+	std	r8, VCPU_SDAR(r9)
+	mfspr	r3, SPRN_PMC1
+	mfspr	r4, SPRN_PMC2
+	mfspr	r5, SPRN_PMC3
+	mfspr	r6, SPRN_PMC4
+	mfspr	r7, SPRN_PMC5
+	mfspr	r8, SPRN_PMC6
+	stw	r3, VCPU_PMC(r9)
+	stw	r4, VCPU_PMC + 4(r9)
+	stw	r5, VCPU_PMC + 8(r9)
+	stw	r6, VCPU_PMC + 12(r9)
+	stw	r7, VCPU_PMC + 16(r9)
+	stw	r8, VCPU_PMC + 20(r9)
+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
+	stw	r6, VCPU_PMC + 24(r9)
+	stw	r7, VCPU_PMC + 28(r9)
+	std	r8, VCPU_MMCR + 32(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
+
 /*
  * This works around a hardware bug on POWER8E processors, where
  * writing a 1 to the MMCR0[PMAO] bit doesn't generate a