KVM: PPC: Book3S HV: Context-switch new POWER8 SPRs

This adds fields to the struct kvm_vcpu_arch to store the new
guest-accessible SPRs on POWER8, adds code to the get/set_one_reg
functions to allow userspace to access this state, and adds code to
the guest entry and exit to context-switch these SPRs between host
and guest.

Note that DPDES (Directed Privileged Doorbell Exception State) is
shared between threads on a core; hence we store it in struct
kvmppc_vcore and have the master thread save and restore it.

Signed-off-by: Michael Neuling <mikey@neuling.org>
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>

6 files changed, 361 insertions, 3 deletions

diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h
index b850544dbc3f..81c92d1d7978 100644
--- a/arch/powerpc/include/asm/kvm_host.h
+++ b/arch/powerpc/include/asm/kvm_host.h
@@ -304,6 +304,7 @@ struct kvmppc_vcore {
 	ulong lpcr;
 	u32 arch_compat;
 	ulong pcr;
+	ulong dpdes;		/* doorbell state (POWER8) */
 };
 
 #define VCORE_ENTRY_COUNT(vc)	((vc)->entry_exit_count & 0xff)
@@ -448,6 +449,7 @@ struct kvm_vcpu_arch {
 	ulong pc;
 	ulong ctr;
 	ulong lr;
+	ulong tar;
 
 	ulong xer;
 	u32 cr;
@@ -457,13 +459,32 @@ struct kvm_vcpu_arch {
 	ulong guest_owned_ext;
 	ulong purr;
 	ulong spurr;
+	ulong ic;
+	ulong vtb;
 	ulong dscr;
 	ulong amr;
 	ulong uamor;
+	ulong iamr;
 	u32 ctrl;
 	ulong dabr;
+	ulong dawr;
+	ulong dawrx;
+	ulong ciabr;
 	ulong cfar;
 	ulong ppr;
+	ulong pspb;
+	ulong fscr;
+	ulong tfhar;
+	ulong tfiar;
+	ulong texasr;
+	ulong ebbhr;
+	ulong ebbrr;
+	ulong bescr;
+	ulong csigr;
+	ulong tacr;
+	ulong tcscr;
+	ulong acop;
+	ulong wort;
 	ulong shadow_srr1;
 #endif
 	u32 vrsave; /* also USPRG0 */
@@ -498,10 +519,12 @@ struct kvm_vcpu_arch {
 	u32 ccr1;
 	u32 dbsr;
 
-	u64 mmcr[3];
+	u64 mmcr[5];
 	u32 pmc[8];
+	u32 spmc[2];
 	u64 siar;
 	u64 sdar;
+	u64 sier;
 
 #ifdef CONFIG_KVM_EXIT_TIMING
 	struct mutex exit_timing_lock;
diff --git a/arch/powerpc/include/asm/reg.h b/arch/powerpc/include/asm/reg.h
index 5c45787d551e..2f41e6475648 100644
--- a/arch/powerpc/include/asm/reg.h
+++ b/arch/powerpc/include/asm/reg.h
@@ -223,6 +223,11 @@
 #define   CTRL_TE	0x00c00000	/* thread enable */
 #define   CTRL_RUNLATCH	0x1
 #define SPRN_DAWR	0xB4
+#define SPRN_CIABR	0xBB
+#define   CIABR_PRIV		0x3
+#define   CIABR_PRIV_USER	1
+#define   CIABR_PRIV_SUPER	2
+#define   CIABR_PRIV_HYPER	3
 #define SPRN_DAWRX	0xBC
 #define   DAWRX_USER	(1UL << 0)
 #define   DAWRX_KERNEL	(1UL << 1)
@@ -260,6 +265,8 @@
 #define SPRN_HRMOR	0x139	/* Real mode offset register */
 #define SPRN_HSRR0	0x13A	/* Hypervisor Save/Restore 0 */
 #define SPRN_HSRR1	0x13B	/* Hypervisor Save/Restore 1 */
+#define SPRN_IC		0x350	/* Virtual Instruction Count */
+#define SPRN_VTB	0x351	/* Virtual Time Base */
 /* HFSCR and FSCR bit numbers are the same */
 #define FSCR_TAR_LG	8	/* Enable Target Address Register */
 #define FSCR_EBB_LG	7	/* Enable Event Based Branching */
@@ -368,6 +375,8 @@
 #define DER_EBRKE	0x00000002	/* External Breakpoint Interrupt */
 #define DER_DPIE	0x00000001	/* Dev. Port Nonmaskable Request */
 #define SPRN_DMISS	0x3D0		/* Data TLB Miss Register */
+#define SPRN_DHDES	0x0B1		/* Directed Hyp. Doorbell Exc. State */
+#define SPRN_DPDES	0x0B0		/* Directed Priv. Doorbell Exc. State */
 #define SPRN_EAR	0x11A		/* External Address Register */
 #define SPRN_HASH1	0x3D2		/* Primary Hash Address Register */
 #define SPRN_HASH2	0x3D3		/* Secondary Hash Address Resgister */
@@ -427,6 +436,7 @@
 #define SPRN_IABR	0x3F2	/* Instruction Address Breakpoint Register */
 #define SPRN_IABR2	0x3FA		/* 83xx */
 #define SPRN_IBCR	0x135		/* 83xx Insn Breakpoint Control Reg */
+#define SPRN_IAMR	0x03D		/* Instr. Authority Mask Reg */
 #define SPRN_HID4	0x3F4		/* 970 HID4 */
 #define  HID4_LPES0	 (1ul << (63-0)) /* LPAR env. sel. bit 0 */
 #define	 HID4_RMLS2_SH	 (63 - 2)	/* Real mode limit bottom 2 bits */
@@ -541,6 +551,7 @@
 #define SPRN_PIR	0x3FF	/* Processor Identification Register */
 #endif
 #define SPRN_TIR	0x1BE	/* Thread Identification Register */
+#define SPRN_PSPB	0x09F	/* Problem State Priority Boost reg */
 #define SPRN_PTEHI	0x3D5	/* 981 7450 PTE HI word (S/W TLB load) */
 #define SPRN_PTELO	0x3D6	/* 982 7450 PTE LO word (S/W TLB load) */
 #define SPRN_PURR	0x135	/* Processor Utilization of Resources Reg */
@@ -682,6 +693,7 @@
 #define SPRN_EBBHR	804	/* Event based branch handler register */
 #define SPRN_EBBRR	805	/* Event based branch return register */
 #define SPRN_BESCR	806	/* Branch event status and control register */
+#define SPRN_WORT	895	/* Workload optimization register - thread */
 
 #define SPRN_PMC1	787
 #define SPRN_PMC2	788
@@ -698,6 +710,11 @@
 #define   SIER_SIHV		0x1000000	/* Sampled MSR_HV */
 #define   SIER_SIAR_VALID	0x0400000	/* SIAR contents valid */
 #define   SIER_SDAR_VALID	0x0200000	/* SDAR contents valid */
+#define SPRN_TACR	888
+#define SPRN_TCSCR	889
+#define SPRN_CSIGR	890
+#define SPRN_SPMC1	892
+#define SPRN_SPMC2	893
 
 /* When EBB is enabled, some of MMCR0/MMCR2/SIER are user accessible */
 #define MMCR0_USER_MASK	(MMCR0_FC | MMCR0_PMXE | MMCR0_PMAO)
diff --git a/arch/powerpc/include/uapi/asm/kvm.h b/arch/powerpc/include/uapi/asm/kvm.h
index 6836ec79a830..a586fb9b77bd 100644
--- a/arch/powerpc/include/uapi/asm/kvm.h
+++ b/arch/powerpc/include/uapi/asm/kvm.h
@@ -545,6 +545,7 @@ struct kvm_get_htab_header {
 #define KVM_REG_PPC_TCSCR	(KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xb1)
 #define KVM_REG_PPC_PID		(KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xb2)
 #define KVM_REG_PPC_ACOP	(KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xb3)
+#define KVM_REG_PPC_WORT	(KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xb4)
 
 #define KVM_REG_PPC_VRSAVE	(KVM_REG_PPC | KVM_REG_SIZE_U32 | 0xb4)
 #define KVM_REG_PPC_LPCR	(KVM_REG_PPC | KVM_REG_SIZE_U32 | 0xb5)
diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c
index 332ae66883e4..043900abbbb0 100644
--- a/arch/powerpc/kernel/asm-offsets.c
+++ b/arch/powerpc/kernel/asm-offsets.c
@@ -432,6 +432,7 @@ int main(void)
 	DEFINE(VCPU_XER, offsetof(struct kvm_vcpu, arch.xer));
 	DEFINE(VCPU_CTR, offsetof(struct kvm_vcpu, arch.ctr));
 	DEFINE(VCPU_LR, offsetof(struct kvm_vcpu, arch.lr));
+	DEFINE(VCPU_TAR, offsetof(struct kvm_vcpu, arch.tar));
 	DEFINE(VCPU_CR, offsetof(struct kvm_vcpu, arch.cr));
 	DEFINE(VCPU_PC, offsetof(struct kvm_vcpu, arch.pc));
 #ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
@@ -484,11 +485,17 @@ int main(void)
 	DEFINE(VCPU_VCPUID, offsetof(struct kvm_vcpu, vcpu_id));
 	DEFINE(VCPU_PURR, offsetof(struct kvm_vcpu, arch.purr));
 	DEFINE(VCPU_SPURR, offsetof(struct kvm_vcpu, arch.spurr));
+	DEFINE(VCPU_IC, offsetof(struct kvm_vcpu, arch.ic));
+	DEFINE(VCPU_VTB, offsetof(struct kvm_vcpu, arch.vtb));
 	DEFINE(VCPU_DSCR, offsetof(struct kvm_vcpu, arch.dscr));
 	DEFINE(VCPU_AMR, offsetof(struct kvm_vcpu, arch.amr));
 	DEFINE(VCPU_UAMOR, offsetof(struct kvm_vcpu, arch.uamor));
+	DEFINE(VCPU_IAMR, offsetof(struct kvm_vcpu, arch.iamr));
 	DEFINE(VCPU_CTRL, offsetof(struct kvm_vcpu, arch.ctrl));
 	DEFINE(VCPU_DABR, offsetof(struct kvm_vcpu, arch.dabr));
+	DEFINE(VCPU_DAWR, offsetof(struct kvm_vcpu, arch.dawr));
+	DEFINE(VCPU_DAWRX, offsetof(struct kvm_vcpu, arch.dawrx));
+	DEFINE(VCPU_CIABR, offsetof(struct kvm_vcpu, arch.ciabr));
 	DEFINE(VCPU_HFLAGS, offsetof(struct kvm_vcpu, arch.hflags));
 	DEFINE(VCPU_DEC, offsetof(struct kvm_vcpu, arch.dec));
 	DEFINE(VCPU_DEC_EXPIRES, offsetof(struct kvm_vcpu, arch.dec_expires));
@@ -497,8 +504,10 @@ int main(void)
 	DEFINE(VCPU_PRODDED, offsetof(struct kvm_vcpu, arch.prodded));
 	DEFINE(VCPU_MMCR, offsetof(struct kvm_vcpu, arch.mmcr));
 	DEFINE(VCPU_PMC, offsetof(struct kvm_vcpu, arch.pmc));
+	DEFINE(VCPU_SPMC, offsetof(struct kvm_vcpu, arch.spmc));
 	DEFINE(VCPU_SIAR, offsetof(struct kvm_vcpu, arch.siar));
 	DEFINE(VCPU_SDAR, offsetof(struct kvm_vcpu, arch.sdar));
+	DEFINE(VCPU_SIER, offsetof(struct kvm_vcpu, arch.sier));
 	DEFINE(VCPU_SLB, offsetof(struct kvm_vcpu, arch.slb));
 	DEFINE(VCPU_SLB_MAX, offsetof(struct kvm_vcpu, arch.slb_max));
 	DEFINE(VCPU_SLB_NR, offsetof(struct kvm_vcpu, arch.slb_nr));
@@ -508,6 +517,19 @@ int main(void)
 	DEFINE(VCPU_TRAP, offsetof(struct kvm_vcpu, arch.trap));
 	DEFINE(VCPU_CFAR, offsetof(struct kvm_vcpu, arch.cfar));
 	DEFINE(VCPU_PPR, offsetof(struct kvm_vcpu, arch.ppr));
+	DEFINE(VCPU_FSCR, offsetof(struct kvm_vcpu, arch.fscr));
+	DEFINE(VCPU_PSPB, offsetof(struct kvm_vcpu, arch.pspb));
+	DEFINE(VCPU_TFHAR, offsetof(struct kvm_vcpu, arch.tfhar));
+	DEFINE(VCPU_TFIAR, offsetof(struct kvm_vcpu, arch.tfiar));
+	DEFINE(VCPU_TEXASR, offsetof(struct kvm_vcpu, arch.texasr));
+	DEFINE(VCPU_EBBHR, offsetof(struct kvm_vcpu, arch.ebbhr));
+	DEFINE(VCPU_EBBRR, offsetof(struct kvm_vcpu, arch.ebbrr));
+	DEFINE(VCPU_BESCR, offsetof(struct kvm_vcpu, arch.bescr));
+	DEFINE(VCPU_CSIGR, offsetof(struct kvm_vcpu, arch.csigr));
+	DEFINE(VCPU_TACR, offsetof(struct kvm_vcpu, arch.tacr));
+	DEFINE(VCPU_TCSCR, offsetof(struct kvm_vcpu, arch.tcscr));
+	DEFINE(VCPU_ACOP, offsetof(struct kvm_vcpu, arch.acop));
+	DEFINE(VCPU_WORT, offsetof(struct kvm_vcpu, arch.wort));
 	DEFINE(VCPU_SHADOW_SRR1, offsetof(struct kvm_vcpu, arch.shadow_srr1));
 	DEFINE(VCORE_ENTRY_EXIT, offsetof(struct kvmppc_vcore, entry_exit_count));
 	DEFINE(VCORE_NAP_COUNT, offsetof(struct kvmppc_vcore, nap_count));
@@ -517,6 +539,7 @@ int main(void)
 	DEFINE(VCORE_TB_OFFSET, offsetof(struct kvmppc_vcore, tb_offset));
 	DEFINE(VCORE_LPCR, offsetof(struct kvmppc_vcore, lpcr));
 	DEFINE(VCORE_PCR, offsetof(struct kvmppc_vcore, pcr));
+	DEFINE(VCORE_DPDES, offsetof(struct kvmppc_vcore, dpdes));
 	DEFINE(VCPU_SLB_E, offsetof(struct kvmppc_slb, orige));
 	DEFINE(VCPU_SLB_V, offsetof(struct kvmppc_slb, origv));
 	DEFINE(VCPU_SLB_SIZE, sizeof(struct kvmppc_slb));
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index 7da53cd215db..5b08ddf91d2d 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -800,7 +800,7 @@ static int kvmppc_get_one_reg_hv(struct kvm_vcpu *vcpu, u64 id,
 	case KVM_REG_PPC_UAMOR:
 		*val = get_reg_val(id, vcpu->arch.uamor);
 		break;
-	case KVM_REG_PPC_MMCR0 ... KVM_REG_PPC_MMCRA:
+	case KVM_REG_PPC_MMCR0 ... KVM_REG_PPC_MMCRS:
 		i = id - KVM_REG_PPC_MMCR0;
 		*val = get_reg_val(id, vcpu->arch.mmcr[i]);
 		break;
@@ -808,12 +808,85 @@ static int kvmppc_get_one_reg_hv(struct kvm_vcpu *vcpu, u64 id,
 		i = id - KVM_REG_PPC_PMC1;
 		*val = get_reg_val(id, vcpu->arch.pmc[i]);
 		break;
+	case KVM_REG_PPC_SPMC1 ... KVM_REG_PPC_SPMC2:
+		i = id - KVM_REG_PPC_SPMC1;
+		*val = get_reg_val(id, vcpu->arch.spmc[i]);
+		break;
 	case KVM_REG_PPC_SIAR:
 		*val = get_reg_val(id, vcpu->arch.siar);
 		break;
 	case KVM_REG_PPC_SDAR:
 		*val = get_reg_val(id, vcpu->arch.sdar);
 		break;
+	case KVM_REG_PPC_SIER:
+		*val = get_reg_val(id, vcpu->arch.sier);
+		break;
+	case KVM_REG_PPC_IAMR:
+		*val = get_reg_val(id, vcpu->arch.iamr);
+		break;
+	case KVM_REG_PPC_TFHAR:
+		*val = get_reg_val(id, vcpu->arch.tfhar);
+		break;
+	case KVM_REG_PPC_TFIAR:
+		*val = get_reg_val(id, vcpu->arch.tfiar);
+		break;
+	case KVM_REG_PPC_TEXASR:
+		*val = get_reg_val(id, vcpu->arch.texasr);
+		break;
+	case KVM_REG_PPC_FSCR:
+		*val = get_reg_val(id, vcpu->arch.fscr);
+		break;
+	case KVM_REG_PPC_PSPB:
+		*val = get_reg_val(id, vcpu->arch.pspb);
+		break;
+	case KVM_REG_PPC_EBBHR:
+		*val = get_reg_val(id, vcpu->arch.ebbhr);
+		break;
+	case KVM_REG_PPC_EBBRR:
+		*val = get_reg_val(id, vcpu->arch.ebbrr);
+		break;
+	case KVM_REG_PPC_BESCR:
+		*val = get_reg_val(id, vcpu->arch.bescr);
+		break;
+	case KVM_REG_PPC_TAR:
+		*val = get_reg_val(id, vcpu->arch.tar);
+		break;
+	case KVM_REG_PPC_DPDES:
+		*val = get_reg_val(id, vcpu->arch.vcore->dpdes);
+		break;
+	case KVM_REG_PPC_DAWR:
+		*val = get_reg_val(id, vcpu->arch.dawr);
+		break;
+	case KVM_REG_PPC_DAWRX:
+		*val = get_reg_val(id, vcpu->arch.dawrx);
+		break;
+	case KVM_REG_PPC_CIABR:
+		*val = get_reg_val(id, vcpu->arch.ciabr);
+		break;
+	case KVM_REG_PPC_IC:
+		*val = get_reg_val(id, vcpu->arch.ic);
+		break;
+	case KVM_REG_PPC_VTB:
+		*val = get_reg_val(id, vcpu->arch.vtb);
+		break;
+	case KVM_REG_PPC_CSIGR:
+		*val = get_reg_val(id, vcpu->arch.csigr);
+		break;
+	case KVM_REG_PPC_TACR:
+		*val = get_reg_val(id, vcpu->arch.tacr);
+		break;
+	case KVM_REG_PPC_TCSCR:
+		*val = get_reg_val(id, vcpu->arch.tcscr);
+		break;
+	case KVM_REG_PPC_PID:
+		*val = get_reg_val(id, vcpu->arch.pid);
+		break;
+	case KVM_REG_PPC_ACOP:
+		*val = get_reg_val(id, vcpu->arch.acop);
+		break;
+	case KVM_REG_PPC_WORT:
+		*val = get_reg_val(id, vcpu->arch.wort);
+		break;
 	case KVM_REG_PPC_VPA_ADDR:
 		spin_lock(&vcpu->arch.vpa_update_lock);
 		*val = get_reg_val(id, vcpu->arch.vpa.next_gpa);
@@ -882,7 +955,7 @@ static int kvmppc_set_one_reg_hv(struct kvm_vcpu *vcpu, u64 id,
 	case KVM_REG_PPC_UAMOR:
 		vcpu->arch.uamor = set_reg_val(id, *val);
 		break;
-	case KVM_REG_PPC_MMCR0 ... KVM_REG_PPC_MMCRA:
+	case KVM_REG_PPC_MMCR0 ... KVM_REG_PPC_MMCRS:
 		i = id - KVM_REG_PPC_MMCR0;
 		vcpu->arch.mmcr[i] = set_reg_val(id, *val);
 		break;
@@ -890,12 +963,88 @@ static int kvmppc_set_one_reg_hv(struct kvm_vcpu *vcpu, u64 id,
 		i = id - KVM_REG_PPC_PMC1;
 		vcpu->arch.pmc[i] = set_reg_val(id, *val);
 		break;
+	case KVM_REG_PPC_SPMC1 ... KVM_REG_PPC_SPMC2:
+		i = id - KVM_REG_PPC_SPMC1;
+		vcpu->arch.spmc[i] = set_reg_val(id, *val);
+		break;
 	case KVM_REG_PPC_SIAR:
 		vcpu->arch.siar = set_reg_val(id, *val);
 		break;
 	case KVM_REG_PPC_SDAR:
 		vcpu->arch.sdar = set_reg_val(id, *val);
 		break;
+	case KVM_REG_PPC_SIER:
+		vcpu->arch.sier = set_reg_val(id, *val);
+		break;
+	case KVM_REG_PPC_IAMR:
+		vcpu->arch.iamr = set_reg_val(id, *val);
+		break;
+	case KVM_REG_PPC_TFHAR:
+		vcpu->arch.tfhar = set_reg_val(id, *val);
+		break;
+	case KVM_REG_PPC_TFIAR:
+		vcpu->arch.tfiar = set_reg_val(id, *val);
+		break;
+	case KVM_REG_PPC_TEXASR:
+		vcpu->arch.texasr = set_reg_val(id, *val);
+		break;
+	case KVM_REG_PPC_FSCR:
+		vcpu->arch.fscr = set_reg_val(id, *val);
+		break;
+	case KVM_REG_PPC_PSPB:
+		vcpu->arch.pspb = set_reg_val(id, *val);
+		break;
+	case KVM_REG_PPC_EBBHR:
+		vcpu->arch.ebbhr = set_reg_val(id, *val);
+		break;
+	case KVM_REG_PPC_EBBRR:
+		vcpu->arch.ebbrr = set_reg_val(id, *val);
+		break;
+	case KVM_REG_PPC_BESCR:
+		vcpu->arch.bescr = set_reg_val(id, *val);
+		break;
+	case KVM_REG_PPC_TAR:
+		vcpu->arch.tar = set_reg_val(id, *val);
+		break;
+	case KVM_REG_PPC_DPDES:
+		vcpu->arch.vcore->dpdes = set_reg_val(id, *val);
+		break;
+	case KVM_REG_PPC_DAWR:
+		vcpu->arch.dawr = set_reg_val(id, *val);
+		break;
+	case KVM_REG_PPC_DAWRX:
+		vcpu->arch.dawrx = set_reg_val(id, *val) & ~DAWRX_HYP;
+		break;
+	case KVM_REG_PPC_CIABR:
+		vcpu->arch.ciabr = set_reg_val(id, *val);
+		/* Don't allow setting breakpoints in hypervisor code */
+		if ((vcpu->arch.ciabr & CIABR_PRIV) == CIABR_PRIV_HYPER)
+			vcpu->arch.ciabr &= ~CIABR_PRIV;	/* disable */
+		break;
+	case KVM_REG_PPC_IC:
+		vcpu->arch.ic = set_reg_val(id, *val);
+		break;
+	case KVM_REG_PPC_VTB:
+		vcpu->arch.vtb = set_reg_val(id, *val);
+		break;
+	case KVM_REG_PPC_CSIGR:
+		vcpu->arch.csigr = set_reg_val(id, *val);
+		break;
+	case KVM_REG_PPC_TACR:
+		vcpu->arch.tacr = set_reg_val(id, *val);
+		break;
+	case KVM_REG_PPC_TCSCR:
+		vcpu->arch.tcscr = set_reg_val(id, *val);
+		break;
+	case KVM_REG_PPC_PID:
+		vcpu->arch.pid = set_reg_val(id, *val);
+		break;
+	case KVM_REG_PPC_ACOP:
+		vcpu->arch.acop = set_reg_val(id, *val);
+		break;
+	case KVM_REG_PPC_WORT:
+		vcpu->arch.wort = set_reg_val(id, *val);
+		break;
 	case KVM_REG_PPC_VPA_ADDR:
 		addr = set_reg_val(id, *val);
 		r = -EINVAL;
diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
index 8bbe91bdb6da..691dd1ef555b 100644
--- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S
+++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
@@ -460,6 +460,13 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_201)
 	beq	38f
 	mtspr	SPRN_PCR, r7
 38:
+
+BEGIN_FTR_SECTION
+	/* DPDES is shared between threads */
+	ld	r8, VCORE_DPDES(r5)
+	mtspr	SPRN_DPDES, r8
+END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
+
 	li	r0,1
 	stb	r0,VCORE_IN_GUEST(r5)	/* signal secondaries to continue */
 	b	10f
@@ -659,6 +666,18 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_201)
 	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)
+	lwz	r7, VCPU_PMC + 24(r4)
+	lwz	r8, VCPU_PMC + 28(r4)
+	ld	r9, VCPU_MMCR + 32(r4)
+	mtspr	SPRN_MMCR2, r5
+	mtspr	SPRN_SIER, r6
+	mtspr	SPRN_SPMC1, r7
+	mtspr	SPRN_SPMC2, r8
+	mtspr	SPRN_MMCRS, r9
+END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
 	mtspr	SPRN_MMCR0, r3
 	isync
 
@@ -690,6 +709,61 @@ BEGIN_FTR_SECTION
 	mtspr	SPRN_DSCR, r5
 END_FTR_SECTION_IFSET(CPU_FTR_ARCH_206)
 
+BEGIN_FTR_SECTION
+	/* Skip next section on POWER7 or PPC970 */
+	b	8f
+END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_207S)
+	/* Turn on TM so we can access TFHAR/TFIAR/TEXASR */
+	mfmsr	r8
+	li	r0, 1
+	rldimi	r8, r0, MSR_TM_LG, 63-MSR_TM_LG
+	mtmsrd	r8
+
+	/* Load up POWER8-specific registers */
+	ld	r5, VCPU_IAMR(r4)
+	lwz	r6, VCPU_PSPB(r4)
+	ld	r7, VCPU_FSCR(r4)
+	mtspr	SPRN_IAMR, r5
+	mtspr	SPRN_PSPB, r6
+	mtspr	SPRN_FSCR, r7
+	ld	r5, VCPU_DAWR(r4)
+	ld	r6, VCPU_DAWRX(r4)
+	ld	r7, VCPU_CIABR(r4)
+	ld	r8, VCPU_TAR(r4)
+	mtspr	SPRN_DAWR, r5
+	mtspr	SPRN_DAWRX, r6
+	mtspr	SPRN_CIABR, r7
+	mtspr	SPRN_TAR, r8
+	ld	r5, VCPU_IC(r4)
+	ld	r6, VCPU_VTB(r4)
+	mtspr	SPRN_IC, r5
+	mtspr	SPRN_VTB, r6
+	ld	r5, VCPU_TFHAR(r4)
+	ld	r6, VCPU_TFIAR(r4)
+	ld	r7, VCPU_TEXASR(r4)
+	ld	r8, VCPU_EBBHR(r4)
+	mtspr	SPRN_TFHAR, r5
+	mtspr	SPRN_TFIAR, r6
+	mtspr	SPRN_TEXASR, r7
+	mtspr	SPRN_EBBHR, r8
+	ld	r5, VCPU_EBBRR(r4)
+	ld	r6, VCPU_BESCR(r4)
+	ld	r7, VCPU_CSIGR(r4)
+	ld	r8, VCPU_TACR(r4)
+	mtspr	SPRN_EBBRR, r5
+	mtspr	SPRN_BESCR, r6
+	mtspr	SPRN_CSIGR, r7
+	mtspr	SPRN_TACR, r8
+	ld	r5, VCPU_TCSCR(r4)
+	ld	r6, VCPU_ACOP(r4)
+	lwz	r7, VCPU_GUEST_PID(r4)
+	ld	r8, VCPU_WORT(r4)
+	mtspr	SPRN_TCSCR, r5
+	mtspr	SPRN_ACOP, r6
+	mtspr	SPRN_PID, r7
+	mtspr	SPRN_WORT, r8
+8:
+
 	/*
 	 * Set the decrementer to the guest decrementer.
 	 */
@@ -1081,6 +1155,54 @@ END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_201)
 	add	r5,r5,r6
 	std	r5,VCPU_DEC_EXPIRES(r9)
 
+BEGIN_FTR_SECTION
+	b	8f
+END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_207S)
+	/* Turn on TM so we can access TFHAR/TFIAR/TEXASR */
+	mfmsr	r8
+	li	r0, 1
+	rldimi	r8, r0, MSR_TM_LG, 63-MSR_TM_LG
+	mtmsrd	r8
+
+	/* Save POWER8-specific registers */
+	mfspr	r5, SPRN_IAMR
+	mfspr	r6, SPRN_PSPB
+	mfspr	r7, SPRN_FSCR
+	std	r5, VCPU_IAMR(r9)
+	stw	r6, VCPU_PSPB(r9)
+	std	r7, VCPU_FSCR(r9)
+	mfspr	r5, SPRN_IC
+	mfspr	r6, SPRN_VTB
+	mfspr	r7, SPRN_TAR
+	std	r5, VCPU_IC(r9)
+	std	r6, VCPU_VTB(r9)
+	std	r7, VCPU_TAR(r9)
+	mfspr	r5, SPRN_TFHAR
+	mfspr	r6, SPRN_TFIAR
+	mfspr	r7, SPRN_TEXASR
+	mfspr	r8, SPRN_EBBHR
+	std	r5, VCPU_TFHAR(r9)
+	std	r6, VCPU_TFIAR(r9)
+	std	r7, VCPU_TEXASR(r9)
+	std	r8, VCPU_EBBHR(r9)
+	mfspr	r5, SPRN_EBBRR
+	mfspr	r6, SPRN_BESCR
+	mfspr	r7, SPRN_CSIGR
+	mfspr	r8, SPRN_TACR
+	std	r5, VCPU_EBBRR(r9)
+	std	r6, VCPU_BESCR(r9)
+	std	r7, VCPU_CSIGR(r9)
+	std	r8, VCPU_TACR(r9)
+	mfspr	r5, SPRN_TCSCR
+	mfspr	r6, SPRN_ACOP
+	mfspr	r7, SPRN_PID
+	mfspr	r8, SPRN_WORT
+	std	r5, VCPU_TCSCR(r9)
+	std	r6, VCPU_ACOP(r9)
+	stw	r7, VCPU_GUEST_PID(r9)
+	std	r8, VCPU_WORT(r9)
+8:
+
 	/* Save and reset AMR and UAMOR before turning on the MMU */
 BEGIN_FTR_SECTION
 	mfspr	r5,SPRN_AMR
@@ -1190,6 +1312,20 @@ BEGIN_FTR_SECTION
 	stw	r10, VCPU_PMC + 24(r9)
 	stw	r11, VCPU_PMC + 28(r9)
 END_FTR_SECTION_IFSET(CPU_FTR_ARCH_201)
+BEGIN_FTR_SECTION
+	mfspr	r4, SPRN_MMCR2
+	mfspr	r5, SPRN_SIER
+	mfspr	r6, SPRN_SPMC1
+	mfspr	r7, SPRN_SPMC2
+	mfspr	r8, SPRN_MMCRS
+	std	r4, VCPU_MMCR + 24(r9)
+	std	r5, VCPU_SIER(r9)
+	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_IFSET(CPU_FTR_ARCH_207S)
 22:
 	/* Clear out SLB */
 	li	r5,0
@@ -1290,6 +1426,15 @@ secondary_too_late:
 	mtspr	SPRN_LPID,r7
 	isync
 
+BEGIN_FTR_SECTION
+	/* DPDES is shared between threads */
+	mfspr	r7, SPRN_DPDES
+	std	r7, VCORE_DPDES(r5)
+	/* clear DPDES so we don't get guest doorbells in the host */
+	li	r8, 0
+	mtspr	SPRN_DPDES, r8
+END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
+
 	/* Subtract timebase offset from timebase */
 	ld	r8,VCORE_TB_OFFSET(r5)
 	cmpdi	r8,0