Merge tag 'kvm-ppc-next-4.18-2' of git://git.kernel.org/pub/scm/linux/kernel/git/paulus/powerpc into HEAD

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

@@ -134,7 +134,13 @@ unsigned long prepare_ftrace_return(unsigned long parent, unsigned long ip);
 void pnv_power9_force_smt4_catch(void);
 void pnv_power9_force_smt4_release(void);
 
+/* Transaction memory related */
 void tm_enable(void);
 void tm_disable(void);
 void tm_abort(uint8_t cause);
+
+struct kvm_vcpu;
+void _kvmppc_restore_tm_pr(struct kvm_vcpu *vcpu, u64 guest_msr);
+void _kvmppc_save_tm_pr(struct kvm_vcpu *vcpu, u64 guest_msr);
+
 #endif /* _ASM_POWERPC_ASM_PROTOTYPES_H */

arch/powerpc/include/asm/kvm_book3s.h

@@ -104,6 +104,7 @@ struct kvmppc_vcore {
 	ulong vtb;		/* virtual timebase */
 	ulong conferring_threads;
 	unsigned int halt_poll_ns;
+	atomic_t online_count;
 };
 
 struct kvmppc_vcpu_book3s {
@@ -209,6 +210,7 @@ extern void kvmppc_book3s_queue_irqprio(struct kvm_vcpu *vcpu, unsigned int vec)
 extern void kvmppc_book3s_dequeue_irqprio(struct kvm_vcpu *vcpu,
 					  unsigned int vec);
 extern void kvmppc_inject_interrupt(struct kvm_vcpu *vcpu, int vec, u64 flags);
+extern void kvmppc_trigger_fac_interrupt(struct kvm_vcpu *vcpu, ulong fac);
 extern void kvmppc_set_bat(struct kvm_vcpu *vcpu, struct kvmppc_bat *bat,
 			   bool upper, u32 val);
 extern void kvmppc_giveup_ext(struct kvm_vcpu *vcpu, ulong msr);
@@ -256,6 +258,21 @@ extern int kvmppc_hcall_impl_pr(unsigned long cmd);
 extern int kvmppc_hcall_impl_hv_realmode(unsigned long cmd);
 extern void kvmppc_copy_to_svcpu(struct kvm_vcpu *vcpu);
 extern void kvmppc_copy_from_svcpu(struct kvm_vcpu *vcpu);
+
+#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+void kvmppc_save_tm_pr(struct kvm_vcpu *vcpu);
+void kvmppc_restore_tm_pr(struct kvm_vcpu *vcpu);
+void kvmppc_save_tm_sprs(struct kvm_vcpu *vcpu);
+void kvmppc_restore_tm_sprs(struct kvm_vcpu *vcpu);
+#else
+static inline void kvmppc_save_tm_pr(struct kvm_vcpu *vcpu) {}
+static inline void kvmppc_restore_tm_pr(struct kvm_vcpu *vcpu) {}
+static inline void kvmppc_save_tm_sprs(struct kvm_vcpu *vcpu) {}
+static inline void kvmppc_restore_tm_sprs(struct kvm_vcpu *vcpu) {}
+#endif
+
+void kvmppc_giveup_fac(struct kvm_vcpu *vcpu, ulong fac);
+
 extern int kvm_irq_bypass;
 
 static inline struct kvmppc_vcpu_book3s *to_book3s(struct kvm_vcpu *vcpu)
@@ -274,12 +291,12 @@ static inline struct kvmppc_vcpu_book3s *to_book3s(struct kvm_vcpu *vcpu)
 
 static inline void kvmppc_set_gpr(struct kvm_vcpu *vcpu, int num, ulong val)
 {
-	vcpu->arch.gpr[num] = val;
+	vcpu->arch.regs.gpr[num] = val;
 }
 
 static inline ulong kvmppc_get_gpr(struct kvm_vcpu *vcpu, int num)
 {
-	return vcpu->arch.gpr[num];
+	return vcpu->arch.regs.gpr[num];
 }
 
 static inline void kvmppc_set_cr(struct kvm_vcpu *vcpu, u32 val)
@@ -294,42 +311,42 @@ static inline u32 kvmppc_get_cr(struct kvm_vcpu *vcpu)
 
 static inline void kvmppc_set_xer(struct kvm_vcpu *vcpu, ulong val)
 {
-	vcpu->arch.xer = val;
+	vcpu->arch.regs.xer = val;
 }
 
 static inline ulong kvmppc_get_xer(struct kvm_vcpu *vcpu)
 {
-	return vcpu->arch.xer;
+	return vcpu->arch.regs.xer;
 }
 
 static inline void kvmppc_set_ctr(struct kvm_vcpu *vcpu, ulong val)
 {
-	vcpu->arch.ctr = val;
+	vcpu->arch.regs.ctr = val;
 }
 
 static inline ulong kvmppc_get_ctr(struct kvm_vcpu *vcpu)
 {
-	return vcpu->arch.ctr;
+	return vcpu->arch.regs.ctr;
 }
 
 static inline void kvmppc_set_lr(struct kvm_vcpu *vcpu, ulong val)
 {
-	vcpu->arch.lr = val;
+	vcpu->arch.regs.link = val;
 }
 
 static inline ulong kvmppc_get_lr(struct kvm_vcpu *vcpu)
 {
-	return vcpu->arch.lr;
+	return vcpu->arch.regs.link;
 }
 
 static inline void kvmppc_set_pc(struct kvm_vcpu *vcpu, ulong val)
 {
-	vcpu->arch.pc = val;
+	vcpu->arch.regs.nip = val;
 }
 
 static inline ulong kvmppc_get_pc(struct kvm_vcpu *vcpu)
 {
-	return vcpu->arch.pc;
+	return vcpu->arch.regs.nip;
 }
 
 static inline u64 kvmppc_get_msr(struct kvm_vcpu *vcpu);

arch/powerpc/include/asm/kvm_book3s_64.h

@@ -483,15 +483,15 @@ static inline u64 sanitize_msr(u64 msr)
 static inline void copy_from_checkpoint(struct kvm_vcpu *vcpu)
 {
 	vcpu->arch.cr  = vcpu->arch.cr_tm;
-	vcpu->arch.xer = vcpu->arch.xer_tm;
-	vcpu->arch.lr  = vcpu->arch.lr_tm;
-	vcpu->arch.ctr = vcpu->arch.ctr_tm;
+	vcpu->arch.regs.xer = vcpu->arch.xer_tm;
+	vcpu->arch.regs.link  = vcpu->arch.lr_tm;
+	vcpu->arch.regs.ctr = vcpu->arch.ctr_tm;
 	vcpu->arch.amr = vcpu->arch.amr_tm;
 	vcpu->arch.ppr = vcpu->arch.ppr_tm;
 	vcpu->arch.dscr = vcpu->arch.dscr_tm;
 	vcpu->arch.tar = vcpu->arch.tar_tm;
-	memcpy(vcpu->arch.gpr, vcpu->arch.gpr_tm,
-	       sizeof(vcpu->arch.gpr));
+	memcpy(vcpu->arch.regs.gpr, vcpu->arch.gpr_tm,
+	       sizeof(vcpu->arch.regs.gpr));
 	vcpu->arch.fp  = vcpu->arch.fp_tm;
 	vcpu->arch.vr  = vcpu->arch.vr_tm;
 	vcpu->arch.vrsave = vcpu->arch.vrsave_tm;
@@ -500,15 +500,15 @@ static inline void copy_from_checkpoint(struct kvm_vcpu *vcpu)
 static inline void copy_to_checkpoint(struct kvm_vcpu *vcpu)
 {
 	vcpu->arch.cr_tm  = vcpu->arch.cr;
-	vcpu->arch.xer_tm = vcpu->arch.xer;
-	vcpu->arch.lr_tm  = vcpu->arch.lr;
-	vcpu->arch.ctr_tm = vcpu->arch.ctr;
+	vcpu->arch.xer_tm = vcpu->arch.regs.xer;
+	vcpu->arch.lr_tm  = vcpu->arch.regs.link;
+	vcpu->arch.ctr_tm = vcpu->arch.regs.ctr;
 	vcpu->arch.amr_tm = vcpu->arch.amr;
 	vcpu->arch.ppr_tm = vcpu->arch.ppr;
 	vcpu->arch.dscr_tm = vcpu->arch.dscr;
 	vcpu->arch.tar_tm = vcpu->arch.tar;
-	memcpy(vcpu->arch.gpr_tm, vcpu->arch.gpr,
-	       sizeof(vcpu->arch.gpr));
+	memcpy(vcpu->arch.gpr_tm, vcpu->arch.regs.gpr,
+	       sizeof(vcpu->arch.regs.gpr));
 	vcpu->arch.fp_tm  = vcpu->arch.fp;
 	vcpu->arch.vr_tm  = vcpu->arch.vr;
 	vcpu->arch.vrsave_tm = vcpu->arch.vrsave;

arch/powerpc/include/asm/kvm_booke.h

@@ -36,12 +36,12 @@
 
 static inline void kvmppc_set_gpr(struct kvm_vcpu *vcpu, int num, ulong val)
 {
-	vcpu->arch.gpr[num] = val;
+	vcpu->arch.regs.gpr[num] = val;
 }
 
 static inline ulong kvmppc_get_gpr(struct kvm_vcpu *vcpu, int num)
 {
-	return vcpu->arch.gpr[num];
+	return vcpu->arch.regs.gpr[num];
 }
 
 static inline void kvmppc_set_cr(struct kvm_vcpu *vcpu, u32 val)
@@ -56,12 +56,12 @@ static inline u32 kvmppc_get_cr(struct kvm_vcpu *vcpu)
 
 static inline void kvmppc_set_xer(struct kvm_vcpu *vcpu, ulong val)
 {
-	vcpu->arch.xer = val;
+	vcpu->arch.regs.xer = val;
 }
 
 static inline ulong kvmppc_get_xer(struct kvm_vcpu *vcpu)
 {
-	return vcpu->arch.xer;
+	return vcpu->arch.regs.xer;
 }
 
 static inline bool kvmppc_need_byteswap(struct kvm_vcpu *vcpu)
@@ -72,32 +72,32 @@ static inline bool kvmppc_need_byteswap(struct kvm_vcpu *vcpu)
 
 static inline void kvmppc_set_ctr(struct kvm_vcpu *vcpu, ulong val)
 {
-	vcpu->arch.ctr = val;
+	vcpu->arch.regs.ctr = val;
 }
 
 static inline ulong kvmppc_get_ctr(struct kvm_vcpu *vcpu)
 {
-	return vcpu->arch.ctr;
+	return vcpu->arch.regs.ctr;
 }
 
 static inline void kvmppc_set_lr(struct kvm_vcpu *vcpu, ulong val)
 {
-	vcpu->arch.lr = val;
+	vcpu->arch.regs.link = val;
 }
 
 static inline ulong kvmppc_get_lr(struct kvm_vcpu *vcpu)
 {
-	return vcpu->arch.lr;
+	return vcpu->arch.regs.link;
 }
 
 static inline void kvmppc_set_pc(struct kvm_vcpu *vcpu, ulong val)
 {
-	vcpu->arch.pc = val;
+	vcpu->arch.regs.nip = val;
 }
 
 static inline ulong kvmppc_get_pc(struct kvm_vcpu *vcpu)
 {
-	return vcpu->arch.pc;
+	return vcpu->arch.regs.nip;
 }
 
 static inline ulong kvmppc_get_fault_dar(struct kvm_vcpu *vcpu)

arch/powerpc/include/asm/kvm_host.h

@@ -269,7 +269,6 @@ struct kvm_arch {
 	unsigned long host_lpcr;
 	unsigned long sdr1;
 	unsigned long host_sdr1;
-	int tlbie_lock;
 	unsigned long lpcr;
 	unsigned long vrma_slb_v;
 	int mmu_ready;
@@ -454,6 +453,12 @@ struct mmio_hpte_cache {
 #define KVMPPC_VSX_COPY_WORD		1
 #define KVMPPC_VSX_COPY_DWORD		2
 #define KVMPPC_VSX_COPY_DWORD_LOAD_DUMP	3
+#define KVMPPC_VSX_COPY_WORD_LOAD_DUMP	4
+
+#define KVMPPC_VMX_COPY_BYTE		8
+#define KVMPPC_VMX_COPY_HWORD		9
+#define KVMPPC_VMX_COPY_WORD		10
+#define KVMPPC_VMX_COPY_DWORD		11
 
 struct openpic;
 
@@ -486,7 +491,7 @@ struct kvm_vcpu_arch {
 	struct kvmppc_book3s_shadow_vcpu *shadow_vcpu;
 #endif
 
-	ulong gpr[32];
+	struct pt_regs regs;
 
 	struct thread_fp_state fp;
 
@@ -521,14 +526,10 @@ struct kvm_vcpu_arch {
 	u32 qpr[32];
 #endif
 
-	ulong pc;
-	ulong ctr;
-	ulong lr;
 #ifdef CONFIG_PPC_BOOK3S
 	ulong tar;
 #endif
 
-	ulong xer;
 	u32 cr;
 
 #ifdef CONFIG_PPC_BOOK3S
@@ -626,7 +627,6 @@ struct kvm_vcpu_arch {
 
 	struct thread_vr_state vr_tm;
 	u32 vrsave_tm; /* also USPRG0 */
-
 #endif
 
 #ifdef CONFIG_KVM_EXIT_TIMING
@@ -681,16 +681,17 @@ struct kvm_vcpu_arch {
 	 * Number of simulations for vsx.
 	 * If we use 2*8bytes to simulate 1*16bytes,
 	 * then the number should be 2 and
-	 * mmio_vsx_copy_type=KVMPPC_VSX_COPY_DWORD.
+	 * mmio_copy_type=KVMPPC_VSX_COPY_DWORD.
 	 * If we use 4*4bytes to simulate 1*16bytes,
 	 * the number should be 4 and
 	 * mmio_vsx_copy_type=KVMPPC_VSX_COPY_WORD.
 	 */
 	u8 mmio_vsx_copy_nums;
 	u8 mmio_vsx_offset;
-	u8 mmio_vsx_copy_type;
 	u8 mmio_vsx_tx_sx_enabled;
 	u8 mmio_vmx_copy_nums;
+	u8 mmio_vmx_offset;
+	u8 mmio_copy_type;
 	u8 osi_needed;
 	u8 osi_enabled;
 	u8 papr_enabled;
@@ -772,6 +773,8 @@ struct kvm_vcpu_arch {
 	u64 busy_preempt;
 
 	u32 emul_inst;
+
+	u32 online;
 #endif
 
 #ifdef CONFIG_KVM_BOOK3S_HV_EXIT_TIMING

arch/powerpc/include/asm/kvm_ppc.h

@@ -52,7 +52,7 @@ enum emulation_result {
 	EMULATE_EXIT_USER,    /* emulation requires exit to user-space */
 };
 
-enum instruction_type {
+enum instruction_fetch_type {
 	INST_GENERIC,
 	INST_SC,		/* system call */
 };
@@ -81,10 +81,10 @@ extern int kvmppc_handle_loads(struct kvm_run *run, struct kvm_vcpu *vcpu,
 extern int kvmppc_handle_vsx_load(struct kvm_run *run, struct kvm_vcpu *vcpu,
 				unsigned int rt, unsigned int bytes,
 			int is_default_endian, int mmio_sign_extend);
-extern int kvmppc_handle_load128_by2x64(struct kvm_run *run,
-		struct kvm_vcpu *vcpu, unsigned int rt, int is_default_endian);
-extern int kvmppc_handle_store128_by2x64(struct kvm_run *run,
-		struct kvm_vcpu *vcpu, unsigned int rs, int is_default_endian);
+extern int kvmppc_handle_vmx_load(struct kvm_run *run, struct kvm_vcpu *vcpu,
+		unsigned int rt, unsigned int bytes, int is_default_endian);
+extern int kvmppc_handle_vmx_store(struct kvm_run *run, struct kvm_vcpu *vcpu,
+		unsigned int rs, unsigned int bytes, int is_default_endian);
 extern int kvmppc_handle_store(struct kvm_run *run, struct kvm_vcpu *vcpu,
 			       u64 val, unsigned int bytes,
 			       int is_default_endian);
@@ -93,7 +93,7 @@ extern int kvmppc_handle_vsx_store(struct kvm_run *run, struct kvm_vcpu *vcpu,
 				int is_default_endian);
 
 extern int kvmppc_load_last_inst(struct kvm_vcpu *vcpu,
-				 enum instruction_type type, u32 *inst);
+				 enum instruction_fetch_type type, u32 *inst);
 
 extern int kvmppc_ld(struct kvm_vcpu *vcpu, ulong *eaddr, int size, void *ptr,
 		     bool data);
@@ -265,6 +265,8 @@ union kvmppc_one_reg {
 	vector128 vval;
 	u64	vsxval[2];
 	u32	vsx32val[4];
+	u16	vsx16val[8];
+	u8	vsx8val[16];
 	struct {
 		u64	addr;
 		u64	length;
@@ -324,13 +326,14 @@ struct kvmppc_ops {
 	int (*get_rmmu_info)(struct kvm *kvm, struct kvm_ppc_rmmu_info *info);
 	int (*set_smt_mode)(struct kvm *kvm, unsigned long mode,
 			    unsigned long flags);
+	void (*giveup_ext)(struct kvm_vcpu *vcpu, ulong msr);
 };
 
 extern struct kvmppc_ops *kvmppc_hv_ops;
 extern struct kvmppc_ops *kvmppc_pr_ops;
 
 static inline int kvmppc_get_last_inst(struct kvm_vcpu *vcpu,
-					enum instruction_type type, u32 *inst)
+				enum instruction_fetch_type type, u32 *inst)
 {
 	int ret = EMULATE_DONE;
 	u32 fetched_inst;

arch/powerpc/include/asm/reg.h

@@ -385,6 +385,7 @@
 #define SPRN_PSSCR	0x357	/* Processor Stop Status and Control Register (ISA 3.0) */
 #define SPRN_PSSCR_PR	0x337	/* PSSCR ISA 3.0, privileged mode access */
 #define SPRN_PMCR	0x374	/* Power Management Control Register */
+#define SPRN_RWMR	0x375	/* Region-Weighting Mode Register */
 
 /* HFSCR and FSCR bit numbers are the same */
 #define FSCR_SCV_LG	12	/* Enable System Call Vectored */

arch/powerpc/include/uapi/asm/kvm.h

@@ -633,6 +633,7 @@ struct kvm_ppc_cpu_char {
 #define KVM_REG_PPC_PSSCR	(KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xbd)
 
 #define KVM_REG_PPC_DEC_EXPIRY	(KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xbe)
+#define KVM_REG_PPC_ONLINE	(KVM_REG_PPC | KVM_REG_SIZE_U32 | 0xbf)
 
 /* Transactional Memory checkpointed state:
  * This is all GPRs, all VSX regs and a subset of SPRs

arch/powerpc/kernel/asm-offsets.c

@@ -426,20 +426,20 @@ int main(void)
 	OFFSET(VCPU_HOST_STACK, kvm_vcpu, arch.host_stack);
 	OFFSET(VCPU_HOST_PID, kvm_vcpu, arch.host_pid);
 	OFFSET(VCPU_GUEST_PID, kvm_vcpu, arch.pid);
-	OFFSET(VCPU_GPRS, kvm_vcpu, arch.gpr);
+	OFFSET(VCPU_GPRS, kvm_vcpu, arch.regs.gpr);
 	OFFSET(VCPU_VRSAVE, kvm_vcpu, arch.vrsave);
 	OFFSET(VCPU_FPRS, kvm_vcpu, arch.fp.fpr);
 #ifdef CONFIG_ALTIVEC
 	OFFSET(VCPU_VRS, kvm_vcpu, arch.vr.vr);
 #endif
-	OFFSET(VCPU_XER, kvm_vcpu, arch.xer);
-	OFFSET(VCPU_CTR, kvm_vcpu, arch.ctr);
-	OFFSET(VCPU_LR, kvm_vcpu, arch.lr);
+	OFFSET(VCPU_XER, kvm_vcpu, arch.regs.xer);
+	OFFSET(VCPU_CTR, kvm_vcpu, arch.regs.ctr);
+	OFFSET(VCPU_LR, kvm_vcpu, arch.regs.link);
 #ifdef CONFIG_PPC_BOOK3S
 	OFFSET(VCPU_TAR, kvm_vcpu, arch.tar);
 #endif
 	OFFSET(VCPU_CR, kvm_vcpu, arch.cr);
-	OFFSET(VCPU_PC, kvm_vcpu, arch.pc);
+	OFFSET(VCPU_PC, kvm_vcpu, arch.regs.nip);
 #ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
 	OFFSET(VCPU_MSR, kvm_vcpu, arch.shregs.msr);
 	OFFSET(VCPU_SRR0, kvm_vcpu, arch.shregs.srr0);
@@ -696,10 +696,10 @@ int main(void)
 
 #else /* CONFIG_PPC_BOOK3S */
 	OFFSET(VCPU_CR, kvm_vcpu, arch.cr);
-	OFFSET(VCPU_XER, kvm_vcpu, arch.xer);
-	OFFSET(VCPU_LR, kvm_vcpu, arch.lr);
-	OFFSET(VCPU_CTR, kvm_vcpu, arch.ctr);
-	OFFSET(VCPU_PC, kvm_vcpu, arch.pc);
+	OFFSET(VCPU_XER, kvm_vcpu, arch.regs.xer);
+	OFFSET(VCPU_LR, kvm_vcpu, arch.regs.link);
+	OFFSET(VCPU_CTR, kvm_vcpu, arch.regs.ctr);
+	OFFSET(VCPU_PC, kvm_vcpu, arch.regs.nip);
 	OFFSET(VCPU_SPRG9, kvm_vcpu, arch.sprg9);
 	OFFSET(VCPU_LAST_INST, kvm_vcpu, arch.last_inst);
 	OFFSET(VCPU_FAULT_DEAR, kvm_vcpu, arch.fault_dear);

arch/powerpc/kvm/Makefile

@@ -63,6 +63,9 @@ kvm-pr-y := \
 	book3s_64_mmu.o \
 	book3s_32_mmu.o
 
+kvm-book3s_64-builtin-objs-$(CONFIG_KVM_BOOK3S_64_HANDLER) += \
+	tm.o
+
 ifdef CONFIG_KVM_BOOK3S_PR_POSSIBLE
 kvm-book3s_64-builtin-objs-$(CONFIG_KVM_BOOK3S_64_HANDLER) += \
 	book3s_rmhandlers.o

arch/powerpc/kvm/book3s.c

@@ -134,7 +134,7 @@ void kvmppc_inject_interrupt(struct kvm_vcpu *vcpu, int vec, u64 flags)
 {
 	kvmppc_unfixup_split_real(vcpu);
 	kvmppc_set_srr0(vcpu, kvmppc_get_pc(vcpu));
-	kvmppc_set_srr1(vcpu, kvmppc_get_msr(vcpu) | flags);
+	kvmppc_set_srr1(vcpu, (kvmppc_get_msr(vcpu) & ~0x783f0000ul) | flags);
 	kvmppc_set_pc(vcpu, kvmppc_interrupt_offset(vcpu) + vec);
 	vcpu->arch.mmu.reset_msr(vcpu);
 }
@@ -256,18 +256,15 @@ void kvmppc_core_queue_data_storage(struct kvm_vcpu *vcpu, ulong dar,
 {
 	kvmppc_set_dar(vcpu, dar);
 	kvmppc_set_dsisr(vcpu, flags);
-	kvmppc_book3s_queue_irqprio(vcpu, BOOK3S_INTERRUPT_DATA_STORAGE);
+	kvmppc_inject_interrupt(vcpu, BOOK3S_INTERRUPT_DATA_STORAGE, 0);
 }
-EXPORT_SYMBOL_GPL(kvmppc_core_queue_data_storage);	/* used by kvm_hv */
+EXPORT_SYMBOL_GPL(kvmppc_core_queue_data_storage);
 
 void kvmppc_core_queue_inst_storage(struct kvm_vcpu *vcpu, ulong flags)
 {
-	u64 msr = kvmppc_get_msr(vcpu);
-	msr &= ~(SRR1_ISI_NOPT | SRR1_ISI_N_OR_G | SRR1_ISI_PROT);
-	msr |= flags & (SRR1_ISI_NOPT | SRR1_ISI_N_OR_G | SRR1_ISI_PROT);
-	kvmppc_set_msr_fast(vcpu, msr);
-	kvmppc_book3s_queue_irqprio(vcpu, BOOK3S_INTERRUPT_INST_STORAGE);
+	kvmppc_inject_interrupt(vcpu, BOOK3S_INTERRUPT_INST_STORAGE, flags);
 }
+EXPORT_SYMBOL_GPL(kvmppc_core_queue_inst_storage);
 
 static int kvmppc_book3s_irqprio_deliver(struct kvm_vcpu *vcpu,
 					 unsigned int priority)
@@ -450,8 +447,8 @@ int kvmppc_xlate(struct kvm_vcpu *vcpu, ulong eaddr, enum xlate_instdata xlid,
 	return r;
 }
 
-int kvmppc_load_last_inst(struct kvm_vcpu *vcpu, enum instruction_type type,
-					 u32 *inst)
+int kvmppc_load_last_inst(struct kvm_vcpu *vcpu,
+		enum instruction_fetch_type type, u32 *inst)
 {
 	ulong pc = kvmppc_get_pc(vcpu);
 	int r;
@@ -509,8 +506,6 @@ int kvm_arch_vcpu_ioctl_get_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs)
 {
 	int i;
 
-	vcpu_load(vcpu);
-
 	regs->pc = kvmppc_get_pc(vcpu);
 	regs->cr = kvmppc_get_cr(vcpu);
 	regs->ctr = kvmppc_get_ctr(vcpu);
@@ -532,7 +527,6 @@ int kvm_arch_vcpu_ioctl_get_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs)
 	for (i = 0; i < ARRAY_SIZE(regs->gpr); i++)
 		regs->gpr[i] = kvmppc_get_gpr(vcpu, i);
 
-	vcpu_put(vcpu);
 	return 0;
 }
 
@@ -540,8 +534,6 @@ int kvm_arch_vcpu_ioctl_set_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs)
 {
 	int i;
 
-	vcpu_load(vcpu);
-
 	kvmppc_set_pc(vcpu, regs->pc);
 	kvmppc_set_cr(vcpu, regs->cr);
 	kvmppc_set_ctr(vcpu, regs->ctr);
@@ -562,7 +554,6 @@ int kvm_arch_vcpu_ioctl_set_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs)
 	for (i = 0; i < ARRAY_SIZE(regs->gpr); i++)
 		kvmppc_set_gpr(vcpu, i, regs->gpr[i]);
 
-	vcpu_put(vcpu);
 	return 0;
 }
 

arch/powerpc/kvm/book3s.h

@@ -31,4 +31,10 @@ extern int kvmppc_core_emulate_mfspr_pr(struct kvm_vcpu *vcpu,
 extern int kvmppc_book3s_init_pr(void);
 extern void kvmppc_book3s_exit_pr(void);
 
+#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+extern void kvmppc_emulate_tabort(struct kvm_vcpu *vcpu, int ra_val);
+#else
+static inline void kvmppc_emulate_tabort(struct kvm_vcpu *vcpu, int ra_val) {}
+#endif
+
 #endif

arch/powerpc/kvm/book3s_32_mmu.c

@@ -52,7 +52,7 @@
 static inline bool check_debug_ip(struct kvm_vcpu *vcpu)
 {
 #ifdef DEBUG_MMU_PTE_IP
-	return vcpu->arch.pc == DEBUG_MMU_PTE_IP;
+	return vcpu->arch.regs.nip == DEBUG_MMU_PTE_IP;
 #else
 	return true;
 #endif

arch/powerpc/kvm/book3s_64_mmu.c

@@ -38,7 +38,16 @@
 
 static void kvmppc_mmu_book3s_64_reset_msr(struct kvm_vcpu *vcpu)
 {
-	kvmppc_set_msr(vcpu, vcpu->arch.intr_msr);
+	unsigned long msr = vcpu->arch.intr_msr;
+	unsigned long cur_msr = kvmppc_get_msr(vcpu);
+
+	/* If transactional, change to suspend mode on IRQ delivery */
+	if (MSR_TM_TRANSACTIONAL(cur_msr))
+		msr |= MSR_TS_S;
+	else
+		msr |= cur_msr & MSR_TS_MASK;
+
+	kvmppc_set_msr(vcpu, msr);
 }
 
 static struct kvmppc_slb *kvmppc_mmu_book3s_64_find_slbe(

arch/powerpc/kvm/book3s_64_mmu_hv.c

@@ -272,6 +272,9 @@ int kvmppc_mmu_hv_init(void)
 	if (!cpu_has_feature(CPU_FTR_HVMODE))
 		return -EINVAL;
 
+	if (!mmu_has_feature(MMU_FTR_LOCKLESS_TLBIE))
+		return -EINVAL;
+
 	/* POWER7 has 10-bit LPIDs (12-bit in POWER8) */
 	host_lpid = mfspr(SPRN_LPID);
 	rsvd_lpid = LPID_RSVD;

arch/powerpc/kvm/book3s_64_mmu_radix.c

@@ -139,44 +139,24 @@ int kvmppc_mmu_radix_xlate(struct kvm_vcpu *vcpu, gva_t eaddr,
 	return 0;
 }
 
-#ifdef CONFIG_PPC_64K_PAGES
-#define MMU_BASE_PSIZE	MMU_PAGE_64K
-#else
-#define MMU_BASE_PSIZE	MMU_PAGE_4K
-#endif
-
 static void kvmppc_radix_tlbie_page(struct kvm *kvm, unsigned long addr,
 				    unsigned int pshift)
 {
-	int psize = MMU_BASE_PSIZE;
-
-	if (pshift >= PUD_SHIFT)
-		psize = MMU_PAGE_1G;
-	else if (pshift >= PMD_SHIFT)
-		psize = MMU_PAGE_2M;
-	addr &= ~0xfffUL;
-	addr |= mmu_psize_defs[psize].ap << 5;
-	asm volatile("ptesync": : :"memory");
-	asm volatile(PPC_TLBIE_5(%0, %1, 0, 0, 1)
-		     : : "r" (addr), "r" (kvm->arch.lpid) : "memory");
-	if (cpu_has_feature(CPU_FTR_P9_TLBIE_BUG))
-		asm volatile(PPC_TLBIE_5(%0, %1, 0, 0, 1)
-			     : : "r" (addr), "r" (kvm->arch.lpid) : "memory");
-	asm volatile("eieio ; tlbsync ; ptesync": : :"memory");
+	unsigned long psize = PAGE_SIZE;
+
+	if (pshift)
+		psize = 1UL << pshift;
+
+	addr &= ~(psize - 1);
+	radix__flush_tlb_lpid_page(kvm->arch.lpid, addr, psize);
 }
 
-static void kvmppc_radix_flush_pwc(struct kvm *kvm, unsigned long addr)
+static void kvmppc_radix_flush_pwc(struct kvm *kvm)
 {
-	unsigned long rb = 0x2 << PPC_BITLSHIFT(53); /* IS = 2 */
-
-	asm volatile("ptesync": : :"memory");
-	/* RIC=1 PRS=0 R=1 IS=2 */
-	asm volatile(PPC_TLBIE_5(%0, %1, 1, 0, 1)
-		     : : "r" (rb), "r" (kvm->arch.lpid) : "memory");
-	asm volatile("eieio ; tlbsync ; ptesync": : :"memory");
+	radix__flush_pwc_lpid(kvm->arch.lpid);
 }
 
-unsigned long kvmppc_radix_update_pte(struct kvm *kvm, pte_t *ptep,
+static unsigned long kvmppc_radix_update_pte(struct kvm *kvm, pte_t *ptep,
 				      unsigned long clr, unsigned long set,
 				      unsigned long addr, unsigned int shift)
 {
@@ -228,6 +208,167 @@ static void kvmppc_pmd_free(pmd_t *pmdp)
 	kmem_cache_free(kvm_pmd_cache, pmdp);
 }
 
+static void kvmppc_unmap_pte(struct kvm *kvm, pte_t *pte,
+			     unsigned long gpa, unsigned int shift)
+
+{
+	unsigned long page_size = 1ul << shift;
+	unsigned long old;
+
+	old = kvmppc_radix_update_pte(kvm, pte, ~0UL, 0, gpa, shift);
+	kvmppc_radix_tlbie_page(kvm, gpa, shift);
+	if (old & _PAGE_DIRTY) {
+		unsigned long gfn = gpa >> PAGE_SHIFT;
+		struct kvm_memory_slot *memslot;
+
+		memslot = gfn_to_memslot(kvm, gfn);
+		if (memslot && memslot->dirty_bitmap)
+			kvmppc_update_dirty_map(memslot, gfn, page_size);
+	}
+}
+
+/*
+ * kvmppc_free_p?d are used to free existing page tables, and recursively
+ * descend and clear and free children.
+ * Callers are responsible for flushing the PWC.
+ *
+ * When page tables are being unmapped/freed as part of page fault path
+ * (full == false), ptes are not expected. There is code to unmap them
+ * and emit a warning if encountered, but there may already be data
+ * corruption due to the unexpected mappings.
+ */
+static void kvmppc_unmap_free_pte(struct kvm *kvm, pte_t *pte, bool full)
+{
+	if (full) {
+		memset(pte, 0, sizeof(long) << PTE_INDEX_SIZE);
+	} else {
+		pte_t *p = pte;
+		unsigned long it;
+
+		for (it = 0; it < PTRS_PER_PTE; ++it, ++p) {
+			if (pte_val(*p) == 0)
+				continue;
+			WARN_ON_ONCE(1);
+			kvmppc_unmap_pte(kvm, p,
+					 pte_pfn(*p) << PAGE_SHIFT,
+					 PAGE_SHIFT);
+		}
+	}
+
+	kvmppc_pte_free(pte);
+}
+
+static void kvmppc_unmap_free_pmd(struct kvm *kvm, pmd_t *pmd, bool full)
+{
+	unsigned long im;
+	pmd_t *p = pmd;
+
+	for (im = 0; im < PTRS_PER_PMD; ++im, ++p) {
+		if (!pmd_present(*p))
+			continue;
+		if (pmd_is_leaf(*p)) {
+			if (full) {
+				pmd_clear(p);
+			} else {
+				WARN_ON_ONCE(1);
+				kvmppc_unmap_pte(kvm, (pte_t *)p,
+					 pte_pfn(*(pte_t *)p) << PAGE_SHIFT,
+					 PMD_SHIFT);
+			}
+		} else {
+			pte_t *pte;
+
+			pte = pte_offset_map(p, 0);
+			kvmppc_unmap_free_pte(kvm, pte, full);
+			pmd_clear(p);
+		}
+	}
+	kvmppc_pmd_free(pmd);
+}
+
+static void kvmppc_unmap_free_pud(struct kvm *kvm, pud_t *pud)
+{
+	unsigned long iu;
+	pud_t *p = pud;
+
+	for (iu = 0; iu < PTRS_PER_PUD; ++iu, ++p) {
+		if (!pud_present(*p))
+			continue;
+		if (pud_huge(*p)) {
+			pud_clear(p);
+		} else {
+			pmd_t *pmd;
+
+			pmd = pmd_offset(p, 0);
+			kvmppc_unmap_free_pmd(kvm, pmd, true);
+			pud_clear(p);
+		}
+	}
+	pud_free(kvm->mm, pud);
+}
+
+void kvmppc_free_radix(struct kvm *kvm)
+{
+	unsigned long ig;
+	pgd_t *pgd;
+
+	if (!kvm->arch.pgtable)
+		return;
+	pgd = kvm->arch.pgtable;
+	for (ig = 0; ig < PTRS_PER_PGD; ++ig, ++pgd) {
+		pud_t *pud;
+
+		if (!pgd_present(*pgd))
+			continue;
+		pud = pud_offset(pgd, 0);
+		kvmppc_unmap_free_pud(kvm, pud);
+		pgd_clear(pgd);
+	}
+	pgd_free(kvm->mm, kvm->arch.pgtable);
+	kvm->arch.pgtable = NULL;
+}
+
+static void kvmppc_unmap_free_pmd_entry_table(struct kvm *kvm, pmd_t *pmd,
+					      unsigned long gpa)
+{
+	pte_t *pte = pte_offset_kernel(pmd, 0);
+
+	/*
+	 * Clearing the pmd entry then flushing the PWC ensures that the pte
+	 * page no longer be cached by the MMU, so can be freed without
+	 * flushing the PWC again.
+	 */
+	pmd_clear(pmd);
+	kvmppc_radix_flush_pwc(kvm);
+
+	kvmppc_unmap_free_pte(kvm, pte, false);
+}
+
+static void kvmppc_unmap_free_pud_entry_table(struct kvm *kvm, pud_t *pud,
+					unsigned long gpa)
+{
+	pmd_t *pmd = pmd_offset(pud, 0);
+
+	/*
+	 * Clearing the pud entry then flushing the PWC ensures that the pmd
+	 * page and any children pte pages will no longer be cached by the MMU,
+	 * so can be freed without flushing the PWC again.
+	 */
+	pud_clear(pud);
+	kvmppc_radix_flush_pwc(kvm);
+
+	kvmppc_unmap_free_pmd(kvm, pmd, false);
+}
+
+/*
+ * There are a number of bits which may differ between different faults to
+ * the same partition scope entry. RC bits, in the course of cleaning and
+ * aging. And the write bit can change, either the access could have been
+ * upgraded, or a read fault could happen concurrently with a write fault
+ * that sets those bits first.
+ */
+#define PTE_BITS_MUST_MATCH (~(_PAGE_WRITE | _PAGE_DIRTY | _PAGE_ACCESSED))
+
 static int kvmppc_create_pte(struct kvm *kvm, pte_t pte, unsigned long gpa,
 			     unsigned int level, unsigned long mmu_seq)
 {
@@ -235,7 +376,6 @@ static int kvmppc_create_pte(struct kvm *kvm, pte_t pte, unsigned long gpa,
 	pud_t *pud, *new_pud = NULL;
 	pmd_t *pmd, *new_pmd = NULL;
 	pte_t *ptep, *new_ptep = NULL;
-	unsigned long old;
 	int ret;
 
 	/* Traverse the guest's 2nd-level tree, allocate new levels needed */
@@ -273,42 +413,39 @@ static int kvmppc_create_pte(struct kvm *kvm, pte_t pte, unsigned long gpa,
 	if (pud_huge(*pud)) {
 		unsigned long hgpa = gpa & PUD_MASK;
 
+		/* Check if we raced and someone else has set the same thing */
+		if (level == 2) {
+			if (pud_raw(*pud) == pte_raw(pte)) {
+				ret = 0;
+				goto out_unlock;
+			}
+			/* Valid 1GB page here already, add our extra bits */
+			WARN_ON_ONCE((pud_val(*pud) ^ pte_val(pte)) &
+							PTE_BITS_MUST_MATCH);
+			kvmppc_radix_update_pte(kvm, (pte_t *)pud,
+					      0, pte_val(pte), hgpa, PUD_SHIFT);
+			ret = 0;
+			goto out_unlock;
+		}
 		/*
 		 * If we raced with another CPU which has just put
 		 * a 1GB pte in after we saw a pmd page, try again.
 		 */
-		if (level <= 1 && !new_pmd) {
+		if (!new_pmd) {
 			ret = -EAGAIN;
 			goto out_unlock;
 		}
-		/* Check if we raced and someone else has set the same thing */
-		if (level == 2 && pud_raw(*pud) == pte_raw(pte)) {
-			ret = 0;
-			goto out_unlock;
-		}
 		/* Valid 1GB page here already, remove it */
-		old = kvmppc_radix_update_pte(kvm, (pte_t *)pud,
-					      ~0UL, 0, hgpa, PUD_SHIFT);
-		kvmppc_radix_tlbie_page(kvm, hgpa, PUD_SHIFT);
-		if (old & _PAGE_DIRTY) {
-			unsigned long gfn = hgpa >> PAGE_SHIFT;
-			struct kvm_memory_slot *memslot;
-			memslot = gfn_to_memslot(kvm, gfn);
-			if (memslot && memslot->dirty_bitmap)
-				kvmppc_update_dirty_map(memslot,
-							gfn, PUD_SIZE);
-		}
+		kvmppc_unmap_pte(kvm, (pte_t *)pud, hgpa, PUD_SHIFT);
 	}
 	if (level == 2) {
 		if (!pud_none(*pud)) {
 			/*
 			 * There's a page table page here, but we wanted to
 			 * install a large page, so remove and free the page
-			 * table page.  new_pmd will be NULL since level == 2.
+			 * table page.
 			 */
-			new_pmd = pmd_offset(pud, 0);
-			pud_clear(pud);
-			kvmppc_radix_flush_pwc(kvm, gpa);
+			kvmppc_unmap_free_pud_entry_table(kvm, pud, gpa);
 		}
 		kvmppc_radix_set_pte_at(kvm, gpa, (pte_t *)pud, pte);
 		ret = 0;
@@ -324,42 +461,40 @@ static int kvmppc_create_pte(struct kvm *kvm, pte_t pte, unsigned long gpa,
 	if (pmd_is_leaf(*pmd)) {
 		unsigned long lgpa = gpa & PMD_MASK;
 
+		/* Check if we raced and someone else has set the same thing */
+		if (level == 1) {
+			if (pmd_raw(*pmd) == pte_raw(pte)) {
+				ret = 0;
+				goto out_unlock;
+			}
+			/* Valid 2MB page here already, add our extra bits */
+			WARN_ON_ONCE((pmd_val(*pmd) ^ pte_val(pte)) &
+							PTE_BITS_MUST_MATCH);
+			kvmppc_radix_update_pte(kvm, pmdp_ptep(pmd),
+					      0, pte_val(pte), lgpa, PMD_SHIFT);
+			ret = 0;
+			goto out_unlock;
+		}
+
 		/*
 		 * If we raced with another CPU which has just put
 		 * a 2MB pte in after we saw a pte page, try again.
 		 */
-		if (level == 0 && !new_ptep) {
+		if (!new_ptep) {
 			ret = -EAGAIN;
 			goto out_unlock;
 		}
-		/* Check if we raced and someone else has set the same thing */
-		if (level == 1 && pmd_raw(*pmd) == pte_raw(pte)) {
-			ret = 0;
-			goto out_unlock;
-		}
 		/* Valid 2MB page here already, remove it */
-		old = kvmppc_radix_update_pte(kvm, pmdp_ptep(pmd),
-					      ~0UL, 0, lgpa, PMD_SHIFT);
-		kvmppc_radix_tlbie_page(kvm, lgpa, PMD_SHIFT);
-		if (old & _PAGE_DIRTY) {
-			unsigned long gfn = lgpa >> PAGE_SHIFT;
-			struct kvm_memory_slot *memslot;
-			memslot = gfn_to_memslot(kvm, gfn);
-			if (memslot && memslot->dirty_bitmap)
-				kvmppc_update_dirty_map(memslot,
-							gfn, PMD_SIZE);
-		}
+		kvmppc_unmap_pte(kvm, pmdp_ptep(pmd), lgpa, PMD_SHIFT);
 	}
 	if (level == 1) {
 		if (!pmd_none(*pmd)) {
 			/*
 			 * There's a page table page here, but we wanted to
 			 * install a large page, so remove and free the page
-			 * table page.  new_ptep will be NULL since level == 1.
+			 * table page.
 			 */
-			new_ptep = pte_offset_kernel(pmd, 0);
-			pmd_clear(pmd);
-			kvmppc_radix_flush_pwc(kvm, gpa);
+			kvmppc_unmap_free_pmd_entry_table(kvm, pmd, gpa);
 		}
 		kvmppc_radix_set_pte_at(kvm, gpa, pmdp_ptep(pmd), pte);
 		ret = 0;
@@ -378,12 +513,12 @@ static int kvmppc_create_pte(struct kvm *kvm, pte_t pte, unsigned long gpa,
 			ret = 0;
 			goto out_unlock;
 		}
-		/* PTE was previously valid, so invalidate it */
-		old = kvmppc_radix_update_pte(kvm, ptep, _PAGE_PRESENT,
-					      0, gpa, 0);
-		kvmppc_radix_tlbie_page(kvm, gpa, 0);
-		if (old & _PAGE_DIRTY)
-			mark_page_dirty(kvm, gpa >> PAGE_SHIFT);
+		/* Valid page here already, add our extra bits */
+		WARN_ON_ONCE((pte_val(*ptep) ^ pte_val(pte)) &
+							PTE_BITS_MUST_MATCH);
+		kvmppc_radix_update_pte(kvm, ptep, 0, pte_val(pte), gpa, 0);
+		ret = 0;
+		goto out_unlock;
 	}
 	kvmppc_radix_set_pte_at(kvm, gpa, ptep, pte);
 	ret = 0;
@@ -565,9 +700,13 @@ int kvmppc_book3s_radix_page_fault(struct kvm_run *run, struct kvm_vcpu *vcpu,
 			unsigned long mask = (1ul << shift) - PAGE_SIZE;
 			pte = __pte(pte_val(pte) | (hva & mask));
 		}
-		if (!(writing || upgrade_write))
-			pte = __pte(pte_val(pte) & ~ _PAGE_WRITE);
-		pte = __pte(pte_val(pte) | _PAGE_EXEC);
+		pte = __pte(pte_val(pte) | _PAGE_EXEC | _PAGE_ACCESSED);
+		if (writing || upgrade_write) {
+			if (pte_val(pte) & _PAGE_WRITE)
+				pte = __pte(pte_val(pte) | _PAGE_DIRTY);
+		} else {
+			pte = __pte(pte_val(pte) & ~(_PAGE_WRITE | _PAGE_DIRTY));
+		}
 	}
 
 	/* Allocate space in the tree and write the PTE */
@@ -734,51 +873,6 @@ int kvmppc_init_vm_radix(struct kvm *kvm)
 	return 0;
 }
 
-void kvmppc_free_radix(struct kvm *kvm)
-{
-	unsigned long ig, iu, im;
-	pte_t *pte;
-	pmd_t *pmd;
-	pud_t *pud;
-	pgd_t *pgd;
-
-	if (!kvm->arch.pgtable)
-		return;
-	pgd = kvm->arch.pgtable;
-	for (ig = 0; ig < PTRS_PER_PGD; ++ig, ++pgd) {
-		if (!pgd_present(*pgd))
-			continue;
-		pud = pud_offset(pgd, 0);
-		for (iu = 0; iu < PTRS_PER_PUD; ++iu, ++pud) {
-			if (!pud_present(*pud))
-				continue;
-			if (pud_huge(*pud)) {
-				pud_clear(pud);
-				continue;
-			}
-			pmd = pmd_offset(pud, 0);
-			for (im = 0; im < PTRS_PER_PMD; ++im, ++pmd) {
-				if (pmd_is_leaf(*pmd)) {
-					pmd_clear(pmd);
-					continue;
-				}
-				if (!pmd_present(*pmd))
-					continue;
-				pte = pte_offset_map(pmd, 0);
-				memset(pte, 0, sizeof(long) << PTE_INDEX_SIZE);
-				kvmppc_pte_free(pte);
-				pmd_clear(pmd);
-			}
-			kvmppc_pmd_free(pmd_offset(pud, 0));
-			pud_clear(pud);
-		}
-		pud_free(kvm->mm, pud_offset(pgd, 0));
-		pgd_clear(pgd);
-	}
-	pgd_free(kvm->mm, kvm->arch.pgtable);
-	kvm->arch.pgtable = NULL;
-}
-
 static void pte_ctor(void *addr)
 {
 	memset(addr, 0, RADIX_PTE_TABLE_SIZE);

arch/powerpc/kvm/book3s_64_vio.c

@@ -176,14 +176,12 @@ extern long kvm_spapr_tce_attach_iommu_group(struct kvm *kvm, int tablefd,
 
 		if (!tbltmp)
 			continue;
-		/*
-		 * Make sure hardware table parameters are exactly the same;
-		 * this is used in the TCE handlers where boundary checks
-		 * use only the first attached table.
-		 */
-		if ((tbltmp->it_page_shift == stt->page_shift) &&
-				(tbltmp->it_offset == stt->offset) &&
-				(tbltmp->it_size == stt->size)) {
+		/* Make sure hardware table parameters are compatible */
+		if ((tbltmp->it_page_shift <= stt->page_shift) &&
+				(tbltmp->it_offset << tbltmp->it_page_shift ==
+				 stt->offset << stt->page_shift) &&
+				(tbltmp->it_size << tbltmp->it_page_shift ==
+				 stt->size << stt->page_shift)) {
 			/*
 			 * Reference the table to avoid races with
 			 * add/remove DMA windows.
@@ -237,7 +235,7 @@ static void release_spapr_tce_table(struct rcu_head *head)
 	kfree(stt);
 }
 
-static int kvm_spapr_tce_fault(struct vm_fault *vmf)
+static vm_fault_t kvm_spapr_tce_fault(struct vm_fault *vmf)
 {
 	struct kvmppc_spapr_tce_table *stt = vmf->vma->vm_file->private_data;
 	struct page *page;
@@ -302,7 +300,8 @@ long kvm_vm_ioctl_create_spapr_tce(struct kvm *kvm,
 	int ret = -ENOMEM;
 	int i;
 
-	if (!args->size)
+	if (!args->size || args->page_shift < 12 || args->page_shift > 34 ||
+		(args->offset + args->size > (ULLONG_MAX >> args->page_shift)))
 		return -EINVAL;
 
 	size = _ALIGN_UP(args->size, PAGE_SIZE >> 3);
@@ -396,7 +395,7 @@ static long kvmppc_tce_iommu_mapped_dec(struct kvm *kvm,
 	return H_SUCCESS;
 }
 
-static long kvmppc_tce_iommu_unmap(struct kvm *kvm,
+static long kvmppc_tce_iommu_do_unmap(struct kvm *kvm,
 		struct iommu_table *tbl, unsigned long entry)
 {
 	enum dma_data_direction dir = DMA_NONE;
@@ -416,7 +415,24 @@ static long kvmppc_tce_iommu_unmap(struct kvm *kvm,
 	return ret;
 }
 
-long kvmppc_tce_iommu_map(struct kvm *kvm, struct iommu_table *tbl,
+static long kvmppc_tce_iommu_unmap(struct kvm *kvm,
+		struct kvmppc_spapr_tce_table *stt, struct iommu_table *tbl,
+		unsigned long entry)
+{
+	unsigned long i, ret = H_SUCCESS;
+	unsigned long subpages = 1ULL << (stt->page_shift - tbl->it_page_shift);
+	unsigned long io_entry = entry * subpages;
+
+	for (i = 0; i < subpages; ++i) {
+		ret = kvmppc_tce_iommu_do_unmap(kvm, tbl, io_entry + i);
+		if (ret != H_SUCCESS)
+			break;
+	}
+
+	return ret;
+}
+
+long kvmppc_tce_iommu_do_map(struct kvm *kvm, struct iommu_table *tbl,
 		unsigned long entry, unsigned long ua,
 		enum dma_data_direction dir)
 {
@@ -453,6 +469,27 @@ long kvmppc_tce_iommu_map(struct kvm *kvm, struct iommu_table *tbl,
 	return 0;
 }
 
+static long kvmppc_tce_iommu_map(struct kvm *kvm,
+		struct kvmppc_spapr_tce_table *stt, struct iommu_table *tbl,
+		unsigned long entry, unsigned long ua,
+		enum dma_data_direction dir)
+{
+	unsigned long i, pgoff, ret = H_SUCCESS;
+	unsigned long subpages = 1ULL << (stt->page_shift - tbl->it_page_shift);
+	unsigned long io_entry = entry * subpages;
+
+	for (i = 0, pgoff = 0; i < subpages;
+			++i, pgoff += IOMMU_PAGE_SIZE(tbl)) {
+
+		ret = kvmppc_tce_iommu_do_map(kvm, tbl,
+				io_entry + i, ua + pgoff, dir);
+		if (ret != H_SUCCESS)
+			break;
+	}
+
+	return ret;
+}
+
 long kvmppc_h_put_tce(struct kvm_vcpu *vcpu, unsigned long liobn,
 		      unsigned long ioba, unsigned long tce)
 {
@@ -491,10 +528,10 @@ long kvmppc_h_put_tce(struct kvm_vcpu *vcpu, unsigned long liobn,
 
 	list_for_each_entry_lockless(stit, &stt->iommu_tables, next) {
 		if (dir == DMA_NONE)
-			ret = kvmppc_tce_iommu_unmap(vcpu->kvm,
+			ret = kvmppc_tce_iommu_unmap(vcpu->kvm, stt,
 					stit->tbl, entry);
 		else
-			ret = kvmppc_tce_iommu_map(vcpu->kvm, stit->tbl,
+			ret = kvmppc_tce_iommu_map(vcpu->kvm, stt, stit->tbl,
 					entry, ua, dir);
 
 		if (ret == H_SUCCESS)
@@ -570,7 +607,7 @@ long kvmppc_h_put_tce_indirect(struct kvm_vcpu *vcpu,
 			return H_PARAMETER;
 
 		list_for_each_entry_lockless(stit, &stt->iommu_tables, next) {
-			ret = kvmppc_tce_iommu_map(vcpu->kvm,
+			ret = kvmppc_tce_iommu_map(vcpu->kvm, stt,
 					stit->tbl, entry + i, ua,
 					iommu_tce_direction(tce));
 
@@ -615,10 +652,10 @@ long kvmppc_h_stuff_tce(struct kvm_vcpu *vcpu,
 		return H_PARAMETER;
 
 	list_for_each_entry_lockless(stit, &stt->iommu_tables, next) {
-		unsigned long entry = ioba >> stit->tbl->it_page_shift;
+		unsigned long entry = ioba >> stt->page_shift;
 
 		for (i = 0; i < npages; ++i) {
-			ret = kvmppc_tce_iommu_unmap(vcpu->kvm,
+			ret = kvmppc_tce_iommu_unmap(vcpu->kvm, stt,
 					stit->tbl, entry + i);
 
 			if (ret == H_SUCCESS)

arch/powerpc/kvm/book3s_64_vio_hv.c

@@ -221,7 +221,7 @@ static long kvmppc_rm_tce_iommu_mapped_dec(struct kvm *kvm,
 	return H_SUCCESS;
 }
 
-static long kvmppc_rm_tce_iommu_unmap(struct kvm *kvm,
+static long kvmppc_rm_tce_iommu_do_unmap(struct kvm *kvm,
 		struct iommu_table *tbl, unsigned long entry)
 {
 	enum dma_data_direction dir = DMA_NONE;
@@ -245,7 +245,24 @@ static long kvmppc_rm_tce_iommu_unmap(struct kvm *kvm,
 	return ret;
 }
 
-static long kvmppc_rm_tce_iommu_map(struct kvm *kvm, struct iommu_table *tbl,
+static long kvmppc_rm_tce_iommu_unmap(struct kvm *kvm,
+		struct kvmppc_spapr_tce_table *stt, struct iommu_table *tbl,
+		unsigned long entry)
+{
+	unsigned long i, ret = H_SUCCESS;
+	unsigned long subpages = 1ULL << (stt->page_shift - tbl->it_page_shift);
+	unsigned long io_entry = entry * subpages;
+
+	for (i = 0; i < subpages; ++i) {
+		ret = kvmppc_rm_tce_iommu_do_unmap(kvm, tbl, io_entry + i);
+		if (ret != H_SUCCESS)
+			break;
+	}
+
+	return ret;
+}
+
+static long kvmppc_rm_tce_iommu_do_map(struct kvm *kvm, struct iommu_table *tbl,
 		unsigned long entry, unsigned long ua,
 		enum dma_data_direction dir)
 {
@@ -290,6 +307,27 @@ static long kvmppc_rm_tce_iommu_map(struct kvm *kvm, struct iommu_table *tbl,
 	return 0;
 }
 
+static long kvmppc_rm_tce_iommu_map(struct kvm *kvm,
+		struct kvmppc_spapr_tce_table *stt, struct iommu_table *tbl,
+		unsigned long entry, unsigned long ua,
+		enum dma_data_direction dir)
+{
+	unsigned long i, pgoff, ret = H_SUCCESS;
+	unsigned long subpages = 1ULL << (stt->page_shift - tbl->it_page_shift);
+	unsigned long io_entry = entry * subpages;
+
+	for (i = 0, pgoff = 0; i < subpages;
+			++i, pgoff += IOMMU_PAGE_SIZE(tbl)) {
+
+		ret = kvmppc_rm_tce_iommu_do_map(kvm, tbl,
+				io_entry + i, ua + pgoff, dir);
+		if (ret != H_SUCCESS)
+			break;
+	}
+
+	return ret;
+}
+
 long kvmppc_rm_h_put_tce(struct kvm_vcpu *vcpu, unsigned long liobn,
 		unsigned long ioba, unsigned long tce)
 {
@@ -327,10 +365,10 @@ long kvmppc_rm_h_put_tce(struct kvm_vcpu *vcpu, unsigned long liobn,
 
 	list_for_each_entry_lockless(stit, &stt->iommu_tables, next) {
 		if (dir == DMA_NONE)
-			ret = kvmppc_rm_tce_iommu_unmap(vcpu->kvm,
+			ret = kvmppc_rm_tce_iommu_unmap(vcpu->kvm, stt,
 					stit->tbl, entry);
 		else
-			ret = kvmppc_rm_tce_iommu_map(vcpu->kvm,
+			ret = kvmppc_rm_tce_iommu_map(vcpu->kvm, stt,
 					stit->tbl, entry, ua, dir);
 
 		if (ret == H_SUCCESS)
@@ -477,7 +515,7 @@ long kvmppc_rm_h_put_tce_indirect(struct kvm_vcpu *vcpu,
 			return H_PARAMETER;
 
 		list_for_each_entry_lockless(stit, &stt->iommu_tables, next) {
-			ret = kvmppc_rm_tce_iommu_map(vcpu->kvm,
+			ret = kvmppc_rm_tce_iommu_map(vcpu->kvm, stt,
 					stit->tbl, entry + i, ua,
 					iommu_tce_direction(tce));
 
@@ -526,10 +564,10 @@ long kvmppc_rm_h_stuff_tce(struct kvm_vcpu *vcpu,
 		return H_PARAMETER;
 
 	list_for_each_entry_lockless(stit, &stt->iommu_tables, next) {
-		unsigned long entry = ioba >> stit->tbl->it_page_shift;
+		unsigned long entry = ioba >> stt->page_shift;
 
 		for (i = 0; i < npages; ++i) {
-			ret = kvmppc_rm_tce_iommu_unmap(vcpu->kvm,
+			ret = kvmppc_rm_tce_iommu_unmap(vcpu->kvm, stt,
 					stit->tbl, entry + i);
 
 			if (ret == H_SUCCESS)
@@ -571,7 +609,7 @@ long kvmppc_h_get_tce(struct kvm_vcpu *vcpu, unsigned long liobn,
 	page = stt->pages[idx / TCES_PER_PAGE];
 	tbl = (u64 *)page_address(page);
 
-	vcpu->arch.gpr[4] = tbl[idx % TCES_PER_PAGE];
+	vcpu->arch.regs.gpr[4] = tbl[idx % TCES_PER_PAGE];
 
 	return H_SUCCESS;
 }

arch/powerpc/kvm/book3s_emulate.c

@@ -23,7 +23,9 @@
 #include <asm/reg.h>
 #include <asm/switch_to.h>
 #include <asm/time.h>
+#include <asm/tm.h>
 #include "book3s.h"
+#include <asm/asm-prototypes.h>
 
 #define OP_19_XOP_RFID		18
 #define OP_19_XOP_RFI		50
@@ -47,6 +49,12 @@
 #define OP_31_XOP_EIOIO		854
 #define OP_31_XOP_SLBMFEE	915
 
+#define OP_31_XOP_TBEGIN	654
+#define OP_31_XOP_TABORT	910
+
+#define OP_31_XOP_TRECLAIM	942
+#define OP_31_XOP_TRCHKPT	1006
+
 /* DCBZ is actually 1014, but we patch it to 1010 so we get a trap */
 #define OP_31_XOP_DCBZ		1010
 
@@ -87,6 +95,157 @@ static bool spr_allowed(struct kvm_vcpu *vcpu, enum priv_level level)
 	return true;
 }
 
+#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+static inline void kvmppc_copyto_vcpu_tm(struct kvm_vcpu *vcpu)
+{
+	memcpy(&vcpu->arch.gpr_tm[0], &vcpu->arch.regs.gpr[0],
+			sizeof(vcpu->arch.gpr_tm));
+	memcpy(&vcpu->arch.fp_tm, &vcpu->arch.fp,
+			sizeof(struct thread_fp_state));
+	memcpy(&vcpu->arch.vr_tm, &vcpu->arch.vr,
+			sizeof(struct thread_vr_state));
+	vcpu->arch.ppr_tm = vcpu->arch.ppr;
+	vcpu->arch.dscr_tm = vcpu->arch.dscr;
+	vcpu->arch.amr_tm = vcpu->arch.amr;
+	vcpu->arch.ctr_tm = vcpu->arch.regs.ctr;
+	vcpu->arch.tar_tm = vcpu->arch.tar;
+	vcpu->arch.lr_tm = vcpu->arch.regs.link;
+	vcpu->arch.cr_tm = vcpu->arch.cr;
+	vcpu->arch.xer_tm = vcpu->arch.regs.xer;
+	vcpu->arch.vrsave_tm = vcpu->arch.vrsave;
+}
+
+static inline void kvmppc_copyfrom_vcpu_tm(struct kvm_vcpu *vcpu)
+{
+	memcpy(&vcpu->arch.regs.gpr[0], &vcpu->arch.gpr_tm[0],
+			sizeof(vcpu->arch.regs.gpr));
+	memcpy(&vcpu->arch.fp, &vcpu->arch.fp_tm,
+			sizeof(struct thread_fp_state));
+	memcpy(&vcpu->arch.vr, &vcpu->arch.vr_tm,
+			sizeof(struct thread_vr_state));
+	vcpu->arch.ppr = vcpu->arch.ppr_tm;
+	vcpu->arch.dscr = vcpu->arch.dscr_tm;
+	vcpu->arch.amr = vcpu->arch.amr_tm;
+	vcpu->arch.regs.ctr = vcpu->arch.ctr_tm;
+	vcpu->arch.tar = vcpu->arch.tar_tm;
+	vcpu->arch.regs.link = vcpu->arch.lr_tm;
+	vcpu->arch.cr = vcpu->arch.cr_tm;
+	vcpu->arch.regs.xer = vcpu->arch.xer_tm;
+	vcpu->arch.vrsave = vcpu->arch.vrsave_tm;
+}
+
+static void kvmppc_emulate_treclaim(struct kvm_vcpu *vcpu, int ra_val)
+{
+	unsigned long guest_msr = kvmppc_get_msr(vcpu);
+	int fc_val = ra_val ? ra_val : 1;
+	uint64_t texasr;
+
+	/* CR0 = 0 | MSR[TS] | 0 */
+	vcpu->arch.cr = (vcpu->arch.cr & ~(CR0_MASK << CR0_SHIFT)) |
+		(((guest_msr & MSR_TS_MASK) >> (MSR_TS_S_LG - 1))
+		 << CR0_SHIFT);
+
+	preempt_disable();
+	tm_enable();
+	texasr = mfspr(SPRN_TEXASR);
+	kvmppc_save_tm_pr(vcpu);
+	kvmppc_copyfrom_vcpu_tm(vcpu);
+
+	/* failure recording depends on Failure Summary bit */
+	if (!(texasr & TEXASR_FS)) {
+		texasr &= ~TEXASR_FC;
+		texasr |= ((u64)fc_val << TEXASR_FC_LG) | TEXASR_FS;
+
+		texasr &= ~(TEXASR_PR | TEXASR_HV);
+		if (kvmppc_get_msr(vcpu) & MSR_PR)
+			texasr |= TEXASR_PR;
+
+		if (kvmppc_get_msr(vcpu) & MSR_HV)
+			texasr |= TEXASR_HV;
+
+		vcpu->arch.texasr = texasr;
+		vcpu->arch.tfiar = kvmppc_get_pc(vcpu);
+		mtspr(SPRN_TEXASR, texasr);
+		mtspr(SPRN_TFIAR, vcpu->arch.tfiar);
+	}
+	tm_disable();
+	/*
+	 * treclaim need quit to non-transactional state.
+	 */
+	guest_msr &= ~(MSR_TS_MASK);
+	kvmppc_set_msr(vcpu, guest_msr);
+	preempt_enable();
+
+	if (vcpu->arch.shadow_fscr & FSCR_TAR)
+		mtspr(SPRN_TAR, vcpu->arch.tar);
+}
+
+static void kvmppc_emulate_trchkpt(struct kvm_vcpu *vcpu)
+{
+	unsigned long guest_msr = kvmppc_get_msr(vcpu);
+
+	preempt_disable();
+	/*
+	 * need flush FP/VEC/VSX to vcpu save area before
+	 * copy.
+	 */
+	kvmppc_giveup_ext(vcpu, MSR_VSX);
+	kvmppc_giveup_fac(vcpu, FSCR_TAR_LG);
+	kvmppc_copyto_vcpu_tm(vcpu);
+	kvmppc_save_tm_sprs(vcpu);
+
+	/*
+	 * as a result of trecheckpoint. set TS to suspended.
+	 */
+	guest_msr &= ~(MSR_TS_MASK);
+	guest_msr |= MSR_TS_S;
+	kvmppc_set_msr(vcpu, guest_msr);
+	kvmppc_restore_tm_pr(vcpu);
+	preempt_enable();
+}
+
+/* emulate tabort. at guest privilege state */
+void kvmppc_emulate_tabort(struct kvm_vcpu *vcpu, int ra_val)
+{
+	/* currently we only emulate tabort. but no emulation of other
+	 * tabort variants since there is no kernel usage of them at
+	 * present.
+	 */
+	unsigned long guest_msr = kvmppc_get_msr(vcpu);
+	uint64_t org_texasr;
+
+	preempt_disable();
+	tm_enable();
+	org_texasr = mfspr(SPRN_TEXASR);
+	tm_abort(ra_val);
+
+	/* CR0 = 0 | MSR[TS] | 0 */
+	vcpu->arch.cr = (vcpu->arch.cr & ~(CR0_MASK << CR0_SHIFT)) |
+		(((guest_msr & MSR_TS_MASK) >> (MSR_TS_S_LG - 1))
+		 << CR0_SHIFT);
+
+	vcpu->arch.texasr = mfspr(SPRN_TEXASR);
+	/* failure recording depends on Failure Summary bit,
+	 * and tabort will be treated as nops in non-transactional
+	 * state.
+	 */
+	if (!(org_texasr & TEXASR_FS) &&
+			MSR_TM_ACTIVE(guest_msr)) {
+		vcpu->arch.texasr &= ~(TEXASR_PR | TEXASR_HV);
+		if (guest_msr & MSR_PR)
+			vcpu->arch.texasr |= TEXASR_PR;
+
+		if (guest_msr & MSR_HV)
+			vcpu->arch.texasr |= TEXASR_HV;
+
+		vcpu->arch.tfiar = kvmppc_get_pc(vcpu);
+	}
+	tm_disable();
+	preempt_enable();
+}
+
+#endif
+
 int kvmppc_core_emulate_op_pr(struct kvm_run *run, struct kvm_vcpu *vcpu,
 			      unsigned int inst, int *advance)
 {
@@ -117,11 +276,28 @@ int kvmppc_core_emulate_op_pr(struct kvm_run *run, struct kvm_vcpu *vcpu,
 	case 19:
 		switch (get_xop(inst)) {
 		case OP_19_XOP_RFID:
-		case OP_19_XOP_RFI:
+		case OP_19_XOP_RFI: {
+			unsigned long srr1 = kvmppc_get_srr1(vcpu);
+#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+			unsigned long cur_msr = kvmppc_get_msr(vcpu);
+
+			/*
+			 * add rules to fit in ISA specification regarding TM
+			 * state transistion in TM disable/Suspended state,
+			 * and target TM state is TM inactive(00) state. (the
+			 * change should be suppressed).
+			 */
+			if (((cur_msr & MSR_TM) == 0) &&
+				((srr1 & MSR_TM) == 0) &&
+				MSR_TM_SUSPENDED(cur_msr) &&
+				!MSR_TM_ACTIVE(srr1))
+				srr1 |= MSR_TS_S;
+#endif
 			kvmppc_set_pc(vcpu, kvmppc_get_srr0(vcpu));
-			kvmppc_set_msr(vcpu, kvmppc_get_srr1(vcpu));
+			kvmppc_set_msr(vcpu, srr1);
 			*advance = 0;
 			break;
+		}
 
 		default:
 			emulated = EMULATE_FAIL;
@@ -304,6 +480,140 @@ int kvmppc_core_emulate_op_pr(struct kvm_run *run, struct kvm_vcpu *vcpu,
 
 			break;
 		}
+#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+		case OP_31_XOP_TBEGIN:
+		{
+			if (!cpu_has_feature(CPU_FTR_TM))
+				break;
+
+			if (!(kvmppc_get_msr(vcpu) & MSR_TM)) {
+				kvmppc_trigger_fac_interrupt(vcpu, FSCR_TM_LG);
+				emulated = EMULATE_AGAIN;
+				break;
+			}
+
+			if (!(kvmppc_get_msr(vcpu) & MSR_PR)) {
+				preempt_disable();
+				vcpu->arch.cr = (CR0_TBEGIN_FAILURE |
+				  (vcpu->arch.cr & ~(CR0_MASK << CR0_SHIFT)));
+
+				vcpu->arch.texasr = (TEXASR_FS | TEXASR_EXACT |
+					(((u64)(TM_CAUSE_EMULATE | TM_CAUSE_PERSISTENT))
+						 << TEXASR_FC_LG));
+
+				if ((inst >> 21) & 0x1)
+					vcpu->arch.texasr |= TEXASR_ROT;
+
+				if (kvmppc_get_msr(vcpu) & MSR_HV)
+					vcpu->arch.texasr |= TEXASR_HV;
+
+				vcpu->arch.tfhar = kvmppc_get_pc(vcpu) + 4;
+				vcpu->arch.tfiar = kvmppc_get_pc(vcpu);
+
+				kvmppc_restore_tm_sprs(vcpu);
+				preempt_enable();
+			} else
+				emulated = EMULATE_FAIL;
+			break;
+		}
+		case OP_31_XOP_TABORT:
+		{
+			ulong guest_msr = kvmppc_get_msr(vcpu);
+			unsigned long ra_val = 0;
+
+			if (!cpu_has_feature(CPU_FTR_TM))
+				break;
+
+			if (!(kvmppc_get_msr(vcpu) & MSR_TM)) {
+				kvmppc_trigger_fac_interrupt(vcpu, FSCR_TM_LG);
+				emulated = EMULATE_AGAIN;
+				break;
+			}
+
+			/* only emulate for privilege guest, since problem state
+			 * guest can run with TM enabled and we don't expect to
+			 * trap at here for that case.
+			 */
+			WARN_ON(guest_msr & MSR_PR);
+
+			if (ra)
+				ra_val = kvmppc_get_gpr(vcpu, ra);
+
+			kvmppc_emulate_tabort(vcpu, ra_val);
+			break;
+		}
+		case OP_31_XOP_TRECLAIM:
+		{
+			ulong guest_msr = kvmppc_get_msr(vcpu);
+			unsigned long ra_val = 0;
+
+			if (!cpu_has_feature(CPU_FTR_TM))
+				break;
+
+			if (!(kvmppc_get_msr(vcpu) & MSR_TM)) {
+				kvmppc_trigger_fac_interrupt(vcpu, FSCR_TM_LG);
+				emulated = EMULATE_AGAIN;
+				break;
+			}
+
+			/* generate interrupts based on priorities */
+			if (guest_msr & MSR_PR) {
+				/* Privileged Instruction type Program Interrupt */
+				kvmppc_core_queue_program(vcpu, SRR1_PROGPRIV);
+				emulated = EMULATE_AGAIN;
+				break;
+			}
+
+			if (!MSR_TM_ACTIVE(guest_msr)) {
+				/* TM bad thing interrupt */
+				kvmppc_core_queue_program(vcpu, SRR1_PROGTM);
+				emulated = EMULATE_AGAIN;
+				break;
+			}
+
+			if (ra)
+				ra_val = kvmppc_get_gpr(vcpu, ra);
+			kvmppc_emulate_treclaim(vcpu, ra_val);
+			break;
+		}
+		case OP_31_XOP_TRCHKPT:
+		{
+			ulong guest_msr = kvmppc_get_msr(vcpu);
+			unsigned long texasr;
+
+			if (!cpu_has_feature(CPU_FTR_TM))
+				break;
+
+			if (!(kvmppc_get_msr(vcpu) & MSR_TM)) {
+				kvmppc_trigger_fac_interrupt(vcpu, FSCR_TM_LG);
+				emulated = EMULATE_AGAIN;
+				break;
+			}
+
+			/* generate interrupt based on priorities */
+			if (guest_msr & MSR_PR) {
+				/* Privileged Instruction type Program Intr */
+				kvmppc_core_queue_program(vcpu, SRR1_PROGPRIV);
+				emulated = EMULATE_AGAIN;
+				break;
+			}
+
+			tm_enable();
+			texasr = mfspr(SPRN_TEXASR);
+			tm_disable();
+
+			if (MSR_TM_ACTIVE(guest_msr) ||
+				!(texasr & (TEXASR_FS))) {
+				/* TM bad thing interrupt */
+				kvmppc_core_queue_program(vcpu, SRR1_PROGTM);
+				emulated = EMULATE_AGAIN;
+				break;
+			}
+
+			kvmppc_emulate_trchkpt(vcpu);
+			break;
+		}
+#endif
 		default:
 			emulated = EMULATE_FAIL;
 		}
@@ -465,13 +775,38 @@ int kvmppc_core_emulate_mtspr_pr(struct kvm_vcpu *vcpu, int sprn, ulong spr_val)
 		break;
 #ifdef CONFIG_PPC_TRANSACTIONAL_MEM
 	case SPRN_TFHAR:
-		vcpu->arch.tfhar = spr_val;
-		break;
 	case SPRN_TEXASR:
-		vcpu->arch.texasr = spr_val;
-		break;
 	case SPRN_TFIAR:
-		vcpu->arch.tfiar = spr_val;
+		if (!cpu_has_feature(CPU_FTR_TM))
+			break;
+
+		if (!(kvmppc_get_msr(vcpu) & MSR_TM)) {
+			kvmppc_trigger_fac_interrupt(vcpu, FSCR_TM_LG);
+			emulated = EMULATE_AGAIN;
+			break;
+		}
+
+		if (MSR_TM_ACTIVE(kvmppc_get_msr(vcpu)) &&
+			!((MSR_TM_SUSPENDED(kvmppc_get_msr(vcpu))) &&
+					(sprn == SPRN_TFHAR))) {
+			/* it is illegal to mtspr() TM regs in
+			 * other than non-transactional state, with
+			 * the exception of TFHAR in suspend state.
+			 */
+			kvmppc_core_queue_program(vcpu, SRR1_PROGTM);
+			emulated = EMULATE_AGAIN;
+			break;
+		}
+
+		tm_enable();
+		if (sprn == SPRN_TFHAR)
+			mtspr(SPRN_TFHAR, spr_val);
+		else if (sprn == SPRN_TEXASR)
+			mtspr(SPRN_TEXASR, spr_val);
+		else
+			mtspr(SPRN_TFIAR, spr_val);
+		tm_disable();
+
 		break;
 #endif
 #endif
@@ -618,13 +953,25 @@ int kvmppc_core_emulate_mfspr_pr(struct kvm_vcpu *vcpu, int sprn, ulong *spr_val
 		break;
 #ifdef CONFIG_PPC_TRANSACTIONAL_MEM
 	case SPRN_TFHAR:
-		*spr_val = vcpu->arch.tfhar;
-		break;
 	case SPRN_TEXASR:
-		*spr_val = vcpu->arch.texasr;
-		break;
 	case SPRN_TFIAR:
-		*spr_val = vcpu->arch.tfiar;
+		if (!cpu_has_feature(CPU_FTR_TM))
+			break;
+
+		if (!(kvmppc_get_msr(vcpu) & MSR_TM)) {
+			kvmppc_trigger_fac_interrupt(vcpu, FSCR_TM_LG);
+			emulated = EMULATE_AGAIN;
+			break;
+		}
+
+		tm_enable();
+		if (sprn == SPRN_TFHAR)
+			*spr_val = mfspr(SPRN_TFHAR);
+		else if (sprn == SPRN_TEXASR)
+			*spr_val = mfspr(SPRN_TEXASR);
+		else if (sprn == SPRN_TFIAR)
+			*spr_val = mfspr(SPRN_TFIAR);
+		tm_disable();
 		break;
 #endif
 #endif

arch/powerpc/kvm/book3s_hv.c

@@ -123,6 +123,32 @@ static bool no_mixing_hpt_and_radix;
 static void kvmppc_end_cede(struct kvm_vcpu *vcpu);
 static int kvmppc_hv_setup_htab_rma(struct kvm_vcpu *vcpu);
 
+/*
+ * RWMR values for POWER8.  These control the rate at which PURR
+ * and SPURR count and should be set according to the number of
+ * online threads in the vcore being run.
+ */
+#define RWMR_RPA_P8_1THREAD	0x164520C62609AECA
+#define RWMR_RPA_P8_2THREAD	0x7FFF2908450D8DA9
+#define RWMR_RPA_P8_3THREAD	0x164520C62609AECA
+#define RWMR_RPA_P8_4THREAD	0x199A421245058DA9
+#define RWMR_RPA_P8_5THREAD	0x164520C62609AECA
+#define RWMR_RPA_P8_6THREAD	0x164520C62609AECA
+#define RWMR_RPA_P8_7THREAD	0x164520C62609AECA
+#define RWMR_RPA_P8_8THREAD	0x164520C62609AECA
+
+static unsigned long p8_rwmr_values[MAX_SMT_THREADS + 1] = {
+	RWMR_RPA_P8_1THREAD,
+	RWMR_RPA_P8_1THREAD,
+	RWMR_RPA_P8_2THREAD,
+	RWMR_RPA_P8_3THREAD,
+	RWMR_RPA_P8_4THREAD,
+	RWMR_RPA_P8_5THREAD,
+	RWMR_RPA_P8_6THREAD,
+	RWMR_RPA_P8_7THREAD,
+	RWMR_RPA_P8_8THREAD,
+};
+
 static inline struct kvm_vcpu *next_runnable_thread(struct kvmppc_vcore *vc,
 		int *ip)
 {
@@ -371,13 +397,13 @@ static void kvmppc_dump_regs(struct kvm_vcpu *vcpu)
 
 	pr_err("vcpu %p (%d):\n", vcpu, vcpu->vcpu_id);
 	pr_err("pc  = %.16lx  msr = %.16llx  trap = %x\n",
-	       vcpu->arch.pc, vcpu->arch.shregs.msr, vcpu->arch.trap);
+	       vcpu->arch.regs.nip, vcpu->arch.shregs.msr, vcpu->arch.trap);
 	for (r = 0; r < 16; ++r)
 		pr_err("r%2d = %.16lx  r%d = %.16lx\n",
 		       r, kvmppc_get_gpr(vcpu, r),
 		       r+16, kvmppc_get_gpr(vcpu, r+16));
 	pr_err("ctr = %.16lx  lr  = %.16lx\n",
-	       vcpu->arch.ctr, vcpu->arch.lr);
+	       vcpu->arch.regs.ctr, vcpu->arch.regs.link);
 	pr_err("srr0 = %.16llx srr1 = %.16llx\n",
 	       vcpu->arch.shregs.srr0, vcpu->arch.shregs.srr1);
 	pr_err("sprg0 = %.16llx sprg1 = %.16llx\n",
@@ -385,7 +411,7 @@ static void kvmppc_dump_regs(struct kvm_vcpu *vcpu)
 	pr_err("sprg2 = %.16llx sprg3 = %.16llx\n",
 	       vcpu->arch.shregs.sprg2, vcpu->arch.shregs.sprg3);
 	pr_err("cr = %.8x  xer = %.16lx  dsisr = %.8x\n",
-	       vcpu->arch.cr, vcpu->arch.xer, vcpu->arch.shregs.dsisr);
+	       vcpu->arch.cr, vcpu->arch.regs.xer, vcpu->arch.shregs.dsisr);
 	pr_err("dar = %.16llx\n", vcpu->arch.shregs.dar);
 	pr_err("fault dar = %.16lx dsisr = %.8x\n",
 	       vcpu->arch.fault_dar, vcpu->arch.fault_dsisr);
@@ -1526,6 +1552,9 @@ static int kvmppc_get_one_reg_hv(struct kvm_vcpu *vcpu, u64 id,
 		*val = get_reg_val(id, vcpu->arch.dec_expires +
 				   vcpu->arch.vcore->tb_offset);
 		break;
+	case KVM_REG_PPC_ONLINE:
+		*val = get_reg_val(id, vcpu->arch.online);
+		break;
 	default:
 		r = -EINVAL;
 		break;
@@ -1757,6 +1786,14 @@ static int kvmppc_set_one_reg_hv(struct kvm_vcpu *vcpu, u64 id,
 		vcpu->arch.dec_expires = set_reg_val(id, *val) -
 			vcpu->arch.vcore->tb_offset;
 		break;
+	case KVM_REG_PPC_ONLINE:
+		i = set_reg_val(id, *val);
+		if (i && !vcpu->arch.online)
+			atomic_inc(&vcpu->arch.vcore->online_count);
+		else if (!i && vcpu->arch.online)
+			atomic_dec(&vcpu->arch.vcore->online_count);
+		vcpu->arch.online = i;
+		break;
 	default:
 		r = -EINVAL;
 		break;
@@ -2850,6 +2887,25 @@ static noinline void kvmppc_run_core(struct kvmppc_vcore *vc)
 		}
 	}
 
+	/*
+	 * On POWER8, set RWMR register.
+	 * Since it only affects PURR and SPURR, it doesn't affect
+	 * the host, so we don't save/restore the host value.
+	 */
+	if (is_power8) {
+		unsigned long rwmr_val = RWMR_RPA_P8_8THREAD;
+		int n_online = atomic_read(&vc->online_count);
+
+		/*
+		 * Use the 8-thread value if we're doing split-core
+		 * or if the vcore's online count looks bogus.
+		 */
+		if (split == 1 && threads_per_subcore == MAX_SMT_THREADS &&
+		    n_online >= 1 && n_online <= MAX_SMT_THREADS)
+			rwmr_val = p8_rwmr_values[n_online];
+		mtspr(SPRN_RWMR, rwmr_val);
+	}
+
 	/* Start all the threads */
 	active = 0;
 	for (sub = 0; sub < core_info.n_subcores; ++sub) {
@@ -2902,6 +2958,32 @@ static noinline void kvmppc_run_core(struct kvmppc_vcore *vc)
 	for (sub = 0; sub < core_info.n_subcores; ++sub)
 		spin_unlock(&core_info.vc[sub]->lock);
 
+	if (kvm_is_radix(vc->kvm)) {
+		int tmp = pcpu;
+
+		/*
+		 * Do we need to flush the process scoped TLB for the LPAR?
+		 *
+		 * 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 here.
+		 *
+		 * Hash must be flushed in realmode in order to use tlbiel.
+		 */
+		mtspr(SPRN_LPID, vc->kvm->arch.lpid);
+		isync();
+
+		if (cpu_has_feature(CPU_FTR_ARCH_300))
+			tmp &= ~0x3UL;
+
+		if (cpumask_test_cpu(tmp, &vc->kvm->arch.need_tlb_flush)) {
+			radix__local_flush_tlb_lpid_guest(vc->kvm->arch.lpid);
+			/* Clear the bit after the TLB flush */
+			cpumask_clear_cpu(tmp, &vc->kvm->arch.need_tlb_flush);
+		}
+	}
+
 	/*
 	 * Interrupts will be enabled once we get into the guest,
 	 * so tell lockdep that we're about to enable interrupts.
@@ -3356,6 +3438,15 @@ static int kvmppc_vcpu_run_hv(struct kvm_run *run, struct kvm_vcpu *vcpu)
 	}
 #endif
 
+	/*
+	 * Force online to 1 for the sake of old userspace which doesn't
+	 * set it.
+	 */
+	if (!vcpu->arch.online) {
+		atomic_inc(&vcpu->arch.vcore->online_count);
+		vcpu->arch.online = 1;
+	}
+
 	kvmppc_core_prepare_to_enter(vcpu);
 
 	/* No need to go into the guest when all we'll do is come back out */

arch/powerpc/kvm/book3s_hv_builtin.c

@@ -18,6 +18,7 @@
 #include <linux/cma.h>
 #include <linux/bitops.h>
 
+#include <asm/asm-prototypes.h>
 #include <asm/cputable.h>
 #include <asm/kvm_ppc.h>
 #include <asm/kvm_book3s.h>
@@ -211,9 +212,9 @@ long kvmppc_h_random(struct kvm_vcpu *vcpu)
 
 	/* Only need to do the expensive mfmsr() on radix */
 	if (kvm_is_radix(vcpu->kvm) && (mfmsr() & MSR_IR))
-		r = powernv_get_random_long(&vcpu->arch.gpr[4]);
+		r = powernv_get_random_long(&vcpu->arch.regs.gpr[4]);
 	else
-		r = powernv_get_random_real_mode(&vcpu->arch.gpr[4]);
+		r = powernv_get_random_real_mode(&vcpu->arch.regs.gpr[4]);
 	if (r)
 		return H_SUCCESS;
 
@@ -562,7 +563,7 @@ unsigned long kvmppc_rm_h_xirr_x(struct kvm_vcpu *vcpu)
 {
 	if (!kvmppc_xics_enabled(vcpu))
 		return H_TOO_HARD;
-	vcpu->arch.gpr[5] = get_tb();
+	vcpu->arch.regs.gpr[5] = get_tb();
 	if (xive_enabled()) {
 		if (is_rm())
 			return xive_rm_h_xirr(vcpu);
@@ -633,7 +634,19 @@ int kvmppc_rm_h_eoi(struct kvm_vcpu *vcpu, unsigned long xirr)
 
 void kvmppc_bad_interrupt(struct pt_regs *regs)
 {
-	die("Bad interrupt in KVM entry/exit code", regs, SIGABRT);
+	/*
+	 * 100 could happen at any time, 200 can happen due to invalid real
+	 * address access for example (or any time due to a hardware problem).
+	 */
+	if (TRAP(regs) == 0x100) {
+		get_paca()->in_nmi++;
+		system_reset_exception(regs);
+		get_paca()->in_nmi--;
+	} else if (TRAP(regs) == 0x200) {
+		machine_check_exception(regs);
+	} else {
+		die("Bad interrupt in KVM entry/exit code", regs, SIGABRT);
+	}
 	panic("Bad KVM trap");
 }
 

arch/powerpc/kvm/book3s_hv_interrupts.S

@@ -137,7 +137,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300)
 /*
  * We return here in virtual mode after the guest exits
  * with something that we can't handle in real mode.
- * Interrupts are enabled again at this point.
+ * Interrupts are still hard-disabled.
  */
 
 	/*

arch/powerpc/kvm/book3s_hv_rm_mmu.c

@@ -418,7 +418,8 @@ long kvmppc_h_enter(struct kvm_vcpu *vcpu, unsigned long flags,
 		    long pte_index, unsigned long pteh, unsigned long ptel)
 {
 	return kvmppc_do_h_enter(vcpu->kvm, flags, pte_index, pteh, ptel,
-				 vcpu->arch.pgdir, true, &vcpu->arch.gpr[4]);
+				 vcpu->arch.pgdir, true,
+				 &vcpu->arch.regs.gpr[4]);
 }
 
 #ifdef __BIG_ENDIAN__
@@ -434,24 +435,6 @@ static inline int is_mmio_hpte(unsigned long v, unsigned long r)
 		(HPTE_R_KEY_HI | HPTE_R_KEY_LO));
 }
 
-static inline int try_lock_tlbie(unsigned int *lock)
-{
-	unsigned int tmp, old;
-	unsigned int token = LOCK_TOKEN;
-
-	asm volatile("1:lwarx	%1,0,%2\n"
-		     "	cmpwi	cr0,%1,0\n"
-		     "	bne	2f\n"
-		     "  stwcx.	%3,0,%2\n"
-		     "	bne-	1b\n"
-		     "  isync\n"
-		     "2:"
-		     : "=&r" (tmp), "=&r" (old)
-		     : "r" (lock), "r" (token)
-		     : "cc", "memory");
-	return old == 0;
-}
-
 static void do_tlbies(struct kvm *kvm, unsigned long *rbvalues,
 		      long npages, int global, bool need_sync)
 {
@@ -463,8 +446,6 @@ static void do_tlbies(struct kvm *kvm, unsigned long *rbvalues,
 	 * the RS field, this is backwards-compatible with P7 and P8.
 	 */
 	if (global) {
-		while (!try_lock_tlbie(&kvm->arch.tlbie_lock))
-			cpu_relax();
 		if (need_sync)
 			asm volatile("ptesync" : : : "memory");
 		for (i = 0; i < npages; ++i) {
@@ -483,7 +464,6 @@ static void do_tlbies(struct kvm *kvm, unsigned long *rbvalues,
 		}
 
 		asm volatile("eieio; tlbsync; ptesync" : : : "memory");
-		kvm->arch.tlbie_lock = 0;
 	} else {
 		if (need_sync)
 			asm volatile("ptesync" : : : "memory");
@@ -561,13 +541,13 @@ long kvmppc_h_remove(struct kvm_vcpu *vcpu, unsigned long flags,
 		     unsigned long pte_index, unsigned long avpn)
 {
 	return kvmppc_do_h_remove(vcpu->kvm, flags, pte_index, avpn,
-				  &vcpu->arch.gpr[4]);
+				  &vcpu->arch.regs.gpr[4]);
 }
 
 long kvmppc_h_bulk_remove(struct kvm_vcpu *vcpu)
 {
 	struct kvm *kvm = vcpu->kvm;
-	unsigned long *args = &vcpu->arch.gpr[4];
+	unsigned long *args = &vcpu->arch.regs.gpr[4];
 	__be64 *hp, *hptes[4];
 	unsigned long tlbrb[4];
 	long int i, j, k, n, found, indexes[4];
@@ -787,8 +767,8 @@ long kvmppc_h_read(struct kvm_vcpu *vcpu, unsigned long flags,
 			r = rev[i].guest_rpte | (r & (HPTE_R_R | HPTE_R_C));
 			r &= ~HPTE_GR_RESERVED;
 		}
-		vcpu->arch.gpr[4 + i * 2] = v;
-		vcpu->arch.gpr[5 + i * 2] = r;
+		vcpu->arch.regs.gpr[4 + i * 2] = v;
+		vcpu->arch.regs.gpr[5 + i * 2] = r;
 	}
 	return H_SUCCESS;
 }
@@ -834,7 +814,7 @@ long kvmppc_h_clear_ref(struct kvm_vcpu *vcpu, unsigned long flags,
 			}
 		}
 	}
-	vcpu->arch.gpr[4] = gr;
+	vcpu->arch.regs.gpr[4] = gr;
 	ret = H_SUCCESS;
  out:
 	unlock_hpte(hpte, v & ~HPTE_V_HVLOCK);
@@ -881,7 +861,7 @@ long kvmppc_h_clear_mod(struct kvm_vcpu *vcpu, unsigned long flags,
 			kvmppc_set_dirty_from_hpte(kvm, v, gr);
 		}
 	}
-	vcpu->arch.gpr[4] = gr;
+	vcpu->arch.regs.gpr[4] = gr;
 	ret = H_SUCCESS;
  out:
 	unlock_hpte(hpte, v & ~HPTE_V_HVLOCK);

arch/powerpc/kvm/book3s_hv_rm_xics.c

@@ -517,7 +517,7 @@ unsigned long xics_rm_h_xirr(struct kvm_vcpu *vcpu)
 	} while (!icp_rm_try_update(icp, old_state, new_state));
 
 	/* Return the result in GPR4 */
-	vcpu->arch.gpr[4] = xirr;
+	vcpu->arch.regs.gpr[4] = xirr;
 
 	return check_too_hard(xics, icp);
 }

arch/powerpc/kvm/book3s_hv_rmhandlers.S

@@ -39,8 +39,6 @@ BEGIN_FTR_SECTION;				\
 	extsw	reg, reg;			\
 END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_300)
 
-#define VCPU_GPRS_TM(reg) (((reg) * ULONG_SIZE) + VCPU_GPR_TM)
-
 /* Values in HSTATE_NAPPING(r13) */
 #define NAPPING_CEDE	1
 #define NAPPING_NOVCPU	2
@@ -639,6 +637,10 @@ kvmppc_hv_entry:
 	/* Primary thread switches to guest partition. */
 	cmpwi	r6,0
 	bne	10f
+
+	/* Radix has already switched LPID and flushed core TLB */
+	bne	cr7, 22f
+
 	lwz	r7,KVM_LPID(r9)
 BEGIN_FTR_SECTION
 	ld	r6,KVM_SDR1(r9)
@@ -650,7 +652,7 @@ END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_300)
 	mtspr	SPRN_LPID,r7
 	isync
 
-	/* See if we need to flush the TLB */
+	/* See if we need to flush the TLB. Hash has to be done in RM */
 	lhz	r6,PACAPACAINDEX(r13)	/* test_bit(cpu, need_tlb_flush) */
 BEGIN_FTR_SECTION
 	/*
@@ -677,15 +679,10 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300)
 	li	r7,0x800		/* IS field = 0b10 */
 	ptesync
 	li	r0,0			/* RS for P9 version of tlbiel */
-	bne	cr7, 29f
 28:	tlbiel	r7			/* On P9, rs=0, RIC=0, PRS=0, R=0 */
 	addi	r7,r7,0x1000
 	bdnz	28b
-	b	30f
-29:	PPC_TLBIEL(7,0,2,1,1)		/* for radix, RIC=2, PRS=1, R=1 */
-	addi	r7,r7,0x1000
-	bdnz	29b
-30:	ptesync
+	ptesync
 23:	ldarx	r7,0,r6			/* clear the bit after TLB flushed */
 	andc	r7,r7,r8
 	stdcx.	r7,0,r6
@@ -799,7 +796,10 @@ END_FTR_SECTION(CPU_FTR_TM | CPU_FTR_P9_TM_HV_ASSIST, 0)
 	/*
 	 * NOTE THAT THIS TRASHES ALL NON-VOLATILE REGISTERS INCLUDING CR
 	 */
-	bl	kvmppc_restore_tm
+	mr      r3, r4
+	ld      r4, VCPU_MSR(r3)
+	bl	kvmppc_restore_tm_hv
+	ld	r4, HSTATE_KVM_VCPU(r13)
 91:
 #endif
 
@@ -1783,7 +1783,10 @@ END_FTR_SECTION(CPU_FTR_TM | CPU_FTR_P9_TM_HV_ASSIST, 0)
 	/*
 	 * NOTE THAT THIS TRASHES ALL NON-VOLATILE REGISTERS INCLUDING CR
 	 */
-	bl	kvmppc_save_tm
+	mr      r3, r9
+	ld      r4, VCPU_MSR(r3)
+	bl	kvmppc_save_tm_hv
+	ld	r9, HSTATE_KVM_VCPU(r13)
 91:
 #endif
 
@@ -2686,8 +2689,9 @@ END_FTR_SECTION(CPU_FTR_TM | CPU_FTR_P9_TM_HV_ASSIST, 0)
 	/*
 	 * NOTE THAT THIS TRASHES ALL NON-VOLATILE REGISTERS INCLUDING CR
 	 */
-	ld	r9, HSTATE_KVM_VCPU(r13)
-	bl	kvmppc_save_tm
+	ld	r3, HSTATE_KVM_VCPU(r13)
+	ld      r4, VCPU_MSR(r3)
+	bl	kvmppc_save_tm_hv
 91:
 #endif
 
@@ -2805,7 +2809,10 @@ END_FTR_SECTION(CPU_FTR_TM | CPU_FTR_P9_TM_HV_ASSIST, 0)
 	/*
 	 * NOTE THAT THIS TRASHES ALL NON-VOLATILE REGISTERS INCLUDING CR
 	 */
-	bl	kvmppc_restore_tm
+	mr      r3, r4
+	ld      r4, VCPU_MSR(r3)
+	bl	kvmppc_restore_tm_hv
+	ld	r4, HSTATE_KVM_VCPU(r13)
 91:
 #endif
 
@@ -3126,11 +3133,22 @@ END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC)
 #ifdef CONFIG_PPC_TRANSACTIONAL_MEM
 /*
  * Save transactional state and TM-related registers.
- * Called with r9 pointing to the vcpu struct.
+ * Called with r3 pointing to the vcpu struct and r4 containing
+ * the guest MSR value.
  * This can modify all checkpointed registers, but
- * restores r1, r2 and r9 (vcpu pointer) before exit.
+ * restores r1 and r2 before exit.
  */
-kvmppc_save_tm:
+kvmppc_save_tm_hv:
+	/* See if we need to handle fake suspend mode */
+BEGIN_FTR_SECTION
+	b	__kvmppc_save_tm
+END_FTR_SECTION_IFCLR(CPU_FTR_P9_TM_HV_ASSIST)
+
+	lbz	r0, HSTATE_FAKE_SUSPEND(r13) /* Were we fake suspended? */
+	cmpwi	r0, 0
+	beq	__kvmppc_save_tm
+
+	/* The following code handles the fake_suspend = 1 case */
 	mflr	r0
 	std	r0, PPC_LR_STKOFF(r1)
 	stdu	r1, -PPC_MIN_STKFRM(r1)
@@ -3141,59 +3159,37 @@ kvmppc_save_tm:
 	rldimi	r8, r0, MSR_TM_LG, 63-MSR_TM_LG
 	mtmsrd	r8
 
-	ld	r5, VCPU_MSR(r9)
-	rldicl. r5, r5, 64 - MSR_TS_S_LG, 62
-	beq	1f	/* TM not active in guest. */
-
-	std	r1, HSTATE_HOST_R1(r13)
-	li	r3, TM_CAUSE_KVM_RESCHED
-
-BEGIN_FTR_SECTION
-	lbz	r0, HSTATE_FAKE_SUSPEND(r13) /* Were we fake suspended? */
-	cmpwi	r0, 0
-	beq	3f
 	rldicl. r8, r8, 64 - MSR_TS_S_LG, 62 /* Did we actually hrfid? */
 	beq	4f
-BEGIN_FTR_SECTION_NESTED(96)
+BEGIN_FTR_SECTION
 	bl	pnv_power9_force_smt4_catch
-END_FTR_SECTION_NESTED(CPU_FTR_P9_TM_XER_SO_BUG, CPU_FTR_P9_TM_XER_SO_BUG, 96)
+END_FTR_SECTION_IFSET(CPU_FTR_P9_TM_XER_SO_BUG)
 	nop
-	b	6f
-3:
-	/* Emulation of the treclaim instruction needs TEXASR before treclaim */
-	mfspr	r6, SPRN_TEXASR
-	std	r6, VCPU_ORIG_TEXASR(r9)
-6:
-END_FTR_SECTION_IFSET(CPU_FTR_P9_TM_HV_ASSIST)
 
-	/* Clear the MSR RI since r1, r13 are all going to be foobar. */
+	std	r1, HSTATE_HOST_R1(r13)
+
+	/* Clear the MSR RI since r1, r13 may be foobar. */
 	li	r5, 0
 	mtmsrd	r5, 1
 
-	/* All GPRs are volatile at this point. */
+	/* We have to treclaim here because that's the only way to do S->N */
+	li	r3, TM_CAUSE_KVM_RESCHED
 	TRECLAIM(R3)
 
-	/* Temporarily store r13 and r9 so we have some regs to play with */
-	SET_SCRATCH0(r13)
-	GET_PACA(r13)
-	std	r9, PACATMSCRATCH(r13)
-
-	/* If doing TM emulation on POWER9 DD2.2, check for fake suspend mode */
-BEGIN_FTR_SECTION
-	lbz	r9, HSTATE_FAKE_SUSPEND(r13)
-	cmpwi	r9, 0
-	beq	2f
 	/*
 	 * We were in fake suspend, so we are not going to save the
 	 * register state as the guest checkpointed state (since
 	 * we already have it), therefore we can now use any volatile GPR.
 	 */
-	/* Reload stack pointer and TOC. */
+	/* Reload PACA pointer, stack pointer and TOC. */
+	GET_PACA(r13)
 	ld	r1, HSTATE_HOST_R1(r13)
 	ld	r2, PACATOC(r13)
+
 	/* Set MSR RI now we have r1 and r13 back. */
 	li	r5, MSR_RI
 	mtmsrd	r5, 1
+
 	HMT_MEDIUM
 	ld	r6, HSTATE_DSCR(r13)
 	mtspr	SPRN_DSCR, r6
@@ -3208,85 +3204,9 @@ END_FTR_SECTION_NESTED(CPU_FTR_P9_TM_XER_SO_BUG, CPU_FTR_P9_TM_XER_SO_BUG, 96)
 	li	r0, PSSCR_FAKE_SUSPEND
 	andc	r3, r3, r0
 	mtspr	SPRN_PSSCR, r3
-	ld	r9, HSTATE_KVM_VCPU(r13)
-	/* Don't save TEXASR, use value from last exit in real suspend state */
-	b	11f
-2:
-END_FTR_SECTION_IFSET(CPU_FTR_P9_TM_HV_ASSIST)
 
+	/* Don't save TEXASR, use value from last exit in real suspend state */
 	ld	r9, HSTATE_KVM_VCPU(r13)
-
-	/* Get a few more GPRs free. */
-	std	r29, VCPU_GPRS_TM(29)(r9)
-	std	r30, VCPU_GPRS_TM(30)(r9)
-	std	r31, VCPU_GPRS_TM(31)(r9)
-
-	/* Save away PPR and DSCR soon so don't run with user values. */
-	mfspr	r31, SPRN_PPR
-	HMT_MEDIUM
-	mfspr	r30, SPRN_DSCR
-	ld	r29, HSTATE_DSCR(r13)
-	mtspr	SPRN_DSCR, r29
-
-	/* Save all but r9, r13 & r29-r31 */
-	reg = 0
-	.rept	29
-	.if (reg != 9) && (reg != 13)
-	std	reg, VCPU_GPRS_TM(reg)(r9)
-	.endif
-	reg = reg + 1
-	.endr
-	/* ... now save r13 */
-	GET_SCRATCH0(r4)
-	std	r4, VCPU_GPRS_TM(13)(r9)
-	/* ... and save r9 */
-	ld	r4, PACATMSCRATCH(r13)
-	std	r4, VCPU_GPRS_TM(9)(r9)
-
-	/* Reload stack pointer and TOC. */
-	ld	r1, HSTATE_HOST_R1(r13)
-	ld	r2, PACATOC(r13)
-
-	/* Set MSR RI now we have r1 and r13 back. */
-	li	r5, MSR_RI
-	mtmsrd	r5, 1
-
-	/* Save away checkpinted SPRs. */
-	std	r31, VCPU_PPR_TM(r9)
-	std	r30, VCPU_DSCR_TM(r9)
-	mflr	r5
-	mfcr	r6
-	mfctr	r7
-	mfspr	r8, SPRN_AMR
-	mfspr	r10, SPRN_TAR
-	mfxer	r11
-	std	r5, VCPU_LR_TM(r9)
-	stw	r6, VCPU_CR_TM(r9)
-	std	r7, VCPU_CTR_TM(r9)
-	std	r8, VCPU_AMR_TM(r9)
-	std	r10, VCPU_TAR_TM(r9)
-	std	r11, VCPU_XER_TM(r9)
-
-	/* Restore r12 as trap number. */
-	lwz	r12, VCPU_TRAP(r9)
-
-	/* Save FP/VSX. */
-	addi	r3, r9, VCPU_FPRS_TM
-	bl	store_fp_state
-	addi	r3, r9, VCPU_VRS_TM
-	bl	store_vr_state
-	mfspr	r6, SPRN_VRSAVE
-	stw	r6, VCPU_VRSAVE_TM(r9)
-1:
-	/*
-	 * We need to save these SPRs after the treclaim so that the software
-	 * error code is recorded correctly in the TEXASR.  Also the user may
-	 * change these outside of a transaction, so they must always be
-	 * context switched.
-	 */
-	mfspr	r7, SPRN_TEXASR
-	std	r7, VCPU_TEXASR(r9)
-11:
 	mfspr	r5, SPRN_TFHAR
 	mfspr	r6, SPRN_TFIAR
 	std	r5, VCPU_TFHAR(r9)
@@ -3299,149 +3219,63 @@ END_FTR_SECTION_IFSET(CPU_FTR_P9_TM_HV_ASSIST)
 
 /*
  * Restore transactional state and TM-related registers.
- * Called with r4 pointing to the vcpu struct.
+ * Called with r3 pointing to the vcpu struct
+ * and r4 containing the guest MSR value.
  * This potentially modifies all checkpointed registers.
- * It restores r1, r2, r4 from the PACA.
+ * It restores r1 and r2 from the PACA.
  */
-kvmppc_restore_tm:
+kvmppc_restore_tm_hv:
+	/*
+	 * If we are doing TM emulation for the guest on a POWER9 DD2,
+	 * then we don't actually do a trechkpt -- we either set up
+	 * fake-suspend mode, or emulate a TM rollback.
+	 */
+BEGIN_FTR_SECTION
+	b	__kvmppc_restore_tm
+END_FTR_SECTION_IFCLR(CPU_FTR_P9_TM_HV_ASSIST)
 	mflr	r0
 	std	r0, PPC_LR_STKOFF(r1)
 
-	/* Turn on TM/FP/VSX/VMX so we can restore them. */
+	li	r0, 0
+	stb	r0, HSTATE_FAKE_SUSPEND(r13)
+
+	/* Turn on TM so we can restore TM SPRs */
 	mfmsr	r5
-	li	r6, MSR_TM >> 32
-	sldi	r6, r6, 32
-	or	r5, r5, r6
-	ori	r5, r5, MSR_FP
-	oris	r5, r5, (MSR_VEC | MSR_VSX)@h
+	li	r0, 1
+	rldimi	r5, r0, MSR_TM_LG, 63-MSR_TM_LG
 	mtmsrd	r5
 
 	/*
 	 * The user may change these outside of a transaction, so they must
 	 * always be context switched.
 	 */
-	ld	r5, VCPU_TFHAR(r4)
-	ld	r6, VCPU_TFIAR(r4)
-	ld	r7, VCPU_TEXASR(r4)
+	ld	r5, VCPU_TFHAR(r3)
+	ld	r6, VCPU_TFIAR(r3)
+	ld	r7, VCPU_TEXASR(r3)
 	mtspr	SPRN_TFHAR, r5
 	mtspr	SPRN_TFIAR, r6
 	mtspr	SPRN_TEXASR, r7
 
-	li	r0, 0
-	stb	r0, HSTATE_FAKE_SUSPEND(r13)
-	ld	r5, VCPU_MSR(r4)
-	rldicl. r5, r5, 64 - MSR_TS_S_LG, 62
+	rldicl. r5, r4, 64 - MSR_TS_S_LG, 62
 	beqlr		/* TM not active in guest */
-	std	r1, HSTATE_HOST_R1(r13)
 
-	/* Make sure the failure summary is set, otherwise we'll program check
-	 * when we trechkpt.  It's possible that this might have been not set
-	 * on a kvmppc_set_one_reg() call but we shouldn't let this crash the
-	 * host.
-	 */
+	/* Make sure the failure summary is set */
 	oris	r7, r7, (TEXASR_FS)@h
 	mtspr	SPRN_TEXASR, r7
 
-	/*
-	 * If we are doing TM emulation for the guest on a POWER9 DD2,
-	 * then we don't actually do a trechkpt -- we either set up
-	 * fake-suspend mode, or emulate a TM rollback.
-	 */
-BEGIN_FTR_SECTION
-	b	.Ldo_tm_fake_load
-END_FTR_SECTION_IFSET(CPU_FTR_P9_TM_HV_ASSIST)
-
-	/*
-	 * We need to load up the checkpointed state for the guest.
-	 * We need to do this early as it will blow away any GPRs, VSRs and
-	 * some SPRs.
-	 */
-
-	mr	r31, r4
-	addi	r3, r31, VCPU_FPRS_TM
-	bl	load_fp_state
-	addi	r3, r31, VCPU_VRS_TM
-	bl	load_vr_state
-	mr	r4, r31
-	lwz	r7, VCPU_VRSAVE_TM(r4)
-	mtspr	SPRN_VRSAVE, r7
-
-	ld	r5, VCPU_LR_TM(r4)
-	lwz	r6, VCPU_CR_TM(r4)
-	ld	r7, VCPU_CTR_TM(r4)
-	ld	r8, VCPU_AMR_TM(r4)
-	ld	r9, VCPU_TAR_TM(r4)
-	ld	r10, VCPU_XER_TM(r4)
-	mtlr	r5
-	mtcr	r6
-	mtctr	r7
-	mtspr	SPRN_AMR, r8
-	mtspr	SPRN_TAR, r9
-	mtxer	r10
-
-	/*
-	 * Load up PPR and DSCR values but don't put them in the actual SPRs
-	 * till the last moment to avoid running with userspace PPR and DSCR for
-	 * too long.
-	 */
-	ld	r29, VCPU_DSCR_TM(r4)
-	ld	r30, VCPU_PPR_TM(r4)
-
-	std	r2, PACATMSCRATCH(r13) /* Save TOC */
-
-	/* Clear the MSR RI since r1, r13 are all going to be foobar. */
-	li	r5, 0
-	mtmsrd	r5, 1
-
-	/* Load GPRs r0-r28 */
-	reg = 0
-	.rept	29
-	ld	reg, VCPU_GPRS_TM(reg)(r31)
-	reg = reg + 1
-	.endr
-
-	mtspr	SPRN_DSCR, r29
-	mtspr	SPRN_PPR, r30
-
-	/* Load final GPRs */
-	ld	29, VCPU_GPRS_TM(29)(r31)
-	ld	30, VCPU_GPRS_TM(30)(r31)
-	ld	31, VCPU_GPRS_TM(31)(r31)
-
-	/* TM checkpointed state is now setup.  All GPRs are now volatile. */
-	TRECHKPT
-
-	/* Now let's get back the state we need. */
-	HMT_MEDIUM
-	GET_PACA(r13)
-	ld	r29, HSTATE_DSCR(r13)
-	mtspr	SPRN_DSCR, r29
-	ld	r4, HSTATE_KVM_VCPU(r13)
-	ld	r1, HSTATE_HOST_R1(r13)
-	ld	r2, PACATMSCRATCH(r13)
-
-	/* Set the MSR RI since we have our registers back. */
-	li	r5, MSR_RI
-	mtmsrd	r5, 1
-9:
-	ld	r0, PPC_LR_STKOFF(r1)
-	mtlr	r0
-	blr
-
-.Ldo_tm_fake_load:
 	cmpwi	r5, 1		/* check for suspended state */
 	bgt	10f
 	stb	r5, HSTATE_FAKE_SUSPEND(r13)
-	b	9b		/* and return */
+	b	9f		/* and return */
 10:	stdu	r1, -PPC_MIN_STKFRM(r1)
 	/* guest is in transactional state, so simulate rollback */
-	mr	r3, r4
 	bl	kvmhv_emulate_tm_rollback
 	nop
-	ld      r4, HSTATE_KVM_VCPU(r13) /* our vcpu pointer has been trashed */
 	addi	r1, r1, PPC_MIN_STKFRM
-	b	9b
-#endif
+9:	ld	r0, PPC_LR_STKOFF(r1)
+	mtlr	r0
+	blr
+#endif /* CONFIG_PPC_TRANSACTIONAL_MEM */
 
 /*
  * We come here if we get any exception or interrupt while we are
@@ -3572,6 +3406,8 @@ END_MMU_FTR_SECTION_IFSET(MMU_FTR_TYPE_RADIX)
 	bcl	20, 31, .+4
 5:	mflr	r3
 	addi	r3, r3, 9f - 5b
+	li	r4, -1
+	rldimi	r3, r4, 62, 0	/* ensure 0xc000000000000000 bits are set */
 	ld	r4, PACAKMSR(r13)
 	mtspr	SPRN_SRR0, r3
 	mtspr	SPRN_SRR1, r4

arch/powerpc/kvm/book3s_hv_tm.c

@@ -19,7 +19,7 @@ static void emulate_tx_failure(struct kvm_vcpu *vcpu, u64 failure_cause)
 	u64 texasr, tfiar;
 	u64 msr = vcpu->arch.shregs.msr;
 
-	tfiar = vcpu->arch.pc & ~0x3ull;
+	tfiar = vcpu->arch.regs.nip & ~0x3ull;
 	texasr = (failure_cause << 56) | TEXASR_ABORT | TEXASR_FS | TEXASR_EXACT;
 	if (MSR_TM_SUSPENDED(vcpu->arch.shregs.msr))
 		texasr |= TEXASR_SUSP;
@@ -57,8 +57,8 @@ int kvmhv_p9_tm_emulation(struct kvm_vcpu *vcpu)
 			       (newmsr & MSR_TM)));
 		newmsr = sanitize_msr(newmsr);
 		vcpu->arch.shregs.msr = newmsr;
-		vcpu->arch.cfar = vcpu->arch.pc - 4;
-		vcpu->arch.pc = vcpu->arch.shregs.srr0;
+		vcpu->arch.cfar = vcpu->arch.regs.nip - 4;
+		vcpu->arch.regs.nip = vcpu->arch.shregs.srr0;
 		return RESUME_GUEST;
 
 	case PPC_INST_RFEBB:
@@ -90,8 +90,8 @@ int kvmhv_p9_tm_emulation(struct kvm_vcpu *vcpu)
 		vcpu->arch.bescr = bescr;
 		msr = (msr & ~MSR_TS_MASK) | MSR_TS_T;
 		vcpu->arch.shregs.msr = msr;
-		vcpu->arch.cfar = vcpu->arch.pc - 4;
-		vcpu->arch.pc = vcpu->arch.ebbrr;
+		vcpu->arch.cfar = vcpu->arch.regs.nip - 4;
+		vcpu->arch.regs.nip = vcpu->arch.ebbrr;
 		return RESUME_GUEST;
 
 	case PPC_INST_MTMSRD:

arch/powerpc/kvm/book3s_hv_tm_builtin.c

@@ -35,8 +35,8 @@ int kvmhv_p9_tm_emulation_early(struct kvm_vcpu *vcpu)
 			return 0;
 		newmsr = sanitize_msr(newmsr);
 		vcpu->arch.shregs.msr = newmsr;
-		vcpu->arch.cfar = vcpu->arch.pc - 4;
-		vcpu->arch.pc = vcpu->arch.shregs.srr0;
+		vcpu->arch.cfar = vcpu->arch.regs.nip - 4;
+		vcpu->arch.regs.nip = vcpu->arch.shregs.srr0;
 		return 1;
 
 	case PPC_INST_RFEBB:
@@ -58,8 +58,8 @@ int kvmhv_p9_tm_emulation_early(struct kvm_vcpu *vcpu)
 		mtspr(SPRN_BESCR, bescr);
 		msr = (msr & ~MSR_TS_MASK) | MSR_TS_T;
 		vcpu->arch.shregs.msr = msr;
-		vcpu->arch.cfar = vcpu->arch.pc - 4;
-		vcpu->arch.pc = mfspr(SPRN_EBBRR);
+		vcpu->arch.cfar = vcpu->arch.regs.nip - 4;
+		vcpu->arch.regs.nip = mfspr(SPRN_EBBRR);
 		return 1;
 
 	case PPC_INST_MTMSRD:
@@ -103,7 +103,7 @@ int kvmhv_p9_tm_emulation_early(struct kvm_vcpu *vcpu)
 void kvmhv_emulate_tm_rollback(struct kvm_vcpu *vcpu)
 {
 	vcpu->arch.shregs.msr &= ~MSR_TS_MASK;	/* go to N state */
-	vcpu->arch.pc = vcpu->arch.tfhar;
+	vcpu->arch.regs.nip = vcpu->arch.tfhar;
 	copy_from_checkpoint(vcpu);
 	vcpu->arch.cr = (vcpu->arch.cr & 0x0fffffff) | 0xa0000000;
 }

arch/powerpc/kvm/book3s_pr.c

@@ -42,6 +42,8 @@
 #include <linux/highmem.h>
 #include <linux/module.h>
 #include <linux/miscdevice.h>
+#include <asm/asm-prototypes.h>
+#include <asm/tm.h>
 
 #include "book3s.h"
 
@@ -53,7 +55,9 @@
 
 static int kvmppc_handle_ext(struct kvm_vcpu *vcpu, unsigned int exit_nr,
 			     ulong msr);
-static void kvmppc_giveup_fac(struct kvm_vcpu *vcpu, ulong fac);
+#ifdef CONFIG_PPC_BOOK3S_64
+static int kvmppc_handle_fac(struct kvm_vcpu *vcpu, ulong fac);
+#endif
 
 /* Some compatibility defines */
 #ifdef CONFIG_PPC_BOOK3S_32
@@ -114,6 +118,8 @@ static void kvmppc_core_vcpu_load_pr(struct kvm_vcpu *vcpu, int cpu)
 
 	if (kvmppc_is_split_real(vcpu))
 		kvmppc_fixup_split_real(vcpu);
+
+	kvmppc_restore_tm_pr(vcpu);
 }
 
 static void kvmppc_core_vcpu_put_pr(struct kvm_vcpu *vcpu)
@@ -133,6 +139,7 @@ static void kvmppc_core_vcpu_put_pr(struct kvm_vcpu *vcpu)
 
 	kvmppc_giveup_ext(vcpu, MSR_FP | MSR_VEC | MSR_VSX);
 	kvmppc_giveup_fac(vcpu, FSCR_TAR_LG);
+	kvmppc_save_tm_pr(vcpu);
 
 	/* Enable AIL if supported */
 	if (cpu_has_feature(CPU_FTR_HVMODE) &&
@@ -147,25 +154,25 @@ void kvmppc_copy_to_svcpu(struct kvm_vcpu *vcpu)
 {
 	struct kvmppc_book3s_shadow_vcpu *svcpu = svcpu_get(vcpu);
 
-	svcpu->gpr[0] = vcpu->arch.gpr[0];
-	svcpu->gpr[1] = vcpu->arch.gpr[1];
-	svcpu->gpr[2] = vcpu->arch.gpr[2];
-	svcpu->gpr[3] = vcpu->arch.gpr[3];
-	svcpu->gpr[4] = vcpu->arch.gpr[4];
-	svcpu->gpr[5] = vcpu->arch.gpr[5];
-	svcpu->gpr[6] = vcpu->arch.gpr[6];
-	svcpu->gpr[7] = vcpu->arch.gpr[7];
-	svcpu->gpr[8] = vcpu->arch.gpr[8];
-	svcpu->gpr[9] = vcpu->arch.gpr[9];
-	svcpu->gpr[10] = vcpu->arch.gpr[10];
-	svcpu->gpr[11] = vcpu->arch.gpr[11];
-	svcpu->gpr[12] = vcpu->arch.gpr[12];
-	svcpu->gpr[13] = vcpu->arch.gpr[13];
+	svcpu->gpr[0] = vcpu->arch.regs.gpr[0];
+	svcpu->gpr[1] = vcpu->arch.regs.gpr[1];
+	svcpu->gpr[2] = vcpu->arch.regs.gpr[2];
+	svcpu->gpr[3] = vcpu->arch.regs.gpr[3];
+	svcpu->gpr[4] = vcpu->arch.regs.gpr[4];
+	svcpu->gpr[5] = vcpu->arch.regs.gpr[5];
+	svcpu->gpr[6] = vcpu->arch.regs.gpr[6];
+	svcpu->gpr[7] = vcpu->arch.regs.gpr[7];
+	svcpu->gpr[8] = vcpu->arch.regs.gpr[8];
+	svcpu->gpr[9] = vcpu->arch.regs.gpr[9];
+	svcpu->gpr[10] = vcpu->arch.regs.gpr[10];
+	svcpu->gpr[11] = vcpu->arch.regs.gpr[11];
+	svcpu->gpr[12] = vcpu->arch.regs.gpr[12];
+	svcpu->gpr[13] = vcpu->arch.regs.gpr[13];
 	svcpu->cr  = vcpu->arch.cr;
-	svcpu->xer = vcpu->arch.xer;
-	svcpu->ctr = vcpu->arch.ctr;
-	svcpu->lr  = vcpu->arch.lr;
-	svcpu->pc  = vcpu->arch.pc;
+	svcpu->xer = vcpu->arch.regs.xer;
+	svcpu->ctr = vcpu->arch.regs.ctr;
+	svcpu->lr  = vcpu->arch.regs.link;
+	svcpu->pc  = vcpu->arch.regs.nip;
 #ifdef CONFIG_PPC_BOOK3S_64
 	svcpu->shadow_fscr = vcpu->arch.shadow_fscr;
 #endif
@@ -182,10 +189,45 @@ void kvmppc_copy_to_svcpu(struct kvm_vcpu *vcpu)
 	svcpu_put(svcpu);
 }
 
+static void kvmppc_recalc_shadow_msr(struct kvm_vcpu *vcpu)
+{
+	ulong guest_msr = kvmppc_get_msr(vcpu);
+	ulong smsr = guest_msr;
+
+	/* Guest MSR values */
+#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+	smsr &= MSR_FE0 | MSR_FE1 | MSR_SF | MSR_SE | MSR_BE | MSR_LE |
+		MSR_TM | MSR_TS_MASK;
+#else
+	smsr &= MSR_FE0 | MSR_FE1 | MSR_SF | MSR_SE | MSR_BE | MSR_LE;
+#endif
+	/* Process MSR values */
+	smsr |= MSR_ME | MSR_RI | MSR_IR | MSR_DR | MSR_PR | MSR_EE;
+	/* External providers the guest reserved */
+	smsr |= (guest_msr & vcpu->arch.guest_owned_ext);
+	/* 64-bit Process MSR values */
+#ifdef CONFIG_PPC_BOOK3S_64
+	smsr |= MSR_ISF | MSR_HV;
+#endif
+#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+	/*
+	 * in guest privileged state, we want to fail all TM transactions.
+	 * So disable MSR TM bit so that all tbegin. will be able to be
+	 * trapped into host.
+	 */
+	if (!(guest_msr & MSR_PR))
+		smsr &= ~MSR_TM;
+#endif
+	vcpu->arch.shadow_msr = smsr;
+}
+
 /* Copy data touched by real-mode code from shadow vcpu back to vcpu */
 void kvmppc_copy_from_svcpu(struct kvm_vcpu *vcpu)
 {
 	struct kvmppc_book3s_shadow_vcpu *svcpu = svcpu_get(vcpu);
+#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+	ulong old_msr;
+#endif
 
 	/*
 	 * Maybe we were already preempted and synced the svcpu from
@@ -194,25 +236,25 @@ void kvmppc_copy_from_svcpu(struct kvm_vcpu *vcpu)
 	if (!svcpu->in_use)
 		goto out;
 
-	vcpu->arch.gpr[0] = svcpu->gpr[0];
-	vcpu->arch.gpr[1] = svcpu->gpr[1];
-	vcpu->arch.gpr[2] = svcpu->gpr[2];
-	vcpu->arch.gpr[3] = svcpu->gpr[3];
-	vcpu->arch.gpr[4] = svcpu->gpr[4];
-	vcpu->arch.gpr[5] = svcpu->gpr[5];
-	vcpu->arch.gpr[6] = svcpu->gpr[6];
-	vcpu->arch.gpr[7] = svcpu->gpr[7];
-	vcpu->arch.gpr[8] = svcpu->gpr[8];
-	vcpu->arch.gpr[9] = svcpu->gpr[9];
-	vcpu->arch.gpr[10] = svcpu->gpr[10];
-	vcpu->arch.gpr[11] = svcpu->gpr[11];
-	vcpu->arch.gpr[12] = svcpu->gpr[12];
-	vcpu->arch.gpr[13] = svcpu->gpr[13];
+	vcpu->arch.regs.gpr[0] = svcpu->gpr[0];
+	vcpu->arch.regs.gpr[1] = svcpu->gpr[1];
+	vcpu->arch.regs.gpr[2] = svcpu->gpr[2];
+	vcpu->arch.regs.gpr[3] = svcpu->gpr[3];
+	vcpu->arch.regs.gpr[4] = svcpu->gpr[4];
+	vcpu->arch.regs.gpr[5] = svcpu->gpr[5];
+	vcpu->arch.regs.gpr[6] = svcpu->gpr[6];
+	vcpu->arch.regs.gpr[7] = svcpu->gpr[7];
+	vcpu->arch.regs.gpr[8] = svcpu->gpr[8];
+	vcpu->arch.regs.gpr[9] = svcpu->gpr[9];
+	vcpu->arch.regs.gpr[10] = svcpu->gpr[10];
+	vcpu->arch.regs.gpr[11] = svcpu->gpr[11];
+	vcpu->arch.regs.gpr[12] = svcpu->gpr[12];
+	vcpu->arch.regs.gpr[13] = svcpu->gpr[13];
 	vcpu->arch.cr  = svcpu->cr;
-	vcpu->arch.xer = svcpu->xer;
-	vcpu->arch.ctr = svcpu->ctr;
-	vcpu->arch.lr  = svcpu->lr;
-	vcpu->arch.pc  = svcpu->pc;
+	vcpu->arch.regs.xer = svcpu->xer;
+	vcpu->arch.regs.ctr = svcpu->ctr;
+	vcpu->arch.regs.link  = svcpu->lr;
+	vcpu->arch.regs.nip  = svcpu->pc;
 	vcpu->arch.shadow_srr1 = svcpu->shadow_srr1;
 	vcpu->arch.fault_dar   = svcpu->fault_dar;
 	vcpu->arch.fault_dsisr = svcpu->fault_dsisr;
@@ -228,12 +270,116 @@ void kvmppc_copy_from_svcpu(struct kvm_vcpu *vcpu)
 	to_book3s(vcpu)->vtb += get_vtb() - vcpu->arch.entry_vtb;
 	if (cpu_has_feature(CPU_FTR_ARCH_207S))
 		vcpu->arch.ic += mfspr(SPRN_IC) - vcpu->arch.entry_ic;
+
+#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+	/*
+	 * Unlike other MSR bits, MSR[TS]bits can be changed at guest without
+	 * notifying host:
+	 *  modified by unprivileged instructions like "tbegin"/"tend"/
+	 * "tresume"/"tsuspend" in PR KVM guest.
+	 *
+	 * It is necessary to sync here to calculate a correct shadow_msr.
+	 *
+	 * privileged guest's tbegin will be failed at present. So we
+	 * only take care of problem state guest.
+	 */
+	old_msr = kvmppc_get_msr(vcpu);
+	if (unlikely((old_msr & MSR_PR) &&
+		(vcpu->arch.shadow_srr1 & (MSR_TS_MASK)) !=
+				(old_msr & (MSR_TS_MASK)))) {
+		old_msr &= ~(MSR_TS_MASK);
+		old_msr |= (vcpu->arch.shadow_srr1 & (MSR_TS_MASK));
+		kvmppc_set_msr_fast(vcpu, old_msr);
+		kvmppc_recalc_shadow_msr(vcpu);
+	}
+#endif
+
 	svcpu->in_use = false;
 
 out:
 	svcpu_put(svcpu);
 }
 
+#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+void kvmppc_save_tm_sprs(struct kvm_vcpu *vcpu)
+{
+	tm_enable();
+	vcpu->arch.tfhar = mfspr(SPRN_TFHAR);
+	vcpu->arch.texasr = mfspr(SPRN_TEXASR);
+	vcpu->arch.tfiar = mfspr(SPRN_TFIAR);
+	tm_disable();
+}
+
+void kvmppc_restore_tm_sprs(struct kvm_vcpu *vcpu)
+{
+	tm_enable();
+	mtspr(SPRN_TFHAR, vcpu->arch.tfhar);
+	mtspr(SPRN_TEXASR, vcpu->arch.texasr);
+	mtspr(SPRN_TFIAR, vcpu->arch.tfiar);
+	tm_disable();
+}
+
+/* loadup math bits which is enabled at kvmppc_get_msr() but not enabled at
+ * hardware.
+ */
+static void kvmppc_handle_lost_math_exts(struct kvm_vcpu *vcpu)
+{
+	ulong exit_nr;
+	ulong ext_diff = (kvmppc_get_msr(vcpu) & ~vcpu->arch.guest_owned_ext) &
+		(MSR_FP | MSR_VEC | MSR_VSX);
+
+	if (!ext_diff)
+		return;
+
+	if (ext_diff == MSR_FP)
+		exit_nr = BOOK3S_INTERRUPT_FP_UNAVAIL;
+	else if (ext_diff == MSR_VEC)
+		exit_nr = BOOK3S_INTERRUPT_ALTIVEC;
+	else
+		exit_nr = BOOK3S_INTERRUPT_VSX;
+
+	kvmppc_handle_ext(vcpu, exit_nr, ext_diff);
+}
+
+void kvmppc_save_tm_pr(struct kvm_vcpu *vcpu)
+{
+	if (!(MSR_TM_ACTIVE(kvmppc_get_msr(vcpu)))) {
+		kvmppc_save_tm_sprs(vcpu);
+		return;
+	}
+
+	kvmppc_giveup_fac(vcpu, FSCR_TAR_LG);
+	kvmppc_giveup_ext(vcpu, MSR_VSX);
+
+	preempt_disable();
+	_kvmppc_save_tm_pr(vcpu, mfmsr());
+	preempt_enable();
+}
+
+void kvmppc_restore_tm_pr(struct kvm_vcpu *vcpu)
+{
+	if (!MSR_TM_ACTIVE(kvmppc_get_msr(vcpu))) {
+		kvmppc_restore_tm_sprs(vcpu);
+		if (kvmppc_get_msr(vcpu) & MSR_TM) {
+			kvmppc_handle_lost_math_exts(vcpu);
+			if (vcpu->arch.fscr & FSCR_TAR)
+				kvmppc_handle_fac(vcpu, FSCR_TAR_LG);
+		}
+		return;
+	}
+
+	preempt_disable();
+	_kvmppc_restore_tm_pr(vcpu, kvmppc_get_msr(vcpu));
+	preempt_enable();
+
+	if (kvmppc_get_msr(vcpu) & MSR_TM) {
+		kvmppc_handle_lost_math_exts(vcpu);
+		if (vcpu->arch.fscr & FSCR_TAR)
+			kvmppc_handle_fac(vcpu, FSCR_TAR_LG);
+	}
+}
+#endif
+
 static int kvmppc_core_check_requests_pr(struct kvm_vcpu *vcpu)
 {
 	int r = 1; /* Indicate we want to get back into the guest */
@@ -306,32 +452,29 @@ static void kvm_set_spte_hva_pr(struct kvm *kvm, unsigned long hva, pte_t pte)
 
 /*****************************************/
 
-static void kvmppc_recalc_shadow_msr(struct kvm_vcpu *vcpu)
-{
-	ulong guest_msr = kvmppc_get_msr(vcpu);
-	ulong smsr = guest_msr;
-
-	/* Guest MSR values */
-	smsr &= MSR_FE0 | MSR_FE1 | MSR_SF | MSR_SE | MSR_BE | MSR_LE;
-	/* Process MSR values */
-	smsr |= MSR_ME | MSR_RI | MSR_IR | MSR_DR | MSR_PR | MSR_EE;
-	/* External providers the guest reserved */
-	smsr |= (guest_msr & vcpu->arch.guest_owned_ext);
-	/* 64-bit Process MSR values */
-#ifdef CONFIG_PPC_BOOK3S_64
-	smsr |= MSR_ISF | MSR_HV;
-#endif
-	vcpu->arch.shadow_msr = smsr;
-}
-
 static void kvmppc_set_msr_pr(struct kvm_vcpu *vcpu, u64 msr)
 {
-	ulong old_msr = kvmppc_get_msr(vcpu);
+	ulong old_msr;
+
+	/* For PAPR guest, make sure MSR reflects guest mode */
+	if (vcpu->arch.papr_enabled)
+		msr = (msr & ~MSR_HV) | MSR_ME;
 
 #ifdef EXIT_DEBUG
 	printk(KERN_INFO "KVM: Set MSR to 0x%llx\n", msr);
 #endif
 
+#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+	/* We should never target guest MSR to TS=10 && PR=0,
+	 * since we always fail transaction for guest privilege
+	 * state.
+	 */
+	if (!(msr & MSR_PR) && MSR_TM_TRANSACTIONAL(msr))
+		kvmppc_emulate_tabort(vcpu,
+			TM_CAUSE_KVM_FAC_UNAV | TM_CAUSE_PERSISTENT);
+#endif
+
+	old_msr = kvmppc_get_msr(vcpu);
 	msr &= to_book3s(vcpu)->msr_mask;
 	kvmppc_set_msr_fast(vcpu, msr);
 	kvmppc_recalc_shadow_msr(vcpu);
@@ -387,6 +530,11 @@ static void kvmppc_set_msr_pr(struct kvm_vcpu *vcpu, u64 msr)
 	/* Preload FPU if it's enabled */
 	if (kvmppc_get_msr(vcpu) & MSR_FP)
 		kvmppc_handle_ext(vcpu, BOOK3S_INTERRUPT_FP_UNAVAIL, MSR_FP);
+
+#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+	if (kvmppc_get_msr(vcpu) & MSR_TM)
+		kvmppc_handle_lost_math_exts(vcpu);
+#endif
 }
 
 void kvmppc_set_pvr_pr(struct kvm_vcpu *vcpu, u32 pvr)
@@ -584,24 +732,20 @@ int kvmppc_handle_pagefault(struct kvm_run *run, struct kvm_vcpu *vcpu,
 		pte.may_execute = !data;
 	}
 
-	if (page_found == -ENOENT) {
-		/* Page not found in guest PTE entries */
-		u64 ssrr1 = vcpu->arch.shadow_srr1;
-		u64 msr = kvmppc_get_msr(vcpu);
-		kvmppc_set_dar(vcpu, kvmppc_get_fault_dar(vcpu));
-		kvmppc_set_dsisr(vcpu, vcpu->arch.fault_dsisr);
-		kvmppc_set_msr_fast(vcpu, msr | (ssrr1 & 0xf8000000ULL));
-		kvmppc_book3s_queue_irqprio(vcpu, vec);
-	} else if (page_found == -EPERM) {
-		/* Storage protection */
-		u32 dsisr = vcpu->arch.fault_dsisr;
-		u64 ssrr1 = vcpu->arch.shadow_srr1;
-		u64 msr = kvmppc_get_msr(vcpu);
-		kvmppc_set_dar(vcpu, kvmppc_get_fault_dar(vcpu));
-		dsisr = (dsisr & ~DSISR_NOHPTE) | DSISR_PROTFAULT;
-		kvmppc_set_dsisr(vcpu, dsisr);
-		kvmppc_set_msr_fast(vcpu, msr | (ssrr1 & 0xf8000000ULL));
-		kvmppc_book3s_queue_irqprio(vcpu, vec);
+	if (page_found == -ENOENT || page_found == -EPERM) {
+		/* Page not found in guest PTE entries, or protection fault */
+		u64 flags;
+
+		if (page_found == -EPERM)
+			flags = DSISR_PROTFAULT;
+		else
+			flags = DSISR_NOHPTE;
+		if (data) {
+			flags |= vcpu->arch.fault_dsisr & DSISR_ISSTORE;
+			kvmppc_core_queue_data_storage(vcpu, eaddr, flags);
+		} else {
+			kvmppc_core_queue_inst_storage(vcpu, flags);
+		}
 	} else if (page_found == -EINVAL) {
 		/* Page not found in guest SLB */
 		kvmppc_set_dar(vcpu, kvmppc_get_fault_dar(vcpu));
@@ -683,7 +827,7 @@ void kvmppc_giveup_ext(struct kvm_vcpu *vcpu, ulong msr)
 }
 
 /* Give up facility (TAR / EBB / DSCR) */
-static void kvmppc_giveup_fac(struct kvm_vcpu *vcpu, ulong fac)
+void kvmppc_giveup_fac(struct kvm_vcpu *vcpu, ulong fac)
 {
 #ifdef CONFIG_PPC_BOOK3S_64
 	if (!(vcpu->arch.shadow_fscr & (1ULL << fac))) {
@@ -802,7 +946,7 @@ static void kvmppc_handle_lost_ext(struct kvm_vcpu *vcpu)
 
 #ifdef CONFIG_PPC_BOOK3S_64
 
-static void kvmppc_trigger_fac_interrupt(struct kvm_vcpu *vcpu, ulong fac)
+void kvmppc_trigger_fac_interrupt(struct kvm_vcpu *vcpu, ulong fac)
 {
 	/* Inject the Interrupt Cause field and trigger a guest interrupt */
 	vcpu->arch.fscr &= ~(0xffULL << 56);
@@ -864,6 +1008,18 @@ static int kvmppc_handle_fac(struct kvm_vcpu *vcpu, ulong fac)
 		break;
 	}
 
+#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+	/* Since we disabled MSR_TM at privilege state, the mfspr instruction
+	 * for TM spr can trigger TM fac unavailable. In this case, the
+	 * emulation is handled by kvmppc_emulate_fac(), which invokes
+	 * kvmppc_emulate_mfspr() finally. But note the mfspr can include
+	 * RT for NV registers. So it need to restore those NV reg to reflect
+	 * the update.
+	 */
+	if ((fac == FSCR_TM_LG) && !(kvmppc_get_msr(vcpu) & MSR_PR))
+		return RESUME_GUEST_NV;
+#endif
+
 	return RESUME_GUEST;
 }
 
@@ -872,7 +1028,12 @@ void kvmppc_set_fscr(struct kvm_vcpu *vcpu, u64 fscr)
 	if ((vcpu->arch.fscr & FSCR_TAR) && !(fscr & FSCR_TAR)) {
 		/* TAR got dropped, drop it in shadow too */
 		kvmppc_giveup_fac(vcpu, FSCR_TAR_LG);
+	} else if (!(vcpu->arch.fscr & FSCR_TAR) && (fscr & FSCR_TAR)) {
+		vcpu->arch.fscr = fscr;
+		kvmppc_handle_fac(vcpu, FSCR_TAR_LG);
+		return;
 	}
+
 	vcpu->arch.fscr = fscr;
 }
 #endif
@@ -1017,10 +1178,8 @@ int kvmppc_handle_exit_pr(struct kvm_run *run, struct kvm_vcpu *vcpu,
 			kvmppc_mmu_pte_flush(vcpu, kvmppc_get_pc(vcpu), ~0xFFFUL);
 			r = RESUME_GUEST;
 		} else {
-			u64 msr = kvmppc_get_msr(vcpu);
-			msr |= shadow_srr1 & 0x58000000;
-			kvmppc_set_msr_fast(vcpu, msr);
-			kvmppc_book3s_queue_irqprio(vcpu, exit_nr);
+			kvmppc_core_queue_inst_storage(vcpu,
+						shadow_srr1 & 0x58000000);
 			r = RESUME_GUEST;
 		}
 		break;
@@ -1059,9 +1218,7 @@ int kvmppc_handle_exit_pr(struct kvm_run *run, struct kvm_vcpu *vcpu,
 			r = kvmppc_handle_pagefault(run, vcpu, dar, exit_nr);
 			srcu_read_unlock(&vcpu->kvm->srcu, idx);
 		} else {
-			kvmppc_set_dar(vcpu, dar);
-			kvmppc_set_dsisr(vcpu, fault_dsisr);
-			kvmppc_book3s_queue_irqprio(vcpu, exit_nr);
+			kvmppc_core_queue_data_storage(vcpu, dar, fault_dsisr);
 			r = RESUME_GUEST;
 		}
 		break;
@@ -1092,10 +1249,13 @@ int kvmppc_handle_exit_pr(struct kvm_run *run, struct kvm_vcpu *vcpu,
 	case BOOK3S_INTERRUPT_EXTERNAL:
 	case BOOK3S_INTERRUPT_EXTERNAL_LEVEL:
 	case BOOK3S_INTERRUPT_EXTERNAL_HV:
+	case BOOK3S_INTERRUPT_H_VIRT:
 		vcpu->stat.ext_intr_exits++;
 		r = RESUME_GUEST;
 		break;
+	case BOOK3S_INTERRUPT_HMI:
 	case BOOK3S_INTERRUPT_PERFMON:
+	case BOOK3S_INTERRUPT_SYSTEM_RESET:
 		r = RESUME_GUEST;
 		break;
 	case BOOK3S_INTERRUPT_PROGRAM:
@@ -1225,8 +1385,7 @@ int kvmppc_handle_exit_pr(struct kvm_run *run, struct kvm_vcpu *vcpu,
 	}
 #ifdef CONFIG_PPC_BOOK3S_64
 	case BOOK3S_INTERRUPT_FAC_UNAVAIL:
-		kvmppc_handle_fac(vcpu, vcpu->arch.shadow_fscr >> 56);
-		r = RESUME_GUEST;
+		r = kvmppc_handle_fac(vcpu, vcpu->arch.shadow_fscr >> 56);
 		break;
 #endif
 	case BOOK3S_INTERRUPT_MACHINE_CHECK:
@@ -1379,6 +1538,73 @@ static int kvmppc_get_one_reg_pr(struct kvm_vcpu *vcpu, u64 id,
 		else
 			*val = get_reg_val(id, 0);
 		break;
+#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+	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_TM_GPR0 ... KVM_REG_PPC_TM_GPR31:
+		*val = get_reg_val(id,
+				vcpu->arch.gpr_tm[id-KVM_REG_PPC_TM_GPR0]);
+		break;
+	case KVM_REG_PPC_TM_VSR0 ... KVM_REG_PPC_TM_VSR63:
+	{
+		int i, j;
+
+		i = id - KVM_REG_PPC_TM_VSR0;
+		if (i < 32)
+			for (j = 0; j < TS_FPRWIDTH; j++)
+				val->vsxval[j] = vcpu->arch.fp_tm.fpr[i][j];
+		else {
+			if (cpu_has_feature(CPU_FTR_ALTIVEC))
+				val->vval = vcpu->arch.vr_tm.vr[i-32];
+			else
+				r = -ENXIO;
+		}
+		break;
+	}
+	case KVM_REG_PPC_TM_CR:
+		*val = get_reg_val(id, vcpu->arch.cr_tm);
+		break;
+	case KVM_REG_PPC_TM_XER:
+		*val = get_reg_val(id, vcpu->arch.xer_tm);
+		break;
+	case KVM_REG_PPC_TM_LR:
+		*val = get_reg_val(id, vcpu->arch.lr_tm);
+		break;
+	case KVM_REG_PPC_TM_CTR:
+		*val = get_reg_val(id, vcpu->arch.ctr_tm);
+		break;
+	case KVM_REG_PPC_TM_FPSCR:
+		*val = get_reg_val(id, vcpu->arch.fp_tm.fpscr);
+		break;
+	case KVM_REG_PPC_TM_AMR:
+		*val = get_reg_val(id, vcpu->arch.amr_tm);
+		break;
+	case KVM_REG_PPC_TM_PPR:
+		*val = get_reg_val(id, vcpu->arch.ppr_tm);
+		break;
+	case KVM_REG_PPC_TM_VRSAVE:
+		*val = get_reg_val(id, vcpu->arch.vrsave_tm);
+		break;
+	case KVM_REG_PPC_TM_VSCR:
+		if (cpu_has_feature(CPU_FTR_ALTIVEC))
+			*val = get_reg_val(id, vcpu->arch.vr_tm.vscr.u[3]);
+		else
+			r = -ENXIO;
+		break;
+	case KVM_REG_PPC_TM_DSCR:
+		*val = get_reg_val(id, vcpu->arch.dscr_tm);
+		break;
+	case KVM_REG_PPC_TM_TAR:
+		*val = get_reg_val(id, vcpu->arch.tar_tm);
+		break;
+#endif
 	default:
 		r = -EINVAL;
 		break;
@@ -1412,6 +1638,72 @@ static int kvmppc_set_one_reg_pr(struct kvm_vcpu *vcpu, u64 id,
 	case KVM_REG_PPC_LPCR_64:
 		kvmppc_set_lpcr_pr(vcpu, set_reg_val(id, *val));
 		break;
+#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+	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_TM_GPR0 ... KVM_REG_PPC_TM_GPR31:
+		vcpu->arch.gpr_tm[id - KVM_REG_PPC_TM_GPR0] =
+			set_reg_val(id, *val);
+		break;
+	case KVM_REG_PPC_TM_VSR0 ... KVM_REG_PPC_TM_VSR63:
+	{
+		int i, j;
+
+		i = id - KVM_REG_PPC_TM_VSR0;
+		if (i < 32)
+			for (j = 0; j < TS_FPRWIDTH; j++)
+				vcpu->arch.fp_tm.fpr[i][j] = val->vsxval[j];
+		else
+			if (cpu_has_feature(CPU_FTR_ALTIVEC))
+				vcpu->arch.vr_tm.vr[i-32] = val->vval;
+			else
+				r = -ENXIO;
+		break;
+	}
+	case KVM_REG_PPC_TM_CR:
+		vcpu->arch.cr_tm = set_reg_val(id, *val);
+		break;
+	case KVM_REG_PPC_TM_XER:
+		vcpu->arch.xer_tm = set_reg_val(id, *val);
+		break;
+	case KVM_REG_PPC_TM_LR:
+		vcpu->arch.lr_tm = set_reg_val(id, *val);
+		break;
+	case KVM_REG_PPC_TM_CTR:
+		vcpu->arch.ctr_tm = set_reg_val(id, *val);
+		break;
+	case KVM_REG_PPC_TM_FPSCR:
+		vcpu->arch.fp_tm.fpscr = set_reg_val(id, *val);
+		break;
+	case KVM_REG_PPC_TM_AMR:
+		vcpu->arch.amr_tm = set_reg_val(id, *val);
+		break;
+	case KVM_REG_PPC_TM_PPR:
+		vcpu->arch.ppr_tm = set_reg_val(id, *val);
+		break;
+	case KVM_REG_PPC_TM_VRSAVE:
+		vcpu->arch.vrsave_tm = set_reg_val(id, *val);
+		break;
+	case KVM_REG_PPC_TM_VSCR:
+		if (cpu_has_feature(CPU_FTR_ALTIVEC))
+			vcpu->arch.vr.vscr.u[3] = set_reg_val(id, *val);
+		else
+			r = -ENXIO;
+		break;
+	case KVM_REG_PPC_TM_DSCR:
+		vcpu->arch.dscr_tm = set_reg_val(id, *val);
+		break;
+	case KVM_REG_PPC_TM_TAR:
+		vcpu->arch.tar_tm = set_reg_val(id, *val);
+		break;
+#endif
 	default:
 		r = -EINVAL;
 		break;
@@ -1687,6 +1979,17 @@ static int kvm_vm_ioctl_get_smmu_info_pr(struct kvm *kvm,
 
 	return 0;
 }
+
+static int kvm_configure_mmu_pr(struct kvm *kvm, struct kvm_ppc_mmuv3_cfg *cfg)
+{
+	if (!cpu_has_feature(CPU_FTR_ARCH_300))
+		return -ENODEV;
+	/* Require flags and process table base and size to all be zero. */
+	if (cfg->flags || cfg->process_table)
+		return -EINVAL;
+	return 0;
+}
+
 #else
 static int kvm_vm_ioctl_get_smmu_info_pr(struct kvm *kvm,
 					 struct kvm_ppc_smmu_info *info)
@@ -1735,9 +2038,12 @@ static void kvmppc_core_destroy_vm_pr(struct kvm *kvm)
 static int kvmppc_core_check_processor_compat_pr(void)
 {
 	/*
-	 * Disable KVM for Power9 untill the required bits merged.
+	 * PR KVM can work on POWER9 inside a guest partition
+	 * running in HPT mode.  It can't work if we are using
+	 * radix translation (because radix provides no way for
+	 * a process to have unique translations in quadrant 3).
 	 */
-	if (cpu_has_feature(CPU_FTR_ARCH_300))
+	if (cpu_has_feature(CPU_FTR_ARCH_300) && radix_enabled())
 		return -EIO;
 	return 0;
 }
@@ -1781,7 +2087,9 @@ static struct kvmppc_ops kvm_ops_pr = {
 	.arch_vm_ioctl  = kvm_arch_vm_ioctl_pr,
 #ifdef CONFIG_PPC_BOOK3S_64
 	.hcall_implemented = kvmppc_hcall_impl_pr,
+	.configure_mmu = kvm_configure_mmu_pr,
 #endif
+	.giveup_ext = kvmppc_giveup_ext,
 };
 
 

arch/powerpc/kvm/book3s_segment.S

@@ -383,6 +383,19 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
 	 */
 
 	PPC_LL	r6, HSTATE_HOST_MSR(r13)
+#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+	/*
+	 * We don't want to change MSR[TS] bits via rfi here.
+	 * The actual TM handling logic will be in host with
+	 * recovered DR/IR bits after HSTATE_VMHANDLER.
+	 * And MSR_TM can be enabled in HOST_MSR so rfid may
+	 * not suppress this change and can lead to exception.
+	 * Manually set MSR to prevent TS state change here.
+	 */
+	mfmsr   r7
+	rldicl  r7, r7, 64 - MSR_TS_S_LG, 62
+	rldimi  r6, r7, MSR_TS_S_LG, 63 - MSR_TS_T_LG
+#endif
 	PPC_LL	r8, HSTATE_VMHANDLER(r13)
 
 #ifdef CONFIG_PPC64

arch/powerpc/kvm/book3s_xive_template.c

@@ -334,7 +334,7 @@ X_STATIC unsigned long GLUE(X_PFX,h_xirr)(struct kvm_vcpu *vcpu)
 	 */
 
 	/* Return interrupt and old CPPR in GPR4 */
-	vcpu->arch.gpr[4] = hirq | (old_cppr << 24);
+	vcpu->arch.regs.gpr[4] = hirq | (old_cppr << 24);
 
 	return H_SUCCESS;
 }
@@ -369,7 +369,7 @@ X_STATIC unsigned long GLUE(X_PFX,h_ipoll)(struct kvm_vcpu *vcpu, unsigned long
 	hirq = GLUE(X_PFX,scan_interrupts)(xc, pending, scan_poll);
 
 	/* Return interrupt and old CPPR in GPR4 */
-	vcpu->arch.gpr[4] = hirq | (xc->cppr << 24);
+	vcpu->arch.regs.gpr[4] = hirq | (xc->cppr << 24);
 
 	return H_SUCCESS;
 }

arch/powerpc/kvm/booke.c

@@ -77,8 +77,10 @@ void kvmppc_dump_vcpu(struct kvm_vcpu *vcpu)
 {
 	int i;
 
-	printk("pc:   %08lx msr:  %08llx\n", vcpu->arch.pc, vcpu->arch.shared->msr);
-	printk("lr:   %08lx ctr:  %08lx\n", vcpu->arch.lr, vcpu->arch.ctr);
+	printk("pc:   %08lx msr:  %08llx\n", vcpu->arch.regs.nip,
+			vcpu->arch.shared->msr);
+	printk("lr:   %08lx ctr:  %08lx\n", vcpu->arch.regs.link,
+			vcpu->arch.regs.ctr);
 	printk("srr0: %08llx srr1: %08llx\n", vcpu->arch.shared->srr0,
 					    vcpu->arch.shared->srr1);
 
@@ -491,24 +493,25 @@ static int kvmppc_booke_irqprio_deliver(struct kvm_vcpu *vcpu,
 	if (allowed) {
 		switch (int_class) {
 		case INT_CLASS_NONCRIT:
-			set_guest_srr(vcpu, vcpu->arch.pc,
+			set_guest_srr(vcpu, vcpu->arch.regs.nip,
 				      vcpu->arch.shared->msr);
 			break;
 		case INT_CLASS_CRIT:
-			set_guest_csrr(vcpu, vcpu->arch.pc,
+			set_guest_csrr(vcpu, vcpu->arch.regs.nip,
 				       vcpu->arch.shared->msr);
 			break;
 		case INT_CLASS_DBG:
-			set_guest_dsrr(vcpu, vcpu->arch.pc,
+			set_guest_dsrr(vcpu, vcpu->arch.regs.nip,
 				       vcpu->arch.shared->msr);
 			break;
 		case INT_CLASS_MC:
-			set_guest_mcsrr(vcpu, vcpu->arch.pc,
+			set_guest_mcsrr(vcpu, vcpu->arch.regs.nip,
 					vcpu->arch.shared->msr);
 			break;
 		}
 
-		vcpu->arch.pc = vcpu->arch.ivpr | vcpu->arch.ivor[priority];
+		vcpu->arch.regs.nip = vcpu->arch.ivpr |
+					vcpu->arch.ivor[priority];
 		if (update_esr == true)
 			kvmppc_set_esr(vcpu, vcpu->arch.queued_esr);
 		if (update_dear == true)
@@ -826,7 +829,7 @@ static int emulation_exit(struct kvm_run *run, struct kvm_vcpu *vcpu)
 
 	case EMULATE_FAIL:
 		printk(KERN_CRIT "%s: emulation at %lx failed (%08x)\n",
-		       __func__, vcpu->arch.pc, vcpu->arch.last_inst);
+		       __func__, vcpu->arch.regs.nip, vcpu->arch.last_inst);
 		/* For debugging, encode the failing instruction and
 		 * report it to userspace. */
 		run->hw.hardware_exit_reason = ~0ULL << 32;
@@ -875,7 +878,7 @@ static int kvmppc_handle_debug(struct kvm_run *run, struct kvm_vcpu *vcpu)
 	 */
 	vcpu->arch.dbsr = 0;
 	run->debug.arch.status = 0;
-	run->debug.arch.address = vcpu->arch.pc;
+	run->debug.arch.address = vcpu->arch.regs.nip;
 
 	if (dbsr & (DBSR_IAC1 | DBSR_IAC2 | DBSR_IAC3 | DBSR_IAC4)) {
 		run->debug.arch.status |= KVMPPC_DEBUG_BREAKPOINT;
@@ -971,7 +974,7 @@ static int kvmppc_resume_inst_load(struct kvm_run *run, struct kvm_vcpu *vcpu,
 
 	case EMULATE_FAIL:
 		pr_debug("%s: load instruction from guest address %lx failed\n",
-		       __func__, vcpu->arch.pc);
+		       __func__, vcpu->arch.regs.nip);
 		/* For debugging, encode the failing instruction and
 		 * report it to userspace. */
 		run->hw.hardware_exit_reason = ~0ULL << 32;
@@ -1169,7 +1172,7 @@ int kvmppc_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu,
 	case BOOKE_INTERRUPT_SPE_FP_DATA:
 	case BOOKE_INTERRUPT_SPE_FP_ROUND:
 		printk(KERN_CRIT "%s: unexpected SPE interrupt %u at %08lx\n",
-		       __func__, exit_nr, vcpu->arch.pc);
+		       __func__, exit_nr, vcpu->arch.regs.nip);
 		run->hw.hardware_exit_reason = exit_nr;
 		r = RESUME_HOST;
 		break;
@@ -1299,7 +1302,7 @@ int kvmppc_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu,
 	}
 
 	case BOOKE_INTERRUPT_ITLB_MISS: {
-		unsigned long eaddr = vcpu->arch.pc;
+		unsigned long eaddr = vcpu->arch.regs.nip;
 		gpa_t gpaddr;
 		gfn_t gfn;
 		int gtlb_index;
@@ -1391,7 +1394,7 @@ int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu)
 	int i;
 	int r;
 
-	vcpu->arch.pc = 0;
+	vcpu->arch.regs.nip = 0;
 	vcpu->arch.shared->pir = vcpu->vcpu_id;
 	kvmppc_set_gpr(vcpu, 1, (16<<20) - 8); /* -8 for the callee-save LR slot */
 	kvmppc_set_msr(vcpu, 0);
@@ -1440,10 +1443,10 @@ int kvm_arch_vcpu_ioctl_get_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs)
 
 	vcpu_load(vcpu);
 
-	regs->pc = vcpu->arch.pc;
+	regs->pc = vcpu->arch.regs.nip;
 	regs->cr = kvmppc_get_cr(vcpu);
-	regs->ctr = vcpu->arch.ctr;
-	regs->lr = vcpu->arch.lr;
+	regs->ctr = vcpu->arch.regs.ctr;
+	regs->lr = vcpu->arch.regs.link;
 	regs->xer = kvmppc_get_xer(vcpu);
 	regs->msr = vcpu->arch.shared->msr;
 	regs->srr0 = kvmppc_get_srr0(vcpu);
@@ -1471,10 +1474,10 @@ int kvm_arch_vcpu_ioctl_set_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs)
 
 	vcpu_load(vcpu);
 
-	vcpu->arch.pc = regs->pc;
+	vcpu->arch.regs.nip = regs->pc;
 	kvmppc_set_cr(vcpu, regs->cr);
-	vcpu->arch.ctr = regs->ctr;
-	vcpu->arch.lr = regs->lr;
+	vcpu->arch.regs.ctr = regs->ctr;
+	vcpu->arch.regs.link = regs->lr;
 	kvmppc_set_xer(vcpu, regs->xer);
 	kvmppc_set_msr(vcpu, regs->msr);
 	kvmppc_set_srr0(vcpu, regs->srr0);

arch/powerpc/kvm/booke_emulate.c

@@ -34,19 +34,19 @@
 
 static void kvmppc_emul_rfi(struct kvm_vcpu *vcpu)
 {
-	vcpu->arch.pc = vcpu->arch.shared->srr0;
+	vcpu->arch.regs.nip = vcpu->arch.shared->srr0;
 	kvmppc_set_msr(vcpu, vcpu->arch.shared->srr1);
 }
 
 static void kvmppc_emul_rfdi(struct kvm_vcpu *vcpu)
 {
-	vcpu->arch.pc = vcpu->arch.dsrr0;
+	vcpu->arch.regs.nip = vcpu->arch.dsrr0;
 	kvmppc_set_msr(vcpu, vcpu->arch.dsrr1);
 }
 
 static void kvmppc_emul_rfci(struct kvm_vcpu *vcpu)
 {
-	vcpu->arch.pc = vcpu->arch.csrr0;
+	vcpu->arch.regs.nip = vcpu->arch.csrr0;
 	kvmppc_set_msr(vcpu, vcpu->arch.csrr1);
 }
 

arch/powerpc/kvm/e500_emulate.c

@@ -53,7 +53,7 @@ static int dbell2prio(ulong param)
 
 static int kvmppc_e500_emul_msgclr(struct kvm_vcpu *vcpu, int rb)
 {
-	ulong param = vcpu->arch.gpr[rb];
+	ulong param = vcpu->arch.regs.gpr[rb];
 	int prio = dbell2prio(param);
 
 	if (prio < 0)
@@ -65,7 +65,7 @@ static int kvmppc_e500_emul_msgclr(struct kvm_vcpu *vcpu, int rb)
 
 static int kvmppc_e500_emul_msgsnd(struct kvm_vcpu *vcpu, int rb)
 {
-	ulong param = vcpu->arch.gpr[rb];
+	ulong param = vcpu->arch.regs.gpr[rb];
 	int prio = dbell2prio(rb);
 	int pir = param & PPC_DBELL_PIR_MASK;
 	int i;
@@ -94,7 +94,7 @@ static int kvmppc_e500_emul_ehpriv(struct kvm_run *run, struct kvm_vcpu *vcpu,
 	switch (get_oc(inst)) {
 	case EHPRIV_OC_DEBUG:
 		run->exit_reason = KVM_EXIT_DEBUG;
-		run->debug.arch.address = vcpu->arch.pc;
+		run->debug.arch.address = vcpu->arch.regs.nip;
 		run->debug.arch.status = 0;
 		kvmppc_account_exit(vcpu, DEBUG_EXITS);
 		emulated = EMULATE_EXIT_USER;

arch/powerpc/kvm/e500_mmu.c

@@ -513,7 +513,7 @@ void kvmppc_mmu_itlb_miss(struct kvm_vcpu *vcpu)
 {
 	unsigned int as = !!(vcpu->arch.shared->msr & MSR_IS);
 
-	kvmppc_e500_deliver_tlb_miss(vcpu, vcpu->arch.pc, as);
+	kvmppc_e500_deliver_tlb_miss(vcpu, vcpu->arch.regs.nip, as);
 }
 
 void kvmppc_mmu_dtlb_miss(struct kvm_vcpu *vcpu)

arch/powerpc/kvm/e500_mmu_host.c

@@ -625,8 +625,8 @@ void kvmppc_mmu_map(struct kvm_vcpu *vcpu, u64 eaddr, gpa_t gpaddr,
 }
 
 #ifdef CONFIG_KVM_BOOKE_HV
-int kvmppc_load_last_inst(struct kvm_vcpu *vcpu, enum instruction_type type,
-			  u32 *instr)
+int kvmppc_load_last_inst(struct kvm_vcpu *vcpu,
+		enum instruction_fetch_type type, u32 *instr)
 {
 	gva_t geaddr;
 	hpa_t addr;
@@ -715,8 +715,8 @@ int kvmppc_load_last_inst(struct kvm_vcpu *vcpu, enum instruction_type type,
 	return EMULATE_DONE;
 }
 #else
-int kvmppc_load_last_inst(struct kvm_vcpu *vcpu, enum instruction_type type,
-			  u32 *instr)
+int kvmppc_load_last_inst(struct kvm_vcpu *vcpu,
+		enum instruction_fetch_type type, u32 *instr)
 {
 	return EMULATE_AGAIN;
 }

arch/powerpc/kvm/emulate_loadstore.c

@@ -31,6 +31,7 @@
 #include <asm/kvm_ppc.h>
 #include <asm/disassemble.h>
 #include <asm/ppc-opcode.h>
+#include <asm/sstep.h>
 #include "timing.h"
 #include "trace.h"
 
@@ -84,8 +85,9 @@ int kvmppc_emulate_loadstore(struct kvm_vcpu *vcpu)
 	struct kvm_run *run = vcpu->run;
 	u32 inst;
 	int ra, rs, rt;
-	enum emulation_result emulated;
+	enum emulation_result emulated = EMULATE_FAIL;
 	int advance = 1;
+	struct instruction_op op;
 
 	/* this default type might be overwritten by subcategories */
 	kvmppc_set_exit_type(vcpu, EMULATED_INST_EXITS);
@@ -107,580 +109,276 @@ int kvmppc_emulate_loadstore(struct kvm_vcpu *vcpu)
 	vcpu->arch.mmio_vsx_tx_sx_enabled = get_tx_or_sx(inst);
 	vcpu->arch.mmio_vsx_copy_nums = 0;
 	vcpu->arch.mmio_vsx_offset = 0;
-	vcpu->arch.mmio_vsx_copy_type = KVMPPC_VSX_COPY_NONE;
+	vcpu->arch.mmio_copy_type = KVMPPC_VSX_COPY_NONE;
 	vcpu->arch.mmio_sp64_extend = 0;
 	vcpu->arch.mmio_sign_extend = 0;
 	vcpu->arch.mmio_vmx_copy_nums = 0;
+	vcpu->arch.mmio_vmx_offset = 0;
+	vcpu->arch.mmio_host_swabbed = 0;
 
-	switch (get_op(inst)) {
-	case 31:
-		switch (get_xop(inst)) {
-		case OP_31_XOP_LWZX:
-			emulated = kvmppc_handle_load(run, vcpu, rt, 4, 1);
-			break;
-
-		case OP_31_XOP_LWZUX:
-			emulated = kvmppc_handle_load(run, vcpu, rt, 4, 1);
-			kvmppc_set_gpr(vcpu, ra, vcpu->arch.vaddr_accessed);
-			break;
+	emulated = EMULATE_FAIL;
+	vcpu->arch.regs.msr = vcpu->arch.shared->msr;
+	vcpu->arch.regs.ccr = vcpu->arch.cr;
+	if (analyse_instr(&op, &vcpu->arch.regs, inst) == 0) {
+		int type = op.type & INSTR_TYPE_MASK;
+		int size = GETSIZE(op.type);
 
-		case OP_31_XOP_LBZX:
-			emulated = kvmppc_handle_load(run, vcpu, rt, 1, 1);
-			break;
-
-		case OP_31_XOP_LBZUX:
-			emulated = kvmppc_handle_load(run, vcpu, rt, 1, 1);
-			kvmppc_set_gpr(vcpu, ra, vcpu->arch.vaddr_accessed);
-			break;
+		switch (type) {
+		case LOAD:  {
+			int instr_byte_swap = op.type & BYTEREV;
 
-		case OP_31_XOP_STDX:
-			emulated = kvmppc_handle_store(run, vcpu,
-					kvmppc_get_gpr(vcpu, rs), 8, 1);
-			break;
+			if (op.type & SIGNEXT)
+				emulated = kvmppc_handle_loads(run, vcpu,
+						op.reg, size, !instr_byte_swap);
+			else
+				emulated = kvmppc_handle_load(run, vcpu,
+						op.reg, size, !instr_byte_swap);
 
-		case OP_31_XOP_STDUX:
-			emulated = kvmppc_handle_store(run, vcpu,
-					kvmppc_get_gpr(vcpu, rs), 8, 1);
-			kvmppc_set_gpr(vcpu, ra, vcpu->arch.vaddr_accessed);
-			break;
+			if ((op.type & UPDATE) && (emulated != EMULATE_FAIL))
+				kvmppc_set_gpr(vcpu, op.update_reg, op.ea);
 
-		case OP_31_XOP_STWX:
-			emulated = kvmppc_handle_store(run, vcpu,
-					kvmppc_get_gpr(vcpu, rs), 4, 1);
-			break;
-
-		case OP_31_XOP_STWUX:
-			emulated = kvmppc_handle_store(run, vcpu,
-					kvmppc_get_gpr(vcpu, rs), 4, 1);
-			kvmppc_set_gpr(vcpu, ra, vcpu->arch.vaddr_accessed);
-			break;
-
-		case OP_31_XOP_STBX:
-			emulated = kvmppc_handle_store(run, vcpu,
-					kvmppc_get_gpr(vcpu, rs), 1, 1);
-			break;
-
-		case OP_31_XOP_STBUX:
-			emulated = kvmppc_handle_store(run, vcpu,
-					kvmppc_get_gpr(vcpu, rs), 1, 1);
-			kvmppc_set_gpr(vcpu, ra, vcpu->arch.vaddr_accessed);
-			break;
-
-		case OP_31_XOP_LHAX:
-			emulated = kvmppc_handle_loads(run, vcpu, rt, 2, 1);
-			break;
-
-		case OP_31_XOP_LHAUX:
-			emulated = kvmppc_handle_loads(run, vcpu, rt, 2, 1);
-			kvmppc_set_gpr(vcpu, ra, vcpu->arch.vaddr_accessed);
-			break;
-
-		case OP_31_XOP_LHZX:
-			emulated = kvmppc_handle_load(run, vcpu, rt, 2, 1);
-			break;
-
-		case OP_31_XOP_LHZUX:
-			emulated = kvmppc_handle_load(run, vcpu, rt, 2, 1);
-			kvmppc_set_gpr(vcpu, ra, vcpu->arch.vaddr_accessed);
-			break;
-
-		case OP_31_XOP_STHX:
-			emulated = kvmppc_handle_store(run, vcpu,
-					kvmppc_get_gpr(vcpu, rs), 2, 1);
-			break;
-
-		case OP_31_XOP_STHUX:
-			emulated = kvmppc_handle_store(run, vcpu,
-					kvmppc_get_gpr(vcpu, rs), 2, 1);
-			kvmppc_set_gpr(vcpu, ra, vcpu->arch.vaddr_accessed);
-			break;
-
-		case OP_31_XOP_DCBST:
-		case OP_31_XOP_DCBF:
-		case OP_31_XOP_DCBI:
-			/* Do nothing. The guest is performing dcbi because
-			 * hardware DMA is not snooped by the dcache, but
-			 * emulated DMA either goes through the dcache as
-			 * normal writes, or the host kernel has handled dcache
-			 * coherence. */
-			break;
-
-		case OP_31_XOP_LWBRX:
-			emulated = kvmppc_handle_load(run, vcpu, rt, 4, 0);
-			break;
-
-		case OP_31_XOP_STWBRX:
-			emulated = kvmppc_handle_store(run, vcpu,
-					kvmppc_get_gpr(vcpu, rs), 4, 0);
 			break;
-
-		case OP_31_XOP_LHBRX:
-			emulated = kvmppc_handle_load(run, vcpu, rt, 2, 0);
-			break;
-
-		case OP_31_XOP_STHBRX:
-			emulated = kvmppc_handle_store(run, vcpu,
-					kvmppc_get_gpr(vcpu, rs), 2, 0);
-			break;
-
-		case OP_31_XOP_LDBRX:
-			emulated = kvmppc_handle_load(run, vcpu, rt, 8, 0);
-			break;
-
-		case OP_31_XOP_STDBRX:
-			emulated = kvmppc_handle_store(run, vcpu,
-					kvmppc_get_gpr(vcpu, rs), 8, 0);
-			break;
-
-		case OP_31_XOP_LDX:
-			emulated = kvmppc_handle_load(run, vcpu, rt, 8, 1);
-			break;
-
-		case OP_31_XOP_LDUX:
-			emulated = kvmppc_handle_load(run, vcpu, rt, 8, 1);
-			kvmppc_set_gpr(vcpu, ra, vcpu->arch.vaddr_accessed);
-			break;
-
-		case OP_31_XOP_LWAX:
-			emulated = kvmppc_handle_loads(run, vcpu, rt, 4, 1);
-			break;
-
-		case OP_31_XOP_LWAUX:
-			emulated = kvmppc_handle_loads(run, vcpu, rt, 4, 1);
-			kvmppc_set_gpr(vcpu, ra, vcpu->arch.vaddr_accessed);
-			break;
-
+		}
 #ifdef CONFIG_PPC_FPU
-		case OP_31_XOP_LFSX:
-			if (kvmppc_check_fp_disabled(vcpu))
-				return EMULATE_DONE;
-			vcpu->arch.mmio_sp64_extend = 1;
-			emulated = kvmppc_handle_load(run, vcpu,
-				KVM_MMIO_REG_FPR|rt, 4, 1);
-			break;
-
-		case OP_31_XOP_LFSUX:
+		case LOAD_FP:
 			if (kvmppc_check_fp_disabled(vcpu))
 				return EMULATE_DONE;
-			vcpu->arch.mmio_sp64_extend = 1;
-			emulated = kvmppc_handle_load(run, vcpu,
-				KVM_MMIO_REG_FPR|rt, 4, 1);
-			kvmppc_set_gpr(vcpu, ra, vcpu->arch.vaddr_accessed);
-			break;
 
-		case OP_31_XOP_LFDX:
-			if (kvmppc_check_fp_disabled(vcpu))
-				return EMULATE_DONE;
-			emulated = kvmppc_handle_load(run, vcpu,
-				KVM_MMIO_REG_FPR|rt, 8, 1);
-			break;
+			if (op.type & FPCONV)
+				vcpu->arch.mmio_sp64_extend = 1;
 
-		case OP_31_XOP_LFDUX:
-			if (kvmppc_check_fp_disabled(vcpu))
-				return EMULATE_DONE;
-			emulated = kvmppc_handle_load(run, vcpu,
-				KVM_MMIO_REG_FPR|rt, 8, 1);
-			kvmppc_set_gpr(vcpu, ra, vcpu->arch.vaddr_accessed);
-			break;
-
-		case OP_31_XOP_LFIWAX:
-			if (kvmppc_check_fp_disabled(vcpu))
-				return EMULATE_DONE;
-			emulated = kvmppc_handle_loads(run, vcpu,
-				KVM_MMIO_REG_FPR|rt, 4, 1);
-			break;
+			if (op.type & SIGNEXT)
+				emulated = kvmppc_handle_loads(run, vcpu,
+					     KVM_MMIO_REG_FPR|op.reg, size, 1);
+			else
+				emulated = kvmppc_handle_load(run, vcpu,
+					     KVM_MMIO_REG_FPR|op.reg, size, 1);
 
-		case OP_31_XOP_LFIWZX:
-			if (kvmppc_check_fp_disabled(vcpu))
-				return EMULATE_DONE;
-			emulated = kvmppc_handle_load(run, vcpu,
-				KVM_MMIO_REG_FPR|rt, 4, 1);
-			break;
+			if ((op.type & UPDATE) && (emulated != EMULATE_FAIL))
+				kvmppc_set_gpr(vcpu, op.update_reg, op.ea);
 
-		case OP_31_XOP_STFSX:
-			if (kvmppc_check_fp_disabled(vcpu))
-				return EMULATE_DONE;
-			vcpu->arch.mmio_sp64_extend = 1;
-			emulated = kvmppc_handle_store(run, vcpu,
-				VCPU_FPR(vcpu, rs), 4, 1);
 			break;
-
-		case OP_31_XOP_STFSUX:
-			if (kvmppc_check_fp_disabled(vcpu))
-				return EMULATE_DONE;
-			vcpu->arch.mmio_sp64_extend = 1;
-			emulated = kvmppc_handle_store(run, vcpu,
-				VCPU_FPR(vcpu, rs), 4, 1);
-			kvmppc_set_gpr(vcpu, ra, vcpu->arch.vaddr_accessed);
-			break;
-
-		case OP_31_XOP_STFDX:
-			if (kvmppc_check_fp_disabled(vcpu))
-				return EMULATE_DONE;
-			emulated = kvmppc_handle_store(run, vcpu,
-				VCPU_FPR(vcpu, rs), 8, 1);
-			break;
-
-		case OP_31_XOP_STFDUX:
-			if (kvmppc_check_fp_disabled(vcpu))
+#endif
+#ifdef CONFIG_ALTIVEC
+		case LOAD_VMX:
+			if (kvmppc_check_altivec_disabled(vcpu))
 				return EMULATE_DONE;
-			emulated = kvmppc_handle_store(run, vcpu,
-				VCPU_FPR(vcpu, rs), 8, 1);
-			kvmppc_set_gpr(vcpu, ra, vcpu->arch.vaddr_accessed);
-			break;
 
-		case OP_31_XOP_STFIWX:
-			if (kvmppc_check_fp_disabled(vcpu))
-				return EMULATE_DONE;
-			emulated = kvmppc_handle_store(run, vcpu,
-				VCPU_FPR(vcpu, rs), 4, 1);
+			/* Hardware enforces alignment of VMX accesses */
+			vcpu->arch.vaddr_accessed &= ~((unsigned long)size - 1);
+			vcpu->arch.paddr_accessed &= ~((unsigned long)size - 1);
+
+			if (size == 16) { /* lvx */
+				vcpu->arch.mmio_copy_type =
+						KVMPPC_VMX_COPY_DWORD;
+			} else if (size == 4) { /* lvewx  */
+				vcpu->arch.mmio_copy_type =
+						KVMPPC_VMX_COPY_WORD;
+			} else if (size == 2) { /* lvehx  */
+				vcpu->arch.mmio_copy_type =
+						KVMPPC_VMX_COPY_HWORD;
+			} else if (size == 1) { /* lvebx  */
+				vcpu->arch.mmio_copy_type =
+						KVMPPC_VMX_COPY_BYTE;
+			} else
+				break;
+
+			vcpu->arch.mmio_vmx_offset =
+				(vcpu->arch.vaddr_accessed & 0xf)/size;
+
+			if (size == 16) {
+				vcpu->arch.mmio_vmx_copy_nums = 2;
+				emulated = kvmppc_handle_vmx_load(run,
+						vcpu, KVM_MMIO_REG_VMX|op.reg,
+						8, 1);
+			} else {
+				vcpu->arch.mmio_vmx_copy_nums = 1;
+				emulated = kvmppc_handle_vmx_load(run, vcpu,
+						KVM_MMIO_REG_VMX|op.reg,
+						size, 1);
+			}
 			break;
 #endif
-
 #ifdef CONFIG_VSX
-		case OP_31_XOP_LXSDX:
-			if (kvmppc_check_vsx_disabled(vcpu))
-				return EMULATE_DONE;
-			vcpu->arch.mmio_vsx_copy_nums = 1;
-			vcpu->arch.mmio_vsx_copy_type = KVMPPC_VSX_COPY_DWORD;
-			emulated = kvmppc_handle_vsx_load(run, vcpu,
-				KVM_MMIO_REG_VSX|rt, 8, 1, 0);
-			break;
-
-		case OP_31_XOP_LXSSPX:
-			if (kvmppc_check_vsx_disabled(vcpu))
-				return EMULATE_DONE;
-			vcpu->arch.mmio_vsx_copy_nums = 1;
-			vcpu->arch.mmio_vsx_copy_type = KVMPPC_VSX_COPY_DWORD;
-			vcpu->arch.mmio_sp64_extend = 1;
-			emulated = kvmppc_handle_vsx_load(run, vcpu,
-				KVM_MMIO_REG_VSX|rt, 4, 1, 0);
-			break;
+		case LOAD_VSX: {
+			int io_size_each;
+
+			if (op.vsx_flags & VSX_CHECK_VEC) {
+				if (kvmppc_check_altivec_disabled(vcpu))
+					return EMULATE_DONE;
+			} else {
+				if (kvmppc_check_vsx_disabled(vcpu))
+					return EMULATE_DONE;
+			}
+
+			if (op.vsx_flags & VSX_FPCONV)
+				vcpu->arch.mmio_sp64_extend = 1;
+
+			if (op.element_size == 8)  {
+				if (op.vsx_flags & VSX_SPLAT)
+					vcpu->arch.mmio_copy_type =
+						KVMPPC_VSX_COPY_DWORD_LOAD_DUMP;
+				else
+					vcpu->arch.mmio_copy_type =
+						KVMPPC_VSX_COPY_DWORD;
+			} else if (op.element_size == 4) {
+				if (op.vsx_flags & VSX_SPLAT)
+					vcpu->arch.mmio_copy_type =
+						KVMPPC_VSX_COPY_WORD_LOAD_DUMP;
+				else
+					vcpu->arch.mmio_copy_type =
+						KVMPPC_VSX_COPY_WORD;
+			} else
+				break;
+
+			if (size < op.element_size) {
+				/* precision convert case: lxsspx, etc */
+				vcpu->arch.mmio_vsx_copy_nums = 1;
+				io_size_each = size;
+			} else { /* lxvw4x, lxvd2x, etc */
+				vcpu->arch.mmio_vsx_copy_nums =
+					size/op.element_size;
+				io_size_each = op.element_size;
+			}
 
-		case OP_31_XOP_LXSIWAX:
-			if (kvmppc_check_vsx_disabled(vcpu))
-				return EMULATE_DONE;
-			vcpu->arch.mmio_vsx_copy_nums = 1;
-			vcpu->arch.mmio_vsx_copy_type = KVMPPC_VSX_COPY_DWORD;
 			emulated = kvmppc_handle_vsx_load(run, vcpu,
-				KVM_MMIO_REG_VSX|rt, 4, 1, 1);
-			break;
-
-		case OP_31_XOP_LXSIWZX:
-			if (kvmppc_check_vsx_disabled(vcpu))
-				return EMULATE_DONE;
-			vcpu->arch.mmio_vsx_copy_nums = 1;
-			vcpu->arch.mmio_vsx_copy_type = KVMPPC_VSX_COPY_DWORD;
-			emulated = kvmppc_handle_vsx_load(run, vcpu,
-				KVM_MMIO_REG_VSX|rt, 4, 1, 0);
+					KVM_MMIO_REG_VSX | (op.reg & 0x1f),
+					io_size_each, 1, op.type & SIGNEXT);
 			break;
+		}
+#endif
+		case STORE:
+			/* if need byte reverse, op.val has been reversed by
+			 * analyse_instr().
+			 */
+			emulated = kvmppc_handle_store(run, vcpu, op.val,
+					size, 1);
 
-		case OP_31_XOP_LXVD2X:
-		/*
-		 * In this case, the official load/store process is like this:
-		 * Step1, exit from vm by page fault isr, then kvm save vsr.
-		 * Please see guest_exit_cont->store_fp_state->SAVE_32VSRS
-		 * as reference.
-		 *
-		 * Step2, copy data between memory and VCPU
-		 * Notice: for LXVD2X/STXVD2X/LXVW4X/STXVW4X, we use
-		 * 2copies*8bytes or 4copies*4bytes
-		 * to simulate one copy of 16bytes.
-		 * Also there is an endian issue here, we should notice the
-		 * layout of memory.
-		 * Please see MARCO of LXVD2X_ROT/STXVD2X_ROT as more reference.
-		 * If host is little-endian, kvm will call XXSWAPD for
-		 * LXVD2X_ROT/STXVD2X_ROT.
-		 * So, if host is little-endian,
-		 * the postion of memeory should be swapped.
-		 *
-		 * Step3, return to guest, kvm reset register.
-		 * Please see kvmppc_hv_entry->load_fp_state->REST_32VSRS
-		 * as reference.
-		 */
-			if (kvmppc_check_vsx_disabled(vcpu))
-				return EMULATE_DONE;
-			vcpu->arch.mmio_vsx_copy_nums = 2;
-			vcpu->arch.mmio_vsx_copy_type = KVMPPC_VSX_COPY_DWORD;
-			emulated = kvmppc_handle_vsx_load(run, vcpu,
-				KVM_MMIO_REG_VSX|rt, 8, 1, 0);
-			break;
+			if ((op.type & UPDATE) && (emulated != EMULATE_FAIL))
+				kvmppc_set_gpr(vcpu, op.update_reg, op.ea);
 
-		case OP_31_XOP_LXVW4X:
-			if (kvmppc_check_vsx_disabled(vcpu))
-				return EMULATE_DONE;
-			vcpu->arch.mmio_vsx_copy_nums = 4;
-			vcpu->arch.mmio_vsx_copy_type = KVMPPC_VSX_COPY_WORD;
-			emulated = kvmppc_handle_vsx_load(run, vcpu,
-				KVM_MMIO_REG_VSX|rt, 4, 1, 0);
 			break;
-
-		case OP_31_XOP_LXVDSX:
-			if (kvmppc_check_vsx_disabled(vcpu))
+#ifdef CONFIG_PPC_FPU
+		case STORE_FP:
+			if (kvmppc_check_fp_disabled(vcpu))
 				return EMULATE_DONE;
-			vcpu->arch.mmio_vsx_copy_nums = 1;
-			vcpu->arch.mmio_vsx_copy_type =
-				 KVMPPC_VSX_COPY_DWORD_LOAD_DUMP;
-			emulated = kvmppc_handle_vsx_load(run, vcpu,
-				KVM_MMIO_REG_VSX|rt, 8, 1, 0);
-			break;
 
-		case OP_31_XOP_STXSDX:
-			if (kvmppc_check_vsx_disabled(vcpu))
-				return EMULATE_DONE;
-			vcpu->arch.mmio_vsx_copy_nums = 1;
-			vcpu->arch.mmio_vsx_copy_type = KVMPPC_VSX_COPY_DWORD;
-			emulated = kvmppc_handle_vsx_store(run, vcpu,
-						 rs, 8, 1);
-			break;
+			/* The FP registers need to be flushed so that
+			 * kvmppc_handle_store() can read actual FP vals
+			 * from vcpu->arch.
+			 */
+			if (vcpu->kvm->arch.kvm_ops->giveup_ext)
+				vcpu->kvm->arch.kvm_ops->giveup_ext(vcpu,
+						MSR_FP);
 
-		case OP_31_XOP_STXSSPX:
-			if (kvmppc_check_vsx_disabled(vcpu))
-				return EMULATE_DONE;
-			vcpu->arch.mmio_vsx_copy_nums = 1;
-			vcpu->arch.mmio_vsx_copy_type = KVMPPC_VSX_COPY_DWORD;
-			vcpu->arch.mmio_sp64_extend = 1;
-			emulated = kvmppc_handle_vsx_store(run, vcpu,
-						 rs, 4, 1);
-			break;
+			if (op.type & FPCONV)
+				vcpu->arch.mmio_sp64_extend = 1;
 
-		case OP_31_XOP_STXSIWX:
-			if (kvmppc_check_vsx_disabled(vcpu))
-				return EMULATE_DONE;
-			vcpu->arch.mmio_vsx_offset = 1;
-			vcpu->arch.mmio_vsx_copy_nums = 1;
-			vcpu->arch.mmio_vsx_copy_type = KVMPPC_VSX_COPY_WORD;
-			emulated = kvmppc_handle_vsx_store(run, vcpu,
-							 rs, 4, 1);
-			break;
+			emulated = kvmppc_handle_store(run, vcpu,
+					VCPU_FPR(vcpu, op.reg), size, 1);
 
-		case OP_31_XOP_STXVD2X:
-			if (kvmppc_check_vsx_disabled(vcpu))
-				return EMULATE_DONE;
-			vcpu->arch.mmio_vsx_copy_nums = 2;
-			vcpu->arch.mmio_vsx_copy_type = KVMPPC_VSX_COPY_DWORD;
-			emulated = kvmppc_handle_vsx_store(run, vcpu,
-							 rs, 8, 1);
-			break;
+			if ((op.type & UPDATE) && (emulated != EMULATE_FAIL))
+				kvmppc_set_gpr(vcpu, op.update_reg, op.ea);
 
-		case OP_31_XOP_STXVW4X:
-			if (kvmppc_check_vsx_disabled(vcpu))
-				return EMULATE_DONE;
-			vcpu->arch.mmio_vsx_copy_nums = 4;
-			vcpu->arch.mmio_vsx_copy_type = KVMPPC_VSX_COPY_WORD;
-			emulated = kvmppc_handle_vsx_store(run, vcpu,
-							 rs, 4, 1);
 			break;
-#endif /* CONFIG_VSX */
-
+#endif
 #ifdef CONFIG_ALTIVEC
-		case OP_31_XOP_LVX:
+		case STORE_VMX:
 			if (kvmppc_check_altivec_disabled(vcpu))
 				return EMULATE_DONE;
-			vcpu->arch.vaddr_accessed &= ~0xFULL;
-			vcpu->arch.paddr_accessed &= ~0xFULL;
-			vcpu->arch.mmio_vmx_copy_nums = 2;
-			emulated = kvmppc_handle_load128_by2x64(run, vcpu,
-					KVM_MMIO_REG_VMX|rt, 1);
-			break;
 
-		case OP_31_XOP_STVX:
-			if (kvmppc_check_altivec_disabled(vcpu))
-				return EMULATE_DONE;
-			vcpu->arch.vaddr_accessed &= ~0xFULL;
-			vcpu->arch.paddr_accessed &= ~0xFULL;
-			vcpu->arch.mmio_vmx_copy_nums = 2;
-			emulated = kvmppc_handle_store128_by2x64(run, vcpu,
-					rs, 1);
-			break;
-#endif /* CONFIG_ALTIVEC */
+			/* Hardware enforces alignment of VMX accesses. */
+			vcpu->arch.vaddr_accessed &= ~((unsigned long)size - 1);
+			vcpu->arch.paddr_accessed &= ~((unsigned long)size - 1);
+
+			if (vcpu->kvm->arch.kvm_ops->giveup_ext)
+				vcpu->kvm->arch.kvm_ops->giveup_ext(vcpu,
+						MSR_VEC);
+			if (size == 16) { /* stvx */
+				vcpu->arch.mmio_copy_type =
+						KVMPPC_VMX_COPY_DWORD;
+			} else if (size == 4) { /* stvewx  */
+				vcpu->arch.mmio_copy_type =
+						KVMPPC_VMX_COPY_WORD;
+			} else if (size == 2) { /* stvehx  */
+				vcpu->arch.mmio_copy_type =
+						KVMPPC_VMX_COPY_HWORD;
+			} else if (size == 1) { /* stvebx  */
+				vcpu->arch.mmio_copy_type =
+						KVMPPC_VMX_COPY_BYTE;
+			} else
+				break;
+
+			vcpu->arch.mmio_vmx_offset =
+				(vcpu->arch.vaddr_accessed & 0xf)/size;
+
+			if (size == 16) {
+				vcpu->arch.mmio_vmx_copy_nums = 2;
+				emulated = kvmppc_handle_vmx_store(run,
+						vcpu, op.reg, 8, 1);
+			} else {
+				vcpu->arch.mmio_vmx_copy_nums = 1;
+				emulated = kvmppc_handle_vmx_store(run,
+						vcpu, op.reg, size, 1);
+			}
 
-		default:
-			emulated = EMULATE_FAIL;
 			break;
-		}
-		break;
-
-	case OP_LWZ:
-		emulated = kvmppc_handle_load(run, vcpu, rt, 4, 1);
-		break;
-
-#ifdef CONFIG_PPC_FPU
-	case OP_STFS:
-		if (kvmppc_check_fp_disabled(vcpu))
-			return EMULATE_DONE;
-		vcpu->arch.mmio_sp64_extend = 1;
-		emulated = kvmppc_handle_store(run, vcpu,
-			VCPU_FPR(vcpu, rs),
-			4, 1);
-		break;
-
-	case OP_STFSU:
-		if (kvmppc_check_fp_disabled(vcpu))
-			return EMULATE_DONE;
-		vcpu->arch.mmio_sp64_extend = 1;
-		emulated = kvmppc_handle_store(run, vcpu,
-			VCPU_FPR(vcpu, rs),
-			4, 1);
-		kvmppc_set_gpr(vcpu, ra, vcpu->arch.vaddr_accessed);
-		break;
-
-	case OP_STFD:
-		if (kvmppc_check_fp_disabled(vcpu))
-			return EMULATE_DONE;
-		emulated = kvmppc_handle_store(run, vcpu,
-			VCPU_FPR(vcpu, rs),
-	                               8, 1);
-		break;
-
-	case OP_STFDU:
-		if (kvmppc_check_fp_disabled(vcpu))
-			return EMULATE_DONE;
-		emulated = kvmppc_handle_store(run, vcpu,
-			VCPU_FPR(vcpu, rs),
-	                               8, 1);
-		kvmppc_set_gpr(vcpu, ra, vcpu->arch.vaddr_accessed);
-		break;
 #endif
+#ifdef CONFIG_VSX
+		case STORE_VSX: {
+			int io_size_each;
+
+			if (op.vsx_flags & VSX_CHECK_VEC) {
+				if (kvmppc_check_altivec_disabled(vcpu))
+					return EMULATE_DONE;
+			} else {
+				if (kvmppc_check_vsx_disabled(vcpu))
+					return EMULATE_DONE;
+			}
+
+			if (vcpu->kvm->arch.kvm_ops->giveup_ext)
+				vcpu->kvm->arch.kvm_ops->giveup_ext(vcpu,
+						MSR_VSX);
+
+			if (op.vsx_flags & VSX_FPCONV)
+				vcpu->arch.mmio_sp64_extend = 1;
+
+			if (op.element_size == 8)
+				vcpu->arch.mmio_copy_type =
+						KVMPPC_VSX_COPY_DWORD;
+			else if (op.element_size == 4)
+				vcpu->arch.mmio_copy_type =
+						KVMPPC_VSX_COPY_WORD;
+			else
+				break;
+
+			if (size < op.element_size) {
+				/* precise conversion case, like stxsspx */
+				vcpu->arch.mmio_vsx_copy_nums = 1;
+				io_size_each = size;
+			} else { /* stxvw4x, stxvd2x, etc */
+				vcpu->arch.mmio_vsx_copy_nums =
+						size/op.element_size;
+				io_size_each = op.element_size;
+			}
 
-	case OP_LD:
-		rt = get_rt(inst);
-		switch (inst & 3) {
-		case 0:	/* ld */
-			emulated = kvmppc_handle_load(run, vcpu, rt, 8, 1);
-			break;
-		case 1: /* ldu */
-			emulated = kvmppc_handle_load(run, vcpu, rt, 8, 1);
-			kvmppc_set_gpr(vcpu, ra, vcpu->arch.vaddr_accessed);
-			break;
-		case 2:	/* lwa */
-			emulated = kvmppc_handle_loads(run, vcpu, rt, 4, 1);
+			emulated = kvmppc_handle_vsx_store(run, vcpu,
+					op.reg & 0x1f, io_size_each, 1);
 			break;
-		default:
-			emulated = EMULATE_FAIL;
 		}
-		break;
-
-	case OP_LWZU:
-		emulated = kvmppc_handle_load(run, vcpu, rt, 4, 1);
-		kvmppc_set_gpr(vcpu, ra, vcpu->arch.vaddr_accessed);
-		break;
-
-	case OP_LBZ:
-		emulated = kvmppc_handle_load(run, vcpu, rt, 1, 1);
-		break;
-
-	case OP_LBZU:
-		emulated = kvmppc_handle_load(run, vcpu, rt, 1, 1);
-		kvmppc_set_gpr(vcpu, ra, vcpu->arch.vaddr_accessed);
-		break;
-
-	case OP_STW:
-		emulated = kvmppc_handle_store(run, vcpu,
-					       kvmppc_get_gpr(vcpu, rs),
-		                               4, 1);
-		break;
-
-	case OP_STD:
-		rs = get_rs(inst);
-		switch (inst & 3) {
-		case 0:	/* std */
-			emulated = kvmppc_handle_store(run, vcpu,
-				kvmppc_get_gpr(vcpu, rs), 8, 1);
-			break;
-		case 1: /* stdu */
-			emulated = kvmppc_handle_store(run, vcpu,
-				kvmppc_get_gpr(vcpu, rs), 8, 1);
-			kvmppc_set_gpr(vcpu, ra, vcpu->arch.vaddr_accessed);
+#endif
+		case CACHEOP:
+			/* Do nothing. The guest is performing dcbi because
+			 * hardware DMA is not snooped by the dcache, but
+			 * emulated DMA either goes through the dcache as
+			 * normal writes, or the host kernel has handled dcache
+			 * coherence.
+			 */
+			emulated = EMULATE_DONE;
 			break;
 		default:
-			emulated = EMULATE_FAIL;
+			break;
 		}
-		break;
-
-	case OP_STWU:
-		emulated = kvmppc_handle_store(run, vcpu,
-				kvmppc_get_gpr(vcpu, rs), 4, 1);
-		kvmppc_set_gpr(vcpu, ra, vcpu->arch.vaddr_accessed);
-		break;
-
-	case OP_STB:
-		emulated = kvmppc_handle_store(run, vcpu,
-				kvmppc_get_gpr(vcpu, rs), 1, 1);
-		break;
-
-	case OP_STBU:
-		emulated = kvmppc_handle_store(run, vcpu,
-				kvmppc_get_gpr(vcpu, rs), 1, 1);
-		kvmppc_set_gpr(vcpu, ra, vcpu->arch.vaddr_accessed);
-		break;
-
-	case OP_LHZ:
-		emulated = kvmppc_handle_load(run, vcpu, rt, 2, 1);
-		break;
-
-	case OP_LHZU:
-		emulated = kvmppc_handle_load(run, vcpu, rt, 2, 1);
-		kvmppc_set_gpr(vcpu, ra, vcpu->arch.vaddr_accessed);
-		break;
-
-	case OP_LHA:
-		emulated = kvmppc_handle_loads(run, vcpu, rt, 2, 1);
-		break;
-
-	case OP_LHAU:
-		emulated = kvmppc_handle_loads(run, vcpu, rt, 2, 1);
-		kvmppc_set_gpr(vcpu, ra, vcpu->arch.vaddr_accessed);
-		break;
-
-	case OP_STH:
-		emulated = kvmppc_handle_store(run, vcpu,
-				kvmppc_get_gpr(vcpu, rs), 2, 1);
-		break;
-
-	case OP_STHU:
-		emulated = kvmppc_handle_store(run, vcpu,
-				kvmppc_get_gpr(vcpu, rs), 2, 1);
-		kvmppc_set_gpr(vcpu, ra, vcpu->arch.vaddr_accessed);
-		break;
-
-#ifdef CONFIG_PPC_FPU
-	case OP_LFS:
-		if (kvmppc_check_fp_disabled(vcpu))
-			return EMULATE_DONE;
-		vcpu->arch.mmio_sp64_extend = 1;
-		emulated = kvmppc_handle_load(run, vcpu,
-			KVM_MMIO_REG_FPR|rt, 4, 1);
-		break;
-
-	case OP_LFSU:
-		if (kvmppc_check_fp_disabled(vcpu))
-			return EMULATE_DONE;
-		vcpu->arch.mmio_sp64_extend = 1;
-		emulated = kvmppc_handle_load(run, vcpu,
-			KVM_MMIO_REG_FPR|rt, 4, 1);
-		kvmppc_set_gpr(vcpu, ra, vcpu->arch.vaddr_accessed);
-		break;
-
-	case OP_LFD:
-		if (kvmppc_check_fp_disabled(vcpu))
-			return EMULATE_DONE;
-		emulated = kvmppc_handle_load(run, vcpu,
-			KVM_MMIO_REG_FPR|rt, 8, 1);
-		break;
-
-	case OP_LFDU:
-		if (kvmppc_check_fp_disabled(vcpu))
-			return EMULATE_DONE;
-		emulated = kvmppc_handle_load(run, vcpu,
-			KVM_MMIO_REG_FPR|rt, 8, 1);
-		kvmppc_set_gpr(vcpu, ra, vcpu->arch.vaddr_accessed);
-		break;
-#endif
-
-	default:
-		emulated = EMULATE_FAIL;
-		break;
 	}
 
 	if (emulated == EMULATE_FAIL) {

arch/powerpc/kvm/powerpc.c

@@ -648,9 +648,8 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 #endif
 #ifdef CONFIG_PPC_TRANSACTIONAL_MEM
 	case KVM_CAP_PPC_HTM:
-		r = hv_enabled &&
-		    (!!(cur_cpu_spec->cpu_user_features2 & PPC_FEATURE2_HTM) ||
-		     cpu_has_feature(CPU_FTR_P9_TM_HV_ASSIST));
+		r = !!(cur_cpu_spec->cpu_user_features2 & PPC_FEATURE2_HTM) ||
+		     (hv_enabled && cpu_has_feature(CPU_FTR_P9_TM_HV_ASSIST));
 		break;
 #endif
 	default:
@@ -907,6 +906,26 @@ static inline void kvmppc_set_vsr_dword_dump(struct kvm_vcpu *vcpu,
 	}
 }
 
+static inline void kvmppc_set_vsr_word_dump(struct kvm_vcpu *vcpu,
+	u32 gpr)
+{
+	union kvmppc_one_reg val;
+	int index = vcpu->arch.io_gpr & KVM_MMIO_REG_MASK;
+
+	if (vcpu->arch.mmio_vsx_tx_sx_enabled) {
+		val.vsx32val[0] = gpr;
+		val.vsx32val[1] = gpr;
+		val.vsx32val[2] = gpr;
+		val.vsx32val[3] = gpr;
+		VCPU_VSX_VR(vcpu, index) = val.vval;
+	} else {
+		val.vsx32val[0] = gpr;
+		val.vsx32val[1] = gpr;
+		VCPU_VSX_FPR(vcpu, index, 0) = val.vsxval[0];
+		VCPU_VSX_FPR(vcpu, index, 1) = val.vsxval[0];
+	}
+}
+
 static inline void kvmppc_set_vsr_word(struct kvm_vcpu *vcpu,
 	u32 gpr32)
 {
@@ -933,30 +952,110 @@ static inline void kvmppc_set_vsr_word(struct kvm_vcpu *vcpu,
 #endif /* CONFIG_VSX */
 
 #ifdef CONFIG_ALTIVEC
+static inline int kvmppc_get_vmx_offset_generic(struct kvm_vcpu *vcpu,
+		int index, int element_size)
+{
+	int offset;
+	int elts = sizeof(vector128)/element_size;
+
+	if ((index < 0) || (index >= elts))
+		return -1;
+
+	if (kvmppc_need_byteswap(vcpu))
+		offset = elts - index - 1;
+	else
+		offset = index;
+
+	return offset;
+}
+
+static inline int kvmppc_get_vmx_dword_offset(struct kvm_vcpu *vcpu,
+		int index)
+{
+	return kvmppc_get_vmx_offset_generic(vcpu, index, 8);
+}
+
+static inline int kvmppc_get_vmx_word_offset(struct kvm_vcpu *vcpu,
+		int index)
+{
+	return kvmppc_get_vmx_offset_generic(vcpu, index, 4);
+}
+
+static inline int kvmppc_get_vmx_hword_offset(struct kvm_vcpu *vcpu,
+		int index)
+{
+	return kvmppc_get_vmx_offset_generic(vcpu, index, 2);
+}
+
+static inline int kvmppc_get_vmx_byte_offset(struct kvm_vcpu *vcpu,
+		int index)
+{
+	return kvmppc_get_vmx_offset_generic(vcpu, index, 1);
+}
+
+
 static inline void kvmppc_set_vmx_dword(struct kvm_vcpu *vcpu,
-		u64 gpr)
+	u64 gpr)
 {
+	union kvmppc_one_reg val;
+	int offset = kvmppc_get_vmx_dword_offset(vcpu,
+			vcpu->arch.mmio_vmx_offset);
 	int index = vcpu->arch.io_gpr & KVM_MMIO_REG_MASK;
-	u32 hi, lo;
-	u32 di;
 
-#ifdef __BIG_ENDIAN
-	hi = gpr >> 32;
-	lo = gpr & 0xffffffff;
-#else
-	lo = gpr >> 32;
-	hi = gpr & 0xffffffff;
-#endif
+	if (offset == -1)
+		return;
+
+	val.vval = VCPU_VSX_VR(vcpu, index);
+	val.vsxval[offset] = gpr;
+	VCPU_VSX_VR(vcpu, index) = val.vval;
+}
+
+static inline void kvmppc_set_vmx_word(struct kvm_vcpu *vcpu,
+	u32 gpr32)
+{
+	union kvmppc_one_reg val;
+	int offset = kvmppc_get_vmx_word_offset(vcpu,
+			vcpu->arch.mmio_vmx_offset);
+	int index = vcpu->arch.io_gpr & KVM_MMIO_REG_MASK;
 
-	di = 2 - vcpu->arch.mmio_vmx_copy_nums;		/* doubleword index */
-	if (di > 1)
+	if (offset == -1)
 		return;
 
-	if (vcpu->arch.mmio_host_swabbed)
-		di = 1 - di;
+	val.vval = VCPU_VSX_VR(vcpu, index);
+	val.vsx32val[offset] = gpr32;
+	VCPU_VSX_VR(vcpu, index) = val.vval;
+}
+
+static inline void kvmppc_set_vmx_hword(struct kvm_vcpu *vcpu,
+	u16 gpr16)
+{
+	union kvmppc_one_reg val;
+	int offset = kvmppc_get_vmx_hword_offset(vcpu,
+			vcpu->arch.mmio_vmx_offset);
+	int index = vcpu->arch.io_gpr & KVM_MMIO_REG_MASK;
+
+	if (offset == -1)
+		return;
+
+	val.vval = VCPU_VSX_VR(vcpu, index);
+	val.vsx16val[offset] = gpr16;
+	VCPU_VSX_VR(vcpu, index) = val.vval;
+}
+
+static inline void kvmppc_set_vmx_byte(struct kvm_vcpu *vcpu,
+	u8 gpr8)
+{
+	union kvmppc_one_reg val;
+	int offset = kvmppc_get_vmx_byte_offset(vcpu,
+			vcpu->arch.mmio_vmx_offset);
+	int index = vcpu->arch.io_gpr & KVM_MMIO_REG_MASK;
+
+	if (offset == -1)
+		return;
 
-	VCPU_VSX_VR(vcpu, index).u[di * 2] = hi;
-	VCPU_VSX_VR(vcpu, index).u[di * 2 + 1] = lo;
+	val.vval = VCPU_VSX_VR(vcpu, index);
+	val.vsx8val[offset] = gpr8;
+	VCPU_VSX_VR(vcpu, index) = val.vval;
 }
 #endif /* CONFIG_ALTIVEC */
 
@@ -1041,6 +1140,9 @@ static void kvmppc_complete_mmio_load(struct kvm_vcpu *vcpu,
 		kvmppc_set_gpr(vcpu, vcpu->arch.io_gpr, gpr);
 		break;
 	case KVM_MMIO_REG_FPR:
+		if (vcpu->kvm->arch.kvm_ops->giveup_ext)
+			vcpu->kvm->arch.kvm_ops->giveup_ext(vcpu, MSR_FP);
+
 		VCPU_FPR(vcpu, vcpu->arch.io_gpr & KVM_MMIO_REG_MASK) = gpr;
 		break;
 #ifdef CONFIG_PPC_BOOK3S
@@ -1054,18 +1156,36 @@ static void kvmppc_complete_mmio_load(struct kvm_vcpu *vcpu,
 #endif
 #ifdef CONFIG_VSX
 	case KVM_MMIO_REG_VSX:
-		if (vcpu->arch.mmio_vsx_copy_type == KVMPPC_VSX_COPY_DWORD)
+		if (vcpu->kvm->arch.kvm_ops->giveup_ext)
+			vcpu->kvm->arch.kvm_ops->giveup_ext(vcpu, MSR_VSX);
+
+		if (vcpu->arch.mmio_copy_type == KVMPPC_VSX_COPY_DWORD)
 			kvmppc_set_vsr_dword(vcpu, gpr);
-		else if (vcpu->arch.mmio_vsx_copy_type == KVMPPC_VSX_COPY_WORD)
+		else if (vcpu->arch.mmio_copy_type == KVMPPC_VSX_COPY_WORD)
 			kvmppc_set_vsr_word(vcpu, gpr);
-		else if (vcpu->arch.mmio_vsx_copy_type ==
+		else if (vcpu->arch.mmio_copy_type ==
 				KVMPPC_VSX_COPY_DWORD_LOAD_DUMP)
 			kvmppc_set_vsr_dword_dump(vcpu, gpr);
+		else if (vcpu->arch.mmio_copy_type ==
+				KVMPPC_VSX_COPY_WORD_LOAD_DUMP)
+			kvmppc_set_vsr_word_dump(vcpu, gpr);
 		break;
 #endif
 #ifdef CONFIG_ALTIVEC
 	case KVM_MMIO_REG_VMX:
-		kvmppc_set_vmx_dword(vcpu, gpr);
+		if (vcpu->kvm->arch.kvm_ops->giveup_ext)
+			vcpu->kvm->arch.kvm_ops->giveup_ext(vcpu, MSR_VEC);
+
+		if (vcpu->arch.mmio_copy_type == KVMPPC_VMX_COPY_DWORD)
+			kvmppc_set_vmx_dword(vcpu, gpr);
+		else if (vcpu->arch.mmio_copy_type == KVMPPC_VMX_COPY_WORD)
+			kvmppc_set_vmx_word(vcpu, gpr);
+		else if (vcpu->arch.mmio_copy_type ==
+				KVMPPC_VMX_COPY_HWORD)
+			kvmppc_set_vmx_hword(vcpu, gpr);
+		else if (vcpu->arch.mmio_copy_type ==
+				KVMPPC_VMX_COPY_BYTE)
+			kvmppc_set_vmx_byte(vcpu, gpr);
 		break;
 #endif
 	default:
@@ -1228,7 +1348,7 @@ static inline int kvmppc_get_vsr_data(struct kvm_vcpu *vcpu, int rs, u64 *val)
 	u32 dword_offset, word_offset;
 	union kvmppc_one_reg reg;
 	int vsx_offset = 0;
-	int copy_type = vcpu->arch.mmio_vsx_copy_type;
+	int copy_type = vcpu->arch.mmio_copy_type;
 	int result = 0;
 
 	switch (copy_type) {
@@ -1344,14 +1464,16 @@ static int kvmppc_emulate_mmio_vsx_loadstore(struct kvm_vcpu *vcpu,
 #endif /* CONFIG_VSX */
 
 #ifdef CONFIG_ALTIVEC
-/* handle quadword load access in two halves */
-int kvmppc_handle_load128_by2x64(struct kvm_run *run, struct kvm_vcpu *vcpu,
-		unsigned int rt, int is_default_endian)
+int kvmppc_handle_vmx_load(struct kvm_run *run, struct kvm_vcpu *vcpu,
+		unsigned int rt, unsigned int bytes, int is_default_endian)
 {
 	enum emulation_result emulated = EMULATE_DONE;
 
+	if (vcpu->arch.mmio_vsx_copy_nums > 2)
+		return EMULATE_FAIL;
+
 	while (vcpu->arch.mmio_vmx_copy_nums) {
-		emulated = __kvmppc_handle_load(run, vcpu, rt, 8,
+		emulated = __kvmppc_handle_load(run, vcpu, rt, bytes,
 				is_default_endian, 0);
 
 		if (emulated != EMULATE_DONE)
@@ -1359,55 +1481,127 @@ int kvmppc_handle_load128_by2x64(struct kvm_run *run, struct kvm_vcpu *vcpu,
 
 		vcpu->arch.paddr_accessed += run->mmio.len;
 		vcpu->arch.mmio_vmx_copy_nums--;
+		vcpu->arch.mmio_vmx_offset++;
 	}
 
 	return emulated;
 }
 
-static inline int kvmppc_get_vmx_data(struct kvm_vcpu *vcpu, int rs, u64 *val)
+int kvmppc_get_vmx_dword(struct kvm_vcpu *vcpu, int index, u64 *val)
 {
-	vector128 vrs = VCPU_VSX_VR(vcpu, rs);
-	u32 di;
-	u64 w0, w1;
+	union kvmppc_one_reg reg;
+	int vmx_offset = 0;
+	int result = 0;
 
-	di = 2 - vcpu->arch.mmio_vmx_copy_nums;		/* doubleword index */
-	if (di > 1)
+	vmx_offset =
+		kvmppc_get_vmx_dword_offset(vcpu, vcpu->arch.mmio_vmx_offset);
+
+	if (vmx_offset == -1)
 		return -1;
 
-	if (vcpu->arch.mmio_host_swabbed)
-		di = 1 - di;
+	reg.vval = VCPU_VSX_VR(vcpu, index);
+	*val = reg.vsxval[vmx_offset];
 
-	w0 = vrs.u[di * 2];
-	w1 = vrs.u[di * 2 + 1];
+	return result;
+}
 
-#ifdef __BIG_ENDIAN
-	*val = (w0 << 32) | w1;
-#else
-	*val = (w1 << 32) | w0;
-#endif
-	return 0;
+int kvmppc_get_vmx_word(struct kvm_vcpu *vcpu, int index, u64 *val)
+{
+	union kvmppc_one_reg reg;
+	int vmx_offset = 0;
+	int result = 0;
+
+	vmx_offset =
+		kvmppc_get_vmx_word_offset(vcpu, vcpu->arch.mmio_vmx_offset);
+
+	if (vmx_offset == -1)
+		return -1;
+
+	reg.vval = VCPU_VSX_VR(vcpu, index);
+	*val = reg.vsx32val[vmx_offset];
+
+	return result;
+}
+
+int kvmppc_get_vmx_hword(struct kvm_vcpu *vcpu, int index, u64 *val)
+{
+	union kvmppc_one_reg reg;
+	int vmx_offset = 0;
+	int result = 0;
+
+	vmx_offset =
+		kvmppc_get_vmx_hword_offset(vcpu, vcpu->arch.mmio_vmx_offset);
+
+	if (vmx_offset == -1)
+		return -1;
+
+	reg.vval = VCPU_VSX_VR(vcpu, index);
+	*val = reg.vsx16val[vmx_offset];
+
+	return result;
 }
 
-/* handle quadword store in two halves */
-int kvmppc_handle_store128_by2x64(struct kvm_run *run, struct kvm_vcpu *vcpu,
-		unsigned int rs, int is_default_endian)
+int kvmppc_get_vmx_byte(struct kvm_vcpu *vcpu, int index, u64 *val)
+{
+	union kvmppc_one_reg reg;
+	int vmx_offset = 0;
+	int result = 0;
+
+	vmx_offset =
+		kvmppc_get_vmx_byte_offset(vcpu, vcpu->arch.mmio_vmx_offset);
+
+	if (vmx_offset == -1)
+		return -1;
+
+	reg.vval = VCPU_VSX_VR(vcpu, index);
+	*val = reg.vsx8val[vmx_offset];
+
+	return result;
+}
+
+int kvmppc_handle_vmx_store(struct kvm_run *run, struct kvm_vcpu *vcpu,
+		unsigned int rs, unsigned int bytes, int is_default_endian)
 {
 	u64 val = 0;
+	unsigned int index = rs & KVM_MMIO_REG_MASK;
 	enum emulation_result emulated = EMULATE_DONE;
 
+	if (vcpu->arch.mmio_vsx_copy_nums > 2)
+		return EMULATE_FAIL;
+
 	vcpu->arch.io_gpr = rs;
 
 	while (vcpu->arch.mmio_vmx_copy_nums) {
-		if (kvmppc_get_vmx_data(vcpu, rs, &val) == -1)
+		switch (vcpu->arch.mmio_copy_type) {
+		case KVMPPC_VMX_COPY_DWORD:
+			if (kvmppc_get_vmx_dword(vcpu, index, &val) == -1)
+				return EMULATE_FAIL;
+
+			break;
+		case KVMPPC_VMX_COPY_WORD:
+			if (kvmppc_get_vmx_word(vcpu, index, &val) == -1)
+				return EMULATE_FAIL;
+			break;
+		case KVMPPC_VMX_COPY_HWORD:
+			if (kvmppc_get_vmx_hword(vcpu, index, &val) == -1)
+				return EMULATE_FAIL;
+			break;
+		case KVMPPC_VMX_COPY_BYTE:
+			if (kvmppc_get_vmx_byte(vcpu, index, &val) == -1)
+				return EMULATE_FAIL;
+			break;
+		default:
 			return EMULATE_FAIL;
+		}
 
-		emulated = kvmppc_handle_store(run, vcpu, val, 8,
+		emulated = kvmppc_handle_store(run, vcpu, val, bytes,
 				is_default_endian);
 		if (emulated != EMULATE_DONE)
 			break;
 
 		vcpu->arch.paddr_accessed += run->mmio.len;
 		vcpu->arch.mmio_vmx_copy_nums--;
+		vcpu->arch.mmio_vmx_offset++;
 	}
 
 	return emulated;
@@ -1422,11 +1616,11 @@ static int kvmppc_emulate_mmio_vmx_loadstore(struct kvm_vcpu *vcpu,
 	vcpu->arch.paddr_accessed += run->mmio.len;
 
 	if (!vcpu->mmio_is_write) {
-		emulated = kvmppc_handle_load128_by2x64(run, vcpu,
-				vcpu->arch.io_gpr, 1);
+		emulated = kvmppc_handle_vmx_load(run, vcpu,
+				vcpu->arch.io_gpr, run->mmio.len, 1);
 	} else {
-		emulated = kvmppc_handle_store128_by2x64(run, vcpu,
-				vcpu->arch.io_gpr, 1);
+		emulated = kvmppc_handle_vmx_store(run, vcpu,
+				vcpu->arch.io_gpr, run->mmio.len, 1);
 	}
 
 	switch (emulated) {
@@ -1570,8 +1764,10 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run)
 		}
 #endif
 #ifdef CONFIG_ALTIVEC
-		if (vcpu->arch.mmio_vmx_copy_nums > 0)
+		if (vcpu->arch.mmio_vmx_copy_nums > 0) {
 			vcpu->arch.mmio_vmx_copy_nums--;
+			vcpu->arch.mmio_vmx_offset++;
+		}
 
 		if (vcpu->arch.mmio_vmx_copy_nums > 0) {
 			r = kvmppc_emulate_mmio_vmx_loadstore(vcpu, run);
@@ -1784,16 +1980,16 @@ long kvm_arch_vcpu_ioctl(struct file *filp,
 	void __user *argp = (void __user *)arg;
 	long r;
 
-	vcpu_load(vcpu);
-
 	switch (ioctl) {
 	case KVM_ENABLE_CAP:
 	{
 		struct kvm_enable_cap cap;
 		r = -EFAULT;
+		vcpu_load(vcpu);
 		if (copy_from_user(&cap, argp, sizeof(cap)))
 			goto out;
 		r = kvm_vcpu_ioctl_enable_cap(vcpu, &cap);
+		vcpu_put(vcpu);
 		break;
 	}
 
@@ -1815,9 +2011,11 @@ long kvm_arch_vcpu_ioctl(struct file *filp,
 	case KVM_DIRTY_TLB: {
 		struct kvm_dirty_tlb dirty;
 		r = -EFAULT;
+		vcpu_load(vcpu);
 		if (copy_from_user(&dirty, argp, sizeof(dirty)))
 			goto out;
 		r = kvm_vcpu_ioctl_dirty_tlb(vcpu, &dirty);
+		vcpu_put(vcpu);
 		break;
 	}
 #endif
@@ -1826,7 +2024,6 @@ long kvm_arch_vcpu_ioctl(struct file *filp,
 	}
 
 out:
-	vcpu_put(vcpu);
 	return r;
 }
 

arch/powerpc/kvm/tm.S

@@ -0,0 +1,384 @@
+/*
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License, version 2, as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * Derived from book3s_hv_rmhandlers.S, which is:
+ *
+ * Copyright 2011 Paul Mackerras, IBM Corp. <paulus@au1.ibm.com>
+ *
+ */
+
+#include <asm/reg.h>
+#include <asm/ppc_asm.h>
+#include <asm/asm-offsets.h>
+#include <asm/export.h>
+#include <asm/tm.h>
+#include <asm/cputable.h>
+
+#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+#define VCPU_GPRS_TM(reg) (((reg) * ULONG_SIZE) + VCPU_GPR_TM)
+
+/*
+ * Save transactional state and TM-related registers.
+ * Called with:
+ * - r3 pointing to the vcpu struct
+ * - r4 points to the MSR with current TS bits:
+ * 	(For HV KVM, it is VCPU_MSR ; For PR KVM, it is host MSR).
+ * This can modify all checkpointed registers, but
+ * restores r1, r2 before exit.
+ */
+_GLOBAL(__kvmppc_save_tm)
+	mflr	r0
+	std	r0, PPC_LR_STKOFF(r1)
+
+	/* Turn on TM. */
+	mfmsr	r8
+	li	r0, 1
+	rldimi	r8, r0, MSR_TM_LG, 63-MSR_TM_LG
+	ori     r8, r8, MSR_FP
+	oris    r8, r8, (MSR_VEC | MSR_VSX)@h
+	mtmsrd	r8
+
+	rldicl. r4, r4, 64 - MSR_TS_S_LG, 62
+	beq	1f	/* TM not active in guest. */
+
+	std	r1, HSTATE_SCRATCH2(r13)
+	std	r3, HSTATE_SCRATCH1(r13)
+
+#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
+BEGIN_FTR_SECTION
+	/* Emulation of the treclaim instruction needs TEXASR before treclaim */
+	mfspr	r6, SPRN_TEXASR
+	std	r6, VCPU_ORIG_TEXASR(r3)
+END_FTR_SECTION_IFSET(CPU_FTR_P9_TM_HV_ASSIST)
+#endif
+
+	/* Clear the MSR RI since r1, r13 are all going to be foobar. */
+	li	r5, 0
+	mtmsrd	r5, 1
+
+	li	r3, TM_CAUSE_KVM_RESCHED
+
+	/* All GPRs are volatile at this point. */
+	TRECLAIM(R3)
+
+	/* Temporarily store r13 and r9 so we have some regs to play with */
+	SET_SCRATCH0(r13)
+	GET_PACA(r13)
+	std	r9, PACATMSCRATCH(r13)
+	ld	r9, HSTATE_SCRATCH1(r13)
+
+	/* Get a few more GPRs free. */
+	std	r29, VCPU_GPRS_TM(29)(r9)
+	std	r30, VCPU_GPRS_TM(30)(r9)
+	std	r31, VCPU_GPRS_TM(31)(r9)
+
+	/* Save away PPR and DSCR soon so don't run with user values. */
+	mfspr	r31, SPRN_PPR
+	HMT_MEDIUM
+	mfspr	r30, SPRN_DSCR
+#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
+	ld	r29, HSTATE_DSCR(r13)
+	mtspr	SPRN_DSCR, r29
+#endif
+
+	/* Save all but r9, r13 & r29-r31 */
+	reg = 0
+	.rept	29
+	.if (reg != 9) && (reg != 13)
+	std	reg, VCPU_GPRS_TM(reg)(r9)
+	.endif
+	reg = reg + 1
+	.endr
+	/* ... now save r13 */
+	GET_SCRATCH0(r4)
+	std	r4, VCPU_GPRS_TM(13)(r9)
+	/* ... and save r9 */
+	ld	r4, PACATMSCRATCH(r13)
+	std	r4, VCPU_GPRS_TM(9)(r9)
+
+	/* Reload stack pointer and TOC. */
+	ld	r1, HSTATE_SCRATCH2(r13)
+	ld	r2, PACATOC(r13)
+
+	/* Set MSR RI now we have r1 and r13 back. */
+	li	r5, MSR_RI
+	mtmsrd	r5, 1
+
+	/* Save away checkpinted SPRs. */
+	std	r31, VCPU_PPR_TM(r9)
+	std	r30, VCPU_DSCR_TM(r9)
+	mflr	r5
+	mfcr	r6
+	mfctr	r7
+	mfspr	r8, SPRN_AMR
+	mfspr	r10, SPRN_TAR
+	mfxer	r11
+	std	r5, VCPU_LR_TM(r9)
+	stw	r6, VCPU_CR_TM(r9)
+	std	r7, VCPU_CTR_TM(r9)
+	std	r8, VCPU_AMR_TM(r9)
+	std	r10, VCPU_TAR_TM(r9)
+	std	r11, VCPU_XER_TM(r9)
+
+	/* Restore r12 as trap number. */
+	lwz	r12, VCPU_TRAP(r9)
+
+	/* Save FP/VSX. */
+	addi	r3, r9, VCPU_FPRS_TM
+	bl	store_fp_state
+	addi	r3, r9, VCPU_VRS_TM
+	bl	store_vr_state
+	mfspr	r6, SPRN_VRSAVE
+	stw	r6, VCPU_VRSAVE_TM(r9)
+1:
+	/*
+	 * We need to save these SPRs after the treclaim so that the software
+	 * error code is recorded correctly in the TEXASR.  Also the user may
+	 * change these outside of a transaction, so they must always be
+	 * context switched.
+	 */
+	mfspr	r7, SPRN_TEXASR
+	std	r7, VCPU_TEXASR(r9)
+11:
+	mfspr	r5, SPRN_TFHAR
+	mfspr	r6, SPRN_TFIAR
+	std	r5, VCPU_TFHAR(r9)
+	std	r6, VCPU_TFIAR(r9)
+
+	ld	r0, PPC_LR_STKOFF(r1)
+	mtlr	r0
+	blr
+
+/*
+ * _kvmppc_save_tm_pr() is a wrapper around __kvmppc_save_tm(), so that it can
+ * be invoked from C function by PR KVM only.
+ */
+_GLOBAL(_kvmppc_save_tm_pr)
+	mflr	r5
+	std	r5, PPC_LR_STKOFF(r1)
+	stdu    r1, -SWITCH_FRAME_SIZE(r1)
+	SAVE_NVGPRS(r1)
+
+	/* save MSR since TM/math bits might be impacted
+	 * by __kvmppc_save_tm().
+	 */
+	mfmsr	r5
+	SAVE_GPR(5, r1)
+
+	/* also save DSCR/CR/TAR so that it can be recovered later */
+	mfspr   r6, SPRN_DSCR
+	SAVE_GPR(6, r1)
+
+	mfcr    r7
+	stw     r7, _CCR(r1)
+
+	mfspr   r8, SPRN_TAR
+	SAVE_GPR(8, r1)
+
+	bl	__kvmppc_save_tm
+
+	REST_GPR(8, r1)
+	mtspr   SPRN_TAR, r8
+
+	ld      r7, _CCR(r1)
+	mtcr	r7
+
+	REST_GPR(6, r1)
+	mtspr   SPRN_DSCR, r6
+
+	/* need preserve current MSR's MSR_TS bits */
+	REST_GPR(5, r1)
+	mfmsr   r6
+	rldicl  r6, r6, 64 - MSR_TS_S_LG, 62
+	rldimi  r5, r6, MSR_TS_S_LG, 63 - MSR_TS_T_LG
+	mtmsrd  r5
+
+	REST_NVGPRS(r1)
+	addi    r1, r1, SWITCH_FRAME_SIZE
+	ld	r5, PPC_LR_STKOFF(r1)
+	mtlr	r5
+	blr
+
+EXPORT_SYMBOL_GPL(_kvmppc_save_tm_pr);
+
+/*
+ * Restore transactional state and TM-related registers.
+ * Called with:
+ *  - r3 pointing to the vcpu struct.
+ *  - r4 is the guest MSR with desired TS bits:
+ * 	For HV KVM, it is VCPU_MSR
+ * 	For PR KVM, it is provided by caller
+ * This potentially modifies all checkpointed registers.
+ * It restores r1, r2 from the PACA.
+ */
+_GLOBAL(__kvmppc_restore_tm)
+	mflr	r0
+	std	r0, PPC_LR_STKOFF(r1)
+
+	/* Turn on TM/FP/VSX/VMX so we can restore them. */
+	mfmsr	r5
+	li	r6, MSR_TM >> 32
+	sldi	r6, r6, 32
+	or	r5, r5, r6
+	ori	r5, r5, MSR_FP
+	oris	r5, r5, (MSR_VEC | MSR_VSX)@h
+	mtmsrd	r5
+
+	/*
+	 * The user may change these outside of a transaction, so they must
+	 * always be context switched.
+	 */
+	ld	r5, VCPU_TFHAR(r3)
+	ld	r6, VCPU_TFIAR(r3)
+	ld	r7, VCPU_TEXASR(r3)
+	mtspr	SPRN_TFHAR, r5
+	mtspr	SPRN_TFIAR, r6
+	mtspr	SPRN_TEXASR, r7
+
+	mr	r5, r4
+	rldicl. r5, r5, 64 - MSR_TS_S_LG, 62
+	beqlr		/* TM not active in guest */
+	std	r1, HSTATE_SCRATCH2(r13)
+
+	/* Make sure the failure summary is set, otherwise we'll program check
+	 * when we trechkpt.  It's possible that this might have been not set
+	 * on a kvmppc_set_one_reg() call but we shouldn't let this crash the
+	 * host.
+	 */
+	oris	r7, r7, (TEXASR_FS)@h
+	mtspr	SPRN_TEXASR, r7
+
+	/*
+	 * We need to load up the checkpointed state for the guest.
+	 * We need to do this early as it will blow away any GPRs, VSRs and
+	 * some SPRs.
+	 */
+
+	mr	r31, r3
+	addi	r3, r31, VCPU_FPRS_TM
+	bl	load_fp_state
+	addi	r3, r31, VCPU_VRS_TM
+	bl	load_vr_state
+	mr	r3, r31
+	lwz	r7, VCPU_VRSAVE_TM(r3)
+	mtspr	SPRN_VRSAVE, r7
+
+	ld	r5, VCPU_LR_TM(r3)
+	lwz	r6, VCPU_CR_TM(r3)
+	ld	r7, VCPU_CTR_TM(r3)
+	ld	r8, VCPU_AMR_TM(r3)
+	ld	r9, VCPU_TAR_TM(r3)
+	ld	r10, VCPU_XER_TM(r3)
+	mtlr	r5
+	mtcr	r6
+	mtctr	r7
+	mtspr	SPRN_AMR, r8
+	mtspr	SPRN_TAR, r9
+	mtxer	r10
+
+	/*
+	 * Load up PPR and DSCR values but don't put them in the actual SPRs
+	 * till the last moment to avoid running with userspace PPR and DSCR for
+	 * too long.
+	 */
+	ld	r29, VCPU_DSCR_TM(r3)
+	ld	r30, VCPU_PPR_TM(r3)
+
+	std	r2, PACATMSCRATCH(r13) /* Save TOC */
+
+	/* Clear the MSR RI since r1, r13 are all going to be foobar. */
+	li	r5, 0
+	mtmsrd	r5, 1
+
+	/* Load GPRs r0-r28 */
+	reg = 0
+	.rept	29
+	ld	reg, VCPU_GPRS_TM(reg)(r31)
+	reg = reg + 1
+	.endr
+
+	mtspr	SPRN_DSCR, r29
+	mtspr	SPRN_PPR, r30
+
+	/* Load final GPRs */
+	ld	29, VCPU_GPRS_TM(29)(r31)
+	ld	30, VCPU_GPRS_TM(30)(r31)
+	ld	31, VCPU_GPRS_TM(31)(r31)
+
+	/* TM checkpointed state is now setup.  All GPRs are now volatile. */
+	TRECHKPT
+
+	/* Now let's get back the state we need. */
+	HMT_MEDIUM
+	GET_PACA(r13)
+#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
+	ld	r29, HSTATE_DSCR(r13)
+	mtspr	SPRN_DSCR, r29
+#endif
+	ld	r1, HSTATE_SCRATCH2(r13)
+	ld	r2, PACATMSCRATCH(r13)
+
+	/* Set the MSR RI since we have our registers back. */
+	li	r5, MSR_RI
+	mtmsrd	r5, 1
+	ld	r0, PPC_LR_STKOFF(r1)
+	mtlr	r0
+	blr
+
+/*
+ * _kvmppc_restore_tm_pr() is a wrapper around __kvmppc_restore_tm(), so that it
+ * can be invoked from C function by PR KVM only.
+ */
+_GLOBAL(_kvmppc_restore_tm_pr)
+	mflr	r5
+	std	r5, PPC_LR_STKOFF(r1)
+	stdu    r1, -SWITCH_FRAME_SIZE(r1)
+	SAVE_NVGPRS(r1)
+
+	/* save MSR to avoid TM/math bits change */
+	mfmsr	r5
+	SAVE_GPR(5, r1)
+
+	/* also save DSCR/CR/TAR so that it can be recovered later */
+	mfspr   r6, SPRN_DSCR
+	SAVE_GPR(6, r1)
+
+	mfcr    r7
+	stw     r7, _CCR(r1)
+
+	mfspr   r8, SPRN_TAR
+	SAVE_GPR(8, r1)
+
+	bl	__kvmppc_restore_tm
+
+	REST_GPR(8, r1)
+	mtspr   SPRN_TAR, r8
+
+	ld      r7, _CCR(r1)
+	mtcr	r7
+
+	REST_GPR(6, r1)
+	mtspr   SPRN_DSCR, r6
+
+	/* need preserve current MSR's MSR_TS bits */
+	REST_GPR(5, r1)
+	mfmsr   r6
+	rldicl  r6, r6, 64 - MSR_TS_S_LG, 62
+	rldimi  r5, r6, MSR_TS_S_LG, 63 - MSR_TS_T_LG
+	mtmsrd  r5
+
+	REST_NVGPRS(r1)
+	addi    r1, r1, SWITCH_FRAME_SIZE
+	ld	r5, PPC_LR_STKOFF(r1)
+	mtlr	r5
+	blr
+
+EXPORT_SYMBOL_GPL(_kvmppc_restore_tm_pr);
+#endif /* CONFIG_PPC_TRANSACTIONAL_MEM */