Merge tag 'kvm-3.15-1' of git://git.kernel.org/pub/scm/virt/kvm/kvm

Pull kvm updates from Paolo Bonzini:
 "PPC and ARM do not have much going on this time.  Most of the cool
  stuff, instead, is in s390 and (after a few releases) x86.

  ARM has some caching fixes and PPC has transactional memory support in
  guests.  MIPS has some fixes, with more probably coming in 3.16 as
  QEMU will soon get support for MIPS KVM.

  For x86 there are optimizations for debug registers, which trigger on
  some Windows games, and other important fixes for Windows guests.  We
  now expose to the guest Broadwell instruction set extensions and also
  Intel MPX.  There's also a fix/workaround for OS X guests, nested
  virtualization features (preemption timer), and a couple kvmclock
  refinements.

  For s390, the main news is asynchronous page faults, together with
  improvements to IRQs (floating irqs and adapter irqs) that speed up
  virtio devices"

* tag 'kvm-3.15-1' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (96 commits)
  KVM: PPC: Book3S HV: Save/restore host PMU registers that are new in POWER8
  KVM: PPC: Book3S HV: Fix decrementer timeouts with non-zero TB offset
  KVM: PPC: Book3S HV: Don't use kvm_memslots() in real mode
  KVM: PPC: Book3S HV: Return ENODEV error rather than EIO
  KVM: PPC: Book3S: Trim top 4 bits of physical address in RTAS code
  KVM: PPC: Book3S HV: Add get/set_one_reg for new TM state
  KVM: PPC: Book3S HV: Add transactional memory support
  KVM: Specify byte order for KVM_EXIT_MMIO
  KVM: vmx: fix MPX detection
  KVM: PPC: Book3S HV: Fix KVM hang with CONFIG_KVM_XICS=n
  KVM: PPC: Book3S: Introduce hypervisor call H_GET_TCE
  KVM: PPC: Book3S HV: Fix incorrect userspace exit on ioeventfd write
  KVM: s390: clear local interrupts at cpu initial reset
  KVM: s390: Fix possible memory leak in SIGP functions
  KVM: s390: fix calculation of idle_mask array size
  KVM: s390: randomize sca address
  KVM: ioapic: reinject pending interrupts on KVM_SET_IRQCHIP
  KVM: Bump KVM_MAX_IRQ_ROUTES for s390
  KVM: s390: irq routing for adapter interrupts.
  KVM: s390: adapter interrupt sources
  ...

7 files changed, 352 insertions, 66 deletions

diff --git a/arch/powerpc/kvm/book3s_64_mmu_hv.c b/arch/powerpc/kvm/book3s_64_mmu_hv.c
index 303ece75b8e4..fb25ebc0af0c 100644
--- a/arch/powerpc/kvm/book3s_64_mmu_hv.c
+++ b/arch/powerpc/kvm/book3s_64_mmu_hv.c
@@ -262,7 +262,14 @@ int kvmppc_mmu_hv_init(void)
 
 static void kvmppc_mmu_book3s_64_hv_reset_msr(struct kvm_vcpu *vcpu)
 {
-	kvmppc_set_msr(vcpu, vcpu->arch.intr_msr);
+	unsigned long msr = vcpu->arch.intr_msr;
+
+	/* If transactional, change to suspend mode on IRQ delivery */
+	if (MSR_TM_TRANSACTIONAL(vcpu->arch.shregs.msr))
+		msr |= MSR_TS_S;
+	else
+		msr |= vcpu->arch.shregs.msr & MSR_TS_MASK;
+	kvmppc_set_msr(vcpu, msr);
 }
 
 /*
diff --git a/arch/powerpc/kvm/book3s_64_vio_hv.c b/arch/powerpc/kvm/book3s_64_vio_hv.c
index 2c25f5412bdb..89e96b3e0039 100644
--- a/arch/powerpc/kvm/book3s_64_vio_hv.c
+++ b/arch/powerpc/kvm/book3s_64_vio_hv.c
@@ -75,3 +75,31 @@ long kvmppc_h_put_tce(struct kvm_vcpu *vcpu, unsigned long liobn,
 	return H_TOO_HARD;
 }
 EXPORT_SYMBOL_GPL(kvmppc_h_put_tce);
+
+long kvmppc_h_get_tce(struct kvm_vcpu *vcpu, unsigned long liobn,
+		      unsigned long ioba)
+{
+	struct kvm *kvm = vcpu->kvm;
+	struct kvmppc_spapr_tce_table *stt;
+
+	list_for_each_entry(stt, &kvm->arch.spapr_tce_tables, list) {
+		if (stt->liobn == liobn) {
+			unsigned long idx = ioba >> SPAPR_TCE_SHIFT;
+			struct page *page;
+			u64 *tbl;
+
+			if (ioba >= stt->window_size)
+				return H_PARAMETER;
+
+			page = stt->pages[idx / TCES_PER_PAGE];
+			tbl = (u64 *)page_address(page);
+
+			vcpu->arch.gpr[4] = tbl[idx % TCES_PER_PAGE];
+			return H_SUCCESS;
+		}
+	}
+
+	/* Didn't find the liobn, punt it to userspace */
+	return H_TOO_HARD;
+}
+EXPORT_SYMBOL_GPL(kvmppc_h_get_tce);
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index 17fc9496b6ac..8227dba5af0f 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -86,7 +86,7 @@ static void kvmppc_fast_vcpu_kick_hv(struct kvm_vcpu *vcpu)
 
 	/* CPU points to the first thread of the core */
 	if (cpu != me && cpu >= 0 && cpu < nr_cpu_ids) {
-#ifdef CONFIG_KVM_XICS
+#ifdef CONFIG_PPC_ICP_NATIVE
 		int real_cpu = cpu + vcpu->arch.ptid;
 		if (paca[real_cpu].kvm_hstate.xics_phys)
 			xics_wake_cpu(real_cpu);
@@ -879,17 +879,6 @@ static int kvmppc_get_one_reg_hv(struct kvm_vcpu *vcpu, u64 id,
 	case KVM_REG_PPC_IAMR:
 		*val = get_reg_val(id, vcpu->arch.iamr);
 		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;
-#endif
 	case KVM_REG_PPC_FSCR:
 		*val = get_reg_val(id, vcpu->arch.fscr);
 		break;
@@ -970,6 +959,69 @@ static int kvmppc_get_one_reg_hv(struct kvm_vcpu *vcpu, u64 id,
 	case KVM_REG_PPC_PPR:
 		*val = get_reg_val(id, vcpu->arch.ppr);
 		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:
+		i = id - KVM_REG_PPC_TM_GPR0;
+		*val = get_reg_val(id, vcpu->arch.gpr_tm[i]);
+		break;
+	case KVM_REG_PPC_TM_VSR0 ... KVM_REG_PPC_TM_VSR63:
+	{
+		int 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_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
 	case KVM_REG_PPC_ARCH_COMPAT:
 		*val = get_reg_val(id, vcpu->arch.vcore->arch_compat);
 		break;
@@ -1039,17 +1091,6 @@ static int kvmppc_set_one_reg_hv(struct kvm_vcpu *vcpu, u64 id,
 	case KVM_REG_PPC_IAMR:
 		vcpu->arch.iamr = 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;
-#endif
 	case KVM_REG_PPC_FSCR:
 		vcpu->arch.fscr = set_reg_val(id, *val);
 		break;
@@ -1144,6 +1185,68 @@ static int kvmppc_set_one_reg_hv(struct kvm_vcpu *vcpu, u64 id,
 	case KVM_REG_PPC_PPR:
 		vcpu->arch.ppr = 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:
+		i = id - KVM_REG_PPC_TM_GPR0;
+		vcpu->arch.gpr_tm[i] = set_reg_val(id, *val);
+		break;
+	case KVM_REG_PPC_TM_VSR0 ... KVM_REG_PPC_TM_VSR63:
+	{
+		int 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_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
 	case KVM_REG_PPC_ARCH_COMPAT:
 		r = kvmppc_set_arch_compat(vcpu, set_reg_val(id, *val));
 		break;
@@ -1360,9 +1463,7 @@ static void kvmppc_start_thread(struct kvm_vcpu *vcpu)
 	smp_wmb();
 #if defined(CONFIG_PPC_ICP_NATIVE) && defined(CONFIG_SMP)
 	if (cpu != smp_processor_id()) {
-#ifdef CONFIG_KVM_XICS
 		xics_wake_cpu(cpu);
-#endif
 		if (vcpu->arch.ptid)
 			++vc->n_woken;
 	}
@@ -1530,7 +1631,7 @@ static void kvmppc_run_core(struct kvmppc_vcore *vc)
 		vcpu->arch.trap = 0;
 
 		if (vcpu->arch.ceded) {
-			if (ret != RESUME_GUEST)
+			if (!is_kvmppc_resume_guest(ret))
 				kvmppc_end_cede(vcpu);
 			else
 				kvmppc_set_timer(vcpu);
@@ -1541,7 +1642,7 @@ static void kvmppc_run_core(struct kvmppc_vcore *vc)
 	vc->vcore_state = VCORE_INACTIVE;
 	list_for_each_entry_safe(vcpu, vnext, &vc->runnable_threads,
 				 arch.run_list) {
-		if (vcpu->arch.ret != RESUME_GUEST) {
+		if (!is_kvmppc_resume_guest(vcpu->arch.ret)) {
 			kvmppc_remove_runnable(vc, vcpu);
 			wake_up(&vcpu->arch.cpu_run);
 		}
@@ -1731,7 +1832,7 @@ static int kvmppc_vcpu_run_hv(struct kvm_run *run, struct kvm_vcpu *vcpu)
 				vcpu->arch.fault_dar, vcpu->arch.fault_dsisr);
 			srcu_read_unlock(&vcpu->kvm->srcu, srcu_idx);
 		}
-	} while (r == RESUME_GUEST);
+	} while (is_kvmppc_resume_guest(r));
 
  out:
 	vcpu->arch.state = KVMPPC_VCPU_NOTREADY;
@@ -2366,7 +2467,7 @@ static int kvmppc_book3s_init_hv(void)
 	 */
 	r = kvmppc_core_check_processor_compat_hv();
 	if (r < 0)
-		return r;
+		return -ENODEV;
 
 	kvm_ops_hv.owner = THIS_MODULE;
 	kvmppc_hv_ops = &kvm_ops_hv;
diff --git a/arch/powerpc/kvm/book3s_hv_interrupts.S b/arch/powerpc/kvm/book3s_hv_interrupts.S
index e873796b1a29..e18e3cfc32de 100644
--- a/arch/powerpc/kvm/book3s_hv_interrupts.S
+++ b/arch/powerpc/kvm/book3s_hv_interrupts.S
@@ -71,6 +71,14 @@ END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_207S)
 	mtmsrd  r10,1
 
 	/* Save host PMU registers */
+BEGIN_FTR_SECTION
+	/* Work around P8 PMAE bug */
+	li	r3, -1
+	clrrdi	r3, r3, 10
+	mfspr	r8, SPRN_MMCR2
+	mtspr	SPRN_MMCR2, r3		/* freeze all counters using MMCR2 */
+	isync
+END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
 	li	r3, 1
 	sldi	r3, r3, 31		/* MMCR0_FC (freeze counters) bit */
 	mfspr	r7, SPRN_MMCR0		/* save MMCR0 */
@@ -87,9 +95,18 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_206)
 	cmpwi	r5, 0
 	beq	31f			/* skip if not */
 	mfspr	r5, SPRN_MMCR1
+	mfspr	r9, SPRN_SIAR
+	mfspr	r10, SPRN_SDAR
 	std	r7, HSTATE_MMCR(r13)
 	std	r5, HSTATE_MMCR + 8(r13)
 	std	r6, HSTATE_MMCR + 16(r13)
+	std	r9, HSTATE_MMCR + 24(r13)
+	std	r10, HSTATE_MMCR + 32(r13)
+BEGIN_FTR_SECTION
+	mfspr	r9, SPRN_SIER
+	std	r8, HSTATE_MMCR + 40(r13)
+	std	r9, HSTATE_MMCR + 48(r13)
+END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
 	mfspr	r3, SPRN_PMC1
 	mfspr	r5, SPRN_PMC2
 	mfspr	r6, SPRN_PMC3
@@ -110,6 +127,11 @@ BEGIN_FTR_SECTION
 	stw	r10, HSTATE_PMC + 24(r13)
 	stw	r11, HSTATE_PMC + 28(r13)
 END_FTR_SECTION_IFSET(CPU_FTR_ARCH_201)
+BEGIN_FTR_SECTION
+	mfspr	r9, SPRN_SIER
+	std	r8, HSTATE_MMCR + 40(r13)
+	std	r9, HSTATE_MMCR + 48(r13)
+END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
 31:
 
 	/*
diff --git a/arch/powerpc/kvm/book3s_hv_rm_mmu.c b/arch/powerpc/kvm/book3s_hv_rm_mmu.c
index 37fb3caa4c80..1d6c56ad5b60 100644
--- a/arch/powerpc/kvm/book3s_hv_rm_mmu.c
+++ b/arch/powerpc/kvm/book3s_hv_rm_mmu.c
@@ -111,7 +111,7 @@ static void remove_revmap_chain(struct kvm *kvm, long pte_index,
 	rcbits = hpte_r & (HPTE_R_R | HPTE_R_C);
 	ptel = rev->guest_rpte |= rcbits;
 	gfn = hpte_rpn(ptel, hpte_page_size(hpte_v, ptel));
-	memslot = __gfn_to_memslot(kvm_memslots(kvm), gfn);
+	memslot = __gfn_to_memslot(kvm_memslots_raw(kvm), gfn);
 	if (!memslot)
 		return;
 
@@ -192,7 +192,7 @@ long kvmppc_do_h_enter(struct kvm *kvm, unsigned long flags,
 	/* Find the memslot (if any) for this address */
 	gpa = (ptel & HPTE_R_RPN) & ~(psize - 1);
 	gfn = gpa >> PAGE_SHIFT;
-	memslot = __gfn_to_memslot(kvm_memslots(kvm), gfn);
+	memslot = __gfn_to_memslot(kvm_memslots_raw(kvm), gfn);
 	pa = 0;
 	is_io = ~0ul;
 	rmap = NULL;
@@ -670,7 +670,7 @@ long kvmppc_h_protect(struct kvm_vcpu *vcpu, unsigned long flags,
 
 			psize = hpte_page_size(v, r);
 			gfn = ((r & HPTE_R_RPN) & ~(psize - 1)) >> PAGE_SHIFT;
-			memslot = __gfn_to_memslot(kvm_memslots(kvm), gfn);
+			memslot = __gfn_to_memslot(kvm_memslots_raw(kvm), gfn);
 			if (memslot) {
 				hva = __gfn_to_hva_memslot(memslot, gfn);
 				pte = lookup_linux_pte_and_update(pgdir, hva,
diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
index 53d647f8e741..ffbb871c2bd8 100644
--- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S
+++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
@@ -28,6 +28,9 @@
 #include <asm/exception-64s.h>
 #include <asm/kvm_book3s_asm.h>
 #include <asm/mmu-hash64.h>
+#include <asm/tm.h>
+
+#define VCPU_GPRS_TM(reg) (((reg) * ULONG_SIZE) + VCPU_GPR_TM)
 
 #ifdef __LITTLE_ENDIAN__
 #error Need to fix lppaca and SLB shadow accesses in little endian mode
@@ -106,8 +109,18 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_201)
 	ld	r3, HSTATE_MMCR(r13)
 	ld	r4, HSTATE_MMCR + 8(r13)
 	ld	r5, HSTATE_MMCR + 16(r13)
+	ld	r6, HSTATE_MMCR + 24(r13)
+	ld	r7, HSTATE_MMCR + 32(r13)
 	mtspr	SPRN_MMCR1, r4
 	mtspr	SPRN_MMCRA, r5
+	mtspr	SPRN_SIAR, r6
+	mtspr	SPRN_SDAR, r7
+BEGIN_FTR_SECTION
+	ld	r8, HSTATE_MMCR + 40(r13)
+	ld	r9, HSTATE_MMCR + 48(r13)
+	mtspr	SPRN_MMCR2, r8
+	mtspr	SPRN_SIER, r9
+END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
 	mtspr	SPRN_MMCR0, r3
 	isync
 23:
@@ -597,6 +610,116 @@ BEGIN_FTR_SECTION
  END_FTR_SECTION_NESTED(CPU_FTR_ARCH_206, CPU_FTR_ARCH_206, 89)
 END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_207S)
 
+#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+BEGIN_FTR_SECTION
+	b	skip_tm
+END_FTR_SECTION_IFCLR(CPU_FTR_TM)
+
+	/* 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(r4)
+	ld	r6, VCPU_TFIAR(r4)
+	ld	r7, VCPU_TEXASR(r4)
+	mtspr	SPRN_TFHAR, r5
+	mtspr	SPRN_TFIAR, r6
+	mtspr	SPRN_TEXASR, r7
+
+	ld	r5, VCPU_MSR(r4)
+	rldicl. r5, r5, 64 - MSR_TS_S_LG, 62
+	beq	skip_tm	/* TM not active in guest */
+
+	/* 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, 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)
+	mtlr	r5
+	mtcr	r6
+	mtctr	r7
+	mtspr	SPRN_AMR, r8
+	mtspr	SPRN_TAR, r9
+
+	/*
+	 * 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
+skip_tm:
+#endif
+
 	/* Load guest PMU registers */
 	/* R4 is live here (vcpu pointer) */
 	li	r3, 1
@@ -704,14 +827,6 @@ END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_207S)
 	ld	r6, VCPU_VTB(r4)
 	mtspr	SPRN_IC, r5
 	mtspr	SPRN_VTB, r6
-#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
-	ld	r5, VCPU_TFHAR(r4)
-	ld	r6, VCPU_TFIAR(r4)
-	ld	r7, VCPU_TEXASR(r4)
-	mtspr	SPRN_TFHAR, r5
-	mtspr	SPRN_TFIAR, r6
-	mtspr	SPRN_TEXASR, r7
-#endif
 	ld	r8, VCPU_EBBHR(r4)
 	mtspr	SPRN_EBBHR, r8
 	ld	r5, VCPU_EBBRR(r4)
@@ -736,6 +851,10 @@ END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_207S)
 	 * Set the decrementer to the guest decrementer.
 	 */
 	ld	r8,VCPU_DEC_EXPIRES(r4)
+	/* r8 is a host timebase value here, convert to guest TB */
+	ld	r5,HSTATE_KVM_VCORE(r13)
+	ld	r6,VCORE_TB_OFFSET(r5)
+	add	r8,r8,r6
 	mftb	r7
 	subf	r3,r7,r8
 	mtspr	SPRN_DEC,r3
@@ -817,7 +936,8 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_206)
 12:	mtspr	SPRN_SRR0, r10
 	mr	r10,r0
 	mtspr	SPRN_SRR1, r11
-	ld	r11, VCPU_INTR_MSR(r4)
+	mr	r9, r4
+	bl	kvmppc_msr_interrupt
 5:
 
 /*
@@ -1098,17 +1218,15 @@ END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_201)
 	mftb	r6
 	extsw	r5,r5
 	add	r5,r5,r6
+	/* r5 is a guest timebase value here, convert to host TB */
+	ld	r3,HSTATE_KVM_VCORE(r13)
+	ld	r4,VCORE_TB_OFFSET(r3)
+	subf	r5,r4,r5
 	std	r5,VCPU_DEC_EXPIRES(r9)
 
 BEGIN_FTR_SECTION
 	b	8f
 END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_207S)
-	/* Turn on TM so we can access TFHAR/TFIAR/TEXASR */
-	mfmsr	r8
-	li	r0, 1
-	rldimi	r8, r0, MSR_TM_LG, 63-MSR_TM_LG
-	mtmsrd	r8
-
 	/* Save POWER8-specific registers */
 	mfspr	r5, SPRN_IAMR
 	mfspr	r6, SPRN_PSPB
@@ -1122,14 +1240,6 @@ END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_207S)
 	std	r5, VCPU_IC(r9)
 	std	r6, VCPU_VTB(r9)
 	std	r7, VCPU_TAR(r9)
-#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
-	mfspr	r5, SPRN_TFHAR
-	mfspr	r6, SPRN_TFIAR
-	mfspr	r7, SPRN_TEXASR
-	std	r5, VCPU_TFHAR(r9)
-	std	r6, VCPU_TFIAR(r9)
-	std	r7, VCPU_TEXASR(r9)
-#endif
 	mfspr	r8, SPRN_EBBHR
 	std	r8, VCPU_EBBHR(r9)
 	mfspr	r5, SPRN_EBBRR
@@ -1387,7 +1497,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
 	ld	r8,VCORE_TB_OFFSET(r5)
 	cmpdi	r8,0
 	beq	17f
-	mftb	r6			/* current host timebase */
+	mftb	r6			/* current guest timebase */
 	subf	r8,r8,r6
 	mtspr	SPRN_TBU40,r8		/* update upper 40 bits */
 	mftb	r7			/* check if lower 24 bits overflowed */
@@ -1557,7 +1667,7 @@ kvmppc_hdsi:
 	mtspr	SPRN_SRR0, r10
 	mtspr	SPRN_SRR1, r11
 	li	r10, BOOK3S_INTERRUPT_DATA_STORAGE
-	ld	r11, VCPU_INTR_MSR(r9)
+	bl	kvmppc_msr_interrupt
 fast_interrupt_c_return:
 6:	ld	r7, VCPU_CTR(r9)
 	lwz	r8, VCPU_XER(r9)
@@ -1626,7 +1736,7 @@ kvmppc_hisi:
 1:	mtspr	SPRN_SRR0, r10
 	mtspr	SPRN_SRR1, r11
 	li	r10, BOOK3S_INTERRUPT_INST_STORAGE
-	ld	r11, VCPU_INTR_MSR(r9)
+	bl	kvmppc_msr_interrupt
 	b	fast_interrupt_c_return
 
 3:	ld	r6, VCPU_KVM(r9)	/* not relocated, use VRMA */
@@ -1669,7 +1779,7 @@ sc_1_fast_return:
 	mtspr	SPRN_SRR0,r10
 	mtspr	SPRN_SRR1,r11
 	li	r10, BOOK3S_INTERRUPT_SYSCALL
-	ld	r11, VCPU_INTR_MSR(r9)
+	bl	kvmppc_msr_interrupt
 	mr	r4,r9
 	b	fast_guest_return
 
@@ -1691,7 +1801,7 @@ hcall_real_table:
 	.long	0		/* 0x10 - H_CLEAR_MOD */
 	.long	0		/* 0x14 - H_CLEAR_REF */
 	.long	.kvmppc_h_protect - hcall_real_table
-	.long	0		/* 0x1c - H_GET_TCE */
+	.long	.kvmppc_h_get_tce - hcall_real_table
 	.long	.kvmppc_h_put_tce - hcall_real_table
 	.long	0		/* 0x24 - H_SET_SPRG0 */
 	.long	.kvmppc_h_set_dabr - hcall_real_table
@@ -1997,7 +2107,7 @@ machine_check_realmode:
 	beq	mc_cont
 	/* If not, deliver a machine check.  SRR0/1 are already set */
 	li	r10, BOOK3S_INTERRUPT_MACHINE_CHECK
-	ld	r11, VCPU_INTR_MSR(r9)
+	bl	kvmppc_msr_interrupt
 	b	fast_interrupt_c_return
 
 /*
@@ -2138,8 +2248,6 @@ END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC)
 	mfspr	r6,SPRN_VRSAVE
 	stw	r6,VCPU_VRSAVE(r31)
 	mtlr	r30
-	mtmsrd	r5
-	isync
 	blr
 
 /*
@@ -2186,3 +2294,20 @@ END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC)
  */
 kvmppc_bad_host_intr:
 	b	.
+
+/*
+ * This mimics the MSR transition on IRQ delivery.  The new guest MSR is taken
+ * from VCPU_INTR_MSR and is modified based on the required TM state changes.
+ *   r11 has the guest MSR value (in/out)
+ *   r9 has a vcpu pointer (in)
+ *   r0 is used as a scratch register
+ */
+kvmppc_msr_interrupt:
+	rldicl	r0, r11, 64 - MSR_TS_S_LG, 62
+	cmpwi	r0, 2 /* Check if we are in transactional state..  */
+	ld	r11, VCPU_INTR_MSR(r9)
+	bne	1f
+	/* ... if transactional, change to suspended */
+	li	r0, 1
+1:	rldimi	r11, r0, MSR_TS_S_LG, 63 - MSR_TS_T_LG
+	blr
diff --git a/arch/powerpc/kvm/book3s_rtas.c b/arch/powerpc/kvm/book3s_rtas.c
index cf95cdef73c9..7a053157483b 100644
--- a/arch/powerpc/kvm/book3s_rtas.c
+++ b/arch/powerpc/kvm/book3s_rtas.c
@@ -213,8 +213,11 @@ int kvmppc_rtas_hcall(struct kvm_vcpu *vcpu)
 	gpa_t args_phys;
 	int rc;
 
-	/* r4 contains the guest physical address of the RTAS args */
-	args_phys = kvmppc_get_gpr(vcpu, 4);
+	/*
+	 * r4 contains the guest physical address of the RTAS args
+	 * Mask off the top 4 bits since this is a guest real address
+	 */
+	args_phys = kvmppc_get_gpr(vcpu, 4) & KVM_PAM;
 
 	rc = kvm_read_guest(vcpu->kvm, args_phys, &args, sizeof(args));
 	if (rc)