Merge tag 'kvm-3.6-1' of git://git.kernel.org/pub/scm/virt/kvm/kvm

Pull KVM updates from Avi Kivity:
 "Highlights include
  - full big real mode emulation on pre-Westmere Intel hosts (can be
    disabled with emulate_invalid_guest_state=0)
  - relatively small ppc and s390 updates
  - PCID/INVPCID support in guests
  - EOI avoidance; 3.6 guests should perform better on 3.6 hosts on
    interrupt intensive workloads)
  - Lockless write faults during live migration
  - EPT accessed/dirty bits support for new Intel processors"

Fix up conflicts in:
 - Documentation/virtual/kvm/api.txt:

   Stupid subchapter numbering, added next to each other.

 - arch/powerpc/kvm/booke_interrupts.S:

   PPC asm changes clashing with the KVM fixes

 - arch/s390/include/asm/sigp.h, arch/s390/kvm/sigp.c:

   Duplicated commits through the kvm tree and the s390 tree, with
   subsequent edits in the KVM tree.

* tag 'kvm-3.6-1' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (93 commits)
  KVM: fix race with level interrupts
  x86, hyper: fix build with !CONFIG_KVM_GUEST
  Revert "apic: fix kvm build on UP without IOAPIC"
  KVM guest: switch to apic_set_eoi_write, apic_write
  apic: add apic_set_eoi_write for PV use
  KVM: VMX: Implement PCID/INVPCID for guests with EPT
  KVM: Add x86_hyper_kvm to complete detect_hypervisor_platform check
  KVM: PPC: Critical interrupt emulation support
  KVM: PPC: e500mc: Fix tlbilx emulation for 64-bit guests
  KVM: PPC64: booke: Set interrupt computation mode for 64-bit host
  KVM: PPC: bookehv: Add ESR flag to Data Storage Interrupt
  KVM: PPC: bookehv64: Add support for std/ld emulation.
  booke: Added crit/mc exception handler for e500v2
  booke/bookehv: Add host crit-watchdog exception support
  KVM: MMU: document mmu-lock and fast page fault
  KVM: MMU: fix kvm_mmu_pagetable_walk tracepoint
  KVM: MMU: trace fast page fault
  KVM: MMU: fast path of handling guest page fault
  KVM: MMU: introduce SPTE_MMU_WRITEABLE bit
  KVM: MMU: fold tlb flush judgement into mmu_spte_update
  ...

12 files changed, 260 insertions, 79 deletions

diff --git a/arch/powerpc/kvm/book3s_64_mmu_hv.c b/arch/powerpc/kvm/book3s_64_mmu_hv.c
index 80a577517584..d03eb6f7b058 100644
--- a/arch/powerpc/kvm/book3s_64_mmu_hv.c
+++ b/arch/powerpc/kvm/book3s_64_mmu_hv.c
@@ -37,56 +37,121 @@
 /* POWER7 has 10-bit LPIDs, PPC970 has 6-bit LPIDs */
 #define MAX_LPID_970	63
 
-long kvmppc_alloc_hpt(struct kvm *kvm)
+/* Power architecture requires HPT is at least 256kB */
+#define PPC_MIN_HPT_ORDER	18
+
+long kvmppc_alloc_hpt(struct kvm *kvm, u32 *htab_orderp)
 {
 	unsigned long hpt;
-	long lpid;
 	struct revmap_entry *rev;
 	struct kvmppc_linear_info *li;
+	long order = kvm_hpt_order;
 
-	/* Allocate guest's hashed page table */
-	li = kvm_alloc_hpt();
-	if (li) {
-		/* using preallocated memory */
-		hpt = (ulong)li->base_virt;
-		kvm->arch.hpt_li = li;
-	} else {
-		/* using dynamic memory */
+	if (htab_orderp) {
+		order = *htab_orderp;
+		if (order < PPC_MIN_HPT_ORDER)
+			order = PPC_MIN_HPT_ORDER;
+	}
+
+	/*
+	 * If the user wants a different size from default,
+	 * try first to allocate it from the kernel page allocator.
+	 */
+	hpt = 0;
+	if (order != kvm_hpt_order) {
 		hpt = __get_free_pages(GFP_KERNEL|__GFP_ZERO|__GFP_REPEAT|
-				       __GFP_NOWARN, HPT_ORDER - PAGE_SHIFT);
+				       __GFP_NOWARN, order - PAGE_SHIFT);
+		if (!hpt)
+			--order;
 	}
 
+	/* Next try to allocate from the preallocated pool */
 	if (!hpt) {
-		pr_err("kvm_alloc_hpt: Couldn't alloc HPT\n");
-		return -ENOMEM;
+		li = kvm_alloc_hpt();
+		if (li) {
+			hpt = (ulong)li->base_virt;
+			kvm->arch.hpt_li = li;
+			order = kvm_hpt_order;
+		}
 	}
+
+	/* Lastly try successively smaller sizes from the page allocator */
+	while (!hpt && order > PPC_MIN_HPT_ORDER) {
+		hpt = __get_free_pages(GFP_KERNEL|__GFP_ZERO|__GFP_REPEAT|
+				       __GFP_NOWARN, order - PAGE_SHIFT);
+		if (!hpt)
+			--order;
+	}
+
+	if (!hpt)
+		return -ENOMEM;
+
 	kvm->arch.hpt_virt = hpt;
+	kvm->arch.hpt_order = order;
+	/* HPTEs are 2**4 bytes long */
+	kvm->arch.hpt_npte = 1ul << (order - 4);
+	/* 128 (2**7) bytes in each HPTEG */
+	kvm->arch.hpt_mask = (1ul << (order - 7)) - 1;
 
 	/* Allocate reverse map array */
-	rev = vmalloc(sizeof(struct revmap_entry) * HPT_NPTE);
+	rev = vmalloc(sizeof(struct revmap_entry) * kvm->arch.hpt_npte);
 	if (!rev) {
 		pr_err("kvmppc_alloc_hpt: Couldn't alloc reverse map array\n");
 		goto out_freehpt;
 	}
 	kvm->arch.revmap = rev;
+	kvm->arch.sdr1 = __pa(hpt) | (order - 18);
 
-	lpid = kvmppc_alloc_lpid();
-	if (lpid < 0)
-		goto out_freeboth;
+	pr_info("KVM guest htab at %lx (order %ld), LPID %x\n",
+		hpt, order, kvm->arch.lpid);
 
-	kvm->arch.sdr1 = __pa(hpt) | (HPT_ORDER - 18);
-	kvm->arch.lpid = lpid;
-
-	pr_info("KVM guest htab at %lx, LPID %lx\n", hpt, lpid);
+	if (htab_orderp)
+		*htab_orderp = order;
 	return 0;
 
- out_freeboth:
-	vfree(rev);
  out_freehpt:
-	free_pages(hpt, HPT_ORDER - PAGE_SHIFT);
+	if (kvm->arch.hpt_li)
+		kvm_release_hpt(kvm->arch.hpt_li);
+	else
+		free_pages(hpt, order - PAGE_SHIFT);
 	return -ENOMEM;
 }
 
+long kvmppc_alloc_reset_hpt(struct kvm *kvm, u32 *htab_orderp)
+{
+	long err = -EBUSY;
+	long order;
+
+	mutex_lock(&kvm->lock);
+	if (kvm->arch.rma_setup_done) {
+		kvm->arch.rma_setup_done = 0;
+		/* order rma_setup_done vs. vcpus_running */
+		smp_mb();
+		if (atomic_read(&kvm->arch.vcpus_running)) {
+			kvm->arch.rma_setup_done = 1;
+			goto out;
+		}
+	}
+	if (kvm->arch.hpt_virt) {
+		order = kvm->arch.hpt_order;
+		/* Set the entire HPT to 0, i.e. invalid HPTEs */
+		memset((void *)kvm->arch.hpt_virt, 0, 1ul << order);
+		/*
+		 * Set the whole last_vcpu array to an invalid vcpu number.
+		 * This ensures that each vcpu will flush its TLB on next entry.
+		 */
+		memset(kvm->arch.last_vcpu, 0xff, sizeof(kvm->arch.last_vcpu));
+		*htab_orderp = order;
+		err = 0;
+	} else {
+		err = kvmppc_alloc_hpt(kvm, htab_orderp);
+		order = *htab_orderp;
+	}
+ out:
+	mutex_unlock(&kvm->lock);
+	return err;
+}
+
 void kvmppc_free_hpt(struct kvm *kvm)
 {
 	kvmppc_free_lpid(kvm->arch.lpid);
@@ -94,7 +159,8 @@ void kvmppc_free_hpt(struct kvm *kvm)
 	if (kvm->arch.hpt_li)
 		kvm_release_hpt(kvm->arch.hpt_li);
 	else
-		free_pages(kvm->arch.hpt_virt, HPT_ORDER - PAGE_SHIFT);
+		free_pages(kvm->arch.hpt_virt,
+			   kvm->arch.hpt_order - PAGE_SHIFT);
 }
 
 /* Bits in first HPTE dword for pagesize 4k, 64k or 16M */
@@ -119,6 +185,7 @@ void kvmppc_map_vrma(struct kvm_vcpu *vcpu, struct kvm_memory_slot *memslot,
 	unsigned long psize;
 	unsigned long hp0, hp1;
 	long ret;
+	struct kvm *kvm = vcpu->kvm;
 
 	psize = 1ul << porder;
 	npages = memslot->npages >> (porder - PAGE_SHIFT);
@@ -127,8 +194,8 @@ void kvmppc_map_vrma(struct kvm_vcpu *vcpu, struct kvm_memory_slot *memslot,
 	if (npages > 1ul << (40 - porder))
 		npages = 1ul << (40 - porder);
 	/* Can't use more than 1 HPTE per HPTEG */
-	if (npages > HPT_NPTEG)
-		npages = HPT_NPTEG;
+	if (npages > kvm->arch.hpt_mask + 1)
+		npages = kvm->arch.hpt_mask + 1;
 
 	hp0 = HPTE_V_1TB_SEG | (VRMA_VSID << (40 - 16)) |
 		HPTE_V_BOLTED | hpte0_pgsize_encoding(psize);
@@ -138,7 +205,7 @@ void kvmppc_map_vrma(struct kvm_vcpu *vcpu, struct kvm_memory_slot *memslot,
 	for (i = 0; i < npages; ++i) {
 		addr = i << porder;
 		/* can't use hpt_hash since va > 64 bits */
-		hash = (i ^ (VRMA_VSID ^ (VRMA_VSID << 25))) & HPT_HASH_MASK;
+		hash = (i ^ (VRMA_VSID ^ (VRMA_VSID << 25))) & kvm->arch.hpt_mask;
 		/*
 		 * We assume that the hash table is empty and no
 		 * vcpus are using it at this stage.  Since we create
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index 3abe1b86e583..83e929e66f9d 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -56,7 +56,7 @@
 /* #define EXIT_DEBUG_INT */
 
 static void kvmppc_end_cede(struct kvm_vcpu *vcpu);
-static int kvmppc_hv_setup_rma(struct kvm_vcpu *vcpu);
+static int kvmppc_hv_setup_htab_rma(struct kvm_vcpu *vcpu);
 
 void kvmppc_core_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 {
@@ -1104,11 +1104,15 @@ int kvmppc_vcpu_run(struct kvm_run *run, struct kvm_vcpu *vcpu)
 		return -EINTR;
 	}
 
-	/* On the first time here, set up VRMA or RMA */
+	atomic_inc(&vcpu->kvm->arch.vcpus_running);
+	/* Order vcpus_running vs. rma_setup_done, see kvmppc_alloc_reset_hpt */
+	smp_mb();
+
+	/* On the first time here, set up HTAB and VRMA or RMA */
 	if (!vcpu->kvm->arch.rma_setup_done) {
-		r = kvmppc_hv_setup_rma(vcpu);
+		r = kvmppc_hv_setup_htab_rma(vcpu);
 		if (r)
-			return r;
+			goto out;
 	}
 
 	flush_fp_to_thread(current);
@@ -1126,6 +1130,9 @@ int kvmppc_vcpu_run(struct kvm_run *run, struct kvm_vcpu *vcpu)
 			kvmppc_core_prepare_to_enter(vcpu);
 		}
 	} while (r == RESUME_GUEST);
+
+ out:
+	atomic_dec(&vcpu->kvm->arch.vcpus_running);
 	return r;
 }
 
@@ -1341,7 +1348,7 @@ void kvmppc_core_commit_memory_region(struct kvm *kvm,
 {
 }
 
-static int kvmppc_hv_setup_rma(struct kvm_vcpu *vcpu)
+static int kvmppc_hv_setup_htab_rma(struct kvm_vcpu *vcpu)
 {
 	int err = 0;
 	struct kvm *kvm = vcpu->kvm;
@@ -1360,6 +1367,15 @@ static int kvmppc_hv_setup_rma(struct kvm_vcpu *vcpu)
 	if (kvm->arch.rma_setup_done)
 		goto out;	/* another vcpu beat us to it */
 
+	/* Allocate hashed page table (if not done already) and reset it */
+	if (!kvm->arch.hpt_virt) {
+		err = kvmppc_alloc_hpt(kvm, NULL);
+		if (err) {
+			pr_err("KVM: Couldn't alloc HPT\n");
+			goto out;
+		}
+	}
+
 	/* Look up the memslot for guest physical address 0 */
 	memslot = gfn_to_memslot(kvm, 0);
 
@@ -1471,13 +1487,14 @@ static int kvmppc_hv_setup_rma(struct kvm_vcpu *vcpu)
 
 int kvmppc_core_init_vm(struct kvm *kvm)
 {
-	long r;
-	unsigned long lpcr;
+	unsigned long lpcr, lpid;
 
-	/* Allocate hashed page table */
-	r = kvmppc_alloc_hpt(kvm);
-	if (r)
-		return r;
+	/* Allocate the guest's logical partition ID */
+
+	lpid = kvmppc_alloc_lpid();
+	if (lpid < 0)
+		return -ENOMEM;
+	kvm->arch.lpid = lpid;
 
 	INIT_LIST_HEAD(&kvm->arch.spapr_tce_tables);
 
@@ -1487,7 +1504,6 @@ int kvmppc_core_init_vm(struct kvm *kvm)
 
 	if (cpu_has_feature(CPU_FTR_ARCH_201)) {
 		/* PPC970; HID4 is effectively the LPCR */
-		unsigned long lpid = kvm->arch.lpid;
 		kvm->arch.host_lpid = 0;
 		kvm->arch.host_lpcr = lpcr = mfspr(SPRN_HID4);
 		lpcr &= ~((3 << HID4_LPID1_SH) | (0xful << HID4_LPID5_SH));
diff --git a/arch/powerpc/kvm/book3s_hv_builtin.c b/arch/powerpc/kvm/book3s_hv_builtin.c
index e1b60f56f2a1..fb4eac290fef 100644
--- a/arch/powerpc/kvm/book3s_hv_builtin.c
+++ b/arch/powerpc/kvm/book3s_hv_builtin.c
@@ -25,6 +25,9 @@ static void __init kvm_linear_init_one(ulong size, int count, int type);
 static struct kvmppc_linear_info *kvm_alloc_linear(int type);
 static void kvm_release_linear(struct kvmppc_linear_info *ri);
 
+int kvm_hpt_order = KVM_DEFAULT_HPT_ORDER;
+EXPORT_SYMBOL_GPL(kvm_hpt_order);
+
 /*************** RMA *************/
 
 /*
@@ -209,7 +212,7 @@ static void kvm_release_linear(struct kvmppc_linear_info *ri)
 void __init kvm_linear_init(void)
 {
 	/* HPT */
-	kvm_linear_init_one(1 << HPT_ORDER, kvm_hpt_count, KVM_LINEAR_HPT);
+	kvm_linear_init_one(1 << kvm_hpt_order, kvm_hpt_count, KVM_LINEAR_HPT);
 
 	/* RMA */
 	/* Only do this on PPC970 in HV mode */
diff --git a/arch/powerpc/kvm/book3s_hv_rm_mmu.c b/arch/powerpc/kvm/book3s_hv_rm_mmu.c
index cec4daddbf31..5c70d19494f9 100644
--- a/arch/powerpc/kvm/book3s_hv_rm_mmu.c
+++ b/arch/powerpc/kvm/book3s_hv_rm_mmu.c
@@ -237,7 +237,7 @@ long kvmppc_h_enter(struct kvm_vcpu *vcpu, unsigned long flags,
 
 	/* Find and lock the HPTEG slot to use */
  do_insert:
-	if (pte_index >= HPT_NPTE)
+	if (pte_index >= kvm->arch.hpt_npte)
 		return H_PARAMETER;
 	if (likely((flags & H_EXACT) == 0)) {
 		pte_index &= ~7UL;
@@ -352,7 +352,7 @@ long kvmppc_h_remove(struct kvm_vcpu *vcpu, unsigned long flags,
 	unsigned long v, r, rb;
 	struct revmap_entry *rev;
 
-	if (pte_index >= HPT_NPTE)
+	if (pte_index >= kvm->arch.hpt_npte)
 		return H_PARAMETER;
 	hpte = (unsigned long *)(kvm->arch.hpt_virt + (pte_index << 4));
 	while (!try_lock_hpte(hpte, HPTE_V_HVLOCK))
@@ -419,7 +419,8 @@ long kvmppc_h_bulk_remove(struct kvm_vcpu *vcpu)
 				i = 4;
 				break;
 			}
-			if (req != 1 || flags == 3 || pte_index >= HPT_NPTE) {
+			if (req != 1 || flags == 3 ||
+			    pte_index >= kvm->arch.hpt_npte) {
 				/* parameter error */
 				args[j] = ((0xa0 | flags) << 56) + pte_index;
 				ret = H_PARAMETER;
@@ -521,7 +522,7 @@ long kvmppc_h_protect(struct kvm_vcpu *vcpu, unsigned long flags,
 	struct revmap_entry *rev;
 	unsigned long v, r, rb, mask, bits;
 
-	if (pte_index >= HPT_NPTE)
+	if (pte_index >= kvm->arch.hpt_npte)
 		return H_PARAMETER;
 
 	hpte = (unsigned long *)(kvm->arch.hpt_virt + (pte_index << 4));
@@ -583,7 +584,7 @@ long kvmppc_h_read(struct kvm_vcpu *vcpu, unsigned long flags,
 	int i, n = 1;
 	struct revmap_entry *rev = NULL;
 
-	if (pte_index >= HPT_NPTE)
+	if (pte_index >= kvm->arch.hpt_npte)
 		return H_PARAMETER;
 	if (flags & H_READ_4) {
 		pte_index &= ~3;
@@ -678,7 +679,7 @@ long kvmppc_hv_find_lock_hpte(struct kvm *kvm, gva_t eaddr, unsigned long slb_v,
 		somask = (1UL << 28) - 1;
 		vsid = (slb_v & ~SLB_VSID_B) >> SLB_VSID_SHIFT;
 	}
-	hash = (vsid ^ ((eaddr & somask) >> pshift)) & HPT_HASH_MASK;
+	hash = (vsid ^ ((eaddr & somask) >> pshift)) & kvm->arch.hpt_mask;
 	avpn = slb_v & ~(somask >> 16);	/* also includes B */
 	avpn |= (eaddr & somask) >> 16;
 
@@ -723,7 +724,7 @@ long kvmppc_hv_find_lock_hpte(struct kvm *kvm, gva_t eaddr, unsigned long slb_v,
 		if (val & HPTE_V_SECONDARY)
 			break;
 		val |= HPTE_V_SECONDARY;
-		hash = hash ^ HPT_HASH_MASK;
+		hash = hash ^ kvm->arch.hpt_mask;
 	}
 	return -1;
 }
diff --git a/arch/powerpc/kvm/booke.c b/arch/powerpc/kvm/booke.c
index 72f13f4a06e0..d25a097c852b 100644
--- a/arch/powerpc/kvm/booke.c
+++ b/arch/powerpc/kvm/booke.c
@@ -612,6 +612,12 @@ static void kvmppc_fill_pt_regs(struct pt_regs *regs)
 	regs->link = lr;
 }
 
+/*
+ * For interrupts needed to be handled by host interrupt handlers,
+ * corresponding host handler are called from here in similar way
+ * (but not exact) as they are called from low level handler
+ * (such as from arch/powerpc/kernel/head_fsl_booke.S).
+ */
 static void kvmppc_restart_interrupt(struct kvm_vcpu *vcpu,
 				     unsigned int exit_nr)
 {
@@ -639,6 +645,17 @@ static void kvmppc_restart_interrupt(struct kvm_vcpu *vcpu,
 		kvmppc_fill_pt_regs(&regs);
 		performance_monitor_exception(&regs);
 		break;
+	case BOOKE_INTERRUPT_WATCHDOG:
+		kvmppc_fill_pt_regs(&regs);
+#ifdef CONFIG_BOOKE_WDT
+		WatchdogException(&regs);
+#else
+		unknown_exception(&regs);
+#endif
+		break;
+	case BOOKE_INTERRUPT_CRITICAL:
+		unknown_exception(&regs);
+		break;
 	}
 }
 
@@ -683,6 +700,10 @@ int kvmppc_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu,
 		r = RESUME_GUEST;
 		break;
 
+	case BOOKE_INTERRUPT_WATCHDOG:
+		r = RESUME_GUEST;
+		break;
+
 	case BOOKE_INTERRUPT_DOORBELL:
 		kvmppc_account_exit(vcpu, DBELL_EXITS);
 		r = RESUME_GUEST;
@@ -1267,6 +1288,11 @@ void kvmppc_decrementer_func(unsigned long data)
 {
 	struct kvm_vcpu *vcpu = (struct kvm_vcpu *)data;
 
+	if (vcpu->arch.tcr & TCR_ARE) {
+		vcpu->arch.dec = vcpu->arch.decar;
+		kvmppc_emulate_dec(vcpu);
+	}
+
 	kvmppc_set_tsr_bits(vcpu, TSR_DIS);
 }
 
diff --git a/arch/powerpc/kvm/booke_emulate.c b/arch/powerpc/kvm/booke_emulate.c
index 6c76397f2af4..12834bb608ab 100644
--- a/arch/powerpc/kvm/booke_emulate.c
+++ b/arch/powerpc/kvm/booke_emulate.c
@@ -24,6 +24,7 @@
 #include "booke.h"
 
 #define OP_19_XOP_RFI     50
+#define OP_19_XOP_RFCI    51
 
 #define OP_31_XOP_MFMSR   83
 #define OP_31_XOP_WRTEE   131
@@ -36,6 +37,12 @@ static void kvmppc_emul_rfi(struct kvm_vcpu *vcpu)
 	kvmppc_set_msr(vcpu, vcpu->arch.shared->srr1);
 }
 
+static void kvmppc_emul_rfci(struct kvm_vcpu *vcpu)
+{
+	vcpu->arch.pc = vcpu->arch.csrr0;
+	kvmppc_set_msr(vcpu, vcpu->arch.csrr1);
+}
+
 int kvmppc_booke_emulate_op(struct kvm_run *run, struct kvm_vcpu *vcpu,
                             unsigned int inst, int *advance)
 {
@@ -52,6 +59,12 @@ int kvmppc_booke_emulate_op(struct kvm_run *run, struct kvm_vcpu *vcpu,
 			*advance = 0;
 			break;
 
+		case OP_19_XOP_RFCI:
+			kvmppc_emul_rfci(vcpu);
+			kvmppc_set_exit_type(vcpu, EMULATED_RFCI_EXITS);
+			*advance = 0;
+			break;
+
 		default:
 			emulated = EMULATE_FAIL;
 			break;
@@ -113,6 +126,12 @@ int kvmppc_booke_emulate_mtspr(struct kvm_vcpu *vcpu, int sprn, ulong spr_val)
 	case SPRN_ESR:
 		vcpu->arch.shared->esr = spr_val;
 		break;
+	case SPRN_CSRR0:
+		vcpu->arch.csrr0 = spr_val;
+		break;
+	case SPRN_CSRR1:
+		vcpu->arch.csrr1 = spr_val;
+		break;
 	case SPRN_DBCR0:
 		vcpu->arch.dbcr0 = spr_val;
 		break;
@@ -129,6 +148,9 @@ int kvmppc_booke_emulate_mtspr(struct kvm_vcpu *vcpu, int sprn, ulong spr_val)
 		kvmppc_set_tcr(vcpu, spr_val);
 		break;
 
+	case SPRN_DECAR:
+		vcpu->arch.decar = spr_val;
+		break;
 	/*
 	 * Note: SPRG4-7 are user-readable.
 	 * These values are loaded into the real SPRGs when resuming the
@@ -229,6 +251,12 @@ int kvmppc_booke_emulate_mfspr(struct kvm_vcpu *vcpu, int sprn, ulong *spr_val)
 	case SPRN_ESR:
 		*spr_val = vcpu->arch.shared->esr;
 		break;
+	case SPRN_CSRR0:
+		*spr_val = vcpu->arch.csrr0;
+		break;
+	case SPRN_CSRR1:
+		*spr_val = vcpu->arch.csrr1;
+		break;
 	case SPRN_DBCR0:
 		*spr_val = vcpu->arch.dbcr0;
 		break;
diff --git a/arch/powerpc/kvm/booke_interrupts.S b/arch/powerpc/kvm/booke_interrupts.S
index 8fd4b2a0911b..bb46b32f9813 100644
--- a/arch/powerpc/kvm/booke_interrupts.S
+++ b/arch/powerpc/kvm/booke_interrupts.S
@@ -52,16 +52,21 @@
                        (1<<BOOKE_INTERRUPT_PROGRAM) | \
                        (1<<BOOKE_INTERRUPT_DTLB_MISS))
 
-.macro KVM_HANDLER ivor_nr
+.macro KVM_HANDLER ivor_nr scratch srr0
 _GLOBAL(kvmppc_handler_\ivor_nr)
 	/* Get pointer to vcpu and record exit number. */
-	mtspr	SPRN_SPRG_WSCRATCH0, r4
+	mtspr	\scratch , r4
 	mfspr	r4, SPRN_SPRG_RVCPU
+	stw	r3, VCPU_GPR(R3)(r4)
 	stw	r5, VCPU_GPR(R5)(r4)
 	stw	r6, VCPU_GPR(R6)(r4)
+	mfspr	r3, \scratch
 	mfctr	r5
-	lis	r6, kvmppc_resume_host@h
+	stw	r3, VCPU_GPR(R4)(r4)
 	stw	r5, VCPU_CTR(r4)
+	mfspr	r3, \srr0
+	lis	r6, kvmppc_resume_host@h
+	stw	r3, VCPU_PC(r4)
 	li	r5, \ivor_nr
 	ori	r6, r6, kvmppc_resume_host@l
 	mtctr	r6
@@ -69,37 +74,35 @@ _GLOBAL(kvmppc_handler_\ivor_nr)
 .endm
 
 _GLOBAL(kvmppc_handlers_start)
-KVM_HANDLER BOOKE_INTERRUPT_CRITICAL
-KVM_HANDLER BOOKE_INTERRUPT_MACHINE_CHECK
-KVM_HANDLER BOOKE_INTERRUPT_DATA_STORAGE
-KVM_HANDLER BOOKE_INTERRUPT_INST_STORAGE
-KVM_HANDLER BOOKE_INTERRUPT_EXTERNAL
-KVM_HANDLER BOOKE_INTERRUPT_ALIGNMENT
-KVM_HANDLER BOOKE_INTERRUPT_PROGRAM
-KVM_HANDLER BOOKE_INTERRUPT_FP_UNAVAIL
-KVM_HANDLER BOOKE_INTERRUPT_SYSCALL
-KVM_HANDLER BOOKE_INTERRUPT_AP_UNAVAIL
-KVM_HANDLER BOOKE_INTERRUPT_DECREMENTER
-KVM_HANDLER BOOKE_INTERRUPT_FIT
-KVM_HANDLER BOOKE_INTERRUPT_WATCHDOG
-KVM_HANDLER BOOKE_INTERRUPT_DTLB_MISS
-KVM_HANDLER BOOKE_INTERRUPT_ITLB_MISS
-KVM_HANDLER BOOKE_INTERRUPT_DEBUG
-KVM_HANDLER BOOKE_INTERRUPT_SPE_UNAVAIL
-KVM_HANDLER BOOKE_INTERRUPT_SPE_FP_DATA
-KVM_HANDLER BOOKE_INTERRUPT_SPE_FP_ROUND
+KVM_HANDLER BOOKE_INTERRUPT_CRITICAL SPRN_SPRG_RSCRATCH_CRIT SPRN_CSRR0
+KVM_HANDLER BOOKE_INTERRUPT_MACHINE_CHECK  SPRN_SPRG_RSCRATCH_MC SPRN_MCSRR0
+KVM_HANDLER BOOKE_INTERRUPT_DATA_STORAGE SPRN_SPRG_RSCRATCH0 SPRN_SRR0
+KVM_HANDLER BOOKE_INTERRUPT_INST_STORAGE SPRN_SPRG_RSCRATCH0 SPRN_SRR0
+KVM_HANDLER BOOKE_INTERRUPT_EXTERNAL SPRN_SPRG_RSCRATCH0 SPRN_SRR0
+KVM_HANDLER BOOKE_INTERRUPT_ALIGNMENT SPRN_SPRG_RSCRATCH0 SPRN_SRR0
+KVM_HANDLER BOOKE_INTERRUPT_PROGRAM SPRN_SPRG_RSCRATCH0 SPRN_SRR0
+KVM_HANDLER BOOKE_INTERRUPT_FP_UNAVAIL SPRN_SPRG_RSCRATCH0 SPRN_SRR0
+KVM_HANDLER BOOKE_INTERRUPT_SYSCALL SPRN_SPRG_RSCRATCH0 SPRN_SRR0
+KVM_HANDLER BOOKE_INTERRUPT_AP_UNAVAIL SPRN_SPRG_RSCRATCH0 SPRN_SRR0
+KVM_HANDLER BOOKE_INTERRUPT_DECREMENTER SPRN_SPRG_RSCRATCH0 SPRN_SRR0
+KVM_HANDLER BOOKE_INTERRUPT_FIT SPRN_SPRG_RSCRATCH0 SPRN_SRR0
+KVM_HANDLER BOOKE_INTERRUPT_WATCHDOG SPRN_SPRG_RSCRATCH_CRIT SPRN_CSRR0
+KVM_HANDLER BOOKE_INTERRUPT_DTLB_MISS SPRN_SPRG_RSCRATCH0 SPRN_SRR0
+KVM_HANDLER BOOKE_INTERRUPT_ITLB_MISS SPRN_SPRG_RSCRATCH0 SPRN_SRR0
+KVM_HANDLER BOOKE_INTERRUPT_DEBUG SPRN_SPRG_RSCRATCH_CRIT SPRN_CSRR0
+KVM_HANDLER BOOKE_INTERRUPT_SPE_UNAVAIL SPRN_SPRG_RSCRATCH0 SPRN_SRR0
+KVM_HANDLER BOOKE_INTERRUPT_SPE_FP_DATA SPRN_SPRG_RSCRATCH0 SPRN_SRR0
+KVM_HANDLER BOOKE_INTERRUPT_SPE_FP_ROUND SPRN_SPRG_RSCRATCH0 SPRN_SRR0
 
 _GLOBAL(kvmppc_handler_len)
 	.long kvmppc_handler_1 - kvmppc_handler_0
 
-
 /* Registers:
  *  SPRG_SCRATCH0: guest r4
  *  r4: vcpu pointer
  *  r5: KVM exit number
  */
 _GLOBAL(kvmppc_resume_host)
-	stw	r3, VCPU_GPR(R3)(r4)
 	mfcr	r3
 	stw	r3, VCPU_CR(r4)
 	stw	r7, VCPU_GPR(R7)(r4)
@@ -180,10 +183,6 @@ _GLOBAL(kvmppc_resume_host)
 	stw	r3, VCPU_LR(r4)
 	mfxer	r3
 	stw	r3, VCPU_XER(r4)
-	mfspr	r3, SPRN_SPRG_RSCRATCH0
-	stw	r3, VCPU_GPR(R4)(r4)
-	mfspr	r3, SPRN_SRR0
-	stw	r3, VCPU_PC(r4)
 
 	/* Restore host stack pointer and PID before IVPR, since the host
 	 * exception handlers use them. */
diff --git a/arch/powerpc/kvm/bookehv_interrupts.S b/arch/powerpc/kvm/bookehv_interrupts.S
index 1685dc43bcf2..d28c2d43ac1b 100644
--- a/arch/powerpc/kvm/bookehv_interrupts.S
+++ b/arch/powerpc/kvm/bookehv_interrupts.S
@@ -262,7 +262,7 @@ kvm_lvl_handler BOOKE_INTERRUPT_CRITICAL, \
 kvm_lvl_handler BOOKE_INTERRUPT_MACHINE_CHECK, \
 	SPRN_SPRG_RSCRATCH_MC, SPRN_MCSRR0, SPRN_MCSRR1, 0
 kvm_handler BOOKE_INTERRUPT_DATA_STORAGE, \
-	SPRN_SRR0, SPRN_SRR1, (NEED_EMU | NEED_DEAR)
+	SPRN_SRR0, SPRN_SRR1, (NEED_EMU | NEED_DEAR | NEED_ESR)
 kvm_handler BOOKE_INTERRUPT_INST_STORAGE, SPRN_SRR0, SPRN_SRR1, NEED_ESR
 kvm_handler BOOKE_INTERRUPT_EXTERNAL, SPRN_SRR0, SPRN_SRR1, 0
 kvm_handler BOOKE_INTERRUPT_ALIGNMENT, \
diff --git a/arch/powerpc/kvm/e500_emulate.c b/arch/powerpc/kvm/e500_emulate.c
index 8b99e076dc81..e04b0ef55ce0 100644
--- a/arch/powerpc/kvm/e500_emulate.c
+++ b/arch/powerpc/kvm/e500_emulate.c
@@ -269,6 +269,9 @@ int kvmppc_core_emulate_mfspr(struct kvm_vcpu *vcpu, int sprn, ulong *spr_val)
 		*spr_val = vcpu->arch.shared->mas7_3 >> 32;
 		break;
 #endif
+	case SPRN_DECAR:
+		*spr_val = vcpu->arch.decar;
+		break;
 	case SPRN_TLB0CFG:
 		*spr_val = vcpu->arch.tlbcfg[0];
 		break;
diff --git a/arch/powerpc/kvm/e500mc.c b/arch/powerpc/kvm/e500mc.c
index fe6c1de6b701..1f89d26e65fb 100644
--- a/arch/powerpc/kvm/e500mc.c
+++ b/arch/powerpc/kvm/e500mc.c
@@ -1,5 +1,5 @@
 /*
- * Copyright (C) 2010 Freescale Semiconductor, Inc. All rights reserved.
+ * Copyright (C) 2010,2012 Freescale Semiconductor, Inc. All rights reserved.
  *
  * Author: Varun Sethi, <varun.sethi@freescale.com>
  *
@@ -57,7 +57,8 @@ void kvmppc_e500_tlbil_one(struct kvmppc_vcpu_e500 *vcpu_e500,
 			   struct kvm_book3e_206_tlb_entry *gtlbe)
 {
 	unsigned int tid, ts;
-	u32 val, eaddr, lpid;
+	gva_t eaddr;
+	u32 val, lpid;
 	unsigned long flags;
 
 	ts = get_tlb_ts(gtlbe);
@@ -183,6 +184,9 @@ int kvmppc_core_vcpu_setup(struct kvm_vcpu *vcpu)
 
 	vcpu->arch.shadow_epcr = SPRN_EPCR_DSIGS | SPRN_EPCR_DGTMI | \
 				 SPRN_EPCR_DUVD;
+#ifdef CONFIG_64BIT
+	vcpu->arch.shadow_epcr |= SPRN_EPCR_ICM;
+#endif
 	vcpu->arch.shadow_msrp = MSRP_UCLEP | MSRP_DEP | MSRP_PMMP;
 	vcpu->arch.eplc = EPC_EGS | (vcpu->kvm->arch.lpid << EPC_ELPID_SHIFT);
 	vcpu->arch.epsc = vcpu->arch.eplc;
diff --git a/arch/powerpc/kvm/emulate.c b/arch/powerpc/kvm/emulate.c
index f90e86dea7a2..ee04abaefe23 100644
--- a/arch/powerpc/kvm/emulate.c
+++ b/arch/powerpc/kvm/emulate.c
@@ -59,11 +59,13 @@
 #define OP_31_XOP_STHBRX    918
 
 #define OP_LWZ  32
+#define OP_LD   58
 #define OP_LWZU 33
 #define OP_LBZ  34
 #define OP_LBZU 35
 #define OP_STW  36
 #define OP_STWU 37
+#define OP_STD  62
 #define OP_STB  38
 #define OP_STBU 39
 #define OP_LHZ  40
@@ -392,6 +394,12 @@ int kvmppc_emulate_instruction(struct kvm_run *run, struct kvm_vcpu *vcpu)
 		emulated = kvmppc_handle_load(run, vcpu, rt, 4, 1);
 		break;
 
+	/* TBD: Add support for other 64 bit load variants like ldu, ldux, ldx etc. */
+	case OP_LD:
+		rt = get_rt(inst);
+		emulated = kvmppc_handle_load(run, vcpu, rt, 8, 1);
+		break;
+
 	case OP_LWZU:
 		emulated = kvmppc_handle_load(run, vcpu, rt, 4, 1);
 		kvmppc_set_gpr(vcpu, ra, vcpu->arch.vaddr_accessed);
@@ -412,6 +420,14 @@ int kvmppc_emulate_instruction(struct kvm_run *run, struct kvm_vcpu *vcpu)
 		                               4, 1);
 		break;
 
+	/* TBD: Add support for other 64 bit store variants like stdu, stdux, stdx etc. */
+	case OP_STD:
+		rs = get_rs(inst);
+		emulated = kvmppc_handle_store(run, vcpu,
+					       kvmppc_get_gpr(vcpu, rs),
+		                               8, 1);
+		break;
+
 	case OP_STWU:
 		emulated = kvmppc_handle_store(run, vcpu,
 					       kvmppc_get_gpr(vcpu, rs),
diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c
index 1493c8de947b..87f4dc886076 100644
--- a/arch/powerpc/kvm/powerpc.c
+++ b/arch/powerpc/kvm/powerpc.c
@@ -246,6 +246,7 @@ int kvm_dev_ioctl_check_extension(long ext)
 #endif
 #ifdef CONFIG_PPC_BOOK3S_64
 	case KVM_CAP_SPAPR_TCE:
+	case KVM_CAP_PPC_ALLOC_HTAB:
 		r = 1;
 		break;
 #endif /* CONFIG_PPC_BOOK3S_64 */
@@ -802,6 +803,23 @@ long kvm_arch_vm_ioctl(struct file *filp,
 			r = -EFAULT;
 		break;
 	}
+
+	case KVM_PPC_ALLOCATE_HTAB: {
+		struct kvm *kvm = filp->private_data;
+		u32 htab_order;
+
+		r = -EFAULT;
+		if (get_user(htab_order, (u32 __user *)argp))
+			break;
+		r = kvmppc_alloc_reset_hpt(kvm, &htab_order);
+		if (r)
+			break;
+		r = -EFAULT;
+		if (put_user(htab_order, (u32 __user *)argp))
+			break;
+		r = 0;
+		break;
+	}
 #endif /* CONFIG_KVM_BOOK3S_64_HV */
 
 #ifdef CONFIG_PPC_BOOK3S_64