Merge branch 'next' of git://git.kernel.org/pub/scm/virt/kvm/kvm

Pull KVM updates from Gleb Natapov:
 "The highlights of the release are nested EPT and pv-ticketlocks
  support (hypervisor part, guest part, which is most of the code, goes
  through tip tree).  Apart of that there are many fixes for all arches"

Fix up semantic conflicts as discussed in the pull request thread..

* 'next' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (88 commits)
  ARM: KVM: Add newlines to panic strings
  ARM: KVM: Work around older compiler bug
  ARM: KVM: Simplify tracepoint text
  ARM: KVM: Fix kvm_set_pte assignment
  ARM: KVM: vgic: Bump VGIC_NR_IRQS to 256
  ARM: KVM: Bugfix: vgic_bytemap_get_reg per cpu regs
  ARM: KVM: vgic: fix GICD_ICFGRn access
  ARM: KVM: vgic: simplify vgic_get_target_reg
  KVM: MMU: remove unused parameter
  KVM: PPC: Book3S PR: Rework kvmppc_mmu_book3s_64_xlate()
  KVM: PPC: Book3S PR: Make instruction fetch fallback work for system calls
  KVM: PPC: Book3S PR: Don't corrupt guest state when kernel uses VMX
  KVM: x86: update masterclock when kvmclock_offset is calculated (v2)
  KVM: PPC: Book3S: Fix compile error in XICS emulation
  KVM: PPC: Book3S PR: return appropriate error when allocation fails
  arch: powerpc: kvm: add signed type cast for comparation
  KVM: x86: add comments where MMIO does not return to the emulator
  KVM: vmx: count exits to userspace during invalid guest emulation
  KVM: rename __kvm_io_bus_sort_cmp to kvm_io_bus_cmp
  kvm: optimize away THP checks in kvm_is_mmio_pfn()
  ...

23 files changed, 679 insertions, 357 deletions

diff --git a/arch/powerpc/include/asm/kvm_book3s.h b/arch/powerpc/include/asm/kvm_book3s.h
index 08891d07aeb..fa19e2f1a87 100644
--- a/arch/powerpc/include/asm/kvm_book3s.h
+++ b/arch/powerpc/include/asm/kvm_book3s.h
@@ -334,6 +334,27 @@ static inline u32 kvmppc_get_last_inst(struct kvm_vcpu *vcpu)
 	return r;
 }
 
+/*
+ * Like kvmppc_get_last_inst(), but for fetching a sc instruction.
+ * Because the sc instruction sets SRR0 to point to the following
+ * instruction, we have to fetch from pc - 4.
+ */
+static inline u32 kvmppc_get_last_sc(struct kvm_vcpu *vcpu)
+{
+	ulong pc = kvmppc_get_pc(vcpu) - 4;
+	struct kvmppc_book3s_shadow_vcpu *svcpu = svcpu_get(vcpu);
+	u32 r;
+
+	/* Load the instruction manually if it failed to do so in the
+	 * exit path */
+	if (svcpu->last_inst == KVM_INST_FETCH_FAILED)
+		kvmppc_ld(vcpu, &pc, sizeof(u32), &svcpu->last_inst, false);
+
+	r = svcpu->last_inst;
+	svcpu_put(svcpu);
+	return r;
+}
+
 static inline ulong kvmppc_get_fault_dar(struct kvm_vcpu *vcpu)
 {
 	struct kvmppc_book3s_shadow_vcpu *svcpu = svcpu_get(vcpu);
@@ -446,6 +467,23 @@ static inline u32 kvmppc_get_last_inst(struct kvm_vcpu *vcpu)
 	return vcpu->arch.last_inst;
 }
 
+/*
+ * Like kvmppc_get_last_inst(), but for fetching a sc instruction.
+ * Because the sc instruction sets SRR0 to point to the following
+ * instruction, we have to fetch from pc - 4.
+ */
+static inline u32 kvmppc_get_last_sc(struct kvm_vcpu *vcpu)
+{
+	ulong pc = kvmppc_get_pc(vcpu) - 4;
+
+	/* Load the instruction manually if it failed to do so in the
+	 * exit path */
+	if (vcpu->arch.last_inst == KVM_INST_FETCH_FAILED)
+		kvmppc_ld(vcpu, &pc, sizeof(u32), &vcpu->arch.last_inst, false);
+
+	return vcpu->arch.last_inst;
+}
+
 static inline ulong kvmppc_get_fault_dar(struct kvm_vcpu *vcpu)
 {
 	return vcpu->arch.fault_dar;
diff --git a/arch/powerpc/include/asm/kvm_book3s_64.h b/arch/powerpc/include/asm/kvm_book3s_64.h
index a1ecb14e444..86d638a3b35 100644
--- a/arch/powerpc/include/asm/kvm_book3s_64.h
+++ b/arch/powerpc/include/asm/kvm_book3s_64.h
@@ -37,7 +37,7 @@ static inline void svcpu_put(struct kvmppc_book3s_shadow_vcpu *svcpu)
 
 #ifdef CONFIG_KVM_BOOK3S_64_HV
 #define KVM_DEFAULT_HPT_ORDER	24	/* 16MB HPT by default */
-extern int kvm_hpt_order;		/* order of preallocated HPTs */
+extern unsigned long kvm_rma_pages;
 #endif
 
 #define VRMA_VSID	0x1ffffffUL	/* 1TB VSID reserved for VRMA */
@@ -100,7 +100,7 @@ static inline unsigned long compute_tlbie_rb(unsigned long v, unsigned long r,
 			/* (masks depend on page size) */
 			rb |= 0x1000;		/* page encoding in LP field */
 			rb |= (va_low & 0x7f) << 16; /* 7b of VA in AVA/LP field */
-			rb |= (va_low & 0xfe);	/* AVAL field (P7 doesn't seem to care) */
+			rb |= ((va_low << 4) & 0xf0);	/* AVAL field (P7 doesn't seem to care) */
 		}
 	} else {
 		/* 4kB page */
diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h
index af326cde7cb..33283532e9d 100644
--- a/arch/powerpc/include/asm/kvm_host.h
+++ b/arch/powerpc/include/asm/kvm_host.h
@@ -183,13 +183,9 @@ struct kvmppc_spapr_tce_table {
 	struct page *pages[0];
 };
 
-struct kvmppc_linear_info {
-	void		*base_virt;
-	unsigned long	 base_pfn;
-	unsigned long	 npages;
-	struct list_head list;
-	atomic_t	 use_count;
-	int		 type;
+struct kvm_rma_info {
+	atomic_t use_count;
+	unsigned long base_pfn;
 };
 
 /* XICS components, defined in book3s_xics.c */
@@ -246,7 +242,7 @@ struct kvm_arch {
 	int tlbie_lock;
 	unsigned long lpcr;
 	unsigned long rmor;
-	struct kvmppc_linear_info *rma;
+	struct kvm_rma_info *rma;
 	unsigned long vrma_slb_v;
 	int rma_setup_done;
 	int using_mmu_notifiers;
@@ -259,7 +255,7 @@ struct kvm_arch {
 	spinlock_t slot_phys_lock;
 	cpumask_t need_tlb_flush;
 	struct kvmppc_vcore *vcores[KVM_MAX_VCORES];
-	struct kvmppc_linear_info *hpt_li;
+	int hpt_cma_alloc;
 #endif /* CONFIG_KVM_BOOK3S_64_HV */
 #ifdef CONFIG_PPC_BOOK3S_64
 	struct list_head spapr_tce_tables;
diff --git a/arch/powerpc/include/asm/kvm_ppc.h b/arch/powerpc/include/asm/kvm_ppc.h
index a5287fe03d7..b15554a26c2 100644
--- a/arch/powerpc/include/asm/kvm_ppc.h
+++ b/arch/powerpc/include/asm/kvm_ppc.h
@@ -137,10 +137,10 @@ extern long kvmppc_h_put_tce(struct kvm_vcpu *vcpu, unsigned long liobn,
 			     unsigned long ioba, unsigned long tce);
 extern long kvm_vm_ioctl_allocate_rma(struct kvm *kvm,
 				struct kvm_allocate_rma *rma);
-extern struct kvmppc_linear_info *kvm_alloc_rma(void);
-extern void kvm_release_rma(struct kvmppc_linear_info *ri);
-extern struct kvmppc_linear_info *kvm_alloc_hpt(void);
-extern void kvm_release_hpt(struct kvmppc_linear_info *li);
+extern struct kvm_rma_info *kvm_alloc_rma(void);
+extern void kvm_release_rma(struct kvm_rma_info *ri);
+extern struct page *kvm_alloc_hpt(unsigned long nr_pages);
+extern void kvm_release_hpt(struct page *page, unsigned long nr_pages);
 extern int kvmppc_core_init_vm(struct kvm *kvm);
 extern void kvmppc_core_destroy_vm(struct kvm *kvm);
 extern void kvmppc_core_free_memslot(struct kvm_memory_slot *free,
@@ -261,6 +261,7 @@ void kvmppc_set_pid(struct kvm_vcpu *vcpu, u32 pid);
 struct openpic;
 
 #ifdef CONFIG_KVM_BOOK3S_64_HV
+extern void kvm_cma_reserve(void) __init;
 static inline void kvmppc_set_xics_phys(int cpu, unsigned long addr)
 {
 	paca[cpu].kvm_hstate.xics_phys = addr;
@@ -281,13 +282,12 @@ static inline void kvmppc_set_host_ipi(int cpu, u8 host_ipi)
 }
 
 extern void kvmppc_fast_vcpu_kick(struct kvm_vcpu *vcpu);
-extern void kvm_linear_init(void);
 
 #else
-static inline void kvmppc_set_xics_phys(int cpu, unsigned long addr)
+static inline void __init kvm_cma_reserve(void)
 {}
 
-static inline void kvm_linear_init(void)
+static inline void kvmppc_set_xics_phys(int cpu, unsigned long addr)
 {}
 
 static inline u32 kvmppc_get_xics_latch(void)
@@ -394,10 +394,15 @@ static inline void kvmppc_mmu_flush_icache(pfn_t pfn)
 	}
 }
 
-/* Please call after prepare_to_enter. This function puts the lazy ee state
-   back to normal mode, without actually enabling interrupts. */
-static inline void kvmppc_lazy_ee_enable(void)
+/*
+ * Please call after prepare_to_enter. This function puts the lazy ee and irq
+ * disabled tracking state back to normal mode, without actually enabling
+ * interrupts.
+ */
+static inline void kvmppc_fix_ee_before_entry(void)
 {
+	trace_hardirqs_on();
+
 #ifdef CONFIG_PPC64
 	/* Only need to enable IRQs by hard enabling them after this */
 	local_paca->irq_happened = 0;
diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c
index 8207459efe5..d8958be5f31 100644
--- a/arch/powerpc/kernel/asm-offsets.c
+++ b/arch/powerpc/kernel/asm-offsets.c
@@ -454,6 +454,7 @@ int main(void)
 	DEFINE(VCPU_SPRG2, offsetof(struct kvm_vcpu, arch.shregs.sprg2));
 	DEFINE(VCPU_SPRG3, offsetof(struct kvm_vcpu, arch.shregs.sprg3));
 #endif
+	DEFINE(VCPU_SHARED_SPRG3, offsetof(struct kvm_vcpu_arch_shared, sprg3));
 	DEFINE(VCPU_SHARED_SPRG4, offsetof(struct kvm_vcpu_arch_shared, sprg4));
 	DEFINE(VCPU_SHARED_SPRG5, offsetof(struct kvm_vcpu_arch_shared, sprg5));
 	DEFINE(VCPU_SHARED_SPRG6, offsetof(struct kvm_vcpu_arch_shared, sprg6));
diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c
index 389fb8077cc..fe6a58c9f0b 100644
--- a/arch/powerpc/kernel/setup_64.c
+++ b/arch/powerpc/kernel/setup_64.c
@@ -229,6 +229,8 @@ void __init early_setup(unsigned long dt_ptr)
 	/* Initialize the hash table or TLB handling */
 	early_init_mmu();
 
+	kvm_cma_reserve();
+
 	/*
 	 * Reserve any gigantic pages requested on the command line.
 	 * memblock needs to have been initialized by the time this is
@@ -609,8 +611,6 @@ void __init setup_arch(char **cmdline_p)
 	/* Initialize the MMU context management stuff */
 	mmu_context_init();
 
-	kvm_linear_init();
-
 	/* Interrupt code needs to be 64K-aligned */
 	if ((unsigned long)_stext & 0xffff)
 		panic("Kernelbase not 64K-aligned (0x%lx)!\n",
diff --git a/arch/powerpc/kvm/Kconfig b/arch/powerpc/kvm/Kconfig
index eb643f86257..ffaef2cb101 100644
--- a/arch/powerpc/kvm/Kconfig
+++ b/arch/powerpc/kvm/Kconfig
@@ -72,6 +72,7 @@ config KVM_BOOK3S_64_HV
 	bool "KVM support for POWER7 and PPC970 using hypervisor mode in host"
 	depends on KVM_BOOK3S_64
 	select MMU_NOTIFIER
+	select CMA
 	---help---
 	  Support running unmodified book3s_64 guest kernels in
 	  virtual machines on POWER7 and PPC970 processors that have
diff --git a/arch/powerpc/kvm/Makefile b/arch/powerpc/kvm/Makefile
index 008cd856c5b..6646c952c5e 100644
--- a/arch/powerpc/kvm/Makefile
+++ b/arch/powerpc/kvm/Makefile
@@ -81,6 +81,7 @@ kvm-book3s_64-builtin-objs-$(CONFIG_KVM_BOOK3S_64_HV) := \
 	book3s_64_vio_hv.o \
 	book3s_hv_ras.o \
 	book3s_hv_builtin.o \
+	book3s_hv_cma.o \
 	$(kvm-book3s_64-builtin-xics-objs-y)
 
 kvm-book3s_64-objs-$(CONFIG_KVM_XICS) += \
diff --git a/arch/powerpc/kvm/book3s_64_mmu.c b/arch/powerpc/kvm/book3s_64_mmu.c
index 739bfbadb85..7e345e00661 100644
--- a/arch/powerpc/kvm/book3s_64_mmu.c
+++ b/arch/powerpc/kvm/book3s_64_mmu.c
@@ -182,10 +182,13 @@ static int kvmppc_mmu_book3s_64_xlate(struct kvm_vcpu *vcpu, gva_t eaddr,
 	hva_t ptegp;
 	u64 pteg[16];
 	u64 avpn = 0;
+	u64 v, r;
+	u64 v_val, v_mask;
+	u64 eaddr_mask;
 	int i;
-	u8 key = 0;
+	u8 pp, key = 0;
 	bool found = false;
-	int second = 0;
+	bool second = false;
 	ulong mp_ea = vcpu->arch.magic_page_ea;
 
 	/* Magic page override */
@@ -208,8 +211,16 @@ static int kvmppc_mmu_book3s_64_xlate(struct kvm_vcpu *vcpu, gva_t eaddr,
 		goto no_seg_found;
 
 	avpn = kvmppc_mmu_book3s_64_get_avpn(slbe, eaddr);
+	v_val = avpn & HPTE_V_AVPN;
+
 	if (slbe->tb)
-		avpn |= SLB_VSID_B_1T;
+		v_val |= SLB_VSID_B_1T;
+	if (slbe->large)
+		v_val |= HPTE_V_LARGE;
+	v_val |= HPTE_V_VALID;
+
+	v_mask = SLB_VSID_B | HPTE_V_AVPN | HPTE_V_LARGE | HPTE_V_VALID |
+		HPTE_V_SECONDARY;
 
 do_second:
 	ptegp = kvmppc_mmu_book3s_64_get_pteg(vcpu_book3s, slbe, eaddr, second);
@@ -227,91 +238,74 @@ do_second:
 		key = 4;
 
 	for (i=0; i<16; i+=2) {
-		u64 v = pteg[i];
-		u64 r = pteg[i+1];
-
-		/* Valid check */
-		if (!(v & HPTE_V_VALID))
-			continue;
-		/* Hash check */
-		if ((v & HPTE_V_SECONDARY) != second)
-			continue;
-
-		/* AVPN compare */
-		if (HPTE_V_COMPARE(avpn, v)) {
-			u8 pp = (r & HPTE_R_PP) | key;
-			int eaddr_mask = 0xFFF;
-
-			gpte->eaddr = eaddr;
-			gpte->vpage = kvmppc_mmu_book3s_64_ea_to_vp(vcpu,
-								    eaddr,
-								    data);
-			if (slbe->large)
-				eaddr_mask = 0xFFFFFF;
-			gpte->raddr = (r & HPTE_R_RPN) | (eaddr & eaddr_mask);
-			gpte->may_execute = ((r & HPTE_R_N) ? false : true);
-			gpte->may_read = false;
-			gpte->may_write = false;
-
-			switch (pp) {
-			case 0:
-			case 1:
-			case 2:
-			case 6:
-				gpte->may_write = true;
-				/* fall through */
-			case 3:
-			case 5:
-			case 7:
-				gpte->may_read = true;
-				break;
-			}
-
-			dprintk("KVM MMU: Translated 0x%lx [0x%llx] -> 0x%llx "
-				"-> 0x%lx\n",
-				eaddr, avpn, gpte->vpage, gpte->raddr);
+		/* Check all relevant fields of 1st dword */
+		if ((pteg[i] & v_mask) == v_val) {
 			found = true;
 			break;
 		}
 	}
 
-	/* Update PTE R and C bits, so the guest's swapper knows we used the
-	 * page */
-	if (found) {
-		u32 oldr = pteg[i+1];
+	if (!found) {
+		if (second)
+			goto no_page_found;
+		v_val |= HPTE_V_SECONDARY;
+		second = true;
+		goto do_second;
+	}
 
-		if (gpte->may_read) {
-			/* Set the accessed flag */
-			pteg[i+1] |= HPTE_R_R;
-		}
-		if (gpte->may_write) {
-			/* Set the dirty flag */
-			pteg[i+1] |= HPTE_R_C;
-		} else {
-			dprintk("KVM: Mapping read-only page!\n");
-		}
+	v = pteg[i];
+	r = pteg[i+1];
+	pp = (r & HPTE_R_PP) | key;
+	eaddr_mask = 0xFFF;
+
+	gpte->eaddr = eaddr;
+	gpte->vpage = kvmppc_mmu_book3s_64_ea_to_vp(vcpu, eaddr, data);
+	if (slbe->large)
+		eaddr_mask = 0xFFFFFF;
+	gpte->raddr = (r & HPTE_R_RPN & ~eaddr_mask) | (eaddr & eaddr_mask);
+	gpte->may_execute = ((r & HPTE_R_N) ? false : true);
+	gpte->may_read = false;
+	gpte->may_write = false;
+
+	switch (pp) {
+	case 0:
+	case 1:
+	case 2:
+	case 6:
+		gpte->may_write = true;
+		/* fall through */
+	case 3:
+	case 5:
+	case 7:
+		gpte->may_read = true;
+		break;
+	}
 
-		/* Write back into the PTEG */
-		if (pteg[i+1] != oldr)
-			copy_to_user((void __user *)ptegp, pteg, sizeof(pteg));
+	dprintk("KVM MMU: Translated 0x%lx [0x%llx] -> 0x%llx "
+		"-> 0x%lx\n",
+		eaddr, avpn, gpte->vpage, gpte->raddr);
 
-		if (!gpte->may_read)
-			return -EPERM;
-		return 0;
-	} else {
-		dprintk("KVM MMU: No PTE found (ea=0x%lx sdr1=0x%llx "
-			"ptegp=0x%lx)\n",
-			eaddr, to_book3s(vcpu)->sdr1, ptegp);
-		for (i = 0; i < 16; i += 2)
-			dprintk("   %02d: 0x%llx - 0x%llx (0x%llx)\n",
-				i, pteg[i], pteg[i+1], avpn);
-
-		if (!second) {
-			second = HPTE_V_SECONDARY;
-			goto do_second;
-		}
+	/* Update PTE R and C bits, so the guest's swapper knows we used the
+	 * page */
+	if (gpte->may_read) {
+		/* Set the accessed flag */
+		r |= HPTE_R_R;
+	}
+	if (data && gpte->may_write) {
+		/* Set the dirty flag -- XXX even if not writing */
+		r |= HPTE_R_C;
+	}
+
+	/* Write back into the PTEG */
+	if (pteg[i+1] != r) {
+		pteg[i+1] = r;
+		copy_to_user((void __user *)ptegp, pteg, sizeof(pteg));
 	}
 
+	if (!gpte->may_read)
+		return -EPERM;
+	return 0;
+
 no_page_found:
 	return -ENOENT;
 
diff --git a/arch/powerpc/kvm/book3s_64_mmu_hv.c b/arch/powerpc/kvm/book3s_64_mmu_hv.c
index 710d31317d8..043eec8461e 100644
--- a/arch/powerpc/kvm/book3s_64_mmu_hv.c
+++ b/arch/powerpc/kvm/book3s_64_mmu_hv.c
@@ -37,6 +37,8 @@
 #include <asm/ppc-opcode.h>
 #include <asm/cputable.h>
 
+#include "book3s_hv_cma.h"
+
 /* POWER7 has 10-bit LPIDs, PPC970 has 6-bit LPIDs */
 #define MAX_LPID_970	63
 
@@ -52,8 +54,8 @@ long kvmppc_alloc_hpt(struct kvm *kvm, u32 *htab_orderp)
 {
 	unsigned long hpt;
 	struct revmap_entry *rev;
-	struct kvmppc_linear_info *li;
-	long order = kvm_hpt_order;
+	struct page *page = NULL;
+	long order = KVM_DEFAULT_HPT_ORDER;
 
 	if (htab_orderp) {
 		order = *htab_orderp;
@@ -61,26 +63,23 @@ long kvmppc_alloc_hpt(struct kvm *kvm, u32 *htab_orderp)
 			order = PPC_MIN_HPT_ORDER;
 	}
 
+	kvm->arch.hpt_cma_alloc = 0;
 	/*
-	 * If the user wants a different size from default,
 	 * try first to allocate it from the kernel page allocator.
+	 * We keep the CMA reserved for failed allocation.
 	 */
-	hpt = 0;
-	if (order != kvm_hpt_order) {
-		hpt = __get_free_pages(GFP_KERNEL|__GFP_ZERO|__GFP_REPEAT|
-				       __GFP_NOWARN, order - PAGE_SHIFT);
-		if (!hpt)
-			--order;
-	}
+	hpt = __get_free_pages(GFP_KERNEL | __GFP_ZERO | __GFP_REPEAT |
+			       __GFP_NOWARN, order - PAGE_SHIFT);
 
 	/* Next try to allocate from the preallocated pool */
 	if (!hpt) {
-		li = kvm_alloc_hpt();
-		if (li) {
-			hpt = (ulong)li->base_virt;
-			kvm->arch.hpt_li = li;
-			order = kvm_hpt_order;
-		}
+		VM_BUG_ON(order < KVM_CMA_CHUNK_ORDER);
+		page = kvm_alloc_hpt(1 << (order - PAGE_SHIFT));
+		if (page) {
+			hpt = (unsigned long)pfn_to_kaddr(page_to_pfn(page));
+			kvm->arch.hpt_cma_alloc = 1;
+		} else
+			--order;
 	}
 
 	/* Lastly try successively smaller sizes from the page allocator */
@@ -118,8 +117,8 @@ long kvmppc_alloc_hpt(struct kvm *kvm, u32 *htab_orderp)
 	return 0;
 
  out_freehpt:
-	if (kvm->arch.hpt_li)
-		kvm_release_hpt(kvm->arch.hpt_li);
+	if (kvm->arch.hpt_cma_alloc)
+		kvm_release_hpt(page, 1 << (order - PAGE_SHIFT));
 	else
 		free_pages(hpt, order - PAGE_SHIFT);
 	return -ENOMEM;
@@ -165,8 +164,9 @@ void kvmppc_free_hpt(struct kvm *kvm)
 {
 	kvmppc_free_lpid(kvm->arch.lpid);
 	vfree(kvm->arch.revmap);
-	if (kvm->arch.hpt_li)
-		kvm_release_hpt(kvm->arch.hpt_li);
+	if (kvm->arch.hpt_cma_alloc)
+		kvm_release_hpt(virt_to_page(kvm->arch.hpt_virt),
+				1 << (kvm->arch.hpt_order - PAGE_SHIFT));
 	else
 		free_pages(kvm->arch.hpt_virt,
 			   kvm->arch.hpt_order - PAGE_SHIFT);
@@ -1579,7 +1579,7 @@ int kvm_vm_ioctl_get_htab_fd(struct kvm *kvm, struct kvm_get_htab_fd *ghf)
 	ctx->first_pass = 1;
 
 	rwflag = (ghf->flags & KVM_GET_HTAB_WRITE) ? O_WRONLY : O_RDONLY;
-	ret = anon_inode_getfd("kvm-htab", &kvm_htab_fops, ctx, rwflag);
+	ret = anon_inode_getfd("kvm-htab", &kvm_htab_fops, ctx, rwflag | O_CLOEXEC);
 	if (ret < 0) {
 		kvm_put_kvm(kvm);
 		return ret;
diff --git a/arch/powerpc/kvm/book3s_64_vio.c b/arch/powerpc/kvm/book3s_64_vio.c
index b2d3f3b2de7..54cf9bc94da 100644
--- a/arch/powerpc/kvm/book3s_64_vio.c
+++ b/arch/powerpc/kvm/book3s_64_vio.c
@@ -136,7 +136,7 @@ long kvm_vm_ioctl_create_spapr_tce(struct kvm *kvm,
 	mutex_unlock(&kvm->lock);
 
 	return anon_inode_getfd("kvm-spapr-tce", &kvm_spapr_tce_fops,
-				stt, O_RDWR);
+				stt, O_RDWR | O_CLOEXEC);
 
 fail:
 	if (stt) {
diff --git a/arch/powerpc/kvm/book3s_emulate.c b/arch/powerpc/kvm/book3s_emulate.c
index 1f6344c4408..360ce68c980 100644
--- a/arch/powerpc/kvm/book3s_emulate.c
+++ b/arch/powerpc/kvm/book3s_emulate.c
@@ -458,6 +458,7 @@ int kvmppc_core_emulate_mtspr(struct kvm_vcpu *vcpu, int sprn, ulong spr_val)
 	case SPRN_PMC4_GEKKO:
 	case SPRN_WPAR_GEKKO:
 	case SPRN_MSSSR0:
+	case SPRN_DABR:
 		break;
 unprivileged:
 	default:
@@ -555,6 +556,7 @@ int kvmppc_core_emulate_mfspr(struct kvm_vcpu *vcpu, int sprn, ulong *spr_val)
 	case SPRN_PMC4_GEKKO:
 	case SPRN_WPAR_GEKKO:
 	case SPRN_MSSSR0:
+	case SPRN_DABR:
 		*spr_val = 0;
 		break;
 	default:
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index 7629cd3eb91..b0ee3bc9ca7 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -680,13 +680,12 @@ static int kvmppc_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu,
 }
 
 int kvm_arch_vcpu_ioctl_get_sregs(struct kvm_vcpu *vcpu,
-                                  struct kvm_sregs *sregs)
+				  struct kvm_sregs *sregs)
 {
 	int i;
 
-	sregs->pvr = vcpu->arch.pvr;
-
 	memset(sregs, 0, sizeof(struct kvm_sregs));
+	sregs->pvr = vcpu->arch.pvr;
 	for (i = 0; i < vcpu->arch.slb_max; i++) {
 		sregs->u.s.ppc64.slb[i].slbe = vcpu->arch.slb[i].orige;
 		sregs->u.s.ppc64.slb[i].slbv = vcpu->arch.slb[i].origv;
@@ -696,7 +695,7 @@ int kvm_arch_vcpu_ioctl_get_sregs(struct kvm_vcpu *vcpu,
 }
 
 int kvm_arch_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu,
-                                  struct kvm_sregs *sregs)
+				  struct kvm_sregs *sregs)
 {
 	int i, j;
 
@@ -1511,10 +1510,10 @@ static inline int lpcr_rmls(unsigned long rma_size)
 
 static int kvm_rma_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
 {
-	struct kvmppc_linear_info *ri = vma->vm_file->private_data;
 	struct page *page;
+	struct kvm_rma_info *ri = vma->vm_file->private_data;
 
-	if (vmf->pgoff >= ri->npages)
+	if (vmf->pgoff >= kvm_rma_pages)
 		return VM_FAULT_SIGBUS;
 
 	page = pfn_to_page(ri->base_pfn + vmf->pgoff);
@@ -1536,7 +1535,7 @@ static int kvm_rma_mmap(struct file *file, struct vm_area_struct *vma)
 
 static int kvm_rma_release(struct inode *inode, struct file *filp)
 {
-	struct kvmppc_linear_info *ri = filp->private_data;
+	struct kvm_rma_info *ri = filp->private_data;
 
 	kvm_release_rma(ri);
 	return 0;
@@ -1549,18 +1548,27 @@ static const struct file_operations kvm_rma_fops = {
 
 long kvm_vm_ioctl_allocate_rma(struct kvm *kvm, struct kvm_allocate_rma *ret)
 {
-	struct kvmppc_linear_info *ri;
 	long fd;
+	struct kvm_rma_info *ri;
+	/*
+	 * Only do this on PPC970 in HV mode
+	 */
+	if (!cpu_has_feature(CPU_FTR_HVMODE) ||
+	    !cpu_has_feature(CPU_FTR_ARCH_201))
+		return -EINVAL;
+
+	if (!kvm_rma_pages)
+		return -EINVAL;
 
 	ri = kvm_alloc_rma();
 	if (!ri)
 		return -ENOMEM;
 
-	fd = anon_inode_getfd("kvm-rma", &kvm_rma_fops, ri, O_RDWR);
+	fd = anon_inode_getfd("kvm-rma", &kvm_rma_fops, ri, O_RDWR | O_CLOEXEC);
 	if (fd < 0)
 		kvm_release_rma(ri);
 
-	ret->rma_size = ri->npages << PAGE_SHIFT;
+	ret->rma_size = kvm_rma_pages << PAGE_SHIFT;
 	return fd;
 }
 
@@ -1725,7 +1733,7 @@ static int kvmppc_hv_setup_htab_rma(struct kvm_vcpu *vcpu)
 {
 	int err = 0;
 	struct kvm *kvm = vcpu->kvm;
-	struct kvmppc_linear_info *ri = NULL;
+	struct kvm_rma_info *ri = NULL;
 	unsigned long hva;
 	struct kvm_memory_slot *memslot;
 	struct vm_area_struct *vma;
@@ -1803,7 +1811,7 @@ static int kvmppc_hv_setup_htab_rma(struct kvm_vcpu *vcpu)
 
 	} else {
 		/* Set up to use an RMO region */
-		rma_size = ri->npages;
+		rma_size = kvm_rma_pages;
 		if (rma_size > memslot->npages)
 			rma_size = memslot->npages;
 		rma_size <<= PAGE_SHIFT;
@@ -1831,14 +1839,14 @@ static int kvmppc_hv_setup_htab_rma(struct kvm_vcpu *vcpu)
 			/* POWER7 */
 			lpcr &= ~(LPCR_VPM0 | LPCR_VRMA_L);
 			lpcr |= rmls << LPCR_RMLS_SH;
-			kvm->arch.rmor = kvm->arch.rma->base_pfn << PAGE_SHIFT;
+			kvm->arch.rmor = ri->base_pfn << PAGE_SHIFT;
 		}
 		kvm->arch.lpcr = lpcr;
 		pr_info("KVM: Using RMO at %lx size %lx (LPCR = %lx)\n",
 			ri->base_pfn << PAGE_SHIFT, rma_size, lpcr);
 
 		/* Initialize phys addrs of pages in RMO */
-		npages = ri->npages;
+		npages = kvm_rma_pages;
 		porder = __ilog2(npages);
 		physp = memslot->arch.slot_phys;
 		if (physp) {
diff --git a/arch/powerpc/kvm/book3s_hv_builtin.c b/arch/powerpc/kvm/book3s_hv_builtin.c
index ec0a9e5de10..8cd0daebb82 100644
--- a/arch/powerpc/kvm/book3s_hv_builtin.c
+++ b/arch/powerpc/kvm/book3s_hv_builtin.c
@@ -13,33 +13,34 @@
 #include <linux/spinlock.h>
 #include <linux/bootmem.h>
 #include <linux/init.h>
+#include <linux/memblock.h>
+#include <linux/sizes.h>
 
 #include <asm/cputable.h>
 #include <asm/kvm_ppc.h>
 #include <asm/kvm_book3s.h>
 
-#define KVM_LINEAR_RMA		0
-#define KVM_LINEAR_HPT		1
-
-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 *************/
-
+#include "book3s_hv_cma.h"
+/*
+ * Hash page table alignment on newer cpus(CPU_FTR_ARCH_206)
+ * should be power of 2.
+ */
+#define HPT_ALIGN_PAGES		((1 << 18) >> PAGE_SHIFT) /* 256k */
+/*
+ * By default we reserve 5% of memory for hash pagetable allocation.
+ */
+static unsigned long kvm_cma_resv_ratio = 5;
 /*
- * This maintains a list of RMAs (real mode areas) for KVM guests to use.
+ * We allocate RMAs (real mode areas) for KVM guests from the KVM CMA area.
  * Each RMA has to be physically contiguous and of a size that the
  * hardware supports.  PPC970 and POWER7 support 64MB, 128MB and 256MB,
  * and other larger sizes.  Since we are unlikely to be allocate that
  * much physically contiguous memory after the system is up and running,
- * we preallocate a set of RMAs in early boot for KVM to use.
+ * we preallocate a set of RMAs in early boot using CMA.
+ * should be power of 2.
  */
-static unsigned long kvm_rma_size = 64 << 20;	/* 64MB */
-static unsigned long kvm_rma_count;
+unsigned long kvm_rma_pages = (1 << 27) >> PAGE_SHIFT;	/* 128MB */
+EXPORT_SYMBOL_GPL(kvm_rma_pages);
 
 /* Work out RMLS (real mode limit selector) field value for a given RMA size.
    Assumes POWER7 or PPC970. */
@@ -69,165 +70,114 @@ static inline int lpcr_rmls(unsigned long rma_size)
 
 static int __init early_parse_rma_size(char *p)
 {
-	if (!p)
-		return 1;
+	unsigned long kvm_rma_size;
 
+	pr_debug("%s(%s)\n", __func__, p);
+	if (!p)
+		return -EINVAL;
 	kvm_rma_size = memparse(p, &p);
-
+	/*
+	 * Check that the requested size is one supported in hardware
+	 */
+	if (lpcr_rmls(kvm_rma_size) < 0) {
+		pr_err("RMA size of 0x%lx not supported\n", kvm_rma_size);
+		return -EINVAL;
+	}
+	kvm_rma_pages = kvm_rma_size >> PAGE_SHIFT;
 	return 0;
 }
 early_param("kvm_rma_size", early_parse_rma_size);
 
-static int __init early_parse_rma_count(char *p)
+struct kvm_rma_info *kvm_alloc_rma()
 {
-	if (!p)
-		return 1;
-
-	kvm_rma_count = simple_strtoul(p, NULL, 0);
-
-	return 0;
-}
-early_param("kvm_rma_count", early_parse_rma_count);
-
-struct kvmppc_linear_info *kvm_alloc_rma(void)
-{
-	return kvm_alloc_linear(KVM_LINEAR_RMA);
+	struct page *page;
+	struct kvm_rma_info *ri;
+
+	ri = kmalloc(sizeof(struct kvm_rma_info), GFP_KERNEL);
+	if (!ri)
+		return NULL;
+	page = kvm_alloc_cma(kvm_rma_pages, kvm_rma_pages);
+	if (!page)
+		goto err_out;
+	atomic_set(&ri->use_count, 1);
+	ri->base_pfn = page_to_pfn(page);
+	return ri;
+err_out:
+	kfree(ri);
+	return NULL;
 }
 EXPORT_SYMBOL_GPL(kvm_alloc_rma);
 
-void kvm_release_rma(struct kvmppc_linear_info *ri)
+void kvm_release_rma(struct kvm_rma_info *ri)
 {
-	kvm_release_linear(ri);
+	if (atomic_dec_and_test(&ri->use_count)) {
+		kvm_release_cma(pfn_to_page(ri->base_pfn), kvm_rma_pages);
+		kfree(ri);
+	}
 }
 EXPORT_SYMBOL_GPL(kvm_release_rma);
 
-/*************** HPT *************/
-
-/*
- * This maintains a list of big linear HPT tables that contain the GVA->HPA
- * memory mappings. If we don't reserve those early on, we might not be able
- * to get a big (usually 16MB) linear memory region from the kernel anymore.
- */
-
-static unsigned long kvm_hpt_count;
-
-static int __init early_parse_hpt_count(char *p)
+static int __init early_parse_kvm_cma_resv(char *p)
 {
+	pr_debug("%s(%s)\n", __func__, p);
 	if (!p)
-		return 1;
-
-	kvm_hpt_count = simple_strtoul(p, NULL, 0);
-
-	return 0;
+		return -EINVAL;
+	return kstrtoul(p, 0, &kvm_cma_resv_ratio);
 }
-early_param("kvm_hpt_count", early_parse_hpt_count);
+early_param("kvm_cma_resv_ratio", early_parse_kvm_cma_resv);
 
-struct kvmppc_linear_info *kvm_alloc_hpt(void)
+struct page *kvm_alloc_hpt(unsigned long nr_pages)
 {
-	return kvm_alloc_linear(KVM_LINEAR_HPT);
+	unsigned long align_pages = HPT_ALIGN_PAGES;
+
+	/* Old CPUs require HPT aligned on a multiple of its size */
+	if (!cpu_has_feature(CPU_FTR_ARCH_206))
+		align_pages = nr_pages;
+	return kvm_alloc_cma(nr_pages, align_pages);
 }
 EXPORT_SYMBOL_GPL(kvm_alloc_hpt);
 
-void kvm_release_hpt(struct kvmppc_linear_info *li)
+void kvm_release_hpt(struct page *page, unsigned long nr_pages)
 {
-	kvm_release_linear(li);
+	kvm_release_cma(page, nr_pages);
 }
 EXPORT_SYMBOL_GPL(kvm_release_hpt);
 
-/*************** generic *************/
-
-static LIST_HEAD(free_linears);
-static DEFINE_SPINLOCK(linear_lock);
-
-static void __init kvm_linear_init_one(ulong size, int count, int type)
-{
-	unsigned long i;
-	unsigned long j, npages;
-	void *linear;
-	struct page *pg;
-	const char *typestr;
-	struct kvmppc_linear_info *linear_info;
-
-	if (!count)
-		return;
-
-	typestr = (type == KVM_LINEAR_RMA) ? "RMA" : "HPT";
-
-	npages = size >> PAGE_SHIFT;
-	linear_info = alloc_bootmem(count * sizeof(struct kvmppc_linear_info));
-	for (i = 0; i < count; ++i) {
-		linear = alloc_bootmem_align(size, size);
-		pr_debug("Allocated KVM %s at %p (%ld MB)\n", typestr, linear,
-			 size >> 20);
-		linear_info[i].base_virt = linear;
-		linear_info[i].base_pfn = __pa(linear) >> PAGE_SHIFT;
-		linear_info[i].npages = npages;
-		linear_info[i].type = type;
-		list_add_tail(&linear_info[i].list, &free_linears);
-		atomic_set(&linear_info[i].use_count, 0);
-
-		pg = pfn_to_page(linear_info[i].base_pfn);
-		for (j = 0; j < npages; ++j) {
-			atomic_inc(&pg->_count);
-			++pg;
-		}
-	}
-}
-
-static struct kvmppc_linear_info *kvm_alloc_linear(int type)
-{
-	struct kvmppc_linear_info *ri, *ret;
-
-	ret = NULL;
-	spin_lock(&linear_lock);
-	list_for_each_entry(ri, &free_linears, list) {
-		if (ri->type != type)
-			continue;
-
-		list_del(&ri->list);
-		atomic_inc(&ri->use_count);
-		memset(ri->base_virt, 0, ri->npages << PAGE_SHIFT);
-		ret = ri;
-		break;
-	}
-	spin_unlock(&linear_lock);
-	return ret;
-}
-
-static void kvm_release_linear(struct kvmppc_linear_info *ri)
-{
-	if (atomic_dec_and_test(&ri->use_count)) {
-		spin_lock(&linear_lock);
-		list_add_tail(&ri->list, &free_linears);
-		spin_unlock(&linear_lock);
-
-	}
-}
-
-/*
- * Called at boot time while the bootmem allocator is active,
- * to allocate contiguous physical memory for the hash page
- * tables for guests.
+/**
+ * kvm_cma_reserve() - reserve area for kvm hash pagetable
+ *
+ * This function reserves memory from early allocator. It should be
+ * called by arch specific code once the early allocator (memblock or bootmem)
+ * has been activated and all other subsystems have already allocated/reserved
+ * memory.
  */
-void __init kvm_linear_init(void)
+void __init kvm_cma_reserve(void)
 {
-	/* HPT */
-	kvm_linear_init_one(1 << kvm_hpt_order, kvm_hpt_count, KVM_LINEAR_HPT);
-
-	/* RMA */
-	/* Only do this on PPC970 in HV mode */
-	if (!cpu_has_feature(CPU_FTR_HVMODE) ||
-	    !cpu_has_feature(CPU_FTR_ARCH_201))
-		return;
-
-	if (!kvm_rma_size || !kvm_rma_count)
-		return;
-
-	/* Check that the requested size is one supported in hardware */
-	if (lpcr_rmls(kvm_rma_size) < 0) {
-		pr_err("RMA size of 0x%lx not supported\n", kvm_rma_size);
-		return;
+	unsigned long align_size;
+	struct memblock_region *reg;
+	phys_addr_t selected_size = 0;
+	/*
+	 * We cannot use memblock_phys_mem_size() here, because
+	 * memblock_analyze() has not been called yet.
+	 */
+	for_each_memblock(memory, reg)
+		selected_size += memblock_region_memory_end_pfn(reg) -
+				 memblock_region_memory_base_pfn(reg);
+
+	selected_size = (selected_size * kvm_cma_resv_ratio / 100) << PAGE_SHIFT;
+	if (selected_size) {
+		pr_debug("%s: reserving %ld MiB for global area\n", __func__,
+			 (unsigned long)selected_size / SZ_1M);
+		/*
+		 * Old CPUs require HPT aligned on a multiple of its size. So for them
+		 * make the alignment as max size we could request.
+		 */
+		if (!cpu_has_feature(CPU_FTR_ARCH_206))
+			align_size = __rounddown_pow_of_two(selected_size);
+		else
+			align_size = HPT_ALIGN_PAGES << PAGE_SHIFT;
+
+		align_size = max(kvm_rma_pages << PAGE_SHIFT, align_size);
+		kvm_cma_declare_contiguous(selected_size, align_size);
 	}
-
-	kvm_linear_init_one(kvm_rma_size, kvm_rma_count, KVM_LINEAR_RMA);
 }
diff --git a/arch/powerpc/kvm/book3s_hv_cma.c b/arch/powerpc/kvm/book3s_hv_cma.c
new file mode 100644
index 00000000000..d9d3d8553d5
--- /dev/null
+++ b/arch/powerpc/kvm/book3s_hv_cma.c
@@ -0,0 +1,240 @@
+/*
+ * Contiguous Memory Allocator for ppc KVM hash pagetable  based on CMA
+ * for DMA mapping framework
+ *
+ * Copyright IBM Corporation, 2013
+ * Author Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License as
+ * published by the Free Software Foundation; either version 2 of the
+ * License or (at your optional) any later version of the license.
+ *
+ */
+#define pr_fmt(fmt) "kvm_cma: " fmt
+
+#ifdef CONFIG_CMA_DEBUG
+#ifndef DEBUG
+#  define DEBUG
+#endif
+#endif
+
+#include <linux/memblock.h>
+#include <linux/mutex.h>
+#include <linux/sizes.h>
+#include <linux/slab.h>
+
+#include "book3s_hv_cma.h"
+
+struct kvm_cma {
+	unsigned long	base_pfn;
+	unsigned long	count;
+	unsigned long	*bitmap;
+};
+
+static DEFINE_MUTEX(kvm_cma_mutex);
+static struct kvm_cma kvm_cma_area;
+
+/**
+ * kvm_cma_declare_contiguous() - reserve area for contiguous memory handling
+ *			          for kvm hash pagetable
+ * @size:  Size of the reserved memory.
+ * @alignment:  Alignment for the contiguous memory area
+ *
+ * This function reserves memory for kvm cma area. It should be
+ * called by arch code when early allocator (memblock or bootmem)
+ * is still activate.
+ */
+long __init kvm_cma_declare_contiguous(phys_addr_t size, phys_addr_t alignment)
+{
+	long base_pfn;
+	phys_addr_t addr;
+	struct kvm_cma *cma = &kvm_cma_area;
+
+	pr_debug("%s(size %lx)\n", __func__, (unsigned long)size);
+
+	if (!size)
+		return -EINVAL;
+	/*
+	 * Sanitise input arguments.
+	 * We should be pageblock aligned for CMA.
+	 */
+	alignment = max(alignment, (phys_addr_t)(PAGE_SIZE << pageblock_order));
+	size = ALIGN(size, alignment);
+	/*
+	 * Reserve memory
+	 * Use __memblock_alloc_base() since
+	 * memblock_alloc_base() panic()s.
+	 */
+	addr = __memblock_alloc_base(size, alignment, 0);
+	if (!addr) {
+		base_pfn = -ENOMEM;
+		goto err;
+	} else
+		base_pfn = PFN_DOWN(addr);
+
+	/*
+	 * Each reserved area must be initialised later, when more kernel
+	 * subsystems (like slab allocator) are available.
+	 */
+	cma->base_pfn = base_pfn;
+	cma->count    = size >> PAGE_SHIFT;
+	pr_info("CMA: reserved %ld MiB\n", (unsigned long)size / SZ_1M);
+	return 0;
+err:
+	pr_err("CMA: failed to reserve %ld MiB\n", (unsigned long)size / SZ_1M);
+	return base_pfn;
+}
+
+/**
+ * kvm_alloc_cma() - allocate pages from contiguous area
+ * @nr_pages: Requested number of pages.
+ * @align_pages: Requested alignment in number of pages
+ *
+ * This function allocates memory buffer for hash pagetable.
+ */
+struct page *kvm_alloc_cma(unsigned long nr_pages, unsigned long align_pages)
+{
+	int ret;
+	struct page *page = NULL;
+	struct kvm_cma *cma = &kvm_cma_area;
+	unsigned long chunk_count, nr_chunk;
+	unsigned long mask, pfn, pageno, start = 0;
+
+
+	if (!cma || !cma->count)
+		return NULL;
+
+	pr_debug("%s(cma %p, count %lu, align pages %lu)\n", __func__,
+		 (void *)cma, nr_pages, align_pages);
+
+	if (!nr_pages)
+		return NULL;
+	/*
+	 * align mask with chunk size. The bit tracks pages in chunk size
+	 */
+	VM_BUG_ON(!is_power_of_2(align_pages));
+	mask = (align_pages >> (KVM_CMA_CHUNK_ORDER - PAGE_SHIFT)) - 1;
+	BUILD_BUG_ON(PAGE_SHIFT > KVM_CMA_CHUNK_ORDER);
+
+	chunk_count = cma->count >>  (KVM_CMA_CHUNK_ORDER - PAGE_SHIFT);
+	nr_chunk = nr_pages >> (KVM_CMA_CHUNK_ORDER - PAGE_SHIFT);
+
+	mutex_lock(&kvm_cma_mutex);
+	for (;;) {
+		pageno = bitmap_find_next_zero_area(cma->bitmap, chunk_count,
+						    start, nr_chunk, mask);
+		if (pageno >= chunk_count)
+			break;
+
+		pfn = cma->base_pfn + (pageno << (KVM_CMA_CHUNK_ORDER - PAGE_SHIFT));
+		ret = alloc_contig_range(pfn, pfn + nr_pages, MIGRATE_CMA);
+		if (ret == 0) {
+			bitmap_set(cma->bitmap, pageno, nr_chunk);
+			page = pfn_to_page(pfn);
+			memset(pfn_to_kaddr(pfn), 0, nr_pages << PAGE_SHIFT);
+			break;
+		} else if (ret != -EBUSY) {
+			break;
+		}
+		pr_debug("%s(): memory range at %p is busy, retrying\n",
+			 __func__, pfn_to_page(pfn));
+		/* try again with a bit different memory target */
+		start = pageno + mask + 1;
+	}
+	mutex_unlock(&kvm_cma_mutex);
+	pr_debug("%s(): returned %p\n", __func__, page);
+	return page;
+}
+
+/**
+ * kvm_release_cma() - release allocated pages for hash pagetable
+ * @pages: Allocated pages.
+ * @nr_pages: Number of allocated pages.
+ *
+ * This function releases memory allocated by kvm_alloc_cma().
+ * It returns false when provided pages do not belong to contiguous area and
+ * true otherwise.
+ */
+bool kvm_release_cma(struct page *pages, unsigned long nr_pages)
+{
+	unsigned long pfn;
+	unsigned long nr_chunk;
+	struct kvm_cma *cma = &kvm_cma_area;
+
+	if (!cma || !pages)
+		return false;
+
+	pr_debug("%s(page %p count %lu)\n", __func__, (void *)pages, nr_pages);
+
+	pfn = page_to_pfn(pages);
+
+	if (pfn < cma->base_pfn || pfn >= cma->base_pfn + cma->count)
+		return false;
+
+	VM_BUG_ON(pfn + nr_pages > cma->base_pfn + cma->count);
+	nr_chunk = nr_pages >>  (KVM_CMA_CHUNK_ORDER - PAGE_SHIFT);
+
+	mutex_lock(&kvm_cma_mutex);
+	bitmap_clear(cma->bitmap,
+		     (pfn - cma->base_pfn) >> (KVM_CMA_CHUNK_ORDER - PAGE_SHIFT),
+		     nr_chunk);
+	free_contig_range(pfn, nr_pages);
+	mutex_unlock(&kvm_cma_mutex);
+
+	return true;
+}
+
+static int __init kvm_cma_activate_area(unsigned long base_pfn,
+					unsigned long count)
+{
+	unsigned long pfn = base_pfn;
+	unsigned i = count >> pageblock_order;
+	struct zone *zone;
+
+	WARN_ON_ONCE(!pfn_valid(pfn));
+	zone = page_zone(pfn_to_page(pfn));
+	do {
+		unsigned j;
+		base_pfn = pfn;
+		for (j = pageblock_nr_pages; j; --j, pfn++) {
+			WARN_ON_ONCE(!pfn_valid(pfn));
+			/*
+			 * alloc_contig_range requires the pfn range
+			 * specified to be in the same zone. Make this
+			 * simple by forcing the entire CMA resv range
+			 * to be in the same zone.
+			 */
+			if (page_zone(pfn_to_page(pfn)) != zone)
+				return -EINVAL;
+		}
+		init_cma_reserved_pageblock(pfn_to_page(base_pfn));
+	} while (--i);
+	return 0;
+}
+
+static int __init kvm_cma_init_reserved_areas(void)
+{
+	int bitmap_size, ret;
+	unsigned long chunk_count;
+	struct kvm_cma *cma = &kvm_cma_area;
+
+	pr_debug("%s()\n", __func__);
+	if (!cma->count)
+		return 0;
+	chunk_count = cma->count >> (KVM_CMA_CHUNK_ORDER - PAGE_SHIFT);
+	bitmap_size = BITS_TO_LONGS(chunk_count) * sizeof(long);
+	cma->bitmap = kzalloc(bitmap_size, GFP_KERNEL);
+	if (!cma->bitmap)
+		return -ENOMEM;
+
+	ret = kvm_cma_activate_area(cma->base_pfn, cma->count);
+	if (ret)
+		goto error;
+	return 0;
+
+error:
+	kfree(cma->bitmap);
+	return ret;
+}
+core_initcall(kvm_cma_init_reserved_areas);
diff --git a/arch/powerpc/kvm/book3s_hv_cma.h b/arch/powerpc/kvm/book3s_hv_cma.h
new file mode 100644
index 00000000000..655144f75fa
--- /dev/null
+++ b/arch/powerpc/kvm/book3s_hv_cma.h
@@ -0,0 +1,27 @@
+/*
+ * Contiguous Memory Allocator for ppc KVM hash pagetable  based on CMA
+ * for DMA mapping framework
+ *
+ * Copyright IBM Corporation, 2013
+ * Author Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License as
+ * published by the Free Software Foundation; either version 2 of the
+ * License or (at your optional) any later version of the license.
+ *
+ */
+
+#ifndef __POWERPC_KVM_CMA_ALLOC_H__
+#define __POWERPC_KVM_CMA_ALLOC_H__
+/*
+ * Both RMA and Hash page allocation will be multiple of 256K.
+ */
+#define KVM_CMA_CHUNK_ORDER	18
+
+extern struct page *kvm_alloc_cma(unsigned long nr_pages,
+				  unsigned long align_pages);
+extern bool kvm_release_cma(struct page *pages, unsigned long nr_pages);
+extern long kvm_cma_declare_contiguous(phys_addr_t size,
+				       phys_addr_t alignment) __init;
+#endif
diff --git a/arch/powerpc/kvm/book3s_hv_rm_mmu.c b/arch/powerpc/kvm/book3s_hv_rm_mmu.c
index fc25689a9f3..45e30d6e462 100644
--- a/arch/powerpc/kvm/book3s_hv_rm_mmu.c
+++ b/arch/powerpc/kvm/book3s_hv_rm_mmu.c
@@ -383,6 +383,80 @@ static inline int try_lock_tlbie(unsigned int *lock)
 	return old == 0;
 }
 
+/*
+ * tlbie/tlbiel is a bit different on the PPC970 compared to later
+ * processors such as POWER7; the large page bit is in the instruction
+ * not RB, and the top 16 bits and the bottom 12 bits of the VA
+ * in RB must be 0.
+ */
+static void do_tlbies_970(struct kvm *kvm, unsigned long *rbvalues,
+			  long npages, int global, bool need_sync)
+{
+	long i;
+
+	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) {
+			unsigned long rb = rbvalues[i];
+
+			if (rb & 1)		/* large page */
+				asm volatile("tlbie %0,1" : :
+					     "r" (rb & 0x0000fffffffff000ul));
+			else
+				asm volatile("tlbie %0,0" : :
+					     "r" (rb & 0x0000fffffffff000ul));
+		}
+		asm volatile("eieio; tlbsync; ptesync" : : : "memory");
+		kvm->arch.tlbie_lock = 0;
+	} else {
+		if (need_sync)
+			asm volatile("ptesync" : : : "memory");
+		for (i = 0; i < npages; ++i) {
+			unsigned long rb = rbvalues[i];
+
+			if (rb & 1)		/* large page */
+				asm volatile("tlbiel %0,1" : :
+					     "r" (rb & 0x0000fffffffff000ul));
+			else
+				asm volatile("tlbiel %0,0" : :
+					     "r" (rb & 0x0000fffffffff000ul));
+		}
+		asm volatile("ptesync" : : : "memory");
+	}
+}
+
+static void do_tlbies(struct kvm *kvm, unsigned long *rbvalues,
+		      long npages, int global, bool need_sync)
+{
+	long i;
+
+	if (cpu_has_feature(CPU_FTR_ARCH_201)) {
+		/* PPC970 tlbie instruction is a bit different */
+		do_tlbies_970(kvm, rbvalues, npages, global, need_sync);
+		return;
+	}
+	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)
+			asm volatile(PPC_TLBIE(%1,%0) : :
+				     "r" (rbvalues[i]), "r" (kvm->arch.lpid));
+		asm volatile("eieio; tlbsync; ptesync" : : : "memory");
+		kvm->arch.tlbie_lock = 0;
+	} else {
+		if (need_sync)
+			asm volatile("ptesync" : : : "memory");
+		for (i = 0; i < npages; ++i)
+			asm volatile("tlbiel %0" : : "r" (rbvalues[i]));
+		asm volatile("ptesync" : : : "memory");
+	}
+}
+
 long kvmppc_do_h_remove(struct kvm *kvm, unsigned long flags,
 			unsigned long pte_index, unsigned long avpn,
 			unsigned long *hpret)
@@ -408,19 +482,7 @@ long kvmppc_do_h_remove(struct kvm *kvm, unsigned long flags,
 	if (v & HPTE_V_VALID) {
 		hpte[0] &= ~HPTE_V_VALID;
 		rb = compute_tlbie_rb(v, hpte[1], pte_index);
-		if (global_invalidates(kvm, flags)) {
-			while (!try_lock_tlbie(&kvm->arch.tlbie_lock))
-				cpu_relax();
-			asm volatile("ptesync" : : : "memory");
-			asm volatile(PPC_TLBIE(%1,%0)"; eieio; tlbsync"
-				     : : "r" (rb), "r" (kvm->arch.lpid));
-			asm volatile("ptesync" : : : "memory");
-			kvm->arch.tlbie_lock = 0;
-		} else {
-			asm volatile("ptesync" : : : "memory");
-			asm volatile("tlbiel %0" : : "r" (rb));
-			asm volatile("ptesync" : : : "memory");
-		}
+		do_tlbies(kvm, &rb, 1, global_invalidates(kvm, flags), true);
 		/* Read PTE low word after tlbie to get final R/C values */
 		remove_revmap_chain(kvm, pte_index, rev, v, hpte[1]);
 	}
@@ -448,12 +510,11 @@ long kvmppc_h_bulk_remove(struct kvm_vcpu *vcpu)
 	unsigned long *hp, *hptes[4], tlbrb[4];
 	long int i, j, k, n, found, indexes[4];
 	unsigned long flags, req, pte_index, rcbits;
-	long int local = 0;
+	int global;
 	long int ret = H_SUCCESS;
 	struct revmap_entry *rev, *revs[4];
 
-	if (atomic_read(&kvm->online_vcpus) == 1)
-		local = 1;
+	global = global_invalidates(kvm, 0);
 	for (i = 0; i < 4 && ret == H_SUCCESS; ) {
 		n = 0;
 		for (; i < 4; ++i) {
@@ -529,22 +590,7 @@ long kvmppc_h_bulk_remove(struct kvm_vcpu *vcpu)
 			break;
 
 		/* Now that we've collected a batch, do the tlbies */
-		if (!local) {
-			while(!try_lock_tlbie(&kvm->arch.tlbie_lock))
-				cpu_relax();
-			asm volatile("ptesync" : : : "memory");
-			for (k = 0; k < n; ++k)
-				asm volatile(PPC_TLBIE(%1,%0) : :
-					     "r" (tlbrb[k]),
-					     "r" (kvm->arch.lpid));
-			asm volatile("eieio; tlbsync; ptesync" : : : "memory");
-			kvm->arch.tlbie_lock = 0;
-		} else {
-			asm volatile("ptesync" : : : "memory");
-			for (k = 0; k < n; ++k)
-				asm volatile("tlbiel %0" : : "r" (tlbrb[k]));
-			asm volatile("ptesync" : : : "memory");
-		}
+		do_tlbies(kvm, tlbrb, n, global, true);
 
 		/* Read PTE low words after tlbie to get final R/C values */
 		for (k = 0; k < n; ++k) {
@@ -603,19 +649,7 @@ long kvmppc_h_protect(struct kvm_vcpu *vcpu, unsigned long flags,
 	if (v & HPTE_V_VALID) {
 		rb = compute_tlbie_rb(v, r, pte_index);
 		hpte[0] = v & ~HPTE_V_VALID;
-		if (global_invalidates(kvm, flags)) {
-			while(!try_lock_tlbie(&kvm->arch.tlbie_lock))
-				cpu_relax();
-			asm volatile("ptesync" : : : "memory");
-			asm volatile(PPC_TLBIE(%1,%0)"; eieio; tlbsync"
-				     : : "r" (rb), "r" (kvm->arch.lpid));
-			asm volatile("ptesync" : : : "memory");
-			kvm->arch.tlbie_lock = 0;
-		} else {
-			asm volatile("ptesync" : : : "memory");
-			asm volatile("tlbiel %0" : : "r" (rb));
-			asm volatile("ptesync" : : : "memory");
-		}
+		do_tlbies(kvm, &rb, 1, global_invalidates(kvm, flags), true);
 		/*
 		 * If the host has this page as readonly but the guest
 		 * wants to make it read/write, reduce the permissions.
@@ -686,13 +720,7 @@ void kvmppc_invalidate_hpte(struct kvm *kvm, unsigned long *hptep,
 
 	hptep[0] &= ~HPTE_V_VALID;
 	rb = compute_tlbie_rb(hptep[0], hptep[1], pte_index);
-	while (!try_lock_tlbie(&kvm->arch.tlbie_lock))
-		cpu_relax();
-	asm volatile("ptesync" : : : "memory");
-	asm volatile(PPC_TLBIE(%1,%0)"; eieio; tlbsync"
-		     : : "r" (rb), "r" (kvm->arch.lpid));
-	asm volatile("ptesync" : : : "memory");
-	kvm->arch.tlbie_lock = 0;
+	do_tlbies(kvm, &rb, 1, 1, true);
 }
 EXPORT_SYMBOL_GPL(kvmppc_invalidate_hpte);
 
@@ -706,12 +734,7 @@ void kvmppc_clear_ref_hpte(struct kvm *kvm, unsigned long *hptep,
 	rbyte = (hptep[1] & ~HPTE_R_R) >> 8;
 	/* modify only the second-last byte, which contains the ref bit */
 	*((char *)hptep + 14) = rbyte;
-	while (!try_lock_tlbie(&kvm->arch.tlbie_lock))
-		cpu_relax();
-	asm volatile(PPC_TLBIE(%1,%0)"; eieio; tlbsync"
-		     : : "r" (rb), "r" (kvm->arch.lpid));
-	asm volatile("ptesync" : : : "memory");
-	kvm->arch.tlbie_lock = 0;
+	do_tlbies(kvm, &rb, 1, 1, false);
 }
 EXPORT_SYMBOL_GPL(kvmppc_clear_ref_hpte);
 
diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
index b02f91e4c70..60dce5bfab3 100644
--- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S
+++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
@@ -1381,7 +1381,7 @@ hcall_try_real_mode:
 	cmpldi	r3,hcall_real_table_end - hcall_real_table
 	bge	guest_exit_cont
 	LOAD_REG_ADDR(r4, hcall_real_table)
-	lwzx	r3,r3,r4
+	lwax	r3,r3,r4
 	cmpwi	r3,0
 	beq	guest_exit_cont
 	add	r3,r3,r4
diff --git a/arch/powerpc/kvm/book3s_interrupts.S b/arch/powerpc/kvm/book3s_interrupts.S
index 48cbbf86295..17cfae5497a 100644
--- a/arch/powerpc/kvm/book3s_interrupts.S
+++ b/arch/powerpc/kvm/book3s_interrupts.S
@@ -92,6 +92,11 @@ kvm_start_lightweight:
 	PPC_LL	r3, VCPU_HFLAGS(r4)
 	rldicl	r3, r3, 0, 63		/* r3 &= 1 */
 	stb	r3, HSTATE_RESTORE_HID5(r13)
+
+	/* Load up guest SPRG3 value, since it's user readable */
+	ld	r3, VCPU_SHARED(r4)
+	ld	r3, VCPU_SHARED_SPRG3(r3)
+	mtspr	SPRN_SPRG3, r3
 #endif /* CONFIG_PPC_BOOK3S_64 */
 
 	PPC_LL	r4, VCPU_SHADOW_MSR(r4)	/* get shadow_msr */
@@ -123,6 +128,15 @@ kvmppc_handler_highmem:
 	/* R7 = vcpu */
 	PPC_LL	r7, GPR4(r1)
 
+#ifdef CONFIG_PPC_BOOK3S_64
+	/*
+	 * Reload kernel SPRG3 value.
+	 * No need to save guest value as usermode can't modify SPRG3.
+	 */
+	ld	r3, PACA_SPRG3(r13)
+	mtspr	SPRN_SPRG3, r3
+#endif /* CONFIG_PPC_BOOK3S_64 */
+
 	PPC_STL	r14, VCPU_GPR(R14)(r7)
 	PPC_STL	r15, VCPU_GPR(R15)(r7)
 	PPC_STL	r16, VCPU_GPR(R16)(r7)
diff --git a/arch/powerpc/kvm/book3s_pr.c b/arch/powerpc/kvm/book3s_pr.c
index c6e13d9a9e1..27db1e66595 100644
--- a/arch/powerpc/kvm/book3s_pr.c
+++ b/arch/powerpc/kvm/book3s_pr.c
@@ -468,7 +468,8 @@ void kvmppc_giveup_ext(struct kvm_vcpu *vcpu, ulong msr)
 		 * both the traditional FP registers and the added VSX
 		 * registers into thread.fpr[].
 		 */
-		giveup_fpu(current);
+		if (current->thread.regs->msr & MSR_FP)
+			giveup_fpu(current);
 		for (i = 0; i < ARRAY_SIZE(vcpu->arch.fpr); i++)
 			vcpu_fpr[i] = thread_fpr[get_fpr_index(i)];
 
@@ -483,7 +484,8 @@ void kvmppc_giveup_ext(struct kvm_vcpu *vcpu, ulong msr)
 
 #ifdef CONFIG_ALTIVEC
 	if (msr & MSR_VEC) {
-		giveup_altivec(current);
+		if (current->thread.regs->msr & MSR_VEC)
+			giveup_altivec(current);
 		memcpy(vcpu->arch.vr, t->vr, sizeof(vcpu->arch.vr));
 		vcpu->arch.vscr = t->vscr;
 	}
@@ -575,8 +577,6 @@ static int kvmppc_handle_ext(struct kvm_vcpu *vcpu, unsigned int exit_nr,
 	printk(KERN_INFO "Loading up ext 0x%lx\n", msr);
 #endif
 
-	current->thread.regs->msr |= msr;
-
 	if (msr & MSR_FP) {
 		for (i = 0; i < ARRAY_SIZE(vcpu->arch.fpr); i++)
 			thread_fpr[get_fpr_index(i)] = vcpu_fpr[i];
@@ -598,12 +598,32 @@ static int kvmppc_handle_ext(struct kvm_vcpu *vcpu, unsigned int exit_nr,
 #endif
 	}
 
+	current->thread.regs->msr |= msr;
 	vcpu->arch.guest_owned_ext |= msr;
 	kvmppc_recalc_shadow_msr(vcpu);
 
 	return RESUME_GUEST;
 }
 
+/*
+ * Kernel code using FP or VMX could have flushed guest state to
+ * the thread_struct; if so, get it back now.
+ */
+static void kvmppc_handle_lost_ext(struct kvm_vcpu *vcpu)
+{
+	unsigned long lost_ext;
+
+	lost_ext = vcpu->arch.guest_owned_ext & ~current->thread.regs->msr;
+	if (!lost_ext)
+		return;
+
+	if (lost_ext & MSR_FP)
+		kvmppc_load_up_fpu();
+	if (lost_ext & MSR_VEC)
+		kvmppc_load_up_altivec();
+	current->thread.regs->msr |= lost_ext;
+}
+
 int kvmppc_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu,
                        unsigned int exit_nr)
 {
@@ -772,7 +792,7 @@ program_interrupt:
 	}
 	case BOOK3S_INTERRUPT_SYSCALL:
 		if (vcpu->arch.papr_enabled &&
-		    (kvmppc_get_last_inst(vcpu) == 0x44000022) &&
+		    (kvmppc_get_last_sc(vcpu) == 0x44000022) &&
 		    !(vcpu->arch.shared->msr & MSR_PR)) {
 			/* SC 1 papr hypercalls */
 			ulong cmd = kvmppc_get_gpr(vcpu, 3);
@@ -890,8 +910,9 @@ program_interrupt:
 			local_irq_enable();
 			r = s;
 		} else {
-			kvmppc_lazy_ee_enable();
+			kvmppc_fix_ee_before_entry();
 		}
+		kvmppc_handle_lost_ext(vcpu);
 	}
 
 	trace_kvm_book3s_reenter(r, vcpu);
@@ -1162,7 +1183,7 @@ int kvmppc_vcpu_run(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu)
 	if (vcpu->arch.shared->msr & MSR_FP)
 		kvmppc_handle_ext(vcpu, BOOK3S_INTERRUPT_FP_UNAVAIL, MSR_FP);
 
-	kvmppc_lazy_ee_enable();
+	kvmppc_fix_ee_before_entry();
 
 	ret = __kvmppc_vcpu_run(kvm_run, vcpu);
 
diff --git a/arch/powerpc/kvm/book3s_xics.c b/arch/powerpc/kvm/book3s_xics.c
index 94c1dd46b83..a3a5cb8ee7e 100644
--- a/arch/powerpc/kvm/book3s_xics.c
+++ b/arch/powerpc/kvm/book3s_xics.c
@@ -19,6 +19,7 @@
 #include <asm/hvcall.h>
 #include <asm/xics.h>
 #include <asm/debug.h>
+#include <asm/time.h>
 
 #include <linux/debugfs.h>
 #include <linux/seq_file.h>
diff --git a/arch/powerpc/kvm/booke.c b/arch/powerpc/kvm/booke.c
index dcc94f01600..17722d82f1d 100644
--- a/arch/powerpc/kvm/booke.c
+++ b/arch/powerpc/kvm/booke.c
@@ -674,8 +674,6 @@ int kvmppc_vcpu_run(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu)
 		goto out;
 	}
 
-	kvm_guest_enter();
-
 #ifdef CONFIG_PPC_FPU
 	/* Save userspace FPU state in stack */
 	enable_kernel_fp();
@@ -698,7 +696,7 @@ int kvmppc_vcpu_run(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu)
 	kvmppc_load_guest_fp(vcpu);
 #endif
 
-	kvmppc_lazy_ee_enable();
+	kvmppc_fix_ee_before_entry();
 
 	ret = __kvmppc_vcpu_run(kvm_run, vcpu);
 
@@ -1168,7 +1166,7 @@ int kvmppc_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu,
 			local_irq_enable();
 			r = (s << 2) | RESUME_HOST | (r & RESUME_FLAG_NV);
 		} else {
-			kvmppc_lazy_ee_enable();
+			kvmppc_fix_ee_before_entry();
 		}
 	}
 
diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c
index 6316ee336e8..f55e14cd176 100644
--- a/arch/powerpc/kvm/powerpc.c
+++ b/arch/powerpc/kvm/powerpc.c
@@ -117,8 +117,6 @@ int kvmppc_prepare_to_enter(struct kvm_vcpu *vcpu)
 			kvm_guest_exit();
 			continue;
 		}
-
-		trace_hardirqs_on();
 #endif
 
 		kvm_guest_enter();
@@ -420,6 +418,10 @@ int kvm_arch_create_memslot(struct kvm_memory_slot *slot, unsigned long npages)
 	return kvmppc_core_create_memslot(slot, npages);
 }
 
+void kvm_arch_memslots_updated(struct kvm *kvm)
+{
+}
+
 int kvm_arch_prepare_memory_region(struct kvm *kvm,
 				   struct kvm_memory_slot *memslot,
 				   struct kvm_userspace_memory_region *mem,