Merge tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm

Pull KVM changes from Paolo Bonzini:
 "Here are the 3.13 KVM changes.  There was a lot of work on the PPC
  side: the HV and emulation flavors can now coexist in a single kernel
  is probably the most interesting change from a user point of view.

  On the x86 side there are nested virtualization improvements and a few
  bugfixes.

  ARM got transparent huge page support, improved overcommit, and
  support for big endian guests.

  Finally, there is a new interface to connect KVM with VFIO.  This
  helps with devices that use NoSnoop PCI transactions, letting the
  driver in the guest execute WBINVD instructions.  This includes some
  nVidia cards on Windows, that fail to start without these patches and
  the corresponding userspace changes"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (146 commits)
  kvm, vmx: Fix lazy FPU on nested guest
  arm/arm64: KVM: PSCI: propagate caller endianness to the incoming vcpu
  arm/arm64: KVM: MMIO support for BE guest
  kvm, cpuid: Fix sparse warning
  kvm: Delete prototype for non-existent function kvm_check_iopl
  kvm: Delete prototype for non-existent function complete_pio
  hung_task: add method to reset detector
  pvclock: detect watchdog reset at pvclock read
  kvm: optimize out smp_mb after srcu_read_unlock
  srcu: API for barrier after srcu read unlock
  KVM: remove vm mmap method
  KVM: IOMMU: hva align mapping page size
  KVM: x86: trace cpuid emulation when called from emulator
  KVM: emulator: cleanup decode_register_operand() a bit
  KVM: emulator: check rex prefix inside decode_register()
  KVM: x86: fix emulation of "movzbl %bpl, %eax"
  kvm_host: typo fix
  KVM: x86: emulate SAHF instruction
  MAINTAINERS: add tree for kvm.git
  Documentation/kvm: add a 00-INDEX file
  ...

13 files changed, 513 insertions, 190 deletions

diff --git a/arch/arm/kvm/Kconfig b/arch/arm/kvm/Kconfig
index ebf5015508b5..466bd299b1a8 100644
--- a/arch/arm/kvm/Kconfig
+++ b/arch/arm/kvm/Kconfig
@@ -20,6 +20,7 @@ config KVM
 	bool "Kernel-based Virtual Machine (KVM) support"
 	select PREEMPT_NOTIFIERS
 	select ANON_INODES
+	select HAVE_KVM_CPU_RELAX_INTERCEPT
 	select KVM_MMIO
 	select KVM_ARM_HOST
 	depends on ARM_VIRT_EXT && ARM_LPAE
diff --git a/arch/arm/kvm/Makefile b/arch/arm/kvm/Makefile
index d99bee4950e5..789bca9e64a7 100644
--- a/arch/arm/kvm/Makefile
+++ b/arch/arm/kvm/Makefile
@@ -19,6 +19,6 @@ kvm-arm-y = $(KVM)/kvm_main.o $(KVM)/coalesced_mmio.o
 
 obj-y += kvm-arm.o init.o interrupts.o
 obj-y += arm.o handle_exit.o guest.o mmu.o emulate.o reset.o
-obj-y += coproc.o coproc_a15.o mmio.o psci.o perf.o
+obj-y += coproc.o coproc_a15.o coproc_a7.o mmio.o psci.o perf.o
 obj-$(CONFIG_KVM_ARM_VGIC) += $(KVM)/arm/vgic.o
 obj-$(CONFIG_KVM_ARM_TIMER) += $(KVM)/arm/arch_timer.o
diff --git a/arch/arm/kvm/arm.c b/arch/arm/kvm/arm.c
index aea7ccb8d397..2a700e00528d 100644
--- a/arch/arm/kvm/arm.c
+++ b/arch/arm/kvm/arm.c
@@ -152,12 +152,13 @@ int kvm_arch_vcpu_fault(struct kvm_vcpu *vcpu, struct vm_fault *vmf)
 	return VM_FAULT_SIGBUS;
 }
 
-void kvm_arch_free_memslot(struct kvm_memory_slot *free,
+void kvm_arch_free_memslot(struct kvm *kvm, struct kvm_memory_slot *free,
 			   struct kvm_memory_slot *dont)
 {
 }
 
-int kvm_arch_create_memslot(struct kvm_memory_slot *slot, unsigned long npages)
+int kvm_arch_create_memslot(struct kvm *kvm, struct kvm_memory_slot *slot,
+			    unsigned long npages)
 {
 	return 0;
 }
@@ -797,6 +798,19 @@ long kvm_arch_vm_ioctl(struct file *filp,
 			return -EFAULT;
 		return kvm_vm_ioctl_set_device_addr(kvm, &dev_addr);
 	}
+	case KVM_ARM_PREFERRED_TARGET: {
+		int err;
+		struct kvm_vcpu_init init;
+
+		err = kvm_vcpu_preferred_target(&init);
+		if (err)
+			return err;
+
+		if (copy_to_user(argp, &init, sizeof(init)))
+			return -EFAULT;
+
+		return 0;
+	}
 	default:
 		return -EINVAL;
 	}
diff --git a/arch/arm/kvm/coproc.c b/arch/arm/kvm/coproc.c
index db9cf692d4dd..78c0885d6501 100644
--- a/arch/arm/kvm/coproc.c
+++ b/arch/arm/kvm/coproc.c
@@ -71,6 +71,98 @@ int kvm_handle_cp14_access(struct kvm_vcpu *vcpu, struct kvm_run *run)
 	return 1;
 }
 
+static void reset_mpidr(struct kvm_vcpu *vcpu, const struct coproc_reg *r)
+{
+	/*
+	 * Compute guest MPIDR. We build a virtual cluster out of the
+	 * vcpu_id, but we read the 'U' bit from the underlying
+	 * hardware directly.
+	 */
+	vcpu->arch.cp15[c0_MPIDR] = ((read_cpuid_mpidr() & MPIDR_SMP_BITMASK) |
+				     ((vcpu->vcpu_id >> 2) << MPIDR_LEVEL_BITS) |
+				     (vcpu->vcpu_id & 3));
+}
+
+/* TRM entries A7:4.3.31 A15:4.3.28 - RO WI */
+static bool access_actlr(struct kvm_vcpu *vcpu,
+			 const struct coproc_params *p,
+			 const struct coproc_reg *r)
+{
+	if (p->is_write)
+		return ignore_write(vcpu, p);
+
+	*vcpu_reg(vcpu, p->Rt1) = vcpu->arch.cp15[c1_ACTLR];
+	return true;
+}
+
+/* TRM entries A7:4.3.56, A15:4.3.60 - R/O. */
+static bool access_cbar(struct kvm_vcpu *vcpu,
+			const struct coproc_params *p,
+			const struct coproc_reg *r)
+{
+	if (p->is_write)
+		return write_to_read_only(vcpu, p);
+	return read_zero(vcpu, p);
+}
+
+/* TRM entries A7:4.3.49, A15:4.3.48 - R/O WI */
+static bool access_l2ctlr(struct kvm_vcpu *vcpu,
+			  const struct coproc_params *p,
+			  const struct coproc_reg *r)
+{
+	if (p->is_write)
+		return ignore_write(vcpu, p);
+
+	*vcpu_reg(vcpu, p->Rt1) = vcpu->arch.cp15[c9_L2CTLR];
+	return true;
+}
+
+static void reset_l2ctlr(struct kvm_vcpu *vcpu, const struct coproc_reg *r)
+{
+	u32 l2ctlr, ncores;
+
+	asm volatile("mrc p15, 1, %0, c9, c0, 2\n" : "=r" (l2ctlr));
+	l2ctlr &= ~(3 << 24);
+	ncores = atomic_read(&vcpu->kvm->online_vcpus) - 1;
+	/* How many cores in the current cluster and the next ones */
+	ncores -= (vcpu->vcpu_id & ~3);
+	/* Cap it to the maximum number of cores in a single cluster */
+	ncores = min(ncores, 3U);
+	l2ctlr |= (ncores & 3) << 24;
+
+	vcpu->arch.cp15[c9_L2CTLR] = l2ctlr;
+}
+
+static void reset_actlr(struct kvm_vcpu *vcpu, const struct coproc_reg *r)
+{
+	u32 actlr;
+
+	/* ACTLR contains SMP bit: make sure you create all cpus first! */
+	asm volatile("mrc p15, 0, %0, c1, c0, 1\n" : "=r" (actlr));
+	/* Make the SMP bit consistent with the guest configuration */
+	if (atomic_read(&vcpu->kvm->online_vcpus) > 1)
+		actlr |= 1U << 6;
+	else
+		actlr &= ~(1U << 6);
+
+	vcpu->arch.cp15[c1_ACTLR] = actlr;
+}
+
+/*
+ * TRM entries: A7:4.3.50, A15:4.3.49
+ * R/O WI (even if NSACR.NS_L2ERR, a write of 1 is ignored).
+ */
+static bool access_l2ectlr(struct kvm_vcpu *vcpu,
+			   const struct coproc_params *p,
+			   const struct coproc_reg *r)
+{
+	if (p->is_write)
+		return ignore_write(vcpu, p);
+
+	*vcpu_reg(vcpu, p->Rt1) = 0;
+	return true;
+}
+
 /* See note at ARM ARM B1.14.4 */
 static bool access_dcsw(struct kvm_vcpu *vcpu,
 			const struct coproc_params *p,
@@ -153,10 +245,22 @@ static bool pm_fake(struct kvm_vcpu *vcpu,
  *            registers preceding 32-bit ones.
  */
 static const struct coproc_reg cp15_regs[] = {
+	/* MPIDR: we use VMPIDR for guest access. */
+	{ CRn( 0), CRm( 0), Op1( 0), Op2( 5), is32,
+			NULL, reset_mpidr, c0_MPIDR },
+
 	/* CSSELR: swapped by interrupt.S. */
 	{ CRn( 0), CRm( 0), Op1( 2), Op2( 0), is32,
 			NULL, reset_unknown, c0_CSSELR },
 
+	/* ACTLR: trapped by HCR.TAC bit. */
+	{ CRn( 1), CRm( 0), Op1( 0), Op2( 1), is32,
+			access_actlr, reset_actlr, c1_ACTLR },
+
+	/* CPACR: swapped by interrupt.S. */
+	{ CRn( 1), CRm( 0), Op1( 0), Op2( 2), is32,
+			NULL, reset_val, c1_CPACR, 0x00000000 },
+
 	/* TTBR0/TTBR1: swapped by interrupt.S. */
 	{ CRm64( 2), Op1( 0), is64, NULL, reset_unknown64, c2_TTBR0 },
 	{ CRm64( 2), Op1( 1), is64, NULL, reset_unknown64, c2_TTBR1 },
@@ -195,6 +299,13 @@ static const struct coproc_reg cp15_regs[] = {
 	{ CRn( 7), CRm(10), Op1( 0), Op2( 2), is32, access_dcsw},
 	{ CRn( 7), CRm(14), Op1( 0), Op2( 2), is32, access_dcsw},
 	/*
+	 * L2CTLR access (guest wants to know #CPUs).
+	 */
+	{ CRn( 9), CRm( 0), Op1( 1), Op2( 2), is32,
+			access_l2ctlr, reset_l2ctlr, c9_L2CTLR },
+	{ CRn( 9), CRm( 0), Op1( 1), Op2( 3), is32, access_l2ectlr},
+
+	/*
 	 * Dummy performance monitor implementation.
 	 */
 	{ CRn( 9), CRm(12), Op1( 0), Op2( 0), is32, access_pmcr},
@@ -234,6 +345,9 @@ static const struct coproc_reg cp15_regs[] = {
 	/* CNTKCTL: swapped by interrupt.S. */
 	{ CRn(14), CRm( 1), Op1( 0), Op2( 0), is32,
 			NULL, reset_val, c14_CNTKCTL, 0x00000000 },
+
+	/* The Configuration Base Address Register. */
+	{ CRn(15), CRm( 0), Op1( 4), Op2( 0), is32, access_cbar},
 };
 
 /* Target specific emulation tables */
@@ -241,6 +355,12 @@ static struct kvm_coproc_target_table *target_tables[KVM_ARM_NUM_TARGETS];
 
 void kvm_register_target_coproc_table(struct kvm_coproc_target_table *table)
 {
+	unsigned int i;
+
+	for (i = 1; i < table->num; i++)
+		BUG_ON(cmp_reg(&table->table[i-1],
+			       &table->table[i]) >= 0);
+
 	target_tables[table->target] = table;
 }
 
diff --git a/arch/arm/kvm/coproc_a15.c b/arch/arm/kvm/coproc_a15.c
index cf93472b9dd6..bb0cac1410cc 100644
--- a/arch/arm/kvm/coproc_a15.c
+++ b/arch/arm/kvm/coproc_a15.c
@@ -17,101 +17,12 @@
  * Foundation, 51 Franklin Street, Fifth Floor, Boston, MA  02110-1301, USA.
  */
 #include <linux/kvm_host.h>
-#include <asm/cputype.h>
-#include <asm/kvm_arm.h>
-#include <asm/kvm_host.h>
-#include <asm/kvm_emulate.h>
 #include <asm/kvm_coproc.h>
+#include <asm/kvm_emulate.h>
 #include <linux/init.h>
 
-static void reset_mpidr(struct kvm_vcpu *vcpu, const struct coproc_reg *r)
-{
-	/*
-	 * Compute guest MPIDR:
-	 * (Even if we present only one VCPU to the guest on an SMP
-	 * host we don't set the U bit in the MPIDR, or vice versa, as
-	 * revealing the underlying hardware properties is likely to
-	 * be the best choice).
-	 */
-	vcpu->arch.cp15[c0_MPIDR] = (read_cpuid_mpidr() & ~MPIDR_LEVEL_MASK)
-		| (vcpu->vcpu_id & MPIDR_LEVEL_MASK);
-}
-
 #include "coproc.h"
 
-/* A15 TRM 4.3.28: RO WI */
-static bool access_actlr(struct kvm_vcpu *vcpu,
-			 const struct coproc_params *p,
-			 const struct coproc_reg *r)
-{
-	if (p->is_write)
-		return ignore_write(vcpu, p);
-
-	*vcpu_reg(vcpu, p->Rt1) = vcpu->arch.cp15[c1_ACTLR];
-	return true;
-}
-
-/* A15 TRM 4.3.60: R/O. */
-static bool access_cbar(struct kvm_vcpu *vcpu,
-			const struct coproc_params *p,
-			const struct coproc_reg *r)
-{
-	if (p->is_write)
-		return write_to_read_only(vcpu, p);
-	return read_zero(vcpu, p);
-}
-
-/* A15 TRM 4.3.48: R/O WI. */
-static bool access_l2ctlr(struct kvm_vcpu *vcpu,
-			  const struct coproc_params *p,
-			  const struct coproc_reg *r)
-{
-	if (p->is_write)
-		return ignore_write(vcpu, p);
-
-	*vcpu_reg(vcpu, p->Rt1) = vcpu->arch.cp15[c9_L2CTLR];
-	return true;
-}
-
-static void reset_l2ctlr(struct kvm_vcpu *vcpu, const struct coproc_reg *r)
-{
-	u32 l2ctlr, ncores;
-
-	asm volatile("mrc p15, 1, %0, c9, c0, 2\n" : "=r" (l2ctlr));
-	l2ctlr &= ~(3 << 24);
-	ncores = atomic_read(&vcpu->kvm->online_vcpus) - 1;
-	l2ctlr |= (ncores & 3) << 24;
-
-	vcpu->arch.cp15[c9_L2CTLR] = l2ctlr;
-}
-
-static void reset_actlr(struct kvm_vcpu *vcpu, const struct coproc_reg *r)
-{
-	u32 actlr;
-
-	/* ACTLR contains SMP bit: make sure you create all cpus first! */
-	asm volatile("mrc p15, 0, %0, c1, c0, 1\n" : "=r" (actlr));
-	/* Make the SMP bit consistent with the guest configuration */
-	if (atomic_read(&vcpu->kvm->online_vcpus) > 1)
-		actlr |= 1U << 6;
-	else
-		actlr &= ~(1U << 6);
-
-	vcpu->arch.cp15[c1_ACTLR] = actlr;
-}
-
-/* A15 TRM 4.3.49: R/O WI (even if NSACR.NS_L2ERR, a write of 1 is ignored). */
-static bool access_l2ectlr(struct kvm_vcpu *vcpu,
-			   const struct coproc_params *p,
-			   const struct coproc_reg *r)
-{
-	if (p->is_write)
-		return ignore_write(vcpu, p);
-
-	*vcpu_reg(vcpu, p->Rt1) = 0;
-	return true;
-}
-
 /*
  * A15-specific CP15 registers.
  * CRn denotes the primary register number, but is copied to the CRm in the
@@ -121,29 +32,9 @@ static bool access_l2ectlr(struct kvm_vcpu *vcpu,
  *            registers preceding 32-bit ones.
  */
 static const struct coproc_reg a15_regs[] = {
-	/* MPIDR: we use VMPIDR for guest access. */
-	{ CRn( 0), CRm( 0), Op1( 0), Op2( 5), is32,
-			NULL, reset_mpidr, c0_MPIDR },
-
 	/* SCTLR: swapped by interrupt.S. */
 	{ CRn( 1), CRm( 0), Op1( 0), Op2( 0), is32,
 			NULL, reset_val, c1_SCTLR, 0x00C50078 },
-	/* ACTLR: trapped by HCR.TAC bit. */
-	{ CRn( 1), CRm( 0), Op1( 0), Op2( 1), is32,
-			access_actlr, reset_actlr, c1_ACTLR },
-	/* CPACR: swapped by interrupt.S. */
-	{ CRn( 1), CRm( 0), Op1( 0), Op2( 2), is32,
-			NULL, reset_val, c1_CPACR, 0x00000000 },
-
-	/*
-	 * L2CTLR access (guest wants to know #CPUs).
-	 */
-	{ CRn( 9), CRm( 0), Op1( 1), Op2( 2), is32,
-			access_l2ctlr, reset_l2ctlr, c9_L2CTLR },
-	{ CRn( 9), CRm( 0), Op1( 1), Op2( 3), is32, access_l2ectlr},
-
-	/* The Configuration Base Address Register. */
-	{ CRn(15), CRm( 0), Op1( 4), Op2( 0), is32, access_cbar},
 };
 
 static struct kvm_coproc_target_table a15_target_table = {
@@ -154,12 +45,6 @@ static struct kvm_coproc_target_table a15_target_table = {
 
 static int __init coproc_a15_init(void)
 {
-	unsigned int i;
-
-	for (i = 1; i < ARRAY_SIZE(a15_regs); i++)
-		BUG_ON(cmp_reg(&a15_regs[i-1],
-			       &a15_regs[i]) >= 0);
-
 	kvm_register_target_coproc_table(&a15_target_table);
 	return 0;
 }
diff --git a/arch/arm/kvm/coproc_a7.c b/arch/arm/kvm/coproc_a7.c
new file mode 100644
index 000000000000..1df767331588
--- /dev/null
+++ b/arch/arm/kvm/coproc_a7.c
@@ -0,0 +1,54 @@
+/*
+ * Copyright (C) 2012 - Virtual Open Systems and Columbia University
+ * Copyright (C) 2013 - ARM Ltd
+ *
+ * Authors: Rusty Russell <rusty@rustcorp.au>
+ *          Christoffer Dall <c.dall@virtualopensystems.com>
+ *          Jonathan Austin <jonathan.austin@arm.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License, version 2, as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, 51 Franklin Street, Fifth Floor, Boston, MA  02110-1301, USA.
+ */
+#include <linux/kvm_host.h>
+#include <asm/kvm_coproc.h>
+#include <asm/kvm_emulate.h>
+#include <linux/init.h>
+
+#include "coproc.h"
+
+/*
+ * Cortex-A7 specific CP15 registers.
+ * CRn denotes the primary register number, but is copied to the CRm in the
+ * user space API for 64-bit register access in line with the terminology used
+ * in the ARM ARM.
+ * Important: Must be sorted ascending by CRn, CRM, Op1, Op2 and with 64-bit
+ *            registers preceding 32-bit ones.
+ */
+static const struct coproc_reg a7_regs[] = {
+	/* SCTLR: swapped by interrupt.S. */
+	{ CRn( 1), CRm( 0), Op1( 0), Op2( 0), is32,
+			NULL, reset_val, c1_SCTLR, 0x00C50878 },
+};
+
+static struct kvm_coproc_target_table a7_target_table = {
+	.target = KVM_ARM_TARGET_CORTEX_A7,
+	.table = a7_regs,
+	.num = ARRAY_SIZE(a7_regs),
+};
+
+static int __init coproc_a7_init(void)
+{
+	kvm_register_target_coproc_table(&a7_target_table);
+	return 0;
+}
+late_initcall(coproc_a7_init);
diff --git a/arch/arm/kvm/emulate.c b/arch/arm/kvm/emulate.c
index bdede9e7da51..d6c005283678 100644
--- a/arch/arm/kvm/emulate.c
+++ b/arch/arm/kvm/emulate.c
@@ -354,7 +354,7 @@ static void inject_abt(struct kvm_vcpu *vcpu, bool is_pabt, unsigned long addr)
 	*vcpu_pc(vcpu) = exc_vector_base(vcpu) + vect_offset;
 
 	if (is_pabt) {
-		/* Set DFAR and DFSR */
+		/* Set IFAR and IFSR */
 		vcpu->arch.cp15[c6_IFAR] = addr;
 		is_lpae = (vcpu->arch.cp15[c2_TTBCR] >> 31);
 		/* Always give debug fault for now - should give guest a clue */
diff --git a/arch/arm/kvm/guest.c b/arch/arm/kvm/guest.c
index 152d03612181..20f8d97904af 100644
--- a/arch/arm/kvm/guest.c
+++ b/arch/arm/kvm/guest.c
@@ -190,6 +190,8 @@ int __attribute_const__ kvm_target_cpu(void)
 		return -EINVAL;
 
 	switch (part_number) {
+	case ARM_CPU_PART_CORTEX_A7:
+		return KVM_ARM_TARGET_CORTEX_A7;
 	case ARM_CPU_PART_CORTEX_A15:
 		return KVM_ARM_TARGET_CORTEX_A15;
 	default:
@@ -202,7 +204,7 @@ int kvm_vcpu_set_target(struct kvm_vcpu *vcpu,
 {
 	unsigned int i;
 
-	/* We can only do a cortex A15 for now. */
+	/* We can only cope with guest==host and only on A15/A7 (for now). */
 	if (init->target != kvm_target_cpu())
 		return -EINVAL;
 
@@ -222,6 +224,26 @@ int kvm_vcpu_set_target(struct kvm_vcpu *vcpu,
 	return kvm_reset_vcpu(vcpu);
 }
 
+int kvm_vcpu_preferred_target(struct kvm_vcpu_init *init)
+{
+	int target = kvm_target_cpu();
+
+	if (target < 0)
+		return -ENODEV;
+
+	memset(init, 0, sizeof(*init));
+
+	/*
+	 * For now, we don't return any features.
+	 * In future, we might use features to return target
+	 * specific features available for the preferred
+	 * target type.
+	 */
+	init->target = (__u32)target;
+
+	return 0;
+}
+
 int kvm_arch_vcpu_ioctl_get_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu)
 {
 	return -EINVAL;
diff --git a/arch/arm/kvm/handle_exit.c b/arch/arm/kvm/handle_exit.c
index df4c82d47ad7..a92079011a83 100644
--- a/arch/arm/kvm/handle_exit.c
+++ b/arch/arm/kvm/handle_exit.c
@@ -73,23 +73,29 @@ static int handle_dabt_hyp(struct kvm_vcpu *vcpu, struct kvm_run *run)
 }
 
 /**
- * kvm_handle_wfi - handle a wait-for-interrupts instruction executed by a guest
+ * kvm_handle_wfx - handle a WFI or WFE instructions trapped in guests
  * @vcpu:	the vcpu pointer
  * @run:	the kvm_run structure pointer
  *
- * Simply sets the wait_for_interrupts flag on the vcpu structure, which will
- * halt execution of world-switches and schedule other host processes until
- * there is an incoming IRQ or FIQ to the VM.
+ * WFE: Yield the CPU and come back to this vcpu when the scheduler
+ * decides to.
+ * WFI: Simply call kvm_vcpu_block(), which will halt execution of
+ * world-switches and schedule other host processes until there is an
+ * incoming IRQ or FIQ to the VM.
  */
-static int kvm_handle_wfi(struct kvm_vcpu *vcpu, struct kvm_run *run)
+static int kvm_handle_wfx(struct kvm_vcpu *vcpu, struct kvm_run *run)
 {
 	trace_kvm_wfi(*vcpu_pc(vcpu));
-	kvm_vcpu_block(vcpu);
+	if (kvm_vcpu_get_hsr(vcpu) & HSR_WFI_IS_WFE)
+		kvm_vcpu_on_spin(vcpu);
+	else
+		kvm_vcpu_block(vcpu);
+
 	return 1;
 }
 
 static exit_handle_fn arm_exit_handlers[] = {
-	[HSR_EC_WFI]		= kvm_handle_wfi,
+	[HSR_EC_WFI]		= kvm_handle_wfx,
 	[HSR_EC_CP15_32]	= kvm_handle_cp15_32,
 	[HSR_EC_CP15_64]	= kvm_handle_cp15_64,
 	[HSR_EC_CP14_MR]	= kvm_handle_cp14_access,
diff --git a/arch/arm/kvm/mmio.c b/arch/arm/kvm/mmio.c
index 0c25d9487d53..4cb5a93182e9 100644
--- a/arch/arm/kvm/mmio.c
+++ b/arch/arm/kvm/mmio.c
@@ -23,6 +23,68 @@
 
 #include "trace.h"
 
+static void mmio_write_buf(char *buf, unsigned int len, unsigned long data)
+{
+	void *datap = NULL;
+	union {
+		u8	byte;
+		u16	hword;
+		u32	word;
+		u64	dword;
+	} tmp;
+
+	switch (len) {
+	case 1:
+		tmp.byte	= data;
+		datap		= &tmp.byte;
+		break;
+	case 2:
+		tmp.hword	= data;
+		datap		= &tmp.hword;
+		break;
+	case 4:
+		tmp.word	= data;
+		datap		= &tmp.word;
+		break;
+	case 8:
+		tmp.dword	= data;
+		datap		= &tmp.dword;
+		break;
+	}
+
+	memcpy(buf, datap, len);
+}
+
+static unsigned long mmio_read_buf(char *buf, unsigned int len)
+{
+	unsigned long data = 0;
+	union {
+		u16	hword;
+		u32	word;
+		u64	dword;
+	} tmp;
+
+	switch (len) {
+	case 1:
+		data = buf[0];
+		break;
+	case 2:
+		memcpy(&tmp.hword, buf, len);
+		data = tmp.hword;
+		break;
+	case 4:
+		memcpy(&tmp.word, buf, len);
+		data = tmp.word;
+		break;
+	case 8:
+		memcpy(&tmp.dword, buf, len);
+		data = tmp.dword;
+		break;
+	}
+
+	return data;
+}
+
 /**
  * kvm_handle_mmio_return -- Handle MMIO loads after user space emulation
  * @vcpu: The VCPU pointer
@@ -33,28 +95,27 @@
  */
 int kvm_handle_mmio_return(struct kvm_vcpu *vcpu, struct kvm_run *run)
 {
-	unsigned long *dest;
+	unsigned long data;
 	unsigned int len;
 	int mask;
 
 	if (!run->mmio.is_write) {
-		dest = vcpu_reg(vcpu, vcpu->arch.mmio_decode.rt);
-		*dest = 0;
-
 		len = run->mmio.len;
 		if (len > sizeof(unsigned long))
 			return -EINVAL;
 
-		memcpy(dest, run->mmio.data, len);
-
-		trace_kvm_mmio(KVM_TRACE_MMIO_READ, len, run->mmio.phys_addr,
-				*((u64 *)run->mmio.data));
+		data = mmio_read_buf(run->mmio.data, len);
 
 		if (vcpu->arch.mmio_decode.sign_extend &&
 		    len < sizeof(unsigned long)) {
 			mask = 1U << ((len * 8) - 1);
-			*dest = (*dest ^ mask) - mask;
+			data = (data ^ mask) - mask;
 		}
+
+		trace_kvm_mmio(KVM_TRACE_MMIO_READ, len, run->mmio.phys_addr,
+			       data);
+		data = vcpu_data_host_to_guest(vcpu, data, len);
+		*vcpu_reg(vcpu, vcpu->arch.mmio_decode.rt) = data;
 	}
 
 	return 0;
@@ -105,6 +166,7 @@ int io_mem_abort(struct kvm_vcpu *vcpu, struct kvm_run *run,
 		 phys_addr_t fault_ipa)
 {
 	struct kvm_exit_mmio mmio;
+	unsigned long data;
 	unsigned long rt;
 	int ret;
 
@@ -125,13 +187,15 @@ int io_mem_abort(struct kvm_vcpu *vcpu, struct kvm_run *run,
 	}
 
 	rt = vcpu->arch.mmio_decode.rt;
+	data = vcpu_data_guest_to_host(vcpu, *vcpu_reg(vcpu, rt), mmio.len);
+
 	trace_kvm_mmio((mmio.is_write) ? KVM_TRACE_MMIO_WRITE :
 					 KVM_TRACE_MMIO_READ_UNSATISFIED,
 			mmio.len, fault_ipa,
-			(mmio.is_write) ? *vcpu_reg(vcpu, rt) : 0);
+			(mmio.is_write) ? data : 0);
 
 	if (mmio.is_write)
-		memcpy(mmio.data, vcpu_reg(vcpu, rt), mmio.len);
+		mmio_write_buf(mmio.data, mmio.len, data);
 
 	if (vgic_handle_mmio(vcpu, run, &mmio))
 		return 1;
diff --git a/arch/arm/kvm/mmu.c b/arch/arm/kvm/mmu.c
index b0de86b56c13..371958370de4 100644
--- a/arch/arm/kvm/mmu.c
+++ b/arch/arm/kvm/mmu.c
@@ -19,6 +19,7 @@
 #include <linux/mman.h>
 #include <linux/kvm_host.h>
 #include <linux/io.h>
+#include <linux/hugetlb.h>
 #include <trace/events/kvm.h>
 #include <asm/pgalloc.h>
 #include <asm/cacheflush.h>
@@ -41,6 +42,8 @@ static unsigned long hyp_idmap_start;
 static unsigned long hyp_idmap_end;
 static phys_addr_t hyp_idmap_vector;
 
+#define kvm_pmd_huge(_x)	(pmd_huge(_x) || pmd_trans_huge(_x))
+
 static void kvm_tlb_flush_vmid_ipa(struct kvm *kvm, phys_addr_t ipa)
 {
 	/*
@@ -93,19 +96,29 @@ static bool page_empty(void *ptr)
 
 static void clear_pud_entry(struct kvm *kvm, pud_t *pud, phys_addr_t addr)
 {
-	pmd_t *pmd_table = pmd_offset(pud, 0);
-	pud_clear(pud);
-	kvm_tlb_flush_vmid_ipa(kvm, addr);
-	pmd_free(NULL, pmd_table);
+	if (pud_huge(*pud)) {
+		pud_clear(pud);
+		kvm_tlb_flush_vmid_ipa(kvm, addr);
+	} else {
+		pmd_t *pmd_table = pmd_offset(pud, 0);
+		pud_clear(pud);
+		kvm_tlb_flush_vmid_ipa(kvm, addr);
+		pmd_free(NULL, pmd_table);
+	}
 	put_page(virt_to_page(pud));
 }
 
 static void clear_pmd_entry(struct kvm *kvm, pmd_t *pmd, phys_addr_t addr)
 {
-	pte_t *pte_table = pte_offset_kernel(pmd, 0);
-	pmd_clear(pmd);
-	kvm_tlb_flush_vmid_ipa(kvm, addr);
-	pte_free_kernel(NULL, pte_table);
+	if (kvm_pmd_huge(*pmd)) {
+		pmd_clear(pmd);
+		kvm_tlb_flush_vmid_ipa(kvm, addr);
+	} else {
+		pte_t *pte_table = pte_offset_kernel(pmd, 0);
+		pmd_clear(pmd);
+		kvm_tlb_flush_vmid_ipa(kvm, addr);
+		pte_free_kernel(NULL, pte_table);
+	}
 	put_page(virt_to_page(pmd));
 }
 
@@ -136,18 +149,32 @@ static void unmap_range(struct kvm *kvm, pgd_t *pgdp,
 			continue;
 		}
 
+		if (pud_huge(*pud)) {
+			/*
+			 * If we are dealing with a huge pud, just clear it and
+			 * move on.
+			 */
+			clear_pud_entry(kvm, pud, addr);
+			addr = pud_addr_end(addr, end);
+			continue;
+		}
+
 		pmd = pmd_offset(pud, addr);
 		if (pmd_none(*pmd)) {
 			addr = pmd_addr_end(addr, end);
 			continue;
 		}
 
-		pte = pte_offset_kernel(pmd, addr);
-		clear_pte_entry(kvm, pte, addr);
-		next = addr + PAGE_SIZE;
+		if (!kvm_pmd_huge(*pmd)) {
+			pte = pte_offset_kernel(pmd, addr);
+			clear_pte_entry(kvm, pte, addr);
+			next = addr + PAGE_SIZE;
+		}
 
-		/* If we emptied the pte, walk back up the ladder */
-		if (page_empty(pte)) {
+		/*
+		 * If the pmd entry is to be cleared, walk back up the ladder
+		 */
+		if (kvm_pmd_huge(*pmd) || page_empty(pte)) {
 			clear_pmd_entry(kvm, pmd, addr);
 			next = pmd_addr_end(addr, end);
 			if (page_empty(pmd) && !page_empty(pud)) {
@@ -420,29 +447,71 @@ void kvm_free_stage2_pgd(struct kvm *kvm)
 	kvm->arch.pgd = NULL;
 }
 
-
-static int stage2_set_pte(struct kvm *kvm, struct kvm_mmu_memory_cache *cache,
-			  phys_addr_t addr, const pte_t *new_pte, bool iomap)
+static pmd_t *stage2_get_pmd(struct kvm *kvm, struct kvm_mmu_memory_cache *cache,
+			     phys_addr_t addr)
 {
 	pgd_t *pgd;
 	pud_t *pud;
 	pmd_t *pmd;
-	pte_t *pte, old_pte;
 
-	/* Create 2nd stage page table mapping - Level 1 */
 	pgd = kvm->arch.pgd + pgd_index(addr);
 	pud = pud_offset(pgd, addr);
 	if (pud_none(*pud)) {
 		if (!cache)
-			return 0; /* ignore calls from kvm_set_spte_hva */
+			return NULL;
 		pmd = mmu_memory_cache_alloc(cache);
 		pud_populate(NULL, pud, pmd);
 		get_page(virt_to_page(pud));
 	}
 
-	pmd = pmd_offset(pud, addr);
+	return pmd_offset(pud, addr);
+}
+
+static int stage2_set_pmd_huge(struct kvm *kvm, struct kvm_mmu_memory_cache
+			       *cache, phys_addr_t addr, const pmd_t *new_pmd)
+{
+	pmd_t *pmd, old_pmd;
+
+	pmd = stage2_get_pmd(kvm, cache, addr);
+	VM_BUG_ON(!pmd);
+
+	/*
+	 * Mapping in huge pages should only happen through a fault.  If a
+	 * page is merged into a transparent huge page, the individual
+	 * subpages of that huge page should be unmapped through MMU
+	 * notifiers before we get here.
+	 *
+	 * Merging of CompoundPages is not supported; they should become
+	 * splitting first, unmapped, merged, and mapped back in on-demand.
+	 */
+	VM_BUG_ON(pmd_present(*pmd) && pmd_pfn(*pmd) != pmd_pfn(*new_pmd));
+
+	old_pmd = *pmd;
+	kvm_set_pmd(pmd, *new_pmd);
+	if (pmd_present(old_pmd))
+		kvm_tlb_flush_vmid_ipa(kvm, addr);
+	else
+		get_page(virt_to_page(pmd));
+	return 0;
+}
+
+static int stage2_set_pte(struct kvm *kvm, struct kvm_mmu_memory_cache *cache,
+			  phys_addr_t addr, const pte_t *new_pte, bool iomap)
+{
+	pmd_t *pmd;
+	pte_t *pte, old_pte;
 
-	/* Create 2nd stage page table mapping - Level 2 */
+	/* Create stage-2 page table mapping - Level 1 */
+	pmd = stage2_get_pmd(kvm, cache, addr);
+	if (!pmd) {
+		/*
+		 * Ignore calls from kvm_set_spte_hva for unallocated
+		 * address ranges.
+		 */
+		return 0;
+	}
+
+	/* Create stage-2 page mappings - Level 2 */
 	if (pmd_none(*pmd)) {
 		if (!cache)
 			return 0; /* ignore calls from kvm_set_spte_hva */
@@ -507,16 +576,60 @@ out:
 	return ret;
 }
 
+static bool transparent_hugepage_adjust(pfn_t *pfnp, phys_addr_t *ipap)
+{
+	pfn_t pfn = *pfnp;
+	gfn_t gfn = *ipap >> PAGE_SHIFT;
+
+	if (PageTransCompound(pfn_to_page(pfn))) {
+		unsigned long mask;
+		/*
+		 * The address we faulted on is backed by a transparent huge
+		 * page.  However, because we map the compound huge page and
+		 * not the individual tail page, we need to transfer the
+		 * refcount to the head page.  We have to be careful that the
+		 * THP doesn't start to split while we are adjusting the
+		 * refcounts.
+		 *
+		 * We are sure this doesn't happen, because mmu_notifier_retry
+		 * was successful and we are holding the mmu_lock, so if this
+		 * THP is trying to split, it will be blocked in the mmu
+		 * notifier before touching any of the pages, specifically
+		 * before being able to call __split_huge_page_refcount().
+		 *
+		 * We can therefore safely transfer the refcount from PG_tail
+		 * to PG_head and switch the pfn from a tail page to the head
+		 * page accordingly.
+		 */
+		mask = PTRS_PER_PMD - 1;
+		VM_BUG_ON((gfn & mask) != (pfn & mask));
+		if (pfn & mask) {
+			*ipap &= PMD_MASK;
+			kvm_release_pfn_clean(pfn);
+			pfn &= ~mask;
+			kvm_get_pfn(pfn);
+			*pfnp = pfn;
+		}
+
+		return true;
+	}
+
+	return false;
+}
+
 static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
-			  gfn_t gfn, struct kvm_memory_slot *memslot,
+			  struct kvm_memory_slot *memslot,
 			  unsigned long fault_status)
 {
-	pte_t new_pte;
-	pfn_t pfn;
 	int ret;
-	bool write_fault, writable;
+	bool write_fault, writable, hugetlb = false, force_pte = false;
 	unsigned long mmu_seq;
+	gfn_t gfn = fault_ipa >> PAGE_SHIFT;
+	unsigned long hva = gfn_to_hva(vcpu->kvm, gfn);
+	struct kvm *kvm = vcpu->kvm;
 	struct kvm_mmu_memory_cache *memcache = &vcpu->arch.mmu_page_cache;
+	struct vm_area_struct *vma;
+	pfn_t pfn;
 
 	write_fault = kvm_is_write_fault(kvm_vcpu_get_hsr(vcpu));
 	if (fault_status == FSC_PERM && !write_fault) {
@@ -524,6 +637,26 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 		return -EFAULT;
 	}
 
+	/* Let's check if we will get back a huge page backed by hugetlbfs */
+	down_read(&current->mm->mmap_sem);
+	vma = find_vma_intersection(current->mm, hva, hva + 1);
+	if (is_vm_hugetlb_page(vma)) {
+		hugetlb = true;
+		gfn = (fault_ipa & PMD_MASK) >> PAGE_SHIFT;
+	} else {
+		/*
+		 * Pages belonging to VMAs not aligned to the PMD mapping
+		 * granularity cannot be mapped using block descriptors even
+		 * if the pages belong to a THP for the process, because the
+		 * stage-2 block descriptor will cover more than a single THP
+		 * and we loose atomicity for unmapping, updates, and splits
+		 * of the THP or other pages in the stage-2 block range.
+		 */
+		if (vma->vm_start & ~PMD_MASK)
+			force_pte = true;
+	}
+	up_read(&current->mm->mmap_sem);
+
 	/* We need minimum second+third level pages */
 	ret = mmu_topup_memory_cache(memcache, 2, KVM_NR_MEM_OBJS);
 	if (ret)
@@ -541,26 +674,40 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 	 */
 	smp_rmb();
 
-	pfn = gfn_to_pfn_prot(vcpu->kvm, gfn, write_fault, &writable);
+	pfn = gfn_to_pfn_prot(kvm, gfn, write_fault, &writable);
 	if (is_error_pfn(pfn))
 		return -EFAULT;
 
-	new_pte = pfn_pte(pfn, PAGE_S2);
-	coherent_icache_guest_page(vcpu->kvm, gfn);
-
-	spin_lock(&vcpu->kvm->mmu_lock);
-	if (mmu_notifier_retry(vcpu->kvm, mmu_seq))
+	spin_lock(&kvm->mmu_lock);
+	if (mmu_notifier_retry(kvm, mmu_seq))
 		goto out_unlock;
-	if (writable) {
-		kvm_set_s2pte_writable(&new_pte);
-		kvm_set_pfn_dirty(pfn);
+	if (!hugetlb && !force_pte)
+		hugetlb = transparent_hugepage_adjust(&pfn, &fault_ipa);
+
+	if (hugetlb) {
+		pmd_t new_pmd = pfn_pmd(pfn, PAGE_S2);
+		new_pmd = pmd_mkhuge(new_pmd);
+		if (writable) {
+			kvm_set_s2pmd_writable(&new_pmd);
+			kvm_set_pfn_dirty(pfn);
+		}
+		coherent_icache_guest_page(kvm, hva & PMD_MASK, PMD_SIZE);
+		ret = stage2_set_pmd_huge(kvm, memcache, fault_ipa, &new_pmd);
+	} else {
+		pte_t new_pte = pfn_pte(pfn, PAGE_S2);
+		if (writable) {
+			kvm_set_s2pte_writable(&new_pte);
+			kvm_set_pfn_dirty(pfn);
+		}
+		coherent_icache_guest_page(kvm, hva, PAGE_SIZE);
+		ret = stage2_set_pte(kvm, memcache, fault_ipa, &new_pte, false);
 	}
-	stage2_set_pte(vcpu->kvm, memcache, fault_ipa, &new_pte, false);
+
 
 out_unlock:
-	spin_unlock(&vcpu->kvm->mmu_lock);
+	spin_unlock(&kvm->mmu_lock);
 	kvm_release_pfn_clean(pfn);
-	return 0;
+	return ret;
 }
 
 /**
@@ -629,7 +776,7 @@ int kvm_handle_guest_abort(struct kvm_vcpu *vcpu, struct kvm_run *run)
 
 	memslot = gfn_to_memslot(vcpu->kvm, gfn);
 
-	ret = user_mem_abort(vcpu, fault_ipa, gfn, memslot, fault_status);
+	ret = user_mem_abort(vcpu, fault_ipa, memslot, fault_status);
 	if (ret == 0)
 		ret = 1;
 out_unlock:
diff --git a/arch/arm/kvm/psci.c b/arch/arm/kvm/psci.c
index 86a693a02ba3..0881bf169fbc 100644
--- a/arch/arm/kvm/psci.c
+++ b/arch/arm/kvm/psci.c
@@ -18,6 +18,7 @@
 #include <linux/kvm_host.h>
 #include <linux/wait.h>
 
+#include <asm/cputype.h>
 #include <asm/kvm_emulate.h>
 #include <asm/kvm_psci.h>
 
@@ -34,22 +35,30 @@ static void kvm_psci_vcpu_off(struct kvm_vcpu *vcpu)
 static unsigned long kvm_psci_vcpu_on(struct kvm_vcpu *source_vcpu)
 {
 	struct kvm *kvm = source_vcpu->kvm;
-	struct kvm_vcpu *vcpu;
+	struct kvm_vcpu *vcpu = NULL, *tmp;
 	wait_queue_head_t *wq;
 	unsigned long cpu_id;
+	unsigned long mpidr;
 	phys_addr_t target_pc;
+	int i;
 
 	cpu_id = *vcpu_reg(source_vcpu, 1);
 	if (vcpu_mode_is_32bit(source_vcpu))
 		cpu_id &= ~((u32) 0);
 
-	if (cpu_id >= atomic_read(&kvm->online_vcpus))
+	kvm_for_each_vcpu(i, tmp, kvm) {
+		mpidr = kvm_vcpu_get_mpidr(tmp);
+		if ((mpidr & MPIDR_HWID_BITMASK) == (cpu_id & MPIDR_HWID_BITMASK)) {
+			vcpu = tmp;
+			break;
+		}
+	}
+
+	if (!vcpu)
 		return KVM_PSCI_RET_INVAL;
 
 	target_pc = *vcpu_reg(source_vcpu, 2);
 
-	vcpu = kvm_get_vcpu(kvm, cpu_id);
-
 	wq = kvm_arch_vcpu_wq(vcpu);
 	if (!waitqueue_active(wq))
 		return KVM_PSCI_RET_INVAL;
@@ -62,6 +71,10 @@ static unsigned long kvm_psci_vcpu_on(struct kvm_vcpu *source_vcpu)
 		vcpu_set_thumb(vcpu);
 	}
 
+	/* Propagate caller endianness */
+	if (kvm_vcpu_is_be(source_vcpu))
+		kvm_vcpu_set_be(vcpu);
+
 	*vcpu_pc(vcpu) = target_pc;
 	vcpu->arch.pause = false;
 	smp_mb();		/* Make sure the above is visible */
diff --git a/arch/arm/kvm/reset.c b/arch/arm/kvm/reset.c
index c02ba4af599f..f558c073c023 100644
--- a/arch/arm/kvm/reset.c
+++ b/arch/arm/kvm/reset.c
@@ -30,16 +30,14 @@
 #include <kvm/arm_arch_timer.h>
 
 /******************************************************************************
- * Cortex-A15 Reset Values
+ * Cortex-A15 and Cortex-A7 Reset Values
  */
 
-static const int a15_max_cpu_idx = 3;
-
-static struct kvm_regs a15_regs_reset = {
+static struct kvm_regs cortexa_regs_reset = {
 	.usr_regs.ARM_cpsr = SVC_MODE | PSR_A_BIT | PSR_I_BIT | PSR_F_BIT,
 };
 
-static const struct kvm_irq_level a15_vtimer_irq = {
+static const struct kvm_irq_level cortexa_vtimer_irq = {
 	{ .irq = 27 },
 	.level = 1,
 };
@@ -62,12 +60,11 @@ int kvm_reset_vcpu(struct kvm_vcpu *vcpu)
 	const struct kvm_irq_level *cpu_vtimer_irq;
 
 	switch (vcpu->arch.target) {
+	case KVM_ARM_TARGET_CORTEX_A7:
 	case KVM_ARM_TARGET_CORTEX_A15:
-		if (vcpu->vcpu_id > a15_max_cpu_idx)
-			return -EINVAL;
-		reset_regs = &a15_regs_reset;
+		reset_regs = &cortexa_regs_reset;
 		vcpu->arch.midr = read_cpuid_id();
-		cpu_vtimer_irq = &a15_vtimer_irq;
+		cpu_vtimer_irq = &cortexa_vtimer_irq;
 		break;
 	default:
 		return -ENODEV;