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

Pull KVM updates from Paolo Bonzini:
 "First round of KVM updates for 3.14; PPC parts will come next week.

  Nothing major here, just bugfixes all over the place.  The most
  interesting part is the ARM guys' virtualized interrupt controller
  overhaul, which lets userspace get/set the state and thus enables
  migration of ARM VMs"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (67 commits)
  kvm: make KVM_MMU_AUDIT help text more readable
  KVM: s390: Fix memory access error detection
  KVM: nVMX: Update guest activity state field on L2 exits
  KVM: nVMX: Fix nested_run_pending on activity state HLT
  KVM: nVMX: Clean up handling of VMX-related MSRs
  KVM: nVMX: Add tracepoints for nested_vmexit and nested_vmexit_inject
  KVM: nVMX: Pass vmexit parameters to nested_vmx_vmexit
  KVM: nVMX: Leave VMX mode on clearing of feature control MSR
  KVM: VMX: Fix DR6 update on #DB exception
  KVM: SVM: Fix reading of DR6
  KVM: x86: Sync DR7 on KVM_SET_DEBUGREGS
  add support for Hyper-V reference time counter
  KVM: remove useless write to vcpu->hv_clock.tsc_timestamp
  KVM: x86: fix tsc catchup issue with tsc scaling
  KVM: x86: limit PIT timer frequency
  KVM: x86: handle invalid root_hpa everywhere
  kvm: Provide kvm_vcpu_eligible_for_directed_yield() stub
  kvm: vfio: silence GCC warning
  KVM: ARM: Remove duplicate include
  arm/arm64: KVM: relax the requirements of VMA alignment for THP
  ...

8 files changed, 176 insertions, 34 deletions

diff --git a/arch/arm/include/asm/kvm_host.h b/arch/arm/include/asm/kvm_host.h
index 8a6f6db14ee4..098f7dd6d564 100644
--- a/arch/arm/include/asm/kvm_host.h
+++ b/arch/arm/include/asm/kvm_host.h
@@ -225,4 +225,7 @@ static inline int kvm_arch_dev_ioctl_check_extension(long ext)
 int kvm_perf_init(void);
 int kvm_perf_teardown(void);
 
+u64 kvm_arm_timer_get_reg(struct kvm_vcpu *, u64 regid);
+int kvm_arm_timer_set_reg(struct kvm_vcpu *, u64 regid, u64 value);
+
 #endif /* __ARM_KVM_HOST_H__ */
diff --git a/arch/arm/include/asm/kvm_mmu.h b/arch/arm/include/asm/kvm_mmu.h
index 77de4a41cc50..2d122adcdb22 100644
--- a/arch/arm/include/asm/kvm_mmu.h
+++ b/arch/arm/include/asm/kvm_mmu.h
@@ -140,6 +140,7 @@ static inline void coherent_icache_guest_page(struct kvm *kvm, hva_t hva,
 }
 
 #define kvm_flush_dcache_to_poc(a,l)	__cpuc_flush_dcache_area((a), (l))
+#define kvm_virt_to_phys(x)		virt_to_idmap((unsigned long)(x))
 
 #endif	/* !__ASSEMBLY__ */
 
diff --git a/arch/arm/include/uapi/asm/kvm.h b/arch/arm/include/uapi/asm/kvm.h
index c498b60c0505..ef0c8785ba16 100644
--- a/arch/arm/include/uapi/asm/kvm.h
+++ b/arch/arm/include/uapi/asm/kvm.h
@@ -119,6 +119,26 @@ struct kvm_arch_memory_slot {
 #define KVM_REG_ARM_32_CRN_MASK		0x0000000000007800
 #define KVM_REG_ARM_32_CRN_SHIFT	11
 
+#define ARM_CP15_REG_SHIFT_MASK(x,n) \
+	(((x) << KVM_REG_ARM_ ## n ## _SHIFT) & KVM_REG_ARM_ ## n ## _MASK)
+
+#define __ARM_CP15_REG(op1,crn,crm,op2) \
+	(KVM_REG_ARM | (15 << KVM_REG_ARM_COPROC_SHIFT) | \
+	ARM_CP15_REG_SHIFT_MASK(op1, OPC1) | \
+	ARM_CP15_REG_SHIFT_MASK(crn, 32_CRN) | \
+	ARM_CP15_REG_SHIFT_MASK(crm, CRM) | \
+	ARM_CP15_REG_SHIFT_MASK(op2, 32_OPC2))
+
+#define ARM_CP15_REG32(...) (__ARM_CP15_REG(__VA_ARGS__) | KVM_REG_SIZE_U32)
+
+#define __ARM_CP15_REG64(op1,crm) \
+	(__ARM_CP15_REG(op1, 0, crm, 0) | KVM_REG_SIZE_U64)
+#define ARM_CP15_REG64(...) __ARM_CP15_REG64(__VA_ARGS__)
+
+#define KVM_REG_ARM_TIMER_CTL		ARM_CP15_REG32(0, 14, 3, 1)
+#define KVM_REG_ARM_TIMER_CNT		ARM_CP15_REG64(1, 14) 
+#define KVM_REG_ARM_TIMER_CVAL		ARM_CP15_REG64(3, 14) 
+
 /* Normal registers are mapped as coprocessor 16. */
 #define KVM_REG_ARM_CORE		(0x0010 << KVM_REG_ARM_COPROC_SHIFT)
 #define KVM_REG_ARM_CORE_REG(name)	(offsetof(struct kvm_regs, name) / 4)
@@ -143,6 +163,14 @@ struct kvm_arch_memory_slot {
 #define KVM_REG_ARM_VFP_FPINST		0x1009
 #define KVM_REG_ARM_VFP_FPINST2		0x100A
 
+/* Device Control API: ARM VGIC */
+#define KVM_DEV_ARM_VGIC_GRP_ADDR	0
+#define KVM_DEV_ARM_VGIC_GRP_DIST_REGS	1
+#define KVM_DEV_ARM_VGIC_GRP_CPU_REGS	2
+#define   KVM_DEV_ARM_VGIC_CPUID_SHIFT	32
+#define   KVM_DEV_ARM_VGIC_CPUID_MASK	(0xffULL << KVM_DEV_ARM_VGIC_CPUID_SHIFT)
+#define   KVM_DEV_ARM_VGIC_OFFSET_SHIFT	0
+#define   KVM_DEV_ARM_VGIC_OFFSET_MASK	(0xffffffffULL << KVM_DEV_ARM_VGIC_OFFSET_SHIFT)
 
 /* KVM_IRQ_LINE irq field index values */
 #define KVM_ARM_IRQ_TYPE_SHIFT		24
diff --git a/arch/arm/kvm/arm.c b/arch/arm/kvm/arm.c
index b18165ca1d38..1d8248ea5669 100644
--- a/arch/arm/kvm/arm.c
+++ b/arch/arm/kvm/arm.c
@@ -138,6 +138,8 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
 	if (ret)
 		goto out_free_stage2_pgd;
 
+	kvm_timer_init(kvm);
+
 	/* Mark the initial VMID generation invalid */
 	kvm->arch.vmid_gen = 0;
 
@@ -189,6 +191,7 @@ int kvm_dev_ioctl_check_extension(long ext)
 	case KVM_CAP_IRQCHIP:
 		r = vgic_present;
 		break;
+	case KVM_CAP_DEVICE_CTRL:
 	case KVM_CAP_USER_MEMORY:
 	case KVM_CAP_SYNC_MMU:
 	case KVM_CAP_DESTROY_MEMORY_REGION_WORKS:
@@ -340,6 +343,13 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 
 void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu)
 {
+	/*
+	 * The arch-generic KVM code expects the cpu field of a vcpu to be -1
+	 * if the vcpu is no longer assigned to a cpu.  This is used for the
+	 * optimized make_all_cpus_request path.
+	 */
+	vcpu->cpu = -1;
+
 	kvm_arm_set_running_vcpu(NULL);
 }
 
@@ -463,6 +473,8 @@ static void update_vttbr(struct kvm *kvm)
 
 static int kvm_vcpu_first_run_init(struct kvm_vcpu *vcpu)
 {
+	int ret;
+
 	if (likely(vcpu->arch.has_run_once))
 		return 0;
 
@@ -472,22 +484,12 @@ static int kvm_vcpu_first_run_init(struct kvm_vcpu *vcpu)
 	 * Initialize the VGIC before running a vcpu the first time on
 	 * this VM.
 	 */
-	if (irqchip_in_kernel(vcpu->kvm) &&
-	    unlikely(!vgic_initialized(vcpu->kvm))) {
-		int ret = kvm_vgic_init(vcpu->kvm);
+	if (unlikely(!vgic_initialized(vcpu->kvm))) {
+		ret = kvm_vgic_init(vcpu->kvm);
 		if (ret)
 			return ret;
 	}
 
-	/*
-	 * Handle the "start in power-off" case by calling into the
-	 * PSCI code.
-	 */
-	if (test_and_clear_bit(KVM_ARM_VCPU_POWER_OFF, vcpu->arch.features)) {
-		*vcpu_reg(vcpu, 0) = KVM_PSCI_FN_CPU_OFF;
-		kvm_psci_call(vcpu);
-	}
-
 	return 0;
 }
 
@@ -701,6 +703,24 @@ int kvm_vm_ioctl_irq_line(struct kvm *kvm, struct kvm_irq_level *irq_level,
 	return -EINVAL;
 }
 
+static int kvm_arch_vcpu_ioctl_vcpu_init(struct kvm_vcpu *vcpu,
+					 struct kvm_vcpu_init *init)
+{
+	int ret;
+
+	ret = kvm_vcpu_set_target(vcpu, init);
+	if (ret)
+		return ret;
+
+	/*
+	 * Handle the "start in power-off" case by marking the VCPU as paused.
+	 */
+	if (__test_and_clear_bit(KVM_ARM_VCPU_POWER_OFF, vcpu->arch.features))
+		vcpu->arch.pause = true;
+
+	return 0;
+}
+
 long kvm_arch_vcpu_ioctl(struct file *filp,
 			 unsigned int ioctl, unsigned long arg)
 {
@@ -714,8 +734,7 @@ long kvm_arch_vcpu_ioctl(struct file *filp,
 		if (copy_from_user(&init, argp, sizeof(init)))
 			return -EFAULT;
 
-		return kvm_vcpu_set_target(vcpu, &init);
-
+		return kvm_arch_vcpu_ioctl_vcpu_init(vcpu, &init);
 	}
 	case KVM_SET_ONE_REG:
 	case KVM_GET_ONE_REG: {
@@ -773,7 +792,7 @@ static int kvm_vm_ioctl_set_device_addr(struct kvm *kvm,
 	case KVM_ARM_DEVICE_VGIC_V2:
 		if (!vgic_present)
 			return -ENXIO;
-		return kvm_vgic_set_addr(kvm, type, dev_addr->addr);
+		return kvm_vgic_addr(kvm, type, &dev_addr->addr, true);
 	default:
 		return -ENODEV;
 	}
diff --git a/arch/arm/kvm/guest.c b/arch/arm/kvm/guest.c
index 20f8d97904af..2786eae10c0d 100644
--- a/arch/arm/kvm/guest.c
+++ b/arch/arm/kvm/guest.c
@@ -109,6 +109,83 @@ int kvm_arch_vcpu_ioctl_set_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs)
 	return -EINVAL;
 }
 
+#ifndef CONFIG_KVM_ARM_TIMER
+
+#define NUM_TIMER_REGS 0
+
+static int copy_timer_indices(struct kvm_vcpu *vcpu, u64 __user *uindices)
+{
+	return 0;
+}
+
+static bool is_timer_reg(u64 index)
+{
+	return false;
+}
+
+int kvm_arm_timer_set_reg(struct kvm_vcpu *vcpu, u64 regid, u64 value)
+{
+	return 0;
+}
+
+u64 kvm_arm_timer_get_reg(struct kvm_vcpu *vcpu, u64 regid)
+{
+	return 0;
+}
+
+#else
+
+#define NUM_TIMER_REGS 3
+
+static bool is_timer_reg(u64 index)
+{
+	switch (index) {
+	case KVM_REG_ARM_TIMER_CTL:
+	case KVM_REG_ARM_TIMER_CNT:
+	case KVM_REG_ARM_TIMER_CVAL:
+		return true;
+	}
+	return false;
+}
+
+static int copy_timer_indices(struct kvm_vcpu *vcpu, u64 __user *uindices)
+{
+	if (put_user(KVM_REG_ARM_TIMER_CTL, uindices))
+		return -EFAULT;
+	uindices++;
+	if (put_user(KVM_REG_ARM_TIMER_CNT, uindices))
+		return -EFAULT;
+	uindices++;
+	if (put_user(KVM_REG_ARM_TIMER_CVAL, uindices))
+		return -EFAULT;
+
+	return 0;
+}
+
+#endif
+
+static int set_timer_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg)
+{
+	void __user *uaddr = (void __user *)(long)reg->addr;
+	u64 val;
+	int ret;
+
+	ret = copy_from_user(&val, uaddr, KVM_REG_SIZE(reg->id));
+	if (ret != 0)
+		return ret;
+
+	return kvm_arm_timer_set_reg(vcpu, reg->id, val);
+}
+
+static int get_timer_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg)
+{
+	void __user *uaddr = (void __user *)(long)reg->addr;
+	u64 val;
+
+	val = kvm_arm_timer_get_reg(vcpu, reg->id);
+	return copy_to_user(uaddr, &val, KVM_REG_SIZE(reg->id));
+}
+
 static unsigned long num_core_regs(void)
 {
 	return sizeof(struct kvm_regs) / sizeof(u32);
@@ -121,7 +198,8 @@ static unsigned long num_core_regs(void)
  */
 unsigned long kvm_arm_num_regs(struct kvm_vcpu *vcpu)
 {
-	return num_core_regs() + kvm_arm_num_coproc_regs(vcpu);
+	return num_core_regs() + kvm_arm_num_coproc_regs(vcpu)
+		+ NUM_TIMER_REGS;
 }
 
 /**
@@ -133,6 +211,7 @@ int kvm_arm_copy_reg_indices(struct kvm_vcpu *vcpu, u64 __user *uindices)
 {
 	unsigned int i;
 	const u64 core_reg = KVM_REG_ARM | KVM_REG_SIZE_U32 | KVM_REG_ARM_CORE;
+	int ret;
 
 	for (i = 0; i < sizeof(struct kvm_regs)/sizeof(u32); i++) {
 		if (put_user(core_reg | i, uindices))
@@ -140,6 +219,11 @@ int kvm_arm_copy_reg_indices(struct kvm_vcpu *vcpu, u64 __user *uindices)
 		uindices++;
 	}
 
+	ret = copy_timer_indices(vcpu, uindices);
+	if (ret)
+		return ret;
+	uindices += NUM_TIMER_REGS;
+
 	return kvm_arm_copy_coproc_indices(vcpu, uindices);
 }
 
@@ -153,6 +237,9 @@ int kvm_arm_get_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg)
 	if ((reg->id & KVM_REG_ARM_COPROC_MASK) == KVM_REG_ARM_CORE)
 		return get_core_reg(vcpu, reg);
 
+	if (is_timer_reg(reg->id))
+		return get_timer_reg(vcpu, reg);
+
 	return kvm_arm_coproc_get_reg(vcpu, reg);
 }
 
@@ -166,6 +253,9 @@ int kvm_arm_set_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg)
 	if ((reg->id & KVM_REG_ARM_COPROC_MASK) == KVM_REG_ARM_CORE)
 		return set_core_reg(vcpu, reg);
 
+	if (is_timer_reg(reg->id))
+		return set_timer_reg(vcpu, reg);
+
 	return kvm_arm_coproc_set_reg(vcpu, reg);
 }
 
diff --git a/arch/arm/kvm/handle_exit.c b/arch/arm/kvm/handle_exit.c
index a92079011a83..0de91fc6de0f 100644
--- a/arch/arm/kvm/handle_exit.c
+++ b/arch/arm/kvm/handle_exit.c
@@ -26,8 +26,6 @@
 
 #include "trace.h"
 
-#include "trace.h"
-
 typedef int (*exit_handle_fn)(struct kvm_vcpu *, struct kvm_run *);
 
 static int handle_svc_hyp(struct kvm_vcpu *vcpu, struct kvm_run *run)
diff --git a/arch/arm/kvm/mmu.c b/arch/arm/kvm/mmu.c
index 580906989db1..7789857d1470 100644
--- a/arch/arm/kvm/mmu.c
+++ b/arch/arm/kvm/mmu.c
@@ -667,14 +667,16 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 		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.
+		 * Pages belonging to memslots that don't have the same
+		 * alignment for userspace and IPA 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)
+		if ((memslot->userspace_addr & ~PMD_MASK) !=
+		    ((memslot->base_gfn << PAGE_SHIFT) & ~PMD_MASK))
 			force_pte = true;
 	}
 	up_read(&current->mm->mmap_sem);
@@ -916,9 +918,9 @@ int kvm_mmu_init(void)
 {
 	int err;
 
-	hyp_idmap_start = virt_to_phys(__hyp_idmap_text_start);
-	hyp_idmap_end = virt_to_phys(__hyp_idmap_text_end);
-	hyp_idmap_vector = virt_to_phys(__kvm_hyp_init);
+	hyp_idmap_start = kvm_virt_to_phys(__hyp_idmap_text_start);
+	hyp_idmap_end = kvm_virt_to_phys(__hyp_idmap_text_end);
+	hyp_idmap_vector = kvm_virt_to_phys(__kvm_hyp_init);
 
 	if ((hyp_idmap_start ^ hyp_idmap_end) & PAGE_MASK) {
 		/*
@@ -945,7 +947,7 @@ int kvm_mmu_init(void)
 		 */
 		kvm_flush_dcache_to_poc(init_bounce_page, len);
 
-		phys_base = virt_to_phys(init_bounce_page);
+		phys_base = kvm_virt_to_phys(init_bounce_page);
 		hyp_idmap_vector += phys_base - hyp_idmap_start;
 		hyp_idmap_start = phys_base;
 		hyp_idmap_end = phys_base + len;
diff --git a/arch/arm/kvm/psci.c b/arch/arm/kvm/psci.c
index 0881bf169fbc..448f60e8d23c 100644
--- a/arch/arm/kvm/psci.c
+++ b/arch/arm/kvm/psci.c
@@ -54,15 +54,15 @@ static unsigned long kvm_psci_vcpu_on(struct kvm_vcpu *source_vcpu)
 		}
 	}
 
-	if (!vcpu)
+	/*
+	 * Make sure the caller requested a valid CPU and that the CPU is
+	 * turned off.
+	 */
+	if (!vcpu || !vcpu->arch.pause)
 		return KVM_PSCI_RET_INVAL;
 
 	target_pc = *vcpu_reg(source_vcpu, 2);
 
-	wq = kvm_arch_vcpu_wq(vcpu);
-	if (!waitqueue_active(wq))
-		return KVM_PSCI_RET_INVAL;
-
 	kvm_reset_vcpu(vcpu);
 
 	/* Gracefully handle Thumb2 entry point */
@@ -79,6 +79,7 @@ static unsigned long kvm_psci_vcpu_on(struct kvm_vcpu *source_vcpu)
 	vcpu->arch.pause = false;
 	smp_mb();		/* Make sure the above is visible */
 
+	wq = kvm_arch_vcpu_wq(vcpu);
 	wake_up_interruptible(wq);
 
 	return KVM_PSCI_RET_SUCCESS;