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

Pull more KVM updates from Paolo Bonzini:
 - ARM bugfix and MSI injection support
 - x86 nested virt tweak and OOPS fix
 - Simplify pvclock code (vdso bits acked by Andy Lutomirski).

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm:
  nvmx: mark ept single context invalidation as supported
  nvmx: remove comment about missing nested vpid support
  KVM: lapic: fix access preemption timer stuff even if kernel_irqchip=off
  KVM: documentation: fix KVM_CAP_X2APIC_API information
  x86: vdso: use __pvclock_read_cycles
  pvclock: introduce seqcount-like API
  arm64: KVM: Set cpsr before spsr on fault injection
  KVM: arm: vgic-irqfd: Workaround changing kvm_set_routing_entry prototype
  KVM: arm/arm64: Enable MSI routing
  KVM: arm/arm64: Enable irqchip routing
  KVM: Move kvm_setup_default/empty_irq_routing declaration in arch specific header
  KVM: irqchip: Convey devid to kvm_set_msi
  KVM: Add devid in kvm_kernel_irq_routing_entry
  KVM: api: Pass the devid in the msi routing entry

13 files changed, 96 insertions, 62 deletions

diff --git a/arch/arm/kvm/Kconfig b/arch/arm/kvm/Kconfig
index 95a000515e43..3e1cd0452d67 100644
--- a/arch/arm/kvm/Kconfig
+++ b/arch/arm/kvm/Kconfig
@@ -32,6 +32,8 @@ config KVM
 	select KVM_VFIO
 	select HAVE_KVM_EVENTFD
 	select HAVE_KVM_IRQFD
+	select HAVE_KVM_IRQCHIP
+	select HAVE_KVM_IRQ_ROUTING
 	depends on ARM_VIRT_EXT && ARM_LPAE && ARM_ARCH_TIMER
 	---help---
 	  Support hosting virtualized guest machines.
diff --git a/arch/arm/kvm/Makefile b/arch/arm/kvm/Makefile
index 5e28df80dca7..10d77a66cad5 100644
--- a/arch/arm/kvm/Makefile
+++ b/arch/arm/kvm/Makefile
@@ -29,4 +29,5 @@ obj-y += $(KVM)/arm/vgic/vgic-v2.o
 obj-y += $(KVM)/arm/vgic/vgic-mmio.o
 obj-y += $(KVM)/arm/vgic/vgic-mmio-v2.o
 obj-y += $(KVM)/arm/vgic/vgic-kvm-device.o
+obj-y += $(KVM)/irqchip.o
 obj-y += $(KVM)/arm/arch_timer.o
diff --git a/arch/arm/kvm/irq.h b/arch/arm/kvm/irq.h
new file mode 100644
index 000000000000..b74099b905fd
--- /dev/null
+++ b/arch/arm/kvm/irq.h
@@ -0,0 +1,19 @@
+/*
+ * irq.h: in kernel interrupt controller related definitions
+ * Copyright (c) 2016 Red Hat, Inc.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This header is included by irqchip.c. However, on ARM, interrupt
+ * controller declarations are located in include/kvm/arm_vgic.h since
+ * they are mostly shared between arm and arm64.
+ */
+
+#ifndef __IRQ_H
+#define __IRQ_H
+
+#include <kvm/arm_vgic.h>
+
+#endif
diff --git a/arch/arm64/kvm/Kconfig b/arch/arm64/kvm/Kconfig
index 9d2eff0b3ad3..9c9edc98d271 100644
--- a/arch/arm64/kvm/Kconfig
+++ b/arch/arm64/kvm/Kconfig
@@ -37,6 +37,8 @@ config KVM
 	select KVM_ARM_VGIC_V3
 	select KVM_ARM_PMU if HW_PERF_EVENTS
 	select HAVE_KVM_MSI
+	select HAVE_KVM_IRQCHIP
+	select HAVE_KVM_IRQ_ROUTING
 	---help---
 	  Support hosting virtualized guest machines.
 	  We don't support KVM with 16K page tables yet, due to the multiple
diff --git a/arch/arm64/kvm/Makefile b/arch/arm64/kvm/Makefile
index a5b96642a9cb..695eb3c7ef41 100644
--- a/arch/arm64/kvm/Makefile
+++ b/arch/arm64/kvm/Makefile
@@ -30,5 +30,6 @@ kvm-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/vgic/vgic-mmio-v2.o
 kvm-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/vgic/vgic-mmio-v3.o
 kvm-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/vgic/vgic-kvm-device.o
 kvm-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/vgic/vgic-its.o
+kvm-$(CONFIG_KVM_ARM_HOST) += $(KVM)/irqchip.o
 kvm-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/arch_timer.o
 kvm-$(CONFIG_KVM_ARM_PMU) += $(KVM)/arm/pmu.o
diff --git a/arch/arm64/kvm/inject_fault.c b/arch/arm64/kvm/inject_fault.c
index e9e0e6db73f6..898c0e6aedd4 100644
--- a/arch/arm64/kvm/inject_fault.c
+++ b/arch/arm64/kvm/inject_fault.c
@@ -132,16 +132,14 @@ static u64 get_except_vector(struct kvm_vcpu *vcpu, enum exception_type type)
 static void inject_abt64(struct kvm_vcpu *vcpu, bool is_iabt, unsigned long addr)
 {
 	unsigned long cpsr = *vcpu_cpsr(vcpu);
-	bool is_aarch32;
+	bool is_aarch32 = vcpu_mode_is_32bit(vcpu);
 	u32 esr = 0;
 
-	is_aarch32 = vcpu_mode_is_32bit(vcpu);
-
-	*vcpu_spsr(vcpu) = cpsr;
 	*vcpu_elr_el1(vcpu) = *vcpu_pc(vcpu);
-
 	*vcpu_pc(vcpu) = get_except_vector(vcpu, except_type_sync);
+
 	*vcpu_cpsr(vcpu) = PSTATE_FAULT_BITS_64;
+	*vcpu_spsr(vcpu) = cpsr;
 
 	vcpu_sys_reg(vcpu, FAR_EL1) = addr;
 
@@ -172,11 +170,11 @@ static void inject_undef64(struct kvm_vcpu *vcpu)
 	unsigned long cpsr = *vcpu_cpsr(vcpu);
 	u32 esr = (ESR_ELx_EC_UNKNOWN << ESR_ELx_EC_SHIFT);
 
-	*vcpu_spsr(vcpu) = cpsr;
 	*vcpu_elr_el1(vcpu) = *vcpu_pc(vcpu);
-
 	*vcpu_pc(vcpu) = get_except_vector(vcpu, except_type_sync);
+
 	*vcpu_cpsr(vcpu) = PSTATE_FAULT_BITS_64;
+	*vcpu_spsr(vcpu) = cpsr;
 
 	/*
 	 * Build an unknown exception, depending on the instruction
diff --git a/arch/arm64/kvm/irq.h b/arch/arm64/kvm/irq.h
new file mode 100644
index 000000000000..b74099b905fd
--- /dev/null
+++ b/arch/arm64/kvm/irq.h
@@ -0,0 +1,19 @@
+/*
+ * irq.h: in kernel interrupt controller related definitions
+ * Copyright (c) 2016 Red Hat, Inc.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This header is included by irqchip.c. However, on ARM, interrupt
+ * controller declarations are located in include/kvm/arm_vgic.h since
+ * they are mostly shared between arm and arm64.
+ */
+
+#ifndef __IRQ_H
+#define __IRQ_H
+
+#include <kvm/arm_vgic.h>
+
+#endif
diff --git a/arch/x86/entry/vdso/vclock_gettime.c b/arch/x86/entry/vdso/vclock_gettime.c
index 2f02d23a05ef..94d54d0defa7 100644
--- a/arch/x86/entry/vdso/vclock_gettime.c
+++ b/arch/x86/entry/vdso/vclock_gettime.c
@@ -96,9 +96,8 @@ static notrace cycle_t vread_pvclock(int *mode)
 {
 	const struct pvclock_vcpu_time_info *pvti = &get_pvti0()->pvti;
 	cycle_t ret;
-	u64 tsc, pvti_tsc;
-	u64 last, delta, pvti_system_time;
-	u32 version, pvti_tsc_to_system_mul, pvti_tsc_shift;
+	u64 last;
+	u32 version;
 
 	/*
 	 * Note: The kernel and hypervisor must guarantee that cpu ID
@@ -123,29 +122,15 @@ static notrace cycle_t vread_pvclock(int *mode)
 	 */
 
 	do {
-		version = pvti->version;
-
-		smp_rmb();
+		version = pvclock_read_begin(pvti);
 
 		if (unlikely(!(pvti->flags & PVCLOCK_TSC_STABLE_BIT))) {
 			*mode = VCLOCK_NONE;
 			return 0;
 		}
 
-		tsc = rdtsc_ordered();
-		pvti_tsc_to_system_mul = pvti->tsc_to_system_mul;
-		pvti_tsc_shift = pvti->tsc_shift;
-		pvti_system_time = pvti->system_time;
-		pvti_tsc = pvti->tsc_timestamp;
-
-		/* Make sure that the version double-check is last. */
-		smp_rmb();
-	} while (unlikely((version & 1) || version != pvti->version));
-
-	delta = tsc - pvti_tsc;
-	ret = pvti_system_time +
-		pvclock_scale_delta(delta, pvti_tsc_to_system_mul,
-				    pvti_tsc_shift);
+		ret = __pvclock_read_cycles(pvti);
+	} while (pvclock_read_retry(pvti, version));
 
 	/* refer to vread_tsc() comment for rationale */
 	last = gtod->cycle_last;
diff --git a/arch/x86/include/asm/pvclock.h b/arch/x86/include/asm/pvclock.h
index 7c1c89598688..d019f0cc80ec 100644
--- a/arch/x86/include/asm/pvclock.h
+++ b/arch/x86/include/asm/pvclock.h
@@ -25,6 +25,24 @@ void pvclock_resume(void);
 
 void pvclock_touch_watchdogs(void);
 
+static __always_inline
+unsigned pvclock_read_begin(const struct pvclock_vcpu_time_info *src)
+{
+	unsigned version = src->version & ~1;
+	/* Make sure that the version is read before the data. */
+	virt_rmb();
+	return version;
+}
+
+static __always_inline
+bool pvclock_read_retry(const struct pvclock_vcpu_time_info *src,
+			unsigned version)
+{
+	/* Make sure that the version is re-read after the data. */
+	virt_rmb();
+	return unlikely(version != src->version);
+}
+
 /*
  * Scale a 64-bit delta by scaling and multiplying by a 32-bit fraction,
  * yielding a 64-bit result.
@@ -69,23 +87,12 @@ static inline u64 pvclock_scale_delta(u64 delta, u32 mul_frac, int shift)
 }
 
 static __always_inline
-unsigned __pvclock_read_cycles(const struct pvclock_vcpu_time_info *src,
-			       cycle_t *cycles, u8 *flags)
+cycle_t __pvclock_read_cycles(const struct pvclock_vcpu_time_info *src)
 {
-	unsigned version;
-	cycle_t offset;
-	u64 delta;
-
-	version = src->version;
-	/* Make the latest version visible */
-	smp_rmb();
-
-	delta = rdtsc_ordered() - src->tsc_timestamp;
-	offset = pvclock_scale_delta(delta, src->tsc_to_system_mul,
-				   src->tsc_shift);
-	*cycles = src->system_time + offset;
-	*flags = src->flags;
-	return version;
+	u64 delta = rdtsc_ordered() - src->tsc_timestamp;
+	cycle_t offset = pvclock_scale_delta(delta, src->tsc_to_system_mul,
+					     src->tsc_shift);
+	return src->system_time + offset;
 }
 
 struct pvclock_vsyscall_time_info {
diff --git a/arch/x86/kernel/pvclock.c b/arch/x86/kernel/pvclock.c
index 06c58ce46762..3599404e3089 100644
--- a/arch/x86/kernel/pvclock.c
+++ b/arch/x86/kernel/pvclock.c
@@ -64,14 +64,9 @@ u8 pvclock_read_flags(struct pvclock_vcpu_time_info *src)
 	u8 flags;
 
 	do {
-		version = src->version;
-		/* Make the latest version visible */
-		smp_rmb();
-
+		version = pvclock_read_begin(src);
 		flags = src->flags;
-		/* Make sure that the version double-check is last. */
-		smp_rmb();
-	} while ((src->version & 1) || version != src->version);
+	} while (pvclock_read_retry(src, version));
 
 	return flags & valid_flags;
 }
@@ -84,10 +79,10 @@ cycle_t pvclock_clocksource_read(struct pvclock_vcpu_time_info *src)
 	u8 flags;
 
 	do {
-		version = __pvclock_read_cycles(src, &ret, &flags);
-		/* Make sure that the version double-check is last. */
-		smp_rmb();
-	} while ((src->version & 1) || version != src->version);
+		version = pvclock_read_begin(src);
+		ret = __pvclock_read_cycles(src);
+		flags = src->flags;
+	} while (pvclock_read_retry(src, version));
 
 	if (unlikely((flags & PVCLOCK_GUEST_STOPPED) != 0)) {
 		src->flags &= ~PVCLOCK_GUEST_STOPPED;
diff --git a/arch/x86/kvm/irq.h b/arch/x86/kvm/irq.h
index 61ebdc13a29a..035731eb3897 100644
--- a/arch/x86/kvm/irq.h
+++ b/arch/x86/kvm/irq.h
@@ -120,4 +120,7 @@ void __kvm_migrate_timers(struct kvm_vcpu *vcpu);
 
 int apic_has_pending_timer(struct kvm_vcpu *vcpu);
 
+int kvm_setup_default_irq_routing(struct kvm *kvm);
+int kvm_setup_empty_irq_routing(struct kvm *kvm);
+
 #endif
diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index 730cf174090a..b62c85229711 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -1349,6 +1349,9 @@ static void start_sw_tscdeadline(struct kvm_lapic *apic)
 
 bool kvm_lapic_hv_timer_in_use(struct kvm_vcpu *vcpu)
 {
+	if (!lapic_in_kernel(vcpu))
+		return false;
+
 	return vcpu->arch.apic->lapic_timer.hv_timer_in_use;
 }
 EXPORT_SYMBOL_GPL(kvm_lapic_hv_timer_in_use);
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index bc354f003ce1..a45d8580f91e 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -2809,12 +2809,8 @@ static void nested_vmx_setup_ctls_msrs(struct vcpu_vmx *vmx)
 			vmx->nested.nested_vmx_ept_caps |=
 				VMX_EPT_EXECUTE_ONLY_BIT;
 		vmx->nested.nested_vmx_ept_caps &= vmx_capability.ept;
-		/*
-		 * For nested guests, we don't do anything specific
-		 * for single context invalidation. Hence, only advertise
-		 * support for global context invalidation.
-		 */
-		vmx->nested.nested_vmx_ept_caps |= VMX_EPT_EXTENT_GLOBAL_BIT;
+		vmx->nested.nested_vmx_ept_caps |= VMX_EPT_EXTENT_GLOBAL_BIT |
+			VMX_EPT_EXTENT_CONTEXT_BIT;
 	} else
 		vmx->nested.nested_vmx_ept_caps = 0;
 
@@ -2945,7 +2941,6 @@ static int vmx_get_vmx_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 *pdata)
 			vmx->nested.nested_vmx_secondary_ctls_high);
 		break;
 	case MSR_IA32_VMX_EPT_VPID_CAP:
-		/* Currently, no nested vpid support */
 		*pdata = vmx->nested.nested_vmx_ept_caps |
 			((u64)vmx->nested.nested_vmx_vpid_caps << 32);
 		break;
@@ -7609,12 +7604,16 @@ static int handle_invept(struct kvm_vcpu *vcpu)
 
 	switch (type) {
 	case VMX_EPT_EXTENT_GLOBAL:
+	/*
+	 * TODO: track mappings and invalidate
+	 * single context requests appropriately
+	 */
+	case VMX_EPT_EXTENT_CONTEXT:
 		kvm_mmu_sync_roots(vcpu);
 		kvm_make_request(KVM_REQ_TLB_FLUSH, vcpu);
 		nested_vmx_succeed(vcpu);
 		break;
 	default:
-		/* Trap single context invalidation invept calls */
 		BUG_ON(1);
 		break;
 	}