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

Documentation/virtual/kvm/api.txt

@@ -1433,13 +1433,16 @@ KVM_ASSIGN_DEV_IRQ. Partial deassignment of host or guest IRQ is allowed.
 4.52 KVM_SET_GSI_ROUTING
 
 Capability: KVM_CAP_IRQ_ROUTING
-Architectures: x86 s390
+Architectures: x86 s390 arm arm64
 Type: vm ioctl
 Parameters: struct kvm_irq_routing (in)
 Returns: 0 on success, -1 on error
 
 Sets the GSI routing table entries, overwriting any previously set entries.
 
+On arm/arm64, GSI routing has the following limitation:
+- GSI routing does not apply to KVM_IRQ_LINE but only to KVM_IRQFD.
+
 struct kvm_irq_routing {
 	__u32 nr;
 	__u32 flags;
@@ -1468,7 +1471,13 @@ struct kvm_irq_routing_entry {
 #define KVM_IRQ_ROUTING_S390_ADAPTER 3
 #define KVM_IRQ_ROUTING_HV_SINT 4
 
-No flags are specified so far, the corresponding field must be set to zero.
+flags:
+- KVM_MSI_VALID_DEVID: used along with KVM_IRQ_ROUTING_MSI routing entry
+  type, specifies that the devid field contains a valid value.  The per-VM
+  KVM_CAP_MSI_DEVID capability advertises the requirement to provide
+  the device ID.  If this capability is not available, userspace should
+  never set the KVM_MSI_VALID_DEVID flag as the ioctl might fail.
+- zero otherwise
 
 struct kvm_irq_routing_irqchip {
 	__u32 irqchip;
@@ -1479,9 +1488,16 @@ struct kvm_irq_routing_msi {
 	__u32 address_lo;
 	__u32 address_hi;
 	__u32 data;
-	__u32 pad;
+	union {
+		__u32 pad;
+		__u32 devid;
+	};
 };
 
+If KVM_MSI_VALID_DEVID is set, devid contains a unique device identifier
+for the device that wrote the MSI message.  For PCI, this is usually a
+BFD identifier in the lower 16 bits.
+
 On x86, address_hi is ignored unless the KVM_X2APIC_API_USE_32BIT_IDS
 feature of KVM_CAP_X2APIC_API capability is enabled.  If it is enabled,
 address_hi bits 31-8 provide bits 31-8 of the destination id.  Bits 7-0 of
@@ -2199,18 +2215,19 @@ struct kvm_msi {
 	__u8  pad[12];
 };
 
-flags: KVM_MSI_VALID_DEVID: devid contains a valid value
-devid: If KVM_MSI_VALID_DEVID is set, contains a unique device identifier
-       for the device that wrote the MSI message.
-       For PCI, this is usually a BFD identifier in the lower 16 bits.
+flags: KVM_MSI_VALID_DEVID: devid contains a valid value.  The per-VM
+  KVM_CAP_MSI_DEVID capability advertises the requirement to provide
+  the device ID.  If this capability is not available, userspace
+  should never set the KVM_MSI_VALID_DEVID flag as the ioctl might fail.
 
-The per-VM KVM_CAP_MSI_DEVID capability advertises the need to provide
-the device ID. If this capability is not set, userland cannot rely on
-the kernel to allow the KVM_MSI_VALID_DEVID flag being set.
+If KVM_MSI_VALID_DEVID is set, devid contains a unique device identifier
+for the device that wrote the MSI message.  For PCI, this is usually a
+BFD identifier in the lower 16 bits.
 
-On x86, address_hi is ignored unless the KVM_CAP_X2APIC_API capability is
-enabled.  If it is enabled, address_hi bits 31-8 provide bits 31-8 of the
-destination id.  Bits 7-0 of address_hi must be zero.
+On x86, address_hi is ignored unless the KVM_X2APIC_API_USE_32BIT_IDS
+feature of KVM_CAP_X2APIC_API capability is enabled.  If it is enabled,
+address_hi bits 31-8 provide bits 31-8 of the destination id.  Bits 7-0 of
+address_hi must be zero.
 
 
 4.71 KVM_CREATE_PIT2
@@ -2383,9 +2400,13 @@ Note that closing the resamplefd is not sufficient to disable the
 irqfd.  The KVM_IRQFD_FLAG_RESAMPLE is only necessary on assignment
 and need not be specified with KVM_IRQFD_FLAG_DEASSIGN.
 
-On ARM/ARM64, the gsi field in the kvm_irqfd struct specifies the Shared
-Peripheral Interrupt (SPI) index, such that the GIC interrupt ID is
-given by gsi + 32.
+On arm/arm64, gsi routing being supported, the following can happen:
+- in case no routing entry is associated to this gsi, injection fails
+- in case the gsi is associated to an irqchip routing entry,
+  irqchip.pin + 32 corresponds to the injected SPI ID.
+- in case the gsi is associated to an MSI routing entry, the MSI
+  message and device ID are translated into an LPI (support restricted
+  to GICv3 ITS in-kernel emulation).
 
 4.76 KVM_PPC_ALLOCATE_HTAB
 

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.

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

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

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

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

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

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

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;

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 {

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;

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

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);

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;
 	}