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

Pull KVM updates from Paolo Bonzini:
 "First batch of KVM changes for 4.1

  The most interesting bit here is irqfd/ioeventfd support for ARM and
  ARM64.

  Summary:

  ARM/ARM64:
     fixes for live migration, irqfd and ioeventfd support (enabling
     vhost, too), page aging

  s390:
     interrupt handling rework, allowing to inject all local interrupts
     via new ioctl and to get/set the full local irq state for migration
     and introspection.  New ioctls to access memory by virtual address,
     and to get/set the guest storage keys.  SIMD support.

  MIPS:
     FPU and MIPS SIMD Architecture (MSA) support.  Includes some
     patches from Ralf Baechle's MIPS tree.

  x86:
     bugfixes (notably for pvclock, the others are small) and cleanups.
     Another small latency improvement for the TSC deadline timer"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (146 commits)
  KVM: use slowpath for cross page cached accesses
  kvm: mmu: lazy collapse small sptes into large sptes
  KVM: x86: Clear CR2 on VCPU reset
  KVM: x86: DR0-DR3 are not clear on reset
  KVM: x86: BSP in MSR_IA32_APICBASE is writable
  KVM: x86: simplify kvm_apic_map
  KVM: x86: avoid logical_map when it is invalid
  KVM: x86: fix mixed APIC mode broadcast
  KVM: x86: use MDA for interrupt matching
  kvm/ppc/mpic: drop unused IRQ_testbit
  KVM: nVMX: remove unnecessary double caching of MAXPHYADDR
  KVM: nVMX: checks for address bits beyond MAXPHYADDR on VM-entry
  KVM: x86: cache maxphyaddr CPUID leaf in struct kvm_vcpu
  KVM: vmx: pass error code with internal error #2
  x86: vdso: fix pvclock races with task migration
  KVM: remove kvm_read_hva and kvm_read_hva_atomic
  KVM: x86: optimize delivery of TSC deadline timer interrupt
  KVM: x86: extract blocking logic from __vcpu_run
  kvm: x86: fix x86 eflags fixed bit
  KVM: s390: migrate vcpu interrupt state
  ...

Documentation/virtual/kvm/devices/s390_flic.txt

@@ -27,6 +27,9 @@ Groups:
     Copies all floating interrupts into a buffer provided by userspace.
     When the buffer is too small it returns -ENOMEM, which is the indication
     for userspace to try again with a bigger buffer.
+    -ENOBUFS is returned when the allocation of a kernelspace buffer has
+    failed.
+    -EFAULT is returned when copying data to userspace failed.
     All interrupts remain pending, i.e. are not deleted from the list of
     currently pending interrupts.
     attr->addr contains the userspace address of the buffer into which all

MAINTAINERS

@@ -5591,6 +5591,8 @@ S:	Supported
 F:	Documentation/*/kvm*.txt
 F:	Documentation/virtual/kvm/
 F:	arch/*/kvm/
+F:	arch/x86/kernel/kvm.c
+F:	arch/x86/kernel/kvmclock.c
 F:	arch/*/include/asm/kvm*
 F:	include/linux/kvm*
 F:	include/uapi/linux/kvm*

arch/arm/include/asm/kvm_arm.h

@@ -185,6 +185,7 @@
 #define HSR_COND	(0xfU << HSR_COND_SHIFT)
 
 #define FSC_FAULT	(0x04)
+#define FSC_ACCESS	(0x08)
 #define FSC_PERM	(0x0c)
 
 /* Hyp Prefetch Fault Address Register (HPFAR/HDFAR) */

arch/arm/include/asm/kvm_host.h

@@ -27,6 +27,8 @@
 #include <asm/fpstate.h>
 #include <kvm/arm_arch_timer.h>
 
+#define __KVM_HAVE_ARCH_INTC_INITIALIZED
+
 #if defined(CONFIG_KVM_ARM_MAX_VCPUS)
 #define KVM_MAX_VCPUS CONFIG_KVM_ARM_MAX_VCPUS
 #else
@@ -165,19 +167,10 @@ void kvm_set_spte_hva(struct kvm *kvm, unsigned long hva, pte_t pte);
 
 unsigned long kvm_arm_num_regs(struct kvm_vcpu *vcpu);
 int kvm_arm_copy_reg_indices(struct kvm_vcpu *vcpu, u64 __user *indices);
+int kvm_age_hva(struct kvm *kvm, unsigned long start, unsigned long end);
+int kvm_test_age_hva(struct kvm *kvm, unsigned long hva);
 
 /* We do not have shadow page tables, hence the empty hooks */
-static inline int kvm_age_hva(struct kvm *kvm, unsigned long start,
-			      unsigned long end)
-{
-	return 0;
-}
-
-static inline int kvm_test_age_hva(struct kvm *kvm, unsigned long hva)
-{
-	return 0;
-}
-
 static inline void kvm_arch_mmu_notifier_invalidate_page(struct kvm *kvm,
 							 unsigned long address)
 {

arch/arm/include/asm/kvm_mmio.h

@@ -28,28 +28,6 @@ struct kvm_decode {
 	bool sign_extend;
 };
 
-/*
- * The in-kernel MMIO emulation code wants to use a copy of run->mmio,
- * which is an anonymous type. Use our own type instead.
- */
-struct kvm_exit_mmio {
-	phys_addr_t	phys_addr;
-	u8		data[8];
-	u32		len;
-	bool		is_write;
-	void		*private;
-};
-
-static inline void kvm_prepare_mmio(struct kvm_run *run,
-				    struct kvm_exit_mmio *mmio)
-{
-	run->mmio.phys_addr	= mmio->phys_addr;
-	run->mmio.len		= mmio->len;
-	run->mmio.is_write	= mmio->is_write;
-	memcpy(run->mmio.data, mmio->data, mmio->len);
-	run->exit_reason	= KVM_EXIT_MMIO;
-}
-
 int kvm_handle_mmio_return(struct kvm_vcpu *vcpu, struct kvm_run *run);
 int io_mem_abort(struct kvm_vcpu *vcpu, struct kvm_run *run,
 		 phys_addr_t fault_ipa);

arch/arm/include/uapi/asm/kvm.h

@@ -198,6 +198,9 @@ struct kvm_arch_memory_slot {
 /* Highest supported SPI, from VGIC_NR_IRQS */
 #define KVM_ARM_IRQ_GIC_MAX		127
 
+/* One single KVM irqchip, ie. the VGIC */
+#define KVM_NR_IRQCHIPS          1
+
 /* PSCI interface */
 #define KVM_PSCI_FN_BASE		0x95c1ba5e
 #define KVM_PSCI_FN(n)			(KVM_PSCI_FN_BASE + (n))

arch/arm/kernel/asm-offsets.c

@@ -190,7 +190,6 @@ int main(void)
   DEFINE(VCPU_HxFAR,		offsetof(struct kvm_vcpu, arch.fault.hxfar));
   DEFINE(VCPU_HPFAR,		offsetof(struct kvm_vcpu, arch.fault.hpfar));
   DEFINE(VCPU_HYP_PC,		offsetof(struct kvm_vcpu, arch.fault.hyp_pc));
-#ifdef CONFIG_KVM_ARM_VGIC
   DEFINE(VCPU_VGIC_CPU,		offsetof(struct kvm_vcpu, arch.vgic_cpu));
   DEFINE(VGIC_V2_CPU_HCR,	offsetof(struct vgic_cpu, vgic_v2.vgic_hcr));
   DEFINE(VGIC_V2_CPU_VMCR,	offsetof(struct vgic_cpu, vgic_v2.vgic_vmcr));
@@ -200,14 +199,11 @@ int main(void)
   DEFINE(VGIC_V2_CPU_APR,	offsetof(struct vgic_cpu, vgic_v2.vgic_apr));
   DEFINE(VGIC_V2_CPU_LR,	offsetof(struct vgic_cpu, vgic_v2.vgic_lr));
   DEFINE(VGIC_CPU_NR_LR,	offsetof(struct vgic_cpu, nr_lr));
-#ifdef CONFIG_KVM_ARM_TIMER
   DEFINE(VCPU_TIMER_CNTV_CTL,	offsetof(struct kvm_vcpu, arch.timer_cpu.cntv_ctl));
   DEFINE(VCPU_TIMER_CNTV_CVAL,	offsetof(struct kvm_vcpu, arch.timer_cpu.cntv_cval));
   DEFINE(KVM_TIMER_CNTVOFF,	offsetof(struct kvm, arch.timer.cntvoff));
   DEFINE(KVM_TIMER_ENABLED,	offsetof(struct kvm, arch.timer.enabled));
-#endif
   DEFINE(KVM_VGIC_VCTRL,	offsetof(struct kvm, arch.vgic.vctrl_base));
-#endif
   DEFINE(KVM_VTTBR,		offsetof(struct kvm, arch.vttbr));
 #endif
   return 0; 

arch/arm/kvm/Kconfig

@@ -18,6 +18,7 @@ if VIRTUALIZATION
 
 config KVM
 	bool "Kernel-based Virtual Machine (KVM) support"
+	depends on MMU && OF
 	select PREEMPT_NOTIFIERS
 	select ANON_INODES
 	select HAVE_KVM_CPU_RELAX_INTERCEPT
@@ -26,21 +27,20 @@ config KVM
 	select KVM_ARM_HOST
 	select KVM_GENERIC_DIRTYLOG_READ_PROTECT
 	select SRCU
-	depends on ARM_VIRT_EXT && ARM_LPAE
+	select MMU_NOTIFIER
+	select HAVE_KVM_EVENTFD
+	select HAVE_KVM_IRQFD
+	depends on ARM_VIRT_EXT && ARM_LPAE && ARM_ARCH_TIMER
 	---help---
-	  Support hosting virtualized guest machines. You will also
-	  need to select one or more of the processor modules below.
+	  Support hosting virtualized guest machines.
 
 	  This module provides access to the hardware capabilities through
 	  a character device node named /dev/kvm.
 
 	  If unsure, say N.
 
 config KVM_ARM_HOST
-	bool "KVM host support for ARM cpus."
-	depends on KVM
-	depends on MMU
-	select	MMU_NOTIFIER
+	bool
 	---help---
 	  Provides host support for ARM processors.
 
@@ -55,20 +55,4 @@ config KVM_ARM_MAX_VCPUS
 	  large, so only choose a reasonable number that you expect to
 	  actually use.
 
-config KVM_ARM_VGIC
-	bool "KVM support for Virtual GIC"
-	depends on KVM_ARM_HOST && OF
-	select HAVE_KVM_IRQCHIP
-	default y
-	---help---
-	  Adds support for a hardware assisted, in-kernel GIC emulation.
-
-config KVM_ARM_TIMER
-	bool "KVM support for Architected Timers"
-	depends on KVM_ARM_VGIC && ARM_ARCH_TIMER
-	select HAVE_KVM_IRQCHIP
-	default y
-	---help---
-	  Adds support for the Architected Timers in virtual machines
-
 endif # VIRTUALIZATION

arch/arm/kvm/Makefile

@@ -7,20 +7,20 @@ ifeq ($(plus_virt),+virt)
 	plus_virt_def := -DREQUIRES_VIRT=1
 endif
 
-ccflags-y += -Ivirt/kvm -Iarch/arm/kvm
+ccflags-y += -Iarch/arm/kvm
 CFLAGS_arm.o := -I. $(plus_virt_def)
 CFLAGS_mmu.o := -I.
 
 AFLAGS_init.o := -Wa,-march=armv7-a$(plus_virt)
 AFLAGS_interrupts.o := -Wa,-march=armv7-a$(plus_virt)
 
 KVM := ../../../virt/kvm
-kvm-arm-y = $(KVM)/kvm_main.o $(KVM)/coalesced_mmio.o
+kvm-arm-y = $(KVM)/kvm_main.o $(KVM)/coalesced_mmio.o $(KVM)/eventfd.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 coproc_a7.o mmio.o psci.o perf.o
-obj-$(CONFIG_KVM_ARM_VGIC) += $(KVM)/arm/vgic.o
-obj-$(CONFIG_KVM_ARM_VGIC) += $(KVM)/arm/vgic-v2.o
-obj-$(CONFIG_KVM_ARM_VGIC) += $(KVM)/arm/vgic-v2-emul.o
-obj-$(CONFIG_KVM_ARM_TIMER) += $(KVM)/arm/arch_timer.o
+obj-y += $(KVM)/arm/vgic.o
+obj-y += $(KVM)/arm/vgic-v2.o
+obj-y += $(KVM)/arm/vgic-v2-emul.o
+obj-y += $(KVM)/arm/arch_timer.o

arch/arm/kvm/arm.c

@@ -61,8 +61,6 @@ static atomic64_t kvm_vmid_gen = ATOMIC64_INIT(1);
 static u8 kvm_next_vmid;
 static DEFINE_SPINLOCK(kvm_vmid_lock);
 
-static bool vgic_present;
-
 static void kvm_arm_set_running_vcpu(struct kvm_vcpu *vcpu)
 {
 	BUG_ON(preemptible());
@@ -173,8 +171,8 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 	int r;
 	switch (ext) {
 	case KVM_CAP_IRQCHIP:
-		r = vgic_present;
-		break;
+	case KVM_CAP_IRQFD:
+	case KVM_CAP_IOEVENTFD:
 	case KVM_CAP_DEVICE_CTRL:
 	case KVM_CAP_USER_MEMORY:
 	case KVM_CAP_SYNC_MMU:
@@ -183,6 +181,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 	case KVM_CAP_ARM_PSCI:
 	case KVM_CAP_ARM_PSCI_0_2:
 	case KVM_CAP_READONLY_MEM:
+	case KVM_CAP_MP_STATE:
 		r = 1;
 		break;
 	case KVM_CAP_COALESCED_MMIO:
@@ -268,7 +267,7 @@ void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu)
 
 int kvm_cpu_has_pending_timer(struct kvm_vcpu *vcpu)
 {
-	return 0;
+	return kvm_timer_should_fire(vcpu);
 }
 
 int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu)
@@ -313,13 +312,29 @@ int kvm_arch_vcpu_ioctl_set_guest_debug(struct kvm_vcpu *vcpu,
 int kvm_arch_vcpu_ioctl_get_mpstate(struct kvm_vcpu *vcpu,
 				    struct kvm_mp_state *mp_state)
 {
-	return -EINVAL;
+	if (vcpu->arch.pause)
+		mp_state->mp_state = KVM_MP_STATE_STOPPED;
+	else
+		mp_state->mp_state = KVM_MP_STATE_RUNNABLE;
+
+	return 0;
 }
 
 int kvm_arch_vcpu_ioctl_set_mpstate(struct kvm_vcpu *vcpu,
 				    struct kvm_mp_state *mp_state)
 {
-	return -EINVAL;
+	switch (mp_state->mp_state) {
+	case KVM_MP_STATE_RUNNABLE:
+		vcpu->arch.pause = false;
+		break;
+	case KVM_MP_STATE_STOPPED:
+		vcpu->arch.pause = true;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	return 0;
 }
 
 /**
@@ -452,6 +467,11 @@ static int kvm_vcpu_first_run_init(struct kvm_vcpu *vcpu)
 	return 0;
 }
 
+bool kvm_arch_intc_initialized(struct kvm *kvm)
+{
+	return vgic_initialized(kvm);
+}
+
 static void vcpu_pause(struct kvm_vcpu *vcpu)
 {
 	wait_queue_head_t *wq = kvm_arch_vcpu_wq(vcpu);
@@ -831,8 +851,6 @@ static int kvm_vm_ioctl_set_device_addr(struct kvm *kvm,
 
 	switch (dev_id) {
 	case KVM_ARM_DEVICE_VGIC_V2:
-		if (!vgic_present)
-			return -ENXIO;
 		return kvm_vgic_addr(kvm, type, &dev_addr->addr, true);
 	default:
 		return -ENODEV;
@@ -847,10 +865,7 @@ long kvm_arch_vm_ioctl(struct file *filp,
 
 	switch (ioctl) {
 	case KVM_CREATE_IRQCHIP: {
-		if (vgic_present)
-			return kvm_vgic_create(kvm, KVM_DEV_TYPE_ARM_VGIC_V2);
-		else
-			return -ENXIO;
+		return kvm_vgic_create(kvm, KVM_DEV_TYPE_ARM_VGIC_V2);
 	}
 	case KVM_ARM_SET_DEVICE_ADDR: {
 		struct kvm_arm_device_addr dev_addr;
@@ -1035,10 +1050,6 @@ static int init_hyp_mode(void)
 	if (err)
 		goto out_free_context;
 
-#ifdef CONFIG_KVM_ARM_VGIC
-		vgic_present = true;
-#endif
-
 	/*
 	 * Init HYP architected timer support
 	 */

arch/arm/kvm/guest.c

@@ -109,22 +109,6 @@ 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;
-}
-
-#else
-
 #define NUM_TIMER_REGS 3
 
 static bool is_timer_reg(u64 index)
@@ -152,8 +136,6 @@ static int copy_timer_indices(struct kvm_vcpu *vcpu, u64 __user *uindices)
 	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;