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

Pull second batch of KVM updates from Radim Krčmář:
 "General:

   - move kvm_stat tool from QEMU repo into tools/kvm/kvm_stat (kvm_stat
     had nothing to do with QEMU in the first place -- the tool only
     interprets debugfs)

   - expose per-vm statistics in debugfs and support them in kvm_stat
     (KVM always collected per-vm statistics, but they were summarised
     into global statistics)

  x86:

   - fix dynamic APICv (VMX was improperly configured and a guest could
     access host's APIC MSRs, CVE-2016-4440)

   - minor fixes

  ARM changes from Christoffer Dall:

   - new vgic reimplementation of our horribly broken legacy vgic
     implementation.  The two implementations will live side-by-side
     (with the new being the configured default) for one kernel release
     and then we'll remove the legacy one.

   - fix for a non-critical issue with virtual abort injection to guests"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (70 commits)
  tools: kvm_stat: Add comments
  tools: kvm_stat: Introduce pid monitoring
  KVM: Create debugfs dir and stat files for each VM
  MAINTAINERS: Add kvm tools
  tools: kvm_stat: Powerpc related fixes
  tools: Add kvm_stat man page
  tools: Add kvm_stat vm monitor script
  kvm:vmx: more complete state update on APICv on/off
  KVM: SVM: Add more SVM_EXIT_REASONS
  KVM: Unify traced vector format
  svm: bitwise vs logical op typo
  KVM: arm/arm64: vgic-new: Synchronize changes to active state
  KVM: arm/arm64: vgic-new: enable build
  KVM: arm/arm64: vgic-new: implement mapped IRQ handling
  KVM: arm/arm64: vgic-new: Wire up irqfd injection
  KVM: arm/arm64: vgic-new: Add vgic_v2/v3_enable
  KVM: arm/arm64: vgic-new: vgic_init: implement map_resources
  KVM: arm/arm64: vgic-new: vgic_init: implement vgic_init
  KVM: arm/arm64: vgic-new: vgic_init: implement vgic_create
  KVM: arm/arm64: vgic-new: vgic_init: implement kvm_vgic_hyp_init
  ...

MAINTAINERS

@@ -6491,6 +6491,7 @@ F:	arch/*/include/asm/kvm*
 F:	include/linux/kvm*
 F:	include/uapi/linux/kvm*
 F:	virt/kvm/
+F:	tools/kvm/
 
 KERNEL VIRTUAL MACHINE (KVM) FOR AMD-V
 M:	Joerg Roedel <[email protected]>

arch/arm/include/asm/kvm_host.h

@@ -41,6 +41,8 @@
 
 #define KVM_MAX_VCPUS VGIC_V2_MAX_CPUS
 
+#define KVM_REQ_VCPU_EXIT	8
+
 u32 *kvm_vcpu_reg(struct kvm_vcpu *vcpu, u8 reg_num, u32 mode);
 int __attribute_const__ kvm_target_cpu(void);
 int kvm_reset_vcpu(struct kvm_vcpu *vcpu);
@@ -226,6 +228,10 @@ static inline void kvm_arch_mmu_notifier_invalidate_page(struct kvm *kvm,
 
 struct kvm_vcpu *kvm_arm_get_running_vcpu(void);
 struct kvm_vcpu __percpu **kvm_get_running_vcpus(void);
+void kvm_arm_halt_guest(struct kvm *kvm);
+void kvm_arm_resume_guest(struct kvm *kvm);
+void kvm_arm_halt_vcpu(struct kvm_vcpu *vcpu);
+void kvm_arm_resume_vcpu(struct kvm_vcpu *vcpu);
 
 int kvm_arm_copy_coproc_indices(struct kvm_vcpu *vcpu, u64 __user *uindices);
 unsigned long kvm_arm_num_coproc_regs(struct kvm_vcpu *vcpu);

arch/arm/include/asm/kvm_mmio.h

@@ -28,6 +28,9 @@ struct kvm_decode {
 	bool sign_extend;
 };
 
+void kvm_mmio_write_buf(void *buf, unsigned int len, unsigned long data);
+unsigned long kvm_mmio_read_buf(const void *buf, unsigned int len);
+
 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/kvm/Kconfig

@@ -46,6 +46,13 @@ config KVM_ARM_HOST
 	---help---
 	  Provides host support for ARM processors.
 
+config KVM_NEW_VGIC
+	bool "New VGIC implementation"
+	depends on KVM
+	default y
+	---help---
+	  uses the new VGIC implementation
+
 source drivers/vhost/Kconfig
 
 endif # VIRTUALIZATION

arch/arm/kvm/Makefile

@@ -21,7 +21,18 @@ obj-$(CONFIG_KVM_ARM_HOST) += hyp/
 obj-y += kvm-arm.o init.o interrupts.o
 obj-y += arm.o handle_exit.o guest.o mmu.o emulate.o reset.o
 obj-y += coproc.o coproc_a15.o coproc_a7.o mmio.o psci.o perf.o
+
+ifeq ($(CONFIG_KVM_NEW_VGIC),y)
+obj-y += $(KVM)/arm/vgic/vgic.o
+obj-y += $(KVM)/arm/vgic/vgic-init.o
+obj-y += $(KVM)/arm/vgic/vgic-irqfd.o
+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
+else
 obj-y += $(KVM)/arm/vgic.o
 obj-y += $(KVM)/arm/vgic-v2.o
 obj-y += $(KVM)/arm/vgic-v2-emul.o
+endif
 obj-y += $(KVM)/arm/arch_timer.o

arch/arm/kvm/arm.c

@@ -455,7 +455,7 @@ static void update_vttbr(struct kvm *kvm)
 static int kvm_vcpu_first_run_init(struct kvm_vcpu *vcpu)
 {
 	struct kvm *kvm = vcpu->kvm;
-	int ret;
+	int ret = 0;
 
 	if (likely(vcpu->arch.has_run_once))
 		return 0;
@@ -478,40 +478,47 @@ static int kvm_vcpu_first_run_init(struct kvm_vcpu *vcpu)
 	 * interrupts from the virtual timer with a userspace gic.
 	 */
 	if (irqchip_in_kernel(kvm) && vgic_initialized(kvm))
-		kvm_timer_enable(kvm);
+		ret = kvm_timer_enable(vcpu);
 
-	return 0;
+	return ret;
 }
 
 bool kvm_arch_intc_initialized(struct kvm *kvm)
 {
 	return vgic_initialized(kvm);
 }
 
-static void kvm_arm_halt_guest(struct kvm *kvm) __maybe_unused;
-static void kvm_arm_resume_guest(struct kvm *kvm) __maybe_unused;
-
-static void kvm_arm_halt_guest(struct kvm *kvm)
+void kvm_arm_halt_guest(struct kvm *kvm)
 {
 	int i;
 	struct kvm_vcpu *vcpu;
 
 	kvm_for_each_vcpu(i, vcpu, kvm)
 		vcpu->arch.pause = true;
-	force_vm_exit(cpu_all_mask);
+	kvm_make_all_cpus_request(kvm, KVM_REQ_VCPU_EXIT);
+}
+
+void kvm_arm_halt_vcpu(struct kvm_vcpu *vcpu)
+{
+	vcpu->arch.pause = true;
+	kvm_vcpu_kick(vcpu);
 }
 
-static void kvm_arm_resume_guest(struct kvm *kvm)
+void kvm_arm_resume_vcpu(struct kvm_vcpu *vcpu)
+{
+	struct swait_queue_head *wq = kvm_arch_vcpu_wq(vcpu);
+
+	vcpu->arch.pause = false;
+	swake_up(wq);
+}
+
+void kvm_arm_resume_guest(struct kvm *kvm)
 {
 	int i;
 	struct kvm_vcpu *vcpu;
 
-	kvm_for_each_vcpu(i, vcpu, kvm) {
-		struct swait_queue_head *wq = kvm_arch_vcpu_wq(vcpu);
-
-		vcpu->arch.pause = false;
-		swake_up(wq);
-	}
+	kvm_for_each_vcpu(i, vcpu, kvm)
+		kvm_arm_resume_vcpu(vcpu);
 }
 
 static void vcpu_sleep(struct kvm_vcpu *vcpu)

arch/arm/kvm/mmio.c

@@ -23,7 +23,7 @@
 
 #include "trace.h"
 
-static void mmio_write_buf(char *buf, unsigned int len, unsigned long data)
+void kvm_mmio_write_buf(void *buf, unsigned int len, unsigned long data)
 {
 	void *datap = NULL;
 	union {
@@ -55,7 +55,7 @@ static void mmio_write_buf(char *buf, unsigned int len, unsigned long data)
 	memcpy(buf, datap, len);
 }
 
-static unsigned long mmio_read_buf(char *buf, unsigned int len)
+unsigned long kvm_mmio_read_buf(const void *buf, unsigned int len)
 {
 	unsigned long data = 0;
 	union {
@@ -66,7 +66,7 @@ static unsigned long mmio_read_buf(char *buf, unsigned int len)
 
 	switch (len) {
 	case 1:
-		data = buf[0];
+		data = *(u8 *)buf;
 		break;
 	case 2:
 		memcpy(&tmp.hword, buf, len);
@@ -87,11 +87,10 @@ static unsigned long mmio_read_buf(char *buf, unsigned int len)
 
 /**
  * kvm_handle_mmio_return -- Handle MMIO loads after user space emulation
+ *			     or in-kernel IO emulation
+ *
  * @vcpu: The VCPU pointer
  * @run:  The VCPU run struct containing the mmio data
- *
- * This should only be called after returning from userspace for MMIO load
- * emulation.
  */
 int kvm_handle_mmio_return(struct kvm_vcpu *vcpu, struct kvm_run *run)
 {
@@ -104,7 +103,7 @@ int kvm_handle_mmio_return(struct kvm_vcpu *vcpu, struct kvm_run *run)
 		if (len > sizeof(unsigned long))
 			return -EINVAL;
 
-		data = mmio_read_buf(run->mmio.data, len);
+		data = kvm_mmio_read_buf(run->mmio.data, len);
 
 		if (vcpu->arch.mmio_decode.sign_extend &&
 		    len < sizeof(unsigned long)) {
@@ -190,7 +189,7 @@ int io_mem_abort(struct kvm_vcpu *vcpu, struct kvm_run *run,
 					       len);
 
 		trace_kvm_mmio(KVM_TRACE_MMIO_WRITE, len, fault_ipa, data);
-		mmio_write_buf(data_buf, len, data);
+		kvm_mmio_write_buf(data_buf, len, data);
 
 		ret = kvm_io_bus_write(vcpu, KVM_MMIO_BUS, fault_ipa, len,
 				       data_buf);
@@ -206,18 +205,19 @@ int io_mem_abort(struct kvm_vcpu *vcpu, struct kvm_run *run,
 	run->mmio.is_write	= is_write;
 	run->mmio.phys_addr	= fault_ipa;
 	run->mmio.len		= len;
-	if (is_write)
-		memcpy(run->mmio.data, data_buf, len);
 
 	if (!ret) {
 		/* We handled the access successfully in the kernel. */
+		if (!is_write)
+			memcpy(run->mmio.data, data_buf, len);
 		vcpu->stat.mmio_exit_kernel++;
 		kvm_handle_mmio_return(vcpu, run);
 		return 1;
-	} else {
-		vcpu->stat.mmio_exit_user++;
 	}
 
+	if (is_write)
+		memcpy(run->mmio.data, data_buf, len);
+	vcpu->stat.mmio_exit_user++;
 	run->exit_reason	= KVM_EXIT_MMIO;
 	return 0;
 }

arch/arm64/include/asm/kvm_host.h

@@ -43,6 +43,8 @@
 
 #define KVM_VCPU_MAX_FEATURES 4
 
+#define KVM_REQ_VCPU_EXIT	8
+
 int __attribute_const__ kvm_target_cpu(void);
 int kvm_reset_vcpu(struct kvm_vcpu *vcpu);
 int kvm_arch_dev_ioctl_check_extension(long ext);
@@ -327,6 +329,10 @@ static inline void kvm_arch_mmu_notifier_invalidate_page(struct kvm *kvm,
 
 struct kvm_vcpu *kvm_arm_get_running_vcpu(void);
 struct kvm_vcpu * __percpu *kvm_get_running_vcpus(void);
+void kvm_arm_halt_guest(struct kvm *kvm);
+void kvm_arm_resume_guest(struct kvm *kvm);
+void kvm_arm_halt_vcpu(struct kvm_vcpu *vcpu);
+void kvm_arm_resume_vcpu(struct kvm_vcpu *vcpu);
 
 u64 __kvm_call_hyp(void *hypfn, ...);
 #define kvm_call_hyp(f, ...) __kvm_call_hyp(kvm_ksym_ref(f), ##__VA_ARGS__)

arch/arm64/include/asm/kvm_mmio.h

@@ -30,6 +30,9 @@ struct kvm_decode {
 	bool sign_extend;
 };
 
+void kvm_mmio_write_buf(void *buf, unsigned int len, unsigned long data);
+unsigned long kvm_mmio_read_buf(const void *buf, unsigned int len);
+
 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/arm64/kvm/Kconfig

@@ -54,6 +54,13 @@ config KVM_ARM_PMU
 	  Adds support for a virtual Performance Monitoring Unit (PMU) in
 	  virtual machines.
 
+config KVM_NEW_VGIC
+	bool "New VGIC implementation"
+	depends on KVM
+	default y
+        ---help---
+          uses the new VGIC implementation
+
 source drivers/vhost/Kconfig
 
 endif # VIRTUALIZATION

arch/arm64/kvm/Makefile

@@ -20,10 +20,22 @@ kvm-$(CONFIG_KVM_ARM_HOST) += emulate.o inject_fault.o regmap.o
 kvm-$(CONFIG_KVM_ARM_HOST) += hyp.o hyp-init.o handle_exit.o
 kvm-$(CONFIG_KVM_ARM_HOST) += guest.o debug.o reset.o sys_regs.o sys_regs_generic_v8.o
 
+ifeq ($(CONFIG_KVM_NEW_VGIC),y)
+kvm-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/vgic/vgic.o
+kvm-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/vgic/vgic-init.o
+kvm-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/vgic/vgic-irqfd.o
+kvm-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/vgic/vgic-v2.o
+kvm-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/vgic/vgic-v3.o
+kvm-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/vgic/vgic-mmio.o
+kvm-$(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) += $(KVM)/arm/vgic/vgic-kvm-device.o
+else
 kvm-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/vgic.o
 kvm-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/vgic-v2.o
 kvm-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/vgic-v2-emul.o
 kvm-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/vgic-v3.o
 kvm-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/vgic-v3-emul.o
+endif
 kvm-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/arch_timer.o
 kvm-$(CONFIG_KVM_ARM_PMU) += $(KVM)/arm/pmu.o

arch/arm64/kvm/inject_fault.c

@@ -162,7 +162,7 @@ static void inject_abt64(struct kvm_vcpu *vcpu, bool is_iabt, unsigned long addr
 		esr |= (ESR_ELx_EC_IABT_CUR << ESR_ELx_EC_SHIFT);
 
 	if (!is_iabt)
-		esr |= ESR_ELx_EC_DABT_LOW;
+		esr |= ESR_ELx_EC_DABT_LOW << ESR_ELx_EC_SHIFT;
 
 	vcpu_sys_reg(vcpu, ESR_EL1) = esr | ESR_ELx_FSC_EXTABT;
 }