The usual smattering of fixes and tunings that came in too late for the

merge window, but should not wait four months before they appear in
 a release.  I also travelled a bit more than usual in the first part
 of May, which didn't help with picking up patches and reports promptly.
 -----BEGIN PGP SIGNATURE-----
 Version: GnuPG v2.0.22 (GNU/Linux)
 
 iQEcBAABAgAGBQJc6RkmAAoJEL/70l94x66DhEAH/ijCkibV9vOUu8n/lSxMjAzi
 I/Y1VEaVRFuQ6u0QSjWBBg22tVsWuWiVbonJ63w3JMRwi5Q5zW9REE7EaKRAa/eC
 FiFE7vTesYh6sGVwdMCwoinjMDyCp7hybvtBc608+MWhVmrdzTYtPm5N85wxIDtW
 xH5Kr2mVeLC43X3vfegolmXZ1obAbZEToJvOgJrYFhnzsmVYYl182kfGtrppBoO0
 XXDPuDRGpTrm6A2oADMdOv+mT9p51pHsedmHQaDGXwAGEC/BkOGKdIdBfwppEwy7
 QP2NGqwkHIyghV1aCPacT6O6G6xL0i2rfvlJ7+e6o7deU4uMXAqIdQ2DbIcHy3g=
 =5IW2
 -----END PGP SIGNATURE-----

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

Pull KVM fixes from Paolo Bonzini:
 "The usual smattering of fixes and tunings that came in too late for
  the merge window, but should not wait four months before they appear
  in a release.

  I also travelled a bit more than usual in the first part of May, which
  didn't help with picking up patches and reports promptly"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (33 commits)
  KVM: x86: fix return value for reserved EFER
  tools/kvm_stat: fix fields filter for child events
  KVM: selftests: Wrap vcpu_nested_state_get/set functions with x86 guard
  kvm: selftests: aarch64: compile with warnings on
  kvm: selftests: aarch64: fix default vm mode
  kvm: selftests: aarch64: dirty_log_test: fix unaligned memslot size
  KVM: s390: fix memory slot handling for KVM_SET_USER_MEMORY_REGION
  KVM: x86/pmu: do not mask the value that is written to fixed PMUs
  KVM: x86/pmu: mask the result of rdpmc according to the width of the counters
  x86/kvm/pmu: Set AMD's virt PMU version to 1
  KVM: x86: do not spam dmesg with VMCS/VMCB dumps
  kvm: Check irqchip mode before assign irqfd
  kvm: svm/avic: fix off-by-one in checking host APIC ID
  KVM: selftests: do not blindly clobber registers in guest asm
  KVM: selftests: Remove duplicated TEST_ASSERT in hyperv_cpuid.c
  KVM: LAPIC: Expose per-vCPU timer_advance_ns to userspace
  KVM: LAPIC: Fix lapic_timer_advance_ns parameter overflow
  kvm: vmx: Fix -Wmissing-prototypes warnings
  KVM: nVMX: Fix using __this_cpu_read() in preemptible context
  kvm: fix compilation on s390
  ...

MAINTAINERS

@@ -8611,14 +8611,12 @@ F:	arch/x86/include/asm/svm.h
 F:	arch/x86/kvm/svm.c
 
 KERNEL VIRTUAL MACHINE FOR ARM/ARM64 (KVM/arm, KVM/arm64)
-M:	Christoffer Dall <christoffer.dall@arm.com>
 M:	Marc Zyngier <marc.zyngier@arm.com>
 R:	James Morse <james.morse@arm.com>
 R:	Julien Thierry <julien.thierry@arm.com>
 R:	Suzuki K Pouloze <suzuki.poulose@arm.com>
 L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
 L:	kvmarm@lists.cs.columbia.edu
-W:	http://systems.cs.columbia.edu/projects/kvm-arm
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/kvmarm/kvmarm.git
 S:	Maintained
 F:	arch/arm/include/uapi/asm/kvm*

arch/arm/kvm/hyp/Makefile

@@ -11,6 +11,7 @@ CFLAGS_ARMV7VE		   :=$(call cc-option, -march=armv7ve)
 
 obj-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/hyp/vgic-v3-sr.o
 obj-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/hyp/timer-sr.o
+obj-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/hyp/aarch32.o
 
 obj-$(CONFIG_KVM_ARM_HOST) += tlb.o
 obj-$(CONFIG_KVM_ARM_HOST) += cp15-sr.o

arch/arm64/include/asm/kvm_host.h

@@ -592,9 +592,6 @@ static inline int kvm_arch_vcpu_run_pid_change(struct kvm_vcpu *vcpu)
 void kvm_set_pmu_events(u32 set, struct perf_event_attr *attr);
 void kvm_clr_pmu_events(u32 clr);
 
-void __pmu_switch_to_host(struct kvm_cpu_context *host_ctxt);
-bool __pmu_switch_to_guest(struct kvm_cpu_context *host_ctxt);
-
 void kvm_vcpu_pmu_restore_guest(struct kvm_vcpu *vcpu);
 void kvm_vcpu_pmu_restore_host(struct kvm_vcpu *vcpu);
 #else

arch/arm64/kvm/hyp/Makefile

@@ -10,6 +10,7 @@ KVM=../../../../virt/kvm
 
 obj-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/hyp/vgic-v3-sr.o
 obj-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/hyp/timer-sr.o
+obj-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/hyp/aarch32.o
 
 obj-$(CONFIG_KVM_ARM_HOST) += vgic-v2-cpuif-proxy.o
 obj-$(CONFIG_KVM_ARM_HOST) += sysreg-sr.o

arch/arm64/kvm/hyp/switch.c

@@ -16,6 +16,7 @@
  */
 
 #include <linux/arm-smccc.h>
+#include <linux/kvm_host.h>
 #include <linux/types.h>
 #include <linux/jump_label.h>
 #include <uapi/linux/psci.h>
@@ -505,6 +506,44 @@ static void __hyp_text __set_host_arch_workaround_state(struct kvm_vcpu *vcpu)
 #endif
 }
 
+/**
+ * Disable host events, enable guest events
+ */
+static bool __hyp_text __pmu_switch_to_guest(struct kvm_cpu_context *host_ctxt)
+{
+	struct kvm_host_data *host;
+	struct kvm_pmu_events *pmu;
+
+	host = container_of(host_ctxt, struct kvm_host_data, host_ctxt);
+	pmu = &host->pmu_events;
+
+	if (pmu->events_host)
+		write_sysreg(pmu->events_host, pmcntenclr_el0);
+
+	if (pmu->events_guest)
+		write_sysreg(pmu->events_guest, pmcntenset_el0);
+
+	return (pmu->events_host || pmu->events_guest);
+}
+
+/**
+ * Disable guest events, enable host events
+ */
+static void __hyp_text __pmu_switch_to_host(struct kvm_cpu_context *host_ctxt)
+{
+	struct kvm_host_data *host;
+	struct kvm_pmu_events *pmu;
+
+	host = container_of(host_ctxt, struct kvm_host_data, host_ctxt);
+	pmu = &host->pmu_events;
+
+	if (pmu->events_guest)
+		write_sysreg(pmu->events_guest, pmcntenclr_el0);
+
+	if (pmu->events_host)
+		write_sysreg(pmu->events_host, pmcntenset_el0);
+}
+
 /* Switch to the guest for VHE systems running in EL2 */
 int kvm_vcpu_run_vhe(struct kvm_vcpu *vcpu)
 {

arch/arm64/kvm/pmu.c

@@ -53,44 +53,6 @@ void kvm_clr_pmu_events(u32 clr)
 	ctx->pmu_events.events_guest &= ~clr;
 }
 
-/**
- * Disable host events, enable guest events
- */
-bool __hyp_text __pmu_switch_to_guest(struct kvm_cpu_context *host_ctxt)
-{
-	struct kvm_host_data *host;
-	struct kvm_pmu_events *pmu;
-
-	host = container_of(host_ctxt, struct kvm_host_data, host_ctxt);
-	pmu = &host->pmu_events;
-
-	if (pmu->events_host)
-		write_sysreg(pmu->events_host, pmcntenclr_el0);
-
-	if (pmu->events_guest)
-		write_sysreg(pmu->events_guest, pmcntenset_el0);
-
-	return (pmu->events_host || pmu->events_guest);
-}
-
-/**
- * Disable guest events, enable host events
- */
-void __hyp_text __pmu_switch_to_host(struct kvm_cpu_context *host_ctxt)
-{
-	struct kvm_host_data *host;
-	struct kvm_pmu_events *pmu;
-
-	host = container_of(host_ctxt, struct kvm_host_data, host_ctxt);
-	pmu = &host->pmu_events;
-
-	if (pmu->events_guest)
-		write_sysreg(pmu->events_guest, pmcntenclr_el0);
-
-	if (pmu->events_host)
-		write_sysreg(pmu->events_host, pmcntenset_el0);
-}
-
 #define PMEVTYPER_READ_CASE(idx)				\
 	case idx:						\
 		return read_sysreg(pmevtyper##idx##_el0)

arch/s390/include/asm/kvm_host.h

@@ -36,7 +36,7 @@
  */
 #define KVM_NR_IRQCHIPS 1
 #define KVM_IRQCHIP_NUM_PINS 4096
-#define KVM_HALT_POLL_NS_DEFAULT 80000
+#define KVM_HALT_POLL_NS_DEFAULT 50000
 
 /* s390-specific vcpu->requests bit members */
 #define KVM_REQ_ENABLE_IBS	KVM_ARCH_REQ(0)

arch/s390/kvm/kvm-s390.c

@@ -181,7 +181,7 @@ MODULE_PARM_DESC(hpage, "1m huge page backing support");
 /* maximum percentage of steal time for polling.  >100 is treated like 100 */
 static u8 halt_poll_max_steal = 10;
 module_param(halt_poll_max_steal, byte, 0644);
-MODULE_PARM_DESC(hpage, "Maximum percentage of steal time to allow polling");
+MODULE_PARM_DESC(halt_poll_max_steal, "Maximum percentage of steal time to allow polling");
 
 /*
  * For now we handle at most 16 double words as this is what the s390 base
@@ -4524,21 +4524,28 @@ void kvm_arch_commit_memory_region(struct kvm *kvm,
 				const struct kvm_memory_slot *new,
 				enum kvm_mr_change change)
 {
-	int rc;
+	int rc = 0;
-
-	/* If the basics of the memslot do not change, we do not want
-	 * to update the gmap. Every update causes several unnecessary
-	 * segment translation exceptions. This is usually handled just
-	 * fine by the normal fault handler + gmap, but it will also
-	 * cause faults on the prefix page of running guest CPUs.
-	 */
-	if (old->userspace_addr == mem->userspace_addr &&
-	    old->base_gfn * PAGE_SIZE == mem->guest_phys_addr &&
-	    old->npages * PAGE_SIZE == mem->memory_size)
-		return;
 
+	switch (change) {
+	case KVM_MR_DELETE:
+		rc = gmap_unmap_segment(kvm->arch.gmap, old->base_gfn * PAGE_SIZE,
+					old->npages * PAGE_SIZE);
+		break;
+	case KVM_MR_MOVE:
+		rc = gmap_unmap_segment(kvm->arch.gmap, old->base_gfn * PAGE_SIZE,
+					old->npages * PAGE_SIZE);
+		if (rc)
+			break;
+		/* FALLTHROUGH */
+	case KVM_MR_CREATE:
 		rc = gmap_map_segment(kvm->arch.gmap, mem->userspace_addr,
 				      mem->guest_phys_addr, mem->memory_size);
+		break;
+	case KVM_MR_FLAGS_ONLY:
+		break;
+	default:
+		WARN(1, "Unknown KVM MR CHANGE: %d\n", change);
+	}
 	if (rc)
 		pr_warn("failed to commit memory region\n");
 	return;

arch/x86/kvm/cpuid.c

@@ -456,8 +456,9 @@ static inline int __do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function,
 		}
 		break;
 	}
-	/* function 4 has additional index. */
+	/* functions 4 and 0x8000001d have additional index. */
-	case 4: {
+	case 4:
+	case 0x8000001d: {
 		int i, cache_type;
 
 		entry->flags |= KVM_CPUID_FLAG_SIGNIFCANT_INDEX;
@@ -701,8 +702,7 @@ static inline int __do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function,
 		entry->ecx = entry->edx = 0;
 		break;
 	case 0x8000001a:
-		break;
+	case 0x8000001e:
-	case 0x8000001d:
 		break;
 	/*Add support for Centaur's CPUID instruction*/
 	case 0xC0000000:

arch/x86/kvm/debugfs.c

@@ -9,12 +9,22 @@
  */
 #include <linux/kvm_host.h>
 #include <linux/debugfs.h>
+#include "lapic.h"
 
 bool kvm_arch_has_vcpu_debugfs(void)
 {
 	return true;
 }
 
+static int vcpu_get_timer_advance_ns(void *data, u64 *val)
+{
+	struct kvm_vcpu *vcpu = (struct kvm_vcpu *) data;
+	*val = vcpu->arch.apic->lapic_timer.timer_advance_ns;
+	return 0;
+}
+
+DEFINE_SIMPLE_ATTRIBUTE(vcpu_timer_advance_ns_fops, vcpu_get_timer_advance_ns, NULL, "%llu\n");
+
 static int vcpu_get_tsc_offset(void *data, u64 *val)
 {
 	struct kvm_vcpu *vcpu = (struct kvm_vcpu *) data;
@@ -51,6 +61,14 @@ int kvm_arch_create_vcpu_debugfs(struct kvm_vcpu *vcpu)
 	if (!ret)
 		return -ENOMEM;
 
+	if (lapic_in_kernel(vcpu)) {
+		ret = debugfs_create_file("lapic_timer_advance_ns", 0444,
+								vcpu->debugfs_dentry,
+								vcpu, &vcpu_timer_advance_ns_fops);
+		if (!ret)
+			return -ENOMEM;
+	}
+
 	if (kvm_has_tsc_control) {
 		ret = debugfs_create_file("tsc-scaling-ratio", 0444,
 							vcpu->debugfs_dentry,

arch/x86/kvm/irq.c

@@ -172,3 +172,10 @@ void __kvm_migrate_timers(struct kvm_vcpu *vcpu)
 	__kvm_migrate_apic_timer(vcpu);
 	__kvm_migrate_pit_timer(vcpu);
 }
+
+bool kvm_arch_irqfd_allowed(struct kvm *kvm, struct kvm_irqfd *args)
+{
+	bool resample = args->flags & KVM_IRQFD_FLAG_RESAMPLE;
+
+	return resample ? irqchip_kernel(kvm) : irqchip_in_kernel(kvm);
+}

arch/x86/kvm/irq.h

@@ -114,6 +114,7 @@ static inline int irqchip_in_kernel(struct kvm *kvm)
 	return mode != KVM_IRQCHIP_NONE;
 }
 
+bool kvm_arch_irqfd_allowed(struct kvm *kvm, struct kvm_irqfd *args);
 void kvm_inject_pending_timer_irqs(struct kvm_vcpu *vcpu);
 void kvm_inject_apic_timer_irqs(struct kvm_vcpu *vcpu);
 void kvm_apic_nmi_wd_deliver(struct kvm_vcpu *vcpu);

arch/x86/kvm/pmu.c

@@ -283,7 +283,7 @@ int kvm_pmu_rdpmc(struct kvm_vcpu *vcpu, unsigned idx, u64 *data)
 	bool fast_mode = idx & (1u << 31);
 	struct kvm_pmu *pmu = vcpu_to_pmu(vcpu);
 	struct kvm_pmc *pmc;
-	u64 ctr_val;
+	u64 mask = fast_mode ? ~0u : ~0ull;
 
 	if (!pmu->version)
 		return 1;
@@ -291,15 +291,11 @@ int kvm_pmu_rdpmc(struct kvm_vcpu *vcpu, unsigned idx, u64 *data)
 	if (is_vmware_backdoor_pmc(idx))
 		return kvm_pmu_rdpmc_vmware(vcpu, idx, data);
 
-	pmc = kvm_x86_ops->pmu_ops->msr_idx_to_pmc(vcpu, idx);
+	pmc = kvm_x86_ops->pmu_ops->msr_idx_to_pmc(vcpu, idx, &mask);
 	if (!pmc)
 		return 1;
 
-	ctr_val = pmc_read_counter(pmc);
+	*data = pmc_read_counter(pmc) & mask;
-	if (fast_mode)
-		ctr_val = (u32)ctr_val;
-
-	*data = ctr_val;
 	return 0;
 }
 

arch/x86/kvm/pmu.h

@@ -25,7 +25,8 @@ struct kvm_pmu_ops {
 	unsigned (*find_fixed_event)(int idx);
 	bool (*pmc_is_enabled)(struct kvm_pmc *pmc);
 	struct kvm_pmc *(*pmc_idx_to_pmc)(struct kvm_pmu *pmu, int pmc_idx);
-	struct kvm_pmc *(*msr_idx_to_pmc)(struct kvm_vcpu *vcpu, unsigned idx);
+	struct kvm_pmc *(*msr_idx_to_pmc)(struct kvm_vcpu *vcpu, unsigned idx,
+					  u64 *mask);
 	int (*is_valid_msr_idx)(struct kvm_vcpu *vcpu, unsigned idx);
 	bool (*is_valid_msr)(struct kvm_vcpu *vcpu, u32 msr);
 	int (*get_msr)(struct kvm_vcpu *vcpu, u32 msr, u64 *data);

arch/x86/kvm/pmu_amd.c

@@ -186,7 +186,7 @@ static int amd_is_valid_msr_idx(struct kvm_vcpu *vcpu, unsigned idx)
 }
 
 /* idx is the ECX register of RDPMC instruction */
-static struct kvm_pmc *amd_msr_idx_to_pmc(struct kvm_vcpu *vcpu, unsigned idx)
+static struct kvm_pmc *amd_msr_idx_to_pmc(struct kvm_vcpu *vcpu, unsigned idx, u64 *mask)
 {
 	struct kvm_pmu *pmu = vcpu_to_pmu(vcpu);
 	struct kvm_pmc *counters;
@@ -269,10 +269,10 @@ static void amd_pmu_refresh(struct kvm_vcpu *vcpu)
 
 	pmu->counter_bitmask[KVM_PMC_GP] = ((u64)1 << 48) - 1;
 	pmu->reserved_bits = 0xffffffff00200000ull;
+	pmu->version = 1;
 	/* not applicable to AMD; but clean them to prevent any fall out */
 	pmu->counter_bitmask[KVM_PMC_FIXED] = 0;
 	pmu->nr_arch_fixed_counters = 0;
-	pmu->version = 0;
 	pmu->global_status = 0;
 }
 

arch/x86/kvm/svm.c

@@ -379,6 +379,9 @@ module_param(vgif, int, 0444);
 static int sev = IS_ENABLED(CONFIG_AMD_MEM_ENCRYPT_ACTIVE_BY_DEFAULT);
 module_param(sev, int, 0444);
 
+static bool __read_mostly dump_invalid_vmcb = 0;
+module_param(dump_invalid_vmcb, bool, 0644);
+
 static u8 rsm_ins_bytes[] = "\x0f\xaa";
 
 static void svm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0);
@@ -2024,7 +2027,11 @@ static void avic_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 	if (!kvm_vcpu_apicv_active(vcpu))
 		return;
 
-	if (WARN_ON(h_physical_id >= AVIC_MAX_PHYSICAL_ID_COUNT))
+	/*
+	 * Since the host physical APIC id is 8 bits,
+	 * we can support host APIC ID upto 255.
+	 */
+	if (WARN_ON(h_physical_id > AVIC_PHYSICAL_ID_ENTRY_HOST_PHYSICAL_ID_MASK))
 		return;
 
 	entry = READ_ONCE(*(svm->avic_physical_id_cache));
@@ -4824,6 +4831,11 @@ static void dump_vmcb(struct kvm_vcpu *vcpu)
 	struct vmcb_control_area *control = &svm->vmcb->control;
 	struct vmcb_save_area *save = &svm->vmcb->save;
 
+	if (!dump_invalid_vmcb) {
+		pr_warn_ratelimited("set kvm_amd.dump_invalid_vmcb=1 to dump internal KVM state.\n");
+		return;
+	}
+
 	pr_err("VMCB Control Area:\n");
 	pr_err("%-20s%04x\n", "cr_read:", control->intercept_cr & 0xffff);
 	pr_err("%-20s%04x\n", "cr_write:", control->intercept_cr >> 16);
@@ -4982,7 +4994,6 @@ static int handle_exit(struct kvm_vcpu *vcpu)
 		kvm_run->exit_reason = KVM_EXIT_FAIL_ENTRY;
 		kvm_run->fail_entry.hardware_entry_failure_reason
 			= svm->vmcb->control.exit_code;
-		pr_err("KVM: FAILED VMRUN WITH VMCB:\n");
 		dump_vmcb(vcpu);
 		return 0;
 	}

arch/x86/kvm/vmx/nested.c

@@ -2784,14 +2784,13 @@ static int nested_vmx_check_vmentry_hw(struct kvm_vcpu *vcpu)
 	      : "cc", "memory"
 	);
 
-	preempt_enable();
-
 	if (vmx->msr_autoload.host.nr)
 		vmcs_write32(VM_EXIT_MSR_LOAD_COUNT, vmx->msr_autoload.host.nr);
 	if (vmx->msr_autoload.guest.nr)
 		vmcs_write32(VM_ENTRY_MSR_LOAD_COUNT, vmx->msr_autoload.guest.nr);
 
 	if (vm_fail) {
+		preempt_enable();
 		WARN_ON_ONCE(vmcs_read32(VM_INSTRUCTION_ERROR) !=
 			     VMXERR_ENTRY_INVALID_CONTROL_FIELD);
 		return 1;
@@ -2803,6 +2802,7 @@ static int nested_vmx_check_vmentry_hw(struct kvm_vcpu *vcpu)
 	local_irq_enable();
 	if (hw_breakpoint_active())
 		set_debugreg(__this_cpu_read(cpu_dr7), 7);
+	preempt_enable();
 
 	/*
 	 * A non-failing VMEntry means we somehow entered guest mode with
@@ -5423,39 +5423,44 @@ static int vmx_set_nested_state(struct kvm_vcpu *vcpu,
 	if (!(kvm_state->flags & KVM_STATE_NESTED_GUEST_MODE))
 		return 0;
 
+	vmx->nested.nested_run_pending =
+		!!(kvm_state->flags & KVM_STATE_NESTED_RUN_PENDING);
+
+	ret = -EINVAL;
 	if (nested_cpu_has_shadow_vmcs(vmcs12) &&
 	    vmcs12->vmcs_link_pointer != -1ull) {
 		struct vmcs12 *shadow_vmcs12 = get_shadow_vmcs12(vcpu);
 
-		if (kvm_state->size < sizeof(*kvm_state) + 2 * sizeof(*vmcs12))
+		if (kvm_state->size < sizeof(*kvm_state) + VMCS12_SIZE + sizeof(*vmcs12))
-			return -EINVAL;
+			goto error_guest_mode;
 
 		if (copy_from_user(shadow_vmcs12,
 				   user_kvm_nested_state->data + VMCS12_SIZE,
-				   sizeof(*vmcs12)))
+				   sizeof(*vmcs12))) {
-			return -EFAULT;
+			ret = -EFAULT;
+			goto error_guest_mode;
+		}
 
 		if (shadow_vmcs12->hdr.revision_id != VMCS12_REVISION ||
 		    !shadow_vmcs12->hdr.shadow_vmcs)
-			return -EINVAL;
+			goto error_guest_mode;
 	}
 
 	if (nested_vmx_check_controls(vcpu, vmcs12) ||
 	    nested_vmx_check_host_state(vcpu, vmcs12) ||
 	    nested_vmx_check_guest_state(vcpu, vmcs12, &exit_qual))
-		return -EINVAL;
+		goto error_guest_mode;
 
 	vmx->nested.dirty_vmcs12 = true;
-	vmx->nested.nested_run_pending =
-		!!(kvm_state->flags & KVM_STATE_NESTED_RUN_PENDING);
-
 	ret = nested_vmx_enter_non_root_mode(vcpu, false);
-	if (ret) {
+	if (ret)
-		vmx->nested.nested_run_pending = 0;
+		goto error_guest_mode;
-		return -EINVAL;
-	}
 
 	return 0;
+
+error_guest_mode:
+	vmx->nested.nested_run_pending = 0;
+	return ret;
 }
 
 void nested_vmx_vcpu_setup(void)

arch/x86/kvm/vmx/pmu_intel.c

@@ -126,7 +126,7 @@ static int intel_is_valid_msr_idx(struct kvm_vcpu *vcpu, unsigned idx)
 }
 
 static struct kvm_pmc *intel_msr_idx_to_pmc(struct kvm_vcpu *vcpu,
-					    unsigned idx)
+					    unsigned idx, u64 *mask)
 {
 	struct kvm_pmu *pmu = vcpu_to_pmu(vcpu);
 	bool fixed = idx & (1u << 30);
@@ -138,6 +138,7 @@ static struct kvm_pmc *intel_msr_idx_to_pmc(struct kvm_vcpu *vcpu,
 	if (fixed && idx >= pmu->nr_arch_fixed_counters)
 		return NULL;
 	counters = fixed ? pmu->fixed_counters : pmu->gp_counters;
+	*mask &= pmu->counter_bitmask[fixed ? KVM_PMC_FIXED : KVM_PMC_GP];
 
 	return &counters[idx];
 }
@@ -183,9 +184,13 @@ static int intel_pmu_get_msr(struct kvm_vcpu *vcpu, u32 msr, u64 *data)
 		*data = pmu->global_ovf_ctrl;
 		return 0;
 	default:
-		if ((pmc = get_gp_pmc(pmu, msr, MSR_IA32_PERFCTR0)) ||
+		if ((pmc = get_gp_pmc(pmu, msr, MSR_IA32_PERFCTR0))) {
-		    (pmc = get_fixed_pmc(pmu, msr))) {
+			u64 val = pmc_read_counter(pmc);
-			*data = pmc_read_counter(pmc);
+			*data = val & pmu->counter_bitmask[KVM_PMC_GP];
+			return 0;
+		} else if ((pmc = get_fixed_pmc(pmu, msr))) {
+			u64 val = pmc_read_counter(pmc);
+			*data = val & pmu->counter_bitmask[KVM_PMC_FIXED];
 			return 0;
 		} else if ((pmc = get_gp_pmc(pmu, msr, MSR_P6_EVNTSEL0))) {
 			*data = pmc->eventsel;
@@ -235,11 +240,14 @@ static int intel_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 		}
 		break;
 	default:
-		if ((pmc = get_gp_pmc(pmu, msr, MSR_IA32_PERFCTR0)) ||
+		if ((pmc = get_gp_pmc(pmu, msr, MSR_IA32_PERFCTR0))) {
-		    (pmc = get_fixed_pmc(pmu, msr))) {
+			if (msr_info->host_initiated)
-			if (!msr_info->host_initiated)
+				pmc->counter = data;
-				data = (s64)(s32)data;
+			else
-			pmc->counter += data - pmc_read_counter(pmc);
+				pmc->counter = (s32)data;
+			return 0;
+		} else if ((pmc = get_fixed_pmc(pmu, msr))) {
+			pmc->counter = data;
 			return 0;
 		} else if ((pmc = get_gp_pmc(pmu, msr, MSR_P6_EVNTSEL0))) {
 			if (data == pmc->eventsel)

arch/x86/kvm/vmx/vmx.c

@@ -114,6 +114,9 @@ static u64 __read_mostly host_xss;
 bool __read_mostly enable_pml = 1;
 module_param_named(pml, enable_pml, bool, S_IRUGO);
 
+static bool __read_mostly dump_invalid_vmcs = 0;
+module_param(dump_invalid_vmcs, bool, 0644);
+
 #define MSR_BITMAP_MODE_X2APIC		1
 #define MSR_BITMAP_MODE_X2APIC_APICV	2
 
@@ -5607,15 +5610,24 @@ static void vmx_dump_dtsel(char *name, uint32_t limit)
 
 void dump_vmcs(void)
 {
-	u32 vmentry_ctl = vmcs_read32(VM_ENTRY_CONTROLS);
+	u32 vmentry_ctl, vmexit_ctl;
-	u32 vmexit_ctl = vmcs_read32(VM_EXIT_CONTROLS);
+	u32 cpu_based_exec_ctrl, pin_based_exec_ctrl, secondary_exec_control;
-	u32 cpu_based_exec_ctrl = vmcs_read32(CPU_BASED_VM_EXEC_CONTROL);
+	unsigned long cr4;
-	u32 pin_based_exec_ctrl = vmcs_read32(PIN_BASED_VM_EXEC_CONTROL);
+	u64 efer;
-	u32 secondary_exec_control = 0;
-	unsigned long cr4 = vmcs_readl(GUEST_CR4);
-	u64 efer = vmcs_read64(GUEST_IA32_EFER);
 	int i, n;
 
+	if (!dump_invalid_vmcs) {
+		pr_warn_ratelimited("set kvm_intel.dump_invalid_vmcs=1 to dump internal KVM state.\n");
+		return;
+	}
+
+	vmentry_ctl = vmcs_read32(VM_ENTRY_CONTROLS);
+	vmexit_ctl = vmcs_read32(VM_EXIT_CONTROLS);
+	cpu_based_exec_ctrl = vmcs_read32(CPU_BASED_VM_EXEC_CONTROL);
+	pin_based_exec_ctrl = vmcs_read32(PIN_BASED_VM_EXEC_CONTROL);
+	cr4 = vmcs_readl(GUEST_CR4);
+	efer = vmcs_read64(GUEST_IA32_EFER);
+	secondary_exec_control = 0;
 	if (cpu_has_secondary_exec_ctrls())
 		secondary_exec_control = vmcs_read32(SECONDARY_VM_EXEC_CONTROL);
 

arch/x86/kvm/vmx/vmx.h

@@ -319,6 +319,7 @@ void vmx_set_nmi_mask(struct kvm_vcpu *vcpu, bool masked);
 void vmx_set_virtual_apic_mode(struct kvm_vcpu *vcpu);
 struct shared_msr_entry *find_msr_entry(struct vcpu_vmx *vmx, u32 msr);
 void pt_update_intercept_for_msr(struct vcpu_vmx *vmx);
+void vmx_update_host_rsp(struct vcpu_vmx *vmx, unsigned long host_rsp);
 
 #define POSTED_INTR_ON  0
 #define POSTED_INTR_SN  1

arch/x86/kvm/x86.c

@@ -143,7 +143,7 @@ module_param(tsc_tolerance_ppm, uint, S_IRUGO | S_IWUSR);
  * tuning, i.e. allows priveleged userspace to set an exact advancement time.
  */
 static int __read_mostly lapic_timer_advance_ns = -1;
-module_param(lapic_timer_advance_ns, uint, S_IRUGO | S_IWUSR);
+module_param(lapic_timer_advance_ns, int, S_IRUGO | S_IWUSR);
 
 static bool __read_mostly vector_hashing = true;
 module_param(vector_hashing, bool, S_IRUGO);
@@ -1298,7 +1298,7 @@ static int set_efer(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 	u64 efer = msr_info->data;
 
 	if (efer & efer_reserved_bits)
-		return false;
+		return 1;
 
 	if (!msr_info->host_initiated) {
 		if (!__kvm_valid_efer(vcpu, efer))

tools/kvm/kvm_stat/kvm_stat

@@ -575,8 +575,12 @@ class TracepointProvider(Provider):
     def update_fields(self, fields_filter):
         """Refresh fields, applying fields_filter"""
         self.fields = [field for field in self._get_available_fields()
-                       if self.is_field_wanted(fields_filter, field) or
+                       if self.is_field_wanted(fields_filter, field)]
-                       ARCH.tracepoint_is_child(field)]
+        # add parents for child fields - otherwise we won't see any output!
+        for field in self._fields:
+            parent = ARCH.tracepoint_is_child(field)
+            if (parent and parent not in self._fields):
+                self.fields.append(parent)
 
     @staticmethod
     def _get_online_cpus():
@@ -735,8 +739,12 @@ class DebugfsProvider(Provider):
     def update_fields(self, fields_filter):
         """Refresh fields, applying fields_filter"""
         self._fields = [field for field in self._get_available_fields()
-                        if self.is_field_wanted(fields_filter, field) or
+                        if self.is_field_wanted(fields_filter, field)]
-                        ARCH.debugfs_is_child(field)]
+        # add parents for child fields - otherwise we won't see any output!
+        for field in self._fields:
+            parent = ARCH.debugfs_is_child(field)
+            if (parent and parent not in self._fields):
+                self.fields.append(parent)
 
     @property
     def fields(self):

tools/kvm/kvm_stat/kvm_stat.txt

@@ -34,6 +34,8 @@ INTERACTIVE COMMANDS
 *c*::	clear filter
 
 *f*::	filter by regular expression
+ ::     *Note*: Child events pull in their parents, and parents' stats summarize
+                all child events, not just the filtered ones
 
 *g*::	filter by guest name/PID
 

tools/testing/selftests/kvm/Makefile

@@ -35,7 +35,9 @@ LIBKVM += $(LIBKVM_$(UNAME_M))
 INSTALL_HDR_PATH = $(top_srcdir)/usr
 LINUX_HDR_PATH = $(INSTALL_HDR_PATH)/include/
 LINUX_TOOL_INCLUDE = $(top_srcdir)/tools/include
-CFLAGS += -O2 -g -std=gnu99 -fno-stack-protector -fno-PIE -I$(LINUX_TOOL_INCLUDE) -I$(LINUX_HDR_PATH) -Iinclude -I$(<D) -Iinclude/$(UNAME_M) -I..
+CFLAGS += -Wall -Wstrict-prototypes -Wuninitialized -O2 -g -std=gnu99 \
+	-fno-stack-protector -fno-PIE -I$(LINUX_TOOL_INCLUDE) \
+	-I$(LINUX_HDR_PATH) -Iinclude -I$(<D) -Iinclude/$(UNAME_M) -I..
 
 no-pie-option := $(call try-run, echo 'int main() { return 0; }' | \
         $(CC) -Werror $(KBUILD_CPPFLAGS) $(CC_OPTION_CFLAGS) -no-pie -x c - -o "$$TMP", -no-pie)

tools/testing/selftests/kvm/dirty_log_test.c

@@ -131,6 +131,7 @@ static void *vcpu_worker(void *data)
 	while (!READ_ONCE(host_quit)) {
 		/* Let the guest dirty the random pages */
 		ret = _vcpu_run(vm, VCPU_ID);
+		TEST_ASSERT(ret == 0, "vcpu_run failed: %d\n", ret);
 		if (get_ucall(vm, VCPU_ID, &uc) == UCALL_SYNC) {
 			pages_count += TEST_PAGES_PER_LOOP;
 			generate_random_array(guest_array, TEST_PAGES_PER_LOOP);
@@ -292,7 +293,7 @@ static void run_test(enum vm_guest_mode mode, unsigned long iterations,
 	 * A little more than 1G of guest page sized pages.  Cover the
 	 * case where the size is not aligned to 64 pages.
 	 */
-	guest_num_pages = (1ul << (30 - guest_page_shift)) + 3;
+	guest_num_pages = (1ul << (30 - guest_page_shift)) + 16;
 	host_page_size = getpagesize();
 	host_num_pages = (guest_num_pages * guest_page_size) / host_page_size +
 			 !!((guest_num_pages * guest_page_size) % host_page_size);
@@ -426,8 +427,11 @@ int main(int argc, char *argv[])
 	unsigned long interval = TEST_HOST_LOOP_INTERVAL;
 	bool mode_selected = false;
 	uint64_t phys_offset = 0;
-	unsigned int mode, host_ipa_limit;
+	unsigned int mode;
 	int opt, i;
+#ifdef __aarch64__
+	unsigned int host_ipa_limit;
+#endif
 
 #ifdef USE_CLEAR_DIRTY_LOG
 	if (!kvm_check_cap(KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2)) {

tools/testing/selftests/kvm/include/kvm_util.h

@@ -118,10 +118,12 @@ void vcpu_events_get(struct kvm_vm *vm, uint32_t vcpuid,
 		     struct kvm_vcpu_events *events);
 void vcpu_events_set(struct kvm_vm *vm, uint32_t vcpuid,
 		     struct kvm_vcpu_events *events);
+#ifdef __x86_64__
 void vcpu_nested_state_get(struct kvm_vm *vm, uint32_t vcpuid,
 			   struct kvm_nested_state *state);
 int vcpu_nested_state_set(struct kvm_vm *vm, uint32_t vcpuid,
 			  struct kvm_nested_state *state, bool ignore_error);
+#endif
 
 const char *exit_reason_str(unsigned int exit_reason);
 

tools/testing/selftests/kvm/lib/aarch64/processor.c

@@ -7,6 +7,8 @@
 
 #define _GNU_SOURCE /* for program_invocation_name */
 
+#include <linux/compiler.h>
+
 #include "kvm_util.h"
 #include "../kvm_util_internal.h"
 #include "processor.h"
@@ -67,15 +69,13 @@ static uint64_t ptrs_per_pgd(struct kvm_vm *vm)
 	return 1 << (vm->va_bits - shift);
 }
 
-static uint64_t ptrs_per_pte(struct kvm_vm *vm)
+static uint64_t __maybe_unused ptrs_per_pte(struct kvm_vm *vm)
 {
 	return 1 << (vm->page_shift - 3);
 }
 
 void virt_pgd_alloc(struct kvm_vm *vm, uint32_t pgd_memslot)
 {
-	int rc;
-
 	if (!vm->pgd_created) {
 		vm_paddr_t paddr = vm_phy_pages_alloc(vm,
 			page_align(vm, ptrs_per_pgd(vm) * 8) / vm->page_size,
@@ -181,6 +181,7 @@ vm_paddr_t addr_gva2gpa(struct kvm_vm *vm, vm_vaddr_t gva)
 unmapped_gva:
 	TEST_ASSERT(false, "No mapping for vm virtual address, "
 		    "gva: 0x%lx", gva);
+	exit(1);
 }
 
 static void pte_dump(FILE *stream, struct kvm_vm *vm, uint8_t indent, uint64_t page, int level)
@@ -226,7 +227,7 @@ struct kvm_vm *vm_create_default(uint32_t vcpuid, uint64_t extra_mem_pages,
 	uint64_t extra_pg_pages = (extra_mem_pages / ptrs_per_4k_pte) * 2;
 	struct kvm_vm *vm;
 
-	vm = vm_create(VM_MODE_P52V48_4K, DEFAULT_GUEST_PHY_PAGES + extra_pg_pages, O_RDWR);
+	vm = vm_create(VM_MODE_P40V48_4K, DEFAULT_GUEST_PHY_PAGES + extra_pg_pages, O_RDWR);
 
 	kvm_vm_elf_load(vm, program_invocation_name, 0, 0);
 	vm_vcpu_add_default(vm, vcpuid, guest_code);
@@ -312,6 +313,6 @@ void vcpu_dump(FILE *stream, struct kvm_vm *vm, uint32_t vcpuid, uint8_t indent)
 	get_reg(vm, vcpuid, ARM64_CORE_REG(regs.pstate), &pstate);
 	get_reg(vm, vcpuid, ARM64_CORE_REG(regs.pc), &pc);
 
-	fprintf(stream, "%*spstate: 0x%.16llx pc: 0x%.16llx\n",
+	fprintf(stream, "%*spstate: 0x%.16lx pc: 0x%.16lx\n",
 		indent, "", pstate, pc);
 }

tools/testing/selftests/kvm/lib/kvm_util.c

@@ -135,7 +135,6 @@ struct kvm_vm *_vm_create(enum vm_guest_mode mode, uint64_t phy_pages,
 			  int perm, unsigned long type)
 {
 	struct kvm_vm *vm;
-	int kvm_fd;
 
 	vm = calloc(1, sizeof(*vm));
 	TEST_ASSERT(vm != NULL, "Insufficient Memory");
@@ -556,7 +555,6 @@ void vm_userspace_mem_region_add(struct kvm_vm *vm,
 	uint32_t flags)
 {
 	int ret;
-	unsigned long pmem_size = 0;
 	struct userspace_mem_region *region;
 	size_t huge_page_size = KVM_UTIL_PGS_PER_HUGEPG * vm->page_size;
 
@@ -1250,6 +1248,7 @@ void vcpu_events_set(struct kvm_vm *vm, uint32_t vcpuid,
 		ret, errno);
 }
 
+#ifdef __x86_64__
 void vcpu_nested_state_get(struct kvm_vm *vm, uint32_t vcpuid,
 			   struct kvm_nested_state *state)
 {
@@ -1281,6 +1280,7 @@ int vcpu_nested_state_set(struct kvm_vm *vm, uint32_t vcpuid,
 
 	return ret;
 }
+#endif
 
 /*
  * VM VCPU System Regs Get
@@ -1334,7 +1334,6 @@ void vcpu_sregs_set(struct kvm_vm *vm, uint32_t vcpuid, struct kvm_sregs *sregs)
 int _vcpu_sregs_set(struct kvm_vm *vm, uint32_t vcpuid, struct kvm_sregs *sregs)
 {
 	struct vcpu *vcpu = vcpu_find(vm, vcpuid);
-	int ret;
 
 	TEST_ASSERT(vcpu != NULL, "vcpu not found, vcpuid: %u", vcpuid);
 

tools/testing/selftests/kvm/lib/ucall.c

@@ -142,7 +142,7 @@ uint64_t get_ucall(struct kvm_vm *vm, uint32_t vcpu_id, struct ucall *uc)
 		vm_vaddr_t gva;
 		TEST_ASSERT(run->mmio.is_write && run->mmio.len == 8,
 			    "Unexpected ucall exit mmio address access");
-		gva = *(vm_vaddr_t *)run->mmio.data;
+		memcpy(&gva, run->mmio.data, sizeof(gva));
 		memcpy(uc, addr_gva2hva(vm, gva), sizeof(*uc));
 	}
 

tools/testing/selftests/kvm/lib/x86_64/processor.c

@@ -229,8 +229,6 @@ void sregs_dump(FILE *stream, struct kvm_sregs *sregs,
 
 void virt_pgd_alloc(struct kvm_vm *vm, uint32_t pgd_memslot)
 {
-	int rc;
-
 	TEST_ASSERT(vm->mode == VM_MODE_P52V48_4K, "Attempt to use "
 		"unknown or unsupported guest mode, mode: 0x%x", vm->mode);
 
@@ -549,7 +547,6 @@ vm_paddr_t addr_gva2gpa(struct kvm_vm *vm, vm_vaddr_t gva)
 	struct pageDirectoryPointerEntry *pdpe;
 	struct pageDirectoryEntry *pde;
 	struct pageTableEntry *pte;
-	void *hva;
 
 	TEST_ASSERT(vm->mode == VM_MODE_P52V48_4K, "Attempt to use "
 		"unknown or unsupported guest mode, mode: 0x%x", vm->mode);
@@ -582,6 +579,7 @@ vm_paddr_t addr_gva2gpa(struct kvm_vm *vm, vm_vaddr_t gva)
 unmapped_gva:
 	TEST_ASSERT(false, "No mapping for vm virtual address, "
 		    "gva: 0x%lx", gva);
+	exit(EXIT_FAILURE);
 }
 
 static void kvm_setup_gdt(struct kvm_vm *vm, struct kvm_dtable *dt, int gdt_memslot,

tools/testing/selftests/kvm/x86_64/cr4_cpuid_sync_test.c

@@ -87,6 +87,7 @@ int main(int argc, char *argv[])
 	while (1) {
 		rc = _vcpu_run(vm, VCPU_ID);
 
+		TEST_ASSERT(rc == 0, "vcpu_run failed: %d\n", rc);
 		TEST_ASSERT(run->exit_reason == KVM_EXIT_IO,
 			    "Unexpected exit reason: %u (%s),\n",
 			    run->exit_reason,

tools/testing/selftests/kvm/x86_64/evmcs_test.c

@@ -19,8 +19,6 @@
 
 #define VCPU_ID		5
 
-static bool have_nested_state;
-
 void l2_guest_code(void)
 {
 	GUEST_SYNC(6);
@@ -73,7 +71,6 @@ void guest_code(struct vmx_pages *vmx_pages)
 
 int main(int argc, char *argv[])
 {
-	struct vmx_pages *vmx_pages = NULL;
 	vm_vaddr_t vmx_pages_gva = 0;
 
 	struct kvm_regs regs1, regs2;
@@ -88,8 +85,6 @@ int main(int argc, char *argv[])
 		 .args[0] = (unsigned long)&evmcs_ver
 	};
 
-	struct kvm_cpuid_entry2 *entry = kvm_get_supported_cpuid_entry(1);
-
 	/* Create VM */
 	vm = vm_create_default(VCPU_ID, 0, guest_code);
 
@@ -113,7 +108,7 @@ int main(int argc, char *argv[])
 
 	vcpu_regs_get(vm, VCPU_ID, &regs1);
 
-	vmx_pages = vcpu_alloc_vmx(vm, &vmx_pages_gva);
+	vcpu_alloc_vmx(vm, &vmx_pages_gva);
 	vcpu_args_set(vm, VCPU_ID, 1, vmx_pages_gva);
 
 	for (stage = 1;; stage++) {

tools/testing/selftests/kvm/x86_64/hyperv_cpuid.c

@@ -52,15 +52,11 @@ static void test_hv_cpuid(struct kvm_cpuid2 *hv_cpuid_entries,
 		TEST_ASSERT(entry->index == 0,
 			    ".index field should be zero");
 
-		TEST_ASSERT(entry->index == 0,
-			    ".index field should be zero");
-
 		TEST_ASSERT(entry->flags == 0,
 			    ".flags field should be zero");
 
-		TEST_ASSERT(entry->padding[0] == entry->padding[1]
+		TEST_ASSERT(!entry->padding[0] && !entry->padding[1] &&
-			    == entry->padding[2] == 0,
+			    !entry->padding[2], "padding should be zero");
-			    ".index field should be zero");
 
 		/*
 		 * If needed for debug:
@@ -90,7 +86,6 @@ struct kvm_cpuid2 *kvm_get_supported_hv_cpuid(struct kvm_vm *vm)
 {
 	int nent = 20; /* should be enough */
 	static struct kvm_cpuid2 *cpuid;
-	int ret;
 
 	cpuid = malloc(sizeof(*cpuid) + nent * sizeof(struct kvm_cpuid_entry2));
 

tools/testing/selftests/kvm/x86_64/platform_info_test.c

@@ -81,7 +81,6 @@ static void test_msr_platform_info_disabled(struct kvm_vm *vm)
 int main(int argc, char *argv[])
 {
 	struct kvm_vm *vm;
-	struct kvm_run *state;
 	int rv;
 	uint64_t msr_platform_info;
 

tools/testing/selftests/kvm/x86_64/smm_test.c

@@ -87,7 +87,6 @@ void guest_code(struct vmx_pages *vmx_pages)
 
 int main(int argc, char *argv[])
 {
-	struct vmx_pages *vmx_pages = NULL;
 	vm_vaddr_t vmx_pages_gva = 0;
 
 	struct kvm_regs regs;
@@ -115,7 +114,7 @@ int main(int argc, char *argv[])
 	vcpu_set_msr(vm, VCPU_ID, MSR_IA32_SMBASE, SMRAM_GPA);
 
 	if (kvm_check_cap(KVM_CAP_NESTED_STATE)) {
-		vmx_pages = vcpu_alloc_vmx(vm, &vmx_pages_gva);
+		vcpu_alloc_vmx(vm, &vmx_pages_gva);
 		vcpu_args_set(vm, VCPU_ID, 1, vmx_pages_gva);
 	} else {
 		printf("will skip SMM test with VMX enabled\n");

tools/testing/selftests/kvm/x86_64/state_test.c

@@ -22,8 +22,6 @@
 
 #define VCPU_ID		5
 
-static bool have_nested_state;
-
 void l2_guest_code(void)
 {
 	GUEST_SYNC(6);
@@ -122,7 +120,6 @@ void guest_code(struct vmx_pages *vmx_pages)
 
 int main(int argc, char *argv[])
 {
-	struct vmx_pages *vmx_pages = NULL;
 	vm_vaddr_t vmx_pages_gva = 0;
 
 	struct kvm_regs regs1, regs2;
@@ -132,8 +129,6 @@ int main(int argc, char *argv[])
 	struct ucall uc;
 	int stage;
 
-	struct kvm_cpuid_entry2 *entry = kvm_get_supported_cpuid_entry(1);
-
 	/* Create VM */
 	vm = vm_create_default(VCPU_ID, 0, guest_code);
 	vcpu_set_cpuid(vm, VCPU_ID, kvm_get_supported_cpuid());
@@ -142,7 +137,7 @@ int main(int argc, char *argv[])
 	vcpu_regs_get(vm, VCPU_ID, &regs1);
 
 	if (kvm_check_cap(KVM_CAP_NESTED_STATE)) {
-		vmx_pages = vcpu_alloc_vmx(vm, &vmx_pages_gva);
+		vcpu_alloc_vmx(vm, &vmx_pages_gva);
 		vcpu_args_set(vm, VCPU_ID, 1, vmx_pages_gva);
 	} else {
 		printf("will skip nested state checks\n");

tools/testing/selftests/kvm/x86_64/sync_regs_test.c

@@ -25,9 +25,15 @@
 
 void guest_code(void)
 {
+	/*
+	 * use a callee-save register, otherwise the compiler
+	 * saves it around the call to GUEST_SYNC.
+	 */
+	register u32 stage asm("rbx");
 	for (;;) {
 		GUEST_SYNC(0);
-		asm volatile ("inc %r11");
+		stage++;
+		asm volatile ("" : : "r" (stage));
 	}
 }
 
@@ -147,7 +153,7 @@ int main(int argc, char *argv[])
 	compare_vcpu_events(&events, &run->s.regs.events);
 
 	/* Set and verify various register values. */
-	run->s.regs.regs.r11 = 0xBAD1DEA;
+	run->s.regs.regs.rbx = 0xBAD1DEA;
 	run->s.regs.sregs.apic_base = 1 << 11;
 	/* TODO run->s.regs.events.XYZ = ABC; */
 
@@ -158,9 +164,9 @@ int main(int argc, char *argv[])
 		    "Unexpected exit reason: %u (%s),\n",
 		    run->exit_reason,
 		    exit_reason_str(run->exit_reason));
-	TEST_ASSERT(run->s.regs.regs.r11 == 0xBAD1DEA + 1,
+	TEST_ASSERT(run->s.regs.regs.rbx == 0xBAD1DEA + 1,
-		    "r11 sync regs value incorrect 0x%llx.",
+		    "rbx sync regs value incorrect 0x%llx.",
-		    run->s.regs.regs.r11);
+		    run->s.regs.regs.rbx);
 	TEST_ASSERT(run->s.regs.sregs.apic_base == 1 << 11,
 		    "apic_base sync regs value incorrect 0x%llx.",
 		    run->s.regs.sregs.apic_base);
@@ -179,15 +185,15 @@ int main(int argc, char *argv[])
 	 */
 	run->kvm_valid_regs = TEST_SYNC_FIELDS;
 	run->kvm_dirty_regs = 0;
-	run->s.regs.regs.r11 = 0xDEADBEEF;
+	run->s.regs.regs.rbx = 0xDEADBEEF;
 	rv = _vcpu_run(vm, VCPU_ID);
 	TEST_ASSERT(run->exit_reason == KVM_EXIT_IO,
 		    "Unexpected exit reason: %u (%s),\n",
 		    run->exit_reason,
 		    exit_reason_str(run->exit_reason));
-	TEST_ASSERT(run->s.regs.regs.r11 != 0xDEADBEEF,
+	TEST_ASSERT(run->s.regs.regs.rbx != 0xDEADBEEF,
-		    "r11 sync regs value incorrect 0x%llx.",
+		    "rbx sync regs value incorrect 0x%llx.",
-		    run->s.regs.regs.r11);
+		    run->s.regs.regs.rbx);
 
 	/* Clear kvm_valid_regs bits and kvm_dirty_bits.
 	 * Verify s.regs values are not overwritten with existing guest values
@@ -195,21 +201,21 @@ int main(int argc, char *argv[])
 	 */
 	run->kvm_valid_regs = 0;
 	run->kvm_dirty_regs = 0;
-	run->s.regs.regs.r11 = 0xAAAA;
+	run->s.regs.regs.rbx = 0xAAAA;
-	regs.r11 = 0xBAC0;
+	regs.rbx = 0xBAC0;
 	vcpu_regs_set(vm, VCPU_ID, &regs);
 	rv = _vcpu_run(vm, VCPU_ID);
 	TEST_ASSERT(run->exit_reason == KVM_EXIT_IO,
 		    "Unexpected exit reason: %u (%s),\n",
 		    run->exit_reason,
 		    exit_reason_str(run->exit_reason));
-	TEST_ASSERT(run->s.regs.regs.r11 == 0xAAAA,
+	TEST_ASSERT(run->s.regs.regs.rbx == 0xAAAA,
-		    "r11 sync regs value incorrect 0x%llx.",
+		    "rbx sync regs value incorrect 0x%llx.",
-		    run->s.regs.regs.r11);
+		    run->s.regs.regs.rbx);
 	vcpu_regs_get(vm, VCPU_ID, &regs);
-	TEST_ASSERT(regs.r11 == 0xBAC0 + 1,
+	TEST_ASSERT(regs.rbx == 0xBAC0 + 1,
-		    "r11 guest value incorrect 0x%llx.",
+		    "rbx guest value incorrect 0x%llx.",
-		    regs.r11);
+		    regs.rbx);
 
 	/* Clear kvm_valid_regs bits. Verify s.regs values are not overwritten
 	 * with existing guest values but that guest values are overwritten
@@ -217,19 +223,19 @@ int main(int argc, char *argv[])
 	 */
 	run->kvm_valid_regs = 0;
 	run->kvm_dirty_regs = TEST_SYNC_FIELDS;
-	run->s.regs.regs.r11 = 0xBBBB;
+	run->s.regs.regs.rbx = 0xBBBB;
 	rv = _vcpu_run(vm, VCPU_ID);
 	TEST_ASSERT(run->exit_reason == KVM_EXIT_IO,
 		    "Unexpected exit reason: %u (%s),\n",
 		    run->exit_reason,
 		    exit_reason_str(run->exit_reason));
-	TEST_ASSERT(run->s.regs.regs.r11 == 0xBBBB,
+	TEST_ASSERT(run->s.regs.regs.rbx == 0xBBBB,
-		    "r11 sync regs value incorrect 0x%llx.",
+		    "rbx sync regs value incorrect 0x%llx.",
-		    run->s.regs.regs.r11);
+		    run->s.regs.regs.rbx);
 	vcpu_regs_get(vm, VCPU_ID, &regs);
-	TEST_ASSERT(regs.r11 == 0xBBBB + 1,
+	TEST_ASSERT(regs.rbx == 0xBBBB + 1,
-		    "r11 guest value incorrect 0x%llx.",
+		    "rbx guest value incorrect 0x%llx.",
-		    regs.r11);
+		    regs.rbx);
 
 	kvm_vm_free(vm);
 

tools/testing/selftests/kvm/x86_64/vmx_close_while_nested_test.c

@@ -39,8 +39,6 @@ static void l1_guest_code(struct vmx_pages *vmx_pages)
 {
 #define L2_GUEST_STACK_SIZE 64
 	unsigned long l2_guest_stack[L2_GUEST_STACK_SIZE];
-	uint32_t control;
-	uintptr_t save_cr3;
 
 	GUEST_ASSERT(prepare_for_vmx_operation(vmx_pages));
 	GUEST_ASSERT(load_vmcs(vmx_pages));
@@ -55,7 +53,6 @@ static void l1_guest_code(struct vmx_pages *vmx_pages)
 
 int main(int argc, char *argv[])
 {
-	struct vmx_pages *vmx_pages;
 	vm_vaddr_t vmx_pages_gva;
 	struct kvm_cpuid_entry2 *entry = kvm_get_supported_cpuid_entry(1);
 
@@ -68,7 +65,7 @@ int main(int argc, char *argv[])
 	vcpu_set_cpuid(vm, VCPU_ID, kvm_get_supported_cpuid());
 
 	/* Allocate VMX pages and shared descriptors (vmx_pages). */
-	vmx_pages = vcpu_alloc_vmx(vm, &vmx_pages_gva);
+	vcpu_alloc_vmx(vm, &vmx_pages_gva);
 	vcpu_args_set(vm, VCPU_ID, 1, vmx_pages_gva);
 
 	for (;;) {

tools/testing/selftests/kvm/x86_64/vmx_set_nested_state_test.c

@@ -75,7 +75,7 @@ void set_revision_id_for_vmcs12(struct kvm_nested_state *state,
 				u32 vmcs12_revision)
 {
 	/* Set revision_id in vmcs12 to vmcs12_revision. */
-	*(u32 *)(state->data) = vmcs12_revision;
+	memcpy(state->data, &vmcs12_revision, sizeof(u32));
 }
 
 void set_default_state(struct kvm_nested_state *state)

tools/testing/selftests/kvm/x86_64/vmx_tsc_adjust_test.c

@@ -121,7 +121,7 @@ static void l1_guest_code(struct vmx_pages *vmx_pages)
 	GUEST_DONE();
 }
 
-void report(int64_t val)
+static void report(int64_t val)
 {
 	printf("IA32_TSC_ADJUST is %ld (%lld * TSC_ADJUST_VALUE + %lld).\n",
 	       val, val / TSC_ADJUST_VALUE, val % TSC_ADJUST_VALUE);
@@ -129,7 +129,6 @@ void report(int64_t val)
 
 int main(int argc, char *argv[])
 {
-	struct vmx_pages *vmx_pages;
 	vm_vaddr_t vmx_pages_gva;
 	struct kvm_cpuid_entry2 *entry = kvm_get_supported_cpuid_entry(1);
 
@@ -142,7 +141,7 @@ int main(int argc, char *argv[])
 	vcpu_set_cpuid(vm, VCPU_ID, kvm_get_supported_cpuid());
 
 	/* Allocate VMX pages and shared descriptors (vmx_pages). */
-	vmx_pages = vcpu_alloc_vmx(vm, &vmx_pages_gva);
+	vcpu_alloc_vmx(vm, &vmx_pages_gva);
 	vcpu_args_set(vm, VCPU_ID, 1, vmx_pages_gva);
 
 	for (;;) {

virt/kvm/arm/aarch32.c

@@ -25,127 +25,6 @@
 #include <asm/kvm_emulate.h>
 #include <asm/kvm_hyp.h>
 
-/*
- * stolen from arch/arm/kernel/opcodes.c
- *
- * condition code lookup table
- * index into the table is test code: EQ, NE, ... LT, GT, AL, NV
- *
- * bit position in short is condition code: NZCV
- */
-static const unsigned short cc_map[16] = {
-	0xF0F0,			/* EQ == Z set            */
-	0x0F0F,			/* NE                     */
-	0xCCCC,			/* CS == C set            */
-	0x3333,			/* CC                     */
-	0xFF00,			/* MI == N set            */
-	0x00FF,			/* PL                     */
-	0xAAAA,			/* VS == V set            */
-	0x5555,			/* VC                     */
-	0x0C0C,			/* HI == C set && Z clear */
-	0xF3F3,			/* LS == C clear || Z set */
-	0xAA55,			/* GE == (N==V)           */
-	0x55AA,			/* LT == (N!=V)           */
-	0x0A05,			/* GT == (!Z && (N==V))   */
-	0xF5FA,			/* LE == (Z || (N!=V))    */
-	0xFFFF,			/* AL always              */
-	0			/* NV                     */
-};
-
-/*
- * Check if a trapped instruction should have been executed or not.
- */
-bool __hyp_text kvm_condition_valid32(const struct kvm_vcpu *vcpu)
-{
-	unsigned long cpsr;
-	u32 cpsr_cond;
-	int cond;
-
-	/* Top two bits non-zero?  Unconditional. */
-	if (kvm_vcpu_get_hsr(vcpu) >> 30)
-		return true;
-
-	/* Is condition field valid? */
-	cond = kvm_vcpu_get_condition(vcpu);
-	if (cond == 0xE)
-		return true;
-
-	cpsr = *vcpu_cpsr(vcpu);
-
-	if (cond < 0) {
-		/* This can happen in Thumb mode: examine IT state. */
-		unsigned long it;
-
-		it = ((cpsr >> 8) & 0xFC) | ((cpsr >> 25) & 0x3);
-
-		/* it == 0 => unconditional. */
-		if (it == 0)
-			return true;
-
-		/* The cond for this insn works out as the top 4 bits. */
-		cond = (it >> 4);
-	}
-
-	cpsr_cond = cpsr >> 28;
-
-	if (!((cc_map[cond] >> cpsr_cond) & 1))
-		return false;
-
-	return true;
-}
-
-/**
- * adjust_itstate - adjust ITSTATE when emulating instructions in IT-block
- * @vcpu:	The VCPU pointer
- *
- * When exceptions occur while instructions are executed in Thumb IF-THEN
- * blocks, the ITSTATE field of the CPSR is not advanced (updated), so we have
- * to do this little bit of work manually. The fields map like this:
- *
- * IT[7:0] -> CPSR[26:25],CPSR[15:10]
- */
-static void __hyp_text kvm_adjust_itstate(struct kvm_vcpu *vcpu)
-{
-	unsigned long itbits, cond;
-	unsigned long cpsr = *vcpu_cpsr(vcpu);
-	bool is_arm = !(cpsr & PSR_AA32_T_BIT);
-
-	if (is_arm || !(cpsr & PSR_AA32_IT_MASK))
-		return;
-
-	cond = (cpsr & 0xe000) >> 13;
-	itbits = (cpsr & 0x1c00) >> (10 - 2);
-	itbits |= (cpsr & (0x3 << 25)) >> 25;
-
-	/* Perform ITAdvance (see page A2-52 in ARM DDI 0406C) */
-	if ((itbits & 0x7) == 0)
-		itbits = cond = 0;
-	else
-		itbits = (itbits << 1) & 0x1f;
-
-	cpsr &= ~PSR_AA32_IT_MASK;
-	cpsr |= cond << 13;
-	cpsr |= (itbits & 0x1c) << (10 - 2);
-	cpsr |= (itbits & 0x3) << 25;
-	*vcpu_cpsr(vcpu) = cpsr;
-}
-
-/**
- * kvm_skip_instr - skip a trapped instruction and proceed to the next
- * @vcpu: The vcpu pointer
- */
-void __hyp_text kvm_skip_instr32(struct kvm_vcpu *vcpu, bool is_wide_instr)
-{
-	bool is_thumb;
-
-	is_thumb = !!(*vcpu_cpsr(vcpu) & PSR_AA32_T_BIT);
-	if (is_thumb && !is_wide_instr)
-		*vcpu_pc(vcpu) += 2;
-	else
-		*vcpu_pc(vcpu) += 4;
-	kvm_adjust_itstate(vcpu);
-}
-
 /*
  * Table taken from ARMv8 ARM DDI0487B-B, table G1-10.
  */

virt/kvm/arm/hyp/aarch32.c

@@ -0,0 +1,136 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Hyp portion of the (not much of an) Emulation layer for 32bit guests.
+ *
+ * Copyright (C) 2012,2013 - ARM Ltd
+ * Author: Marc Zyngier <marc.zyngier@arm.com>
+ *
+ * based on arch/arm/kvm/emulate.c
+ * Copyright (C) 2012 - Virtual Open Systems and Columbia University
+ * Author: Christoffer Dall <c.dall@virtualopensystems.com>
+ */
+
+#include <linux/kvm_host.h>
+#include <asm/kvm_emulate.h>
+#include <asm/kvm_hyp.h>
+
+/*
+ * stolen from arch/arm/kernel/opcodes.c
+ *
+ * condition code lookup table
+ * index into the table is test code: EQ, NE, ... LT, GT, AL, NV
+ *
+ * bit position in short is condition code: NZCV
+ */
+static const unsigned short cc_map[16] = {
+	0xF0F0,			/* EQ == Z set            */
+	0x0F0F,			/* NE                     */
+	0xCCCC,			/* CS == C set            */
+	0x3333,			/* CC                     */
+	0xFF00,			/* MI == N set            */
+	0x00FF,			/* PL                     */
+	0xAAAA,			/* VS == V set            */
+	0x5555,			/* VC                     */
+	0x0C0C,			/* HI == C set && Z clear */
+	0xF3F3,			/* LS == C clear || Z set */
+	0xAA55,			/* GE == (N==V)           */
+	0x55AA,			/* LT == (N!=V)           */
+	0x0A05,			/* GT == (!Z && (N==V))   */
+	0xF5FA,			/* LE == (Z || (N!=V))    */
+	0xFFFF,			/* AL always              */
+	0			/* NV                     */
+};
+
+/*
+ * Check if a trapped instruction should have been executed or not.
+ */
+bool __hyp_text kvm_condition_valid32(const struct kvm_vcpu *vcpu)
+{
+	unsigned long cpsr;
+	u32 cpsr_cond;
+	int cond;
+
+	/* Top two bits non-zero?  Unconditional. */
+	if (kvm_vcpu_get_hsr(vcpu) >> 30)
+		return true;
+
+	/* Is condition field valid? */
+	cond = kvm_vcpu_get_condition(vcpu);
+	if (cond == 0xE)
+		return true;
+
+	cpsr = *vcpu_cpsr(vcpu);
+
+	if (cond < 0) {
+		/* This can happen in Thumb mode: examine IT state. */
+		unsigned long it;
+
+		it = ((cpsr >> 8) & 0xFC) | ((cpsr >> 25) & 0x3);
+
+		/* it == 0 => unconditional. */
+		if (it == 0)
+			return true;
+
+		/* The cond for this insn works out as the top 4 bits. */
+		cond = (it >> 4);
+	}
+
+	cpsr_cond = cpsr >> 28;
+
+	if (!((cc_map[cond] >> cpsr_cond) & 1))
+		return false;
+
+	return true;
+}
+
+/**
+ * adjust_itstate - adjust ITSTATE when emulating instructions in IT-block
+ * @vcpu:	The VCPU pointer
+ *
+ * When exceptions occur while instructions are executed in Thumb IF-THEN
+ * blocks, the ITSTATE field of the CPSR is not advanced (updated), so we have
+ * to do this little bit of work manually. The fields map like this:
+ *
+ * IT[7:0] -> CPSR[26:25],CPSR[15:10]
+ */
+static void __hyp_text kvm_adjust_itstate(struct kvm_vcpu *vcpu)
+{
+	unsigned long itbits, cond;
+	unsigned long cpsr = *vcpu_cpsr(vcpu);
+	bool is_arm = !(cpsr & PSR_AA32_T_BIT);
+
+	if (is_arm || !(cpsr & PSR_AA32_IT_MASK))
+		return;
+
+	cond = (cpsr & 0xe000) >> 13;
+	itbits = (cpsr & 0x1c00) >> (10 - 2);
+	itbits |= (cpsr & (0x3 << 25)) >> 25;
+
+	/* Perform ITAdvance (see page A2-52 in ARM DDI 0406C) */
+	if ((itbits & 0x7) == 0)
+		itbits = cond = 0;
+	else
+		itbits = (itbits << 1) & 0x1f;
+
+	cpsr &= ~PSR_AA32_IT_MASK;
+	cpsr |= cond << 13;
+	cpsr |= (itbits & 0x1c) << (10 - 2);
+	cpsr |= (itbits & 0x3) << 25;
+	*vcpu_cpsr(vcpu) = cpsr;
+}
+
+/**
+ * kvm_skip_instr - skip a trapped instruction and proceed to the next
+ * @vcpu: The vcpu pointer
+ */
+void __hyp_text kvm_skip_instr32(struct kvm_vcpu *vcpu, bool is_wide_instr)
+{
+	bool is_thumb;
+
+	is_thumb = !!(*vcpu_cpsr(vcpu) & PSR_AA32_T_BIT);
+	if (is_thumb && !is_wide_instr)
+		*vcpu_pc(vcpu) += 2;
+	else
+		*vcpu_pc(vcpu) += 4;
+	kvm_adjust_itstate(vcpu);
+}

virt/kvm/eventfd.c

@@ -44,6 +44,12 @@
 
 static struct workqueue_struct *irqfd_cleanup_wq;
 
+bool __attribute__((weak))
+kvm_arch_irqfd_allowed(struct kvm *kvm, struct kvm_irqfd *args)
+{
+	return true;
+}
+
 static void
 irqfd_inject(struct work_struct *work)
 {
@@ -297,6 +303,9 @@ kvm_irqfd_assign(struct kvm *kvm, struct kvm_irqfd *args)
 	if (!kvm_arch_intc_initialized(kvm))
 		return -EAGAIN;
 
+	if (!kvm_arch_irqfd_allowed(kvm, args))
+		return -EINVAL;
+
 	irqfd = kzalloc(sizeof(*irqfd), GFP_KERNEL_ACCOUNT);
 	if (!irqfd)
 		return -ENOMEM;

virt/kvm/kvm_main.c

@@ -52,6 +52,7 @@
 #include <linux/sort.h>
 #include <linux/bsearch.h>
 #include <linux/io.h>
+#include <linux/lockdep.h>
 
 #include <asm/processor.h>
 #include <asm/ioctl.h>
@@ -1760,8 +1761,10 @@ static int __kvm_map_gfn(struct kvm_memory_slot *slot, gfn_t gfn,
 	if (pfn_valid(pfn)) {
 		page = pfn_to_page(pfn);
 		hva = kmap(page);
+#ifdef CONFIG_HAS_IOMEM
 	} else {
 		hva = memremap(pfn_to_hpa(pfn), PAGE_SIZE, MEMREMAP_WB);
+#endif
 	}
 
 	if (!hva)
@@ -4181,7 +4184,9 @@ static int kvm_suspend(void)
 static void kvm_resume(void)
 {
 	if (kvm_usage_count) {
-		lockdep_assert_held(&kvm_count_lock);
+#ifdef CONFIG_LOCKDEP
+		WARN_ON(lockdep_is_held(&kvm_count_lock));
+#endif
 		hardware_enable_nolock(NULL);
 	}
 }