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
  ...

13 files changed, 109 insertions, 49 deletions

diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c
index 80a642a0143d..e18a9f9f65b5 100644
--- a/arch/x86/kvm/cpuid.c
+++ b/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. */
-	case 4: {
+	/* functions 4 and 0x8000001d have additional index. */
+	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 0x8000001d:
+	case 0x8000001e:
 		break;
 	/*Add support for Centaur's CPUID instruction*/
 	case 0xC0000000:
diff --git a/arch/x86/kvm/debugfs.c b/arch/x86/kvm/debugfs.c
index c19c7ede9bd6..a2f3432ce090 100644
--- a/arch/x86/kvm/debugfs.c
+++ b/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,
diff --git a/arch/x86/kvm/irq.c b/arch/x86/kvm/irq.c
index faa264822cee..007bc654f928 100644
--- a/arch/x86/kvm/irq.c
+++ b/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);
+}
diff --git a/arch/x86/kvm/irq.h b/arch/x86/kvm/irq.h
index d5005cc26521..fd210cdd4983 100644
--- a/arch/x86/kvm/irq.h
+++ b/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);
diff --git a/arch/x86/kvm/pmu.c b/arch/x86/kvm/pmu.c
index e39741997893..dd745b58ffd8 100644
--- a/arch/x86/kvm/pmu.c
+++ b/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);
-	if (fast_mode)
-		ctr_val = (u32)ctr_val;
-
-	*data = ctr_val;
+	*data = pmc_read_counter(pmc) & mask;
 	return 0;
 }
 
diff --git a/arch/x86/kvm/pmu.h b/arch/x86/kvm/pmu.h
index ba8898e1a854..22dff661145a 100644
--- a/arch/x86/kvm/pmu.h
+++ b/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);
diff --git a/arch/x86/kvm/pmu_amd.c b/arch/x86/kvm/pmu_amd.c
index 1495a735b38e..d3118088f1cd 100644
--- a/arch/x86/kvm/pmu_amd.c
+++ b/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;
 }
 
diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
index a849dcb7fbc5..735b8c01895e 100644
--- a/arch/x86/kvm/svm.c
+++ b/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;
 	}
diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c
index f1a69117ac0f..1032f068f0b9 100644
--- a/arch/x86/kvm/vmx/nested.c
+++ b/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))
-			return -EINVAL;
+		if (kvm_state->size < sizeof(*kvm_state) + VMCS12_SIZE + sizeof(*vmcs12))
+			goto error_guest_mode;
 
 		if (copy_from_user(shadow_vmcs12,
 				   user_kvm_nested_state->data + VMCS12_SIZE,
-				   sizeof(*vmcs12)))
-			return -EFAULT;
+				   sizeof(*vmcs12))) {
+			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) {
-		vmx->nested.nested_run_pending = 0;
-		return -EINVAL;
-	}
+	if (ret)
+		goto error_guest_mode;
 
 	return 0;
+
+error_guest_mode:
+	vmx->nested.nested_run_pending = 0;
+	return ret;
 }
 
 void nested_vmx_vcpu_setup(void)
diff --git a/arch/x86/kvm/vmx/pmu_intel.c b/arch/x86/kvm/vmx/pmu_intel.c
index f8502c376b37..a99613a060dd 100644
--- a/arch/x86/kvm/vmx/pmu_intel.c
+++ b/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)) ||
-		    (pmc = get_fixed_pmc(pmu, msr))) {
-			*data = pmc_read_counter(pmc);
+		if ((pmc = get_gp_pmc(pmu, msr, MSR_IA32_PERFCTR0))) {
+			u64 val = 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)) ||
-		    (pmc = get_fixed_pmc(pmu, msr))) {
-			if (!msr_info->host_initiated)
-				data = (s64)(s32)data;
-			pmc->counter += data - pmc_read_counter(pmc);
+		if ((pmc = get_gp_pmc(pmu, msr, MSR_IA32_PERFCTR0))) {
+			if (msr_info->host_initiated)
+				pmc->counter = data;
+			else
+				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)
diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index 1ac167614032..b93e36ddee5e 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/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 vmexit_ctl = vmcs_read32(VM_EXIT_CONTROLS);
-	u32 cpu_based_exec_ctrl = vmcs_read32(CPU_BASED_VM_EXEC_CONTROL);
-	u32 pin_based_exec_ctrl = vmcs_read32(PIN_BASED_VM_EXEC_CONTROL);
-	u32 secondary_exec_control = 0;
-	unsigned long cr4 = vmcs_readl(GUEST_CR4);
-	u64 efer = vmcs_read64(GUEST_IA32_EFER);
+	u32 vmentry_ctl, vmexit_ctl;
+	u32 cpu_based_exec_ctrl, pin_based_exec_ctrl, secondary_exec_control;
+	unsigned long cr4;
+	u64 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);
 
diff --git a/arch/x86/kvm/vmx/vmx.h b/arch/x86/kvm/vmx/vmx.h
index 63d37ccce3dc..61128b48c503 100644
--- a/arch/x86/kvm/vmx/vmx.h
+++ b/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
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 536b78c4af6e..acb179f78fdc 100644
--- a/arch/x86/kvm/x86.c
+++ b/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))