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

Pull KVM updates from Paolo Bonzini: "s390: - ioctl hardening - selftests ARM: - ITS translation cache - support for 512 vCPUs - various cleanups and bugfixes PPC: - various minor fixes and preparation x86: - bugfixes all over the place (posted interrupts, SVM, emulation corner cases, blocked INIT) - some IPI optimizations" * tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (75 commits) KVM: X86: Use IPI shorthands in kvm guest when support KVM: x86: Fix INIT signal handling in various CPU states KVM: VMX: Introduce exit reason for receiving INIT signal on guest-mode KVM: VMX: Stop the preemption timer during vCPU reset KVM: LAPIC: Micro optimize IPI latency kvm: Nested KVM MMUs need PAE root too KVM: x86: set ctxt->have_exception in x86_decode_insn() KVM: x86: always stop emulation on page fault KVM: nVMX: trace nested VM-Enter failures detected by H/W KVM: nVMX: add tracepoint for failed nested VM-Enter x86: KVM: svm: Fix a check in nested_svm_vmrun() KVM: x86: Return to userspace with internal error on unexpected exit reason KVM: x86: Add kvm_emulate_{rd,wr}msr() to consolidate VXM/SVM code KVM: x86: Refactor up kvm_{g,s}et_msr() to simplify callers doc: kvm: Fix return description of KVM_SET_MSRS KVM: X86: Tune PLE Window tracepoint KVM: VMX: Change ple_window type to unsigned int KVM: X86: Remove tailing newline for tracepoints KVM: X86: Trace vcpu_id for vmexit KVM: x86: Manually calculate reserved bits when loading PDPTRS ...
2019-09-18 09:49:13 -07:00
parent 404e634fdb fb3925d06c
commit fe38bd6862
63 changed files with 1701 additions and 804 deletions
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -68,10 +68,8 @@ MODULE_DEVICE_TABLE(x86cpu, svm_cpu_id);
 #define SEG_TYPE_LDT 2
 #define SEG_TYPE_BUSY_TSS16 3

-#define SVM_FEATURE_NPT            (1 <<  0)
 #define SVM_FEATURE_LBRV           (1 <<  1)
 #define SVM_FEATURE_SVML           (1 <<  2)
-#define SVM_FEATURE_NRIP           (1 <<  3)
 #define SVM_FEATURE_TSC_RATE       (1 <<  4)
 #define SVM_FEATURE_VMCB_CLEAN     (1 <<  5)
 #define SVM_FEATURE_FLUSH_ASID     (1 <<  6)
@@ -770,7 +768,7 @@ static void svm_set_interrupt_shadow(struct kvm_vcpu *vcpu, int mask)

 }

-static void skip_emulated_instruction(struct kvm_vcpu *vcpu)
+static int skip_emulated_instruction(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_svm *svm = to_svm(vcpu);

@@ -779,18 +777,17 @@ static void skip_emulated_instruction(struct kvm_vcpu *vcpu)
 		svm->next_rip = svm->vmcb->control.next_rip;
 	}

-	if (!svm->next_rip) {
-		if (kvm_emulate_instruction(vcpu, EMULTYPE_SKIP) !=
-				EMULATE_DONE)
-			printk(KERN_DEBUG "%s: NOP\n", __func__);
-		return;
-	}
+	if (!svm->next_rip)
+		return kvm_emulate_instruction(vcpu, EMULTYPE_SKIP);
+
 	if (svm->next_rip - kvm_rip_read(vcpu) > MAX_INST_SIZE)
 		printk(KERN_ERR "%s: ip 0x%lx next 0x%llx\n",
 		       __func__, kvm_rip_read(vcpu), svm->next_rip);

 	kvm_rip_write(vcpu, svm->next_rip);
 	svm_set_interrupt_shadow(vcpu, 0);
+
+	return EMULATE_DONE;
 }

 static void svm_queue_exception(struct kvm_vcpu *vcpu)
@@ -821,7 +818,7 @@ static void svm_queue_exception(struct kvm_vcpu *vcpu)
 		 * raises a fault that is not intercepted. Still better than
 		 * failing in all cases.
 		 */
-		skip_emulated_instruction(&svm->vcpu);
+		(void)skip_emulated_instruction(&svm->vcpu);
 		rip = kvm_rip_read(&svm->vcpu);
 		svm->int3_rip = rip + svm->vmcb->save.cs.base;
 		svm->int3_injected = rip - old_rip;
@@ -1269,11 +1266,11 @@ static void grow_ple_window(struct kvm_vcpu *vcpu)
 							pause_filter_count_grow,
 							pause_filter_count_max);

-	if (control->pause_filter_count != old)
+	if (control->pause_filter_count != old) {
 		mark_dirty(svm->vmcb, VMCB_INTERCEPTS);
-
-	trace_kvm_ple_window_grow(vcpu->vcpu_id,
-				  control->pause_filter_count, old);
+		trace_kvm_ple_window_update(vcpu->vcpu_id,
+					    control->pause_filter_count, old);
+	}
 }

 static void shrink_ple_window(struct kvm_vcpu *vcpu)
@@ -1287,11 +1284,11 @@ static void shrink_ple_window(struct kvm_vcpu *vcpu)
 						    pause_filter_count,
 						    pause_filter_count_shrink,
 						    pause_filter_count);
-	if (control->pause_filter_count != old)
+	if (control->pause_filter_count != old) {
 		mark_dirty(svm->vmcb, VMCB_INTERCEPTS);
-
-	trace_kvm_ple_window_shrink(vcpu->vcpu_id,
-				    control->pause_filter_count, old);
+		trace_kvm_ple_window_update(vcpu->vcpu_id,
+					    control->pause_filter_count, old);
+	}
 }

 static __init int svm_hardware_setup(void)
@@ -2136,6 +2133,9 @@ static struct kvm_vcpu *svm_create_vcpu(struct kvm *kvm, unsigned int id)
 	struct page *nested_msrpm_pages;
 	int err;

+	BUILD_BUG_ON_MSG(offsetof(struct vcpu_svm, vcpu) != 0,
+		"struct kvm_vcpu must be at offset 0 for arch usercopy region");
+
 	svm = kmem_cache_zalloc(kvm_vcpu_cache, GFP_KERNEL_ACCOUNT);
 	if (!svm) {
 		err = -ENOMEM;
@@ -2903,13 +2903,11 @@ static int nop_on_interception(struct vcpu_svm *svm)

 static int halt_interception(struct vcpu_svm *svm)
 {
-	svm->next_rip = kvm_rip_read(&svm->vcpu) + 1;
 	return kvm_emulate_halt(&svm->vcpu);
 }

 static int vmmcall_interception(struct vcpu_svm *svm)
 {
-	svm->next_rip = kvm_rip_read(&svm->vcpu) + 3;
 	return kvm_emulate_hypercall(&svm->vcpu);
 }

@@ -3588,9 +3586,9 @@ static void enter_svm_guest_mode(struct vcpu_svm *svm, u64 vmcb_gpa,
 	mark_all_dirty(svm->vmcb);
 }

-static bool nested_svm_vmrun(struct vcpu_svm *svm)
+static int nested_svm_vmrun(struct vcpu_svm *svm)
 {
-	int rc;
+	int ret;
 	struct vmcb *nested_vmcb;
 	struct vmcb *hsave = svm->nested.hsave;
 	struct vmcb *vmcb = svm->vmcb;
@@ -3599,13 +3597,16 @@ static bool nested_svm_vmrun(struct vcpu_svm *svm)

 	vmcb_gpa = svm->vmcb->save.rax;

-	rc = kvm_vcpu_map(&svm->vcpu, gpa_to_gfn(vmcb_gpa), &map);
-	if (rc) {
-		if (rc == -EINVAL)
-			kvm_inject_gp(&svm->vcpu, 0);
-		return false;
+	ret = kvm_vcpu_map(&svm->vcpu, gpa_to_gfn(vmcb_gpa), &map);
+	if (ret == -EINVAL) {
+		kvm_inject_gp(&svm->vcpu, 0);
+		return 1;
+	} else if (ret) {
+		return kvm_skip_emulated_instruction(&svm->vcpu);
 	}

+	ret = kvm_skip_emulated_instruction(&svm->vcpu);
+
 	nested_vmcb = map.hva;

 	if (!nested_vmcb_checks(nested_vmcb)) {
@@ -3616,7 +3617,7 @@ static bool nested_svm_vmrun(struct vcpu_svm *svm)

 		kvm_vcpu_unmap(&svm->vcpu, &map, true);

-		return false;
+		return ret;
 	}

 	trace_kvm_nested_vmrun(svm->vmcb->save.rip, vmcb_gpa,
@@ -3660,7 +3661,16 @@ static bool nested_svm_vmrun(struct vcpu_svm *svm)

 	enter_svm_guest_mode(svm, vmcb_gpa, nested_vmcb, &map);

-	return true;
+	if (!nested_svm_vmrun_msrpm(svm)) {
+		svm->vmcb->control.exit_code    = SVM_EXIT_ERR;
+		svm->vmcb->control.exit_code_hi = 0;
+		svm->vmcb->control.exit_info_1  = 0;
+		svm->vmcb->control.exit_info_2  = 0;
+
+		nested_svm_vmexit(svm);
+	}
+
+	return ret;
 }

 static void nested_svm_vmloadsave(struct vmcb *from_vmcb, struct vmcb *to_vmcb)
@@ -3697,7 +3707,6 @@ static int vmload_interception(struct vcpu_svm *svm)

 	nested_vmcb = map.hva;

-	svm->next_rip = kvm_rip_read(&svm->vcpu) + 3;
 	ret = kvm_skip_emulated_instruction(&svm->vcpu);

 	nested_svm_vmloadsave(nested_vmcb, svm->vmcb);
@@ -3724,7 +3733,6 @@ static int vmsave_interception(struct vcpu_svm *svm)

 	nested_vmcb = map.hva;

-	svm->next_rip = kvm_rip_read(&svm->vcpu) + 3;
 	ret = kvm_skip_emulated_instruction(&svm->vcpu);

 	nested_svm_vmloadsave(svm->vmcb, nested_vmcb);
@@ -3738,27 +3746,7 @@ static int vmrun_interception(struct vcpu_svm *svm)
 	if (nested_svm_check_permissions(svm))
 		return 1;

-	/* Save rip after vmrun instruction */
-	kvm_rip_write(&svm->vcpu, kvm_rip_read(&svm->vcpu) + 3);
-
-	if (!nested_svm_vmrun(svm))
-		return 1;
-
-	if (!nested_svm_vmrun_msrpm(svm))
-		goto failed;
-
-	return 1;
-
-failed:
-
-	svm->vmcb->control.exit_code    = SVM_EXIT_ERR;
-	svm->vmcb->control.exit_code_hi = 0;
-	svm->vmcb->control.exit_info_1  = 0;
-	svm->vmcb->control.exit_info_2  = 0;
-
-	nested_svm_vmexit(svm);
-
-	return 1;
+	return nested_svm_vmrun(svm);
 }

 static int stgi_interception(struct vcpu_svm *svm)
@@ -3775,7 +3763,6 @@ static int stgi_interception(struct vcpu_svm *svm)
 	if (vgif_enabled(svm))
 		clr_intercept(svm, INTERCEPT_STGI);

-	svm->next_rip = kvm_rip_read(&svm->vcpu) + 3;
 	ret = kvm_skip_emulated_instruction(&svm->vcpu);
 	kvm_make_request(KVM_REQ_EVENT, &svm->vcpu);

@@ -3791,7 +3778,6 @@ static int clgi_interception(struct vcpu_svm *svm)
 	if (nested_svm_check_permissions(svm))
 		return 1;

-	svm->next_rip = kvm_rip_read(&svm->vcpu) + 3;
 	ret = kvm_skip_emulated_instruction(&svm->vcpu);

 	disable_gif(svm);
@@ -3816,7 +3802,6 @@ static int invlpga_interception(struct vcpu_svm *svm)
 	/* Let's treat INVLPGA the same as INVLPG (can be optimized!) */
 	kvm_mmu_invlpg(vcpu, kvm_rax_read(&svm->vcpu));

-	svm->next_rip = kvm_rip_read(&svm->vcpu) + 3;
 	return kvm_skip_emulated_instruction(&svm->vcpu);
 }

@@ -3839,7 +3824,6 @@ static int xsetbv_interception(struct vcpu_svm *svm)
 	u32 index = kvm_rcx_read(&svm->vcpu);

 	if (kvm_set_xcr(&svm->vcpu, index, new_bv) == 0) {
-		svm->next_rip = kvm_rip_read(&svm->vcpu) + 3;
 		return kvm_skip_emulated_instruction(&svm->vcpu);
 	}

@@ -3898,25 +3882,29 @@ static int task_switch_interception(struct vcpu_svm *svm)
 	if (reason != TASK_SWITCH_GATE ||
 	    int_type == SVM_EXITINTINFO_TYPE_SOFT ||
 	    (int_type == SVM_EXITINTINFO_TYPE_EXEPT &&
-	     (int_vec == OF_VECTOR || int_vec == BP_VECTOR)))
-		skip_emulated_instruction(&svm->vcpu);
+	     (int_vec == OF_VECTOR || int_vec == BP_VECTOR))) {
+		if (skip_emulated_instruction(&svm->vcpu) != EMULATE_DONE)
+			goto fail;
+	}

 	if (int_type != SVM_EXITINTINFO_TYPE_SOFT)
 		int_vec = -1;

 	if (kvm_task_switch(&svm->vcpu, tss_selector, int_vec, reason,
-				has_error_code, error_code) == EMULATE_FAIL) {
-		svm->vcpu.run->exit_reason = KVM_EXIT_INTERNAL_ERROR;
-		svm->vcpu.run->internal.suberror = KVM_INTERNAL_ERROR_EMULATION;
-		svm->vcpu.run->internal.ndata = 0;
-		return 0;
-	}
+				has_error_code, error_code) == EMULATE_FAIL)
+		goto fail;
+
 	return 1;
+
+fail:
+	svm->vcpu.run->exit_reason = KVM_EXIT_INTERNAL_ERROR;
+	svm->vcpu.run->internal.suberror = KVM_INTERNAL_ERROR_EMULATION;
+	svm->vcpu.run->internal.ndata = 0;
+	return 0;
 }

 static int cpuid_interception(struct vcpu_svm *svm)
 {
-	svm->next_rip = kvm_rip_read(&svm->vcpu) + 2;
 	return kvm_emulate_cpuid(&svm->vcpu);
 }

@@ -4232,23 +4220,7 @@ static int svm_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)

 static int rdmsr_interception(struct vcpu_svm *svm)
 {
-	u32 ecx = kvm_rcx_read(&svm->vcpu);
-	struct msr_data msr_info;
-
-	msr_info.index = ecx;
-	msr_info.host_initiated = false;
-	if (svm_get_msr(&svm->vcpu, &msr_info)) {
-		trace_kvm_msr_read_ex(ecx);
-		kvm_inject_gp(&svm->vcpu, 0);
-		return 1;
-	} else {
-		trace_kvm_msr_read(ecx, msr_info.data);
-
-		kvm_rax_write(&svm->vcpu, msr_info.data & 0xffffffff);
-		kvm_rdx_write(&svm->vcpu, msr_info.data >> 32);
-		svm->next_rip = kvm_rip_read(&svm->vcpu) + 2;
-		return kvm_skip_emulated_instruction(&svm->vcpu);
-	}
+	return kvm_emulate_rdmsr(&svm->vcpu);
 }

 static int svm_set_vm_cr(struct kvm_vcpu *vcpu, u64 data)
@@ -4438,23 +4410,7 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr)

 static int wrmsr_interception(struct vcpu_svm *svm)
 {
-	struct msr_data msr;
-	u32 ecx = kvm_rcx_read(&svm->vcpu);
-	u64 data = kvm_read_edx_eax(&svm->vcpu);
-
-	msr.data = data;
-	msr.index = ecx;
-	msr.host_initiated = false;
-
-	svm->next_rip = kvm_rip_read(&svm->vcpu) + 2;
-	if (kvm_set_msr(&svm->vcpu, &msr)) {
-		trace_kvm_msr_write_ex(ecx, data);
-		kvm_inject_gp(&svm->vcpu, 0);
-		return 1;
-	} else {
-		trace_kvm_msr_write(ecx, data);
-		return kvm_skip_emulated_instruction(&svm->vcpu);
-	}
+	return kvm_emulate_wrmsr(&svm->vcpu);
 }

 static int msr_interception(struct vcpu_svm *svm)
@@ -5025,9 +4981,14 @@ static int handle_exit(struct kvm_vcpu *vcpu)

 	if (exit_code >= ARRAY_SIZE(svm_exit_handlers)
 	    || !svm_exit_handlers[exit_code]) {
-		WARN_ONCE(1, "svm: unexpected exit reason 0x%x\n", exit_code);
-		kvm_queue_exception(vcpu, UD_VECTOR);
-		return 1;
+		vcpu_unimpl(vcpu, "svm: unexpected exit reason 0x%x\n", exit_code);
+		dump_vmcb(vcpu);
+		vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR;
+		vcpu->run->internal.suberror =
+			KVM_INTERNAL_ERROR_UNEXPECTED_EXIT_REASON;
+		vcpu->run->internal.ndata = 1;
+		vcpu->run->internal.data[0] = exit_code;
+		return 0;
 	}

 	return svm_exit_handlers[exit_code](svm);
@@ -5274,7 +5235,8 @@ get_pi_vcpu_info(struct kvm *kvm, struct kvm_kernel_irq_routing_entry *e,

 	kvm_set_msi_irq(kvm, e, &irq);

-	if (!kvm_intr_is_single_vcpu(kvm, &irq, &vcpu)) {
+	if (!kvm_intr_is_single_vcpu(kvm, &irq, &vcpu) ||
+	    !kvm_irq_is_postable(&irq)) {
 		pr_debug("SVM: %s: use legacy intr remap mode for irq %u\n",
 			 __func__, irq.vector);
 		return -1;
@@ -5328,6 +5290,7 @@ static int svm_update_pi_irte(struct kvm *kvm, unsigned int host_irq,
 		 * 1. When cannot target interrupt to a specific vcpu.
 		 * 2. Unsetting posted interrupt.
 		 * 3. APIC virtialization is disabled for the vcpu.
+		 * 4. IRQ has incompatible delivery mode (SMI, INIT, etc)
 		 */
 		if (!get_pi_vcpu_info(kvm, e, &vcpu_info, &svm) && set &&
 		    kvm_vcpu_apicv_active(&svm->vcpu)) {
@@ -5933,6 +5896,8 @@ static void svm_cpuid_update(struct kvm_vcpu *vcpu)
 	guest_cpuid_clear(vcpu, X86_FEATURE_X2APIC);
 }

+#define F(x) bit(X86_FEATURE_##x)
+
 static void svm_set_supported_cpuid(u32 func, struct kvm_cpuid_entry2 *entry)
 {
 	switch (func) {
@@ -5944,6 +5909,11 @@ static void svm_set_supported_cpuid(u32 func, struct kvm_cpuid_entry2 *entry)
 		if (nested)
 			entry->ecx |= (1 << 2); /* Set SVM bit */
 		break;
+	case 0x80000008:
+		if (boot_cpu_has(X86_FEATURE_LS_CFG_SSBD) ||
+		     boot_cpu_has(X86_FEATURE_AMD_SSBD))
+			entry->ebx |= F(VIRT_SSBD);
+		break;
 	case 0x8000000A:
 		entry->eax = 1; /* SVM revision 1 */
 		entry->ebx = 8; /* Lets support 8 ASIDs in case we add proper
@@ -5954,11 +5924,11 @@ static void svm_set_supported_cpuid(u32 func, struct kvm_cpuid_entry2 *entry)

 		/* Support next_rip if host supports it */
 		if (boot_cpu_has(X86_FEATURE_NRIPS))
-			entry->edx |= SVM_FEATURE_NRIP;
+			entry->edx |= F(NRIPS);

 		/* Support NPT for the guest if enabled */
 		if (npt_enabled)
-			entry->edx |= SVM_FEATURE_NPT;
+			entry->edx |= F(NPT);

 		break;
 	case 0x8000001F:
@@ -6067,6 +6037,7 @@ static const struct __x86_intercept {
 	[x86_intercept_ins]		= POST_EX(SVM_EXIT_IOIO),
 	[x86_intercept_out]		= POST_EX(SVM_EXIT_IOIO),
 	[x86_intercept_outs]		= POST_EX(SVM_EXIT_IOIO),
+	[x86_intercept_xsetbv]		= PRE_EX(SVM_EXIT_XSETBV),
 };

 #undef PRE_EX
@@ -7193,6 +7164,21 @@ static bool svm_need_emulation_on_page_fault(struct kvm_vcpu *vcpu)
 	return false;
 }

+static bool svm_apic_init_signal_blocked(struct kvm_vcpu *vcpu)
+{
+	struct vcpu_svm *svm = to_svm(vcpu);
+
+	/*
+	 * TODO: Last condition latch INIT signals on vCPU when
+	 * vCPU is in guest-mode and vmcb12 defines intercept on INIT.
+	 * To properly emulate the INIT intercept, SVM should implement
+	 * kvm_x86_ops->check_nested_events() and call nested_svm_vmexit()
+	 * there if an INIT signal is pending.
+	 */
+	return !gif_set(svm) ||
+		   (svm->vmcb->control.intercept & (1ULL << INTERCEPT_INIT));
+}
+
 static struct kvm_x86_ops svm_x86_ops __ro_after_init = {
 	.cpu_has_kvm_support = has_svm,
 	.disabled_by_bios = is_disabled,
@@ -7329,6 +7315,8 @@ static struct kvm_x86_ops svm_x86_ops __ro_after_init = {
 	.nested_get_evmcs_version = NULL,

 	.need_emulation_on_page_fault = svm_need_emulation_on_page_fault,
+
+	.apic_init_signal_blocked = svm_apic_init_signal_blocked,
 };

 static int __init svm_init(void)