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

torvalds · torvalds · commit 63623fd44972 · 2020-02-24T11:48:17.000-08:00
Pull kvm fixes from Paolo Bonzini: "Bugfixes, including the fix for CVE-2020-2732 and a few issues found by 'make W=1'" * tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: KVM: s390: rstify new ioctls in api.rst KVM: nVMX: Check IO instruction VM-exit conditions KVM: nVMX: Refactor IO bitmap checks into helper function KVM: nVMX: Don't emulate instructions in guest mode KVM: nVMX: Emulate MTF when performing instruction emulation KVM: fix error handling in svm_hardware_setup KVM: SVM: Fix potential memory leak in svm_cpu_init() KVM: apic: avoid calculating pending eoi from an uninitialized val KVM: nVMX: clear PIN_BASED_POSTED_INTR from nested pinbased_ctls only when apicv is globally disabled KVM: nVMX: handle nested posted interrupts when apicv is disabled for L1 kvm: x86: svm: Fix NULL pointer dereference when AVIC not enabled KVM: VMX: Add VMX_FEATURE_USR_WAIT_PAUSE KVM: nVMX: Hold KVM's srcu lock when syncing vmcs12->shadow KVM: x86: don't notify userspace IOAPIC on edge-triggered interrupt EOI kvm/emulate: fix a -Werror=cast-function-type KVM: x86: fix incorrect comparison in trace event KVM: nVMX: Fix some obsolete comments and grammar error KVM: x86: fix missing prototypes KVM: x86: enable -Werror
diff --git a/Documentation/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst
@@ -4611,35 +4611,38 @@ unpins the VPA pages and releases all the device pages that are used to
 track the secure pages by hypervisor.
 
 4.122 KVM_S390_NORMAL_RESET
+---------------------------
 
-Capability: KVM_CAP_S390_VCPU_RESETS
-Architectures: s390
-Type: vcpu ioctl
-Parameters: none
-Returns: 0
+:Capability: KVM_CAP_S390_VCPU_RESETS
+:Architectures: s390
+:Type: vcpu ioctl
+:Parameters: none
+:Returns: 0
 
 This ioctl resets VCPU registers and control structures according to
 the cpu reset definition in the POP (Principles Of Operation).
 
 4.123 KVM_S390_INITIAL_RESET
+----------------------------
 
-Capability: none
-Architectures: s390
-Type: vcpu ioctl
-Parameters: none
-Returns: 0
+:Capability: none
+:Architectures: s390
+:Type: vcpu ioctl
+:Parameters: none
+:Returns: 0
 
 This ioctl resets VCPU registers and control structures according to
 the initial cpu reset definition in the POP. However, the cpu is not
 put into ESA mode. This reset is a superset of the normal reset.
 
 4.124 KVM_S390_CLEAR_RESET
+--------------------------
 
-Capability: KVM_CAP_S390_VCPU_RESETS
-Architectures: s390
-Type: vcpu ioctl
-Parameters: none
-Returns: 0
+:Capability: KVM_CAP_S390_VCPU_RESETS
+:Architectures: s390
+:Type: vcpu ioctl
+:Parameters: none
+:Returns: 0
 
 This ioctl resets VCPU registers and control structures according to
 the clear cpu reset definition in the POP. However, the cpu is not put
diff --git a/arch/x86/include/asm/kvm_emulate.h b/arch/x86/include/asm/kvm_emulate.h
@@ -292,6 +292,14 @@ enum x86emul_mode {
 #define X86EMUL_SMM_MASK             (1 << 6)
 #define X86EMUL_SMM_INSIDE_NMI_MASK  (1 << 7)
 
+/*
+ * fastop functions are declared as taking a never-defined fastop parameter,
+ * so they can't be called from C directly.
+ */
+struct fastop;
+
+typedef void (*fastop_t)(struct fastop *);
+
 struct x86_emulate_ctxt {
 	const struct x86_emulate_ops *ops;
 
@@ -324,7 +332,10 @@ struct x86_emulate_ctxt {
 	struct operand src;
 	struct operand src2;
 	struct operand dst;
-	int (*execute)(struct x86_emulate_ctxt *ctxt);
+	union {
+		int (*execute)(struct x86_emulate_ctxt *ctxt);
+		fastop_t fop;
+	};
 	int (*check_perm)(struct x86_emulate_ctxt *ctxt);
 	/*
 	 * The following six fields are cleared together,
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
@@ -1122,6 +1122,7 @@ struct kvm_x86_ops {
 	int (*handle_exit)(struct kvm_vcpu *vcpu,
 		enum exit_fastpath_completion exit_fastpath);
 	int (*skip_emulated_instruction)(struct kvm_vcpu *vcpu);
+	void (*update_emulated_instruction)(struct kvm_vcpu *vcpu);
 	void (*set_interrupt_shadow)(struct kvm_vcpu *vcpu, int mask);
 	u32 (*get_interrupt_shadow)(struct kvm_vcpu *vcpu);
 	void (*patch_hypercall)(struct kvm_vcpu *vcpu,
@@ -1146,7 +1147,7 @@ struct kvm_x86_ops {
 	void (*load_eoi_exitmap)(struct kvm_vcpu *vcpu, u64 *eoi_exit_bitmap);
 	void (*set_virtual_apic_mode)(struct kvm_vcpu *vcpu);
 	void (*set_apic_access_page_addr)(struct kvm_vcpu *vcpu, hpa_t hpa);
-	void (*deliver_posted_interrupt)(struct kvm_vcpu *vcpu, int vector);
+	int (*deliver_posted_interrupt)(struct kvm_vcpu *vcpu, int vector);
 	int (*sync_pir_to_irr)(struct kvm_vcpu *vcpu);
 	int (*set_tss_addr)(struct kvm *kvm, unsigned int addr);
 	int (*set_identity_map_addr)(struct kvm *kvm, u64 ident_addr);
diff --git a/arch/x86/include/asm/vmx.h b/arch/x86/include/asm/vmx.h
@@ -72,7 +72,7 @@
 #define SECONDARY_EXEC_MODE_BASED_EPT_EXEC	VMCS_CONTROL_BIT(MODE_BASED_EPT_EXEC)
 #define SECONDARY_EXEC_PT_USE_GPA		VMCS_CONTROL_BIT(PT_USE_GPA)
 #define SECONDARY_EXEC_TSC_SCALING              VMCS_CONTROL_BIT(TSC_SCALING)
-#define SECONDARY_EXEC_ENABLE_USR_WAIT_PAUSE	0x04000000
+#define SECONDARY_EXEC_ENABLE_USR_WAIT_PAUSE	VMCS_CONTROL_BIT(USR_WAIT_PAUSE)
 
 #define PIN_BASED_EXT_INTR_MASK                 VMCS_CONTROL_BIT(INTR_EXITING)
 #define PIN_BASED_NMI_EXITING                   VMCS_CONTROL_BIT(NMI_EXITING)
diff --git a/arch/x86/include/asm/vmxfeatures.h b/arch/x86/include/asm/vmxfeatures.h
@@ -81,6 +81,7 @@
 #define VMX_FEATURE_MODE_BASED_EPT_EXEC	( 2*32+ 22) /* "ept_mode_based_exec" Enable separate EPT EXEC bits for supervisor vs. user */
 #define VMX_FEATURE_PT_USE_GPA		( 2*32+ 24) /* "" Processor Trace logs GPAs */
 #define VMX_FEATURE_TSC_SCALING		( 2*32+ 25) /* Scale hardware TSC when read in guest */
+#define VMX_FEATURE_USR_WAIT_PAUSE	( 2*32+ 26) /* Enable TPAUSE, UMONITOR, UMWAIT in guest */
 #define VMX_FEATURE_ENCLV_EXITING	( 2*32+ 28) /* "" VM-Exit on ENCLV (leaf dependent) */
 
 #endif /* _ASM_X86_VMXFEATURES_H */
diff --git a/arch/x86/include/uapi/asm/kvm.h b/arch/x86/include/uapi/asm/kvm.h
@@ -390,6 +390,7 @@ struct kvm_sync_regs {
 #define KVM_STATE_NESTED_GUEST_MODE	0x00000001
 #define KVM_STATE_NESTED_RUN_PENDING	0x00000002
 #define KVM_STATE_NESTED_EVMCS		0x00000004
+#define KVM_STATE_NESTED_MTF_PENDING	0x00000008
 
 #define KVM_STATE_NESTED_SMM_GUEST_MODE	0x00000001
 #define KVM_STATE_NESTED_SMM_VMXON	0x00000002
diff --git a/arch/x86/kvm/Makefile b/arch/x86/kvm/Makefile
@@ -1,6 +1,7 @@
 # SPDX-License-Identifier: GPL-2.0
 
 ccflags-y += -Iarch/x86/kvm
+ccflags-y += -Werror
 
 KVM := ../../../virt/kvm
 
diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
@@ -191,25 +191,6 @@
 #define NR_FASTOP (ilog2(sizeof(ulong)) + 1)
 #define FASTOP_SIZE 8
 
-/*
- * fastop functions have a special calling convention:
- *
- * dst:    rax        (in/out)
- * src:    rdx        (in/out)
- * src2:   rcx        (in)
- * flags:  rflags     (in/out)
- * ex:     rsi        (in:fastop pointer, out:zero if exception)
- *
- * Moreover, they are all exactly FASTOP_SIZE bytes long, so functions for
- * different operand sizes can be reached by calculation, rather than a jump
- * table (which would be bigger than the code).
- *
- * fastop functions are declared as taking a never-defined fastop parameter,
- * so they can't be called from C directly.
- */
-
-struct fastop;
-
 struct opcode {
 	u64 flags : 56;
 	u64 intercept : 8;
@@ -311,8 +292,19 @@ static void invalidate_registers(struct x86_emulate_ctxt *ctxt)
 #define ON64(x)
 #endif
 
-typedef void (*fastop_t)(struct fastop *);
-
+/*
+ * fastop functions have a special calling convention:
+ *
+ * dst:    rax        (in/out)
+ * src:    rdx        (in/out)
+ * src2:   rcx        (in)
+ * flags:  rflags     (in/out)
+ * ex:     rsi        (in:fastop pointer, out:zero if exception)
+ *
+ * Moreover, they are all exactly FASTOP_SIZE bytes long, so functions for
+ * different operand sizes can be reached by calculation, rather than a jump
+ * table (which would be bigger than the code).
+ */
 static int fastop(struct x86_emulate_ctxt *ctxt, fastop_t fop);
 
 #define __FOP_FUNC(name) \
@@ -5683,7 +5675,7 @@ int x86_emulate_insn(struct x86_emulate_ctxt *ctxt)
 
 	if (ctxt->execute) {
 		if (ctxt->d & Fastop)
-			rc = fastop(ctxt, (fastop_t)ctxt->execute);
+			rc = fastop(ctxt, ctxt->fop);
 		else
 			rc = ctxt->execute(ctxt);
 		if (rc != X86EMUL_CONTINUE)
diff --git a/arch/x86/kvm/irq_comm.c b/arch/x86/kvm/irq_comm.c
@@ -417,7 +417,7 @@ void kvm_scan_ioapic_routes(struct kvm_vcpu *vcpu,
 
 			kvm_set_msi_irq(vcpu->kvm, entry, &irq);
 
-			if (irq.level &&
+			if (irq.trig_mode &&
 			    kvm_apic_match_dest(vcpu, NULL, APIC_DEST_NOSHORT,
 						irq.dest_id, irq.dest_mode))
 				__set_bit(irq.vector, ioapic_handled_vectors);
diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
@@ -627,9 +627,11 @@ static inline bool pv_eoi_enabled(struct kvm_vcpu *vcpu)
 static bool pv_eoi_get_pending(struct kvm_vcpu *vcpu)
 {
 	u8 val;
-	if (pv_eoi_get_user(vcpu, &val) < 0)
+	if (pv_eoi_get_user(vcpu, &val) < 0) {
 		printk(KERN_WARNING "Can't read EOI MSR value: 0x%llx\n",
 			   (unsigned long long)vcpu->arch.pv_eoi.msr_val);
+		return false;
+	}
 	return val & 0x1;
 }
 
@@ -1046,11 +1048,8 @@ static int __apic_accept_irq(struct kvm_lapic *apic, int delivery_mode,
 						       apic->regs + APIC_TMR);
 		}
 
-		if (vcpu->arch.apicv_active)
-			kvm_x86_ops->deliver_posted_interrupt(vcpu, vector);
-		else {
+		if (kvm_x86_ops->deliver_posted_interrupt(vcpu, vector)) {
 			kvm_lapic_set_irr(vector, apic);
-
 			kvm_make_request(KVM_REQ_EVENT, vcpu);
 			kvm_vcpu_kick(vcpu);
 		}
diff --git a/arch/x86/kvm/mmutrace.h b/arch/x86/kvm/mmutrace.h
@@ -339,7 +339,7 @@ TRACE_EVENT(
 		/* These depend on page entry type, so compute them now.  */
 		__field(bool, r)
 		__field(bool, x)
-		__field(u8, u)
+		__field(signed char, u)
 	),
 
 	TP_fast_assign(
diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
@@ -1005,33 +1005,32 @@ static void svm_cpu_uninit(int cpu)
 static int svm_cpu_init(int cpu)
 {
 	struct svm_cpu_data *sd;
-	int r;
 
 	sd = kzalloc(sizeof(struct svm_cpu_data), GFP_KERNEL);
 	if (!sd)
 		return -ENOMEM;
 	sd->cpu = cpu;
-	r = -ENOMEM;
 	sd->save_area = alloc_page(GFP_KERNEL);
 	if (!sd->save_area)
-		goto err_1;
+		goto free_cpu_data;
 
 	if (svm_sev_enabled()) {
-		r = -ENOMEM;
 		sd->sev_vmcbs = kmalloc_array(max_sev_asid + 1,
 					      sizeof(void *),
 					      GFP_KERNEL);
 		if (!sd->sev_vmcbs)
-			goto err_1;
+			goto free_save_area;
 	}
 
 	per_cpu(svm_data, cpu) = sd;
 
 	return 0;
 
-err_1:
+free_save_area:
+	__free_page(sd->save_area);
+free_cpu_data:
 	kfree(sd);
-	return r;
+	return -ENOMEM;
 
 }
 
@@ -1350,6 +1349,24 @@ static __init void svm_adjust_mmio_mask(void)
 	kvm_mmu_set_mmio_spte_mask(mask, mask, PT_WRITABLE_MASK | PT_USER_MASK);
 }
 
+static void svm_hardware_teardown(void)
+{
+	int cpu;
+
+	if (svm_sev_enabled()) {
+		bitmap_free(sev_asid_bitmap);
+		bitmap_free(sev_reclaim_asid_bitmap);
+
+		sev_flush_asids();
+	}
+
+	for_each_possible_cpu(cpu)
+		svm_cpu_uninit(cpu);
+
+	__free_pages(pfn_to_page(iopm_base >> PAGE_SHIFT), IOPM_ALLOC_ORDER);
+	iopm_base = 0;
+}
+
 static __init int svm_hardware_setup(void)
 {
 	int cpu;
@@ -1463,29 +1480,10 @@ static __init int svm_hardware_setup(void)
 	return 0;
 
 err:
-	__free_pages(iopm_pages, IOPM_ALLOC_ORDER);
-	iopm_base = 0;
+	svm_hardware_teardown();
 	return r;
 }
 
-static __exit void svm_hardware_unsetup(void)
-{
-	int cpu;
-
-	if (svm_sev_enabled()) {
-		bitmap_free(sev_asid_bitmap);
-		bitmap_free(sev_reclaim_asid_bitmap);
-
-		sev_flush_asids();
-	}
-
-	for_each_possible_cpu(cpu)
-		svm_cpu_uninit(cpu);
-
-	__free_pages(pfn_to_page(iopm_base >> PAGE_SHIFT), IOPM_ALLOC_ORDER);
-	iopm_base = 0;
-}
-
 static void init_seg(struct vmcb_seg *seg)
 {
 	seg->selector = 0;
@@ -5232,6 +5230,9 @@ static void svm_refresh_apicv_exec_ctrl(struct kvm_vcpu *vcpu)
 	struct vmcb *vmcb = svm->vmcb;
 	bool activated = kvm_vcpu_apicv_active(vcpu);
 
+	if (!avic)
+		return;
+
 	if (activated) {
 		/**
 		 * During AVIC temporary deactivation, guest could update
@@ -5255,8 +5256,11 @@ static void svm_load_eoi_exitmap(struct kvm_vcpu *vcpu, u64 *eoi_exit_bitmap)
 	return;
 }
 
-static void svm_deliver_avic_intr(struct kvm_vcpu *vcpu, int vec)
+static int svm_deliver_avic_intr(struct kvm_vcpu *vcpu, int vec)
 {
+	if (!vcpu->arch.apicv_active)
+		return -1;
+
 	kvm_lapic_set_irr(vec, vcpu->arch.apic);
 	smp_mb__after_atomic();
 
@@ -5268,6 +5272,8 @@ static void svm_deliver_avic_intr(struct kvm_vcpu *vcpu, int vec)
 		put_cpu();
 	} else
 		kvm_vcpu_wake_up(vcpu);
+
+	return 0;
 }
 
 static bool svm_dy_apicv_has_pending_interrupt(struct kvm_vcpu *vcpu)
@@ -7378,7 +7384,7 @@ static struct kvm_x86_ops svm_x86_ops __ro_after_init = {
 	.cpu_has_kvm_support = has_svm,
 	.disabled_by_bios = is_disabled,
 	.hardware_setup = svm_hardware_setup,
-	.hardware_unsetup = svm_hardware_unsetup,
+	.hardware_unsetup = svm_hardware_teardown,
 	.check_processor_compatibility = svm_check_processor_compat,
 	.hardware_enable = svm_hardware_enable,
 	.hardware_disable = svm_hardware_disable,
@@ -7433,6 +7439,7 @@ static struct kvm_x86_ops svm_x86_ops __ro_after_init = {
 	.run = svm_vcpu_run,
 	.handle_exit = handle_exit,
 	.skip_emulated_instruction = skip_emulated_instruction,
+	.update_emulated_instruction = NULL,
 	.set_interrupt_shadow = svm_set_interrupt_shadow,
 	.get_interrupt_shadow = svm_get_interrupt_shadow,
 	.patch_hypercall = svm_patch_hypercall,
diff --git a/arch/x86/kvm/vmx/capabilities.h b/arch/x86/kvm/vmx/capabilities.h
@@ -12,6 +12,7 @@ extern bool __read_mostly enable_ept;
 extern bool __read_mostly enable_unrestricted_guest;
 extern bool __read_mostly enable_ept_ad_bits;
 extern bool __read_mostly enable_pml;
+extern bool __read_mostly enable_apicv;
 extern int __read_mostly pt_mode;
 
 #define PT_MODE_SYSTEM		0
diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c
diff --git a/arch/x86/kvm/vmx/nested.h b/arch/x86/kvm/vmx/nested.h
diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
diff --git a/arch/x86/kvm/vmx/vmx.h b/arch/x86/kvm/vmx/vmx.h
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h

Original file line number	Diff line number	Diff line change
`@@ -627,9 +627,11 @@ static inline bool pv_eoi_enabled(struct kvm_vcpu *vcpu)`
`627`	`627`	`static bool pv_eoi_get_pending(struct kvm_vcpu *vcpu)`
`628`	`628`	`{`
`629`	`629`	`u8 val;`
`630`		`- if (pv_eoi_get_user(vcpu, &val) < 0)`
	`630`	`+ if (pv_eoi_get_user(vcpu, &val) < 0) {`
`631`	`631`	`printk(KERN_WARNING "Can't read EOI MSR value: 0x%llx\n",`
`632`	`632`	`(unsigned long long)vcpu->arch.pv_eoi.msr_val);`
	`633`	`+ return false;`
	`634`	`+ }`
`633`	`635`	`return val & 0x1;`
`634`	`636`	`}`
`635`	`637`
`@@ -1046,11 +1048,8 @@ static int __apic_accept_irq(struct kvm_lapic *apic, int delivery_mode,`
`1046`	`1048`	`apic->regs + APIC_TMR);`
`1047`	`1049`	`}`
`1048`	`1050`
`1049`		`- if (vcpu->arch.apicv_active)`
`1050`		`- kvm_x86_ops->deliver_posted_interrupt(vcpu, vector);`
`1051`		`- else {`
	`1051`	`+ if (kvm_x86_ops->deliver_posted_interrupt(vcpu, vector)) {`
`1052`	`1052`	`kvm_lapic_set_irr(vector, apic);`
`1053`		`-`
`1054`	`1053`	`kvm_make_request(KVM_REQ_EVENT, vcpu);`
`1055`	`1054`	`kvm_vcpu_kick(vcpu);`
`1056`	`1055`	`}`