1 files changed, 91 insertions, 71 deletions

diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index c26255f19603..c5a4b1978cbf 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -32,6 +32,7 @@
 #include <linux/slab.h>
 #include <linux/tboot.h>
 #include <linux/hrtimer.h>
+#include <linux/nospec.h>
 #include "kvm_cache_regs.h"
 #include "x86.h"
 
@@ -47,6 +48,7 @@
 #include <asm/kexec.h>
 #include <asm/apic.h>
 #include <asm/irq_remapping.h>
+#include <asm/spec-ctrl.h>
 
 #include "trace.h"
 #include "pmu.h"
@@ -124,6 +126,12 @@ module_param_named(pml, enable_pml, bool, S_IRUGO);
 
 #define VMX_MISC_EMULATED_PREEMPTION_TIMER_RATE 5
 
+#define VMX_VPID_EXTENT_SUPPORTED_MASK		\
+	(VMX_VPID_EXTENT_INDIVIDUAL_ADDR_BIT |	\
+	VMX_VPID_EXTENT_SINGLE_CONTEXT_BIT |	\
+	VMX_VPID_EXTENT_GLOBAL_CONTEXT_BIT |	\
+	VMX_VPID_EXTENT_SINGLE_NON_GLOBAL_BIT)
+
 /*
  * These 2 parameters are used to config the controls for Pause-Loop Exiting:
  * ple_gap:    upper bound on the amount of time between two successive
@@ -826,21 +834,18 @@ static const unsigned short vmcs_field_to_offset_table[] = {
 
 static inline short vmcs_field_to_offset(unsigned long field)
 {
-	BUILD_BUG_ON(ARRAY_SIZE(vmcs_field_to_offset_table) > SHRT_MAX);
+	const size_t size = ARRAY_SIZE(vmcs_field_to_offset_table);
+	unsigned short offset;
 
-	if (field >= ARRAY_SIZE(vmcs_field_to_offset_table))
+	BUILD_BUG_ON(size > SHRT_MAX);
+	if (field >= size)
 		return -ENOENT;
 
-	/*
-	 * FIXME: Mitigation for CVE-2017-5753.  To be replaced with a
-	 * generic mechanism.
-	 */
-	asm("lfence");
-
-	if (vmcs_field_to_offset_table[field] == 0)
+	field = array_index_nospec(field, size);
+	offset = vmcs_field_to_offset_table[field];
+	if (offset == 0)
 		return -ENOENT;
-
-	return vmcs_field_to_offset_table[field];
+	return offset;
 }
 
 static inline struct vmcs12 *get_vmcs12(struct kvm_vcpu *vcpu)
@@ -1006,6 +1011,13 @@ static inline bool is_machine_check(u32 intr_info)
 		(INTR_TYPE_HARD_EXCEPTION | MC_VECTOR | INTR_INFO_VALID_MASK);
 }
 
+/* Undocumented: icebp/int1 */
+static inline bool is_icebp(u32 intr_info)
+{
+	return (intr_info & (INTR_INFO_INTR_TYPE_MASK | INTR_INFO_VALID_MASK))
+		== (INTR_TYPE_PRIV_SW_EXCEPTION | INTR_INFO_VALID_MASK);
+}
+
 static inline bool cpu_has_vmx_msr_bitmap(void)
 {
 	return vmcs_config.cpu_based_exec_ctrl & CPU_BASED_USE_MSR_BITMAPS;
@@ -2307,6 +2319,8 @@ static void vmx_queue_exception(struct kvm_vcpu *vcpu, unsigned nr,
 		return;
 	}
 
+	WARN_ON_ONCE(vmx->emulation_required);
+
 	if (kvm_exception_is_soft(nr)) {
 		vmcs_write32(VM_ENTRY_INSTRUCTION_LEN,
 			     vmx->vcpu.arch.event_exit_inst_len);
@@ -2658,8 +2672,7 @@ static void nested_vmx_setup_ctls_msrs(struct vcpu_vmx *vmx)
 	 */
 	if (enable_vpid)
 		vmx->nested.nested_vmx_vpid_caps = VMX_VPID_INVVPID_BIT |
-				VMX_VPID_EXTENT_SINGLE_CONTEXT_BIT |
-				VMX_VPID_EXTENT_GLOBAL_CONTEXT_BIT;
+			VMX_VPID_EXTENT_SUPPORTED_MASK;
 	else
 		vmx->nested.nested_vmx_vpid_caps = 0;
 
@@ -4513,7 +4526,7 @@ static int vmx_cpu_uses_apicv(struct kvm_vcpu *vcpu)
 	return enable_apicv && lapic_in_kernel(vcpu);
 }
 
-static int vmx_complete_nested_posted_interrupt(struct kvm_vcpu *vcpu)
+static void vmx_complete_nested_posted_interrupt(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
 	int max_irr;
@@ -4524,19 +4537,15 @@ static int vmx_complete_nested_posted_interrupt(struct kvm_vcpu *vcpu)
 	    vmx->nested.pi_pending) {
 		vmx->nested.pi_pending = false;
 		if (!pi_test_and_clear_on(vmx->nested.pi_desc))
-			return 0;
+			return;
 
 		max_irr = find_last_bit(
 			(unsigned long *)vmx->nested.pi_desc->pir, 256);
 
 		if (max_irr == 256)
-			return 0;
+			return;
 
 		vapic_page = kmap(vmx->nested.virtual_apic_page);
-		if (!vapic_page) {
-			WARN_ON(1);
-			return -ENOMEM;
-		}
 		__kvm_apic_update_irr(vmx->nested.pi_desc->pir, vapic_page);
 		kunmap(vmx->nested.virtual_apic_page);
 
@@ -4547,7 +4556,6 @@ static int vmx_complete_nested_posted_interrupt(struct kvm_vcpu *vcpu)
 			vmcs_write16(GUEST_INTR_STATUS, status);
 		}
 	}
-	return 0;
 }
 
 static inline bool kvm_vcpu_trigger_posted_interrupt(struct kvm_vcpu *vcpu)
@@ -4594,14 +4602,15 @@ static int vmx_deliver_nested_posted_interrupt(struct kvm_vcpu *vcpu,
 
 	if (is_guest_mode(vcpu) &&
 	    vector == vmx->nested.posted_intr_nv) {
-		/* the PIR and ON have been set by L1. */
-		kvm_vcpu_trigger_posted_interrupt(vcpu);
 		/*
 		 * If a posted intr is not recognized by hardware,
 		 * we will accomplish it in the next vmentry.
 		 */
 		vmx->nested.pi_pending = true;
 		kvm_make_request(KVM_REQ_EVENT, vcpu);
+		/* the PIR and ON have been set by L1. */
+		if (!kvm_vcpu_trigger_posted_interrupt(vcpu))
+			kvm_vcpu_kick(vcpu);
 		return 0;
 	}
 	return -1;
@@ -4953,7 +4962,7 @@ static void vmx_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event)
 		vmcs_write64(GUEST_IA32_DEBUGCTL, 0);
 	}
 
-	vmcs_writel(GUEST_RFLAGS, 0x02);
+	kvm_set_rflags(vcpu, X86_EFLAGS_FIXED);
 	kvm_rip_write(vcpu, 0xfff0);
 
 	vmcs_writel(GUEST_GDTR_BASE, 0);
@@ -5333,7 +5342,7 @@ static int handle_exception(struct kvm_vcpu *vcpu)
 		      (KVM_GUESTDBG_SINGLESTEP | KVM_GUESTDBG_USE_HW_BP))) {
 			vcpu->arch.dr6 &= ~15;
 			vcpu->arch.dr6 |= dr6 | DR6_RTM;
-			if (!(dr6 & ~DR6_RESERVED)) /* icebp */
+			if (is_icebp(intr_info))
 				skip_emulated_instruction(vcpu);
 
 			kvm_queue_exception(vcpu, DB_VECTOR);
@@ -6022,7 +6031,7 @@ static int handle_invalid_guest_state(struct kvm_vcpu *vcpu)
 		if (test_bit(KVM_REQ_EVENT, &vcpu->requests))
 			return 1;
 
-		err = emulate_instruction(vcpu, EMULTYPE_NO_REEXECUTE);
+		err = emulate_instruction(vcpu, 0);
 
 		if (err == EMULATE_USER_EXIT) {
 			++vcpu->stat.mmio_exits;
@@ -6030,12 +6039,12 @@ static int handle_invalid_guest_state(struct kvm_vcpu *vcpu)
 			goto out;
 		}
 
-		if (err != EMULATE_DONE) {
-			vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR;
-			vcpu->run->internal.suberror = KVM_INTERNAL_ERROR_EMULATION;
-			vcpu->run->internal.ndata = 0;
-			return 0;
-		}
+		if (err != EMULATE_DONE)
+			goto emulation_error;
+
+		if (vmx->emulation_required && !vmx->rmode.vm86_active &&
+		    vcpu->arch.exception.pending)
+			goto emulation_error;
 
 		if (vcpu->arch.halt_request) {
 			vcpu->arch.halt_request = 0;
@@ -6051,6 +6060,12 @@ static int handle_invalid_guest_state(struct kvm_vcpu *vcpu)
 
 out:
 	return ret;
+
+emulation_error:
+	vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR;
+	vcpu->run->internal.suberror = KVM_INTERNAL_ERROR_EMULATION;
+	vcpu->run->internal.ndata = 0;
+	return 0;
 }
 
 static int __grow_ple_window(int val)
@@ -6677,8 +6692,7 @@ static int nested_vmx_check_vmptr(struct kvm_vcpu *vcpu, int exit_reason,
 			vmcs_read32(VMX_INSTRUCTION_INFO), false, &gva))
 		return 1;
 
-	if (kvm_read_guest_virt(&vcpu->arch.emulate_ctxt, gva, &vmptr,
-				sizeof(vmptr), &e)) {
+	if (kvm_read_guest_virt(vcpu, gva, &vmptr, sizeof(vmptr), &e)) {
 		kvm_inject_page_fault(vcpu, &e);
 		return 1;
 	}
@@ -6829,6 +6843,8 @@ static int handle_vmon(struct kvm_vcpu *vcpu)
 		     HRTIMER_MODE_REL);
 	vmx->nested.preemption_timer.function = vmx_preemption_timer_fn;
 
+	vmx->nested.vpid02 = allocate_vpid();
+
 	vmx->nested.vmxon = true;
 
 	skip_emulated_instruction(vcpu);
@@ -7196,8 +7212,8 @@ static int handle_vmread(struct kvm_vcpu *vcpu)
 				vmx_instruction_info, true, &gva))
 			return 1;
 		/* _system ok, as nested_vmx_check_permission verified cpl=0 */
-		kvm_write_guest_virt_system(&vcpu->arch.emulate_ctxt, gva,
-			     &field_value, (is_long_mode(vcpu) ? 8 : 4), NULL);
+		kvm_write_guest_virt_system(vcpu, gva, &field_value,
+					    (is_long_mode(vcpu) ? 8 : 4), NULL);
 	}
 
 	nested_vmx_succeed(vcpu);
@@ -7232,8 +7248,8 @@ static int handle_vmwrite(struct kvm_vcpu *vcpu)
 		if (get_vmx_mem_address(vcpu, exit_qualification,
 				vmx_instruction_info, false, &gva))
 			return 1;
-		if (kvm_read_guest_virt(&vcpu->arch.emulate_ctxt, gva,
-			   &field_value, (is_64_bit_mode(vcpu) ? 8 : 4), &e)) {
+		if (kvm_read_guest_virt(vcpu, gva, &field_value,
+					(is_64_bit_mode(vcpu) ? 8 : 4), &e)) {
 			kvm_inject_page_fault(vcpu, &e);
 			return 1;
 		}
@@ -7323,9 +7339,9 @@ static int handle_vmptrst(struct kvm_vcpu *vcpu)
 			vmx_instruction_info, true, &vmcs_gva))
 		return 1;
 	/* ok to use *_system, as nested_vmx_check_permission verified cpl=0 */
-	if (kvm_write_guest_virt_system(&vcpu->arch.emulate_ctxt, vmcs_gva,
-				 (void *)&to_vmx(vcpu)->nested.current_vmptr,
-				 sizeof(u64), &e)) {
+	if (kvm_write_guest_virt_system(vcpu, vmcs_gva,
+					(void *)&to_vmx(vcpu)->nested.current_vmptr,
+					sizeof(u64), &e)) {
 		kvm_inject_page_fault(vcpu, &e);
 		return 1;
 	}
@@ -7366,7 +7382,7 @@ static int handle_invept(struct kvm_vcpu *vcpu)
 
 	types = (vmx->nested.nested_vmx_ept_caps >> VMX_EPT_EXTENT_SHIFT) & 6;
 
-	if (!(types & (1UL << type))) {
+	if (type >= 32 || !(types & (1 << type))) {
 		nested_vmx_failValid(vcpu,
 				VMXERR_INVALID_OPERAND_TO_INVEPT_INVVPID);
 		skip_emulated_instruction(vcpu);
@@ -7379,8 +7395,7 @@ static int handle_invept(struct kvm_vcpu *vcpu)
 	if (get_vmx_mem_address(vcpu, vmcs_readl(EXIT_QUALIFICATION),
 			vmx_instruction_info, false, &gva))
 		return 1;
-	if (kvm_read_guest_virt(&vcpu->arch.emulate_ctxt, gva, &operand,
-				sizeof(operand), &e)) {
+	if (kvm_read_guest_virt(vcpu, gva, &operand, sizeof(operand), &e)) {
 		kvm_inject_page_fault(vcpu, &e);
 		return 1;
 	}
@@ -7423,9 +7438,10 @@ static int handle_invvpid(struct kvm_vcpu *vcpu)
 	vmx_instruction_info = vmcs_read32(VMX_INSTRUCTION_INFO);
 	type = kvm_register_readl(vcpu, (vmx_instruction_info >> 28) & 0xf);
 
-	types = (vmx->nested.nested_vmx_vpid_caps >> 8) & 0x7;
+	types = (vmx->nested.nested_vmx_vpid_caps &
+			VMX_VPID_EXTENT_SUPPORTED_MASK) >> 8;
 
-	if (!(types & (1UL << type))) {
+	if (type >= 32 || !(types & (1 << type))) {
 		nested_vmx_failValid(vcpu,
 			VMXERR_INVALID_OPERAND_TO_INVEPT_INVVPID);
 		skip_emulated_instruction(vcpu);
@@ -7438,28 +7454,33 @@ static int handle_invvpid(struct kvm_vcpu *vcpu)
 	if (get_vmx_mem_address(vcpu, vmcs_readl(EXIT_QUALIFICATION),
 			vmx_instruction_info, false, &gva))
 		return 1;
-	if (kvm_read_guest_virt(&vcpu->arch.emulate_ctxt, gva, &vpid,
-				sizeof(u32), &e)) {
+	if (kvm_read_guest_virt(vcpu, gva, &vpid, sizeof(u32), &e)) {
 		kvm_inject_page_fault(vcpu, &e);
 		return 1;
 	}
 
 	switch (type) {
+	case VMX_VPID_EXTENT_INDIVIDUAL_ADDR:
 	case VMX_VPID_EXTENT_SINGLE_CONTEXT:
-		/*
-		 * Old versions of KVM use the single-context version so we
-		 * have to support it; just treat it the same as all-context.
-		 */
+	case VMX_VPID_EXTENT_SINGLE_NON_GLOBAL:
+		if (!vpid) {
+			nested_vmx_failValid(vcpu,
+				VMXERR_INVALID_OPERAND_TO_INVEPT_INVVPID);
+			skip_emulated_instruction(vcpu);
+			return 1;
+		}
+		break;
 	case VMX_VPID_EXTENT_ALL_CONTEXT:
-		__vmx_flush_tlb(vcpu, to_vmx(vcpu)->nested.vpid02);
-		nested_vmx_succeed(vcpu);
 		break;
 	default:
-		/* Trap individual address invalidation invvpid calls */
-		BUG_ON(1);
-		break;
+		WARN_ON_ONCE(1);
+		skip_emulated_instruction(vcpu);
+		return 1;
 	}
 
+	__vmx_flush_tlb(vcpu, vmx->nested.vpid02);
+	nested_vmx_succeed(vcpu);
+
 	skip_emulated_instruction(vcpu);
 	return 1;
 }
@@ -7643,11 +7664,13 @@ static bool nested_vmx_exit_handled_cr(struct kvm_vcpu *vcpu,
 {
 	unsigned long exit_qualification = vmcs_readl(EXIT_QUALIFICATION);
 	int cr = exit_qualification & 15;
-	int reg = (exit_qualification >> 8) & 15;
-	unsigned long val = kvm_register_readl(vcpu, reg);
+	int reg;
+	unsigned long val;
 
 	switch ((exit_qualification >> 4) & 3) {
 	case 0: /* mov to cr */
+		reg = (exit_qualification >> 8) & 15;
+		val = kvm_register_readl(vcpu, reg);
 		switch (cr) {
 		case 0:
 			if (vmcs12->cr0_guest_host_mask &
@@ -7702,6 +7725,7 @@ static bool nested_vmx_exit_handled_cr(struct kvm_vcpu *vcpu,
 		 * lmsw can change bits 1..3 of cr0, and only set bit 0 of
 		 * cr0. Other attempted changes are ignored, with no exit.
 		 */
+		val = (exit_qualification >> LMSW_SOURCE_DATA_SHIFT) & 0x0f;
 		if (vmcs12->cr0_guest_host_mask & 0xe &
 		    (val ^ vmcs12->cr0_read_shadow))
 			return true;
@@ -8375,13 +8399,13 @@ static void vmx_handle_external_intr(struct kvm_vcpu *vcpu)
 			"pushf\n\t"
 			"orl $0x200, (%%" _ASM_SP ")\n\t"
 			__ASM_SIZE(push) " $%c[cs]\n\t"
-			"call *%[entry]\n\t"
+			CALL_NOSPEC
 			:
 #ifdef CONFIG_X86_64
 			[sp]"=&r"(tmp)
 #endif
 			:
-			[entry]"r"(entry),
+			THUNK_TARGET(entry),
 			[ss]"i"(__KERNEL_DS),
 			[cs]"i"(__KERNEL_CS)
 			);
@@ -8701,6 +8725,9 @@ static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu)
 #endif
 	      );
 
+	/* Eliminate branch target predictions from guest mode */
+	vmexit_fill_RSB();
+
 	/* MSR_IA32_DEBUGCTLMSR is zeroed on vmexit. Restore it if needed */
 	if (debugctlmsr)
 		update_debugctlmsr(debugctlmsr);
@@ -8862,10 +8889,8 @@ static struct kvm_vcpu *vmx_create_vcpu(struct kvm *kvm, unsigned int id)
 			goto free_vmcs;
 	}
 
-	if (nested) {
+	if (nested)
 		nested_vmx_setup_ctls_msrs(vmx);
-		vmx->nested.vpid02 = allocate_vpid();
-	}
 
 	vmx->nested.posted_intr_nv = -1;
 	vmx->nested.current_vmptr = -1ull;
@@ -8874,7 +8899,6 @@ static struct kvm_vcpu *vmx_create_vcpu(struct kvm *kvm, unsigned int id)
 	return &vmx->vcpu;
 
 free_vmcs:
-	free_vpid(vmx->nested.vpid02);
 	free_loaded_vmcs(vmx->loaded_vmcs);
 free_msrs:
 	kfree(vmx->guest_msrs);
@@ -9235,11 +9259,6 @@ static inline bool nested_vmx_merge_msr_bitmap(struct kvm_vcpu *vcpu,
 		return false;
 	}
 	msr_bitmap = (unsigned long *)kmap(page);
-	if (!msr_bitmap) {
-		nested_release_page_clean(page);
-		WARN_ON(1);
-		return false;
-	}
 
 	if (nested_cpu_has_virt_x2apic_mode(vmcs12)) {
 		if (nested_cpu_has_apic_reg_virt(vmcs12))
@@ -10161,7 +10180,8 @@ static int vmx_check_nested_events(struct kvm_vcpu *vcpu, bool external_intr)
 		return 0;
 	}
 
-	return vmx_complete_nested_posted_interrupt(vcpu);
+	vmx_complete_nested_posted_interrupt(vcpu);
+	return 0;
 }
 
 static u32 vmx_get_preemption_timer_value(struct kvm_vcpu *vcpu)