Merge pull request #46 from toradex/4.9-2.3.x-imx

4.9 2.3.x imx

4 files changed, 69 insertions, 29 deletions

diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index 69a81a7daa24..c8630569e392 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -57,7 +57,7 @@
 #define APIC_BUS_CYCLE_NS 1
 
 /* #define apic_debug(fmt,arg...) printk(KERN_WARNING fmt,##arg) */
-#define apic_debug(fmt, arg...)
+#define apic_debug(fmt, arg...) do {} while (0)
 
 /* 14 is the version for Xeon and Pentium 8.4.8*/
 #define APIC_VERSION			(0x14UL | ((KVM_APIC_LVT_NUM - 1) << 16))
diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
index fa1b0e3c8a06..01eb0451b96d 100644
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -2862,6 +2862,14 @@ static int nested_svm_vmexit(struct vcpu_svm *svm)
 	kvm_mmu_reset_context(&svm->vcpu);
 	kvm_mmu_load(&svm->vcpu);
 
+	/*
+	 * Drop what we picked up for L2 via svm_complete_interrupts() so it
+	 * doesn't end up in L1.
+	 */
+	svm->vcpu.arch.nmi_injected = false;
+	kvm_clear_exception_queue(&svm->vcpu);
+	kvm_clear_interrupt_queue(&svm->vcpu);
+
 	return 0;
 }
 
@@ -3932,25 +3940,14 @@ static int avic_incomplete_ipi_interception(struct vcpu_svm *svm)
 		kvm_lapic_reg_write(apic, APIC_ICR, icrl);
 		break;
 	case AVIC_IPI_FAILURE_TARGET_NOT_RUNNING: {
-		int i;
-		struct kvm_vcpu *vcpu;
-		struct kvm *kvm = svm->vcpu.kvm;
 		struct kvm_lapic *apic = svm->vcpu.arch.apic;
 
 		/*
-		 * At this point, we expect that the AVIC HW has already
-		 * set the appropriate IRR bits on the valid target
-		 * vcpus. So, we just need to kick the appropriate vcpu.
+		 * Update ICR high and low, then emulate sending IPI,
+		 * which is handled when writing APIC_ICR.
 		 */
-		kvm_for_each_vcpu(i, vcpu, kvm) {
-			bool m = kvm_apic_match_dest(vcpu, apic,
-						     icrl & KVM_APIC_SHORT_MASK,
-						     GET_APIC_DEST_FIELD(icrh),
-						     icrl & KVM_APIC_DEST_MASK);
-
-			if (m && !avic_vcpu_is_running(vcpu))
-				kvm_vcpu_wake_up(vcpu);
-		}
+		kvm_lapic_reg_write(apic, APIC_ICR2, icrh);
+		kvm_lapic_reg_write(apic, APIC_ICR, icrl);
 		break;
 	}
 	case AVIC_IPI_FAILURE_INVALID_TARGET:
@@ -5223,6 +5220,13 @@ static bool svm_cpu_has_accelerated_tpr(void)
 
 static bool svm_has_emulated_msr(int index)
 {
+	switch (index) {
+	case MSR_IA32_MCG_EXT_CTL:
+		return false;
+	default:
+		break;
+	}
+
 	return true;
 }
 
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 8888d894bf39..a34fb7284024 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -1077,7 +1077,7 @@ static void copy_vmcs12_to_shadow(struct vcpu_vmx *vmx);
 static void copy_shadow_to_vmcs12(struct vcpu_vmx *vmx);
 static int alloc_identity_pagetable(struct kvm *kvm);
 static void vmx_update_msr_bitmap(struct kvm_vcpu *vcpu);
-static void __always_inline vmx_disable_intercept_for_msr(unsigned long *msr_bitmap,
+static __always_inline void vmx_disable_intercept_for_msr(unsigned long *msr_bitmap,
 							  u32 msr, int type);
 
 static DEFINE_PER_CPU(struct vmcs *, vmxarea);
@@ -2178,7 +2178,8 @@ static void add_atomic_switch_msr(struct vcpu_vmx *vmx, unsigned msr,
 	if (!entry_only)
 		j = find_msr(&m->host, msr);
 
-	if (i == NR_AUTOLOAD_MSRS || j == NR_AUTOLOAD_MSRS) {
+	if ((i < 0 && m->guest.nr == NR_AUTOLOAD_MSRS) ||
+		(j < 0 &&  m->host.nr == NR_AUTOLOAD_MSRS)) {
 		printk_once(KERN_WARNING "Not enough msr switch entries. "
 				"Can't add msr %x\n", msr);
 		return;
@@ -4872,7 +4873,7 @@ static void free_vpid(int vpid)
 	spin_unlock(&vmx_vpid_lock);
 }
 
-static void __always_inline vmx_disable_intercept_for_msr(unsigned long *msr_bitmap,
+static __always_inline void vmx_disable_intercept_for_msr(unsigned long *msr_bitmap,
 							  u32 msr, int type)
 {
 	int f = sizeof(unsigned long);
@@ -4907,7 +4908,7 @@ static void __always_inline vmx_disable_intercept_for_msr(unsigned long *msr_bit
 	}
 }
 
-static void __always_inline vmx_enable_intercept_for_msr(unsigned long *msr_bitmap,
+static __always_inline void vmx_enable_intercept_for_msr(unsigned long *msr_bitmap,
 							 u32 msr, int type)
 {
 	int f = sizeof(unsigned long);
@@ -4942,7 +4943,7 @@ static void __always_inline vmx_enable_intercept_for_msr(unsigned long *msr_bitm
 	}
 }
 
-static void __always_inline vmx_set_intercept_for_msr(unsigned long *msr_bitmap,
+static __always_inline void vmx_set_intercept_for_msr(unsigned long *msr_bitmap,
 			     			      u32 msr, int type, bool value)
 {
 	if (value)
@@ -5964,6 +5965,7 @@ static int handle_external_interrupt(struct kvm_vcpu *vcpu)
 static int handle_triple_fault(struct kvm_vcpu *vcpu)
 {
 	vcpu->run->exit_reason = KVM_EXIT_SHUTDOWN;
+	vcpu->mmio_needed = 0;
 	return 0;
 }
 
@@ -6548,9 +6550,24 @@ static int handle_ept_misconfig(struct kvm_vcpu *vcpu)
 
 	gpa = vmcs_read64(GUEST_PHYSICAL_ADDRESS);
 	if (!kvm_io_bus_write(vcpu, KVM_FAST_MMIO_BUS, gpa, 0, NULL)) {
-		skip_emulated_instruction(vcpu);
 		trace_kvm_fast_mmio(gpa);
-		return 1;
+		/*
+		* Doing kvm_skip_emulated_instruction() depends on undefined
+		* behavior: Intel's manual doesn't mandate
+		* VM_EXIT_INSTRUCTION_LEN to be set in VMCS when EPT MISCONFIG
+		* occurs and while on real hardware it was observed to be set,
+		* other hypervisors (namely Hyper-V) don't set it, we end up
+		* advancing IP with some random value. Disable fast mmio when
+		* running nested and keep it for real hardware in hope that
+		* VM_EXIT_INSTRUCTION_LEN will always be set correctly.
+		*/
+		if (!static_cpu_has(X86_FEATURE_HYPERVISOR)) {
+			skip_emulated_instruction(vcpu);
+			return 1;
+		}
+		else
+			return x86_emulate_instruction(vcpu, gpa, EMULTYPE_SKIP,
+						       NULL, 0) == EMULATE_DONE;
 	}
 
 	ret = handle_mmio_page_fault(vcpu, gpa, true);
@@ -7030,6 +7047,10 @@ static int get_vmx_mem_address(struct kvm_vcpu *vcpu,
 	/* Addr = segment_base + offset */
 	/* offset = base + [index * scale] + displacement */
 	off = exit_qualification; /* holds the displacement */
+	if (addr_size == 1)
+		off = (gva_t)sign_extend64(off, 31);
+	else if (addr_size == 0)
+		off = (gva_t)sign_extend64(off, 15);
 	if (base_is_valid)
 		off += kvm_register_read(vcpu, base_reg);
 	if (index_is_valid)
@@ -7072,10 +7093,16 @@ static int get_vmx_mem_address(struct kvm_vcpu *vcpu,
 		/* Protected mode: #GP(0)/#SS(0) if the segment is unusable.
 		 */
 		exn = (s.unusable != 0);
-		/* Protected mode: #GP(0)/#SS(0) if the memory
-		 * operand is outside the segment limit.
+
+		/*
+		 * Protected mode: #GP(0)/#SS(0) if the memory operand is
+		 * outside the segment limit.  All CPUs that support VMX ignore
+		 * limit checks for flat segments, i.e. segments with base==0,
+		 * limit==0xffffffff and of type expand-up data or code.
 		 */
-		exn = exn || (off + sizeof(u64) > s.limit);
+		if (!(s.base == 0 && s.limit == 0xffffffff &&
+		     ((s.type & 8) || !(s.type & 4))))
+			exn = exn || (off + sizeof(u64) > s.limit);
 	}
 	if (exn) {
 		kvm_queue_exception_e(vcpu,
@@ -7353,6 +7380,7 @@ static void free_nested(struct vcpu_vmx *vmx)
 	if (!vmx->nested.vmxon)
 		return;
 
+	hrtimer_cancel(&vmx->nested.preemption_timer);
 	vmx->nested.vmxon = false;
 	free_vpid(vmx->nested.vpid02);
 	nested_release_vmcs12(vmx);
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 27d13b870e07..a29df9ccbfde 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -4513,6 +4513,13 @@ int kvm_read_guest_virt(struct kvm_vcpu *vcpu,
 {
 	u32 access = (kvm_x86_ops->get_cpl(vcpu) == 3) ? PFERR_USER_MASK : 0;
 
+	/*
+	 * FIXME: this should call handle_emulation_failure if X86EMUL_IO_NEEDED
+	 * is returned, but our callers are not ready for that and they blindly
+	 * call kvm_inject_page_fault.  Ensure that they at least do not leak
+	 * uninitialized kernel stack memory into cr2 and error code.
+	 */
+	memset(exception, 0, sizeof(*exception));
 	return kvm_read_guest_virt_helper(addr, val, bytes, vcpu, access,
 					  exception);
 }
@@ -5707,7 +5714,8 @@ int x86_emulate_instruction(struct kvm_vcpu *vcpu,
 		 * handle watchpoints yet, those would be handled in
 		 * the emulate_ops.
 		 */
-		if (kvm_vcpu_check_breakpoint(vcpu, &r))
+		if (!(emulation_type & EMULTYPE_SKIP) &&
+		    kvm_vcpu_check_breakpoint(vcpu, &r))
 			return r;
 
 		ctxt->interruptibility = 0;
@@ -5794,8 +5802,7 @@ restart:
 		toggle_interruptibility(vcpu, ctxt->interruptibility);
 		vcpu->arch.emulate_regs_need_sync_to_vcpu = false;
 		kvm_rip_write(vcpu, ctxt->eip);
-		if (r == EMULATE_DONE &&
-		    (ctxt->tf || (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP)))
+		if (r == EMULATE_DONE && ctxt->tf)
 			kvm_vcpu_do_singlestep(vcpu, &r);
 		if (!ctxt->have_exception ||
 		    exception_type(ctxt->exception.vector) == EXCPT_TRAP)
@@ -6762,6 +6769,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
 		}
 		if (kvm_check_request(KVM_REQ_TRIPLE_FAULT, vcpu)) {
 			vcpu->run->exit_reason = KVM_EXIT_SHUTDOWN;
+			vcpu->mmio_needed = 0;
 			r = 0;
 			goto out;
 		}