X-Git-Url: http://ftp.safe.ca/?a=blobdiff_plain;f=arch%2Fx86%2Fkvm%2Fx86.c;h=fd5101b57fa3c266f0e0430e79e3056682b02306;hb=c76de350c8a3ba770becc17eaa744dc3c7642295;hp=aff3479867a8f34bba84e3d83cd44a17bc1cac54;hpb=79fac95ecfa3969aab8119d37ccd7226165f933a;p=safe%2Fjmp%2Flinux-2.6

diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index aff3479..fd5101b 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -428,9 +428,11 @@ out:
 
 void kvm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0)
 {
+	cr0 |= X86_CR0_ET;
+
 	if (cr0 & CR0_RESERVED_BITS) {
 		printk(KERN_DEBUG "set_cr0: 0x%lx #GP, reserved bits 0x%lx\n",
-		       cr0, vcpu->arch.cr0);
+		       cr0, kvm_read_cr0(vcpu));
 		kvm_inject_gp(vcpu, 0);
 		return;
 	}
@@ -488,7 +490,7 @@ EXPORT_SYMBOL_GPL(kvm_set_cr0);
 
 void kvm_lmsw(struct kvm_vcpu *vcpu, unsigned long msw)
 {
-	kvm_set_cr0(vcpu, (vcpu->arch.cr0 & ~0x0ful) | (msw & 0x0f));
+	kvm_set_cr0(vcpu, kvm_read_cr0_bits(vcpu, ~0x0ful) | (msw & 0x0f));
 }
 EXPORT_SYMBOL_GPL(kvm_lmsw);
 
@@ -620,9 +622,11 @@ static inline u32 bit(int bitno)
  * kvm-specific. Those are put in the beginning of the list.
  */
 
-#define KVM_SAVE_MSRS_BEGIN	2
+#define KVM_SAVE_MSRS_BEGIN	5
 static u32 msrs_to_save[] = {
 	MSR_KVM_SYSTEM_TIME, MSR_KVM_WALL_CLOCK,
+	HV_X64_MSR_GUEST_OS_ID, HV_X64_MSR_HYPERCALL,
+	HV_X64_MSR_APIC_ASSIST_PAGE,
 	MSR_IA32_SYSENTER_CS, MSR_IA32_SYSENTER_ESP, MSR_IA32_SYSENTER_EIP,
 	MSR_K6_STAR,
 #ifdef CONFIG_X86_64
@@ -1002,6 +1006,100 @@ out:
 	return r;
 }
 
+static bool kvm_hv_hypercall_enabled(struct kvm *kvm)
+{
+	return kvm->arch.hv_hypercall & HV_X64_MSR_HYPERCALL_ENABLE;
+}
+
+static bool kvm_hv_msr_partition_wide(u32 msr)
+{
+	bool r = false;
+	switch (msr) {
+	case HV_X64_MSR_GUEST_OS_ID:
+	case HV_X64_MSR_HYPERCALL:
+		r = true;
+		break;
+	}
+
+	return r;
+}
+
+static int set_msr_hyperv_pw(struct kvm_vcpu *vcpu, u32 msr, u64 data)
+{
+	struct kvm *kvm = vcpu->kvm;
+
+	switch (msr) {
+	case HV_X64_MSR_GUEST_OS_ID:
+		kvm->arch.hv_guest_os_id = data;
+		/* setting guest os id to zero disables hypercall page */
+		if (!kvm->arch.hv_guest_os_id)
+			kvm->arch.hv_hypercall &= ~HV_X64_MSR_HYPERCALL_ENABLE;
+		break;
+	case HV_X64_MSR_HYPERCALL: {
+		u64 gfn;
+		unsigned long addr;
+		u8 instructions[4];
+
+		/* if guest os id is not set hypercall should remain disabled */
+		if (!kvm->arch.hv_guest_os_id)
+			break;
+		if (!(data & HV_X64_MSR_HYPERCALL_ENABLE)) {
+			kvm->arch.hv_hypercall = data;
+			break;
+		}
+		gfn = data >> HV_X64_MSR_HYPERCALL_PAGE_ADDRESS_SHIFT;
+		addr = gfn_to_hva(kvm, gfn);
+		if (kvm_is_error_hva(addr))
+			return 1;
+		kvm_x86_ops->patch_hypercall(vcpu, instructions);
+		((unsigned char *)instructions)[3] = 0xc3; /* ret */
+		if (copy_to_user((void __user *)addr, instructions, 4))
+			return 1;
+		kvm->arch.hv_hypercall = data;
+		break;
+	}
+	default:
+		pr_unimpl(vcpu, "HYPER-V unimplemented wrmsr: 0x%x "
+			  "data 0x%llx\n", msr, data);
+		return 1;
+	}
+	return 0;
+}
+
+static int set_msr_hyperv(struct kvm_vcpu *vcpu, u32 msr, u64 data)
+{
+	switch (msr) {
+	case HV_X64_MSR_APIC_ASSIST_PAGE: {
+		unsigned long addr;
+
+		if (!(data & HV_X64_MSR_APIC_ASSIST_PAGE_ENABLE)) {
+			vcpu->arch.hv_vapic = data;
+			break;
+		}
+		addr = gfn_to_hva(vcpu->kvm, data >>
+				  HV_X64_MSR_APIC_ASSIST_PAGE_ADDRESS_SHIFT);
+		if (kvm_is_error_hva(addr))
+			return 1;
+		if (clear_user((void __user *)addr, PAGE_SIZE))
+			return 1;
+		vcpu->arch.hv_vapic = data;
+		break;
+	}
+	case HV_X64_MSR_EOI:
+		return kvm_hv_vapic_msr_write(vcpu, APIC_EOI, data);
+	case HV_X64_MSR_ICR:
+		return kvm_hv_vapic_msr_write(vcpu, APIC_ICR, data);
+	case HV_X64_MSR_TPR:
+		return kvm_hv_vapic_msr_write(vcpu, APIC_TASKPRI, data);
+	default:
+		pr_unimpl(vcpu, "HYPER-V unimplemented wrmsr: 0x%x "
+			  "data 0x%llx\n", msr, data);
+		return 1;
+	}
+
+	return 0;
+}
+
 int kvm_set_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 data)
 {
 	switch (msr) {
@@ -1116,6 +1214,16 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 data)
 		pr_unimpl(vcpu, "unimplemented perfctr wrmsr: "
 			"0x%x data 0x%llx\n", msr, data);
 		break;
+	case HV_X64_MSR_GUEST_OS_ID ... HV_X64_MSR_SINT15:
+		if (kvm_hv_msr_partition_wide(msr)) {
+			int r;
+			mutex_lock(&vcpu->kvm->lock);
+			r = set_msr_hyperv_pw(vcpu, msr, data);
+			mutex_unlock(&vcpu->kvm->lock);
+			return r;
+		} else
+			return set_msr_hyperv(vcpu, msr, data);
+		break;
 	default:
 		if (msr && (msr == vcpu->kvm->arch.xen_hvm_config.msr))
 			return xen_hvm_config(vcpu, data);
@@ -1215,6 +1323,54 @@ static int get_msr_mce(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata)
 	return 0;
 }
 
+static int get_msr_hyperv_pw(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata)
+{
+	u64 data = 0;
+	struct kvm *kvm = vcpu->kvm;
+
+	switch (msr) {
+	case HV_X64_MSR_GUEST_OS_ID:
+		data = kvm->arch.hv_guest_os_id;
+		break;
+	case HV_X64_MSR_HYPERCALL:
+		data = kvm->arch.hv_hypercall;
+		break;
+	default:
+		pr_unimpl(vcpu, "Hyper-V unhandled rdmsr: 0x%x\n", msr);
+		return 1;
+	}
+
+	*pdata = data;
+	return 0;
+}
+
+static int get_msr_hyperv(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata)
+{
+	u64 data = 0;
+
+	switch (msr) {
+	case HV_X64_MSR_VP_INDEX: {
+		int r;
+		struct kvm_vcpu *v;
+		kvm_for_each_vcpu(r, v, vcpu->kvm)
+			if (v == vcpu)
+				data = r;
+		break;
+	}
+	case HV_X64_MSR_EOI:
+		return kvm_hv_vapic_msr_read(vcpu, APIC_EOI, pdata);
+	case HV_X64_MSR_ICR:
+		return kvm_hv_vapic_msr_read(vcpu, APIC_ICR, pdata);
+	case HV_X64_MSR_TPR:
+		return kvm_hv_vapic_msr_read(vcpu, APIC_TASKPRI, pdata);
+	default:
+		pr_unimpl(vcpu, "Hyper-V unhandled rdmsr: 0x%x\n", msr);
+		return 1;
+	}
+	*pdata = data;
+	return 0;
+}
+
 int kvm_get_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata)
 {
 	u64 data;
@@ -1281,6 +1437,16 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata)
 	case MSR_IA32_MCG_STATUS:
 	case MSR_IA32_MC0_CTL ... MSR_IA32_MC0_CTL + 4 * KVM_MAX_MCE_BANKS - 1:
 		return get_msr_mce(vcpu, msr, pdata);
+	case HV_X64_MSR_GUEST_OS_ID ... HV_X64_MSR_SINT15:
+		if (kvm_hv_msr_partition_wide(msr)) {
+			int r;
+			mutex_lock(&vcpu->kvm->lock);
+			r = get_msr_hyperv_pw(vcpu, msr, pdata);
+			mutex_unlock(&vcpu->kvm->lock);
+			return r;
+		} else
+			return get_msr_hyperv(vcpu, msr, pdata);
+		break;
 	default:
 		if (!ignore_msrs) {
 			pr_unimpl(vcpu, "unhandled rdmsr: 0x%x\n", msr);
@@ -1396,6 +1562,9 @@ int kvm_dev_ioctl_check_extension(long ext)
 	case KVM_CAP_XEN_HVM:
 	case KVM_CAP_ADJUST_CLOCK:
 	case KVM_CAP_VCPU_EVENTS:
+	case KVM_CAP_HYPERV:
+	case KVM_CAP_HYPERV_VAPIC:
+	case KVM_CAP_HYPERV_SPIN:
 		r = 1;
 		break;
 	case KVM_CAP_COALESCED_MMIO:
@@ -1509,8 +1678,8 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 
 void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu)
 {
-	kvm_x86_ops->vcpu_put(vcpu);
 	kvm_put_guest_fpu(vcpu);
+	kvm_x86_ops->vcpu_put(vcpu);
 }
 
 static int is_efer_nx(void)
@@ -1641,10 +1810,12 @@ static void do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function,
 			 u32 index, int *nent, int maxnent)
 {
 	unsigned f_nx = is_efer_nx() ? F(NX) : 0;
-	unsigned f_gbpages = kvm_x86_ops->gb_page_enable() ? F(GBPAGES) : 0;
 #ifdef CONFIG_X86_64
+	unsigned f_gbpages = (kvm_x86_ops->get_lpage_level() == PT_PDPE_LEVEL)
+				? F(GBPAGES) : 0;
 	unsigned f_lm = F(LM);
 #else
+	unsigned f_gbpages = 0;
 	unsigned f_lm = 0;
 #endif
 	unsigned f_rdtscp = kvm_x86_ops->rdtscp_supported() ? F(RDTSCP) : 0;
@@ -3093,35 +3264,20 @@ int emulate_invlpg(struct kvm_vcpu *vcpu, gva_t address)
 
 int emulate_clts(struct kvm_vcpu *vcpu)
 {
-	kvm_x86_ops->set_cr0(vcpu, vcpu->arch.cr0 & ~X86_CR0_TS);
+	kvm_x86_ops->set_cr0(vcpu, kvm_read_cr0_bits(vcpu, ~X86_CR0_TS));
 	return X86EMUL_CONTINUE;
 }
 
 int emulator_get_dr(struct x86_emulate_ctxt *ctxt, int dr, unsigned long *dest)
 {
-	struct kvm_vcpu *vcpu = ctxt->vcpu;
-
-	switch (dr) {
-	case 0 ... 3:
-		*dest = kvm_x86_ops->get_dr(vcpu, dr);
-		return X86EMUL_CONTINUE;
-	default:
-		pr_unimpl(vcpu, "%s: unexpected dr %u\n", __func__, dr);
-		return X86EMUL_UNHANDLEABLE;
-	}
+	return kvm_x86_ops->get_dr(ctxt->vcpu, dr, dest);
 }
 
 int emulator_set_dr(struct x86_emulate_ctxt *ctxt, int dr, unsigned long value)
 {
 	unsigned long mask = (ctxt->mode == X86EMUL_MODE_PROT64) ? ~0ULL : ~0U;
-	int exception;
 
-	kvm_x86_ops->set_dr(ctxt->vcpu, dr, value & mask, &exception);
-	if (exception) {
-		/* FIXME: better handling */
-		return X86EMUL_UNHANDLEABLE;
-	}
-	return X86EMUL_CONTINUE;
+	return kvm_x86_ops->set_dr(ctxt->vcpu, dr, value & mask);
 }
 
 void kvm_report_emulation_failure(struct kvm_vcpu *vcpu, const char *context)
@@ -3614,11 +3770,77 @@ static inline gpa_t hc_gpa(struct kvm_vcpu *vcpu, unsigned long a0,
 		return a0 | ((gpa_t)a1 << 32);
 }
 
+int kvm_hv_hypercall(struct kvm_vcpu *vcpu)
+{
+	u64 param, ingpa, outgpa, ret;
+	uint16_t code, rep_idx, rep_cnt, res = HV_STATUS_SUCCESS, rep_done = 0;
+	bool fast, longmode;
+	int cs_db, cs_l;
+
+	/*
+	 * hypercall generates UD from non zero cpl and real mode
+	 * per HYPER-V spec
+	 */
+	if (kvm_x86_ops->get_cpl(vcpu) != 0 ||
+	    !kvm_read_cr0_bits(vcpu, X86_CR0_PE)) {
+		kvm_queue_exception(vcpu, UD_VECTOR);
+		return 0;
+	}
+
+	kvm_x86_ops->get_cs_db_l_bits(vcpu, &cs_db, &cs_l);
+	longmode = is_long_mode(vcpu) && cs_l == 1;
+
+	if (!longmode) {
+		param = ((u64)kvm_register_read(vcpu, VCPU_REGS_RDX) << 32) |
+			(kvm_register_read(vcpu, VCPU_REGS_RAX) & 0xffffffff);
+		ingpa = ((u64)kvm_register_read(vcpu, VCPU_REGS_RBX) << 32) |
+			(kvm_register_read(vcpu, VCPU_REGS_RCX) & 0xffffffff);
+		outgpa = ((u64)kvm_register_read(vcpu, VCPU_REGS_RDI) << 32) |
+			(kvm_register_read(vcpu, VCPU_REGS_RSI) & 0xffffffff);
+	}
+#ifdef CONFIG_X86_64
+	else {
+		param = kvm_register_read(vcpu, VCPU_REGS_RCX);
+		ingpa = kvm_register_read(vcpu, VCPU_REGS_RDX);
+		outgpa = kvm_register_read(vcpu, VCPU_REGS_R8);
+	}
+#endif
+
+	code = param & 0xffff;
+	fast = (param >> 16) & 0x1;
+	rep_cnt = (param >> 32) & 0xfff;
+	rep_idx = (param >> 48) & 0xfff;
+
+	trace_kvm_hv_hypercall(code, fast, rep_cnt, rep_idx, ingpa, outgpa);
+
+	switch (code) {
+	case HV_X64_HV_NOTIFY_LONG_SPIN_WAIT:
+		kvm_vcpu_on_spin(vcpu);
+		break;
+	default:
+		res = HV_STATUS_INVALID_HYPERCALL_CODE;
+		break;
+	}
+
+	ret = res | (((u64)rep_done & 0xfff) << 32);
+	if (longmode) {
+		kvm_register_write(vcpu, VCPU_REGS_RAX, ret);
+	} else {
+		kvm_register_write(vcpu, VCPU_REGS_RDX, ret >> 32);
+		kvm_register_write(vcpu, VCPU_REGS_RAX, ret & 0xffffffff);
+	}
+
+	return 1;
+}
+
 int kvm_emulate_hypercall(struct kvm_vcpu *vcpu)
 {
 	unsigned long nr, a0, a1, a2, a3, ret;
 	int r = 1;
 
+	if (kvm_hv_hypercall_enabled(vcpu->kvm))
+		return kvm_hv_hypercall(vcpu);
+
 	nr = kvm_register_read(vcpu, VCPU_REGS_RAX);
 	a0 = kvm_register_read(vcpu, VCPU_REGS_RBX);
 	a1 = kvm_register_read(vcpu, VCPU_REGS_RCX);
@@ -3712,7 +3934,7 @@ unsigned long realmode_get_cr(struct kvm_vcpu *vcpu, int cr)
 
 	switch (cr) {
 	case 0:
-		value = vcpu->arch.cr0;
+		value = kvm_read_cr0(vcpu);
 		break;
 	case 2:
 		value = vcpu->arch.cr2;
@@ -3739,7 +3961,7 @@ void realmode_set_cr(struct kvm_vcpu *vcpu, int cr, unsigned long val,
 {
 	switch (cr) {
 	case 0:
-		kvm_set_cr0(vcpu, mk_cr_64(vcpu->arch.cr0, val));
+		kvm_set_cr0(vcpu, mk_cr_64(kvm_read_cr0(vcpu), val));
 		*rflags = kvm_get_rflags(vcpu);
 		break;
 	case 2:
@@ -4004,6 +4226,10 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
 			r = 0;
 			goto out;
 		}
+		if (test_and_clear_bit(KVM_REQ_DEACTIVATE_FPU, &vcpu->requests)) {
+			vcpu->fpu_active = 0;
+			kvm_x86_ops->fpu_deactivate(vcpu);
+		}
 	}
 
 	preempt_disable();
@@ -4333,7 +4559,7 @@ int kvm_arch_vcpu_ioctl_get_sregs(struct kvm_vcpu *vcpu,
 	sregs->gdt.limit = dt.limit;
 	sregs->gdt.base = dt.base;
 
-	sregs->cr0 = vcpu->arch.cr0;
+	sregs->cr0 = kvm_read_cr0(vcpu);
 	sregs->cr2 = vcpu->arch.cr2;
 	sregs->cr3 = vcpu->arch.cr3;
 	sregs->cr4 = kvm_read_cr4(vcpu);
@@ -4519,7 +4745,7 @@ int kvm_load_segment_descriptor(struct kvm_vcpu *vcpu, u16 selector,
 {
 	struct kvm_segment kvm_seg;
 
-	if (is_vm86_segment(vcpu, seg) || !(vcpu->arch.cr0 & X86_CR0_PE))
+	if (is_vm86_segment(vcpu, seg) || !(kvm_read_cr0_bits(vcpu, X86_CR0_PE)))
 		return kvm_load_realmode_segment(vcpu, selector, seg);
 	if (load_segment_descriptor_to_kvm_desct(vcpu, selector, &kvm_seg))
 		return 1;
@@ -4797,7 +5023,7 @@ int kvm_task_switch(struct kvm_vcpu *vcpu, u16 tss_selector, int reason)
 					      &nseg_desc);
 	}
 
-	kvm_x86_ops->set_cr0(vcpu, vcpu->arch.cr0 | X86_CR0_TS);
+	kvm_x86_ops->set_cr0(vcpu, kvm_read_cr0(vcpu) | X86_CR0_TS);
 	seg_desct_to_kvm_desct(&nseg_desc, tss_selector, &tr_seg);
 	tr_seg.type = 11;
 	kvm_set_segment(vcpu, &tr_seg, VCPU_SREG_TR);
@@ -4832,7 +5058,7 @@ int kvm_arch_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu,
 	kvm_x86_ops->set_efer(vcpu, sregs->efer);
 	kvm_set_apic_base(vcpu, sregs->apic_base);
 
-	mmu_reset_needed |= vcpu->arch.cr0 != sregs->cr0;
+	mmu_reset_needed |= kvm_read_cr0(vcpu) != sregs->cr0;
 	kvm_x86_ops->set_cr0(vcpu, sregs->cr0);
 	vcpu->arch.cr0 = sregs->cr0;
 
@@ -4871,7 +5097,7 @@ int kvm_arch_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu,
 	/* Older userspace won't unhalt the vcpu on reset. */
 	if (kvm_vcpu_is_bsp(vcpu) && kvm_rip_read(vcpu) == 0xfff0 &&
 	    sregs->cs.selector == 0xf000 && sregs->cs.base == 0xffff0000 &&
-	    !(vcpu->arch.cr0 & X86_CR0_PE))
+	    !(kvm_read_cr0_bits(vcpu, X86_CR0_PE)))
 		vcpu->arch.mp_state = KVM_MP_STATE_RUNNABLE;
 
 	vcpu_put(vcpu);
@@ -5073,6 +5299,7 @@ void kvm_put_guest_fpu(struct kvm_vcpu *vcpu)
 	kvm_fx_save(&vcpu->arch.guest_fx_image);
 	kvm_fx_restore(&vcpu->arch.host_fx_image);
 	++vcpu->stat.fpu_reload;
+	set_bit(KVM_REQ_DEACTIVATE_FPU, &vcpu->requests);
 }
 EXPORT_SYMBOL_GPL(kvm_put_guest_fpu);
 
@@ -5305,6 +5532,7 @@ void kvm_arch_destroy_vm(struct kvm *kvm)
 		put_page(kvm->arch.apic_access_page);
 	if (kvm->arch.ept_identity_pagetable)
 		put_page(kvm->arch.ept_identity_pagetable);
+	cleanup_srcu_struct(&kvm->srcu);
 	kfree(kvm->arch.aliases);
 	kfree(kvm);
 }