Merge tag 'kvm-3.7-1' of git://git.kernel.org/pub/scm/virt/kvm/kvm

Pull KVM updates from Avi Kivity:
 "Highlights of the changes for this release include support for vfio
  level triggered interrupts, improved big real mode support on older
  Intels, a streamlines guest page table walker, guest APIC speedups,
  PIO optimizations, better overcommit handling, and read-only memory."

* tag 'kvm-3.7-1' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (138 commits)
  KVM: s390: Fix vcpu_load handling in interrupt code
  KVM: x86: Fix guest debug across vcpu INIT reset
  KVM: Add resampling irqfds for level triggered interrupts
  KVM: optimize apic interrupt delivery
  KVM: MMU: Eliminate pointless temporary 'ac'
  KVM: MMU: Avoid access/dirty update loop if all is well
  KVM: MMU: Eliminate eperm temporary
  KVM: MMU: Optimize is_last_gpte()
  KVM: MMU: Simplify walk_addr_generic() loop
  KVM: MMU: Optimize pte permission checks
  KVM: MMU: Update accessed and dirty bits after guest pagetable walk
  KVM: MMU: Move gpte_access() out of paging_tmpl.h
  KVM: MMU: Optimize gpte_access() slightly
  KVM: MMU: Push clean gpte write protection out of gpte_access()
  KVM: clarify kvmclock documentation
  KVM: make processes waiting on vcpu mutex killable
  KVM: SVM: Make use of asm.h
  KVM: VMX: Make use of asm.h
  KVM: VMX: Make lto-friendly
  KVM: x86: lapic: Clean up find_highest_vector() and count_vectors()
  ...

Conflicts:
	arch/s390/include/asm/processor.h
	arch/x86/kvm/i8259.c

arch/x86/kvm/vmx.c

@@ -127,6 +127,8 @@ module_param(ple_gap, int, S_IRUGO);
 static int ple_window = KVM_VMX_DEFAULT_PLE_WINDOW;
 module_param(ple_window, int, S_IRUGO);
 
+extern const ulong vmx_return;
+
 #define NR_AUTOLOAD_MSRS 8
 #define VMCS02_POOL_SIZE 1
 
@@ -405,16 +407,16 @@ struct vcpu_vmx {
 	struct {
 		int vm86_active;
 		ulong save_rflags;
+		struct kvm_segment segs[8];
+	} rmode;
+	struct {
+		u32 bitmask; /* 4 bits per segment (1 bit per field) */
 		struct kvm_save_segment {
 			u16 selector;
 			unsigned long base;
 			u32 limit;
 			u32 ar;
-		} tr, es, ds, fs, gs;
-	} rmode;
-	struct {
-		u32 bitmask; /* 4 bits per segment (1 bit per field) */
-		struct kvm_save_segment seg[8];
+		} seg[8];
 	} segment_cache;
 	int vpid;
 	bool emulation_required;
@@ -450,7 +452,7 @@ static inline struct vcpu_vmx *to_vmx(struct kvm_vcpu *vcpu)
 #define FIELD64(number, name)	[number] = VMCS12_OFFSET(name), \
 				[number##_HIGH] = VMCS12_OFFSET(name)+4
 
-static unsigned short vmcs_field_to_offset_table[] = {
+static const unsigned short vmcs_field_to_offset_table[] = {
 	FIELD(VIRTUAL_PROCESSOR_ID, virtual_processor_id),
 	FIELD(GUEST_ES_SELECTOR, guest_es_selector),
 	FIELD(GUEST_CS_SELECTOR, guest_cs_selector),
@@ -596,10 +598,9 @@ static inline struct vmcs12 *get_vmcs12(struct kvm_vcpu *vcpu)
 static struct page *nested_get_page(struct kvm_vcpu *vcpu, gpa_t addr)
 {
 	struct page *page = gfn_to_page(vcpu->kvm, addr >> PAGE_SHIFT);
-	if (is_error_page(page)) {
-		kvm_release_page_clean(page);
+	if (is_error_page(page))
 		return NULL;
-	}
+
 	return page;
 }
 
@@ -667,7 +668,7 @@ static struct vmx_capability {
 		.ar_bytes = GUEST_##seg##_AR_BYTES,	   	\
 	}
 
-static struct kvm_vmx_segment_field {
+static const struct kvm_vmx_segment_field {
 	unsigned selector;
 	unsigned base;
 	unsigned limit;
@@ -1343,7 +1344,7 @@ static bool update_transition_efer(struct vcpu_vmx *vmx, int efer_offset)
 	guest_efer = vmx->vcpu.arch.efer;
 
 	/*
-	 * NX is emulated; LMA and LME handled by hardware; SCE meaninless
+	 * NX is emulated; LMA and LME handled by hardware; SCE meaningless
 	 * outside long mode
 	 */
 	ignore_bits = EFER_NX | EFER_SCE;
@@ -1995,7 +1996,7 @@ static __init void nested_vmx_setup_ctls_msrs(void)
 #endif
 		CPU_BASED_MOV_DR_EXITING | CPU_BASED_UNCOND_IO_EXITING |
 		CPU_BASED_USE_IO_BITMAPS | CPU_BASED_MONITOR_EXITING |
-		CPU_BASED_RDPMC_EXITING |
+		CPU_BASED_RDPMC_EXITING | CPU_BASED_RDTSC_EXITING |
 		CPU_BASED_ACTIVATE_SECONDARY_CONTROLS;
 	/*
 	 * We can allow some features even when not supported by the
@@ -2291,16 +2292,6 @@ static void vmx_cache_reg(struct kvm_vcpu *vcpu, enum kvm_reg reg)
 	}
 }
 
-static void set_guest_debug(struct kvm_vcpu *vcpu, struct kvm_guest_debug *dbg)
-{
-	if (vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP)
-		vmcs_writel(GUEST_DR7, dbg->arch.debugreg[7]);
-	else
-		vmcs_writel(GUEST_DR7, vcpu->arch.dr7);
-
-	update_exception_bitmap(vcpu);
-}
-
 static __init int cpu_has_kvm_support(void)
 {
 	return cpu_has_vmx();
@@ -2698,20 +2689,17 @@ static __exit void hardware_unsetup(void)
 	free_kvm_area();
 }
 
-static void fix_pmode_dataseg(int seg, struct kvm_save_segment *save)
+static void fix_pmode_dataseg(struct kvm_vcpu *vcpu, int seg, struct kvm_segment *save)
 {
-	struct kvm_vmx_segment_field *sf = &kvm_vmx_segment_fields[seg];
+	const struct kvm_vmx_segment_field *sf = &kvm_vmx_segment_fields[seg];
+	struct kvm_segment tmp = *save;
 
-	if (vmcs_readl(sf->base) == save->base && (save->base & AR_S_MASK)) {
-		vmcs_write16(sf->selector, save->selector);
-		vmcs_writel(sf->base, save->base);
-		vmcs_write32(sf->limit, save->limit);
-		vmcs_write32(sf->ar_bytes, save->ar);
-	} else {
-		u32 dpl = (vmcs_read16(sf->selector) & SELECTOR_RPL_MASK)
-			<< AR_DPL_SHIFT;
-		vmcs_write32(sf->ar_bytes, 0x93 | dpl);
+	if (!(vmcs_readl(sf->base) == tmp.base && tmp.s)) {
+		tmp.base = vmcs_readl(sf->base);
+		tmp.selector = vmcs_read16(sf->selector);
+		tmp.s = 1;
 	}
+	vmx_set_segment(vcpu, &tmp, seg);
 }
 
 static void enter_pmode(struct kvm_vcpu *vcpu)
@@ -2724,10 +2712,7 @@ static void enter_pmode(struct kvm_vcpu *vcpu)
 
 	vmx_segment_cache_clear(vmx);
 
-	vmcs_write16(GUEST_TR_SELECTOR, vmx->rmode.tr.selector);
-	vmcs_writel(GUEST_TR_BASE, vmx->rmode.tr.base);
-	vmcs_write32(GUEST_TR_LIMIT, vmx->rmode.tr.limit);
-	vmcs_write32(GUEST_TR_AR_BYTES, vmx->rmode.tr.ar);
+	vmx_set_segment(vcpu, &vmx->rmode.segs[VCPU_SREG_TR], VCPU_SREG_TR);
 
 	flags = vmcs_readl(GUEST_RFLAGS);
 	flags &= RMODE_GUEST_OWNED_EFLAGS_BITS;
@@ -2742,10 +2727,10 @@ static void enter_pmode(struct kvm_vcpu *vcpu)
 	if (emulate_invalid_guest_state)
 		return;
 
-	fix_pmode_dataseg(VCPU_SREG_ES, &vmx->rmode.es);
-	fix_pmode_dataseg(VCPU_SREG_DS, &vmx->rmode.ds);
-	fix_pmode_dataseg(VCPU_SREG_GS, &vmx->rmode.gs);
-	fix_pmode_dataseg(VCPU_SREG_FS, &vmx->rmode.fs);
+	fix_pmode_dataseg(vcpu, VCPU_SREG_ES, &vmx->rmode.segs[VCPU_SREG_ES]);
+	fix_pmode_dataseg(vcpu, VCPU_SREG_DS, &vmx->rmode.segs[VCPU_SREG_DS]);
+	fix_pmode_dataseg(vcpu, VCPU_SREG_FS, &vmx->rmode.segs[VCPU_SREG_FS]);
+	fix_pmode_dataseg(vcpu, VCPU_SREG_GS, &vmx->rmode.segs[VCPU_SREG_GS]);
 
 	vmx_segment_cache_clear(vmx);
 
@@ -2773,14 +2758,10 @@ static gva_t rmode_tss_base(struct kvm *kvm)
 	return kvm->arch.tss_addr;
 }
 
-static void fix_rmode_seg(int seg, struct kvm_save_segment *save)
+static void fix_rmode_seg(int seg, struct kvm_segment *save)
 {
-	struct kvm_vmx_segment_field *sf = &kvm_vmx_segment_fields[seg];
+	const struct kvm_vmx_segment_field *sf = &kvm_vmx_segment_fields[seg];
 
-	save->selector = vmcs_read16(sf->selector);
-	save->base = vmcs_readl(sf->base);
-	save->limit = vmcs_read32(sf->limit);
-	save->ar = vmcs_read32(sf->ar_bytes);
 	vmcs_write16(sf->selector, save->base >> 4);
 	vmcs_write32(sf->base, save->base & 0xffff0);
 	vmcs_write32(sf->limit, 0xffff);
@@ -2800,9 +2781,16 @@ static void enter_rmode(struct kvm_vcpu *vcpu)
 	if (enable_unrestricted_guest)
 		return;
 
+	vmx_get_segment(vcpu, &vmx->rmode.segs[VCPU_SREG_TR], VCPU_SREG_TR);
+	vmx_get_segment(vcpu, &vmx->rmode.segs[VCPU_SREG_ES], VCPU_SREG_ES);
+	vmx_get_segment(vcpu, &vmx->rmode.segs[VCPU_SREG_DS], VCPU_SREG_DS);
+	vmx_get_segment(vcpu, &vmx->rmode.segs[VCPU_SREG_FS], VCPU_SREG_FS);
+	vmx_get_segment(vcpu, &vmx->rmode.segs[VCPU_SREG_GS], VCPU_SREG_GS);
+
 	vmx->emulation_required = 1;
 	vmx->rmode.vm86_active = 1;
 
+
 	/*
 	 * Very old userspace does not call KVM_SET_TSS_ADDR before entering
 	 * vcpu. Call it here with phys address pointing 16M below 4G.
@@ -2817,14 +2805,8 @@ static void enter_rmode(struct kvm_vcpu *vcpu)
 
 	vmx_segment_cache_clear(vmx);
 
-	vmx->rmode.tr.selector = vmcs_read16(GUEST_TR_SELECTOR);
-	vmx->rmode.tr.base = vmcs_readl(GUEST_TR_BASE);
 	vmcs_writel(GUEST_TR_BASE, rmode_tss_base(vcpu->kvm));
-
-	vmx->rmode.tr.limit = vmcs_read32(GUEST_TR_LIMIT);
 	vmcs_write32(GUEST_TR_LIMIT, RMODE_TSS_SIZE - 1);
-
-	vmx->rmode.tr.ar = vmcs_read32(GUEST_TR_AR_BYTES);
 	vmcs_write32(GUEST_TR_AR_BYTES, 0x008b);
 
 	flags = vmcs_readl(GUEST_RFLAGS);
@@ -3117,35 +3099,24 @@ static void vmx_get_segment(struct kvm_vcpu *vcpu,
 			    struct kvm_segment *var, int seg)
 {
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
-	struct kvm_save_segment *save;
 	u32 ar;
 
 	if (vmx->rmode.vm86_active
 	    && (seg == VCPU_SREG_TR || seg == VCPU_SREG_ES
 		|| seg == VCPU_SREG_DS || seg == VCPU_SREG_FS
-		|| seg == VCPU_SREG_GS)
-	    && !emulate_invalid_guest_state) {
-		switch (seg) {
-		case VCPU_SREG_TR: save = &vmx->rmode.tr; break;
-		case VCPU_SREG_ES: save = &vmx->rmode.es; break;
-		case VCPU_SREG_DS: save = &vmx->rmode.ds; break;
-		case VCPU_SREG_FS: save = &vmx->rmode.fs; break;
-		case VCPU_SREG_GS: save = &vmx->rmode.gs; break;
-		default: BUG();
-		}
-		var->selector = save->selector;
-		var->base = save->base;
-		var->limit = save->limit;
-		ar = save->ar;
+		|| seg == VCPU_SREG_GS)) {
+		*var = vmx->rmode.segs[seg];
 		if (seg == VCPU_SREG_TR
 		    || var->selector == vmx_read_guest_seg_selector(vmx, seg))
-			goto use_saved_rmode_seg;
+			return;
+		var->base = vmx_read_guest_seg_base(vmx, seg);
+		var->selector = vmx_read_guest_seg_selector(vmx, seg);
+		return;
 	}
 	var->base = vmx_read_guest_seg_base(vmx, seg);
 	var->limit = vmx_read_guest_seg_limit(vmx, seg);
 	var->selector = vmx_read_guest_seg_selector(vmx, seg);
 	ar = vmx_read_guest_seg_ar(vmx, seg);
-use_saved_rmode_seg:
 	if ((ar & AR_UNUSABLE_MASK) && !emulate_invalid_guest_state)
 		ar = 0;
 	var->type = ar & 15;
@@ -3227,23 +3198,21 @@ static void vmx_set_segment(struct kvm_vcpu *vcpu,
 			    struct kvm_segment *var, int seg)
 {
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
-	struct kvm_vmx_segment_field *sf = &kvm_vmx_segment_fields[seg];
+	const struct kvm_vmx_segment_field *sf = &kvm_vmx_segment_fields[seg];
 	u32 ar;
 
 	vmx_segment_cache_clear(vmx);
 
 	if (vmx->rmode.vm86_active && seg == VCPU_SREG_TR) {
 		vmcs_write16(sf->selector, var->selector);
-		vmx->rmode.tr.selector = var->selector;
-		vmx->rmode.tr.base = var->base;
-		vmx->rmode.tr.limit = var->limit;
-		vmx->rmode.tr.ar = vmx_segment_access_rights(var);
+		vmx->rmode.segs[VCPU_SREG_TR] = *var;
 		return;
 	}
 	vmcs_writel(sf->base, var->base);
 	vmcs_write32(sf->limit, var->limit);
 	vmcs_write16(sf->selector, var->selector);
 	if (vmx->rmode.vm86_active && var->s) {
+		vmx->rmode.segs[seg] = *var;
 		/*
 		 * Hack real-mode segments into vm86 compatibility.
 		 */
@@ -3258,7 +3227,7 @@ static void vmx_set_segment(struct kvm_vcpu *vcpu,
 	 * qemu binaries.
 	 *   IA32 arch specifies that at the time of processor reset the
 	 * "Accessed" bit in the AR field of segment registers is 1. And qemu
-	 * is setting it to 0 in the usedland code. This causes invalid guest
+	 * is setting it to 0 in the userland code. This causes invalid guest
 	 * state vmexit when "unrestricted guest" mode is turned on.
 	 *    Fix for this setup issue in cpu_reset is being pushed in the qemu
 	 * tree. Newer qemu binaries with that qemu fix would not need this
@@ -3288,16 +3257,10 @@ static void vmx_set_segment(struct kvm_vcpu *vcpu,
 				     vmcs_readl(GUEST_CS_BASE) >> 4);
 			break;
 		case VCPU_SREG_ES:
-			fix_rmode_seg(VCPU_SREG_ES, &vmx->rmode.es);
-			break;
 		case VCPU_SREG_DS:
-			fix_rmode_seg(VCPU_SREG_DS, &vmx->rmode.ds);
-			break;
 		case VCPU_SREG_GS:
-			fix_rmode_seg(VCPU_SREG_GS, &vmx->rmode.gs);
-			break;
 		case VCPU_SREG_FS:
-			fix_rmode_seg(VCPU_SREG_FS, &vmx->rmode.fs);
+			fix_rmode_seg(seg, &vmx->rmode.segs[seg]);
 			break;
 		case VCPU_SREG_SS:
 			vmcs_write16(GUEST_SS_SELECTOR,
@@ -3351,9 +3314,9 @@ static bool rmode_segment_valid(struct kvm_vcpu *vcpu, int seg)
 
 	if (var.base != (var.selector << 4))
 		return false;
-	if (var.limit != 0xffff)
+	if (var.limit < 0xffff)
 		return false;
-	if (ar != 0xf3)
+	if (((ar | (3 << AR_DPL_SHIFT)) & ~(AR_G_MASK | AR_DB_MASK)) != 0xf3)
 		return false;
 
 	return true;
@@ -3605,7 +3568,7 @@ out:
 
 static void seg_setup(int seg)
 {
-	struct kvm_vmx_segment_field *sf = &kvm_vmx_segment_fields[seg];
+	const struct kvm_vmx_segment_field *sf = &kvm_vmx_segment_fields[seg];
 	unsigned int ar;
 
 	vmcs_write16(sf->selector, 0);
@@ -3770,8 +3733,7 @@ static void vmx_set_constant_host_state(void)
 	native_store_idt(&dt);
 	vmcs_writel(HOST_IDTR_BASE, dt.address);   /* 22.2.4 */
 
-	asm("mov $.Lkvm_vmx_return, %0" : "=r"(tmpl));
-	vmcs_writel(HOST_RIP, tmpl); /* 22.2.5 */
+	vmcs_writel(HOST_RIP, vmx_return); /* 22.2.5 */
 
 	rdmsr(MSR_IA32_SYSENTER_CS, low32, high32);
 	vmcs_write32(HOST_IA32_SYSENTER_CS, low32);
@@ -4005,8 +3967,6 @@ static int vmx_vcpu_reset(struct kvm_vcpu *vcpu)
 		kvm_rip_write(vcpu, 0);
 	kvm_register_write(vcpu, VCPU_REGS_RSP, 0);
 
-	vmcs_writel(GUEST_DR7, 0x400);
-
 	vmcs_writel(GUEST_GDTR_BASE, 0);
 	vmcs_write32(GUEST_GDTR_LIMIT, 0xffff);
 
@@ -4456,7 +4416,7 @@ vmx_patch_hypercall(struct kvm_vcpu *vcpu, unsigned char *hypercall)
 	hypercall[2] = 0xc1;
 }
 
-/* called to set cr0 as approriate for a mov-to-cr0 exit. */
+/* called to set cr0 as appropriate for a mov-to-cr0 exit. */
 static int handle_set_cr0(struct kvm_vcpu *vcpu, unsigned long val)
 {
 	if (to_vmx(vcpu)->nested.vmxon &&
@@ -5701,7 +5661,7 @@ static int handle_vmptrst(struct kvm_vcpu *vcpu)
  * may resume.  Otherwise they set the kvm_run parameter to indicate what needs
  * to be done to userspace and return 0.
  */
-static int (*kvm_vmx_exit_handlers[])(struct kvm_vcpu *vcpu) = {
+static int (*const kvm_vmx_exit_handlers[])(struct kvm_vcpu *vcpu) = {
 	[EXIT_REASON_EXCEPTION_NMI]           = handle_exception,
 	[EXIT_REASON_EXTERNAL_INTERRUPT]      = handle_external_interrupt,
 	[EXIT_REASON_TRIPLE_FAULT]            = handle_triple_fault,
@@ -6229,17 +6189,10 @@ static void atomic_switch_perf_msrs(struct vcpu_vmx *vmx)
 					msrs[i].host);
 }
 
-#ifdef CONFIG_X86_64
-#define R "r"
-#define Q "q"
-#else
-#define R "e"
-#define Q "l"
-#endif
-
 static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
+	unsigned long debugctlmsr;
 
 	if (is_guest_mode(vcpu) && !vmx->nested.nested_run_pending) {
 		struct vmcs12 *vmcs12 = get_vmcs12(vcpu);
@@ -6279,34 +6232,35 @@ static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu)
 		vmx_set_interrupt_shadow(vcpu, 0);
 
 	atomic_switch_perf_msrs(vmx);
+	debugctlmsr = get_debugctlmsr();
 
 	vmx->__launched = vmx->loaded_vmcs->launched;
 	asm(
 		/* Store host registers */
-		"push %%"R"dx; push %%"R"bp;"
-		"push %%"R"cx \n\t" /* placeholder for guest rcx */
-		"push %%"R"cx \n\t"
-		"cmp %%"R"sp, %c[host_rsp](%0) \n\t"
+		"push %%" _ASM_DX "; push %%" _ASM_BP ";"
+		"push %%" _ASM_CX " \n\t" /* placeholder for guest rcx */
+		"push %%" _ASM_CX " \n\t"
+		"cmp %%" _ASM_SP ", %c[host_rsp](%0) \n\t"
 		"je 1f \n\t"
-		"mov %%"R"sp, %c[host_rsp](%0) \n\t"
+		"mov %%" _ASM_SP ", %c[host_rsp](%0) \n\t"
 		__ex(ASM_VMX_VMWRITE_RSP_RDX) "\n\t"
 		"1: \n\t"
 		/* Reload cr2 if changed */
-		"mov %c[cr2](%0), %%"R"ax \n\t"
-		"mov %%cr2, %%"R"dx \n\t"
-		"cmp %%"R"ax, %%"R"dx \n\t"
+		"mov %c[cr2](%0), %%" _ASM_AX " \n\t"
+		"mov %%cr2, %%" _ASM_DX " \n\t"
+		"cmp %%" _ASM_AX ", %%" _ASM_DX " \n\t"
 		"je 2f \n\t"
-		"mov %%"R"ax, %%cr2 \n\t"
+		"mov %%" _ASM_AX", %%cr2 \n\t"
 		"2: \n\t"
 		/* Check if vmlaunch of vmresume is needed */
 		"cmpl $0, %c[launched](%0) \n\t"
 		/* Load guest registers.  Don't clobber flags. */
-		"mov %c[rax](%0), %%"R"ax \n\t"
-		"mov %c[rbx](%0), %%"R"bx \n\t"
-		"mov %c[rdx](%0), %%"R"dx \n\t"
-		"mov %c[rsi](%0), %%"R"si \n\t"
-		"mov %c[rdi](%0), %%"R"di \n\t"
-		"mov %c[rbp](%0), %%"R"bp \n\t"
+		"mov %c[rax](%0), %%" _ASM_AX " \n\t"
+		"mov %c[rbx](%0), %%" _ASM_BX " \n\t"
+		"mov %c[rdx](%0), %%" _ASM_DX " \n\t"
+		"mov %c[rsi](%0), %%" _ASM_SI " \n\t"
+		"mov %c[rdi](%0), %%" _ASM_DI " \n\t"
+		"mov %c[rbp](%0), %%" _ASM_BP " \n\t"
 #ifdef CONFIG_X86_64
 		"mov %c[r8](%0),  %%r8  \n\t"
 		"mov %c[r9](%0),  %%r9  \n\t"
@@ -6317,24 +6271,24 @@ static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu)
 		"mov %c[r14](%0), %%r14 \n\t"
 		"mov %c[r15](%0), %%r15 \n\t"
 #endif
-		"mov %c[rcx](%0), %%"R"cx \n\t" /* kills %0 (ecx) */
+		"mov %c[rcx](%0), %%" _ASM_CX " \n\t" /* kills %0 (ecx) */
 
 		/* Enter guest mode */
-		"jne .Llaunched \n\t"
+		"jne 1f \n\t"
 		__ex(ASM_VMX_VMLAUNCH) "\n\t"
-		"jmp .Lkvm_vmx_return \n\t"
-		".Llaunched: " __ex(ASM_VMX_VMRESUME) "\n\t"
-		".Lkvm_vmx_return: "
+		"jmp 2f \n\t"
+		"1: " __ex(ASM_VMX_VMRESUME) "\n\t"
+		"2: "
 		/* Save guest registers, load host registers, keep flags */
-		"mov %0, %c[wordsize](%%"R"sp) \n\t"
+		"mov %0, %c[wordsize](%%" _ASM_SP ") \n\t"
 		"pop %0 \n\t"
-		"mov %%"R"ax, %c[rax](%0) \n\t"
-		"mov %%"R"bx, %c[rbx](%0) \n\t"
-		"pop"Q" %c[rcx](%0) \n\t"
-		"mov %%"R"dx, %c[rdx](%0) \n\t"
-		"mov %%"R"si, %c[rsi](%0) \n\t"
-		"mov %%"R"di, %c[rdi](%0) \n\t"
-		"mov %%"R"bp, %c[rbp](%0) \n\t"
+		"mov %%" _ASM_AX ", %c[rax](%0) \n\t"
+		"mov %%" _ASM_BX ", %c[rbx](%0) \n\t"
+		__ASM_SIZE(pop) " %c[rcx](%0) \n\t"
+		"mov %%" _ASM_DX ", %c[rdx](%0) \n\t"
+		"mov %%" _ASM_SI ", %c[rsi](%0) \n\t"
+		"mov %%" _ASM_DI ", %c[rdi](%0) \n\t"
+		"mov %%" _ASM_BP ", %c[rbp](%0) \n\t"
 #ifdef CONFIG_X86_64
 		"mov %%r8,  %c[r8](%0) \n\t"
 		"mov %%r9,  %c[r9](%0) \n\t"
@@ -6345,11 +6299,15 @@ static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu)
 		"mov %%r14, %c[r14](%0) \n\t"
 		"mov %%r15, %c[r15](%0) \n\t"
 #endif
-		"mov %%cr2, %%"R"ax   \n\t"
-		"mov %%"R"ax, %c[cr2](%0) \n\t"
+		"mov %%cr2, %%" _ASM_AX "   \n\t"
+		"mov %%" _ASM_AX ", %c[cr2](%0) \n\t"
 
-		"pop  %%"R"bp; pop  %%"R"dx \n\t"
+		"pop  %%" _ASM_BP "; pop  %%" _ASM_DX " \n\t"
 		"setbe %c[fail](%0) \n\t"
+		".pushsection .rodata \n\t"
+		".global vmx_return \n\t"
+		"vmx_return: " _ASM_PTR " 2b \n\t"
+		".popsection"
 	      : : "c"(vmx), "d"((unsigned long)HOST_RSP),
 		[launched]"i"(offsetof(struct vcpu_vmx, __launched)),
 		[fail]"i"(offsetof(struct vcpu_vmx, fail)),
@@ -6374,12 +6332,18 @@ static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu)
 		[cr2]"i"(offsetof(struct vcpu_vmx, vcpu.arch.cr2)),
 		[wordsize]"i"(sizeof(ulong))
 	      : "cc", "memory"
-		, R"ax", R"bx", R"di", R"si"
 #ifdef CONFIG_X86_64
+		, "rax", "rbx", "rdi", "rsi"
 		, "r8", "r9", "r10", "r11", "r12", "r13", "r14", "r15"
+#else
+		, "eax", "ebx", "edi", "esi"
 #endif
 	      );
 
+	/* MSR_IA32_DEBUGCTLMSR is zeroed on vmexit. Restore it if needed */
+	if (debugctlmsr)
+		update_debugctlmsr(debugctlmsr);
+
 #ifndef CONFIG_X86_64
 	/*
 	 * The sysexit path does not restore ds/es, so we must set them to
@@ -6424,9 +6388,6 @@ static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu)
 	vmx_complete_interrupts(vmx);
 }
 
-#undef R
-#undef Q
-
 static void vmx_free_vcpu(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
@@ -7281,7 +7242,7 @@ static struct kvm_x86_ops vmx_x86_ops = {
 	.vcpu_load = vmx_vcpu_load,
 	.vcpu_put = vmx_vcpu_put,
 
-	.set_guest_debug = set_guest_debug,
+	.update_db_bp_intercept = update_exception_bitmap,
 	.get_msr = vmx_get_msr,
 	.set_msr = vmx_set_msr,
 	.get_segment_base = vmx_get_segment_base,