Merge tag 'kvm-3.15-1' of git://git.kernel.org/pub/scm/virt/kvm/kvm

Pull kvm updates from Paolo Bonzini:
 "PPC and ARM do not have much going on this time.  Most of the cool
  stuff, instead, is in s390 and (after a few releases) x86.

  ARM has some caching fixes and PPC has transactional memory support in
  guests.  MIPS has some fixes, with more probably coming in 3.16 as
  QEMU will soon get support for MIPS KVM.

  For x86 there are optimizations for debug registers, which trigger on
  some Windows games, and other important fixes for Windows guests.  We
  now expose to the guest Broadwell instruction set extensions and also
  Intel MPX.  There's also a fix/workaround for OS X guests, nested
  virtualization features (preemption timer), and a couple kvmclock
  refinements.

  For s390, the main news is asynchronous page faults, together with
  improvements to IRQs (floating irqs and adapter irqs) that speed up
  virtio devices"

* tag 'kvm-3.15-1' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (96 commits)
  KVM: PPC: Book3S HV: Save/restore host PMU registers that are new in POWER8
  KVM: PPC: Book3S HV: Fix decrementer timeouts with non-zero TB offset
  KVM: PPC: Book3S HV: Don't use kvm_memslots() in real mode
  KVM: PPC: Book3S HV: Return ENODEV error rather than EIO
  KVM: PPC: Book3S: Trim top 4 bits of physical address in RTAS code
  KVM: PPC: Book3S HV: Add get/set_one_reg for new TM state
  KVM: PPC: Book3S HV: Add transactional memory support
  KVM: Specify byte order for KVM_EXIT_MMIO
  KVM: vmx: fix MPX detection
  KVM: PPC: Book3S HV: Fix KVM hang with CONFIG_KVM_XICS=n
  KVM: PPC: Book3S: Introduce hypervisor call H_GET_TCE
  KVM: PPC: Book3S HV: Fix incorrect userspace exit on ioeventfd write
  KVM: s390: clear local interrupts at cpu initial reset
  KVM: s390: Fix possible memory leak in SIGP functions
  KVM: s390: fix calculation of idle_mask array size
  KVM: s390: randomize sca address
  KVM: ioapic: reinject pending interrupts on KVM_SET_IRQCHIP
  KVM: Bump KVM_MAX_IRQ_ROUTES for s390
  KVM: s390: irq routing for adapter interrupts.
  KVM: s390: adapter interrupt sources
  ...

8 files changed, 443 insertions, 179 deletions

diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c
index e5503d8..bea6067 100644
--- a/arch/x86/kvm/cpuid.c
+++ b/arch/x86/kvm/cpuid.c
@@ -28,7 +28,7 @@ static u32 xstate_required_size(u64 xstate_bv)
 	int feature_bit = 0;
 	u32 ret = XSAVE_HDR_SIZE + XSAVE_HDR_OFFSET;
 
-	xstate_bv &= ~XSTATE_FPSSE;
+	xstate_bv &= XSTATE_EXTEND_MASK;
 	while (xstate_bv) {
 		if (xstate_bv & 0x1) {
 		        u32 eax, ebx, ecx, edx;
@@ -43,6 +43,16 @@ static u32 xstate_required_size(u64 xstate_bv)
 	return ret;
 }
 
+u64 kvm_supported_xcr0(void)
+{
+	u64 xcr0 = KVM_SUPPORTED_XCR0 & host_xcr0;
+
+	if (!kvm_x86_ops->mpx_supported())
+		xcr0 &= ~(XSTATE_BNDREGS | XSTATE_BNDCSR);
+
+	return xcr0;
+}
+
 void kvm_update_cpuid(struct kvm_vcpu *vcpu)
 {
 	struct kvm_cpuid_entry2 *best;
@@ -73,9 +83,9 @@ void kvm_update_cpuid(struct kvm_vcpu *vcpu)
 	} else {
 		vcpu->arch.guest_supported_xcr0 =
 			(best->eax | ((u64)best->edx << 32)) &
-			host_xcr0 & KVM_SUPPORTED_XCR0;
-		vcpu->arch.guest_xstate_size =
-			xstate_required_size(vcpu->arch.guest_supported_xcr0);
+			kvm_supported_xcr0();
+		vcpu->arch.guest_xstate_size = best->ebx =
+			xstate_required_size(vcpu->arch.xcr0);
 	}
 
 	kvm_pmu_cpuid_update(vcpu);
@@ -210,13 +220,6 @@ static void do_cpuid_1_ent(struct kvm_cpuid_entry2 *entry, u32 function,
 	entry->flags = 0;
 }
 
-static bool supported_xcr0_bit(unsigned bit)
-{
-	u64 mask = ((u64)1 << bit);
-
-	return mask & KVM_SUPPORTED_XCR0 & host_xcr0;
-}
-
 #define F(x) bit(X86_FEATURE_##x)
 
 static int __do_cpuid_ent_emulated(struct kvm_cpuid_entry2 *entry,
@@ -256,6 +259,7 @@ static inline int __do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function,
 #endif
 	unsigned f_rdtscp = kvm_x86_ops->rdtscp_supported() ? F(RDTSCP) : 0;
 	unsigned f_invpcid = kvm_x86_ops->invpcid_supported() ? F(INVPCID) : 0;
+	unsigned f_mpx = kvm_x86_ops->mpx_supported() ? F(MPX) : 0;
 
 	/* cpuid 1.edx */
 	const u32 kvm_supported_word0_x86_features =
@@ -303,7 +307,8 @@ static inline int __do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function,
 	/* cpuid 7.0.ebx */
 	const u32 kvm_supported_word9_x86_features =
 		F(FSGSBASE) | F(BMI1) | F(HLE) | F(AVX2) | F(SMEP) |
-		F(BMI2) | F(ERMS) | f_invpcid | F(RTM);
+		F(BMI2) | F(ERMS) | f_invpcid | F(RTM) | f_mpx | F(RDSEED) |
+		F(ADX);
 
 	/* all calls to cpuid_count() should be made on the same cpu */
 	get_cpu();
@@ -436,16 +441,18 @@ static inline int __do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function,
 	}
 	case 0xd: {
 		int idx, i;
+		u64 supported = kvm_supported_xcr0();
 
-		entry->eax &= host_xcr0 & KVM_SUPPORTED_XCR0;
-		entry->edx &= (host_xcr0 & KVM_SUPPORTED_XCR0) >> 32;
+		entry->eax &= supported;
+		entry->edx &= supported >> 32;
 		entry->flags |= KVM_CPUID_FLAG_SIGNIFCANT_INDEX;
 		for (idx = 1, i = 1; idx < 64; ++idx) {
+			u64 mask = ((u64)1 << idx);
 			if (*nent >= maxnent)
 				goto out;
 
 			do_cpuid_1_ent(&entry[i], function, idx);
-			if (entry[i].eax == 0 || !supported_xcr0_bit(idx))
+			if (entry[i].eax == 0 || !(supported & mask))
 				continue;
 			entry[i].flags |=
 			       KVM_CPUID_FLAG_SIGNIFCANT_INDEX;
diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index 07ffca0..205b17e 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -3668,6 +3668,10 @@ static const struct gprefix pfx_vmovntpx = {
 	I(0, em_mov), N, N, N,
 };
 
+static const struct gprefix pfx_0f_28_0f_29 = {
+	I(Aligned, em_mov), I(Aligned, em_mov), N, N,
+};
+
 static const struct escape escape_d9 = { {
 	N, N, N, N, N, N, N, I(DstMem, em_fnstcw),
 }, {
@@ -3870,7 +3874,9 @@ static const struct opcode twobyte_table[256] = {
 	IIP(ModRM | SrcMem | Priv | Op3264, em_cr_write, cr_write, check_cr_write),
 	IIP(ModRM | SrcMem | Priv | Op3264, em_dr_write, dr_write, check_dr_write),
 	N, N, N, N,
-	N, N, N, GP(ModRM | DstMem | SrcReg | Sse | Mov | Aligned, &pfx_vmovntpx),
+	GP(ModRM | DstReg | SrcMem | Mov | Sse, &pfx_0f_28_0f_29),
+	GP(ModRM | DstMem | SrcReg | Mov | Sse, &pfx_0f_28_0f_29),
+	N, GP(ModRM | DstMem | SrcReg | Sse | Mov | Aligned, &pfx_vmovntpx),
 	N, N, N, N,
 	/* 0x30 - 0x3F */
 	II(ImplicitOps | Priv, em_wrmsr, wrmsr),
diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index 9b53135..f5704d9 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -3329,7 +3329,7 @@ static int kvm_arch_setup_async_pf(struct kvm_vcpu *vcpu, gva_t gva, gfn_t gfn)
 	arch.direct_map = vcpu->arch.mmu.direct_map;
 	arch.cr3 = vcpu->arch.mmu.get_cr3(vcpu);
 
-	return kvm_setup_async_pf(vcpu, gva, gfn, &arch);
+	return kvm_setup_async_pf(vcpu, gva, gfn_to_hva(vcpu->kvm, gfn), &arch);
 }
 
 static bool can_do_async_pf(struct kvm_vcpu *vcpu)
diff --git a/arch/x86/kvm/paging_tmpl.h b/arch/x86/kvm/paging_tmpl.h
index cba218a..b1e6c1b 100644
--- a/arch/x86/kvm/paging_tmpl.h
+++ b/arch/x86/kvm/paging_tmpl.h
@@ -913,7 +913,8 @@ static gpa_t FNAME(gva_to_gpa_nested)(struct kvm_vcpu *vcpu, gva_t vaddr,
  *   and kvm_mmu_notifier_invalidate_range_start detect the mapping page isn't
  *   used by guest then tlbs are not flushed, so guest is allowed to access the
  *   freed pages.
- *   And we increase kvm->tlbs_dirty to delay tlbs flush in this case.
+ *   We set tlbs_dirty to let the notifier know this change and delay the flush
+ *   until such a case actually happens.
  */
 static int FNAME(sync_page)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp)
 {
@@ -942,7 +943,7 @@ static int FNAME(sync_page)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp)
 			return -EINVAL;
 
 		if (FNAME(prefetch_invalid_gpte)(vcpu, sp, &sp->spt[i], gpte)) {
-			vcpu->kvm->tlbs_dirty++;
+			vcpu->kvm->tlbs_dirty = true;
 			continue;
 		}
 
@@ -957,7 +958,7 @@ static int FNAME(sync_page)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp)
 
 		if (gfn != sp->gfns[i]) {
 			drop_spte(vcpu->kvm, &sp->spt[i]);
-			vcpu->kvm->tlbs_dirty++;
+			vcpu->kvm->tlbs_dirty = true;
 			continue;
 		}
 
diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
index 2de1bc0..7f4f9c2 100644
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -34,6 +34,7 @@
 #include <asm/perf_event.h>
 #include <asm/tlbflush.h>
 #include <asm/desc.h>
+#include <asm/debugreg.h>
 #include <asm/kvm_para.h>
 
 #include <asm/virtext.h>
@@ -303,20 +304,35 @@ static inline bool is_cr_intercept(struct vcpu_svm *svm, int bit)
 	return vmcb->control.intercept_cr & (1U << bit);
 }
 
-static inline void set_dr_intercept(struct vcpu_svm *svm, int bit)
+static inline void set_dr_intercepts(struct vcpu_svm *svm)
 {
 	struct vmcb *vmcb = get_host_vmcb(svm);
 
-	vmcb->control.intercept_dr |= (1U << bit);
+	vmcb->control.intercept_dr = (1 << INTERCEPT_DR0_READ)
+		| (1 << INTERCEPT_DR1_READ)
+		| (1 << INTERCEPT_DR2_READ)
+		| (1 << INTERCEPT_DR3_READ)
+		| (1 << INTERCEPT_DR4_READ)
+		| (1 << INTERCEPT_DR5_READ)
+		| (1 << INTERCEPT_DR6_READ)
+		| (1 << INTERCEPT_DR7_READ)
+		| (1 << INTERCEPT_DR0_WRITE)
+		| (1 << INTERCEPT_DR1_WRITE)
+		| (1 << INTERCEPT_DR2_WRITE)
+		| (1 << INTERCEPT_DR3_WRITE)
+		| (1 << INTERCEPT_DR4_WRITE)
+		| (1 << INTERCEPT_DR5_WRITE)
+		| (1 << INTERCEPT_DR6_WRITE)
+		| (1 << INTERCEPT_DR7_WRITE);
 
 	recalc_intercepts(svm);
 }
 
-static inline void clr_dr_intercept(struct vcpu_svm *svm, int bit)
+static inline void clr_dr_intercepts(struct vcpu_svm *svm)
 {
 	struct vmcb *vmcb = get_host_vmcb(svm);
 
-	vmcb->control.intercept_dr &= ~(1U << bit);
+	vmcb->control.intercept_dr = 0;
 
 	recalc_intercepts(svm);
 }
@@ -1080,23 +1096,7 @@ static void init_vmcb(struct vcpu_svm *svm)
 	set_cr_intercept(svm, INTERCEPT_CR4_WRITE);
 	set_cr_intercept(svm, INTERCEPT_CR8_WRITE);
 
-	set_dr_intercept(svm, INTERCEPT_DR0_READ);
-	set_dr_intercept(svm, INTERCEPT_DR1_READ);
-	set_dr_intercept(svm, INTERCEPT_DR2_READ);
-	set_dr_intercept(svm, INTERCEPT_DR3_READ);
-	set_dr_intercept(svm, INTERCEPT_DR4_READ);
-	set_dr_intercept(svm, INTERCEPT_DR5_READ);
-	set_dr_intercept(svm, INTERCEPT_DR6_READ);
-	set_dr_intercept(svm, INTERCEPT_DR7_READ);
-
-	set_dr_intercept(svm, INTERCEPT_DR0_WRITE);
-	set_dr_intercept(svm, INTERCEPT_DR1_WRITE);
-	set_dr_intercept(svm, INTERCEPT_DR2_WRITE);
-	set_dr_intercept(svm, INTERCEPT_DR3_WRITE);
-	set_dr_intercept(svm, INTERCEPT_DR4_WRITE);
-	set_dr_intercept(svm, INTERCEPT_DR5_WRITE);
-	set_dr_intercept(svm, INTERCEPT_DR6_WRITE);
-	set_dr_intercept(svm, INTERCEPT_DR7_WRITE);
+	set_dr_intercepts(svm);
 
 	set_exception_intercept(svm, PF_VECTOR);
 	set_exception_intercept(svm, UD_VECTOR);
@@ -1684,6 +1684,21 @@ static void svm_set_dr6(struct kvm_vcpu *vcpu, unsigned long value)
 	mark_dirty(svm->vmcb, VMCB_DR);
 }
 
+static void svm_sync_dirty_debug_regs(struct kvm_vcpu *vcpu)
+{
+	struct vcpu_svm *svm = to_svm(vcpu);
+
+	get_debugreg(vcpu->arch.db[0], 0);
+	get_debugreg(vcpu->arch.db[1], 1);
+	get_debugreg(vcpu->arch.db[2], 2);
+	get_debugreg(vcpu->arch.db[3], 3);
+	vcpu->arch.dr6 = svm_get_dr6(vcpu);
+	vcpu->arch.dr7 = svm->vmcb->save.dr7;
+
+	vcpu->arch.switch_db_regs &= ~KVM_DEBUGREG_WONT_EXIT;
+	set_dr_intercepts(svm);
+}
+
 static void svm_set_dr7(struct kvm_vcpu *vcpu, unsigned long value)
 {
 	struct vcpu_svm *svm = to_svm(vcpu);
@@ -2842,6 +2857,7 @@ static int iret_interception(struct vcpu_svm *svm)
 	clr_intercept(svm, INTERCEPT_IRET);
 	svm->vcpu.arch.hflags |= HF_IRET_MASK;
 	svm->nmi_iret_rip = kvm_rip_read(&svm->vcpu);
+	kvm_make_request(KVM_REQ_EVENT, &svm->vcpu);
 	return 1;
 }
 
@@ -2974,6 +2990,17 @@ static int dr_interception(struct vcpu_svm *svm)
 	unsigned long val;
 	int err;
 
+	if (svm->vcpu.guest_debug == 0) {
+		/*
+		 * No more DR vmexits; force a reload of the debug registers
+		 * and reenter on this instruction.  The next vmexit will
+		 * retrieve the full state of the debug registers.
+		 */
+		clr_dr_intercepts(svm);
+		svm->vcpu.arch.switch_db_regs |= KVM_DEBUGREG_WONT_EXIT;
+		return 1;
+	}
+
 	if (!boot_cpu_has(X86_FEATURE_DECODEASSISTS))
 		return emulate_on_interception(svm);
 
@@ -3649,7 +3676,7 @@ static int svm_interrupt_allowed(struct kvm_vcpu *vcpu)
 	return ret;
 }
 
-static int enable_irq_window(struct kvm_vcpu *vcpu)
+static void enable_irq_window(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_svm *svm = to_svm(vcpu);
 
@@ -3663,16 +3690,15 @@ static int enable_irq_window(struct kvm_vcpu *vcpu)
 		svm_set_vintr(svm);
 		svm_inject_irq(svm, 0x0);
 	}
-	return 0;
 }
 
-static int enable_nmi_window(struct kvm_vcpu *vcpu)
+static void enable_nmi_window(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_svm *svm = to_svm(vcpu);
 
 	if ((svm->vcpu.arch.hflags & (HF_NMI_MASK | HF_IRET_MASK))
 	    == HF_NMI_MASK)
-		return 0; /* IRET will cause a vm exit */
+		return; /* IRET will cause a vm exit */
 
 	/*
 	 * Something prevents NMI from been injected. Single step over possible
@@ -3681,7 +3707,6 @@ static int enable_nmi_window(struct kvm_vcpu *vcpu)
 	svm->nmi_singlestep = true;
 	svm->vmcb->save.rflags |= (X86_EFLAGS_TF | X86_EFLAGS_RF);
 	update_db_bp_intercept(vcpu);
-	return 0;
 }
 
 static int svm_set_tss_addr(struct kvm *kvm, unsigned int addr)
@@ -4064,6 +4089,11 @@ static bool svm_invpcid_supported(void)
 	return false;
 }
 
+static bool svm_mpx_supported(void)
+{
+	return false;
+}
+
 static bool svm_has_wbinvd_exit(void)
 {
 	return true;
@@ -4302,6 +4332,7 @@ static struct kvm_x86_ops svm_x86_ops = {
 	.get_dr6 = svm_get_dr6,
 	.set_dr6 = svm_set_dr6,
 	.set_dr7 = svm_set_dr7,
+	.sync_dirty_debug_regs = svm_sync_dirty_debug_regs,
 	.cache_reg = svm_cache_reg,
 	.get_rflags = svm_get_rflags,
 	.set_rflags = svm_set_rflags,
@@ -4345,6 +4376,7 @@ static struct kvm_x86_ops svm_x86_ops = {
 
 	.rdtscp_supported = svm_rdtscp_supported,
 	.invpcid_supported = svm_invpcid_supported,
+	.mpx_supported = svm_mpx_supported,
 
 	.set_supported_cpuid = svm_set_supported_cpuid,
 
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 3927528..1320e0f 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -31,6 +31,7 @@
 #include <linux/ftrace_event.h>
 #include <linux/slab.h>
 #include <linux/tboot.h>
+#include <linux/hrtimer.h>
 #include "kvm_cache_regs.h"
 #include "x86.h"
 
@@ -42,6 +43,7 @@
 #include <asm/i387.h>
 #include <asm/xcr.h>
 #include <asm/perf_event.h>
+#include <asm/debugreg.h>
 #include <asm/kexec.h>
 
 #include "trace.h"
@@ -110,6 +112,8 @@ module_param(nested, bool, S_IRUGO);
 
 #define RMODE_GUEST_OWNED_EFLAGS_BITS (~(X86_EFLAGS_IOPL | X86_EFLAGS_VM))
 
+#define VMX_MISC_EMULATED_PREEMPTION_TIMER_RATE 5
+
 /*
  * 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
@@ -202,6 +206,7 @@ struct __packed vmcs12 {
 	u64 guest_pdptr1;
 	u64 guest_pdptr2;
 	u64 guest_pdptr3;
+	u64 guest_bndcfgs;
 	u64 host_ia32_pat;
 	u64 host_ia32_efer;
 	u64 host_ia32_perf_global_ctrl;
@@ -374,6 +379,9 @@ struct nested_vmx {
 	 */
 	struct page *apic_access_page;
 	u64 msr_ia32_feature_control;
+
+	struct hrtimer preemption_timer;
+	bool preemption_timer_expired;
 };
 
 #define POSTED_INTR_ON  0
@@ -441,6 +449,7 @@ struct vcpu_vmx {
 #endif
 		int           gs_ldt_reload_needed;
 		int           fs_reload_needed;
+		u64           msr_host_bndcfgs;
 	} host_state;
 	struct {
 		int vm86_active;
@@ -533,6 +542,7 @@ static const unsigned long shadow_read_write_fields[] = {
 	GUEST_CS_LIMIT,
 	GUEST_CS_BASE,
 	GUEST_ES_BASE,
+	GUEST_BNDCFGS,
 	CR0_GUEST_HOST_MASK,
 	CR0_READ_SHADOW,
 	CR4_READ_SHADOW,
@@ -588,6 +598,7 @@ static const unsigned short vmcs_field_to_offset_table[] = {
 	FIELD64(GUEST_PDPTR1, guest_pdptr1),
 	FIELD64(GUEST_PDPTR2, guest_pdptr2),
 	FIELD64(GUEST_PDPTR3, guest_pdptr3),
+	FIELD64(GUEST_BNDCFGS, guest_bndcfgs),
 	FIELD64(HOST_IA32_PAT, host_ia32_pat),
 	FIELD64(HOST_IA32_EFER, host_ia32_efer),
 	FIELD64(HOST_IA32_PERF_GLOBAL_CTRL, host_ia32_perf_global_ctrl),
@@ -718,6 +729,7 @@ static unsigned long nested_ept_get_cr3(struct kvm_vcpu *vcpu);
 static u64 construct_eptp(unsigned long root_hpa);
 static void kvm_cpu_vmxon(u64 addr);
 static void kvm_cpu_vmxoff(void);
+static bool vmx_mpx_supported(void);
 static int vmx_set_tss_addr(struct kvm *kvm, unsigned int addr);
 static void vmx_set_segment(struct kvm_vcpu *vcpu,
 			    struct kvm_segment *var, int seg);
@@ -728,6 +740,7 @@ static u32 vmx_segment_access_rights(struct kvm_segment *var);
 static void vmx_sync_pir_to_irr_dummy(struct kvm_vcpu *vcpu);
 static void copy_vmcs12_to_shadow(struct vcpu_vmx *vmx);
 static void copy_shadow_to_vmcs12(struct vcpu_vmx *vmx);
+static bool vmx_mpx_supported(void);
 
 static DEFINE_PER_CPU(struct vmcs *, vmxarea);
 static DEFINE_PER_CPU(struct vmcs *, current_vmcs);
@@ -1047,6 +1060,12 @@ static inline bool nested_cpu_has_virtual_nmis(struct vmcs12 *vmcs12)
 	return vmcs12->pin_based_vm_exec_control & PIN_BASED_VIRTUAL_NMIS;
 }
 
+static inline bool nested_cpu_has_preemption_timer(struct vmcs12 *vmcs12)
+{
+	return vmcs12->pin_based_vm_exec_control &
+		PIN_BASED_VMX_PREEMPTION_TIMER;
+}
+
 static inline int nested_cpu_has_ept(struct vmcs12 *vmcs12)
 {
 	return nested_cpu_has2(vmcs12, SECONDARY_EXEC_ENABLE_EPT);
@@ -1710,6 +1729,8 @@ static void vmx_save_host_state(struct kvm_vcpu *vcpu)
 	if (is_long_mode(&vmx->vcpu))
 		wrmsrl(MSR_KERNEL_GS_BASE, vmx->msr_guest_kernel_gs_base);
 #endif
+	if (boot_cpu_has(X86_FEATURE_MPX))
+		rdmsrl(MSR_IA32_BNDCFGS, vmx->host_state.msr_host_bndcfgs);
 	for (i = 0; i < vmx->save_nmsrs; ++i)
 		kvm_set_shared_msr(vmx->guest_msrs[i].index,
 				   vmx->guest_msrs[i].data,
@@ -1747,6 +1768,8 @@ static void __vmx_load_host_state(struct vcpu_vmx *vmx)
 #ifdef CONFIG_X86_64
 	wrmsrl(MSR_KERNEL_GS_BASE, vmx->msr_host_kernel_gs_base);
 #endif
+	if (vmx->host_state.msr_host_bndcfgs)
+		wrmsrl(MSR_IA32_BNDCFGS, vmx->host_state.msr_host_bndcfgs);
 	/*
 	 * If the FPU is not active (through the host task or
 	 * the guest vcpu), then restore the cr0.TS bit.
@@ -2248,9 +2271,9 @@ static __init void nested_vmx_setup_ctls_msrs(void)
 	 */
 	nested_vmx_pinbased_ctls_low |= PIN_BASED_ALWAYSON_WITHOUT_TRUE_MSR;
 	nested_vmx_pinbased_ctls_high &= PIN_BASED_EXT_INTR_MASK |
-		PIN_BASED_NMI_EXITING | PIN_BASED_VIRTUAL_NMIS |
+		PIN_BASED_NMI_EXITING | PIN_BASED_VIRTUAL_NMIS;
+	nested_vmx_pinbased_ctls_high |= PIN_BASED_ALWAYSON_WITHOUT_TRUE_MSR |
 		PIN_BASED_VMX_PREEMPTION_TIMER;
-	nested_vmx_pinbased_ctls_high |= PIN_BASED_ALWAYSON_WITHOUT_TRUE_MSR;
 
 	/*
 	 * Exit controls
@@ -2265,15 +2288,12 @@ static __init void nested_vmx_setup_ctls_msrs(void)
 #ifdef CONFIG_X86_64
 		VM_EXIT_HOST_ADDR_SPACE_SIZE |
 #endif
-		VM_EXIT_LOAD_IA32_PAT | VM_EXIT_SAVE_IA32_PAT |
+		VM_EXIT_LOAD_IA32_PAT | VM_EXIT_SAVE_IA32_PAT;
+	nested_vmx_exit_ctls_high |= VM_EXIT_ALWAYSON_WITHOUT_TRUE_MSR |
+		VM_EXIT_LOAD_IA32_EFER | VM_EXIT_SAVE_IA32_EFER |
 		VM_EXIT_SAVE_VMX_PREEMPTION_TIMER;
-	if (!(nested_vmx_pinbased_ctls_high & PIN_BASED_VMX_PREEMPTION_TIMER) ||
-	    !(nested_vmx_exit_ctls_high & VM_EXIT_SAVE_VMX_PREEMPTION_TIMER)) {
-		nested_vmx_exit_ctls_high &= ~VM_EXIT_SAVE_VMX_PREEMPTION_TIMER;
-		nested_vmx_pinbased_ctls_high &= ~PIN_BASED_VMX_PREEMPTION_TIMER;
-	}
-	nested_vmx_exit_ctls_high |= (VM_EXIT_ALWAYSON_WITHOUT_TRUE_MSR |
-		VM_EXIT_LOAD_IA32_EFER | VM_EXIT_SAVE_IA32_EFER);
+	if (vmx_mpx_supported())
+		nested_vmx_exit_ctls_high |= VM_EXIT_CLEAR_BNDCFGS;
 
 	/* entry controls */
 	rdmsr(MSR_IA32_VMX_ENTRY_CTLS,
@@ -2287,6 +2307,8 @@ static __init void nested_vmx_setup_ctls_msrs(void)
 		VM_ENTRY_LOAD_IA32_PAT;
 	nested_vmx_entry_ctls_high |= (VM_ENTRY_ALWAYSON_WITHOUT_TRUE_MSR |
 				       VM_ENTRY_LOAD_IA32_EFER);
+	if (vmx_mpx_supported())
+		nested_vmx_entry_ctls_high |= VM_ENTRY_LOAD_BNDCFGS;
 
 	/* cpu-based controls */
 	rdmsr(MSR_IA32_VMX_PROCBASED_CTLS,
@@ -2342,9 +2364,9 @@ static __init void nested_vmx_setup_ctls_msrs(void)
 
 	/* miscellaneous data */
 	rdmsr(MSR_IA32_VMX_MISC, nested_vmx_misc_low, nested_vmx_misc_high);
-	nested_vmx_misc_low &= VMX_MISC_PREEMPTION_TIMER_RATE_MASK |
-		VMX_MISC_SAVE_EFER_LMA;
-	nested_vmx_misc_low |= VMX_MISC_ACTIVITY_HLT;
+	nested_vmx_misc_low &= VMX_MISC_SAVE_EFER_LMA;
+	nested_vmx_misc_low |= VMX_MISC_EMULATED_PREEMPTION_TIMER_RATE |
+		VMX_MISC_ACTIVITY_HLT;
 	nested_vmx_misc_high = 0;
 }
 
@@ -2479,6 +2501,11 @@ static int vmx_get_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 *pdata)
 	case MSR_IA32_SYSENTER_ESP:
 		data = vmcs_readl(GUEST_SYSENTER_ESP);
 		break;
+	case MSR_IA32_BNDCFGS:
+		if (!vmx_mpx_supported())
+			return 1;
+		data = vmcs_read64(GUEST_BNDCFGS);
+		break;
 	case MSR_IA32_FEATURE_CONTROL:
 		if (!nested_vmx_allowed(vcpu))
 			return 1;
@@ -2547,6 +2574,11 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 	case MSR_IA32_SYSENTER_ESP:
 		vmcs_writel(GUEST_SYSENTER_ESP, data);
 		break;
+	case MSR_IA32_BNDCFGS:
+		if (!vmx_mpx_supported())
+			return 1;
+		vmcs_write64(GUEST_BNDCFGS, data);
+		break;
 	case MSR_IA32_TSC:
 		kvm_write_tsc(vcpu, msr_info);
 		break;
@@ -2832,12 +2864,12 @@ static __init int setup_vmcs_config(struct vmcs_config *vmcs_conf)
 		      vmx_capability.ept, vmx_capability.vpid);
 	}
 
-	min = 0;
+	min = VM_EXIT_SAVE_DEBUG_CONTROLS;
 #ifdef CONFIG_X86_64
 	min |= VM_EXIT_HOST_ADDR_SPACE_SIZE;
 #endif
 	opt = VM_EXIT_SAVE_IA32_PAT | VM_EXIT_LOAD_IA32_PAT |
-		VM_EXIT_ACK_INTR_ON_EXIT;
+		VM_EXIT_ACK_INTR_ON_EXIT | VM_EXIT_CLEAR_BNDCFGS;
 	if (adjust_vmx_controls(min, opt, MSR_IA32_VMX_EXIT_CTLS,
 				&_vmexit_control) < 0)
 		return -EIO;
@@ -2853,8 +2885,8 @@ static __init int setup_vmcs_config(struct vmcs_config *vmcs_conf)
 		!(_vmexit_control & VM_EXIT_ACK_INTR_ON_EXIT))
 		_pin_based_exec_control &= ~PIN_BASED_POSTED_INTR;
 
-	min = 0;
-	opt = VM_ENTRY_LOAD_IA32_PAT;
+	min = VM_ENTRY_LOAD_DEBUG_CONTROLS;
+	opt = VM_ENTRY_LOAD_IA32_PAT | VM_ENTRY_LOAD_BNDCFGS;
 	if (adjust_vmx_controls(min, opt, MSR_IA32_VMX_ENTRY_CTLS,
 				&_vmentry_control) < 0)
 		return -EIO;
@@ -4223,6 +4255,10 @@ static u32 vmx_pin_based_exec_ctrl(struct vcpu_vmx *vmx)
 static u32 vmx_exec_control(struct vcpu_vmx *vmx)
 {
 	u32 exec_control = vmcs_config.cpu_based_exec_ctrl;
+
+	if (vmx->vcpu.arch.switch_db_regs & KVM_DEBUGREG_WONT_EXIT)
+		exec_control &= ~CPU_BASED_MOV_DR_EXITING;
+
 	if (!vm_need_tpr_shadow(vmx->vcpu.kvm)) {
 		exec_control &= ~CPU_BASED_TPR_SHADOW;
 #ifdef CONFIG_X86_64
@@ -4496,39 +4532,28 @@ static bool nested_exit_on_nmi(struct kvm_vcpu *vcpu)
 		PIN_BASED_NMI_EXITING;
 }
 
-static int enable_irq_window(struct kvm_vcpu *vcpu)
+static void enable_irq_window(struct kvm_vcpu *vcpu)
 {
 	u32 cpu_based_vm_exec_control;
 
-	if (is_guest_mode(vcpu) && nested_exit_on_intr(vcpu))
-		/*
-		 * We get here if vmx_interrupt_allowed() said we can't
-		 * inject to L1 now because L2 must run. The caller will have
-		 * to make L2 exit right after entry, so we can inject to L1
-		 * more promptly.
-		 */
-		return -EBUSY;
-
 	cpu_based_vm_exec_control = vmcs_read32(CPU_BASED_VM_EXEC_CONTROL);
 	cpu_based_vm_exec_control |= CPU_BASED_VIRTUAL_INTR_PENDING;
 	vmcs_write32(CPU_BASED_VM_EXEC_CONTROL, cpu_based_vm_exec_control);
-	return 0;
 }
 
-static int enable_nmi_window(struct kvm_vcpu *vcpu)
+static void enable_nmi_window(struct kvm_vcpu *vcpu)
 {
 	u32 cpu_based_vm_exec_control;
 
-	if (!cpu_has_virtual_nmis())
-		return enable_irq_window(vcpu);
-
-	if (vmcs_read32(GUEST_INTERRUPTIBILITY_INFO) & GUEST_INTR_STATE_STI)
-		return enable_irq_window(vcpu);
+	if (!cpu_has_virtual_nmis() ||
+	    vmcs_read32(GUEST_INTERRUPTIBILITY_INFO) & GUEST_INTR_STATE_STI) {
+		enable_irq_window(vcpu);
+		return;
+	}
 
 	cpu_based_vm_exec_control = vmcs_read32(CPU_BASED_VM_EXEC_CONTROL);
 	cpu_based_vm_exec_control |= CPU_BASED_VIRTUAL_NMI_PENDING;
 	vmcs_write32(CPU_BASED_VM_EXEC_CONTROL, cpu_based_vm_exec_control);
-	return 0;
 }
 
 static void vmx_inject_irq(struct kvm_vcpu *vcpu)
@@ -4620,22 +4645,8 @@ static void vmx_set_nmi_mask(struct kvm_vcpu *vcpu, bool masked)
 
 static int vmx_nmi_allowed(struct kvm_vcpu *vcpu)
 {
-	if (is_guest_mode(vcpu)) {
-		if (to_vmx(vcpu)->nested.nested_run_pending)
-			return 0;
-		if (nested_exit_on_nmi(vcpu)) {
-			nested_vmx_vmexit(vcpu, EXIT_REASON_EXCEPTION_NMI,
-					  NMI_VECTOR | INTR_TYPE_NMI_INTR |
-					  INTR_INFO_VALID_MASK, 0);
-			/*
-			 * The NMI-triggered VM exit counts as injection:
-			 * clear this one and block further NMIs.
-			 */
-			vcpu->arch.nmi_pending = 0;
-			vmx_set_nmi_mask(vcpu, true);
-			return 0;
-		}
-	}
+	if (to_vmx(vcpu)->nested.nested_run_pending)
+		return 0;
 
 	if (!cpu_has_virtual_nmis() && to_vmx(vcpu)->soft_vnmi_blocked)
 		return 0;
@@ -4647,19 +4658,8 @@ static int vmx_nmi_allowed(struct kvm_vcpu *vcpu)
 
 static int vmx_interrupt_allowed(struct kvm_vcpu *vcpu)
 {
-	if (is_guest_mode(vcpu)) {
-		if (to_vmx(vcpu)->nested.nested_run_pending)
-			return 0;
-		if (nested_exit_on_intr(vcpu)) {
-			nested_vmx_vmexit(vcpu, EXIT_REASON_EXTERNAL_INTERRUPT,
-					  0, 0);
-			/*
-			 * fall through to normal code, but now in L1, not L2
-			 */
-		}
-	}
-
-	return (vmcs_readl(GUEST_RFLAGS) & X86_EFLAGS_IF) &&
+	return (!to_vmx(vcpu)->nested.nested_run_pending &&
+		vmcs_readl(GUEST_RFLAGS) & X86_EFLAGS_IF) &&
 		!(vmcs_read32(GUEST_INTERRUPTIBILITY_INFO) &
 			(GUEST_INTR_STATE_STI | GUEST_INTR_STATE_MOV_SS));
 }
@@ -5102,6 +5102,22 @@ static int handle_dr(struct kvm_vcpu *vcpu)
 		}
 	}
 
+	if (vcpu->guest_debug == 0) {
+		u32 cpu_based_vm_exec_control;
+
+		cpu_based_vm_exec_control = vmcs_read32(CPU_BASED_VM_EXEC_CONTROL);
+		cpu_based_vm_exec_control &= ~CPU_BASED_MOV_DR_EXITING;
+		vmcs_write32(CPU_BASED_VM_EXEC_CONTROL, cpu_based_vm_exec_control);
+
+		/*
+		 * No more DR vmexits; force a reload of the debug registers
+		 * and reenter on this instruction.  The next vmexit will
+		 * retrieve the full state of the debug registers.
+		 */
+		vcpu->arch.switch_db_regs |= KVM_DEBUGREG_WONT_EXIT;
+		return 1;
+	}
+
 	exit_qualification = vmcs_readl(EXIT_QUALIFICATION);
 	dr = exit_qualification & DEBUG_REG_ACCESS_NUM;
 	reg = DEBUG_REG_ACCESS_REG(exit_qualification);
@@ -5128,6 +5144,24 @@ static void vmx_set_dr6(struct kvm_vcpu *vcpu, unsigned long val)
 {
 }
 
+static void vmx_sync_dirty_debug_regs(struct kvm_vcpu *vcpu)
+{
+	u32 cpu_based_vm_exec_control;
+
+	get_debugreg(vcpu->arch.db[0], 0);
+	get_debugreg(vcpu->arch.db[1], 1);
+	get_debugreg(vcpu->arch.db[2], 2);
+	get_debugreg(vcpu->arch.db[3], 3);
+	get_debugreg(vcpu->arch.dr6, 6);
+	vcpu->arch.dr7 = vmcs_readl(GUEST_DR7);
+
+	vcpu->arch.switch_db_regs &= ~KVM_DEBUGREG_WONT_EXIT;
+
+	cpu_based_vm_exec_control = vmcs_read32(CPU_BASED_VM_EXEC_CONTROL);
+	cpu_based_vm_exec_control |= CPU_BASED_MOV_DR_EXITING;
+	vmcs_write32(CPU_BASED_VM_EXEC_CONTROL, cpu_based_vm_exec_control);
+}
+
 static void vmx_set_dr7(struct kvm_vcpu *vcpu, unsigned long val)
 {
 	vmcs_writel(GUEST_DR7, val);
@@ -5727,6 +5761,18 @@ static void nested_vmx_failValid(struct kvm_vcpu *vcpu,
 	 */
 }
 
+static enum hrtimer_restart vmx_preemption_timer_fn(struct hrtimer *timer)
+{
+	struct vcpu_vmx *vmx =
+		container_of(timer, struct vcpu_vmx, nested.preemption_timer);
+
+	vmx->nested.preemption_timer_expired = true;
+	kvm_make_request(KVM_REQ_EVENT, &vmx->vcpu);
+	kvm_vcpu_kick(&vmx->vcpu);
+
+	return HRTIMER_NORESTART;
+}
+
 /*
  * Emulate the VMXON instruction.
  * Currently, we just remember that VMX is active, and do not save or even
@@ -5791,6 +5837,10 @@ static int handle_vmon(struct kvm_vcpu *vcpu)
 	INIT_LIST_HEAD(&(vmx->nested.vmcs02_pool));
 	vmx->nested.vmcs02_num = 0;
 
+	hrtimer_init(&vmx->nested.preemption_timer, CLOCK_MONOTONIC,
+		     HRTIMER_MODE_REL);
+	vmx->nested.preemption_timer.function = vmx_preemption_timer_fn;
+
 	vmx->nested.vmxon = true;
 
 	skip_emulated_instruction(vcpu);
@@ -6767,9 +6817,6 @@ static bool nested_vmx_exit_handled(struct kvm_vcpu *vcpu)
 		 * table is L0's fault.
 		 */
 		return 0;
-	case EXIT_REASON_PREEMPTION_TIMER:
-		return vmcs12->pin_based_vm_exec_control &
-			PIN_BASED_VMX_PREEMPTION_TIMER;
 	case EXIT_REASON_WBINVD:
 		return nested_cpu_has2(vmcs12, SECONDARY_EXEC_WBINVD_EXITING);
 	case EXIT_REASON_XSETBV:
@@ -6785,27 +6832,6 @@ static void vmx_get_exit_info(struct kvm_vcpu *vcpu, u64 *info1, u64 *info2)
 	*info2 = vmcs_read32(VM_EXIT_INTR_INFO);
 }
 
-static void nested_adjust_preemption_timer(struct kvm_vcpu *vcpu)
-{
-	u64 delta_tsc_l1;
-	u32 preempt_val_l1, preempt_val_l2, preempt_scale;
-
-	if (!(get_vmcs12(vcpu)->pin_based_vm_exec_control &
-			PIN_BASED_VMX_PREEMPTION_TIMER))
-		return;
-	preempt_scale = native_read_msr(MSR_IA32_VMX_MISC) &
-			MSR_IA32_VMX_MISC_PREEMPTION_TIMER_SCALE;
-	preempt_val_l2 = vmcs_read32(VMX_PREEMPTION_TIMER_VALUE);
-	delta_tsc_l1 = vmx_read_l1_tsc(vcpu, native_read_tsc())
-		- vcpu->arch.last_guest_tsc;
-	preempt_val_l1 = delta_tsc_l1 >> preempt_scale;
-	if (preempt_val_l2 <= preempt_val_l1)
-		preempt_val_l2 = 0;
-	else
-		preempt_val_l2 -= preempt_val_l1;
-	vmcs_write32(VMX_PREEMPTION_TIMER_VALUE, preempt_val_l2);
-}
-
 /*
  * The guest has exited.  See if we can fix it or if we need userspace
  * assistance.
@@ -7052,6 +7078,12 @@ static void vmx_handle_external_intr(struct kvm_vcpu *vcpu)
 		local_irq_enable();
 }
 
+static bool vmx_mpx_supported(void)
+{
+	return (vmcs_config.vmexit_ctrl & VM_EXIT_CLEAR_BNDCFGS) &&
+		(vmcs_config.vmentry_ctrl & VM_ENTRY_LOAD_BNDCFGS);
+}
+
 static void vmx_recover_nmi_blocking(struct vcpu_vmx *vmx)
 {
 	u32 exit_intr_info;
@@ -7218,8 +7250,6 @@ static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu)
 	atomic_switch_perf_msrs(vmx);
 	debugctlmsr = get_debugctlmsr();
 
-	if (is_guest_mode(vcpu) && !vmx->nested.nested_run_pending)
-		nested_adjust_preemption_timer(vcpu);
 	vmx->__launched = vmx->loaded_vmcs->launched;
 	asm(
 		/* Store host registers */
@@ -7616,6 +7646,28 @@ static void vmx_inject_page_fault_nested(struct kvm_vcpu *vcpu,
 		kvm_inject_page_fault(vcpu, fault);
 }
 
+static void vmx_start_preemption_timer(struct kvm_vcpu *vcpu)
+{
+	u64 preemption_timeout = get_vmcs12(vcpu)->vmx_preemption_timer_value;
+	struct vcpu_vmx *vmx = to_vmx(vcpu);
+
+	if (vcpu->arch.virtual_tsc_khz == 0)
+		return;
+
+	/* Make sure short timeouts reliably trigger an immediate vmexit.
+	 * hrtimer_start does not guarantee this. */
+	if (preemption_timeout <= 1) {
+		vmx_preemption_timer_fn(&vmx->nested.preemption_timer);
+		return;
+	}
+
+	preemption_timeout <<= VMX_MISC_EMULATED_PREEMPTION_TIMER_RATE;
+	preemption_timeout *= 1000000;
+	do_div(preemption_timeout, vcpu->arch.virtual_tsc_khz);
+	hrtimer_start(&vmx->nested.preemption_timer,
+		      ns_to_ktime(preemption_timeout), HRTIMER_MODE_REL);
+}
+
 /*
  * prepare_vmcs02 is called when the L1 guest hypervisor runs its nested
  * L2 guest. L1 has a vmcs for L2 (vmcs12), and this function "merges" it
@@ -7629,7 +7681,6 @@ static void prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12)
 {
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
 	u32 exec_control;
-	u32 exit_control;
 
 	vmcs_write16(GUEST_ES_SELECTOR, vmcs12->guest_es_selector);
 	vmcs_write16(GUEST_CS_SELECTOR, vmcs12->guest_cs_selector);
@@ -7687,13 +7738,14 @@ static void prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12)
 
 	vmcs_write64(VMCS_LINK_POINTER, -1ull);
 
-	vmcs_write32(PIN_BASED_VM_EXEC_CONTROL,
-		(vmcs_config.pin_based_exec_ctrl |
-		 vmcs12->pin_based_vm_exec_control));
+	exec_control = vmcs12->pin_based_vm_exec_control;
+	exec_control |= vmcs_config.pin_based_exec_ctrl;
+	exec_control &= ~PIN_BASED_VMX_PREEMPTION_TIMER;
+	vmcs_write32(PIN_BASED_VM_EXEC_CONTROL, exec_control);
 
-	if (vmcs12->pin_based_vm_exec_control & PIN_BASED_VMX_PREEMPTION_TIMER)
-		vmcs_write32(VMX_PREEMPTION_TIMER_VALUE,
-			     vmcs12->vmx_preemption_timer_value);
+	vmx->nested.preemption_timer_expired = false;
+	if (nested_cpu_has_preemption_timer(vmcs12))
+		vmx_start_preemption_timer(vcpu);
 
 	/*
 	 * Whether page-faults are trapped is determined by a combination of
@@ -7721,7 +7773,7 @@ static void prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12)
 		enable_ept ? vmcs12->page_fault_error_code_match : 0);
 
 	if (cpu_has_secondary_exec_ctrls()) {
-		u32 exec_control = vmx_secondary_exec_control(vmx);
+		exec_control = vmx_secondary_exec_control(vmx);
 		if (!vmx->rdtscp_enabled)
 			exec_control &= ~SECONDARY_EXEC_RDTSCP;
 		/* Take the following fields only from vmcs12 */
@@ -7808,10 +7860,7 @@ static void prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12)
 	 * we should use its exit controls. Note that VM_EXIT_LOAD_IA32_EFER
 	 * bits are further modified by vmx_set_efer() below.
 	 */
-	exit_control = vmcs_config.vmexit_ctrl;
-	if (vmcs12->pin_based_vm_exec_control & PIN_BASED_VMX_PREEMPTION_TIMER)
-		exit_control |= VM_EXIT_SAVE_VMX_PREEMPTION_TIMER;
-	vm_exit_controls_init(vmx, exit_control);
+	vmcs_write32(VM_EXIT_CONTROLS, vmcs_config.vmexit_ctrl);
 
 	/* vmcs12's VM_ENTRY_LOAD_IA32_EFER and VM_ENTRY_IA32E_MODE are
 	 * emulated by vmx_set_efer(), below.
@@ -7830,6 +7879,9 @@ static void prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12)
 
 	set_cr4_guest_host_mask(vmx);
 
+	if (vmcs12->vm_entry_controls & VM_ENTRY_LOAD_BNDCFGS)
+		vmcs_write64(GUEST_BNDCFGS, vmcs12->guest_bndcfgs);
+
 	if (vmcs12->cpu_based_vm_exec_control & CPU_BASED_USE_TSC_OFFSETING)
 		vmcs_write64(TSC_OFFSET,
 			vmx->nested.vmcs01_tsc_offset + vmcs12->tsc_offset);
@@ -8155,6 +8207,58 @@ static void vmcs12_save_pending_event(struct kvm_vcpu *vcpu,
 	}
 }
 
+static int vmx_check_nested_events(struct kvm_vcpu *vcpu, bool external_intr)
+{
+	struct vcpu_vmx *vmx = to_vmx(vcpu);
+
+	if (nested_cpu_has_preemption_timer(get_vmcs12(vcpu)) &&
+	    vmx->nested.preemption_timer_expired) {
+		if (vmx->nested.nested_run_pending)
+			return -EBUSY;
+		nested_vmx_vmexit(vcpu, EXIT_REASON_PREEMPTION_TIMER, 0, 0);
+		return 0;
+	}
+
+	if (vcpu->arch.nmi_pending && nested_exit_on_nmi(vcpu)) {
+		if (vmx->nested.nested_run_pending ||
+		    vcpu->arch.interrupt.pending)
+			return -EBUSY;
+		nested_vmx_vmexit(vcpu, EXIT_REASON_EXCEPTION_NMI,
+				  NMI_VECTOR | INTR_TYPE_NMI_INTR |
+				  INTR_INFO_VALID_MASK, 0);
+		/*
+		 * The NMI-triggered VM exit counts as injection:
+		 * clear this one and block further NMIs.
+		 */
+		vcpu->arch.nmi_pending = 0;
+		vmx_set_nmi_mask(vcpu, true);
+		return 0;
+	}
+
+	if ((kvm_cpu_has_interrupt(vcpu) || external_intr) &&
+	    nested_exit_on_intr(vcpu)) {
+		if (vmx->nested.nested_run_pending)
+			return -EBUSY;
+		nested_vmx_vmexit(vcpu, EXIT_REASON_EXTERNAL_INTERRUPT, 0, 0);
+	}
+
+	return 0;
+}
+
+static u32 vmx_get_preemption_timer_value(struct kvm_vcpu *vcpu)
+{
+	ktime_t remaining =
+		hrtimer_get_remaining(&to_vmx(vcpu)->nested.preemption_timer);
+	u64 value;
+
+	if (ktime_to_ns(remaining) <= 0)
+		return 0;
+
+	value = ktime_to_ns(remaining) * vcpu->arch.virtual_tsc_khz;
+	do_div(value, 1000000);
+	return value >> VMX_MISC_EMULATED_PREEMPTION_TIMER_RATE;
+}
+
 /*
  * prepare_vmcs12 is part of what we need to do when the nested L2 guest exits
  * and we want to prepare to run its L1 parent. L1 keeps a vmcs for L2 (vmcs12),
@@ -8225,10 +8329,13 @@ static void prepare_vmcs12(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12,
 	else
 		vmcs12->guest_activity_state = GUEST_ACTIVITY_ACTIVE;
 
-	if ((vmcs12->pin_based_vm_exec_control & PIN_BASED_VMX_PREEMPTION_TIMER) &&
-	    (vmcs12->vm_exit_controls & VM_EXIT_SAVE_VMX_PREEMPTION_TIMER))
-		vmcs12->vmx_preemption_timer_value =
-			vmcs_read32(VMX_PREEMPTION_TIMER_VALUE);
+	if (nested_cpu_has_preemption_timer(vmcs12)) {
+		if (vmcs12->vm_exit_controls &
+		    VM_EXIT_SAVE_VMX_PREEMPTION_TIMER)
+			vmcs12->vmx_preemption_timer_value =
+				vmx_get_preemption_timer_value(vcpu);
+		hrtimer_cancel(&to_vmx(vcpu)->nested.preemption_timer);
+	}
 
 	/*
 	 * In some cases (usually, nested EPT), L2 is allowed to change its
@@ -8260,6 +8367,8 @@ static void prepare_vmcs12(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12,
 	vmcs12->guest_sysenter_cs = vmcs_read32(GUEST_SYSENTER_CS);
 	vmcs12->guest_sysenter_esp = vmcs_readl(GUEST_SYSENTER_ESP);
 	vmcs12->guest_sysenter_eip = vmcs_readl(GUEST_SYSENTER_EIP);
+	if (vmx_mpx_supported())
+		vmcs12->guest_bndcfgs = vmcs_read64(GUEST_BNDCFGS);
 
 	/* update exit information fields: */
 
@@ -8369,6 +8478,10 @@ static void load_vmcs12_host_state(struct kvm_vcpu *vcpu,
 	vmcs_writel(GUEST_IDTR_BASE, vmcs12->host_idtr_base);
 	vmcs_writel(GUEST_GDTR_BASE, vmcs12->host_gdtr_base);
 
+	/* If not VM_EXIT_CLEAR_BNDCFGS, the L2 value propagates to L1.  */
+	if (vmcs12->vm_exit_controls & VM_EXIT_CLEAR_BNDCFGS)
+		vmcs_write64(GUEST_BNDCFGS, 0);
+
 	if (vmcs12->vm_exit_controls & VM_EXIT_LOAD_IA32_PAT) {
 		vmcs_write64(GUEST_IA32_PAT, vmcs12->host_ia32_pat);
 		vcpu->arch.pat = vmcs12->host_ia32_pat;
@@ -8495,6 +8608,9 @@ static void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 exit_reason,
 		nested_vmx_succeed(vcpu);
 	if (enable_shadow_vmcs)
 		vmx->nested.sync_shadow_vmcs = true;
+
+	/* in case we halted in L2 */
+	vcpu->arch.mp_state = KVM_MP_STATE_RUNNABLE;
 }
 
 /*
@@ -8573,6 +8689,7 @@ static struct kvm_x86_ops vmx_x86_ops = {
 	.get_dr6 = vmx_get_dr6,
 	.set_dr6 = vmx_set_dr6,
 	.set_dr7 = vmx_set_dr7,
+	.sync_dirty_debug_regs = vmx_sync_dirty_debug_regs,
 	.cache_reg = vmx_cache_reg,
 	.get_rflags = vmx_get_rflags,
 	.set_rflags = vmx_set_rflags,
@@ -8634,6 +8751,9 @@ static struct kvm_x86_ops vmx_x86_ops = {
 
 	.check_intercept = vmx_check_intercept,
 	.handle_external_intr = vmx_handle_external_intr,
+	.mpx_supported = vmx_mpx_supported,
+
+	.check_nested_events = vmx_check_nested_events,
 };
 
 static int __init vmx_init(void)
@@ -8721,6 +8841,8 @@ static int __init vmx_init(void)
 	vmx_disable_intercept_for_msr(MSR_IA32_SYSENTER_CS, false);
 	vmx_disable_intercept_for_msr(MSR_IA32_SYSENTER_ESP, false);
 	vmx_disable_intercept_for_msr(MSR_IA32_SYSENTER_EIP, false);
+	vmx_disable_intercept_for_msr(MSR_IA32_BNDCFGS, true);
+
 	memcpy(vmx_msr_bitmap_legacy_x2apic,
 			vmx_msr_bitmap_legacy, PAGE_SIZE);
 	memcpy(vmx_msr_bitmap_longmode_x2apic,
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 2b85784..d1c55f8 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -595,13 +595,13 @@ static void kvm_put_guest_xcr0(struct kvm_vcpu *vcpu)
 
 int __kvm_set_xcr(struct kvm_vcpu *vcpu, u32 index, u64 xcr)
 {
-	u64 xcr0;
+	u64 xcr0 = xcr;
+	u64 old_xcr0 = vcpu->arch.xcr0;
 	u64 valid_bits;
 
 	/* Only support XCR_XFEATURE_ENABLED_MASK(xcr0) now  */
 	if (index != XCR_XFEATURE_ENABLED_MASK)
 		return 1;
-	xcr0 = xcr;
 	if (!(xcr0 & XSTATE_FP))
 		return 1;
 	if ((xcr0 & XSTATE_YMM) && !(xcr0 & XSTATE_SSE))
@@ -616,8 +616,14 @@ int __kvm_set_xcr(struct kvm_vcpu *vcpu, u32 index, u64 xcr)
 	if (xcr0 & ~valid_bits)
 		return 1;
 
+	if ((!(xcr0 & XSTATE_BNDREGS)) != (!(xcr0 & XSTATE_BNDCSR)))
+		return 1;
+
 	kvm_put_guest_xcr0(vcpu);
 	vcpu->arch.xcr0 = xcr0;
+
+	if ((xcr0 ^ old_xcr0) & XSTATE_EXTEND_MASK)
+		kvm_update_cpuid(vcpu);
 	return 0;
 }
 
@@ -753,7 +759,9 @@ static void kvm_update_dr7(struct kvm_vcpu *vcpu)
 	else
 		dr7 = vcpu->arch.dr7;
 	kvm_x86_ops->set_dr7(vcpu, dr7);
-	vcpu->arch.switch_db_regs = (dr7 & DR7_BP_EN_MASK);
+	vcpu->arch.switch_db_regs &= ~KVM_DEBUGREG_BP_ENABLED;
+	if (dr7 & DR7_BP_EN_MASK)
+		vcpu->arch.switch_db_regs |= KVM_DEBUGREG_BP_ENABLED;
 }
 
 static int __kvm_set_dr(struct kvm_vcpu *vcpu, int dr, unsigned long val)
@@ -879,7 +887,7 @@ static u32 msrs_to_save[] = {
 	MSR_CSTAR, MSR_KERNEL_GS_BASE, MSR_SYSCALL_MASK, MSR_LSTAR,
 #endif
 	MSR_IA32_TSC, MSR_IA32_CR_PAT, MSR_VM_HSAVE_PA,
-	MSR_IA32_FEATURE_CONTROL
+	MSR_IA32_FEATURE_CONTROL, MSR_IA32_BNDCFGS
 };
 
 static unsigned num_msrs_to_save;
@@ -1581,7 +1589,6 @@ static int kvm_guest_time_update(struct kvm_vcpu *v)
 	/* With all the info we got, fill in the values */
 	vcpu->hv_clock.tsc_timestamp = tsc_timestamp;
 	vcpu->hv_clock.system_time = kernel_ns + v->kvm->arch.kvmclock_offset;
-	vcpu->last_kernel_ns = kernel_ns;
 	vcpu->last_guest_tsc = tsc_timestamp;
 
 	/*
@@ -1623,14 +1630,21 @@ static int kvm_guest_time_update(struct kvm_vcpu *v)
  * the others.
  *
  * So in those cases, request a kvmclock update for all vcpus.
- * The worst case for a remote vcpu to update its kvmclock
- * is then bounded by maximum nohz sleep latency.
+ * We need to rate-limit these requests though, as they can
+ * considerably slow guests that have a large number of vcpus.
+ * The time for a remote vcpu to update its kvmclock is bound
+ * by the delay we use to rate-limit the updates.
  */
 
-static void kvm_gen_kvmclock_update(struct kvm_vcpu *v)
+#define KVMCLOCK_UPDATE_DELAY msecs_to_jiffies(100)
+
+static void kvmclock_update_fn(struct work_struct *work)
 {
 	int i;
-	struct kvm *kvm = v->kvm;
+	struct delayed_work *dwork = to_delayed_work(work);
+	struct kvm_arch *ka = container_of(dwork, struct kvm_arch,
+					   kvmclock_update_work);
+	struct kvm *kvm = container_of(ka, struct kvm, arch);
 	struct kvm_vcpu *vcpu;
 
 	kvm_for_each_vcpu(i, vcpu, kvm) {
@@ -1639,6 +1653,29 @@ static void kvm_gen_kvmclock_update(struct kvm_vcpu *v)
 	}
 }
 
+static void kvm_gen_kvmclock_update(struct kvm_vcpu *v)
+{
+	struct kvm *kvm = v->kvm;
+
+	set_bit(KVM_REQ_CLOCK_UPDATE, &v->requests);
+	schedule_delayed_work(&kvm->arch.kvmclock_update_work,
+					KVMCLOCK_UPDATE_DELAY);
+}
+
+#define KVMCLOCK_SYNC_PERIOD (300 * HZ)
+
+static void kvmclock_sync_fn(struct work_struct *work)
+{
+	struct delayed_work *dwork = to_delayed_work(work);
+	struct kvm_arch *ka = container_of(dwork, struct kvm_arch,
+					   kvmclock_sync_work);
+	struct kvm *kvm = container_of(ka, struct kvm, arch);
+
+	schedule_delayed_work(&kvm->arch.kvmclock_update_work, 0);
+	schedule_delayed_work(&kvm->arch.kvmclock_sync_work,
+					KVMCLOCK_SYNC_PERIOD);
+}
+
 static bool msr_mtrr_valid(unsigned msr)
 {
 	switch (msr) {
@@ -2323,9 +2360,12 @@ static int get_msr_hyperv(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata)
 	case HV_X64_MSR_VP_INDEX: {
 		int r;
 		struct kvm_vcpu *v;
-		kvm_for_each_vcpu(r, v, vcpu->kvm)
-			if (v == vcpu)
+		kvm_for_each_vcpu(r, v, vcpu->kvm) {
+			if (v == vcpu) {
 				data = r;
+				break;
+			}
+		}
 		break;
 	}
 	case HV_X64_MSR_EOI:
@@ -2617,6 +2657,7 @@ int kvm_dev_ioctl_check_extension(long ext)
 	case KVM_CAP_KVMCLOCK_CTRL:
 	case KVM_CAP_READONLY_MEM:
 	case KVM_CAP_HYPERV_TIME:
+	case KVM_CAP_IOAPIC_POLARITY_IGNORED:
 #ifdef CONFIG_KVM_DEVICE_ASSIGNMENT
 	case KVM_CAP_ASSIGN_DEV_IRQ:
 	case KVM_CAP_PCI_2_3:
@@ -3043,9 +3084,7 @@ static int kvm_vcpu_ioctl_x86_set_xsave(struct kvm_vcpu *vcpu,
 		 * CPUID leaf 0xD, index 0, EDX:EAX.  This is for compatibility
 		 * with old userspace.
 		 */
-		if (xstate_bv & ~KVM_SUPPORTED_XCR0)
-			return -EINVAL;
-		if (xstate_bv & ~host_xcr0)
+		if (xstate_bv & ~kvm_supported_xcr0())
 			return -EINVAL;
 		memcpy(&vcpu->arch.guest_fpu.state->xsave,
 			guest_xsave->region, vcpu->arch.guest_xstate_size);
@@ -3898,6 +3937,23 @@ static void kvm_init_msr_list(void)
 	for (i = j = KVM_SAVE_MSRS_BEGIN; i < ARRAY_SIZE(msrs_to_save); i++) {
 		if (rdmsr_safe(msrs_to_save[i], &dummy[0], &dummy[1]) < 0)
 			continue;
+
+		/*
+		 * Even MSRs that are valid in the host may not be exposed
+		 * to the guests in some cases.  We could work around this
+		 * in VMX with the generic MSR save/load machinery, but it
+		 * is not really worthwhile since it will really only
+		 * happen with nested virtualization.
+		 */
+		switch (msrs_to_save[i]) {
+		case MSR_IA32_BNDCFGS:
+			if (!kvm_x86_ops->mpx_supported())
+				continue;
+			break;
+		default:
+			break;
+		}
+
 		if (j < i)
 			msrs_to_save[j] = msrs_to_save[i];
 		j++;
@@ -4394,6 +4450,7 @@ static int emulator_cmpxchg_emulated(struct x86_emulate_ctxt *ctxt,
 	if (!exchanged)
 		return X86EMUL_CMPXCHG_FAILED;
 
+	mark_page_dirty(vcpu->kvm, gpa >> PAGE_SHIFT);
 	kvm_mmu_pte_write(vcpu, gpa, new, bytes);
 
 	return X86EMUL_CONTINUE;
@@ -5537,9 +5594,10 @@ int kvm_arch_init(void *opaque)
 		goto out_free_percpu;
 
 	kvm_set_mmio_spte_mask();
-	kvm_init_msr_list();
 
 	kvm_x86_ops = ops;
+	kvm_init_msr_list();
+
 	kvm_mmu_set_mask_ptes(PT_USER_MASK, PT_ACCESSED_MASK,
 			PT_DIRTY_MASK, PT64_NX_MASK, 0);
 
@@ -5782,8 +5840,10 @@ static void update_cr8_intercept(struct kvm_vcpu *vcpu)
 	kvm_x86_ops->update_cr8_intercept(vcpu, tpr, max_irr);
 }
 
-static void inject_pending_event(struct kvm_vcpu *vcpu)
+static int inject_pending_event(struct kvm_vcpu *vcpu, bool req_int_win)
 {
+	int r;
+
 	/* try to reinject previous events if any */
 	if (vcpu->arch.exception.pending) {
 		trace_kvm_inj_exception(vcpu->arch.exception.nr,
@@ -5793,17 +5853,23 @@ static void inject_pending_event(struct kvm_vcpu *vcpu)
 					  vcpu->arch.exception.has_error_code,
 					  vcpu->arch.exception.error_code,
 					  vcpu->arch.exception.reinject);
-		return;
+		return 0;
 	}
 
 	if (vcpu->arch.nmi_injected) {
 		kvm_x86_ops->set_nmi(vcpu);
-		return;
+		return 0;
 	}
 
 	if (vcpu->arch.interrupt.pending) {
 		kvm_x86_ops->set_irq(vcpu);
-		return;
+		return 0;
+	}
+
+	if (is_guest_mode(vcpu) && kvm_x86_ops->check_nested_events) {
+		r = kvm_x86_ops->check_nested_events(vcpu, req_int_win);
+		if (r != 0)
+			return r;
 	}
 
 	/* try to inject new event if pending */
@@ -5820,6 +5886,7 @@ static void inject_pending_event(struct kvm_vcpu *vcpu)
 			kvm_x86_ops->set_irq(vcpu);
 		}
 	}
+	return 0;
 }
 
 static void process_nmi(struct kvm_vcpu *vcpu)
@@ -5924,15 +5991,13 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
 			goto out;
 		}
 
-		inject_pending_event(vcpu);
-
+		if (inject_pending_event(vcpu, req_int_win) != 0)
+			req_immediate_exit = true;
 		/* enable NMI/IRQ window open exits if needed */
-		if (vcpu->arch.nmi_pending)
-			req_immediate_exit =
-				kvm_x86_ops->enable_nmi_window(vcpu) != 0;
+		else if (vcpu->arch.nmi_pending)
+			kvm_x86_ops->enable_nmi_window(vcpu);
 		else if (kvm_cpu_has_injectable_intr(vcpu) || req_int_win)
-			req_immediate_exit =
-				kvm_x86_ops->enable_irq_window(vcpu) != 0;
+			kvm_x86_ops->enable_irq_window(vcpu);
 
 		if (kvm_lapic_enabled(vcpu)) {
 			/*
@@ -5992,12 +6057,28 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
 		set_debugreg(vcpu->arch.eff_db[1], 1);
 		set_debugreg(vcpu->arch.eff_db[2], 2);
 		set_debugreg(vcpu->arch.eff_db[3], 3);
+		set_debugreg(vcpu->arch.dr6, 6);
 	}
 
 	trace_kvm_entry(vcpu->vcpu_id);
 	kvm_x86_ops->run(vcpu);
 
 	/*
+	 * Do this here before restoring debug registers on the host.  And
+	 * since we do this before handling the vmexit, a DR access vmexit
+	 * can (a) read the correct value of the debug registers, (b) set
+	 * KVM_DEBUGREG_WONT_EXIT again.
+	 */
+	if (unlikely(vcpu->arch.switch_db_regs & KVM_DEBUGREG_WONT_EXIT)) {
+		int i;
+
+		WARN_ON(vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP);
+		kvm_x86_ops->sync_dirty_debug_regs(vcpu);
+		for (i = 0; i < KVM_NR_DB_REGS; i++)
+			vcpu->arch.eff_db[i] = vcpu->arch.db[i];
+	}
+
+	/*
 	 * If the guest has used debug registers, at least dr7
 	 * will be disabled while returning to the host.
 	 * If we don't have active breakpoints in the host, we don't
@@ -6711,6 +6792,7 @@ int kvm_arch_vcpu_postcreate(struct kvm_vcpu *vcpu)
 {
 	int r;
 	struct msr_data msr;
+	struct kvm *kvm = vcpu->kvm;
 
 	r = vcpu_load(vcpu);
 	if (r)
@@ -6721,6 +6803,9 @@ int kvm_arch_vcpu_postcreate(struct kvm_vcpu *vcpu)
 	kvm_write_tsc(vcpu, &msr);
 	vcpu_put(vcpu);
 
+	schedule_delayed_work(&kvm->arch.kvmclock_sync_work,
+					KVMCLOCK_SYNC_PERIOD);
+
 	return r;
 }
 
@@ -7013,6 +7098,9 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
 
 	pvclock_update_vm_gtod_copy(kvm);
 
+	INIT_DELAYED_WORK(&kvm->arch.kvmclock_update_work, kvmclock_update_fn);
+	INIT_DELAYED_WORK(&kvm->arch.kvmclock_sync_work, kvmclock_sync_fn);
+
 	return 0;
 }
 
@@ -7050,6 +7138,8 @@ static void kvm_free_vcpus(struct kvm *kvm)
 
 void kvm_arch_sync_events(struct kvm *kvm)
 {
+	cancel_delayed_work_sync(&kvm->arch.kvmclock_sync_work);
+	cancel_delayed_work_sync(&kvm->arch.kvmclock_update_work);
 	kvm_free_all_assigned_devices(kvm);
 	kvm_free_pit(kvm);
 }
@@ -7248,6 +7338,9 @@ void kvm_arch_flush_shadow_memslot(struct kvm *kvm,
 
 int kvm_arch_vcpu_runnable(struct kvm_vcpu *vcpu)
 {
+	if (is_guest_mode(vcpu) && kvm_x86_ops->check_nested_events)
+		kvm_x86_ops->check_nested_events(vcpu, false);
+
 	return (vcpu->arch.mp_state == KVM_MP_STATE_RUNNABLE &&
 		!vcpu->arch.apf.halted)
 		|| !list_empty_careful(&vcpu->async_pf.done)
diff --git a/arch/x86/kvm/x86.h b/arch/x86/kvm/x86.h
index 8da5823..8c97bac 100644
--- a/arch/x86/kvm/x86.h
+++ b/arch/x86/kvm/x86.h
@@ -122,9 +122,12 @@ int kvm_write_guest_virt_system(struct x86_emulate_ctxt *ctxt,
 	gva_t addr, void *val, unsigned int bytes,
 	struct x86_exception *exception);
 
-#define KVM_SUPPORTED_XCR0	(XSTATE_FP | XSTATE_SSE | XSTATE_YMM)
+#define KVM_SUPPORTED_XCR0     (XSTATE_FP | XSTATE_SSE | XSTATE_YMM \
+				| XSTATE_BNDREGS | XSTATE_BNDCSR)
 extern u64 host_xcr0;
 
+extern u64 kvm_supported_xcr0(void);
+
 extern unsigned int min_timer_period_us;
 
 extern struct static_key kvm_no_apic_vcpu;