Merge tag 'v3.13-rc7' into x86/efi-kexec to resolve conflicts

Conflicts:
	arch/x86/platform/efi/efi.c
	drivers/firmware/efi/Kconfig

Signed-off-by: Ingo Molnar <mingo@kernel.org>

24 files changed, 129 insertions, 95 deletions

diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index e903c71f7e6..0952ecd60ec 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -26,6 +26,7 @@ config X86
 	select HAVE_AOUT if X86_32
 	select HAVE_UNSTABLE_SCHED_CLOCK
 	select ARCH_SUPPORTS_NUMA_BALANCING
+	select ARCH_SUPPORTS_INT128 if X86_64
 	select ARCH_WANTS_PROT_NUMA_PROT_NONE
 	select HAVE_IDE
 	select HAVE_OPROFILE
diff --git a/arch/x86/Makefile b/arch/x86/Makefile
index 41250fb3398..57d02150712 100644
--- a/arch/x86/Makefile
+++ b/arch/x86/Makefile
@@ -31,6 +31,9 @@ ifeq ($(CONFIG_X86_32),y)
 
         KBUILD_CFLAGS += -msoft-float -mregparm=3 -freg-struct-return
 
+        # Don't autogenerate MMX or SSE instructions
+        KBUILD_CFLAGS += -mno-mmx -mno-sse
+
         # Never want PIC in a 32-bit kernel, prevent breakage with GCC built
         # with nonstandard options
         KBUILD_CFLAGS += -fno-pic
@@ -57,8 +60,11 @@ else
         KBUILD_AFLAGS += -m64
         KBUILD_CFLAGS += -m64
 
+        # Don't autogenerate MMX or SSE instructions
+        KBUILD_CFLAGS += -mno-mmx -mno-sse
+
 	# Use -mpreferred-stack-boundary=3 if supported.
-	KBUILD_CFLAGS += $(call cc-option,-mno-sse -mpreferred-stack-boundary=3)
+	KBUILD_CFLAGS += $(call cc-option,-mpreferred-stack-boundary=3)
 
         # FIXME - should be integrated in Makefile.cpu (Makefile_32.cpu)
         cflags-$(CONFIG_MK8) += $(call cc-option,-march=k8)
diff --git a/arch/x86/boot/Makefile b/arch/x86/boot/Makefile
index dce69a25689..d9c11956fce 100644
--- a/arch/x86/boot/Makefile
+++ b/arch/x86/boot/Makefile
@@ -53,18 +53,18 @@ $(obj)/cpustr.h: $(obj)/mkcpustr FORCE
 
 # How to compile the 16-bit code.  Note we always compile for -march=i386,
 # that way we can complain to the user if the CPU is insufficient.
-KBUILD_CFLAGS	:= $(USERINCLUDE) -g -Os -D_SETUP -D__KERNEL__ \
+KBUILD_CFLAGS	:= $(USERINCLUDE) -m32 -g -Os -D_SETUP -D__KERNEL__ \
 		   -DDISABLE_BRANCH_PROFILING \
 		   -Wall -Wstrict-prototypes \
 		   -march=i386 -mregparm=3 \
 		   -include $(srctree)/$(src)/code16gcc.h \
 		   -fno-strict-aliasing -fomit-frame-pointer -fno-pic \
+		   -mno-mmx -mno-sse \
 		   $(call cc-option, -ffreestanding) \
 		   $(call cc-option, -fno-toplevel-reorder,\
-			$(call cc-option, -fno-unit-at-a-time)) \
+		   $(call cc-option, -fno-unit-at-a-time)) \
 		   $(call cc-option, -fno-stack-protector) \
 		   $(call cc-option, -mpreferred-stack-boundary=2)
-KBUILD_CFLAGS	+= $(call cc-option, -m32)
 KBUILD_AFLAGS	:= $(KBUILD_CFLAGS) -D__ASSEMBLY__
 GCOV_PROFILE := n
 
diff --git a/arch/x86/boot/compressed/Makefile b/arch/x86/boot/compressed/Makefile
index dcd90df10ab..c8a6792e784 100644
--- a/arch/x86/boot/compressed/Makefile
+++ b/arch/x86/boot/compressed/Makefile
@@ -13,6 +13,7 @@ KBUILD_CFLAGS += -DDISABLE_BRANCH_PROFILING
 cflags-$(CONFIG_X86_32) := -march=i386
 cflags-$(CONFIG_X86_64) := -mcmodel=small
 KBUILD_CFLAGS += $(cflags-y)
+KBUILD_CFLAGS += -mno-mmx -mno-sse
 KBUILD_CFLAGS += $(call cc-option,-ffreestanding)
 KBUILD_CFLAGS += $(call cc-option,-fno-stack-protector)
 
diff --git a/arch/x86/include/asm/atomic.h b/arch/x86/include/asm/atomic.h
index da31c8b8a92..b17f4f48ecd 100644
--- a/arch/x86/include/asm/atomic.h
+++ b/arch/x86/include/asm/atomic.h
@@ -77,7 +77,7 @@ static inline void atomic_sub(int i, atomic_t *v)
  */
 static inline int atomic_sub_and_test(int i, atomic_t *v)
 {
-	GEN_BINARY_RMWcc(LOCK_PREFIX "subl", v->counter, i, "%0", "e");
+	GEN_BINARY_RMWcc(LOCK_PREFIX "subl", v->counter, "er", i, "%0", "e");
 }
 
 /**
@@ -141,7 +141,7 @@ static inline int atomic_inc_and_test(atomic_t *v)
  */
 static inline int atomic_add_negative(int i, atomic_t *v)
 {
-	GEN_BINARY_RMWcc(LOCK_PREFIX "addl", v->counter, i, "%0", "s");
+	GEN_BINARY_RMWcc(LOCK_PREFIX "addl", v->counter, "er", i, "%0", "s");
 }
 
 /**
diff --git a/arch/x86/include/asm/atomic64_64.h b/arch/x86/include/asm/atomic64_64.h
index 3f065c985ae..46e9052bbd2 100644
--- a/arch/x86/include/asm/atomic64_64.h
+++ b/arch/x86/include/asm/atomic64_64.h
@@ -72,7 +72,7 @@ static inline void atomic64_sub(long i, atomic64_t *v)
  */
 static inline int atomic64_sub_and_test(long i, atomic64_t *v)
 {
-	GEN_BINARY_RMWcc(LOCK_PREFIX "subq", v->counter, i, "%0", "e");
+	GEN_BINARY_RMWcc(LOCK_PREFIX "subq", v->counter, "er", i, "%0", "e");
 }
 
 /**
@@ -138,7 +138,7 @@ static inline int atomic64_inc_and_test(atomic64_t *v)
  */
 static inline int atomic64_add_negative(long i, atomic64_t *v)
 {
-	GEN_BINARY_RMWcc(LOCK_PREFIX "addq", v->counter, i, "%0", "s");
+	GEN_BINARY_RMWcc(LOCK_PREFIX "addq", v->counter, "er", i, "%0", "s");
 }
 
 /**
diff --git a/arch/x86/include/asm/bitops.h b/arch/x86/include/asm/bitops.h
index 6d76d093598..9fc1af74dc8 100644
--- a/arch/x86/include/asm/bitops.h
+++ b/arch/x86/include/asm/bitops.h
@@ -205,7 +205,7 @@ static inline void change_bit(long nr, volatile unsigned long *addr)
  */
 static inline int test_and_set_bit(long nr, volatile unsigned long *addr)
 {
-	GEN_BINARY_RMWcc(LOCK_PREFIX "bts", *addr, nr, "%0", "c");
+	GEN_BINARY_RMWcc(LOCK_PREFIX "bts", *addr, "Ir", nr, "%0", "c");
 }
 
 /**
@@ -251,7 +251,7 @@ static inline int __test_and_set_bit(long nr, volatile unsigned long *addr)
  */
 static inline int test_and_clear_bit(long nr, volatile unsigned long *addr)
 {
-	GEN_BINARY_RMWcc(LOCK_PREFIX "btr", *addr, nr, "%0", "c");
+	GEN_BINARY_RMWcc(LOCK_PREFIX "btr", *addr, "Ir", nr, "%0", "c");
 }
 
 /**
@@ -304,7 +304,7 @@ static inline int __test_and_change_bit(long nr, volatile unsigned long *addr)
  */
 static inline int test_and_change_bit(long nr, volatile unsigned long *addr)
 {
-	GEN_BINARY_RMWcc(LOCK_PREFIX "btc", *addr, nr, "%0", "c");
+	GEN_BINARY_RMWcc(LOCK_PREFIX "btc", *addr, "Ir", nr, "%0", "c");
 }
 
 static __always_inline int constant_test_bit(long nr, const volatile unsigned long *addr)
diff --git a/arch/x86/include/asm/local.h b/arch/x86/include/asm/local.h
index 5b23e605e70..4ad6560847b 100644
--- a/arch/x86/include/asm/local.h
+++ b/arch/x86/include/asm/local.h
@@ -52,7 +52,7 @@ static inline void local_sub(long i, local_t *l)
  */
 static inline int local_sub_and_test(long i, local_t *l)
 {
-	GEN_BINARY_RMWcc(_ASM_SUB, l->a.counter, i, "%0", "e");
+	GEN_BINARY_RMWcc(_ASM_SUB, l->a.counter, "er", i, "%0", "e");
 }
 
 /**
@@ -92,7 +92,7 @@ static inline int local_inc_and_test(local_t *l)
  */
 static inline int local_add_negative(long i, local_t *l)
 {
-	GEN_BINARY_RMWcc(_ASM_ADD, l->a.counter, i, "%0", "s");
+	GEN_BINARY_RMWcc(_ASM_ADD, l->a.counter, "er", i, "%0", "s");
 }
 
 /**
diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h
index 3d199945870..bbc8b12fa44 100644
--- a/arch/x86/include/asm/pgtable.h
+++ b/arch/x86/include/asm/pgtable.h
@@ -452,9 +452,16 @@ static inline int pte_present(pte_t a)
 }
 
 #define pte_accessible pte_accessible
-static inline int pte_accessible(pte_t a)
+static inline bool pte_accessible(struct mm_struct *mm, pte_t a)
 {
-	return pte_flags(a) & _PAGE_PRESENT;
+	if (pte_flags(a) & _PAGE_PRESENT)
+		return true;
+
+	if ((pte_flags(a) & (_PAGE_PROTNONE | _PAGE_NUMA)) &&
+			mm_tlb_flush_pending(mm))
+		return true;
+
+	return false;
 }
 
 static inline int pte_hidden(pte_t pte)
diff --git a/arch/x86/include/asm/preempt.h b/arch/x86/include/asm/preempt.h
index 8729723636f..c8b051933b1 100644
--- a/arch/x86/include/asm/preempt.h
+++ b/arch/x86/include/asm/preempt.h
@@ -8,6 +8,12 @@
 DECLARE_PER_CPU(int, __preempt_count);
 
 /*
+ * We use the PREEMPT_NEED_RESCHED bit as an inverted NEED_RESCHED such
+ * that a decrement hitting 0 means we can and should reschedule.
+ */
+#define PREEMPT_ENABLED	(0 + PREEMPT_NEED_RESCHED)
+
+/*
  * We mask the PREEMPT_NEED_RESCHED bit so as not to confuse all current users
  * that think a non-zero value indicates we cannot preempt.
  */
@@ -74,6 +80,11 @@ static __always_inline void __preempt_count_sub(int val)
 	__this_cpu_add_4(__preempt_count, -val);
 }
 
+/*
+ * Because we keep PREEMPT_NEED_RESCHED set when we do _not_ need to reschedule
+ * a decrement which hits zero means we have no preempt_count and should
+ * reschedule.
+ */
 static __always_inline bool __preempt_count_dec_and_test(void)
 {
 	GEN_UNARY_RMWcc("decl", __preempt_count, __percpu_arg(0), "e");
diff --git a/arch/x86/include/asm/rmwcc.h b/arch/x86/include/asm/rmwcc.h
index 1ff990f1de8..8f7866a5b9a 100644
--- a/arch/x86/include/asm/rmwcc.h
+++ b/arch/x86/include/asm/rmwcc.h
@@ -16,8 +16,8 @@ cc_label:								\
 #define GEN_UNARY_RMWcc(op, var, arg0, cc) 				\
 	__GEN_RMWcc(op " " arg0, var, cc)
 
-#define GEN_BINARY_RMWcc(op, var, val, arg0, cc)			\
-	__GEN_RMWcc(op " %1, " arg0, var, cc, "er" (val))
+#define GEN_BINARY_RMWcc(op, var, vcon, val, arg0, cc)			\
+	__GEN_RMWcc(op " %1, " arg0, var, cc, vcon (val))
 
 #else /* !CC_HAVE_ASM_GOTO */
 
@@ -33,8 +33,8 @@ do {									\
 #define GEN_UNARY_RMWcc(op, var, arg0, cc)				\
 	__GEN_RMWcc(op " " arg0, var, cc)
 
-#define GEN_BINARY_RMWcc(op, var, val, arg0, cc)			\
-	__GEN_RMWcc(op " %2, " arg0, var, cc, "er" (val))
+#define GEN_BINARY_RMWcc(op, var, vcon, val, arg0, cc)			\
+	__GEN_RMWcc(op " %2, " arg0, var, cc, vcon (val))
 
 #endif /* CC_HAVE_ASM_GOTO */
 
diff --git a/arch/x86/include/asm/trace/irq_vectors.h b/arch/x86/include/asm/trace/irq_vectors.h
index 2874df24e7a..4cab890007a 100644
--- a/arch/x86/include/asm/trace/irq_vectors.h
+++ b/arch/x86/include/asm/trace/irq_vectors.h
@@ -72,6 +72,17 @@ DEFINE_IRQ_VECTOR_EVENT(x86_platform_ipi);
 DEFINE_IRQ_VECTOR_EVENT(irq_work);
 
 /*
+ * We must dis-allow sampling irq_work_exit() because perf event sampling
+ * itself can cause irq_work, which would lead to an infinite loop;
+ *
+ *  1) irq_work_exit happens
+ *  2) generates perf sample
+ *  3) generates irq_work
+ *  4) goto 1
+ */
+TRACE_EVENT_PERF_PERM(irq_work_exit, is_sampling_event(p_event) ? -EPERM : 0);
+
+/*
  * call_function - called when entering/exiting a call function interrupt
  * vector handler
  */
diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c
index dc1ec0dff93..ea04b342c02 100644
--- a/arch/x86/kernel/cpu/intel.c
+++ b/arch/x86/kernel/cpu/intel.c
@@ -387,7 +387,8 @@ static void init_intel(struct cpuinfo_x86 *c)
 			set_cpu_cap(c, X86_FEATURE_PEBS);
 	}
 
-	if (c->x86 == 6 && c->x86_model == 29 && cpu_has_clflush)
+	if (c->x86 == 6 && cpu_has_clflush &&
+	    (c->x86_model == 29 || c->x86_model == 46 || c->x86_model == 47))
 		set_cpu_cap(c, X86_FEATURE_CLFLUSH_MONITOR);
 
 #ifdef CONFIG_X86_64
diff --git a/arch/x86/kernel/cpu/perf_event.h b/arch/x86/kernel/cpu/perf_event.h
index fd00bb29425..c1a861829d8 100644
--- a/arch/x86/kernel/cpu/perf_event.h
+++ b/arch/x86/kernel/cpu/perf_event.h
@@ -262,11 +262,20 @@ struct cpu_hw_events {
 	__EVENT_CONSTRAINT(c, n, INTEL_ARCH_EVENT_MASK, \
 			  HWEIGHT(n), 0, PERF_X86_EVENT_PEBS_ST_HSW)
 
-#define EVENT_CONSTRAINT_END		\
-	EVENT_CONSTRAINT(0, 0, 0)
+/*
+ * We define the end marker as having a weight of -1
+ * to enable blacklisting of events using a counter bitmask
+ * of zero and thus a weight of zero.
+ * The end marker has a weight that cannot possibly be
+ * obtained from counting the bits in the bitmask.
+ */
+#define EVENT_CONSTRAINT_END { .weight = -1 }
 
+/*
+ * Check for end marker with weight == -1
+ */
 #define for_each_event_constraint(e, c)	\
-	for ((e) = (c); (e)->weight; (e)++)
+	for ((e) = (c); (e)->weight != -1; (e)++)
 
 /*
  * Extra registers for specific events.
diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c
index da3c599584a..c752cb43e52 100644
--- a/arch/x86/kernel/reboot.c
+++ b/arch/x86/kernel/reboot.c
@@ -558,6 +558,17 @@ void native_machine_shutdown(void)
 {
 	/* Stop the cpus and apics */
 #ifdef CONFIG_X86_IO_APIC
+	/*
+	 * Disabling IO APIC before local APIC is a workaround for
+	 * erratum AVR31 in "Intel Atom Processor C2000 Product Family
+	 * Specification Update". In this situation, interrupts that target
+	 * a Logical Processor whose Local APIC is either in the process of
+	 * being hardware disabled or software disabled are neither delivered
+	 * nor discarded. When this erratum occurs, the processor may hang.
+	 *
+	 * Even without the erratum, it still makes sense to quiet IO APIC
+	 * before disabling Local APIC.
+	 */
 	disable_IO_APIC();
 #endif
 
diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index 5439117d5c4..1673940cf9c 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -143,6 +143,8 @@ static inline int kvm_apic_id(struct kvm_lapic *apic)
 	return (kvm_apic_get_reg(apic, APIC_ID) >> 24) & 0xff;
 }
 
+#define KVM_X2APIC_CID_BITS 0
+
 static void recalculate_apic_map(struct kvm *kvm)
 {
 	struct kvm_apic_map *new, *old = NULL;
@@ -180,7 +182,8 @@ static void recalculate_apic_map(struct kvm *kvm)
 		if (apic_x2apic_mode(apic)) {
 			new->ldr_bits = 32;
 			new->cid_shift = 16;
-			new->cid_mask = new->lid_mask = 0xffff;
+			new->cid_mask = (1 << KVM_X2APIC_CID_BITS) - 1;
+			new->lid_mask = 0xffff;
 		} else if (kvm_apic_sw_enabled(apic) &&
 				!new->cid_mask /* flat mode */ &&
 				kvm_apic_get_reg(apic, APIC_DFR) == APIC_DFR_CLUSTER) {
@@ -841,7 +844,8 @@ static u32 apic_get_tmcct(struct kvm_lapic *apic)
 	ASSERT(apic != NULL);
 
 	/* if initial count is 0, current count should also be 0 */
-	if (kvm_apic_get_reg(apic, APIC_TMICT) == 0)
+	if (kvm_apic_get_reg(apic, APIC_TMICT) == 0 ||
+		apic->lapic_timer.period == 0)
 		return 0;
 
 	remaining = hrtimer_get_remaining(&apic->lapic_timer.timer);
@@ -1346,6 +1350,10 @@ void kvm_lapic_set_base(struct kvm_vcpu *vcpu, u64 value)
 		return;
 	}
 
+	if (!kvm_vcpu_is_bsp(apic->vcpu))
+		value &= ~MSR_IA32_APICBASE_BSP;
+	vcpu->arch.apic_base = value;
+
 	/* update jump label if enable bit changes */
 	if ((vcpu->arch.apic_base ^ value) & MSR_IA32_APICBASE_ENABLE) {
 		if (value & MSR_IA32_APICBASE_ENABLE)
@@ -1355,10 +1363,6 @@ void kvm_lapic_set_base(struct kvm_vcpu *vcpu, u64 value)
 		recalculate_apic_map(vcpu->kvm);
 	}
 
-	if (!kvm_vcpu_is_bsp(apic->vcpu))
-		value &= ~MSR_IA32_APICBASE_BSP;
-
-	vcpu->arch.apic_base = value;
 	if ((old_value ^ value) & X2APIC_ENABLE) {
 		if (value & X2APIC_ENABLE) {
 			u32 id = kvm_apic_id(apic);
@@ -1691,7 +1695,6 @@ static void apic_sync_pv_eoi_from_guest(struct kvm_vcpu *vcpu,
 void kvm_lapic_sync_from_vapic(struct kvm_vcpu *vcpu)
 {
 	u32 data;
-	void *vapic;
 
 	if (test_bit(KVM_APIC_PV_EOI_PENDING, &vcpu->arch.apic_attention))
 		apic_sync_pv_eoi_from_guest(vcpu, vcpu->arch.apic);
@@ -1699,9 +1702,8 @@ void kvm_lapic_sync_from_vapic(struct kvm_vcpu *vcpu)
 	if (!test_bit(KVM_APIC_CHECK_VAPIC, &vcpu->arch.apic_attention))
 		return;
 
-	vapic = kmap_atomic(vcpu->arch.apic->vapic_page);
-	data = *(u32 *)(vapic + offset_in_page(vcpu->arch.apic->vapic_addr));
-	kunmap_atomic(vapic);
+	kvm_read_guest_cached(vcpu->kvm, &vcpu->arch.apic->vapic_cache, &data,
+				sizeof(u32));
 
 	apic_set_tpr(vcpu->arch.apic, data & 0xff);
 }
@@ -1737,7 +1739,6 @@ void kvm_lapic_sync_to_vapic(struct kvm_vcpu *vcpu)
 	u32 data, tpr;
 	int max_irr, max_isr;
 	struct kvm_lapic *apic = vcpu->arch.apic;
-	void *vapic;
 
 	apic_sync_pv_eoi_to_guest(vcpu, apic);
 
@@ -1753,18 +1754,24 @@ void kvm_lapic_sync_to_vapic(struct kvm_vcpu *vcpu)
 		max_isr = 0;
 	data = (tpr & 0xff) | ((max_isr & 0xf0) << 8) | (max_irr << 24);
 
-	vapic = kmap_atomic(vcpu->arch.apic->vapic_page);
-	*(u32 *)(vapic + offset_in_page(vcpu->arch.apic->vapic_addr)) = data;
-	kunmap_atomic(vapic);
+	kvm_write_guest_cached(vcpu->kvm, &vcpu->arch.apic->vapic_cache, &data,
+				sizeof(u32));
 }
 
-void kvm_lapic_set_vapic_addr(struct kvm_vcpu *vcpu, gpa_t vapic_addr)
+int kvm_lapic_set_vapic_addr(struct kvm_vcpu *vcpu, gpa_t vapic_addr)
 {
-	vcpu->arch.apic->vapic_addr = vapic_addr;
-	if (vapic_addr)
+	if (vapic_addr) {
+		if (kvm_gfn_to_hva_cache_init(vcpu->kvm,
+					&vcpu->arch.apic->vapic_cache,
+					vapic_addr, sizeof(u32)))
+			return -EINVAL;
 		__set_bit(KVM_APIC_CHECK_VAPIC, &vcpu->arch.apic_attention);
-	else
+	} else {
 		__clear_bit(KVM_APIC_CHECK_VAPIC, &vcpu->arch.apic_attention);
+	}
+
+	vcpu->arch.apic->vapic_addr = vapic_addr;
+	return 0;
 }
 
 int kvm_x2apic_msr_write(struct kvm_vcpu *vcpu, u32 msr, u64 data)
diff --git a/arch/x86/kvm/lapic.h b/arch/x86/kvm/lapic.h
index c730ac9fe80..c8b0d0d2da5 100644
--- a/arch/x86/kvm/lapic.h
+++ b/arch/x86/kvm/lapic.h
@@ -34,7 +34,7 @@ struct kvm_lapic {
 	 */
 	void *regs;
 	gpa_t vapic_addr;
-	struct page *vapic_page;
+	struct gfn_to_hva_cache vapic_cache;
 	unsigned long pending_events;
 	unsigned int sipi_vector;
 };
@@ -76,7 +76,7 @@ void kvm_set_lapic_tscdeadline_msr(struct kvm_vcpu *vcpu, u64 data);
 void kvm_apic_write_nodecode(struct kvm_vcpu *vcpu, u32 offset);
 void kvm_apic_set_eoi_accelerated(struct kvm_vcpu *vcpu, int vector);
 
-void kvm_lapic_set_vapic_addr(struct kvm_vcpu *vcpu, gpa_t vapic_addr);
+int kvm_lapic_set_vapic_addr(struct kvm_vcpu *vcpu, gpa_t vapic_addr);
 void kvm_lapic_sync_from_vapic(struct kvm_vcpu *vcpu);
 void kvm_lapic_sync_to_vapic(struct kvm_vcpu *vcpu);
 
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index b2fe1c252f3..da7837e1349 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -8283,8 +8283,7 @@ static void load_vmcs12_host_state(struct kvm_vcpu *vcpu,
 	vcpu->arch.cr4_guest_owned_bits = ~vmcs_readl(CR4_GUEST_HOST_MASK);
 	kvm_set_cr4(vcpu, vmcs12->host_cr4);
 
-	if (nested_cpu_has_ept(vmcs12))
-		nested_ept_uninit_mmu_context(vcpu);
+	nested_ept_uninit_mmu_context(vcpu);
 
 	kvm_set_cr3(vcpu, vmcs12->host_cr3);
 	kvm_mmu_reset_context(vcpu);
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 21ef1ba184a..5d004da1e35 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -3214,8 +3214,7 @@ long kvm_arch_vcpu_ioctl(struct file *filp,
 		r = -EFAULT;
 		if (copy_from_user(&va, argp, sizeof va))
 			goto out;
-		r = 0;
-		kvm_lapic_set_vapic_addr(vcpu, va.vapic_addr);
+		r = kvm_lapic_set_vapic_addr(vcpu, va.vapic_addr);
 		break;
 	}
 	case KVM_X86_SETUP_MCE: {
@@ -5739,36 +5738,6 @@ static void post_kvm_run_save(struct kvm_vcpu *vcpu)
 			!kvm_event_needs_reinjection(vcpu);
 }
 
-static int vapic_enter(struct kvm_vcpu *vcpu)
-{
-	struct kvm_lapic *apic = vcpu->arch.apic;
-	struct page *page;
-
-	if (!apic || !apic->vapic_addr)
-		return 0;
-
-	page = gfn_to_page(vcpu->kvm, apic->vapic_addr >> PAGE_SHIFT);
-	if (is_error_page(page))
-		return -EFAULT;
-
-	vcpu->arch.apic->vapic_page = page;
-	return 0;
-}
-
-static void vapic_exit(struct kvm_vcpu *vcpu)
-{
-	struct kvm_lapic *apic = vcpu->arch.apic;
-	int idx;
-
-	if (!apic || !apic->vapic_addr)
-		return;
-
-	idx = srcu_read_lock(&vcpu->kvm->srcu);
-	kvm_release_page_dirty(apic->vapic_page);
-	mark_page_dirty(vcpu->kvm, apic->vapic_addr >> PAGE_SHIFT);
-	srcu_read_unlock(&vcpu->kvm->srcu, idx);
-}
-
 static void update_cr8_intercept(struct kvm_vcpu *vcpu)
 {
 	int max_irr, tpr;
@@ -6069,11 +6038,6 @@ static int __vcpu_run(struct kvm_vcpu *vcpu)
 	struct kvm *kvm = vcpu->kvm;
 
 	vcpu->srcu_idx = srcu_read_lock(&kvm->srcu);
-	r = vapic_enter(vcpu);
-	if (r) {
-		srcu_read_unlock(&kvm->srcu, vcpu->srcu_idx);
-		return r;
-	}
 
 	r = 1;
 	while (r > 0) {
@@ -6132,8 +6096,6 @@ static int __vcpu_run(struct kvm_vcpu *vcpu)
 
 	srcu_read_unlock(&kvm->srcu, vcpu->srcu_idx);
 
-	vapic_exit(vcpu);
-
 	return r;
 }
 
diff --git a/arch/x86/mm/gup.c b/arch/x86/mm/gup.c
index dd74e46828c..0596e8e0cc1 100644
--- a/arch/x86/mm/gup.c
+++ b/arch/x86/mm/gup.c
@@ -83,6 +83,12 @@ static noinline int gup_pte_range(pmd_t pmd, unsigned long addr,
 		pte_t pte = gup_get_pte(ptep);
 		struct page *page;
 
+		/* Similar to the PMD case, NUMA hinting must take slow path */
+		if (pte_numa(pte)) {
+			pte_unmap(ptep);
+			return 0;
+		}
+
 		if ((pte_flags(pte) & (mask | _PAGE_SPECIAL)) != mask) {
 			pte_unmap(ptep);
 			return 0;
@@ -167,6 +173,13 @@ static int gup_pmd_range(pud_t pud, unsigned long addr, unsigned long end,
 		if (pmd_none(pmd) || pmd_trans_splitting(pmd))
 			return 0;
 		if (unlikely(pmd_large(pmd))) {
+			/*
+			 * NUMA hinting faults need to be handled in the GUP
+			 * slowpath for accounting purposes and so that they
+			 * can be serialised against THP migration.
+			 */
+			if (pmd_numa(pmd))
+				return 0;
 			if (!gup_huge_pmd(pmd, addr, next, write, pages, nr))
 				return 0;
 		} else {
diff --git a/arch/x86/platform/efi/early_printk.c b/arch/x86/platform/efi/early_printk.c
index 6599a0027b7..81b506d5bef 100644
--- a/arch/x86/platform/efi/early_printk.c
+++ b/arch/x86/platform/efi/early_printk.c
@@ -142,7 +142,7 @@ early_efi_write(struct console *con, const char *str, unsigned int num)
 			efi_y += font->height;
 		}
 
-		if (efi_y + font->height >= si->lfb_height) {
+		if (efi_y + font->height > si->lfb_height) {
 			u32 i;
 
 			efi_y -= font->height;
diff --git a/arch/x86/platform/efi/efi.c b/arch/x86/platform/efi/efi.c
index 7ed3ecfde98..d62ec87a2b2 100644
--- a/arch/x86/platform/efi/efi.c
+++ b/arch/x86/platform/efi/efi.c
@@ -764,18 +764,11 @@ void __init efi_init(void)
 			return;
 		set_bit(EFI_RUNTIME_SERVICES, &x86_efi_facility);
 	}
-
 	if (efi_memmap_init())
 		return;
 
 	set_bit(EFI_MEMMAP, &x86_efi_facility);
 
-#ifdef CONFIG_X86_32
-	if (efi_is_native()) {
-		x86_platform.get_wallclock = efi_get_time;
-		x86_platform.set_wallclock = efi_set_rtc_mmss;
-	}
-#endif
 	print_efi_memmap();
 }
 
diff --git a/arch/x86/platform/uv/tlb_uv.c b/arch/x86/platform/uv/tlb_uv.c
index 0f92173a12b..efe4d722039 100644
--- a/arch/x86/platform/uv/tlb_uv.c
+++ b/arch/x86/platform/uv/tlb_uv.c
@@ -1070,12 +1070,13 @@ const struct cpumask *uv_flush_tlb_others(const struct cpumask *cpumask,
 	unsigned long status;
 
 	bcp = &per_cpu(bau_control, cpu);
-	stat = bcp->statp;
-	stat->s_enters++;
 
 	if (bcp->nobau)
 		return cpumask;
 
+	stat = bcp->statp;
+	stat->s_enters++;
+
 	if (bcp->busy) {
 		descriptor_status =
 			read_lmmr(UVH_LB_BAU_SB_ACTIVATION_STATUS_0);
diff --git a/arch/x86/realmode/rm/Makefile b/arch/x86/realmode/rm/Makefile
index 88692871823..9cac82588cb 100644
--- a/arch/x86/realmode/rm/Makefile
+++ b/arch/x86/realmode/rm/Makefile
@@ -73,9 +73,10 @@ KBUILD_CFLAGS	:= $(LINUXINCLUDE) -m32 -g -Os -D_SETUP -D__KERNEL__ -D_WAKEUP \
 		   -march=i386 -mregparm=3 \
 		   -include $(srctree)/$(src)/../../boot/code16gcc.h \
 		   -fno-strict-aliasing -fomit-frame-pointer -fno-pic \
+		   -mno-mmx -mno-sse \
 		   $(call cc-option, -ffreestanding) \
 		   $(call cc-option, -fno-toplevel-reorder,\
-			$(call cc-option, -fno-unit-at-a-time)) \
+		   $(call cc-option, -fno-unit-at-a-time)) \
 		   $(call cc-option, -fno-stack-protector) \
 		   $(call cc-option, -mpreferred-stack-boundary=2)
 KBUILD_AFLAGS	:= $(KBUILD_CFLAGS) -D__ASSEMBLY__