Merge 3.0.75

Change-Id: Iefad0afd76773f4a9556775cd0fa8dcacb135cdf

31 files changed, 111 insertions, 236 deletions

diff --git a/arch/alpha/kernel/sys_nautilus.c b/arch/alpha/kernel/sys_nautilus.c
index 99c0f46..dc616b3 100644
--- a/arch/alpha/kernel/sys_nautilus.c
+++ b/arch/alpha/kernel/sys_nautilus.c
@@ -189,6 +189,10 @@ nautilus_machine_check(unsigned long vector, unsigned long la_ptr)
 extern void free_reserved_mem(void *, void *);
 extern void pcibios_claim_one_bus(struct pci_bus *);
 
+static struct resource irongate_io = {
+	.name	= "Irongate PCI IO",
+	.flags	= IORESOURCE_IO,
+};
 static struct resource irongate_mem = {
 	.name	= "Irongate PCI MEM",
 	.flags	= IORESOURCE_MEM,
@@ -210,6 +214,7 @@ nautilus_init_pci(void)
 
 	irongate = pci_get_bus_and_slot(0, 0);
 	bus->self = irongate;
+	bus->resource[0] = &irongate_io;
 	bus->resource[1] = &irongate_mem;
 
 	pci_bus_size_bridges(bus);
diff --git a/arch/arm/include/asm/signal.h b/arch/arm/include/asm/signal.h
index 43ba0fb..559ee24 100644
--- a/arch/arm/include/asm/signal.h
+++ b/arch/arm/include/asm/signal.h
@@ -127,6 +127,7 @@ struct sigaction {
 	__sigrestore_t sa_restorer;
 	sigset_t sa_mask;		/* mask last for extensibility */
 };
+#define __ARCH_HAS_SA_RESTORER
 
 struct k_sigaction {
 	struct sigaction sa;
diff --git a/arch/arm/mm/cache-feroceon-l2.c b/arch/arm/mm/cache-feroceon-l2.c
index e0b0e7a..09f8851 100644
--- a/arch/arm/mm/cache-feroceon-l2.c
+++ b/arch/arm/mm/cache-feroceon-l2.c
@@ -342,6 +342,7 @@ void __init feroceon_l2_init(int __l2_wt_override)
 	outer_cache.inv_range = feroceon_l2_inv_range;
 	outer_cache.clean_range = feroceon_l2_clean_range;
 	outer_cache.flush_range = feroceon_l2_flush_range;
+	outer_cache.inv_all = l2_inv_all;
 
 	enable_l2();
 
diff --git a/arch/avr32/include/asm/signal.h b/arch/avr32/include/asm/signal.h
index 8790dfc..e6952a0 100644
--- a/arch/avr32/include/asm/signal.h
+++ b/arch/avr32/include/asm/signal.h
@@ -128,6 +128,7 @@ struct sigaction {
 	__sigrestore_t sa_restorer;
 	sigset_t sa_mask;		/* mask last for extensibility */
 };
+#define __ARCH_HAS_SA_RESTORER
 
 struct k_sigaction {
 	struct sigaction sa;
diff --git a/arch/cris/include/asm/signal.h b/arch/cris/include/asm/signal.h
index ea6af9a..057fea2 100644
--- a/arch/cris/include/asm/signal.h
+++ b/arch/cris/include/asm/signal.h
@@ -122,6 +122,7 @@ struct sigaction {
 	void (*sa_restorer)(void);
 	sigset_t sa_mask;		/* mask last for extensibility */
 };
+#define __ARCH_HAS_SA_RESTORER
 
 struct k_sigaction {
 	struct sigaction sa;
diff --git a/arch/h8300/include/asm/signal.h b/arch/h8300/include/asm/signal.h
index fd8b66e..8695707 100644
--- a/arch/h8300/include/asm/signal.h
+++ b/arch/h8300/include/asm/signal.h
@@ -121,6 +121,7 @@ struct sigaction {
 	void (*sa_restorer)(void);
 	sigset_t sa_mask;		/* mask last for extensibility */
 };
+#define __ARCH_HAS_SA_RESTORER
 
 struct k_sigaction {
 	struct sigaction sa;
diff --git a/arch/ia64/kvm/kvm-ia64.c b/arch/ia64/kvm/kvm-ia64.c
index 8213efe..a874213 100644
--- a/arch/ia64/kvm/kvm-ia64.c
+++ b/arch/ia64/kvm/kvm-ia64.c
@@ -1168,6 +1168,11 @@ out:
 
 #define PALE_RESET_ENTRY    0x80000000ffffffb0UL
 
+bool kvm_vcpu_compatible(struct kvm_vcpu *vcpu)
+{
+	return irqchip_in_kernel(vcpu->kcm) == (vcpu->arch.apic != NULL);
+}
+
 int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu)
 {
 	struct kvm_vcpu *v;
diff --git a/arch/m32r/include/asm/signal.h b/arch/m32r/include/asm/signal.h
index b2eeb0d..802d561 100644
--- a/arch/m32r/include/asm/signal.h
+++ b/arch/m32r/include/asm/signal.h
@@ -123,6 +123,7 @@ struct sigaction {
 	__sigrestore_t sa_restorer;
 	sigset_t sa_mask;		/* mask last for extensibility */
 };
+#define __ARCH_HAS_SA_RESTORER
 
 struct k_sigaction {
 	struct sigaction sa;
diff --git a/arch/m68k/include/asm/signal.h b/arch/m68k/include/asm/signal.h
index 0b6b0e5..ee80858 100644
--- a/arch/m68k/include/asm/signal.h
+++ b/arch/m68k/include/asm/signal.h
@@ -119,6 +119,7 @@ struct sigaction {
 	__sigrestore_t sa_restorer;
 	sigset_t sa_mask;		/* mask last for extensibility */
 };
+#define __ARCH_HAS_SA_RESTORER
 
 struct k_sigaction {
 	struct sigaction sa;
diff --git a/arch/mn10300/include/asm/signal.h b/arch/mn10300/include/asm/signal.h
index 1865d72..eecaa76 100644
--- a/arch/mn10300/include/asm/signal.h
+++ b/arch/mn10300/include/asm/signal.h
@@ -131,6 +131,7 @@ struct sigaction {
 	__sigrestore_t sa_restorer;
 	sigset_t sa_mask;		/* mask last for extensibility */
 };
+#define __ARCH_HAS_SA_RESTORER
 
 struct k_sigaction {
 	struct sigaction sa;
diff --git a/arch/powerpc/include/asm/signal.h b/arch/powerpc/include/asm/signal.h
index 3eb13be..ec63a0a 100644
--- a/arch/powerpc/include/asm/signal.h
+++ b/arch/powerpc/include/asm/signal.h
@@ -109,6 +109,7 @@ struct sigaction {
 	__sigrestore_t sa_restorer;
 	sigset_t sa_mask;		/* mask last for extensibility */
 };
+#define __ARCH_HAS_SA_RESTORER
 
 struct k_sigaction {
 	struct sigaction sa;
diff --git a/arch/powerpc/platforms/pseries/lpar.c b/arch/powerpc/platforms/pseries/lpar.c
index 81e30d9..2e0b2a7 100644
--- a/arch/powerpc/platforms/pseries/lpar.c
+++ b/arch/powerpc/platforms/pseries/lpar.c
@@ -377,7 +377,13 @@ static long pSeries_lpar_hpte_remove(unsigned long hpte_group)
 					   (0x1UL << 4), &dummy1, &dummy2);
 		if (lpar_rc == H_SUCCESS)
 			return i;
-		BUG_ON(lpar_rc != H_NOT_FOUND);
+
+		/*
+		 * The test for adjunct partition is performed before the
+		 * ANDCOND test.  H_RESOURCE may be returned, so we need to
+		 * check for that as well.
+		 */
+		BUG_ON(lpar_rc != H_NOT_FOUND && lpar_rc != H_RESOURCE);
 
 		slot_offset++;
 		slot_offset &= 0x7;
diff --git a/arch/s390/include/asm/signal.h b/arch/s390/include/asm/signal.h
index cdf5cb2..c872626 100644
--- a/arch/s390/include/asm/signal.h
+++ b/arch/s390/include/asm/signal.h
@@ -131,6 +131,7 @@ struct sigaction {
         void (*sa_restorer)(void);
         sigset_t sa_mask;               /* mask last for extensibility */
 };
+#define __ARCH_HAS_SA_RESTORER
 
 struct k_sigaction {
         struct sigaction sa;
diff --git a/arch/sparc/include/asm/signal.h b/arch/sparc/include/asm/signal.h
index e49b828..4929431 100644
--- a/arch/sparc/include/asm/signal.h
+++ b/arch/sparc/include/asm/signal.h
@@ -191,6 +191,7 @@ struct __old_sigaction {
 	unsigned long		sa_flags;
 	void			(*sa_restorer)(void);  /* not used by Linux/SPARC yet */
 };
+#define __ARCH_HAS_SA_RESTORER
 
 typedef struct sigaltstack {
 	void			__user *ss_sp;
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index a0e9bda..90bf314 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -1219,10 +1219,6 @@ config HAVE_ARCH_BOOTMEM
 	def_bool y
 	depends on X86_32 && NUMA
 
-config HAVE_ARCH_ALLOC_REMAP
-	def_bool y
-	depends on X86_32 && NUMA
-
 config ARCH_HAVE_MEMORY_PRESENT
 	def_bool y
 	depends on X86_32 && DISCONTIGMEM
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index d2ac8e2..1eb45de 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -391,8 +391,8 @@ struct kvm_vcpu_arch {
 	gpa_t time;
 	struct pvclock_vcpu_time_info hv_clock;
 	unsigned int hw_tsc_khz;
-	unsigned int time_offset;
-	struct page *time_page;
+	struct gfn_to_hva_cache pv_time;
+	bool pv_time_enabled;
 	u64 last_guest_tsc;
 	u64 last_kernel_ns;
 	u64 last_tsc_nsec;
diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h
index ebbc4d8..2fdfe31 100644
--- a/arch/x86/include/asm/paravirt.h
+++ b/arch/x86/include/asm/paravirt.h
@@ -731,7 +731,10 @@ static inline void arch_leave_lazy_mmu_mode(void)
 	PVOP_VCALL0(pv_mmu_ops.lazy_mode.leave);
 }
 
-void arch_flush_lazy_mmu_mode(void);
+static inline void arch_flush_lazy_mmu_mode(void)
+{
+	PVOP_VCALL0(pv_mmu_ops.lazy_mode.flush);
+}
 
 static inline void __set_fixmap(unsigned /* enum fixed_addresses */ idx,
 				phys_addr_t phys, pgprot_t flags)
diff --git a/arch/x86/include/asm/paravirt_types.h b/arch/x86/include/asm/paravirt_types.h
index 8288509..4b67ec9 100644
--- a/arch/x86/include/asm/paravirt_types.h
+++ b/arch/x86/include/asm/paravirt_types.h
@@ -85,6 +85,7 @@ struct pv_lazy_ops {
 	/* Set deferred update mode, used for batching operations. */
 	void (*enter)(void);
 	void (*leave)(void);
+	void (*flush)(void);
 };
 
 struct pv_time_ops {
@@ -673,6 +674,7 @@ void paravirt_end_context_switch(struct task_struct *next);
 
 void paravirt_enter_lazy_mmu(void);
 void paravirt_leave_lazy_mmu(void);
+void paravirt_flush_lazy_mmu(void);
 
 void _paravirt_nop(void);
 u32 _paravirt_ident_32(u32);
diff --git a/arch/x86/include/asm/signal.h b/arch/x86/include/asm/signal.h
index 598457c..6cbc795 100644
--- a/arch/x86/include/asm/signal.h
+++ b/arch/x86/include/asm/signal.h
@@ -125,6 +125,8 @@ typedef unsigned long sigset_t;
 extern void do_notify_resume(struct pt_regs *, void *, __u32);
 # endif /* __KERNEL__ */
 
+#define __ARCH_HAS_SA_RESTORER
+
 #ifdef __i386__
 # ifdef __KERNEL__
 struct old_sigaction {
diff --git a/arch/x86/kernel/amd_iommu.c b/arch/x86/kernel/amd_iommu.c
index bfd75ff..d9302b7 100644
--- a/arch/x86/kernel/amd_iommu.c
+++ b/arch/x86/kernel/amd_iommu.c
@@ -53,6 +53,8 @@ static struct protection_domain *pt_domain;
 
 static struct iommu_ops amd_iommu_ops;
 
+static struct dma_map_ops amd_iommu_dma_ops;
+
 /*
  * general struct to manage commands send to an IOMMU
  */
@@ -1778,18 +1780,20 @@ static int device_change_notifier(struct notifier_block *nb,
 
 		domain = domain_for_device(dev);
 
-		/* allocate a protection domain if a device is added */
 		dma_domain = find_protection_domain(devid);
-		if (dma_domain)
-			goto out;
-		dma_domain = dma_ops_domain_alloc();
-		if (!dma_domain)
-			goto out;
-		dma_domain->target_dev = devid;
+		if (!dma_domain) {
+			/* allocate a protection domain if a device is added */
+			dma_domain = dma_ops_domain_alloc();
+			if (!dma_domain)
+				goto out;
+			dma_domain->target_dev = devid;
+
+			spin_lock_irqsave(&iommu_pd_list_lock, flags);
+			list_add_tail(&dma_domain->list, &iommu_pd_list);
+			spin_unlock_irqrestore(&iommu_pd_list_lock, flags);
+		}
 
-		spin_lock_irqsave(&iommu_pd_list_lock, flags);
-		list_add_tail(&dma_domain->list, &iommu_pd_list);
-		spin_unlock_irqrestore(&iommu_pd_list_lock, flags);
+		dev->archdata.dma_ops = &amd_iommu_dma_ops;
 
 		break;
 	case BUS_NOTIFY_DEL_DEVICE:
diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c
index 869e1ae..704faba 100644
--- a/arch/x86/kernel/paravirt.c
+++ b/arch/x86/kernel/paravirt.c
@@ -253,6 +253,18 @@ void paravirt_leave_lazy_mmu(void)
 	leave_lazy(PARAVIRT_LAZY_MMU);
 }
 
+void paravirt_flush_lazy_mmu(void)
+{
+	preempt_disable();
+
+	if (paravirt_get_lazy_mode() == PARAVIRT_LAZY_MMU) {
+		arch_leave_lazy_mmu_mode();
+		arch_enter_lazy_mmu_mode();
+	}
+
+	preempt_enable();
+}
+
 void paravirt_start_context_switch(struct task_struct *prev)
 {
 	BUG_ON(preemptible());
@@ -282,18 +294,6 @@ enum paravirt_lazy_mode paravirt_get_lazy_mode(void)
 	return percpu_read(paravirt_lazy_mode);
 }
 
-void arch_flush_lazy_mmu_mode(void)
-{
-	preempt_disable();
-
-	if (paravirt_get_lazy_mode() == PARAVIRT_LAZY_MMU) {
-		arch_leave_lazy_mmu_mode();
-		arch_enter_lazy_mmu_mode();
-	}
-
-	preempt_enable();
-}
-
 struct pv_info pv_info = {
 	.name = "bare hardware",
 	.paravirt_enabled = 0,
@@ -462,6 +462,7 @@ struct pv_mmu_ops pv_mmu_ops = {
 	.lazy_mode = {
 		.enter = paravirt_nop,
 		.leave = paravirt_nop,
+		.flush = paravirt_nop,
 	},
 
 	.set_fixmap = native_set_fixmap,
diff --git a/arch/x86/kvm/i8254.c b/arch/x86/kvm/i8254.c
index efad723..43e04d1 100644
--- a/arch/x86/kvm/i8254.c
+++ b/arch/x86/kvm/i8254.c
@@ -338,11 +338,15 @@ static enum hrtimer_restart pit_timer_fn(struct hrtimer *data)
 		return HRTIMER_NORESTART;
 }
 
-static void create_pit_timer(struct kvm_kpit_state *ps, u32 val, int is_period)
+static void create_pit_timer(struct kvm *kvm, u32 val, int is_period)
 {
+	struct kvm_kpit_state *ps = &kvm->arch.vpit->pit_state;
 	struct kvm_timer *pt = &ps->pit_timer;
 	s64 interval;
 
+	if (!irqchip_in_kernel(kvm))
+		return;
+
 	interval = muldiv64(val, NSEC_PER_SEC, KVM_PIT_FREQ);
 
 	pr_debug("create pit timer, interval is %llu nsec\n", interval);
@@ -394,13 +398,13 @@ static void pit_load_count(struct kvm *kvm, int channel, u32 val)
         /* FIXME: enhance mode 4 precision */
 	case 4:
 		if (!(ps->flags & KVM_PIT_FLAGS_HPET_LEGACY)) {
-			create_pit_timer(ps, val, 0);
+			create_pit_timer(kvm, val, 0);
 		}
 		break;
 	case 2:
 	case 3:
 		if (!(ps->flags & KVM_PIT_FLAGS_HPET_LEGACY)){
-			create_pit_timer(ps, val, 1);
+			create_pit_timer(kvm, val, 1);
 		}
 		break;
 	default:
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index fbb0936..15e79a6 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -575,6 +575,9 @@ static bool guest_cpuid_has_xsave(struct kvm_vcpu *vcpu)
 {
 	struct kvm_cpuid_entry2 *best;
 
+	if (!cpu_has_xsave)
+		return 0;
+
 	best = kvm_find_cpuid_entry(vcpu, 1, 0);
 	return best && (best->ecx & bit(X86_FEATURE_XSAVE));
 }
@@ -1070,7 +1073,6 @@ static int kvm_guest_time_update(struct kvm_vcpu *v)
 {
 	unsigned long flags;
 	struct kvm_vcpu_arch *vcpu = &v->arch;
-	void *shared_kaddr;
 	unsigned long this_tsc_khz;
 	s64 kernel_ns, max_kernel_ns;
 	u64 tsc_timestamp;
@@ -1106,7 +1108,7 @@ static int kvm_guest_time_update(struct kvm_vcpu *v)
 
 	local_irq_restore(flags);
 
-	if (!vcpu->time_page)
+	if (!vcpu->pv_time_enabled)
 		return 0;
 
 	/*
@@ -1164,14 +1166,9 @@ static int kvm_guest_time_update(struct kvm_vcpu *v)
 	 */
 	vcpu->hv_clock.version += 2;
 
-	shared_kaddr = kmap_atomic(vcpu->time_page, KM_USER0);
-
-	memcpy(shared_kaddr + vcpu->time_offset, &vcpu->hv_clock,
-	       sizeof(vcpu->hv_clock));
-
-	kunmap_atomic(shared_kaddr, KM_USER0);
-
-	mark_page_dirty(v->kvm, vcpu->time >> PAGE_SHIFT);
+	kvm_write_guest_cached(v->kvm, &vcpu->pv_time,
+				&vcpu->hv_clock,
+				sizeof(vcpu->hv_clock));
 	return 0;
 }
 
@@ -1451,7 +1448,8 @@ static int kvm_pv_enable_async_pf(struct kvm_vcpu *vcpu, u64 data)
 		return 0;
 	}
 
-	if (kvm_gfn_to_hva_cache_init(vcpu->kvm, &vcpu->arch.apf.data, gpa))
+	if (kvm_gfn_to_hva_cache_init(vcpu->kvm, &vcpu->arch.apf.data, gpa,
+					sizeof(u32)))
 		return 1;
 
 	vcpu->arch.apf.send_user_only = !(data & KVM_ASYNC_PF_SEND_ALWAYS);
@@ -1461,10 +1459,7 @@ static int kvm_pv_enable_async_pf(struct kvm_vcpu *vcpu, u64 data)
 
 static void kvmclock_reset(struct kvm_vcpu *vcpu)
 {
-	if (vcpu->arch.time_page) {
-		kvm_release_page_dirty(vcpu->arch.time_page);
-		vcpu->arch.time_page = NULL;
-	}
+	vcpu->arch.pv_time_enabled = false;
 }
 
 int kvm_set_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 data)
@@ -1524,6 +1519,7 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 data)
 		break;
 	case MSR_KVM_SYSTEM_TIME_NEW:
 	case MSR_KVM_SYSTEM_TIME: {
+		u64 gpa_offset;
 		kvmclock_reset(vcpu);
 
 		vcpu->arch.time = data;
@@ -1533,16 +1529,14 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 data)
 		if (!(data & 1))
 			break;
 
-		/* ...but clean it before doing the actual write */
-		vcpu->arch.time_offset = data & ~(PAGE_MASK | 1);
-
-		vcpu->arch.time_page =
-				gfn_to_page(vcpu->kvm, data >> PAGE_SHIFT);
+		gpa_offset = data & ~(PAGE_MASK | 1);
 
-		if (is_error_page(vcpu->arch.time_page)) {
-			kvm_release_page_clean(vcpu->arch.time_page);
-			vcpu->arch.time_page = NULL;
-		}
+		if (kvm_gfn_to_hva_cache_init(vcpu->kvm,
+		     &vcpu->arch.pv_time, data & ~1ULL,
+		     sizeof(struct pvclock_vcpu_time_info)))
+			vcpu->arch.pv_time_enabled = false;
+		else
+			vcpu->arch.pv_time_enabled = true;
 		break;
 	}
 	case MSR_KVM_ASYNC_PF_EN:
@@ -3410,6 +3404,9 @@ long kvm_arch_vm_ioctl(struct file *filp,
 		r = -EEXIST;
 		if (kvm->arch.vpic)
 			goto create_irqchip_unlock;
+		r = -EINVAL;
+		if (atomic_read(&kvm->online_vcpus))
+			goto create_irqchip_unlock;
 		r = -ENOMEM;
 		vpic = kvm_create_pic(kvm);
 		if (vpic) {
@@ -5851,6 +5848,9 @@ int kvm_arch_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu,
 	int pending_vec, max_bits, idx;
 	struct desc_ptr dt;
 
+	if (!guest_cpuid_has_xsave(vcpu) && (sregs->cr4 & X86_CR4_OSXSAVE))
+		return -EINVAL;
+
 	dt.size = sregs->idt.limit;
 	dt.address = sregs->idt.base;
 	kvm_x86_ops->set_idt(vcpu, &dt);
@@ -6116,12 +6116,7 @@ int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu)
 	if (r == 0)
 		r = kvm_mmu_setup(vcpu);
 	vcpu_put(vcpu);
-	if (r < 0)
-		goto free_vcpu;
 
-	return 0;
-free_vcpu:
-	kvm_x86_ops->vcpu_free(vcpu);
 	return r;
 }
 
@@ -6194,6 +6189,11 @@ void kvm_arch_check_processor_compat(void *rtn)
 	kvm_x86_ops->check_processor_compatibility(rtn);
 }
 
+bool kvm_vcpu_compatible(struct kvm_vcpu *vcpu)
+{
+	return irqchip_in_kernel(vcpu->kvm) == (vcpu->arch.apic != NULL);
+}
+
 int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu)
 {
 	struct page *page;
@@ -6243,6 +6243,7 @@ int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu)
 	if (!zalloc_cpumask_var(&vcpu->arch.wbinvd_dirty_mask, GFP_KERNEL))
 		goto fail_free_mce_banks;
 
+	vcpu->arch.pv_time_enabled = false;
 	kvm_async_pf_hash_reset(vcpu);
 
 	return 0;
diff --git a/arch/x86/lguest/boot.c b/arch/x86/lguest/boot.c
index db832fd..2d45247 100644
--- a/arch/x86/lguest/boot.c
+++ b/arch/x86/lguest/boot.c
@@ -1309,6 +1309,7 @@ __init void lguest_init(void)
 	pv_mmu_ops.read_cr3 = lguest_read_cr3;
 	pv_mmu_ops.lazy_mode.enter = paravirt_enter_lazy_mmu;
 	pv_mmu_ops.lazy_mode.leave = lguest_leave_lazy_mmu_mode;
+	pv_mmu_ops.lazy_mode.flush = paravirt_flush_lazy_mmu;
 	pv_mmu_ops.pte_update = lguest_pte_update;
 	pv_mmu_ops.pte_update_defer = lguest_pte_update;
 
diff --git a/arch/x86/lib/usercopy_64.c b/arch/x86/lib/usercopy_64.c
index b7c2849..554b7b5 100644
--- a/arch/x86/lib/usercopy_64.c
+++ b/arch/x86/lib/usercopy_64.c
@@ -169,10 +169,10 @@ copy_user_handle_tail(char *to, char *from, unsigned len, unsigned zerorest)
 	char c;
 	unsigned zero_len;
 
-	for (; len; --len) {
+	for (; len; --len, to++) {
 		if (__get_user_nocheck(c, from++, sizeof(char)))
 			break;
-		if (__put_user_nocheck(c, to++, sizeof(char)))
+		if (__put_user_nocheck(c, to, sizeof(char)))
 			break;
 	}
 
diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c
index 3b2ad91..7653f14 100644
--- a/arch/x86/mm/fault.c
+++ b/arch/x86/mm/fault.c
@@ -376,10 +376,12 @@ static noinline __kprobes int vmalloc_fault(unsigned long address)
 	if (pgd_none(*pgd_ref))
 		return -1;
 
-	if (pgd_none(*pgd))
+	if (pgd_none(*pgd)) {
 		set_pgd(pgd, *pgd_ref);
-	else
+		arch_flush_lazy_mmu_mode();
+	} else {
 		BUG_ON(pgd_page_vaddr(*pgd) != pgd_page_vaddr(*pgd_ref));
+	}
 
 	/*
 	 * Below here mismatches are bugs because these lower tables
diff --git a/arch/x86/mm/numa.c b/arch/x86/mm/numa.c
index f5510d8..469ccae 100644
--- a/arch/x86/mm/numa.c
+++ b/arch/x86/mm/numa.c
@@ -207,9 +207,6 @@ static void __init setup_node_data(int nid, u64 start, u64 end)
 	if (end && (end - start) < NODE_MIN_SIZE)
 		return;
 
-	/* initialize remap allocator before aligning to ZONE_ALIGN */
-	init_alloc_remap(nid, start, end);
-
 	start = roundup(start, ZONE_ALIGN);
 
 	printk(KERN_INFO "Initmem setup node %d %016Lx-%016Lx\n",
diff --git a/arch/x86/mm/numa_32.c b/arch/x86/mm/numa_32.c
index 849a975..025d469 100644
--- a/arch/x86/mm/numa_32.c
+++ b/arch/x86/mm/numa_32.c
@@ -73,167 +73,6 @@ unsigned long node_memmap_size_bytes(int nid, unsigned long start_pfn,
 
 extern unsigned long highend_pfn, highstart_pfn;
 
-#define LARGE_PAGE_BYTES (PTRS_PER_PTE * PAGE_SIZE)
-
-static void *node_remap_start_vaddr[MAX_NUMNODES];
-void set_pmd_pfn(unsigned long vaddr, unsigned long pfn, pgprot_t flags);
-
-/*
- * Remap memory allocator
- */
-static unsigned long node_remap_start_pfn[MAX_NUMNODES];
-static void *node_remap_end_vaddr[MAX_NUMNODES];
-static void *node_remap_alloc_vaddr[MAX_NUMNODES];
-
-/**
- * alloc_remap - Allocate remapped memory
- * @nid: NUMA node to allocate memory from
- * @size: The size of allocation
- *
- * Allocate @size bytes from the remap area of NUMA node @nid.  The
- * size of the remap area is predetermined by init_alloc_remap() and
- * only the callers considered there should call this function.  For
- * more info, please read the comment on top of init_alloc_remap().
- *
- * The caller must be ready to handle allocation failure from this
- * function and fall back to regular memory allocator in such cases.
- *
- * CONTEXT:
- * Single CPU early boot context.
- *
- * RETURNS:
- * Pointer to the allocated memory on success, %NULL on failure.
- */
-void *alloc_remap(int nid, unsigned long size)
-{
-	void *allocation = node_remap_alloc_vaddr[nid];
-
-	size = ALIGN(size, L1_CACHE_BYTES);
-
-	if (!allocation || (allocation + size) > node_remap_end_vaddr[nid])
-		return NULL;
-
-	node_remap_alloc_vaddr[nid] += size;
-	memset(allocation, 0, size);
-
-	return allocation;
-}
-
-#ifdef CONFIG_HIBERNATION
-/**
- * resume_map_numa_kva - add KVA mapping to the temporary page tables created
- *                       during resume from hibernation
- * @pgd_base - temporary resume page directory
- */
-void resume_map_numa_kva(pgd_t *pgd_base)
-{
-	int node;
-
-	for_each_online_node(node) {
-		unsigned long start_va, start_pfn, nr_pages, pfn;
-
-		start_va = (unsigned long)node_remap_start_vaddr[node];
-		start_pfn = node_remap_start_pfn[node];
-		nr_pages = (node_remap_end_vaddr[node] -
-			    node_remap_start_vaddr[node]) >> PAGE_SHIFT;
-
-		printk(KERN_DEBUG "%s: node %d\n", __func__, node);
-
-		for (pfn = 0; pfn < nr_pages; pfn += PTRS_PER_PTE) {
-			unsigned long vaddr = start_va + (pfn << PAGE_SHIFT);
-			pgd_t *pgd = pgd_base + pgd_index(vaddr);
-			pud_t *pud = pud_offset(pgd, vaddr);
-			pmd_t *pmd = pmd_offset(pud, vaddr);
-
-			set_pmd(pmd, pfn_pmd(start_pfn + pfn,
-						PAGE_KERNEL_LARGE_EXEC));
-
-			printk(KERN_DEBUG "%s: %08lx -> pfn %08lx\n",
-				__func__, vaddr, start_pfn + pfn);
-		}
-	}
-}
-#endif
-
-/**
- * init_alloc_remap - Initialize remap allocator for a NUMA node
- * @nid: NUMA node to initizlie remap allocator for
- *
- * NUMA nodes may end up without any lowmem.  As allocating pgdat and
- * memmap on a different node with lowmem is inefficient, a special
- * remap allocator is implemented which can be used by alloc_remap().
- *
- * For each node, the amount of memory which will be necessary for
- * pgdat and memmap is calculated and two memory areas of the size are
- * allocated - one in the node and the other in lowmem; then, the area
- * in the node is remapped to the lowmem area.
- *
- * As pgdat and memmap must be allocated in lowmem anyway, this
- * doesn't waste lowmem address space; however, the actual lowmem
- * which gets remapped over is wasted.  The amount shouldn't be
- * problematic on machines this feature will be used.
- *
- * Initialization failure isn't fatal.  alloc_remap() is used
- * opportunistically and the callers will fall back to other memory
- * allocation mechanisms on failure.
- */
-void __init init_alloc_remap(int nid, u64 start, u64 end)
-{
-	unsigned long start_pfn = start >> PAGE_SHIFT;
-	unsigned long end_pfn = end >> PAGE_SHIFT;
-	unsigned long size, pfn;
-	u64 node_pa, remap_pa;
-	void *remap_va;
-
-	/*
-	 * The acpi/srat node info can show hot-add memroy zones where
-	 * memory could be added but not currently present.
-	 */
-	printk(KERN_DEBUG "node %d pfn: [%lx - %lx]\n",
-	       nid, start_pfn, end_pfn);
-
-	/* calculate the necessary space aligned to large page size */
-	size = node_memmap_size_bytes(nid, start_pfn, end_pfn);
-	size += ALIGN(sizeof(pg_data_t), PAGE_SIZE);
-	size = ALIGN(size, LARGE_PAGE_BYTES);
-
-	/* allocate node memory and the lowmem remap area */
-	node_pa = memblock_find_in_range(start, end, size, LARGE_PAGE_BYTES);
-	if (node_pa == MEMBLOCK_ERROR) {
-		pr_warning("remap_alloc: failed to allocate %lu bytes for node %d\n",
-			   size, nid);
-		return;
-	}
-	memblock_x86_reserve_range(node_pa, node_pa + size, "KVA RAM");
-
-	remap_pa = memblock_find_in_range(min_low_pfn << PAGE_SHIFT,
-					  max_low_pfn << PAGE_SHIFT,
-					  size, LARGE_PAGE_BYTES);
-	if (remap_pa == MEMBLOCK_ERROR) {
-		pr_warning("remap_alloc: failed to allocate %lu bytes remap area for node %d\n",
-			   size, nid);
-		memblock_x86_free_range(node_pa, node_pa + size);
-		return;
-	}
-	memblock_x86_reserve_range(remap_pa, remap_pa + size, "KVA PG");
-	remap_va = phys_to_virt(remap_pa);
-
-	/* perform actual remap */
-	for (pfn = 0; pfn < size >> PAGE_SHIFT; pfn += PTRS_PER_PTE)
-		set_pmd_pfn((unsigned long)remap_va + (pfn << PAGE_SHIFT),
-			    (node_pa >> PAGE_SHIFT) + pfn,
-			    PAGE_KERNEL_LARGE);
-
-	/* initialize remap allocator parameters */
-	node_remap_start_pfn[nid] = node_pa >> PAGE_SHIFT;
-	node_remap_start_vaddr[nid] = remap_va;
-	node_remap_end_vaddr[nid] = remap_va + size;
-	node_remap_alloc_vaddr[nid] = remap_va;
-
-	printk(KERN_DEBUG "remap_alloc: node %d [%08llx-%08llx) -> [%p-%p)\n",
-	       nid, node_pa, node_pa + size, remap_va, remap_va + size);
-}
-
 void __init initmem_init(void)
 {
 	x86_numa_init();
diff --git a/arch/x86/mm/numa_internal.h b/arch/x86/mm/numa_internal.h
index 7178c3a..ad86ec9 100644
--- a/arch/x86/mm/numa_internal.h
+++ b/arch/x86/mm/numa_internal.h
@@ -21,12 +21,6 @@ void __init numa_reset_distance(void);
 
 void __init x86_numa_init(void);
 
-#ifdef CONFIG_X86_64
-static inline void init_alloc_remap(int nid, u64 start, u64 end)	{ }
-#else
-void __init init_alloc_remap(int nid, u64 start, u64 end);
-#endif
-
 #ifdef CONFIG_NUMA_EMU
 void __init numa_emulation(struct numa_meminfo *numa_meminfo,
 			   int numa_dist_cnt);
diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c
index d957dce..a0aed70 100644
--- a/arch/x86/xen/mmu.c
+++ b/arch/x86/xen/mmu.c
@@ -2011,6 +2011,7 @@ static const struct pv_mmu_ops xen_mmu_ops __initconst = {
 	.lazy_mode = {
 		.enter = paravirt_enter_lazy_mmu,
 		.leave = xen_leave_lazy_mmu,
+		.flush = paravirt_flush_lazy_mmu,
 	},
 
 	.set_fixmap = xen_set_fixmap,
diff --git a/arch/xtensa/include/asm/signal.h b/arch/xtensa/include/asm/signal.h
index 633ba73..75edf8a 100644
--- a/arch/xtensa/include/asm/signal.h
+++ b/arch/xtensa/include/asm/signal.h
@@ -133,6 +133,7 @@ struct sigaction {
 	void (*sa_restorer)(void);
 	sigset_t sa_mask;		/* mask last for extensibility */
 };
+#define __ARCH_HAS_SA_RESTORER
 
 struct k_sigaction {
 	struct sigaction sa;