Merge branch 'for-4.4/hotplug' into libnvdimm-for-next

10 files changed, 142 insertions, 92 deletions

diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 328c8352480c..96d058a87100 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -1308,6 +1308,7 @@ config HIGHMEM
 config X86_PAE
 	bool "PAE (Physical Address Extension) Support"
 	depends on X86_32 && !HIGHMEM4G
+	select SWIOTLB
 	---help---
 	  PAE is required for NX support, and furthermore enables
 	  larger swapspace support for non-overcommit purposes. It
diff --git a/arch/x86/crypto/camellia_aesni_avx_glue.c b/arch/x86/crypto/camellia_aesni_avx_glue.c
index 80a0e4389c9a..bacaa13acac5 100644
--- a/arch/x86/crypto/camellia_aesni_avx_glue.c
+++ b/arch/x86/crypto/camellia_aesni_avx_glue.c
@@ -554,6 +554,11 @@ static int __init camellia_aesni_init(void)
 {
 	const char *feature_name;
 
+	if (!cpu_has_avx || !cpu_has_aes || !cpu_has_osxsave) {
+		pr_info("AVX or AES-NI instructions are not detected.\n");
+		return -ENODEV;
+	}
+
 	if (!cpu_has_xfeatures(XSTATE_SSE | XSTATE_YMM, &feature_name)) {
 		pr_info("CPU feature '%s' is not supported.\n", feature_name);
 		return -ENODEV;
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 2beee0382088..3a36ee704c30 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -1226,10 +1226,8 @@ void kvm_complete_insn_gp(struct kvm_vcpu *vcpu, int err);
 
 int kvm_is_in_guest(void);
 
-int __x86_set_memory_region(struct kvm *kvm,
-			    const struct kvm_userspace_memory_region *mem);
-int x86_set_memory_region(struct kvm *kvm,
-			  const struct kvm_userspace_memory_region *mem);
+int __x86_set_memory_region(struct kvm *kvm, int id, gpa_t gpa, u32 size);
+int x86_set_memory_region(struct kvm *kvm, int id, gpa_t gpa, u32 size);
 bool kvm_vcpu_is_reset_bsp(struct kvm_vcpu *vcpu);
 bool kvm_vcpu_is_bsp(struct kvm_vcpu *vcpu);
 
diff --git a/arch/x86/include/asm/xen/hypercall.h b/arch/x86/include/asm/xen/hypercall.h
index 83aea8055119..4c20dd333412 100644
--- a/arch/x86/include/asm/xen/hypercall.h
+++ b/arch/x86/include/asm/xen/hypercall.h
@@ -336,10 +336,10 @@ HYPERVISOR_update_descriptor(u64 ma, u64 desc)
 	return _hypercall4(int, update_descriptor, ma, ma>>32, desc, desc>>32);
 }
 
-static inline int
+static inline long
 HYPERVISOR_memory_op(unsigned int cmd, void *arg)
 {
-	return _hypercall2(int, memory_op, cmd, arg);
+	return _hypercall2(long, memory_op, cmd, arg);
 }
 
 static inline int
diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index b372a7557c16..9da95b9daf8d 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -2418,7 +2418,7 @@ static int rsm_load_state_64(struct x86_emulate_ctxt *ctxt, u64 smbase)
 	u64 val, cr0, cr4;
 	u32 base3;
 	u16 selector;
-	int i;
+	int i, r;
 
 	for (i = 0; i < 16; i++)
 		*reg_write(ctxt, i) = GET_SMSTATE(u64, smbase, 0x7ff8 - i * 8);
@@ -2460,13 +2460,17 @@ static int rsm_load_state_64(struct x86_emulate_ctxt *ctxt, u64 smbase)
 	dt.address =                GET_SMSTATE(u64, smbase, 0x7e68);
 	ctxt->ops->set_gdt(ctxt, &dt);
 
+	r = rsm_enter_protected_mode(ctxt, cr0, cr4);
+	if (r != X86EMUL_CONTINUE)
+		return r;
+
 	for (i = 0; i < 6; i++) {
-		int r = rsm_load_seg_64(ctxt, smbase, i);
+		r = rsm_load_seg_64(ctxt, smbase, i);
 		if (r != X86EMUL_CONTINUE)
 			return r;
 	}
 
-	return rsm_enter_protected_mode(ctxt, cr0, cr4);
+	return X86EMUL_CONTINUE;
 }
 
 static int em_rsm(struct x86_emulate_ctxt *ctxt)
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 06ef4908ba61..6a8bc64566ab 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -4105,17 +4105,13 @@ static void seg_setup(int seg)
 static int alloc_apic_access_page(struct kvm *kvm)
 {
 	struct page *page;
-	struct kvm_userspace_memory_region kvm_userspace_mem;
 	int r = 0;
 
 	mutex_lock(&kvm->slots_lock);
 	if (kvm->arch.apic_access_page_done)
 		goto out;
-	kvm_userspace_mem.slot = APIC_ACCESS_PAGE_PRIVATE_MEMSLOT;
-	kvm_userspace_mem.flags = 0;
-	kvm_userspace_mem.guest_phys_addr = APIC_DEFAULT_PHYS_BASE;
-	kvm_userspace_mem.memory_size = PAGE_SIZE;
-	r = __x86_set_memory_region(kvm, &kvm_userspace_mem);
+	r = __x86_set_memory_region(kvm, APIC_ACCESS_PAGE_PRIVATE_MEMSLOT,
+				    APIC_DEFAULT_PHYS_BASE, PAGE_SIZE);
 	if (r)
 		goto out;
 
@@ -4140,17 +4136,12 @@ static int alloc_identity_pagetable(struct kvm *kvm)
 {
 	/* Called with kvm->slots_lock held. */
 
-	struct kvm_userspace_memory_region kvm_userspace_mem;
 	int r = 0;
 
 	BUG_ON(kvm->arch.ept_identity_pagetable_done);
 
-	kvm_userspace_mem.slot = IDENTITY_PAGETABLE_PRIVATE_MEMSLOT;
-	kvm_userspace_mem.flags = 0;
-	kvm_userspace_mem.guest_phys_addr =
-		kvm->arch.ept_identity_map_addr;
-	kvm_userspace_mem.memory_size = PAGE_SIZE;
-	r = __x86_set_memory_region(kvm, &kvm_userspace_mem);
+	r = __x86_set_memory_region(kvm, IDENTITY_PAGETABLE_PRIVATE_MEMSLOT,
+				    kvm->arch.ept_identity_map_addr, PAGE_SIZE);
 
 	return r;
 }
@@ -4949,14 +4940,9 @@ static int vmx_interrupt_allowed(struct kvm_vcpu *vcpu)
 static int vmx_set_tss_addr(struct kvm *kvm, unsigned int addr)
 {
 	int ret;
-	struct kvm_userspace_memory_region tss_mem = {
-		.slot = TSS_PRIVATE_MEMSLOT,
-		.guest_phys_addr = addr,
-		.memory_size = PAGE_SIZE * 3,
-		.flags = 0,
-	};
 
-	ret = x86_set_memory_region(kvm, &tss_mem);
+	ret = x86_set_memory_region(kvm, TSS_PRIVATE_MEMSLOT, addr,
+				    PAGE_SIZE * 3);
 	if (ret)
 		return ret;
 	kvm->arch.tss_addr = addr;
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 92511d4b7236..9a9a19830321 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -6453,6 +6453,12 @@ static inline int vcpu_block(struct kvm *kvm, struct kvm_vcpu *vcpu)
 	return 1;
 }
 
+static inline bool kvm_vcpu_running(struct kvm_vcpu *vcpu)
+{
+	return (vcpu->arch.mp_state == KVM_MP_STATE_RUNNABLE &&
+		!vcpu->arch.apf.halted);
+}
+
 static int vcpu_run(struct kvm_vcpu *vcpu)
 {
 	int r;
@@ -6461,8 +6467,7 @@ static int vcpu_run(struct kvm_vcpu *vcpu)
 	vcpu->srcu_idx = srcu_read_lock(&kvm->srcu);
 
 	for (;;) {
-		if (vcpu->arch.mp_state == KVM_MP_STATE_RUNNABLE &&
-		    !vcpu->arch.apf.halted)
+		if (kvm_vcpu_running(vcpu))
 			r = vcpu_enter_guest(vcpu);
 		else
 			r = vcpu_block(kvm, vcpu);
@@ -7474,34 +7479,66 @@ void kvm_arch_sync_events(struct kvm *kvm)
 	kvm_free_pit(kvm);
 }
 
-int __x86_set_memory_region(struct kvm *kvm,
-			    const struct kvm_userspace_memory_region *mem)
+int __x86_set_memory_region(struct kvm *kvm, int id, gpa_t gpa, u32 size)
 {
 	int i, r;
+	unsigned long hva;
+	struct kvm_memslots *slots = kvm_memslots(kvm);
+	struct kvm_memory_slot *slot, old;
 
 	/* Called with kvm->slots_lock held.  */
-	BUG_ON(mem->slot >= KVM_MEM_SLOTS_NUM);
+	if (WARN_ON(id >= KVM_MEM_SLOTS_NUM))
+		return -EINVAL;
+
+	slot = id_to_memslot(slots, id);
+	if (size) {
+		if (WARN_ON(slot->npages))
+			return -EEXIST;
+
+		/*
+		 * MAP_SHARED to prevent internal slot pages from being moved
+		 * by fork()/COW.
+		 */
+		hva = vm_mmap(NULL, 0, size, PROT_READ | PROT_WRITE,
+			      MAP_SHARED | MAP_ANONYMOUS, 0);
+		if (IS_ERR((void *)hva))
+			return PTR_ERR((void *)hva);
+	} else {
+		if (!slot->npages)
+			return 0;
 
+		hva = 0;
+	}
+
+	old = *slot;
 	for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++) {
-		struct kvm_userspace_memory_region m = *mem;
+		struct kvm_userspace_memory_region m;
 
-		m.slot |= i << 16;
+		m.slot = id | (i << 16);
+		m.flags = 0;
+		m.guest_phys_addr = gpa;
+		m.userspace_addr = hva;
+		m.memory_size = size;
 		r = __kvm_set_memory_region(kvm, &m);
 		if (r < 0)
 			return r;
 	}
 
+	if (!size) {
+		r = vm_munmap(old.userspace_addr, old.npages * PAGE_SIZE);
+		WARN_ON(r < 0);
+	}
+
 	return 0;
 }
 EXPORT_SYMBOL_GPL(__x86_set_memory_region);
 
-int x86_set_memory_region(struct kvm *kvm,
-			  const struct kvm_userspace_memory_region *mem)
+int x86_set_memory_region(struct kvm *kvm, int id, gpa_t gpa, u32 size)
 {
 	int r;
 
 	mutex_lock(&kvm->slots_lock);
-	r = __x86_set_memory_region(kvm, mem);
+	r = __x86_set_memory_region(kvm, id, gpa, size);
 	mutex_unlock(&kvm->slots_lock);
 
 	return r;
@@ -7516,16 +7553,9 @@ void kvm_arch_destroy_vm(struct kvm *kvm)
 		 * unless the the memory map has changed due to process exit
 		 * or fd copying.
 		 */
-		struct kvm_userspace_memory_region mem;
-		memset(&mem, 0, sizeof(mem));
-		mem.slot = APIC_ACCESS_PAGE_PRIVATE_MEMSLOT;
-		x86_set_memory_region(kvm, &mem);
-
-		mem.slot = IDENTITY_PAGETABLE_PRIVATE_MEMSLOT;
-		x86_set_memory_region(kvm, &mem);
-
-		mem.slot = TSS_PRIVATE_MEMSLOT;
-		x86_set_memory_region(kvm, &mem);
+		x86_set_memory_region(kvm, APIC_ACCESS_PAGE_PRIVATE_MEMSLOT, 0, 0);
+		x86_set_memory_region(kvm, IDENTITY_PAGETABLE_PRIVATE_MEMSLOT, 0, 0);
+		x86_set_memory_region(kvm, TSS_PRIVATE_MEMSLOT, 0, 0);
 	}
 	kvm_iommu_unmap_guest(kvm);
 	kfree(kvm->arch.vpic);
@@ -7628,27 +7658,6 @@ int kvm_arch_prepare_memory_region(struct kvm *kvm,
 				const struct kvm_userspace_memory_region *mem,
 				enum kvm_mr_change change)
 {
-	/*
-	 * Only private memory slots need to be mapped here since
-	 * KVM_SET_MEMORY_REGION ioctl is no longer supported.
-	 */
-	if ((memslot->id >= KVM_USER_MEM_SLOTS) && (change == KVM_MR_CREATE)) {
-		unsigned long userspace_addr;
-
-		/*
-		 * MAP_SHARED to prevent internal slot pages from being moved
-		 * by fork()/COW.
-		 */
-		userspace_addr = vm_mmap(NULL, 0, memslot->npages * PAGE_SIZE,
-					 PROT_READ | PROT_WRITE,
-					 MAP_SHARED | MAP_ANONYMOUS, 0);
-
-		if (IS_ERR((void *)userspace_addr))
-			return PTR_ERR((void *)userspace_addr);
-
-		memslot->userspace_addr = userspace_addr;
-	}
-
 	return 0;
 }
 
@@ -7710,17 +7719,6 @@ void kvm_arch_commit_memory_region(struct kvm *kvm,
 {
 	int nr_mmu_pages = 0;
 
-	if (change == KVM_MR_DELETE && old->id >= KVM_USER_MEM_SLOTS) {
-		int ret;
-
-		ret = vm_munmap(old->userspace_addr,
-				old->npages * PAGE_SIZE);
-		if (ret < 0)
-			printk(KERN_WARNING
-			       "kvm_vm_ioctl_set_memory_region: "
-			       "failed to munmap memory\n");
-	}
-
 	if (!kvm->arch.n_requested_mmu_pages)
 		nr_mmu_pages = kvm_mmu_calculate_mmu_pages(kvm);
 
@@ -7769,19 +7767,36 @@ void kvm_arch_flush_shadow_memslot(struct kvm *kvm,
 	kvm_mmu_invalidate_zap_all_pages(kvm);
 }
 
+static inline bool kvm_vcpu_has_events(struct kvm_vcpu *vcpu)
+{
+	if (!list_empty_careful(&vcpu->async_pf.done))
+		return true;
+
+	if (kvm_apic_has_events(vcpu))
+		return true;
+
+	if (vcpu->arch.pv.pv_unhalted)
+		return true;
+
+	if (atomic_read(&vcpu->arch.nmi_queued))
+		return true;
+
+	if (test_bit(KVM_REQ_SMI, &vcpu->requests))
+		return true;
+
+	if (kvm_arch_interrupt_allowed(vcpu) &&
+	    kvm_cpu_has_interrupt(vcpu))
+		return true;
+
+	return false;
+}
+
 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)
-		|| kvm_apic_has_events(vcpu)
-		|| vcpu->arch.pv.pv_unhalted
-		|| atomic_read(&vcpu->arch.nmi_queued) ||
-		(kvm_arch_interrupt_allowed(vcpu) &&
-		 kvm_cpu_has_interrupt(vcpu));
+	return kvm_vcpu_running(vcpu) || kvm_vcpu_has_events(vcpu);
 }
 
 int kvm_arch_vcpu_should_kick(struct kvm_vcpu *vcpu)
diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c
index 30d12afe52ed..993b7a71386d 100644
--- a/arch/x86/xen/enlighten.c
+++ b/arch/x86/xen/enlighten.c
@@ -33,6 +33,10 @@
 #include <linux/memblock.h>
 #include <linux/edd.h>
 
+#ifdef CONFIG_KEXEC_CORE
+#include <linux/kexec.h>
+#endif
+
 #include <xen/xen.h>
 #include <xen/events.h>
 #include <xen/interface/xen.h>
@@ -1077,6 +1081,7 @@ static int xen_write_msr_safe(unsigned int msr, unsigned low, unsigned high)
 		/* Fast syscall setup is all done in hypercalls, so
 		   these are all ignored.  Stub them out here to stop
 		   Xen console noise. */
+		break;
 
 	default:
 		if (!pmu_msr_write(msr, low, high, &ret))
@@ -1807,6 +1812,21 @@ static struct notifier_block xen_hvm_cpu_notifier = {
 	.notifier_call	= xen_hvm_cpu_notify,
 };
 
+#ifdef CONFIG_KEXEC_CORE
+static void xen_hvm_shutdown(void)
+{
+	native_machine_shutdown();
+	if (kexec_in_progress)
+		xen_reboot(SHUTDOWN_soft_reset);
+}
+
+static void xen_hvm_crash_shutdown(struct pt_regs *regs)
+{
+	native_machine_crash_shutdown(regs);
+	xen_reboot(SHUTDOWN_soft_reset);
+}
+#endif
+
 static void __init xen_hvm_guest_init(void)
 {
 	if (xen_pv_domain())
@@ -1826,6 +1846,10 @@ static void __init xen_hvm_guest_init(void)
 	x86_init.irqs.intr_init = xen_init_IRQ;
 	xen_hvm_init_time_ops();
 	xen_hvm_init_mmu_ops();
+#ifdef CONFIG_KEXEC_CORE
+	machine_ops.shutdown = xen_hvm_shutdown;
+	machine_ops.crash_shutdown = xen_hvm_crash_shutdown;
+#endif
 }
 #endif
 
diff --git a/arch/x86/xen/p2m.c b/arch/x86/xen/p2m.c
index bfc08b13044b..660b3cfef234 100644
--- a/arch/x86/xen/p2m.c
+++ b/arch/x86/xen/p2m.c
@@ -112,6 +112,15 @@ static unsigned long *p2m_identity;
 static pte_t *p2m_missing_pte;
 static pte_t *p2m_identity_pte;
 
+/*
+ * Hint at last populated PFN.
+ *
+ * Used to set HYPERVISOR_shared_info->arch.max_pfn so the toolstack
+ * can avoid scanning the whole P2M (which may be sized to account for
+ * hotplugged memory).
+ */
+static unsigned long xen_p2m_last_pfn;
+
 static inline unsigned p2m_top_index(unsigned long pfn)
 {
 	BUG_ON(pfn >= MAX_P2M_PFN);
@@ -270,7 +279,7 @@ void xen_setup_mfn_list_list(void)
 	else
 		HYPERVISOR_shared_info->arch.pfn_to_mfn_frame_list_list =
 			virt_to_mfn(p2m_top_mfn);
-	HYPERVISOR_shared_info->arch.max_pfn = xen_max_p2m_pfn;
+	HYPERVISOR_shared_info->arch.max_pfn = xen_p2m_last_pfn;
 	HYPERVISOR_shared_info->arch.p2m_generation = 0;
 	HYPERVISOR_shared_info->arch.p2m_vaddr = (unsigned long)xen_p2m_addr;
 	HYPERVISOR_shared_info->arch.p2m_cr3 =
@@ -406,6 +415,8 @@ void __init xen_vmalloc_p2m_tree(void)
 	static struct vm_struct vm;
 	unsigned long p2m_limit;
 
+	xen_p2m_last_pfn = xen_max_p2m_pfn;
+
 	p2m_limit = (phys_addr_t)P2M_LIMIT * 1024 * 1024 * 1024 / PAGE_SIZE;
 	vm.flags = VM_ALLOC;
 	vm.size = ALIGN(sizeof(unsigned long) * max(xen_max_p2m_pfn, p2m_limit),
@@ -608,6 +619,12 @@ static bool alloc_p2m(unsigned long pfn)
 			free_p2m_page(p2m);
 	}
 
+	/* Expanded the p2m? */
+	if (pfn > xen_p2m_last_pfn) {
+		xen_p2m_last_pfn = pfn;
+		HYPERVISOR_shared_info->arch.max_pfn = xen_p2m_last_pfn;
+	}
+
 	return true;
 }
 
diff --git a/arch/x86/xen/setup.c b/arch/x86/xen/setup.c
index f5ef6746d47a..1c30e4ab1022 100644
--- a/arch/x86/xen/setup.c
+++ b/arch/x86/xen/setup.c
@@ -548,7 +548,7 @@ static unsigned long __init xen_get_max_pages(void)
 {
 	unsigned long max_pages, limit;
 	domid_t domid = DOMID_SELF;
-	int ret;
+	long ret;
 
 	limit = xen_get_pages_limit();
 	max_pages = limit;
@@ -798,7 +798,7 @@ char * __init xen_memory_setup(void)
 		xen_ignore_unusable();
 
 	/* Make sure the Xen-supplied memory map is well-ordered. */
-	sanitize_e820_map(xen_e820_map, xen_e820_map_entries,
+	sanitize_e820_map(xen_e820_map, ARRAY_SIZE(xen_e820_map),
 			  &xen_e820_map_entries);
 
 	max_pages = xen_get_max_pages();