18 files changed, 132 insertions, 66 deletions

diff --git a/arch/x86/kernel/acpi/wakeup_32.S b/arch/x86/kernel/acpi/wakeup_32.S
index 665c6b7d2ea9..0c26b1b44e51 100644
--- a/arch/x86/kernel/acpi/wakeup_32.S
+++ b/arch/x86/kernel/acpi/wakeup_32.S
@@ -12,11 +12,13 @@ ENTRY(wakeup_pmode_return)
 wakeup_pmode_return:
 	movw	$__KERNEL_DS, %ax
 	movw	%ax, %ss
-	movw	%ax, %ds
-	movw	%ax, %es
 	movw	%ax, %fs
 	movw	%ax, %gs
 
+	movw	$__USER_DS, %ax
+	movw	%ax, %ds
+	movw	%ax, %es
+
 	# reload the gdt, as we need the full 32 bit address
 	lidt	saved_idt
 	lldt	saved_ldt
diff --git a/arch/x86/kernel/bootflag.c b/arch/x86/kernel/bootflag.c
index 5de7f4c56971..52c8e3c7789d 100644
--- a/arch/x86/kernel/bootflag.c
+++ b/arch/x86/kernel/bootflag.c
@@ -98,4 +98,4 @@ static int __init sbf_init(void)
 
 	return 0;
 }
-module_init(sbf_init);
+arch_initcall(sbf_init);
diff --git a/arch/x86/kernel/check.c b/arch/x86/kernel/check.c
index 83a7995625a6..58118e207a69 100644
--- a/arch/x86/kernel/check.c
+++ b/arch/x86/kernel/check.c
@@ -91,7 +91,8 @@ void __init setup_bios_corruption_check(void)
 
 	corruption_check_size = round_up(corruption_check_size, PAGE_SIZE);
 
-	for_each_free_mem_range(i, NUMA_NO_NODE, &start, &end, NULL) {
+	for_each_free_mem_range(i, NUMA_NO_NODE, MEMBLOCK_NONE, &start, &end,
+				NULL) {
 		start = clamp_t(phys_addr_t, round_up(start, PAGE_SIZE),
 				PAGE_SIZE, corruption_check_size);
 		end = clamp_t(phys_addr_t, round_down(end, PAGE_SIZE),
diff --git a/arch/x86/kernel/cpu/perf_event_intel_bts.c b/arch/x86/kernel/cpu/perf_event_intel_bts.c
index 7795f3f8b1d5..43dd672d788b 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_bts.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_bts.c
@@ -530,5 +530,4 @@ static __init int bts_init(void)
 
 	return perf_pmu_register(&bts_pmu, "intel_bts", -1);
 }
-
-module_init(bts_init);
+arch_initcall(bts_init);
diff --git a/arch/x86/kernel/cpu/perf_event_intel_pt.c b/arch/x86/kernel/cpu/perf_event_intel_pt.c
index 159887c3a89d..183de719628d 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_pt.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_pt.c
@@ -1106,5 +1106,4 @@ static __init int pt_init(void)
 
 	return ret;
 }
-
-module_init(pt_init);
+arch_initcall(pt_init);
diff --git a/arch/x86/kernel/devicetree.c b/arch/x86/kernel/devicetree.c
index 5ee771859b6f..1f4acd68b98b 100644
--- a/arch/x86/kernel/devicetree.c
+++ b/arch/x86/kernel/devicetree.c
@@ -65,7 +65,7 @@ static int __init add_bus_probe(void)
 
 	return of_platform_bus_probe(NULL, ce4100_ids, NULL);
 }
-module_init(add_bus_probe);
+device_initcall(add_bus_probe);
 
 #ifdef CONFIG_PCI
 struct device_node *pcibios_get_phb_of_node(struct pci_bus *bus)
diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c
index e2ce85db2283..a102564d08eb 100644
--- a/arch/x86/kernel/e820.c
+++ b/arch/x86/kernel/e820.c
@@ -149,6 +149,7 @@ static void __init e820_print_type(u32 type)
 	case E820_UNUSABLE:
 		printk(KERN_CONT "unusable");
 		break;
+	case E820_PMEM:
 	case E820_PRAM:
 		printk(KERN_CONT "persistent (type %u)", type);
 		break;
@@ -918,11 +919,32 @@ static inline const char *e820_type_to_string(int e820_type)
 	case E820_ACPI:	return "ACPI Tables";
 	case E820_NVS:	return "ACPI Non-volatile Storage";
 	case E820_UNUSABLE:	return "Unusable memory";
-	case E820_PRAM: return "Persistent RAM";
+	case E820_PRAM: return "Persistent Memory (legacy)";
+	case E820_PMEM: return "Persistent Memory";
 	default:	return "reserved";
 	}
 }
 
+static bool do_mark_busy(u32 type, struct resource *res)
+{
+	/* this is the legacy bios/dos rom-shadow + mmio region */
+	if (res->start < (1ULL<<20))
+		return true;
+
+	/*
+	 * Treat persistent memory like device memory, i.e. reserve it
+	 * for exclusive use of a driver
+	 */
+	switch (type) {
+	case E820_RESERVED:
+	case E820_PRAM:
+	case E820_PMEM:
+		return false;
+	default:
+		return true;
+	}
+}
+
 /*
  * Mark e820 reserved areas as busy for the resource manager.
  */
@@ -952,9 +974,7 @@ void __init e820_reserve_resources(void)
 		 * pci device BAR resource and insert them later in
 		 * pcibios_resource_survey()
 		 */
-		if (((e820.map[i].type != E820_RESERVED) &&
-		     (e820.map[i].type != E820_PRAM)) ||
-		     res->start < (1ULL<<20)) {
+		if (do_mark_busy(e820.map[i].type, res)) {
 			res->flags |= IORESOURCE_BUSY;
 			insert_resource(&iomem_resource, res);
 		}
@@ -1123,7 +1143,8 @@ void __init memblock_find_dma_reserve(void)
 		nr_pages += end_pfn - start_pfn;
 	}
 
-	for_each_free_mem_range(u, NUMA_NO_NODE, &start, &end, NULL) {
+	for_each_free_mem_range(u, NUMA_NO_NODE, MEMBLOCK_NONE, &start, &end,
+				NULL) {
 		start_pfn = min_t(unsigned long, PFN_UP(start), MAX_DMA_PFN);
 		end_pfn = min_t(unsigned long, PFN_DOWN(end), MAX_DMA_PFN);
 		if (start_pfn < end_pfn)
diff --git a/arch/x86/kernel/early-quirks.c b/arch/x86/kernel/early-quirks.c
index 5cb9a4d6f623..9f9cc682e561 100644
--- a/arch/x86/kernel/early-quirks.c
+++ b/arch/x86/kernel/early-quirks.c
@@ -546,6 +546,7 @@ static const struct pci_device_id intel_stolen_ids[] __initconst = {
 	INTEL_BDW_D_IDS(&gen8_stolen_funcs),
 	INTEL_CHV_IDS(&chv_stolen_funcs),
 	INTEL_SKL_IDS(&gen9_stolen_funcs),
+	INTEL_BXT_IDS(&gen9_stolen_funcs),
 };
 
 static void __init intel_graphics_stolen(int num, int slot, int func)
diff --git a/arch/x86/kernel/kexec-bzimage64.c b/arch/x86/kernel/kexec-bzimage64.c
index ca05f86481aa..ca83f7ac388b 100644
--- a/arch/x86/kernel/kexec-bzimage64.c
+++ b/arch/x86/kernel/kexec-bzimage64.c
@@ -72,15 +72,16 @@ static int setup_cmdline(struct kimage *image, struct boot_params *params,
 			 unsigned long cmdline_len)
 {
 	char *cmdline_ptr = ((char *)params) + cmdline_offset;
-	unsigned long cmdline_ptr_phys, len;
+	unsigned long cmdline_ptr_phys, len = 0;
 	uint32_t cmdline_low_32, cmdline_ext_32;
 
-	memcpy(cmdline_ptr, cmdline, cmdline_len);
 	if (image->type == KEXEC_TYPE_CRASH) {
-		len = sprintf(cmdline_ptr + cmdline_len - 1,
-			" elfcorehdr=0x%lx", image->arch.elf_load_addr);
-		cmdline_len += len;
+		len = sprintf(cmdline_ptr,
+			"elfcorehdr=0x%lx ", image->arch.elf_load_addr);
 	}
+	memcpy(cmdline_ptr + len, cmdline, cmdline_len);
+	cmdline_len += len;
+
 	cmdline_ptr[cmdline_len - 1] = '\0';
 
 	pr_debug("Final command line is: %s\n", cmdline_ptr);
diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c
index 1681504e44a4..47190bd399e7 100644
--- a/arch/x86/kernel/kvm.c
+++ b/arch/x86/kernel/kvm.c
@@ -331,7 +331,7 @@ static void kvm_guest_apic_eoi_write(u32 reg, u32 val)
 	apic_write(APIC_EOI, APIC_EOI_ACK);
 }
 
-void kvm_guest_cpu_init(void)
+static void kvm_guest_cpu_init(void)
 {
 	if (!kvm_para_available())
 		return;
@@ -688,7 +688,7 @@ static inline void spin_time_accum_blocked(u64 start)
 static struct dentry *d_spin_debug;
 static struct dentry *d_kvm_debug;
 
-struct dentry *kvm_init_debugfs(void)
+static struct dentry *kvm_init_debugfs(void)
 {
 	d_kvm_debug = debugfs_create_dir("kvm-guest", NULL);
 	if (!d_kvm_debug)
diff --git a/arch/x86/kernel/kvmclock.c b/arch/x86/kernel/kvmclock.c
index 42caaef897c8..49487b488061 100644
--- a/arch/x86/kernel/kvmclock.c
+++ b/arch/x86/kernel/kvmclock.c
@@ -24,6 +24,7 @@
 #include <linux/percpu.h>
 #include <linux/hardirq.h>
 #include <linux/memblock.h>
+#include <linux/sched.h>
 
 #include <asm/x86_init.h>
 #include <asm/reboot.h>
@@ -217,8 +218,10 @@ static void kvm_shutdown(void)
 
 void __init kvmclock_init(void)
 {
+	struct pvclock_vcpu_time_info *vcpu_time;
 	unsigned long mem;
-	int size;
+	int size, cpu;
+	u8 flags;
 
 	size = PAGE_ALIGN(sizeof(struct pvclock_vsyscall_time_info)*NR_CPUS);
 
@@ -264,7 +267,14 @@ void __init kvmclock_init(void)
 	pv_info.name = "KVM";
 
 	if (kvm_para_has_feature(KVM_FEATURE_CLOCKSOURCE_STABLE_BIT))
-		pvclock_set_flags(PVCLOCK_TSC_STABLE_BIT);
+		pvclock_set_flags(~0);
+
+	cpu = get_cpu();
+	vcpu_time = &hv_clock[cpu].pvti;
+	flags = pvclock_read_flags(vcpu_time);
+	if (flags & PVCLOCK_COUNTS_FROM_ZERO)
+		set_sched_clock_stable();
+	put_cpu();
 }
 
 int __init kvm_setup_vsyscall_timeinfo(void)
diff --git a/arch/x86/kernel/machine_kexec_64.c b/arch/x86/kernel/machine_kexec_64.c
index 11546b462fa6..819ab3f9c9c7 100644
--- a/arch/x86/kernel/machine_kexec_64.c
+++ b/arch/x86/kernel/machine_kexec_64.c
@@ -26,6 +26,7 @@
 #include <asm/io_apic.h>
 #include <asm/debugreg.h>
 #include <asm/kexec-bzimage64.h>
+#include <asm/setup.h>
 
 #ifdef CONFIG_KEXEC_FILE
 static struct kexec_file_ops *kexec_file_loaders[] = {
@@ -335,7 +336,7 @@ void arch_crash_save_vmcoreinfo(void)
 	VMCOREINFO_LENGTH(node_data, MAX_NUMNODES);
 #endif
 	vmcoreinfo_append_str("KERNELOFFSET=%lx\n",
-			      (unsigned long)&_text - __START_KERNEL);
+			      kaslr_offset());
 }
 
 /* arch-dependent functionality related to kexec file-based syscall */
diff --git a/arch/x86/kernel/pmem.c b/arch/x86/kernel/pmem.c
index 3420c874ddc5..64f90f53bb85 100644
--- a/arch/x86/kernel/pmem.c
+++ b/arch/x86/kernel/pmem.c
@@ -1,53 +1,82 @@
 /*
  * Copyright (c) 2015, Christoph Hellwig.
+ * Copyright (c) 2015, Intel Corporation.
  */
-#include <linux/memblock.h>
 #include <linux/platform_device.h>
-#include <linux/slab.h>
+#include <linux/libnvdimm.h>
+#include <linux/module.h>
 #include <asm/e820.h>
-#include <asm/page_types.h>
-#include <asm/setup.h>
 
-static __init void register_pmem_device(struct resource *res)
+static void e820_pmem_release(struct device *dev)
 {
-	struct platform_device *pdev;
-	int error;
+	struct nvdimm_bus *nvdimm_bus = dev->platform_data;
 
-	pdev = platform_device_alloc("pmem", PLATFORM_DEVID_AUTO);
-	if (!pdev)
-		return;
+	if (nvdimm_bus)
+		nvdimm_bus_unregister(nvdimm_bus);
+}
 
-	error = platform_device_add_resources(pdev, res, 1);
-	if (error)
-		goto out_put_pdev;
+static struct platform_device e820_pmem = {
+	.name = "e820_pmem",
+	.id = -1,
+	.dev = {
+		.release = e820_pmem_release,
+	},
+};
 
-	error = platform_device_add(pdev);
-	if (error)
-		goto out_put_pdev;
-	return;
+static const struct attribute_group *e820_pmem_attribute_groups[] = {
+	&nvdimm_bus_attribute_group,
+	NULL,
+};
 
-out_put_pdev:
-	dev_warn(&pdev->dev, "failed to add 'pmem' (persistent memory) device!\n");
-	platform_device_put(pdev);
-}
+static const struct attribute_group *e820_pmem_region_attribute_groups[] = {
+	&nd_region_attribute_group,
+	&nd_device_attribute_group,
+	NULL,
+};
 
-static __init int register_pmem_devices(void)
+static __init int register_e820_pmem(void)
 {
-	int i;
+	static struct nvdimm_bus_descriptor nd_desc;
+	struct device *dev = &e820_pmem.dev;
+	struct nvdimm_bus *nvdimm_bus;
+	int rc, i;
+
+	rc = platform_device_register(&e820_pmem);
+	if (rc)
+		return rc;
+
+	nd_desc.attr_groups = e820_pmem_attribute_groups;
+	nd_desc.provider_name = "e820";
+	nvdimm_bus = nvdimm_bus_register(dev, &nd_desc);
+	if (!nvdimm_bus)
+		goto err;
+	dev->platform_data = nvdimm_bus;
 
 	for (i = 0; i < e820.nr_map; i++) {
 		struct e820entry *ei = &e820.map[i];
+		struct resource res = {
+			.flags	= IORESOURCE_MEM,
+			.start	= ei->addr,
+			.end	= ei->addr + ei->size - 1,
+		};
+		struct nd_region_desc ndr_desc;
+
+		if (ei->type != E820_PRAM)
+			continue;
 
-		if (ei->type == E820_PRAM) {
-			struct resource res = {
-				.flags	= IORESOURCE_MEM,
-				.start	= ei->addr,
-				.end	= ei->addr + ei->size - 1,
-			};
-			register_pmem_device(&res);
-		}
+		memset(&ndr_desc, 0, sizeof(ndr_desc));
+		ndr_desc.res = &res;
+		ndr_desc.attr_groups = e820_pmem_region_attribute_groups;
+		ndr_desc.numa_node = NUMA_NO_NODE;
+		if (!nvdimm_pmem_region_create(nvdimm_bus, &ndr_desc))
+			goto err;
 	}
 
 	return 0;
+
+ err:
+	dev_err(dev, "failed to register legacy persistent memory ranges\n");
+	platform_device_unregister(&e820_pmem);
+	return -ENXIO;
 }
-device_initcall(register_pmem_devices);
+device_initcall(register_e820_pmem);
diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c
index c09c99ccf3e3..f73c962fe636 100644
--- a/arch/x86/kernel/process_32.c
+++ b/arch/x86/kernel/process_32.c
@@ -128,8 +128,8 @@ void release_thread(struct task_struct *dead_task)
 	release_vm86_irqs(dead_task);
 }
 
-int copy_thread(unsigned long clone_flags, unsigned long sp,
-	unsigned long arg, struct task_struct *p)
+int copy_thread_tls(unsigned long clone_flags, unsigned long sp,
+	unsigned long arg, struct task_struct *p, unsigned long tls)
 {
 	struct pt_regs *childregs = task_pt_regs(p);
 	struct task_struct *tsk;
@@ -184,7 +184,7 @@ int copy_thread(unsigned long clone_flags, unsigned long sp,
 	 */
 	if (clone_flags & CLONE_SETTLS)
 		err = do_set_thread_area(p, -1,
-			(struct user_desc __user *)childregs->si, 0);
+			(struct user_desc __user *)tls, 0);
 
 	if (err && p->thread.io_bitmap_ptr) {
 		kfree(p->thread.io_bitmap_ptr);
diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c
index 843f92e4c711..71d7849a07f7 100644
--- a/arch/x86/kernel/process_64.c
+++ b/arch/x86/kernel/process_64.c
@@ -150,8 +150,8 @@ static inline u32 read_32bit_tls(struct task_struct *t, int tls)
 	return get_desc_base(&t->thread.tls_array[tls]);
 }
 
-int copy_thread(unsigned long clone_flags, unsigned long sp,
-		unsigned long arg, struct task_struct *p)
+int copy_thread_tls(unsigned long clone_flags, unsigned long sp,
+		unsigned long arg, struct task_struct *p, unsigned long tls)
 {
 	int err;
 	struct pt_regs *childregs;
@@ -207,10 +207,10 @@ int copy_thread(unsigned long clone_flags, unsigned long sp,
 #ifdef CONFIG_IA32_EMULATION
 		if (is_ia32_task())
 			err = do_set_thread_area(p, -1,
-				(struct user_desc __user *)childregs->si, 0);
+				(struct user_desc __user *)tls, 0);
 		else
 #endif
-			err = do_arch_prctl(p, ARCH_SET_FS, childregs->r8);
+			err = do_arch_prctl(p, ARCH_SET_FS, tls);
 		if (err)
 			goto out;
 	}
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index 265a6fdea8b7..d3b95b89e9b2 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -836,7 +836,7 @@ dump_kernel_offset(struct notifier_block *self, unsigned long v, void *p)
 {
 	if (kaslr_enabled()) {
 		pr_emerg("Kernel Offset: 0x%lx from 0x%lx (relocation range: 0x%lx-0x%lx)\n",
-			 (unsigned long)&_text - __START_KERNEL,
+			 kaslr_offset(),
 			 __START_KERNEL,
 			 __START_KERNEL_map,
 			 MODULES_VADDR-1);
@@ -1105,6 +1105,9 @@ void __init setup_arch(char **cmdline_p)
 	memblock_set_current_limit(ISA_END_ADDRESS);
 	memblock_x86_fill();
 
+	if (efi_enabled(EFI_BOOT))
+		efi_find_mirror();
+
 	/*
 	 * The EFI specification says that boot service code won't be called
 	 * after ExitBootServices(). This is, in fact, a lie.
diff --git a/arch/x86/kernel/vsmp_64.c b/arch/x86/kernel/vsmp_64.c
index ee22c1d93ae5..b034b1b14b9c 100644
--- a/arch/x86/kernel/vsmp_64.c
+++ b/arch/x86/kernel/vsmp_64.c
@@ -72,7 +72,7 @@ asmlinkage __visible void vsmp_irq_enable(void)
 }
 PV_CALLEE_SAVE_REGS_THUNK(vsmp_irq_enable);
 
-static unsigned __init_or_module vsmp_patch(u8 type, u16 clobbers, void *ibuf,
+static unsigned __init vsmp_patch(u8 type, u16 clobbers, void *ibuf,
 				  unsigned long addr, unsigned len)
 {
 	switch (type) {
diff --git a/arch/x86/kernel/x86_init.c b/arch/x86/kernel/x86_init.c
index 3cee10abf01d..3839628d962e 100644
--- a/arch/x86/kernel/x86_init.c
+++ b/arch/x86/kernel/x86_init.c
@@ -11,7 +11,6 @@
 #include <asm/bios_ebda.h>
 #include <asm/paravirt.h>
 #include <asm/pci_x86.h>
-#include <asm/pci.h>
 #include <asm/mpspec.h>
 #include <asm/setup.h>
 #include <asm/apic.h>