Merge branch 'x86/mm' into x86/asm, to unify the two branches for simplicity

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

arch/x86/include/asm/desc.h

@@ -36,7 +36,7 @@ static inline void fill_ldt(struct desc_struct *desc, const struct user_desc *in
 
 extern struct desc_ptr idt_descr;
 extern gate_desc idt_table[];
-extern struct desc_ptr debug_idt_descr;
+extern const struct desc_ptr debug_idt_descr;
 extern gate_desc debug_idt_table[];
 
 struct gdt_page {

arch/x86/include/asm/fpu/xstate.h

@@ -45,7 +45,8 @@
 extern u64 xfeatures_mask;
 extern u64 xstate_fx_sw_bytes[USER_XSTATE_FX_SW_WORDS];
 
-extern void update_regset_xstate_info(unsigned int size, u64 xstate_mask);
+extern void __init update_regset_xstate_info(unsigned int size,
+					     u64 xstate_mask);
 
 void fpu__xstate_clear_all_cpu_caps(void);
 void *get_xsave_addr(struct xregs_state *xsave, int xstate);

arch/x86/include/asm/kaslr.h

@@ -6,6 +6,7 @@ unsigned long kaslr_get_random_long(const char *purpose);
 #ifdef CONFIG_RANDOMIZE_MEMORY
 extern unsigned long page_offset_base;
 extern unsigned long vmalloc_base;
+extern unsigned long vmemmap_base;
 
 void kernel_randomize_memory(void);
 #else

arch/x86/include/asm/pgtable_64_types.h

@@ -57,11 +57,13 @@ typedef struct { pteval_t pte; } pte_t;
 #define MAXMEM		_AC(__AC(1, UL) << MAX_PHYSMEM_BITS, UL)
 #define VMALLOC_SIZE_TB	_AC(32, UL)
 #define __VMALLOC_BASE	_AC(0xffffc90000000000, UL)
-#define VMEMMAP_START	_AC(0xffffea0000000000, UL)
+#define __VMEMMAP_BASE	_AC(0xffffea0000000000, UL)
 #ifdef CONFIG_RANDOMIZE_MEMORY
 #define VMALLOC_START	vmalloc_base
+#define VMEMMAP_START	vmemmap_base
 #else
 #define VMALLOC_START	__VMALLOC_BASE
+#define VMEMMAP_START	__VMEMMAP_BASE
 #endif /* CONFIG_RANDOMIZE_MEMORY */
 #define VMALLOC_END	(VMALLOC_START + _AC((VMALLOC_SIZE_TB << 40) - 1, UL))
 #define MODULES_VADDR    (__START_KERNEL_map + KERNEL_IMAGE_SIZE)

arch/x86/kernel/apic/apic_flat_64.c

@@ -25,7 +25,7 @@
 static struct apic apic_physflat;
 static struct apic apic_flat;
 
-struct apic __read_mostly *apic = &apic_flat;
+struct apic *apic __ro_after_init = &apic_flat;
 EXPORT_SYMBOL_GPL(apic);
 
 static int flat_acpi_madt_oem_check(char *oem_id, char *oem_table_id)
@@ -154,7 +154,7 @@ static int flat_probe(void)
 	return 1;
 }
 
-static struct apic apic_flat =  {
+static struct apic apic_flat __ro_after_init = {
 	.name				= "flat",
 	.probe				= flat_probe,
 	.acpi_madt_oem_check		= flat_acpi_madt_oem_check,
@@ -248,7 +248,7 @@ static int physflat_probe(void)
 	return 0;
 }
 
-static struct apic apic_physflat =  {
+static struct apic apic_physflat __ro_after_init = {
 
 	.name				= "physical flat",
 	.probe				= physflat_probe,

arch/x86/kernel/apic/apic_noop.c

@@ -108,7 +108,7 @@ static void noop_apic_write(u32 reg, u32 v)
 	WARN_ON_ONCE(boot_cpu_has(X86_FEATURE_APIC) && !disable_apic);
 }
 
-struct apic apic_noop = {
+struct apic apic_noop __ro_after_init = {
 	.name				= "noop",
 	.probe				= noop_probe,
 	.acpi_madt_oem_check		= NULL,

arch/x86/kernel/apic/bigsmp_32.c

@@ -142,7 +142,7 @@ static int probe_bigsmp(void)
 	return dmi_bigsmp;
 }
 
-static struct apic apic_bigsmp = {
+static struct apic apic_bigsmp __ro_after_init = {
 
 	.name				= "bigsmp",
 	.probe				= probe_bigsmp,

arch/x86/kernel/apic/msi.c

@@ -269,7 +269,7 @@ static void hpet_msi_write_msg(struct irq_data *data, struct msi_msg *msg)
 	hpet_msi_write(irq_data_get_irq_handler_data(data), msg);
 }
 
-static struct irq_chip hpet_msi_controller = {
+static struct irq_chip hpet_msi_controller __ro_after_init = {
 	.name = "HPET-MSI",
 	.irq_unmask = hpet_msi_unmask,
 	.irq_mask = hpet_msi_mask,

arch/x86/kernel/apic/probe_32.c

@@ -72,7 +72,7 @@ static int probe_default(void)
 	return 1;
 }
 
-static struct apic apic_default = {
+static struct apic apic_default __ro_after_init = {
 
 	.name				= "default",
 	.probe				= probe_default,
@@ -126,7 +126,7 @@ static struct apic apic_default = {
 
 apic_driver(apic_default);
 
-struct apic *apic = &apic_default;
+struct apic *apic __ro_after_init = &apic_default;
 EXPORT_SYMBOL_GPL(apic);
 
 static int cmdline_apic __initdata;

arch/x86/kernel/apic/x2apic_cluster.c

@@ -227,7 +227,7 @@ static void cluster_vector_allocation_domain(int cpu, struct cpumask *retmask,
 		cpumask_and(retmask, mask, per_cpu(cpus_in_cluster, cpu));
 }
 
-static struct apic apic_x2apic_cluster = {
+static struct apic apic_x2apic_cluster __ro_after_init = {
 
 	.name				= "cluster x2apic",
 	.probe				= x2apic_cluster_probe,

arch/x86/kernel/apic/x2apic_phys.c

@@ -98,7 +98,7 @@ static int x2apic_phys_probe(void)
 	return apic == &apic_x2apic_phys;
 }
 
-static struct apic apic_x2apic_phys = {
+static struct apic apic_x2apic_phys __ro_after_init = {
 
 	.name				= "physical x2apic",
 	.probe				= x2apic_phys_probe,

arch/x86/kernel/apic/x2apic_uv_x.c

@@ -560,7 +560,7 @@ static int uv_probe(void)
 	return apic == &apic_x2apic_uv_x;
 }
 
-static struct apic __refdata apic_x2apic_uv_x = {
+static struct apic apic_x2apic_uv_x __ro_after_init = {
 
 	.name				= "UV large system",
 	.probe				= uv_probe,

arch/x86/kernel/cpu/common.c

@@ -1265,9 +1265,14 @@ static __init int setup_disablecpuid(char *arg)
 __setup("clearcpuid=", setup_disablecpuid);
 
 #ifdef CONFIG_X86_64
-struct desc_ptr idt_descr = { NR_VECTORS * 16 - 1, (unsigned long) idt_table };
-struct desc_ptr debug_idt_descr = { NR_VECTORS * 16 - 1,
-				    (unsigned long) debug_idt_table };
+struct desc_ptr idt_descr __ro_after_init = {
+	.size = NR_VECTORS * 16 - 1,
+	.address = (unsigned long) idt_table,
+};
+const struct desc_ptr debug_idt_descr = {
+	.size = NR_VECTORS * 16 - 1,
+	.address = (unsigned long) debug_idt_table,
+};
 
 DEFINE_PER_CPU_FIRST(union irq_stack_union,
 		     irq_stack_union) __aligned(PAGE_SIZE) __visible;

arch/x86/kernel/cpu/mtrr/main.c

@@ -72,14 +72,14 @@ static DEFINE_MUTEX(mtrr_mutex);
 u64 size_or_mask, size_and_mask;
 static bool mtrr_aps_delayed_init;
 
-static const struct mtrr_ops *mtrr_ops[X86_VENDOR_NUM];
+static const struct mtrr_ops *mtrr_ops[X86_VENDOR_NUM] __ro_after_init;
 
 const struct mtrr_ops *mtrr_if;
 
 static void set_mtrr(unsigned int reg, unsigned long base,
 		     unsigned long size, mtrr_type type);
 
-void set_mtrr_ops(const struct mtrr_ops *ops)
+void __init set_mtrr_ops(const struct mtrr_ops *ops)
 {
 	if (ops->vendor && ops->vendor < X86_VENDOR_NUM)
 		mtrr_ops[ops->vendor] = ops;

arch/x86/kernel/cpu/mtrr/mtrr.h

@@ -54,7 +54,7 @@ void fill_mtrr_var_range(unsigned int index,
 bool get_mtrr_state(void);
 void mtrr_bp_pat_init(void);
 
-extern void set_mtrr_ops(const struct mtrr_ops *ops);
+extern void __init set_mtrr_ops(const struct mtrr_ops *ops);
 
 extern u64 size_or_mask, size_and_mask;
 extern const struct mtrr_ops *mtrr_if;

arch/x86/kernel/ksysfs.c

@@ -184,7 +184,7 @@ static ssize_t setup_data_data_read(struct file *fp,
 
 static struct kobj_attribute type_attr = __ATTR_RO(type);
 
-static struct bin_attribute data_attr = {
+static struct bin_attribute data_attr __ro_after_init = {
 	.attr = {
 		.name = "data",
 		.mode = S_IRUGO,

arch/x86/kernel/kvmclock.c

@@ -29,7 +29,7 @@
 #include <asm/x86_init.h>
 #include <asm/reboot.h>
 
-static int kvmclock = 1;
+static int kvmclock __ro_after_init = 1;
 static int msr_kvm_system_time = MSR_KVM_SYSTEM_TIME;
 static int msr_kvm_wall_clock = MSR_KVM_WALL_CLOCK;
 static cycle_t kvm_sched_clock_offset;

arch/x86/kernel/paravirt.c

@@ -389,7 +389,7 @@ NOKPROBE_SYMBOL(native_load_idt);
 #define PTE_IDENT	__PV_IS_CALLEE_SAVE(_paravirt_ident_64)
 #endif
 
-struct pv_mmu_ops pv_mmu_ops = {
+struct pv_mmu_ops pv_mmu_ops __ro_after_init = {
 
 	.read_cr2 = native_read_cr2,
 	.write_cr2 = native_write_cr2,

arch/x86/kernel/ptrace.c

@@ -1250,7 +1250,7 @@ long compat_arch_ptrace(struct task_struct *child, compat_long_t request,
 
 #ifdef CONFIG_X86_64
 
-static struct user_regset x86_64_regsets[] __read_mostly = {
+static struct user_regset x86_64_regsets[] __ro_after_init = {
 	[REGSET_GENERAL] = {
 		.core_note_type = NT_PRSTATUS,
 		.n = sizeof(struct user_regs_struct) / sizeof(long),
@@ -1291,7 +1291,7 @@ static const struct user_regset_view user_x86_64_view = {
 #endif	/* CONFIG_X86_64 */
 
 #if defined CONFIG_X86_32 || defined CONFIG_IA32_EMULATION
-static struct user_regset x86_32_regsets[] __read_mostly = {
+static struct user_regset x86_32_regsets[] __ro_after_init = {
 	[REGSET_GENERAL] = {
 		.core_note_type = NT_PRSTATUS,
 		.n = sizeof(struct user_regs_struct32) / sizeof(u32),
@@ -1344,7 +1344,7 @@ static const struct user_regset_view user_x86_32_view = {
  */
 u64 xstate_fx_sw_bytes[USER_XSTATE_FX_SW_WORDS];
 
-void update_regset_xstate_info(unsigned int size, u64 xstate_mask)
+void __init update_regset_xstate_info(unsigned int size, u64 xstate_mask)
 {
 #ifdef CONFIG_X86_64
 	x86_64_regsets[REGSET_XSTATE].n = size / sizeof(u64);

arch/x86/kernel/reboot.c

@@ -705,7 +705,7 @@ static void native_machine_power_off(void)
 	tboot_shutdown(TB_SHUTDOWN_HALT);
 }
 
-struct machine_ops machine_ops = {
+struct machine_ops machine_ops __ro_after_init = {
 	.power_off = native_machine_power_off,
 	.shutdown = native_machine_shutdown,
 	.emergency_restart = native_machine_emergency_restart,

arch/x86/kernel/setup.c

@@ -210,9 +210,9 @@ EXPORT_SYMBOL(boot_cpu_data);
 
 
 #if !defined(CONFIG_X86_PAE) || defined(CONFIG_X86_64)
-__visible unsigned long mmu_cr4_features;
+__visible unsigned long mmu_cr4_features __ro_after_init;
 #else
-__visible unsigned long mmu_cr4_features = X86_CR4_PAE;
+__visible unsigned long mmu_cr4_features __ro_after_init = X86_CR4_PAE;
 #endif
 
 /* Boot loader ID and version as integers, for the benefit of proc_dointvec */

arch/x86/kernel/setup_percpu.c

@@ -33,7 +33,7 @@ EXPORT_PER_CPU_SYMBOL(cpu_number);
 DEFINE_PER_CPU_READ_MOSTLY(unsigned long, this_cpu_off) = BOOT_PERCPU_OFFSET;
 EXPORT_PER_CPU_SYMBOL(this_cpu_off);
 
-unsigned long __per_cpu_offset[NR_CPUS] __read_mostly = {
+unsigned long __per_cpu_offset[NR_CPUS] __ro_after_init = {
 	[0 ... NR_CPUS-1] = BOOT_PERCPU_OFFSET,
 };
 EXPORT_SYMBOL(__per_cpu_offset);

arch/x86/kernel/x86_init.c

@@ -91,7 +91,7 @@ struct x86_cpuinit_ops x86_cpuinit = {
 static void default_nmi_init(void) { };
 static int default_i8042_detect(void) { return 1; };
 
-struct x86_platform_ops x86_platform = {
+struct x86_platform_ops x86_platform __ro_after_init = {
 	.calibrate_cpu			= native_calibrate_cpu,
 	.calibrate_tsc			= native_calibrate_tsc,
 	.get_wallclock			= mach_get_cmos_time,
@@ -108,7 +108,7 @@ struct x86_platform_ops x86_platform = {
 EXPORT_SYMBOL_GPL(x86_platform);
 
 #if defined(CONFIG_PCI_MSI)
-struct x86_msi_ops x86_msi = {
+struct x86_msi_ops x86_msi __ro_after_init = {
 	.setup_msi_irqs		= native_setup_msi_irqs,
 	.teardown_msi_irq	= native_teardown_msi_irq,
 	.teardown_msi_irqs	= default_teardown_msi_irqs,
@@ -137,7 +137,7 @@ void arch_restore_msi_irqs(struct pci_dev *dev)
 }
 #endif
 
-struct x86_io_apic_ops x86_io_apic_ops = {
+struct x86_io_apic_ops x86_io_apic_ops __ro_after_init = {
 	.read			= native_io_apic_read,
 	.disable		= native_disable_io_apic,
 };

arch/x86/kvm/svm.c

@@ -4961,7 +4961,7 @@ static inline void avic_post_state_restore(struct kvm_vcpu *vcpu)
 	avic_handle_ldr_update(vcpu);
 }
 
-static struct kvm_x86_ops svm_x86_ops = {
+static struct kvm_x86_ops svm_x86_ops __ro_after_init = {
 	.cpu_has_kvm_support = has_svm,
 	.disabled_by_bios = is_disabled,
 	.hardware_setup = svm_hardware_setup,

arch/x86/kvm/vmx.c

@@ -11175,7 +11175,7 @@ static void vmx_setup_mce(struct kvm_vcpu *vcpu)
 			~FEATURE_CONTROL_LMCE;
 }
 
-static struct kvm_x86_ops vmx_x86_ops = {
+static struct kvm_x86_ops vmx_x86_ops __ro_after_init = {
 	.cpu_has_kvm_support = cpu_has_kvm_support,
 	.disabled_by_bios = vmx_disabled_by_bios,
 	.hardware_setup = hardware_setup,

arch/x86/mm/kaslr.c

@@ -40,17 +40,26 @@
  * You need to add an if/def entry if you introduce a new memory region
  * compatible with KASLR. Your entry must be in logical order with memory
  * layout. For example, ESPFIX is before EFI because its virtual address is
- * before. You also need to add a BUILD_BUG_ON in kernel_randomize_memory to
+ * before. You also need to add a BUILD_BUG_ON() in kernel_randomize_memory() to
  * ensure that this order is correct and won't be changed.
  */
 static const unsigned long vaddr_start = __PAGE_OFFSET_BASE;
-static const unsigned long vaddr_end = VMEMMAP_START;
+
+#if defined(CONFIG_X86_ESPFIX64)
+static const unsigned long vaddr_end = ESPFIX_BASE_ADDR;
+#elif defined(CONFIG_EFI)
+static const unsigned long vaddr_end = EFI_VA_START;
+#else
+static const unsigned long vaddr_end = __START_KERNEL_map;
+#endif
 
 /* Default values */
 unsigned long page_offset_base = __PAGE_OFFSET_BASE;
 EXPORT_SYMBOL(page_offset_base);
 unsigned long vmalloc_base = __VMALLOC_BASE;
 EXPORT_SYMBOL(vmalloc_base);
+unsigned long vmemmap_base = __VMEMMAP_BASE;
+EXPORT_SYMBOL(vmemmap_base);
 
 /*
  * Memory regions randomized by KASLR (except modules that use a separate logic
@@ -63,6 +72,7 @@ static __initdata struct kaslr_memory_region {
 } kaslr_regions[] = {
 	{ &page_offset_base, 64/* Maximum */ },
 	{ &vmalloc_base, VMALLOC_SIZE_TB },
+	{ &vmemmap_base, 1 },
 };
 
 /* Get size in bytes used by the memory region */
@@ -89,6 +99,18 @@ void __init kernel_randomize_memory(void)
 	struct rnd_state rand_state;
 	unsigned long remain_entropy;
 
+	/*
+	 * All these BUILD_BUG_ON checks ensures the memory layout is
+	 * consistent with the vaddr_start/vaddr_end variables.
+	 */
+	BUILD_BUG_ON(vaddr_start >= vaddr_end);
+	BUILD_BUG_ON(config_enabled(CONFIG_X86_ESPFIX64) &&
+		     vaddr_end >= EFI_VA_START);
+	BUILD_BUG_ON((config_enabled(CONFIG_X86_ESPFIX64) ||
+		      config_enabled(CONFIG_EFI)) &&
+		     vaddr_end >= __START_KERNEL_map);
+	BUILD_BUG_ON(vaddr_end > __START_KERNEL_map);
+
 	if (!kaslr_memory_enabled())
 		return;
 

arch/x86/pci/pcbios.c

@@ -120,9 +120,12 @@ static unsigned long __init bios32_service(unsigned long service)
 static struct {
 	unsigned long address;
 	unsigned short segment;
-} pci_indirect = { 0, __KERNEL_CS };
+} pci_indirect __ro_after_init = {
+	.address = 0,
+	.segment = __KERNEL_CS,
+};
 
-static int pci_bios_present;
+static int pci_bios_present __ro_after_init;
 
 static int __init check_pcibios(void)
 {