diff options
Diffstat (limited to 'arch/x86/kernel/setup.c')
| -rw-r--r-- | arch/x86/kernel/setup.c | 340 |
1 files changed, 212 insertions, 128 deletions
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index 3e1e96efadfe..fb27be697128 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -7,10 +7,11 @@ */ #include <linux/acpi.h> #include <linux/console.h> +#include <linux/cpu.h> #include <linux/crash_dump.h> #include <linux/dma-map-ops.h> -#include <linux/dmi.h> #include <linux/efi.h> +#include <linux/hugetlb.h> #include <linux/ima.h> #include <linux/init_ohci1394_dma.h> #include <linux/initrd.h> @@ -18,24 +19,23 @@ #include <linux/memblock.h> #include <linux/panic_notifier.h> #include <linux/pci.h> +#include <linux/random.h> #include <linux/root_dev.h> -#include <linux/hugetlb.h> -#include <linux/tboot.h> -#include <linux/usb/xhci-dbgp.h> #include <linux/static_call.h> #include <linux/swiotlb.h> -#include <linux/random.h> +#include <linux/tboot.h> +#include <linux/usb/xhci-dbgp.h> +#include <linux/vmalloc.h> #include <uapi/linux/mount.h> #include <xen/xen.h> #include <asm/apic.h> -#include <asm/efi.h> -#include <asm/numa.h> #include <asm/bios_ebda.h> #include <asm/bugs.h> #include <asm/cacheinfo.h> +#include <asm/coco.h> #include <asm/cpu.h> #include <asm/efi.h> #include <asm/gart.h> @@ -46,15 +46,16 @@ #include <asm/mce.h> #include <asm/memtype.h> #include <asm/mtrr.h> -#include <asm/realmode.h> +#include <asm/nmi.h> +#include <asm/numa.h> #include <asm/olpc_ofw.h> #include <asm/pci-direct.h> #include <asm/prom.h> #include <asm/proto.h> +#include <asm/realmode.h> #include <asm/thermal.h> #include <asm/unwind.h> #include <asm/vsyscall.h> -#include <linux/vmalloc.h> /* * max_low_pfn_mapped: highest directly mapped pfn < 4 GB @@ -130,6 +131,7 @@ struct ist_info ist_info; struct cpuinfo_x86 boot_cpu_data __read_mostly; EXPORT_SYMBOL(boot_cpu_data); +SYM_PIC_ALIAS(boot_cpu_data); #if !defined(CONFIG_X86_PAE) || defined(CONFIG_X86_64) __visible unsigned long mmu_cr4_features __ro_after_init; @@ -145,6 +147,67 @@ static size_t ima_kexec_buffer_size; /* Boot loader ID and version as integers, for the benefit of proc_dointvec */ int bootloader_type, bootloader_version; +static const struct ctl_table x86_sysctl_table[] = { + { + .procname = "unknown_nmi_panic", + .data = &unknown_nmi_panic, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec, + }, + { + .procname = "panic_on_unrecovered_nmi", + .data = &panic_on_unrecovered_nmi, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec, + }, + { + .procname = "panic_on_io_nmi", + .data = &panic_on_io_nmi, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec, + }, + { + .procname = "bootloader_type", + .data = &bootloader_type, + .maxlen = sizeof(int), + .mode = 0444, + .proc_handler = proc_dointvec, + }, + { + .procname = "bootloader_version", + .data = &bootloader_version, + .maxlen = sizeof(int), + .mode = 0444, + .proc_handler = proc_dointvec, + }, + { + .procname = "io_delay_type", + .data = &io_delay_type, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec, + }, +#if defined(CONFIG_ACPI_SLEEP) + { + .procname = "acpi_video_flags", + .data = &acpi_realmode_flags, + .maxlen = sizeof(unsigned long), + .mode = 0644, + .proc_handler = proc_doulongvec_minmax, + }, +#endif +}; + +static int __init init_x86_sysctl(void) +{ + register_sysctl_init("kernel", x86_sysctl_table); + return 0; +} +arch_initcall(init_x86_sysctl); + /* * Setup options */ @@ -163,7 +226,8 @@ unsigned long saved_video_mode; static char __initdata command_line[COMMAND_LINE_SIZE]; #ifdef CONFIG_CMDLINE_BOOL -static char __initdata builtin_cmdline[COMMAND_LINE_SIZE] = CONFIG_CMDLINE; +char builtin_cmdline[COMMAND_LINE_SIZE] = CONFIG_CMDLINE; +bool builtin_cmdline_added __ro_after_init; #endif #if defined(CONFIG_EDD) || defined(CONFIG_EDD_MODULE) @@ -218,8 +282,8 @@ static void __init cleanup_highmap(void) static void __init reserve_brk(void) { if (_brk_end > _brk_start) - memblock_reserve(__pa_symbol(_brk_start), - _brk_end - _brk_start); + memblock_reserve_kern(__pa_symbol(_brk_start), + _brk_end - _brk_start); /* Mark brk area as locked down and no longer taking any new allocations */ @@ -257,6 +321,7 @@ static void __init relocate_initrd(void) u64 ramdisk_image = get_ramdisk_image(); u64 ramdisk_size = get_ramdisk_size(); u64 area_size = PAGE_ALIGN(ramdisk_size); + int ret = 0; /* We need to move the initrd down into directly mapped mem */ u64 relocated_ramdisk = memblock_phys_alloc_range(area_size, PAGE_SIZE, 0, @@ -270,7 +335,9 @@ static void __init relocate_initrd(void) printk(KERN_INFO "Allocated new RAMDISK: [mem %#010llx-%#010llx]\n", relocated_ramdisk, relocated_ramdisk + ramdisk_size - 1); - copy_from_early_mem((void *)initrd_start, ramdisk_image, ramdisk_size); + ret = copy_from_early_mem((void *)initrd_start, ramdisk_image, ramdisk_size); + if (ret) + panic("Copy RAMDISK failed\n"); printk(KERN_INFO "Move RAMDISK from [mem %#010llx-%#010llx] to" " [mem %#010llx-%#010llx]\n", @@ -289,7 +356,7 @@ static void __init early_reserve_initrd(void) !ramdisk_image || !ramdisk_size) return; /* No initrd provided by bootloader */ - memblock_reserve(ramdisk_image, ramdisk_end - ramdisk_image); + memblock_reserve_kern(ramdisk_image, ramdisk_end - ramdisk_image); } static void __init reserve_initrd(void) @@ -342,7 +409,7 @@ static void __init add_early_ima_buffer(u64 phys_addr) } if (data->size) { - memblock_reserve(data->addr, data->size); + memblock_reserve_kern(data->addr, data->size); ima_kexec_buffer_phys = data->addr; ima_kexec_buffer_size = data->size; } @@ -380,6 +447,29 @@ int __init ima_get_kexec_buffer(void **addr, size_t *size) } #endif +static void __init add_kho(u64 phys_addr, u32 data_len) +{ + struct kho_data *kho; + u64 addr = phys_addr + sizeof(struct setup_data); + u64 size = data_len - sizeof(struct setup_data); + + if (!IS_ENABLED(CONFIG_KEXEC_HANDOVER)) { + pr_warn("Passed KHO data, but CONFIG_KEXEC_HANDOVER not set. Ignoring.\n"); + return; + } + + kho = early_memremap(addr, size); + if (!kho) { + pr_warn("setup: failed to memremap kho data (0x%llx, 0x%llx)\n", + addr, size); + return; + } + + kho_populate(kho->fdt_addr, kho->fdt_size, kho->scratch_addr, kho->scratch_size); + + early_memunmap(kho, size); +} + static void __init parse_setup_data(void) { struct setup_data *data; @@ -408,6 +498,9 @@ static void __init parse_setup_data(void) case SETUP_IMA: add_early_ima_buffer(pa_data); break; + case SETUP_KEXEC_KHO: + add_kho(pa_data, data_len); + break; case SETUP_RNG_SEED: data = early_memremap(pa_data, data_len); add_bootloader_randomness(data->data, data->len); @@ -424,6 +517,46 @@ static void __init parse_setup_data(void) } } +/* + * Translate the fields of 'struct boot_param' into global variables + * representing these parameters. + */ +static void __init parse_boot_params(void) +{ + ROOT_DEV = old_decode_dev(boot_params.hdr.root_dev); + screen_info = boot_params.screen_info; + edid_info = boot_params.edid_info; +#ifdef CONFIG_X86_32 + apm_info.bios = boot_params.apm_bios_info; + ist_info = boot_params.ist_info; +#endif + saved_video_mode = boot_params.hdr.vid_mode; + bootloader_type = boot_params.hdr.type_of_loader; + if ((bootloader_type >> 4) == 0xe) { + bootloader_type &= 0xf; + bootloader_type |= (boot_params.hdr.ext_loader_type+0x10) << 4; + } + bootloader_version = bootloader_type & 0xf; + bootloader_version |= boot_params.hdr.ext_loader_ver << 4; + +#ifdef CONFIG_BLK_DEV_RAM + rd_image_start = boot_params.hdr.ram_size & RAMDISK_IMAGE_START_MASK; +#endif +#ifdef CONFIG_EFI + if (!strncmp((char *)&boot_params.efi_info.efi_loader_signature, + EFI32_LOADER_SIGNATURE, 4)) { + set_bit(EFI_BOOT, &efi.flags); + } else if (!strncmp((char *)&boot_params.efi_info.efi_loader_signature, + EFI64_LOADER_SIGNATURE, 4)) { + set_bit(EFI_BOOT, &efi.flags); + set_bit(EFI_64BIT, &efi.flags); + } +#endif + + if (!boot_params.hdr.root_flags) + root_mountflags &= ~MS_RDONLY; +} + static void __init memblock_x86_reserve_range_setup_data(void) { struct setup_indirect *indirect; @@ -442,7 +575,7 @@ static void __init memblock_x86_reserve_range_setup_data(void) len = sizeof(*data); pa_next = data->next; - memblock_reserve(pa_data, sizeof(*data) + data->len); + memblock_reserve_kern(pa_data, sizeof(*data) + data->len); if (data->type == SETUP_INDIRECT) { len += data->len; @@ -456,7 +589,7 @@ static void __init memblock_x86_reserve_range_setup_data(void) indirect = (struct setup_indirect *)data->data; if (indirect->type != SETUP_INDIRECT) - memblock_reserve(indirect->addr, indirect->len); + memblock_reserve_kern(indirect->addr, indirect->len); } pa_data = pa_next; @@ -467,14 +600,13 @@ static void __init memblock_x86_reserve_range_setup_data(void) static void __init arch_reserve_crashkernel(void) { unsigned long long crash_base, crash_size, low_size = 0; - char *cmdline = boot_command_line; bool high = false; int ret; if (!IS_ENABLED(CONFIG_CRASH_RESERVE)) return; - ret = parse_crashkernel(cmdline, memblock_phys_mem_size(), + ret = parse_crashkernel(boot_command_line, memblock_phys_mem_size(), &crash_size, &crash_base, &low_size, &high); if (ret) @@ -485,8 +617,7 @@ static void __init arch_reserve_crashkernel(void) return; } - reserve_crashkernel_generic(cmdline, crash_size, crash_base, - low_size, high); + reserve_crashkernel_generic(crash_size, crash_base, low_size, high); } static struct resource standard_io_resources[] = { @@ -522,6 +653,23 @@ void __init reserve_standard_io_resources(void) } +static void __init setup_kernel_resources(void) +{ + code_resource.start = __pa_symbol(_text); + code_resource.end = __pa_symbol(_etext)-1; + rodata_resource.start = __pa_symbol(__start_rodata); + rodata_resource.end = __pa_symbol(__end_rodata)-1; + data_resource.start = __pa_symbol(_sdata); + data_resource.end = __pa_symbol(_edata)-1; + bss_resource.start = __pa_symbol(__bss_start); + bss_resource.end = __pa_symbol(__bss_stop)-1; + + insert_resource(&iomem_resource, &code_resource); + insert_resource(&iomem_resource, &rodata_resource); + insert_resource(&iomem_resource, &data_resource); + insert_resource(&iomem_resource, &bss_resource); +} + static bool __init snb_gfx_workaround_needed(void) { #ifdef CONFIG_PCI @@ -644,8 +792,8 @@ static void __init early_reserve_memory(void) * __end_of_kernel_reserve symbol must be explicitly reserved with a * separate memblock_reserve() or they will be discarded. */ - memblock_reserve(__pa_symbol(_text), - (unsigned long)__end_of_kernel_reserve - (unsigned long)_text); + memblock_reserve_kern(__pa_symbol(_text), + (unsigned long)__end_of_kernel_reserve - (unsigned long)_text); /* * The first 4Kb of memory is a BIOS owned area, but generally it is @@ -753,6 +901,23 @@ void __init setup_arch(char **cmdline_p) boot_cpu_data.x86_phys_bits = MAX_PHYSMEM_BITS; #endif +#ifdef CONFIG_CMDLINE_BOOL +#ifdef CONFIG_CMDLINE_OVERRIDE + strscpy(boot_command_line, builtin_cmdline, COMMAND_LINE_SIZE); +#else + if (builtin_cmdline[0]) { + /* append boot loader cmdline to builtin */ + strlcat(builtin_cmdline, " ", COMMAND_LINE_SIZE); + strlcat(builtin_cmdline, boot_command_line, COMMAND_LINE_SIZE); + strscpy(boot_command_line, builtin_cmdline, COMMAND_LINE_SIZE); + } +#endif + builtin_cmdline_added = true; +#endif + + strscpy(command_line, boot_command_line, COMMAND_LINE_SIZE); + *cmdline_p = command_line; + /* * If we have OLPC OFW, we might end up relocating the fixmap due to * reserve_top(), so do this before touching the ioremap area. @@ -767,35 +932,7 @@ void __init setup_arch(char **cmdline_p) setup_olpc_ofw_pgd(); - ROOT_DEV = old_decode_dev(boot_params.hdr.root_dev); - screen_info = boot_params.screen_info; - edid_info = boot_params.edid_info; -#ifdef CONFIG_X86_32 - apm_info.bios = boot_params.apm_bios_info; - ist_info = boot_params.ist_info; -#endif - saved_video_mode = boot_params.hdr.vid_mode; - bootloader_type = boot_params.hdr.type_of_loader; - if ((bootloader_type >> 4) == 0xe) { - bootloader_type &= 0xf; - bootloader_type |= (boot_params.hdr.ext_loader_type+0x10) << 4; - } - bootloader_version = bootloader_type & 0xf; - bootloader_version |= boot_params.hdr.ext_loader_ver << 4; - -#ifdef CONFIG_BLK_DEV_RAM - rd_image_start = boot_params.hdr.ram_size & RAMDISK_IMAGE_START_MASK; -#endif -#ifdef CONFIG_EFI - if (!strncmp((char *)&boot_params.efi_info.efi_loader_signature, - EFI32_LOADER_SIGNATURE, 4)) { - set_bit(EFI_BOOT, &efi.flags); - } else if (!strncmp((char *)&boot_params.efi_info.efi_loader_signature, - EFI64_LOADER_SIGNATURE, 4)) { - set_bit(EFI_BOOT, &efi.flags); - set_bit(EFI_64BIT, &efi.flags); - } -#endif + parse_boot_params(); x86_init.oem.arch_setup(); @@ -819,35 +956,8 @@ void __init setup_arch(char **cmdline_p) copy_edd(); - if (!boot_params.hdr.root_flags) - root_mountflags &= ~MS_RDONLY; setup_initial_init_mm(_text, _etext, _edata, (void *)_brk_end); - code_resource.start = __pa_symbol(_text); - code_resource.end = __pa_symbol(_etext)-1; - rodata_resource.start = __pa_symbol(__start_rodata); - rodata_resource.end = __pa_symbol(__end_rodata)-1; - data_resource.start = __pa_symbol(_sdata); - data_resource.end = __pa_symbol(_edata)-1; - bss_resource.start = __pa_symbol(__bss_start); - bss_resource.end = __pa_symbol(__bss_stop)-1; - -#ifdef CONFIG_CMDLINE_BOOL -#ifdef CONFIG_CMDLINE_OVERRIDE - strscpy(boot_command_line, builtin_cmdline, COMMAND_LINE_SIZE); -#else - if (builtin_cmdline[0]) { - /* append boot loader cmdline to builtin */ - strlcat(builtin_cmdline, " ", COMMAND_LINE_SIZE); - strlcat(builtin_cmdline, boot_command_line, COMMAND_LINE_SIZE); - strscpy(boot_command_line, builtin_cmdline, COMMAND_LINE_SIZE); - } -#endif -#endif - - strscpy(command_line, boot_command_line, COMMAND_LINE_SIZE); - *cmdline_p = command_line; - /* * x86_configure_nx() is called before parse_early_param() to detect * whether hardware doesn't support NX (so that the early EHCI debug @@ -860,30 +970,6 @@ void __init setup_arch(char **cmdline_p) if (efi_enabled(EFI_BOOT)) efi_memblock_x86_reserve_range(); -#ifdef CONFIG_MEMORY_HOTPLUG - /* - * Memory used by the kernel cannot be hot-removed because Linux - * cannot migrate the kernel pages. When memory hotplug is - * enabled, we should prevent memblock from allocating memory - * for the kernel. - * - * ACPI SRAT records all hotpluggable memory ranges. But before - * SRAT is parsed, we don't know about it. - * - * The kernel image is loaded into memory at very early time. We - * cannot prevent this anyway. So on NUMA system, we set any - * node the kernel resides in as un-hotpluggable. - * - * Since on modern servers, one node could have double-digit - * gigabytes memory, we can assume the memory around the kernel - * image is also un-hotpluggable. So before SRAT is parsed, just - * allocate memory near the kernel image to try the best to keep - * the kernel away from hotpluggable memory. - */ - if (movable_node_is_enabled()) - memblock_set_bottom_up(true); -#endif - x86_report_nx(); apic_setup_apic_calls(); @@ -895,14 +981,13 @@ void __init setup_arch(char **cmdline_p) setup_clear_cpu_cap(X86_FEATURE_APIC); } - e820__reserve_setup_data(); e820__finish_early_params(); if (efi_enabled(EFI_BOOT)) efi_init(); reserve_ibft_region(); - dmi_setup(); + x86_init.resources.dmi_setup(); /* * VMware detection requires dmi to be available, so this @@ -915,11 +1000,11 @@ void __init setup_arch(char **cmdline_p) tsc_early_init(); x86_init.resources.probe_roms(); - /* after parse_early_param, so could debug it */ - insert_resource(&iomem_resource, &code_resource); - insert_resource(&iomem_resource, &rodata_resource); - insert_resource(&iomem_resource, &data_resource); - insert_resource(&iomem_resource, &bss_resource); + /* + * Add resources for kernel text and data to the iomem_resource. + * Do it after parse_early_param, so it can be debugged. + */ + setup_kernel_resources(); e820_add_kernel_range(); trim_bios_range(); @@ -966,8 +1051,6 @@ void __init setup_arch(char **cmdline_p) max_low_pfn = e820__end_of_low_ram_pfn(); else max_low_pfn = max_pfn; - - high_memory = (void *)__va(max_pfn * PAGE_SIZE - 1) + 1; #endif /* Find and reserve MPTABLE area */ @@ -984,7 +1067,6 @@ void __init setup_arch(char **cmdline_p) cleanup_highmap(); - memblock_set_current_limit(ISA_END_ADDRESS); e820__memblock_setup(); /* @@ -992,8 +1074,8 @@ void __init setup_arch(char **cmdline_p) * memory size. */ mem_encrypt_setup_arch(); + cc_random_init(); - efi_fake_memmap(); efi_find_mirror(); efi_esrt_init(); efi_mokvar_table_init(); @@ -1036,7 +1118,12 @@ void __init setup_arch(char **cmdline_p) init_mem_mapping(); - idt_setup_early_pf(); + /* + * init_mem_mapping() relies on the early IDT page fault handling. + * Now either enable FRED or install the real page fault handler + * for 64-bit in the IDT. + */ + cpu_init_replace_early_idt(); /* * Update mmu_cr4_features (and, indirectly, trampoline_cr4_features) @@ -1097,8 +1184,10 @@ void __init setup_arch(char **cmdline_p) initmem_init(); dma_contiguous_reserve(max_pfn_mapped << PAGE_SHIFT); - if (boot_cpu_has(X86_FEATURE_GBPAGES)) + if (boot_cpu_has(X86_FEATURE_GBPAGES)) { hugetlb_cma_reserve(PUD_SHIFT - PAGE_SHIFT); + hugetlb_bootmem_alloc(); + } /* * Reserve memory for crash kernel after SRAT is parsed so that it @@ -1106,8 +1195,6 @@ void __init setup_arch(char **cmdline_p) */ arch_reserve_crashkernel(); - memblock_find_dma_reserve(); - if (!early_xdbc_setup_hardware()) early_xdbc_register_console(); @@ -1206,16 +1293,6 @@ void __init i386_reserve_resources(void) #endif /* CONFIG_X86_32 */ -#ifndef CONFIG_SMP -void __init smp_prepare_boot_cpu(void) -{ - struct cpuinfo_x86 *c = &cpu_data(0); - - *c = boot_cpu_data; - c->initialized = true; -} -#endif - static struct notifier_block kernel_offset_notifier = { .notifier_call = dump_kernel_offset }; @@ -1227,3 +1304,10 @@ static int __init register_kernel_offset_dumper(void) return 0; } __initcall(register_kernel_offset_dumper); + +#ifdef CONFIG_HOTPLUG_CPU +bool arch_cpu_is_hotpluggable(int cpu) +{ + return cpu > 0; +} +#endif /* CONFIG_HOTPLUG_CPU */ |