diff options
Diffstat (limited to 'arch/x86/kernel/setup.c')
| -rw-r--r-- | arch/x86/kernel/setup.c | 790 |
1 files changed, 513 insertions, 277 deletions
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index f7b8b9894b2..78a0e629892 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -31,9 +31,9 @@ #include <linux/apm_bios.h> #include <linux/initrd.h> #include <linux/bootmem.h> +#include <linux/memblock.h> #include <linux/seq_file.h> #include <linux/console.h> -#include <linux/mca.h> #include <linux/root_dev.h> #include <linux/highmem.h> #include <linux/module.h> @@ -49,13 +49,13 @@ #include <asm/pci-direct.h> #include <linux/init_ohci1394_dma.h> #include <linux/kvm_para.h> +#include <linux/dma-contiguous.h> #include <linux/errno.h> #include <linux/kernel.h> #include <linux/stddef.h> #include <linux/unistd.h> #include <linux/ptrace.h> -#include <linux/slab.h> #include <linux/user.h> #include <linux/delay.h> @@ -68,12 +68,13 @@ #include <linux/percpu.h> #include <linux/crash_dump.h> #include <linux/tboot.h> +#include <linux/jiffies.h> #include <video/edid.h> #include <asm/mtrr.h> #include <asm/apic.h> -#include <asm/trampoline.h> +#include <asm/realmode.h> #include <asm/e820.h> #include <asm/mpspec.h> #include <asm/setup.h> @@ -81,17 +82,14 @@ #include <asm/timer.h> #include <asm/i8259.h> #include <asm/sections.h> -#include <asm/dmi.h> #include <asm/io_apic.h> #include <asm/ist.h> -#include <asm/vmi.h> #include <asm/setup_arch.h> #include <asm/bios_ebda.h> #include <asm/cacheflush.h> #include <asm/processor.h> #include <asm/bugs.h> -#include <asm/system.h> #include <asm/vsyscall.h> #include <asm/cpu.h> #include <asm/desc.h> @@ -103,27 +101,30 @@ #include <asm/paravirt.h> #include <asm/hypervisor.h> +#include <asm/olpc_ofw.h> #include <asm/percpu.h> #include <asm/topology.h> #include <asm/apicdef.h> -#include <asm/k8.h> -#ifdef CONFIG_X86_64 -#include <asm/numa_64.h> -#endif +#include <asm/amd_nb.h> #include <asm/mce.h> +#include <asm/alternative.h> +#include <asm/prom.h> /* - * end_pfn only includes RAM, while max_pfn_mapped includes all e820 entries. - * The direct mapping extends to max_pfn_mapped, so that we can directly access - * apertures, ACPI and other tables without having to play with fixmaps. + * max_low_pfn_mapped: highest direct mapped pfn under 4GB + * max_pfn_mapped: highest direct mapped pfn over 4GB + * + * The direct mapping only covers E820_RAM regions, so the ranges and gaps are + * represented by pfn_mapped */ unsigned long max_low_pfn_mapped; unsigned long max_pfn_mapped; +#ifdef CONFIG_DMI RESERVE_BRK(dmi_alloc, 65536); +#endif -unsigned int boot_cpu_id __read_mostly; static __initdata unsigned long _brk_start = (unsigned long)__brk_base; unsigned long _brk_end = (unsigned long)__brk_base; @@ -140,11 +141,7 @@ int default_check_phys_apicid_present(int phys_apicid) } #endif -#ifndef CONFIG_DEBUG_BOOT_PARAMS -struct boot_params __initdata boot_params; -#else struct boot_params boot_params; -#endif /* * Machine setup.. @@ -173,16 +170,14 @@ static struct resource bss_resource = { #ifdef CONFIG_X86_32 /* cpu data as detected by the assembly code in head.S */ -struct cpuinfo_x86 new_cpu_data __cpuinitdata = {0, 0, 0, 0, -1, 1, 0, 0, -1}; +struct cpuinfo_x86 new_cpu_data = { + .wp_works_ok = -1, +}; /* common cpu data for all cpus */ -struct cpuinfo_x86 boot_cpu_data __read_mostly = {0, 0, 0, 0, -1, 1, 0, 0, -1}; +struct cpuinfo_x86 boot_cpu_data __read_mostly = { + .wp_works_ok = -1, +}; EXPORT_SYMBOL(boot_cpu_data); -static void set_mca_bus(int x) -{ -#ifdef CONFIG_MCA - MCA_bus = x; -#endif -} unsigned int def_to_bigsmp; @@ -211,9 +206,9 @@ EXPORT_SYMBOL(boot_cpu_data); #if !defined(CONFIG_X86_PAE) || defined(CONFIG_X86_64) -unsigned long mmu_cr4_features; +__visible unsigned long mmu_cr4_features; #else -unsigned long mmu_cr4_features = X86_CR4_PAE; +__visible unsigned long mmu_cr4_features = X86_CR4_PAE; #endif /* Boot loader ID and version as integers, for the benefit of proc_dointvec */ @@ -283,16 +278,8 @@ void * __init extend_brk(size_t size, size_t align) return ret; } -#ifdef CONFIG_X86_64 -static void __init init_gbpages(void) -{ - if (direct_gbpages && cpu_has_gbpages) - printk(KERN_INFO "Using GB pages for direct mapping\n"); - else - direct_gbpages = 0; -} -#else -static inline void init_gbpages(void) +#ifdef CONFIG_X86_32 +static void __init cleanup_highmap(void) { } #endif @@ -300,56 +287,64 @@ static inline void init_gbpages(void) static void __init reserve_brk(void) { if (_brk_end > _brk_start) - reserve_early(__pa(_brk_start), __pa(_brk_end), "BRK"); + memblock_reserve(__pa_symbol(_brk_start), + _brk_end - _brk_start); /* Mark brk area as locked down and no longer taking any new allocations */ _brk_start = 0; } +u64 relocated_ramdisk; + #ifdef CONFIG_BLK_DEV_INITRD +static u64 __init get_ramdisk_image(void) +{ + u64 ramdisk_image = boot_params.hdr.ramdisk_image; + + ramdisk_image |= (u64)boot_params.ext_ramdisk_image << 32; + + return ramdisk_image; +} +static u64 __init get_ramdisk_size(void) +{ + u64 ramdisk_size = boot_params.hdr.ramdisk_size; + + ramdisk_size |= (u64)boot_params.ext_ramdisk_size << 32; + + return ramdisk_size; +} + #define MAX_MAP_CHUNK (NR_FIX_BTMAPS << PAGE_SHIFT) static void __init relocate_initrd(void) { - - u64 ramdisk_image = boot_params.hdr.ramdisk_image; - u64 ramdisk_size = boot_params.hdr.ramdisk_size; - u64 end_of_lowmem = max_low_pfn_mapped << PAGE_SHIFT; - u64 ramdisk_here; + /* Assume only end is not page aligned */ + u64 ramdisk_image = get_ramdisk_image(); + u64 ramdisk_size = get_ramdisk_size(); + u64 area_size = PAGE_ALIGN(ramdisk_size); unsigned long slop, clen, mapaddr; char *p, *q; - /* We need to move the initrd down into lowmem */ - ramdisk_here = find_e820_area(0, end_of_lowmem, ramdisk_size, - PAGE_SIZE); + /* We need to move the initrd down into directly mapped mem */ + relocated_ramdisk = memblock_find_in_range(0, PFN_PHYS(max_pfn_mapped), + area_size, PAGE_SIZE); - if (ramdisk_here == -1ULL) + if (!relocated_ramdisk) panic("Cannot find place for new RAMDISK of size %lld\n", - ramdisk_size); + ramdisk_size); - /* Note: this includes all the lowmem currently occupied by + /* Note: this includes all the mem currently occupied by the initrd, we rely on that fact to keep the data intact. */ - reserve_early(ramdisk_here, ramdisk_here + ramdisk_size, - "NEW RAMDISK"); - initrd_start = ramdisk_here + PAGE_OFFSET; + memblock_reserve(relocated_ramdisk, area_size); + initrd_start = relocated_ramdisk + PAGE_OFFSET; initrd_end = initrd_start + ramdisk_size; - printk(KERN_INFO "Allocated new RAMDISK: %08llx - %08llx\n", - ramdisk_here, ramdisk_here + ramdisk_size); + printk(KERN_INFO "Allocated new RAMDISK: [mem %#010llx-%#010llx]\n", + relocated_ramdisk, relocated_ramdisk + ramdisk_size - 1); q = (char *)initrd_start; - /* Copy any lowmem portion of the initrd */ - if (ramdisk_image < end_of_lowmem) { - clen = end_of_lowmem - ramdisk_image; - p = (char *)__va(ramdisk_image); - memcpy(q, p, clen); - q += clen; - ramdisk_image += clen; - ramdisk_size -= clen; - } - - /* Copy the highmem portion of the initrd */ + /* Copy the initrd */ while (ramdisk_size) { slop = ramdisk_image & ~PAGE_MASK; clen = ramdisk_size; @@ -363,21 +358,35 @@ static void __init relocate_initrd(void) ramdisk_image += clen; ramdisk_size -= clen; } - /* high pages is not converted by early_res_to_bootmem */ - ramdisk_image = boot_params.hdr.ramdisk_image; - ramdisk_size = boot_params.hdr.ramdisk_size; - printk(KERN_INFO "Move RAMDISK from %016llx - %016llx to" - " %08llx - %08llx\n", + + ramdisk_image = get_ramdisk_image(); + ramdisk_size = get_ramdisk_size(); + printk(KERN_INFO "Move RAMDISK from [mem %#010llx-%#010llx] to" + " [mem %#010llx-%#010llx]\n", ramdisk_image, ramdisk_image + ramdisk_size - 1, - ramdisk_here, ramdisk_here + ramdisk_size - 1); + relocated_ramdisk, relocated_ramdisk + ramdisk_size - 1); } +static void __init early_reserve_initrd(void) +{ + /* Assume only end is not page aligned */ + u64 ramdisk_image = get_ramdisk_image(); + u64 ramdisk_size = get_ramdisk_size(); + u64 ramdisk_end = PAGE_ALIGN(ramdisk_image + ramdisk_size); + + if (!boot_params.hdr.type_of_loader || + !ramdisk_image || !ramdisk_size) + return; /* No initrd provided by bootloader */ + + memblock_reserve(ramdisk_image, ramdisk_end - ramdisk_image); +} static void __init reserve_initrd(void) { - u64 ramdisk_image = boot_params.hdr.ramdisk_image; - u64 ramdisk_size = boot_params.hdr.ramdisk_size; - u64 ramdisk_end = ramdisk_image + ramdisk_size; - u64 end_of_lowmem = max_low_pfn_mapped << PAGE_SHIFT; + /* Assume only end is not page aligned */ + u64 ramdisk_image = get_ramdisk_image(); + u64 ramdisk_size = get_ramdisk_size(); + u64 ramdisk_end = PAGE_ALIGN(ramdisk_image + ramdisk_size); + u64 mapped_size; if (!boot_params.hdr.type_of_loader || !ramdisk_image || !ramdisk_size) @@ -385,23 +394,18 @@ static void __init reserve_initrd(void) initrd_start = 0; - if (ramdisk_size >= (end_of_lowmem>>1)) { - free_early(ramdisk_image, ramdisk_end); - printk(KERN_ERR "initrd too large to handle, " - "disabling initrd\n"); - return; - } + mapped_size = memblock_mem_size(max_pfn_mapped); + if (ramdisk_size >= (mapped_size>>1)) + panic("initrd too large to handle, " + "disabling initrd (%lld needed, %lld available)\n", + ramdisk_size, mapped_size>>1); - printk(KERN_INFO "RAMDISK: %08llx - %08llx\n", ramdisk_image, - ramdisk_end); + printk(KERN_INFO "RAMDISK: [mem %#010llx-%#010llx]\n", ramdisk_image, + ramdisk_end - 1); - - if (ramdisk_end <= end_of_lowmem) { - /* All in lowmem, easy case */ - /* - * don't need to reserve again, already reserved early - * in i386_start_kernel - */ + if (pfn_range_is_mapped(PFN_DOWN(ramdisk_image), + PFN_DOWN(ramdisk_end))) { + /* All are mapped, easy case */ initrd_start = ramdisk_image + PAGE_OFFSET; initrd_end = initrd_start + ramdisk_size; return; @@ -409,9 +413,12 @@ static void __init reserve_initrd(void) relocate_initrd(); - free_early(ramdisk_image, ramdisk_end); + memblock_free(ramdisk_image, ramdisk_end - ramdisk_image); } #else +static void __init early_reserve_initrd(void) +{ +} static void __init reserve_initrd(void) { } @@ -420,22 +427,34 @@ static void __init reserve_initrd(void) static void __init parse_setup_data(void) { struct setup_data *data; - u64 pa_data; + u64 pa_data, pa_next; - if (boot_params.hdr.version < 0x0209) - return; pa_data = boot_params.hdr.setup_data; while (pa_data) { - data = early_memremap(pa_data, PAGE_SIZE); - switch (data->type) { + u32 data_len, map_len, data_type; + + map_len = max(PAGE_SIZE - (pa_data & ~PAGE_MASK), + (u64)sizeof(struct setup_data)); + data = early_memremap(pa_data, map_len); + data_len = data->len + sizeof(struct setup_data); + data_type = data->type; + pa_next = data->next; + early_iounmap(data, map_len); + + switch (data_type) { case SETUP_E820_EXT: - parse_e820_ext(data, pa_data); + parse_e820_ext(pa_data, data_len); + break; + case SETUP_DTB: + add_dtb(pa_data); + break; + case SETUP_EFI: + parse_efi_setup(pa_data, data_len); break; default: break; } - pa_data = data->next; - early_iounmap(data, PAGE_SIZE); + pa_data = pa_next; } } @@ -445,8 +464,6 @@ static void __init e820_reserve_setup_data(void) u64 pa_data; int found = 0; - if (boot_params.hdr.version < 0x0209) - return; pa_data = boot_params.hdr.setup_data; while (pa_data) { data = early_memremap(pa_data, sizeof(*data)); @@ -465,19 +482,15 @@ static void __init e820_reserve_setup_data(void) e820_print_map("reserve setup_data"); } -static void __init reserve_early_setup_data(void) +static void __init memblock_x86_reserve_range_setup_data(void) { struct setup_data *data; u64 pa_data; - char buf[32]; - if (boot_params.hdr.version < 0x0209) - return; pa_data = boot_params.hdr.setup_data; while (pa_data) { data = early_memremap(pa_data, sizeof(*data)); - sprintf(buf, "setup data %x", data->type); - reserve_early(pa_data, pa_data+sizeof(*data)+data->len, buf); + memblock_reserve(pa_data, sizeof(*data) + data->len); pa_data = data->next; early_iounmap(data, sizeof(*data)); } @@ -489,49 +502,118 @@ static void __init reserve_early_setup_data(void) #ifdef CONFIG_KEXEC -static inline unsigned long long get_total_mem(void) +/* + * Keep the crash kernel below this limit. On 32 bits earlier kernels + * would limit the kernel to the low 512 MiB due to mapping restrictions. + * On 64bit, old kexec-tools need to under 896MiB. + */ +#ifdef CONFIG_X86_32 +# define CRASH_KERNEL_ADDR_LOW_MAX (512 << 20) +# define CRASH_KERNEL_ADDR_HIGH_MAX (512 << 20) +#else +# define CRASH_KERNEL_ADDR_LOW_MAX (896UL<<20) +# define CRASH_KERNEL_ADDR_HIGH_MAX MAXMEM +#endif + +static void __init reserve_crashkernel_low(void) { - unsigned long long total; +#ifdef CONFIG_X86_64 + const unsigned long long alignment = 16<<20; /* 16M */ + unsigned long long low_base = 0, low_size = 0; + unsigned long total_low_mem; + unsigned long long base; + bool auto_set = false; + int ret; + + total_low_mem = memblock_mem_size(1UL<<(32-PAGE_SHIFT)); + /* crashkernel=Y,low */ + ret = parse_crashkernel_low(boot_command_line, total_low_mem, + &low_size, &base); + if (ret != 0) { + /* + * two parts from lib/swiotlb.c: + * swiotlb size: user specified with swiotlb= or default. + * swiotlb overflow buffer: now is hardcoded to 32k. + * We round it to 8M for other buffers that + * may need to stay low too. + */ + low_size = swiotlb_size_or_default() + (8UL<<20); + auto_set = true; + } else { + /* passed with crashkernel=0,low ? */ + if (!low_size) + return; + } - total = max_pfn - min_low_pfn; + low_base = memblock_find_in_range(low_size, (1ULL<<32), + low_size, alignment); - return total << PAGE_SHIFT; + if (!low_base) { + if (!auto_set) + pr_info("crashkernel low reservation failed - No suitable area found.\n"); + + return; + } + + memblock_reserve(low_base, low_size); + pr_info("Reserving %ldMB of low memory at %ldMB for crashkernel (System low RAM: %ldMB)\n", + (unsigned long)(low_size >> 20), + (unsigned long)(low_base >> 20), + (unsigned long)(total_low_mem >> 20)); + crashk_low_res.start = low_base; + crashk_low_res.end = low_base + low_size - 1; + insert_resource(&iomem_resource, &crashk_low_res); +#endif } static void __init reserve_crashkernel(void) { + const unsigned long long alignment = 16<<20; /* 16M */ unsigned long long total_mem; unsigned long long crash_size, crash_base; + bool high = false; int ret; - total_mem = get_total_mem(); + total_mem = memblock_phys_mem_size(); + /* crashkernel=XM */ ret = parse_crashkernel(boot_command_line, total_mem, &crash_size, &crash_base); - if (ret != 0 || crash_size <= 0) - return; + if (ret != 0 || crash_size <= 0) { + /* crashkernel=X,high */ + ret = parse_crashkernel_high(boot_command_line, total_mem, + &crash_size, &crash_base); + if (ret != 0 || crash_size <= 0) + return; + high = true; + } /* 0 means: find the address automatically */ if (crash_base <= 0) { - const unsigned long long alignment = 16<<20; /* 16M */ + /* + * kexec want bzImage is below CRASH_KERNEL_ADDR_MAX + */ + crash_base = memblock_find_in_range(alignment, + high ? CRASH_KERNEL_ADDR_HIGH_MAX : + CRASH_KERNEL_ADDR_LOW_MAX, + crash_size, alignment); - crash_base = find_e820_area(alignment, ULONG_MAX, crash_size, - alignment); - if (crash_base == -1ULL) { + if (!crash_base) { pr_info("crashkernel reservation failed - No suitable area found.\n"); return; } + } else { unsigned long long start; - start = find_e820_area(crash_base, ULONG_MAX, crash_size, - 1<<20); + start = memblock_find_in_range(crash_base, + crash_base + crash_size, crash_size, 1<<20); if (start != crash_base) { pr_info("crashkernel reservation failed - memory is in use.\n"); return; } } - reserve_early(crash_base, crash_base + crash_size, "CRASH KERNEL"); + memblock_reserve(crash_base, crash_size); printk(KERN_INFO "Reserving %ldMB of memory at %ldMB " "for crashkernel (System RAM: %ldMB)\n", @@ -542,6 +624,9 @@ static void __init reserve_crashkernel(void) crashk_res.start = crash_base; crashk_res.end = crash_base + crash_size - 1; insert_resource(&iomem_resource, &crashk_res); + + if (crash_base >= (1ULL<<32)) + reserve_crashkernel_low(); } #else static void __init reserve_crashkernel(void) @@ -582,82 +667,179 @@ void __init reserve_standard_io_resources(void) } +static __init void reserve_ibft_region(void) +{ + unsigned long addr, size = 0; + + addr = find_ibft_region(&size); + + if (size) + memblock_reserve(addr, size); +} + +static bool __init snb_gfx_workaround_needed(void) +{ +#ifdef CONFIG_PCI + int i; + u16 vendor, devid; + static const __initconst u16 snb_ids[] = { + 0x0102, + 0x0112, + 0x0122, + 0x0106, + 0x0116, + 0x0126, + 0x010a, + }; + + /* Assume no if something weird is going on with PCI */ + if (!early_pci_allowed()) + return false; + + vendor = read_pci_config_16(0, 2, 0, PCI_VENDOR_ID); + if (vendor != 0x8086) + return false; + + devid = read_pci_config_16(0, 2, 0, PCI_DEVICE_ID); + for (i = 0; i < ARRAY_SIZE(snb_ids); i++) + if (devid == snb_ids[i]) + return true; +#endif + + return false; +} + /* - * Note: elfcorehdr_addr is not just limited to vmcore. It is also used by - * is_kdump_kernel() to determine if we are booting after a panic. Hence - * ifdef it under CONFIG_CRASH_DUMP and not CONFIG_PROC_VMCORE. + * Sandy Bridge graphics has trouble with certain ranges, exclude + * them from allocation. */ +static void __init trim_snb_memory(void) +{ + static const __initconst unsigned long bad_pages[] = { + 0x20050000, + 0x20110000, + 0x20130000, + 0x20138000, + 0x40004000, + }; + int i; -#ifdef CONFIG_CRASH_DUMP -/* elfcorehdr= specifies the location of elf core header - * stored by the crashed kernel. This option will be passed - * by kexec loader to the capture kernel. + if (!snb_gfx_workaround_needed()) + return; + + printk(KERN_DEBUG "reserving inaccessible SNB gfx pages\n"); + + /* + * Reserve all memory below the 1 MB mark that has not + * already been reserved. + */ + memblock_reserve(0, 1<<20); + + for (i = 0; i < ARRAY_SIZE(bad_pages); i++) { + if (memblock_reserve(bad_pages[i], PAGE_SIZE)) + printk(KERN_WARNING "failed to reserve 0x%08lx\n", + bad_pages[i]); + } +} + +/* + * Here we put platform-specific memory range workarounds, i.e. + * memory known to be corrupt or otherwise in need to be reserved on + * specific platforms. + * + * If this gets used more widely it could use a real dispatch mechanism. */ -static int __init setup_elfcorehdr(char *arg) +static void __init trim_platform_memory_ranges(void) { - char *end; - if (!arg) - return -EINVAL; - elfcorehdr_addr = memparse(arg, &end); - return end > arg ? 0 : -EINVAL; + trim_snb_memory(); } -early_param("elfcorehdr", setup_elfcorehdr); -#endif -#ifdef CONFIG_X86_RESERVE_LOW_64K -static int __init dmi_low_memory_corruption(const struct dmi_system_id *d) +static void __init trim_bios_range(void) { - printk(KERN_NOTICE - "%s detected: BIOS may corrupt low RAM, working around it.\n", - d->ident); + /* + * A special case is the first 4Kb of memory; + * This is a BIOS owned area, not kernel ram, but generally + * not listed as such in the E820 table. + * + * This typically reserves additional memory (64KiB by default) + * since some BIOSes are known to corrupt low memory. See the + * Kconfig help text for X86_RESERVE_LOW. + */ + e820_update_range(0, PAGE_SIZE, E820_RAM, E820_RESERVED); - e820_update_range(0, 0x10000, E820_RAM, E820_RESERVED); - sanitize_e820_map(e820.map, ARRAY_SIZE(e820.map), &e820.nr_map); + /* + * special case: Some BIOSen report the PC BIOS + * area (640->1Mb) as ram even though it is not. + * take them out. + */ + e820_remove_range(BIOS_BEGIN, BIOS_END - BIOS_BEGIN, E820_RAM, 1); - return 0; + sanitize_e820_map(e820.map, ARRAY_SIZE(e820.map), &e820.nr_map); } -#endif -/* List of systems that have known low memory corruption BIOS problems */ -static struct dmi_system_id __initdata bad_bios_dmi_table[] = { -#ifdef CONFIG_X86_RESERVE_LOW_64K - { - .callback = dmi_low_memory_corruption, - .ident = "AMI BIOS", - .matches = { - DMI_MATCH(DMI_BIOS_VENDOR, "American Megatrends Inc."), - }, - }, - { - .callback = dmi_low_memory_corruption, - .ident = "Phoenix BIOS", - .matches = { - DMI_MATCH(DMI_BIOS_VENDOR, "Phoenix Technologies"), - }, - }, - { - .callback = dmi_low_memory_corruption, - .ident = "Phoenix/MSC BIOS", - .matches = { - DMI_MATCH(DMI_BIOS_VENDOR, "Phoenix/MSC"), - }, - }, - { +/* called before trim_bios_range() to spare extra sanitize */ +static void __init e820_add_kernel_range(void) +{ + u64 start = __pa_symbol(_text); + u64 size = __pa_symbol(_end) - start; + /* - * AMI BIOS with low memory corruption was found on Intel DG45ID board. - * It hase different DMI_BIOS_VENDOR = "Intel Corp.", for now we will - * match only DMI_BOARD_NAME and see if there is more bad products - * with this vendor. + * Complain if .text .data and .bss are not marked as E820_RAM and + * attempt to fix it by adding the range. We may have a confused BIOS, + * or the user may have used memmap=exactmap or memmap=xxM$yyM to + * exclude kernel range. If we really are running on top non-RAM, + * we will crash later anyways. */ - .callback = dmi_low_memory_corruption, - .ident = "AMI BIOS", - .matches = { - DMI_MATCH(DMI_BOARD_NAME, "DG45ID"), - }, - }, -#endif - {} -}; + if (e820_all_mapped(start, start + size, E820_RAM)) + return; + + pr_warn(".text .data .bss are not marked as E820_RAM!\n"); + e820_remove_range(start, size, E820_RAM, 0); + e820_add_region(start, size, E820_RAM); +} + +static unsigned reserve_low = CONFIG_X86_RESERVE_LOW << 10; + +static int __init parse_reservelow(char *p) +{ + unsigned long long size; + + if (!p) + return -EINVAL; + + size = memparse(p, &p); + + if (size < 4096) + size = 4096; + + if (size > 640*1024) + size = 640*1024; + + reserve_low = size; + + return 0; +} + +early_param("reservelow", parse_reservelow); + +static void __init trim_low_memory_range(void) +{ + memblock_reserve(0, ALIGN(reserve_low, PAGE_SIZE)); +} + +/* + * Dump out kernel offset information on panic. + */ +static int +dump_kernel_offset(struct notifier_block *self, unsigned long v, void *p) +{ + pr_emerg("Kernel Offset: 0x%lx from 0x%lx " + "(relocation range: 0x%lx-0x%lx)\n", + (unsigned long)&_text - __START_KERNEL, __START_KERNEL, + __START_KERNEL_map, MODULES_VADDR-1); + + return 0; +} /* * Determine if we were loaded by an EFI loader. If so, then we have also been @@ -674,22 +856,46 @@ static struct dmi_system_id __initdata bad_bios_dmi_table[] = { void __init setup_arch(char **cmdline_p) { - int acpi = 0; - int k8 = 0; + memblock_reserve(__pa_symbol(_text), + (unsigned long)__bss_stop - (unsigned long)_text); + + early_reserve_initrd(); + + /* + * At this point everything still needed from the boot loader + * or BIOS or kernel text should be early reserved or marked not + * RAM in e820. All other memory is free game. + */ #ifdef CONFIG_X86_32 memcpy(&boot_cpu_data, &new_cpu_data, sizeof(new_cpu_data)); - visws_early_detect(); + + /* + * copy kernel address range established so far and switch + * to the proper swapper page table + */ + clone_pgd_range(swapper_pg_dir + KERNEL_PGD_BOUNDARY, + initial_page_table + KERNEL_PGD_BOUNDARY, + KERNEL_PGD_PTRS); + + load_cr3(swapper_pg_dir); + __flush_tlb_all(); #else printk(KERN_INFO "Command line: %s\n", boot_command_line); #endif - /* VMI may relocate the fixmap; do this before touching ioremap area */ - vmi_init(); + /* + * If we have OLPC OFW, we might end up relocating the fixmap due to + * reserve_top(), so do this before touching the ioremap area. + */ + olpc_ofw_detect(); + early_trap_init(); early_cpu_init(); early_ioremap_init(); + 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; @@ -697,7 +903,6 @@ void __init setup_arch(char **cmdline_p) apm_info.bios = boot_params.apm_bios_info; ist_info = boot_params.ist_info; if (boot_params.sys_desc_table.length != 0) { - set_mca_bus(boot_params.sys_desc_table.table[3] & 0x2); machine_id = boot_params.sys_desc_table.table[0]; machine_submodel_id = boot_params.sys_desc_table.table[1]; BIOS_revision = boot_params.sys_desc_table.table[2]; @@ -719,23 +924,23 @@ void __init setup_arch(char **cmdline_p) #endif #ifdef CONFIG_EFI if (!strncmp((char *)&boot_params.efi_info.efi_loader_signature, -#ifdef CONFIG_X86_32 - "EL32", -#else - "EL64", -#endif - 4)) { - efi_enabled = 1; - efi_reserve_early(); + "EL32", 4)) { + set_bit(EFI_BOOT, &efi.flags); + } else if (!strncmp((char *)&boot_params.efi_info.efi_loader_signature, + "EL64", 4)) { + set_bit(EFI_BOOT, &efi.flags); + set_bit(EFI_64BIT, &efi.flags); } + + if (efi_enabled(EFI_BOOT)) + efi_memblock_x86_reserve_range(); #endif x86_init.oem.arch_setup(); + iomem_resource.end = (1ULL << boot_cpu_data.x86_phys_bits) - 1; setup_memory_map(); parse_setup_data(); - /* update the e820_saved too */ - e820_reserve_setup_data(); copy_edd(); @@ -746,12 +951,12 @@ void __init setup_arch(char **cmdline_p) init_mm.end_data = (unsigned long) _edata; init_mm.brk = _brk_end; - code_resource.start = virt_to_phys(_text); - code_resource.end = virt_to_phys(_etext)-1; - data_resource.start = virt_to_phys(_etext); - data_resource.end = virt_to_phys(_edata)-1; - bss_resource.start = virt_to_phys(&__bss_start); - bss_resource.end = virt_to_phys(&__bss_stop)-1; + code_resource.start = __pa_symbol(_text); + code_resource.end = __pa_symbol(_etext)-1; + data_resource.start = __pa_symbol(_etext); + 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 @@ -782,11 +987,8 @@ void __init setup_arch(char **cmdline_p) x86_report_nx(); - /* Must be before kernel pagetables are setup */ - vmi_activate(); - /* after early param, so could get panic from serial */ - reserve_early_setup_data(); + memblock_x86_reserve_range_setup_data(); if (acpi_mps_check()) { #ifdef CONFIG_X86_LOCAL_APIC @@ -800,14 +1002,16 @@ void __init setup_arch(char **cmdline_p) early_dump_pci_devices(); #endif + /* update the e820_saved too */ + e820_reserve_setup_data(); finish_e820_parsing(); - if (efi_enabled) + if (efi_enabled(EFI_BOOT)) efi_init(); dmi_scan_machine(); - - dmi_check_system(bad_bios_dmi_table); + dmi_memdev_walk(); + dmi_set_dump_stack_arch_desc(); /* * VMware detection requires dmi to be available, so this @@ -822,7 +1026,8 @@ void __init setup_arch(char **cmdline_p) insert_resource(&iomem_resource, &data_resource); insert_resource(&iomem_resource, &bss_resource); - + e820_add_kernel_range(); + trim_bios_range(); #ifdef CONFIG_X86_32 if (ppro_with_ram_bug()) { e820_update_range(0x70000000ULL, 0x40000ULL, E820_RAM, @@ -841,8 +1046,6 @@ void __init setup_arch(char **cmdline_p) */ max_pfn = e820_end_of_ram_pfn(); - /* preallocate 4k for mptable mpc */ - early_reserve_e820_mpc_new(); /* update e820 for memory not covered by WB MTRRs */ mtrr_bp_init(); if (mtrr_trim_uncached_memory(max_pfn)) @@ -852,8 +1055,6 @@ void __init setup_arch(char **cmdline_p) /* max_low_pfn get updated here */ find_low_pfn_range(); #else - num_physpages = max_pfn; - check_x2apic(); /* How many end-of-memory variables you have, grandma! */ @@ -864,47 +1065,62 @@ void __init setup_arch(char **cmdline_p) max_low_pfn = max_pfn; high_memory = (void *)__va(max_pfn * PAGE_SIZE - 1) + 1; - max_pfn_mapped = KERNEL_IMAGE_SIZE >> PAGE_SHIFT; #endif -#ifdef CONFIG_X86_CHECK_BIOS_CORRUPTION - setup_bios_corruption_check(); -#endif + /* + * Find and reserve possible boot-time SMP configuration: + */ + find_smp_config(); - printk(KERN_DEBUG "initial memory mapped : 0 - %08lx\n", - max_pfn_mapped<<PAGE_SHIFT); + reserve_ibft_region(); - reserve_brk(); + early_alloc_pgt_buf(); /* - * Find and reserve possible boot-time SMP configuration: + * Need to conclude brk, before memblock_x86_fill() + * it could use memblock_find_in_range, could overlap with + * brk area. */ - find_smp_config(); + reserve_brk(); - reserve_trampoline_memory(); + cleanup_highmap(); + + memblock_set_current_limit(ISA_END_ADDRESS); + memblock_x86_fill(); -#ifdef CONFIG_ACPI_SLEEP /* - * Reserve low memory region for sleep support. - * even before init_memory_mapping + * The EFI specification says that boot service code won't be called + * after ExitBootServices(). This is, in fact, a lie. */ - acpi_reserve_wakeup_memory(); -#endif - init_gbpages(); + if (efi_enabled(EFI_MEMMAP)) + efi_reserve_boot_services(); - /* max_pfn_mapped is updated here */ - max_low_pfn_mapped = init_memory_mapping(0, max_low_pfn<<PAGE_SHIFT); - max_pfn_mapped = max_low_pfn_mapped; + /* preallocate 4k for mptable mpc */ + early_reserve_e820_mpc_new(); -#ifdef CONFIG_X86_64 - if (max_pfn > max_low_pfn) { - max_pfn_mapped = init_memory_mapping(1UL<<32, - max_pfn<<PAGE_SHIFT); - /* can we preseve max_low_pfn ?*/ - max_low_pfn = max_pfn; - } +#ifdef CONFIG_X86_CHECK_BIOS_CORRUPTION + setup_bios_corruption_check(); +#endif + +#ifdef CONFIG_X86_32 + printk(KERN_DEBUG "initial memory mapped: [mem 0x00000000-%#010lx]\n", + (max_pfn_mapped<<PAGE_SHIFT) - 1); #endif + reserve_real_mode(); + + trim_platform_memory_ranges(); + trim_low_memory_range(); + + init_mem_mapping(); + + early_trap_pf_init(); + + setup_real_mode(); + + memblock_set_current_limit(get_max_mapped()); + dma_contiguous_reserve(max_pfn_mapped << PAGE_SHIFT); + /* * NOTE: On x86-32, only from this point on, fixmaps are ready for use. */ @@ -913,10 +1129,14 @@ void __init setup_arch(char **cmdline_p) if (init_ohci1394_dma_early) init_ohci1394_dma_on_all_controllers(); #endif + /* Allocate bigger log buffer */ + setup_log_buf(1); reserve_initrd(); - reserve_crashkernel(); +#if defined(CONFIG_ACPI) && defined(CONFIG_BLK_DEV_INITRD) + acpi_initrd_override((void *)initrd_start, initrd_end - initrd_start); +#endif vsmp_init(); @@ -929,38 +1149,35 @@ void __init setup_arch(char **cmdline_p) early_acpi_boot_init(); -#ifdef CONFIG_ACPI_NUMA - /* - * Parse SRAT to discover nodes. - */ - acpi = acpi_numa_init(); -#endif - -#ifdef CONFIG_K8_NUMA - if (!acpi) - k8 = !k8_numa_init(0, max_pfn); -#endif - - initmem_init(0, max_pfn, acpi, k8); + initmem_init(); -#ifdef CONFIG_X86_64 /* - * dma32_reserve_bootmem() allocates bootmem which may conflict - * with the crashkernel command line, so do that after - * reserve_crashkernel() + * Reserve memory for crash kernel after SRAT is parsed so that it + * won't consume hotpluggable memory. */ - dma32_reserve_bootmem(); -#endif + reserve_crashkernel(); - reserve_ibft_region(); + memblock_find_dma_reserve(); -#ifdef CONFIG_KVM_CLOCK +#ifdef CONFIG_KVM_GUEST kvmclock_init(); #endif - x86_init.paging.pagetable_setup_start(swapper_pg_dir); - paging_init(); - x86_init.paging.pagetable_setup_done(swapper_pg_dir); + x86_init.paging.pagetable_init(); + + if (boot_cpu_data.cpuid_level >= 0) { + /* A CPU has %cr4 if and only if it has CPUID */ + mmu_cr4_features = read_cr4(); + if (trampoline_cr4_features) + *trampoline_cr4_features = mmu_cr4_features; + } + +#ifdef CONFIG_X86_32 + /* sync back kernel address range */ + clone_pgd_range(initial_page_table + KERNEL_PGD_BOUNDARY, + swapper_pg_dir + KERNEL_PGD_BOUNDARY, + KERNEL_PGD_PTRS); +#endif tboot_probe(); @@ -976,8 +1193,8 @@ void __init setup_arch(char **cmdline_p) * Read APIC and some other early information from ACPI tables. */ acpi_boot_init(); - sfi_init(); + x86_dtb_init(); /* * get boot-time SMP configuration: @@ -987,15 +1204,11 @@ void __init setup_arch(char **cmdline_p) prefill_possible_map(); -#ifdef CONFIG_X86_64 init_cpu_to_node(); -#endif init_apic_mappings(); - ioapic_init_mappings(); - - /* need to wait for io_apic is mapped */ - probe_nr_irqs_gsi(); + if (x86_io_apic_ops.init) + x86_io_apic_ops.init(); kvm_guest_init(); @@ -1008,7 +1221,7 @@ void __init setup_arch(char **cmdline_p) #ifdef CONFIG_VT #if defined(CONFIG_VGA_CONSOLE) - if (!efi_enabled || (efi_mem_type(0xa0000) != EFI_CONVENTIONAL_MEMORY)) + if (!efi_enabled(EFI_BOOT) || (efi_mem_type(0xa0000) != EFI_CONVENTIONAL_MEMORY)) conswitchp = &vga_con; #elif defined(CONFIG_DUMMY_CONSOLE) conswitchp = &dummy_con; @@ -1016,7 +1229,18 @@ void __init setup_arch(char **cmdline_p) #endif x86_init.oem.banner(); + x86_init.timers.wallclock_init(); + mcheck_init(); + + arch_init_ideal_nops(); + + register_refined_jiffies(CLOCK_TICK_RATE); + +#ifdef CONFIG_EFI + if (efi_enabled(EFI_BOOT)) + efi_apply_memmap_quirks(); +#endif } #ifdef CONFIG_X86_32 @@ -1035,3 +1259,15 @@ void __init i386_reserve_resources(void) } #endif /* CONFIG_X86_32 */ + +static struct notifier_block kernel_offset_notifier = { + .notifier_call = dump_kernel_offset +}; + +static int __init register_kernel_offset_dumper(void) +{ + atomic_notifier_chain_register(&panic_notifier_list, + &kernel_offset_notifier); + return 0; +} +__initcall(register_kernel_offset_dumper); |