#include <linux/screen_info.h>
#include <linux/ioport.h>
#include <linux/acpi.h>
+#include <linux/sfi.h>
#include <linux/apm_bios.h>
#include <linux/initrd.h>
#include <linux/bootmem.h>
#include <linux/percpu.h>
#include <linux/crash_dump.h>
+#include <linux/tboot.h>
#include <video/edid.h>
#include <asm/mtrr.h>
#include <asm/apic.h>
+#include <asm/trampoline.h>
#include <asm/e820.h>
#include <asm/mpspec.h>
#include <asm/setup.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/mce.h>
-#ifndef ARCH_SETUP
-#define ARCH_SETUP
-#endif
+/*
+ * 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.
+ */
+unsigned long max_low_pfn_mapped;
+unsigned long max_pfn_mapped;
+
+RESERVE_BRK(dmi_alloc, 65536);
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;
+
#ifdef CONFIG_X86_64
int default_cpu_present_to_apicid(int mps_cpu)
{
return __default_cpu_present_to_apicid(mps_cpu);
}
-int default_check_phys_apicid_present(int boot_cpu_physical_apicid)
+int default_check_phys_apicid_present(int phys_apicid)
{
- return __default_check_phys_apicid_present(boot_cpu_physical_apicid);
+ return __default_check_phys_apicid_present(phys_apicid);
}
#endif
#ifdef CONFIG_X86_32
-/* This value is set up by the early boot code to point to the value
- immediately after the boot time page tables. It contains a *physical*
- address, and must not be in the .bss segment! */
-unsigned long init_pg_tables_start __initdata = ~0UL;
-unsigned long init_pg_tables_end __initdata = ~0UL;
-
-static struct resource video_ram_resource = {
- .name = "Video RAM area",
- .start = 0xa0000,
- .end = 0xbffff,
- .flags = IORESOURCE_BUSY | IORESOURCE_MEM
-};
-
/* 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};
/* common cpu data for all cpus */
#endif
#else
-struct cpuinfo_x86 boot_cpu_data __read_mostly;
+struct cpuinfo_x86 boot_cpu_data __read_mostly = {
+ .x86_phys_bits = MAX_PHYSMEM_BITS,
+};
EXPORT_SYMBOL(boot_cpu_data);
#endif
unsigned long mmu_cr4_features = X86_CR4_PAE;
#endif
-/* Boot loader ID as an integer, for the benefit of proc_dointvec */
-int bootloader_type;
-
-/*
- * Early DMI memory
- */
-int dmi_alloc_index;
-char dmi_alloc_data[DMI_MAX_DATA];
+/* Boot loader ID and version as integers, for the benefit of proc_dointvec */
+int bootloader_type, bootloader_version;
/*
* Setup options
* from boot_params into a safe place.
*
*/
-static inline void copy_edd(void)
+static inline void __init copy_edd(void)
{
memcpy(edd.mbr_signature, boot_params.edd_mbr_sig_buffer,
sizeof(edd.mbr_signature));
edd.edd_info_nr = boot_params.eddbuf_entries;
}
#else
-static inline void copy_edd(void)
+static inline void __init copy_edd(void)
{
}
#endif
-#ifdef CONFIG_BLK_DEV_INITRD
+void * __init extend_brk(size_t size, size_t align)
+{
+ size_t mask = align - 1;
+ void *ret;
-#ifdef CONFIG_X86_32
+ BUG_ON(_brk_start == 0);
+ BUG_ON(align & mask);
+
+ _brk_end = (_brk_end + mask) & ~mask;
+ BUG_ON((char *)(_brk_end + size) > __brk_limit);
+
+ ret = (void *)_brk_end;
+ _brk_end += size;
+
+ memset(ret, 0, size);
+
+ 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)
+{
+}
+#endif
+
+static void __init reserve_brk(void)
+{
+ if (_brk_end > _brk_start)
+ reserve_early(__pa(_brk_start), __pa(_brk_end), "BRK");
+
+ /* Mark brk area as locked down and no longer taking any
+ new allocations */
+ _brk_start = 0;
+}
+
+#ifdef CONFIG_BLK_DEV_INITRD
#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 << PAGE_SHIFT;
+ u64 end_of_lowmem = max_low_pfn_mapped << PAGE_SHIFT;
u64 ramdisk_here;
unsigned long slop, clen, mapaddr;
char *p, *q;
ramdisk_image, ramdisk_image + ramdisk_size - 1,
ramdisk_here, ramdisk_here + ramdisk_size - 1);
}
-#endif
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 << PAGE_SHIFT;
+ u64 end_of_lowmem = max_low_pfn_mapped << PAGE_SHIFT;
if (!boot_params.hdr.type_of_loader ||
!ramdisk_image || !ramdisk_size)
return;
}
-#ifdef CONFIG_X86_32
relocate_initrd();
-#else
- printk(KERN_ERR "initrd extends beyond end of memory "
- "(0x%08llx > 0x%08llx)\ndisabling initrd\n",
- ramdisk_end, end_of_lowmem);
- initrd_start = 0;
-#endif
+
free_early(ramdisk_image, ramdisk_end);
}
#else
#ifdef CONFIG_KEXEC
-/**
- * Reserve @size bytes of crashkernel memory at any suitable offset.
- *
- * @size: Size of the crashkernel memory to reserve.
- * Returns the base address on success, and -1ULL on failure.
- */
-static
-unsigned long long __init find_and_reserve_crashkernel(unsigned long long size)
-{
- const unsigned long long alignment = 16<<20; /* 16M */
- unsigned long long start = 0LL;
-
- while (1) {
- int ret;
-
- start = find_e820_area(start, ULONG_MAX, size, alignment);
- if (start == -1ULL)
- return start;
-
- /* try to reserve it */
- ret = reserve_bootmem_generic(start, size, BOOTMEM_EXCLUSIVE);
- if (ret >= 0)
- return start;
-
- start += alignment;
- }
-}
-
static inline unsigned long long get_total_mem(void)
{
unsigned long long total;
- total = max_low_pfn - min_low_pfn;
-#ifdef CONFIG_HIGHMEM
- total += highend_pfn - highstart_pfn;
-#endif
+ total = max_pfn - min_low_pfn;
return total << PAGE_SHIFT;
}
/* 0 means: find the address automatically */
if (crash_base <= 0) {
- crash_base = find_and_reserve_crashkernel(crash_size);
+ const unsigned long long alignment = 16<<20; /* 16M */
+
+ crash_base = find_e820_area(alignment, ULONG_MAX, crash_size,
+ alignment);
if (crash_base == -1ULL) {
- pr_info("crashkernel reservation failed. "
- "No suitable area found.\n");
+ pr_info("crashkernel reservation failed - No suitable area found.\n");
return;
}
} else {
- ret = reserve_bootmem_generic(crash_base, crash_size,
- BOOTMEM_EXCLUSIVE);
- if (ret < 0) {
- pr_info("crashkernel reservation failed - "
- "memory is in use\n");
+ unsigned long long start;
+
+ start = find_e820_area(crash_base, ULONG_MAX, 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");
printk(KERN_INFO "Reserving %ldMB of memory at %ldMB "
"for crashkernel (System RAM: %ldMB)\n",
.flags = IORESOURCE_BUSY | IORESOURCE_IO }
};
-static void __init reserve_standard_io_resources(void)
+void __init reserve_standard_io_resources(void)
{
int i;
early_param("elfcorehdr", setup_elfcorehdr);
#endif
-static int __init default_update_apic(void)
-{
-#ifdef CONFIG_SMP
- if (!apic->wakeup_cpu)
- apic->wakeup_cpu = wakeup_secondary_cpu_via_init;
-#endif
-
- return 0;
-}
-
-static struct x86_quirks default_x86_quirks __initdata = {
- .update_apic = default_update_apic,
-};
-
-struct x86_quirks *x86_quirks __initdata = &default_x86_quirks;
-
#ifdef CONFIG_X86_RESERVE_LOW_64K
static int __init dmi_low_memory_corruption(const struct dmi_system_id *d)
{
DMI_MATCH(DMI_BIOS_VENDOR, "Phoenix Technologies"),
},
},
+ {
+ .callback = dmi_low_memory_corruption,
+ .ident = "Phoenix/MSC BIOS",
+ .matches = {
+ DMI_MATCH(DMI_BIOS_VENDOR, "Phoenix/MSC"),
+ },
+ },
+ {
+ /*
+ * 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.
+ */
+ .callback = dmi_low_memory_corruption,
+ .ident = "AMI BIOS",
+ .matches = {
+ DMI_MATCH(DMI_BOARD_NAME, "DG45ID"),
+ },
+ },
#endif
{}
};
void __init setup_arch(char **cmdline_p)
{
+ int acpi = 0;
+ int k8 = 0;
+
#ifdef CONFIG_X86_32
memcpy(&boot_cpu_data, &new_cpu_data, sizeof(new_cpu_data));
visws_early_detect();
#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
- ARCH_SETUP
+ x86_init.oem.arch_setup();
setup_memory_map();
parse_setup_data();
init_mm.start_code = (unsigned long) _text;
init_mm.end_code = (unsigned long) _etext;
init_mm.end_data = (unsigned long) _edata;
-#ifdef CONFIG_X86_32
- init_mm.brk = init_pg_tables_end + PAGE_OFFSET;
-#else
- init_mm.brk = (unsigned long) &_end;
-#endif
+ init_mm.brk = _brk_end;
code_resource.start = virt_to_phys(_text);
code_resource.end = virt_to_phys(_etext)-1;
strlcpy(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
+ * console setup can safely call set_fixmap()). It may then be called
+ * again from within noexec_setup() during parsing early parameters
+ * to honor the respective command line option.
+ */
+ x86_configure_nx();
+
parse_early_param();
-#ifdef CONFIG_X86_64
- check_efer();
-#endif
+ x86_report_nx();
/* Must be before kernel pagetables are setup */
vmi_activate();
finish_e820_parsing();
+ if (efi_enabled)
+ efi_init();
+
dmi_scan_machine();
dmi_check_system(bad_bios_dmi_table);
* VMware detection requires dmi to be available, so this
* needs to be done after dmi_scan_machine, for the BP.
*/
- init_hypervisor(&boot_cpu_data);
+ init_hypervisor_platform();
-#ifdef CONFIG_X86_32
- probe_roms();
-#endif
+ x86_init.resources.probe_roms();
/* after parse_early_param, so could debug it */
insert_resource(&iomem_resource, &code_resource);
insert_resource(&iomem_resource, &data_resource);
insert_resource(&iomem_resource, &bss_resource);
- if (efi_enabled)
- efi_init();
#ifdef CONFIG_X86_32
if (ppro_with_ram_bug()) {
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
+ printk(KERN_DEBUG "initial memory mapped : 0 - %08lx\n",
+ max_pfn_mapped<<PAGE_SHIFT);
+
+ reserve_brk();
+
+ /*
+ * Find and reserve possible boot-time SMP configuration:
+ */
+ find_smp_config();
+
+ reserve_trampoline_memory();
+
+#ifdef CONFIG_ACPI_SLEEP
+ /*
+ * Reserve low memory region for sleep support.
+ * even before init_memory_mapping
+ */
+ acpi_reserve_wakeup_memory();
+#endif
+ init_gbpages();
+
/* 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;
reserve_initrd();
-#ifdef CONFIG_X86_64
+ reserve_crashkernel();
+
vsmp_init();
-#endif
io_delay_init();
/*
* Parse SRAT to discover nodes.
*/
- acpi_numa_init();
+ acpi = acpi_numa_init();
#endif
- initmem_init(0, max_pfn);
-
-#ifdef CONFIG_ACPI_SLEEP
- /*
- * Reserve low memory region for sleep support.
- */
- acpi_reserve_bootmem();
+#ifdef CONFIG_K8_NUMA
+ if (!acpi)
+ k8 = !k8_numa_init(0, max_pfn);
#endif
- /*
- * Find and reserve possible boot-time SMP configuration:
- */
- find_smp_config();
- reserve_crashkernel();
+ initmem_init(0, max_pfn, acpi, k8);
#ifdef CONFIG_X86_64
/*
kvmclock_init();
#endif
- paravirt_pagetable_setup_start(swapper_pg_dir);
+ x86_init.paging.pagetable_setup_start(swapper_pg_dir);
paging_init();
- paravirt_pagetable_setup_done(swapper_pg_dir);
- paravirt_post_allocator_init();
+ x86_init.paging.pagetable_setup_done(swapper_pg_dir);
+
+ tboot_probe();
#ifdef CONFIG_X86_64
map_vsyscall();
*/
acpi_boot_init();
-#if defined(CONFIG_X86_MPPARSE) || defined(CONFIG_X86_VISWS)
+ sfi_init();
+
/*
* get boot-time SMP configuration:
*/
if (smp_found_config)
get_smp_config();
-#endif
prefill_possible_map();
e820_reserve_resources();
e820_mark_nosave_regions(max_low_pfn);
-#ifdef CONFIG_X86_32
- request_resource(&iomem_resource, &video_ram_resource);
-#endif
- reserve_standard_io_resources();
+ x86_init.resources.reserve_resources();
e820_setup_gap();
conswitchp = &dummy_con;
#endif
#endif
-}
-
-#ifdef CONFIG_X86_32
-
-/**
- * x86_quirk_pre_intr_init - initialisation prior to setting up interrupt vectors
- *
- * Description:
- * Perform any necessary interrupt initialisation prior to setting up
- * the "ordinary" interrupt call gates. For legacy reasons, the ISA
- * interrupts should be initialised here if the machine emulates a PC
- * in any way.
- **/
-void __init x86_quirk_pre_intr_init(void)
-{
- if (x86_quirks->arch_pre_intr_init) {
- if (x86_quirks->arch_pre_intr_init())
- return;
- }
- init_ISA_irqs();
-}
+ x86_init.oem.banner();
-/**
- * x86_quirk_intr_init - post gate setup interrupt initialisation
- *
- * Description:
- * Fill in any interrupts that may have been left out by the general
- * init_IRQ() routine. interrupts having to do with the machine rather
- * than the devices on the I/O bus (like APIC interrupts in intel MP
- * systems) are started here.
- **/
-void __init x86_quirk_intr_init(void)
-{
- if (x86_quirks->arch_intr_init) {
- if (x86_quirks->arch_intr_init())
- return;
- }
+ mcheck_init();
}
-/**
- * x86_quirk_trap_init - initialise system specific traps
- *
- * Description:
- * Called as the final act of trap_init(). Used in VISWS to initialise
- * the various board specific APIC traps.
- **/
-void __init x86_quirk_trap_init(void)
-{
- if (x86_quirks->arch_trap_init) {
- if (x86_quirks->arch_trap_init())
- return;
- }
-}
+#ifdef CONFIG_X86_32
-static struct irqaction irq0 = {
- .handler = timer_interrupt,
- .flags = IRQF_DISABLED | IRQF_NOBALANCING | IRQF_IRQPOLL | IRQF_TIMER,
- .mask = CPU_MASK_NONE,
- .name = "timer"
+static struct resource video_ram_resource = {
+ .name = "Video RAM area",
+ .start = 0xa0000,
+ .end = 0xbffff,
+ .flags = IORESOURCE_BUSY | IORESOURCE_MEM
};
-/**
- * x86_quirk_pre_time_init - do any specific initialisations before.
- *
- **/
-void __init x86_quirk_pre_time_init(void)
+void __init i386_reserve_resources(void)
{
- if (x86_quirks->arch_pre_time_init)
- x86_quirks->arch_pre_time_init();
+ request_resource(&iomem_resource, &video_ram_resource);
+ reserve_standard_io_resources();
}
-/**
- * x86_quirk_time_init - do any specific initialisations for the system timer.
- *
- * Description:
- * Must plug the system timer interrupt source at HZ into the IRQ listed
- * in irq_vectors.h:TIMER_IRQ
- **/
-void __init x86_quirk_time_init(void)
-{
- if (x86_quirks->arch_time_init) {
- /*
- * A nonzero return code does not mean failure, it means
- * that the architecture quirk does not want any
- * generic (timer) setup to be performed after this:
- */
- if (x86_quirks->arch_time_init())
- return;
- }
-
- irq0.mask = cpumask_of_cpu(0);
- setup_irq(0, &irq0);
-}
#endif /* CONFIG_X86_32 */