#include <linux/ptrace.h>
#include <linux/slab.h>
#include <linux/user.h>
-#include <linux/a.out.h>
#include <linux/screen_info.h>
#include <linux/ioport.h>
#include <linux/delay.h>
#include <linux/crash_dump.h>
#include <linux/root_dev.h>
#include <linux/pci.h>
+#include <linux/efi.h>
#include <linux/acpi.h>
#include <linux/kallsyms.h>
#include <linux/edd.h>
#include <linux/dma-mapping.h>
#include <linux/ctype.h>
#include <linux/uaccess.h>
+#include <linux/init_ohci1394_dma.h>
#include <asm/mtrr.h>
#include <asm/uaccess.h>
#include <asm/system.h>
+#include <asm/vsyscall.h>
#include <asm/io.h>
#include <asm/smp.h>
#include <asm/msr.h>
#include <video/edid.h>
#include <asm/e820.h>
#include <asm/dma.h>
+#include <asm/gart.h>
#include <asm/mpspec.h>
#include <asm/mmu_context.h>
#include <asm/proto.h>
#include <asm/cacheflush.h>
#include <asm/mce.h>
#include <asm/ds.h>
+#include <asm/topology.h>
#ifdef CONFIG_PARAVIRT
#include <asm/paravirt.h>
struct cpuinfo_x86 boot_cpu_data __read_mostly;
EXPORT_SYMBOL(boot_cpu_data);
+__u32 cleared_cpu_caps[NCAPINTS] __cpuinitdata;
+
unsigned long mmu_cr4_features;
/* Boot loader ID as an integer, for the benefit of proc_dointvec */
unsigned long bootmap_size, bootmap;
bootmap_size = bootmem_bootmap_pages(end_pfn)<<PAGE_SHIFT;
- bootmap = find_e820_area(0, end_pfn<<PAGE_SHIFT, bootmap_size);
+ bootmap = find_e820_area(0, end_pfn<<PAGE_SHIFT, bootmap_size,
+ PAGE_SIZE);
if (bootmap == -1L)
panic("Cannot find bootmem map of size %ld\n", bootmap_size);
bootmap_size = init_bootmem(bootmap >> PAGE_SHIFT, end_pfn);
e820_register_active_regions(0, start_pfn, end_pfn);
free_bootmem_with_active_regions(0, end_pfn);
- reserve_bootmem(bootmap, bootmap_size);
+ reserve_bootmem(bootmap, bootmap_size, BOOTMEM_DEFAULT);
}
#endif
#ifdef CONFIG_KEXEC
static void __init reserve_crashkernel(void)
{
- unsigned long long free_mem;
+ unsigned long long total_mem;
unsigned long long crash_size, crash_base;
int ret;
- free_mem =
- ((unsigned long long)max_low_pfn - min_low_pfn) << PAGE_SHIFT;
+ total_mem = ((unsigned long long)max_low_pfn - min_low_pfn) << PAGE_SHIFT;
- ret = parse_crashkernel(boot_command_line, free_mem,
+ ret = parse_crashkernel(boot_command_line, total_mem,
&crash_size, &crash_base);
if (ret == 0 && crash_size) {
- if (crash_base > 0) {
- printk(KERN_INFO "Reserving %ldMB of memory at %ldMB "
- "for crashkernel (System RAM: %ldMB)\n",
- (unsigned long)(crash_size >> 20),
- (unsigned long)(crash_base >> 20),
- (unsigned long)(free_mem >> 20));
- crashk_res.start = crash_base;
- crashk_res.end = crash_base + crash_size - 1;
- reserve_bootmem(crash_base, crash_size);
- } else
+ if (crash_base <= 0) {
printk(KERN_INFO "crashkernel reservation failed - "
"you have to specify a base address\n");
+ return;
+ }
+
+ if (reserve_bootmem(crash_base, crash_size,
+ BOOTMEM_EXCLUSIVE) < 0) {
+ printk(KERN_INFO "crashkernel reservation failed - "
+ "memory is in use\n");
+ return;
+ }
+
+ printk(KERN_INFO "Reserving %ldMB of memory at %ldMB "
+ "for crashkernel (System RAM: %ldMB)\n",
+ (unsigned long)(crash_size >> 20),
+ (unsigned long)(crash_base >> 20),
+ (unsigned long)(total_mem >> 20));
+ crashk_res.start = crash_base;
+ crashk_res.end = crash_base + crash_size - 1;
}
}
#else
{}
#endif
-#define EBDA_ADDR_POINTER 0x40E
-
-unsigned __initdata ebda_addr;
-unsigned __initdata ebda_size;
-
-static void discover_ebda(void)
-{
- /*
- * there is a real-mode segmented pointer pointing to the
- * 4K EBDA area at 0x40E
- */
- ebda_addr = *(unsigned short *)__va(EBDA_ADDR_POINTER);
- /*
- * There can be some situations, like paravirtualized guests,
- * in which there is no available ebda information. In such
- * case, just skip it
- */
- if (!ebda_addr) {
- ebda_size = 0;
- return;
- }
-
- ebda_addr <<= 4;
-
- ebda_size = *(unsigned short *)__va(ebda_addr);
-
- /* Round EBDA up to pages */
- if (ebda_size == 0)
- ebda_size = 1;
- ebda_size <<= 10;
- ebda_size = round_up(ebda_size + (ebda_addr & ~PAGE_MASK), PAGE_SIZE);
- if (ebda_size > 64*1024)
- ebda_size = 64*1024;
-}
-
/* Overridden in paravirt.c if CONFIG_PARAVIRT */
-void __attribute__((weak)) memory_setup(void)
+void __attribute__((weak)) __init memory_setup(void)
{
machine_specific_memory_setup();
}
+/*
+ * setup_arch - architecture-specific boot-time initializations
+ *
+ * Note: On x86_64, fixmaps are ready for use even before this is called.
+ */
void __init setup_arch(char **cmdline_p)
{
unsigned i;
rd_prompt = ((boot_params.hdr.ram_size & RAMDISK_PROMPT_FLAG) != 0);
rd_doload = ((boot_params.hdr.ram_size & RAMDISK_LOAD_FLAG) != 0);
#endif
+#ifdef CONFIG_EFI
+ if (!strncmp((char *)&boot_params.efi_info.efi_loader_signature,
+ "EL64", 4))
+ efi_enabled = 1;
+#endif
ARCH_SETUP
parse_early_param();
+#ifdef CONFIG_PROVIDE_OHCI1394_DMA_INIT
+ if (init_ohci1394_dma_early)
+ init_ohci1394_dma_on_all_controllers();
+#endif
+
finish_e820_parsing();
+ early_gart_iommu_check();
+
e820_register_active_regions(0, 0, -1UL);
/*
* partially used pages are not usable - thus
* we are rounding upwards:
*/
end_pfn = e820_end_of_ram();
+ /* update e820 for memory not covered by WB MTRRs */
+ mtrr_bp_init();
+ if (mtrr_trim_uncached_memory(end_pfn)) {
+ e820_register_active_regions(0, 0, -1UL);
+ end_pfn = e820_end_of_ram();
+ }
+
num_physpages = end_pfn;
check_efer();
- discover_ebda();
-
init_memory_mapping(0, (end_pfn_map << PAGE_SHIFT));
+ if (efi_enabled)
+ efi_init();
dmi_scan_machine();
io_delay_init();
#ifdef CONFIG_SMP
- /* setup to use the static apicid table during kernel startup */
- x86_cpu_to_apicid_ptr = (void *)&x86_cpu_to_apicid_init;
+ /* setup to use the early static init tables during kernel startup */
+ x86_cpu_to_apicid_early_ptr = (void *)x86_cpu_to_apicid_init;
+ x86_bios_cpu_apicid_early_ptr = (void *)x86_bios_cpu_apicid_init;
+#ifdef CONFIG_NUMA
+ x86_cpu_to_node_map_early_ptr = (void *)x86_cpu_to_node_map_init;
+#endif
#endif
#ifdef CONFIG_ACPI
contig_initmem_init(0, end_pfn);
#endif
- /* Reserve direct mapping */
- reserve_bootmem_generic(table_start << PAGE_SHIFT,
- (table_end - table_start) << PAGE_SHIFT);
-
- /* reserve kernel */
- reserve_bootmem_generic(__pa_symbol(&_text),
- __pa_symbol(&_end) - __pa_symbol(&_text));
-
- /*
- * reserve physical page 0 - it's a special BIOS page on many boxes,
- * enabling clean reboots, SMP operation, laptop functions.
- */
- reserve_bootmem_generic(0, PAGE_SIZE);
-
- /* reserve ebda region */
- if (ebda_addr)
- reserve_bootmem_generic(ebda_addr, ebda_size);
-#ifdef CONFIG_NUMA
- /* reserve nodemap region */
- if (nodemap_addr)
- reserve_bootmem_generic(nodemap_addr, nodemap_size);
-#endif
-
-#ifdef CONFIG_SMP
- /* Reserve SMP trampoline */
- reserve_bootmem_generic(SMP_TRAMPOLINE_BASE, 2*PAGE_SIZE);
-#endif
+ early_res_to_bootmem();
#ifdef CONFIG_ACPI_SLEEP
/*
*/
acpi_reserve_bootmem();
#endif
+
+ if (efi_enabled)
+ efi_reserve_bootmem();
+
/*
* Find and reserve possible boot-time SMP configuration:
*/
initrd_start = ramdisk_image + PAGE_OFFSET;
initrd_end = initrd_start+ramdisk_size;
} else {
+ /* Assumes everything on node 0 */
+ free_bootmem(ramdisk_image, ramdisk_size);
printk(KERN_ERR "initrd extends beyond end of memory "
"(0x%08lx > 0x%08lx)\ndisabling initrd\n",
ramdisk_end, end_of_mem);
#endif
reserve_crashkernel();
paging_init();
+ map_vsyscall();
early_quirks();
- /*
- * set this early, so we dont allocate cpu0
- * if MADT list doesnt list BSP first
- * mpparse.c/MP_processor_info() allocates logical cpu numbers.
- */
- cpu_set(0, cpu_present_map);
#ifdef CONFIG_ACPI
/*
* Read APIC and some other early information from ACPI tables.
#ifdef CONFIG_VT
#if defined(CONFIG_VGA_CONSOLE)
- conswitchp = &vga_con;
+ if (!efi_enabled || (efi_mem_type(0xa0000) != EFI_CONVENTIONAL_MEMORY))
+ conswitchp = &vga_con;
#elif defined(CONFIG_DUMMY_CONSOLE)
conswitchp = &dummy_con;
#endif
printk(KERN_INFO "CPU: L2 Cache: %dK (%d bytes/line)\n",
c->x86_cache_size, ecx & 0xFF);
}
-
- if (n >= 0x80000007)
- cpuid(0x80000007, &dummy, &dummy, &dummy, &c->x86_power);
if (n >= 0x80000008) {
cpuid(0x80000008, &eax, &dummy, &dummy, &dummy);
c->x86_virt_bits = (eax >> 8) & 0xff;
}
#ifdef CONFIG_NUMA
-static int nearby_node(int apicid)
+static int __cpuinit nearby_node(int apicid)
{
int i, node;
* On a AMD dual core setup the lower bits of the APIC id distingush the cores.
* Assumes number of cores is a power of two.
*/
-static void __init amd_detect_cmp(struct cpuinfo_x86 *c)
+static void __cpuinit amd_detect_cmp(struct cpuinfo_x86 *c)
{
#ifdef CONFIG_SMP
unsigned bits;
#endif
}
-static void __cpuinit early_init_amd(struct cpuinfo_x86 *c)
+static void __cpuinit early_init_amd_mc(struct cpuinfo_x86 *c)
{
#ifdef CONFIG_SMP
unsigned bits, ecx;
return 0;
}
+static void __cpuinit early_init_amd(struct cpuinfo_x86 *c)
+{
+ early_init_amd_mc(c);
+
+ /* c->x86_power is 8000_0007 edx. Bit 8 is constant TSC */
+ if (c->x86_power & (1<<8))
+ set_cpu_cap(c, X86_FEATURE_CONSTANT_TSC);
+}
+
static void __cpuinit init_amd(struct cpuinfo_x86 *c)
{
unsigned level;
}
display_cacheinfo(c);
- /* c->x86_power is 8000_0007 edx. Bit 8 is constant TSC */
- if (c->x86_power & (1<<8))
- set_cpu_cap(c, X86_FEATURE_CONSTANT_TSC);
-
/* Multi core CPU? */
if (c->extended_cpuid_level >= 0x80000008)
amd_detect_cmp(c);
if (c->x86 == 0xf || c->x86 == 0x10 || c->x86 == 0x11)
set_cpu_cap(c, X86_FEATURE_K8);
- /* RDTSC can be speculated around */
- clear_cpu_cap(c, X86_FEATURE_SYNC_RDTSC);
-
- /* Family 10 doesn't support C states in MWAIT so don't use it */
- if (c->x86 == 0x10 && !force_mwait)
- clear_cpu_cap(c, X86_FEATURE_MWAIT);
+ /* MFENCE stops RDTSC speculation */
+ set_cpu_cap(c, X86_FEATURE_MFENCE_RDTSC);
if (amd_apic_timer_broken())
disable_apic_timer = 1;
}
-static void __cpuinit detect_ht(struct cpuinfo_x86 *c)
+void __cpuinit detect_ht(struct cpuinfo_x86 *c)
{
#ifdef CONFIG_SMP
u32 eax, ebx, ecx, edx;
return 1;
}
-static void srat_detect_node(void)
+static void __cpuinit srat_detect_node(void)
{
#ifdef CONFIG_NUMA
unsigned node;
/* Don't do the funky fallback heuristics the AMD version employs
for now. */
node = apicid_to_node[apicid];
- if (node == NUMA_NO_NODE)
+ if (node == NUMA_NO_NODE || !node_online(node))
node = first_node(node_online_map);
numa_set_node(cpu, node);
#endif
}
+static void __cpuinit early_init_intel(struct cpuinfo_x86 *c)
+{
+ if ((c->x86 == 0xf && c->x86_model >= 0x03) ||
+ (c->x86 == 0x6 && c->x86_model >= 0x0e))
+ set_bit(X86_FEATURE_CONSTANT_TSC, &c->x86_capability);
+}
+
static void __cpuinit init_intel(struct cpuinfo_x86 *c)
{
/* Cache sizes */
set_cpu_cap(c, X86_FEATURE_CONSTANT_TSC);
if (c->x86 == 6)
set_cpu_cap(c, X86_FEATURE_REP_GOOD);
- if (c->x86 == 15)
- set_cpu_cap(c, X86_FEATURE_SYNC_RDTSC);
- else
- clear_cpu_cap(c, X86_FEATURE_SYNC_RDTSC);
+ set_cpu_cap(c, X86_FEATURE_LFENCE_RDTSC);
c->x86_max_cores = intel_num_cpu_cores(c);
srat_detect_node();
c->x86_vendor = X86_VENDOR_UNKNOWN;
}
-struct cpu_model_info {
- int vendor;
- int family;
- char *model_names[16];
-};
-
/* Do some early cpuid on the boot CPU to get some parameter that are
needed before check_bugs. Everything advanced is in identify_cpu
below. */
c->x86_capability[2] = cpuid_edx(0x80860001);
}
+ c->extended_cpuid_level = cpuid_eax(0x80000000);
+ if (c->extended_cpuid_level >= 0x80000007)
+ c->x86_power = cpuid_edx(0x80000007);
+
switch (c->x86_vendor) {
case X86_VENDOR_AMD:
early_init_amd(c);
break;
+ case X86_VENDOR_INTEL:
+ early_init_intel(c);
+ break;
}
}
break;
}
- select_idle_routine(c);
detect_ht(c);
/*
boot_cpu_data.x86_capability[i] &= c->x86_capability[i];
}
+ /* Clear all flags overriden by options */
+ for (i = 0; i < NCAPINTS; i++)
+ c->x86_capability[i] &= ~cleared_cpu_caps[i];
+
#ifdef CONFIG_X86_MCE
mcheck_init(c);
#endif
+ select_idle_routine(c);
+
if (c != &boot_cpu_data)
mtrr_ap_init();
#ifdef CONFIG_NUMA
numa_add_cpu(smp_processor_id());
#endif
+
}
+static __init int setup_noclflush(char *arg)
+{
+ setup_clear_cpu_cap(X86_FEATURE_CLFLSH);
+ return 1;
+}
+__setup("noclflush", setup_noclflush);
+
void __cpuinit print_cpu_info(struct cpuinfo_x86 *c)
{
if (c->x86_model_id[0])
- printk(KERN_INFO "%s", c->x86_model_id);
+ printk(KERN_CONT "%s", c->x86_model_id);
if (c->x86_mask || c->cpuid_level >= 0)
printk(KERN_CONT " stepping %02x\n", c->x86_mask);
printk(KERN_CONT "\n");
}
+static __init int setup_disablecpuid(char *arg)
+{
+ int bit;
+ if (get_option(&arg, &bit) && bit < NCAPINTS*32)
+ setup_clear_cpu_cap(bit);
+ else
+ return 0;
+ return 1;
+}
+__setup("clearcpuid=", setup_disablecpuid);
+
/*
* Get CPU information for use by the procfs.
*/
struct cpuinfo_x86 *c = v;
int cpu = 0, i;
- /*
- * These flag bits must match the definitions in <asm/cpufeature.h>.
- * NULL means this bit is undefined or reserved; either way it doesn't
- * have meaning as far as Linux is concerned. Note that it's important
- * to realize there is a difference between this table and CPUID -- if
- * applications want to get the raw CPUID data, they should access
- * /dev/cpu/<cpu_nr>/cpuid instead.
- */
- static const char *const x86_cap_flags[] = {
- /* Intel-defined */
- "fpu", "vme", "de", "pse", "tsc", "msr", "pae", "mce",
- "cx8", "apic", NULL, "sep", "mtrr", "pge", "mca", "cmov",
- "pat", "pse36", "pn", "clflush", NULL, "dts", "acpi", "mmx",
- "fxsr", "sse", "sse2", "ss", "ht", "tm", "ia64", "pbe",
-
- /* AMD-defined */
- NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
- NULL, NULL, NULL, "syscall", NULL, NULL, NULL, NULL,
- NULL, NULL, NULL, NULL, "nx", NULL, "mmxext", NULL,
- NULL, "fxsr_opt", "pdpe1gb", "rdtscp", NULL, "lm",
- "3dnowext", "3dnow",
-
- /* Transmeta-defined */
- "recovery", "longrun", NULL, "lrti", NULL, NULL, NULL, NULL,
- NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
- NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
- NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
-
- /* Other (Linux-defined) */
- "cxmmx", "k6_mtrr", "cyrix_arr", "centaur_mcr",
- NULL, NULL, NULL, NULL,
- "constant_tsc", "up", NULL, "arch_perfmon",
- "pebs", "bts", NULL, "sync_rdtsc",
- "rep_good", NULL, NULL, NULL, NULL, NULL, NULL, NULL,
- NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
-
- /* Intel-defined (#2) */
- "pni", NULL, NULL, "monitor", "ds_cpl", "vmx", "smx", "est",
- "tm2", "ssse3", "cid", NULL, NULL, "cx16", "xtpr", NULL,
- NULL, NULL, "dca", "sse4_1", "sse4_2", NULL, NULL, "popcnt",
- NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
-
- /* VIA/Cyrix/Centaur-defined */
- NULL, NULL, "rng", "rng_en", NULL, NULL, "ace", "ace_en",
- "ace2", "ace2_en", "phe", "phe_en", "pmm", "pmm_en", NULL, NULL,
- NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
- NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
-
- /* AMD-defined (#2) */
- "lahf_lm", "cmp_legacy", "svm", "extapic",
- "cr8_legacy", "abm", "sse4a", "misalignsse",
- "3dnowprefetch", "osvw", "ibs", "sse5",
- "skinit", "wdt", NULL, NULL,
- NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
- NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
-
- /* Auxiliary (Linux-defined) */
- "ida", NULL, NULL, NULL, NULL, NULL, NULL, NULL,
- NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
- NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
- NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
- };
- static const char *const x86_power_flags[] = {
- "ts", /* temperature sensor */
- "fid", /* frequency id control */
- "vid", /* voltage id control */
- "ttp", /* thermal trip */
- "tm",
- "stc",
- "100mhzsteps",
- "hwpstate",
- "", /* tsc invariant mapped to constant_tsc */
- /* nothing */
- };
-
-
#ifdef CONFIG_SMP
cpu = c->cpu_index;
#endif
{
}
-struct seq_operations cpuinfo_op = {
+const struct seq_operations cpuinfo_op = {
.start = c_start,
.next = c_next,
.stop = c_stop,
git://ftp.safe.ca / safe / jmp / linux-2.6 / blobdiff