u32 pretcode;
int sig;
struct sigcontext_ia32 sc;
- struct _fpstate_ia32 fpstate;
+ struct _fpstate_ia32 fpstate_unused; /* look at kernel/sigframe.h */
unsigned int extramask[_COMPAT_NSIG_WORDS-1];
char retcode[8];
+ /* fp state follows here */
};
struct rt_sigframe
u32 puc;
compat_siginfo_t info;
struct ucontext_ia32 uc;
- struct _fpstate_ia32 fpstate;
char retcode[8];
+ /* fp state follows here */
};
#define COPY(x) { \
{ unsigned int cur; \
unsigned short pre; \
err |= __get_user(pre, &sc->seg); \
- asm volatile("movl %%" #seg ",%0" : "=r" (cur)); \
+ savesegment(seg, cur); \
pre |= mask; \
if (pre != cur) loadsegment(seg, pre); }
unsigned int *peax)
{
unsigned int tmpflags, gs, oldgs, err = 0;
- struct _fpstate_ia32 __user *buf;
+ void __user *buf;
u32 tmp;
/* Always make any pending restarted system calls return -EINTR */
*/
err |= __get_user(gs, &sc->gs);
gs |= 3;
- asm("movl %%gs,%0" : "=r" (oldgs));
+ savesegment(gs, oldgs);
if (gs != oldgs)
load_gs_index(gs);
err |= __get_user(tmp, &sc->fpstate);
buf = compat_ptr(tmp);
- if (buf) {
- if (!access_ok(VERIFY_READ, buf, sizeof(*buf)))
- goto badframe;
- err |= restore_i387_ia32(buf);
- } else {
- struct task_struct *me = current;
-
- if (used_math()) {
- clear_fpu(me);
- clear_used_math();
- }
- }
+ err |= restore_i387_xstate_ia32(buf);
err |= __get_user(tmp, &sc->ax);
*peax = tmp;
return err;
-
- badframe:
- return 1;
}
asmlinkage long sys32_sigreturn(struct pt_regs *regs)
*/
static int ia32_setup_sigcontext(struct sigcontext_ia32 __user *sc,
- struct _fpstate_ia32 __user *fpstate,
+ void __user *fpstate,
struct pt_regs *regs, unsigned int mask)
{
int tmp, err = 0;
- tmp = 0;
- __asm__("movl %%gs,%0" : "=r"(tmp): "0"(tmp));
+ savesegment(gs, tmp);
err |= __put_user(tmp, (unsigned int __user *)&sc->gs);
- __asm__("movl %%fs,%0" : "=r"(tmp): "0"(tmp));
+ savesegment(fs, tmp);
err |= __put_user(tmp, (unsigned int __user *)&sc->fs);
- __asm__("movl %%ds,%0" : "=r"(tmp): "0"(tmp));
+ savesegment(ds, tmp);
err |= __put_user(tmp, (unsigned int __user *)&sc->ds);
- __asm__("movl %%es,%0" : "=r"(tmp): "0"(tmp));
+ savesegment(es, tmp);
err |= __put_user(tmp, (unsigned int __user *)&sc->es);
err |= __put_user((u32)regs->di, &sc->di);
err |= __put_user((u32)regs->flags, &sc->flags);
err |= __put_user((u32)regs->sp, &sc->sp_at_signal);
- tmp = save_i387_ia32(fpstate);
+ tmp = save_i387_xstate_ia32(fpstate);
if (tmp < 0)
err = -EFAULT;
else {
* Determine which stack to use..
*/
static void __user *get_sigframe(struct k_sigaction *ka, struct pt_regs *regs,
- size_t frame_size)
+ size_t frame_size,
+ void **fpstate)
{
unsigned long sp;
ka->sa.sa_restorer)
sp = (unsigned long) ka->sa.sa_restorer;
+ if (used_math()) {
+ sp = sp - sig_xstate_ia32_size;
+ *fpstate = (struct _fpstate_ia32 *) sp;
+ }
+
sp -= frame_size;
/* Align the stack pointer according to the i386 ABI,
* i.e. so that on function entry ((sp + 4) & 15) == 0. */
struct sigframe __user *frame;
void __user *restorer;
int err = 0;
+ void __user *fpstate = NULL;
/* copy_to_user optimizes that into a single 8 byte store */
static const struct {
0,
};
- frame = get_sigframe(ka, regs, sizeof(*frame));
+ frame = get_sigframe(ka, regs, sizeof(*frame), &fpstate);
if (!access_ok(VERIFY_WRITE, frame, sizeof(*frame)))
goto give_sigsegv;
if (err)
goto give_sigsegv;
- err |= ia32_setup_sigcontext(&frame->sc, &frame->fpstate, regs,
- set->sig[0]);
+ err |= ia32_setup_sigcontext(&frame->sc, fpstate, regs, set->sig[0]);
if (err)
goto give_sigsegv;
regs->dx = 0;
regs->cx = 0;
- asm volatile("movl %0,%%ds" :: "r" (__USER32_DS));
- asm volatile("movl %0,%%es" :: "r" (__USER32_DS));
+ loadsegment(ds, __USER32_DS);
+ loadsegment(es, __USER32_DS);
regs->cs = __USER32_CS;
regs->ss = __USER32_DS;
struct rt_sigframe __user *frame;
void __user *restorer;
int err = 0;
+ void __user *fpstate = NULL;
/* __copy_to_user optimizes that into a single 8 byte store */
static const struct {
0,
};
- frame = get_sigframe(ka, regs, sizeof(*frame));
+ frame = get_sigframe(ka, regs, sizeof(*frame), &fpstate);
if (!access_ok(VERIFY_WRITE, frame, sizeof(*frame)))
goto give_sigsegv;
goto give_sigsegv;
/* Create the ucontext. */
- err |= __put_user(0, &frame->uc.uc_flags);
+ if (cpu_has_xsave)
+ err |= __put_user(UC_FP_XSTATE, &frame->uc.uc_flags);
+ else
+ err |= __put_user(0, &frame->uc.uc_flags);
err |= __put_user(0, &frame->uc.uc_link);
err |= __put_user(current->sas_ss_sp, &frame->uc.uc_stack.ss_sp);
err |= __put_user(sas_ss_flags(regs->sp),
&frame->uc.uc_stack.ss_flags);
err |= __put_user(current->sas_ss_size, &frame->uc.uc_stack.ss_size);
- err |= ia32_setup_sigcontext(&frame->uc.uc_mcontext, &frame->fpstate,
+ err |= ia32_setup_sigcontext(&frame->uc.uc_mcontext, fpstate,
regs, set->sig[0]);
err |= __copy_to_user(&frame->uc.uc_sigmask, set, sizeof(*set));
if (err)
regs->dx = (unsigned long) &frame->info;
regs->cx = (unsigned long) &frame->uc;
- asm volatile("movl %0,%%ds" :: "r" (__USER32_DS));
- asm volatile("movl %0,%%es" :: "r" (__USER32_DS));
+ loadsegment(ds, __USER32_DS);
+ loadsegment(es, __USER32_DS);
regs->cs = __USER32_CS;
regs->ss = __USER32_DS;
#include <linux/init.h>
+ #include <linux/kernel.h>
+ #include <linux/sched.h>
#include <linux/string.h>
+ #include <linux/bootmem.h>
+ #include <linux/bitops.h>
+ #include <linux/module.h>
+ #include <linux/kgdb.h>
+ #include <linux/topology.h>
#include <linux/delay.h>
#include <linux/smp.h>
- #include <linux/module.h>
#include <linux/percpu.h>
- #include <linux/bootmem.h>
- #include <asm/processor.h>
#include <asm/i387.h>
#include <asm/msr.h>
#include <asm/io.h>
+ #include <asm/linkage.h>
#include <asm/mmu_context.h>
#include <asm/mtrr.h>
#include <asm/mce.h>
#include <asm/pat.h>
#include <asm/asm.h>
+ #include <asm/numa.h>
#ifdef CONFIG_X86_LOCAL_APIC
#include <asm/mpspec.h>
#include <asm/apic.h>
#include <mach_apic.h>
+ #include <asm/genapic.h>
#endif
+ #include <asm/pda.h>
+ #include <asm/pgtable.h>
+ #include <asm/processor.h>
+ #include <asm/desc.h>
+ #include <asm/atomic.h>
+ #include <asm/proto.h>
+ #include <asm/sections.h>
+ #include <asm/setup.h>
+
#include "cpu.h"
+ static struct cpu_dev *this_cpu __cpuinitdata;
+
+ #ifdef CONFIG_X86_64
+ /* We need valid kernel segments for data and code in long mode too
+ * IRET will check the segment types kkeil 2000/10/28
+ * Also sysret mandates a special GDT layout
+ */
+ /* The TLS descriptors are currently at a different place compared to i386.
+ Hopefully nobody expects them at a fixed place (Wine?) */
DEFINE_PER_CPU(struct gdt_page, gdt_page) = { .gdt = {
+ [GDT_ENTRY_KERNEL32_CS] = { { { 0x0000ffff, 0x00cf9b00 } } },
+ [GDT_ENTRY_KERNEL_CS] = { { { 0x0000ffff, 0x00af9b00 } } },
+ [GDT_ENTRY_KERNEL_DS] = { { { 0x0000ffff, 0x00cf9300 } } },
+ [GDT_ENTRY_DEFAULT_USER32_CS] = { { { 0x0000ffff, 0x00cffb00 } } },
+ [GDT_ENTRY_DEFAULT_USER_DS] = { { { 0x0000ffff, 0x00cff300 } } },
+ [GDT_ENTRY_DEFAULT_USER_CS] = { { { 0x0000ffff, 0x00affb00 } } },
+ } };
+ #else
+ DEFINE_PER_CPU_PAGE_ALIGNED(struct gdt_page, gdt_page) = { .gdt = {
[GDT_ENTRY_KERNEL_CS] = { { { 0x0000ffff, 0x00cf9a00 } } },
[GDT_ENTRY_KERNEL_DS] = { { { 0x0000ffff, 0x00cf9200 } } },
[GDT_ENTRY_DEFAULT_USER_CS] = { { { 0x0000ffff, 0x00cffa00 } } },
[GDT_ENTRY_ESPFIX_SS] = { { { 0x00000000, 0x00c09200 } } },
[GDT_ENTRY_PERCPU] = { { { 0x00000000, 0x00000000 } } },
} };
+ #endif
EXPORT_PER_CPU_SYMBOL_GPL(gdt_page);
- __u32 cleared_cpu_caps[NCAPINTS] __cpuinitdata;
-
+ #ifdef CONFIG_X86_32
static int cachesize_override __cpuinitdata = -1;
static int disable_x86_serial_nr __cpuinitdata = 1;
- struct cpu_dev *cpu_devs[X86_VENDOR_NUM] = {};
+ static int __init cachesize_setup(char *str)
+ {
+ get_option(&str, &cachesize_override);
+ return 1;
+ }
+ __setup("cachesize=", cachesize_setup);
+
+ static int __init x86_fxsr_setup(char *s)
+ {
+ setup_clear_cpu_cap(X86_FEATURE_FXSR);
+ setup_clear_cpu_cap(X86_FEATURE_XMM);
+ return 1;
+ }
+ __setup("nofxsr", x86_fxsr_setup);
+
+ static int __init x86_sep_setup(char *s)
+ {
+ setup_clear_cpu_cap(X86_FEATURE_SEP);
+ return 1;
+ }
+ __setup("nosep", x86_sep_setup);
+
+ /* Standard macro to see if a specific flag is changeable */
+ static inline int flag_is_changeable_p(u32 flag)
+ {
+ u32 f1, f2;
+
+ asm("pushfl\n\t"
+ "pushfl\n\t"
+ "popl %0\n\t"
+ "movl %0,%1\n\t"
+ "xorl %2,%0\n\t"
+ "pushl %0\n\t"
+ "popfl\n\t"
+ "pushfl\n\t"
+ "popl %0\n\t"
+ "popfl\n\t"
+ : "=&r" (f1), "=&r" (f2)
+ : "ir" (flag));
+
+ return ((f1^f2) & flag) != 0;
+ }
+
+ /* Probe for the CPUID instruction */
+ static int __cpuinit have_cpuid_p(void)
+ {
+ return flag_is_changeable_p(X86_EFLAGS_ID);
+ }
+
+ static void __cpuinit squash_the_stupid_serial_number(struct cpuinfo_x86 *c)
+ {
+ if (cpu_has(c, X86_FEATURE_PN) && disable_x86_serial_nr) {
+ /* Disable processor serial number */
+ unsigned long lo, hi;
+ rdmsr(MSR_IA32_BBL_CR_CTL, lo, hi);
+ lo |= 0x200000;
+ wrmsr(MSR_IA32_BBL_CR_CTL, lo, hi);
+ printk(KERN_NOTICE "CPU serial number disabled.\n");
+ clear_cpu_cap(c, X86_FEATURE_PN);
+
+ /* Disabling the serial number may affect the cpuid level */
+ c->cpuid_level = cpuid_eax(0);
+ }
+ }
+
+ static int __init x86_serial_nr_setup(char *s)
+ {
+ disable_x86_serial_nr = 0;
+ return 1;
+ }
+ __setup("serialnumber", x86_serial_nr_setup);
+ #else
+ static inline int flag_is_changeable_p(u32 flag)
+ {
+ return 1;
+ }
+ /* Probe for the CPUID instruction */
+ static inline int have_cpuid_p(void)
+ {
+ return 1;
+ }
+ static inline void squash_the_stupid_serial_number(struct cpuinfo_x86 *c)
+ {
+ }
+ #endif
+
+ /*
+ * Naming convention should be: <Name> [(<Codename>)]
+ * This table only is used unless init_<vendor>() below doesn't set it;
+ * in particular, if CPUID levels 0x80000002..4 are supported, this isn't used
+ *
+ */
+
+ /* Look up CPU names by table lookup. */
+ static char __cpuinit *table_lookup_model(struct cpuinfo_x86 *c)
+ {
+ struct cpu_model_info *info;
+
+ if (c->x86_model >= 16)
+ return NULL; /* Range check */
+
+ if (!this_cpu)
+ return NULL;
+
+ info = this_cpu->c_models;
+
+ while (info && info->family) {
+ if (info->family == c->x86)
+ return info->model_names[c->x86_model];
+ info++;
+ }
+ return NULL; /* Not found */
+ }
+
+ __u32 cleared_cpu_caps[NCAPINTS] __cpuinitdata;
+
+ /* Current gdt points %fs at the "master" per-cpu area: after this,
+ * it's on the real one. */
+ void switch_to_new_gdt(void)
+ {
+ struct desc_ptr gdt_descr;
+
+ gdt_descr.address = (long)get_cpu_gdt_table(smp_processor_id());
+ gdt_descr.size = GDT_SIZE - 1;
+ load_gdt(&gdt_descr);
+ #ifdef CONFIG_X86_32
+ asm("mov %0, %%fs" : : "r" (__KERNEL_PERCPU) : "memory");
+ #endif
+ }
+
+ static struct cpu_dev *cpu_devs[X86_VENDOR_NUM] = {};
static void __cpuinit default_init(struct cpuinfo_x86 *c)
{
+ #ifdef CONFIG_X86_64
+ display_cacheinfo(c);
+ #else
/* Not much we can do here... */
/* Check if at least it has cpuid */
if (c->cpuid_level == -1) {
else if (c->x86 == 3)
strcpy(c->x86_model_id, "386");
}
+ #endif
}
static struct cpu_dev __cpuinitdata default_cpu = {
.c_init = default_init,
.c_vendor = "Unknown",
+ .c_x86_vendor = X86_VENDOR_UNKNOWN,
};
- static struct cpu_dev *this_cpu __cpuinitdata = &default_cpu;
- static int __init cachesize_setup(char *str)
- {
- get_option(&str, &cachesize_override);
- return 1;
- }
- __setup("cachesize=", cachesize_setup);
-
- int __cpuinit get_model_name(struct cpuinfo_x86 *c)
+ static void __cpuinit get_model_name(struct cpuinfo_x86 *c)
{
unsigned int *v;
char *p, *q;
- if (cpuid_eax(0x80000000) < 0x80000004)
- return 0;
+ if (c->extended_cpuid_level < 0x80000004)
+ return;
v = (unsigned int *) c->x86_model_id;
cpuid(0x80000002, &v[0], &v[1], &v[2], &v[3]);
while (q <= &c->x86_model_id[48])
*q++ = '\0'; /* Zero-pad the rest */
}
-
- return 1;
}
-
void __cpuinit display_cacheinfo(struct cpuinfo_x86 *c)
{
- unsigned int n, dummy, ecx, edx, l2size;
+ unsigned int n, dummy, ebx, ecx, edx, l2size;
- n = cpuid_eax(0x80000000);
+ n = c->extended_cpuid_level;
if (n >= 0x80000005) {
- cpuid(0x80000005, &dummy, &dummy, &ecx, &edx);
+ cpuid(0x80000005, &dummy, &ebx, &ecx, &edx);
printk(KERN_INFO "CPU: L1 I Cache: %dK (%d bytes/line), D cache %dK (%d bytes/line)\n",
- edx>>24, edx&0xFF, ecx>>24, ecx&0xFF);
- c->x86_cache_size = (ecx>>24)+(edx>>24);
+ edx>>24, edx&0xFF, ecx>>24, ecx&0xFF);
+ c->x86_cache_size = (ecx>>24) + (edx>>24);
+ #ifdef CONFIG_X86_64
+ /* On K8 L1 TLB is inclusive, so don't count it */
+ c->x86_tlbsize = 0;
+ #endif
}
if (n < 0x80000006) /* Some chips just has a large L1. */
return;
- ecx = cpuid_ecx(0x80000006);
+ cpuid(0x80000006, &dummy, &ebx, &ecx, &edx);
l2size = ecx >> 16;
+ #ifdef CONFIG_X86_64
+ c->x86_tlbsize += ((ebx >> 16) & 0xfff) + (ebx & 0xfff);
+ #else
/* do processor-specific cache resizing */
if (this_cpu->c_size_cache)
l2size = this_cpu->c_size_cache(c, l2size);
if (l2size == 0)
return; /* Again, no L2 cache is possible */
+ #endif
c->x86_cache_size = l2size;
printk(KERN_INFO "CPU: L2 Cache: %dK (%d bytes/line)\n",
- l2size, ecx & 0xFF);
+ l2size, ecx & 0xFF);
}
- /*
- * Naming convention should be: <Name> [(<Codename>)]
- * This table only is used unless init_<vendor>() below doesn't set it;
- * in particular, if CPUID levels 0x80000002..4 are supported, this isn't used
- *
- */
-
- /* Look up CPU names by table lookup. */
- static char __cpuinit *table_lookup_model(struct cpuinfo_x86 *c)
+ void __cpuinit detect_ht(struct cpuinfo_x86 *c)
{
- struct cpu_model_info *info;
+ #ifdef CONFIG_X86_HT
+ u32 eax, ebx, ecx, edx;
+ int index_msb, core_bits;
- if (c->x86_model >= 16)
- return NULL; /* Range check */
+ if (!cpu_has(c, X86_FEATURE_HT))
+ return;
- if (!this_cpu)
- return NULL;
+ if (cpu_has(c, X86_FEATURE_CMP_LEGACY))
+ goto out;
- info = this_cpu->c_models;
+ if (cpu_has(c, X86_FEATURE_XTOPOLOGY))
+ return;
- while (info && info->family) {
- if (info->family == c->x86)
- return info->model_names[c->x86_model];
- info++;
+ cpuid(1, &eax, &ebx, &ecx, &edx);
+
+ smp_num_siblings = (ebx & 0xff0000) >> 16;
+
+ if (smp_num_siblings == 1) {
+ printk(KERN_INFO "CPU: Hyper-Threading is disabled\n");
+ } else if (smp_num_siblings > 1) {
+
+ if (smp_num_siblings > NR_CPUS) {
+ printk(KERN_WARNING "CPU: Unsupported number of siblings %d",
+ smp_num_siblings);
+ smp_num_siblings = 1;
+ return;
+ }
+
+ index_msb = get_count_order(smp_num_siblings);
+ #ifdef CONFIG_X86_64
+ c->phys_proc_id = phys_pkg_id(index_msb);
+ #else
+ c->phys_proc_id = phys_pkg_id(c->initial_apicid, index_msb);
+ #endif
+
+ smp_num_siblings = smp_num_siblings / c->x86_max_cores;
+
+ index_msb = get_count_order(smp_num_siblings);
+
+ core_bits = get_count_order(c->x86_max_cores);
+
+ #ifdef CONFIG_X86_64
+ c->cpu_core_id = phys_pkg_id(index_msb) &
+ ((1 << core_bits) - 1);
+ #else
+ c->cpu_core_id = phys_pkg_id(c->initial_apicid, index_msb) &
+ ((1 << core_bits) - 1);
+ #endif
}
- return NULL; /* Not found */
- }
+ out:
+ if ((c->x86_max_cores * smp_num_siblings) > 1) {
+ printk(KERN_INFO "CPU: Physical Processor ID: %d\n",
+ c->phys_proc_id);
+ printk(KERN_INFO "CPU: Processor Core ID: %d\n",
+ c->cpu_core_id);
+ }
+ #endif
+ }
- static void __cpuinit get_cpu_vendor(struct cpuinfo_x86 *c, int early)
+ static void __cpuinit get_cpu_vendor(struct cpuinfo_x86 *c)
{
char *v = c->x86_vendor_id;
int i;
static int printed;
for (i = 0; i < X86_VENDOR_NUM; i++) {
- if (cpu_devs[i]) {
- if (!strcmp(v, cpu_devs[i]->c_ident[0]) ||
- (cpu_devs[i]->c_ident[1] &&
- !strcmp(v, cpu_devs[i]->c_ident[1]))) {
- c->x86_vendor = i;
- if (!early)
- this_cpu = cpu_devs[i];
- return;
- }
+ if (!cpu_devs[i])
+ break;
+
+ if (!strcmp(v, cpu_devs[i]->c_ident[0]) ||
+ (cpu_devs[i]->c_ident[1] &&
+ !strcmp(v, cpu_devs[i]->c_ident[1]))) {
+ this_cpu = cpu_devs[i];
+ c->x86_vendor = this_cpu->c_x86_vendor;
+ return;
}
}
+
if (!printed) {
printed++;
- printk(KERN_ERR "CPU: Vendor unknown, using generic init.\n");
+ printk(KERN_ERR "CPU: vendor_id '%s' unknown, using generic init.\n", v);
printk(KERN_ERR "CPU: Your system may be unstable.\n");
}
+
c->x86_vendor = X86_VENDOR_UNKNOWN;
this_cpu = &default_cpu;
}
-
- static int __init x86_fxsr_setup(char *s)
- {
- setup_clear_cpu_cap(X86_FEATURE_FXSR);
- setup_clear_cpu_cap(X86_FEATURE_XMM);
- return 1;
- }
- __setup("nofxsr", x86_fxsr_setup);
-
-
- static int __init x86_sep_setup(char *s)
- {
- setup_clear_cpu_cap(X86_FEATURE_SEP);
- return 1;
- }
- __setup("nosep", x86_sep_setup);
-
-
- /* Standard macro to see if a specific flag is changeable */
- static inline int flag_is_changeable_p(u32 flag)
- {
- u32 f1, f2;
-
- asm("pushfl\n\t"
- "pushfl\n\t"
- "popl %0\n\t"
- "movl %0,%1\n\t"
- "xorl %2,%0\n\t"
- "pushl %0\n\t"
- "popfl\n\t"
- "pushfl\n\t"
- "popl %0\n\t"
- "popfl\n\t"
- : "=&r" (f1), "=&r" (f2)
- : "ir" (flag));
-
- return ((f1^f2) & flag) != 0;
- }
-
-
- /* Probe for the CPUID instruction */
- static int __cpuinit have_cpuid_p(void)
- {
- return flag_is_changeable_p(X86_EFLAGS_ID);
- }
-
- void __init cpu_detect(struct cpuinfo_x86 *c)
+ void __cpuinit cpu_detect(struct cpuinfo_x86 *c)
{
/* Get vendor name */
cpuid(0x00000000, (unsigned int *)&c->cpuid_level,
(unsigned int *)&c->x86_vendor_id[4]);
c->x86 = 4;
+ /* Intel-defined flags: level 0x00000001 */
if (c->cpuid_level >= 0x00000001) {
u32 junk, tfms, cap0, misc;
cpuid(0x00000001, &tfms, &misc, &junk, &cap0);
- c->x86 = (tfms >> 8) & 15;
- c->x86_model = (tfms >> 4) & 15;
+ c->x86 = (tfms >> 8) & 0xf;
+ c->x86_model = (tfms >> 4) & 0xf;
+ c->x86_mask = tfms & 0xf;
if (c->x86 == 0xf)
c->x86 += (tfms >> 20) & 0xff;
if (c->x86 >= 0x6)
- c->x86_model += ((tfms >> 16) & 0xF) << 4;
- c->x86_mask = tfms & 15;
+ c->x86_model += ((tfms >> 16) & 0xf) << 4;
if (cap0 & (1<<19)) {
- c->x86_cache_alignment = ((misc >> 8) & 0xff) * 8;
c->x86_clflush_size = ((misc >> 8) & 0xff) * 8;
+ c->x86_cache_alignment = c->x86_clflush_size;
}
}
}
- static void __cpuinit early_get_cap(struct cpuinfo_x86 *c)
+
+ static void __cpuinit get_cpu_cap(struct cpuinfo_x86 *c)
{
u32 tfms, xlvl;
- unsigned int ebx;
+ u32 ebx;
- memset(&c->x86_capability, 0, sizeof c->x86_capability);
- if (have_cpuid_p()) {
- /* Intel-defined flags: level 0x00000001 */
- if (c->cpuid_level >= 0x00000001) {
- u32 capability, excap;
- cpuid(0x00000001, &tfms, &ebx, &excap, &capability);
- c->x86_capability[0] = capability;
- c->x86_capability[4] = excap;
- }
+ /* Intel-defined flags: level 0x00000001 */
+ if (c->cpuid_level >= 0x00000001) {
+ u32 capability, excap;
+ cpuid(0x00000001, &tfms, &ebx, &excap, &capability);
+ c->x86_capability[0] = capability;
+ c->x86_capability[4] = excap;
+ }
- /* AMD-defined flags: level 0x80000001 */
- xlvl = cpuid_eax(0x80000000);
- if ((xlvl & 0xffff0000) == 0x80000000) {
- if (xlvl >= 0x80000001) {
- c->x86_capability[1] = cpuid_edx(0x80000001);
- c->x86_capability[6] = cpuid_ecx(0x80000001);
- }
+ /* AMD-defined flags: level 0x80000001 */
+ xlvl = cpuid_eax(0x80000000);
+ c->extended_cpuid_level = xlvl;
+ if ((xlvl & 0xffff0000) == 0x80000000) {
+ if (xlvl >= 0x80000001) {
+ c->x86_capability[1] = cpuid_edx(0x80000001);
+ c->x86_capability[6] = cpuid_ecx(0x80000001);
}
+ }
+ #ifdef CONFIG_X86_64
+ if (c->extended_cpuid_level >= 0x80000008) {
+ u32 eax = cpuid_eax(0x80000008);
+
+ c->x86_virt_bits = (eax >> 8) & 0xff;
+ c->x86_phys_bits = eax & 0xff;
}
+ #endif
+
+ if (c->extended_cpuid_level >= 0x80000007)
+ c->x86_power = cpuid_edx(0x80000007);
}
+ static void __cpuinit identify_cpu_without_cpuid(struct cpuinfo_x86 *c)
+ {
+ #ifdef CONFIG_X86_32
+ int i;
+
+ /*
+ * First of all, decide if this is a 486 or higher
+ * It's a 486 if we can modify the AC flag
+ */
+ if (flag_is_changeable_p(X86_EFLAGS_AC))
+ c->x86 = 4;
+ else
+ c->x86 = 3;
+
+ for (i = 0; i < X86_VENDOR_NUM; i++)
+ if (cpu_devs[i] && cpu_devs[i]->c_identify) {
+ c->x86_vendor_id[0] = 0;
+ cpu_devs[i]->c_identify(c);
+ if (c->x86_vendor_id[0]) {
+ get_cpu_vendor(c);
+ break;
+ }
+ }
+ #endif
+ }
+
/*
* Do minimum CPU detection early.
* Fields really needed: vendor, cpuid_level, family, model, mask,
* WARNING: this function is only called on the BP. Don't add code here
* that is supposed to run on all CPUs.
*/
- static void __init early_cpu_detect(void)
+ static void __init early_identify_cpu(struct cpuinfo_x86 *c)
{
- struct cpuinfo_x86 *c = &boot_cpu_data;
-
- c->x86_cache_alignment = 32;
+ #ifdef CONFIG_X86_64
+ c->x86_clflush_size = 64;
+ #else
c->x86_clflush_size = 32;
+ #endif
+ c->x86_cache_alignment = c->x86_clflush_size;
+
+ memset(&c->x86_capability, 0, sizeof c->x86_capability);
+ c->extended_cpuid_level = 0;
+ if (!have_cpuid_p())
+ identify_cpu_without_cpuid(c);
+
+ /* cyrix could have cpuid enabled via c_identify()*/
if (!have_cpuid_p())
return;
cpu_detect(c);
- get_cpu_vendor(c, 1);
+ get_cpu_vendor(c);
- early_get_cap(c);
+ get_cpu_cap(c);
- if (c->x86_vendor != X86_VENDOR_UNKNOWN &&
- cpu_devs[c->x86_vendor]->c_early_init)
- cpu_devs[c->x86_vendor]->c_early_init(c);
+ if (this_cpu->c_early_init)
+ this_cpu->c_early_init(c);
+
+ validate_pat_support(c);
+ }
+
+ void __init early_cpu_init(void)
+ {
+ struct cpu_dev **cdev;
+ int count = 0;
+
+ printk("KERNEL supported cpus:\n");
+ for (cdev = __x86_cpu_dev_start; cdev < __x86_cpu_dev_end; cdev++) {
+ struct cpu_dev *cpudev = *cdev;
+ unsigned int j;
+
+ if (count >= X86_VENDOR_NUM)
+ break;
+ cpu_devs[count] = cpudev;
+ count++;
+
+ for (j = 0; j < 2; j++) {
+ if (!cpudev->c_ident[j])
+ continue;
+ printk(" %s %s\n", cpudev->c_vendor,
+ cpudev->c_ident[j]);
+ }
+ }
+
+ early_identify_cpu(&boot_cpu_data);
}
/*
* The NOPL instruction is supposed to exist on all CPUs with
- * family >= 6, unfortunately, that's not true in practice because
+ * family >= 6; unfortunately, that's not true in practice because
* of early VIA chips and (more importantly) broken virtualizers that
- * are not easy to detect. Hence, probe for it based on first
- * principles.
- *
- * Note: no 64-bit chip is known to lack these, but put the code here
- * for consistency with 32 bits, and to make it utterly trivial to
- * diagnose the problem should it ever surface.
+ * are not easy to detect. In the latter case it doesn't even *fail*
+ * reliably, so probing for it doesn't even work. Disable it completely
+ * unless we can find a reliable way to detect all the broken cases.
*/
static void __cpuinit detect_nopl(struct cpuinfo_x86 *c)
{
- const u32 nopl_signature = 0x888c53b1; /* Random number */
- u32 has_nopl = nopl_signature;
-
clear_cpu_cap(c, X86_FEATURE_NOPL);
- if (c->x86 >= 6) {
- asm volatile("\n"
- "1: .byte 0x0f,0x1f,0xc0\n" /* nopl %eax */
- "2:\n"
- " .section .fixup,\"ax\"\n"
- "3: xor %0,%0\n"
- " jmp 2b\n"
- " .previous\n"
- _ASM_EXTABLE(1b,3b)
- : "+a" (has_nopl));
-
- if (has_nopl == nopl_signature)
- set_cpu_cap(c, X86_FEATURE_NOPL);
- }
}
static void __cpuinit generic_identify(struct cpuinfo_x86 *c)
{
- u32 tfms, xlvl;
- unsigned int ebx;
-
- if (have_cpuid_p()) {
- /* Get vendor name */
- cpuid(0x00000000, (unsigned int *)&c->cpuid_level,
- (unsigned int *)&c->x86_vendor_id[0],
- (unsigned int *)&c->x86_vendor_id[8],
- (unsigned int *)&c->x86_vendor_id[4]);
-
- get_cpu_vendor(c, 0);
- /* Initialize the standard set of capabilities */
- /* Note that the vendor-specific code below might override */
- /* Intel-defined flags: level 0x00000001 */
- if (c->cpuid_level >= 0x00000001) {
- u32 capability, excap;
- cpuid(0x00000001, &tfms, &ebx, &excap, &capability);
- c->x86_capability[0] = capability;
- c->x86_capability[4] = excap;
- c->x86 = (tfms >> 8) & 15;
- c->x86_model = (tfms >> 4) & 15;
- if (c->x86 == 0xf)
- c->x86 += (tfms >> 20) & 0xff;
- if (c->x86 >= 0x6)
- c->x86_model += ((tfms >> 16) & 0xF) << 4;
- c->x86_mask = tfms & 15;
- c->initial_apicid = (ebx >> 24) & 0xFF;
- #ifdef CONFIG_X86_HT
- c->apicid = phys_pkg_id(c->initial_apicid, 0);
- c->phys_proc_id = c->initial_apicid;
- #else
- c->apicid = c->initial_apicid;
- #endif
- if (test_cpu_cap(c, X86_FEATURE_CLFLSH))
- c->x86_clflush_size = ((ebx >> 8) & 0xff) * 8;
- } else {
- /* Have CPUID level 0 only - unheard of */
- c->x86 = 4;
- }
+ c->extended_cpuid_level = 0;
- /* AMD-defined flags: level 0x80000001 */
- xlvl = cpuid_eax(0x80000000);
- if ((xlvl & 0xffff0000) == 0x80000000) {
- if (xlvl >= 0x80000001) {
- c->x86_capability[1] = cpuid_edx(0x80000001);
- c->x86_capability[6] = cpuid_ecx(0x80000001);
- }
- if (xlvl >= 0x80000004)
- get_model_name(c); /* Default name */
- }
+ if (!have_cpuid_p())
+ identify_cpu_without_cpuid(c);
- init_scattered_cpuid_features(c);
- detect_nopl(c);
- }
- }
+ /* cyrix could have cpuid enabled via c_identify()*/
+ if (!have_cpuid_p())
+ return;
- static void __cpuinit squash_the_stupid_serial_number(struct cpuinfo_x86 *c)
- {
- if (cpu_has(c, X86_FEATURE_PN) && disable_x86_serial_nr) {
- /* Disable processor serial number */
- unsigned long lo, hi;
- rdmsr(MSR_IA32_BBL_CR_CTL, lo, hi);
- lo |= 0x200000;
- wrmsr(MSR_IA32_BBL_CR_CTL, lo, hi);
- printk(KERN_NOTICE "CPU serial number disabled.\n");
- clear_cpu_cap(c, X86_FEATURE_PN);
+ cpu_detect(c);
- /* Disabling the serial number may affect the cpuid level */
- c->cpuid_level = cpuid_eax(0);
- }
- }
+ get_cpu_vendor(c);
- static int __init x86_serial_nr_setup(char *s)
- {
- disable_x86_serial_nr = 0;
- return 1;
- }
- __setup("serialnumber", x86_serial_nr_setup);
+ get_cpu_cap(c);
+ if (c->cpuid_level >= 0x00000001) {
+ c->initial_apicid = (cpuid_ebx(1) >> 24) & 0xFF;
+ #ifdef CONFIG_X86_32
+ # ifdef CONFIG_X86_HT
+ c->apicid = phys_pkg_id(c->initial_apicid, 0);
+ # else
+ c->apicid = c->initial_apicid;
+ # endif
+ #endif
+ #ifdef CONFIG_X86_HT
+ c->phys_proc_id = c->initial_apicid;
+ #endif
+ }
+
+ get_model_name(c); /* Default name */
+
+ init_scattered_cpuid_features(c);
+ detect_nopl(c);
+ }
/*
* This does the hard work of actually picking apart the CPU stuff...
c->loops_per_jiffy = loops_per_jiffy;
c->x86_cache_size = -1;
c->x86_vendor = X86_VENDOR_UNKNOWN;
- c->cpuid_level = -1; /* CPUID not detected */
c->x86_model = c->x86_mask = 0; /* So far unknown... */
c->x86_vendor_id[0] = '\0'; /* Unset */
c->x86_model_id[0] = '\0'; /* Unset */
c->x86_max_cores = 1;
+ c->x86_coreid_bits = 0;
+ #ifdef CONFIG_X86_64
+ c->x86_clflush_size = 64;
+ #else
+ c->cpuid_level = -1; /* CPUID not detected */
c->x86_clflush_size = 32;
+ #endif
+ c->x86_cache_alignment = c->x86_clflush_size;
memset(&c->x86_capability, 0, sizeof c->x86_capability);
- if (!have_cpuid_p()) {
- /*
- * First of all, decide if this is a 486 or higher
- * It's a 486 if we can modify the AC flag
- */
- if (flag_is_changeable_p(X86_EFLAGS_AC))
- c->x86 = 4;
- else
- c->x86 = 3;
- }
-
generic_identify(c);
if (this_cpu->c_identify)
this_cpu->c_identify(c);
+ #ifdef CONFIG_X86_64
+ c->apicid = phys_pkg_id(0);
+ #endif
+
/*
* Vendor-specific initialization. In this section we
* canonicalize the feature flags, meaning if there are
c->x86, c->x86_model);
}
+ #ifdef CONFIG_X86_64
+ detect_ht(c);
+ #endif
+
/*
* On SMP, boot_cpu_data holds the common feature set between
* all CPUs; so make sure that we indicate which features are
*/
if (c != &boot_cpu_data) {
/* AND the already accumulated flags with these */
- for (i = 0 ; i < NCAPINTS ; i++)
+ for (i = 0; i < NCAPINTS; i++)
boot_cpu_data.x86_capability[i] &= c->x86_capability[i];
}
for (i = 0; i < NCAPINTS; i++)
c->x86_capability[i] &= ~cleared_cpu_caps[i];
+ #ifdef CONFIG_X86_MCE
/* Init Machine Check Exception if available. */
mcheck_init(c);
+ #endif
select_idle_routine(c);
+
+ #if defined(CONFIG_NUMA) && defined(CONFIG_X86_64)
+ numa_add_cpu(smp_processor_id());
+ #endif
}
void __init identify_boot_cpu(void)
{
identify_cpu(&boot_cpu_data);
+ #ifdef CONFIG_X86_32
sysenter_setup();
enable_sep_cpu();
+ #endif
}
void __cpuinit identify_secondary_cpu(struct cpuinfo_x86 *c)
{
BUG_ON(c == &boot_cpu_data);
identify_cpu(c);
+ #ifdef CONFIG_X86_32
enable_sep_cpu();
+ #endif
mtrr_ap_init();
}
- #ifdef CONFIG_X86_HT
- void __cpuinit detect_ht(struct cpuinfo_x86 *c)
- {
- u32 eax, ebx, ecx, edx;
- int index_msb, core_bits;
-
- cpuid(1, &eax, &ebx, &ecx, &edx);
-
- if (!cpu_has(c, X86_FEATURE_HT) || cpu_has(c, X86_FEATURE_CMP_LEGACY))
- return;
-
- smp_num_siblings = (ebx & 0xff0000) >> 16;
+ struct msr_range {
+ unsigned min;
+ unsigned max;
+ };
- if (smp_num_siblings == 1) {
- printk(KERN_INFO "CPU: Hyper-Threading is disabled\n");
- } else if (smp_num_siblings > 1) {
+ static struct msr_range msr_range_array[] __cpuinitdata = {
+ { 0x00000000, 0x00000418},
+ { 0xc0000000, 0xc000040b},
+ { 0xc0010000, 0xc0010142},
+ { 0xc0011000, 0xc001103b},
+ };
- if (smp_num_siblings > NR_CPUS) {
- printk(KERN_WARNING "CPU: Unsupported number of the "
- "siblings %d", smp_num_siblings);
- smp_num_siblings = 1;
- return;
+ static void __cpuinit print_cpu_msr(void)
+ {
+ unsigned index;
+ u64 val;
+ int i;
+ unsigned index_min, index_max;
+
+ for (i = 0; i < ARRAY_SIZE(msr_range_array); i++) {
+ index_min = msr_range_array[i].min;
+ index_max = msr_range_array[i].max;
+ for (index = index_min; index < index_max; index++) {
+ if (rdmsrl_amd_safe(index, &val))
+ continue;
+ printk(KERN_INFO " MSR%08x: %016llx\n", index, val);
}
+ }
+ }
- index_msb = get_count_order(smp_num_siblings);
- c->phys_proc_id = phys_pkg_id(c->initial_apicid, index_msb);
-
- printk(KERN_INFO "CPU: Physical Processor ID: %d\n",
- c->phys_proc_id);
-
- smp_num_siblings = smp_num_siblings / c->x86_max_cores;
-
- index_msb = get_count_order(smp_num_siblings) ;
+ static int show_msr __cpuinitdata;
+ static __init int setup_show_msr(char *arg)
+ {
+ int num;
- core_bits = get_count_order(c->x86_max_cores);
+ get_option(&arg, &num);
- c->cpu_core_id = phys_pkg_id(c->initial_apicid, index_msb) &
- ((1 << core_bits) - 1);
-
- if (c->x86_max_cores > 1)
- printk(KERN_INFO "CPU: Processor Core ID: %d\n",
- c->cpu_core_id);
- }
+ if (num > 0)
+ show_msr = num;
+ return 1;
}
- #endif
+ __setup("show_msr=", setup_show_msr);
static __init int setup_noclflush(char *arg)
{
vendor = c->x86_vendor_id;
if (vendor && strncmp(c->x86_model_id, vendor, strlen(vendor)))
- printk("%s ", vendor);
+ printk(KERN_CONT "%s ", vendor);
- if (!c->x86_model_id[0])
- printk("%d86", c->x86);
+ if (c->x86_model_id[0])
+ printk(KERN_CONT "%s", c->x86_model_id);
else
- printk("%s", c->x86_model_id);
+ printk(KERN_CONT "%d86", c->x86);
if (c->x86_mask || c->cpuid_level >= 0)
- printk(" stepping %02x\n", c->x86_mask);
+ printk(KERN_CONT " stepping %02x\n", c->x86_mask);
else
- printk("\n");
+ printk(KERN_CONT "\n");
+
+ #ifdef CONFIG_SMP
+ if (c->cpu_index < show_msr)
+ print_cpu_msr();
+ #else
+ if (show_msr)
+ print_cpu_msr();
+ #endif
}
static __init int setup_disablecpuid(char *arg)
cpumask_t cpu_initialized __cpuinitdata = CPU_MASK_NONE;
- void __init early_cpu_init(void)
+ #ifdef CONFIG_X86_64
+ struct x8664_pda **_cpu_pda __read_mostly;
+ EXPORT_SYMBOL(_cpu_pda);
+
+ struct desc_ptr idt_descr = { 256 * 16 - 1, (unsigned long) idt_table };
+
+ char boot_cpu_stack[IRQSTACKSIZE] __page_aligned_bss;
+
+ void __cpuinit pda_init(int cpu)
+ {
+ struct x8664_pda *pda = cpu_pda(cpu);
+
+ /* Setup up data that may be needed in __get_free_pages early */
+ loadsegment(fs, 0);
+ loadsegment(gs, 0);
+ /* Memory clobbers used to order PDA accessed */
+ mb();
+ wrmsrl(MSR_GS_BASE, pda);
+ mb();
+
+ pda->cpunumber = cpu;
+ pda->irqcount = -1;
+ pda->kernelstack = (unsigned long)stack_thread_info() -
+ PDA_STACKOFFSET + THREAD_SIZE;
+ pda->active_mm = &init_mm;
+ pda->mmu_state = 0;
+
+ if (cpu == 0) {
+ /* others are initialized in smpboot.c */
+ pda->pcurrent = &init_task;
+ pda->irqstackptr = boot_cpu_stack;
+ pda->irqstackptr += IRQSTACKSIZE - 64;
+ } else {
+ if (!pda->irqstackptr) {
+ pda->irqstackptr = (char *)
+ __get_free_pages(GFP_ATOMIC, IRQSTACK_ORDER);
+ if (!pda->irqstackptr)
+ panic("cannot allocate irqstack for cpu %d",
+ cpu);
+ pda->irqstackptr += IRQSTACKSIZE - 64;
+ }
+
+ if (pda->nodenumber == 0 && cpu_to_node(cpu) != NUMA_NO_NODE)
+ pda->nodenumber = cpu_to_node(cpu);
+ }
+ }
+
+ char boot_exception_stacks[(N_EXCEPTION_STACKS - 1) * EXCEPTION_STKSZ +
+ DEBUG_STKSZ] __page_aligned_bss;
+
+ extern asmlinkage void ignore_sysret(void);
+
+ /* May not be marked __init: used by software suspend */
+ void syscall_init(void)
{
- struct cpu_vendor_dev *cvdev;
+ /*
+ * LSTAR and STAR live in a bit strange symbiosis.
+ * They both write to the same internal register. STAR allows to
+ * set CS/DS but only a 32bit target. LSTAR sets the 64bit rip.
+ */
+ wrmsrl(MSR_STAR, ((u64)__USER32_CS)<<48 | ((u64)__KERNEL_CS)<<32);
+ wrmsrl(MSR_LSTAR, system_call);
+ wrmsrl(MSR_CSTAR, ignore_sysret);
- for (cvdev = __x86cpuvendor_start ;
- cvdev < __x86cpuvendor_end ;
- cvdev++)
- cpu_devs[cvdev->vendor] = cvdev->cpu_dev;
+ #ifdef CONFIG_IA32_EMULATION
+ syscall32_cpu_init();
+ #endif
- early_cpu_detect();
- validate_pat_support(&boot_cpu_data);
+ /* Flags to clear on syscall */
+ wrmsrl(MSR_SYSCALL_MASK,
+ X86_EFLAGS_TF|X86_EFLAGS_DF|X86_EFLAGS_IF|X86_EFLAGS_IOPL);
}
+ unsigned long kernel_eflags;
+
+ /*
+ * Copies of the original ist values from the tss are only accessed during
+ * debugging, no special alignment required.
+ */
+ DEFINE_PER_CPU(struct orig_ist, orig_ist);
+
+ #else
+
/* Make sure %fs is initialized properly in idle threads */
struct pt_regs * __cpuinit idle_regs(struct pt_regs *regs)
{
regs->fs = __KERNEL_PERCPU;
return regs;
}
-
- /* Current gdt points %fs at the "master" per-cpu area: after this,
- * it's on the real one. */
- void switch_to_new_gdt(void)
- {
- struct desc_ptr gdt_descr;
-
- gdt_descr.address = (long)get_cpu_gdt_table(smp_processor_id());
- gdt_descr.size = GDT_SIZE - 1;
- load_gdt(&gdt_descr);
- asm("mov %0, %%fs" : : "r" (__KERNEL_PERCPU) : "memory");
- }
+ #endif
/*
* cpu_init() initializes state that is per-CPU. Some data is already
* initialized (naturally) in the bootstrap process, such as the GDT
* and IDT. We reload them nevertheless, this function acts as a
* 'CPU state barrier', nothing should get across.
+ * A lot of state is already set up in PDA init for 64 bit
*/
+ #ifdef CONFIG_X86_64
+ void __cpuinit cpu_init(void)
+ {
+ int cpu = stack_smp_processor_id();
+ struct tss_struct *t = &per_cpu(init_tss, cpu);
+ struct orig_ist *orig_ist = &per_cpu(orig_ist, cpu);
+ unsigned long v;
+ char *estacks = NULL;
+ struct task_struct *me;
+ int i;
+
+ /* CPU 0 is initialised in head64.c */
+ if (cpu != 0)
+ pda_init(cpu);
+ else
+ estacks = boot_exception_stacks;
+
+ me = current;
+
+ if (cpu_test_and_set(cpu, cpu_initialized))
+ panic("CPU#%d already initialized!\n", cpu);
+
+ printk(KERN_INFO "Initializing CPU#%d\n", cpu);
+
+ clear_in_cr4(X86_CR4_VME|X86_CR4_PVI|X86_CR4_TSD|X86_CR4_DE);
+
+ /*
+ * Initialize the per-CPU GDT with the boot GDT,
+ * and set up the GDT descriptor:
+ */
+
+ switch_to_new_gdt();
+ load_idt((const struct desc_ptr *)&idt_descr);
+
+ memset(me->thread.tls_array, 0, GDT_ENTRY_TLS_ENTRIES * 8);
+ syscall_init();
+
+ wrmsrl(MSR_FS_BASE, 0);
+ wrmsrl(MSR_KERNEL_GS_BASE, 0);
+ barrier();
+
+ check_efer();
+ if (cpu != 0 && x2apic)
+ enable_x2apic();
+
+ /*
+ * set up and load the per-CPU TSS
+ */
+ if (!orig_ist->ist[0]) {
+ static const unsigned int order[N_EXCEPTION_STACKS] = {
+ [0 ... N_EXCEPTION_STACKS - 1] = EXCEPTION_STACK_ORDER,
+ [DEBUG_STACK - 1] = DEBUG_STACK_ORDER
+ };
+ for (v = 0; v < N_EXCEPTION_STACKS; v++) {
+ if (cpu) {
+ estacks = (char *)__get_free_pages(GFP_ATOMIC, order[v]);
+ if (!estacks)
+ panic("Cannot allocate exception "
+ "stack %ld %d\n", v, cpu);
+ }
+ estacks += PAGE_SIZE << order[v];
+ orig_ist->ist[v] = t->x86_tss.ist[v] =
+ (unsigned long)estacks;
+ }
+ }
+
+ t->x86_tss.io_bitmap_base = offsetof(struct tss_struct, io_bitmap);
+ /*
+ * <= is required because the CPU will access up to
+ * 8 bits beyond the end of the IO permission bitmap.
+ */
+ for (i = 0; i <= IO_BITMAP_LONGS; i++)
+ t->io_bitmap[i] = ~0UL;
+
+ atomic_inc(&init_mm.mm_count);
+ me->active_mm = &init_mm;
+ if (me->mm)
+ BUG();
+ enter_lazy_tlb(&init_mm, me);
+
+ load_sp0(t, ¤t->thread);
+ set_tss_desc(cpu, t);
+ load_TR_desc();
+ load_LDT(&init_mm.context);
+
+ #ifdef CONFIG_KGDB
+ /*
+ * If the kgdb is connected no debug regs should be altered. This
+ * is only applicable when KGDB and a KGDB I/O module are built
+ * into the kernel and you are using early debugging with
+ * kgdbwait. KGDB will control the kernel HW breakpoint registers.
+ */
+ if (kgdb_connected && arch_kgdb_ops.correct_hw_break)
+ arch_kgdb_ops.correct_hw_break();
+ else {
+ #endif
+ /*
+ * Clear all 6 debug registers:
+ */
+
+ set_debugreg(0UL, 0);
+ set_debugreg(0UL, 1);
+ set_debugreg(0UL, 2);
+ set_debugreg(0UL, 3);
+ set_debugreg(0UL, 6);
+ set_debugreg(0UL, 7);
+ #ifdef CONFIG_KGDB
+ /* If the kgdb is connected no debug regs should be altered. */
+ }
+ #endif
+
+ fpu_init();
+
+ raw_local_save_flags(kernel_eflags);
+
+ if (is_uv_system())
+ uv_cpu_init();
+ }
+
+ #else
+
void __cpuinit cpu_init(void)
{
int cpu = smp_processor_id();
/*
* Force FPU initialization:
*/
- current_thread_info()->status = 0;
+ if (cpu_has_xsave)
+ current_thread_info()->status = TS_XSAVE;
+ else
+ current_thread_info()->status = 0;
clear_used_math();
mxcsr_feature_mask_init();
+
+ /*
+ * Boot processor to setup the FP and extended state context info.
+ */
+ if (!smp_processor_id())
+ init_thread_xstate();
+
+ xsave_init();
}
#ifdef CONFIG_HOTPLUG_CPU
per_cpu(cpu_tlbstate, cpu).active_mm = &init_mm;
}
#endif
+
+ #endif
EXPORT_SYMBOL(idle_nomwait);
struct kmem_cache *task_xstate_cachep;
- static int force_mwait __cpuinitdata;
int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src)
{
static void poll_idle(void)
{
local_irq_enable();
- cpu_relax();
+ while (!need_resched())
+ cpu_relax();
}
/*
return 1;
}
+static cpumask_t c1e_mask = CPU_MASK_NONE;
+static int c1e_detected;
+
+void c1e_remove_cpu(int cpu)
+{
+ cpu_clear(cpu, c1e_mask);
+}
+
/*
* C1E aware idle routine. We check for C1E active in the interrupt
* pending message MSR. If we detect C1E, then we handle it the same
*/
static void c1e_idle(void)
{
- static cpumask_t c1e_mask = CPU_MASK_NONE;
- static int c1e_detected;
-
if (need_resched())
return;
rdmsr(MSR_K8_INT_PENDING_MSG, lo, hi);
if (lo & K8_INTP_C1E_ACTIVE_MASK) {
c1e_detected = 1;
- mark_tsc_unstable("TSC halt in C1E");
- printk(KERN_INFO "System has C1E enabled\n");
+ if (!boot_cpu_has(X86_FEATURE_CONSTANT_TSC))
+ mark_tsc_unstable("TSC halt in AMD C1E");
+ printk(KERN_INFO "System has AMD C1E enabled\n");
+ set_cpu_cap(&boot_cpu_data, X86_FEATURE_AMDC1E);
}
}
char __user *pretcode;
int sig;
struct sigcontext sc;
- struct _fpstate fpstate;
+ /*
+ * fpstate is unused. fpstate is moved/allocated after
+ * retcode[] below. This movement allows to have the FP state and the
+ * future state extensions (xsave) stay together.
+ * And at the same time retaining the unused fpstate, prevents changing
+ * the offset of extramask[] in the sigframe and thus prevent any
+ * legacy application accessing/modifying it.
+ */
+ struct _fpstate fpstate_unused;
unsigned long extramask[_NSIG_WORDS-1];
char retcode[8];
+ /* fp state follows here */
};
struct rt_sigframe {
void __user *puc;
struct siginfo info;
struct ucontext uc;
- struct _fpstate fpstate;
char retcode[8];
+ /* fp state follows here */
};
#else
struct rt_sigframe {
char __user *pretcode;
struct ucontext uc;
struct siginfo info;
+ /* fp state follows here */
};
+
+int ia32_setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info,
+ sigset_t *set, struct pt_regs *regs);
+int ia32_setup_frame(int sig, struct k_sigaction *ka,
+ sigset_t *set, struct pt_regs *regs);
#endif
#include <linux/errno.h>
#include <linux/sched.h>
#include <linux/wait.h>
+#include <linux/tracehook.h>
#include <linux/elf.h>
#include <linux/smp.h>
#include <linux/mm.h>
}
{
- struct _fpstate __user *buf;
+ void __user *buf;
err |= __get_user(buf, &sc->fpstate);
- if (buf) {
- if (!access_ok(VERIFY_READ, buf, sizeof(*buf)))
- goto badframe;
- err |= restore_i387(buf);
- } else {
- struct task_struct *me = current;
-
- if (used_math()) {
- clear_fpu(me);
- clear_used_math();
- }
- }
+ err |= restore_i387_xstate(buf);
}
err |= __get_user(*pax, &sc->ax);
return err;
-
- badframe:
- return 1;
}
asmlinkage unsigned long sys_sigreturn(unsigned long __unused)
* Set up a signal frame.
*/
static int
- setup_sigcontext(struct sigcontext __user *sc, struct _fpstate __user *fpstate,
+ setup_sigcontext(struct sigcontext __user *sc, void __user *fpstate,
struct pt_regs *regs, unsigned long mask)
{
int tmp, err = 0;
err |= __put_user(regs->sp, &sc->sp_at_signal);
err |= __put_user(regs->ss, (unsigned int __user *)&sc->ss);
- tmp = save_i387(fpstate);
+ tmp = save_i387_xstate(fpstate);
if (tmp < 0)
err = 1;
else
* Determine which stack to use..
*/
static inline void __user *
- get_sigframe(struct k_sigaction *ka, struct pt_regs *regs, size_t frame_size)
+ get_sigframe(struct k_sigaction *ka, struct pt_regs *regs, size_t frame_size,
+ void **fpstate)
{
unsigned long sp;
sp = (unsigned long) ka->sa.sa_restorer;
}
+ if (used_math()) {
+ sp = sp - sig_xstate_size;
+ *fpstate = (struct _fpstate *) sp;
+ }
+
sp -= frame_size;
/*
* Align the stack pointer according to the i386 ABI,
void __user *restorer;
int err = 0;
int usig;
+ void __user *fpstate = NULL;
- frame = get_sigframe(ka, regs, sizeof(*frame));
+ frame = get_sigframe(ka, regs, sizeof(*frame), &fpstate);
if (!access_ok(VERIFY_WRITE, frame, sizeof(*frame)))
goto give_sigsegv;
if (err)
goto give_sigsegv;
- err = setup_sigcontext(&frame->sc, &frame->fpstate, regs, set->sig[0]);
+ err = setup_sigcontext(&frame->sc, fpstate, regs, set->sig[0]);
if (err)
goto give_sigsegv;
void __user *restorer;
int err = 0;
int usig;
+ void __user *fpstate = NULL;
- frame = get_sigframe(ka, regs, sizeof(*frame));
+ frame = get_sigframe(ka, regs, sizeof(*frame), &fpstate);
if (!access_ok(VERIFY_WRITE, frame, sizeof(*frame)))
goto give_sigsegv;
goto give_sigsegv;
/* Create the ucontext. */
- err |= __put_user(0, &frame->uc.uc_flags);
+ if (cpu_has_xsave)
+ err |= __put_user(UC_FP_XSTATE, &frame->uc.uc_flags);
+ else
+ err |= __put_user(0, &frame->uc.uc_flags);
err |= __put_user(0, &frame->uc.uc_link);
err |= __put_user(current->sas_ss_sp, &frame->uc.uc_stack.ss_sp);
err |= __put_user(sas_ss_flags(regs->sp),
&frame->uc.uc_stack.ss_flags);
err |= __put_user(current->sas_ss_size, &frame->uc.uc_stack.ss_size);
- err |= setup_sigcontext(&frame->uc.uc_mcontext, &frame->fpstate,
+ err |= setup_sigcontext(&frame->uc.uc_mcontext, fpstate,
regs, set->sig[0]);
err |= __copy_to_user(&frame->uc.uc_sigmask, set, sizeof(*set));
if (err)
* handler too.
*/
regs->flags &= ~X86_EFLAGS_TF;
- if (test_thread_flag(TIF_SINGLESTEP))
- ptrace_notify(SIGTRAP);
spin_lock_irq(¤t->sighand->siglock);
sigorsets(¤t->blocked, ¤t->blocked, &ka->sa.sa_mask);
recalc_sigpending();
spin_unlock_irq(¤t->sighand->siglock);
+ tracehook_signal_handler(sig, info, ka, regs,
+ test_thread_flag(TIF_SINGLESTEP));
+
return 0;
}
if (thread_info_flags & _TIF_SIGPENDING)
do_signal(regs);
+ if (thread_info_flags & _TIF_NOTIFY_RESUME) {
+ clear_thread_flag(TIF_NOTIFY_RESUME);
+ tracehook_notify_resume(regs);
+ }
+
clear_thread_flag(TIF_IRET);
}
#include <linux/errno.h>
#include <linux/wait.h>
#include <linux/ptrace.h>
+#include <linux/tracehook.h>
#include <linux/unistd.h>
#include <linux/stddef.h>
#include <linux/personality.h>
#include <linux/compiler.h>
+#include <linux/uaccess.h>
+
#include <asm/processor.h>
#include <asm/ucontext.h>
-#include <asm/uaccess.h>
#include <asm/i387.h>
#include <asm/proto.h>
#include <asm/ia32_unistd.h>
#include <asm/mce.h>
+#include <asm/syscall.h>
#include <asm/syscalls.h>
#include "sigframe.h"
# define FIX_EFLAGS __FIX_EFLAGS
#endif
-int ia32_setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info,
- sigset_t *set, struct pt_regs * regs);
-int ia32_setup_frame(int sig, struct k_sigaction *ka,
- sigset_t *set, struct pt_regs * regs);
-
asmlinkage long
sys_sigaltstack(const stack_t __user *uss, stack_t __user *uoss,
struct pt_regs *regs)
return do_sigaltstack(uss, uoss, regs->sp);
}
- /*
- * Signal frame handlers.
- */
-
- static inline int save_i387(struct _fpstate __user *buf)
- {
- struct task_struct *tsk = current;
- int err = 0;
-
- BUILD_BUG_ON(sizeof(struct user_i387_struct) !=
- sizeof(tsk->thread.xstate->fxsave));
-
- if ((unsigned long)buf % 16)
- printk("save_i387: bad fpstate %p\n", buf);
-
- if (!used_math())
- return 0;
- clear_used_math(); /* trigger finit */
- if (task_thread_info(tsk)->status & TS_USEDFPU) {
- err = save_i387_checking((struct i387_fxsave_struct __user *)
- buf);
- if (err)
- return err;
- task_thread_info(tsk)->status &= ~TS_USEDFPU;
- stts();
- } else {
- if (__copy_to_user(buf, &tsk->thread.xstate->fxsave,
- sizeof(struct i387_fxsave_struct)))
- return -1;
- }
- return 1;
- }
-
- /*
- * This restores directly out of user space. Exceptions are handled.
- */
- static inline int restore_i387(struct _fpstate __user *buf)
- {
- struct task_struct *tsk = current;
- int err;
-
- if (!used_math()) {
- err = init_fpu(tsk);
- if (err)
- return err;
- }
-
- if (!(task_thread_info(current)->status & TS_USEDFPU)) {
- clts();
- task_thread_info(current)->status |= TS_USEDFPU;
- }
- err = restore_fpu_checking((__force struct i387_fxsave_struct *)buf);
- if (unlikely(err)) {
- /*
- * Encountered an error while doing the restore from the
- * user buffer, clear the fpu state.
- */
- clear_fpu(tsk);
- clear_used_math();
- }
- return err;
- }
-
/*
* Do a signal return; undo the signal stack.
*/
/* Always make any pending restarted system calls return -EINTR */
current_thread_info()->restart_block.fn = do_no_restart_syscall;
-#define COPY(x) err |= __get_user(regs->x, &sc->x)
+#define COPY(x) (err |= __get_user(regs->x, &sc->x))
COPY(di); COPY(si); COPY(bp); COPY(sp); COPY(bx);
COPY(dx); COPY(cx); COPY(ip);
}
{
- struct _fpstate __user * buf;
+ struct _fpstate __user *buf;
err |= __get_user(buf, &sc->fpstate);
-
- if (buf) {
- if (!access_ok(VERIFY_READ, buf, sizeof(*buf)))
- goto badframe;
- err |= restore_i387(buf);
- } else {
- struct task_struct *me = current;
- if (used_math()) {
- clear_fpu(me);
- clear_used_math();
- }
- }
+ err |= restore_i387_xstate(buf);
}
err |= __get_user(*pax, &sc->ax);
return err;
-
- badframe:
- return 1;
}
asmlinkage long sys_rt_sigreturn(struct pt_regs *regs)
current->blocked = set;
recalc_sigpending();
spin_unlock_irq(¤t->sighand->siglock);
-
+
if (restore_sigcontext(regs, &frame->uc.uc_mcontext, &ax))
goto badframe;
return ax;
badframe:
- signal_fault(regs,frame,"sigreturn");
+ signal_fault(regs, frame, "sigreturn");
return 0;
-}
+}
/*
* Set up a signal frame.
*/
static inline int
-setup_sigcontext(struct sigcontext __user *sc, struct pt_regs *regs, unsigned long mask, struct task_struct *me)
+setup_sigcontext(struct sigcontext __user *sc, struct pt_regs *regs,
+ unsigned long mask, struct task_struct *me)
{
int err = 0;
sp = current->sas_ss_sp + current->sas_ss_size;
}
- return (void __user *)round_down(sp - size, 16);
+ return (void __user *)round_down(sp - size, 64);
}
static int setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info,
- sigset_t *set, struct pt_regs * regs)
+ sigset_t *set, struct pt_regs *regs)
{
struct rt_sigframe __user *frame;
- struct _fpstate __user *fp = NULL;
+ void __user *fp = NULL;
int err = 0;
struct task_struct *me = current;
if (used_math()) {
- fp = get_stack(ka, regs, sizeof(struct _fpstate));
+ fp = get_stack(ka, regs, sig_xstate_size);
frame = (void __user *)round_down(
(unsigned long)fp - sizeof(struct rt_sigframe), 16) - 8;
- if (!access_ok(VERIFY_WRITE, fp, sizeof(struct _fpstate)))
- goto give_sigsegv;
-
- if (save_i387(fp) < 0)
+ if (save_i387_xstate(fp) < 0)
- err |= -1;
+ err |= -1;
} else
frame = get_stack(ka, regs, sizeof(struct rt_sigframe)) - 8;
if (!access_ok(VERIFY_WRITE, frame, sizeof(*frame)))
goto give_sigsegv;
- if (ka->sa.sa_flags & SA_SIGINFO) {
+ if (ka->sa.sa_flags & SA_SIGINFO) {
err |= copy_siginfo_to_user(&frame->info, info);
if (err)
goto give_sigsegv;
}
-
+
/* Create the ucontext. */
- err |= __put_user(0, &frame->uc.uc_flags);
+ if (cpu_has_xsave)
+ err |= __put_user(UC_FP_XSTATE, &frame->uc.uc_flags);
+ else
+ err |= __put_user(0, &frame->uc.uc_flags);
err |= __put_user(0, &frame->uc.uc_link);
err |= __put_user(me->sas_ss_sp, &frame->uc.uc_stack.ss_sp);
err |= __put_user(sas_ss_flags(regs->sp),
err |= __put_user(me->sas_ss_size, &frame->uc.uc_stack.ss_size);
err |= setup_sigcontext(&frame->uc.uc_mcontext, regs, set->sig[0], me);
err |= __put_user(fp, &frame->uc.uc_mcontext.fpstate);
- if (sizeof(*set) == 16) {
+ if (sizeof(*set) == 16) {
__put_user(set->sig[0], &frame->uc.uc_sigmask.sig[0]);
- __put_user(set->sig[1], &frame->uc.uc_sigmask.sig[1]);
+ __put_user(set->sig[1], &frame->uc.uc_sigmask.sig[1]);
} else
err |= __copy_to_user(&frame->uc.uc_sigmask, set, sizeof(*set));
err |= __put_user(ka->sa.sa_restorer, &frame->pretcode);
} else {
/* could use a vstub here */
- goto give_sigsegv;
+ goto give_sigsegv;
}
if (err)
/* Set up registers for signal handler */
regs->di = sig;
- /* In case the signal handler was declared without prototypes */
+ /* In case the signal handler was declared without prototypes */
regs->ax = 0;
/* This also works for non SA_SIGINFO handlers because they expect the
return -EFAULT;
}
-/*
- * Return -1L or the syscall number that @regs is executing.
- */
-static long current_syscall(struct pt_regs *regs)
-{
- /*
- * We always sign-extend a -1 value being set here,
- * so this is always either -1L or a syscall number.
- */
- return regs->orig_ax;
-}
-
-/*
- * Return a value that is -EFOO if the system call in @regs->orig_ax
- * returned an error. This only works for @regs from @current.
- */
-static long current_syscall_ret(struct pt_regs *regs)
-{
-#ifdef CONFIG_IA32_EMULATION
- if (test_thread_flag(TIF_IA32))
- /*
- * Sign-extend the value so (int)-EFOO becomes (long)-EFOO
- * and will match correctly in comparisons.
- */
- return (int) regs->ax;
-#endif
- return regs->ax;
-}
-
/*
* OK, we're invoking a handler
- */
+ */
static int
handle_signal(unsigned long sig, siginfo_t *info, struct k_sigaction *ka,
int ret;
/* Are we from a system call? */
- if (current_syscall(regs) >= 0) {
+ if (syscall_get_nr(current, regs) >= 0) {
/* If so, check system call restarting.. */
- switch (current_syscall_ret(regs)) {
+ switch (syscall_get_error(current, regs)) {
case -ERESTART_RESTARTBLOCK:
case -ERESTARTNOHAND:
regs->ax = -EINTR;
ret = ia32_setup_rt_frame(sig, ka, info, oldset, regs);
else
ret = ia32_setup_frame(sig, ka, oldset, regs);
- } else
+ } else
#endif
ret = setup_rt_frame(sig, ka, info, oldset, regs);
* handler too.
*/
regs->flags &= ~X86_EFLAGS_TF;
- if (test_thread_flag(TIF_SINGLESTEP))
- ptrace_notify(SIGTRAP);
spin_lock_irq(¤t->sighand->siglock);
- sigorsets(¤t->blocked,¤t->blocked,&ka->sa.sa_mask);
+ sigorsets(¤t->blocked, ¤t->blocked, &ka->sa.sa_mask);
if (!(ka->sa.sa_flags & SA_NODEFER))
- sigaddset(¤t->blocked,sig);
+ sigaddset(¤t->blocked, sig);
recalc_sigpending();
spin_unlock_irq(¤t->sighand->siglock);
+
+ tracehook_signal_handler(sig, info, ka, regs,
+ test_thread_flag(TIF_SINGLESTEP));
}
return ret;
}
/* Did we come from a system call? */
- if (current_syscall(regs) >= 0) {
+ if (syscall_get_nr(current, regs) >= 0) {
/* Restart the system call - no handlers present */
- switch (current_syscall_ret(regs)) {
+ switch (syscall_get_error(current, regs)) {
case -ERESTARTNOHAND:
case -ERESTARTSYS:
case -ERESTARTNOINTR:
/* deal with pending signal delivery */
if (thread_info_flags & _TIF_SIGPENDING)
do_signal(regs);
+
+ if (thread_info_flags & _TIF_NOTIFY_RESUME) {
+ clear_thread_flag(TIF_NOTIFY_RESUME);
+ tracehook_notify_resume(regs);
+ }
}
void signal_fault(struct pt_regs *regs, void __user *frame, char *where)
-{
- struct task_struct *me = current;
+{
+ struct task_struct *me = current;
if (show_unhandled_signals && printk_ratelimit()) {
printk("%s[%d] bad frame in %s frame:%p ip:%lx sp:%lx orax:%lx",
- me->comm,me->pid,where,frame,regs->ip,regs->sp,regs->orig_ax);
+ me->comm, me->pid, where, frame, regs->ip,
+ regs->sp, regs->orig_ax);
print_vma_addr(" in ", regs->ip);
printk("\n");
}
- force_sig(SIGSEGV, me);
-}
+ force_sig(SIGSEGV, me);
+}
#include <linux/bug.h>
#include <linux/nmi.h>
#include <linux/mm.h>
+#include <linux/smp.h>
+#include <linux/io.h>
#if defined(CONFIG_EDAC)
#include <linux/edac.h>
#include <asm/unwind.h>
#include <asm/desc.h>
#include <asm/i387.h>
-#include <asm/nmi.h>
-#include <asm/smp.h>
-#include <asm/io.h>
#include <asm/pgalloc.h>
#include <asm/proto.h>
#include <asm/pda.h>
void printk_address(unsigned long address, int reliable)
{
- printk(" [<%016lx>] %s%pS\n", address, reliable ? "": "? ", (void *) address);
+ printk(" [<%016lx>] %s%pS\n",
+ address, reliable ? "" : "? ", (void *) address);
}
static unsigned long *in_exception_stack(unsigned cpu, unsigned long stack,
[STACKFAULT_STACK - 1] = "#SS",
[MCE_STACK - 1] = "#MC",
#if DEBUG_STKSZ > EXCEPTION_STKSZ
- [N_EXCEPTION_STACKS ... N_EXCEPTION_STACKS + DEBUG_STKSZ / EXCEPTION_STKSZ - 2] = "#DB[?]"
+ [N_EXCEPTION_STACKS ...
+ N_EXCEPTION_STACKS + DEBUG_STKSZ / EXCEPTION_STKSZ - 2] = "#DB[?]"
#endif
};
unsigned k;
}
/*
- * x86-64 can have up to three kernel stacks:
+ * x86-64 can have up to three kernel stacks:
* process stack
* interrupt stack
* severe exception (double fault, nmi, stack fault, debug, mce) hardware stack
const struct stacktrace_ops *ops, void *data)
{
const unsigned cpu = get_cpu();
- unsigned long *irqstack_end = (unsigned long*)cpu_pda(cpu)->irqstackptr;
+ unsigned long *irqstack_end = (unsigned long *)cpu_pda(cpu)->irqstackptr;
unsigned used = 0;
struct thread_info *tinfo;
if (!bp) {
if (task == current) {
/* Grab bp right from our regs */
- asm("movq %%rbp, %0" : "=r" (bp) :);
+ asm("movq %%rbp, %0" : "=r" (bp) : );
} else {
/* bp is the last reg pushed by switch_to */
bp = *(unsigned long *) task->thread.sp;
unsigned long *stack;
int i;
const int cpu = smp_processor_id();
- unsigned long *irqstack_end = (unsigned long *) (cpu_pda(cpu)->irqstackptr);
- unsigned long *irqstack = (unsigned long *) (cpu_pda(cpu)->irqstackptr - IRQSTACKSIZE);
+ unsigned long *irqstack_end =
+ (unsigned long *) (cpu_pda(cpu)->irqstackptr);
+ unsigned long *irqstack =
+ (unsigned long *) (cpu_pda(cpu)->irqstackptr - IRQSTACKSIZE);
- // debugging aid: "show_stack(NULL, NULL);" prints the
- // back trace for this cpu.
+ /*
+ * debugging aid: "show_stack(NULL, NULL);" prints the
+ * back trace for this cpu.
+ */
if (sp == NULL) {
if (task)
#ifdef CONFIG_FRAME_POINTER
if (!bp)
- asm("movq %%rbp, %0" : "=r" (bp):);
+ asm("movq %%rbp, %0" : "=r" (bp) : );
#endif
printk("Pid: %d, comm: %.20s %s %s %.*s\n",
init_utsname()->version);
show_trace(NULL, NULL, &stack, bp);
}
-
EXPORT_SYMBOL(dump_stack);
void show_registers(struct pt_regs *regs)
raw_local_irq_save(flags);
cpu = smp_processor_id();
if (!__raw_spin_trylock(&die_lock)) {
- if (cpu == die_owner)
+ if (cpu == die_owner)
/* nested oops. should stop eventually */;
else
__raw_spin_lock(&die_lock);
}
#define DO_ERROR(trapnr, signr, str, name) \
-asmlinkage void do_##name(struct pt_regs * regs, long error_code) \
+asmlinkage void do_##name(struct pt_regs *regs, long error_code) \
{ \
if (notify_die(DIE_TRAP, str, regs, error_code, trapnr, signr) \
== NOTIFY_STOP) \
}
#define DO_ERROR_INFO(trapnr, signr, str, name, sicode, siaddr) \
-asmlinkage void do_##name(struct pt_regs * regs, long error_code) \
+asmlinkage void do_##name(struct pt_regs *regs, long error_code) \
{ \
siginfo_t info; \
info.si_signo = signr; \
preempt_conditional_cli(regs);
}
-asmlinkage void do_double_fault(struct pt_regs * regs, long error_code)
+asmlinkage void do_double_fault(struct pt_regs *regs, long error_code)
{
static const char str[] = "double fault";
struct task_struct *tsk = current;
}
static notrace __kprobes void
-unknown_nmi_error(unsigned char reason, struct pt_regs * regs)
+unknown_nmi_error(unsigned char reason, struct pt_regs *regs)
{
- if (notify_die(DIE_NMIUNKNOWN, "nmi", regs, reason, 2, SIGINT) == NOTIFY_STOP)
+ if (notify_die(DIE_NMIUNKNOWN, "nmi", regs, reason, 2, SIGINT) ==
+ NOTIFY_STOP)
return;
printk(KERN_EMERG "Uhhuh. NMI received for unknown reason %02x.\n",
reason);
else if (user_mode(eregs))
regs = task_pt_regs(current);
/* Exception from kernel and interrupts are enabled. Move to
- kernel process stack. */
+ kernel process stack. */
else if (eregs->flags & X86_EFLAGS_IF)
regs = (struct pt_regs *)(eregs->sp -= sizeof(struct pt_regs));
if (eregs != regs)
}
/* runs on IST stack. */
-asmlinkage void __kprobes do_debug(struct pt_regs * regs,
+asmlinkage void __kprobes do_debug(struct pt_regs *regs,
unsigned long error_code)
{
struct task_struct *tsk = current;
asmlinkage void bad_intr(void)
{
- printk("bad interrupt");
+ printk("bad interrupt");
}
asmlinkage void do_simd_coprocessor_error(struct pt_regs *regs)
conditional_sti(regs);
if (!user_mode(regs) &&
- kernel_math_error(regs, "kernel simd math error", 19))
+ kernel_math_error(regs, "kernel simd math error", 19))
return;
/*
force_sig_info(SIGFPE, &info, task);
}
-asmlinkage void do_spurious_interrupt_bug(struct pt_regs * regs)
+asmlinkage void do_spurious_interrupt_bug(struct pt_regs *regs)
{
}
/*
* Paranoid restore. send a SIGSEGV if we fail to restore the state.
*/
- if (unlikely(restore_fpu_checking(&me->thread.xstate->fxsave))) {
+ if (unlikely(restore_fpu_checking(me))) {
stts();
force_sig(SIGSEGV, me);
return;
set_intr_gate(0, ÷_error);
set_intr_gate_ist(1, &debug, DEBUG_STACK);
set_intr_gate_ist(2, &nmi, NMI_STACK);
- set_system_gate_ist(3, &int3, DEBUG_STACK); /* int3 can be called from all */
- set_system_gate(4, &overflow); /* int4 can be called from all */
+ /* int3 can be called from all */
+ set_system_gate_ist(3, &int3, DEBUG_STACK);
+ /* int4 can be called from all */
+ set_system_gate(4, &overflow);
set_intr_gate(5, &bounds);
set_intr_gate(6, &invalid_op);
set_intr_gate(7, &device_not_available);
#ifdef CONFIG_IA32_EMULATION
set_system_gate(IA32_SYSCALL_VECTOR, ia32_syscall);
#endif
- /*
- * initialize the per thread extended state:
- */
- init_thread_xstate();
/*
* Should be a barrier for any external CPU state:
*/
#define AR_RESERVD_MASK 0xfffe0f00
- #define MSR_IA32_VMX_BASIC 0x480
- #define MSR_IA32_VMX_PINBASED_CTLS 0x481
- #define MSR_IA32_VMX_PROCBASED_CTLS 0x482
- #define MSR_IA32_VMX_EXIT_CTLS 0x483
- #define MSR_IA32_VMX_ENTRY_CTLS 0x484
- #define MSR_IA32_VMX_MISC 0x485
- #define MSR_IA32_VMX_CR0_FIXED0 0x486
- #define MSR_IA32_VMX_CR0_FIXED1 0x487
- #define MSR_IA32_VMX_CR4_FIXED0 0x488
- #define MSR_IA32_VMX_CR4_FIXED1 0x489
- #define MSR_IA32_VMX_VMCS_ENUM 0x48a
- #define MSR_IA32_VMX_PROCBASED_CTLS2 0x48b
- #define MSR_IA32_VMX_EPT_VPID_CAP 0x48c
-
- #define MSR_IA32_FEATURE_CONTROL 0x3a
#define MSR_IA32_FEATURE_CONTROL_LOCKED 0x1
#define MSR_IA32_FEATURE_CONTROL_VMXON_ENABLED 0x4
#define VMX_EPT_READABLE_MASK 0x1ull
#define VMX_EPT_WRITABLE_MASK 0x2ull
#define VMX_EPT_EXECUTABLE_MASK 0x4ull
-#define VMX_EPT_FAKE_ACCESSED_MASK (1ull << 62)
-#define VMX_EPT_FAKE_DIRTY_MASK (1ull << 63)
#define VMX_EPT_IDENTITY_PAGETABLE_ADDR 0xfffbc000ul
int after_bootmem;
+ unsigned long __supported_pte_mask __read_mostly = ~0UL;
+ EXPORT_SYMBOL_GPL(__supported_pte_mask);
+
+ static int do_not_nx __cpuinitdata;
+
+ /*
+ * noexec=on|off
+ * Control non-executable mappings for 64-bit processes.
+ *
+ * on Enable (default)
+ * off Disable
+ */
+ static int __init nonx_setup(char *str)
+ {
+ if (!str)
+ return -EINVAL;
+ if (!strncmp(str, "on", 2)) {
+ __supported_pte_mask |= _PAGE_NX;
+ do_not_nx = 0;
+ } else if (!strncmp(str, "off", 3)) {
+ do_not_nx = 1;
+ __supported_pte_mask &= ~_PAGE_NX;
+ }
+ return 0;
+ }
+ early_param("noexec", nonx_setup);
+
+ void __cpuinit check_efer(void)
+ {
+ unsigned long efer;
+
+ rdmsrl(MSR_EFER, efer);
+ if (!(efer & EFER_NX) || do_not_nx)
+ __supported_pte_mask &= ~_PAGE_NX;
+ }
+
+ int force_personality32;
+
+ /*
+ * noexec32=on|off
+ * Control non executable heap for 32bit processes.
+ * To control the stack too use noexec=off
+ *
+ * on PROT_READ does not imply PROT_EXEC for 32-bit processes (default)
+ * off PROT_READ implies PROT_EXEC
+ */
+ static int __init nonx32_setup(char *str)
+ {
+ if (!strcmp(str, "on"))
+ force_personality32 &= ~READ_IMPLIES_EXEC;
+ else if (!strcmp(str, "off"))
+ force_personality32 |= READ_IMPLIES_EXEC;
+ return 1;
+ }
+ __setup("noexec32=", nonx32_setup);
+
/*
* NOTE: This function is marked __ref because it calls __init function
* (alloc_bootmem_pages). It's safe to do it ONLY when after_bootmem == 0.
void __init cleanup_highmap(void)
{
unsigned long vaddr = __START_KERNEL_map;
- unsigned long end = round_up((unsigned long)_end, PMD_SIZE) - 1;
+ unsigned long end = roundup((unsigned long)_end, PMD_SIZE) - 1;
pmd_t *pmd = level2_kernel_pgt;
pmd_t *last_pmd = pmd + PTRS_PER_PMD;
}
static unsigned long __meminit
-phys_pte_init(pte_t *pte_page, unsigned long addr, unsigned long end)
+phys_pte_init(pte_t *pte_page, unsigned long addr, unsigned long end,
+ pgprot_t prot)
{
unsigned pages = 0;
unsigned long last_map_addr = end;
break;
}
+ /*
+ * We will re-use the existing mapping.
+ * Xen for example has some special requirements, like mapping
+ * pagetable pages as RO. So assume someone who pre-setup
+ * these mappings are more intelligent.
+ */
if (pte_val(*pte))
continue;
if (0)
printk(" pte=%p addr=%lx pte=%016lx\n",
pte, addr, pfn_pte(addr >> PAGE_SHIFT, PAGE_KERNEL).pte);
- set_pte(pte, pfn_pte(addr >> PAGE_SHIFT, PAGE_KERNEL));
- last_map_addr = (addr & PAGE_MASK) + PAGE_SIZE;
pages++;
+ set_pte(pte, pfn_pte(addr >> PAGE_SHIFT, prot));
+ last_map_addr = (addr & PAGE_MASK) + PAGE_SIZE;
}
+
update_page_count(PG_LEVEL_4K, pages);
return last_map_addr;
}
static unsigned long __meminit
-phys_pte_update(pmd_t *pmd, unsigned long address, unsigned long end)
+phys_pte_update(pmd_t *pmd, unsigned long address, unsigned long end,
+ pgprot_t prot)
{
pte_t *pte = (pte_t *)pmd_page_vaddr(*pmd);
- return phys_pte_init(pte, address, end);
+ return phys_pte_init(pte, address, end, prot);
}
static unsigned long __meminit
phys_pmd_init(pmd_t *pmd_page, unsigned long address, unsigned long end,
- unsigned long page_size_mask)
+ unsigned long page_size_mask, pgprot_t prot)
{
unsigned long pages = 0;
unsigned long last_map_addr = end;
- unsigned long start = address;
int i = pmd_index(address);
unsigned long pte_phys;
pmd_t *pmd = pmd_page + pmd_index(address);
pte_t *pte;
+ pgprot_t new_prot = prot;
if (address >= end) {
if (!after_bootmem) {
if (!pmd_large(*pmd)) {
spin_lock(&init_mm.page_table_lock);
last_map_addr = phys_pte_update(pmd, address,
- end);
+ end, prot);
spin_unlock(&init_mm.page_table_lock);
+ continue;
}
- /* Count entries we're using from level2_ident_pgt */
- if (start == 0)
- pages++;
- continue;
+ /*
+ * If we are ok with PG_LEVEL_2M mapping, then we will
+ * use the existing mapping,
+ *
+ * Otherwise, we will split the large page mapping but
+ * use the same existing protection bits except for
+ * large page, so that we don't violate Intel's TLB
+ * Application note (317080) which says, while changing
+ * the page sizes, new and old translations should
+ * not differ with respect to page frame and
+ * attributes.
+ */
+ if (page_size_mask & (1 << PG_LEVEL_2M))
+ continue;
+ new_prot = pte_pgprot(pte_clrhuge(*(pte_t *)pmd));
}
if (page_size_mask & (1<<PG_LEVEL_2M)) {
pages++;
spin_lock(&init_mm.page_table_lock);
set_pte((pte_t *)pmd,
- pfn_pte(address >> PAGE_SHIFT, PAGE_KERNEL_LARGE));
+ pfn_pte(address >> PAGE_SHIFT,
+ __pgprot(pgprot_val(prot) | _PAGE_PSE)));
spin_unlock(&init_mm.page_table_lock);
last_map_addr = (address & PMD_MASK) + PMD_SIZE;
continue;
}
pte = alloc_low_page(&pte_phys);
- last_map_addr = phys_pte_init(pte, address, end);
+ last_map_addr = phys_pte_init(pte, address, end, new_prot);
unmap_low_page(pte);
spin_lock(&init_mm.page_table_lock);
static unsigned long __meminit
phys_pmd_update(pud_t *pud, unsigned long address, unsigned long end,
- unsigned long page_size_mask)
+ unsigned long page_size_mask, pgprot_t prot)
{
pmd_t *pmd = pmd_offset(pud, 0);
unsigned long last_map_addr;
- last_map_addr = phys_pmd_init(pmd, address, end, page_size_mask);
+ last_map_addr = phys_pmd_init(pmd, address, end, page_size_mask, prot);
__flush_tlb_all();
return last_map_addr;
}
unsigned long pmd_phys;
pud_t *pud = pud_page + pud_index(addr);
pmd_t *pmd;
+ pgprot_t prot = PAGE_KERNEL;
if (addr >= end)
break;
}
if (pud_val(*pud)) {
- if (!pud_large(*pud))
+ if (!pud_large(*pud)) {
last_map_addr = phys_pmd_update(pud, addr, end,
- page_size_mask);
- continue;
+ page_size_mask, prot);
+ continue;
+ }
+ /*
+ * If we are ok with PG_LEVEL_1G mapping, then we will
+ * use the existing mapping.
+ *
+ * Otherwise, we will split the gbpage mapping but use
+ * the same existing protection bits except for large
+ * page, so that we don't violate Intel's TLB
+ * Application note (317080) which says, while changing
+ * the page sizes, new and old translations should
+ * not differ with respect to page frame and
+ * attributes.
+ */
+ if (page_size_mask & (1 << PG_LEVEL_1G))
+ continue;
+ prot = pte_pgprot(pte_clrhuge(*(pte_t *)pud));
}
if (page_size_mask & (1<<PG_LEVEL_1G)) {
}
pmd = alloc_low_page(&pmd_phys);
- last_map_addr = phys_pmd_init(pmd, addr, end, page_size_mask);
+ last_map_addr = phys_pmd_init(pmd, addr, end, page_size_mask,
+ prot);
unmap_low_page(pmd);
spin_lock(&init_mm.page_table_lock);
spin_unlock(&init_mm.page_table_lock);
}
__flush_tlb_all();
+
update_page_count(PG_LEVEL_1G, pages);
return last_map_addr;
return phys_pud_init(pud, addr, end, page_size_mask);
}
-static void __init find_early_table_space(unsigned long end)
+static void __init find_early_table_space(unsigned long end, int use_pse,
+ int use_gbpages)
{
unsigned long puds, pmds, ptes, tables, start;
puds = (end + PUD_SIZE - 1) >> PUD_SHIFT;
- tables = round_up(puds * sizeof(pud_t), PAGE_SIZE);
- if (direct_gbpages) {
+ tables = roundup(puds * sizeof(pud_t), PAGE_SIZE);
+ if (use_gbpages) {
unsigned long extra;
extra = end - ((end>>PUD_SHIFT) << PUD_SHIFT);
pmds = (extra + PMD_SIZE - 1) >> PMD_SHIFT;
} else
pmds = (end + PMD_SIZE - 1) >> PMD_SHIFT;
- tables += round_up(pmds * sizeof(pmd_t), PAGE_SIZE);
+ tables += roundup(pmds * sizeof(pmd_t), PAGE_SIZE);
- if (cpu_has_pse) {
+ if (use_pse) {
unsigned long extra;
extra = end - ((end>>PMD_SHIFT) << PMD_SHIFT);
ptes = (extra + PAGE_SIZE - 1) >> PAGE_SHIFT;
} else
ptes = (end + PAGE_SIZE - 1) >> PAGE_SHIFT;
- tables += round_up(ptes * sizeof(pte_t), PAGE_SIZE);
+ tables += roundup(ptes * sizeof(pte_t), PAGE_SIZE);
/*
* RED-PEN putting page tables only on node 0 could
pgd_populate(&init_mm, pgd, __va(pud_phys));
spin_unlock(&init_mm.page_table_lock);
}
+ __flush_tlb_all();
return last_map_addr;
}
struct map_range mr[NR_RANGE_MR];
int nr_range, i;
+ int use_pse, use_gbpages;
printk(KERN_INFO "init_memory_mapping\n");
if (!after_bootmem)
init_gbpages();
- if (direct_gbpages)
+#ifdef CONFIG_DEBUG_PAGEALLOC
+ /*
+ * For CONFIG_DEBUG_PAGEALLOC, identity mapping will use small pages.
+ * This will simplify cpa(), which otherwise needs to support splitting
+ * large pages into small in interrupt context, etc.
+ */
+ use_pse = use_gbpages = 0;
+#else
+ use_pse = cpu_has_pse;
+ use_gbpages = direct_gbpages;
+#endif
+
+ if (use_gbpages)
page_size_mask |= 1 << PG_LEVEL_1G;
- if (cpu_has_pse)
+ if (use_pse)
page_size_mask |= 1 << PG_LEVEL_2M;
memset(mr, 0, sizeof(mr));
(mr[i].page_size_mask & (1<<PG_LEVEL_2M))?"2M":"4k"));
if (!after_bootmem)
- find_early_table_space(end);
+ find_early_table_space(end, use_pse, use_gbpages);
for (i = 0; i < nr_range; i++)
last_map_addr = kernel_physical_mapping_init(
reservedpages << (PAGE_SHIFT-10),
datasize >> 10,
initsize >> 10);
-
- cpa_init();
}
void free_init_pages(char *what, unsigned long begin, unsigned long end)
#include <asm/required-features.h>
- #define NCAPINTS 8 /* N 32-bit words worth of info */
+ #define NCAPINTS 9 /* N 32-bit words worth of info */
+
+ /*
+ * Note: If the comment begins with a quoted string, that string is used
+ * in /proc/cpuinfo instead of the macro name. If the string is "",
+ * this feature bit is not displayed in /proc/cpuinfo at all.
+ */
/* Intel-defined CPU features, CPUID level 0x00000001 (edx), word 0 */
#define X86_FEATURE_FPU (0*32+ 0) /* Onboard FPU */
#define X86_FEATURE_DE (0*32+ 2) /* Debugging Extensions */
#define X86_FEATURE_PSE (0*32+ 3) /* Page Size Extensions */
#define X86_FEATURE_TSC (0*32+ 4) /* Time Stamp Counter */
- #define X86_FEATURE_MSR (0*32+ 5) /* Model-Specific Registers, RDMSR, WRMSR */
+ #define X86_FEATURE_MSR (0*32+ 5) /* Model-Specific Registers */
#define X86_FEATURE_PAE (0*32+ 6) /* Physical Address Extensions */
#define X86_FEATURE_MCE (0*32+ 7) /* Machine Check Architecture */
#define X86_FEATURE_CX8 (0*32+ 8) /* CMPXCHG8 instruction */
#define X86_FEATURE_MTRR (0*32+12) /* Memory Type Range Registers */
#define X86_FEATURE_PGE (0*32+13) /* Page Global Enable */
#define X86_FEATURE_MCA (0*32+14) /* Machine Check Architecture */
- #define X86_FEATURE_CMOV (0*32+15) /* CMOV instruction (FCMOVCC and FCOMI too if FPU present) */
+ #define X86_FEATURE_CMOV (0*32+15) /* CMOV instructions */
+ /* (plus FCMOVcc, FCOMI with FPU) */
#define X86_FEATURE_PAT (0*32+16) /* Page Attribute Table */
#define X86_FEATURE_PSE36 (0*32+17) /* 36-bit PSEs */
#define X86_FEATURE_PN (0*32+18) /* Processor serial number */
- #define X86_FEATURE_CLFLSH (0*32+19) /* Supports the CLFLUSH instruction */
- #define X86_FEATURE_DS (0*32+21) /* Debug Store */
+ #define X86_FEATURE_CLFLSH (0*32+19) /* "clflush" CLFLUSH instruction */
+ #define X86_FEATURE_DS (0*32+21) /* "dts" Debug Store */
#define X86_FEATURE_ACPI (0*32+22) /* ACPI via MSR */
#define X86_FEATURE_MMX (0*32+23) /* Multimedia Extensions */
- #define X86_FEATURE_FXSR (0*32+24) /* FXSAVE and FXRSTOR instructions (fast save and restore */
- /* of FPU context), and CR4.OSFXSR available */
- #define X86_FEATURE_XMM (0*32+25) /* Streaming SIMD Extensions */
- #define X86_FEATURE_XMM2 (0*32+26) /* Streaming SIMD Extensions-2 */
- #define X86_FEATURE_SELFSNOOP (0*32+27) /* CPU self snoop */
+ #define X86_FEATURE_FXSR (0*32+24) /* FXSAVE/FXRSTOR, CR4.OSFXSR */
+ #define X86_FEATURE_XMM (0*32+25) /* "sse" */
+ #define X86_FEATURE_XMM2 (0*32+26) /* "sse2" */
+ #define X86_FEATURE_SELFSNOOP (0*32+27) /* "ss" CPU self snoop */
#define X86_FEATURE_HT (0*32+28) /* Hyper-Threading */
- #define X86_FEATURE_ACC (0*32+29) /* Automatic clock control */
+ #define X86_FEATURE_ACC (0*32+29) /* "tm" Automatic clock control */
#define X86_FEATURE_IA64 (0*32+30) /* IA-64 processor */
+ #define X86_FEATURE_PBE (0*32+31) /* Pending Break Enable */
/* AMD-defined CPU features, CPUID level 0x80000001, word 1 */
/* Don't duplicate feature flags which are redundant with Intel! */
#define X86_FEATURE_MP (1*32+19) /* MP Capable. */
#define X86_FEATURE_NX (1*32+20) /* Execute Disable */
#define X86_FEATURE_MMXEXT (1*32+22) /* AMD MMX extensions */
- #define X86_FEATURE_GBPAGES (1*32+26) /* GB pages */
+ #define X86_FEATURE_FXSR_OPT (1*32+25) /* FXSAVE/FXRSTOR optimizations */
+ #define X86_FEATURE_GBPAGES (1*32+26) /* "pdpe1gb" GB pages */
#define X86_FEATURE_RDTSCP (1*32+27) /* RDTSCP */
#define X86_FEATURE_LM (1*32+29) /* Long Mode (x86-64) */
#define X86_FEATURE_3DNOWEXT (1*32+30) /* AMD 3DNow! extensions */
#define X86_FEATURE_CYRIX_ARR (3*32+ 2) /* Cyrix ARRs (= MTRRs) */
#define X86_FEATURE_CENTAUR_MCR (3*32+ 3) /* Centaur MCRs (= MTRRs) */
/* cpu types for specific tunings: */
- #define X86_FEATURE_K8 (3*32+ 4) /* Opteron, Athlon64 */
- #define X86_FEATURE_K7 (3*32+ 5) /* Athlon */
- #define X86_FEATURE_P3 (3*32+ 6) /* P3 */
- #define X86_FEATURE_P4 (3*32+ 7) /* P4 */
+ #define X86_FEATURE_K8 (3*32+ 4) /* "" Opteron, Athlon64 */
+ #define X86_FEATURE_K7 (3*32+ 5) /* "" Athlon */
+ #define X86_FEATURE_P3 (3*32+ 6) /* "" P3 */
+ #define X86_FEATURE_P4 (3*32+ 7) /* "" P4 */
#define X86_FEATURE_CONSTANT_TSC (3*32+ 8) /* TSC ticks at a constant rate */
#define X86_FEATURE_UP (3*32+ 9) /* smp kernel running on up */
- #define X86_FEATURE_FXSAVE_LEAK (3*32+10) /* FXSAVE leaks FOP/FIP/FOP */
+ #define X86_FEATURE_FXSAVE_LEAK (3*32+10) /* "" FXSAVE leaks FOP/FIP/FOP */
#define X86_FEATURE_ARCH_PERFMON (3*32+11) /* Intel Architectural PerfMon */
++#define X86_FEATURE_NOPL (3*32+20) /* The NOPL (0F 1F) instructions */
#define X86_FEATURE_PEBS (3*32+12) /* Precise-Event Based Sampling */
#define X86_FEATURE_BTS (3*32+13) /* Branch Trace Store */
- #define X86_FEATURE_SYSCALL32 (3*32+14) /* syscall in ia32 userspace */
- #define X86_FEATURE_SYSENTER32 (3*32+15) /* sysenter in ia32 userspace */
- #define X86_FEATURE_REP_GOOD (3*32+16) /* rep microcode works well on this CPU */
- #define X86_FEATURE_MFENCE_RDTSC (3*32+17) /* Mfence synchronizes RDTSC */
- #define X86_FEATURE_LFENCE_RDTSC (3*32+18) /* Lfence synchronizes RDTSC */
- #define X86_FEATURE_11AP (3*32+19) /* Bad local APIC aka 11AP */
+ #define X86_FEATURE_SYSCALL32 (3*32+14) /* "" syscall in ia32 userspace */
+ #define X86_FEATURE_SYSENTER32 (3*32+15) /* "" sysenter in ia32 userspace */
+ #define X86_FEATURE_REP_GOOD (3*32+16) /* rep microcode works well */
+ #define X86_FEATURE_MFENCE_RDTSC (3*32+17) /* "" Mfence synchronizes RDTSC */
+ #define X86_FEATURE_LFENCE_RDTSC (3*32+18) /* "" Lfence synchronizes RDTSC */
+ #define X86_FEATURE_11AP (3*32+19) /* "" Bad local APIC aka 11AP */
#define X86_FEATURE_NOPL (3*32+20) /* The NOPL (0F 1F) instructions */
+#define X86_FEATURE_AMDC1E (3*32+21) /* AMD C1E detected */
+ #define X86_FEATURE_XTOPOLOGY (3*32+21) /* cpu topology enum extensions */
/* Intel-defined CPU features, CPUID level 0x00000001 (ecx), word 4 */
- #define X86_FEATURE_XMM3 (4*32+ 0) /* Streaming SIMD Extensions-3 */
- #define X86_FEATURE_MWAIT (4*32+ 3) /* Monitor/Mwait support */
- #define X86_FEATURE_DSCPL (4*32+ 4) /* CPL Qualified Debug Store */
+ #define X86_FEATURE_XMM3 (4*32+ 0) /* "pni" SSE-3 */
+ #define X86_FEATURE_PCLMULQDQ (4*32+ 1) /* PCLMULQDQ instruction */
+ #define X86_FEATURE_DTES64 (4*32+ 2) /* 64-bit Debug Store */
+ #define X86_FEATURE_MWAIT (4*32+ 3) /* "monitor" Monitor/Mwait support */
+ #define X86_FEATURE_DSCPL (4*32+ 4) /* "ds_cpl" CPL Qual. Debug Store */
+ #define X86_FEATURE_VMX (4*32+ 5) /* Hardware virtualization */
+ #define X86_FEATURE_SMX (4*32+ 6) /* Safer mode */
#define X86_FEATURE_EST (4*32+ 7) /* Enhanced SpeedStep */
#define X86_FEATURE_TM2 (4*32+ 8) /* Thermal Monitor 2 */
+ #define X86_FEATURE_SSSE3 (4*32+ 9) /* Supplemental SSE-3 */
#define X86_FEATURE_CID (4*32+10) /* Context ID */
+ #define X86_FEATURE_FMA (4*32+12) /* Fused multiply-add */
#define X86_FEATURE_CX16 (4*32+13) /* CMPXCHG16B */
#define X86_FEATURE_XTPR (4*32+14) /* Send Task Priority Messages */
+ #define X86_FEATURE_PDCM (4*32+15) /* Performance Capabilities */
#define X86_FEATURE_DCA (4*32+18) /* Direct Cache Access */
+ #define X86_FEATURE_XMM4_1 (4*32+19) /* "sse4_1" SSE-4.1 */
+ #define X86_FEATURE_XMM4_2 (4*32+20) /* "sse4_2" SSE-4.2 */
#define X86_FEATURE_X2APIC (4*32+21) /* x2APIC */
- #define X86_FEATURE_XMM4_2 (4*32+20) /* Streaming SIMD Extensions-4.2 */
+ #define X86_FEATURE_AES (4*32+25) /* AES instructions */
+ #define X86_FEATURE_XSAVE (4*32+26) /* XSAVE/XRSTOR/XSETBV/XGETBV */
+ #define X86_FEATURE_OSXSAVE (4*32+27) /* "" XSAVE enabled in the OS */
+ #define X86_FEATURE_AVX (4*32+28) /* Advanced Vector Extensions */
/* VIA/Cyrix/Centaur-defined CPU features, CPUID level 0xC0000001, word 5 */
- #define X86_FEATURE_XSTORE (5*32+ 2) /* on-CPU RNG present (xstore insn) */
- #define X86_FEATURE_XSTORE_EN (5*32+ 3) /* on-CPU RNG enabled */
- #define X86_FEATURE_XCRYPT (5*32+ 6) /* on-CPU crypto (xcrypt insn) */
- #define X86_FEATURE_XCRYPT_EN (5*32+ 7) /* on-CPU crypto enabled */
+ #define X86_FEATURE_XSTORE (5*32+ 2) /* "rng" RNG present (xstore) */
+ #define X86_FEATURE_XSTORE_EN (5*32+ 3) /* "rng_en" RNG enabled */
+ #define X86_FEATURE_XCRYPT (5*32+ 6) /* "ace" on-CPU crypto (xcrypt) */
+ #define X86_FEATURE_XCRYPT_EN (5*32+ 7) /* "ace_en" on-CPU crypto enabled */
#define X86_FEATURE_ACE2 (5*32+ 8) /* Advanced Cryptography Engine v2 */
#define X86_FEATURE_ACE2_EN (5*32+ 9) /* ACE v2 enabled */
- #define X86_FEATURE_PHE (5*32+ 10) /* PadLock Hash Engine */
- #define X86_FEATURE_PHE_EN (5*32+ 11) /* PHE enabled */
- #define X86_FEATURE_PMM (5*32+ 12) /* PadLock Montgomery Multiplier */
- #define X86_FEATURE_PMM_EN (5*32+ 13) /* PMM enabled */
+ #define X86_FEATURE_PHE (5*32+10) /* PadLock Hash Engine */
+ #define X86_FEATURE_PHE_EN (5*32+11) /* PHE enabled */
+ #define X86_FEATURE_PMM (5*32+12) /* PadLock Montgomery Multiplier */
+ #define X86_FEATURE_PMM_EN (5*32+13) /* PMM enabled */
/* More extended AMD flags: CPUID level 0x80000001, ecx, word 6 */
#define X86_FEATURE_LAHF_LM (6*32+ 0) /* LAHF/SAHF in long mode */
#define X86_FEATURE_CMP_LEGACY (6*32+ 1) /* If yes HyperThreading not valid */
- #define X86_FEATURE_IBS (6*32+ 10) /* Instruction Based Sampling */
+ #define X86_FEATURE_SVM (6*32+ 2) /* Secure virtual machine */
+ #define X86_FEATURE_EXTAPIC (6*32+ 3) /* Extended APIC space */
+ #define X86_FEATURE_CR8_LEGACY (6*32+ 4) /* CR8 in 32-bit mode */
+ #define X86_FEATURE_ABM (6*32+ 5) /* Advanced bit manipulation */
+ #define X86_FEATURE_SSE4A (6*32+ 6) /* SSE-4A */
+ #define X86_FEATURE_MISALIGNSSE (6*32+ 7) /* Misaligned SSE mode */
+ #define X86_FEATURE_3DNOWPREFETCH (6*32+ 8) /* 3DNow prefetch instructions */
+ #define X86_FEATURE_OSVW (6*32+ 9) /* OS Visible Workaround */
+ #define X86_FEATURE_IBS (6*32+10) /* Instruction Based Sampling */
+ #define X86_FEATURE_SSE5 (6*32+11) /* SSE-5 */
+ #define X86_FEATURE_SKINIT (6*32+12) /* SKINIT/STGI instructions */
+ #define X86_FEATURE_WDT (6*32+13) /* Watchdog timer */
/*
* Auxiliary flags: Linux defined - For features scattered in various
*/
#define X86_FEATURE_IDA (7*32+ 0) /* Intel Dynamic Acceleration */
+ /* Virtualization flags: Linux defined */
+ #define X86_FEATURE_TPR_SHADOW (8*32+ 0) /* Intel TPR Shadow */
+ #define X86_FEATURE_VNMI (8*32+ 1) /* Intel Virtual NMI */
+ #define X86_FEATURE_FLEXPRIORITY (8*32+ 2) /* Intel FlexPriority */
+ #define X86_FEATURE_EPT (8*32+ 3) /* Intel Extended Page Table */
+ #define X86_FEATURE_VPID (8*32+ 4) /* Intel Virtual Processor ID */
+
#if defined(__KERNEL__) && !defined(__ASSEMBLY__)
#include <linux/bitops.h>
} while (0)
#define setup_force_cpu_cap(bit) do { \
set_cpu_cap(&boot_cpu_data, bit); \
- clear_bit(bit, (unsigned long *)cleared_cpu_caps); \
+ clear_bit(bit, (unsigned long *)cleared_cpu_caps); \
} while (0)
#define cpu_has_fpu boot_cpu_has(X86_FEATURE_FPU)
#define cpu_has_gbpages boot_cpu_has(X86_FEATURE_GBPAGES)
#define cpu_has_arch_perfmon boot_cpu_has(X86_FEATURE_ARCH_PERFMON)
#define cpu_has_pat boot_cpu_has(X86_FEATURE_PAT)
- #define cpu_has_x2apic boot_cpu_has(X86_FEATURE_X2APIC)
+ #define cpu_has_xmm4_1 boot_cpu_has(X86_FEATURE_XMM4_1)
#define cpu_has_xmm4_2 boot_cpu_has(X86_FEATURE_XMM4_2)
+ #define cpu_has_x2apic boot_cpu_has(X86_FEATURE_X2APIC)
+ #define cpu_has_xsave boot_cpu_has(X86_FEATURE_XSAVE)
#if defined(CONFIG_X86_INVLPG) || defined(CONFIG_X86_64)
# define cpu_has_invlpg 1
* Warning: layout of LSW is hardcoded in entry.S
*/
#define TIF_SYSCALL_TRACE 0 /* syscall trace active */
+#define TIF_NOTIFY_RESUME 1 /* callback before returning to user */
#define TIF_SIGPENDING 2 /* signal pending */
#define TIF_NEED_RESCHED 3 /* rescheduling necessary */
#define TIF_SINGLESTEP 4 /* reenable singlestep on user return*/
#define TIF_BTS_TRACE_TS 27 /* record scheduling event timestamps */
#define _TIF_SYSCALL_TRACE (1 << TIF_SYSCALL_TRACE)
+#define _TIF_NOTIFY_RESUME (1 << TIF_NOTIFY_RESUME)
#define _TIF_SIGPENDING (1 << TIF_SIGPENDING)
#define _TIF_SINGLESTEP (1 << TIF_SINGLESTEP)
#define _TIF_NEED_RESCHED (1 << TIF_NEED_RESCHED)
/* Only used for 64 bit */
#define _TIF_DO_NOTIFY_MASK \
- (_TIF_SIGPENDING|_TIF_MCE_NOTIFY)
+ (_TIF_SIGPENDING|_TIF_MCE_NOTIFY|_TIF_NOTIFY_RESUME)
/* flags to check in __switch_to() */
#define _TIF_WORK_CTXSW \
#define TS_POLLING 0x0004 /* true if in idle loop
and not sleeping */
#define TS_RESTORE_SIGMASK 0x0008 /* restore signal mask in do_signal() */
+ #define TS_XSAVE 0x0010 /* Use xsave/xrstor */
#define tsk_is_polling(t) (task_thread_info(t)->status & TS_POLLING)
extern int request_resource(struct resource *root, struct resource *new);
extern int release_resource(struct resource *new);
+ extern void reserve_region_with_split(struct resource *root,
+ resource_size_t start, resource_size_t end,
+ const char *name);
extern int insert_resource(struct resource *parent, struct resource *new);
extern void insert_resource_expand_to_fit(struct resource *root, struct resource *new);
extern int allocate_resource(struct resource *root, struct resource *new,
struct resource *parent, resource_size_t start,
resource_size_t n, const char *name);
-#define devm_release_region(start,n) \
+#define devm_release_region(dev, start, n) \
__devm_release_region(dev, &ioport_resource, (start), (n))
-#define devm_release_mem_region(start,n) \
+#define devm_release_mem_region(dev, start, n) \
__devm_release_region(dev, &iomem_resource, (start), (n))
extern void __devm_release_region(struct device *dev, struct resource *parent,