#include <linux/sched.h>
#include <linux/string.h>
#include <linux/bootmem.h>
+#include <linux/bitops.h>
+#include <linux/module.h>
+#include <asm/bootsetup.h>
#include <asm/pda.h>
#include <asm/pgtable.h>
#include <asm/processor.h>
#include <asm/desc.h>
-#include <asm/bitops.h>
#include <asm/atomic.h>
#include <asm/mmu_context.h>
#include <asm/smp.h>
#include <asm/i387.h>
#include <asm/percpu.h>
-#include <asm/mtrr.h>
#include <asm/proto.h>
-#include <asm/mman.h>
-#include <asm/numa.h>
+#include <asm/sections.h>
-char x86_boot_params[2048] __initdata = {0,};
+char x86_boot_params[BOOT_PARAM_SIZE] __initdata = {0,};
-unsigned long cpu_initialized __initdata = 0;
+cpumask_t cpu_initialized __cpuinitdata = CPU_MASK_NONE;
-struct x8664_pda cpu_pda[NR_CPUS] __cacheline_aligned;
+struct x8664_pda *_cpu_pda[NR_CPUS] __read_mostly;
+struct x8664_pda boot_cpu_pda[NR_CPUS] __cacheline_aligned;
-extern struct task_struct init_task;
-
-extern unsigned char __per_cpu_start[], __per_cpu_end[];
-
-extern struct desc_ptr cpu_gdt_descr[];
-struct desc_ptr idt_descr = { 256 * 16, (unsigned long) idt_table };
+struct desc_ptr idt_descr = { 256 * 16 - 1, (unsigned long) idt_table };
char boot_cpu_stack[IRQSTACKSIZE] __attribute__((section(".bss.page_aligned")));
-unsigned long __supported_pte_mask = ~0UL;
-static int do_not_nx __initdata = 0;
-unsigned long vm_stack_flags = __VM_STACK_FLAGS;
-unsigned long vm_stack_flags32 = __VM_STACK_FLAGS;
-unsigned long vm_data_default_flags = __VM_DATA_DEFAULT_FLAGS;
-unsigned long vm_data_default_flags32 = __VM_DATA_DEFAULT_FLAGS;
-unsigned long vm_force_exec32 = PROT_EXEC;
+unsigned long __supported_pte_mask __read_mostly = ~0UL;
+static int do_not_nx __cpuinitdata = 0;
/* noexec=on|off
Control non executable mappings for 64bit processes.
-on Enable
+on Enable(default)
off Disable
-noforce (default) Don't enable by default for heap/stack/data,
- but allow PROT_EXEC to be effective
-
*/
-static int __init nonx_setup(char *str)
+void __init nonx_setup(const char *str)
{
- if (!strcmp(str, "on")) {
+ if (!strncmp(str, "on", 2)) {
__supported_pte_mask |= _PAGE_NX;
do_not_nx = 0;
- vm_data_default_flags &= ~VM_EXEC;
- vm_stack_flags &= ~VM_EXEC;
- } else if (!strcmp(str, "noforce") || !strcmp(str, "off")) {
- do_not_nx = (str[0] == 'o');
- if (do_not_nx)
- __supported_pte_mask &= ~_PAGE_NX;
- vm_data_default_flags |= VM_EXEC;
- vm_stack_flags |= VM_EXEC;
- }
- return 1;
-}
-
-__setup("noexec=", nonx_setup);
-
-/* noexec32=opt{,opt}
-
-Control the no exec default for 32bit processes. Can be also overwritten
-per executable using ELF header flags (e.g. needed for the X server)
-Requires noexec=on or noexec=noforce to be effective.
-
-Valid options:
- all,on Heap,stack,data is non executable.
- off (default) Heap,stack,data is executable
- stack Stack is non executable, heap/data is.
- force Don't imply PROT_EXEC for PROT_READ
- compat (default) Imply PROT_EXEC for PROT_READ
-
-*/
- static int __init nonx32_setup(char *s)
- {
- while (*s) {
- if (!strncmp(s, "all", 3) || !strncmp(s,"on",2)) {
- vm_data_default_flags32 &= ~VM_EXEC;
- vm_stack_flags32 &= ~VM_EXEC;
- } else if (!strncmp(s, "off",3)) {
- vm_data_default_flags32 |= VM_EXEC;
- vm_stack_flags32 |= VM_EXEC;
- } else if (!strncmp(s, "stack", 5)) {
- vm_data_default_flags32 |= VM_EXEC;
- vm_stack_flags32 &= ~VM_EXEC;
- } else if (!strncmp(s, "force",5)) {
- vm_force_exec32 = 0;
- } else if (!strncmp(s, "compat",5)) {
- vm_force_exec32 = PROT_EXEC;
- }
- s += strcspn(s, ",");
- if (*s == ',')
- ++s;
- }
- return 1;
-}
-
-__setup("noexec32=", nonx32_setup);
+ } else if (!strncmp(str, "off", 3)) {
+ do_not_nx = 1;
+ __supported_pte_mask &= ~_PAGE_NX;
+ }
+}
/*
* Great future plan:
- * Declare PDA itself and support (irqstack,tss,pml4) as per cpu data.
+ * Declare PDA itself and support (irqstack,tss,pgd) as per cpu data.
* Always point %gs to its beginning
*/
void __init setup_per_cpu_areas(void)
int i;
unsigned long size;
+#ifdef CONFIG_HOTPLUG_CPU
+ prefill_possible_map();
+#endif
+
/* Copy section for each CPU (we discard the original) */
size = ALIGN(__per_cpu_end - __per_cpu_start, SMP_CACHE_BYTES);
#ifdef CONFIG_MODULES
size = PERCPU_ENOUGH_ROOM;
#endif
- for (i = 0; i < NR_CPUS; i++) {
- unsigned char *ptr;
- /* If possible allocate on the node of the CPU.
- In case it doesn't exist round-robin nodes. */
- if (!NODE_DATA(i % numnodes)) {
- printk("cpu with no node %d, numnodes %d\n", i, numnodes);
+ for_each_cpu_mask (i, cpu_possible_map) {
+ char *ptr;
+
+ if (!NODE_DATA(cpu_to_node(i))) {
+ printk("cpu with no node %d, num_online_nodes %d\n",
+ i, num_online_nodes());
ptr = alloc_bootmem(size);
} else {
- ptr = alloc_bootmem_node(NODE_DATA(i % numnodes), size);
+ ptr = alloc_bootmem_node(NODE_DATA(cpu_to_node(i)), size);
}
if (!ptr)
panic("Cannot allocate cpu data for CPU %d\n", i);
- cpu_pda[i].data_offset = ptr - __per_cpu_start;
+ cpu_pda(i)->data_offset = ptr - __per_cpu_start;
memcpy(ptr, __per_cpu_start, __per_cpu_end - __per_cpu_start);
}
}
void pda_init(int cpu)
{
- pml4_t *level4;
- struct x8664_pda *pda = &cpu_pda[cpu];
+ struct x8664_pda *pda = cpu_pda(cpu);
/* Setup up data that may be needed in __get_free_pages early */
asm volatile("movl %0,%%fs ; movl %0,%%gs" :: "r" (0));
- wrmsrl(MSR_GS_BASE, cpu_pda + cpu);
+ wrmsrl(MSR_GS_BASE, pda);
- pda->me = pda;
pda->cpunumber = cpu;
pda->irqcount = -1;
pda->kernelstack =
/* others are initialized in smpboot.c */
pda->pcurrent = &init_task;
pda->irqstackptr = boot_cpu_stack;
- level4 = init_level4_pgt;
} else {
- level4 = (pml4_t *)__get_free_pages(GFP_ATOMIC, 0);
- if (!level4)
- panic("Cannot allocate top level page for cpu %d", cpu);
pda->irqstackptr = (char *)
__get_free_pages(GFP_ATOMIC, IRQSTACK_ORDER);
if (!pda->irqstackptr)
panic("cannot allocate irqstack for cpu %d", cpu);
}
- pda->level4_pgt = (unsigned long *)level4;
- if (level4 != init_level4_pgt)
- memcpy(level4, &init_level4_pgt, PAGE_SIZE);
- set_pml4(level4 + 510, mk_kernel_pml4(__pa_symbol(boot_vmalloc_pgt)));
- asm volatile("movq %0,%%cr3" :: "r" (__pa(level4)));
pda->irqstackptr += IRQSTACKSIZE-64;
}
-char boot_exception_stacks[N_EXCEPTION_STACKS * EXCEPTION_STKSZ]
+char boot_exception_stacks[(N_EXCEPTION_STACKS - 1) * EXCEPTION_STKSZ + DEBUG_STKSZ]
__attribute__((section(".bss.page_aligned")));
/* May not be marked __init: used by software suspend */
wrmsrl(MSR_SYSCALL_MASK, EF_TF|EF_DF|EF_IE|0x3000);
}
-void __init check_efer(void)
+void __cpuinit check_efer(void)
{
unsigned long efer;
* 'CPU state barrier', nothing should get across.
* A lot of state is already set up in PDA init.
*/
-void __init cpu_init (void)
+void __cpuinit cpu_init (void)
{
-#ifdef CONFIG_SMP
int cpu = stack_smp_processor_id();
-#else
- int cpu = smp_processor_id();
-#endif
struct tss_struct *t = &per_cpu(init_tss, cpu);
unsigned long v;
char *estacks = NULL;
/* CPU 0 is initialised in head64.c */
if (cpu != 0) {
pda_init(cpu);
+ zap_low_mappings(cpu);
} else
estacks = boot_exception_stacks;
me = current;
- if (test_and_set_bit(cpu, &cpu_initialized))
+ if (cpu_test_and_set(cpu, cpu_initialized))
panic("CPU#%d already initialized!\n", cpu);
printk("Initializing CPU#%d\n", cpu);
- clear_in_cr4(X86_CR4_VME|X86_CR4_PVI|X86_CR4_TSD|X86_CR4_DE);
+ 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:
*/
- if (cpu) {
- memcpy(cpu_gdt_table[cpu], cpu_gdt_table[0], GDT_SIZE);
- }
+ if (cpu)
+ memcpy(cpu_gdt(cpu), cpu_gdt_table, GDT_SIZE);
cpu_gdt_descr[cpu].size = GDT_SIZE;
- cpu_gdt_descr[cpu].address = (unsigned long)cpu_gdt_table[cpu];
- __asm__ __volatile__("lgdt %0": "=m" (cpu_gdt_descr[cpu]));
- __asm__ __volatile__("lidt %0": "=m" (idt_descr));
-
- memcpy(me->thread.tls_array, cpu_gdt_table[cpu], GDT_ENTRY_TLS_ENTRIES * 8);
-
- /*
- * Delete NT
- */
-
- asm volatile("pushfq ; popq %%rax ; btr $14,%%rax ; pushq %%rax ; popfq" ::: "eax");
-
- if (cpu == 0)
- early_identify_cpu(&boot_cpu_data);
+ asm volatile("lgdt %0" :: "m" (cpu_gdt_descr[cpu]));
+ asm volatile("lidt %0" :: "m" (idt_descr));
+ memset(me->thread.tls_array, 0, GDT_ENTRY_TLS_ENTRIES * 8);
syscall_init();
wrmsrl(MSR_FS_BASE, 0);
*/
for (v = 0; v < N_EXCEPTION_STACKS; v++) {
if (cpu) {
- estacks = (char *)__get_free_pages(GFP_ATOMIC,
- EXCEPTION_STACK_ORDER);
+ static const unsigned int order[N_EXCEPTION_STACKS] = {
+ [0 ... N_EXCEPTION_STACKS - 1] = EXCEPTION_STACK_ORDER,
+ [DEBUG_STACK - 1] = DEBUG_STACK_ORDER
+ };
+
+ estacks = (char *)__get_free_pages(GFP_ATOMIC, order[v]);
if (!estacks)
panic("Cannot allocate exception stack %ld %d\n",
v, cpu);
}
- estacks += EXCEPTION_STKSZ;
+ switch (v + 1) {
+#if DEBUG_STKSZ > EXCEPTION_STKSZ
+ case DEBUG_STACK:
+ cpu_pda(cpu)->debugstack = (unsigned long)estacks;
+ estacks += DEBUG_STKSZ;
+ break;
+#endif
+ default:
+ estacks += EXCEPTION_STKSZ;
+ break;
+ }
t->ist[v] = (unsigned long)estacks;
}
* Clear all 6 debug registers:
*/
- set_debug(0UL, 0);
- set_debug(0UL, 1);
- set_debug(0UL, 2);
- set_debug(0UL, 3);
- set_debug(0UL, 6);
- set_debug(0UL, 7);
+ set_debugreg(0UL, 0);
+ set_debugreg(0UL, 1);
+ set_debugreg(0UL, 2);
+ set_debugreg(0UL, 3);
+ set_debugreg(0UL, 6);
+ set_debugreg(0UL, 7);
fpu_init();
-
-#ifdef CONFIG_NUMA
- numa_add_cpu(cpu);
-#endif
}