linux/arch/x86/kernel/setup64.c

288 lines
7.1 KiB
C
Raw Normal View History

/*
* X86-64 specific CPU setup.
* Copyright (C) 1995 Linus Torvalds
* Copyright 2001, 2002, 2003 SuSE Labs / Andi Kleen.
* See setup.c for older changelog.
*/
#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 <asm/pda.h>
#include <asm/pgtable.h>
#include <asm/processor.h>
#include <asm/desc.h>
#include <asm/atomic.h>
#include <asm/mmu_context.h>
#include <asm/smp.h>
#include <asm/i387.h>
#include <asm/percpu.h>
#include <asm/proto.h>
#include <asm/sections.h>
#include <asm/setup.h>
x86: support for new UV apic UV supports really big systems. So big, in fact, that the APICID register does not contain enough bits to contain an APICID that is unique across all cpus. The UV BIOS supports 3 APICID modes: - legacy mode. This mode uses the old APIC mode where APICID is in bits [31:24] of the APICID register. - x2apic mode. This mode is whitebox-compatible. APICIDs are unique across all cpus. Standard x2apic APIC operations (Intel-defined) can be used for IPIs. The node identifier fits within the Intel-defined portion of the APICID register. - x2apic-uv mode. In this mode, the APICIDs on each node have unique IDs, but IDs on different node are not unique. For example, if each mode has 32 cpus, the APICIDs on each node might be 0 - 31. Every node has the same set of IDs. The UV hub is used to route IPIs/interrupts to the correct node. Traditional APIC operations WILL NOT WORK. In x2apic-uv mode, the ACPI tables all contain a full unique ID (note: exact bit layout still changing but the following is close): nnnnnnnnnnlc0cch n = unique node number l = socket number on board c = core h = hyperthread Only the "lc0cch" bits are written to the APICID register. The remaining bits are supplied by having the get_apic_id() function "OR" the extra bits into the value read from the APICID register. (Hmmm.. why not keep the ENTIRE APICID register in per-cpu data....) The x2apic-uv mode is recognized by the MADT table containing: oem_id = "SGI" oem_table_id = "UV-X" Signed-off-by: Jack Steiner <steiner@sgi.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-03-28 19:12:16 +00:00
#include <asm/genapic.h>
#ifndef CONFIG_DEBUG_BOOT_PARAMS
struct boot_params __initdata boot_params;
#else
struct boot_params boot_params;
#endif
cpumask_t cpu_initialized __cpuinitdata = CPU_MASK_NONE;
struct x8664_pda *_cpu_pda[NR_CPUS] __read_mostly;
EXPORT_SYMBOL(_cpu_pda);
struct x8664_pda boot_cpu_pda[NR_CPUS] __cacheline_aligned;
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 __read_mostly = ~0UL;
EXPORT_SYMBOL_GPL(__supported_pte_mask);
static int do_not_nx __cpuinitdata = 0;
/* noexec=on|off
Control non executable mappings for 64bit 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);
int force_personality32 = 0;
/* 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 32bit 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);
void pda_init(int 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));
/* 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;
} else {
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;
}
char boot_exception_stacks[(N_EXCEPTION_STACKS - 1) * EXCEPTION_STKSZ + DEBUG_STKSZ]
__attribute__((section(".bss.page_aligned")));
extern asmlinkage void ignore_sysret(void);
/* May not be marked __init: used by software suspend */
void syscall_init(void)
{
/*
* 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);
#ifdef CONFIG_IA32_EMULATION
syscall32_cpu_init ();
#endif
/* Flags to clear on syscall */
wrmsrl(MSR_SYSCALL_MASK,
X86_EFLAGS_TF|X86_EFLAGS_DF|X86_EFLAGS_IF|X86_EFLAGS_IOPL);
}
void __cpuinit check_efer(void)
{
unsigned long efer;
rdmsrl(MSR_EFER, efer);
if (!(efer & EFER_NX) || do_not_nx) {
__supported_pte_mask &= ~_PAGE_NX;
}
}
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);
/*
* 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.
*/
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("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:
*/
if (cpu)
memcpy(get_cpu_gdt_table(cpu), cpu_gdt_table, GDT_SIZE);
cpu_gdt_descr[cpu].size = GDT_SIZE;
load_gdt((const struct desc_ptr *)&cpu_gdt_descr[cpu]);
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();
/*
* set up and load the per-CPU TSS
*/
for (v = 0; v < N_EXCEPTION_STACKS; v++) {
static const unsigned int order[N_EXCEPTION_STACKS] = {
[0 ... N_EXCEPTION_STACKS - 1] = EXCEPTION_STACK_ORDER,
[DEBUG_STACK - 1] = DEBUG_STACK_ORDER
};
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);
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);
x86: support for new UV apic UV supports really big systems. So big, in fact, that the APICID register does not contain enough bits to contain an APICID that is unique across all cpus. The UV BIOS supports 3 APICID modes: - legacy mode. This mode uses the old APIC mode where APICID is in bits [31:24] of the APICID register. - x2apic mode. This mode is whitebox-compatible. APICIDs are unique across all cpus. Standard x2apic APIC operations (Intel-defined) can be used for IPIs. The node identifier fits within the Intel-defined portion of the APICID register. - x2apic-uv mode. In this mode, the APICIDs on each node have unique IDs, but IDs on different node are not unique. For example, if each mode has 32 cpus, the APICIDs on each node might be 0 - 31. Every node has the same set of IDs. The UV hub is used to route IPIs/interrupts to the correct node. Traditional APIC operations WILL NOT WORK. In x2apic-uv mode, the ACPI tables all contain a full unique ID (note: exact bit layout still changing but the following is close): nnnnnnnnnnlc0cch n = unique node number l = socket number on board c = core h = hyperthread Only the "lc0cch" bits are written to the APICID register. The remaining bits are supplied by having the get_apic_id() function "OR" the extra bits into the value read from the APICID register. (Hmmm.. why not keep the ENTIRE APICID register in per-cpu data....) The x2apic-uv mode is recognized by the MADT table containing: oem_id = "SGI" oem_table_id = "UV-X" Signed-off-by: Jack Steiner <steiner@sgi.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-03-28 19:12:16 +00:00
if (is_uv_system())
uv_cpu_init();
}