linux/arch/x86/kernel/head64.c
Andy Lutomirski 425be5679f x86/asm/irq: Stop relying on magic JMP behavior for early_idt_handlers
The early_idt_handlers asm code generates an array of entry
points spaced nine bytes apart.  It's not really clear from that
code or from the places that reference it what's going on, and
the code only works in the first place because GAS never
generates two-byte JMP instructions when jumping to global
labels.

Clean up the code to generate the correct array stride (member size)
explicitly. This should be considerably more robust against
screw-ups, as GAS will warn if a .fill directive has a negative
count.  Using '. =' to advance would have been even more robust
(it would generate an actual error if it tried to move
backwards), but it would pad with nulls, confusing anyone who
tries to disassemble the code.  The new scheme should be much
clearer to future readers.

While we're at it, improve the comments and rename the array and
common code.

Binutils may start relaxing jumps to non-weak labels.  If so,
this change will fix our build, and we may need to backport this
change.

Before, on x86_64:

  0000000000000000 <early_idt_handlers>:
     0:   6a 00                   pushq  $0x0
     2:   6a 00                   pushq  $0x0
     4:   e9 00 00 00 00          jmpq   9 <early_idt_handlers+0x9>
                          5: R_X86_64_PC32        early_idt_handler-0x4
  ...
    48:   66 90                   xchg   %ax,%ax
    4a:   6a 08                   pushq  $0x8
    4c:   e9 00 00 00 00          jmpq   51 <early_idt_handlers+0x51>
                          4d: R_X86_64_PC32       early_idt_handler-0x4
  ...
   117:   6a 00                   pushq  $0x0
   119:   6a 1f                   pushq  $0x1f
   11b:   e9 00 00 00 00          jmpq   120 <early_idt_handler>
                          11c: R_X86_64_PC32      early_idt_handler-0x4

After:

  0000000000000000 <early_idt_handler_array>:
     0:   6a 00                   pushq  $0x0
     2:   6a 00                   pushq  $0x0
     4:   e9 14 01 00 00          jmpq   11d <early_idt_handler_common>
  ...
    48:   6a 08                   pushq  $0x8
    4a:   e9 d1 00 00 00          jmpq   120 <early_idt_handler_common>
    4f:   cc                      int3
    50:   cc                      int3
  ...
   117:   6a 00                   pushq  $0x0
   119:   6a 1f                   pushq  $0x1f
   11b:   eb 03                   jmp    120 <early_idt_handler_common>
   11d:   cc                      int3
   11e:   cc                      int3
   11f:   cc                      int3

Signed-off-by: Andy Lutomirski <luto@kernel.org>
Acked-by: H. Peter Anvin <hpa@linux.intel.com>
Cc: Binutils <binutils@sourceware.org>
Cc: Borislav Petkov <bp@alien8.de>
Cc: H.J. Lu <hjl.tools@gmail.com>
Cc: Jan Beulich <JBeulich@suse.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: <stable@vger.kernel.org>
Link: http://lkml.kernel.org/r/ac027962af343b0c599cbfcf50b945ad2ef3d7a8.1432336324.git.luto@kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-06-02 09:39:40 +02:00

199 lines
5.1 KiB
C

/*
* prepare to run common code
*
* Copyright (C) 2000 Andrea Arcangeli <andrea@suse.de> SuSE
*/
#include <linux/init.h>
#include <linux/linkage.h>
#include <linux/types.h>
#include <linux/kernel.h>
#include <linux/string.h>
#include <linux/percpu.h>
#include <linux/start_kernel.h>
#include <linux/io.h>
#include <linux/memblock.h>
#include <asm/processor.h>
#include <asm/proto.h>
#include <asm/smp.h>
#include <asm/setup.h>
#include <asm/desc.h>
#include <asm/pgtable.h>
#include <asm/tlbflush.h>
#include <asm/sections.h>
#include <asm/kdebug.h>
#include <asm/e820.h>
#include <asm/bios_ebda.h>
#include <asm/bootparam_utils.h>
#include <asm/microcode.h>
#include <asm/kasan.h>
/*
* Manage page tables very early on.
*/
extern pgd_t early_level4_pgt[PTRS_PER_PGD];
extern pmd_t early_dynamic_pgts[EARLY_DYNAMIC_PAGE_TABLES][PTRS_PER_PMD];
static unsigned int __initdata next_early_pgt = 2;
pmdval_t early_pmd_flags = __PAGE_KERNEL_LARGE & ~(_PAGE_GLOBAL | _PAGE_NX);
/* Wipe all early page tables except for the kernel symbol map */
static void __init reset_early_page_tables(void)
{
unsigned long i;
for (i = 0; i < PTRS_PER_PGD-1; i++)
early_level4_pgt[i].pgd = 0;
next_early_pgt = 0;
write_cr3(__pa_nodebug(early_level4_pgt));
}
/* Create a new PMD entry */
int __init early_make_pgtable(unsigned long address)
{
unsigned long physaddr = address - __PAGE_OFFSET;
unsigned long i;
pgdval_t pgd, *pgd_p;
pudval_t pud, *pud_p;
pmdval_t pmd, *pmd_p;
/* Invalid address or early pgt is done ? */
if (physaddr >= MAXMEM || read_cr3() != __pa_nodebug(early_level4_pgt))
return -1;
again:
pgd_p = &early_level4_pgt[pgd_index(address)].pgd;
pgd = *pgd_p;
/*
* The use of __START_KERNEL_map rather than __PAGE_OFFSET here is
* critical -- __PAGE_OFFSET would point us back into the dynamic
* range and we might end up looping forever...
*/
if (pgd)
pud_p = (pudval_t *)((pgd & PTE_PFN_MASK) + __START_KERNEL_map - phys_base);
else {
if (next_early_pgt >= EARLY_DYNAMIC_PAGE_TABLES) {
reset_early_page_tables();
goto again;
}
pud_p = (pudval_t *)early_dynamic_pgts[next_early_pgt++];
for (i = 0; i < PTRS_PER_PUD; i++)
pud_p[i] = 0;
*pgd_p = (pgdval_t)pud_p - __START_KERNEL_map + phys_base + _KERNPG_TABLE;
}
pud_p += pud_index(address);
pud = *pud_p;
if (pud)
pmd_p = (pmdval_t *)((pud & PTE_PFN_MASK) + __START_KERNEL_map - phys_base);
else {
if (next_early_pgt >= EARLY_DYNAMIC_PAGE_TABLES) {
reset_early_page_tables();
goto again;
}
pmd_p = (pmdval_t *)early_dynamic_pgts[next_early_pgt++];
for (i = 0; i < PTRS_PER_PMD; i++)
pmd_p[i] = 0;
*pud_p = (pudval_t)pmd_p - __START_KERNEL_map + phys_base + _KERNPG_TABLE;
}
pmd = (physaddr & PMD_MASK) + early_pmd_flags;
pmd_p[pmd_index(address)] = pmd;
return 0;
}
/* Don't add a printk in there. printk relies on the PDA which is not initialized
yet. */
static void __init clear_bss(void)
{
memset(__bss_start, 0,
(unsigned long) __bss_stop - (unsigned long) __bss_start);
}
static unsigned long get_cmd_line_ptr(void)
{
unsigned long cmd_line_ptr = boot_params.hdr.cmd_line_ptr;
cmd_line_ptr |= (u64)boot_params.ext_cmd_line_ptr << 32;
return cmd_line_ptr;
}
static void __init copy_bootdata(char *real_mode_data)
{
char * command_line;
unsigned long cmd_line_ptr;
memcpy(&boot_params, real_mode_data, sizeof boot_params);
sanitize_boot_params(&boot_params);
cmd_line_ptr = get_cmd_line_ptr();
if (cmd_line_ptr) {
command_line = __va(cmd_line_ptr);
memcpy(boot_command_line, command_line, COMMAND_LINE_SIZE);
}
}
asmlinkage __visible void __init x86_64_start_kernel(char * real_mode_data)
{
int i;
/*
* Build-time sanity checks on the kernel image and module
* area mappings. (these are purely build-time and produce no code)
*/
BUILD_BUG_ON(MODULES_VADDR < __START_KERNEL_map);
BUILD_BUG_ON(MODULES_VADDR - __START_KERNEL_map < KERNEL_IMAGE_SIZE);
BUILD_BUG_ON(MODULES_LEN + KERNEL_IMAGE_SIZE > 2*PUD_SIZE);
BUILD_BUG_ON((__START_KERNEL_map & ~PMD_MASK) != 0);
BUILD_BUG_ON((MODULES_VADDR & ~PMD_MASK) != 0);
BUILD_BUG_ON(!(MODULES_VADDR > __START_KERNEL));
BUILD_BUG_ON(!(((MODULES_END - 1) & PGDIR_MASK) ==
(__START_KERNEL & PGDIR_MASK)));
BUILD_BUG_ON(__fix_to_virt(__end_of_fixed_addresses) <= MODULES_END);
cr4_init_shadow();
/* Kill off the identity-map trampoline */
reset_early_page_tables();
kasan_map_early_shadow(early_level4_pgt);
/* clear bss before set_intr_gate with early_idt_handler */
clear_bss();
for (i = 0; i < NUM_EXCEPTION_VECTORS; i++)
set_intr_gate(i, early_idt_handler_array[i]);
load_idt((const struct desc_ptr *)&idt_descr);
copy_bootdata(__va(real_mode_data));
/*
* Load microcode early on BSP.
*/
load_ucode_bsp();
clear_page(init_level4_pgt);
/* set init_level4_pgt kernel high mapping*/
init_level4_pgt[511] = early_level4_pgt[511];
kasan_map_early_shadow(init_level4_pgt);
x86_64_start_reservations(real_mode_data);
}
void __init x86_64_start_reservations(char *real_mode_data)
{
/* version is always not zero if it is copied */
if (!boot_params.hdr.version)
copy_bootdata(__va(real_mode_data));
reserve_ebda_region();
start_kernel();
}