linux/arch/x86/kernel/head64.c
Yinghai Lu c967da6a0b x86: Make sure free_init_pages() frees pages on page boundary
When CONFIG_NO_BOOTMEM=y, it could use memory more effiently, or
in a more compact fashion.

Example:

 Allocated new RAMDISK: 00ec2000 - 0248ce57
 Move RAMDISK from 000000002ea04000 - 000000002ffcee56 to 00ec2000 - 0248ce56

The new RAMDISK's end is not page aligned.
Last page could be shared with other users.

When free_init_pages are called for initrd or .init, the page
could be freed and we could corrupt other data.

code segment in free_init_pages():

 |        for (; addr < end; addr += PAGE_SIZE) {
 |                ClearPageReserved(virt_to_page(addr));
 |                init_page_count(virt_to_page(addr));
 |                memset((void *)(addr & ~(PAGE_SIZE-1)),
 |                        POISON_FREE_INITMEM, PAGE_SIZE);
 |                free_page(addr);
 |                totalram_pages++;
 |        }

last half page could be used as one whole free page.

So page align the boundaries.

-v2: make the original initramdisk to be aligned, according to
     Johannes, otherwise we have the chance to lose one page.
     we still need to keep initrd_end not aligned, otherwise it could
     confuse decompressor.
-v3: change to WARN_ON instead, suggested by Johannes.
-v4: use PAGE_ALIGN, suggested by Johannes.
     We may fix that macro name later to PAGE_ALIGN_UP, and PAGE_ALIGN_DOWN
     Add comments about assuming ramdisk start is aligned
     in relocate_initrd(), change to re get ramdisk_image instead of save it
     to make diff smaller. Add warning for wrong range, suggested by Johannes.
-v6: remove one WARN()
     We need to align beginning in free_init_pages()
     do not copy more than ramdisk_size, noticed by Johannes

Reported-by: Stanislaw Gruszka <sgruszka@redhat.com>
Tested-by: Stanislaw Gruszka <sgruszka@redhat.com>
Signed-off-by: Yinghai Lu <yinghai@kernel.org>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Cc: David Miller <davem@davemloft.net>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
LKML-Reference: <1269830604-26214-3-git-send-email-yinghai@kernel.org>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-03-29 18:55:33 +02:00

124 lines
3.3 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 <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/trampoline.h>
#include <asm/bios_ebda.h>
static void __init zap_identity_mappings(void)
{
pgd_t *pgd = pgd_offset_k(0UL);
pgd_clear(pgd);
__flush_tlb_all();
}
/* 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 void __init copy_bootdata(char *real_mode_data)
{
char * command_line;
memcpy(&boot_params, real_mode_data, sizeof boot_params);
if (boot_params.hdr.cmd_line_ptr) {
command_line = __va(boot_params.hdr.cmd_line_ptr);
memcpy(boot_command_line, command_line, COMMAND_LINE_SIZE);
}
}
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 < KERNEL_IMAGE_START);
BUILD_BUG_ON(MODULES_VADDR-KERNEL_IMAGE_START < KERNEL_IMAGE_SIZE);
BUILD_BUG_ON(MODULES_LEN + KERNEL_IMAGE_SIZE > 2*PUD_SIZE);
BUILD_BUG_ON((KERNEL_IMAGE_START & ~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);
/* clear bss before set_intr_gate with early_idt_handler */
clear_bss();
/* Make NULL pointers segfault */
zap_identity_mappings();
/* Cleanup the over mapped high alias */
cleanup_highmap();
for (i = 0; i < NUM_EXCEPTION_VECTORS; i++) {
#ifdef CONFIG_EARLY_PRINTK
set_intr_gate(i, &early_idt_handlers[i]);
#else
set_intr_gate(i, early_idt_handler);
#endif
}
load_idt((const struct desc_ptr *)&idt_descr);
if (console_loglevel == 10)
early_printk("Kernel alive\n");
x86_64_start_reservations(real_mode_data);
}
void __init x86_64_start_reservations(char *real_mode_data)
{
copy_bootdata(__va(real_mode_data));
reserve_early(__pa_symbol(&_text), __pa_symbol(&__bss_stop), "TEXT DATA BSS");
#ifdef CONFIG_BLK_DEV_INITRD
/* Reserve INITRD */
if (boot_params.hdr.type_of_loader && boot_params.hdr.ramdisk_image) {
/* Assume only end is not page aligned */
unsigned long ramdisk_image = boot_params.hdr.ramdisk_image;
unsigned long ramdisk_size = boot_params.hdr.ramdisk_size;
unsigned long ramdisk_end = PAGE_ALIGN(ramdisk_image + ramdisk_size);
reserve_early(ramdisk_image, ramdisk_end, "RAMDISK");
}
#endif
reserve_ebda_region();
/*
* At this point everything still needed from the boot loader
* or BIOS or kernel text should be early reserved or marked not
* RAM in e820. All other memory is free game.
*/
start_kernel();
}