linux-stable/arch/x86/kernel/head64.c
Ingo Molnar edce21216a x86/boot: Reorganize and clean up the BIOS area reservation code
So the reserve_ebda_region() code has accumulated a number of
problems over the years that make it really difficult to read
and understand:

- The calculation of 'lowmem' and 'ebda_addr' is an unnecessarily
  interleaved mess of first lowmem, then ebda_addr, then lowmem tweaks...

- 'lowmem' here means 'super low mem' - i.e. 16-bit addressable memory. In other
  parts of the x86 code 'lowmem' means 32-bit addressable memory... This makes it
  super confusing to read.

- It does not help at all that we have various memory range markers, half of which
  are 'start of range', half of which are 'end of range' - but this crucial
  property is not obvious in the naming at all ... gave me a headache trying to
  understand all this.

- Also, the 'ebda_addr' name sucks: it highlights that it's an address (which is
  obvious, all values here are addresses!), while it does not highlight that it's
  the _start_ of the EBDA region ...

- 'BIOS_LOWMEM_KILOBYTES' says a lot of things, except that this is the only value
  that is a pointer to a value, not a memory range address!

- The function name itself is a misnomer: it says 'reserve_ebda_region()' while
  its main purpose is to reserve all the firmware ROM typically between 640K and
  1MB, while the 'EBDA' part is only a small part of that ...

- Likewise, the paravirt quirk flag name 'ebda_search' is misleading as well: this
  too should be about whether to reserve firmware areas in the paravirt case.

- In fact thinking about this as 'end of RAM' is confusing: what this function
  *really* wants to reserve is firmware data and code areas! Once the thinking is
  inverted from a mixed 'ram' and 'reserved firmware area' notion to a pure
  'reserved area' notion everything becomes a lot clearer.

To improve all this rewrite the whole code (without changing the logic):

- Firstly invert the naming from 'lowmem end' to 'BIOS reserved area start'
  and propagate this concept through all the variable names and constants.

	BIOS_RAM_SIZE_KB_PTR		// was: BIOS_LOWMEM_KILOBYTES

	BIOS_START_MIN			// was: INSANE_CUTOFF

	ebda_start			// was: ebda_addr
	bios_start			// was: lowmem

	BIOS_START_MAX			// was: LOWMEM_CAP

- Then clean up the name of the function itself by renaming it
  to reserve_bios_regions() and renaming the ::ebda_search paravirt
  flag to ::reserve_bios_regions.

- Fix up all the comments (fix typos), harmonize and simplify their
  formulation and remove comments that become unnecessary due to
  the much better naming all around.

Signed-off-by: Ingo Molnar <mingo@kernel.org>
2016-07-21 10:11:57 +02:00

197 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)
{
memset(early_level4_pgt, 0, sizeof(pgd_t)*(PTRS_PER_PGD-1));
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;
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++];
memset(pud_p, 0, sizeof(*pud_p) * PTRS_PER_PUD);
*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++];
memset(pmd_p, 0, sizeof(*pmd_p) * PTRS_PER_PMD);
*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();
clear_bss();
clear_page(init_level4_pgt);
kasan_early_init();
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();
/* set init_level4_pgt kernel high mapping*/
init_level4_pgt[511] = early_level4_pgt[511];
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));
x86_early_init_platform_quirks();
reserve_bios_regions();
switch (boot_params.hdr.hardware_subarch) {
case X86_SUBARCH_INTEL_MID:
x86_intel_mid_early_setup();
break;
default:
break;
}
start_kernel();
}