2005-04-17 06:20:36 +08:00
|
|
|
/*
|
|
|
|
* linux/arch/alpha/mm/init.c
|
|
|
|
*
|
|
|
|
* Copyright (C) 1995 Linus Torvalds
|
|
|
|
*/
|
|
|
|
|
|
|
|
/* 2.3.x zone allocator, 1999 Andrea Arcangeli <andrea@suse.de> */
|
|
|
|
|
2006-01-10 12:51:37 +08:00
|
|
|
#include <linux/pagemap.h>
|
2005-04-17 06:20:36 +08:00
|
|
|
#include <linux/signal.h>
|
|
|
|
#include <linux/sched.h>
|
|
|
|
#include <linux/kernel.h>
|
|
|
|
#include <linux/errno.h>
|
|
|
|
#include <linux/string.h>
|
|
|
|
#include <linux/types.h>
|
|
|
|
#include <linux/ptrace.h>
|
|
|
|
#include <linux/mman.h>
|
|
|
|
#include <linux/mm.h>
|
|
|
|
#include <linux/swap.h>
|
|
|
|
#include <linux/init.h>
|
|
|
|
#include <linux/bootmem.h> /* max_low_pfn */
|
|
|
|
#include <linux/vmalloc.h>
|
include cleanup: Update gfp.h and slab.h includes to prepare for breaking implicit slab.h inclusion from percpu.h
percpu.h is included by sched.h and module.h and thus ends up being
included when building most .c files. percpu.h includes slab.h which
in turn includes gfp.h making everything defined by the two files
universally available and complicating inclusion dependencies.
percpu.h -> slab.h dependency is about to be removed. Prepare for
this change by updating users of gfp and slab facilities include those
headers directly instead of assuming availability. As this conversion
needs to touch large number of source files, the following script is
used as the basis of conversion.
http://userweb.kernel.org/~tj/misc/slabh-sweep.py
The script does the followings.
* Scan files for gfp and slab usages and update includes such that
only the necessary includes are there. ie. if only gfp is used,
gfp.h, if slab is used, slab.h.
* When the script inserts a new include, it looks at the include
blocks and try to put the new include such that its order conforms
to its surrounding. It's put in the include block which contains
core kernel includes, in the same order that the rest are ordered -
alphabetical, Christmas tree, rev-Xmas-tree or at the end if there
doesn't seem to be any matching order.
* If the script can't find a place to put a new include (mostly
because the file doesn't have fitting include block), it prints out
an error message indicating which .h file needs to be added to the
file.
The conversion was done in the following steps.
1. The initial automatic conversion of all .c files updated slightly
over 4000 files, deleting around 700 includes and adding ~480 gfp.h
and ~3000 slab.h inclusions. The script emitted errors for ~400
files.
2. Each error was manually checked. Some didn't need the inclusion,
some needed manual addition while adding it to implementation .h or
embedding .c file was more appropriate for others. This step added
inclusions to around 150 files.
3. The script was run again and the output was compared to the edits
from #2 to make sure no file was left behind.
4. Several build tests were done and a couple of problems were fixed.
e.g. lib/decompress_*.c used malloc/free() wrappers around slab
APIs requiring slab.h to be added manually.
5. The script was run on all .h files but without automatically
editing them as sprinkling gfp.h and slab.h inclusions around .h
files could easily lead to inclusion dependency hell. Most gfp.h
inclusion directives were ignored as stuff from gfp.h was usually
wildly available and often used in preprocessor macros. Each
slab.h inclusion directive was examined and added manually as
necessary.
6. percpu.h was updated not to include slab.h.
7. Build test were done on the following configurations and failures
were fixed. CONFIG_GCOV_KERNEL was turned off for all tests (as my
distributed build env didn't work with gcov compiles) and a few
more options had to be turned off depending on archs to make things
build (like ipr on powerpc/64 which failed due to missing writeq).
* x86 and x86_64 UP and SMP allmodconfig and a custom test config.
* powerpc and powerpc64 SMP allmodconfig
* sparc and sparc64 SMP allmodconfig
* ia64 SMP allmodconfig
* s390 SMP allmodconfig
* alpha SMP allmodconfig
* um on x86_64 SMP allmodconfig
8. percpu.h modifications were reverted so that it could be applied as
a separate patch and serve as bisection point.
Given the fact that I had only a couple of failures from tests on step
6, I'm fairly confident about the coverage of this conversion patch.
If there is a breakage, it's likely to be something in one of the arch
headers which should be easily discoverable easily on most builds of
the specific arch.
Signed-off-by: Tejun Heo <tj@kernel.org>
Guess-its-ok-by: Christoph Lameter <cl@linux-foundation.org>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
2010-03-24 16:04:11 +08:00
|
|
|
#include <linux/gfp.h>
|
2005-04-17 06:20:36 +08:00
|
|
|
|
|
|
|
#include <asm/system.h>
|
|
|
|
#include <asm/uaccess.h>
|
|
|
|
#include <asm/pgtable.h>
|
|
|
|
#include <asm/pgalloc.h>
|
|
|
|
#include <asm/hwrpb.h>
|
|
|
|
#include <asm/dma.h>
|
|
|
|
#include <asm/mmu_context.h>
|
|
|
|
#include <asm/console.h>
|
|
|
|
#include <asm/tlb.h>
|
|
|
|
|
|
|
|
DEFINE_PER_CPU(struct mmu_gather, mmu_gathers);
|
|
|
|
|
|
|
|
extern void die_if_kernel(char *,struct pt_regs *,long);
|
|
|
|
|
|
|
|
static struct pcb_struct original_pcb;
|
|
|
|
|
|
|
|
pgd_t *
|
|
|
|
pgd_alloc(struct mm_struct *mm)
|
|
|
|
{
|
|
|
|
pgd_t *ret, *init;
|
|
|
|
|
|
|
|
ret = (pgd_t *)__get_free_page(GFP_KERNEL | __GFP_ZERO);
|
|
|
|
init = pgd_offset(&init_mm, 0UL);
|
|
|
|
if (ret) {
|
|
|
|
#ifdef CONFIG_ALPHA_LARGE_VMALLOC
|
|
|
|
memcpy (ret + USER_PTRS_PER_PGD, init + USER_PTRS_PER_PGD,
|
|
|
|
(PTRS_PER_PGD - USER_PTRS_PER_PGD - 1)*sizeof(pgd_t));
|
|
|
|
#else
|
|
|
|
pgd_val(ret[PTRS_PER_PGD-2]) = pgd_val(init[PTRS_PER_PGD-2]);
|
|
|
|
#endif
|
|
|
|
|
|
|
|
/* The last PGD entry is the VPTB self-map. */
|
|
|
|
pgd_val(ret[PTRS_PER_PGD-1])
|
|
|
|
= pte_val(mk_pte(virt_to_page(ret), PAGE_KERNEL));
|
|
|
|
}
|
|
|
|
return ret;
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
|
|
/*
|
|
|
|
* BAD_PAGE is the page that is used for page faults when linux
|
|
|
|
* is out-of-memory. Older versions of linux just did a
|
|
|
|
* do_exit(), but using this instead means there is less risk
|
|
|
|
* for a process dying in kernel mode, possibly leaving an inode
|
|
|
|
* unused etc..
|
|
|
|
*
|
|
|
|
* BAD_PAGETABLE is the accompanying page-table: it is initialized
|
|
|
|
* to point to BAD_PAGE entries.
|
|
|
|
*
|
|
|
|
* ZERO_PAGE is a special page that is used for zero-initialized
|
|
|
|
* data and COW.
|
|
|
|
*/
|
|
|
|
pmd_t *
|
|
|
|
__bad_pagetable(void)
|
|
|
|
{
|
|
|
|
memset((void *) EMPTY_PGT, 0, PAGE_SIZE);
|
|
|
|
return (pmd_t *) EMPTY_PGT;
|
|
|
|
}
|
|
|
|
|
|
|
|
pte_t
|
|
|
|
__bad_page(void)
|
|
|
|
{
|
|
|
|
memset((void *) EMPTY_PGE, 0, PAGE_SIZE);
|
|
|
|
return pte_mkdirty(mk_pte(virt_to_page(EMPTY_PGE), PAGE_SHARED));
|
|
|
|
}
|
|
|
|
|
|
|
|
static inline unsigned long
|
|
|
|
load_PCB(struct pcb_struct *pcb)
|
|
|
|
{
|
|
|
|
register unsigned long sp __asm__("$30");
|
|
|
|
pcb->ksp = sp;
|
|
|
|
return __reload_thread(pcb);
|
|
|
|
}
|
|
|
|
|
|
|
|
/* Set up initial PCB, VPTB, and other such nicities. */
|
|
|
|
|
|
|
|
static inline void
|
|
|
|
switch_to_system_map(void)
|
|
|
|
{
|
|
|
|
unsigned long newptbr;
|
|
|
|
unsigned long original_pcb_ptr;
|
|
|
|
|
|
|
|
/* Initialize the kernel's page tables. Linux puts the vptb in
|
|
|
|
the last slot of the L1 page table. */
|
|
|
|
memset(swapper_pg_dir, 0, PAGE_SIZE);
|
|
|
|
newptbr = ((unsigned long) swapper_pg_dir - PAGE_OFFSET) >> PAGE_SHIFT;
|
|
|
|
pgd_val(swapper_pg_dir[1023]) =
|
|
|
|
(newptbr << 32) | pgprot_val(PAGE_KERNEL);
|
|
|
|
|
|
|
|
/* Set the vptb. This is often done by the bootloader, but
|
|
|
|
shouldn't be required. */
|
|
|
|
if (hwrpb->vptb != 0xfffffffe00000000UL) {
|
|
|
|
wrvptptr(0xfffffffe00000000UL);
|
|
|
|
hwrpb->vptb = 0xfffffffe00000000UL;
|
|
|
|
hwrpb_update_checksum(hwrpb);
|
|
|
|
}
|
|
|
|
|
|
|
|
/* Also set up the real kernel PCB while we're at it. */
|
|
|
|
init_thread_info.pcb.ptbr = newptbr;
|
|
|
|
init_thread_info.pcb.flags = 1; /* set FEN, clear everything else */
|
|
|
|
original_pcb_ptr = load_PCB(&init_thread_info.pcb);
|
|
|
|
tbia();
|
|
|
|
|
|
|
|
/* Save off the contents of the original PCB so that we can
|
|
|
|
restore the original console's page tables for a clean reboot.
|
|
|
|
|
|
|
|
Note that the PCB is supposed to be a physical address, but
|
|
|
|
since KSEG values also happen to work, folks get confused.
|
|
|
|
Check this here. */
|
|
|
|
|
|
|
|
if (original_pcb_ptr < PAGE_OFFSET) {
|
|
|
|
original_pcb_ptr = (unsigned long)
|
|
|
|
phys_to_virt(original_pcb_ptr);
|
|
|
|
}
|
|
|
|
original_pcb = *(struct pcb_struct *) original_pcb_ptr;
|
|
|
|
}
|
|
|
|
|
|
|
|
int callback_init_done;
|
|
|
|
|
|
|
|
void * __init
|
|
|
|
callback_init(void * kernel_end)
|
|
|
|
{
|
|
|
|
struct crb_struct * crb;
|
|
|
|
pgd_t *pgd;
|
|
|
|
pmd_t *pmd;
|
|
|
|
void *two_pages;
|
|
|
|
|
|
|
|
/* Starting at the HWRPB, locate the CRB. */
|
|
|
|
crb = (struct crb_struct *)((char *)hwrpb + hwrpb->crb_offset);
|
|
|
|
|
|
|
|
if (alpha_using_srm) {
|
|
|
|
/* Tell the console whither it is to be remapped. */
|
|
|
|
if (srm_fixup(VMALLOC_START, (unsigned long)hwrpb))
|
|
|
|
__halt(); /* "We're boned." --Bender */
|
|
|
|
|
|
|
|
/* Edit the procedure descriptors for DISPATCH and FIXUP. */
|
|
|
|
crb->dispatch_va = (struct procdesc_struct *)
|
|
|
|
(VMALLOC_START + (unsigned long)crb->dispatch_va
|
|
|
|
- crb->map[0].va);
|
|
|
|
crb->fixup_va = (struct procdesc_struct *)
|
|
|
|
(VMALLOC_START + (unsigned long)crb->fixup_va
|
|
|
|
- crb->map[0].va);
|
|
|
|
}
|
|
|
|
|
|
|
|
switch_to_system_map();
|
|
|
|
|
|
|
|
/* Allocate one PGD and one PMD. In the case of SRM, we'll need
|
|
|
|
these to actually remap the console. There is an assumption
|
|
|
|
here that only one of each is needed, and this allows for 8MB.
|
|
|
|
On systems with larger consoles, additional pages will be
|
|
|
|
allocated as needed during the mapping process.
|
|
|
|
|
|
|
|
In the case of not SRM, but not CONFIG_ALPHA_LARGE_VMALLOC,
|
|
|
|
we need to allocate the PGD we use for vmalloc before we start
|
|
|
|
forking other tasks. */
|
|
|
|
|
|
|
|
two_pages = (void *)
|
|
|
|
(((unsigned long)kernel_end + ~PAGE_MASK) & PAGE_MASK);
|
|
|
|
kernel_end = two_pages + 2*PAGE_SIZE;
|
|
|
|
memset(two_pages, 0, 2*PAGE_SIZE);
|
|
|
|
|
|
|
|
pgd = pgd_offset_k(VMALLOC_START);
|
|
|
|
pgd_set(pgd, (pmd_t *)two_pages);
|
|
|
|
pmd = pmd_offset(pgd, VMALLOC_START);
|
|
|
|
pmd_set(pmd, (pte_t *)(two_pages + PAGE_SIZE));
|
|
|
|
|
|
|
|
if (alpha_using_srm) {
|
|
|
|
static struct vm_struct console_remap_vm;
|
2009-02-20 15:29:08 +08:00
|
|
|
unsigned long nr_pages = 0;
|
|
|
|
unsigned long vaddr;
|
2005-04-17 06:20:36 +08:00
|
|
|
unsigned long i, j;
|
|
|
|
|
2009-02-20 15:29:08 +08:00
|
|
|
/* calculate needed size */
|
|
|
|
for (i = 0; i < crb->map_entries; ++i)
|
|
|
|
nr_pages += crb->map[i].count;
|
|
|
|
|
|
|
|
/* register the vm area */
|
|
|
|
console_remap_vm.flags = VM_ALLOC;
|
|
|
|
console_remap_vm.size = nr_pages << PAGE_SHIFT;
|
2009-02-24 10:57:21 +08:00
|
|
|
vm_area_register_early(&console_remap_vm, PAGE_SIZE);
|
2009-02-20 15:29:08 +08:00
|
|
|
|
2009-03-01 15:03:16 +08:00
|
|
|
vaddr = (unsigned long)console_remap_vm.addr;
|
2009-02-20 15:29:08 +08:00
|
|
|
|
2005-04-17 06:20:36 +08:00
|
|
|
/* Set up the third level PTEs and update the virtual
|
|
|
|
addresses of the CRB entries. */
|
|
|
|
for (i = 0; i < crb->map_entries; ++i) {
|
|
|
|
unsigned long pfn = crb->map[i].pa >> PAGE_SHIFT;
|
|
|
|
crb->map[i].va = vaddr;
|
|
|
|
for (j = 0; j < crb->map[i].count; ++j) {
|
2007-10-20 07:04:37 +08:00
|
|
|
/* Newer consoles (especially on larger
|
2005-04-17 06:20:36 +08:00
|
|
|
systems) may require more pages of
|
|
|
|
PTEs. Grab additional pages as needed. */
|
|
|
|
if (pmd != pmd_offset(pgd, vaddr)) {
|
|
|
|
memset(kernel_end, 0, PAGE_SIZE);
|
|
|
|
pmd = pmd_offset(pgd, vaddr);
|
|
|
|
pmd_set(pmd, (pte_t *)kernel_end);
|
|
|
|
kernel_end += PAGE_SIZE;
|
|
|
|
}
|
|
|
|
set_pte(pte_offset_kernel(pmd, vaddr),
|
|
|
|
pfn_pte(pfn, PAGE_KERNEL));
|
|
|
|
pfn++;
|
|
|
|
vaddr += PAGE_SIZE;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
callback_init_done = 1;
|
|
|
|
return kernel_end;
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
|
|
#ifndef CONFIG_DISCONTIGMEM
|
|
|
|
/*
|
|
|
|
* paging_init() sets up the memory map.
|
|
|
|
*/
|
2007-07-31 15:37:53 +08:00
|
|
|
void __init paging_init(void)
|
2005-04-17 06:20:36 +08:00
|
|
|
{
|
2006-09-26 14:31:10 +08:00
|
|
|
unsigned long zones_size[MAX_NR_ZONES] = {0, };
|
2005-04-17 06:20:36 +08:00
|
|
|
unsigned long dma_pfn, high_pfn;
|
|
|
|
|
|
|
|
dma_pfn = virt_to_phys((char *)MAX_DMA_ADDRESS) >> PAGE_SHIFT;
|
|
|
|
high_pfn = max_pfn = max_low_pfn;
|
|
|
|
|
|
|
|
if (dma_pfn >= high_pfn)
|
|
|
|
zones_size[ZONE_DMA] = high_pfn;
|
|
|
|
else {
|
|
|
|
zones_size[ZONE_DMA] = dma_pfn;
|
|
|
|
zones_size[ZONE_NORMAL] = high_pfn - dma_pfn;
|
|
|
|
}
|
|
|
|
|
|
|
|
/* Initialize mem_map[]. */
|
|
|
|
free_area_init(zones_size);
|
|
|
|
|
|
|
|
/* Initialize the kernel's ZERO_PGE. */
|
|
|
|
memset((void *)ZERO_PGE, 0, PAGE_SIZE);
|
|
|
|
}
|
|
|
|
#endif /* CONFIG_DISCONTIGMEM */
|
|
|
|
|
|
|
|
#if defined(CONFIG_ALPHA_GENERIC) || defined(CONFIG_ALPHA_SRM)
|
|
|
|
void
|
|
|
|
srm_paging_stop (void)
|
|
|
|
{
|
|
|
|
/* Move the vptb back to where the SRM console expects it. */
|
|
|
|
swapper_pg_dir[1] = swapper_pg_dir[1023];
|
|
|
|
tbia();
|
|
|
|
wrvptptr(0x200000000UL);
|
|
|
|
hwrpb->vptb = 0x200000000UL;
|
|
|
|
hwrpb_update_checksum(hwrpb);
|
|
|
|
|
|
|
|
/* Reload the page tables that the console had in use. */
|
|
|
|
load_PCB(&original_pcb);
|
|
|
|
tbia();
|
|
|
|
}
|
|
|
|
#endif
|
|
|
|
|
|
|
|
#ifndef CONFIG_DISCONTIGMEM
|
|
|
|
static void __init
|
|
|
|
printk_memory_info(void)
|
|
|
|
{
|
|
|
|
unsigned long codesize, reservedpages, datasize, initsize, tmp;
|
|
|
|
extern int page_is_ram(unsigned long) __init;
|
|
|
|
extern char _text, _etext, _data, _edata;
|
|
|
|
extern char __init_begin, __init_end;
|
|
|
|
|
|
|
|
/* printk all informations */
|
|
|
|
reservedpages = 0;
|
|
|
|
for (tmp = 0; tmp < max_low_pfn; tmp++)
|
|
|
|
/*
|
|
|
|
* Only count reserved RAM pages
|
|
|
|
*/
|
|
|
|
if (page_is_ram(tmp) && PageReserved(mem_map+tmp))
|
|
|
|
reservedpages++;
|
|
|
|
|
|
|
|
codesize = (unsigned long) &_etext - (unsigned long) &_text;
|
|
|
|
datasize = (unsigned long) &_edata - (unsigned long) &_data;
|
|
|
|
initsize = (unsigned long) &__init_end - (unsigned long) &__init_begin;
|
|
|
|
|
|
|
|
printk("Memory: %luk/%luk available (%luk kernel code, %luk reserved, %luk data, %luk init)\n",
|
2009-09-22 08:02:36 +08:00
|
|
|
nr_free_pages() << (PAGE_SHIFT-10),
|
2005-04-17 06:20:36 +08:00
|
|
|
max_mapnr << (PAGE_SHIFT-10),
|
|
|
|
codesize >> 10,
|
|
|
|
reservedpages << (PAGE_SHIFT-10),
|
|
|
|
datasize >> 10,
|
|
|
|
initsize >> 10);
|
|
|
|
}
|
|
|
|
|
|
|
|
void __init
|
|
|
|
mem_init(void)
|
|
|
|
{
|
|
|
|
max_mapnr = num_physpages = max_low_pfn;
|
|
|
|
totalram_pages += free_all_bootmem();
|
|
|
|
high_memory = (void *) __va(max_low_pfn * PAGE_SIZE);
|
|
|
|
|
|
|
|
printk_memory_info();
|
|
|
|
}
|
|
|
|
#endif /* CONFIG_DISCONTIGMEM */
|
|
|
|
|
|
|
|
void
|
|
|
|
free_reserved_mem(void *start, void *end)
|
|
|
|
{
|
|
|
|
void *__start = start;
|
|
|
|
for (; __start < end; __start += PAGE_SIZE) {
|
|
|
|
ClearPageReserved(virt_to_page(__start));
|
2006-03-22 16:08:40 +08:00
|
|
|
init_page_count(virt_to_page(__start));
|
2005-04-17 06:20:36 +08:00
|
|
|
free_page((long)__start);
|
|
|
|
totalram_pages++;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
void
|
|
|
|
free_initmem(void)
|
|
|
|
{
|
|
|
|
extern char __init_begin, __init_end;
|
|
|
|
|
|
|
|
free_reserved_mem(&__init_begin, &__init_end);
|
|
|
|
printk ("Freeing unused kernel memory: %ldk freed\n",
|
|
|
|
(&__init_end - &__init_begin) >> 10);
|
|
|
|
}
|
|
|
|
|
|
|
|
#ifdef CONFIG_BLK_DEV_INITRD
|
|
|
|
void
|
|
|
|
free_initrd_mem(unsigned long start, unsigned long end)
|
|
|
|
{
|
|
|
|
free_reserved_mem((void *)start, (void *)end);
|
|
|
|
printk ("Freeing initrd memory: %ldk freed\n", (end - start) >> 10);
|
|
|
|
}
|
|
|
|
#endif
|