linux/arch/um/kernel/mem.c

321 lines
7.3 KiB
C
Raw Normal View History

/*
* Copyright (C) 2000 - 2007 Jeff Dike (jdike@{addtoit,linux.intel}.com)
* Licensed under the GPL
*/
#include <linux/stddef.h>
#include <linux/bootmem.h>
#include <linux/gfp.h>
#include <linux/highmem.h>
#include <linux/mm.h>
#include <linux/swap.h>
#include <asm/fixmap.h>
#include <asm/page.h>
#include "as-layout.h"
#include "init.h"
#include "kern.h"
#include "kern_util.h"
#include "mem_user.h"
#include "os.h"
/* allocated in paging_init, zeroed in mem_init, and unchanged thereafter */
unsigned long *empty_zero_page = NULL;
/* allocated in paging_init and unchanged thereafter */
static unsigned long *empty_bad_page = NULL;
/*
* Initialized during boot, and readonly for initializing page tables
* afterwards
*/
pgd_t swapper_pg_dir[PTRS_PER_PGD];
/* Initialized at boot time, and readonly after that */
unsigned long long highmem;
int kmalloc_ok = 0;
/* Used during early boot */
static unsigned long brk_end;
#ifdef CONFIG_HIGHMEM
static void setup_highmem(unsigned long highmem_start,
unsigned long highmem_len)
{
struct page *page;
unsigned long highmem_pfn;
int i;
highmem_pfn = __pa(highmem_start) >> PAGE_SHIFT;
for (i = 0; i < highmem_len >> PAGE_SHIFT; i++) {
page = &mem_map[highmem_pfn + i];
ClearPageReserved(page);
init_page_count(page);
__free_page(page);
}
}
#endif
void __init mem_init(void)
{
/* clear the zero-page */
memset(empty_zero_page, 0, PAGE_SIZE);
/* Map in the area just after the brk now that kmalloc is about
* to be turned on.
*/
brk_end = (unsigned long) UML_ROUND_UP(sbrk(0));
map_memory(brk_end, __pa(brk_end), uml_reserved - brk_end, 1, 1, 0);
free_bootmem(__pa(brk_end), uml_reserved - brk_end);
uml_reserved = brk_end;
/* this will put all low memory onto the freelists */
totalram_pages = free_all_bootmem();
max_low_pfn = totalram_pages;
#ifdef CONFIG_HIGHMEM
totalhigh_pages = highmem >> PAGE_SHIFT;
totalram_pages += totalhigh_pages;
#endif
num_physpages = totalram_pages;
max_pfn = totalram_pages;
printk(KERN_INFO "Memory: %luk available\n",
(unsigned long) nr_free_pages() << (PAGE_SHIFT-10));
kmalloc_ok = 1;
#ifdef CONFIG_HIGHMEM
setup_highmem(end_iomem, highmem);
#endif
}
/*
* Create a page table and place a pointer to it in a middle page
* directory entry.
*/
static void __init one_page_table_init(pmd_t *pmd)
{
if (pmd_none(*pmd)) {
pte_t *pte = (pte_t *) alloc_bootmem_low_pages(PAGE_SIZE);
set_pmd(pmd, __pmd(_KERNPG_TABLE +
(unsigned long) __pa(pte)));
if (pte != pte_offset_kernel(pmd, 0))
BUG();
}
}
static void __init one_md_table_init(pud_t *pud)
{
#ifdef CONFIG_3_LEVEL_PGTABLES
pmd_t *pmd_table = (pmd_t *) alloc_bootmem_low_pages(PAGE_SIZE);
set_pud(pud, __pud(_KERNPG_TABLE + (unsigned long) __pa(pmd_table)));
if (pmd_table != pmd_offset(pud, 0))
BUG();
#endif
}
static void __init fixrange_init(unsigned long start, unsigned long end,
pgd_t *pgd_base)
{
pgd_t *pgd;
pud_t *pud;
pmd_t *pmd;
int i, j;
unsigned long vaddr;
vaddr = start;
i = pgd_index(vaddr);
j = pmd_index(vaddr);
pgd = pgd_base + i;
for ( ; (i < PTRS_PER_PGD) && (vaddr < end); pgd++, i++) {
pud = pud_offset(pgd, vaddr);
if (pud_none(*pud))
one_md_table_init(pud);
pmd = pmd_offset(pud, vaddr);
for (; (j < PTRS_PER_PMD) && (vaddr < end); pmd++, j++) {
one_page_table_init(pmd);
vaddr += PMD_SIZE;
}
j = 0;
}
}
#ifdef CONFIG_HIGHMEM
pte_t *kmap_pte;
pgprot_t kmap_prot;
#define kmap_get_fixmap_pte(vaddr) \
pte_offset_kernel(pmd_offset(pud_offset(pgd_offset_k(vaddr), (vaddr)),\
uml: header untangling Untangle UML headers somewhat and add some includes where they were needed explicitly, but gotten accidentally via some other header. arch/um/include/um_uaccess.h loses asm/fixmap.h because it uses no fixmap stuff and gains elf.h, because it needs FIXADDR_USER_*, and archsetjmp.h, because it needs jmp_buf. pmd_alloc_one is uninlined because it needs mm_struct, and that's inconvenient to provide in asm-um/pgtable-3level.h. elf_core_copy_fpregs is also uninlined from elf-i386.h and elf-x86_64.h, which duplicated the code anyway, to arch/um/kernel/process.c, so that the reference to current_thread doesn't pull sched.h or anything related into asm/elf.h. arch/um/sys-i386/ldt.c, arch/um/kernel/tlb.c and arch/um/kernel/skas/uaccess.c got sched.h because they dereference task_structs. Its includes of linux and asm headers got turned from "" to <>. arch/um/sys-i386/bug.c gets asm/errno.h because it needs errno constants. asm/elf-i386 gets asm/user.h because it needs user_regs_struct. asm/fixmap.h gets page.h because it needs PAGE_SIZE and PAGE_MASK and system.h for BUG_ON. asm/pgtable doesn't need sched.h. asm/processor-generic.h defined mm_segment_t, but didn't use it. So, that definition is moved to uaccess.h, which defines a bunch of mm_segment_t-related stuff. thread_info.h uses mm_segment_t, and includes uaccess.h, which causes a recursion. So, the definition is placed above the include of thread_info. in uaccess.h. thread_info.h also gets page.h because it needs PAGE_SIZE. ObCheckpatchViolationJustification - I'm not adding a typedef; I'm moving mm_segment_t from one place to another. Signed-off-by: Jeff Dike <jdike@linux.intel.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-02-05 14:30:53 +08:00
(vaddr)), (vaddr))
static void __init kmap_init(void)
{
unsigned long kmap_vstart;
/* cache the first kmap pte */
kmap_vstart = __fix_to_virt(FIX_KMAP_BEGIN);
kmap_pte = kmap_get_fixmap_pte(kmap_vstart);
kmap_prot = PAGE_KERNEL;
}
static void __init init_highmem(void)
{
pgd_t *pgd;
pud_t *pud;
pmd_t *pmd;
pte_t *pte;
unsigned long vaddr;
/*
* Permanent kmaps:
*/
vaddr = PKMAP_BASE;
fixrange_init(vaddr, vaddr + PAGE_SIZE*LAST_PKMAP, swapper_pg_dir);
pgd = swapper_pg_dir + pgd_index(vaddr);
pud = pud_offset(pgd, vaddr);
pmd = pmd_offset(pud, vaddr);
pte = pte_offset_kernel(pmd, vaddr);
pkmap_page_table = pte;
kmap_init();
}
#endif /* CONFIG_HIGHMEM */
static void __init fixaddr_user_init( void)
{
#ifdef CONFIG_ARCH_REUSE_HOST_VSYSCALL_AREA
long size = FIXADDR_USER_END - FIXADDR_USER_START;
pgd_t *pgd;
pud_t *pud;
pmd_t *pmd;
pte_t *pte;
phys_t p;
unsigned long v, vaddr = FIXADDR_USER_START;
if (!size)
return;
fixrange_init( FIXADDR_USER_START, FIXADDR_USER_END, swapper_pg_dir);
v = (unsigned long) alloc_bootmem_low_pages(size);
memcpy((void *) v , (void *) FIXADDR_USER_START, size);
p = __pa(v);
for ( ; size > 0; size -= PAGE_SIZE, vaddr += PAGE_SIZE,
p += PAGE_SIZE) {
pgd = swapper_pg_dir + pgd_index(vaddr);
pud = pud_offset(pgd, vaddr);
pmd = pmd_offset(pud, vaddr);
pte = pte_offset_kernel(pmd, vaddr);
pte_set_val(*pte, p, PAGE_READONLY);
}
#endif
}
void __init paging_init(void)
{
unsigned long zones_size[MAX_NR_ZONES], vaddr;
int i;
empty_zero_page = (unsigned long *) alloc_bootmem_low_pages(PAGE_SIZE);
empty_bad_page = (unsigned long *) alloc_bootmem_low_pages(PAGE_SIZE);
for (i = 0; i < ARRAY_SIZE(zones_size); i++)
zones_size[i] = 0;
zones_size[ZONE_NORMAL] = (end_iomem >> PAGE_SHIFT) -
(uml_physmem >> PAGE_SHIFT);
#ifdef CONFIG_HIGHMEM
zones_size[ZONE_HIGHMEM] = highmem >> PAGE_SHIFT;
#endif
free_area_init(zones_size);
/*
* Fixed mappings, only the page table structure has to be
* created - mappings will be set by set_fixmap():
*/
vaddr = __fix_to_virt(__end_of_fixed_addresses - 1) & PMD_MASK;
fixrange_init(vaddr, FIXADDR_TOP, swapper_pg_dir);
fixaddr_user_init();
#ifdef CONFIG_HIGHMEM
init_highmem();
#endif
}
uml: header untangling Untangle UML headers somewhat and add some includes where they were needed explicitly, but gotten accidentally via some other header. arch/um/include/um_uaccess.h loses asm/fixmap.h because it uses no fixmap stuff and gains elf.h, because it needs FIXADDR_USER_*, and archsetjmp.h, because it needs jmp_buf. pmd_alloc_one is uninlined because it needs mm_struct, and that's inconvenient to provide in asm-um/pgtable-3level.h. elf_core_copy_fpregs is also uninlined from elf-i386.h and elf-x86_64.h, which duplicated the code anyway, to arch/um/kernel/process.c, so that the reference to current_thread doesn't pull sched.h or anything related into asm/elf.h. arch/um/sys-i386/ldt.c, arch/um/kernel/tlb.c and arch/um/kernel/skas/uaccess.c got sched.h because they dereference task_structs. Its includes of linux and asm headers got turned from "" to <>. arch/um/sys-i386/bug.c gets asm/errno.h because it needs errno constants. asm/elf-i386 gets asm/user.h because it needs user_regs_struct. asm/fixmap.h gets page.h because it needs PAGE_SIZE and PAGE_MASK and system.h for BUG_ON. asm/pgtable doesn't need sched.h. asm/processor-generic.h defined mm_segment_t, but didn't use it. So, that definition is moved to uaccess.h, which defines a bunch of mm_segment_t-related stuff. thread_info.h uses mm_segment_t, and includes uaccess.h, which causes a recursion. So, the definition is placed above the include of thread_info. in uaccess.h. thread_info.h also gets page.h because it needs PAGE_SIZE. ObCheckpatchViolationJustification - I'm not adding a typedef; I'm moving mm_segment_t from one place to another. Signed-off-by: Jeff Dike <jdike@linux.intel.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-02-05 14:30:53 +08:00
/*
* This can't do anything because nothing in the kernel image can be freed
* since it's not in kernel physical memory.
*/
void free_initmem(void)
{
}
#ifdef CONFIG_BLK_DEV_INITRD
void free_initrd_mem(unsigned long start, unsigned long end)
{
if (start < end)
printk(KERN_INFO "Freeing initrd memory: %ldk freed\n",
(end - start) >> 10);
for (; start < end; start += PAGE_SIZE) {
ClearPageReserved(virt_to_page(start));
init_page_count(virt_to_page(start));
free_page(start);
totalram_pages++;
}
}
#endif
uml: header untangling Untangle UML headers somewhat and add some includes where they were needed explicitly, but gotten accidentally via some other header. arch/um/include/um_uaccess.h loses asm/fixmap.h because it uses no fixmap stuff and gains elf.h, because it needs FIXADDR_USER_*, and archsetjmp.h, because it needs jmp_buf. pmd_alloc_one is uninlined because it needs mm_struct, and that's inconvenient to provide in asm-um/pgtable-3level.h. elf_core_copy_fpregs is also uninlined from elf-i386.h and elf-x86_64.h, which duplicated the code anyway, to arch/um/kernel/process.c, so that the reference to current_thread doesn't pull sched.h or anything related into asm/elf.h. arch/um/sys-i386/ldt.c, arch/um/kernel/tlb.c and arch/um/kernel/skas/uaccess.c got sched.h because they dereference task_structs. Its includes of linux and asm headers got turned from "" to <>. arch/um/sys-i386/bug.c gets asm/errno.h because it needs errno constants. asm/elf-i386 gets asm/user.h because it needs user_regs_struct. asm/fixmap.h gets page.h because it needs PAGE_SIZE and PAGE_MASK and system.h for BUG_ON. asm/pgtable doesn't need sched.h. asm/processor-generic.h defined mm_segment_t, but didn't use it. So, that definition is moved to uaccess.h, which defines a bunch of mm_segment_t-related stuff. thread_info.h uses mm_segment_t, and includes uaccess.h, which causes a recursion. So, the definition is placed above the include of thread_info. in uaccess.h. thread_info.h also gets page.h because it needs PAGE_SIZE. ObCheckpatchViolationJustification - I'm not adding a typedef; I'm moving mm_segment_t from one place to another. Signed-off-by: Jeff Dike <jdike@linux.intel.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-02-05 14:30:53 +08:00
/* Allocate and free page tables. */
pgd_t *pgd_alloc(struct mm_struct *mm)
{
pgd_t *pgd = (pgd_t *)__get_free_page(GFP_KERNEL);
if (pgd) {
memset(pgd, 0, USER_PTRS_PER_PGD * sizeof(pgd_t));
memcpy(pgd + USER_PTRS_PER_PGD,
swapper_pg_dir + USER_PTRS_PER_PGD,
(PTRS_PER_PGD - USER_PTRS_PER_PGD) * sizeof(pgd_t));
}
return pgd;
}
void pgd_free(struct mm_struct *mm, pgd_t *pgd)
{
free_page((unsigned long) pgd);
}
pte_t *pte_alloc_one_kernel(struct mm_struct *mm, unsigned long address)
{
pte_t *pte;
pte = (pte_t *)__get_free_page(GFP_KERNEL|__GFP_REPEAT|__GFP_ZERO);
return pte;
}
CONFIG_HIGHPTE vs. sub-page page tables. Background: I've implemented 1K/2K page tables for s390. These sub-page page tables are required to properly support the s390 virtualization instruction with KVM. The SIE instruction requires that the page tables have 256 page table entries (pte) followed by 256 page status table entries (pgste). The pgstes are only required if the process is using the SIE instruction. The pgstes are updated by the hardware and by the hypervisor for a number of reasons, one of them is dirty and reference bit tracking. To avoid wasting memory the standard pte table allocation should return 1K/2K (31/64 bit) and 2K/4K if the process is using SIE. Problem: Page size on s390 is 4K, page table size is 1K or 2K. That means the s390 version for pte_alloc_one cannot return a pointer to a struct page. Trouble is that with the CONFIG_HIGHPTE feature on x86 pte_alloc_one cannot return a pointer to a pte either, since that would require more than 32 bit for the return value of pte_alloc_one (and the pte * would not be accessible since its not kmapped). Solution: The only solution I found to this dilemma is a new typedef: a pgtable_t. For s390 pgtable_t will be a (pte *) - to be introduced with a later patch. For everybody else it will be a (struct page *). The additional problem with the initialization of the ptl lock and the NR_PAGETABLE accounting is solved with a constructor pgtable_page_ctor and a destructor pgtable_page_dtor. The page table allocation and free functions need to call these two whenever a page table page is allocated or freed. pmd_populate will get a pgtable_t instead of a struct page pointer. To get the pgtable_t back from a pmd entry that has been installed with pmd_populate a new function pmd_pgtable is added. It replaces the pmd_page call in free_pte_range and apply_to_pte_range. Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: <linux-arch@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-02-08 20:22:04 +08:00
pgtable_t pte_alloc_one(struct mm_struct *mm, unsigned long address)
{
struct page *pte;
pte = alloc_page(GFP_KERNEL|__GFP_REPEAT|__GFP_ZERO);
CONFIG_HIGHPTE vs. sub-page page tables. Background: I've implemented 1K/2K page tables for s390. These sub-page page tables are required to properly support the s390 virtualization instruction with KVM. The SIE instruction requires that the page tables have 256 page table entries (pte) followed by 256 page status table entries (pgste). The pgstes are only required if the process is using the SIE instruction. The pgstes are updated by the hardware and by the hypervisor for a number of reasons, one of them is dirty and reference bit tracking. To avoid wasting memory the standard pte table allocation should return 1K/2K (31/64 bit) and 2K/4K if the process is using SIE. Problem: Page size on s390 is 4K, page table size is 1K or 2K. That means the s390 version for pte_alloc_one cannot return a pointer to a struct page. Trouble is that with the CONFIG_HIGHPTE feature on x86 pte_alloc_one cannot return a pointer to a pte either, since that would require more than 32 bit for the return value of pte_alloc_one (and the pte * would not be accessible since its not kmapped). Solution: The only solution I found to this dilemma is a new typedef: a pgtable_t. For s390 pgtable_t will be a (pte *) - to be introduced with a later patch. For everybody else it will be a (struct page *). The additional problem with the initialization of the ptl lock and the NR_PAGETABLE accounting is solved with a constructor pgtable_page_ctor and a destructor pgtable_page_dtor. The page table allocation and free functions need to call these two whenever a page table page is allocated or freed. pmd_populate will get a pgtable_t instead of a struct page pointer. To get the pgtable_t back from a pmd entry that has been installed with pmd_populate a new function pmd_pgtable is added. It replaces the pmd_page call in free_pte_range and apply_to_pte_range. Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: <linux-arch@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-02-08 20:22:04 +08:00
if (pte)
pgtable_page_ctor(pte);
return pte;
}
uml: header untangling Untangle UML headers somewhat and add some includes where they were needed explicitly, but gotten accidentally via some other header. arch/um/include/um_uaccess.h loses asm/fixmap.h because it uses no fixmap stuff and gains elf.h, because it needs FIXADDR_USER_*, and archsetjmp.h, because it needs jmp_buf. pmd_alloc_one is uninlined because it needs mm_struct, and that's inconvenient to provide in asm-um/pgtable-3level.h. elf_core_copy_fpregs is also uninlined from elf-i386.h and elf-x86_64.h, which duplicated the code anyway, to arch/um/kernel/process.c, so that the reference to current_thread doesn't pull sched.h or anything related into asm/elf.h. arch/um/sys-i386/ldt.c, arch/um/kernel/tlb.c and arch/um/kernel/skas/uaccess.c got sched.h because they dereference task_structs. Its includes of linux and asm headers got turned from "" to <>. arch/um/sys-i386/bug.c gets asm/errno.h because it needs errno constants. asm/elf-i386 gets asm/user.h because it needs user_regs_struct. asm/fixmap.h gets page.h because it needs PAGE_SIZE and PAGE_MASK and system.h for BUG_ON. asm/pgtable doesn't need sched.h. asm/processor-generic.h defined mm_segment_t, but didn't use it. So, that definition is moved to uaccess.h, which defines a bunch of mm_segment_t-related stuff. thread_info.h uses mm_segment_t, and includes uaccess.h, which causes a recursion. So, the definition is placed above the include of thread_info. in uaccess.h. thread_info.h also gets page.h because it needs PAGE_SIZE. ObCheckpatchViolationJustification - I'm not adding a typedef; I'm moving mm_segment_t from one place to another. Signed-off-by: Jeff Dike <jdike@linux.intel.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-02-05 14:30:53 +08:00
#ifdef CONFIG_3_LEVEL_PGTABLES
pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long address)
{
pmd_t *pmd = (pmd_t *) __get_free_page(GFP_KERNEL);
if (pmd)
memset(pmd, 0, PAGE_SIZE);
return pmd;
}
#endif
void *uml_kmalloc(int size, int flags)
{
return kmalloc(size, flags);
}