linux/mm/vmalloc.c

874 lines
20 KiB
C
Raw Normal View History

/*
* linux/mm/vmalloc.c
*
* Copyright (C) 1993 Linus Torvalds
* Support of BIGMEM added by Gerhard Wichert, Siemens AG, July 1999
* SMP-safe vmalloc/vfree/ioremap, Tigran Aivazian <tigran@veritas.com>, May 2000
* Major rework to support vmap/vunmap, Christoph Hellwig, SGI, August 2002
* Numa awareness, Christoph Lameter, SGI, June 2005
*/
#include <linux/mm.h>
#include <linux/module.h>
#include <linux/highmem.h>
#include <linux/slab.h>
#include <linux/spinlock.h>
#include <linux/interrupt.h>
#include <linux/vmalloc.h>
#include <asm/uaccess.h>
#include <asm/tlbflush.h>
DEFINE_RWLOCK(vmlist_lock);
struct vm_struct *vmlist;
static void *__vmalloc_node(unsigned long size, gfp_t gfp_mask, pgprot_t prot,
int node);
static void vunmap_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end)
{
pte_t *pte;
pte = pte_offset_kernel(pmd, addr);
do {
pte_t ptent = ptep_get_and_clear(&init_mm, addr, pte);
WARN_ON(!pte_none(ptent) && !pte_present(ptent));
} while (pte++, addr += PAGE_SIZE, addr != end);
}
static inline void vunmap_pmd_range(pud_t *pud, unsigned long addr,
unsigned long end)
{
pmd_t *pmd;
unsigned long next;
pmd = pmd_offset(pud, addr);
do {
next = pmd_addr_end(addr, end);
if (pmd_none_or_clear_bad(pmd))
continue;
vunmap_pte_range(pmd, addr, next);
} while (pmd++, addr = next, addr != end);
}
static inline void vunmap_pud_range(pgd_t *pgd, unsigned long addr,
unsigned long end)
{
pud_t *pud;
unsigned long next;
pud = pud_offset(pgd, addr);
do {
next = pud_addr_end(addr, end);
if (pud_none_or_clear_bad(pud))
continue;
vunmap_pmd_range(pud, addr, next);
} while (pud++, addr = next, addr != end);
}
void unmap_kernel_range(unsigned long addr, unsigned long size)
{
pgd_t *pgd;
unsigned long next;
unsigned long start = addr;
unsigned long end = addr + size;
BUG_ON(addr >= end);
pgd = pgd_offset_k(addr);
flush_cache_vunmap(addr, end);
do {
next = pgd_addr_end(addr, end);
if (pgd_none_or_clear_bad(pgd))
continue;
vunmap_pud_range(pgd, addr, next);
} while (pgd++, addr = next, addr != end);
flush_tlb_kernel_range(start, end);
}
static void unmap_vm_area(struct vm_struct *area)
{
unmap_kernel_range((unsigned long)area->addr, area->size);
}
static int vmap_pte_range(pmd_t *pmd, unsigned long addr,
unsigned long end, pgprot_t prot, struct page ***pages)
{
pte_t *pte;
[PATCH] mm: init_mm without ptlock First step in pushing down the page_table_lock. init_mm.page_table_lock has been used throughout the architectures (usually for ioremap): not to serialize kernel address space allocation (that's usually vmlist_lock), but because pud_alloc,pmd_alloc,pte_alloc_kernel expect caller holds it. Reverse that: don't lock or unlock init_mm.page_table_lock in any of the architectures; instead rely on pud_alloc,pmd_alloc,pte_alloc_kernel to take and drop it when allocating a new one, to check lest a racing task already did. Similarly no page_table_lock in vmalloc's map_vm_area. Some temporary ugliness in __pud_alloc and __pmd_alloc: since they also handle user mms, which are converted only by a later patch, for now they have to lock differently according to whether or not it's init_mm. If sources get muddled, there's a danger that an arch source taking init_mm.page_table_lock will be mixed with common source also taking it (or neither take it). So break the rules and make another change, which should break the build for such a mismatch: remove the redundant mm arg from pte_alloc_kernel (ppc64 scrapped its distinct ioremap_mm in 2.6.13). Exceptions: arm26 used pte_alloc_kernel on user mm, now pte_alloc_map; ia64 used pte_alloc_map on init_mm, now pte_alloc_kernel; parisc had bad args to pmd_alloc and pte_alloc_kernel in unused USE_HPPA_IOREMAP code; ppc64 map_io_page forgot to unlock on failure; ppc mmu_mapin_ram and ppc64 im_free took page_table_lock for no good reason. Signed-off-by: Hugh Dickins <hugh@veritas.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-10-30 01:16:21 +00:00
pte = pte_alloc_kernel(pmd, addr);
if (!pte)
return -ENOMEM;
do {
struct page *page = **pages;
WARN_ON(!pte_none(*pte));
if (!page)
return -ENOMEM;
set_pte_at(&init_mm, addr, pte, mk_pte(page, prot));
(*pages)++;
} while (pte++, addr += PAGE_SIZE, addr != end);
return 0;
}
static inline int vmap_pmd_range(pud_t *pud, unsigned long addr,
unsigned long end, pgprot_t prot, struct page ***pages)
{
pmd_t *pmd;
unsigned long next;
pmd = pmd_alloc(&init_mm, pud, addr);
if (!pmd)
return -ENOMEM;
do {
next = pmd_addr_end(addr, end);
if (vmap_pte_range(pmd, addr, next, prot, pages))
return -ENOMEM;
} while (pmd++, addr = next, addr != end);
return 0;
}
static inline int vmap_pud_range(pgd_t *pgd, unsigned long addr,
unsigned long end, pgprot_t prot, struct page ***pages)
{
pud_t *pud;
unsigned long next;
pud = pud_alloc(&init_mm, pgd, addr);
if (!pud)
return -ENOMEM;
do {
next = pud_addr_end(addr, end);
if (vmap_pmd_range(pud, addr, next, prot, pages))
return -ENOMEM;
} while (pud++, addr = next, addr != end);
return 0;
}
int map_vm_area(struct vm_struct *area, pgprot_t prot, struct page ***pages)
{
pgd_t *pgd;
unsigned long next;
unsigned long addr = (unsigned long) area->addr;
unsigned long end = addr + area->size - PAGE_SIZE;
int err;
BUG_ON(addr >= end);
pgd = pgd_offset_k(addr);
do {
next = pgd_addr_end(addr, end);
err = vmap_pud_range(pgd, addr, next, prot, pages);
if (err)
break;
} while (pgd++, addr = next, addr != end);
flush_cache_vmap((unsigned long) area->addr, end);
return err;
}
EXPORT_SYMBOL_GPL(map_vm_area);
/*
* Map a vmalloc()-space virtual address to the physical page.
*/
struct page *vmalloc_to_page(const void *vmalloc_addr)
{
unsigned long addr = (unsigned long) vmalloc_addr;
struct page *page = NULL;
pgd_t *pgd = pgd_offset_k(addr);
pud_t *pud;
pmd_t *pmd;
pte_t *ptep, pte;
if (!pgd_none(*pgd)) {
pud = pud_offset(pgd, addr);
if (!pud_none(*pud)) {
pmd = pmd_offset(pud, addr);
if (!pmd_none(*pmd)) {
ptep = pte_offset_map(pmd, addr);
pte = *ptep;
if (pte_present(pte))
page = pte_page(pte);
pte_unmap(ptep);
}
}
}
return page;
}
EXPORT_SYMBOL(vmalloc_to_page);
/*
* Map a vmalloc()-space virtual address to the physical page frame number.
*/
unsigned long vmalloc_to_pfn(const void *vmalloc_addr)
{
return page_to_pfn(vmalloc_to_page(vmalloc_addr));
}
EXPORT_SYMBOL(vmalloc_to_pfn);
static struct vm_struct *__get_vm_area_node(unsigned long size, unsigned long flags,
unsigned long start, unsigned long end,
int node, gfp_t gfp_mask)
{
struct vm_struct **p, *tmp, *area;
unsigned long align = 1;
unsigned long addr;
BUG_ON(in_interrupt());
if (flags & VM_IOREMAP) {
int bit = fls(size);
if (bit > IOREMAP_MAX_ORDER)
bit = IOREMAP_MAX_ORDER;
else if (bit < PAGE_SHIFT)
bit = PAGE_SHIFT;
align = 1ul << bit;
}
addr = ALIGN(start, align);
size = PAGE_ALIGN(size);
if (unlikely(!size))
return NULL;
Categorize GFP flags The function of GFP_LEVEL_MASK seems to be unclear. In order to clear up the mystery we get rid of it and replace GFP_LEVEL_MASK with 3 sets of GFP flags: GFP_RECLAIM_MASK Flags used to control page allocator reclaim behavior. GFP_CONSTRAINT_MASK Flags used to limit where allocations can occur. GFP_SLAB_BUG_MASK Flags that the slab allocator BUG()s on. These replace the uses of GFP_LEVEL mask in the slab allocators and in vmalloc.c. The use of the flags not included in these sets may occur as a result of a slab allocation standing in for a page allocation when constructing scatter gather lists. Extraneous flags are cleared and not passed through to the page allocator. __GFP_MOVABLE/RECLAIMABLE, __GFP_COLD and __GFP_COMP will now be ignored if passed to a slab allocator. Change the allocation of allocator meta data in SLAB and vmalloc to not pass through flags listed in GFP_CONSTRAINT_MASK. SLAB already removes the __GFP_THISNODE flag for such allocations. Generalize that to also cover vmalloc. The use of GFP_CONSTRAINT_MASK also includes __GFP_HARDWALL. The impact of allocator metadata placement on access latency to the cachelines of the object itself is minimal since metadata is only referenced on alloc and free. The attempt is still made to place the meta data optimally but we consistently allow fallback both in SLAB and vmalloc (SLUB does not need to allocate metadata like that). Allocator metadata may serve multiple in kernel users and thus should not be subject to the limitations arising from a single allocation context. [akpm@linux-foundation.org: fix fallback_alloc()] Signed-off-by: Christoph Lameter <clameter@sgi.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-10-16 08:25:41 +00:00
area = kmalloc_node(sizeof(*area), gfp_mask & GFP_RECLAIM_MASK, node);
if (unlikely(!area))
return NULL;
/*
* We always allocate a guard page.
*/
size += PAGE_SIZE;
write_lock(&vmlist_lock);
for (p = &vmlist; (tmp = *p) != NULL ;p = &tmp->next) {
if ((unsigned long)tmp->addr < addr) {
if((unsigned long)tmp->addr + tmp->size >= addr)
addr = ALIGN(tmp->size +
(unsigned long)tmp->addr, align);
continue;
}
if ((size + addr) < addr)
goto out;
if (size + addr <= (unsigned long)tmp->addr)
goto found;
addr = ALIGN(tmp->size + (unsigned long)tmp->addr, align);
if (addr > end - size)
goto out;
}
if ((size + addr) < addr)
goto out;
if (addr > end - size)
goto out;
found:
area->next = *p;
*p = area;
area->flags = flags;
area->addr = (void *)addr;
area->size = size;
area->pages = NULL;
area->nr_pages = 0;
area->phys_addr = 0;
write_unlock(&vmlist_lock);
return area;
out:
write_unlock(&vmlist_lock);
kfree(area);
if (printk_ratelimit())
printk(KERN_WARNING "allocation failed: out of vmalloc space - use vmalloc=<size> to increase size.\n");
return NULL;
}
struct vm_struct *__get_vm_area(unsigned long size, unsigned long flags,
unsigned long start, unsigned long end)
{
return __get_vm_area_node(size, flags, start, end, -1, GFP_KERNEL);
}
EXPORT_SYMBOL_GPL(__get_vm_area);
/**
* get_vm_area - reserve a contiguous kernel virtual area
* @size: size of the area
* @flags: %VM_IOREMAP for I/O mappings or VM_ALLOC
*
* Search an area of @size in the kernel virtual mapping area,
* and reserved it for out purposes. Returns the area descriptor
* on success or %NULL on failure.
*/
struct vm_struct *get_vm_area(unsigned long size, unsigned long flags)
{
return __get_vm_area(size, flags, VMALLOC_START, VMALLOC_END);
}
struct vm_struct *get_vm_area_node(unsigned long size, unsigned long flags,
int node, gfp_t gfp_mask)
{
return __get_vm_area_node(size, flags, VMALLOC_START, VMALLOC_END, node,
gfp_mask);
}
/* Caller must hold vmlist_lock */
static struct vm_struct *__find_vm_area(const void *addr)
{
struct vm_struct *tmp;
for (tmp = vmlist; tmp != NULL; tmp = tmp->next) {
if (tmp->addr == addr)
break;
}
return tmp;
}
/* Caller must hold vmlist_lock */
static struct vm_struct *__remove_vm_area(const void *addr)
{
struct vm_struct **p, *tmp;
for (p = &vmlist ; (tmp = *p) != NULL ;p = &tmp->next) {
if (tmp->addr == addr)
goto found;
}
return NULL;
found:
unmap_vm_area(tmp);
*p = tmp->next;
/*
* Remove the guard page.
*/
tmp->size -= PAGE_SIZE;
return tmp;
}
/**
* remove_vm_area - find and remove a continuous kernel virtual area
* @addr: base address
*
* Search for the kernel VM area starting at @addr, and remove it.
* This function returns the found VM area, but using it is NOT safe
* on SMP machines, except for its size or flags.
*/
struct vm_struct *remove_vm_area(const void *addr)
{
struct vm_struct *v;
write_lock(&vmlist_lock);
v = __remove_vm_area(addr);
write_unlock(&vmlist_lock);
return v;
}
static void __vunmap(const void *addr, int deallocate_pages)
{
struct vm_struct *area;
if (!addr)
return;
if ((PAGE_SIZE-1) & (unsigned long)addr) {
printk(KERN_ERR "Trying to vfree() bad address (%p)\n", addr);
WARN_ON(1);
return;
}
area = remove_vm_area(addr);
if (unlikely(!area)) {
printk(KERN_ERR "Trying to vfree() nonexistent vm area (%p)\n",
addr);
WARN_ON(1);
return;
}
debug_check_no_locks_freed(addr, area->size);
if (deallocate_pages) {
int i;
for (i = 0; i < area->nr_pages; i++) {
struct page *page = area->pages[i];
BUG_ON(!page);
__free_page(page);
}
if (area->flags & VM_VPAGES)
vfree(area->pages);
else
kfree(area->pages);
}
kfree(area);
return;
}
/**
* vfree - release memory allocated by vmalloc()
* @addr: memory base address
*
* Free the virtually continuous memory area starting at @addr, as
* obtained from vmalloc(), vmalloc_32() or __vmalloc(). If @addr is
* NULL, no operation is performed.
*
* Must not be called in interrupt context.
*/
void vfree(const void *addr)
{
BUG_ON(in_interrupt());
__vunmap(addr, 1);
}
EXPORT_SYMBOL(vfree);
/**
* vunmap - release virtual mapping obtained by vmap()
* @addr: memory base address
*
* Free the virtually contiguous memory area starting at @addr,
* which was created from the page array passed to vmap().
*
* Must not be called in interrupt context.
*/
void vunmap(const void *addr)
{
BUG_ON(in_interrupt());
__vunmap(addr, 0);
}
EXPORT_SYMBOL(vunmap);
/**
* vmap - map an array of pages into virtually contiguous space
* @pages: array of page pointers
* @count: number of pages to map
* @flags: vm_area->flags
* @prot: page protection for the mapping
*
* Maps @count pages from @pages into contiguous kernel virtual
* space.
*/
void *vmap(struct page **pages, unsigned int count,
unsigned long flags, pgprot_t prot)
{
struct vm_struct *area;
if (count > num_physpages)
return NULL;
area = get_vm_area((count << PAGE_SHIFT), flags);
if (!area)
return NULL;
if (map_vm_area(area, prot, &pages)) {
vunmap(area->addr);
return NULL;
}
return area->addr;
}
EXPORT_SYMBOL(vmap);
static void *__vmalloc_area_node(struct vm_struct *area, gfp_t gfp_mask,
pgprot_t prot, int node)
{
struct page **pages;
unsigned int nr_pages, array_size, i;
nr_pages = (area->size - PAGE_SIZE) >> PAGE_SHIFT;
array_size = (nr_pages * sizeof(struct page *));
area->nr_pages = nr_pages;
/* Please note that the recursion is strictly bounded. */
if (array_size > PAGE_SIZE) {
pages = __vmalloc_node(array_size, gfp_mask | __GFP_ZERO,
PAGE_KERNEL, node);
area->flags |= VM_VPAGES;
} else {
pages = kmalloc_node(array_size,
Categorize GFP flags The function of GFP_LEVEL_MASK seems to be unclear. In order to clear up the mystery we get rid of it and replace GFP_LEVEL_MASK with 3 sets of GFP flags: GFP_RECLAIM_MASK Flags used to control page allocator reclaim behavior. GFP_CONSTRAINT_MASK Flags used to limit where allocations can occur. GFP_SLAB_BUG_MASK Flags that the slab allocator BUG()s on. These replace the uses of GFP_LEVEL mask in the slab allocators and in vmalloc.c. The use of the flags not included in these sets may occur as a result of a slab allocation standing in for a page allocation when constructing scatter gather lists. Extraneous flags are cleared and not passed through to the page allocator. __GFP_MOVABLE/RECLAIMABLE, __GFP_COLD and __GFP_COMP will now be ignored if passed to a slab allocator. Change the allocation of allocator meta data in SLAB and vmalloc to not pass through flags listed in GFP_CONSTRAINT_MASK. SLAB already removes the __GFP_THISNODE flag for such allocations. Generalize that to also cover vmalloc. The use of GFP_CONSTRAINT_MASK also includes __GFP_HARDWALL. The impact of allocator metadata placement on access latency to the cachelines of the object itself is minimal since metadata is only referenced on alloc and free. The attempt is still made to place the meta data optimally but we consistently allow fallback both in SLAB and vmalloc (SLUB does not need to allocate metadata like that). Allocator metadata may serve multiple in kernel users and thus should not be subject to the limitations arising from a single allocation context. [akpm@linux-foundation.org: fix fallback_alloc()] Signed-off-by: Christoph Lameter <clameter@sgi.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-10-16 08:25:41 +00:00
(gfp_mask & GFP_RECLAIM_MASK) | __GFP_ZERO,
node);
}
area->pages = pages;
if (!area->pages) {
remove_vm_area(area->addr);
kfree(area);
return NULL;
}
for (i = 0; i < area->nr_pages; i++) {
struct page *page;
if (node < 0)
page = alloc_page(gfp_mask);
else
page = alloc_pages_node(node, gfp_mask, 0);
if (unlikely(!page)) {
/* Successfully allocated i pages, free them in __vunmap() */
area->nr_pages = i;
goto fail;
}
area->pages[i] = page;
}
if (map_vm_area(area, prot, &pages))
goto fail;
return area->addr;
fail:
vfree(area->addr);
return NULL;
}
void *__vmalloc_area(struct vm_struct *area, gfp_t gfp_mask, pgprot_t prot)
{
return __vmalloc_area_node(area, gfp_mask, prot, -1);
}
/**
* __vmalloc_node - allocate virtually contiguous memory
* @size: allocation size
* @gfp_mask: flags for the page level allocator
* @prot: protection mask for the allocated pages
* @node: node to use for allocation or -1
*
* Allocate enough pages to cover @size from the page level
* allocator with @gfp_mask flags. Map them into contiguous
* kernel virtual space, using a pagetable protection of @prot.
*/
static void *__vmalloc_node(unsigned long size, gfp_t gfp_mask, pgprot_t prot,
int node)
{
struct vm_struct *area;
size = PAGE_ALIGN(size);
if (!size || (size >> PAGE_SHIFT) > num_physpages)
return NULL;
area = get_vm_area_node(size, VM_ALLOC, node, gfp_mask);
if (!area)
return NULL;
return __vmalloc_area_node(area, gfp_mask, prot, node);
}
void *__vmalloc(unsigned long size, gfp_t gfp_mask, pgprot_t prot)
{
return __vmalloc_node(size, gfp_mask, prot, -1);
}
EXPORT_SYMBOL(__vmalloc);
/**
* vmalloc - allocate virtually contiguous memory
* @size: allocation size
* Allocate enough pages to cover @size from the page level
* allocator and map them into contiguous kernel virtual space.
*
* For tight control over page level allocator and protection flags
* use __vmalloc() instead.
*/
void *vmalloc(unsigned long size)
{
return __vmalloc(size, GFP_KERNEL | __GFP_HIGHMEM, PAGE_KERNEL);
}
EXPORT_SYMBOL(vmalloc);
/**
* vmalloc_user - allocate zeroed virtually contiguous memory for userspace
* @size: allocation size
*
* The resulting memory area is zeroed so it can be mapped to userspace
* without leaking data.
*/
void *vmalloc_user(unsigned long size)
{
struct vm_struct *area;
void *ret;
ret = __vmalloc(size, GFP_KERNEL | __GFP_HIGHMEM | __GFP_ZERO, PAGE_KERNEL);
if (ret) {
write_lock(&vmlist_lock);
area = __find_vm_area(ret);
area->flags |= VM_USERMAP;
write_unlock(&vmlist_lock);
}
return ret;
}
EXPORT_SYMBOL(vmalloc_user);
/**
* vmalloc_node - allocate memory on a specific node
* @size: allocation size
* @node: numa node
*
* Allocate enough pages to cover @size from the page level
* allocator and map them into contiguous kernel virtual space.
*
* For tight control over page level allocator and protection flags
* use __vmalloc() instead.
*/
void *vmalloc_node(unsigned long size, int node)
{
return __vmalloc_node(size, GFP_KERNEL | __GFP_HIGHMEM, PAGE_KERNEL, node);
}
EXPORT_SYMBOL(vmalloc_node);
[PATCH] DocBook: changes and extensions to the kernel documentation I have recompiled Linux kernel 2.6.11.5 documentation for me and our university students again. The documentation could be extended for more sources which are equipped by structured comments for recent 2.6 kernels. I have tried to proceed with that task. I have done that more times from 2.6.0 time and it gets boring to do same changes again and again. Linux kernel compiles after changes for i386 and ARM targets. I have added references to some more files into kernel-api book, I have added some section names as well. So please, check that changes do not break something and that categories are not too much skewed. I have changed kernel-doc to accept "fastcall" and "asmlinkage" words reserved by kernel convention. Most of the other changes are modifications in the comments to make kernel-doc happy, accept some parameters description and do not bail out on errors. Changed <pid> to @pid in the description, moved some #ifdef before comments to correct function to comments bindings, etc. You can see result of the modified documentation build at http://cmp.felk.cvut.cz/~pisa/linux/lkdb-2.6.11.tar.gz Some more sources are ready to be included into kernel-doc generated documentation. Sources has been added into kernel-api for now. Some more section names added and probably some more chaos introduced as result of quick cleanup work. Signed-off-by: Pavel Pisa <pisa@cmp.felk.cvut.cz> Signed-off-by: Martin Waitz <tali@admingilde.org> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-05-01 15:59:25 +00:00
#ifndef PAGE_KERNEL_EXEC
# define PAGE_KERNEL_EXEC PAGE_KERNEL
#endif
/**
* vmalloc_exec - allocate virtually contiguous, executable memory
* @size: allocation size
*
* Kernel-internal function to allocate enough pages to cover @size
* the page level allocator and map them into contiguous and
* executable kernel virtual space.
*
* For tight control over page level allocator and protection flags
* use __vmalloc() instead.
*/
void *vmalloc_exec(unsigned long size)
{
return __vmalloc(size, GFP_KERNEL | __GFP_HIGHMEM, PAGE_KERNEL_EXEC);
}
#if defined(CONFIG_64BIT) && defined(CONFIG_ZONE_DMA32)
#define GFP_VMALLOC32 GFP_DMA32 | GFP_KERNEL
#elif defined(CONFIG_64BIT) && defined(CONFIG_ZONE_DMA)
#define GFP_VMALLOC32 GFP_DMA | GFP_KERNEL
#else
#define GFP_VMALLOC32 GFP_KERNEL
#endif
/**
* vmalloc_32 - allocate virtually contiguous memory (32bit addressable)
* @size: allocation size
*
* Allocate enough 32bit PA addressable pages to cover @size from the
* page level allocator and map them into contiguous kernel virtual space.
*/
void *vmalloc_32(unsigned long size)
{
return __vmalloc(size, GFP_VMALLOC32, PAGE_KERNEL);
}
EXPORT_SYMBOL(vmalloc_32);
/**
* vmalloc_32_user - allocate zeroed virtually contiguous 32bit memory
* @size: allocation size
*
* The resulting memory area is 32bit addressable and zeroed so it can be
* mapped to userspace without leaking data.
*/
void *vmalloc_32_user(unsigned long size)
{
struct vm_struct *area;
void *ret;
ret = __vmalloc(size, GFP_VMALLOC32 | __GFP_ZERO, PAGE_KERNEL);
if (ret) {
write_lock(&vmlist_lock);
area = __find_vm_area(ret);
area->flags |= VM_USERMAP;
write_unlock(&vmlist_lock);
}
return ret;
}
EXPORT_SYMBOL(vmalloc_32_user);
long vread(char *buf, char *addr, unsigned long count)
{
struct vm_struct *tmp;
char *vaddr, *buf_start = buf;
unsigned long n;
/* Don't allow overflow */
if ((unsigned long) addr + count < count)
count = -(unsigned long) addr;
read_lock(&vmlist_lock);
for (tmp = vmlist; tmp; tmp = tmp->next) {
vaddr = (char *) tmp->addr;
if (addr >= vaddr + tmp->size - PAGE_SIZE)
continue;
while (addr < vaddr) {
if (count == 0)
goto finished;
*buf = '\0';
buf++;
addr++;
count--;
}
n = vaddr + tmp->size - PAGE_SIZE - addr;
do {
if (count == 0)
goto finished;
*buf = *addr;
buf++;
addr++;
count--;
} while (--n > 0);
}
finished:
read_unlock(&vmlist_lock);
return buf - buf_start;
}
long vwrite(char *buf, char *addr, unsigned long count)
{
struct vm_struct *tmp;
char *vaddr, *buf_start = buf;
unsigned long n;
/* Don't allow overflow */
if ((unsigned long) addr + count < count)
count = -(unsigned long) addr;
read_lock(&vmlist_lock);
for (tmp = vmlist; tmp; tmp = tmp->next) {
vaddr = (char *) tmp->addr;
if (addr >= vaddr + tmp->size - PAGE_SIZE)
continue;
while (addr < vaddr) {
if (count == 0)
goto finished;
buf++;
addr++;
count--;
}
n = vaddr + tmp->size - PAGE_SIZE - addr;
do {
if (count == 0)
goto finished;
*addr = *buf;
buf++;
addr++;
count--;
} while (--n > 0);
}
finished:
read_unlock(&vmlist_lock);
return buf - buf_start;
}
/**
* remap_vmalloc_range - map vmalloc pages to userspace
* @vma: vma to cover (map full range of vma)
* @addr: vmalloc memory
* @pgoff: number of pages into addr before first page to map
* @returns: 0 for success, -Exxx on failure
*
* This function checks that addr is a valid vmalloc'ed area, and
* that it is big enough to cover the vma. Will return failure if
* that criteria isn't met.
*
* Similar to remap_pfn_range() (see mm/memory.c)
*/
int remap_vmalloc_range(struct vm_area_struct *vma, void *addr,
unsigned long pgoff)
{
struct vm_struct *area;
unsigned long uaddr = vma->vm_start;
unsigned long usize = vma->vm_end - vma->vm_start;
int ret;
if ((PAGE_SIZE-1) & (unsigned long)addr)
return -EINVAL;
read_lock(&vmlist_lock);
area = __find_vm_area(addr);
if (!area)
goto out_einval_locked;
if (!(area->flags & VM_USERMAP))
goto out_einval_locked;
if (usize + (pgoff << PAGE_SHIFT) > area->size - PAGE_SIZE)
goto out_einval_locked;
read_unlock(&vmlist_lock);
addr += pgoff << PAGE_SHIFT;
do {
struct page *page = vmalloc_to_page(addr);
ret = vm_insert_page(vma, uaddr, page);
if (ret)
return ret;
uaddr += PAGE_SIZE;
addr += PAGE_SIZE;
usize -= PAGE_SIZE;
} while (usize > 0);
/* Prevent "things" like memory migration? VM_flags need a cleanup... */
vma->vm_flags |= VM_RESERVED;
return ret;
out_einval_locked:
read_unlock(&vmlist_lock);
return -EINVAL;
}
EXPORT_SYMBOL(remap_vmalloc_range);
/*
* Implement a stub for vmalloc_sync_all() if the architecture chose not to
* have one.
*/
void __attribute__((weak)) vmalloc_sync_all(void)
{
}
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 12:22:04 +00:00
static int f(pte_t *pte, pgtable_t table, unsigned long addr, void *data)
{
/* apply_to_page_range() does all the hard work. */
return 0;
}
/**
* alloc_vm_area - allocate a range of kernel address space
* @size: size of the area
* @returns: NULL on failure, vm_struct on success
*
* This function reserves a range of kernel address space, and
* allocates pagetables to map that range. No actual mappings
* are created. If the kernel address space is not shared
* between processes, it syncs the pagetable across all
* processes.
*/
struct vm_struct *alloc_vm_area(size_t size)
{
struct vm_struct *area;
area = get_vm_area(size, VM_IOREMAP);
if (area == NULL)
return NULL;
/*
* This ensures that page tables are constructed for this region
* of kernel virtual address space and mapped into init_mm.
*/
if (apply_to_page_range(&init_mm, (unsigned long)area->addr,
area->size, f, NULL)) {
free_vm_area(area);
return NULL;
}
/* Make sure the pagetables are constructed in process kernel
mappings */
vmalloc_sync_all();
return area;
}
EXPORT_SYMBOL_GPL(alloc_vm_area);
void free_vm_area(struct vm_struct *area)
{
struct vm_struct *ret;
ret = remove_vm_area(area->addr);
BUG_ON(ret != area);
kfree(area);
}
EXPORT_SYMBOL_GPL(free_vm_area);