* 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>
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;
} while (pud++, addr = next, addr != end);
}
-void unmap_vm_area(struct vm_struct *area)
+void unmap_kernel_range(unsigned long addr, unsigned long size)
{
pgd_t *pgd;
unsigned long next;
- unsigned long addr = (unsigned long) area->addr;
- unsigned long end = addr + area->size;
+ unsigned long start = addr;
+ unsigned long end = addr + size;
BUG_ON(addr >= end);
pgd = pgd_offset_k(addr);
continue;
vunmap_pud_range(pgd, addr, next);
} while (pgd++, addr = next, addr != end);
- flush_tlb_kernel_range((unsigned long) area->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,
{
pte_t *pte;
- pte = pte_alloc_kernel(&init_mm, pmd, addr);
+ pte = pte_alloc_kernel(pmd, addr);
if (!pte)
return -ENOMEM;
do {
BUG_ON(addr >= end);
pgd = pgd_offset_k(addr);
- spin_lock(&init_mm.page_table_lock);
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);
- spin_unlock(&init_mm.page_table_lock);
flush_cache_vmap((unsigned long) area->addr, end);
return err;
}
+EXPORT_SYMBOL_GPL(map_vm_area);
-#define IOREMAP_MAX_ORDER (7 + PAGE_SHIFT) /* 128 pages */
+/*
+ * 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);
-struct vm_struct *__get_vm_area(unsigned long size, unsigned long flags,
- unsigned long start, unsigned long end)
+/*
+ * 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);
}
addr = ALIGN(start, align);
size = PAGE_ALIGN(size);
-
- area = kmalloc(sizeof(*area), GFP_KERNEL);
- if (unlikely(!area))
+ if (unlikely(!size))
return NULL;
- if (unlikely(!size)) {
- kfree (area);
+ area = kmalloc_node(sizeof(*area), gfp_mask & GFP_RECLAIM_MASK, node);
+
+ if (unlikely(!area))
return NULL;
- }
/*
* We always allocate a guard page.
if (addr > end - size)
goto out;
}
+ if ((size + addr) < addr)
+ goto out;
+ if (addr > end - size)
+ goto out;
found:
area->next = *p;
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 contingous kernel virtual 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
*
return __get_vm_area(size, flags, VMALLOC_START, VMALLOC_END);
}
-/**
- * remove_vm_area - find and remove a contingous 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.
- */
-struct vm_struct *remove_vm_area(void *addr)
+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;
- write_lock(&vmlist_lock);
for (p = &vmlist ; (tmp = *p) != NULL ;p = &tmp->next) {
if (tmp->addr == addr)
goto found;
}
- write_unlock(&vmlist_lock);
return NULL;
found:
unmap_vm_area(tmp);
*p = tmp->next;
- write_unlock(&vmlist_lock);
/*
* Remove the guard page.
return tmp;
}
-void __vunmap(void *addr, int deallocate_pages)
+/**
+ * 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;
return;
}
+ debug_check_no_locks_freed(addr, area->size);
+
if (deallocate_pages) {
int i;
for (i = 0; i < area->nr_pages; i++) {
- if (unlikely(!area->pages[i]))
- BUG();
- __free_page(area->pages[i]);
+ struct page *page = area->pages[i];
+
+ BUG_ON(!page);
+ __free_page(page);
}
- if (area->nr_pages > PAGE_SIZE/sizeof(struct page *))
+ if (area->flags & VM_VPAGES)
vfree(area->pages);
else
kfree(area->pages);
/**
* vfree - release memory allocated by vmalloc()
- *
* @addr: memory base address
*
- * Free the virtually contiguous memory area starting at @addr, as
- * obtained from vmalloc(), vmalloc_32() or __vmalloc().
+ * 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.
*
- * May not be called in interrupt context.
+ * Must not be called in interrupt context.
*/
-void vfree(void *addr)
+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().
*
- * May not be called in interrupt context.
+ * Must not be called in interrupt context.
*/
-void vunmap(void *addr)
+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
return area->addr;
}
-
EXPORT_SYMBOL(vmap);
-void *__vmalloc_area(struct vm_struct *area, unsigned int __nocast gfp_mask, pgprot_t prot)
+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;
area->nr_pages = nr_pages;
/* Please note that the recursion is strictly bounded. */
- if (array_size > PAGE_SIZE)
- pages = __vmalloc(array_size, gfp_mask, PAGE_KERNEL);
- else
- pages = kmalloc(array_size, (gfp_mask & ~__GFP_HIGHMEM));
+ 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,
+ (gfp_mask & GFP_RECLAIM_MASK) | __GFP_ZERO,
+ node);
+ }
area->pages = pages;
if (!area->pages) {
remove_vm_area(area->addr);
kfree(area);
return NULL;
}
- memset(area->pages, 0, array_size);
for (i = 0; i < area->nr_pages; i++) {
- area->pages[i] = alloc_page(gfp_mask);
- if (unlikely(!area->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))
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 - allocate virtually contiguous memory
- *
+ * __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.
*/
-void *__vmalloc(unsigned long size, unsigned int __nocast gfp_mask, pgprot_t prot)
+static void *__vmalloc_node(unsigned long size, gfp_t gfp_mask, pgprot_t prot,
+ int node)
{
struct vm_struct *area;
if (!size || (size >> PAGE_SHIFT) > num_physpages)
return NULL;
- area = get_vm_area(size, VM_ALLOC);
+ area = get_vm_area_node(size, VM_ALLOC, node, gfp_mask);
if (!area)
return NULL;
- return __vmalloc_area(area, gfp_mask, prot);
+ 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 cotrol over page level allocator and protection flags
+ * 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);
+ return __vmalloc(size, GFP_KERNEL | __GFP_HIGHMEM, PAGE_KERNEL);
}
-
EXPORT_SYMBOL(vmalloc);
/**
- * vmalloc_exec - allocate virtually contiguous, executable memory
+ * 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
*
- * Kernel-internal function to allocate enough pages to cover @size
- * the page level allocator and map them into contiguous and
- * executable kernel virtual space.
+ * Allocate enough pages to cover @size from the page level
+ * allocator and map them into contiguous kernel virtual space.
*
- * For tight cotrol over page level allocator and protection flags
+ * 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);
#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
*/
void *vmalloc_32(unsigned long size)
{
- return __vmalloc(size, GFP_KERNEL, PAGE_KERNEL);
+ 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;
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)
+{
+}
+
+
+static int f(pte_t *pte, struct page *pmd_page, 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);
git://ftp.safe.ca / safe / jmp / linux-2.6 / blobdiff