* Copyright (c) 2000-2003 David McCullough <davidm@snapgear.com>
* Copyright (c) 2000-2001 D Jeff Dionne <jeff@uClinux.org>
* Copyright (c) 2002 Greg Ungerer <gerg@snapgear.com>
+ * Copyright (c) 2007 Paul Mundt <lethal@linux-sh.org>
*/
#include <linux/module.h>
#include <linux/pagemap.h>
#include <linux/slab.h>
#include <linux/vmalloc.h>
-#include <linux/ptrace.h>
+#include <linux/tracehook.h>
#include <linux/blkdev.h>
#include <linux/backing-dev.h>
#include <linux/mount.h>
#include <asm/tlb.h>
#include <asm/tlbflush.h>
+#include "internal.h"
+
void *high_memory;
struct page *mem_map;
unsigned long max_mapnr;
unsigned long num_physpages;
unsigned long askedalloc, realalloc;
-atomic_t vm_committed_space = ATOMIC_INIT(0);
+atomic_long_t vm_committed_space = ATOMIC_LONG_INIT(0);
int sysctl_overcommit_memory = OVERCOMMIT_GUESS; /* heuristic overcommit */
int sysctl_overcommit_ratio = 50; /* default is 50% */
int sysctl_max_map_count = DEFAULT_MAX_MAP_COUNT;
i_size_write(inode, offset);
out_truncate:
- if (inode->i_op && inode->i_op->truncate)
+ if (inode->i_op->truncate)
inode->i_op->truncate(inode);
return 0;
out_sig:
{
struct page *page;
- if (!objp || !((page = virt_to_page(objp))))
+ /*
+ * If the object we have should not have ksize performed on it,
+ * return size of 0
+ */
+ if (!objp || !virt_addr_valid(objp))
return 0;
+ page = virt_to_head_page(objp);
+
+ /*
+ * If the allocator sets PageSlab, we know the pointer came from
+ * kmalloc().
+ */
if (PageSlab(page))
return ksize(objp);
- BUG_ON(page->index < 0);
- BUG_ON(page->index >= MAX_ORDER);
-
- return (PAGE_SIZE << page->index);
+ /*
+ * The ksize() function is only guaranteed to work for pointers
+ * returned by kmalloc(). So handle arbitrary pointers here.
+ */
+ return PAGE_SIZE << compound_order(page);
}
-/*
- * get a list of pages in an address range belonging to the specified process
- * and indicate the VMA that covers each page
- * - this is potentially dodgy as we may end incrementing the page count of a
- * slab page or a secondary page from a compound page
- * - don't permit access to VMAs that don't support it, such as I/O mappings
- */
-int get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
- unsigned long start, int len, int write, int force,
- struct page **pages, struct vm_area_struct **vmas)
+int __get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
+ unsigned long start, int len, int flags,
+ struct page **pages, struct vm_area_struct **vmas)
{
struct vm_area_struct *vma;
unsigned long vm_flags;
int i;
+ int write = !!(flags & GUP_FLAGS_WRITE);
+ int force = !!(flags & GUP_FLAGS_FORCE);
+ int ignore = !!(flags & GUP_FLAGS_IGNORE_VMA_PERMISSIONS);
/* calculate required read or write permissions.
* - if 'force' is set, we only require the "MAY" flags.
/* protect what we can, including chardevs */
if (vma->vm_flags & (VM_IO | VM_PFNMAP) ||
- !(vm_flags & vma->vm_flags))
+ (!ignore && !(vm_flags & vma->vm_flags)))
goto finish_or_fault;
if (pages) {
finish_or_fault:
return i ? : -EFAULT;
}
+
+
+/*
+ * get a list of pages in an address range belonging to the specified process
+ * and indicate the VMA that covers each page
+ * - this is potentially dodgy as we may end incrementing the page count of a
+ * slab page or a secondary page from a compound page
+ * - don't permit access to VMAs that don't support it, such as I/O mappings
+ */
+int get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
+ unsigned long start, int len, int write, int force,
+ struct page **pages, struct vm_area_struct **vmas)
+{
+ int flags = 0;
+
+ if (write)
+ flags |= GUP_FLAGS_WRITE;
+ if (force)
+ flags |= GUP_FLAGS_FORCE;
+
+ return __get_user_pages(tsk, mm,
+ start, len, flags,
+ pages, vmas);
+}
EXPORT_SYMBOL(get_user_pages);
DEFINE_RWLOCK(vmlist_lock);
}
EXPORT_SYMBOL(__vmalloc);
+void *vmalloc_user(unsigned long size)
+{
+ void *ret;
+
+ ret = __vmalloc(size, GFP_KERNEL | __GFP_HIGHMEM | __GFP_ZERO,
+ PAGE_KERNEL);
+ if (ret) {
+ struct vm_area_struct *vma;
+
+ down_write(¤t->mm->mmap_sem);
+ vma = find_vma(current->mm, (unsigned long)ret);
+ if (vma)
+ vma->vm_flags |= VM_USERMAP;
+ up_write(¤t->mm->mmap_sem);
+ }
+
+ return ret;
+}
+EXPORT_SYMBOL(vmalloc_user);
+
struct page *vmalloc_to_page(const void *addr)
{
return virt_to_page(addr);
}
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);
+}
+
/**
* vmalloc_32 - allocate virtually contiguous memory (32bit addressable)
* @size: allocation size
*
* The resulting memory area is 32bit addressable and zeroed so it can be
* mapped to userspace without leaking data.
+ *
+ * VM_USERMAP is set on the corresponding VMA so that subsequent calls to
+ * remap_vmalloc_range() are permissible.
*/
void *vmalloc_32_user(unsigned long size)
{
- return __vmalloc(size, GFP_KERNEL | __GFP_ZERO, PAGE_KERNEL);
+ /*
+ * We'll have to sort out the ZONE_DMA bits for 64-bit,
+ * but for now this can simply use vmalloc_user() directly.
+ */
+ return vmalloc_user(size);
}
EXPORT_SYMBOL(vmalloc_32_user);
* it's being traced - otherwise breakpoints set in it may interfere
* with another untraced process
*/
- if ((flags & MAP_PRIVATE) && (current->ptrace & PT_PTRACED))
+ if ((flags & MAP_PRIVATE) && tracehook_expect_breakpoints(current))
vm_flags &= ~VM_MAYSHARE;
return vm_flags;
INIT_LIST_HEAD(&vma->anon_vma_node);
atomic_set(&vma->vm_usage, 1);
- if (file)
+ if (file) {
get_file(file);
+ if (vm_flags & VM_EXECUTABLE) {
+ added_exe_file_vma(current->mm);
+ vma->vm_mm = current->mm;
+ }
+ }
vma->vm_file = file;
vma->vm_flags = vm_flags;
vma->vm_start = addr;
up_write(&nommu_vma_sem);
kfree(vml);
if (vma) {
- if (vma->vm_file)
+ if (vma->vm_file) {
fput(vma->vm_file);
+ if (vma->vm_flags & VM_EXECUTABLE)
+ removed_exe_file_vma(vma->vm_mm);
+ }
kfree(vma);
}
return ret;
/*
* handle mapping disposal for uClinux
*/
-static void put_vma(struct vm_area_struct *vma)
+static void put_vma(struct mm_struct *mm, struct vm_area_struct *vma)
{
if (vma) {
down_write(&nommu_vma_sem);
realalloc -= kobjsize(vma);
askedalloc -= sizeof(*vma);
- if (vma->vm_file)
+ if (vma->vm_file) {
fput(vma->vm_file);
+ if (vma->vm_flags & VM_EXECUTABLE)
+ removed_exe_file_vma(mm);
+ }
kfree(vma);
}
found:
vml = *parent;
- put_vma(vml->vma);
+ put_vma(mm, vml->vma);
*parent = vml->next;
realalloc -= kobjsize(vml);
while ((tmp = mm->context.vmlist)) {
mm->context.vmlist = tmp->next;
- put_vma(tmp->vma);
+ put_vma(mm, tmp->vma);
realalloc -= kobjsize(tmp);
askedalloc -= sizeof(*tmp);
}
EXPORT_SYMBOL(remap_pfn_range);
+int remap_vmalloc_range(struct vm_area_struct *vma, void *addr,
+ unsigned long pgoff)
+{
+ unsigned int size = vma->vm_end - vma->vm_start;
+
+ if (!(vma->vm_flags & VM_USERMAP))
+ return -EINVAL;
+
+ vma->vm_start = (unsigned long)(addr + (pgoff << PAGE_SHIFT));
+ vma->vm_end = vma->vm_start + size;
+
+ return 0;
+}
+EXPORT_SYMBOL(remap_vmalloc_range);
+
void swap_unplug_io_fn(struct backing_dev_info *bdi, struct page *page)
{
}
/* Don't let a single process grow too big:
leave 3% of the size of this process for other processes */
- allowed -= current->mm->total_vm / 32;
+ if (mm)
+ allowed -= mm->total_vm / 32;
/*
* cast `allowed' as a signed long because vm_committed_space
* sometimes has a negative value
*/
- if (atomic_read(&vm_committed_space) < (long)allowed)
+ if (atomic_long_read(&vm_committed_space) < (long)allowed)
return 0;
error:
vm_unacct_memory(pages);
git://ftp.safe.ca / safe / jmp / linux-2.6 / blobdiff