[PATCH] mm: fix xip issue with /dev/zero

Fix the bug, that reading into xip mapping from /dev/zero fills the user
page table with ZERO_PAGE() entries.  Later on, xip cannot tell which pages
have been ZERO_PAGE() filled by access to a sparse mapping, and which ones
origin from /dev/zero.  It will unmap ZERO_PAGE from all mappings when
filling the sparse hole with data.  xip does now use its own zeroed page
for its sparse mappings.  Please apply.

Signed-off-by: Carsten Otte <cotte@de.ibm.com>
Signed-off-by: Hugh Dickins <hugh@veritas.com>
Cc: Nick Piggin <nickpiggin@yahoo.com.au>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
This commit is contained in:
Carsten Otte 2007-03-29 01:20:39 -07:00 committed by Linus Torvalds
parent 90ed52ebe4
commit a76c0b9763
1 changed files with 37 additions and 11 deletions

View File

@ -16,6 +16,29 @@
#include <asm/tlbflush.h>
#include "filemap.h"
/*
* We do use our own empty page to avoid interference with other users
* of ZERO_PAGE(), such as /dev/zero
*/
static struct page *__xip_sparse_page;
static struct page *xip_sparse_page(void)
{
if (!__xip_sparse_page) {
unsigned long zeroes = get_zeroed_page(GFP_HIGHUSER);
if (zeroes) {
static DEFINE_SPINLOCK(xip_alloc_lock);
spin_lock(&xip_alloc_lock);
if (!__xip_sparse_page)
__xip_sparse_page = virt_to_page(zeroes);
else
free_page(zeroes);
spin_unlock(&xip_alloc_lock);
}
}
return __xip_sparse_page;
}
/*
* This is a file read routine for execute in place files, and uses
* the mapping->a_ops->get_xip_page() function for the actual low-level
@ -162,7 +185,7 @@ EXPORT_SYMBOL_GPL(xip_file_sendfile);
* xip_write
*
* This function walks all vmas of the address_space and unmaps the
* ZERO_PAGE when found at pgoff. Should it go in rmap.c?
* __xip_sparse_page when found at pgoff.
*/
static void
__xip_unmap (struct address_space * mapping,
@ -177,13 +200,16 @@ __xip_unmap (struct address_space * mapping,
spinlock_t *ptl;
struct page *page;
page = __xip_sparse_page;
if (!page)
return;
spin_lock(&mapping->i_mmap_lock);
vma_prio_tree_foreach(vma, &iter, &mapping->i_mmap, pgoff, pgoff) {
mm = vma->vm_mm;
address = vma->vm_start +
((pgoff - vma->vm_pgoff) << PAGE_SHIFT);
BUG_ON(address < vma->vm_start || address >= vma->vm_end);
page = ZERO_PAGE(0);
pte = page_check_address(page, mm, address, &ptl);
if (pte) {
/* Nuke the page table entry. */
@ -222,16 +248,14 @@ xip_file_nopage(struct vm_area_struct * area,
+ area->vm_pgoff;
size = (i_size_read(inode) + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT;
if (pgoff >= size) {
return NULL;
}
if (pgoff >= size)
return NOPAGE_SIGBUS;
page = mapping->a_ops->get_xip_page(mapping, pgoff*(PAGE_SIZE/512), 0);
if (!IS_ERR(page)) {
if (!IS_ERR(page))
goto out;
}
if (PTR_ERR(page) != -ENODATA)
return NULL;
return NOPAGE_SIGBUS;
/* sparse block */
if ((area->vm_flags & (VM_WRITE | VM_MAYWRITE)) &&
@ -241,12 +265,14 @@ xip_file_nopage(struct vm_area_struct * area,
page = mapping->a_ops->get_xip_page (mapping,
pgoff*(PAGE_SIZE/512), 1);
if (IS_ERR(page))
return NULL;
return NOPAGE_SIGBUS;
/* unmap page at pgoff from all other vmas */
__xip_unmap(mapping, pgoff);
} else {
/* not shared and writable, use ZERO_PAGE() */
page = ZERO_PAGE(0);
/* not shared and writable, use xip_sparse_page() */
page = xip_sparse_page();
if (!page)
return NOPAGE_OOM;
}
out: