1 files changed, 104 insertions, 300 deletions

diff --git a/mm/filemap.c b/mm/filemap.c
index c6ebd9f912ab..49a6fe375d01 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -120,6 +120,7 @@ void __remove_from_page_cache(struct page *page)
 	page->mapping = NULL;
 	mapping->nrpages--;
 	__dec_zone_page_state(page, NR_FILE_PAGES);
+	BUG_ON(page_mapped(page));
 }
 
 void remove_from_page_cache(struct page *page)
@@ -866,13 +867,11 @@ void do_generic_mapping_read(struct address_space *mapping,
 {
 	struct inode *inode = mapping->host;
 	unsigned long index;
-	unsigned long end_index;
 	unsigned long offset;
 	unsigned long last_index;
 	unsigned long next_index;
 	unsigned long prev_index;
 	unsigned int prev_offset;
-	loff_t isize;
 	struct page *cached_page;
 	int error;
 	struct file_ra_state ra = *_ra;
@@ -885,42 +884,58 @@ void do_generic_mapping_read(struct address_space *mapping,
 	last_index = (*ppos + desc->count + PAGE_CACHE_SIZE-1) >> PAGE_CACHE_SHIFT;
 	offset = *ppos & ~PAGE_CACHE_MASK;
 
-	isize = i_size_read(inode);
-	if (!isize)
-		goto out;
-
-	end_index = (isize - 1) >> PAGE_CACHE_SHIFT;
 	for (;;) {
 		struct page *page;
+		unsigned long end_index;
+		loff_t isize;
 		unsigned long nr, ret;
 
+		cond_resched();
+find_page:
+		page = find_get_page(mapping, index);
+		if (!page) {
+			page_cache_sync_readahead(mapping,
+					&ra, filp,
+					index, last_index - index);
+			page = find_get_page(mapping, index);
+			if (unlikely(page == NULL))
+				goto no_cached_page;
+		}
+		if (PageReadahead(page)) {
+			page_cache_async_readahead(mapping,
+					&ra, filp, page,
+					index, last_index - index);
+		}
+		if (!PageUptodate(page))
+			goto page_not_up_to_date;
+page_ok:
+		/*
+		 * i_size must be checked after we know the page is Uptodate.
+		 *
+		 * Checking i_size after the check allows us to calculate
+		 * the correct value for "nr", which means the zero-filled
+		 * part of the page is not copied back to userspace (unless
+		 * another truncate extends the file - this is desired though).
+		 */
+
+		isize = i_size_read(inode);
+		end_index = (isize - 1) >> PAGE_CACHE_SHIFT;
+		if (unlikely(!isize || index > end_index)) {
+			page_cache_release(page);
+			goto out;
+		}
+
 		/* nr is the maximum number of bytes to copy from this page */
 		nr = PAGE_CACHE_SIZE;
-		if (index >= end_index) {
-			if (index > end_index)
-				goto out;
+		if (index == end_index) {
 			nr = ((isize - 1) & ~PAGE_CACHE_MASK) + 1;
 			if (nr <= offset) {
+				page_cache_release(page);
 				goto out;
 			}
 		}
 		nr = nr - offset;
 
-		cond_resched();
-		if (index == next_index)
-			next_index = page_cache_readahead(mapping, &ra, filp,
-					index, last_index - index);
-
-find_page:
-		page = find_get_page(mapping, index);
-		if (unlikely(page == NULL)) {
-			handle_ra_miss(mapping, &ra, index);
-			goto no_cached_page;
-		}
-		if (!PageUptodate(page))
-			goto page_not_up_to_date;
-page_ok:
-
 		/* If users can be writing to this page using arbitrary
 		 * virtual addresses, take care about potential aliasing
 		 * before reading the page on the kernel side.
@@ -1006,31 +1021,6 @@ readpage:
 			unlock_page(page);
 		}
 
-		/*
-		 * i_size must be checked after we have done ->readpage.
-		 *
-		 * Checking i_size after the readpage allows us to calculate
-		 * the correct value for "nr", which means the zero-filled
-		 * part of the page is not copied back to userspace (unless
-		 * another truncate extends the file - this is desired though).
-		 */
-		isize = i_size_read(inode);
-		end_index = (isize - 1) >> PAGE_CACHE_SHIFT;
-		if (unlikely(!isize || index > end_index)) {
-			page_cache_release(page);
-			goto out;
-		}
-
-		/* nr is the maximum number of bytes to copy from this page */
-		nr = PAGE_CACHE_SIZE;
-		if (index == end_index) {
-			nr = ((isize - 1) & ~PAGE_CACHE_MASK) + 1;
-			if (nr <= offset) {
-				page_cache_release(page);
-				goto out;
-			}
-		}
-		nr = nr - offset;
 		goto page_ok;
 
 readpage_error:
@@ -1066,6 +1056,7 @@ no_cached_page:
 
 out:
 	*_ra = ra;
+	_ra->prev_index = prev_index;
 
 	*ppos = ((loff_t) index << PAGE_CACHE_SHIFT) + offset;
 	if (cached_page)
@@ -1218,6 +1209,8 @@ generic_file_aio_read(struct kiocb *iocb, const struct iovec *iov,
 				retval = retval ?: desc.error;
 				break;
 			}
+			if (desc.count > 0)
+				break;
 		}
 	}
 out:
@@ -1314,62 +1307,62 @@ static int fastcall page_cache_read(struct file * file, unsigned long offset)
 #define MMAP_LOTSAMISS  (100)
 
 /**
- * filemap_nopage - read in file data for page fault handling
- * @area:	the applicable vm_area
- * @address:	target address to read in
- * @type:	returned with VM_FAULT_{MINOR,MAJOR} if not %NULL
+ * filemap_fault - read in file data for page fault handling
+ * @vma:	vma in which the fault was taken
+ * @vmf:	struct vm_fault containing details of the fault
  *
- * filemap_nopage() is invoked via the vma operations vector for a
+ * filemap_fault() is invoked via the vma operations vector for a
  * mapped memory region to read in file data during a page fault.
  *
  * The goto's are kind of ugly, but this streamlines the normal case of having
  * it in the page cache, and handles the special cases reasonably without
  * having a lot of duplicated code.
  */
-struct page *filemap_nopage(struct vm_area_struct *area,
-				unsigned long address, int *type)
+int filemap_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
 {
 	int error;
-	struct file *file = area->vm_file;
+	struct file *file = vma->vm_file;
 	struct address_space *mapping = file->f_mapping;
 	struct file_ra_state *ra = &file->f_ra;
 	struct inode *inode = mapping->host;
 	struct page *page;
-	unsigned long size, pgoff;
-	int did_readaround = 0, majmin = VM_FAULT_MINOR;
-
-	pgoff = ((address-area->vm_start) >> PAGE_CACHE_SHIFT) + area->vm_pgoff;
+	unsigned long size;
+	int did_readaround = 0;
+	int ret = 0;
 
-retry_all:
 	size = (i_size_read(inode) + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT;
-	if (pgoff >= size)
+	if (vmf->pgoff >= size)
 		goto outside_data_content;
 
 	/* If we don't want any read-ahead, don't bother */
-	if (VM_RandomReadHint(area))
+	if (VM_RandomReadHint(vma))
 		goto no_cached_page;
 
 	/*
-	 * The readahead code wants to be told about each and every page
-	 * so it can build and shrink its windows appropriately
-	 *
-	 * For sequential accesses, we use the generic readahead logic.
-	 */
-	if (VM_SequentialReadHint(area))
-		page_cache_readahead(mapping, ra, file, pgoff, 1);
-
-	/*
 	 * Do we have something in the page cache already?
 	 */
 retry_find:
-	page = find_get_page(mapping, pgoff);
+	page = find_lock_page(mapping, vmf->pgoff);
+	/*
+	 * For sequential accesses, we use the generic readahead logic.
+	 */
+	if (VM_SequentialReadHint(vma)) {
+		if (!page) {
+			page_cache_sync_readahead(mapping, ra, file,
+							   vmf->pgoff, 1);
+			page = find_lock_page(mapping, vmf->pgoff);
+			if (!page)
+				goto no_cached_page;
+		}
+		if (PageReadahead(page)) {
+			page_cache_async_readahead(mapping, ra, file, page,
+							   vmf->pgoff, 1);
+		}
+	}
+
 	if (!page) {
 		unsigned long ra_pages;
 
-		if (VM_SequentialReadHint(area)) {
-			handle_ra_miss(mapping, ra, pgoff);
-			goto no_cached_page;
-		}
 		ra->mmap_miss++;
 
 		/*
@@ -1384,7 +1377,7 @@ retry_find:
 		 * check did_readaround, as this is an inner loop.
 		 */
 		if (!did_readaround) {
-			majmin = VM_FAULT_MAJOR;
+			ret = VM_FAULT_MAJOR;
 			count_vm_event(PGMAJFAULT);
 		}
 		did_readaround = 1;
@@ -1392,11 +1385,11 @@ retry_find:
 		if (ra_pages) {
 			pgoff_t start = 0;
 
-			if (pgoff > ra_pages / 2)
-				start = pgoff - ra_pages / 2;
+			if (vmf->pgoff > ra_pages / 2)
+				start = vmf->pgoff - ra_pages / 2;
 			do_page_cache_readahead(mapping, file, start, ra_pages);
 		}
-		page = find_get_page(mapping, pgoff);
+		page = find_lock_page(mapping, vmf->pgoff);
 		if (!page)
 			goto no_cached_page;
 	}
@@ -1405,35 +1398,42 @@ retry_find:
 		ra->mmap_hit++;
 
 	/*
-	 * Ok, found a page in the page cache, now we need to check
-	 * that it's up-to-date.
+	 * We have a locked page in the page cache, now we need to check
+	 * that it's up-to-date. If not, it is going to be due to an error.
 	 */
-	if (!PageUptodate(page))
+	if (unlikely(!PageUptodate(page)))
 		goto page_not_uptodate;
 
-success:
+	/* Must recheck i_size under page lock */
+	size = (i_size_read(inode) + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT;
+	if (unlikely(vmf->pgoff >= size)) {
+		unlock_page(page);
+		goto outside_data_content;
+	}
+
 	/*
 	 * Found the page and have a reference on it.
 	 */
 	mark_page_accessed(page);
-	if (type)
-		*type = majmin;
-	return page;
+	ra->prev_index = page->index;
+	vmf->page = page;
+	return ret | VM_FAULT_LOCKED;
 
 outside_data_content:
 	/*
 	 * An external ptracer can access pages that normally aren't
 	 * accessible..
 	 */
-	if (area->vm_mm == current->mm)
-		return NOPAGE_SIGBUS;
+	if (vma->vm_mm == current->mm)
+		return VM_FAULT_SIGBUS;
+
 	/* Fall through to the non-read-ahead case */
 no_cached_page:
 	/*
 	 * We're only likely to ever get here if MADV_RANDOM is in
 	 * effect.
 	 */
-	error = page_cache_read(file, pgoff);
+	error = page_cache_read(file, vmf->pgoff);
 
 	/*
 	 * The page we want has now been added to the page cache.
@@ -1449,12 +1449,13 @@ no_cached_page:
 	 * to schedule I/O.
 	 */
 	if (error == -ENOMEM)
-		return NOPAGE_OOM;
-	return NOPAGE_SIGBUS;
+		return VM_FAULT_OOM;
+	return VM_FAULT_SIGBUS;
 
 page_not_uptodate:
+	/* IO error path */
 	if (!did_readaround) {
-		majmin = VM_FAULT_MAJOR;
+		ret = VM_FAULT_MAJOR;
 		count_vm_event(PGMAJFAULT);
 	}
 
@@ -1464,217 +1465,21 @@ page_not_uptodate:
 	 * because there really aren't any performance issues here
 	 * and we need to check for errors.
 	 */
-	lock_page(page);
-
-	/* Somebody truncated the page on us? */
-	if (!page->mapping) {
-		unlock_page(page);
-		page_cache_release(page);
-		goto retry_all;
-	}
-
-	/* Somebody else successfully read it in? */
-	if (PageUptodate(page)) {
-		unlock_page(page);
-		goto success;
-	}
 	ClearPageError(page);
 	error = mapping->a_ops->readpage(file, page);
-	if (!error) {
-		wait_on_page_locked(page);
-		if (PageUptodate(page))
-			goto success;
-	} else if (error == AOP_TRUNCATED_PAGE) {
-		page_cache_release(page);
-		goto retry_find;
-	}
-
-	/*
-	 * Things didn't work out. Return zero to tell the
-	 * mm layer so, possibly freeing the page cache page first.
-	 */
-	shrink_readahead_size_eio(file, ra);
 	page_cache_release(page);
-	return NOPAGE_SIGBUS;
-}
-EXPORT_SYMBOL(filemap_nopage);
 
-static struct page * filemap_getpage(struct file *file, unsigned long pgoff,
-					int nonblock)
-{
-	struct address_space *mapping = file->f_mapping;
-	struct page *page;
-	int error;
-
-	/*
-	 * Do we have something in the page cache already?
-	 */
-retry_find:
-	page = find_get_page(mapping, pgoff);
-	if (!page) {
-		if (nonblock)
-			return NULL;
-		goto no_cached_page;
-	}
-
-	/*
-	 * Ok, found a page in the page cache, now we need to check
-	 * that it's up-to-date.
-	 */
-	if (!PageUptodate(page)) {
-		if (nonblock) {
-			page_cache_release(page);
-			return NULL;
-		}
-		goto page_not_uptodate;
-	}
-
-success:
-	/*
-	 * Found the page and have a reference on it.
-	 */
-	mark_page_accessed(page);
-	return page;
-
-no_cached_page:
-	error = page_cache_read(file, pgoff);
-
-	/*
-	 * The page we want has now been added to the page cache.
-	 * In the unlikely event that someone removed it in the
-	 * meantime, we'll just come back here and read it again.
-	 */
-	if (error >= 0)
+	if (!error || error == AOP_TRUNCATED_PAGE)
 		goto retry_find;
 
-	/*
-	 * An error return from page_cache_read can result if the
-	 * system is low on memory, or a problem occurs while trying
-	 * to schedule I/O.
-	 */
-	return NULL;
-
-page_not_uptodate:
-	lock_page(page);
-
-	/* Did it get truncated while we waited for it? */
-	if (!page->mapping) {
-		unlock_page(page);
-		goto err;
-	}
-
-	/* Did somebody else get it up-to-date? */
-	if (PageUptodate(page)) {
-		unlock_page(page);
-		goto success;
-	}
-
-	error = mapping->a_ops->readpage(file, page);
-	if (!error) {
-		wait_on_page_locked(page);
-		if (PageUptodate(page))
-			goto success;
-	} else if (error == AOP_TRUNCATED_PAGE) {
-		page_cache_release(page);
-		goto retry_find;
-	}
-
-	/*
-	 * Umm, take care of errors if the page isn't up-to-date.
-	 * Try to re-read it _once_. We do this synchronously,
-	 * because there really aren't any performance issues here
-	 * and we need to check for errors.
-	 */
-	lock_page(page);
-
-	/* Somebody truncated the page on us? */
-	if (!page->mapping) {
-		unlock_page(page);
-		goto err;
-	}
-	/* Somebody else successfully read it in? */
-	if (PageUptodate(page)) {
-		unlock_page(page);
-		goto success;
-	}
-
-	ClearPageError(page);
-	error = mapping->a_ops->readpage(file, page);
-	if (!error) {
-		wait_on_page_locked(page);
-		if (PageUptodate(page))
-			goto success;
-	} else if (error == AOP_TRUNCATED_PAGE) {
-		page_cache_release(page);
-		goto retry_find;
-	}
-
-	/*
-	 * Things didn't work out. Return zero to tell the
-	 * mm layer so, possibly freeing the page cache page first.
-	 */
-err:
-	page_cache_release(page);
-
-	return NULL;
-}
-
-int filemap_populate(struct vm_area_struct *vma, unsigned long addr,
-		unsigned long len, pgprot_t prot, unsigned long pgoff,
-		int nonblock)
-{
-	struct file *file = vma->vm_file;
-	struct address_space *mapping = file->f_mapping;
-	struct inode *inode = mapping->host;
-	unsigned long size;
-	struct mm_struct *mm = vma->vm_mm;
-	struct page *page;
-	int err;
-
-	if (!nonblock)
-		force_page_cache_readahead(mapping, vma->vm_file,
-					pgoff, len >> PAGE_CACHE_SHIFT);
-
-repeat:
-	size = (i_size_read(inode) + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT;
-	if (pgoff + (len >> PAGE_CACHE_SHIFT) > size)
-		return -EINVAL;
-
-	page = filemap_getpage(file, pgoff, nonblock);
-
-	/* XXX: This is wrong, a filesystem I/O error may have happened. Fix that as
-	 * done in shmem_populate calling shmem_getpage */
-	if (!page && !nonblock)
-		return -ENOMEM;
-
-	if (page) {
-		err = install_page(mm, vma, addr, page, prot);
-		if (err) {
-			page_cache_release(page);
-			return err;
-		}
-	} else if (vma->vm_flags & VM_NONLINEAR) {
-		/* No page was found just because we can't read it in now (being
-		 * here implies nonblock != 0), but the page may exist, so set
-		 * the PTE to fault it in later. */
-		err = install_file_pte(mm, vma, addr, pgoff, prot);
-		if (err)
-			return err;
-	}
-
-	len -= PAGE_SIZE;
-	addr += PAGE_SIZE;
-	pgoff++;
-	if (len)
-		goto repeat;
-
-	return 0;
+	/* Things didn't work out. Return zero to tell the mm layer so. */
+	shrink_readahead_size_eio(file, ra);
+	return VM_FAULT_SIGBUS;
 }
-EXPORT_SYMBOL(filemap_populate);
+EXPORT_SYMBOL(filemap_fault);
 
 struct vm_operations_struct generic_file_vm_ops = {
-	.nopage		= filemap_nopage,
-	.populate	= filemap_populate,
+	.fault		= filemap_fault,
 };
 
 /* This is used for a general mmap of a disk file */
@@ -1687,6 +1492,7 @@ int generic_file_mmap(struct file * file, struct vm_area_struct * vma)
 		return -ENOEXEC;
 	file_accessed(file);
 	vma->vm_ops = &generic_file_vm_ops;
+	vma->vm_flags |= VM_CAN_NONLINEAR;
 	return 0;
 }
 
@@ -1964,7 +1770,6 @@ inline int generic_write_checks(struct file *file, loff_t *pos, size_t *count, i
 	if (unlikely(*pos + *count > MAX_NON_LFS &&
 				!(file->f_flags & O_LARGEFILE))) {
 		if (*pos >= MAX_NON_LFS) {
-			send_sig(SIGXFSZ, current, 0);
 			return -EFBIG;
 		}
 		if (*count > MAX_NON_LFS - (unsigned long)*pos) {
@@ -1982,7 +1787,6 @@ inline int generic_write_checks(struct file *file, loff_t *pos, size_t *count, i
 	if (likely(!isblk)) {
 		if (unlikely(*pos >= inode->i_sb->s_maxbytes)) {
 			if (*count || *pos > inode->i_sb->s_maxbytes) {
-				send_sig(SIGXFSZ, current, 0);
 				return -EFBIG;
 			}
 			/* zero-length writes at ->s_maxbytes are OK */