buffered write deadlock fix

Index: linux-2.6/fs/libfs.c
===================================================================
@@ -327,32 +327,35 @@ int simple_readpage(struct file *file, s
 int simple_prepare_write(struct file *file, struct page *page,
 			unsigned from, unsigned to)
 {
-	if (!PageUptodate(page)) {
-		if (to - from != PAGE_CACHE_SIZE) {
-			void *kaddr = kmap_atomic(page, KM_USER0);
-			memset(kaddr, 0, from);
-			memset(kaddr + to, 0, PAGE_CACHE_SIZE - to);
-			flush_dcache_page(page);
-			kunmap_atomic(kaddr, KM_USER0);
-		}
+	if (PageUptodate(page))
+		return 0;
+
+	if (to - from != PAGE_CACHE_SIZE) {
+		clear_highpage(page);
+		flush_dcache_page(page);
 		SetPageUptodate(page);
 	}
+
 	return 0;
 }
 
 int simple_commit_write(struct file *file, struct page *page,
-			unsigned offset, unsigned to)
+			unsigned from, unsigned to)
 {
-	struct inode *inode = page->mapping->host;
-	loff_t pos = ((loff_t)page->index << PAGE_CACHE_SHIFT) + to;
-
-	/*
-	 * No need to use i_size_read() here, the i_size
-	 * cannot change under us because we hold the i_mutex.
-	 */
-	if (pos > inode->i_size)
-		i_size_write(inode, pos);
-	set_page_dirty(page);
+	if (to > from) {
+		struct inode *inode = page->mapping->host;
+		loff_t pos = ((loff_t)page->index << PAGE_CACHE_SHIFT) + to;
+
+		if (to - from == PAGE_CACHE_SIZE)
+			SetPageUptodate(page);
+		/*
+		 * No need to use i_size_read() here, the i_size
+		 * cannot change under us because we hold the i_mutex.
+		 */
+		if (pos > inode->i_size)
+			i_size_write(inode, pos);
+		set_page_dirty(page);
+	}
 	return 0;
 }
 

Index: linux-2.6/fs/buffer.c
===================================================================
@@ -2344,6 +2344,8 @@ int nobh_prepare_write(struct page *page
 
 	if (is_mapped_to_disk)
 		SetPageMappedToDisk(page);
+
+	/* XXX: information leak vs read(2) */
 	SetPageUptodate(page);
 
 	/*

Index: linux-2.6/fs/libfs.c
===================================================================
@@ -327,25 +327,32 @@ int simple_readpage(struct file *file, s
 int simple_prepare_write(struct file *file, struct page *page,
 			unsigned from, unsigned to)
 {
-	if (!PageUptodate(page)) {
-		if (to - from != PAGE_CACHE_SIZE) {
-			void *kaddr = kmap_atomic(page, KM_USER0);
-			memset(kaddr, 0, from);
-			memset(kaddr + to, 0, PAGE_CACHE_SIZE - to);
-			flush_dcache_page(page);
-			kunmap_atomic(kaddr, KM_USER0);
-		}
+	if (PageUptodate(page))
+		return 0;
+
+	if (to - from != PAGE_CACHE_SIZE) {
+		/*
+		 * Partial-page write? Initialise the complete page and
+		 * set it uptodate. We could avoid initialising the
+		 * (from, to) hole, and opt to mark it uptodate in
+		 * simple_commit_write, but that's probably only a win
+		 * for filesystems that would need to read blocks off disk.
+		 */
+		memclear_highpage_flush(page, 0, PAGE_CACHE_SIZE);
 		SetPageUptodate(page);
 	}
+
 	return 0;
 }
 
 int simple_commit_write(struct file *file, struct page *page,
-			unsigned offset, unsigned to)
+			unsigned from, unsigned to)
 {
 	struct inode *inode = page->mapping->host;
 	loff_t pos = ((loff_t)page->index << PAGE_CACHE_SHIFT) + to;
 
+	if (to - from == PAGE_CACHE_SIZE)
+		SetPageUptodate(page);
 	/*
 	 * No need to use i_size_read() here, the i_size
 	 * cannot change under us because we hold the i_mutex.

@@ -353,6 +360,7 @@ int simple_commit_write(struct file *fil
 	if (pos > inode->i_size)
 		i_size_write(inode, pos);
 	set_page_dirty(page);
+
 	return 0;
 }
 

Index: linux-2.6/fs/buffer.c
===================================================================
@@ -2344,17 +2344,6 @@ int nobh_prepare_write(struct page *page
 
 	if (is_mapped_to_disk)
 		SetPageMappedToDisk(page);
-	SetPageUptodate(page);
-
-	/*
-	 * Setting the page dirty here isn't necessary for the prepare_write
-	 * function - commit_write will do that.  But if/when this function is
-	 * used within the pagefault handler to ensure that all mmapped pages
-	 * have backing space in the filesystem, we will need to dirty the page
-	 * if its contents were altered.
-	 */
-	if (dirtied_it)
-		set_page_dirty(page);
 
 	return 0;
 

@@ -2384,6 +2373,7 @@ int nobh_commit_write(struct file *file,
 	struct inode *inode = page->mapping->host;
 	loff_t pos = ((loff_t)page->index << PAGE_CACHE_SHIFT) + to;
 
+	SetPageUptodate(page);
 	set_page_dirty(page);
 	if (pos > inode->i_size) {
 		i_size_write(inode, pos);

Index: linux-2.6/mm/filemap.c
===================================================================
@@ -1911,12 +1911,6 @@ generic_file_buffered_write(struct kiocb
 			break;
 		}
 
-		if (unlikely(bytes == 0)) {
-			status = 0;
-			copied = 0;
-			goto zero_length_segment;
-		}
-
 		status = a_ops->prepare_write(file, page, offset, offset+bytes);
 		if (unlikely(status)) {
 			loff_t isize = i_size_read(inode);

@@ -1946,8 +1940,7 @@ generic_file_buffered_write(struct kiocb
 			page_cache_release(page);
 			continue;
 		}
-zero_length_segment:
-		if (likely(copied >= 0)) {
+		if (likely(copied > 0)) {
 			if (!status)
 				status = copied;
 

Index: linux-2.6/mm/filemap.h
===================================================================
@@ -87,7 +87,7 @@ filemap_set_next_iovec(const struct iove
 	const struct iovec *iov = *iovp;
 	size_t base = *basep;
 
-	do {
+	while (bytes) {
 		int copy = min(bytes, iov->iov_len - base);
 
 		bytes -= copy;

@@ -96,7 +96,7 @@ filemap_set_next_iovec(const struct iove
 			iov++;
 			base = 0;
 		}
-	} while (bytes);
+	}
 	*iovp = iov;
 	*basep = base;
 }

Index: linux-2.6/mm/filemap.c
===================================================================
@@ -1881,21 +1881,14 @@ generic_file_buffered_write(struct kiocb
 	do {
 		unsigned long index;
 		unsigned long offset;
+		unsigned long maxlen;
 		size_t copied;
 
 		offset = (pos & (PAGE_CACHE_SIZE -1)); /* Within page */
 		index = pos >> PAGE_CACHE_SHIFT;
 		bytes = PAGE_CACHE_SIZE - offset;
-
-		/* Limit the size of the copy to the caller's write size */
-		bytes = min(bytes, count);
-
-		/*
-		 * Limit the size of the copy to that of the current segment,
-		 * because fault_in_pages_readable() doesn't know how to walk
-		 * segments.
-		 */
-		bytes = min(bytes, cur_iov->iov_len - iov_base);
+		if (bytes > count)
+			bytes = count;
 
 		/*
 		 * Bring in the user page that we will copy from _first_.

@@ -1903,7 +1896,10 @@ generic_file_buffered_write(struct kiocb
 		 * same page as we're writing to, without it being marked
 		 * up-to-date.
 		 */
-		fault_in_pages_readable(buf, bytes);
+		maxlen = cur_iov->iov_len - iov_base;
+		if (maxlen > bytes)
+			maxlen = bytes;
+		fault_in_pages_readable(buf, maxlen);
 
 		page = __grab_cache_page(mapping,index,&cached_page,&lru_pvec);
 		if (!page) {

Index: linux-2.6/mm/filemap.c
===================================================================
@@ -1854,16 +1854,15 @@ generic_file_buffered_write(struct kiocb
 		size_t count, ssize_t written)
 {
 	struct file *file = iocb->ki_filp;
-	struct address_space * mapping = file->f_mapping;
+	struct address_space *mapping = file->f_mapping;
 	const struct address_space_operations *a_ops = mapping->a_ops;
 	struct inode 	*inode = mapping->host;
 	long		status = 0;
 	struct page	*page;
 	struct page	*cached_page = NULL;
-	size_t		bytes;
 	struct pagevec	lru_pvec;
 	const struct iovec *cur_iov = iov; /* current iovec */
-	size_t		iov_base = 0;	   /* offset in the current iovec */
+	size_t		iov_offset = 0;	   /* offset in the current iovec */
 	char __user	*buf;
 
 	pagevec_init(&lru_pvec, 0);

@@ -1874,31 +1873,33 @@ generic_file_buffered_write(struct kiocb
 	if (likely(nr_segs == 1))
 		buf = iov->iov_base + written;
 	else {
-		filemap_set_next_iovec(&cur_iov, &iov_base, written);
-		buf = cur_iov->iov_base + iov_base;
+		filemap_set_next_iovec(&cur_iov, &iov_offset, written);
+		buf = cur_iov->iov_base + iov_offset;
 	}
 
 	do {
-		unsigned long index;
-		unsigned long offset;
-		unsigned long maxlen;
-		size_t copied;
+		pgoff_t index;		/* Pagecache index for current page */
+		unsigned long offset;	/* Offset into pagecache page */
+		unsigned long maxlen;	/* Bytes remaining in current iovec */
+		size_t bytes;		/* Bytes to write to page */
+		size_t copied;		/* Bytes copied from user */
 
-		offset = (pos & (PAGE_CACHE_SIZE -1)); /* Within page */
+		offset = (pos & (PAGE_CACHE_SIZE - 1));
 		index = pos >> PAGE_CACHE_SHIFT;
 		bytes = PAGE_CACHE_SIZE - offset;
 		if (bytes > count)
 			bytes = count;
 
+		maxlen = cur_iov->iov_len - iov_offset;
+		if (maxlen > bytes)
+			maxlen = bytes;
+
 		/*
 		 * Bring in the user page that we will copy from _first_.
 		 * Otherwise there's a nasty deadlock on copying from the
 		 * same page as we're writing to, without it being marked
 		 * up-to-date.
 		 */
-		maxlen = cur_iov->iov_len - iov_base;
-		if (maxlen > bytes)
-			maxlen = bytes;
 		fault_in_pages_readable(buf, maxlen);
 
 		page = __grab_cache_page(mapping,index,&cached_page,&lru_pvec);

@@ -1929,7 +1930,7 @@ generic_file_buffered_write(struct kiocb
 							buf, bytes);
 		else
 			copied = filemap_copy_from_user_iovec(page, offset,
-						cur_iov, iov_base, bytes);
+						cur_iov, iov_offset, bytes);
 		flush_dcache_page(page);
 		status = a_ops->commit_write(file, page, offset, offset+bytes);
 		if (status == AOP_TRUNCATED_PAGE) {

@@ -1947,12 +1948,12 @@ generic_file_buffered_write(struct kiocb
 				buf += status;
 				if (unlikely(nr_segs > 1)) {
 					filemap_set_next_iovec(&cur_iov,
-							&iov_base, status);
+							&iov_offset, status);
 					if (count)
 						buf = cur_iov->iov_base +
-							iov_base;
+							iov_offset;
 				} else {
-					iov_base += status;
+					iov_offset += status;
 				}
 			}
 		}

Index: linux-2.6/mm/filemap.c
===================================================================
@@ -1894,6 +1894,7 @@ generic_file_buffered_write(struct kiocb
 		if (maxlen > bytes)
 			maxlen = bytes;
 
+#ifndef CONFIG_DEBUG_VM
 		/*
 		 * Bring in the user page that we will copy from _first_.
 		 * Otherwise there's a nasty deadlock on copying from the

@@ -1901,6 +1902,7 @@ generic_file_buffered_write(struct kiocb
 		 * up-to-date.
 		 */
 		fault_in_pages_readable(buf, maxlen);
+#endif
 
 		page = __grab_cache_page(mapping,index,&cached_page,&lru_pvec);
 		if (!page) {

Index: linux-2.6/mm/filemap.c
===================================================================
@@ -1911,22 +1911,9 @@ generic_file_buffered_write(struct kiocb
 		}
 
 		status = a_ops->prepare_write(file, page, offset, offset+bytes);
-		if (unlikely(status)) {
-			loff_t isize = i_size_read(inode);
+		if (unlikely(status))
+			goto fs_write_aop_error;
 
-			if (status != AOP_TRUNCATED_PAGE)
-				unlock_page(page);
-			page_cache_release(page);
-			if (status == AOP_TRUNCATED_PAGE)
-				continue;
-			/*
-			 * prepare_write() may have instantiated a few blocks
-			 * outside i_size.  Trim these off again.
-			 */
-			if (pos + bytes > isize)
-				vmtruncate(inode, isize);
-			break;
-		}
 		if (likely(nr_segs == 1))
 			copied = filemap_copy_from_user(page, offset,
 							buf, bytes);

@@ -1935,40 +1922,53 @@ generic_file_buffered_write(struct kiocb
 						cur_iov, iov_offset, bytes);
 		flush_dcache_page(page);
 		status = a_ops->commit_write(file, page, offset, offset+bytes);
-		if (status == AOP_TRUNCATED_PAGE) {
-			page_cache_release(page);
-			continue;
+		if (unlikely(status < 0))
+			goto fs_write_aop_error;
+		if (unlikely(copied != bytes)) {
+			status = -EFAULT;
+			goto fs_write_aop_error;
 		}
-		if (likely(copied > 0)) {
-			if (!status)
-				status = copied;
+		if (unlikely(status > 0)) /* filesystem did partial write */
+			copied = status;
 
-			if (status >= 0) {
-				written += status;
-				count -= status;
-				pos += status;
-				buf += status;
-				if (unlikely(nr_segs > 1)) {
-					filemap_set_next_iovec(&cur_iov,
-							&iov_offset, status);
-					if (count)
-						buf = cur_iov->iov_base +
-							iov_offset;
-				} else {
-					iov_offset += status;
-				}
+		if (likely(copied > 0)) {
+			written += copied;
+			count -= copied;
+			pos += copied;
+			buf += copied;
+			if (unlikely(nr_segs > 1)) {
+				filemap_set_next_iovec(&cur_iov,
+						&iov_offset, copied);
+				if (count)
+					buf = cur_iov->iov_base + iov_offset;
+			} else {
+				iov_offset += copied;
 			}
 		}
-		if (unlikely(copied != bytes))
-			if (status >= 0)
-				status = -EFAULT;
 		unlock_page(page);
 		mark_page_accessed(page);
 		page_cache_release(page);
-		if (status < 0)
-			break;
 		balance_dirty_pages_ratelimited(mapping);
 		cond_resched();
+		continue;
+
+fs_write_aop_error:
+		if (status != AOP_TRUNCATED_PAGE)
+			unlock_page(page);
+		page_cache_release(page);
+
+		/*
+		 * prepare_write() may have instantiated a few blocks
+		 * outside i_size.  Trim these off again. Don't need
+		 * i_size_read because we hold i_mutex.
+		 */
+		if (pos + bytes > inode->i_size)
+			vmtruncate(inode, inode->i_size);
+		if (status == AOP_TRUNCATED_PAGE)
+			continue;
+		else
+			break;
+
 	} while (count);
 	*ppos = pos;
 

Index: linux-2.6/mm/filemap.c
===================================================================
@@ -686,26 +686,22 @@ EXPORT_SYMBOL(find_lock_page);
 struct page *find_or_create_page(struct address_space *mapping,
 		unsigned long index, gfp_t gfp_mask)
 {
-	struct page *page, *cached_page = NULL;
+	struct page *page;
 	int err;
 repeat:
 	page = find_lock_page(mapping, index);
 	if (!page) {
-		if (!cached_page) {
-			cached_page = alloc_page(gfp_mask);
-			if (!cached_page)
-				return NULL;
-		}
-		err = add_to_page_cache_lru(cached_page, mapping,
-					index, gfp_mask);
-		if (!err) {
-			page = cached_page;
-			cached_page = NULL;
-		} else if (err == -EEXIST)
-			goto repeat;
+		page = alloc_page(gfp_mask);
+		if (!page)
+			return NULL;
+		err = add_to_page_cache_lru(page, mapping, index, gfp_mask);
+		if (unlikely(err)) {
+			page_cache_release(page);
+			page = NULL;
+			if (err == -EEXIST)
+				goto repeat;
+		}
 	}
-	if (cached_page)
-		page_cache_release(cached_page);
 	return page;
 }
 EXPORT_SYMBOL(find_or_create_page);

@@ -891,11 +887,9 @@ void do_generic_mapping_read(struct addr
 	unsigned long next_index;
 	unsigned long prev_index;
 	loff_t isize;
-	struct page *cached_page;
 	int error;
 	struct file_ra_state ra = *_ra;
 
-	cached_page = NULL;
 	index = *ppos >> PAGE_CACHE_SHIFT;
 	next_index = index;
 	prev_index = ra.prev_page;

@@ -1059,23 +1053,20 @@ no_cached_page:
 		 * Ok, it wasn't cached, so we need to create a new
 		 * page..
 		 */
-		if (!cached_page) {
-			cached_page = page_cache_alloc_cold(mapping);
-			if (!cached_page) {
-				desc->error = -ENOMEM;
-				goto out;
-			}
+		page = page_cache_alloc_cold(mapping);
+		if (!page) {
+			desc->error = -ENOMEM;
+			goto out;
 		}
-		error = add_to_page_cache_lru(cached_page, mapping,
+		error = add_to_page_cache_lru(page, mapping,
 						index, GFP_KERNEL);
 		if (error) {
+			page_cache_release(page);
 			if (error == -EEXIST)
 				goto find_page;
 			desc->error = error;
 			goto out;
 		}
-		page = cached_page;
-		cached_page = NULL;
 		goto readpage;
 	}
 

@@ -1083,8 +1074,6 @@ out:
 	*_ra = ra;
 
 	*ppos = ((loff_t) index << PAGE_CACHE_SHIFT) + offset;
-	if (cached_page)
-		page_cache_release(cached_page);
 	if (filp)
 		file_accessed(filp);
 }

@@ -1542,35 +1531,28 @@ static inline struct page *__read_cache_
 				int (*filler)(void *,struct page*),
 				void *data)
 {
-	struct page *page, *cached_page = NULL;
+	struct page *page;
 	int err;
 repeat:
 	page = find_get_page(mapping, index);
 	if (!page) {
-		if (!cached_page) {
-			cached_page = page_cache_alloc_cold(mapping);
-			if (!cached_page)
-				return ERR_PTR(-ENOMEM);
-		}
-		err = add_to_page_cache_lru(cached_page, mapping,
-					index, GFP_KERNEL);
-		if (err == -EEXIST)
-			goto repeat;
-		if (err < 0) {
+		page = page_cache_alloc_cold(mapping);
+		if (!page)
+			return ERR_PTR(-ENOMEM);
+		err = add_to_page_cache_lru(page, mapping, index, GFP_KERNEL);
+		if (unlikely(err)) {
+			page_cache_release(page);
+			if (err == -EEXIST)
+				goto repeat;
 			/* Presumably ENOMEM for radix tree node */
-			page_cache_release(cached_page);
 			return ERR_PTR(err);
 		}
-		page = cached_page;
-		cached_page = NULL;
 		err = filler(data, page);
 		if (err < 0) {
 			page_cache_release(page);
 			page = ERR_PTR(err);
 		}
 	}
-	if (cached_page)
-		page_cache_release(cached_page);
 	return page;
 }
 

@@ -1621,40 +1603,6 @@ retry:
 EXPORT_SYMBOL(read_cache_page);
 
 /*
- * If the page was newly created, increment its refcount and add it to the
- * caller's lru-buffering pagevec.  This function is specifically for
- * generic_file_write().
- */
-static inline struct page *
-__grab_cache_page(struct address_space *mapping, unsigned long index,
-			struct page **cached_page, struct pagevec *lru_pvec)
-{
-	int err;
-	struct page *page;
-repeat:
-	page = find_lock_page(mapping, index);
-	if (!page) {
-		if (!*cached_page) {
-			*cached_page = page_cache_alloc(mapping);
-			if (!*cached_page)
-				return NULL;
-		}
-		err = add_to_page_cache(*cached_page, mapping,
-					index, GFP_KERNEL);
-		if (err == -EEXIST)
-			goto repeat;
-		if (err == 0) {
-			page = *cached_page;
-			page_cache_get(page);
-			if (!pagevec_add(lru_pvec, page))
-				__pagevec_lru_add(lru_pvec);
-			*cached_page = NULL;
-		}
-	}
-	return page;
-}
-
-/*
  * The logic we want is
  *
  *	if suid or (sgid and xgrp)

@@ -1848,6 +1796,33 @@ generic_file_direct_write(struct kiocb *
 }
 EXPORT_SYMBOL(generic_file_direct_write);
 
+/*
+ * Find or create a page at the given pagecache position. Return the locked
+ * page. This function is specifically for buffered writes.
+ */
+static struct page *__grab_cache_page(struct address_space *mapping,
+							pgoff_t index)
+{
+	int status;
+	struct page *page;
+repeat:
+	page = find_lock_page(mapping, index);
+	if (likely(page))
+		return page;
+
+	page = page_cache_alloc(mapping);
+	if (!page)
+		return NULL;
+	status = add_to_page_cache_lru(page, mapping, index, GFP_KERNEL);
+	if (unlikely(status)) {
+		page_cache_release(page);
+		if (status == -EEXIST)
+			goto repeat;
+		return NULL;
+	}
+	return page;
+}
+
 ssize_t
 generic_file_buffered_write(struct kiocb *iocb, const struct iovec *iov,
 		unsigned long nr_segs, loff_t pos, loff_t *ppos,

@@ -1858,15 +1833,10 @@ generic_file_buffered_write(struct kiocb
 	const struct address_space_operations *a_ops = mapping->a_ops;
 	struct inode 	*inode = mapping->host;
 	long		status = 0;
-	struct page	*page;
-	struct page	*cached_page = NULL;
-	struct pagevec	lru_pvec;
 	const struct iovec *cur_iov = iov; /* current iovec */
 	size_t		iov_offset = 0;	   /* offset in the current iovec */
 	char __user	*buf;
 
-	pagevec_init(&lru_pvec, 0);
-
 	/*
 	 * handle partial DIO write.  Adjust cur_iov if needed.
 	 */

@@ -1878,6 +1848,7 @@ generic_file_buffered_write(struct kiocb
 	}
 
 	do {
+		struct page *page;
 		pgoff_t index;		/* Pagecache index for current page */
 		unsigned long offset;	/* Offset into pagecache page */
 		unsigned long maxlen;	/* Bytes remaining in current iovec */

@@ -1904,7 +1875,8 @@ generic_file_buffered_write(struct kiocb
 		fault_in_pages_readable(buf, maxlen);
 #endif
 
-		page = __grab_cache_page(mapping,index,&cached_page,&lru_pvec);
+
+		page = __grab_cache_page(mapping, index);
 		if (!page) {
 			status = -ENOMEM;
 			break;

@@ -1972,9 +1944,6 @@ fs_write_aop_error:
 	} while (count);
 	*ppos = pos;
 
-	if (cached_page)
-		page_cache_release(cached_page);
-
 	/*
 	 * For now, when the user asks for O_SYNC, we'll actually give O_DSYNC
 	 */

@@ -1994,7 +1963,6 @@ fs_write_aop_error:
 	if (unlikely(file->f_flags & O_DIRECT) && written)
 		status = filemap_write_and_wait(mapping);
 
-	pagevec_lru_add(&lru_pvec);
 	return written ? written : status;
 }
 EXPORT_SYMBOL(generic_file_buffered_write);

Index: linux-2.6/fs/mpage.c
===================================================================
@@ -389,31 +389,25 @@ mpage_readpages(struct address_space *ma
 	struct bio *bio = NULL;
 	unsigned page_idx;
 	sector_t last_block_in_bio = 0;
-	struct pagevec lru_pvec;
 	struct buffer_head map_bh;
 	unsigned long first_logical_block = 0;
 
 	clear_buffer_mapped(&map_bh);
-	pagevec_init(&lru_pvec, 0);
 	for (page_idx = 0; page_idx < nr_pages; page_idx++) {
 		struct page *page = list_entry(pages->prev, struct page, lru);
 
 		prefetchw(&page->flags);
 		list_del(&page->lru);
-		if (!add_to_page_cache(page, mapping,
+		if (!add_to_page_cache_lru(page, mapping,
 					page->index, GFP_KERNEL)) {
 			bio = do_mpage_readpage(bio, page,
 					nr_pages - page_idx,
 					&last_block_in_bio, &map_bh,
 					&first_logical_block,
 					get_block);
-			if (!pagevec_add(&lru_pvec, page))
-				__pagevec_lru_add(&lru_pvec);
-		} else {
-			page_cache_release(page);
 		}
+		page_cache_release(page);
 	}
-	pagevec_lru_add(&lru_pvec);
 	BUG_ON(!list_empty(pages));
 	if (bio)
 		mpage_bio_submit(READ, bio);

Index: linux-2.6/mm/readahead.c
===================================================================
@@ -133,28 +133,25 @@ int read_cache_pages(struct address_spac
 			int (*filler)(void *, struct page *), void *data)
 {
 	struct page *page;
-	struct pagevec lru_pvec;
 	int ret = 0;
 
-	pagevec_init(&lru_pvec, 0);
-
 	while (!list_empty(pages)) {
 		page = list_to_page(pages);
 		list_del(&page->lru);
-		if (add_to_page_cache(page, mapping, page->index, GFP_KERNEL)) {
+		if (add_to_page_cache_lru(page, mapping,
+					page->index, GFP_KERNEL)) {
 			page_cache_release(page);
 			continue;
 		}
+		page_cache_release(page);
+
 		ret = filler(data, page);
-		if (!pagevec_add(&lru_pvec, page))
-			__pagevec_lru_add(&lru_pvec);
-		if (ret) {
+		if (unlikely(ret)) {
 			put_pages_list(pages);
 			break;
 		}
 		task_io_account_read(PAGE_CACHE_SIZE);
 	}
-	pagevec_lru_add(&lru_pvec);
 	return ret;
 }
 

@@ -164,7 +161,6 @@ static int read_pages(struct address_spa
 		struct list_head *pages, unsigned nr_pages)
 {
 	unsigned page_idx;
-	struct pagevec lru_pvec;
 	int ret;
 
 	if (mapping->a_ops->readpages) {

@@ -174,19 +170,15 @@ static int read_pages(struct address_spa
 		goto out;
 	}
 
-	pagevec_init(&lru_pvec, 0);
 	for (page_idx = 0; page_idx < nr_pages; page_idx++) {
 		struct page *page = list_to_page(pages);
 		list_del(&page->lru);
-		if (!add_to_page_cache(page, mapping,
+		if (!add_to_page_cache_lru(page, mapping,
 					page->index, GFP_KERNEL)) {
 			mapping->a_ops->readpage(filp, page);
-			if (!pagevec_add(&lru_pvec, page))
-				__pagevec_lru_add(&lru_pvec);
-		} else
-			page_cache_release(page);
+		}
+		page_cache_release(page);
 	}
-	pagevec_lru_add(&lru_pvec);
 	ret = 0;
 out:
 	return ret;

Index: linux-2.6/mm/filemap.h
===================================================================
@@ -22,82 +22,82 @@ __filemap_copy_from_user_iovec_inatomic(
 
 /*
  * Copy as much as we can into the page and return the number of bytes which
- * were sucessfully copied.  If a fault is encountered then clear the page
- * out to (offset+bytes) and return the number of bytes which were copied.
- *
- * NOTE: For this to work reliably we really want copy_from_user_inatomic_nocache
- * to *NOT* zero any tail of the buffer that it failed to copy.  If it does,
- * and if the following non-atomic copy succeeds, then there is a small window
- * where the target page contains neither the data before the write, nor the
- * data after the write (it contains zero).  A read at this time will see
- * data that is inconsistent with any ordering of the read and the write.
- * (This has been detected in practice).
+ * were sucessfully copied.  If a fault is encountered then return the number of
+ * bytes which were copied.
  */
 static inline size_t
-filemap_copy_from_user(struct page *page, unsigned long offset,
-			const char __user *buf, unsigned bytes)
+filemap_copy_from_user_atomic(struct page *page, unsigned long offset,
+			const struct iovec *iov, unsigned long nr_segs,
+			size_t base, size_t bytes)
 {
 	char *kaddr;
-	int left;
+	size_t copied;
 
 	kaddr = kmap_atomic(page, KM_USER0);
-	left = __copy_from_user_inatomic_nocache(kaddr + offset, buf, bytes);
+	if (likely(nr_segs == 1)) {
+		int left;
+		char __user *buf = iov->iov_base + base;
+		left = __copy_from_user_inatomic_nocache(kaddr + offset,
+							buf, bytes);
+		copied = bytes - left;
+	} else {
+		copied = __filemap_copy_from_user_iovec_inatomic(kaddr + offset,
+							iov, base, bytes);
+	}
 	kunmap_atomic(kaddr, KM_USER0);
 
-	if (left != 0) {
-		/* Do it the slow way */
-		kaddr = kmap(page);
-		left = __copy_from_user_nocache(kaddr + offset, buf, bytes);
-		kunmap(page);
-	}
-	return bytes - left;
+	return copied;
 }
 
 /*
- * This has the same sideeffects and return value as filemap_copy_from_user().
- * The difference is that on a fault we need to memset the remainder of the
- * page (out to offset+bytes), to emulate filemap_copy_from_user()'s
- * single-segment behaviour.
+ * This has the same sideeffects and return value as
+ * filemap_copy_from_user_atomic().
+ * The difference is that it attempts to resolve faults.
  */
 static inline size_t
-filemap_copy_from_user_iovec(struct page *page, unsigned long offset,
-			const struct iovec *iov, size_t base, size_t bytes)
+filemap_copy_from_user(struct page *page, unsigned long offset,
+			const struct iovec *iov, unsigned long nr_segs,
+			 size_t base, size_t bytes)
 {
 	char *kaddr;
 	size_t copied;
 
-	kaddr = kmap_atomic(page, KM_USER0);
-	copied = __filemap_copy_from_user_iovec_inatomic(kaddr + offset, iov,
-							 base, bytes);
-	kunmap_atomic(kaddr, KM_USER0);
-	if (copied != bytes) {
-		kaddr = kmap(page);
-		copied = __filemap_copy_from_user_iovec_inatomic(kaddr + offset, iov,
-								 base, bytes);
-		if (bytes - copied)
-			memset(kaddr + offset + copied, 0, bytes - copied);
-		kunmap(page);
+	kaddr = kmap(page);
+	if (likely(nr_segs == 1)) {
+		int left;
+		char __user *buf = iov->iov_base + base;
+		left = __copy_from_user_nocache(kaddr + offset, buf, bytes);
+		copied = bytes - left;
+	} else {
+		copied = __filemap_copy_from_user_iovec_inatomic(kaddr + offset,
+							iov, base, bytes);
 	}
+	kunmap(page);
 	return copied;
 }
 
 static inline void
-filemap_set_next_iovec(const struct iovec **iovp, size_t *basep, size_t bytes)
+filemap_set_next_iovec(const struct iovec **iovp, unsigned long nr_segs,
+						 size_t *basep, size_t bytes)
 {
-	const struct iovec *iov = *iovp;
-	size_t base = *basep;
-
-	while (bytes) {
-		int copy = min(bytes, iov->iov_len - base);
-
-		bytes -= copy;
-		base += copy;
-		if (iov->iov_len == base) {
-			iov++;
-			base = 0;
+	if (likely(nr_segs == 1)) {
+		*basep += bytes;
+	} else {
+		const struct iovec *iov = *iovp;
+		size_t base = *basep;
+
+		while (bytes) {
+			int copy = min(bytes, iov->iov_len - base);
+
+			bytes -= copy;
+			base += copy;
+			if (iov->iov_len == base) {
+				iov++;
+				base = 0;
+			}
 		}
+		*iovp = iov;
+		*basep = base;
 	}
-	*iovp = iov;
-	*basep = base;
 }
 #endif

Index: linux-2.6/mm/filemap.c
===================================================================
@@ -1840,12 +1840,7 @@ generic_file_buffered_write(struct kiocb
 	/*
 	 * handle partial DIO write.  Adjust cur_iov if needed.
 	 */
-	if (likely(nr_segs == 1))
-		buf = iov->iov_base + written;
-	else {
-		filemap_set_next_iovec(&cur_iov, &iov_offset, written);
-		buf = cur_iov->iov_base + iov_offset;
-	}
+	filemap_set_next_iovec(&cur_iov, nr_segs, &iov_offset, written);
 
 	do {
 		struct page *page;

@@ -1855,6 +1850,7 @@ generic_file_buffered_write(struct kiocb
 		size_t bytes;		/* Bytes to write to page */
 		size_t copied;		/* Bytes copied from user */
 
+		buf = cur_iov->iov_base + iov_offset;
 		offset = (pos & (PAGE_CACHE_SIZE - 1));
 		index = pos >> PAGE_CACHE_SHIFT;
 		bytes = PAGE_CACHE_SIZE - offset;

@@ -1886,13 +1882,10 @@ generic_file_buffered_write(struct kiocb
 		if (unlikely(status))
 			goto fs_write_aop_error;
 
-		if (likely(nr_segs == 1))
-			copied = filemap_copy_from_user(page, offset,
-							buf, bytes);
-		else
-			copied = filemap_copy_from_user_iovec(page, offset,
-						cur_iov, iov_offset, bytes);
+		copied = filemap_copy_from_user(page, offset,
+					cur_iov, nr_segs, iov_offset, bytes);
 		flush_dcache_page(page);
+
 		status = a_ops->commit_write(file, page, offset, offset+bytes);
 		if (unlikely(status < 0))
 			goto fs_write_aop_error;

@@ -1903,20 +1896,11 @@ generic_file_buffered_write(struct kiocb
 		if (unlikely(status > 0)) /* filesystem did partial write */
 			copied = status;
 
-		if (likely(copied > 0)) {
-			written += copied;
-			count -= copied;
-			pos += copied;
-			buf += copied;
-			if (unlikely(nr_segs > 1)) {
-				filemap_set_next_iovec(&cur_iov,
-						&iov_offset, copied);
-				if (count)
-					buf = cur_iov->iov_base + iov_offset;
-			} else {
-				iov_offset += copied;
-			}
-		}
+		written += copied;
+		count -= copied;
+		pos += copied;
+		filemap_set_next_iovec(&cur_iov, nr_segs, &iov_offset, copied);
+
 		unlock_page(page);
 		mark_page_accessed(page);
 		page_cache_release(page);

Index: linux-2.6/mm/filemap.c
===================================================================
@@ -1843,11 +1843,12 @@ generic_file_buffered_write(struct kiocb
 	filemap_set_next_iovec(&cur_iov, nr_segs, &iov_offset, written);
 
 	do {
+		struct page *src_page;
 		struct page *page;
 		pgoff_t index;		/* Pagecache index for current page */
 		unsigned long offset;	/* Offset into pagecache page */
-		unsigned long maxlen;	/* Bytes remaining in current iovec */
-		size_t bytes;		/* Bytes to write to page */
+		unsigned long seglen;	/* Bytes remaining in current iovec */
+		unsigned long bytes;	/* Bytes to write to page */
 		size_t copied;		/* Bytes copied from user */
 
 		buf = cur_iov->iov_base + iov_offset;

@@ -1857,20 +1858,30 @@ generic_file_buffered_write(struct kiocb
 		if (bytes > count)
 			bytes = count;
 
-		maxlen = cur_iov->iov_len - iov_offset;
-		if (maxlen > bytes)
-			maxlen = bytes;
+		/*
+		 * a non-NULL src_page indicates that we're doing the
+		 * copy via get_user_pages and kmap.
+		 */
+		src_page = NULL;
+
+		seglen = cur_iov->iov_len - iov_offset;
+		if (seglen > bytes)
+			seglen = bytes;
 
-#ifndef CONFIG_DEBUG_VM
 		/*
 		 * Bring in the user page that we will copy from _first_.
 		 * Otherwise there's a nasty deadlock on copying from the
 		 * same page as we're writing to, without it being marked
 		 * up-to-date.
+		 *
+		 * Not only is this an optimisation, but it is also required
+		 * to check that the address is actually valid, when atomic
+		 * usercopies are used, below.
 		 */
-		fault_in_pages_readable(buf, maxlen);
-#endif
-
+		if (unlikely(fault_in_pages_readable(buf, seglen))) {
+			status = -EFAULT;
+			break;
+		}
 
 		page = __grab_cache_page(mapping, index);
 		if (!page) {

@@ -1878,32 +1889,94 @@ generic_file_buffered_write(struct kiocb
 			break;
 		}
 
+		/*
+		 * non-uptodate pages cannot cope with short copies, and we
+		 * cannot take a pagefault with the destination page locked.
+		 * So pin the source page to copy it.
+		 */
+		if (!PageUptodate(page)) {
+			unlock_page(page);
+
+			bytes = min(bytes, PAGE_CACHE_SIZE -
+				     ((unsigned long)buf & ~PAGE_CACHE_MASK));
+
+			/*
+			 * Cannot get_user_pages with a page locked for the
+			 * same reason as we can't take a page fault with a
+			 * page locked (as explained below).
+			 */
+			down_read(&current->mm->mmap_sem);
+			status = get_user_pages(current, current->mm,
+					(unsigned long)buf & PAGE_CACHE_MASK, 1,
+					0, 0, &src_page, NULL);
+			up_read(&current->mm->mmap_sem);
+			if (status != 1) {
+				page_cache_release(page);
+				break;
+			}
+
+			lock_page(page);
+			if (!page->mapping) {
+				unlock_page(page);
+				page_cache_release(page);
+				page_cache_release(src_page);
+				continue;
+			}
+
+		}
+
 		status = a_ops->prepare_write(file, page, offset, offset+bytes);
 		if (unlikely(status))
 			goto fs_write_aop_error;
 
-		copied = filemap_copy_from_user(page, offset,
+		if (!src_page) {
+			/*
+			 * Must not enter the pagefault handler here, because
+			 * we hold the page lock, so we might recursively
+			 * deadlock on the same lock, or get an ABBA deadlock
+			 * against a different lock, or against the mmap_sem
+			 * (which nests outside the page lock).  So increment
+			 * preempt count, and use _atomic usercopies.
+			 *
+			 * The page is uptodate so we are OK to encounter a
+			 * short copy: if unmodified parts of the page are
+			 * marked dirty and written out to disk, it doesn't
+			 * really matter.
+			 */
+			pagefault_disable();
+			copied = filemap_copy_from_user_atomic(page, offset,
 					cur_iov, nr_segs, iov_offset, bytes);
+			pagefault_enable();
+		} else {
+			char *src, *dst;
+			src = kmap(src_page);
+			dst = kmap(page);
+			memcpy(dst + offset,
+				src + ((unsigned long)buf & ~PAGE_CACHE_MASK),
+				bytes);
+			kunmap(page);
+			kunmap(src_page);
+			copied = bytes;
+		}
 		flush_dcache_page(page);
 
 		status = a_ops->commit_write(file, page, offset, offset+bytes);
 		if (unlikely(status < 0))
 			goto fs_write_aop_error;
-		if (unlikely(copied != bytes)) {
-			status = -EFAULT;
-			goto fs_write_aop_error;
-		}
 		if (unlikely(status > 0)) /* filesystem did partial write */
-			copied = status;
+			copied = min_t(size_t, copied, status);
+
+		unlock_page(page);
+		mark_page_accessed(page);
+		page_cache_release(page);
+		if (src_page)
+			page_cache_release(src_page);
 
 		written += copied;
 		count -= copied;
 		pos += copied;
 		filemap_set_next_iovec(&cur_iov, nr_segs, &iov_offset, copied);
 
-		unlock_page(page);
-		mark_page_accessed(page);
-		page_cache_release(page);
 		balance_dirty_pages_ratelimited(mapping);
 		cond_resched();
 		continue;

@@ -1912,6 +1985,8 @@ fs_write_aop_error:
 		if (status != AOP_TRUNCATED_PAGE)
 			unlock_page(page);
 		page_cache_release(page);
+		if (src_page)
+			page_cache_release(src_page);
 
 		/*
 		 * prepare_write() may have instantiated a few blocks

@@ -1924,7 +1999,6 @@ fs_write_aop_error:
 			continue;
 		else
 			break;
-
 	} while (count);
 	*ppos = pos;
 

Index: linux-2.6/include/linux/pagemap.h
===================================================================
@@ -198,6 +198,9 @@ static inline int fault_in_pages_writeab
 {
 	int ret;
 
+	if (unlikely(size == 0))
+		return 0;
+
 	/*
 	 * Writing zeroes into userspace here is OK, because we know that if
 	 * the zero gets there, we'll be overwriting it.

@@ -217,19 +220,23 @@ static inline int fault_in_pages_writeab
 	return ret;
 }
 
-static inline void fault_in_pages_readable(const char __user *uaddr, int size)
+static inline int fault_in_pages_readable(const char __user *uaddr, int size)
 {
 	volatile char c;
 	int ret;
 
+	if (unlikely(size == 0))
+		return 0;
+
 	ret = __get_user(c, uaddr);
 	if (ret == 0) {
 		const char __user *end = uaddr + size - 1;
 
 		if (((unsigned long)uaddr & PAGE_MASK) !=
 				((unsigned long)end & PAGE_MASK))
-		 	__get_user(c, end);
+		 	ret = __get_user(c, end);
 	}
+	return ret;
 }
 
 #endif /* _LINUX_PAGEMAP_H */

@@ -997,6 +997,7 @@ struct page * filemap_nopage(struct vm_a
 	struct page *page;
 	unsigned long size, pgoff, endoff;
 	int did_readahead;
+	struct page *locked_page = current->locked_page;
 
 	pgoff = ((address - area->vm_start) >> PAGE_CACHE_SHIFT) + area->vm_pgoff;
 	endoff = ((area->vm_end - area->vm_start) >> PAGE_CACHE_SHIFT) + area->vm_pgoff;

@@ -1092,10 +1093,12 @@ no_cached_page:
 
 page_not_uptodate:
 	inc_page_state(pgmajfault);
-	lock_page(page);
+	if (page != locked_page)
+		lock_page(page);
 
 	/* Did it get unhashed while we waited for it? */
 	if (!page->mapping) {
+		BUG_ON(page == locked_page);	/* can't happen: i_sem */
 		unlock_page(page);
 		page_cache_release(page);
 		goto retry_all;

@@ -1103,12 +1106,15 @@ page_not_uptodate:
 
 	/* Did somebody else get it up-to-date? */
 	if (PageUptodate(page)) {
-		unlock_page(page);
+		if (page != locked_page)
+			unlock_page(page);
 		goto success;
 	}
 
 	if (!mapping->a_ops->readpage(file, page)) {
 		wait_on_page_locked(page);
+		if (page == locked_page)
+			lock_page(page);
 		if (PageUptodate(page))
 			goto success;
 	}

@@ -1119,10 +1125,12 @@ page_not_uptodate:
 	 * because there really aren't any performance issues here
 	 * and we need to check for errors.
 	 */
-	lock_page(page);
+	if (page != locked_page)
+		lock_page(page);
 
 	/* Somebody truncated the page on us? */
 	if (!page->mapping) {
+		BUG_ON(page == locked_page);	/* can't happen: i_sem */
 		unlock_page(page);
 		page_cache_release(page);
 		goto retry_all;

@@ -1130,12 +1138,15 @@ page_not_uptodate:
 
 	/* Somebody else successfully read it in? */
 	if (PageUptodate(page)) {
-		unlock_page(page);
+		if (page != locked_page)
+			unlock_page(page);
 		goto success;
 	}
 	ClearPageError(page);
 	if (!mapping->a_ops->readpage(file, page)) {
 		wait_on_page_locked(page);
+		if (page == locked_page)
+			lock_page(page);
 		if (PageUptodate(page))
 			goto success;
 	}

@@ -1445,6 +1456,11 @@ void remove_suid(struct dentry *dentry)
 	}
 }
 
+/*
+ * There is rare deadlock scenario in which the source and dest pages are
+ * the same, and the VM evicts the page at the wrong time.   Here we set
+ * current->locked_page to signal that to special-case code in filemap_nopage
+ */
 static inline int
 filemap_copy_from_user(struct page *page, unsigned long offset,
 			const char *buf, unsigned bytes)

@@ -1459,7 +1475,9 @@ filemap_copy_from_user(struct page *page
 	if (left != 0) {
 		/* Do it the slow way */
 		kaddr = kmap(page);
+		current->locked_page = page;
 		left = __copy_from_user(kaddr + offset, buf, bytes);
+		current->locked_page = NULL;
 		kunmap(page);
 	}
 	return left;

@@ -266,6 +266,7 @@ extern struct user_struct root_user;
 
 typedef struct prio_array prio_array_t;
 struct backing_dev_info;
+struct page;
 
 struct task_struct {
 	volatile long state;	/* -1 unrunnable, 0 runnable, >0 stopped */

@@ -387,6 +388,7 @@ struct task_struct {
 	void *journal_info;
 	struct dentry *proc_dentry;
 	struct backing_dev_info *backing_dev_info;
+	struct page *locked_page;
 };
 
 extern void __put_task_struct(struct task_struct *tsk);