1 files changed, 101 insertions, 83 deletions

diff --git a/mm/filemap.c b/mm/filemap.c
index 5dfc093ceb3d..edb1b0b5cc8d 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -670,7 +670,8 @@ repeat:
 	page = find_lock_page(mapping, index);
 	if (!page) {
 		if (!cached_page) {
-			cached_page = alloc_page(gfp_mask);
+			cached_page =
+				__page_cache_alloc(gfp_mask);
 			if (!cached_page)
 				return NULL;
 		}
@@ -750,6 +751,7 @@ unsigned find_get_pages_contig(struct address_space *mapping, pgoff_t index,
 	read_unlock_irq(&mapping->tree_lock);
 	return i;
 }
+EXPORT_SYMBOL(find_get_pages_contig);
 
 /**
  * find_get_pages_tag - find and return pages that match @tag
@@ -778,6 +780,7 @@ unsigned find_get_pages_tag(struct address_space *mapping, pgoff_t *index,
 	read_unlock_irq(&mapping->tree_lock);
 	return ret;
 }
+EXPORT_SYMBOL(find_get_pages_tag);
 
 /**
  * grab_cache_page_nowait - returns locked page at given index in given cache
@@ -868,6 +871,7 @@ void do_generic_mapping_read(struct address_space *mapping,
 	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;
@@ -876,7 +880,8 @@ void do_generic_mapping_read(struct address_space *mapping,
 	cached_page = NULL;
 	index = *ppos >> PAGE_CACHE_SHIFT;
 	next_index = index;
-	prev_index = ra.prev_page;
+	prev_index = ra.prev_index;
+	prev_offset = ra.prev_offset;
 	last_index = (*ppos + desc->count + PAGE_CACHE_SIZE-1) >> PAGE_CACHE_SHIFT;
 	offset = *ppos & ~PAGE_CACHE_MASK;
 
@@ -924,10 +929,10 @@ page_ok:
 			flush_dcache_page(page);
 
 		/*
-		 * When (part of) the same page is read multiple times
-		 * in succession, only mark it as accessed the first time.
+		 * When a sequential read accesses a page several times,
+		 * only mark it as accessed the first time.
 		 */
-		if (prev_index != index)
+		if (prev_index != index || offset != prev_offset)
 			mark_page_accessed(page);
 		prev_index = index;
 
@@ -945,6 +950,8 @@ page_ok:
 		offset += ret;
 		index += offset >> PAGE_CACHE_SHIFT;
 		offset &= ~PAGE_CACHE_MASK;
+		prev_offset = offset;
+		ra.prev_offset = offset;
 
 		page_cache_release(page);
 		if (ret == nr && desc->count)
@@ -1106,6 +1113,45 @@ success:
 	return size;
 }
 
+/*
+ * Performs necessary checks before doing a write
+ * @iov:	io vector request
+ * @nr_segs:	number of segments in the iovec
+ * @count:	number of bytes to write
+ * @access_flags: type of access: %VERIFY_READ or %VERIFY_WRITE
+ *
+ * Adjust number of segments and amount of bytes to write (nr_segs should be
+ * properly initialized first). Returns appropriate error code that caller
+ * should return or zero in case that write should be allowed.
+ */
+int generic_segment_checks(const struct iovec *iov,
+			unsigned long *nr_segs, size_t *count, int access_flags)
+{
+	unsigned long   seg;
+	size_t cnt = 0;
+	for (seg = 0; seg < *nr_segs; seg++) {
+		const struct iovec *iv = &iov[seg];
+
+		/*
+		 * If any segment has a negative length, or the cumulative
+		 * length ever wraps negative then return -EINVAL.
+		 */
+		cnt += iv->iov_len;
+		if (unlikely((ssize_t)(cnt|iv->iov_len) < 0))
+			return -EINVAL;
+		if (access_ok(access_flags, iv->iov_base, iv->iov_len))
+			continue;
+		if (seg == 0)
+			return -EFAULT;
+		*nr_segs = seg;
+		cnt -= iv->iov_len;	/* This segment is no good */
+		break;
+	}
+	*count = cnt;
+	return 0;
+}
+EXPORT_SYMBOL(generic_segment_checks);
+
 /**
  * generic_file_aio_read - generic filesystem read routine
  * @iocb:	kernel I/O control block
@@ -1127,24 +1173,9 @@ generic_file_aio_read(struct kiocb *iocb, const struct iovec *iov,
 	loff_t *ppos = &iocb->ki_pos;
 
 	count = 0;
-	for (seg = 0; seg < nr_segs; seg++) {
-		const struct iovec *iv = &iov[seg];
-
-		/*
-		 * If any segment has a negative length, or the cumulative
-		 * length ever wraps negative then return -EINVAL.
-		 */
-		count += iv->iov_len;
-		if (unlikely((ssize_t)(count|iv->iov_len) < 0))
-			return -EINVAL;
-		if (access_ok(VERIFY_WRITE, iv->iov_base, iv->iov_len))
-			continue;
-		if (seg == 0)
-			return -EFAULT;
-		nr_segs = seg;
-		count -= iv->iov_len;	/* This segment is no good */
-		break;
-	}
+	retval = generic_segment_checks(iov, &nr_segs, &count, VERIFY_WRITE);
+	if (retval)
+		return retval;
 
 	/* coalesce the iovecs and go direct-to-BIO for O_DIRECT */
 	if (filp->f_flags & O_DIRECT) {
@@ -1446,30 +1477,6 @@ page_not_uptodate:
 		majmin = VM_FAULT_MAJOR;
 		count_vm_event(PGMAJFAULT);
 	}
-	lock_page(page);
-
-	/* Did it get unhashed while we waited for it? */
-	if (!page->mapping) {
-		unlock_page(page);
-		page_cache_release(page);
-		goto retry_all;
-	}
-
-	/* 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.
@@ -1726,7 +1733,7 @@ int generic_file_readonly_mmap(struct file * file, struct vm_area_struct * vma)
 EXPORT_SYMBOL(generic_file_mmap);
 EXPORT_SYMBOL(generic_file_readonly_mmap);
 
-static inline struct page *__read_cache_page(struct address_space *mapping,
+static struct page *__read_cache_page(struct address_space *mapping,
 				unsigned long index,
 				int (*filler)(void *,struct page*),
 				void *data)
@@ -1763,17 +1770,11 @@ repeat:
 	return page;
 }
 
-/**
- * read_cache_page - read into page cache, fill it if needed
- * @mapping:	the page's address_space
- * @index:	the page index
- * @filler:	function to perform the read
- * @data:	destination for read data
- *
- * Read into the page cache. If a page already exists,
- * and PageUptodate() is not set, try to fill the page.
+/*
+ * Same as read_cache_page, but don't wait for page to become unlocked
+ * after submitting it to the filler.
  */
-struct page *read_cache_page(struct address_space *mapping,
+struct page *read_cache_page_async(struct address_space *mapping,
 				unsigned long index,
 				int (*filler)(void *,struct page*),
 				void *data)
@@ -1784,7 +1785,7 @@ struct page *read_cache_page(struct address_space *mapping,
 retry:
 	page = __read_cache_page(mapping, index, filler, data);
 	if (IS_ERR(page))
-		goto out;
+		return page;
 	mark_page_accessed(page);
 	if (PageUptodate(page))
 		goto out;
@@ -1802,7 +1803,40 @@ retry:
 	err = filler(data, page);
 	if (err < 0) {
 		page_cache_release(page);
-		page = ERR_PTR(err);
+		return ERR_PTR(err);
+	}
+out:
+	mark_page_accessed(page);
+	return page;
+}
+EXPORT_SYMBOL(read_cache_page_async);
+
+/**
+ * read_cache_page - read into page cache, fill it if needed
+ * @mapping:	the page's address_space
+ * @index:	the page index
+ * @filler:	function to perform the read
+ * @data:	destination for read data
+ *
+ * Read into the page cache. If a page already exists, and PageUptodate() is
+ * not set, try to fill the page then wait for it to become unlocked.
+ *
+ * If the page does not get brought uptodate, return -EIO.
+ */
+struct page *read_cache_page(struct address_space *mapping,
+				unsigned long index,
+				int (*filler)(void *,struct page*),
+				void *data)
+{
+	struct page *page;
+
+	page = read_cache_page_async(mapping, index, filler, data);
+	if (IS_ERR(page))
+		goto out;
+	wait_on_page_locked(page);
+	if (!PageUptodate(page)) {
+		page_cache_release(page);
+		page = ERR_PTR(-EIO);
 	}
  out:
 	return page;
@@ -2211,30 +2245,14 @@ __generic_file_aio_write_nolock(struct kiocb *iocb, const struct iovec *iov,
 	size_t ocount;		/* original count */
 	size_t count;		/* after file limit checks */
 	struct inode 	*inode = mapping->host;
-	unsigned long	seg;
 	loff_t		pos;
 	ssize_t		written;
 	ssize_t		err;
 
 	ocount = 0;
-	for (seg = 0; seg < nr_segs; seg++) {
-		const struct iovec *iv = &iov[seg];
-
-		/*
-		 * If any segment has a negative length, or the cumulative
-		 * length ever wraps negative then return -EINVAL.
-		 */
-		ocount += iv->iov_len;
-		if (unlikely((ssize_t)(ocount|iv->iov_len) < 0))
-			return -EINVAL;
-		if (access_ok(VERIFY_READ, iv->iov_base, iv->iov_len))
-			continue;
-		if (seg == 0)
-			return -EFAULT;
-		nr_segs = seg;
-		ocount -= iv->iov_len;	/* This segment is no good */
-		break;
-	}
+	err = generic_segment_checks(iov, &nr_segs, &ocount, VERIFY_READ);
+	if (err)
+		return err;
 
 	count = ocount;
 	pos = *ppos;
@@ -2294,10 +2312,10 @@ __generic_file_aio_write_nolock(struct kiocb *iocb, const struct iovec *iov,
 		 * semantics.
 		 */
 		endbyte = pos + written_buffered - written - 1;
-		err = do_sync_file_range(file, pos, endbyte,
-					 SYNC_FILE_RANGE_WAIT_BEFORE|
-					 SYNC_FILE_RANGE_WRITE|
-					 SYNC_FILE_RANGE_WAIT_AFTER);
+		err = do_sync_mapping_range(file->f_mapping, pos, endbyte,
+					    SYNC_FILE_RANGE_WAIT_BEFORE|
+					    SYNC_FILE_RANGE_WRITE|
+					    SYNC_FILE_RANGE_WAIT_AFTER);
 		if (err == 0) {
 			written = written_buffered;
 			invalidate_mapping_pages(mapping,