Merge branch 'linus' into stackprotector

Conflicts:
	arch/x86/kernel/Makefile
	include/asm-x86/pda.h

1 files changed, 86 insertions, 22 deletions

diff --git a/fs/buffer.c b/fs/buffer.c
index a073f3f4f01..ac78d4c19b3 100644
--- a/fs/buffer.c
+++ b/fs/buffer.c
@@ -580,7 +580,7 @@ EXPORT_SYMBOL(mark_buffer_async_write);
 /*
  * The buffer's backing address_space's private_lock must be held
  */
-static inline void __remove_assoc_queue(struct buffer_head *bh)
+static void __remove_assoc_queue(struct buffer_head *bh)
 {
 	list_del_init(&bh->b_assoc_buffers);
 	WARN_ON(!bh->b_assoc_map);
@@ -706,7 +706,7 @@ static int __set_page_dirty(struct page *page,
 	if (TestSetPageDirty(page))
 		return 0;
 
-	write_lock_irq(&mapping->tree_lock);
+	spin_lock_irq(&mapping->tree_lock);
 	if (page->mapping) {	/* Race with truncate? */
 		WARN_ON_ONCE(warn && !PageUptodate(page));
 
@@ -719,7 +719,7 @@ static int __set_page_dirty(struct page *page,
 		radix_tree_tag_set(&mapping->page_tree,
 				page_index(page), PAGECACHE_TAG_DIRTY);
 	}
-	write_unlock_irq(&mapping->tree_lock);
+	spin_unlock_irq(&mapping->tree_lock);
 	__mark_inode_dirty(mapping->host, I_DIRTY_PAGES);
 
 	return 1;
@@ -821,7 +821,7 @@ static int fsync_buffers_list(spinlock_t *lock, struct list_head *list)
 				 * contents - it is a noop if I/O is still in
 				 * flight on potentially older contents.
 				 */
-				ll_rw_block(SWRITE, 1, &bh);
+				ll_rw_block(SWRITE_SYNC, 1, &bh);
 				brelse(bh);
 				spin_lock(lock);
 			}
@@ -1214,8 +1214,7 @@ void __brelse(struct buffer_head * buf)
 		put_bh(buf);
 		return;
 	}
-	printk(KERN_ERR "VFS: brelse: Trying to free free buffer\n");
-	WARN_ON(1);
+	WARN(1, KERN_ERR "VFS: brelse: Trying to free free buffer\n");
 }
 
 /*
@@ -1464,7 +1463,7 @@ static void invalidate_bh_lru(void *arg)
 	
 void invalidate_bh_lrus(void)
 {
-	on_each_cpu(invalidate_bh_lru, NULL, 1, 1);
+	on_each_cpu(invalidate_bh_lru, NULL, 1);
 }
 EXPORT_SYMBOL_GPL(invalidate_bh_lrus);
 
@@ -1691,11 +1690,13 @@ static int __block_write_full_page(struct inode *inode, struct page *page,
 			 */
 			clear_buffer_dirty(bh);
 			set_buffer_uptodate(bh);
-		} else if (!buffer_mapped(bh) && buffer_dirty(bh)) {
+		} else if ((!buffer_mapped(bh) || buffer_delay(bh)) &&
+			   buffer_dirty(bh)) {
 			WARN_ON(bh->b_size != blocksize);
 			err = get_block(inode, block, bh, 1);
 			if (err)
 				goto recover;
+			clear_buffer_delay(bh);
 			if (buffer_new(bh)) {
 				/* blockdev mappings never come here */
 				clear_buffer_new(bh);
@@ -1719,7 +1720,7 @@ static int __block_write_full_page(struct inode *inode, struct page *page,
 		 */
 		if (wbc->sync_mode != WB_SYNC_NONE || !wbc->nonblocking) {
 			lock_buffer(bh);
-		} else if (test_set_buffer_locked(bh)) {
+		} else if (!trylock_buffer(bh)) {
 			redirty_page_for_writepage(wbc, page);
 			continue;
 		}
@@ -1774,7 +1775,8 @@ recover:
 	bh = head;
 	/* Recovery: lock and submit the mapped buffers */
 	do {
-		if (buffer_mapped(bh) && buffer_dirty(bh)) {
+		if (buffer_mapped(bh) && buffer_dirty(bh) &&
+		    !buffer_delay(bh)) {
 			lock_buffer(bh);
 			mark_buffer_async_write(bh);
 		} else {
@@ -2061,6 +2063,7 @@ int generic_write_end(struct file *file, struct address_space *mapping,
 			struct page *page, void *fsdata)
 {
 	struct inode *inode = mapping->host;
+	int i_size_changed = 0;
 
 	copied = block_write_end(file, mapping, pos, len, copied, page, fsdata);
 
@@ -2073,17 +2076,72 @@ int generic_write_end(struct file *file, struct address_space *mapping,
 	 */
 	if (pos+copied > inode->i_size) {
 		i_size_write(inode, pos+copied);
-		mark_inode_dirty(inode);
+		i_size_changed = 1;
 	}
 
 	unlock_page(page);
 	page_cache_release(page);
 
+	/*
+	 * Don't mark the inode dirty under page lock. First, it unnecessarily
+	 * makes the holding time of page lock longer. Second, it forces lock
+	 * ordering of page lock and transaction start for journaling
+	 * filesystems.
+	 */
+	if (i_size_changed)
+		mark_inode_dirty(inode);
+
 	return copied;
 }
 EXPORT_SYMBOL(generic_write_end);
 
 /*
+ * block_is_partially_uptodate checks whether buffers within a page are
+ * uptodate or not.
+ *
+ * Returns true if all buffers which correspond to a file portion
+ * we want to read are uptodate.
+ */
+int block_is_partially_uptodate(struct page *page, read_descriptor_t *desc,
+					unsigned long from)
+{
+	struct inode *inode = page->mapping->host;
+	unsigned block_start, block_end, blocksize;
+	unsigned to;
+	struct buffer_head *bh, *head;
+	int ret = 1;
+
+	if (!page_has_buffers(page))
+		return 0;
+
+	blocksize = 1 << inode->i_blkbits;
+	to = min_t(unsigned, PAGE_CACHE_SIZE - from, desc->count);
+	to = from + to;
+	if (from < blocksize && to > PAGE_CACHE_SIZE - blocksize)
+		return 0;
+
+	head = page_buffers(page);
+	bh = head;
+	block_start = 0;
+	do {
+		block_end = block_start + blocksize;
+		if (block_end > from && block_start < to) {
+			if (!buffer_uptodate(bh)) {
+				ret = 0;
+				break;
+			}
+			if (block_end >= to)
+				break;
+		}
+		block_start = block_end;
+		bh = bh->b_this_page;
+	} while (bh != head);
+
+	return ret;
+}
+EXPORT_SYMBOL(block_is_partially_uptodate);
+
+/*
  * Generic "read page" function for block devices that have the normal
  * get_block functionality. This is most of the block device filesystems.
  * Reads the page asynchronously --- the unlock_buffer() and
@@ -2868,14 +2926,17 @@ int submit_bh(int rw, struct buffer_head * bh)
 	BUG_ON(!buffer_mapped(bh));
 	BUG_ON(!bh->b_end_io);
 
-	if (buffer_ordered(bh) && (rw == WRITE))
-		rw = WRITE_BARRIER;
+	/*
+	 * Mask in barrier bit for a write (could be either a WRITE or a
+	 * WRITE_SYNC
+	 */
+	if (buffer_ordered(bh) && (rw & WRITE))
+		rw |= WRITE_BARRIER;
 
 	/*
-	 * Only clear out a write error when rewriting, should this
-	 * include WRITE_SYNC as well?
+	 * Only clear out a write error when rewriting
 	 */
-	if (test_set_buffer_req(bh) && (rw == WRITE || rw == WRITE_BARRIER))
+	if (test_set_buffer_req(bh) && (rw & WRITE))
 		clear_buffer_write_io_error(bh);
 
 	/*
@@ -2940,16 +3001,19 @@ void ll_rw_block(int rw, int nr, struct buffer_head *bhs[])
 	for (i = 0; i < nr; i++) {
 		struct buffer_head *bh = bhs[i];
 
-		if (rw == SWRITE)
+		if (rw == SWRITE || rw == SWRITE_SYNC)
 			lock_buffer(bh);
-		else if (test_set_buffer_locked(bh))
+		else if (!trylock_buffer(bh))
 			continue;
 
-		if (rw == WRITE || rw == SWRITE) {
+		if (rw == WRITE || rw == SWRITE || rw == SWRITE_SYNC) {
 			if (test_clear_buffer_dirty(bh)) {
 				bh->b_end_io = end_buffer_write_sync;
 				get_bh(bh);
-				submit_bh(WRITE, bh);
+				if (rw == SWRITE_SYNC)
+					submit_bh(WRITE_SYNC, bh);
+				else
+					submit_bh(WRITE, bh);
 				continue;
 			}
 		} else {
@@ -2978,7 +3042,7 @@ int sync_dirty_buffer(struct buffer_head *bh)
 	if (test_clear_buffer_dirty(bh)) {
 		get_bh(bh);
 		bh->b_end_io = end_buffer_write_sync;
-		ret = submit_bh(WRITE, bh);
+		ret = submit_bh(WRITE_SYNC, bh);
 		wait_on_buffer(bh);
 		if (buffer_eopnotsupp(bh)) {
 			clear_buffer_eopnotsupp(bh);
@@ -3256,7 +3320,7 @@ int bh_submit_read(struct buffer_head *bh)
 EXPORT_SYMBOL(bh_submit_read);
 
 static void
-init_buffer_head(struct kmem_cache *cachep, void *data)
+init_buffer_head(void *data)
 {
 	struct buffer_head *bh = data;