1 files changed, 58 insertions, 62 deletions

diff --git a/fs/buffer.c b/fs/buffer.c
index 6024877335ca..44c14a87750e 100644
--- a/fs/buffer.c
+++ b/fs/buffer.c
@@ -61,23 +61,16 @@ inline void touch_buffer(struct buffer_head *bh)
 }
 EXPORT_SYMBOL(touch_buffer);
 
-static int sleep_on_buffer(void *word)
-{
-	io_schedule();
-	return 0;
-}
-
 void __lock_buffer(struct buffer_head *bh)
 {
-	wait_on_bit_lock(&bh->b_state, BH_Lock, sleep_on_buffer,
-							TASK_UNINTERRUPTIBLE);
+	wait_on_bit_lock_io(&bh->b_state, BH_Lock, TASK_UNINTERRUPTIBLE);
 }
 EXPORT_SYMBOL(__lock_buffer);
 
 void unlock_buffer(struct buffer_head *bh)
 {
 	clear_bit_unlock(BH_Lock, &bh->b_state);
-	smp_mb__after_clear_bit();
+	smp_mb__after_atomic();
 	wake_up_bit(&bh->b_state, BH_Lock);
 }
 EXPORT_SYMBOL(unlock_buffer);
@@ -123,7 +116,7 @@ EXPORT_SYMBOL(buffer_check_dirty_writeback);
  */
 void __wait_on_buffer(struct buffer_head * bh)
 {
-	wait_on_bit(&bh->b_state, BH_Lock, sleep_on_buffer, TASK_UNINTERRUPTIBLE);
+	wait_on_bit_io(&bh->b_state, BH_Lock, TASK_UNINTERRUPTIBLE);
 }
 EXPORT_SYMBOL(__wait_on_buffer);
 
@@ -227,7 +220,7 @@ __find_get_block_slow(struct block_device *bdev, sector_t block)
 	int all_mapped = 1;
 
 	index = block >> (PAGE_CACHE_SHIFT - bd_inode->i_blkbits);
-	page = find_get_page(bd_mapping, index);
+	page = find_get_page_flags(bd_mapping, index, FGP_ACCESSED);
 	if (!page)
 		goto out;
 
@@ -654,14 +647,16 @@ EXPORT_SYMBOL(mark_buffer_dirty_inode);
 static void __set_page_dirty(struct page *page,
 		struct address_space *mapping, int warn)
 {
-	spin_lock_irq(&mapping->tree_lock);
+	unsigned long flags;
+
+	spin_lock_irqsave(&mapping->tree_lock, flags);
 	if (page->mapping) {	/* Race with truncate? */
 		WARN_ON_ONCE(warn && !PageUptodate(page));
 		account_page_dirtied(page, mapping);
 		radix_tree_tag_set(&mapping->page_tree,
 				page_index(page), PAGECACHE_TAG_DIRTY);
 	}
-	spin_unlock_irq(&mapping->tree_lock);
+	spin_unlock_irqrestore(&mapping->tree_lock, flags);
 	__mark_inode_dirty(mapping->host, I_DIRTY_PAGES);
 }
 
@@ -1027,7 +1022,8 @@ grow_dev_page(struct block_device *bdev, sector_t block,
 		bh = page_buffers(page);
 		if (bh->b_size == size) {
 			end_block = init_page_buffers(page, bdev,
-						index << sizebits, size);
+						(sector_t)index << sizebits,
+						size);
 			goto done;
 		}
 		if (!try_to_free_buffers(page))
@@ -1048,7 +1044,8 @@ grow_dev_page(struct block_device *bdev, sector_t block,
 	 */
 	spin_lock(&inode->i_mapping->private_lock);
 	link_dev_buffers(page, bh);
-	end_block = init_page_buffers(page, bdev, index << sizebits, size);
+	end_block = init_page_buffers(page, bdev, (sector_t)index << sizebits,
+			size);
 	spin_unlock(&inode->i_mapping->private_lock);
 done:
 	ret = (block < end_block) ? 1 : -ENXIO;
@@ -1256,7 +1253,7 @@ static struct buffer_head *__bread_slow(struct buffer_head *bh)
  * a local interrupt disable for that.
  */
 
-#define BH_LRU_SIZE	8
+#define BH_LRU_SIZE	16
 
 struct bh_lru {
 	struct buffer_head *bhs[BH_LRU_SIZE];
@@ -1312,7 +1309,7 @@ static void bh_lru_install(struct buffer_head *bh)
 		}
 		while (out < BH_LRU_SIZE)
 			bhs[out++] = NULL;
-		memcpy(__this_cpu_ptr(&bh_lrus.bhs), bhs, sizeof(bhs));
+		memcpy(this_cpu_ptr(&bh_lrus.bhs), bhs, sizeof(bhs));
 	}
 	bh_lru_unlock();
 
@@ -1364,12 +1361,13 @@ __find_get_block(struct block_device *bdev, sector_t block, unsigned size)
 	struct buffer_head *bh = lookup_bh_lru(bdev, block, size);
 
 	if (bh == NULL) {
+		/* __find_get_block_slow will mark the page accessed */
 		bh = __find_get_block_slow(bdev, block);
 		if (bh)
 			bh_lru_install(bh);
-	}
-	if (bh)
+	} else
 		touch_buffer(bh);
+
 	return bh;
 }
 EXPORT_SYMBOL(__find_get_block);
@@ -1481,16 +1479,27 @@ EXPORT_SYMBOL(set_bh_page);
 /*
  * Called when truncating a buffer on a page completely.
  */
+
+/* Bits that are cleared during an invalidate */
+#define BUFFER_FLAGS_DISCARD \
+	(1 << BH_Mapped | 1 << BH_New | 1 << BH_Req | \
+	 1 << BH_Delay | 1 << BH_Unwritten)
+
 static void discard_buffer(struct buffer_head * bh)
 {
+	unsigned long b_state, b_state_old;
+
 	lock_buffer(bh);
 	clear_buffer_dirty(bh);
 	bh->b_bdev = NULL;
-	clear_buffer_mapped(bh);
-	clear_buffer_req(bh);
-	clear_buffer_new(bh);
-	clear_buffer_delay(bh);
-	clear_buffer_unwritten(bh);
+	b_state = bh->b_state;
+	for (;;) {
+		b_state_old = cmpxchg(&bh->b_state, b_state,
+				      (b_state & ~BUFFER_FLAGS_DISCARD));
+		if (b_state_old == b_state)
+			break;
+		b_state = b_state_old;
+	}
 	unlock_buffer(bh);
 }
 
@@ -2112,8 +2121,8 @@ EXPORT_SYMBOL(generic_write_end);
  * 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)
+int block_is_partially_uptodate(struct page *page, unsigned long from,
+					unsigned long count)
 {
 	unsigned block_start, block_end, blocksize;
 	unsigned to;
@@ -2125,7 +2134,7 @@ int block_is_partially_uptodate(struct page *page, read_descriptor_t *desc,
 
 	head = page_buffers(page);
 	blocksize = head->b_size;
-	to = min_t(unsigned, PAGE_CACHE_SIZE - from, desc->count);
+	to = min_t(unsigned, PAGE_CACHE_SIZE - from, count);
 	to = from + to;
 	if (from < blocksize && to > PAGE_CACHE_SIZE - blocksize)
 		return 0;
@@ -2877,10 +2886,9 @@ EXPORT_SYMBOL(block_truncate_page);
 
 /*
  * The generic ->writepage function for buffer-backed address_spaces
- * this form passes in the end_io handler used to finish the IO.
  */
-int block_write_full_page_endio(struct page *page, get_block_t *get_block,
-			struct writeback_control *wbc, bh_end_io_t *handler)
+int block_write_full_page(struct page *page, get_block_t *get_block,
+			struct writeback_control *wbc)
 {
 	struct inode * const inode = page->mapping->host;
 	loff_t i_size = i_size_read(inode);
@@ -2890,7 +2898,7 @@ int block_write_full_page_endio(struct page *page, get_block_t *get_block,
 	/* Is the page fully inside i_size? */
 	if (page->index < end_index)
 		return __block_write_full_page(inode, page, get_block, wbc,
-					       handler);
+					       end_buffer_async_write);
 
 	/* Is the page fully outside i_size? (truncate in progress) */
 	offset = i_size & (PAGE_CACHE_SIZE-1);
@@ -2913,18 +2921,8 @@ int block_write_full_page_endio(struct page *page, get_block_t *get_block,
 	 * writes to that region are not written out to the file."
 	 */
 	zero_user_segment(page, offset, PAGE_CACHE_SIZE);
-	return __block_write_full_page(inode, page, get_block, wbc, handler);
-}
-EXPORT_SYMBOL(block_write_full_page_endio);
-
-/*
- * The generic ->writepage function for buffer-backed address_spaces
- */
-int block_write_full_page(struct page *page, get_block_t *get_block,
-			struct writeback_control *wbc)
-{
-	return block_write_full_page_endio(page, get_block, wbc,
-					   end_buffer_async_write);
+	return __block_write_full_page(inode, page, get_block, wbc,
+							end_buffer_async_write);
 }
 EXPORT_SYMBOL(block_write_full_page);
 
@@ -2958,7 +2956,7 @@ static void end_bio_bh_io_sync(struct bio *bio, int err)
 
 /*
  * This allows us to do IO even on the odd last sectors
- * of a device, even if the bh block size is some multiple
+ * of a device, even if the block size is some multiple
  * of the physical sector size.
  *
  * We'll just truncate the bio to the size of the device,
@@ -2968,10 +2966,11 @@ static void end_bio_bh_io_sync(struct bio *bio, int err)
  * errors, this only handles the "we need to be able to
  * do IO at the final sector" case.
  */
-static void guard_bh_eod(int rw, struct bio *bio, struct buffer_head *bh)
+void guard_bio_eod(int rw, struct bio *bio)
 {
 	sector_t maxsector;
-	unsigned bytes;
+	struct bio_vec *bvec = &bio->bi_io_vec[bio->bi_vcnt - 1];
+	unsigned truncated_bytes;
 
 	maxsector = i_size_read(bio->bi_bdev->bd_inode) >> 9;
 	if (!maxsector)
@@ -2982,27 +2981,24 @@ static void guard_bh_eod(int rw, struct bio *bio, struct buffer_head *bh)
 	 * let it through, and the IO layer will turn it into
 	 * an EIO.
 	 */
-	if (unlikely(bio->bi_sector >= maxsector))
+	if (unlikely(bio->bi_iter.bi_sector >= maxsector))
 		return;
 
-	maxsector -= bio->bi_sector;
-	bytes = bio->bi_size;
-	if (likely((bytes >> 9) <= maxsector))
+	maxsector -= bio->bi_iter.bi_sector;
+	if (likely((bio->bi_iter.bi_size >> 9) <= maxsector))
 		return;
 
-	/* Uhhuh. We've got a bh that straddles the device size! */
-	bytes = maxsector << 9;
+	/* Uhhuh. We've got a bio that straddles the device size! */
+	truncated_bytes = bio->bi_iter.bi_size - (maxsector << 9);
 
 	/* Truncate the bio.. */
-	bio->bi_size = bytes;
-	bio->bi_io_vec[0].bv_len = bytes;
+	bio->bi_iter.bi_size -= truncated_bytes;
+	bvec->bv_len -= truncated_bytes;
 
 	/* ..and clear the end of the buffer for reads */
 	if ((rw & RW_MASK) == READ) {
-		void *kaddr = kmap_atomic(bh->b_page);
-		memset(kaddr + bh_offset(bh) + bytes, 0, bh->b_size - bytes);
-		kunmap_atomic(kaddr);
-		flush_dcache_page(bh->b_page);
+		zero_user(bvec->bv_page, bvec->bv_offset + bvec->bv_len,
+				truncated_bytes);
 	}
 }
 
@@ -3029,21 +3025,21 @@ int _submit_bh(int rw, struct buffer_head *bh, unsigned long bio_flags)
 	 */
 	bio = bio_alloc(GFP_NOIO, 1);
 
-	bio->bi_sector = bh->b_blocknr * (bh->b_size >> 9);
+	bio->bi_iter.bi_sector = bh->b_blocknr * (bh->b_size >> 9);
 	bio->bi_bdev = bh->b_bdev;
 	bio->bi_io_vec[0].bv_page = bh->b_page;
 	bio->bi_io_vec[0].bv_len = bh->b_size;
 	bio->bi_io_vec[0].bv_offset = bh_offset(bh);
 
 	bio->bi_vcnt = 1;
-	bio->bi_size = bh->b_size;
+	bio->bi_iter.bi_size = bh->b_size;
 
 	bio->bi_end_io = end_bio_bh_io_sync;
 	bio->bi_private = bh;
 	bio->bi_flags |= bio_flags;
 
 	/* Take care of bh's that straddle the end of the device */
-	guard_bh_eod(rw, bio, bh);
+	guard_bio_eod(rw, bio);
 
 	if (buffer_meta(bh))
 		rw |= REQ_META;
@@ -3086,7 +3082,7 @@ EXPORT_SYMBOL(submit_bh);
  * until the buffer gets unlocked).
  *
  * ll_rw_block sets b_end_io to simple completion handler that marks
- * the buffer up-to-date (if approriate), unlocks the buffer and wakes
+ * the buffer up-to-date (if appropriate), unlocks the buffer and wakes
  * any waiters. 
  *
  * All of the buffers must be for the same device, and must also be a