Merge branch 'for-chris' of git://github.com/sensille/linux into integration

Conflicts:
	fs/btrfs/ctree.h
Signed-off-by: Chris Mason <chris.mason@oracle.com>

fs/btrfs/Makefile

@@ -7,6 +7,7 @@ btrfs-y += super.o ctree.o extent-tree.o print-tree.o root-tree.o dir-item.o \
 	   extent_map.o sysfs.o struct-funcs.o xattr.o ordered-data.o \
 	   extent_io.o volumes.o async-thread.o ioctl.o locking.o orphan.o \
 	   export.o tree-log.o free-space-cache.o zlib.o lzo.o \
-	   compression.o delayed-ref.o relocation.o delayed-inode.o scrub.o
+	   compression.o delayed-ref.o relocation.o delayed-inode.o scrub.o \
+	   reada.o
 
 btrfs-$(CONFIG_BTRFS_FS_POSIX_ACL) += acl.o

fs/btrfs/ctree.h

@@ -1074,6 +1074,7 @@ struct btrfs_fs_info {
 	struct btrfs_workers endio_freespace_worker;
 	struct btrfs_workers submit_workers;
 	struct btrfs_workers caching_workers;
+	struct btrfs_workers readahead_workers;
 
 	/*
 	 * fixup workers take dirty pages that didn't properly go through
@@ -1158,6 +1159,10 @@ struct btrfs_fs_info {
 
 	struct btrfs_delayed_root *delayed_root;
 
+	/* readahead tree */
+	spinlock_t reada_lock;
+	struct radix_tree_root reada_tree;
+
 	/* next backup root to be overwritten */
 	int backup_root_index;
 };
@@ -2812,4 +2817,20 @@ int btrfs_scrub_cancel_devid(struct btrfs_root *root, u64 devid);
 int btrfs_scrub_progress(struct btrfs_root *root, u64 devid,
 			 struct btrfs_scrub_progress *progress);
 
+/* reada.c */
+struct reada_control {
+	struct btrfs_root	*root;		/* tree to prefetch */
+	struct btrfs_key	key_start;
+	struct btrfs_key	key_end;	/* exclusive */
+	atomic_t		elems;
+	struct kref		refcnt;
+	wait_queue_head_t	wait;
+};
+struct reada_control *btrfs_reada_add(struct btrfs_root *root,
+			      struct btrfs_key *start, struct btrfs_key *end);
+int btrfs_reada_wait(void *handle);
+void btrfs_reada_detach(void *handle);
+int btree_readahead_hook(struct btrfs_root *root, struct extent_buffer *eb,
+			 u64 start, int err);
+
 #endif

fs/btrfs/disk-io.c

@@ -366,7 +366,8 @@ static int btree_read_extent_buffer_pages(struct btrfs_root *root,
 	clear_bit(EXTENT_BUFFER_CORRUPT, &eb->bflags);
 	io_tree = &BTRFS_I(root->fs_info->btree_inode)->io_tree;
 	while (1) {
-		ret = read_extent_buffer_pages(io_tree, eb, start, 1,
+		ret = read_extent_buffer_pages(io_tree, eb, start,
+					       WAIT_COMPLETE,
 					       btree_get_extent, mirror_num);
 		if (!ret &&
 		    !verify_parent_transid(io_tree, eb, parent_transid))
@@ -607,11 +608,47 @@ static int btree_readpage_end_io_hook(struct page *page, u64 start, u64 end,
 	end = min_t(u64, eb->len, PAGE_CACHE_SIZE);
 	end = eb->start + end - 1;
 err:
+	if (test_bit(EXTENT_BUFFER_READAHEAD, &eb->bflags)) {
+		clear_bit(EXTENT_BUFFER_READAHEAD, &eb->bflags);
+		btree_readahead_hook(root, eb, eb->start, ret);
+	}
+
 	free_extent_buffer(eb);
 out:
 	return ret;
 }
 
+static int btree_io_failed_hook(struct bio *failed_bio,
+			 struct page *page, u64 start, u64 end,
+			 struct extent_state *state)
+{
+	struct extent_io_tree *tree;
+	unsigned long len;
+	struct extent_buffer *eb;
+	struct btrfs_root *root = BTRFS_I(page->mapping->host)->root;
+
+	tree = &BTRFS_I(page->mapping->host)->io_tree;
+	if (page->private == EXTENT_PAGE_PRIVATE)
+		goto out;
+	if (!page->private)
+		goto out;
+
+	len = page->private >> 2;
+	WARN_ON(len == 0);
+
+	eb = alloc_extent_buffer(tree, start, len, page);
+	if (eb == NULL)
+		goto out;
+
+	if (test_bit(EXTENT_BUFFER_READAHEAD, &eb->bflags)) {
+		clear_bit(EXTENT_BUFFER_READAHEAD, &eb->bflags);
+		btree_readahead_hook(root, eb, eb->start, -EIO);
+	}
+
+out:
+	return -EIO;	/* we fixed nothing */
+}
+
 static void end_workqueue_bio(struct bio *bio, int err)
 {
 	struct end_io_wq *end_io_wq = bio->bi_private;
@@ -973,11 +1010,43 @@ int readahead_tree_block(struct btrfs_root *root, u64 bytenr, u32 blocksize,
 	if (!buf)
 		return 0;
 	read_extent_buffer_pages(&BTRFS_I(btree_inode)->io_tree,
-				 buf, 0, 0, btree_get_extent, 0);
+				 buf, 0, WAIT_NONE, btree_get_extent, 0);
 	free_extent_buffer(buf);
 	return ret;
 }
 
+int reada_tree_block_flagged(struct btrfs_root *root, u64 bytenr, u32 blocksize,
+			 int mirror_num, struct extent_buffer **eb)
+{
+	struct extent_buffer *buf = NULL;
+	struct inode *btree_inode = root->fs_info->btree_inode;
+	struct extent_io_tree *io_tree = &BTRFS_I(btree_inode)->io_tree;
+	int ret;
+
+	buf = btrfs_find_create_tree_block(root, bytenr, blocksize);
+	if (!buf)
+		return 0;
+
+	set_bit(EXTENT_BUFFER_READAHEAD, &buf->bflags);
+
+	ret = read_extent_buffer_pages(io_tree, buf, 0, WAIT_PAGE_LOCK,
+				       btree_get_extent, mirror_num);
+	if (ret) {
+		free_extent_buffer(buf);
+		return ret;
+	}
+
+	if (test_bit(EXTENT_BUFFER_CORRUPT, &buf->bflags)) {
+		free_extent_buffer(buf);
+		return -EIO;
+	} else if (extent_buffer_uptodate(io_tree, buf, NULL)) {
+		*eb = buf;
+	} else {
+		free_extent_buffer(buf);
+	}
+	return 0;
+}
+
 struct extent_buffer *btrfs_find_tree_block(struct btrfs_root *root,
 					    u64 bytenr, u32 blocksize)
 {
@@ -1904,6 +1973,10 @@ struct btrfs_root *open_ctree(struct super_block *sb,
 	fs_info->trans_no_join = 0;
 	fs_info->free_chunk_space = 0;
 
+	/* readahead state */
+	INIT_RADIX_TREE(&fs_info->reada_tree, GFP_NOFS & ~__GFP_WAIT);
+	spin_lock_init(&fs_info->reada_lock);
+
 	fs_info->thread_pool_size = min_t(unsigned long,
 					  num_online_cpus() + 2, 8);
 
@@ -2103,6 +2176,9 @@ struct btrfs_root *open_ctree(struct super_block *sb,
 	btrfs_init_workers(&fs_info->delayed_workers, "delayed-meta",
 			   fs_info->thread_pool_size,
 			   &fs_info->generic_worker);
+	btrfs_init_workers(&fs_info->readahead_workers, "readahead",
+			   fs_info->thread_pool_size,
+			   &fs_info->generic_worker);
 
 	/*
 	 * endios are largely parallel and should have a very
@@ -2113,6 +2189,7 @@ struct btrfs_root *open_ctree(struct super_block *sb,
 
 	fs_info->endio_write_workers.idle_thresh = 2;
 	fs_info->endio_meta_write_workers.idle_thresh = 2;
+	fs_info->readahead_workers.idle_thresh = 2;
 
 	btrfs_start_workers(&fs_info->workers, 1);
 	btrfs_start_workers(&fs_info->generic_worker, 1);
@@ -2126,6 +2203,7 @@ struct btrfs_root *open_ctree(struct super_block *sb,
 	btrfs_start_workers(&fs_info->endio_freespace_worker, 1);
 	btrfs_start_workers(&fs_info->delayed_workers, 1);
 	btrfs_start_workers(&fs_info->caching_workers, 1);
+	btrfs_start_workers(&fs_info->readahead_workers, 1);
 
 	fs_info->bdi.ra_pages *= btrfs_super_num_devices(disk_super);
 	fs_info->bdi.ra_pages = max(fs_info->bdi.ra_pages,
@@ -2855,6 +2933,7 @@ int close_ctree(struct btrfs_root *root)
 	btrfs_stop_workers(&fs_info->submit_workers);
 	btrfs_stop_workers(&fs_info->delayed_workers);
 	btrfs_stop_workers(&fs_info->caching_workers);
+	btrfs_stop_workers(&fs_info->readahead_workers);
 
 	btrfs_close_devices(fs_info->fs_devices);
 	btrfs_mapping_tree_free(&fs_info->mapping_tree);
@@ -3363,6 +3442,7 @@ static int btrfs_cleanup_transaction(struct btrfs_root *root)
 static struct extent_io_ops btree_extent_io_ops = {
 	.write_cache_pages_lock_hook = btree_lock_page_hook,
 	.readpage_end_io_hook = btree_readpage_end_io_hook,
+	.readpage_io_failed_hook = btree_io_failed_hook,
 	.submit_bio_hook = btree_submit_bio_hook,
 	/* note we're sharing with inode.c for the merge bio hook */
 	.merge_bio_hook = btrfs_merge_bio_hook,

fs/btrfs/disk-io.h

@@ -40,6 +40,8 @@ struct extent_buffer *read_tree_block(struct btrfs_root *root, u64 bytenr,
 				      u32 blocksize, u64 parent_transid);
 int readahead_tree_block(struct btrfs_root *root, u64 bytenr, u32 blocksize,
 			 u64 parent_transid);
+int reada_tree_block_flagged(struct btrfs_root *root, u64 bytenr, u32 blocksize,
+			 int mirror_num, struct extent_buffer **eb);
 struct extent_buffer *btrfs_find_create_tree_block(struct btrfs_root *root,
 						   u64 bytenr, u32 blocksize);
 int clean_tree_block(struct btrfs_trans_handle *trans,

fs/btrfs/extent_io.c

@@ -1919,7 +1919,7 @@ static void end_bio_extent_readpage(struct bio *bio, int err)
 		if (!uptodate && tree->ops &&
 		    tree->ops->readpage_io_failed_hook) {
 			ret = tree->ops->readpage_io_failed_hook(bio, page,
-							 start, end, NULL);
+							 start, end, state);
 			if (ret == 0) {
 				uptodate =
 					test_bit(BIO_UPTODATE, &bio->bi_flags);
@@ -3551,8 +3551,7 @@ int extent_buffer_uptodate(struct extent_io_tree *tree,
 }
 
 int read_extent_buffer_pages(struct extent_io_tree *tree,
-			     struct extent_buffer *eb,
-			     u64 start, int wait,
+			     struct extent_buffer *eb, u64 start, int wait,
 			     get_extent_t *get_extent, int mirror_num)
 {
 	unsigned long i;
@@ -3588,7 +3587,7 @@ int read_extent_buffer_pages(struct extent_io_tree *tree,
 	num_pages = num_extent_pages(eb->start, eb->len);
 	for (i = start_i; i < num_pages; i++) {
 		page = extent_buffer_page(eb, i);
-		if (!wait) {
+		if (wait == WAIT_NONE) {
 			if (!trylock_page(page))
 				goto unlock_exit;
 		} else {
@@ -3632,7 +3631,7 @@ int read_extent_buffer_pages(struct extent_io_tree *tree,
 	if (bio)
 		submit_one_bio(READ, bio, mirror_num, bio_flags);
 
-	if (ret || !wait)
+	if (ret || wait != WAIT_COMPLETE)
 		return ret;
 
 	for (i = start_i; i < num_pages; i++) {

fs/btrfs/extent_io.h

@@ -33,6 +33,7 @@
 #define EXTENT_BUFFER_BLOCKING 1
 #define EXTENT_BUFFER_DIRTY 2
 #define EXTENT_BUFFER_CORRUPT 3
+#define EXTENT_BUFFER_READAHEAD 4	/* this got triggered by readahead */
 
 /* these are flags for extent_clear_unlock_delalloc */
 #define EXTENT_CLEAR_UNLOCK_PAGE 0x1
@@ -252,6 +253,9 @@ struct extent_buffer *alloc_extent_buffer(struct extent_io_tree *tree,
 struct extent_buffer *find_extent_buffer(struct extent_io_tree *tree,
 					 u64 start, unsigned long len);
 void free_extent_buffer(struct extent_buffer *eb);
+#define WAIT_NONE	0
+#define WAIT_COMPLETE	1
+#define WAIT_PAGE_LOCK	2
 int read_extent_buffer_pages(struct extent_io_tree *tree,
 			     struct extent_buffer *eb, u64 start, int wait,
 			     get_extent_t *get_extent, int mirror_num);

fs/btrfs/scrub.c

@@ -29,15 +29,12 @@
  * any can be found.
  *
  * Future enhancements:
- *  - To enhance the performance, better read-ahead strategies for the
- *    extent-tree can be employed.
  *  - In case an unrepairable extent is encountered, track which files are
  *    affected and report them
  *  - In case of a read error on files with nodatasum, map the file and read
  *    the extent to trigger a writeback of the good copy
  *  - track and record media errors, throw out bad devices
  *  - add a mode to also read unallocated space
- *  - make the prefetch cancellable
  */
 
 struct scrub_bio;
@@ -741,13 +738,16 @@ static noinline_for_stack int scrub_stripe(struct scrub_dev *sdev,
 	int slot;
 	int i;
 	u64 nstripes;
-	int start_stripe;
 	struct extent_buffer *l;
 	struct btrfs_key key;
 	u64 physical;
 	u64 logical;
 	u64 generation;
 	u64 mirror_num;
+	struct reada_control *reada1;
+	struct reada_control *reada2;
+	struct btrfs_key key_start;
+	struct btrfs_key key_end;
 
 	u64 increment = map->stripe_len;
 	u64 offset;
@@ -779,81 +779,67 @@ static noinline_for_stack int scrub_stripe(struct scrub_dev *sdev,
 	if (!path)
 		return -ENOMEM;
 
-	path->reada = 2;
 	path->search_commit_root = 1;
 	path->skip_locking = 1;
 
 	/*
-	 * find all extents for each stripe and just read them to get
-	 * them into the page cache
-	 * FIXME: we can do better. build a more intelligent prefetching
+	 * trigger the readahead for extent tree csum tree and wait for
+	 * completion. During readahead, the scrub is officially paused
+	 * to not hold off transaction commits
 	 */
 	logical = base + offset;
-	physical = map->stripes[num].physical;
-	ret = 0;
-	for (i = 0; i < nstripes; ++i) {
-		key.objectid = logical;
-		key.type = BTRFS_EXTENT_ITEM_KEY;
-		key.offset = (u64)0;
-
-		ret = btrfs_search_slot(NULL, root, &key, path, 0, 0);
-		if (ret < 0)
-			goto out_noplug;
-
-		/*
-		 * we might miss half an extent here, but that doesn't matter,
-		 * as it's only the prefetch
-		 */
-		while (1) {
-			l = path->nodes[0];
-			slot = path->slots[0];
-			if (slot >= btrfs_header_nritems(l)) {
-				ret = btrfs_next_leaf(root, path);
-				if (ret == 0)
-					continue;
-				if (ret < 0)
-					goto out_noplug;
 
-				break;
-			}
-			btrfs_item_key_to_cpu(l, &key, slot);
+	wait_event(sdev->list_wait,
+		   atomic_read(&sdev->in_flight) == 0);
+	atomic_inc(&fs_info->scrubs_paused);
+	wake_up(&fs_info->scrub_pause_wait);
 
-			if (key.objectid >= logical + map->stripe_len)
-				break;
+	/* FIXME it might be better to start readahead at commit root */
+	key_start.objectid = logical;
+	key_start.type = BTRFS_EXTENT_ITEM_KEY;
+	key_start.offset = (u64)0;
+	key_end.objectid = base + offset + nstripes * increment;
+	key_end.type = BTRFS_EXTENT_ITEM_KEY;
+	key_end.offset = (u64)0;
+	reada1 = btrfs_reada_add(root, &key_start, &key_end);
+
+	key_start.objectid = BTRFS_EXTENT_CSUM_OBJECTID;
+	key_start.type = BTRFS_EXTENT_CSUM_KEY;
+	key_start.offset = logical;
+	key_end.objectid = BTRFS_EXTENT_CSUM_OBJECTID;
+	key_end.type = BTRFS_EXTENT_CSUM_KEY;
+	key_end.offset = base + offset + nstripes * increment;
+	reada2 = btrfs_reada_add(csum_root, &key_start, &key_end);
+
+	if (!IS_ERR(reada1))
+		btrfs_reada_wait(reada1);
+	if (!IS_ERR(reada2))
+		btrfs_reada_wait(reada2);
 
-			path->slots[0]++;
-		}
-		btrfs_release_path(path);
-		logical += increment;
-		physical += map->stripe_len;
-		cond_resched();
+	mutex_lock(&fs_info->scrub_lock);
+	while (atomic_read(&fs_info->scrub_pause_req)) {
+		mutex_unlock(&fs_info->scrub_lock);
+		wait_event(fs_info->scrub_pause_wait,
+		   atomic_read(&fs_info->scrub_pause_req) == 0);
+		mutex_lock(&fs_info->scrub_lock);
 	}
+	atomic_dec(&fs_info->scrubs_paused);
+	mutex_unlock(&fs_info->scrub_lock);
+	wake_up(&fs_info->scrub_pause_wait);
 
 	/*
 	 * collect all data csums for the stripe to avoid seeking during
 	 * the scrub. This might currently (crc32) end up to be about 1MB
 	 */
-	start_stripe = 0;
 	blk_start_plug(&plug);
-again:
-	logical = base + offset + start_stripe * increment;
-	for (i = start_stripe; i < nstripes; ++i) {
-		ret = btrfs_lookup_csums_range(csum_root, logical,
-					       logical + map->stripe_len - 1,
-					       &sdev->csum_list, 1);
-		if (ret)
-			goto out;
 
-		logical += increment;
-		cond_resched();
-	}
 	/*
 	 * now find all extents for each stripe and scrub them
 	 */
-	logical = base + offset + start_stripe * increment;
-	physical = map->stripes[num].physical + start_stripe * map->stripe_len;
+	logical = base + offset;
+	physical = map->stripes[num].physical;
 	ret = 0;
-	for (i = start_stripe; i < nstripes; ++i) {
+	for (i = 0; i < nstripes; ++i) {
 		/*
 		 * canceled?
 		 */
@@ -882,11 +868,14 @@ static noinline_for_stack int scrub_stripe(struct scrub_dev *sdev,
 			atomic_dec(&fs_info->scrubs_paused);
 			mutex_unlock(&fs_info->scrub_lock);
 			wake_up(&fs_info->scrub_pause_wait);
-			scrub_free_csums(sdev);
-			start_stripe = i;
-			goto again;
 		}
 
+		ret = btrfs_lookup_csums_range(csum_root, logical,
+					       logical + map->stripe_len - 1,
+					       &sdev->csum_list, 1);
+		if (ret)
+			goto out;
+
 		key.objectid = logical;
 		key.type = BTRFS_EXTENT_ITEM_KEY;
 		key.offset = (u64)0;
@@ -982,7 +971,6 @@ static noinline_for_stack int scrub_stripe(struct scrub_dev *sdev,
 
 out:
 	blk_finish_plug(&plug);
-out_noplug:
 	btrfs_free_path(path);
 	return ret < 0 ? ret : 0;
 }

fs/btrfs/volumes.c

@@ -366,6 +366,14 @@ static noinline int device_list_add(const char *path,
 		}
 		INIT_LIST_HEAD(&device->dev_alloc_list);
 
+		/* init readahead state */
+		spin_lock_init(&device->reada_lock);
+		device->reada_curr_zone = NULL;
+		atomic_set(&device->reada_in_flight, 0);
+		device->reada_next = 0;
+		INIT_RADIX_TREE(&device->reada_zones, GFP_NOFS & ~__GFP_WAIT);
+		INIT_RADIX_TREE(&device->reada_extents, GFP_NOFS & ~__GFP_WAIT);
+
 		mutex_lock(&fs_devices->device_list_mutex);
 		list_add_rcu(&device->dev_list, &fs_devices->devices);
 		mutex_unlock(&fs_devices->device_list_mutex);

fs/btrfs/volumes.h

@@ -92,6 +92,14 @@ struct btrfs_device {
 	struct btrfs_work work;
 	struct rcu_head rcu;
 	struct work_struct rcu_work;
+
+	/* readahead state */
+	spinlock_t reada_lock;
+	atomic_t reada_in_flight;
+	u64 reada_next;
+	struct reada_zone *reada_curr_zone;
+	struct radix_tree_root reada_zones;
+	struct radix_tree_root reada_extents;
 };
 
 struct btrfs_fs_devices {