1 files changed, 150 insertions, 133 deletions

diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 62e0cafd6e25..7cda51995c1e 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -46,6 +46,10 @@
 #include "check-integrity.h"
 #include "rcu-string.h"
 
+#ifdef CONFIG_X86
+#include <asm/cpufeature.h>
+#endif
+
 static struct extent_io_ops btree_extent_io_ops;
 static void end_workqueue_fn(struct btrfs_work *work);
 static void free_fs_root(struct btrfs_root *root);
@@ -217,26 +221,16 @@ static struct extent_map *btree_get_extent(struct inode *inode,
 	write_lock(&em_tree->lock);
 	ret = add_extent_mapping(em_tree, em);
 	if (ret == -EEXIST) {
-		u64 failed_start = em->start;
-		u64 failed_len = em->len;
-
 		free_extent_map(em);
 		em = lookup_extent_mapping(em_tree, start, len);
-		if (em) {
-			ret = 0;
-		} else {
-			em = lookup_extent_mapping(em_tree, failed_start,
-						   failed_len);
-			ret = -EIO;
-		}
+		if (!em)
+			em = ERR_PTR(-EIO);
 	} else if (ret) {
 		free_extent_map(em);
-		em = NULL;
+		em = ERR_PTR(ret);
 	}
 	write_unlock(&em_tree->lock);
 
-	if (ret)
-		em = ERR_PTR(ret);
 out:
 	return em;
 }
@@ -377,9 +371,13 @@ static int btree_read_extent_buffer_pages(struct btrfs_root *root,
 		ret = read_extent_buffer_pages(io_tree, eb, start,
 					       WAIT_COMPLETE,
 					       btree_get_extent, mirror_num);
-		if (!ret && !verify_parent_transid(io_tree, eb,
+		if (!ret) {
+			if (!verify_parent_transid(io_tree, eb,
 						   parent_transid, 0))
-			break;
+				break;
+			else
+				ret = -EIO;
+		}
 
 		/*
 		 * This buffer's crc is fine, but its contents are corrupted, so
@@ -435,10 +433,6 @@ static int csum_dirty_buffer(struct btrfs_root *root, struct page *page)
 		WARN_ON(1);
 		return 0;
 	}
-	if (eb->pages[0] != page) {
-		WARN_ON(1);
-		return 0;
-	}
 	if (!PageUptodate(page)) {
 		WARN_ON(1);
 		return 0;
@@ -754,9 +748,7 @@ static void run_one_async_done(struct btrfs_work *work)
 	limit = btrfs_async_submit_limit(fs_info);
 	limit = limit * 2 / 3;
 
-	atomic_dec(&fs_info->nr_async_submits);
-
-	if (atomic_read(&fs_info->nr_async_submits) < limit &&
+	if (atomic_dec_return(&fs_info->nr_async_submits) < limit &&
 	    waitqueue_active(&fs_info->async_submit_wait))
 		wake_up(&fs_info->async_submit_wait);
 
@@ -867,10 +859,22 @@ static int __btree_submit_bio_done(struct inode *inode, int rw, struct bio *bio,
 	return btrfs_map_bio(BTRFS_I(inode)->root, rw, bio, mirror_num, 1);
 }
 
+static int check_async_write(struct inode *inode, unsigned long bio_flags)
+{
+	if (bio_flags & EXTENT_BIO_TREE_LOG)
+		return 0;
+#ifdef CONFIG_X86
+	if (cpu_has_xmm4_2)
+		return 0;
+#endif
+	return 1;
+}
+
 static int btree_submit_bio_hook(struct inode *inode, int rw, struct bio *bio,
 				 int mirror_num, unsigned long bio_flags,
 				 u64 bio_offset)
 {
+	int async = check_async_write(inode, bio_flags);
 	int ret;
 
 	if (!(rw & REQ_WRITE)) {
@@ -885,6 +889,12 @@ static int btree_submit_bio_hook(struct inode *inode, int rw, struct bio *bio,
 			return ret;
 		return btrfs_map_bio(BTRFS_I(inode)->root, rw, bio,
 				     mirror_num, 0);
+	} else if (!async) {
+		ret = btree_csum_one_bio(bio);
+		if (ret)
+			return ret;
+		return btrfs_map_bio(BTRFS_I(inode)->root, rw, bio,
+				     mirror_num, 0);
 	}
 
 	/*
@@ -1166,8 +1176,8 @@ static void __setup_root(u32 nodesize, u32 leafsize, u32 sectorsize,
 	atomic_set(&root->log_commit[0], 0);
 	atomic_set(&root->log_commit[1], 0);
 	atomic_set(&root->log_writers, 0);
+	atomic_set(&root->log_batch, 0);
 	atomic_set(&root->orphan_inodes, 0);
-	root->log_batch = 0;
 	root->log_transid = 0;
 	root->last_log_commit = 0;
 	extent_io_tree_init(&root->dirty_log_pages,
@@ -1665,9 +1675,10 @@ static int transaction_kthread(void *arg)
 		spin_unlock(&root->fs_info->trans_lock);
 
 		/* If the file system is aborted, this will always fail. */
-		trans = btrfs_join_transaction(root);
+		trans = btrfs_attach_transaction(root);
 		if (IS_ERR(trans)) {
-			cannot_commit = true;
+			if (PTR_ERR(trans) != -ENOENT)
+				cannot_commit = true;
 			goto sleep;
 		}
 		if (transid == trans->transid) {
@@ -1992,13 +2003,11 @@ int open_ctree(struct super_block *sb,
 	INIT_LIST_HEAD(&fs_info->trans_list);
 	INIT_LIST_HEAD(&fs_info->dead_roots);
 	INIT_LIST_HEAD(&fs_info->delayed_iputs);
-	INIT_LIST_HEAD(&fs_info->hashers);
 	INIT_LIST_HEAD(&fs_info->delalloc_inodes);
 	INIT_LIST_HEAD(&fs_info->ordered_operations);
 	INIT_LIST_HEAD(&fs_info->caching_block_groups);
 	spin_lock_init(&fs_info->delalloc_lock);
 	spin_lock_init(&fs_info->trans_lock);
-	spin_lock_init(&fs_info->ref_cache_lock);
 	spin_lock_init(&fs_info->fs_roots_radix_lock);
 	spin_lock_init(&fs_info->delayed_iput_lock);
 	spin_lock_init(&fs_info->defrag_inodes_lock);
@@ -2012,12 +2021,15 @@ int open_ctree(struct super_block *sb,
 	INIT_LIST_HEAD(&fs_info->space_info);
 	INIT_LIST_HEAD(&fs_info->tree_mod_seq_list);
 	btrfs_mapping_init(&fs_info->mapping_tree);
-	btrfs_init_block_rsv(&fs_info->global_block_rsv);
-	btrfs_init_block_rsv(&fs_info->delalloc_block_rsv);
-	btrfs_init_block_rsv(&fs_info->trans_block_rsv);
-	btrfs_init_block_rsv(&fs_info->chunk_block_rsv);
-	btrfs_init_block_rsv(&fs_info->empty_block_rsv);
-	btrfs_init_block_rsv(&fs_info->delayed_block_rsv);
+	btrfs_init_block_rsv(&fs_info->global_block_rsv,
+			     BTRFS_BLOCK_RSV_GLOBAL);
+	btrfs_init_block_rsv(&fs_info->delalloc_block_rsv,
+			     BTRFS_BLOCK_RSV_DELALLOC);
+	btrfs_init_block_rsv(&fs_info->trans_block_rsv, BTRFS_BLOCK_RSV_TRANS);
+	btrfs_init_block_rsv(&fs_info->chunk_block_rsv, BTRFS_BLOCK_RSV_CHUNK);
+	btrfs_init_block_rsv(&fs_info->empty_block_rsv, BTRFS_BLOCK_RSV_EMPTY);
+	btrfs_init_block_rsv(&fs_info->delayed_block_rsv,
+			     BTRFS_BLOCK_RSV_DELOPS);
 	atomic_set(&fs_info->nr_async_submits, 0);
 	atomic_set(&fs_info->async_delalloc_pages, 0);
 	atomic_set(&fs_info->async_submit_draining, 0);
@@ -2032,8 +2044,6 @@ int open_ctree(struct super_block *sb,
 	fs_info->free_chunk_space = 0;
 	fs_info->tree_mod_log = RB_ROOT;
 
-	init_waitqueue_head(&fs_info->tree_mod_seq_wait);
-
 	/* readahead state */
 	INIT_RADIX_TREE(&fs_info->reada_tree, GFP_NOFS & ~__GFP_WAIT);
 	spin_lock_init(&fs_info->reada_lock);
@@ -2491,6 +2501,8 @@ retry_root_backup:
 		printk(KERN_ERR "Failed to read block groups: %d\n", ret);
 		goto fail_block_groups;
 	}
+	fs_info->num_tolerated_disk_barrier_failures =
+		btrfs_calc_num_tolerated_disk_barrier_failures(fs_info);
 
 	fs_info->cleaner_kthread = kthread_run(cleaner_kthread, tree_root,
 					       "btrfs-cleaner");
@@ -2528,8 +2540,7 @@ retry_root_backup:
 		goto fail_trans_kthread;
 
 	/* do not make disk changes in broken FS */
-	if (btrfs_super_log_root(disk_super) != 0 &&
-	    !(fs_info->fs_state & BTRFS_SUPER_FLAG_ERROR)) {
+	if (btrfs_super_log_root(disk_super) != 0) {
 		u64 bytenr = btrfs_super_log_root(disk_super);
 
 		if (fs_devices->rw_devices == 0) {
@@ -2875,12 +2886,10 @@ static int write_dev_flush(struct btrfs_device *device, int wait)
 			printk_in_rcu("btrfs: disabling barriers on dev %s\n",
 				      rcu_str_deref(device->name));
 			device->nobarriers = 1;
-		}
-		if (!bio_flagged(bio, BIO_UPTODATE)) {
+		} else if (!bio_flagged(bio, BIO_UPTODATE)) {
 			ret = -EIO;
-			if (!bio_flagged(bio, BIO_EOPNOTSUPP))
-				btrfs_dev_stat_inc_and_print(device,
-					BTRFS_DEV_STAT_FLUSH_ERRS);
+			btrfs_dev_stat_inc_and_print(device,
+				BTRFS_DEV_STAT_FLUSH_ERRS);
 		}
 
 		/* drop the reference from the wait == 0 run */
@@ -2919,14 +2928,15 @@ static int barrier_all_devices(struct btrfs_fs_info *info)
 {
 	struct list_head *head;
 	struct btrfs_device *dev;
-	int errors = 0;
+	int errors_send = 0;
+	int errors_wait = 0;
 	int ret;
 
 	/* send down all the barriers */
 	head = &info->fs_devices->devices;
 	list_for_each_entry_rcu(dev, head, dev_list) {
 		if (!dev->bdev) {
-			errors++;
+			errors_send++;
 			continue;
 		}
 		if (!dev->in_fs_metadata || !dev->writeable)
@@ -2934,13 +2944,13 @@ static int barrier_all_devices(struct btrfs_fs_info *info)
 
 		ret = write_dev_flush(dev, 0);
 		if (ret)
-			errors++;
+			errors_send++;
 	}
 
 	/* wait for all the barriers */
 	list_for_each_entry_rcu(dev, head, dev_list) {
 		if (!dev->bdev) {
-			errors++;
+			errors_wait++;
 			continue;
 		}
 		if (!dev->in_fs_metadata || !dev->writeable)
@@ -2948,13 +2958,87 @@ static int barrier_all_devices(struct btrfs_fs_info *info)
 
 		ret = write_dev_flush(dev, 1);
 		if (ret)
-			errors++;
+			errors_wait++;
 	}
-	if (errors)
+	if (errors_send > info->num_tolerated_disk_barrier_failures ||
+	    errors_wait > info->num_tolerated_disk_barrier_failures)
 		return -EIO;
 	return 0;
 }
 
+int btrfs_calc_num_tolerated_disk_barrier_failures(
+	struct btrfs_fs_info *fs_info)
+{
+	struct btrfs_ioctl_space_info space;
+	struct btrfs_space_info *sinfo;
+	u64 types[] = {BTRFS_BLOCK_GROUP_DATA,
+		       BTRFS_BLOCK_GROUP_SYSTEM,
+		       BTRFS_BLOCK_GROUP_METADATA,
+		       BTRFS_BLOCK_GROUP_DATA | BTRFS_BLOCK_GROUP_METADATA};
+	int num_types = 4;
+	int i;
+	int c;
+	int num_tolerated_disk_barrier_failures =
+		(int)fs_info->fs_devices->num_devices;
+
+	for (i = 0; i < num_types; i++) {
+		struct btrfs_space_info *tmp;
+
+		sinfo = NULL;
+		rcu_read_lock();
+		list_for_each_entry_rcu(tmp, &fs_info->space_info, list) {
+			if (tmp->flags == types[i]) {
+				sinfo = tmp;
+				break;
+			}
+		}
+		rcu_read_unlock();
+
+		if (!sinfo)
+			continue;
+
+		down_read(&sinfo->groups_sem);
+		for (c = 0; c < BTRFS_NR_RAID_TYPES; c++) {
+			if (!list_empty(&sinfo->block_groups[c])) {
+				u64 flags;
+
+				btrfs_get_block_group_info(
+					&sinfo->block_groups[c], &space);
+				if (space.total_bytes == 0 ||
+				    space.used_bytes == 0)
+					continue;
+				flags = space.flags;
+				/*
+				 * return
+				 * 0: if dup, single or RAID0 is configured for
+				 *    any of metadata, system or data, else
+				 * 1: if RAID5 is configured, or if RAID1 or
+				 *    RAID10 is configured and only two mirrors
+				 *    are used, else
+				 * 2: if RAID6 is configured, else
+				 * num_mirrors - 1: if RAID1 or RAID10 is
+				 *                  configured and more than
+				 *                  2 mirrors are used.
+				 */
+				if (num_tolerated_disk_barrier_failures > 0 &&
+				    ((flags & (BTRFS_BLOCK_GROUP_DUP |
+					       BTRFS_BLOCK_GROUP_RAID0)) ||
+				     ((flags & BTRFS_BLOCK_GROUP_PROFILE_MASK)
+				      == 0)))
+					num_tolerated_disk_barrier_failures = 0;
+				else if (num_tolerated_disk_barrier_failures > 1
+					 &&
+					 (flags & (BTRFS_BLOCK_GROUP_RAID1 |
+						   BTRFS_BLOCK_GROUP_RAID10)))
+					num_tolerated_disk_barrier_failures = 1;
+			}
+		}
+		up_read(&sinfo->groups_sem);
+	}
+
+	return num_tolerated_disk_barrier_failures;
+}
+
 int write_all_supers(struct btrfs_root *root, int max_mirrors)
 {
 	struct list_head *head;
@@ -2977,8 +3061,16 @@ int write_all_supers(struct btrfs_root *root, int max_mirrors)
 	mutex_lock(&root->fs_info->fs_devices->device_list_mutex);
 	head = &root->fs_info->fs_devices->devices;
 
-	if (do_barriers)
-		barrier_all_devices(root->fs_info);
+	if (do_barriers) {
+		ret = barrier_all_devices(root->fs_info);
+		if (ret) {
+			mutex_unlock(
+				&root->fs_info->fs_devices->device_list_mutex);
+			btrfs_error(root->fs_info, ret,
+				    "errors while submitting device barriers.");
+			return ret;
+		}
+	}
 
 	list_for_each_entry_rcu(dev, head, dev_list) {
 		if (!dev->bdev) {
@@ -3189,30 +3281,14 @@ int close_ctree(struct btrfs_root *root)
 	/* clear out the rbtree of defraggable inodes */
 	btrfs_run_defrag_inodes(fs_info);
 
-	/*
-	 * Here come 2 situations when btrfs is broken to flip readonly:
-	 *
-	 * 1. when btrfs flips readonly somewhere else before
-	 * btrfs_commit_super, sb->s_flags has MS_RDONLY flag,
-	 * and btrfs will skip to write sb directly to keep
-	 * ERROR state on disk.
-	 *
-	 * 2. when btrfs flips readonly just in btrfs_commit_super,
-	 * and in such case, btrfs cannot write sb via btrfs_commit_super,
-	 * and since fs_state has been set BTRFS_SUPER_FLAG_ERROR flag,
-	 * btrfs will cleanup all FS resources first and write sb then.
-	 */
 	if (!(fs_info->sb->s_flags & MS_RDONLY)) {
 		ret = btrfs_commit_super(root);
 		if (ret)
 			printk(KERN_ERR "btrfs: commit super ret %d\n", ret);
 	}
 
-	if (fs_info->fs_state & BTRFS_SUPER_FLAG_ERROR) {
-		ret = btrfs_error_commit_super(root);
-		if (ret)
-			printk(KERN_ERR "btrfs: commit super ret %d\n", ret);
-	}
+	if (fs_info->fs_state & BTRFS_SUPER_FLAG_ERROR)
+		btrfs_error_commit_super(root);
 
 	btrfs_put_block_group_cache(fs_info);
 
@@ -3228,10 +3304,6 @@ int close_ctree(struct btrfs_root *root)
 		printk(KERN_INFO "btrfs: at unmount delalloc count %llu\n",
 		       (unsigned long long)fs_info->delalloc_bytes);
 	}
-	if (fs_info->total_ref_cache_size) {
-		printk(KERN_INFO "btrfs: at umount reference cache size %llu\n",
-		       (unsigned long long)fs_info->total_ref_cache_size);
-	}
 
 	free_extent_buffer(fs_info->extent_root->node);
 	free_extent_buffer(fs_info->extent_root->commit_root);
@@ -3377,52 +3449,6 @@ int btrfs_read_buffer(struct extent_buffer *buf, u64 parent_transid)
 	return btree_read_extent_buffer_pages(root, buf, 0, parent_transid);
 }
 
-int btree_lock_page_hook(struct page *page, void *data,
-				void (*flush_fn)(void *))
-{
-	struct inode *inode = page->mapping->host;
-	struct btrfs_root *root = BTRFS_I(inode)->root;
-	struct extent_buffer *eb;
-
-	/*
-	 * We culled this eb but the page is still hanging out on the mapping,
-	 * carry on.
-	 */
-	if (!PagePrivate(page))
-		goto out;
-
-	eb = (struct extent_buffer *)page->private;
-	if (!eb) {
-		WARN_ON(1);
-		goto out;
-	}
-	if (page != eb->pages[0])
-		goto out;
-
-	if (!btrfs_try_tree_write_lock(eb)) {
-		flush_fn(data);
-		btrfs_tree_lock(eb);
-	}
-	btrfs_set_header_flag(eb, BTRFS_HEADER_FLAG_WRITTEN);
-
-	if (test_and_clear_bit(EXTENT_BUFFER_DIRTY, &eb->bflags)) {
-		spin_lock(&root->fs_info->delalloc_lock);
-		if (root->fs_info->dirty_metadata_bytes >= eb->len)
-			root->fs_info->dirty_metadata_bytes -= eb->len;
-		else
-			WARN_ON(1);
-		spin_unlock(&root->fs_info->delalloc_lock);
-	}
-
-	btrfs_tree_unlock(eb);
-out:
-	if (!trylock_page(page)) {
-		flush_fn(data);
-		lock_page(page);
-	}
-	return 0;
-}
-
 static int btrfs_check_super_valid(struct btrfs_fs_info *fs_info,
 			      int read_only)
 {
@@ -3434,18 +3460,11 @@ static int btrfs_check_super_valid(struct btrfs_fs_info *fs_info,
 	if (read_only)
 		return 0;
 
-	if (fs_info->fs_state & BTRFS_SUPER_FLAG_ERROR) {
-		printk(KERN_WARNING "warning: mount fs with errors, "
-		       "running btrfsck is recommended\n");
-	}
-
 	return 0;
 }
 
-int btrfs_error_commit_super(struct btrfs_root *root)
+void btrfs_error_commit_super(struct btrfs_root *root)
 {
-	int ret;
-
 	mutex_lock(&root->fs_info->cleaner_mutex);
 	btrfs_run_delayed_iputs(root);
 	mutex_unlock(&root->fs_info->cleaner_mutex);
@@ -3455,10 +3474,6 @@ int btrfs_error_commit_super(struct btrfs_root *root)
 
 	/* cleanup FS via transaction */
 	btrfs_cleanup_transaction(root);
-
-	ret = write_ctree_super(NULL, root, 0);
-
-	return ret;
 }
 
 static void btrfs_destroy_ordered_operations(struct btrfs_root *root)
@@ -3636,7 +3651,7 @@ static int btrfs_destroy_marked_extents(struct btrfs_root *root,
 
 	while (1) {
 		ret = find_first_extent_bit(dirty_pages, start, &start, &end,
-					    mark);
+					    mark, NULL);
 		if (ret)
 			break;
 
@@ -3691,7 +3706,7 @@ static int btrfs_destroy_pinned_extent(struct btrfs_root *root,
 again:
 	while (1) {
 		ret = find_first_extent_bit(unpin, 0, &start, &end,
-					    EXTENT_DIRTY);
+					    EXTENT_DIRTY, NULL);
 		if (ret)
 			break;
 
@@ -3782,14 +3797,17 @@ int btrfs_cleanup_transaction(struct btrfs_root *root)
 		/* FIXME: cleanup wait for commit */
 		t->in_commit = 1;
 		t->blocked = 1;
+		smp_mb();
 		if (waitqueue_active(&root->fs_info->transaction_blocked_wait))
 			wake_up(&root->fs_info->transaction_blocked_wait);
 
 		t->blocked = 0;
+		smp_mb();
 		if (waitqueue_active(&root->fs_info->transaction_wait))
 			wake_up(&root->fs_info->transaction_wait);
 
 		t->commit_done = 1;
+		smp_mb();
 		if (waitqueue_active(&t->commit_wait))
 			wake_up(&t->commit_wait);
 
@@ -3825,7 +3843,6 @@ 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,