Merge branch 'master' of /home/davem/src/GIT/linux-2.6/

8 files changed, 92 insertions, 40 deletions

diff --git a/fs/ext4/balloc.c b/fs/ext4/balloc.c
index 9a50b8052dc..de9459b4cb9 100644
--- a/fs/ext4/balloc.c
+++ b/fs/ext4/balloc.c
@@ -609,7 +609,9 @@ int ext4_claim_free_blocks(struct ext4_sb_info *sbi,
  */
 int ext4_should_retry_alloc(struct super_block *sb, int *retries)
 {
-	if (!ext4_has_free_blocks(EXT4_SB(sb), 1) || (*retries)++ > 3)
+	if (!ext4_has_free_blocks(EXT4_SB(sb), 1) ||
+	    (*retries)++ > 3 ||
+	    !EXT4_SB(sb)->s_journal)
 		return 0;
 
 	jbd_debug(1, "%s: retrying operation after ENOSPC\n", sb->s_id);
diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index aafc9eba1c2..b0c87dce66a 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -868,7 +868,7 @@ static inline unsigned ext4_rec_len_from_disk(__le16 dlen)
 {
 	unsigned len = le16_to_cpu(dlen);
 
-	if (len == EXT4_MAX_REC_LEN)
+	if (len == EXT4_MAX_REC_LEN || len == 0)
 		return 1 << 16;
 	return len;
 }
diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c
index e2eab196875..e0aa4fe4f59 100644
--- a/fs/ext4/extents.c
+++ b/fs/ext4/extents.c
@@ -1122,7 +1122,8 @@ ext4_ext_search_right(struct inode *inode, struct ext4_ext_path *path,
 	struct ext4_extent_idx *ix;
 	struct ext4_extent *ex;
 	ext4_fsblk_t block;
-	int depth, ee_len;
+	int depth;	/* Note, NOT eh_depth; depth from top of tree */
+	int ee_len;
 
 	BUG_ON(path == NULL);
 	depth = path->p_depth;
@@ -1179,7 +1180,8 @@ got_index:
 		if (bh == NULL)
 			return -EIO;
 		eh = ext_block_hdr(bh);
-		if (ext4_ext_check_header(inode, eh, depth)) {
+		/* subtract from p_depth to get proper eh_depth */
+		if (ext4_ext_check_header(inode, eh, path->p_depth - depth)) {
 			put_bh(bh);
 			return -EIO;
 		}
diff --git a/fs/ext4/ialloc.c b/fs/ext4/ialloc.c
index 4fb86a0061d..2d2b3585ee9 100644
--- a/fs/ext4/ialloc.c
+++ b/fs/ext4/ialloc.c
@@ -188,7 +188,7 @@ void ext4_free_inode(handle_t *handle, struct inode *inode)
 	struct ext4_group_desc *gdp;
 	struct ext4_super_block *es;
 	struct ext4_sb_info *sbi;
-	int fatal = 0, err, count;
+	int fatal = 0, err, count, cleared;
 	ext4_group_t flex_group;
 
 	if (atomic_read(&inode->i_count) > 1) {
@@ -248,8 +248,10 @@ void ext4_free_inode(handle_t *handle, struct inode *inode)
 		goto error_return;
 
 	/* Ok, now we can actually update the inode bitmaps.. */
-	if (!ext4_clear_bit_atomic(sb_bgl_lock(sbi, block_group),
-					bit, bitmap_bh->b_data))
+	spin_lock(sb_bgl_lock(sbi, block_group));
+	cleared = ext4_clear_bit(bit, bitmap_bh->b_data);
+	spin_unlock(sb_bgl_lock(sbi, block_group));
+	if (!cleared)
 		ext4_error(sb, "ext4_free_inode",
 			   "bit already cleared for inode %lu", ino);
 	else {
@@ -696,6 +698,7 @@ struct inode *ext4_new_inode(handle_t *handle, struct inode *dir, int mode)
 	struct inode *ret;
 	ext4_group_t i;
 	int free = 0;
+	static int once = 1;
 	ext4_group_t flex_group;
 
 	/* Cannot create files in a deleted directory */
@@ -715,6 +718,14 @@ struct inode *ext4_new_inode(handle_t *handle, struct inode *dir, int mode)
 
 	if (sbi->s_log_groups_per_flex) {
 		ret2 = find_group_flex(sb, dir, &group);
+		if (ret2 == -1) {
+			ret2 = find_group_other(sb, dir, &group);
+			if (ret2 == 0 && once)
+				once = 0;
+				printk(KERN_NOTICE "ext4: find_group_flex "
+				       "failed, fallback succeeded dir %lu\n",
+				       dir->i_ino);
+		}
 		goto got_group;
 	}
 
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 03ba20be132..c7fed5b1874 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -47,8 +47,10 @@
 static inline int ext4_begin_ordered_truncate(struct inode *inode,
 					      loff_t new_size)
 {
-	return jbd2_journal_begin_ordered_truncate(&EXT4_I(inode)->jinode,
-						   new_size);
+	return jbd2_journal_begin_ordered_truncate(
+					EXT4_SB(inode->i_sb)->s_journal,
+					&EXT4_I(inode)->jinode,
+					new_size);
 }
 
 static void ext4_invalidatepage(struct page *page, unsigned long offset);
@@ -1366,6 +1368,10 @@ retry:
 		goto out;
 	}
 
+	/* We cannot recurse into the filesystem as the transaction is already
+	 * started */
+	flags |= AOP_FLAG_NOFS;
+
 	page = grab_cache_page_write_begin(mapping, index, flags);
 	if (!page) {
 		ext4_journal_stop(handle);
@@ -1375,7 +1381,7 @@ retry:
 	*pagep = page;
 
 	ret = block_write_begin(file, mapping, pos, len, flags, pagep, fsdata,
-							ext4_get_block);
+				ext4_get_block);
 
 	if (!ret && ext4_should_journal_data(inode)) {
 		ret = walk_page_buffers(handle, page_buffers(page),
@@ -2437,6 +2443,7 @@ static int ext4_da_writepages(struct address_space *mapping,
 	int no_nrwrite_index_update;
 	int pages_written = 0;
 	long pages_skipped;
+	int range_cyclic, cycled = 1, io_done = 0;
 	int needed_blocks, ret = 0, nr_to_writebump = 0;
 	struct ext4_sb_info *sbi = EXT4_SB(mapping->host->i_sb);
 
@@ -2488,9 +2495,15 @@ static int ext4_da_writepages(struct address_space *mapping,
 	if (wbc->range_start == 0 && wbc->range_end == LLONG_MAX)
 		range_whole = 1;
 
-	if (wbc->range_cyclic)
+	range_cyclic = wbc->range_cyclic;
+	if (wbc->range_cyclic) {
 		index = mapping->writeback_index;
-	else
+		if (index)
+			cycled = 0;
+		wbc->range_start = index << PAGE_CACHE_SHIFT;
+		wbc->range_end  = LLONG_MAX;
+		wbc->range_cyclic = 0;
+	} else
 		index = wbc->range_start >> PAGE_CACHE_SHIFT;
 
 	mpd.wbc = wbc;
@@ -2504,6 +2517,7 @@ static int ext4_da_writepages(struct address_space *mapping,
 	wbc->no_nrwrite_index_update = 1;
 	pages_skipped = wbc->pages_skipped;
 
+retry:
 	while (!ret && wbc->nr_to_write > 0) {
 
 		/*
@@ -2530,7 +2544,7 @@ static int ext4_da_writepages(struct address_space *mapping,
 
 		ext4_journal_stop(handle);
 
-		if (mpd.retval == -ENOSPC) {
+		if ((mpd.retval == -ENOSPC) && sbi->s_journal) {
 			/* commit the transaction which would
 			 * free blocks released in the transaction
 			 * and try again
@@ -2546,6 +2560,7 @@ static int ext4_da_writepages(struct address_space *mapping,
 			pages_written += mpd.pages_written;
 			wbc->pages_skipped = pages_skipped;
 			ret = 0;
+			io_done = 1;
 		} else if (wbc->nr_to_write)
 			/*
 			 * There is no more writeout needed
@@ -2554,6 +2569,13 @@ static int ext4_da_writepages(struct address_space *mapping,
 			 */
 			break;
 	}
+	if (!io_done && !cycled) {
+		cycled = 1;
+		index = 0;
+		wbc->range_start = index << PAGE_CACHE_SHIFT;
+		wbc->range_end  = mapping->writeback_index - 1;
+		goto retry;
+	}
 	if (pages_skipped != wbc->pages_skipped)
 		printk(KERN_EMERG "This should not happen leaving %s "
 				"with nr_to_write = %ld ret = %d\n",
@@ -2561,6 +2583,7 @@ static int ext4_da_writepages(struct address_space *mapping,
 
 	/* Update index */
 	index += pages_written;
+	wbc->range_cyclic = range_cyclic;
 	if (wbc->range_cyclic || (range_whole && wbc->nr_to_write > 0))
 		/*
 		 * set the writeback_index so that range_cyclic
@@ -2648,6 +2671,9 @@ retry:
 		ret = PTR_ERR(handle);
 		goto out;
 	}
+	/* We cannot recurse into the filesystem as the transaction is already
+	 * started */
+	flags |= AOP_FLAG_NOFS;
 
 	page = grab_cache_page_write_begin(mapping, index, flags);
 	if (!page) {
diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c
index deba54f6cbe..9f61e62f435 100644
--- a/fs/ext4/mballoc.c
+++ b/fs/ext4/mballoc.c
@@ -1447,7 +1447,7 @@ static void ext4_mb_measure_extent(struct ext4_allocation_context *ac,
 	struct ext4_free_extent *gex = &ac->ac_g_ex;
 
 	BUG_ON(ex->fe_len <= 0);
-	BUG_ON(ex->fe_len >= EXT4_BLOCKS_PER_GROUP(ac->ac_sb));
+	BUG_ON(ex->fe_len > EXT4_BLOCKS_PER_GROUP(ac->ac_sb));
 	BUG_ON(ex->fe_start >= EXT4_BLOCKS_PER_GROUP(ac->ac_sb));
 	BUG_ON(ac->ac_status != AC_STATUS_CONTINUE);
 
@@ -3292,7 +3292,7 @@ ext4_mb_normalize_request(struct ext4_allocation_context *ac,
 	}
 	BUG_ON(start + size <= ac->ac_o_ex.fe_logical &&
 			start > ac->ac_o_ex.fe_logical);
-	BUG_ON(size <= 0 || size >= EXT4_BLOCKS_PER_GROUP(ac->ac_sb));
+	BUG_ON(size <= 0 || size > EXT4_BLOCKS_PER_GROUP(ac->ac_sb));
 
 	/* now prepare goal request */
 
@@ -3589,6 +3589,7 @@ static void ext4_mb_put_pa(struct ext4_allocation_context *ac,
 			struct super_block *sb, struct ext4_prealloc_space *pa)
 {
 	ext4_group_t grp;
+	ext4_fsblk_t grp_blk;
 
 	if (!atomic_dec_and_test(&pa->pa_count) || pa->pa_free != 0)
 		return;
@@ -3603,8 +3604,12 @@ static void ext4_mb_put_pa(struct ext4_allocation_context *ac,
 	pa->pa_deleted = 1;
 	spin_unlock(&pa->pa_lock);
 
-	/* -1 is to protect from crossing allocation group */
-	ext4_get_group_no_and_offset(sb, pa->pa_pstart - 1, &grp, NULL);
+	grp_blk = pa->pa_pstart;
+	/* If linear, pa_pstart may be in the next group when pa is used up */
+	if (pa->pa_linear)
+		grp_blk--;
+
+	ext4_get_group_no_and_offset(sb, grp_blk, &grp, NULL);
 
 	/*
 	 * possible race:
@@ -3693,6 +3698,8 @@ ext4_mb_new_inode_pa(struct ext4_allocation_context *ac)
 	pa->pa_free = pa->pa_len;
 	atomic_set(&pa->pa_count, 1);
 	spin_lock_init(&pa->pa_lock);
+	INIT_LIST_HEAD(&pa->pa_inode_list);
+	INIT_LIST_HEAD(&pa->pa_group_list);
 	pa->pa_deleted = 0;
 	pa->pa_linear = 0;
 
@@ -3755,6 +3762,7 @@ ext4_mb_new_group_pa(struct ext4_allocation_context *ac)
 	atomic_set(&pa->pa_count, 1);
 	spin_lock_init(&pa->pa_lock);
 	INIT_LIST_HEAD(&pa->pa_inode_list);
+	INIT_LIST_HEAD(&pa->pa_group_list);
 	pa->pa_deleted = 0;
 	pa->pa_linear = 1;
 
@@ -4476,23 +4484,26 @@ static int ext4_mb_release_context(struct ext4_allocation_context *ac)
 			pa->pa_free -= ac->ac_b_ex.fe_len;
 			pa->pa_len -= ac->ac_b_ex.fe_len;
 			spin_unlock(&pa->pa_lock);
-			/*
-			 * We want to add the pa to the right bucket.
-			 * Remove it from the list and while adding
-			 * make sure the list to which we are adding
-			 * doesn't grow big.
-			 */
-			if (likely(pa->pa_free)) {
-				spin_lock(pa->pa_obj_lock);
-				list_del_rcu(&pa->pa_inode_list);
-				spin_unlock(pa->pa_obj_lock);
-				ext4_mb_add_n_trim(ac);
-			}
 		}
-		ext4_mb_put_pa(ac, ac->ac_sb, pa);
 	}
 	if (ac->alloc_semp)
 		up_read(ac->alloc_semp);
+	if (pa) {
+		/*
+		 * We want to add the pa to the right bucket.
+		 * Remove it from the list and while adding
+		 * make sure the list to which we are adding
+		 * doesn't grow big.  We need to release
+		 * alloc_semp before calling ext4_mb_add_n_trim()
+		 */
+		if (pa->pa_linear && likely(pa->pa_free)) {
+			spin_lock(pa->pa_obj_lock);
+			list_del_rcu(&pa->pa_inode_list);
+			spin_unlock(pa->pa_obj_lock);
+			ext4_mb_add_n_trim(ac);
+		}
+		ext4_mb_put_pa(ac, ac->ac_sb, pa);
+	}
 	if (ac->ac_bitmap_page)
 		page_cache_release(ac->ac_bitmap_page);
 	if (ac->ac_buddy_page)
diff --git a/fs/ext4/migrate.c b/fs/ext4/migrate.c
index 734abca25e3..fe64d9f7985 100644
--- a/fs/ext4/migrate.c
+++ b/fs/ext4/migrate.c
@@ -481,7 +481,7 @@ int ext4_ext_migrate(struct inode *inode)
 					+ 1);
 	if (IS_ERR(handle)) {
 		retval = PTR_ERR(handle);
-		goto err_out;
+		return retval;
 	}
 	tmp_inode = ext4_new_inode(handle,
 				inode->i_sb->s_root->d_inode,
@@ -489,8 +489,7 @@ int ext4_ext_migrate(struct inode *inode)
 	if (IS_ERR(tmp_inode)) {
 		retval = -ENOMEM;
 		ext4_journal_stop(handle);
-		tmp_inode = NULL;
-		goto err_out;
+		return retval;
 	}
 	i_size_write(tmp_inode, i_size_read(inode));
 	/*
@@ -618,8 +617,7 @@ err_out:
 
 	ext4_journal_stop(handle);
 
-	if (tmp_inode)
-		iput(tmp_inode);
+	iput(tmp_inode);
 
 	return retval;
 }
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index e5f06a5f045..39d1993cfa1 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -3046,14 +3046,17 @@ static void ext4_write_super(struct super_block *sb)
 static int ext4_sync_fs(struct super_block *sb, int wait)
 {
 	int ret = 0;
+	tid_t target;
 
 	trace_mark(ext4_sync_fs, "dev %s wait %d", sb->s_id, wait);
 	sb->s_dirt = 0;
 	if (EXT4_SB(sb)->s_journal) {
-		if (wait)
-			ret = ext4_force_commit(sb);
-		else
- 			jbd2_journal_start_commit(EXT4_SB(sb)->s_journal, NULL);
+		if (jbd2_journal_start_commit(EXT4_SB(sb)->s_journal,
+					      &target)) {
+			if (wait)
+				jbd2_log_wait_commit(EXT4_SB(sb)->s_journal,
+						     target);
+		}
 	} else {
 		ext4_commit_super(sb, EXT4_SB(sb)->s_es, wait);
 	}
@@ -3088,7 +3091,6 @@ static int ext4_freeze(struct super_block *sb)
 
 		/* Journal blocked and flushed, clear needs_recovery flag. */
 		EXT4_CLEAR_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_RECOVER);
-		ext4_commit_super(sb, EXT4_SB(sb)->s_es, 1);
 		error = ext4_commit_super(sb, EXT4_SB(sb)->s_es, 1);
 		if (error)
 			goto out;