Merge branch 'for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tytso/ext4

* 'for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tytso/ext4: ext4: Fix NULL dereference in ext4_ext_migrate()'s error handling ext4: Implement range_cyclic in ext4_da_writepages instead of write_cache_pages ext4: Initialize preallocation list_head's properly ext4: Fix lockdep warning ext4: Fix to read empty directory blocks correctly in 64k jbd2: Avoid possible NULL dereference in jbd2_journal_begin_ordered_truncate() Revert "ext4: wait on all pending commits in ext4_sync_fs()" jbd2: Fix return value of jbd2_journal_start_commit()
2009-02-17 14:05:05 -08:00 · 2009-02-17 14:05:05 -08:00 · 3512a79dbc
--- 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;
 }
--- 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);
@ -2437,6 +2439,7 @@ 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 +2491,15 @@ 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 +2513,7 @@ 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) {

 		/*
@ -2546,6 +2556,7 @@ 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 +2565,13 @@ 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 +2579,7 @@ 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
--- a/fs/ext4/mballoc.c
+++ b/fs/ext4/mballoc.c
@ -3693,6 +3693,8 @@ 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 +3757,7 @@ 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 +4479,26 @@ 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)
--- 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;
 }
--- 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);
 	}
--- a/fs/jbd2/journal.c
+++ b/fs/jbd2/journal.c
@ -450,7 +450,7 @@ int __jbd2_log_space_left(journal_t *journal)
 }

 /*
- * Called under j_state_lock.  Returns true if a transaction was started.
+ * Called under j_state_lock.  Returns true if a transaction commit was started.
 */
 int __jbd2_log_start_commit(journal_t *journal, tid_t target)
 {
@ -518,7 +518,8 @@ int jbd2_journal_force_commit_nested(journal_t *journal)

 /*
 * Start a commit of the current running transaction (if any).  Returns true
- * if a transaction was started, and fills its tid in at *ptid
+ * if a transaction is going to be committed (or is currently already
+ * committing), and fills its tid in at *ptid
 */
 int jbd2_journal_start_commit(journal_t *journal, tid_t *ptid)
 {
@ -528,15 +529,19 @@ int jbd2_journal_start_commit(journal_t *journal, tid_t *ptid)
 	if (journal->j_running_transaction) {
 		tid_t tid = journal->j_running_transaction->t_tid;

-		ret = __jbd2_log_start_commit(journal, tid);
-		if (ret && ptid)
+		__jbd2_log_start_commit(journal, tid);
+		/* There's a running transaction and we've just made sure
+		 * it's commit has been scheduled. */
+		if (ptid)
 			*ptid = tid;
-	} else if (journal->j_committing_transaction && ptid) {
+		ret = 1;
+	} else if (journal->j_committing_transaction) {
 		/*
 		 * If ext3_write_super() recently started a commit, then we
 		 * have to wait for completion of that transaction
 		 */
-		*ptid = journal->j_committing_transaction->t_tid;
+		if (ptid)
+			*ptid = journal->j_committing_transaction->t_tid;
 		ret = 1;
 	}
 	spin_unlock(&journal->j_state_lock);
--- a/fs/jbd2/transaction.c
+++ b/fs/jbd2/transaction.c
@ -2129,26 +2129,46 @@ done:
 }

 /*
- * This function must be called when inode is journaled in ordered mode
- * before truncation happens. It starts writeout of truncated part in
- * case it is in the committing transaction so that we stand to ordered
- * mode consistency guarantees.
+ * File truncate and transaction commit interact with each other in a
+ * non-trivial way.  If a transaction writing data block A is
+ * committing, we cannot discard the data by truncate until we have
+ * written them.  Otherwise if we crashed after the transaction with
+ * write has committed but before the transaction with truncate has
+ * committed, we could see stale data in block A.  This function is a
+ * helper to solve this problem.  It starts writeout of the truncated
+ * part in case it is in the committing transaction.
+ *
+ * Filesystem code must call this function when inode is journaled in
+ * ordered mode before truncation happens and after the inode has been
+ * placed on orphan list with the new inode size. The second condition
+ * avoids the race that someone writes new data and we start
+ * committing the transaction after this function has been called but
+ * before a transaction for truncate is started (and furthermore it
+ * allows us to optimize the case where the addition to orphan list
+ * happens in the same transaction as write --- we don't have to write
+ * any data in such case).
 */
-int jbd2_journal_begin_ordered_truncate(struct jbd2_inode *inode,
+int jbd2_journal_begin_ordered_truncate(journal_t *journal,
+					struct jbd2_inode *jinode,
 					loff_t new_size)
 {
-	journal_t *journal;
-	transaction_t *commit_trans;
+	transaction_t *inode_trans, *commit_trans;
 	int ret = 0;

-	if (!inode->i_transaction && !inode->i_next_transaction)
+	/* This is a quick check to avoid locking if not necessary */
+	if (!jinode->i_transaction)
 		goto out;
-	journal = inode->i_transaction->t_journal;
+	/* Locks are here just to force reading of recent values, it is
+	 * enough that the transaction was not committing before we started
+	 * a transaction adding the inode to orphan list */
 	spin_lock(&journal->j_state_lock);
 	commit_trans = journal->j_committing_transaction;
 	spin_unlock(&journal->j_state_lock);
-	if (inode->i_transaction == commit_trans) {
-		ret = filemap_fdatawrite_range(inode->i_vfs_inode->i_mapping,
+	spin_lock(&journal->j_list_lock);
+	inode_trans = jinode->i_transaction;
+	spin_unlock(&journal->j_list_lock);
+	if (inode_trans == commit_trans) {
+		ret = filemap_fdatawrite_range(jinode->i_vfs_inode->i_mapping,
 			new_size, LLONG_MAX);
 		if (ret)
 			jbd2_journal_abort(journal, ret);
--- a/fs/ocfs2/journal.h
+++ b/fs/ocfs2/journal.h
@ -513,8 +513,10 @@ static inline int ocfs2_jbd2_file_inode(handle_t *handle, struct inode *inode)
 static inline int ocfs2_begin_ordered_truncate(struct inode *inode,
 					       loff_t new_size)
 {
-	return jbd2_journal_begin_ordered_truncate(&OCFS2_I(inode)->ip_jinode,
-						   new_size);
+	return jbd2_journal_begin_ordered_truncate(
+				OCFS2_SB(inode->i_sb)->journal->j_journal,
+				&OCFS2_I(inode)->ip_jinode,
+				new_size);
 }

 #endif /* OCFS2_JOURNAL_H */
--- a/include/linux/jbd2.h
+++ b/include/linux/jbd2.h
@ -1150,7 +1150,8 @@ extern int	   jbd2_journal_clear_err  (journal_t *);
 extern int	   jbd2_journal_bmap(journal_t *, unsigned long, unsigned long long *);
 extern int	   jbd2_journal_force_commit(journal_t *);
 extern int	   jbd2_journal_file_inode(handle_t *handle, struct jbd2_inode *inode);
-extern int	   jbd2_journal_begin_ordered_truncate(struct jbd2_inode *inode, loff_t new_size);
+extern int	   jbd2_journal_begin_ordered_truncate(journal_t *journal,
+				struct jbd2_inode *inode, loff_t new_size);
 extern void	   jbd2_journal_init_jbd_inode(struct jbd2_inode *jinode, struct inode *inode);
 extern void	   jbd2_journal_release_jbd_inode(journal_t *journal, struct jbd2_inode *jinode);