Merge commit 'ext4/next'

11 files changed, 77 insertions, 63 deletions

diff --git a/fs/ext4/balloc.c b/fs/ext4/balloc.c
index 38b85fbb40c5..046f638146e1 100644
--- a/fs/ext4/balloc.c
+++ b/fs/ext4/balloc.c
@@ -55,7 +55,8 @@ static int ext4_block_in_group(struct super_block *sb, ext4_fsblk_t block,
 }
 
 static int ext4_group_used_meta_blocks(struct super_block *sb,
-				ext4_group_t block_group)
+				       ext4_group_t block_group,
+				       struct ext4_group_desc *gdp)
 {
 	ext4_fsblk_t tmp;
 	struct ext4_sb_info *sbi = EXT4_SB(sb);
@@ -63,10 +64,6 @@ static int ext4_group_used_meta_blocks(struct super_block *sb,
 	int used_blocks = sbi->s_itb_per_group + 2;
 
 	if (EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_FLEX_BG)) {
-		struct ext4_group_desc *gdp;
-		struct buffer_head *bh;
-
-		gdp = ext4_get_group_desc(sb, block_group, &bh);
 		if (!ext4_block_in_group(sb, ext4_block_bitmap(sb, gdp),
 					block_group))
 			used_blocks--;
@@ -177,7 +174,7 @@ unsigned ext4_init_block_bitmap(struct super_block *sb, struct buffer_head *bh,
 		 */
 		mark_bitmap_end(group_blocks, sb->s_blocksize * 8, bh->b_data);
 	}
-	return free_blocks - ext4_group_used_meta_blocks(sb, block_group);
+	return free_blocks - ext4_group_used_meta_blocks(sb, block_group, gdp);
 }
 
 
diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index ae7590fac9de..0db01421da3e 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -33,14 +33,6 @@
 #undef EXT4FS_DEBUG
 
 /*
- * Define EXT4_RESERVATION to reserve data blocks for expanding files
- */
-#define EXT4_DEFAULT_RESERVE_BLOCKS	8
-/*max window size: 1024(direct blocks) + 3([t,d]indirect blocks) */
-#define EXT4_MAX_RESERVE_BLOCKS		1027
-#define EXT4_RESERVE_WINDOW_NOT_ALLOCATED 0
-
-/*
  * Debug code
  */
 #ifdef EXT4FS_DEBUG
@@ -54,8 +46,6 @@
 #define ext4_debug(f, a...)	do {} while (0)
 #endif
 
-#define EXT4_MULTIBLOCK_ALLOCATOR	1
-
 /* prefer goal again. length */
 #define EXT4_MB_HINT_MERGE		1
 /* blocks already reserved */
@@ -869,7 +859,7 @@ 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/ext4_i.h b/fs/ext4/ext4_i.h
index e69acc16f5c4..2d516c0a22af 100644
--- a/fs/ext4/ext4_i.h
+++ b/fs/ext4/ext4_i.h
@@ -33,9 +33,6 @@ typedef __u32 ext4_lblk_t;
 /* data type for block group number */
 typedef unsigned int ext4_group_t;
 
-#define rsv_start rsv_window._rsv_start
-#define rsv_end rsv_window._rsv_end
-
 /*
  * storage for cached extent
  */
diff --git a/fs/ext4/ext4_sb.h b/fs/ext4/ext4_sb.h
index 039b6ea1a042..e318f486cc24 100644
--- a/fs/ext4/ext4_sb.h
+++ b/fs/ext4/ext4_sb.h
@@ -65,10 +65,6 @@ struct ext4_sb_info {
 	struct blockgroup_lock s_blockgroup_lock;
 	struct proc_dir_entry *s_proc;
 
-	/* root of the per fs reservation window tree */
-	spinlock_t s_rsv_window_lock;
-	struct rb_root s_rsv_window_root;
-
 	/* Journaling */
 	struct inode *s_journal_inode;
 	struct journal_s *s_journal;
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 43e5e7798635..e78551a6dfdd 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);
diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c
index 8c6ad3b84125..bf4384bfbca5 100644
--- a/fs/ext4/mballoc.c
+++ b/fs/ext4/mballoc.c
@@ -4479,23 +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)
diff --git a/fs/ext4/mballoc.h b/fs/ext4/mballoc.h
index 10a2921baf14..7acf5ef24537 100644
--- a/fs/ext4/mballoc.h
+++ b/fs/ext4/mballoc.h
@@ -247,7 +247,6 @@ static inline void ext4_mb_store_history(struct ext4_allocation_context *ac)
 
 #define in_range(b, first, len)	((b) >= (first) && (b) <= (first) + (len) - 1)
 
-struct buffer_head *read_block_bitmap(struct super_block *, ext4_group_t);
 static inline ext4_fsblk_t ext4_grp_offs_to_block(struct super_block *sb,
 					struct ext4_free_extent *fex)
 {
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index a7b8cb1047c9..1a92bf42cbf4 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -3048,14 +3048,17 @@ 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);
 	}
diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c
index eb343008eded..58144102bf25 100644
--- 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);
diff --git a/fs/jbd2/transaction.c b/fs/jbd2/transaction.c
index 46b4e347ed7d..28ce21d8598e 100644
--- 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);
diff --git a/fs/ocfs2/journal.h b/fs/ocfs2/journal.h
index c4847caf4cc1..21601ee3f25a 100644
--- a/fs/ocfs2/journal.h
+++ b/fs/ocfs2/journal.h
@@ -524,8 +524,10 @@ 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 */