7 files changed, 69 insertions, 30 deletions

diff --git a/fs/ext4/ialloc.c b/fs/ext4/ialloc.c
index fe34d74cfb19..2a117e286e54 100644
--- a/fs/ext4/ialloc.c
+++ b/fs/ext4/ialloc.c
@@ -718,6 +718,8 @@ got:
                         gdp->bg_flags &= cpu_to_le16(~EXT4_BG_BLOCK_UNINIT);
                         free = ext4_free_blocks_after_init(sb, group, gdp);
                         gdp->bg_free_blocks_count = cpu_to_le16(free);
+                        gdp->bg_checksum = ext4_group_desc_csum(sbi, group,
+                                                                gdp);
                 }
                 spin_unlock(sb_bgl_lock(sbi, group));
 
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 8dbf6953845b..be21a5ae33cb 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -2329,6 +2329,8 @@ static int ext4_da_writepage(struct page *page,
                         unlock_page(page);
                         return 0;
                 }
+                /* now mark the buffer_heads as dirty and uptodate */
+                block_commit_write(page, 0, PAGE_CACHE_SIZE);
         }
 
         if (test_opt(inode->i_sb, NOBH) && ext4_should_writeback_data(inode))
@@ -4580,9 +4582,10 @@ static int ext4_indirect_trans_blocks(struct inode *inode, int nrblocks,
 static int ext4_index_trans_blocks(struct inode *inode, int nrblocks, int chunk)
 {
         if (!(EXT4_I(inode)->i_flags & EXT4_EXTENTS_FL))
-                return ext4_indirect_trans_blocks(inode, nrblocks, 0);
-        return ext4_ext_index_trans_blocks(inode, nrblocks, 0);
+                return ext4_indirect_trans_blocks(inode, nrblocks, chunk);
+        return ext4_ext_index_trans_blocks(inode, nrblocks, chunk);
 }
+
 /*
  * Account for index blocks, block groups bitmaps and block group
  * descriptor blocks if modify datablocks and index blocks
diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c
index dfe17a134052..444ad998f72e 100644
--- a/fs/ext4/mballoc.c
+++ b/fs/ext4/mballoc.c
@@ -4441,6 +4441,7 @@ ext4_mb_free_metadata(handle_t *handle, struct ext4_buddy *e4b,
                 else if (block >= (entry->start_blk + entry->count))
                         n = &(*n)->rb_right;
                 else {
+                        ext4_unlock_group(sb, group);
                         ext4_error(sb, __func__,
                             "Double free of blocks %d (%d %d)\n",
                             block, entry->start_blk, entry->count);
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index 994859df010e..e4a241c65dbe 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -1458,9 +1458,8 @@ static int ext4_fill_flex_info(struct super_block *sb)
 
         /* We allocate both existing and potentially added groups */
         flex_group_count = ((sbi->s_groups_count + groups_per_flex - 1) +
-                            ((sbi->s_es->s_reserved_gdt_blocks +1 ) <<
-                              EXT4_DESC_PER_BLOCK_BITS(sb))) /
-                           groups_per_flex;
+                        ((le16_to_cpu(sbi->s_es->s_reserved_gdt_blocks) + 1) <<
+                              EXT4_DESC_PER_BLOCK_BITS(sb))) / groups_per_flex;
         sbi->s_flex_groups = kzalloc(flex_group_count *
                                      sizeof(struct flex_groups), GFP_KERNEL);
         if (sbi->s_flex_groups == NULL) {
@@ -2885,12 +2884,9 @@ int ext4_force_commit(struct super_block *sb)
 /*
  * Ext4 always journals updates to the superblock itself, so we don't
  * have to propagate any other updates to the superblock on disk at this
- * point.  Just start an async writeback to get the buffers on their way
- * to the disk.
- *
- * This implicitly triggers the writebehind on sync().
+ * point.  (We can probably nuke this function altogether, and remove
+ * any mention to sb->s_dirt in all of fs/ext4; eventual cleanup...)
  */
-
 static void ext4_write_super(struct super_block *sb)
 {
         if (mutex_trylock(&sb->s_lock) != 0)
@@ -2900,15 +2896,15 @@ static void ext4_write_super(struct super_block *sb)
 
 static int ext4_sync_fs(struct super_block *sb, int wait)
 {
-        tid_t target;
+        int ret = 0;
 
         trace_mark(ext4_sync_fs, "dev %s wait %d", sb->s_id, wait);
         sb->s_dirt = 0;
-        if (jbd2_journal_start_commit(EXT4_SB(sb)->s_journal, &target)) {
-                if (wait)
-                        jbd2_log_wait_commit(EXT4_SB(sb)->s_journal, target);
-        }
-        return 0;
+        if (wait)
+                ret = ext4_force_commit(sb);
+        else
+                jbd2_journal_start_commit(EXT4_SB(sb)->s_journal, NULL);
+        return ret;
 }
 
 /*
diff --git a/fs/jbd/checkpoint.c b/fs/jbd/checkpoint.c
index 1bd8d4acc6f2..61f32f3868cd 100644
--- a/fs/jbd/checkpoint.c
+++ b/fs/jbd/checkpoint.c
@@ -115,7 +115,7 @@ static int __try_to_free_cp_buf(struct journal_head *jh)
  */
 void __log_wait_for_space(journal_t *journal)
 {
-        int nblocks;
+        int nblocks, space_left;
         assert_spin_locked(&journal->j_state_lock);
 
         nblocks = jbd_space_needed(journal);
@@ -128,25 +128,42 @@ void __log_wait_for_space(journal_t *journal)
                 /*
                  * Test again, another process may have checkpointed while we
                  * were waiting for the checkpoint lock. If there are no
-                 * outstanding transactions there is nothing to checkpoint and
-                 * we can't make progress. Abort the journal in this case.
+                 * transactions ready to be checkpointed, try to recover
+                 * journal space by calling cleanup_journal_tail(), and if
+                 * that doesn't work, by waiting for the currently committing
+                 * transaction to complete.  If there is absolutely no way
+                 * to make progress, this is either a BUG or corrupted
+                 * filesystem, so abort the journal and leave a stack
+                 * trace for forensic evidence.
                  */
                 spin_lock(&journal->j_state_lock);
                 spin_lock(&journal->j_list_lock);
                 nblocks = jbd_space_needed(journal);
-                if (__log_space_left(journal) < nblocks) {
+                space_left = __log_space_left(journal);
+                if (space_left < nblocks) {
                         int chkpt = journal->j_checkpoint_transactions != NULL;
+                        tid_t tid = 0;
 
+                        if (journal->j_committing_transaction)
+                                tid = journal->j_committing_transaction->t_tid;
                         spin_unlock(&journal->j_list_lock);
                         spin_unlock(&journal->j_state_lock);
                         if (chkpt) {
                                 log_do_checkpoint(journal);
+                        } else if (cleanup_journal_tail(journal) == 0) {
+                                /* We were able to recover space; yay! */
+                                ;
+                        } else if (tid) {
+                                log_wait_commit(journal, tid);
                         } else {
-                                printk(KERN_ERR "%s: no transactions\n",
-                                       __func__);
+                                printk(KERN_ERR "%s: needed %d blocks and "
+                                       "only had %d space available\n",
+                                       __func__, nblocks, space_left);
+                                printk(KERN_ERR "%s: no way to get more "
+                                       "journal space\n", __func__);
+                                WARN_ON(1);
                                 journal_abort(journal, 0);
                         }
-
                         spin_lock(&journal->j_state_lock);
                 } else {
                         spin_unlock(&journal->j_list_lock);
diff --git a/fs/jbd2/checkpoint.c b/fs/jbd2/checkpoint.c
index 9203c3332f17..9497718fe920 100644
--- a/fs/jbd2/checkpoint.c
+++ b/fs/jbd2/checkpoint.c
@@ -116,7 +116,7 @@ static int __try_to_free_cp_buf(struct journal_head *jh)
  */
 void __jbd2_log_wait_for_space(journal_t *journal)
 {
-        int nblocks;
+        int nblocks, space_left;
         assert_spin_locked(&journal->j_state_lock);
 
         nblocks = jbd_space_needed(journal);
@@ -129,25 +129,43 @@ void __jbd2_log_wait_for_space(journal_t *journal)
                 /*
                  * Test again, another process may have checkpointed while we
                  * were waiting for the checkpoint lock. If there are no
-                 * outstanding transactions there is nothing to checkpoint and
-                 * we can't make progress. Abort the journal in this case.
+                 * transactions ready to be checkpointed, try to recover
+                 * journal space by calling cleanup_journal_tail(), and if
+                 * that doesn't work, by waiting for the currently committing
+                 * transaction to complete.  If there is absolutely no way
+                 * to make progress, this is either a BUG or corrupted
+                 * filesystem, so abort the journal and leave a stack
+                 * trace for forensic evidence.
                  */
                 spin_lock(&journal->j_state_lock);
                 spin_lock(&journal->j_list_lock);
                 nblocks = jbd_space_needed(journal);
-                if (__jbd2_log_space_left(journal) < nblocks) {
+                space_left = __jbd2_log_space_left(journal);
+                if (space_left < nblocks) {
                         int chkpt = journal->j_checkpoint_transactions != NULL;
+                        tid_t tid = 0;
 
+                        if (journal->j_committing_transaction)
+                                tid = journal->j_committing_transaction->t_tid;
                         spin_unlock(&journal->j_list_lock);
                         spin_unlock(&journal->j_state_lock);
                         if (chkpt) {
                                 jbd2_log_do_checkpoint(journal);
+                        } else if (jbd2_cleanup_journal_tail(journal) == 0) {
+                                /* We were able to recover space; yay! */
+                                ;
+                        } else if (tid) {
+                                jbd2_log_wait_commit(journal, tid);
                         } else {
-                                printk(KERN_ERR "%s: no transactions\n",
-                                       __func__);
+                                printk(KERN_ERR "%s: needed %d blocks and "
+                                       "only had %d space available\n",
+                                       __func__, nblocks, space_left);
+                                printk(KERN_ERR "%s: no way to get more "
+                                       "journal space in %s\n", __func__,
+                                       journal->j_devname);
+                                WARN_ON(1);
                                 jbd2_journal_abort(journal, 0);
                         }
-
                         spin_lock(&journal->j_state_lock);
                 } else {
                         spin_unlock(&journal->j_list_lock);
diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c
index 783de118de92..e70d657a19f8 100644
--- a/fs/jbd2/journal.c
+++ b/fs/jbd2/journal.c
@@ -1089,6 +1089,7 @@ journal_t * jbd2_journal_init_inode (struct inode *inode)
         if (!journal->j_wbuf) {
                 printk(KERN_ERR "%s: Cant allocate bhs for commit thread\n",
                         __func__);
+                jbd2_stats_proc_exit(journal);
                 kfree(journal);
                 return NULL;
         }
@@ -1098,6 +1099,7 @@ journal_t * jbd2_journal_init_inode (struct inode *inode)
         if (err) {
                 printk(KERN_ERR "%s: Cannnot locate journal superblock\n",
                        __func__);
+                jbd2_stats_proc_exit(journal);
                 kfree(journal);
                 return NULL;
         }