10 files changed, 102 insertions, 51 deletions

diff --git a/fs/ext4/balloc.c b/fs/ext4/balloc.c
index 6bba06b09dd1..de9459b4cb94 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);
@@ -684,15 +686,15 @@ ext4_fsblk_t ext4_count_free_blocks(struct super_block *sb)
                 gdp = ext4_get_group_desc(sb, i, NULL);
                 if (!gdp)
                         continue;
-                desc_count += le16_to_cpu(gdp->bg_free_blocks_count);
+                desc_count += ext4_free_blks_count(sb, gdp);
                 brelse(bitmap_bh);
                 bitmap_bh = ext4_read_block_bitmap(sb, i);
                 if (bitmap_bh == NULL)
                         continue;
 
                 x = ext4_count_free(bitmap_bh, sb->s_blocksize);
-                printk(KERN_DEBUG "group %lu: stored = %d, counted = %u\n",
-                        i, le16_to_cpu(gdp->bg_free_blocks_count), x);
+                printk(KERN_DEBUG "group %u: stored = %d, counted = %u\n",
+                        i, ext4_free_blks_count(sb, gdp), x);
                 bitmap_count += x;
         }
         brelse(bitmap_bh);
diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index c668e4377d76..b0c87dce66a3 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;
 }
@@ -1206,8 +1206,11 @@ static inline void ext4_r_blocks_count_set(struct ext4_super_block *es,
 
 static inline loff_t ext4_isize(struct ext4_inode *raw_inode)
 {
-        return ((loff_t)le32_to_cpu(raw_inode->i_size_high) << 32) |
-                le32_to_cpu(raw_inode->i_size_lo);
+        if (S_ISREG(le16_to_cpu(raw_inode->i_mode)))
+                return ((loff_t)le32_to_cpu(raw_inode->i_size_high) << 32) |
+                        le32_to_cpu(raw_inode->i_size_lo);
+        else
+                return (loff_t) le32_to_cpu(raw_inode->i_size_lo);
 }
 
 static inline void ext4_isize_set(struct ext4_inode *raw_inode, loff_t i_size)
diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c
index 54bf0623a9ae..e2eab196875f 100644
--- a/fs/ext4/extents.c
+++ b/fs/ext4/extents.c
@@ -3048,7 +3048,7 @@ retry:
                         WARN_ON(ret <= 0);
                         printk(KERN_ERR "%s: ext4_ext_get_blocks "
                                     "returned error inode#%lu, block=%u, "
-                                    "max_blocks=%lu", __func__,
+                                    "max_blocks=%u", __func__,
                                     inode->i_ino, block, max_blocks);
 #endif
                         ext4_mark_inode_dirty(handle, inode);
diff --git a/fs/ext4/ialloc.c b/fs/ext4/ialloc.c
index 4fb86a0061d0..f18a919be70b 100644
--- a/fs/ext4/ialloc.c
+++ b/fs/ext4/ialloc.c
@@ -715,6 +715,13 @@ 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 && printk_ratelimit())
+                                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 a6444cee0c7e..c7fed5b18745 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);
@@ -360,9 +362,9 @@ static int ext4_block_to_path(struct inode *inode,
                 final = ptrs;
         } else {
                 ext4_warning(inode->i_sb, "ext4_block_to_path",
-                                "block %lu > max",
+                                "block %lu > max in inode %lu",
                                 i_block + direct_blocks +
-                                indirect_blocks + double_blocks);
+                                indirect_blocks + double_blocks, inode->i_ino);
         }
         if (boundary)
                 *boundary = final - 1 - (i_block & (ptrs - 1));
@@ -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) {
@@ -2821,9 +2847,6 @@ static sector_t ext4_bmap(struct address_space *mapping, sector_t block)
                 filemap_write_and_wait(mapping);
         }
 
-        BUG_ON(!EXT4_JOURNAL(inode) &&
-               EXT4_I(inode)->i_state & EXT4_STATE_JDATA);
-
         if (EXT4_JOURNAL(inode) && EXT4_I(inode)->i_state & EXT4_STATE_JDATA) {
                 /*
                  * This is a REALLY heavyweight approach, but the use of
@@ -3622,7 +3645,7 @@ static void ext4_free_data(handle_t *handle, struct inode *inode,
                  * block pointed to itself, it would have been detached when
                  * the block was cleared. Check for this instead of OOPSing.
                  */
-                if (bh2jh(this_bh))
+                if ((EXT4_JOURNAL(inode) == NULL) || bh2jh(this_bh))
                         ext4_handle_dirty_metadata(handle, inode, this_bh);
                 else
                         ext4_error(inode->i_sb, __func__,
diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c
index 918aec0c8a11..4415beeb0b62 100644
--- a/fs/ext4/mballoc.c
+++ b/fs/ext4/mballoc.c
@@ -3025,7 +3025,7 @@ ext4_mb_mark_diskspace_used(struct ext4_allocation_context *ac,
                 goto out_err;
 
         ext4_debug("using block group %u(%d)\n", ac->ac_b_ex.fe_group,
-                        gdp->bg_free_blocks_count);
+                        ext4_free_blks_count(sb, gdp));
 
         err = ext4_journal_get_write_access(handle, gdp_bh);
         if (err)
@@ -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)
diff --git a/fs/ext4/migrate.c b/fs/ext4/migrate.c
index 734abca25e35..fe64d9f79852 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/namei.c b/fs/ext4/namei.c
index fec0b4c2f5f1..ba702bd7910d 100644
--- a/fs/ext4/namei.c
+++ b/fs/ext4/namei.c
@@ -1368,7 +1368,7 @@ static int make_indexed_dir(handle_t *handle, struct dentry *dentry,
         struct fake_dirent *fde;
 
         blocksize =  dir->i_sb->s_blocksize;
-        dxtrace(printk(KERN_DEBUG "Creating index\n"));
+        dxtrace(printk(KERN_DEBUG "Creating index: inode %lu\n", dir->i_ino));
         retval = ext4_journal_get_write_access(handle, bh);
         if (retval) {
                 ext4_std_error(dir->i_sb, retval);
@@ -1377,6 +1377,20 @@ static int make_indexed_dir(handle_t *handle, struct dentry *dentry,
         }
         root = (struct dx_root *) bh->b_data;
 
+        /* The 0th block becomes the root, move the dirents out */
+        fde = &root->dotdot;
+        de = (struct ext4_dir_entry_2 *)((char *)fde +
+                ext4_rec_len_from_disk(fde->rec_len));
+        if ((char *) de >= (((char *) root) + blocksize)) {
+                ext4_error(dir->i_sb, __func__,
+                           "invalid rec_len for '..' in inode %lu",
+                           dir->i_ino);
+                brelse(bh);
+                return -EIO;
+        }
+        len = ((char *) root) + blocksize - (char *) de;
+
+        /* Allocate new block for the 0th block's dirents */
         bh2 = ext4_append(handle, dir, &block, &retval);
         if (!(bh2)) {
                 brelse(bh);
@@ -1385,11 +1399,6 @@ static int make_indexed_dir(handle_t *handle, struct dentry *dentry,
         EXT4_I(dir)->i_flags |= EXT4_INDEX_FL;
         data1 = bh2->b_data;
 
-        /* The 0th block becomes the root, move the dirents out */
-        fde = &root->dotdot;
-        de = (struct ext4_dir_entry_2 *)((char *)fde +
-                ext4_rec_len_from_disk(fde->rec_len));
-        len = ((char *) root) + blocksize - (char *) de;
         memcpy (data1, de, len);
         de = (struct ext4_dir_entry_2 *) data1;
         top = data1 + len;
diff --git a/fs/ext4/resize.c b/fs/ext4/resize.c
index c328be5d6885..c06886abd658 100644
--- a/fs/ext4/resize.c
+++ b/fs/ext4/resize.c
@@ -861,12 +861,13 @@ int ext4_group_add(struct super_block *sb, struct ext4_new_group_data *input)
         gdp = (struct ext4_group_desc *)((char *)primary->b_data +
                                          gdb_off * EXT4_DESC_SIZE(sb));
 
+        memset(gdp, 0, EXT4_DESC_SIZE(sb));
         ext4_block_bitmap_set(sb, gdp, input->block_bitmap); /* LV FIXME */
         ext4_inode_bitmap_set(sb, gdp, input->inode_bitmap); /* LV FIXME */
         ext4_inode_table_set(sb, gdp, input->inode_table); /* LV FIXME */
         ext4_free_blks_set(sb, gdp, input->free_blocks_count);
         ext4_free_inodes_set(sb, gdp, EXT4_INODES_PER_GROUP(sb));
-        gdp->bg_flags |= cpu_to_le16(EXT4_BG_INODE_ZEROED);
+        gdp->bg_flags = cpu_to_le16(EXT4_BG_INODE_ZEROED);
         gdp->bg_checksum = ext4_group_desc_csum(sbi, input->group, gdp);
 
         /*
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index e5f06a5f045e..39d1993cfa13 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;