1 files changed, 161 insertions, 95 deletions

diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 8ca2763df091..59fbbe899acc 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -191,6 +191,7 @@ static int ext4_journal_test_restart(handle_t *handle, struct inode *inode)
 void ext4_delete_inode (struct inode * inode)
 {
         handle_t *handle;
+        int err;
 
         if (ext4_should_order_data(inode))
                 ext4_begin_ordered_truncate(inode, 0);
@@ -199,8 +200,9 @@ void ext4_delete_inode (struct inode * inode)
         if (is_bad_inode(inode))
                 goto no_delete;
 
-        handle = start_transaction(inode);
+        handle = ext4_journal_start(inode, blocks_for_truncate(inode)+3);
         if (IS_ERR(handle)) {
+                ext4_std_error(inode->i_sb, PTR_ERR(handle));
                 /*
                  * If we're going to skip the normal cleanup, we still need to
                  * make sure that the in-core orphan linked list is properly
@@ -213,8 +215,34 @@ void ext4_delete_inode (struct inode * inode)
         if (IS_SYNC(inode))
                 handle->h_sync = 1;
         inode->i_size = 0;
+        err = ext4_mark_inode_dirty(handle, inode);
+        if (err) {
+                ext4_warning(inode->i_sb, __func__,
+                             "couldn't mark inode dirty (err %d)", err);
+                goto stop_handle;
+        }
         if (inode->i_blocks)
                 ext4_truncate(inode);
+
+        /*
+         * ext4_ext_truncate() doesn't reserve any slop when it
+         * restarts journal transactions; therefore there may not be
+         * enough credits left in the handle to remove the inode from
+         * the orphan list and set the dtime field.
+         */
+        if (handle->h_buffer_credits < 3) {
+                err = ext4_journal_extend(handle, 3);
+                if (err > 0)
+                        err = ext4_journal_restart(handle, 3);
+                if (err != 0) {
+                        ext4_warning(inode->i_sb, __func__,
+                                     "couldn't extend journal (err %d)", err);
+                stop_handle:
+                        ext4_journal_stop(handle);
+                        goto no_delete;
+                }
+        }
+
         /*
          * Kill off the orphan record which ext4_truncate created.
          * AKPM: I think this can be inside the above `if'.
@@ -952,6 +980,67 @@ out:
         return err;
 }
 
+/*
+ * Calculate the number of metadata blocks need to reserve
+ * to allocate @blocks for non extent file based file
+ */
+static int ext4_indirect_calc_metadata_amount(struct inode *inode, int blocks)
+{
+        int icap = EXT4_ADDR_PER_BLOCK(inode->i_sb);
+        int ind_blks, dind_blks, tind_blks;
+
+        /* number of new indirect blocks needed */
+        ind_blks = (blocks + icap - 1) / icap;
+
+        dind_blks = (ind_blks + icap - 1) / icap;
+
+        tind_blks = 1;
+
+        return ind_blks + dind_blks + tind_blks;
+}
+
+/*
+ * Calculate the number of metadata blocks need to reserve
+ * to allocate given number of blocks
+ */
+static int ext4_calc_metadata_amount(struct inode *inode, int blocks)
+{
+        if (EXT4_I(inode)->i_flags & EXT4_EXTENTS_FL)
+                return ext4_ext_calc_metadata_amount(inode, blocks);
+
+        return ext4_indirect_calc_metadata_amount(inode, blocks);
+}
+
+static void ext4_da_update_reserve_space(struct inode *inode, int used)
+{
+        struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
+        int total, mdb, mdb_free;
+
+        spin_lock(&EXT4_I(inode)->i_block_reservation_lock);
+        /* recalculate the number of metablocks still need to be reserved */
+        total = EXT4_I(inode)->i_reserved_data_blocks - used;
+        mdb = ext4_calc_metadata_amount(inode, total);
+
+        /* figure out how many metablocks to release */
+        BUG_ON(mdb > EXT4_I(inode)->i_reserved_meta_blocks);
+        mdb_free = EXT4_I(inode)->i_reserved_meta_blocks - mdb;
+
+        /* Account for allocated meta_blocks */
+        mdb_free -= EXT4_I(inode)->i_allocated_meta_blocks;
+
+        /* update fs free blocks counter for truncate case */
+        percpu_counter_add(&sbi->s_freeblocks_counter, mdb_free);
+
+        /* update per-inode reservations */
+        BUG_ON(used  > EXT4_I(inode)->i_reserved_data_blocks);
+        EXT4_I(inode)->i_reserved_data_blocks -= used;
+
+        BUG_ON(mdb > EXT4_I(inode)->i_reserved_meta_blocks);
+        EXT4_I(inode)->i_reserved_meta_blocks = mdb;
+        EXT4_I(inode)->i_allocated_meta_blocks = 0;
+        spin_unlock(&EXT4_I(inode)->i_block_reservation_lock);
+}
+
 /* Maximum number of blocks we map for direct IO at once. */
 #define DIO_MAX_BLOCKS 4096
 /*
@@ -965,10 +1054,9 @@ out:
 
 
 /*
+ * The ext4_get_blocks_wrap() function try to look up the requested blocks,
+ * and returns if the blocks are already mapped.
  *
- *
- * ext4_ext4 get_block() wrapper function
- * It will do a look up first, and returns if the blocks already mapped.
  * Otherwise it takes the write lock of the i_data_sem and allocate blocks
  * and store the allocated blocks in the result buffer head and mark it
  * mapped.
@@ -1069,7 +1157,7 @@ int ext4_get_blocks_wrap(handle_t *handle, struct inode *inode, sector_t block,
                  * which were deferred till now
                  */
                 if ((retval > 0) && buffer_delay(bh))
-                        ext4_da_release_space(inode, retval, 0);
+                        ext4_da_update_reserve_space(inode, retval);
         }
 
         up_write((&EXT4_I(inode)->i_data_sem));
@@ -1336,12 +1424,8 @@ static int ext4_ordered_write_end(struct file *file,
 {
         handle_t *handle = ext4_journal_current_handle();
         struct inode *inode = mapping->host;
-        unsigned from, to;
         int ret = 0, ret2;
 
-        from = pos & (PAGE_CACHE_SIZE - 1);
-        to = from + len;
-
         ret = ext4_jbd2_file_inode(handle, inode);
 
         if (ret == 0) {
@@ -1437,36 +1521,6 @@ static int ext4_journalled_write_end(struct file *file,
 
         return ret ? ret : copied;
 }
-/*
- * Calculate the number of metadata blocks need to reserve
- * to allocate @blocks for non extent file based file
- */
-static int ext4_indirect_calc_metadata_amount(struct inode *inode, int blocks)
-{
-        int icap = EXT4_ADDR_PER_BLOCK(inode->i_sb);
-        int ind_blks, dind_blks, tind_blks;
-
-        /* number of new indirect blocks needed */
-        ind_blks = (blocks + icap - 1) / icap;
-
-        dind_blks = (ind_blks + icap - 1) / icap;
-
-        tind_blks = 1;
-
-        return ind_blks + dind_blks + tind_blks;
-}
-
-/*
- * Calculate the number of metadata blocks need to reserve
- * to allocate given number of blocks
- */
-static int ext4_calc_metadata_amount(struct inode *inode, int blocks)
-{
-        if (EXT4_I(inode)->i_flags & EXT4_EXTENTS_FL)
-                return ext4_ext_calc_metadata_amount(inode, blocks);
-
-        return ext4_indirect_calc_metadata_amount(inode, blocks);
-}
 
 static int ext4_da_reserve_space(struct inode *inode, int nrblocks)
 {
@@ -1490,7 +1544,6 @@ static int ext4_da_reserve_space(struct inode *inode, int nrblocks)
                 spin_unlock(&EXT4_I(inode)->i_block_reservation_lock);
                 return -ENOSPC;
         }
-
         /* reduce fs free blocks counter */
         percpu_counter_sub(&sbi->s_freeblocks_counter, total);
 
@@ -1501,35 +1554,31 @@ static int ext4_da_reserve_space(struct inode *inode, int nrblocks)
         return 0;       /* success */
 }
 
-void ext4_da_release_space(struct inode *inode, int used, int to_free)
+static void ext4_da_release_space(struct inode *inode, int to_free)
 {
         struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
         int total, mdb, mdb_free, release;
 
         spin_lock(&EXT4_I(inode)->i_block_reservation_lock);
         /* recalculate the number of metablocks still need to be reserved */
-        total = EXT4_I(inode)->i_reserved_data_blocks - used - to_free;
+        total = EXT4_I(inode)->i_reserved_data_blocks - to_free;
         mdb = ext4_calc_metadata_amount(inode, total);
 
         /* figure out how many metablocks to release */
         BUG_ON(mdb > EXT4_I(inode)->i_reserved_meta_blocks);
         mdb_free = EXT4_I(inode)->i_reserved_meta_blocks - mdb;
 
-        /* Account for allocated meta_blocks */
-        mdb_free -= EXT4_I(inode)->i_allocated_meta_blocks;
-
         release = to_free + mdb_free;
 
         /* update fs free blocks counter for truncate case */
         percpu_counter_add(&sbi->s_freeblocks_counter, release);
 
         /* update per-inode reservations */
-        BUG_ON(used + to_free > EXT4_I(inode)->i_reserved_data_blocks);
-        EXT4_I(inode)->i_reserved_data_blocks -= (used + to_free);
+        BUG_ON(to_free > EXT4_I(inode)->i_reserved_data_blocks);
+        EXT4_I(inode)->i_reserved_data_blocks -= to_free;
 
         BUG_ON(mdb > EXT4_I(inode)->i_reserved_meta_blocks);
         EXT4_I(inode)->i_reserved_meta_blocks = mdb;
-        EXT4_I(inode)->i_allocated_meta_blocks = 0;
         spin_unlock(&EXT4_I(inode)->i_block_reservation_lock);
 }
 
@@ -1551,7 +1600,7 @@ static void ext4_da_page_release_reservation(struct page *page,
                 }
                 curr_off = next_off;
         } while ((bh = bh->b_this_page) != head);
-        ext4_da_release_space(page->mapping->host, 0, to_release);
+        ext4_da_release_space(page->mapping->host, to_release);
 }
 
 /*
@@ -2280,8 +2329,11 @@ retry:
         }
 
         page = __grab_cache_page(mapping, index);
-        if (!page)
-                return -ENOMEM;
+        if (!page) {
+                ext4_journal_stop(handle);
+                ret = -ENOMEM;
+                goto out;
+        }
         *pagep = page;
 
         ret = block_write_begin(file, mapping, pos, len, flags, pagep, fsdata,
@@ -2806,59 +2858,63 @@ static int ext4_journalled_set_page_dirty(struct page *page)
 }
 
 static const struct address_space_operations ext4_ordered_aops = {
-        .readpage       = ext4_readpage,
-        .readpages      = ext4_readpages,
-        .writepage      = ext4_normal_writepage,
-        .sync_page      = block_sync_page,
-        .write_begin    = ext4_write_begin,
-        .write_end      = ext4_ordered_write_end,
-        .bmap           = ext4_bmap,
-        .invalidatepage = ext4_invalidatepage,
-        .releasepage    = ext4_releasepage,
-        .direct_IO      = ext4_direct_IO,
-        .migratepage    = buffer_migrate_page,
+        .readpage               = ext4_readpage,
+        .readpages              = ext4_readpages,
+        .writepage              = ext4_normal_writepage,
+        .sync_page              = block_sync_page,
+        .write_begin            = ext4_write_begin,
+        .write_end              = ext4_ordered_write_end,
+        .bmap                   = ext4_bmap,
+        .invalidatepage         = ext4_invalidatepage,
+        .releasepage            = ext4_releasepage,
+        .direct_IO              = ext4_direct_IO,
+        .migratepage            = buffer_migrate_page,
+        .is_partially_uptodate  = block_is_partially_uptodate,
 };
 
 static const struct address_space_operations ext4_writeback_aops = {
-        .readpage       = ext4_readpage,
-        .readpages      = ext4_readpages,
-        .writepage      = ext4_normal_writepage,
-        .sync_page      = block_sync_page,
-        .write_begin    = ext4_write_begin,
-        .write_end      = ext4_writeback_write_end,
-        .bmap           = ext4_bmap,
-        .invalidatepage = ext4_invalidatepage,
-        .releasepage    = ext4_releasepage,
-        .direct_IO      = ext4_direct_IO,
-        .migratepage    = buffer_migrate_page,
+        .readpage               = ext4_readpage,
+        .readpages              = ext4_readpages,
+        .writepage              = ext4_normal_writepage,
+        .sync_page              = block_sync_page,
+        .write_begin            = ext4_write_begin,
+        .write_end              = ext4_writeback_write_end,
+        .bmap                   = ext4_bmap,
+        .invalidatepage         = ext4_invalidatepage,
+        .releasepage            = ext4_releasepage,
+        .direct_IO              = ext4_direct_IO,
+        .migratepage            = buffer_migrate_page,
+        .is_partially_uptodate  = block_is_partially_uptodate,
 };
 
 static const struct address_space_operations ext4_journalled_aops = {
-        .readpage       = ext4_readpage,
-        .readpages      = ext4_readpages,
-        .writepage      = ext4_journalled_writepage,
-        .sync_page      = block_sync_page,
-        .write_begin    = ext4_write_begin,
-        .write_end      = ext4_journalled_write_end,
-        .set_page_dirty = ext4_journalled_set_page_dirty,
-        .bmap           = ext4_bmap,
-        .invalidatepage = ext4_invalidatepage,
-        .releasepage    = ext4_releasepage,
+        .readpage               = ext4_readpage,
+        .readpages              = ext4_readpages,
+        .writepage              = ext4_journalled_writepage,
+        .sync_page              = block_sync_page,
+        .write_begin            = ext4_write_begin,
+        .write_end              = ext4_journalled_write_end,
+        .set_page_dirty         = ext4_journalled_set_page_dirty,
+        .bmap                   = ext4_bmap,
+        .invalidatepage         = ext4_invalidatepage,
+        .releasepage            = ext4_releasepage,
+        .is_partially_uptodate  = block_is_partially_uptodate,
 };
 
 static const struct address_space_operations ext4_da_aops = {
-        .readpage       = ext4_readpage,
-        .readpages      = ext4_readpages,
-        .writepage      = ext4_da_writepage,
-        .writepages     = ext4_da_writepages,
-        .sync_page      = block_sync_page,
-        .write_begin    = ext4_da_write_begin,
-        .write_end      = ext4_da_write_end,
-        .bmap           = ext4_bmap,
-        .invalidatepage = ext4_da_invalidatepage,
-        .releasepage    = ext4_releasepage,
-        .direct_IO      = ext4_direct_IO,
-        .migratepage    = buffer_migrate_page,
+        .readpage               = ext4_readpage,
+        .readpages              = ext4_readpages,
+        .writepage              = ext4_da_writepage,
+        .writepages             = ext4_da_writepages,
+        .sync_page              = block_sync_page,
+        .write_begin            = ext4_da_write_begin,
+        .write_end              = ext4_da_write_end,
+        .bmap                   = ext4_bmap,
+        .invalidatepage         = ext4_da_invalidatepage,
+        .releasepage            = ext4_releasepage,
+        .direct_IO              = ext4_direct_IO,
+        .migratepage            = buffer_migrate_page,
+        .is_partially_uptodate  = block_is_partially_uptodate,
 };
 
 void ext4_set_aops(struct inode *inode)
@@ -3586,6 +3642,16 @@ static int __ext4_get_inode_loc(struct inode *inode,
         }
         if (!buffer_uptodate(bh)) {
                 lock_buffer(bh);
+
+                /*
+                 * If the buffer has the write error flag, we have failed
+                 * to write out another inode in the same block.  In this
+                 * case, we don't have to read the block because we may
+                 * read the old inode data successfully.
+                 */
+                if (buffer_write_io_error(bh) && !buffer_uptodate(bh))
+                        set_buffer_uptodate(bh);
+
                 if (buffer_uptodate(bh)) {
                         /* someone brought it uptodate while we waited */
                         unlock_buffer(bh);