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: (61 commits)
  ext4: Documention update for new ordered mode and delayed allocation
  ext4: do not set extents feature from the kernel
  ext4: Don't allow nonextenst mount option for large filesystem
  ext4: Enable delalloc by default.
  ext4: delayed allocation i_blocks fix for stat
  ext4: fix delalloc i_disksize early update issue
  ext4: Handle page without buffers in ext4_*_writepage()
  ext4: Add ordered mode support for delalloc
  ext4: Invert lock ordering of page_lock and transaction start in delalloc
  mm: Add range_cont mode for writeback
  ext4: delayed allocation ENOSPC handling
  percpu_counter: new function percpu_counter_sum_and_set
  ext4: Add delayed allocation support in data=writeback mode
  vfs: add hooks for ext4's delayed allocation support
  jbd2: Remove data=ordered mode support using jbd buffer heads
  ext4: Use new framework for data=ordered mode in JBD2
  jbd2: Implement data=ordered mode handling via inodes
  vfs: export filemap_fdatawrite_range()
  ext4: Fix lock inversion in ext4_ext_truncate()
  ext4: Invert the locking order of page_lock and transaction start
  ...

1 files changed, 73 insertions, 38 deletions

diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c
index 47929c4e3dae..42c4c0c892ed 100644
--- a/fs/ext4/extents.c
+++ b/fs/ext4/extents.c
@@ -92,17 +92,16 @@ static void ext4_idx_store_pblock(struct ext4_extent_idx *ix, ext4_fsblk_t pb)
         ix->ei_leaf_hi = cpu_to_le16((unsigned long) ((pb >> 31) >> 1) & 0xffff);
 }
 
-static handle_t *ext4_ext_journal_restart(handle_t *handle, int needed)
+static int ext4_ext_journal_restart(handle_t *handle, int needed)
 {
         int err;
 
         if (handle->h_buffer_credits > needed)
-                return handle;
-        if (!ext4_journal_extend(handle, needed))
-                return handle;
-        err = ext4_journal_restart(handle, needed);
-
-        return handle;
+                return 0;
+        err = ext4_journal_extend(handle, needed);
+        if (err)
+                return err;
+        return ext4_journal_restart(handle, needed);
 }
 
 /*
@@ -180,15 +179,18 @@ static ext4_fsblk_t ext4_ext_find_goal(struct inode *inode,
         return bg_start + colour + block;
 }
 
+/*
+ * Allocation for a meta data block
+ */
 static ext4_fsblk_t
-ext4_ext_new_block(handle_t *handle, struct inode *inode,
+ext4_ext_new_meta_block(handle_t *handle, struct inode *inode,
                         struct ext4_ext_path *path,
                         struct ext4_extent *ex, int *err)
 {
         ext4_fsblk_t goal, newblock;
 
         goal = ext4_ext_find_goal(inode, path, le32_to_cpu(ex->ee_block));
-        newblock = ext4_new_block(handle, inode, goal, err);
+        newblock = ext4_new_meta_block(handle, inode, goal, err);
         return newblock;
 }
 
@@ -246,6 +248,36 @@ static int ext4_ext_space_root_idx(struct inode *inode)
         return size;
 }
 
+/*
+ * Calculate the number of metadata blocks needed
+ * to allocate @blocks
+ * Worse case is one block per extent
+ */
+int ext4_ext_calc_metadata_amount(struct inode *inode, int blocks)
+{
+        int lcap, icap, rcap, leafs, idxs, num;
+        int newextents = blocks;
+
+        rcap = ext4_ext_space_root_idx(inode);
+        lcap = ext4_ext_space_block(inode);
+        icap = ext4_ext_space_block_idx(inode);
+
+        /* number of new leaf blocks needed */
+        num = leafs = (newextents + lcap - 1) / lcap;
+
+        /*
+         * Worse case, we need separate index block(s)
+         * to link all new leaf blocks
+         */
+        idxs = (leafs + icap - 1) / icap;
+        do {
+                num += idxs;
+                idxs = (idxs + icap - 1) / icap;
+        } while (idxs > rcap);
+
+        return num;
+}
+
 static int
 ext4_ext_max_entries(struct inode *inode, int depth)
 {
@@ -524,6 +556,7 @@ ext4_ext_find_extent(struct inode *inode, ext4_lblk_t block,
                 alloc = 1;
         }
         path[0].p_hdr = eh;
+        path[0].p_bh = NULL;
 
         i = depth;
         /* walk through the tree */
@@ -552,12 +585,14 @@ ext4_ext_find_extent(struct inode *inode, ext4_lblk_t block,
         }
 
         path[ppos].p_depth = i;
-        path[ppos].p_hdr = eh;
         path[ppos].p_ext = NULL;
         path[ppos].p_idx = NULL;
 
         /* find extent */
         ext4_ext_binsearch(inode, path + ppos, block);
+        /* if not an empty leaf */
+        if (path[ppos].p_ext)
+                path[ppos].p_block = ext_pblock(path[ppos].p_ext);
 
         ext4_ext_show_path(inode, path);
 
@@ -688,7 +723,8 @@ static int ext4_ext_split(handle_t *handle, struct inode *inode,
         /* allocate all needed blocks */
         ext_debug("allocate %d blocks for indexes/leaf\n", depth - at);
         for (a = 0; a < depth - at; a++) {
-                newblock = ext4_ext_new_block(handle, inode, path, newext, &err);
+                newblock = ext4_ext_new_meta_block(handle, inode, path,
+                                                   newext, &err);
                 if (newblock == 0)
                         goto cleanup;
                 ablocks[a] = newblock;
@@ -884,7 +920,7 @@ static int ext4_ext_grow_indepth(handle_t *handle, struct inode *inode,
         ext4_fsblk_t newblock;
         int err = 0;
 
-        newblock = ext4_ext_new_block(handle, inode, path, newext, &err);
+        newblock = ext4_ext_new_meta_block(handle, inode, path, newext, &err);
         if (newblock == 0)
                 return err;
 
@@ -981,6 +1017,8 @@ repeat:
                 /* if we found index with free entry, then use that
                  * entry: create all needed subtree and add new leaf */
                 err = ext4_ext_split(handle, inode, path, newext, i);
+                if (err)
+                        goto out;
 
                 /* refill path */
                 ext4_ext_drop_refs(path);
@@ -1883,11 +1921,9 @@ ext4_ext_rm_leaf(handle_t *handle, struct inode *inode,
                 credits += 2 * EXT4_QUOTA_TRANS_BLOCKS(inode->i_sb);
 #endif
 
-                handle = ext4_ext_journal_restart(handle, credits);
-                if (IS_ERR(handle)) {
-                        err = PTR_ERR(handle);
+                err = ext4_ext_journal_restart(handle, credits);
+                if (err)
                         goto out;
-                }
 
                 err = ext4_ext_get_access(handle, inode, path + depth);
                 if (err)
@@ -2529,6 +2565,7 @@ int ext4_ext_get_blocks(handle_t *handle, struct inode *inode,
         int err = 0, depth, ret;
         unsigned long allocated = 0;
         struct ext4_allocation_request ar;
+        loff_t disksize;
 
         __clear_bit(BH_New, &bh_result->b_state);
         ext_debug("blocks %u/%lu requested for inode %u\n",
@@ -2616,8 +2653,7 @@ int ext4_ext_get_blocks(handle_t *handle, struct inode *inode,
                                  */
                                 if (allocated > max_blocks)
                                         allocated = max_blocks;
-                                /* mark the buffer unwritten */
-                                __set_bit(BH_Unwritten, &bh_result->b_state);
+                                set_buffer_unwritten(bh_result);
                                 goto out2;
                         }
 
@@ -2716,14 +2752,19 @@ int ext4_ext_get_blocks(handle_t *handle, struct inode *inode,
                 goto out2;
         }
 
-        if (extend_disksize && inode->i_size > EXT4_I(inode)->i_disksize)
-                EXT4_I(inode)->i_disksize = inode->i_size;
-
         /* previous routine could use block we allocated */
         newblock = ext_pblock(&newex);
         allocated = ext4_ext_get_actual_len(&newex);
 outnew:
-        __set_bit(BH_New, &bh_result->b_state);
+        if (extend_disksize) {
+                disksize = ((loff_t) iblock + ar.len) << inode->i_blkbits;
+                if (disksize > i_size_read(inode))
+                        disksize = i_size_read(inode);
+                if (disksize > EXT4_I(inode)->i_disksize)
+                        EXT4_I(inode)->i_disksize = disksize;
+        }
+
+        set_buffer_new(bh_result);
 
         /* Cache only when it is _not_ an uninitialized extent */
         if (create != EXT4_CREATE_UNINITIALIZED_EXT)
@@ -2733,7 +2774,7 @@ out:
         if (allocated > max_blocks)
                 allocated = max_blocks;
         ext4_ext_show_leaf(inode, path);
-        __set_bit(BH_Mapped, &bh_result->b_state);
+        set_buffer_mapped(bh_result);
         bh_result->b_bdev = inode->i_sb->s_bdev;
         bh_result->b_blocknr = newblock;
 out2:
@@ -2744,7 +2785,7 @@ out2:
         return err ? err : allocated;
 }
 
-void ext4_ext_truncate(struct inode * inode, struct page *page)
+void ext4_ext_truncate(struct inode *inode)
 {
         struct address_space *mapping = inode->i_mapping;
         struct super_block *sb = inode->i_sb;
@@ -2757,18 +2798,14 @@ void ext4_ext_truncate(struct inode * inode, struct page *page)
          */
         err = ext4_writepage_trans_blocks(inode) + 3;
         handle = ext4_journal_start(inode, err);
-        if (IS_ERR(handle)) {
-                if (page) {
-                        clear_highpage(page);
-                        flush_dcache_page(page);
-                        unlock_page(page);
-                        page_cache_release(page);
-                }
+        if (IS_ERR(handle))
                 return;
-        }
 
-        if (page)
-                ext4_block_truncate_page(handle, page, mapping, inode->i_size);
+        if (inode->i_size & (sb->s_blocksize - 1))
+                ext4_block_truncate_page(handle, mapping, inode->i_size);
+
+        if (ext4_orphan_add(handle, inode))
+                goto out_stop;
 
         down_write(&EXT4_I(inode)->i_data_sem);
         ext4_ext_invalidate_cache(inode);
@@ -2780,8 +2817,6 @@ void ext4_ext_truncate(struct inode * inode, struct page *page)
          * Probably we need not scan at all,
          * because page truncation is enough.
          */
-        if (ext4_orphan_add(handle, inode))
-                goto out_stop;
 
         /* we have to know where to truncate from in crash case */
         EXT4_I(inode)->i_disksize = inode->i_size;
@@ -2798,6 +2833,7 @@ void ext4_ext_truncate(struct inode * inode, struct page *page)
                 handle->h_sync = 1;
 
 out_stop:
+        up_write(&EXT4_I(inode)->i_data_sem);
         /*
          * If this was a simple ftruncate() and the file will remain alive,
          * then we need to clear up the orphan record which we created above.
@@ -2808,7 +2844,6 @@ out_stop:
         if (inode->i_nlink)
                 ext4_orphan_del(handle, inode);
 
-        up_write(&EXT4_I(inode)->i_data_sem);
         inode->i_mtime = inode->i_ctime = ext4_current_time(inode);
         ext4_mark_inode_dirty(handle, inode);
         ext4_journal_stop(handle);
@@ -2911,7 +2946,7 @@ retry:
                 }
                 ret = ext4_get_blocks_wrap(handle, inode, block,
                                           max_blocks, &map_bh,
-                                          EXT4_CREATE_UNINITIALIZED_EXT, 0);
+                                          EXT4_CREATE_UNINITIALIZED_EXT, 0, 0);
                 if (ret <= 0) {
 #ifdef EXT4FS_DEBUG
                         WARN_ON(ret <= 0);