+static void bi_complete(struct bio *bio, int error)
+{
+ complete((struct completion *)bio->bi_private);
+}
+
+/* FIXME!! we need to try to merge to left or right after zero-out */
+static int ext4_ext_zeroout(struct inode *inode, struct ext4_extent *ex)
+{
+ int ret = -EIO;
+ struct bio *bio;
+ int blkbits, blocksize;
+ sector_t ee_pblock;
+ struct completion event;
+ unsigned int ee_len, len, done, offset;
+
+
+ blkbits = inode->i_blkbits;
+ blocksize = inode->i_sb->s_blocksize;
+ ee_len = ext4_ext_get_actual_len(ex);
+ ee_pblock = ext_pblock(ex);
+
+ /* convert ee_pblock to 512 byte sectors */
+ ee_pblock = ee_pblock << (blkbits - 9);
+
+ while (ee_len > 0) {
+
+ if (ee_len > BIO_MAX_PAGES)
+ len = BIO_MAX_PAGES;
+ else
+ len = ee_len;
+
+ bio = bio_alloc(GFP_NOIO, len);
+ bio->bi_sector = ee_pblock;
+ bio->bi_bdev = inode->i_sb->s_bdev;
+
+ done = 0;
+ offset = 0;
+ while (done < len) {
+ ret = bio_add_page(bio, ZERO_PAGE(0),
+ blocksize, offset);
+ if (ret != blocksize) {
+ /*
+ * We can't add any more pages because of
+ * hardware limitations. Start a new bio.
+ */
+ break;
+ }
+ done++;
+ offset += blocksize;
+ if (offset >= PAGE_CACHE_SIZE)
+ offset = 0;
+ }
+
+ init_completion(&event);
+ bio->bi_private = &event;
+ bio->bi_end_io = bi_complete;
+ submit_bio(WRITE, bio);
+ wait_for_completion(&event);
+
+ if (test_bit(BIO_UPTODATE, &bio->bi_flags))
+ ret = 0;
+ else {
+ ret = -EIO;
+ break;
+ }
+ bio_put(bio);
+ ee_len -= done;
+ ee_pblock += done << (blkbits - 9);
+ }
+ return ret;
+}
+
+#define EXT4_EXT_ZERO_LEN 7
+
+/*
+ * This function is called by ext4_ext_get_blocks() if someone tries to write
+ * to an uninitialized extent. It may result in splitting the uninitialized
+ * extent into multiple extents (upto three - one initialized and two
+ * uninitialized).
+ * There are three possibilities:
+ * a> There is no split required: Entire extent should be initialized
+ * b> Splits in two extents: Write is happening at either end of the extent
+ * c> Splits in three extents: Somone is writing in middle of the extent
+ */
+static int ext4_ext_convert_to_initialized(handle_t *handle,
+ struct inode *inode,
+ struct ext4_ext_path *path,
+ ext4_lblk_t iblock,
+ unsigned int max_blocks)
+{
+ struct ext4_extent *ex, newex, orig_ex;
+ struct ext4_extent *ex1 = NULL;
+ struct ext4_extent *ex2 = NULL;
+ struct ext4_extent *ex3 = NULL;
+ struct ext4_extent_header *eh;
+ ext4_lblk_t ee_block;
+ unsigned int allocated, ee_len, depth;
+ ext4_fsblk_t newblock;
+ int err = 0;
+ int ret = 0;
+
+ depth = ext_depth(inode);
+ eh = path[depth].p_hdr;
+ ex = path[depth].p_ext;
+ ee_block = le32_to_cpu(ex->ee_block);
+ ee_len = ext4_ext_get_actual_len(ex);
+ allocated = ee_len - (iblock - ee_block);
+ newblock = iblock - ee_block + ext_pblock(ex);
+ ex2 = ex;
+ orig_ex.ee_block = ex->ee_block;
+ orig_ex.ee_len = cpu_to_le16(ee_len);
+ ext4_ext_store_pblock(&orig_ex, ext_pblock(ex));
+
+ err = ext4_ext_get_access(handle, inode, path + depth);
+ if (err)
+ goto out;
+ /* If extent has less than 2*EXT4_EXT_ZERO_LEN zerout directly */
+ if (ee_len <= 2*EXT4_EXT_ZERO_LEN) {
+ err = ext4_ext_zeroout(inode, &orig_ex);
+ if (err)
+ goto fix_extent_len;
+ /* update the extent length and mark as initialized */
+ ex->ee_block = orig_ex.ee_block;
+ ex->ee_len = orig_ex.ee_len;
+ ext4_ext_store_pblock(ex, ext_pblock(&orig_ex));
+ ext4_ext_dirty(handle, inode, path + depth);
+ /* zeroed the full extent */
+ return allocated;
+ }
+
+ /* ex1: ee_block to iblock - 1 : uninitialized */
+ if (iblock > ee_block) {
+ ex1 = ex;
+ ex1->ee_len = cpu_to_le16(iblock - ee_block);
+ ext4_ext_mark_uninitialized(ex1);
+ ex2 = &newex;
+ }
+ /*
+ * for sanity, update the length of the ex2 extent before
+ * we insert ex3, if ex1 is NULL. This is to avoid temporary
+ * overlap of blocks.
+ */
+ if (!ex1 && allocated > max_blocks)
+ ex2->ee_len = cpu_to_le16(max_blocks);
+ /* ex3: to ee_block + ee_len : uninitialised */
+ if (allocated > max_blocks) {
+ unsigned int newdepth;
+ /* If extent has less than EXT4_EXT_ZERO_LEN zerout directly */
+ if (allocated <= EXT4_EXT_ZERO_LEN) {
+ /*
+ * iblock == ee_block is handled by the zerouout
+ * at the beginning.
+ * Mark first half uninitialized.
+ * Mark second half initialized and zero out the
+ * initialized extent
+ */
+ ex->ee_block = orig_ex.ee_block;
+ ex->ee_len = cpu_to_le16(ee_len - allocated);
+ ext4_ext_mark_uninitialized(ex);
+ ext4_ext_store_pblock(ex, ext_pblock(&orig_ex));
+ ext4_ext_dirty(handle, inode, path + depth);
+
+ ex3 = &newex;
+ ex3->ee_block = cpu_to_le32(iblock);
+ ext4_ext_store_pblock(ex3, newblock);
+ ex3->ee_len = cpu_to_le16(allocated);
+ err = ext4_ext_insert_extent(handle, inode, path, ex3);
+ if (err == -ENOSPC) {
+ err = ext4_ext_zeroout(inode, &orig_ex);
+ if (err)
+ goto fix_extent_len;
+ ex->ee_block = orig_ex.ee_block;
+ ex->ee_len = orig_ex.ee_len;
+ ext4_ext_store_pblock(ex, ext_pblock(&orig_ex));
+ ext4_ext_dirty(handle, inode, path + depth);
+ /* blocks available from iblock */
+ return allocated;
+
+ } else if (err)
+ goto fix_extent_len;
+
+ /*
+ * We need to zero out the second half because
+ * an fallocate request can update file size and
+ * converting the second half to initialized extent
+ * implies that we can leak some junk data to user
+ * space.
+ */
+ err = ext4_ext_zeroout(inode, ex3);
+ if (err) {
+ /*
+ * We should actually mark the
+ * second half as uninit and return error
+ * Insert would have changed the extent
+ */
+ depth = ext_depth(inode);
+ ext4_ext_drop_refs(path);
+ path = ext4_ext_find_extent(inode,
+ iblock, path);
+ if (IS_ERR(path)) {
+ err = PTR_ERR(path);
+ return err;
+ }
+ /* get the second half extent details */
+ ex = path[depth].p_ext;
+ err = ext4_ext_get_access(handle, inode,
+ path + depth);
+ if (err)
+ return err;
+ ext4_ext_mark_uninitialized(ex);
+ ext4_ext_dirty(handle, inode, path + depth);
+ return err;
+ }
+
+ /* zeroed the second half */
+ return allocated;
+ }
+ ex3 = &newex;
+ ex3->ee_block = cpu_to_le32(iblock + max_blocks);
+ ext4_ext_store_pblock(ex3, newblock + max_blocks);
+ ex3->ee_len = cpu_to_le16(allocated - max_blocks);
+ ext4_ext_mark_uninitialized(ex3);
+ err = ext4_ext_insert_extent(handle, inode, path, ex3);
+ if (err == -ENOSPC) {
+ err = ext4_ext_zeroout(inode, &orig_ex);
+ if (err)
+ goto fix_extent_len;
+ /* update the extent length and mark as initialized */
+ ex->ee_block = orig_ex.ee_block;
+ ex->ee_len = orig_ex.ee_len;
+ ext4_ext_store_pblock(ex, ext_pblock(&orig_ex));
+ ext4_ext_dirty(handle, inode, path + depth);
+ /* zeroed the full extent */
+ /* blocks available from iblock */
+ return allocated;
+
+ } else if (err)
+ goto fix_extent_len;
+ /*
+ * The depth, and hence eh & ex might change
+ * as part of the insert above.
+ */
+ newdepth = ext_depth(inode);
+ /*
+ * update the extent length after successful insert of the
+ * split extent
+ */
+ orig_ex.ee_len = cpu_to_le16(ee_len -
+ ext4_ext_get_actual_len(ex3));
+ depth = newdepth;
+ ext4_ext_drop_refs(path);
+ path = ext4_ext_find_extent(inode, iblock, path);
+ if (IS_ERR(path)) {
+ err = PTR_ERR(path);
+ goto out;
+ }
+ eh = path[depth].p_hdr;
+ ex = path[depth].p_ext;
+ if (ex2 != &newex)
+ ex2 = ex;
+
+ err = ext4_ext_get_access(handle, inode, path + depth);
+ if (err)
+ goto out;
+
+ allocated = max_blocks;
+
+ /* If extent has less than EXT4_EXT_ZERO_LEN and we are trying
+ * to insert a extent in the middle zerout directly
+ * otherwise give the extent a chance to merge to left
+ */
+ if (le16_to_cpu(orig_ex.ee_len) <= EXT4_EXT_ZERO_LEN &&
+ iblock != ee_block) {
+ err = ext4_ext_zeroout(inode, &orig_ex);
+ if (err)
+ goto fix_extent_len;
+ /* update the extent length and mark as initialized */
+ ex->ee_block = orig_ex.ee_block;
+ ex->ee_len = orig_ex.ee_len;
+ ext4_ext_store_pblock(ex, ext_pblock(&orig_ex));
+ ext4_ext_dirty(handle, inode, path + depth);
+ /* zero out the first half */
+ /* blocks available from iblock */
+ return allocated;
+ }
+ }
+ /*
+ * If there was a change of depth as part of the
+ * insertion of ex3 above, we need to update the length
+ * of the ex1 extent again here
+ */
+ if (ex1 && ex1 != ex) {
+ ex1 = ex;
+ ex1->ee_len = cpu_to_le16(iblock - ee_block);
+ ext4_ext_mark_uninitialized(ex1);
+ ex2 = &newex;
+ }
+ /* ex2: iblock to iblock + maxblocks-1 : initialised */
+ ex2->ee_block = cpu_to_le32(iblock);
+ ext4_ext_store_pblock(ex2, newblock);
+ ex2->ee_len = cpu_to_le16(allocated);
+ if (ex2 != ex)
+ goto insert;
+ /*
+ * New (initialized) extent starts from the first block
+ * in the current extent. i.e., ex2 == ex
+ * We have to see if it can be merged with the extent
+ * on the left.
+ */
+ if (ex2 > EXT_FIRST_EXTENT(eh)) {
+ /*
+ * To merge left, pass "ex2 - 1" to try_to_merge(),
+ * since it merges towards right _only_.
+ */
+ ret = ext4_ext_try_to_merge(inode, path, ex2 - 1);
+ if (ret) {
+ err = ext4_ext_correct_indexes(handle, inode, path);
+ if (err)
+ goto out;
+ depth = ext_depth(inode);
+ ex2--;
+ }
+ }
+ /*
+ * Try to Merge towards right. This might be required
+ * only when the whole extent is being written to.
+ * i.e. ex2 == ex and ex3 == NULL.
+ */
+ if (!ex3) {
+ ret = ext4_ext_try_to_merge(inode, path, ex2);
+ if (ret) {
+ err = ext4_ext_correct_indexes(handle, inode, path);
+ if (err)
+ goto out;
+ }
+ }
+ /* Mark modified extent as dirty */
+ err = ext4_ext_dirty(handle, inode, path + depth);
+ goto out;
+insert:
+ err = ext4_ext_insert_extent(handle, inode, path, &newex);
+ if (err == -ENOSPC) {
+ err = ext4_ext_zeroout(inode, &orig_ex);
+ if (err)
+ goto fix_extent_len;
+ /* update the extent length and mark as initialized */
+ ex->ee_block = orig_ex.ee_block;
+ ex->ee_len = orig_ex.ee_len;
+ ext4_ext_store_pblock(ex, ext_pblock(&orig_ex));
+ ext4_ext_dirty(handle, inode, path + depth);
+ /* zero out the first half */
+ return allocated;
+ } else if (err)
+ goto fix_extent_len;
+out:
+ return err ? err : allocated;
+
+fix_extent_len:
+ ex->ee_block = orig_ex.ee_block;
+ ex->ee_len = orig_ex.ee_len;
+ ext4_ext_store_pblock(ex, ext_pblock(&orig_ex));
+ ext4_ext_mark_uninitialized(ex);
+ ext4_ext_dirty(handle, inode, path + depth);
+ return err;
+}
+
+/*
+ * Block allocation/map/preallocation routine for extents based files
+ *
+ *
+ * Need to be called with
+ * down_read(&EXT4_I(inode)->i_data_sem) if not allocating file system block
+ * (ie, create is zero). Otherwise down_write(&EXT4_I(inode)->i_data_sem)
+ *
+ * return > 0, number of of blocks already mapped/allocated
+ * if create == 0 and these are pre-allocated blocks
+ * buffer head is unmapped
+ * otherwise blocks are mapped
+ *
+ * return = 0, if plain look up failed (blocks have not been allocated)
+ * buffer head is unmapped
+ *
+ * return < 0, error case.
+ */