Ocfs2/move_extents: move entire/partial extent.

ocfs2_move_extent() logic will validate the goal_offset_in_block,
where extents to be moved, what's more, it also compromises a bit
to probe the appropriate region around given goal_offset when the
original goal is not able to fit the movement.

Signed-off-by: Tristan Ye <tristan.ye@oracle.com>

1 files changed, 165 insertions, 0 deletions

diff --git a/fs/ocfs2/move_extents.c b/fs/ocfs2/move_extents.c
index 390354a4ecb..ae15c998a82 100644
--- a/fs/ocfs2/move_extents.c
+++ b/fs/ocfs2/move_extents.c
@@ -632,3 +632,168 @@ static inline int ocfs2_block_group_set_bits(handle_t *handle,
 bail:
         return status;
 }
+
+static int ocfs2_move_extent(struct ocfs2_move_extents_context *context,
+                             u32 cpos, u32 phys_cpos, u32 *new_phys_cpos,
+                             u32 len, int ext_flags)
+{
+        int ret, credits = 0, extra_blocks = 0, goal_bit = 0;
+        handle_t *handle;
+        struct inode *inode = context->inode;
+        struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
+        struct inode *tl_inode = osb->osb_tl_inode;
+        struct inode *gb_inode = NULL;
+        struct buffer_head *gb_bh = NULL;
+        struct buffer_head *gd_bh = NULL;
+        struct ocfs2_group_desc *gd;
+        struct ocfs2_refcount_tree *ref_tree = NULL;
+        u32 move_max_hop = ocfs2_blocks_to_clusters(inode->i_sb,
+                                                    context->range->me_threshold);
+        u64 phys_blkno, new_phys_blkno;
+
+        phys_blkno = ocfs2_clusters_to_blocks(inode->i_sb, phys_cpos);
+
+        if ((ext_flags & OCFS2_EXT_REFCOUNTED) && len) {
+
+                BUG_ON(!(OCFS2_I(inode)->ip_dyn_features &
+                         OCFS2_HAS_REFCOUNT_FL));
+
+                BUG_ON(!context->refcount_loc);
+
+                ret = ocfs2_lock_refcount_tree(osb, context->refcount_loc, 1,
+                                               &ref_tree, NULL);
+                if (ret) {
+                        mlog_errno(ret);
+                        return ret;
+                }
+
+                ret = ocfs2_prepare_refcount_change_for_del(inode,
+                                                        context->refcount_loc,
+                                                        phys_blkno,
+                                                        len,
+                                                        &credits,
+                                                        &extra_blocks);
+                if (ret) {
+                        mlog_errno(ret);
+                        goto out;
+                }
+        }
+
+        ret = ocfs2_lock_allocators_move_extents(inode, &context->et, len, 1,
+                                                 &context->meta_ac,
+                                                 NULL, extra_blocks, &credits);
+        if (ret) {
+                mlog_errno(ret);
+                goto out;
+        }
+
+        /*
+         * need to count 2 extra credits for global_bitmap inode and
+         * group descriptor.
+         */
+        credits += OCFS2_INODE_UPDATE_CREDITS + 1;
+
+        /*
+         * ocfs2_move_extent() didn't reserve any clusters in lock_allocators()
+         * logic, while we still need to lock the global_bitmap.
+         */
+        gb_inode = ocfs2_get_system_file_inode(osb, GLOBAL_BITMAP_SYSTEM_INODE,
+                                               OCFS2_INVALID_SLOT);
+        if (!gb_inode) {
+                mlog(ML_ERROR, "unable to get global_bitmap inode\n");
+                ret = -EIO;
+                goto out;
+        }
+
+        mutex_lock(&gb_inode->i_mutex);
+
+        ret = ocfs2_inode_lock(gb_inode, &gb_bh, 1);
+        if (ret) {
+                mlog_errno(ret);
+                goto out_unlock_gb_mutex;
+        }
+
+        mutex_lock(&tl_inode->i_mutex);
+
+        handle = ocfs2_start_trans(osb, credits);
+        if (IS_ERR(handle)) {
+                ret = PTR_ERR(handle);
+                mlog_errno(ret);
+                goto out_unlock_tl_inode;
+        }
+
+        new_phys_blkno = ocfs2_clusters_to_blocks(inode->i_sb, *new_phys_cpos);
+        ret = ocfs2_find_victim_alloc_group(inode, new_phys_blkno,
+                                            GLOBAL_BITMAP_SYSTEM_INODE,
+                                            OCFS2_INVALID_SLOT,
+                                            &goal_bit, &gd_bh);
+        if (ret) {
+                mlog_errno(ret);
+                goto out_commit;
+        }
+
+        /*
+         * probe the victim cluster group to find a proper
+         * region to fit wanted movement, it even will perfrom
+         * a best-effort attempt by compromising to a threshold
+         * around the goal.
+         */
+        ocfs2_probe_alloc_group(inode, gd_bh, &goal_bit, len, move_max_hop,
+                                new_phys_cpos);
+        if (!new_phys_cpos) {
+                ret = -ENOSPC;
+                goto out_commit;
+        }
+
+        ret = __ocfs2_move_extent(handle, context, cpos, len, phys_cpos,
+                                  *new_phys_cpos, ext_flags);
+        if (ret) {
+                mlog_errno(ret);
+                goto out_commit;
+        }
+
+        gd = (struct ocfs2_group_desc *)gd_bh->b_data;
+        ret = ocfs2_alloc_dinode_update_counts(gb_inode, handle, gb_bh, len,
+                                               le16_to_cpu(gd->bg_chain));
+        if (ret) {
+                mlog_errno(ret);
+                goto out_commit;
+        }
+
+        ret = ocfs2_block_group_set_bits(handle, gb_inode, gd, gd_bh,
+                                         goal_bit, len);
+        if (ret)
+                mlog_errno(ret);
+
+        /*
+         * Here we should write the new page out first if we are
+         * in write-back mode.
+         */
+        ret = ocfs2_cow_sync_writeback(inode->i_sb, context->inode, cpos, len);
+        if (ret)
+                mlog_errno(ret);
+
+out_commit:
+        ocfs2_commit_trans(osb, handle);
+        brelse(gd_bh);
+
+out_unlock_tl_inode:
+        mutex_unlock(&tl_inode->i_mutex);
+
+        ocfs2_inode_unlock(gb_inode, 1);
+out_unlock_gb_mutex:
+        mutex_unlock(&gb_inode->i_mutex);
+        brelse(gb_bh);
+        iput(gb_inode);
+
+out:
+        if (context->meta_ac) {
+                ocfs2_free_alloc_context(context->meta_ac);
+                context->meta_ac = NULL;
+        }
+
+        if (ref_tree)
+                ocfs2_unlock_refcount_tree(osb, ref_tree, 1);
+
+        return ret;
+}