ocfs2: Limit inode allocation to 32bits.

ocfs2 inode numbers are block numbers.  For any filesystem with less
than 2^32 blocks, this is not a problem.  However, when ocfs2 starts
using JDB2, it will be able to support filesystems with more than 2^32
blocks.  This would result in inode numbers higher than 2^32.

The problem is that stat(2) can't handle those numbers on 32bit
machines.  The simple solution is to have ocfs2 allocate all inodes
below that boundary.

The suballoc code is changed to honor an optional block limit.  Only the
inode suballocator sets that limit - all other allocations stay unlimited.

The biggest trick is to grow the inode suballocator beneath that limit.
There's no point in allocating block groups that are above the limit,
then rejecting their elements later on.  We want to prevent the inode
allocator from ever having block groups above the limit.  This involves
a little gyration with the local alloc code.  If the local alloc window
is above the limit, it signals the caller to try the global bitmap but
does not disable the local alloc file (which can be used for other
allocations).

[ Minor cleanup - removed an ML_NOTICE comment. --Mark ]

Signed-off-by: Joel Becker <joel.becker@oracle.com>
Signed-off-by: Mark Fasheh <mfasheh@suse.com>

1 files changed, 55 insertions, 0 deletions

diff --git a/fs/ocfs2/localalloc.c b/fs/ocfs2/localalloc.c
index b889f10d8090..02227c392510 100644
--- a/fs/ocfs2/localalloc.c
+++ b/fs/ocfs2/localalloc.c
@@ -570,6 +570,46 @@ out:
         return status;
 }
 
+/* Check to see if the local alloc window is within ac->ac_max_block */
+static int ocfs2_local_alloc_in_range(struct inode *inode,
+                                      struct ocfs2_alloc_context *ac,
+                                      u32 bits_wanted)
+{
+        struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
+        struct ocfs2_dinode *alloc;
+        struct ocfs2_local_alloc *la;
+        int start;
+        u64 block_off;
+
+        if (!ac->ac_max_block)
+                return 1;
+
+        alloc = (struct ocfs2_dinode *) osb->local_alloc_bh->b_data;
+        la = OCFS2_LOCAL_ALLOC(alloc);
+
+        start = ocfs2_local_alloc_find_clear_bits(osb, alloc, bits_wanted);
+        if (start == -1) {
+                mlog_errno(-ENOSPC);
+                return 0;
+        }
+
+        /*
+         * Converting (bm_off + start + bits_wanted) to blocks gives us
+         * the blkno just past our actual allocation.  This is perfect
+         * to compare with ac_max_block.
+         */
+        block_off = ocfs2_clusters_to_blocks(inode->i_sb,
+                                             le32_to_cpu(la->la_bm_off) +
+                                             start + bits_wanted);
+        mlog(0, "Checking %llu against %llu\n",
+             (unsigned long long)block_off,
+             (unsigned long long)ac->ac_max_block);
+        if (block_off > ac->ac_max_block)
+                return 0;
+
+        return 1;
+}
+
 /*
  * make sure we've got at least bits_wanted contiguous bits in the
  * local alloc. You lose them when you drop i_mutex.
@@ -658,6 +698,21 @@ int ocfs2_reserve_local_alloc_bits(struct ocfs2_super *osb,
                         goto bail;
         }
 
+        if (ac->ac_max_block)
+                mlog(0, "Calling in_range for max block %llu\n",
+                     (unsigned long long)ac->ac_max_block);
+
+        if (!ocfs2_local_alloc_in_range(local_alloc_inode, ac,
+                                        bits_wanted)) {
+                /*
+                 * The window is outside ac->ac_max_block.
+                 * This errno tells the caller to keep localalloc enabled
+                 * but to get the allocation from the main bitmap.
+                 */
+                status = -EFBIG;
+                goto bail;
+        }
+
         ac->ac_inode = local_alloc_inode;
         /* We should never use localalloc from another slot */
         ac->ac_alloc_slot = osb->slot_num;