[Ocfs2-devel] Large (> 16TiB) volumes revisited

[Patrick J. LoPresti]

Joel --

I have applied the changes you suggested.  Revised patch is below.

Oh, one trivial thing I forgot to mention:  I changed the errno for
the failure cases from EINVAL to EFBIG since that is what ext4 uses.

My next step will be to test this...  But what is next after that?  Do
I send this as a "[PATCH] ..." to ocfs2-devel and linux-kernel, or do
I just send to ocfs2-devel and one of you passes it on?

 - Pat


diff --git a/fs/ocfs2/super.c b/fs/ocfs2/super.c
index 0eaa929..084d28d 100644
--- a/fs/ocfs2/super.c
+++ b/fs/ocfs2/super.c
@@ -1991,6 +1991,45 @@ static int ocfs2_setup_osb_uuid(struct
ocfs2_super *osb, const unsigned char *uu
 	return 0;
 }

+/* Check to make sure entire volume is addressable on this system. */
+static int ocfs2_check_addressable(struct ocfs2_super *osb,
+				   struct ocfs2_dinode *di)
+{
+	int status = 0;
+	const u32 clusters = le32_to_cpu(di->i_clusters);
+	const u64 max_block = ocfs2_clusters_to_blocks(osb->sb, clusters) - 1;
+
+	/* Absolute addressability check (borrowed from ext4/super.c) */
+	if ((max_block >
+	     (sector_t)(~0LL) >> (osb->sb->s_blocksize_bits - 9)) ||
+	    (max_block > (pgoff_t)(~0LL) >> (PAGE_CACHE_SHIFT -
+					     osb->sb->s_blocksize_bits))) {
+		mlog(ML_ERROR, "Volume too large "
+		     "to mount safely on this system");
+		status = -EFBIG;
+		goto out;
+	}
+
+	/* 32-bit block number is always OK. */
+	if (max_block <= (u32)~0UL)
+		goto out;
+
+	/* Volume is "huge", so see if our journal is new enough to
+	   support it. */
+	if (!(OCFS2_HAS_COMPAT_FEATURE(osb->sb,
+				       OCFS2_FEATURE_COMPAT_JBD2_SB) &&
+	      jbd2_journal_check_used_features(osb->journal->j_journal, 0, 0,
+					       JBD2_FEATURE_INCOMPAT_64BIT))) {
+		mlog(ML_ERROR, "The journal cannot address the entire volume. "
+		     "Enable the 'block64' journal option with tunefs.ocfs2");
+		status = -EFBIG;
+		goto out;
+	}
+
+ out:
+	return status;
+}
+
 static int ocfs2_initialize_super(struct super_block *sb,
 				  struct buffer_head *bh,
 				  int sector_size,
@@ -2215,13 +2254,9 @@ static int ocfs2_initialize_super(struct super_block *sb,
 		goto bail;
 	}

-	if (ocfs2_clusters_to_blocks(osb->sb, le32_to_cpu(di->i_clusters) - 1)
-	    > (u32)~0UL) {
-		mlog(ML_ERROR, "Volume might try to write to blocks beyond "
-		     "what jbd can address in 32 bits.\n");
-		status = -EINVAL;
+	status = ocfs2_check_addressable(osb, di);
+	if (status)
 		goto bail;
-	}

 	if (ocfs2_setup_osb_uuid(osb, di->id2.i_super.s_uuid,
 				 sizeof(di->id2.i_super.s_uuid))) {