ocfs2: Add the USERSPACE_STACK incompat bit.

The filesystem gains the USERSPACE_STACK incomat bit and the
s_cluster_info field on the superblock.  When a userspace stack is in
use, the name of the stack is stored on-disk for mount-time
verification.

The "cluster_stack" option is added to mount(2) processing.  The mount
process needs to pass the matching stack name.  If the passed name and
the on-disk name do not match, the mount is failed.

When using the classic o2cb stack, the incompat bit is *not* set and no
mount option is used other than the usual heartbeat=local.  Thus, the
filesystem is compatible with older tools.

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

3 files changed, 134 insertions, 3 deletions

diff --git a/fs/ocfs2/ocfs2.h b/fs/ocfs2/ocfs2.h
index af929eca541..9ff5811345a 100644
--- a/fs/ocfs2/ocfs2.h
+++ b/fs/ocfs2/ocfs2.h
@@ -248,6 +248,7 @@ struct ocfs2_super
 	struct ocfs2_alloc_stats alloc_stats;
 	char dev_str[20];		/* "major,minor" of the device */
 
+	char osb_cluster_stack[OCFS2_STACK_LABEL_LEN + 1];
 	struct ocfs2_cluster_connection *cconn;
 	struct ocfs2_lock_res osb_super_lockres;
 	struct ocfs2_lock_res osb_rename_lockres;
@@ -368,6 +369,12 @@ static inline int ocfs2_is_soft_readonly(struct ocfs2_super *osb)
 	return ret;
 }
 
+static inline int ocfs2_userspace_stack(struct ocfs2_super *osb)
+{
+	return (osb->s_feature_incompat &
+		OCFS2_FEATURE_INCOMPAT_USERSPACE_STACK);
+}
+
 static inline int ocfs2_mount_local(struct ocfs2_super *osb)
 {
 	return (osb->s_feature_incompat & OCFS2_FEATURE_INCOMPAT_LOCAL_MOUNT);
diff --git a/fs/ocfs2/ocfs2_fs.h b/fs/ocfs2/ocfs2_fs.h
index c49502329ab..52c42666515 100644
--- a/fs/ocfs2/ocfs2_fs.h
+++ b/fs/ocfs2/ocfs2_fs.h
@@ -89,7 +89,8 @@
 #define OCFS2_FEATURE_INCOMPAT_SUPP	(OCFS2_FEATURE_INCOMPAT_LOCAL_MOUNT \
 					 | OCFS2_FEATURE_INCOMPAT_SPARSE_ALLOC \
 					 | OCFS2_FEATURE_INCOMPAT_INLINE_DATA \
-					 | OCFS2_FEATURE_INCOMPAT_EXTENDED_SLOT_MAP)
+					 | OCFS2_FEATURE_INCOMPAT_EXTENDED_SLOT_MAP \
+					 | OCFS2_FEATURE_INCOMPAT_USERSPACE_STACK)
 #define OCFS2_FEATURE_RO_COMPAT_SUPP	OCFS2_FEATURE_RO_COMPAT_UNWRITTEN
 
 /*
@@ -131,6 +132,17 @@
 
 
 /*
+ * Support for alternate, userspace cluster stacks.  If set, the superblock
+ * field s_cluster_info contains a tag for the alternate stack in use as
+ * well as the name of the cluster being joined.
+ * mount.ocfs2 must pass in a matching stack name.
+ *
+ * If not set, the classic stack will be used.  This is compatbile with
+ * all older versions.
+ */
+#define OCFS2_FEATURE_INCOMPAT_USERSPACE_STACK	0x0080
+
+/*
  * backup superblock flag is used to indicate that this volume
  * has backup superblocks.
  */
@@ -272,6 +284,10 @@ struct ocfs2_new_group_input {
 #define OCFS2_VOL_UUID_LEN		16
 #define OCFS2_MAX_VOL_LABEL_LEN		64
 
+/* The alternate, userspace stack fields */
+#define OCFS2_STACK_LABEL_LEN		4
+#define OCFS2_CLUSTER_NAME_LEN		16
+
 /* Journal limits (in bytes) */
 #define OCFS2_MIN_JOURNAL_SIZE		(4 * 1024 * 1024)
 
@@ -513,6 +529,13 @@ struct ocfs2_slot_map_extended {
  */
 };
 
+struct ocfs2_cluster_info {
+/*00*/	__u8   ci_stack[OCFS2_STACK_LABEL_LEN];
+	__le32 ci_reserved;
+/*08*/	__u8   ci_cluster[OCFS2_CLUSTER_NAME_LEN];
+/*18*/
+};
+
 /*
  * On disk superblock for OCFS2
  * Note that it is contained inside an ocfs2_dinode, so all offsets
@@ -545,7 +568,20 @@ struct ocfs2_super_block {
 					 * group header */
 /*50*/	__u8  s_label[OCFS2_MAX_VOL_LABEL_LEN];	/* Label for mounting, etc. */
 /*90*/	__u8  s_uuid[OCFS2_VOL_UUID_LEN];	/* 128-bit uuid */
-/*A0*/
+/*A0*/  struct ocfs2_cluster_info s_cluster_info; /* Selected userspace
+						     stack.  Only valid
+						     with INCOMPAT flag. */
+/*B8*/  __le64 s_reserved2[17];		/* Fill out superblock */
+/*140*/
+
+	/*
+	 * NOTE: As stated above, all offsets are relative to
+	 * ocfs2_dinode.id2, which is at 0xC0 in the inode.
+	 * 0xC0 + 0x140 = 0x200 or 512 bytes.  A superblock must fit within
+	 * our smallest blocksize, which is 512 bytes.  To ensure this,
+	 * we reserve the space in s_reserved2.  Anything past s_reserved2
+	 * will not be available on the smallest blocksize.
+	 */
 };
 
 /*
diff --git a/fs/ocfs2/super.c b/fs/ocfs2/super.c
index e27a0d47ea2..96ebe36d5d7 100644
--- a/fs/ocfs2/super.c
+++ b/fs/ocfs2/super.c
@@ -87,6 +87,7 @@ struct mount_options
 	unsigned int	atime_quantum;
 	signed short	slot;
 	unsigned int	localalloc_opt;
+	char		cluster_stack[OCFS2_STACK_LABEL_LEN + 1];
 };
 
 static int ocfs2_parse_options(struct super_block *sb, char *options,
@@ -152,6 +153,7 @@ enum {
 	Opt_commit,
 	Opt_localalloc,
 	Opt_localflocks,
+	Opt_stack,
 	Opt_err,
 };
 
@@ -170,6 +172,7 @@ static match_table_t tokens = {
 	{Opt_commit, "commit=%u"},
 	{Opt_localalloc, "localalloc=%d"},
 	{Opt_localflocks, "localflocks"},
+	{Opt_stack, "cluster_stack=%s"},
 	{Opt_err, NULL}
 };
 
@@ -549,8 +552,17 @@ static int ocfs2_verify_heartbeat(struct ocfs2_super *osb)
 		}
 	}
 
+	if (ocfs2_userspace_stack(osb)) {
+		if (osb->s_mount_opt & OCFS2_MOUNT_HB_LOCAL) {
+			mlog(ML_ERROR, "Userspace stack expected, but "
+			     "o2cb heartbeat arguments passed to mount\n");
+			return -EINVAL;
+		}
+	}
+
 	if (!(osb->s_mount_opt & OCFS2_MOUNT_HB_LOCAL)) {
-		if (!ocfs2_mount_local(osb) && !ocfs2_is_hard_readonly(osb)) {
+		if (!ocfs2_mount_local(osb) && !ocfs2_is_hard_readonly(osb) &&
+		    !ocfs2_userspace_stack(osb)) {
 			mlog(ML_ERROR, "Heartbeat has to be started to mount "
 			     "a read-write clustered device.\n");
 			return -EINVAL;
@@ -560,6 +572,35 @@ static int ocfs2_verify_heartbeat(struct ocfs2_super *osb)
 	return 0;
 }
 
+/*
+ * If we're using a userspace stack, mount should have passed
+ * a name that matches the disk.  If not, mount should not
+ * have passed a stack.
+ */
+static int ocfs2_verify_userspace_stack(struct ocfs2_super *osb,
+					struct mount_options *mopt)
+{
+	if (!ocfs2_userspace_stack(osb) && mopt->cluster_stack[0]) {
+		mlog(ML_ERROR,
+		     "cluster stack passed to mount, but this filesystem "
+		     "does not support it\n");
+		return -EINVAL;
+	}
+
+	if (ocfs2_userspace_stack(osb) &&
+	    strncmp(osb->osb_cluster_stack, mopt->cluster_stack,
+		    OCFS2_STACK_LABEL_LEN)) {
+		mlog(ML_ERROR,
+		     "cluster stack passed to mount (\"%s\") does not "
+		     "match the filesystem (\"%s\")\n",
+		     mopt->cluster_stack,
+		     osb->osb_cluster_stack);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
 static int ocfs2_fill_super(struct super_block *sb, void *data, int silent)
 {
 	struct dentry *root;
@@ -598,6 +639,10 @@ static int ocfs2_fill_super(struct super_block *sb, void *data, int silent)
 	osb->osb_commit_interval = parsed_options.commit_interval;
 	osb->local_alloc_size = parsed_options.localalloc_opt;
 
+	status = ocfs2_verify_userspace_stack(osb, &parsed_options);
+	if (status)
+		goto read_super_error;
+
 	sb->s_magic = OCFS2_SUPER_MAGIC;
 
 	/* Hard readonly mode only if: bdev_read_only, MS_RDONLY,
@@ -752,6 +797,7 @@ static int ocfs2_parse_options(struct super_block *sb,
 	mopt->atime_quantum = OCFS2_DEFAULT_ATIME_QUANTUM;
 	mopt->slot = OCFS2_INVALID_SLOT;
 	mopt->localalloc_opt = OCFS2_DEFAULT_LOCAL_ALLOC_SIZE;
+	mopt->cluster_stack[0] = '\0';
 
 	if (!options) {
 		status = 1;
@@ -853,6 +899,25 @@ static int ocfs2_parse_options(struct super_block *sb,
 			if (!is_remount)
 				mopt->mount_opt |= OCFS2_MOUNT_LOCALFLOCKS;
 			break;
+		case Opt_stack:
+			/* Check both that the option we were passed
+			 * is of the right length and that it is a proper
+			 * string of the right length.
+			 */
+			if (((args[0].to - args[0].from) !=
+			     OCFS2_STACK_LABEL_LEN) ||
+			    (strnlen(args[0].from,
+				     OCFS2_STACK_LABEL_LEN) !=
+			     OCFS2_STACK_LABEL_LEN)) {
+				mlog(ML_ERROR,
+				     "Invalid cluster_stack option\n");
+				status = 0;
+				goto bail;
+			}
+			memcpy(mopt->cluster_stack, args[0].from,
+			       OCFS2_STACK_LABEL_LEN);
+			mopt->cluster_stack[OCFS2_STACK_LABEL_LEN] = '\0';
+			break;
 		default:
 			mlog(ML_ERROR,
 			     "Unrecognized mount option \"%s\" "
@@ -911,6 +976,10 @@ static int ocfs2_show_options(struct seq_file *s, struct vfsmount *mnt)
 	if (opts & OCFS2_MOUNT_LOCALFLOCKS)
 		seq_printf(s, ",localflocks,");
 
+	if (osb->osb_cluster_stack[0])
+		seq_printf(s, ",cluster_stack=%.*s", OCFS2_STACK_LABEL_LEN,
+			   osb->osb_cluster_stack);
+
 	return 0;
 }
 
@@ -1403,6 +1472,25 @@ static int ocfs2_initialize_super(struct super_block *sb,
 		goto bail;
 	}
 
+	if (ocfs2_userspace_stack(osb)) {
+		memcpy(osb->osb_cluster_stack,
+		       OCFS2_RAW_SB(di)->s_cluster_info.ci_stack,
+		       OCFS2_STACK_LABEL_LEN);
+		osb->osb_cluster_stack[OCFS2_STACK_LABEL_LEN] = '\0';
+		if (strlen(osb->osb_cluster_stack) != OCFS2_STACK_LABEL_LEN) {
+			mlog(ML_ERROR,
+			     "couldn't mount because of an invalid "
+			     "cluster stack label (%s) \n",
+			     osb->osb_cluster_stack);
+			status = -EINVAL;
+			goto bail;
+		}
+	} else {
+		/* The empty string is identical with classic tools that
+		 * don't know about s_cluster_info. */
+		osb->osb_cluster_stack[0] = '\0';
+	}
+
 	get_random_bytes(&osb->s_next_generation, sizeof(u32));
 
 	/* FIXME