ceph: add feature bits to connection handshake (protocol change)

Define supported and required feature set.  Fail connection if the server
requires features we do not support (TAG_FEATURES), or if the server does
not support features we require.

Signed-off-by: Sage Weil <sage@newdream.net>

4 files changed, 53 insertions, 17 deletions

diff --git a/fs/ceph/ceph_fs.h b/fs/ceph/ceph_fs.h
index e87dfa6ec8e5..db3fed33c4aa 100644
--- a/fs/ceph/ceph_fs.h
+++ b/fs/ceph/ceph_fs.h
@@ -50,6 +50,12 @@
 #define CEPH_MAX_MON   31
 
 
+/*
+ * feature bits
+ */
+#define CEPH_FEATURE_SUPPORTED  0
+#define CEPH_FEATURE_REQUIRED   0
+
 
 /*
  * ceph_file_layout - describe data layout for a file/inode
diff --git a/fs/ceph/dir.c b/fs/ceph/dir.c
index fde839c61236..5107384ee029 100644
--- a/fs/ceph/dir.c
+++ b/fs/ceph/dir.c
@@ -1135,9 +1135,9 @@ void ceph_dentry_lru_add(struct dentry *dn)
 {
         struct ceph_dentry_info *di = ceph_dentry(dn);
         struct ceph_mds_client *mdsc;
-        dout("dentry_lru_add %p %p\t%.*s\n",
-                        di, dn, dn->d_name.len, dn->d_name.name);
 
+        dout("dentry_lru_add %p %p '%.*s'\n", di, dn,
+             dn->d_name.len, dn->d_name.name);
         if (di) {
                 mdsc = &ceph_client(dn->d_sb)->mdsc;
                 spin_lock(&mdsc->dentry_lru_lock);
@@ -1151,9 +1151,9 @@ void ceph_dentry_lru_touch(struct dentry *dn)
 {
         struct ceph_dentry_info *di = ceph_dentry(dn);
         struct ceph_mds_client *mdsc;
-        dout("dentry_lru_touch %p %p\t%.*s\n",
-                        di, dn, dn->d_name.len, dn->d_name.name);
 
+        dout("dentry_lru_touch %p %p '%.*s'\n", di, dn,
+             dn->d_name.len, dn->d_name.name);
         if (di) {
                 mdsc = &ceph_client(dn->d_sb)->mdsc;
                 spin_lock(&mdsc->dentry_lru_lock);
@@ -1167,8 +1167,8 @@ void ceph_dentry_lru_del(struct dentry *dn)
         struct ceph_dentry_info *di = ceph_dentry(dn);
         struct ceph_mds_client *mdsc;
 
-        dout("dentry_lru_del %p %p\t%.*s\n",
-                        di, dn, dn->d_name.len, dn->d_name.name);
+        dout("dentry_lru_del %p %p '%.*s'\n", di, dn,
+             dn->d_name.len, dn->d_name.name);
         if (di) {
                 mdsc = &ceph_client(dn->d_sb)->mdsc;
                 spin_lock(&mdsc->dentry_lru_lock);
diff --git a/fs/ceph/messenger.c b/fs/ceph/messenger.c
index 506b638a023b..68052f664280 100644
--- a/fs/ceph/messenger.c
+++ b/fs/ceph/messenger.c
@@ -631,6 +631,7 @@ static void prepare_write_connect(struct ceph_messenger *msgr,
         dout("prepare_write_connect %p cseq=%d gseq=%d proto=%d\n", con,
              con->connect_seq, global_seq, proto);
 
+        con->out_connect.features = CEPH_FEATURE_SUPPORTED;
         con->out_connect.host_type = cpu_to_le32(CEPH_ENTITY_TYPE_CLIENT);
         con->out_connect.connect_seq = cpu_to_le32(con->connect_seq);
         con->out_connect.global_seq = cpu_to_le32(global_seq);
@@ -1080,15 +1081,37 @@ static int process_banner(struct ceph_connection *con)
         return 0;
 }
 
+static void fail_protocol(struct ceph_connection *con)
+{
+        reset_connection(con);
+        set_bit(CLOSED, &con->state);  /* in case there's queued work */
+
+        mutex_unlock(&con->mutex);
+        if (con->ops->bad_proto)
+                con->ops->bad_proto(con);
+        mutex_lock(&con->mutex);
+}
+
 static int process_connect(struct ceph_connection *con)
 {
+        u64 sup_feat = CEPH_FEATURE_SUPPORTED;
+        u64 req_feat = CEPH_FEATURE_REQUIRED;
+        u64 server_feat = le64_to_cpu(con->in_reply.features);
+
         dout("process_connect on %p tag %d\n", con, (int)con->in_tag);
 
         switch (con->in_reply.tag) {
+        case CEPH_MSGR_TAG_FEATURES:
+                pr_err("%s%lld %s feature set mismatch,"
+                       " my %llx < server's %llx, missing %llx\n",
+                       ENTITY_NAME(con->peer_name),
+                       pr_addr(&con->peer_addr.in_addr),
+                       sup_feat, server_feat, server_feat & ~sup_feat);
+                con->error_msg = "missing required protocol features";
+                fail_protocol(con);
+                return -1;
+
         case CEPH_MSGR_TAG_BADPROTOVER:
-                dout("process_connect got BADPROTOVER my %d != their %d\n",
-                     le32_to_cpu(con->out_connect.protocol_version),
-                     le32_to_cpu(con->in_reply.protocol_version));
                 pr_err("%s%lld %s protocol version mismatch,"
                        " my %d != server's %d\n",
                        ENTITY_NAME(con->peer_name),
@@ -1096,13 +1119,7 @@ static int process_connect(struct ceph_connection *con)
                        le32_to_cpu(con->out_connect.protocol_version),
                        le32_to_cpu(con->in_reply.protocol_version));
                 con->error_msg = "protocol version mismatch";
-                reset_connection(con);
-                set_bit(CLOSED, &con->state);  /* in case there's queued work */
-
-                mutex_unlock(&con->mutex);
-                if (con->ops->bad_proto)
-                        con->ops->bad_proto(con);
-                mutex_lock(&con->mutex);
+                fail_protocol(con);
                 return -1;
 
         case CEPH_MSGR_TAG_BADAUTHORIZER:
@@ -1173,6 +1190,16 @@ static int process_connect(struct ceph_connection *con)
                 break;
 
         case CEPH_MSGR_TAG_READY:
+                if (req_feat & ~server_feat) {
+                        pr_err("%s%lld %s protocol feature mismatch,"
+                               " my required %llx > server's %llx, need %llx\n",
+                               ENTITY_NAME(con->peer_name),
+                               pr_addr(&con->peer_addr.in_addr),
+                               req_feat, server_feat, req_feat & ~server_feat);
+                        con->error_msg = "missing required protocol features";
+                        fail_protocol(con);
+                        return -1;
+                }
                 clear_bit(CONNECTING, &con->state);
                 con->peer_global_seq = le32_to_cpu(con->in_reply.global_seq);
                 con->connect_seq++;
diff --git a/fs/ceph/msgr.h b/fs/ceph/msgr.h
index e46d8b806dea..be83f93182ee 100644
--- a/fs/ceph/msgr.h
+++ b/fs/ceph/msgr.h
@@ -21,7 +21,7 @@
  * whenever the wire protocol changes.  try to keep this string length
  * constant.
  */
-#define CEPH_BANNER "ceph v025"
+#define CEPH_BANNER "ceph v026"
 #define CEPH_BANNER_MAX_LEN 30
 
 
@@ -100,12 +100,14 @@ struct ceph_entity_inst {
 #define CEPH_MSGR_TAG_KEEPALIVE     9  /* just a keepalive byte! */
 #define CEPH_MSGR_TAG_BADPROTOVER  10  /* bad protocol version */
 #define CEPH_MSGR_TAG_BADAUTHORIZER 11 /* bad authorizer */
+#define CEPH_MSGR_TAG_FEATURES      12 /* insufficient features */
 
 
 /*
  * connection negotiation
  */
 struct ceph_msg_connect {
+        __le64 features;     /* supported feature bits */
         __le32 host_type;    /* CEPH_ENTITY_TYPE_* */
         __le32 global_seq;   /* count connections initiated by this host */
         __le32 connect_seq;  /* count connections initiated in this session */
@@ -117,6 +119,7 @@ struct ceph_msg_connect {
 
 struct ceph_msg_connect_reply {
         __u8 tag;
+        __le64 features;     /* feature bits for this session */
         __le32 global_seq;
         __le32 connect_seq;
         __le32 protocol_version;