[15/18] cifs: reconnect unresponsive servers

Commit Message

Jeff Layton Dec. 27, 2010, 2:30 a.m. UTC

None

Patch

diff --git a/fs/cifs/cifsfs.c b/fs/cifs/cifsfs.c
index e0fabbf..27fa0a2 100644
--- a/fs/cifs/cifsfs.c
+++ b/fs/cifs/cifsfs.c
@@ -80,6 +80,11 @@  bool sign_zero_copy = false;
 module_param(sign_zero_copy, bool, 0644);
 MODULE_PARM_DESC(sign_zero_copy, "Don't copy pages on write with signing "
 				 "enabled. Default: N");
+unsigned short echo_retries = 5;
+module_param(echo_retries, ushort, 0644);
+MODULE_PARM_DESC(echo_retries, "Number of echo attempts before giving up and "
+				 "reconnecting server. Default: 5. 0 means "
+				 "never reconnect.");
 extern mempool_t *cifs_sm_req_poolp;
 extern mempool_t *cifs_req_poolp;
 extern mempool_t *cifs_mid_poolp;
diff --git a/fs/cifs/cifsglob.h b/fs/cifs/cifsglob.h
index 64d69f9..1dc74f4 100644
--- a/fs/cifs/cifsglob.h
+++ b/fs/cifs/cifsglob.h
@@ -799,6 +799,9 @@  GLOBAL_EXTERN unsigned int cifs_min_small;  /* min size of small buf pool */
 GLOBAL_EXTERN unsigned int cifs_max_pending; /* MAX requests at once to server*/
 GLOBAL_EXTERN bool sign_zero_copy; /* don't copy written pages with signing */
 
+/* reconnect after this many failed echo attempts */
+GLOBAL_EXTERN unsigned short echo_retries;
+
 void cifs_oplock_break(struct work_struct *work);
 void cifs_oplock_break_get(struct cifsFileInfo *cfile);
 void cifs_oplock_break_put(struct cifsFileInfo *cfile);
diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c
index 57187c6..0e7ae1e 100644
--- a/fs/cifs/connect.c
+++ b/fs/cifs/connect.c
@@ -186,6 +186,7 @@  cifs_reconnect(struct TCP_Server_Info *server)
 	kfree(server->session_key.response);
 	server->session_key.response = NULL;
 	server->session_key.len = 0;
+	server->lstrp = jiffies;
 	mutex_unlock(&server->srv_mutex);
 
 	/* mark submitted MIDs for retry and issue callback */
@@ -420,7 +421,20 @@  cifs_demultiplex_thread(struct TCP_Server_Info *server)
 		smb_msg.msg_control = NULL;
 		smb_msg.msg_controllen = 0;
 		pdu_length = 4; /* enough to get RFC1001 header */
+
 incomplete_rcv:
+		if (echo_retries > 0 &&
+		    time_after(jiffies, server->lstrp +
+					(echo_retries * SMB_ECHO_INTERVAL))) {
+			cERROR(1, "Server %s has not responded in %d seconds. "
+				  "Reconnecting...", server->hostname,
+				  (echo_retries * SMB_ECHO_INTERVAL / HZ));
+			cifs_reconnect(server);
+			csocket = server->ssocket;
+			wake_up(&server->response_q);
+			continue;
+		}
+
 		length =
 		    kernel_recvmsg(csocket, &smb_msg,
 				&iov, 1, pdu_length, 0 /* BB other flags? */);
@@ -581,6 +595,8 @@  incomplete_rcv:
 		}
 
 		mid_entry = NULL;
+		server->lstrp = jiffies;
+
 		spin_lock(&GlobalMid_Lock);
 		list_for_each_safe(tmp, tmp2, &server->pending_mid_q) {
 			mid_entry = list_entry(tmp, struct mid_q_entry, qhead);
@@ -629,10 +645,6 @@  multi_t2_fnd:
 #ifdef CONFIG_CIFS_STATS2
 				mid_entry->when_received = jiffies;
 #endif
-				/* so we do not time out requests to  server
-				which is still responding (since server could
-				be busy but not dead) */
-				server->lstrp = jiffies;
 				break;
 			}
 			mid_entry = NULL;
@@ -1683,6 +1695,7 @@  cifs_get_tcp_session(struct smb_vol *volume_info)
 		volume_info->target_rfc1001_name, RFC1001_NAME_LEN_WITH_NULL);
 	tcp_ses->session_estab = false;
 	tcp_ses->sequence_number = 0;
+	tcp_ses->lstrp = jiffies;
 	INIT_LIST_HEAD(&tcp_ses->tcp_ses_list);
 	INIT_LIST_HEAD(&tcp_ses->smb_ses_list);
 	INIT_DELAYED_WORK(&tcp_ses->echo, cifs_echo_request);