Merge git://git.samba.org/sfrench/cifs-2.6

Pull CIFS fixes from Steve French

* git://git.samba.org/sfrench/cifs-2.6:
  cifs: clean up ordering in exit_cifs
  cifs: clean up call to cifs_dfs_release_automount_timer()
  CIFS: Delete echo_retries module parm
  CIFS: Prepare credits code for a slot reservation
  CIFS: Make wait_for_free_request killable
  CIFS: Introduce credit-based flow control
  CIFS: Simplify inFlight logic
  cifs: fix issue mounting of DFS ROOT when redirecting from one domain controller to the next
  CIFS: Respect negotiated MaxMpxCount
  CIFS: Fix a spurious error in cifs_push_posix_locks

fs/cifs/README

@@ -753,10 +753,6 @@ module loading or during the runtime by using the interface
 
 i.e. echo "value" > /sys/module/cifs/parameters/<param>
 
-1. echo_retries - The number of echo attempts before giving up and
-		  reconnecting to the server. The default is 5. The value 0
-		  means never reconnect.
-
-2. enable_oplocks - Enable or disable oplocks. Oplocks are enabled by default.
+1. enable_oplocks - Enable or disable oplocks. Oplocks are enabled by default.
 		    [Y/y/1]. To disable use any of [N/n/0].
 

fs/cifs/cifs_debug.c

@@ -171,8 +171,7 @@ static int cifs_debug_data_proc_show(struct seq_file *m, void *v)
 			seq_printf(m, "TCP status: %d\n\tLocal Users To "
 				   "Server: %d SecMode: 0x%x Req On Wire: %d",
 				   server->tcpStatus, server->srv_count,
-				   server->sec_mode,
-				   atomic_read(&server->inFlight));
+				   server->sec_mode, in_flight(server));
 
 #ifdef CONFIG_CIFS_STATS2
 			seq_printf(m, " In Send: %d In MaxReq Wait: %d",

fs/cifs/cifsfs.c

@@ -76,12 +76,7 @@ MODULE_PARM_DESC(cifs_min_small, "Small network buffers in pool. Default: 30 "
 unsigned int cifs_max_pending = CIFS_MAX_REQ;
 module_param(cifs_max_pending, int, 0444);
 MODULE_PARM_DESC(cifs_max_pending, "Simultaneous requests to server. "
-				   "Default: 50 Range: 2 to 256");
-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.");
+				   "Default: 32767 Range: 2 to 32767.");
 module_param(enable_oplocks, bool, 0644);
 MODULE_PARM_DESC(enable_oplocks, "Enable or disable oplocks (bool). Default:"
 				 "y/Y/1");
@@ -1111,9 +1106,9 @@ init_cifs(void)
 	if (cifs_max_pending < 2) {
 		cifs_max_pending = 2;
 		cFYI(1, "cifs_max_pending set to min of 2");
-	} else if (cifs_max_pending > 256) {
-		cifs_max_pending = 256;
-		cFYI(1, "cifs_max_pending set to max of 256");
+	} else if (cifs_max_pending > CIFS_MAX_REQ) {
+		cifs_max_pending = CIFS_MAX_REQ;
+		cFYI(1, "cifs_max_pending set to max of %u", CIFS_MAX_REQ);
 	}
 
 	rc = cifs_fscache_register();
@@ -1175,22 +1170,20 @@ static void __exit
 exit_cifs(void)
 {
 	cFYI(DBG2, "exit_cifs");
-	cifs_proc_clean();
-	cifs_fscache_unregister();
-#ifdef CONFIG_CIFS_DFS_UPCALL
+	unregister_filesystem(&cifs_fs_type);
 	cifs_dfs_release_automount_timer();
-#endif
 #ifdef CONFIG_CIFS_ACL
 	cifs_destroy_idmaptrees();
 	exit_cifs_idmap();
 #endif
 #ifdef CONFIG_CIFS_UPCALL
 	unregister_key_type(&cifs_spnego_key_type);
 #endif
-	unregister_filesystem(&cifs_fs_type);
-	cifs_destroy_inodecache();
-	cifs_destroy_mids();
 	cifs_destroy_request_bufs();
+	cifs_destroy_mids();
+	cifs_destroy_inodecache();
+	cifs_fscache_unregister();
+	cifs_proc_clean();
 }
 
 MODULE_AUTHOR("Steve French <[email protected]>");

fs/cifs/cifsglob.h

@@ -55,14 +55,9 @@
 
 /*
  * MAX_REQ is the maximum number of requests that WE will send
- * on one socket concurrently. It also matches the most common
- * value of max multiplex returned by servers.  We may
- * eventually want to use the negotiated value (in case
- * future servers can handle more) when we are more confident that
- * we will not have problems oveloading the socket with pending
- * write data.
+ * on one socket concurrently.
  */
-#define CIFS_MAX_REQ 50
+#define CIFS_MAX_REQ 32767
 
 #define RFC1001_NAME_LEN 15
 #define RFC1001_NAME_LEN_WITH_NULL (RFC1001_NAME_LEN + 1)
@@ -255,14 +250,17 @@ struct TCP_Server_Info {
 	bool noblocksnd;		/* use blocking sendmsg */
 	bool noautotune;		/* do not autotune send buf sizes */
 	bool tcp_nodelay;
-	atomic_t inFlight;  /* number of requests on the wire to server */
+	int credits;  /* send no more requests at once */
+	unsigned int in_flight;  /* number of requests on the wire to server */
+	spinlock_t req_lock;  /* protect the two values above */
 	struct mutex srv_mutex;
 	struct task_struct *tsk;
 	char server_GUID[16];
 	char sec_mode;
 	bool session_estab; /* mark when very first sess is established */
 	u16 dialect; /* dialect index that server chose */
 	enum securityEnum secType;
+	bool oplocks:1; /* enable oplocks */
 	unsigned int maxReq;	/* Clients should submit no more */
 	/* than maxReq distinct unanswered SMBs to the server when using  */
 	/* multiplexed reads or writes */
@@ -307,6 +305,36 @@ struct TCP_Server_Info {
 #endif
 };
 
+static inline unsigned int
+in_flight(struct TCP_Server_Info *server)
+{
+	unsigned int num;
+	spin_lock(&server->req_lock);
+	num = server->in_flight;
+	spin_unlock(&server->req_lock);
+	return num;
+}
+
+static inline int*
+get_credits_field(struct TCP_Server_Info *server)
+{
+	/*
+	 * This will change to switch statement when we reserve slots for echos
+	 * and oplock breaks.
+	 */
+	return &server->credits;
+}
+
+static inline bool
+has_credits(struct TCP_Server_Info *server, int *credits)
+{
+	int num;
+	spin_lock(&server->req_lock);
+	num = *credits;
+	spin_unlock(&server->req_lock);
+	return num > 0;
+}
+
 /*
  * Macros to allow the TCP_Server_Info->net field and related code to drop out
  * when CONFIG_NET_NS isn't set.
@@ -1010,9 +1038,6 @@ GLOBAL_EXTERN unsigned int cifs_min_rcv;    /* min size of big ntwrk buf pool */
 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*/
 
-/* reconnect after this many failed echo attempts */
-GLOBAL_EXTERN unsigned short echo_retries;
-
 #ifdef CONFIG_CIFS_ACL
 GLOBAL_EXTERN struct rb_root uidtree;
 GLOBAL_EXTERN struct rb_root gidtree;

fs/cifs/cifsproto.h

@@ -88,6 +88,9 @@ extern int SendReceiveBlockingLock(const unsigned int xid,
 			struct smb_hdr *in_buf ,
 			struct smb_hdr *out_buf,
 			int *bytes_returned);
+extern void cifs_add_credits(struct TCP_Server_Info *server,
+			     const unsigned int add);
+extern void cifs_set_credits(struct TCP_Server_Info *server, const int val);
 extern int checkSMB(struct smb_hdr *smb, __u16 mid, unsigned int length);
 extern bool is_valid_oplock_break(struct smb_hdr *smb,
 				  struct TCP_Server_Info *);
@@ -168,7 +171,13 @@ extern struct smb_vol *cifs_get_volume_info(char *mount_data,
 					    const char *devname);
 extern int cifs_mount(struct cifs_sb_info *, struct smb_vol *);
 extern void cifs_umount(struct cifs_sb_info *);
+
+#if IS_ENABLED(CONFIG_CIFS_DFS_UPCALL)
 extern void cifs_dfs_release_automount_timer(void);
+#else /* ! IS_ENABLED(CONFIG_CIFS_DFS_UPCALL) */
+#define cifs_dfs_release_automount_timer()	do { } while (0)
+#endif /* ! IS_ENABLED(CONFIG_CIFS_DFS_UPCALL) */
+
 void cifs_proc_init(void);
 void cifs_proc_clean(void);
 

fs/cifs/cifssmb.c

@@ -458,7 +458,10 @@ CIFSSMBNegotiate(unsigned int xid, struct cifs_ses *ses)
 			goto neg_err_exit;
 		}
 		server->sec_mode = (__u8)le16_to_cpu(rsp->SecurityMode);
-		server->maxReq = le16_to_cpu(rsp->MaxMpxCount);
+		server->maxReq = min_t(unsigned int,
+				       le16_to_cpu(rsp->MaxMpxCount),
+				       cifs_max_pending);
+		cifs_set_credits(server, server->maxReq);
 		server->maxBuf = le16_to_cpu(rsp->MaxBufSize);
 		server->max_vcs = le16_to_cpu(rsp->MaxNumberVcs);
 		/* even though we do not use raw we might as well set this
@@ -564,7 +567,9 @@ CIFSSMBNegotiate(unsigned int xid, struct cifs_ses *ses)
 
 	/* one byte, so no need to convert this or EncryptionKeyLen from
 	   little endian */
-	server->maxReq = le16_to_cpu(pSMBr->MaxMpxCount);
+	server->maxReq = min_t(unsigned int, le16_to_cpu(pSMBr->MaxMpxCount),
+			       cifs_max_pending);
+	cifs_set_credits(server, server->maxReq);
 	/* probably no need to store and check maxvcs */
 	server->maxBuf = le32_to_cpu(pSMBr->MaxBufferSize);
 	server->max_rw = le32_to_cpu(pSMBr->MaxRawSize);
@@ -716,8 +721,7 @@ cifs_echo_callback(struct mid_q_entry *mid)
 	struct TCP_Server_Info *server = mid->callback_data;
 
 	DeleteMidQEntry(mid);
-	atomic_dec(&server->inFlight);
-	wake_up(&server->request_q);
+	cifs_add_credits(server, 1);
 }
 
 int
@@ -1669,8 +1673,7 @@ cifs_readv_callback(struct mid_q_entry *mid)
 
 	queue_work(system_nrt_wq, &rdata->work);
 	DeleteMidQEntry(mid);
-	atomic_dec(&server->inFlight);
-	wake_up(&server->request_q);
+	cifs_add_credits(server, 1);
 }
 
 /* cifs_async_readv - send an async write, and set up mid to handle result */
@@ -2110,8 +2113,7 @@ cifs_writev_callback(struct mid_q_entry *mid)
 
 	queue_work(system_nrt_wq, &wdata->work);
 	DeleteMidQEntry(mid);
-	atomic_dec(&tcon->ses->server->inFlight);
-	wake_up(&tcon->ses->server->request_q);
+	cifs_add_credits(tcon->ses->server, 1);
 }
 
 /* cifs_async_writev - send an async write, and set up mid to handle result */

fs/cifs/connect.c

@@ -373,12 +373,22 @@ allocate_buffers(struct TCP_Server_Info *server)
 static bool
 server_unresponsive(struct TCP_Server_Info *server)
 {
-	if (echo_retries > 0 && server->tcpStatus == CifsGood &&
-	    time_after(jiffies, server->lstrp +
-				(echo_retries * SMB_ECHO_INTERVAL))) {
+	/*
+	 * We need to wait 2 echo intervals to make sure we handle such
+	 * situations right:
+	 * 1s  client sends a normal SMB request
+	 * 2s  client gets a response
+	 * 30s echo workqueue job pops, and decides we got a response recently
+	 *     and don't need to send another
+	 * ...
+	 * 65s kernel_recvmsg times out, and we see that we haven't gotten
+	 *     a response in >60s.
+	 */
+	if (server->tcpStatus == CifsGood &&
+	    time_after(jiffies, server->lstrp + 2 * SMB_ECHO_INTERVAL)) {
 		cERROR(1, "Server %s has not responded in %d seconds. "
 			  "Reconnecting...", server->hostname,
-			  (echo_retries * SMB_ECHO_INTERVAL / HZ));
+			  (2 * SMB_ECHO_INTERVAL) / HZ);
 		cifs_reconnect(server);
 		wake_up(&server->response_q);
 		return true;
@@ -642,19 +652,11 @@ static void clean_demultiplex_info(struct TCP_Server_Info *server)
 	spin_unlock(&GlobalMid_Lock);
 	wake_up_all(&server->response_q);
 
-	/*
-	 * Check if we have blocked requests that need to free. Note that
-	 * cifs_max_pending is normally 50, but can be set at module install
-	 * time to as little as two.
-	 */
-	spin_lock(&GlobalMid_Lock);
-	if (atomic_read(&server->inFlight) >= cifs_max_pending)
-		atomic_set(&server->inFlight, cifs_max_pending - 1);
-	/*
-	 * We do not want to set the max_pending too low or we could end up
-	 * with the counter going negative.
-	 */
-	spin_unlock(&GlobalMid_Lock);
+	/* check if we have blocked requests that need to free */
+	spin_lock(&server->req_lock);
+	if (server->credits <= 0)
+		server->credits = 1;
+	spin_unlock(&server->req_lock);
 	/*
 	 * Although there should not be any requests blocked on this queue it
 	 * can not hurt to be paranoid and try to wake up requests that may
@@ -1909,7 +1911,8 @@ cifs_get_tcp_session(struct smb_vol *volume_info)
 	tcp_ses->noblocksnd = volume_info->noblocksnd;
 	tcp_ses->noautotune = volume_info->noautotune;
 	tcp_ses->tcp_nodelay = volume_info->sockopt_tcp_nodelay;
-	atomic_set(&tcp_ses->inFlight, 0);
+	tcp_ses->in_flight = 0;
+	tcp_ses->credits = 1;
 	init_waitqueue_head(&tcp_ses->response_q);
 	init_waitqueue_head(&tcp_ses->request_q);
 	INIT_LIST_HEAD(&tcp_ses->pending_mid_q);
@@ -3371,7 +3374,7 @@ cifs_ra_pages(struct cifs_sb_info *cifs_sb)
 int
 cifs_mount(struct cifs_sb_info *cifs_sb, struct smb_vol *volume_info)
 {
-	int rc = 0;
+	int rc;
 	int xid;
 	struct cifs_ses *pSesInfo;
 	struct cifs_tcon *tcon;
@@ -3398,6 +3401,7 @@ cifs_mount(struct cifs_sb_info *cifs_sb, struct smb_vol *volume_info)
 		FreeXid(xid);
 	}
 #endif
+	rc = 0;
 	tcon = NULL;
 	pSesInfo = NULL;
 	srvTcp = NULL;
@@ -3759,9 +3763,11 @@ int cifs_negotiate_protocol(unsigned int xid, struct cifs_ses *ses)
 	if (server->maxBuf != 0)
 		return 0;
 
+	cifs_set_credits(server, 1);
 	rc = CIFSSMBNegotiate(xid, ses);
 	if (rc == -EAGAIN) {
 		/* retry only once on 1st time connection */
+		cifs_set_credits(server, 1);
 		rc = CIFSSMBNegotiate(xid, ses);
 		if (rc == -EAGAIN)
 			rc = -EHOSTDOWN;

fs/cifs/dir.c

@@ -171,7 +171,7 @@ cifs_create(struct inode *inode, struct dentry *direntry, umode_t mode,
 	}
 	tcon = tlink_tcon(tlink);
 
-	if (enable_oplocks)
+	if (tcon->ses->server->oplocks)
 		oplock = REQ_OPLOCK;
 
 	if (nd)
@@ -492,7 +492,7 @@ cifs_lookup(struct inode *parent_dir_inode, struct dentry *direntry,
 {
 	int xid;
 	int rc = 0; /* to get around spurious gcc warning, set to zero here */
-	__u32 oplock = enable_oplocks ? REQ_OPLOCK : 0;
+	__u32 oplock;
 	__u16 fileHandle = 0;
 	bool posix_open = false;
 	struct cifs_sb_info *cifs_sb;
@@ -518,6 +518,8 @@ cifs_lookup(struct inode *parent_dir_inode, struct dentry *direntry,
 	}
 	pTcon = tlink_tcon(tlink);
 
+	oplock = pTcon->ses->server->oplocks ? REQ_OPLOCK : 0;
+
 	/*
 	 * Don't allow the separator character in a path component.
 	 * The VFS will not allow "/", but "\" is allowed by posix.