Merge tag 'isci-for-3.5' into misc

isci update for 3.5

1/ Rework remote-node-context (RNC) handling for proper management of
   the silicon state machine in error handling and hot-plug conditions.
   Further details below, suffice to say if the RNC is mismanaged the
   silicon state machines may lock up.

2/ Refactor the initialization code to be reused for suspend/resume support

3/ Miscellaneous bug fixes to address discovery issues and hardware
   compatibility.

RNC rework details from Jeff Skirvin:

In the controller, devices as they appear on a SAS domain (or
direct-attached SATA devices) are represented by memory structures known
as "Remote Node Contexts" (RNCs).  These structures are transferred from
main memory to the controller using a set of register commands; these
commands include setting up the context ("posting"), removing the
context ("invalidating"), and commands to control the scheduling of
commands and connections to that remote device ("suspensions" and
"resumptions").  There is a similar path to control RNC scheduling from
the protocol engine, which interprets the results of command and data
transmission and reception.

In general, the controller chooses among non-suspended RNCs to find one
that has work requiring scheduling the transmission of command and data
frames to a target.  Likewise, when a target tries to return data back
to the initiator, the state of the RNC is used by the controller to
determine how to treat the incoming request. As an example, if the RNC
is in the state "TX/RX Suspended", incoming SSP connection requests from
the target will be rejected by the controller hardware.  When an RNC is
"TX Suspended", it will not be selected by the controller hardware to
start outgoing command or data operations (with certain priority-based
exceptions).

As mentioned above, there are two sources for management of the RNC
states: commands from driver software, and the result of transmission
and reception conditions of commands and data signaled by the controller
hardware.  As an example of the latter, if an outgoing SSP command ends
with a OPEN_REJECT(BAD_DESTINATION) status, the RNC state will
transition to the "TX Suspended" state, and this is signaled by the
controller hardware in the status to the completion of the pending
command as well as signaled in a controller hardware event.  Examples of
the former are included in the patch changelogs.

Driver software is required to suspend the RNC in a "TX/RX Suspended"
condition before any outstanding commands can be terminated.  Failure to
guarantee this can lead to a complete hardware hang condition.  Earlier
versions of the driver software did not guarantee that an RNC was
correctly managed before I/O termination, and so operated in an unsafe
way.

Further, the driver performed unnecessary contortions to preserve the
remote device command state and so was more complicated than it needed
to be.  A simplifying driver assumption is that once an I/O has entered
the error handler path without having completed in the target, the
requirement on the driver is that all use of the sas_task must end.
Beyond that, recovery of operation is dependent on libsas and other
components to reset, rediscover and reconfigure the device before normal
operation can restart.  In the driver, this simplifying assumption meant
that the RNC management could be reduced to entry into the suspended
state, terminating the targeted I/O request, and resuming the RNC as
needed for device-specific management such as an SSP Abort Task or LUN
Reset Management request.

10 files changed, 91 insertions, 39 deletions

diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c
index 2555816e7788..00bdb1d9d690 100644
--- a/net/netfilter/ipvs/ip_vs_core.c
+++ b/net/netfilter/ipvs/ip_vs_core.c
@@ -1924,6 +1924,7 @@ protocol_fail:
 control_fail:
 	ip_vs_estimator_net_cleanup(net);
 estimator_fail:
+	net->ipvs = NULL;
 	return -ENOMEM;
 }
 
@@ -1936,6 +1937,7 @@ static void __net_exit __ip_vs_cleanup(struct net *net)
 	ip_vs_control_net_cleanup(net);
 	ip_vs_estimator_net_cleanup(net);
 	IP_VS_DBG(2, "ipvs netns %d released\n", net_ipvs(net)->gen);
+	net->ipvs = NULL;
 }
 
 static void __net_exit __ip_vs_dev_cleanup(struct net *net)
@@ -1993,10 +1995,18 @@ static int __init ip_vs_init(void)
 		goto cleanup_dev;
 	}
 
+	ret = ip_vs_register_nl_ioctl();
+	if (ret < 0) {
+		pr_err("can't register netlink/ioctl.\n");
+		goto cleanup_hooks;
+	}
+
 	pr_info("ipvs loaded.\n");
 
 	return ret;
 
+cleanup_hooks:
+	nf_unregister_hooks(ip_vs_ops, ARRAY_SIZE(ip_vs_ops));
 cleanup_dev:
 	unregister_pernet_device(&ipvs_core_dev_ops);
 cleanup_sub:
@@ -2012,6 +2022,7 @@ exit:
 
 static void __exit ip_vs_cleanup(void)
 {
+	ip_vs_unregister_nl_ioctl();
 	nf_unregister_hooks(ip_vs_ops, ARRAY_SIZE(ip_vs_ops));
 	unregister_pernet_device(&ipvs_core_dev_ops);
 	unregister_pernet_subsys(&ipvs_core_ops);	/* free ip_vs struct */
diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c
index b3afe189af61..f5589987fc80 100644
--- a/net/netfilter/ipvs/ip_vs_ctl.c
+++ b/net/netfilter/ipvs/ip_vs_ctl.c
@@ -3680,7 +3680,7 @@ int __net_init ip_vs_control_net_init_sysctl(struct net *net)
 	return 0;
 }
 
-void __net_init ip_vs_control_net_cleanup_sysctl(struct net *net)
+void __net_exit ip_vs_control_net_cleanup_sysctl(struct net *net)
 {
 	struct netns_ipvs *ipvs = net_ipvs(net);
 
@@ -3692,7 +3692,7 @@ void __net_init ip_vs_control_net_cleanup_sysctl(struct net *net)
 #else
 
 int __net_init ip_vs_control_net_init_sysctl(struct net *net) { return 0; }
-void __net_init ip_vs_control_net_cleanup_sysctl(struct net *net) { }
+void __net_exit ip_vs_control_net_cleanup_sysctl(struct net *net) { }
 
 #endif
 
@@ -3750,21 +3750,10 @@ void __net_exit ip_vs_control_net_cleanup(struct net *net)
 	free_percpu(ipvs->tot_stats.cpustats);
 }
 
-int __init ip_vs_control_init(void)
+int __init ip_vs_register_nl_ioctl(void)
 {
-	int idx;
 	int ret;
 
-	EnterFunction(2);
-
-	/* Initialize svc_table, ip_vs_svc_fwm_table, rs_table */
-	for(idx = 0; idx < IP_VS_SVC_TAB_SIZE; idx++)  {
-		INIT_LIST_HEAD(&ip_vs_svc_table[idx]);
-		INIT_LIST_HEAD(&ip_vs_svc_fwm_table[idx]);
-	}
-
-	smp_wmb();	/* Do we really need it now ? */
-
 	ret = nf_register_sockopt(&ip_vs_sockopts);
 	if (ret) {
 		pr_err("cannot register sockopt.\n");
@@ -3776,28 +3765,47 @@ int __init ip_vs_control_init(void)
 		pr_err("cannot register Generic Netlink interface.\n");
 		goto err_genl;
 	}
-
-	ret = register_netdevice_notifier(&ip_vs_dst_notifier);
-	if (ret < 0)
-		goto err_notf;
-
-	LeaveFunction(2);
 	return 0;
 
-err_notf:
-	ip_vs_genl_unregister();
 err_genl:
 	nf_unregister_sockopt(&ip_vs_sockopts);
 err_sock:
 	return ret;
 }
 
+void ip_vs_unregister_nl_ioctl(void)
+{
+	ip_vs_genl_unregister();
+	nf_unregister_sockopt(&ip_vs_sockopts);
+}
+
+int __init ip_vs_control_init(void)
+{
+	int idx;
+	int ret;
+
+	EnterFunction(2);
+
+	/* Initialize svc_table, ip_vs_svc_fwm_table, rs_table */
+	for (idx = 0; idx < IP_VS_SVC_TAB_SIZE; idx++) {
+		INIT_LIST_HEAD(&ip_vs_svc_table[idx]);
+		INIT_LIST_HEAD(&ip_vs_svc_fwm_table[idx]);
+	}
+
+	smp_wmb();	/* Do we really need it now ? */
+
+	ret = register_netdevice_notifier(&ip_vs_dst_notifier);
+	if (ret < 0)
+		return ret;
+
+	LeaveFunction(2);
+	return 0;
+}
+
 
 void ip_vs_control_cleanup(void)
 {
 	EnterFunction(2);
 	unregister_netdevice_notifier(&ip_vs_dst_notifier);
-	ip_vs_genl_unregister();
-	nf_unregister_sockopt(&ip_vs_sockopts);
 	LeaveFunction(2);
 }
diff --git a/net/netfilter/ipvs/ip_vs_ftp.c b/net/netfilter/ipvs/ip_vs_ftp.c
index 538d74ee4f68..e39f693dd3e4 100644
--- a/net/netfilter/ipvs/ip_vs_ftp.c
+++ b/net/netfilter/ipvs/ip_vs_ftp.c
@@ -439,6 +439,8 @@ static int __net_init __ip_vs_ftp_init(struct net *net)
 	struct ip_vs_app *app;
 	struct netns_ipvs *ipvs = net_ipvs(net);
 
+	if (!ipvs)
+		return -ENOENT;
 	app = kmemdup(&ip_vs_ftp, sizeof(struct ip_vs_app), GFP_KERNEL);
 	if (!app)
 		return -ENOMEM;
diff --git a/net/netfilter/ipvs/ip_vs_lblc.c b/net/netfilter/ipvs/ip_vs_lblc.c
index 0f16283fd058..caa43704e55e 100644
--- a/net/netfilter/ipvs/ip_vs_lblc.c
+++ b/net/netfilter/ipvs/ip_vs_lblc.c
@@ -551,6 +551,9 @@ static int __net_init __ip_vs_lblc_init(struct net *net)
 {
 	struct netns_ipvs *ipvs = net_ipvs(net);
 
+	if (!ipvs)
+		return -ENOENT;
+
 	if (!net_eq(net, &init_net)) {
 		ipvs->lblc_ctl_table = kmemdup(vs_vars_table,
 						sizeof(vs_vars_table),
diff --git a/net/netfilter/ipvs/ip_vs_lblcr.c b/net/netfilter/ipvs/ip_vs_lblcr.c
index eec797f8cce7..548bf37aa29e 100644
--- a/net/netfilter/ipvs/ip_vs_lblcr.c
+++ b/net/netfilter/ipvs/ip_vs_lblcr.c
@@ -745,6 +745,9 @@ static int __net_init __ip_vs_lblcr_init(struct net *net)
 {
 	struct netns_ipvs *ipvs = net_ipvs(net);
 
+	if (!ipvs)
+		return -ENOENT;
+
 	if (!net_eq(net, &init_net)) {
 		ipvs->lblcr_ctl_table = kmemdup(vs_vars_table,
 						sizeof(vs_vars_table),
diff --git a/net/netfilter/ipvs/ip_vs_proto.c b/net/netfilter/ipvs/ip_vs_proto.c
index f843a8833250..ed835e67a07e 100644
--- a/net/netfilter/ipvs/ip_vs_proto.c
+++ b/net/netfilter/ipvs/ip_vs_proto.c
@@ -59,9 +59,6 @@ static int __used __init register_ip_vs_protocol(struct ip_vs_protocol *pp)
 	return 0;
 }
 
-#if defined(CONFIG_IP_VS_PROTO_TCP) || defined(CONFIG_IP_VS_PROTO_UDP) || \
-    defined(CONFIG_IP_VS_PROTO_SCTP) || defined(CONFIG_IP_VS_PROTO_AH) || \
-    defined(CONFIG_IP_VS_PROTO_ESP)
 /*
  *	register an ipvs protocols netns related data
  */
@@ -81,12 +78,18 @@ register_ip_vs_proto_netns(struct net *net, struct ip_vs_protocol *pp)
 	ipvs->proto_data_table[hash] = pd;
 	atomic_set(&pd->appcnt, 0);	/* Init app counter */
 
-	if (pp->init_netns != NULL)
-		pp->init_netns(net, pd);
+	if (pp->init_netns != NULL) {
+		int ret = pp->init_netns(net, pd);
+		if (ret) {
+			/* unlink an free proto data */
+			ipvs->proto_data_table[hash] = pd->next;
+			kfree(pd);
+			return ret;
+		}
+	}
 
 	return 0;
 }
-#endif
 
 /*
  *	unregister an ipvs protocol
@@ -316,22 +319,35 @@ ip_vs_tcpudp_debug_packet(int af, struct ip_vs_protocol *pp,
  */
 int __net_init ip_vs_protocol_net_init(struct net *net)
 {
+	int i, ret;
+	static struct ip_vs_protocol *protos[] = {
 #ifdef CONFIG_IP_VS_PROTO_TCP
-	register_ip_vs_proto_netns(net, &ip_vs_protocol_tcp);
+        &ip_vs_protocol_tcp,
 #endif
 #ifdef CONFIG_IP_VS_PROTO_UDP
-	register_ip_vs_proto_netns(net, &ip_vs_protocol_udp);
+	&ip_vs_protocol_udp,
 #endif
 #ifdef CONFIG_IP_VS_PROTO_SCTP
-	register_ip_vs_proto_netns(net, &ip_vs_protocol_sctp);
+	&ip_vs_protocol_sctp,
 #endif
 #ifdef CONFIG_IP_VS_PROTO_AH
-	register_ip_vs_proto_netns(net, &ip_vs_protocol_ah);
+	&ip_vs_protocol_ah,
 #endif
 #ifdef CONFIG_IP_VS_PROTO_ESP
-	register_ip_vs_proto_netns(net, &ip_vs_protocol_esp);
+	&ip_vs_protocol_esp,
 #endif
+	};
+
+	for (i = 0; i < ARRAY_SIZE(protos); i++) {
+		ret = register_ip_vs_proto_netns(net, protos[i]);
+		if (ret < 0)
+			goto cleanup;
+	}
 	return 0;
+
+cleanup:
+	ip_vs_protocol_net_cleanup(net);
+	return ret;
 }
 
 void __net_exit ip_vs_protocol_net_cleanup(struct net *net)
diff --git a/net/netfilter/ipvs/ip_vs_proto_sctp.c b/net/netfilter/ipvs/ip_vs_proto_sctp.c
index 1fbf7a2816f5..9f3fb751c491 100644
--- a/net/netfilter/ipvs/ip_vs_proto_sctp.c
+++ b/net/netfilter/ipvs/ip_vs_proto_sctp.c
@@ -1090,7 +1090,7 @@ out:
  *   timeouts is netns related now.
  * ---------------------------------------------
  */
-static void __ip_vs_sctp_init(struct net *net, struct ip_vs_proto_data *pd)
+static int __ip_vs_sctp_init(struct net *net, struct ip_vs_proto_data *pd)
 {
 	struct netns_ipvs *ipvs = net_ipvs(net);
 
@@ -1098,6 +1098,9 @@ static void __ip_vs_sctp_init(struct net *net, struct ip_vs_proto_data *pd)
 	spin_lock_init(&ipvs->sctp_app_lock);
 	pd->timeout_table = ip_vs_create_timeout_table((int *)sctp_timeouts,
 							sizeof(sctp_timeouts));
+	if (!pd->timeout_table)
+		return -ENOMEM;
+	return 0;
 }
 
 static void __ip_vs_sctp_exit(struct net *net, struct ip_vs_proto_data *pd)
diff --git a/net/netfilter/ipvs/ip_vs_proto_tcp.c b/net/netfilter/ipvs/ip_vs_proto_tcp.c
index ef8641f7af83..cd609cc62721 100644
--- a/net/netfilter/ipvs/ip_vs_proto_tcp.c
+++ b/net/netfilter/ipvs/ip_vs_proto_tcp.c
@@ -677,7 +677,7 @@ void ip_vs_tcp_conn_listen(struct net *net, struct ip_vs_conn *cp)
  *   timeouts is netns related now.
  * ---------------------------------------------
  */
-static void __ip_vs_tcp_init(struct net *net, struct ip_vs_proto_data *pd)
+static int __ip_vs_tcp_init(struct net *net, struct ip_vs_proto_data *pd)
 {
 	struct netns_ipvs *ipvs = net_ipvs(net);
 
@@ -685,7 +685,10 @@ static void __ip_vs_tcp_init(struct net *net, struct ip_vs_proto_data *pd)
 	spin_lock_init(&ipvs->tcp_app_lock);
 	pd->timeout_table = ip_vs_create_timeout_table((int *)tcp_timeouts,
 							sizeof(tcp_timeouts));
+	if (!pd->timeout_table)
+		return -ENOMEM;
 	pd->tcp_state_table =  tcp_states;
+	return 0;
 }
 
 static void __ip_vs_tcp_exit(struct net *net, struct ip_vs_proto_data *pd)
diff --git a/net/netfilter/ipvs/ip_vs_proto_udp.c b/net/netfilter/ipvs/ip_vs_proto_udp.c
index f4b7262896bb..2fedb2dcb3d1 100644
--- a/net/netfilter/ipvs/ip_vs_proto_udp.c
+++ b/net/netfilter/ipvs/ip_vs_proto_udp.c
@@ -467,7 +467,7 @@ udp_state_transition(struct ip_vs_conn *cp, int direction,
 	cp->timeout = pd->timeout_table[IP_VS_UDP_S_NORMAL];
 }
 
-static void __udp_init(struct net *net, struct ip_vs_proto_data *pd)
+static int __udp_init(struct net *net, struct ip_vs_proto_data *pd)
 {
 	struct netns_ipvs *ipvs = net_ipvs(net);
 
@@ -475,6 +475,9 @@ static void __udp_init(struct net *net, struct ip_vs_proto_data *pd)
 	spin_lock_init(&ipvs->udp_app_lock);
 	pd->timeout_table = ip_vs_create_timeout_table((int *)udp_timeouts,
 							sizeof(udp_timeouts));
+	if (!pd->timeout_table)
+		return -ENOMEM;
+	return 0;
 }
 
 static void __udp_exit(struct net *net, struct ip_vs_proto_data *pd)
diff --git a/net/netfilter/xt_CT.c b/net/netfilter/xt_CT.c
index 59530e93fa58..3746d8b9a478 100644
--- a/net/netfilter/xt_CT.c
+++ b/net/netfilter/xt_CT.c
@@ -227,7 +227,7 @@ static int xt_ct_tg_check_v1(const struct xt_tgchk_param *par)
 	}
 
 #ifdef CONFIG_NF_CONNTRACK_TIMEOUT
-	if (info->timeout) {
+	if (info->timeout[0]) {
 		typeof(nf_ct_timeout_find_get_hook) timeout_find_get;
 		struct nf_conn_timeout *timeout_ext;