Merge branch 'sctp-rfc7829'

Xin Long says:

====================
sctp: update from rfc7829

SCTP-PF was implemented based on a Internet-Draft in 2012:

https://tools.ietf.org/html/draft-nishida-tsvwg-sctp-failover-05

It's been updated quite a few by rfc7829 in 2016.

This patchset adds the following features:

1. add SCTP_ADDR_POTENTIALLY_FAILED notification
2. add pf_expose per netns/sock/asoc
3. add SCTP_EXPOSE_POTENTIALLY_FAILED_STATE sockopt
4. add ps_retrans per netns/sock/asoc/transport
(Primary Path Switchover)
5. add spt_pathcpthld for SCTP_PEER_ADDR_THLDS sockopt

v1->v2:
- See Patch 2/5 and Patch 5/5.
v2->v3:
- See Patch 1/5, 2/5 and 3/5.
v3->v4:
- See Patch 1/5, 2/5, 3/5 and 4/5.
====================

Signed-off-by: David S. Miller <[e-mail]>

Documentation/networking/ip-sysctl.txt

···
 
 	Default: 1
 
+pf_expose - INTEGER
+	Unset or enable/disable pf (pf is short for potentially failed) state
+	exposure.  Applications can control the exposure of the PF path state
+	in the SCTP_PEER_ADDR_CHANGE event and the SCTP_GET_PEER_ADDR_INFO
+	sockopt.   When it's unset, no SCTP_PEER_ADDR_CHANGE event with
+	SCTP_ADDR_PF state will be sent and a SCTP_PF-state transport info
+	can be got via SCTP_GET_PEER_ADDR_INFO sockopt;  When it's enabled,
+	a SCTP_PEER_ADDR_CHANGE event will be sent for a transport becoming
+	SCTP_PF state and a SCTP_PF-state transport info can be got via
+	SCTP_GET_PEER_ADDR_INFO sockopt;  When it's diabled, no
+	SCTP_PEER_ADDR_CHANGE event will be sent and it returns -EACCES when
+	trying to get a SCTP_PF-state transport info via SCTP_GET_PEER_ADDR_INFO
+	sockopt.
+
+	0: Unset pf state exposure, Compatible with old applications.
+
+	1: Disable pf state exposure.
+
+	2: Enable pf state exposure.
+
+	Default: 0
+
 addip_noauth_enable - BOOLEAN
 	Dynamic Address Reconfiguration (ADD-IP) requires the use of
 	authentication to protect the operations of adding or removing new
···
 	disable pf state.
 
 	Default: 0
+
+ps_retrans - INTEGER
+	Primary.Switchover.Max.Retrans (PSMR), it's a tunable parameter coming
+	from section-5 "Primary Path Switchover" in rfc7829.  The primary path
+	will be changed to another active path when the path error counter on
+	the old primary path exceeds PSMR, so that "the SCTP sender is allowed
+	to continue data transmission on a new working path even when the old
+	primary destination address becomes active again".   Note this feature
+	is disabled by initializing 'ps_retrans' per netns as 0xffff by default,
+	and its value can't be less than 'pf_retrans' when changing by sysctl.
+
+	Default: 0xffff
 
 rto_initial - INTEGER
 	The initial round trip timeout value in milliseconds that will be used

include/net/netns/sctp.h

···
 	 */
 	int pf_retrans;
 
+	/* Primary.Switchover.Max.Retrans sysctl value
+	 * taken from:
+	 * https://tools.ietf.org/html/rfc7829
+	 */
+	int ps_retrans;
+
 	/*
 	 * Disable Potentially-Failed feature, the feature is enabled by default
 	 * pf_enable	-  0  : disable pf
 	 *		- >0  : enable pf
 	 */
 	int pf_enable;
+
+	/*
+	 * Disable Potentially-Failed state exposure, ignored by default
+	 * pf_expose	-  0  : compatible with old applications (by default)
+	 *		-  1  : disable pf state exposure
+	 *		-  2  : enable  pf state exposure
+	 */
+	int pf_expose;
 
 	/*
 	 * Policy for preforming sctp/socket accounting

include/net/sctp/constants.h

···
 				 * functions simpler to write.
 				 */
 
+/* These are the values for pf exposure, UNUSED is to keep compatible with old
+ * applications by default.
+ */
+enum {
+	SCTP_PF_EXPOSE_UNSET,
+	SCTP_PF_EXPOSE_DISABLE,
+	SCTP_PF_EXPOSE_ENABLE,
+};
+#define SCTP_PF_EXPOSE_MAX	SCTP_PF_EXPOSE_ENABLE
+
+#define SCTP_PS_RETRANS_MAX	0xffff
+
 /* These return values describe the success or failure of a number of
  * routines which form the lower interface to SCTP_outqueue.
  */

include/net/sctp/structs.h

···
 	__u32 flowlabel;
 	__u8  dscp;
 
-	int pf_retrans;
+	__u16 pf_retrans;
+	__u16 ps_retrans;
 
 	/* The initial Path MTU to use for new associations. */
 	__u32 pathmtu;
···
 	__u32 adaptation_ind;
 	__u32 pd_point;
 	__u16	nodelay:1,
+		pf_expose:2,
 		reuse:1,
 		disable_fragments:1,
 		v4mapped:1,
···
 	 * and will be initialized from the assocs value.  This can be changed
 	 * using the SCTP_PEER_ADDR_THLDS socket option
 	 */
-	int pf_retrans;
+	__u16 pf_retrans;
+	/* Used for primary path switchover. */
+	__u16 ps_retrans;
 	/* PMTU	      : The current known path MTU.  */
 	__u32 pathmtu;
 
···
 	 * and will be initialized from the assocs value.  This can be
 	 * changed using the SCTP_PEER_ADDR_THLDS socket option
 	 */
-	int pf_retrans;
+	__u16 pf_retrans;
+	/* Used for primary path switchover. */
+	__u16 ps_retrans;
 
 	/* Maximum number of times the endpoint will retransmit INIT  */
 	__u16 max_init_attempts;
···
 
 	__u8 need_ecne:1,	/* Need to send an ECNE Chunk? */
 	     temp:1,		/* Is it a temporary association? */
+	     pf_expose:2,       /* Expose pf state? */
 	     force_delay:1;
 
 	__u8 strreset_enable;

include/uapi/linux/sctp.h

···
 #define SCTP_DEFAULT_SNDINFO	34
 #define SCTP_AUTH_DEACTIVATE_KEY	35
 #define SCTP_REUSE_PORT		36
+#define SCTP_PEER_ADDR_THLDS_V2	37
 
 /* Internal Socket Options. Some of the sctp library functions are
  * implemented using these socket options.
···
 #define SCTP_ASCONF_SUPPORTED	128
 #define SCTP_AUTH_SUPPORTED	129
 #define SCTP_ECN_SUPPORTED	130
+#define SCTP_EXPOSE_POTENTIALLY_FAILED_STATE	131
+#define SCTP_EXPOSE_PF_STATE	SCTP_EXPOSE_POTENTIALLY_FAILED_STATE
 
 /* PR-SCTP policies */
 #define SCTP_PR_SCTP_NONE	0x0000
···
 	SCTP_ADDR_ADDED,
 	SCTP_ADDR_MADE_PRIM,
 	SCTP_ADDR_CONFIRMED,
+	SCTP_ADDR_POTENTIALLY_FAILED,
+#define SCTP_ADDR_PF	SCTP_ADDR_POTENTIALLY_FAILED
 };
 
 
···
 enum sctp_spinfo_state {
 	SCTP_INACTIVE,
 	SCTP_PF,
+#define	SCTP_POTENTIALLY_FAILED		SCTP_PF
 	SCTP_ACTIVE,
 	SCTP_UNCONFIRMED,
 	SCTP_UNKNOWN = 0xffff  /* Value used for transport state unknown */
···
 	struct sockaddr_storage spt_address;
 	__u16 spt_pathmaxrxt;
 	__u16 spt_pathpfthld;
+};
+
+/* Use a new structure with spt_pathcpthld for back compatibility */
+struct sctp_paddrthlds_v2 {
+	sctp_assoc_t spt_assoc_id;
+	struct sockaddr_storage spt_address;
+	__u16 spt_pathmaxrxt;
+	__u16 spt_pathpfthld;
+	__u16 spt_pathcpthld;
 };
 
 /*

net/sctp/associola.c

···
 	 */
 	asoc->max_retrans = sp->assocparams.sasoc_asocmaxrxt;
 	asoc->pf_retrans  = sp->pf_retrans;
+	asoc->ps_retrans  = sp->ps_retrans;
+	asoc->pf_expose   = sp->pf_expose;
 
 	asoc->rto_initial = msecs_to_jiffies(sp->rtoinfo.srto_initial);
 	asoc->rto_max = msecs_to_jiffies(sp->rtoinfo.srto_max);
···
 
 	/* And the partial failure retrans threshold */
 	peer->pf_retrans = asoc->pf_retrans;
+	/* And the primary path switchover retrans threshold */
+	peer->ps_retrans = asoc->ps_retrans;
 
 	/* Initialize the peer's SACK delay timeout based on the
 	 * association configured value.
···
 				  enum sctp_transport_cmd command,
 				  sctp_sn_error_t error)
 {
+	int spc_state = SCTP_ADDR_AVAILABLE;
 	bool ulp_notify = true;
-	int spc_state = 0;
 
 	/* Record the transition on the transport.  */
 	switch (command) {
···
 		 * to heartbeat success, report the SCTP_ADDR_CONFIRMED
 		 * state to the user, otherwise report SCTP_ADDR_AVAILABLE.
 		 */
-		if (SCTP_UNCONFIRMED == transport->state &&
-		    SCTP_HEARTBEAT_SUCCESS == error)
-			spc_state = SCTP_ADDR_CONFIRMED;
-		else
-			spc_state = SCTP_ADDR_AVAILABLE;
-		/* Don't inform ULP about transition from PF to
-		 * active state and set cwnd to 1 MTU, see SCTP
-		 * Quick failover draft section 5.1, point 5
-		 */
-		if (transport->state == SCTP_PF) {
+		if (transport->state == SCTP_PF &&
+		    asoc->pf_expose != SCTP_PF_EXPOSE_ENABLE)
 			ulp_notify = false;
-			transport->cwnd = asoc->pathmtu;
-		}
+		else if (transport->state == SCTP_UNCONFIRMED &&
+			 error == SCTP_HEARTBEAT_SUCCESS)
+			spc_state = SCTP_ADDR_CONFIRMED;
+
 		transport->state = SCTP_ACTIVE;
 		break;
 
···
 		 * to inactive state.  Also, release the cached route since
 		 * there may be a better route next time.
 		 */
-		if (transport->state != SCTP_UNCONFIRMED)
+		if (transport->state != SCTP_UNCONFIRMED) {
 			transport->state = SCTP_INACTIVE;
-		else {
+			spc_state = SCTP_ADDR_UNREACHABLE;
+		} else {
 			sctp_transport_dst_release(transport);
 			ulp_notify = false;
 		}
-
-		spc_state = SCTP_ADDR_UNREACHABLE;
 		break;
 
 	case SCTP_TRANSPORT_PF:
 		transport->state = SCTP_PF;
-		ulp_notify = false;
+		if (asoc->pf_expose != SCTP_PF_EXPOSE_ENABLE)
+			ulp_notify = false;
+		else
+			spc_state = SCTP_ADDR_POTENTIALLY_FAILED;
 		break;
 
 	default:

net/sctp/protocol.c

···
 	/* Max.Burst		    - 4 */
 	net->sctp.max_burst			= SCTP_DEFAULT_MAX_BURST;
 
+	/* Disable of Primary Path Switchover by default */
+	net->sctp.ps_retrans = SCTP_PS_RETRANS_MAX;
+
 	/* Enable pf state by default */
 	net->sctp.pf_enable = 1;
+
+	/* Ignore pf exposure feature by default */
+	net->sctp.pf_expose = SCTP_PF_EXPOSE_UNSET;
 
 	/* Association.Max.Retrans  - 10 attempts
 	 * Path.Max.Retrans         - 5  attempts (per destination address)

net/sctp/sm_sideeffect.c

···
 					     SCTP_FAILED_THRESHOLD);
 	}
 
+	if (transport->error_count > transport->ps_retrans &&
+	    asoc->peer.primary_path == transport &&
+	    asoc->peer.active_path != transport)
+		sctp_assoc_set_primary(asoc, asoc->peer.active_path);
+
 	/* E2) For the destination address for which the timer
 	 * expires, set RTO <- RTO * 2 ("back off the timer").  The
 	 * maximum value discussed in rule C7 above (RTO.max) may be

net/sctp/socket.c

···
  */
 static int sctp_setsockopt_paddr_thresholds(struct sock *sk,
 					    char __user *optval,
-					    unsigned int optlen)
+					    unsigned int optlen, bool v2)
 {
-	struct sctp_paddrthlds val;
+	struct sctp_paddrthlds_v2 val;
 	struct sctp_transport *trans;
 	struct sctp_association *asoc;
+	int len;
 
-	if (optlen < sizeof(struct sctp_paddrthlds))
+	len = v2 ? sizeof(val) : sizeof(struct sctp_paddrthlds);
+	if (optlen < len)
 		return -EINVAL;
-	if (copy_from_user(&val, (struct sctp_paddrthlds __user *)optval,
-			   sizeof(struct sctp_paddrthlds)))
+	if (copy_from_user(&val, optval, len))
 		return -EFAULT;
+
+	if (v2 && val.spt_pathpfthld > val.spt_pathcpthld)
+		return -EINVAL;
 
 	if (!sctp_is_any(sk, (const union sctp_addr *)&val.spt_address)) {
 		trans = sctp_addr_id2transport(sk, &val.spt_address,
···
 
 		if (val.spt_pathmaxrxt)
 			trans->pathmaxrxt = val.spt_pathmaxrxt;
+		if (v2)
+			trans->ps_retrans = val.spt_pathcpthld;
 		trans->pf_retrans = val.spt_pathpfthld;
 
 		return 0;
···
 				    transports) {
 			if (val.spt_pathmaxrxt)
 				trans->pathmaxrxt = val.spt_pathmaxrxt;
+			if (v2)
+				trans->ps_retrans = val.spt_pathcpthld;
 			trans->pf_retrans = val.spt_pathpfthld;
 		}
 
 		if (val.spt_pathmaxrxt)
 			asoc->pathmaxrxt = val.spt_pathmaxrxt;
+		if (v2)
+			asoc->ps_retrans = val.spt_pathcpthld;
 		asoc->pf_retrans = val.spt_pathpfthld;
 	} else {
 		struct sctp_sock *sp = sctp_sk(sk);
 
 		if (val.spt_pathmaxrxt)
 			sp->pathmaxrxt = val.spt_pathmaxrxt;
+		if (v2)
+			sp->ps_retrans = val.spt_pathcpthld;
 		sp->pf_retrans = val.spt_pathpfthld;
 	}
 
···
 	return retval;
 }
 
+static int sctp_setsockopt_pf_expose(struct sock *sk,
+				     char __user *optval,
+				     unsigned int optlen)
+{
+	struct sctp_assoc_value params;
+	struct sctp_association *asoc;
+	int retval = -EINVAL;
+
+	if (optlen != sizeof(params))
+		goto out;
+
+	if (copy_from_user(&params, optval, optlen)) {
+		retval = -EFAULT;
+		goto out;
+	}
+
+	if (params.assoc_value > SCTP_PF_EXPOSE_MAX)
+		goto out;
+
+	asoc = sctp_id2assoc(sk, params.assoc_id);
+	if (!asoc && params.assoc_id != SCTP_FUTURE_ASSOC &&
+	    sctp_style(sk, UDP))
+		goto out;
+
+	if (asoc)
+		asoc->pf_expose = params.assoc_value;
+	else
+		sctp_sk(sk)->pf_expose = params.assoc_value;
+	retval = 0;
+
+out:
+	return retval;
+}
+
 /* API 6.2 setsockopt(), getsockopt()
  *
  * Applications use setsockopt() and getsockopt() to set or retrieve
···
 		retval = sctp_setsockopt_auto_asconf(sk, optval, optlen);
 		break;
 	case SCTP_PEER_ADDR_THLDS:
-		retval = sctp_setsockopt_paddr_thresholds(sk, optval, optlen);
+		retval = sctp_setsockopt_paddr_thresholds(sk, optval, optlen,
+							  false);
+		break;
+	case SCTP_PEER_ADDR_THLDS_V2:
+		retval = sctp_setsockopt_paddr_thresholds(sk, optval, optlen,
+							  true);
 		break;
 	case SCTP_RECVRCVINFO:
 		retval = sctp_setsockopt_recvrcvinfo(sk, optval, optlen);
···
 		break;
 	case SCTP_ECN_SUPPORTED:
 		retval = sctp_setsockopt_ecn_supported(sk, optval, optlen);
+		break;
+	case SCTP_EXPOSE_POTENTIALLY_FAILED_STATE:
+		retval = sctp_setsockopt_pf_expose(sk, optval, optlen);
 		break;
 	default:
 		retval = -ENOPROTOOPT;
···
 	sp->hbinterval  = net->sctp.hb_interval;
 	sp->pathmaxrxt  = net->sctp.max_retrans_path;
 	sp->pf_retrans  = net->sctp.pf_retrans;
+	sp->ps_retrans  = net->sctp.ps_retrans;
+	sp->pf_expose   = net->sctp.pf_expose;
 	sp->pathmtu     = 0; /* allow default discovery */
 	sp->sackdelay   = net->sctp.sack_timeout;
 	sp->sackfreq	= 2;
···
 
 	transport = sctp_addr_id2transport(sk, &pinfo.spinfo_address,
 					   pinfo.spinfo_assoc_id);
-	if (!transport)
-		return -EINVAL;
+	if (!transport) {
+		retval = -EINVAL;
+		goto out;
+	}
+
+	if (transport->state == SCTP_PF &&
+	    transport->asoc->pf_expose == SCTP_PF_EXPOSE_DISABLE) {
+		retval = -EACCES;
+		goto out;
+	}
 
 	pinfo.spinfo_assoc_id = sctp_assoc2id(transport->asoc);
 	pinfo.spinfo_state = transport->state;
···
  * http://www.ietf.org/id/draft-nishida-tsvwg-sctp-failover-05.txt
  */
 static int sctp_getsockopt_paddr_thresholds(struct sock *sk,
-					    char __user *optval,
-					    int len,
-					    int __user *optlen)
+					    char __user *optval, int len,
+					    int __user *optlen, bool v2)
 {
-	struct sctp_paddrthlds val;
+	struct sctp_paddrthlds_v2 val;
 	struct sctp_transport *trans;
 	struct sctp_association *asoc;
+	int min;
 
-	if (len < sizeof(struct sctp_paddrthlds))
+	min = v2 ? sizeof(val) : sizeof(struct sctp_paddrthlds);
+	if (len < min)
 		return -EINVAL;
-	len = sizeof(struct sctp_paddrthlds);
-	if (copy_from_user(&val, (struct sctp_paddrthlds __user *)optval, len))
+	len = min;
+	if (copy_from_user(&val, optval, len))
 		return -EFAULT;
 
 	if (!sctp_is_any(sk, (const union sctp_addr *)&val.spt_address)) {
···
 
 		val.spt_pathmaxrxt = trans->pathmaxrxt;
 		val.spt_pathpfthld = trans->pf_retrans;
+		val.spt_pathcpthld = trans->ps_retrans;
 
 		goto out;
 	}
···
 	if (asoc) {
 		val.spt_pathpfthld = asoc->pf_retrans;
 		val.spt_pathmaxrxt = asoc->pathmaxrxt;
+		val.spt_pathcpthld = asoc->ps_retrans;
 	} else {
 		struct sctp_sock *sp = sctp_sk(sk);
 
 		val.spt_pathpfthld = sp->pf_retrans;
 		val.spt_pathmaxrxt = sp->pathmaxrxt;
+		val.spt_pathcpthld = sp->ps_retrans;
 	}
 
 out:
···
 	return retval;
 }
 
+static int sctp_getsockopt_pf_expose(struct sock *sk, int len,
+				     char __user *optval,
+				     int __user *optlen)
+{
+	struct sctp_assoc_value params;
+	struct sctp_association *asoc;
+	int retval = -EFAULT;
+
+	if (len < sizeof(params)) {
+		retval = -EINVAL;
+		goto out;
+	}
+
+	len = sizeof(params);
+	if (copy_from_user(&params, optval, len))
+		goto out;
+
+	asoc = sctp_id2assoc(sk, params.assoc_id);
+	if (!asoc && params.assoc_id != SCTP_FUTURE_ASSOC &&
+	    sctp_style(sk, UDP)) {
+		retval = -EINVAL;
+		goto out;
+	}
+
+	params.assoc_value = asoc ? asoc->pf_expose
+				  : sctp_sk(sk)->pf_expose;
+
+	if (put_user(len, optlen))
+		goto out;
+
+	if (copy_to_user(optval, &params, len))
+		goto out;
+
+	retval = 0;
+
+out:
+	return retval;
+}
+
 static int sctp_getsockopt(struct sock *sk, int level, int optname,
 			   char __user *optval, int __user *optlen)
 {
···
 		retval = sctp_getsockopt_auto_asconf(sk, len, optval, optlen);
 		break;
 	case SCTP_PEER_ADDR_THLDS:
-		retval = sctp_getsockopt_paddr_thresholds(sk, optval, len, optlen);
+		retval = sctp_getsockopt_paddr_thresholds(sk, optval, len,
+							  optlen, false);
+		break;
+	case SCTP_PEER_ADDR_THLDS_V2:
+		retval = sctp_getsockopt_paddr_thresholds(sk, optval, len,
+							  optlen, true);
 		break;
 	case SCTP_GET_ASSOC_STATS:
 		retval = sctp_getsockopt_assoc_stats(sk, len, optval, optlen);
···
 		break;
 	case SCTP_ECN_SUPPORTED:
 		retval = sctp_getsockopt_ecn_supported(sk, len, optval, optlen);
+		break;
+	case SCTP_EXPOSE_POTENTIALLY_FAILED_STATE:
+		retval = sctp_getsockopt_pf_expose(sk, len, optval, optlen);
 		break;
 	default:
 		retval = -ENOPROTOOPT;

net/sctp/sysctl.c

···
 static int rto_beta_min = 0;
 static int rto_alpha_max = 1000;
 static int rto_beta_max = 1000;
+static int pf_expose_max = SCTP_PF_EXPOSE_MAX;
+static int ps_retrans_max = SCTP_PS_RETRANS_MAX;
 
 static unsigned long max_autoclose_min = 0;
 static unsigned long max_autoclose_max =
···
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec_minmax,
 		.extra1		= SYSCTL_ZERO,
-		.extra2		= SYSCTL_INT_MAX,
+		.extra2		= &init_net.sctp.ps_retrans,
+	},
+	{
+		.procname	= "ps_retrans",
+		.data		= &init_net.sctp.ps_retrans,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec_minmax,
+		.extra1		= &init_net.sctp.pf_retrans,
+		.extra2		= &ps_retrans_max,
 	},
 	{
 		.procname	= "sndbuf_policy",
···
 		.maxlen		= sizeof(int),
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec,
+	},
+	{
+		.procname	= "pf_expose",
+		.data		= &init_net.sctp.pf_expose,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec_minmax,
+		.extra1		= SYSCTL_ZERO,
+		.extra2		= &pf_expose_max,
 	},
 
 	{ /* sentinel */ }