Merge ../linux-2.6

7 files changed, 239 insertions, 128 deletions

diff --git a/net/sctp/input.c b/net/sctp/input.c
index d117ebc75cf8..1662f9cc869e 100644
--- a/net/sctp/input.c
+++ b/net/sctp/input.c
@@ -73,6 +73,8 @@ static struct sctp_association *__sctp_lookup_association(
 					const union sctp_addr *peer,
 					struct sctp_transport **pt);
 
+static void sctp_add_backlog(struct sock *sk, struct sk_buff *skb);
+
 
 /* Calculate the SCTP checksum of an SCTP packet.  */
 static inline int sctp_rcv_checksum(struct sk_buff *skb)
@@ -186,7 +188,6 @@ int sctp_rcv(struct sk_buff *skb)
 	 */
 	if (sk->sk_bound_dev_if && (sk->sk_bound_dev_if != af->skb_iif(skb)))
 	{
-		sock_put(sk);
 		if (asoc) {
 			sctp_association_put(asoc);
 			asoc = NULL;
@@ -197,7 +198,6 @@ int sctp_rcv(struct sk_buff *skb)
 		sk = sctp_get_ctl_sock();
 		ep = sctp_sk(sk)->ep;
 		sctp_endpoint_hold(ep);
-		sock_hold(sk);
 		rcvr = &ep->base;
 	}
 
@@ -253,25 +253,18 @@ int sctp_rcv(struct sk_buff *skb)
 	 */
 	sctp_bh_lock_sock(sk);
 
-	/* It is possible that the association could have moved to a different
-	 * socket if it is peeled off. If so, update the sk.
-	 */ 
-	if (sk != rcvr->sk) {
-		sctp_bh_lock_sock(rcvr->sk);
-		sctp_bh_unlock_sock(sk);
-		sk = rcvr->sk;
-	}
-
 	if (sock_owned_by_user(sk))
-		sk_add_backlog(sk, skb);
+		sctp_add_backlog(sk, skb);
 	else
-		sctp_backlog_rcv(sk, skb);
+		sctp_inq_push(&chunk->rcvr->inqueue, chunk);
 
-	/* Release the sock and the sock ref we took in the lookup calls.
-	 * The asoc/ep ref will be released in sctp_backlog_rcv.
-	 */
 	sctp_bh_unlock_sock(sk);
-	sock_put(sk);
+
+	/* Release the asoc/ep ref we took in the lookup calls. */
+	if (asoc)
+		sctp_association_put(asoc);
+	else
+		sctp_endpoint_put(ep);
 
 	return 0;
 
@@ -280,8 +273,7 @@ discard_it:
 	return 0;
 
 discard_release:
-	/* Release any structures we may be holding. */
-	sock_put(sk);
+	/* Release the asoc/ep ref we took in the lookup calls. */
 	if (asoc)
 		sctp_association_put(asoc);
 	else
@@ -290,56 +282,87 @@ discard_release:
 	goto discard_it;
 }
 
-/* Handle second half of inbound skb processing.  If the sock was busy,
- * we may have need to delay processing until later when the sock is
- * released (on the backlog).   If not busy, we call this routine
- * directly from the bottom half.
+/* Process the backlog queue of the socket.  Every skb on
+ * the backlog holds a ref on an association or endpoint.
+ * We hold this ref throughout the state machine to make
+ * sure that the structure we need is still around.
  */
 int sctp_backlog_rcv(struct sock *sk, struct sk_buff *skb)
 {
 	struct sctp_chunk *chunk = SCTP_INPUT_CB(skb)->chunk;
- 	struct sctp_inq *inqueue = NULL;
+ 	struct sctp_inq *inqueue = &chunk->rcvr->inqueue;
  	struct sctp_ep_common *rcvr = NULL;
+	int backloged = 0;
 
  	rcvr = chunk->rcvr;
 
-	BUG_TRAP(rcvr->sk == sk);
-
- 	if (rcvr->dead) {
- 		sctp_chunk_free(chunk);
- 	} else {
- 		inqueue = &chunk->rcvr->inqueue;
- 		sctp_inq_push(inqueue, chunk);
- 	}
-
-	/* Release the asoc/ep ref we took in the lookup calls in sctp_rcv. */ 
- 	if (SCTP_EP_TYPE_ASSOCIATION == rcvr->type)
- 		sctp_association_put(sctp_assoc(rcvr));
- 	else
- 		sctp_endpoint_put(sctp_ep(rcvr));
-  
+	/* If the rcvr is dead then the association or endpoint
+	 * has been deleted and we can safely drop the chunk
+	 * and refs that we are holding.
+	 */
+	if (rcvr->dead) {
+		sctp_chunk_free(chunk);
+		goto done;
+	}
+
+	if (unlikely(rcvr->sk != sk)) {
+		/* In this case, the association moved from one socket to
+		 * another.  We are currently sitting on the backlog of the
+		 * old socket, so we need to move.
+		 * However, since we are here in the process context we
+		 * need to take make sure that the user doesn't own
+		 * the new socket when we process the packet.
+		 * If the new socket is user-owned, queue the chunk to the
+		 * backlog of the new socket without dropping any refs.
+		 * Otherwise, we can safely push the chunk on the inqueue.
+		 */
+
+		sk = rcvr->sk;
+		sctp_bh_lock_sock(sk);
+
+		if (sock_owned_by_user(sk)) {
+			sk_add_backlog(sk, skb);
+			backloged = 1;
+		} else
+			sctp_inq_push(inqueue, chunk);
+
+		sctp_bh_unlock_sock(sk);
+
+		/* If the chunk was backloged again, don't drop refs */
+		if (backloged)
+			return 0;
+	} else {
+		sctp_inq_push(inqueue, chunk);
+	}
+
+done:
+	/* Release the refs we took in sctp_add_backlog */
+	if (SCTP_EP_TYPE_ASSOCIATION == rcvr->type)
+		sctp_association_put(sctp_assoc(rcvr));
+	else if (SCTP_EP_TYPE_SOCKET == rcvr->type)
+		sctp_endpoint_put(sctp_ep(rcvr));
+	else
+		BUG();
+
         return 0;
 }
 
-void sctp_backlog_migrate(struct sctp_association *assoc, 
-			  struct sock *oldsk, struct sock *newsk)
+static void sctp_add_backlog(struct sock *sk, struct sk_buff *skb)
 {
-	struct sk_buff *skb;
-	struct sctp_chunk *chunk;
+	struct sctp_chunk *chunk = SCTP_INPUT_CB(skb)->chunk;
+	struct sctp_ep_common *rcvr = chunk->rcvr;
 
-	skb = oldsk->sk_backlog.head;
-	oldsk->sk_backlog.head = oldsk->sk_backlog.tail = NULL;
-	while (skb != NULL) {
-		struct sk_buff *next = skb->next;
-
-		chunk = SCTP_INPUT_CB(skb)->chunk;
-		skb->next = NULL;
-		if (&assoc->base == chunk->rcvr)
-			sk_add_backlog(newsk, skb);
-		else
-			sk_add_backlog(oldsk, skb);
-		skb = next;
-	}
+	/* Hold the assoc/ep while hanging on the backlog queue.
+	 * This way, we know structures we need will not disappear from us
+	 */
+	if (SCTP_EP_TYPE_ASSOCIATION == rcvr->type)
+		sctp_association_hold(sctp_assoc(rcvr));
+	else if (SCTP_EP_TYPE_SOCKET == rcvr->type)
+		sctp_endpoint_hold(sctp_ep(rcvr));
+	else
+		BUG();
+
+	sk_add_backlog(sk, skb);
 }
 
 /* Handle icmp frag needed error. */
@@ -412,7 +435,7 @@ struct sock *sctp_err_lookup(int family, struct sk_buff *skb,
 	union sctp_addr daddr;
 	struct sctp_af *af;
 	struct sock *sk = NULL;
-	struct sctp_association *asoc = NULL;
+	struct sctp_association *asoc;
 	struct sctp_transport *transport = NULL;
 
 	*app = NULL; *tpp = NULL;
@@ -453,7 +476,6 @@ struct sock *sctp_err_lookup(int family, struct sk_buff *skb,
 	return sk;
 
 out:
-	sock_put(sk);
 	if (asoc)
 		sctp_association_put(asoc);
 	return NULL;
@@ -463,7 +485,6 @@ out:
 void sctp_err_finish(struct sock *sk, struct sctp_association *asoc)
 {
 	sctp_bh_unlock_sock(sk);
-	sock_put(sk);
 	if (asoc)
 		sctp_association_put(asoc);
 }
@@ -490,7 +511,7 @@ void sctp_v4_err(struct sk_buff *skb, __u32 info)
 	int type = skb->h.icmph->type;
 	int code = skb->h.icmph->code;
 	struct sock *sk;
-	struct sctp_association *asoc;
+	struct sctp_association *asoc = NULL;
 	struct sctp_transport *transport;
 	struct inet_sock *inet;
 	char *saveip, *savesctp;
@@ -716,7 +737,6 @@ static struct sctp_endpoint *__sctp_rcv_lookup_endpoint(const union sctp_addr *l
 
 hit:
 	sctp_endpoint_hold(ep);
-	sock_hold(epb->sk);
 	read_unlock(&head->lock);
 	return ep;
 }
@@ -818,7 +838,6 @@ static struct sctp_association *__sctp_lookup_association(
 hit:
 	*pt = transport;
 	sctp_association_hold(asoc);
-	sock_hold(epb->sk);
 	read_unlock(&head->lock);
 	return asoc;
 }
@@ -846,7 +865,6 @@ int sctp_has_association(const union sctp_addr *laddr,
 	struct sctp_transport *transport;
 
 	if ((asoc = sctp_lookup_association(laddr, paddr, &transport))) {
-		sock_put(asoc->base.sk);
 		sctp_association_put(asoc);
 		return 1;
 	}
diff --git a/net/sctp/inqueue.c b/net/sctp/inqueue.c
index 297b8951463e..cf0c767d43ae 100644
--- a/net/sctp/inqueue.c
+++ b/net/sctp/inqueue.c
@@ -149,6 +149,7 @@ struct sctp_chunk *sctp_inq_pop(struct sctp_inq *queue)
 		/* This is the first chunk in the packet.  */
 		chunk->singleton = 1;
 		ch = (sctp_chunkhdr_t *) chunk->skb->data;
+		chunk->data_accepted = 0;
 	}
 
         chunk->chunk_hdr = ch;
diff --git a/net/sctp/sm_sideeffect.c b/net/sctp/sm_sideeffect.c
index 8d1dc24bab4c..c5beb2ad7ef7 100644
--- a/net/sctp/sm_sideeffect.c
+++ b/net/sctp/sm_sideeffect.c
@@ -498,10 +498,6 @@ static void sctp_cmd_assoc_failed(sctp_cmd_seq_t *commands,
 	sctp_add_cmd_sf(commands, SCTP_CMD_NEW_STATE,
 			SCTP_STATE(SCTP_STATE_CLOSED));
 
-	/* Set sk_err to ECONNRESET on a 1-1 style socket. */
-	if (!sctp_style(asoc->base.sk, UDP))
-		asoc->base.sk->sk_err = ECONNRESET; 
-
 	/* SEND_FAILED sent later when cleaning up the association. */
 	asoc->outqueue.error = error;
 	sctp_add_cmd_sf(commands, SCTP_CMD_DELETE_TCB, SCTP_NULL());
@@ -838,6 +834,15 @@ static void sctp_cmd_del_non_primary(struct sctp_association *asoc)
 	return;
 }
 
+/* Helper function to set sk_err on a 1-1 style socket. */
+static void sctp_cmd_set_sk_err(struct sctp_association *asoc, int error)
+{
+	struct sock *sk = asoc->base.sk;
+
+	if (!sctp_style(sk, UDP))
+		sk->sk_err = error;
+}
+
 /* These three macros allow us to pull the debugging code out of the
  * main flow of sctp_do_sm() to keep attention focused on the real
  * functionality there.
@@ -1458,6 +1463,9 @@ static int sctp_cmd_interpreter(sctp_event_t event_type,
 			local_cork = 0;
 			asoc->peer.retran_path = t;
 			break;
+		case SCTP_CMD_SET_SK_ERR:
+			sctp_cmd_set_sk_err(asoc, cmd->obj.error);
+			break;
 		default:
 			printk(KERN_WARNING "Impossible command: %u, %p\n",
 			       cmd->verb, cmd->obj.ptr);
diff --git a/net/sctp/sm_statefuns.c b/net/sctp/sm_statefuns.c
index 2b9a832b29a7..8bc279219a72 100644
--- a/net/sctp/sm_statefuns.c
+++ b/net/sctp/sm_statefuns.c
@@ -93,7 +93,7 @@ static sctp_disposition_t sctp_sf_shut_8_4_5(const struct sctp_endpoint *ep,
 static struct sctp_sackhdr *sctp_sm_pull_sack(struct sctp_chunk *chunk);
 
 static sctp_disposition_t sctp_stop_t1_and_abort(sctp_cmd_seq_t *commands,
-					   __u16 error,
+					   __u16 error, int sk_err,
 					   const struct sctp_association *asoc,
 					   struct sctp_transport *transport);
 
@@ -448,7 +448,7 @@ sctp_disposition_t sctp_sf_do_5_1C_ack(const struct sctp_endpoint *ep,
 	__u32 init_tag;
 	struct sctp_chunk *err_chunk;
 	struct sctp_packet *packet;
-	sctp_disposition_t ret;
+	__u16 error;
 
 	if (!sctp_vtag_verify(chunk, asoc))
 		return sctp_sf_pdiscard(ep, asoc, type, arg, commands);
@@ -480,11 +480,9 @@ sctp_disposition_t sctp_sf_do_5_1C_ack(const struct sctp_endpoint *ep,
 			goto nomem;
 
 		sctp_add_cmd_sf(commands, SCTP_CMD_REPLY, SCTP_CHUNK(reply));
-		sctp_add_cmd_sf(commands, SCTP_CMD_NEW_STATE,
-				SCTP_STATE(SCTP_STATE_CLOSED));
-		SCTP_INC_STATS(SCTP_MIB_ABORTEDS);
-		sctp_add_cmd_sf(commands, SCTP_CMD_DELETE_TCB, SCTP_NULL());
-		return SCTP_DISPOSITION_DELETE_TCB;
+		return sctp_stop_t1_and_abort(commands, SCTP_ERROR_INV_PARAM,
+					      ECONNREFUSED, asoc,
+					      chunk->transport);
 	}
 
 	/* Verify the INIT chunk before processing it. */
@@ -511,27 +509,16 @@ sctp_disposition_t sctp_sf_do_5_1C_ack(const struct sctp_endpoint *ep,
 				sctp_add_cmd_sf(commands, SCTP_CMD_SEND_PKT,
 						SCTP_PACKET(packet));
 				SCTP_INC_STATS(SCTP_MIB_OUTCTRLCHUNKS);
-				sctp_add_cmd_sf(commands, SCTP_CMD_NEW_STATE,
-						SCTP_STATE(SCTP_STATE_CLOSED));
-				sctp_add_cmd_sf(commands, SCTP_CMD_DELETE_TCB,
-						SCTP_NULL());
-				return SCTP_DISPOSITION_CONSUME;
+				error = SCTP_ERROR_INV_PARAM;
 			} else {
-				sctp_add_cmd_sf(commands, SCTP_CMD_NEW_STATE,
-						SCTP_STATE(SCTP_STATE_CLOSED));
-				sctp_add_cmd_sf(commands, SCTP_CMD_DELETE_TCB,
-						SCTP_NULL());
-				return SCTP_DISPOSITION_NOMEM;
+				error = SCTP_ERROR_NO_RESOURCE;
 			}
 		} else {
-			ret = sctp_sf_tabort_8_4_8(ep, asoc, type, arg,
-						   commands);
-			sctp_add_cmd_sf(commands, SCTP_CMD_NEW_STATE,
-					SCTP_STATE(SCTP_STATE_CLOSED));
-			sctp_add_cmd_sf(commands, SCTP_CMD_DELETE_TCB,
-					SCTP_NULL());
-			return ret;
+			sctp_sf_tabort_8_4_8(ep, asoc, type, arg, commands);
+			error = SCTP_ERROR_INV_PARAM;
 		}
+		return sctp_stop_t1_and_abort(commands, error, ECONNREFUSED,
+						asoc, chunk->transport);
 	}
 
 	/* Tag the variable length parameters.  Note that we never
@@ -636,8 +623,9 @@ sctp_disposition_t sctp_sf_do_5_1D_ce(const struct sctp_endpoint *ep,
 	 */
         chunk->subh.cookie_hdr =
 		(struct sctp_signed_cookie *)chunk->skb->data;
-	skb_pull(chunk->skb,
-		 ntohs(chunk->chunk_hdr->length) - sizeof(sctp_chunkhdr_t));
+	if (!pskb_pull(chunk->skb, ntohs(chunk->chunk_hdr->length) -
+					 sizeof(sctp_chunkhdr_t)))
+		goto nomem;
 
 	/* 5.1 D) Upon reception of the COOKIE ECHO chunk, Endpoint
 	 * "Z" will reply with a COOKIE ACK chunk after building a TCB
@@ -885,6 +873,8 @@ sctp_disposition_t sctp_sf_sendbeat_8_3(const struct sctp_endpoint *ep,
 	struct sctp_transport *transport = (struct sctp_transport *) arg;
 
 	if (asoc->overall_error_count >= asoc->max_retrans) {
+		sctp_add_cmd_sf(commands, SCTP_CMD_SET_SK_ERR,
+				SCTP_ERROR(ETIMEDOUT));
 		/* CMD_ASSOC_FAILED calls CMD_DELETE_TCB. */
 		sctp_add_cmd_sf(commands, SCTP_CMD_ASSOC_FAILED,
 				SCTP_U32(SCTP_ERROR_NO_ERROR));
@@ -965,7 +955,8 @@ sctp_disposition_t sctp_sf_beat_8_3(const struct sctp_endpoint *ep,
 	 */
 	chunk->subh.hb_hdr = (sctp_heartbeathdr_t *) chunk->skb->data;
 	paylen = ntohs(chunk->chunk_hdr->length) - sizeof(sctp_chunkhdr_t);
-	skb_pull(chunk->skb, paylen);
+	if (!pskb_pull(chunk->skb, paylen))
+		goto nomem;
 
 	reply = sctp_make_heartbeat_ack(asoc, chunk,
 					chunk->subh.hb_hdr, paylen);
@@ -1028,6 +1019,12 @@ sctp_disposition_t sctp_sf_backbeat_8_3(const struct sctp_endpoint *ep,
 						  commands);
 
 	hbinfo = (sctp_sender_hb_info_t *) chunk->skb->data;
+	/* Make sure that the length of the parameter is what we expect */
+	if (ntohs(hbinfo->param_hdr.length) !=
+				    sizeof(sctp_sender_hb_info_t)) {
+		return SCTP_DISPOSITION_DISCARD;
+	}
+
 	from_addr = hbinfo->daddr;
 	link = sctp_assoc_lookup_paddr(asoc, &from_addr);
 
@@ -1860,8 +1857,9 @@ sctp_disposition_t sctp_sf_do_5_2_4_dupcook(const struct sctp_endpoint *ep,
 	 * are in good shape.
 	 */
         chunk->subh.cookie_hdr = (struct sctp_signed_cookie *)chunk->skb->data;
-	skb_pull(chunk->skb, ntohs(chunk->chunk_hdr->length) -
-		 sizeof(sctp_chunkhdr_t));
+	if (!pskb_pull(chunk->skb, ntohs(chunk->chunk_hdr->length) -
+					sizeof(sctp_chunkhdr_t)))
+		goto nomem;
 
 	/* In RFC 2960 5.2.4 3, if both Verification Tags in the State Cookie
 	 * of a duplicate COOKIE ECHO match the Verification Tags of the
@@ -2123,6 +2121,8 @@ static sctp_disposition_t sctp_sf_do_5_2_6_stale(const struct sctp_endpoint *ep,
 	int attempts = asoc->init_err_counter + 1;
 
 	if (attempts > asoc->max_init_attempts) {
+		sctp_add_cmd_sf(commands, SCTP_CMD_SET_SK_ERR,
+				SCTP_ERROR(ETIMEDOUT));
 		sctp_add_cmd_sf(commands, SCTP_CMD_INIT_FAILED,
 				SCTP_U32(SCTP_ERROR_STALE_COOKIE));
 		return SCTP_DISPOSITION_DELETE_TCB;
@@ -2259,6 +2259,7 @@ sctp_disposition_t sctp_sf_do_9_1_abort(const struct sctp_endpoint *ep,
 	if (len >= sizeof(struct sctp_chunkhdr) + sizeof(struct sctp_errhdr))
 		error = ((sctp_errhdr_t *)chunk->skb->data)->cause;
 
+	sctp_add_cmd_sf(commands, SCTP_CMD_SET_SK_ERR, SCTP_ERROR(ECONNRESET));
  	/* ASSOC_FAILED will DELETE_TCB. */
 	sctp_add_cmd_sf(commands, SCTP_CMD_ASSOC_FAILED, SCTP_U32(error));
 	SCTP_INC_STATS(SCTP_MIB_ABORTEDS);
@@ -2303,7 +2304,8 @@ sctp_disposition_t sctp_sf_cookie_wait_abort(const struct sctp_endpoint *ep,
 	if (len >= sizeof(struct sctp_chunkhdr) + sizeof(struct sctp_errhdr))
 		error = ((sctp_errhdr_t *)chunk->skb->data)->cause;
 
-	return sctp_stop_t1_and_abort(commands, error, asoc, chunk->transport);
+	return sctp_stop_t1_and_abort(commands, error, ECONNREFUSED, asoc,
+				      chunk->transport);
 }
 
 /*
@@ -2315,7 +2317,8 @@ sctp_disposition_t sctp_sf_cookie_wait_icmp_abort(const struct sctp_endpoint *ep
 					void *arg,
 					sctp_cmd_seq_t *commands)
 {
-	return sctp_stop_t1_and_abort(commands, SCTP_ERROR_NO_ERROR, asoc,
+	return sctp_stop_t1_and_abort(commands, SCTP_ERROR_NO_ERROR,
+				      ENOPROTOOPT, asoc,
 				      (struct sctp_transport *)arg);
 }
 
@@ -2340,7 +2343,7 @@ sctp_disposition_t sctp_sf_cookie_echoed_abort(const struct sctp_endpoint *ep,
  * This is common code called by several sctp_sf_*_abort() functions above.
  */
 static sctp_disposition_t sctp_stop_t1_and_abort(sctp_cmd_seq_t *commands,
-					   __u16 error,
+					   __u16 error, int sk_err,
 					   const struct sctp_association *asoc,
 					   struct sctp_transport *transport)
 {
@@ -2350,6 +2353,7 @@ static sctp_disposition_t sctp_stop_t1_and_abort(sctp_cmd_seq_t *commands,
 	SCTP_INC_STATS(SCTP_MIB_ABORTEDS);
 	sctp_add_cmd_sf(commands, SCTP_CMD_TIMER_STOP,
 			SCTP_TO(SCTP_EVENT_TIMEOUT_T1_INIT));
+	sctp_add_cmd_sf(commands, SCTP_CMD_SET_SK_ERR, SCTP_ERROR(sk_err));
 	/* CMD_INIT_FAILED will DELETE_TCB. */
 	sctp_add_cmd_sf(commands, SCTP_CMD_INIT_FAILED,
 			SCTP_U32(error));
@@ -3333,6 +3337,8 @@ sctp_disposition_t sctp_sf_do_asconf_ack(const struct sctp_endpoint *ep,
 		sctp_add_cmd_sf(commands, SCTP_CMD_TIMER_STOP,
 				SCTP_TO(SCTP_EVENT_TIMEOUT_T4_RTO));
 		sctp_add_cmd_sf(commands, SCTP_CMD_DISCARD_PACKET,SCTP_NULL());
+		sctp_add_cmd_sf(commands, SCTP_CMD_SET_SK_ERR,
+			        SCTP_ERROR(ECONNABORTED));
 		sctp_add_cmd_sf(commands, SCTP_CMD_ASSOC_FAILED,
 				SCTP_U32(SCTP_ERROR_ASCONF_ACK));
 		SCTP_INC_STATS(SCTP_MIB_ABORTEDS);
@@ -3359,6 +3365,8 @@ sctp_disposition_t sctp_sf_do_asconf_ack(const struct sctp_endpoint *ep,
 		 * processing the rest of the chunks in the packet.
 		 */
 		sctp_add_cmd_sf(commands, SCTP_CMD_DISCARD_PACKET,SCTP_NULL());
+		sctp_add_cmd_sf(commands, SCTP_CMD_SET_SK_ERR,
+			        SCTP_ERROR(ECONNABORTED));
 		sctp_add_cmd_sf(commands, SCTP_CMD_ASSOC_FAILED,
 				SCTP_U32(SCTP_ERROR_ASCONF_ACK));
 		SCTP_INC_STATS(SCTP_MIB_ABORTEDS);
@@ -3711,9 +3719,13 @@ static sctp_disposition_t sctp_sf_violation_chunklen(
 	if (asoc->state <= SCTP_STATE_COOKIE_ECHOED) {
 		sctp_add_cmd_sf(commands, SCTP_CMD_TIMER_STOP,
 				SCTP_TO(SCTP_EVENT_TIMEOUT_T1_INIT));
+		sctp_add_cmd_sf(commands, SCTP_CMD_SET_SK_ERR,
+				SCTP_ERROR(ECONNREFUSED));
 		sctp_add_cmd_sf(commands, SCTP_CMD_INIT_FAILED,
 				SCTP_U32(SCTP_ERROR_PROTO_VIOLATION));
 	} else {
+		sctp_add_cmd_sf(commands, SCTP_CMD_SET_SK_ERR,
+			        SCTP_ERROR(ECONNABORTED));
 		sctp_add_cmd_sf(commands, SCTP_CMD_ASSOC_FAILED,
 				SCTP_U32(SCTP_ERROR_PROTO_VIOLATION));
 		SCTP_DEC_STATS(SCTP_MIB_CURRESTAB);
@@ -4031,6 +4043,8 @@ sctp_disposition_t sctp_sf_do_9_1_prm_abort(
 	 * TCB.  This is a departure from our typical NOMEM handling.
 	 */
 
+	sctp_add_cmd_sf(commands, SCTP_CMD_SET_SK_ERR,
+			SCTP_ERROR(ECONNABORTED));
 	/* Delete the established association. */
 	sctp_add_cmd_sf(commands, SCTP_CMD_ASSOC_FAILED,
 			SCTP_U32(SCTP_ERROR_USER_ABORT));
@@ -4172,6 +4186,8 @@ sctp_disposition_t sctp_sf_cookie_wait_prm_abort(
 	 * TCB.  This is a departure from our typical NOMEM handling.
 	 */
 
+	sctp_add_cmd_sf(commands, SCTP_CMD_SET_SK_ERR,
+			SCTP_ERROR(ECONNREFUSED));
 	/* Delete the established association. */
 	sctp_add_cmd_sf(commands, SCTP_CMD_INIT_FAILED,
 			SCTP_U32(SCTP_ERROR_USER_ABORT));
@@ -4540,6 +4556,8 @@ sctp_disposition_t sctp_sf_do_6_3_3_rtx(const struct sctp_endpoint *ep,
 	struct sctp_transport *transport = arg;
 
 	if (asoc->overall_error_count >= asoc->max_retrans) {
+		sctp_add_cmd_sf(commands, SCTP_CMD_SET_SK_ERR,
+				SCTP_ERROR(ETIMEDOUT));
 		/* CMD_ASSOC_FAILED calls CMD_DELETE_TCB. */
 		sctp_add_cmd_sf(commands, SCTP_CMD_ASSOC_FAILED,
 				SCTP_U32(SCTP_ERROR_NO_ERROR));
@@ -4659,6 +4677,8 @@ sctp_disposition_t sctp_sf_t1_init_timer_expire(const struct sctp_endpoint *ep,
 		SCTP_DEBUG_PRINTK("Giving up on INIT, attempts: %d"
 				  " max_init_attempts: %d\n",
 				  attempts, asoc->max_init_attempts);
+		sctp_add_cmd_sf(commands, SCTP_CMD_SET_SK_ERR,
+				SCTP_ERROR(ETIMEDOUT));
 		sctp_add_cmd_sf(commands, SCTP_CMD_INIT_FAILED,
 				SCTP_U32(SCTP_ERROR_NO_ERROR));
 		return SCTP_DISPOSITION_DELETE_TCB;
@@ -4708,6 +4728,8 @@ sctp_disposition_t sctp_sf_t1_cookie_timer_expire(const struct sctp_endpoint *ep
 
 		sctp_add_cmd_sf(commands, SCTP_CMD_REPLY, SCTP_CHUNK(repl));
 	} else {
+		sctp_add_cmd_sf(commands, SCTP_CMD_SET_SK_ERR,
+				SCTP_ERROR(ETIMEDOUT));
 		sctp_add_cmd_sf(commands, SCTP_CMD_INIT_FAILED,
 				SCTP_U32(SCTP_ERROR_NO_ERROR));
 		return SCTP_DISPOSITION_DELETE_TCB;
@@ -4739,6 +4761,8 @@ sctp_disposition_t sctp_sf_t2_timer_expire(const struct sctp_endpoint *ep,
 
 	SCTP_DEBUG_PRINTK("Timer T2 expired.\n");
 	if (asoc->overall_error_count >= asoc->max_retrans) {
+		sctp_add_cmd_sf(commands, SCTP_CMD_SET_SK_ERR,
+				SCTP_ERROR(ETIMEDOUT));
 		/* Note:  CMD_ASSOC_FAILED calls CMD_DELETE_TCB. */
 		sctp_add_cmd_sf(commands, SCTP_CMD_ASSOC_FAILED,
 				SCTP_U32(SCTP_ERROR_NO_ERROR));
@@ -4814,6 +4838,8 @@ sctp_disposition_t sctp_sf_t4_timer_expire(
 	if (asoc->overall_error_count >= asoc->max_retrans) {
 		sctp_add_cmd_sf(commands, SCTP_CMD_TIMER_STOP,
 				SCTP_TO(SCTP_EVENT_TIMEOUT_T4_RTO));
+		sctp_add_cmd_sf(commands, SCTP_CMD_SET_SK_ERR,
+				SCTP_ERROR(ETIMEDOUT));
 		sctp_add_cmd_sf(commands, SCTP_CMD_ASSOC_FAILED,
 				SCTP_U32(SCTP_ERROR_NO_ERROR));
 		SCTP_INC_STATS(SCTP_MIB_ABORTEDS);
@@ -4867,6 +4893,8 @@ sctp_disposition_t sctp_sf_t5_timer_expire(const struct sctp_endpoint *ep,
 		goto nomem;
 
 	sctp_add_cmd_sf(commands, SCTP_CMD_REPLY, SCTP_CHUNK(reply));
+	sctp_add_cmd_sf(commands, SCTP_CMD_SET_SK_ERR,
+			SCTP_ERROR(ETIMEDOUT));
 	sctp_add_cmd_sf(commands, SCTP_CMD_ASSOC_FAILED,
 			SCTP_U32(SCTP_ERROR_NO_ERROR));
 
@@ -5151,7 +5179,9 @@ static int sctp_eat_data(const struct sctp_association *asoc,
 	int tmp;
 	__u32 tsn;
 	int account_value;
+	struct sctp_tsnmap *map = (struct sctp_tsnmap *)&asoc->peer.tsn_map;
 	struct sock *sk = asoc->base.sk;
+	int rcvbuf_over = 0;
 
 	data_hdr = chunk->subh.data_hdr = (sctp_datahdr_t *)chunk->skb->data;
 	skb_pull(chunk->skb, sizeof(sctp_datahdr_t));
@@ -5162,10 +5192,16 @@ static int sctp_eat_data(const struct sctp_association *asoc,
 	/* ASSERT:  Now skb->data is really the user data.  */
 
 	/*
-	 * if we are established, and we have used up our receive
-	 * buffer memory, drop the frame
-	 */
-	if (asoc->state == SCTP_STATE_ESTABLISHED) {
+	 * If we are established, and we have used up our receive buffer
+	 * memory, think about droping the frame.
+	 * Note that we have an opportunity to improve performance here.
+	 * If we accept one chunk from an skbuff, we have to keep all the
+	 * memory of that skbuff around until the chunk is read into user
+	 * space. Therefore, once we accept 1 chunk we may as well accept all
+	 * remaining chunks in the skbuff. The data_accepted flag helps us do
+	 * that.
+	 */
+	if ((asoc->state == SCTP_STATE_ESTABLISHED) && (!chunk->data_accepted)) {
 		/*
 		 * If the receive buffer policy is 1, then each
 		 * association can allocate up to sk_rcvbuf bytes
@@ -5176,9 +5212,25 @@ static int sctp_eat_data(const struct sctp_association *asoc,
 			account_value = atomic_read(&asoc->rmem_alloc);
 		else
 			account_value = atomic_read(&sk->sk_rmem_alloc);
-
-		if (account_value > sk->sk_rcvbuf)
-			return SCTP_IERROR_IGNORE_TSN;
+		if (account_value > sk->sk_rcvbuf) {
+			/*
+			 * We need to make forward progress, even when we are
+			 * under memory pressure, so we always allow the
+			 * next tsn after the ctsn ack point to be accepted.
+			 * This lets us avoid deadlocks in which we have to
+			 * drop frames that would otherwise let us drain the
+			 * receive queue.
+			 */
+			if ((sctp_tsnmap_get_ctsn(map) + 1) != tsn)
+				return SCTP_IERROR_IGNORE_TSN;
+
+			/*
+			 * We're going to accept the frame but we should renege
+			 * to make space for it. This will send us down that
+			 * path later in this function.
+			 */
+			rcvbuf_over = 1;
+		}
 	}
 
 	/* Process ECN based congestion.
@@ -5226,6 +5278,7 @@ static int sctp_eat_data(const struct sctp_association *asoc,
 	datalen -= sizeof(sctp_data_chunk_t);
 
 	deliver = SCTP_CMD_CHUNK_ULP;
+	chunk->data_accepted = 1;
 
 	/* Think about partial delivery. */
 	if ((datalen >= asoc->rwnd) && (!asoc->ulpq.pd_mode)) {
@@ -5242,7 +5295,8 @@ static int sctp_eat_data(const struct sctp_association *asoc,
 	 * large spill over.
 	 */
 	if (!asoc->rwnd || asoc->rwnd_over ||
-	    (datalen > asoc->rwnd + asoc->frag_point)) {
+	    (datalen > asoc->rwnd + asoc->frag_point) ||
+	    rcvbuf_over) {
 
 		/* If this is the next TSN, consider reneging to make
 		 * room.   Note: Playing nice with a confused sender.  A
@@ -5250,8 +5304,8 @@ static int sctp_eat_data(const struct sctp_association *asoc,
 		 * space and in the future we may want to detect and
 		 * do more drastic reneging.
 		 */
-		if (sctp_tsnmap_has_gap(&asoc->peer.tsn_map) &&
-		    (sctp_tsnmap_get_ctsn(&asoc->peer.tsn_map) + 1) == tsn) {
+		if (sctp_tsnmap_has_gap(map) &&
+		    (sctp_tsnmap_get_ctsn(map) + 1) == tsn) {
 			SCTP_DEBUG_PRINTK("Reneging for tsn:%u\n", tsn);
 			deliver = SCTP_CMD_RENEGE;
 		} else {
@@ -5280,6 +5334,8 @@ static int sctp_eat_data(const struct sctp_association *asoc,
 		 * processing the rest of the chunks in the packet.
 		 */
 		sctp_add_cmd_sf(commands, SCTP_CMD_DISCARD_PACKET,SCTP_NULL());
+		sctp_add_cmd_sf(commands, SCTP_CMD_SET_SK_ERR,
+				SCTP_ERROR(ECONNABORTED));
 		sctp_add_cmd_sf(commands, SCTP_CMD_ASSOC_FAILED,
 				SCTP_U32(SCTP_ERROR_NO_DATA));
 		SCTP_INC_STATS(SCTP_MIB_ABORTEDS);
diff --git a/net/sctp/sm_statetable.c b/net/sctp/sm_statetable.c
index 75ef10408764..8bcca5676151 100644
--- a/net/sctp/sm_statetable.c
+++ b/net/sctp/sm_statetable.c
@@ -366,9 +366,9 @@ const sctp_sm_table_entry_t *sctp_sm_lookup_event(sctp_event_t event_type,
 	/* SCTP_STATE_EMPTY */ \
 	{.fn = sctp_sf_ootb, .name = "sctp_sf_ootb"}, \
 	/* SCTP_STATE_CLOSED */ \
-	{.fn = sctp_sf_bug, .name = "sctp_sf_bug"}, \
+	{.fn = sctp_sf_discard_chunk, .name = "sctp_sf_discard_chunk"}, \
 	/* SCTP_STATE_COOKIE_WAIT */ \
-	{.fn = sctp_sf_bug, .name = "sctp_sf_bug"}, \
+	{.fn = sctp_sf_discard_chunk, .name = "sctp_sf_discard_chunk"}, \
 	/* SCTP_STATE_COOKIE_ECHOED */ \
 	{.fn = sctp_sf_do_ecne, .name = "sctp_sf_do_ecne"}, \
 	/* SCTP_STATE_ESTABLISHED */ \
@@ -380,7 +380,7 @@ const sctp_sm_table_entry_t *sctp_sm_lookup_event(sctp_event_t event_type,
 	/* SCTP_STATE_SHUTDOWN_RECEIVED */ \
 	{.fn = sctp_sf_do_ecne, .name = "sctp_sf_do_ecne"}, \
 	/* SCTP_STATE_SHUTDOWN_ACK_SENT */ \
-	{.fn = sctp_sf_bug, .name = "sctp_sf_bug"}, \
+	{.fn = sctp_sf_discard_chunk, .name = "sctp_sf_discard_chunk"}, \
 } /* TYPE_SCTP_ECN_ECNE */
 
 #define TYPE_SCTP_ECN_CWR { \
@@ -401,7 +401,7 @@ const sctp_sm_table_entry_t *sctp_sm_lookup_event(sctp_event_t event_type,
 	/* SCTP_STATE_SHUTDOWN_RECEIVED */ \
 	{.fn = sctp_sf_discard_chunk, .name = "sctp_sf_discard_chunk"}, \
 	/* SCTP_STATE_SHUTDOWN_ACK_SENT */ \
-	{.fn = sctp_sf_bug, .name = "sctp_sf_bug"}, \
+	{.fn = sctp_sf_discard_chunk, .name = "sctp_sf_discard_chunk"}, \
 } /* TYPE_SCTP_ECN_CWR */
 
 #define TYPE_SCTP_SHUTDOWN_COMPLETE { \
@@ -647,7 +647,7 @@ chunk_event_table_unknown[SCTP_STATE_NUM_STATES] = {
 	/* SCTP_STATE_EMPTY */ \
 	{.fn = sctp_sf_bug, .name = "sctp_sf_bug"}, \
 	/* SCTP_STATE_CLOSED */ \
-	{.fn = sctp_sf_bug, .name = "sctp_sf_bug"}, \
+	{.fn = sctp_sf_error_closed, .name = "sctp_sf_error_closed"}, \
 	/* SCTP_STATE_COOKIE_WAIT */ \
 	{.fn = sctp_sf_do_prm_requestheartbeat,		      \
 	 .name = "sctp_sf_do_prm_requestheartbeat"},          \
diff --git a/net/sctp/socket.c b/net/sctp/socket.c
index b6e4b89539b3..174d4d35e951 100644
--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -1057,6 +1057,7 @@ static int __sctp_connect(struct sock* sk,
 	inet_sk(sk)->dport = htons(asoc->peer.port);
 	af = sctp_get_af_specific(to.sa.sa_family);
 	af->to_sk_daddr(&to, sk);
+	sk->sk_err = 0;
 
 	timeo = sock_sndtimeo(sk, sk->sk_socket->file->f_flags & O_NONBLOCK);
 	err = sctp_wait_for_connect(asoc, &timeo);
@@ -1228,7 +1229,7 @@ SCTP_STATIC void sctp_close(struct sock *sk, long timeout)
 
 	ep = sctp_sk(sk)->ep;
 
-	/* Walk all associations on a socket, not on an endpoint.  */
+	/* Walk all associations on an endpoint.  */
 	list_for_each_safe(pos, temp, &ep->asocs) {
 		asoc = list_entry(pos, struct sctp_association, asocs);
 
@@ -1241,13 +1242,13 @@ SCTP_STATIC void sctp_close(struct sock *sk, long timeout)
 			if (sctp_state(asoc, CLOSED)) {
 				sctp_unhash_established(asoc);
 				sctp_association_free(asoc);
+				continue;
+			}
+		}
 
-			} else if (sock_flag(sk, SOCK_LINGER) &&
-				   !sk->sk_lingertime)
-				sctp_primitive_ABORT(asoc, NULL);
-			else
-				sctp_primitive_SHUTDOWN(asoc, NULL);
-		} else
+		if (sock_flag(sk, SOCK_LINGER) && !sk->sk_lingertime)
+			sctp_primitive_ABORT(asoc, NULL);
+		else
 			sctp_primitive_SHUTDOWN(asoc, NULL);
 	}
 
@@ -5317,6 +5318,7 @@ static int sctp_wait_for_sndbuf(struct sctp_association *asoc, long *timeo_p,
 		 */
 		sctp_release_sock(sk);
 		current_timeo = schedule_timeout(current_timeo);
+		BUG_ON(sk != asoc->base.sk);
 		sctp_lock_sock(sk);
 
 		*timeo_p = current_timeo;
@@ -5604,12 +5606,14 @@ static void sctp_sock_migrate(struct sock *oldsk, struct sock *newsk,
 	 */
 	newsp->type = type;
 
-	spin_lock_bh(&oldsk->sk_lock.slock);
-	/* Migrate the backlog from oldsk to newsk. */
-	sctp_backlog_migrate(assoc, oldsk, newsk);
-	/* Migrate the association to the new socket. */
+	/* Mark the new socket "in-use" by the user so that any packets
+	 * that may arrive on the association after we've moved it are
+	 * queued to the backlog.  This prevents a potential race between
+	 * backlog processing on the old socket and new-packet processing
+	 * on the new socket.
+	 */
+	sctp_lock_sock(newsk);
 	sctp_assoc_migrate(assoc, newsk);
-	spin_unlock_bh(&oldsk->sk_lock.slock);
 
 	/* If the association on the newsk is already closed before accept()
 	 * is called, set RCV_SHUTDOWN flag.
@@ -5618,6 +5622,7 @@ static void sctp_sock_migrate(struct sock *oldsk, struct sock *newsk,
 		newsk->sk_shutdown |= RCV_SHUTDOWN;
 
 	newsk->sk_state = SCTP_SS_ESTABLISHED;
+	sctp_release_sock(newsk);
 }
 
 /* This proto struct describes the ULP interface for SCTP.  */
diff --git a/net/sctp/ulpqueue.c b/net/sctp/ulpqueue.c
index 2080b2d28c98..575e556aeb3e 100644
--- a/net/sctp/ulpqueue.c
+++ b/net/sctp/ulpqueue.c
@@ -279,6 +279,7 @@ static inline void sctp_ulpq_store_reasm(struct sctp_ulpq *ulpq,
 static struct sctp_ulpevent *sctp_make_reassembled_event(struct sk_buff_head *queue, struct sk_buff *f_frag, struct sk_buff *l_frag)
 {
 	struct sk_buff *pos;
+	struct sk_buff *new = NULL;
 	struct sctp_ulpevent *event;
 	struct sk_buff *pnext, *last;
 	struct sk_buff *list = skb_shinfo(f_frag)->frag_list;
@@ -297,11 +298,33 @@ static struct sctp_ulpevent *sctp_make_reassembled_event(struct sk_buff_head *qu
 	 */
 	if (last)
 		last->next = pos;
-	else
-		skb_shinfo(f_frag)->frag_list = pos;
+ 	else {
+ 		if (skb_cloned(f_frag)) {
+ 			/* This is a cloned skb, we can't just modify
+ 			 * the frag_list.  We need a new skb to do that.
+ 			 * Instead of calling skb_unshare(), we'll do it
+ 			 * ourselves since we need to delay the free.
+ 			 */
+ 			new = skb_copy(f_frag, GFP_ATOMIC);
+ 			if (!new)
+ 				return NULL;	/* try again later */
+
+ 			new->sk = f_frag->sk;
+
+ 			skb_shinfo(new)->frag_list = pos;
+ 		} else
+ 			skb_shinfo(f_frag)->frag_list = pos;
+ 	}
 
 	/* Remove the first fragment from the reassembly queue.  */
 	__skb_unlink(f_frag, queue);
+
+ 	/* if we did unshare, then free the old skb and re-assign */
+ 	if (new) {
+ 		kfree_skb(f_frag);
+ 		f_frag = new;
+ 	}
+
 	while (pos) {
 
 		pnext = pos->next;