Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next

Pull networking updates from David Miller:
 "Highlights:

   1) Support AES128-CCM ciphers in kTLS, from Vakul Garg.

   2) Add fib_sync_mem to control the amount of dirty memory we allow to
      queue up between synchronize RCU calls, from David Ahern.

   3) Make flow classifier more lockless, from Vlad Buslov.

   4) Add PHY downshift support to aquantia driver, from Heiner
      Kallweit.

   5) Add SKB cache for TCP rx and tx, from Eric Dumazet. This reduces
      contention on SLAB spinlocks in heavy RPC workloads.

   6) Partial GSO offload support in XFRM, from Boris Pismenny.

   7) Add fast link down support to ethtool, from Heiner Kallweit.

   8) Use siphash for IP ID generator, from Eric Dumazet.

   9) Pull nexthops even further out from ipv4/ipv6 routes and FIB
      entries, from David Ahern.

  10) Move skb->xmit_more into a per-cpu variable, from Florian
      Westphal.

  11) Improve eBPF verifier speed and increase maximum program size,
      from Alexei Starovoitov.

  12) Eliminate per-bucket spinlocks in rhashtable, and instead use bit
      spinlocks. From Neil Brown.

  13) Allow tunneling with GUE encap in ipvs, from Jacky Hu.

  14) Improve link partner cap detection in generic PHY code, from
      Heiner Kallweit.

  15) Add layer 2 encap support to bpf_skb_adjust_room(), from Alan
      Maguire.

  16) Remove SKB list implementation assumptions in SCTP, your's truly.

  17) Various cleanups, optimizations, and simplifications in r8169
      driver. From Heiner Kallweit.

  18) Add memory accounting on TX and RX path of SCTP, from Xin Long.

  19) Switch PHY drivers over to use dynamic featue detection, from
      Heiner Kallweit.

  20) Support flow steering without masking in dpaa2-eth, from Ioana
      Ciocoi.

  21) Implement ndo_get_devlink_port in netdevsim driver, from Jiri
      Pirko.

  22) Increase the strict parsing of current and future netlink
      attributes, also export such policies to userspace. From Johannes
      Berg.

  23) Allow DSA tag drivers to be modular, from Andrew Lunn.

  24) Remove legacy DSA probing support, also from Andrew Lunn.

  25) Allow ll_temac driver to be used on non-x86 platforms, from Esben
      Haabendal.

  26) Add a generic tracepoint for TX queue timeouts to ease debugging,
      from Cong Wang.

  27) More indirect call optimizations, from Paolo Abeni"

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1763 commits)
  cxgb4: Fix error path in cxgb4_init_module
  net: phy: improve pause mode reporting in phy_print_status
  dt-bindings: net: Fix a typo in the phy-mode list for ethernet bindings
  net: macb: Change interrupt and napi enable order in open
  net: ll_temac: Improve error message on error IRQ
  net/sched: remove block pointer from common offload structure
  net: ethernet: support of_get_mac_address new ERR_PTR error
  net: usb: smsc: fix warning reported by kbuild test robot
  staging: octeon-ethernet: Fix of_get_mac_address ERR_PTR check
  net: dsa: support of_get_mac_address new ERR_PTR error
  net: dsa: sja1105: Fix status initialization in sja1105_get_ethtool_stats
  vrf: sit mtu should not be updated when vrf netdev is the link
  net: dsa: Fix error cleanup path in dsa_init_module
  l2tp: Fix possible NULL pointer dereference
  taprio: add null check on sched_nest to avoid potential null pointer dereference
  net: mvpp2: cls: fix less than zero check on a u32 variable
  net_sched: sch_fq: handle non connected flows
  net_sched: sch_fq: do not assume EDT packets are ordered
  net: hns3: use devm_kcalloc when allocating desc_cb
  net: hns3: some cleanup for struct hns3_enet_ring
  ...

7 files changed, 94 insertions, 56 deletions

diff --git a/net/sctp/ipv6.c b/net/sctp/ipv6.c
index 6200cd2b4b99..188c47eb206e 100644
--- a/net/sctp/ipv6.c
+++ b/net/sctp/ipv6.c
@@ -1030,6 +1030,7 @@ static const struct proto_ops inet6_seqpacket_ops = {
 	.getname	   = sctp_getname,
 	.poll		   = sctp_poll,
 	.ioctl		   = inet6_ioctl,
+	.gettstamp	   = sock_gettstamp,
 	.listen		   = sctp_inet_listen,
 	.shutdown	   = inet_shutdown,
 	.setsockopt	   = sock_common_setsockopt,
diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c
index 951afdeea5e9..f0631bf486b6 100644
--- a/net/sctp/protocol.c
+++ b/net/sctp/protocol.c
@@ -1026,6 +1026,7 @@ static const struct proto_ops inet_seqpacket_ops = {
 	.getname	   = inet_getname,	/* Semantics are different.  */
 	.poll		   = sctp_poll,
 	.ioctl		   = inet_ioctl,
+	.gettstamp	   = sock_gettstamp,
 	.listen		   = sctp_inet_listen,
 	.shutdown	   = inet_shutdown,	/* Looks harmless.  */
 	.setsockopt	   = sock_common_setsockopt, /* IP_SOL IP_OPTION is a problem */
diff --git a/net/sctp/sm_statefuns.c b/net/sctp/sm_statefuns.c
index 713a669d2058..e3f4abe6134e 100644
--- a/net/sctp/sm_statefuns.c
+++ b/net/sctp/sm_statefuns.c
@@ -6431,13 +6431,15 @@ static int sctp_eat_data(const struct sctp_association *asoc,
 	 * in sctp_ulpevent_make_rcvmsg will drop the frame if we grow our
 	 * memory usage too much
 	 */
-	if (*sk->sk_prot_creator->memory_pressure) {
+	if (sk_under_memory_pressure(sk)) {
 		if (sctp_tsnmap_has_gap(map) &&
 		    (sctp_tsnmap_get_ctsn(map) + 1) == tsn) {
 			pr_debug("%s: under pressure, reneging for tsn:%u\n",
 				 __func__, tsn);
 			deliver = SCTP_CMD_RENEGE;
-		 }
+		} else {
+			sk_mem_reclaim(sk);
+		}
 	}
 
 	/*
diff --git a/net/sctp/socket.c b/net/sctp/socket.c
index 4583fa914e62..e4e892cc5644 100644
--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -1913,7 +1913,10 @@ static int sctp_sendmsg_to_asoc(struct sctp_association *asoc,
 	if (sctp_wspace(asoc) < (int)msg_len)
 		sctp_prsctp_prune(asoc, sinfo, msg_len - sctp_wspace(asoc));
 
-	if (sctp_wspace(asoc) <= 0) {
+	if (sk_under_memory_pressure(sk))
+		sk_mem_reclaim(sk);
+
+	if (sctp_wspace(asoc) <= 0 || !sk_wmem_schedule(sk, msg_len)) {
 		timeo = sock_sndtimeo(sk, msg->msg_flags & MSG_DONTWAIT);
 		err = sctp_wait_for_sndbuf(asoc, &timeo, msg_len);
 		if (err)
@@ -8931,7 +8934,10 @@ static int sctp_wait_for_sndbuf(struct sctp_association *asoc, long *timeo_p,
 			goto do_error;
 		if (signal_pending(current))
 			goto do_interrupted;
-		if ((int)msg_len <= sctp_wspace(asoc))
+		if (sk_under_memory_pressure(sk))
+			sk_mem_reclaim(sk);
+		if ((int)msg_len <= sctp_wspace(asoc) &&
+		    sk_wmem_schedule(sk, msg_len))
 			break;
 
 		/* Let another process have a go.  Since we are going
diff --git a/net/sctp/stream_interleave.c b/net/sctp/stream_interleave.c
index 102c6fefe38c..25e0b7e5189c 100644
--- a/net/sctp/stream_interleave.c
+++ b/net/sctp/stream_interleave.c
@@ -484,14 +484,15 @@ static struct sctp_ulpevent *sctp_intl_order(struct sctp_ulpq *ulpq,
 }
 
 static int sctp_enqueue_event(struct sctp_ulpq *ulpq,
-			      struct sctp_ulpevent *event)
+			      struct sk_buff_head *skb_list)
 {
-	struct sk_buff *skb = sctp_event2skb(event);
 	struct sock *sk = ulpq->asoc->base.sk;
 	struct sctp_sock *sp = sctp_sk(sk);
-	struct sk_buff_head *skb_list;
+	struct sctp_ulpevent *event;
+	struct sk_buff *skb;
 
-	skb_list = (struct sk_buff_head *)skb->prev;
+	skb = __skb_peek(skb_list);
+	event = sctp_skb2event(skb);
 
 	if (sk->sk_shutdown & RCV_SHUTDOWN &&
 	    (sk->sk_shutdown & SEND_SHUTDOWN ||
@@ -858,19 +859,24 @@ static int sctp_ulpevent_idata(struct sctp_ulpq *ulpq,
 
 	if (!(event->msg_flags & SCTP_DATA_UNORDERED)) {
 		event = sctp_intl_reasm(ulpq, event);
-		if (event && event->msg_flags & MSG_EOR) {
+		if (event) {
 			skb_queue_head_init(&temp);
 			__skb_queue_tail(&temp, sctp_event2skb(event));
 
-			event = sctp_intl_order(ulpq, event);
+			if (event->msg_flags & MSG_EOR)
+				event = sctp_intl_order(ulpq, event);
 		}
 	} else {
 		event = sctp_intl_reasm_uo(ulpq, event);
+		if (event) {
+			skb_queue_head_init(&temp);
+			__skb_queue_tail(&temp, sctp_event2skb(event));
+		}
 	}
 
 	if (event) {
 		event_eor = (event->msg_flags & MSG_EOR) ? 1 : 0;
-		sctp_enqueue_event(ulpq, event);
+		sctp_enqueue_event(ulpq, &temp);
 	}
 
 	return event_eor;
@@ -944,20 +950,27 @@ out:
 static void sctp_intl_start_pd(struct sctp_ulpq *ulpq, gfp_t gfp)
 {
 	struct sctp_ulpevent *event;
+	struct sk_buff_head temp;
 
 	if (!skb_queue_empty(&ulpq->reasm)) {
 		do {
 			event = sctp_intl_retrieve_first(ulpq);
-			if (event)
-				sctp_enqueue_event(ulpq, event);
+			if (event) {
+				skb_queue_head_init(&temp);
+				__skb_queue_tail(&temp, sctp_event2skb(event));
+				sctp_enqueue_event(ulpq, &temp);
+			}
 		} while (event);
 	}
 
 	if (!skb_queue_empty(&ulpq->reasm_uo)) {
 		do {
 			event = sctp_intl_retrieve_first_uo(ulpq);
-			if (event)
-				sctp_enqueue_event(ulpq, event);
+			if (event) {
+				skb_queue_head_init(&temp);
+				__skb_queue_tail(&temp, sctp_event2skb(event));
+				sctp_enqueue_event(ulpq, &temp);
+			}
 		} while (event);
 	}
 }
@@ -1059,7 +1072,7 @@ static void sctp_intl_reap_ordered(struct sctp_ulpq *ulpq, __u16 sid)
 
 	if (event) {
 		sctp_intl_retrieve_ordered(ulpq, event);
-		sctp_enqueue_event(ulpq, event);
+		sctp_enqueue_event(ulpq, &temp);
 	}
 }
 
@@ -1298,6 +1311,15 @@ static void sctp_handle_iftsn(struct sctp_ulpq *ulpq, struct sctp_chunk *chunk)
 			       ntohl(skip->mid), skip->flags);
 }
 
+static int do_ulpq_tail_event(struct sctp_ulpq *ulpq, struct sctp_ulpevent *event)
+{
+	struct sk_buff_head temp;
+
+	skb_queue_head_init(&temp);
+	__skb_queue_tail(&temp, sctp_event2skb(event));
+	return sctp_ulpq_tail_event(ulpq, &temp);
+}
+
 static struct sctp_stream_interleave sctp_stream_interleave_0 = {
 	.data_chunk_len		= sizeof(struct sctp_data_chunk),
 	.ftsn_chunk_len		= sizeof(struct sctp_fwdtsn_chunk),
@@ -1306,7 +1328,7 @@ static struct sctp_stream_interleave sctp_stream_interleave_0 = {
 	.assign_number		= sctp_chunk_assign_ssn,
 	.validate_data		= sctp_validate_data,
 	.ulpevent_data		= sctp_ulpq_tail_data,
-	.enqueue_event		= sctp_ulpq_tail_event,
+	.enqueue_event		= do_ulpq_tail_event,
 	.renege_events		= sctp_ulpq_renege,
 	.start_pd		= sctp_ulpq_partial_delivery,
 	.abort_pd		= sctp_ulpq_abort_pd,
@@ -1317,6 +1339,16 @@ static struct sctp_stream_interleave sctp_stream_interleave_0 = {
 	.handle_ftsn		= sctp_handle_fwdtsn,
 };
 
+static int do_sctp_enqueue_event(struct sctp_ulpq *ulpq,
+				 struct sctp_ulpevent *event)
+{
+	struct sk_buff_head temp;
+
+	skb_queue_head_init(&temp);
+	__skb_queue_tail(&temp, sctp_event2skb(event));
+	return sctp_enqueue_event(ulpq, &temp);
+}
+
 static struct sctp_stream_interleave sctp_stream_interleave_1 = {
 	.data_chunk_len		= sizeof(struct sctp_idata_chunk),
 	.ftsn_chunk_len		= sizeof(struct sctp_ifwdtsn_chunk),
@@ -1325,7 +1357,7 @@ static struct sctp_stream_interleave sctp_stream_interleave_1 = {
 	.assign_number		= sctp_chunk_assign_mid,
 	.validate_data		= sctp_validate_idata,
 	.ulpevent_data		= sctp_ulpevent_idata,
-	.enqueue_event		= sctp_enqueue_event,
+	.enqueue_event		= do_sctp_enqueue_event,
 	.renege_events		= sctp_renege_events,
 	.start_pd		= sctp_intl_start_pd,
 	.abort_pd		= sctp_intl_abort_pd,
diff --git a/net/sctp/ulpevent.c b/net/sctp/ulpevent.c
index 8cb7d9858270..c2a7478587ab 100644
--- a/net/sctp/ulpevent.c
+++ b/net/sctp/ulpevent.c
@@ -634,8 +634,9 @@ struct sctp_ulpevent *sctp_ulpevent_make_rcvmsg(struct sctp_association *asoc,
 						gfp_t gfp)
 {
 	struct sctp_ulpevent *event = NULL;
-	struct sk_buff *skb;
-	size_t padding, len;
+	struct sk_buff *skb = chunk->skb;
+	struct sock *sk = asoc->base.sk;
+	size_t padding, datalen;
 	int rx_count;
 
 	/*
@@ -646,15 +647,12 @@ struct sctp_ulpevent *sctp_ulpevent_make_rcvmsg(struct sctp_association *asoc,
 	if (asoc->ep->rcvbuf_policy)
 		rx_count = atomic_read(&asoc->rmem_alloc);
 	else
-		rx_count = atomic_read(&asoc->base.sk->sk_rmem_alloc);
+		rx_count = atomic_read(&sk->sk_rmem_alloc);
 
-	if (rx_count >= asoc->base.sk->sk_rcvbuf) {
+	datalen = ntohs(chunk->chunk_hdr->length);
 
-		if ((asoc->base.sk->sk_userlocks & SOCK_RCVBUF_LOCK) ||
-		    (!sk_rmem_schedule(asoc->base.sk, chunk->skb,
-				       chunk->skb->truesize)))
-			goto fail;
-	}
+	if (rx_count >= sk->sk_rcvbuf || !sk_rmem_schedule(sk, skb, datalen))
+		goto fail;
 
 	/* Clone the original skb, sharing the data.  */
 	skb = skb_clone(chunk->skb, gfp);
@@ -681,8 +679,7 @@ struct sctp_ulpevent *sctp_ulpevent_make_rcvmsg(struct sctp_association *asoc,
 	 * The sender should never pad with more than 3 bytes.  The receiver
 	 * MUST ignore the padding bytes.
 	 */
-	len = ntohs(chunk->chunk_hdr->length);
-	padding = SCTP_PAD4(len) - len;
+	padding = SCTP_PAD4(datalen) - datalen;
 
 	/* Fixup cloned skb with just this chunks data.  */
 	skb_trim(skb, chunk->chunk_end - padding - skb->data);
diff --git a/net/sctp/ulpqueue.c b/net/sctp/ulpqueue.c
index 5dde92101743..a212fe079c07 100644
--- a/net/sctp/ulpqueue.c
+++ b/net/sctp/ulpqueue.c
@@ -116,12 +116,13 @@ int sctp_ulpq_tail_data(struct sctp_ulpq *ulpq, struct sctp_chunk *chunk,
 	event = sctp_ulpq_reasm(ulpq, event);
 
 	/* Do ordering if needed.  */
-	if ((event) && (event->msg_flags & MSG_EOR)) {
+	if (event) {
 		/* Create a temporary list to collect chunks on.  */
 		skb_queue_head_init(&temp);
 		__skb_queue_tail(&temp, sctp_event2skb(event));
 
-		event = sctp_ulpq_order(ulpq, event);
+		if (event->msg_flags & MSG_EOR)
+			event = sctp_ulpq_order(ulpq, event);
 	}
 
 	/* Send event to the ULP.  'event' is the sctp_ulpevent for
@@ -129,7 +130,7 @@ int sctp_ulpq_tail_data(struct sctp_ulpq *ulpq, struct sctp_chunk *chunk,
 	 */
 	if (event) {
 		event_eor = (event->msg_flags & MSG_EOR) ? 1 : 0;
-		sctp_ulpq_tail_event(ulpq, event);
+		sctp_ulpq_tail_event(ulpq, &temp);
 	}
 
 	return event_eor;
@@ -193,18 +194,17 @@ static int sctp_ulpq_clear_pd(struct sctp_ulpq *ulpq)
 	return sctp_clear_pd(ulpq->asoc->base.sk, ulpq->asoc);
 }
 
-/* If the SKB of 'event' is on a list, it is the first such member
- * of that list.
- */
-int sctp_ulpq_tail_event(struct sctp_ulpq *ulpq, struct sctp_ulpevent *event)
+int sctp_ulpq_tail_event(struct sctp_ulpq *ulpq, struct sk_buff_head *skb_list)
 {
 	struct sock *sk = ulpq->asoc->base.sk;
 	struct sctp_sock *sp = sctp_sk(sk);
-	struct sk_buff_head *queue, *skb_list;
-	struct sk_buff *skb = sctp_event2skb(event);
+	struct sctp_ulpevent *event;
+	struct sk_buff_head *queue;
+	struct sk_buff *skb;
 	int clear_pd = 0;
 
-	skb_list = (struct sk_buff_head *) skb->prev;
+	skb = __skb_peek(skb_list);
+	event = sctp_skb2event(skb);
 
 	/* If the socket is just going to throw this away, do not
 	 * even try to deliver it.
@@ -257,13 +257,7 @@ int sctp_ulpq_tail_event(struct sctp_ulpq *ulpq, struct sctp_ulpevent *event)
 		}
 	}
 
-	/* If we are harvesting multiple skbs they will be
-	 * collected on a list.
-	 */
-	if (skb_list)
-		skb_queue_splice_tail_init(skb_list, queue);
-	else
-		__skb_queue_tail(queue, skb);
+	skb_queue_splice_tail_init(skb_list, queue);
 
 	/* Did we just complete partial delivery and need to get
 	 * rolling again?  Move pending data to the receive
@@ -738,25 +732,25 @@ void sctp_ulpq_reasm_flushtsn(struct sctp_ulpq *ulpq, __u32 fwd_tsn)
 static void sctp_ulpq_reasm_drain(struct sctp_ulpq *ulpq)
 {
 	struct sctp_ulpevent *event = NULL;
-	struct sk_buff_head temp;
 
 	if (skb_queue_empty(&ulpq->reasm))
 		return;
 
 	while ((event = sctp_ulpq_retrieve_reassembled(ulpq)) != NULL) {
-		/* Do ordering if needed.  */
-		if ((event) && (event->msg_flags & MSG_EOR)) {
-			skb_queue_head_init(&temp);
-			__skb_queue_tail(&temp, sctp_event2skb(event));
+		struct sk_buff_head temp;
+
+		skb_queue_head_init(&temp);
+		__skb_queue_tail(&temp, sctp_event2skb(event));
 
+		/* Do ordering if needed.  */
+		if (event->msg_flags & MSG_EOR)
 			event = sctp_ulpq_order(ulpq, event);
-		}
 
 		/* Send event to the ULP.  'event' is the
 		 * sctp_ulpevent for  very first SKB on the  temp' list.
 		 */
 		if (event)
-			sctp_ulpq_tail_event(ulpq, event);
+			sctp_ulpq_tail_event(ulpq, &temp);
 	}
 }
 
@@ -956,7 +950,7 @@ static void sctp_ulpq_reap_ordered(struct sctp_ulpq *ulpq, __u16 sid)
 	if (event) {
 		/* see if we have more ordered that we can deliver */
 		sctp_ulpq_retrieve_ordered(ulpq, event);
-		sctp_ulpq_tail_event(ulpq, event);
+		sctp_ulpq_tail_event(ulpq, &temp);
 	}
 }
 
@@ -1082,7 +1076,11 @@ void sctp_ulpq_partial_delivery(struct sctp_ulpq *ulpq,
 		event = sctp_ulpq_retrieve_first(ulpq);
 		/* Send event to the ULP.   */
 		if (event) {
-			sctp_ulpq_tail_event(ulpq, event);
+			struct sk_buff_head temp;
+
+			skb_queue_head_init(&temp);
+			__skb_queue_tail(&temp, sctp_event2skb(event));
+			sctp_ulpq_tail_event(ulpq, &temp);
 			sctp_ulpq_set_pd(ulpq);
 			return;
 		}
@@ -1106,7 +1104,8 @@ void sctp_ulpq_renege(struct sctp_ulpq *ulpq, struct sctp_chunk *chunk,
 			freed += sctp_ulpq_renege_frags(ulpq, needed - freed);
 	}
 	/* If able to free enough room, accept this chunk. */
-	if (freed >= needed) {
+	if (sk_rmem_schedule(asoc->base.sk, chunk->skb, needed) &&
+	    freed >= needed) {
 		int retval = sctp_ulpq_tail_data(ulpq, chunk, gfp);
 		/*
 		 * Enter partial delivery if chunk has not been