Merge git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net

Merge in the fixes we had queued in case there was another -rc.

Signed-off-by: Jakub Kicinski <[e-mail]>

drivers/net/ethernet/amd/xgbe/xgbe-common.h

···
 #define MDIO_VEND2_PMA_CDR_CONTROL	0x8056
 #endif
 
+#ifndef MDIO_VEND2_PMA_MISC_CTRL0
+#define MDIO_VEND2_PMA_MISC_CTRL0	0x8090
+#endif
+
 #ifndef MDIO_CTRL1_SPEED1G
 #define MDIO_CTRL1_SPEED1G		(MDIO_CTRL1_SPEED10G & ~BMCR_SPEED100)
 #endif
···
 #define XGBE_PMA_RX_RST_0_MASK		BIT(4)
 #define XGBE_PMA_RX_RST_0_RESET_ON	0x10
 #define XGBE_PMA_RX_RST_0_RESET_OFF	0x00
+
+#define XGBE_PMA_PLL_CTRL_MASK		BIT(15)
+#define XGBE_PMA_PLL_CTRL_ENABLE	BIT(15)
+#define XGBE_PMA_PLL_CTRL_DISABLE	0x0000
 
 /* Bit setting and getting macros
  *  The get macro will extract the current bit field value from within

drivers/net/ethernet/amd/xgbe/xgbe-phy-v2.c

···
 	}
 }
 
+static void xgbe_phy_pll_ctrl(struct xgbe_prv_data *pdata, bool enable)
+{
+	XMDIO_WRITE_BITS(pdata, MDIO_MMD_PMAPMD, MDIO_VEND2_PMA_MISC_CTRL0,
+			 XGBE_PMA_PLL_CTRL_MASK,
+			 enable ? XGBE_PMA_PLL_CTRL_ENABLE
+				: XGBE_PMA_PLL_CTRL_DISABLE);
+
+	/* Wait for command to complete */
+	usleep_range(100, 200);
+}
+
 static void xgbe_phy_perform_ratechange(struct xgbe_prv_data *pdata,
 					unsigned int cmd, unsigned int sub_cmd)
 {
 	unsigned int s0 = 0;
 	unsigned int wait;
+
+	/* Disable PLL re-initialization during FW command processing */
+	xgbe_phy_pll_ctrl(pdata, false);
 
 	/* Log if a previous command did not complete */
 	if (XP_IOREAD_BITS(pdata, XP_DRIVER_INT_RO, STATUS)) {
···
 	wait = XGBE_RATECHANGE_COUNT;
 	while (wait--) {
 		if (!XP_IOREAD_BITS(pdata, XP_DRIVER_INT_RO, STATUS))
-			return;
+			goto reenable_pll;
 
 		usleep_range(1000, 2000);
 	}
···
 
 	/* Reset on error */
 	xgbe_phy_rx_reset(pdata);
+
+reenable_pll:
+	/* Enable PLL re-initialization */
+	xgbe_phy_pll_ctrl(pdata, true);
 }
 
 static void xgbe_phy_rrc(struct xgbe_prv_data *pdata)

drivers/net/ethernet/ibm/ibmvnic.c

···
 	ind_bufp = &tx_scrq->ind_buf;
 
 	if (test_bit(0, &adapter->resetting)) {
-		if (!netif_subqueue_stopped(netdev, skb))
-			netif_stop_subqueue(netdev, queue_num);
 		dev_kfree_skb_any(skb);
 
 		tx_send_failed++;
···
 
 	if (adapter->state == VNIC_PROBING) {
 		netdev_warn(netdev, "Adapter reset during probe\n");
-		adapter->init_done_rc = EAGAIN;
+		adapter->init_done_rc = -EAGAIN;
 		ret = EAGAIN;
 		goto err;
 	}
···
 			 */
 			adapter->login_pending = false;
 
-			if (!completion_done(&adapter->init_done)) {
-				complete(&adapter->init_done);
-				adapter->init_done_rc = -EIO;
-			}
-
 			if (adapter->state == VNIC_DOWN)
 				rc = ibmvnic_reset(adapter, VNIC_RESET_PASSIVE_INIT);
 			else
···
 					   rc);
 				adapter->failover_pending = false;
 			}
+
+			if (!completion_done(&adapter->init_done)) {
+				complete(&adapter->init_done);
+				if (!adapter->init_done_rc)
+					adapter->init_done_rc = -EAGAIN;
+			}
+
 			break;
 		case IBMVNIC_CRQ_INIT_COMPLETE:
 			dev_info(dev, "Partner initialization complete\n");
···
 	crq->cur = 0;
 	spin_lock_init(&crq->lock);
 
+	/* process any CRQs that were queued before we enabled interrupts */
+	tasklet_schedule(&adapter->tasklet);
+
 	return retrc;
 
 req_irq_failed:
···
 		}
 
 		rc = ibmvnic_reset_init(adapter, false);
-	} while (rc == EAGAIN);
+	} while (rc == -EAGAIN);
 
 	/* We are ignoring the error from ibmvnic_reset_init() assuming that the
 	 * partner is not ready. CRQ is not active. When the partner becomes

drivers/net/ethernet/netronome/nfp/nfp_net_common.c

···
 		if (napi_complete_done(napi, pkts_polled))
 			nfp_net_irq_unmask(r_vec->nfp_net, r_vec->irq_entry);
 
-	if (r_vec->nfp_net->rx_coalesce_adapt_on) {
+	if (r_vec->nfp_net->rx_coalesce_adapt_on && r_vec->rx_ring) {
 		struct dim_sample dim_sample = {};
 		unsigned int start;
 		u64 pkts, bytes;
···
 		net_dim(&r_vec->rx_dim, dim_sample);
 	}
 
-	if (r_vec->nfp_net->tx_coalesce_adapt_on) {
+	if (r_vec->nfp_net->tx_coalesce_adapt_on && r_vec->tx_ring) {
 		struct dim_sample dim_sample = {};
 		unsigned int start;
 		u64 pkts, bytes;
···
 
 	/* copy RX interrupt coalesce parameters */
 	value = (moder.pkts << 16) | (factor * moder.usec);
-	rtnl_lock();
 	nn_writel(nn, NFP_NET_CFG_RXR_IRQ_MOD(r_vec->rx_ring->idx), value);
 	(void)nfp_net_reconfig(nn, NFP_NET_CFG_UPDATE_IRQMOD);
-	rtnl_unlock();
 
 	dim->state = DIM_START_MEASURE;
 }
···
 
 	/* copy TX interrupt coalesce parameters */
 	value = (moder.pkts << 16) | (factor * moder.usec);
-	rtnl_lock();
 	nn_writel(nn, NFP_NET_CFG_TXR_IRQ_MOD(r_vec->tx_ring->idx), value);
 	(void)nfp_net_reconfig(nn, NFP_NET_CFG_UPDATE_IRQMOD);
-	rtnl_unlock();
 
 	dim->state = DIM_START_MEASURE;
 }

drivers/net/phy/phylink.c

···
 		return -EOPNOTSUPP;
 
 	if (!phylink_test(pl->supported, Asym_Pause) &&
-	    !pause->autoneg && pause->rx_pause != pause->tx_pause)
+	    pause->rx_pause != pause->tx_pause)
 		return -EINVAL;
 
 	pause_state = 0;

include/net/flow_dissector.h

···
 #define FLOW_DISSECTOR_F_PARSE_1ST_FRAG		BIT(0)
 #define FLOW_DISSECTOR_F_STOP_AT_FLOW_LABEL	BIT(1)
 #define FLOW_DISSECTOR_F_STOP_AT_ENCAP		BIT(2)
+#define FLOW_DISSECTOR_F_STOP_BEFORE_ENCAP	BIT(3)
 
 struct flow_dissector_key {
 	enum flow_dissector_key_id key_id;

include/net/sctp/sctp.h

···
 
 static inline int sctp_transport_pl_hlen(struct sctp_transport *t)
 {
-	return __sctp_mtu_payload(sctp_sk(t->asoc->base.sk), t, 0, 0);
+	return __sctp_mtu_payload(sctp_sk(t->asoc->base.sk), t, 0, 0) -
+	       sizeof(struct sctphdr);
 }
 
 static inline void sctp_transport_pl_reset(struct sctp_transport *t)
···
 	if (t->pl.state == SCTP_PL_DISABLED)
 		return;
 
-	if (del_timer(&t->probe_timer))
-		sctp_transport_put(t);
-
 	t->pl.state = SCTP_PL_BASE;
 	t->pl.pmtu = SCTP_BASE_PLPMTU;
 	t->pl.probe_size = SCTP_BASE_PLPMTU;
+	sctp_transport_reset_probe_timer(t);
 }
 
 static inline bool sctp_transport_pl_enabled(struct sctp_transport *t)

net/bridge/br_private.h

···
 
 static inline int br_cfm_mep_count(struct net_bridge *br, u32 *count)
 {
+	*count = 0;
 	return -EOPNOTSUPP;
 }
 
 static inline int br_cfm_peer_mep_count(struct net_bridge *br, u32 *count)
 {
+	*count = 0;
 	return -EOPNOTSUPP;
 }
 #endif

net/core/flow_dissector.c

···
 
 	switch (ip_proto) {
 	case IPPROTO_GRE:
+		if (flags & FLOW_DISSECTOR_F_STOP_BEFORE_ENCAP) {
+			fdret = FLOW_DISSECT_RET_OUT_GOOD;
+			break;
+		}
+
 		fdret = __skb_flow_dissect_gre(skb, key_control, flow_dissector,
 					       target_container, data,
 					       &proto, &nhoff, &hlen, flags);
···
 		break;
 	}
 	case IPPROTO_IPIP:
+		if (flags & FLOW_DISSECTOR_F_STOP_BEFORE_ENCAP) {
+			fdret = FLOW_DISSECT_RET_OUT_GOOD;
+			break;
+		}
+
 		proto = htons(ETH_P_IP);
 
 		key_control->flags |= FLOW_DIS_ENCAPSULATION;
···
 		break;
 
 	case IPPROTO_IPV6:
+		if (flags & FLOW_DISSECTOR_F_STOP_BEFORE_ENCAP) {
+			fdret = FLOW_DISSECT_RET_OUT_GOOD;
+			break;
+		}
+
 		proto = htons(ETH_P_IPV6);
 
 		key_control->flags |= FLOW_DIS_ENCAPSULATION;

net/ipv6/udp.c

···
 	if (!fl6.flowi6_oif)
 		fl6.flowi6_oif = np->sticky_pktinfo.ipi6_ifindex;
 
-	fl6.flowi6_mark = ipc6.sockc.mark;
 	fl6.flowi6_uid = sk->sk_uid;
 
 	if (msg->msg_controllen) {
···
 	ipc6.opt = opt;
 
 	fl6.flowi6_proto = sk->sk_protocol;
+	fl6.flowi6_mark = ipc6.sockc.mark;
 	fl6.daddr = *daddr;
 	if (ipv6_addr_any(&fl6.saddr) && !ipv6_addr_any(&np->saddr))
 		fl6.saddr = np->saddr;

net/sched/cls_flower.c

···
 				    ARRAY_SIZE(fl_ct_info_to_flower_map),
 				    post_ct);
 		skb_flow_dissect_hash(skb, &mask->dissector, &skb_key);
-		skb_flow_dissect(skb, &mask->dissector, &skb_key, 0);
+		skb_flow_dissect(skb, &mask->dissector, &skb_key,
+				 FLOW_DISSECTOR_F_STOP_BEFORE_ENCAP);
 
 		f = fl_mask_lookup(mask, &skb_key);
 		if (f && !tc_skip_sw(f->flags)) {

net/sctp/output.c

···
 	chunk = list_entry(packet->chunk_list.next, struct sctp_chunk, list);
 	sk = chunk->skb->sk;
 
-	/* check gso */
 	if (packet->size > tp->pathmtu && !packet->ipfragok && !chunk->pmtu_probe) {
-		if (!sk_can_gso(sk)) {
-			pr_err_once("Trying to GSO but underlying device doesn't support it.");
-			goto out;
+		if (tp->pl.state == SCTP_PL_ERROR) { /* do IP fragmentation if in Error state */
+			packet->ipfragok = 1;
+		} else {
+			if (!sk_can_gso(sk)) { /* check gso */
+				pr_err_once("Trying to GSO but underlying device doesn't support it.");
+				goto out;
+			}
+			gso = 1;
 		}
-		gso = 1;
 	}
 
 	/* alloc head skb */

net/sctp/transport.c

···
 		if (t->pl.probe_size == SCTP_BASE_PLPMTU) { /* BASE_PLPMTU Confirmation Failed */
 			t->pl.state = SCTP_PL_ERROR; /* Base -> Error */
 
-			t->pl.pmtu = SCTP_MIN_PLPMTU;
+			t->pl.pmtu = SCTP_BASE_PLPMTU;
 			t->pathmtu = t->pl.pmtu + sctp_transport_pl_hlen(t);
 			sctp_assoc_sync_pmtu(t->asoc);
 		}
···
 		if (pmtu >= SCTP_MIN_PLPMTU && pmtu < SCTP_BASE_PLPMTU) {
 			t->pl.state = SCTP_PL_ERROR; /* Base -> Error */
 
-			t->pl.pmtu = SCTP_MIN_PLPMTU;
+			t->pl.pmtu = SCTP_BASE_PLPMTU;
 			t->pathmtu = t->pl.pmtu + sctp_transport_pl_hlen(t);
+			return true;
 		}
 	} else if (t->pl.state == SCTP_PL_SEARCH) {
 		if (pmtu >= SCTP_BASE_PLPMTU && pmtu < t->pl.pmtu) {
···
 			t->pl.probe_high = 0;
 			t->pl.pmtu = SCTP_BASE_PLPMTU;
 			t->pathmtu = t->pl.pmtu + sctp_transport_pl_hlen(t);
+			return true;
 		} else if (pmtu > t->pl.pmtu && pmtu < t->pl.probe_size) {
 			t->pl.probe_size = pmtu;
 			t->pl.probe_count = 0;
-
-			return false;
 		}
 	} else if (t->pl.state == SCTP_PL_COMPLETE) {
 		if (pmtu >= SCTP_BASE_PLPMTU && pmtu < t->pl.pmtu) {
···
 			t->pl.probe_high = 0;
 			t->pl.pmtu = SCTP_BASE_PLPMTU;
 			t->pathmtu = t->pl.pmtu + sctp_transport_pl_hlen(t);
+			return true;
 		}
 	}
 
-	return true;
+	return false;
 }
 
 bool sctp_transport_update_pmtu(struct sctp_transport *t, u32 pmtu)

tools/testing/selftests/net/.gitignore

···
 timestamping
 txtimestamp
 so_netns_cookie
+test_unix_oob
+gro
+ioam6_parser
+toeplitz
+cmsg_so_mark

tools/testing/selftests/net/Makefile

···
 TEST_PROGS += ioam6.sh
 TEST_PROGS += gro.sh
 TEST_PROGS += gre_gso.sh
+TEST_PROGS += cmsg_so_mark.sh
 TEST_PROGS_EXTENDED := in_netns.sh
 TEST_GEN_FILES =  socket nettest
 TEST_GEN_FILES += psock_fanout psock_tpacket msg_zerocopy reuseport_addr_any
···
 TEST_GEN_PROGS = reuseport_bpf reuseport_bpf_cpu reuseport_bpf_numa
 TEST_GEN_PROGS += reuseport_dualstack reuseaddr_conflict tls
 TEST_GEN_FILES += toeplitz
+TEST_GEN_FILES += cmsg_so_mark
 
 TEST_FILES := settings
 

tools/testing/selftests/net/cmsg_so_mark.c

···
+// SPDX-License-Identifier: GPL-2.0-or-later
+#include <errno.h>
+#include <netdb.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <unistd.h>
+#include <linux/types.h>
+#include <sys/socket.h>
+
+int main(int argc, const char **argv)
+{
+	char cbuf[CMSG_SPACE(sizeof(__u32))];
+	struct addrinfo hints, *ai;
+	struct cmsghdr *cmsg;
+	struct iovec iov[1];
+	struct msghdr msg;
+	int mark;
+	int err;
+	int fd;
+
+	if (argc != 4) {
+		fprintf(stderr, "Usage: %s <dst_ip> <port> <mark>\n", argv[0]);
+		return 1;
+	}
+	mark = atoi(argv[3]);
+
+	memset(&hints, 0, sizeof(hints));
+	hints.ai_family = AF_UNSPEC;
+	hints.ai_socktype = SOCK_DGRAM;
+
+	ai = NULL;
+	err = getaddrinfo(argv[1], argv[2], &hints, &ai);
+	if (err) {
+		fprintf(stderr, "Can't resolve address: %s\n", strerror(errno));
+		return 1;
+	}
+
+	fd = socket(ai->ai_family, SOCK_DGRAM, IPPROTO_UDP);
+	if (fd < 0) {
+		fprintf(stderr, "Can't open socket: %s\n", strerror(errno));
+		freeaddrinfo(ai);
+		return 1;
+	}
+
+	iov[0].iov_base = "bla";
+	iov[0].iov_len = 4;
+
+	msg.msg_name = ai->ai_addr;
+	msg.msg_namelen = ai->ai_addrlen;
+	msg.msg_iov = iov;
+	msg.msg_iovlen = 1;
+	msg.msg_control = cbuf;
+	msg.msg_controllen = sizeof(cbuf);
+
+	cmsg = CMSG_FIRSTHDR(&msg);
+	cmsg->cmsg_level = SOL_SOCKET;
+	cmsg->cmsg_type = SO_MARK;
+	cmsg->cmsg_len = CMSG_LEN(sizeof(__u32));
+	*(__u32 *)CMSG_DATA(cmsg) = mark;
+
+	err = sendmsg(fd, &msg, 0);
+
+	close(fd);
+	freeaddrinfo(ai);
+	return err != 4;
+}

tools/testing/selftests/net/cmsg_so_mark.sh

···
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+NS=ns
+IP4=172.16.0.1/24
+TGT4=172.16.0.2
+IP6=2001:db8:1::1/64
+TGT6=2001:db8:1::2
+MARK=1000
+
+cleanup()
+{
+    ip netns del $NS
+}
+
+trap cleanup EXIT
+
+# Namespaces
+ip netns add $NS
+
+# Connectivity
+ip -netns $NS link add type dummy
+ip -netns $NS link set dev dummy0 up
+ip -netns $NS addr add $IP4 dev dummy0
+ip -netns $NS addr add $IP6 dev dummy0
+
+ip -netns $NS rule add fwmark $MARK lookup 300
+ip -6 -netns $NS rule add fwmark $MARK lookup 300
+ip -netns $NS route add prohibit any table 300
+ip -6 -netns $NS route add prohibit any table 300
+
+# Test
+BAD=0
+TOTAL=0
+
+check_result() {
+    ((TOTAL++))
+    if [ $1 -ne $2 ]; then
+	echo "  Case $3 returned $1, expected $2"
+	((BAD++))
+    fi
+}
+
+ip netns exec $NS ./cmsg_so_mark $TGT4 1234 $((MARK + 1))
+check_result $? 0 "IPv4 pass"
+ip netns exec $NS ./cmsg_so_mark $TGT6 1234 $((MARK + 1))
+check_result $? 0 "IPv6 pass"
+
+ip netns exec $NS ./cmsg_so_mark $TGT4 1234 $MARK
+check_result $? 1 "IPv4 rejection"
+ip netns exec $NS ./cmsg_so_mark $TGT6 1234 $MARK
+check_result $? 1 "IPv6 rejection"
+
+# Summary
+if [ $BAD -ne 0 ]; then
+    echo "FAIL - $BAD/$TOTAL cases failed"
+    exit 1
+else
+    echo "OK"
+    exit 0
+fi

tools/testing/selftests/net/forwarding/bridge_igmp.sh

···
 	local X=("192.0.2.20" "192.0.2.30")
 
 	# GMI should be 3 seconds
-	ip link set dev br0 type bridge mcast_query_interval 100 mcast_query_response_interval 100
+	ip link set dev br0 type bridge mcast_query_interval 100 \
+					mcast_query_response_interval 100 \
+					mcast_membership_interval 300
 
 	v3exclude_prepare $h1 $ALL_MAC $ALL_GROUP
-	ip link set dev br0 type bridge mcast_query_interval 500 mcast_query_response_interval 500
+	ip link set dev br0 type bridge mcast_query_interval 500 \
+					mcast_query_response_interval 500 \
+					mcast_membership_interval 1500
+
 	$MZ $h1 -c 1 -b $ALL_MAC -B $ALL_GROUP -t ip "proto=2,p=$MZPKT_ALLOW2" -q
 	sleep 3
 	bridge -j -d -s mdb show dev br0 \
···
 	log_test "IGMPv3 group $TEST_GROUP exclude timeout"
 
 	ip link set dev br0 type bridge mcast_query_interval 12500 \
-					mcast_query_response_interval 1000
+					mcast_query_response_interval 1000 \
+					mcast_membership_interval 26000
 
 	v3cleanup $swp1 $TEST_GROUP
 }

tools/testing/selftests/net/forwarding/bridge_mld.sh

···
 	local X=("2001:db8:1::20" "2001:db8:1::30")
 
 	# GMI should be 3 seconds
-	ip link set dev br0 type bridge mcast_query_interval 100 mcast_query_response_interval 100
+	ip link set dev br0 type bridge mcast_query_interval 100 \
+					mcast_query_response_interval 100 \
+					mcast_membership_interval 300
 
 	mldv2exclude_prepare $h1
-	ip link set dev br0 type bridge mcast_query_interval 500 mcast_query_response_interval 500
+	ip link set dev br0 type bridge mcast_query_interval 500 \
+					mcast_query_response_interval 500 \
+					mcast_membership_interval 1500
+
 	$MZ $h1 -c 1 $MZPKT_ALLOW2 -q
 	sleep 3
 	bridge -j -d -s mdb show dev br0 \
···
 	log_test "MLDv2 group $TEST_GROUP exclude timeout"
 
 	ip link set dev br0 type bridge mcast_query_interval 12500 \
-					mcast_query_response_interval 1000
+					mcast_query_response_interval 1000 \
+					mcast_membership_interval 26000
 
 	mldv2cleanup $swp1
 }