Merge tag 'net-5.19-rc4' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net

Pull networking fixes from Paolo Abeni:
 "Including fixes from bpf and netfilter.

  Current release - regressions:

   - netfilter: cttimeout: fix slab-out-of-bounds read in
     cttimeout_net_exit

Current release - new code bugs:

   - bpf: ftrace: keep address offset in ftrace_lookup_symbols

   - bpf: force cookies array to follow symbols sorting

  Previous releases - regressions:

   - ipv4: ping: fix bind address validity check

   - tipc: fix use-after-free read in tipc_named_reinit

   - eth: veth: add updating of trans_start

  Previous releases - always broken:

   - sock: redo the psock vs ULP protection check

   - netfilter: nf_dup_netdev: fix skb_under_panic

   - bpf: fix request_sock leak in sk lookup helpers

   - eth: igb: fix a use-after-free issue in igb_clean_tx_ring

   - eth: ice: prohibit improper channel config for DCB

   - eth: at803x: fix null pointer dereference on AR9331 phy

   - eth: virtio_net: fix xdp_rxq_info bug after suspend/resume

  Misc:

   - eth: hinic: replace memcpy() with direct assignment"

* tag 'net-5.19-rc4' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net: (47 commits)
  net: openvswitch: fix parsing of nw_proto for IPv6 fragments
  sock: redo the psock vs ULP protection check
  Revert "net/tls: fix tls_sk_proto_close executed repeatedly"
  virtio_net: fix xdp_rxq_info bug after suspend/resume
  igb: Make DMA faster when CPU is active on the PCIe link
  net: dsa: qca8k: reduce mgmt ethernet timeout
  net: dsa: qca8k: reset cpu port on MTU change
  MAINTAINERS: Add a maintainer for OCP Time Card
  hinic: Replace memcpy() with direct assignment
  Revert "drivers/net/ethernet/neterion/vxge: Fix a use-after-free bug in vxge-main.c"
  net: phy: smsc: Disable Energy Detect Power-Down in interrupt mode
  ice: ethtool: Prohibit improper channel config for DCB
  ice: ethtool: advertise 1000M speeds properly
  ice: Fix switchdev rules book keeping
  ice: ignore protocol field in GTP offload
  netfilter: nf_dup_netdev: add and use recursion counter
  netfilter: nf_dup_netdev: do not push mac header a second time
  selftests: netfilter: correct PKTGEN_SCRIPT_PATHS in nft_concat_range.sh
  net/tls: fix tls_sk_proto_close executed repeatedly
  erspan: do not assume transport header is always set
  ...

Author: torvalds

MAINTAINERS

@@ -3662,7 +3662,7 @@ BPF JIT for ARM
 M:	Shubham Bansal <illusionist.neo@gmail.com>
 L:	netdev@vger.kernel.org
 L:	bpf@vger.kernel.org
-S:	Maintained
+S:	Odd Fixes
 F:	arch/arm/net/
 
 BPF JIT for ARM64
@@ -3686,14 +3686,15 @@ BPF JIT for NFP NICs
 M:	Jakub Kicinski <kuba@kernel.org>
 L:	netdev@vger.kernel.org
 L:	bpf@vger.kernel.org
-S:	Supported
+S:	Odd Fixes
 F:	drivers/net/ethernet/netronome/nfp/bpf/
 
 BPF JIT for POWERPC (32-BIT AND 64-BIT)
 M:	Naveen N. Rao <naveen.n.rao@linux.ibm.com>
+M:	Michael Ellerman <mpe@ellerman.id.au>
 L:	netdev@vger.kernel.org
 L:	bpf@vger.kernel.org
-S:	Maintained
+S:	Supported
 F:	arch/powerpc/net/
 
 BPF JIT for RISC-V (32-bit)
@@ -3719,22 +3720,22 @@ M:	Heiko Carstens <hca@linux.ibm.com>
 M:	Vasily Gorbik <gor@linux.ibm.com>
 L:	netdev@vger.kernel.org
 L:	bpf@vger.kernel.org
-S:	Maintained
+S:	Supported
 F:	arch/s390/net/
 X:	arch/s390/net/pnet.c
 
 BPF JIT for SPARC (32-BIT AND 64-BIT)
 M:	David S. Miller <davem@davemloft.net>
 L:	netdev@vger.kernel.org
 L:	bpf@vger.kernel.org
-S:	Maintained
+S:	Odd Fixes
 F:	arch/sparc/net/
 
 BPF JIT for X86 32-BIT
 M:	Wang YanQing <udknight@gmail.com>
 L:	netdev@vger.kernel.org
 L:	bpf@vger.kernel.org
-S:	Maintained
+S:	Odd Fixes
 F:	arch/x86/net/bpf_jit_comp32.c
 
 BPF JIT for X86 64-BIT
@@ -3757,6 +3758,19 @@ F:	include/linux/bpf_lsm.h
 F:	kernel/bpf/bpf_lsm.c
 F:	security/bpf/
 
+BPF L7 FRAMEWORK
+M:	John Fastabend <john.fastabend@gmail.com>
+M:	Jakub Sitnicki <jakub@cloudflare.com>
+L:	netdev@vger.kernel.org
+L:	bpf@vger.kernel.org
+S:	Maintained
+F:	include/linux/skmsg.h
+F:	net/core/skmsg.c
+F:	net/core/sock_map.c
+F:	net/ipv4/tcp_bpf.c
+F:	net/ipv4/udp_bpf.c
+F:	net/unix/unix_bpf.c
+
 BPFTOOL
 M:	Quentin Monnet <quentin@isovalent.com>
 L:	bpf@vger.kernel.org
@@ -11098,20 +11112,6 @@ S:	Maintained
 F:	include/net/l3mdev.h
 F:	net/l3mdev
 
-L7 BPF FRAMEWORK
-M:	John Fastabend <john.fastabend@gmail.com>
-M:	Daniel Borkmann <daniel@iogearbox.net>
-M:	Jakub Sitnicki <jakub@cloudflare.com>
-L:	netdev@vger.kernel.org
-L:	bpf@vger.kernel.org
-S:	Maintained
-F:	include/linux/skmsg.h
-F:	net/core/skmsg.c
-F:	net/core/sock_map.c
-F:	net/ipv4/tcp_bpf.c
-F:	net/ipv4/udp_bpf.c
-F:	net/unix/unix_bpf.c
-
 LANDLOCK SECURITY MODULE
 M:	Mickaël Salaün <mic@digikod.net>
 L:	linux-security-module@vger.kernel.org
@@ -13954,7 +13954,6 @@ F:	net/ipv6/tcp*.c
 NETWORKING [TLS]
 M:	Boris Pismenny <borisp@nvidia.com>
 M:	John Fastabend <john.fastabend@gmail.com>
-M:	Daniel Borkmann <daniel@iogearbox.net>
 M:	Jakub Kicinski <kuba@kernel.org>
 L:	netdev@vger.kernel.org
 S:	Maintained
@@ -14871,6 +14870,7 @@ F:	include/dt-bindings/
 
 OPENCOMPUTE PTP CLOCK DRIVER
 M:	Jonathan Lemon <jonathan.lemon@gmail.com>
+M:	Vadim Fedorenko <vadfed@fb.com>
 L:	netdev@vger.kernel.org
 S:	Maintained
 F:	drivers/ptp/ptp_ocp.c

arch/x86/net/bpf_jit_comp.c

@@ -1420,8 +1420,9 @@ st:			if (is_imm8(insn->off))
 		case BPF_JMP | BPF_CALL:
 			func = (u8 *) __bpf_call_base + imm32;
 			if (tail_call_reachable) {
+				/* mov rax, qword ptr [rbp - rounded_stack_depth - 8] */
 				EMIT3_off32(0x48, 0x8B, 0x85,
-					    -(bpf_prog->aux->stack_depth + 8));
+					    -round_up(bpf_prog->aux->stack_depth, 8) - 8);
 				if (!imm32 || emit_call(&prog, func, image + addrs[i - 1] + 7))
 					return -EINVAL;
 			} else {

drivers/net/bonding/bond_main.c

@@ -3684,9 +3684,11 @@ static void bond_activebackup_arp_mon(struct bonding *bond)
 		if (!rtnl_trylock())
 			return;
 
-		if (should_notify_peers)
+		if (should_notify_peers) {
+			bond->send_peer_notif--;
 			call_netdevice_notifiers(NETDEV_NOTIFY_PEERS,
 						 bond->dev);
+		}
 		if (should_notify_rtnl) {
 			bond_slave_state_notify(bond);
 			bond_slave_link_notify(bond);

drivers/net/dsa/qca8k.c

@@ -2334,6 +2334,7 @@ static int
 qca8k_port_change_mtu(struct dsa_switch *ds, int port, int new_mtu)
 {
 	struct qca8k_priv *priv = ds->priv;
+	int ret;
 
 	/* We have only have a general MTU setting.
 	 * DSA always set the CPU port's MTU to the largest MTU of the slave
@@ -2344,8 +2345,27 @@ qca8k_port_change_mtu(struct dsa_switch *ds, int port, int new_mtu)
 	if (!dsa_is_cpu_port(ds, port))
 		return 0;
 
+	/* To change the MAX_FRAME_SIZE the cpu ports must be off or
+	 * the switch panics.
+	 * Turn off both cpu ports before applying the new value to prevent
+	 * this.
+	 */
+	if (priv->port_enabled_map & BIT(0))
+		qca8k_port_set_status(priv, 0, 0);
+
+	if (priv->port_enabled_map & BIT(6))
+		qca8k_port_set_status(priv, 6, 0);
+
 	/* Include L2 header / FCS length */
-	return qca8k_write(priv, QCA8K_MAX_FRAME_SIZE, new_mtu + ETH_HLEN + ETH_FCS_LEN);
+	ret = qca8k_write(priv, QCA8K_MAX_FRAME_SIZE, new_mtu + ETH_HLEN + ETH_FCS_LEN);
+
+	if (priv->port_enabled_map & BIT(0))
+		qca8k_port_set_status(priv, 0, 1);
+
+	if (priv->port_enabled_map & BIT(6))
+		qca8k_port_set_status(priv, 6, 1);
+
+	return ret;
 }
 
 static int

drivers/net/dsa/qca8k.h

@@ -15,7 +15,7 @@
 
 #define QCA8K_ETHERNET_MDIO_PRIORITY			7
 #define QCA8K_ETHERNET_PHY_PRIORITY			6
-#define QCA8K_ETHERNET_TIMEOUT				100
+#define QCA8K_ETHERNET_TIMEOUT				5
 
 #define QCA8K_NUM_PORTS					7
 #define QCA8K_NUM_CPU_PORTS				2

drivers/net/ethernet/huawei/hinic/hinic_devlink.c

@@ -43,9 +43,7 @@ static bool check_image_valid(struct hinic_devlink_priv *priv, const u8 *buf,
 
 	for (i = 0; i < fw_image->fw_info.fw_section_cnt; i++) {
 		len += fw_image->fw_section_info[i].fw_section_len;
-		memcpy(&host_image->image_section_info[i],
-		       &fw_image->fw_section_info[i],
-		       sizeof(struct fw_section_info_st));
+		host_image->image_section_info[i] = fw_image->fw_section_info[i];
 	}
 
 	if (len != fw_image->fw_len ||

drivers/net/ethernet/intel/ice/ice_ethtool.c

@@ -2189,6 +2189,42 @@ ice_setup_autoneg(struct ice_port_info *p, struct ethtool_link_ksettings *ks,
 	return err;
 }
 
+/**
+ * ice_set_phy_type_from_speed - set phy_types based on speeds
+ * and advertised modes
+ * @ks: ethtool link ksettings struct
+ * @phy_type_low: pointer to the lower part of phy_type
+ * @phy_type_high: pointer to the higher part of phy_type
+ * @adv_link_speed: targeted link speeds bitmap
+ */
+static void
+ice_set_phy_type_from_speed(const struct ethtool_link_ksettings *ks,
+			    u64 *phy_type_low, u64 *phy_type_high,
+			    u16 adv_link_speed)
+{
+	/* Handle 1000M speed in a special way because ice_update_phy_type
+	 * enables all link modes, but having mixed copper and optical
+	 * standards is not supported.
+	 */
+	adv_link_speed &= ~ICE_AQ_LINK_SPEED_1000MB;
+
+	if (ethtool_link_ksettings_test_link_mode(ks, advertising,
+						  1000baseT_Full))
+		*phy_type_low |= ICE_PHY_TYPE_LOW_1000BASE_T |
+				 ICE_PHY_TYPE_LOW_1G_SGMII;
+
+	if (ethtool_link_ksettings_test_link_mode(ks, advertising,
+						  1000baseKX_Full))
+		*phy_type_low |= ICE_PHY_TYPE_LOW_1000BASE_KX;
+
+	if (ethtool_link_ksettings_test_link_mode(ks, advertising,
+						  1000baseX_Full))
+		*phy_type_low |= ICE_PHY_TYPE_LOW_1000BASE_SX |
+				 ICE_PHY_TYPE_LOW_1000BASE_LX;
+
+	ice_update_phy_type(phy_type_low, phy_type_high, adv_link_speed);
+}
+
 /**
  * ice_set_link_ksettings - Set Speed and Duplex
  * @netdev: network interface device structure
@@ -2320,7 +2356,8 @@ ice_set_link_ksettings(struct net_device *netdev,
 		adv_link_speed = curr_link_speed;
 
 	/* Convert the advertise link speeds to their corresponded PHY_TYPE */
-	ice_update_phy_type(&phy_type_low, &phy_type_high, adv_link_speed);
+	ice_set_phy_type_from_speed(ks, &phy_type_low, &phy_type_high,
+				    adv_link_speed);
 
 	if (!autoneg_changed && adv_link_speed == curr_link_speed) {
 		netdev_info(netdev, "Nothing changed, exiting without setting anything.\n");
@@ -3470,6 +3507,16 @@ static int ice_set_channels(struct net_device *dev, struct ethtool_channels *ch)
 	new_rx = ch->combined_count + ch->rx_count;
 	new_tx = ch->combined_count + ch->tx_count;
 
+	if (new_rx < vsi->tc_cfg.numtc) {
+		netdev_err(dev, "Cannot set less Rx channels, than Traffic Classes you have (%u)\n",
+			   vsi->tc_cfg.numtc);
+		return -EINVAL;
+	}
+	if (new_tx < vsi->tc_cfg.numtc) {
+		netdev_err(dev, "Cannot set less Tx channels, than Traffic Classes you have (%u)\n",
+			   vsi->tc_cfg.numtc);
+		return -EINVAL;
+	}
 	if (new_rx > ice_get_max_rxq(pf)) {
 		netdev_err(dev, "Maximum allowed Rx channels is %d\n",
 			   ice_get_max_rxq(pf));

drivers/net/ethernet/intel/ice/ice_lib.c

@@ -909,7 +909,7 @@ static void ice_set_dflt_vsi_ctx(struct ice_hw *hw, struct ice_vsi_ctx *ctxt)
  * @vsi: the VSI being configured
  * @ctxt: VSI context structure
  */
-static void ice_vsi_setup_q_map(struct ice_vsi *vsi, struct ice_vsi_ctx *ctxt)
+static int ice_vsi_setup_q_map(struct ice_vsi *vsi, struct ice_vsi_ctx *ctxt)
 {
 	u16 offset = 0, qmap = 0, tx_count = 0, pow = 0;
 	u16 num_txq_per_tc, num_rxq_per_tc;
@@ -982,7 +982,18 @@ static void ice_vsi_setup_q_map(struct ice_vsi *vsi, struct ice_vsi_ctx *ctxt)
 	else
 		vsi->num_rxq = num_rxq_per_tc;
 
+	if (vsi->num_rxq > vsi->alloc_rxq) {
+		dev_err(ice_pf_to_dev(vsi->back), "Trying to use more Rx queues (%u), than were allocated (%u)!\n",
+			vsi->num_rxq, vsi->alloc_rxq);
+		return -EINVAL;
+	}
+
 	vsi->num_txq = tx_count;
+	if (vsi->num_txq > vsi->alloc_txq) {
+		dev_err(ice_pf_to_dev(vsi->back), "Trying to use more Tx queues (%u), than were allocated (%u)!\n",
+			vsi->num_txq, vsi->alloc_txq);
+		return -EINVAL;
+	}
 
 	if (vsi->type == ICE_VSI_VF && vsi->num_txq != vsi->num_rxq) {
 		dev_dbg(ice_pf_to_dev(vsi->back), "VF VSI should have same number of Tx and Rx queues. Hence making them equal\n");
@@ -1000,6 +1011,8 @@ static void ice_vsi_setup_q_map(struct ice_vsi *vsi, struct ice_vsi_ctx *ctxt)
 	 */
 	ctxt->info.q_mapping[0] = cpu_to_le16(vsi->rxq_map[0]);
 	ctxt->info.q_mapping[1] = cpu_to_le16(vsi->num_rxq);
+
+	return 0;
 }
 
 /**
@@ -1187,7 +1200,10 @@ static int ice_vsi_init(struct ice_vsi *vsi, bool init_vsi)
 	if (vsi->type == ICE_VSI_CHNL) {
 		ice_chnl_vsi_setup_q_map(vsi, ctxt);
 	} else {
-		ice_vsi_setup_q_map(vsi, ctxt);
+		ret = ice_vsi_setup_q_map(vsi, ctxt);
+		if (ret)
+			goto out;
+
 		if (!init_vsi) /* means VSI being updated */
 			/* must to indicate which section of VSI context are
 			 * being modified
@@ -3464,7 +3480,7 @@ void ice_vsi_cfg_netdev_tc(struct ice_vsi *vsi, u8 ena_tc)
  *
  * Prepares VSI tc_config to have queue configurations based on MQPRIO options.
  */
-static void
+static int
 ice_vsi_setup_q_map_mqprio(struct ice_vsi *vsi, struct ice_vsi_ctx *ctxt,
 			   u8 ena_tc)
 {
@@ -3513,7 +3529,18 @@ ice_vsi_setup_q_map_mqprio(struct ice_vsi *vsi, struct ice_vsi_ctx *ctxt,
 
 	/* Set actual Tx/Rx queue pairs */
 	vsi->num_txq = offset + qcount_tx;
+	if (vsi->num_txq > vsi->alloc_txq) {
+		dev_err(ice_pf_to_dev(vsi->back), "Trying to use more Tx queues (%u), than were allocated (%u)!\n",
+			vsi->num_txq, vsi->alloc_txq);
+		return -EINVAL;
+	}
+
 	vsi->num_rxq = offset + qcount_rx;
+	if (vsi->num_rxq > vsi->alloc_rxq) {
+		dev_err(ice_pf_to_dev(vsi->back), "Trying to use more Rx queues (%u), than were allocated (%u)!\n",
+			vsi->num_rxq, vsi->alloc_rxq);
+		return -EINVAL;
+	}
 
 	/* Setup queue TC[0].qmap for given VSI context */
 	ctxt->info.tc_mapping[0] = cpu_to_le16(qmap);
@@ -3531,6 +3558,8 @@ ice_vsi_setup_q_map_mqprio(struct ice_vsi *vsi, struct ice_vsi_ctx *ctxt,
 	dev_dbg(ice_pf_to_dev(vsi->back), "vsi->num_rxq = %d\n",  vsi->num_rxq);
 	dev_dbg(ice_pf_to_dev(vsi->back), "all_numtc %u, all_enatc: 0x%04x, tc_cfg.numtc %u\n",
 		vsi->all_numtc, vsi->all_enatc, vsi->tc_cfg.numtc);
+
+	return 0;
 }
 
 /**
@@ -3580,9 +3609,12 @@ int ice_vsi_cfg_tc(struct ice_vsi *vsi, u8 ena_tc)
 
 	if (vsi->type == ICE_VSI_PF &&
 	    test_bit(ICE_FLAG_TC_MQPRIO, pf->flags))
-		ice_vsi_setup_q_map_mqprio(vsi, ctx, ena_tc);
+		ret = ice_vsi_setup_q_map_mqprio(vsi, ctx, ena_tc);
 	else
-		ice_vsi_setup_q_map(vsi, ctx);
+		ret = ice_vsi_setup_q_map(vsi, ctx);
+
+	if (ret)
+		goto out;
 
 	/* must to indicate which section of VSI context are being modified */
 	ctx->info.valid_sections = cpu_to_le16(ICE_AQ_VSI_PROP_RXQ_MAP_VALID);

drivers/net/ethernet/intel/ice/ice_tc_lib.c

@@ -524,6 +524,7 @@ ice_eswitch_add_tc_fltr(struct ice_vsi *vsi, struct ice_tc_flower_fltr *fltr)
 	 */
 	fltr->rid = rule_added.rid;
 	fltr->rule_id = rule_added.rule_id;
+	fltr->dest_id = rule_added.vsi_handle;
 
 exit:
 	kfree(list);
@@ -993,7 +994,9 @@ ice_parse_cls_flower(struct net_device *filter_dev, struct ice_vsi *vsi,
 		n_proto_key = ntohs(match.key->n_proto);
 		n_proto_mask = ntohs(match.mask->n_proto);
 
-		if (n_proto_key == ETH_P_ALL || n_proto_key == 0) {
+		if (n_proto_key == ETH_P_ALL || n_proto_key == 0 ||
+		    fltr->tunnel_type == TNL_GTPU ||
+		    fltr->tunnel_type == TNL_GTPC) {
 			n_proto_key = 0;
 			n_proto_mask = 0;
 		} else {