Merge tag 'net-next-for-5.16' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next

Pull networking updates from Jakub Kicinski:
 "Core:

   - Remove socket skb caches

   - Add a SO_RESERVE_MEM socket op to forward allocate buffer space and
     avoid memory accounting overhead on each message sent

   - Introduce managed neighbor entries - added by control plane and
     resolved by the kernel for use in acceleration paths (BPF / XDP
     right now, HW offload users will benefit as well)

   - Make neighbor eviction on link down controllable by userspace to
     work around WiFi networks with bad roaming implementations

   - vrf: Rework interaction with netfilter/conntrack

   - fq_codel: implement L4S style ce_threshold_ect1 marking

   - sch: Eliminate unnecessary RCU waits in mini_qdisc_pair_swap()

  BPF:

   - Add support for new btf kind BTF_KIND_TAG, arbitrary type tagging
     as implemented in LLVM14

   - Introduce bpf_get_branch_snapshot() to capture Last Branch Records

   - Implement variadic trace_printk helper

   - Add a new Bloomfilter map type

   - Track <8-byte scalar spill and refill

   - Access hw timestamp through BPF's __sk_buff

   - Disallow unprivileged BPF by default

   - Document BPF licensing

  Netfilter:

   - Introduce egress hook for looking at raw outgoing packets

   - Allow matching on and modifying inner headers / payload data

   - Add NFT_META_IFTYPE to match on the interface type either from
     ingress or egress

  Protocols:

   - Multi-Path TCP:
      - increase default max additional subflows to 2
      - rework forward memory allocation
      - add getsockopts: MPTCP_INFO, MPTCP_TCPINFO, MPTCP_SUBFLOW_ADDRS

   - MCTP flow support allowing lower layer drivers to configure msg
     muxing as needed

   - Automatic Multicast Tunneling (AMT) driver based on RFC7450

   - HSR support the redbox supervision frames (IEC-62439-3:2018)

   - Support for the ip6ip6 encapsulation of IOAM

   - Netlink interface for CAN-FD's Transmitter Delay Compensation

   - Support SMC-Rv2 eliminating the current same-subnet restriction, by
     exploiting the UDP encapsulation feature of RoCE adapters

   - TLS: add SM4 GCM/CCM crypto support

   - Bluetooth: initial support for link quality and audio/codec offload

  Driver APIs:

   - Add a batched interface for RX buffer allocation in AF_XDP buffer
     pool

   - ethtool: Add ability to control transceiver modules' power mode

   - phy: Introduce supported interfaces bitmap to express MAC
     capabilities and simplify PHY code

   - Drop rtnl_lock from DSA .port_fdb_{add,del} callbacks

  New drivers:

   - WiFi driver for Realtek 8852AE 802.11ax devices (rtw89)

   - Ethernet driver for ASIX AX88796C SPI device (x88796c)

  Drivers:

   - Broadcom PHYs
      - support 72165, 7712 16nm PHYs
      - support IDDQ-SR for additional power savings

   - PHY support for QCA8081, QCA9561 PHYs

   - NXP DPAA2: support for IRQ coalescing

   - NXP Ethernet (enetc): support for software TCP segmentation

   - Renesas Ethernet (ravb) - support DMAC and EMAC blocks of
     Gigabit-capable IP found on RZ/G2L SoC

   - Intel 100G Ethernet
      - support for eswitch offload of TC/OvS flow API, including
        offload of GRE, VxLAN, Geneve tunneling
      - support application device queues - ability to assign Rx and Tx
        queues to application threads
      - PTP and PPS (pulse-per-second) extensions

   - Broadcom Ethernet (bnxt)
      - devlink health reporting and device reload extensions

   - Mellanox Ethernet (mlx5)
      - offload macvlan interfaces
      - support HW offload of TC rules involving OVS internal ports
      - support HW-GRO and header/data split
      - support application device queues

   - Marvell OcteonTx2:
      - add XDP support for PF
      - add PTP support for VF

   - Qualcomm Ethernet switch (qca8k): support for QCA8328

   - Realtek Ethernet DSA switch (rtl8366rb)
      - support bridge offload
      - support STP, fast aging, disabling address learning
      - support for Realtek RTL8365MB-VC, a 4+1 port 10M/100M/1GE switch

   - Mellanox Ethernet/IB switch (mlxsw)
      - multi-level qdisc hierarchy offload (e.g. RED, prio and shaping)
      - offload root TBF qdisc as port shaper
      - support multiple routing interface MAC address prefixes
      - support for IP-in-IP with IPv6 underlay

   - MediaTek WiFi (mt76)
      - mt7921 - ASPM, 6GHz, SDIO and testmode support
      - mt7915 - LED and TWT support

   - Qualcomm WiFi (ath11k)
      - include channel rx and tx time in survey dump statistics
      - support for 80P80 and 160 MHz bandwidths
      - support channel 2 in 6 GHz band
      - spectral scan support for QCN9074
      - support for rx decapsulation offload (data frames in 802.3
        format)

   - Qualcomm phone SoC WiFi (wcn36xx)
      - enable Idle Mode Power Save (IMPS) to reduce power consumption
        during idle

   - Bluetooth driver support for MediaTek MT7922 and MT7921

   - Enable support for AOSP Bluetooth extension in Qualcomm WCN399x and
     Realtek 8822C/8852A

   - Microsoft vNIC driver (mana)
      - support hibernation and kexec

   - Google vNIC driver (gve)
      - support for jumbo frames
      - implement Rx page reuse

  Refactor:

   - Make all writes to netdev->dev_addr go thru helpers, so that we can
     add this address to the address rbtree and handle the updates

   - Various TCP cleanups and optimizations including improvements to
     CPU cache use

   - Simplify the gnet_stats, Qdisc stats' handling and remove
     qdisc->running sequence counter

   - Driver changes and API updates to address devlink locking
     deficiencies"

* tag 'net-next-for-5.16' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next: (2122 commits)
  Revert "net: avoid double accounting for pure zerocopy skbs"
  selftests: net: add arp_ndisc_evict_nocarrier
  net: ndisc: introduce ndisc_evict_nocarrier sysctl parameter
  net: arp: introduce arp_evict_nocarrier sysctl parameter
  libbpf: Deprecate AF_XDP support
  kbuild: Unify options for BTF generation for vmlinux and modules
  selftests/bpf: Add a testcase for 64-bit bounds propagation issue.
  bpf: Fix propagation of signed bounds from 64-bit min/max into 32-bit.
  bpf: Fix propagation of bounds from 64-bit min/max into 32-bit and var_off.
  net: vmxnet3: remove multiple false checks in vmxnet3_ethtool.c
  net: avoid double accounting for pure zerocopy skbs
  tcp: rename sk_wmem_free_skb
  netdevsim: fix uninit value in nsim_drv_configure_vfs()
  selftests/bpf: Fix also no-alu32 strobemeta selftest
  bpf: Add missing map_delete_elem method to bloom filter map
  selftests/bpf: Add bloom map success test for userspace calls
  bpf: Add alignment padding for "map_extra" + consolidate holes
  bpf: Bloom filter map naming fixups
  selftests/bpf: Add test cases for struct_ops prog
  bpf: Add dummy BPF STRUCT_OPS for test purpose
  ...

1 files changed, 146 insertions, 14 deletions

diff --git a/net/smc/smc_ib.c b/net/smc/smc_ib.c
index a8845343d183..d93055ec17ae 100644
--- a/net/smc/smc_ib.c
+++ b/net/smc/smc_ib.c
@@ -17,6 +17,7 @@
 #include <linux/scatterlist.h>
 #include <linux/wait.h>
 #include <linux/mutex.h>
+#include <linux/inetdevice.h>
 #include <rdma/ib_verbs.h>
 #include <rdma/ib_cache.h>
 
@@ -62,16 +63,23 @@ static int smc_ib_modify_qp_rtr(struct smc_link *lnk)
 		IB_QP_STATE | IB_QP_AV | IB_QP_PATH_MTU | IB_QP_DEST_QPN |
 		IB_QP_RQ_PSN | IB_QP_MAX_DEST_RD_ATOMIC | IB_QP_MIN_RNR_TIMER;
 	struct ib_qp_attr qp_attr;
+	u8 hop_lim = 1;
 
 	memset(&qp_attr, 0, sizeof(qp_attr));
 	qp_attr.qp_state = IB_QPS_RTR;
 	qp_attr.path_mtu = min(lnk->path_mtu, lnk->peer_mtu);
 	qp_attr.ah_attr.type = RDMA_AH_ATTR_TYPE_ROCE;
 	rdma_ah_set_port_num(&qp_attr.ah_attr, lnk->ibport);
-	rdma_ah_set_grh(&qp_attr.ah_attr, NULL, 0, lnk->sgid_index, 1, 0);
+	if (lnk->lgr->smc_version == SMC_V2 && lnk->lgr->uses_gateway)
+		hop_lim = IPV6_DEFAULT_HOPLIMIT;
+	rdma_ah_set_grh(&qp_attr.ah_attr, NULL, 0, lnk->sgid_index, hop_lim, 0);
 	rdma_ah_set_dgid_raw(&qp_attr.ah_attr, lnk->peer_gid);
-	memcpy(&qp_attr.ah_attr.roce.dmac, lnk->peer_mac,
-	       sizeof(lnk->peer_mac));
+	if (lnk->lgr->smc_version == SMC_V2 && lnk->lgr->uses_gateway)
+		memcpy(&qp_attr.ah_attr.roce.dmac, lnk->lgr->nexthop_mac,
+		       sizeof(lnk->lgr->nexthop_mac));
+	else
+		memcpy(&qp_attr.ah_attr.roce.dmac, lnk->peer_mac,
+		       sizeof(lnk->peer_mac));
 	qp_attr.dest_qp_num = lnk->peer_qpn;
 	qp_attr.rq_psn = lnk->peer_psn; /* starting receive packet seq # */
 	qp_attr.max_dest_rd_atomic = 1; /* max # of resources for incoming
@@ -183,9 +191,81 @@ bool smc_ib_port_active(struct smc_ib_device *smcibdev, u8 ibport)
 	return smcibdev->pattr[ibport - 1].state == IB_PORT_ACTIVE;
 }
 
+int smc_ib_find_route(__be32 saddr, __be32 daddr,
+		      u8 nexthop_mac[], u8 *uses_gateway)
+{
+	struct neighbour *neigh = NULL;
+	struct rtable *rt = NULL;
+	struct flowi4 fl4 = {
+		.saddr = saddr,
+		.daddr = daddr
+	};
+
+	if (daddr == cpu_to_be32(INADDR_NONE))
+		goto out;
+	rt = ip_route_output_flow(&init_net, &fl4, NULL);
+	if (IS_ERR(rt))
+		goto out;
+	if (rt->rt_uses_gateway && rt->rt_gw_family != AF_INET)
+		goto out;
+	neigh = rt->dst.ops->neigh_lookup(&rt->dst, NULL, &fl4.daddr);
+	if (neigh) {
+		memcpy(nexthop_mac, neigh->ha, ETH_ALEN);
+		*uses_gateway = rt->rt_uses_gateway;
+		return 0;
+	}
+out:
+	return -ENOENT;
+}
+
+static int smc_ib_determine_gid_rcu(const struct net_device *ndev,
+				    const struct ib_gid_attr *attr,
+				    u8 gid[], u8 *sgid_index,
+				    struct smc_init_info_smcrv2 *smcrv2)
+{
+	if (!smcrv2 && attr->gid_type == IB_GID_TYPE_ROCE) {
+		if (gid)
+			memcpy(gid, &attr->gid, SMC_GID_SIZE);
+		if (sgid_index)
+			*sgid_index = attr->index;
+		return 0;
+	}
+	if (smcrv2 && attr->gid_type == IB_GID_TYPE_ROCE_UDP_ENCAP &&
+	    smc_ib_gid_to_ipv4((u8 *)&attr->gid) != cpu_to_be32(INADDR_NONE)) {
+		struct in_device *in_dev = __in_dev_get_rcu(ndev);
+		const struct in_ifaddr *ifa;
+		bool subnet_match = false;
+
+		if (!in_dev)
+			goto out;
+		in_dev_for_each_ifa_rcu(ifa, in_dev) {
+			if (!inet_ifa_match(smcrv2->saddr, ifa))
+				continue;
+			subnet_match = true;
+			break;
+		}
+		if (!subnet_match)
+			goto out;
+		if (smcrv2->daddr && smc_ib_find_route(smcrv2->saddr,
+						       smcrv2->daddr,
+						       smcrv2->nexthop_mac,
+						       &smcrv2->uses_gateway))
+			goto out;
+
+		if (gid)
+			memcpy(gid, &attr->gid, SMC_GID_SIZE);
+		if (sgid_index)
+			*sgid_index = attr->index;
+		return 0;
+	}
+out:
+	return -ENODEV;
+}
+
 /* determine the gid for an ib-device port and vlan id */
 int smc_ib_determine_gid(struct smc_ib_device *smcibdev, u8 ibport,
-			 unsigned short vlan_id, u8 gid[], u8 *sgid_index)
+			 unsigned short vlan_id, u8 gid[], u8 *sgid_index,
+			 struct smc_init_info_smcrv2 *smcrv2)
 {
 	const struct ib_gid_attr *attr;
 	const struct net_device *ndev;
@@ -201,15 +281,13 @@ int smc_ib_determine_gid(struct smc_ib_device *smcibdev, u8 ibport,
 		if (!IS_ERR(ndev) &&
 		    ((!vlan_id && !is_vlan_dev(ndev)) ||
 		     (vlan_id && is_vlan_dev(ndev) &&
-		      vlan_dev_vlan_id(ndev) == vlan_id)) &&
-		    attr->gid_type == IB_GID_TYPE_ROCE) {
-			rcu_read_unlock();
-			if (gid)
-				memcpy(gid, &attr->gid, SMC_GID_SIZE);
-			if (sgid_index)
-				*sgid_index = attr->index;
-			rdma_put_gid_attr(attr);
-			return 0;
+		      vlan_dev_vlan_id(ndev) == vlan_id))) {
+			if (!smc_ib_determine_gid_rcu(ndev, attr, gid,
+						      sgid_index, smcrv2)) {
+				rcu_read_unlock();
+				rdma_put_gid_attr(attr);
+				return 0;
+			}
 		}
 		rcu_read_unlock();
 		rdma_put_gid_attr(attr);
@@ -217,6 +295,58 @@ int smc_ib_determine_gid(struct smc_ib_device *smcibdev, u8 ibport,
 	return -ENODEV;
 }
 
+/* check if gid is still defined on smcibdev */
+static bool smc_ib_check_link_gid(u8 gid[SMC_GID_SIZE], bool smcrv2,
+				  struct smc_ib_device *smcibdev, u8 ibport)
+{
+	const struct ib_gid_attr *attr;
+	bool rc = false;
+	int i;
+
+	for (i = 0; !rc && i < smcibdev->pattr[ibport - 1].gid_tbl_len; i++) {
+		attr = rdma_get_gid_attr(smcibdev->ibdev, ibport, i);
+		if (IS_ERR(attr))
+			continue;
+
+		rcu_read_lock();
+		if ((!smcrv2 && attr->gid_type == IB_GID_TYPE_ROCE) ||
+		    (smcrv2 && attr->gid_type == IB_GID_TYPE_ROCE_UDP_ENCAP &&
+		     !(ipv6_addr_type((const struct in6_addr *)&attr->gid)
+				     & IPV6_ADDR_LINKLOCAL)))
+			if (!memcmp(gid, &attr->gid, SMC_GID_SIZE))
+				rc = true;
+		rcu_read_unlock();
+		rdma_put_gid_attr(attr);
+	}
+	return rc;
+}
+
+/* check all links if the gid is still defined on smcibdev */
+static void smc_ib_gid_check(struct smc_ib_device *smcibdev, u8 ibport)
+{
+	struct smc_link_group *lgr;
+	int i;
+
+	spin_lock_bh(&smc_lgr_list.lock);
+	list_for_each_entry(lgr, &smc_lgr_list.list, list) {
+		if (strncmp(smcibdev->pnetid[ibport - 1], lgr->pnet_id,
+			    SMC_MAX_PNETID_LEN))
+			continue; /* lgr is not affected */
+		if (list_empty(&lgr->list))
+			continue;
+		for (i = 0; i < SMC_LINKS_PER_LGR_MAX; i++) {
+			if (lgr->lnk[i].state == SMC_LNK_UNUSED ||
+			    lgr->lnk[i].smcibdev != smcibdev)
+				continue;
+			if (!smc_ib_check_link_gid(lgr->lnk[i].gid,
+						   lgr->smc_version == SMC_V2,
+						   smcibdev, ibport))
+				smcr_port_err(smcibdev, ibport);
+		}
+	}
+	spin_unlock_bh(&smc_lgr_list.lock);
+}
+
 static int smc_ib_remember_port_attr(struct smc_ib_device *smcibdev, u8 ibport)
 {
 	int rc;
@@ -255,6 +385,7 @@ static void smc_ib_port_event_work(struct work_struct *work)
 		} else {
 			clear_bit(port_idx, smcibdev->ports_going_away);
 			smcr_port_add(smcibdev, port_idx + 1);
+			smc_ib_gid_check(smcibdev, port_idx + 1);
 		}
 	}
 }
@@ -523,6 +654,7 @@ void smc_ib_destroy_queue_pair(struct smc_link *lnk)
 /* create a queue pair within the protection domain for a link */
 int smc_ib_create_queue_pair(struct smc_link *lnk)
 {
+	int sges_per_buf = (lnk->lgr->smc_version == SMC_V2) ? 2 : 1;
 	struct ib_qp_init_attr qp_attr = {
 		.event_handler = smc_ib_qp_event_handler,
 		.qp_context = lnk,
@@ -536,7 +668,7 @@ int smc_ib_create_queue_pair(struct smc_link *lnk)
 			.max_send_wr = SMC_WR_BUF_CNT * 3,
 			.max_recv_wr = SMC_WR_BUF_CNT * 3,
 			.max_send_sge = SMC_IB_MAX_SEND_SGE,
-			.max_recv_sge = 1,
+			.max_recv_sge = sges_per_buf,
 		},
 		.sq_sig_type = IB_SIGNAL_REQ_WR,
 		.qp_type = IB_QPT_RC,