Merge tag 'net-next-6.17' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next

Pull networking updates from Jakub Kicinski:
 "Core & protocols:

   - Wrap datapath globals into net_aligned_data, to avoid false sharing

   - Preserve MSG_ZEROCOPY in forwarding (e.g. out of a container)

   - Add SO_INQ and SCM_INQ support to AF_UNIX

   - Add SIOCINQ support to AF_VSOCK

   - Add TCP_MAXSEG sockopt to MPTCP

   - Add IPv6 force_forwarding sysctl to enable forwarding per interface

   - Make TCP validation of whether packet fully fits in the receive
     window and the rcv_buf more strict. With increased use of HW
     aggregation a single "packet" can be multiple 100s of kB

   - Add MSG_MORE flag to optimize large TCP transmissions via sockmap,
     improves latency up to 33% for sockmap users

   - Convert TCP send queue handling from tasklet to BH workque

   - Improve BPF iteration over TCP sockets to see each socket exactly
     once

   - Remove obsolete and unused TCP RFC3517/RFC6675 loss recovery code

   - Support enabling kernel threads for NAPI processing on per-NAPI
     instance basis rather than a whole device. Fully stop the kernel
     NAPI thread when threaded NAPI gets disabled. Previously thread
     would stick around until ifdown due to tricky synchronization

   - Allow multicast routing to take effect on locally-generated packets

   - Add output interface argument for End.X in segment routing

   - MCTP: add support for gateway routing, improve bind() handling

   - Don't require rtnl_lock when fetching an IPv6 neighbor over Netlink

   - Add a new neighbor flag ("extern_valid"), which cedes refresh
     responsibilities to userspace. This is needed for EVPN multi-homing
     where a neighbor entry for a multi-homed host needs to be synced
     across all the VTEPs among which the host is multi-homed

   - Support NUD_PERMANENT for proxy neighbor entries

   - Add a new queuing discipline for IETF RFC9332 DualQ Coupled AQM

   - Add sequence numbers to netconsole messages. Unregister
     netconsole's console when all net targets are removed. Code
     refactoring. Add a number of selftests

   - Align IPSec inbound SA lookup to RFC 4301. Only SPI and protocol
     should be used for an inbound SA lookup

   - Support inspecting ref_tracker state via DebugFS

   - Don't force bonding advertisement frames tx to ~333 ms boundaries.
     Add broadcast_neighbor option to send ARP/ND on all bonded links

   - Allow providing upcall pid for the 'execute' command in openvswitch

   - Remove DCCP support from Netfilter's conntrack

   - Disallow multiple packet duplications in the queuing layer

   - Prevent use of deprecated iptables code on PREEMPT_RT

  Driver API:

   - Support RSS and hashing configuration over ethtool Netlink

   - Add dedicated ethtool callbacks for getting and setting hashing
     fields

   - Add support for power budget evaluation strategy in PSE /
     Power-over-Ethernet. Generate Netlink events for overcurrent etc

   - Support DPLL phase offset monitoring across all device inputs.
     Support providing clock reference and SYNC over separate DPLL
     inputs

   - Support traffic classes in devlink rate API for bandwidth
     management

   - Remove rtnl_lock dependency from UDP tunnel port configuration

  Device drivers:

   - Add a new Broadcom driver for 800G Ethernet (bnge)

   - Add a standalone driver for Microchip ZL3073x DPLL

   - Remove IBM's NETIUCV device driver

   - Ethernet high-speed NICs:
      - Broadcom (bnxt):
         - support zero-copy Tx of DMABUF memory
         - take page size into account for page pool recycling rings
      - Intel (100G, ice, idpf):
         - idpf: XDP and AF_XDP support preparations
         - idpf: add flow steering
         - add link_down_events statistic
         - clean up the TSPLL code
         - preparations for live VM migration
      - nVidia/Mellanox:
         - support zero-copy Rx/Tx interfaces (DMABUF and io_uring)
         - optimize context memory usage for matchers
         - expose serial numbers in devlink info
         - support PCIe congestion metrics
      - Meta (fbnic):
         - add 25G, 50G, and 100G link modes to phylink
         - support dumping FW logs
      - Marvell/Cavium:
         - support for CN20K generation of the Octeon chips
      - Amazon:
         - add HW clock (without timestamping, just hypervisor time access)

   - Ethernet virtual:
      - VirtIO net:
         - support segmentation of UDP-tunnel-encapsulated packets
      - Google (gve):
         - support packet timestamping and clock synchronization
      - Microsoft vNIC:
         - add handler for device-originated servicing events
         - allow dynamic MSI-X vector allocation
         - support Tx bandwidth clamping

   - Ethernet NICs consumer, and embedded:
      - AMD:
         - amd-xgbe: hardware timestamping and PTP clock support
      - Broadcom integrated MACs (bcmgenet, bcmasp):
         - use napi_complete_done() return value to support NAPI polling
         - add support for re-starting auto-negotiation
      - Broadcom switches (b53):
         - support BCM5325 switches
         - add bcm63xx EPHY power control
      - Synopsys (stmmac):
         - lots of code refactoring and cleanups
      - TI:
         - icssg-prueth: read firmware-names from device tree
         - icssg: PRP offload support
      - Microchip:
         - lan78xx: convert to PHYLINK for improved PHY and MAC management
         - ksz: add KSZ8463 switch support
      - Intel:
         - support similar queue priority scheme in multi-queue and
           time-sensitive networking (taprio)
         - support packet pre-emption in both
      - RealTek (r8169):
         - enable EEE at 5Gbps on RTL8126
      - Airoha:
         - add PPPoE offload support
         - MDIO bus controller for Airoha AN7583

   - Ethernet PHYs:
      - support for the IPQ5018 internal GE PHY
      - micrel KSZ9477 switch-integrated PHYs:
         - add MDI/MDI-X control support
         - add RX error counters
         - add cable test support
         - add Signal Quality Indicator (SQI) reporting
      - dp83tg720: improve reset handling and reduce link recovery time
      - support bcm54811 (and its MII-Lite interface type)
      - air_en8811h: support resume/suspend
      - support PHY counters for QCA807x and QCA808x
      - support WoL for QCA807x

   - CAN drivers:
      - rcar_canfd: support for Transceiver Delay Compensation
      - kvaser: report FW versions via devlink dev info

   - WiFi:
      - extended regulatory info support (6 GHz)
      - add statistics and beacon monitor for Multi-Link Operation (MLO)
      - support S1G aggregation, improve S1G support
      - add Radio Measurement action fields
      - support per-radio RTS threshold
      - some work around how FIPS affects wifi, which was wrong (RC4 is
        used by TKIP, not only WEP)
      - improvements for unsolicited probe response handling

   - WiFi drivers:
      - RealTek (rtw88):
         - IBSS mode for SDIO devices
      - RealTek (rtw89):
         - BT coexistence for MLO/WiFi7
         - concurrent station + P2P support
         - support for USB devices RTL8851BU/RTL8852BU
      - Intel (iwlwifi):
         - use embedded PNVM in (to be released) FW images to fix
           compatibility issues
         - many cleanups (unused FW APIs, PCIe code, WoWLAN)
         - some FIPS interoperability
      - MediaTek (mt76):
         - firmware recovery improvements
         - more MLO work
      - Qualcomm/Atheros (ath12k):
         - fix scan on multi-radio devices
         - more EHT/Wi-Fi 7 features
         - encapsulation/decapsulation offload
      - Broadcom (brcm80211):
         - support SDIO 43751 device

   - Bluetooth:
      - hci_event: add support for handling LE BIG Sync Lost event
      - ISO: add socket option to report packet seqnum via CMSG
      - ISO: support SCM_TIMESTAMPING for ISO TS

   - Bluetooth drivers:
      - intel_pcie: support Function Level Reset
      - nxpuart: add support for 4M baudrate
      - nxpuart: implement powerup sequence, reset, FW dump, and FW loading"

* tag 'net-next-6.17' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next: (1742 commits)
  dpll: zl3073x: Fix build failure
  selftests: bpf: fix legacy netfilter options
  ipv6: annotate data-races around rt->fib6_nsiblings
  ipv6: fix possible infinite loop in fib6_info_uses_dev()
  ipv6: prevent infinite loop in rt6_nlmsg_size()
  ipv6: add a retry logic in net6_rt_notify()
  vrf: Drop existing dst reference in vrf_ip6_input_dst
  net/sched: taprio: align entry index attr validation with mqprio
  net: fsl_pq_mdio: use dev_err_probe
  selftests: rtnetlink.sh: remove esp4_offload after test
  vsock: remove unnecessary null check in vsock_getname()
  igb: xsk: solve negative overflow of nb_pkts in zerocopy mode
  stmmac: xsk: fix negative overflow of budget in zerocopy mode
  dt-bindings: ieee802154: Convert at86rf230.txt yaml format
  net: dsa: microchip: Disable PTP function of KSZ8463
  net: dsa: microchip: Setup fiber ports for KSZ8463
  net: dsa: microchip: Write switch MAC address differently for KSZ8463
  net: dsa: microchip: Use different registers for KSZ8463
  net: dsa: microchip: Add KSZ8463 switch support to KSZ DSA driver
  dt-bindings: net: dsa: microchip: Add KSZ8463 switch support
  ...

1 files changed, 22 insertions, 21 deletions

diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index fccb05fb3a79..f639a2ae881a 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -413,7 +413,7 @@ static struct neighbour *ipv4_neigh_lookup(const struct dst_entry *dst,
 					   const void *daddr)
 {
 	const struct rtable *rt = container_of(dst, struct rtable, dst);
-	struct net_device *dev = dst->dev;
+	struct net_device *dev = dst_dev(dst);
 	struct neighbour *n;
 
 	rcu_read_lock();
@@ -440,7 +440,7 @@ static struct neighbour *ipv4_neigh_lookup(const struct dst_entry *dst,
 static void ipv4_confirm_neigh(const struct dst_entry *dst, const void *daddr)
 {
 	const struct rtable *rt = container_of(dst, struct rtable, dst);
-	struct net_device *dev = dst->dev;
+	struct net_device *dev = dst_dev(dst);
 	const __be32 *pkey = daddr;
 
 	if (rt->rt_gw_family == AF_INET) {
@@ -556,7 +556,8 @@ static void build_sk_flow_key(struct flowi4 *fl4, const struct sock *sk)
 			   inet_test_bit(HDRINCL, sk) ?
 				IPPROTO_RAW : sk->sk_protocol,
 			   inet_sk_flowi_flags(sk),
-			   daddr, inet->inet_saddr, 0, 0, sk->sk_uid);
+			   daddr, inet->inet_saddr, 0, 0,
+			   sk_uid(sk));
 	rcu_read_unlock();
 }
 
@@ -716,7 +717,7 @@ static void update_or_create_fnhe(struct fib_nh_common *nhc, __be32 daddr,
 		 */
 		rt = rcu_dereference(nhc->nhc_rth_input);
 		if (rt)
-			rt->dst.obsolete = DST_OBSOLETE_KILL;
+			WRITE_ONCE(rt->dst.obsolete, DST_OBSOLETE_KILL);
 
 		for_each_possible_cpu(i) {
 			struct rtable __rcu **prt;
@@ -724,7 +725,7 @@ static void update_or_create_fnhe(struct fib_nh_common *nhc, __be32 daddr,
 			prt = per_cpu_ptr(nhc->nhc_pcpu_rth_output, i);
 			rt = rcu_dereference(*prt);
 			if (rt)
-				rt->dst.obsolete = DST_OBSOLETE_KILL;
+				WRITE_ONCE(rt->dst.obsolete, DST_OBSOLETE_KILL);
 		}
 	}
 
@@ -796,7 +797,7 @@ static void __ip_do_redirect(struct rtable *rt, struct sk_buff *skb, struct flow
 						jiffies + ip_rt_gc_timeout);
 			}
 			if (kill_route)
-				rt->dst.obsolete = DST_OBSOLETE_KILL;
+				WRITE_ONCE(rt->dst.obsolete, DST_OBSOLETE_KILL);
 			call_netevent_notifiers(NETEVENT_NEIGH_UPDATE, n);
 		}
 		neigh_release(n);
@@ -841,9 +842,9 @@ static void ipv4_negative_advice(struct sock *sk,
 {
 	struct rtable *rt = dst_rtable(dst);
 
-	if ((dst->obsolete > 0) ||
+	if ((READ_ONCE(dst->obsolete) > 0) ||
 	    (rt->rt_flags & RTCF_REDIRECTED) ||
-	    rt->dst.expires)
+	    READ_ONCE(rt->dst.expires))
 		sk_dst_reset(sk);
 }
 
@@ -1025,14 +1026,15 @@ static void __ip_rt_update_pmtu(struct rtable *rt, struct flowi4 *fl4, u32 mtu)
 		return;
 
 	rcu_read_lock();
-	net = dev_net_rcu(dst->dev);
+	net = dev_net_rcu(dst_dev(dst));
 	if (mtu < net->ipv4.ip_rt_min_pmtu) {
 		lock = true;
 		mtu = min(old_mtu, net->ipv4.ip_rt_min_pmtu);
 	}
 
 	if (rt->rt_pmtu == mtu && !lock &&
-	    time_before(jiffies, dst->expires - net->ipv4.ip_rt_mtu_expires / 2))
+	    time_before(jiffies, READ_ONCE(dst->expires) -
+				 net->ipv4.ip_rt_mtu_expires / 2))
 		goto out;
 
 	if (fib_lookup(net, fl4, &res, 0) == 0) {
@@ -1135,7 +1137,7 @@ void ipv4_sk_update_pmtu(struct sk_buff *skb, struct sock *sk, u32 mtu)
 	__build_flow_key(net, &fl4, sk, iph, 0, 0, 0, 0, 0);
 
 	rt = dst_rtable(odst);
-	if (odst->obsolete && !odst->ops->check(odst, 0)) {
+	if (READ_ONCE(odst->obsolete) && !odst->ops->check(odst, 0)) {
 		rt = ip_route_output_flow(sock_net(sk), &fl4, sk);
 		if (IS_ERR(rt))
 			goto out;
@@ -1210,7 +1212,8 @@ INDIRECT_CALLABLE_SCOPE struct dst_entry *ipv4_dst_check(struct dst_entry *dst,
 	 * this is indicated by setting obsolete to DST_OBSOLETE_KILL or
 	 * DST_OBSOLETE_DEAD.
 	 */
-	if (dst->obsolete != DST_OBSOLETE_FORCE_CHK || rt_is_expired(rt))
+	if (READ_ONCE(dst->obsolete) != DST_OBSOLETE_FORCE_CHK ||
+	    rt_is_expired(rt))
 		return NULL;
 	return dst;
 }
@@ -1323,7 +1326,7 @@ static unsigned int ipv4_default_advmss(const struct dst_entry *dst)
 	struct net *net;
 
 	rcu_read_lock();
-	net = dev_net_rcu(dst->dev);
+	net = dev_net_rcu(dst_dev(dst));
 	advmss = max_t(unsigned int, ipv4_mtu(dst) - header_size,
 				   net->ipv4.ip_rt_min_advmss);
 	rcu_read_unlock();
@@ -1570,7 +1573,7 @@ void rt_flush_dev(struct net_device *dev)
 static bool rt_cache_valid(const struct rtable *rt)
 {
 	return	rt &&
-		rt->dst.obsolete == DST_OBSOLETE_FORCE_CHK &&
+		READ_ONCE(rt->dst.obsolete) == DST_OBSOLETE_FORCE_CHK &&
 		!rt_is_expired(rt);
 }
 
@@ -1684,8 +1687,8 @@ struct rtable *rt_dst_clone(struct net_device *dev, struct rtable *rt)
 		else if (rt->rt_gw_family == AF_INET6)
 			new_rt->rt_gw6 = rt->rt_gw6;
 
-		new_rt->dst.input = rt->dst.input;
-		new_rt->dst.output = rt->dst.output;
+		new_rt->dst.input = READ_ONCE(rt->dst.input);
+		new_rt->dst.output = READ_ONCE(rt->dst.output);
 		new_rt->dst.error = rt->dst.error;
 		new_rt->dst.lastuse = jiffies;
 		new_rt->dst.lwtstate = lwtstate_get(rt->dst.lwtstate);
@@ -2585,7 +2588,6 @@ static struct rtable *__mkroute_output(const struct fib_result *res,
 	do_cache = true;
 	if (type == RTN_BROADCAST) {
 		flags |= RTCF_BROADCAST | RTCF_LOCAL;
-		fi = NULL;
 	} else if (type == RTN_MULTICAST) {
 		flags |= RTCF_MULTICAST | RTCF_LOCAL;
 		if (!ip_check_mc_rcu(in_dev, fl4->daddr, fl4->saddr,
@@ -2660,7 +2662,7 @@ add:
 			if (IN_DEV_MFORWARD(in_dev) &&
 			    !ipv4_is_local_multicast(fl4->daddr)) {
 				rth->dst.input = ip_mr_input;
-				rth->dst.output = ip_mc_output;
+				rth->dst.output = ip_mr_output;
 			}
 		}
 #endif
@@ -2977,8 +2979,7 @@ static int rt_fill_info(struct net *net, __be32 dst, __be32 src,
 	if (rt->dst.dev &&
 	    nla_put_u32(skb, RTA_OIF, rt->dst.dev->ifindex))
 		goto nla_put_failure;
-	if (rt->dst.lwtstate &&
-	    lwtunnel_fill_encap(skb, rt->dst.lwtstate, RTA_ENCAP, RTA_ENCAP_TYPE) < 0)
+	if (lwtunnel_fill_encap(skb, rt->dst.lwtstate, RTA_ENCAP, RTA_ENCAP_TYPE) < 0)
 		goto nla_put_failure;
 #ifdef CONFIG_IP_ROUTE_CLASSID
 	if (rt->dst.tclassid &&
@@ -3009,7 +3010,7 @@ static int rt_fill_info(struct net *net, __be32 dst, __be32 src,
 		}
 	}
 
-	expires = rt->dst.expires;
+	expires = READ_ONCE(rt->dst.expires);
 	if (expires) {
 		unsigned long now = jiffies;