Merge tag 'net-next-6.0' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next

Pull networking changes from Paolo Abeni:
 "Core:

   - Refactor the forward memory allocation to better cope with memory
     pressure with many open sockets, moving from a per socket cache to
     a per-CPU one

   - Replace rwlocks with RCU for better fairness in ping, raw sockets
     and IP multicast router.

   - Network-side support for IO uring zero-copy send.

   - A few skb drop reason improvements, including codegen the source
     file with string mapping instead of using macro magic.

   - Rename reference tracking helpers to a more consistent netdev_*
     schema.

   - Adapt u64_stats_t type to address load/store tearing issues.

   - Refine debug helper usage to reduce the log noise caused by bots.

  BPF:

   - Improve socket map performance, avoiding skb cloning on read
     operation.

   - Add support for 64 bits enum, to match types exposed by kernel.

   - Introduce support for sleepable uprobes program.

   - Introduce support for enum textual representation in libbpf.

   - New helpers to implement synproxy with eBPF/XDP.

   - Improve loop performances, inlining indirect calls when possible.

   - Removed all the deprecated libbpf APIs.

   - Implement new eBPF-based LSM flavor.

   - Add type match support, which allow accurate queries to the eBPF
     used types.

   - A few TCP congetsion control framework usability improvements.

   - Add new infrastructure to manipulate CT entries via eBPF programs.

   - Allow for livepatch (KLP) and BPF trampolines to attach to the same
     kernel function.

  Protocols:

   - Introduce per network namespace lookup tables for unix sockets,
     increasing scalability and reducing contention.

   - Preparation work for Wi-Fi 7 Multi-Link Operation (MLO) support.

   - Add support to forciby close TIME_WAIT TCP sockets via user-space
     tools.

   - Significant performance improvement for the TLS 1.3 receive path,
     both for zero-copy and not-zero-copy.

   - Support for changing the initial MTPCP subflow priority/backup
     status

   - Introduce virtually contingus buffers for sockets over RDMA, to
     cope better with memory pressure.

   - Extend CAN ethtool support with timestamping capabilities

   - Refactor CAN build infrastructure to allow building only the needed
     features.

  Driver API:

   - Remove devlink mutex to allow parallel commands on multiple links.

   - Add support for pause stats in distributed switch.

   - Implement devlink helpers to query and flash line cards.

   - New helper for phy mode to register conversion.

  New hardware / drivers:

   - Ethernet DSA driver for the rockchip mt7531 on BPI-R2 Pro.

   - Ethernet DSA driver for the Renesas RZ/N1 A5PSW switch.

   - Ethernet DSA driver for the Microchip LAN937x switch.

   - Ethernet PHY driver for the Aquantia AQR113C EPHY.

   - CAN driver for the OBD-II ELM327 interface.

   - CAN driver for RZ/N1 SJA1000 CAN controller.

   - Bluetooth: Infineon CYW55572 Wi-Fi plus Bluetooth combo device.

  Drivers:

   - Intel Ethernet NICs:
      - i40e: add support for vlan pruning
      - i40e: add support for XDP framented packets
      - ice: improved vlan offload support
      - ice: add support for PPPoE offload

   - Mellanox Ethernet (mlx5)
      - refactor packet steering offload for performance and scalability
      - extend support for TC offload
      - refactor devlink code to clean-up the locking schema
      - support stacked vlans for bridge offloads
      - use TLS objects pool to improve connection rate

   - Netronome Ethernet NICs (nfp):
      - extend support for IPv6 fields mangling offload
      - add support for vepa mode in HW bridge
      - better support for virtio data path acceleration (VDPA)
      - enable TSO by default

   - Microsoft vNIC driver (mana)
      - add support for XDP redirect

   - Others Ethernet drivers:
      - bonding: add per-port priority support
      - microchip lan743x: extend phy support
      - Fungible funeth: support UDP segmentation offload and XDP xmit
      - Solarflare EF100: add support for virtual function representors
      - MediaTek SoC: add XDP support

   - Mellanox Ethernet/IB switch (mlxsw):
      - dropped support for unreleased H/W (XM router).
      - improved stats accuracy
      - unified bridge model coversion improving scalability (parts 1-6)
      - support for PTP in Spectrum-2 asics

   - Broadcom PHYs
      - add PTP support for BCM54210E
      - add support for the BCM53128 internal PHY

   - Marvell Ethernet switches (prestera):
      - implement support for multicast forwarding offload

   - Embedded Ethernet switches:
      - refactor OcteonTx MAC filter for better scalability
      - improve TC H/W offload for the Felix driver
      - refactor the Microchip ksz8 and ksz9477 drivers to share the
        probe code (parts 1, 2), add support for phylink mac
        configuration

   - Other WiFi:
      - Microchip wilc1000: diable WEP support and enable WPA3
      - Atheros ath10k: encapsulation offload support

  Old code removal:

   - Neterion vxge ethernet driver: this is untouched since more than 10 years"

* tag 'net-next-6.0' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next: (1890 commits)
  doc: sfp-phylink: Fix a broken reference
  wireguard: selftests: support UML
  wireguard: allowedips: don't corrupt stack when detecting overflow
  wireguard: selftests: update config fragments
  wireguard: ratelimiter: use hrtimer in selftest
  net/mlx5e: xsk: Discard unaligned XSK frames on striding RQ
  net: usb: ax88179_178a: Bind only to vendor-specific interface
  selftests: net: fix IOAM test skip return code
  net: usb: make USB_RTL8153_ECM non user configurable
  net: marvell: prestera: remove reduntant code
  octeontx2-pf: Reduce minimum mtu size to 60
  net: devlink: Fix missing mutex_unlock() call
  net/tls: Remove redundant workqueue flush before destroy
  net: txgbe: Fix an error handling path in txgbe_probe()
  net: dsa: Fix spelling mistakes and cleanup code
  Documentation: devlink: add add devlink-selftests to the table of contents
  dccp: put dccp_qpolicy_full() and dccp_qpolicy_push() in the same lock
  net: ionic: fix error check for vlan flags in ionic_set_nic_features()
  net: ice: fix error NETIF_F_HW_VLAN_CTAG_FILTER check in ice_vsi_sync_fltr()
  nfp: flower: add support for tunnel offload without key ID
  ...

1 files changed, 138 insertions, 2 deletions

diff --git a/net/ipv6/seg6_iptunnel.c b/net/ipv6/seg6_iptunnel.c
index e756ba705fd9..34db881204d2 100644
--- a/net/ipv6/seg6_iptunnel.c
+++ b/net/ipv6/seg6_iptunnel.c
@@ -36,9 +36,11 @@ static size_t seg6_lwt_headroom(struct seg6_iptunnel_encap *tuninfo)
 	case SEG6_IPTUN_MODE_INLINE:
 		break;
 	case SEG6_IPTUN_MODE_ENCAP:
+	case SEG6_IPTUN_MODE_ENCAP_RED:
 		head = sizeof(struct ipv6hdr);
 		break;
 	case SEG6_IPTUN_MODE_L2ENCAP:
+	case SEG6_IPTUN_MODE_L2ENCAP_RED:
 		return 0;
 	}
 
@@ -197,6 +199,124 @@ int seg6_do_srh_encap(struct sk_buff *skb, struct ipv6_sr_hdr *osrh, int proto)
 }
 EXPORT_SYMBOL_GPL(seg6_do_srh_encap);
 
+/* encapsulate an IPv6 packet within an outer IPv6 header with reduced SRH */
+static int seg6_do_srh_encap_red(struct sk_buff *skb,
+				 struct ipv6_sr_hdr *osrh, int proto)
+{
+	__u8 first_seg = osrh->first_segment;
+	struct dst_entry *dst = skb_dst(skb);
+	struct net *net = dev_net(dst->dev);
+	struct ipv6hdr *hdr, *inner_hdr;
+	int hdrlen = ipv6_optlen(osrh);
+	int red_tlv_offset, tlv_offset;
+	struct ipv6_sr_hdr *isrh;
+	bool skip_srh = false;
+	__be32 flowlabel;
+	int tot_len, err;
+	int red_hdrlen;
+	int tlvs_len;
+
+	if (first_seg > 0) {
+		red_hdrlen = hdrlen - sizeof(struct in6_addr);
+	} else {
+		/* NOTE: if tag/flags and/or other TLVs are introduced in the
+		 * seg6_iptunnel infrastructure, they should be considered when
+		 * deciding to skip the SRH.
+		 */
+		skip_srh = !sr_has_hmac(osrh);
+
+		red_hdrlen = skip_srh ? 0 : hdrlen;
+	}
+
+	tot_len = red_hdrlen + sizeof(struct ipv6hdr);
+
+	err = skb_cow_head(skb, tot_len + skb->mac_len);
+	if (unlikely(err))
+		return err;
+
+	inner_hdr = ipv6_hdr(skb);
+	flowlabel = seg6_make_flowlabel(net, skb, inner_hdr);
+
+	skb_push(skb, tot_len);
+	skb_reset_network_header(skb);
+	skb_mac_header_rebuild(skb);
+	hdr = ipv6_hdr(skb);
+
+	/* based on seg6_do_srh_encap() */
+	if (skb->protocol == htons(ETH_P_IPV6)) {
+		ip6_flow_hdr(hdr, ip6_tclass(ip6_flowinfo(inner_hdr)),
+			     flowlabel);
+		hdr->hop_limit = inner_hdr->hop_limit;
+	} else {
+		ip6_flow_hdr(hdr, 0, flowlabel);
+		hdr->hop_limit = ip6_dst_hoplimit(skb_dst(skb));
+
+		memset(IP6CB(skb), 0, sizeof(*IP6CB(skb)));
+		IP6CB(skb)->iif = skb->skb_iif;
+	}
+
+	/* no matter if we have to skip the SRH or not, the first segment
+	 * always comes in the pushed IPv6 header.
+	 */
+	hdr->daddr = osrh->segments[first_seg];
+
+	if (skip_srh) {
+		hdr->nexthdr = proto;
+
+		set_tun_src(net, dst->dev, &hdr->daddr, &hdr->saddr);
+		goto out;
+	}
+
+	/* we cannot skip the SRH, slow path */
+
+	hdr->nexthdr = NEXTHDR_ROUTING;
+	isrh = (void *)hdr + sizeof(struct ipv6hdr);
+
+	if (unlikely(!first_seg)) {
+		/* this is a very rare case; we have only one SID but
+		 * we cannot skip the SRH since we are carrying some
+		 * other info.
+		 */
+		memcpy(isrh, osrh, hdrlen);
+		goto srcaddr;
+	}
+
+	tlv_offset = sizeof(*osrh) + (first_seg + 1) * sizeof(struct in6_addr);
+	red_tlv_offset = tlv_offset - sizeof(struct in6_addr);
+
+	memcpy(isrh, osrh, red_tlv_offset);
+
+	tlvs_len = hdrlen - tlv_offset;
+	if (unlikely(tlvs_len > 0)) {
+		const void *s = (const void *)osrh + tlv_offset;
+		void *d = (void *)isrh + red_tlv_offset;
+
+		memcpy(d, s, tlvs_len);
+	}
+
+	--isrh->first_segment;
+	isrh->hdrlen -= 2;
+
+srcaddr:
+	isrh->nexthdr = proto;
+	set_tun_src(net, dst->dev, &hdr->daddr, &hdr->saddr);
+
+#ifdef CONFIG_IPV6_SEG6_HMAC
+	if (unlikely(!skip_srh && sr_has_hmac(isrh))) {
+		err = seg6_push_hmac(net, &hdr->saddr, isrh);
+		if (unlikely(err))
+			return err;
+	}
+#endif
+
+out:
+	hdr->payload_len = htons(skb->len - sizeof(struct ipv6hdr));
+
+	skb_postpush_rcsum(skb, hdr, tot_len);
+
+	return 0;
+}
+
 /* insert an SRH within an IPv6 packet, just after the IPv6 header */
 int seg6_do_srh_inline(struct sk_buff *skb, struct ipv6_sr_hdr *osrh)
 {
@@ -269,6 +389,7 @@ static int seg6_do_srh(struct sk_buff *skb)
 			return err;
 		break;
 	case SEG6_IPTUN_MODE_ENCAP:
+	case SEG6_IPTUN_MODE_ENCAP_RED:
 		err = iptunnel_handle_offloads(skb, SKB_GSO_IPXIP6);
 		if (err)
 			return err;
@@ -280,7 +401,11 @@ static int seg6_do_srh(struct sk_buff *skb)
 		else
 			return -EINVAL;
 
-		err = seg6_do_srh_encap(skb, tinfo->srh, proto);
+		if (tinfo->mode == SEG6_IPTUN_MODE_ENCAP)
+			err = seg6_do_srh_encap(skb, tinfo->srh, proto);
+		else
+			err = seg6_do_srh_encap_red(skb, tinfo->srh, proto);
+
 		if (err)
 			return err;
 
@@ -289,6 +414,7 @@ static int seg6_do_srh(struct sk_buff *skb)
 		skb->protocol = htons(ETH_P_IPV6);
 		break;
 	case SEG6_IPTUN_MODE_L2ENCAP:
+	case SEG6_IPTUN_MODE_L2ENCAP_RED:
 		if (!skb_mac_header_was_set(skb))
 			return -EINVAL;
 
@@ -298,7 +424,13 @@ static int seg6_do_srh(struct sk_buff *skb)
 		skb_mac_header_rebuild(skb);
 		skb_push(skb, skb->mac_len);
 
-		err = seg6_do_srh_encap(skb, tinfo->srh, IPPROTO_ETHERNET);
+		if (tinfo->mode == SEG6_IPTUN_MODE_L2ENCAP)
+			err = seg6_do_srh_encap(skb, tinfo->srh,
+						IPPROTO_ETHERNET);
+		else
+			err = seg6_do_srh_encap_red(skb, tinfo->srh,
+						    IPPROTO_ETHERNET);
+
 		if (err)
 			return err;
 
@@ -517,6 +649,10 @@ static int seg6_build_state(struct net *net, struct nlattr *nla,
 		break;
 	case SEG6_IPTUN_MODE_L2ENCAP:
 		break;
+	case SEG6_IPTUN_MODE_ENCAP_RED:
+		break;
+	case SEG6_IPTUN_MODE_L2ENCAP_RED:
+		break;
 	default:
 		return -EINVAL;
 	}