Merge tag 'net-next-6.2' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next

Pull networking updates from Paolo Abeni:
 "Core:

   - Allow live renaming when an interface is up

   - Add retpoline wrappers for tc, improving considerably the
     performances of complex queue discipline configurations

   - Add inet drop monitor support

   - A few GRO performance improvements

   - Add infrastructure for atomic dev stats, addressing long standing
     data races

   - De-duplicate common code between OVS and conntrack offloading
     infrastructure

   - A bunch of UBSAN_BOUNDS/FORTIFY_SOURCE improvements

   - Netfilter: introduce packet parser for tunneled packets

   - Replace IPVS timer-based estimators with kthreads to scale up the
     workload with the number of available CPUs

   - Add the helper support for connection-tracking OVS offload

  BPF:

   - Support for user defined BPF objects: the use case is to allocate
     own objects, build own object hierarchies and use the building
     blocks to build own data structures flexibly, for example, linked
     lists in BPF

   - Make cgroup local storage available to non-cgroup attached BPF
     programs

   - Avoid unnecessary deadlock detection and failures wrt BPF task
     storage helpers

   - A relevant bunch of BPF verifier fixes and improvements

   - Veristat tool improvements to support custom filtering, sorting,
     and replay of results

   - Add LLVM disassembler as default library for dumping JITed code

   - Lots of new BPF documentation for various BPF maps

   - Add bpf_rcu_read_{,un}lock() support for sleepable programs

   - Add RCU grace period chaining to BPF to wait for the completion of
     access from both sleepable and non-sleepable BPF programs

   - Add support storing struct task_struct objects as kptrs in maps

   - Improve helper UAPI by explicitly defining BPF_FUNC_xxx integer
     values

   - Add libbpf *_opts API-variants for bpf_*_get_fd_by_id() functions

  Protocols:

   - TCP: implement Protective Load Balancing across switch links

   - TCP: allow dynamically disabling TCP-MD5 static key, reverting back
     to fast[er]-path

   - UDP: Introduce optional per-netns hash lookup table

   - IPv6: simplify and cleanup sockets disposal

   - Netlink: support different type policies for each generic netlink
     operation

   - MPTCP: add MSG_FASTOPEN and FastOpen listener side support

   - MPTCP: add netlink notification support for listener sockets events

   - SCTP: add VRF support, allowing sctp sockets binding to VRF devices

   - Add bridging MAC Authentication Bypass (MAB) support

   - Extensions for Ethernet VPN bridging implementation to better
     support multicast scenarios

   - More work for Wi-Fi 7 support, comprising conversion of all the
     existing drivers to internal TX queue usage

   - IPSec: introduce a new offload type (packet offload) allowing
     complete header processing and crypto offloading

   - IPSec: extended ack support for more descriptive XFRM error
     reporting

   - RXRPC: increase SACK table size and move processing into a
     per-local endpoint kernel thread, reducing considerably the
     required locking

   - IEEE 802154: synchronous send frame and extended filtering support,
     initial support for scanning available 15.4 networks

   - Tun: bump the link speed from 10Mbps to 10Gbps

   - Tun/VirtioNet: implement UDP segmentation offload support

  Driver API:

   - PHY/SFP: improve power level switching between standard level 1 and
     the higher power levels

   - New API for netdev <-> devlink_port linkage

   - PTP: convert existing drivers to new frequency adjustment
     implementation

   - DSA: add support for rx offloading

   - Autoload DSA tagging driver when dynamically changing protocol

   - Add new PCP and APPTRUST attributes to Data Center Bridging

   - Add configuration support for 800Gbps link speed

   - Add devlink port function attribute to enable/disable RoCE and
     migratable

   - Extend devlink-rate to support strict prioriry and weighted fair
     queuing

   - Add devlink support to directly reading from region memory

   - New device tree helper to fetch MAC address from nvmem

   - New big TCP helper to simplify temporary header stripping

  New hardware / drivers:

   - Ethernet:
      - Marvel Octeon CNF95N and CN10KB Ethernet Switches
      - Marvel Prestera AC5X Ethernet Switch
      - WangXun 10 Gigabit NIC
      - Motorcomm yt8521 Gigabit Ethernet
      - Microchip ksz9563 Gigabit Ethernet Switch
      - Microsoft Azure Network Adapter
      - Linux Automation 10Base-T1L adapter

   - PHY:
      - Aquantia AQR112 and AQR412
      - Motorcomm YT8531S

   - PTP:
      - Orolia ART-CARD

   - WiFi:
      - MediaTek Wi-Fi 7 (802.11be) devices
      - RealTek rtw8821cu, rtw8822bu, rtw8822cu and rtw8723du USB
        devices

   - Bluetooth:
      - Broadcom BCM4377/4378/4387 Bluetooth chipsets
      - Realtek RTL8852BE and RTL8723DS
      - Cypress.CYW4373A0 WiFi + Bluetooth combo device

  Drivers:

   - CAN:
      - gs_usb: bus error reporting support
      - kvaser_usb: listen only and bus error reporting support

   - Ethernet NICs:
      - Intel (100G):
         - extend action skbedit to RX queue mapping
         - implement devlink-rate support
         - support direct read from memory
      - nVidia/Mellanox (mlx5):
         - SW steering improvements, increasing rules update rate
         - Support for enhanced events compression
         - extend H/W offload packet manipulation capabilities
         - implement IPSec packet offload mode
      - nVidia/Mellanox (mlx4):
         - better big TCP support
      - Netronome Ethernet NICs (nfp):
         - IPsec offload support
         - add support for multicast filter
      - Broadcom:
         - RSS and PTP support improvements
      - AMD/SolarFlare:
         - netlink extened ack improvements
         - add basic flower matches to offload, and related stats
      - Virtual NICs:
         - ibmvnic: introduce affinity hint support
      - small / embedded:
         - FreeScale fec: add initial XDP support
         - Marvel mv643xx_eth: support MII/GMII/RGMII modes for Kirkwood
         - TI am65-cpsw: add suspend/resume support
         - Mediatek MT7986: add RX wireless wthernet dispatch support
         - Realtek 8169: enable GRO software interrupt coalescing per
           default

   - Ethernet high-speed switches:
      - Microchip (sparx5):
         - add support for Sparx5 TC/flower H/W offload via VCAP
      - Mellanox mlxsw:
         - add 802.1X and MAC Authentication Bypass offload support
         - add ip6gre support

   - Embedded Ethernet switches:
      - Mediatek (mtk_eth_soc):
         - improve PCS implementation, add DSA untag support
         - enable flow offload support
      - Renesas:
         - add rswitch R-Car Gen4 gPTP support
      - Microchip (lan966x):
         - add full XDP support
         - add TC H/W offload via VCAP
         - enable PTP on bridge interfaces
      - Microchip (ksz8):
         - add MTU support for KSZ8 series

   - Qualcomm 802.11ax WiFi (ath11k):
      - support configuring channel dwell time during scan

   - MediaTek WiFi (mt76):
      - enable Wireless Ethernet Dispatch (WED) offload support
      - add ack signal support
      - enable coredump support
      - remain_on_channel support

   - Intel WiFi (iwlwifi):
      - enable Wi-Fi 7 Extremely High Throughput (EHT) PHY capabilities
      - 320 MHz channels support

   - RealTek WiFi (rtw89):
      - new dynamic header firmware format support
      - wake-over-WLAN support"

* tag 'net-next-6.2' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next: (2002 commits)
  ipvs: fix type warning in do_div() on 32 bit
  net: lan966x: Remove a useless test in lan966x_ptp_add_trap()
  net: ipa: add IPA v4.7 support
  dt-bindings: net: qcom,ipa: Add SM6350 compatible
  bnxt: Use generic HBH removal helper in tx path
  IPv6/GRO: generic helper to remove temporary HBH/jumbo header in driver
  selftests: forwarding: Add bridge MDB test
  selftests: forwarding: Rename bridge_mdb test
  bridge: mcast: Support replacement of MDB port group entries
  bridge: mcast: Allow user space to specify MDB entry routing protocol
  bridge: mcast: Allow user space to add (*, G) with a source list and filter mode
  bridge: mcast: Add support for (*, G) with a source list and filter mode
  bridge: mcast: Avoid arming group timer when (S, G) corresponds to a source
  bridge: mcast: Add a flag for user installed source entries
  bridge: mcast: Expose __br_multicast_del_group_src()
  bridge: mcast: Expose br_multicast_new_group_src()
  bridge: mcast: Add a centralized error path
  bridge: mcast: Place netlink policy before validation functions
  bridge: mcast: Split (*, G) and (S, G) addition into different functions
  bridge: mcast: Do not derive entry type from its filter mode
  ...

1 files changed, 138 insertions, 3 deletions

diff --git a/net/netfilter/nft_payload.c b/net/netfilter/nft_payload.c
index 4edd899aeb9b..17b418a5a593 100644
--- a/net/netfilter/nft_payload.c
+++ b/net/netfilter/nft_payload.c
@@ -19,6 +19,7 @@
 /* For layer 4 checksum field offset. */
 #include <linux/tcp.h>
 #include <linux/udp.h>
+#include <net/gre.h>
 #include <linux/icmpv6.h>
 #include <linux/ip.h>
 #include <linux/ipv6.h>
@@ -100,6 +101,41 @@ static int __nft_payload_inner_offset(struct nft_pktinfo *pkt)
 		pkt->inneroff = thoff + __tcp_hdrlen(th);
 		}
 		break;
+	case IPPROTO_GRE: {
+		u32 offset = sizeof(struct gre_base_hdr);
+		struct gre_base_hdr *gre, _gre;
+		__be16 version;
+
+		gre = skb_header_pointer(pkt->skb, thoff, sizeof(_gre), &_gre);
+		if (!gre)
+			return -1;
+
+		version = gre->flags & GRE_VERSION;
+		switch (version) {
+		case GRE_VERSION_0:
+			if (gre->flags & GRE_ROUTING)
+				return -1;
+
+			if (gre->flags & GRE_CSUM) {
+				offset += sizeof_field(struct gre_full_hdr, csum) +
+					  sizeof_field(struct gre_full_hdr, reserved1);
+			}
+			if (gre->flags & GRE_KEY)
+				offset += sizeof_field(struct gre_full_hdr, key);
+
+			if (gre->flags & GRE_SEQ)
+				offset += sizeof_field(struct gre_full_hdr, seq);
+			break;
+		default:
+			return -1;
+		}
+
+		pkt->inneroff = thoff + offset;
+		}
+		break;
+	case IPPROTO_IPIP:
+		pkt->inneroff = thoff;
+		break;
 	default:
 		return -1;
 	}
@@ -109,7 +145,7 @@ static int __nft_payload_inner_offset(struct nft_pktinfo *pkt)
 	return 0;
 }
 
-static int nft_payload_inner_offset(const struct nft_pktinfo *pkt)
+int nft_payload_inner_offset(const struct nft_pktinfo *pkt)
 {
 	if (!(pkt->flags & NFT_PKTINFO_INNER) &&
 	    __nft_payload_inner_offset((struct nft_pktinfo *)pkt) < 0)
@@ -195,7 +231,8 @@ static int nft_payload_init(const struct nft_ctx *ctx,
 					priv->len);
 }
 
-static int nft_payload_dump(struct sk_buff *skb, const struct nft_expr *expr)
+static int nft_payload_dump(struct sk_buff *skb,
+			    const struct nft_expr *expr, bool reset)
 {
 	const struct nft_payload *priv = nft_expr_priv(expr);
 
@@ -552,6 +589,92 @@ const struct nft_expr_ops nft_payload_fast_ops = {
 	.offload	= nft_payload_offload,
 };
 
+void nft_payload_inner_eval(const struct nft_expr *expr, struct nft_regs *regs,
+			    const struct nft_pktinfo *pkt,
+			    struct nft_inner_tun_ctx *tun_ctx)
+{
+	const struct nft_payload *priv = nft_expr_priv(expr);
+	const struct sk_buff *skb = pkt->skb;
+	u32 *dest = &regs->data[priv->dreg];
+	int offset;
+
+	if (priv->len % NFT_REG32_SIZE)
+		dest[priv->len / NFT_REG32_SIZE] = 0;
+
+	switch (priv->base) {
+	case NFT_PAYLOAD_TUN_HEADER:
+		if (!(tun_ctx->flags & NFT_PAYLOAD_CTX_INNER_TUN))
+			goto err;
+
+		offset = tun_ctx->inner_tunoff;
+		break;
+	case NFT_PAYLOAD_LL_HEADER:
+		if (!(tun_ctx->flags & NFT_PAYLOAD_CTX_INNER_LL))
+			goto err;
+
+		offset = tun_ctx->inner_lloff;
+		break;
+	case NFT_PAYLOAD_NETWORK_HEADER:
+		if (!(tun_ctx->flags & NFT_PAYLOAD_CTX_INNER_NH))
+			goto err;
+
+		offset = tun_ctx->inner_nhoff;
+		break;
+	case NFT_PAYLOAD_TRANSPORT_HEADER:
+		if (!(tun_ctx->flags & NFT_PAYLOAD_CTX_INNER_TH))
+			goto err;
+
+		offset = tun_ctx->inner_thoff;
+		break;
+	default:
+		WARN_ON_ONCE(1);
+		goto err;
+	}
+	offset += priv->offset;
+
+	if (skb_copy_bits(skb, offset, dest, priv->len) < 0)
+		goto err;
+
+	return;
+err:
+	regs->verdict.code = NFT_BREAK;
+}
+
+static int nft_payload_inner_init(const struct nft_ctx *ctx,
+				  const struct nft_expr *expr,
+				  const struct nlattr * const tb[])
+{
+	struct nft_payload *priv = nft_expr_priv(expr);
+	u32 base;
+
+	base   = ntohl(nla_get_be32(tb[NFTA_PAYLOAD_BASE]));
+	switch (base) {
+	case NFT_PAYLOAD_TUN_HEADER:
+	case NFT_PAYLOAD_LL_HEADER:
+	case NFT_PAYLOAD_NETWORK_HEADER:
+	case NFT_PAYLOAD_TRANSPORT_HEADER:
+		break;
+	default:
+		return -EOPNOTSUPP;
+	}
+
+	priv->base   = base;
+	priv->offset = ntohl(nla_get_be32(tb[NFTA_PAYLOAD_OFFSET]));
+	priv->len    = ntohl(nla_get_be32(tb[NFTA_PAYLOAD_LEN]));
+
+	return nft_parse_register_store(ctx, tb[NFTA_PAYLOAD_DREG],
+					&priv->dreg, NULL, NFT_DATA_VALUE,
+					priv->len);
+}
+
+static const struct nft_expr_ops nft_payload_inner_ops = {
+	.type		= &nft_payload_type,
+	.size		= NFT_EXPR_SIZE(sizeof(struct nft_payload)),
+	.init		= nft_payload_inner_init,
+	.dump		= nft_payload_dump,
+	/* direct call to nft_payload_inner_eval(). */
+};
+
 static inline void nft_csum_replace(__sum16 *sum, __wsum fsum, __wsum tsum)
 {
 	*sum = csum_fold(csum_add(csum_sub(~csum_unfold(*sum), fsum), tsum));
@@ -665,6 +788,16 @@ static int nft_payload_csum_inet(struct sk_buff *skb, const u32 *src,
 	return 0;
 }
 
+struct nft_payload_set {
+	enum nft_payload_bases	base:8;
+	u8			offset;
+	u8			len;
+	u8			sreg;
+	u8			csum_type;
+	u8			csum_offset;
+	u8			csum_flags;
+};
+
 static void nft_payload_set_eval(const struct nft_expr *expr,
 				 struct nft_regs *regs,
 				 const struct nft_pktinfo *pkt)
@@ -787,7 +920,8 @@ static int nft_payload_set_init(const struct nft_ctx *ctx,
 				       priv->len);
 }
 
-static int nft_payload_set_dump(struct sk_buff *skb, const struct nft_expr *expr)
+static int nft_payload_set_dump(struct sk_buff *skb,
+				const struct nft_expr *expr, bool reset)
 {
 	const struct nft_payload_set *priv = nft_expr_priv(expr);
 
@@ -885,6 +1019,7 @@ nft_payload_select_ops(const struct nft_ctx *ctx,
 struct nft_expr_type nft_payload_type __read_mostly = {
 	.name		= "payload",
 	.select_ops	= nft_payload_select_ops,
+	.inner_ops	= &nft_payload_inner_ops,
 	.policy		= nft_payload_policy,
 	.maxattr	= NFTA_PAYLOAD_MAX,
 	.owner		= THIS_MODULE,