Merge tag 'net-next-5.14' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next

Pull networking updates from Jakub Kicinski:
 "Core:

   - BPF:
      - add syscall program type and libbpf support for generating
        instructions and bindings for in-kernel BPF loaders (BPF loaders
        for BPF), this is a stepping stone for signed BPF programs
      - infrastructure to migrate TCP child sockets from one listener to
        another in the same reuseport group/map to improve flexibility
        of service hand-off/restart
      - add broadcast support to XDP redirect

   - allow bypass of the lockless qdisc to improving performance (for
     pktgen: +23% with one thread, +44% with 2 threads)

   - add a simpler version of "DO_ONCE()" which does not require jump
     labels, intended for slow-path usage

   - virtio/vsock: introduce SOCK_SEQPACKET support

   - add getsocketopt to retrieve netns cookie

   - ip: treat lowest address of a IPv4 subnet as ordinary unicast
     address allowing reclaiming of precious IPv4 addresses

   - ipv6: use prandom_u32() for ID generation

   - ip: add support for more flexible field selection for hashing
     across multi-path routes (w/ offload to mlxsw)

   - icmp: add support for extended RFC 8335 PROBE (ping)

   - seg6: add support for SRv6 End.DT46 behavior

   - mptcp:
      - DSS checksum support (RFC 8684) to detect middlebox meddling
      - support Connection-time 'C' flag
      - time stamping support

   - sctp: packetization Layer Path MTU Discovery (RFC 8899)

   - xfrm: speed up state addition with seq set

   - WiFi:
      - hidden AP discovery on 6 GHz and other HE 6 GHz improvements
      - aggregation handling improvements for some drivers
      - minstrel improvements for no-ack frames
      - deferred rate control for TXQs to improve reaction times
      - switch from round robin to virtual time-based airtime scheduler

   - add trace points:
      - tcp checksum errors
      - openvswitch - action execution, upcalls
      - socket errors via sk_error_report

  Device APIs:

   - devlink: add rate API for hierarchical control of max egress rate
     of virtual devices (VFs, SFs etc.)

   - don't require RCU read lock to be held around BPF hooks in NAPI
     context

   - page_pool: generic buffer recycling

  New hardware/drivers:

   - mobile:
      - iosm: PCIe Driver for Intel M.2 Modem
      - support for Qualcomm MSM8998 (ipa)

   - WiFi: Qualcomm QCN9074 and WCN6855 PCI devices

   - sparx5: Microchip SparX-5 family of Enterprise Ethernet switches

   - Mellanox BlueField Gigabit Ethernet (control NIC of the DPU)

   - NXP SJA1110 Automotive Ethernet 10-port switch

   - Qualcomm QCA8327 switch support (qca8k)

   - Mikrotik 10/25G NIC (atl1c)

  Driver changes:

   - ACPI support for some MDIO, MAC and PHY devices from Marvell and
     NXP (our first foray into MAC/PHY description via ACPI)

   - HW timestamping (PTP) support: bnxt_en, ice, sja1105, hns3, tja11xx

   - Mellanox/Nvidia NIC (mlx5)
      - NIC VF offload of L2 bridging
      - support IRQ distribution to Sub-functions

   - Marvell (prestera):
      - add flower and match all
      - devlink trap
      - link aggregation

   - Netronome (nfp): connection tracking offload

   - Intel 1GE (igc): add AF_XDP support

   - Marvell DPU (octeontx2): ingress ratelimit offload

   - Google vNIC (gve): new ring/descriptor format support

   - Qualcomm mobile (rmnet & ipa): inline checksum offload support

   - MediaTek WiFi (mt76)
      - mt7915 MSI support
      - mt7915 Tx status reporting
      - mt7915 thermal sensors support
      - mt7921 decapsulation offload
      - mt7921 enable runtime pm and deep sleep

   - Realtek WiFi (rtw88)
      - beacon filter support
      - Tx antenna path diversity support
      - firmware crash information via devcoredump

   - Qualcomm WiFi (wcn36xx)
      - Wake-on-WLAN support with magic packets and GTK rekeying

   - Micrel PHY (ksz886x/ksz8081): add cable test support"

* tag 'net-next-5.14' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next: (2168 commits)
  tcp: change ICSK_CA_PRIV_SIZE definition
  tcp_yeah: check struct yeah size at compile time
  gve: DQO: Fix off by one in gve_rx_dqo()
  stmmac: intel: set PCI_D3hot in suspend
  stmmac: intel: Enable PHY WOL option in EHL
  net: stmmac: option to enable PHY WOL with PMT enabled
  net: say "local" instead of "static" addresses in ndo_dflt_fdb_{add,del}
  net: use netdev_info in ndo_dflt_fdb_{add,del}
  ptp: Set lookup cookie when creating a PTP PPS source.
  net: sock: add trace for socket errors
  net: sock: introduce sk_error_report
  net: dsa: replay the local bridge FDB entries pointing to the bridge dev too
  net: dsa: ensure during dsa_fdb_offload_notify that dev_hold and dev_put are on the same dev
  net: dsa: include fdb entries pointing to bridge in the host fdb list
  net: dsa: include bridge addresses which are local in the host fdb list
  net: dsa: sync static FDB entries on foreign interfaces to hardware
  net: dsa: install the host MDB and FDB entries in the master's RX filter
  net: dsa: reference count the FDB addresses at the cross-chip notifier level
  net: dsa: introduce a separate cross-chip notifier type for host FDBs
  net: dsa: reference count the MDB entries at the cross-chip notifier level
  ...

1 files changed, 63 insertions, 4 deletions

diff --git a/net/netfilter/nft_exthdr.c b/net/netfilter/nft_exthdr.c
index f64f0017e9a5..af4ee874a067 100644
--- a/net/netfilter/nft_exthdr.c
+++ b/net/netfilter/nft_exthdr.c
@@ -10,8 +10,10 @@
 #include <linux/netlink.h>
 #include <linux/netfilter.h>
 #include <linux/netfilter/nf_tables.h>
+#include <linux/sctp.h>
 #include <net/netfilter/nf_tables_core.h>
 #include <net/netfilter/nf_tables.h>
+#include <net/sctp/sctp.h>
 #include <net/tcp.h>
 
 struct nft_exthdr {
@@ -42,6 +44,9 @@ static void nft_exthdr_ipv6_eval(const struct nft_expr *expr,
 	unsigned int offset = 0;
 	int err;
 
+	if (pkt->skb->protocol != htons(ETH_P_IPV6))
+		goto err;
+
 	err = ipv6_find_hdr(pkt->skb, &offset, priv->type, NULL, NULL);
 	if (priv->flags & NFT_EXTHDR_F_PRESENT) {
 		nft_reg_store8(dest, err >= 0);
@@ -162,10 +167,10 @@ nft_tcp_header_pointer(const struct nft_pktinfo *pkt,
 {
 	struct tcphdr *tcph;
 
-	if (!pkt->tprot_set || pkt->tprot != IPPROTO_TCP)
+	if (pkt->tprot != IPPROTO_TCP)
 		return NULL;
 
-	tcph = skb_header_pointer(pkt->skb, pkt->xt.thoff, sizeof(*tcph), buffer);
+	tcph = skb_header_pointer(pkt->skb, nft_thoff(pkt), sizeof(*tcph), buffer);
 	if (!tcph)
 		return NULL;
 
@@ -173,7 +178,7 @@ nft_tcp_header_pointer(const struct nft_pktinfo *pkt,
 	if (*tcphdr_len < sizeof(*tcph) || *tcphdr_len > len)
 		return NULL;
 
-	return skb_header_pointer(pkt->skb, pkt->xt.thoff, *tcphdr_len, buffer);
+	return skb_header_pointer(pkt->skb, nft_thoff(pkt), *tcphdr_len, buffer);
 }
 
 static void nft_exthdr_tcp_eval(const struct nft_expr *expr,
@@ -249,7 +254,7 @@ static void nft_exthdr_tcp_set_eval(const struct nft_expr *expr,
 			return;
 
 		if (skb_ensure_writable(pkt->skb,
-					pkt->xt.thoff + i + priv->len))
+					nft_thoff(pkt) + i + priv->len))
 			return;
 
 		tcph = nft_tcp_header_pointer(pkt, sizeof(buff), buff,
@@ -300,6 +305,48 @@ static void nft_exthdr_tcp_set_eval(const struct nft_expr *expr,
 	}
 }
 
+static void nft_exthdr_sctp_eval(const struct nft_expr *expr,
+				 struct nft_regs *regs,
+				 const struct nft_pktinfo *pkt)
+{
+	unsigned int offset = nft_thoff(pkt) + sizeof(struct sctphdr);
+	struct nft_exthdr *priv = nft_expr_priv(expr);
+	u32 *dest = &regs->data[priv->dreg];
+	const struct sctp_chunkhdr *sch;
+	struct sctp_chunkhdr _sch;
+
+	if (pkt->tprot != IPPROTO_SCTP)
+		goto err;
+
+	do {
+		sch = skb_header_pointer(pkt->skb, offset, sizeof(_sch), &_sch);
+		if (!sch || !sch->length)
+			break;
+
+		if (sch->type == priv->type) {
+			if (priv->flags & NFT_EXTHDR_F_PRESENT) {
+				nft_reg_store8(dest, true);
+				return;
+			}
+			if (priv->offset + priv->len > ntohs(sch->length) ||
+			    offset + ntohs(sch->length) > pkt->skb->len)
+				break;
+
+			dest[priv->len / NFT_REG32_SIZE] = 0;
+			if (skb_copy_bits(pkt->skb, offset + priv->offset,
+					  dest, priv->len) < 0)
+				break;
+			return;
+		}
+		offset += SCTP_PAD4(ntohs(sch->length));
+	} while (offset < pkt->skb->len);
+err:
+	if (priv->flags & NFT_EXTHDR_F_PRESENT)
+		nft_reg_store8(dest, false);
+	else
+		regs->verdict.code = NFT_BREAK;
+}
+
 static const struct nla_policy nft_exthdr_policy[NFTA_EXTHDR_MAX + 1] = {
 	[NFTA_EXTHDR_DREG]		= { .type = NLA_U32 },
 	[NFTA_EXTHDR_TYPE]		= { .type = NLA_U8 },
@@ -499,6 +546,14 @@ static const struct nft_expr_ops nft_exthdr_tcp_set_ops = {
 	.dump		= nft_exthdr_dump_set,
 };
 
+static const struct nft_expr_ops nft_exthdr_sctp_ops = {
+	.type		= &nft_exthdr_type,
+	.size		= NFT_EXPR_SIZE(sizeof(struct nft_exthdr)),
+	.eval		= nft_exthdr_sctp_eval,
+	.init		= nft_exthdr_init,
+	.dump		= nft_exthdr_dump,
+};
+
 static const struct nft_expr_ops *
 nft_exthdr_select_ops(const struct nft_ctx *ctx,
 		      const struct nlattr * const tb[])
@@ -529,6 +584,10 @@ nft_exthdr_select_ops(const struct nft_ctx *ctx,
 				return &nft_exthdr_ipv4_ops;
 		}
 		break;
+	case NFT_EXTHDR_OP_SCTP:
+		if (tb[NFTA_EXTHDR_DREG])
+			return &nft_exthdr_sctp_ops;
+		break;
 	}
 
 	return ERR_PTR(-EOPNOTSUPP);