Merge tag 'net-next-6.3' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-nextgrafted

Pull networking updates from Jakub Kicinski:
 "Core:

   - Add dedicated kmem_cache for typical/small skb->head, avoid having
     to access struct page at kfree time, and improve memory use.

   - Introduce sysctl to set default RPS configuration for new netdevs.

   - Define Netlink protocol specification format which can be used to
     describe messages used by each family and auto-generate parsers.
     Add tools for generating kernel data structures and uAPI headers.

   - Expose all net/core sysctls inside netns.

   - Remove 4s sleep in netpoll if carrier is instantly detected on
     boot.

   - Add configurable limit of MDB entries per port, and port-vlan.

   - Continue populating drop reasons throughout the stack.

   - Retire a handful of legacy Qdiscs and classifiers.

  Protocols:

   - Support IPv4 big TCP (TSO frames larger than 64kB).

   - Add IP_LOCAL_PORT_RANGE socket option, to control local port range
     on socket by socket basis.

   - Track and report in procfs number of MPTCP sockets used.

   - Support mixing IPv4 and IPv6 flows in the in-kernel MPTCP path
     manager.

   - IPv6: don't check net.ipv6.route.max_size and rely on garbage
     collection to free memory (similarly to IPv4).

   - Support Penultimate Segment Pop (PSP) flavor in SRv6 (RFC8986).

   - ICMP: add per-rate limit counters.

   - Add support for user scanning requests in ieee802154.

   - Remove static WEP support.

   - Support minimal Wi-Fi 7 Extremely High Throughput (EHT) rate
     reporting.

   - WiFi 7 EHT channel puncturing support (client & AP).

  BPF:

   - Add a rbtree data structure following the "next-gen data structure"
     precedent set by recently added linked list, that is, by using
     kfunc + kptr instead of adding a new BPF map type.

   - Expose XDP hints via kfuncs with initial support for RX hash and
     timestamp metadata.

   - Add BPF_F_NO_TUNNEL_KEY extension to bpf_skb_set_tunnel_key to
     better support decap on GRE tunnel devices not operating in collect
     metadata.

   - Improve x86 JIT's codegen for PROBE_MEM runtime error checks.

   - Remove the need for trace_printk_lock for bpf_trace_printk and
     bpf_trace_vprintk helpers.

   - Extend libbpf's bpf_tracing.h support for tracing arguments of
     kprobes/uprobes and syscall as a special case.

   - Significantly reduce the search time for module symbols by
     livepatch and BPF.

   - Enable cpumasks to be used as kptrs, which is useful for tracing
     programs tracking which tasks end up running on which CPUs in
     different time intervals.

   - Add support for BPF trampoline on s390x and riscv64.

   - Add capability to export the XDP features supported by the NIC.

   - Add __bpf_kfunc tag for marking kernel functions as kfuncs.

   - Add cgroup.memory=nobpf kernel parameter option to disable BPF
     memory accounting for container environments.

  Netfilter:

   - Remove the CLUSTERIP target. It has been marked as obsolete for
     years, and we still have WARN splats wrt races of the out-of-band
     /proc interface installed by this target.

   - Add 'destroy' commands to nf_tables. They are identical to the
     existing 'delete' commands, but do not return an error if the
     referenced object (set, chain, rule...) did not exist.

  Driver API:

   - Improve cpumask_local_spread() locality to help NICs set the right
     IRQ affinity on AMD platforms.

   - Separate C22 and C45 MDIO bus transactions more clearly.

   - Introduce new DCB table to control DSCP rewrite on egress.

   - Support configuration of Physical Layer Collision Avoidance (PLCA)
     Reconciliation Sublayer (RS) (802.3cg-2019). Modern version of
     shared medium Ethernet.

   - Support for MAC Merge layer (IEEE 802.3-2018 clause 99). Allowing
     preemption of low priority frames by high priority frames.

   - Add support for controlling MACSec offload using netlink SET.

   - Rework devlink instance refcounts to allow registration and
     de-registration under the instance lock. Split the code into
     multiple files, drop some of the unnecessarily granular locks and
     factor out common parts of netlink operation handling.

   - Add TX frame aggregation parameters (for USB drivers).

   - Add a new attr TCA_EXT_WARN_MSG to report TC (offload) warning
     messages with notifications for debug.

   - Allow offloading of UDP NEW connections via act_ct.

   - Add support for per action HW stats in TC.

   - Support hardware miss to TC action (continue processing in SW from
     a specific point in the action chain).

   - Warn if old Wireless Extension user space interface is used with
     modern cfg80211/mac80211 drivers. Do not support Wireless
     Extensions for Wi-Fi 7 devices at all. Everyone should switch to
     using nl80211 interface instead.

   - Improve the CAN bit timing configuration. Use extack to return
     error messages directly to user space, update the SJW handling,
     including the definition of a new default value that will benefit
     CAN-FD controllers, by increasing their oscillator tolerance.

  New hardware / drivers:

   - Ethernet:
      - nVidia BlueField-3 support (control traffic driver)
      - Ethernet support for imx93 SoCs
      - Motorcomm yt8531 gigabit Ethernet PHY
      - onsemi NCN26000 10BASE-T1S PHY (with support for PLCA)
      - Microchip LAN8841 PHY (incl. cable diagnostics and PTP)
      - Amlogic gxl MDIO mux

   - WiFi:
      - RealTek RTL8188EU (rtl8xxxu)
      - Qualcomm Wi-Fi 7 devices (ath12k)

   - CAN:
      - Renesas R-Car V4H

  Drivers:

   - Bluetooth:
      - Set Per Platform Antenna Gain (PPAG) for Intel controllers.

   - Ethernet NICs:
      - Intel (1G, igc):
         - support TSN / Qbv / packet scheduling features of i226 model
      - Intel (100G, ice):
         - use GNSS subsystem instead of TTY
         - multi-buffer XDP support
         - extend support for GPIO pins to E823 devices
      - nVidia/Mellanox:
         - update the shared buffer configuration on PFC commands
         - implement PTP adjphase function for HW offset control
         - TC support for Geneve and GRE with VF tunnel offload
         - more efficient crypto key management method
         - multi-port eswitch support
      - Netronome/Corigine:
         - add DCB IEEE support
         - support IPsec offloading for NFP3800
      - Freescale/NXP (enetc):
         - support XDP_REDIRECT for XDP non-linear buffers
         - improve reconfig, avoid link flap and waiting for idle
         - support MAC Merge layer
      - Other NICs:
         - sfc/ef100: add basic devlink support for ef100
         - ionic: rx_push mode operation (writing descriptors via MMIO)
         - bnxt: use the auxiliary bus abstraction for RDMA
         - r8169: disable ASPM and reset bus in case of tx timeout
         - cpsw: support QSGMII mode for J721e CPSW9G
         - cpts: support pulse-per-second output
         - ngbe: add an mdio bus driver
         - usbnet: optimize usbnet_bh() by avoiding unnecessary queuing
         - r8152: handle devices with FW with NCM support
         - amd-xgbe: support 10Mbps, 2.5GbE speeds and rx-adaptation
         - virtio-net: support multi buffer XDP
         - virtio/vsock: replace virtio_vsock_pkt with sk_buff
         - tsnep: XDP support

   - Ethernet high-speed switches:
      - nVidia/Mellanox (mlxsw):
         - add support for latency TLV (in FW control messages)
      - Microchip (sparx5):
         - separate explicit and implicit traffic forwarding rules, make
           the implicit rules always active
         - add support for egress DSCP rewrite
         - IS0 VCAP support (Ingress Classification)
         - IS2 VCAP filters (protos, L3 addrs, L4 ports, flags, ToS
           etc.)
         - ES2 VCAP support (Egress Access Control)
         - support for Per-Stream Filtering and Policing (802.1Q,
           8.6.5.1)

   - Ethernet embedded switches:
      - Marvell (mv88e6xxx):
         - add MAB (port auth) offload support
         - enable PTP receive for mv88e6390
      - NXP (ocelot):
         - support MAC Merge layer
         - support for the the vsc7512 internal copper phys
      - Microchip:
         - lan9303: convert to PHYLINK
         - lan966x: support TC flower filter statistics
         - lan937x: PTP support for KSZ9563/KSZ8563 and LAN937x
         - lan937x: support Credit Based Shaper configuration
         - ksz9477: support Energy Efficient Ethernet
      - other:
         - qca8k: convert to regmap read/write API, use bulk operations
         - rswitch: Improve TX timestamp accuracy

   - Intel WiFi (iwlwifi):
      - EHT (Wi-Fi 7) rate reporting
      - STEP equalizer support: transfer some STEP (connection to radio
        on platforms with integrated wifi) related parameters from the
        BIOS to the firmware.

   - Qualcomm 802.11ax WiFi (ath11k):
      - IPQ5018 support
      - Fine Timing Measurement (FTM) responder role support
      - channel 177 support

   - MediaTek WiFi (mt76):
      - per-PHY LED support
      - mt7996: EHT (Wi-Fi 7) support
      - Wireless Ethernet Dispatch (WED) reset support
      - switch to using page pool allocator

   - RealTek WiFi (rtw89):
      - support new version of Bluetooth co-existance

   - Mobile:
      - rmnet: support TX aggregation"

* tag 'net-next-6.3' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next: (1872 commits)
  page_pool: add a comment explaining the fragment counter usage
  net: ethtool: fix __ethtool_dev_mm_supported() implementation
  ethtool: pse-pd: Fix double word in comments
  xsk: add linux/vmalloc.h to xsk.c
  sefltests: netdevsim: wait for devlink instance after netns removal
  selftest: fib_tests: Always cleanup before exit
  net/mlx5e: Align IPsec ASO result memory to be as required by hardware
  net/mlx5e: TC, Set CT miss to the specific ct action instance
  net/mlx5e: Rename CHAIN_TO_REG to MAPPED_OBJ_TO_REG
  net/mlx5: Refactor tc miss handling to a single function
  net/mlx5: Kconfig: Make tc offload depend on tc skb extension
  net/sched: flower: Support hardware miss to tc action
  net/sched: flower: Move filter handle initialization earlier
  net/sched: cls_api: Support hardware miss to tc action
  net/sched: Rename user cookie and act cookie
  sfc: fix builds without CONFIG_RTC_LIB
  sfc: clean up some inconsistent indentings
  net/mlx4_en: Introduce flexible array to silence overflow warning
  net: lan966x: Fix possible deadlock inside PTP
  net/ulp: Remove redundant ->clone() test in inet_clone_ulp().
  ...

1 files changed, 641 insertions, 0 deletions

diff --git a/net/ipv4/ip_options.c b/net/ipv4/ip_options.c
new file mode 100644
index 000000000..a9e22a098
--- /dev/null
+++ b/net/ipv4/ip_options.c
@@ -0,0 +1,641 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * INET		An implementation of the TCP/IP protocol suite for the LINUX
+ *		operating system.  INET is implemented using the  BSD Socket
+ *		interface as the means of communication with the user level.
+ *
+ *		The options processing module for ip.c
+ *
+ * Authors:	A.N.Kuznetsov
+ *
+ */
+
+#define pr_fmt(fmt) "IPv4: " fmt
+
+#include <linux/capability.h>
+#include <linux/module.h>
+#include <linux/slab.h>
+#include <linux/types.h>
+#include <linux/uaccess.h>
+#include <asm/unaligned.h>
+#include <linux/skbuff.h>
+#include <linux/ip.h>
+#include <linux/icmp.h>
+#include <linux/netdevice.h>
+#include <linux/rtnetlink.h>
+#include <net/sock.h>
+#include <net/ip.h>
+#include <net/icmp.h>
+#include <net/route.h>
+#include <net/cipso_ipv4.h>
+#include <net/ip_fib.h>
+
+/*
+ * Write options to IP header, record destination address to
+ * source route option, address of outgoing interface
+ * (we should already know it, so that this  function is allowed be
+ * called only after routing decision) and timestamp,
+ * if we originate this datagram.
+ *
+ * daddr is real destination address, next hop is recorded in IP header.
+ * saddr is address of outgoing interface.
+ */
+
+void ip_options_build(struct sk_buff *skb, struct ip_options *opt,
+		      __be32 daddr, struct rtable *rt)
+{
+	unsigned char *iph = skb_network_header(skb);
+
+	memcpy(&(IPCB(skb)->opt), opt, sizeof(struct ip_options));
+	memcpy(iph + sizeof(struct iphdr), opt->__data, opt->optlen);
+	opt = &(IPCB(skb)->opt);
+
+	if (opt->srr)
+		memcpy(iph + opt->srr + iph[opt->srr + 1] - 4, &daddr, 4);
+
+	if (opt->rr_needaddr)
+		ip_rt_get_source(iph + opt->rr + iph[opt->rr + 2] - 5, skb, rt);
+	if (opt->ts_needaddr)
+		ip_rt_get_source(iph + opt->ts + iph[opt->ts + 2] - 9, skb, rt);
+	if (opt->ts_needtime) {
+		__be32 midtime;
+
+		midtime = inet_current_timestamp();
+		memcpy(iph + opt->ts + iph[opt->ts + 2] - 5, &midtime, 4);
+	}
+}
+
+/*
+ * Provided (sopt, skb) points to received options,
+ * build in dopt compiled option set appropriate for answering.
+ * i.e. invert SRR option, copy anothers,
+ * and grab room in RR/TS options.
+ *
+ * NOTE: dopt cannot point to skb.
+ */
+
+int __ip_options_echo(struct net *net, struct ip_options *dopt,
+		      struct sk_buff *skb, const struct ip_options *sopt)
+{
+	unsigned char *sptr, *dptr;
+	int soffset, doffset;
+	int	optlen;
+
+	memset(dopt, 0, sizeof(struct ip_options));
+
+	if (sopt->optlen == 0)
+		return 0;
+
+	sptr = skb_network_header(skb);
+	dptr = dopt->__data;
+
+	if (sopt->rr) {
+		optlen  = sptr[sopt->rr+1];
+		soffset = sptr[sopt->rr+2];
+		dopt->rr = dopt->optlen + sizeof(struct iphdr);
+		memcpy(dptr, sptr+sopt->rr, optlen);
+		if (sopt->rr_needaddr && soffset <= optlen) {
+			if (soffset + 3 > optlen)
+				return -EINVAL;
+			dptr[2] = soffset + 4;
+			dopt->rr_needaddr = 1;
+		}
+		dptr += optlen;
+		dopt->optlen += optlen;
+	}
+	if (sopt->ts) {
+		optlen = sptr[sopt->ts+1];
+		soffset = sptr[sopt->ts+2];
+		dopt->ts = dopt->optlen + sizeof(struct iphdr);
+		memcpy(dptr, sptr+sopt->ts, optlen);
+		if (soffset <= optlen) {
+			if (sopt->ts_needaddr) {
+				if (soffset + 3 > optlen)
+					return -EINVAL;
+				dopt->ts_needaddr = 1;
+				soffset += 4;
+			}
+			if (sopt->ts_needtime) {
+				if (soffset + 3 > optlen)
+					return -EINVAL;
+				if ((dptr[3]&0xF) != IPOPT_TS_PRESPEC) {
+					dopt->ts_needtime = 1;
+					soffset += 4;
+				} else {
+					dopt->ts_needtime = 0;
+
+					if (soffset + 7 <= optlen) {
+						__be32 addr;
+
+						memcpy(&addr, dptr+soffset-1, 4);
+						if (inet_addr_type(net, addr) != RTN_UNICAST) {
+							dopt->ts_needtime = 1;
+							soffset += 8;
+						}
+					}
+				}
+			}
+			dptr[2] = soffset;
+		}
+		dptr += optlen;
+		dopt->optlen += optlen;
+	}
+	if (sopt->srr) {
+		unsigned char *start = sptr+sopt->srr;
+		__be32 faddr;
+
+		optlen  = start[1];
+		soffset = start[2];
+		doffset = 0;
+		if (soffset > optlen)
+			soffset = optlen + 1;
+		soffset -= 4;
+		if (soffset > 3) {
+			memcpy(&faddr, &start[soffset-1], 4);
+			for (soffset -= 4, doffset = 4; soffset > 3; soffset -= 4, doffset += 4)
+				memcpy(&dptr[doffset-1], &start[soffset-1], 4);
+			/*
+			 * RFC1812 requires to fix illegal source routes.
+			 */
+			if (memcmp(&ip_hdr(skb)->saddr,
+				   &start[soffset + 3], 4) == 0)
+				doffset -= 4;
+		}
+		if (doffset > 3) {
+			dopt->faddr = faddr;
+			dptr[0] = start[0];
+			dptr[1] = doffset+3;
+			dptr[2] = 4;
+			dptr += doffset+3;
+			dopt->srr = dopt->optlen + sizeof(struct iphdr);
+			dopt->optlen += doffset+3;
+			dopt->is_strictroute = sopt->is_strictroute;
+		}
+	}
+	if (sopt->cipso) {
+		optlen  = sptr[sopt->cipso+1];
+		dopt->cipso = dopt->optlen+sizeof(struct iphdr);
+		memcpy(dptr, sptr+sopt->cipso, optlen);
+		dptr += optlen;
+		dopt->optlen += optlen;
+	}
+	while (dopt->optlen & 3) {
+		*dptr++ = IPOPT_END;
+		dopt->optlen++;
+	}
+	return 0;
+}
+
+/*
+ *	Options "fragmenting", just fill options not
+ *	allowed in fragments with NOOPs.
+ *	Simple and stupid 8), but the most efficient way.
+ */
+
+void ip_options_fragment(struct sk_buff *skb)
+{
+	unsigned char *optptr = skb_network_header(skb) + sizeof(struct iphdr);
+	struct ip_options *opt = &(IPCB(skb)->opt);
+	int  l = opt->optlen;
+	int  optlen;
+
+	while (l > 0) {
+		switch (*optptr) {
+		case IPOPT_END:
+			return;
+		case IPOPT_NOOP:
+			l--;
+			optptr++;
+			continue;
+		}
+		optlen = optptr[1];
+		if (optlen < 2 || optlen > l)
+		  return;
+		if (!IPOPT_COPIED(*optptr))
+			memset(optptr, IPOPT_NOOP, optlen);
+		l -= optlen;
+		optptr += optlen;
+	}
+	opt->ts = 0;
+	opt->rr = 0;
+	opt->rr_needaddr = 0;
+	opt->ts_needaddr = 0;
+	opt->ts_needtime = 0;
+}
+
+/* helper used by ip_options_compile() to call fib_compute_spec_dst()
+ * at most one time.
+ */
+static void spec_dst_fill(__be32 *spec_dst, struct sk_buff *skb)
+{
+	if (*spec_dst == htonl(INADDR_ANY))
+		*spec_dst = fib_compute_spec_dst(skb);
+}
+
+/*
+ * Verify options and fill pointers in struct options.
+ * Caller should clear *opt, and set opt->data.
+ * If opt == NULL, then skb->data should point to IP header.
+ */
+
+int __ip_options_compile(struct net *net,
+			 struct ip_options *opt, struct sk_buff *skb,
+			 __be32 *info)
+{
+	__be32 spec_dst = htonl(INADDR_ANY);
+	unsigned char *pp_ptr = NULL;
+	struct rtable *rt = NULL;
+	unsigned char *optptr;
+	unsigned char *iph;
+	int optlen, l;
+
+	if (skb) {
+		rt = skb_rtable(skb);
+		optptr = (unsigned char *)&(ip_hdr(skb)[1]);
+	} else
+		optptr = opt->__data;
+	iph = optptr - sizeof(struct iphdr);
+
+	for (l = opt->optlen; l > 0; ) {
+		switch (*optptr) {
+		case IPOPT_END:
+			for (optptr++, l--; l > 0; optptr++, l--) {
+				if (*optptr != IPOPT_END) {
+					*optptr = IPOPT_END;
+					opt->is_changed = 1;
+				}
+			}
+			goto eol;
+		case IPOPT_NOOP:
+			l--;
+			optptr++;
+			continue;
+		}
+		if (unlikely(l < 2)) {
+			pp_ptr = optptr;
+			goto error;
+		}
+		optlen = optptr[1];
+		if (optlen < 2 || optlen > l) {
+			pp_ptr = optptr;
+			goto error;
+		}
+		switch (*optptr) {
+		case IPOPT_SSRR:
+		case IPOPT_LSRR:
+			if (optlen < 3) {
+				pp_ptr = optptr + 1;
+				goto error;
+			}
+			if (optptr[2] < 4) {
+				pp_ptr = optptr + 2;
+				goto error;
+			}
+			/* NB: cf RFC-1812 5.2.4.1 */
+			if (opt->srr) {
+				pp_ptr = optptr;
+				goto error;
+			}
+			if (!skb) {
+				if (optptr[2] != 4 || optlen < 7 || ((optlen-3) & 3)) {
+					pp_ptr = optptr + 1;
+					goto error;
+				}
+				memcpy(&opt->faddr, &optptr[3], 4);
+				if (optlen > 7)
+					memmove(&optptr[3], &optptr[7], optlen-7);
+			}
+			opt->is_strictroute = (optptr[0] == IPOPT_SSRR);
+			opt->srr = optptr - iph;
+			break;
+		case IPOPT_RR:
+			if (opt->rr) {
+				pp_ptr = optptr;
+				goto error;
+			}
+			if (optlen < 3) {
+				pp_ptr = optptr + 1;
+				goto error;
+			}
+			if (optptr[2] < 4) {
+				pp_ptr = optptr + 2;
+				goto error;
+			}
+			if (optptr[2] <= optlen) {
+				if (optptr[2]+3 > optlen) {
+					pp_ptr = optptr + 2;
+					goto error;
+				}
+				if (rt) {
+					spec_dst_fill(&spec_dst, skb);
+					memcpy(&optptr[optptr[2]-1], &spec_dst, 4);
+					opt->is_changed = 1;
+				}
+				optptr[2] += 4;
+				opt->rr_needaddr = 1;
+			}
+			opt->rr = optptr - iph;
+			break;
+		case IPOPT_TIMESTAMP:
+			if (opt->ts) {
+				pp_ptr = optptr;
+				goto error;
+			}
+			if (optlen < 4) {
+				pp_ptr = optptr + 1;
+				goto error;
+			}
+			if (optptr[2] < 5) {
+				pp_ptr = optptr + 2;
+				goto error;
+			}
+			if (optptr[2] <= optlen) {
+				unsigned char *timeptr = NULL;
+				if (optptr[2]+3 > optlen) {
+					pp_ptr = optptr + 2;
+					goto error;
+				}
+				switch (optptr[3]&0xF) {
+				case IPOPT_TS_TSONLY:
+					if (skb)
+						timeptr = &optptr[optptr[2]-1];
+					opt->ts_needtime = 1;
+					optptr[2] += 4;
+					break;
+				case IPOPT_TS_TSANDADDR:
+					if (optptr[2]+7 > optlen) {
+						pp_ptr = optptr + 2;
+						goto error;
+					}
+					if (rt)  {
+						spec_dst_fill(&spec_dst, skb);
+						memcpy(&optptr[optptr[2]-1], &spec_dst, 4);
+						timeptr = &optptr[optptr[2]+3];
+					}
+					opt->ts_needaddr = 1;
+					opt->ts_needtime = 1;
+					optptr[2] += 8;
+					break;
+				case IPOPT_TS_PRESPEC:
+					if (optptr[2]+7 > optlen) {
+						pp_ptr = optptr + 2;
+						goto error;
+					}
+					{
+						__be32 addr;
+						memcpy(&addr, &optptr[optptr[2]-1], 4);
+						if (inet_addr_type(net, addr) == RTN_UNICAST)
+							break;
+						if (skb)
+							timeptr = &optptr[optptr[2]+3];
+					}
+					opt->ts_needtime = 1;
+					optptr[2] += 8;
+					break;
+				default:
+					if (!skb && !ns_capable(net->user_ns, CAP_NET_RAW)) {
+						pp_ptr = optptr + 3;
+						goto error;
+					}
+					break;
+				}
+				if (timeptr) {
+					__be32 midtime;
+
+					midtime = inet_current_timestamp();
+					memcpy(timeptr, &midtime, 4);
+					opt->is_changed = 1;
+				}
+			} else if ((optptr[3]&0xF) != IPOPT_TS_PRESPEC) {
+				unsigned int overflow = optptr[3]>>4;
+				if (overflow == 15) {
+					pp_ptr = optptr + 3;
+					goto error;
+				}
+				if (skb) {
+					optptr[3] = (optptr[3]&0xF)|((overflow+1)<<4);
+					opt->is_changed = 1;
+				}
+			}
+			opt->ts = optptr - iph;
+			break;
+		case IPOPT_RA:
+			if (optlen < 4) {
+				pp_ptr = optptr + 1;
+				goto error;
+			}
+			if (optptr[2] == 0 && optptr[3] == 0)
+				opt->router_alert = optptr - iph;
+			break;
+		case IPOPT_CIPSO:
+			if ((!skb && !ns_capable(net->user_ns, CAP_NET_RAW)) || opt->cipso) {
+				pp_ptr = optptr;
+				goto error;
+			}
+			opt->cipso = optptr - iph;
+			if (cipso_v4_validate(skb, &optptr)) {
+				pp_ptr = optptr;
+				goto error;
+			}
+			break;
+		case IPOPT_SEC:
+		case IPOPT_SID:
+		default:
+			if (!skb && !ns_capable(net->user_ns, CAP_NET_RAW)) {
+				pp_ptr = optptr;
+				goto error;
+			}
+			break;
+		}
+		l -= optlen;
+		optptr += optlen;
+	}
+
+eol:
+	if (!pp_ptr)
+		return 0;
+
+error:
+	if (info)
+		*info = htonl((pp_ptr-iph)<<24);
+	return -EINVAL;
+}
+EXPORT_SYMBOL(__ip_options_compile);
+
+int ip_options_compile(struct net *net,
+		       struct ip_options *opt, struct sk_buff *skb)
+{
+	int ret;
+	__be32 info;
+
+	ret = __ip_options_compile(net, opt, skb, &info);
+	if (ret != 0 && skb)
+		icmp_send(skb, ICMP_PARAMETERPROB, 0, info);
+	return ret;
+}
+EXPORT_SYMBOL(ip_options_compile);
+
+/*
+ *	Undo all the changes done by ip_options_compile().
+ */
+
+void ip_options_undo(struct ip_options *opt)
+{
+	if (opt->srr) {
+		unsigned char *optptr = opt->__data + opt->srr - sizeof(struct iphdr);
+
+		memmove(optptr + 7, optptr + 3, optptr[1] - 7);
+		memcpy(optptr + 3, &opt->faddr, 4);
+	}
+	if (opt->rr_needaddr) {
+		unsigned char *optptr = opt->__data + opt->rr - sizeof(struct iphdr);
+
+		optptr[2] -= 4;
+		memset(&optptr[optptr[2] - 1], 0, 4);
+	}
+	if (opt->ts) {
+		unsigned char *optptr = opt->__data + opt->ts - sizeof(struct iphdr);
+
+		if (opt->ts_needtime) {
+			optptr[2] -= 4;
+			memset(&optptr[optptr[2] - 1], 0, 4);
+			if ((optptr[3] & 0xF) == IPOPT_TS_PRESPEC)
+				optptr[2] -= 4;
+		}
+		if (opt->ts_needaddr) {
+			optptr[2] -= 4;
+			memset(&optptr[optptr[2] - 1], 0, 4);
+		}
+	}
+}
+
+int ip_options_get(struct net *net, struct ip_options_rcu **optp,
+		   sockptr_t data, int optlen)
+{
+	struct ip_options_rcu *opt;
+
+	opt = kzalloc(sizeof(struct ip_options_rcu) + ((optlen + 3) & ~3),
+		       GFP_KERNEL);
+	if (!opt)
+		return -ENOMEM;
+	if (optlen && copy_from_sockptr(opt->opt.__data, data, optlen)) {
+		kfree(opt);
+		return -EFAULT;
+	}
+
+	while (optlen & 3)
+		opt->opt.__data[optlen++] = IPOPT_END;
+	opt->opt.optlen = optlen;
+	if (optlen && ip_options_compile(net, &opt->opt, NULL)) {
+		kfree(opt);
+		return -EINVAL;
+	}
+	kfree(*optp);
+	*optp = opt;
+	return 0;
+}
+
+void ip_forward_options(struct sk_buff *skb)
+{
+	struct   ip_options *opt	= &(IPCB(skb)->opt);
+	unsigned char *optptr;
+	struct rtable *rt = skb_rtable(skb);
+	unsigned char *raw = skb_network_header(skb);
+
+	if (opt->rr_needaddr) {
+		optptr = (unsigned char *)raw + opt->rr;
+		ip_rt_get_source(&optptr[optptr[2]-5], skb, rt);
+		opt->is_changed = 1;
+	}
+	if (opt->srr_is_hit) {
+		int srrptr, srrspace;
+
+		optptr = raw + opt->srr;
+
+		for ( srrptr = optptr[2], srrspace = optptr[1];
+		     srrptr <= srrspace;
+		     srrptr += 4
+		     ) {
+			if (srrptr + 3 > srrspace)
+				break;
+			if (memcmp(&opt->nexthop, &optptr[srrptr-1], 4) == 0)
+				break;
+		}
+		if (srrptr + 3 <= srrspace) {
+			opt->is_changed = 1;
+			ip_hdr(skb)->daddr = opt->nexthop;
+			ip_rt_get_source(&optptr[srrptr-1], skb, rt);
+			optptr[2] = srrptr+4;
+		} else {
+			net_crit_ratelimited("%s(): Argh! Destination lost!\n",
+					     __func__);
+		}
+		if (opt->ts_needaddr) {
+			optptr = raw + opt->ts;
+			ip_rt_get_source(&optptr[optptr[2]-9], skb, rt);
+			opt->is_changed = 1;
+		}
+	}
+	if (opt->is_changed) {
+		opt->is_changed = 0;
+		ip_send_check(ip_hdr(skb));
+	}
+}
+
+int ip_options_rcv_srr(struct sk_buff *skb, struct net_device *dev)
+{
+	struct ip_options *opt = &(IPCB(skb)->opt);
+	int srrspace, srrptr;
+	__be32 nexthop;
+	struct iphdr *iph = ip_hdr(skb);
+	unsigned char *optptr = skb_network_header(skb) + opt->srr;
+	struct rtable *rt = skb_rtable(skb);
+	struct rtable *rt2;
+	unsigned long orefdst;
+	int err;
+
+	if (!rt)
+		return 0;
+
+	if (skb->pkt_type != PACKET_HOST)
+		return -EINVAL;
+	if (rt->rt_type == RTN_UNICAST) {
+		if (!opt->is_strictroute)
+			return 0;
+		icmp_send(skb, ICMP_PARAMETERPROB, 0, htonl(16<<24));
+		return -EINVAL;
+	}
+	if (rt->rt_type != RTN_LOCAL)
+		return -EINVAL;
+
+	for (srrptr = optptr[2], srrspace = optptr[1]; srrptr <= srrspace; srrptr += 4) {
+		if (srrptr + 3 > srrspace) {
+			icmp_send(skb, ICMP_PARAMETERPROB, 0, htonl((opt->srr+2)<<24));
+			return -EINVAL;
+		}
+		memcpy(&nexthop, &optptr[srrptr-1], 4);
+
+		orefdst = skb->_skb_refdst;
+		skb_dst_set(skb, NULL);
+		err = ip_route_input(skb, nexthop, iph->saddr, iph->tos, dev);
+		rt2 = skb_rtable(skb);
+		if (err || (rt2->rt_type != RTN_UNICAST && rt2->rt_type != RTN_LOCAL)) {
+			skb_dst_drop(skb);
+			skb->_skb_refdst = orefdst;
+			return -EINVAL;
+		}
+		refdst_drop(orefdst);
+		if (rt2->rt_type != RTN_LOCAL)
+			break;
+		/* Superfast 8) loopback forward */
+		iph->daddr = nexthop;
+		opt->is_changed = 1;
+	}
+	if (srrptr <= srrspace) {
+		opt->srr_is_hit = 1;
+		opt->nexthop = nexthop;
+		opt->is_changed = 1;
+	}
+	return 0;
+}
+EXPORT_SYMBOL(ip_options_rcv_srr);