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, 604 insertions, 0 deletions

diff --git a/net/ipv4/ah4.c b/net/ipv4/ah4.c
new file mode 100644
index 000000000..015c0f4ec
--- /dev/null
+++ b/net/ipv4/ah4.c
@@ -0,0 +1,604 @@
+// SPDX-License-Identifier: GPL-2.0-only
+#define pr_fmt(fmt) "IPsec: " fmt
+
+#include <crypto/algapi.h>
+#include <crypto/hash.h>
+#include <linux/err.h>
+#include <linux/module.h>
+#include <linux/slab.h>
+#include <net/ip.h>
+#include <net/xfrm.h>
+#include <net/ah.h>
+#include <linux/crypto.h>
+#include <linux/pfkeyv2.h>
+#include <linux/scatterlist.h>
+#include <net/icmp.h>
+#include <net/protocol.h>
+
+struct ah_skb_cb {
+	struct xfrm_skb_cb xfrm;
+	void *tmp;
+};
+
+#define AH_SKB_CB(__skb) ((struct ah_skb_cb *)&((__skb)->cb[0]))
+
+static void *ah_alloc_tmp(struct crypto_ahash *ahash, int nfrags,
+			  unsigned int size)
+{
+	unsigned int len;
+
+	len = size + crypto_ahash_digestsize(ahash) +
+	      (crypto_ahash_alignmask(ahash) &
+	       ~(crypto_tfm_ctx_alignment() - 1));
+
+	len = ALIGN(len, crypto_tfm_ctx_alignment());
+
+	len += sizeof(struct ahash_request) + crypto_ahash_reqsize(ahash);
+	len = ALIGN(len, __alignof__(struct scatterlist));
+
+	len += sizeof(struct scatterlist) * nfrags;
+
+	return kmalloc(len, GFP_ATOMIC);
+}
+
+static inline u8 *ah_tmp_auth(void *tmp, unsigned int offset)
+{
+	return tmp + offset;
+}
+
+static inline u8 *ah_tmp_icv(struct crypto_ahash *ahash, void *tmp,
+			     unsigned int offset)
+{
+	return PTR_ALIGN((u8 *)tmp + offset, crypto_ahash_alignmask(ahash) + 1);
+}
+
+static inline struct ahash_request *ah_tmp_req(struct crypto_ahash *ahash,
+					       u8 *icv)
+{
+	struct ahash_request *req;
+
+	req = (void *)PTR_ALIGN(icv + crypto_ahash_digestsize(ahash),
+				crypto_tfm_ctx_alignment());
+
+	ahash_request_set_tfm(req, ahash);
+
+	return req;
+}
+
+static inline struct scatterlist *ah_req_sg(struct crypto_ahash *ahash,
+					     struct ahash_request *req)
+{
+	return (void *)ALIGN((unsigned long)(req + 1) +
+			     crypto_ahash_reqsize(ahash),
+			     __alignof__(struct scatterlist));
+}
+
+/* Clear mutable options and find final destination to substitute
+ * into IP header for icv calculation. Options are already checked
+ * for validity, so paranoia is not required. */
+
+static int ip_clear_mutable_options(const struct iphdr *iph, __be32 *daddr)
+{
+	unsigned char *optptr = (unsigned char *)(iph+1);
+	int  l = iph->ihl*4 - sizeof(struct iphdr);
+	int  optlen;
+
+	while (l > 0) {
+		switch (*optptr) {
+		case IPOPT_END:
+			return 0;
+		case IPOPT_NOOP:
+			l--;
+			optptr++;
+			continue;
+		}
+		optlen = optptr[1];
+		if (optlen<2 || optlen>l)
+			return -EINVAL;
+		switch (*optptr) {
+		case IPOPT_SEC:
+		case 0x85:	/* Some "Extended Security" crap. */
+		case IPOPT_CIPSO:
+		case IPOPT_RA:
+		case 0x80|21:	/* RFC1770 */
+			break;
+		case IPOPT_LSRR:
+		case IPOPT_SSRR:
+			if (optlen < 6)
+				return -EINVAL;
+			memcpy(daddr, optptr+optlen-4, 4);
+			fallthrough;
+		default:
+			memset(optptr, 0, optlen);
+		}
+		l -= optlen;
+		optptr += optlen;
+	}
+	return 0;
+}
+
+static void ah_output_done(void *data, int err)
+{
+	u8 *icv;
+	struct iphdr *iph;
+	struct sk_buff *skb = data;
+	struct xfrm_state *x = skb_dst(skb)->xfrm;
+	struct ah_data *ahp = x->data;
+	struct iphdr *top_iph = ip_hdr(skb);
+	struct ip_auth_hdr *ah = ip_auth_hdr(skb);
+	int ihl = ip_hdrlen(skb);
+
+	iph = AH_SKB_CB(skb)->tmp;
+	icv = ah_tmp_icv(ahp->ahash, iph, ihl);
+	memcpy(ah->auth_data, icv, ahp->icv_trunc_len);
+
+	top_iph->tos = iph->tos;
+	top_iph->ttl = iph->ttl;
+	top_iph->frag_off = iph->frag_off;
+	if (top_iph->ihl != 5) {
+		top_iph->daddr = iph->daddr;
+		memcpy(top_iph+1, iph+1, top_iph->ihl*4 - sizeof(struct iphdr));
+	}
+
+	kfree(AH_SKB_CB(skb)->tmp);
+	xfrm_output_resume(skb->sk, skb, err);
+}
+
+static int ah_output(struct xfrm_state *x, struct sk_buff *skb)
+{
+	int err;
+	int nfrags;
+	int ihl;
+	u8 *icv;
+	struct sk_buff *trailer;
+	struct crypto_ahash *ahash;
+	struct ahash_request *req;
+	struct scatterlist *sg;
+	struct iphdr *iph, *top_iph;
+	struct ip_auth_hdr *ah;
+	struct ah_data *ahp;
+	int seqhi_len = 0;
+	__be32 *seqhi;
+	int sglists = 0;
+	struct scatterlist *seqhisg;
+
+	ahp = x->data;
+	ahash = ahp->ahash;
+
+	if ((err = skb_cow_data(skb, 0, &trailer)) < 0)
+		goto out;
+	nfrags = err;
+
+	skb_push(skb, -skb_network_offset(skb));
+	ah = ip_auth_hdr(skb);
+	ihl = ip_hdrlen(skb);
+
+	if (x->props.flags & XFRM_STATE_ESN) {
+		sglists = 1;
+		seqhi_len = sizeof(*seqhi);
+	}
+	err = -ENOMEM;
+	iph = ah_alloc_tmp(ahash, nfrags + sglists, ihl + seqhi_len);
+	if (!iph)
+		goto out;
+	seqhi = (__be32 *)((char *)iph + ihl);
+	icv = ah_tmp_icv(ahash, seqhi, seqhi_len);
+	req = ah_tmp_req(ahash, icv);
+	sg = ah_req_sg(ahash, req);
+	seqhisg = sg + nfrags;
+
+	memset(ah->auth_data, 0, ahp->icv_trunc_len);
+
+	top_iph = ip_hdr(skb);
+
+	iph->tos = top_iph->tos;
+	iph->ttl = top_iph->ttl;
+	iph->frag_off = top_iph->frag_off;
+
+	if (top_iph->ihl != 5) {
+		iph->daddr = top_iph->daddr;
+		memcpy(iph+1, top_iph+1, top_iph->ihl*4 - sizeof(struct iphdr));
+		err = ip_clear_mutable_options(top_iph, &top_iph->daddr);
+		if (err)
+			goto out_free;
+	}
+
+	ah->nexthdr = *skb_mac_header(skb);
+	*skb_mac_header(skb) = IPPROTO_AH;
+
+	top_iph->tos = 0;
+	top_iph->tot_len = htons(skb->len);
+	top_iph->frag_off = 0;
+	top_iph->ttl = 0;
+	top_iph->check = 0;
+
+	if (x->props.flags & XFRM_STATE_ALIGN4)
+		ah->hdrlen  = (XFRM_ALIGN4(sizeof(*ah) + ahp->icv_trunc_len) >> 2) - 2;
+	else
+		ah->hdrlen  = (XFRM_ALIGN8(sizeof(*ah) + ahp->icv_trunc_len) >> 2) - 2;
+
+	ah->reserved = 0;
+	ah->spi = x->id.spi;
+	ah->seq_no = htonl(XFRM_SKB_CB(skb)->seq.output.low);
+
+	sg_init_table(sg, nfrags + sglists);
+	err = skb_to_sgvec_nomark(skb, sg, 0, skb->len);
+	if (unlikely(err < 0))
+		goto out_free;
+
+	if (x->props.flags & XFRM_STATE_ESN) {
+		/* Attach seqhi sg right after packet payload */
+		*seqhi = htonl(XFRM_SKB_CB(skb)->seq.output.hi);
+		sg_set_buf(seqhisg, seqhi, seqhi_len);
+	}
+	ahash_request_set_crypt(req, sg, icv, skb->len + seqhi_len);
+	ahash_request_set_callback(req, 0, ah_output_done, skb);
+
+	AH_SKB_CB(skb)->tmp = iph;
+
+	err = crypto_ahash_digest(req);
+	if (err) {
+		if (err == -EINPROGRESS)
+			goto out;
+
+		if (err == -ENOSPC)
+			err = NET_XMIT_DROP;
+		goto out_free;
+	}
+
+	memcpy(ah->auth_data, icv, ahp->icv_trunc_len);
+
+	top_iph->tos = iph->tos;
+	top_iph->ttl = iph->ttl;
+	top_iph->frag_off = iph->frag_off;
+	if (top_iph->ihl != 5) {
+		top_iph->daddr = iph->daddr;
+		memcpy(top_iph+1, iph+1, top_iph->ihl*4 - sizeof(struct iphdr));
+	}
+
+out_free:
+	kfree(iph);
+out:
+	return err;
+}
+
+static void ah_input_done(void *data, int err)
+{
+	u8 *auth_data;
+	u8 *icv;
+	struct iphdr *work_iph;
+	struct sk_buff *skb = data;
+	struct xfrm_state *x = xfrm_input_state(skb);
+	struct ah_data *ahp = x->data;
+	struct ip_auth_hdr *ah = ip_auth_hdr(skb);
+	int ihl = ip_hdrlen(skb);
+	int ah_hlen = (ah->hdrlen + 2) << 2;
+
+	if (err)
+		goto out;
+
+	work_iph = AH_SKB_CB(skb)->tmp;
+	auth_data = ah_tmp_auth(work_iph, ihl);
+	icv = ah_tmp_icv(ahp->ahash, auth_data, ahp->icv_trunc_len);
+
+	err = crypto_memneq(icv, auth_data, ahp->icv_trunc_len) ? -EBADMSG : 0;
+	if (err)
+		goto out;
+
+	err = ah->nexthdr;
+
+	skb->network_header += ah_hlen;
+	memcpy(skb_network_header(skb), work_iph, ihl);
+	__skb_pull(skb, ah_hlen + ihl);
+
+	if (x->props.mode == XFRM_MODE_TUNNEL)
+		skb_reset_transport_header(skb);
+	else
+		skb_set_transport_header(skb, -ihl);
+out:
+	kfree(AH_SKB_CB(skb)->tmp);
+	xfrm_input_resume(skb, err);
+}
+
+static int ah_input(struct xfrm_state *x, struct sk_buff *skb)
+{
+	int ah_hlen;
+	int ihl;
+	int nexthdr;
+	int nfrags;
+	u8 *auth_data;
+	u8 *icv;
+	struct sk_buff *trailer;
+	struct crypto_ahash *ahash;
+	struct ahash_request *req;
+	struct scatterlist *sg;
+	struct iphdr *iph, *work_iph;
+	struct ip_auth_hdr *ah;
+	struct ah_data *ahp;
+	int err = -ENOMEM;
+	int seqhi_len = 0;
+	__be32 *seqhi;
+	int sglists = 0;
+	struct scatterlist *seqhisg;
+
+	if (!pskb_may_pull(skb, sizeof(*ah)))
+		goto out;
+
+	ah = (struct ip_auth_hdr *)skb->data;
+	ahp = x->data;
+	ahash = ahp->ahash;
+
+	nexthdr = ah->nexthdr;
+	ah_hlen = (ah->hdrlen + 2) << 2;
+
+	if (x->props.flags & XFRM_STATE_ALIGN4) {
+		if (ah_hlen != XFRM_ALIGN4(sizeof(*ah) + ahp->icv_full_len) &&
+		    ah_hlen != XFRM_ALIGN4(sizeof(*ah) + ahp->icv_trunc_len))
+			goto out;
+	} else {
+		if (ah_hlen != XFRM_ALIGN8(sizeof(*ah) + ahp->icv_full_len) &&
+		    ah_hlen != XFRM_ALIGN8(sizeof(*ah) + ahp->icv_trunc_len))
+			goto out;
+	}
+
+	if (!pskb_may_pull(skb, ah_hlen))
+		goto out;
+
+	/* We are going to _remove_ AH header to keep sockets happy,
+	 * so... Later this can change. */
+	if (skb_unclone(skb, GFP_ATOMIC))
+		goto out;
+
+	skb->ip_summed = CHECKSUM_NONE;
+
+
+	if ((err = skb_cow_data(skb, 0, &trailer)) < 0)
+		goto out;
+	nfrags = err;
+
+	ah = (struct ip_auth_hdr *)skb->data;
+	iph = ip_hdr(skb);
+	ihl = ip_hdrlen(skb);
+
+	if (x->props.flags & XFRM_STATE_ESN) {
+		sglists = 1;
+		seqhi_len = sizeof(*seqhi);
+	}
+
+	work_iph = ah_alloc_tmp(ahash, nfrags + sglists, ihl +
+				ahp->icv_trunc_len + seqhi_len);
+	if (!work_iph) {
+		err = -ENOMEM;
+		goto out;
+	}
+
+	seqhi = (__be32 *)((char *)work_iph + ihl);
+	auth_data = ah_tmp_auth(seqhi, seqhi_len);
+	icv = ah_tmp_icv(ahash, auth_data, ahp->icv_trunc_len);
+	req = ah_tmp_req(ahash, icv);
+	sg = ah_req_sg(ahash, req);
+	seqhisg = sg + nfrags;
+
+	memcpy(work_iph, iph, ihl);
+	memcpy(auth_data, ah->auth_data, ahp->icv_trunc_len);
+	memset(ah->auth_data, 0, ahp->icv_trunc_len);
+
+	iph->ttl = 0;
+	iph->tos = 0;
+	iph->frag_off = 0;
+	iph->check = 0;
+	if (ihl > sizeof(*iph)) {
+		__be32 dummy;
+		err = ip_clear_mutable_options(iph, &dummy);
+		if (err)
+			goto out_free;
+	}
+
+	skb_push(skb, ihl);
+
+	sg_init_table(sg, nfrags + sglists);
+	err = skb_to_sgvec_nomark(skb, sg, 0, skb->len);
+	if (unlikely(err < 0))
+		goto out_free;
+
+	if (x->props.flags & XFRM_STATE_ESN) {
+		/* Attach seqhi sg right after packet payload */
+		*seqhi = XFRM_SKB_CB(skb)->seq.input.hi;
+		sg_set_buf(seqhisg, seqhi, seqhi_len);
+	}
+	ahash_request_set_crypt(req, sg, icv, skb->len + seqhi_len);
+	ahash_request_set_callback(req, 0, ah_input_done, skb);
+
+	AH_SKB_CB(skb)->tmp = work_iph;
+
+	err = crypto_ahash_digest(req);
+	if (err) {
+		if (err == -EINPROGRESS)
+			goto out;
+
+		goto out_free;
+	}
+
+	err = crypto_memneq(icv, auth_data, ahp->icv_trunc_len) ? -EBADMSG : 0;
+	if (err)
+		goto out_free;
+
+	skb->network_header += ah_hlen;
+	memcpy(skb_network_header(skb), work_iph, ihl);
+	__skb_pull(skb, ah_hlen + ihl);
+	if (x->props.mode == XFRM_MODE_TUNNEL)
+		skb_reset_transport_header(skb);
+	else
+		skb_set_transport_header(skb, -ihl);
+
+	err = nexthdr;
+
+out_free:
+	kfree (work_iph);
+out:
+	return err;
+}
+
+static int ah4_err(struct sk_buff *skb, u32 info)
+{
+	struct net *net = dev_net(skb->dev);
+	const struct iphdr *iph = (const struct iphdr *)skb->data;
+	struct ip_auth_hdr *ah = (struct ip_auth_hdr *)(skb->data+(iph->ihl<<2));
+	struct xfrm_state *x;
+
+	switch (icmp_hdr(skb)->type) {
+	case ICMP_DEST_UNREACH:
+		if (icmp_hdr(skb)->code != ICMP_FRAG_NEEDED)
+			return 0;
+		break;
+	case ICMP_REDIRECT:
+		break;
+	default:
+		return 0;
+	}
+
+	x = xfrm_state_lookup(net, skb->mark, (const xfrm_address_t *)&iph->daddr,
+			      ah->spi, IPPROTO_AH, AF_INET);
+	if (!x)
+		return 0;
+
+	if (icmp_hdr(skb)->type == ICMP_DEST_UNREACH)
+		ipv4_update_pmtu(skb, net, info, 0, IPPROTO_AH);
+	else
+		ipv4_redirect(skb, net, 0, IPPROTO_AH);
+	xfrm_state_put(x);
+
+	return 0;
+}
+
+static int ah_init_state(struct xfrm_state *x, struct netlink_ext_ack *extack)
+{
+	struct ah_data *ahp = NULL;
+	struct xfrm_algo_desc *aalg_desc;
+	struct crypto_ahash *ahash;
+
+	if (!x->aalg) {
+		NL_SET_ERR_MSG(extack, "AH requires a state with an AUTH algorithm");
+		goto error;
+	}
+
+	if (x->encap) {
+		NL_SET_ERR_MSG(extack, "AH is not compatible with encapsulation");
+		goto error;
+	}
+
+	ahp = kzalloc(sizeof(*ahp), GFP_KERNEL);
+	if (!ahp)
+		return -ENOMEM;
+
+	ahash = crypto_alloc_ahash(x->aalg->alg_name, 0, 0);
+	if (IS_ERR(ahash)) {
+		NL_SET_ERR_MSG(extack, "Kernel was unable to initialize cryptographic operations");
+		goto error;
+	}
+
+	ahp->ahash = ahash;
+	if (crypto_ahash_setkey(ahash, x->aalg->alg_key,
+				(x->aalg->alg_key_len + 7) / 8)) {
+		NL_SET_ERR_MSG(extack, "Kernel was unable to initialize cryptographic operations");
+		goto error;
+	}
+
+	/*
+	 * Lookup the algorithm description maintained by xfrm_algo,
+	 * verify crypto transform properties, and store information
+	 * we need for AH processing.  This lookup cannot fail here
+	 * after a successful crypto_alloc_ahash().
+	 */
+	aalg_desc = xfrm_aalg_get_byname(x->aalg->alg_name, 0);
+	BUG_ON(!aalg_desc);
+
+	if (aalg_desc->uinfo.auth.icv_fullbits/8 !=
+	    crypto_ahash_digestsize(ahash)) {
+		NL_SET_ERR_MSG(extack, "Kernel was unable to initialize cryptographic operations");
+		goto error;
+	}
+
+	ahp->icv_full_len = aalg_desc->uinfo.auth.icv_fullbits/8;
+	ahp->icv_trunc_len = x->aalg->alg_trunc_len/8;
+
+	if (x->props.flags & XFRM_STATE_ALIGN4)
+		x->props.header_len = XFRM_ALIGN4(sizeof(struct ip_auth_hdr) +
+						  ahp->icv_trunc_len);
+	else
+		x->props.header_len = XFRM_ALIGN8(sizeof(struct ip_auth_hdr) +
+						  ahp->icv_trunc_len);
+	if (x->props.mode == XFRM_MODE_TUNNEL)
+		x->props.header_len += sizeof(struct iphdr);
+	x->data = ahp;
+
+	return 0;
+
+error:
+	if (ahp) {
+		crypto_free_ahash(ahp->ahash);
+		kfree(ahp);
+	}
+	return -EINVAL;
+}
+
+static void ah_destroy(struct xfrm_state *x)
+{
+	struct ah_data *ahp = x->data;
+
+	if (!ahp)
+		return;
+
+	crypto_free_ahash(ahp->ahash);
+	kfree(ahp);
+}
+
+static int ah4_rcv_cb(struct sk_buff *skb, int err)
+{
+	return 0;
+}
+
+static const struct xfrm_type ah_type =
+{
+	.owner		= THIS_MODULE,
+	.proto	     	= IPPROTO_AH,
+	.flags		= XFRM_TYPE_REPLAY_PROT,
+	.init_state	= ah_init_state,
+	.destructor	= ah_destroy,
+	.input		= ah_input,
+	.output		= ah_output
+};
+
+static struct xfrm4_protocol ah4_protocol = {
+	.handler	=	xfrm4_rcv,
+	.input_handler	=	xfrm_input,
+	.cb_handler	=	ah4_rcv_cb,
+	.err_handler	=	ah4_err,
+	.priority	=	0,
+};
+
+static int __init ah4_init(void)
+{
+	if (xfrm_register_type(&ah_type, AF_INET) < 0) {
+		pr_info("%s: can't add xfrm type\n", __func__);
+		return -EAGAIN;
+	}
+	if (xfrm4_protocol_register(&ah4_protocol, IPPROTO_AH) < 0) {
+		pr_info("%s: can't add protocol\n", __func__);
+		xfrm_unregister_type(&ah_type, AF_INET);
+		return -EAGAIN;
+	}
+	return 0;
+}
+
+static void __exit ah4_fini(void)
+{
+	if (xfrm4_protocol_deregister(&ah4_protocol, IPPROTO_AH) < 0)
+		pr_info("%s: can't remove protocol\n", __func__);
+	xfrm_unregister_type(&ah_type, AF_INET);
+}
+
+module_init(ah4_init);
+module_exit(ah4_fini);
+MODULE_LICENSE("GPL");
+MODULE_ALIAS_XFRM_TYPE(AF_INET, XFRM_PROTO_AH);