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, 420 insertions, 0 deletions

diff --git a/crypto/fcrypt.c b/crypto/fcrypt.c
new file mode 100644
index 000000000..95a16e888
--- /dev/null
+++ b/crypto/fcrypt.c
@@ -0,0 +1,420 @@
+/* FCrypt encryption algorithm
+ *
+ * Copyright (C) 2006 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ *
+ * Based on code:
+ *
+ * Copyright (c) 1995 - 2000 Kungliga Tekniska Högskolan
+ * (Royal Institute of Technology, Stockholm, Sweden).
+ * All rights reserved.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions
+ * are met:
+ *
+ * 1. Redistributions of source code must retain the above copyright
+ *    notice, this list of conditions and the following disclaimer.
+ *
+ * 2. Redistributions in binary form must reproduce the above copyright
+ *    notice, this list of conditions and the following disclaimer in the
+ *    documentation and/or other materials provided with the distribution.
+ *
+ * 3. Neither the name of the Institute nor the names of its contributors
+ *    may be used to endorse or promote products derived from this software
+ *    without specific prior written permission.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE INSTITUTE AND CONTRIBUTORS ``AS IS'' AND
+ * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+ * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED.  IN NO EVENT SHALL THE INSTITUTE OR CONTRIBUTORS BE LIABLE
+ * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
+ * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
+ * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
+ * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
+ * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
+ * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
+ * SUCH DAMAGE.
+ */
+
+#include <asm/byteorder.h>
+#include <crypto/algapi.h>
+#include <linux/bitops.h>
+#include <linux/init.h>
+#include <linux/module.h>
+
+#define ROUNDS 16
+
+struct fcrypt_ctx {
+	__be32 sched[ROUNDS];
+};
+
+/* Rotate right two 32 bit numbers as a 56 bit number */
+#define ror56(hi, lo, n)					\
+do {								\
+	u32 t = lo & ((1 << n) - 1);				\
+	lo = (lo >> n) | ((hi & ((1 << n) - 1)) << (32 - n));	\
+	hi = (hi >> n) | (t << (24-n));				\
+} while (0)
+
+/* Rotate right one 64 bit number as a 56 bit number */
+#define ror56_64(k, n) (k = (k >> n) | ((k & ((1 << n) - 1)) << (56 - n)))
+
+/*
+ * Sboxes for Feistel network derived from
+ * /afs/transarc.com/public/afsps/afs.rel31b.export-src/rxkad/sboxes.h
+ */
+#undef Z
+#define Z(x) cpu_to_be32(x << 3)
+static const __be32 sbox0[256] = {
+	Z(0xea), Z(0x7f), Z(0xb2), Z(0x64), Z(0x9d), Z(0xb0), Z(0xd9), Z(0x11),
+	Z(0xcd), Z(0x86), Z(0x86), Z(0x91), Z(0x0a), Z(0xb2), Z(0x93), Z(0x06),
+	Z(0x0e), Z(0x06), Z(0xd2), Z(0x65), Z(0x73), Z(0xc5), Z(0x28), Z(0x60),
+	Z(0xf2), Z(0x20), Z(0xb5), Z(0x38), Z(0x7e), Z(0xda), Z(0x9f), Z(0xe3),
+	Z(0xd2), Z(0xcf), Z(0xc4), Z(0x3c), Z(0x61), Z(0xff), Z(0x4a), Z(0x4a),
+	Z(0x35), Z(0xac), Z(0xaa), Z(0x5f), Z(0x2b), Z(0xbb), Z(0xbc), Z(0x53),
+	Z(0x4e), Z(0x9d), Z(0x78), Z(0xa3), Z(0xdc), Z(0x09), Z(0x32), Z(0x10),
+	Z(0xc6), Z(0x6f), Z(0x66), Z(0xd6), Z(0xab), Z(0xa9), Z(0xaf), Z(0xfd),
+	Z(0x3b), Z(0x95), Z(0xe8), Z(0x34), Z(0x9a), Z(0x81), Z(0x72), Z(0x80),
+	Z(0x9c), Z(0xf3), Z(0xec), Z(0xda), Z(0x9f), Z(0x26), Z(0x76), Z(0x15),
+	Z(0x3e), Z(0x55), Z(0x4d), Z(0xde), Z(0x84), Z(0xee), Z(0xad), Z(0xc7),
+	Z(0xf1), Z(0x6b), Z(0x3d), Z(0xd3), Z(0x04), Z(0x49), Z(0xaa), Z(0x24),
+	Z(0x0b), Z(0x8a), Z(0x83), Z(0xba), Z(0xfa), Z(0x85), Z(0xa0), Z(0xa8),
+	Z(0xb1), Z(0xd4), Z(0x01), Z(0xd8), Z(0x70), Z(0x64), Z(0xf0), Z(0x51),
+	Z(0xd2), Z(0xc3), Z(0xa7), Z(0x75), Z(0x8c), Z(0xa5), Z(0x64), Z(0xef),
+	Z(0x10), Z(0x4e), Z(0xb7), Z(0xc6), Z(0x61), Z(0x03), Z(0xeb), Z(0x44),
+	Z(0x3d), Z(0xe5), Z(0xb3), Z(0x5b), Z(0xae), Z(0xd5), Z(0xad), Z(0x1d),
+	Z(0xfa), Z(0x5a), Z(0x1e), Z(0x33), Z(0xab), Z(0x93), Z(0xa2), Z(0xb7),
+	Z(0xe7), Z(0xa8), Z(0x45), Z(0xa4), Z(0xcd), Z(0x29), Z(0x63), Z(0x44),
+	Z(0xb6), Z(0x69), Z(0x7e), Z(0x2e), Z(0x62), Z(0x03), Z(0xc8), Z(0xe0),
+	Z(0x17), Z(0xbb), Z(0xc7), Z(0xf3), Z(0x3f), Z(0x36), Z(0xba), Z(0x71),
+	Z(0x8e), Z(0x97), Z(0x65), Z(0x60), Z(0x69), Z(0xb6), Z(0xf6), Z(0xe6),
+	Z(0x6e), Z(0xe0), Z(0x81), Z(0x59), Z(0xe8), Z(0xaf), Z(0xdd), Z(0x95),
+	Z(0x22), Z(0x99), Z(0xfd), Z(0x63), Z(0x19), Z(0x74), Z(0x61), Z(0xb1),
+	Z(0xb6), Z(0x5b), Z(0xae), Z(0x54), Z(0xb3), Z(0x70), Z(0xff), Z(0xc6),
+	Z(0x3b), Z(0x3e), Z(0xc1), Z(0xd7), Z(0xe1), Z(0x0e), Z(0x76), Z(0xe5),
+	Z(0x36), Z(0x4f), Z(0x59), Z(0xc7), Z(0x08), Z(0x6e), Z(0x82), Z(0xa6),
+	Z(0x93), Z(0xc4), Z(0xaa), Z(0x26), Z(0x49), Z(0xe0), Z(0x21), Z(0x64),
+	Z(0x07), Z(0x9f), Z(0x64), Z(0x81), Z(0x9c), Z(0xbf), Z(0xf9), Z(0xd1),
+	Z(0x43), Z(0xf8), Z(0xb6), Z(0xb9), Z(0xf1), Z(0x24), Z(0x75), Z(0x03),
+	Z(0xe4), Z(0xb0), Z(0x99), Z(0x46), Z(0x3d), Z(0xf5), Z(0xd1), Z(0x39),
+	Z(0x72), Z(0x12), Z(0xf6), Z(0xba), Z(0x0c), Z(0x0d), Z(0x42), Z(0x2e)
+};
+
+#undef Z
+#define Z(x) cpu_to_be32(((x & 0x1f) << 27) | (x >> 5))
+static const __be32 sbox1[256] = {
+	Z(0x77), Z(0x14), Z(0xa6), Z(0xfe), Z(0xb2), Z(0x5e), Z(0x8c), Z(0x3e),
+	Z(0x67), Z(0x6c), Z(0xa1), Z(0x0d), Z(0xc2), Z(0xa2), Z(0xc1), Z(0x85),
+	Z(0x6c), Z(0x7b), Z(0x67), Z(0xc6), Z(0x23), Z(0xe3), Z(0xf2), Z(0x89),
+	Z(0x50), Z(0x9c), Z(0x03), Z(0xb7), Z(0x73), Z(0xe6), Z(0xe1), Z(0x39),
+	Z(0x31), Z(0x2c), Z(0x27), Z(0x9f), Z(0xa5), Z(0x69), Z(0x44), Z(0xd6),
+	Z(0x23), Z(0x83), Z(0x98), Z(0x7d), Z(0x3c), Z(0xb4), Z(0x2d), Z(0x99),
+	Z(0x1c), Z(0x1f), Z(0x8c), Z(0x20), Z(0x03), Z(0x7c), Z(0x5f), Z(0xad),
+	Z(0xf4), Z(0xfa), Z(0x95), Z(0xca), Z(0x76), Z(0x44), Z(0xcd), Z(0xb6),
+	Z(0xb8), Z(0xa1), Z(0xa1), Z(0xbe), Z(0x9e), Z(0x54), Z(0x8f), Z(0x0b),
+	Z(0x16), Z(0x74), Z(0x31), Z(0x8a), Z(0x23), Z(0x17), Z(0x04), Z(0xfa),
+	Z(0x79), Z(0x84), Z(0xb1), Z(0xf5), Z(0x13), Z(0xab), Z(0xb5), Z(0x2e),
+	Z(0xaa), Z(0x0c), Z(0x60), Z(0x6b), Z(0x5b), Z(0xc4), Z(0x4b), Z(0xbc),
+	Z(0xe2), Z(0xaf), Z(0x45), Z(0x73), Z(0xfa), Z(0xc9), Z(0x49), Z(0xcd),
+	Z(0x00), Z(0x92), Z(0x7d), Z(0x97), Z(0x7a), Z(0x18), Z(0x60), Z(0x3d),
+	Z(0xcf), Z(0x5b), Z(0xde), Z(0xc6), Z(0xe2), Z(0xe6), Z(0xbb), Z(0x8b),
+	Z(0x06), Z(0xda), Z(0x08), Z(0x15), Z(0x1b), Z(0x88), Z(0x6a), Z(0x17),
+	Z(0x89), Z(0xd0), Z(0xa9), Z(0xc1), Z(0xc9), Z(0x70), Z(0x6b), Z(0xe5),
+	Z(0x43), Z(0xf4), Z(0x68), Z(0xc8), Z(0xd3), Z(0x84), Z(0x28), Z(0x0a),
+	Z(0x52), Z(0x66), Z(0xa3), Z(0xca), Z(0xf2), Z(0xe3), Z(0x7f), Z(0x7a),
+	Z(0x31), Z(0xf7), Z(0x88), Z(0x94), Z(0x5e), Z(0x9c), Z(0x63), Z(0xd5),
+	Z(0x24), Z(0x66), Z(0xfc), Z(0xb3), Z(0x57), Z(0x25), Z(0xbe), Z(0x89),
+	Z(0x44), Z(0xc4), Z(0xe0), Z(0x8f), Z(0x23), Z(0x3c), Z(0x12), Z(0x52),
+	Z(0xf5), Z(0x1e), Z(0xf4), Z(0xcb), Z(0x18), Z(0x33), Z(0x1f), Z(0xf8),
+	Z(0x69), Z(0x10), Z(0x9d), Z(0xd3), Z(0xf7), Z(0x28), Z(0xf8), Z(0x30),
+	Z(0x05), Z(0x5e), Z(0x32), Z(0xc0), Z(0xd5), Z(0x19), Z(0xbd), Z(0x45),
+	Z(0x8b), Z(0x5b), Z(0xfd), Z(0xbc), Z(0xe2), Z(0x5c), Z(0xa9), Z(0x96),
+	Z(0xef), Z(0x70), Z(0xcf), Z(0xc2), Z(0x2a), Z(0xb3), Z(0x61), Z(0xad),
+	Z(0x80), Z(0x48), Z(0x81), Z(0xb7), Z(0x1d), Z(0x43), Z(0xd9), Z(0xd7),
+	Z(0x45), Z(0xf0), Z(0xd8), Z(0x8a), Z(0x59), Z(0x7c), Z(0x57), Z(0xc1),
+	Z(0x79), Z(0xc7), Z(0x34), Z(0xd6), Z(0x43), Z(0xdf), Z(0xe4), Z(0x78),
+	Z(0x16), Z(0x06), Z(0xda), Z(0x92), Z(0x76), Z(0x51), Z(0xe1), Z(0xd4),
+	Z(0x70), Z(0x03), Z(0xe0), Z(0x2f), Z(0x96), Z(0x91), Z(0x82), Z(0x80)
+};
+
+#undef Z
+#define Z(x) cpu_to_be32(x << 11)
+static const __be32 sbox2[256] = {
+	Z(0xf0), Z(0x37), Z(0x24), Z(0x53), Z(0x2a), Z(0x03), Z(0x83), Z(0x86),
+	Z(0xd1), Z(0xec), Z(0x50), Z(0xf0), Z(0x42), Z(0x78), Z(0x2f), Z(0x6d),
+	Z(0xbf), Z(0x80), Z(0x87), Z(0x27), Z(0x95), Z(0xe2), Z(0xc5), Z(0x5d),
+	Z(0xf9), Z(0x6f), Z(0xdb), Z(0xb4), Z(0x65), Z(0x6e), Z(0xe7), Z(0x24),
+	Z(0xc8), Z(0x1a), Z(0xbb), Z(0x49), Z(0xb5), Z(0x0a), Z(0x7d), Z(0xb9),
+	Z(0xe8), Z(0xdc), Z(0xb7), Z(0xd9), Z(0x45), Z(0x20), Z(0x1b), Z(0xce),
+	Z(0x59), Z(0x9d), Z(0x6b), Z(0xbd), Z(0x0e), Z(0x8f), Z(0xa3), Z(0xa9),
+	Z(0xbc), Z(0x74), Z(0xa6), Z(0xf6), Z(0x7f), Z(0x5f), Z(0xb1), Z(0x68),
+	Z(0x84), Z(0xbc), Z(0xa9), Z(0xfd), Z(0x55), Z(0x50), Z(0xe9), Z(0xb6),
+	Z(0x13), Z(0x5e), Z(0x07), Z(0xb8), Z(0x95), Z(0x02), Z(0xc0), Z(0xd0),
+	Z(0x6a), Z(0x1a), Z(0x85), Z(0xbd), Z(0xb6), Z(0xfd), Z(0xfe), Z(0x17),
+	Z(0x3f), Z(0x09), Z(0xa3), Z(0x8d), Z(0xfb), Z(0xed), Z(0xda), Z(0x1d),
+	Z(0x6d), Z(0x1c), Z(0x6c), Z(0x01), Z(0x5a), Z(0xe5), Z(0x71), Z(0x3e),
+	Z(0x8b), Z(0x6b), Z(0xbe), Z(0x29), Z(0xeb), Z(0x12), Z(0x19), Z(0x34),
+	Z(0xcd), Z(0xb3), Z(0xbd), Z(0x35), Z(0xea), Z(0x4b), Z(0xd5), Z(0xae),
+	Z(0x2a), Z(0x79), Z(0x5a), Z(0xa5), Z(0x32), Z(0x12), Z(0x7b), Z(0xdc),
+	Z(0x2c), Z(0xd0), Z(0x22), Z(0x4b), Z(0xb1), Z(0x85), Z(0x59), Z(0x80),
+	Z(0xc0), Z(0x30), Z(0x9f), Z(0x73), Z(0xd3), Z(0x14), Z(0x48), Z(0x40),
+	Z(0x07), Z(0x2d), Z(0x8f), Z(0x80), Z(0x0f), Z(0xce), Z(0x0b), Z(0x5e),
+	Z(0xb7), Z(0x5e), Z(0xac), Z(0x24), Z(0x94), Z(0x4a), Z(0x18), Z(0x15),
+	Z(0x05), Z(0xe8), Z(0x02), Z(0x77), Z(0xa9), Z(0xc7), Z(0x40), Z(0x45),
+	Z(0x89), Z(0xd1), Z(0xea), Z(0xde), Z(0x0c), Z(0x79), Z(0x2a), Z(0x99),
+	Z(0x6c), Z(0x3e), Z(0x95), Z(0xdd), Z(0x8c), Z(0x7d), Z(0xad), Z(0x6f),
+	Z(0xdc), Z(0xff), Z(0xfd), Z(0x62), Z(0x47), Z(0xb3), Z(0x21), Z(0x8a),
+	Z(0xec), Z(0x8e), Z(0x19), Z(0x18), Z(0xb4), Z(0x6e), Z(0x3d), Z(0xfd),
+	Z(0x74), Z(0x54), Z(0x1e), Z(0x04), Z(0x85), Z(0xd8), Z(0xbc), Z(0x1f),
+	Z(0x56), Z(0xe7), Z(0x3a), Z(0x56), Z(0x67), Z(0xd6), Z(0xc8), Z(0xa5),
+	Z(0xf3), Z(0x8e), Z(0xde), Z(0xae), Z(0x37), Z(0x49), Z(0xb7), Z(0xfa),
+	Z(0xc8), Z(0xf4), Z(0x1f), Z(0xe0), Z(0x2a), Z(0x9b), Z(0x15), Z(0xd1),
+	Z(0x34), Z(0x0e), Z(0xb5), Z(0xe0), Z(0x44), Z(0x78), Z(0x84), Z(0x59),
+	Z(0x56), Z(0x68), Z(0x77), Z(0xa5), Z(0x14), Z(0x06), Z(0xf5), Z(0x2f),
+	Z(0x8c), Z(0x8a), Z(0x73), Z(0x80), Z(0x76), Z(0xb4), Z(0x10), Z(0x86)
+};
+
+#undef Z
+#define Z(x) cpu_to_be32(x << 19)
+static const __be32 sbox3[256] = {
+	Z(0xa9), Z(0x2a), Z(0x48), Z(0x51), Z(0x84), Z(0x7e), Z(0x49), Z(0xe2),
+	Z(0xb5), Z(0xb7), Z(0x42), Z(0x33), Z(0x7d), Z(0x5d), Z(0xa6), Z(0x12),
+	Z(0x44), Z(0x48), Z(0x6d), Z(0x28), Z(0xaa), Z(0x20), Z(0x6d), Z(0x57),
+	Z(0xd6), Z(0x6b), Z(0x5d), Z(0x72), Z(0xf0), Z(0x92), Z(0x5a), Z(0x1b),
+	Z(0x53), Z(0x80), Z(0x24), Z(0x70), Z(0x9a), Z(0xcc), Z(0xa7), Z(0x66),
+	Z(0xa1), Z(0x01), Z(0xa5), Z(0x41), Z(0x97), Z(0x41), Z(0x31), Z(0x82),
+	Z(0xf1), Z(0x14), Z(0xcf), Z(0x53), Z(0x0d), Z(0xa0), Z(0x10), Z(0xcc),
+	Z(0x2a), Z(0x7d), Z(0xd2), Z(0xbf), Z(0x4b), Z(0x1a), Z(0xdb), Z(0x16),
+	Z(0x47), Z(0xf6), Z(0x51), Z(0x36), Z(0xed), Z(0xf3), Z(0xb9), Z(0x1a),
+	Z(0xa7), Z(0xdf), Z(0x29), Z(0x43), Z(0x01), Z(0x54), Z(0x70), Z(0xa4),
+	Z(0xbf), Z(0xd4), Z(0x0b), Z(0x53), Z(0x44), Z(0x60), Z(0x9e), Z(0x23),
+	Z(0xa1), Z(0x18), Z(0x68), Z(0x4f), Z(0xf0), Z(0x2f), Z(0x82), Z(0xc2),
+	Z(0x2a), Z(0x41), Z(0xb2), Z(0x42), Z(0x0c), Z(0xed), Z(0x0c), Z(0x1d),
+	Z(0x13), Z(0x3a), Z(0x3c), Z(0x6e), Z(0x35), Z(0xdc), Z(0x60), Z(0x65),
+	Z(0x85), Z(0xe9), Z(0x64), Z(0x02), Z(0x9a), Z(0x3f), Z(0x9f), Z(0x87),
+	Z(0x96), Z(0xdf), Z(0xbe), Z(0xf2), Z(0xcb), Z(0xe5), Z(0x6c), Z(0xd4),
+	Z(0x5a), Z(0x83), Z(0xbf), Z(0x92), Z(0x1b), Z(0x94), Z(0x00), Z(0x42),
+	Z(0xcf), Z(0x4b), Z(0x00), Z(0x75), Z(0xba), Z(0x8f), Z(0x76), Z(0x5f),
+	Z(0x5d), Z(0x3a), Z(0x4d), Z(0x09), Z(0x12), Z(0x08), Z(0x38), Z(0x95),
+	Z(0x17), Z(0xe4), Z(0x01), Z(0x1d), Z(0x4c), Z(0xa9), Z(0xcc), Z(0x85),
+	Z(0x82), Z(0x4c), Z(0x9d), Z(0x2f), Z(0x3b), Z(0x66), Z(0xa1), Z(0x34),
+	Z(0x10), Z(0xcd), Z(0x59), Z(0x89), Z(0xa5), Z(0x31), Z(0xcf), Z(0x05),
+	Z(0xc8), Z(0x84), Z(0xfa), Z(0xc7), Z(0xba), Z(0x4e), Z(0x8b), Z(0x1a),
+	Z(0x19), Z(0xf1), Z(0xa1), Z(0x3b), Z(0x18), Z(0x12), Z(0x17), Z(0xb0),
+	Z(0x98), Z(0x8d), Z(0x0b), Z(0x23), Z(0xc3), Z(0x3a), Z(0x2d), Z(0x20),
+	Z(0xdf), Z(0x13), Z(0xa0), Z(0xa8), Z(0x4c), Z(0x0d), Z(0x6c), Z(0x2f),
+	Z(0x47), Z(0x13), Z(0x13), Z(0x52), Z(0x1f), Z(0x2d), Z(0xf5), Z(0x79),
+	Z(0x3d), Z(0xa2), Z(0x54), Z(0xbd), Z(0x69), Z(0xc8), Z(0x6b), Z(0xf3),
+	Z(0x05), Z(0x28), Z(0xf1), Z(0x16), Z(0x46), Z(0x40), Z(0xb0), Z(0x11),
+	Z(0xd3), Z(0xb7), Z(0x95), Z(0x49), Z(0xcf), Z(0xc3), Z(0x1d), Z(0x8f),
+	Z(0xd8), Z(0xe1), Z(0x73), Z(0xdb), Z(0xad), Z(0xc8), Z(0xc9), Z(0xa9),
+	Z(0xa1), Z(0xc2), Z(0xc5), Z(0xe3), Z(0xba), Z(0xfc), Z(0x0e), Z(0x25)
+};
+
+/*
+ * This is a 16 round Feistel network with permutation F_ENCRYPT
+ */
+#define F_ENCRYPT(R, L, sched)						\
+do {									\
+	union lc4 { __be32 l; u8 c[4]; } u;				\
+	u.l = sched ^ R;						\
+	L ^= sbox0[u.c[0]] ^ sbox1[u.c[1]] ^ sbox2[u.c[2]] ^ sbox3[u.c[3]]; \
+} while (0)
+
+/*
+ * encryptor
+ */
+static void fcrypt_encrypt(struct crypto_tfm *tfm, u8 *dst, const u8 *src)
+{
+	const struct fcrypt_ctx *ctx = crypto_tfm_ctx(tfm);
+	struct {
+		__be32 l, r;
+	} X;
+
+	memcpy(&X, src, sizeof(X));
+
+	F_ENCRYPT(X.r, X.l, ctx->sched[0x0]);
+	F_ENCRYPT(X.l, X.r, ctx->sched[0x1]);
+	F_ENCRYPT(X.r, X.l, ctx->sched[0x2]);
+	F_ENCRYPT(X.l, X.r, ctx->sched[0x3]);
+	F_ENCRYPT(X.r, X.l, ctx->sched[0x4]);
+	F_ENCRYPT(X.l, X.r, ctx->sched[0x5]);
+	F_ENCRYPT(X.r, X.l, ctx->sched[0x6]);
+	F_ENCRYPT(X.l, X.r, ctx->sched[0x7]);
+	F_ENCRYPT(X.r, X.l, ctx->sched[0x8]);
+	F_ENCRYPT(X.l, X.r, ctx->sched[0x9]);
+	F_ENCRYPT(X.r, X.l, ctx->sched[0xa]);
+	F_ENCRYPT(X.l, X.r, ctx->sched[0xb]);
+	F_ENCRYPT(X.r, X.l, ctx->sched[0xc]);
+	F_ENCRYPT(X.l, X.r, ctx->sched[0xd]);
+	F_ENCRYPT(X.r, X.l, ctx->sched[0xe]);
+	F_ENCRYPT(X.l, X.r, ctx->sched[0xf]);
+
+	memcpy(dst, &X, sizeof(X));
+}
+
+/*
+ * decryptor
+ */
+static void fcrypt_decrypt(struct crypto_tfm *tfm, u8 *dst, const u8 *src)
+{
+	const struct fcrypt_ctx *ctx = crypto_tfm_ctx(tfm);
+	struct {
+		__be32 l, r;
+	} X;
+
+	memcpy(&X, src, sizeof(X));
+
+	F_ENCRYPT(X.l, X.r, ctx->sched[0xf]);
+	F_ENCRYPT(X.r, X.l, ctx->sched[0xe]);
+	F_ENCRYPT(X.l, X.r, ctx->sched[0xd]);
+	F_ENCRYPT(X.r, X.l, ctx->sched[0xc]);
+	F_ENCRYPT(X.l, X.r, ctx->sched[0xb]);
+	F_ENCRYPT(X.r, X.l, ctx->sched[0xa]);
+	F_ENCRYPT(X.l, X.r, ctx->sched[0x9]);
+	F_ENCRYPT(X.r, X.l, ctx->sched[0x8]);
+	F_ENCRYPT(X.l, X.r, ctx->sched[0x7]);
+	F_ENCRYPT(X.r, X.l, ctx->sched[0x6]);
+	F_ENCRYPT(X.l, X.r, ctx->sched[0x5]);
+	F_ENCRYPT(X.r, X.l, ctx->sched[0x4]);
+	F_ENCRYPT(X.l, X.r, ctx->sched[0x3]);
+	F_ENCRYPT(X.r, X.l, ctx->sched[0x2]);
+	F_ENCRYPT(X.l, X.r, ctx->sched[0x1]);
+	F_ENCRYPT(X.r, X.l, ctx->sched[0x0]);
+
+	memcpy(dst, &X, sizeof(X));
+}
+
+/*
+ * Generate a key schedule from key, the least significant bit in each key byte
+ * is parity and shall be ignored. This leaves 56 significant bits in the key
+ * to scatter over the 16 key schedules. For each schedule extract the low
+ * order 32 bits and use as schedule, then rotate right by 11 bits.
+ */
+static int fcrypt_setkey(struct crypto_tfm *tfm, const u8 *key, unsigned int keylen)
+{
+	struct fcrypt_ctx *ctx = crypto_tfm_ctx(tfm);
+
+#if BITS_PER_LONG == 64  /* the 64-bit version can also be used for 32-bit
+			  * kernels - it seems to be faster but the code is
+			  * larger */
+
+	u64 k;	/* k holds all 56 non-parity bits */
+
+	/* discard the parity bits */
+	k = (*key++) >> 1;
+	k <<= 7;
+	k |= (*key++) >> 1;
+	k <<= 7;
+	k |= (*key++) >> 1;
+	k <<= 7;
+	k |= (*key++) >> 1;
+	k <<= 7;
+	k |= (*key++) >> 1;
+	k <<= 7;
+	k |= (*key++) >> 1;
+	k <<= 7;
+	k |= (*key++) >> 1;
+	k <<= 7;
+	k |= (*key) >> 1;
+
+	/* Use lower 32 bits for schedule, rotate by 11 each round (16 times) */
+	ctx->sched[0x0] = cpu_to_be32(k); ror56_64(k, 11);
+	ctx->sched[0x1] = cpu_to_be32(k); ror56_64(k, 11);
+	ctx->sched[0x2] = cpu_to_be32(k); ror56_64(k, 11);
+	ctx->sched[0x3] = cpu_to_be32(k); ror56_64(k, 11);
+	ctx->sched[0x4] = cpu_to_be32(k); ror56_64(k, 11);
+	ctx->sched[0x5] = cpu_to_be32(k); ror56_64(k, 11);
+	ctx->sched[0x6] = cpu_to_be32(k); ror56_64(k, 11);
+	ctx->sched[0x7] = cpu_to_be32(k); ror56_64(k, 11);
+	ctx->sched[0x8] = cpu_to_be32(k); ror56_64(k, 11);
+	ctx->sched[0x9] = cpu_to_be32(k); ror56_64(k, 11);
+	ctx->sched[0xa] = cpu_to_be32(k); ror56_64(k, 11);
+	ctx->sched[0xb] = cpu_to_be32(k); ror56_64(k, 11);
+	ctx->sched[0xc] = cpu_to_be32(k); ror56_64(k, 11);
+	ctx->sched[0xd] = cpu_to_be32(k); ror56_64(k, 11);
+	ctx->sched[0xe] = cpu_to_be32(k); ror56_64(k, 11);
+	ctx->sched[0xf] = cpu_to_be32(k);
+
+	return 0;
+#else
+	u32 hi, lo;		/* hi is upper 24 bits and lo lower 32, total 56 */
+
+	/* discard the parity bits */
+	lo = (*key++) >> 1;
+	lo <<= 7;
+	lo |= (*key++) >> 1;
+	lo <<= 7;
+	lo |= (*key++) >> 1;
+	lo <<= 7;
+	lo |= (*key++) >> 1;
+	hi = lo >> 4;
+	lo &= 0xf;
+	lo <<= 7;
+	lo |= (*key++) >> 1;
+	lo <<= 7;
+	lo |= (*key++) >> 1;
+	lo <<= 7;
+	lo |= (*key++) >> 1;
+	lo <<= 7;
+	lo |= (*key) >> 1;
+
+	/* Use lower 32 bits for schedule, rotate by 11 each round (16 times) */
+	ctx->sched[0x0] = cpu_to_be32(lo); ror56(hi, lo, 11);
+	ctx->sched[0x1] = cpu_to_be32(lo); ror56(hi, lo, 11);
+	ctx->sched[0x2] = cpu_to_be32(lo); ror56(hi, lo, 11);
+	ctx->sched[0x3] = cpu_to_be32(lo); ror56(hi, lo, 11);
+	ctx->sched[0x4] = cpu_to_be32(lo); ror56(hi, lo, 11);
+	ctx->sched[0x5] = cpu_to_be32(lo); ror56(hi, lo, 11);
+	ctx->sched[0x6] = cpu_to_be32(lo); ror56(hi, lo, 11);
+	ctx->sched[0x7] = cpu_to_be32(lo); ror56(hi, lo, 11);
+	ctx->sched[0x8] = cpu_to_be32(lo); ror56(hi, lo, 11);
+	ctx->sched[0x9] = cpu_to_be32(lo); ror56(hi, lo, 11);
+	ctx->sched[0xa] = cpu_to_be32(lo); ror56(hi, lo, 11);
+	ctx->sched[0xb] = cpu_to_be32(lo); ror56(hi, lo, 11);
+	ctx->sched[0xc] = cpu_to_be32(lo); ror56(hi, lo, 11);
+	ctx->sched[0xd] = cpu_to_be32(lo); ror56(hi, lo, 11);
+	ctx->sched[0xe] = cpu_to_be32(lo); ror56(hi, lo, 11);
+	ctx->sched[0xf] = cpu_to_be32(lo);
+	return 0;
+#endif
+}
+
+static struct crypto_alg fcrypt_alg = {
+	.cra_name		=	"fcrypt",
+	.cra_driver_name	=	"fcrypt-generic",
+	.cra_flags		=	CRYPTO_ALG_TYPE_CIPHER,
+	.cra_blocksize		=	8,
+	.cra_ctxsize		=	sizeof(struct fcrypt_ctx),
+	.cra_module		=	THIS_MODULE,
+	.cra_u			=	{ .cipher = {
+	.cia_min_keysize	=	8,
+	.cia_max_keysize	=	8,
+	.cia_setkey		=	fcrypt_setkey,
+	.cia_encrypt		=	fcrypt_encrypt,
+	.cia_decrypt		=	fcrypt_decrypt } }
+};
+
+static int __init fcrypt_mod_init(void)
+{
+	return crypto_register_alg(&fcrypt_alg);
+}
+
+static void __exit fcrypt_mod_fini(void)
+{
+	crypto_unregister_alg(&fcrypt_alg);
+}
+
+subsys_initcall(fcrypt_mod_init);
+module_exit(fcrypt_mod_fini);
+
+MODULE_LICENSE("Dual BSD/GPL");
+MODULE_DESCRIPTION("FCrypt Cipher Algorithm");
+MODULE_AUTHOR("David Howells <dhowells@redhat.com>");
+MODULE_ALIAS_CRYPTO("fcrypt");