From 5b7c4cabbb65f5c469464da6c5f614cbd7f730f2 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Tue, 21 Feb 2023 18:24:12 -0800 Subject: Merge tag 'net-next-6.3' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next 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(). ... --- arch/arm64/crypto/sm4-neon-core.S | 679 ++++++++++++++++++++++++++++++++++++++ 1 file changed, 679 insertions(+) create mode 100644 arch/arm64/crypto/sm4-neon-core.S (limited to 'arch/arm64/crypto/sm4-neon-core.S') diff --git a/arch/arm64/crypto/sm4-neon-core.S b/arch/arm64/crypto/sm4-neon-core.S new file mode 100644 index 000000000..f295b4b7d --- /dev/null +++ b/arch/arm64/crypto/sm4-neon-core.S @@ -0,0 +1,679 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* + * SM4 Cipher Algorithm for ARMv8 NEON + * as specified in + * https://tools.ietf.org/id/draft-ribose-cfrg-sm4-10.html + * + * Copyright (C) 2022, Alibaba Group. + * Copyright (C) 2022 Tianjia Zhang + */ + +#include +#include + +/* Register macros */ + +#define RTMP0 v8 +#define RTMP1 v9 +#define RTMP2 v10 +#define RTMP3 v11 + +#define RTMP4 v12 +#define RTMP5 v13 +#define RTMP6 v14 +#define RTMP7 v15 + +#define RX0 v12 +#define RX1 v13 +#define RKEY v14 +#define RIV v15 + +/* Helper macros. */ + +#define SM4_PREPARE() \ + adr_l x5, crypto_sm4_sbox; \ + ld1 {v16.16b-v19.16b}, [x5], #64; \ + ld1 {v20.16b-v23.16b}, [x5], #64; \ + ld1 {v24.16b-v27.16b}, [x5], #64; \ + ld1 {v28.16b-v31.16b}, [x5]; + +#define transpose_4x4(s0, s1, s2, s3) \ + zip1 RTMP0.4s, s0.4s, s1.4s; \ + zip1 RTMP1.4s, s2.4s, s3.4s; \ + zip2 RTMP2.4s, s0.4s, s1.4s; \ + zip2 RTMP3.4s, s2.4s, s3.4s; \ + zip1 s0.2d, RTMP0.2d, RTMP1.2d; \ + zip2 s1.2d, RTMP0.2d, RTMP1.2d; \ + zip1 s2.2d, RTMP2.2d, RTMP3.2d; \ + zip2 s3.2d, RTMP2.2d, RTMP3.2d; + +#define transpose_4x4_2x(s0, s1, s2, s3, s4, s5, s6, s7) \ + zip1 RTMP0.4s, s0.4s, s1.4s; \ + zip1 RTMP1.4s, s2.4s, s3.4s; \ + zip2 RTMP2.4s, s0.4s, s1.4s; \ + zip2 RTMP3.4s, s2.4s, s3.4s; \ + zip1 RTMP4.4s, s4.4s, s5.4s; \ + zip1 RTMP5.4s, s6.4s, s7.4s; \ + zip2 RTMP6.4s, s4.4s, s5.4s; \ + zip2 RTMP7.4s, s6.4s, s7.4s; \ + zip1 s0.2d, RTMP0.2d, RTMP1.2d; \ + zip2 s1.2d, RTMP0.2d, RTMP1.2d; \ + zip1 s2.2d, RTMP2.2d, RTMP3.2d; \ + zip2 s3.2d, RTMP2.2d, RTMP3.2d; \ + zip1 s4.2d, RTMP4.2d, RTMP5.2d; \ + zip2 s5.2d, RTMP4.2d, RTMP5.2d; \ + zip1 s6.2d, RTMP6.2d, RTMP7.2d; \ + zip2 s7.2d, RTMP6.2d, RTMP7.2d; + +#define rotate_clockwise_4x4(s0, s1, s2, s3) \ + zip1 RTMP0.4s, s1.4s, s0.4s; \ + zip2 RTMP1.4s, s1.4s, s0.4s; \ + zip1 RTMP2.4s, s3.4s, s2.4s; \ + zip2 RTMP3.4s, s3.4s, s2.4s; \ + zip1 s0.2d, RTMP2.2d, RTMP0.2d; \ + zip2 s1.2d, RTMP2.2d, RTMP0.2d; \ + zip1 s2.2d, RTMP3.2d, RTMP1.2d; \ + zip2 s3.2d, RTMP3.2d, RTMP1.2d; + +#define rotate_clockwise_4x4_2x(s0, s1, s2, s3, s4, s5, s6, s7) \ + zip1 RTMP0.4s, s1.4s, s0.4s; \ + zip1 RTMP2.4s, s3.4s, s2.4s; \ + zip2 RTMP1.4s, s1.4s, s0.4s; \ + zip2 RTMP3.4s, s3.4s, s2.4s; \ + zip1 RTMP4.4s, s5.4s, s4.4s; \ + zip1 RTMP6.4s, s7.4s, s6.4s; \ + zip2 RTMP5.4s, s5.4s, s4.4s; \ + zip2 RTMP7.4s, s7.4s, s6.4s; \ + zip1 s0.2d, RTMP2.2d, RTMP0.2d; \ + zip2 s1.2d, RTMP2.2d, RTMP0.2d; \ + zip1 s2.2d, RTMP3.2d, RTMP1.2d; \ + zip2 s3.2d, RTMP3.2d, RTMP1.2d; \ + zip1 s4.2d, RTMP6.2d, RTMP4.2d; \ + zip2 s5.2d, RTMP6.2d, RTMP4.2d; \ + zip1 s6.2d, RTMP7.2d, RTMP5.2d; \ + zip2 s7.2d, RTMP7.2d, RTMP5.2d; + +#define ROUND4(round, s0, s1, s2, s3) \ + dup RX0.4s, RKEY.s[round]; \ + /* rk ^ s1 ^ s2 ^ s3 */ \ + eor RTMP1.16b, s2.16b, s3.16b; \ + eor RX0.16b, RX0.16b, s1.16b; \ + eor RX0.16b, RX0.16b, RTMP1.16b; \ + \ + /* sbox, non-linear part */ \ + movi RTMP3.16b, #64; /* sizeof(sbox) / 4 */ \ + tbl RTMP0.16b, {v16.16b-v19.16b}, RX0.16b; \ + sub RX0.16b, RX0.16b, RTMP3.16b; \ + tbx RTMP0.16b, {v20.16b-v23.16b}, RX0.16b; \ + sub RX0.16b, RX0.16b, RTMP3.16b; \ + tbx RTMP0.16b, {v24.16b-v27.16b}, RX0.16b; \ + sub RX0.16b, RX0.16b, RTMP3.16b; \ + tbx RTMP0.16b, {v28.16b-v31.16b}, RX0.16b; \ + \ + /* linear part */ \ + shl RTMP1.4s, RTMP0.4s, #8; \ + shl RTMP2.4s, RTMP0.4s, #16; \ + shl RTMP3.4s, RTMP0.4s, #24; \ + sri RTMP1.4s, RTMP0.4s, #(32-8); \ + sri RTMP2.4s, RTMP0.4s, #(32-16); \ + sri RTMP3.4s, RTMP0.4s, #(32-24); \ + /* RTMP1 = x ^ rol32(x, 8) ^ rol32(x, 16) */ \ + eor RTMP1.16b, RTMP1.16b, RTMP0.16b; \ + eor RTMP1.16b, RTMP1.16b, RTMP2.16b; \ + /* RTMP3 = x ^ rol32(x, 24) ^ rol32(RTMP1, 2) */ \ + eor RTMP3.16b, RTMP3.16b, RTMP0.16b; \ + shl RTMP2.4s, RTMP1.4s, 2; \ + sri RTMP2.4s, RTMP1.4s, #(32-2); \ + eor RTMP3.16b, RTMP3.16b, RTMP2.16b; \ + /* s0 ^= RTMP3 */ \ + eor s0.16b, s0.16b, RTMP3.16b; + +#define SM4_CRYPT_BLK4_BE(b0, b1, b2, b3) \ + mov x6, 8; \ +4: \ + ld1 {RKEY.4s}, [x0], #16; \ + subs x6, x6, #1; \ + \ + ROUND4(0, b0, b1, b2, b3); \ + ROUND4(1, b1, b2, b3, b0); \ + ROUND4(2, b2, b3, b0, b1); \ + ROUND4(3, b3, b0, b1, b2); \ + \ + bne 4b; \ + \ + rev32 b0.16b, b0.16b; \ + rev32 b1.16b, b1.16b; \ + rev32 b2.16b, b2.16b; \ + rev32 b3.16b, b3.16b; \ + \ + rotate_clockwise_4x4(b0, b1, b2, b3); \ + \ + /* repoint to rkey */ \ + sub x0, x0, #128; + +#define SM4_CRYPT_BLK4(b0, b1, b2, b3) \ + rev32 b0.16b, b0.16b; \ + rev32 b1.16b, b1.16b; \ + rev32 b2.16b, b2.16b; \ + rev32 b3.16b, b3.16b; \ + SM4_CRYPT_BLK4_BE(b0, b1, b2, b3); + +#define ROUND8(round, s0, s1, s2, s3, t0, t1, t2, t3) \ + /* rk ^ s1 ^ s2 ^ s3 */ \ + dup RX0.4s, RKEY.s[round]; \ + eor RTMP0.16b, s2.16b, s3.16b; \ + mov RX1.16b, RX0.16b; \ + eor RTMP1.16b, t2.16b, t3.16b; \ + eor RX0.16b, RX0.16b, s1.16b; \ + eor RX1.16b, RX1.16b, t1.16b; \ + eor RX0.16b, RX0.16b, RTMP0.16b; \ + eor RX1.16b, RX1.16b, RTMP1.16b; \ + \ + /* sbox, non-linear part */ \ + movi RTMP3.16b, #64; /* sizeof(sbox) / 4 */ \ + tbl RTMP0.16b, {v16.16b-v19.16b}, RX0.16b; \ + tbl RTMP1.16b, {v16.16b-v19.16b}, RX1.16b; \ + sub RX0.16b, RX0.16b, RTMP3.16b; \ + sub RX1.16b, RX1.16b, RTMP3.16b; \ + tbx RTMP0.16b, {v20.16b-v23.16b}, RX0.16b; \ + tbx RTMP1.16b, {v20.16b-v23.16b}, RX1.16b; \ + sub RX0.16b, RX0.16b, RTMP3.16b; \ + sub RX1.16b, RX1.16b, RTMP3.16b; \ + tbx RTMP0.16b, {v24.16b-v27.16b}, RX0.16b; \ + tbx RTMP1.16b, {v24.16b-v27.16b}, RX1.16b; \ + sub RX0.16b, RX0.16b, RTMP3.16b; \ + sub RX1.16b, RX1.16b, RTMP3.16b; \ + tbx RTMP0.16b, {v28.16b-v31.16b}, RX0.16b; \ + tbx RTMP1.16b, {v28.16b-v31.16b}, RX1.16b; \ + \ + /* linear part */ \ + shl RX0.4s, RTMP0.4s, #8; \ + shl RX1.4s, RTMP1.4s, #8; \ + shl RTMP2.4s, RTMP0.4s, #16; \ + shl RTMP3.4s, RTMP1.4s, #16; \ + sri RX0.4s, RTMP0.4s, #(32 - 8); \ + sri RX1.4s, RTMP1.4s, #(32 - 8); \ + sri RTMP2.4s, RTMP0.4s, #(32 - 16); \ + sri RTMP3.4s, RTMP1.4s, #(32 - 16); \ + /* RX = x ^ rol32(x, 8) ^ rol32(x, 16) */ \ + eor RX0.16b, RX0.16b, RTMP0.16b; \ + eor RX1.16b, RX1.16b, RTMP1.16b; \ + eor RX0.16b, RX0.16b, RTMP2.16b; \ + eor RX1.16b, RX1.16b, RTMP3.16b; \ + /* RTMP0/1 ^= x ^ rol32(x, 24) ^ rol32(RX, 2) */ \ + shl RTMP2.4s, RTMP0.4s, #24; \ + shl RTMP3.4s, RTMP1.4s, #24; \ + sri RTMP2.4s, RTMP0.4s, #(32 - 24); \ + sri RTMP3.4s, RTMP1.4s, #(32 - 24); \ + eor RTMP0.16b, RTMP0.16b, RTMP2.16b; \ + eor RTMP1.16b, RTMP1.16b, RTMP3.16b; \ + shl RTMP2.4s, RX0.4s, #2; \ + shl RTMP3.4s, RX1.4s, #2; \ + sri RTMP2.4s, RX0.4s, #(32 - 2); \ + sri RTMP3.4s, RX1.4s, #(32 - 2); \ + eor RTMP0.16b, RTMP0.16b, RTMP2.16b; \ + eor RTMP1.16b, RTMP1.16b, RTMP3.16b; \ + /* s0/t0 ^= RTMP0/1 */ \ + eor s0.16b, s0.16b, RTMP0.16b; \ + eor t0.16b, t0.16b, RTMP1.16b; + +#define SM4_CRYPT_BLK8_norotate(b0, b1, b2, b3, b4, b5, b6, b7) \ + rev32 b0.16b, b0.16b; \ + rev32 b1.16b, b1.16b; \ + rev32 b2.16b, b2.16b; \ + rev32 b3.16b, b3.16b; \ + rev32 b4.16b, b4.16b; \ + rev32 b5.16b, b5.16b; \ + rev32 b6.16b, b6.16b; \ + rev32 b7.16b, b7.16b; \ + \ + mov x6, 8; \ +8: \ + ld1 {RKEY.4s}, [x0], #16; \ + subs x6, x6, #1; \ + \ + ROUND8(0, b0, b1, b2, b3, b4, b5, b6, b7); \ + ROUND8(1, b1, b2, b3, b0, b5, b6, b7, b4); \ + ROUND8(2, b2, b3, b0, b1, b6, b7, b4, b5); \ + ROUND8(3, b3, b0, b1, b2, b7, b4, b5, b6); \ + \ + bne 8b; \ + \ + rev32 b0.16b, b0.16b; \ + rev32 b1.16b, b1.16b; \ + rev32 b2.16b, b2.16b; \ + rev32 b3.16b, b3.16b; \ + rev32 b4.16b, b4.16b; \ + rev32 b5.16b, b5.16b; \ + rev32 b6.16b, b6.16b; \ + rev32 b7.16b, b7.16b; \ + \ + /* repoint to rkey */ \ + sub x0, x0, #128; + +#define SM4_CRYPT_BLK8(b0, b1, b2, b3, b4, b5, b6, b7) \ + SM4_CRYPT_BLK8_norotate(b0, b1, b2, b3, b4, b5, b6, b7); \ + rotate_clockwise_4x4_2x(b0, b1, b2, b3, b4, b5, b6, b7); \ + + +.align 3 +SYM_FUNC_START(sm4_neon_crypt) + /* input: + * x0: round key array, CTX + * x1: dst + * x2: src + * w3: nblocks + */ + SM4_PREPARE() + +.Lcrypt_loop_8x: + sub w3, w3, #8 + tbnz w3, #31, .Lcrypt_4x + + ld4 {v0.4s-v3.4s}, [x2], #64 + ld4 {v4.4s-v7.4s}, [x2], #64 + + SM4_CRYPT_BLK8(v0, v1, v2, v3, v4, v5, v6, v7) + + st1 {v0.16b-v3.16b}, [x1], #64 + st1 {v4.16b-v7.16b}, [x1], #64 + + cbz w3, .Lcrypt_end + b .Lcrypt_loop_8x + +.Lcrypt_4x: + add w3, w3, #8 + cmp w3, #4 + blt .Lcrypt_tail + + sub w3, w3, #4 + + ld4 {v0.4s-v3.4s}, [x2], #64 + + SM4_CRYPT_BLK4(v0, v1, v2, v3) + + st1 {v0.16b-v3.16b}, [x1], #64 + + cbz w3, .Lcrypt_end + +.Lcrypt_tail: + cmp w3, #2 + ld1 {v0.16b}, [x2], #16 + blt .Lcrypt_tail_load_done + ld1 {v1.16b}, [x2], #16 + beq .Lcrypt_tail_load_done + ld1 {v2.16b}, [x2], #16 + +.Lcrypt_tail_load_done: + transpose_4x4(v0, v1, v2, v3) + + SM4_CRYPT_BLK4(v0, v1, v2, v3) + + cmp w3, #2 + st1 {v0.16b}, [x1], #16 + blt .Lcrypt_end + st1 {v1.16b}, [x1], #16 + beq .Lcrypt_end + st1 {v2.16b}, [x1], #16 + +.Lcrypt_end: + ret +SYM_FUNC_END(sm4_neon_crypt) + +.align 3 +SYM_FUNC_START(sm4_neon_cbc_dec) + /* input: + * x0: round key array, CTX + * x1: dst + * x2: src + * x3: iv (big endian, 128 bit) + * w4: nblocks + */ + SM4_PREPARE() + + ld1 {RIV.16b}, [x3] + +.Lcbc_dec_loop_8x: + sub w4, w4, #8 + tbnz w4, #31, .Lcbc_dec_4x + + ld4 {v0.4s-v3.4s}, [x2], #64 + ld4 {v4.4s-v7.4s}, [x2] + + SM4_CRYPT_BLK8_norotate(v0, v1, v2, v3, v4, v5, v6, v7) + + /* Avoid overwriting the RIV register */ + rotate_clockwise_4x4(v0, v1, v2, v3) + rotate_clockwise_4x4(v4, v5, v6, v7) + + sub x2, x2, #64 + + eor v0.16b, v0.16b, RIV.16b + + ld1 {RTMP0.16b-RTMP3.16b}, [x2], #64 + ld1 {RTMP4.16b-RTMP7.16b}, [x2], #64 + + eor v1.16b, v1.16b, RTMP0.16b + eor v2.16b, v2.16b, RTMP1.16b + eor v3.16b, v3.16b, RTMP2.16b + eor v4.16b, v4.16b, RTMP3.16b + eor v5.16b, v5.16b, RTMP4.16b + eor v6.16b, v6.16b, RTMP5.16b + eor v7.16b, v7.16b, RTMP6.16b + + mov RIV.16b, RTMP7.16b + + st1 {v0.16b-v3.16b}, [x1], #64 + st1 {v4.16b-v7.16b}, [x1], #64 + + cbz w4, .Lcbc_dec_end + b .Lcbc_dec_loop_8x + +.Lcbc_dec_4x: + add w4, w4, #8 + cmp w4, #4 + blt .Lcbc_dec_tail + + sub w4, w4, #4 + + ld1 {v0.16b-v3.16b}, [x2], #64 + + rev32 v4.16b, v0.16b + rev32 v5.16b, v1.16b + rev32 v6.16b, v2.16b + rev32 v7.16b, v3.16b + + transpose_4x4(v4, v5, v6, v7) + + SM4_CRYPT_BLK4_BE(v4, v5, v6, v7) + + eor v4.16b, v4.16b, RIV.16b + eor v5.16b, v5.16b, v0.16b + eor v6.16b, v6.16b, v1.16b + eor v7.16b, v7.16b, v2.16b + + mov RIV.16b, v3.16b + + st1 {v4.16b-v7.16b}, [x1], #64 + + cbz w4, .Lcbc_dec_end + +.Lcbc_dec_tail: + cmp w4, #2 + ld1 {v0.16b}, [x2], #16 + blt .Lcbc_dec_tail_load_done + ld1 {v1.16b}, [x2], #16 + beq .Lcbc_dec_tail_load_done + ld1 {v2.16b}, [x2], #16 + +.Lcbc_dec_tail_load_done: + rev32 v4.16b, v0.16b + rev32 v5.16b, v1.16b + rev32 v6.16b, v2.16b + + transpose_4x4(v4, v5, v6, v7) + + SM4_CRYPT_BLK4_BE(v4, v5, v6, v7) + + cmp w4, #2 + eor v4.16b, v4.16b, RIV.16b + mov RIV.16b, v0.16b + st1 {v4.16b}, [x1], #16 + blt .Lcbc_dec_end + + eor v5.16b, v5.16b, v0.16b + mov RIV.16b, v1.16b + st1 {v5.16b}, [x1], #16 + beq .Lcbc_dec_end + + eor v6.16b, v6.16b, v1.16b + mov RIV.16b, v2.16b + st1 {v6.16b}, [x1], #16 + +.Lcbc_dec_end: + /* store new IV */ + st1 {RIV.16b}, [x3] + + ret +SYM_FUNC_END(sm4_neon_cbc_dec) + +.align 3 +SYM_FUNC_START(sm4_neon_cfb_dec) + /* input: + * x0: round key array, CTX + * x1: dst + * x2: src + * x3: iv (big endian, 128 bit) + * w4: nblocks + */ + SM4_PREPARE() + + ld1 {v0.16b}, [x3] + +.Lcfb_dec_loop_8x: + sub w4, w4, #8 + tbnz w4, #31, .Lcfb_dec_4x + + ld1 {v1.16b-v3.16b}, [x2], #48 + ld4 {v4.4s-v7.4s}, [x2] + + transpose_4x4(v0, v1, v2, v3) + + SM4_CRYPT_BLK8(v0, v1, v2, v3, v4, v5, v6, v7) + + sub x2, x2, #48 + ld1 {RTMP0.16b-RTMP3.16b}, [x2], #64 + ld1 {RTMP4.16b-RTMP7.16b}, [x2], #64 + + eor v0.16b, v0.16b, RTMP0.16b + eor v1.16b, v1.16b, RTMP1.16b + eor v2.16b, v2.16b, RTMP2.16b + eor v3.16b, v3.16b, RTMP3.16b + eor v4.16b, v4.16b, RTMP4.16b + eor v5.16b, v5.16b, RTMP5.16b + eor v6.16b, v6.16b, RTMP6.16b + eor v7.16b, v7.16b, RTMP7.16b + + st1 {v0.16b-v3.16b}, [x1], #64 + st1 {v4.16b-v7.16b}, [x1], #64 + + mov v0.16b, RTMP7.16b + + cbz w4, .Lcfb_dec_end + b .Lcfb_dec_loop_8x + +.Lcfb_dec_4x: + add w4, w4, #8 + cmp w4, #4 + blt .Lcfb_dec_tail + + sub w4, w4, #4 + + ld1 {v4.16b-v7.16b}, [x2], #64 + + rev32 v0.16b, v0.16b /* v0 is IV register */ + rev32 v1.16b, v4.16b + rev32 v2.16b, v5.16b + rev32 v3.16b, v6.16b + + transpose_4x4(v0, v1, v2, v3) + + SM4_CRYPT_BLK4_BE(v0, v1, v2, v3) + + eor v0.16b, v0.16b, v4.16b + eor v1.16b, v1.16b, v5.16b + eor v2.16b, v2.16b, v6.16b + eor v3.16b, v3.16b, v7.16b + + st1 {v0.16b-v3.16b}, [x1], #64 + + mov v0.16b, v7.16b + + cbz w4, .Lcfb_dec_end + +.Lcfb_dec_tail: + cmp w4, #2 + ld1 {v4.16b}, [x2], #16 + blt .Lcfb_dec_tail_load_done + ld1 {v5.16b}, [x2], #16 + beq .Lcfb_dec_tail_load_done + ld1 {v6.16b}, [x2], #16 + +.Lcfb_dec_tail_load_done: + rev32 v0.16b, v0.16b /* v0 is IV register */ + rev32 v1.16b, v4.16b + rev32 v2.16b, v5.16b + + transpose_4x4(v0, v1, v2, v3) + + SM4_CRYPT_BLK4_BE(v0, v1, v2, v3) + + cmp w4, #2 + eor v0.16b, v0.16b, v4.16b + st1 {v0.16b}, [x1], #16 + mov v0.16b, v4.16b + blt .Lcfb_dec_end + + eor v1.16b, v1.16b, v5.16b + st1 {v1.16b}, [x1], #16 + mov v0.16b, v5.16b + beq .Lcfb_dec_end + + eor v2.16b, v2.16b, v6.16b + st1 {v2.16b}, [x1], #16 + mov v0.16b, v6.16b + +.Lcfb_dec_end: + /* store new IV */ + st1 {v0.16b}, [x3] + + ret +SYM_FUNC_END(sm4_neon_cfb_dec) + +.align 3 +SYM_FUNC_START(sm4_neon_ctr_crypt) + /* input: + * x0: round key array, CTX + * x1: dst + * x2: src + * x3: ctr (big endian, 128 bit) + * w4: nblocks + */ + SM4_PREPARE() + + ldp x7, x8, [x3] + rev x7, x7 + rev x8, x8 + +.Lctr_crypt_loop_8x: + sub w4, w4, #8 + tbnz w4, #31, .Lctr_crypt_4x + +#define inc_le128(vctr) \ + mov vctr.d[1], x8; \ + mov vctr.d[0], x7; \ + adds x8, x8, #1; \ + rev64 vctr.16b, vctr.16b; \ + adc x7, x7, xzr; + + /* construct CTRs */ + inc_le128(v0) /* +0 */ + inc_le128(v1) /* +1 */ + inc_le128(v2) /* +2 */ + inc_le128(v3) /* +3 */ + inc_le128(v4) /* +4 */ + inc_le128(v5) /* +5 */ + inc_le128(v6) /* +6 */ + inc_le128(v7) /* +7 */ + + transpose_4x4_2x(v0, v1, v2, v3, v4, v5, v6, v7) + + SM4_CRYPT_BLK8(v0, v1, v2, v3, v4, v5, v6, v7) + + ld1 {RTMP0.16b-RTMP3.16b}, [x2], #64 + ld1 {RTMP4.16b-RTMP7.16b}, [x2], #64 + + eor v0.16b, v0.16b, RTMP0.16b + eor v1.16b, v1.16b, RTMP1.16b + eor v2.16b, v2.16b, RTMP2.16b + eor v3.16b, v3.16b, RTMP3.16b + eor v4.16b, v4.16b, RTMP4.16b + eor v5.16b, v5.16b, RTMP5.16b + eor v6.16b, v6.16b, RTMP6.16b + eor v7.16b, v7.16b, RTMP7.16b + + st1 {v0.16b-v3.16b}, [x1], #64 + st1 {v4.16b-v7.16b}, [x1], #64 + + cbz w4, .Lctr_crypt_end + b .Lctr_crypt_loop_8x + +.Lctr_crypt_4x: + add w4, w4, #8 + cmp w4, #4 + blt .Lctr_crypt_tail + + sub w4, w4, #4 + + /* construct CTRs */ + inc_le128(v0) /* +0 */ + inc_le128(v1) /* +1 */ + inc_le128(v2) /* +2 */ + inc_le128(v3) /* +3 */ + + ld1 {v4.16b-v7.16b}, [x2], #64 + + transpose_4x4(v0, v1, v2, v3) + + SM4_CRYPT_BLK4(v0, v1, v2, v3) + + eor v0.16b, v0.16b, v4.16b + eor v1.16b, v1.16b, v5.16b + eor v2.16b, v2.16b, v6.16b + eor v3.16b, v3.16b, v7.16b + + st1 {v0.16b-v3.16b}, [x1], #64 + + cbz w4, .Lctr_crypt_end + +.Lctr_crypt_tail: + /* inc_le128 will change the sign bit */ + ld1 {v4.16b}, [x2], #16 + inc_le128(v0) + cmp w4, #2 + blt .Lctr_crypt_tail_load_done + + ld1 {v5.16b}, [x2], #16 + inc_le128(v1) + cmp w4, #2 + beq .Lctr_crypt_tail_load_done + + ld1 {v6.16b}, [x2], #16 + inc_le128(v2) + +.Lctr_crypt_tail_load_done: + transpose_4x4(v0, v1, v2, v3) + + SM4_CRYPT_BLK4(v0, v1, v2, v3) + + cmp w4, #2 + + eor v0.16b, v0.16b, v4.16b + st1 {v0.16b}, [x1], #16 + blt .Lctr_crypt_end + + eor v1.16b, v1.16b, v5.16b + st1 {v1.16b}, [x1], #16 + beq .Lctr_crypt_end + + eor v2.16b, v2.16b, v6.16b + st1 {v2.16b}, [x1], #16 + +.Lctr_crypt_end: + /* store new CTR */ + rev x7, x7 + rev x8, x8 + stp x7, x8, [x3] + + ret +SYM_FUNC_END(sm4_neon_ctr_crypt) -- cgit v1.2.3