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, 496 insertions, 0 deletions

diff --git a/arch/x86/crypto/sm4-aesni-avx2-asm_64.S b/arch/x86/crypto/sm4-aesni-avx2-asm_64.S
new file mode 100644
index 000000000..98ede9459
--- /dev/null
+++ b/arch/x86/crypto/sm4-aesni-avx2-asm_64.S
@@ -0,0 +1,496 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * SM4 Cipher Algorithm, AES-NI/AVX2 optimized.
+ * as specified in
+ * https://tools.ietf.org/id/draft-ribose-cfrg-sm4-10.html
+ *
+ * Copyright (C) 2018 Markku-Juhani O. Saarinen <mjos@iki.fi>
+ * Copyright (C) 2020 Jussi Kivilinna <jussi.kivilinna@iki.fi>
+ * Copyright (c) 2021 Tianjia Zhang <tianjia.zhang@linux.alibaba.com>
+ */
+
+/* Based on SM4 AES-NI work by libgcrypt and Markku-Juhani O. Saarinen at:
+ *  https://github.com/mjosaarinen/sm4ni
+ */
+
+#include <linux/linkage.h>
+#include <linux/cfi_types.h>
+#include <asm/frame.h>
+
+#define rRIP         (%rip)
+
+/* vector registers */
+#define RX0          %ymm0
+#define RX1          %ymm1
+#define MASK_4BIT    %ymm2
+#define RTMP0        %ymm3
+#define RTMP1        %ymm4
+#define RTMP2        %ymm5
+#define RTMP3        %ymm6
+#define RTMP4        %ymm7
+
+#define RA0          %ymm8
+#define RA1          %ymm9
+#define RA2          %ymm10
+#define RA3          %ymm11
+
+#define RB0          %ymm12
+#define RB1          %ymm13
+#define RB2          %ymm14
+#define RB3          %ymm15
+
+#define RNOT         %ymm0
+#define RBSWAP       %ymm1
+
+#define RX0x         %xmm0
+#define RX1x         %xmm1
+#define MASK_4BITx   %xmm2
+
+#define RNOTx        %xmm0
+#define RBSWAPx      %xmm1
+
+#define RTMP0x       %xmm3
+#define RTMP1x       %xmm4
+#define RTMP2x       %xmm5
+#define RTMP3x       %xmm6
+#define RTMP4x       %xmm7
+
+
+/* helper macros */
+
+/* Transpose four 32-bit words between 128-bit vector lanes. */
+#define transpose_4x4(x0, x1, x2, x3, t1, t2) \
+	vpunpckhdq x1, x0, t2;                \
+	vpunpckldq x1, x0, x0;                \
+	                                      \
+	vpunpckldq x3, x2, t1;                \
+	vpunpckhdq x3, x2, x2;                \
+	                                      \
+	vpunpckhqdq t1, x0, x1;               \
+	vpunpcklqdq t1, x0, x0;               \
+	                                      \
+	vpunpckhqdq x2, t2, x3;               \
+	vpunpcklqdq x2, t2, x2;
+
+/* post-SubByte transform. */
+#define transform_pre(x, lo_t, hi_t, mask4bit, tmp0) \
+	vpand x, mask4bit, tmp0;                     \
+	vpandn x, mask4bit, x;                       \
+	vpsrld $4, x, x;                             \
+	                                             \
+	vpshufb tmp0, lo_t, tmp0;                    \
+	vpshufb x, hi_t, x;                          \
+	vpxor tmp0, x, x;
+
+/* post-SubByte transform. Note: x has been XOR'ed with mask4bit by
+ * 'vaeslastenc' instruction. */
+#define transform_post(x, lo_t, hi_t, mask4bit, tmp0) \
+	vpandn mask4bit, x, tmp0;                     \
+	vpsrld $4, x, x;                              \
+	vpand x, mask4bit, x;                         \
+	                                              \
+	vpshufb tmp0, lo_t, tmp0;                     \
+	vpshufb x, hi_t, x;                           \
+	vpxor tmp0, x, x;
+
+
+.section	.rodata.cst16, "aM", @progbits, 16
+.align 16
+
+/*
+ * Following four affine transform look-up tables are from work by
+ * Markku-Juhani O. Saarinen, at https://github.com/mjosaarinen/sm4ni
+ *
+ * These allow exposing SM4 S-Box from AES SubByte.
+ */
+
+/* pre-SubByte affine transform, from SM4 field to AES field. */
+.Lpre_tf_lo_s:
+	.quad 0x9197E2E474720701, 0xC7C1B4B222245157
+.Lpre_tf_hi_s:
+	.quad 0xE240AB09EB49A200, 0xF052B91BF95BB012
+
+/* post-SubByte affine transform, from AES field to SM4 field. */
+.Lpost_tf_lo_s:
+	.quad 0x5B67F2CEA19D0834, 0xEDD14478172BBE82
+.Lpost_tf_hi_s:
+	.quad 0xAE7201DD73AFDC00, 0x11CDBE62CC1063BF
+
+/* For isolating SubBytes from AESENCLAST, inverse shift row */
+.Linv_shift_row:
+	.byte 0x00, 0x0d, 0x0a, 0x07, 0x04, 0x01, 0x0e, 0x0b
+	.byte 0x08, 0x05, 0x02, 0x0f, 0x0c, 0x09, 0x06, 0x03
+
+/* Inverse shift row + Rotate left by 8 bits on 32-bit words with vpshufb */
+.Linv_shift_row_rol_8:
+	.byte 0x07, 0x00, 0x0d, 0x0a, 0x0b, 0x04, 0x01, 0x0e
+	.byte 0x0f, 0x08, 0x05, 0x02, 0x03, 0x0c, 0x09, 0x06
+
+/* Inverse shift row + Rotate left by 16 bits on 32-bit words with vpshufb */
+.Linv_shift_row_rol_16:
+	.byte 0x0a, 0x07, 0x00, 0x0d, 0x0e, 0x0b, 0x04, 0x01
+	.byte 0x02, 0x0f, 0x08, 0x05, 0x06, 0x03, 0x0c, 0x09
+
+/* Inverse shift row + Rotate left by 24 bits on 32-bit words with vpshufb */
+.Linv_shift_row_rol_24:
+	.byte 0x0d, 0x0a, 0x07, 0x00, 0x01, 0x0e, 0x0b, 0x04
+	.byte 0x05, 0x02, 0x0f, 0x08, 0x09, 0x06, 0x03, 0x0c
+
+/* For CTR-mode IV byteswap */
+.Lbswap128_mask:
+	.byte 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0
+
+/* For input word byte-swap */
+.Lbswap32_mask:
+	.byte 3, 2, 1, 0, 7, 6, 5, 4, 11, 10, 9, 8, 15, 14, 13, 12
+
+.align 4
+/* 4-bit mask */
+.L0f0f0f0f:
+	.long 0x0f0f0f0f
+
+/* 12 bytes, only for padding */
+.Lpadding_deadbeef:
+	.long 0xdeadbeef, 0xdeadbeef, 0xdeadbeef
+
+.text
+SYM_FUNC_START_LOCAL(__sm4_crypt_blk16)
+	/* input:
+	 *	%rdi: round key array, CTX
+	 *	RA0, RA1, RA2, RA3, RB0, RB1, RB2, RB3: sixteen parallel
+	 *						plaintext blocks
+	 * output:
+	 *	RA0, RA1, RA2, RA3, RB0, RB1, RB2, RB3: sixteen parallel
+	 * 						ciphertext blocks
+	 */
+	FRAME_BEGIN
+
+	vbroadcasti128 .Lbswap32_mask rRIP, RTMP2;
+	vpshufb RTMP2, RA0, RA0;
+	vpshufb RTMP2, RA1, RA1;
+	vpshufb RTMP2, RA2, RA2;
+	vpshufb RTMP2, RA3, RA3;
+	vpshufb RTMP2, RB0, RB0;
+	vpshufb RTMP2, RB1, RB1;
+	vpshufb RTMP2, RB2, RB2;
+	vpshufb RTMP2, RB3, RB3;
+
+	vpbroadcastd .L0f0f0f0f rRIP, MASK_4BIT;
+	transpose_4x4(RA0, RA1, RA2, RA3, RTMP0, RTMP1);
+	transpose_4x4(RB0, RB1, RB2, RB3, RTMP0, RTMP1);
+
+#define ROUND(round, s0, s1, s2, s3, r0, r1, r2, r3)                \
+	vpbroadcastd (4*(round))(%rdi), RX0;                        \
+	vbroadcasti128 .Lpre_tf_lo_s rRIP, RTMP4;                   \
+	vbroadcasti128 .Lpre_tf_hi_s rRIP, RTMP1;                   \
+	vmovdqa RX0, RX1;                                           \
+	vpxor s1, RX0, RX0;                                         \
+	vpxor s2, RX0, RX0;                                         \
+	vpxor s3, RX0, RX0; /* s1 ^ s2 ^ s3 ^ rk */                 \
+	vbroadcasti128 .Lpost_tf_lo_s rRIP, RTMP2;                  \
+	vbroadcasti128 .Lpost_tf_hi_s rRIP, RTMP3;                  \
+	vpxor r1, RX1, RX1;                                         \
+	vpxor r2, RX1, RX1;                                         \
+	vpxor r3, RX1, RX1; /* r1 ^ r2 ^ r3 ^ rk */                 \
+	                                                            \
+	/* sbox, non-linear part */                                 \
+	transform_pre(RX0, RTMP4, RTMP1, MASK_4BIT, RTMP0);         \
+	transform_pre(RX1, RTMP4, RTMP1, MASK_4BIT, RTMP0);         \
+	vextracti128 $1, RX0, RTMP4x;                               \
+	vextracti128 $1, RX1, RTMP0x;                               \
+	vaesenclast MASK_4BITx, RX0x, RX0x;                         \
+	vaesenclast MASK_4BITx, RTMP4x, RTMP4x;                     \
+	vaesenclast MASK_4BITx, RX1x, RX1x;                         \
+	vaesenclast MASK_4BITx, RTMP0x, RTMP0x;                     \
+	vinserti128 $1, RTMP4x, RX0, RX0;                           \
+	vbroadcasti128 .Linv_shift_row rRIP, RTMP4;                 \
+	vinserti128 $1, RTMP0x, RX1, RX1;                           \
+	transform_post(RX0, RTMP2, RTMP3, MASK_4BIT, RTMP0);        \
+	transform_post(RX1, RTMP2, RTMP3, MASK_4BIT, RTMP0);        \
+	                                                            \
+	/* linear part */                                           \
+	vpshufb RTMP4, RX0, RTMP0;                                  \
+	vpxor RTMP0, s0, s0; /* s0 ^ x */                           \
+	vpshufb RTMP4, RX1, RTMP2;                                  \
+	vbroadcasti128 .Linv_shift_row_rol_8 rRIP, RTMP4;           \
+	vpxor RTMP2, r0, r0; /* r0 ^ x */                           \
+	vpshufb RTMP4, RX0, RTMP1;                                  \
+	vpxor RTMP1, RTMP0, RTMP0; /* x ^ rol(x,8) */               \
+	vpshufb RTMP4, RX1, RTMP3;                                  \
+	vbroadcasti128 .Linv_shift_row_rol_16 rRIP, RTMP4;          \
+	vpxor RTMP3, RTMP2, RTMP2; /* x ^ rol(x,8) */               \
+	vpshufb RTMP4, RX0, RTMP1;                                  \
+	vpxor RTMP1, RTMP0, RTMP0; /* x ^ rol(x,8) ^ rol(x,16) */   \
+	vpshufb RTMP4, RX1, RTMP3;                                  \
+	vbroadcasti128 .Linv_shift_row_rol_24 rRIP, RTMP4;          \
+	vpxor RTMP3, RTMP2, RTMP2; /* x ^ rol(x,8) ^ rol(x,16) */   \
+	vpshufb RTMP4, RX0, RTMP1;                                  \
+	vpxor RTMP1, s0, s0; /* s0 ^ x ^ rol(x,24) */               \
+	vpslld $2, RTMP0, RTMP1;                                    \
+	vpsrld $30, RTMP0, RTMP0;                                   \
+	vpxor RTMP0, s0, s0;                                        \
+	/* s0 ^ x ^ rol(x,2) ^ rol(x,10) ^ rol(x,18) ^ rol(x,24) */ \
+	vpxor RTMP1, s0, s0;                                        \
+	vpshufb RTMP4, RX1, RTMP3;                                  \
+	vpxor RTMP3, r0, r0; /* r0 ^ x ^ rol(x,24) */               \
+	vpslld $2, RTMP2, RTMP3;                                    \
+	vpsrld $30, RTMP2, RTMP2;                                   \
+	vpxor RTMP2, r0, r0;                                        \
+	/* r0 ^ x ^ rol(x,2) ^ rol(x,10) ^ rol(x,18) ^ rol(x,24) */ \
+	vpxor RTMP3, r0, r0;
+
+	leaq (32*4)(%rdi), %rax;
+.align 16
+.Lroundloop_blk8:
+	ROUND(0, RA0, RA1, RA2, RA3, RB0, RB1, RB2, RB3);
+	ROUND(1, RA1, RA2, RA3, RA0, RB1, RB2, RB3, RB0);
+	ROUND(2, RA2, RA3, RA0, RA1, RB2, RB3, RB0, RB1);
+	ROUND(3, RA3, RA0, RA1, RA2, RB3, RB0, RB1, RB2);
+	leaq (4*4)(%rdi), %rdi;
+	cmpq %rax, %rdi;
+	jne .Lroundloop_blk8;
+
+#undef ROUND
+
+	vbroadcasti128 .Lbswap128_mask rRIP, RTMP2;
+
+	transpose_4x4(RA0, RA1, RA2, RA3, RTMP0, RTMP1);
+	transpose_4x4(RB0, RB1, RB2, RB3, RTMP0, RTMP1);
+	vpshufb RTMP2, RA0, RA0;
+	vpshufb RTMP2, RA1, RA1;
+	vpshufb RTMP2, RA2, RA2;
+	vpshufb RTMP2, RA3, RA3;
+	vpshufb RTMP2, RB0, RB0;
+	vpshufb RTMP2, RB1, RB1;
+	vpshufb RTMP2, RB2, RB2;
+	vpshufb RTMP2, RB3, RB3;
+
+	FRAME_END
+	RET;
+SYM_FUNC_END(__sm4_crypt_blk16)
+
+#define inc_le128(x, minus_one, tmp) \
+	vpcmpeqq minus_one, x, tmp;  \
+	vpsubq minus_one, x, x;      \
+	vpslldq $8, tmp, tmp;        \
+	vpsubq tmp, x, x;
+
+/*
+ * void sm4_aesni_avx2_ctr_enc_blk16(const u32 *rk, u8 *dst,
+ *                                   const u8 *src, u8 *iv)
+ */
+SYM_TYPED_FUNC_START(sm4_aesni_avx2_ctr_enc_blk16)
+	/* input:
+	 *	%rdi: round key array, CTX
+	 *	%rsi: dst (16 blocks)
+	 *	%rdx: src (16 blocks)
+	 *	%rcx: iv (big endian, 128bit)
+	 */
+	FRAME_BEGIN
+
+	movq 8(%rcx), %rax;
+	bswapq %rax;
+
+	vzeroupper;
+
+	vbroadcasti128 .Lbswap128_mask rRIP, RTMP3;
+	vpcmpeqd RNOT, RNOT, RNOT;
+	vpsrldq $8, RNOT, RNOT;   /* ab: -1:0 ; cd: -1:0 */
+	vpaddq RNOT, RNOT, RTMP2; /* ab: -2:0 ; cd: -2:0 */
+
+	/* load IV and byteswap */
+	vmovdqu (%rcx), RTMP4x;
+	vpshufb RTMP3x, RTMP4x, RTMP4x;
+	vmovdqa RTMP4x, RTMP0x;
+	inc_le128(RTMP4x, RNOTx, RTMP1x);
+	vinserti128 $1, RTMP4x, RTMP0, RTMP0;
+	vpshufb RTMP3, RTMP0, RA0; /* +1 ; +0 */
+
+	/* check need for handling 64-bit overflow and carry */
+	cmpq $(0xffffffffffffffff - 16), %rax;
+	ja .Lhandle_ctr_carry;
+
+	/* construct IVs */
+	vpsubq RTMP2, RTMP0, RTMP0; /* +3 ; +2 */
+	vpshufb RTMP3, RTMP0, RA1;
+	vpsubq RTMP2, RTMP0, RTMP0; /* +5 ; +4 */
+	vpshufb RTMP3, RTMP0, RA2;
+	vpsubq RTMP2, RTMP0, RTMP0; /* +7 ; +6 */
+	vpshufb RTMP3, RTMP0, RA3;
+	vpsubq RTMP2, RTMP0, RTMP0; /* +9 ; +8 */
+	vpshufb RTMP3, RTMP0, RB0;
+	vpsubq RTMP2, RTMP0, RTMP0; /* +11 ; +10 */
+	vpshufb RTMP3, RTMP0, RB1;
+	vpsubq RTMP2, RTMP0, RTMP0; /* +13 ; +12 */
+	vpshufb RTMP3, RTMP0, RB2;
+	vpsubq RTMP2, RTMP0, RTMP0; /* +15 ; +14 */
+	vpshufb RTMP3, RTMP0, RB3;
+	vpsubq RTMP2, RTMP0, RTMP0; /* +16 */
+	vpshufb RTMP3x, RTMP0x, RTMP0x;
+
+	jmp .Lctr_carry_done;
+
+.Lhandle_ctr_carry:
+	/* construct IVs */
+	inc_le128(RTMP0, RNOT, RTMP1);
+	inc_le128(RTMP0, RNOT, RTMP1);
+	vpshufb RTMP3, RTMP0, RA1; /* +3 ; +2 */
+	inc_le128(RTMP0, RNOT, RTMP1);
+	inc_le128(RTMP0, RNOT, RTMP1);
+	vpshufb RTMP3, RTMP0, RA2; /* +5 ; +4 */
+	inc_le128(RTMP0, RNOT, RTMP1);
+	inc_le128(RTMP0, RNOT, RTMP1);
+	vpshufb RTMP3, RTMP0, RA3; /* +7 ; +6 */
+	inc_le128(RTMP0, RNOT, RTMP1);
+	inc_le128(RTMP0, RNOT, RTMP1);
+	vpshufb RTMP3, RTMP0, RB0; /* +9 ; +8 */
+	inc_le128(RTMP0, RNOT, RTMP1);
+	inc_le128(RTMP0, RNOT, RTMP1);
+	vpshufb RTMP3, RTMP0, RB1; /* +11 ; +10 */
+	inc_le128(RTMP0, RNOT, RTMP1);
+	inc_le128(RTMP0, RNOT, RTMP1);
+	vpshufb RTMP3, RTMP0, RB2; /* +13 ; +12 */
+	inc_le128(RTMP0, RNOT, RTMP1);
+	inc_le128(RTMP0, RNOT, RTMP1);
+	vpshufb RTMP3, RTMP0, RB3; /* +15 ; +14 */
+	inc_le128(RTMP0, RNOT, RTMP1);
+	vextracti128 $1, RTMP0, RTMP0x;
+	vpshufb RTMP3x, RTMP0x, RTMP0x; /* +16 */
+
+.align 4
+.Lctr_carry_done:
+	/* store new IV */
+	vmovdqu RTMP0x, (%rcx);
+
+	call __sm4_crypt_blk16;
+
+	vpxor (0 * 32)(%rdx), RA0, RA0;
+	vpxor (1 * 32)(%rdx), RA1, RA1;
+	vpxor (2 * 32)(%rdx), RA2, RA2;
+	vpxor (3 * 32)(%rdx), RA3, RA3;
+	vpxor (4 * 32)(%rdx), RB0, RB0;
+	vpxor (5 * 32)(%rdx), RB1, RB1;
+	vpxor (6 * 32)(%rdx), RB2, RB2;
+	vpxor (7 * 32)(%rdx), RB3, RB3;
+
+	vmovdqu RA0, (0 * 32)(%rsi);
+	vmovdqu RA1, (1 * 32)(%rsi);
+	vmovdqu RA2, (2 * 32)(%rsi);
+	vmovdqu RA3, (3 * 32)(%rsi);
+	vmovdqu RB0, (4 * 32)(%rsi);
+	vmovdqu RB1, (5 * 32)(%rsi);
+	vmovdqu RB2, (6 * 32)(%rsi);
+	vmovdqu RB3, (7 * 32)(%rsi);
+
+	vzeroall;
+	FRAME_END
+	RET;
+SYM_FUNC_END(sm4_aesni_avx2_ctr_enc_blk16)
+
+/*
+ * void sm4_aesni_avx2_cbc_dec_blk16(const u32 *rk, u8 *dst,
+ *                                   const u8 *src, u8 *iv)
+ */
+SYM_TYPED_FUNC_START(sm4_aesni_avx2_cbc_dec_blk16)
+	/* input:
+	 *	%rdi: round key array, CTX
+	 *	%rsi: dst (16 blocks)
+	 *	%rdx: src (16 blocks)
+	 *	%rcx: iv
+	 */
+	FRAME_BEGIN
+
+	vzeroupper;
+
+	vmovdqu (0 * 32)(%rdx), RA0;
+	vmovdqu (1 * 32)(%rdx), RA1;
+	vmovdqu (2 * 32)(%rdx), RA2;
+	vmovdqu (3 * 32)(%rdx), RA3;
+	vmovdqu (4 * 32)(%rdx), RB0;
+	vmovdqu (5 * 32)(%rdx), RB1;
+	vmovdqu (6 * 32)(%rdx), RB2;
+	vmovdqu (7 * 32)(%rdx), RB3;
+
+	call __sm4_crypt_blk16;
+
+	vmovdqu (%rcx), RNOTx;
+	vinserti128 $1, (%rdx), RNOT, RNOT;
+	vpxor RNOT, RA0, RA0;
+	vpxor (0 * 32 + 16)(%rdx), RA1, RA1;
+	vpxor (1 * 32 + 16)(%rdx), RA2, RA2;
+	vpxor (2 * 32 + 16)(%rdx), RA3, RA3;
+	vpxor (3 * 32 + 16)(%rdx), RB0, RB0;
+	vpxor (4 * 32 + 16)(%rdx), RB1, RB1;
+	vpxor (5 * 32 + 16)(%rdx), RB2, RB2;
+	vpxor (6 * 32 + 16)(%rdx), RB3, RB3;
+	vmovdqu (7 * 32 + 16)(%rdx), RNOTx;
+	vmovdqu RNOTx, (%rcx); /* store new IV */
+
+	vmovdqu RA0, (0 * 32)(%rsi);
+	vmovdqu RA1, (1 * 32)(%rsi);
+	vmovdqu RA2, (2 * 32)(%rsi);
+	vmovdqu RA3, (3 * 32)(%rsi);
+	vmovdqu RB0, (4 * 32)(%rsi);
+	vmovdqu RB1, (5 * 32)(%rsi);
+	vmovdqu RB2, (6 * 32)(%rsi);
+	vmovdqu RB3, (7 * 32)(%rsi);
+
+	vzeroall;
+	FRAME_END
+	RET;
+SYM_FUNC_END(sm4_aesni_avx2_cbc_dec_blk16)
+
+/*
+ * void sm4_aesni_avx2_cfb_dec_blk16(const u32 *rk, u8 *dst,
+ *                                   const u8 *src, u8 *iv)
+ */
+SYM_TYPED_FUNC_START(sm4_aesni_avx2_cfb_dec_blk16)
+	/* input:
+	 *	%rdi: round key array, CTX
+	 *	%rsi: dst (16 blocks)
+	 *	%rdx: src (16 blocks)
+	 *	%rcx: iv
+	 */
+	FRAME_BEGIN
+
+	vzeroupper;
+
+	/* Load input */
+	vmovdqu (%rcx), RNOTx;
+	vinserti128 $1, (%rdx), RNOT, RA0;
+	vmovdqu (0 * 32 + 16)(%rdx), RA1;
+	vmovdqu (1 * 32 + 16)(%rdx), RA2;
+	vmovdqu (2 * 32 + 16)(%rdx), RA3;
+	vmovdqu (3 * 32 + 16)(%rdx), RB0;
+	vmovdqu (4 * 32 + 16)(%rdx), RB1;
+	vmovdqu (5 * 32 + 16)(%rdx), RB2;
+	vmovdqu (6 * 32 + 16)(%rdx), RB3;
+
+	/* Update IV */
+	vmovdqu (7 * 32 + 16)(%rdx), RNOTx;
+	vmovdqu RNOTx, (%rcx);
+
+	call __sm4_crypt_blk16;
+
+	vpxor (0 * 32)(%rdx), RA0, RA0;
+	vpxor (1 * 32)(%rdx), RA1, RA1;
+	vpxor (2 * 32)(%rdx), RA2, RA2;
+	vpxor (3 * 32)(%rdx), RA3, RA3;
+	vpxor (4 * 32)(%rdx), RB0, RB0;
+	vpxor (5 * 32)(%rdx), RB1, RB1;
+	vpxor (6 * 32)(%rdx), RB2, RB2;
+	vpxor (7 * 32)(%rdx), RB3, RB3;
+
+	vmovdqu RA0, (0 * 32)(%rsi);
+	vmovdqu RA1, (1 * 32)(%rsi);
+	vmovdqu RA2, (2 * 32)(%rsi);
+	vmovdqu RA3, (3 * 32)(%rsi);
+	vmovdqu RB0, (4 * 32)(%rsi);
+	vmovdqu RB1, (5 * 32)(%rsi);
+	vmovdqu RB2, (6 * 32)(%rsi);
+	vmovdqu RB3, (7 * 32)(%rsi);
+
+	vzeroall;
+	FRAME_END
+	RET;
+SYM_FUNC_END(sm4_aesni_avx2_cfb_dec_blk16)