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, 487 insertions, 0 deletions

diff --git a/arch/x86/crypto/sm4_aesni_avx_glue.c b/arch/x86/crypto/sm4_aesni_avx_glue.c
new file mode 100644
index 000000000..7800f77d6
--- /dev/null
+++ b/arch/x86/crypto/sm4_aesni_avx_glue.c
@@ -0,0 +1,487 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * SM4 Cipher Algorithm, AES-NI/AVX optimized.
+ * as specified in
+ * https://tools.ietf.org/id/draft-ribose-cfrg-sm4-10.html
+ *
+ * Copyright (c) 2021, Alibaba Group.
+ * Copyright (c) 2021 Tianjia Zhang <tianjia.zhang@linux.alibaba.com>
+ */
+
+#include <linux/module.h>
+#include <linux/crypto.h>
+#include <linux/kernel.h>
+#include <asm/simd.h>
+#include <crypto/internal/simd.h>
+#include <crypto/internal/skcipher.h>
+#include <crypto/sm4.h>
+#include "sm4-avx.h"
+
+#define SM4_CRYPT8_BLOCK_SIZE	(SM4_BLOCK_SIZE * 8)
+
+asmlinkage void sm4_aesni_avx_crypt4(const u32 *rk, u8 *dst,
+				const u8 *src, int nblocks);
+asmlinkage void sm4_aesni_avx_crypt8(const u32 *rk, u8 *dst,
+				const u8 *src, int nblocks);
+asmlinkage void sm4_aesni_avx_ctr_enc_blk8(const u32 *rk, u8 *dst,
+				const u8 *src, u8 *iv);
+asmlinkage void sm4_aesni_avx_cbc_dec_blk8(const u32 *rk, u8 *dst,
+				const u8 *src, u8 *iv);
+asmlinkage void sm4_aesni_avx_cfb_dec_blk8(const u32 *rk, u8 *dst,
+				const u8 *src, u8 *iv);
+
+static int sm4_skcipher_setkey(struct crypto_skcipher *tfm, const u8 *key,
+			unsigned int key_len)
+{
+	struct sm4_ctx *ctx = crypto_skcipher_ctx(tfm);
+
+	return sm4_expandkey(ctx, key, key_len);
+}
+
+static int ecb_do_crypt(struct skcipher_request *req, const u32 *rkey)
+{
+	struct skcipher_walk walk;
+	unsigned int nbytes;
+	int err;
+
+	err = skcipher_walk_virt(&walk, req, false);
+
+	while ((nbytes = walk.nbytes) > 0) {
+		const u8 *src = walk.src.virt.addr;
+		u8 *dst = walk.dst.virt.addr;
+
+		kernel_fpu_begin();
+		while (nbytes >= SM4_CRYPT8_BLOCK_SIZE) {
+			sm4_aesni_avx_crypt8(rkey, dst, src, 8);
+			dst += SM4_CRYPT8_BLOCK_SIZE;
+			src += SM4_CRYPT8_BLOCK_SIZE;
+			nbytes -= SM4_CRYPT8_BLOCK_SIZE;
+		}
+		while (nbytes >= SM4_BLOCK_SIZE) {
+			unsigned int nblocks = min(nbytes >> 4, 4u);
+			sm4_aesni_avx_crypt4(rkey, dst, src, nblocks);
+			dst += nblocks * SM4_BLOCK_SIZE;
+			src += nblocks * SM4_BLOCK_SIZE;
+			nbytes -= nblocks * SM4_BLOCK_SIZE;
+		}
+		kernel_fpu_end();
+
+		err = skcipher_walk_done(&walk, nbytes);
+	}
+
+	return err;
+}
+
+int sm4_avx_ecb_encrypt(struct skcipher_request *req)
+{
+	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
+	struct sm4_ctx *ctx = crypto_skcipher_ctx(tfm);
+
+	return ecb_do_crypt(req, ctx->rkey_enc);
+}
+EXPORT_SYMBOL_GPL(sm4_avx_ecb_encrypt);
+
+int sm4_avx_ecb_decrypt(struct skcipher_request *req)
+{
+	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
+	struct sm4_ctx *ctx = crypto_skcipher_ctx(tfm);
+
+	return ecb_do_crypt(req, ctx->rkey_dec);
+}
+EXPORT_SYMBOL_GPL(sm4_avx_ecb_decrypt);
+
+int sm4_cbc_encrypt(struct skcipher_request *req)
+{
+	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
+	struct sm4_ctx *ctx = crypto_skcipher_ctx(tfm);
+	struct skcipher_walk walk;
+	unsigned int nbytes;
+	int err;
+
+	err = skcipher_walk_virt(&walk, req, false);
+
+	while ((nbytes = walk.nbytes) > 0) {
+		const u8 *iv = walk.iv;
+		const u8 *src = walk.src.virt.addr;
+		u8 *dst = walk.dst.virt.addr;
+
+		while (nbytes >= SM4_BLOCK_SIZE) {
+			crypto_xor_cpy(dst, src, iv, SM4_BLOCK_SIZE);
+			sm4_crypt_block(ctx->rkey_enc, dst, dst);
+			iv = dst;
+			src += SM4_BLOCK_SIZE;
+			dst += SM4_BLOCK_SIZE;
+			nbytes -= SM4_BLOCK_SIZE;
+		}
+		if (iv != walk.iv)
+			memcpy(walk.iv, iv, SM4_BLOCK_SIZE);
+
+		err = skcipher_walk_done(&walk, nbytes);
+	}
+
+	return err;
+}
+EXPORT_SYMBOL_GPL(sm4_cbc_encrypt);
+
+int sm4_avx_cbc_decrypt(struct skcipher_request *req,
+			unsigned int bsize, sm4_crypt_func func)
+{
+	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
+	struct sm4_ctx *ctx = crypto_skcipher_ctx(tfm);
+	struct skcipher_walk walk;
+	unsigned int nbytes;
+	int err;
+
+	err = skcipher_walk_virt(&walk, req, false);
+
+	while ((nbytes = walk.nbytes) > 0) {
+		const u8 *src = walk.src.virt.addr;
+		u8 *dst = walk.dst.virt.addr;
+
+		kernel_fpu_begin();
+
+		while (nbytes >= bsize) {
+			func(ctx->rkey_dec, dst, src, walk.iv);
+			dst += bsize;
+			src += bsize;
+			nbytes -= bsize;
+		}
+
+		while (nbytes >= SM4_BLOCK_SIZE) {
+			u8 keystream[SM4_BLOCK_SIZE * 8];
+			u8 iv[SM4_BLOCK_SIZE];
+			unsigned int nblocks = min(nbytes >> 4, 8u);
+			int i;
+
+			sm4_aesni_avx_crypt8(ctx->rkey_dec, keystream,
+						src, nblocks);
+
+			src += ((int)nblocks - 2) * SM4_BLOCK_SIZE;
+			dst += (nblocks - 1) * SM4_BLOCK_SIZE;
+			memcpy(iv, src + SM4_BLOCK_SIZE, SM4_BLOCK_SIZE);
+
+			for (i = nblocks - 1; i > 0; i--) {
+				crypto_xor_cpy(dst, src,
+					&keystream[i * SM4_BLOCK_SIZE],
+					SM4_BLOCK_SIZE);
+				src -= SM4_BLOCK_SIZE;
+				dst -= SM4_BLOCK_SIZE;
+			}
+			crypto_xor_cpy(dst, walk.iv, keystream, SM4_BLOCK_SIZE);
+			memcpy(walk.iv, iv, SM4_BLOCK_SIZE);
+			dst += nblocks * SM4_BLOCK_SIZE;
+			src += (nblocks + 1) * SM4_BLOCK_SIZE;
+			nbytes -= nblocks * SM4_BLOCK_SIZE;
+		}
+
+		kernel_fpu_end();
+		err = skcipher_walk_done(&walk, nbytes);
+	}
+
+	return err;
+}
+EXPORT_SYMBOL_GPL(sm4_avx_cbc_decrypt);
+
+static int cbc_decrypt(struct skcipher_request *req)
+{
+	return sm4_avx_cbc_decrypt(req, SM4_CRYPT8_BLOCK_SIZE,
+				sm4_aesni_avx_cbc_dec_blk8);
+}
+
+int sm4_cfb_encrypt(struct skcipher_request *req)
+{
+	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
+	struct sm4_ctx *ctx = crypto_skcipher_ctx(tfm);
+	struct skcipher_walk walk;
+	unsigned int nbytes;
+	int err;
+
+	err = skcipher_walk_virt(&walk, req, false);
+
+	while ((nbytes = walk.nbytes) > 0) {
+		u8 keystream[SM4_BLOCK_SIZE];
+		const u8 *iv = walk.iv;
+		const u8 *src = walk.src.virt.addr;
+		u8 *dst = walk.dst.virt.addr;
+
+		while (nbytes >= SM4_BLOCK_SIZE) {
+			sm4_crypt_block(ctx->rkey_enc, keystream, iv);
+			crypto_xor_cpy(dst, src, keystream, SM4_BLOCK_SIZE);
+			iv = dst;
+			src += SM4_BLOCK_SIZE;
+			dst += SM4_BLOCK_SIZE;
+			nbytes -= SM4_BLOCK_SIZE;
+		}
+		if (iv != walk.iv)
+			memcpy(walk.iv, iv, SM4_BLOCK_SIZE);
+
+		/* tail */
+		if (walk.nbytes == walk.total && nbytes > 0) {
+			sm4_crypt_block(ctx->rkey_enc, keystream, walk.iv);
+			crypto_xor_cpy(dst, src, keystream, nbytes);
+			nbytes = 0;
+		}
+
+		err = skcipher_walk_done(&walk, nbytes);
+	}
+
+	return err;
+}
+EXPORT_SYMBOL_GPL(sm4_cfb_encrypt);
+
+int sm4_avx_cfb_decrypt(struct skcipher_request *req,
+			unsigned int bsize, sm4_crypt_func func)
+{
+	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
+	struct sm4_ctx *ctx = crypto_skcipher_ctx(tfm);
+	struct skcipher_walk walk;
+	unsigned int nbytes;
+	int err;
+
+	err = skcipher_walk_virt(&walk, req, false);
+
+	while ((nbytes = walk.nbytes) > 0) {
+		const u8 *src = walk.src.virt.addr;
+		u8 *dst = walk.dst.virt.addr;
+
+		kernel_fpu_begin();
+
+		while (nbytes >= bsize) {
+			func(ctx->rkey_enc, dst, src, walk.iv);
+			dst += bsize;
+			src += bsize;
+			nbytes -= bsize;
+		}
+
+		while (nbytes >= SM4_BLOCK_SIZE) {
+			u8 keystream[SM4_BLOCK_SIZE * 8];
+			unsigned int nblocks = min(nbytes >> 4, 8u);
+
+			memcpy(keystream, walk.iv, SM4_BLOCK_SIZE);
+			if (nblocks > 1)
+				memcpy(&keystream[SM4_BLOCK_SIZE], src,
+					(nblocks - 1) * SM4_BLOCK_SIZE);
+			memcpy(walk.iv, src + (nblocks - 1) * SM4_BLOCK_SIZE,
+				SM4_BLOCK_SIZE);
+
+			sm4_aesni_avx_crypt8(ctx->rkey_enc, keystream,
+						keystream, nblocks);
+
+			crypto_xor_cpy(dst, src, keystream,
+					nblocks * SM4_BLOCK_SIZE);
+			dst += nblocks * SM4_BLOCK_SIZE;
+			src += nblocks * SM4_BLOCK_SIZE;
+			nbytes -= nblocks * SM4_BLOCK_SIZE;
+		}
+
+		kernel_fpu_end();
+
+		/* tail */
+		if (walk.nbytes == walk.total && nbytes > 0) {
+			u8 keystream[SM4_BLOCK_SIZE];
+
+			sm4_crypt_block(ctx->rkey_enc, keystream, walk.iv);
+			crypto_xor_cpy(dst, src, keystream, nbytes);
+			nbytes = 0;
+		}
+
+		err = skcipher_walk_done(&walk, nbytes);
+	}
+
+	return err;
+}
+EXPORT_SYMBOL_GPL(sm4_avx_cfb_decrypt);
+
+static int cfb_decrypt(struct skcipher_request *req)
+{
+	return sm4_avx_cfb_decrypt(req, SM4_CRYPT8_BLOCK_SIZE,
+				sm4_aesni_avx_cfb_dec_blk8);
+}
+
+int sm4_avx_ctr_crypt(struct skcipher_request *req,
+			unsigned int bsize, sm4_crypt_func func)
+{
+	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
+	struct sm4_ctx *ctx = crypto_skcipher_ctx(tfm);
+	struct skcipher_walk walk;
+	unsigned int nbytes;
+	int err;
+
+	err = skcipher_walk_virt(&walk, req, false);
+
+	while ((nbytes = walk.nbytes) > 0) {
+		const u8 *src = walk.src.virt.addr;
+		u8 *dst = walk.dst.virt.addr;
+
+		kernel_fpu_begin();
+
+		while (nbytes >= bsize) {
+			func(ctx->rkey_enc, dst, src, walk.iv);
+			dst += bsize;
+			src += bsize;
+			nbytes -= bsize;
+		}
+
+		while (nbytes >= SM4_BLOCK_SIZE) {
+			u8 keystream[SM4_BLOCK_SIZE * 8];
+			unsigned int nblocks = min(nbytes >> 4, 8u);
+			int i;
+
+			for (i = 0; i < nblocks; i++) {
+				memcpy(&keystream[i * SM4_BLOCK_SIZE],
+					walk.iv, SM4_BLOCK_SIZE);
+				crypto_inc(walk.iv, SM4_BLOCK_SIZE);
+			}
+			sm4_aesni_avx_crypt8(ctx->rkey_enc, keystream,
+					keystream, nblocks);
+
+			crypto_xor_cpy(dst, src, keystream,
+					nblocks * SM4_BLOCK_SIZE);
+			dst += nblocks * SM4_BLOCK_SIZE;
+			src += nblocks * SM4_BLOCK_SIZE;
+			nbytes -= nblocks * SM4_BLOCK_SIZE;
+		}
+
+		kernel_fpu_end();
+
+		/* tail */
+		if (walk.nbytes == walk.total && nbytes > 0) {
+			u8 keystream[SM4_BLOCK_SIZE];
+
+			memcpy(keystream, walk.iv, SM4_BLOCK_SIZE);
+			crypto_inc(walk.iv, SM4_BLOCK_SIZE);
+
+			sm4_crypt_block(ctx->rkey_enc, keystream, keystream);
+
+			crypto_xor_cpy(dst, src, keystream, nbytes);
+			dst += nbytes;
+			src += nbytes;
+			nbytes = 0;
+		}
+
+		err = skcipher_walk_done(&walk, nbytes);
+	}
+
+	return err;
+}
+EXPORT_SYMBOL_GPL(sm4_avx_ctr_crypt);
+
+static int ctr_crypt(struct skcipher_request *req)
+{
+	return sm4_avx_ctr_crypt(req, SM4_CRYPT8_BLOCK_SIZE,
+				sm4_aesni_avx_ctr_enc_blk8);
+}
+
+static struct skcipher_alg sm4_aesni_avx_skciphers[] = {
+	{
+		.base = {
+			.cra_name		= "__ecb(sm4)",
+			.cra_driver_name	= "__ecb-sm4-aesni-avx",
+			.cra_priority		= 400,
+			.cra_flags		= CRYPTO_ALG_INTERNAL,
+			.cra_blocksize		= SM4_BLOCK_SIZE,
+			.cra_ctxsize		= sizeof(struct sm4_ctx),
+			.cra_module		= THIS_MODULE,
+		},
+		.min_keysize	= SM4_KEY_SIZE,
+		.max_keysize	= SM4_KEY_SIZE,
+		.walksize	= 8 * SM4_BLOCK_SIZE,
+		.setkey		= sm4_skcipher_setkey,
+		.encrypt	= sm4_avx_ecb_encrypt,
+		.decrypt	= sm4_avx_ecb_decrypt,
+	}, {
+		.base = {
+			.cra_name		= "__cbc(sm4)",
+			.cra_driver_name	= "__cbc-sm4-aesni-avx",
+			.cra_priority		= 400,
+			.cra_flags		= CRYPTO_ALG_INTERNAL,
+			.cra_blocksize		= SM4_BLOCK_SIZE,
+			.cra_ctxsize		= sizeof(struct sm4_ctx),
+			.cra_module		= THIS_MODULE,
+		},
+		.min_keysize	= SM4_KEY_SIZE,
+		.max_keysize	= SM4_KEY_SIZE,
+		.ivsize		= SM4_BLOCK_SIZE,
+		.walksize	= 8 * SM4_BLOCK_SIZE,
+		.setkey		= sm4_skcipher_setkey,
+		.encrypt	= sm4_cbc_encrypt,
+		.decrypt	= cbc_decrypt,
+	}, {
+		.base = {
+			.cra_name		= "__cfb(sm4)",
+			.cra_driver_name	= "__cfb-sm4-aesni-avx",
+			.cra_priority		= 400,
+			.cra_flags		= CRYPTO_ALG_INTERNAL,
+			.cra_blocksize		= 1,
+			.cra_ctxsize		= sizeof(struct sm4_ctx),
+			.cra_module		= THIS_MODULE,
+		},
+		.min_keysize	= SM4_KEY_SIZE,
+		.max_keysize	= SM4_KEY_SIZE,
+		.ivsize		= SM4_BLOCK_SIZE,
+		.chunksize	= SM4_BLOCK_SIZE,
+		.walksize	= 8 * SM4_BLOCK_SIZE,
+		.setkey		= sm4_skcipher_setkey,
+		.encrypt	= sm4_cfb_encrypt,
+		.decrypt	= cfb_decrypt,
+	}, {
+		.base = {
+			.cra_name		= "__ctr(sm4)",
+			.cra_driver_name	= "__ctr-sm4-aesni-avx",
+			.cra_priority		= 400,
+			.cra_flags		= CRYPTO_ALG_INTERNAL,
+			.cra_blocksize		= 1,
+			.cra_ctxsize		= sizeof(struct sm4_ctx),
+			.cra_module		= THIS_MODULE,
+		},
+		.min_keysize	= SM4_KEY_SIZE,
+		.max_keysize	= SM4_KEY_SIZE,
+		.ivsize		= SM4_BLOCK_SIZE,
+		.chunksize	= SM4_BLOCK_SIZE,
+		.walksize	= 8 * SM4_BLOCK_SIZE,
+		.setkey		= sm4_skcipher_setkey,
+		.encrypt	= ctr_crypt,
+		.decrypt	= ctr_crypt,
+	}
+};
+
+static struct simd_skcipher_alg *
+simd_sm4_aesni_avx_skciphers[ARRAY_SIZE(sm4_aesni_avx_skciphers)];
+
+static int __init sm4_init(void)
+{
+	const char *feature_name;
+
+	if (!boot_cpu_has(X86_FEATURE_AVX) ||
+	    !boot_cpu_has(X86_FEATURE_AES) ||
+	    !boot_cpu_has(X86_FEATURE_OSXSAVE)) {
+		pr_info("AVX or AES-NI instructions are not detected.\n");
+		return -ENODEV;
+	}
+
+	if (!cpu_has_xfeatures(XFEATURE_MASK_SSE | XFEATURE_MASK_YMM,
+				&feature_name)) {
+		pr_info("CPU feature '%s' is not supported.\n", feature_name);
+		return -ENODEV;
+	}
+
+	return simd_register_skciphers_compat(sm4_aesni_avx_skciphers,
+					ARRAY_SIZE(sm4_aesni_avx_skciphers),
+					simd_sm4_aesni_avx_skciphers);
+}
+
+static void __exit sm4_exit(void)
+{
+	simd_unregister_skciphers(sm4_aesni_avx_skciphers,
+					ARRAY_SIZE(sm4_aesni_avx_skciphers),
+					simd_sm4_aesni_avx_skciphers);
+}
+
+module_init(sm4_init);
+module_exit(sm4_exit);
+
+MODULE_LICENSE("GPL v2");
+MODULE_AUTHOR("Tianjia Zhang <tianjia.zhang@linux.alibaba.com>");
+MODULE_DESCRIPTION("SM4 Cipher Algorithm, AES-NI/AVX optimized");
+MODULE_ALIAS_CRYPTO("sm4");
+MODULE_ALIAS_CRYPTO("sm4-aesni-avx");