crypto: arm64/sm4 - add CE implementation for GCM mode

This patch is a CE-optimized assembly implementation for GCM mode.

Benchmark on T-Head Yitian-710 2.75 GHz, the data comes from the 224 and 224
modes of tcrypt, and compared the performance before and after this patch (the
driver used before this patch is gcm_base(ctr-sm4-ce,ghash-generic)).
The abscissas are blocks of different lengths. The data is tabulated and the
unit is Mb/s:

Before (gcm_base(ctr-sm4-ce,ghash-generic)):

gcm(sm4)     |     16      64      256      512     1024     1420     4096     8192
-------------+---------------------------------------------------------------------
  GCM enc    |  25.24   64.65   104.66   116.69   123.81   125.12   129.67   130.62
  GCM dec    |  25.40   64.80   104.74   116.70   123.81   125.21   129.68   130.59
  GCM mb enc |  24.95   64.06   104.20   116.38   123.55   124.97   129.63   130.61
  GCM mb dec |  24.92   64.00   104.13   116.34   123.55   124.98   129.56   130.48

After:

gcm-sm4-ce   |     16      64      256      512     1024     1420     4096     8192
-------------+---------------------------------------------------------------------
  GCM enc    | 108.62  397.18   971.60  1283.92  1522.77  1513.39  1777.00  1806.96
  GCM dec    | 116.36  398.14  1004.27  1319.11  1624.21  1635.43  1932.54  1974.20
  GCM mb enc | 107.13  391.79   962.05  1274.94  1514.76  1508.57  1769.07  1801.58
  GCM mb dec | 113.40  389.36   988.51  1307.68  1619.10  1631.55  1931.70  1970.86

Signed-off-by: Tianjia Zhang <[email protected]>
Signed-off-by: Herbert Xu <[email protected]>

arch/arm64/crypto/Kconfig

@@ -297,6 +297,22 @@ config CRYPTO_SM4_ARM64_CE_CCM
 	  - ARMv8 Crypto Extensions
 	  - NEON (Advanced SIMD) extensions
 
+config CRYPTO_SM4_ARM64_CE_GCM
+	tristate "AEAD cipher: SM4 in GCM mode (ARMv8 Crypto Extensions)"
+	depends on KERNEL_MODE_NEON
+	select CRYPTO_ALGAPI
+	select CRYPTO_AEAD
+	select CRYPTO_SM4
+	select CRYPTO_SM4_ARM64_CE_BLK
+	help
+	  AEAD cipher: SM4 cipher algorithms (OSCCA GB/T 32907-2016) with
+	  GCM (Galois/Counter Mode) authenticated encryption mode (NIST SP800-38D)
+
+	  Architecture: arm64 using:
+	  - ARMv8 Crypto Extensions
+	  - PMULL (Polynomial Multiply Long) instructions
+	  - NEON (Advanced SIMD) extensions
+
 config CRYPTO_CRCT10DIF_ARM64_CE
 	tristate "CRCT10DIF (PMULL)"
 	depends on KERNEL_MODE_NEON && CRC_T10DIF

arch/arm64/crypto/Makefile

@@ -32,6 +32,9 @@ sm4-ce-y := sm4-ce-glue.o sm4-ce-core.o
 obj-$(CONFIG_CRYPTO_SM4_ARM64_CE_CCM) += sm4-ce-ccm.o
 sm4-ce-ccm-y := sm4-ce-ccm-glue.o sm4-ce-ccm-core.o
 
+obj-$(CONFIG_CRYPTO_SM4_ARM64_CE_GCM) += sm4-ce-gcm.o
+sm4-ce-gcm-y := sm4-ce-gcm-glue.o sm4-ce-gcm-core.o
+
 obj-$(CONFIG_CRYPTO_SM4_ARM64_NEON_BLK) += sm4-neon.o
 sm4-neon-y := sm4-neon-glue.o sm4-neon-core.o