Implement a faster version of the GHASH transform which amortizes the
reduction modulo the characteristic polynomial across two input blocks at
a time. This is based on the Intel white paper "Carry-Less Multiplication
Instruction and its Usage for Computing the GCM Mode"

On a Cortex-A53, the gcm(aes) performance increases 24%, from 3.0 cycles per
byte to 2.4 cpb for large input sizes.

Signed-off-by: Ard Biesheuvel <ard.biesheu...@linaro.org>
---
Raw numbers after the patch

 arch/arm64/crypto/ghash-ce-core.S | 87 +++++++-------------
 arch/arm64/crypto/ghash-ce-glue.c | 33 ++++++--
 2 files changed, 54 insertions(+), 66 deletions(-)

diff --git a/arch/arm64/crypto/ghash-ce-core.S 
b/arch/arm64/crypto/ghash-ce-core.S
index 437a2fb0f7f9..c144b526abe6 100644
--- a/arch/arm64/crypto/ghash-ce-core.S
+++ b/arch/arm64/crypto/ghash-ce-core.S
@@ -290,6 +290,11 @@ ENDPROC(pmull_ghash_update_p8)
        KS1             .req    v9
        INP0            .req    v10
        INP1            .req    v11
+       HH              .req    v12
+       Hhl             .req    v13
+       XLn             .req    v14
+       XMn             .req    v15
+       XHn             .req    v16
 
        .macro          load_round_keys, rounds, rk
        cmp             \rounds, #12
@@ -342,13 +347,13 @@ CPU_LE(   rev             x28, x28        )
 
 0:     mov             x0, x25
        load_round_keys w26, x0
-       ld1             {SHASH.2d}, [x23]
+       add             x1, x23, #32
+       ld1             {HH.2d-Hhl.2d}, [x23]
+       ld1             {SHASH.2d}, [x1]
        ld1             {XL.2d}, [x20]
 
        movi            MASK.16b, #0xe1
-       ext             SHASH2.16b, SHASH.16b, SHASH.16b, #8
        shl             MASK.2d, MASK.2d, #57
-       eor             SHASH2.16b, SHASH2.16b, SHASH.16b
 
        .if             \enc == 1
        ld1             {KS0.16b-KS1.16b}, [x27]
@@ -372,116 +377,82 @@ CPU_LE(  rev             x28, x28        )
        ins             KS0.d[1], x9                    // set lower counter
        ins             KS1.d[1], x10
 
-       rev64           T1.16b, INP0.16b
+       rev64           T1.16b, INP1.16b
 
        cmp             w26, #12
        b.ge            4f                              // AES-192/256?
 
 2:     enc_round       KS0, v21
-
-       ext             T2.16b, XL.16b, XL.16b, #8
        ext             IN1.16b, T1.16b, T1.16b, #8
 
        enc_round       KS1, v21
-
-       eor             T1.16b, T1.16b, T2.16b
-       eor             XL.16b, XL.16b, IN1.16b
+       pmull2          XHn.1q, SHASH.2d, IN1.2d        // a1 * b1
 
        enc_round       KS0, v22
-
-       pmull2          XH.1q, SHASH.2d, XL.2d          // a1 * b1
-       eor             T1.16b, T1.16b, XL.16b
+       eor             T1.16b, T1.16b, IN1.16b
 
        enc_round       KS1, v22
-
-       pmull           XL.1q, SHASH.1d, XL.1d          // a0 * b0
-       pmull           XM.1q, SHASH2.1d, T1.1d         // (a1 + a0)(b1 + b0)
+       pmull           XLn.1q, SHASH.1d, IN1.1d        // a0 * b0
 
        enc_round       KS0, v23
-
-       ext             T1.16b, XL.16b, XH.16b, #8
-       eor             T2.16b, XL.16b, XH.16b
-       eor             XM.16b, XM.16b, T1.16b
+       pmull           XMn.1q, Hhl.1d, T1.1d           // (a1 + a0)(b1 + b0)
 
        enc_round       KS1, v23
-
-       eor             XM.16b, XM.16b, T2.16b
-       pmull           T2.1q, XL.1d, MASK.1d
+       rev64           T1.16b, INP0.16b
+       ext             T2.16b, XL.16b, XL.16b, #8
 
        enc_round       KS0, v24
-
-       mov             XH.d[0], XM.d[1]
-       mov             XM.d[1], XL.d[0]
+       ext             IN1.16b, T1.16b, T1.16b, #8
+       eor             T1.16b, T1.16b, T2.16b
 
        enc_round       KS1, v24
-
-       eor             XL.16b, XM.16b, T2.16b
+       eor             XL.16b, XL.16b, IN1.16b
 
        enc_round       KS0, v25
-
-       ext             T2.16b, XL.16b, XL.16b, #8
+       pmull2          XH.1q, HH.2d, XL.2d             // a1 * b1
 
        enc_round       KS1, v25
-
-       pmull           XL.1q, XL.1d, MASK.1d
-       eor             T2.16b, T2.16b, XH.16b
+       eor             T1.16b, T1.16b, XL.16b
 
        enc_round       KS0, v26
-
-       eor             XL.16b, XL.16b, T2.16b
-       rev64           T1.16b, INP1.16b
+       pmull           XL.1q, HH.1d, XL.1d             // a0 * b0
 
        enc_round       KS1, v26
-
-       ext             T2.16b, XL.16b, XL.16b, #8
-       ext             IN1.16b, T1.16b, T1.16b, #8
+       pmull2          XM.1q, Hhl.2d, T1.2d            // (a1 + a0)(b1 + b0)
 
        enc_round       KS0, v27
-
-       eor             T1.16b, T1.16b, T2.16b
-       eor             XL.16b, XL.16b, IN1.16b
+       eor             XH.16b, XH.16b, XHn.16b
+       eor             XM.16b, XM.16b, XMn.16b
 
        enc_round       KS1, v27
-
-       pmull2          XH.1q, SHASH.2d, XL.2d          // a1 * b1
-       eor             T1.16b, T1.16b, XL.16b
+       eor             XL.16b, XL.16b, XLn.16b
+       ext             T1.16b, XL.16b, XH.16b, #8
 
        enc_round       KS0, v28
-
-       pmull           XL.1q, SHASH.1d, XL.1d          // a0 * b0
-       pmull           XM.1q, SHASH2.1d, T1.1d         // (a1 + a0)(b1 + b0)
-
-       enc_round       KS1, v28
-
-       ext             T1.16b, XL.16b, XH.16b, #8
        eor             T2.16b, XL.16b, XH.16b
        eor             XM.16b, XM.16b, T1.16b
 
-       enc_round       KS0, v29
-
+       enc_round       KS1, v28
        eor             XM.16b, XM.16b, T2.16b
+
+       enc_round       KS0, v29
        pmull           T2.1q, XL.1d, MASK.1d
 
        enc_round       KS1, v29
-
        mov             XH.d[0], XM.d[1]
        mov             XM.d[1], XL.d[0]
 
        aese            KS0.16b, v30.16b
-
        eor             XL.16b, XM.16b, T2.16b
 
        aese            KS1.16b, v30.16b
-
        ext             T2.16b, XL.16b, XL.16b, #8
 
        eor             KS0.16b, KS0.16b, v31.16b
-
        pmull           XL.1q, XL.1d, MASK.1d
        eor             T2.16b, T2.16b, XH.16b
 
        eor             KS1.16b, KS1.16b, v31.16b
-
        eor             XL.16b, XL.16b, T2.16b
 
        .if             \enc == 0
diff --git a/arch/arm64/crypto/ghash-ce-glue.c 
b/arch/arm64/crypto/ghash-ce-glue.c
index 371f8368c196..65a0b8239620 100644
--- a/arch/arm64/crypto/ghash-ce-glue.c
+++ b/arch/arm64/crypto/ghash-ce-glue.c
@@ -46,6 +46,8 @@ struct ghash_desc_ctx {
 
 struct gcm_aes_ctx {
        struct crypto_aes_ctx   aes_key;
+       u64                     h2[2];
+       u64                     hhl[2];
        struct ghash_key        ghash_key;
 };
 
@@ -62,12 +64,11 @@ static void (*pmull_ghash_update)(int blocks, u64 dg[], 
const char *src,
                                  const char *head);
 
 asmlinkage void pmull_gcm_encrypt(int blocks, u64 dg[], u8 dst[],
-                                 const u8 src[], struct ghash_key const *k,
-                                 u8 ctr[], u32 const rk[], int rounds,
-                                 u8 ks[]);
+                                 const u8 src[], u64 const *k, u8 ctr[],
+                                 u32 const rk[], int rounds, u8 ks[]);
 
 asmlinkage void pmull_gcm_decrypt(int blocks, u64 dg[], u8 dst[],
-                                 const u8 src[], struct ghash_key const *k,
+                                 const u8 src[], u64 const *k,
                                  u8 ctr[], u32 const rk[], int rounds);
 
 asmlinkage void pmull_gcm_encrypt_block(u8 dst[], u8 const src[],
@@ -233,7 +234,8 @@ static int gcm_setkey(struct crypto_aead *tfm, const u8 
*inkey,
                      unsigned int keylen)
 {
        struct gcm_aes_ctx *ctx = crypto_aead_ctx(tfm);
-       u8 key[GHASH_BLOCK_SIZE];
+       be128 h1, h2;
+       u8 *key = (u8 *)&h1;
        int ret;
 
        ret = crypto_aes_expand_key(&ctx->aes_key, inkey, keylen);
@@ -245,7 +247,22 @@ static int gcm_setkey(struct crypto_aead *tfm, const u8 
*inkey,
        __aes_arm64_encrypt(ctx->aes_key.key_enc, key, (u8[AES_BLOCK_SIZE]){},
                            num_rounds(&ctx->aes_key));
 
-       return __ghash_setkey(&ctx->ghash_key, key, sizeof(key));
+       __ghash_setkey(&ctx->ghash_key, key, sizeof(be128));
+
+       /* calculate H^2 and Hhl (used for 2-way aggregation) */
+       h2 = h1;
+       gf128mul_lle(&h2, &h1);
+
+       ctx->h2[0] = (be64_to_cpu(h2.b) << 1) | (be64_to_cpu(h2.a) >> 63);
+       ctx->h2[1] = (be64_to_cpu(h2.a) << 1) | (be64_to_cpu(h2.b) >> 63);
+
+       if (be64_to_cpu(h2.a) >> 63)
+               ctx->h2[1] ^= 0xc200000000000000UL;
+
+       ctx->hhl[0] = ctx->ghash_key.a ^ ctx->ghash_key.b;
+       ctx->hhl[1] = ctx->h2[0] ^ ctx->h2[1];
+
+       return 0;
 }
 
 static int gcm_setauthsize(struct crypto_aead *tfm, unsigned int authsize)
@@ -381,7 +398,7 @@ static int gcm_encrypt(struct aead_request *req)
 
                        kernel_neon_begin();
                        pmull_gcm_encrypt(blocks, dg, walk.dst.virt.addr,
-                                         walk.src.virt.addr, &ctx->ghash_key,
+                                         walk.src.virt.addr, ctx->h2,
                                          iv, ctx->aes_key.key_enc,
                                          num_rounds(&ctx->aes_key), ks);
                        kernel_neon_end();
@@ -490,7 +507,7 @@ static int gcm_decrypt(struct aead_request *req)
 
                        kernel_neon_begin();
                        pmull_gcm_decrypt(blocks, dg, walk.dst.virt.addr,
-                                         walk.src.virt.addr, &ctx->ghash_key,
+                                         walk.src.virt.addr, ctx->h2,
                                          iv, ctx->aes_key.key_enc, nrounds);
                        kernel_neon_end();
 
-- 
2.18.0

tcrypt performance numbers for a Cortex-A53 @ 1 GHz (CONFIG_PREEMPT disabled)

BASELINE:
=========
test  0 (128 bit key,   16 byte blocks): 445165 operations in 1 seconds (  
7122640 bytes)
test  1 (128 bit key,   64 byte blocks): 437076 operations in 1 seconds ( 
27972864 bytes)
test  2 (128 bit key,  256 byte blocks): 354203 operations in 1 seconds ( 
90675968 bytes)
test  3 (128 bit key,  512 byte blocks): 284031 operations in 1 seconds 
(145423872 bytes)
test  4 (128 bit key, 1024 byte blocks): 203473 operations in 1 seconds 
(208356352 bytes)
test  5 (128 bit key, 2048 byte blocks): 129855 operations in 1 seconds 
(265943040 bytes)
test  6 (128 bit key, 4096 byte blocks):  75686 operations in 1 seconds 
(310009856 bytes)
test  7 (128 bit key, 8192 byte blocks):  40167 operations in 1 seconds 
(329048064 bytes)
test  8 (192 bit key,   16 byte blocks): 441610 operations in 1 seconds (  
7065760 bytes)
test  9 (192 bit key,   64 byte blocks): 429364 operations in 1 seconds ( 
27479296 bytes)
test 10 (192 bit key,  256 byte blocks): 343303 operations in 1 seconds ( 
87885568 bytes)
test 11 (192 bit key,  512 byte blocks): 272029 operations in 1 seconds 
(139278848 bytes)
test 12 (192 bit key, 1024 byte blocks): 192399 operations in 1 seconds 
(197016576 bytes)
test 13 (192 bit key, 2048 byte blocks): 121298 operations in 1 seconds 
(248418304 bytes)
test 14 (192 bit key, 4096 byte blocks):  69994 operations in 1 seconds 
(286695424 bytes)
test 15 (192 bit key, 8192 byte blocks):  37045 operations in 1 seconds 
(303472640 bytes)
test 16 (256 bit key,   16 byte blocks): 438244 operations in 1 seconds (  
7011904 bytes)
test 17 (256 bit key,   64 byte blocks): 423345 operations in 1 seconds ( 
27094080 bytes)
test 18 (256 bit key,  256 byte blocks): 336844 operations in 1 seconds ( 
86232064 bytes)
test 19 (256 bit key,  512 byte blocks): 265711 operations in 1 seconds 
(136044032 bytes)
test 20 (256 bit key, 1024 byte blocks): 186853 operations in 1 seconds 
(191337472 bytes)
test 21 (256 bit key, 2048 byte blocks): 117301 operations in 1 seconds 
(240232448 bytes)
test 22 (256 bit key, 4096 byte blocks):  67513 operations in 1 seconds 
(276533248 bytes)
test 23 (256 bit key, 8192 byte blocks):  35629 operations in 1 seconds 
(291872768 bytes)


THIS PATCH:
===========
test  0 (128 bit key,   16 byte blocks): 441257 operations in 1 seconds (  
7060112 bytes)
test  1 (128 bit key,   64 byte blocks): 436595 operations in 1 seconds ( 
27942080 bytes)
test  2 (128 bit key,  256 byte blocks): 369839 operations in 1 seconds ( 
94678784 bytes)
test  3 (128 bit key,  512 byte blocks): 308239 operations in 1 seconds 
(157818368 bytes)
test  4 (128 bit key, 1024 byte blocks): 231004 operations in 1 seconds 
(236548096 bytes)
test  5 (128 bit key, 2048 byte blocks): 153930 operations in 1 seconds 
(315248640 bytes)
test  6 (128 bit key, 4096 byte blocks):  92739 operations in 1 seconds 
(379858944 bytes)
test  7 (128 bit key, 8192 byte blocks):  49934 operations in 1 seconds 
(409059328 bytes)
test  8 (192 bit key,   16 byte blocks): 437427 operations in 1 seconds (  
6998832 bytes)
test  9 (192 bit key,   64 byte blocks): 429462 operations in 1 seconds ( 
27485568 bytes)
test 10 (192 bit key,  256 byte blocks): 358183 operations in 1 seconds ( 
91694848 bytes)
test 11 (192 bit key,  512 byte blocks): 294539 operations in 1 seconds 
(150803968 bytes)
test 12 (192 bit key, 1024 byte blocks): 217082 operations in 1 seconds 
(222291968 bytes)
test 13 (192 bit key, 2048 byte blocks): 140672 operations in 1 seconds 
(288096256 bytes)
test 14 (192 bit key, 4096 byte blocks):  84369 operations in 1 seconds 
(345575424 bytes)
test 15 (192 bit key, 8192 byte blocks):  45280 operations in 1 seconds 
(370933760 bytes)
test 16 (256 bit key,   16 byte blocks): 434127 operations in 1 seconds (  
6946032 bytes)
test 17 (256 bit key,   64 byte blocks): 423837 operations in 1 seconds ( 
27125568 bytes)
test 18 (256 bit key,  256 byte blocks): 351244 operations in 1 seconds ( 
89918464 bytes)
test 19 (256 bit key,  512 byte blocks): 286884 operations in 1 seconds 
(146884608 bytes)
test 20 (256 bit key, 1024 byte blocks): 209954 operations in 1 seconds 
(214992896 bytes)
test 21 (256 bit key, 2048 byte blocks): 136553 operations in 1 seconds 
(279660544 bytes)
test 22 (256 bit key, 4096 byte blocks):  80749 operations in 1 seconds 
(330747904 bytes)
test 23 (256 bit key, 8192 byte blocks):  43118 operations in 1 seconds 
(353222656 bytes)

Reply via email to