Received-SPF: pass (google.com: domain of linux-crypto-owner@vger.kernel.org designates 2620:137:e000::1:20 as permitted sender) client-ip=2620:137:e000::1:20;
From:   Taehee Yoo <ap420073@gmail.com>
To:     linux-crypto@vger.kernel.org, herbert@gondor.apana.org.au,
        davem@davemloft.net, tglx@linutronix.de, mingo@redhat.com,
        bp@alien8.de, dave.hansen@linux.intel.com, hpa@zytor.com,
        kirill.shutemov@linux.intel.com, richard@nod.at,
        viro@zeniv.linux.org.uk,
        sathyanarayanan.kuppuswamy@linux.intel.com, jpoimboe@kernel.org,
        elliott@hpe.com, x86@kernel.org, jussi.kivilinna@iki.fi
Cc:     ap420073@gmail.com
Subject: [PATCH v3 1/4] crypto: aria: add keystream array into struct aria_ctx
Date:   Sun,  6 Nov 2022 14:36:24 +0000
Message-Id: <20221106143627.30920-2-ap420073@gmail.com>
In-Reply-To: <20221106143627.30920-1-ap420073@gmail.com>
References: <20221106143627.30920-1-ap420073@gmail.com>
Precedence: bulk

avx accelerated aria module used local keystream array.
But, keystream array size is too big.
So, it puts the keystream array into struct aria_ctx.

Signed-off-by: Taehee Yoo <ap420073@gmail.com>
---

v3:
 - No changes.

v2:
 - Patch introduced.

 arch/x86/crypto/aria-avx.h            |  3 ---
 arch/x86/crypto/aria_aesni_avx_glue.c | 24 +++++++++++-------------
 include/crypto/aria.h                 | 11 +++++++++++
 3 files changed, 22 insertions(+), 16 deletions(-)

diff --git a/arch/x86/crypto/aria-avx.h b/arch/x86/crypto/aria-avx.h
index 01e9a01dc157..afd37af95e58 100644
--- a/arch/x86/crypto/aria-avx.h
+++ b/arch/x86/crypto/aria-avx.h
@@ -4,9 +4,6 @@
 
 #include <linux/types.h>
 
-#define ARIA_AESNI_PARALLEL_BLOCKS 16
-#define ARIA_AESNI_PARALLEL_BLOCK_SIZE  (ARIA_BLOCK_SIZE * 16)
-
 struct aria_avx_ops {
 	void (*aria_encrypt_16way)(const void *ctx, u8 *dst, const u8 *src);
 	void (*aria_decrypt_16way)(const void *ctx, u8 *dst, const u8 *src);
diff --git a/arch/x86/crypto/aria_aesni_avx_glue.c b/arch/x86/crypto/aria_aesni_avx_glue.c
index c561ea4fefa5..b122482d0c9d 100644
--- a/arch/x86/crypto/aria_aesni_avx_glue.c
+++ b/arch/x86/crypto/aria_aesni_avx_glue.c
@@ -86,10 +86,9 @@ static int aria_avx_ctr_encrypt(struct skcipher_request *req)
 		u8 *dst = walk.dst.virt.addr;
 
 		while (nbytes >= ARIA_AESNI_PARALLEL_BLOCK_SIZE) {
-			u8 keystream[ARIA_AESNI_PARALLEL_BLOCK_SIZE];
-
 			kernel_fpu_begin();
-			aria_ops.aria_ctr_crypt_16way(ctx, dst, src, keystream,
+			aria_ops.aria_ctr_crypt_16way(ctx, dst, src,
+						      &ctx->keystream[0],
 						      walk.iv);
 			kernel_fpu_end();
 			dst += ARIA_AESNI_PARALLEL_BLOCK_SIZE;
@@ -98,28 +97,27 @@ static int aria_avx_ctr_encrypt(struct skcipher_request *req)
 		}
 
 		while (nbytes >= ARIA_BLOCK_SIZE) {
-			u8 keystream[ARIA_BLOCK_SIZE];
-
-			memcpy(keystream, walk.iv, ARIA_BLOCK_SIZE);
+			memcpy(&ctx->keystream[0], walk.iv, ARIA_BLOCK_SIZE);
 			crypto_inc(walk.iv, ARIA_BLOCK_SIZE);
 
-			aria_encrypt(ctx, keystream, keystream);
+			aria_encrypt(ctx, &ctx->keystream[0],
+				     &ctx->keystream[0]);
 
-			crypto_xor_cpy(dst, src, keystream, ARIA_BLOCK_SIZE);
+			crypto_xor_cpy(dst, src, &ctx->keystream[0],
+				       ARIA_BLOCK_SIZE);
 			dst += ARIA_BLOCK_SIZE;
 			src += ARIA_BLOCK_SIZE;
 			nbytes -= ARIA_BLOCK_SIZE;
 		}
 
 		if (walk.nbytes == walk.total && nbytes > 0) {
-			u8 keystream[ARIA_BLOCK_SIZE];
-
-			memcpy(keystream, walk.iv, ARIA_BLOCK_SIZE);
+			memcpy(&ctx->keystream[0], walk.iv, ARIA_BLOCK_SIZE);
 			crypto_inc(walk.iv, ARIA_BLOCK_SIZE);
 
-			aria_encrypt(ctx, keystream, keystream);
+			aria_encrypt(ctx, &ctx->keystream[0],
+				     &ctx->keystream[0]);
 
-			crypto_xor_cpy(dst, src, keystream, nbytes);
+			crypto_xor_cpy(dst, src, &ctx->keystream[0], nbytes);
 			dst += nbytes;
 			src += nbytes;
 			nbytes = 0;
diff --git a/include/crypto/aria.h b/include/crypto/aria.h
index 254da46cc385..f5c7a87378cd 100644
--- a/include/crypto/aria.h
+++ b/include/crypto/aria.h
@@ -31,11 +31,22 @@
 #define ARIA_MAX_RD_KEYS	17
 #define ARIA_RD_KEY_WORDS	(ARIA_BLOCK_SIZE / sizeof(u32))
 
+#define ARIA_AESNI_PARALLEL_BLOCKS 16
+#define ARIA_AESNI_PARALLEL_BLOCK_SIZE  (ARIA_BLOCK_SIZE * 16)
+#if defined(CONFIG_CRYPTO_ARIA_AESNI_AVX_X86_64) ||	\
+	defined(CONFIG_CRYPTO_ARIA_AESNI_AVX_X86_64_MODULE)
+#define ARIA_KEYSTREAM_SIZE ARIA_AESNI_PARALLEL_BLOCK_SIZE
+#endif
+
 struct aria_ctx {
 	u32 enc_key[ARIA_MAX_RD_KEYS][ARIA_RD_KEY_WORDS];
 	u32 dec_key[ARIA_MAX_RD_KEYS][ARIA_RD_KEY_WORDS];
 	int rounds;
 	int key_length;
+#if defined(CONFIG_CRYPTO_ARIA_AESNI_AVX_X86_64) ||	\
+	defined(CONFIG_CRYPTO_ARIA_AESNI_AVX_X86_64_MODULE)
+	u8 keystream[ARIA_KEYSTREAM_SIZE];
+#endif
 };
 
 static const u32 s1[256] = {
-- 
2.17.1