From b8d2e7bac3f768e5ab0b52a4a6dd65aa130113be Mon Sep 17 00:00:00 2001 From: Eric Biggers Date: Wed, 16 Oct 2024 17:00:44 -0700 Subject: [PATCH] crypto: x86/aegis128 - eliminate some indirect calls Instead of using a struct of function pointers to decide whether to call the encryption or decryption assembly functions, use a conditional branch on a bool. Force-inline the functions to avoid actually generating the branch. This improves performance slightly since indirect calls are slow. Remove the now-unnecessary CFI stubs. Note that just force-inlining the existing functions might cause the compiler to optimize out the indirect branches, but that would not be a reliable way to do it and the CFI stubs would still be required. Reviewed-by: Ondrej Mosnacek Signed-off-by: Eric Biggers Signed-off-by: Herbert Xu --- arch/x86/crypto/aegis128-aesni-asm.S | 9 ++-- arch/x86/crypto/aegis128-aesni-glue.c | 74 +++++++++++++-------------- 2 files changed, 40 insertions(+), 43 deletions(-) diff --git a/arch/x86/crypto/aegis128-aesni-asm.S b/arch/x86/crypto/aegis128-aesni-asm.S index 2de859173940..1b57558548c7 100644 --- a/arch/x86/crypto/aegis128-aesni-asm.S +++ b/arch/x86/crypto/aegis128-aesni-asm.S @@ -7,7 +7,6 @@ */ #include -#include #include #define STATE0 %xmm0 @@ -403,7 +402,7 @@ SYM_FUNC_END(crypto_aegis128_aesni_ad) * void crypto_aegis128_aesni_enc(void *state, unsigned int length, * const void *src, void *dst); */ -SYM_TYPED_FUNC_START(crypto_aegis128_aesni_enc) +SYM_FUNC_START(crypto_aegis128_aesni_enc) FRAME_BEGIN cmp $0x10, LEN @@ -500,7 +499,7 @@ SYM_FUNC_END(crypto_aegis128_aesni_enc) * void crypto_aegis128_aesni_enc_tail(void *state, unsigned int length, * const void *src, void *dst); */ -SYM_TYPED_FUNC_START(crypto_aegis128_aesni_enc_tail) +SYM_FUNC_START(crypto_aegis128_aesni_enc_tail) FRAME_BEGIN /* load the state: */ @@ -557,7 +556,7 @@ SYM_FUNC_END(crypto_aegis128_aesni_enc_tail) * void crypto_aegis128_aesni_dec(void *state, unsigned int length, * const void *src, void *dst); */ -SYM_TYPED_FUNC_START(crypto_aegis128_aesni_dec) +SYM_FUNC_START(crypto_aegis128_aesni_dec) FRAME_BEGIN cmp $0x10, LEN @@ -654,7 +653,7 @@ SYM_FUNC_END(crypto_aegis128_aesni_dec) * void crypto_aegis128_aesni_dec_tail(void *state, unsigned int length, * const void *src, void *dst); */ -SYM_TYPED_FUNC_START(crypto_aegis128_aesni_dec_tail) +SYM_FUNC_START(crypto_aegis128_aesni_dec_tail) FRAME_BEGIN /* load the state: */ diff --git a/arch/x86/crypto/aegis128-aesni-glue.c b/arch/x86/crypto/aegis128-aesni-glue.c index 96586470154e..deb39cef0be1 100644 --- a/arch/x86/crypto/aegis128-aesni-glue.c +++ b/arch/x86/crypto/aegis128-aesni-glue.c @@ -56,16 +56,6 @@ struct aegis_ctx { struct aegis_block key; }; -struct aegis_crypt_ops { - int (*skcipher_walk_init)(struct skcipher_walk *walk, - struct aead_request *req, bool atomic); - - void (*crypt_blocks)(void *state, unsigned int length, const void *src, - void *dst); - void (*crypt_tail)(void *state, unsigned int length, const void *src, - void *dst); -}; - static void crypto_aegis128_aesni_process_ad( struct aegis_state *state, struct scatterlist *sg_src, unsigned int assoclen) @@ -114,20 +104,37 @@ static void crypto_aegis128_aesni_process_ad( } } -static void crypto_aegis128_aesni_process_crypt( - struct aegis_state *state, struct skcipher_walk *walk, - const struct aegis_crypt_ops *ops) +static __always_inline void +crypto_aegis128_aesni_process_crypt(struct aegis_state *state, + struct skcipher_walk *walk, bool enc) { while (walk->nbytes >= AEGIS128_BLOCK_SIZE) { - ops->crypt_blocks(state, - round_down(walk->nbytes, AEGIS128_BLOCK_SIZE), - walk->src.virt.addr, walk->dst.virt.addr); + if (enc) + crypto_aegis128_aesni_enc( + state, + round_down(walk->nbytes, + AEGIS128_BLOCK_SIZE), + walk->src.virt.addr, + walk->dst.virt.addr); + else + crypto_aegis128_aesni_dec( + state, + round_down(walk->nbytes, + AEGIS128_BLOCK_SIZE), + walk->src.virt.addr, + walk->dst.virt.addr); skcipher_walk_done(walk, walk->nbytes % AEGIS128_BLOCK_SIZE); } if (walk->nbytes) { - ops->crypt_tail(state, walk->nbytes, walk->src.virt.addr, - walk->dst.virt.addr); + if (enc) + crypto_aegis128_aesni_enc_tail(state, walk->nbytes, + walk->src.virt.addr, + walk->dst.virt.addr); + else + crypto_aegis128_aesni_dec_tail(state, walk->nbytes, + walk->src.virt.addr, + walk->dst.virt.addr); skcipher_walk_done(walk, 0); } } @@ -162,23 +169,26 @@ static int crypto_aegis128_aesni_setauthsize(struct crypto_aead *tfm, return 0; } -static void crypto_aegis128_aesni_crypt(struct aead_request *req, - struct aegis_block *tag_xor, - unsigned int cryptlen, - const struct aegis_crypt_ops *ops) +static __always_inline void +crypto_aegis128_aesni_crypt(struct aead_request *req, + struct aegis_block *tag_xor, + unsigned int cryptlen, bool enc) { struct crypto_aead *tfm = crypto_aead_reqtfm(req); struct aegis_ctx *ctx = crypto_aegis128_aesni_ctx(tfm); struct skcipher_walk walk; struct aegis_state state; - ops->skcipher_walk_init(&walk, req, true); + if (enc) + skcipher_walk_aead_encrypt(&walk, req, true); + else + skcipher_walk_aead_decrypt(&walk, req, true); kernel_fpu_begin(); crypto_aegis128_aesni_init(&state, ctx->key.bytes, req->iv); crypto_aegis128_aesni_process_ad(&state, req->src, req->assoclen); - crypto_aegis128_aesni_process_crypt(&state, &walk, ops); + crypto_aegis128_aesni_process_crypt(&state, &walk, enc); crypto_aegis128_aesni_final(&state, tag_xor, req->assoclen, cryptlen); kernel_fpu_end(); @@ -186,18 +196,12 @@ static void crypto_aegis128_aesni_crypt(struct aead_request *req, static int crypto_aegis128_aesni_encrypt(struct aead_request *req) { - static const struct aegis_crypt_ops OPS = { - .skcipher_walk_init = skcipher_walk_aead_encrypt, - .crypt_blocks = crypto_aegis128_aesni_enc, - .crypt_tail = crypto_aegis128_aesni_enc_tail, - }; - struct crypto_aead *tfm = crypto_aead_reqtfm(req); struct aegis_block tag = {}; unsigned int authsize = crypto_aead_authsize(tfm); unsigned int cryptlen = req->cryptlen; - crypto_aegis128_aesni_crypt(req, &tag, cryptlen, &OPS); + crypto_aegis128_aesni_crypt(req, &tag, cryptlen, true); scatterwalk_map_and_copy(tag.bytes, req->dst, req->assoclen + cryptlen, authsize, 1); @@ -208,12 +212,6 @@ static int crypto_aegis128_aesni_decrypt(struct aead_request *req) { static const struct aegis_block zeros = {}; - static const struct aegis_crypt_ops OPS = { - .skcipher_walk_init = skcipher_walk_aead_decrypt, - .crypt_blocks = crypto_aegis128_aesni_dec, - .crypt_tail = crypto_aegis128_aesni_dec_tail, - }; - struct crypto_aead *tfm = crypto_aead_reqtfm(req); struct aegis_block tag; unsigned int authsize = crypto_aead_authsize(tfm); @@ -222,7 +220,7 @@ static int crypto_aegis128_aesni_decrypt(struct aead_request *req) scatterwalk_map_and_copy(tag.bytes, req->src, req->assoclen + cryptlen, authsize, 0); - crypto_aegis128_aesni_crypt(req, &tag, cryptlen, &OPS); + crypto_aegis128_aesni_crypt(req, &tag, cryptlen, false); return crypto_memneq(tag.bytes, zeros.bytes, authsize) ? -EBADMSG : 0; } -- 2.50.1