From 2d3b6fae7d1a2ad821769440daa91d7eec5c8250 Mon Sep 17 00:00:00 2001 From: Eneas U de Queiroz Date: Fri, 20 Dec 2019 09:41:44 -0300 Subject: [PATCH] crypto: qce - use AES fallback for small requests Process small blocks using the fallback cipher, as a workaround for an observed failure (DMA-related, apparently) when computing the GCM ghash key. This brings a speed gain as well, since it avoids the latency of using the hardware engine to process small blocks. Using software for all 16-byte requests would be enough to make GCM work, but to increase performance, a larger threshold would be better. Measuring the performance of supported ciphers with openssl speed, software matches hardware at around 768-1024 bytes. Considering the 256-bit ciphers, software is 2-3 times faster than qce at 256-bytes, 30% faster at 512, and about even at 768-bytes. With 128-bit keys, the break-even point would be around 1024-bytes. This adds the 'aes_sw_max_len' parameter, to set the largest request length processed by the software fallback. Its default is being set to 512 bytes, a little lower than the break-even point, to balance the cost in CPU usage. Signed-off-by: Eneas U de Queiroz --- a/drivers/crypto/Kconfig +++ b/drivers/crypto/Kconfig @@ -585,6 +585,29 @@ config CRYPTO_DEV_QCE hardware. To compile this driver as a module, choose M here. The module will be called qcrypto. +config CRYPTO_DEV_QCE_SW_MAX_LEN + int "Default maximum request size to use software for AES" + depends on CRYPTO_DEV_QCE && CRYPTO_DEV_QCE_SKCIPHER + default 512 + help + This sets the default maximum request size to perform AES requests + using software instead of the crypto engine. It can be changed by + setting the aes_sw_max_len parameter. + + Small blocks are processed faster in software than hardware. + Considering the 256-bit ciphers, software is 2-3 times faster than + qce at 256-bytes, 30% faster at 512, and about even at 768-bytes. + With 128-bit keys, the break-even point would be around 1024-bytes. + + The default is set a little lower, to 512 bytes, to balance the + cost in CPU usage. The minimum recommended setting is 16-bytes + (1 AES block), since AES-GCM will fail if you set it lower. + Setting this to zero will send all requests to the hardware. + + Note that 192-bit keys are not supported by the hardware and are + always processed by the software fallback, and all DES requests + are done by the hardware. + config CRYPTO_DEV_QCOM_RNG tristate "Qualcomm Random Number Generator Driver" depends on ARCH_QCOM || COMPILE_TEST --- a/drivers/crypto/qce/skcipher.c +++ b/drivers/crypto/qce/skcipher.c @@ -13,6 +13,7 @@ #include #include +#include #include #include #include @@ -20,6 +21,13 @@ #include "cipher.h" +static unsigned int aes_sw_max_len = CONFIG_CRYPTO_DEV_QCE_SW_MAX_LEN; +module_param(aes_sw_max_len, uint, 0644); +MODULE_PARM_DESC(aes_sw_max_len, + "Only use hardware for AES requests larger than this " + "[0=always use hardware; anything <16 breaks AES-GCM; default=" + __stringify(CONFIG_CRYPTO_DEV_QCE_SOFT_THRESHOLD)"]"); + static LIST_HEAD(skcipher_algs); static void qce_skcipher_done(void *data) @@ -170,15 +178,7 @@ static int qce_skcipher_setkey(struct cr if (!key || !keylen) return -EINVAL; - if (IS_AES(flags)) { - switch (IS_XTS(flags) ? keylen >> 1 : keylen) { - case AES_KEYSIZE_128: - case AES_KEYSIZE_256: - break; - default: - goto fallback; - } - } else if (IS_DES(flags)) { + if (IS_DES(flags)) { u32 tmp[DES_EXPKEY_WORDS]; ret = des_ekey(tmp, key); @@ -189,8 +189,8 @@ static int qce_skcipher_setkey(struct cr ctx->enc_keylen = keylen; memcpy(ctx->enc_key, key, keylen); - return 0; -fallback: + if (!IS_AES(flags)) + return 0; ret = crypto_skcipher_setkey(ctx->fallback, key, keylen); if (!ret) ctx->enc_keylen = keylen; @@ -213,8 +213,9 @@ static int qce_skcipher_crypt(struct skc rctx->flags |= encrypt ? QCE_ENCRYPT : QCE_DECRYPT; keylen = IS_XTS(rctx->flags) ? ctx->enc_keylen >> 1 : ctx->enc_keylen; - if (IS_AES(rctx->flags) && keylen != AES_KEYSIZE_128 && - keylen != AES_KEYSIZE_256) { + if (IS_AES(rctx->flags) && + ((keylen != AES_KEYSIZE_128 && keylen != AES_KEYSIZE_256) || + req->cryptlen <= aes_sw_max_len)) { SKCIPHER_REQUEST_ON_STACK(subreq, ctx->fallback); skcipher_request_set_tfm(subreq, ctx->fallback);