Add an accelerated version of the 'essiv(cbc(aes),aes,sha256' skcipher, which is used by fscrypt or dm-crypt on systems where CBC mode is signficantly more performant than XTS mode (e.g., when using a h/w accelerator which supports the former but not the latter) This avoids a separate call into the AES cipher for every invocation. Signed-off-by: Ard Biesheuvel <ard.biesheuvel@xxxxxxxxxx> --- arch/arm64/crypto/aes-glue.c | 123 ++++++++++++++++++++ arch/arm64/crypto/aes-modes.S | 29 ++++- 2 files changed, 151 insertions(+), 1 deletion(-) diff --git a/arch/arm64/crypto/aes-glue.c b/arch/arm64/crypto/aes-glue.c index 11b85ce02d7a..7097739e7cd9 100644 --- a/arch/arm64/crypto/aes-glue.c +++ b/arch/arm64/crypto/aes-glue.c @@ -12,6 +12,7 @@ #include <asm/hwcap.h> #include <asm/simd.h> #include <crypto/aes.h> +#include <crypto/sha.h> #include <crypto/internal/hash.h> #include <crypto/internal/simd.h> #include <crypto/internal/skcipher.h> @@ -34,6 +35,8 @@ #define aes_cbc_decrypt ce_aes_cbc_decrypt #define aes_cbc_cts_encrypt ce_aes_cbc_cts_encrypt #define aes_cbc_cts_decrypt ce_aes_cbc_cts_decrypt +#define aes_essiv_cbc_encrypt ce_aes_essiv_cbc_encrypt +#define aes_essiv_cbc_decrypt ce_aes_essiv_cbc_decrypt #define aes_ctr_encrypt ce_aes_ctr_encrypt #define aes_xts_encrypt ce_aes_xts_encrypt #define aes_xts_decrypt ce_aes_xts_decrypt @@ -50,6 +53,8 @@ MODULE_DESCRIPTION("AES-ECB/CBC/CTR/XTS using ARMv8 Crypto Extensions"); #define aes_cbc_decrypt neon_aes_cbc_decrypt #define aes_cbc_cts_encrypt neon_aes_cbc_cts_encrypt #define aes_cbc_cts_decrypt neon_aes_cbc_cts_decrypt +#define aes_essiv_cbc_encrypt neon_aes_essiv_cbc_encrypt +#define aes_essiv_cbc_decrypt neon_aes_essiv_cbc_decrypt #define aes_ctr_encrypt neon_aes_ctr_encrypt #define aes_xts_encrypt neon_aes_xts_encrypt #define aes_xts_decrypt neon_aes_xts_decrypt @@ -93,6 +98,13 @@ asmlinkage void aes_xts_decrypt(u8 out[], u8 const in[], u32 const rk1[], int rounds, int blocks, u32 const rk2[], u8 iv[], int first); +asmlinkage void aes_essiv_cbc_encrypt(u8 out[], u8 const in[], u32 const rk1[], + int rounds, int blocks, u8 iv[], + u32 const rk2[]); +asmlinkage void aes_essiv_cbc_decrypt(u8 out[], u8 const in[], u32 const rk1[], + int rounds, int blocks, u8 iv[], + u32 const rk2[]); + asmlinkage void aes_mac_update(u8 const in[], u32 const rk[], int rounds, int blocks, u8 dg[], int enc_before, int enc_after); @@ -108,6 +120,12 @@ struct crypto_aes_xts_ctx { struct crypto_aes_ctx __aligned(8) key2; }; +struct crypto_aes_essiv_cbc_ctx { + struct crypto_aes_ctx key1; + struct crypto_aes_ctx __aligned(8) key2; + struct crypto_shash *hash; +}; + struct mac_tfm_ctx { struct crypto_aes_ctx key; u8 __aligned(8) consts[]; @@ -145,6 +163,31 @@ static int xts_set_key(struct crypto_skcipher *tfm, const u8 *in_key, return -EINVAL; } +static int essiv_cbc_set_key(struct crypto_skcipher *tfm, const u8 *in_key, + unsigned int key_len) +{ + struct crypto_aes_essiv_cbc_ctx *ctx = crypto_skcipher_ctx(tfm); + SHASH_DESC_ON_STACK(desc, ctx->hash); + u8 digest[SHA256_DIGEST_SIZE]; + int ret; + + ret = aes_expandkey(&ctx->key1, in_key, key_len); + if (ret) + goto out; + + desc->tfm = ctx->hash; + crypto_shash_digest(desc, in_key, key_len, digest); + + ret = aes_expandkey(&ctx->key2, digest, sizeof(digest)); + if (ret) + goto out; + + return 0; +out: + crypto_skcipher_set_flags(tfm, CRYPTO_TFM_RES_BAD_KEY_LEN); + return -EINVAL; +} + static int ecb_encrypt(struct skcipher_request *req) { struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req); @@ -359,6 +402,68 @@ static int cts_cbc_decrypt(struct skcipher_request *req) return skcipher_walk_done(&walk, 0); } +static int essiv_cbc_init_tfm(struct crypto_skcipher *tfm) +{ + struct crypto_aes_essiv_cbc_ctx *ctx = crypto_skcipher_ctx(tfm); + + ctx->hash = crypto_alloc_shash("sha256", 0, 0); + if (IS_ERR(ctx->hash)) + return PTR_ERR(ctx->hash); + + return 0; +} + +static void essiv_cbc_exit_tfm(struct crypto_skcipher *tfm) +{ + struct crypto_aes_essiv_cbc_ctx *ctx = crypto_skcipher_ctx(tfm); + + crypto_free_shash(ctx->hash); +} + +static int essiv_cbc_encrypt(struct skcipher_request *req) +{ + struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req); + struct crypto_aes_essiv_cbc_ctx *ctx = crypto_skcipher_ctx(tfm); + int err, rounds = 6 + ctx->key1.key_length / 4; + struct skcipher_walk walk; + unsigned int blocks; + + err = skcipher_walk_virt(&walk, req, false); + + blocks = walk.nbytes / AES_BLOCK_SIZE; + if (blocks) { + kernel_neon_begin(); + aes_essiv_cbc_encrypt(walk.dst.virt.addr, walk.src.virt.addr, + ctx->key1.key_enc, rounds, blocks, + req->iv, ctx->key2.key_enc); + kernel_neon_end(); + err = skcipher_walk_done(&walk, walk.nbytes % AES_BLOCK_SIZE); + } + return err ?: cbc_encrypt_walk(req, &walk); +} + +static int essiv_cbc_decrypt(struct skcipher_request *req) +{ + struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req); + struct crypto_aes_essiv_cbc_ctx *ctx = crypto_skcipher_ctx(tfm); + int err, rounds = 6 + ctx->key1.key_length / 4; + struct skcipher_walk walk; + unsigned int blocks; + + err = skcipher_walk_virt(&walk, req, false); + + blocks = walk.nbytes / AES_BLOCK_SIZE; + if (blocks) { + kernel_neon_begin(); + aes_essiv_cbc_decrypt(walk.dst.virt.addr, walk.src.virt.addr, + ctx->key1.key_dec, rounds, blocks, + req->iv, ctx->key2.key_enc); + kernel_neon_end(); + err = skcipher_walk_done(&walk, walk.nbytes % AES_BLOCK_SIZE); + } + return err ?: cbc_decrypt_walk(req, &walk); +} + static int ctr_encrypt(struct skcipher_request *req) { struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req); @@ -502,6 +607,24 @@ static struct skcipher_alg aes_algs[] = { { .encrypt = cts_cbc_encrypt, .decrypt = cts_cbc_decrypt, .init = cts_cbc_init_tfm, +}, { + .base = { + .cra_name = "__essiv(cbc(aes),aes,sha256)", + .cra_driver_name = "__essiv-cbc-aes-sha256-" MODE, + .cra_priority = PRIO + 1, + .cra_flags = CRYPTO_ALG_INTERNAL, + .cra_blocksize = AES_BLOCK_SIZE, + .cra_ctxsize = sizeof(struct crypto_aes_essiv_cbc_ctx), + .cra_module = THIS_MODULE, + }, + .min_keysize = AES_MIN_KEY_SIZE, + .max_keysize = AES_MAX_KEY_SIZE, + .ivsize = AES_BLOCK_SIZE, + .setkey = essiv_cbc_set_key, + .encrypt = essiv_cbc_encrypt, + .decrypt = essiv_cbc_decrypt, + .init = essiv_cbc_init_tfm, + .exit = essiv_cbc_exit_tfm, }, { .base = { .cra_name = "__ctr(aes)", diff --git a/arch/arm64/crypto/aes-modes.S b/arch/arm64/crypto/aes-modes.S index 4c7ce231963c..2ef3d7244ea8 100644 --- a/arch/arm64/crypto/aes-modes.S +++ b/arch/arm64/crypto/aes-modes.S @@ -91,10 +91,25 @@ AES_ENDPROC(aes_ecb_decrypt) * int blocks, u8 iv[]) * aes_cbc_decrypt(u8 out[], u8 const in[], u8 const rk[], int rounds, * int blocks, u8 iv[]) + * aes_essiv_cbc_encrypt(u8 out[], u8 const in[], u32 const rk1[], + * int rounds, int blocks, u8 iv[], + * u32 const rk2[]); + * aes_essiv_cbc_decrypt(u8 out[], u8 const in[], u32 const rk1[], + * int rounds, int blocks, u8 iv[], + * u32 const rk2[]); */ +AES_ENTRY(aes_essiv_cbc_encrypt) + ld1 {v4.16b}, [x5] /* get iv */ + + mov w8, #14 /* AES-256: 14 rounds */ + enc_prepare w8, x6, x7 + encrypt_block v4, w8, x6, x7, w9 + b .Lessivcbcencstart + AES_ENTRY(aes_cbc_encrypt) ld1 {v4.16b}, [x5] /* get iv */ +.Lessivcbcencstart: enc_prepare w3, x2, x6 .Lcbcencloop4x: @@ -126,13 +141,25 @@ AES_ENTRY(aes_cbc_encrypt) st1 {v4.16b}, [x5] /* return iv */ ret AES_ENDPROC(aes_cbc_encrypt) +AES_ENDPROC(aes_essiv_cbc_encrypt) +AES_ENTRY(aes_essiv_cbc_decrypt) + stp x29, x30, [sp, #-16]! + mov x29, sp + + ld1 {v7.16b}, [x5] /* get iv */ + + mov w8, #14 /* AES-256: 14 rounds */ + enc_prepare w8, x6, x7 + encrypt_block v7, w8, x6, x7, w9 + b .Lessivcbcdecstart AES_ENTRY(aes_cbc_decrypt) stp x29, x30, [sp, #-16]! mov x29, sp ld1 {v7.16b}, [x5] /* get iv */ +.Lessivcbcdecstart: dec_prepare w3, x2, x6 .LcbcdecloopNx: @@ -168,6 +195,7 @@ AES_ENTRY(aes_cbc_decrypt) ldp x29, x30, [sp], #16 ret AES_ENDPROC(aes_cbc_decrypt) +AES_ENDPROC(aes_essiv_cbc_decrypt) /* @@ -247,7 +275,6 @@ AES_ENDPROC(aes_cbc_cts_decrypt) .byte 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff .previous - /* * aes_ctr_encrypt(u8 out[], u8 const in[], u8 const rk[], int rounds, * int blocks, u8 ctr[]) -- 2.17.1