Because kernel_fpu_begin() and kernel_fpu_end() operations are too
slow, the performance gain of general mode implementation + aes-aesni
is almost all compensated.
The AES-NI support for more modes are implemented as follow:
- Add a new AES algorithm implementation named __aes-aesni without
kernel_fpu_begin/end()
- Use fpu(<mode>(AES)) to provide kenrel_fpu_begin/end() invoking
- Add <mode>(AES) ablkcipher, which uses cryptd(fpu(<mode>(AES))) to
defer cryption to cryptd context in soft_irq context.
Now the ctr, lrw, pcbc and xts support are added.
Performance testing based on dm-crypt shows that cryption time can be
reduced to 50% of general mode implementation + aes-aesni implementation.
v2: Add description of mode acceleration support in Kconfig
Signed-off-by: Huang Ying <ying.huang@xxxxxxxxx>
---
arch/x86/crypto/aesni-intel_glue.c | 256 +++++++++++++++++++++++++++++++++++++
crypto/Kconfig | 5
2 files changed, 261 insertions(+)
--- a/arch/x86/crypto/aesni-intel_glue.c
+++ b/arch/x86/crypto/aesni-intel_glue.c
@@ -21,6 +21,22 @@
#include <asm/i387.h>
#include <asm/aes.h>
+#if defined(CONFIG_CRYPTO_CTR) || defined(CONFIG_CRYPTO_CTR_MODULE)
+#define HAS_CTR
+#endif
+
+#if defined(CONFIG_CRYPTO_LRW) || defined(CONFIG_CRYPTO_LRW_MODULE)
+#define HAS_LRW
+#endif
+
+#if defined(CONFIG_CRYPTO_PCBC) || defined(CONFIG_CRYPTO_PCBC_MODULE)
+#define HAS_PCBC
+#endif
+
+#if defined(CONFIG_CRYPTO_XTS) || defined(CONFIG_CRYPTO_XTS_MODULE)
+#define HAS_XTS
+#endif
+
struct async_aes_ctx {
struct cryptd_ablkcipher *cryptd_tfm;
};
@@ -137,6 +153,41 @@ static struct crypto_alg aesni_alg = {
}
};
+static void __aes_encrypt(struct crypto_tfm *tfm, u8 *dst, const u8 *src)
+{
+ struct crypto_aes_ctx *ctx = aes_ctx(crypto_tfm_ctx(tfm));
+
+ aesni_enc(ctx, dst, src);
+}
+
+static void __aes_decrypt(struct crypto_tfm *tfm, u8 *dst, const u8 *src)
+{
+ struct crypto_aes_ctx *ctx = aes_ctx(crypto_tfm_ctx(tfm));
+
+ aesni_dec(ctx, dst, src);
+}
+
+static struct crypto_alg __aesni_alg = {
+ .cra_name = "__aes-aesni",
+ .cra_driver_name = "__driver-aes-aesni",
+ .cra_priority = 0,
+ .cra_flags = CRYPTO_ALG_TYPE_CIPHER,
+ .cra_blocksize = AES_BLOCK_SIZE,
+ .cra_ctxsize = sizeof(struct crypto_aes_ctx)+AESNI_ALIGN-1,
+ .cra_alignmask = 0,
+ .cra_module = THIS_MODULE,
+ .cra_list = LIST_HEAD_INIT(__aesni_alg.cra_list),
+ .cra_u = {
+ .cipher = {
+ .cia_min_keysize = AES_MIN_KEY_SIZE,
+ .cia_max_keysize = AES_MAX_KEY_SIZE,
+ .cia_setkey = aes_set_key,
+ .cia_encrypt = __aes_encrypt,
+ .cia_decrypt = __aes_decrypt
+ }
+ }
+};
+
static int ecb_encrypt(struct blkcipher_desc *desc,
struct scatterlist *dst, struct scatterlist *src,
unsigned int nbytes)
@@ -411,6 +462,162 @@ static struct crypto_alg ablk_cbc_alg =
},
};
+#ifdef HAS_CTR
+static int ablk_ctr_init(struct crypto_tfm *tfm)
+{
+ struct cryptd_ablkcipher *cryptd_tfm;
+
+ cryptd_tfm = cryptd_alloc_ablkcipher("fpu(ctr(__driver-aes-aesni))",
+ 0, 0);
+ if (IS_ERR(cryptd_tfm))
+ return PTR_ERR(cryptd_tfm);
+ ablk_init_common(tfm, cryptd_tfm);
+ return 0;
+}
+
+static struct crypto_alg ablk_ctr_alg = {
+ .cra_name = "ctr(aes)",
+ .cra_driver_name = "ctr-aes-aesni",
+ .cra_priority = 400,
+ .cra_flags = CRYPTO_ALG_TYPE_ABLKCIPHER|CRYPTO_ALG_ASYNC,
+ .cra_blocksize = AES_BLOCK_SIZE,
+ .cra_ctxsize = sizeof(struct async_aes_ctx),
+ .cra_alignmask = 0,
+ .cra_type = &crypto_ablkcipher_type,
+ .cra_module = THIS_MODULE,
+ .cra_list = LIST_HEAD_INIT(ablk_ctr_alg.cra_list),
+ .cra_init = ablk_ctr_init,
+ .cra_exit = ablk_exit,
+ .cra_u = {
+ .ablkcipher = {
+ .min_keysize = AES_MIN_KEY_SIZE,
+ .max_keysize = AES_MAX_KEY_SIZE,
+ .ivsize = AES_BLOCK_SIZE,
+ .setkey = ablk_set_key,
+ .encrypt = ablk_encrypt,
+ .decrypt = ablk_decrypt,
+ },
+ },
+};
+#endif
+
+#ifdef HAS_LRW
+static int ablk_lrw_init(struct crypto_tfm *tfm)
+{
+ struct cryptd_ablkcipher *cryptd_tfm;
+
+ cryptd_tfm = cryptd_alloc_ablkcipher("fpu(lrw(__driver-aes-aesni))",
+ 0, 0);
+ if (IS_ERR(cryptd_tfm))
+ return PTR_ERR(cryptd_tfm);
+ ablk_init_common(tfm, cryptd_tfm);
+ return 0;
+}
+
+static struct crypto_alg ablk_lrw_alg = {
+ .cra_name = "lrw(aes)",
+ .cra_driver_name = "lrw-aes-aesni",
+ .cra_priority = 400,
+ .cra_flags = CRYPTO_ALG_TYPE_ABLKCIPHER|CRYPTO_ALG_ASYNC,
+ .cra_blocksize = AES_BLOCK_SIZE,
+ .cra_ctxsize = sizeof(struct async_aes_ctx),
+ .cra_alignmask = 0,
+ .cra_type = &crypto_ablkcipher_type,
+ .cra_module = THIS_MODULE,
+ .cra_list = LIST_HEAD_INIT(ablk_lrw_alg.cra_list),
+ .cra_init = ablk_lrw_init,
+ .cra_exit = ablk_exit,
+ .cra_u = {
+ .ablkcipher = {
+ .min_keysize = AES_MIN_KEY_SIZE,
+ .max_keysize = AES_MAX_KEY_SIZE,
+ .ivsize = AES_BLOCK_SIZE,
+ .setkey = ablk_set_key,
+ .encrypt = ablk_encrypt,
+ .decrypt = ablk_decrypt,
+ },
+ },
+};
+#endif
+
+#ifdef HAS_PCBC
+static int ablk_pcbc_init(struct crypto_tfm *tfm)
+{
+ struct cryptd_ablkcipher *cryptd_tfm;
+
+ cryptd_tfm = cryptd_alloc_ablkcipher("fpu(pcbc(__driver-aes-aesni))",
+ 0, 0);
+ if (IS_ERR(cryptd_tfm))
+ return PTR_ERR(cryptd_tfm);
+ ablk_init_common(tfm, cryptd_tfm);
+ return 0;
+}
+
+static struct crypto_alg ablk_pcbc_alg = {
+ .cra_name = "pcbc(aes)",
+ .cra_driver_name = "pcbc-aes-aesni",
+ .cra_priority = 400,
+ .cra_flags = CRYPTO_ALG_TYPE_ABLKCIPHER|CRYPTO_ALG_ASYNC,
+ .cra_blocksize = AES_BLOCK_SIZE,
+ .cra_ctxsize = sizeof(struct async_aes_ctx),
+ .cra_alignmask = 0,
+ .cra_type = &crypto_ablkcipher_type,
+ .cra_module = THIS_MODULE,
+ .cra_list = LIST_HEAD_INIT(ablk_pcbc_alg.cra_list),
+ .cra_init = ablk_pcbc_init,
+ .cra_exit = ablk_exit,
+ .cra_u = {
+ .ablkcipher = {
+ .min_keysize = AES_MIN_KEY_SIZE,
+ .max_keysize = AES_MAX_KEY_SIZE,
+ .ivsize = AES_BLOCK_SIZE,
+ .setkey = ablk_set_key,
+ .encrypt = ablk_encrypt,
+ .decrypt = ablk_decrypt,
+ },
+ },
+};
+#endif
+
+#ifdef HAS_XTS
+static int ablk_xts_init(struct crypto_tfm *tfm)
+{
+ struct cryptd_ablkcipher *cryptd_tfm;
+
+ cryptd_tfm = cryptd_alloc_ablkcipher("fpu(xts(__driver-aes-aesni))",
+ 0, 0);
+ if (IS_ERR(cryptd_tfm))
+ return PTR_ERR(cryptd_tfm);
+ ablk_init_common(tfm, cryptd_tfm);
+ return 0;
+}
+
+static struct crypto_alg ablk_xts_alg = {
+ .cra_name = "xts(aes)",
+ .cra_driver_name = "xts-aes-aesni",
+ .cra_priority = 400,
+ .cra_flags = CRYPTO_ALG_TYPE_ABLKCIPHER|CRYPTO_ALG_ASYNC,
+ .cra_blocksize = AES_BLOCK_SIZE,
+ .cra_ctxsize = sizeof(struct async_aes_ctx),
+ .cra_alignmask = 0,
+ .cra_type = &crypto_ablkcipher_type,
+ .cra_module = THIS_MODULE,
+ .cra_list = LIST_HEAD_INIT(ablk_xts_alg.cra_list),
+ .cra_init = ablk_xts_init,
+ .cra_exit = ablk_exit,
+ .cra_u = {
+ .ablkcipher = {
+ .min_keysize = AES_MIN_KEY_SIZE,
+ .max_keysize = AES_MAX_KEY_SIZE,
+ .ivsize = AES_BLOCK_SIZE,
+ .setkey = ablk_set_key,
+ .encrypt = ablk_encrypt,
+ .decrypt = ablk_decrypt,
+ },
+ },
+};
+#endif
+
static int __init aesni_init(void)
{
int err;
@@ -421,6 +628,8 @@ static int __init aesni_init(void)
}
if ((err = crypto_register_alg(&aesni_alg)))
goto aes_err;
+ if ((err = crypto_register_alg(&__aesni_alg)))
+ goto __aes_err;
if ((err = crypto_register_alg(&blk_ecb_alg)))
goto blk_ecb_err;
if ((err = crypto_register_alg(&blk_cbc_alg)))
@@ -429,9 +638,41 @@ static int __init aesni_init(void)
goto ablk_ecb_err;
if ((err = crypto_register_alg(&ablk_cbc_alg)))
goto ablk_cbc_err;
+#ifdef HAS_CTR
+ if ((err = crypto_register_alg(&ablk_ctr_alg)))
+ goto ablk_ctr_err;
+#endif
+#ifdef HAS_LRW
+ if ((err = crypto_register_alg(&ablk_lrw_alg)))
+ goto ablk_lrw_err;
+#endif
+#ifdef HAS_PCBC
+ if ((err = crypto_register_alg(&ablk_pcbc_alg)))
+ goto ablk_pcbc_err;
+#endif
+#ifdef HAS_XTS
+ if ((err = crypto_register_alg(&ablk_xts_alg)))
+ goto ablk_xts_err;
+#endif
return err;
+#ifdef HAS_XTS
+ablk_xts_err:
+#endif
+#ifdef HAS_PCBC
+ crypto_unregister_alg(&ablk_pcbc_alg);
+ablk_pcbc_err:
+#endif
+#ifdef HAS_LRW
+ crypto_unregister_alg(&ablk_lrw_alg);
+ablk_lrw_err:
+#endif
+#ifdef HAS_CTR
+ crypto_unregister_alg(&ablk_ctr_alg);
+ablk_ctr_err:
+#endif
+ crypto_unregister_alg(&ablk_cbc_alg);
ablk_cbc_err:
crypto_unregister_alg(&ablk_ecb_alg);
ablk_ecb_err:
@@ -439,6 +680,8 @@ ablk_ecb_err:
blk_cbc_err:
crypto_unregister_alg(&blk_ecb_alg);
blk_ecb_err:
+ crypto_unregister_alg(&__aesni_alg);
+__aes_err:
crypto_unregister_alg(&aesni_alg);
aes_err:
return err;
@@ -446,10 +689,23 @@ aes_err:
static void __exit aesni_exit(void)
{
+#ifdef HAS_XTS
+ crypto_unregister_alg(&ablk_xts_alg);
+#endif
+#ifdef HAS_PCBC
+ crypto_unregister_alg(&ablk_pcbc_alg);
+#endif
+#ifdef HAS_LRW
+ crypto_unregister_alg(&ablk_lrw_alg);
+#endif
+#ifdef HAS_CTR
+ crypto_unregister_alg(&ablk_ctr_alg);
+#endif
crypto_unregister_alg(&ablk_cbc_alg);
crypto_unregister_alg(&ablk_ecb_alg);
crypto_unregister_alg(&blk_cbc_alg);
crypto_unregister_alg(&blk_ecb_alg);
+ crypto_unregister_alg(&__aesni_alg);
crypto_unregister_alg(&aesni_alg);
}
--- a/crypto/Kconfig
+++ b/crypto/Kconfig
@@ -491,6 +491,7 @@ config CRYPTO_AES_NI_INTEL
select CRYPTO_AES_X86_64
select CRYPTO_CRYPTD
select CRYPTO_ALGAPI
+ select CRYPTO_FPU
help
Use Intel AES-NI instructions for AES algorithm.
@@ -510,6 +511,10 @@ config CRYPTO_AES_NI_INTEL
See <http://csrc.nist.gov/encryption/aes/> for more information.
+ In addition to AES cipher algorithm support, the
+ acceleration for some popular block cipher mode is supported
+ too, including ECB, CBC, CTR, LRW, PCBC, XTS.
+
config CRYPTO_ANUBIS
tristate "Anubis cipher algorithm"
select CRYPTO_ALGAPI
Attachment:
signature.asc
Description: This is a digitally signed message part
