linux_dsm_epyc7002/crypto/tcrypt.c

1302 lines
28 KiB
C
Raw Normal View History

/*
* Quick & dirty crypto testing module.
*
* This will only exist until we have a better testing mechanism
* (e.g. a char device).
*
* Copyright (c) 2002 James Morris <jmorris@intercode.com.au>
* Copyright (c) 2002 Jean-Francois Dive <jef@linuxbe.org>
* Copyright (c) 2007 Nokia Siemens Networks
*
* Updated RFC4106 AES-GCM testing.
* Authors: Aidan O'Mahony (aidan.o.mahony@intel.com)
* Adrian Hoban <adrian.hoban@intel.com>
* Gabriele Paoloni <gabriele.paoloni@intel.com>
* Tadeusz Struk (tadeusz.struk@intel.com)
* Copyright (c) 2010, Intel Corporation.
*
* This program is free software; you can redistribute it and/or modify it
* under the terms of the GNU General Public License as published by the Free
* Software Foundation; either version 2 of the License, or (at your option)
* any later version.
*
*/
#include <crypto/hash.h>
#include <linux/err.h>
#include <linux/init.h>
include cleanup: Update gfp.h and slab.h includes to prepare for breaking implicit slab.h inclusion from percpu.h percpu.h is included by sched.h and module.h and thus ends up being included when building most .c files. percpu.h includes slab.h which in turn includes gfp.h making everything defined by the two files universally available and complicating inclusion dependencies. percpu.h -> slab.h dependency is about to be removed. Prepare for this change by updating users of gfp and slab facilities include those headers directly instead of assuming availability. As this conversion needs to touch large number of source files, the following script is used as the basis of conversion. http://userweb.kernel.org/~tj/misc/slabh-sweep.py The script does the followings. * Scan files for gfp and slab usages and update includes such that only the necessary includes are there. ie. if only gfp is used, gfp.h, if slab is used, slab.h. * When the script inserts a new include, it looks at the include blocks and try to put the new include such that its order conforms to its surrounding. It's put in the include block which contains core kernel includes, in the same order that the rest are ordered - alphabetical, Christmas tree, rev-Xmas-tree or at the end if there doesn't seem to be any matching order. * If the script can't find a place to put a new include (mostly because the file doesn't have fitting include block), it prints out an error message indicating which .h file needs to be added to the file. The conversion was done in the following steps. 1. The initial automatic conversion of all .c files updated slightly over 4000 files, deleting around 700 includes and adding ~480 gfp.h and ~3000 slab.h inclusions. The script emitted errors for ~400 files. 2. Each error was manually checked. Some didn't need the inclusion, some needed manual addition while adding it to implementation .h or embedding .c file was more appropriate for others. This step added inclusions to around 150 files. 3. The script was run again and the output was compared to the edits from #2 to make sure no file was left behind. 4. Several build tests were done and a couple of problems were fixed. e.g. lib/decompress_*.c used malloc/free() wrappers around slab APIs requiring slab.h to be added manually. 5. The script was run on all .h files but without automatically editing them as sprinkling gfp.h and slab.h inclusions around .h files could easily lead to inclusion dependency hell. Most gfp.h inclusion directives were ignored as stuff from gfp.h was usually wildly available and often used in preprocessor macros. Each slab.h inclusion directive was examined and added manually as necessary. 6. percpu.h was updated not to include slab.h. 7. Build test were done on the following configurations and failures were fixed. CONFIG_GCOV_KERNEL was turned off for all tests (as my distributed build env didn't work with gcov compiles) and a few more options had to be turned off depending on archs to make things build (like ipr on powerpc/64 which failed due to missing writeq). * x86 and x86_64 UP and SMP allmodconfig and a custom test config. * powerpc and powerpc64 SMP allmodconfig * sparc and sparc64 SMP allmodconfig * ia64 SMP allmodconfig * s390 SMP allmodconfig * alpha SMP allmodconfig * um on x86_64 SMP allmodconfig 8. percpu.h modifications were reverted so that it could be applied as a separate patch and serve as bisection point. Given the fact that I had only a couple of failures from tests on step 6, I'm fairly confident about the coverage of this conversion patch. If there is a breakage, it's likely to be something in one of the arch headers which should be easily discoverable easily on most builds of the specific arch. Signed-off-by: Tejun Heo <tj@kernel.org> Guess-its-ok-by: Christoph Lameter <cl@linux-foundation.org> Cc: Ingo Molnar <mingo@redhat.com> Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
2010-03-24 15:04:11 +07:00
#include <linux/gfp.h>
#include <linux/module.h>
#include <linux/scatterlist.h>
#include <linux/string.h>
#include <linux/moduleparam.h>
#include <linux/jiffies.h>
#include <linux/timex.h>
#include <linux/interrupt.h>
#include "tcrypt.h"
#include "internal.h"
/*
* Need slab memory for testing (size in number of pages).
*/
#define TVMEMSIZE 4
/*
* Used by test_cipher_speed()
*/
#define ENCRYPT 1
#define DECRYPT 0
/*
* Used by test_cipher_speed()
*/
static unsigned int sec;
static char *alg = NULL;
static u32 type;
static u32 mask;
static int mode;
static char *tvmem[TVMEMSIZE];
static char *check[] = {
"des", "md5", "des3_ede", "rot13", "sha1", "sha224", "sha256",
"blowfish", "twofish", "serpent", "sha384", "sha512", "md4", "aes",
"cast6", "arc4", "michael_mic", "deflate", "crc32c", "tea", "xtea",
"khazad", "wp512", "wp384", "wp256", "tnepres", "xeta", "fcrypt",
"camellia", "seed", "salsa20", "rmd128", "rmd160", "rmd256", "rmd320",
"lzo", "cts", "zlib", NULL
};
static int test_cipher_jiffies(struct blkcipher_desc *desc, int enc,
struct scatterlist *sg, int blen, int sec)
{
unsigned long start, end;
int bcount;
int ret;
for (start = jiffies, end = start + sec * HZ, bcount = 0;
time_before(jiffies, end); bcount++) {
if (enc)
ret = crypto_blkcipher_encrypt(desc, sg, sg, blen);
else
ret = crypto_blkcipher_decrypt(desc, sg, sg, blen);
if (ret)
return ret;
}
printk("%d operations in %d seconds (%ld bytes)\n",
bcount, sec, (long)bcount * blen);
return 0;
}
static int test_cipher_cycles(struct blkcipher_desc *desc, int enc,
struct scatterlist *sg, int blen)
{
unsigned long cycles = 0;
int ret = 0;
int i;
local_bh_disable();
local_irq_disable();
/* Warm-up run. */
for (i = 0; i < 4; i++) {
if (enc)
ret = crypto_blkcipher_encrypt(desc, sg, sg, blen);
else
ret = crypto_blkcipher_decrypt(desc, sg, sg, blen);
if (ret)
goto out;
}
/* The real thing. */
for (i = 0; i < 8; i++) {
cycles_t start, end;
start = get_cycles();
if (enc)
ret = crypto_blkcipher_encrypt(desc, sg, sg, blen);
else
ret = crypto_blkcipher_decrypt(desc, sg, sg, blen);
end = get_cycles();
if (ret)
goto out;
cycles += end - start;
}
out:
local_irq_enable();
local_bh_enable();
if (ret == 0)
printk("1 operation in %lu cycles (%d bytes)\n",
(cycles + 4) / 8, blen);
return ret;
}
static u32 block_sizes[] = { 16, 64, 256, 1024, 8192, 0 };
static void test_cipher_speed(const char *algo, int enc, unsigned int sec,
struct cipher_speed_template *template,
unsigned int tcount, u8 *keysize)
{
unsigned int ret, i, j, iv_len;
const char *key;
char iv[128];
struct crypto_blkcipher *tfm;
struct blkcipher_desc desc;
const char *e;
u32 *b_size;
if (enc == ENCRYPT)
e = "encryption";
else
e = "decryption";
printk("\ntesting speed of %s %s\n", algo, e);
tfm = crypto_alloc_blkcipher(algo, 0, CRYPTO_ALG_ASYNC);
if (IS_ERR(tfm)) {
printk("failed to load transform for %s: %ld\n", algo,
PTR_ERR(tfm));
return;
}
desc.tfm = tfm;
desc.flags = 0;
i = 0;
do {
b_size = block_sizes;
do {
struct scatterlist sg[TVMEMSIZE];
if ((*keysize + *b_size) > TVMEMSIZE * PAGE_SIZE) {
printk("template (%u) too big for "
"tvmem (%lu)\n", *keysize + *b_size,
TVMEMSIZE * PAGE_SIZE);
goto out;
}
printk("test %u (%d bit key, %d byte blocks): ", i,
*keysize * 8, *b_size);
memset(tvmem[0], 0xff, PAGE_SIZE);
/* set key, plain text and IV */
key = tvmem[0];
for (j = 0; j < tcount; j++) {
if (template[j].klen == *keysize) {
key = template[j].key;
break;
}
}
ret = crypto_blkcipher_setkey(tfm, key, *keysize);
if (ret) {
printk("setkey() failed flags=%x\n",
crypto_blkcipher_get_flags(tfm));
goto out;
}
sg_init_table(sg, TVMEMSIZE);
sg_set_buf(sg, tvmem[0] + *keysize,
PAGE_SIZE - *keysize);
for (j = 1; j < TVMEMSIZE; j++) {
sg_set_buf(sg + j, tvmem[j], PAGE_SIZE);
memset (tvmem[j], 0xff, PAGE_SIZE);
}
iv_len = crypto_blkcipher_ivsize(tfm);
if (iv_len) {
memset(&iv, 0xff, iv_len);
crypto_blkcipher_set_iv(tfm, iv, iv_len);
}
if (sec)
ret = test_cipher_jiffies(&desc, enc, sg,
*b_size, sec);
else
ret = test_cipher_cycles(&desc, enc, sg,
*b_size);
if (ret) {
printk("%s() failed flags=%x\n", e, desc.flags);
break;
}
b_size++;
i++;
} while (*b_size);
keysize++;
} while (*keysize);
out:
crypto_free_blkcipher(tfm);
}
static int test_hash_jiffies_digest(struct hash_desc *desc,
struct scatterlist *sg, int blen,
char *out, int sec)
{
unsigned long start, end;
int bcount;
int ret;
for (start = jiffies, end = start + sec * HZ, bcount = 0;
time_before(jiffies, end); bcount++) {
ret = crypto_hash_digest(desc, sg, blen, out);
if (ret)
return ret;
}
printk("%6u opers/sec, %9lu bytes/sec\n",
bcount / sec, ((long)bcount * blen) / sec);
return 0;
}
static int test_hash_jiffies(struct hash_desc *desc, struct scatterlist *sg,
int blen, int plen, char *out, int sec)
{
unsigned long start, end;
int bcount, pcount;
int ret;
if (plen == blen)
return test_hash_jiffies_digest(desc, sg, blen, out, sec);
for (start = jiffies, end = start + sec * HZ, bcount = 0;
time_before(jiffies, end); bcount++) {
ret = crypto_hash_init(desc);
if (ret)
return ret;
for (pcount = 0; pcount < blen; pcount += plen) {
ret = crypto_hash_update(desc, sg, plen);
if (ret)
return ret;
}
/* we assume there is enough space in 'out' for the result */
ret = crypto_hash_final(desc, out);
if (ret)
return ret;
}
printk("%6u opers/sec, %9lu bytes/sec\n",
bcount / sec, ((long)bcount * blen) / sec);
return 0;
}
static int test_hash_cycles_digest(struct hash_desc *desc,
struct scatterlist *sg, int blen, char *out)
{
unsigned long cycles = 0;
int i;
int ret;
local_bh_disable();
local_irq_disable();
/* Warm-up run. */
for (i = 0; i < 4; i++) {
ret = crypto_hash_digest(desc, sg, blen, out);
if (ret)
goto out;
}
/* The real thing. */
for (i = 0; i < 8; i++) {
cycles_t start, end;
start = get_cycles();
ret = crypto_hash_digest(desc, sg, blen, out);
if (ret)
goto out;
end = get_cycles();
cycles += end - start;
}
out:
local_irq_enable();
local_bh_enable();
if (ret)
return ret;
printk("%6lu cycles/operation, %4lu cycles/byte\n",
cycles / 8, cycles / (8 * blen));
return 0;
}
static int test_hash_cycles(struct hash_desc *desc, struct scatterlist *sg,
int blen, int plen, char *out)
{
unsigned long cycles = 0;
int i, pcount;
int ret;
if (plen == blen)
return test_hash_cycles_digest(desc, sg, blen, out);
local_bh_disable();
local_irq_disable();
/* Warm-up run. */
for (i = 0; i < 4; i++) {
ret = crypto_hash_init(desc);
if (ret)
goto out;
for (pcount = 0; pcount < blen; pcount += plen) {
ret = crypto_hash_update(desc, sg, plen);
if (ret)
goto out;
}
ret = crypto_hash_final(desc, out);
if (ret)
goto out;
}
/* The real thing. */
for (i = 0; i < 8; i++) {
cycles_t start, end;
start = get_cycles();
ret = crypto_hash_init(desc);
if (ret)
goto out;
for (pcount = 0; pcount < blen; pcount += plen) {
ret = crypto_hash_update(desc, sg, plen);
if (ret)
goto out;
}
ret = crypto_hash_final(desc, out);
if (ret)
goto out;
end = get_cycles();
cycles += end - start;
}
out:
local_irq_enable();
local_bh_enable();
if (ret)
return ret;
printk("%6lu cycles/operation, %4lu cycles/byte\n",
cycles / 8, cycles / (8 * blen));
return 0;
}
crypto: tcrypt - Add speed tests for async hashing These are invoked in the 'mode' range of 400 to 499. The cost of async vs. sync for the software algorithm implementations varies. It can be as low as 16 cycles but as much as a couple hundred. Here two runs of md5 testing, async then sync: testing speed of async md5 test 0 ( 16 byte blocks, 16 bytes per update, 1 updates): 2448 cycles/operation, 153 cycles/byte test 1 ( 64 byte blocks, 16 bytes per update, 4 updates): 4992 cycles/operation, 78 cycles/byte test 2 ( 64 byte blocks, 64 bytes per update, 1 updates): 3808 cycles/operation, 59 cycles/byte test 3 ( 256 byte blocks, 16 bytes per update, 16 updates): 14000 cycles/operation, 54 cycles/byte test 4 ( 256 byte blocks, 64 bytes per update, 4 updates): 8480 cycles/operation, 33 cycles/byte test 5 ( 256 byte blocks, 256 bytes per update, 1 updates): 7280 cycles/operation, 28 cycles/byte test 6 ( 1024 byte blocks, 16 bytes per update, 64 updates): 50016 cycles/operation, 48 cycles/byte test 7 ( 1024 byte blocks, 256 bytes per update, 4 updates): 22496 cycles/operation, 21 cycles/byte test 8 ( 1024 byte blocks, 1024 bytes per update, 1 updates): 21232 cycles/operation, 20 cycles/byte test 9 ( 2048 byte blocks, 16 bytes per update, 128 updates): 117184 cycles/operation, 57 cycles/byte test 10 ( 2048 byte blocks, 256 bytes per update, 8 updates): 43008 cycles/operation, 21 cycles/byte test 11 ( 2048 byte blocks, 1024 bytes per update, 2 updates): 40176 cycles/operation, 19 cycles/byte test 12 ( 2048 byte blocks, 2048 bytes per update, 1 updates): 39888 cycles/operation, 19 cycles/byte test 13 ( 4096 byte blocks, 16 bytes per update, 256 updates): 194176 cycles/operation, 47 cycles/byte test 14 ( 4096 byte blocks, 256 bytes per update, 16 updates): 84096 cycles/operation, 20 cycles/byte test 15 ( 4096 byte blocks, 1024 bytes per update, 4 updates): 78336 cycles/operation, 19 cycles/byte test 16 ( 4096 byte blocks, 4096 bytes per update, 1 updates): 77120 cycles/operation, 18 cycles/byte test 17 ( 8192 byte blocks, 16 bytes per update, 512 updates): 403056 cycles/operation, 49 cycles/byte test 18 ( 8192 byte blocks, 256 bytes per update, 32 updates): 166112 cycles/operation, 20 cycles/byte test 19 ( 8192 byte blocks, 1024 bytes per update, 8 updates): 154768 cycles/operation, 18 cycles/byte test 20 ( 8192 byte blocks, 4096 bytes per update, 2 updates): 151904 cycles/operation, 18 cycles/byte test 21 ( 8192 byte blocks, 8192 bytes per update, 1 updates): 155456 cycles/operation, 18 cycles/byte testing speed of md5 test 0 ( 16 byte blocks, 16 bytes per update, 1 updates): 2208 cycles/operation, 138 cycles/byte test 1 ( 64 byte blocks, 16 bytes per update, 4 updates): 5008 cycles/operation, 78 cycles/byte test 2 ( 64 byte blocks, 64 bytes per update, 1 updates): 3600 cycles/operation, 56 cycles/byte test 3 ( 256 byte blocks, 16 bytes per update, 16 updates): 14080 cycles/operation, 55 cycles/byte test 4 ( 256 byte blocks, 64 bytes per update, 4 updates): 8560 cycles/operation, 33 cycles/byte test 5 ( 256 byte blocks, 256 bytes per update, 1 updates): 7040 cycles/operation, 27 cycles/byte test 6 ( 1024 byte blocks, 16 bytes per update, 64 updates): 50592 cycles/operation, 49 cycles/byte test 7 ( 1024 byte blocks, 256 bytes per update, 4 updates): 22736 cycles/operation, 22 cycles/byte test 8 ( 1024 byte blocks, 1024 bytes per update, 1 updates): 24960 cycles/operation, 24 cycles/byte test 9 ( 2048 byte blocks, 16 bytes per update, 128 updates): 99312 cycles/operation, 48 cycles/byte test 10 ( 2048 byte blocks, 256 bytes per update, 8 updates): 43520 cycles/operation, 21 cycles/byte test 11 ( 2048 byte blocks, 1024 bytes per update, 2 updates): 40704 cycles/operation, 19 cycles/byte test 12 ( 2048 byte blocks, 2048 bytes per update, 1 updates): 39552 cycles/operation, 19 cycles/byte test 13 ( 4096 byte blocks, 16 bytes per update, 256 updates): 196720 cycles/operation, 48 cycles/byte test 14 ( 4096 byte blocks, 256 bytes per update, 16 updates): 85152 cycles/operation, 20 cycles/byte test 15 ( 4096 byte blocks, 1024 bytes per update, 4 updates): 79408 cycles/operation, 19 cycles/byte test 16 ( 4096 byte blocks, 4096 bytes per update, 1 updates): 76816 cycles/operation, 18 cycles/byte test 17 ( 8192 byte blocks, 16 bytes per update, 512 updates): 391520 cycles/operation, 47 cycles/byte test 18 ( 8192 byte blocks, 256 bytes per update, 32 updates): 168464 cycles/operation, 20 cycles/byte test 19 ( 8192 byte blocks, 1024 bytes per update, 8 updates): 156912 cycles/operation, 19 cycles/byte test 20 ( 8192 byte blocks, 4096 bytes per update, 2 updates): 154016 cycles/operation, 18 cycles/byte test 21 ( 8192 byte blocks, 8192 bytes per update, 1 updates): 153856 cycles/operation, 18 cycles/byte We can ditch the sync hash code at some point if we feel that makes sense. For now I've left it there. Signed-off-by: David S. Miller <davem@davemloft.net> Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
2010-05-19 11:11:21 +07:00
static void test_hash_sg_init(struct scatterlist *sg)
{
int i;
sg_init_table(sg, TVMEMSIZE);
for (i = 0; i < TVMEMSIZE; i++) {
sg_set_buf(sg + i, tvmem[i], PAGE_SIZE);
memset(tvmem[i], 0xff, PAGE_SIZE);
}
}
static void test_hash_speed(const char *algo, unsigned int sec,
struct hash_speed *speed)
{
struct scatterlist sg[TVMEMSIZE];
struct crypto_hash *tfm;
struct hash_desc desc;
static char output[1024];
int i;
int ret;
printk(KERN_INFO "\ntesting speed of %s\n", algo);
tfm = crypto_alloc_hash(algo, 0, CRYPTO_ALG_ASYNC);
if (IS_ERR(tfm)) {
printk(KERN_ERR "failed to load transform for %s: %ld\n", algo,
PTR_ERR(tfm));
return;
}
desc.tfm = tfm;
desc.flags = 0;
if (crypto_hash_digestsize(tfm) > sizeof(output)) {
printk(KERN_ERR "digestsize(%u) > outputbuffer(%zu)\n",
crypto_hash_digestsize(tfm), sizeof(output));
goto out;
}
crypto: tcrypt - Add speed tests for async hashing These are invoked in the 'mode' range of 400 to 499. The cost of async vs. sync for the software algorithm implementations varies. It can be as low as 16 cycles but as much as a couple hundred. Here two runs of md5 testing, async then sync: testing speed of async md5 test 0 ( 16 byte blocks, 16 bytes per update, 1 updates): 2448 cycles/operation, 153 cycles/byte test 1 ( 64 byte blocks, 16 bytes per update, 4 updates): 4992 cycles/operation, 78 cycles/byte test 2 ( 64 byte blocks, 64 bytes per update, 1 updates): 3808 cycles/operation, 59 cycles/byte test 3 ( 256 byte blocks, 16 bytes per update, 16 updates): 14000 cycles/operation, 54 cycles/byte test 4 ( 256 byte blocks, 64 bytes per update, 4 updates): 8480 cycles/operation, 33 cycles/byte test 5 ( 256 byte blocks, 256 bytes per update, 1 updates): 7280 cycles/operation, 28 cycles/byte test 6 ( 1024 byte blocks, 16 bytes per update, 64 updates): 50016 cycles/operation, 48 cycles/byte test 7 ( 1024 byte blocks, 256 bytes per update, 4 updates): 22496 cycles/operation, 21 cycles/byte test 8 ( 1024 byte blocks, 1024 bytes per update, 1 updates): 21232 cycles/operation, 20 cycles/byte test 9 ( 2048 byte blocks, 16 bytes per update, 128 updates): 117184 cycles/operation, 57 cycles/byte test 10 ( 2048 byte blocks, 256 bytes per update, 8 updates): 43008 cycles/operation, 21 cycles/byte test 11 ( 2048 byte blocks, 1024 bytes per update, 2 updates): 40176 cycles/operation, 19 cycles/byte test 12 ( 2048 byte blocks, 2048 bytes per update, 1 updates): 39888 cycles/operation, 19 cycles/byte test 13 ( 4096 byte blocks, 16 bytes per update, 256 updates): 194176 cycles/operation, 47 cycles/byte test 14 ( 4096 byte blocks, 256 bytes per update, 16 updates): 84096 cycles/operation, 20 cycles/byte test 15 ( 4096 byte blocks, 1024 bytes per update, 4 updates): 78336 cycles/operation, 19 cycles/byte test 16 ( 4096 byte blocks, 4096 bytes per update, 1 updates): 77120 cycles/operation, 18 cycles/byte test 17 ( 8192 byte blocks, 16 bytes per update, 512 updates): 403056 cycles/operation, 49 cycles/byte test 18 ( 8192 byte blocks, 256 bytes per update, 32 updates): 166112 cycles/operation, 20 cycles/byte test 19 ( 8192 byte blocks, 1024 bytes per update, 8 updates): 154768 cycles/operation, 18 cycles/byte test 20 ( 8192 byte blocks, 4096 bytes per update, 2 updates): 151904 cycles/operation, 18 cycles/byte test 21 ( 8192 byte blocks, 8192 bytes per update, 1 updates): 155456 cycles/operation, 18 cycles/byte testing speed of md5 test 0 ( 16 byte blocks, 16 bytes per update, 1 updates): 2208 cycles/operation, 138 cycles/byte test 1 ( 64 byte blocks, 16 bytes per update, 4 updates): 5008 cycles/operation, 78 cycles/byte test 2 ( 64 byte blocks, 64 bytes per update, 1 updates): 3600 cycles/operation, 56 cycles/byte test 3 ( 256 byte blocks, 16 bytes per update, 16 updates): 14080 cycles/operation, 55 cycles/byte test 4 ( 256 byte blocks, 64 bytes per update, 4 updates): 8560 cycles/operation, 33 cycles/byte test 5 ( 256 byte blocks, 256 bytes per update, 1 updates): 7040 cycles/operation, 27 cycles/byte test 6 ( 1024 byte blocks, 16 bytes per update, 64 updates): 50592 cycles/operation, 49 cycles/byte test 7 ( 1024 byte blocks, 256 bytes per update, 4 updates): 22736 cycles/operation, 22 cycles/byte test 8 ( 1024 byte blocks, 1024 bytes per update, 1 updates): 24960 cycles/operation, 24 cycles/byte test 9 ( 2048 byte blocks, 16 bytes per update, 128 updates): 99312 cycles/operation, 48 cycles/byte test 10 ( 2048 byte blocks, 256 bytes per update, 8 updates): 43520 cycles/operation, 21 cycles/byte test 11 ( 2048 byte blocks, 1024 bytes per update, 2 updates): 40704 cycles/operation, 19 cycles/byte test 12 ( 2048 byte blocks, 2048 bytes per update, 1 updates): 39552 cycles/operation, 19 cycles/byte test 13 ( 4096 byte blocks, 16 bytes per update, 256 updates): 196720 cycles/operation, 48 cycles/byte test 14 ( 4096 byte blocks, 256 bytes per update, 16 updates): 85152 cycles/operation, 20 cycles/byte test 15 ( 4096 byte blocks, 1024 bytes per update, 4 updates): 79408 cycles/operation, 19 cycles/byte test 16 ( 4096 byte blocks, 4096 bytes per update, 1 updates): 76816 cycles/operation, 18 cycles/byte test 17 ( 8192 byte blocks, 16 bytes per update, 512 updates): 391520 cycles/operation, 47 cycles/byte test 18 ( 8192 byte blocks, 256 bytes per update, 32 updates): 168464 cycles/operation, 20 cycles/byte test 19 ( 8192 byte blocks, 1024 bytes per update, 8 updates): 156912 cycles/operation, 19 cycles/byte test 20 ( 8192 byte blocks, 4096 bytes per update, 2 updates): 154016 cycles/operation, 18 cycles/byte test 21 ( 8192 byte blocks, 8192 bytes per update, 1 updates): 153856 cycles/operation, 18 cycles/byte We can ditch the sync hash code at some point if we feel that makes sense. For now I've left it there. Signed-off-by: David S. Miller <davem@davemloft.net> Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
2010-05-19 11:11:21 +07:00
test_hash_sg_init(sg);
for (i = 0; speed[i].blen != 0; i++) {
if (speed[i].blen > TVMEMSIZE * PAGE_SIZE) {
printk(KERN_ERR
"template (%u) too big for tvmem (%lu)\n",
speed[i].blen, TVMEMSIZE * PAGE_SIZE);
goto out;
}
if (speed[i].klen)
crypto_hash_setkey(tfm, tvmem[0], speed[i].klen);
printk(KERN_INFO "test%3u "
"(%5u byte blocks,%5u bytes per update,%4u updates): ",
i, speed[i].blen, speed[i].plen, speed[i].blen / speed[i].plen);
if (sec)
ret = test_hash_jiffies(&desc, sg, speed[i].blen,
speed[i].plen, output, sec);
else
ret = test_hash_cycles(&desc, sg, speed[i].blen,
speed[i].plen, output);
if (ret) {
printk(KERN_ERR "hashing failed ret=%d\n", ret);
break;
}
}
out:
crypto_free_hash(tfm);
}
crypto: tcrypt - Add speed tests for async hashing These are invoked in the 'mode' range of 400 to 499. The cost of async vs. sync for the software algorithm implementations varies. It can be as low as 16 cycles but as much as a couple hundred. Here two runs of md5 testing, async then sync: testing speed of async md5 test 0 ( 16 byte blocks, 16 bytes per update, 1 updates): 2448 cycles/operation, 153 cycles/byte test 1 ( 64 byte blocks, 16 bytes per update, 4 updates): 4992 cycles/operation, 78 cycles/byte test 2 ( 64 byte blocks, 64 bytes per update, 1 updates): 3808 cycles/operation, 59 cycles/byte test 3 ( 256 byte blocks, 16 bytes per update, 16 updates): 14000 cycles/operation, 54 cycles/byte test 4 ( 256 byte blocks, 64 bytes per update, 4 updates): 8480 cycles/operation, 33 cycles/byte test 5 ( 256 byte blocks, 256 bytes per update, 1 updates): 7280 cycles/operation, 28 cycles/byte test 6 ( 1024 byte blocks, 16 bytes per update, 64 updates): 50016 cycles/operation, 48 cycles/byte test 7 ( 1024 byte blocks, 256 bytes per update, 4 updates): 22496 cycles/operation, 21 cycles/byte test 8 ( 1024 byte blocks, 1024 bytes per update, 1 updates): 21232 cycles/operation, 20 cycles/byte test 9 ( 2048 byte blocks, 16 bytes per update, 128 updates): 117184 cycles/operation, 57 cycles/byte test 10 ( 2048 byte blocks, 256 bytes per update, 8 updates): 43008 cycles/operation, 21 cycles/byte test 11 ( 2048 byte blocks, 1024 bytes per update, 2 updates): 40176 cycles/operation, 19 cycles/byte test 12 ( 2048 byte blocks, 2048 bytes per update, 1 updates): 39888 cycles/operation, 19 cycles/byte test 13 ( 4096 byte blocks, 16 bytes per update, 256 updates): 194176 cycles/operation, 47 cycles/byte test 14 ( 4096 byte blocks, 256 bytes per update, 16 updates): 84096 cycles/operation, 20 cycles/byte test 15 ( 4096 byte blocks, 1024 bytes per update, 4 updates): 78336 cycles/operation, 19 cycles/byte test 16 ( 4096 byte blocks, 4096 bytes per update, 1 updates): 77120 cycles/operation, 18 cycles/byte test 17 ( 8192 byte blocks, 16 bytes per update, 512 updates): 403056 cycles/operation, 49 cycles/byte test 18 ( 8192 byte blocks, 256 bytes per update, 32 updates): 166112 cycles/operation, 20 cycles/byte test 19 ( 8192 byte blocks, 1024 bytes per update, 8 updates): 154768 cycles/operation, 18 cycles/byte test 20 ( 8192 byte blocks, 4096 bytes per update, 2 updates): 151904 cycles/operation, 18 cycles/byte test 21 ( 8192 byte blocks, 8192 bytes per update, 1 updates): 155456 cycles/operation, 18 cycles/byte testing speed of md5 test 0 ( 16 byte blocks, 16 bytes per update, 1 updates): 2208 cycles/operation, 138 cycles/byte test 1 ( 64 byte blocks, 16 bytes per update, 4 updates): 5008 cycles/operation, 78 cycles/byte test 2 ( 64 byte blocks, 64 bytes per update, 1 updates): 3600 cycles/operation, 56 cycles/byte test 3 ( 256 byte blocks, 16 bytes per update, 16 updates): 14080 cycles/operation, 55 cycles/byte test 4 ( 256 byte blocks, 64 bytes per update, 4 updates): 8560 cycles/operation, 33 cycles/byte test 5 ( 256 byte blocks, 256 bytes per update, 1 updates): 7040 cycles/operation, 27 cycles/byte test 6 ( 1024 byte blocks, 16 bytes per update, 64 updates): 50592 cycles/operation, 49 cycles/byte test 7 ( 1024 byte blocks, 256 bytes per update, 4 updates): 22736 cycles/operation, 22 cycles/byte test 8 ( 1024 byte blocks, 1024 bytes per update, 1 updates): 24960 cycles/operation, 24 cycles/byte test 9 ( 2048 byte blocks, 16 bytes per update, 128 updates): 99312 cycles/operation, 48 cycles/byte test 10 ( 2048 byte blocks, 256 bytes per update, 8 updates): 43520 cycles/operation, 21 cycles/byte test 11 ( 2048 byte blocks, 1024 bytes per update, 2 updates): 40704 cycles/operation, 19 cycles/byte test 12 ( 2048 byte blocks, 2048 bytes per update, 1 updates): 39552 cycles/operation, 19 cycles/byte test 13 ( 4096 byte blocks, 16 bytes per update, 256 updates): 196720 cycles/operation, 48 cycles/byte test 14 ( 4096 byte blocks, 256 bytes per update, 16 updates): 85152 cycles/operation, 20 cycles/byte test 15 ( 4096 byte blocks, 1024 bytes per update, 4 updates): 79408 cycles/operation, 19 cycles/byte test 16 ( 4096 byte blocks, 4096 bytes per update, 1 updates): 76816 cycles/operation, 18 cycles/byte test 17 ( 8192 byte blocks, 16 bytes per update, 512 updates): 391520 cycles/operation, 47 cycles/byte test 18 ( 8192 byte blocks, 256 bytes per update, 32 updates): 168464 cycles/operation, 20 cycles/byte test 19 ( 8192 byte blocks, 1024 bytes per update, 8 updates): 156912 cycles/operation, 19 cycles/byte test 20 ( 8192 byte blocks, 4096 bytes per update, 2 updates): 154016 cycles/operation, 18 cycles/byte test 21 ( 8192 byte blocks, 8192 bytes per update, 1 updates): 153856 cycles/operation, 18 cycles/byte We can ditch the sync hash code at some point if we feel that makes sense. For now I've left it there. Signed-off-by: David S. Miller <davem@davemloft.net> Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
2010-05-19 11:11:21 +07:00
struct tcrypt_result {
struct completion completion;
int err;
};
static void tcrypt_complete(struct crypto_async_request *req, int err)
{
struct tcrypt_result *res = req->data;
if (err == -EINPROGRESS)
return;
res->err = err;
complete(&res->completion);
}
static inline int do_one_ahash_op(struct ahash_request *req, int ret)
{
if (ret == -EINPROGRESS || ret == -EBUSY) {
struct tcrypt_result *tr = req->base.data;
ret = wait_for_completion_interruptible(&tr->completion);
if (!ret)
ret = tr->err;
INIT_COMPLETION(tr->completion);
}
return ret;
}
static int test_ahash_jiffies_digest(struct ahash_request *req, int blen,
char *out, int sec)
{
unsigned long start, end;
int bcount;
int ret;
for (start = jiffies, end = start + sec * HZ, bcount = 0;
time_before(jiffies, end); bcount++) {
ret = do_one_ahash_op(req, crypto_ahash_digest(req));
if (ret)
return ret;
}
printk("%6u opers/sec, %9lu bytes/sec\n",
bcount / sec, ((long)bcount * blen) / sec);
return 0;
}
static int test_ahash_jiffies(struct ahash_request *req, int blen,
int plen, char *out, int sec)
{
unsigned long start, end;
int bcount, pcount;
int ret;
if (plen == blen)
return test_ahash_jiffies_digest(req, blen, out, sec);
for (start = jiffies, end = start + sec * HZ, bcount = 0;
time_before(jiffies, end); bcount++) {
ret = crypto_ahash_init(req);
if (ret)
return ret;
for (pcount = 0; pcount < blen; pcount += plen) {
ret = do_one_ahash_op(req, crypto_ahash_update(req));
if (ret)
return ret;
}
/* we assume there is enough space in 'out' for the result */
ret = do_one_ahash_op(req, crypto_ahash_final(req));
if (ret)
return ret;
}
pr_cont("%6u opers/sec, %9lu bytes/sec\n",
bcount / sec, ((long)bcount * blen) / sec);
return 0;
}
static int test_ahash_cycles_digest(struct ahash_request *req, int blen,
char *out)
{
unsigned long cycles = 0;
int ret, i;
/* Warm-up run. */
for (i = 0; i < 4; i++) {
ret = do_one_ahash_op(req, crypto_ahash_digest(req));
if (ret)
goto out;
}
/* The real thing. */
for (i = 0; i < 8; i++) {
cycles_t start, end;
start = get_cycles();
ret = do_one_ahash_op(req, crypto_ahash_digest(req));
if (ret)
goto out;
end = get_cycles();
cycles += end - start;
}
out:
if (ret)
return ret;
pr_cont("%6lu cycles/operation, %4lu cycles/byte\n",
cycles / 8, cycles / (8 * blen));
return 0;
}
static int test_ahash_cycles(struct ahash_request *req, int blen,
int plen, char *out)
{
unsigned long cycles = 0;
int i, pcount, ret;
if (plen == blen)
return test_ahash_cycles_digest(req, blen, out);
/* Warm-up run. */
for (i = 0; i < 4; i++) {
ret = crypto_ahash_init(req);
if (ret)
goto out;
for (pcount = 0; pcount < blen; pcount += plen) {
ret = do_one_ahash_op(req, crypto_ahash_update(req));
if (ret)
goto out;
}
ret = do_one_ahash_op(req, crypto_ahash_final(req));
if (ret)
goto out;
}
/* The real thing. */
for (i = 0; i < 8; i++) {
cycles_t start, end;
start = get_cycles();
ret = crypto_ahash_init(req);
if (ret)
goto out;
for (pcount = 0; pcount < blen; pcount += plen) {
ret = do_one_ahash_op(req, crypto_ahash_update(req));
if (ret)
goto out;
}
ret = do_one_ahash_op(req, crypto_ahash_final(req));
if (ret)
goto out;
end = get_cycles();
cycles += end - start;
}
out:
if (ret)
return ret;
pr_cont("%6lu cycles/operation, %4lu cycles/byte\n",
cycles / 8, cycles / (8 * blen));
return 0;
}
static void test_ahash_speed(const char *algo, unsigned int sec,
struct hash_speed *speed)
{
struct scatterlist sg[TVMEMSIZE];
struct tcrypt_result tresult;
struct ahash_request *req;
struct crypto_ahash *tfm;
static char output[1024];
int i, ret;
printk(KERN_INFO "\ntesting speed of async %s\n", algo);
tfm = crypto_alloc_ahash(algo, 0, 0);
if (IS_ERR(tfm)) {
pr_err("failed to load transform for %s: %ld\n",
algo, PTR_ERR(tfm));
return;
}
if (crypto_ahash_digestsize(tfm) > sizeof(output)) {
pr_err("digestsize(%u) > outputbuffer(%zu)\n",
crypto_ahash_digestsize(tfm), sizeof(output));
goto out;
}
test_hash_sg_init(sg);
req = ahash_request_alloc(tfm, GFP_KERNEL);
if (!req) {
pr_err("ahash request allocation failure\n");
goto out;
}
init_completion(&tresult.completion);
ahash_request_set_callback(req, CRYPTO_TFM_REQ_MAY_BACKLOG,
tcrypt_complete, &tresult);
for (i = 0; speed[i].blen != 0; i++) {
if (speed[i].blen > TVMEMSIZE * PAGE_SIZE) {
pr_err("template (%u) too big for tvmem (%lu)\n",
speed[i].blen, TVMEMSIZE * PAGE_SIZE);
break;
}
pr_info("test%3u "
"(%5u byte blocks,%5u bytes per update,%4u updates): ",
i, speed[i].blen, speed[i].plen, speed[i].blen / speed[i].plen);
ahash_request_set_crypt(req, sg, output, speed[i].plen);
if (sec)
ret = test_ahash_jiffies(req, speed[i].blen,
speed[i].plen, output, sec);
else
ret = test_ahash_cycles(req, speed[i].blen,
speed[i].plen, output);
if (ret) {
pr_err("hashing failed ret=%d\n", ret);
break;
}
}
ahash_request_free(req);
out:
crypto_free_ahash(tfm);
}
static void test_available(void)
{
char **name = check;
while (*name) {
printk("alg %s ", *name);
printk(crypto_has_alg(*name, 0, 0) ?
"found\n" : "not found\n");
name++;
}
}
static inline int tcrypt_test(const char *alg)
{
int ret;
ret = alg_test(alg, alg, 0, 0);
/* non-fips algs return -EINVAL in fips mode */
if (fips_enabled && ret == -EINVAL)
ret = 0;
return ret;
}
static int do_test(int m)
{
int i;
int ret = 0;
switch (m) {
case 0:
for (i = 1; i < 200; i++)
ret += do_test(i);
break;
case 1:
ret += tcrypt_test("md5");
break;
case 2:
ret += tcrypt_test("sha1");
break;
case 3:
ret += tcrypt_test("ecb(des)");
ret += tcrypt_test("cbc(des)");
break;
case 4:
ret += tcrypt_test("ecb(des3_ede)");
ret += tcrypt_test("cbc(des3_ede)");
break;
case 5:
ret += tcrypt_test("md4");
break;
case 6:
ret += tcrypt_test("sha256");
break;
case 7:
ret += tcrypt_test("ecb(blowfish)");
ret += tcrypt_test("cbc(blowfish)");
break;
case 8:
ret += tcrypt_test("ecb(twofish)");
ret += tcrypt_test("cbc(twofish)");
break;
case 9:
ret += tcrypt_test("ecb(serpent)");
break;
case 10:
ret += tcrypt_test("ecb(aes)");
ret += tcrypt_test("cbc(aes)");
ret += tcrypt_test("lrw(aes)");
ret += tcrypt_test("xts(aes)");
ret += tcrypt_test("ctr(aes)");
ret += tcrypt_test("rfc3686(ctr(aes))");
break;
case 11:
ret += tcrypt_test("sha384");
break;
case 12:
ret += tcrypt_test("sha512");
break;
case 13:
ret += tcrypt_test("deflate");
break;
case 14:
ret += tcrypt_test("ecb(cast5)");
break;
case 15:
ret += tcrypt_test("ecb(cast6)");
break;
case 16:
ret += tcrypt_test("ecb(arc4)");
break;
case 17:
ret += tcrypt_test("michael_mic");
break;
case 18:
ret += tcrypt_test("crc32c");
break;
case 19:
ret += tcrypt_test("ecb(tea)");
break;
case 20:
ret += tcrypt_test("ecb(xtea)");
break;
case 21:
ret += tcrypt_test("ecb(khazad)");
break;
case 22:
ret += tcrypt_test("wp512");
break;
case 23:
ret += tcrypt_test("wp384");
break;
case 24:
ret += tcrypt_test("wp256");
break;
case 25:
ret += tcrypt_test("ecb(tnepres)");
break;
case 26:
ret += tcrypt_test("ecb(anubis)");
ret += tcrypt_test("cbc(anubis)");
break;
case 27:
ret += tcrypt_test("tgr192");
break;
case 28:
ret += tcrypt_test("tgr160");
break;
case 29:
ret += tcrypt_test("tgr128");
break;
case 30:
ret += tcrypt_test("ecb(xeta)");
break;
case 31:
ret += tcrypt_test("pcbc(fcrypt)");
break;
case 32:
ret += tcrypt_test("ecb(camellia)");
ret += tcrypt_test("cbc(camellia)");
break;
case 33:
ret += tcrypt_test("sha224");
break;
case 34:
ret += tcrypt_test("salsa20");
break;
case 35:
ret += tcrypt_test("gcm(aes)");
break;
case 36:
ret += tcrypt_test("lzo");
break;
case 37:
ret += tcrypt_test("ccm(aes)");
break;
case 38:
ret += tcrypt_test("cts(cbc(aes))");
break;
case 39:
ret += tcrypt_test("rmd128");
break;
case 40:
ret += tcrypt_test("rmd160");
break;
case 41:
ret += tcrypt_test("rmd256");
break;
case 42:
ret += tcrypt_test("rmd320");
break;
case 43:
ret += tcrypt_test("ecb(seed)");
break;
case 44:
ret += tcrypt_test("zlib");
break;
case 45:
ret += tcrypt_test("rfc4309(ccm(aes))");
break;
case 100:
ret += tcrypt_test("hmac(md5)");
break;
case 101:
ret += tcrypt_test("hmac(sha1)");
break;
case 102:
ret += tcrypt_test("hmac(sha256)");
break;
case 103:
ret += tcrypt_test("hmac(sha384)");
break;
case 104:
ret += tcrypt_test("hmac(sha512)");
break;
case 105:
ret += tcrypt_test("hmac(sha224)");
break;
case 106:
ret += tcrypt_test("xcbc(aes)");
break;
case 107:
ret += tcrypt_test("hmac(rmd128)");
break;
case 108:
ret += tcrypt_test("hmac(rmd160)");
break;
case 109:
ret += tcrypt_test("vmac(aes)");
break;
case 150:
ret += tcrypt_test("ansi_cprng");
break;
case 151:
ret += tcrypt_test("rfc4106(gcm(aes))");
break;
case 200:
test_cipher_speed("ecb(aes)", ENCRYPT, sec, NULL, 0,
speed_template_16_24_32);
test_cipher_speed("ecb(aes)", DECRYPT, sec, NULL, 0,
speed_template_16_24_32);
test_cipher_speed("cbc(aes)", ENCRYPT, sec, NULL, 0,
speed_template_16_24_32);
test_cipher_speed("cbc(aes)", DECRYPT, sec, NULL, 0,
speed_template_16_24_32);
test_cipher_speed("lrw(aes)", ENCRYPT, sec, NULL, 0,
speed_template_32_40_48);
test_cipher_speed("lrw(aes)", DECRYPT, sec, NULL, 0,
speed_template_32_40_48);
test_cipher_speed("xts(aes)", ENCRYPT, sec, NULL, 0,
speed_template_32_48_64);
test_cipher_speed("xts(aes)", DECRYPT, sec, NULL, 0,
speed_template_32_48_64);
break;
case 201:
test_cipher_speed("ecb(des3_ede)", ENCRYPT, sec,
des3_speed_template, DES3_SPEED_VECTORS,
speed_template_24);
test_cipher_speed("ecb(des3_ede)", DECRYPT, sec,
des3_speed_template, DES3_SPEED_VECTORS,
speed_template_24);
test_cipher_speed("cbc(des3_ede)", ENCRYPT, sec,
des3_speed_template, DES3_SPEED_VECTORS,
speed_template_24);
test_cipher_speed("cbc(des3_ede)", DECRYPT, sec,
des3_speed_template, DES3_SPEED_VECTORS,
speed_template_24);
break;
case 202:
test_cipher_speed("ecb(twofish)", ENCRYPT, sec, NULL, 0,
speed_template_16_24_32);
test_cipher_speed("ecb(twofish)", DECRYPT, sec, NULL, 0,
speed_template_16_24_32);
test_cipher_speed("cbc(twofish)", ENCRYPT, sec, NULL, 0,
speed_template_16_24_32);
test_cipher_speed("cbc(twofish)", DECRYPT, sec, NULL, 0,
speed_template_16_24_32);
break;
case 203:
test_cipher_speed("ecb(blowfish)", ENCRYPT, sec, NULL, 0,
speed_template_8_32);
test_cipher_speed("ecb(blowfish)", DECRYPT, sec, NULL, 0,
speed_template_8_32);
test_cipher_speed("cbc(blowfish)", ENCRYPT, sec, NULL, 0,
speed_template_8_32);
test_cipher_speed("cbc(blowfish)", DECRYPT, sec, NULL, 0,
speed_template_8_32);
break;
case 204:
test_cipher_speed("ecb(des)", ENCRYPT, sec, NULL, 0,
speed_template_8);
test_cipher_speed("ecb(des)", DECRYPT, sec, NULL, 0,
speed_template_8);
test_cipher_speed("cbc(des)", ENCRYPT, sec, NULL, 0,
speed_template_8);
test_cipher_speed("cbc(des)", DECRYPT, sec, NULL, 0,
speed_template_8);
break;
case 205:
test_cipher_speed("ecb(camellia)", ENCRYPT, sec, NULL, 0,
speed_template_16_24_32);
test_cipher_speed("ecb(camellia)", DECRYPT, sec, NULL, 0,
speed_template_16_24_32);
test_cipher_speed("cbc(camellia)", ENCRYPT, sec, NULL, 0,
speed_template_16_24_32);
test_cipher_speed("cbc(camellia)", DECRYPT, sec, NULL, 0,
speed_template_16_24_32);
break;
case 206:
test_cipher_speed("salsa20", ENCRYPT, sec, NULL, 0,
speed_template_16_32);
break;
case 300:
/* fall through */
case 301:
test_hash_speed("md4", sec, generic_hash_speed_template);
if (mode > 300 && mode < 400) break;
case 302:
test_hash_speed("md5", sec, generic_hash_speed_template);
if (mode > 300 && mode < 400) break;
case 303:
test_hash_speed("sha1", sec, generic_hash_speed_template);
if (mode > 300 && mode < 400) break;
case 304:
test_hash_speed("sha256", sec, generic_hash_speed_template);
if (mode > 300 && mode < 400) break;
case 305:
test_hash_speed("sha384", sec, generic_hash_speed_template);
if (mode > 300 && mode < 400) break;
case 306:
test_hash_speed("sha512", sec, generic_hash_speed_template);
if (mode > 300 && mode < 400) break;
case 307:
test_hash_speed("wp256", sec, generic_hash_speed_template);
if (mode > 300 && mode < 400) break;
case 308:
test_hash_speed("wp384", sec, generic_hash_speed_template);
if (mode > 300 && mode < 400) break;
case 309:
test_hash_speed("wp512", sec, generic_hash_speed_template);
if (mode > 300 && mode < 400) break;
case 310:
test_hash_speed("tgr128", sec, generic_hash_speed_template);
if (mode > 300 && mode < 400) break;
case 311:
test_hash_speed("tgr160", sec, generic_hash_speed_template);
if (mode > 300 && mode < 400) break;
case 312:
test_hash_speed("tgr192", sec, generic_hash_speed_template);
if (mode > 300 && mode < 400) break;
case 313:
test_hash_speed("sha224", sec, generic_hash_speed_template);
if (mode > 300 && mode < 400) break;
case 314:
test_hash_speed("rmd128", sec, generic_hash_speed_template);
if (mode > 300 && mode < 400) break;
case 315:
test_hash_speed("rmd160", sec, generic_hash_speed_template);
if (mode > 300 && mode < 400) break;
case 316:
test_hash_speed("rmd256", sec, generic_hash_speed_template);
if (mode > 300 && mode < 400) break;
case 317:
test_hash_speed("rmd320", sec, generic_hash_speed_template);
if (mode > 300 && mode < 400) break;
case 318:
test_hash_speed("ghash-generic", sec, hash_speed_template_16);
if (mode > 300 && mode < 400) break;
case 399:
break;
crypto: tcrypt - Add speed tests for async hashing These are invoked in the 'mode' range of 400 to 499. The cost of async vs. sync for the software algorithm implementations varies. It can be as low as 16 cycles but as much as a couple hundred. Here two runs of md5 testing, async then sync: testing speed of async md5 test 0 ( 16 byte blocks, 16 bytes per update, 1 updates): 2448 cycles/operation, 153 cycles/byte test 1 ( 64 byte blocks, 16 bytes per update, 4 updates): 4992 cycles/operation, 78 cycles/byte test 2 ( 64 byte blocks, 64 bytes per update, 1 updates): 3808 cycles/operation, 59 cycles/byte test 3 ( 256 byte blocks, 16 bytes per update, 16 updates): 14000 cycles/operation, 54 cycles/byte test 4 ( 256 byte blocks, 64 bytes per update, 4 updates): 8480 cycles/operation, 33 cycles/byte test 5 ( 256 byte blocks, 256 bytes per update, 1 updates): 7280 cycles/operation, 28 cycles/byte test 6 ( 1024 byte blocks, 16 bytes per update, 64 updates): 50016 cycles/operation, 48 cycles/byte test 7 ( 1024 byte blocks, 256 bytes per update, 4 updates): 22496 cycles/operation, 21 cycles/byte test 8 ( 1024 byte blocks, 1024 bytes per update, 1 updates): 21232 cycles/operation, 20 cycles/byte test 9 ( 2048 byte blocks, 16 bytes per update, 128 updates): 117184 cycles/operation, 57 cycles/byte test 10 ( 2048 byte blocks, 256 bytes per update, 8 updates): 43008 cycles/operation, 21 cycles/byte test 11 ( 2048 byte blocks, 1024 bytes per update, 2 updates): 40176 cycles/operation, 19 cycles/byte test 12 ( 2048 byte blocks, 2048 bytes per update, 1 updates): 39888 cycles/operation, 19 cycles/byte test 13 ( 4096 byte blocks, 16 bytes per update, 256 updates): 194176 cycles/operation, 47 cycles/byte test 14 ( 4096 byte blocks, 256 bytes per update, 16 updates): 84096 cycles/operation, 20 cycles/byte test 15 ( 4096 byte blocks, 1024 bytes per update, 4 updates): 78336 cycles/operation, 19 cycles/byte test 16 ( 4096 byte blocks, 4096 bytes per update, 1 updates): 77120 cycles/operation, 18 cycles/byte test 17 ( 8192 byte blocks, 16 bytes per update, 512 updates): 403056 cycles/operation, 49 cycles/byte test 18 ( 8192 byte blocks, 256 bytes per update, 32 updates): 166112 cycles/operation, 20 cycles/byte test 19 ( 8192 byte blocks, 1024 bytes per update, 8 updates): 154768 cycles/operation, 18 cycles/byte test 20 ( 8192 byte blocks, 4096 bytes per update, 2 updates): 151904 cycles/operation, 18 cycles/byte test 21 ( 8192 byte blocks, 8192 bytes per update, 1 updates): 155456 cycles/operation, 18 cycles/byte testing speed of md5 test 0 ( 16 byte blocks, 16 bytes per update, 1 updates): 2208 cycles/operation, 138 cycles/byte test 1 ( 64 byte blocks, 16 bytes per update, 4 updates): 5008 cycles/operation, 78 cycles/byte test 2 ( 64 byte blocks, 64 bytes per update, 1 updates): 3600 cycles/operation, 56 cycles/byte test 3 ( 256 byte blocks, 16 bytes per update, 16 updates): 14080 cycles/operation, 55 cycles/byte test 4 ( 256 byte blocks, 64 bytes per update, 4 updates): 8560 cycles/operation, 33 cycles/byte test 5 ( 256 byte blocks, 256 bytes per update, 1 updates): 7040 cycles/operation, 27 cycles/byte test 6 ( 1024 byte blocks, 16 bytes per update, 64 updates): 50592 cycles/operation, 49 cycles/byte test 7 ( 1024 byte blocks, 256 bytes per update, 4 updates): 22736 cycles/operation, 22 cycles/byte test 8 ( 1024 byte blocks, 1024 bytes per update, 1 updates): 24960 cycles/operation, 24 cycles/byte test 9 ( 2048 byte blocks, 16 bytes per update, 128 updates): 99312 cycles/operation, 48 cycles/byte test 10 ( 2048 byte blocks, 256 bytes per update, 8 updates): 43520 cycles/operation, 21 cycles/byte test 11 ( 2048 byte blocks, 1024 bytes per update, 2 updates): 40704 cycles/operation, 19 cycles/byte test 12 ( 2048 byte blocks, 2048 bytes per update, 1 updates): 39552 cycles/operation, 19 cycles/byte test 13 ( 4096 byte blocks, 16 bytes per update, 256 updates): 196720 cycles/operation, 48 cycles/byte test 14 ( 4096 byte blocks, 256 bytes per update, 16 updates): 85152 cycles/operation, 20 cycles/byte test 15 ( 4096 byte blocks, 1024 bytes per update, 4 updates): 79408 cycles/operation, 19 cycles/byte test 16 ( 4096 byte blocks, 4096 bytes per update, 1 updates): 76816 cycles/operation, 18 cycles/byte test 17 ( 8192 byte blocks, 16 bytes per update, 512 updates): 391520 cycles/operation, 47 cycles/byte test 18 ( 8192 byte blocks, 256 bytes per update, 32 updates): 168464 cycles/operation, 20 cycles/byte test 19 ( 8192 byte blocks, 1024 bytes per update, 8 updates): 156912 cycles/operation, 19 cycles/byte test 20 ( 8192 byte blocks, 4096 bytes per update, 2 updates): 154016 cycles/operation, 18 cycles/byte test 21 ( 8192 byte blocks, 8192 bytes per update, 1 updates): 153856 cycles/operation, 18 cycles/byte We can ditch the sync hash code at some point if we feel that makes sense. For now I've left it there. Signed-off-by: David S. Miller <davem@davemloft.net> Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
2010-05-19 11:11:21 +07:00
case 400:
/* fall through */
case 401:
test_ahash_speed("md4", sec, generic_hash_speed_template);
if (mode > 400 && mode < 500) break;
case 402:
test_ahash_speed("md5", sec, generic_hash_speed_template);
if (mode > 400 && mode < 500) break;
case 403:
test_ahash_speed("sha1", sec, generic_hash_speed_template);
if (mode > 400 && mode < 500) break;
case 404:
test_ahash_speed("sha256", sec, generic_hash_speed_template);
if (mode > 400 && mode < 500) break;
case 405:
test_ahash_speed("sha384", sec, generic_hash_speed_template);
if (mode > 400 && mode < 500) break;
case 406:
test_ahash_speed("sha512", sec, generic_hash_speed_template);
if (mode > 400 && mode < 500) break;
case 407:
test_ahash_speed("wp256", sec, generic_hash_speed_template);
if (mode > 400 && mode < 500) break;
case 408:
test_ahash_speed("wp384", sec, generic_hash_speed_template);
if (mode > 400 && mode < 500) break;
case 409:
test_ahash_speed("wp512", sec, generic_hash_speed_template);
if (mode > 400 && mode < 500) break;
case 410:
test_ahash_speed("tgr128", sec, generic_hash_speed_template);
if (mode > 400 && mode < 500) break;
case 411:
test_ahash_speed("tgr160", sec, generic_hash_speed_template);
if (mode > 400 && mode < 500) break;
case 412:
test_ahash_speed("tgr192", sec, generic_hash_speed_template);
if (mode > 400 && mode < 500) break;
case 413:
test_ahash_speed("sha224", sec, generic_hash_speed_template);
if (mode > 400 && mode < 500) break;
case 414:
test_ahash_speed("rmd128", sec, generic_hash_speed_template);
if (mode > 400 && mode < 500) break;
case 415:
test_ahash_speed("rmd160", sec, generic_hash_speed_template);
if (mode > 400 && mode < 500) break;
case 416:
test_ahash_speed("rmd256", sec, generic_hash_speed_template);
if (mode > 400 && mode < 500) break;
case 417:
test_ahash_speed("rmd320", sec, generic_hash_speed_template);
if (mode > 400 && mode < 500) break;
case 499:
break;
case 1000:
test_available();
break;
}
return ret;
}
static int do_alg_test(const char *alg, u32 type, u32 mask)
{
return crypto_has_alg(alg, type, mask ?: CRYPTO_ALG_TYPE_MASK) ?
0 : -ENOENT;
}
static int __init tcrypt_mod_init(void)
{
int err = -ENOMEM;
int i;
for (i = 0; i < TVMEMSIZE; i++) {
tvmem[i] = (void *)__get_free_page(GFP_KERNEL);
if (!tvmem[i])
goto err_free_tv;
}
if (alg)
err = do_alg_test(alg, type, mask);
else
err = do_test(mode);
if (err) {
printk(KERN_ERR "tcrypt: one or more tests failed!\n");
goto err_free_tv;
}
/* We intentionaly return -EAGAIN to prevent keeping the module,
* unless we're running in fips mode. It does all its work from
* init() and doesn't offer any runtime functionality, but in
* the fips case, checking for a successful load is helpful.
* => we don't need it in the memory, do we?
* -- mludvig
*/
if (!fips_enabled)
err = -EAGAIN;
err_free_tv:
for (i = 0; i < TVMEMSIZE && tvmem[i]; i++)
free_page((unsigned long)tvmem[i]);
return err;
}
/*
* If an init function is provided, an exit function must also be provided
* to allow module unload.
*/
static void __exit tcrypt_mod_fini(void) { }
module_init(tcrypt_mod_init);
module_exit(tcrypt_mod_fini);
module_param(alg, charp, 0);
module_param(type, uint, 0);
module_param(mask, uint, 0);
module_param(mode, int, 0);
module_param(sec, uint, 0);
MODULE_PARM_DESC(sec, "Length in seconds of speed tests "
"(defaults to zero which uses CPU cycles instead)");
MODULE_LICENSE("GPL");
MODULE_DESCRIPTION("Quick & dirty crypto testing module");
MODULE_AUTHOR("James Morris <jmorris@intercode.com.au>");