OrgACRN
/
acrn-kernel
mirror of https://github.com/projectacrn/acrn-kernel.git
1
0
Fork 0
Code Issues Releases Wiki Activity

crypto: x86/sha512 - load based on CPU features 

x86 optimized crypto modules built as modules rather than built-in
to the kernel end up as .ko files in the filesystem, e.g., in
/usr/lib/modules. If the filesystem itself is a module, these might
not be available when the crypto API is initialized, resulting in
the generic implementation being used (e.g., sha512_transform rather
than sha512_transform_avx2).

In one test case, CPU utilization in the sha512 function dropped
from 15.34% to 7.18% after forcing loading of the optimized module.

Add module aliases for this x86 optimized crypto module based on CPU
feature bits so udev gets a chance to load them later in the boot
process when the filesystems are all running.

Signed-off-by: Robert Elliott <elliott@hpe.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
This commit is contained in:
Robert Elliott 2022-08-13 18:04:31 -05:00 committed by Herbert Xu
parent 6a088a2cbc
commit aa031b8f70
1 changed files with 10 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

10
arch/x86/crypto/sha512_ssse3_glue.c
View File

@ -36,6 +36,7 @@
#include <linux/types.h>
#include <crypto/sha2.h>
#include <crypto/sha512_base.h>
#include <asm/cpu_device_id.h>
#include <asm/simd.h>
asmlinkage void sha512_transform_ssse3(struct sha512_state *state,
@ -284,6 +285,13 @@ static int register_sha512_avx2(void)
ARRAY_SIZE(sha512_avx2_algs));
return 0;
}
static const struct x86_cpu_id module_cpu_ids[] = {
X86_MATCH_FEATURE(X86_FEATURE_AVX2, NULL),
X86_MATCH_FEATURE(X86_FEATURE_AVX, NULL),
X86_MATCH_FEATURE(X86_FEATURE_SSSE3, NULL),
{}
};
MODULE_DEVICE_TABLE(x86cpu, module_cpu_ids);
static void unregister_sha512_avx2(void)
{
@ -294,6 +302,8 @@ static void unregister_sha512_avx2(void)
static int __init sha512_ssse3_mod_init(void)
{
if (!x86_match_cpu(module_cpu_ids))
return -ENODEV;
if (register_sha512_ssse3())
goto fail;