* [PATCH v2 2/3] crypto: x86 - Remove CONFIG_AS_SHA256_NI
2025-04-04 7:41 [PATCH v2 1/3] crypto: x86 - Remove CONFIG_AS_SHA1_NI Uros Bizjak
@ 2025-04-04 7:41 ` Uros Bizjak
2025-04-04 7:41 ` [PATCH v2 3/3] crypto: x86 - Remove CONFIG_AS_AVX512 handling Uros Bizjak
2025-04-07 5:28 ` [PATCH v2 1/3] crypto: x86 - Remove CONFIG_AS_SHA1_NI Herbert Xu
2 siblings, 0 replies; 4+ messages in thread
From: Uros Bizjak @ 2025-04-04 7:41 UTC (permalink / raw)
To: linux-crypto, x86, linux-kernel
Cc: Uros Bizjak, Herbert Xu, David S. Miller, Thomas Gleixner,
Ingo Molnar, Borislav Petkov, Dave Hansen, H. Peter Anvin,
Eric Biggers
Current minimum required version of binutils is 2.25,
which supports SHA-256 instruction mnemonics.
Remove check for assembler support of SHA-256 instructions
and all relevant macros for conditional compilation.
No functional change intended.
Signed-off-by: Uros Bizjak <ubizjak@gmail.com>
Cc: Herbert Xu <herbert@gondor.apana.org.au>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Reviewed-by: Eric Biggers <ebiggers@kernel.org>
---
arch/x86/Kconfig.assembler | 4 ----
arch/x86/crypto/Makefile | 3 +--
arch/x86/crypto/sha256_ssse3_glue.c | 10 ----------
3 files changed, 1 insertion(+), 16 deletions(-)
diff --git a/arch/x86/Kconfig.assembler b/arch/x86/Kconfig.assembler
index 70fe87bb1055..4d06fd3c8dfe 100644
--- a/arch/x86/Kconfig.assembler
+++ b/arch/x86/Kconfig.assembler
@@ -6,10 +6,6 @@ config AS_AVX512
help
Supported by binutils >= 2.25 and LLVM integrated assembler
-config AS_SHA256_NI
- def_bool $(as-instr,sha256msg1 %xmm0$(comma)%xmm1)
- help
- Supported by binutils >= 2.24 and LLVM integrated assembler
config AS_TPAUSE
def_bool $(as-instr,tpause %ecx)
help
diff --git a/arch/x86/crypto/Makefile b/arch/x86/crypto/Makefile
index 97c1dbc3b7d6..e06b739176c9 100644
--- a/arch/x86/crypto/Makefile
+++ b/arch/x86/crypto/Makefile
@@ -59,8 +59,7 @@ obj-$(CONFIG_CRYPTO_SHA1_SSSE3) += sha1-ssse3.o
sha1-ssse3-y := sha1_avx2_x86_64_asm.o sha1_ssse3_asm.o sha1_ni_asm.o sha1_ssse3_glue.o
obj-$(CONFIG_CRYPTO_SHA256_SSSE3) += sha256-ssse3.o
-sha256-ssse3-y := sha256-ssse3-asm.o sha256-avx-asm.o sha256-avx2-asm.o sha256_ssse3_glue.o
-sha256-ssse3-$(CONFIG_AS_SHA256_NI) += sha256_ni_asm.o
+sha256-ssse3-y := sha256-ssse3-asm.o sha256-avx-asm.o sha256-avx2-asm.o sha256_ni_asm.o sha256_ssse3_glue.o
obj-$(CONFIG_CRYPTO_SHA512_SSSE3) += sha512-ssse3.o
sha512-ssse3-y := sha512-ssse3-asm.o sha512-avx-asm.o sha512-avx2-asm.o sha512_ssse3_glue.o
diff --git a/arch/x86/crypto/sha256_ssse3_glue.c b/arch/x86/crypto/sha256_ssse3_glue.c
index e04a43d9f7d5..429a3cefbab4 100644
--- a/arch/x86/crypto/sha256_ssse3_glue.c
+++ b/arch/x86/crypto/sha256_ssse3_glue.c
@@ -45,9 +45,7 @@ asmlinkage void sha256_transform_ssse3(struct sha256_state *state,
const u8 *data, int blocks);
static const struct x86_cpu_id module_cpu_ids[] = {
-#ifdef CONFIG_AS_SHA256_NI
X86_MATCH_FEATURE(X86_FEATURE_SHA_NI, NULL),
-#endif
X86_MATCH_FEATURE(X86_FEATURE_AVX2, NULL),
X86_MATCH_FEATURE(X86_FEATURE_AVX, NULL),
X86_MATCH_FEATURE(X86_FEATURE_SSSE3, NULL),
@@ -329,7 +327,6 @@ static void unregister_sha256_avx2(void)
ARRAY_SIZE(sha256_avx2_algs));
}
-#ifdef CONFIG_AS_SHA256_NI
asmlinkage void sha256_ni_transform(struct sha256_state *digest,
const u8 *data, int rounds);
@@ -403,11 +400,6 @@ static void unregister_sha256_ni(void)
ARRAY_SIZE(sha256_ni_algs));
}
-#else
-static inline int register_sha256_ni(void) { return 0; }
-static inline void unregister_sha256_ni(void) { }
-#endif
-
static int __init sha256_ssse3_mod_init(void)
{
if (!x86_match_cpu(module_cpu_ids))
@@ -461,7 +453,5 @@ MODULE_ALIAS_CRYPTO("sha224");
MODULE_ALIAS_CRYPTO("sha224-ssse3");
MODULE_ALIAS_CRYPTO("sha224-avx");
MODULE_ALIAS_CRYPTO("sha224-avx2");
-#ifdef CONFIG_AS_SHA256_NI
MODULE_ALIAS_CRYPTO("sha256-ni");
MODULE_ALIAS_CRYPTO("sha224-ni");
-#endif
--
2.49.0
^ permalink raw reply [flat|nested] 4+ messages in thread* [PATCH v2 3/3] crypto: x86 - Remove CONFIG_AS_AVX512 handling
2025-04-04 7:41 [PATCH v2 1/3] crypto: x86 - Remove CONFIG_AS_SHA1_NI Uros Bizjak
2025-04-04 7:41 ` [PATCH v2 2/3] crypto: x86 - Remove CONFIG_AS_SHA256_NI Uros Bizjak
@ 2025-04-04 7:41 ` Uros Bizjak
2025-04-07 5:28 ` [PATCH v2 1/3] crypto: x86 - Remove CONFIG_AS_SHA1_NI Herbert Xu
2 siblings, 0 replies; 4+ messages in thread
From: Uros Bizjak @ 2025-04-04 7:41 UTC (permalink / raw)
To: linux-crypto, x86, linux-kernel
Cc: Uros Bizjak, Herbert Xu, David S. Miller, Thomas Gleixner,
Ingo Molnar, Borislav Petkov, Dave Hansen, H. Peter Anvin,
Eric Biggers
Current minimum required version of binutils is 2.25,
which supports AVX-512 instruction mnemonics.
Remove check for assembler support of AVX-512 instructions
and all relevant macros for conditional compilation.
No functional change intended.
Signed-off-by: Uros Bizjak <ubizjak@gmail.com>
Cc: Herbert Xu <herbert@gondor.apana.org.au>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Reviewed-by: Eric Biggers <ebiggers@kernel.org>
---
v2: Do not remove AS_AVX512 from arch/x86/Kconfig.assembler.
---
arch/x86/crypto/Kconfig | 2 +-
arch/x86/crypto/Makefile | 3 +--
arch/x86/crypto/blake2s-core.S | 4 ----
arch/x86/crypto/blake2s-glue.c | 6 ++----
arch/x86/crypto/chacha_glue.c | 6 ++----
arch/x86/crypto/poly1305-x86_64-cryptogams.pl | 8 --------
arch/x86/crypto/poly1305_glue.c | 6 +++---
7 files changed, 9 insertions(+), 26 deletions(-)
diff --git a/arch/x86/crypto/Kconfig b/arch/x86/crypto/Kconfig
index 3d948f10c94c..547bb0db9217 100644
--- a/arch/x86/crypto/Kconfig
+++ b/arch/x86/crypto/Kconfig
@@ -332,7 +332,7 @@ config CRYPTO_ARIA_AESNI_AVX2_X86_64
config CRYPTO_ARIA_GFNI_AVX512_X86_64
tristate "Ciphers: ARIA with modes: ECB, CTR (AVX512/GFNI)"
- depends on X86 && 64BIT && AS_AVX512 && AS_GFNI
+ depends on X86 && 64BIT && AS_GFNI
select CRYPTO_SKCIPHER
select CRYPTO_SIMD
select CRYPTO_ALGAPI
diff --git a/arch/x86/crypto/Makefile b/arch/x86/crypto/Makefile
index e06b739176c9..2f22b381f244 100644
--- a/arch/x86/crypto/Makefile
+++ b/arch/x86/crypto/Makefile
@@ -43,8 +43,7 @@ obj-$(CONFIG_CRYPTO_AEGIS128_AESNI_SSE2) += aegis128-aesni.o
aegis128-aesni-y := aegis128-aesni-asm.o aegis128-aesni-glue.o
obj-$(CONFIG_CRYPTO_CHACHA20_X86_64) += chacha-x86_64.o
-chacha-x86_64-y := chacha-avx2-x86_64.o chacha-ssse3-x86_64.o chacha_glue.o
-chacha-x86_64-$(CONFIG_AS_AVX512) += chacha-avx512vl-x86_64.o
+chacha-x86_64-y := chacha-avx2-x86_64.o chacha-ssse3-x86_64.o chacha-avx512vl-x86_64.o chacha_glue.o
obj-$(CONFIG_CRYPTO_AES_NI_INTEL) += aesni-intel.o
aesni-intel-y := aesni-intel_asm.o aesni-intel_glue.o
diff --git a/arch/x86/crypto/blake2s-core.S b/arch/x86/crypto/blake2s-core.S
index b50b35ff1fdb..ac1c845445a4 100644
--- a/arch/x86/crypto/blake2s-core.S
+++ b/arch/x86/crypto/blake2s-core.S
@@ -29,7 +29,6 @@ SIGMA:
.byte 13, 7, 12, 3, 11, 14, 1, 9, 2, 5, 15, 8, 10, 0, 4, 6
.byte 6, 14, 11, 0, 15, 9, 3, 8, 10, 12, 13, 1, 5, 2, 7, 4
.byte 10, 8, 7, 1, 2, 4, 6, 5, 13, 15, 9, 3, 0, 11, 14, 12
-#ifdef CONFIG_AS_AVX512
.section .rodata.cst64.BLAKE2S_SIGMA2, "aM", @progbits, 640
.align 64
SIGMA2:
@@ -43,7 +42,6 @@ SIGMA2:
.long 6, 13, 0, 14, 12, 2, 1, 11, 15, 4, 5, 8, 7, 9, 3, 10
.long 15, 5, 4, 13, 10, 7, 3, 11, 12, 2, 0, 6, 9, 8, 1, 14
.long 8, 7, 14, 11, 13, 15, 0, 12, 10, 4, 5, 6, 3, 2, 1, 9
-#endif /* CONFIG_AS_AVX512 */
.text
SYM_FUNC_START(blake2s_compress_ssse3)
@@ -174,7 +172,6 @@ SYM_FUNC_START(blake2s_compress_ssse3)
RET
SYM_FUNC_END(blake2s_compress_ssse3)
-#ifdef CONFIG_AS_AVX512
SYM_FUNC_START(blake2s_compress_avx512)
vmovdqu (%rdi),%xmm0
vmovdqu 0x10(%rdi),%xmm1
@@ -253,4 +250,3 @@ SYM_FUNC_START(blake2s_compress_avx512)
vzeroupper
RET
SYM_FUNC_END(blake2s_compress_avx512)
-#endif /* CONFIG_AS_AVX512 */
diff --git a/arch/x86/crypto/blake2s-glue.c b/arch/x86/crypto/blake2s-glue.c
index 0313f9673f56..00f84f29cc8c 100644
--- a/arch/x86/crypto/blake2s-glue.c
+++ b/arch/x86/crypto/blake2s-glue.c
@@ -41,8 +41,7 @@ void blake2s_compress(struct blake2s_state *state, const u8 *block,
SZ_4K / BLAKE2S_BLOCK_SIZE);
kernel_fpu_begin();
- if (IS_ENABLED(CONFIG_AS_AVX512) &&
- static_branch_likely(&blake2s_use_avx512))
+ if (static_branch_likely(&blake2s_use_avx512))
blake2s_compress_avx512(state, block, blocks, inc);
else
blake2s_compress_ssse3(state, block, blocks, inc);
@@ -59,8 +58,7 @@ static int __init blake2s_mod_init(void)
if (boot_cpu_has(X86_FEATURE_SSSE3))
static_branch_enable(&blake2s_use_ssse3);
- if (IS_ENABLED(CONFIG_AS_AVX512) &&
- boot_cpu_has(X86_FEATURE_AVX) &&
+ if (boot_cpu_has(X86_FEATURE_AVX) &&
boot_cpu_has(X86_FEATURE_AVX2) &&
boot_cpu_has(X86_FEATURE_AVX512F) &&
boot_cpu_has(X86_FEATURE_AVX512VL) &&
diff --git a/arch/x86/crypto/chacha_glue.c b/arch/x86/crypto/chacha_glue.c
index 8bb74a272879..ce12ad807af1 100644
--- a/arch/x86/crypto/chacha_glue.c
+++ b/arch/x86/crypto/chacha_glue.c
@@ -48,8 +48,7 @@ static unsigned int chacha_advance(unsigned int len, unsigned int maxblocks)
static void chacha_dosimd(u32 *state, u8 *dst, const u8 *src,
unsigned int bytes, int nrounds)
{
- if (IS_ENABLED(CONFIG_AS_AVX512) &&
- static_branch_likely(&chacha_use_avx512vl)) {
+ if (static_branch_likely(&chacha_use_avx512vl)) {
while (bytes >= CHACHA_BLOCK_SIZE * 8) {
chacha_8block_xor_avx512vl(state, dst, src, bytes,
nrounds);
@@ -282,8 +281,7 @@ static int __init chacha_simd_mod_init(void)
cpu_has_xfeatures(XFEATURE_MASK_SSE | XFEATURE_MASK_YMM, NULL)) {
static_branch_enable(&chacha_use_avx2);
- if (IS_ENABLED(CONFIG_AS_AVX512) &&
- boot_cpu_has(X86_FEATURE_AVX512VL) &&
+ if (boot_cpu_has(X86_FEATURE_AVX512VL) &&
boot_cpu_has(X86_FEATURE_AVX512BW)) /* kmovq */
static_branch_enable(&chacha_use_avx512vl);
}
diff --git a/arch/x86/crypto/poly1305-x86_64-cryptogams.pl b/arch/x86/crypto/poly1305-x86_64-cryptogams.pl
index b9abcd79c1f4..409ec6955733 100644
--- a/arch/x86/crypto/poly1305-x86_64-cryptogams.pl
+++ b/arch/x86/crypto/poly1305-x86_64-cryptogams.pl
@@ -2811,18 +2811,10 @@ if ($avx>2) {
# reason stack layout is kept identical to poly1305_blocks_avx2. If not
# for this tail, we wouldn't have to even allocate stack frame...
-if($kernel) {
- $code .= "#ifdef CONFIG_AS_AVX512\n";
-}
-
&declare_function("poly1305_blocks_avx512", 32, 4);
poly1305_blocks_avxN(1);
&end_function("poly1305_blocks_avx512");
-if ($kernel) {
- $code .= "#endif\n";
-}
-
if (!$kernel && $avx>3) {
########################################################################
# VPMADD52 version using 2^44 radix.
diff --git a/arch/x86/crypto/poly1305_glue.c b/arch/x86/crypto/poly1305_glue.c
index 08ff4b489f7e..8b5593c46da7 100644
--- a/arch/x86/crypto/poly1305_glue.c
+++ b/arch/x86/crypto/poly1305_glue.c
@@ -107,7 +107,7 @@ static void poly1305_simd_blocks(void *ctx, const u8 *inp, size_t len,
const size_t bytes = min_t(size_t, len, SZ_4K);
kernel_fpu_begin();
- if (IS_ENABLED(CONFIG_AS_AVX512) && static_branch_likely(&poly1305_use_avx512))
+ if (static_branch_likely(&poly1305_use_avx512))
poly1305_blocks_avx512(ctx, inp, bytes, padbit);
else if (static_branch_likely(&poly1305_use_avx2))
poly1305_blocks_avx2(ctx, inp, bytes, padbit);
@@ -265,8 +265,8 @@ static int __init poly1305_simd_mod_init(void)
if (boot_cpu_has(X86_FEATURE_AVX) && boot_cpu_has(X86_FEATURE_AVX2) &&
cpu_has_xfeatures(XFEATURE_MASK_SSE | XFEATURE_MASK_YMM, NULL))
static_branch_enable(&poly1305_use_avx2);
- if (IS_ENABLED(CONFIG_AS_AVX512) && boot_cpu_has(X86_FEATURE_AVX) &&
- boot_cpu_has(X86_FEATURE_AVX2) && boot_cpu_has(X86_FEATURE_AVX512F) &&
+ if (boot_cpu_has(X86_FEATURE_AVX) && boot_cpu_has(X86_FEATURE_AVX2) &&
+ boot_cpu_has(X86_FEATURE_AVX512F) &&
cpu_has_xfeatures(XFEATURE_MASK_SSE | XFEATURE_MASK_YMM | XFEATURE_MASK_AVX512, NULL) &&
/* Skylake downclocks unacceptably much when using zmm, but later generations are fast. */
boot_cpu_data.x86_vfm != INTEL_SKYLAKE_X)
--
2.49.0
^ permalink raw reply [flat|nested] 4+ messages in thread