libbb/sha256: optional x86 hardware accelerated hashing

64 bit:
function                                             old     new   delta
sha256_process_block64_shaNI                           -     730    +730
.rodata                                           108314  108586    +272
sha256_begin                                          31      83     +52
------------------------------------------------------------------------------
(add/remove: 5/1 grow/shrink: 2/0 up/down: 1055/-1)          Total: 1054 bytes

32 bit:
function                                             old     new   delta
sha256_process_block64_shaNI                           -     747    +747
.rodata                                           104318  104590    +272
sha256_begin                                          29      84     +55
------------------------------------------------------------------------------
(add/remove: 5/1 grow/shrink: 2/0 up/down: 1075/-1)          Total: 1074 bytes

Signed-off-by: Denys Vlasenko <vda.linux@googlemail.com>

9 files changed, 612 insertions, 26 deletions

diff --git a/libbb/Config.src b/libbb/Config.src
index 708d3b0..0ecd5bd 100644
--- a/libbb/Config.src
+++ b/libbb/Config.src
@@ -70,6 +70,12 @@ config SHA1_HWACCEL
 	On x86, this adds ~590 bytes of code. Throughput
 	is about twice as fast as fully-unrolled generic code.
 
+config SHA256_HWACCEL
+	bool "SHA256: Use hardware accelerated instructions if possible"
+	default y
+	help
+	On x86, this adds ~1k bytes of code.
+
 config SHA3_SMALL
 	int "SHA3: Trade bytes for speed (0:fast, 1:slow)"
 	default 1  # all "fast or small" options default to small
diff --git a/libbb/Kbuild.src b/libbb/Kbuild.src
index b9d34de..653025e 100644
--- a/libbb/Kbuild.src
+++ b/libbb/Kbuild.src
@@ -59,6 +59,8 @@ lib-y += hash_md5_sha.o
 lib-y += hash_md5_sha_x86-64.o
 lib-y += hash_md5_sha_x86-64_shaNI.o
 lib-y += hash_md5_sha_x86-32_shaNI.o
+lib-y += hash_md5_sha256_x86-64_shaNI.o
+lib-y += hash_md5_sha256_x86-32_shaNI.o
 # Alternative (disabled) MD5 implementation
 #lib-y += hash_md5prime.o
 lib-y += messages.o
diff --git a/libbb/hash_md5_sha.c b/libbb/hash_md5_sha.c
index a23db51..880ffab 100644
--- a/libbb/hash_md5_sha.c
+++ b/libbb/hash_md5_sha.c
@@ -13,6 +13,27 @@
 
 #define NEED_SHA512 (ENABLE_SHA512SUM || ENABLE_USE_BB_CRYPT_SHA)
 
+#if ENABLE_SHA1_HWACCEL || ENABLE_SHA256_HWACCEL
+# if defined(__GNUC__) && (defined(__i386__) || defined(__x86_64__))
+static void cpuid(unsigned *eax, unsigned *ebx, unsigned *ecx, unsigned *edx)
+{
+	asm ("cpuid"
+		: "=a"(*eax), "=b"(*ebx), "=c"(*ecx), "=d"(*edx)
+		: "0"(*eax),  "1"(*ebx),  "2"(*ecx),  "3"(*edx)
+	);
+}
+static smallint shaNI;
+void FAST_FUNC sha1_process_block64_shaNI(sha1_ctx_t *ctx);
+void FAST_FUNC sha256_process_block64_shaNI(sha256_ctx_t *ctx);
+#  if defined(__i386__)
+struct ASM_expects_76_shaNI { char t[1 - 2*(offsetof(sha256_ctx_t, hash) != 76)]; };
+#  endif
+#  if defined(__x86_64__)
+struct ASM_expects_80_shaNI { char t[1 - 2*(offsetof(sha256_ctx_t, hash) != 80)]; };
+#  endif
+# endif
+#endif
+
 /* gcc 4.2.1 optimizes rotr64 better with inline than with macro
  * (for rotX32, there is no difference). Why? My guess is that
  * macro requires clever common subexpression elimination heuristics
@@ -1142,25 +1163,6 @@ static void FAST_FUNC sha512_process_block128(sha512_ctx_t *ctx)
 }
 #endif /* NEED_SHA512 */
 
-#if ENABLE_SHA1_HWACCEL
-# if defined(__GNUC__) && (defined(__i386__) || defined(__x86_64__))
-static void cpuid(unsigned *eax, unsigned *ebx, unsigned *ecx, unsigned *edx)
-{
-	asm ("cpuid"
-		: "=a"(*eax), "=b"(*ebx), "=c"(*ecx), "=d"(*edx)
-		: "0"(*eax),  "1"(*ebx),  "2"(*ecx),  "3"(*edx)
-	);
-}
-void FAST_FUNC sha1_process_block64_shaNI(sha1_ctx_t *ctx);
-#  if defined(__i386__)
-struct ASM_expects_76_shaNI { char t[1 - 2*(offsetof(sha1_ctx_t, hash) != 76)]; };
-#  endif
-#  if defined(__x86_64__)
-struct ASM_expects_80_shaNI { char t[1 - 2*(offsetof(sha1_ctx_t, hash) != 80)]; };
-#  endif
-# endif
-#endif
-
 void FAST_FUNC sha1_begin(sha1_ctx_t *ctx)
 {
 	ctx->hash[0] = 0x67452301;
@@ -1173,7 +1175,6 @@ void FAST_FUNC sha1_begin(sha1_ctx_t *ctx)
 #if ENABLE_SHA1_HWACCEL
 # if defined(__GNUC__) && (defined(__i386__) || defined(__x86_64__))
 	{
-		static smallint shaNI;
 		if (!shaNI) {
 			unsigned eax = 7, ebx = ebx, ecx = 0, edx = edx;
 			cpuid(&eax, &ebx, &ecx, &edx);
@@ -1225,6 +1226,19 @@ void FAST_FUNC sha256_begin(sha256_ctx_t *ctx)
 	memcpy(&ctx->total64, init256, sizeof(init256));
 	/*ctx->total64 = 0; - done by prepending two 32-bit zeros to init256 */
 	ctx->process_block = sha256_process_block64;
+#if ENABLE_SHA256_HWACCEL
+# if defined(__GNUC__) && (defined(__i386__) || defined(__x86_64__))
+	{
+		if (!shaNI) {
+			unsigned eax = 7, ebx = ebx, ecx = 0, edx = edx;
+			cpuid(&eax, &ebx, &ecx, &edx);
+			shaNI = ((ebx >> 29) << 1) - 1;
+		}
+		if (shaNI > 0)
+			ctx->process_block = sha256_process_block64_shaNI;
+	}
+# endif
+#endif
 }
 
 #if NEED_SHA512
diff --git a/libbb/hash_md5_sha256_x86-32_shaNI.S b/libbb/hash_md5_sha256_x86-32_shaNI.S
new file mode 100644
index 0000000..56e37fa
--- /dev/null
+++ b/libbb/hash_md5_sha256_x86-32_shaNI.S
@@ -0,0 +1,283 @@
+#if ENABLE_SHA256_HWACCEL && defined(__GNUC__) && defined(__i386__)
+/* The code is adapted from Linux kernel's source */
+
+// We use shorter insns, even though they are for "wrong"
+// data type (fp, not int).
+// For Intel, there is no penalty for doing it at all
+// (CPUs which do have such penalty do not support SHA1 insns).
+// For AMD, the penalty is one extra cycle
+// (allegedly: I failed to find measurable difference).
+
+//#define mova128 movdqa
+#define mova128 movaps
+//#define movu128 movdqu
+#define movu128 movups
+//#define shuf128_32 pshufd
+#define shuf128_32 shufps
+
+	.section	.text.sha256_process_block64_shaNI, "ax", @progbits
+	.globl	sha256_process_block64_shaNI
+	.hidden	sha256_process_block64_shaNI
+	.type	sha256_process_block64_shaNI, @function
+
+#define DATA_PTR	%eax
+
+#define SHA256CONSTANTS	%ecx
+
+#define MSG		%xmm0
+#define STATE0		%xmm1
+#define STATE1		%xmm2
+#define MSGTMP0		%xmm3
+#define MSGTMP1		%xmm4
+#define MSGTMP2		%xmm5
+#define MSGTMP3		%xmm6
+#define MSGTMP4		%xmm7
+
+	.balign	8	# allow decoders to fetch at least 3 first insns
+sha256_process_block64_shaNI:
+	pushl		%ebp
+	movl		%esp, %ebp
+	subl		$32, %esp
+	andl		$~0xF, %esp	# paddd needs aligned memory operand
+
+	movu128		76+0*16(%eax), STATE0
+	movu128		76+1*16(%eax), STATE1
+
+	shuf128_32	$0xB1, STATE0,  STATE0		/* CDAB */
+	shuf128_32	$0x1B, STATE1,  STATE1		/* EFGH */
+	mova128		STATE0, MSGTMP4
+	palignr		$8, STATE1,  STATE0		/* ABEF */
+	pblendw		$0xF0, MSGTMP4, STATE1		/* CDGH */
+
+#	mova128		PSHUFFLE_BSWAP32_FLIP_MASK, SHUF_MASK
+	lea		K256, SHA256CONSTANTS
+
+	/* Save hash values for addition after rounds */
+	mova128		STATE0, 0*16(%esp)
+	mova128		STATE1, 1*16(%esp)
+
+	/* Rounds 0-3 */
+	movu128		0*16(DATA_PTR), MSG
+	pshufb		PSHUFFLE_BSWAP32_FLIP_MASK, MSG
+	mova128		MSG, MSGTMP0
+		paddd		0*16(SHA256CONSTANTS), MSG
+		sha256rnds2	STATE0, STATE1
+		shuf128_32	$0x0E, MSG, MSG
+		sha256rnds2	STATE1, STATE0
+
+	/* Rounds 4-7 */
+	movu128		1*16(DATA_PTR), MSG
+	pshufb		PSHUFFLE_BSWAP32_FLIP_MASK, MSG
+	mova128		MSG, MSGTMP1
+		paddd		1*16(SHA256CONSTANTS), MSG
+		sha256rnds2	STATE0, STATE1
+		shuf128_32	$0x0E, MSG, MSG
+		sha256rnds2	STATE1, STATE0
+	sha256msg1	MSGTMP1, MSGTMP0
+
+	/* Rounds 8-11 */
+	movu128		2*16(DATA_PTR), MSG
+	pshufb		PSHUFFLE_BSWAP32_FLIP_MASK, MSG
+	mova128		MSG, MSGTMP2
+		paddd		2*16(SHA256CONSTANTS), MSG
+		sha256rnds2	STATE0, STATE1
+		shuf128_32	$0x0E, MSG, MSG
+		sha256rnds2	STATE1, STATE0
+	sha256msg1	MSGTMP2, MSGTMP1
+
+	/* Rounds 12-15 */
+	movu128		3*16(DATA_PTR), MSG
+	pshufb		PSHUFFLE_BSWAP32_FLIP_MASK, MSG
+	mova128		MSG, MSGTMP3
+		paddd		3*16(SHA256CONSTANTS), MSG
+		sha256rnds2	STATE0, STATE1
+	mova128		MSGTMP3, MSGTMP4
+	palignr		$4, MSGTMP2, MSGTMP4
+	paddd		MSGTMP4, MSGTMP0
+	sha256msg2	MSGTMP3, MSGTMP0
+		shuf128_32	$0x0E, MSG, MSG
+		sha256rnds2	STATE1, STATE0
+	sha256msg1	MSGTMP3, MSGTMP2
+
+	/* Rounds 16-19 */
+	mova128		MSGTMP0, MSG
+		paddd		4*16(SHA256CONSTANTS), MSG
+		sha256rnds2	STATE0, STATE1
+	mova128		MSGTMP0, MSGTMP4
+	palignr		$4, MSGTMP3, MSGTMP4
+	paddd		MSGTMP4, MSGTMP1
+	sha256msg2	MSGTMP0, MSGTMP1
+		shuf128_32	$0x0E, MSG, MSG
+		sha256rnds2	STATE1, STATE0
+	sha256msg1	MSGTMP0, MSGTMP3
+
+	/* Rounds 20-23 */
+	mova128		MSGTMP1, MSG
+		paddd		5*16(SHA256CONSTANTS), MSG
+		sha256rnds2	STATE0, STATE1
+	mova128		MSGTMP1, MSGTMP4
+	palignr		$4, MSGTMP0, MSGTMP4
+	paddd		MSGTMP4, MSGTMP2
+	sha256msg2	MSGTMP1, MSGTMP2
+		shuf128_32	$0x0E, MSG, MSG
+		sha256rnds2	STATE1, STATE0
+	sha256msg1	MSGTMP1, MSGTMP0
+
+	/* Rounds 24-27 */
+	mova128		MSGTMP2, MSG
+		paddd		6*16(SHA256CONSTANTS), MSG
+		sha256rnds2	STATE0, STATE1
+	mova128		MSGTMP2, MSGTMP4
+	palignr		$4, MSGTMP1, MSGTMP4
+	paddd		MSGTMP4, MSGTMP3
+	sha256msg2	MSGTMP2, MSGTMP3
+		shuf128_32	$0x0E, MSG, MSG
+		sha256rnds2	STATE1, STATE0
+	sha256msg1	MSGTMP2, MSGTMP1
+
+	/* Rounds 28-31 */
+	mova128		MSGTMP3, MSG
+		paddd		7*16(SHA256CONSTANTS), MSG
+		sha256rnds2	STATE0, STATE1
+	mova128		MSGTMP3, MSGTMP4
+	palignr		$4, MSGTMP2, MSGTMP4
+	paddd		MSGTMP4, MSGTMP0
+	sha256msg2	MSGTMP3, MSGTMP0
+		shuf128_32	$0x0E, MSG, MSG
+		sha256rnds2	STATE1, STATE0
+	sha256msg1	MSGTMP3, MSGTMP2
+
+	/* Rounds 32-35 */
+	mova128		MSGTMP0, MSG
+		paddd		8*16(SHA256CONSTANTS), MSG
+		sha256rnds2	STATE0, STATE1
+	mova128		MSGTMP0, MSGTMP4
+	palignr		$4, MSGTMP3, MSGTMP4
+	paddd		MSGTMP4, MSGTMP1
+	sha256msg2	MSGTMP0, MSGTMP1
+		shuf128_32	$0x0E, MSG, MSG
+		sha256rnds2	STATE1, STATE0
+	sha256msg1	MSGTMP0, MSGTMP3
+
+	/* Rounds 36-39 */
+	mova128		MSGTMP1, MSG
+		paddd		9*16(SHA256CONSTANTS), MSG
+		sha256rnds2	STATE0, STATE1
+	mova128		MSGTMP1, MSGTMP4
+	palignr		$4, MSGTMP0, MSGTMP4
+	paddd		MSGTMP4, MSGTMP2
+	sha256msg2	MSGTMP1, MSGTMP2
+		shuf128_32	$0x0E, MSG, MSG
+		sha256rnds2	STATE1, STATE0
+	sha256msg1	MSGTMP1, MSGTMP0
+
+	/* Rounds 40-43 */
+	mova128		MSGTMP2, MSG
+		paddd		10*16(SHA256CONSTANTS), MSG
+		sha256rnds2	STATE0, STATE1
+	mova128		MSGTMP2, MSGTMP4
+	palignr		$4, MSGTMP1, MSGTMP4
+	paddd		MSGTMP4, MSGTMP3
+	sha256msg2	MSGTMP2, MSGTMP3
+		shuf128_32	$0x0E, MSG, MSG
+		sha256rnds2	STATE1, STATE0
+	sha256msg1	MSGTMP2, MSGTMP1
+
+	/* Rounds 44-47 */
+	mova128		MSGTMP3, MSG
+		paddd		11*16(SHA256CONSTANTS), MSG
+		sha256rnds2	STATE0, STATE1
+	mova128		MSGTMP3, MSGTMP4
+	palignr		$4, MSGTMP2, MSGTMP4
+	paddd		MSGTMP4, MSGTMP0
+	sha256msg2	MSGTMP3, MSGTMP0
+		shuf128_32	$0x0E, MSG, MSG
+		sha256rnds2	STATE1, STATE0
+	sha256msg1	MSGTMP3, MSGTMP2
+
+	/* Rounds 48-51 */
+	mova128		MSGTMP0, MSG
+		paddd		12*16(SHA256CONSTANTS), MSG
+		sha256rnds2	STATE0, STATE1
+	mova128		MSGTMP0, MSGTMP4
+	palignr		$4, MSGTMP3, MSGTMP4
+	paddd		MSGTMP4, MSGTMP1
+	sha256msg2	MSGTMP0, MSGTMP1
+		shuf128_32	$0x0E, MSG, MSG
+		sha256rnds2	STATE1, STATE0
+	sha256msg1	MSGTMP0, MSGTMP3
+
+	/* Rounds 52-55 */
+	mova128		MSGTMP1, MSG
+		paddd		13*16(SHA256CONSTANTS), MSG
+		sha256rnds2	STATE0, STATE1
+	mova128		MSGTMP1, MSGTMP4
+	palignr		$4, MSGTMP0, MSGTMP4
+	paddd		MSGTMP4, MSGTMP2
+	sha256msg2	MSGTMP1, MSGTMP2
+		shuf128_32	$0x0E, MSG, MSG
+		sha256rnds2	STATE1, STATE0
+
+	/* Rounds 56-59 */
+	mova128		MSGTMP2, MSG
+		paddd		14*16(SHA256CONSTANTS), MSG
+		sha256rnds2	STATE0, STATE1
+	mova128		MSGTMP2, MSGTMP4
+	palignr		$4, MSGTMP1, MSGTMP4
+	paddd		MSGTMP4, MSGTMP3
+	sha256msg2	MSGTMP2, MSGTMP3
+		shuf128_32	$0x0E, MSG, MSG
+		sha256rnds2	STATE1, STATE0
+
+	/* Rounds 60-63 */
+	mova128		MSGTMP3, MSG
+		paddd		15*16(SHA256CONSTANTS), MSG
+		sha256rnds2	STATE0, STATE1
+		shuf128_32	$0x0E, MSG, MSG
+		sha256rnds2	STATE1, STATE0
+
+	/* Add current hash values with previously saved */
+	paddd		0*16(%esp), STATE0
+	paddd		1*16(%esp), STATE1
+
+	/* Write hash values back in the correct order */
+	shuf128_32	$0x1B, STATE0,  STATE0		/* FEBA */
+	shuf128_32	$0xB1, STATE1,  STATE1		/* DCHG */
+	mova128		STATE0, MSGTMP4
+	pblendw		$0xF0, STATE1,  STATE0		/* DCBA */
+	palignr		$8, MSGTMP4, STATE1		/* HGFE */
+
+	movu128		STATE0, 76+0*16(%eax)
+	movu128		STATE1, 76+1*16(%eax)
+
+	movl	%ebp, %esp
+	popl	%ebp
+	ret
+	.size	sha256_process_block64_shaNI, .-sha256_process_block64_shaNI
+
+.section	.rodata.cst256.K256, "aM", @progbits, 256
+.balign 16
+K256:
+	.long	0x428a2f98,0x71374491,0xb5c0fbcf,0xe9b5dba5
+	.long	0x3956c25b,0x59f111f1,0x923f82a4,0xab1c5ed5
+	.long	0xd807aa98,0x12835b01,0x243185be,0x550c7dc3
+	.long	0x72be5d74,0x80deb1fe,0x9bdc06a7,0xc19bf174
+	.long	0xe49b69c1,0xefbe4786,0x0fc19dc6,0x240ca1cc
+	.long	0x2de92c6f,0x4a7484aa,0x5cb0a9dc,0x76f988da
+	.long	0x983e5152,0xa831c66d,0xb00327c8,0xbf597fc7
+	.long	0xc6e00bf3,0xd5a79147,0x06ca6351,0x14292967
+	.long	0x27b70a85,0x2e1b2138,0x4d2c6dfc,0x53380d13
+	.long	0x650a7354,0x766a0abb,0x81c2c92e,0x92722c85
+	.long	0xa2bfe8a1,0xa81a664b,0xc24b8b70,0xc76c51a3
+	.long	0xd192e819,0xd6990624,0xf40e3585,0x106aa070
+	.long	0x19a4c116,0x1e376c08,0x2748774c,0x34b0bcb5
+	.long	0x391c0cb3,0x4ed8aa4a,0x5b9cca4f,0x682e6ff3
+	.long	0x748f82ee,0x78a5636f,0x84c87814,0x8cc70208
+	.long	0x90befffa,0xa4506ceb,0xbef9a3f7,0xc67178f2
+
+.section	.rodata.cst16.PSHUFFLE_BSWAP32_FLIP_MASK, "aM", @progbits, 16
+.balign 16
+PSHUFFLE_BSWAP32_FLIP_MASK:
+	.octa 0x0c0d0e0f08090a0b0405060700010203
+
+#endif
diff --git a/libbb/hash_md5_sha256_x86-64_shaNI.S b/libbb/hash_md5_sha256_x86-64_shaNI.S
new file mode 100644
index 0000000..1c2b75a
--- /dev/null
+++ b/libbb/hash_md5_sha256_x86-64_shaNI.S
@@ -0,0 +1,281 @@
+#if ENABLE_SHA256_HWACCEL && defined(__GNUC__) && defined(__x86_64__)
+/* The code is adapted from Linux kernel's source */
+
+// We use shorter insns, even though they are for "wrong"
+// data type (fp, not int).
+// For Intel, there is no penalty for doing it at all
+// (CPUs which do have such penalty do not support SHA1 insns).
+// For AMD, the penalty is one extra cycle
+// (allegedly: I failed to find measurable difference).
+
+//#define mova128 movdqa
+#define mova128 movaps
+//#define movu128 movdqu
+#define movu128 movups
+//#define shuf128_32 pshufd
+#define shuf128_32 shufps
+
+	.section	.text.sha256_process_block64_shaNI, "ax", @progbits
+	.globl	sha256_process_block64_shaNI
+	.hidden	sha256_process_block64_shaNI
+	.type	sha256_process_block64_shaNI, @function
+
+#define DATA_PTR	%rdi
+
+#define SHA256CONSTANTS	%rax
+
+#define MSG		%xmm0
+#define STATE0		%xmm1
+#define STATE1		%xmm2
+#define MSGTMP0		%xmm3
+#define MSGTMP1		%xmm4
+#define MSGTMP2		%xmm5
+#define MSGTMP3		%xmm6
+#define MSGTMP4		%xmm7
+
+#define SHUF_MASK	%xmm8
+
+#define ABEF_SAVE	%xmm9
+#define CDGH_SAVE	%xmm10
+
+	.balign	8	# allow decoders to fetch at least 2 first insns
+sha256_process_block64_shaNI:
+	movu128		80+0*16(%rdi), STATE0
+	movu128		80+1*16(%rdi), STATE1
+
+	shuf128_32	$0xB1, STATE0,  STATE0		/* CDAB */
+	shuf128_32	$0x1B, STATE1,  STATE1		/* EFGH */
+	mova128		STATE0, MSGTMP4
+	palignr		$8, STATE1,  STATE0		/* ABEF */
+	pblendw		$0xF0, MSGTMP4, STATE1		/* CDGH */
+
+	mova128		PSHUFFLE_BSWAP32_FLIP_MASK(%rip), SHUF_MASK
+	lea		K256(%rip), SHA256CONSTANTS
+
+	/* Save hash values for addition after rounds */
+	mova128		STATE0, ABEF_SAVE
+	mova128		STATE1, CDGH_SAVE
+
+	/* Rounds 0-3 */
+	movu128		0*16(DATA_PTR), MSG
+	pshufb		SHUF_MASK, MSG
+	mova128		MSG, MSGTMP0
+		paddd		0*16(SHA256CONSTANTS), MSG
+		sha256rnds2	STATE0, STATE1
+		shuf128_32	$0x0E, MSG, MSG
+		sha256rnds2	STATE1, STATE0
+
+	/* Rounds 4-7 */
+	movu128		1*16(DATA_PTR), MSG
+	pshufb		SHUF_MASK, MSG
+	mova128		MSG, MSGTMP1
+		paddd		1*16(SHA256CONSTANTS), MSG
+		sha256rnds2	STATE0, STATE1
+		shuf128_32	$0x0E, MSG, MSG
+		sha256rnds2	STATE1, STATE0
+	sha256msg1	MSGTMP1, MSGTMP0
+
+	/* Rounds 8-11 */
+	movu128		2*16(DATA_PTR), MSG
+	pshufb		SHUF_MASK, MSG
+	mova128		MSG, MSGTMP2
+		paddd		2*16(SHA256CONSTANTS), MSG
+		sha256rnds2	STATE0, STATE1
+		shuf128_32	$0x0E, MSG, MSG
+		sha256rnds2	STATE1, STATE0
+	sha256msg1	MSGTMP2, MSGTMP1
+
+	/* Rounds 12-15 */
+	movu128		3*16(DATA_PTR), MSG
+	pshufb		SHUF_MASK, MSG
+	mova128		MSG, MSGTMP3
+		paddd		3*16(SHA256CONSTANTS), MSG
+		sha256rnds2	STATE0, STATE1
+	mova128		MSGTMP3, MSGTMP4
+	palignr		$4, MSGTMP2, MSGTMP4
+	paddd		MSGTMP4, MSGTMP0
+	sha256msg2	MSGTMP3, MSGTMP0
+		shuf128_32	$0x0E, MSG, MSG
+		sha256rnds2	STATE1, STATE0
+	sha256msg1	MSGTMP3, MSGTMP2
+
+	/* Rounds 16-19 */
+	mova128		MSGTMP0, MSG
+		paddd		4*16(SHA256CONSTANTS), MSG
+		sha256rnds2	STATE0, STATE1
+	mova128		MSGTMP0, MSGTMP4
+	palignr		$4, MSGTMP3, MSGTMP4
+	paddd		MSGTMP4, MSGTMP1
+	sha256msg2	MSGTMP0, MSGTMP1
+		shuf128_32	$0x0E, MSG, MSG
+		sha256rnds2	STATE1, STATE0
+	sha256msg1	MSGTMP0, MSGTMP3
+
+	/* Rounds 20-23 */
+	mova128		MSGTMP1, MSG
+		paddd		5*16(SHA256CONSTANTS), MSG
+		sha256rnds2	STATE0, STATE1
+	mova128		MSGTMP1, MSGTMP4
+	palignr		$4, MSGTMP0, MSGTMP4
+	paddd		MSGTMP4, MSGTMP2
+	sha256msg2	MSGTMP1, MSGTMP2
+		shuf128_32	$0x0E, MSG, MSG
+		sha256rnds2	STATE1, STATE0
+	sha256msg1	MSGTMP1, MSGTMP0
+
+	/* Rounds 24-27 */
+	mova128		MSGTMP2, MSG
+		paddd		6*16(SHA256CONSTANTS), MSG
+		sha256rnds2	STATE0, STATE1
+	mova128		MSGTMP2, MSGTMP4
+	palignr		$4, MSGTMP1, MSGTMP4
+	paddd		MSGTMP4, MSGTMP3
+	sha256msg2	MSGTMP2, MSGTMP3
+		shuf128_32	$0x0E, MSG, MSG
+		sha256rnds2	STATE1, STATE0
+	sha256msg1	MSGTMP2, MSGTMP1
+
+	/* Rounds 28-31 */
+	mova128		MSGTMP3, MSG
+		paddd		7*16(SHA256CONSTANTS), MSG
+		sha256rnds2	STATE0, STATE1
+	mova128		MSGTMP3, MSGTMP4
+	palignr		$4, MSGTMP2, MSGTMP4
+	paddd		MSGTMP4, MSGTMP0
+	sha256msg2	MSGTMP3, MSGTMP0
+		shuf128_32	$0x0E, MSG, MSG
+		sha256rnds2	STATE1, STATE0
+	sha256msg1	MSGTMP3, MSGTMP2
+
+	/* Rounds 32-35 */
+	mova128		MSGTMP0, MSG
+		paddd		8*16(SHA256CONSTANTS), MSG
+		sha256rnds2	STATE0, STATE1
+	mova128		MSGTMP0, MSGTMP4
+	palignr		$4, MSGTMP3, MSGTMP4
+	paddd		MSGTMP4, MSGTMP1
+	sha256msg2	MSGTMP0, MSGTMP1
+		shuf128_32	$0x0E, MSG, MSG
+		sha256rnds2	STATE1, STATE0
+	sha256msg1	MSGTMP0, MSGTMP3
+
+	/* Rounds 36-39 */
+	mova128		MSGTMP1, MSG
+		paddd		9*16(SHA256CONSTANTS), MSG
+		sha256rnds2	STATE0, STATE1
+	mova128		MSGTMP1, MSGTMP4
+	palignr		$4, MSGTMP0, MSGTMP4
+	paddd		MSGTMP4, MSGTMP2
+	sha256msg2	MSGTMP1, MSGTMP2
+		shuf128_32	$0x0E, MSG, MSG
+		sha256rnds2	STATE1, STATE0
+	sha256msg1	MSGTMP1, MSGTMP0
+
+	/* Rounds 40-43 */
+	mova128		MSGTMP2, MSG
+		paddd		10*16(SHA256CONSTANTS), MSG
+		sha256rnds2	STATE0, STATE1
+	mova128		MSGTMP2, MSGTMP4
+	palignr		$4, MSGTMP1, MSGTMP4
+	paddd		MSGTMP4, MSGTMP3
+	sha256msg2	MSGTMP2, MSGTMP3
+		shuf128_32	$0x0E, MSG, MSG
+		sha256rnds2	STATE1, STATE0
+	sha256msg1	MSGTMP2, MSGTMP1
+
+	/* Rounds 44-47 */
+	mova128		MSGTMP3, MSG
+		paddd		11*16(SHA256CONSTANTS), MSG
+		sha256rnds2	STATE0, STATE1
+	mova128		MSGTMP3, MSGTMP4
+	palignr		$4, MSGTMP2, MSGTMP4
+	paddd		MSGTMP4, MSGTMP0
+	sha256msg2	MSGTMP3, MSGTMP0
+		shuf128_32	$0x0E, MSG, MSG
+		sha256rnds2	STATE1, STATE0
+	sha256msg1	MSGTMP3, MSGTMP2
+
+	/* Rounds 48-51 */
+	mova128		MSGTMP0, MSG
+		paddd		12*16(SHA256CONSTANTS), MSG
+		sha256rnds2	STATE0, STATE1
+	mova128		MSGTMP0, MSGTMP4
+	palignr		$4, MSGTMP3, MSGTMP4
+	paddd		MSGTMP4, MSGTMP1
+	sha256msg2	MSGTMP0, MSGTMP1
+		shuf128_32	$0x0E, MSG, MSG
+		sha256rnds2	STATE1, STATE0
+	sha256msg1	MSGTMP0, MSGTMP3
+
+	/* Rounds 52-55 */
+	mova128		MSGTMP1, MSG
+		paddd		13*16(SHA256CONSTANTS), MSG
+		sha256rnds2	STATE0, STATE1
+	mova128		MSGTMP1, MSGTMP4
+	palignr		$4, MSGTMP0, MSGTMP4
+	paddd		MSGTMP4, MSGTMP2
+	sha256msg2	MSGTMP1, MSGTMP2
+		shuf128_32	$0x0E, MSG, MSG
+		sha256rnds2	STATE1, STATE0
+
+	/* Rounds 56-59 */
+	mova128		MSGTMP2, MSG
+		paddd		14*16(SHA256CONSTANTS), MSG
+		sha256rnds2	STATE0, STATE1
+	mova128		MSGTMP2, MSGTMP4
+	palignr		$4, MSGTMP1, MSGTMP4
+	paddd		MSGTMP4, MSGTMP3
+	sha256msg2	MSGTMP2, MSGTMP3
+		shuf128_32	$0x0E, MSG, MSG
+		sha256rnds2	STATE1, STATE0
+
+	/* Rounds 60-63 */
+	mova128		MSGTMP3, MSG
+		paddd		15*16(SHA256CONSTANTS), MSG
+		sha256rnds2	STATE0, STATE1
+		shuf128_32	$0x0E, MSG, MSG
+		sha256rnds2	STATE1, STATE0
+
+	/* Add current hash values with previously saved */
+	paddd		ABEF_SAVE, STATE0
+	paddd		CDGH_SAVE, STATE1
+
+	/* Write hash values back in the correct order */
+	shuf128_32	$0x1B, STATE0,  STATE0		/* FEBA */
+	shuf128_32	$0xB1, STATE1,  STATE1		/* DCHG */
+	mova128		STATE0, MSGTMP4
+	pblendw		$0xF0, STATE1,  STATE0		/* DCBA */
+	palignr		$8, MSGTMP4, STATE1		/* HGFE */
+
+	movu128		STATE0, 80+0*16(%rdi)
+	movu128		STATE1, 80+1*16(%rdi)
+
+	ret
+	.size	sha256_process_block64_shaNI, .-sha256_process_block64_shaNI
+
+.section	.rodata.cst256.K256, "aM", @progbits, 256
+.balign 16
+K256:
+	.long	0x428a2f98,0x71374491,0xb5c0fbcf,0xe9b5dba5
+	.long	0x3956c25b,0x59f111f1,0x923f82a4,0xab1c5ed5
+	.long	0xd807aa98,0x12835b01,0x243185be,0x550c7dc3
+	.long	0x72be5d74,0x80deb1fe,0x9bdc06a7,0xc19bf174
+	.long	0xe49b69c1,0xefbe4786,0x0fc19dc6,0x240ca1cc
+	.long	0x2de92c6f,0x4a7484aa,0x5cb0a9dc,0x76f988da
+	.long	0x983e5152,0xa831c66d,0xb00327c8,0xbf597fc7
+	.long	0xc6e00bf3,0xd5a79147,0x06ca6351,0x14292967
+	.long	0x27b70a85,0x2e1b2138,0x4d2c6dfc,0x53380d13
+	.long	0x650a7354,0x766a0abb,0x81c2c92e,0x92722c85
+	.long	0xa2bfe8a1,0xa81a664b,0xc24b8b70,0xc76c51a3
+	.long	0xd192e819,0xd6990624,0xf40e3585,0x106aa070
+	.long	0x19a4c116,0x1e376c08,0x2748774c,0x34b0bcb5
+	.long	0x391c0cb3,0x4ed8aa4a,0x5b9cca4f,0x682e6ff3
+	.long	0x748f82ee,0x78a5636f,0x84c87814,0x8cc70208
+	.long	0x90befffa,0xa4506ceb,0xbef9a3f7,0xc67178f2
+
+.section	.rodata.cst16.PSHUFFLE_BSWAP32_FLIP_MASK, "aM", @progbits, 16
+.balign 16
+PSHUFFLE_BSWAP32_FLIP_MASK:
+	.octa 0x0c0d0e0f08090a0b0405060700010203
+
+#endif
diff --git a/libbb/hash_md5_sha_x86-32_shaNI.S b/libbb/hash_md5_sha_x86-32_shaNI.S
index 166cfd3..11b855e 100644
--- a/libbb/hash_md5_sha_x86-32_shaNI.S
+++ b/libbb/hash_md5_sha_x86-32_shaNI.S
@@ -20,7 +20,7 @@
 #define extr128_32 pextrd
 //#define extr128_32 extractps	# not shorter
 
-	.section	.text.sha1_process_block64_shaNI,"ax",@progbits
+	.section	.text.sha1_process_block64_shaNI, "ax", @progbits
 	.globl	sha1_process_block64_shaNI
 	.hidden	sha1_process_block64_shaNI
 	.type	sha1_process_block64_shaNI, @function
@@ -224,7 +224,7 @@ sha1_process_block64_shaNI:
 	.size	sha1_process_block64_shaNI, .-sha1_process_block64_shaNI
 
 .section	.rodata.cst16.PSHUFFLE_BYTE_FLIP_MASK, "aM", @progbits, 16
-.align 16
+.balign 16
 PSHUFFLE_BYTE_FLIP_MASK:
 	.octa 0x000102030405060708090a0b0c0d0e0f
 
diff --git a/libbb/hash_md5_sha_x86-64.S b/libbb/hash_md5_sha_x86-64.S
index 743269d..47ace60 100644
--- a/libbb/hash_md5_sha_x86-64.S
+++ b/libbb/hash_md5_sha_x86-64.S
@@ -1394,7 +1394,7 @@ sha1_process_block64:
 	.size	sha1_process_block64, .-sha1_process_block64
 
 	.section	.rodata.cst16.sha1const, "aM", @progbits, 16
-	.align	16
+	.balign	16
 rconst0x5A827999:
 	.long	0x5A827999
 	.long	0x5A827999
diff --git a/libbb/hash_md5_sha_x86-64.S.sh b/libbb/hash_md5_sha_x86-64.S.sh
index 47c40af..656fb54 100755
--- a/libbb/hash_md5_sha_x86-64.S.sh
+++ b/libbb/hash_md5_sha_x86-64.S.sh
@@ -433,7 +433,7 @@ echo "
 	.size	sha1_process_block64, .-sha1_process_block64
 
 	.section	.rodata.cst16.sha1const, \"aM\", @progbits, 16
-	.align	16
+	.balign	16
 rconst0x5A827999:
 	.long	0x5A827999
 	.long	0x5A827999
diff --git a/libbb/hash_md5_sha_x86-64_shaNI.S b/libbb/hash_md5_sha_x86-64_shaNI.S
index 33cc3bf..ba92f09 100644
--- a/libbb/hash_md5_sha_x86-64_shaNI.S
+++ b/libbb/hash_md5_sha_x86-64_shaNI.S
@@ -20,7 +20,7 @@
 #define extr128_32 pextrd
 //#define extr128_32 extractps	# not shorter
 
-	.section	.text.sha1_process_block64_shaNI,"ax",@progbits
+	.section	.text.sha1_process_block64_shaNI, "ax", @progbits
 	.globl	sha1_process_block64_shaNI
 	.hidden	sha1_process_block64_shaNI
 	.type	sha1_process_block64_shaNI, @function
@@ -218,7 +218,7 @@ sha1_process_block64_shaNI:
 	.size	sha1_process_block64_shaNI, .-sha1_process_block64_shaNI
 
 .section	.rodata.cst16.PSHUFFLE_BYTE_FLIP_MASK, "aM", @progbits, 16
-.align 16
+.balign 16
 PSHUFFLE_BYTE_FLIP_MASK:
 	.octa 0x000102030405060708090a0b0c0d0e0f