lib/crypto: powerpc/sha1: Migrate optimized code into library

Instead of exposing the powerpc-optimized SHA-1 code via
powerpc-specific crypto_shash algorithms, instead just implement the
sha1_blocks() library function.  This is much simpler, it makes the
SHA-1 library functions be powerpc-optimized, and it fixes the
longstanding issue where the powerpc-optimized SHA-1 code was disabled
by default.  SHA-1 still remains available through crypto_shash, but
individual architectures no longer need to handle it.

Note: to see the diff from arch/powerpc/crypto/sha1-spe-glue.c to
lib/crypto/powerpc/sha1.h, view this commit with 'git show -M10'.

Reviewed-by: Ard Biesheuvel <ardb@kernel.org>
Link: https://lore.kernel.org/r/20250712232329.818226-11-ebiggers@kernel.org
Signed-off-by: Eric Biggers <ebiggers@kernel.org>

1 files changed, 188 insertions, 0 deletions

diff --git a/lib/crypto/powerpc/sha1-powerpc-asm.S b/lib/crypto/powerpc/sha1-powerpc-asm.S
new file mode 100644
index 000000000000..f0d5ed557ab1
--- /dev/null
+++ b/lib/crypto/powerpc/sha1-powerpc-asm.S
@@ -0,0 +1,188 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * SHA-1 implementation for PowerPC.
+ *
+ * Copyright (C) 2005 Paul Mackerras <paulus@samba.org>
+ */
+
+#include <asm/ppc_asm.h>
+#include <asm/asm-offsets.h>
+#include <asm/asm-compat.h>
+
+#ifdef __BIG_ENDIAN__
+#define LWZ(rt, d, ra)	\
+	lwz	rt,d(ra)
+#else
+#define LWZ(rt, d, ra)	\
+	li	rt,d;	\
+	lwbrx	rt,rt,ra
+#endif
+
+/*
+ * We roll the registers for T, A, B, C, D, E around on each
+ * iteration; T on iteration t is A on iteration t+1, and so on.
+ * We use registers 7 - 12 for this.
+ */
+#define RT(t)	((((t)+5)%6)+7)
+#define RA(t)	((((t)+4)%6)+7)
+#define RB(t)	((((t)+3)%6)+7)
+#define RC(t)	((((t)+2)%6)+7)
+#define RD(t)	((((t)+1)%6)+7)
+#define RE(t)	((((t)+0)%6)+7)
+
+/* We use registers 16 - 31 for the W values */
+#define W(t)	(((t)%16)+16)
+
+#define LOADW(t)				\
+	LWZ(W(t),(t)*4,r4)
+
+#define STEPD0_LOAD(t)				\
+	andc	r0,RD(t),RB(t);		\
+	and	r6,RB(t),RC(t);		\
+	rotlwi	RT(t),RA(t),5;			\
+	or	r6,r6,r0;			\
+	add	r0,RE(t),r15;			\
+	add	RT(t),RT(t),r6;		\
+	add	r14,r0,W(t);			\
+	LWZ(W((t)+4),((t)+4)*4,r4);	\
+	rotlwi	RB(t),RB(t),30;			\
+	add	RT(t),RT(t),r14
+
+#define STEPD0_UPDATE(t)			\
+	and	r6,RB(t),RC(t);		\
+	andc	r0,RD(t),RB(t);		\
+	rotlwi	RT(t),RA(t),5;			\
+	rotlwi	RB(t),RB(t),30;			\
+	or	r6,r6,r0;			\
+	add	r0,RE(t),r15;			\
+	xor	r5,W((t)+4-3),W((t)+4-8);		\
+	add	RT(t),RT(t),r6;		\
+	xor	W((t)+4),W((t)+4-16),W((t)+4-14);	\
+	add	r0,r0,W(t);			\
+	xor	W((t)+4),W((t)+4),r5;			\
+	add	RT(t),RT(t),r0;		\
+	rotlwi	W((t)+4),W((t)+4),1
+
+#define STEPD1(t)				\
+	xor	r6,RB(t),RC(t);		\
+	rotlwi	RT(t),RA(t),5;			\
+	rotlwi	RB(t),RB(t),30;			\
+	xor	r6,r6,RD(t);			\
+	add	r0,RE(t),r15;			\
+	add	RT(t),RT(t),r6;		\
+	add	r0,r0,W(t);			\
+	add	RT(t),RT(t),r0
+
+#define STEPD1_UPDATE(t)				\
+	xor	r6,RB(t),RC(t);		\
+	rotlwi	RT(t),RA(t),5;			\
+	rotlwi	RB(t),RB(t),30;			\
+	xor	r6,r6,RD(t);			\
+	add	r0,RE(t),r15;			\
+	xor	r5,W((t)+4-3),W((t)+4-8);		\
+	add	RT(t),RT(t),r6;		\
+	xor	W((t)+4),W((t)+4-16),W((t)+4-14);	\
+	add	r0,r0,W(t);			\
+	xor	W((t)+4),W((t)+4),r5;			\
+	add	RT(t),RT(t),r0;		\
+	rotlwi	W((t)+4),W((t)+4),1
+
+#define STEPD2_UPDATE(t)			\
+	and	r6,RB(t),RC(t);		\
+	and	r0,RB(t),RD(t);		\
+	rotlwi	RT(t),RA(t),5;			\
+	or	r6,r6,r0;			\
+	rotlwi	RB(t),RB(t),30;			\
+	and	r0,RC(t),RD(t);		\
+	xor	r5,W((t)+4-3),W((t)+4-8);	\
+	or	r6,r6,r0;			\
+	xor	W((t)+4),W((t)+4-16),W((t)+4-14);	\
+	add	r0,RE(t),r15;			\
+	add	RT(t),RT(t),r6;		\
+	add	r0,r0,W(t);			\
+	xor	W((t)+4),W((t)+4),r5;		\
+	add	RT(t),RT(t),r0;		\
+	rotlwi	W((t)+4),W((t)+4),1
+
+#define STEP0LD4(t)				\
+	STEPD0_LOAD(t);				\
+	STEPD0_LOAD((t)+1);			\
+	STEPD0_LOAD((t)+2);			\
+	STEPD0_LOAD((t)+3)
+
+#define STEPUP4(t, fn)				\
+	STEP##fn##_UPDATE(t);			\
+	STEP##fn##_UPDATE((t)+1);		\
+	STEP##fn##_UPDATE((t)+2);		\
+	STEP##fn##_UPDATE((t)+3)
+
+#define STEPUP20(t, fn)				\
+	STEPUP4(t, fn);				\
+	STEPUP4((t)+4, fn);			\
+	STEPUP4((t)+8, fn);			\
+	STEPUP4((t)+12, fn);			\
+	STEPUP4((t)+16, fn)
+
+_GLOBAL(powerpc_sha_transform)
+	PPC_STLU r1,-INT_FRAME_SIZE(r1)
+	SAVE_GPRS(14, 31, r1)
+
+	/* Load up A - E */
+	lwz	RA(0),0(r3)	/* A */
+	lwz	RB(0),4(r3)	/* B */
+	lwz	RC(0),8(r3)	/* C */
+	lwz	RD(0),12(r3)	/* D */
+	lwz	RE(0),16(r3)	/* E */
+
+	LOADW(0)
+	LOADW(1)
+	LOADW(2)
+	LOADW(3)
+
+	lis	r15,0x5a82	/* K0-19 */
+	ori	r15,r15,0x7999
+	STEP0LD4(0)
+	STEP0LD4(4)
+	STEP0LD4(8)
+	STEPUP4(12, D0)
+	STEPUP4(16, D0)
+
+	lis	r15,0x6ed9	/* K20-39 */
+	ori	r15,r15,0xeba1
+	STEPUP20(20, D1)
+
+	lis	r15,0x8f1b	/* K40-59 */
+	ori	r15,r15,0xbcdc
+	STEPUP20(40, D2)
+
+	lis	r15,0xca62	/* K60-79 */
+	ori	r15,r15,0xc1d6
+	STEPUP4(60, D1)
+	STEPUP4(64, D1)
+	STEPUP4(68, D1)
+	STEPUP4(72, D1)
+	lwz	r20,16(r3)
+	STEPD1(76)
+	lwz	r19,12(r3)
+	STEPD1(77)
+	lwz	r18,8(r3)
+	STEPD1(78)
+	lwz	r17,4(r3)
+	STEPD1(79)
+
+	lwz	r16,0(r3)
+	add	r20,RE(80),r20
+	add	RD(0),RD(80),r19
+	add	RC(0),RC(80),r18
+	add	RB(0),RB(80),r17
+	add	RA(0),RA(80),r16
+	mr	RE(0),r20
+	stw	RA(0),0(r3)
+	stw	RB(0),4(r3)
+	stw	RC(0),8(r3)
+	stw	RD(0),12(r3)
+	stw	RE(0),16(r3)
+
+	REST_GPRS(14, 31, r1)
+	addi	r1,r1,INT_FRAME_SIZE
+	blr