Skip to contentSkip to conversation

lib/crypto: arm64: Assume a little-endian kernel

PATCH Applied Eric Biggers 2 participants 3 messages Apr 1 – Apr 2

Subsystems (2)
lore
Share & tools
lore

Eric Biggers

author maintainer
#0 lore raw

PATCH 1/1 lib/crypto: arm64: Assume a little-endian kernel

Since support for big-endian arm64 kernels was removed, the CPU_LE() macro now unconditionally emits the code it is passed, and the CPU_BE() macro now unconditionally discards the code it is passed.

Simplify the assembly code in lib/crypto/arm64/ accordingly.

---

This patch is targeting libcrypto-next

 lib/crypto/arm64/aes-cipher-core.S  | 10 -------
 lib/crypto/arm64/chacha-neon-core.S | 16 -----------
 lib/crypto/arm64/ghash-neon-core.S  |  2 +-
 lib/crypto/arm64/sha1-ce-core.S     |  8 +++---
 lib/crypto/arm64/sha256-ce.S        | 41 +++++++++++++----------------
 lib/crypto/arm64/sha512-ce-core.S   | 16 +++++------
 lib/crypto/arm64/sm3-ce-core.S      |  8 +++---
 7 files changed, 36 insertions(+), 65 deletions(-)
lib/crypto/arm64/aes-cipher-core.S +0 -10
index 651f701c56a86..0b05ec4be65fb 100644
@@ -85,15 +85,10 @@
 	ldp		w4, w5, [in]
 	ldp		w6, w7, [in, #8]
 	ldp		w8, w9, [rk], #16
 	ldp		w10, w11, [rk, #-8]
 
-CPU_BE(	rev		w4, w4		)
-CPU_BE(	rev		w5, w5		)
-CPU_BE(	rev		w6, w6		)
-CPU_BE(	rev		w7, w7		)
-
 	eor		w4, w4, w8
 	eor		w5, w5, w9
 	eor		w6, w6, w10
 	eor		w7, w7, w11
 
@@ -110,15 +105,10 @@ CPU_BE(	rev		w7, w7		)
 2:	\round		w4, w5, w6, w7, w8, w9, w10, w11
 	b		0b
 3:	adr_l		tt, \ltab
 	\round		w4, w5, w6, w7, w8, w9, w10, w11, \bsz, b
 
-CPU_BE(	rev		w4, w4		)
-CPU_BE(	rev		w5, w5		)
-CPU_BE(	rev		w6, w6		)
-CPU_BE(	rev		w7, w7		)
-
 	stp		w4, w5, [out]
 	stp		w6, w7, [out, #8]
 	ret
 	.endm
 
lib/crypto/arm64/chacha-neon-core.S +0 -16
index 80079586ecc7a..cb18eec968bdf 100644
@@ -529,14 +529,10 @@ SYM_FUNC_START(chacha_4block_xor_neon)
 	  add		a0, a0, w6
 	  add		a1, a1, w7
 	add		v3.4s, v3.4s, v19.4s
 	  add		a2, a2, w8
 	  add		a3, a3, w9
-CPU_BE(	  rev		a0, a0		)
-CPU_BE(	  rev		a1, a1		)
-CPU_BE(	  rev		a2, a2		)
-CPU_BE(	  rev		a3, a3		)
 
 	ld4r		{v24.4s-v27.4s}, [x0], #16
 	ld4r		{v28.4s-v31.4s}, [x0]
 
 	// x4[0-3] += s1[0]
@@ -553,14 +549,10 @@ CPU_BE(	  rev		a3, a3		)
 	  add		a4, a4, w6
 	  add		a5, a5, w7
 	add		v7.4s, v7.4s, v23.4s
 	  add		a6, a6, w8
 	  add		a7, a7, w9
-CPU_BE(	  rev		a4, a4		)
-CPU_BE(	  rev		a5, a5		)
-CPU_BE(	  rev		a6, a6		)
-CPU_BE(	  rev		a7, a7		)
 
 	// x8[0-3] += s2[0]
 	// x9[0-3] += s2[1]
 	// x10[0-3] += s2[2]
 	// x11[0-3] += s2[3]
@@ -574,14 +566,10 @@ CPU_BE(	  rev		a7, a7		)
 	  add		a8, a8, w6
 	  add		a9, a9, w7
 	add		v11.4s, v11.4s, v27.4s
 	  add		a10, a10, w8
 	  add		a11, a11, w9
-CPU_BE(	  rev		a8, a8		)
-CPU_BE(	  rev		a9, a9		)
-CPU_BE(	  rev		a10, a10	)
-CPU_BE(	  rev		a11, a11	)
 
 	// x12[0-3] += s3[0]
 	// x13[0-3] += s3[1]
 	// x14[0-3] += s3[2]
 	// x15[0-3] += s3[3]
@@ -595,14 +583,10 @@ CPU_BE(	  rev		a11, a11	)
 	  add		a12, a12, w6
 	  add		a13, a13, w7
 	add		v15.4s, v15.4s, v31.4s
 	  add		a14, a14, w8
 	  add		a15, a15, w9
-CPU_BE(	  rev		a12, a12	)
-CPU_BE(	  rev		a13, a13	)
-CPU_BE(	  rev		a14, a14	)
-CPU_BE(	  rev		a15, a15	)
 
 	// interleave 32-bit words in state n, n+1
 	  ldp		w6, w7, [x2], #64
 	zip1		v16.4s, v0.4s, v1.4s
 	  ldp		w8, w9, [x2, #-56]
lib/crypto/arm64/ghash-neon-core.S +1 -1
index 85b20fcd98fef..4c5799172b49c 100644
@@ -190,11 +190,11 @@ SYM_FUNC_START(pmull_ghash_update_p8)
 
 0:	ld1		{T1.2d}, [x2], #16
 	sub		x0, x0, #1
 
 	/* multiply XL by SHASH in GF(2^128) */
-CPU_LE(	rev64		T1.16b, T1.16b	)
+	rev64		T1.16b, T1.16b
 
 	ext		T2.16b, XL.16b, XL.16b, #8
 	ext		IN1.16b, T1.16b, T1.16b, #8
 	eor		T1.16b, T1.16b, T2.16b
 	eor		XL.16b, XL.16b, IN1.16b
lib/crypto/arm64/sha1-ce-core.S +4 -4
index 8fbd4767f0f0c..128d8393c94fb 100644
@@ -78,14 +78,14 @@ SYM_FUNC_START(__sha1_ce_transform)
 
 	/* load input */
 0:	ld1		{v8.4s-v11.4s}, [x1], #64
 	sub		x2, x2, #1
 
-CPU_LE(	rev32		v8.16b, v8.16b		)
-CPU_LE(	rev32		v9.16b, v9.16b		)
-CPU_LE(	rev32		v10.16b, v10.16b	)
-CPU_LE(	rev32		v11.16b, v11.16b	)
+	rev32		v8.16b, v8.16b
+	rev32		v9.16b, v9.16b
+	rev32		v10.16b, v10.16b
+	rev32		v11.16b, v11.16b
 
 	add		t0.4s, v8.4s, k0.4s
 	mov		dg0v.16b, dgav.16b
 
 	add_update	c, ev, k0,  8,  9, 10, 11, dgb
lib/crypto/arm64/sha256-ce.S +19 -22

88 lines not on this page · raw message

lib/crypto/arm64/sha512-ce-core.S +8 -8
index ffd51acfd1eed..0d472f5a48f95 100644
@@ -108,18 +108,18 @@ SYM_FUNC_START(__sha512_ce_transform)
 	/* load input */
 0:	ld1		{v12.2d-v15.2d}, [x1], #64
 	ld1		{v16.2d-v19.2d}, [x1], #64
 	sub		x2, x2, #1
 
-CPU_LE(	rev64		v12.16b, v12.16b	)
-CPU_LE(	rev64		v13.16b, v13.16b	)
-CPU_LE(	rev64		v14.16b, v14.16b	)
-CPU_LE(	rev64		v15.16b, v15.16b	)
-CPU_LE(	rev64		v16.16b, v16.16b	)
-CPU_LE(	rev64		v17.16b, v17.16b	)
-CPU_LE(	rev64		v18.16b, v18.16b	)
-CPU_LE(	rev64		v19.16b, v19.16b	)
+	rev64		v12.16b, v12.16b
+	rev64		v13.16b, v13.16b
+	rev64		v14.16b, v14.16b
+	rev64		v15.16b, v15.16b
+	rev64		v16.16b, v16.16b
+	rev64		v17.16b, v17.16b
+	rev64		v18.16b, v18.16b
+	rev64		v19.16b, v19.16b
 
 	mov		x4, x3				// rc pointer
 
 	mov		v0.16b, v8.16b
 	mov		v1.16b, v9.16b
lib/crypto/arm64/sm3-ce-core.S +4 -4
index 9cef7ea7f34f0..ee7f900d7cff7 100644
@@ -89,14 +89,14 @@ SYM_FUNC_START(sm3_ce_transform)
 	sub		x2, x2, #1
 
 	mov		v15.16b, v8.16b
 	mov		v16.16b, v9.16b
 
-CPU_LE(	rev32		v0.16b, v0.16b		)
-CPU_LE(	rev32		v1.16b, v1.16b		)
-CPU_LE(	rev32		v2.16b, v2.16b		)
-CPU_LE(	rev32		v3.16b, v3.16b		)
+	rev32		v0.16b, v0.16b
+	rev32		v1.16b, v1.16b
+	rev32		v2.16b, v2.16b
+	rev32		v3.16b, v3.16b
 
 	ext		v11.16b, v13.16b, v13.16b, #4
 
 	qround		a, v0, v1, v2, v3, v4
 	qround		a, v1, v2, v3, v4, v0

base-commit: d2a68aba8505ce88b39c34ecb3b707c776af79d4

Signature · 1 line
2.53.0
maintainer Reviewed-by on v1 1/1
#1 lore raw
Quoted 11 lines · Eric Biggers

Since support for big-endian arm64 kernels was removed, the CPU_LE() macro now unconditionally emits the code it is passed, and the CPU_BE() macro now unconditionally discards the code it is passed.

Simplify the assembly code in lib/crypto/arm64/ accordingly.

---

This patch is targeting libcrypto-next

Quoted 9 lines
 lib/crypto/arm64/aes-cipher-core.S  | 10 -------
 lib/crypto/arm64/chacha-neon-core.S | 16 -----------
 lib/crypto/arm64/ghash-neon-core.S  |  2 +-
 lib/crypto/arm64/sha1-ce-core.S     |  8 +++---
 lib/crypto/arm64/sha256-ce.S        | 41 +++++++++++++----------------
 lib/crypto/arm64/sha512-ce-core.S   | 16 +++++------
 lib/crypto/arm64/sm3-ce-core.S      |  8 +++---
 7 files changed, 36 insertions(+), 65 deletions(-)
author maintainer Applied
#2 lore raw
In reply to Eric Biggers
Quoted 8 lines · Eric Biggers

Since support for big-endian arm64 kernels was removed, the CPU_LE() macro now unconditionally emits the code it is passed, and the CPU_BE() macro now unconditionally discards the code it is passed.

Simplify the assembly code in lib/crypto/arm64/ accordingly.

---

Applied to https://git.kernel.org/pub/scm/linux/kernel/git/ebiggers/linux.git/log/?h=libcrypto-next

- Eric