Update build files in generated-src

aws · Jan 15, 2024 · 2e3ff96 · 2e3ff96
1 parent 0380bac
commit 2e3ff96
Show file tree

Hide file tree

Showing 11 changed files with 87 additions and 461 deletions.
diff --git a/generated-src/ios-aarch64/crypto/fipsmodule/aesv8-gcm-armv8-unroll8.S b/generated-src/ios-aarch64/crypto/fipsmodule/aesv8-gcm-armv8-unroll8.S
diff --git a/generated-src/ios-aarch64/crypto/fipsmodule/aesv8-gcm-armv8.S b/generated-src/ios-aarch64/crypto/fipsmodule/aesv8-gcm-armv8.S
@@ -83,7 +83,6 @@ _aes_gcm_enc_kernel:
 	aese	v1.16b, v19.16b
 	aesmc	v1.16b, v1.16b          // AES block 1 - round 1
 	ldr	q14, [x6, #48]                              // load h3l | h3h
-	ext	v14.16b, v14.16b, v14.16b, #8
 	aese	v3.16b, v18.16b
 	aesmc	v3.16b, v3.16b          // AES block 3 - round 0
 	aese	v2.16b, v19.16b
@@ -92,14 +91,12 @@ _aes_gcm_enc_kernel:
 	aese	v1.16b, v20.16b
 	aesmc	v1.16b, v1.16b          // AES block 1 - round 2
 	ldr	q13, [x6, #32]                              // load h2l | h2h
-	ext	v13.16b, v13.16b, v13.16b, #8
 	aese	v3.16b, v19.16b
 	aesmc	v3.16b, v3.16b          // AES block 3 - round 1
 	ldr	q30, [x8, #192]                               // load rk12
 	aese	v2.16b, v20.16b
 	aesmc	v2.16b, v2.16b          // AES block 2 - round 2
 	ldr	q15, [x6, #80]                              // load h4l | h4h
-	ext	v15.16b, v15.16b, v15.16b, #8
 	aese	v1.16b, v21.16b
 	aesmc	v1.16b, v1.16b          // AES block 1 - round 3
 	ldr	q29, [x8, #176]                               // load rk11
@@ -142,7 +139,6 @@ _aes_gcm_enc_kernel:
 	aese	v0.16b, v24.16b
 	aesmc	v0.16b, v0.16b          // AES block 0 - round 6
 	ldr	q12, [x6]                                   // load h1l | h1h
-	ext	v12.16b, v12.16b, v12.16b, #8
 	aese	v2.16b, v24.16b
 	aesmc	v2.16b, v2.16b          // AES block 2 - round 6
 	ldr	q28, [x8, #160]                               // load rk10
@@ -843,15 +839,12 @@ _aes_gcm_dec_kernel:
 	aese	v0.16b, v18.16b
 	aesmc	v0.16b, v0.16b          // AES block 0 - round 0
 	ldr	q14, [x6, #48]                              // load h3l | h3h
-	ext	v14.16b, v14.16b, v14.16b, #8
 	aese	v3.16b, v18.16b
 	aesmc	v3.16b, v3.16b          // AES block 3 - round 0
 	ldr	q15, [x6, #80]                              // load h4l | h4h
-	ext	v15.16b, v15.16b, v15.16b, #8
 	aese	v1.16b, v18.16b
 	aesmc	v1.16b, v1.16b          // AES block 1 - round 0
 	ldr	q13, [x6, #32]                              // load h2l | h2h
-	ext	v13.16b, v13.16b, v13.16b, #8
 	aese	v2.16b, v18.16b
 	aesmc	v2.16b, v2.16b          // AES block 2 - round 0
 	ldr	q20, [x8, #32]                                 // load rk2
@@ -871,7 +864,6 @@ _aes_gcm_dec_kernel:
 	aese	v0.16b, v20.16b
 	aesmc	v0.16b, v0.16b          // AES block 0 - round 2
 	ldr	q12, [x6]                                   // load h1l | h1h
-	ext	v12.16b, v12.16b, v12.16b, #8
 	aese	v2.16b, v20.16b
 	aesmc	v2.16b, v2.16b          // AES block 2 - round 2
 	ldr	q28, [x8, #160]                               // load rk10

diff --git a/generated-src/ios-aarch64/crypto/fipsmodule/ghashv8-armx.S b/generated-src/ios-aarch64/crypto/fipsmodule/ghashv8-armx.S
@@ -30,7 +30,9 @@ _gcm_init_v8:
 	and	v16.16b,v16.16b,v17.16b
 	orr	v3.16b,v3.16b,v18.16b		//H<<<=1
 	eor	v20.16b,v3.16b,v16.16b		//twisted H
+	ext	v20.16b, v20.16b, v20.16b, #8
 	st1	{v20.2d},[x0],#16		//store Htable[0]
+	ext	v20.16b, v20.16b, v20.16b, #8
 
 	//calculate H^2
 	ext	v16.16b,v20.16b,v20.16b,#8		//Karatsuba pre-processing
@@ -57,7 +59,10 @@ _gcm_init_v8:
 	ext	v17.16b,v22.16b,v22.16b,#8		//Karatsuba pre-processing
 	eor	v17.16b,v17.16b,v22.16b
 	ext	v21.16b,v16.16b,v17.16b,#8		//pack Karatsuba pre-processed
-	st1	{v21.2d,v22.2d},[x0],#32	//store Htable[1..2]
+	st1	{v21.2d},[x0],#16	//store Htable[1..2]
+	ext	v22.16b, v22.16b, v22.16b, #8
+	st1	{v22.2d},[x0],#16	//store Htable[1..2]
+	ext	v22.16b, v22.16b, v22.16b, #8
 	//calculate H^3 and H^4
 	pmull	v0.1q,v20.1d, v22.1d
 	pmull	v5.1q,v22.1d,v22.1d
@@ -101,7 +106,11 @@ _gcm_init_v8:
 	eor	v17.16b,v17.16b,v25.16b
 	eor	v18.16b,v18.16b,v22.16b
 	ext	v24.16b,v16.16b,v17.16b,#8	//pack Karatsuba pre-processed
+	ext	v23.16b, v23.16b, v23.16b, #8
+	ext	v25.16b, v25.16b, v25.16b, #8
 	st1	{v23.2d,v24.2d,v25.2d},[x0],#48	//store Htable[3..5]
+	ext	v23.16b, v23.16b, v23.16b, #8
+	ext	v25.16b, v25.16b, v25.16b, #8
 
 	//calculate H^5 and H^6
 	pmull	v0.1q,v22.1d, v23.1d
@@ -145,7 +154,11 @@ _gcm_init_v8:
 	eor	v17.16b,v17.16b,v28.16b
 	eor	v18.16b,v18.16b,v22.16b
 	ext	v27.16b,v16.16b,v17.16b,#8	//pack Karatsuba pre-processed
+	ext	v26.16b, v26.16b, v26.16b, #8
+	ext	v28.16b, v28.16b, v28.16b, #8
 	st1	{v26.2d,v27.2d,v28.2d},[x0],#48	//store Htable[6..8]
+	ext	v26.16b, v26.16b, v26.16b, #8
+	ext	v28.16b, v28.16b, v28.16b, #8
 
 	//calculate H^7 and H^8
 	pmull	v0.1q,v22.1d,v26.1d
@@ -187,6 +200,8 @@ _gcm_init_v8:
 	eor	v16.16b,v16.16b,v29.16b
 	eor	v17.16b,v17.16b,v31.16b
 	ext	v30.16b,v16.16b,v17.16b,#8	//pack Karatsuba pre-processed
+	ext	v29.16b, v29.16b, v29.16b, #8
+	ext	v31.16b, v31.16b, v31.16b, #8
 	st1	{v29.2d,v30.2d,v31.2d},[x0]		//store Htable[9..11]
 	ret
 
@@ -199,6 +214,7 @@ _gcm_gmult_v8:
 	ld1	{v17.2d},[x0]		//load Xi
 	movi	v19.16b,#0xe1
 	ld1	{v20.2d,v21.2d},[x1]	//load twisted H, ...
+	ext	v20.16b,v20.16b,v20.16b,#8
 	shl	v19.2d,v19.2d,#57
 #ifndef __AARCH64EB__
 	rev64	v17.16b,v17.16b
@@ -258,8 +274,10 @@ _gcm_ghash_v8:
 						//loaded twice, but last
 						//copy is not processed
 	ld1	{v20.2d,v21.2d},[x1],#32	//load twisted H, ..., H^2
+	ext	v20.16b,v20.16b,v20.16b,#8
 	movi	v19.16b,#0xe1
 	ld1	{v22.2d},[x1]
+	ext	v22.16b,v22.16b,v22.16b,#8
 	csel	x12,xzr,x12,eq			//is it time to zero x12?
 	ext	v0.16b,v0.16b,v0.16b,#8		//rotate Xi
 	ld1	{v16.2d},[x2],#16	//load [rotated] I[0]
@@ -373,8 +391,12 @@ gcm_ghash_v8_4x:
 Lgcm_ghash_v8_4x:
 	ld1	{v0.2d},[x0]		//load [rotated] Xi
 	ld1	{v20.2d,v21.2d,v22.2d},[x1],#48	//load twisted H, ..., H^2
+	ext	v20.16b,v20.16b,v20.16b,#8
+	ext	v22.16b,v22.16b,v22.16b,#8
 	movi	v19.16b,#0xe1
 	ld1	{v26.2d,v27.2d,v28.2d},[x1]	//load twisted H^3, ..., H^4
+	ext	v26.16b,v26.16b,v26.16b,#8
+	ext	v28.16b,v28.16b,v28.16b,#8
 	shl	v19.2d,v19.2d,#57		//compose 0xc2.0 constant
 
 	ld1	{v4.2d,v5.2d,v6.2d,v7.2d},[x2],#64

diff --git a/generated-src/ios-arm/crypto/fipsmodule/ghashv8-armx.S b/generated-src/ios-arm/crypto/fipsmodule/ghashv8-armx.S
@@ -34,7 +34,9 @@ _gcm_init_v8:
 	vand	q8,q8,q9
 	vorr	q3,q3,q10		@ H<<<=1
 	veor	q12,q3,q8		@ twisted H
+	vext.8	q12, q12, q12, #8
 	vst1.64	{q12},[r0]!		@ store Htable[0]
+	vext.8	q12, q12, q12, #8
 
 	@ calculate H^2
 	vext.8	q8,q12,q12,#8		@ Karatsuba pre-processing
@@ -61,7 +63,10 @@ _gcm_init_v8:
 	vext.8	q9,q14,q14,#8		@ Karatsuba pre-processing
 	veor	q9,q9,q14
 	vext.8	q13,q8,q9,#8		@ pack Karatsuba pre-processed
-	vst1.64	{q13,q14},[r0]!	@ store Htable[1..2]
+	vst1.64	{q13},[r0]!	@ store Htable[1..2]
+	vext.8	q14, q14, q14, #8
+	vst1.64	{q14},[r0]!	@ store Htable[1..2]
+	vext.8	q14, q14, q14, #8
 	bx	lr
 
 .globl	_gcm_gmult_v8
@@ -75,6 +80,7 @@ _gcm_gmult_v8:
 	vld1.64	{q9},[r0]		@ load Xi
 	vmov.i8	q11,#0xe1
 	vld1.64	{q12,q13},[r1]	@ load twisted H, ...
+	vext.8	q12,q12,q12,#8
 	vshl.u64	q11,q11,#57
 #ifndef __ARMEB__
 	vrev64.8	q9,q9
@@ -135,8 +141,10 @@ _gcm_ghash_v8:
 						@ loaded twice, but last
 						@ copy is not processed
 	vld1.64	{q12,q13},[r1]!	@ load twisted H, ..., H^2
+	vext.8	q12,q12,q12,#8
 	vmov.i8	q11,#0xe1
 	vld1.64	{q14},[r1]
+	vext.8	q14,q14,q14,#8
 	moveq	r12,#0			@ is it time to zero r12?
 	vext.8	q0,q0,q0,#8		@ rotate Xi
 	vld1.64	{q8},[r2]!	@ load [rotated] I[0]