crypto: arm64/sha2-ce - simplify NEON yield

Instead of calling into kernel_neon_end() and kernel_neon_begin() (and
potentially into schedule()) from the assembler code when running in
task mode and a reschedule is pending, perform only the preempt count
check in assembler, but simply return early in this case, and let the C
code deal with the consequences.

This reverts commit d82f37ab5e2426287013eba38b1212e8b71e5be3.

Signed-off-by: Ard Biesheuvel <ardb@kernel.org>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>

1 files changed, 13 insertions, 25 deletions

diff --git a/arch/arm64/crypto/sha2-ce-core.S b/arch/arm64/crypto/sha2-ce-core.S
index 3f9d0f326987..6cdea7d56059 100644
--- a/arch/arm64/crypto/sha2-ce-core.S
+++ b/arch/arm64/crypto/sha2-ce-core.S
@@ -76,36 +76,30 @@
 	 */
 	.text
 SYM_FUNC_START(sha2_ce_transform)
-	frame_push	3
-
-	mov		x19, x0
-	mov		x20, x1
-	mov		x21, x2
-
 	/* load round constants */
-0:	adr_l		x8, .Lsha2_rcon
+	adr_l		x8, .Lsha2_rcon
 	ld1		{ v0.4s- v3.4s}, [x8], #64
 	ld1		{ v4.4s- v7.4s}, [x8], #64
 	ld1		{ v8.4s-v11.4s}, [x8], #64
 	ld1		{v12.4s-v15.4s}, [x8]
 
 	/* load state */
-	ld1		{dgav.4s, dgbv.4s}, [x19]
+	ld1		{dgav.4s, dgbv.4s}, [x0]
 
 	/* load sha256_ce_state::finalize */
 	ldr_l		w4, sha256_ce_offsetof_finalize, x4
-	ldr		w4, [x19, x4]
+	ldr		w4, [x0, x4]
 
 	/* load input */
-1:	ld1		{v16.4s-v19.4s}, [x20], #64
-	sub		w21, w21, #1
+0:	ld1		{v16.4s-v19.4s}, [x1], #64
+	sub		w2, w2, #1
 
 CPU_LE(	rev32		v16.16b, v16.16b	)
 CPU_LE(	rev32		v17.16b, v17.16b	)
 CPU_LE(	rev32		v18.16b, v18.16b	)
 CPU_LE(	rev32		v19.16b, v19.16b	)
 
-2:	add		t0.4s, v16.4s, v0.4s
+1:	add		t0.4s, v16.4s, v0.4s
 	mov		dg0v.16b, dgav.16b
 	mov		dg1v.16b, dgbv.16b
 
@@ -134,24 +128,18 @@ CPU_LE(	rev32		v19.16b, v19.16b	)
 	add		dgbv.4s, dgbv.4s, dg1v.4s
 
 	/* handled all input blocks? */
-	cbz		w21, 3f
-
-	if_will_cond_yield_neon
-	st1		{dgav.4s, dgbv.4s}, [x19]
-	do_cond_yield_neon
+	cbz		w2, 2f
+	cond_yield	3f, x5
 	b		0b
-	endif_yield_neon
-
-	b		1b
 
 	/*
 	 * Final block: add padding and total bit count.
 	 * Skip if the input size was not a round multiple of the block size,
 	 * the padding is handled by the C code in that case.
 	 */
-3:	cbz		x4, 4f
+2:	cbz		x4, 3f
 	ldr_l		w4, sha256_ce_offsetof_count, x4
-	ldr		x4, [x19, x4]
+	ldr		x4, [x0, x4]
 	movi		v17.2d, #0
 	mov		x8, #0x80000000
 	movi		v18.2d, #0
@@ -160,10 +148,10 @@ CPU_LE(	rev32		v19.16b, v19.16b	)
 	mov		x4, #0
 	mov		v19.d[0], xzr
 	mov		v19.d[1], x7
-	b		2b
+	b		1b
 
 	/* store new state */
-4:	st1		{dgav.4s, dgbv.4s}, [x19]
-	frame_pop
+3:	st1		{dgav.4s, dgbv.4s}, [x0]
+	mov		w0, w2
 	ret
 SYM_FUNC_END(sha2_ce_transform)