Only perform the NEON yield check for every 4 blocks of input, to
prevent taking a considerable performance hit on cores with very
fast crypto instructions and comparatively slow memory accesses,
such as the Cortex-A53.
Signed-off-by: Ard Biesheuvel <ard.biesheu...@linaro.org>
---
arch/arm64/crypto/sha1-ce-core.S | 3 +++
1 file changed, 3 insertions(+)
diff --git a/arch/arm64/crypto/sha1-ce-core.S b/arch/arm64/crypto/sha1-ce-core.S
index 78eb35fb5056..f592c55218d0 100644
--- a/arch/arm64/crypto/sha1-ce-core.S
+++ b/arch/arm64/crypto/sha1-ce-core.S
@@ -129,6 +129,9 @@ CPU_LE( rev32 v11.16b, v11.16b )
add dgbv.2s, dgbv.2s, dg1v.2s
add dgav.4s, dgav.4s, dg0v.4s
+ tst w21, #0x3 // yield only every 4 blocks
+ b.ne 1b
+
cbz w21, 3f
if_will_cond_yield_neon
--
2.11.0
