From: Andy Polyakov <appro@openssl.org>
Date: Mon, 24 Jul 2017 19:50:52 +0000 (+0200)
Subject: x86_64 assembly pack: "optimize" for Knights Landing.
X-Git-Tag: OpenSSL_1_1_0g~126
X-Git-Url: https://git.librecmc.org/?a=commitdiff_plain;h=738a9dd53cacce593cd7d67e18e1273549640a79;p=oweals%2Fopenssl.git

x86_64 assembly pack: "optimize" for Knights Landing.

"Optimize" is in quotes because it's rather a "salvage operation"
for now. Idea is to identify processor capability flags that
drive Knights Landing to suboptimial code paths and mask them.
Two flags were identified, XSAVE and ADCX/ADOX. Former affects
choice of AES-NI code path specific for Silvermont (Knights Landing
is of Silvermont "ancestry"). And 64-bit ADCX/ADOX instructions are
effectively mishandled at decode time. In both cases we are looking
at ~2x improvement.

Hardware used for benchmarking courtesy of Atos, experiments run by
Romain Dolbeau <romain.dolbeau@atos.net>. Kudos!

This is minimalistic backpoint of 64d92d74985ebb3d0be58a9718f9e080a14a8e7f

Thanks to David Benjamin for spotting typo in Knights Landing detection!

Reviewed-by: Rich Salz <rsalz@openssl.org>
(Merged from https://github.com/openssl/openssl/pull/4006)
---

diff --git a/crypto/x86_64cpuid.pl b/crypto/x86_64cpuid.pl
index afc50af020..7995b5cc25 100644
--- a/crypto/x86_64cpuid.pl
+++ b/crypto/x86_64cpuid.pl
@@ -143,8 +143,19 @@ OPENSSL_ia32_cpuid:
 	or	\$0x40000000,%edx	# set reserved bit#30 on Intel CPUs
 	and	\$15,%ah
 	cmp	\$15,%ah		# examine Family ID
-	jne	.Lnotintel
+	jne	.LnotP4
 	or	\$0x00100000,%edx	# set reserved bit#20 to engage RC4_CHAR
+.LnotP4:
+	cmp	\$6,%ah
+	jne	.Lnotintel
+	and	\$0x0fff0ff0,%eax
+	cmp	\$0x00050670,%eax	# Knights Landing
+	je	.Lknights
+	cmp	\$0x00080650,%eax	# Knights Mill (according to sde)
+	jne	.Lnotintel
+.Lknights:
+	and	\$0xfbffffff,%ecx	# clear XSAVE flag to mimic Silvermont
+
 .Lnotintel:
 	bt	\$28,%edx		# test hyper-threading bit
 	jnc	.Lgeneric
@@ -169,6 +180,10 @@ OPENSSL_ia32_cpuid:
 	mov	\$7,%eax
 	xor	%ecx,%ecx
 	cpuid
+	bt	\$26,%r9d		# check XSAVE bit, cleared on Knights
+	jc	.Lnotknights
+	and	\$0xfff7ffff,%ebx	# clear ADCX/ADOX flag
+.Lnotknights:
 	mov	%ebx,8(%rdi)		# save extended feature flags
 .Lno_extended_info: