8 files changed, 9 insertions, 9 deletions

diff --git a/src/crypto/sha/asm/sha1-586.pl b/src/crypto/sha/asm/sha1-586.pl
index 4895eb3..e0b5d83 100644
--- a/src/crypto/sha/asm/sha1-586.pl
+++ b/src/crypto/sha/asm/sha1-586.pl
@@ -66,9 +66,9 @@
 # switch to AVX alone improves performance by as little as 4% in
 # comparison to SSSE3 code path. But below result doesn't look like
 # 4% improvement... Trouble is that Sandy Bridge decodes 'ro[rl]' as
-# pair of µ-ops, and it's the additional µ-ops, two per round, that
+# pair of µ-ops, and it's the additional µ-ops, two per round, that
 # make it run slower than Core2 and Westmere. But 'sh[rl]d' is decoded
-# as single µ-op by Sandy Bridge and it's replacing 'ro[rl]' with
+# as single µ-op by Sandy Bridge and it's replacing 'ro[rl]' with
 # equivalent 'sh[rl]d' that is responsible for the impressive 5.1
 # cycles per processed byte. But 'sh[rl]d' is not something that used
 # to be fast, nor does it appear to be fast in upcoming Bulldozer
diff --git a/src/crypto/sha/asm/sha1-armv4-large.pl b/src/crypto/sha/asm/sha1-armv4-large.pl
index a20d336..64e2ed6 100644
--- a/src/crypto/sha/asm/sha1-armv4-large.pl
+++ b/src/crypto/sha/asm/sha1-armv4-large.pl
@@ -178,7 +178,7 @@ ___
 }
 
 $code=<<___;
-#include "arm_arch.h"
+#include <openssl/arm_arch.h>
 
 .text
 .code	32
diff --git a/src/crypto/sha/asm/sha1-armv8.pl b/src/crypto/sha/asm/sha1-armv8.pl
index a8c08c2..1c4fe4a 100644
--- a/src/crypto/sha/asm/sha1-armv8.pl
+++ b/src/crypto/sha/asm/sha1-armv8.pl
@@ -162,7 +162,7 @@ ___
 }
 
 $code.=<<___;
-#include "arm_arch.h"
+#include <openssl/arm_arch.h>
 
 .text
 
diff --git a/src/crypto/sha/asm/sha256-586.pl b/src/crypto/sha/asm/sha256-586.pl
index 6462e45..e907714 100644
--- a/src/crypto/sha/asm/sha256-586.pl
+++ b/src/crypto/sha/asm/sha256-586.pl
@@ -10,7 +10,7 @@
 # SHA256 block transform for x86. September 2007.
 #
 # Performance improvement over compiler generated code varies from
-# 10% to 40% [see below]. Not very impressive on some µ-archs, but
+# 10% to 40% [see below]. Not very impressive on some µ-archs, but
 # it's 5 times smaller and optimizies amount of writes.
 #
 # May 2012.
diff --git a/src/crypto/sha/asm/sha256-armv4.pl b/src/crypto/sha/asm/sha256-armv4.pl
index df71676..7e07147 100644
--- a/src/crypto/sha/asm/sha256-armv4.pl
+++ b/src/crypto/sha/asm/sha256-armv4.pl
@@ -168,7 +168,7 @@ ___
 
 $code=<<___;
 #ifndef __KERNEL__
-# include "arm_arch.h"
+# include <openssl/arm_arch.h>
 #else
 # define __ARM_ARCH__ __LINUX_ARM_ARCH__
 # define __ARM_MAX_ARCH__ 7
diff --git a/src/crypto/sha/asm/sha512-586.pl b/src/crypto/sha/asm/sha512-586.pl
index e96ec00..2f6a202 100644
--- a/src/crypto/sha/asm/sha512-586.pl
+++ b/src/crypto/sha/asm/sha512-586.pl
@@ -37,7 +37,7 @@
 #
 # IALU code-path is optimized for elder Pentiums. On vanilla Pentium
 # performance improvement over compiler generated code reaches ~60%,
-# while on PIII - ~35%. On newer µ-archs improvement varies from 15%
+# while on PIII - ~35%. On newer µ-archs improvement varies from 15%
 # to 50%, but it's less important as they are expected to execute SSE2
 # code-path, which is commonly ~2-3x faster [than compiler generated
 # code]. SSE2 code-path is as fast as original sha512-sse2.pl, even
diff --git a/src/crypto/sha/asm/sha512-armv4.pl b/src/crypto/sha/asm/sha512-armv4.pl
index 2964a39..cd3662a 100644
--- a/src/crypto/sha/asm/sha512-armv4.pl
+++ b/src/crypto/sha/asm/sha512-armv4.pl
@@ -191,7 +191,7 @@ ___
 }
 $code=<<___;
 #ifndef __KERNEL__
-# include "arm_arch.h"
+# include <openssl/arm_arch.h>
 # define VFP_ABI_PUSH	vstmdb	sp!,{d8-d15}
 # define VFP_ABI_POP	vldmia	sp!,{d8-d15}
 #else
diff --git a/src/crypto/sha/asm/sha512-armv8.pl b/src/crypto/sha/asm/sha512-armv8.pl
index 43e7293..40eb17a 100644
--- a/src/crypto/sha/asm/sha512-armv8.pl
+++ b/src/crypto/sha/asm/sha512-armv8.pl
@@ -164,7 +164,7 @@ ___
 }
 
 $code.=<<___;
-#include "arm_arch.h"
+#include <openssl/arm_arch.h>
 
 .text