x86: Add avx2 optimized functions for the wchar_t strcpy family

Implemented:
    wcscat-avx2  (+ 744 bytes
    wcscpy-avx2  (+ 539 bytes)
    wcpcpy-avx2  (+ 577 bytes)
    wcsncpy-avx2 (+1108 bytes)
    wcpncpy-avx2 (+1214 bytes)
    wcsncat-avx2 (+1085 bytes)

Performance Changes:
    Times are from N = 10 runs of the benchmark suite and are reported
    as geometric mean of all ratios of New Implementation / Best Old
    Implementation. Best Old Implementation was determined with the
    highest ISA implementation.

    wcscat-avx2     -> 0.975
    wcscpy-avx2     -> 0.591
    wcpcpy-avx2     -> 0.698
    wcsncpy-avx2    -> 0.730
    wcpncpy-avx2    -> 0.711
    wcsncat-avx2    -> 0.954

Code Size Changes:
    This change  increase the size of libc.so by ~5.5kb bytes. For
    reference the patch optimizing the normal strcpy family functions
    decreases libc.so by ~5.2kb.

Full check passes on x86-64 and build succeeds for all ISA levels w/
and w/o multiarch.

16 files changed, 99 insertions, 8 deletions

diff --git a/sysdeps/x86_64/multiarch/Makefile b/sysdeps/x86_64/multiarch/Makefile
index d6e01940c3..e1e894c963 100644
--- a/sysdeps/x86_64/multiarch/Makefile
+++ b/sysdeps/x86_64/multiarch/Makefile
@@ -131,10 +131,13 @@ endif
 
 ifeq ($(subdir),wcsmbs)
 sysdep_routines += \
+  wcpcpy-avx2 \
   wcpcpy-evex \
   wcpcpy-generic \
+  wcpncpy-avx2 \
   wcpncpy-evex \
   wcpncpy-generic \
+  wcscat-avx2 \
   wcscat-evex \
   wcscat-generic \
   wcschr-avx2 \
@@ -146,6 +149,7 @@ sysdep_routines += \
   wcscmp-avx2-rtm \
   wcscmp-evex \
   wcscmp-sse2 \
+  wcscpy-avx2 \
   wcscpy-evex \
   wcscpy-generic \
   wcscpy-ssse3 \
@@ -155,11 +159,13 @@ sysdep_routines += \
   wcslen-evex512 \
   wcslen-sse2 \
   wcslen-sse4_1 \
+  wcsncat-avx2 \
   wcsncat-evex \
   wcsncat-generic \
   wcsncmp-avx2 \
   wcsncmp-avx2-rtm \
   wcsncmp-evex \
+  wcsncpy-avx2 \
   wcsncpy-evex \
   wcsncpy-generic \
   wcsnlen-avx2 \
diff --git a/sysdeps/x86_64/multiarch/ifunc-impl-list.c b/sysdeps/x86_64/multiarch/ifunc-impl-list.c
index c908d6c158..0c15dfebfd 100644
--- a/sysdeps/x86_64/multiarch/ifunc-impl-list.c
+++ b/sysdeps/x86_64/multiarch/ifunc-impl-list.c
@@ -907,6 +907,10 @@ __libc_ifunc_impl_list (const char *name, struct libc_ifunc_impl *array,
 				      && CPU_FEATURE_USABLE (BMI2)),
 				     __wcscpy_evex)
 	      X86_IFUNC_IMPL_ADD_V3 (array, i, wcscpy,
+				     (CPU_FEATURE_USABLE (AVX2)
+				      && CPU_FEATURE_USABLE (BMI2)),
+				     __wcscpy_avx2)
+	      X86_IFUNC_IMPL_ADD_V2 (array, i, wcscpy,
 				     CPU_FEATURE_USABLE (SSSE3),
 				     __wcscpy_ssse3)
 	      X86_IFUNC_IMPL_ADD_V1 (array, i, wcscpy,
@@ -920,7 +924,11 @@ __libc_ifunc_impl_list (const char *name, struct libc_ifunc_impl *array,
 				      && CPU_FEATURE_USABLE (AVX512BW)
 				      && CPU_FEATURE_USABLE (BMI2)),
 				     __wcsncpy_evex)
-	      X86_IFUNC_IMPL_ADD_V3 (array, i, wcpncpy,
+	      X86_IFUNC_IMPL_ADD_V3 (array, i, wcsncpy,
+				     (CPU_FEATURE_USABLE (AVX2)
+				      && CPU_FEATURE_USABLE (BMI2)),
+				     __wcsncpy_avx2)
+	      X86_IFUNC_IMPL_ADD_V2 (array, i, wcpncpy,
 				     1,
 				     __wcsncpy_generic))
 
@@ -932,6 +940,10 @@ __libc_ifunc_impl_list (const char *name, struct libc_ifunc_impl *array,
 				      && CPU_FEATURE_USABLE (BMI2)),
 				     __wcpcpy_evex)
 	      X86_IFUNC_IMPL_ADD_V3 (array, i, wcpcpy,
+				     (CPU_FEATURE_USABLE (AVX2)
+				      && CPU_FEATURE_USABLE (BMI2)),
+				     __wcpcpy_avx2)
+	      X86_IFUNC_IMPL_ADD_V2 (array, i, wcpcpy,
 				     1,
 				     __wcpcpy_generic))
 
@@ -942,7 +954,11 @@ __libc_ifunc_impl_list (const char *name, struct libc_ifunc_impl *array,
 				      && CPU_FEATURE_USABLE (AVX512BW)
 				      && CPU_FEATURE_USABLE (BMI2)),
 				     __wcpncpy_evex)
-	      X86_IFUNC_IMPL_ADD_V3 (array, i, wcsncpy,
+	      X86_IFUNC_IMPL_ADD_V3 (array, i, wcpncpy,
+				     (CPU_FEATURE_USABLE (AVX2)
+				      && CPU_FEATURE_USABLE (BMI2)),
+				     __wcpncpy_avx2)
+	      X86_IFUNC_IMPL_ADD_V2 (array, i, wcsncpy,
 				     1,
 				     __wcpncpy_generic))
 
@@ -954,6 +970,10 @@ __libc_ifunc_impl_list (const char *name, struct libc_ifunc_impl *array,
 				      && CPU_FEATURE_USABLE (BMI2)),
 				     __wcscat_evex)
 	      X86_IFUNC_IMPL_ADD_V3 (array, i, wcscat,
+				     (CPU_FEATURE_USABLE (AVX2)
+				      && CPU_FEATURE_USABLE (BMI2)),
+				     __wcscat_avx2)
+	      X86_IFUNC_IMPL_ADD_V2 (array, i, wcscat,
 				     1,
 				     __wcscat_generic))
 
@@ -965,6 +985,10 @@ __libc_ifunc_impl_list (const char *name, struct libc_ifunc_impl *array,
 				      && CPU_FEATURE_USABLE (BMI2)),
 				     __wcsncat_evex)
 	      X86_IFUNC_IMPL_ADD_V3 (array, i, wcsncat,
+				     (CPU_FEATURE_USABLE (AVX2)
+				      && CPU_FEATURE_USABLE (BMI2)),
+				     __wcsncat_avx2)
+	      X86_IFUNC_IMPL_ADD_V2 (array, i, wcsncat,
 				     1,
 				     __wcsncat_generic))
 
diff --git a/sysdeps/x86_64/multiarch/ifunc-wcs.h b/sysdeps/x86_64/multiarch/ifunc-wcs.h
index 1d2a63458b..51194e620e 100644
--- a/sysdeps/x86_64/multiarch/ifunc-wcs.h
+++ b/sysdeps/x86_64/multiarch/ifunc-wcs.h
@@ -27,6 +27,8 @@
 
 extern __typeof (REDIRECT_NAME) OPTIMIZE (evex) attribute_hidden;
 
+extern __typeof (REDIRECT_NAME) OPTIMIZE (avx2) attribute_hidden;
+
 extern __typeof (REDIRECT_NAME) OPTIMIZE (GENERIC) attribute_hidden;
 
 static inline void *
@@ -42,6 +44,11 @@ IFUNC_SELECTOR (void)
       if (X86_ISA_CPU_FEATURE_USABLE_P (cpu_features, AVX512VL)
 	  && X86_ISA_CPU_FEATURE_USABLE_P (cpu_features, AVX512BW))
 	return OPTIMIZE (evex);
+
+      if (X86_ISA_CPU_FEATURES_ARCH_P (cpu_features,
+				       Prefer_No_VZEROUPPER, !))
+	return OPTIMIZE (avx2);
+
     }
 
   return OPTIMIZE (GENERIC);
diff --git a/sysdeps/x86_64/multiarch/wcpcpy-avx2.S b/sysdeps/x86_64/multiarch/wcpcpy-avx2.S
new file mode 100644
index 0000000000..0fffd912d3
--- /dev/null
+++ b/sysdeps/x86_64/multiarch/wcpcpy-avx2.S
@@ -0,0 +1,8 @@
+#ifndef WCPCPY
+# define WCPCPY	__wcpcpy_avx2
+#endif
+
+#define USE_AS_STPCPY
+#define USE_AS_WCSCPY
+#define STRCPY	WCPCPY
+#include "strcpy-avx2.S"
diff --git a/sysdeps/x86_64/multiarch/wcpcpy-generic.c b/sysdeps/x86_64/multiarch/wcpcpy-generic.c
index 6039196a3e..0ba29b081f 100644
--- a/sysdeps/x86_64/multiarch/wcpcpy-generic.c
+++ b/sysdeps/x86_64/multiarch/wcpcpy-generic.c
@@ -19,7 +19,7 @@
 /* We always need to build this implementation as strspn-sse4 needs to
    be able to fallback to it.  */
 #include <isa-level.h>
-#if ISA_SHOULD_BUILD (3)
+#if ISA_SHOULD_BUILD (2)
 
 # define WCPCPY __wcpcpy_generic
 # include <wcsmbs/wcpcpy.c>
diff --git a/sysdeps/x86_64/multiarch/wcpncpy-avx2.S b/sysdeps/x86_64/multiarch/wcpncpy-avx2.S
new file mode 100644
index 0000000000..b7e594f7b7
--- /dev/null
+++ b/sysdeps/x86_64/multiarch/wcpncpy-avx2.S
@@ -0,0 +1,8 @@
+#ifndef WCPNCPY
+# define WCPNCPY	__wcpncpy_avx2
+#endif
+
+#define USE_AS_WCSCPY
+#define USE_AS_STPCPY
+#define STRNCPY	WCPNCPY
+#include "strncpy-avx2.S"
diff --git a/sysdeps/x86_64/multiarch/wcpncpy-generic.c b/sysdeps/x86_64/multiarch/wcpncpy-generic.c
index de8d34320e..4aab4ecdd2 100644
--- a/sysdeps/x86_64/multiarch/wcpncpy-generic.c
+++ b/sysdeps/x86_64/multiarch/wcpncpy-generic.c
@@ -19,7 +19,7 @@
 /* We always need to build this implementation as strspn-sse4 needs to
    be able to fallback to it.  */
 #include <isa-level.h>
-#if ISA_SHOULD_BUILD (3)
+#if ISA_SHOULD_BUILD (2)
 
 # define WCPNCPY __wcpncpy_generic
 # include <wcsmbs/wcpncpy.c>
diff --git a/sysdeps/x86_64/multiarch/wcscat-avx2.S b/sysdeps/x86_64/multiarch/wcscat-avx2.S
new file mode 100644
index 0000000000..a20f23c09d
--- /dev/null
+++ b/sysdeps/x86_64/multiarch/wcscat-avx2.S
@@ -0,0 +1,10 @@
+#ifndef WCSCAT
+# define WCSCAT	__wcscat_avx2
+#endif
+
+#define USE_AS_WCSCPY
+#define USE_AS_STRCAT
+
+#define STRCPY	WCSCAT
+
+#include "strcpy-avx2.S"
diff --git a/sysdeps/x86_64/multiarch/wcscat-generic.c b/sysdeps/x86_64/multiarch/wcscat-generic.c
index d86b4d5c00..6476f85bbb 100644
--- a/sysdeps/x86_64/multiarch/wcscat-generic.c
+++ b/sysdeps/x86_64/multiarch/wcscat-generic.c
@@ -19,7 +19,7 @@
 /* We always need to build this implementation as strspn-sse4 needs to
    be able to fallback to it.  */
 #include <isa-level.h>
-#if ISA_SHOULD_BUILD (3)
+#if ISA_SHOULD_BUILD (2)
 
 # define WCSCAT __wcscat_generic
 # include <wcsmbs/wcscat.c>
diff --git a/sysdeps/x86_64/multiarch/wcscpy-avx2.S b/sysdeps/x86_64/multiarch/wcscpy-avx2.S
new file mode 100644
index 0000000000..6bc509da07
--- /dev/null
+++ b/sysdeps/x86_64/multiarch/wcscpy-avx2.S
@@ -0,0 +1,7 @@
+#ifndef WCSCPY
+# define WCSCPY	__wcscpy_avx2
+#endif
+
+#define USE_AS_WCSCPY
+#define STRCPY	WCSCPY
+#include "strcpy-avx2.S"
diff --git a/sysdeps/x86_64/multiarch/wcscpy-generic.c b/sysdeps/x86_64/multiarch/wcscpy-generic.c
index 4a1fffae4b..600d606c45 100644
--- a/sysdeps/x86_64/multiarch/wcscpy-generic.c
+++ b/sysdeps/x86_64/multiarch/wcscpy-generic.c
@@ -18,7 +18,7 @@
 
 
 #include <isa-level.h>
-#if ISA_SHOULD_BUILD (3)
+#if ISA_SHOULD_BUILD (2)
 
 # define WCSCPY  __wcscpy_generic
 # include <wcsmbs/wcscpy.c>
diff --git a/sysdeps/x86_64/multiarch/wcscpy.c b/sysdeps/x86_64/multiarch/wcscpy.c
index 9ad77da8ac..e204059873 100644
--- a/sysdeps/x86_64/multiarch/wcscpy.c
+++ b/sysdeps/x86_64/multiarch/wcscpy.c
@@ -28,6 +28,8 @@
 
 extern __typeof (REDIRECT_NAME) OPTIMIZE (evex) attribute_hidden;
 
+extern __typeof (REDIRECT_NAME) OPTIMIZE (avx2) attribute_hidden;
+
 extern __typeof (REDIRECT_NAME) OPTIMIZE (ssse3) attribute_hidden;
 
 extern __typeof (REDIRECT_NAME) OPTIMIZE (generic) attribute_hidden;
@@ -44,6 +46,9 @@ IFUNC_SELECTOR (void)
       if (X86_ISA_CPU_FEATURE_USABLE_P (cpu_features, AVX512VL)
 	  && X86_ISA_CPU_FEATURE_USABLE_P (cpu_features, AVX512BW))
 	return OPTIMIZE (evex);
+
+      if (X86_ISA_CPU_FEATURES_ARCH_P (cpu_features, Prefer_No_VZEROUPPER, !))
+	return OPTIMIZE (avx2);
     }
 
   if (X86_ISA_CPU_FEATURE_USABLE_P (cpu_features, SSSE3))
diff --git a/sysdeps/x86_64/multiarch/wcsncat-avx2.S b/sysdeps/x86_64/multiarch/wcsncat-avx2.S
new file mode 100644
index 0000000000..a72105b7e9
--- /dev/null
+++ b/sysdeps/x86_64/multiarch/wcsncat-avx2.S
@@ -0,0 +1,9 @@
+#ifndef WCSNCAT
+# define WCSNCAT	__wcsncat_avx2
+#endif
+
+#define USE_AS_WCSCPY
+#define USE_AS_STRCAT
+
+#define STRNCAT	WCSNCAT
+#include "strncat-avx2.S"
diff --git a/sysdeps/x86_64/multiarch/wcsncat-generic.c b/sysdeps/x86_64/multiarch/wcsncat-generic.c
index 4b55cb40bc..9ced02b35e 100644
--- a/sysdeps/x86_64/multiarch/wcsncat-generic.c
+++ b/sysdeps/x86_64/multiarch/wcsncat-generic.c
@@ -19,7 +19,7 @@
 /* We always need to build this implementation as strspn-sse4 needs to
    be able to fallback to it.  */
 #include <isa-level.h>
-#if ISA_SHOULD_BUILD (3)
+#if ISA_SHOULD_BUILD (2)
 
 # define WCSNCAT __wcsncat_generic
 # include <wcsmbs/wcsncat.c>
diff --git a/sysdeps/x86_64/multiarch/wcsncpy-avx2.S b/sysdeps/x86_64/multiarch/wcsncpy-avx2.S
new file mode 100644
index 0000000000..3a1a8a372c
--- /dev/null
+++ b/sysdeps/x86_64/multiarch/wcsncpy-avx2.S
@@ -0,0 +1,7 @@
+#ifndef WCSNCPY
+# define WCSNCPY	__wcsncpy_avx2
+#endif
+
+#define USE_AS_WCSCPY
+#define STRNCPY	WCSNCPY
+#include "strncpy-avx2.S"
diff --git a/sysdeps/x86_64/multiarch/wcsncpy-generic.c b/sysdeps/x86_64/multiarch/wcsncpy-generic.c
index d0e8a86605..693521713b 100644
--- a/sysdeps/x86_64/multiarch/wcsncpy-generic.c
+++ b/sysdeps/x86_64/multiarch/wcsncpy-generic.c
@@ -19,7 +19,7 @@
 /* We always need to build this implementation as strspn-sse4 needs to
    be able to fallback to it.  */
 #include <isa-level.h>
-#if ISA_SHOULD_BUILD (3)
+#if ISA_SHOULD_BUILD (2)
 
 # define WCSNCPY __wcsncpy_generic
 # include <wcsmbs/wcsncpy.c>