x86: Add detection of the AES and SHA New Instructions

The AES instructions were first introduced with the Westmere shrink
(22nm) of the Nehalem architecture. The SHA instructions are still
pending on Intel architecture, but is available on AMD family 17h (gcc
argument -march=znver1).

Both features operate on SSE registers, so that's why the MSVC command-
line argument is the SSE2 one and the configure-time tests depend on
features.sse2.

The qmake feature names end in "ni" because "aes" and "sha" are too
simple and could clash with other uses. The QT_COMPILER_SUPPORTS_ macro
doesn't have the "NI" suffix because it has to match the GCC/Clang
predefined macro.

Change-Id: I445bb15619f6401494e8fffd149dbd1f862ff51c
Reviewed-by: Allan Sandfeld Jensen <allan.jensen@qt.io>

15 files changed, 150 insertions, 1 deletions

diff --git a/config.tests/common/aesni/aesni.cpp b/config.tests/common/aesni/aesni.cpp
new file mode 100644
index 0000000000..a177183c72
--- /dev/null
+++ b/config.tests/common/aesni/aesni.cpp
@@ -0,0 +1,49 @@
+/****************************************************************************
+**
+** Copyright (C) 2017 Intel Corporation.
+** Contact: https://www.qt.io/licensing/
+**
+** This file is part of the config.tests of the Qt Toolkit.
+**
+** $QT_BEGIN_LICENSE:LGPL$
+** Commercial License Usage
+** Licensees holding valid commercial Qt licenses may use this file in
+** accordance with the commercial license agreement provided with the
+** Software or, alternatively, in accordance with the terms contained in
+** a written agreement between you and The Qt Company. For licensing terms
+** and conditions see https://www.qt.io/terms-conditions. For further
+** information use the contact form at https://www.qt.io/contact-us.
+**
+** GNU Lesser General Public License Usage
+** Alternatively, this file may be used under the terms of the GNU Lesser
+** General Public License version 3 as published by the Free Software
+** Foundation and appearing in the file LICENSE.LGPL3 included in the
+** packaging of this file. Please review the following information to
+** ensure the GNU Lesser General Public License version 3 requirements
+** will be met: https://www.gnu.org/licenses/lgpl-3.0.html.
+**
+** GNU General Public License Usage
+** Alternatively, this file may be used under the terms of the GNU
+** General Public License version 2.0 or (at your option) the GNU General
+** Public license version 3 or any later version approved by the KDE Free
+** Qt Foundation. The licenses are as published by the Free Software
+** Foundation and appearing in the file LICENSE.GPL2 and LICENSE.GPL3
+** included in the packaging of this file. Please review the following
+** information to ensure the GNU General Public License requirements will
+** be met: https://www.gnu.org/licenses/gpl-2.0.html and
+** https://www.gnu.org/licenses/gpl-3.0.html.
+**
+** $QT_END_LICENSE$
+**
+****************************************************************************/
+
+#include <wmmintrin.h>
+
+int main(int, char**)
+{
+    __m128i a = _mm_setzero_si128();
+    __m128i b = _mm_aesenc_si128(a, a);
+    __m128i c = _mm_aesdec_si128(a, b);
+    (void)c;
+    return 0;
+}
diff --git a/config.tests/common/aesni/aesni.pro b/config.tests/common/aesni/aesni.pro
new file mode 100644
index 0000000000..49cb132ef7
--- /dev/null
+++ b/config.tests/common/aesni/aesni.pro
@@ -0,0 +1,3 @@
+SOURCES = aesni.cpp
+!defined(QMAKE_CFLAGS_AESNI, "var"): error("This compiler does not support AES New Instructions")
+else: QMAKE_CXXFLAGS += $$QMAKE_CFLAGS_AESNI
diff --git a/config.tests/common/shani/shani.cpp b/config.tests/common/shani/shani.cpp
new file mode 100644
index 0000000000..0fe6e87dd8
--- /dev/null
+++ b/config.tests/common/shani/shani.cpp
@@ -0,0 +1,50 @@
+/****************************************************************************
+**
+** Copyright (C) 2017 Intel Corporation.
+** Contact: https://www.qt.io/licensing/
+**
+** This file is part of the config.tests of the Qt Toolkit.
+**
+** $QT_BEGIN_LICENSE:LGPL$
+** Commercial License Usage
+** Licensees holding valid commercial Qt licenses may use this file in
+** accordance with the commercial license agreement provided with the
+** Software or, alternatively, in accordance with the terms contained in
+** a written agreement between you and The Qt Company. For licensing terms
+** and conditions see https://www.qt.io/terms-conditions. For further
+** information use the contact form at https://www.qt.io/contact-us.
+**
+** GNU Lesser General Public License Usage
+** Alternatively, this file may be used under the terms of the GNU Lesser
+** General Public License version 3 as published by the Free Software
+** Foundation and appearing in the file LICENSE.LGPL3 included in the
+** packaging of this file. Please review the following information to
+** ensure the GNU Lesser General Public License version 3 requirements
+** will be met: https://www.gnu.org/licenses/lgpl-3.0.html.
+**
+** GNU General Public License Usage
+** Alternatively, this file may be used under the terms of the GNU
+** General Public License version 2.0 or (at your option) the GNU General
+** Public license version 3 or any later version approved by the KDE Free
+** Qt Foundation. The licenses are as published by the Free Software
+** Foundation and appearing in the file LICENSE.GPL2 and LICENSE.GPL3
+** included in the packaging of this file. Please review the following
+** information to ensure the GNU General Public License requirements will
+** be met: https://www.gnu.org/licenses/gpl-2.0.html and
+** https://www.gnu.org/licenses/gpl-3.0.html.
+**
+** $QT_END_LICENSE$
+**
+****************************************************************************/
+
+#include <immintrin.h>
+
+int main(int, char**)
+{
+    __m128i a = _mm_setzero_si128();
+    __m128i b = _mm_sha1rnds4_epu32(a, a, 0);
+    __m128i c = _mm_sha1msg1_epu32(a, b);
+    __m128i d = _mm_sha256msg2_epu32(b, c);
+    (void)d;
+    return 0;
+}
diff --git a/config.tests/common/shani/shani.pro b/config.tests/common/shani/shani.pro
new file mode 100644
index 0000000000..278f49ef90
--- /dev/null
+++ b/config.tests/common/shani/shani.pro
@@ -0,0 +1,3 @@
+SOURCES = shani.cpp
+!defined(QMAKE_CFLAGS_SHANI, "var"): error("This compiler does not support Secure Hash Algorithm extensions")
+else: QMAKE_CXXFLAGS += $$QMAKE_CFLAGS_SHANI
diff --git a/configure.json b/configure.json
index 276bb095e5..6ccb1acdd9 100644
--- a/configure.json
+++ b/configure.json
@@ -317,11 +317,21 @@
             "type": "compile",
             "test": "common/sse4_2"
         },
+        "aesni": {
+            "label": "AES new instructions",
+            "type": "compile",
+            "test": "common/aesni"
+        },
         "f16c": {
             "label": "F16C instructions",
             "type": "compile",
             "test": "common/f16c"
         },
+        "shani": {
+            "label": "SHA new instructions",
+            "type": "compile",
+            "test": "common/shani"
+        },
         "avx": {
             "label": "AVX instructions",
             "type": "compile",
@@ -871,6 +881,22 @@
                 { "type": "define", "name": "QT_COMPILER_SUPPORTS_AVX512VBMI", "value": 1 }
             ]
         },
+        "aesni": {
+            "label": "aesni",
+            "condition": "features.sse2 && tests.aesni",
+            "output": [
+                "privateConfig",
+                { "type": "define", "name": "QT_COMPILER_SUPPORTS_AES", "value": 1 }
+            ]
+        },
+        "shani": {
+            "label": "shani",
+            "condition": "features.sse2 && tests.shani",
+            "output": [
+                "privateConfig",
+                { "type": "define", "name": "QT_COMPILER_SUPPORTS_SHA", "value": 1 }
+            ]
+        },
         "mips_dsp": {
             "label": "DSP",
             "condition": "arch.mips && tests.mips_dsp",
diff --git a/mkspecs/common/gcc-base.conf b/mkspecs/common/gcc-base.conf
index 9ddebae506..ca5697dd90 100644
--- a/mkspecs/common/gcc-base.conf
+++ b/mkspecs/common/gcc-base.conf
@@ -97,6 +97,8 @@ QMAKE_CFLAGS_AVX512BW  += -mavx512bw
 QMAKE_CFLAGS_AVX512VL  += -mavx512vl
 QMAKE_CFLAGS_AVX512IFMA += -mavx512ifma
 QMAKE_CFLAGS_AVX512VBMI += -mavx512vbmi
+QMAKE_CFLAGS_AESNI     += -maes
+QMAKE_CFLAGS_SHANI     += -msha
 QMAKE_CFLAGS_NEON      += -mfpu=neon
 QMAKE_CFLAGS_MIPS_DSP  += -mdsp
 QMAKE_CFLAGS_MIPS_DSPR2 += -mdspr2
diff --git a/mkspecs/common/msvc-desktop.conf b/mkspecs/common/msvc-desktop.conf
index 02b8441547..0ca27fe4ec 100644
--- a/mkspecs/common/msvc-desktop.conf
+++ b/mkspecs/common/msvc-desktop.conf
@@ -44,6 +44,8 @@ QMAKE_CFLAGS_SSE3       = $$QMAKE_CFLAGS_SSE2
 QMAKE_CFLAGS_SSSE3      = $$QMAKE_CFLAGS_SSE2
 QMAKE_CFLAGS_SSE4_1     = $$QMAKE_CFLAGS_SSE2
 QMAKE_CFLAGS_SSE4_2     = $$QMAKE_CFLAGS_SSE2
+QMAKE_CFLAGS_AESNI      = $$QMAKE_CFLAGS_SSE2
+QMAKE_CFLAGS_SHANI      = $$QMAKE_CFLAGS_SSE2
 
 QMAKE_CXX               = $$QMAKE_CC
 QMAKE_CXXFLAGS          = $$QMAKE_CFLAGS
diff --git a/mkspecs/common/qcc-base.conf b/mkspecs/common/qcc-base.conf
index 4ef03d8587..77e0476777 100644
--- a/mkspecs/common/qcc-base.conf
+++ b/mkspecs/common/qcc-base.conf
@@ -33,6 +33,8 @@ QMAKE_CFLAGS_SSE4_1    += -msse4.1
 QMAKE_CFLAGS_SSE4_2    += -msse4.2
 QMAKE_CFLAGS_AVX       += -mavx
 QMAKE_CFLAGS_AVX2      += -mavx2
+QMAKE_CFLAGS_AESNI     += -maes
+QMAKE_CFLAGS_SHANI     += -msha
 
 QMAKE_CXXFLAGS         += $$QMAKE_CFLAGS -lang-c++
 QMAKE_CXXFLAGS_DEPS    += $$QMAKE_CFLAGS_DEPS
diff --git a/mkspecs/common/winrt_winphone/qmake.conf b/mkspecs/common/winrt_winphone/qmake.conf
index 818264c46b..1b9bf4d20f 100644
--- a/mkspecs/common/winrt_winphone/qmake.conf
+++ b/mkspecs/common/winrt_winphone/qmake.conf
@@ -34,6 +34,8 @@ QMAKE_CFLAGS_SSE4_1     = -arch:SSE2
 QMAKE_CFLAGS_SSE4_2     = -arch:SSE2
 QMAKE_CFLAGS_AVX        = -arch:AVX
 QMAKE_CFLAGS_AVX2       = -arch:AVX
+QMAKE_CFLAGS_AESNI      = -arch:SSE2
+QMAKE_CFLAGS_SHANI      = -arch:SSE2
 
 QMAKE_CXX               = $$QMAKE_CC
 QMAKE_CXXFLAGS          = $$QMAKE_CFLAGS
diff --git a/mkspecs/features/simd.prf b/mkspecs/features/simd.prf
index 953fc52c65..aca9ae6243 100644
--- a/mkspecs/features/simd.prf
+++ b/mkspecs/features/simd.prf
@@ -93,6 +93,8 @@ addSimdCompiler(sse3)
 addSimdCompiler(ssse3)
 addSimdCompiler(sse4_1)
 addSimdCompiler(sse4_2)
+addSimdCompiler(aesni)
+addSimdCompiler(shani)
 addSimdCompiler(avx)
 addSimdCompiler(avx2)
 addSimdCompiler(avx512f)
diff --git a/mkspecs/linux-icc/qmake.conf b/mkspecs/linux-icc/qmake.conf
index 4822d2a0e0..bc753647ec 100644
--- a/mkspecs/linux-icc/qmake.conf
+++ b/mkspecs/linux-icc/qmake.conf
@@ -42,6 +42,8 @@ QMAKE_CFLAGS_AVX512PF  += -xMIC-AVX512
 QMAKE_CFLAGS_AVX512DQ  += -xCORE-AVX512
 QMAKE_CFLAGS_AVX512BW  += -xCORE-AVX512
 QMAKE_CFLAGS_AVX512VL  += -xCORE-AVX512
+QMAKE_CFLAGS_AESNI     += -maes
+QMAKE_CFLAGS_SHANI     += -msha
 
 QMAKE_CXX               = icpc
 QMAKE_CXXFLAGS          = $$QMAKE_CFLAGS
diff --git a/mkspecs/macx-icc/qmake.conf b/mkspecs/macx-icc/qmake.conf
index 533f9cd86d..210b281987 100644
--- a/mkspecs/macx-icc/qmake.conf
+++ b/mkspecs/macx-icc/qmake.conf
@@ -40,6 +40,8 @@ QMAKE_CFLAGS_AVX512PF  += -xMIC-AVX512
 QMAKE_CFLAGS_AVX512DQ  += -xCORE-AVX512
 QMAKE_CFLAGS_AVX512BW  += -xCORE-AVX512
 QMAKE_CFLAGS_AVX512VL  += -xCORE-AVX512
+QMAKE_CFLAGS_AESNI     += -maes
+QMAKE_CFLAGS_SHANI     += -msha
 
 QMAKE_CXX               = icpc
 QMAKE_CXXFLAGS          = $$QMAKE_CFLAGS
diff --git a/mkspecs/win32-g++/qmake.conf b/mkspecs/win32-g++/qmake.conf
index d6b08f5323..5f98bd1d03 100644
--- a/mkspecs/win32-g++/qmake.conf
+++ b/mkspecs/win32-g++/qmake.conf
@@ -28,6 +28,8 @@ QMAKE_YACCFLAGS         = -d
 QMAKE_CFLAGS           += -fno-keep-inline-dllexport
 QMAKE_CFLAGS_WARN_ON   += -Wextra
 QMAKE_CFLAGS_SSE2      += -mstackrealign
+QMAKE_CFLAGS_AESNI      = -maes
+QMAKE_CFLAGS_SHANI      = -msha
 
 QMAKE_CXX               = $${CROSS_COMPILE}g++
 QMAKE_CXXFLAGS_THREAD   = $$QMAKE_CFLAGS_THREAD
diff --git a/mkspecs/win32-icc/qmake.conf b/mkspecs/win32-icc/qmake.conf
index 6e2589b4c4..9a86407043 100644
--- a/mkspecs/win32-icc/qmake.conf
+++ b/mkspecs/win32-icc/qmake.conf
@@ -33,6 +33,8 @@ QMAKE_CFLAGS_AVX512PF  += -QxMIC-AVX512
 QMAKE_CFLAGS_AVX512DQ  += -QxCORE-AVX512
 QMAKE_CFLAGS_AVX512BW  += -QxCORE-AVX512
 QMAKE_CFLAGS_AVX512VL  += -QxCORE-AVX512
+QMAKE_CFLAGS_AESNI      = -QxSSE2
+QMAKE_CFLAGS_SHANI      = -QxSSE4.2
 
 QMAKE_CXX               = $$QMAKE_CC
 QMAKE_CXXFLAGS          = $$QMAKE_CFLAGS /Zc:forScope
diff --git a/src/corelib/tools/qsimd_p.h b/src/corelib/tools/qsimd_p.h
index f6164e2297..59a8dd9d0c 100644
--- a/src/corelib/tools/qsimd_p.h
+++ b/src/corelib/tools/qsimd_p.h
@@ -261,7 +261,7 @@
 #  endif
 #endif
 
-#if defined(__AES__) || defined(__PCLMUL__)
+#if defined(__AES__) || defined(__PCLMUL__) || (defined(QT_COMPILER_SUPPORTS_AES) && defined(QT_COMPILER_SUPPORTS_SIMD_ALWAYS))
 #  include <wmmintrin.h>
 #endif