Add x86_64 compute levels as additional system types

When performing distributed builds of machine learning packages, it
would be nice if builders without the required SIMD instructions can
be excluded as build nodes.

Since x86_64 has accumulated a large number of different instruction
set extensions, listing all possible extensions would be unwieldy.
AMD, Intel, Red Hat, and SUSE have recently defined four different
microarchitecture levels that are now part of the x86-64 psABI
supplement and will be used in glibc 2.33:

https://gitlab.com/x86-psABIs/x86-64-ABI
https://lwn.net/Articles/844831/

This change uses libcpuid to detect CPU features and then uses them to
add the supported x86_64 levels to the additional system types. For
example on a Ryzen 3700X:

$ ~/aps/bin/nix -vv --version | grep "Additional system"
Additional system types: i686-linux, x86_64-v1-linux, x86_64-v2-linux, x86_64-v3-linux

9 files changed, 126 insertions, 11 deletions

diff --git a/Makefile.config.in b/Makefile.config.in
index d1e59e4e7..9d0500e48 100644
--- a/Makefile.config.in
+++ b/Makefile.config.in
@@ -9,6 +9,7 @@ CXXFLAGS = @CXXFLAGS@
 EDITLINE_LIBS = @EDITLINE_LIBS@
 ENABLE_S3 = @ENABLE_S3@
 GTEST_LIBS = @GTEST_LIBS@
+HAVE_LIBCPUID = @HAVE_LIBCPUID@
 HAVE_SECCOMP = @HAVE_SECCOMP@
 LDFLAGS = @LDFLAGS@
 LIBARCHIVE_LIBS = @LIBARCHIVE_LIBS@
diff --git a/configure.ac b/configure.ac
index 2047ed8d2..a24287ff6 100644
--- a/configure.ac
+++ b/configure.ac
@@ -218,6 +218,14 @@ LDFLAGS="-lz $LDFLAGS"
 # Look for libbrotli{enc,dec}.
 PKG_CHECK_MODULES([LIBBROTLI], [libbrotlienc libbrotlidec], [CXXFLAGS="$LIBBROTLI_CFLAGS $CXXFLAGS"])
 
+# Look for libcpuid.
+if test "$machine_name" = "x86_64"; then
+  PKG_CHECK_MODULES([LIBCPUID], [libcpuid], [CXXFLAGS="$LIBCPUID_CFLAGS $CXXFLAGS"])
+  have_libcpuid=1
+  AC_DEFINE([HAVE_LIBCPUID], [1], [Use libcpuid])
+fi
+AC_SUBST(HAVE_LIBCPUID, [$have_libcpuid])
+
 
 # Look for libseccomp, required for Linux sandboxing.
 if test "$sys_name" = linux; then
diff --git a/flake.nix b/flake.nix
index 8c60934e6..3ad7cca97 100644
--- a/flake.nix
+++ b/flake.nix
@@ -91,7 +91,8 @@
             gmock
           ]
           ++ lib.optionals stdenv.isLinux [libseccomp utillinuxMinimal]
-          ++ lib.optional (stdenv.isLinux || stdenv.isDarwin) libsodium;
+          ++ lib.optional (stdenv.isLinux || stdenv.isDarwin) libsodium
+          ++ lib.optional stdenv.isx86_64 libcpuid;
 
         awsDeps = lib.optional (stdenv.isLinux || stdenv.isDarwin)
           (aws-sdk-cpp.override {
diff --git a/src/libstore/globals.cc b/src/libstore/globals.cc
index 0531aad9f..df07aee9b 100644
--- a/src/libstore/globals.cc
+++ b/src/libstore/globals.cc
@@ -3,6 +3,7 @@
 #include "archive.hh"
 #include "args.hh"
 #include "abstract-setting-to-json.hh"
+#include "compute-levels.hh"
 
 #include <algorithm>
 #include <map>
@@ -133,24 +134,29 @@ StringSet Settings::getDefaultSystemFeatures()
 
 StringSet Settings::getDefaultExtraPlatforms()
 {
+    StringSet extraPlatforms;
+
     if (std::string{SYSTEM} == "x86_64-linux" && !isWSL1())
-        return StringSet{"i686-linux"};
-#if __APPLE__
+        extraPlatforms.insert("i686-linux");
+
+#if __linux__
+    StringSet levels = computeLevels();
+    for (auto iter = levels.begin(); iter != levels.end(); ++iter)
+        extraPlatforms.insert(*iter + "-linux");
+#elif __APPLE__
     // Rosetta 2 emulation layer can run x86_64 binaries on aarch64
     // machines. Note that we can’t force processes from executing
     // x86_64 in aarch64 environments or vice versa since they can
     // always exec with their own binary preferences.
-    else if (pathExists("/Library/Apple/System/Library/LaunchDaemons/com.apple.oahd.plist")) {
+    if (pathExists("/Library/Apple/System/Library/LaunchDaemons/com.apple.oahd.plist")) {
         if (std::string{SYSTEM} == "x86_64-darwin")
-            return StringSet{"aarch64-darwin"};
+            extraPlatforms.insert("aarch64-darwin");
         else if (std::string{SYSTEM} == "aarch64-darwin")
-            return StringSet{"x86_64-darwin"};
-        else
-            return StringSet{};
+            extraPlatforms.insert("x86_64-darwin");
     }
 #endif
-    else
-        return StringSet{};
+
+    return extraPlatforms;
 }
 
 bool Settings::isExperimentalFeatureEnabled(const std::string & name)
diff --git a/src/libutil/compute-levels.cc b/src/libutil/compute-levels.cc
new file mode 100644
index 000000000..19eaedfa8
--- /dev/null
+++ b/src/libutil/compute-levels.cc
@@ -0,0 +1,80 @@
+#include "types.hh"
+
+#if HAVE_LIBCPUID
+#include <libcpuid/libcpuid.h>
+#endif
+
+namespace nix {
+
+#if HAVE_LIBCPUID
+
+StringSet computeLevels() {
+    StringSet levels;
+
+    if (!cpuid_present())
+        return levels;
+
+    cpu_raw_data_t raw;
+    cpu_id_t data;
+
+    if (cpuid_get_raw_data(&raw) < 0)
+        return levels;
+
+    if (cpu_identify(&raw, &data) < 0)
+        return levels;
+
+    if (!(data.flags[CPU_FEATURE_CMOV] &&
+            data.flags[CPU_FEATURE_CX8] &&
+            data.flags[CPU_FEATURE_FPU] &&
+            data.flags[CPU_FEATURE_FXSR] &&
+            data.flags[CPU_FEATURE_MMX] &&
+            data.flags[CPU_FEATURE_SSE] &&
+            data.flags[CPU_FEATURE_SSE2]))
+        return levels;
+
+    levels.insert("x86_64-v1");
+
+    if (!(data.flags[CPU_FEATURE_CX16] &&
+            data.flags[CPU_FEATURE_LAHF_LM] &&
+            data.flags[CPU_FEATURE_POPCNT] &&
+            // SSE3
+            data.flags[CPU_FEATURE_PNI] &&
+            data.flags[CPU_FEATURE_SSSE3] &&
+            data.flags[CPU_FEATURE_SSE4_1] &&
+            data.flags[CPU_FEATURE_SSE4_2]))
+        return levels;
+
+    levels.insert("x86_64-v2");
+
+    if (!(data.flags[CPU_FEATURE_AVX] &&
+            data.flags[CPU_FEATURE_AVX2] &&
+            data.flags[CPU_FEATURE_F16C] &&
+            data.flags[CPU_FEATURE_FMA3] &&
+            // LZCNT
+            data.flags[CPU_FEATURE_ABM] &&
+            data.flags[CPU_FEATURE_MOVBE]))
+        return levels;
+
+    levels.insert("x86_64-v3");
+
+    if (!(data.flags[CPU_FEATURE_AVX512F] &&
+            data.flags[CPU_FEATURE_AVX512BW] &&
+            data.flags[CPU_FEATURE_AVX512CD] &&
+            data.flags[CPU_FEATURE_AVX512DQ] &&
+            data.flags[CPU_FEATURE_AVX512VL]))
+        return levels;
+
+    levels.insert("x86_64-v4");
+
+    return levels;
+}
+
+#else
+
+StringSet computeLevels() {
+    return StringSet{};
+}
+
+#endif // HAVE_LIBCPUID
+
+}
diff --git a/src/libutil/compute-levels.hh b/src/libutil/compute-levels.hh
new file mode 100644
index 000000000..8ded295f9
--- /dev/null
+++ b/src/libutil/compute-levels.hh
@@ -0,0 +1,7 @@
+#include "types.hh"
+
+namespace nix {
+
+StringSet computeLevels();
+
+}
diff --git a/src/libutil/local.mk b/src/libutil/local.mk
index ae7eb67ad..5341c58e6 100644
--- a/src/libutil/local.mk
+++ b/src/libutil/local.mk
@@ -7,3 +7,7 @@ libutil_DIR := $(d)
 libutil_SOURCES := $(wildcard $(d)/*.cc)
 
 libutil_LDFLAGS = $(LIBLZMA_LIBS) -lbz2 -pthread $(OPENSSL_LIBS) $(LIBBROTLI_LIBS) $(LIBARCHIVE_LIBS) $(BOOST_LDFLAGS) -lboost_context
+
+ifeq ($(HAVE_LIBCPUID), 1)
+	libutil_LDFLAGS += -lcpuid
+endif
diff --git a/tests/compute-levels.sh b/tests/compute-levels.sh
new file mode 100644
index 000000000..e4322dfa1
--- /dev/null
+++ b/tests/compute-levels.sh
@@ -0,0 +1,7 @@
+source common.sh
+
+if [[ $(uname -ms) = "Linux x86_64" ]]; then
+    # x86_64 CPUs must always support the baseline
+    # microarchitecture level.
+    nix -vv --version | grep -q "x86_64-v1-linux"
+fi
diff --git a/tests/local.mk b/tests/local.mk
index aa8b4f9bf..06be8cec1 100644
--- a/tests/local.mk
+++ b/tests/local.mk
@@ -38,7 +38,8 @@ nix_tests = \
   describe-stores.sh \
   flakes.sh \
   content-addressed.sh \
-  build.sh
+  build.sh \
+  compute-levels.sh
   # parallel.sh
   # build-remote-content-addressed-fixed.sh \