[llvm] d441188 - [Support][X86] Change getHostNumPhsicalCores() to return number of physical cores enabled by affinity

[Fangrui Song via llvm-commits]

Author: Fangrui Song
Date: 2020-04-17T07:45:04-07:00
New Revision: d441188c15183c9496e44169966112304a1fc915

URL: https://github.com/llvm/llvm-project/commit/d441188c15183c9496e44169966112304a1fc915
DIFF: https://github.com/llvm/llvm-project/commit/d441188c15183c9496e44169966112304a1fc915.diff

LOG: [Support][X86] Change getHostNumPhsicalCores() to return number of physical cores enabled by affinity

Fixes https://bugs.llvm.org/show_bug.cgi?id=45556

While here, make the x86-64 code available for x86-32.

The output has been available and stable since
https://git.kernel.org/linus/3dd9d514846cdca1dcef2e4fce666d85e199e844 (2005)
```
processor:
...
physical id:
siblings:
core id:
```

Don't check HAVE_SCHED_GETAFFINITY/HAVE_CPU_COUNT. The interface is
simply available in every libc which can build LLVM.

Reviewed By: aganea

Differential Revision: https://reviews.llvm.org/D78324

Added: 
    

Modified: 
    llvm/lib/Support/Host.cpp

Removed: 
    


################################################################################
diff  --git a/llvm/lib/Support/Host.cpp b/llvm/lib/Support/Host.cpp
index f23645680648..43df31d0efea 100644
--- a/llvm/lib/Support/Host.cpp
+++ b/llvm/lib/Support/Host.cpp
@@ -1277,11 +1277,18 @@ StringRef sys::getHostCPUName() {
 StringRef sys::getHostCPUName() { return "generic"; }
 #endif
 
-#if defined(__linux__) && defined(__x86_64__)
+#if defined(__linux__) && (defined(__i386__) || defined(__x86_64__))
 // On Linux, the number of physical cores can be computed from /proc/cpuinfo,
 // using the number of unique physical/core id pairs. The following
 // implementation reads the /proc/cpuinfo format on an x86_64 system.
 int computeHostNumPhysicalCores() {
+  // Enabled represents the number of physical id/core id pairs with at least
+  // one processor id enabled by the CPU affinity mask.
+  cpu_set_t Affinity, Enabled;
+  if (sched_getaffinity(0, sizeof(Affinity), &Affinity) != 0)
+    return -1;
+  CPU_ZERO(&Enabled);
+
   // Read /proc/cpuinfo as a stream (until EOF reached). It cannot be
   // mmapped because it appears to have 0 size.
   llvm::ErrorOr<std::unique_ptr<llvm::MemoryBuffer>> Text =
@@ -1294,33 +1301,29 @@ int computeHostNumPhysicalCores() {
   SmallVector<StringRef, 8> strs;
   (*Text)->getBuffer().split(strs, "\n", /*MaxSplit=*/-1,
                              /*KeepEmpty=*/false);
+  int CurProcessor = -1;
   int CurPhysicalId = -1;
+  int CurSiblings = -1;
   int CurCoreId = -1;
-  SmallSet<std::pair<int, int>, 32> UniqueItems;
-  for (auto &Line : strs) {
-    Line = Line.trim();
-    if (!Line.startswith("physical id") && !Line.startswith("core id"))
-      continue;
+  for (StringRef Line : strs) {
     std::pair<StringRef, StringRef> Data = Line.split(':');
     auto Name = Data.first.trim();
     auto Val = Data.second.trim();
-    if (Name == "physical id") {
-      assert(CurPhysicalId == -1 &&
-             "Expected a core id before seeing another physical id");
+    // These fields are available if the kernel is configured with CONFIG_SMP.
+    if (Name == "processor")
+      Val.getAsInteger(10, CurProcessor);
+    else if (Name == "physical id")
       Val.getAsInteger(10, CurPhysicalId);
-    }
-    if (Name == "core id") {
-      assert(CurCoreId == -1 &&
-             "Expected a physical id before seeing another core id");
+    else if (Name == "siblings")
+      Val.getAsInteger(10, CurSiblings);
+    else if (Name == "core id") {
       Val.getAsInteger(10, CurCoreId);
-    }
-    if (CurPhysicalId != -1 && CurCoreId != -1) {
-      UniqueItems.insert(std::make_pair(CurPhysicalId, CurCoreId));
-      CurPhysicalId = -1;
-      CurCoreId = -1;
+      // The processor id corresponds to an index into cpu_set_t.
+      if (CPU_ISSET(CurProcessor, &Affinity))
+        CPU_SET(CurPhysicalId * CurSiblings + CurCoreId, &Enabled);
     }
   }
-  return UniqueItems.size();
+  return CPU_COUNT(&Enabled);
 }
 #elif defined(__APPLE__) && defined(__x86_64__)
 #include <sys/param.h>