[Core] Fix parallel_for for Linux

[jhenderson]

Summary

rL299635 exposed a latent bug in the Linux implementation of parallel_for, which resulted in it calling the function outside of the range requested, resulting later in a segmentation fault. This change fixes this issue and adds a unit test.

[ruiu]

LGTM. Wow, that seems like a dangerous bug. Thank you for finding and fixing!

[jhenderson]

Closed by rL299748 (I forgot to add the Differential Revision tag to the commit message...).

include/lld/Core/Parallel.h

 template <class IndexTy, class FuncTy>
 void parallel_for(IndexTy Begin, IndexTy End, FuncTy Fn) {
   ptrdiff_t TaskSize = (End - Begin) / 1024;
   if (TaskSize == 0)
     TaskSize = 1;
 
   TaskGroup Tg;
   IndexTy I = Begin;
-  for (; I < End; I += TaskSize) {
+  for (; I + TaskSize < End; I += TaskSize) {
     Tg.spawn([=, &Fn] {
       for (IndexTy J = I, E = I + TaskSize; J != E; ++J)
         Fn(J);
     });
-    Begin += TaskSize;
   }
   Tg.spawn([=, &Fn] {
     for (IndexTy J = I; J < End; ++J)
       Fn(J);
   });
 }
 #endif
 } // end namespace lld
 
 #endif // LLD_CORE_PARALLEL_H

unittests/CoreTests/ParallelTest.cpp

TEST(Parallel, sort) {
   std::uniform_int_distribution<uint32_t> dist;
 
   for (auto &i : array)
     i = dist(randEngine);
 
   lld::parallel_sort(std::begin(array), std::end(array));
   ASSERT_TRUE(std::is_sorted(std::begin(array), std::end(array)));
 }
+
+TEST(Parallel, parallel_for) {
+  // We need to test the case with a TaskSize > 1. We are white-box testing
+  // here. The TaskSize is calculated as (End - Begin) / 1024 at the time of
+  // writing.
+  uint32_t range[2050];
+  std::fill(range, range + 2050, 1);
+  lld::parallel_for(0, 2049, [&range](size_t I) { ++range[I]; });
+
+  uint32_t expected[2049];
+  std::fill(expected, expected + 2049, 2);
+  ASSERT_TRUE(std::equal(range, range + 2049, expected));
+  // Check that we don't write past the end of the requested range.
+  ASSERT_EQ(range[2049], 1);
+}