Merging r345826:

------------------------------------------------------------------------
r345826 | erichkeane | 2018-11-01 05:50:37 -0700 (Thu, 01 Nov 2018) | 15 lines

CPU-Dispatch-- Fix conflict between 'generic' and 'pentium'

When a dispatch function was being emitted that had both a generic and a
pentium configuration listed, we would assert.  This is because neither
configuration has any 'features' associated with it so they were both
considered the 'default' version.  'pentium' lacks any features because
we implement it in terms of __builtin_cpu_supports (instead of Intel
proprietary checks), which is unable to decern between the two.

The fix for this is to omit the 'generic' version from the dispatcher if
both are present. This permits existing code to compile, and still will
choose the 'best' version available (since 'pentium' is technically
better than 'generic').

Change-Id: I4b69f3e0344e74cbdbb04497845d5895dd05fda0
------------------------------------------------------------------------

2 files changed, 25 insertions, 0 deletions

diff --git a/clang/lib/CodeGen/CodeGenModule.cpp b/clang/lib/CodeGen/CodeGenModule.cpp
index 2654247b959..448a8b298e8 100644
--- a/clang/lib/CodeGen/CodeGenModule.cpp
+++ b/clang/lib/CodeGen/CodeGenModule.cpp
@@ -2505,6 +2505,22 @@ void CodeGenModule::emitCPUDispatchDefinition(GlobalDecl GD) {
         return CodeGenFunction::GetX86CpuSupportsMask(LHS.Conditions.Features) >
                CodeGenFunction::GetX86CpuSupportsMask(RHS.Conditions.Features);
       });
+
+  // If the list contains multiple 'default' versions, such as when it contains
+  // 'pentium' and 'generic', don't emit the call to the generic one (since we
+  // always run on at least a 'pentium'). We do this by deleting the 'least
+  // advanced' (read, lowest mangling letter).
+  while (Options.size() > 1 &&
+         CodeGenFunction::GetX86CpuSupportsMask(
+             (Options.end() - 2)->Conditions.Features) == 0) {
+    StringRef LHSName = (Options.end() - 2)->Function->getName();
+    StringRef RHSName = (Options.end() - 1)->Function->getName();
+    if (LHSName.compare(RHSName) < 0)
+      Options.erase(Options.end() - 2);
+    else
+      Options.erase(Options.end() - 1);
+  }
+
   CodeGenFunction CGF(*this);
   CGF.EmitMultiVersionResolver(ResolverFunc, Options);
 }
diff --git a/clang/test/CodeGen/attr-cpuspecific.c b/clang/test/CodeGen/attr-cpuspecific.c
index 1b98b5dc967..6005456f0b2 100644
--- a/clang/test/CodeGen/attr-cpuspecific.c
+++ b/clang/test/CodeGen/attr-cpuspecific.c
@@ -96,6 +96,15 @@ void HasGeneric(void);
 // CHECK: ret void ()* @HasGeneric.A
 // CHECK-NOT: call void @llvm.trap
 
+__attribute__((cpu_dispatch(atom, generic, pentium)))
+int GenericAndPentium(int i, double d);
+// CHECK: define i32 (i32, double)* @GenericAndPentium.resolver()
+// CHECK: call void @__cpu_indicator_init
+// CHECK: ret i32 (i32, double)* @GenericAndPentium.O
+// CHECK: ret i32 (i32, double)* @GenericAndPentium.B
+// CHECK-NOT: ret i32 (i32, double)* @GenericAndPentium.A
+// CHECK-NOT: call void @llvm.trap
+
 // CHECK: attributes #[[S]] = {{.*}}"target-features"="+avx,+cmov,+f16c,+mmx,+popcnt,+sse,+sse2,+sse3,+sse4.1,+sse4.2,+ssse3,+x87,+xsave"
 // CHECK: attributes #[[K]] = {{.*}}"target-features"="+adx,+avx,+avx2,+avx512cd,+avx512er,+avx512f,+avx512pf,+bmi,+cmov,+f16c,+fma,+lzcnt,+mmx,+movbe,+popcnt,+sse,+sse2,+sse3,+sse4.1,+sse4.2,+ssse3,+x87,+xsave"
 // CHECK: attributes #[[O]] = {{.*}}"target-features"="+cmov,+mmx,+movbe,+sse,+sse2,+sse3,+ssse3,+x87"