[FuncSpec] Fix missed opportunities for function specialisation

[chill]

Summary

When collecting the possible constant arguments to
specialise a function the compiler will abandon the search
on the first argument that is for some reason unsuitable as
a specialisation constant. Thus, depending on the traversal
order of the functions and call sites, the compiler can end
up with a different set of possible constants, hence with
different set of specialisations.

With this patch, the compiler will skip unsuitable
constants, but nevertheless will continue searching for
more.

[ChuanqiXu]

LGTM. Thanks!

llvm/lib/Transforms/IPO/FunctionSpecialization.cpp

for (User *U : F->users()) {
 
       // If the parent of the call site will never be executed, we don't need
       // to worry about the passed value.
       if (!Solver.isBlockExecutable(CS.getParent()))
         continue;
 
       auto *V = CS.getArgOperand(A->getArgNo());
       if (isa<PoisonValue>(V))
-        return;
+        continue;
 
       // TrackValueOfGlobalVariable only tracks scalar global variables.
       if (auto *GV = dyn_cast<GlobalVariable>(V)) {
         // Check if we want to specialize on the address of non-constant
         // global values.
-        if (!GV->isConstant())
-          if (!SpecializeOnAddresses)
-            return;
+        if (!GV->isConstant() && !SpecializeOnAddresses)
+          continue;
 
         if (!GV->getValueType()->isSingleValueType())
-          return;
+          continue;
       }
 
       if (isa<Constant>(V) && (Solver.getLatticeValueFor(V).isConstant() ||
                                EnableSpecializationForLiteralConstant))
         Constants.push_back({&CS, cast<Constant>(V)});
     }
   }
 

llvm/test/Transforms/FunctionSpecialization/func-spec-get-possible-constants.ll

+; RUN: opt -S --passes=function-specialization < %s | FileCheck %s
+define dso_local i32 @p0(i32 noundef %x) {
+entry:
+  %add = add nsw i32 %x, 1
+  ret i32 %add
+}
+
+define dso_local i32 @p1(i32 noundef %x) {
+entry:
+  %sub = add nsw i32 %x, -1
+  ret i32 %sub
+}
+
+define dso_local i32 @g0(i32 noundef %x) {
+entry:
+  %call = tail call fastcc i32 @f(i32 noundef %x, ptr noundef nonnull @p0)
+  ret i32 %call
+}
+
+define internal fastcc i32 @f(i32 noundef %x, ptr nocapture noundef readonly %p) noinline  {
+entry:
+  %call = tail call i32 %p(i32 noundef %x)
+  %add = add nsw i32 %call, %x
+  ret i32 %add
+}
+
+define dso_local i32 @g1(i32 noundef %x) {
+entry:
+  %call = tail call fastcc i32 @f(i32 noundef %x, ptr noundef nonnull @p1)
+  ret i32 %call
+}
+
+define dso_local i32 @g2(i32 noundef %x) {
+entry:
+  %call = tail call fastcc i32 @f(i32 noundef %x, ptr poison)
+  ret i32 %call
+}
+
+; Check that a single argument, that cannot be used for specialisation, does not
+; prevent specialisation based on other arguments.
+; CHECK: @f.1
+; CHECK: @f.2