[PowerPC] fix a bug in TCO eligibility check

If the callee and caller use different calling convensions, we cannot apply TCO if the callee requires arguments on stack; e.g. C calling convention and Fast CC use the same registers for parameter passing, but the stack offset is not necessarily same.

This patch also recommit r319218 "[PowerPC] Allow tail calls of fastcc functions from C CallingConv functions." by @sfertile since the problem reported in r320106 should be fixed.

Differential Revision: https://reviews.llvm.org/D40893



git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@321579 91177308-0d34-0410-b5e6-96231b3b80d8

3 files changed, 41 insertions, 9 deletions

diff --git a/lib/Target/PowerPC/PPCISelLowering.cpp b/lib/Target/PowerPC/PPCISelLowering.cpp
index cea59de3e8a..f9de65fcb1d 100644
--- a/lib/Target/PowerPC/PPCISelLowering.cpp
+++ b/lib/Target/PowerPC/PPCISelLowering.cpp
@@ -4397,13 +4397,18 @@ hasSameArgumentList(const Function *CallerFn, ImmutableCallSite CS) {
 static bool
 areCallingConvEligibleForTCO_64SVR4(CallingConv::ID CallerCC,
                                     CallingConv::ID CalleeCC) {
-  // Tail or Sibling call optimization (TCO/SCO) needs callee and caller to
-  // have the same calling convention.
-  if (CallerCC != CalleeCC)
+  // Tail calls are possible with fastcc and ccc.
+  auto isTailCallableCC  = [] (CallingConv::ID CC){
+      return  CC == CallingConv::C || CC == CallingConv::Fast;
+  };
+  if (!isTailCallableCC(CallerCC) || !isTailCallableCC(CalleeCC))
     return false;
 
-  // Tail or Sibling calls can be done with fastcc/ccc.
-  return (CallerCC == CallingConv::Fast || CallerCC == CallingConv::C);
+  // We can safely tail call both fastcc and ccc callees from a c calling
+  // convention caller. If the caller is fastcc, we may have less stack space
+  // than a non-fastcc caller with the same signature so disable tail-calls in
+  // that case.
+  return CallerCC == CallingConv::C || CallerCC == CalleeCC;
 }
 
 bool
@@ -4434,10 +4439,28 @@ PPCTargetLowering::IsEligibleForTailCallOptimization_64SVR4(
   // Callee contains any byval parameter is not supported, too.
   // Note: This is a quick work around, because in some cases, e.g.
   // caller's stack size > callee's stack size, we are still able to apply
-  // sibling call optimization. See: https://reviews.llvm.org/D23441#513574
+  // sibling call optimization. For example, gcc is able to do SCO for caller1
+  // in the following example, but not for caller2.
+  //   struct test {
+  //     long int a;
+  //     char ary[56];
+  //   } gTest;
+  //   __attribute__((noinline)) int callee(struct test v, struct test *b) {
+  //     b->a = v.a;
+  //     return 0;
+  //   }
+  //   void caller1(struct test a, struct test c, struct test *b) {
+  //     callee(gTest, b); }
+  //   void caller2(struct test *b) { callee(gTest, b); }
   if (any_of(Outs, [](const ISD::OutputArg& OA) { return OA.Flags.isByVal(); }))
     return false;
 
+  // If callee and caller use different calling conventions, we cannot pass
+  // parameters on stack since offsets for the parameter area may be different.
+  if (Caller.getCallingConv() != CalleeCC &&
+      needStackSlotPassParameters(Subtarget, Outs))
+    return false;
+
   // No TCO/SCO on indirect call because Caller have to restore its TOC
   if (!isFunctionGlobalAddress(Callee) &&
       !isa<ExternalSymbolSDNode>(Callee))
diff --git a/test/CodeGen/PowerPC/duplicate-returns-for-tailcall.ll b/test/CodeGen/PowerPC/duplicate-returns-for-tailcall.ll
index 520efd8106f..9c0e77dafde 100644
--- a/test/CodeGen/PowerPC/duplicate-returns-for-tailcall.ll
+++ b/test/CodeGen/PowerPC/duplicate-returns-for-tailcall.ll
@@ -42,10 +42,10 @@ if.end4:                                          ; preds = %if.end
 if.then6:                                         ; preds = %if.end4
   %call7 = tail call fastcc signext i32 @call3(i32 signext %a, i32 signext %b, i32 signext %c)
   br label %return
-; No duplication here because the calling convention mismatch means we won't tail-call
+; tail calling a fastcc function from a ccc function is supported.
 ; CHECK_LABEL: if.then13:
-; CHECK:       tail call fastcc signext i32 @call3
-; CHECK-NEXT:  br
+; CHECK:       %[[T2:[a-zA-Z0-9]+]] = tail call fastcc signext i32 @call3
+; CHECK-NEXT:  ret i32 %[[T2]]
 
 return:                                           ; preds = %if.end4, %if.then6, %if.then2, %if.then
   %retval.0 = phi i32 [ %call, %if.then ], [ %call3, %if.then2 ], [ %call7, %if.then6 ], [ %c, %if.end4 ]
diff --git a/test/CodeGen/PowerPC/ppc64-sibcall.ll b/test/CodeGen/PowerPC/ppc64-sibcall.ll
index 3c08ecb5119..fc0e71f878c 100644
--- a/test/CodeGen/PowerPC/ppc64-sibcall.ll
+++ b/test/CodeGen/PowerPC/ppc64-sibcall.ll
@@ -41,6 +41,15 @@ define void @caller_64_64_copy([8 x i64] %a, [8 x i64] %b) #1 {
 ; CHECK-SCO: b callee_64_64_copy
 }
 
+define internal fastcc void @callee_64_64_copy_fastcc([8 x i64] %a, [8 x i64] %b) #0 { ret void }
+define void @caller_64_64_copy_ccc([8 x i64] %a, [8 x i64] %b) #1 {
+  tail call fastcc void @callee_64_64_copy_fastcc([8 x i64] %a, [8 x i64] %b)
+  ret void
+; If caller and callee use different calling convensions, we cannot apply TCO.
+; CHECK-SCO-LABEL: caller_64_64_copy_ccc:
+; CHECK-SCO: bl callee_64_64_copy_fastcc
+}
+
 define void @caller_64_64_reorder_copy([8 x i64] %a, [8 x i64] %b) #1 {
   tail call void @callee_64_64_copy([8 x i64] %b, [8 x i64] %a)
   ret void