[XRay] support conditional return on PPC.

Summary: Conditional returns were not taken into consideration at all. Implement them by turning them into jumps and normal returns. This means there is a slightly higher performance penalty for conditional returns, but this is the best we can do, and it still disturbs little of the rest.

Reviewers: dberris, echristo

Subscribers: sanjoy, nemanjai, hiraditya, kbarton, llvm-commits

Differential Revision: https://reviews.llvm.org/D38102

llvm-svn: 314005

2 files changed, 111 insertions, 0 deletions

diff --git a/llvm/test/CodeGen/PowerPC/xray-conditional-return.ll b/llvm/test/CodeGen/PowerPC/xray-conditional-return.ll
new file mode 100644
index 00000000000..4454d3dc62a
--- /dev/null
+++ b/llvm/test/CodeGen/PowerPC/xray-conditional-return.ll
@@ -0,0 +1,79 @@
+; RUN: llc -filetype=asm -o - -mtriple=powerpc64le-unknown-linux-gnu < %s | FileCheck %s
+
+define void @Foo(i32 signext %a, i32 signext %b) #0 {
+; CHECK-LABEL: @Foo
+; CHECK:   cmpw [[CR:[0-9]+]]
+; CHECK-NEXT:   ble [[CR]], [[LABEL:\.[a-zA-Z0-9]+]]
+; CHECK-NEXT:   .p2align  3
+; CHECK-NEXT: {{\.[a-zA-Z0-9]+}}:
+; CHECK-NEXT:   blr
+; CHECK-NEXT:   nop
+; CHECK-NEXT:   std 0
+; CHECK-NEXT:   mflr 0
+; CHECK-NEXT:   bl __xray_FunctionExit
+; CHECK-NEXT:   nop
+; CHECK-NEXT:   mtlr 0
+; CHECK-NEXT:   blr
+; CHECK-NEXT: [[LABEL]]:
+entry:
+  %cmp = icmp sgt i32 %a, %b
+  br i1 %cmp, label %return, label %if.end
+
+; CHECK:      .p2align  3
+; CHECK-NEXT: {{\.[a-zA-Z0-9]+}}:
+; CHECK-NEXT:   blr
+; CHECK-NEXT:   nop
+; CHECK-NEXT:   std 0
+; CHECK-NEXT:   mflr 0
+; CHECK-NEXT:   bl __xray_FunctionExit
+; CHECK-NEXT:   nop
+; CHECK-NEXT:   mtlr 0
+; CHECK-NEXT:   blr
+if.end:
+  tail call void @Bar()
+  br label %return
+
+return:
+  ret void
+}
+
+define void @Foo2(i32 signext %a, i32 signext %b) #0 {
+; CHECK-LABEL: @Foo2
+; CHECK:   cmpw [[CR:[0-9]+]]
+; CHECK-NEXT:   bge [[CR]], [[LABEL:\.[a-zA-Z0-9]+]]
+; CHECK-NEXT:   .p2align  3
+; CHECK-NEXT: {{\.[a-zA-Z0-9]+}}:
+; CHECK-NEXT:   blr
+; CHECK-NEXT:   nop
+; CHECK-NEXT:   std 0
+; CHECK-NEXT:   mflr 0
+; CHECK-NEXT:   bl __xray_FunctionExit
+; CHECK-NEXT:   nop
+; CHECK-NEXT:   mtlr 0
+; CHECK-NEXT:   blr
+; CHECK-NEXT: [[LABEL]]:
+entry:
+  %cmp = icmp slt i32 %a, %b
+  br i1 %cmp, label %return, label %if.end
+
+; CHECK:      .p2align  3
+; CHECK-NEXT: {{\.[a-zA-Z0-9]+}}:
+; CHECK-NEXT:   blr
+; CHECK-NEXT:   nop
+; CHECK-NEXT:   std 0
+; CHECK-NEXT:   mflr 0
+; CHECK-NEXT:   bl __xray_FunctionExit
+; CHECK-NEXT:   nop
+; CHECK-NEXT:   mtlr 0
+; CHECK-NEXT:   blr
+if.end:
+  tail call void @Bar()
+  br label %return
+
+return:
+  ret void
+}
+
+declare void @Bar()
+
+attributes #0 = { "function-instrument"="xray-always" }
diff --git a/llvm/test/CodeGen/PowerPC/xray-ret-is-terminator.ll b/llvm/test/CodeGen/PowerPC/xray-ret-is-terminator.ll
new file mode 100644
index 00000000000..7e63530912a
--- /dev/null
+++ b/llvm/test/CodeGen/PowerPC/xray-ret-is-terminator.ll
@@ -0,0 +1,32 @@
+; RUN: llc -o - -mtriple=powerpc64le-unknown-linux-gnu < %s | FileCheck %s
+
+define void @ILLBeBack() #0 {
+; CHECK-LABEL @ILLBeBack
+; CHECK: beq {{[0-9]+}}, [[LABEL:\.[a-zA-Z0-9_]+]]
+; CHECK: bl __xray_FunctionExit
+; CHECK: [[LABEL]]:
+bb:
+  br i1 undef, label %bb1, label %bb8
+
+bb1:
+  %tmp = tail call i64 asm sideeffect "", "=&r,=*m,b,r,*m,~{cc}"(i64* nonnull undef, i64* nonnull undef, i64 1, i64* nonnull undef)
+  %tmp2 = icmp eq i64 %tmp, 0
+  br i1 %tmp2, label %bb3, label %bb8
+
+bb3:
+  %tmp4 = tail call i64 asm sideeffect "", "=&r,=*m,b,r,r,*m,~{cc}"(i64* undef, i64* undef, i64 0, i64 undef, i64* undef)
+  %tmp5 = icmp eq i64 0, %tmp4
+  br i1 %tmp5, label %bb6, label %bb3
+
+bb6:
+  br i1 undef, label %bb7, label %bb8
+
+bb7:
+  tail call void () undef()
+  ret void
+
+bb8:
+  ret void
+}
+
+attributes #0 = { "function-instrument"="xray-always" }