[SystemZ] Add proper mcount handling

When compiling with `-pg`, the `EntryExitInstrumenterPass` will insert calls
to the glibc function `mcount` at the begining of each `MachineFunction`.

On SystemZ, these calls require special handling:

- The call to `mcount` needs to happen at the beginning of the prologue.
- Prior to the call to `mcount`, register `%r14`, the return address of the
  callee function, must be stored 8 bytes above the stack pointer `%r15`.
  After the call to `mcount` returns, that register needs to be restored.

This commit adds some special handling to the EntryExitInstrumenterPass that
keeps the insertion of the mcount function into the module, but skips over
insertion of the actual call in order to perform this insertion in the
`emitPrologue` function. There, a simple sequence of store/call/load is
inserted, which implements the above.

Author: dominik-steenken

llvm/lib/Target/SystemZ/SystemZFrameLowering.cpp

@@ -18,6 +18,7 @@
 #include "llvm/CodeGen/RegisterScavenging.h"
 #include "llvm/CodeGen/TargetLoweringObjectFileImpl.h"
 #include "llvm/IR/Function.h"
+#include "llvm/IR/Module.h"
 #include "llvm/Target/TargetMachine.h"
 
 using namespace llvm;
@@ -558,6 +559,33 @@ void SystemZELFFrameLowering::emitPrologue(MachineFunction &MF,
   // to determine the end of the prologue.
   DebugLoc DL;
 
+  // Add mcount instrumentation if necessary.
+  if (MF.getFunction()
+          .getFnAttribute("instrument-function-entry-inlined")
+          .getValueAsString() == "mcount") {
+
+    // Store return address 8 bytes above stack pointer.
+    BuildMI(MBB, MBBI, DL, ZII->get(SystemZ::STG))
+        .addReg(SystemZ::R14D)
+        .addReg(SystemZ::R15D)
+        .addImm(8)
+        .addReg(0);
+
+    // Call mcount (Regmask 0 to ensure this will not be moved by the
+    // scheduler.).
+    const uint32_t Mask = 0;
+    BuildMI(MBB, MBBI, DL, ZII->get(SystemZ::CallBRASL))
+        .addGlobalAddress(MF.getFunction().getParent()->getFunction("mcount"))
+        .addRegMask(&Mask);
+
+    // Reload return address drom 8 bytes above stack pointer.
+    BuildMI(MBB, MBBI, DL, ZII->get(SystemZ::LG))
+        .addReg(SystemZ::R14D)
+        .addReg(SystemZ::R15D)
+        .addImm(8)
+        .addReg(0);
+  }
+
   // The current offset of the stack pointer from the CFA.
   int64_t SPOffsetFromCFA = -SystemZMC::ELFCFAOffsetFromInitialSP;
 

llvm/lib/Transforms/Utils/EntryExitInstrumenter.cpp

@@ -22,7 +22,7 @@
 
 using namespace llvm;
 
-static void insertCall(Function &CurFn, StringRef Func,
+static bool insertCall(Function &CurFn, StringRef Func,
                        BasicBlock::iterator InsertionPt, DebugLoc DL) {
   Module &M = *InsertionPt->getParent()->getParent()->getParent();
   LLVMContext &C = InsertionPt->getParent()->getContext();
@@ -63,12 +63,17 @@ static void insertCall(Function &CurFn, StringRef Func,
                                   false));
       CallInst *Call = CallInst::Create(Fn, RetAddr, "", InsertionPt);
       Call->setDebugLoc(DL);
+    } else if (TargetTriple.isSystemZ()) {
+      M.getOrInsertFunction(Func, Type::getVoidTy(C));
+      // skip insertion for `mcount` on SystemZ. This will be handled later in
+      // `emitPrologue`.
+      return false;
     } else {
       FunctionCallee Fn = M.getOrInsertFunction(Func, Type::getVoidTy(C));
       CallInst *Call = CallInst::Create(Fn, "", InsertionPt);
       Call->setDebugLoc(DL);
     }
-    return;
+    return true;
   }
 
   if (Func == "__cyg_profile_func_enter" || Func == "__cyg_profile_func_exit") {
@@ -87,7 +92,7 @@ static void insertCall(Function &CurFn, StringRef Func,
     CallInst *Call =
         CallInst::Create(Fn, ArrayRef<Value *>(Args), "", InsertionPt);
     Call->setDebugLoc(DL);
-    return;
+    return true;
   }
 
   // We only know how to call a fixed set of instrumentation functions, because
@@ -129,9 +134,9 @@ static bool runOnFunction(Function &F, bool PostInlining) {
     if (auto SP = F.getSubprogram())
       DL = DILocation::get(SP->getContext(), SP->getScopeLine(), 0, SP);
 
-    insertCall(F, EntryFunc, F.begin()->getFirstInsertionPt(), DL);
-    Changed = true;
-    F.removeFnAttr(EntryAttr);
+    Changed = insertCall(F, EntryFunc, F.begin()->getFirstInsertionPt(), DL);
+    if (Changed)
+      F.removeFnAttr(EntryAttr);
   }
 
   if (!ExitFunc.empty()) {

llvm/test/CodeGen/SystemZ/mcount.ll

@@ -0,0 +1,35 @@
+; Test proper insertion of mcount instrumentation
+;
+; RUN: llc < %s -mtriple=s390x-linux-gnu -o - | FileCheck %s
+;
+; CHECK: # %bb.0:
+; CHECK-NEXT: stg %r14, 8(%r15)
+; CHECK-NEXT: brasl %r14, mcount@PLT
+; CHECK-NEXT: lg %r14, 8(%r15)
+define dso_local signext i32 @fib(i32 noundef signext %n) #0 {
+entry:
+  %n.addr = alloca i32, align 4
+  store i32 %n, ptr %n.addr, align 4
+  %0 = load i32, ptr %n.addr, align 4
+  %cmp = icmp sle i32 %0, 1
+  br i1 %cmp, label %cond.true, label %cond.false
+
+cond.true:                                        ; preds = %entry
+  br label %cond.end
+
+cond.false:                                       ; preds = %entry
+  %1 = load i32, ptr %n.addr, align 4
+  %sub = sub nsw i32 %1, 1
+  %call = call signext i32 @fib(i32 noundef signext %sub)
+  %2 = load i32, ptr %n.addr, align 4
+  %sub1 = sub nsw i32 %2, 2
+  %call2 = call signext i32 @fib(i32 noundef signext %sub1)
+  %add = add nsw i32 %call, %call2
+  br label %cond.end
+
+cond.end:                                         ; preds = %cond.false, %cond.true
+  %cond = phi i32 [ 1, %cond.true ], [ %add, %cond.false ]
+  ret i32 %cond
+}
+
+attributes #0 = { "instrument-function-entry-inlined"="mcount" }