[SystemZ] Add proper mcount handling (llvm#135767)

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.

The desired change in the `EntryExitInstrumenterPass` necessitated the
addition of a new attribute and attribute kind to each function, which
is used to trigger the postprocessing, aka call insertion, in
`emitPrologue`. Note that the new attribute must be of a different kind
than the `mcount` atribute, since otherwise it would replace that
attribute and later be deleted by the code that intended to delete
`mcount`. The new attribnute is called `insert-mcount`, while the
attribute kind is `systemz-backend`, to clearly mark it as a
SystemZ-specific backend concern.

This PR should address issue llvm#121137 . The test inserted here is derived
from the example given in that issue.

Author: dominik-steenken

llvm/lib/Target/SystemZ/SystemZFrameLowering.cpp

@@ -17,7 +17,9 @@
 #include "llvm/CodeGen/MachineRegisterInfo.h"
 #include "llvm/CodeGen/RegisterScavenging.h"
 #include "llvm/CodeGen/TargetLoweringObjectFileImpl.h"
+#include "llvm/IR/CallingConv.h"
 #include "llvm/IR/Function.h"
+#include "llvm/IR/Module.h"
 #include "llvm/Target/TargetMachine.h"
 
 using namespace llvm;
@@ -557,6 +559,36 @@ void SystemZELFFrameLowering::emitPrologue(MachineFunction &MF,
   // Debug location must be unknown since the first debug location is used
   // to determine the end of the prologue.
   DebugLoc DL;
+  // Add mcount instrumentation if necessary.
+  if (MF.getFunction()
+          .getFnAttribute("systemz-instrument-function-entry")
+          .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 from CC AnyReg since mcount preserves all normal
+    // argument registers).
+    FunctionCallee FC = MF.getFunction().getParent()->getOrInsertFunction(
+        "mcount", Type::getVoidTy(MF.getFunction().getContext()));
+    const uint32_t *Mask = MF.getSubtarget<SystemZSubtarget>()
+                               .getSpecialRegisters()
+                               ->getCallPreservedMask(MF, CallingConv::AnyReg);
+    BuildMI(MBB, MBBI, DL, ZII->get(SystemZ::CallBRASL))
+        .addGlobalAddress(dyn_cast<Function>(FC.getCallee()))
+        .addRegMask(Mask);
+
+    // Reload return address from 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

@@ -63,6 +63,11 @@ static void insertCall(Function &CurFn, StringRef Func,
                                   false));
       CallInst *Call = CallInst::Create(Fn, RetAddr, "", InsertionPt);
       Call->setDebugLoc(DL);
+    } else if (TargetTriple.isSystemZ()) {
+      // skip insertion for `mcount` on SystemZ. This will be handled later in
+      // `emitPrologue`. Add custom attribute to denote this.
+      CurFn.addFnAttr(
+          llvm::Attribute::get(C, "systemz-instrument-function-entry", Func));
     } else {
       FunctionCallee Fn = M.getOrInsertFunction(Func, Type::getVoidTy(C));
       CallInst *Call = CallInst::Create(Fn, "", InsertionPt);

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" }