Reapply ccddb6f, "Emit a worst-case prologue_end"

In 39b2979 Pavel has kindly refined the implementation of a test in such
a way that it doesn't trip up over this patch -- the test wishes to
stimulate LLDBs presentation of line0 locations, rather than wanting to
always step on line-zero on entry to artificial_location.c. As that's what
was tripping up this change, reapply.

Original commit message follows.

[DWARF] Emit a worst-case prologue_end flag for pathological inputs (llvm#107849)

prologue_end usually indicates where the end of the function-initialization
lies, and is where debuggers usually choose to put the initial breakpoint
for a function. Our current algorithm piggy-backs it on the first available
source-location: which doesn't necessarily have anything to do with the
start of the function.

To avoid this in heavily-optimised code that lacks many useful source
locations, pick a worst-case "if all else fails" prologue_end location, of
the first instruction that appears to do meaningful computation. It'll be
given the function-scope line number, which should run-on from the start of
the function anyway. This means if your code is completely inverted by the
optimiser, you can at least put a breakpoint at the _start_ like you
expect, even if it's difficult to then step through.

This patch also attempts to preserve some good behaviour we have without
optimisations -- at O0, if the prologue immediately falls into a loop body
without any computation happening, then prologue_end lands at the start of
that loop. This is desirable; but does mean we need to do more work to
detect and support those situations.

Author: jmorse

llvm/lib/CodeGen/AsmPrinter/DwarfDebug.cpp

@@ -2062,6 +2062,16 @@ void DwarfDebug::beginInstruction(const MachineInstr *MI) {
   unsigned LastAsmLine =
       Asm->OutStreamer->getContext().getCurrentDwarfLoc().getLine();
 
+  if (!DL && MI == PrologEndLoc) {
+    // In rare situations, we might want to place the end of the prologue
+    // somewhere that doesn't have a source location already. It should be in
+    // the entry block.
+    assert(MI->getParent() == &*MI->getMF()->begin());
+    recordSourceLine(SP->getScopeLine(), 0, SP,
+                     DWARF2_FLAG_PROLOGUE_END | DWARF2_FLAG_IS_STMT);
+    return;
+  }
+
   bool PrevInstInSameSection =
       (!PrevInstBB ||
        PrevInstBB->getSectionID() == MI->getParent()->getSectionID());
@@ -2138,32 +2148,109 @@ static std::pair<const MachineInstr *, bool>
 findPrologueEndLoc(const MachineFunction *MF) {
   // First known non-DBG_VALUE and non-frame setup location marks
   // the beginning of the function body.
-  const MachineInstr *LineZeroLoc = nullptr;
+  const auto &TII = *MF->getSubtarget().getInstrInfo();
+  const MachineInstr *NonTrivialInst = nullptr;
   const Function &F = MF->getFunction();
 
   // Some instructions may be inserted into prologue after this function. Must
   // keep prologue for these cases.
   bool IsEmptyPrologue =
       !(F.hasPrologueData() || F.getMetadata(LLVMContext::MD_func_sanitize));
-  for (const auto &MBB : *MF) {
-    for (const auto &MI : MBB) {
-      if (!MI.isMetaInstruction()) {
-        if (!MI.getFlag(MachineInstr::FrameSetup) && MI.getDebugLoc()) {
-          // Scan forward to try to find a non-zero line number. The
-          // prologue_end marks the first breakpoint in the function after the
-          // frame setup, and a compiler-generated line 0 location is not a
-          // meaningful breakpoint. If none is found, return the first
-          // location after the frame setup.
-          if (MI.getDebugLoc().getLine())
-            return std::make_pair(&MI, IsEmptyPrologue);
-
-          LineZeroLoc = &MI;
-        }
-        IsEmptyPrologue = false;
-      }
+
+  // Helper lambda to examine each instruction and potentially return it
+  // as the prologue_end point.
+  auto ExamineInst = [&](const MachineInstr &MI)
+      -> std::optional<std::pair<const MachineInstr *, bool>> {
+    // Is this instruction trivial data shuffling or frame-setup?
+    bool isCopy = (TII.isCopyInstr(MI) ? true : false);
+    bool isTrivRemat = TII.isTriviallyReMaterializable(MI);
+    bool isFrameSetup = MI.getFlag(MachineInstr::FrameSetup);
+
+    if (!isFrameSetup && MI.getDebugLoc()) {
+      // Scan forward to try to find a non-zero line number. The
+      // prologue_end marks the first breakpoint in the function after the
+      // frame setup, and a compiler-generated line 0 location is not a
+      // meaningful breakpoint. If none is found, return the first
+      // location after the frame setup.
+      if (MI.getDebugLoc().getLine())
+        return std::make_pair(&MI, IsEmptyPrologue);
+    }
+
+    // Keep track of the first "non-trivial" instruction seen, i.e. anything
+    // that doesn't involve shuffling data around or is a frame-setup.
+    if (!isCopy && !isTrivRemat && !isFrameSetup && !NonTrivialInst)
+      NonTrivialInst = &MI;
+
+    IsEmptyPrologue = false;
+    return std::nullopt;
+  };
+
+  // Examine all the instructions at the start of the function. This doesn't
+  // necessarily mean just the entry block: unoptimised code can fall-through
+  // into an initial loop, and it makes sense to put the initial breakpoint on
+  // the first instruction of such a loop. However, if we pass branches, we're
+  // better off synthesising an early prologue_end.
+  auto CurBlock = MF->begin();
+  auto CurInst = CurBlock->begin();
+  while (true) {
+    // Skip empty blocks, in rare cases the entry can be empty.
+    if (CurInst == CurBlock->end()) {
+      ++CurBlock;
+      CurInst = CurBlock->begin();
+      continue;
     }
+
+    // Check whether this non-meta instruction a good position for prologue_end.
+    if (!CurInst->isMetaInstruction()) {
+      auto FoundInst = ExamineInst(*CurInst);
+      if (FoundInst)
+        return *FoundInst;
+    }
+
+    // Try to continue searching, but use a backup-location if substantive
+    // computation is happening.
+    auto NextInst = std::next(CurInst);
+    if (NextInst != CurInst->getParent()->end()) {
+      // Continue examining the current block.
+      CurInst = NextInst;
+      continue;
+    }
+
+    // We've reached the end of the block. Did we just look at a terminator?
+    if (CurInst->isTerminator()) {
+      // Some kind of "real" control flow is occurring. At the very least
+      // we would have to start exploring the CFG, a good signal that the
+      // prologue is over.
+      break;
+    }
+
+    // If we've already fallen through into a loop, don't fall through
+    // further, use a backup-location.
+    if (CurBlock->pred_size() > 1)
+      break;
+
+    // Fall-through from entry to the next block. This is common at -O0 when
+    // there's no initialisation in the function. Bail if we're also at the
+    // end of the function.
+    if (++CurBlock == MF->end())
+      break;
+    CurInst = CurBlock->begin();
+  }
+
+  // We couldn't find any source-location, suggesting all meaningful information
+  // got optimised away. Set the prologue_end to be the first non-trivial
+  // instruction, which will get the scope line number. This is better than
+  // nothing.
+  // Only do this in the entry block, as we'll be giving it the scope line for
+  // the function. Return IsEmptyPrologue==true if we've picked the first
+  // instruction.
+  if (NonTrivialInst && NonTrivialInst->getParent() == &*MF->begin()) {
+    IsEmptyPrologue = NonTrivialInst == &*MF->begin()->begin();
+    return std::make_pair(NonTrivialInst, IsEmptyPrologue);
   }
-  return std::make_pair(LineZeroLoc, IsEmptyPrologue);
+
+  // If the entry path is empty, just don't have a prologue_end at all.
+  return std::make_pair(nullptr, IsEmptyPrologue);
 }
 
 /// Register a source line with debug info. Returns the  unique label that was
@@ -2195,12 +2282,21 @@ DwarfDebug::emitInitialLocDirective(const MachineFunction &MF, unsigned CUID) {
   bool IsEmptyPrologue = PrologEnd.second;
 
   // If the prolog is empty, no need to generate scope line for the proc.
-  if (IsEmptyPrologue)
-    // In degenerate cases, we can have functions with no source locations
-    // at all. These want a scope line, to avoid a totally empty function.
-    // Thus, only skip scope line if there's location to place prologue_end.
-    if (PrologEndLoc)
-      return PrologEndLoc;
+  if (IsEmptyPrologue) {
+    // If there's nowhere to put a prologue_end flag, emit a scope line in case
+    // there are simply no source locations anywhere in the function.
+    if (PrologEndLoc) {
+      // Avoid trying to assign prologue_end to a line-zero location.
+      // Instructions with no DebugLoc at all are fine, they'll be given the
+      // scope line nuumber.
+      const DebugLoc &DL = PrologEndLoc->getDebugLoc();
+      if (!DL || DL->getLine() != 0)
+        return PrologEndLoc;
+
+      // Later, don't place the prologue_end flag on this line-zero location.
+      PrologEndLoc = nullptr;
+    }
+  }
 
   // Ensure the compile unit is created if the function is called before
   // beginFunction().

llvm/test/CodeGen/X86/no-non-zero-debug-loc-prologue.ll

@@ -1,10 +1,10 @@
-; RUN: llc -filetype=asm -mtriple=x86_64-apple-macosx12.0.0 -O0 %s -o - | FileCheck %s
+; RUN: llc -filetype=asm -mtriple=x86_64-apple-macosx12.0.0 -O0 %s -o - | FileCheck %s --implicit-check-not=prologue_end
 ; CHECK: Lfunc_begin0:
 ; CHECK-NEXT: .file{{.+}}
 ; CHECK-NEXT: .loc 1 1 0 ## test-small.c:1:0{{$}}
 ; CHECK-NEXT: .cfi_startproc
 ; CHECK-NEXT: ## %bb.{{[0-9]+}}:
-; CHECK-NEXT: .loc 1 0 1 prologue_end{{.*}}
+; CHECK-NEXT: .loc 1 0 1
 define void @test() #0 !dbg !9 {
   ret void, !dbg !12
 }
@@ -19,4 +19,4 @@ define void @test() #0 !dbg !9 {
 !9 = distinct !DISubprogram(name: "test", scope: !10, file: !10, line: 1, type: !11, scopeLine: 1, spFlags: DISPFlagDefinition, unit: !5, retainedNodes: !7)
 !10 = !DIFile(filename: "test-small.c", directory: "/Users/shubham/Development/test")
 !11 = !DISubroutineType(types: !7)
-!12 = !DILocation(line: 0, column: 1, scope: !9)
+!12 = !DILocation(line: 0, column: 1, scope: !9)

llvm/test/CodeGen/X86/pseudo_cmov_lower2.ll

@@ -200,9 +200,9 @@ declare void @llvm.dbg.value(metadata, metadata, metadata)
 ; minus the DEBUG_VALUE line and changes in labels..
 define double @foo1_g(float %p1, double %p2, double %p3) nounwind !dbg !4 {
 ; CHECK-LABEL: foo1_g:
-; CHECK:       .file   1 "." "test.c"
-; CHECK-NEXT:  .loc    1 3 0
 ; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    .file   1 "." "test.c"
+; CHECK-NEXT:    .loc 1 3 0 prologue_end
 ; CHECK-NEXT:    xorps %xmm3, %xmm3
 ; CHECK-NEXT:    ucomiss %xmm3, %xmm0
 ; CHECK-NEXT:    movsd {{.*#+}} xmm0 = [1.25E+0,0.0E+0]

llvm/test/DebugInfo/MIR/X86/dbg-prologue-backup-loc2.mir

@@ -0,0 +1,134 @@
+# RUN: llc %s -start-before=livedebugvalues -o - | \
+# RUN:     FileCheck %s --implicit-check-not=prologue_end
+#
+## When picking a "backup" location of the first non-trivial instruction in
+## a function, don't select a location outside of the entry block. We have to
+## give it the function's scope-line, and installing that outside of the entry
+## block is liable to be misleading.
+##
+## Produced from the C below with "clang -O2 -g -mllvm
+## -stop-before=livedebugvalues", then modified to unrotate and shift early
+## insts into the loop block. This means the MIR is meaningless, we only test
+## whether the scope-line will leak into the loop block or not.
+##
+## int glob = 0;
+## int foo(int arg, int sum) {
+##   arg += sum;
+##   while (arg) {
+##     glob--;
+##     arg %= glob;
+##   }
+##   return 0;
+## }
+#
+# CHECK-LABEL: foo:
+# CHECK:        .loc    0 2 0
+# CHECK:        # %bb.0:
+# CHECK-NEXT:   movl    %edi, %edx
+# CHECK-NEXT:   .loc    0 0 0 is_stmt 0
+# CHECK-NEXT:   .Ltmp0:
+# CHECK-NEXT:   .p2align        4
+# CHECK-NEXT:   .LBB0_1:
+# CHECK-LABEL:  addl    %esi, %edx
+
+ 
+--- |
+  ; ModuleID = 'out2.ll'
+  source_filename = "foo.c"
+  target datalayout = "e-m:e-p270:32:32-p271:32:32-p272:64:64-i64:64-i128:128-f80:128-n8:16:32:64-S128"
+  target triple = "x86_64-unknown-linux-gnu"
+  
+  @glob = dso_local local_unnamed_addr global i32 0, align 4, !dbg !0
+  
+  define dso_local noundef i32 @foo(i32 noundef %arg, i32 noundef %sum) local_unnamed_addr !dbg !9 {
+  entry:
+    %add = add nsw i32 %sum, %arg
+    br label %while.body.preheader
+  
+  while.body.preheader:                             ; preds = %entry
+    %glob.promoted = load i32, ptr @glob, align 4
+    br label %while.body, !dbg !13
+  
+  while.body:                                       ; preds = %while.body, %while.body.preheader
+    %arg.addr.06 = phi i32 [ %rem, %while.body ], [ %add, %while.body.preheader ]
+    %dec35 = phi i32 [ %dec, %while.body ], [ %glob.promoted, %while.body.preheader ]
+    %dec = add nsw i32 %dec35, -1, !dbg !14
+    %0 = add i32 %dec35, -1, !dbg !16
+    %rem = srem i32 %arg.addr.06, %0, !dbg !16
+    %tobool.not = icmp eq i32 %rem, 0, !dbg !13
+    br i1 %tobool.not, label %while.cond.while.end_crit_edge, label %while.body, !dbg !13
+  
+  while.cond.while.end_crit_edge:                   ; preds = %while.body
+    store i32 %dec, ptr @glob, align 4, !dbg !14
+    br label %while.end, !dbg !13
+  
+  while.end:                                        ; preds = %while.cond.while.end_crit_edge
+    ret i32 0, !dbg !17
+  }
+  
+  !llvm.dbg.cu = !{!2}
+  !llvm.module.flags = !{!6, !7}
+  !llvm.ident = !{!8}
+  
+  !0 = !DIGlobalVariableExpression(var: !1, expr: !DIExpression())
+  !1 = distinct !DIGlobalVariable(name: "glob", scope: !2, file: !3, line: 1, type: !5, isLocal: false, isDefinition: true)
+  !2 = distinct !DICompileUnit(language: DW_LANG_C11, file: !3, producer: "clang", isOptimized: true, runtimeVersion: 0, emissionKind: FullDebug, globals: !4, splitDebugInlining: false, nameTableKind: None)
+  !3 = !DIFile(filename: "foo.c", directory: "")
+  !4 = !{!0}
+  !5 = !DIBasicType(name: "int", size: 32, encoding: DW_ATE_signed)
+  !6 = !{i32 7, !"Dwarf Version", i32 5}
+  !7 = !{i32 2, !"Debug Info Version", i32 3}
+  !8 = !{!"clang"}
+  !9 = distinct !DISubprogram(name: "foo", scope: !3, file: !3, line: 2, type: !10, scopeLine: 2, flags: DIFlagPrototyped | DIFlagAllCallsDescribed, spFlags: DISPFlagDefinition | DISPFlagOptimized, unit: !2, retainedNodes: !12)
+  !10 = !DISubroutineType(types: !11)
+  !11 = !{!5, !5, !5}
+  !12 = !{}
+  !13 = !DILocation(line: 4, column: 3, scope: !9)
+  !14 = !DILocation(line: 5, column: 9, scope: !15)
+  !15 = distinct !DILexicalBlock(scope: !9, file: !3, line: 4, column: 15)
+  !16 = !DILocation(line: 6, column: 9, scope: !15)
+  !17 = !DILocation(line: 8, column: 3, scope: !9)
+
+...
+---
+name:            foo
+alignment:       16
+tracksRegLiveness: true
+debugInstrRef:   true
+tracksDebugUserValues: true
+liveins:
+  - { reg: '$edi' }
+  - { reg: '$esi' }
+frameInfo:
+  maxAlignment:    1
+  maxCallFrameSize: 0
+  isCalleeSavedInfoValid: true
+machineFunctionInfo:
+  amxProgModel:    None
+body:             |
+  bb.0.entry:
+    liveins: $edi, $esi
+  
+    $edx = MOV32rr $edi
+  
+  bb.1.while.body (align 16):
+    successors: %bb.2(0x04000000), %bb.1(0x7c000000)
+    liveins: $ecx, $edx, $esi
+
+    renamable $edx = nsw ADD32rr killed renamable $edx, renamable $esi, implicit-def dead $eflags
+    renamable $ecx = MOV32rm $rip, 1, $noreg, @glob, $noreg :: (dereferenceable load (s32) from @glob)
+    renamable $ecx = DEC32r killed renamable $ecx, implicit-def dead $eflags
+    $eax = MOV32rr killed $edx
+    CDQ implicit-def $eax, implicit-def $edx, implicit $eax
+    IDIV32r renamable $ecx, implicit-def dead $eax, implicit-def $edx, implicit-def dead $eflags, implicit $eax, implicit $edx
+    TEST32rr renamable $edx, renamable $edx, implicit-def $eflags
+    JCC_1 %bb.1, 5, implicit killed $eflags
+  
+  bb.2.while.cond.while.end_crit_edge:
+    liveins: $ecx, $esi
+  
+    MOV32mr $rip, 1, $noreg, @glob, $noreg, killed renamable $ecx, debug-location !14 :: (store (s32) into @glob)
+    $eax = XOR32rr undef $eax, undef $eax, implicit-def dead $eflags, debug-location !17
+    RET64 $eax, debug-location !17
+
+...

llvm/test/DebugInfo/MIR/X86/empty-inline.mir

@@ -13,9 +13,10 @@
 #
 # CHECK: Address            Line   Column File   ISA Discriminator OpIndex Flags
 # CHECK-NEXT:                ---
-# CHECK-NEXT:                 25      0      1   0             0         0 is_stmt
-# CHECK-NEXT:                 29     28      1   0             0         0 is_stmt prologue_end
+# CHECK-NEXT:                 25      0      1   0             0         0 is_stmt prologue_end
+# CHECK-NEXT:                 29     28      1   0             0         0 is_stmt
 # CHECK-NEXT:                 29     28      1   0             0         0 is_stmt end_sequence
+
 --- |
   source_filename = "t.ll"
   target datalayout = "e-m:o-i64:64-f80:128-n8:16:32:64-S128"