[llvm] [DebugInfo] Don't set prologue_end behind line-zero call insts (PR #156850)

via llvm-commits llvm-commits at lists.llvm.org
Thu Sep 4 03:41:41 PDT 2025


llvmbot wrote:


<!--LLVM PR SUMMARY COMMENT-->

@llvm/pr-subscribers-debuginfo

Author: Jeremy Morse (jmorse)

<details>
<summary>Changes</summary>

In functions that have been seriously deformed during optimisation, there can be call instructions with line-zero immediately after frame setup (see C reproducer in the test added). Our previous algorithms for prologue_end ignored these, meaning someone entering a function at prologue_end would break-in after a function call had completed. Prefer instead to not emit prologue_end at all: there is no good place to put it.

---
Full diff: https://github.com/llvm/llvm-project/pull/156850.diff


3 Files Affected:

- (modified) llvm/lib/CodeGen/AsmPrinter/DwarfDebug.cpp (+9) 
- (modified) llvm/test/DebugInfo/MIR/X86/debug-loc-0.mir (+1-1) 
- (added) llvm/test/DebugInfo/X86/no-prologue-end-after-line0-calls.mir (+129) 


``````````diff
diff --git a/llvm/lib/CodeGen/AsmPrinter/DwarfDebug.cpp b/llvm/lib/CodeGen/AsmPrinter/DwarfDebug.cpp
index c27f100775625..0208167fac6f7 100644
--- a/llvm/lib/CodeGen/AsmPrinter/DwarfDebug.cpp
+++ b/llvm/lib/CodeGen/AsmPrinter/DwarfDebug.cpp
@@ -2291,6 +2291,15 @@ findPrologueEndLoc(const MachineFunction *MF) {
         return *FoundInst;
     }
 
+    // We choose to ignore line-zero locations when setting the prologue as they
+    // can't be stepped on anyway; however in very rare scenarios function calls
+    // can have line zero, and we shouldn't step over those. In these
+    // extraordinary conditions, just bail out and refuse to set a prologue_end.
+    if (CurInst->isCall())
+      if (const DILocation *Loc = CurInst->getDebugLoc().get())
+        if (Loc->getLine() == 0)
+          return std::make_pair(nullptr, true);
+
     // Try to continue searching, but use a backup-location if substantive
     // computation is happening.
     auto NextInst = std::next(CurInst);
diff --git a/llvm/test/DebugInfo/MIR/X86/debug-loc-0.mir b/llvm/test/DebugInfo/MIR/X86/debug-loc-0.mir
index 01862f5905f9c..71489d5a5e485 100644
--- a/llvm/test/DebugInfo/MIR/X86/debug-loc-0.mir
+++ b/llvm/test/DebugInfo/MIR/X86/debug-loc-0.mir
@@ -5,7 +5,7 @@
 # CHECK: Ltmp0:
 # CHECK: .loc 1 0 0
 # CHECK-NOT: .loc 1 0 0
-# CHECK: .loc 1 37 1 prologue_end
+# CHECK: .loc 1 37 1
 
 --- |
   ; ModuleID = '<stdin>'
diff --git a/llvm/test/DebugInfo/X86/no-prologue-end-after-line0-calls.mir b/llvm/test/DebugInfo/X86/no-prologue-end-after-line0-calls.mir
new file mode 100644
index 0000000000000..604b9d1d2eafb
--- /dev/null
+++ b/llvm/test/DebugInfo/X86/no-prologue-end-after-line0-calls.mir
@@ -0,0 +1,129 @@
+# RUN: llc %s -start-after=livedebugvalues -o - -filetype=obj | llvm-dwarfdump - --debug-line | FileCheck %s --implicit-check-not=prologue_end
+#
+## Original code, compiled clang -O2 -g -c
+## 
+## void ext();
+## int main(int argc, char **argv) {
+##   if (argc == 1)
+##     ext();
+##   else
+##     ext();
+##    return 0;
+## }
+## 
+## In the code sequence above, the call to ext is given line zero during
+## optimisation, because the code is duplicated down all function paths thus
+## gets merged. We get something like this as the output:
+##
+##   0:   50                      push   %rax
+##   1:   31 c0                   xor    %eax,%eax
+##   3:   e8 00 00 00 00          call   8 <main+0x8>
+##                        4: R_X86_64_PLT32       ext-0x4
+##   8:   31 c0                   xor    %eax,%eax
+##   a:   59                      pop    %rcx
+##   b:   c3                      ret
+##
+## Where prologue_end is placed on address 8, the clearing of the return
+## register, because it's the first "real" instruction that isn't line zero.
+## This then causes debuggers to skip over the call instruction when entering
+## the function, which is catastrophic.
+##
+## Instead: we shouldn't put a prologue_end on this function at all. It's too
+## deformed from the original code to truly have a position (with a line number)
+## that is both true, and after frame setup. This gives comsumers the
+## opportunity to recognise "this is a crazy function" and act accordingly.
+##
+## Check lines ensure that there's something meaningful in the line table
+## involving line 2, the implicit-check-not is making sure there isn't a
+## prologue_end flag on any line entry.
+#
+# CHECK: standard_opcode_lengths[DW_LNS_set_prologue_end] = 0
+#
+# CHECK:  Address            Line   Column File
+# CHECK:  2      0      0 
+# CHECK:  end_sequence
+--- |
+  ; ModuleID = '/tmp/test.c'
+  source_filename = "/tmp/test.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"
+  
+  ; Function Attrs: nounwind uwtable
+  define dso_local noundef i32 @main(i32 noundef %argc, ptr noundef readnone captures(none) %argv) local_unnamed_addr !dbg !10 {
+  entry:
+      #dbg_value(i32 %argc, !19, !DIExpression(), !21)
+      #dbg_value(ptr %argv, !20, !DIExpression(), !21)
+    tail call void (...) @ext(), !dbg !22
+    ret i32 0, !dbg !24
+  }
+  
+  declare !dbg !25 void @ext(...) local_unnamed_addr
+  
+  !llvm.dbg.cu = !{!0}
+  !llvm.module.flags = !{!2, !3, !4, !5, !6, !7, !8}
+  !llvm.ident = !{!9}
+  
+  !0 = distinct !DICompileUnit(language: DW_LANG_C11, file: !1, producer: "clang version 22.0.0git (/fast/fs/llvm4 8989ec5439dc2df2aeb7e5ea3e6c255ce8e9634d)", isOptimized: true, runtimeVersion: 0, emissionKind: FullDebug, splitDebugInlining: false, nameTableKind: None)
+  !1 = !DIFile(filename: "/tmp/test.c", directory: "/fast/fs/llvm-stage/debug", checksumkind: CSK_MD5, checksum: "9862df54ae1fdd9354308eae69de364a")
+  !2 = !{i32 7, !"Dwarf Version", i32 5}
+  !3 = !{i32 2, !"Debug Info Version", i32 3}
+  !4 = !{i32 1, !"wchar_size", i32 4}
+  !5 = !{i32 8, !"PIC Level", i32 2}
+  !6 = !{i32 7, !"PIE Level", i32 2}
+  !7 = !{i32 7, !"uwtable", i32 2}
+  !8 = !{i32 7, !"debug-info-assignment-tracking", i1 true}
+  !9 = !{!"clang version 22.0.0git (/fast/fs/llvm4 8989ec5439dc2df2aeb7e5ea3e6c255ce8e9634d)"}
+  !10 = distinct !DISubprogram(name: "main", scope: !11, file: !11, line: 2, type: !12, scopeLine: 2, flags: DIFlagPrototyped | DIFlagAllCallsDescribed, spFlags: DISPFlagDefinition | DISPFlagOptimized, unit: !0, retainedNodes: !18, keyInstructions: true)
+  !11 = !DIFile(filename: "/tmp/test.c", directory: "", checksumkind: CSK_MD5, checksum: "9862df54ae1fdd9354308eae69de364a")
+  !12 = !DISubroutineType(types: !13)
+  !13 = !{!14, !14, !15}
+  !14 = !DIBasicType(name: "int", size: 32, encoding: DW_ATE_signed)
+  !15 = !DIDerivedType(tag: DW_TAG_pointer_type, baseType: !16, size: 64)
+  !16 = !DIDerivedType(tag: DW_TAG_pointer_type, baseType: !17, size: 64)
+  !17 = !DIBasicType(name: "char", size: 8, encoding: DW_ATE_signed_char)
+  !18 = !{!19, !20}
+  !19 = !DILocalVariable(name: "argc", arg: 1, scope: !10, file: !11, line: 2, type: !14)
+  !20 = !DILocalVariable(name: "argv", arg: 2, scope: !10, file: !11, line: 2, type: !15)
+  !21 = !DILocation(line: 0, scope: !10)
+  !22 = !DILocation(line: 0, scope: !23)
+  !23 = distinct !DILexicalBlock(scope: !10, file: !11, line: 3, column: 7)
+  !24 = !DILocation(line: 7, column: 4, scope: !10, atomGroup: 2, atomRank: 1)
+  !25 = !DISubprogram(name: "ext", scope: !11, file: !11, line: 1, type: !26, spFlags: DISPFlagOptimized)
+  !26 = !DISubroutineType(types: !27)
+  !27 = !{null}
+...
+---
+name:            main
+alignment:       16
+tracksRegLiveness: true
+noPhis:          true
+isSSA:           false
+noVRegs:         true
+hasFakeUses:     false
+debugInstrRef:   true
+tracksDebugUserValues: true
+frameInfo:
+  stackSize:       8
+  offsetAdjustment: -8
+  maxAlignment:    1
+  adjustsStack:    true
+  hasCalls:        true
+  maxCallFrameSize: 0
+  isCalleeSavedInfoValid: true
+machineFunctionInfo:
+  amxProgModel:    None
+body:             |
+  bb.0.entry:
+    DBG_VALUE $edi, $noreg, !19, !DIExpression(),  debug-location !21
+    DBG_VALUE $rsi, $noreg, !20, !DIExpression(),  debug-location !21
+    frame-setup PUSH64r undef $rax, implicit-def $rsp, implicit $rsp
+    frame-setup CFI_INSTRUCTION def_cfa_offset 16
+    dead $eax = XOR32rr undef $eax, undef $eax, implicit-def dead $eflags, implicit-def $al,  debug-location !22
+    CALL64pcrel32 target-flags(x86-plt) @ext, csr_64, implicit $rsp, implicit $ssp, implicit killed $al, implicit-def $rsp, implicit-def $ssp,  debug-location !22
+    DBG_VALUE $rsi, $noreg, !20, !DIExpression(DW_OP_LLVM_entry_value, 1),  debug-location !21
+    DBG_VALUE $edi, $noreg, !19, !DIExpression(DW_OP_LLVM_entry_value, 1),  debug-location !21
+    $eax = XOR32rr undef $eax, undef $eax, implicit-def dead $eflags,  debug-location !24
+    $rcx = frame-destroy POP64r implicit-def $rsp, implicit $rsp,  debug-location !24
+    frame-destroy CFI_INSTRUCTION def_cfa_offset 8,  debug-location !24
+    RET64 $eax,  debug-location !24
+...

``````````

</details>


https://github.com/llvm/llvm-project/pull/156850


More information about the llvm-commits mailing list