[BPF] Don't crash on missing line info

[tamird]

Summary

When compiling Rust code we may end up with calls to functions provided
by other code units. Presently this code crashes on a null pointer
dereference - this patch avoids that crash and adds a test.

[tamird]

Avoid the crash

[tamird]

Revert back to better error

[eddyz87]

This error could be detected using the following test case:

$ cat test2.c
; ModuleID = 'test2.c'
source_filename = "test2.c"
target datalayout = "e-m:e-p:64:64-i64:64-i128:128-n32:64-S128"
target triple = "bpf"

; Function Attrs: noinline nounwind optnone
define dso_local i64 @foo() {
entry:
  ret i64 42
}

!llvm.dbg.cu = !{!0}
!llvm.module.flags = !{!2, !3, !4, !5}

!0 = distinct !DICompileUnit(language: DW_LANG_C11, file: !1, producer: "foo", isOptimized: false, runtimeVersion: 0, emissionKind: FullDebug, splitDebugInlining: false, nameTableKind: None)
!1 = !DIFile(filename: "file.c", directory: "/some/dir", checksumkind: CSK_MD5, checksum: "f58a7abbd9253986370acb1013fc9e55")
!2 = !{i32 7, !"Dwarf Version", i32 5}
!3 = !{i32 2, !"Debug Info Version", i32 3}
!4 = !{i32 1, !"wchar_size", i32 4}
!5 = !{i32 7, !"frame-pointer", i32 2}
!6 = !{!"clang version 18.0.0 (/home/eddy/work/llvm-project/clang 61cd4a1d35aa7c0f7b312b8f43ed3bff33f20d55)"}

$ llc test2.ll -o /dev/null
/home/eddy/work/llvm-project/llvm/lib/Target/BPF/BTFDebug.cpp:1640:42: runtime error: member call on null pointer of type 'llvm::DISubprogram'
SUMMARY: UndefinedBehaviorSanitizer: undefined-behavior /home/eddy/work/llvm-project/llvm/lib/Target/BPF/BTFDebug.cpp:1640:42 in 

Necessary conditions are: module with debug attributes (llvm.dbg.cu -> DICompileUnit) and a function and instruction w/o debug metadata. I think such test case should be added to the suite.
Also, I don't see a point in reporting this (either as warning or as error). Absence of DISubprogram is ignored in BTFDebug::processFuncPrototypes and it two other places getSubprogram() can't return null. I think the following patch should suffice:

diff --git a/llvm/lib/Target/BPF/BTFDebug.cpp b/llvm/lib/Target/BPF/BTFDebug.cpp
index d886edaff555..6df421934b70 100644
--- a/llvm/lib/Target/BPF/BTFDebug.cpp
+++ b/llvm/lib/Target/BPF/BTFDebug.cpp
@@ -1634,8 +1635,8 @@ void BTFDebug::beginInstruction(const MachineInstr *MI) {
   if (!DL || PrevInstLoc == DL) {
     // This instruction will be skipped, no LineInfo has
     // been generated, construct one based on function signature.
-    if (LineInfoGenerated == false) {
-      auto *S = MI->getMF()->getFunction().getSubprogram();
+    DISubprogram *S = MI->getMF()->getFunction().getSubprogram();
+    if (!LineInfoGenerated && S) {
       MCSymbol *FuncLabel = Asm->getFunctionBegin();
       constructLineInfo(S, FuncLabel, S->getLine(), 0);
       LineInfoGenerated = true;

[tamird]

In D156446#4554118, @eddyz87 wrote:

This error could be detected using the following test case:

$ cat test2.c
; ModuleID = 'test2.c'
source_filename = "test2.c"
target datalayout = "e-m:e-p:64:64-i64:64-i128:128-n32:64-S128"
target triple = "bpf"

; Function Attrs: noinline nounwind optnone
define dso_local i64 @foo() {
entry:
  ret i64 42
}

!llvm.dbg.cu = !{!0}
!llvm.module.flags = !{!2, !3, !4, !5}

!0 = distinct !DICompileUnit(language: DW_LANG_C11, file: !1, producer: "foo", isOptimized: false, runtimeVersion: 0, emissionKind: FullDebug, splitDebugInlining: false, nameTableKind: None)
!1 = !DIFile(filename: "file.c", directory: "/some/dir", checksumkind: CSK_MD5, checksum: "f58a7abbd9253986370acb1013fc9e55")
!2 = !{i32 7, !"Dwarf Version", i32 5}
!3 = !{i32 2, !"Debug Info Version", i32 3}
!4 = !{i32 1, !"wchar_size", i32 4}
!5 = !{i32 7, !"frame-pointer", i32 2}
!6 = !{!"clang version 18.0.0 (/home/eddy/work/llvm-project/clang 61cd4a1d35aa7c0f7b312b8f43ed3bff33f20d55)"}

$ llc test2.ll -o /dev/null
/home/eddy/work/llvm-project/llvm/lib/Target/BPF/BTFDebug.cpp:1640:42: runtime error: member call on null pointer of type 'llvm::DISubprogram'
SUMMARY: UndefinedBehaviorSanitizer: undefined-behavior /home/eddy/work/llvm-project/llvm/lib/Target/BPF/BTFDebug.cpp:1640:42 in 

Necessary conditions are: module with debug attributes (llvm.dbg.cu -> DICompileUnit) and a function and instruction w/o debug metadata. I think such test case should be added to the suite.
Also, I don't see a point in reporting this (either as warning or as error). Absence of DISubprogram is ignored in BTFDebug::processFuncPrototypes and it two other places getSubprogram() can't return null. I think the following patch should suffice:

diff --git a/llvm/lib/Target/BPF/BTFDebug.cpp b/llvm/lib/Target/BPF/BTFDebug.cpp
index d886edaff555..6df421934b70 100644
--- a/llvm/lib/Target/BPF/BTFDebug.cpp
+++ b/llvm/lib/Target/BPF/BTFDebug.cpp
@@ -1634,8 +1635,8 @@ void BTFDebug::beginInstruction(const MachineInstr *MI) {
   if (!DL || PrevInstLoc == DL) {
     // This instruction will be skipped, no LineInfo has
     // been generated, construct one based on function signature.
-    if (LineInfoGenerated == false) {
-      auto *S = MI->getMF()->getFunction().getSubprogram();
+    DISubprogram *S = MI->getMF()->getFunction().getSubprogram();
+    if (!LineInfoGenerated && S) {
       MCSymbol *FuncLabel = Asm->getFunctionBegin();
       constructLineInfo(S, FuncLabel, S->getLine(), 0);
       LineInfoGenerated = true;

Sounds good! I'll do that. Can you share the C source code of the program as well please?

[eddyz87]

In D156446#4554385, @tamird wrote:

Sounds good! I'll do that. Can you share the C source code of the program as well please?

// clang -g --target=bpf -S -emit-llvm test2.c -o -
unsigned long foo(void) {
  return 42;
}

Modified to remove !dbg from function and ret instructions.

[tamird]

Avoid crash, add test.

[tamird]

@ast @yonghong-song please review. This replaces https://reviews.llvm.org/D134533.

[ast]

llvm/lib/Target/BPF/BTFDebug.cpp

1378

parens

[tamird]

Remove braces

[tamird]

llvm/lib/Target/BPF/BTFDebug.cpp

1378

Done.

[tamird]

Less const

[ast]

lgtm assuming all tests are green.

[tamird]

Remove one CHECK line.

llvm/lib/Target/BPF/BTFDebug.cpp

 #include "BTFDebug.h"
 #include "BPF.h"
 #include "BPFCORE.h"
 #include "MCTargetDesc/BPFMCTargetDesc.h"
 #include "llvm/BinaryFormat/ELF.h"
 #include "llvm/CodeGen/AsmPrinter.h"
 #include "llvm/CodeGen/MachineModuleInfo.h"
 #include "llvm/CodeGen/MachineOperand.h"
+#include "llvm/IR/DebugInfoMetadata.h"
 #include "llvm/MC/MCContext.h"
 #include "llvm/MC/MCObjectFileInfo.h"
 #include "llvm/MC/MCSectionELF.h"
 #include "llvm/MC/MCStreamer.h"
 #include "llvm/Support/LineIterator.h"
 #include "llvm/Support/MemoryBuffer.h"
 #include "llvm/Target/TargetLoweringObjectFile.h"
 #include <optional>
void BTFDebug::beginInstruction(const MachineInstr *MI) {
 
   // Skip this instruction if no DebugLoc or the DebugLoc
   // is the same as the previous instruction.
   const DebugLoc &DL = MI->getDebugLoc();
   if (!DL || PrevInstLoc == DL) {
     // This instruction will be skipped, no LineInfo has
     // been generated, construct one based on function signature.
     if (LineInfoGenerated == false) {
-      auto *S = MI->getMF()->getFunction().getSubprogram();
+      const Function &F = MI->getMF()->getFunction();
+      const DISubprogram *const S = F.getSubprogram();
+      if (!S)
+        return;
       MCSymbol *FuncLabel = Asm->getFunctionBegin();
       constructLineInfo(S, FuncLabel, S->getLine(), 0);
       LineInfoGenerated = true;
     }
 
     return;
   }
 

llvm/test/CodeGen/BPF/BTF/incomplete-debuginfo.ll

+; RUN: llc -march=bpfel -filetype=asm -o - %s | FileCheck -check-prefixes=CHECK %s
+; RUN: llc -march=bpfeb -filetype=asm -o - %s | FileCheck -check-prefixes=CHECK %s
+;
+; Source code:
+;   unsigned long foo(void) {
+;     return 42;
+;   }
+;   unsigned long bar(void) {
+;     return 1337;
+;   }
+; Compilation flag:
+;   clang -target bpf -O2 -g -S -emit-llvm test.c -o - | sed -E 's/,? !dbg !(7|11)//'
+
+; Function Attrs: noinline nounwind optnone
+define dso_local i64 @foo() #0 {
+entry:
+  ret i64 42
+}
+
+; Function Attrs: noinline nounwind optnone
+define dso_local i64 @bar() #0 !dbg !12 {
+entry:
+  ret i64 1337, !dbg !13
+}
+
+; CHECK: .section        .BTF,"",@progbits
+; CHECK: .long   0                               # BTF_KIND_FUNC_PROTO(id = 1)
+; CHECK: .long   1                               # BTF_KIND_INT(id = 2)
+; CHECK: .long   15                              # BTF_KIND_FUNC(id = 3)
+; CHECK: .byte   0                               # string offset=0
+; CHECK: .ascii  "unsigned long"                 # string offset=1
+; CHECK: .ascii  "bar"                           # string offset=15
+; CHECK: .ascii  ".text"                         # string offset=19
+; CHECK: .ascii  "  return 1337;"                # string offset=69
+
+attributes #0 = { noinline nounwind optnone "frame-pointer"="all" "no-trapping-math"="true" "stack-protector-buffer-size"="8" }
+
+!llvm.dbg.cu = !{!0}
+!llvm.module.flags = !{!2, !3, !4, !5}
+!llvm.ident = !{!6}
+
+!0 = distinct !DICompileUnit(language: DW_LANG_C11, file: !1, producer: "clang version 18.0.0 (https://github.com/llvm/llvm-project.git 8031b3f2c40d3fe622648b6731a0ae1dc3f37860)", isOptimized: false, runtimeVersion: 0, emissionKind: FullDebug, splitDebugInlining: false, nameTableKind: None)
+!1 = !DIFile(filename: "test.c", directory: "/home/tamird/src/llvm-project-latest", checksumkind: CSK_MD5, checksum: "20bd72139e533d6aed61683730100513")
+!2 = !{i32 7, !"Dwarf Version", i32 5}
+!3 = !{i32 2, !"Debug Info Version", i32 3}
+!4 = !{i32 1, !"wchar_size", i32 4}
+!5 = !{i32 7, !"frame-pointer", i32 2}
+!6 = !{!"clang version 18.0.0 (https://github.com/llvm/llvm-project.git 8031b3f2c40d3fe622648b6731a0ae1dc3f37860)"}
+!7 = distinct !DISubprogram(name: "foo", scope: !1, file: !1, line: 1, type: !8, scopeLine: 1, flags: DIFlagPrototyped, spFlags: DISPFlagDefinition, unit: !0)
+!8 = !DISubroutineType(types: !9)
+!9 = !{!10}
+!10 = !DIBasicType(name: "unsigned long", size: 64, encoding: DW_ATE_unsigned)
+!11 = !DILocation(line: 2, column: 3, scope: !7)
+!12 = distinct !DISubprogram(name: "bar", scope: !1, file: !1, line: 5, type: !8, scopeLine: 5, flags: DIFlagPrototyped, spFlags: DISPFlagDefinition, unit: !0)
+!13 = !DILocation(line: 6, column: 3, scope: !12)