[lld] 0eec7e2 - Reland "[lld-macho] Group undefined symbol diagnostics by symbol".
Nico Weber via llvm-commits
llvm-commits at lists.llvm.org
Wed Jun 15 16:22:58 PDT 2022
Author: Daniel Bertalan
Date: 2022-06-15T19:22:39-04:00
New Revision: 0eec7e2a89abc6e626cad3c6493b3a1c15c10704
URL: https://github.com/llvm/llvm-project/commit/0eec7e2a89abc6e626cad3c6493b3a1c15c10704
DIFF: https://github.com/llvm/llvm-project/commit/0eec7e2a89abc6e626cad3c6493b3a1c15c10704.diff
LOG: Reland "[lld-macho] Group undefined symbol diagnostics by symbol".
This reverts commit 36e7c9a450db5e22af1ec21412d918ceb2313942.
This relands d61341768cf0cff7c with the fix described in
https://reviews.llvm.org/D127753#3587390
Added:
lld/test/MachO/invalid/undef-multi.s
Modified:
lld/ELF/Relocations.cpp
lld/MachO/SymbolTable.cpp
lld/MachO/SymbolTable.h
lld/MachO/Writer.cpp
Removed:
################################################################################
diff --git a/lld/ELF/Relocations.cpp b/lld/ELF/Relocations.cpp
index a272be5480e3..76d448fe471b 100644
--- a/lld/ELF/Relocations.cpp
+++ b/lld/ELF/Relocations.cpp
@@ -558,6 +558,7 @@ static std::string maybeReportDiscarded(Undefined &sym) {
return msg;
}
+namespace {
// Undefined diagnostics are collected in a vector and emitted once all of
// them are known, so that some postprocessing on the list of undefined symbols
// can happen before lld emits diagnostics.
@@ -571,7 +572,8 @@ struct UndefinedDiag {
bool isWarning;
};
-static std::vector<UndefinedDiag> undefs;
+std::vector<UndefinedDiag> undefs;
+}
// Check whether the definition name def is a mangled function name that matches
// the reference name ref.
diff --git a/lld/MachO/SymbolTable.cpp b/lld/MachO/SymbolTable.cpp
index b0c83a568eb6..5bc622126071 100644
--- a/lld/MachO/SymbolTable.cpp
+++ b/lld/MachO/SymbolTable.cpp
@@ -345,35 +345,82 @@ static bool recoverFromUndefinedSymbol(const Undefined &sym) {
return false;
}
-static void printUndefinedDiagnostic(StringRef name, StringRef source) {
- std::string message = "undefined symbol";
- if (config->archMultiple)
- message += (" for arch " + getArchitectureName(config->arch())).str();
- message += (": " + name + "\n>>> referenced by " + source).str();
-
- if (config->undefinedSymbolTreatment == UndefinedSymbolTreatment::error)
- error(message);
- else if (config->undefinedSymbolTreatment ==
- UndefinedSymbolTreatment::warning)
- warn(message);
- else
- assert(false && "diagnostics make sense for -undefined error|warning only");
+namespace {
+struct UndefinedDiag {
+ struct SectionAndOffset {
+ const InputSection *isec;
+ uint64_t offset;
+ };
+
+ std::vector<SectionAndOffset> codeReferences;
+ std::vector<std::string> otherReferences;
+};
+
+MapVector<const Undefined *, UndefinedDiag> undefs;
+}
+
+void macho::reportPendingUndefinedSymbols() {
+ for (const auto &undef : undefs) {
+ const UndefinedDiag &locations = undef.second;
+
+ std::string message = "undefined symbol";
+ if (config->archMultiple)
+ message += (" for arch " + getArchitectureName(config->arch())).str();
+ message += ": " + toString(*undef.first);
+
+ const size_t maxUndefinedReferences = 3;
+ size_t i = 0;
+ for (const std::string &loc : locations.otherReferences) {
+ if (i >= maxUndefinedReferences)
+ break;
+ message += "\n>>> referenced by " + loc;
+ ++i;
+ }
+
+ for (const UndefinedDiag::SectionAndOffset &loc :
+ locations.codeReferences) {
+ if (i >= maxUndefinedReferences)
+ break;
+ // TODO: Get source file/line from debug information.
+ message += "\n>>> referenced by " + loc.isec->getLocation(loc.offset);
+ ++i;
+ }
+
+ size_t totalReferences =
+ locations.otherReferences.size() + locations.codeReferences.size();
+ if (totalReferences > i)
+ message +=
+ ("\n>>> referenced " + Twine(totalReferences - i) + " more times")
+ .str();
+
+ if (config->undefinedSymbolTreatment == UndefinedSymbolTreatment::error)
+ error(message);
+ else if (config->undefinedSymbolTreatment ==
+ UndefinedSymbolTreatment::warning)
+ warn(message);
+ else
+ assert(false &&
+ "diagnostics make sense for -undefined error|warning only");
+ }
+
+ // This function is called multiple times during execution. Clear the printed
+ // diagnostics to avoid printing the same things again the next time.
+ undefs.clear();
}
-void lld::macho::treatUndefinedSymbol(const Undefined &sym, StringRef source) {
+void macho::treatUndefinedSymbol(const Undefined &sym, StringRef source) {
if (recoverFromUndefinedSymbol(sym))
return;
- printUndefinedDiagnostic(sym.getName(), source);
+
+ undefs[&sym].otherReferences.push_back(source.str());
}
-void lld::macho::treatUndefinedSymbol(const Undefined &sym,
- const InputSection *isec,
- uint64_t offset) {
+void macho::treatUndefinedSymbol(const Undefined &sym, const InputSection *isec,
+ uint64_t offset) {
if (recoverFromUndefinedSymbol(sym))
return;
- // TODO: Get source file/line from debug information.
- printUndefinedDiagnostic(toString(sym), isec->getLocation(offset));
+ undefs[&sym].codeReferences.push_back({isec, offset});
}
std::unique_ptr<SymbolTable> macho::symtab;
diff --git a/lld/MachO/SymbolTable.h b/lld/MachO/SymbolTable.h
index a433f41318ea..0ecfa6dcd093 100644
--- a/lld/MachO/SymbolTable.h
+++ b/lld/MachO/SymbolTable.h
@@ -69,6 +69,9 @@ class SymbolTable {
std::vector<Symbol *> symVector;
};
+void reportPendingUndefinedSymbols();
+
+// Call reportPendingUndefinedSymbols() to emit diagnostics.
void treatUndefinedSymbol(const Undefined &, StringRef source);
void treatUndefinedSymbol(const Undefined &, const InputSection *,
uint64_t offset);
diff --git a/lld/MachO/Writer.cpp b/lld/MachO/Writer.cpp
index f2634076e080..74612409bc53 100644
--- a/lld/MachO/Writer.cpp
+++ b/lld/MachO/Writer.cpp
@@ -1133,6 +1133,7 @@ void Writer::writeCodeSignature() {
void Writer::writeOutputFile() {
TimeTraceScope timeScope("Write output file");
openFile();
+ reportPendingUndefinedSymbols();
if (errorCount())
return;
writeSections();
@@ -1155,6 +1156,7 @@ template <class LP> void Writer::run() {
scanRelocations();
// Do not proceed if there was an undefined symbol.
+ reportPendingUndefinedSymbols();
if (errorCount())
return;
diff --git a/lld/test/MachO/invalid/undef-multi.s b/lld/test/MachO/invalid/undef-multi.s
new file mode 100644
index 000000000000..c59bff2a5e63
--- /dev/null
+++ b/lld/test/MachO/invalid/undef-multi.s
@@ -0,0 +1,28 @@
+# REQUIRES: aarch64
+
+# RUN: llvm-mc -filetype=obj -triple=arm64-apple-darwin %s -o %t.o
+# RUN: not %lld -arch arm64 %t.o -o /dev/null 2>&1 | FileCheck -DFILE=%t.o %s
+
+# CHECK: error: undefined symbol: _undef
+# CHECK-NEXT: >>> referenced by [[FILE]]:(symbol _main+0x0)
+# CHECK-NEXT: >>> referenced by [[FILE]]:(symbol _foo+0x0)
+# CHECK-NEXT: >>> referenced by [[FILE]]:(symbol _bar+0x0)
+# CHECK-NEXT: >>> referenced 1 more times
+
+.globl _main
+_main:
+ b _undef
+
+.globl _foo
+_foo:
+ b _undef
+
+.global _bar
+_bar:
+ b _undef
+
+.globl _baz
+_baz:
+ b _undef
+
+.subsections_via_symbols
More information about the llvm-commits
mailing list