[ELF] Reject error-prone meta characters in input section description

The lexer is overly permissive. When parsing file patterns in an input
section description and there is a missing `)`, we would accept many
non-sensible tokens (e.g. `}`) as patterns, leading to confusion, e.g.
`*(SORT_BY_ALIGNMENT(SORT_BY_NAME(.text*)) } PROVIDE_HIDDEN(__code_end = .)`
(#81804).

Ideally, the lexer should be stateful to report more errors like GNU ld
and get rid of hacks like `ScriptLexer::maybeSplitExpr`, but that would
require a large rewrite of the lexer. For now, just reject certain
non-wildcard meta characters to detect common mistakes.

Pull Request: https://github.com/llvm/llvm-project/pull/84130

2 files changed, 36 insertions, 10 deletions

diff --git a/lld/ELF/ScriptParser.cpp b/lld/ELF/ScriptParser.cpp
index f0ede1f..3bb1de9 100644
--- a/lld/ELF/ScriptParser.cpp
+++ b/lld/ELF/ScriptParser.cpp
@@ -717,9 +717,19 @@ SmallVector<SectionPattern, 0> ScriptParser::readInputSectionsList() {
 
     StringMatcher SectionMatcher;
     // Break if the next token is ), EXCLUDE_FILE, or SORT*.
-    while (!errorCount() && peek() != ")" && peek() != "EXCLUDE_FILE" &&
-           peekSortKind() == SortSectionPolicy::Default)
+    while (!errorCount() && peekSortKind() == SortSectionPolicy::Default) {
+      StringRef s = peek();
+      if (s == ")" || s == "EXCLUDE_FILE")
+        break;
+      // Detect common mistakes when certain non-wildcard meta characters are
+      // used without a closing ')'.
+      if (!s.empty() && strchr("(){}", s[0])) {
+        skip();
+        setError("section pattern is expected");
+        break;
+      }
       SectionMatcher.addPattern(unquote(next()));
+    }
 
     if (!SectionMatcher.empty())
       ret.push_back({std::move(excludeFilePat), std::move(SectionMatcher)});
diff --git a/lld/test/ELF/linkerscript/wildcards.s b/lld/test/ELF/linkerscript/wildcards.s
index 1eea278..e9ae722 100644
--- a/lld/test/ELF/linkerscript/wildcards.s
+++ b/lld/test/ELF/linkerscript/wildcards.s
@@ -91,26 +91,42 @@ SECTIONS {
   .text : { *([.]abc .ab[v-y] ) }
 }
 
-## Test a few non-wildcard meta characters rejected by GNU ld.
+## Test a few non-wildcard characters rejected by GNU ld.
 
 #--- lbrace.lds
-# RUN: ld.lld -T lbrace.lds a.o -o out
+# RUN: not ld.lld -T lbrace.lds a.o 2>&1 | FileCheck %s --check-prefix=ERR-LBRACE --match-full-lines --strict-whitespace
+#      ERR-LBRACE:{{.*}}: section pattern is expected
+# ERR-LBRACE-NEXT:>>>   .text : { *(.a* { ) }
+# ERR-LBRACE-NEXT:>>>                   ^
 SECTIONS {
   .text : { *(.a* { ) }
 }
 
+#--- lbrace2.lds
+# RUN: not ld.lld -T lbrace2.lds a.o 2>&1 | FileCheck %s --check-prefix=ERR-LBRACE2 --match-full-lines --strict-whitespace
+#      ERR-LBRACE2:{{.*}}: section pattern is expected
+# ERR-LBRACE2-NEXT:>>>   .text : { *(.a*{) }
+# ERR-LBRACE2-NEXT:>>>                  ^
+SECTIONS {
+  .text : { *(.a*{) }
+}
+
 #--- lparen.lds
-## ( is recognized as a section name pattern. Note, ( is rejected by GNU ld.
-# RUN: ld.lld -T lparen.lds a.o -o out
-# RUN: llvm-objdump --section-headers out | FileCheck --check-prefix=SEC-NO %s
+# RUN: not ld.lld -T lparen.lds a.o 2>&1 | FileCheck %s --check-prefix=ERR-LPAREN --match-full-lines --strict-whitespace
+#      ERR-LPAREN:{{.*}}: section pattern is expected
+# ERR-LPAREN-NEXT:>>>   .text : { *(.a* ( ) }
+# ERR-LPAREN-NEXT:>>>                   ^
 SECTIONS {
- .text : { *(.a* ( ) }
+  .text : { *(.a* ( ) }
 }
 
 #--- rbrace.lds
-# RUN: ld.lld -T rbrace.lds a.o -o out
+# RUN: not ld.lld -T rbrace.lds a.o 2>&1 | FileCheck %s --check-prefix=ERR-RBRACE --match-full-lines --strict-whitespace
+#      ERR-RBRACE:{{.*}}: section pattern is expected
+# ERR-RBRACE-NEXT:>>>   .text : { *(.a* x = 3; } ) }
+# ERR-RBRACE-NEXT:>>>                          ^
 SECTIONS {
-  .text : { *(.a* } ) }
+  .text : { *(.a* x = 3; } ) }
 }
 
 #--- rparen.lds