MC asm parser: allow ?'s in symbol names, and handle @'s in names in MS asm

This is another (final?) stab at making us able to parse our own asm output
on Windows.

Symbols on Windows often contain @'s and ?'s in their names. Our asm parser
didn't like this. ?'s were not allowed, and @'s were intepreted as trying to
reference PLT/GOT/etc.

We can't just add quotes around the bad names, since e.g. for MinGW, we use gas
to assemble, and it doesn't like quotes in some places (notably in .def
directives).

This commit makes us allow ?'s in symbol names, and @'s in symbol names for MS
assembly.

Differential Revision: http://llvm-reviews.chandlerc.com/D1978

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@193000 91177308-0d34-0410-b5e6-96231b3b80d8

3 files changed, 57 insertions, 0 deletions

diff --git a/test/MC/COFF/tricky-names.ll b/test/MC/COFF/tricky-names.ll
new file mode 100644
index 0000000000..6e041d38d3
--- /dev/null
+++ b/test/MC/COFF/tricky-names.ll
@@ -0,0 +1,38 @@
+; Check how tricky symbols are printed in the asm output.
+; RUN: llc -mtriple=i686-pc-win32 %s -o - | FileCheck %s --check-prefix=ASM
+
+; Check that we can roundtrip these names through our assembler.
+; RUN: llc -mtriple=i686-pc-win32 %s -o - | llvm-mc -triple i686-pc-win32 -filetype=obj | llvm-readobj -t | FileCheck %s --check-prefix=READOBJ
+
+
+@"\01??__E_Generic_object@?$_Error_objects@H@std@@YAXXZ" = global i32 0
+@"\01__ZL16ExceptionHandlerP19_EXCEPTION_POINTERS@4" = global i32 0
+@"\01@foo.bar" = global i32 0
+
+define weak i32 @"\01??_B?$num_put@_WV?$back_insert_iterator@V?$basic_string@_WU?$char_traits@_W@std@@V?$allocator@_W@2@@std@@@std@@@std@@51"() section ".text" {
+  %a = load i32* @"\01??__E_Generic_object@?$_Error_objects@H@std@@YAXXZ"
+  %b = load i32* @"\01__ZL16ExceptionHandlerP19_EXCEPTION_POINTERS@4"
+  %c = load i32* @"\01@foo.bar"
+  %x = add i32 %a, %b
+  %y = add i32 %x, %c
+  ret i32 %y
+}
+
+; Check that these symbols are not quoted. They occur in output that gets passed to GAS.
+; ASM: .globl __ZL16ExceptionHandlerP19_EXCEPTION_POINTERS@4
+; ASM-NOT: .globl "__ZL16ExceptionHandlerP19_EXCEPTION_POINTERS@4"
+; ASM: .globl @foo.bar
+; ASM-NOT: .globl "@foo.bar"
+
+; READOBJ: Symbol
+; READOBJ: Name: .text$??_B?$num_put@_WV?$back_insert_iterator@V?$basic_string@_WU?$char_traits@_W@std@@V?$allocator@_W@2@@std@@@std@@@std@@51
+; READOBJ: Section: .text$??_B?$num_put@_WV?$back_insert_iterator@V?$basic_string@_WU?$char_traits@_W@std@@V?$allocator@_W@2@@std@@@std@@@std@@51
+; READOBJ: Symbol
+; READOBJ: Name: ??_B?$num_put@_WV?$back_insert_iterator@V?$basic_string@_WU?$char_traits@_W@std@@V?$allocator@_W@2@@std@@@std@@@std@@51
+; READOBJ: Section: .text$??_B?$num_put@_WV?$back_insert_iterator@V?$basic_string@_WU?$char_traits@_W@std@@V?$allocator@_W@2@@std@@@std@@@std@@51
+; READOBJ: Symbol
+; READOBJ: Name: ??__E_Generic_object@?$_Error_objects@H@std@@YAXXZ
+; READOBJ: Symbol
+; READOBJ: Name: __ZL16ExceptionHandlerP19_EXCEPTION_POINTERS@4
+; READOBJ: Symbol
+; READOBJ: Name: @foo.bar
diff --git a/test/MC/ELF/bad-relocation.s b/test/MC/ELF/bad-relocation.s
new file mode 100644
index 0000000000..1a66744ec8
--- /dev/null
+++ b/test/MC/ELF/bad-relocation.s
@@ -0,0 +1,7 @@
+// RUN: not llvm-mc -filetype=obj -triple i386-pc-linux-gnu %s -o /dev/null 2>&1 | FileCheck  %s
+
+// CHECK: error: invalid variant 'BADRELOC'
+
+        .text
+foo:
+	leal	.Lfoo@BADRELOC(%ebx), %eax
diff --git a/test/MC/ELF/symbol-names.s b/test/MC/ELF/symbol-names.s
new file mode 100644
index 0000000000..6459ac93cc
--- /dev/null
+++ b/test/MC/ELF/symbol-names.s
@@ -0,0 +1,12 @@
+// RUN: llvm-mc -triple i686-pc-linux -filetype=obj %s -o - | llvm-readobj -t | FileCheck %s
+
+// MC allows ?'s in symbol names as an extension.
+
+.text
+.globl foo?bar
+.type foo?bar, @function
+foo?bar:
+ret
+
+// CHECK: Symbol
+// CHECK: Name: foo?bar