From 35aad41c1be05217281675373193d3512d650764 Mon Sep 17 00:00:00 2001
From: Rafael Espindola <rafael.espindola@gmail.com>
Date: Tue, 27 Mar 2018 17:09:23 +0000
Subject: [PATCH] Force SHF_MERGE optimizations with -r.

Some tools (dwarfdump for example) get confused by the current -O0 -r
output since it has multiple copies of .debug_str.

We cannot just merge sections with the same name as they can have
different sh_entsize.

We could have duplicated logic for merging sections based on name and
sh_entsize, but it seems better to just use the existing logic by
enabling optimizations.

llvm-svn: 328640
---
 lld/ELF/InputFiles.cpp        | 16 +++++++++---
 lld/test/ELF/merge-reloc-O0.s | 48 +++++++++++++++++++++++++++++++++++
 2 files changed, 61 insertions(+), 3 deletions(-)
 create mode 100644 lld/test/ELF/merge-reloc-O0.s

diff --git a/lld/ELF/InputFiles.cpp b/lld/ELF/InputFiles.cpp
index 7f676258cf64..c3cdb0996cdc 100644
--- a/lld/ELF/InputFiles.cpp
+++ b/lld/ELF/InputFiles.cpp
@@ -312,9 +312,19 @@ ObjFile<ELFT>::getShtGroupEntries(const Elf_Shdr &Sec) {
 }
 
 template <class ELFT> bool ObjFile<ELFT>::shouldMerge(const Elf_Shdr &Sec) {
-  // We don't merge sections if -O0 (default is -O1). This makes sometimes
-  // the linker significantly faster, although the output will be bigger.
-  if (Config->Optimize == 0)
+  // On a regular link we don't merge sections if -O0 (default is -O1). This
+  // sometimes makes the linker significantly faster, although the output will
+  // be bigger.
+  //
+  // Doing the same for -r would create a problem as it would combine sections
+  // with different sh_entsize. One option would be to just copy every SHF_MERGE
+  // section as is to the output. While this would produce a valid ELF file with
+  // usable SHF_MERGE sections, tools like (llvm-)?dwarfdump get confused when
+  // they see two .debug_str. We could have separate logic for combining
+  // SHF_MERGE sections based both on their name and sh_entsize, but that seems
+  // to be more trouble than it is worth. Instead, we just use the regular (-O1)
+  // logic for -r.
+  if (Config->Optimize == 0 && !Config->Relocatable)
     return false;
 
   // A mergeable section with size 0 is useless because they don't have
diff --git a/lld/test/ELF/merge-reloc-O0.s b/lld/test/ELF/merge-reloc-O0.s
new file mode 100644
index 000000000000..daf5c34b6c0a
--- /dev/null
+++ b/lld/test/ELF/merge-reloc-O0.s
@@ -0,0 +1,48 @@
+# REQUIRES: x86
+# RUN: llvm-mc -filetype=obj -triple=x86_64-pc-linux %s -o %t.o
+# RUN: ld.lld %t.o -r -o %t2.o -O0
+# RUN: llvm-readobj -s -section-data %t2.o | FileCheck %s
+
+# We combine just the sections with the same name and sh_entsize.
+
+# CHECK:      Name: .foo
+# CHECK-NEXT: Type: SHT_PROGBITS
+# CHECK-NEXT: Flags [
+# CHECK-NEXT:   SHF_ALLOC
+# CHECK-NEXT:   SHF_MERGE
+# CHECK-NEXT: ]
+# CHECK-NEXT: Address:
+# CHECK-NEXT: Offset:
+# CHECK-NEXT: Size: 16
+# CHECK-NEXT: Link:
+# CHECK-NEXT: Info:
+# CHECK-NEXT: AddressAlignment: 8
+# CHECK-NEXT: EntrySize: 8
+# CHECK-NEXT: SectionData (
+# CHECK-NEXT:   0000: 41000000 00000000 42000000 00000000
+# CHECK-NEXT: )
+
+# CHECK:      Name: .foo
+# CHECK-NEXT: Type: SHT_PROGBITS
+# CHECK-NEXT: Flags [
+# CHECK-NEXT:   SHF_ALLOC
+# CHECK-NEXT:   SHF_MERGE
+# CHECK-NEXT: ]
+# CHECK-NEXT: Address:
+# CHECK-NEXT: Offset:
+# CHECK-NEXT: Size: 8
+# CHECK-NEXT: Link:
+# CHECK-NEXT: Info:
+# CHECK-NEXT: AddressAlignment: 4
+# CHECK-NEXT: EntrySize: 4
+# CHECK-NEXT: SectionData (
+# CHECK-NEXT:   0000: 41000000 42000000
+# CHECK-NEXT: )
+
+        .section .foo, "aM",@progbits,8,unique,0
+        .quad 0x41
+        .section .foo, "aM",@progbits,8,unique,1
+        .quad 0x42
+        .section .foo, "aM",@progbits,4,unique,2
+        .long 0x41
+        .long 0x42
-- 
GitLab