From abd335a339cb2c5aaf30463ff8451f1eb6e223c7 Mon Sep 17 00:00:00 2001
From: James Henderson <james.henderson@sony.com>
Date: Tue, 7 Apr 2020 11:51:26 +0100
Subject: [PATCH] [llvm-objdump] Fix unstable disassembly output for sections
 with same address

When two sections shared the same address, the disassembly code was
using pointer values when sorting (see the SectionRef less than
operator). Since those values aren't guaranteed to have a specific
order, this meant the disassembly code would sometimes change which
section to pick when finding symbols targeted by calls in fully linked
objects.

This change fixes the non-determinism, so that the same section is
always picked. This might have a negative impact in that now a section
without any symbol might be picked over a section with symbols, but this
will be addressed in a later commit.

Fixes https://bugs.llvm.org/show_bug.cgi?id=45411.

Reviewed by: grimar, MaskRay

Differential Revision: https://reviews.llvm.org/D77640
---
 .../X86/disassemble-same-section-addr.test         | 39 ++++++++++++++++++++++
 llvm/tools/llvm-objdump/llvm-objdump.cpp           |  2 +-
 2 files changed, 40 insertions(+), 1 deletion(-)
 create mode 100644 llvm/test/tools/llvm-objdump/X86/disassemble-same-section-addr.test

diff --git a/llvm/test/tools/llvm-objdump/X86/disassemble-same-section-addr.test b/llvm/test/tools/llvm-objdump/X86/disassemble-same-section-addr.test
new file mode 100644
index 0000000..cbb7788
--- /dev/null
+++ b/llvm/test/tools/llvm-objdump/X86/disassemble-same-section-addr.test
@@ -0,0 +1,39 @@
+## This test shows that llvm-objdump can handle sections with the same address
+## when symbols in those sections are referenced. In the past, the section
+## picked was non-deterministic, resulting in different symbols being found for
+## the section. The test uses YAML for the input, as we need a fully linked ELF
+## to reproduce the original failure.
+
+# RUN: yaml2obj %s -o %t1 -D SECTION=.second
+# RUN: llvm-objdump -d %t1 | FileCheck %s
+# RUN: yaml2obj %s -o %t2 -D SECTION=.first
+## FIXME: this case should print "<target>" too.
+# RUN: llvm-objdump -d %t2 | FileCheck %s --check-prefix=FAIL
+
+# CHECK: callq 0x5 <target>
+# FAIL:  callq 0x5{{$}}
+
+--- !ELF
+FileHeader:
+  Class:   ELFCLASS64
+  Data:    ELFDATA2LSB
+  Type:    ET_EXEC
+  Machine: EM_X86_64
+Sections:
+  - Name:    .caller
+    Type:    SHT_PROGBITS
+    Flags:   [SHF_ALLOC, SHF_EXECINSTR]
+    Address: 0x0
+    Content: e800000000 # Call instruction to next address.
+  - Name:    .first
+    Type:    SHT_PROGBITS
+    Flags:   [SHF_ALLOC, SHF_EXECINSTR]
+    Address: 0x5
+  - Name:    .second
+    Type:    SHT_PROGBITS
+    Flags:   [SHF_ALLOC, SHF_EXECINSTR]
+    Address: 0x5
+Symbols:
+  - Name:    target
+    Section: [[SECTION]]
+    Value:   0x5
diff --git a/llvm/tools/llvm-objdump/llvm-objdump.cpp b/llvm/tools/llvm-objdump/llvm-objdump.cpp
index 06a4978..2f9c6f1 100644
--- a/llvm/tools/llvm-objdump/llvm-objdump.cpp
+++ b/llvm/tools/llvm-objdump/llvm-objdump.cpp
@@ -1249,7 +1249,7 @@ static void disassembleObject(const Target *TheTarget, const ObjectFile *Obj,
   std::vector<std::pair<uint64_t, SectionRef>> SectionAddresses;
   for (SectionRef Sec : Obj->sections())
     SectionAddresses.emplace_back(Sec.getAddress(), Sec);
-  stable_sort(SectionAddresses);
+  llvm::stable_sort(SectionAddresses, llvm::less_first());
 
   // Linked executables (.exe and .dll files) typically don't include a real
   // symbol table but they might contain an export table.
-- 
2.7.4