From dee900ae599bf88d89b2e30fb7c94f18e877c1b4 Mon Sep 17 00:00:00 2001
From: George Rimar <grimar@accesssoftek.com>
Date: Fri, 26 Apr 2019 06:59:30 +0000
Subject: [PATCH] [LLD][ELF] - Do not remove empty sections referenced in
 LOADADDR/ADDR commands.

This is https://bugs.llvm.org//show_bug.cgi?id=38750.

If script references empty sections in LOADADDR/ADDR commands

.empty  : { *(.empty ) }
.text   : AT(LOADADDR (.empty) + SIZEOF (.empty)) { *(.text) }
then an empty section will be removed and LOADADDR/ADDR will evaluate to null.
It is not that user may expect from using of the generic script, what is a common case.

Differential revision: https://reviews.llvm.org/D54621

llvm-svn: 359279
---
 lld/ELF/LinkerScript.cpp                           | 12 ++++++++---
 lld/ELF/OutputSections.h                           |  1 +
 lld/ELF/ScriptParser.cpp                           |  2 ++
 .../linkerscript/empty-sections-expressions.test   | 24 ++++++++++++++++++++++
 4 files changed, 36 insertions(+), 3 deletions(-)
 create mode 100644 lld/test/ELF/linkerscript/empty-sections-expressions.test

diff --git a/lld/ELF/LinkerScript.cpp b/lld/ELF/LinkerScript.cpp
index da6dc82..dd72233 100644
--- a/lld/ELF/LinkerScript.cpp
+++ b/lld/ELF/LinkerScript.cpp
@@ -825,12 +825,18 @@ static bool isDiscardable(OutputSection &Sec) {
   if (!Sec.Phdrs.empty())
     return false;
 
-  // We do not want to remove sections that reference symbols in address and
-  // other expressions. We add script symbols as undefined, and want to ensure
-  // all of them are defined in the output, hence have to keep them.
+  // We do not want to remove OutputSections with expressions that reference
+  // symbols even if the OutputSection is empty. We want to ensure that the
+  // expressions can be evaluated and report an error if they cannot.
   if (Sec.ExpressionsUseSymbols)
     return false;
 
+  // OutputSections may be referenced by name in ADDR and LOADADDR expressions,
+  // as an empty Section can has a valid VMA and LMA we keep the OutputSection
+  // to maintain the integrity of the other Expression.
+  if (Sec.UsedInExpression)
+    return false;
+
   for (BaseCommand *Base : Sec.SectionCommands) {
     if (auto Cmd = dyn_cast<SymbolAssignment>(Base))
       // Don't create empty output sections just for unreferenced PROVIDE
diff --git a/lld/ELF/OutputSections.h b/lld/ELF/OutputSections.h
index d20d820..c072f2c 100644
--- a/lld/ELF/OutputSections.h
+++ b/lld/ELF/OutputSections.h
@@ -90,6 +90,7 @@ public:
   bool NonAlloc = false;
   bool Noload = false;
   bool ExpressionsUseSymbols = false;
+  bool UsedInExpression = false;
   bool InOverlay = false;
 
   void finalize();
diff --git a/lld/ELF/ScriptParser.cpp b/lld/ELF/ScriptParser.cpp
index 783d20c..741b32f 100644
--- a/lld/ELF/ScriptParser.cpp
+++ b/lld/ELF/ScriptParser.cpp
@@ -1154,6 +1154,7 @@ Expr ScriptParser::readPrimary() {
   if (Tok == "ADDR") {
     StringRef Name = readParenLiteral();
     OutputSection *Sec = Script->getOrCreateOutputSection(Name);
+    Sec->UsedInExpression = true;
     return [=]() -> ExprValue {
       checkIfExists(Sec, Location);
       return {Sec, false, 0, Location};
@@ -1230,6 +1231,7 @@ Expr ScriptParser::readPrimary() {
   if (Tok == "LOADADDR") {
     StringRef Name = readParenLiteral();
     OutputSection *Cmd = Script->getOrCreateOutputSection(Name);
+    Cmd->UsedInExpression = true;
     return [=] {
       checkIfExists(Cmd, Location);
       return Cmd->getLMA();
diff --git a/lld/test/ELF/linkerscript/empty-sections-expressions.test b/lld/test/ELF/linkerscript/empty-sections-expressions.test
new file mode 100644
index 0000000..3f1da48
--- /dev/null
+++ b/lld/test/ELF/linkerscript/empty-sections-expressions.test
@@ -0,0 +1,24 @@
+# REQUIRES: x86
+# RUN: echo ".text; nop; .data; .byte 0" \
+# RUN:   | llvm-mc -filetype=obj -triple=x86_64-pc-linux - -o %t.o
+# RUN: ld.lld -o %t --script %s %t.o
+# RUN: llvm-readelf -program-headers %t | FileCheck %s
+
+## Check we do not remove the empty output sections used in LOADADDR/ADDR
+## expressions and hence can evaluate the correct addresses.
+
+# CHECK:      Program Headers:
+# CHECK-NEXT:  Type Offset   VirtAddr           PhysAddr
+# CHECK-NEXT:  LOAD 0x001000 0x0000000000080000 0x0000000000080000
+# CHECK-NEXT:  LOAD 0x001001 0x0000000000080001 0x0000000000082000
+
+# CHECK:      Section to Segment mapping:
+# CHECK:       00 .empty .text
+# CHECK-NEXT:  01 .data
+
+SECTIONS {
+ . = 0x00080000;
+ .empty  : { *(.empty ) }
+ .text   : AT(LOADADDR(.empty) + SIZEOF(.empty)) { *(.text) }
+ .data   : AT(ADDR(.empty) + 0x2000) { *(.data) }
+}
-- 
2.7.4