[lld] 19cedd3 - [lld][WebAssembly] Fix for string merging + negative addends

[Sam Clegg via llvm-commits]

Author: Sam Clegg
Date: 2021-05-11T17:47:57-07:00
New Revision: 19cedd3cd3ab2144f7e477bb90d5f7ba8e500abb

URL: https://github.com/llvm/llvm-project/commit/19cedd3cd3ab2144f7e477bb90d5f7ba8e500abb
DIFF: https://github.com/llvm/llvm-project/commit/19cedd3cd3ab2144f7e477bb90d5f7ba8e500abb.diff

LOG: [lld][WebAssembly] Fix for string merging + negative addends

Don't include the relocation addend when calculating the
virtual address of a symbol.  Instead just pass the symbol's
offset and add the addend afterwards.

Without this fix we hit the `offset is outside the section`
error in MergeInputSegment::getSegmentPiece.

This fixes a real world error we were are seeing in emscripten.

Differential Revision: https://reviews.llvm.org/D102271

Added: 
    

Modified: 
    lld/test/wasm/merge-string.s
    lld/wasm/InputFiles.cpp
    lld/wasm/Symbols.cpp
    lld/wasm/Symbols.h

Removed: 
    


################################################################################
diff  --git a/lld/test/wasm/merge-string.s b/lld/test/wasm/merge-string.s
index af14b18283e2..c422bc7740f8 100644
--- a/lld/test/wasm/merge-string.s
+++ b/lld/test/wasm/merge-string.s
@@ -1,6 +1,12 @@
 // RUN: llvm-mc -filetype=obj -triple=wasm32-unknown-unknown %s -o %t.o
-// RUN: wasm-ld -O2 %t.o -o %t.wasm --no-gc-sections --no-entry
+// RUN: wasm-ld -O1 %t.o -o %t.wasm --no-gc-sections --no-entry
 // RUN: obj2yaml %t.wasm | FileCheck %s --check-prefixes=COMMON,MERGE
+
+// Check that the default is the same as -O1 (since we default to -O1)
+// RUN: wasm-ld %t.o -o %t.wasm --no-gc-sections --no-entry
+// RUN: obj2yaml %t.wasm | FileCheck %s --check-prefixes=COMMON,MERGE
+
+// Check that -O0 disables merging
 // RUN: wasm-ld -O0 %t.o -o %t2.wasm --no-gc-sections --no-entry
 // RUN: obj2yaml %t2.wasm | FileCheck --check-prefixes=COMMON,NOMERGE %s
 
@@ -14,6 +20,11 @@ bar:
         .asciz "bc"
         .size bar, 4
 
+        .section .rodata_relocs,"",@
+negative_addend:
+        .int32 foo-10
+        .size negative_addend, 4
+
 .globl foo
 .globl bar
 .export_name    foo, foo

diff  --git a/lld/wasm/InputFiles.cpp b/lld/wasm/InputFiles.cpp
index bfb60a32e21d..2cb5d59286e3 100644
--- a/lld/wasm/InputFiles.cpp
+++ b/lld/wasm/InputFiles.cpp
@@ -185,7 +185,7 @@ uint64_t ObjFile::calcNewValue(const WasmRelocation &reloc, uint64_t tombstone,
     if (D->segment && D->segment->outputSeg->isTLS())
       return D->getOutputSegmentOffset() + reloc.Addend;
 
-    uint64_t value = D->getVA(reloc.Addend);
+    uint64_t value = D->getVA() + reloc.Addend;
     if (reloc.Type == R_WASM_MEMORY_ADDR_LOCREL_I32) {
       const auto *segment = cast<InputSegment>(chunk);
       uint64_t p = segment->outputSeg->startVA + segment->outputSegmentOffset +

diff  --git a/lld/wasm/Symbols.cpp b/lld/wasm/Symbols.cpp
index 2c0f72b0504e..00fe754e3eaa 100644
--- a/lld/wasm/Symbols.cpp
+++ b/lld/wasm/Symbols.cpp
@@ -286,10 +286,10 @@ DefinedFunction::DefinedFunction(StringRef name, uint32_t flags, InputFile *f,
                      function ? &function->signature : nullptr),
       function(function) {}
 
-uint64_t DefinedData::getVA(uint64_t addend) const {
+uint64_t DefinedData::getVA() const {
   LLVM_DEBUG(dbgs() << "getVA: " << getName() << "\n");
   if (segment)
-    return segment->getVA(value + addend);
+    return segment->getVA(value);
   return value;
 }
 
@@ -301,7 +301,7 @@ void DefinedData::setVA(uint64_t value_) {
 
 uint64_t DefinedData::getOutputSegmentOffset() const {
   LLVM_DEBUG(dbgs() << "getOutputSegmentOffset: " << getName() << "\n");
-  return segment->outputSegmentOffset + value;
+  return segment->getOffset(value);
 }
 
 uint64_t DefinedData::getOutputSegmentIndex() const {

diff  --git a/lld/wasm/Symbols.h b/lld/wasm/Symbols.h
index e6968d45261a..8bc3be0d2247 100644
--- a/lld/wasm/Symbols.h
+++ b/lld/wasm/Symbols.h
@@ -290,7 +290,7 @@ class DefinedData : public DataSymbol {
   static bool classof(const Symbol *s) { return s->kind() == DefinedDataKind; }
 
   // Returns the output virtual address of a defined data symbol.
-  uint64_t getVA(uint64_t addend = 0) const;
+  uint64_t getVA() const;
   void setVA(uint64_t va);
 
   // Returns the offset of a defined data symbol within its OutputSegment.