[llvm] 6be0b9a - [X86] Don't fold negative offset into 32-bit absolute address (e.g. movl $foo-1, %eax)

[Fangrui Song via llvm-commits]

Author: Fangrui Song
Date: 2020-12-30T18:47:26-08:00
New Revision: 6be0b9a8ddca0b2c937b31e0ee33fcbb7eb03dda

URL: https://github.com/llvm/llvm-project/commit/6be0b9a8ddca0b2c937b31e0ee33fcbb7eb03dda
DIFF: https://github.com/llvm/llvm-project/commit/6be0b9a8ddca0b2c937b31e0ee33fcbb7eb03dda.diff

LOG: [X86] Don't fold negative offset into 32-bit absolute address (e.g. movl $foo-1, %eax)

When building abseil-cpp `bin/absl_hash_test` with Clang in -fno-pic
mode, an instruction like `movl $foo-2147483648, $eax` may be produced
(subtracting a number from the address of a static variable). If foo's
address is smaller than 2147483648, GNU ld/gold/LLD will error because
R_X86_64_32 cannot represent a negative value.

```
using absl::Hash;
struct NoOp {
  template < typename HashCode >
  friend HashCode AbslHashValue(HashCode , NoOp );
};
template <typename> class HashIntTest : public testing::Test {};
TYPED_TEST_SUITE_P(HashIntTest);
TYPED_TEST_P(HashIntTest, BasicUsage) {
  if (std::numeric_limits< TypeParam >::min )
    EXPECT_NE(Hash< NoOp >()({}),
              Hash< TypeParam >()(std::numeric_limits< TypeParam >::min()));
}
REGISTER_TYPED_TEST_CASE_P(HashIntTest, BasicUsage);
using IntTypes = testing::Types< int32_t>;
INSTANTIATE_TYPED_TEST_CASE_P(My, HashIntTest, IntTypes);

ld: error: hash_test.cc:(function (anonymous namespace)::gtest_suite_HashIntTest_::BasicUsage<int>::TestBody(): .text+0x4E472): relocation R_X86_64_32 out of range: 18446744071564237392 is not in [0, 4294967295]; references absl::hash_internal::HashState::kSeed
```

Actually any negative offset is not allowed because the symbol address
can be zero (e.g. set by `-Wl,--defsym=foo=0`). So disallow such folding.

Reviewed By: pengfei

Differential Revision: https://reviews.llvm.org/D93931

Added: 
    

Modified: 
    llvm/lib/Target/X86/X86ISelLowering.cpp
    llvm/lib/Target/X86/X86ISelLowering.h
    llvm/test/CodeGen/X86/fold-add.ll

Removed: 
    


################################################################################
diff  --git a/llvm/lib/Target/X86/X86ISelLowering.cpp b/llvm/lib/Target/X86/X86ISelLowering.cpp
index f1803c429fbb..811318054fe1 100644
--- a/llvm/lib/Target/X86/X86ISelLowering.cpp
+++ b/llvm/lib/Target/X86/X86ISelLowering.cpp
@@ -19102,9 +19102,12 @@ SDValue X86TargetLowering::LowerGlobalOrExternal(SDValue Op, SelectionDAG &DAG,
   if (GV) {
     // Create a target global address if this is a global. If possible, fold the
     // offset into the global address reference. Otherwise, ADD it on later.
+    // Suppress the folding if Offset is negative: movl foo-1, %eax is not
+    // allowed because if the address of foo is 0, the ELF R_X86_64_32
+    // relocation will compute to a negative value, which is invalid.
     int64_t GlobalOffset = 0;
-    if (OpFlags == X86II::MO_NO_FLAG &&
-        X86::isOffsetSuitableForCodeModel(Offset, M)) {
+    if (OpFlags == X86II::MO_NO_FLAG && Offset >= 0 &&
+        X86::isOffsetSuitableForCodeModel(Offset, M, true)) {
       std::swap(GlobalOffset, Offset);
     }
     Result = DAG.getTargetGlobalAddress(GV, dl, PtrVT, GlobalOffset, OpFlags);

diff  --git a/llvm/lib/Target/X86/X86ISelLowering.h b/llvm/lib/Target/X86/X86ISelLowering.h
index faf2cc6fdba6..668132239dd3 100644
--- a/llvm/lib/Target/X86/X86ISelLowering.h
+++ b/llvm/lib/Target/X86/X86ISelLowering.h
@@ -855,7 +855,7 @@ namespace llvm {
     /// Returns true of the given offset can be
     /// fit into displacement field of the instruction.
     bool isOffsetSuitableForCodeModel(int64_t Offset, CodeModel::Model M,
-                                      bool hasSymbolicDisplacement = true);
+                                      bool hasSymbolicDisplacement);
 
     /// Determines whether the callee is required to pop its
     /// own arguments. Callee pop is necessary to support tail calls.

diff  --git a/llvm/test/CodeGen/X86/fold-add.ll b/llvm/test/CodeGen/X86/fold-add.ll
index fc21e3b6e372..5dfbccdbe9b5 100644
--- a/llvm/test/CodeGen/X86/fold-add.ll
+++ b/llvm/test/CodeGen/X86/fold-add.ll
@@ -54,10 +54,12 @@ entry:
   ret i64 add (i64 ptrtoint (i32* @foo to i64), i64 1701208431)
 }
 
+;; Test we don't emit movl foo-1, %eax. ELF R_X86_64_32 does not allow
+;; a negative value.
 define dso_local i64 @neg_1() #0 {
 ; CHECK-LABEL: neg_1:
 ; CHECK:       # %bb.0:
-; STATIC-NEXT:   movl $foo-1, %eax
+; STATIC-NEXT:   leaq foo-1(%rip), %rax
 ; PIC-NEXT:      leaq foo-1(%rip), %rax
 ; MSTATIC-NEXT:  movabsq $foo, %rax
 ; MSTATIC-NEXT:  decq %rax
@@ -68,10 +70,12 @@ entry:
   ret i64 add (i64 ptrtoint (i32* @foo to i64), i64 -1)
 }
 
+;; Test we don't emit movl foo-2147483648, %eax. ELF R_X86_64_32 does not allow
+;; a negative value.
 define dso_local i64 @neg_0x80000000() #0 {
 ; CHECK-LABEL: neg_0x80000000:
 ; CHECK:       # %bb.0:
-; STATIC-NEXT:   movl $foo-2147483648, %eax
+; STATIC-NEXT:   leaq foo-2147483648(%rip), %rax
 ; PIC-NEXT:      leaq foo-2147483648(%rip), %rax
 ; MSTATIC-NEXT:  movabsq $foo, %rax
 ; MSTATIC-NEXT:  addq $-2147483648, %rax