release/20.x: [RelLookupTableConverter] Drop unnamed_addr for GVs in entries to avoid generating GOTPCREL relocations (#146068) #146191
+66
−16
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
…id generating GOTPCREL relocations (llvm#146068) The entry in a relative lookup table is a global variable with a constant offset, such as `@gv`, `GEP @gv, 1`, and so on. We cannot only consider the case of a trivial global variable. This PR handles all cases using the existing `IsConstantOffsetFromGlobal` function. (cherry picked from commit c43282a)
|
@llvm/pr-subscribers-llvm-transforms Author: dianqk (dianqk) ChangesBackport c43282a Requested by: @dianqk Full diff: https://github.com/llvm/llvm-project/pull/146191.diff 2 Files Affected:
diff --git a/llvm/lib/Transforms/Utils/RelLookupTableConverter.cpp b/llvm/lib/Transforms/Utils/RelLookupTableConverter.cpp
index 4486cba2bf6c0..fe1fe391f5982 100644
--- a/llvm/lib/Transforms/Utils/RelLookupTableConverter.cpp
+++ b/llvm/lib/Transforms/Utils/RelLookupTableConverter.cpp
@@ -67,6 +67,20 @@ static bool shouldConvertToRelLookupTable(Module &M, GlobalVariable &GV) {
if (!ElemType->isPointerTy() || DL.getPointerTypeSizeInBits(ElemType) != 64)
return false;
+ SmallVector<GlobalVariable *, 4> GVOps;
+ Triple TT(M.getTargetTriple());
+ // FIXME: This should be removed in the future.
+ bool ShouldDropUnnamedAddr =
+ // Drop unnamed_addr to avoid matching pattern in
+ // `handleIndirectSymViaGOTPCRel`, which generates GOTPCREL relocations
+ // not supported by the GNU linker and LLD versions below 18 on aarch64.
+ TT.isAArch64()
+ // Apple's ld64 (and ld-prime on Xcode 15.2) miscompile something on
+ // x86_64-apple-darwin. See
+ // https://github.com/rust-lang/rust/issues/140686 and
+ // https://github.com/rust-lang/rust/issues/141306.
+ || (TT.isX86() && TT.isOSDarwin());
+
for (const Use &Op : Array->operands()) {
Constant *ConstOp = cast<Constant>(&Op);
GlobalValue *GVOp;
@@ -86,8 +100,15 @@ static bool shouldConvertToRelLookupTable(Module &M, GlobalVariable &GV) {
!GlovalVarOp->isDSOLocal() ||
!GlovalVarOp->isImplicitDSOLocal())
return false;
+
+ if (ShouldDropUnnamedAddr)
+ GVOps.push_back(GlovalVarOp);
}
+ if (ShouldDropUnnamedAddr)
+ for (auto *GVOp : GVOps)
+ GVOp->setUnnamedAddr(GlobalValue::UnnamedAddr::None);
+
return true;
}
@@ -109,24 +130,8 @@ static GlobalVariable *createRelLookupTable(Function &Func,
uint64_t Idx = 0;
SmallVector<Constant *, 64> RelLookupTableContents(NumElts);
- Triple TT(M.getTargetTriple());
- // FIXME: This should be removed in the future.
- bool ShouldDropUnnamedAddr =
- // Drop unnamed_addr to avoid matching pattern in
- // `handleIndirectSymViaGOTPCRel`, which generates GOTPCREL relocations
- // not supported by the GNU linker and LLD versions below 18 on aarch64.
- TT.isAArch64()
- // Apple's ld64 (and ld-prime on Xcode 15.2) miscompile something on
- // x86_64-apple-darwin. See
- // https://github.com/rust-lang/rust/issues/140686 and
- // https://github.com/rust-lang/rust/issues/141306.
- || (TT.isX86() && TT.isOSDarwin());
-
for (Use &Operand : LookupTableArr->operands()) {
Constant *Element = cast<Constant>(Operand);
- if (ShouldDropUnnamedAddr)
- if (auto *GlobalElement = dyn_cast<GlobalValue>(Element))
- GlobalElement->setUnnamedAddr(GlobalValue::UnnamedAddr::None);
Type *IntPtrTy = M.getDataLayout().getIntPtrType(M.getContext());
Constant *Base = llvm::ConstantExpr::getPtrToInt(RelLookupTable, IntPtrTy);
Constant *Target = llvm::ConstantExpr::getPtrToInt(Element, IntPtrTy);
diff --git a/llvm/test/Transforms/RelLookupTableConverter/unnamed_addr.ll b/llvm/test/Transforms/RelLookupTableConverter/unnamed_addr.ll
index 78b8a4aa126c9..322c38d090fe1 100644
--- a/llvm/test/Transforms/RelLookupTableConverter/unnamed_addr.ll
+++ b/llvm/test/Transforms/RelLookupTableConverter/unnamed_addr.ll
@@ -20,6 +20,14 @@
@y3 = internal unnamed_addr constant ptr @x0
@load_relative_2.table = private unnamed_addr constant [4 x ptr] [ptr @y3, ptr @y2, ptr @y1, ptr @y0]
+@b0 = private unnamed_addr constant [8 x i8] c"00000000"
+@b1 = private unnamed_addr constant [8 x i8] c"11111111"
+@b2 = private unnamed_addr constant [8 x i8] c"22222222"
+@load_relative_3.table = private unnamed_addr constant [3 x ptr] [
+ ptr getelementptr inbounds (i8, ptr @b0, i64 8),
+ ptr getelementptr inbounds (i8, ptr @b1, i64 8),
+ ptr getelementptr inbounds (i8, ptr @b2, i64 8)]
+
;.
; x86_64-apple-darwin: @a0 = private constant i32 0
; x86_64-apple-darwin: @a1 = private constant i32 1
@@ -34,6 +42,10 @@
; x86_64-apple-darwin: @y2 = internal constant ptr @x1
; x86_64-apple-darwin: @y3 = internal constant ptr @x0
; x86_64-apple-darwin: @load_relative_2.table.rel = private unnamed_addr constant [4 x i32] [i32 trunc (i64 sub (i64 ptrtoint (ptr @y3 to i64), i64 ptrtoint (ptr @load_relative_2.table.rel to i64)) to i32), i32 trunc (i64 sub (i64 ptrtoint (ptr @y2 to i64), i64 ptrtoint (ptr @load_relative_2.table.rel to i64)) to i32), i32 trunc (i64 sub (i64 ptrtoint (ptr @y1 to i64), i64 ptrtoint (ptr @load_relative_2.table.rel to i64)) to i32), i32 trunc (i64 sub (i64 ptrtoint (ptr @y0 to i64), i64 ptrtoint (ptr @load_relative_2.table.rel to i64)) to i32)], align 4
+; x86_64-apple-darwin: @b0 = private constant [8 x i8] c"00000000"
+; x86_64-apple-darwin: @b1 = private constant [8 x i8] c"11111111"
+; x86_64-apple-darwin: @b2 = private constant [8 x i8] c"22222222"
+; x86_64-apple-darwin: @load_relative_3.table.rel = private unnamed_addr constant [3 x i32] [i32 trunc (i64 sub (i64 ptrtoint (ptr getelementptr inbounds (i8, ptr @b0, i64 8) to i64), i64 ptrtoint (ptr @load_relative_3.table.rel to i64)) to i32), i32 trunc (i64 sub (i64 ptrtoint (ptr getelementptr inbounds (i8, ptr @b1, i64 8) to i64), i64 ptrtoint (ptr @load_relative_3.table.rel to i64)) to i32), i32 trunc (i64 sub (i64 ptrtoint (ptr getelementptr inbounds (i8, ptr @b2, i64 8) to i64), i64 ptrtoint (ptr @load_relative_3.table.rel to i64)) to i32)], align 4
;.
; aarch64: @a0 = private constant i32 0
; aarch64: @a1 = private constant i32 1
@@ -48,6 +60,10 @@
; aarch64: @y2 = internal constant ptr @x1
; aarch64: @y3 = internal constant ptr @x0
; aarch64: @load_relative_2.table.rel = private unnamed_addr constant [4 x i32] [i32 trunc (i64 sub (i64 ptrtoint (ptr @y3 to i64), i64 ptrtoint (ptr @load_relative_2.table.rel to i64)) to i32), i32 trunc (i64 sub (i64 ptrtoint (ptr @y2 to i64), i64 ptrtoint (ptr @load_relative_2.table.rel to i64)) to i32), i32 trunc (i64 sub (i64 ptrtoint (ptr @y1 to i64), i64 ptrtoint (ptr @load_relative_2.table.rel to i64)) to i32), i32 trunc (i64 sub (i64 ptrtoint (ptr @y0 to i64), i64 ptrtoint (ptr @load_relative_2.table.rel to i64)) to i32)], align 4
+; aarch64: @b0 = private constant [8 x i8] c"00000000"
+; aarch64: @b1 = private constant [8 x i8] c"11111111"
+; aarch64: @b2 = private constant [8 x i8] c"22222222"
+; aarch64: @load_relative_3.table.rel = private unnamed_addr constant [3 x i32] [i32 trunc (i64 sub (i64 ptrtoint (ptr getelementptr inbounds (i8, ptr @b0, i64 8) to i64), i64 ptrtoint (ptr @load_relative_3.table.rel to i64)) to i32), i32 trunc (i64 sub (i64 ptrtoint (ptr getelementptr inbounds (i8, ptr @b1, i64 8) to i64), i64 ptrtoint (ptr @load_relative_3.table.rel to i64)) to i32), i32 trunc (i64 sub (i64 ptrtoint (ptr getelementptr inbounds (i8, ptr @b2, i64 8) to i64), i64 ptrtoint (ptr @load_relative_3.table.rel to i64)) to i32)], align 4
;.
; x86_64: @a0 = private unnamed_addr constant i32 0
; x86_64: @a1 = private unnamed_addr constant i32 1
@@ -62,6 +78,10 @@
; x86_64: @y2 = internal unnamed_addr constant ptr @x1
; x86_64: @y3 = internal unnamed_addr constant ptr @x0
; x86_64: @load_relative_2.table.rel = private unnamed_addr constant [4 x i32] [i32 trunc (i64 sub (i64 ptrtoint (ptr @y3 to i64), i64 ptrtoint (ptr @load_relative_2.table.rel to i64)) to i32), i32 trunc (i64 sub (i64 ptrtoint (ptr @y2 to i64), i64 ptrtoint (ptr @load_relative_2.table.rel to i64)) to i32), i32 trunc (i64 sub (i64 ptrtoint (ptr @y1 to i64), i64 ptrtoint (ptr @load_relative_2.table.rel to i64)) to i32), i32 trunc (i64 sub (i64 ptrtoint (ptr @y0 to i64), i64 ptrtoint (ptr @load_relative_2.table.rel to i64)) to i32)], align 4
+; x86_64: @b0 = private unnamed_addr constant [8 x i8] c"00000000"
+; x86_64: @b1 = private unnamed_addr constant [8 x i8] c"11111111"
+; x86_64: @b2 = private unnamed_addr constant [8 x i8] c"22222222"
+; x86_64: @load_relative_3.table.rel = private unnamed_addr constant [3 x i32] [i32 trunc (i64 sub (i64 ptrtoint (ptr getelementptr inbounds (i8, ptr @b0, i64 8) to i64), i64 ptrtoint (ptr @load_relative_3.table.rel to i64)) to i32), i32 trunc (i64 sub (i64 ptrtoint (ptr getelementptr inbounds (i8, ptr @b1, i64 8) to i64), i64 ptrtoint (ptr @load_relative_3.table.rel to i64)) to i32), i32 trunc (i64 sub (i64 ptrtoint (ptr getelementptr inbounds (i8, ptr @b2, i64 8) to i64), i64 ptrtoint (ptr @load_relative_3.table.rel to i64)) to i32)], align 4
;.
define ptr @load_relative_1(i64 %offset) {
; x86_64-apple-darwin-LABEL: define ptr @load_relative_1(
@@ -110,6 +130,31 @@ define ptr @load_relative_2(i64 %offset) {
%load = load ptr, ptr %gep
ret ptr %load
}
+
+define ptr @load_relative_3(i64 %offset) {
+; x86_64-apple-darwin-LABEL: define ptr @load_relative_3(
+; x86_64-apple-darwin-SAME: i64 [[OFFSET:%.*]]) {
+; x86_64-apple-darwin-NEXT: [[RELTABLE_SHIFT:%.*]] = shl i64 [[OFFSET]], 2
+; x86_64-apple-darwin-NEXT: [[RELTABLE_INTRINSIC:%.*]] = call ptr @llvm.load.relative.i64(ptr @load_relative_3.table.rel, i64 [[RELTABLE_SHIFT]])
+; x86_64-apple-darwin-NEXT: ret ptr [[RELTABLE_INTRINSIC]]
+;
+; aarch64-LABEL: define ptr @load_relative_3(
+; aarch64-SAME: i64 [[OFFSET:%.*]]) {
+; aarch64-NEXT: [[RELTABLE_SHIFT:%.*]] = shl i64 [[OFFSET]], 2
+; aarch64-NEXT: [[RELTABLE_INTRINSIC:%.*]] = call ptr @llvm.load.relative.i64(ptr @load_relative_3.table.rel, i64 [[RELTABLE_SHIFT]])
+; aarch64-NEXT: ret ptr [[RELTABLE_INTRINSIC]]
+;
+; x86_64-LABEL: define ptr @load_relative_3(
+; x86_64-SAME: i64 [[OFFSET:%.*]]) {
+; x86_64-NEXT: [[RELTABLE_SHIFT:%.*]] = shl i64 [[OFFSET]], 2
+; x86_64-NEXT: [[RELTABLE_INTRINSIC:%.*]] = call ptr @llvm.load.relative.i64(ptr @load_relative_3.table.rel, i64 [[RELTABLE_SHIFT]])
+; x86_64-NEXT: ret ptr [[RELTABLE_INTRINSIC]]
+;
+ %gep = getelementptr inbounds [3 x ptr], ptr @load_relative_3.table, i64 0, i64 %offset
+ %load = load ptr, ptr %gep
+ ret ptr %load
+}
+
;.
; x86_64-apple-darwin: attributes #[[ATTR0:[0-9]+]] = { nocallback nofree nosync nounwind willreturn memory(argmem: read) }
;.
|
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Backport c43282a
Requested by: @dianqk