[AArch64] Fix the upper limit for folded address offsets for COFF
In COFF, the immediates in IMAGE_REL_ARM64_PAGEBASE_REL21 relocations
are limited to 21 bit signed, i.e. the offset has to be less than
(1 << 20). The previous limit did intend to cover for this case, but
had missed that the 21 bit field was signed.
This fixes issue https://github.com/llvm/llvm-project/issues/54753.
Differential Revision: https://reviews.llvm.org/D123160
(cherry picked from commit 8d7a17b7c8b7151b8453903db96fc7f45d9b1bae)
diff --git a/llvm/lib/Target/AArch64/AArch64ISelLowering.cpp b/llvm/lib/Target/AArch64/AArch64ISelLowering.cpp
index 3008466..77260c8 100644
--- a/llvm/lib/Target/AArch64/AArch64ISelLowering.cpp
+++ b/llvm/lib/Target/AArch64/AArch64ISelLowering.cpp
@@ -17115,13 +17115,14 @@
// Check whether folding this offset is legal. It must not go out of bounds of
// the referenced object to avoid violating the code model, and must be
- // smaller than 2^21 because this is the largest offset expressible in all
- // object formats.
+ // smaller than 2^20 because this is the largest offset expressible in all
+ // object formats. (The IMAGE_REL_ARM64_PAGEBASE_REL21 relocation in COFF
+ // stores an immediate signed 21 bit offset.)
//
// This check also prevents us from folding negative offsets, which will end
// up being treated in the same way as large positive ones. They could also
// cause code model violations, and aren't really common enough to matter.
- if (Offset >= (1 << 21))
+ if (Offset >= (1 << 20))
return SDValue();
const GlobalValue *GV = GN->getGlobal();
diff --git a/llvm/lib/Target/AArch64/GISel/AArch64PreLegalizerCombiner.cpp b/llvm/lib/Target/AArch64/GISel/AArch64PreLegalizerCombiner.cpp
index d3f4130..3730030 100644
--- a/llvm/lib/Target/AArch64/GISel/AArch64PreLegalizerCombiner.cpp
+++ b/llvm/lib/Target/AArch64/GISel/AArch64PreLegalizerCombiner.cpp
@@ -162,13 +162,14 @@
// Check whether folding this offset is legal. It must not go out of bounds of
// the referenced object to avoid violating the code model, and must be
- // smaller than 2^21 because this is the largest offset expressible in all
- // object formats.
+ // smaller than 2^20 because this is the largest offset expressible in all
+ // object formats. (The IMAGE_REL_ARM64_PAGEBASE_REL21 relocation in COFF
+ // stores an immediate signed 21 bit offset.)
//
// This check also prevents us from folding negative offsets, which will end
// up being treated in the same way as large positive ones. They could also
// cause code model violations, and aren't really common enough to matter.
- if (NewOffset >= (1 << 21))
+ if (NewOffset >= (1 << 20))
return false;
Type *T = GV->getValueType();
diff --git a/llvm/test/CodeGen/AArch64/fold-global-offsets.ll b/llvm/test/CodeGen/AArch64/fold-global-offsets.ll
index c57de0d..aa5435c 100644
--- a/llvm/test/CodeGen/AArch64/fold-global-offsets.ll
+++ b/llvm/test/CodeGen/AArch64/fold-global-offsets.ll
@@ -84,23 +84,23 @@
define i64 @f5() {
; CHECK-LABEL: f5:
; CHECK: // %bb.0:
-; CHECK-NEXT: adrp x8, x2+2097144
-; CHECK-NEXT: ldr x0, [x8, :lo12:x2+2097144]
+; CHECK-NEXT: adrp x8, x2+1048568
+; CHECK-NEXT: ldr x0, [x8, :lo12:x2+1048568]
; CHECK-NEXT: ret
;
; GISEL-LABEL: f5:
; GISEL: // %bb.0:
-; GISEL-NEXT: adrp x8, x2+2097144
-; GISEL-NEXT: ldr x0, [x8, :lo12:x2+2097144]
+; GISEL-NEXT: adrp x8, x2+1048568
+; GISEL-NEXT: ldr x0, [x8, :lo12:x2+1048568]
; GISEL-NEXT: ret
- %l = load i64, i64* getelementptr ([16777216 x i64], [16777216 x i64]* @x2, i64 0, i64 262143)
+ %l = load i64, i64* getelementptr ([16777216 x i64], [16777216 x i64]* @x2, i64 0, i64 131071)
ret i64 %l
}
define i64 @f6() {
; CHECK-LABEL: f6:
; CHECK: // %bb.0:
-; CHECK-NEXT: mov w8, #2097152
+; CHECK-NEXT: mov w8, #1048576
; CHECK-NEXT: adrp x9, x2
; CHECK-NEXT: add x9, x9, :lo12:x2
; CHECK-NEXT: ldr x0, [x9, x8]
@@ -108,12 +108,12 @@
;
; GISEL-LABEL: f6:
; GISEL: // %bb.0:
-; GISEL-NEXT: mov w8, #2097152
+; GISEL-NEXT: mov w8, #1048576
; GISEL-NEXT: adrp x9, x2
; GISEL-NEXT: add x9, x9, :lo12:x2
; GISEL-NEXT: ldr x0, [x9, x8]
; GISEL-NEXT: ret
- %l = load i64, i64* getelementptr ([16777216 x i64], [16777216 x i64]* @x2, i64 0, i64 262144)
+ %l = load i64, i64* getelementptr ([16777216 x i64], [16777216 x i64]* @x2, i64 0, i64 131072)
ret i64 %l
}