[AArch64] Fix an immediate out of range for large realignments on Windows

Also add a missing FrameSetup flag on the existing add instruction.

This fixes https://github.com/llvm/llvm-project/issues/63701.

Differential Revision: https://reviews.llvm.org/D155447

diff --git a/llvm/lib/Target/AArch64/AArch64FrameLowering.cpp b/llvm/lib/Target/AArch64/AArch64FrameLowering.cpp
index f13344a..029b2ea 100644 (file)
--- a/llvm/lib/Target/AArch64/AArch64FrameLowering.cpp
+++ b/llvm/lib/Target/AArch64/AArch64FrameLowering.cpp
@@ -1739,10 +1739,22 @@ void AArch64FrameLowering::emitPrologue(MachineFunction &MF,
     NumBytes = 0;
 
     if (RealignmentPadding > 0) {
-      BuildMI(MBB, MBBI, DL, TII->get(AArch64::ADDXri), AArch64::X15)
-          .addReg(AArch64::SP)
-          .addImm(RealignmentPadding)
-          .addImm(0);
+      if (RealignmentPadding >= 4096) {
+        BuildMI(MBB, MBBI, DL, TII->get(AArch64::MOVi64imm))
+            .addReg(AArch64::X16, RegState::Define)
+            .addImm(RealignmentPadding)
+            .setMIFlags(MachineInstr::FrameSetup);
+        BuildMI(MBB, MBBI, DL, TII->get(AArch64::ADDXrr), AArch64::X15)
+            .addReg(AArch64::SP)
+            .addReg(AArch64::X16, RegState::Kill)
+            .setMIFlag(MachineInstr::FrameSetup);
+      } else {
+        BuildMI(MBB, MBBI, DL, TII->get(AArch64::ADDXri), AArch64::X15)
+            .addReg(AArch64::SP)
+            .addImm(RealignmentPadding)
+            .addImm(0)
+            .setMIFlag(MachineInstr::FrameSetup);
+      }
 
       uint64_t AndMask = ~(MFI.getMaxAlign().value() - 1);
       BuildMI(MBB, MBBI, DL, TII->get(AArch64::ANDXri), AArch64::SP)

diff --git a/llvm/test/CodeGen/AArch64/win-align-chkstk.ll b/llvm/test/CodeGen/AArch64/win-align-chkstk.ll
index 7c1c3db..5650d78 100644 (file)
--- a/llvm/test/CodeGen/AArch64/win-align-chkstk.ll
+++ b/llvm/test/CodeGen/AArch64/win-align-chkstk.ll
@@ -25,3 +25,28 @@ declare dso_local void @other(ptr noundef)
 ; CHECK-NEXT: sub sp, sp, x15, lsl #4
 ; CHECK-NEXT: add x15, sp, #16
 ; CHECK-NEXT: and sp, x15, #0xffffffffffffffe0
+
+define dso_local void @func2() {
+entry:
+  %buf = alloca [8192 x i8], align 8192
+  %arraydecay = getelementptr inbounds [8192 x i8], ptr %buf, i64 0, i64 0
+  call void @other(ptr noundef %arraydecay)
+  ret void
+}
+
+; CHECK-LABEL: func2:
+; CHECK-NEXT: .seh_proc func2
+; CHECK-NEXT: // %bb.0:
+; CHECK-NEXT: str x28, [sp, #-32]!
+; CHECK-NEXT: .seh_save_reg_x x28, 32
+; CHECK-NEXT: stp x29, x30, [sp, #8]
+; CHECK-NEXT: .seh_save_fplr 8
+; CHECK-NEXT: add x29, sp, #8
+; CHECK-NEXT: .seh_add_fp 8
+; CHECK-NEXT: .seh_endprologue
+; CHECK-NEXT: mov x15, #1533
+; CHECK-NEXT: bl __chkstk
+; CHECK-NEXT: sub sp, sp, x15, lsl #4
+; CHECK-NEXT: mov x16, #8176
+; CHECK-NEXT: add x15, sp, x16
+; CHECK-NEXT: and sp, x15, #0xffffffffffffe000