// function, including the funclet.
int64_t NumBytes = IsFunclet ? getWinEHFuncletFrameSize(MF)
: MFI.getStackSize();
- if (!AFI->hasStackFrame() && !windowsRequiresStackProbe(MF, NumBytes)) {
+
+ // Alignment is required for the parent frame, not the funclet
+ const bool NeedsRealignment =
+ NumBytes && !IsFunclet && RegInfo->hasStackRealignment(MF);
+ int64_t RealignmentPadding =
+ NeedsRealignment ? MFI.getMaxAlign().value() - 16 : 0;
+
+ if (!AFI->hasStackFrame() &&
+ !windowsRequiresStackProbe(MF, NumBytes + RealignmentPadding)) {
assert(!HasFP && "unexpected function without stack frame but with FP");
assert(!SVEStackSize &&
"unexpected function without stack frame but with SVE objects");
if (EmitCFI)
emitCalleeSavedGPRLocations(MBB, MBBI);
- if (windowsRequiresStackProbe(MF, NumBytes)) {
- uint64_t NumWords = NumBytes >> 4;
+ if (windowsRequiresStackProbe(MF, NumBytes + RealignmentPadding)) {
+ uint64_t NumWords = (NumBytes + RealignmentPadding) >> 4;
if (NeedsWinCFI) {
HasWinCFI = true;
// alloc_l can hold at most 256MB, so assume that NumBytes doesn't
.setMIFlag(MachineInstr::FrameSetup);
}
NumBytes = 0;
+
+ if (NeedsRealignment) {
+ BuildMI(MBB, MBBI, DL, TII->get(AArch64::ADDXri), AArch64::X15)
+ .addReg(AArch64::SP)
+ .addImm(RealignmentPadding)
+ .addImm(0);
+
+ uint64_t AndMask = ~(MFI.getMaxAlign().value() - 1);
+ BuildMI(MBB, MBBI, DL, TII->get(AArch64::ANDXri), AArch64::SP)
+ .addReg(AArch64::X15, RegState::Kill)
+ .addImm(AArch64_AM::encodeLogicalImmediate(AndMask, 64));
+ AFI->setStackRealigned(true);
+
+ // No need for SEH instructions here; if we're realigning the stack,
+ // we've set a frame pointer and already finished the SEH prologue.
+ assert(!NeedsWinCFI);
+ }
}
StackOffset AllocateBefore = SVEStackSize, AllocateAfter = {};
// Allocate space for the rest of the frame.
if (NumBytes) {
- // Alignment is required for the parent frame, not the funclet
- const bool NeedsRealignment =
- !IsFunclet && RegInfo->hasStackRealignment(MF);
unsigned scratchSPReg = AArch64::SP;
if (NeedsRealignment) {
--- /dev/null
+; RUN: llc < %s -mtriple=aarch64-windows | FileCheck %s
+
+define dso_local void @func() {
+entry:
+ %buf = alloca [8192 x i8], align 32
+ %arraydecay = getelementptr inbounds [8192 x i8], ptr %buf, i64 0, i64 0
+ call void @other(ptr noundef %arraydecay)
+ ret void
+}
+
+declare dso_local void @other(ptr noundef)
+
+; CHECK-LABEL: func:
+; CHECK-NEXT: .seh_proc func
+; 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, #513
+; CHECK-NEXT: bl __chkstk
+; CHECK-NEXT: sub sp, sp, x15, lsl #4
+; CHECK-NEXT: add x15, sp, #16
+; CHECK-NEXT: and sp, x15, #0xffffffffffffffe0