[AArch64][SVE] Fix epilogue for SVE when the stack is realigned.

[sdesmalen]

Summary

While deallocating the stackframe, the offset used to reload the
callee-saved registers was not pointing to the SVE callee-saves,
but rather to the whole SVE area.

+--------------+
| GRP callee   |   
|     saves    |   
+--------------+ <- FP
| SVE callee   |   
|     saves    |   
+--------------+ <- Should restore SVE callee saves from here
|  SVE Spills  |
|  and Locals  |
+--------------+ <- instead of from here.
|              |   
:              :   
|              |   
+--------------+ <- SP

llvm/lib/Target/AArch64/AArch64FrameLowering.cpp

StackOffset OffsetToCalleeSavesFromSP =
         StackOffset(OffsetToFirstCalleeSaveFromSP, MVT::nxv1i8) + SVEStackSize;
     DeallocateBefore = OffsetToCalleeSavesFromSP;
     DeallocateAfter = SVEStackSize - DeallocateBefore;
   }
 
   // Deallocate the SVE area.
   if (SVEStackSize) {
     if (AFI->isStackRealigned()) {
-      if (AFI->getSVECalleeSavedStackSize())
-        // Set SP to start of SVE area, from which the callee-save reloads
-        // can be done. The code below will deallocate the stack space
+      if (int64_t CalleeSavedSize = AFI->getSVECalleeSavedStackSize())
+        // Set SP to start of SVE callee-save area from which they can
+        // be reloaded. The code below will deallocate the stack space
         // space by moving FP -> SP.
         emitFrameOffset(MBB, RestoreBegin, DL, AArch64::SP, AArch64::FP,
-                        -SVEStackSize, TII, MachineInstr::FrameDestroy);
+                        {-CalleeSavedSize, MVT::nxv1i8}, TII,
+                        MachineInstr::FrameDestroy);
     } else {
       if (AFI->getSVECalleeSavedStackSize()) {
         // Deallocate the non-SVE locals first before we can deallocate (and
         // restore callee saves) from the SVE area.
         emitFrameOffset(MBB, RestoreBegin, DL, AArch64::SP, AArch64::SP,
                         {NumBytes, MVT::i8}, TII, MachineInstr::FrameDestroy);
         NumBytes = 0;
       }

llvm/test/CodeGen/AArch64/framelayout-sve.mir

 # CHECK-NEXT: STR_ZXI killed $z23, $sp, 2
 # CHECK-NEXT: STR_ZXI killed $z22, $sp, 3
 # CHECK:      STR_ZXI killed $z9, $sp, 16
 # CHECK-NEXT: STR_ZXI killed $z8, $sp, 17
 # CHECK-NEXT: $sp = frame-setup ADDVL_XXI $sp, -1
 # CHECK-NEXT: $[[TMP:x[0-9]+]] = frame-setup SUBXri $sp, 16, 0
 # CHECK-NEXT: $sp = ANDXri killed $[[TMP]]
 
-# CHECK:      $sp = frame-destroy ADDVL_XXI $fp, -19
+# CHECK:      $sp = frame-destroy ADDVL_XXI $fp, -18
 # CHECK-NEXT: $p15 = frame-destroy LDR_PXI $sp, 4
 # CHECK-NEXT: $p14 = frame-destroy LDR_PXI $sp, 5
 # CHECK:      $p5 = frame-destroy LDR_PXI $sp, 14
 # CHECK-NEXT: $p4 = frame-destroy LDR_PXI $sp, 15
 # CHECK-NEXT: $z23 = frame-destroy LDR_ZXI $sp, 2
 # CHECK-NEXT: $z22 = frame-destroy LDR_ZXI $sp, 3
 # CHECK:      $z9 = frame-destroy LDR_ZXI $sp, 16
 # CHECK-NEXT: $z8 = frame-destroy LDR_ZXI $sp, 17