[SystemZ] Implement the packed stack layout

Any llvm function with the "packed-stack" attribute will be compiled to use
the packed stack layout which reuses unused parts of the incoming register
save area. This is needed for building the Linux kernel.

Review: Ulrich Weigand
https://reviews.llvm.org/D70821

7 files changed, 274 insertions, 186 deletions

diff --git a/llvm/test/CodeGen/SystemZ/anyregcc-novec.ll b/llvm/test/CodeGen/SystemZ/anyregcc-novec.ll
index f7e2af91792..b37cd220ffe 100644
--- a/llvm/test/CodeGen/SystemZ/anyregcc-novec.ll
+++ b/llvm/test/CodeGen/SystemZ/anyregcc-novec.ll
@@ -5,14 +5,14 @@ define anyregcc void @anyregcc1() {
 entry:
 ;CHECK-LABEL: anyregcc1
 ;CHECK: stmg %r2, %r15, 16(%r15)
-;CHECK: aghi %r15, -256
-;CHECK: std %f0, 384(%r15)
+;CHECK: aghi %r15, -96
+;CHECK: std %f0, 224(%r15)
 ;CHECK: std %f1,
-;CHECK: std %f2, 392(%r15)
+;CHECK: std %f2, 232(%r15)
 ;CHECK: std %f3,
-;CHECK: std %f4, 400(%r15)
+;CHECK: std %f4, 240(%r15)
 ;CHECK: std %f5,
-;CHECK: std %f6, 408(%r15)
+;CHECK: std %f6, 248(%r15)
 ;CHECK: std %f7,
 ;CHECK: std %f8,
 ;CHECK: std %f9,
@@ -26,10 +26,10 @@ entry:
 ;CHECK: .cfi_offset %f2, -24
 ;CHECK: .cfi_offset %f4, -16
 ;CHECK: .cfi_offset %f6, -8
-;CHECK: ld %f0, 384(%r15)
-;CHECK: ld %f2, 392(%r15)
-;CHECK: ld %f4, 400(%r15)
-;CHECK: ld %f6, 408(%r15)
+;CHECK: ld %f0, 224(%r15)
+;CHECK: ld %f2, 232(%r15)
+;CHECK: ld %f4, 240(%r15)
+;CHECK: ld %f6, 248(%r15)
   call void asm sideeffect "", "~{r0},~{r1},~{r2},~{r3},~{r4},~{r5},~{r6},~{r7},~{r8},~{r9},~{r10},~{r11},~{r12},~{r13},~{r14},~{f0},~{f1},~{f2},~{f3},~{f4},~{f5},~{f6},~{f7},~{f8},~{f9},~{f10},~{f11},~{f12},~{f13},~{f14},~{f15}"() nounwind
   ret void
 }
diff --git a/llvm/test/CodeGen/SystemZ/frame-02.ll b/llvm/test/CodeGen/SystemZ/frame-02.ll
index 411a0826d84..d7160483b53 100644
--- a/llvm/test/CodeGen/SystemZ/frame-02.ll
+++ b/llvm/test/CodeGen/SystemZ/frame-02.ll
@@ -4,20 +4,20 @@
 
 ; This function should require all FPRs, but no other spill slots.
 ; We need to save and restore 8 of the 16 FPRs, so the frame size
-; should be exactly 160 + 8 * 8 = 224.  The CFA offset is 160
-; (the caller-allocated part of the frame) + 224.
+; should be exactly 8 * 8 = 64.  The CFA offset is 160
+; (the caller-allocated part of the frame) + 64.
 define void @f1(float *%ptr) {
 ; CHECK-LABEL: f1:
-; CHECK: aghi %r15, -224
-; CHECK: .cfi_def_cfa_offset 384
-; CHECK: std %f8, 216(%r15)
-; CHECK: std %f9, 208(%r15)
-; CHECK: std %f10, 200(%r15)
-; CHECK: std %f11, 192(%r15)
-; CHECK: std %f12, 184(%r15)
-; CHECK: std %f13, 176(%r15)
-; CHECK: std %f14, 168(%r15)
-; CHECK: std %f15, 160(%r15)
+; CHECK: aghi %r15, -64
+; CHECK: .cfi_def_cfa_offset 224
+; CHECK: std %f8, 56(%r15)
+; CHECK: std %f9, 48(%r15)
+; CHECK: std %f10, 40(%r15)
+; CHECK: std %f11, 32(%r15)
+; CHECK: std %f12, 24(%r15)
+; CHECK: std %f13, 16(%r15)
+; CHECK: std %f14, 8(%r15)
+; CHECK: std %f15, 0(%r15)
 ; CHECK: .cfi_offset %f8, -168
 ; CHECK: .cfi_offset %f9, -176
 ; CHECK: .cfi_offset %f10, -184
@@ -27,15 +27,15 @@ define void @f1(float *%ptr) {
 ; CHECK: .cfi_offset %f14, -216
 ; CHECK: .cfi_offset %f15, -224
 ; ...main function body...
-; CHECK: ld %f8, 216(%r15)
-; CHECK: ld %f9, 208(%r15)
-; CHECK: ld %f10, 200(%r15)
-; CHECK: ld %f11, 192(%r15)
-; CHECK: ld %f12, 184(%r15)
-; CHECK: ld %f13, 176(%r15)
-; CHECK: ld %f14, 168(%r15)
-; CHECK: ld %f15, 160(%r15)
-; CHECK: aghi %r15, 224
+; CHECK: ld %f8, 56(%r15)
+; CHECK: ld %f9, 48(%r15)
+; CHECK: ld %f10, 40(%r15)
+; CHECK: ld %f11, 32(%r15)
+; CHECK: ld %f12, 24(%r15)
+; CHECK: ld %f13, 16(%r15)
+; CHECK: ld %f14, 8(%r15)
+; CHECK: ld %f15, 0(%r15)
+; CHECK: aghi %r15, 64
 ; CHECK: br %r14
   %l0 = load volatile float, float *%ptr
   %l1 = load volatile float, float *%ptr
@@ -92,15 +92,15 @@ define void @f1(float *%ptr) {
 ; so %f15 is the one that gets dropped.
 define void @f2(float *%ptr) {
 ; CHECK-LABEL: f2:
-; CHECK: aghi %r15, -216
-; CHECK: .cfi_def_cfa_offset 376
-; CHECK: std %f8, 208(%r15)
-; CHECK: std %f9, 200(%r15)
-; CHECK: std %f10, 192(%r15)
-; CHECK: std %f11, 184(%r15)
-; CHECK: std %f12, 176(%r15)
-; CHECK: std %f13, 168(%r15)
-; CHECK: std %f14, 160(%r15)
+; CHECK: aghi %r15, -56
+; CHECK: .cfi_def_cfa_offset 216
+; CHECK: std %f8, 48(%r15)
+; CHECK: std %f9, 40(%r15)
+; CHECK: std %f10, 32(%r15)
+; CHECK: std %f11, 24(%r15)
+; CHECK: std %f12, 16(%r15)
+; CHECK: std %f13, 8(%r15)
+; CHECK: std %f14, 0(%r15)
 ; CHECK: .cfi_offset %f8, -168
 ; CHECK: .cfi_offset %f9, -176
 ; CHECK: .cfi_offset %f10, -184
@@ -110,14 +110,14 @@ define void @f2(float *%ptr) {
 ; CHECK: .cfi_offset %f14, -216
 ; CHECK-NOT: %f15
 ; ...main function body...
-; CHECK: ld %f8, 208(%r15)
-; CHECK: ld %f9, 200(%r15)
-; CHECK: ld %f10, 192(%r15)
-; CHECK: ld %f11, 184(%r15)
-; CHECK: ld %f12, 176(%r15)
-; CHECK: ld %f13, 168(%r15)
-; CHECK: ld %f14, 160(%r15)
-; CHECK: aghi %r15, 216
+; CHECK: ld %f8, 48(%r15)
+; CHECK: ld %f9, 40(%r15)
+; CHECK: ld %f10, 32(%r15)
+; CHECK: ld %f11, 24(%r15)
+; CHECK: ld %f12, 16(%r15)
+; CHECK: ld %f13, 8(%r15)
+; CHECK: ld %f14, 0(%r15)
+; CHECK: aghi %r15, 56
 ; CHECK: br %r14
   %l0 = load volatile float, float *%ptr
   %l1 = load volatile float, float *%ptr
@@ -170,9 +170,9 @@ define void @f2(float *%ptr) {
 ; Like f1, but should require only one call-saved FPR.
 define void @f3(float *%ptr) {
 ; CHECK-LABEL: f3:
-; CHECK: aghi %r15, -168
-; CHECK: .cfi_def_cfa_offset 328
-; CHECK: std %f8, 160(%r15)
+; CHECK: aghi %r15, -8
+; CHECK: .cfi_def_cfa_offset 168
+; CHECK: std %f8, 0(%r15)
 ; CHECK: .cfi_offset %f8, -168
 ; CHECK-NOT: %f9
 ; CHECK-NOT: %f10
@@ -182,8 +182,8 @@ define void @f3(float *%ptr) {
 ; CHECK-NOT: %f14
 ; CHECK-NOT: %f15
 ; ...main function body...
-; CHECK: ld %f8, 160(%r15)
-; CHECK: aghi %r15, 168
+; CHECK: ld %f8, 0(%r15)
+; CHECK: aghi %r15, 8
 ; CHECK: br %r14
   %l0 = load volatile float, float *%ptr
   %l1 = load volatile float, float *%ptr
diff --git a/llvm/test/CodeGen/SystemZ/frame-03.ll b/llvm/test/CodeGen/SystemZ/frame-03.ll
index 28826150e78..ce2e0244457 100644
--- a/llvm/test/CodeGen/SystemZ/frame-03.ll
+++ b/llvm/test/CodeGen/SystemZ/frame-03.ll
@@ -6,20 +6,20 @@
 
 ; This function should require all FPRs, but no other spill slots.
 ; We need to save and restore 8 of the 16 FPRs, so the frame size
-; should be exactly 160 + 8 * 8 = 224.  The CFA offset is 160
-; (the caller-allocated part of the frame) + 224.
+; should be exactly 8 * 8 = 64.  The CFA offset is 160
+; (the caller-allocated part of the frame) + 64.
 define void @f1(double *%ptr) {
 ; CHECK-LABEL: f1:
-; CHECK: aghi %r15, -224
-; CHECK: .cfi_def_cfa_offset 384
-; CHECK: std %f8, 216(%r15)
-; CHECK: std %f9, 208(%r15)
-; CHECK: std %f10, 200(%r15)
-; CHECK: std %f11, 192(%r15)
-; CHECK: std %f12, 184(%r15)
-; CHECK: std %f13, 176(%r15)
-; CHECK: std %f14, 168(%r15)
-; CHECK: std %f15, 160(%r15)
+; CHECK: aghi %r15, -64
+; CHECK: .cfi_def_cfa_offset 224
+; CHECK: std %f8, 56(%r15)
+; CHECK: std %f9, 48(%r15)
+; CHECK: std %f10, 40(%r15)
+; CHECK: std %f11, 32(%r15)
+; CHECK: std %f12, 24(%r15)
+; CHECK: std %f13, 16(%r15)
+; CHECK: std %f14, 8(%r15)
+; CHECK: std %f15, 0(%r15)
 ; CHECK: .cfi_offset %f8, -168
 ; CHECK: .cfi_offset %f9, -176
 ; CHECK: .cfi_offset %f10, -184
@@ -29,15 +29,15 @@ define void @f1(double *%ptr) {
 ; CHECK: .cfi_offset %f14, -216
 ; CHECK: .cfi_offset %f15, -224
 ; ...main function body...
-; CHECK: ld %f8, 216(%r15)
-; CHECK: ld %f9, 208(%r15)
-; CHECK: ld %f10, 200(%r15)
-; CHECK: ld %f11, 192(%r15)
-; CHECK: ld %f12, 184(%r15)
-; CHECK: ld %f13, 176(%r15)
-; CHECK: ld %f14, 168(%r15)
-; CHECK: ld %f15, 160(%r15)
-; CHECK: aghi %r15, 224
+; CHECK: ld %f8, 56(%r15)
+; CHECK: ld %f9, 48(%r15)
+; CHECK: ld %f10, 40(%r15)
+; CHECK: ld %f11, 32(%r15)
+; CHECK: ld %f12, 24(%r15)
+; CHECK: ld %f13, 16(%r15)
+; CHECK: ld %f14, 8(%r15)
+; CHECK: ld %f15, 0(%r15)
+; CHECK: aghi %r15, 64
 ; CHECK: br %r14
   %l0 = load volatile double, double *%ptr
   %l1 = load volatile double, double *%ptr
@@ -94,15 +94,15 @@ define void @f1(double *%ptr) {
 ; so %f15 is the one that gets dropped.
 define void @f2(double *%ptr) {
 ; CHECK-LABEL: f2:
-; CHECK: aghi %r15, -216
-; CHECK: .cfi_def_cfa_offset 376
-; CHECK: std %f8, 208(%r15)
-; CHECK: std %f9, 200(%r15)
-; CHECK: std %f10, 192(%r15)
-; CHECK: std %f11, 184(%r15)
-; CHECK: std %f12, 176(%r15)
-; CHECK: std %f13, 168(%r15)
-; CHECK: std %f14, 160(%r15)
+; CHECK: aghi %r15, -56
+; CHECK: .cfi_def_cfa_offset 216
+; CHECK: std %f8, 48(%r15)
+; CHECK: std %f9, 40(%r15)
+; CHECK: std %f10, 32(%r15)
+; CHECK: std %f11, 24(%r15)
+; CHECK: std %f12, 16(%r15)
+; CHECK: std %f13, 8(%r15)
+; CHECK: std %f14, 0(%r15)
 ; CHECK: .cfi_offset %f8, -168
 ; CHECK: .cfi_offset %f9, -176
 ; CHECK: .cfi_offset %f10, -184
@@ -112,14 +112,14 @@ define void @f2(double *%ptr) {
 ; CHECK: .cfi_offset %f14, -216
 ; CHECK-NOT: %f15
 ; ...main function body...
-; CHECK: ld %f8, 208(%r15)
-; CHECK: ld %f9, 200(%r15)
-; CHECK: ld %f10, 192(%r15)
-; CHECK: ld %f11, 184(%r15)
-; CHECK: ld %f12, 176(%r15)
-; CHECK: ld %f13, 168(%r15)
-; CHECK: ld %f14, 160(%r15)
-; CHECK: aghi %r15, 216
+; CHECK: ld %f8, 48(%r15)
+; CHECK: ld %f9, 40(%r15)
+; CHECK: ld %f10, 32(%r15)
+; CHECK: ld %f11, 24(%r15)
+; CHECK: ld %f12, 16(%r15)
+; CHECK: ld %f13, 8(%r15)
+; CHECK: ld %f14, 0(%r15)
+; CHECK: aghi %r15, 56
 ; CHECK: br %r14
   %l0 = load volatile double, double *%ptr
   %l1 = load volatile double, double *%ptr
@@ -172,9 +172,9 @@ define void @f2(double *%ptr) {
 ; Like f1, but should require only one call-saved FPR.
 define void @f3(double *%ptr) {
 ; CHECK-LABEL: f3:
-; CHECK: aghi %r15, -168
-; CHECK: .cfi_def_cfa_offset 328
-; CHECK: std %f8, 160(%r15)
+; CHECK: aghi %r15, -8
+; CHECK: .cfi_def_cfa_offset 168
+; CHECK: std %f8, 0(%r15)
 ; CHECK: .cfi_offset %f8, -168
 ; CHECK-NOT: %f9
 ; CHECK-NOT: %f10
@@ -184,8 +184,8 @@ define void @f3(double *%ptr) {
 ; CHECK-NOT: %f14
 ; CHECK-NOT: %f15
 ; ...main function body...
-; CHECK: ld %f8, 160(%r15)
-; CHECK: aghi %r15, 168
+; CHECK: ld %f8, 0(%r15)
+; CHECK: aghi %r15, 8
 ; CHECK: br %r14
   %l0 = load volatile double, double *%ptr
   %l1 = load volatile double, double *%ptr
diff --git a/llvm/test/CodeGen/SystemZ/frame-04.ll b/llvm/test/CodeGen/SystemZ/frame-04.ll
index 5e1b29f570c..ae9c53a7ddc 100644
--- a/llvm/test/CodeGen/SystemZ/frame-04.ll
+++ b/llvm/test/CodeGen/SystemZ/frame-04.ll
@@ -5,20 +5,20 @@
 
 ; This function should require all FPRs, but no other spill slots.
 ; We need to save and restore 8 of the 16 FPRs, so the frame size
-; should be exactly 160 + 8 * 8 = 224.  The CFA offset is 160
-; (the caller-allocated part of the frame) + 224.
+; should be exactly 8 * 8 = 64.  The CFA offset is 160
+; (the caller-allocated part of the frame) + 64.
 define void @f1(fp128 *%ptr) {
 ; CHECK-LABEL: f1:
-; CHECK: aghi %r15, -224
-; CHECK: .cfi_def_cfa_offset 384
-; CHECK: std %f8, 216(%r15)
-; CHECK: std %f9, 208(%r15)
-; CHECK: std %f10, 200(%r15)
-; CHECK: std %f11, 192(%r15)
-; CHECK: std %f12, 184(%r15)
-; CHECK: std %f13, 176(%r15)
-; CHECK: std %f14, 168(%r15)
-; CHECK: std %f15, 160(%r15)
+; CHECK: aghi %r15, -64
+; CHECK: .cfi_def_cfa_offset 224
+; CHECK: std %f8, 56(%r15)
+; CHECK: std %f9, 48(%r15)
+; CHECK: std %f10, 40(%r15)
+; CHECK: std %f11, 32(%r15)
+; CHECK: std %f12, 24(%r15)
+; CHECK: std %f13, 16(%r15)
+; CHECK: std %f14, 8(%r15)
+; CHECK: std %f15, 0(%r15)
 ; CHECK: .cfi_offset %f8, -168
 ; CHECK: .cfi_offset %f9, -176
 ; CHECK: .cfi_offset %f10, -184
@@ -28,15 +28,15 @@ define void @f1(fp128 *%ptr) {
 ; CHECK: .cfi_offset %f14, -216
 ; CHECK: .cfi_offset %f15, -224
 ; ...main function body...
-; CHECK: ld %f8, 216(%r15)
-; CHECK: ld %f9, 208(%r15)
-; CHECK: ld %f10, 200(%r15)
-; CHECK: ld %f11, 192(%r15)
-; CHECK: ld %f12, 184(%r15)
-; CHECK: ld %f13, 176(%r15)
-; CHECK: ld %f14, 168(%r15)
-; CHECK: ld %f15, 160(%r15)
-; CHECK: aghi %r15, 224
+; CHECK: ld %f8, 56(%r15)
+; CHECK: ld %f9, 48(%r15)
+; CHECK: ld %f10, 40(%r15)
+; CHECK: ld %f11, 32(%r15)
+; CHECK: ld %f12, 24(%r15)
+; CHECK: ld %f13, 16(%r15)
+; CHECK: ld %f14, 8(%r15)
+; CHECK: ld %f15, 0(%r15)
+; CHECK: aghi %r15, 64
 ; CHECK: br %r14
   %l0 = load volatile fp128, fp128 *%ptr
   %l1 = load volatile fp128, fp128 *%ptr
@@ -69,14 +69,14 @@ define void @f1(fp128 *%ptr) {
 ; so %f13+%f15 is the pair that gets dropped.
 define void @f2(fp128 *%ptr) {
 ; CHECK-LABEL: f2:
-; CHECK: aghi %r15, -208
-; CHECK: .cfi_def_cfa_offset 368
-; CHECK: std %f8, 200(%r15)
-; CHECK: std %f9, 192(%r15)
-; CHECK: std %f10, 184(%r15)
-; CHECK: std %f11, 176(%r15)
-; CHECK: std %f12, 168(%r15)
-; CHECK: std %f14, 160(%r15)
+; CHECK: aghi %r15, -48
+; CHECK: .cfi_def_cfa_offset 208
+; CHECK: std %f8, 40(%r15)
+; CHECK: std %f9, 32(%r15)
+; CHECK: std %f10, 24(%r15)
+; CHECK: std %f11, 16(%r15)
+; CHECK: std %f12, 8(%r15)
+; CHECK: std %f14, 0(%r15)
 ; CHECK: .cfi_offset %f8, -168
 ; CHECK: .cfi_offset %f9, -176
 ; CHECK: .cfi_offset %f10, -184
@@ -86,13 +86,13 @@ define void @f2(fp128 *%ptr) {
 ; CHECK-NOT: %f13
 ; CHECK-NOT: %f15
 ; ...main function body...
-; CHECK: ld %f8, 200(%r15)
-; CHECK: ld %f9, 192(%r15)
-; CHECK: ld %f10, 184(%r15)
-; CHECK: ld %f11, 176(%r15)
-; CHECK: ld %f12, 168(%r15)
-; CHECK: ld %f14, 160(%r15)
-; CHECK: aghi %r15, 208
+; CHECK: ld %f8, 40(%r15)
+; CHECK: ld %f9, 32(%r15)
+; CHECK: ld %f10, 24(%r15)
+; CHECK: ld %f11, 16(%r15)
+; CHECK: ld %f12, 8(%r15)
+; CHECK: ld %f14, 0(%r15)
+; CHECK: aghi %r15, 48
 ; CHECK: br %r14
   %l0 = load volatile fp128, fp128 *%ptr
   %l1 = load volatile fp128, fp128 *%ptr
@@ -122,10 +122,10 @@ define void @f2(fp128 *%ptr) {
 ; numerical order so the pair should be %f8+%f10.
 define void @f3(fp128 *%ptr) {
 ; CHECK-LABEL: f3:
-; CHECK: aghi %r15, -176
-; CHECK: .cfi_def_cfa_offset 336
-; CHECK: std %f8, 168(%r15)
-; CHECK: std %f10, 160(%r15)
+; CHECK: aghi %r15, -16
+; CHECK: .cfi_def_cfa_offset 176
+; CHECK: std %f8, 8(%r15)
+; CHECK: std %f10, 0(%r15)
 ; CHECK: .cfi_offset %f8, -168
 ; CHECK: .cfi_offset %f10, -176
 ; CHECK-NOT: %f9
@@ -135,9 +135,9 @@ define void @f3(fp128 *%ptr) {
 ; CHECK-NOT: %f14
 ; CHECK-NOT: %f15
 ; ...main function body...
-; CHECK: ld %f8, 168(%r15)
-; CHECK: ld %f10, 160(%r15)
-; CHECK: aghi %r15, 176
+; CHECK: ld %f8, 8(%r15)
+; CHECK: ld %f10, 0(%r15)
+; CHECK: aghi %r15, 16
 ; CHECK: br %r14
   %l0 = load volatile fp128, fp128 *%ptr
   %l1 = load volatile fp128, fp128 *%ptr
diff --git a/llvm/test/CodeGen/SystemZ/frame-19.ll b/llvm/test/CodeGen/SystemZ/frame-19.ll
index 2a0693b9ac4..c6a26600683 100644
--- a/llvm/test/CodeGen/SystemZ/frame-19.ll
+++ b/llvm/test/CodeGen/SystemZ/frame-19.ll
@@ -96,10 +96,11 @@ define void @f1(<16 x i8> *%ptr) {
   ret void
 }
 
-; Like f1, but no 16-byte slot should be needed.
+; Like f1, but no 16-byte slot should be needed, and no outgoing reg save
+; area of 160 bytes.
 define void @f2(<16 x i8> *%ptr) {
 ; CHECK-LABEL: f2:
-; CHECK: aghi %r15, -224
+; CHECK: aghi %r15, -64
 ; CHECK-DAG: std %f8,
 ; CHECK-DAG: std %f9,
 ; CHECK-DAG: std %f10,
@@ -118,7 +119,7 @@ define void @f2(<16 x i8> *%ptr) {
 ; CHECK-DAG: ld %f13,
 ; CHECK-DAG: ld %f14,
 ; CHECK-DAG: ld %f15,
-; CHECK: aghi %r15, 224
+; CHECK: aghi %r15, 64
 ; CHECK: br %r14
   %v0 = load volatile <16 x i8>, <16 x i8> *%ptr
   %v1 = load volatile <16 x i8>, <16 x i8> *%ptr
@@ -190,7 +191,7 @@ define void @f2(<16 x i8> *%ptr) {
 ; Like f2, but only %f8 should be saved.
 define void @f3(<16 x i8> *%ptr) {
 ; CHECK-LABEL: f3:
-; CHECK: aghi %r15, -168
+; CHECK: aghi %r15, -8
 ; CHECK-DAG: std %f8,
 ; CHECK-NOT: vst {{.*}}(%r15)
 ; CHECK-NOT: vl {{.*}}(%r15)
@@ -202,7 +203,7 @@ define void @f3(<16 x i8> *%ptr) {
 ; CHECK-NOT: %v14
 ; CHECK-NOT: %v15
 ; CHECK-DAG: ld %f8,
-; CHECK: aghi %r15, 168
+; CHECK: aghi %r15, 8
 ; CHECK: br %r14
   %v0 = load volatile <16 x i8>, <16 x i8> *%ptr
   %v1 = load volatile <16 x i8>, <16 x i8> *%ptr
diff --git a/llvm/test/CodeGen/SystemZ/frame-20.ll b/llvm/test/CodeGen/SystemZ/frame-20.ll
index 8d601c6f6d5..6653c8185b0 100644
--- a/llvm/test/CodeGen/SystemZ/frame-20.ll
+++ b/llvm/test/CodeGen/SystemZ/frame-20.ll
@@ -5,20 +5,20 @@
 
 ; This function should require all FPRs, but no other spill slots.
 ; We need to save and restore 8 of the 16 FPRs, so the frame size
-; should be exactly 160 + 8 * 8 = 224.  The CFA offset is 160
-; (the caller-allocated part of the frame) + 224.
+; should be exactly 8 * 8 = 64.  The CFA offset is 160
+; (the caller-allocated part of the frame) + 64.
 define void @f1(double *%ptr) {
 ; CHECK-LABEL: f1:
-; CHECK: aghi %r15, -224
-; CHECK: .cfi_def_cfa_offset 384
-; CHECK: std %f8, 216(%r15)
-; CHECK: std %f9, 208(%r15)
-; CHECK: std %f10, 200(%r15)
-; CHECK: std %f11, 192(%r15)
-; CHECK: std %f12, 184(%r15)
-; CHECK: std %f13, 176(%r15)
-; CHECK: std %f14, 168(%r15)
-; CHECK: std %f15, 160(%r15)
+; CHECK: aghi %r15, -64
+; CHECK: .cfi_def_cfa_offset 224
+; CHECK: std %f8, 56(%r15)
+; CHECK: std %f9, 48(%r15)
+; CHECK: std %f10, 40(%r15)
+; CHECK: std %f11, 32(%r15)
+; CHECK: std %f12, 24(%r15)
+; CHECK: std %f13, 16(%r15)
+; CHECK: std %f14, 8(%r15)
+; CHECK: std %f15, 0(%r15)
 ; CHECK: .cfi_offset %f8, -168
 ; CHECK: .cfi_offset %f9, -176
 ; CHECK: .cfi_offset %f10, -184
@@ -35,15 +35,15 @@ define void @f1(double *%ptr) {
 ; CHECK-DAG: vlrepg %v23, 0(%r2)
 ; CHECK-DAG: vlrepg %v24, 0(%r2)
 ; CHECK-DAG: vlrepg %v31, 0(%r2)
-; CHECK: ld %f8, 216(%r15)
-; CHECK: ld %f9, 208(%r15)
-; CHECK: ld %f10, 200(%r15)
-; CHECK: ld %f11, 192(%r15)
-; CHECK: ld %f12, 184(%r15)
-; CHECK: ld %f13, 176(%r15)
-; CHECK: ld %f14, 168(%r15)
-; CHECK: ld %f15, 160(%r15)
-; CHECK: aghi %r15, 224
+; CHECK: ld %f8, 56(%r15)
+; CHECK: ld %f9, 48(%r15)
+; CHECK: ld %f10, 40(%r15)
+; CHECK: ld %f11, 32(%r15)
+; CHECK: ld %f12, 24(%r15)
+; CHECK: ld %f13, 16(%r15)
+; CHECK: ld %f14, 8(%r15)
+; CHECK: ld %f15, 0(%r15)
+; CHECK: aghi %r15, 64
 ; CHECK: br %r14
   %l0 = load volatile double, double *%ptr
   %l1 = load volatile double, double *%ptr
@@ -148,15 +148,15 @@ define void @f1(double *%ptr) {
 ; so %f15 is the one that gets dropped.
 define void @f2(double *%ptr) {
 ; CHECK-LABEL: f2:
-; CHECK: aghi %r15, -216
-; CHECK: .cfi_def_cfa_offset 376
-; CHECK: std %f8, 208(%r15)
-; CHECK: std %f9, 200(%r15)
-; CHECK: std %f10, 192(%r15)
-; CHECK: std %f11, 184(%r15)
-; CHECK: std %f12, 176(%r15)
-; CHECK: std %f13, 168(%r15)
-; CHECK: std %f14, 160(%r15)
+; CHECK: aghi %r15, -56
+; CHECK: .cfi_def_cfa_offset 216
+; CHECK: std %f8, 48(%r15)
+; CHECK: std %f9, 40(%r15)
+; CHECK: std %f10, 32(%r15)
+; CHECK: std %f11, 24(%r15)
+; CHECK: std %f12, 16(%r15)
+; CHECK: std %f13, 8(%r15)
+; CHECK: std %f14, 0(%r15)
 ; CHECK: .cfi_offset %f8, -168
 ; CHECK: .cfi_offset %f9, -176
 ; CHECK: .cfi_offset %f10, -184
@@ -166,14 +166,14 @@ define void @f2(double *%ptr) {
 ; CHECK: .cfi_offset %f14, -216
 ; CHECK-NOT: %v15
 ; CHECK-NOT: %f15
-; CHECK: ld %f8, 208(%r15)
-; CHECK: ld %f9, 200(%r15)
-; CHECK: ld %f10, 192(%r15)
-; CHECK: ld %f11, 184(%r15)
-; CHECK: ld %f12, 176(%r15)
-; CHECK: ld %f13, 168(%r15)
-; CHECK: ld %f14, 160(%r15)
-; CHECK: aghi %r15, 216
+; CHECK: ld %f8, 48(%r15)
+; CHECK: ld %f9, 40(%r15)
+; CHECK: ld %f10, 32(%r15)
+; CHECK: ld %f11, 24(%r15)
+; CHECK: ld %f12, 16(%r15)
+; CHECK: ld %f13, 8(%r15)
+; CHECK: ld %f14, 0(%r15)
+; CHECK: aghi %r15, 56
 ; CHECK: br %r14
   %l0 = load volatile double, double *%ptr
   %l1 = load volatile double, double *%ptr
@@ -274,14 +274,14 @@ define void @f2(double *%ptr) {
 ; Like f1, but should require only one call-saved FPR.
 define void @f3(double *%ptr) {
 ; CHECK-LABEL: f3:
-; CHECK: aghi %r15, -168
-; CHECK: .cfi_def_cfa_offset 328
-; CHECK: std %f8, 160(%r15)
+; CHECK: aghi %r15, -8
+; CHECK: .cfi_def_cfa_offset 168
+; CHECK: std %f8, 0(%r15)
 ; CHECK: .cfi_offset %f8, -168
 ; CHECK-NOT: {{%[fv]9}}
 ; CHECK-NOT: {{%[fv]1[0-5]}}
-; CHECK: ld %f8, 160(%r15)
-; CHECK: aghi %r15, 168
+; CHECK: ld %f8, 0(%r15)
+; CHECK: aghi %r15, 8
 ; CHECK: br %r14
   %l0 = load volatile double, double *%ptr
   %l1 = load volatile double, double *%ptr
diff --git a/llvm/test/CodeGen/SystemZ/frame-22.ll b/llvm/test/CodeGen/SystemZ/frame-22.ll
new file mode 100644
index 00000000000..fd4e3fec508
--- /dev/null
+++ b/llvm/test/CodeGen/SystemZ/frame-22.ll
@@ -0,0 +1,87 @@
+; RUN: llc < %s -mtriple=s390x-linux-gnu | FileCheck %s
+;
+; Test the packed stack layout.
+
+; Test spill/restore of an FPR and a GPR.
+define void @f1() #0 {
+; CHECK-LABEL: f1:
+; CHECK: stmg %r12, %r15, 128(%r15)
+; CHECK-NEXT: .cfi_offset %r12, -32
+; CHECK-NEXT: .cfi_offset %r15, -8
+; CHECK-NEXT: std %f8, 120(%r15)          # 8-byte Folded Spill
+; CHECK-NEXT: .cfi_offset %f8, -40
+; CHECK-NEXT: #APP
+; CHECK-NEXT: #NO_APP
+; CHECK-NEXT: ld %f8, 120(%r15)          # 8-byte Folded Reload
+; CHECK-NEXT: lmg %r12, %r15, 128(%r15)
+; CHECK-NEXT: br %r14
+  call void asm sideeffect "", "~{f8},~{r12}"() nounwind
+  ret void
+}
+
+; Test spill/restore with anyregcc, including an FP argument register.
+define anyregcc void @f2() #0 {
+; CHECK-LABEL: f2:
+; CHECK: stmg %r3, %r15, 56(%r15)
+; CHECK-NEXT: .cfi_offset %r3, -104
+; CHECK-NEXT: .cfi_offset %r15, -8
+; CHECK-NEXT: std %f0, 48(%r15)          # 8-byte Folded Spill
+; CHECK-NEXT: std %f1, 40(%r15)          # 8-byte Folded Spill
+; CHECK-NEXT: .cfi_offset %f0, -112
+; CHECK-NEXT: .cfi_offset %f1, -120
+; CHECK-NEXT: #APP
+; CHECK-NEXT: #NO_APP
+; CHECK-NEXT: ld %f0, 48(%r15)          # 8-byte Folded Reload
+; CHECK-NEXT: ld %f1, 40(%r15)          # 8-byte Folded Reload
+; CHECK-NEXT: lmg %r3, %r15, 56(%r15)
+; CHECK-NEXT: br %r14
+  call void asm sideeffect "", "~{f0},~{f1},~{r3}"() nounwind
+  ret void
+}
+
+; Test spill/restore in local area with incoming stack arguments.
+define i64 @f3(i64 %a, i64 %b, i64 %c, i64 %d, i64 %e, i64 %f,
+               double %A, double %B, double %C, double %D, double %E) #0 {
+; CHECK-LABEL: f3:
+; CHECK: std %f8, 152(%r15)          # 8-byte Folded Spill
+; CHECK-NEXT: .cfi_offset %f8, -8
+; CHECK-NEXT: ld %f0, 168(%r15)
+; CHECK-NEXT: cgdbr %r2, 5, %f0
+; CHECK-NEXT: ag %r2, 160(%r15)
+; CHECK-NEXT: #APP
+; CHECK-NEXT: #NO_APP
+; CHECK-NEXT: ld %f8, 152(%r15)          # 8-byte Folded Reload
+; CHECK-NEXT: br %r14
+  call void asm sideeffect "", "~{f8}"() nounwind
+  %Ei = fptosi double %E to i64
+  %S = add i64 %f, %Ei
+  ret i64 %S
+}
+
+; Test spill/restore in local area with outgoing stack arguments.
+define i64 @f4() #0 {
+; CHECK-LABEL: f4:
+; CHECK: stmg    %r6, %r15, 80(%r15)
+; CHECK-NEXT: .cfi_offset %r6, -80
+; CHECK-NEXT: .cfi_offset %r14, -16
+; CHECK-NEXT: .cfi_offset %r15, -8
+; CHECK-NEXT: aghi    %r15, -104
+; CHECK-NEXT: .cfi_def_cfa_offset 264
+; CHECK-NEXT: std     %f8, 176(%r15)          # 8-byte Folded Spill
+; CHECK-NEXT: .cfi_offset %f8, -88
+; CHECK-NEXT: #APP
+; CHECK-NEXT: #NO_APP
+; CHECK-NEXT: llihh   %r0, 16404
+; CHECK-NEXT: stg     %r0, 168(%r15)
+; CHECK: mvghi   160(%r15), 6
+; CHECK-NEXT: brasl   %r14, f3@PLT
+; CHECK-NEXT: ld      %f8, 176(%r15)          # 8-byte Folded Reload
+; CHECK-NEXT: lmg     %r6, %r15, 184(%r15)
+; CHECK-NEXT: br      %r14
+  call void asm sideeffect "", "~{f8}"() nounwind
+  %C = call i64 @f3 (i64 1, i64 2, i64 3, i64 4, i64 5, i64 6,
+                     double 1.0, double 2.0, double 3.0, double 4.0, double 5.0)
+  ret i64 %C
+}
+
+attributes #0 = { "packed-stack"="true" }