Fix epilogue codegen to avoid leaving the stack pointer in an invalid

state. Previously Thumb2 would restore sp from fp like this:
mov sp, r7
sub, sp, #4
If an interrupt is taken after the 'mov' but before the 'sub', callee-saved
registers might be clobbered by the interrupt handler. Instead, try
restoring directly from sp:
add sp, #4
Or, if necessary (with VLA, etc.) use a scratch register to compute sp and
then restore it:
sub.w r4, r7, #8
mov sp, r7
rdar://8465407


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@119977 91177308-0d34-0410-b5e6-96231b3b80d8

6 files changed, 74 insertions, 14 deletions

diff --git a/test/CodeGen/ARM/hello.ll b/test/CodeGen/ARM/hello.ll
index ccdc7bf..bfed7a6 100644
--- a/test/CodeGen/ARM/hello.ll
+++ b/test/CodeGen/ARM/hello.ll
@@ -1,7 +1,7 @@
 ; RUN: llc < %s -march=arm
 ; RUN: llc < %s -mtriple=arm-linux-gnueabi | grep mov | count 1
 ; RUN: llc < %s -mtriple=arm-linux-gnu --disable-fp-elim | \
-; RUN:   grep mov | count 3
+; RUN:   grep mov | count 2
 ; RUN: llc < %s -mtriple=arm-apple-darwin | grep mov | count 2
 
 @str = internal constant [12 x i8] c"Hello World\00"
diff --git a/test/CodeGen/Thumb/dyn-stackalloc.ll b/test/CodeGen/Thumb/dyn-stackalloc.ll
index 5c8ad97..1f31dca 100644
--- a/test/CodeGen/Thumb/dyn-stackalloc.ll
+++ b/test/CodeGen/Thumb/dyn-stackalloc.ll
@@ -1,12 +1,15 @@
-; RUN: llc < %s -march=thumb | not grep {ldr sp}
-; RUN: llc < %s -mtriple=thumb-apple-darwin | \
-; RUN:   not grep {sub.*r7}
-; RUN: llc < %s -march=thumb | grep {mov.*r6, sp}
+; RUN: llc < %s -mtriple=thumb-apple-darwin | FileCheck %s
 
 	%struct.state = type { i32, %struct.info*, float**, i32, i32, i32, i32, i32, i32, i32, i32, i32, i64, i64, i64, i64, i64, i64, i8* }
 	%struct.info = type { i32, i32, i32, i32, i32, i32, i32, i8* }
 
 define void @t1(%struct.state* %v) {
+; CHECK: t1:
+; CHECK: push
+; CHECK: add r7, sp, #12
+; CHECK: mov r2, sp
+; CHECK: subs r4, r2, r1
+; CHECK: mov sp, r4
 	%tmp6 = load i32* null
 	%tmp8 = alloca float, i32 %tmp6
 	store i32 1, i32* null
@@ -34,6 +37,18 @@ declare fastcc void @f2(float*, float*, float*, i32)
 @str215 = external global [2 x i8]
 
 define void @t2(%struct.comment* %vc, i8* %tag, i8* %contents) {
+; CHECK: t2:
+; CHECK: push
+; CHECK: add r7, sp, #12
+; CHECK: sub sp, #8
+; CHECK: mov r6, sp
+; CHECK: str r2, [r6, #4]
+; CHECK: str r0, [r6]
+; CHECK-NOT: ldr r0, [sp
+; CHECK: ldr r0, [r6, #4]
+; CHECK: mov r0, sp
+; CHECK: subs r5, r0, r1
+; CHECK: mov sp, r5
 	%tmp1 = call i32 @strlen( i8* %tag )
 	%tmp3 = call i32 @strlen( i8* %contents )
 	%tmp4 = add i32 %tmp1, 2
diff --git a/test/CodeGen/Thumb/large-stack.ll b/test/CodeGen/Thumb/large-stack.ll
index b289484..f4dd3e0 100644
--- a/test/CodeGen/Thumb/large-stack.ll
+++ b/test/CodeGen/Thumb/large-stack.ll
@@ -12,8 +12,8 @@ define void @test2() {
 ; CHECK: test2:
 ; CHECK: ldr r0, LCPI
 ; CHECK: add sp, r0
-; CHECK: mov sp, r7
-; CHECK: sub sp, #4
+; CHECK: subs r4, r7, #4
+; CHECK: mov sp, r4
     %tmp = alloca [ 4168 x i8 ] , align 4
     ret void
 }
@@ -24,8 +24,8 @@ define i32 @test3() {
 ; CHECK: add sp, r2
 ; CHECK: ldr r1, LCPI
 ; CHECK: add r1, sp
-; CHECK: mov sp, r7
-; CHECK: sub sp, #4
+; CHECK: subs r4, r7, #4
+; CHECK: mov sp, r4
     %retval = alloca i32, align 4
     %tmp = alloca i32, align 4
     %a = alloca [805306369 x i8], align 16
diff --git a/test/CodeGen/Thumb2/2009-08-06-SpDecBug.ll b/test/CodeGen/Thumb2/2009-08-06-SpDecBug.ll
index f26c6d1..550b3ef 100644
--- a/test/CodeGen/Thumb2/2009-08-06-SpDecBug.ll
+++ b/test/CodeGen/Thumb2/2009-08-06-SpDecBug.ll
@@ -5,8 +5,13 @@
 define hidden i32 @__gcov_execlp(i8* %path, i8* %arg, ...) nounwind {
 entry:
 ; CHECK: __gcov_execlp:
-; CHECK: mov sp, r7
-; CHECK: sub sp, #4
+; CHECK: sub sp, #8
+; CHECK: push
+; CHECK: add r7, sp, #4
+; CHECK: subs r4, r7, #4
+; CHECK: mov sp, r4
+; CHECK-NOT: mov sp, r7
+; CHECK: add sp, #8
 	call void @__gcov_flush() nounwind
 	br i1 undef, label %bb5, label %bb
 
diff --git a/test/CodeGen/Thumb2/2010-08-10-VarSizedAllocaBug.ll b/test/CodeGen/Thumb2/2010-08-10-VarSizedAllocaBug.ll
index abcf13a..41f7f29 100644
--- a/test/CodeGen/Thumb2/2010-08-10-VarSizedAllocaBug.ll
+++ b/test/CodeGen/Thumb2/2010-08-10-VarSizedAllocaBug.ll
@@ -5,6 +5,10 @@
 define internal fastcc i32 @Callee(i32 %i) nounwind {
 entry:
 ; CHECK: Callee:
+; CHECK: push
+; CHECK: mov r4, sp
+; CHECK: sub.w r12, r4, #1000
+; CHECK: mov sp, r12
   %0 = icmp eq i32 %i, 0                          ; <i1> [#uses=1]
   br i1 %0, label %bb2, label %bb
 
@@ -17,9 +21,11 @@ bb:                                               ; preds = %entry
   ret i32 %4
 
 bb2:                                              ; preds = %entry
-; Must restore sp from fp here
-; CHECK: mov sp, r7
-; CHECK: sub sp, #8
+; Must restore sp from fp here. Make sure not to leave sp in a temporarily invalid
+; state though. rdar://8465407
+; CHECK-NOT: mov sp, r7
+; CHECK: sub.w r4, r7, #8
+; CHECK: mov sp, r4
 ; CHECK: pop
   ret i32 0
 }
diff --git a/test/CodeGen/Thumb2/2010-11-22-EpilogueBug.ll b/test/CodeGen/Thumb2/2010-11-22-EpilogueBug.ll
new file mode 100644
index 0000000..313728c
--- /dev/null
+++ b/test/CodeGen/Thumb2/2010-11-22-EpilogueBug.ll
@@ -0,0 +1,34 @@
+; rdar://8465407
+; RUN: llc < %s -mtriple=thumbv7-apple-darwin | FileCheck %s
+
+%struct.buf = type opaque
+
+declare void @bar() nounwind optsize
+
+define void @foo() nounwind optsize {
+; CHECK: foo:
+; CHECK: push
+; CHECK: add r7, sp, #4
+; CHECK: sub sp, #4
+entry:
+  %m.i = alloca %struct.buf*, align 4
+  br label %bb
+
+bb:
+  br i1 undef, label %bb3, label %bb2
+
+bb2:
+  call void @bar() nounwind optsize
+  br i1 undef, label %bb, label %bb3
+
+bb3:
+  br i1 undef, label %return, label %bb
+
+return:
+; CHECK: %return
+; 'mov sp, r7' would have left sp in an invalid state
+; CHECK-NOT: mov sp, r7
+; CHECK-NOT: sub, sp, #4
+; CHECK: add sp, #4
+  ret void
+}