On 05/06/2016 03:44 AM, Dominik Vogt wrote:
diff --git a/gcc/cfgexpand.c b/gcc/cfgexpand.c
index 21f21c9..4d48afd 100644
--- a/gcc/cfgexpand.c
+++ b/gcc/cfgexpand.c
...
@@ -1099,8 +1101,10 @@ expand_stack_vars (bool (*pred) (size_t), struct
stack_vars_data *data)
/* If there were any, allocate space. */
if (large_size > 0)
- large_base = allocate_dynamic_stack_space (GEN_INT (large_size), 0,
- large_align, true);
+ {
+ large_allocsize = GEN_INT (large_size);
+ get_dynamic_stack_size (&large_allocsize, 0, large_align, NULL);
...
See below.
@@ -1186,6 +1190,18 @@ expand_stack_vars (bool (*pred) (size_t), struct
stack_vars_data *data)
/* Large alignment is only processed in the last pass. */
if (pred)
continue;
+
+ if (large_allocsize && ! large_allocation_done)
+ {
+ /* Allocate space the virtual stack vars area in the prologue.
+ */
+ HOST_WIDE_INT loffset;
+
+ loffset = alloc_stack_frame_space (INTVAL (large_allocsize),
+ PREFERRED_STACK_BOUNDARY);
1) Should this use PREFERRED_STACK_BOUNDARY or just STACK_BOUNDARY?
2) Is this the right place for rounding up, or should
it be done above, maybe in get_dynamic_stack_size?
I think PREFERRED_STACK_BOUNDARY is the correct one to use.
I think rounding in either place is fine. We'd like to avoid multiple
roundings, but otherwise I don't think it really matters.
jeff
Not sure whether this is the right
+ large_base = get_dynamic_stack_base (loffset, large_align);
+ large_allocation_done = true;
+ }
gcc_assert (large_base != NULL);
large_alloc += alignb - 1;
diff --git a/gcc/testsuite/gcc.dg/stack-layout-dynamic-1.c
b/gcc/testsuite/gcc.dg/stack-layout-dynamic-1.c
new file mode 100644
index 0000000..e06a16c
--- /dev/null
+++ b/gcc/testsuite/gcc.dg/stack-layout-dynamic-1.c
@@ -0,0 +1,14 @@
+/* Verify that run time aligned local variables are aloocated in the prologue
+ in one pass together with normal local variables. */
+/* { dg-do compile } */
+/* { dg-options "-O0" } */
+
+extern void bar (void *, void *, void *);
+void foo (void)
+{
+ int i;
+ __attribute__ ((aligned(65536))) char runtime_aligned_1[512];
+ __attribute__ ((aligned(32768))) char runtime_aligned_2[1024];
+ bar (&i, &runtime_aligned_1, &runtime_aligned_2);
+}
+/* { dg-final { scan-assembler-times "cfi_def_cfa_offset" 2 { target {
s390*-*-* } } } } */
I've no idea how to test this on other targets, or how to express
the test in a target independent way. The scan-assembler-times
does not work on x86_64.
I wonder if you could force -fomit-frame-pointer and see if we still end
up with a frame pointer?
jeff
