Hi,
this patch makes us to stream out and stream in the order fields of cgraph
correctly, so -fno-toplevel-reorder works within single compilation unit
with -flto-partition=none.
This is currently needed to build kernel with LTO and it is useful otherwise
(i.e. I made the patch originally for some experiments with Mozilla load times)
Andi has patch to fix stream in code to stream in linker order that fixes
the order with -flto-partition=none completely and I will followup with patch
to make partitioning to honor the streaming order.
Boostrapped/regtested x86_64-linux, OK?
Honza
* lto-streamer.h (lto_input_toplevel_asms): Add order_base parameter.
* lto-streamer-in.c (lto_input_toplevel_asms): Stream in order.
* lto-streamer-out.c (lto_output_toplevel_asms): Stream out order.
* lto-cgraph.c (order_base): New static var.
(lto_output_node): Stream in order.
(lto_output_varpool_node): Stream out order.
(input_node): Stream in order.
(input_varpool_node): Stream out order.
(input_cgraph_1): Initialize order base; update call of
lto_input_toplevel_asms.
Index: lto-streamer.h
===================================================================
--- lto-streamer.h (revision 179413)
+++ lto-streamer.h (working copy)
@@ -807,7 +807,7 @@ extern void lto_input_function_body (str
const char *);
extern void lto_input_constructors_and_inits (struct lto_file_decl_data *,
const char *);
-extern void lto_input_toplevel_asms (struct lto_file_decl_data *);
+extern void lto_input_toplevel_asms (struct lto_file_decl_data *, int);
extern struct data_in *lto_data_in_create (struct lto_file_decl_data *,
const char *, unsigned,
VEC(ld_plugin_symbol_resolution_t,heap) *);
Index: lto-streamer-in.c
===================================================================
--- lto-streamer-in.c (revision 179413)
+++ lto-streamer-in.c (working copy)
@@ -1144,7 +1144,7 @@ lto_input_tree (struct lto_input_block *
/* Input toplevel asms. */
void
-lto_input_toplevel_asms (struct lto_file_decl_data *file_data)
+lto_input_toplevel_asms (struct lto_file_decl_data *file_data, int order_base)
{
size_t len;
const char *data = lto_get_section_data (file_data, LTO_section_asm,
@@ -1173,7 +1173,12 @@ lto_input_toplevel_asms (struct lto_file
header->lto_header.minor_version);
while ((str = streamer_read_string_cst (data_in, &ib)))
- cgraph_add_asm_node (str);
+ {
+ struct cgraph_asm_node *node = cgraph_add_asm_node (str);
+ node->order = streamer_read_hwi (&ib) + order_base;
+ if (node->order >= cgraph_order)
+ cgraph_order = node->order + 1;
+ }
clear_line_info (data_in);
lto_data_in_delete (data_in);
Index: lto-streamer-out.c
===================================================================
--- lto-streamer-out.c (revision 179413)
+++ lto-streamer-out.c (working copy)
@@ -954,7 +954,10 @@ lto_output_toplevel_asms (void)
streamer_write_char_stream (ob->string_stream, 0);
for (can = cgraph_asm_nodes; can; can = can->next)
- streamer_write_string_cst (ob, ob->main_stream, can->asm_str);
+ {
+ streamer_write_string_cst (ob, ob->main_stream, can->asm_str);
+ streamer_write_hwi (ob, can->order);
+ }
streamer_write_string_cst (ob, ob->main_stream, NULL_TREE);
Index: lto-cgraph.c
===================================================================
--- lto-cgraph.c (revision 179413)
+++ lto-cgraph.c (working copy)
@@ -54,6 +54,9 @@ static void input_cgraph_opt_summary (VE
/* Number of LDPR values known to GCC. */
#define LDPR_NUM_KNOWN (LDPR_RESOLVED_DYN + 1)
+/* All node orders are ofsetted by ORDER_BASE. */
+static int order_base;
+
/* Cgraph streaming is organized as set of record whose type
is indicated by a tag. */
enum LTO_cgraph_tags
@@ -425,6 +428,7 @@ lto_output_node (struct lto_simple_outpu
streamer_write_enum (ob->main_stream, LTO_cgraph_tags, LTO_cgraph_last_tag,
tag);
+ streamer_write_hwi_stream (ob->main_stream, node->order);
/* In WPA mode, we only output part of the call-graph. Also, we
fake cgraph node attributes. There are two cases that we care.
@@ -548,6 +552,7 @@ lto_output_varpool_node (struct lto_simp
struct bitpack_d bp;
int ref;
+ streamer_write_hwi_stream (ob->main_stream, node->order);
lto_output_var_decl_index (ob->decl_state, ob->main_stream, node->decl);
bp = bitpack_create (ob->main_stream);
bp_pack_value (&bp, node->externally_visible, 1);
@@ -960,7 +965,9 @@ input_node (struct lto_file_decl_data *f
unsigned decl_index;
int ref = LCC_NOT_FOUND, ref2 = LCC_NOT_FOUND;
int clone_ref;
+ int order;
+ order = streamer_read_hwi (ib) + order_base;
clone_ref = streamer_read_hwi (ib);
decl_index = streamer_read_uhwi (ib);
@@ -974,6 +981,10 @@ input_node (struct lto_file_decl_data *f
else
node = cgraph_get_create_node (fn_decl);
+ node->order = order;
+ if (order >= cgraph_order)
+ cgraph_order = order + 1;
+
node->count = streamer_read_hwi (ib);
node->count_materialization_scale = streamer_read_hwi (ib);
@@ -1035,10 +1046,15 @@ input_varpool_node (struct lto_file_decl
struct bitpack_d bp;
int ref = LCC_NOT_FOUND;
bool non_null_aliasof;
+ int order;
+ order = streamer_read_hwi (ib) + order_base;
decl_index = streamer_read_uhwi (ib);
var_decl = lto_file_decl_data_get_var_decl (file_data, decl_index);
node = varpool_node (var_decl);
+ node->order = order;
+ if (order >= cgraph_order)
+ cgraph_order = order + 1;
node->lto_file_data = file_data;
bp = streamer_read_bitpack (ib);
@@ -1178,6 +1194,7 @@ input_cgraph_1 (struct lto_file_decl_dat
unsigned i;
tag = streamer_read_enum (ib, LTO_cgraph_tags, LTO_cgraph_last_tag);
+ order_base = cgraph_order;
while (tag)
{
if (tag == LTO_cgraph_edge)
@@ -1196,7 +1213,7 @@ input_cgraph_1 (struct lto_file_decl_dat
tag = streamer_read_enum (ib, LTO_cgraph_tags, LTO_cgraph_last_tag);
}
- lto_input_toplevel_asms (file_data);
+ lto_input_toplevel_asms (file_data, order_base);
/* AUX pointers should be all non-zero for nodes read from the stream. */
#ifdef ENABLE_CHECKING
