This patch ports messages to the new dump framework, specifically those
involving missing/mismatched/corrupted profile data, indirect call
promotions performed, and inlines. For the inline messages, I ported
Dehao's patch from the google branches that enables printing call chain
information.
I also fixed some issues with the dump_loc support for dumping out
the new messages with location data, specifically to emit column numbers
and to ensure the notes start on a new line.
Finally, I made a couple enhancements to the new dump infrastructure
to enable messages emitted from other parts of the compiler. There
were two issues:
1) The coverage_init routine happens very early, before entering the pass
manager that sets up the dumping. This isn't an issue in trunk yet,
since there currently aren't any messages emitted during coverage_init
(this showed up on the google branch where we emit messages for
LIPO-specific profiles during this part of the compile), but it could be
in the future. This was addressed by enabling dumping within coverage_init,
and is modeled on how dumping is enabled after the pass manager
during finish_optimization_passes.
2) Dumping was only enabled for passes marked with an optinfo_flag
that isn't OPTGROUP_NONE. Currently optgroup flags are only setup for
optimization groups in the categories IPA, LOOP, INLINE and VEC.
What this means is that any dump messages added to a pass that isn't
in one of these groups will silently be suppressed. The OPTGROUP
setting is specified in opt_pass struct, and is also automatically set
to OPTGROUP_IPA for any pass starting with "ipa-". What I did was
to add a new optgroup macro, OPTGROUP_OTHER. This is enabled only
under -fopt-info-optall, which is also the default for -fopt-info.
That way dump messages can be emitted without the requirement that
the pass be part of a group that can be emitted under a specific
optimization group subset. When setting up the dumps, any pass that
has OPTGROUP_NONE after examining the opt_pass struct and the pass
name will use OPTGROUP_OTHER. This doesn't mean that the list of
optgroups shouldn't be expanded, but rather adds a catch-all for
passes that don't currently have or need to be emitted on their own
as part of a new optgroup.
Bootstrapped and tested on x86-64-unknown-linux-gnu.
Ok for trunk?
Thanks,
Teresa
2013-08-06 Teresa Johnson <tejohn...@google.com>
Dehao Chen <de...@google.com>
* dumpfile.c (dump_loc): Add column number to output, make newlines
consistent.
* dumpfile.h (OPTGROUP_OTHER): Add and enable under OPTGROUP_ALL.
* ipa-inline-transform.c (clone_inlined_nodes):
(cgraph_node_opt_info): New function.
(cgraph_node_call_chain): Ditto.
(dump_inline_decision): Ditto.
(inline_call): Invoke dump_inline_decision.
* doc/invoke.texi: Document optall -fopt-info flag.
* profile.c (read_profile_edge_counts): Use new dump framework.
(compute_branch_probabilities): Ditto.
* passes.c (pass_manager::register_one_dump_file): Use OPTGROUP_OTHER
when pass not in any opt group.
* value-prof.c (check_counter): Use new dump framework.
(find_func_by_funcdef_no): Ditto.
(check_ic_target): Ditto.
* coverage.c (get_coverage_counts): Ditto.
(coverage_init): Setup new dump framework.
* ipa-inline.c (inline_small_functions): Set is_in_ipa_inline.
* ipa-inline.h (is_in_ipa_inline): Declare.
* testsuite/gcc.dg/pr40209.c: Use -fopt-info.
* testsuite/gcc.dg/pr26570.c: Ditto.
* testsuite/gcc.dg/pr32773.c: Ditto.
* testsuite/g++.dg/tree-ssa/dom-invalid.C (struct C): Ditto.
Index: dumpfile.c
===================================================================
--- dumpfile.c (revision 201461)
+++ dumpfile.c (working copy)
@@ -257,16 +257,18 @@ dump_open_alternate_stream (struct dump_file_info
void
dump_loc (int dump_kind, FILE *dfile, source_location loc)
{
- /* Currently vectorization passes print location information. */
if (dump_kind)
{
+ /* Ensure dump message starts on a new line. */
+ fprintf (dfile, "\n");
if (LOCATION_LOCUS (loc) > BUILTINS_LOCATION)
- fprintf (dfile, "\n%s:%d: note: ", LOCATION_FILE (loc),
- LOCATION_LINE (loc));
+ fprintf (dfile, "%s:%d:%d: note: ", LOCATION_FILE (loc),
+ LOCATION_LINE (loc), LOCATION_COLUMN (loc));
else if (current_function_decl)
- fprintf (dfile, "\n%s:%d: note: ",
+ fprintf (dfile, "%s:%d:%d: note: ",
DECL_SOURCE_FILE (current_function_decl),
- DECL_SOURCE_LINE (current_function_decl));
+ DECL_SOURCE_LINE (current_function_decl),
+ DECL_SOURCE_COLUMN (current_function_decl));
}
}
Index: dumpfile.h
===================================================================
--- dumpfile.h (revision 201461)
+++ dumpfile.h (working copy)
@@ -97,8 +97,9 @@ enum tree_dump_index
#define OPTGROUP_LOOP (1 << 2) /* Loop optimization passes */
#define OPTGROUP_INLINE (1 << 3) /* Inlining passes */
#define OPTGROUP_VEC (1 << 4) /* Vectorization passes */
+#define OPTGROUP_OTHER (1 << 5) /* All other passes */
#define OPTGROUP_ALL (OPTGROUP_IPA | OPTGROUP_LOOP | OPTGROUP_INLINE \
- | OPTGROUP_VEC)
+ | OPTGROUP_VEC | OPTGROUP_OTHER)
/* Define a tree dump switch. */
struct dump_file_info
Index: ipa-inline-transform.c
===================================================================
--- ipa-inline-transform.c (revision 201461)
+++ ipa-inline-transform.c (working copy)
@@ -192,6 +192,108 @@ clone_inlined_nodes (struct cgraph_edge *e, bool d
}
+#define MAX_INT_LENGTH 20
+
+/* Return NODE's name and profile count, if available. */
+
+static const char *
+cgraph_node_opt_info (struct cgraph_node *node)
+{
+ char *buf;
+ size_t buf_size;
+ const char *bfd_name = lang_hooks.dwarf_name (node->symbol.decl, 0);
+
+ if (!bfd_name)
+ bfd_name = "unknown";
+
+ buf_size = strlen (bfd_name) + 1;
+ if (profile_info)
+ buf_size += (MAX_INT_LENGTH + 3);
+
+ buf = (char *) xmalloc (buf_size);
+
+ strcpy (buf, bfd_name);
+
+ if (profile_info)
+ sprintf (buf, "%s ("HOST_WIDEST_INT_PRINT_DEC")", buf, node->count);
+ return buf;
+}
+
+
+/* Return CALLER's inlined call chain. Save the cgraph_node of the ultimate
+ function that the caller is inlined to in FINAL_CALLER. */
+
+static const char *
+cgraph_node_call_chain (struct cgraph_node *caller,
+ struct cgraph_node **final_caller)
+{
+ struct cgraph_node *node;
+ const char *via_str = " (via inline instance";
+ size_t current_string_len = strlen (via_str) + 1;
+ size_t buf_size = current_string_len;
+ char *buf = (char *) xmalloc (buf_size);
+
+ buf[0] = 0;
+ gcc_assert (caller->global.inlined_to != NULL);
+ strcat (buf, via_str);
+ for (node = caller; node->global.inlined_to != NULL;
+ node = node->callers->caller)
+ {
+ const char *name = cgraph_node_opt_info (node);
+ current_string_len += (strlen (name) + 1);
+ if (current_string_len >= buf_size)
+ {
+ buf_size = current_string_len * 2;
+ buf = (char *) xrealloc (buf, buf_size);
+ }
+ strcat (buf, " ");
+ strcat (buf, name);
+ }
+ strcat (buf, ")");
+ *final_caller = node;
+ return buf;
+}
+
+
+/* Dump the inline decision of EDGE. */
+
+static void
+dump_inline_decision (struct cgraph_edge *edge)
+{
+ location_t locus;
+ const char *inline_chain_text;
+ const char *call_count_text;
+ struct cgraph_node *final_caller = edge->caller;
+
+ if (final_caller->global.inlined_to != NULL)
+ inline_chain_text = cgraph_node_call_chain (final_caller, &final_caller);
+ else
+ inline_chain_text = "";
+
+ if (edge->count > 0)
+ {
+ const char *call_count_str = " with call count ";
+ char *buf = (char *) xmalloc (strlen (call_count_str) + MAX_INT_LENGTH);
+ sprintf (buf, "%s"HOST_WIDEST_INT_PRINT_DEC, call_count_str,
+ edge->count);
+ call_count_text = buf;
+ }
+ else
+ {
+ call_count_text = "";
+ }
+
+ locus = gimple_location (edge->call_stmt);
+ dump_printf_loc (is_in_ipa_inline ? MSG_OPTIMIZED_LOCATIONS : MSG_NOTE,
+ locus,
+ "%s inlined into %s%s%s\n",
+ cgraph_node_opt_info (edge->callee),
+ cgraph_node_opt_info (final_caller),
+ call_count_text,
+ inline_chain_text);
+}
+
+
/* Mark edge E as inlined and update callgraph accordingly. UPDATE_ORIGINAL
specify whether profile of original function should be updated. If any new
indirect edges are discovered in the process, add them to NEW_EDGES, unless
@@ -218,6 +320,9 @@ inline_call (struct cgraph_edge *e, bool update_or
bool predicated = inline_edge_summary (e)->predicate != NULL;
#endif
+ if (dump_enabled_p ())
+ dump_inline_decision (e);
+
/* Don't inline inlined edges. */
gcc_assert (e->inline_failed);
/* Don't even think of inlining inline clone. */
Index: doc/invoke.texi
===================================================================
--- doc/invoke.texi (revision 201461)
+++ doc/invoke.texi (working copy)
@@ -6234,6 +6234,9 @@ Enable dumps from all loop optimizations.
Enable dumps from all inlining optimizations.
@item vec
Enable dumps from all vectorization optimizations.
+@item optall
+Enable dumps from all optimizations. This is a superset of
+the optimization groups listed above.
@end table
For example,
Index: profile.c
===================================================================
--- profile.c (revision 201461)
+++ profile.c (working copy)
@@ -432,8 +432,8 @@ read_profile_edge_counts (gcov_type *exec_counts)
if (flag_profile_correction)
{
static bool informed = 0;
- if (!informed)
- inform (input_location,
+ if (dump_enabled_p () && !informed)
+ dump_printf_loc (MSG_NOTE, input_location,
"corrupted profile info: edge count
exceeds maximal count");
informed = 1;
}
@@ -692,10 +692,11 @@ compute_branch_probabilities (unsigned cfg_checksu
{
/* Inconsistency detected. Make it flow-consistent. */
static int informed = 0;
- if (informed == 0)
+ if (dump_enabled_p () && informed == 0)
{
informed = 1;
- inform (input_location, "correcting inconsistent profile data");
+ dump_printf_loc (MSG_NOTE, input_location,
+ "correcting inconsistent profile data");
}
correct_negative_edge_counts ();
/* Set bb counts to the sum of the outgoing edge counts */
Index: passes.c
===================================================================
--- passes.c (revision 201461)
+++ passes.c (working copy)
@@ -524,6 +524,11 @@ pass_manager::register_one_dump_file (struct opt_p
flag_name = concat (prefix, name, num, NULL);
glob_name = concat (prefix, name, NULL);
optgroup_flags |= pass->optinfo_flags;
+ /* For any passes that do not have an optgroup set, and which are not
+ IPA passes setup above, set the optgroup to OPTGROUP_OTHER so that
+ any dump messages are emitted properly under -fopt-info(-optall). */
+ if (optgroup_flags == OPTGROUP_NONE)
+ optgroup_flags = OPTGROUP_OTHER;
id = dump_register (dot_name, flag_name, glob_name, flags, optgroup_flags);
set_pass_for_id (id, pass);
full_name = concat (prefix, pass->name, num, NULL);
Index: value-prof.c
===================================================================
--- value-prof.c (revision 201461)
+++ value-prof.c (working copy)
@@ -585,9 +585,11 @@ check_counter (gimple stmt, const char * name,
: DECL_SOURCE_LOCATION (current_function_decl);
if (flag_profile_correction)
{
- inform (locus, "correcting inconsistent value profile: "
- "%s profiler overall count (%d) does not match BB count "
- "(%d)", name, (int)*all, (int)bb_count);
+ if (dump_enabled_p ())
+ dump_printf_loc (MSG_MISSED_OPTIMIZATION, locus,
+ "correcting inconsistent value profile: %s "
+ "profiler overall count (%d) does not match BB "
+ "count (%d)", name, (int)*all, (int)bb_count);
*all = bb_count;
if (*count > *all)
*count = *all;
@@ -1209,9 +1211,11 @@ find_func_by_funcdef_no (int func_id)
int max_id = get_last_funcdef_no ();
if (func_id >= max_id || cgraph_node_map[func_id] == NULL)
{
- if (flag_profile_correction)
- inform (DECL_SOURCE_LOCATION (current_function_decl),
- "Inconsistent profile: indirect call target (%d) does
not exist", func_id);
+ if (flag_profile_correction && dump_enabled_p ())
+ dump_printf_loc (MSG_MISSED_OPTIMIZATION,
+ DECL_SOURCE_LOCATION (current_function_decl),
+ "Inconsistent profile: indirect call target (%d) "
+ "does not exist", func_id);
else
error ("Inconsistent profile: indirect call target (%d) does
not exist", func_id);
@@ -1235,8 +1239,10 @@ check_ic_target (gimple call_stmt, struct cgraph_n
return true;
locus = gimple_location (call_stmt);
- inform (locus, "Skipping target %s with mismatching types for icall ",
- cgraph_node_name (target));
+ if (dump_enabled_p ())
+ dump_printf_loc (MSG_MISSED_OPTIMIZATION, locus,
+ "Skipping target %s with mismatching types for icall ",
+ cgraph_node_name (target));
return false;
}
Index: coverage.c
===================================================================
--- coverage.c (revision 201461)
+++ coverage.c (working copy)
@@ -43,6 +43,7 @@ along with GCC; see the file COPYING3. If not see
#include "langhooks.h"
#include "hash-table.h"
#include "tree-iterator.h"
+#include "tree-pass.h"
#include "cgraph.h"
#include "dumpfile.h"
#include "diagnostic-core.h"
@@ -341,11 +342,13 @@ get_coverage_counts (unsigned counter, unsigned ex
{
static int warned = 0;
- if (!warned++)
- inform (input_location, (flag_guess_branch_prob
- ? "file %s not found, execution counts estimated"
- : "file %s not found, execution counts assumed to be zero"),
- da_file_name);
+ if (!warned++ && dump_enabled_p ())
+ dump_printf_loc (MSG_OPTIMIZED_LOCATIONS, input_location,
+ (flag_guess_branch_prob
+ ? "file %s not found, execution counts estimated"
+ : "file %s not found, execution counts assumed to "
+ "be zero"),
+ da_file_name);
return NULL;
}
@@ -369,21 +372,25 @@ get_coverage_counts (unsigned counter, unsigned ex
warning_at (input_location, OPT_Wcoverage_mismatch,
"the control flow of function %qE does not match "
"its profile data (counter %qs)", id, ctr_names[counter]);
- if (warning_printed)
+ if (warning_printed && dump_enabled_p ())
{
- inform (input_location, "use -Wno-error=coverage-mismatch to tolerate "
- "the mismatch but performance may drop if the
function is hot");
+ dump_printf_loc (MSG_OPTIMIZED_LOCATIONS, input_location,
+ "use -Wno-error=coverage-mismatch to tolerate "
+ "the mismatch but performance may drop if the "
+ "function is hot");
if (!seen_error ()
&& !warned++)
{
- inform (input_location, "coverage mismatch ignored");
- inform (input_location, flag_guess_branch_prob
- ? G_("execution counts estimated")
- : G_("execution counts assumed to be zero"));
+ dump_printf_loc (MSG_OPTIMIZED_LOCATIONS, input_location,
+ "coverage mismatch ignored");
+ dump_printf_loc (MSG_OPTIMIZED_LOCATIONS, input_location,
+ flag_guess_branch_prob
+ ? G_("execution counts estimated")
+ : G_("execution counts assumed to be zero"));
if (!flag_guess_branch_prob)
- inform (input_location,
- "this can result in poorly optimized code");
+ dump_printf_loc (MSG_OPTIMIZED_LOCATIONS, input_location,
+ "this can result in poorly optimized code");
}
}
@@ -1103,6 +1110,11 @@ coverage_init (const char *filename)
int len = strlen (filename);
int prefix_len = 0;
+ /* Since coverage_init is invoked very early, before the pass
+ manager, we need to set up the dumping explicitly. This is
+ similar to the handling in finish_optimization_passes. */
+ dump_start (pass_profile.pass.static_pass_number, NULL);
+
if (!profile_data_prefix && !IS_ABSOLUTE_PATH (filename))
profile_data_prefix = getpwd ();
@@ -1145,6 +1157,8 @@ coverage_init (const char *filename)
gcov_write_unsigned (bbg_file_stamp);
}
}
+
+ dump_finish (pass_profile.pass.static_pass_number);
}
/* Performs file-level cleanup. Close notes file, generate coverage
Index: ipa-inline.c
===================================================================
--- ipa-inline.c (revision 201461)
+++ ipa-inline.c (working copy)
@@ -118,6 +118,9 @@ along with GCC; see the file COPYING3. If not see
static int overall_size;
static gcov_type max_count;
+/* Global variable to denote if it is in ipa-inline pass. */
+bool is_in_ipa_inline = false;
+
/* Return false when inlining edge E would lead to violating
limits on function unit growth or stack usage growth.
@@ -1407,6 +1410,8 @@ inline_small_functions (void)
int initial_size = 0;
struct cgraph_node **order = XCNEWVEC (struct cgraph_node *, cgraph_n_nodes);
+ is_in_ipa_inline = true;
+
if (flag_indirect_inlining)
new_indirect_edges.create (8);
Index: ipa-inline.h
===================================================================
--- ipa-inline.h (revision 201461)
+++ ipa-inline.h (working copy)
@@ -234,6 +234,7 @@ void clone_inlined_nodes (struct cgraph_edge *e, b
extern int ncalls_inlined;
extern int nfunctions_inlined;
+extern bool is_in_ipa_inline;
static inline struct inline_summary *
inline_summary (struct cgraph_node *node)
Index: testsuite/gcc.dg/pr40209.c
===================================================================
--- testsuite/gcc.dg/pr40209.c (revision 201461)
+++ testsuite/gcc.dg/pr40209.c (working copy)
@@ -1,5 +1,5 @@
/* { dg-do compile } */
-/* { dg-options "-O2 -fprofile-use" } */
+/* { dg-options "-O2 -fprofile-use -fopt-info" } */
void process(const char *s);
Index: testsuite/gcc.dg/pr26570.c
===================================================================
--- testsuite/gcc.dg/pr26570.c (revision 201461)
+++ testsuite/gcc.dg/pr26570.c (working copy)
@@ -1,5 +1,5 @@
/* { dg-do compile } */
-/* { dg-options "-O2 -fprofile-generate -fprofile-use" } */
+/* { dg-options "-O2 -fprofile-generate -fprofile-use -fopt-info" } */
unsigned test (unsigned a, unsigned b)
{
Index: testsuite/gcc.dg/pr32773.c
===================================================================
--- testsuite/gcc.dg/pr32773.c (revision 201461)
+++ testsuite/gcc.dg/pr32773.c (working copy)
@@ -1,6 +1,6 @@
/* { dg-do compile } */
-/* { dg-options "-O -fprofile-use" } */
-/* { dg-options "-O -m4 -fprofile-use" { target sh-*-* } } */
+/* { dg-options "-O -fprofile-use -fopt-info" } */
+/* { dg-options "-O -m4 -fprofile-use -fopt-info" { target sh-*-* } } */
void foo (int *p)
{
Index: testsuite/g++.dg/tree-ssa/dom-invalid.C
===================================================================
--- testsuite/g++.dg/tree-ssa/dom-invalid.C (revision 201461)
+++ testsuite/g++.dg/tree-ssa/dom-invalid.C (working copy)
@@ -1,7 +1,7 @@
// PR tree-optimization/39557
// invalid post-dom info leads to infinite loop
// { dg-do run }
-// { dg-options "-Wall -fno-exceptions -O2 -fprofile-use -fno-rtti" }
+// { dg-options "-Wall -fno-exceptions -O2 -fprofile-use -fopt-info
-fno-rtti" }
struct C
{
--
Teresa Johnson | Software Engineer | tejohn...@google.com | 408-460-2413
