[PATCH 5/7] Add line map statistics to -fmem-report output

[Dodji Seketeli <dodji@redhat.com>]

This patch adds statistics about line maps' memory consumption and
macro expansion to the output of -fmem-report.  It has been useful in
trying to reduce the memory consumption of the macro maps support.

Tested on x86_64-unknown-linux-gnu against trunk.

gcc/
	* input.c (ONE_K, ONE_M, SCALE, STAT_LABEL, FORMAT_AMOUNT): New
	macros.
	(num_expanded_macros_counter, num_macro_tokens_counter): Declare
	new counters.
	(dump_line_table_statistics): Define new function.
	* input.h (dump_line_table_statistics): Declare new function.
	* toplev.c (dump_memory_report): Call dump_line_table_statistics.

libcpp/
	* line-map.h (struct linemap_stats): Declare new struct.
	(linemap_get_statistics): Declare ...
	* line-map.c (linemap_get_statistics):  ... new function.
	* macro.c (num_expanded_macros_counter, num_macro_tokens_counter):
	Declare new counters.
	(enter_macro_context, replace_args): Update
	num_macro_tokens_counter.
	(cpp_get_token_1): Update num_expanded_macros_counter.
---
 gcc/input.c               |   83 +++++++++++++++++++++++++++++++++++++++++++++
 gcc/input.h               |    2 +
 gcc/toplev.c              |    1 +
 libcpp/include/line-map.h |   17 +++++++++
 libcpp/line-map.c         |   62 +++++++++++++++++++++++++++++++++
 libcpp/macro.c            |   29 +++++++++++++--
 6 files changed, 190 insertions(+), 4 deletions(-)

diff --git a/gcc/input.c b/gcc/input.c
index f3c7bfa..614db3e 100644
--- a/gcc/input.c
+++ b/gcc/input.c
@@ -61,3 +61,86 @@ expand_location (source_location loc)
     }
   return xloc;
 }
+
+#define ONE_K 1024
+#define ONE_M ONE_K * ONE_K
+
+/* Display a number as an integer multiple of either:
+   - 1024, if said integer is >= to 10 K (in base 2)
+   - 1024 * 1024, if said integer is >= 10 M in (base 2)
+ */
+#define SCALE(x) ((unsigned long) ((x) < 10 * ONE_K \
+		  ? (x) \
+		  : ((x) < 10 * ONE_M \
+		     ? (x) / ONE_K \
+		     : (x) / (ONE_M))))
+
+/* For a given integer, display either:
+   - the character 'k', if the number is higher than 10 K (in base 2)
+     but strictly lower than 10 M (in base 2)
+   - the character 'M' if the number is higher than 10 M (in base2)
+   - the charcter ' ' if the number is strictly lower  than 10 K  */
+#define STAT_LABEL(x) ((x) < 10 * ONE_K ? ' ' : ((x) < 10 * ONE_M ? 'k' : 'M'))
+
+/* Display an integer amount as multiple of 1K or 1M (in base 2à).
+   Display the correct unit (either k, M, or ' ') after the amout, as
+   well.  */
+#define FORMAT_AMOUNT(size) SCALE (size), STAT_LABEL (size)
+
+/* Counters defined in libcpp's macro.c.  */
+extern unsigned num_expanded_macros_counter;
+extern unsigned num_macro_tokens_counter;
+
+/* Dump statistics to stderr about the memory usage of the line_table
+   set of line maps.  This also displays some statistics about macro
+   expansion.  */
+
+void
+dump_line_table_statistics (void)
+{
+  struct linemap_stats s;
+
+  memset (&s, 0, sizeof (s));
+
+  fprintf (stderr, "Number of expanded macros:                     %u\n",
+	   num_expanded_macros_counter);  
+  if (num_expanded_macros_counter != 0)
+    fprintf (stderr, "Average number of tokens per macro expansion:  %u\n",
+	     num_macro_tokens_counter / num_expanded_macros_counter);
+  linemap_get_statistics (line_table, &s);
+
+  fprintf (stderr,
+	   "\nLine Table allocations during the "
+	   "compilation process\n");
+  fprintf (stderr, "Total allocated maps size:           %5lu%c\n",
+	   SCALE (s.total_allocated_map_size),
+	   STAT_LABEL (s.total_allocated_map_size));
+  fprintf (stderr, "Total used maps size:                %5lu%c\n",
+	   SCALE (s.total_used_map_size),
+	   STAT_LABEL (s.total_used_map_size));
+  fprintf (stderr, "Ordinary map used size:              %5lu%c\n",
+	   SCALE (s.ordinary_maps_used_size),
+	   STAT_LABEL (s.ordinary_maps_used_size));
+  fprintf (stderr, "Macro maps used size:                %5lu%c\n",
+	   SCALE (s.macro_maps_used_size),
+	   STAT_LABEL (s.macro_maps_used_size));
+  fprintf (stderr, "Number of ordinary maps allocated:   %5lu%c\n",
+	   SCALE (s.num_ordinary_maps_allocated),
+	   STAT_LABEL (s.num_ordinary_maps_allocated));
+  fprintf (stderr, "Number of ordinary maps used:        %5lu%c\n",
+	   SCALE (s.num_ordinary_maps_used),
+	   STAT_LABEL (s.num_ordinary_maps_used));
+  fprintf (stderr, "Number of macro maps used:           %5lu%c\n",
+	   SCALE (s.num_macro_maps_used),
+	   STAT_LABEL (s.num_macro_maps_used));
+  fprintf (stderr, "Ordinary maps allocated size:        %5lu%c\n",
+	   SCALE (s.ordinary_maps_allocated_size),
+	   STAT_LABEL (s.ordinary_maps_allocated_size));
+  fprintf (stderr, "Macro maps locations size:           %5lu%c\n",
+	   SCALE (s.macro_maps_locations_size),
+	   STAT_LABEL (s.macro_maps_locations_size));
+  fprintf (stderr, "Duplicated maps locations size:      %5lu%c\n",
+	   SCALE (s.duplicated_macro_maps_locations_size),
+	   STAT_LABEL (s.duplicated_macro_maps_locations_size));
+  fprintf (stderr, "\n");
+}
diff --git a/gcc/input.h b/gcc/input.h
index 835c95a..ca122b5 100644
--- a/gcc/input.h
+++ b/gcc/input.h
@@ -55,4 +55,6 @@ extern location_t input_location;
   ((linemap_location_in_system_header_p (line_table, LOC)))
 #define in_system_header  (in_system_header_at (input_location))
 
+void dump_line_table_statistics (void);
+
 #endif
diff --git a/gcc/toplev.c b/gcc/toplev.c
index 9a98c5f..6626e7a 100644
--- a/gcc/toplev.c
+++ b/gcc/toplev.c
@@ -1788,6 +1788,7 @@ target_reinit (void)
 void
 dump_memory_report (bool final)
 {
+  dump_line_table_statistics ();
   ggc_print_statistics ();
   stringpool_statistics ();
   dump_tree_statistics ();
diff --git a/libcpp/include/line-map.h b/libcpp/include/line-map.h
index ba937d6..58ad98c 100644
--- a/libcpp/include/line-map.h
+++ b/libcpp/include/line-map.h
@@ -837,6 +837,23 @@ expanded_location linemap_expand_location_full (struct line_maps *,
 						enum location_resolution_kind lrk,
 						source_location *resulting_loc,
 						const struct line_map **loc_map);
+struct linemap_stats
+{
+  size_t num_ordinary_maps_allocated;
+  size_t num_ordinary_maps_used;
+  size_t ordinary_maps_allocated_size;
+  size_t ordinary_maps_used_size;
+  size_t num_macro_maps_used;
+  size_t macro_maps_used_size;
+  size_t macro_maps_locations_size;
+  size_t duplicated_macro_maps_locations_size;
+  size_t total_allocated_map_size;
+  size_t total_used_map_size;
+};
+
+/* Compute and return statistics about the memory consumption of some
+   parts of the line table SET.  */
+void linemap_get_statistics (struct line_maps *, struct linemap_stats *);
 
 /* Dump debugging information about source location LOC into the file
    stream STREAM. SET is the line map set LOC comes from.  */
diff --git a/libcpp/line-map.c b/libcpp/line-map.c
index 2bf743c..d69160c 100644
--- a/libcpp/line-map.c
+++ b/libcpp/line-map.c
@@ -836,3 +836,65 @@ linemap_dump_location (struct line_maps *set,
   fprintf (stream, "{P:%s;F:%s;L:%d;C:%d;S:%d;M:%p;E:%d,LOC:%d}",
 	   path, from, l, c, s, (void*)map, e, loc);
 }
+
+void
+linemap_get_statistics (struct line_maps *set,
+			struct linemap_stats *s)
+{
+  size_t ordinary_maps_allocated_size, ordinary_maps_used_size,
+    macro_maps_allocated_size, macro_maps_used_size,
+    macro_maps_locations_size = 0, duplicated_macro_maps_locations_size = 0,
+    total_allocated_map_size, total_used_map_size;
+  struct line_map *cur_map;
+
+  ordinary_maps_allocated_size =
+    LINEMAPS_ORDINARY_ALLOCATED (set) * sizeof (struct line_map);
+
+  ordinary_maps_used_size =
+    LINEMAPS_ORDINARY_USED (set) * sizeof (struct line_map);
+
+  macro_maps_allocated_size =
+    LINEMAPS_MACRO_ALLOCATED (set) * sizeof (struct line_map);
+
+  for (cur_map = LINEMAPS_MACRO_MAPS (set);
+       cur_map && cur_map <= LINEMAPS_LAST_MACRO_MAP (set);
+       ++cur_map)
+    {
+      unsigned i;
+
+      linemap_assert (linemap_macro_expansion_map_p (cur_map));
+
+      macro_maps_locations_size +=
+	2 * MACRO_MAP_NUM_MACRO_TOKENS (cur_map) * sizeof (source_location);
+
+      for (i = 0; i < 2 * MACRO_MAP_NUM_MACRO_TOKENS (cur_map); i+=2)
+	{
+	  if (MACRO_MAP_LOCATIONS (cur_map)[i] ==
+	      MACRO_MAP_LOCATIONS (cur_map)[i + 1])
+	    duplicated_macro_maps_locations_size +=
+	      sizeof (source_location);
+	}
+    }
+
+  macro_maps_used_size =
+    LINEMAPS_MACRO_USED (set) * sizeof (struct line_map)
+    + macro_maps_locations_size;
+
+  total_used_map_size = ordinary_maps_used_size + macro_maps_used_size;
+
+  total_allocated_map_size =
+    ordinary_maps_allocated_size + macro_maps_allocated_size +
+    macro_maps_locations_size;
+
+  s->num_ordinary_maps_allocated = LINEMAPS_ORDINARY_ALLOCATED (set);
+  s->num_ordinary_maps_used = LINEMAPS_ORDINARY_USED (set);
+  s->ordinary_maps_allocated_size = ordinary_maps_allocated_size;
+  s->ordinary_maps_used_size = ordinary_maps_used_size;
+  s->num_macro_maps_used = LINEMAPS_MACRO_USED (set);
+  s->macro_maps_used_size = macro_maps_used_size;
+  s->macro_maps_locations_size = macro_maps_locations_size;
+  s->duplicated_macro_maps_locations_size =
+    duplicated_macro_maps_locations_size;
+  s->total_allocated_map_size = total_allocated_map_size;
+  s->total_used_map_size = total_used_map_size;
+}
diff --git a/libcpp/macro.c b/libcpp/macro.c
index 936e1b4..e4f941b 100644
--- a/libcpp/macro.c
+++ b/libcpp/macro.c
@@ -173,6 +173,13 @@ static void consume_next_token_from_context (cpp_reader *pfile,
 					     source_location *);
 static const cpp_token* cpp_get_token_1 (cpp_reader *, source_location *);
 
+/* Statistical counter tracking the number of macros that got
+   expanded.  */
+unsigned num_expanded_macros_counter = 0;
+/* Statistical counter tracking the total number tokens resulting
+   from macro expansion.  */
+unsigned num_macro_tokens_counter = 0;
+
 /* Emits a warning if NODE is a macro defined in the main file that
    has not been used.  */
 int
@@ -1088,10 +1095,15 @@ enter_macro_context (cpp_reader *pfile, cpp_hashnode *node,
 					    (const cpp_token **)
 					    macro_tokens->base,
 					    count);
+	      num_macro_tokens_counter += count;
 	    }
 	  else
-	    _cpp_push_token_context (pfile, node, macro->exp.tokens,
-				     macro_real_token_count (macro));
+	    {
+	      unsigned tokens_count = macro_real_token_count (macro);
+	      _cpp_push_token_context (pfile, node, macro->exp.tokens,
+				       tokens_count);
+	      num_macro_tokens_counter += tokens_count;
+	    }
 	}
 
       if (pragma_buff)
@@ -1101,13 +1113,18 @@ enter_macro_context (cpp_reader *pfile, cpp_hashnode *node,
 				     padding_token (pfile, result), 1);
 	  do
 	    {
+	      unsigned tokens_count;
 	      _cpp_buff *tail = pragma_buff->next;
 	      pragma_buff->next = NULL;
+	      tokens_count = ((const cpp_token **) BUFF_FRONT (pragma_buff)
+			      - (const cpp_token **) pragma_buff->base);
 	      push_ptoken_context (pfile, NULL, pragma_buff,
 				   (const cpp_token **) pragma_buff->base,
-				   ((const cpp_token **) BUFF_FRONT (pragma_buff)
-				    - (const cpp_token **) pragma_buff->base));
+				   tokens_count);
 	      pragma_buff = tail;
+	      if (!CPP_OPTION (pfile, track_macro_expansion))
+		num_macro_tokens_counter += tokens_count;
+
 	    }
 	  while (pragma_buff != NULL);
 	  return 2;
@@ -1706,6 +1723,8 @@ replace_args (cpp_reader *pfile, cpp_hashnode *node, cpp_macro *macro,
   else
     push_ptoken_context (pfile, node, buff, first,
 			 tokens_buff_count (buff));
+
+  num_macro_tokens_counter += tokens_buff_count (buff);
 }
 
 /* Return a special padding token, with padding inherited from SOURCE.  */
@@ -2250,6 +2269,8 @@ cpp_get_token_1 (cpp_reader *pfile, source_location *location)
 	}
       else
 	{
+	  if (pfile->context->macro)
+	    ++num_expanded_macros_counter;
 	  _cpp_pop_context (pfile);
 	  if (pfile->state.in_directive)
 	    continue;
-- 
1.7.6