RFA: Line numbering again - for DWARF2

[Daniel Jacobowitz <drow at mvista dot com>]

This one is a little bit grosser, unfortunately, because we do not encounter
functions at the same time as we encounter line numbers.  I think the
performance hit is reasonably small, though, especially as
check_cu_functions will almost never have to loop more than once or twice. 
It will even behave reasonably well against a -ffunction-sections libstdc++
with DWARF-2 information, because functions end up in 'reasonably close to'
the order they started in.  I tried half a dozen other approaches than this
one and couldn't find one less gross without a significant speed hit.

I also enclude the equivalent of Fred's patch, by calling record_line with a
linenumber of 0 when we see DW_LNS_end_sequence.  The only real difference
between the stabs and DWARF-2 cases appears to be in the padding between
functions in the same sequence, which stabs will mark as belonging to
nothing and DWARF-2 does not go to the trouble of so marking.  That doesn't
particularly matter, though.

Fixes about 80 regressions, introduces one (reread, as I described in my
other patch - I believe it was never properly fixed and this has just
exposed it, I'll look at it soon).

OK to commit?  Any objections?

-- 
Daniel Jacobowitz                           Carnegie Mellon University
MontaVista Software                         Debian GNU/Linux Developer

2002-03-21  Daniel Jacobowitz  <drow@mvista.com>

	* dwarf2read.c (struct function_range): New.
	(cu_first_fn, cu_last_fn, cu_cached_fn): New.
	(check_cu_functions): New.
	(read_file_scope): Initialize global function lists.
	Call dwarf_decode_line after processing children.
	(read_func_scope): Add to global function list.
	(dwarf_decode_lines): Call check_cu_functions everywhere
	record_line is called.  Call record_line with a linenumber
	of 0 to mark sequence ends.

Index: dwarf2read.c
===================================================================
RCS file: /cvs/src/src/gdb/dwarf2read.c,v
retrieving revision 1.51
diff -u -p -r1.51 dwarf2read.c
--- dwarf2read.c	2002/03/21 00:53:44	1.51
+++ dwarf2read.c	2002/03/22 02:23:09
@@ -256,6 +256,15 @@ struct attribute
     u;
   };
 
+struct function_range
+{
+  CORE_ADDR lowpc, highpc;
+  int seen_line;
+  struct function_range *next;
+};
+
+static struct function_range *cu_first_fn, *cu_last_fn, *cu_cached_fn;
+
 /* Get at parts of an attribute structure */
 
 #define DW_STRING(attr)    ((attr)->u.str)
@@ -1633,13 +1642,7 @@ read_file_scope (struct die_info *die, s
   start_symtab (name, comp_dir, lowpc);
   record_debugformat ("DWARF 2");
 
-  /* Decode line number information if present.  */
-  attr = dwarf_attr (die, DW_AT_stmt_list);
-  if (attr)
-    {
-      line_offset = DW_UNSND (attr);
-      dwarf_decode_lines (line_offset, comp_dir, abfd, cu_header);
-    }
+  cu_first_fn = cu_last_fn = cu_cached_fn = NULL;
 
   /* Process all dies in compilation unit.  */
   if (die->has_children)
@@ -1651,6 +1654,14 @@ read_file_scope (struct die_info *die, s
 	  child_die = sibling_die (child_die);
 	}
     }
+
+  /* Decode line number information if present.  */
+  attr = dwarf_attr (die, DW_AT_stmt_list);
+  if (attr)
+    {
+      line_offset = DW_UNSND (attr);
+      dwarf_decode_lines (line_offset, comp_dir, abfd, cu_header);
+    }
 }
 
 static void
@@ -1663,6 +1674,7 @@ read_func_scope (struct die_info *die, s
   struct die_info *child_die;
   struct attribute *attr;
   char *name;
+  struct function_range *thisfn;
 
   name = dwarf2_linkage_name (die);
 
@@ -1674,6 +1686,22 @@ read_func_scope (struct die_info *die, s
   lowpc += baseaddr;
   highpc += baseaddr;
 
+  /* Record the function range for dwarf_decode_lines.  */
+  thisfn = (struct function_range *)
+    obstack_alloc (&dwarf2_tmp_obstack, sizeof (struct function_range));
+  thisfn->lowpc = lowpc;
+  thisfn->highpc = highpc;
+  thisfn->seen_line = 0;
+  thisfn->next = NULL;
+
+  if (cu_last_fn == NULL)
+      cu_first_fn = thisfn;
+  else
+      cu_last_fn->next = thisfn;
+
+  cu_last_fn = thisfn;
+
+
   if (objfile->ei.entry_point >= lowpc &&
       objfile->ei.entry_point < highpc)
     {
@@ -3908,6 +3936,48 @@ struct directories
     char **dirs;
   };
 
+/* This function exists to work around a bug in certain compilers
+   (particularly GCC 2.95), in which the first line number marker of a
+   function does not show up until after the prologue, right before
+   the second line number marker.  This function shifts ADDRESS down
+   to the beginning of the function if necessary, and is called on
+   addresses passed to record_line.  */
+
+static CORE_ADDR
+check_cu_functions (CORE_ADDR address)
+{
+  struct function_range *fn;
+
+  /* Find the function_range containing address.  */
+  if (!cu_first_fn)
+    return address;
+
+  if (!cu_cached_fn)
+    cu_cached_fn = cu_first_fn;
+
+  fn = cu_cached_fn;
+  while (fn)
+    if (fn->lowpc <= address && fn->highpc > address)
+      goto found;
+    else
+      fn = fn->next;
+
+  fn = cu_first_fn;
+  while (fn && fn != cu_cached_fn)
+    if (fn->lowpc <= address && fn->highpc > address)
+      goto found;
+    else
+      fn = fn->next;
+
+  return address;
+
+ found:
+  if (fn->seen_line)
+    return address;
+  fn->seen_line = 1;
+  return fn->lowpc;
+}
+
 static void
 dwarf_decode_lines (unsigned int offset, char *comp_dir, bfd *abfd,
 		    const struct comp_unit_head *cu_header)
@@ -4048,6 +4118,7 @@ dwarf_decode_lines (unsigned int offset,
 		* lh.minimum_instruction_length;
 	      line += lh.line_base + (adj_opcode % lh.line_range);
 	      /* append row to matrix using current values */
+	      address = check_cu_functions (address);
 	      record_line (current_subfile, line, address);
 	      basic_block = 1;
 	    }
@@ -4061,12 +4132,7 @@ dwarf_decode_lines (unsigned int offset,
 		{
 		case DW_LNE_end_sequence:
 		  end_sequence = 1;
-		  /* Don't call record_line here.  The end_sequence
-		     instruction provides the address of the first byte
-		     *after* the last line in the sequence; it's not the
-		     address of any real source line.  However, the GDB
-		     linetable structure only records the starts of lines,
-		     not the ends.  This is a weakness of GDB.  */
+		  record_line (current_subfile, 0, address);
 		  break;
 		case DW_LNE_set_address:
 		  address = read_address (abfd, line_ptr, cu_header, &bytes_read);
@@ -4103,6 +4169,7 @@ dwarf_decode_lines (unsigned int offset,
 		}
 	      break;
 	    case DW_LNS_copy:
+	      address = check_cu_functions (address);
 	      record_line (current_subfile, line, address);
 	      basic_block = 0;
 	      break;