[RFC/dwarf-2] Add support for included files
Joel Brobecker
brobecker@gnat.com
Thu Apr 15 22:13:00 GMT 2004
> Could you try one more thing for me?
Sure!
> As you noticed, the only two functions that dwarf_decode_lines calls
> to actually record the information it gets are
> buildsym.c:start_subfile (via dwarf2_start_subfile) and
> buildsym.c:record_line. Could you change dwarf_decode_lines to take
> two function pointers (with an accompanying closure pointer) for those
> two functions? I guess this is an instance of the 'builder' pattern,
> so maybe name it something appropriately suggestive. Let
> dwarf_decode_lines continue to call dwarf2_start_subfile directly,
> just passing the builder func and closure along with filename and
> dirname.
>
> Then, instead of duplicating dwarf_decode_lines, have the existing
> call in read_file_scope and the new call you've added just pass
> different function/closures to it.
I was just wondering, before trying that, if we couldn't maybe do
it in a little simpler way, but non-generic way.
Using the approach you suggest (which I like): We need to define a
couple of wrapper functions around start_subfile and record_line
because their profile will not match the profile of our callbacks.
We'll need 3 callbacks per case (3 for psymtabs, 3 for symtabs).
We'll also have to use void* pointers if we want to make the context
generic, which I would prefer to avoid. It's great for heavily reused
code, but is this worth it for this function.
What we could do instead, is:
. Add a new parameter: struct partial_symtab *pst
. If this pst is NULL, then scan for symtabs as before
. If pst is non NULL, then scan for partial symtabs, and do not
call the 2 buildsym.c functions.
Just for illustration purposes, I tweaked my previous patch. Attached
is a new patch that shows what it would become. I did this because
even if we end up not choosing this solution, it's still a good
intermediate version on which to implement your suggestion.
I verified that the performance impact on GDB was still pretty small.
If you like it, then I'll review, clean it up and properly submit it
for review. Otherwise, I'll send a new version including your
suggestion.
Thanks,
--
Joel
-------------- next part --------------
Index: dwarf2read.c
===================================================================
RCS file: /cvs/src/src/gdb/dwarf2read.c,v
retrieving revision 1.142
diff -u -p -r1.142 dwarf2read.c
--- dwarf2read.c 2 Apr 2004 04:35:46 -0000 1.142
+++ dwarf2read.c 15 Apr 2004 22:02:36 -0000
@@ -583,6 +583,13 @@ static void dwarf2_locate_sections (bfd
static void dwarf2_build_psymtabs_easy (struct objfile *, int);
#endif
+static void dwarf2_create_include_psymtab (char *, struct partial_symtab *,
+ struct objfile *);
+
+static void dwarf2_build_include_psymtabs (struct dwarf2_cu *,
+ const unsigned int,
+ struct partial_symtab *);
+
static void dwarf2_build_psymtabs_hard (struct objfile *, int);
static char *scan_partial_symbols (char *, CORE_ADDR *, CORE_ADDR *,
@@ -629,7 +636,8 @@ static struct abbrev_info *dwarf2_lookup
struct dwarf2_cu *);
static char *read_partial_die (struct partial_die_info *,
- bfd *, char *, struct dwarf2_cu *);
+ bfd *, char *, struct dwarf2_cu *,
+ unsigned int *);
static char *read_full_die (struct die_info **, bfd *, char *,
struct dwarf2_cu *, int *);
@@ -684,12 +692,15 @@ static struct die_info *die_specificatio
static void free_line_header (struct line_header *lh);
+static void add_file_name (struct line_header *, char *, unsigned int,
+ unsigned int, unsigned int);
+
static struct line_header *(dwarf_decode_line_header
(unsigned int offset,
bfd *abfd, struct dwarf2_cu *cu));
static void dwarf_decode_lines (struct line_header *, char *, bfd *,
- struct dwarf2_cu *);
+ struct dwarf2_cu *, struct partial_symtab *);
static void dwarf2_start_subfile (char *, char *);
@@ -1100,6 +1111,65 @@ read_comp_unit_head (struct comp_unit_he
return info_ptr;
}
+/* Allocate a new partial symtab for file named NAME and mark this new
+ partial symtab as being an include of PST. */
+
+static void
+dwarf2_create_include_psymtab (char *name, struct partial_symtab *pst,
+ struct objfile *objfile)
+{
+ struct partial_symtab *subpst = allocate_psymtab (name, objfile);
+
+ subpst->section_offsets = pst->section_offsets;
+ subpst->textlow = 0;
+ subpst->texthigh = 0;
+
+ subpst->dependencies = (struct partial_symtab **)
+ obstack_alloc (&objfile->objfile_obstack,
+ sizeof (struct partial_symtab *));
+ subpst->dependencies[0] = pst;
+ subpst->number_of_dependencies = 1;
+
+ subpst->globals_offset = 0;
+ subpst->n_global_syms = 0;
+ subpst->statics_offset = 0;
+ subpst->n_static_syms = 0;
+ subpst->symtab = NULL;
+ subpst->read_symtab = pst->read_symtab;
+ subpst->readin = 0;
+
+ /* No private part is necessary for include psymtabs. This property
+ can be used to differentiate between such include psymtabs and
+ the regular ones. If it ever happens that a regular psymtab can
+ legitimally have a NULL PST_PRIVATE part, then we'll have to add a
+ dedicated field for that in the dwarf2_pinfo structure. */
+ PST_PRIVATE (subpst) = NULL;
+}
+
+/* Read the line number information located at LINE_OFFSET,
+ and extract the list of sources files included by the
+ source file represented by PST. Build an include partial
+ symtab for each of these included files. */
+
+static void
+dwarf2_build_include_psymtabs (struct dwarf2_cu *cu,
+ const unsigned int line_offset,
+ struct partial_symtab *pst)
+{
+ struct objfile *objfile = cu->objfile;
+ bfd *abfd = objfile->obfd;
+ struct line_header *lh;
+
+ lh = dwarf_decode_line_header (line_offset, abfd, cu);
+ if (lh == NULL)
+ return; /* No linetable, so no includes. */
+
+ dwarf_decode_lines (lh, NULL, abfd, cu, pst);
+
+ free_line_header (lh);
+}
+
+
/* Build the partial symbol table by doing a quick pass through the
.debug_info and .debug_abbrev sections. */
@@ -1168,6 +1238,8 @@ dwarf2_build_psymtabs_hard (struct objfi
{
struct cleanup *back_to_inner;
struct dwarf2_cu cu;
+ unsigned int line_offset = 0;
+
beg_of_comp_unit = info_ptr;
cu.objfile = objfile;
@@ -1208,7 +1280,7 @@ dwarf2_build_psymtabs_hard (struct objfi
/* Read the compilation unit die */
info_ptr = read_partial_die (&comp_unit_die, abfd, info_ptr,
- &cu);
+ &cu, &line_offset);
/* Set the language we're debugging */
set_cu_language (comp_unit_die.language, &cu);
@@ -1269,6 +1341,10 @@ dwarf2_build_psymtabs_hard (struct objfi
info_ptr = beg_of_comp_unit + cu.header.length
+ cu.header.initial_length_size;
+ /* Get the list of files included in the current compilation unit,
+ and build a psymtab for each of them. */
+ dwarf2_build_include_psymtabs (&cu, line_offset, pst);
+
do_cleanups (back_to_inner);
}
do_cleanups (back_to);
@@ -1300,7 +1376,7 @@ scan_partial_symbols (char *info_ptr, CO
inside the loop. */
int info_ptr_updated = 0;
- info_ptr = read_partial_die (&pdi, abfd, info_ptr, cu);
+ info_ptr = read_partial_die (&pdi, abfd, info_ptr, cu, NULL);
/* Anonymous namespaces have no name but have interesting
children, so we need to look at them. Ditto for anonymous
@@ -1652,7 +1728,7 @@ add_partial_structure (struct partial_di
struct partial_die_info child_pdi;
next_child = read_partial_die (&child_pdi, abfd, next_child,
- cu);
+ cu, NULL);
if (!child_pdi.tag)
break;
if (child_pdi.tag == DW_TAG_subprogram)
@@ -1691,7 +1767,7 @@ add_partial_enumeration (struct partial_
while (1)
{
- info_ptr = read_partial_die (&pdi, abfd, info_ptr, cu);
+ info_ptr = read_partial_die (&pdi, abfd, info_ptr, cu, NULL);
if (pdi.tag == 0)
break;
if (pdi.tag != DW_TAG_enumerator || pdi.name == NULL)
@@ -1916,6 +1992,32 @@ psymtab_to_symtab_1 (struct partial_symt
struct cleanup *back_to;
struct attribute *attr;
CORE_ADDR baseaddr;
+ int i;
+
+ for (i = 0; i < pst->number_of_dependencies; i++)
+ if (!pst->dependencies[i]->readin)
+ {
+ /* Inform about additional files that need to be read in. */
+ if (info_verbose)
+ {
+ fputs_filtered (" ", gdb_stdout);
+ wrap_here ("");
+ fputs_filtered ("and ", gdb_stdout);
+ wrap_here ("");
+ printf_filtered ("%s...", pst->dependencies[i]->filename);
+ wrap_here (""); /* Flush output */
+ gdb_flush (gdb_stdout);
+ }
+ psymtab_to_symtab_1 (pst->dependencies[i]);
+ }
+
+ if (PST_PRIVATE (pst) == NULL)
+ {
+ /* It's an include file, no symbols to read for it.
+ Everything is in the parent symtab. */
+ pst->readin = 1;
+ return;
+ }
dwarf2_per_objfile = objfile_data (pst->objfile, dwarf2_objfile_data_key);
@@ -2204,7 +2306,7 @@ read_file_scope (struct die_info *die, s
{
make_cleanup ((make_cleanup_ftype *) free_line_header,
(void *) line_header);
- dwarf_decode_lines (line_header, comp_dir, abfd, cu);
+ dwarf_decode_lines (line_header, comp_dir, abfd, cu, NULL);
}
}
@@ -4414,11 +4516,14 @@ dwarf2_lookup_abbrev (unsigned int numbe
return NULL;
}
-/* Read a minimal amount of information into the minimal die structure. */
+/* Read a minimal amount of information into the minimal die structure.
+ If not NULL, the offset where the Line Number Information data is
+ stored will be saved in LINE_OFFSET. */
static char *
read_partial_die (struct partial_die_info *part_die, bfd *abfd,
- char *info_ptr, struct dwarf2_cu *cu)
+ char *info_ptr, struct dwarf2_cu *cu,
+ unsigned int *line_offset)
{
unsigned int abbrev_number, bytes_read, i;
struct abbrev_info *abbrev;
@@ -4512,6 +4617,9 @@ read_partial_die (struct partial_die_inf
part_die->sibling = dwarf2_per_objfile->info_buffer
+ dwarf2_get_ref_die_offset (&attr, cu);
break;
+ case DW_AT_stmt_list:
+ if (line_offset != NULL)
+ *line_offset = DW_UNSND (&attr);
default:
break;
}
@@ -4527,7 +4635,7 @@ read_partial_die (struct partial_die_inf
spec_ptr = dwarf2_per_objfile->info_buffer
+ dwarf2_get_ref_die_offset (&spec_attr, cu);
- read_partial_die (&spec_die, abfd, spec_ptr, cu);
+ read_partial_die (&spec_die, abfd, spec_ptr, cu, NULL);
if (spec_die.name)
{
part_die->name = spec_die.name;
@@ -5399,7 +5507,7 @@ check_cu_functions (CORE_ADDR address, s
static void
dwarf_decode_lines (struct line_header *lh, char *comp_dir, bfd *abfd,
- struct dwarf2_cu *cu)
+ struct dwarf2_cu *cu, struct partial_symtab *pst)
{
char *line_ptr;
char *line_end;
@@ -5408,6 +5516,38 @@ dwarf_decode_lines (struct line_header *
CORE_ADDR baseaddr;
struct objfile *objfile = cu->objfile;
+ /* When decoding the Line Number Program for the purpose of building
+ the partial symtabs included by the current CU, we need to do
+ the following:
+
+ We first scan the Line Header. It contains a list of files referenced
+ by the Line Number Program. We then scan the Line Number Program
+ for opcodes changing the source file. For each file selected in
+ the program, we mark it as included using the FILE_IS_INCLUDED
+ array. Once we're finished scanning the Line Number Program, we can
+ then iterate over FILE_IS_INCLUDED and create a corresponding
+ include partial symtab for each file that was marked as included.
+ */
+
+ /* FILE_IS_INCLUDED is an array allocated on the heap, which size
+ is stored in FILE_IS_INCLUDED_SIZE. Each element of this array
+ corresponds to the file of the same index in the Line Header,
+ as stored in the line_header struct we built for the current unit.
+ Each element is initially set to zero, and then to nonzero if the
+ corresponding file is included. The size of this array may be
+ larger than necessary, and the number of meaningful entries is
+ stored in lh->num_file_names. */
+ char *file_is_included = NULL;
+ int file_is_included_size = 0;
+ const int decode_for_pst_p = (pst != NULL);
+
+ if (decode_for_pst_p)
+ {
+ file_is_included = xmalloc (lh->file_names_size * sizeof (char));
+ memset (file_is_included, 0, lh->file_names_size * sizeof (char));
+ file_is_included_size = lh->file_names_size;
+ }
+
baseaddr = ANOFFSET (objfile->section_offsets, SECT_OFF_TEXT (objfile));
line_ptr = lh->statement_program_start;
@@ -5425,9 +5565,9 @@ dwarf_decode_lines (struct line_header *
int basic_block = 0;
int end_sequence = 0;
- /* Start a subfile for the current file of the state machine. */
- if (lh->num_file_names >= file)
+ if (!decode_for_pst_p && lh->num_file_names >= file)
{
+ /* Start a subfile for the current file of the state machine. */
/* lh->include_dirs and lh->file_names are 0-based, but the
directory and file name numbers in the statement program
are 1-based. */
@@ -5452,9 +5592,12 @@ dwarf_decode_lines (struct line_header *
address += (adj_opcode / lh->line_range)
* lh->minimum_instruction_length;
line += lh->line_base + (adj_opcode % lh->line_range);
- /* append row to matrix using current values */
- record_line (current_subfile, line,
- check_cu_functions (address, cu));
+ if (!decode_for_pst_p)
+ {
+ /* append row to matrix using current values */
+ record_line (current_subfile, line,
+ check_cu_functions (address, cu));
+ }
basic_block = 1;
}
else switch (op_code)
@@ -5467,7 +5610,8 @@ dwarf_decode_lines (struct line_header *
{
case DW_LNE_end_sequence:
end_sequence = 1;
- record_line (current_subfile, 0, address);
+ if (!decode_for_pst_p)
+ record_line (current_subfile, 0, address);
break;
case DW_LNE_set_address:
address = read_address (abfd, line_ptr, cu, &bytes_read);
@@ -5491,6 +5635,20 @@ dwarf_decode_lines (struct line_header *
read_unsigned_leb128 (abfd, line_ptr, &bytes_read);
line_ptr += bytes_read;
add_file_name (lh, cur_file, dir_index, mod_time, length);
+
+ if (decode_for_pst_p)
+ {
+ if (file_is_included_size != lh->file_names_size)
+ {
+ /* The add_file_name() operation above caused
+ the file_names array size in the line_header
+ struct to be increased. Increase our
+ file_is_included array size accordingly. */
+ file_is_included = xrealloc (file_is_included,
+ lh->file_names_size);
+ }
+ file_is_included [lh->num_file_names - 1] = 0;
+ }
}
break;
default:
@@ -5500,8 +5658,9 @@ dwarf_decode_lines (struct line_header *
}
break;
case DW_LNS_copy:
- record_line (current_subfile, line,
- check_cu_functions (address, cu));
+ if (!decode_for_pst_p)
+ record_line (current_subfile, line,
+ check_cu_functions (address, cu));
basic_block = 0;
break;
case DW_LNS_advance_pc:
@@ -5527,7 +5686,10 @@ dwarf_decode_lines (struct line_header *
dir = lh->include_dirs[fe->dir_index - 1];
else
dir = comp_dir;
- dwarf2_start_subfile (fe->name, dir);
+ if (decode_for_pst_p)
+ file_is_included[file - 1] = 1;
+ else
+ dwarf2_start_subfile (fe->name, dir);
}
break;
case DW_LNS_set_column:
@@ -5564,6 +5726,22 @@ dwarf_decode_lines (struct line_header *
}
}
}
+ }
+
+ if (decode_for_pst_p)
+ {
+ int file_index;
+
+ /* Now that we're done scanning the Line Header Program, we can
+ create the psymtab of each included file. */
+ for (file_index = 0; file_index < lh->num_file_names; file_index++)
+ if (file_is_included[file_index] == 1)
+ {
+ char *include_name = lh->file_names [file_index].name;
+
+ if (strcmp (include_name, pst->filename) != 0)
+ dwarf2_create_include_psymtab (include_name, pst, objfile);
+ }
}
}
More information about the Gdb-patches
mailing list