* [PATCH] ld: Generate PDB string table
@ 2022-11-24 3:40 Mark Harmstone
2022-11-24 7:24 ` Jan Beulich
0 siblings, 1 reply; 2+ messages in thread
From: Mark Harmstone @ 2022-11-24 3:40 UTC (permalink / raw)
To: binutils; +Cc: Mark Harmstone
---
ld/pdb.c | 296 +++++++++++++++++++++++++++++-
ld/pdb.h | 12 ++
ld/testsuite/ld-pe/pdb-strings.d | 10 +
ld/testsuite/ld-pe/pdb-strings1.s | 19 ++
ld/testsuite/ld-pe/pdb-strings2.s | 19 ++
ld/testsuite/ld-pe/pdb.exp | 122 ++++++++++++
6 files changed, 472 insertions(+), 6 deletions(-)
create mode 100644 ld/testsuite/ld-pe/pdb-strings.d
create mode 100644 ld/testsuite/ld-pe/pdb-strings1.s
create mode 100644 ld/testsuite/ld-pe/pdb-strings2.s
diff --git a/ld/pdb.c b/ld/pdb.c
index 6f69574289d..9e8f0ed1ce3 100644
--- a/ld/pdb.c
+++ b/ld/pdb.c
@@ -41,6 +41,23 @@ struct public
uint32_t address;
};
+struct string
+{
+ struct string *next;
+ uint32_t hash;
+ uint32_t offset;
+ size_t len;
+ char s[];
+};
+
+struct string_table
+{
+ struct string *strings_head;
+ struct string *strings_tail;
+ uint32_t strings_len;
+ htab_t hashmap;
+};
+
/* Add a new stream to the PDB archive, and return its BFD. */
static bfd *
add_stream (bfd *pdb, const char *name, uint16_t *stream_num)
@@ -383,15 +400,170 @@ get_arch_number (bfd *abfd)
return IMAGE_FILE_MACHINE_I386;
}
+/* Add a string to the strings table, if it's not already there. */
+static void
+add_string (char *str, size_t len, struct string_table *strings)
+{
+ uint32_t hash = calc_hash (str, len);
+ void **slot;
+
+ slot = htab_find_slot_with_hash (strings->hashmap, str, hash, INSERT);
+
+ if (slot && !*slot)
+ {
+ struct string *s;
+
+ *slot = xmalloc (offsetof (struct string, s) + len);
+
+ s = (struct string *) *slot;
+
+ s->next = NULL;
+ s->hash = hash;
+ s->offset = strings->strings_len;
+ s->len = len;
+ memcpy (s->s, str, len);
+
+ if (strings->strings_tail)
+ strings->strings_tail->next = s;
+ else
+ strings->strings_head = s;
+
+ strings->strings_tail = s;
+
+ strings->strings_len += len + 1;
+ }
+}
+
+/* Return the hash of an entry in the string table. */
+static hashval_t
+hash_string_table_entry (const void * p)
+{
+ struct string *s = (struct string *) p;
+
+ return s->hash;
+}
+
+/* Compare an entry in the string table with a string. */
+static int
+eq_string_table_entry (const void *a, const void *b)
+{
+ struct string *s1 = (struct string *) a;
+ const char *s2 = (const char *) b;
+ size_t s2_len = strlen (s2);
+
+ if (s2_len != s1->len)
+ return 0;
+
+ return memcmp (s1->s, s2, s2_len) == 0;
+}
+
+/* Parse the string table within the .debug$S section. */
+static void
+parse_string_table (bfd_byte *data, size_t size,
+ struct string_table *strings)
+{
+ while (true)
+ {
+ size_t len = strnlen ((char *) data, size);
+
+ add_string ((char *) data, len, strings);
+
+ data += len + 1;
+
+ if (size <= len + 1)
+ break;
+
+ size -= len + 1;
+ }
+}
+
+/* Parse the .debug$S section within an object file. */
+static bool
+handle_debugs_section (asection *s, bfd *mod, struct string_table *strings)
+{
+ bfd_byte *data = NULL;
+ size_t off;
+
+ if (!bfd_get_full_section_contents (mod, s, &data))
+ return false;
+
+ if (!data)
+ return false;
+
+ if (bfd_getl32 (data) != CV_SIGNATURE_C13)
+ {
+ free (data);
+ return true;
+ }
+
+ off = sizeof (uint32_t);
+
+ while (off + sizeof (uint32_t) <= s->size)
+ {
+ uint32_t type, size;
+
+ type = bfd_getl32 (data + off);
+
+ off += sizeof (uint32_t);
+
+ if (off + sizeof (uint32_t) > s->size)
+ {
+ free (data);
+ bfd_set_error (bfd_error_bad_value);
+ return false;
+ }
+
+ size = bfd_getl32 (data + off);
+
+ off += sizeof (uint32_t);
+
+ if (off + size > s->size)
+ {
+ free (data);
+ bfd_set_error (bfd_error_bad_value);
+ return false;
+ }
+
+ switch (type)
+ {
+ case DEBUG_S_STRINGTABLE:
+ parse_string_table (data + off, size, strings);
+
+ break;
+ }
+
+ off += size;
+
+ if (off % sizeof (uint32_t))
+ off += sizeof (uint32_t) - (off % sizeof (uint32_t));
+ }
+
+ free (data);
+
+ return true;
+}
+
/* Populate the module stream, which consists of the transformed .debug$S
data for each object file. */
static bool
-populate_module_stream (bfd *stream, uint32_t *sym_byte_size)
+populate_module_stream (bfd *stream, bfd *mod, uint32_t *sym_byte_size,
+ struct string_table *strings)
{
uint8_t int_buf[sizeof (uint32_t)];
*sym_byte_size = sizeof (uint32_t);
+ /* Process .debug$S section(s). */
+
+ for (asection *s = mod->sections; s; s = s->next)
+ {
+ if (!strcmp (s->name, ".debug$S") && s->size >= sizeof (uint32_t))
+ {
+ if (!handle_debugs_section (s, mod, strings))
+ return false;
+ }
+ }
+
/* Write the signature. */
bfd_putl32 (CV_SIGNATURE_C13, int_buf);
@@ -412,7 +584,7 @@ populate_module_stream (bfd *stream, uint32_t *sym_byte_size)
/* Create the module info substream within the DBI. */
static bool
create_module_info_substream (bfd *abfd, bfd *pdb, void **data,
- uint32_t *size)
+ uint32_t *size, struct string_table *strings)
{
uint8_t *ptr;
@@ -482,7 +654,8 @@ create_module_info_substream (bfd *abfd, bfd *pdb, void **data,
return false;
}
- if (!populate_module_stream (stream, &sym_byte_size))
+ if (!populate_module_stream (stream, in, &sym_byte_size,
+ strings))
{
free (*data);
return false;
@@ -687,14 +860,16 @@ static bool
populate_dbi_stream (bfd *stream, bfd *abfd, bfd *pdb,
uint16_t section_header_stream_num,
uint16_t sym_rec_stream_num,
- uint16_t publics_stream_num)
+ uint16_t publics_stream_num,
+ struct string_table *strings)
{
struct pdb_dbi_stream_header h;
struct optional_dbg_header opt;
void *mod_info, *sc;
uint32_t mod_info_size, sc_size;
- if (!create_module_info_substream (abfd, pdb, &mod_info, &mod_info_size))
+ if (!create_module_info_substream (abfd, pdb, &mod_info, &mod_info_size,
+ strings))
return false;
if (!create_section_contrib_substream (abfd, &sc, &sc_size))
@@ -1107,6 +1282,95 @@ create_section_header_stream (bfd *pdb, bfd *abfd, uint16_t *num)
return true;
}
+/* Populate the "/names" named stream, which contains the string table. */
+static bool
+populate_names_stream (bfd *stream, struct string_table *strings)
+{
+ char int_buf[sizeof (uint32_t)];
+ struct string_table_header h;
+ uint32_t num_strings = 0, num_buckets;
+ struct string **buckets;
+
+ bfd_putl32 (STRING_TABLE_SIGNATURE, &h.signature);
+ bfd_putl32 (STRING_TABLE_VERSION, &h.version);
+
+ if (bfd_bwrite (&h, sizeof (h), stream) != sizeof (h))
+ return false;
+
+ bfd_putl32 (strings->strings_len, int_buf);
+
+ if (bfd_bwrite (int_buf, sizeof (uint32_t), stream) != sizeof (uint32_t))
+ return false;
+
+ int_buf[0] = 0;
+
+ if (bfd_bwrite (int_buf, 1, stream) != 1)
+ return false;
+
+ for (struct string *s = strings->strings_head; s; s = s->next)
+ {
+ if (bfd_bwrite (s->s, s->len, stream) != s->len)
+ return false;
+
+ if (bfd_bwrite (int_buf, 1, stream) != 1)
+ return false;
+
+ num_strings++;
+ }
+
+ num_buckets = num_strings * 2;
+
+ buckets = xmalloc (sizeof (struct string *) * num_buckets);
+ memset (buckets, 0, sizeof (struct string *) * num_buckets);
+
+ for (struct string *s = strings->strings_head; s; s = s->next)
+ {
+ uint32_t bucket_num = s->hash % num_buckets;
+
+ while (buckets[bucket_num])
+ {
+ bucket_num++;
+
+ if (bucket_num == num_buckets)
+ bucket_num = 0;
+ }
+
+ buckets[bucket_num] = s;
+ }
+
+ bfd_putl32 (num_buckets, int_buf);
+
+ if (bfd_bwrite (int_buf, sizeof (uint32_t), stream) != sizeof (uint32_t))
+ {
+ free (buckets);
+ return false;
+ }
+
+ for (unsigned int i = 0; i < num_buckets; i++)
+ {
+ if (buckets[i])
+ bfd_putl32 (buckets[i]->offset, int_buf);
+ else
+ bfd_putl32 (0, int_buf);
+
+ if (bfd_bwrite (int_buf, sizeof (uint32_t), stream) !=
+ sizeof (uint32_t))
+ {
+ free (buckets);
+ return false;
+ }
+ }
+
+ free (buckets);
+
+ bfd_putl32 (num_strings, int_buf);
+
+ if (bfd_bwrite (int_buf, sizeof (uint32_t), stream) != sizeof (uint32_t))
+ return false;
+
+ return true;
+}
+
/* Create a PDB debugging file for the PE image file abfd with the build ID
guid, stored at pdb_name. */
bool
@@ -1117,6 +1381,7 @@ create_pdb_file (bfd *abfd, const char *pdb_name, const unsigned char *guid)
bfd *info_stream, *dbi_stream, *names_stream, *sym_rec_stream,
*publics_stream;
uint16_t section_header_stream_num, sym_rec_stream_num, publics_stream_num;
+ struct string_table strings;
pdb = bfd_openw (pdb_name, "pdb");
if (!pdb)
@@ -1125,6 +1390,13 @@ create_pdb_file (bfd *abfd, const char *pdb_name, const unsigned char *guid)
return false;
}
+ strings.strings_head = NULL;
+ strings.strings_tail = NULL;
+ strings.strings_len = 1;
+ strings.hashmap = htab_create_alloc (0, hash_string_table_entry,
+ eq_string_table_entry, free,
+ xcalloc, free);
+
bfd_set_format (pdb, bfd_archive);
if (!create_old_directory_stream (pdb))
@@ -1201,13 +1473,23 @@ create_pdb_file (bfd *abfd, const char *pdb_name, const unsigned char *guid)
}
if (!populate_dbi_stream (dbi_stream, abfd, pdb, section_header_stream_num,
- sym_rec_stream_num, publics_stream_num))
+ sym_rec_stream_num, publics_stream_num,
+ &strings))
{
einfo (_("%P: warning: cannot populate DBI stream "
"in PDB file: %E\n"));
goto end;
}
+ add_string ("", 0, &strings);
+
+ if (!populate_names_stream (names_stream, &strings))
+ {
+ einfo (_("%P: warning: cannot populate names stream "
+ "in PDB file: %E\n"));
+ goto end;
+ }
+
if (!populate_publics_stream (publics_stream, abfd, sym_rec_stream))
{
einfo (_("%P: warning: cannot populate publics stream "
@@ -1227,5 +1509,7 @@ create_pdb_file (bfd *abfd, const char *pdb_name, const unsigned char *guid)
end:
bfd_close (pdb);
+ htab_delete (strings.hashmap);
+
return ret;
}
diff --git a/ld/pdb.h b/ld/pdb.h
index e22dea18eca..611f71041c0 100644
--- a/ld/pdb.h
+++ b/ld/pdb.h
@@ -155,6 +155,18 @@ struct optional_dbg_header
#define CV_SIGNATURE_C13 4
+#define DEBUG_S_STRINGTABLE 0xf3
+
+#define STRING_TABLE_SIGNATURE 0xeffeeffe
+#define STRING_TABLE_VERSION 1
+
+/* VHdr in nmt.h */
+struct string_table_header
+{
+ uint32_t signature;
+ uint32_t version;
+};
+
#define SECTION_CONTRIB_VERSION_60 0xf12eba2d
/* SC in dbicommon.h */
diff --git a/ld/testsuite/ld-pe/pdb-strings.d b/ld/testsuite/ld-pe/pdb-strings.d
new file mode 100644
index 00000000000..8be853efb72
--- /dev/null
+++ b/ld/testsuite/ld-pe/pdb-strings.d
@@ -0,0 +1,10 @@
+
+*: file format binary
+
+Contents of section .data:
+ 0000 feeffeef 01000000 17000000 0000666f ..............fo
+ 0010 6f006261 72006261 7a007175 78007175 o.bar.baz.qux.qu
+ 0020 7578000c 00000001 0000000a 00000000 ux..............
+ 0030 00000000 00000000 00000012 00000000 ................
+ 0040 00000000 00000002 00000006 00000000 ................
+ 0050 0000000e 00000006 000000 ...........
\ No newline at end of file
diff --git a/ld/testsuite/ld-pe/pdb-strings1.s b/ld/testsuite/ld-pe/pdb-strings1.s
new file mode 100644
index 00000000000..09eedd93fb3
--- /dev/null
+++ b/ld/testsuite/ld-pe/pdb-strings1.s
@@ -0,0 +1,19 @@
+.equ CV_SIGNATURE_C13, 4
+.equ DEBUG_S_STRINGTABLE, 0xf3
+
+.section ".debug$S", "rn"
+.long CV_SIGNATURE_C13
+.long DEBUG_S_STRINGTABLE
+.long .strings_end - .strings_start
+
+.strings_start:
+
+.asciz ""
+.asciz "foo"
+.asciz "bar"
+.asciz "baz"
+.asciz "qux"
+
+.strings_end:
+
+.balign 4
diff --git a/ld/testsuite/ld-pe/pdb-strings2.s b/ld/testsuite/ld-pe/pdb-strings2.s
new file mode 100644
index 00000000000..33d9215e4c8
--- /dev/null
+++ b/ld/testsuite/ld-pe/pdb-strings2.s
@@ -0,0 +1,19 @@
+.equ CV_SIGNATURE_C13, 4
+.equ DEBUG_S_STRINGTABLE, 0xf3
+
+.section ".debug$S", "rn"
+.long CV_SIGNATURE_C13
+.long DEBUG_S_STRINGTABLE
+.long .strings_end - .strings_start
+
+.strings_start:
+
+.asciz ""
+.asciz "bar"
+.asciz "baz"
+.asciz "qux"
+.asciz "quux"
+
+.strings_end:
+
+.balign 4
diff --git a/ld/testsuite/ld-pe/pdb.exp b/ld/testsuite/ld-pe/pdb.exp
index 0be65e22fb6..09e9b4a8809 100644
--- a/ld/testsuite/ld-pe/pdb.exp
+++ b/ld/testsuite/ld-pe/pdb.exp
@@ -703,5 +703,127 @@ proc test2 { } {
test_section_contrib $section_contrib
}
+proc find_named_stream { pdb name } {
+ global ar
+
+ set exec_output [run_host_cmd "$ar" "x --output tmpdir $pdb 0001"]
+
+ if ![string match "" $exec_output] {
+ return 0
+ }
+
+ set fi [open tmpdir/0001]
+ fconfigure $fi -translation binary
+
+ seek $fi 0x1c
+
+ set data [read $fi 4]
+ binary scan $data i string_len
+
+ set strings [read $fi $string_len]
+
+ set string_off 0
+
+ while {[string first \000 $strings $string_off] != -1 } {
+ set str [string range $strings $string_off [expr [string first \000 $strings $string_off] - 1]]
+
+ if { $str eq $name } {
+ break
+ }
+
+ incr string_off [expr [string length $str] + 1]
+ }
+
+ if { [string length $strings] == $string_off } { # string not found
+ close $fi
+ return 0
+ }
+
+ set data [read $fi 4]
+ binary scan $data i num_entries
+
+ seek $fi 4 current
+
+ set data [read $fi 4]
+ binary scan $data i present_bitmap_len
+
+ seek $fi [expr $present_bitmap_len * 4] current
+
+ set data [read $fi 4]
+ binary scan $data i deleted_bitmap_len
+
+ seek $fi [expr $deleted_bitmap_len * 4] current
+
+ for {set i 0} {$i < $num_entries} {incr i} {
+ set data [read $fi 4]
+ binary scan $data i offset
+
+ if { $offset == $string_off } {
+ set data [read $fi 4]
+ binary scan $data i value
+ close $fi
+
+ return $value
+ }
+
+ seek $fi 4 current
+ }
+
+ close $fi
+
+ return 0
+}
+
+proc test3 { } {
+ global as
+ global ar
+ global ld
+ global objdump
+ global srcdir
+ global subdir
+
+ if ![ld_assemble $as $srcdir/$subdir/pdb-strings1.s tmpdir/pdb-strings1.o] {
+ unsupported "Build pdb-strings1.o"
+ return
+ }
+
+ if ![ld_assemble $as $srcdir/$subdir/pdb-strings2.s tmpdir/pdb-strings2.o] {
+ unsupported "Build pdb-strings2.o"
+ return
+ }
+
+ if ![ld_link $ld "tmpdir/pdb-strings.exe" "--pdb=tmpdir/pdb-strings.pdb tmpdir/pdb-strings1.o tmpdir/pdb-strings2.o"] {
+ unsupported "Create PE image with PDB file"
+ return
+ }
+
+ set index [find_named_stream "tmpdir/pdb-strings.pdb" "/names"]
+
+ if { $index == 0 } {
+ fail "Could not find /names stream"
+ return
+ } else {
+ pass "Found /names stream"
+ }
+
+ set index_str [format "%04x" $index]
+
+ set exec_output [run_host_cmd "$ar" "x --output tmpdir tmpdir/pdb-strings.pdb $index_str"]
+
+ if ![string match "" $exec_output] {
+ return 0
+ }
+
+ set exp [file_contents "$srcdir/$subdir/pdb-strings.d"]
+ set got [run_host_cmd "$objdump" "-s --target=binary tmpdir/$index_str"]
+
+ if ![string match $exp $got] {
+ fail "Strings table was not as expected"
+ } else {
+ pass "Strings table was as expected"
+ }
+}
+
test1
test2
+test3
--
2.37.4
^ permalink raw reply [flat|nested] 2+ messages in thread
* Re: [PATCH] ld: Generate PDB string table
2022-11-24 3:40 [PATCH] ld: Generate PDB string table Mark Harmstone
@ 2022-11-24 7:24 ` Jan Beulich
0 siblings, 0 replies; 2+ messages in thread
From: Jan Beulich @ 2022-11-24 7:24 UTC (permalink / raw)
To: Mark Harmstone; +Cc: binutils
On 24.11.2022 04:40, Mark Harmstone wrote:
> ---
A little bit of a description would be nice in almost every patch.
Beyond that just one remark for the moment (I may be able to get to
this later):
> +/* Return the hash of an entry in the string table. */
> +static hashval_t
> +hash_string_table_entry (const void * p)
> +{
> + struct string *s = (struct string *) p;
Whenever possible please avoid casting away const (or modifiers in
general). Here I don't see a need for a cast in the first place:
"const void *" converts find to "const struct ... *" in C.
Jan
^ permalink raw reply [flat|nested] 2+ messages in thread
end of thread, other threads:[~2022-11-24 7:24 UTC | newest]
Thread overview: 2+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2022-11-24 3:40 [PATCH] ld: Generate PDB string table Mark Harmstone
2022-11-24 7:24 ` Jan Beulich
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for read-only IMAP folder(s) and NNTP newsgroup(s).