ld: Handle extended-length data structures in PDB types

A few fixes to minor issues I've discovered in my PDB patches.

* If sizes or offsets are greater than 0x8000, they get encoded as
extended values in the same way as for enum values - e.g. a LF_ULONG
.short followed by a .long.

* I've managed to coax MSVC to produce another type, LF_VFTABLE, which
is seen when dealing with COM. I don't think LLVM emits this. Note that
we can't just implement everything in Microsoft's header files, as most
of it is obsolete.

* Fixes a stupid bug in the test program, where I was adding an index to
a size. The index was hard-coded to 0, so this didn't cause any actual
issues.

6 files changed, 344 insertions, 28 deletions

diff --git a/ld/pdb.c b/ld/pdb.c
index 6a5f737..60e9980 100644
--- a/ld/pdb.c
+++ b/ld/pdb.c
@@ -2476,6 +2476,7 @@ handle_type (uint8_t *data, struct type_entry **map, uint32_t type_num,
 	      case LF_MEMBER:
 		{
 		  struct lf_member *mem = (struct lf_member *) ptr;
+		  uint16_t offset;
 		  size_t name_len, subtype_len;
 
 		  if (left < offsetof (struct lf_member, name))
@@ -2488,9 +2489,34 @@ handle_type (uint8_t *data, struct type_entry **map, uint32_t type_num,
 		  if (!remap_type (&mem->type, map, type_num, num_types))
 		    return false;
 
+		  subtype_len = offsetof (struct lf_member, name);
+
+		  offset = bfd_getl16 (&mem->offset);
+
+		  /* If offset >= 0x8000, actual value follows.  */
+		  if (offset >= 0x8000)
+		    {
+		      unsigned int param_len = extended_value_len (offset);
+
+		      if (param_len == 0)
+			{
+			  einfo (_("%P: warning: unhandled type %v within"
+				   " LF_MEMBER\n"), offset);
+			  return false;
+			}
+
+		      subtype_len += param_len;
+
+		      if (left < subtype_len)
+			{
+			  einfo (_("%P: warning: truncated CodeView type record"
+				  " LF_MEMBER\n"));
+			  return false;
+			}
+		    }
+
 		  name_len =
-		    strnlen (mem->name,
-			     left - offsetof (struct lf_member, name));
+		    strnlen ((char *) mem + subtype_len, left - subtype_len);
 
 		  if (name_len == left - offsetof (struct lf_member, name))
 		    {
@@ -2501,7 +2527,7 @@ handle_type (uint8_t *data, struct type_entry **map, uint32_t type_num,
 
 		  name_len++;
 
-		  subtype_len = offsetof (struct lf_member, name) + name_len;
+		  subtype_len += name_len;
 
 		  if (subtype_len % 4 != 0)
 		    subtype_len += 4 - (subtype_len % 4);
@@ -2706,6 +2732,8 @@ handle_type (uint8_t *data, struct type_entry **map, uint32_t type_num,
 	      case LF_BCLASS:
 		{
 		  struct lf_bclass *bc = (struct lf_bclass *) ptr;
+		  size_t subtype_len;
+		  uint16_t offset;
 
 		  if (left < sizeof (struct lf_bclass))
 		    {
@@ -2718,8 +2746,44 @@ handle_type (uint8_t *data, struct type_entry **map, uint32_t type_num,
 				   num_types))
 		    return false;
 
-		  ptr += sizeof (struct lf_bclass);
-		  left -= sizeof (struct lf_bclass);
+		  subtype_len = sizeof (struct lf_bclass);
+
+		  offset = bfd_getl16 (&bc->offset);
+
+		  /* If offset >= 0x8000, actual value follows.  */
+		  if (offset >= 0x8000)
+		    {
+		      unsigned int param_len = extended_value_len (offset);
+
+		      if (param_len == 0)
+			{
+			  einfo (_("%P: warning: unhandled type %v within"
+				   " LF_BCLASS\n"), offset);
+			  return false;
+			}
+
+		      subtype_len += param_len;
+
+		      if (left < subtype_len)
+			{
+			  einfo (_("%P: warning: truncated CodeView type record"
+				   " LF_BCLASS\n"));
+			  return false;
+			}
+		    }
+
+		  if (subtype_len % 4 != 0)
+		    subtype_len += 4 - (subtype_len % 4);
+
+		  if (left < subtype_len)
+		    {
+		      einfo (_("%P: warning: truncated CodeView type record"
+			       " LF_BCLASS\n"));
+		      return false;
+		    }
+
+		  ptr += subtype_len;
+		  left -= subtype_len;
 
 		  break;
 		}
@@ -2748,6 +2812,8 @@ handle_type (uint8_t *data, struct type_entry **map, uint32_t type_num,
 	      case LF_IVBCLASS:
 		{
 		  struct lf_vbclass *vbc = (struct lf_vbclass *) ptr;
+		  size_t subtype_len;
+		  uint16_t offset;
 
 		  if (left < sizeof (struct lf_vbclass))
 		    {
@@ -2764,8 +2830,70 @@ handle_type (uint8_t *data, struct type_entry **map, uint32_t type_num,
 				   type_num, num_types))
 		    return false;
 
-		  ptr += sizeof (struct lf_vbclass);
-		  left -= sizeof (struct lf_vbclass);
+		  subtype_len = offsetof (struct lf_vbclass,
+					  virtual_base_vbtable_offset);
+
+		  offset = bfd_getl16 (&vbc->virtual_base_pointer_offset);
+
+		  /* If offset >= 0x8000, actual value follows.  */
+		  if (offset >= 0x8000)
+		    {
+		      unsigned int param_len = extended_value_len (offset);
+
+		      if (param_len == 0)
+			{
+			  einfo (_("%P: warning: unhandled type %v within"
+				   " LF_VBCLASS/LF_IVBCLASS\n"), offset);
+			  return false;
+			}
+
+		      subtype_len += param_len;
+
+		      if (left < subtype_len)
+			{
+			  einfo (_("%P: warning: truncated CodeView type record"
+				   " LF_VBCLASS/LF_IVBCLASS\n"));
+			  return false;
+			}
+		    }
+
+		  offset = bfd_getl16 ((char *)vbc + subtype_len);
+		  subtype_len += sizeof (uint16_t);
+
+		  /* If offset >= 0x8000, actual value follows.  */
+		  if (offset >= 0x8000)
+		    {
+		      unsigned int param_len = extended_value_len (offset);
+
+		      if (param_len == 0)
+			{
+			  einfo (_("%P: warning: unhandled type %v within"
+				   " LF_VBCLASS/LF_IVBCLASS\n"), offset);
+			  return false;
+			}
+
+		      subtype_len += param_len;
+
+		      if (left < subtype_len)
+			{
+			  einfo (_("%P: warning: truncated CodeView type record"
+				   " LF_VBCLASS/LF_IVBCLASS\n"));
+			  return false;
+			}
+		    }
+
+		  if (subtype_len % 4 != 0)
+		    subtype_len += 4 - (subtype_len % 4);
+
+		  if (left < subtype_len)
+		    {
+		      einfo (_("%P: warning: truncated CodeView type record"
+			       " LF_VBCLASS/LF_IVBCLASS\n"));
+		      return false;
+		    }
+
+		  ptr += subtype_len;
+		  left -= subtype_len;
 
 		  break;
 		}
@@ -2950,8 +3078,8 @@ handle_type (uint8_t *data, struct type_entry **map, uint32_t type_num,
     case LF_STRUCTURE:
       {
 	struct lf_class *cl = (struct lf_class *) data;
-	uint16_t prop;
-	size_t name_len;
+	uint16_t prop, num_bytes;
+	size_t name_len, name_off;
 
 	if (size < offsetof (struct lf_class, name))
 	  {
@@ -2969,9 +3097,35 @@ handle_type (uint8_t *data, struct type_entry **map, uint32_t type_num,
 	if (!remap_type (&cl->vshape, map, type_num, num_types))
 	  return false;
 
-	name_len = strnlen (cl->name, size - offsetof (struct lf_class, name));
+	name_off = offsetof (struct lf_class, name);
+
+	num_bytes = bfd_getl16 (&cl->length);
 
-	if (name_len == size - offsetof (struct lf_class, name))
+	/* If num_bytes >= 0x8000, actual value follows.  */
+	if (num_bytes >= 0x8000)
+	  {
+	    unsigned int param_len = extended_value_len (num_bytes);
+
+	    if (param_len == 0)
+	      {
+		einfo (_("%P: warning: unhandled type %v within"
+			 " LF_CLASS/LF_STRUCTURE\n"), num_bytes);
+		return false;
+	      }
+
+	    name_off += param_len;
+
+	    if (size < name_off)
+	      {
+		einfo (_("%P: warning: truncated CodeView type record"
+			 " LF_CLASS/LF_STRUCTURE\n"));
+		return false;
+	      }
+	  }
+
+	name_len = strnlen ((char *) cl + name_off, size - name_off);
+
+	if (name_len == size - name_off)
 	  {
 	    einfo (_("%P: warning: name for LF_CLASS/LF_STRUCTURE has no"
 		     " terminating zero\n"));
@@ -2984,10 +3138,11 @@ handle_type (uint8_t *data, struct type_entry **map, uint32_t type_num,
 	  {
 	    /* Structure has another name following first one.  */
 
-	    size_t len = offsetof (struct lf_class, name) + name_len + 1;
+	    size_t len = name_off + name_len + 1;
 	    size_t unique_name_len;
 
-	    unique_name_len = strnlen (cl->name + name_len + 1, size - len);
+	    unique_name_len = strnlen ((char *) cl + name_off + name_len + 1,
+				       size - len);
 
 	    if (unique_name_len == size - len)
 	      {
@@ -2998,10 +3153,10 @@ handle_type (uint8_t *data, struct type_entry **map, uint32_t type_num,
 	  }
 
 	if (!(prop & (CV_PROP_FORWARD_REF | CV_PROP_SCOPED))
-	    && !is_name_anonymous (cl->name, name_len))
+	    && !is_name_anonymous ((char *) cl + name_off, name_len))
 	  {
 	    other_hash = true;
-	    cv_hash = crc32 ((uint8_t *) cl->name, name_len);
+	    cv_hash = crc32 ((uint8_t *) cl + name_off, name_len);
 	  }
 
 	break;
@@ -3010,8 +3165,8 @@ handle_type (uint8_t *data, struct type_entry **map, uint32_t type_num,
     case LF_UNION:
       {
 	struct lf_union *un = (struct lf_union *) data;
-	uint16_t prop;
-	size_t name_len;
+	uint16_t prop, num_bytes;
+	size_t name_len, name_off;
 
 	if (size < offsetof (struct lf_union, name))
 	  {
@@ -3023,9 +3178,35 @@ handle_type (uint8_t *data, struct type_entry **map, uint32_t type_num,
 	if (!remap_type (&un->field_list, map, type_num, num_types))
 	  return false;
 
-	name_len = strnlen (un->name, size - offsetof (struct lf_union, name));
+	name_off = offsetof (struct lf_union, name);
+
+	num_bytes = bfd_getl16 (&un->length);
+
+	/* If num_bytes >= 0x8000, actual value follows.  */
+	if (num_bytes >= 0x8000)
+	  {
+	    unsigned int param_len = extended_value_len (num_bytes);
+
+	    if (param_len == 0)
+	      {
+		einfo (_("%P: warning: unhandled type %v within"
+			 " LF_UNION\n"), num_bytes);
+		return false;
+	      }
+
+	    name_off += param_len;
+
+	    if (size < name_off)
+	      {
+		einfo (_("%P: warning: truncated CodeView type record"
+			 " LF_UNION\n"));
+		return false;
+	      }
+	  }
+
+	name_len = strnlen ((char *) un + name_off, size - name_off);
 
-	if (name_len == size - offsetof (struct lf_union, name))
+	if (name_len == size - name_off)
 	  {
 	    einfo (_("%P: warning: name for LF_UNION has no"
 		     " terminating zero\n"));
@@ -3038,10 +3219,11 @@ handle_type (uint8_t *data, struct type_entry **map, uint32_t type_num,
 	  {
 	    /* Structure has another name following first one.  */
 
-	    size_t len = offsetof (struct lf_union, name) + name_len + 1;
+	    size_t len = name_off + name_len + 1;
 	    size_t unique_name_len;
 
-	    unique_name_len = strnlen (un->name + name_len + 1, size - len);
+	    unique_name_len = strnlen ((char *) un + name_off + name_len + 1,
+				       size - len);
 
 	    if (unique_name_len == size - len)
 	      {
@@ -3052,10 +3234,10 @@ handle_type (uint8_t *data, struct type_entry **map, uint32_t type_num,
 	  }
 
 	if (!(prop & (CV_PROP_FORWARD_REF | CV_PROP_SCOPED))
-	    && !is_name_anonymous (un->name, name_len))
+	    && !is_name_anonymous ((char *) un + name_off, name_len))
 	  {
 	    other_hash = true;
-	    cv_hash = crc32 ((uint8_t *) un->name, name_len);
+	    cv_hash = crc32 ((uint8_t *) un + name_off, name_len);
 	  }
 
 	break;
diff --git a/ld/pdb.h b/ld/pdb.h
index 749a602..ddf731b 100644
--- a/ld/pdb.h
+++ b/ld/pdb.h
@@ -480,7 +480,6 @@ struct lf_bclass
   uint16_t attributes;
   uint32_t base_class_type;
   uint16_t offset;
-  uint16_t padding;
 } ATTRIBUTE_PACKED;
 
 /* lfVFuncTab in cvinfo.h */
diff --git a/ld/testsuite/ld-pe/pdb-types1-hashlist.d b/ld/testsuite/ld-pe/pdb-types1-hashlist.d
index b75f08c..aa00aaf 100644
--- a/ld/testsuite/ld-pe/pdb-types1-hashlist.d
+++ b/ld/testsuite/ld-pe/pdb-types1-hashlist.d
@@ -10,4 +10,6 @@ Contents of section .data:
  0050 ffd80200 b0260100 7c060200 e3240200  *
  0060 63ff0100 fb6b0300 0ad90100 523c0200  *
  0070 4d5e0200 8a940200 4b710300 6aa90300  *
- 0080 0a2c0300 67e10300 4a3d0300           *
\ No newline at end of file
+ 0080 0a2c0300 67e10300 4a3d0300 fa460300  *
+ 0090 db020200 ec4e0100 131e0300 fb120300  *
+ 00a0 aece0200 1db70100                    *
\ No newline at end of file
diff --git a/ld/testsuite/ld-pe/pdb-types1-typelist.d b/ld/testsuite/ld-pe/pdb-types1-typelist.d
index ff2d91c..df862c3 100644
--- a/ld/testsuite/ld-pe/pdb-types1-typelist.d
+++ b/ld/testsuite/ld-pe/pdb-types1-typelist.d
@@ -57,4 +57,18 @@ Contents of section .data:
  0340 7200f2f1 10150000 20100000 6e657374  r....... ...nest
  0350 65645f65 6e756d00 1a000515 01000000  ed_enum.........
  0360 21100000 00000000 00000000 04007175  !.............qu
- 0370 757800f1                             ux..            
\ No newline at end of file
+ 0370 757800f1 12000315 10000000 74000000  ux..........t...
+ 0380 028060ea 00f3f2f1 2e000312 0d150300  ..`.............
+ 0390 23100000 00006100 0d150300 23100000  #.....a.....#...
+ 03a0 028060ea 6200f2f1 0d150300 23100000  ..`.b.......#...
+ 03b0 0480c0d4 01006300 26000515 03000000  ......c.&.......
+ 03c0 24100000 00000000 00000000 048020bf  $............. .
+ 03d0 02006c6f 6e677374 72756374 00f3f2f1  ..longstruct....
+ 03e0 1a000312 0d150300 23100000 00006100  ........#.....a.
+ 03f0 0d150300 23100000 00006200 1a000615  ....#.....b.....
+ 0400 02000000 26100000 028060ea 6c6f6e67  ....&.....`.long
+ 0410 756e696f 6e00f2f1 1e000312 00140000  union...........
+ 0420 25100000 0480c0d4 0100f2f1 0d150300  %...............
+ 0430 23100000 00006400 26000312 01140000  #.....d.&.......
+ 0440 25100000 00000000 028060ea 0480c0d4  %.........`.....
+ 0450 0100f2f1 0d150300 23100000 00006400  ........#.....d.
\ No newline at end of file
diff --git a/ld/testsuite/ld-pe/pdb-types1b.s b/ld/testsuite/ld-pe/pdb-types1b.s
index 89ee6e3..544b338 100644
--- a/ld/testsuite/ld-pe/pdb-types1b.s
+++ b/ld/testsuite/ld-pe/pdb-types1b.s
@@ -33,6 +33,7 @@
 
 .equ LF_USHORT, 0x8002
 .equ LF_LONG, 0x8003
+.equ LF_ULONG, 0x8004
 .equ LF_UQUADWORD, 0x800a
 
 .equ CV_PTR_NEAR32, 0xa
@@ -447,7 +448,7 @@
 
 # Type 1021, struct quux, field list 1020
 .struct4:
-.short .types_end - .struct4 - 2
+.short .arr2 - .struct4 - 2
 .short LF_STRUCTURE
 .short 1 # no. members
 .short 0 # property
@@ -458,4 +459,122 @@
 .asciz "quux" # name
 .byte 0xf1 # padding
 
+# Type 1022, array[60000] of char
+.arr2:
+.short .fieldlist8 - .arr2 - 2
+.short LF_ARRAY
+.long T_CHAR # element type
+.long T_INT4 # index type
+.short LF_USHORT
+.short 60000 # size in bytes
+.byte 0 # name
+.byte 0xf3 # padding
+.byte 0xf2 # padding
+.byte 0xf1 # padding
+
+# Type 1023, field list for struct longstruct
+.fieldlist8:
+.short .struct5 - .fieldlist8 - 2
+.short LF_FIELDLIST
+.short LF_MEMBER
+.short 3 # public
+.long 0x1022
+.short 0 # offset
+.asciz "a"
+.short LF_MEMBER
+.short 3 # public
+.long 0x1022
+.short LF_USHORT
+.short 60000 # offset
+.asciz "b"
+.byte 0xf2 # padding
+.byte 0xf1 # padding
+.short LF_MEMBER
+.short 3 # public
+.long 0x1022
+.short LF_ULONG
+.long 120000 # offset
+.asciz "c"
+
+# Type 1024, struct longstruct
+.struct5:
+.short .fieldlist9 - .struct5 - 2
+.short LF_STRUCTURE
+.short 3 # no. members
+.short 0 # property
+.long 0x1023 # field list
+.long 0 # type derived from
+.long 0 # type of vshape table
+.short LF_ULONG
+.long 180000 # size
+.asciz "longstruct" # name
+.byte 0xf3 # padding
+.byte 0xf2 # padding
+.byte 0xf1 # padding
+
+# Type 1025, field list for union longunion
+.fieldlist9:
+.short .union4 - .fieldlist9 - 2
+.short LF_FIELDLIST
+.short LF_MEMBER
+.short 3 # public
+.long 0x1022
+.short 0 # offset
+.asciz "a"
+.short LF_MEMBER
+.short 3 # public
+.long 0x1022
+.short 0 # offset
+.asciz "b"
+
+# Type 1026, union longunion (field list 1025)
+.union4:
+.short .fieldlist10 - .union4 - 2
+.short LF_UNION
+.short 2 # no. members
+.short 0 # property
+.long 0x1025 # field list
+.short LF_USHORT
+.short 60000 # size
+.asciz "longunion"
+.byte 0xf2 # padding
+.byte 0xf1 # padding
+
+# Type 1027, field list with base class longstruct
+.fieldlist10:
+.short .fieldlist11 - .fieldlist10 - 2
+.short LF_FIELDLIST
+.short LF_BCLASS
+.short 0 # attributes
+.long 0x1024 # base class
+.short LF_ULONG
+.long 120000 # offset within class
+.byte 0xf2 # padding
+.byte 0xf1 # padding
+.short LF_MEMBER
+.short 3 # public
+.long 0x1022
+.short 0 # offset
+.asciz "d"
+
+# Type 1028, field list with virtual base class longstruct
+.fieldlist11:
+.short .types_end - .fieldlist11 - 2
+.short LF_FIELDLIST
+.short LF_VBCLASS
+.short 0 # attributes
+.long 0x1024 # type index of direct virtual base class
+.long 0 # type index of virtual base pointer
+.short LF_USHORT
+.short 60000 # virtual base pointer offset
+.short LF_ULONG
+.long 120000 # virtual base offset from vbtable
+.byte 0xf2 # padding
+.byte 0xf1 # padding
+.short LF_MEMBER
+.short 3 # public
+.long 0x1022
+.short 0 # offset
+.asciz "d"
+
 .types_end:
diff --git a/ld/testsuite/ld-pe/pdb.exp b/ld/testsuite/ld-pe/pdb.exp
index bd50b2f..fbc0cf9 100644
--- a/ld/testsuite/ld-pe/pdb.exp
+++ b/ld/testsuite/ld-pe/pdb.exp
@@ -1029,7 +1029,7 @@ proc test5 { } {
     binary scan $data i end_type
 
     # end_type is one greater than the last type in the stream
-    if { $end_type != 0x1023 } {
+    if { $end_type != 0x102a } {
 	fail "Incorrect end type value in TPI stream."
     } else {
 	pass "Correct end type value in TPI stream."