add separate port_size and mach_port_name_size definitions

* cpu.sym: retrieve size of vm_offset_t and mach_port_name_t from
  gnumach headers at compile type.
* global.{c,h}: add port size as a variable and initialize it to the
  port name size.
* lexxer.l: apply port or port name size to the corresponding types,
  instead of using the word size.
* parser.y: update port size if we're generating for kernel-space
  (server or client). Also re-initialize default port types to account
  for this change.
* type.c: use port size instead of word size in default port types and
  runtime checks.

There are many assumptions about mach_port_t:
 - on kernel side, its size is the same as a pointer. This allows to
   replace the port name with the address of the corresponding data
   structure during copyin in mach_msg()
 - in mig, this is also the "word size", which is derived from gnumach
   headers as the size of integer_t
 - its size is also the same as natural_t, so it's possible to model
   structures like mach_port_status_t as an array of integer_t in
   mig. This is convenient since arrays and structures can't have
   mixed types.
 - its size is always the same as the port name size

This patch does not change the current behaviour on 32-bit kernels,
but allows for some of these assumptions to be broken on 64-bit
kernels. This is needed to have 32-bit port names on 64-bit kernels
and be able to support a 32-bit userspace.  It still leaves the choice
for a 64-bit userspace, if all integer_t and natural_t are to be
extended to 64 bit.

However keeping 32-bit port names seems to be the right thing, based on
previous discussions [1], even for a 64-bit kernel.

The only assumption kept is that in kernel-space ports are always the
size of a pointer, as they refer to a data structure and not to a
specific port name.  To ensure this is true for various user/kernel
combinations, we dynamically change the port size if we're generating
code for kernel-space server or clients, and keep the size of a port the
same of a port name for user-space servers and clients.

[1] https://lists.gnu.org/archive/html/bug-hurd/2012-04/msg00000.html

Signed-off-by: Luca Dariz <luca@orpolo.org>
Message-Id: <20220403150020.120799-2-luca@orpolo.org>

6 files changed, 35 insertions, 17 deletions

diff --git a/cpu.sym b/cpu.sym
index fcf6241..5e34074 100644
--- a/cpu.sym
+++ b/cpu.sym
@@ -106,3 +106,7 @@ expr sizeof(double)			sizeof_double
 expr sizeof(mach_msg_header_t)		sizeof_mach_msg_header_t
 expr sizeof(mach_msg_type_long_t)	sizeof_mach_msg_type_long_t
 expr sizeof(mach_msg_type_t)		sizeof_mach_msg_type_t
+expr sizeof(vm_offset_t)		vm_offset_size
+expr (sizeof(vm_offset_t)*8)		vm_offset_size_in_bits
+expr sizeof(mach_port_name_t)		port_name_size
+expr (sizeof(mach_port_name_t)*8)	port_name_size_in_bits
diff --git a/global.c b/global.c
index 5685186..e2eb76e 100644
--- a/global.c
+++ b/global.c
@@ -24,6 +24,7 @@
  * rights to redistribute these changes.
  */
 
+#include "cpu.h"
 #include "error.h"
 #include "global.h"
 
@@ -65,6 +66,9 @@ string_t InternalHeaderFileName = strNULL;
 string_t UserFileName = strNULL;
 string_t ServerFileName = strNULL;
 
+int port_size = port_name_size;
+int port_size_in_bits = port_name_size_in_bits;
+
 void
 more_global(void)
 {
diff --git a/global.h b/global.h
index 8dbb6fd..cadd7e7 100644
--- a/global.h
+++ b/global.h
@@ -67,6 +67,9 @@ extern string_t InternalHeaderFileName;
 extern string_t UserFileName;
 extern string_t ServerFileName;
 
+extern int port_size;
+extern int port_size_in_bits;
+
 extern void more_global(void);
 
 #ifndef NULL
diff --git a/lexxer.l b/lexxer.l
index 48dda4a..71f43b2 100644
--- a/lexxer.l
+++ b/lexxer.l
@@ -160,7 +160,7 @@ static void doSharp(const char *body); /* process body of # directives */
 <Normal>(?i:countinout)		FRETURN(flCountInOut);
 <Normal>(?i:retcode)		FRETURN(flNone);
 
-<Normal>(?i:polymorphic)	TRETURN(MACH_MSG_TYPE_POLYMORPHIC,word_size_in_bits);
+<Normal>(?i:polymorphic)	TRETURN(MACH_MSG_TYPE_POLYMORPHIC,port_size_in_bits);
 
 <Normal>"MACH_MSG_TYPE_UNSTRUCTURED"	TRETURN(MACH_MSG_TYPE_UNSTRUCTURED,0);
 <Normal>"MACH_MSG_TYPE_BIT"		TRETURN(MACH_MSG_TYPE_BIT,1);
@@ -175,17 +175,17 @@ static void doSharp(const char *body); /* process body of # directives */
 <Normal>"MACH_MSG_TYPE_STRING"		TRETURN(MACH_MSG_TYPE_STRING,0);
 <Normal>"MACH_MSG_TYPE_STRING_C"	TRETURN(MACH_MSG_TYPE_STRING_C,0);
 
-<Normal>"MACH_MSG_TYPE_MOVE_RECEIVE"	TPRETURN(MACH_MSG_TYPE_MOVE_RECEIVE,MACH_MSG_TYPE_PORT_RECEIVE,word_size_in_bits);
-<Normal>"MACH_MSG_TYPE_COPY_SEND"	TPRETURN(MACH_MSG_TYPE_COPY_SEND,MACH_MSG_TYPE_PORT_SEND,word_size_in_bits);
-<Normal>"MACH_MSG_TYPE_MAKE_SEND"	TPRETURN(MACH_MSG_TYPE_MAKE_SEND,MACH_MSG_TYPE_PORT_SEND,word_size_in_bits);
-<Normal>"MACH_MSG_TYPE_MOVE_SEND"	TPRETURN(MACH_MSG_TYPE_MOVE_SEND,MACH_MSG_TYPE_PORT_SEND,word_size_in_bits);
-<Normal>"MACH_MSG_TYPE_MAKE_SEND_ONCE"	TPRETURN(MACH_MSG_TYPE_MAKE_SEND_ONCE,MACH_MSG_TYPE_PORT_SEND_ONCE,word_size_in_bits);
-<Normal>"MACH_MSG_TYPE_MOVE_SEND_ONCE"	TPRETURN(MACH_MSG_TYPE_MOVE_SEND_ONCE,MACH_MSG_TYPE_PORT_SEND_ONCE,word_size_in_bits);
-
-<Normal>"MACH_MSG_TYPE_PORT_NAME"	TRETURN(MACH_MSG_TYPE_PORT_NAME,word_size_in_bits);
-<Normal>"MACH_MSG_TYPE_PORT_RECEIVE"	TPRETURN(MACH_MSG_TYPE_POLYMORPHIC,MACH_MSG_TYPE_PORT_RECEIVE,word_size_in_bits);
-<Normal>"MACH_MSG_TYPE_PORT_SEND"	TPRETURN(MACH_MSG_TYPE_POLYMORPHIC,MACH_MSG_TYPE_PORT_SEND,word_size_in_bits);
-<Normal>"MACH_MSG_TYPE_PORT_SEND_ONCE"	TPRETURN(MACH_MSG_TYPE_POLYMORPHIC,MACH_MSG_TYPE_PORT_SEND_ONCE,word_size_in_bits);
+<Normal>"MACH_MSG_TYPE_MOVE_RECEIVE"	TPRETURN(MACH_MSG_TYPE_MOVE_RECEIVE,MACH_MSG_TYPE_PORT_RECEIVE,port_size_in_bits);
+<Normal>"MACH_MSG_TYPE_COPY_SEND"	TPRETURN(MACH_MSG_TYPE_COPY_SEND,MACH_MSG_TYPE_PORT_SEND,port_size_in_bits);
+<Normal>"MACH_MSG_TYPE_MAKE_SEND"	TPRETURN(MACH_MSG_TYPE_MAKE_SEND,MACH_MSG_TYPE_PORT_SEND,port_size_in_bits);
+<Normal>"MACH_MSG_TYPE_MOVE_SEND"	TPRETURN(MACH_MSG_TYPE_MOVE_SEND,MACH_MSG_TYPE_PORT_SEND,port_size_in_bits);
+<Normal>"MACH_MSG_TYPE_MAKE_SEND_ONCE"	TPRETURN(MACH_MSG_TYPE_MAKE_SEND_ONCE,MACH_MSG_TYPE_PORT_SEND_ONCE,port_size_in_bits);
+<Normal>"MACH_MSG_TYPE_MOVE_SEND_ONCE"	TPRETURN(MACH_MSG_TYPE_MOVE_SEND_ONCE,MACH_MSG_TYPE_PORT_SEND_ONCE,port_size_in_bits);
+
+<Normal>"MACH_MSG_TYPE_PORT_NAME"	TRETURN(MACH_MSG_TYPE_PORT_NAME,port_name_size_in_bits);
+<Normal>"MACH_MSG_TYPE_PORT_RECEIVE"	TPRETURN(MACH_MSG_TYPE_POLYMORPHIC,MACH_MSG_TYPE_PORT_RECEIVE,port_size_in_bits);
+<Normal>"MACH_MSG_TYPE_PORT_SEND"	TPRETURN(MACH_MSG_TYPE_POLYMORPHIC,MACH_MSG_TYPE_PORT_SEND,port_size_in_bits);
+<Normal>"MACH_MSG_TYPE_PORT_SEND_ONCE"	TPRETURN(MACH_MSG_TYPE_POLYMORPHIC,MACH_MSG_TYPE_PORT_SEND_ONCE,port_size_in_bits);
 <Normal>"MACH_MSG_TYPE_POLYMORPHIC"	TRETURN(MACH_MSG_TYPE_POLYMORPHIC,0);
 
 <Normal>":"		RETURN(syColon);
diff --git a/parser.y b/parser.y
index 8c2190b..8d6b2aa 100644
--- a/parser.y
+++ b/parser.y
@@ -116,6 +116,7 @@
 
 #include <stdio.h>
 
+#include "cpu.h"
 #include "error.h"
 #include "lexxer.h"
 #include "global.h"
@@ -223,12 +224,18 @@ SubsystemMod		:	syKernelUser
     if (IsKernelUser)
 	warn("duplicate KernelUser keyword");
     IsKernelUser = TRUE;
+    port_size = vm_offset_size;
+    port_size_in_bits = vm_offset_size_in_bits;
+    init_type();
 }
 			|	syKernelServer
 {
     if (IsKernelServer)
 	warn("duplicate KernelServer keyword");
     IsKernelServer = TRUE;
+    port_size = vm_offset_size;
+    port_size_in_bits = vm_offset_size_in_bits;
+    init_type();
 }
 			;
 
diff --git a/type.c b/type.c
index eb88cf4..86137ae 100644
--- a/type.c
+++ b/type.c
@@ -848,7 +848,7 @@ init_type(void)
     itRequestPortType->itInNameStr = "MACH_MSG_TYPE_COPY_SEND";
     itRequestPortType->itOutName = MACH_MSG_TYPE_PORT_SEND;
     itRequestPortType->itOutNameStr = "MACH_MSG_TYPE_PORT_SEND";
-    itRequestPortType->itSize = word_size_in_bits;
+    itRequestPortType->itSize = port_size_in_bits;
     itCalculateSizeInfo(itRequestPortType);
     itCalculateNameInfo(itRequestPortType);
 
@@ -858,7 +858,7 @@ init_type(void)
     itZeroReplyPortType->itInNameStr = "0";
     itZeroReplyPortType->itOutName = 0;
     itZeroReplyPortType->itOutNameStr = "0";
-    itZeroReplyPortType->itSize = word_size_in_bits;
+    itZeroReplyPortType->itSize = port_size_in_bits;
     itCalculateSizeInfo(itZeroReplyPortType);
     itCalculateNameInfo(itZeroReplyPortType);
 
@@ -868,7 +868,7 @@ init_type(void)
     itRealReplyPortType->itInNameStr = "MACH_MSG_TYPE_MAKE_SEND_ONCE";
     itRealReplyPortType->itOutName = MACH_MSG_TYPE_PORT_SEND_ONCE;
     itRealReplyPortType->itOutNameStr = "MACH_MSG_TYPE_PORT_SEND_ONCE";
-    itRealReplyPortType->itSize = word_size_in_bits;
+    itRealReplyPortType->itSize = port_size_in_bits;
     itCalculateSizeInfo(itRealReplyPortType);
     itCalculateNameInfo(itRealReplyPortType);
 
@@ -906,7 +906,7 @@ itCheckRequestPortType(identifier_t name, const ipc_type_t *it)
 	 (it->itOutName != MACH_MSG_TYPE_PORT_SEND_ONCE) &&
 	 (it->itOutName != MACH_MSG_TYPE_POLYMORPHIC)) ||
 	(it->itNumber != 1) ||
-	(it->itSize != word_size_in_bits) ||
+	(it->itSize != port_size_in_bits) ||
 	!it->itInLine ||
 	it->itDeallocate != d_NO ||
 	!it->itStruct ||
@@ -927,7 +927,7 @@ itCheckReplyPortType(identifier_t name, const ipc_type_t *it)
 	 (it->itOutName != MACH_MSG_TYPE_POLYMORPHIC) &&
 	 (it->itOutName != 0)) ||
 	(it->itNumber != 1) ||
-	(it->itSize != word_size_in_bits) ||
+	(it->itSize != port_size_in_bits) ||
 	!it->itInLine ||
 	it->itDeallocate != d_NO ||
 	!it->itStruct ||