Primary goal for these changes is:

- no longer have kernel have its own page table that is loaded
    on every kernel entry (trap, interrupt, exception). the primary
    purpose is to reduce the number of required reloads.
Result:
  - kernel can only access memory of process that was running when
    kernel was entered
  - kernel must be mapped into every process page table, so traps to
    kernel keep working
Problem:
  - kernel must often access memory of arbitrary processes (e.g. send
    arbitrary processes messages); this can't happen directly any more;
    usually because that process' page table isn't loaded at all, sometimes
    because that memory isn't mapped in at all, sometimes because it isn't
    mapped in read-write.
So:
  - kernel must be able to map in memory of any process, in its own
    address space.
Implementation:
  - VM and kernel share a range of memory in which addresses of
    all page tables of all processes are available. This has two purposes:
      . Kernel has to know what data to copy in order to map in a range
      . Kernel has to know where to write the data in order to map it in
    That last point is because kernel has to write in the currently loaded
    page table.
  - Processes and kernel are separated through segments; kernel segments
    haven't changed.
  - The kernel keeps the process whose page table is currently loaded
    in 'ptproc.'
  - If it wants to map in a range of memory, it writes the value of the
    page directory entry for that range into the page directory entry
    in the currently loaded map. There is a slot reserved for such
    purposes. The kernel can then access this memory directly.
  - In order to do this, its segment has been increased (and the
    segments of processes start where it ends).
  - In the pagefault handler, detect if the kernel is doing
    'trappable' memory access (i.e. a pagefault isn't a fatal
     error) and if so,
       - set the saved instruction pointer to phys_copy_fault,
	 breaking out of phys_copy
       - set the saved eax register to the address of the page
	 fault, both for sanity checking and for checking in
	 which of the two ranges that phys_copy was called
	 with the fault occured
  - Some boot-time processes do not have their own page table,
    and are mapped in with the kernel, and separated with
    segments. The kernel detects this using HASPT. If such a
    process has to be scheduled, any page table will work and
    no page table switch is done.

Major changes in kernel are
  - When accessing user processes memory, kernel no longer
    explicitly checks before it does so if that memory is OK.
    It simply makes the mapping (if necessary), tries to do the
    operation, and traps the pagefault if that memory isn't present;
    if that happens, the copy function returns EFAULT.
    So all of the CHECKRANGE_OR_SUSPEND macros are gone.
  - Kernel no longer has to copy/read and parse page tables.
  - A message copying optimisation: when messages are copied, and
    the recipient isn't mapped in, they are copied into a buffer
    in the kernel. This is done in QueueMess. The next time
    the recipient is scheduled, this message is copied into
    its memory. This happens in schedcheck().
    This eliminates the mapping/copying step for messages, and makes
    it easier to deliver messages. This eliminates soft_notify.
  - Kernel no longer creates a page table at all, so the vm_setbuf
    and pagetable writing in memory.c is gone.

Minor changes in kernel are
  - ipc_stats thrown out, wasn't used
  - misc flags all renamed to MF_*
  - NOREC_* macros to enter and leave functions that should not
    be called recursively; just sanity checks really
  - code to fully decode segment selectors and descriptors
    to print on exceptions
  - lots of vmassert()s added, only executed if DEBUG_VMASSERT is 1

kernel/proto.h

@@ -33,13 +33,12 @@ _PROTOTYPE( int sys_call, (int call_nr, int src_dst,
 					message *m_ptr, long bit_map)	);
 _PROTOTYPE( void sys_call_restart, (struct proc *caller)		);
 _PROTOTYPE( int lock_notify, (int src, int dst)				);
-_PROTOTYPE( int soft_notify, (int dst)					);
+_PROTOTYPE( int mini_notify, (struct proc *src, endpoint_t dst)		);
 _PROTOTYPE( int lock_send, (int dst, message *m_ptr)			);
-_PROTOTYPE( void lock_enqueue, (struct proc *rp)			);
-_PROTOTYPE( void lock_dequeue, (struct proc *rp)			);
 _PROTOTYPE( void enqueue, (struct proc *rp)				);
 _PROTOTYPE( void dequeue, (struct proc *rp)				);
 _PROTOTYPE( void balance_queues, (struct timer *tp)			);
+_PROTOTYPE( void schedcheck, (void)					);
 _PROTOTYPE( struct proc *endpoint_lookup, (endpoint_t ep)		);
 #if DEBUG_ENABLE_IPC_WARNINGS
 _PROTOTYPE( int isokendpt_f, (char *file, int line, endpoint_t e, int *p, int f));
@@ -91,6 +90,8 @@ _PROTOTYPE( void cons_seth, (int pos, int n)				);
 #define CHECK_RUNQUEUES check_runqueues_f(__FILE__, __LINE__)
 _PROTOTYPE( void check_runqueues_f, (char *file, int line) );
 #endif
+_PROTOTYPE( char *rtsflagstr, (int flags) );
+_PROTOTYPE( char *miscflagstr, (int flags) );
 
 /* system/do_safecopy.c */
 _PROTOTYPE( int verify_grant, (endpoint_t, endpoint_t, cp_grant_id_t, vir_bytes,
@@ -106,18 +107,21 @@ _PROTOTYPE( void stop_profile_clock, (void)				);
 #endif
 
 /* functions defined in architecture-dependent files. */
-_PROTOTYPE( void phys_copy, (phys_bytes source, phys_bytes dest,
+_PROTOTYPE( phys_bytes phys_copy, (phys_bytes source, phys_bytes dest,
                 phys_bytes count)                                       );
+_PROTOTYPE( void phys_copy_fault, (void));
 #define virtual_copy(src, dst, bytes) virtual_copy_f(src, dst, bytes, 0)
 #define virtual_copy_vmcheck(src, dst, bytes) virtual_copy_f(src, dst, bytes, 1)
 _PROTOTYPE( int virtual_copy_f, (struct vir_addr *src, struct vir_addr *dst, 
 				vir_bytes bytes, int vmcheck)		);
 _PROTOTYPE( int data_copy, (endpoint_t from, vir_bytes from_addr,
 	endpoint_t to, vir_bytes to_addr, size_t bytes));
+_PROTOTYPE( int data_copy_vmcheck, (endpoint_t from, vir_bytes from_addr,
+	endpoint_t to, vir_bytes to_addr, size_t bytes));
 #define data_copy_to(d, p, v, n) data_copy(SYSTEM, (d), (p), (v), (n));
 #define data_copy_from(d, p, v, n) data_copy((p), (v), SYSTEM, (d), (n));
 _PROTOTYPE( void alloc_segments, (struct proc *rp)                      );
-_PROTOTYPE( void vm_init, (void)                       			);
+_PROTOTYPE( void vm_init, (struct proc *first)        			);
 _PROTOTYPE( void vm_map_range, (u32_t base, u32_t size, u32_t offset)   );
 _PROTOTYPE( int vm_copy, (vir_bytes src, struct proc *srcproc,
 	vir_bytes dst, struct proc *dstproc, phys_bytes bytes));
@@ -130,7 +134,7 @@ _PROTOTYPE( phys_bytes umap_remote, (struct proc* rp, int seg,
 _PROTOTYPE( phys_bytes umap_virtual, (struct proc* rp, int seg,
         vir_bytes vir_addr, vir_bytes bytes)				);
 _PROTOTYPE( phys_bytes seg2phys, (U16_t)                                );
-_PROTOTYPE( void phys_memset, (phys_bytes source, unsigned long pattern,
+_PROTOTYPE( int vm_phys_memset, (phys_bytes source, u8_t pattern,
                 phys_bytes count)                                       );
 _PROTOTYPE( vir_bytes alloc_remote_segment, (u32_t *, segframe_t *,
         int, phys_bytes, vir_bytes, int));
@@ -164,5 +168,10 @@ _PROTOTYPE( int vm_checkrange, (struct proc *caller, struct proc *target,
 	vir_bytes start, vir_bytes length, int writeflag, int checkonly));
 _PROTOTYPE( void proc_stacktrace, (struct proc *proc)	         );
 _PROTOTYPE( int vm_lookup, (struct proc *proc, vir_bytes virtual, vir_bytes *result, u32_t *ptent));
+_PROTOTYPE( int vm_suspend, (struct proc *caller, struct proc *target,
+	phys_bytes lin, phys_bytes size, int wrflag, int type));
+_PROTOTYPE( int delivermsg, (struct proc *target));
+_PROTOTYPE( phys_bytes arch_switch_copymsg, (struct proc *rp, message *m,
+	phys_bytes lin));
 
 #endif /* PROTO_H */