minix/lib/libsys/sef_liveupdate.c
Cristiano Giuffrida cb176df60f New RS and new signal handling for system processes.
UPDATING INFO:
20100317:
        /usr/src/etc/system.conf updated to ignore default kernel calls: copy
        it (or merge it) to /etc/system.conf.
        The hello driver (/dev/hello) added to the distribution:
        # cd /usr/src/commands/scripts && make clean install
        # cd /dev && MAKEDEV hello

KERNEL CHANGES:
- Generic signal handling support. The kernel no longer assumes PM as a signal
manager for every process. The signal manager of a given process can now be
specified in its privilege slot. When a signal has to be delivered, the kernel
performs the lookup and forwards the signal to the appropriate signal manager.
PM is the default signal manager for user processes, RS is the default signal
manager for system processes. To enable ptrace()ing for system processes, it
is sufficient to change the default signal manager to PM. This will temporarily
disable crash recovery, though.
- sys_exit() is now split into sys_exit() (i.e. exit() for system processes,
which generates a self-termination signal), and sys_clear() (i.e. used by PM
to ask the kernel to clear a process slot when a process exits).
- Added a new kernel call (i.e. sys_update()) to swap two process slots and
implement live update.

PM CHANGES:
- Posix signal handling is no longer allowed for system processes. System
signals are split into two fixed categories: termination and non-termination
signals. When a non-termination signaled is processed, PM transforms the signal
into an IPC message and delivers the message to the system process. When a
termination signal is processed, PM terminates the process.
- PM no longer assumes itself as the signal manager for system processes. It now
makes sure that every system signal goes through the kernel before being
actually processes. The kernel will then dispatch the signal to the appropriate
signal manager which may or may not be PM.

SYSLIB CHANGES:
- Simplified SEF init and LU callbacks.
- Added additional predefined SEF callbacks to debug crash recovery and
live update.
- Fixed a temporary ack in the SEF init protocol. SEF init reply is now
completely synchronous.
- Added SEF signal event type to provide a uniform interface for system
processes to deal with signals. A sef_cb_signal_handler() callback is
available for system processes to handle every received signal. A
sef_cb_signal_manager() callback is used by signal managers to process
system signals on behalf of the kernel.
- Fixed a few bugs with memory mapping and DS.

VM CHANGES:
- Page faults and memory requests coming from the kernel are now implemented
using signals.
- Added a new VM call to swap two process slots and implement live update.
- The call is used by RS at update time and in turn invokes the kernel call
sys_update().

RS CHANGES:
- RS has been reworked with a better functional decomposition.
- Better kernel call masks. com.h now defines the set of very basic kernel calls
every system service is allowed to use. This makes system.conf simpler and
easier to maintain. In addition, this guarantees a higher level of isolation
for system libraries that use one or more kernel calls internally (e.g. printf).
- RS is the default signal manager for system processes. By default, RS
intercepts every signal delivered to every system process. This makes crash
recovery possible before bringing PM and friends in the loop.
- RS now supports fast rollback when something goes wrong while initializing
the new version during a live update.
- Live update is now implemented by keeping the two versions side-by-side and
swapping the process slots when the old version is ready to update.
- Crash recovery is now implemented by keeping the two versions side-by-side
and cleaning up the old version only when the recovery process is complete.

DS CHANGES:
- Fixed a bug when the process doing ds_publish() or ds_delete() is not known
by DS.
- Fixed the completely broken support for strings. String publishing is now
implemented in the system library and simply wraps publishing of memory ranges.
Ideally, we should adopt a similar approach for other data types as well.
- Test suite fixed.

DRIVER CHANGES:
- The hello driver has been added to the Minix distribution to demonstrate basic
live update and crash recovery functionalities.
- Other drivers have been adapted to conform the new SEF interface.
2010-03-17 01:15:29 +00:00

292 lines
9.7 KiB
C

#include "syslib.h"
#include <assert.h>
#include <minix/sysutil.h>
/* SEF Live update variables. */
PRIVATE int sef_lu_state = SEF_LU_STATE_NULL;
/* SEF Live update callbacks. */
PRIVATE struct sef_cbs {
sef_cb_lu_prepare_t sef_cb_lu_prepare;
sef_cb_lu_state_isvalid_t sef_cb_lu_state_isvalid;
sef_cb_lu_state_changed_t sef_cb_lu_state_changed;
sef_cb_lu_state_dump_t sef_cb_lu_state_dump;
sef_cb_lu_state_save_t sef_cb_lu_state_save;
} sef_cbs = {
SEF_CB_LU_PREPARE_DEFAULT,
SEF_CB_LU_STATE_ISVALID_DEFAULT,
SEF_CB_LU_STATE_CHANGED_DEFAULT,
SEF_CB_LU_STATE_DUMP_DEFAULT,
SEF_CB_LU_STATE_SAVE_DEFAULT,
};
/* SEF Live update prototypes for sef_receive(). */
PUBLIC _PROTOTYPE( void do_sef_lu_before_receive, (void) );
PUBLIC _PROTOTYPE( int do_sef_lu_request, (message *m_ptr) );
/* SEF Live update helpers. */
PRIVATE _PROTOTYPE( void sef_lu_ready, (int result) );
/* Debug. */
EXTERN _PROTOTYPE( char* sef_debug_header, (void) );
PRIVATE int sef_lu_debug_cycle = 0;
/*===========================================================================*
* do_sef_lu_before_receive *
*===========================================================================*/
PUBLIC void do_sef_lu_before_receive()
{
/* Handle SEF Live update before receive events. */
int r;
/* Nothing to do if we are not preparing for a live update. */
if(sef_lu_state == SEF_LU_STATE_NULL) {
return;
}
/* Debug. */
#if SEF_LU_DEBUG
sef_lu_debug_cycle++;
sef_lu_debug_begin();
sef_lu_dprint("%s, cycle=%d. Dumping state variables:\n",
sef_debug_header(), sef_lu_debug_cycle);
sef_cbs.sef_cb_lu_state_dump(sef_lu_state);
sef_lu_debug_end();
#endif
/* Let the callback code handle the event.
* For SEF_LU_STATE_WORK_FREE, we're always ready, tell immediately.
*/
r = OK;
if(sef_lu_state != SEF_LU_STATE_WORK_FREE) {
r = sef_cbs.sef_cb_lu_prepare(sef_lu_state);
}
if(r == OK) {
sef_lu_ready(OK);
}
}
/*===========================================================================*
* do_sef_lu_request *
*===========================================================================*/
PUBLIC int do_sef_lu_request(message *m_ptr)
{
/* Handle a SEF Live update request. */
int state, old_state, is_valid_state;
sef_lu_debug_cycle = 0;
old_state = sef_lu_state;
state = m_ptr->RS_LU_STATE;
/* Deal with prepare cancel requests first. */
is_valid_state = (state == SEF_LU_STATE_NULL);
/* Otherwise only accept live update requests with a valid state. */
is_valid_state = is_valid_state || sef_cbs.sef_cb_lu_state_isvalid(state);
if(!is_valid_state) {
if(sef_cbs.sef_cb_lu_state_isvalid == SEF_CB_LU_STATE_ISVALID_NULL) {
sef_lu_ready(ENOSYS);
}
else {
sef_lu_ready(EINVAL);
}
}
else {
/* Set the new live update state. */
sef_lu_state = state;
/* If the live update state changed, let the callback code
* handle the rest.
*/
if(old_state != sef_lu_state) {
sef_cbs.sef_cb_lu_state_changed(old_state, sef_lu_state);
}
}
/* Return OK not to let anybody else intercept the request. */
return(OK);
}
/*===========================================================================*
* sef_lu_ready *
*===========================================================================*/
PRIVATE void sef_lu_ready(int result)
{
message m;
int old_state, rs_result, r;
#if SEF_LU_DEBUG
sef_lu_debug_begin();
sef_lu_dprint("%s, cycle=%d. Ready to update with result: %d%s\n",
sef_debug_header(), sef_lu_debug_cycle,
result, (result == OK ? "(OK)" : ""));
sef_lu_debug_end();
#endif
/* If result is OK, let the callback code save
* any state that must be carried over to the new version.
*/
if(result == OK) {
r = sef_cbs.sef_cb_lu_state_save(sef_lu_state);
if(r != OK) {
/* Abort update if callback returned error. */
result = r;
}
}
/* Inform RS that we're ready with the given result. */
m.m_type = RS_LU_PREPARE;
m.RS_LU_STATE = sef_lu_state;
m.RS_LU_RESULT = result;
r = sendrec(RS_PROC_NR, &m);
if ( r != OK) {
panic("sendrec failed: %d", r);
}
#if SEF_LU_DEBUG
rs_result = m.m_type == RS_LU_PREPARE ? EINTR : m.m_type;
sef_lu_debug_begin();
sef_lu_dprint("%s, cycle=%d. The %s aborted the update with result %d!\n",
sef_debug_header(), sef_lu_debug_cycle,
(result == OK ? "server" : "client"),
(result == OK ? rs_result : result)); /* EINTR if update was canceled. */
sef_lu_debug_end();
#endif
/* Something went wrong. Update was aborted and we didn't get updated.
* Restore things back to normal and continue executing.
*/
old_state = sef_lu_state;
sef_lu_state = SEF_LU_STATE_NULL;
if(old_state != sef_lu_state) {
sef_cbs.sef_cb_lu_state_changed(old_state, sef_lu_state);
}
}
/*===========================================================================*
* sef_setcb_lu_prepare *
*===========================================================================*/
PUBLIC void sef_setcb_lu_prepare(sef_cb_lu_prepare_t cb)
{
assert(cb != NULL);
sef_cbs.sef_cb_lu_prepare = cb;
}
/*===========================================================================*
* sef_setcb_lu_state_isvalid *
*===========================================================================*/
PUBLIC void sef_setcb_lu_state_isvalid(sef_cb_lu_state_isvalid_t cb)
{
assert(cb != NULL);
sef_cbs.sef_cb_lu_state_isvalid = cb;
}
/*===========================================================================*
* sef_setcb_lu_state_changed *
*===========================================================================*/
PUBLIC void sef_setcb_lu_state_changed(sef_cb_lu_state_changed_t cb)
{
assert(cb != NULL);
sef_cbs.sef_cb_lu_state_changed = cb;
}
/*===========================================================================*
* sef_setcb_lu_state_dump *
*===========================================================================*/
PUBLIC void sef_setcb_lu_state_dump(sef_cb_lu_state_dump_t cb)
{
assert(cb != NULL);
sef_cbs.sef_cb_lu_state_dump = cb;
}
/*===========================================================================*
* sef_setcb_lu_state_save *
*===========================================================================*/
PUBLIC void sef_setcb_lu_state_save(sef_cb_lu_state_save_t cb)
{
assert(cb != NULL);
sef_cbs.sef_cb_lu_state_save = cb;
}
/*===========================================================================*
* sef_cb_lu_prepare_null *
*===========================================================================*/
PUBLIC int sef_cb_lu_prepare_null(int UNUSED(state))
{
return ENOTREADY;
}
/*===========================================================================*
* sef_cb_lu_state_isvalid_null *
*===========================================================================*/
PUBLIC int sef_cb_lu_state_isvalid_null(int UNUSED(state))
{
return FALSE;
}
/*===========================================================================*
* sef_cb_lu_state_changed_null *
*===========================================================================*/
PUBLIC void sef_cb_lu_state_changed_null(int UNUSED(old_state),
int UNUSED(state))
{
}
/*===========================================================================*
* sef_cb_lu_state_dump_null *
*===========================================================================*/
PUBLIC void sef_cb_lu_state_dump_null(int UNUSED(state))
{
sef_lu_dprint("NULL\n");
}
/*===========================================================================*
* sef_cb_lu_state_save_null *
*===========================================================================*/
PUBLIC int sef_cb_lu_state_save_null(int UNUSED(result))
{
return OK;
}
/*===========================================================================*
* sef_cb_lu_prepare_always_ready *
*===========================================================================*/
PUBLIC int sef_cb_lu_prepare_always_ready(int UNUSED(state))
{
return OK;
}
/*===========================================================================*
* sef_cb_lu_prepare_never_ready *
*===========================================================================*/
PUBLIC int sef_cb_lu_prepare_never_ready(int UNUSED(state))
{
#if SEF_LU_DEBUG
sef_lu_debug_begin();
sef_lu_dprint("%s, cycle=%d. Simulating a service never ready to update...\n",
sef_debug_header(), sef_lu_debug_cycle);
sef_lu_debug_end();
#endif
return ENOTREADY;
}
/*===========================================================================*
* sef_cb_lu_prepare_crash *
*===========================================================================*/
PUBLIC int sef_cb_lu_prepare_crash(int UNUSED(state))
{
panic("Simulating a crash at update prepare time...");
return OK;
}
/*===========================================================================*
* sef_cb_lu_state_isvalid_standard *
*===========================================================================*/
PUBLIC int sef_cb_lu_state_isvalid_standard(int state)
{
return SEF_LU_STATE_IS_STANDARD(state);
}