minix/kernel/system/do_fork.c
David van Moolenbroek b423d7b477 Merge of David's ptrace branch. Summary:
o Support for ptrace T_ATTACH/T_DETACH and T_SYSCALL
o PM signal handling logic should now work properly, even with debuggers
  being present
o Asynchronous PM/VFS protocol, full IPC support for senda(), and
  AMF_NOREPLY senda() flag

DETAILS

Process stop and delay call handling of PM:
o Added sys_runctl() kernel call with sys_stop() and sys_resume()
  aliases, for PM to stop and resume a process
o Added exception for sending/syscall-traced processes to sys_runctl(),
  and matching SIGKREADY pseudo-signal to PM
o Fixed PM signal logic to deal with requests from a process after
  stopping it (so-called "delay calls"), using the SIGKREADY facility
o Fixed various PM panics due to race conditions with delay calls versus
  VFS calls
o Removed special PRIO_STOP priority value
o Added SYS_LOCK RTS kernel flag, to stop an individual process from
  running while modifying its process structure

Signal and debugger handling in PM:
o Fixed debugger signals being dropped if a second signal arrives when
  the debugger has not retrieved the first one
o Fixed debugger signals being sent to the debugger more than once
o Fixed debugger signals unpausing process in VFS; removed PM_UNPAUSE_TR
  protocol message
o Detached debugger signals from general signal logic and from being
  blocked on VFS calls, meaning that even VFS can now be traced
o Fixed debugger being unable to receive more than one pending signal in
  one process stop
o Fixed signal delivery being delayed needlessly when multiple signals
  are pending
o Fixed wait test for tracer, which was returning for children that were
  not waited for
o Removed second parallel pending call from PM to VFS for any process
o Fixed process becoming runnable between exec() and debugger trap
o Added support for notifying the debugger before the parent when a
  debugged child exits
o Fixed debugger death causing child to remain stopped forever
o Fixed consistently incorrect use of _NSIG

Extensions to ptrace():
o Added T_ATTACH and T_DETACH ptrace request, to attach and detach a
  debugger to and from a process
o Added T_SYSCALL ptrace request, to trace system calls
o Added T_SETOPT ptrace request, to set trace options
o Added TO_TRACEFORK trace option, to attach automatically to children
  of a traced process
o Added TO_ALTEXEC trace option, to send SIGSTOP instead of SIGTRAP upon
  a successful exec() of the tracee
o Extended T_GETUSER ptrace support to allow retrieving a process's priv
  structure
o Removed T_STOP ptrace request again, as it does not help implementing
  debuggers properly
o Added MINIX3-specific ptrace test (test42)
o Added proper manual page for ptrace(2)

Asynchronous PM/VFS interface:
o Fixed asynchronous messages not being checked when receive() is called
  with an endpoint other than ANY
o Added AMF_NOREPLY senda() flag, preventing such messages from
  satisfying the receive part of a sendrec()
o Added asynsend3() that takes optional flags; asynsend() is now a
  #define passing in 0 as third parameter
o Made PM/VFS protocol asynchronous; reintroduced tell_fs()
o Made PM_BASE request/reply number range unique
o Hacked in a horrible temporary workaround into RS to deal with newly
  revealed RS-PM-VFS race condition triangle until VFS is asynchronous

System signal handling:
o Fixed shutdown logic of device drivers; removed old SIGKSTOP signal
o Removed is-superuser check from PM's do_procstat() (aka getsigset())
o Added sigset macros to allow system processes to deal with the full
  signal set, rather than just the POSIX subset

Miscellaneous PM fixes:
o Split do_getset into do_get and do_set, merging common code and making
  structure clearer
o Fixed setpriority() being able to put to sleep processes using an
  invalid parameter, or revive zombie processes
o Made find_proc() global; removed obsolete proc_from_pid()
o Cleanup here and there

Also included:
o Fixed false-positive boot order kernel warning
o Removed last traces of old NOTIFY_FROM code

THINGS OF POSSIBLE INTEREST

o It should now be possible to run PM at any priority, even lower than
  user processes
o No assumptions are made about communication speed between PM and VFS,
  although communication must be FIFO
o A debugger will now receive incoming debuggee signals at kill time
  only; the process may not yet be fully stopped
o A first step has been made towards making the SYSTEM task preemptible
2009-09-30 09:57:22 +00:00

119 lines
3.8 KiB
C

/* The kernel call implemented in this file:
* m_type: SYS_FORK
*
* The parameters for this kernel call are:
* m1_i1: PR_ENDPT (parent, process that forked)
* m1_i2: PR_SLOT (child's process table slot)
* m1_p1: PR_MEM_PTR (new memory map for the child)
* m1_i3: PR_FORK_FLAGS (fork flags)
*/
#include "../system.h"
#include "../vm.h"
#include <signal.h>
#include <minix/endpoint.h>
#if USE_FORK
/*===========================================================================*
* do_fork *
*===========================================================================*/
PUBLIC int do_fork(m_ptr)
register message *m_ptr; /* pointer to request message */
{
/* Handle sys_fork(). PR_ENDPT has forked. The child is PR_SLOT. */
#if (_MINIX_CHIP == _CHIP_INTEL)
reg_t old_ldt_sel;
#endif
register struct proc *rpc; /* child process pointer */
struct proc *rpp; /* parent process pointer */
struct mem_map *map_ptr; /* virtual address of map inside caller (PM) */
int i, gen, r;
int p_proc;
if(!isokendpt(m_ptr->PR_ENDPT, &p_proc))
return EINVAL;
rpp = proc_addr(p_proc);
rpc = proc_addr(m_ptr->PR_SLOT);
if (isemptyp(rpp) || ! isemptyp(rpc)) return(EINVAL);
vmassert(!(rpp->p_misc_flags & MF_DELIVERMSG));
/* needs to be receiving so we know where the message buffer is */
if(!RTS_ISSET(rpp, RECEIVING)) {
printf("kernel: fork not done synchronously?\n");
return EINVAL;
}
/* memory becomes readonly */
if (priv(rpp)->s_asynsize > 0) {
printf("kernel: process with waiting asynsend table can't fork\n");
return EINVAL;
}
map_ptr= (struct mem_map *) m_ptr->PR_MEM_PTR;
/* Copy parent 'proc' struct to child. And reinitialize some fields. */
gen = _ENDPOINT_G(rpc->p_endpoint);
#if (_MINIX_CHIP == _CHIP_INTEL)
old_ldt_sel = rpc->p_seg.p_ldt_sel; /* backup local descriptors */
#endif
*rpc = *rpp; /* copy 'proc' struct */
#if (_MINIX_CHIP == _CHIP_INTEL)
rpc->p_seg.p_ldt_sel = old_ldt_sel; /* restore descriptors */
#endif
if(++gen >= _ENDPOINT_MAX_GENERATION) /* increase generation */
gen = 1; /* generation number wraparound */
rpc->p_nr = m_ptr->PR_SLOT; /* this was obliterated by copy */
rpc->p_endpoint = _ENDPOINT(gen, rpc->p_nr); /* new endpoint of slot */
rpc->p_reg.retreg = 0; /* child sees pid = 0 to know it is child */
rpc->p_user_time = 0; /* set all the accounting times to 0 */
rpc->p_sys_time = 0;
rpc->p_reg.psw &= ~TRACEBIT; /* clear trace bit */
rpc->p_misc_flags &= ~(MF_VIRT_TIMER | MF_PROF_TIMER | MF_SC_TRACE);
rpc->p_virt_left = 0; /* disable, clear the process-virtual timers */
rpc->p_prof_left = 0;
/* Parent and child have to share the quantum that the forked process had,
* so that queued processes do not have to wait longer because of the fork.
* If the time left is odd, the child gets an extra tick.
*/
rpc->p_ticks_left = (rpc->p_ticks_left + 1) / 2;
rpp->p_ticks_left = rpp->p_ticks_left / 2;
/* If the parent is a privileged process, take away the privileges from the
* child process and inhibit it from running by setting the NO_PRIV flag.
* The caller should explicitely set the new privileges before executing.
*/
if (priv(rpp)->s_flags & SYS_PROC) {
rpc->p_priv = priv_addr(USER_PRIV_ID);
rpc->p_rts_flags |= NO_PRIV;
}
/* Calculate endpoint identifier, so caller knows what it is. */
m_ptr->PR_ENDPT = rpc->p_endpoint;
m_ptr->PR_FORK_MSGADDR = (char *) rpp->p_delivermsg_vir;
/* Install new map */
r = newmap(rpc, map_ptr);
FIXLINMSG(rpc);
/* Don't schedule process in VM mode until it has a new pagetable. */
if(m_ptr->PR_FORK_FLAGS & PFF_VMINHIBIT) {
RTS_LOCK_SET(rpc, VMINHIBIT);
}
/* Only one in group should have SIGNALED, child doesn't inherit tracing. */
RTS_LOCK_UNSET(rpc, (SIGNALED | SIG_PENDING | P_STOP));
sigemptyset(&rpc->p_pending);
return r;
}
#endif /* USE_FORK */