minix/servers/pm/exec.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

196 lines
5.2 KiB
C

/* This file handles the EXEC system call. It performs the work as follows:
* - see if the permissions allow the file to be executed
* - read the header and extract the sizes
* - fetch the initial args and environment from the user space
* - allocate the memory for the new process
* - copy the initial stack from PM to the process
* - read in the text and data segments and copy to the process
* - take care of setuid and setgid bits
* - fix up 'mproc' table
* - tell kernel about EXEC
* - save offset to initial argc (for ps)
*
* The entry points into this file are:
* do_exec: perform the EXEC system call
* exec_newmem: allocate new memory map for a process that tries to exec
* do_execrestart: finish the special exec call for RS
* exec_restart: finish a regular exec call
* find_share: find a process whose text segment can be shared
*/
#include "pm.h"
#include <sys/stat.h>
#include <minix/callnr.h>
#include <minix/endpoint.h>
#include <minix/com.h>
#include <minix/vm.h>
#include <a.out.h>
#include <signal.h>
#include <string.h>
#include <sys/ptrace.h>
#include "mproc.h"
#include "param.h"
#define ESCRIPT (-2000) /* Returned by read_header for a #! script. */
#define PTRSIZE sizeof(char *) /* Size of pointers in argv[] and envp[]. */
/*===========================================================================*
* do_exec *
*===========================================================================*/
PUBLIC int do_exec()
{
message m;
int r;
/* Forward call to FS */
m.m_type = PM_EXEC;
m.PM_PROC = mp->mp_endpoint;
m.PM_PATH = m_in.exec_name;
m.PM_PATH_LEN = m_in.exec_len;
m.PM_FRAME = m_in.stack_ptr;
m.PM_FRAME_LEN = m_in.stack_bytes;
tell_fs(mp, &m);
/* Do not reply */
return SUSPEND;
}
/*===========================================================================*
* exec_newmem *
*===========================================================================*/
PUBLIC int exec_newmem()
{
int proc_e, proc_n, allow_setuid;
char *ptr;
struct mproc *rmp;
struct exec_newmem args;
int r, flags;
char *stack_top;
if (who_e != FS_PROC_NR && who_e != RS_PROC_NR)
return EPERM;
proc_e= m_in.EXC_NM_PROC;
if (pm_isokendpt(proc_e, &proc_n) != OK)
{
panic(__FILE__, "exec_newmem: got bad endpoint",
proc_e);
}
rmp= &mproc[proc_n];
ptr= m_in.EXC_NM_PTR;
r= sys_datacopy(who_e, (vir_bytes)ptr,
SELF, (vir_bytes)&args, sizeof(args));
if (r != OK)
panic(__FILE__, "exec_newmem: sys_datacopy failed", r);
if((r=vm_exec_newmem(proc_e, &args, sizeof(args), &stack_top, &flags)) == OK) {
allow_setuid= 0; /* Do not allow setuid execution */
if (rmp->mp_tracer == NO_TRACER) {
/* Okay, setuid execution is allowed */
allow_setuid= 1;
rmp->mp_effuid = args.new_uid;
rmp->mp_effgid = args.new_gid;
}
/* System will save command line for debugging, ps(1) output, etc. */
strncpy(rmp->mp_name, args.progname, PROC_NAME_LEN-1);
rmp->mp_name[PROC_NAME_LEN-1] = '\0';
/* Save offset to initial argc (for ps) */
rmp->mp_procargs = (vir_bytes) stack_top - args.args_bytes;
/* Kill process if something goes wrong after this point. */
rmp->mp_flags |= PARTIAL_EXEC;
mp->mp_reply.reply_res2= (vir_bytes) stack_top;
mp->mp_reply.reply_res3= flags;
if (allow_setuid)
mp->mp_reply.reply_res3 |= EXC_NM_RF_ALLOW_SETUID;
} else {
printf("PM: newmem failed for %s\n", args.progname);
}
return r;
}
/*===========================================================================*
* do_execrestart *
*===========================================================================*/
PUBLIC int do_execrestart()
{
int proc_e, proc_n, result;
struct mproc *rmp;
if (who_e != RS_PROC_NR)
return EPERM;
proc_e= m_in.EXC_RS_PROC;
if (pm_isokendpt(proc_e, &proc_n) != OK)
{
panic(__FILE__, "do_execrestart: got bad endpoint",
proc_e);
}
rmp= &mproc[proc_n];
result= m_in.EXC_RS_RESULT;
exec_restart(rmp, result);
return OK;
}
/*===========================================================================*
* exec_restart *
*===========================================================================*/
PUBLIC void exec_restart(rmp, result)
struct mproc *rmp;
int result;
{
int r, sn;
vir_bytes pc;
char *new_sp;
if (result != OK)
{
if (rmp->mp_flags & PARTIAL_EXEC)
{
/* Use SIGILL signal that something went wrong */
rmp->mp_sigstatus = SIGILL;
exit_proc(rmp, 0, FALSE /*dump_core*/);
return;
}
setreply(rmp-mproc, result);
return;
}
rmp->mp_flags &= ~PARTIAL_EXEC;
/* Fix 'mproc' fields, tell kernel that exec is done, reset caught
* sigs.
*/
for (sn = 1; sn < _NSIG; sn++) {
if (sigismember(&rmp->mp_catch, sn)) {
sigdelset(&rmp->mp_catch, sn);
rmp->mp_sigact[sn].sa_handler = SIG_DFL;
sigemptyset(&rmp->mp_sigact[sn].sa_mask);
}
}
/* Cause a signal if this process is traced.
* Do this before making the process runnable again!
*/
if (rmp->mp_tracer != NO_TRACER) {
sn = (rmp->mp_trace_flags & TO_ALTEXEC) ? SIGSTOP : SIGTRAP;
check_sig(rmp->mp_pid, sn);
}
new_sp= (char *)rmp->mp_procargs;
pc= 0; /* for now */
r= sys_exec(rmp->mp_endpoint, new_sp, rmp->mp_name, pc);
if (r != OK) panic(__FILE__, "sys_exec failed", r);
}