minix/kernel/system/do_fork.c
Ben Gras cd8b915ed9 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
2009-09-21 14:31:52 +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);
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 */