minix/kernel/system/do_update.c
Ben Gras 50e2064049 No more intel/minix segments.
This commit removes all traces of Minix segments (the text/data/stack
memory map abstraction in the kernel) and significance of Intel segments
(hardware segments like CS, DS that add offsets to all addressing before
page table translation). This ultimately simplifies the memory layout
and addressing and makes the same layout possible on non-Intel
architectures.

There are only two types of addresses in the world now: virtual
and physical; even the kernel and processes have the same virtual
address space. Kernel and user processes can be distinguished at a
glance as processes won't use 0xF0000000 and above.

No static pre-allocated memory sizes exist any more.

Changes to booting:
        . The pre_init.c leaves the kernel and modules exactly as
          they were left by the bootloader in physical memory
        . The kernel starts running using physical addressing,
          loaded at a fixed location given in its linker script by the
          bootloader.  All code and data in this phase are linked to
          this fixed low location.
        . It makes a bootstrap pagetable to map itself to a
          fixed high location (also in linker script) and jumps to
          the high address. All code and data then use this high addressing.
        . All code/data symbols linked at the low addresses is prefixed by
          an objcopy step with __k_unpaged_*, so that that code cannot
          reference highly-linked symbols (which aren't valid yet) or vice
          versa (symbols that aren't valid any more).
        . The two addressing modes are separated in the linker script by
          collecting the unpaged_*.o objects and linking them with low
          addresses, and linking the rest high. Some objects are linked
          twice, once low and once high.
        . The bootstrap phase passes a lot of information (e.g. free memory
          list, physical location of the modules, etc.) using the kinfo
          struct.
        . After this bootstrap the low-linked part is freed.
        . The kernel maps in VM into the bootstrap page table so that VM can
          begin executing. Its first job is to make page tables for all other
          boot processes. So VM runs before RS, and RS gets a fully dynamic,
          VM-managed address space. VM gets its privilege info from RS as usual
          but that happens after RS starts running.
        . Both the kernel loading VM and VM organizing boot processes happen
	  using the libexec logic. This removes the last reason for VM to
	  still know much about exec() and vm/exec.c is gone.

Further Implementation:
        . All segments are based at 0 and have a 4 GB limit.
        . The kernel is mapped in at the top of the virtual address
          space so as not to constrain the user processes.
        . Processes do not use segments from the LDT at all; there are
          no segments in the LDT any more, so no LLDT is needed.
        . The Minix segments T/D/S are gone and so none of the
          user-space or in-kernel copy functions use them. The copy
          functions use a process endpoint of NONE to realize it's
          a physical address, virtual otherwise.
        . The umap call only makes sense to translate a virtual address
          to a physical address now.
        . Segments-related calls like newmap and alloc_segments are gone.
        . All segments-related translation in VM is gone (vir2map etc).
        . Initialization in VM is simpler as no moving around is necessary.
        . VM and all other boot processes can be linked wherever they wish
          and will be mapped in at the right location by the kernel and VM
          respectively.

Other changes:
        . The multiboot code is less special: it does not use mb_print
          for its diagnostics any more but uses printf() as normal, saving
          the output into the diagnostics buffer, only printing to the
          screen using the direct print functions if a panic() occurs.
        . The multiboot code uses the flexible 'free memory map list'
          style to receive the list of free memory if available.
        . The kernel determines the memory layout of the processes to
          a degree: it tells VM where the kernel starts and ends and
          where the kernel wants the top of the process to be. VM then
          uses this entire range, i.e. the stack is right at the top,
          and mmap()ped bits of memory are placed below that downwards,
          and the break grows upwards.

Other Consequences:
        . Every process gets its own page table as address spaces
          can't be separated any more by segments.
        . As all segments are 0-based, there is no distinction between
          virtual and linear addresses, nor between userspace and
          kernel addresses.
        . Less work is done when context switching, leading to a net
          performance increase. (8% faster on my machine for 'make servers'.)
	. The layout and configuration of the GDT makes sysenter and syscall
	  possible.
2012-07-15 22:30:15 +02:00

181 lines
5.5 KiB
C

/* The kernel call implemented in this file:
* m_type: SYS_UPDATE
*
* The parameters for this kernel call are:
* m2_i1: SYS_UPD_SRC_ENDPT (source process endpoint)
* m2_i2: SYS_UPD_DST_ENDPT (destination process endpoint)
*/
#include "kernel/system.h"
#include "kernel/ipc.h"
#include <string.h>
#include <assert.h>
#if USE_UPDATE
#define DEBUG 0
#define proc_is_updatable(p) \
(RTS_ISSET(p, RTS_NO_PRIV) || RTS_ISSET(p, RTS_SIG_PENDING) \
|| (RTS_ISSET(p, RTS_RECEIVING) && !RTS_ISSET(p, RTS_SENDING)))
static void adjust_proc_slot(struct proc *rp, struct proc *from_rp);
static void adjust_priv_slot(struct priv *privp, struct priv
*from_privp);
static void swap_proc_slot_pointer(struct proc **rpp, struct proc
*src_rp, struct proc *dst_rp);
/*===========================================================================*
* do_update *
*===========================================================================*/
int do_update(struct proc * caller, message * m_ptr)
{
/* Handle sys_update(). Update a process into another by swapping their process
* slots.
*/
endpoint_t src_e, dst_e;
int src_p, dst_p;
struct proc *src_rp, *dst_rp;
struct priv *src_privp, *dst_privp;
struct proc orig_src_proc;
struct proc orig_dst_proc;
struct priv orig_src_priv;
struct priv orig_dst_priv;
int i;
/* Lookup slots for source and destination process. */
src_e = m_ptr->SYS_UPD_SRC_ENDPT;
if(!isokendpt(src_e, &src_p)) {
return EINVAL;
}
src_rp = proc_addr(src_p);
src_privp = priv(src_rp);
if(!(src_privp->s_flags & SYS_PROC)) {
return EPERM;
}
dst_e = m_ptr->SYS_UPD_DST_ENDPT;
if(!isokendpt(dst_e, &dst_p)) {
return EINVAL;
}
dst_rp = proc_addr(dst_p);
dst_privp = priv(dst_rp);
if(!(dst_privp->s_flags & SYS_PROC)) {
return EPERM;
}
assert(!proc_is_runnable(src_rp) && !proc_is_runnable(dst_rp));
/* Check if processes are updatable. */
if(!proc_is_updatable(src_rp) || !proc_is_updatable(dst_rp)) {
return EBUSY;
}
#if DEBUG
printf("do_update: updating %d (%s, %d, %d) into %d (%s, %d, %d)\n",
src_rp->p_endpoint, src_rp->p_name, src_rp->p_nr, priv(src_rp)->s_proc_nr,
dst_rp->p_endpoint, dst_rp->p_name, dst_rp->p_nr, priv(dst_rp)->s_proc_nr);
proc_stacktrace(src_rp);
proc_stacktrace(dst_rp);
printf("do_update: curr ptproc %d\n", get_cpulocal_var(ptproc)->p_endpoint);
#endif
/* Let destination inherit the target mask from source. */
for (i=0; i < NR_SYS_PROCS; i++) {
if (get_sys_bit(priv(src_rp)->s_ipc_to, i)) {
set_sendto_bit(dst_rp, i);
}
}
/* Save existing data. */
orig_src_proc = *src_rp;
orig_src_priv = *(priv(src_rp));
orig_dst_proc = *dst_rp;
orig_dst_priv = *(priv(dst_rp));
/* Swap slots. */
*src_rp = orig_dst_proc;
*src_privp = orig_dst_priv;
*dst_rp = orig_src_proc;
*dst_privp = orig_src_priv;
/* Adjust process slots. */
adjust_proc_slot(src_rp, &orig_src_proc);
adjust_proc_slot(dst_rp, &orig_dst_proc);
/* Adjust privilege slots. */
adjust_priv_slot(priv(src_rp), &orig_src_priv);
adjust_priv_slot(priv(dst_rp), &orig_dst_priv);
/* Swap global process slot addresses. */
swap_proc_slot_pointer(get_cpulocal_var_ptr(ptproc), src_rp, dst_rp);
#if DEBUG
printf("do_update: updated %d (%s, %d, %d) into %d (%s, %d, %d)\n",
src_rp->p_endpoint, src_rp->p_name, src_rp->p_nr, priv(src_rp)->s_proc_nr,
dst_rp->p_endpoint, dst_rp->p_name, dst_rp->p_nr, priv(dst_rp)->s_proc_nr);
proc_stacktrace(src_rp);
proc_stacktrace(dst_rp);
printf("do_update: curr ptproc %d\n", get_cpulocal_var(ptproc)->p_endpoint);
#endif
#ifdef CONFIG_SMP
bits_fill(src_rp->p_stale_tlb, CONFIG_MAX_CPUS);
bits_fill(dst_rp->p_stale_tlb, CONFIG_MAX_CPUS);
#endif
return OK;
}
/*===========================================================================*
* adjust_proc_slot *
*===========================================================================*/
static void adjust_proc_slot(struct proc *rp, struct proc *from_rp)
{
/* Preserve endpoints, slot numbers, priv structure, and IPC. */
rp->p_endpoint = from_rp->p_endpoint;
rp->p_nr = from_rp->p_nr;
rp->p_priv = from_rp->p_priv;
priv(rp)->s_proc_nr = from_rp->p_nr;
rp->p_caller_q = from_rp->p_caller_q;
/* preserve scheduling */
rp->p_scheduler = from_rp->p_scheduler;
#ifdef CONFIG_SMP
rp->p_cpu = from_rp->p_cpu;
memcpy(rp->p_cpu_mask, from_rp->p_cpu_mask,
sizeof(bitchunk_t) * BITMAP_CHUNKS(CONFIG_MAX_CPUS));
#endif
}
/*===========================================================================*
* adjust_priv_slot *
*===========================================================================*/
static void adjust_priv_slot(struct priv *privp, struct priv *from_privp)
{
/* Preserve privilege ids and non-privilege stuff in the priv structure. */
privp->s_id = from_privp->s_id;
privp->s_notify_pending = from_privp->s_notify_pending;
privp->s_int_pending = from_privp->s_int_pending;
privp->s_sig_pending = from_privp->s_sig_pending;
privp->s_alarm_timer = from_privp->s_alarm_timer;
}
/*===========================================================================*
* swap_proc_slot_pointer *
*===========================================================================*/
static void swap_proc_slot_pointer(struct proc **rpp, struct proc *src_rp,
struct proc *dst_rp)
{
if(*rpp == src_rp) {
*rpp = dst_rp;
}
else if(*rpp == dst_rp) {
*rpp = src_rp;
}
}
#endif /* USE_UPDATE */