Minix/minix
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

Primary goal for these changes is:

Browse Source 
- 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
This commit is contained in:
Ben Gras
2009-09-21 14:31:52 +00:00
parent f5b04e1881
commit cd8b915ed9
39 changed files with 2149 additions and 1319 deletions
Download Patch File Download Diff File Expand all files Collapse all files

96
kernel/proc.h
View File

@@ -10,6 +10,7 @@
* struct proc, be sure to change sconst.h to match.
*/
#include <minix/com.h>
#include <minix/portio.h>
#include "const.h"
#include "priv.h"
@@ -39,7 +40,6 @@ struct proc {
struct proc *p_nextready; /* pointer to next ready process */
struct proc *p_caller_q; /* head of list of procs wishing to send */
struct proc *p_q_link; /* link to next proc wishing to send */
message *p_messbuf; /* pointer to passed message buffer */
int p_getfrom_e; /* from whom does process want to receive? */
int p_sendto_e; /* to whom does process want to send? */
@@ -49,6 +49,11 @@ struct proc {
endpoint_t p_endpoint; /* endpoint number, generation-aware */
message p_sendmsg; /* Message from this process if SENDING */
message p_delivermsg; /* Message for this process if MF_DELIVERMSG */
vir_bytes p_delivermsg_vir; /* Virtual addr this proc wants message at */
vir_bytes p_delivermsg_lin; /* Linear addr this proc wants message at */
/* If handler functions detect a process wants to do something with
* memory that isn't present, VM has to fix it. Until it has asked
* what needs to be done and fixed it, save necessary state here.
@@ -60,28 +65,12 @@ struct proc {
struct proc *nextrestart; /* next in vmrestart chain */
struct proc *nextrequestor; /* next in vmrequest chain */
#define VMSTYPE_SYS_NONE 0
#define VMSTYPE_SYS_MESSAGE 1
#define VMSTYPE_SYS_CALL 2
#define VMSTYPE_MSGCOPY 3
#define VMSTYPE_KERNELCALL 1
#define VMSTYPE_DELIVERMSG 2
int type; /* suspended operation */
union {
/* VMSTYPE_SYS_MESSAGE */
message reqmsg; /* suspended request message */
/* VMSTYPE_SYS_CALL */
struct {
int call_nr;
message *m_ptr;
int src_dst_e;
long bit_map;
} sys_call;
/* VMSTYPE_MSGCOPY */
struct {
struct proc *dst;
vir_bytes dst_v;
message msgbuf;
} msgcopy;
} saved;
/* Parameters of request to VM */
@@ -92,10 +81,9 @@ struct proc {
/* VM result when available */
int vmresult;
/* Target gets this set. (But caller and target can be
* the same, so we can't put this in the 'saved' union.)
*/
struct proc *requestor;
#if DEBUG_VMASSERT
char stacktrace[200];
#endif
/* If the suspended operation is a sys_call, its details are
* stored here.
@@ -110,21 +98,26 @@ struct proc {
#define PMAGIC 0xC0FFEE1
int p_magic; /* check validity of proc pointers */
#endif
#if DEBUG_TRACE
int p_schedules;
#endif
};
/* Bits for the runtime flags. A process is runnable iff p_rts_flags == 0. */
#define SLOT_FREE 0x01 /* process slot is free */
#define NO_PRIORITY 0x02 /* process has been stopped */
#define SENDING 0x04 /* process blocked trying to send */
#define RECEIVING 0x08 /* process blocked trying to receive */
#define SIGNALED 0x10 /* set when new kernel signal arrives */
#define SIG_PENDING 0x20 /* unready while signal being processed */
#define P_STOP 0x40 /* set when process is being traced */
#define NO_PRIV 0x80 /* keep forked system process from running */
#define NO_ENDPOINT 0x100 /* process cannot send or receive messages */
#define VMINHIBIT 0x200 /* not scheduled until pagetable set by VM */
#define PAGEFAULT 0x400 /* process has unhandled pagefault */
#define VMREQUEST 0x800 /* originator of vm memory request */
#define SLOT_FREE 0x01 /* process slot is free */
#define NO_PRIORITY 0x02 /* process has been stopped */
#define SENDING 0x04 /* process blocked trying to send */
#define RECEIVING 0x08 /* process blocked trying to receive */
#define SIGNALED 0x10 /* set when new kernel signal arrives */
#define SIG_PENDING 0x20 /* unready while signal being processed */
#define P_STOP 0x40 /* set when process is being traced */
#define NO_PRIV 0x80 /* keep forked system process from running */
#define NO_ENDPOINT 0x100 /* process cannot send or receive messages */
#define VMINHIBIT 0x200 /* not scheduled until pagetable set by VM */
#define PAGEFAULT 0x400 /* process has unhandled pagefault */
#define VMREQUEST 0x800 /* originator of vm memory request */
#define VMREQTARGET 0x1000 /* target of vm memory request */
/* These runtime flags can be tested and manipulated by these macros. */
@@ -134,49 +127,62 @@ struct proc {
/* Set flag and dequeue if the process was runnable. */
#define RTS_SET(rp, f) \
do { \
vmassert(intr_disabled()); \
if(!(rp)->p_rts_flags) { dequeue(rp); } \
(rp)->p_rts_flags |= (f); \
vmassert(intr_disabled()); \
} while(0)
/* Clear flag and enqueue if the process was not runnable but is now. */
#define RTS_UNSET(rp, f) \
do { \
int rts; \
rts = (rp)->p_rts_flags; \
vmassert(intr_disabled()); \
rts = (rp)->p_rts_flags; \
(rp)->p_rts_flags &= ~(f); \
if(rts && !(rp)->p_rts_flags) { enqueue(rp); } \
vmassert(intr_disabled()); \
} while(0)
/* Set flag and dequeue if the process was runnable. */
#define RTS_LOCK_SET(rp, f) \
do { \
if(!(rp)->p_rts_flags) { lock_dequeue(rp); } \
int u = 0; \
if(!intr_disabled()) { u = 1; lock; } \
if(!(rp)->p_rts_flags) { dequeue(rp); } \
(rp)->p_rts_flags |= (f); \
if(u) { unlock; } \
} while(0)
/* Clear flag and enqueue if the process was not runnable but is now. */
#define RTS_LOCK_UNSET(rp, f) \
do { \
int rts; \
rts = (rp)->p_rts_flags; \
int u = 0; \
if(!intr_disabled()) { u = 1; lock; } \
rts = (rp)->p_rts_flags; \
(rp)->p_rts_flags &= ~(f); \
if(rts && !(rp)->p_rts_flags) { lock_enqueue(rp); } \
if(rts && !(rp)->p_rts_flags) { enqueue(rp); } \
if(u) { unlock; } \
} while(0)
/* Set flags to this value. */
#define RTS_LOCK_SETFLAGS(rp, f) \
do { \
if(!(rp)->p_rts_flags && (f)) { lock_dequeue(rp); } \
(rp)->p_rts_flags = (f); \
int u = 0; \
if(!intr_disabled()) { u = 1; lock; } \
if(!(rp)->p_rts_flags && (f)) { dequeue(rp); } \
(rp)->p_rts_flags = (f); \
if(u) { unlock; } \
} while(0)
/* Misc flags */
#define REPLY_PENDING 0x01 /* reply to IPC_REQUEST is pending */
#define VIRT_TIMER 0x02 /* process-virtual timer is running */
#define PROF_TIMER 0x04 /* process-virtual profile timer is running */
#define MF_VM 0x08 /* process uses VM */
#define MF_REPLY_PEND 0x01 /* reply to IPC_REQUEST is pending */
#define MF_VIRT_TIMER 0x02 /* process-virtual timer is running */
#define MF_PROF_TIMER 0x04 /* process-virtual profile timer is running */
#define MF_ASYNMSG 0x10 /* Asynchrous message pending */
#define MF_FULLVM 0x20
#define MF_DELIVERMSG 0x40 /* Copy message for him before running */
/* Scheduling priorities for p_priority. Values must start at zero (highest
* priority) and increment. Priorities of the processes in the boot image