minix/kernel/arch/i386/include/archconst.h
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

143 lines
6 KiB
C

#ifndef _I386_ACONST_H
#define _I386_ACONST_H 1
#include <ibm/interrupt.h>
#include <ibm/memory.h>
#define NR_REMOTE_SEGS 3 /* # remote memory regions (variable) */
/* Constants for protected mode. */
/* Table sizes. */
#define GDT_SIZE (FIRST_LDT_INDEX + NR_TASKS + NR_PROCS)
/* spec. and LDT's */
#define IDT_SIZE (IRQ8_VECTOR + 8) /* only up to the highest vector */
/* Fixed global descriptors. 1 to 7 are prescribed by the BIOS. */
#define GDT_INDEX 1 /* GDT descriptor */
#define IDT_INDEX 2 /* IDT descriptor */
#define DS_INDEX 3 /* kernel DS */
#define ES_INDEX 4 /* kernel ES (386: flag 4 Gb at startup) */
#define SS_INDEX 5 /* kernel SS (386: monitor SS at startup) */
#define CS_INDEX 6 /* kernel CS */
#define MON_CS_INDEX 7 /* temp for BIOS (386: monitor CS at startup) */
#define DS_286_INDEX 8 /* scratch 16-bit source segment */
#define ES_286_INDEX 9 /* scratch 16-bit destination segment */
#define TSS_INDEX 10 /* kernel TSS */
#define FIRST_LDT_INDEX 11 /* rest of descriptors are LDT's */
/* Descriptor structure offsets. */
#define DESC_BASE 2 /* to base_low */
#define DESC_BASE_MIDDLE 4 /* to base_middle */
#define DESC_ACCESS 5 /* to access byte */
#define DESC_SIZE 8 /* sizeof (struct segdesc_s) */
/*
* WARNING no () around the macros, be careful. This is because of ACK assembler
* and will be fixed after switching to GAS
*/
#define GDT_SELECTOR GDT_INDEX * DESC_SIZE
#define IDT_SELECTOR IDT_INDEX * DESC_SIZE
#define DS_SELECTOR DS_INDEX * DESC_SIZE
#define ES_SELECTOR ES_INDEX * DESC_SIZE
/* flat DS is less privileged ES */
#define FLAT_DS_SELECTOR ES_SELECTOR | TASK_PRIVILEGE
#define SS_SELECTOR SS_INDEX * DESC_SIZE
#define CS_SELECTOR CS_INDEX * DESC_SIZE
#define MON_CS_SELECTOR MON_CS_INDEX * DESC_SIZE
#define TSS_SELECTOR TSS_INDEX * DESC_SIZE
#define DS_286_SELECTOR DS_286_INDEX*DESC_SIZE | TASK_PRIVILEGE
#define ES_286_SELECTOR ES_286_INDEX*DESC_SIZE | TASK_PRIVILEGE
/* Privileges. */
#define INTR_PRIVILEGE 0 /* kernel and interrupt handlers */
#define TASK_PRIVILEGE 1 /* kernel tasks */
#define USER_PRIVILEGE 3 /* servers and user processes */
#define RPL_MASK 0x03 /* bits in selector RPL */
/* 286 hardware constants. */
/* Exception vector numbers. */
#define BOUNDS_VECTOR 5 /* bounds check failed */
#define INVAL_OP_VECTOR 6 /* invalid opcode */
#define COPROC_NOT_VECTOR 7 /* coprocessor not available */
#define DOUBLE_FAULT_VECTOR 8
#define COPROC_SEG_VECTOR 9 /* coprocessor segment overrun */
#define INVAL_TSS_VECTOR 10 /* invalid TSS */
#define SEG_NOT_VECTOR 11 /* segment not present */
#define STACK_FAULT_VECTOR 12 /* stack exception */
#define PROTECTION_VECTOR 13 /* general protection */
/* Selector bits. */
#define TI 0x04 /* table indicator */
#define RPL 0x03 /* requester privilege level */
/* Base and limit sizes and shifts. */
#define BASE_MIDDLE_SHIFT 16 /* shift for base --> base_middle */
/* Access-byte and type-byte bits. */
#define PRESENT 0x80 /* set for descriptor present */
#define DPL 0x60 /* descriptor privilege level mask */
#define DPL_SHIFT 5
#define SEGMENT 0x10 /* set for segment-type descriptors */
/* Access-byte bits. */
#define EXECUTABLE 0x08 /* set for executable segment */
#define CONFORMING 0x04 /* set for conforming segment if executable */
#define EXPAND_DOWN 0x04 /* set for expand-down segment if !executable*/
#define READABLE 0x02 /* set for readable segment if executable */
#define WRITEABLE 0x02 /* set for writeable segment if !executable */
#define TSS_BUSY 0x02 /* set if TSS descriptor is busy */
#define ACCESSED 0x01 /* set if segment accessed */
/* Special descriptor types. */
#define AVL_286_TSS 1 /* available 286 TSS */
#define LDT 2 /* local descriptor table */
#define BUSY_286_TSS 3 /* set transparently to the software */
#define CALL_286_GATE 4 /* not used */
#define TASK_GATE 5 /* only used by debugger */
#define INT_286_GATE 6 /* interrupt gate, used for all vectors */
#define TRAP_286_GATE 7 /* not used */
/* Extra 386 hardware constants. */
/* Exception vector numbers. */
#define PAGE_FAULT_VECTOR 14
#define COPROC_ERR_VECTOR 16 /* coprocessor error */
/* Descriptor structure offsets. */
#define DESC_GRANULARITY 6 /* to granularity byte */
#define DESC_BASE_HIGH 7 /* to base_high */
/* Type-byte bits. */
#define DESC_386_BIT 0x08 /* 386 types are obtained by ORing with this */
/* LDT's and TASK_GATE's don't need it */
/* Base and limit sizes and shifts. */
#define BASE_HIGH_SHIFT 24 /* shift for base --> base_high */
#define BYTE_GRAN_MAX 0xFFFFFL /* maximum size for byte granular segment */
#define GRANULARITY_SHIFT 16 /* shift for limit --> granularity */
#define OFFSET_HIGH_SHIFT 16 /* shift for (gate) offset --> offset_high */
#define PAGE_GRAN_SHIFT 12 /* extra shift for page granular limits */
/* Granularity byte. */
#define GRANULAR 0x80 /* set for 4K granularilty */
#define DEFAULT 0x40 /* set for 32-bit defaults (executable seg) */
#define BIG 0x40 /* set for "BIG" (expand-down seg) */
#define AVL 0x10 /* 0 for available */
#define LIMIT_HIGH 0x0F /* mask for high bits of limit */
/* Program stack words and masks. */
#define INIT_PSW 0x0200 /* initial psw */
#define INIT_TASK_PSW 0x1200 /* initial psw for tasks (with IOPL 1) */
#define TRACEBIT 0x0100 /* OR this with psw in proc[] for tracing */
#define SETPSW(rp, new) /* permits only certain bits to be set */ \
((rp)->p_reg.psw = (rp)->p_reg.psw & ~0xCD5 | (new) & 0xCD5)
#define IF_MASK 0x00000200
#define IOPL_MASK 0x003000
#define vir2phys(vir) (kinfo.data_base + (vir_bytes) (vir))
#define phys2vir(ph) ((vir_bytes) (ph) - kinfo.data_base)
#endif /* _I386_ACONST_H */