6.828 总结

diagram:
  IRQ or trap, IDT table, vectors, alltraps
  IDT:
    0: divide by zero
    13: general protection
    14: page fault
    32-255: device IRQs
    32: timer
    33: keyboard
    46: IDE
    64: INT

#define SYSCALL(name) \
  .globl name; \
  name: \
    movl $SYS_ ## name, %eax; \
    int $T_SYSCALL; \
    ret

.globl vector64
vector64:
  pushl $0
  pushl $64
  jmp alltraps

void
trap(struct trapframe *tf)
{
  if(tf->trapno == T_SYSCALL){
    if(myproc()->killed)
      exit();
    myproc()->tf = tf;
    syscall();
    if(myproc()->killed)
      exit();
    return;
  }
    ... ...

  CPU -> MMU -> RAM
      VA     PA

  0x00000000:0x80000000 -- user addresses below KERNBASE
  0x80000000:0x80100000 -- map low 1MB devices (for kernel)
  0x80100000:?          -- kernel instructions/data
  ?         :0x8E000000 -- 224 MB of DRAM mapped here
  0xFE000000:0x00000000 -- more memory-mapped devices

  # Set page directory
  movl    $(V2P_WO(entrypgdir)), %eax
  movl    %eax, %cr3

// The boot page table used in entry.S and entryother.S.
// Page directories (and page tables) must start on page boundaries,
// hence the __aligned__ attribute.
// PTE_PS in a page directory entry enables 4Mbyte pages.

__attribute__((__aligned__(PGSIZE)))
pde_t entrypgdir[NPDENTRIES] = {
  // Map VA's [0, 4MB) to PA's [0, 4MB)
  [0] = (0) | PTE_P | PTE_W | PTE_PS,
  // Map VA's [KERNBASE, KERNBASE+4MB) to PA's [0, 4MB)
  [KERNBASE>>PDXSHIFT] = (0) | PTE_P | PTE_W | PTE_PS,
};

  kinit1(end, P2V(4*1024*1024)); // phys page allocator
  kvmalloc();      // kernel page table
  ...
  kinit2(P2V(4*1024*1024), P2V(PHYSTOP)); // must come after startothers()
  userinit();      // first user process

// Initialization happens in two phases.
// 1. main() calls kinit1() while still using entrypgdir to place just
// the pages mapped by entrypgdir on free list.
// 2. main() calls kinit2() with the rest of the physical pages
// after installing a full page table that maps them on all cores.
void
kinit1(void *vstart, void *vend)
{
  initlock(&kmem.lock, "kmem");
  kmem.use_lock = 0;
  freerange(vstart, vend);  // 注意这里的freerange就是把这个范围里的physical memory free掉
}

void
kinit2(void *vstart, void *vend)
{
  freerange(vstart, vend);
  kmem.use_lock = 1;
}

// There is one page table per process, plus one that's used when
// a CPU is not running any process (kpgdir). The kernel uses the
// current process's page table during system calls and interrupts;
// page protection bits prevent user code from using the kernel's
// mappings.
//
// setupkvm() and exec() set up every page table like this:
//
//   0..KERNBASE: user memory (text+data+stack+heap), mapped to
//                phys memory allocated by the kernel
//   KERNBASE..KERNBASE+EXTMEM: mapped to 0..EXTMEM (for I/O space)
//   KERNBASE+EXTMEM..data: mapped to EXTMEM..V2P(data)
//                for the kernel's instructions and r/o data
//   data..KERNBASE+PHYSTOP: mapped to V2P(data)..PHYSTOP,
//                                  rw data + free physical memory
//   0xfe000000..0: mapped direct (devices such as ioapic)
//
// The kernel allocates physical memory for its heap and for user memory
// between V2P(end) and the end of physical memory (PHYSTOP)
// (directly addressable from end..P2V(PHYSTOP)).

// This table defines the kernel's mappings, which are present in
// every process's page table.
static struct kmap {
  void *virt;
  uint phys_start;
  uint phys_end;
  int perm;
} kmap[] = {
 { (void*)KERNBASE, 0,             EXTMEM,    PTE_W}, // I/O space
 { (void*)KERNLINK, V2P(KERNLINK), V2P(data), 0},     // kern text+rodata
 { (void*)data,     V2P(data),     PHYSTOP,   PTE_W}, // kern data+memory
 { (void*)DEVSPACE, DEVSPACE,      0,         PTE_W}, // more devices
};

// Set up kernel part of a page table.
pde_t*
setupkvm(void)
{
  pde_t *pgdir;
  struct kmap *k;

  if((pgdir = (pde_t*)kalloc()) == 0)
    return 0;
  memset(pgdir, 0, PGSIZE);
  if (P2V(PHYSTOP) > (void*)DEVSPACE)
    panic("PHYSTOP too high");
  for(k = kmap; k < &kmap[NELEM(kmap)]; k++)
    if(mappages(pgdir, k->virt, k->phys_end - k->phys_start,
                (uint)k->phys_start, k->perm) < 0) {
      // Free a page table and all the physical memory pages
      // in the user part.
      freevm(pgdir);
      return 0;
    }
  return pgdir;
}

// Allocate one page table for the machine for the kernel address
// space for scheduler processes.
void
kvmalloc(void)
{
  kpgdir = setupkvm();
  switchkvm();
}

// Switch h/w page table register to the kernel-only page table,
// for when no process is running.
void
switchkvm(void)
{
  lcr3(V2P(kpgdir));   // switch to the kernel page table
}

  if((p->pgdir = setupkvm()) == 0)
    panic("userinit: out of memory?");
  inituvm(p->pgdir, _binary_initcode_start, (int)_binary_initcode_size);

  switchuvm(curproc);
  freevm(oldpgdir);

void
switchuvm(struct proc *p)
{
  if(p == 0)
    panic("switchuvm: no process");
  if(p->kstack == 0)
    panic("switchuvm: no kstack");
  if(p->pgdir == 0)
    panic("switchuvm: no pgdir");

  pushcli();
  mycpu()->gdt[SEG_TSS] = SEG16(STS_T32A, &mycpu()->ts,
                                sizeof(mycpu()->ts)-1, 0);
  mycpu()->gdt[SEG_TSS].s = 0;
  mycpu()->ts.ss0 = SEG_KDATA << 3;
  mycpu()->ts.esp0 = (uint)p->kstack + KSTACKSIZE;
  // setting IOPL=0 in eflags *and* iomb beyond the tss segment limit
  // forbids I/O instructions (e.g., inb and outb) from user space
  mycpu()->ts.iomb = (ushort) 0xFFFF;
  ltr(SEG_TSS << 3);
  lcr3(V2P(p->pgdir));  // switch to process's address space
  popcli();
}

  case T_PGFLT:
  {
    // code from allocuvm
    uint newsz = myproc()->sz;
    uint a = PGROUNDDOWN(rcr2());
    if(a < newsz){
      char *mem = kalloc();
      if(mem == 0) {
        cprintf("out of memory\n");
        exit();
        break;
      }
      memset(mem, 0, PGSIZE);
      mappages(myproc()->pgdir, (char*)a, PGSIZE, V2P(mem), PTE_W|PTE_U);
    }
    break;
  }

// Allocate one 4096-byte page of physical memory.
// Returns a pointer that the kernel can use.
// Returns 0 if the memory cannot be allocated.
char*
kalloc(void)
{
  struct run *r;

  if(kmem.use_lock)
    acquire(&kmem.lock);
  r = kmem.freelist;
  if(r)
    kmem.freelist = r->next;  // 所有空内存的链表
  if(kmem.use_lock)
    release(&kmem.lock);
  return (char*)r;
}