proc.h

// Per-CPU state
struct cpu {
  uchar apicid;                // Local APIC ID
  struct context *scheduler;   // swtch() here to enter scheduler
  struct taskstate ts;         // Used by x86 to find stack for interrupt
  struct segdesc gdt[NSEGS];   // x86 global descriptor table
  volatile uint started;       // Has the CPU started?
  int ncli;                    // Depth of pushcli nesting.
  int intena;                  // Were interrupts enabled before pushcli?

  // Cpu-local storage variables; see below
  struct cpu *cpu;
  struct proc *proc;           // The currently-running process.
};

extern struct cpu cpus[NCPU];
extern int ncpu;

// Per-CPU variables, holding pointers to the
// current cpu and to the current process.
// The asm suffix tells gcc to use "%gs:0" to refer to cpu
// and "%gs:4" to refer to proc.  seginit sets up the
// %gs segment register so that %gs refers to the memory
// holding those two variables in the local cpu's struct cpu.
// This is similar to how thread-local variables are implemented
// in thread libraries such as Linux pthreads.
extern struct cpu *cpu asm("%gs:0");       // &cpus[cpunum()]
extern struct proc *proc asm("%gs:4");     // cpus[cpunum()].proc

//PAGEBREAK: 17
// Saved registers for kernel context switches.
// Don't need to save all the segment registers (%cs, etc),
// because they are constant across kernel contexts.
// Don't need to save %eax, %ecx, %edx, because the
// x86 convention is that the caller has saved them.
// Contexts are stored at the bottom of the stack they
// describe; the stack pointer is the address of the context.
// The layout of the context matches the layout of the stack in swtch.S
// at the "Switch stacks" comment. Switch doesn't save eip explicitly,
// but it is on the stack and allocproc() manipulates it.
struct context {
  uint edi;
  uint esi;
  uint ebx;
  uint ebp;
  uint eip;
};

enum procstate { UNUSED, EMBRYO, SLEEPING, RUNNABLE, RUNNING, ZOMBIE };

// Per-process state
struct proc {
  uint sz;                     // Size of process memory (bytes)
  pde_t* pgdir;                // Page table
  char *kstack;                // Bottom of kernel stack for this process
  enum procstate state;        // Process state
  int pid;                     // Process ID
  struct proc *parent;         // Parent process
  struct trapframe *tf;        // Trap frame for current syscall
  struct context *context;     // swtch() here to run process
  void *chan;                  // If non-zero, sleeping on chan
  int killed;                  // If non-zero, have been killed
  struct file *ofile[NOFILE];  // Open files
  struct inode *cwd;           // Current directory
  char name[16];               // Process name (debugging)
};

// Process memory is laid out contiguously, low addresses first:
//   text
//   original data and bss
//   fixed-size stack
//   expandable heap

vm.c

#include "param.h"
#include "types.h"
#include "defs.h"
#include "x86.h"
#include "memlayout.h"
#include "mmu.h"
#include "proc.h"
#include "elf.h"

extern char data[];  // defined by kernel.ld
pde_t *kpgdir;  // for use in scheduler()

// Set up CPU's kernel segment descriptors.
// Run once on entry on each CPU.
void
seginit(void)
{
  struct cpu *c;

  // Map "logical" addresses to virtual addresses using identity map.
  // Cannot share a CODE descriptor for both kernel and user
  // because it would have to have DPL_USR, but the CPU forbids
  // an interrupt from CPL=0 to DPL=3.
  c = &cpus[cpunum()];
  c->gdt[SEG_KCODE] = SEG(STA_X|STA_R, 0, 0xffffffff, 0);
  c->gdt[SEG_KDATA] = SEG(STA_W, 0, 0xffffffff, 0);
  c->gdt[SEG_UCODE] = SEG(STA_X|STA_R, 0, 0xffffffff, DPL_USER);
  c->gdt[SEG_UDATA] = SEG(STA_W, 0, 0xffffffff, DPL_USER);

  // Map cpu and proc -- these are private per cpu.
  c->gdt[SEG_KCPU] = SEG(STA_W, &c->cpu, 8, 0);

  lgdt(c->gdt, sizeof(c->gdt));
  loadgs(SEG_KCPU << 3);

  // Initialize cpu-local storage.
  cpu = c;
  proc = 0;
}

// Return the address of the PTE in page table pgdir
// that corresponds to virtual address va.  If alloc!=0,
// create any required page table pages.
static pte_t *
walkpgdir(pde_t *pgdir, const void *va, int alloc)
{
  pde_t *pde;
  pte_t *pgtab;

  pde = &pgdir[PDX(va)];
  if(*pde & PTE_P){
    pgtab = (pte_t*)P2V(PTE_ADDR(*pde));
  } else {
    if(!alloc || (pgtab = (pte_t*)kalloc()) == 0)
      return 0;
    // Make sure all those PTE_P bits are zero.
    memset(pgtab, 0, PGSIZE);
    // The permissions here are overly generous, but they can
    // be further restricted by the permissions in the page table
    // entries, if necessary.
    *pde = V2P(pgtab) | PTE_P | PTE_W | PTE_U;
  }
  return &pgtab[PTX(va)];
}

// Create PTEs for virtual addresses starting at va that refer to
// physical addresses starting at pa. va and size might not
// be page-aligned.
static int
mappages(pde_t *pgdir, void *va, uint size, uint pa, int perm)
{
  char *a, *last;
  pte_t *pte;

  a = (char*)PGROUNDDOWN((uint)va);
  last = (char*)PGROUNDDOWN(((uint)va) + size - 1);
  for(;;){
    if((pte = walkpgdir(pgdir, a, 1)) == 0)
      return -1;
    if(*pte & PTE_P)
      panic("remap");
    *pte = pa | perm | PTE_P;
    if(a == last)
      break;
    a += PGSIZE;
    pa += PGSIZE;
  }
  return 0;
}

// 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)
      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
}

// Switch TSS and h/w page table to correspond to process p.
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();
  cpu->gdt[SEG_TSS] = SEG16(STS_T32A, &cpu->ts, sizeof(cpu->ts)-1, 0);
  cpu->gdt[SEG_TSS].s = 0;
  cpu->ts.ss0 = SEG_KDATA << 3;
  cpu->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
  cpu->ts.iomb = (ushort) 0xFFFF;
  ltr(SEG_TSS << 3);
  lcr3(V2P(p->pgdir));  // switch to process's address space
  popcli();
}

// Load the initcode into address 0 of pgdir.
// sz must be less than a page.
void
inituvm(pde_t *pgdir, char *init, uint sz)
{
  char *mem;

  if(sz >= PGSIZE)
    panic("inituvm: more than a page");
  mem = kalloc();
  memset(mem, 0, PGSIZE);
  mappages(pgdir, 0, PGSIZE, V2P(mem), PTE_W|PTE_U);
  memmove(mem, init, sz);
}

// Load a program segment into pgdir.  addr must be page-aligned
// and the pages from addr to addr+sz must already be mapped.
int
loaduvm(pde_t *pgdir, char *addr, struct inode *ip, uint offset, uint sz)
{
  uint i, pa, n;
  pte_t *pte;

  if((uint) addr % PGSIZE != 0)
    panic("loaduvm: addr must be page aligned");
  for(i = 0; i < sz; i += PGSIZE){
    if((pte = walkpgdir(pgdir, addr+i, 0)) == 0)
      panic("loaduvm: address should exist");
    pa = PTE_ADDR(*pte);
    if(sz - i < PGSIZE)
      n = sz - i;
    else
      n = PGSIZE;
    if(readi(ip, P2V(pa), offset+i, n) != n)
      return -1;
  }
  return 0;
}

// Allocate page tables and physical memory to grow process from oldsz to
// newsz, which need not be page aligned.  Returns new size or 0 on error.
int
allocuvm(pde_t *pgdir, uint oldsz, uint newsz)
{
  char *mem;
  uint a;

  if(newsz >= KERNBASE)
    return 0;
  if(newsz < oldsz)
    return oldsz;

  a = PGROUNDUP(oldsz);
  for(; a < newsz; a += PGSIZE){
    mem = kalloc();
    if(mem == 0){
      cprintf("allocuvm out of memory\n");
      deallocuvm(pgdir, newsz, oldsz);
      return 0;
    }
    memset(mem, 0, PGSIZE);
    if(mappages(pgdir, (char*)a, PGSIZE, V2P(mem), PTE_W|PTE_U) < 0){
      cprintf("allocuvm out of memory (2)\n");
      deallocuvm(pgdir, newsz, oldsz);
      kfree(mem);
      return 0;
    }
  }
  return newsz;
}

// Deallocate user pages to bring the process size from oldsz to
// newsz.  oldsz and newsz need not be page-aligned, nor does newsz
// need to be less than oldsz.  oldsz can be larger than the actual
// process size.  Returns the new process size.
int
deallocuvm(pde_t *pgdir, uint oldsz, uint newsz)
{
  pte_t *pte;
  uint a, pa;

  if(newsz >= oldsz)
    return oldsz;

  a = PGROUNDUP(newsz);
  for(; a  < oldsz; a += PGSIZE){
    pte = walkpgdir(pgdir, (char*)a, 0);
    if(!pte)
      a = PGADDR(PDX(a) + 1, 0, 0) - PGSIZE;
    else if((*pte & PTE_P) != 0){
      pa = PTE_ADDR(*pte);
      if(pa == 0)
        panic("kfree");
      char *v = P2V(pa);
      kfree(v);
      *pte = 0;
    }
  }
  return newsz;
}

// Free a page table and all the physical memory pages
// in the user part.
void
freevm(pde_t *pgdir)
{
  uint i;

  if(pgdir == 0)
    panic("freevm: no pgdir");
  deallocuvm(pgdir, KERNBASE, 0);
  for(i = 0; i < NPDENTRIES; i++){
    if(pgdir[i] & PTE_P){
      char * v = P2V(PTE_ADDR(pgdir[i]));
      kfree(v);
    }
  }
  kfree((char*)pgdir);
}

// Clear PTE_U on a page. Used to create an inaccessible
// page beneath the user stack.
void
clearpteu(pde_t *pgdir, char *uva)
{
  pte_t *pte;

  pte = walkpgdir(pgdir, uva, 0);
  if(pte == 0)
    panic("clearpteu");
  *pte &= ~PTE_U;
}

// Given a parent process's page table, create a copy
// of it for a child.
pde_t*
copyuvm(pde_t *pgdir, uint sz)
{
  pde_t *d;
  pte_t *pte;
  uint pa, i, flags;
  char *mem;

  if((d = setupkvm()) == 0)
    return 0;
  for(i = 0; i < sz; i += PGSIZE){
    if((pte = walkpgdir(pgdir, (void *) i, 0)) == 0)
      panic("copyuvm: pte should exist");
    if(!(*pte & PTE_P))
      panic("copyuvm: page not present");
    pa = PTE_ADDR(*pte);
    flags = PTE_FLAGS(*pte);
    if((mem = kalloc()) == 0)
      goto bad;
    memmove(mem, (char*)P2V(pa), PGSIZE);
    if(mappages(d, (void*)i, PGSIZE, V2P(mem), flags) < 0)
      goto bad;
  }
  return d;

bad:
  freevm(d);
  return 0;
}

//PAGEBREAK!
// Map user virtual address to kernel address.
char*
uva2ka(pde_t *pgdir, char *uva)
{
  pte_t *pte;

  pte = walkpgdir(pgdir, uva, 0);
  if((*pte & PTE_P) == 0)
    return 0;
  if((*pte & PTE_U) == 0)
    return 0;
  return (char*)P2V(PTE_ADDR(*pte));
}

// Copy len bytes from p to user address va in page table pgdir.
// Most useful when pgdir is not the current page table.
// uva2ka ensures this only works for PTE_U pages.
int
copyout(pde_t *pgdir, uint va, void *p, uint len)
{
  char *buf, *pa0;
  uint n, va0;

  buf = (char*)p;
  while(len > 0){
    va0 = (uint)PGROUNDDOWN(va);
    pa0 = uva2ka(pgdir, (char*)va0);
    if(pa0 == 0)
      return -1;
    n = PGSIZE - (va - va0);
    if(n > len)
      n = len;
    memmove(pa0 + (va - va0), buf, n);
    len -= n;
    buf += n;
    va = va0 + PGSIZE;
  }
  return 0;
}

spinlock.c

// Mutual exclusion spin locks.

#include "types.h"
#include "defs.h"
#include "param.h"
#include "x86.h"
#include "memlayout.h"
#include "mmu.h"
#include "proc.h"
#include "spinlock.h"

void
initlock(struct spinlock *lk, char *name)
{
  lk->name = name;
  lk->locked = 0;
  lk->cpu = 0;
}

// Acquire the lock.
// Loops (spins) until the lock is acquired.
// Holding a lock for a long time may cause
// other CPUs to waste time spinning to acquire it.
void
acquire(struct spinlock *lk)
{
  pushcli(); // disable interrupts to avoid deadlock.
  if(holding(lk))
    panic("acquire");

  // The xchg is atomic.
  while(xchg(&lk->locked, 1) != 0)
    ;

  // Tell the C compiler and the processor to not move loads or stores
  // past this point, to ensure that the critical section's memory
  // references happen after the lock is acquired.
  __sync_synchronize();

  // Record info about lock acquisition for debugging.
  lk->cpu = cpu;
  getcallerpcs(&lk, lk->pcs);
}

// Release the lock.
void
release(struct spinlock *lk)
{
  if(!holding(lk))
    panic("release");

  lk->pcs[0] = 0;
  lk->cpu = 0;

  // Tell the C compiler and the processor to not move loads or stores
  // past this point, to ensure that all the stores in the critical
  // section are visible to other cores before the lock is released.
  // Both the C compiler and the hardware may re-order loads and
  // stores; __sync_synchronize() tells them both not to.
  __sync_synchronize();

  // Release the lock, equivalent to lk->locked = 0.
  // This code can't use a C assignment, since it might
  // not be atomic. A real OS would use C atomics here.
  asm volatile("movl $0, %0" : "+m" (lk->locked) : );

  popcli();
}

// Record the current call stack in pcs[] by following the %ebp chain.
void
getcallerpcs(void *v, uint pcs[])
{
  uint *ebp;
  int i;

  ebp = (uint*)v - 2;
  for(i = 0; i < 10; i++){
    if(ebp == 0 || ebp < (uint*)KERNBASE || ebp == (uint*)0xffffffff)
      break;
    pcs[i] = ebp[1];     // saved %eip
    ebp = (uint*)ebp[0]; // saved %ebp
  }
  for(; i < 10; i++)
    pcs[i] = 0;
}

// Check whether this cpu is holding the lock.
int
holding(struct spinlock *lock)
{
  return lock->locked && lock->cpu == cpu;
}


// Pushcli/popcli are like cli/sti except that they are matched:
// it takes two popcli to undo two pushcli.  Also, if interrupts
// are off, then pushcli, popcli leaves them off.

void
pushcli(void)
{
  int eflags;

  eflags = readeflags();
  cli();
  if(cpu->ncli == 0)
    cpu->intena = eflags & FL_IF;
  cpu->ncli += 1;
}

void
popcli(void)
{
  if(readeflags()&FL_IF)
    panic("popcli - interruptible");
  if(--cpu->ncli < 0)
    panic("popcli");
  if(cpu->ncli == 0 && cpu->intena)
    sti();
}

spinlock.h

// Mutual exclusion lock.
struct spinlock {
  uint locked;       // Is the lock held?

  // For debugging:
  char *name;        // Name of lock.
  struct cpu *cpu;   // The cpu holding the lock.
  uint pcs[10];      // The call stack (an array of program counters)
                     // that locked the lock.
};

main.c

#include "types.h"
#include "defs.h"
#include "param.h"
#include "memlayout.h"
#include "mmu.h"
#include "proc.h"
#include "x86.h"

static void startothers(void);
static void mpmain(void)  __attribute__((noreturn));
extern pde_t *kpgdir;
extern char end[]; // first address after kernel loaded from ELF file

// Bootstrap processor starts running C code here.
// Allocate a real stack and switch to it, first
// doing some setup required for memory allocator to work.
int
main(void)
{
  kinit1(end, P2V(4*1024*1024)); // phys page allocator
  kvmalloc();      // kernel page table
  mpinit();        // detect other processors
  lapicinit();     // interrupt controller
  seginit();       // segment descriptors
  cprintf("\ncpu%d: starting xv6\n\n", cpunum());
  picinit();       // another interrupt controller
  ioapicinit();    // another interrupt controller
  consoleinit();   // console hardware
  uartinit();      // serial port
  pinit();         // process table
  tvinit();        // trap vectors
  binit();         // buffer cache
  fileinit();      // file table
  ideinit();       // disk
  if(!ismp)
    timerinit();   // uniprocessor timer
  startothers();   // start other processors
  kinit2(P2V(4*1024*1024), P2V(PHYSTOP)); // must come after startothers()
  userinit();      // first user process
  mpmain();        // finish this processor's setup
}

// Other CPUs jump here from entryother.S.
static void
mpenter(void)
{
  switchkvm();
  seginit();
  lapicinit();
  mpmain();
}

// Common CPU setup code.
static void
mpmain(void)
{
  cprintf("cpu%d: starting\n", cpunum());
  idtinit();       // load idt register
  xchg(&cpu->started, 1); // tell startothers() we're up
  scheduler();     // start running processes
}

pde_t entrypgdir[];  // For entry.S

// Start the non-boot (AP) processors.
static void
startothers(void)
{
  extern uchar _binary_entryother_start[], _binary_entryother_size[];
  uchar *code;
  struct cpu *c;
  char *stack;

  // Write entry code to unused memory at 0x7000.
  // The linker has placed the image of entryother.S in
  // _binary_entryother_start.
  code = P2V(0x7000);
  memmove(code, _binary_entryother_start, (uint)_binary_entryother_size);

  for(c = cpus; c < cpus+ncpu; c++){
    if(c == cpus+cpunum())  // We've started already.
      continue;

    // Tell entryother.S what stack to use, where to enter, and what
    // pgdir to use. We cannot use kpgdir yet, because the AP processor
    // is running in low  memory, so we use entrypgdir for the APs too.
    stack = kalloc();
    *(void**)(code-4) = stack + KSTACKSIZE;
    *(void**)(code-8) = mpenter;
    *(int**)(code-12) = (void *) V2P(entrypgdir);

    lapicstartap(c->apicid, V2P(code));

    // wait for cpu to finish mpmain()
    while(c->started == 0)
      ;
  }
}

// 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,
};

entryother.S

#include "asm.h"
#include "memlayout.h"
#include "mmu.h"
	
# Each non-boot CPU ("AP") is started up in response to a STARTUP
# IPI from the boot CPU.  Section B.4.2 of the Multi-Processor
# Specification says that the AP will start in real mode with CS:IP
# set to XY00:0000, where XY is an 8-bit value sent with the
# STARTUP. Thus this code must start at a 4096-byte boundary.
#
# Because this code sets DS to zero, it must sit
# at an address in the low 2^16 bytes.
#
# Startothers (in main.c) sends the STARTUPs one at a time.
# It copies this code (start) at 0x7000.  It puts the address of
# a newly allocated per-core stack in start-4,the address of the
# place to jump to (mpenter) in start-8, and the physical address
# of entrypgdir in start-12.
#
# This code combines elements of bootasm.S and entry.S.

.code16           
.globl start
start:
  cli            

  # Zero data segment registers DS, ES, and SS.
  xorw    %ax,%ax
  movw    %ax,%ds
  movw    %ax,%es
  movw    %ax,%ss

  # Switch from real to protected mode.  Use a bootstrap GDT that makes
  # virtual addresses map directly to physical addresses so that the
  # effective memory map doesn't change during the transition.
  lgdt    gdtdesc
  movl    %cr0, %eax
  orl     $CR0_PE, %eax
  movl    %eax, %cr0

  # Complete the transition to 32-bit protected mode by using a long jmp
  # to reload %cs and %eip.  The segment descriptors are set up with no
  # translation, so that the mapping is still the identity mapping.
  ljmpl    $(SEG_KCODE<<3), $(start32)

//PAGEBREAK!
.code32  # Tell assembler to generate 32-bit code now.
start32:
  # Set up the protected-mode data segment registers
  movw    $(SEG_KDATA<<3), %ax    # Our data segment selector
  movw    %ax, %ds                # -> DS: Data Segment
  movw    %ax, %es                # -> ES: Extra Segment
  movw    %ax, %ss                # -> SS: Stack Segment
  movw    $0, %ax                 # Zero segments not ready for use
  movw    %ax, %fs                # -> FS
  movw    %ax, %gs                # -> GS

  # Turn on page size extension for 4Mbyte pages
  movl    %cr4, %eax
  orl     $(CR4_PSE), %eax
  movl    %eax, %cr4
  # Use entrypgdir as our initial page table
  movl    (start-12), %eax
  movl    %eax, %cr3
  # Turn on paging.
  movl    %cr0, %eax
  orl     $(CR0_PE|CR0_PG|CR0_WP), %eax
  movl    %eax, %cr0

  # Switch to the stack allocated by startothers()
  movl    (start-4), %esp
  # Call mpenter()
  call	 *(start-8)

  movw    $0x8a00, %ax
  movw    %ax, %dx
  outw    %ax, %dx
  movw    $0x8ae0, %ax
  outw    %ax, %dx
spin:
  jmp     spin

.p2align 2
gdt:
  SEG_NULLASM
  SEG_ASM(STA_X|STA_R, 0, 0xffffffff)
  SEG_ASM(STA_W, 0, 0xffffffff)


gdtdesc:
  .word   (gdtdesc - gdt - 1)
  .long   gdt

entry.S

# The xv6 kernel starts executing in this file. This file is linked with
# the kernel C code, so it can refer to kernel symbols such as main().
# The boot block (bootasm.S and bootmain.c) jumps to entry below.
        
# Multiboot header, for multiboot boot loaders like GNU Grub.
# http://www.gnu.org/software/grub/manual/multiboot/multiboot.html
#
# Using GRUB 2, you can boot xv6 from a file stored in a
# Linux file system by copying kernel or kernelmemfs to /boot
# and then adding this menu entry:
#
# menuentry "xv6" {
# 	insmod ext2
# 	set root='(hd0,msdos1)'
# 	set kernel='/boot/kernel'
# 	echo "Loading ${kernel}..."
# 	multiboot ${kernel} ${kernel}
# 	boot
# }

#include "asm.h"
#include "memlayout.h"
#include "mmu.h"
#include "param.h"

# Multiboot header.  Data to direct multiboot loader.
.p2align 2
.text
.globl multiboot_header
multiboot_header:
  #define magic 0x1badb002
  #define flags 0
  .long magic
  .long flags
  .long (-magic-flags)

# By convention, the _start symbol specifies the ELF entry point.
# Since we haven't set up virtual memory yet, our entry point is
# the physical address of 'entry'.
.globl _start
_start = V2P_WO(entry)

# Entering xv6 on boot processor, with paging off.
.globl entry
entry:
  # Turn on page size extension for 4Mbyte pages
  movl    %cr4, %eax
  orl     $(CR4_PSE), %eax
  movl    %eax, %cr4
  # Set page directory
  movl    $(V2P_WO(entrypgdir)), %eax
  movl    %eax, %cr3
  # Turn on paging.
  movl    %cr0, %eax
  orl     $(CR0_PG|CR0_WP), %eax
  movl    %eax, %cr0

  # Set up the stack pointer.
  movl $(stack + KSTACKSIZE), %esp

  # Jump to main(), and switch to executing at
  # high addresses. The indirect call is needed because
  # the assembler produces a PC-relative instruction
  # for a direct jump.
  mov $main, %eax
  jmp *%eax

.comm stack, KSTACKSIZE