MIT_6.S081_xv6.Information 集合

Disassembly of section .text:

0000000080000000 <_entry>:
    80000000:	00009117          	auipc	sp,0x9
    80000004:	86013103          	ld	sp,-1952(sp) # 80008860 <_GLOBAL_OFFSET_TABLE_+0x8>
    80000008:	6505                	lui	a0,0x1
    8000000a:	f14025f3          	csrr	a1,mhartid
    8000000e:	0585                	addi	a1,a1,1
    80000010:	02b50533          	mul	a0,a0,a1
    80000014:	912a                	add	sp,sp,a0
    80000016:	652050ef          	jal	ra,80005668 <start>

	# qemu -kernel loads the kernel at 0x80000000
        # and causes each CPU to jump there.
        # kernel.ld causes the following code to
        # be placed at 0x80000000.
.section .text
.global _entry
_entry:
	# set up a stack for C.
        # stack0 is declared in start.c,
        # with a 4096-byte stack per CPU.
        # sp = stack0 + (hartid * 4096)
        la sp, stack0
        li a0, 1024*4
	csrr a1, mhartid
        addi a1, a1, 1
        mul a0, a0, a1
        add sp, sp, a0
	# jump to start() in start.c
        call start

// entry.S jumps here in machine mode on stack0.
void start()
{
  // set M Previous Privilege mode to Supervisor, for mret.
  unsigned long x = r_mstatus();
  x &= ~MSTATUS_MPP_MASK;
  x |= MSTATUS_MPP_S;
  w_mstatus(x);

  // set M Exception Program Counter to main, for mret.
  // requires gcc -mcmodel=medany
  w_mepc((uint64)main);

  // disable paging for now.
  w_satp(0);

  // delegate all interrupts and exceptions to supervisor mode.
  w_medeleg(0xffff);
  w_mideleg(0xffff);
  w_sie(r_sie() | SIE_SEIE | SIE_STIE | SIE_SSIE);

  // configure Physical Memory Protection to give supervisor mode
  // access to all of physical memory.
  w_pmpaddr0(0x3fffffffffffffull);
  w_pmpcfg0(0xf);

  // ask for clock interrupts.
  timerinit();

  // keep each CPU's hartid in its tp register, for cpuid().
  int id = r_mhartid();
  w_tp(id);

  // switch to supervisor mode and jump to main().
  asm volatile("mret");
}

# Initial process that execs /init.
# This code runs in user space.

#include "syscall.h"

# exec(init, argv)
.globl start
start:
        la a0, init
        la a1, argv
        li a7, SYS_exec
        ecall

struct trapframe {
  /*   0 */ uint64 kernel_satp;   // kernel page table
  /*   8 */ uint64 kernel_sp;     // top of process's kernel stack
  /*  16 */ uint64 kernel_trap;   // usertrap()
  /*  24 */ uint64 epc;           // saved user program counter
  /*  32 */ uint64 kernel_hartid; // saved kernel tp
  /*  40 */ uint64 ra;
  /*  48 */ uint64 sp;
  /*  56 */ uint64 gp;
  /*  64 */ uint64 tp;
  /*  72 */ uint64 t0;
  /*  80 */ uint64 t1;
  /*  88 */ uint64 t2;
  /*  96 */ uint64 s0;
  /* 104 */ uint64 s1;
  /* 112 */ uint64 a0;
  /* 120 */ uint64 a1;
  /* 128 */ uint64 a2;
  /* 136 */ uint64 a3;
  /* 144 */ uint64 a4;
  /* 152 */ uint64 a5;
  /* 160 */ uint64 a6;
  /* 168 */ uint64 a7;
  /* 176 */ uint64 s2;
  /* 184 */ uint64 s3;
  /* 192 */ uint64 s4;
  /* 200 */ uint64 s5;
  /* 208 */ uint64 s6;
  /* 216 */ uint64 s7;
  /* 224 */ uint64 s8;
  /* 232 */ uint64 s9;
  /* 240 */ uint64 s10;
  /* 248 */ uint64 s11;
  /* 256 */ uint64 t3;
  /* 264 */ uint64 t4;
  /* 272 */ uint64 t5;
  /* 280 */ uint64 t6;
};

struct proc {
  struct spinlock lock;

  // p->lock must be held when using these:
  enum procstate state;        // Process state
  void *chan;                  // If non-zero, sleeping on chan
  int killed;                  // If non-zero, have been killed
  int xstate;                  // Exit status to be returned to parent's wait
  int pid;                     // Process ID

  // wait_lock must be held when using this:
  struct proc *parent;         // Parent process

  // these are private to the process, so p->lock need not be held.
  uint64 kstack;               // Virtual address of kernel stack
  uint64 sz;                   // Size of process memory (bytes)
  pagetable_t pagetable;       // User page table
  struct trapframe *trapframe; // data page for trampoline.S
  struct context context;      // swtch() here to run process
  struct file *ofile[NOFILE];  // Open files
  struct inode *cwd;           // Current directory
  char name[16];               // Process name (debugging)
};

uservec:    
	#
        # trap.c sets stvec to point here, so
        # traps from user space start here,
        # in supervisor mode, but with a
        # user page table.
        #
        # sscratch points to where the process's p->trapframe is
        # mapped into user space, at TRAPFRAME.
        #
        
	      # swap a0 and sscratch
        # so that a0 is TRAPFRAME
        csrrw a0, sscratch, a0

        # save the user registers in TRAPFRAME
        sd ra, 40(a0)
        sd sp, 48(a0)
        sd gp, 56(a0)
        sd tp, 64(a0)
        sd t0, 72(a0)
        sd t1, 80(a0)
        sd t2, 88(a0)
        sd s0, 96(a0)
        sd s1, 104(a0)
        sd a1, 120(a0)
        sd a2, 128(a0)
        sd a3, 136(a0)
        sd a4, 144(a0)
        sd a5, 152(a0)
        sd a6, 160(a0)
        sd a7, 168(a0)
        sd s2, 176(a0)
        sd s3, 184(a0)
        sd s4, 192(a0)
        sd s5, 200(a0)
        sd s6, 208(a0)
        sd s7, 216(a0)
        sd s8, 224(a0)
        sd s9, 232(a0)
        sd s10, 240(a0)
        sd s11, 248(a0)
        sd t3, 256(a0)
        sd t4, 264(a0)
        sd t5, 272(a0)
        sd t6, 280(a0)

	# save the user a0 in p->trapframe->a0
        csrr t0, sscratch
        sd t0, 112(a0)

        # restore kernel stack pointer from p->trapframe->kernel_sp
        ld sp, 8(a0)

        # make tp hold the current hartid, from p->trapframe->kernel_hartid
        ld tp, 32(a0)

        # load the address of usertrap(), p->trapframe->kernel_trap
        ld t0, 16(a0)

        # restore kernel page table from p->trapframe->kernel_satp
        ld t1, 0(a0)
        csrw satp, t1
        sfence.vma zero, zero

        # a0 is no longer valid, since the kernel page
        # table does not specially map p->tf.

        # jump to usertrap(), which does not return
        jr t0

void
usertrap(void)
{
  int which_dev = 0;

  if((r_sstatus() & SSTATUS_SPP) != 0)
    panic("usertrap: not from user mode");

  // send interrupts and exceptions to kerneltrap(),
  // since we're now in the kernel.
  w_stvec((uint64)kernelvec);

  struct proc *p = myproc();
  
  // save user program counter.
  p->trapframe->epc = r_sepc();
  
  if(r_scause() == 8){
    // system call

    if(p->killed)
      exit(-1);

    // sepc points to the ecall instruction,
    // but we want to return to the next instruction.
    p->trapframe->epc += 4;

    // an interrupt will change sstatus &c registers,
    // so don't enable until done with those registers.
    intr_on();

    syscall();
  } else if((which_dev = devintr()) != 0){
    // ok
  } else {
    printf("usertrap(): unexpected scause %p pid=%d\n", r_scause(), p->pid);
    printf("            sepc=%p stval=%p\n", r_sepc(), r_stval());
    p->killed = 1;
  }

  if(p->killed)
    exit(-1);

  // give up the CPU if this is a timer interrupt.
  if(which_dev == 2)
    yield();

  usertrapret();
}

void
usertrapret(void)
{
  struct proc *p = myproc();

  // we're about to switch the destination of traps from
  // kerneltrap() to usertrap(), so turn off interrupts until
  // we're back in user space, where usertrap() is correct.
  intr_off();

  // send syscalls, interrupts, and exceptions to trampoline.S
  w_stvec(TRAMPOLINE + (uservec - trampoline));

  // set up trapframe values that uservec will need when
  // the process next re-enters the kernel.
  p->trapframe->kernel_satp = r_satp();         // kernel page table
  p->trapframe->kernel_sp = p->kstack + PGSIZE; // process's kernel stack
  p->trapframe->kernel_trap = (uint64)usertrap;
  p->trapframe->kernel_hartid = r_tp();         // hartid for cpuid()

  // set up the registers that trampoline.S's sret will use
  // to get to user space.
  
  // set S Previous Privilege mode to User.
  unsigned long x = r_sstatus();
  x &= ~SSTATUS_SPP; // clear SPP to 0 for user mode
  x |= SSTATUS_SPIE; // enable interrupts in user mode
  w_sstatus(x);

  // set S Exception Program Counter to the saved user pc.
  w_sepc(p->trapframe->epc);

  // tell trampoline.S the user page table to switch to.
  uint64 satp = MAKE_SATP(p->pagetable);

  // jump to trampoline.S at the top of memory, which 
  // switches to the user page table, restores user registers,
  // and switches to user mode with sret.
  uint64 fn = TRAMPOLINE + (userret - trampoline);
  ((void (*)(uint64,uint64))fn)(TRAPFRAME, satp);
}

userret:
        # userret(TRAPFRAME, pagetable)
        # switch from kernel to user.
        # usertrapret() calls here.
        # a0: TRAPFRAME, in user page table.
        # a1: user page table, for satp.

        # switch to the user page table.
        csrw satp, a1
        sfence.vma zero, zero

        # put the saved user a0 in sscratch, so we
        # can swap it with our a0 (TRAPFRAME) in the last step.
        ld t0, 112(a0)
        csrw sscratch, t0

        # restore all but a0 from TRAPFRAME
        ld ra, 40(a0)
        ld sp, 48(a0)
        ld gp, 56(a0)
        ld tp, 64(a0)
        ld t0, 72(a0)
        ld t1, 80(a0)
        ld t2, 88(a0)
        ld s0, 96(a0)
        ld s1, 104(a0)
        ld a1, 120(a0)
        ld a2, 128(a0)
        ld a3, 136(a0)
        ld a4, 144(a0)
        ld a5, 152(a0)
        ld a6, 160(a0)
        ld a7, 168(a0)
        ld s2, 176(a0)
        ld s3, 184(a0)
        ld s4, 192(a0)
        ld s5, 200(a0)
        ld s6, 208(a0)
        ld s7, 216(a0)
        ld s8, 224(a0)
        ld s9, 232(a0)
        ld s10, 240(a0)
        ld s11, 248(a0)
        ld t3, 256(a0)
        ld t4, 264(a0)
        ld t5, 272(a0)
        ld t6, 280(a0)

	# restore user a0, and save TRAPFRAME in sscratch
        csrrw a0, sscratch, a0
        
        # return to user mode and user pc.
        # usertrapret() set up sstatus and sepc.
        sret

#include "syscall.h"

# exec(init, argv)
.globl start
start:
        la a0, init
        la a1, argv
        li a7, SYS_exec
        ecall

# for(;;) exit();
exit:
        li a7, SYS_exit
        ecall
        jal exit

# char init[] = "/init\0";
init:
  .string "/init\0"

# char *argv[] = { init, 0 };
.p2align 2
argv:
  .long init
  .long 0

static uint64 (*syscalls[])(void) = {
[SYS_fork]    sys_fork,
[SYS_exit]    sys_exit,
[SYS_wait]    sys_wait,
[SYS_pipe]    sys_pipe,
[SYS_read]    sys_read,
[SYS_kill]    sys_kill,
[SYS_exec]    sys_exec,
[SYS_fstat]   sys_fstat,
[SYS_chdir]   sys_chdir,
[SYS_dup]     sys_dup,
[SYS_getpid]  sys_getpid,
[SYS_sbrk]    sys_sbrk,
[SYS_sleep]   sys_sleep,
[SYS_uptime]  sys_uptime,
[SYS_open]    sys_open,
[SYS_write]   sys_write,
[SYS_mknod]   sys_mknod,
[SYS_unlink]  sys_unlink,
[SYS_link]    sys_link,
[SYS_mkdir]   sys_mkdir,
[SYS_close]   sys_close,
};
//系统调用号,系统调用函数
void
syscall(void)
{
  int num;
  struct proc *p = myproc();

  num = p->trapframe->a7;
  if(num > 0 && num < NELEM(syscalls) && syscalls[num]) {
    p->trapframe->a0 = syscalls[num]();
  } else {
    printf("%d %s: unknown sys call %d\n",
            p->pid, p->name, num);
    p->trapframe->a0 = -1;
  }
}

int
copyinstr(pagetable_t pagetable, char *dst, uint64 srcva, uint64 max)
{
  uint64 n, va0, pa0;
  int got_null = 0;

  while(got_null == 0 && max > 0){
    va0 = PGROUNDDOWN(srcva);
    pa0 = walkaddr(pagetable, va0);
    if(pa0 == 0)
      return -1;
    n = PGSIZE - (srcva - va0);
    if(n > max)
      n = max;

    char *p = (char *) (pa0 + (srcva - va0));
    while(n > 0){
      if(*p == '\0'){
        *dst = '\0';
        got_null = 1;
        break;
      } else {
        *dst = *p;
      }
      --n;
      --max;
      p++;
      dst++;
    }

    srcva = va0 + PGSIZE;
  }
  if(got_null){
    return 0;
  } else {
    return -1;
  }
}

kernelvec:
        // make room to save registers.
        addi sp, sp, -256

        // save the registers.
        sd ra, 0(sp)
        sd sp, 8(sp)
        sd gp, 16(sp)
        sd tp, 24(sp)
        sd t0, 32(sp)
        sd t1, 40(sp)
        sd t2, 48(sp)
        sd s0, 56(sp)
        sd s1, 64(sp)
        sd a0, 72(sp)
        sd a1, 80(sp)
        sd a2, 88(sp)
        sd a3, 96(sp)
        sd a4, 104(sp)
        sd a5, 112(sp)
        sd a6, 120(sp)
        sd a7, 128(sp)
        sd s2, 136(sp)
        sd s3, 144(sp)
        sd s4, 152(sp)
        sd s5, 160(sp)
        sd s6, 168(sp)
        sd s7, 176(sp)
        sd s8, 184(sp)
        sd s9, 192(sp)
        sd s10, 200(sp)
        sd s11, 208(sp)
        sd t3, 216(sp)
        sd t4, 224(sp)
        sd t5, 232(sp)
        sd t6, 240(sp)

	// call the C trap handler in trap.c
        call kerneltrap

void 
kerneltrap()
{
  int which_dev = 0;
  uint64 sepc = r_sepc();
  uint64 sstatus = r_sstatus();
  uint64 scause = r_scause();
  
  if((sstatus & SSTATUS_SPP) == 0)
    panic("kerneltrap: not from supervisor mode");
  if(intr_get() != 0)
    panic("kerneltrap: interrupts enabled");

  if((which_dev = devintr()) == 0){
    printf("scause %p\n", scause);
    printf("sepc=%p stval=%p\n", r_sepc(), r_stval());
    panic("kerneltrap");
  }

  // give up the CPU if this is a timer interrupt.
  if(which_dev == 2 && myproc() != 0 && myproc()->state == RUNNING)
    yield();

  // the yield() may have caused some traps to occur,
  // so restore trap registers for use by kernelvec.S's sepc instruction.
  w_sepc(sepc);
  w_sstatus(sstatus);
}

// restore registers.
        ld ra, 0(sp)
        ld sp, 8(sp)
        ld gp, 16(sp)
        // not this, in case we moved CPUs: ld tp, 24(sp)
        ld t0, 32(sp)
        ld t1, 40(sp)
        ld t2, 48(sp)
        ld s0, 56(sp)
        ld s1, 64(sp)
        ld a0, 72(sp)
        ld a1, 80(sp)
        ld a2, 88(sp)
        ld a3, 96(sp)
        ld a4, 104(sp)
        ld a5, 112(sp)
        ld a6, 120(sp)
        ld a7, 128(sp)
        ld s2, 136(sp)
        ld s3, 144(sp)
        ld s4, 152(sp)
        ld s5, 160(sp)
        ld s6, 168(sp)
        ld s7, 176(sp)
        ld s8, 184(sp)
        ld s9, 192(sp)
        ld s10, 200(sp)
        ld s11, 208(sp)
        ld t3, 216(sp)
        ld t4, 224(sp)
        ld t5, 232(sp)
        ld t6, 240(sp)

        addi sp, sp, 256

        // return to whatever we were doing in the kernel.
        sret

pte_t *
walk(pagetable_t pagetable, uint64 va, int alloc)
{
 if(va >= MAXVA)
   panic("walk");
​
 for(int level = 2; level > 0; level--) {
   pte_t *pte = &pagetable[PX(level, va)];
   if(*pte & PTE_V) {
     pagetable = (pagetable_t)PTE2PA(*pte);
  } else {
     if(!alloc || (pagetable = (pde_t*)kalloc()) == 0)
       return 0;
     memset(pagetable, 0, PGSIZE);
     *pte = PA2PTE(pagetable) | PTE_V;
  }
}
 return &pagetable[PX(0, va)];
}

int
mappages(pagetable_t pagetable, uint64 va, uint64 size, uint64 pa, int perm)
{
 uint64 a, last;
 pte_t *pte;
​
 if(size == 0)
   panic("mappages: size");
 
 a = PGROUNDDOWN(va);
 last = PGROUNDDOWN(va + size - 1);
 for(;;){
   if((pte = walk(pagetable, a, 1)) == 0)
     return -1;
   if(*pte & PTE_V)
     panic("mappages: remap");
   *pte = PA2PTE(pa) | perm | PTE_V;
   if(a == last)
     break;
   a += PGSIZE;
   pa += PGSIZE;
}
 return 0;
}

void
kvmmap(pagetable_t kpgtbl, uint64 va, uint64 pa, uint64 sz, int perm)
{
 if(mappages(kpgtbl, va, sz, pa, perm) != 0)
   panic("kvmmap");
}
​
pagetable_t
kvmmake(void)
{
 pagetable_t kpgtbl;
​
 kpgtbl = (pagetable_t) kalloc();
 memset(kpgtbl, 0, PGSIZE);
​
 // uart registers
 kvmmap(kpgtbl, UART0, UART0, PGSIZE, PTE_R | PTE_W);
​
 // virtio mmio disk interface
 kvmmap(kpgtbl, VIRTIO0, VIRTIO0, PGSIZE, PTE_R | PTE_W);
​
 // PLIC
 kvmmap(kpgtbl, PLIC, PLIC, 0x400000, PTE_R | PTE_W);
​
 // map kernel text executable and read-only.
 kvmmap(kpgtbl, KERNBASE, KERNBASE, (uint64)etext-KERNBASE, PTE_R | PTE_X);
​
 // map kernel data and the physical RAM we'll make use of.
 kvmmap(kpgtbl, (uint64)etext, (uint64)etext, PHYSTOP-(uint64)etext, PTE_R | PTE_W);
​
 // map the trampoline for trap entry/exit to
 // the highest virtual address in the kernel.
 kvmmap(kpgtbl, TRAMPOLINE, (uint64)trampoline, PGSIZE, PTE_R | PTE_X);
​
 // map kernel stacks
 proc_mapstacks(kpgtbl);
 
 return kpgtbl;
}

void
kvminithart()
{
 w_satp(MAKE_SATP(kernel_pagetable));
 sfence_vma();
}

void
kinit()
{
 initlock(&kmem.lock, "kmem");
 freerange(end, (void*)PHYSTOP);
}
​
void *
kalloc(void)
{
 struct run *r;
​
 acquire(&kmem.lock);
 r = kmem.freelist;
 if(r)
   kmem.freelist = r->next;
 release(&kmem.lock);
​
 if(r)
   memset((char*)r, 5, PGSIZE); // fill with junk
 return (void*)r;
}

void
kfree(void *pa)
{
 struct run *r;
​
 if(((uint64)pa % PGSIZE) != 0 || (char*)pa < end || (uint64)pa >= PHYSTOP)
   panic("kfree");
​
 // Fill with junk to catch dangling refs.
 memset(pa, 1, PGSIZE);
​
 r = (struct run*)pa;
​
 acquire(&kmem.lock);
 r->next = kmem.freelist;
 kmem.freelist = r;
 release(&kmem.lock);
}

int
growproc(int n)
{
 uint sz;
 struct proc *p = myproc();
​
 sz = p->sz;
 if(n > 0){
   if((sz = uvmalloc(p->pagetable, sz, sz + n)) == 0) {
     return -1;
  }
} else if(n < 0){
   sz = uvmdealloc(p->pagetable, sz, sz + n);
}
 p->sz = sz;
 return 0;
}

#define RHR 0                 // receive holding register (for input bytes)
#define THR 0                 // transmit holding register (for output bytes)
#define IER 1                 // interrupt enable register
#define IER_RX_ENABLE (1<<0)
#define IER_TX_ENABLE (1<<1)
#define FCR 2                 // FIFO control register
#define FCR_FIFO_ENABLE (1<<0)
#define FCR_FIFO_CLEAR (3<<1) // clear the content of the two FIFOs
#define ISR 2                 // interrupt status register
#define LCR 3                 // line control register
#define LCR_EIGHT_BITS (3<<0)
#define LCR_BAUD_LATCH (1<<7) // special mode to set baud rate
#define LSR 5                 // line status register
#define LSR_RX_READY (1<<0)   // input is waiting to be read from RHR
#define LSR_TX_IDLE (1<<5)    // THR can accept another character to send

void
consoleinit(void)
{
  initlock(&cons.lock, "cons");

  uartinit();

  // connect read and write system calls
  // to consoleread and consolewrite.
  devsw[CONSOLE].read = consoleread;
  devsw[CONSOLE].write = consolewrite;
}

WriteReg(IER, IER_TX_ENABLE | IER_RX_ENABLE);

int
devintr()
{
  uint64 scause = r_scause();

  if((scause & 0x8000000000000000L) &&
     (scause & 0xff) == 9){
    // this is a supervisor external interrupt, via PLIC.

    // irq indicates which device interrupted.
    int irq = plic_claim();

    if(irq == UART0_IRQ){
      uartintr();
    } else if(irq == VIRTIO0_IRQ){
      virtio_disk_intr();
    } else if(irq){
      printf("unexpected interrupt irq=%d\n", irq);
    }

    // the PLIC allows each device to raise at most one
    // interrupt at a time; tell the PLIC the device is
    // now allowed to interrupt again.
    if(irq)
      plic_complete(irq);

    return 1;
  } else if(scause == 0x8000000000000001L){
    // software interrupt from a machine-mode timer interrupt,
    // forwarded by timervec in kernelvec.S.

    if(cpuid() == 0){
      clockintr();
    }
    
    // acknowledge the software interrupt by clearing
    // the SSIP bit in sip.
    w_sip(r_sip() & ~2);

    return 2;
  } else {
    return 0;
  }
}
//中断处理分成两个部分,前面部分把存储在UART寄存器的键盘输入发送.
void
uartintr(void)
{
  //keyborad->RHR
  // read and process incoming characters.(处理控制台输入)
  while(1){
    int c = uartgetc();
    if(c == -1)
      break;
    consoleintr(c);
  }

  // send buffered characters.(处理控制台输出)
  acquire(&uart_tx_lock);
  uartstart();
  release(&uart_tx_lock);
}

int
uartgetc(void)
{
  if(ReadReg(LSR) & 0x01){
    // input data is ready.
    return ReadReg(RHR);
  } else {
    return -1;
  }
}

void
uartstart()
{
  while(1){
    if(uart_tx_w == uart_tx_r){
      // transmit buffer is empty.
      return;
    }
    
    if((ReadReg(LSR) & LSR_TX_IDLE) == 0){
      // the UART transmit holding register is full,
      // so we cannot give it another byte.
      // it will interrupt when it's ready for a new byte.
      return;
    }
    
    int c = uart_tx_buf[uart_tx_r % UART_TX_BUF_SIZE];
    uart_tx_r += 1;
    
    // maybe uartputc() is waiting for space in the buffer.
    wakeup(&uart_tx_r);
    
    WriteReg(THR, c);
  }
}

cd abab
process1 :c a
process2 :dabb

.globl swtch
swtch:
        sd ra, 0(a0)
        sd sp, 8(a0)
        sd s0, 16(a0)
        sd s1, 24(a0)
        sd s2, 32(a0)
        sd s3, 40(a0)
        sd s4, 48(a0)
        sd s5, 56(a0)
        sd s6, 64(a0)
        sd s7, 72(a0)
        sd s8, 80(a0)
        sd s9, 88(a0)
        sd s10, 96(a0)
        sd s11, 104(a0)

        ld ra, 0(a1)
        ld sp, 8(a1)
        ld s0, 16(a1)
        ld s1, 24(a1)
        ld s2, 32(a1)
        ld s3, 40(a1)
        ld s4, 48(a1)
        ld s5, 56(a1)
        ld s6, 64(a1)
        ld s7, 72(a1)
        ld s8, 80(a1)
        ld s9, 88(a1)
        ld s10, 96(a1)
        ld s11, 104(a1)
        
        ret
        
swtch(&c->context, &p->context);

// Saved registers for kernel context switches.
struct context {
  uint64 ra;
  uint64 sp;

  // callee-saved
  uint64 s0;
  uint64 s1;
  uint64 s2;
  uint64 s3;
  uint64 s4;
  uint64 s5;
  uint64 s6;
  uint64 s7;
  uint64 s8;
  uint64 s9;
  uint64 s10;
  uint64 s11;
};

void
yield(void)
{
  struct proc *p = myproc();
  acquire(&p->lock);
  p->state = RUNNABLE;
  sched();
  release(&p->lock);
}

void
sched(void)
{
  int intena;
  struct proc *p = myproc();

  if(!holding(&p->lock))
    panic("sched p->lock");
  if(mycpu()->noff != 1)
    panic("sched locks");
  if(p->state == RUNNING)
    panic("sched running");
  if(intr_get())
    panic("sched interruptible");

  intena = mycpu()->intena;
  swtch(&p->context, &mycpu()->context);
  mycpu()->intena = intena;
}

void
scheduler(void)
{
  struct proc *p;
  struct cpu *c = mycpu();
  
  c->proc = 0;
  for(;;){
    // Avoid deadlock by ensuring that devices can interrupt.
    intr_on();

    for(p = proc; p < &proc[NPROC]; p++) {
      acquire(&p->lock);
      if(p->state == RUNNABLE) {
        // Switch to chosen process.  It is the process's job
        // to release its lock and then reacquire it
        // before jumping back to us.
        p->state = RUNNING;
        c->proc = p;
        swtch(&c->context, &p->context);

        // Process is done running for now.
        // It should have changed its p->state before coming back.
        c->proc = 0;
      }
      release(&p->lock);
    }
  }
}

void
forkret(void)
{
  static int first = 1;

  // Still holding p->lock from scheduler.
  release(&myproc()->lock);

  if (first) {
    // File system initialization must be run in the context of a
    // regular process (e.g., because it calls sleep), and thus cannot
    // be run from main().
    first = 0;
    fsinit(ROOTDEV);
  }

  usertrapret();
}

// Per-CPU state.
struct cpu {
  struct proc *proc;          // The process running on this cpu, or null.
  struct context context;     // swtch() here to enter scheduler().
  int noff;                   // Depth of push_off() nesting.
  int intena;                 // Were interrupts enabled before push_off()?
};

struct cpu*
mycpu(void) {
  int id = cpuid();
  struct cpu *c = &cpus[id];
  return c;
}

int
cpuid()
{
  int id = r_tp();
  return id;
}

// Return the current struct proc *, or zero if none.
struct proc*
myproc(void) {
  push_off();
  struct cpu *c = mycpu();
  struct proc *p = c->proc;
  pop_off();
  return p;
}

100 struct semaphore {
101 	struct spinlock lock;
102 	int count;
103 };
104
  
400 void
401 V(struct semaphore *s)
402 {
403 	acquire(&s->lock);
404 	s->count += 1;
405	 	wakeup(s);
406 	release(&s->lock);
407 }
408
409 void
410 P(struct semaphore *s)
411 {
412 	acquire(&s->lock);
413 	while(s->count == 0)
414 		sleep(s, &s->lock);
415 	s->count -= 1;
416 	release(&s->lock);
417 }

// Atomically release lock and sleep on chan.
// Reacquires lock when awakened.
void
sleep(void *chan, struct spinlock *lk)
{
  struct proc *p = myproc();
  
  // Must acquire p->lock in order to
  // change p->state and then call sched.
  // Once we hold p->lock, we can be
  // guaranteed that we won't miss any wakeup
  // (wakeup locks p->lock),
  // so it's okay to release lk.

  acquire(&p->lock);  //DOC: sleeplock1
  release(lk);

  // Go to sleep.
  p->chan = chan;
  p->state = SLEEPING;

  sched();

  // Tidy up.
  p->chan = 0;

  // Reacquire original lock.
  release(&p->lock);
  acquire(lk);
}

// Wake up all processes sleeping on chan.
// Must be called without any p->lock.
void
wakeup(void *chan)
{
  struct proc *p;

  for(p = proc; p < &proc[NPROC]; p++) {
    if(p != myproc()){
      acquire(&p->lock);
      if(p->state == SLEEPING && p->chan == chan) {
        p->state = RUNNABLE;
      }
      release(&p->lock);
    }
  }
}

struct pipe {
  struct spinlock lock;
  char data[PIPESIZE];
  uint nread;     // number of bytes read
  uint nwrite;    // number of bytes written
  int readopen;   // read fd is still open
  int writeopen;  // write fd is still open
};

int
pipewrite(struct pipe *pi, uint64 addr, int n)
{
  int i = 0;
  struct proc *pr = myproc();

  acquire(&pi->lock);
  while(i < n){
    if(pi->readopen == 0 || pr->killed){
      release(&pi->lock);
      return -1;
    }
    if(pi->nwrite == pi->nread + PIPESIZE){ //DOC: pipewrite-full
      wakeup(&pi->nread);
      sleep(&pi->nwrite, &pi->lock);
    } else {
      char ch;
      if(copyin(pr->pagetable, &ch, addr + i, 1) == -1)
        break;
      pi->data[pi->nwrite++ % PIPESIZE] = ch;
      i++;
    }
  }
  wakeup(&pi->nread);
  release(&pi->lock);

  return i;
}

int
piperead(struct pipe *pi, uint64 addr, int n)
{
  int i;
  struct proc *pr = myproc();
  char ch;

  acquire(&pi->lock);
  while(pi->nread == pi->nwrite && pi->writeopen){  //DOC: pipe-empty
    if(pr->killed){
      release(&pi->lock);
      return -1;
    }
    sleep(&pi->nread, &pi->lock); //DOC: piperead-sleep
  }
  for(i = 0; i < n; i++){  //DOC: piperead-copy
    if(pi->nread == pi->nwrite)
      break;
    ch = pi->data[pi->nread++ % PIPESIZE];
    if(copyout(pr->pagetable, addr + i, &ch, 1) == -1)
      break;
  }
  wakeup(&pi->nwrite);  //DOC: piperead-wakeup
  release(&pi->lock);
  return i;
}

int
wait(uint64 addr)
{
  struct proc *np;
  int havekids, pid;
  struct proc *p = myproc();

  acquire(&wait_lock);

  for(;;){
    // Scan through table looking for exited children.
    havekids = 0;
    for(np = proc; np < &proc[NPROC]; np++){
      if(np->parent == p){
        // make sure the child isn't still in exit() or swtch().
        acquire(&np->lock);

        havekids = 1;
        if(np->state == ZOMBIE){
          // Found one.
          pid = np->pid;
          if(addr != 0 && copyout(p->pagetable, addr, (char *)&np->xstate,
                                  sizeof(np->xstate)) < 0) {
            release(&np->lock);
            release(&wait_lock);
            return -1;
          }
          freeproc(np);
          release(&np->lock);
          release(&wait_lock);
          return pid;
        }
        release(&np->lock);
      }
    }

    // No point waiting if we don't have any children.
    if(!havekids || p->killed){
      release(&wait_lock);
      return -1;
    }
    
    // Wait for a child to exit.
    sleep(p, &wait_lock);  //DOC: wait-sleep
  }
}

void
exit(int status)
{
  struct proc *p = myproc();

  if(p == initproc)
    panic("init exiting");

  // Close all open files.
  for(int fd = 0; fd < NOFILE; fd++){
    if(p->ofile[fd]){
      struct file *f = p->ofile[fd];
      fileclose(f);
      p->ofile[fd] = 0;
    }
  }

  begin_op();
  iput(p->cwd);
  end_op();
  p->cwd = 0;

  acquire(&wait_lock);

  // Give any children to init.
  reparent(p);

  // Parent might be sleeping in wait().
  wakeup(p->parent);
  
  acquire(&p->lock);

  p->xstate = status;
  p->state = ZOMBIE;

  release(&wait_lock);

  // Jump into the scheduler, never to return.
  sched();
  panic("zombie exit");
}

int
kill(int pid)
{
  struct proc *p;

  for(p = proc; p < &proc[NPROC]; p++){
    acquire(&p->lock);
    if(p->pid == pid){
      p->killed = 1;
      if(p->state == SLEEPING){
        // Wake process from sleep().
        p->state = RUNNABLE;
      }
      release(&p->lock);
      return 0;
    }
    release(&p->lock);
  }
  return -1;
}

//usertrapret()
if(p->killed)
    exit(-1);

#define BSIZE 1024  // block size
struct buf {
  int valid;   // has data been read from disk?
  int disk;    // does disk "own" buf?
  uint dev;
  uint blockno;
  struct sleeplock lock;
  uint refcnt;
  struct buf *prev; // LRU cache list
  struct buf *next;
  uchar data[BSIZE];
};

struct buf {
  int valid;   // has data been read from disk?
  int disk;    // does disk "own" buf?
  uint dev;
  uint blockno;
  struct sleeplock lock;
  uint refcnt;
  struct buf *prev; // LRU cache list
  struct buf *next;
  uchar data[BSIZE];
};

struct {
  struct spinlock lock;
  struct buf buf[NBUF];

  // Linked list of all buffers, through prev/next.
  // Sorted by how recently the buffer was used.
  // head.next is most recent, head.prev is least.
  struct buf head;
} bcache;

void
binit(void)
{
  struct buf *b;

  initlock(&bcache.lock, "bcache");

  // Create linked list of buffers
  bcache.head.prev = &bcache.head;
  bcache.head.next = &bcache.head;
  for(b = bcache.buf; b < bcache.buf+NBUF; b++){
    b->next = bcache.head.next;
    b->prev = &bcache.head;
    initsleeplock(&b->lock, "buffer");
    bcache.head.next->prev = b;
    bcache.head.next = b;
  }
}

// Look through buffer cache for block on device dev.
// If not found, allocate a buffer.
// In either case, return locked buffer.
static struct buf*
bget(uint dev, uint blockno)
{
  struct buf *b;

  acquire(&bcache.lock);

  // Is the block already cached?
  for(b = bcache.head.next; b != &bcache.head; b = b->next){
    if(b->dev == dev && b->blockno == blockno){
      b->refcnt++;
      release(&bcache.lock);
      acquiresleep(&b->lock);
      return b;
    }
  }

  // Not cached.
  // Recycle the least recently used (LRU) unused buffer.
  for(b = bcache.head.prev; b != &bcache.head; b = b->prev){
    if(b->refcnt == 0) {
      b->dev = dev;
      b->blockno = blockno;
      b->valid = 0;
      b->refcnt = 1;
      release(&bcache.lock);
      acquiresleep(&b->lock);
      return b;
    }
  }
  panic("bget: no buffers");
}

// Return a locked buf with the contents of the indicated block.
struct buf*
bread(uint dev, uint blockno)
{
  struct buf *b;

  b = bget(dev, blockno);
  if(!b->valid) {
    virtio_disk_rw(b, 0);
    b->valid = 1;
  }
  return b;
}

// Write b's contents to disk.  Must be locked.
void
bwrite(struct buf *b)
{
  if(!holdingsleep(&b->lock))
    panic("bwrite");
  virtio_disk_rw(b, 1);
}

// Release a locked buffer.
// Move to the head of the most-recently-used list.
void
brelse(struct buf *b)
{
  if(!holdingsleep(&b->lock))
    panic("brelse");

  releasesleep(&b->lock);

  acquire(&bcache.lock);
  b->refcnt--;
  if (b->refcnt == 0) {
    // no one is waiting for it.
    b->next->prev = b->prev;
    b->prev->next = b->next;
    b->next = bcache.head.next;
    b->prev = &bcache.head;
    bcache.head.next->prev = b;
    bcache.head.next = b;
  }
  
  release(&bcache.lock);
}

void
bpin(struct buf *b) {
  acquire(&bcache.lock);
  b->refcnt++;
  release(&bcache.lock);
}

void
bunpin(struct buf *b) {
  acquire(&bcache.lock);
  b->refcnt--;
  release(&bcache.lock);
}

// Disk layout:
// [ boot block | super block | log | inode blocks |
//                                          free bit map | data blocks]
//
// mkfs computes the super block and builds an initial file system. The
// super block describes the disk layout:
struct superblock {
  uint magic;        // Must be FSMAGIC
  uint size;         // Size of file system image (blocks)
  uint nblocks;      // Number of data blocks
  uint ninodes;      // Number of inodes.
  uint nlog;         // Number of log blocks
  uint logstart;     // Block number of first log block
  uint inodestart;   // Block number of first inode block
  uint bmapstart;    // Block number of first free map block
};

// Contents of the header block, used for both the on-disk header block
// and to keep track in memory of logged block# before commit.
struct logheader {
  int n;
  int block[LOGSIZE];
};

struct log {
  struct spinlock lock;
  int start;
  int size;
  int outstanding; // how many FS sys calls are executing.
  int committing;  // in commit(), please wait.
  int dev;
  struct logheader lh;
};

void
initlog(int dev, struct superblock *sb)
{
  if (sizeof(struct logheader) >= BSIZE)
    panic("initlog: too big logheader");

  initlock(&log.lock, "log");
  log.start = sb->logstart;
  log.size = sb->nlog;
  log.dev = dev;
  recover_from_log();
}

static void
recover_from_log(void)
{
  read_head();
  install_trans(1); // if committed, copy from log to disk
  log.lh.n = 0;
  write_head(); // clear the log
}

// Read the log header from disk into the in-memory log header
static void
read_head(void)
{
  struct buf *buf = bread(log.dev, log.start);
  struct logheader *lh = (struct logheader *) (buf->data);
  int i;
  log.lh.n = lh->n;
  for (i = 0; i < log.lh.n; i++) {
    log.lh.block[i] = lh->block[i];
  }
  brelse(buf);
}

// Copy committed blocks from log to their home location
static void
install_trans(int recovering)
{
  int tail;

  for (tail = 0; tail < log.lh.n; tail++) {
    struct buf *lbuf = bread(log.dev, log.start+tail+1); // read log block
    struct buf *dbuf = bread(log.dev, log.lh.block[tail]); // read dst
    memmove(dbuf->data, lbuf->data, BSIZE);  // copy block to dst
    bwrite(dbuf);  // write dst to disk
    if(recovering == 0)
      bunpin(dbuf);
    brelse(lbuf);
    brelse(dbuf);
  }
}

// called at the start of each FS system call.
void
begin_op(void)
{
  acquire(&log.lock);
  while(1){
    if(log.committing){
      sleep(&log, &log.lock);
    } else if(log.lh.n + (log.outstanding+1)*MAXOPBLOCKS > LOGSIZE){
      // this op might exhaust log space; wait for commit.
      sleep(&log, &log.lock);
    } else {
      log.outstanding += 1;
      release(&log.lock);
      break;
    }
  }
}

// called at the end of each FS system call.
// commits if this was the last outstanding operation.
void
end_op(void)
{
  int do_commit = 0;

  acquire(&log.lock);
  log.outstanding -= 1;
  if(log.committing)
    panic("log.committing");
  if(log.outstanding == 0){
    do_commit = 1;
    log.committing = 1;
  } else {
    // begin_op() may be waiting for log space,
    // and decrementing log.outstanding has decreased
    // the amount of reserved space.
    wakeup(&log);
  }
  release(&log.lock);

  if(do_commit){
    // call commit w/o holding locks, since not allowed
    // to sleep with locks.
    commit();
    acquire(&log.lock);
    log.committing = 0;
    wakeup(&log);
    release(&log.lock);
  }
}

void
log_write(struct buf *b)
{
  int i;

  acquire(&log.lock);
  if (log.lh.n >= LOGSIZE || log.lh.n >= log.size - 1)
    panic("too big a transaction");
  if (log.outstanding < 1)
    panic("log_write outside of trans");

  for (i = 0; i < log.lh.n; i++) {
    if (log.lh.block[i] == b->blockno)   // log absorption
      break;
  }
  log.lh.block[i] = b->blockno;
  if (i == log.lh.n) {  // Add new block to log?
    bpin(b);
    log.lh.n++;
  }
  release(&log.lock);
}

static void
commit()
{
  if (log.lh.n > 0) {
    write_log();     // Write modified blocks from cache to log
    write_head();    // Write header to disk -- the real commit
    install_trans(0); // Now install writes to home locations
    log.lh.n = 0;
    write_head();    // Erase the transaction from the log
  }
}

// Copy modified blocks from cache to log.
static void
write_log(void)
{
  int tail;

  for (tail = 0; tail < log.lh.n; tail++) {
    struct buf *to = bread(log.dev, log.start+tail+1); // log block
    struct buf *from = bread(log.dev, log.lh.block[tail]); // cache block
    memmove(to->data, from->data, BSIZE);
    bwrite(to);  // write the log
    brelse(from);
    brelse(to);
  }
}

// Allocate a zeroed disk block.
static uint
balloc(uint dev)
{
  int b, bi, m;
  struct buf *bp;

  bp = 0;
  for(b = 0; b < sb.size; b += BPB){
    bp = bread(dev, BBLOCK(b, sb));
    for(bi = 0; bi < BPB && b + bi < sb.size; bi++){
      m = 1 << (bi % 8);
      if((bp->data[bi/8] & m) == 0){  // Is block free?
        bp->data[bi/8] |= m;  // Mark block in use.
        log_write(bp);
        brelse(bp);
        bzero(dev, b + bi);
        return b + bi;
      }
    }
    brelse(bp);
  }
  panic("balloc: out of blocks");
}

// Free a disk block.
static void
bfree(int dev, uint b)
{
  struct buf *bp;
  int bi, m;

  bp = bread(dev, BBLOCK(b, sb));
  bi = b % BPB;
  m = 1 << (bi % 8);
  if((bp->data[bi/8] & m) == 0)
    panic("freeing free block");
  bp->data[bi/8] &= ~m;
  log_write(bp);
  brelse(bp);
}

// 下面的宏定义用于type字段，type = 0表示该dinode尚未分配
#define T_DIR     1
#define T_FILE    2
#define T_DEVICE  3
// On-disk inode structure
struct dinode {
  short type;           // File type
  short major;          // Major device number (T_DEVICE only)
  short minor;          // Minor device number (T_DEVICE only)
  short nlink;          // Number of links to inode in file system
  uint size;            // Size of file (bytes)
  uint addrs[NDIRECT+1];   // Data block addresses
};

// in-memory copy of an inode
struct inode {
  uint dev;           // Device number
  uint inum;          // Inode number
  int ref;            // Reference count
  struct sleeplock lock; // protects everything below here
  int valid;          // inode has been read from disk?

  short type;         // copy of disk inode
  short major;
  short minor;
  short nlink;
  uint size;
  uint addrs[NDIRECT+1];
};

struct {
  struct spinlock lock;
  struct inode inode[NINODE];
} itable;
// Find the inode with number inum on device dev
// and return the in-memory copy. Does not lock
// the inode and does not read it from disk.
static struct inode*
iget(uint dev, uint inum)
{
  struct inode *ip, *empty;

  acquire(&itable.lock);

  // Is the inode already in the table?
  empty = 0;
  for(ip = &itable.inode[0]; ip < &itable.inode[NINODE]; ip++){
    if(ip->ref > 0 && ip->dev == dev && ip->inum == inum){
      ip->ref++;
      release(&itable.lock);
      return ip;
    }
    if(empty == 0 && ip->ref == 0)    // Remember empty slot.
      empty = ip;
  }

  // Recycle an inode entry.
  if(empty == 0)
    panic("iget: no inodes");

  ip = empty;
  ip->dev = dev;
  ip->inum = inum;
  ip->ref = 1;
  ip->valid = 0;
  release(&itable.lock);

  return ip;
}

// Inodes per block.
#define IPB           (BSIZE / sizeof(struct dinode))

// Block containing inode i
#define IBLOCK(i, sb)     ((i) / IPB + sb.inodestart)

// Lock the given inode.
// Reads the inode from disk if necessary.
void
ilock(struct inode *ip)
{
  struct buf *bp;
  struct dinode *dip;

  if(ip == 0 || ip->ref < 1)
    panic("ilock");

  acquiresleep(&ip->lock);

  if(ip->valid == 0){
    bp = bread(ip->dev, IBLOCK(ip->inum, sb));
    dip = (struct dinode*)bp->data + ip->inum%IPB;
    ip->type = dip->type;
    ip->major = dip->major;
    ip->minor = dip->minor;
    ip->nlink = dip->nlink;
    ip->size = dip->size;
    memmove(ip->addrs, dip->addrs, sizeof(ip->addrs));
    brelse(bp);
    ip->valid = 1;
    if(ip->type == 0)
      panic("ilock: no type");
  }
}

// Unlock the given inode.
void
iunlock(struct inode *ip)
{
  if(ip == 0 || !holdingsleep(&ip->lock) || ip->ref < 1)
    panic("iunlock");

  releasesleep(&ip->lock);
}

// Increment reference count for ip.
// Returns ip to enable ip = idup(ip1) idiom.
struct inode*
idup(struct inode *ip)
{
  acquire(&itable.lock);
  ip->ref++;
  release(&itable.lock);
  return ip;
}
// Drop a reference to an in-memory inode.
// If that was the last reference, the inode table entry can
// be recycled.
// If that was the last reference and the inode has no links
// to it, free the inode (and its content) on disk.
// All calls to iput() must be inside a transaction in
// case it has to free the inode.
void
iput(struct inode *ip)
{
  acquire(&itable.lock);

  if(ip->ref == 1 && ip->valid && ip->nlink == 0){
    // inode has no links and no other references: truncate and free.

    // ip->ref == 1 means no other process can have ip locked,
    // so this acquiresleep() won't block (or deadlock).
    acquiresleep(&ip->lock);

    release(&itable.lock);

    itrunc(ip);
    ip->type = 0;
    iupdate(ip);
    ip->valid = 0;

    releasesleep(&ip->lock);

    acquire(&itable.lock);
  }

  ip->ref--;
  release(&itable.lock);
}

// Truncate(截断) inode (discard contents).
// Caller must hold ip->lock.
void
itrunc(struct inode *ip)
{
  int i, j;
  struct buf *bp;
  uint *a;
  // 遍历前面NDIRECT个直接块，并进行释放块操作
  for(i = 0; i < NDIRECT; i++){
    if(ip->addrs[i]){
      bfree(ip->dev, ip->addrs[i]);
      ip->addrs[i] = 0;
    }
  }

  if(ip->addrs[NDIRECT]){
    bp = bread(ip->dev, ip->addrs[NDIRECT]);
    a = (uint*)bp->data;
    // 遍历后面NINDIRECT个间接块，进行释放操作
    for(j = 0; j < NINDIRECT; j++){
      if(a[j])
        bfree(ip->dev, a[j]);
    }
    brelse(bp);
    bfree(ip->dev, ip->addrs[NDIRECT]);
    ip->addrs[NDIRECT] = 0;
  }

  ip->size = 0;
  iupdate(ip);
}

static uint
bmap(struct inode *ip, uint bn)
{
  uint addr, *a;
  struct buf *bp;
  // 判断是否为直接块
  if(bn < NDIRECT){
    if((addr = ip->addrs[bn]) == 0)
      ip->addrs[bn] = addr = balloc(ip->dev);
    return addr;
  }
  bn -= NDIRECT;
  // 判断是否是间接块
  if(bn < NINDIRECT){
    // Load indirect block, allocating if necessary.
    if((addr = ip->addrs[NDIRECT]) == 0)
      ip->addrs[NDIRECT] = addr = balloc(ip->dev);
    bp = bread(ip->dev, addr);
    a = (uint*)bp->data;
    if((addr = a[bn]) == 0){
      a[bn] = addr = balloc(ip->dev);
      log_write(bp);
    }
    brelse(bp);
    return addr;
  }

  panic("bmap: out of range");
}

// Write data to inode.
// Caller must hold ip->lock.
// If user_src==1, then src is a user virtual address;
// otherwise, src is a kernel address.
// Returns the number of bytes successfully written.
// If the return value is less than the requested n,
// there was an error of some kind.
int
writei(struct inode *ip, int user_src, uint64 src, uint off, uint n)
{
  uint tot, m;
  struct buf *bp;

  if(off > ip->size || off + n < off)
    return -1;
  if(off + n > MAXFILE*BSIZE)
    return -1;

  for(tot=0; tot<n; tot+=m, off+=m, src+=m){
    bp = bread(ip->dev, bmap(ip, off/BSIZE));
    m = min(n - tot, BSIZE - off%BSIZE);
    if(either_copyin(bp->data + (off % BSIZE), user_src, src, m) == -1) {
      brelse(bp);
      break;
    }
    log_write(bp);
    brelse(bp);
  }

  if(off > ip->size)
    ip->size = off;

  // write the i-node back to disk even if the size didn't change
  // because the loop above might have called bmap() and added a new
  // block to ip->addrs[].
  iupdate(ip);

  return tot;
}

int
readi(struct inode *ip, int user_dst, uint64 dst, uint off, uint n)
{
  uint tot, m;
  struct buf *bp;

  if(off > ip->size || off + n < off)
    return 0;
  if(off + n > ip->size)
    n = ip->size - off;

  for(tot=0; tot<n; tot+=m, off+=m, dst+=m){
    bp = bread(ip->dev, bmap(ip, off/BSIZE));
    m = min(n - tot, BSIZE - off%BSIZE);
    if(either_copyout(user_dst, dst, bp->data + (off % BSIZE), m) == -1) {
      brelse(bp);
      tot = -1;
      break;
    }
    brelse(bp);
  }
  return tot;
}

struct dirent {
  ushort inum;
  char name[DIRSIZ];
};

// Look for a directory entry in a directory.
// If found, set *poff to byte offset of entry.
struct inode*
dirlookup(struct inode *dp, char *name, uint *poff)
{
  uint off, inum;
  struct dirent de;

  if(dp->type != T_DIR)
    panic("dirlookup not DIR");

  for(off = 0; off < dp->size; off += sizeof(de)){
    if(readi(dp, 0, (uint64)&de, off, sizeof(de)) != sizeof(de))
      panic("dirlookup read");
    if(de.inum == 0)
      continue;
    if(namecmp(name, de.name) == 0){
      // entry matches path element
      if(poff)
        *poff = off;
      inum = de.inum;
      return iget(dp->dev, inum);
    }
  }

  return 0;
}

// Look up and return the inode for a path name.
// If parent != 0, return the inode for the parent and copy the final
// path element into name, which must have room for DIRSIZ bytes.
// Must be called inside a transaction since it calls iput().
static struct inode*
namex(char *path, int nameiparent, char *name)
{
  struct inode *ip, *next;

  if(*path == '/')
    ip = iget(ROOTDEV, ROOTINO);
  else
    ip = idup(myproc()->cwd);

  while((path = skipelem(path, name)) != 0){
    ilock(ip);
    if(ip->type != T_DIR){
      iunlockput(ip);
      return 0;
    }
    if(nameiparent && *path == '\0'){
      // Stop one level early.
      iunlock(ip);
      return ip;
    }
    if((next = dirlookup(ip, name, 0)) == 0){
      iunlockput(ip);
      return 0;
    }
    iunlockput(ip);
    ip = next;
  }
  if(nameiparent){
    iput(ip);
    return 0;
  }
  return ip;
}
// Paths

// Copy the next path element from path into name.
// Return a pointer to the element following the copied one.
// The returned path has no leading slashes,
// so the caller can check *path=='\0' to see if the name is the last one.
// If no name to remove, return 0.
//
// Examples:
//   skipelem("a/bb/c", name) = "bb/c", setting name = "a"
//   skipelem("///a//bb", name) = "bb", setting name = "a"
//   skipelem("a", name) = "", setting name = "a"
//   skipelem("", name) = skipelem("////", name) = 0
//
static char*
skipelem(char *path, char *name)
{
  char *s;
  int len;
  // 过滤路径字符串开头所有的'/'
  while(*path == '/')
    path++;
  if(*path == 0)
    return 0;
  s = path;
  while(*path != '/' && *path != 0)
    path++;
  len = path - s;
  if(len >= DIRSIZ)
    memmove(name, s, DIRSIZ);
  else {
    memmove(name, s, len);
    name[len] = 0;
  }
  while(*path == '/')
    path++;
  return path;
}

// Write a new directory entry (name, inum) into the directory dp.
int
dirlink(struct inode *dp, char *name, uint inum)
{
  int off;
  struct dirent de;
  struct inode *ip;

  // Check that name is not present.
  if((ip = dirlookup(dp, name, 0)) != 0){
    iput(ip);
    return -1;
  }

  // Look for an empty dirent.
  for(off = 0; off < dp->size; off += sizeof(de)){
    if(readi(dp, 0, (uint64)&de, off, sizeof(de)) != sizeof(de))
      panic("dirlink read");
    if(de.inum == 0)
      break;
  }

  strncpy(de.name, name, DIRSIZ);
  de.inum = inum;
  if(writei(dp, 0, (uint64)&de, off, sizeof(de)) != sizeof(de))
    panic("dirlink");

  return 0;
}

struct file {
  enum { FD_NONE, FD_PIPE, FD_INODE, FD_DEVICE } type;
  int ref; // reference count
  char readable;
  char writable;
  struct pipe *pipe; // FD_PIPE
  struct inode *ip;  // FD_INODE and FD_DEVICE
  uint off;          // FD_INODE
  short major;       // FD_DEVICE
};

struct {
  struct spinlock lock;
  struct file file[NFILE];
} ftable;

// Allocate a file structure.
struct file*
filealloc(void)
{
  struct file *f;

  acquire(&ftable.lock);
  for(f = ftable.file; f < ftable.file + NFILE; f++){
    if(f->ref == 0){
      f->ref = 1;
      release(&ftable.lock);
      return f;
    }
  }
  release(&ftable.lock);
  return 0;
}

// Increment ref count for file f.
struct file*
filedup(struct file *f)
{
  acquire(&ftable.lock);
  if(f->ref < 1)
    panic("filedup");
  f->ref++;
  release(&ftable.lock);
  return f;
}

// Close file f.  (Decrement ref count, close when reaches 0.)
void
fileclose(struct file *f)
{
  struct file ff;

  acquire(&ftable.lock);
  if(f->ref < 1)
    panic("fileclose");
  if(--f->ref > 0){
    release(&ftable.lock);
    return;
  }
  ff = *f;
  f->ref = 0;
  f->type = FD_NONE;
  release(&ftable.lock);

  if(ff.type == FD_PIPE){
    pipeclose(ff.pipe, ff.writable);
  } else if(ff.type == FD_INODE || ff.type == FD_DEVICE){
    begin_op();
    iput(ff.ip);
    end_op();
  }
}

// Get metadata about file f.
// addr is a user virtual address, pointing to a struct stat.
int
filestat(struct file *f, uint64 addr)
{
  struct proc *p = myproc();
  struct stat st;
  
  if(f->type == FD_INODE || f->type == FD_DEVICE){
    ilock(f->ip);
    stati(f->ip, &st);
    iunlock(f->ip);
    if(copyout(p->pagetable, addr, (char *)&st, sizeof(st)) < 0)
      return -1;
    return 0;
  }
  return -1;
}

// Read from file f.
// addr is a user virtual address.
int
fileread(struct file *f, uint64 addr, int n)
{
  int r = 0;

  if(f->readable == 0)
    return -1;

  if(f->type == FD_PIPE){
    r = piperead(f->pipe, addr, n);
  } else if(f->type == FD_DEVICE){
    if(f->major < 0 || f->major >= NDEV || !devsw[f->major].read)
      return -1;
    r = devsw[f->major].read(1, addr, n);
  } else if(f->type == FD_INODE){
    ilock(f->ip);
    if((r = readi(f->ip, 1, addr, f->off, n)) > 0)
      f->off += r;
    iunlock(f->ip);
  } else {
    panic("fileread");
  }

  return r;
}

// Write to file f.
// addr is a user virtual address.
int
filewrite(struct file *f, uint64 addr, int n)
{
  int r, ret = 0;

  if(f->writable == 0)
    return -1;

  if(f->type == FD_PIPE){
    ret = pipewrite(f->pipe, addr, n);
  } else if(f->type == FD_DEVICE){
    if(f->major < 0 || f->major >= NDEV || !devsw[f->major].write)
      return -1;
    ret = devsw[f->major].write(1, addr, n);
  } else if(f->type == FD_INODE){
    // write a few blocks at a time to avoid exceeding
    // the maximum log transaction size, including
    // i-node, indirect block, allocation blocks,
    // and 2 blocks of slop for non-aligned writes.
    // this really belongs lower down, since writei()
    // might be writing a device like the console.
    int max = ((MAXOPBLOCKS-1-1-2) / 2) * BSIZE;
    int i = 0;
    while(i < n){
      int n1 = n - i;
      if(n1 > max)
        n1 = max;

      begin_op();
      ilock(f->ip);
      if ((r = writei(f->ip, 1, addr + i, f->off, n1)) > 0)
        f->off += r;
      iunlock(f->ip);
      end_op();

      if(r != n1){
        // error from writei
        break;
      }
      i += r;
    }
    ret = (i == n ? n : -1);
  } else {
    panic("filewrite");
  }

  return ret;
}

// Create the path new as a link to the same inode as old.
uint64
sys_link(void)
{
  char name[DIRSIZ], new[MAXPATH], old[MAXPATH];
  struct inode *dp, *ip;

  if(argstr(0, old, MAXPATH) < 0 || argstr(1, new, MAXPATH) < 0)
    return -1;

  begin_op();
  if((ip = namei(old)) == 0){
    end_op();
    return -1;
  }

  ilock(ip);
  if(ip->type == T_DIR){
    iunlockput(ip);
    end_op();
    return -1;
  }

  ip->nlink++;
  iupdate(ip);
  iunlock(ip);

  if((dp = nameiparent(new, name)) == 0)
    goto bad;
  ilock(dp);
  if(dp->dev != ip->dev || dirlink(dp, name, ip->inum) < 0){
    iunlockput(dp);
    goto bad;
  }
  iunlockput(dp);
  iput(ip);

  end_op();

  return 0;

bad:
  ilock(ip);
  ip->nlink--;
  iupdate(ip);
  iunlockput(ip);
  end_op();
  return -1;
}

// map major device number to device functions.
struct devsw {
  int (*read)(int, uint64, int);
  int (*write)(int, uint64, int);
};

struct devsw devsw[NDEV];	// 其中NDEV = 10，xv6最多支持10种不同的驱动
#define CONSOLE 1	// xv6只实现了Console的读写

void
consoleinit(void)
{
  initlock(&cons.lock, "cons");

  uartinit();

  // connect read and write system calls
  // to consoleread and consolewrite.
  devsw[CONSOLE].read = consoleread;
  devsw[CONSOLE].write = consolewrite;
}

  if(open("console", O_RDWR) < 0){
    mknod("console", CONSOLE, 0);
    open("console", O_RDWR);
  }
  dup(0);  // stdout
  dup(0);  // stderr

// 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.
};

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

void
acquire(struct spinlock *lk)
{
  push_off(); // disable interrupts to avoid deadlock.
  if(holding(lk))
    panic("acquire");

  // On RISC-V, sync_lock_test_and_set turns into an atomic swap:
  //   a5 = 1
  //   s1 = &lk->locked
  //   amoswap.w.aq a5, a5, (s1)
  while(__sync_lock_test_and_set(&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 strictly after the lock is acquired.
  // On RISC-V, this emits a fence instruction.
  __sync_synchronize();

  // Record info about lock acquisition for holding() and debugging.
  lk->cpu = mycpu();
}

void
release(struct spinlock *lk)
{
  if(!holding(lk))
    panic("release");

  lk->cpu = 0;

  // Tell the C compiler and the CPU to not move loads or stores
  // past this point, to ensure that all the stores in the critical
  // section are visible to other CPUs before the lock is released,
  // and that loads in the critical section occur strictly before
  // the lock is released.
  // On RISC-V, this emits a fence instruction.
  __sync_synchronize();

  // Release the lock, equivalent to lk->locked = 0.
  // This code doesn't use a C assignment, since the C standard
  // implies that an assignment might be implemented with
  // multiple store instructions.
  // On RISC-V, sync_lock_release turns into an atomic swap:
  //   s1 = &lk->locked
  //   amoswap.w zero, zero, (s1)
  __sync_lock_release(&lk->locked);

  pop_off();
}

获得锁

临界区

释放锁

struct spinlock lock;
int data = 0; // protected by lock
f() {
	acquire(&lock);
	if(data == 0){
		call_once();
		h();
		data = 1;
	}
	release(&lock);
}
g() {
	aquire(&lock);
	if(data == 0){
		call_once();
		data = 1;
	}
	release(&lock);
}

void
clockintr()
{
  acquire(&tickslock);
  ticks++;
  wakeup(&ticks);
  release(&tickslock);
}

uint64
sys_sleep(void)
{
  int n;
  uint ticks0;

  if(argint(0, &n) < 0)
    return -1;
  acquire(&tickslock);
  ticks0 = ticks;
  while(ticks - ticks0 < n){
    if(myproc()->killed){
      release(&tickslock);
      return -1;
    }
    sleep(&ticks, &tickslock);
  }
  release(&tickslock);
  return 0;
}

// push_off/pop_off are like intr_off()/intr_on() except that they are matched:
// it takes two pop_off()s to undo two push_off()s.  Also, if interrupts
// are initially off, then push_off, pop_off leaves them off.

void
push_off(void)
{
  // 获取之前的中断使能状态
  int old = intr_get();
  // 关闭中断使能
  intr_off();
  if(mycpu()->noff == 0)
    mycpu()->intena = old;
  mycpu()->noff += 1;
}

void
pop_off(void)
{
  struct cpu *c = mycpu();
  if(intr_get())
    panic("pop_off - interruptible");
  if(c->noff < 1)
    panic("pop_off");
  c->noff -= 1;
  if(c->noff == 0 && c->intena)
    intr_on();
}

1  l = malloc(sizeof *l);
2  l->data = data;
3  acquire(&listlock);
4  l->next = list;
5  list = l;
6  release(&listlock);

void
acquiresleep(struct sleeplock *lk)
{
  acquire(&lk->lk);
  while (lk->locked) {
    sleep(lk, &lk->lk);
  }
  lk->locked = 1;
  lk->pid = myproc()->pid;
  release(&lk->lk);
}

void
releasesleep(struct sleeplock *lk)
{
  acquire(&lk->lk);
  lk->locked = 0;
  lk->pid = 0;
  wakeup(lk);
  release(&lk->lk);
}