xv6 page table相关代码解析

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13
14
15
16
17
18
19
20
21

// start() jumps here in supervisor mode on all CPUs.
void
main()
{
  if(cpuid() == 0){
    consoleinit();
#if defined(LAB_PGTBL) || defined(LAB_LOCK)
    statsinit();
#endif
    printfinit();
    printf("\n");
    printf("xv6 kernel is booting\n");
    printf("\n");
    kinit();         // physical page allocator
    ...
  } else {
    ...
  }

  scheduler();        
}

1
2
3
4
5
6
7
8
9

extern char end[]; // first address after kernel.
                   // defined by kernel.ld.

void
kinit()
{
  initlock(&kmem.lock, "kmem");
  freerange(end, (void*)PHYSTOP);
}

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11

// define in riscv.h
#define PGROUNDUP(sz)  (((sz)+PGSIZE-1) & ~(PGSIZE-1))

void
freerange(void *pa_start, void *pa_end)
{
  char *p;
  p = (char*)PGROUNDUP((uint64)pa_start);
  for(; p + PGSIZE <= (char*)pa_end; p += PGSIZE)
    kfree(p);
}

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31

struct run {
  struct run *next;
};

struct {
  struct spinlock lock;
  struct run *freelist;
} kmem;

// Free the page of physical memory pointed at by v,
// which normally should have been returned by a
// call to kalloc().  (The exception is when
// initializing the allocator; see kinit above.)
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);
}

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13
14
15
16
17
18

// Allocate one 4096-byte page of physical memory.
// Returns a pointer that the kernel can use.
// Returns 0 if the memory cannot be allocated.
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;
}

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27

#define PGSIZE 4096 // bytes per page
#define PGSHIFT 12  // bits of offset within a page

#define PGROUNDUP(sz)  (((sz)+PGSIZE-1) & ~(PGSIZE-1))
#define PGROUNDDOWN(a) (((a)) & ~(PGSIZE-1))

// shift a physical address to the right place for a PTE.
#define PA2PTE(pa) ((((uint64)pa) >> 12) << 10)

#define PTE2PA(pte) (((pte) >> 10) << 12)

// extract the three 9-bit page table indices from a virtual address.
#define PXMASK          0x1FF // 9 bits
#define PXSHIFT(level)  (PGSHIFT+(9*(level)))
#define PX(level, va) ((((uint64) (va)) >> PXSHIFT(level)) & PXMASK)

// one beyond the highest possible virtual address.
// MAXVA is actually one bit less than the max allowed by
// Sv39, to avoid having to sign-extend virtual addresses
// that have the high bit set.
#define MAXVA (1L << (9 + 9 + 9 + 12 - 1))

#define PTE_V (1L << 0) // valid
#define PTE_R (1L << 1)
#define PTE_W (1L << 2)
#define PTE_X (1L << 3)
#define PTE_U (1L << 4) // 1 -> user can access

1
2

typedef uint64 pte_t;
typedef uint64 *pagetable_t; // 512 PTEs

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13
14
15
16
17
18

pte_t * walk(pagetable_t pagetable, uint64 va, int alloc)
{
  if(va >= MAXVA)  // va 超范围 panic
    panic("walk");

  for(int level = 2; level > 0; level--) { // 从最高一级页表开始逐层找pte
    pte_t *pte = &pagetable[PX(level, va)]; // 找到该层对应的pte
    if(*pte & PTE_V) {                      // 该pte有效则找到了，往下走一层
      pagetable = (pagetable_t)PTE2PA(*pte);
    } else {                              
      if(!alloc || (pagetable = (pde_t*)kalloc()) == 0) // 如果alloc != 0则会分配一张页表
        return 0;                                       // alloc == 0 或者 分配空闲页失败 返回0
      memset(pagetable, 0, PGSIZE);                     // 分配的页做空页表，pte全设为0
      *pte = PA2PTE(pagetable) | PTE_V;                 // 接着往下走
    }
  }
  return &pagetable[PX(0, va)];                  // 返回pte对应的地址
}

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25

// Create PTEs for virtual addresses starting at va that refer to
// physical addresses starting at pa. va and size might not
// be page-aligned. Returns 0 on success, -1 if walk() couldn't
// allocate a needed page-table page.
int
mappages(pagetable_t pagetable, uint64 va, uint64 size, uint64 pa, int perm)
{
  uint64 a, last;
  pte_t *pte;

  a = PGROUNDDOWN(va);  // 开始要做映射的虚拟页
  last = PGROUNDDOWN(va + size - 1);  // 最后一页要做映射的虚拟页
  for(;;){
    if((pte = walk(pagetable, a, 1)) == 0) // 此处walk的alloc 为1 需要分配本来没有的页表
      return -1; // 分配失败
    if(*pte & PTE_V) // 这个va已经映射过了，重新映射也许是无意为之，panic以提前发现错误
      panic("remap");
    *pte = PA2PTE(pa) | perm | PTE_V;  // 设置ppn和flag，即映射到的物理地址和访问权限
    if(a == last)   // 分配完毕
      break;
    a += PGSIZE;   // 下一页
    pa += PGSIZE;  // 下一页
  }
  return 0;
}

1
2
3
4
5
6
7
8
9

// add a mapping to the kernel page table.
// only used when booting.
// does not flush TLB or enable paging.
void
kvmmap(uint64 va, uint64 pa, uint64 sz, int perm)
{
  if(mappages(kernel_pagetable, va, sz, pa, perm) != 0)
    panic("kvmmap");
}

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26

// start() jumps here in supervisor mode on all CPUs.
void
main()
{
  if(cpuid() == 0){
    consoleinit();
#if defined(LAB_PGTBL) || defined(LAB_LOCK)
    statsinit();
#endif
    printfinit();
    printf("\n");
    printf("xv6 kernel is booting\n");
    printf("\n");
    kinit();         // physical page allocator
    kvminit();       // create kernel page table
    kvminithart();   // turn on paging
    procinit();      // process table
    ...  
    userinit();      // first user process
   ...
  } else {
    ...
  }

  scheduler();        
}

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36

// 辅助函数，定义在string.c 顾名思义，设置内存的
void* memset(void *dst, int c, uint n)
{
  char *cdst = (char *) dst;
  int i;
  for(i = 0; i < n; i++){
    cdst[i] = c;
  }
  return dst;
}

/*
 * the kernel's page table.
 */
pagetable_t kernel_pagetable;

void kvminit()
{
  kernel_pagetable = (pagetable_t) kalloc();  // 根页表首先需要分配一页空间
  memset(kernel_pagetable, 0, PGSIZE);        // 全部pte设为0
  // uart registers
  kvmmap(UART0, UART0, PGSIZE, PTE_R | PTE_W);
  // virtio mmio disk interface
  kvmmap(VIRTIO0, VIRTIO0, PGSIZE, PTE_R | PTE_W);
  // CLINT
  kvmmap(CLINT, CLINT, 0x10000, PTE_R | PTE_W);
  // PLIC
  kvmmap(PLIC, PLIC, 0x400000, PTE_R | PTE_W);
  // map kernel text executable and read-only.
  kvmmap(KERNBASE, KERNBASE, (uint64)etext-KERNBASE, PTE_R | PTE_X);
  // map kernel data and the physical RAM we'll make use of.
  kvmmap((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(TRAMPOLINE, (uint64)trampoline, PGSIZE, PTE_R | PTE_X);
}

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28

// use riscv's sv39 page table scheme.
#define SATP_SV39 (8L << 60)
#define MAKE_SATP(pagetable) (SATP_SV39 | (((uint64)pagetable) >> 12))

// supervisor address translation and protection;
// holds the address of the page table.
static inline void 
w_satp(uint64 x)
{
  asm volatile("csrw satp, %0" : : "r" (x));
}

// flush the TLB.
static inline void
sfence_vma()
{
  // the zero, zero means flush all TLB entries.
  asm volatile("sfence.vma zero, zero");
}

// Switch h/w page table register to the kernel's page table,
// and enable paging.
void
kvminithart()
{
  w_satp(MAKE_SATP(kernel_pagetable));
  sfence_vma();
}

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46

// Per-process state
struct proc {
  struct spinlock lock;

  // p->lock must be held when using these:
  enum procstate state;        // Process state
  struct proc *parent;         // Parent process
  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

  // 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)
};

struct proc proc[NPROC];

// initialize the proc table at boot time.
void
procinit(void)
{
  struct proc *p;
  
  initlock(&pid_lock, "nextpid");
  for(p = proc; p < &proc[NPROC]; p++) {
      initlock(&p->lock, "proc");
      // Allocate a page for the process's kernel stack.
      // Map it high in memory, followed by an invalid
      // guard page.
      char *pa = kalloc();
      if(pa == 0)
        panic("kalloc");
      uint64 va = KSTACK((int) (p - proc));
      kvmmap(va, (uint64)pa, PGSIZE, PTE_R | PTE_W);
      p->kstack = va;
  }
  kvminithart();
}

1
2
3

// map kernel stacks beneath the trampoline,
// each surrounded by invalid guard pages.
#define KSTACK(p) (TRAMPOLINE - ((p)+1)* 2*PGSIZE)

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28

# 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

# 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

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13
14
15

// start() jumps here in supervisor mode on all CPUs.
void
main()
{
  if(cpuid() == 0){
    ...   
    userinit();      // first user process
    __sync_synchronize();
    started = 1;
  } else {
    ...
  }

  scheduler();        
}

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25

// Set up first user process.
void
userinit(void)
{
  struct proc *p;

  p = allocproc();  // set trampoline and trapframe
  initproc = p;
  
  // allocate one user page and copy init's instructions
  // and data into it.
  uvminit(p->pagetable, initcode, sizeof(initcode));  // allocate one page and copy data in it
  p->sz = PGSIZE;

  // prepare for the very first "return" from kernel to user.
  p->trapframe->epc = 0;      // user program counter
  p->trapframe->sp = PGSIZE;  // user stack pointer

  safestrcpy(p->name, "initcode", sizeof(p->name));
  p->cwd = namei("/");

  p->state = RUNNABLE;

  release(&p->lock);
}

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45

// Look in the process table for an UNUSED proc.
// If found, initialize state required to run in the kernel,
// and return with p->lock held.
// If there are no free procs, or a memory allocation fails, return 0.
static struct proc*
allocproc(void)
{
  struct proc *p;

  // 从proc中找一个UNUSED的空位
  for(p = proc; p < &proc[NPROC]; p++) {
    acquire(&p->lock);
    if(p->state == UNUSED) {
      goto found;
    } else {
      release(&p->lock);
    }
  }
  return 0;

found:  // 找到UNUSED的可供使用
  p->pid = allocpid();  // 分配一个pid ,也就是当前没有用的最小的整数

  // Allocate a trapframe page.
  if((p->trapframe = (struct trapframe *)kalloc()) == 0){
    release(&p->lock);
    return 0;
  }

  // An empty user page table.
  p->pagetable = proc_pagetable(p); // proc_pagetable映射了虚拟内存的trapframe 和trampoline
  if(p->pagetable == 0){
    freeproc(p);
    release(&p->lock);
    return 0;
  }

  // Set up new context to start executing at forkret,
  // which returns to user space.
  memset(&p->context, 0, sizeof(p->context));
  p->context.ra = (uint64)forkret;  // ra是return address
  p->context.sp = p->kstack + PGSIZE; // sp是stack pointer

  return p;
}

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12

void
uvminit(pagetable_t pagetable, uchar *src, uint sz)
{
  char *mem;

  if(sz >= PGSIZE)
    panic("inituvm: more than a page");
  mem = kalloc();
  memset(mem, 0, PGSIZE);
  mappages(pagetable, 0, PGSIZE, (uint64)mem, PTE_W|PTE_R|PTE_X|PTE_U);
  memmove(mem, src, sz);
}

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11

// a user program that calls exec("/init")
// od -t xC initcode
uchar initcode[] = {
  0x17, 0x05, 0x00, 0x00, 0x13, 0x05, 0x45, 0x02,
  0x97, 0x05, 0x00, 0x00, 0x93, 0x85, 0x35, 0x02,
  0x93, 0x08, 0x70, 0x00, 0x73, 0x00, 0x00, 0x00,
  0x93, 0x08, 0x20, 0x00, 0x73, 0x00, 0x00, 0x00,
  0xef, 0xf0, 0x9f, 0xff, 0x2f, 0x69, 0x6e, 0x69,
  0x74, 0x00, 0x00, 0x24, 0x00, 0x00, 0x00, 0x00,
  0x00, 0x00, 0x00, 0x00
};

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47

// Per-CPU process scheduler.
// Each CPU calls scheduler() after setting itself up.
// Scheduler never returns.  It loops, doing:
//  - choose a process to run.
//  - swtch to start running that process.
//  - eventually that process transfers control
//    via swtch back to the scheduler.
void
scheduler(void)
{
  struct proc *p;
  struct cpu *c = mycpu();
  
  c->proc = 0;
  for(;;){
    // Avoid deadlock by ensuring that devices can interrupt.
    intr_on();
    
    int found = 0;
    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;

        found = 1;
      }
      release(&p->lock);
    }
#if !defined (LAB_FS)
    if(found == 0) {
      intr_on();
      asm volatile("wfi");
    }
#else
    ;
#endif
  }
}

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33

.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

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13
14
15
16
17
18
19

// 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;
};

1
2
3
4
5

// Set up new context to start executing at forkret,
// which returns to user space.
memset(&p->context, 0, sizeof(p->context));
p->context.ra = (uint64)forkret;  // ra是return address
p->context.sp = p->kstack + PGSIZE; // sp是stack pointer

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13
14
15
16
17
18
19
20

// A fork child's very first scheduling by scheduler()
// will swtch to forkret.
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();
}

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46

// Create a new process, copying the parent.
// Sets up child kernel stack to return as if from fork() system call.
int
fork(void)
{
  int i, pid;
  struct proc *np;
  struct proc *p = myproc();

  // Allocate process.
  if((np = allocproc()) == 0){
    return -1;
  }

  // Copy user memory from parent to child.
  if(uvmcopy(p->pagetable, np->pagetable, p->sz) < 0){
    freeproc(np);
    release(&np->lock);
    return -1;
  }
  np->sz = p->sz;

  np->parent = p;

  // copy saved user registers.
  *(np->trapframe) = *(p->trapframe);

  // Cause fork to return 0 in the child.
  np->trapframe->a0 = 0;

  // increment reference counts on open file descriptors.
  for(i = 0; i < NOFILE; i++)
    if(p->ofile[i])
      np->ofile[i] = filedup(p->ofile[i]);
  np->cwd = idup(p->cwd);

  safestrcpy(np->name, p->name, sizeof(p->name));

  pid = np->pid;

  np->state = RUNNABLE;

  release(&np->lock);

  return pid;
}

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35

// Given a parent process's page table, copy
// its memory into a child's page table.
// Copies both the page table and the
// physical memory.
// returns 0 on success, -1 on failure.
// frees any allocated pages on failure.
int
uvmcopy(pagetable_t old, pagetable_t new, uint64 sz)
{
  pte_t *pte;
  uint64 pa, i;
  uint flags;
  char *mem;

  for(i = 0; i < sz; i += PGSIZE){
    if((pte = walk(old, i, 0)) == 0)
      panic("uvmcopy: pte should exist");
    if((*pte & PTE_V) == 0)
      panic("uvmcopy: page not present");
    pa = PTE2PA(*pte);
    flags = PTE_FLAGS(*pte);
    if((mem = kalloc()) == 0)
      goto err;
    memmove(mem, (char*)pa, PGSIZE);
    if(mappages(new, i, PGSIZE, (uint64)mem, flags) != 0){
      kfree(mem);
      goto err;
    }
  }
  return 0;

 err:
  uvmunmap(new, 0, i / PGSIZE, 1);
  return -1;
}

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26

// Remove npages of mappings starting from va. va must be
// page-aligned. The mappings must exist.
// Optionally free the physical memory.
void
uvmunmap(pagetable_t pagetable, uint64 va, uint64 npages, int do_free)
{
  uint64 a;
  pte_t *pte;

  if((va % PGSIZE) != 0)
    panic("uvmunmap: not aligned");

  for(a = va; a < va + npages*PGSIZE; a += PGSIZE){
    if((pte = walk(pagetable, a, 0)) == 0)
      panic("uvmunmap: walk");
    if((*pte & PTE_V) == 0)
      panic("uvmunmap: not mapped");
    if(PTE_FLAGS(*pte) == PTE_V)
      panic("uvmunmap: not a leaf");
    if(do_free){
      uint64 pa = PTE2PA(*pte);
      kfree((void*)pa);
    }
    *pte = 0;
  }
}

  1
  2
  3
  4
  5
  6
  7
  8
  9
 10
 11
 12
 13
 14
 15
 16
 17
 18
 19
 20
 21
 22
 23
 24
 25
 26
 27
 28
 29
 30
 31
 32
 33
 34
 35
 36
 37
 38
 39
 40
 41
 42
 43
 44
 45
 46
 47
 48
 49
 50
 51
 52
 53
 54
 55
 56
 57
 58
 59
 60
 61
 62
 63
 64
 65
 66
 67
 68
 69
 70
 71
 72
 73
 74
 75
 76
 77
 78
 79
 80
 81
 82
 83
 84
 85
 86
 87
 88
 89
 90
 91
 92
 93
 94
 95
 96
 97
 98
 99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118

int
exec(char *path, char **argv)
{
  char *s, *last;
  int i, off;
  uint64 argc, sz = 0, sp, ustack[MAXARG+1], stackbase;
  struct elfhdr elf;
  struct inode *ip;
  struct proghdr ph;
  pagetable_t pagetable = 0, oldpagetable;
  struct proc *p = myproc();

  begin_op(); // filesystem 接口

  if((ip = namei(path)) == 0){ // 找到path相应的inode
    end_op();
    return -1;
  }
  ilock(ip);

  // Check ELF header
  if(readi(ip, 0, (uint64)&elf, 0, sizeof(elf)) != sizeof(elf))
    goto bad;
  if(elf.magic != ELF_MAGIC)
    goto bad;

  if((pagetable = proc_pagetable(p)) == 0) // 给新进程初始化pagetable 即映射trampoline 和 trapframe
    goto bad;

  // Load program into memory.
  for(i=0, off=elf.phoff; i<elf.phnum; i++, off+=sizeof(ph)){ // 读program header 中的一个个条目
    if(readi(ip, 0, (uint64)&ph, off, sizeof(ph)) != sizeof(ph))
      goto bad;
    if(ph.type != ELF_PROG_LOAD) // 不需要加载的条目略
      continue;
    if(ph.memsz < ph.filesz)
      goto bad;
    if(ph.vaddr + ph.memsz < ph.vaddr)
      goto bad;
    uint64 sz1;
    if((sz1 = uvmalloc(pagetable, sz, ph.vaddr + ph.memsz)) == 0) // 给用户分配空间
      goto bad;
    sz = sz1;
    if(ph.vaddr % PGSIZE != 0)
      goto bad;
    if(loadseg(pagetable, ph.vaddr, ip, ph.off, ph.filesz) < 0) // 将段装入之前分配的空间
      goto bad;
  }
  iunlockput(ip);
  end_op();
  ip = 0;

  p = myproc();
  uint64 oldsz = p->sz;

  // Allocate two pages at the next page boundary.
  // Use the second as the user stack.
  sz = PGROUNDUP(sz);
  uint64 sz1;
  if((sz1 = uvmalloc(pagetable, sz, sz + 2*PGSIZE)) == 0) // 多分配两页，一页为用户stack 一页为guard page
    goto bad;
  sz = sz1;
  uvmclear(pagetable, sz-2*PGSIZE);  // 清除guard page 对应的U位
  sp = sz;
  stackbase = sp - PGSIZE;

  // Push argument strings, prepare rest of stack in ustack.
  for(argc = 0; argv[argc]; argc++) { // 初始化用户的参数 即argc argv
    if(argc >= MAXARG)
      goto bad;
    sp -= strlen(argv[argc]) + 1;
    sp -= sp % 16; // riscv sp must be 16-byte aligned
    if(sp < stackbase)
      goto bad;
    if(copyout(pagetable, sp, argv[argc], strlen(argv[argc]) + 1) < 0)
      goto bad;
    ustack[argc] = sp;
  }
  ustack[argc] = 0;

  // push the array of argv[] pointers.
  sp -= (argc+1) * sizeof(uint64);
  sp -= sp % 16;
  if(sp < stackbase)
    goto bad;
  if(copyout(pagetable, sp, (char *)ustack, (argc+1)*sizeof(uint64)) < 0)
    goto bad;

  // arguments to user main(argc, argv)
  // argc is returned via the system call return
  // value, which goes in a0.
  p->trapframe->a1 = sp;

  // Save program name for debugging.
  for(last=s=path; *s; s++)
    if(*s == '/')
      last = s+1;
  safestrcpy(p->name, last, sizeof(p->name));
    
  // Commit to the user image.
  oldpagetable = p->pagetable;
  p->pagetable = pagetable;
  p->sz = sz;
  p->trapframe->epc = elf.entry;  // initial program counter = main
  p->trapframe->sp = sp; // initial stack pointer
  proc_freepagetable(oldpagetable, oldsz);

  return argc; // this ends up in a0, the first argument to main(argc, argv)

 bad:
  if(pagetable)
    proc_freepagetable(pagetable, sz);
  if(ip){
    iunlockput(ip);
    end_op();
  }
  return -1;
}

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27

// Allocate PTEs and physical memory to grow process from oldsz to
// newsz, which need not be page aligned.  Returns new size or 0 on error.
uint64
uvmalloc(pagetable_t pagetable, uint64 oldsz, uint64 newsz)
{
  char *mem;
  uint64 a;

  if(newsz < oldsz)
    return oldsz;

  oldsz = PGROUNDUP(oldsz); // oldsz如果在一页的中间，那么这一页一定之前已经分配过给用户了，所以这里是round up
  for(a = oldsz; a < newsz; a += PGSIZE){ // 每一页分配空闲物理页并进行映射
    mem = kalloc();
    if(mem == 0){
      uvmdealloc(pagetable, a, oldsz);
      return 0;
    }
    memset(mem, 0, PGSIZE);
    if(mappages(pagetable, a, PGSIZE, (uint64)mem, PTE_W|PTE_X|PTE_R|PTE_U) != 0){
      kfree(mem);
      uvmdealloc(pagetable, a, oldsz);
      return 0;
    }
  }
  return newsz;
}

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13
14
15
16
17

// 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.
uint64
uvmdealloc(pagetable_t pagetable, uint64 oldsz, uint64 newsz)
{
  if(newsz >= oldsz)
    return oldsz;

  if(PGROUNDUP(newsz) < PGROUNDUP(oldsz)){
    int npages = (PGROUNDUP(oldsz) - PGROUNDUP(newsz)) / PGSIZE;
    uvmunmap(pagetable, PGROUNDUP(newsz), npages, 1);
  }

  return newsz;
}

1

char *sbrk(int n) // Grow process’s memory by n bytes. Returns start of new memory

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13

uint64
sys_sbrk(void)
{
  int addr;
  int n;

  if(argint(0, &n) < 0) // 获取参数 n
    return -1;
  addr = myproc()->sz;  // 现在进程的地址空间为 [0,sz) 故sz就是新的地址起始位置
  if(growproc(n) < 0)   // 扩大用户进程可用内存
    return -1;
  return addr;
}

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13
14
15
16
17
18
19

// Grow or shrink user memory by n bytes.
// Return 0 on success, -1 on failure.
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;
}