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
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
|
struct vma {
uint64 addr;
int length;
int usedlength;
int prot;
int flags;
int offset;
struct file *fp;
};
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 vma vmas[16];
};
uint64
sys_mmap(void)
{
struct file *f;
uint64 offset;
int n;
int addr, prot, flags, fd;
// 检查传入参数是否合法
if(argint(0, &addr) < 0 || argfd(4, &fd, &f) < 0 || argint(1, &n) < 0 || argaddr(5, &offset) < 0 ||
argint(2, &prot) < 0 || argint(3, &flags) < 0)
return 0xffffffffffffffff;
// 检查权限
if((!f->writable) && (prot & PROT_WRITE) && (flags & MAP_SHARED)) return 0xffffffffffffffff;
// 增加文件引用计数
filedup(f);
f->off = offset;
uint64 retaddr = myproc()->sz;
myproc()->sz += n;
// 寻址一个空闲的 vma
int idx = 0;
for(int i = 0; i < 16; i++) {
if(myproc()->vmas[i].length == 0) {
idx = i;
break;
}
}
// 设置 vma 信息
struct vma *pvma = &myproc()->vmas[idx];
pvma->addr = retaddr;
pvma->length = n;
pvma->prot = prot;
pvma->flags = flags;
pvma->fp = f;
pvma->offset = offset;
return retaddr;
}
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 {
if(r_scause() == 13 || r_scause() == 15) { // 根据 r_scause 的值判断是不是缺页中断
uint64 va = r_stval(); // 获取发生中断的虚拟地址
// 找到发生缺页的 vma
int idx = 0;
for(int i = 0; i < 16; i++) {
if(myproc()->vmas[i].length == 0) continue;
if(va>= myproc()->vmas[i].addr && va < myproc()->vmas[i].addr+myproc()->vmas[i].length) {
idx =i;
break;
}
}
struct vma* pvma = &myproc()->vmas[idx];
if(va>= pvma->addr && va < pvma->addr + pvma->length) {
uint64 a = PGROUNDDOWN(va);
char* mem = kalloc(); // 分配物理页
if(mem == 0){ // 判断是否内存不足
p->killed = 1;
} else {
memset(mem, 0, PGSIZE);
int flags = 0;
// 设置权限位
int prot = pvma->prot;
if(prot & PROT_READ){
flags |= PTE_R;
}
if(prot & PROT_WRITE){
flags |= PTE_W;
}
if(prot & PROT_EXEC){
flags |= PTE_X;
}
if(mappages(p->pagetable, a, PGSIZE, (uint64)mem, flags|PTE_U) != 0){ // 完成映射
kfree(mem);
p->killed = 1;
}
}
// 将文件内容加载到物理内存
struct file *f = pvma->fp;
int r = 0;
ilock(f->ip);
if((r = readi(f->ip, 1, a, a-pvma->addr, PGSIZE)) > 0) {
f->off += r;
pvma->usedlength += PGSIZE;
}
iunlock(f->ip);
} else {
p->killed = 1;
}
} 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 decrmmap(struct file *f)
{
acquire(&ftable.lock);
if(f->ref < 1) {
release(&ftable.lock);
return;
}
if(--f->ref > 0){
release(&ftable.lock);
return;
}
release(&ftable.lock);
}
uint64
sys_munmap(void)
{
int addr, length;
if(argint(0, &addr) < 0 || argint(1, &length) < 0)
return -1;
// 查找 vma
int idx = 0;
for(int i = 0; i < 16; i++) {
if(myproc()->vmas[i].length == 0) continue;
if(addr>= myproc()->vmas[i].addr && addr < myproc()->vmas[i].addr+myproc()->vmas[i].length) {
idx = i;
break;
}
}
struct vma *pvma = &myproc()->vmas[idx];
pte_t *pte;
pvma->fp->off = pvma->offset;
int flag = 0;
// 从 vma 空间中找到要解除映射的页并解除映射
for(int va = addr; va < addr + length; va += PGSIZE){
if((pte = walk(myproc()->pagetable, va, 0)) == 0)
continue;
if((*pte & PTE_V) == 0)
continue;
if(PTE_FLAGS(*pte) == PTE_V)
panic("uvmunmap: not a leaf");
if(pvma->flags & MAP_SHARED){ // 写回文件
filewrite(pvma->fp, va, PGSIZE);
}
uint64 pa = PTE2PA(*pte);
kfree((void*)pa);
pvma->usedlength -= PGSIZE;
flag = 1;
myproc()->sz -= PGSIZE;
*pte = 0;
}
// 所有映射都解除了,释放文件引用计数
if(pvma->usedlength == 0 && flag) {
struct file* f = pvma->fp;
decrmmap(f);
pvma->length = 0;
}
return 0;
}
int
fork(void)
{
int i, pid;
struct proc *np;
struct proc *p = myproc();
// Allocate process.
if((np = allocproc()) == 0){
return -1;
}
// 复制 vma
for(int i = 0; i < 16; i++){
if(p->vmas[i].length == 0) continue;
struct vma* pvma = &np->vmas[i];
struct vma* ppvma = &p->vmas[i];
pvma->addr = ppvma->addr;
pvma->length = ppvma->length;
pvma->prot = ppvma->prot;
pvma->flags = ppvma->flags;
pvma->fp = ppvma->fp;
pvma->offset = ppvma->offset;
pvma->usedlength = ppvma->usedlength;
filedup(pvma->fp);
}
// 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;
}
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"); 由于是懒加载所以这里需要忽略没有 pte 的情况,下面的一行同理
continue;
if((*pte & PTE_V) == 0)
// panic("uvmcopy: page not present");
continue;
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;
}
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"); 同 uvmcopy
continue;
if((*pte & PTE_V) == 0)
// panic("uvmunmap: not mapped");
continue;
if(PTE_FLAGS(*pte) == PTE_V)
panic("uvmunmap: not a leaf");
if(do_free){
uint64 pa = PTE2PA(*pte);
kfree((void*)pa);
}
*pte = 0;
}
}
|