forked from naelag/lab2-f17
-
Notifications
You must be signed in to change notification settings - Fork 0
/
fs.c
671 lines (596 loc) · 15.4 KB
/
fs.c
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
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
// File system implementation. Five layers:
// + Blocks: allocator for raw disk blocks.
// + Log: crash recovery for multi-step updates.
// + Files: inode allocator, reading, writing, metadata.
// + Directories: inode with special contents (list of other inodes!)
// + Names: paths like /usr/rtm/xv6/fs.c for convenient naming.
//
// This file contains the low-level file system manipulation
// routines. The (higher-level) system call implementations
// are in sysfile.c.
#include "types.h"
#include "defs.h"
#include "param.h"
#include "stat.h"
#include "mmu.h"
#include "proc.h"
#include "spinlock.h"
#include "sleeplock.h"
#include "fs.h"
#include "buf.h"
#include "file.h"
#define min(a, b) ((a) < (b) ? (a) : (b))
static void itrunc(struct inode*);
// there should be one superblock per disk device, but we run with
// only one device
struct superblock sb;
// Read the super block.
void
readsb(int dev, struct superblock *sb)
{
struct buf *bp;
bp = bread(dev, 1);
memmove(sb, bp->data, sizeof(*sb));
brelse(bp);
}
// Zero a block.
static void
bzero(int dev, int bno)
{
struct buf *bp;
bp = bread(dev, bno);
memset(bp->data, 0, BSIZE);
log_write(bp);
brelse(bp);
}
// Blocks.
// 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;
readsb(dev, &sb);
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);
}
// Inodes.
//
// An inode describes a single unnamed file.
// The inode disk structure holds metadata: the file's type,
// its size, the number of links referring to it, and the
// list of blocks holding the file's content.
//
// The inodes are laid out sequentially on disk at
// sb.startinode. Each inode has a number, indicating its
// position on the disk.
//
// The kernel keeps a cache of in-use inodes in memory
// to provide a place for synchronizing access
// to inodes used by multiple processes. The cached
// inodes include book-keeping information that is
// not stored on disk: ip->ref and ip->valid.
//
// An inode and its in-memory representation go through a
// sequence of states before they can be used by the
// rest of the file system code.
//
// * Allocation: an inode is allocated if its type (on disk)
// is non-zero. ialloc() allocates, and iput() frees if
// the reference and link counts have fallen to zero.
//
// * Referencing in cache: an entry in the inode cache
// is free if ip->ref is zero. Otherwise ip->ref tracks
// the number of in-memory pointers to the entry (open
// files and current directories). iget() finds or
// creates a cache entry and increments its ref; iput()
// decrements ref.
//
// * Valid: the information (type, size, &c) in an inode
// cache entry is only correct when ip->valid is 1.
// ilock() reads the inode from
// the disk and sets ip->valid, while iput() clears
// ip->valid if ip->ref has fallen to zero.
//
// * Locked: file system code may only examine and modify
// the information in an inode and its content if it
// has first locked the inode.
//
// Thus a typical sequence is:
// ip = iget(dev, inum)
// ilock(ip)
// ... examine and modify ip->xxx ...
// iunlock(ip)
// iput(ip)
//
// ilock() is separate from iget() so that system calls can
// get a long-term reference to an inode (as for an open file)
// and only lock it for short periods (e.g., in read()).
// The separation also helps avoid deadlock and races during
// pathname lookup. iget() increments ip->ref so that the inode
// stays cached and pointers to it remain valid.
//
// Many internal file system functions expect the caller to
// have locked the inodes involved; this lets callers create
// multi-step atomic operations.
//
// The icache.lock spin-lock protects the allocation of icache
// entries. Since ip->ref indicates whether an entry is free,
// and ip->dev and ip->inum indicate which i-node an entry
// holds, one must hold icache.lock while using any of those fields.
//
// An ip->lock sleep-lock protects all ip-> fields other than ref,
// dev, and inum. One must hold ip->lock in order to
// read or write that inode's ip->valid, ip->size, ip->type, &c.
struct {
struct spinlock lock;
struct inode inode[NINODE];
} icache;
void
iinit(int dev)
{
int i = 0;
initlock(&icache.lock, "icache");
for(i = 0; i < NINODE; i++) {
initsleeplock(&icache.inode[i].lock, "inode");
}
readsb(dev, &sb);
cprintf("sb: size %d nblocks %d ninodes %d nlog %d logstart %d\
inodestart %d bmap start %d\n", sb.size, sb.nblocks,
sb.ninodes, sb.nlog, sb.logstart, sb.inodestart,
sb.bmapstart);
}
static struct inode* iget(uint dev, uint inum);
//PAGEBREAK!
// Allocate an inode on device dev.
// Mark it as allocated by giving it type type.
// Returns an unlocked but allocated and referenced inode.
struct inode*
ialloc(uint dev, short type)
{
int inum;
struct buf *bp;
struct dinode *dip;
for(inum = 1; inum < sb.ninodes; inum++){
bp = bread(dev, IBLOCK(inum, sb));
dip = (struct dinode*)bp->data + inum%IPB;
if(dip->type == 0){ // a free inode
memset(dip, 0, sizeof(*dip));
dip->type = type;
log_write(bp); // mark it allocated on the disk
brelse(bp);
return iget(dev, inum);
}
brelse(bp);
}
panic("ialloc: no inodes");
}
// Copy a modified in-memory inode to disk.
// Must be called after every change to an ip->xxx field
// that lives on disk, since i-node cache is write-through.
// Caller must hold ip->lock.
void
iupdate(struct inode *ip)
{
struct buf *bp;
struct dinode *dip;
bp = bread(ip->dev, IBLOCK(ip->inum, sb));
dip = (struct dinode*)bp->data + ip->inum%IPB;
dip->type = ip->type;
dip->major = ip->major;
dip->minor = ip->minor;
dip->nlink = ip->nlink;
dip->size = ip->size;
memmove(dip->addrs, ip->addrs, sizeof(ip->addrs));
log_write(bp);
brelse(bp);
}
// 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(&icache.lock);
// Is the inode already cached?
empty = 0;
for(ip = &icache.inode[0]; ip < &icache.inode[NINODE]; ip++){
if(ip->ref > 0 && ip->dev == dev && ip->inum == inum){
ip->ref++;
release(&icache.lock);
return ip;
}
if(empty == 0 && ip->ref == 0) // Remember empty slot.
empty = ip;
}
// Recycle an inode cache entry.
if(empty == 0)
panic("iget: no inodes");
ip = empty;
ip->dev = dev;
ip->inum = inum;
ip->ref = 1;
ip->valid = 0;
release(&icache.lock);
return ip;
}
// Increment reference count for ip.
// Returns ip to enable ip = idup(ip1) idiom.
struct inode*
idup(struct inode *ip)
{
acquire(&icache.lock);
ip->ref++;
release(&icache.lock);
return ip;
}
// 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);
}
// Drop a reference to an in-memory inode.
// If that was the last reference, the inode cache 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)
{
acquiresleep(&ip->lock);
if(ip->valid && ip->nlink == 0){
acquire(&icache.lock);
int r = ip->ref;
release(&icache.lock);
if(r == 1){
// inode has no links and no other references: truncate and free.
itrunc(ip);
ip->type = 0;
iupdate(ip);
ip->valid = 0;
}
}
releasesleep(&ip->lock);
acquire(&icache.lock);
ip->ref--;
release(&icache.lock);
}
// Common idiom: unlock, then put.
void
iunlockput(struct inode *ip)
{
iunlock(ip);
iput(ip);
}
//PAGEBREAK!
// Inode content
//
// The content (data) associated with each inode is stored
// in blocks on the disk. The first NDIRECT block numbers
// are listed in ip->addrs[]. The next NINDIRECT blocks are
// listed in block ip->addrs[NDIRECT].
// Return the disk block address of the nth block in inode ip.
// If there is no such block, bmap allocates one.
static uint
bmap(struct inode *ip, uint bn)
{
uint addr, *a;
struct buf *bp;
if(bn < NDIRECT){
if((addr = ip->addrs[bn]) == 0)
ip->addrs[bn] = addr = balloc(ip->dev);
return addr;
}
bn -= NDIRECT;
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");
}
// Truncate inode (discard contents).
// Only called when the inode has no links
// to it (no directory entries referring to it)
// and has no in-memory reference to it (is
// not an open file or current directory).
static void
itrunc(struct inode *ip)
{
int i, j;
struct buf *bp;
uint *a;
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;
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);
}
// Copy stat information from inode.
// Caller must hold ip->lock.
void
stati(struct inode *ip, struct stat *st)
{
st->dev = ip->dev;
st->ino = ip->inum;
st->type = ip->type;
st->nlink = ip->nlink;
st->size = ip->size;
}
//PAGEBREAK!
// Read data from inode.
// Caller must hold ip->lock.
int
readi(struct inode *ip, char *dst, uint off, uint n)
{
uint tot, m;
struct buf *bp;
if(ip->type == T_DEV){
if(ip->major < 0 || ip->major >= NDEV || !devsw[ip->major].read)
return -1;
return devsw[ip->major].read(ip, dst, n);
}
if(off > ip->size || off + n < off)
return -1;
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);
memmove(dst, bp->data + off%BSIZE, m);
brelse(bp);
}
return n;
}
// PAGEBREAK!
// Write data to inode.
// Caller must hold ip->lock.
int
writei(struct inode *ip, char *src, uint off, uint n)
{
uint tot, m;
struct buf *bp;
if(ip->type == T_DEV){
if(ip->major < 0 || ip->major >= NDEV || !devsw[ip->major].write)
return -1;
return devsw[ip->major].write(ip, src, n);
}
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);
memmove(bp->data + off%BSIZE, src, m);
log_write(bp);
brelse(bp);
}
if(n > 0 && off > ip->size){
ip->size = off;
iupdate(ip);
}
return n;
}
//PAGEBREAK!
// Directories
int
namecmp(const char *s, const char *t)
{
return strncmp(s, t, 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, (char*)&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;
}
// 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, (char*)&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, (char*)&de, off, sizeof(de)) != sizeof(de))
panic("dirlink");
return 0;
}
//PAGEBREAK!
// 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;
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;
}
// 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;
}
struct inode*
namei(char *path)
{
char name[DIRSIZ];
return namex(path, 0, name);
}
struct inode*
nameiparent(char *path, char *name)
{
return namex(path, 1, name);
}