-
Notifications
You must be signed in to change notification settings - Fork 0
/
exec_plan9.go
658 lines (572 loc) · 15.5 KB
/
exec_plan9.go
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
// Copyright 2009 The Go Authors. All rights reserved.
// Use of this source code is governed by a BSD-style
// license that can be found in the LICENSE file.
// Fork, exec, wait, etc.
package syscall
import (
"runtime"
"sync"
"unsafe"
)
// Lock synchronizing creation of new file descriptors with fork.
//
// We want the child in a fork/exec sequence to inherit only the
// file descriptors we intend. To do that, we mark all file
// descriptors close-on-exec and then, in the child, explicitly
// unmark the ones we want the exec'ed program to keep.
// Unix doesn't make this easy: there is, in general, no way to
// allocate a new file descriptor close-on-exec. Instead you
// have to allocate the descriptor and then mark it close-on-exec.
// If a fork happens between those two events, the child's exec
// will inherit an unwanted file descriptor.
//
// This lock solves that race: the create new fd/mark close-on-exec
// operation is done holding ForkLock for reading, and the fork itself
// is done holding ForkLock for writing. At least, that's the idea.
// There are some complications.
//
// Some system calls that create new file descriptors can block
// for arbitrarily long times: open on a hung NFS server or named
// pipe, accept on a socket, and so on. We can't reasonably grab
// the lock across those operations.
//
// It is worse to inherit some file descriptors than others.
// If a non-malicious child accidentally inherits an open ordinary file,
// that's not a big deal. On the other hand, if a long-lived child
// accidentally inherits the write end of a pipe, then the reader
// of that pipe will not see EOF until that child exits, potentially
// causing the parent program to hang. This is a common problem
// in threaded C programs that use popen.
//
// Luckily, the file descriptors that are most important not to
// inherit are not the ones that can take an arbitrarily long time
// to create: pipe returns instantly, and the net package uses
// non-blocking I/O to accept on a listening socket.
// The rules for which file descriptor-creating operations use the
// ForkLock are as follows:
//
// 1) Pipe. Does not block. Use the ForkLock.
// 2) Socket. Does not block. Use the ForkLock.
// 3) Accept. If using non-blocking mode, use the ForkLock.
// Otherwise, live with the race.
// 4) Open. Can block. Use O_CLOEXEC if available (Linux).
// Otherwise, live with the race.
// 5) Dup. Does not block. Use the ForkLock.
// On Linux, could use fcntl F_DUPFD_CLOEXEC
// instead of the ForkLock, but only for dup(fd, -1).
var ForkLock sync.RWMutex
// StringSlicePtr converts a slice of strings to a slice of pointers
// to NUL-terminated byte arrays. If any string contains a NUL byte
// this function panics instead of returning an error.
//
// Deprecated: Use SlicePtrFromStrings instead.
func StringSlicePtr(ss []string) []*byte {
bb := make([]*byte, len(ss)+1)
for i := 0; i < len(ss); i++ {
bb[i] = StringBytePtr(ss[i])
}
bb[len(ss)] = nil
return bb
}
// SlicePtrFromStrings converts a slice of strings to a slice of
// pointers to NUL-terminated byte arrays. If any string contains
// a NUL byte, it returns (nil, EINVAL).
func SlicePtrFromStrings(ss []string) ([]*byte, error) {
var err error
bb := make([]*byte, len(ss)+1)
for i := 0; i < len(ss); i++ {
bb[i], err = BytePtrFromString(ss[i])
if err != nil {
return nil, err
}
}
bb[len(ss)] = nil
return bb, nil
}
// readdirnames returns the names of files inside the directory represented by dirfd.
func readdirnames(dirfd int) (names []string, err error) {
names = make([]string, 0, 100)
var buf [STATMAX]byte
for {
n, e := Read(dirfd, buf[:])
if e != nil {
return nil, e
}
if n == 0 {
break
}
for i := 0; i < n; {
m, _ := gbit16(buf[i:])
m += 2
if m < STATFIXLEN {
return nil, ErrBadStat
}
s, _, ok := gstring(buf[i+41:])
if !ok {
return nil, ErrBadStat
}
names = append(names, s)
i += int(m)
}
}
return
}
// readdupdevice returns a list of currently opened fds (excluding stdin, stdout, stderr) from the dup device #d.
// ForkLock should be write locked before calling, so that no new fds would be created while the fd list is being read.
func readdupdevice() (fds []int, err error) {
dupdevfd, err := Open("#d", O_RDONLY)
if err != nil {
return
}
defer Close(dupdevfd)
names, err := readdirnames(dupdevfd)
if err != nil {
return
}
fds = make([]int, 0, len(names)/2)
for _, name := range names {
if n := len(name); n > 3 && name[n-3:n] == "ctl" {
continue
}
fd := int(atoi([]byte(name)))
switch fd {
case 0, 1, 2, dupdevfd:
continue
}
fds = append(fds, fd)
}
return
}
var startupFds []int
// Plan 9 does not allow clearing the OCEXEC flag
// from the underlying channel backing an open file descriptor,
// therefore we store a list of already opened file descriptors
// inside startupFds and skip them when manually closing descriptors
// not meant to be passed to a child exec.
func init() {
startupFds, _ = readdupdevice()
}
// forkAndExecInChild forks the process, calling dup onto 0..len(fd)
// and finally invoking exec(argv0, argvv, envv) in the child.
// If a dup or exec fails, it writes the error string to pipe.
// (The pipe write end is close-on-exec so if exec succeeds, it will be closed.)
//
// In the child, this function must not acquire any locks, because
// they might have been locked at the time of the fork. This means
// no rescheduling, no malloc calls, and no new stack segments.
// The calls to RawSyscall are okay because they are assembly
// functions that do not grow the stack.
func forkAndExecInChild(argv0 *byte, argv []*byte, envv []envItem, dir *byte, attr *ProcAttr, fdsToClose []int, pipe int, rflag int) (pid int, err error) {
// Declare all variables at top in case any
// declarations require heap allocation (e.g., errbuf).
var (
r1 uintptr
nextfd int
i int
clearenv int
envfd int
errbuf [ERRMAX]byte
)
// Guard against side effects of shuffling fds below.
// Make sure that nextfd is beyond any currently open files so
// that we can't run the risk of overwriting any of them.
fd := make([]int, len(attr.Files))
nextfd = len(attr.Files)
for i, ufd := range attr.Files {
if nextfd < int(ufd) {
nextfd = int(ufd)
}
fd[i] = int(ufd)
}
nextfd++
if envv != nil {
clearenv = RFCENVG
}
// About to call fork.
// No more allocation or calls of non-assembly functions.
r1, _, _ = RawSyscall(SYS_RFORK, uintptr(RFPROC|RFFDG|RFREND|clearenv|rflag), 0, 0)
if r1 != 0 {
if int32(r1) == -1 {
return 0, NewError(errstr())
}
// parent; return PID
return int(r1), nil
}
// Fork succeeded, now in child.
// Close fds we don't need.
for i = 0; i < len(fdsToClose); i++ {
r1, _, _ = RawSyscall(SYS_CLOSE, uintptr(fdsToClose[i]), 0, 0)
if int32(r1) == -1 {
goto childerror
}
}
if envv != nil {
// Write new environment variables.
for i = 0; i < len(envv); i++ {
r1, _, _ = RawSyscall(SYS_CREATE, uintptr(unsafe.Pointer(envv[i].name)), uintptr(O_WRONLY), uintptr(0666))
if int32(r1) == -1 {
goto childerror
}
envfd = int(r1)
r1, _, _ = RawSyscall6(SYS_PWRITE, uintptr(envfd), uintptr(unsafe.Pointer(envv[i].value)), uintptr(envv[i].nvalue),
^uintptr(0), ^uintptr(0), 0)
if int32(r1) == -1 || int(r1) != envv[i].nvalue {
goto childerror
}
r1, _, _ = RawSyscall(SYS_CLOSE, uintptr(envfd), 0, 0)
if int32(r1) == -1 {
goto childerror
}
}
}
// Chdir
if dir != nil {
r1, _, _ = RawSyscall(SYS_CHDIR, uintptr(unsafe.Pointer(dir)), 0, 0)
if int32(r1) == -1 {
goto childerror
}
}
// Pass 1: look for fd[i] < i and move those up above len(fd)
// so that pass 2 won't stomp on an fd it needs later.
if pipe < nextfd {
r1, _, _ = RawSyscall(SYS_DUP, uintptr(pipe), uintptr(nextfd), 0)
if int32(r1) == -1 {
goto childerror
}
pipe = nextfd
nextfd++
}
for i = 0; i < len(fd); i++ {
if fd[i] >= 0 && fd[i] < int(i) {
r1, _, _ = RawSyscall(SYS_DUP, uintptr(fd[i]), uintptr(nextfd), 0)
if int32(r1) == -1 {
goto childerror
}
fd[i] = nextfd
nextfd++
if nextfd == pipe { // don't stomp on pipe
nextfd++
}
}
}
// Pass 2: dup fd[i] down onto i.
for i = 0; i < len(fd); i++ {
if fd[i] == -1 {
RawSyscall(SYS_CLOSE, uintptr(i), 0, 0)
continue
}
if fd[i] == int(i) {
continue
}
r1, _, _ = RawSyscall(SYS_DUP, uintptr(fd[i]), uintptr(i), 0)
if int32(r1) == -1 {
goto childerror
}
}
// Pass 3: close fd[i] if it was moved in the previous pass.
for i = 0; i < len(fd); i++ {
if fd[i] >= 0 && fd[i] != int(i) {
RawSyscall(SYS_CLOSE, uintptr(fd[i]), 0, 0)
}
}
// Time to exec.
r1, _, _ = RawSyscall(SYS_EXEC,
uintptr(unsafe.Pointer(argv0)),
uintptr(unsafe.Pointer(&argv[0])), 0)
childerror:
// send error string on pipe
RawSyscall(SYS_ERRSTR, uintptr(unsafe.Pointer(&errbuf[0])), uintptr(len(errbuf)), 0)
errbuf[len(errbuf)-1] = 0
i = 0
for i < len(errbuf) && errbuf[i] != 0 {
i++
}
RawSyscall6(SYS_PWRITE, uintptr(pipe), uintptr(unsafe.Pointer(&errbuf[0])), uintptr(i),
^uintptr(0), ^uintptr(0), 0)
for {
RawSyscall(SYS_EXITS, 0, 0, 0)
}
// Calling panic is not actually safe,
// but the for loop above won't break
// and this shuts up the compiler.
panic("unreached")
}
func cexecPipe(p []int) error {
e := Pipe(p)
if e != nil {
return e
}
fd, e := Open("#d/"+itoa(p[1]), O_CLOEXEC)
if e != nil {
Close(p[0])
Close(p[1])
return e
}
Close(fd)
return nil
}
type envItem struct {
name *byte
value *byte
nvalue int
}
type ProcAttr struct {
Dir string // Current working directory.
Env []string // Environment.
Files []uintptr // File descriptors.
Sys *SysProcAttr
}
type SysProcAttr struct {
Rfork int // additional flags to pass to rfork
}
var zeroProcAttr ProcAttr
var zeroSysProcAttr SysProcAttr
func forkExec(argv0 string, argv []string, attr *ProcAttr) (pid int, err error) {
var (
p [2]int
n int
errbuf [ERRMAX]byte
wmsg Waitmsg
)
if attr == nil {
attr = &zeroProcAttr
}
sys := attr.Sys
if sys == nil {
sys = &zeroSysProcAttr
}
p[0] = -1
p[1] = -1
// Convert args to C form.
argv0p, err := BytePtrFromString(argv0)
if err != nil {
return 0, err
}
argvp, err := SlicePtrFromStrings(argv)
if err != nil {
return 0, err
}
destDir := attr.Dir
if destDir == "" {
wdmu.Lock()
destDir = wdStr
wdmu.Unlock()
}
var dir *byte
if destDir != "" {
dir, err = BytePtrFromString(destDir)
if err != nil {
return 0, err
}
}
var envvParsed []envItem
if attr.Env != nil {
envvParsed = make([]envItem, 0, len(attr.Env))
for _, v := range attr.Env {
i := 0
for i < len(v) && v[i] != '=' {
i++
}
envname, err := BytePtrFromString("/env/" + v[:i])
if err != nil {
return 0, err
}
envvalue := make([]byte, len(v)-i)
copy(envvalue, v[i+1:])
envvParsed = append(envvParsed, envItem{envname, &envvalue[0], len(v) - i})
}
}
// Acquire the fork lock to prevent other threads from creating new fds before we fork.
ForkLock.Lock()
// get a list of open fds, excluding stdin,stdout and stderr that need to be closed in the child.
// no new fds can be created while we hold the ForkLock for writing.
openFds, e := readdupdevice()
if e != nil {
ForkLock.Unlock()
return 0, e
}
fdsToClose := make([]int, 0, len(openFds))
for _, fd := range openFds {
doClose := true
// exclude files opened at startup.
for _, sfd := range startupFds {
if fd == sfd {
doClose = false
break
}
}
// exclude files explicitly requested by the caller.
for _, rfd := range attr.Files {
if fd == int(rfd) {
doClose = false
break
}
}
if doClose {
fdsToClose = append(fdsToClose, fd)
}
}
// Allocate child status pipe close on exec.
e = cexecPipe(p[:])
if e != nil {
return 0, e
}
fdsToClose = append(fdsToClose, p[0])
// Kick off child.
pid, err = forkAndExecInChild(argv0p, argvp, envvParsed, dir, attr, fdsToClose, p[1], sys.Rfork)
if err != nil {
if p[0] >= 0 {
Close(p[0])
Close(p[1])
}
ForkLock.Unlock()
return 0, err
}
ForkLock.Unlock()
// Read child error status from pipe.
Close(p[1])
n, err = Read(p[0], errbuf[:])
Close(p[0])
if err != nil || n != 0 {
if n != 0 {
err = NewError(string(errbuf[:n]))
}
// Child failed; wait for it to exit, to make sure
// the zombies don't accumulate.
for wmsg.Pid != pid {
Await(&wmsg)
}
return 0, err
}
// Read got EOF, so pipe closed on exec, so exec succeeded.
return pid, nil
}
type waitErr struct {
Waitmsg
err error
}
var procs struct {
sync.Mutex
waits map[int]chan *waitErr
}
// startProcess starts a new goroutine, tied to the OS
// thread, which runs the process and subsequently waits
// for it to finish, communicating the process stats back
// to any goroutines that may have been waiting on it.
//
// Such a dedicated goroutine is needed because on
// Plan 9, only the parent thread can wait for a child,
// whereas goroutines tend to jump OS threads (e.g.,
// between starting a process and running Wait(), the
// goroutine may have been rescheduled).
func startProcess(argv0 string, argv []string, attr *ProcAttr) (pid int, err error) {
type forkRet struct {
pid int
err error
}
forkc := make(chan forkRet, 1)
go func() {
runtime.LockOSThread()
var ret forkRet
ret.pid, ret.err = forkExec(argv0, argv, attr)
// If fork fails there is nothing to wait for.
if ret.err != nil || ret.pid == 0 {
forkc <- ret
return
}
waitc := make(chan *waitErr, 1)
// Mark that the process is running.
procs.Lock()
if procs.waits == nil {
procs.waits = make(map[int]chan *waitErr)
}
procs.waits[ret.pid] = waitc
procs.Unlock()
forkc <- ret
var w waitErr
for w.err == nil && w.Pid != ret.pid {
w.err = Await(&w.Waitmsg)
}
waitc <- &w
close(waitc)
}()
ret := <-forkc
return ret.pid, ret.err
}
// Combination of fork and exec, careful to be thread safe.
func ForkExec(argv0 string, argv []string, attr *ProcAttr) (pid int, err error) {
return startProcess(argv0, argv, attr)
}
// StartProcess wraps ForkExec for package os.
func StartProcess(argv0 string, argv []string, attr *ProcAttr) (pid int, handle uintptr, err error) {
pid, err = startProcess(argv0, argv, attr)
return pid, 0, err
}
// Ordinary exec.
func Exec(argv0 string, argv []string, envv []string) (err error) {
if envv != nil {
r1, _, _ := RawSyscall(SYS_RFORK, RFCENVG, 0, 0)
if int32(r1) == -1 {
return NewError(errstr())
}
for _, v := range envv {
i := 0
for i < len(v) && v[i] != '=' {
i++
}
fd, e := Create("/env/"+v[:i], O_WRONLY, 0666)
if e != nil {
return e
}
_, e = Write(fd, []byte(v[i+1:]))
if e != nil {
Close(fd)
return e
}
Close(fd)
}
}
argv0p, err := BytePtrFromString(argv0)
if err != nil {
return err
}
argvp, err := SlicePtrFromStrings(argv)
if err != nil {
return err
}
_, _, e1 := Syscall(SYS_EXEC,
uintptr(unsafe.Pointer(argv0p)),
uintptr(unsafe.Pointer(&argvp[0])),
0)
return e1
}
// WaitProcess waits until the pid of a
// running process is found in the queue of
// wait messages. It is used in conjunction
// with ForkExec/StartProcess to wait for a
// running process to exit.
func WaitProcess(pid int, w *Waitmsg) (err error) {
procs.Lock()
ch := procs.waits[pid]
procs.Unlock()
var wmsg *waitErr
if ch != nil {
wmsg = <-ch
procs.Lock()
if procs.waits[pid] == ch {
delete(procs.waits, pid)
}
procs.Unlock()
}
if wmsg == nil {
// ch was missing or ch is closed
return NewError("process not found")
}
if wmsg.err != nil {
return wmsg.err
}
if w != nil {
*w = wmsg.Waitmsg
}
return nil
}