forked from grate-driver/linux
-
Notifications
You must be signed in to change notification settings - Fork 0
/
mqueue.c
1738 lines (1517 loc) · 43.3 KB
/
mqueue.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
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
/*
* POSIX message queues filesystem for Linux.
*
* Copyright (C) 2003,2004 Krzysztof Benedyczak (golbi@mat.uni.torun.pl)
* Michal Wronski (michal.wronski@gmail.com)
*
* Spinlocks: Mohamed Abbas (abbas.mohamed@intel.com)
* Lockless receive & send, fd based notify:
* Manfred Spraul (manfred@colorfullife.com)
*
* Audit: George Wilson (ltcgcw@us.ibm.com)
*
* This file is released under the GPL.
*/
#include <linux/capability.h>
#include <linux/init.h>
#include <linux/pagemap.h>
#include <linux/file.h>
#include <linux/mount.h>
#include <linux/fs_context.h>
#include <linux/namei.h>
#include <linux/sysctl.h>
#include <linux/poll.h>
#include <linux/mqueue.h>
#include <linux/msg.h>
#include <linux/skbuff.h>
#include <linux/vmalloc.h>
#include <linux/netlink.h>
#include <linux/syscalls.h>
#include <linux/audit.h>
#include <linux/signal.h>
#include <linux/mutex.h>
#include <linux/nsproxy.h>
#include <linux/pid.h>
#include <linux/ipc_namespace.h>
#include <linux/user_namespace.h>
#include <linux/slab.h>
#include <linux/sched/wake_q.h>
#include <linux/sched/signal.h>
#include <linux/sched/user.h>
#include <net/sock.h>
#include "util.h"
struct mqueue_fs_context {
struct ipc_namespace *ipc_ns;
};
#define MQUEUE_MAGIC 0x19800202
#define DIRENT_SIZE 20
#define FILENT_SIZE 80
#define SEND 0
#define RECV 1
#define STATE_NONE 0
#define STATE_READY 1
struct posix_msg_tree_node {
struct rb_node rb_node;
struct list_head msg_list;
int priority;
};
/*
* Locking:
*
* Accesses to a message queue are synchronized by acquiring info->lock.
*
* There are two notable exceptions:
* - The actual wakeup of a sleeping task is performed using the wake_q
* framework. info->lock is already released when wake_up_q is called.
* - The exit codepaths after sleeping check ext_wait_queue->state without
* any locks. If it is STATE_READY, then the syscall is completed without
* acquiring info->lock.
*
* MQ_BARRIER:
* To achieve proper release/acquire memory barrier pairing, the state is set to
* STATE_READY with smp_store_release(), and it is read with READ_ONCE followed
* by smp_acquire__after_ctrl_dep(). In addition, wake_q_add_safe() is used.
*
* This prevents the following races:
*
* 1) With the simple wake_q_add(), the task could be gone already before
* the increase of the reference happens
* Thread A
* Thread B
* WRITE_ONCE(wait.state, STATE_NONE);
* schedule_hrtimeout()
* wake_q_add(A)
* if (cmpxchg()) // success
* ->state = STATE_READY (reordered)
* <timeout returns>
* if (wait.state == STATE_READY) return;
* sysret to user space
* sys_exit()
* get_task_struct() // UaF
*
* Solution: Use wake_q_add_safe() and perform the get_task_struct() before
* the smp_store_release() that does ->state = STATE_READY.
*
* 2) Without proper _release/_acquire barriers, the woken up task
* could read stale data
*
* Thread A
* Thread B
* do_mq_timedreceive
* WRITE_ONCE(wait.state, STATE_NONE);
* schedule_hrtimeout()
* state = STATE_READY;
* <timeout returns>
* if (wait.state == STATE_READY) return;
* msg_ptr = wait.msg; // Access to stale data!
* receiver->msg = message; (reordered)
*
* Solution: use _release and _acquire barriers.
*
* 3) There is intentionally no barrier when setting current->state
* to TASK_INTERRUPTIBLE: spin_unlock(&info->lock) provides the
* release memory barrier, and the wakeup is triggered when holding
* info->lock, i.e. spin_lock(&info->lock) provided a pairing
* acquire memory barrier.
*/
struct ext_wait_queue { /* queue of sleeping tasks */
struct task_struct *task;
struct list_head list;
struct msg_msg *msg; /* ptr of loaded message */
int state; /* one of STATE_* values */
};
struct mqueue_inode_info {
spinlock_t lock;
struct inode vfs_inode;
wait_queue_head_t wait_q;
struct rb_root msg_tree;
struct rb_node *msg_tree_rightmost;
struct posix_msg_tree_node *node_cache;
struct mq_attr attr;
struct sigevent notify;
struct pid *notify_owner;
u32 notify_self_exec_id;
struct user_namespace *notify_user_ns;
struct ucounts *ucounts; /* user who created, for accounting */
struct sock *notify_sock;
struct sk_buff *notify_cookie;
/* for tasks waiting for free space and messages, respectively */
struct ext_wait_queue e_wait_q[2];
unsigned long qsize; /* size of queue in memory (sum of all msgs) */
};
static struct file_system_type mqueue_fs_type;
static const struct inode_operations mqueue_dir_inode_operations;
static const struct file_operations mqueue_file_operations;
static const struct super_operations mqueue_super_ops;
static const struct fs_context_operations mqueue_fs_context_ops;
static void remove_notification(struct mqueue_inode_info *info);
static struct kmem_cache *mqueue_inode_cachep;
static inline struct mqueue_inode_info *MQUEUE_I(struct inode *inode)
{
return container_of(inode, struct mqueue_inode_info, vfs_inode);
}
/*
* This routine should be called with the mq_lock held.
*/
static inline struct ipc_namespace *__get_ns_from_inode(struct inode *inode)
{
return get_ipc_ns(inode->i_sb->s_fs_info);
}
static struct ipc_namespace *get_ns_from_inode(struct inode *inode)
{
struct ipc_namespace *ns;
spin_lock(&mq_lock);
ns = __get_ns_from_inode(inode);
spin_unlock(&mq_lock);
return ns;
}
/* Auxiliary functions to manipulate messages' list */
static int msg_insert(struct msg_msg *msg, struct mqueue_inode_info *info)
{
struct rb_node **p, *parent = NULL;
struct posix_msg_tree_node *leaf;
bool rightmost = true;
p = &info->msg_tree.rb_node;
while (*p) {
parent = *p;
leaf = rb_entry(parent, struct posix_msg_tree_node, rb_node);
if (likely(leaf->priority == msg->m_type))
goto insert_msg;
else if (msg->m_type < leaf->priority) {
p = &(*p)->rb_left;
rightmost = false;
} else
p = &(*p)->rb_right;
}
if (info->node_cache) {
leaf = info->node_cache;
info->node_cache = NULL;
} else {
leaf = kmalloc(sizeof(*leaf), GFP_ATOMIC);
if (!leaf)
return -ENOMEM;
INIT_LIST_HEAD(&leaf->msg_list);
}
leaf->priority = msg->m_type;
if (rightmost)
info->msg_tree_rightmost = &leaf->rb_node;
rb_link_node(&leaf->rb_node, parent, p);
rb_insert_color(&leaf->rb_node, &info->msg_tree);
insert_msg:
info->attr.mq_curmsgs++;
info->qsize += msg->m_ts;
list_add_tail(&msg->m_list, &leaf->msg_list);
return 0;
}
static inline void msg_tree_erase(struct posix_msg_tree_node *leaf,
struct mqueue_inode_info *info)
{
struct rb_node *node = &leaf->rb_node;
if (info->msg_tree_rightmost == node)
info->msg_tree_rightmost = rb_prev(node);
rb_erase(node, &info->msg_tree);
if (info->node_cache)
kfree(leaf);
else
info->node_cache = leaf;
}
static inline struct msg_msg *msg_get(struct mqueue_inode_info *info)
{
struct rb_node *parent = NULL;
struct posix_msg_tree_node *leaf;
struct msg_msg *msg;
try_again:
/*
* During insert, low priorities go to the left and high to the
* right. On receive, we want the highest priorities first, so
* walk all the way to the right.
*/
parent = info->msg_tree_rightmost;
if (!parent) {
if (info->attr.mq_curmsgs) {
pr_warn_once("Inconsistency in POSIX message queue, "
"no tree element, but supposedly messages "
"should exist!\n");
info->attr.mq_curmsgs = 0;
}
return NULL;
}
leaf = rb_entry(parent, struct posix_msg_tree_node, rb_node);
if (unlikely(list_empty(&leaf->msg_list))) {
pr_warn_once("Inconsistency in POSIX message queue, "
"empty leaf node but we haven't implemented "
"lazy leaf delete!\n");
msg_tree_erase(leaf, info);
goto try_again;
} else {
msg = list_first_entry(&leaf->msg_list,
struct msg_msg, m_list);
list_del(&msg->m_list);
if (list_empty(&leaf->msg_list)) {
msg_tree_erase(leaf, info);
}
}
info->attr.mq_curmsgs--;
info->qsize -= msg->m_ts;
return msg;
}
static struct inode *mqueue_get_inode(struct super_block *sb,
struct ipc_namespace *ipc_ns, umode_t mode,
struct mq_attr *attr)
{
struct inode *inode;
int ret = -ENOMEM;
inode = new_inode(sb);
if (!inode)
goto err;
inode->i_ino = get_next_ino();
inode->i_mode = mode;
inode->i_uid = current_fsuid();
inode->i_gid = current_fsgid();
inode->i_mtime = inode->i_ctime = inode->i_atime = current_time(inode);
if (S_ISREG(mode)) {
struct mqueue_inode_info *info;
unsigned long mq_bytes, mq_treesize;
inode->i_fop = &mqueue_file_operations;
inode->i_size = FILENT_SIZE;
/* mqueue specific info */
info = MQUEUE_I(inode);
spin_lock_init(&info->lock);
init_waitqueue_head(&info->wait_q);
INIT_LIST_HEAD(&info->e_wait_q[0].list);
INIT_LIST_HEAD(&info->e_wait_q[1].list);
info->notify_owner = NULL;
info->notify_user_ns = NULL;
info->qsize = 0;
info->ucounts = NULL; /* set when all is ok */
info->msg_tree = RB_ROOT;
info->msg_tree_rightmost = NULL;
info->node_cache = NULL;
memset(&info->attr, 0, sizeof(info->attr));
info->attr.mq_maxmsg = min(ipc_ns->mq_msg_max,
ipc_ns->mq_msg_default);
info->attr.mq_msgsize = min(ipc_ns->mq_msgsize_max,
ipc_ns->mq_msgsize_default);
if (attr) {
info->attr.mq_maxmsg = attr->mq_maxmsg;
info->attr.mq_msgsize = attr->mq_msgsize;
}
/*
* We used to allocate a static array of pointers and account
* the size of that array as well as one msg_msg struct per
* possible message into the queue size. That's no longer
* accurate as the queue is now an rbtree and will grow and
* shrink depending on usage patterns. We can, however, still
* account one msg_msg struct per message, but the nodes are
* allocated depending on priority usage, and most programs
* only use one, or a handful, of priorities. However, since
* this is pinned memory, we need to assume worst case, so
* that means the min(mq_maxmsg, max_priorities) * struct
* posix_msg_tree_node.
*/
ret = -EINVAL;
if (info->attr.mq_maxmsg <= 0 || info->attr.mq_msgsize <= 0)
goto out_inode;
if (capable(CAP_SYS_RESOURCE)) {
if (info->attr.mq_maxmsg > HARD_MSGMAX ||
info->attr.mq_msgsize > HARD_MSGSIZEMAX)
goto out_inode;
} else {
if (info->attr.mq_maxmsg > ipc_ns->mq_msg_max ||
info->attr.mq_msgsize > ipc_ns->mq_msgsize_max)
goto out_inode;
}
ret = -EOVERFLOW;
/* check for overflow */
if (info->attr.mq_msgsize > ULONG_MAX/info->attr.mq_maxmsg)
goto out_inode;
mq_treesize = info->attr.mq_maxmsg * sizeof(struct msg_msg) +
min_t(unsigned int, info->attr.mq_maxmsg, MQ_PRIO_MAX) *
sizeof(struct posix_msg_tree_node);
mq_bytes = info->attr.mq_maxmsg * info->attr.mq_msgsize;
if (mq_bytes + mq_treesize < mq_bytes)
goto out_inode;
mq_bytes += mq_treesize;
info->ucounts = get_ucounts(current_ucounts());
if (info->ucounts) {
long msgqueue;
spin_lock(&mq_lock);
msgqueue = inc_rlimit_ucounts(info->ucounts, UCOUNT_RLIMIT_MSGQUEUE, mq_bytes);
if (msgqueue == LONG_MAX || msgqueue > rlimit(RLIMIT_MSGQUEUE)) {
dec_rlimit_ucounts(info->ucounts, UCOUNT_RLIMIT_MSGQUEUE, mq_bytes);
spin_unlock(&mq_lock);
put_ucounts(info->ucounts);
info->ucounts = NULL;
/* mqueue_evict_inode() releases info->messages */
ret = -EMFILE;
goto out_inode;
}
spin_unlock(&mq_lock);
}
} else if (S_ISDIR(mode)) {
inc_nlink(inode);
/* Some things misbehave if size == 0 on a directory */
inode->i_size = 2 * DIRENT_SIZE;
inode->i_op = &mqueue_dir_inode_operations;
inode->i_fop = &simple_dir_operations;
}
return inode;
out_inode:
iput(inode);
err:
return ERR_PTR(ret);
}
static int mqueue_fill_super(struct super_block *sb, struct fs_context *fc)
{
struct inode *inode;
struct ipc_namespace *ns = sb->s_fs_info;
sb->s_iflags |= SB_I_NOEXEC | SB_I_NODEV;
sb->s_blocksize = PAGE_SIZE;
sb->s_blocksize_bits = PAGE_SHIFT;
sb->s_magic = MQUEUE_MAGIC;
sb->s_op = &mqueue_super_ops;
inode = mqueue_get_inode(sb, ns, S_IFDIR | S_ISVTX | S_IRWXUGO, NULL);
if (IS_ERR(inode))
return PTR_ERR(inode);
sb->s_root = d_make_root(inode);
if (!sb->s_root)
return -ENOMEM;
return 0;
}
static int mqueue_get_tree(struct fs_context *fc)
{
struct mqueue_fs_context *ctx = fc->fs_private;
return get_tree_keyed(fc, mqueue_fill_super, ctx->ipc_ns);
}
static void mqueue_fs_context_free(struct fs_context *fc)
{
struct mqueue_fs_context *ctx = fc->fs_private;
put_ipc_ns(ctx->ipc_ns);
kfree(ctx);
}
static int mqueue_init_fs_context(struct fs_context *fc)
{
struct mqueue_fs_context *ctx;
ctx = kzalloc(sizeof(struct mqueue_fs_context), GFP_KERNEL);
if (!ctx)
return -ENOMEM;
ctx->ipc_ns = get_ipc_ns(current->nsproxy->ipc_ns);
put_user_ns(fc->user_ns);
fc->user_ns = get_user_ns(ctx->ipc_ns->user_ns);
fc->fs_private = ctx;
fc->ops = &mqueue_fs_context_ops;
return 0;
}
static struct vfsmount *mq_create_mount(struct ipc_namespace *ns)
{
struct mqueue_fs_context *ctx;
struct fs_context *fc;
struct vfsmount *mnt;
fc = fs_context_for_mount(&mqueue_fs_type, SB_KERNMOUNT);
if (IS_ERR(fc))
return ERR_CAST(fc);
ctx = fc->fs_private;
put_ipc_ns(ctx->ipc_ns);
ctx->ipc_ns = get_ipc_ns(ns);
put_user_ns(fc->user_ns);
fc->user_ns = get_user_ns(ctx->ipc_ns->user_ns);
mnt = fc_mount(fc);
put_fs_context(fc);
return mnt;
}
static void init_once(void *foo)
{
struct mqueue_inode_info *p = (struct mqueue_inode_info *) foo;
inode_init_once(&p->vfs_inode);
}
static struct inode *mqueue_alloc_inode(struct super_block *sb)
{
struct mqueue_inode_info *ei;
ei = kmem_cache_alloc(mqueue_inode_cachep, GFP_KERNEL);
if (!ei)
return NULL;
return &ei->vfs_inode;
}
static void mqueue_free_inode(struct inode *inode)
{
kmem_cache_free(mqueue_inode_cachep, MQUEUE_I(inode));
}
static void mqueue_evict_inode(struct inode *inode)
{
struct mqueue_inode_info *info;
struct ipc_namespace *ipc_ns;
struct msg_msg *msg, *nmsg;
LIST_HEAD(tmp_msg);
clear_inode(inode);
if (S_ISDIR(inode->i_mode))
return;
ipc_ns = get_ns_from_inode(inode);
info = MQUEUE_I(inode);
spin_lock(&info->lock);
while ((msg = msg_get(info)) != NULL)
list_add_tail(&msg->m_list, &tmp_msg);
kfree(info->node_cache);
spin_unlock(&info->lock);
list_for_each_entry_safe(msg, nmsg, &tmp_msg, m_list) {
list_del(&msg->m_list);
free_msg(msg);
}
if (info->ucounts) {
unsigned long mq_bytes, mq_treesize;
/* Total amount of bytes accounted for the mqueue */
mq_treesize = info->attr.mq_maxmsg * sizeof(struct msg_msg) +
min_t(unsigned int, info->attr.mq_maxmsg, MQ_PRIO_MAX) *
sizeof(struct posix_msg_tree_node);
mq_bytes = mq_treesize + (info->attr.mq_maxmsg *
info->attr.mq_msgsize);
spin_lock(&mq_lock);
dec_rlimit_ucounts(info->ucounts, UCOUNT_RLIMIT_MSGQUEUE, mq_bytes);
/*
* get_ns_from_inode() ensures that the
* (ipc_ns = sb->s_fs_info) is either a valid ipc_ns
* to which we now hold a reference, or it is NULL.
* We can't put it here under mq_lock, though.
*/
if (ipc_ns)
ipc_ns->mq_queues_count--;
spin_unlock(&mq_lock);
put_ucounts(info->ucounts);
info->ucounts = NULL;
}
if (ipc_ns)
put_ipc_ns(ipc_ns);
}
static int mqueue_create_attr(struct dentry *dentry, umode_t mode, void *arg)
{
struct inode *dir = dentry->d_parent->d_inode;
struct inode *inode;
struct mq_attr *attr = arg;
int error;
struct ipc_namespace *ipc_ns;
spin_lock(&mq_lock);
ipc_ns = __get_ns_from_inode(dir);
if (!ipc_ns) {
error = -EACCES;
goto out_unlock;
}
if (ipc_ns->mq_queues_count >= ipc_ns->mq_queues_max &&
!capable(CAP_SYS_RESOURCE)) {
error = -ENOSPC;
goto out_unlock;
}
ipc_ns->mq_queues_count++;
spin_unlock(&mq_lock);
inode = mqueue_get_inode(dir->i_sb, ipc_ns, mode, attr);
if (IS_ERR(inode)) {
error = PTR_ERR(inode);
spin_lock(&mq_lock);
ipc_ns->mq_queues_count--;
goto out_unlock;
}
put_ipc_ns(ipc_ns);
dir->i_size += DIRENT_SIZE;
dir->i_ctime = dir->i_mtime = dir->i_atime = current_time(dir);
d_instantiate(dentry, inode);
dget(dentry);
return 0;
out_unlock:
spin_unlock(&mq_lock);
if (ipc_ns)
put_ipc_ns(ipc_ns);
return error;
}
static int mqueue_create(struct user_namespace *mnt_userns, struct inode *dir,
struct dentry *dentry, umode_t mode, bool excl)
{
return mqueue_create_attr(dentry, mode, NULL);
}
static int mqueue_unlink(struct inode *dir, struct dentry *dentry)
{
struct inode *inode = d_inode(dentry);
dir->i_ctime = dir->i_mtime = dir->i_atime = current_time(dir);
dir->i_size -= DIRENT_SIZE;
drop_nlink(inode);
dput(dentry);
return 0;
}
/*
* This is routine for system read from queue file.
* To avoid mess with doing here some sort of mq_receive we allow
* to read only queue size & notification info (the only values
* that are interesting from user point of view and aren't accessible
* through std routines)
*/
static ssize_t mqueue_read_file(struct file *filp, char __user *u_data,
size_t count, loff_t *off)
{
struct mqueue_inode_info *info = MQUEUE_I(file_inode(filp));
char buffer[FILENT_SIZE];
ssize_t ret;
spin_lock(&info->lock);
snprintf(buffer, sizeof(buffer),
"QSIZE:%-10lu NOTIFY:%-5d SIGNO:%-5d NOTIFY_PID:%-6d\n",
info->qsize,
info->notify_owner ? info->notify.sigev_notify : 0,
(info->notify_owner &&
info->notify.sigev_notify == SIGEV_SIGNAL) ?
info->notify.sigev_signo : 0,
pid_vnr(info->notify_owner));
spin_unlock(&info->lock);
buffer[sizeof(buffer)-1] = '\0';
ret = simple_read_from_buffer(u_data, count, off, buffer,
strlen(buffer));
if (ret <= 0)
return ret;
file_inode(filp)->i_atime = file_inode(filp)->i_ctime = current_time(file_inode(filp));
return ret;
}
static int mqueue_flush_file(struct file *filp, fl_owner_t id)
{
struct mqueue_inode_info *info = MQUEUE_I(file_inode(filp));
spin_lock(&info->lock);
if (task_tgid(current) == info->notify_owner)
remove_notification(info);
spin_unlock(&info->lock);
return 0;
}
static __poll_t mqueue_poll_file(struct file *filp, struct poll_table_struct *poll_tab)
{
struct mqueue_inode_info *info = MQUEUE_I(file_inode(filp));
__poll_t retval = 0;
poll_wait(filp, &info->wait_q, poll_tab);
spin_lock(&info->lock);
if (info->attr.mq_curmsgs)
retval = EPOLLIN | EPOLLRDNORM;
if (info->attr.mq_curmsgs < info->attr.mq_maxmsg)
retval |= EPOLLOUT | EPOLLWRNORM;
spin_unlock(&info->lock);
return retval;
}
/* Adds current to info->e_wait_q[sr] before element with smaller prio */
static void wq_add(struct mqueue_inode_info *info, int sr,
struct ext_wait_queue *ewp)
{
struct ext_wait_queue *walk;
list_for_each_entry(walk, &info->e_wait_q[sr].list, list) {
if (walk->task->prio <= current->prio) {
list_add_tail(&ewp->list, &walk->list);
return;
}
}
list_add_tail(&ewp->list, &info->e_wait_q[sr].list);
}
/*
* Puts current task to sleep. Caller must hold queue lock. After return
* lock isn't held.
* sr: SEND or RECV
*/
static int wq_sleep(struct mqueue_inode_info *info, int sr,
ktime_t *timeout, struct ext_wait_queue *ewp)
__releases(&info->lock)
{
int retval;
signed long time;
wq_add(info, sr, ewp);
for (;;) {
/* memory barrier not required, we hold info->lock */
__set_current_state(TASK_INTERRUPTIBLE);
spin_unlock(&info->lock);
time = schedule_hrtimeout_range_clock(timeout, 0,
HRTIMER_MODE_ABS, CLOCK_REALTIME);
if (READ_ONCE(ewp->state) == STATE_READY) {
/* see MQ_BARRIER for purpose/pairing */
smp_acquire__after_ctrl_dep();
retval = 0;
goto out;
}
spin_lock(&info->lock);
/* we hold info->lock, so no memory barrier required */
if (READ_ONCE(ewp->state) == STATE_READY) {
retval = 0;
goto out_unlock;
}
if (signal_pending(current)) {
retval = -ERESTARTSYS;
break;
}
if (time == 0) {
retval = -ETIMEDOUT;
break;
}
}
list_del(&ewp->list);
out_unlock:
spin_unlock(&info->lock);
out:
return retval;
}
/*
* Returns waiting task that should be serviced first or NULL if none exists
*/
static struct ext_wait_queue *wq_get_first_waiter(
struct mqueue_inode_info *info, int sr)
{
struct list_head *ptr;
ptr = info->e_wait_q[sr].list.prev;
if (ptr == &info->e_wait_q[sr].list)
return NULL;
return list_entry(ptr, struct ext_wait_queue, list);
}
static inline void set_cookie(struct sk_buff *skb, char code)
{
((char *)skb->data)[NOTIFY_COOKIE_LEN-1] = code;
}
/*
* The next function is only to split too long sys_mq_timedsend
*/
static void __do_notify(struct mqueue_inode_info *info)
{
/* notification
* invoked when there is registered process and there isn't process
* waiting synchronously for message AND state of queue changed from
* empty to not empty. Here we are sure that no one is waiting
* synchronously. */
if (info->notify_owner &&
info->attr.mq_curmsgs == 1) {
switch (info->notify.sigev_notify) {
case SIGEV_NONE:
break;
case SIGEV_SIGNAL: {
struct kernel_siginfo sig_i;
struct task_struct *task;
/* do_mq_notify() accepts sigev_signo == 0, why?? */
if (!info->notify.sigev_signo)
break;
clear_siginfo(&sig_i);
sig_i.si_signo = info->notify.sigev_signo;
sig_i.si_errno = 0;
sig_i.si_code = SI_MESGQ;
sig_i.si_value = info->notify.sigev_value;
rcu_read_lock();
/* map current pid/uid into info->owner's namespaces */
sig_i.si_pid = task_tgid_nr_ns(current,
ns_of_pid(info->notify_owner));
sig_i.si_uid = from_kuid_munged(info->notify_user_ns,
current_uid());
/*
* We can't use kill_pid_info(), this signal should
* bypass check_kill_permission(). It is from kernel
* but si_fromuser() can't know this.
* We do check the self_exec_id, to avoid sending
* signals to programs that don't expect them.
*/
task = pid_task(info->notify_owner, PIDTYPE_TGID);
if (task && task->self_exec_id ==
info->notify_self_exec_id) {
do_send_sig_info(info->notify.sigev_signo,
&sig_i, task, PIDTYPE_TGID);
}
rcu_read_unlock();
break;
}
case SIGEV_THREAD:
set_cookie(info->notify_cookie, NOTIFY_WOKENUP);
netlink_sendskb(info->notify_sock, info->notify_cookie);
break;
}
/* after notification unregisters process */
put_pid(info->notify_owner);
put_user_ns(info->notify_user_ns);
info->notify_owner = NULL;
info->notify_user_ns = NULL;
}
wake_up(&info->wait_q);
}
static int prepare_timeout(const struct __kernel_timespec __user *u_abs_timeout,
struct timespec64 *ts)
{
if (get_timespec64(ts, u_abs_timeout))
return -EFAULT;
if (!timespec64_valid(ts))
return -EINVAL;
return 0;
}
static void remove_notification(struct mqueue_inode_info *info)
{
if (info->notify_owner != NULL &&
info->notify.sigev_notify == SIGEV_THREAD) {
set_cookie(info->notify_cookie, NOTIFY_REMOVED);
netlink_sendskb(info->notify_sock, info->notify_cookie);
}
put_pid(info->notify_owner);
put_user_ns(info->notify_user_ns);
info->notify_owner = NULL;
info->notify_user_ns = NULL;
}
static int prepare_open(struct dentry *dentry, int oflag, int ro,
umode_t mode, struct filename *name,
struct mq_attr *attr)
{
static const int oflag2acc[O_ACCMODE] = { MAY_READ, MAY_WRITE,
MAY_READ | MAY_WRITE };
int acc;
if (d_really_is_negative(dentry)) {
if (!(oflag & O_CREAT))
return -ENOENT;
if (ro)
return ro;
audit_inode_parent_hidden(name, dentry->d_parent);
return vfs_mkobj(dentry, mode & ~current_umask(),
mqueue_create_attr, attr);
}
/* it already existed */
audit_inode(name, dentry, 0);
if ((oflag & (O_CREAT|O_EXCL)) == (O_CREAT|O_EXCL))
return -EEXIST;
if ((oflag & O_ACCMODE) == (O_RDWR | O_WRONLY))
return -EINVAL;
acc = oflag2acc[oflag & O_ACCMODE];
return inode_permission(&init_user_ns, d_inode(dentry), acc);
}
static int do_mq_open(const char __user *u_name, int oflag, umode_t mode,
struct mq_attr *attr)
{
struct vfsmount *mnt = current->nsproxy->ipc_ns->mq_mnt;
struct dentry *root = mnt->mnt_root;
struct filename *name;
struct path path;
int fd, error;
int ro;
audit_mq_open(oflag, mode, attr);
if (IS_ERR(name = getname(u_name)))
return PTR_ERR(name);
fd = get_unused_fd_flags(O_CLOEXEC);
if (fd < 0)
goto out_putname;
ro = mnt_want_write(mnt); /* we'll drop it in any case */
inode_lock(d_inode(root));
path.dentry = lookup_one_len(name->name, root, strlen(name->name));
if (IS_ERR(path.dentry)) {
error = PTR_ERR(path.dentry);
goto out_putfd;
}
path.mnt = mntget(mnt);
error = prepare_open(path.dentry, oflag, ro, mode, name, attr);
if (!error) {
struct file *file = dentry_open(&path, oflag, current_cred());
if (!IS_ERR(file))
fd_install(fd, file);
else
error = PTR_ERR(file);
}
path_put(&path);
out_putfd:
if (error) {
put_unused_fd(fd);
fd = error;
}
inode_unlock(d_inode(root));
if (!ro)
mnt_drop_write(mnt);
out_putname:
putname(name);
return fd;
}
SYSCALL_DEFINE4(mq_open, const char __user *, u_name, int, oflag, umode_t, mode,
struct mq_attr __user *, u_attr)
{
struct mq_attr attr;
if (u_attr && copy_from_user(&attr, u_attr, sizeof(struct mq_attr)))
return -EFAULT;
return do_mq_open(u_name, oflag, mode, u_attr ? &attr : NULL);
}
SYSCALL_DEFINE1(mq_unlink, const char __user *, u_name)
{
int err;
struct filename *name;
struct dentry *dentry;
struct inode *inode = NULL;
struct ipc_namespace *ipc_ns = current->nsproxy->ipc_ns;
struct vfsmount *mnt = ipc_ns->mq_mnt;
name = getname(u_name);
if (IS_ERR(name))
return PTR_ERR(name);
audit_inode_parent_hidden(name, mnt->mnt_root);
err = mnt_want_write(mnt);
if (err)
goto out_name;
inode_lock_nested(d_inode(mnt->mnt_root), I_MUTEX_PARENT);
dentry = lookup_one_len(name->name, mnt->mnt_root,
strlen(name->name));
if (IS_ERR(dentry)) {
err = PTR_ERR(dentry);
goto out_unlock;
}
inode = d_inode(dentry);
if (!inode) {
err = -ENOENT;
} else {
ihold(inode);
err = vfs_unlink(&init_user_ns, d_inode(dentry->d_parent),
dentry, NULL);
}
dput(dentry);
out_unlock:
inode_unlock(d_inode(mnt->mnt_root));
if (inode)
iput(inode);
mnt_drop_write(mnt);
out_name:
putname(name);
return err;
}
/* Pipelined send and receive functions.
*
* If a receiver finds no waiting message, then it registers itself in the
* list of waiting receivers. A sender checks that list before adding the new
* message into the message array. If there is a waiting receiver, then it
* bypasses the message array and directly hands the message over to the
* receiver. The receiver accepts the message and returns without grabbing the
* queue spinlock:
*
* - Set pointer to message.
* - Queue the receiver task for later wakeup (without the info->lock).
* - Update its state to STATE_READY. Now the receiver can continue.
* - Wake up the process after the lock is dropped. Should the process wake up
* before this wakeup (due to a timeout or a signal) it will either see
* STATE_READY and continue or acquire the lock to check the state again.
*
* The same algorithm is used for senders.