aboutsummaryrefslogtreecommitdiffstats
path: root/arch/mips/kernel/signal.c
blob: d0c68b5d717bce3fde6979d2eeee5e5ac6ea7094 (plain) (blame)
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
/*
 * This file is subject to the terms and conditions of the GNU General Public
 * License.  See the file "COPYING" in the main directory of this archive
 * for more details.
 *
 * Copyright (C) 1991, 1992  Linus Torvalds
 * Copyright (C) 1994 - 2000  Ralf Baechle
 * Copyright (C) 1999, 2000 Silicon Graphics, Inc.
 */
#include <linux/cache.h>
#include <linux/sched.h>
#include <linux/mm.h>
#include <linux/personality.h>
#include <linux/smp.h>
#include <linux/kernel.h>
#include <linux/signal.h>
#include <linux/errno.h>
#include <linux/wait.h>
#include <linux/ptrace.h>
#include <linux/unistd.h>
#include <linux/compiler.h>
#include <linux/syscalls.h>
#include <linux/uaccess.h>
#include <linux/tracehook.h>

#include <asm/abi.h>
#include <asm/asm.h>
#include <linux/bitops.h>
#include <asm/cacheflush.h>
#include <asm/fpu.h>
#include <asm/sim.h>
#include <asm/ucontext.h>
#include <asm/cpu-features.h>
#include <asm/war.h>

#include "signal-common.h"

static int (*save_fp_context)(struct sigcontext __user *sc);
static int (*restore_fp_context)(struct sigcontext __user *sc);

extern asmlinkage int _save_fp_context(struct sigcontext __user *sc);
extern asmlinkage int _restore_fp_context(struct sigcontext __user *sc);

extern asmlinkage int fpu_emulator_save_context(struct sigcontext __user *sc);
extern asmlinkage int fpu_emulator_restore_context(struct sigcontext __user *sc);

/*
 * Horribly complicated - with the bloody RM9000 workarounds enabled
 * the signal trampolines is moving to the end of the structure so we can
 * increase the alignment without breaking software compatibility.
 */
#if ICACHE_REFILLS_WORKAROUND_WAR == 0

struct sigframe {
	u32 sf_ass[4];		/* argument save space for o32 */
	u32 sf_code[2];		/* signal trampoline */
	struct sigcontext sf_sc;
	sigset_t sf_mask;
};

struct rt_sigframe {
	u32 rs_ass[4];		/* argument save space for o32 */
	u32 rs_code[2];		/* signal trampoline */
	struct siginfo rs_info;
	struct ucontext rs_uc;
};

#else

struct sigframe {
	u32 sf_ass[4];			/* argument save space for o32 */
	u32 sf_pad[2];
	struct sigcontext sf_sc;	/* hw context */
	sigset_t sf_mask;
	u32 sf_code[8] ____cacheline_aligned;	/* signal trampoline */
};

struct rt_sigframe {
	u32 rs_ass[4];			/* argument save space for o32 */
	u32 rs_pad[2];
	struct siginfo rs_info;
	struct ucontext rs_uc;
	u32 rs_code[8] ____cacheline_aligned;	/* signal trampoline */
};

#endif

/*
 * Helper routines
 */
static int protected_save_fp_context(struct sigcontext __user *sc)
{
	int err;
	while (1) {
		lock_fpu_owner();
		own_fpu_inatomic(1);
		err = save_fp_context(sc); /* this might fail */
		unlock_fpu_owner();
		if (likely(!err))
			break;
		/* touch the sigcontext and try again */
		err = __put_user(0, &sc->sc_fpregs[0]) |
			__put_user(0, &sc->sc_fpregs[31]) |
			__put_user(0, &sc->sc_fpc_csr);
		if (err)
			break;	/* really bad sigcontext */
	}
	return err;
}

static int protected_restore_fp_context(struct sigcontext __user *sc)
{
	int err, tmp;
	while (1) {
		lock_fpu_owner();
		own_fpu_inatomic(0);
		err = restore_fp_context(sc); /* this might fail */
		unlock_fpu_owner();
		if (likely(!err))
			break;
		/* touch the sigcontext and try again */
		err = __get_user(tmp, &sc->sc_fpregs[0]) |
			__get_user(tmp, &sc->sc_fpregs[31]) |
			__get_user(tmp, &sc->sc_fpc_csr);
		if (err)
			break;	/* really bad sigcontext */
	}
	return err;
}

int setup_sigcontext(struct pt_regs *regs, struct sigcontext __user *sc)
{
	int err = 0;
	int i;
	unsigned int used_math;

	err |= __put_user(regs->cp0_epc, &sc->sc_pc);

	err |= __put_user(0, &sc->sc_regs[0]);
	for (i = 1; i < 32; i++)
		err |= __put_user(regs->regs[i], &sc->sc_regs[i]);

#ifdef CONFIG_CPU_HAS_SMARTMIPS
	err |= __put_user(regs->acx, &sc->sc_acx);
#endif
	err |= __put_user(regs->hi, &sc->sc_mdhi);
	err |= __put_user(regs->lo, &sc->sc_mdlo);
	if (cpu_has_dsp) {
		err |= __put_user(mfhi1(), &sc->sc_hi1);
		err |= __put_user(mflo1(), &sc->sc_lo1);
		err |= __put_user(mfhi2(), &sc->sc_hi2);
		err |= __put_user(mflo2(), &sc->sc_lo2);
		err |= __put_user(mfhi3(), &sc->sc_hi3);
		err |= __put_user(mflo3(), &sc->sc_lo3);
		err |= __put_user(rddsp(DSP_MASK), &sc->sc_dsp);
	}

	used_math = !!used_math();
	err |= __put_user(used_math, &sc->sc_used_math);

	if (used_math) {
		/*
		 * Save FPU state to signal context. Signal handler
		 * will "inherit" current FPU state.
		 */
		err |= protected_save_fp_context(sc);
	}
	return err;
}

int fpcsr_pending(unsigned int __user *fpcsr)
{
	int err, sig = 0;
	unsigned int csr, enabled;

	err = __get_user(csr, fpcsr);
	enabled = FPU_CSR_UNI_X | ((csr & FPU_CSR_ALL_E) << 5);
	/*
	 * If the signal handler set some FPU exceptions, clear it and
	 * send SIGFPE.
	 */
	if (csr & enabled) {
		csr &= ~enabled;
		err |= __put_user(csr, fpcsr);
		sig = SIGFPE;
	}
	return err ?: sig;
}

static int
check_and_restore_fp_context(struct sigcontext __user *sc)
{
	int err, sig;

	err = sig = fpcsr_pending(&sc->sc_fpc_csr);
	if (err > 0)
		err = 0;
	err |= protected_restore_fp_context(sc);
	return err ?: sig;
}

int restore_sigcontext(struct pt_regs *regs, struct sigcontext __user *sc)
{
	unsigned int used_math;
	unsigned long treg;
	int err = 0;
	int i;

	/* Always make any pending restarted system calls return -EINTR */
	current_thread_info()->restart_block.fn = do_no_restart_syscall;

	err |= __get_user(regs->cp0_epc, &sc->sc_pc);

#ifdef CONFIG_CPU_HAS_SMARTMIPS
	err |= __get_user(regs->acx, &sc->sc_acx);
#endif
	err |= __get_user(regs->hi, &sc->sc_mdhi);
	err |= __get_user(regs->lo, &sc->sc_mdlo);
	if (cpu_has_dsp) {
		err |= __get_user(treg, &sc->sc_hi1); mthi1(treg);
		err |= __get_user(treg, &sc->sc_lo1); mtlo1(treg);
		err |= __get_user(treg, &sc->sc_hi2); mthi2(treg);
		err |= __get_user(treg, &sc->sc_lo2); mtlo2(treg);
		err |= __get_user(treg, &sc->sc_hi3); mthi3(treg);
		err |= __get_user(treg, &sc->sc_lo3); mtlo3(treg);
		err |= __get_user(treg, &sc->sc_dsp); wrdsp(treg, DSP_MASK);
	}

	for (i = 1; i < 32; i++)
		err |= __get_user(regs->regs[i], &sc->sc_regs[i]);

	err |= __get_user(used_math, &sc->sc_used_math);
	conditional_used_math(used_math);

	if (used_math) {
		/* restore fpu context if we have used it before */
		if (!err)
			err = check_and_restore_fp_context(sc);
	} else {
		/* signal handler may have used FPU.  Give it up. */
		lose_fpu(0);
	}

	return err;
}

void __user *get_sigframe(struct k_sigaction *ka, struct pt_regs *regs,
			  size_t frame_size)
{
	unsigned long sp;

	/* Default to using normal stack */
	sp = regs->regs[29];

	/*
	 * FPU emulator may have it's own trampoline active just
	 * above the user stack, 16-bytes before the next lowest
	 * 16 byte boundary.  Try to avoid trashing it.
	 */
	sp -= 32;

	/* This is the X/Open sanctioned signal stack switching.  */
	if ((ka->sa.sa_flags & SA_ONSTACK) && (sas_ss_flags (sp) == 0))
		sp = current->sas_ss_sp + current->sas_ss_size;

	return (void __user *)((sp - frame_size) & (ICACHE_REFILLS_WORKAROUND_WAR ? ~(cpu_icache_line_size()-1) : ALMASK));
}

int install_sigtramp(unsigned int __user *tramp, unsigned int syscall)
{
	int err;

	/*
	 * Set up the return code ...
	 *
	 *         li      v0, __NR__foo_sigreturn
	 *         syscall
	 */

	err = __put_user(0x24020000 + syscall, tramp + 0);
	err |= __put_user(0x0000000c         , tramp + 1);
	if (ICACHE_REFILLS_WORKAROUND_WAR) {
		err |= __put_user(0, tramp + 2);
		err |= __put_user(0, tramp + 3);
		err |= __put_user(0, tramp + 4);
		err |= __put_user(0, tramp + 5);
		err |= __put_user(0, tramp + 6);
		err |= __put_user(0, tramp + 7);
	}
	flush_cache_sigtramp((unsigned long) tramp);

	return err;
}

/*
 * Atomically swap in the new signal mask, and wait for a signal.
 */

#ifdef CONFIG_TRAD_SIGNALS
asmlinkage int sys_sigsuspend(nabi_no_regargs struct pt_regs regs)
{
	sigset_t newset;
	sigset_t __user *uset;

	uset = (sigset_t __user *) regs.regs[4];
	if (copy_from_user(&newset, uset, sizeof(sigset_t)))
		return -EFAULT;
	sigdelsetmask(&newset, ~_BLOCKABLE);

	spin_lock_irq(&current->sighand->siglock);
	current->saved_sigmask = current->blocked;
	current->blocked = newset;
	recalc_sigpending();
	spin_unlock_irq(&current->sighand->siglock);

	current->state = TASK_INTERRUPTIBLE;
	schedule();
	set_thread_flag(TIF_RESTORE_SIGMASK);
	return -ERESTARTNOHAND;
}
#endif

asmlinkage int sys_rt_sigsuspend(nabi_no_regargs struct pt_regs regs)
{
	sigset_t newset;
	sigset_t __user *unewset;
	size_t sigsetsize;

	/* XXX Don't preclude handling different sized sigset_t's.  */
	sigsetsize = regs.regs[5];
	if (sigsetsize != sizeof(sigset_t))
		return -EINVAL;

	unewset = (sigset_t __user *) regs.regs[4];
	if (copy_from_user(&newset, unewset, sizeof(newset)))
		return -EFAULT;
	sigdelsetmask(&newset, ~_BLOCKABLE);

	spin_lock_irq(&current->sighand->siglock);
	current->saved_sigmask = current->blocked;
	current->blocked = newset;
	recalc_sigpending();
	spin_unlock_irq(&current->sighand->siglock);

	current->state = TASK_INTERRUPTIBLE;
	schedule();
	set_thread_flag(TIF_RESTORE_SIGMASK);
	return -ERESTARTNOHAND;
}

#ifdef CONFIG_TRAD_SIGNALS
SYSCALL_DEFINE3(sigaction, int, sig, const struct sigaction __user *, act,
	struct sigaction __user *, oact)
{
	struct k_sigaction new_ka, old_ka;
	int ret;
	int err = 0;

	if (act) {
		old_sigset_t mask;

		if (!access_ok(VERIFY_READ, act, sizeof(*act)))
			return -EFAULT;
		err |= __get_user(new_ka.sa.sa_handler, &act->sa_handler);
		err |= __get_user(new_ka.sa.sa_flags, &act->sa_flags);
		err |= __get_user(mask, &act->sa_mask.sig[0]);
		if (err)
			return -EFAULT;

		siginitset(&new_ka.sa.sa_mask, mask);
	}

	ret = do_sigaction(sig, act ? &new_ka : NULL, oact ? &old_ka : NULL);

	if (!ret && oact) {
		if (!access_ok(VERIFY_WRITE, oact, sizeof(*oact)))
			return -EFAULT;
		err |= __put_user(old_ka.sa.sa_flags, &oact->sa_flags);
		err |= __put_user(old_ka.sa.sa_handler, &oact->sa_handler);
		err |= __put_user(old_ka.sa.sa_mask.sig[0], oact->sa_mask.sig);
		err |= __put_user(0, &oact->sa_mask.sig[1]);
		err |= __put_user(0, &oact->sa_mask.sig[2]);
		err |= __put_user(0, &oact->sa_mask.sig[3]);
		if (err)
			return -EFAULT;
	}

	return ret;
}
#endif

asmlinkage int sys_sigaltstack(nabi_no_regargs struct pt_regs regs)
{
	const stack_t __user *uss = (const stack_t __user *) regs.regs[4];
	stack_t __user *uoss = (stack_t __user *) regs.regs[5];
	unsigned long usp = regs.regs[29];

	return do_sigaltstack(uss, uoss, usp);
}

#ifdef CONFIG_TRAD_SIGNALS
asmlinkage void sys_sigreturn(nabi_no_regargs struct pt_regs regs)
{
	struct sigframe __user *frame;
	sigset_t blocked;
	int sig;

	frame = (struct sigframe __user *) regs.regs[29];
	if (!access_ok(VERIFY_READ, frame, sizeof(*frame)))
		goto badframe;
	if (__copy_from_user(&blocked, &frame->sf_mask, sizeof(blocked)))
		goto badframe;

	sigdelsetmask(&blocked, ~_BLOCKABLE);
	spin_lock_irq(&current->sighand->siglock);
	current->blocked = blocked;
	recalc_sigpending();
	spin_unlock_irq(&current->sighand->siglock);

	sig = restore_sigcontext(&regs, &frame->sf_sc);
	if (sig < 0)
		goto badframe;
	else if (sig)
		force_sig(sig, current);

	/*
	 * Don't let your children do this ...
	 */
	__asm__ __volatile__(
		"move\t$29, %0\n\t"
		"j\tsyscall_exit"
		:/* no outputs */
		:"r" (&regs));
	/* Unreached */

badframe:
	force_sig(SIGSEGV, current);
}
#endif /* CONFIG_TRAD_SIGNALS */

asmlinkage void sys_rt_sigreturn(nabi_no_regargs struct pt_regs regs)
{
	struct rt_sigframe __user *frame;
	sigset_t set;
	stack_t st;
	int sig;

	frame = (struct rt_sigframe __user *) regs.regs[29];
	if (!access_ok(VERIFY_READ, frame, sizeof(*frame)))
		goto badframe;
	if (__copy_from_user(&set, &frame->rs_uc.uc_sigmask, sizeof(set)))
		goto badframe;

	sigdelsetmask(&set, ~_BLOCKABLE);
	spin_lock_irq(&current->sighand->siglock);
	current->blocked = set;
	recalc_sigpending();
	spin_unlock_irq(&current->sighand->siglock);

	sig = restore_sigcontext(&regs, &frame->rs_uc.uc_mcontext);
	if (sig < 0)
		goto badframe;
	else if (sig)
		force_sig(sig, current);

	if (__copy_from_user(&st, &frame->rs_uc.uc_stack, sizeof(st)))
		goto badframe;
	/* It is more difficult to avoid calling this function than to
	   call it and ignore errors.  */
	do_sigaltstack((stack_t __user *)&st, NULL, regs.regs[29]);

	/*
	 * Don't let your children do this ...
	 */
	__asm__ __volatile__(
		"move\t$29, %0\n\t"
		"j\tsyscall_exit"
		:/* no outputs */
		:"r" (&regs));
	/* Unreached */

badframe:
	force_sig(SIGSEGV, current);
}

#ifdef CONFIG_TRAD_SIGNALS
static int setup_frame(struct k_sigaction * ka, struct pt_regs *regs,
	int signr, sigset_t *set)
{
	struct sigframe __user *frame;
	int err = 0;

	frame = get_sigframe(ka, regs, sizeof(*frame));
	if (!access_ok(VERIFY_WRITE, frame, sizeof (*frame)))
		goto give_sigsegv;

	err |= install_sigtramp(frame->sf_code, __NR_sigreturn);

	err |= setup_sigcontext(regs, &frame->sf_sc);
	err |= __copy_to_user(&frame->sf_mask, set, sizeof(*set));
	if (err)
		goto give_sigsegv;

	/*
	 * Arguments to signal handler:
	 *
	 *   a0 = signal number
	 *   a1 = 0 (should be cause)
	 *   a2 = pointer to struct sigcontext
	 *
	 * $25 and c0_epc point to the signal handler, $29 points to the
	 * struct sigframe.
	 */
	regs->regs[ 4] = signr;
	regs->regs[ 5] = 0;
	regs->regs[ 6] = (unsigned long) &frame->sf_sc;
	regs->regs[29] = (unsigned long) frame;
	regs->regs[31] = (unsigned long) frame->sf_code;
	regs->cp0_epc = regs->regs[25] = (unsigned long) ka->sa.sa_handler;

	DEBUGP("SIG deliver (%s:%d): sp=0x%p pc=0x%lx ra=0x%lx\n",
	       current->comm, current->pid,
	       frame, regs->cp0_epc, regs->regs[31]);
	return 0;

give_sigsegv:
	force_sigsegv(signr, current);
	return -EFAULT;
}
#endif

static int setup_rt_frame(struct k_sigaction * ka, struct pt_regs *regs,
	int signr, sigset_t *set, siginfo_t *info)
{
	struct rt_sigframe __user *frame;
	int err = 0;

	frame = get_sigframe(ka, regs, sizeof(*frame));
	if (!access_ok(VERIFY_WRITE, frame, sizeof (*frame)))
		goto give_sigsegv;

	err |= install_sigtramp(frame->rs_code, __NR_rt_sigreturn);

	/* Create siginfo.  */
	err |= copy_siginfo_to_user(&frame->rs_info, info);

	/* Create the ucontext.  */
	err |= __put_user(0, &frame->rs_uc.uc_flags);
	err |= __put_user(NULL, &frame->rs_uc.uc_link);
	err |= __put_user((void __user *)current->sas_ss_sp,
	                  &frame->rs_uc.uc_stack.ss_sp);
	err |= __put_user(sas_ss_flags(regs->regs[29]),
	                  &frame->rs_uc.uc_stack.ss_flags);
	err |= __put_user(current->sas_ss_size,
	                  &frame->rs_uc.uc_stack.ss_size);
	err |= setup_sigcontext(regs, &frame->rs_uc.uc_mcontext);
	err |= __copy_to_user(&frame->rs_uc.uc_sigmask, set, sizeof(*set));

	if (err)
		goto give_sigsegv;

	/*
	 * Arguments to signal handler:
	 *
	 *   a0 = signal number
	 *   a1 = 0 (should be cause)
	 *   a2 = pointer to ucontext
	 *
	 * $25 and c0_epc point to the signal handler, $29 points to
	 * the struct rt_sigframe.
	 */
	regs->regs[ 4] = signr;
	regs->regs[ 5] = (unsigned long) &frame->rs_info;
	regs->regs[ 6] = (unsigned long) &frame->rs_uc;
	regs->regs[29] = (unsigned long) frame;
	regs->regs[31] = (unsigned long) frame->rs_code;
	regs->cp0_epc = regs->regs[25] = (unsigned long) ka->sa.sa_handler;

	DEBUGP("SIG deliver (%s:%d): sp=0x%p pc=0x%lx ra=0x%lx\n",
	       current->comm, current->pid,
	       frame, regs->cp0_epc, regs->regs[31]);

	return 0;

give_sigsegv:
	force_sigsegv(signr, current);
	return -EFAULT;
}

struct mips_abi mips_abi = {
#ifdef CONFIG_TRAD_SIGNALS
	.setup_frame	= setup_frame,
#endif
	.setup_rt_frame	= setup_rt_frame,
	.restart	= __NR_restart_syscall
};

static int handle_signal(unsigned long sig, siginfo_t *info,
	struct k_sigaction *ka, sigset_t *oldset, struct pt_regs *regs)
{
	int ret;

	switch(regs->regs[0]) {
	case ERESTART_RESTARTBLOCK:
	case ERESTARTNOHAND:
		regs->regs[2] = EINTR;
		break;
	case ERESTARTSYS:
		if (!(ka->sa.sa_flags & SA_RESTART)) {
			regs->regs[2] = EINTR;
			break;
		}
	/* fallthrough */
	case ERESTARTNOINTR:		/* Userland will reload $v0.  */
		regs->regs[7] = regs->regs[26];
		regs->cp0_epc -= 8;
	}

	regs->regs[0] = 0;		/* Don't deal with this again.  */

	if (sig_uses_siginfo(ka))
		ret = current->thread.abi->setup_rt_frame(ka, regs, sig, oldset, info);
	else
		ret = current->thread.abi->setup_frame(ka, regs, sig, oldset);

	spin_lock_irq(&current->sighand->siglock);
	sigorsets(&current->blocked, &current->blocked, &ka->sa.sa_mask);
	if (!(ka->sa.sa_flags & SA_NODEFER))
		sigaddset(&current->blocked, sig);
	recalc_sigpending();
	spin_unlock_irq(&current->sighand->siglock);

	return ret;
}

static void do_signal(struct pt_regs *regs)
{
	struct k_sigaction ka;
	sigset_t *oldset;
	siginfo_t info;
	int signr;

	/*
	 * We want the common case to go fast, which is why we may in certain
	 * cases get here from kernel mode. Just return without doing anything
	 * if so.
	 */
	if (!user_mode(regs))
		return;

	if (test_thread_flag(TIF_RESTORE_SIGMASK))
		oldset = &current->saved_sigmask;
	else
		oldset = &current->blocked;

	signr = get_signal_to_deliver(&info, &ka, regs, NULL);
	if (signr > 0) {
		/* Whee!  Actually deliver the signal.  */
		if (handle_signal(signr, &info, &ka, oldset, regs) == 0) {
			/*
			 * A signal was successfully delivered; the saved
			 * sigmask will have been stored in the signal frame,
			 * and will be restored by sigreturn, so we can simply
			 * clear the TIF_RESTORE_SIGMASK flag.
			 */
			if (test_thread_flag(TIF_RESTORE_SIGMASK))
				clear_thread_flag(TIF_RESTORE_SIGMASK);
		}

		return;
	}

	/*
	 * Who's code doesn't conform to the restartable syscall convention
	 * dies here!!!  The li instruction, a single machine instruction,
	 * must directly be followed by the syscall instruction.
	 */
	if (regs->regs[0]) {
		if (regs->regs[2] == ERESTARTNOHAND ||
		    regs->regs[2] == ERESTARTSYS ||
		    regs->regs[2] == ERESTARTNOINTR) {
			regs->regs[7] = regs->regs[26];
			regs->cp0_epc -= 8;
		}
		if (regs->regs[2] == ERESTART_RESTARTBLOCK) {
			regs->regs[2] = current->thread.abi->restart;
			regs->regs[7] = regs->regs[26];
			regs->cp0_epc -= 4;
		}
		regs->regs[0] = 0;	/* Don't deal with this again.  */
	}

	/*
	 * If there's no signal to deliver, we just put the saved sigmask
	 * back
	 */
	if (test_thread_flag(TIF_RESTORE_SIGMASK)) {
		clear_thread_flag(TIF_RESTORE_SIGMASK);
		sigprocmask(SIG_SETMASK, &current->saved_sigmask, NULL);
	}
}

/*
 * notification of userspace execution resumption
 * - triggered by the TIF_WORK_MASK flags
 */
asmlinkage void do_notify_resume(struct pt_regs *regs, void *unused,
	__u32 thread_info_flags)
{
	/* deal with pending signal delivery */
	if (thread_info_flags & (_TIF_SIGPENDING | _TIF_RESTORE_SIGMASK))
		do_signal(regs);

	if (thread_info_flags & _TIF_NOTIFY_RESUME) {
		clear_thread_flag(TIF_NOTIFY_RESUME);
		tracehook_notify_resume(regs);
		if (current->replacement_session_keyring)
			key_replace_session_keyring();
	}
}

#ifdef CONFIG_SMP
static int smp_save_fp_context(struct sigcontext __user *sc)
{
	return raw_cpu_has_fpu
	       ? _save_fp_context(sc)
	       : fpu_emulator_save_context(sc);
}

static int smp_restore_fp_context(struct sigcontext __user *sc)
{
	return raw_cpu_has_fpu
	       ? _restore_fp_context(sc)
	       : fpu_emulator_restore_context(sc);
}
#endif

static int signal_setup(void)
{
#ifdef CONFIG_SMP
	/* For now just do the cpu_has_fpu check when the functions are invoked */
	save_fp_context = smp_save_fp_context;
	restore_fp_context = smp_restore_fp_context;
#else
	if (cpu_has_fpu) {
		save_fp_context = _save_fp_context;
		restore_fp_context = _restore_fp_context;
	} else {
		save_fp_context = fpu_emulator_save_context;
		restore_fp_context = fpu_emulator_restore_context;
	}
#endif

	return 0;
}

arch_initcall(signal_setup);
s="hl opt">)) ret = -ENOSPC; if (test_and_clear_bit(AS_EIO, &mapping->flags)) ret = -EIO; return ret; } EXPORT_SYMBOL(filemap_fdatawait_range); /** * filemap_fdatawait - wait for all under-writeback pages to complete * @mapping: address space structure to wait for * * Walk the list of under-writeback pages of the given address space * and wait for all of them. */ int filemap_fdatawait(struct address_space *mapping) { loff_t i_size = i_size_read(mapping->host); if (i_size == 0) return 0; return filemap_fdatawait_range(mapping, 0, i_size - 1); } EXPORT_SYMBOL(filemap_fdatawait); int filemap_write_and_wait(struct address_space *mapping) { int err = 0; if (mapping->nrpages) { err = filemap_fdatawrite(mapping); /* * Even if the above returned error, the pages may be * written partially (e.g. -ENOSPC), so we wait for it. * But the -EIO is special case, it may indicate the worst * thing (e.g. bug) happened, so we avoid waiting for it. */ if (err != -EIO) { int err2 = filemap_fdatawait(mapping); if (!err) err = err2; } } return err; } EXPORT_SYMBOL(filemap_write_and_wait); /** * filemap_write_and_wait_range - write out & wait on a file range * @mapping: the address_space for the pages * @lstart: offset in bytes where the range starts * @lend: offset in bytes where the range ends (inclusive) * * Write out and wait upon file offsets lstart->lend, inclusive. * * Note that `lend' is inclusive (describes the last byte to be written) so * that this function can be used to write to the very end-of-file (end = -1). */ int filemap_write_and_wait_range(struct address_space *mapping, loff_t lstart, loff_t lend) { int err = 0; if (mapping->nrpages) { err = __filemap_fdatawrite_range(mapping, lstart, lend, WB_SYNC_ALL); /* See comment of filemap_write_and_wait() */ if (err != -EIO) { int err2 = filemap_fdatawait_range(mapping, lstart, lend); if (!err) err = err2; } } return err; } EXPORT_SYMBOL(filemap_write_and_wait_range); /** * add_to_page_cache_locked - add a locked page to the pagecache * @page: page to add * @mapping: the page's address_space * @offset: page index * @gfp_mask: page allocation mode * * This function is used to add a page to the pagecache. It must be locked. * This function does not add the page to the LRU. The caller must do that. */ int add_to_page_cache_locked(struct page *page, struct address_space *mapping, pgoff_t offset, gfp_t gfp_mask) { int error; VM_BUG_ON(!PageLocked(page)); error = mem_cgroup_cache_charge(page, current->mm, gfp_mask & GFP_RECLAIM_MASK); if (error) goto out; error = radix_tree_preload(gfp_mask & ~__GFP_HIGHMEM); if (error == 0) { page_cache_get(page); page->mapping = mapping; page->index = offset; spin_lock_irq(&mapping->tree_lock); error = radix_tree_insert(&mapping->page_tree, offset, page); if (likely(!error)) { mapping->nrpages++; __inc_zone_page_state(page, NR_FILE_PAGES); if (PageSwapBacked(page)) __inc_zone_page_state(page, NR_SHMEM); spin_unlock_irq(&mapping->tree_lock); } else { page->mapping = NULL; spin_unlock_irq(&mapping->tree_lock); mem_cgroup_uncharge_cache_page(page); page_cache_release(page); } radix_tree_preload_end(); } else mem_cgroup_uncharge_cache_page(page); out: return error; } EXPORT_SYMBOL(add_to_page_cache_locked); int add_to_page_cache_lru(struct page *page, struct address_space *mapping, pgoff_t offset, gfp_t gfp_mask) { int ret; /* * Splice_read and readahead add shmem/tmpfs pages into the page cache * before shmem_readpage has a chance to mark them as SwapBacked: they * need to go on the anon lru below, and mem_cgroup_cache_charge * (called in add_to_page_cache) needs to know where they're going too. */ if (mapping_cap_swap_backed(mapping)) SetPageSwapBacked(page); ret = add_to_page_cache(page, mapping, offset, gfp_mask); if (ret == 0) { if (page_is_file_cache(page)) lru_cache_add_file(page); else lru_cache_add_anon(page); } return ret; } EXPORT_SYMBOL_GPL(add_to_page_cache_lru); #ifdef CONFIG_NUMA struct page *__page_cache_alloc(gfp_t gfp) { int n; struct page *page; if (cpuset_do_page_mem_spread()) { get_mems_allowed(); n = cpuset_mem_spread_node(); page = alloc_pages_exact_node(n, gfp, 0); put_mems_allowed(); return page; } return alloc_pages(gfp, 0); } EXPORT_SYMBOL(__page_cache_alloc); #endif static int __sleep_on_page_lock(void *word) { io_schedule(); return 0; } /* * In order to wait for pages to become available there must be * waitqueues associated with pages. By using a hash table of * waitqueues where the bucket discipline is to maintain all * waiters on the same queue and wake all when any of the pages * become available, and for the woken contexts to check to be * sure the appropriate page became available, this saves space * at a cost of "thundering herd" phenomena during rare hash * collisions. */ static wait_queue_head_t *page_waitqueue(struct page *page) { const struct zone *zone = page_zone(page); return &zone->wait_table[hash_ptr(page, zone->wait_table_bits)]; } static inline void wake_up_page(struct page *page, int bit) { __wake_up_bit(page_waitqueue(page), &page->flags, bit); } void wait_on_page_bit(struct page *page, int bit_nr) { DEFINE_WAIT_BIT(wait, &page->flags, bit_nr); if (test_bit(bit_nr, &page->flags)) __wait_on_bit(page_waitqueue(page), &wait, sync_page, TASK_UNINTERRUPTIBLE); } EXPORT_SYMBOL(wait_on_page_bit); /** * add_page_wait_queue - Add an arbitrary waiter to a page's wait queue * @page: Page defining the wait queue of interest * @waiter: Waiter to add to the queue * * Add an arbitrary @waiter to the wait queue for the nominated @page. */ void add_page_wait_queue(struct page *page, wait_queue_t *waiter) { wait_queue_head_t *q = page_waitqueue(page); unsigned long flags; spin_lock_irqsave(&q->lock, flags); __add_wait_queue(q, waiter); spin_unlock_irqrestore(&q->lock, flags); } EXPORT_SYMBOL_GPL(add_page_wait_queue); /** * unlock_page - unlock a locked page * @page: the page * * Unlocks the page and wakes up sleepers in ___wait_on_page_locked(). * Also wakes sleepers in wait_on_page_writeback() because the wakeup * mechananism between PageLocked pages and PageWriteback pages is shared. * But that's OK - sleepers in wait_on_page_writeback() just go back to sleep. * * The mb is necessary to enforce ordering between the clear_bit and the read * of the waitqueue (to avoid SMP races with a parallel wait_on_page_locked()). */ void unlock_page(struct page *page) { VM_BUG_ON(!PageLocked(page)); clear_bit_unlock(PG_locked, &page->flags); smp_mb__after_clear_bit(); wake_up_page(page, PG_locked); } EXPORT_SYMBOL(unlock_page); /** * end_page_writeback - end writeback against a page * @page: the page */ void end_page_writeback(struct page *page) { if (TestClearPageReclaim(page)) rotate_reclaimable_page(page); if (!test_clear_page_writeback(page)) BUG(); smp_mb__after_clear_bit(); wake_up_page(page, PG_writeback); } EXPORT_SYMBOL(end_page_writeback); /** * __lock_page - get a lock on the page, assuming we need to sleep to get it * @page: the page to lock * * Ugly. Running sync_page() in state TASK_UNINTERRUPTIBLE is scary. If some * random driver's requestfn sets TASK_RUNNING, we could busywait. However * chances are that on the second loop, the block layer's plug list is empty, * so sync_page() will then return in state TASK_UNINTERRUPTIBLE. */ void __lock_page(struct page *page) { DEFINE_WAIT_BIT(wait, &page->flags, PG_locked); __wait_on_bit_lock(page_waitqueue(page), &wait, sync_page, TASK_UNINTERRUPTIBLE); } EXPORT_SYMBOL(__lock_page); int __lock_page_killable(struct page *page) { DEFINE_WAIT_BIT(wait, &page->flags, PG_locked); return __wait_on_bit_lock(page_waitqueue(page), &wait, sync_page_killable, TASK_KILLABLE); } EXPORT_SYMBOL_GPL(__lock_page_killable); /** * __lock_page_nosync - get a lock on the page, without calling sync_page() * @page: the page to lock * * Variant of lock_page that does not require the caller to hold a reference * on the page's mapping. */ void __lock_page_nosync(struct page *page) { DEFINE_WAIT_BIT(wait, &page->flags, PG_locked); __wait_on_bit_lock(page_waitqueue(page), &wait, __sleep_on_page_lock, TASK_UNINTERRUPTIBLE); } int __lock_page_or_retry(struct page *page, struct mm_struct *mm, unsigned int flags) { if (!(flags & FAULT_FLAG_ALLOW_RETRY)) { __lock_page(page); return 1; } else { up_read(&mm->mmap_sem); wait_on_page_locked(page); return 0; } } /** * find_get_page - find and get a page reference * @mapping: the address_space to search * @offset: the page index * * Is there a pagecache struct page at the given (mapping, offset) tuple? * If yes, increment its refcount and return it; if no, return NULL. */ struct page *find_get_page(struct address_space *mapping, pgoff_t offset) { void **pagep; struct page *page; rcu_read_lock(); repeat: page = NULL; pagep = radix_tree_lookup_slot(&mapping->page_tree, offset); if (pagep) { page = radix_tree_deref_slot(pagep); if (unlikely(!page)) goto out; if (radix_tree_deref_retry(page)) goto repeat; if (!page_cache_get_speculative(page)) goto repeat; /* * Has the page moved? * This is part of the lockless pagecache protocol. See * include/linux/pagemap.h for details. */ if (unlikely(page != *pagep)) { page_cache_release(page); goto repeat; } } out: rcu_read_unlock(); return page; } EXPORT_SYMBOL(find_get_page); /** * find_lock_page - locate, pin and lock a pagecache page * @mapping: the address_space to search * @offset: the page index * * Locates the desired pagecache page, locks it, increments its reference * count and returns its address. * * Returns zero if the page was not present. find_lock_page() may sleep. */ struct page *find_lock_page(struct address_space *mapping, pgoff_t offset) { struct page *page; repeat: page = find_get_page(mapping, offset); if (page) { lock_page(page); /* Has the page been truncated? */ if (unlikely(page->mapping != mapping)) { unlock_page(page); page_cache_release(page); goto repeat; } VM_BUG_ON(page->index != offset); } return page; } EXPORT_SYMBOL(find_lock_page); /** * find_or_create_page - locate or add a pagecache page * @mapping: the page's address_space * @index: the page's index into the mapping * @gfp_mask: page allocation mode * * Locates a page in the pagecache. If the page is not present, a new page * is allocated using @gfp_mask and is added to the pagecache and to the VM's * LRU list. The returned page is locked and has its reference count * incremented. * * find_or_create_page() may sleep, even if @gfp_flags specifies an atomic * allocation! * * find_or_create_page() returns the desired page's address, or zero on * memory exhaustion. */ struct page *find_or_create_page(struct address_space *mapping, pgoff_t index, gfp_t gfp_mask) { struct page *page; int err; repeat: page = find_lock_page(mapping, index); if (!page) { page = __page_cache_alloc(gfp_mask); if (!page) return NULL; /* * We want a regular kernel memory (not highmem or DMA etc) * allocation for the radix tree nodes, but we need to honour * the context-specific requirements the caller has asked for. * GFP_RECLAIM_MASK collects those requirements. */ err = add_to_page_cache_lru(page, mapping, index, (gfp_mask & GFP_RECLAIM_MASK)); if (unlikely(err)) { page_cache_release(page); page = NULL; if (err == -EEXIST) goto repeat; } } return page; } EXPORT_SYMBOL(find_or_create_page); /** * find_get_pages - gang pagecache lookup * @mapping: The address_space to search * @start: The starting page index * @nr_pages: The maximum number of pages * @pages: Where the resulting pages are placed * * find_get_pages() will search for and return a group of up to * @nr_pages pages in the mapping. The pages are placed at @pages. * find_get_pages() takes a reference against the returned pages. * * The search returns a group of mapping-contiguous pages with ascending * indexes. There may be holes in the indices due to not-present pages. * * find_get_pages() returns the number of pages which were found. */ unsigned find_get_pages(struct address_space *mapping, pgoff_t start, unsigned int nr_pages, struct page **pages) { unsigned int i; unsigned int ret; unsigned int nr_found; rcu_read_lock(); restart: nr_found = radix_tree_gang_lookup_slot(&mapping->page_tree, (void ***)pages, start, nr_pages); ret = 0; for (i = 0; i < nr_found; i++) { struct page *page; repeat: page = radix_tree_deref_slot((void **)pages[i]); if (unlikely(!page)) continue; if (radix_tree_deref_retry(page)) { if (ret) start = pages[ret-1]->index; goto restart; } if (!page_cache_get_speculative(page)) goto repeat; /* Has the page moved? */ if (unlikely(page != *((void **)pages[i]))) { page_cache_release(page); goto repeat; } pages[ret] = page; ret++; } rcu_read_unlock(); return ret; } /** * find_get_pages_contig - gang contiguous pagecache lookup * @mapping: The address_space to search * @index: The starting page index * @nr_pages: The maximum number of pages * @pages: Where the resulting pages are placed * * find_get_pages_contig() works exactly like find_get_pages(), except * that the returned number of pages are guaranteed to be contiguous. * * find_get_pages_contig() returns the number of pages which were found. */ unsigned find_get_pages_contig(struct address_space *mapping, pgoff_t index, unsigned int nr_pages, struct page **pages) { unsigned int i; unsigned int ret; unsigned int nr_found; rcu_read_lock(); restart: nr_found = radix_tree_gang_lookup_slot(&mapping->page_tree, (void ***)pages, index, nr_pages); ret = 0; for (i = 0; i < nr_found; i++) { struct page *page; repeat: page = radix_tree_deref_slot((void **)pages[i]); if (unlikely(!page)) continue; if (radix_tree_deref_retry(page)) goto restart; if (page->mapping == NULL || page->index != index) break; if (!page_cache_get_speculative(page)) goto repeat; /* Has the page moved? */ if (unlikely(page != *((void **)pages[i]))) { page_cache_release(page); goto repeat; } pages[ret] = page; ret++; index++; } rcu_read_unlock(); return ret; } EXPORT_SYMBOL(find_get_pages_contig); /** * find_get_pages_tag - find and return pages that match @tag * @mapping: the address_space to search * @index: the starting page index * @tag: the tag index * @nr_pages: the maximum number of pages * @pages: where the resulting pages are placed * * Like find_get_pages, except we only return pages which are tagged with * @tag. We update @index to index the next page for the traversal. */ unsigned find_get_pages_tag(struct address_space *mapping, pgoff_t *index, int tag, unsigned int nr_pages, struct page **pages) { unsigned int i; unsigned int ret; unsigned int nr_found; rcu_read_lock(); restart: nr_found = radix_tree_gang_lookup_tag_slot(&mapping->page_tree, (void ***)pages, *index, nr_pages, tag); ret = 0; for (i = 0; i < nr_found; i++) { struct page *page; repeat: page = radix_tree_deref_slot((void **)pages[i]); if (unlikely(!page)) continue; if (radix_tree_deref_retry(page)) goto restart; if (!page_cache_get_speculative(page)) goto repeat; /* Has the page moved? */ if (unlikely(page != *((void **)pages[i]))) { page_cache_release(page); goto repeat; } pages[ret] = page; ret++; } rcu_read_unlock(); if (ret) *index = pages[ret - 1]->index + 1; return ret; } EXPORT_SYMBOL(find_get_pages_tag); /** * grab_cache_page_nowait - returns locked page at given index in given cache * @mapping: target address_space * @index: the page index * * Same as grab_cache_page(), but do not wait if the page is unavailable. * This is intended for speculative data generators, where the data can * be regenerated if the page couldn't be grabbed. This routine should * be safe to call while holding the lock for another page. * * Clear __GFP_FS when allocating the page to avoid recursion into the fs * and deadlock against the caller's locked page. */ struct page * grab_cache_page_nowait(struct address_space *mapping, pgoff_t index) { struct page *page = find_get_page(mapping, index); if (page) { if (trylock_page(page)) return page; page_cache_release(page); return NULL; } page = __page_cache_alloc(mapping_gfp_mask(mapping) & ~__GFP_FS); if (page && add_to_page_cache_lru(page, mapping, index, GFP_NOFS)) { page_cache_release(page); page = NULL; } return page; } EXPORT_SYMBOL(grab_cache_page_nowait); /* * CD/DVDs are error prone. When a medium error occurs, the driver may fail * a _large_ part of the i/o request. Imagine the worst scenario: * * ---R__________________________________________B__________ * ^ reading here ^ bad block(assume 4k) * * read(R) => miss => readahead(R...B) => media error => frustrating retries * => failing the whole request => read(R) => read(R+1) => * readahead(R+1...B+1) => bang => read(R+2) => read(R+3) => * readahead(R+3...B+2) => bang => read(R+3) => read(R+4) => * readahead(R+4...B+3) => bang => read(R+4) => read(R+5) => ...... * * It is going insane. Fix it by quickly scaling down the readahead size. */ static void shrink_readahead_size_eio(struct file *filp, struct file_ra_state *ra) { ra->ra_pages /= 4; } /** * do_generic_file_read - generic file read routine * @filp: the file to read * @ppos: current file position * @desc: read_descriptor * @actor: read method * * This is a generic file read routine, and uses the * mapping->a_ops->readpage() function for the actual low-level stuff. * * This is really ugly. But the goto's actually try to clarify some * of the logic when it comes to error handling etc. */ static void do_generic_file_read(struct file *filp, loff_t *ppos, read_descriptor_t *desc, read_actor_t actor) { struct address_space *mapping = filp->f_mapping; struct inode *inode = mapping->host; struct file_ra_state *ra = &filp->f_ra; pgoff_t index; pgoff_t last_index; pgoff_t prev_index; unsigned long offset; /* offset into pagecache page */ unsigned int prev_offset; int error; index = *ppos >> PAGE_CACHE_SHIFT; prev_index = ra->prev_pos >> PAGE_CACHE_SHIFT; prev_offset = ra->prev_pos & (PAGE_CACHE_SIZE-1); last_index = (*ppos + desc->count + PAGE_CACHE_SIZE-1) >> PAGE_CACHE_SHIFT; offset = *ppos & ~PAGE_CACHE_MASK; for (;;) { struct page *page; pgoff_t end_index; loff_t isize; unsigned long nr, ret; cond_resched(); find_page: page = find_get_page(mapping, index); if (!page) { page_cache_sync_readahead(mapping, ra, filp, index, last_index - index); page = find_get_page(mapping, index); if (unlikely(page == NULL)) goto no_cached_page; } if (PageReadahead(page)) { page_cache_async_readahead(mapping, ra, filp, page, index, last_index - index); } if (!PageUptodate(page)) { if (inode->i_blkbits == PAGE_CACHE_SHIFT || !mapping->a_ops->is_partially_uptodate) goto page_not_up_to_date; if (!trylock_page(page)) goto page_not_up_to_date; /* Did it get truncated before we got the lock? */ if (!page->mapping) goto page_not_up_to_date_locked; if (!mapping->a_ops->is_partially_uptodate(page, desc, offset)) goto page_not_up_to_date_locked; unlock_page(page); } page_ok: /* * i_size must be checked after we know the page is Uptodate. * * Checking i_size after the check allows us to calculate * the correct value for "nr", which means the zero-filled * part of the page is not copied back to userspace (unless * another truncate extends the file - this is desired though). */ isize = i_size_read(inode); end_index = (isize - 1) >> PAGE_CACHE_SHIFT; if (unlikely(!isize || index > end_index)) { page_cache_release(page); goto out; } /* nr is the maximum number of bytes to copy from this page */ nr = PAGE_CACHE_SIZE; if (index == end_index) { nr = ((isize - 1) & ~PAGE_CACHE_MASK) + 1; if (nr <= offset) { page_cache_release(page); goto out; } } nr = nr - offset; /* If users can be writing to this page using arbitrary * virtual addresses, take care about potential aliasing * before reading the page on the kernel side. */ if (mapping_writably_mapped(mapping)) flush_dcache_page(page); /* * When a sequential read accesses a page several times, * only mark it as accessed the first time. */ if (prev_index != index || offset != prev_offset) mark_page_accessed(page); prev_index = index; /* * Ok, we have the page, and it's up-to-date, so * now we can copy it to user space... * * The actor routine returns how many bytes were actually used.. * NOTE! This may not be the same as how much of a user buffer * we filled up (we may be padding etc), so we can only update * "pos" here (the actor routine has to update the user buffer * pointers and the remaining count). */ ret = actor(desc, page, offset, nr); offset += ret; index += offset >> PAGE_CACHE_SHIFT; offset &= ~PAGE_CACHE_MASK; prev_offset = offset; page_cache_release(page); if (ret == nr && desc->count) continue; goto out; page_not_up_to_date: /* Get exclusive access to the page ... */ error = lock_page_killable(page); if (unlikely(error)) goto readpage_error; page_not_up_to_date_locked: /* Did it get truncated before we got the lock? */ if (!page->mapping) { unlock_page(page); page_cache_release(page); continue; } /* Did somebody else fill it already? */ if (PageUptodate(page)) { unlock_page(page); goto page_ok; } readpage: /* * A previous I/O error may have been due to temporary * failures, eg. multipath errors. * PG_error will be set again if readpage fails. */ ClearPageError(page); /* Start the actual read. The read will unlock the page. */ error = mapping->a_ops->readpage(filp, page); if (unlikely(error)) { if (error == AOP_TRUNCATED_PAGE) { page_cache_release(page); goto find_page; } goto readpage_error; } if (!PageUptodate(page)) { error = lock_page_killable(page); if (unlikely(error)) goto readpage_error; if (!PageUptodate(page)) { if (page->mapping == NULL) { /* * invalidate_mapping_pages got it */ unlock_page(page); page_cache_release(page); goto find_page; } unlock_page(page); shrink_readahead_size_eio(filp, ra); error = -EIO; goto readpage_error; } unlock_page(page); } goto page_ok; readpage_error: /* UHHUH! A synchronous read error occurred. Report it */ desc->error = error; page_cache_release(page); goto out; no_cached_page: /* * Ok, it wasn't cached, so we need to create a new * page.. */ page = page_cache_alloc_cold(mapping); if (!page) { desc->error = -ENOMEM; goto out; } error = add_to_page_cache_lru(page, mapping, index, GFP_KERNEL); if (error) { page_cache_release(page); if (error == -EEXIST) goto find_page; desc->error = error; goto out; } goto readpage; } out: ra->prev_pos = prev_index; ra->prev_pos <<= PAGE_CACHE_SHIFT; ra->prev_pos |= prev_offset; *ppos = ((loff_t)index << PAGE_CACHE_SHIFT) + offset; file_accessed(filp); } int file_read_actor(read_descriptor_t *desc, struct page *page, unsigned long offset, unsigned long size) { char *kaddr; unsigned long left, count = desc->count; if (size > count) size = count; /* * Faults on the destination of a read are common, so do it before * taking the kmap. */ if (!fault_in_pages_writeable(desc->arg.buf, size)) { kaddr = kmap_atomic(page, KM_USER0); left = __copy_to_user_inatomic(desc->arg.buf, kaddr + offset, size); kunmap_atomic(kaddr, KM_USER0); if (left == 0) goto success; } /* Do it the slow way */ kaddr = kmap(page); left = __copy_to_user(desc->arg.buf, kaddr + offset, size); kunmap(page); if (left) { size -= left; desc->error = -EFAULT; } success: desc->count = count - size; desc->written += size; desc->arg.buf += size; return size; } /* * Performs necessary checks before doing a write * @iov: io vector request * @nr_segs: number of segments in the iovec * @count: number of bytes to write * @access_flags: type of access: %VERIFY_READ or %VERIFY_WRITE * * Adjust number of segments and amount of bytes to write (nr_segs should be * properly initialized first). Returns appropriate error code that caller * should return or zero in case that write should be allowed. */ int generic_segment_checks(const struct iovec *iov, unsigned long *nr_segs, size_t *count, int access_flags) { unsigned long seg; size_t cnt = 0; for (seg = 0; seg < *nr_segs; seg++) { const struct iovec *iv = &iov[seg]; /* * If any segment has a negative length, or the cumulative * length ever wraps negative then return -EINVAL. */ cnt += iv->iov_len; if (unlikely((ssize_t)(cnt|iv->iov_len) < 0)) return -EINVAL; if (access_ok(access_flags, iv->iov_base, iv->iov_len)) continue; if (seg == 0) return -EFAULT; *nr_segs = seg; cnt -= iv->iov_len; /* This segment is no good */ break; } *count = cnt; return 0; } EXPORT_SYMBOL(generic_segment_checks); /** * generic_file_aio_read - generic filesystem read routine * @iocb: kernel I/O control block * @iov: io vector request * @nr_segs: number of segments in the iovec * @pos: current file position * * This is the "read()" routine for all filesystems * that can use the page cache directly. */ ssize_t generic_file_aio_read(struct kiocb *iocb, const struct iovec *iov, unsigned long nr_segs, loff_t pos) { struct file *filp = iocb->ki_filp; ssize_t retval; unsigned long seg = 0; size_t count; loff_t *ppos = &iocb->ki_pos; count = 0; retval = generic_segment_checks(iov, &nr_segs, &count, VERIFY_WRITE); if (retval) return retval; /* coalesce the iovecs and go direct-to-BIO for O_DIRECT */ if (filp->f_flags & O_DIRECT) { loff_t size; struct address_space *mapping; struct inode *inode; mapping = filp->f_mapping; inode = mapping->host; if (!count) goto out; /* skip atime */ size = i_size_read(inode); if (pos < size) { retval = filemap_write_and_wait_range(mapping, pos, pos + iov_length(iov, nr_segs) - 1); if (!retval) { retval = mapping->a_ops->direct_IO(READ, iocb, iov, pos, nr_segs); } if (retval > 0) { *ppos = pos + retval; count -= retval; } /* * Btrfs can have a short DIO read if we encounter * compressed extents, so if there was an error, or if * we've already read everything we wanted to, or if * there was a short read because we hit EOF, go ahead * and return. Otherwise fallthrough to buffered io for * the rest of the read. */ if (retval < 0 || !count || *ppos >= size) { file_accessed(filp); goto out; } } } count = retval; for (seg = 0; seg < nr_segs; seg++) { read_descriptor_t desc; loff_t offset = 0; /* * If we did a short DIO read we need to skip the section of the * iov that we've already read data into. */ if (count) { if (count > iov[seg].iov_len) { count -= iov[seg].iov_len; continue; } offset = count; count = 0; } desc.written = 0; desc.arg.buf = iov[seg].iov_base + offset; desc.count = iov[seg].iov_len - offset; if (desc.count == 0) continue; desc.error = 0; do_generic_file_read(filp, ppos, &desc, file_read_actor); retval += desc.written; if (desc.error) { retval = retval ?: desc.error; break; } if (desc.count > 0) break; } out: return retval; } EXPORT_SYMBOL(generic_file_aio_read); static ssize_t do_readahead(struct address_space *mapping, struct file *filp, pgoff_t index, unsigned long nr) { if (!mapping || !mapping->a_ops || !mapping->a_ops->readpage) return -EINVAL; force_page_cache_readahead(mapping, filp, index, nr); return 0; } SYSCALL_DEFINE(readahead)(int fd, loff_t offset, size_t count) { ssize_t ret; struct file *file; ret = -EBADF; file = fget(fd); if (file) { if (file->f_mode & FMODE_READ) { struct address_space *mapping = file->f_mapping; pgoff_t start = offset >> PAGE_CACHE_SHIFT; pgoff_t end = (offset + count - 1) >> PAGE_CACHE_SHIFT; unsigned long len = end - start + 1; ret = do_readahead(mapping, file, start, len); } fput(file); } return ret; } #ifdef CONFIG_HAVE_SYSCALL_WRAPPERS asmlinkage long SyS_readahead(long fd, loff_t offset, long count) { return SYSC_readahead((int) fd, offset, (size_t) count); } SYSCALL_ALIAS(sys_readahead, SyS_readahead); #endif #ifdef CONFIG_MMU /** * page_cache_read - adds requested page to the page cache if not already there * @file: file to read * @offset: page index * * This adds the requested page to the page cache if it isn't already there, * and schedules an I/O to read in its contents from disk. */ static int page_cache_read(struct file *file, pgoff_t offset) { struct address_space *mapping = file->f_mapping; struct page *page; int ret; do { page = page_cache_alloc_cold(mapping); if (!page) return -ENOMEM; ret = add_to_page_cache_lru(page, mapping, offset, GFP_KERNEL); if (ret == 0) ret = mapping->a_ops->readpage(file, page); else if (ret == -EEXIST) ret = 0; /* losing race to add is OK */ page_cache_release(page); } while (ret == AOP_TRUNCATED_PAGE); return ret; } #define MMAP_LOTSAMISS (100) /* * Synchronous readahead happens when we don't even find * a page in the page cache at all. */ static void do_sync_mmap_readahead(struct vm_area_struct *vma, struct file_ra_state *ra, struct file *file, pgoff_t offset) { unsigned long ra_pages; struct address_space *mapping = file->f_mapping; /* If we don't want any read-ahead, don't bother */ if (VM_RandomReadHint(vma)) return; if (VM_SequentialReadHint(vma) || offset - 1 == (ra->prev_pos >> PAGE_CACHE_SHIFT)) { page_cache_sync_readahead(mapping, ra, file, offset, ra->ra_pages); return; } if (ra->mmap_miss < INT_MAX) ra->mmap_miss++; /* * Do we miss much more than hit in this file? If so, * stop bothering with read-ahead. It will only hurt. */ if (ra->mmap_miss > MMAP_LOTSAMISS) return; /* * mmap read-around */ ra_pages = max_sane_readahead(ra->ra_pages); if (ra_pages) { ra->start = max_t(long, 0, offset - ra_pages/2); ra->size = ra_pages; ra->async_size = 0; ra_submit(ra, mapping, file); } } /* * Asynchronous readahead happens when we find the page and PG_readahead, * so we want to possibly extend the readahead further.. */ static void do_async_mmap_readahead(struct vm_area_struct *vma, struct file_ra_state *ra, struct file *file, struct page *page, pgoff_t offset) { struct address_space *mapping = file->f_mapping; /* If we don't want any read-ahead, don't bother */ if (VM_RandomReadHint(vma)) return; if (ra->mmap_miss > 0) ra->mmap_miss--; if (PageReadahead(page)) page_cache_async_readahead(mapping, ra, file, page, offset, ra->ra_pages); } /** * filemap_fault - read in file data for page fault handling * @vma: vma in which the fault was taken * @vmf: struct vm_fault containing details of the fault * * filemap_fault() is invoked via the vma operations vector for a * mapped memory region to read in file data during a page fault. * * The goto's are kind of ugly, but this streamlines the normal case of having * it in the page cache, and handles the special cases reasonably without * having a lot of duplicated code. */ int filemap_fault(struct vm_area_struct *vma, struct vm_fault *vmf) { int error; struct file *file = vma->vm_file; struct address_space *mapping = file->f_mapping; struct file_ra_state *ra = &file->f_ra; struct inode *inode = mapping->host; pgoff_t offset = vmf->pgoff; struct page *page; pgoff_t size; int ret = 0; size = (i_size_read(inode) + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT; if (offset >= size) return VM_FAULT_SIGBUS; /* * Do we have something in the page cache already? */ page = find_get_page(mapping, offset); if (likely(page)) { /* * We found the page, so try async readahead before * waiting for the lock. */ do_async_mmap_readahead(vma, ra, file, page, offset); } else { /* No page in the page cache at all */ do_sync_mmap_readahead(vma, ra, file, offset); count_vm_event(PGMAJFAULT); ret = VM_FAULT_MAJOR; retry_find: page = find_get_page(mapping, offset); if (!page) goto no_cached_page; } if (!lock_page_or_retry(page, vma->vm_mm, vmf->flags)) { page_cache_release(page); return ret | VM_FAULT_RETRY; } /* Did it get truncated? */ if (unlikely(page->mapping != mapping)) { unlock_page(page); put_page(page); goto retry_find; } VM_BUG_ON(page->index != offset); /* * We have a locked page in the page cache, now we need to check * that it's up-to-date. If not, it is going to be due to an error. */ if (unlikely(!PageUptodate(page))) goto page_not_uptodate; /* * Found the page and have a reference on it. * We must recheck i_size under page lock. */ size = (i_size_read(inode) + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT; if (unlikely(offset >= size)) { unlock_page(page); page_cache_release(page); return VM_FAULT_SIGBUS; } ra->prev_pos = (loff_t)offset << PAGE_CACHE_SHIFT; vmf->page = page; return ret | VM_FAULT_LOCKED; no_cached_page: /* * We're only likely to ever get here if MADV_RANDOM is in * effect. */ error = page_cache_read(file, offset); /* * The page we want has now been added to the page cache. * In the unlikely event that someone removed it in the * meantime, we'll just come back here and read it again. */ if (error >= 0) goto retry_find; /* * An error return from page_cache_read can result if the * system is low on memory, or a problem occurs while trying * to schedule I/O. */ if (error == -ENOMEM) return VM_FAULT_OOM; return VM_FAULT_SIGBUS; page_not_uptodate: /* * Umm, take care of errors if the page isn't up-to-date. * Try to re-read it _once_. We do this synchronously, * because there really aren't any performance issues here * and we need to check for errors. */ ClearPageError(page); error = mapping->a_ops->readpage(file, page); if (!error) { wait_on_page_locked(page); if (!PageUptodate(page)) error = -EIO; } page_cache_release(page); if (!error || error == AOP_TRUNCATED_PAGE) goto retry_find; /* Things didn't work out. Return zero to tell the mm layer so. */ shrink_readahead_size_eio(file, ra); return VM_FAULT_SIGBUS; } EXPORT_SYMBOL(filemap_fault); const struct vm_operations_struct generic_file_vm_ops = { .fault = filemap_fault, }; /* This is used for a general mmap of a disk file */ int generic_file_mmap(struct file * file, struct vm_area_struct * vma) { struct address_space *mapping = file->f_mapping; if (!mapping->a_ops->readpage) return -ENOEXEC; file_accessed(file); vma->vm_ops = &generic_file_vm_ops; vma->vm_flags |= VM_CAN_NONLINEAR; return 0; } /* * This is for filesystems which do not implement ->writepage. */ int generic_file_readonly_mmap(struct file *file, struct vm_area_struct *vma) { if ((vma->vm_flags & VM_SHARED) && (vma->vm_flags & VM_MAYWRITE)) return -EINVAL; return generic_file_mmap(file, vma); } #else int generic_file_mmap(struct file * file, struct vm_area_struct * vma) { return -ENOSYS; } int generic_file_readonly_mmap(struct file * file, struct vm_area_struct * vma) { return -ENOSYS; } #endif /* CONFIG_MMU */ EXPORT_SYMBOL(generic_file_mmap); EXPORT_SYMBOL(generic_file_readonly_mmap); static struct page *__read_cache_page(struct address_space *mapping, pgoff_t index, int (*filler)(void *,struct page*), void *data, gfp_t gfp) { struct page *page; int err; repeat: page = find_get_page(mapping, index); if (!page) { page = __page_cache_alloc(gfp | __GFP_COLD); if (!page) return ERR_PTR(-ENOMEM); err = add_to_page_cache_lru(page, mapping, index, GFP_KERNEL); if (unlikely(err)) { page_cache_release(page); if (err == -EEXIST) goto repeat; /* Presumably ENOMEM for radix tree node */ return ERR_PTR(err); } err = filler(data, page); if (err < 0) { page_cache_release(page); page = ERR_PTR(err); } } return page; } static struct page *do_read_cache_page(struct address_space *mapping, pgoff_t index, int (*filler)(void *,struct page*), void *data, gfp_t gfp) { struct page *page; int err; retry: page = __read_cache_page(mapping, index, filler, data, gfp); if (IS_ERR(page)) return page; if (PageUptodate(page)) goto out; lock_page(page); if (!page->mapping) { unlock_page(page); page_cache_release(page); goto retry; } if (PageUptodate(page)) { unlock_page(page); goto out; } err = filler(data, page); if (err < 0) { page_cache_release(page); return ERR_PTR(err); } out: mark_page_accessed(page); return page; } /** * read_cache_page_async - read into page cache, fill it if needed * @mapping: the page's address_space * @index: the page index * @filler: function to perform the read * @data: destination for read data * * Same as read_cache_page, but don't wait for page to become unlocked * after submitting it to the filler. * * Read into the page cache. If a page already exists, and PageUptodate() is * not set, try to fill the page but don't wait for it to become unlocked. * * If the page does not get brought uptodate, return -EIO. */ struct page *read_cache_page_async(struct address_space *mapping, pgoff_t index, int (*filler)(void *,struct page*), void *data) { return do_read_cache_page(mapping, index, filler, data, mapping_gfp_mask(mapping)); } EXPORT_SYMBOL(read_cache_page_async); static struct page *wait_on_page_read(struct page *page) { if (!IS_ERR(page)) { wait_on_page_locked(page); if (!PageUptodate(page)) { page_cache_release(page); page = ERR_PTR(-EIO); } } return page; } /** * read_cache_page_gfp - read into page cache, using specified page allocation flags. * @mapping: the page's address_space * @index: the page index * @gfp: the page allocator flags to use if allocating * * This is the same as "read_mapping_page(mapping, index, NULL)", but with * any new page allocations done using the specified allocation flags. Note * that the Radix tree operations will still use GFP_KERNEL, so you can't * expect to do this atomically or anything like that - but you can pass in * other page requirements. * * If the page does not get brought uptodate, return -EIO. */ struct page *read_cache_page_gfp(struct address_space *mapping, pgoff_t index, gfp_t gfp) { filler_t *filler = (filler_t *)mapping->a_ops->readpage; return wait_on_page_read(do_read_cache_page(mapping, index, filler, NULL, gfp)); } EXPORT_SYMBOL(read_cache_page_gfp); /** * read_cache_page - read into page cache, fill it if needed * @mapping: the page's address_space * @index: the page index * @filler: function to perform the read * @data: destination for read data * * Read into the page cache. If a page already exists, and PageUptodate() is * not set, try to fill the page then wait for it to become unlocked. * * If the page does not get brought uptodate, return -EIO. */ struct page *read_cache_page(struct address_space *mapping, pgoff_t index, int (*filler)(void *,struct page*), void *data) { return wait_on_page_read(read_cache_page_async(mapping, index, filler, data)); } EXPORT_SYMBOL(read_cache_page); /* * The logic we want is * * if suid or (sgid and xgrp) * remove privs */ int should_remove_suid(struct dentry *dentry) { mode_t mode = dentry->d_inode->i_mode; int kill = 0; /* suid always must be killed */ if (unlikely(mode & S_ISUID)) kill = ATTR_KILL_SUID; /* * sgid without any exec bits is just a mandatory locking mark; leave * it alone. If some exec bits are set, it's a real sgid; kill it. */ if (unlikely((mode & S_ISGID) && (mode & S_IXGRP))) kill |= ATTR_KILL_SGID; if (unlikely(kill && !capable(CAP_FSETID) && S_ISREG(mode))) return kill; return 0; } EXPORT_SYMBOL(should_remove_suid); static int __remove_suid(struct dentry *dentry, int kill) { struct iattr newattrs; newattrs.ia_valid = ATTR_FORCE | kill; return notify_change(dentry, &newattrs); } int file_remove_suid(struct file *file) { struct dentry *dentry = file->f_path.dentry; int killsuid = should_remove_suid(dentry); int killpriv = security_inode_need_killpriv(dentry); int error = 0; if (killpriv < 0) return killpriv; if (killpriv) error = security_inode_killpriv(dentry); if (!error && killsuid) error = __remove_suid(dentry, killsuid); return error; } EXPORT_SYMBOL(file_remove_suid); static size_t __iovec_copy_from_user_inatomic(char *vaddr, const struct iovec *iov, size_t base, size_t bytes) { size_t copied = 0, left = 0; while (bytes) { char __user *buf = iov->iov_base + base; int copy = min(bytes, iov->iov_len - base); base = 0; left = __copy_from_user_inatomic(vaddr, buf, copy); copied += copy; bytes -= copy; vaddr += copy; iov++; if (unlikely(left)) break; } return copied - left; } /* * Copy as much as we can into the page and return the number of bytes which * were successfully copied. If a fault is encountered then return the number of * bytes which were copied. */ size_t iov_iter_copy_from_user_atomic(struct page *page, struct iov_iter *i, unsigned long offset, size_t bytes) { char *kaddr; size_t copied; BUG_ON(!in_atomic()); kaddr = kmap_atomic(page, KM_USER0); if (likely(i->nr_segs == 1)) { int left; char __user *buf = i->iov->iov_base + i->iov_offset; left = __copy_from_user_inatomic(kaddr + offset, buf, bytes); copied = bytes - left; } else { copied = __iovec_copy_from_user_inatomic(kaddr + offset, i->iov, i->iov_offset, bytes); } kunmap_atomic(kaddr, KM_USER0); return copied; } EXPORT_SYMBOL(iov_iter_copy_from_user_atomic); /* * This has the same sideeffects and return value as * iov_iter_copy_from_user_atomic(). * The difference is that it attempts to resolve faults. * Page must not be locked. */ size_t iov_iter_copy_from_user(struct page *page, struct iov_iter *i, unsigned long offset, size_t bytes) { char *kaddr; size_t copied; kaddr = kmap(page); if (likely(i->nr_segs == 1)) { int left; char __user *buf = i->iov->iov_base + i->iov_offset; left = __copy_from_user(kaddr + offset, buf, bytes); copied = bytes - left; } else { copied = __iovec_copy_from_user_inatomic(kaddr + offset, i->iov, i->iov_offset, bytes); } kunmap(page); return copied; } EXPORT_SYMBOL(iov_iter_copy_from_user); void iov_iter_advance(struct iov_iter *i, size_t bytes) { BUG_ON(i->count < bytes); if (likely(i->nr_segs == 1)) { i->iov_offset += bytes; i->count -= bytes; } else { const struct iovec *iov = i->iov; size_t base = i->iov_offset; /* * The !iov->iov_len check ensures we skip over unlikely * zero-length segments (without overruning the iovec). */ while (bytes || unlikely(i->count && !iov->iov_len)) { int copy; copy = min(bytes, iov->iov_len - base); BUG_ON(!i->count || i->count < copy); i->count -= copy; bytes -= copy; base += copy; if (iov->iov_len == base) { iov++; base = 0; } } i->iov = iov; i->iov_offset = base; } } EXPORT_SYMBOL(iov_iter_advance); /* * Fault in the first iovec of the given iov_iter, to a maximum length * of bytes. Returns 0 on success, or non-zero if the memory could not be * accessed (ie. because it is an invalid address). * * writev-intensive code may want this to prefault several iovecs -- that * would be possible (callers must not rely on the fact that _only_ the * first iovec will be faulted with the current implementation). */ int iov_iter_fault_in_readable(struct iov_iter *i, size_t bytes) { char __user *buf = i->iov->iov_base + i->iov_offset; bytes = min(bytes, i->iov->iov_len - i->iov_offset); return fault_in_pages_readable(buf, bytes); } EXPORT_SYMBOL(iov_iter_fault_in_readable); /* * Return the count of just the current iov_iter segment. */ size_t iov_iter_single_seg_count(struct iov_iter *i) { const struct iovec *iov = i->iov; if (i->nr_segs == 1) return i->count; else return min(i->count, iov->iov_len - i->iov_offset); } EXPORT_SYMBOL(iov_iter_single_seg_count); /* * Performs necessary checks before doing a write * * Can adjust writing position or amount of bytes to write. * Returns appropriate error code that caller should return or * zero in case that write should be allowed. */ inline int generic_write_checks(struct file *file, loff_t *pos, size_t *count, int isblk) { struct inode *inode = file->f_mapping->host; unsigned long limit = rlimit(RLIMIT_FSIZE); if (unlikely(*pos < 0)) return -EINVAL; if (!isblk) { /* FIXME: this is for backwards compatibility with 2.4 */ if (file->f_flags & O_APPEND) *pos = i_size_read(inode); if (limit != RLIM_INFINITY) { if (*pos >= limit) { send_sig(SIGXFSZ, current, 0); return -EFBIG; } if (*count > limit - (typeof(limit))*pos) { *count = limit - (typeof(limit))*pos; } } } /* * LFS rule */ if (unlikely(*pos + *count > MAX_NON_LFS && !(file->f_flags & O_LARGEFILE))) { if (*pos >= MAX_NON_LFS) { return -EFBIG; } if (*count > MAX_NON_LFS - (unsigned long)*pos) { *count = MAX_NON_LFS - (unsigned long)*pos; } } /* * Are we about to exceed the fs block limit ? * * If we have written data it becomes a short write. If we have * exceeded without writing data we send a signal and return EFBIG. * Linus frestrict idea will clean these up nicely.. */ if (likely(!isblk)) { if (unlikely(*pos >= inode->i_sb->s_maxbytes)) { if (*count || *pos > inode->i_sb->s_maxbytes) { return -EFBIG; } /* zero-length writes at ->s_maxbytes are OK */ } if (unlikely(*pos + *count > inode->i_sb->s_maxbytes)) *count = inode->i_sb->s_maxbytes - *pos; } else { #ifdef CONFIG_BLOCK loff_t isize; if (bdev_read_only(I_BDEV(inode))) return -EPERM; isize = i_size_read(inode); if (*pos >= isize) { if (*count || *pos > isize) return -ENOSPC; } if (*pos + *count > isize) *count = isize - *pos; #else return -EPERM; #endif } return 0; } EXPORT_SYMBOL(generic_write_checks); int pagecache_write_begin(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, unsigned flags, struct page **pagep, void **fsdata) { const struct address_space_operations *aops = mapping->a_ops; return aops->write_begin(file, mapping, pos, len, flags, pagep, fsdata); } EXPORT_SYMBOL(pagecache_write_begin); int pagecache_write_end(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, unsigned copied, struct page *page, void *fsdata) { const struct address_space_operations *aops = mapping->a_ops; mark_page_accessed(page); return aops->write_end(file, mapping, pos, len, copied, page, fsdata); } EXPORT_SYMBOL(pagecache_write_end); ssize_t generic_file_direct_write(struct kiocb *iocb, const struct iovec *iov, unsigned long *nr_segs, loff_t pos, loff_t *ppos, size_t count, size_t ocount) { struct file *file = iocb->ki_filp; struct address_space *mapping = file->f_mapping; struct inode *inode = mapping->host; ssize_t written; size_t write_len; pgoff_t end; if (count != ocount) *nr_segs = iov_shorten((struct iovec *)iov, *nr_segs, count); write_len = iov_length(iov, *nr_segs); end = (pos + write_len - 1) >> PAGE_CACHE_SHIFT; written = filemap_write_and_wait_range(mapping, pos, pos + write_len - 1); if (written) goto out; /* * After a write we want buffered reads to be sure to go to disk to get * the new data. We invalidate clean cached page from the region we're * about to write. We do this *before* the write so that we can return * without clobbering -EIOCBQUEUED from ->direct_IO(). */ if (mapping->nrpages) { written = invalidate_inode_pages2_range(mapping, pos >> PAGE_CACHE_SHIFT, end); /* * If a page can not be invalidated, return 0 to fall back * to buffered write. */ if (written) { if (written == -EBUSY) return 0; goto out; } } written = mapping->a_ops->direct_IO(WRITE, iocb, iov, pos, *nr_segs); /* * Finally, try again to invalidate clean pages which might have been * cached by non-direct readahead, or faulted in by get_user_pages() * if the source of the write was an mmap'ed region of the file * we're writing. Either one is a pretty crazy thing to do, * so we don't support it 100%. If this invalidation * fails, tough, the write still worked... */ if (mapping->nrpages) { invalidate_inode_pages2_range(mapping, pos >> PAGE_CACHE_SHIFT, end); } if (written > 0) { pos += written; if (pos > i_size_read(inode) && !S_ISBLK(inode->i_mode)) { i_size_write(inode, pos); mark_inode_dirty(inode); } *ppos = pos; } out: return written; } EXPORT_SYMBOL(generic_file_direct_write); /* * Find or create a page at the given pagecache position. Return the locked * page. This function is specifically for buffered writes. */ struct page *grab_cache_page_write_begin(struct address_space *mapping, pgoff_t index, unsigned flags) { int status; struct page *page; gfp_t gfp_notmask = 0; if (flags & AOP_FLAG_NOFS) gfp_notmask = __GFP_FS; repeat: page = find_lock_page(mapping, index); if (likely(page)) return page; page = __page_cache_alloc(mapping_gfp_mask(mapping) & ~gfp_notmask); if (!page) return NULL; status = add_to_page_cache_lru(page, mapping, index, GFP_KERNEL & ~gfp_notmask); if (unlikely(status)) { page_cache_release(page); if (status == -EEXIST) goto repeat; return NULL; } return page; } EXPORT_SYMBOL(grab_cache_page_write_begin); static ssize_t generic_perform_write(struct file *file, struct iov_iter *i, loff_t pos) { struct address_space *mapping = file->f_mapping; const struct address_space_operations *a_ops = mapping->a_ops; long status = 0; ssize_t written = 0; unsigned int flags = 0; /* * Copies from kernel address space cannot fail (NFSD is a big user). */ if (segment_eq(get_fs(), KERNEL_DS)) flags |= AOP_FLAG_UNINTERRUPTIBLE; do { struct page *page; unsigned long offset; /* Offset into pagecache page */ unsigned long bytes; /* Bytes to write to page */ size_t copied; /* Bytes copied from user */ void *fsdata; offset = (pos & (PAGE_CACHE_SIZE - 1)); bytes = min_t(unsigned long, PAGE_CACHE_SIZE - offset, iov_iter_count(i)); again: /* * Bring in the user page that we will copy from _first_. * Otherwise there's a nasty deadlock on copying from the * same page as we're writing to, without it being marked * up-to-date. * * Not only is this an optimisation, but it is also required * to check that the address is actually valid, when atomic * usercopies are used, below. */ if (unlikely(iov_iter_fault_in_readable(i, bytes))) { status = -EFAULT; break; } status = a_ops->write_begin(file, mapping, pos, bytes, flags, &page, &fsdata); if (unlikely(status)) break; if (mapping_writably_mapped(mapping)) flush_dcache_page(page); pagefault_disable(); copied = iov_iter_copy_from_user_atomic(page, i, offset, bytes); pagefault_enable(); flush_dcache_page(page); mark_page_accessed(page); status = a_ops->write_end(file, mapping, pos, bytes, copied, page, fsdata); if (unlikely(status < 0)) break; copied = status; cond_resched(); iov_iter_advance(i, copied); if (unlikely(copied == 0)) { /* * If we were unable to copy any data at all, we must * fall back to a single segment length write. * * If we didn't fallback here, we could livelock * because not all segments in the iov can be copied at * once without a pagefault. */ bytes = min_t(unsigned long, PAGE_CACHE_SIZE - offset, iov_iter_single_seg_count(i)); goto again; } pos += copied; written += copied; balance_dirty_pages_ratelimited(mapping); } while (iov_iter_count(i)); return written ? written : status; } ssize_t generic_file_buffered_write(struct kiocb *iocb, const struct iovec *iov, unsigned long nr_segs, loff_t pos, loff_t *ppos, size_t count, ssize_t written) { struct file *file = iocb->ki_filp; ssize_t status; struct iov_iter i; iov_iter_init(&i, iov, nr_segs, count, written); status = generic_perform_write(file, &i, pos); if (likely(status >= 0)) { written += status; *ppos = pos + status; } return written ? written : status; } EXPORT_SYMBOL(generic_file_buffered_write); /** * __generic_file_aio_write - write data to a file * @iocb: IO state structure (file, offset, etc.) * @iov: vector with data to write * @nr_segs: number of segments in the vector * @ppos: position where to write * * This function does all the work needed for actually writing data to a * file. It does all basic checks, removes SUID from the file, updates * modification times and calls proper subroutines depending on whether we * do direct IO or a standard buffered write. * * It expects i_mutex to be grabbed unless we work on a block device or similar * object which does not need locking at all. * * This function does *not* take care of syncing data in case of O_SYNC write. * A caller has to handle it. This is mainly due to the fact that we want to * avoid syncing under i_mutex. */ ssize_t __generic_file_aio_write(struct kiocb *iocb, const struct iovec *iov, unsigned long nr_segs, loff_t *ppos) { struct file *file = iocb->ki_filp; struct address_space * mapping = file->f_mapping; size_t ocount; /* original count */ size_t count; /* after file limit checks */ struct inode *inode = mapping->host; loff_t pos; ssize_t written; ssize_t err; ocount = 0; err = generic_segment_checks(iov, &nr_segs, &ocount, VERIFY_READ); if (err) return err; count = ocount; pos = *ppos; vfs_check_frozen(inode->i_sb, SB_FREEZE_WRITE); /* We can write back this queue in page reclaim */ current->backing_dev_info = mapping->backing_dev_info; written = 0; err = generic_write_checks(file, &pos, &count, S_ISBLK(inode->i_mode)); if (err) goto out; if (count == 0) goto out; err = file_remove_suid(file); if (err) goto out; file_update_time(file); /* coalesce the iovecs and go direct-to-BIO for O_DIRECT */ if (unlikely(file->f_flags & O_DIRECT)) { loff_t endbyte; ssize_t written_buffered; written = generic_file_direct_write(iocb, iov, &nr_segs, pos, ppos, count, ocount); if (written < 0 || written == count) goto out; /* * direct-io write to a hole: fall through to buffered I/O * for completing the rest of the request. */ pos += written; count -= written; written_buffered = generic_file_buffered_write(iocb, iov, nr_segs, pos, ppos, count, written); /* * If generic_file_buffered_write() retuned a synchronous error * then we want to return the number of bytes which were * direct-written, or the error code if that was zero. Note * that this differs from normal direct-io semantics, which * will return -EFOO even if some bytes were written. */ if (written_buffered < 0) { err = written_buffered; goto out; } /* * We need to ensure that the page cache pages are written to * disk and invalidated to preserve the expected O_DIRECT * semantics. */ endbyte = pos + written_buffered - written - 1; err = filemap_write_and_wait_range(file->f_mapping, pos, endbyte); if (err == 0) { written = written_buffered; invalidate_mapping_pages(mapping, pos >> PAGE_CACHE_SHIFT, endbyte >> PAGE_CACHE_SHIFT); } else { /* * We don't know how much we wrote, so just return * the number of bytes which were direct-written */ } } else { written = generic_file_buffered_write(iocb, iov, nr_segs, pos, ppos, count, written); } out: current->backing_dev_info = NULL; return written ? written : err; } EXPORT_SYMBOL(__generic_file_aio_write); /** * generic_file_aio_write - write data to a file * @iocb: IO state structure * @iov: vector with data to write * @nr_segs: number of segments in the vector * @pos: position in file where to write * * This is a wrapper around __generic_file_aio_write() to be used by most * filesystems. It takes care of syncing the file in case of O_SYNC file * and acquires i_mutex as needed. */ ssize_t generic_file_aio_write(struct kiocb *iocb, const struct iovec *iov, unsigned long nr_segs, loff_t pos) { struct file *file = iocb->ki_filp; struct inode *inode = file->f_mapping->host; ssize_t ret; BUG_ON(iocb->ki_pos != pos); mutex_lock(&inode->i_mutex); ret = __generic_file_aio_write(iocb, iov, nr_segs, &iocb->ki_pos); mutex_unlock(&inode->i_mutex); if (ret > 0 || ret == -EIOCBQUEUED) { ssize_t err; err = generic_write_sync(file, pos, ret); if (err < 0 && ret > 0) ret = err; } return ret; } EXPORT_SYMBOL(generic_file_aio_write); /** * try_to_release_page() - release old fs-specific metadata on a page * * @page: the page which the kernel is trying to free * @gfp_mask: memory allocation flags (and I/O mode) * * The address_space is to try to release any data against the page * (presumably at page->private). If the release was successful, return `1'. * Otherwise return zero. * * This may also be called if PG_fscache is set on a page, indicating that the * page is known to the local caching routines. * * The @gfp_mask argument specifies whether I/O may be performed to release * this page (__GFP_IO), and whether the call may block (__GFP_WAIT & __GFP_FS). * */ int try_to_release_page(struct page *page, gfp_t gfp_mask) { struct address_space * const mapping = page->mapping; BUG_ON(!PageLocked(page)); if (PageWriteback(page)) return 0; if (mapping && mapping->a_ops->releasepage) return mapping->a_ops->releasepage(page, gfp_mask); return try_to_free_buffers(page); } EXPORT_SYMBOL(try_to_release_page);