summaryrefslogtreecommitdiffstats
path: root/arch/sh/mm/fault.c
blob: 4c98b6f20e0226de25074bc0e47aa76f2cd93a2d (plain)
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
/*
 * Page fault handler for SH with an MMU.
 *
 *  Copyright (C) 1999  Niibe Yutaka
 *  Copyright (C) 2003 - 2012  Paul Mundt
 *
 *  Based on linux/arch/i386/mm/fault.c:
 *   Copyright (C) 1995  Linus Torvalds
 *
 * 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.
 */
#include <linux/kernel.h>
#include <linux/mm.h>
#include <linux/sched/signal.h>
#include <linux/hardirq.h>
#include <linux/kprobes.h>
#include <linux/perf_event.h>
#include <linux/kdebug.h>
#include <linux/uaccess.h>
#include <asm/io_trapped.h>
#include <asm/mmu_context.h>
#include <asm/tlbflush.h>
#include <asm/traps.h>

static inline int notify_page_fault(struct pt_regs *regs, int trap)
{
	int ret = 0;

	if (kprobes_built_in() && !user_mode(regs)) {
		preempt_disable();
		if (kprobe_running() && kprobe_fault_handler(regs, trap))
			ret = 1;
		preempt_enable();
	}

	return ret;
}

static void
force_sig_info_fault(int si_signo, int si_code, unsigned long address,
		     struct task_struct *tsk)
{
	siginfo_t info;

	clear_siginfo(&info);
	info.si_signo	= si_signo;
	info.si_errno	= 0;
	info.si_code	= si_code;
	info.si_addr	= (void __user *)address;

	force_sig_info(si_signo, &info, tsk);
}

/*
 * This is useful to dump out the page tables associated with
 * 'addr' in mm 'mm'.
 */
static void show_pte(struct mm_struct *mm, unsigned long addr)
{
	pgd_t *pgd;

	if (mm) {
		pgd = mm->pgd;
	} else {
		pgd = get_TTB();

		if (unlikely(!pgd))
			pgd = swapper_pg_dir;
	}

	printk(KERN_ALERT "pgd = %p\n", pgd);
	pgd += pgd_index(addr);
	printk(KERN_ALERT "[%08lx] *pgd=%0*Lx", addr,
	       (u32)(sizeof(*pgd) * 2), (u64)pgd_val(*pgd));

	do {
		pud_t *pud;
		pmd_t *pmd;
		pte_t *pte;

		if (pgd_none(*pgd))
			break;

		if (pgd_bad(*pgd)) {
			printk("(bad)");
			break;
		}

		pud = pud_offset(pgd, addr);
		if (PTRS_PER_PUD != 1)
			printk(", *pud=%0*Lx", (u32)(sizeof(*pud) * 2),
			       (u64)pud_val(*pud));

		if (pud_none(*pud))
			break;

		if (pud_bad(*pud)) {
			printk("(bad)");
			break;
		}

		pmd = pmd_offset(pud, addr);
		if (PTRS_PER_PMD != 1)
			printk(", *pmd=%0*Lx", (u32)(sizeof(*pmd) * 2),
			       (u64)pmd_val(*pmd));

		if (pmd_none(*pmd))
			break;

		if (pmd_bad(*pmd)) {
			printk("(bad)");
			break;
		}

		/* We must not map this if we have highmem enabled */
		if (PageHighMem(pfn_to_page(pmd_val(*pmd) >> PAGE_SHIFT)))
			break;

		pte = pte_offset_kernel(pmd, addr);
		printk(", *pte=%0*Lx", (u32)(sizeof(*pte) * 2),
		       (u64)pte_val(*pte));
	} while (0);

	printk("\n");
}

static inline pmd_t *vmalloc_sync_one(pgd_t *pgd, unsigned long address)
{
	unsigned index = pgd_index(address);
	pgd_t *pgd_k;
	pud_t *pud, *pud_k;
	pmd_t *pmd, *pmd_k;

	pgd += index;
	pgd_k = init_mm.pgd + index;

	if (!pgd_present(*pgd_k))
		return NULL;

	pud = pud_offset(pgd, address);
	pud_k = pud_offset(pgd_k, address);
	if (!pud_present(*pud_k))
		return NULL;

	if (!pud_present(*pud))
	    set_pud(pud, *pud_k);

	pmd = pmd_offset(pud, address);
	pmd_k = pmd_offset(pud_k, address);
	if (!pmd_present(*pmd_k))
		return NULL;

	if (!pmd_present(*pmd))
		set_pmd(pmd, *pmd_k);
	else {
		/*
		 * The page tables are fully synchronised so there must
		 * be another reason for the fault. Return NULL here to
		 * signal that we have not taken care of the fault.
		 */
		BUG_ON(pmd_page(*pmd) != pmd_page(*pmd_k));
		return NULL;
	}

	return pmd_k;
}

#ifdef CONFIG_SH_STORE_QUEUES
#define __FAULT_ADDR_LIMIT	P3_ADDR_MAX
#else
#define __FAULT_ADDR_LIMIT	VMALLOC_END
#endif

/*
 * Handle a fault on the vmalloc or module mapping area
 */
static noinline int vmalloc_fault(unsigned long address)
{
	pgd_t *pgd_k;
	pmd_t *pmd_k;
	pte_t *pte_k;

	/* Make sure we are in vmalloc/module/P3 area: */
	if (!(address >= VMALLOC_START && address < __FAULT_ADDR_LIMIT))
		return -1;

	/*
	 * Synchronize this task's top level page-table
	 * with the 'reference' page table.
	 *
	 * Do _not_ use "current" here. We might be inside
	 * an interrupt in the middle of a task switch..
	 */
	pgd_k = get_TTB();
	pmd_k = vmalloc_sync_one(pgd_k, address);
	if (!pmd_k)
		return -1;

	pte_k = pte_offset_kernel(pmd_k, address);
	if (!pte_present(*pte_k))
		return -1;

	return 0;
}

static void
show_fault_oops(struct pt_regs *regs, unsigned long address)
{
	if (!oops_may_print())
		return;

	printk(KERN_ALERT "BUG: unable to handle kernel ");
	if (address < PAGE_SIZE)
		printk(KERN_CONT "NULL pointer dereference");
	else
		printk(KERN_CONT "paging request");

	printk(KERN_CONT " at %08lx\n", address);
	printk(KERN_ALERT "PC:");
	printk_address(regs->pc, 1);

	show_pte(NULL, address);
}

static noinline void
no_context(struct pt_regs *regs, unsigned long error_code,
	   unsigned long address)
{
	/* Are we prepared to handle this kernel fault?  */
	if (fixup_exception(regs))
		return;

	if (handle_trapped_io(regs, address))
		return;

	/*
	 * Oops. The kernel tried to access some bad page. We'll have to
	 * terminate things with extreme prejudice.
	 */
	bust_spinlocks(1);

	show_fault_oops(regs, address);

	die("Oops", regs, error_code);
	bust_spinlocks(0);
	do_exit(SIGKILL);
}

static void
__bad_area_nosemaphore(struct pt_regs *regs, unsigned long error_code,
		       unsigned long address, int si_code)
{
	struct task_struct *tsk = current;

	/* User mode accesses just cause a SIGSEGV */
	if (user_mode(regs)) {
		/*
		 * It's possible to have interrupts off here:
		 */
		local_irq_enable();

		force_sig_info_fault(SIGSEGV, si_code, address, tsk);

		return;
	}

	no_context(regs, error_code, address);
}

static noinline void
bad_area_nosemaphore(struct pt_regs *regs, unsigned long error_code,
		     unsigned long address)
{
	__bad_area_nosemaphore(regs, error_code, address, SEGV_MAPERR);
}

static void
__bad_area(struct pt_regs *regs, unsigned long error_code,
	   unsigned long address, int si_code)
{
	struct mm_struct *mm = current->mm;

	/*
	 * Something tried to access memory that isn't in our memory map..
	 * Fix it, but check if it's kernel or user first..
	 */
	up_read(&mm->mmap_sem);

	__bad_area_nosemaphore(regs, error_code, address, si_code);
}

static noinline void
bad_area(struct pt_regs *regs, unsigned long error_code, unsigned long address)
{
	__bad_area(regs, error_code, address, SEGV_MAPERR);
}

static noinline void
bad_area_access_error(struct pt_regs *regs, unsigned long error_code,
		      unsigned long address)
{
	__bad_area(regs, error_code, address, SEGV_ACCERR);
}

static void
do_sigbus(struct pt_regs *regs, unsigned long error_code, unsigned long address)
{
	struct task_struct *tsk = current;
	struct mm_struct *mm = tsk->mm;

	up_read(&mm->mmap_sem);

	/* Kernel mode? Handle exceptions or die: */
	if (!user_mode(regs))
		no_context(regs, error_code, address);

	force_sig_info_fault(SIGBUS, BUS_ADRERR, address, tsk);
}

static noinline int
mm_fault_error(struct pt_regs *regs, unsigned long error_code,
	       unsigned long address, unsigned int fault)
{
	/*
	 * Pagefault was interrupted by SIGKILL. We have no reason to
	 * continue pagefault.
	 */
	if (fatal_signal_pending(current)) {
		if (!(fault & VM_FAULT_RETRY))
			up_read(&current->mm->mmap_sem);
		if (!user_mode(regs))
			no_context(regs, error_code, address);
		return 1;
	}

	if (!(fault & VM_FAULT_ERROR))
		return 0;

	if (fault & VM_FAULT_OOM) {
		/* Kernel mode? Handle exceptions or die: */
		if (!user_mode(regs)) {
			up_read(&current->mm->mmap_sem);
			no_context(regs, error_code, address);
			return 1;
		}
		up_read(&current->mm->mmap_sem);

		/*
		 * We ran out of memory, call the OOM killer, and return the
		 * userspace (which will retry the fault, or kill us if we got
		 * oom-killed):
		 */
		pagefault_out_of_memory();
	} else {
		if (fault & VM_FAULT_SIGBUS)
			do_sigbus(regs, error_code, address);
		else if (fault & VM_FAULT_SIGSEGV)
			bad_area(regs, error_code, address);
		else
			BUG();
	}

	return 1;
}

static inline int access_error(int error_code, struct vm_area_struct *vma)
{
	if (error_code & FAULT_CODE_WRITE) {
		/* write, present and write, not present: */
		if (unlikely(!(vma->vm_flags & VM_WRITE)))
			return 1;
		return 0;
	}

	/* ITLB miss on NX page */
	if (unlikely((error_code & FAULT_CODE_ITLB) &&
		     !(vma->vm_flags & VM_EXEC)))
		return 1;

	/* read, not present: */
	if (unlikely(!(vma->vm_flags & (VM_READ | VM_EXEC | VM_WRITE))))
		return 1;

	return 0;
}

static int fault_in_kernel_space(unsigned long address)
{
	return address >= TASK_SIZE;
}

/*
 * This routine handles page faults.  It determines the address,
 * and the problem, and then passes it off to one of the appropriate
 * routines.
 */
asmlinkage void __kprobes do_page_fault(struct pt_regs *regs,
					unsigned long error_code,
					unsigned long address)
{
	unsigned long vec;
	struct task_struct *tsk;
	struct mm_struct *mm;
	struct vm_area_struct * vma;
	int fault;
	unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE;

	tsk = current;
	mm = tsk->mm;
	vec = lookup_exception_vector();

	/*
	 * We fault-in kernel-space virtual memory on-demand. The
	 * 'reference' page table is init_mm.pgd.
	 *
	 * NOTE! We MUST NOT take any locks for this case. We may
	 * be in an interrupt or a critical region, and should
	 * only copy the information from the master page table,
	 * nothing more.
	 */
	if (unlikely(fault_in_kernel_space(address))) {
		if (vmalloc_fault(address) >= 0)
			return;
		if (notify_page_fault(regs, vec))
			return;

		bad_area_nosemaphore(regs, error_code, address);
		return;
	}

	if (unlikely(notify_page_fault(regs, vec)))
		return;

	/* Only enable interrupts if they were on before the fault */
	if ((regs->sr & SR_IMASK) != SR_IMASK)
		local_irq_enable();

	perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, address);

	/*
	 * If we're in an interrupt, have no user context or are running
	 * with pagefaults disabled then we must not take the fault:
	 */
	if (unlikely(faulthandler_disabled() || !mm)) {
		bad_area_nosemaphore(regs, error_code, address);
		return;
	}

retry:
	down_read(&mm->mmap_sem);

	vma = find_vma(mm, address);
	if (unlikely(!vma)) {
		bad_area(regs, error_code, address);
		return;
	}
	if (likely(vma->vm_start <= address))
		goto good_area;
	if (unlikely(!(vma->vm_flags & VM_GROWSDOWN))) {
		bad_area(regs, error_code, address);
		return;
	}
	if (unlikely(expand_stack(vma, address))) {
		bad_area(regs, error_code, address);
		return;
	}

	/*
	 * Ok, we have a good vm_area for this memory access, so
	 * we can handle it..
	 */
good_area:
	if (unlikely(access_error(error_code, vma))) {
		bad_area_access_error(regs, error_code, address);
		return;
	}

	set_thread_fault_code(error_code);

	if (user_mode(regs))
		flags |= FAULT_FLAG_USER;
	if (error_code & FAULT_CODE_WRITE)
		flags |= FAULT_FLAG_WRITE;

	/*
	 * If for any reason at all we couldn't handle the fault,
	 * make sure we exit gracefully rather than endlessly redo
	 * the fault.
	 */
	fault = handle_mm_fault(vma, address, flags);

	if (unlikely(fault & (VM_FAULT_RETRY | VM_FAULT_ERROR)))
		if (mm_fault_error(regs, error_code, address, fault))
			return;

	if (flags & FAULT_FLAG_ALLOW_RETRY) {
		if (fault & VM_FAULT_MAJOR) {
			tsk->maj_flt++;
			perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MAJ, 1,
				      regs, address);
		} else {
			tsk->min_flt++;
			perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MIN, 1,
				      regs, address);
		}
		if (fault & VM_FAULT_RETRY) {
			flags &= ~FAULT_FLAG_ALLOW_RETRY;
			flags |= FAULT_FLAG_TRIED;

			/*
			 * No need to up_read(&mm->mmap_sem) as we would
			 * have already released it in __lock_page_or_retry
			 * in mm/filemap.c.
			 */
			goto retry;
		}
	}

	up_read(&mm->mmap_sem);
}