summaryrefslogtreecommitdiff
path: root/arch/powerpc/mm/fault.c
blob: 34f641d4a2fe90f6f17604c7684abad102208230 (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
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
// SPDX-License-Identifier: GPL-2.0-or-later
/*
 *  PowerPC version
 *    Copyright (C) 1995-1996 Gary Thomas (gdt@linuxppc.org)
 *
 *  Derived from "arch/i386/mm/fault.c"
 *    Copyright (C) 1991, 1992, 1993, 1994  Linus Torvalds
 *
 *  Modified by Cort Dougan and Paul Mackerras.
 *
 *  Modified for PPC64 by Dave Engebretsen (engebret@ibm.com)
 */

#include <linux/signal.h>
#include <linux/sched.h>
#include <linux/sched/task_stack.h>
#include <linux/kernel.h>
#include <linux/errno.h>
#include <linux/string.h>
#include <linux/types.h>
#include <linux/pagemap.h>
#include <linux/ptrace.h>
#include <linux/mman.h>
#include <linux/mm.h>
#include <linux/interrupt.h>
#include <linux/highmem.h>
#include <linux/extable.h>
#include <linux/kprobes.h>
#include <linux/kdebug.h>
#include <linux/perf_event.h>
#include <linux/ratelimit.h>
#include <linux/context_tracking.h>
#include <linux/hugetlb.h>
#include <linux/uaccess.h>
#include <linux/kfence.h>
#include <linux/pkeys.h>

#include <asm/firmware.h>
#include <asm/interrupt.h>
#include <asm/page.h>
#include <asm/mmu.h>
#include <asm/mmu_context.h>
#include <asm/siginfo.h>
#include <asm/debug.h>
#include <asm/kup.h>
#include <asm/inst.h>


/*
 * do_page_fault error handling helpers
 */

static int
__bad_area_nosemaphore(struct pt_regs *regs, unsigned long address, int si_code)
{
	/*
	 * If we are in kernel mode, bail out with a SEGV, this will
	 * be caught by the assembly which will restore the non-volatile
	 * registers before calling bad_page_fault()
	 */
	if (!user_mode(regs))
		return SIGSEGV;

	_exception(SIGSEGV, regs, si_code, address);

	return 0;
}

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

static int __bad_area(struct pt_regs *regs, 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..
	 */
	mmap_read_unlock(mm);

	return __bad_area_nosemaphore(regs, address, si_code);
}

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

static noinline int bad_access_pkey(struct pt_regs *regs, unsigned long address,
				    struct vm_area_struct *vma)
{
	struct mm_struct *mm = current->mm;
	int pkey;

	/*
	 * We don't try to fetch the pkey from page table because reading
	 * page table without locking doesn't guarantee stable pte value.
	 * Hence the pkey value that we return to userspace can be different
	 * from the pkey that actually caused access error.
	 *
	 * It does *not* guarantee that the VMA we find here
	 * was the one that we faulted on.
	 *
	 * 1. T1   : mprotect_key(foo, PAGE_SIZE, pkey=4);
	 * 2. T1   : set AMR to deny access to pkey=4, touches, page
	 * 3. T1   : faults...
	 * 4.    T2: mprotect_key(foo, PAGE_SIZE, pkey=5);
	 * 5. T1   : enters fault handler, takes mmap_lock, etc...
	 * 6. T1   : reaches here, sees vma_pkey(vma)=5, when we really
	 *	     faulted on a pte with its pkey=4.
	 */
	pkey = vma_pkey(vma);

	mmap_read_unlock(mm);

	/*
	 * If we are in kernel mode, bail out with a SEGV, this will
	 * be caught by the assembly which will restore the non-volatile
	 * registers before calling bad_page_fault()
	 */
	if (!user_mode(regs))
		return SIGSEGV;

	_exception_pkey(regs, address, pkey);

	return 0;
}

static noinline int bad_access(struct pt_regs *regs, unsigned long address)
{
	return __bad_area(regs, address, SEGV_ACCERR);
}

static int do_sigbus(struct pt_regs *regs, unsigned long address,
		     vm_fault_t fault)
{
	if (!user_mode(regs))
		return SIGBUS;

	current->thread.trap_nr = BUS_ADRERR;
#ifdef CONFIG_MEMORY_FAILURE
	if (fault & (VM_FAULT_HWPOISON|VM_FAULT_HWPOISON_LARGE)) {
		unsigned int lsb = 0; /* shutup gcc */

		pr_err("MCE: Killing %s:%d due to hardware memory corruption fault at %lx\n",
			current->comm, current->pid, address);

		if (fault & VM_FAULT_HWPOISON_LARGE)
			lsb = hstate_index_to_shift(VM_FAULT_GET_HINDEX(fault));
		if (fault & VM_FAULT_HWPOISON)
			lsb = PAGE_SHIFT;

		force_sig_mceerr(BUS_MCEERR_AR, (void __user *)address, lsb);
		return 0;
	}

#endif
	force_sig_fault(SIGBUS, BUS_ADRERR, (void __user *)address);
	return 0;
}

static int mm_fault_error(struct pt_regs *regs, unsigned long addr,
				vm_fault_t fault)
{
	/*
	 * Kernel page fault interrupted by SIGKILL. We have no reason to
	 * continue processing.
	 */
	if (fatal_signal_pending(current) && !user_mode(regs))
		return SIGKILL;

	/* Out of memory */
	if (fault & VM_FAULT_OOM) {
		/*
		 * We ran out of memory, or some other thing happened to us that
		 * made us unable to handle the page fault gracefully.
		 */
		if (!user_mode(regs))
			return SIGSEGV;
		pagefault_out_of_memory();
	} else {
		if (fault & (VM_FAULT_SIGBUS|VM_FAULT_HWPOISON|
			     VM_FAULT_HWPOISON_LARGE))
			return do_sigbus(regs, addr, fault);
		else if (fault & VM_FAULT_SIGSEGV)
			return bad_area_nosemaphore(regs, addr);
		else
			BUG();
	}
	return 0;
}

/* Is this a bad kernel fault ? */
static bool bad_kernel_fault(struct pt_regs *regs, unsigned long error_code,
			     unsigned long address, bool is_write)
{
	int is_exec = TRAP(regs) == INTERRUPT_INST_STORAGE;

	/* NX faults set DSISR_PROTFAULT on the 8xx, DSISR_NOEXEC_OR_G on others */
	if (is_exec && (error_code & (DSISR_NOEXEC_OR_G | DSISR_KEYFAULT |
				      DSISR_PROTFAULT))) {
		pr_crit_ratelimited("kernel tried to execute %s page (%lx) - exploit attempt? (uid: %d)\n",
				    address >= TASK_SIZE ? "exec-protected" : "user",
				    address,
				    from_kuid(&init_user_ns, current_uid()));

		// Kernel exec fault is always bad
		return true;
	}

	// Kernel fault on kernel address is bad
	if (address >= TASK_SIZE)
		return true;

	// Read/write fault blocked by KUAP is bad, it can never succeed.
	if (bad_kuap_fault(regs, address, is_write)) {
		pr_crit_ratelimited("Kernel attempted to %s user page (%lx) - exploit attempt? (uid: %d)\n",
				    is_write ? "write" : "read", address,
				    from_kuid(&init_user_ns, current_uid()));

		// Fault on user outside of certain regions (eg. copy_tofrom_user()) is bad
		if (!search_exception_tables(regs->nip))
			return true;

		// Read/write fault in a valid region (the exception table search passed
		// above), but blocked by KUAP is bad, it can never succeed.
		return WARN(true, "Bug: %s fault blocked by KUAP!", is_write ? "Write" : "Read");
	}

	// What's left? Kernel fault on user and allowed by KUAP in the faulting context.
	return false;
}

static bool access_pkey_error(bool is_write, bool is_exec, bool is_pkey,
			      struct vm_area_struct *vma)
{
	/*
	 * Make sure to check the VMA so that we do not perform
	 * faults just to hit a pkey fault as soon as we fill in a
	 * page. Only called for current mm, hence foreign == 0
	 */
	if (!arch_vma_access_permitted(vma, is_write, is_exec, 0))
		return true;

	return false;
}

static bool access_error(bool is_write, bool is_exec, struct vm_area_struct *vma)
{
	/*
	 * Allow execution from readable areas if the MMU does not
	 * provide separate controls over reading and executing.
	 *
	 * Note: That code used to not be enabled for 4xx/BookE.
	 * It is now as I/D cache coherency for these is done at
	 * set_pte_at() time and I see no reason why the test
	 * below wouldn't be valid on those processors. This -may-
	 * break programs compiled with a really old ABI though.
	 */
	if (is_exec) {
		return !(vma->vm_flags & VM_EXEC) &&
			(cpu_has_feature(CPU_FTR_NOEXECUTE) ||
			 !(vma->vm_flags & (VM_READ | VM_WRITE)));
	}

	if (is_write) {
		if (unlikely(!(vma->vm_flags & VM_WRITE)))
			return true;
		return false;
	}

	if (unlikely(!vma_is_accessible(vma)))
		return true;
	/*
	 * We should ideally do the vma pkey access check here. But in the
	 * fault path, handle_mm_fault() also does the same check. To avoid
	 * these multiple checks, we skip it here and handle access error due
	 * to pkeys later.
	 */
	return false;
}

#ifdef CONFIG_PPC_SMLPAR
static inline void cmo_account_page_fault(void)
{
	if (firmware_has_feature(FW_FEATURE_CMO)) {
		u32 page_ins;

		preempt_disable();
		page_ins = be32_to_cpu(get_lppaca()->page_ins);
		page_ins += 1 << PAGE_FACTOR;
		get_lppaca()->page_ins = cpu_to_be32(page_ins);
		preempt_enable();
	}
}
#else
static inline void cmo_account_page_fault(void) { }
#endif /* CONFIG_PPC_SMLPAR */

static void sanity_check_fault(bool is_write, bool is_user,
			       unsigned long error_code, unsigned long address)
{
	/*
	 * Userspace trying to access kernel address, we get PROTFAULT for that.
	 */
	if (is_user && address >= TASK_SIZE) {
		if ((long)address == -1)
			return;

		pr_crit_ratelimited("%s[%d]: User access of kernel address (%lx) - exploit attempt? (uid: %d)\n",
				   current->comm, current->pid, address,
				   from_kuid(&init_user_ns, current_uid()));
		return;
	}

	if (!IS_ENABLED(CONFIG_PPC_BOOK3S))
		return;

	/*
	 * For hash translation mode, we should never get a
	 * PROTFAULT. Any update to pte to reduce access will result in us
	 * removing the hash page table entry, thus resulting in a DSISR_NOHPTE
	 * fault instead of DSISR_PROTFAULT.
	 *
	 * A pte update to relax the access will not result in a hash page table
	 * entry invalidate and hence can result in DSISR_PROTFAULT.
	 * ptep_set_access_flags() doesn't do a hpte flush. This is why we have
	 * the special !is_write in the below conditional.
	 *
	 * For platforms that doesn't supports coherent icache and do support
	 * per page noexec bit, we do setup things such that we do the
	 * sync between D/I cache via fault. But that is handled via low level
	 * hash fault code (hash_page_do_lazy_icache()) and we should not reach
	 * here in such case.
	 *
	 * For wrong access that can result in PROTFAULT, the above vma->vm_flags
	 * check should handle those and hence we should fall to the bad_area
	 * handling correctly.
	 *
	 * For embedded with per page exec support that doesn't support coherent
	 * icache we do get PROTFAULT and we handle that D/I cache sync in
	 * set_pte_at while taking the noexec/prot fault. Hence this is WARN_ON
	 * is conditional for server MMU.
	 *
	 * For radix, we can get prot fault for autonuma case, because radix
	 * page table will have them marked noaccess for user.
	 */
	if (radix_enabled() || is_write)
		return;

	WARN_ON_ONCE(error_code & DSISR_PROTFAULT);
}

/*
 * Define the correct "is_write" bit in error_code based
 * on the processor family
 */
#if (defined(CONFIG_4xx) || defined(CONFIG_BOOKE))
#define page_fault_is_write(__err)	((__err) & ESR_DST)
#else
#define page_fault_is_write(__err)	((__err) & DSISR_ISSTORE)
#endif

#if defined(CONFIG_4xx) || defined(CONFIG_BOOKE)
#define page_fault_is_bad(__err)	(0)
#elif defined(CONFIG_PPC_8xx)
#define page_fault_is_bad(__err)	((__err) & DSISR_NOEXEC_OR_G)
#elif defined(CONFIG_PPC64)
#define page_fault_is_bad(__err)	((__err) & DSISR_BAD_FAULT_64S)
#else
#define page_fault_is_bad(__err)	((__err) & DSISR_BAD_FAULT_32S)
#endif

/*
 * For 600- and 800-family processors, the error_code parameter is DSISR
 * for a data fault, SRR1 for an instruction fault.
 * For 400-family processors the error_code parameter is ESR for a data fault,
 * 0 for an instruction fault.
 * For 64-bit processors, the error_code parameter is DSISR for a data access
 * fault, SRR1 & 0x08000000 for an instruction access fault.
 *
 * The return value is 0 if the fault was handled, or the signal
 * number if this is a kernel fault that can't be handled here.
 */
static int ___do_page_fault(struct pt_regs *regs, unsigned long address,
			   unsigned long error_code)
{
	struct vm_area_struct * vma;
	struct mm_struct *mm = current->mm;
	unsigned int flags = FAULT_FLAG_DEFAULT;
	int is_exec = TRAP(regs) == INTERRUPT_INST_STORAGE;
	int is_user = user_mode(regs);
	int is_write = page_fault_is_write(error_code);
	vm_fault_t fault, major = 0;
	bool kprobe_fault = kprobe_page_fault(regs, 11);

	if (unlikely(debugger_fault_handler(regs) || kprobe_fault))
		return 0;

	if (unlikely(page_fault_is_bad(error_code))) {
		if (is_user) {
			_exception(SIGBUS, regs, BUS_OBJERR, address);
			return 0;
		}
		return SIGBUS;
	}

	/* Additional sanity check(s) */
	sanity_check_fault(is_write, is_user, error_code, address);

	/*
	 * The kernel should never take an execute fault nor should it
	 * take a page fault to a kernel address or a page fault to a user
	 * address outside of dedicated places
	 */
	if (unlikely(!is_user && bad_kernel_fault(regs, error_code, address, is_write))) {
		if (kfence_handle_page_fault(address, is_write, regs))
			return 0;

		return SIGSEGV;
	}

	/*
	 * If we're in an interrupt, have no user context or are running
	 * in a region with pagefaults disabled then we must not take the fault
	 */
	if (unlikely(faulthandler_disabled() || !mm)) {
		if (is_user)
			printk_ratelimited(KERN_ERR "Page fault in user mode"
					   " with faulthandler_disabled()=%d"
					   " mm=%p\n",
					   faulthandler_disabled(), mm);
		return bad_area_nosemaphore(regs, address);
	}

	interrupt_cond_local_irq_enable(regs);

	perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, address);

	/*
	 * We want to do this outside mmap_lock, because reading code around nip
	 * can result in fault, which will cause a deadlock when called with
	 * mmap_lock held
	 */
	if (is_user)
		flags |= FAULT_FLAG_USER;
	if (is_write)
		flags |= FAULT_FLAG_WRITE;
	if (is_exec)
		flags |= FAULT_FLAG_INSTRUCTION;

	/* When running in the kernel we expect faults to occur only to
	 * addresses in user space.  All other faults represent errors in the
	 * kernel and should generate an OOPS.  Unfortunately, in the case of an
	 * erroneous fault occurring in a code path which already holds mmap_lock
	 * we will deadlock attempting to validate the fault against the
	 * address space.  Luckily the kernel only validly references user
	 * space from well defined areas of code, which are listed in the
	 * exceptions table.
	 *
	 * As the vast majority of faults will be valid we will only perform
	 * the source reference check when there is a possibility of a deadlock.
	 * Attempt to lock the address space, if we cannot we then validate the
	 * source.  If this is invalid we can skip the address space check,
	 * thus avoiding the deadlock.
	 */
	if (unlikely(!mmap_read_trylock(mm))) {
		if (!is_user && !search_exception_tables(regs->nip))
			return bad_area_nosemaphore(regs, address);

retry:
		mmap_read_lock(mm);
	} else {
		/*
		 * The above down_read_trylock() might have succeeded in
		 * which case we'll have missed the might_sleep() from
		 * down_read():
		 */
		might_sleep();
	}

	vma = find_vma(mm, address);
	if (unlikely(!vma))
		return bad_area(regs, address);

	if (unlikely(vma->vm_start > address)) {
		if (unlikely(!(vma->vm_flags & VM_GROWSDOWN)))
			return bad_area(regs, address);

		if (unlikely(expand_stack(vma, address)))
			return bad_area(regs, address);
	}

	if (unlikely(access_pkey_error(is_write, is_exec,
				       (error_code & DSISR_KEYFAULT), vma)))
		return bad_access_pkey(regs, address, vma);

	if (unlikely(access_error(is_write, is_exec, vma)))
		return bad_access(regs, address);

	/*
	 * 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, regs);

	major |= fault & VM_FAULT_MAJOR;

	if (fault_signal_pending(fault, regs))
		return user_mode(regs) ? 0 : SIGBUS;

	/*
	 * Handle the retry right now, the mmap_lock has been released in that
	 * case.
	 */
	if (unlikely(fault & VM_FAULT_RETRY)) {
		if (flags & FAULT_FLAG_ALLOW_RETRY) {
			flags |= FAULT_FLAG_TRIED;
			goto retry;
		}
	}

	mmap_read_unlock(current->mm);

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

	/*
	 * Major/minor page fault accounting.
	 */
	if (major)
		cmo_account_page_fault();

	return 0;
}
NOKPROBE_SYMBOL(___do_page_fault);

static __always_inline void __do_page_fault(struct pt_regs *regs)
{
	long err;

	err = ___do_page_fault(regs, regs->dar, regs->dsisr);
	if (unlikely(err))
		bad_page_fault(regs, err);
}

DEFINE_INTERRUPT_HANDLER(do_page_fault)
{
	__do_page_fault(regs);
}

#ifdef CONFIG_PPC_BOOK3S_64
/* Same as do_page_fault but interrupt entry has already run in do_hash_fault */
void hash__do_page_fault(struct pt_regs *regs)
{
	__do_page_fault(regs);
}
NOKPROBE_SYMBOL(hash__do_page_fault);
#endif

/*
 * bad_page_fault is called when we have a bad access from the kernel.
 * It is called from the DSI and ISI handlers in head.S and from some
 * of the procedures in traps.c.
 */
static void __bad_page_fault(struct pt_regs *regs, int sig)
{
	int is_write = page_fault_is_write(regs->dsisr);

	/* kernel has accessed a bad area */

	switch (TRAP(regs)) {
	case INTERRUPT_DATA_STORAGE:
	case INTERRUPT_DATA_SEGMENT:
	case INTERRUPT_H_DATA_STORAGE:
		pr_alert("BUG: %s on %s at 0x%08lx\n",
			 regs->dar < PAGE_SIZE ? "Kernel NULL pointer dereference" :
			 "Unable to handle kernel data access",
			 is_write ? "write" : "read", regs->dar);
		break;
	case INTERRUPT_INST_STORAGE:
	case INTERRUPT_INST_SEGMENT:
		pr_alert("BUG: Unable to handle kernel instruction fetch%s",
			 regs->nip < PAGE_SIZE ? " (NULL pointer?)\n" : "\n");
		break;
	case INTERRUPT_ALIGNMENT:
		pr_alert("BUG: Unable to handle kernel unaligned access at 0x%08lx\n",
			 regs->dar);
		break;
	default:
		pr_alert("BUG: Unable to handle unknown paging fault at 0x%08lx\n",
			 regs->dar);
		break;
	}
	printk(KERN_ALERT "Faulting instruction address: 0x%08lx\n",
		regs->nip);

	if (task_stack_end_corrupted(current))
		printk(KERN_ALERT "Thread overran stack, or stack corrupted\n");

	die("Kernel access of bad area", regs, sig);
}

void bad_page_fault(struct pt_regs *regs, int sig)
{
	const struct exception_table_entry *entry;

	/* Are we prepared to handle this fault?  */
	entry = search_exception_tables(instruction_pointer(regs));
	if (entry)
		instruction_pointer_set(regs, extable_fixup(entry));
	else
		__bad_page_fault(regs, sig);
}

#ifdef CONFIG_PPC_BOOK3S_64
DEFINE_INTERRUPT_HANDLER(do_bad_page_fault_segv)
{
	bad_page_fault(regs, SIGSEGV);
}
#endif