summaryrefslogtreecommitdiff
path: root/arch/arm64/kernel/mte.c
blob: b2b730233274b72f4e1c619d39a0e68d22835f13 (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
// SPDX-License-Identifier: GPL-2.0-only
/*
 * Copyright (C) 2020 ARM Ltd.
 */

#include <linux/bitops.h>
#include <linux/cpu.h>
#include <linux/kernel.h>
#include <linux/mm.h>
#include <linux/prctl.h>
#include <linux/sched.h>
#include <linux/sched/mm.h>
#include <linux/string.h>
#include <linux/swap.h>
#include <linux/swapops.h>
#include <linux/thread_info.h>
#include <linux/types.h>
#include <linux/uaccess.h>
#include <linux/uio.h>

#include <asm/barrier.h>
#include <asm/cpufeature.h>
#include <asm/mte.h>
#include <asm/ptrace.h>
#include <asm/sysreg.h>

static DEFINE_PER_CPU_READ_MOSTLY(u64, mte_tcf_preferred);

#ifdef CONFIG_KASAN_HW_TAGS
/*
 * The asynchronous and asymmetric MTE modes have the same behavior for
 * store operations. This flag is set when either of these modes is enabled.
 */
DEFINE_STATIC_KEY_FALSE(mte_async_or_asymm_mode);
EXPORT_SYMBOL_GPL(mte_async_or_asymm_mode);
#endif

static void mte_sync_page_tags(struct page *page, pte_t old_pte,
			       bool check_swap, bool pte_is_tagged)
{
	if (check_swap && is_swap_pte(old_pte)) {
		swp_entry_t entry = pte_to_swp_entry(old_pte);

		if (!non_swap_entry(entry) && mte_restore_tags(entry, page))
			return;
	}

	if (!pte_is_tagged)
		return;

	mte_clear_page_tags(page_address(page));
}

void mte_sync_tags(pte_t old_pte, pte_t pte)
{
	struct page *page = pte_page(pte);
	long i, nr_pages = compound_nr(page);
	bool check_swap = nr_pages == 1;
	bool pte_is_tagged = pte_tagged(pte);

	/* Early out if there's nothing to do */
	if (!check_swap && !pte_is_tagged)
		return;

	/* if PG_mte_tagged is set, tags have already been initialised */
	for (i = 0; i < nr_pages; i++, page++) {
		if (!test_and_set_bit(PG_mte_tagged, &page->flags))
			mte_sync_page_tags(page, old_pte, check_swap,
					   pte_is_tagged);
	}

	/* ensure the tags are visible before the PTE is set */
	smp_wmb();
}

int memcmp_pages(struct page *page1, struct page *page2)
{
	char *addr1, *addr2;
	int ret;

	addr1 = page_address(page1);
	addr2 = page_address(page2);
	ret = memcmp(addr1, addr2, PAGE_SIZE);

	if (!system_supports_mte() || ret)
		return ret;

	/*
	 * If the page content is identical but at least one of the pages is
	 * tagged, return non-zero to avoid KSM merging. If only one of the
	 * pages is tagged, set_pte_at() may zero or change the tags of the
	 * other page via mte_sync_tags().
	 */
	if (test_bit(PG_mte_tagged, &page1->flags) ||
	    test_bit(PG_mte_tagged, &page2->flags))
		return addr1 != addr2;

	return ret;
}

static inline void __mte_enable_kernel(const char *mode, unsigned long tcf)
{
	/* Enable MTE Sync Mode for EL1. */
	sysreg_clear_set(sctlr_el1, SCTLR_EL1_TCF_MASK,
			 SYS_FIELD_PREP(SCTLR_EL1, TCF, tcf));
	isb();

	pr_info_once("MTE: enabled in %s mode at EL1\n", mode);
}

#ifdef CONFIG_KASAN_HW_TAGS
void mte_enable_kernel_sync(void)
{
	/*
	 * Make sure we enter this function when no PE has set
	 * async mode previously.
	 */
	WARN_ONCE(system_uses_mte_async_or_asymm_mode(),
			"MTE async mode enabled system wide!");

	__mte_enable_kernel("synchronous", SCTLR_EL1_TCF_SYNC);
}

void mte_enable_kernel_async(void)
{
	__mte_enable_kernel("asynchronous", SCTLR_EL1_TCF_ASYNC);

	/*
	 * MTE async mode is set system wide by the first PE that
	 * executes this function.
	 *
	 * Note: If in future KASAN acquires a runtime switching
	 * mode in between sync and async, this strategy needs
	 * to be reviewed.
	 */
	if (!system_uses_mte_async_or_asymm_mode())
		static_branch_enable(&mte_async_or_asymm_mode);
}

void mte_enable_kernel_asymm(void)
{
	if (cpus_have_cap(ARM64_MTE_ASYMM)) {
		__mte_enable_kernel("asymmetric", SCTLR_EL1_TCF_ASYMM);

		/*
		 * MTE asymm mode behaves as async mode for store
		 * operations. The mode is set system wide by the
		 * first PE that executes this function.
		 *
		 * Note: If in future KASAN acquires a runtime switching
		 * mode in between sync and async, this strategy needs
		 * to be reviewed.
		 */
		if (!system_uses_mte_async_or_asymm_mode())
			static_branch_enable(&mte_async_or_asymm_mode);
	} else {
		/*
		 * If the CPU does not support MTE asymmetric mode the
		 * kernel falls back on synchronous mode which is the
		 * default for kasan=on.
		 */
		mte_enable_kernel_sync();
	}
}
#endif

#ifdef CONFIG_KASAN_HW_TAGS
void mte_check_tfsr_el1(void)
{
	u64 tfsr_el1 = read_sysreg_s(SYS_TFSR_EL1);

	if (unlikely(tfsr_el1 & SYS_TFSR_EL1_TF1)) {
		/*
		 * Note: isb() is not required after this direct write
		 * because there is no indirect read subsequent to it
		 * (per ARM DDI 0487F.c table D13-1).
		 */
		write_sysreg_s(0, SYS_TFSR_EL1);

		kasan_report_async();
	}
}
#endif

/*
 * This is where we actually resolve the system and process MTE mode
 * configuration into an actual value in SCTLR_EL1 that affects
 * userspace.
 */
static void mte_update_sctlr_user(struct task_struct *task)
{
	/*
	 * This must be called with preemption disabled and can only be called
	 * on the current or next task since the CPU must match where the thread
	 * is going to run. The caller is responsible for calling
	 * update_sctlr_el1() later in the same preemption disabled block.
	 */
	unsigned long sctlr = task->thread.sctlr_user;
	unsigned long mte_ctrl = task->thread.mte_ctrl;
	unsigned long pref, resolved_mte_tcf;

	pref = __this_cpu_read(mte_tcf_preferred);
	/*
	 * If there is no overlap between the system preferred and
	 * program requested values go with what was requested.
	 */
	resolved_mte_tcf = (mte_ctrl & pref) ? pref : mte_ctrl;
	sctlr &= ~SCTLR_EL1_TCF0_MASK;
	/*
	 * Pick an actual setting. The order in which we check for
	 * set bits and map into register values determines our
	 * default order.
	 */
	if (resolved_mte_tcf & MTE_CTRL_TCF_ASYMM)
		sctlr |= SYS_FIELD_PREP_ENUM(SCTLR_EL1, TCF0, ASYMM);
	else if (resolved_mte_tcf & MTE_CTRL_TCF_ASYNC)
		sctlr |= SYS_FIELD_PREP_ENUM(SCTLR_EL1, TCF0, ASYNC);
	else if (resolved_mte_tcf & MTE_CTRL_TCF_SYNC)
		sctlr |= SYS_FIELD_PREP_ENUM(SCTLR_EL1, TCF0, SYNC);
	task->thread.sctlr_user = sctlr;
}

static void mte_update_gcr_excl(struct task_struct *task)
{
	/*
	 * SYS_GCR_EL1 will be set to current->thread.mte_ctrl value by
	 * mte_set_user_gcr() in kernel_exit, but only if KASAN is enabled.
	 */
	if (kasan_hw_tags_enabled())
		return;

	write_sysreg_s(
		((task->thread.mte_ctrl >> MTE_CTRL_GCR_USER_EXCL_SHIFT) &
		 SYS_GCR_EL1_EXCL_MASK) | SYS_GCR_EL1_RRND,
		SYS_GCR_EL1);
}

#ifdef CONFIG_KASAN_HW_TAGS
/* Only called from assembly, silence sparse */
void __init kasan_hw_tags_enable(struct alt_instr *alt, __le32 *origptr,
				 __le32 *updptr, int nr_inst);

void __init kasan_hw_tags_enable(struct alt_instr *alt, __le32 *origptr,
				 __le32 *updptr, int nr_inst)
{
	BUG_ON(nr_inst != 1); /* Branch -> NOP */

	if (kasan_hw_tags_enabled())
		*updptr = cpu_to_le32(aarch64_insn_gen_nop());
}
#endif

void mte_thread_init_user(void)
{
	if (!system_supports_mte())
		return;

	/* clear any pending asynchronous tag fault */
	dsb(ish);
	write_sysreg_s(0, SYS_TFSRE0_EL1);
	clear_thread_flag(TIF_MTE_ASYNC_FAULT);
	/* disable tag checking and reset tag generation mask */
	set_mte_ctrl(current, 0);
}

void mte_thread_switch(struct task_struct *next)
{
	if (!system_supports_mte())
		return;

	mte_update_sctlr_user(next);
	mte_update_gcr_excl(next);

	/* TCO may not have been disabled on exception entry for the current task. */
	mte_disable_tco_entry(next);

	/*
	 * Check if an async tag exception occurred at EL1.
	 *
	 * Note: On the context switch path we rely on the dsb() present
	 * in __switch_to() to guarantee that the indirect writes to TFSR_EL1
	 * are synchronized before this point.
	 */
	isb();
	mte_check_tfsr_el1();
}

void mte_suspend_enter(void)
{
	if (!system_supports_mte())
		return;

	/*
	 * The barriers are required to guarantee that the indirect writes
	 * to TFSR_EL1 are synchronized before we report the state.
	 */
	dsb(nsh);
	isb();

	/* Report SYS_TFSR_EL1 before suspend entry */
	mte_check_tfsr_el1();
}

long set_mte_ctrl(struct task_struct *task, unsigned long arg)
{
	u64 mte_ctrl = (~((arg & PR_MTE_TAG_MASK) >> PR_MTE_TAG_SHIFT) &
			SYS_GCR_EL1_EXCL_MASK) << MTE_CTRL_GCR_USER_EXCL_SHIFT;

	if (!system_supports_mte())
		return 0;

	if (arg & PR_MTE_TCF_ASYNC)
		mte_ctrl |= MTE_CTRL_TCF_ASYNC;
	if (arg & PR_MTE_TCF_SYNC)
		mte_ctrl |= MTE_CTRL_TCF_SYNC;

	/*
	 * If the system supports it and both sync and async modes are
	 * specified then implicitly enable asymmetric mode.
	 * Userspace could see a mix of both sync and async anyway due
	 * to differing or changing defaults on CPUs.
	 */
	if (cpus_have_cap(ARM64_MTE_ASYMM) &&
	    (arg & PR_MTE_TCF_ASYNC) &&
	    (arg & PR_MTE_TCF_SYNC))
		mte_ctrl |= MTE_CTRL_TCF_ASYMM;

	task->thread.mte_ctrl = mte_ctrl;
	if (task == current) {
		preempt_disable();
		mte_update_sctlr_user(task);
		mte_update_gcr_excl(task);
		update_sctlr_el1(task->thread.sctlr_user);
		preempt_enable();
	}

	return 0;
}

long get_mte_ctrl(struct task_struct *task)
{
	unsigned long ret;
	u64 mte_ctrl = task->thread.mte_ctrl;
	u64 incl = (~mte_ctrl >> MTE_CTRL_GCR_USER_EXCL_SHIFT) &
		   SYS_GCR_EL1_EXCL_MASK;

	if (!system_supports_mte())
		return 0;

	ret = incl << PR_MTE_TAG_SHIFT;
	if (mte_ctrl & MTE_CTRL_TCF_ASYNC)
		ret |= PR_MTE_TCF_ASYNC;
	if (mte_ctrl & MTE_CTRL_TCF_SYNC)
		ret |= PR_MTE_TCF_SYNC;

	return ret;
}

/*
 * Access MTE tags in another process' address space as given in mm. Update
 * the number of tags copied. Return 0 if any tags copied, error otherwise.
 * Inspired by __access_remote_vm().
 */
static int __access_remote_tags(struct mm_struct *mm, unsigned long addr,
				struct iovec *kiov, unsigned int gup_flags)
{
	struct vm_area_struct *vma;
	void __user *buf = kiov->iov_base;
	size_t len = kiov->iov_len;
	int ret;
	int write = gup_flags & FOLL_WRITE;

	if (!access_ok(buf, len))
		return -EFAULT;

	if (mmap_read_lock_killable(mm))
		return -EIO;

	while (len) {
		unsigned long tags, offset;
		void *maddr;
		struct page *page = NULL;

		ret = get_user_pages_remote(mm, addr, 1, gup_flags, &page,
					    &vma, NULL);
		if (ret <= 0)
			break;

		/*
		 * Only copy tags if the page has been mapped as PROT_MTE
		 * (PG_mte_tagged set). Otherwise the tags are not valid and
		 * not accessible to user. Moreover, an mprotect(PROT_MTE)
		 * would cause the existing tags to be cleared if the page
		 * was never mapped with PROT_MTE.
		 */
		if (!(vma->vm_flags & VM_MTE)) {
			ret = -EOPNOTSUPP;
			put_page(page);
			break;
		}
		WARN_ON_ONCE(!test_bit(PG_mte_tagged, &page->flags));

		/* limit access to the end of the page */
		offset = offset_in_page(addr);
		tags = min(len, (PAGE_SIZE - offset) / MTE_GRANULE_SIZE);

		maddr = page_address(page);
		if (write) {
			tags = mte_copy_tags_from_user(maddr + offset, buf, tags);
			set_page_dirty_lock(page);
		} else {
			tags = mte_copy_tags_to_user(buf, maddr + offset, tags);
		}
		put_page(page);

		/* error accessing the tracer's buffer */
		if (!tags)
			break;

		len -= tags;
		buf += tags;
		addr += tags * MTE_GRANULE_SIZE;
	}
	mmap_read_unlock(mm);

	/* return an error if no tags copied */
	kiov->iov_len = buf - kiov->iov_base;
	if (!kiov->iov_len) {
		/* check for error accessing the tracee's address space */
		if (ret <= 0)
			return -EIO;
		else
			return -EFAULT;
	}

	return 0;
}

/*
 * Copy MTE tags in another process' address space at 'addr' to/from tracer's
 * iovec buffer. Return 0 on success. Inspired by ptrace_access_vm().
 */
static int access_remote_tags(struct task_struct *tsk, unsigned long addr,
			      struct iovec *kiov, unsigned int gup_flags)
{
	struct mm_struct *mm;
	int ret;

	mm = get_task_mm(tsk);
	if (!mm)
		return -EPERM;

	if (!tsk->ptrace || (current != tsk->parent) ||
	    ((get_dumpable(mm) != SUID_DUMP_USER) &&
	     !ptracer_capable(tsk, mm->user_ns))) {
		mmput(mm);
		return -EPERM;
	}

	ret = __access_remote_tags(mm, addr, kiov, gup_flags);
	mmput(mm);

	return ret;
}

int mte_ptrace_copy_tags(struct task_struct *child, long request,
			 unsigned long addr, unsigned long data)
{
	int ret;
	struct iovec kiov;
	struct iovec __user *uiov = (void __user *)data;
	unsigned int gup_flags = FOLL_FORCE;

	if (!system_supports_mte())
		return -EIO;

	if (get_user(kiov.iov_base, &uiov->iov_base) ||
	    get_user(kiov.iov_len, &uiov->iov_len))
		return -EFAULT;

	if (request == PTRACE_POKEMTETAGS)
		gup_flags |= FOLL_WRITE;

	/* align addr to the MTE tag granule */
	addr &= MTE_GRANULE_MASK;

	ret = access_remote_tags(child, addr, &kiov, gup_flags);
	if (!ret)
		ret = put_user(kiov.iov_len, &uiov->iov_len);

	return ret;
}

static ssize_t mte_tcf_preferred_show(struct device *dev,
				      struct device_attribute *attr, char *buf)
{
	switch (per_cpu(mte_tcf_preferred, dev->id)) {
	case MTE_CTRL_TCF_ASYNC:
		return sysfs_emit(buf, "async\n");
	case MTE_CTRL_TCF_SYNC:
		return sysfs_emit(buf, "sync\n");
	case MTE_CTRL_TCF_ASYMM:
		return sysfs_emit(buf, "asymm\n");
	default:
		return sysfs_emit(buf, "???\n");
	}
}

static ssize_t mte_tcf_preferred_store(struct device *dev,
				       struct device_attribute *attr,
				       const char *buf, size_t count)
{
	u64 tcf;

	if (sysfs_streq(buf, "async"))
		tcf = MTE_CTRL_TCF_ASYNC;
	else if (sysfs_streq(buf, "sync"))
		tcf = MTE_CTRL_TCF_SYNC;
	else if (cpus_have_cap(ARM64_MTE_ASYMM) && sysfs_streq(buf, "asymm"))
		tcf = MTE_CTRL_TCF_ASYMM;
	else
		return -EINVAL;

	device_lock(dev);
	per_cpu(mte_tcf_preferred, dev->id) = tcf;
	device_unlock(dev);

	return count;
}
static DEVICE_ATTR_RW(mte_tcf_preferred);

static int register_mte_tcf_preferred_sysctl(void)
{
	unsigned int cpu;

	if (!system_supports_mte())
		return 0;

	for_each_possible_cpu(cpu) {
		per_cpu(mte_tcf_preferred, cpu) = MTE_CTRL_TCF_ASYNC;
		device_create_file(get_cpu_device(cpu),
				   &dev_attr_mte_tcf_preferred);
	}

	return 0;
}
subsys_initcall(register_mte_tcf_preferred_sysctl);

/*
 * Return 0 on success, the number of bytes not probed otherwise.
 */
size_t mte_probe_user_range(const char __user *uaddr, size_t size)
{
	const char __user *end = uaddr + size;
	int err = 0;
	char val;

	__raw_get_user(val, uaddr, err);
	if (err)
		return size;

	uaddr = PTR_ALIGN(uaddr, MTE_GRANULE_SIZE);
	while (uaddr < end) {
		/*
		 * A read is sufficient for mte, the caller should have probed
		 * for the pte write permission if required.
		 */
		__raw_get_user(val, uaddr, err);
		if (err)
			return end - uaddr;
		uaddr += MTE_GRANULE_SIZE;
	}
	(void)val;

	return 0;
}