summaryrefslogtreecommitdiff
path: root/arch/arm64/kernel/mte.c
blob: 80b62fe49dcfd329971065afb08adc59b61647d2 (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
// SPDX-License-Identifier: GPL-2.0-only
/*
 * Copyright (C) 2020 ARM Ltd.
 */

#include <linux/bitops.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/uio.h>

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

u64 gcr_kernel_excl __ro_after_init;

static void mte_sync_page_tags(struct page *page, pte_t *ptep, bool check_swap)
{
	pte_t old_pte = READ_ONCE(*ptep);

	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;
	}

	page_kasan_tag_reset(page);
	/*
	 * We need smp_wmb() in between setting the flags and clearing the
	 * tags because if another thread reads page->flags and builds a
	 * tagged address out of it, there is an actual dependency to the
	 * memory access, but on the current thread we do not guarantee that
	 * the new page->flags are visible before the tags were updated.
	 */
	smp_wmb();
	mte_clear_page_tags(page_address(page));
}

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

	/* 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, ptep, check_swap);
	}
}

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;
}

u8 mte_get_mem_tag(void *addr)
{
	if (!system_supports_mte())
		return 0xFF;

	asm(__MTE_PREAMBLE "ldg %0, [%0]"
	    : "+r" (addr));

	return mte_get_ptr_tag(addr);
}

u8 mte_get_random_tag(void)
{
	void *addr;

	if (!system_supports_mte())
		return 0xFF;

	asm(__MTE_PREAMBLE "irg %0, %0"
	    : "+r" (addr));

	return mte_get_ptr_tag(addr);
}

void *mte_set_mem_tag_range(void *addr, size_t size, u8 tag)
{
	void *ptr = addr;

	if ((!system_supports_mte()) || (size == 0))
		return addr;

	/* Make sure that size is MTE granule aligned. */
	WARN_ON(size & (MTE_GRANULE_SIZE - 1));

	/* Make sure that the address is MTE granule aligned. */
	WARN_ON((u64)addr & (MTE_GRANULE_SIZE - 1));

	tag = 0xF0 | tag;
	ptr = (void *)__tag_set(ptr, tag);

	mte_assign_mem_tag_range(ptr, size);

	return ptr;
}

void mte_init_tags(u64 max_tag)
{
	static bool gcr_kernel_excl_initialized;

	if (!gcr_kernel_excl_initialized) {
		/*
		 * The format of the tags in KASAN is 0xFF and in MTE is 0xF.
		 * This conversion extracts an MTE tag from a KASAN tag.
		 */
		u64 incl = GENMASK(FIELD_GET(MTE_TAG_MASK >> MTE_TAG_SHIFT,
					     max_tag), 0);

		gcr_kernel_excl = ~incl & SYS_GCR_EL1_EXCL_MASK;
		gcr_kernel_excl_initialized = true;
	}

	/* Enable the kernel exclude mask for random tags generation. */
	write_sysreg_s(SYS_GCR_EL1_RRND | gcr_kernel_excl, SYS_GCR_EL1);
}

void mte_enable_kernel(void)
{
	/* Enable MTE Sync Mode for EL1. */
	sysreg_clear_set(sctlr_el1, SCTLR_ELx_TCF_MASK, SCTLR_ELx_TCF_SYNC);
	isb();
}

static void update_sctlr_el1_tcf0(u64 tcf0)
{
	/* ISB required for the kernel uaccess routines */
	sysreg_clear_set(sctlr_el1, SCTLR_EL1_TCF0_MASK, tcf0);
	isb();
}

static void set_sctlr_el1_tcf0(u64 tcf0)
{
	/*
	 * mte_thread_switch() checks current->thread.sctlr_tcf0 as an
	 * optimisation. Disable preemption so that it does not see
	 * the variable update before the SCTLR_EL1.TCF0 one.
	 */
	preempt_disable();
	current->thread.sctlr_tcf0 = tcf0;
	update_sctlr_el1_tcf0(tcf0);
	preempt_enable();
}

static void update_gcr_el1_excl(u64 excl)
{

	/*
	 * Note that the mask controlled by the user via prctl() is an
	 * include while GCR_EL1 accepts an exclude mask.
	 * No need for ISB since this only affects EL0 currently, implicit
	 * with ERET.
	 */
	sysreg_clear_set_s(SYS_GCR_EL1, SYS_GCR_EL1_EXCL_MASK, excl);
}

static void set_gcr_el1_excl(u64 excl)
{
	current->thread.gcr_user_excl = excl;

	/*
	 * SYS_GCR_EL1 will be set to current->thread.gcr_user_excl value
	 * by mte_set_user_gcr() in kernel_exit,
	 */
}

void flush_mte_state(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 */
	set_sctlr_el1_tcf0(SCTLR_EL1_TCF0_NONE);
	/* reset tag generation mask */
	set_gcr_el1_excl(SYS_GCR_EL1_EXCL_MASK);
}

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

	/* avoid expensive SCTLR_EL1 accesses if no change */
	if (current->thread.sctlr_tcf0 != next->thread.sctlr_tcf0)
		update_sctlr_el1_tcf0(next->thread.sctlr_tcf0);
}

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

	update_gcr_el1_excl(gcr_kernel_excl);
}

long set_mte_ctrl(struct task_struct *task, unsigned long arg)
{
	u64 tcf0;
	u64 gcr_excl = ~((arg & PR_MTE_TAG_MASK) >> PR_MTE_TAG_SHIFT) &
		       SYS_GCR_EL1_EXCL_MASK;

	if (!system_supports_mte())
		return 0;

	switch (arg & PR_MTE_TCF_MASK) {
	case PR_MTE_TCF_NONE:
		tcf0 = SCTLR_EL1_TCF0_NONE;
		break;
	case PR_MTE_TCF_SYNC:
		tcf0 = SCTLR_EL1_TCF0_SYNC;
		break;
	case PR_MTE_TCF_ASYNC:
		tcf0 = SCTLR_EL1_TCF0_ASYNC;
		break;
	default:
		return -EINVAL;
	}

	if (task != current) {
		task->thread.sctlr_tcf0 = tcf0;
		task->thread.gcr_user_excl = gcr_excl;
	} else {
		set_sctlr_el1_tcf0(tcf0);
		set_gcr_el1_excl(gcr_excl);
	}

	return 0;
}

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

	if (!system_supports_mte())
		return 0;

	ret = incl << PR_MTE_TAG_SHIFT;

	switch (task->thread.sctlr_tcf0) {
	case SCTLR_EL1_TCF0_NONE:
		ret |= PR_MTE_TCF_NONE;
		break;
	case SCTLR_EL1_TCF0_SYNC:
		ret |= PR_MTE_TCF_SYNC;
		break;
	case SCTLR_EL1_TCF0_ASYNC:
		ret |= PR_MTE_TCF_ASYNC;
		break;
	}

	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;
}