summaryrefslogtreecommitdiffstats
path: root/kernel/scs.c
blob: e2a71fc82fa0686c48bb62f7d559e47445096237 (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
// SPDX-License-Identifier: GPL-2.0
/*
 * Shadow Call Stack support.
 *
 * Copyright (C) 2019 Google LLC
 */

#include <linux/cpuhotplug.h>
#include <linux/kasan.h>
#include <linux/mm.h>
#include <linux/scs.h>
#include <linux/vmalloc.h>
#include <linux/vmstat.h>

static void __scs_account(void *s, int account)
{
	struct page *scs_page = vmalloc_to_page(s);

	mod_node_page_state(page_pgdat(scs_page), NR_KERNEL_SCS_KB,
			    account * (SCS_SIZE / SZ_1K));
}

/* Matches NR_CACHED_STACKS for VMAP_STACK */
#define NR_CACHED_SCS 2
static DEFINE_PER_CPU(void *, scs_cache[NR_CACHED_SCS]);

static void *__scs_alloc(int node)
{
	int i;
	void *s;

	for (i = 0; i < NR_CACHED_SCS; i++) {
		s = this_cpu_xchg(scs_cache[i], NULL);
		if (s) {
			kasan_unpoison_vmalloc(s, SCS_SIZE);
			memset(s, 0, SCS_SIZE);
			return s;
		}
	}

	return __vmalloc_node_range(SCS_SIZE, 1, VMALLOC_START, VMALLOC_END,
				    GFP_SCS, PAGE_KERNEL, 0, node,
				    __builtin_return_address(0));
}

void *scs_alloc(int node)
{
	void *s;

	s = __scs_alloc(node);
	if (!s)
		return NULL;

	*__scs_magic(s) = SCS_END_MAGIC;

	/*
	 * Poison the allocation to catch unintentional accesses to
	 * the shadow stack when KASAN is enabled.
	 */
	kasan_poison_vmalloc(s, SCS_SIZE);
	__scs_account(s, 1);
	return s;
}

void scs_free(void *s)
{
	int i;

	__scs_account(s, -1);

	/*
	 * We cannot sleep as this can be called in interrupt context,
	 * so use this_cpu_cmpxchg to update the cache, and vfree_atomic
	 * to free the stack.
	 */

	for (i = 0; i < NR_CACHED_SCS; i++)
		if (this_cpu_cmpxchg(scs_cache[i], 0, s) == NULL)
			return;

	vfree_atomic(s);
}

static int scs_cleanup(unsigned int cpu)
{
	int i;
	void **cache = per_cpu_ptr(scs_cache, cpu);

	for (i = 0; i < NR_CACHED_SCS; i++) {
		vfree(cache[i]);
		cache[i] = NULL;
	}

	return 0;
}

void __init scs_init(void)
{
	cpuhp_setup_state(CPUHP_BP_PREPARE_DYN, "scs:scs_cache", NULL,
			  scs_cleanup);
}

int scs_prepare(struct task_struct *tsk, int node)
{
	void *s = scs_alloc(node);

	if (!s)
		return -ENOMEM;

	task_scs(tsk) = task_scs_sp(tsk) = s;
	return 0;
}

static void scs_check_usage(struct task_struct *tsk)
{
	static unsigned long highest;

	unsigned long *p, prev, curr = highest, used = 0;

	if (!IS_ENABLED(CONFIG_DEBUG_STACK_USAGE))
		return;

	for (p = task_scs(tsk); p < __scs_magic(tsk); ++p) {
		if (!READ_ONCE_NOCHECK(*p))
			break;
		used += sizeof(*p);
	}

	while (used > curr) {
		prev = cmpxchg_relaxed(&highest, curr, used);

		if (prev == curr) {
			pr_info("%s (%d): highest shadow stack usage: %lu bytes\n",
				tsk->comm, task_pid_nr(tsk), used);
			break;
		}

		curr = prev;
	}
}

void scs_release(struct task_struct *tsk)
{
	void *s = task_scs(tsk);

	if (!s)
		return;

	WARN(task_scs_end_corrupted(tsk),
	     "corrupted shadow stack detected when freeing task\n");
	scs_check_usage(tsk);
	scs_free(s);
}