summaryrefslogtreecommitdiffstats
path: root/kernel/events/callchain.c
blob: c04917cad1bfdc50fe4f00b08eaa58c9e7e7692e (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
/*
 * Performance events callchain code, extracted from core.c:
 *
 *  Copyright (C) 2008 Thomas Gleixner <tglx@linutronix.de>
 *  Copyright (C) 2008-2011 Red Hat, Inc., Ingo Molnar
 *  Copyright (C) 2008-2011 Red Hat, Inc., Peter Zijlstra
 *  Copyright  ©  2009 Paul Mackerras, IBM Corp. <paulus@au1.ibm.com>
 *
 * For licensing details see kernel-base/COPYING
 */

#include <linux/perf_event.h>
#include <linux/slab.h>
#include <linux/sched/task_stack.h>

#include "internal.h"

struct callchain_cpus_entries {
	struct rcu_head			rcu_head;
	struct perf_callchain_entry	*cpu_entries[0];
};

int sysctl_perf_event_max_stack __read_mostly = PERF_MAX_STACK_DEPTH;
int sysctl_perf_event_max_contexts_per_stack __read_mostly = PERF_MAX_CONTEXTS_PER_STACK;

static inline size_t perf_callchain_entry__sizeof(void)
{
	return (sizeof(struct perf_callchain_entry) +
		sizeof(__u64) * (sysctl_perf_event_max_stack +
				 sysctl_perf_event_max_contexts_per_stack));
}

static DEFINE_PER_CPU(int, callchain_recursion[PERF_NR_CONTEXTS]);
static atomic_t nr_callchain_events;
static DEFINE_MUTEX(callchain_mutex);
static struct callchain_cpus_entries *callchain_cpus_entries;


__weak void perf_callchain_kernel(struct perf_callchain_entry_ctx *entry,
				  struct pt_regs *regs)
{
}

__weak void perf_callchain_user(struct perf_callchain_entry_ctx *entry,
				struct pt_regs *regs)
{
}

static void release_callchain_buffers_rcu(struct rcu_head *head)
{
	struct callchain_cpus_entries *entries;
	int cpu;

	entries = container_of(head, struct callchain_cpus_entries, rcu_head);

	for_each_possible_cpu(cpu)
		kfree(entries->cpu_entries[cpu]);

	kfree(entries);
}

static void release_callchain_buffers(void)
{
	struct callchain_cpus_entries *entries;

	entries = callchain_cpus_entries;
	RCU_INIT_POINTER(callchain_cpus_entries, NULL);
	call_rcu(&entries->rcu_head, release_callchain_buffers_rcu);
}

static int alloc_callchain_buffers(void)
{
	int cpu;
	int size;
	struct callchain_cpus_entries *entries;

	/*
	 * We can't use the percpu allocation API for data that can be
	 * accessed from NMI. Use a temporary manual per cpu allocation
	 * until that gets sorted out.
	 */
	size = offsetof(struct callchain_cpus_entries, cpu_entries[nr_cpu_ids]);

	entries = kzalloc(size, GFP_KERNEL);
	if (!entries)
		return -ENOMEM;

	size = perf_callchain_entry__sizeof() * PERF_NR_CONTEXTS;

	for_each_possible_cpu(cpu) {
		entries->cpu_entries[cpu] = kmalloc_node(size, GFP_KERNEL,
							 cpu_to_node(cpu));
		if (!entries->cpu_entries[cpu])
			goto fail;
	}

	rcu_assign_pointer(callchain_cpus_entries, entries);

	return 0;

fail:
	for_each_possible_cpu(cpu)
		kfree(entries->cpu_entries[cpu]);
	kfree(entries);

	return -ENOMEM;
}

int get_callchain_buffers(int event_max_stack)
{
	int err = 0;
	int count;

	mutex_lock(&callchain_mutex);

	count = atomic_inc_return(&nr_callchain_events);
	if (WARN_ON_ONCE(count < 1)) {
		err = -EINVAL;
		goto exit;
	}

	if (count > 1) {
		/* If the allocation failed, give up */
		if (!callchain_cpus_entries)
			err = -ENOMEM;
		/*
		 * If requesting per event more than the global cap,
		 * return a different error to help userspace figure
		 * this out.
		 *
		 * And also do it here so that we have &callchain_mutex held.
		 */
		if (event_max_stack > sysctl_perf_event_max_stack)
			err = -EOVERFLOW;
		goto exit;
	}

	err = alloc_callchain_buffers();
exit:
	if (err)
		atomic_dec(&nr_callchain_events);

	mutex_unlock(&callchain_mutex);

	return err;
}

void put_callchain_buffers(void)
{
	if (atomic_dec_and_mutex_lock(&nr_callchain_events, &callchain_mutex)) {
		release_callchain_buffers();
		mutex_unlock(&callchain_mutex);
	}
}

static struct perf_callchain_entry *get_callchain_entry(int *rctx)
{
	int cpu;
	struct callchain_cpus_entries *entries;

	*rctx = get_recursion_context(this_cpu_ptr(callchain_recursion));
	if (*rctx == -1)
		return NULL;

	entries = rcu_dereference(callchain_cpus_entries);
	if (!entries)
		return NULL;

	cpu = smp_processor_id();

	return (((void *)entries->cpu_entries[cpu]) +
		(*rctx * perf_callchain_entry__sizeof()));
}

static void
put_callchain_entry(int rctx)
{
	put_recursion_context(this_cpu_ptr(callchain_recursion), rctx);
}

struct perf_callchain_entry *
perf_callchain(struct perf_event *event, struct pt_regs *regs)
{
	bool kernel = !event->attr.exclude_callchain_kernel;
	bool user   = !event->attr.exclude_callchain_user;
	/* Disallow cross-task user callchains. */
	bool crosstask = event->ctx->task && event->ctx->task != current;
	const u32 max_stack = event->attr.sample_max_stack;

	if (!kernel && !user)
		return NULL;

	return get_perf_callchain(regs, 0, kernel, user, max_stack, crosstask, true);
}

struct perf_callchain_entry *
get_perf_callchain(struct pt_regs *regs, u32 init_nr, bool kernel, bool user,
		   u32 max_stack, bool crosstask, bool add_mark)
{
	struct perf_callchain_entry *entry;
	struct perf_callchain_entry_ctx ctx;
	int rctx;

	entry = get_callchain_entry(&rctx);
	if (rctx == -1)
		return NULL;

	if (!entry)
		goto exit_put;

	ctx.entry     = entry;
	ctx.max_stack = max_stack;
	ctx.nr	      = entry->nr = init_nr;
	ctx.contexts       = 0;
	ctx.contexts_maxed = false;

	if (kernel && !user_mode(regs)) {
		if (add_mark)
			perf_callchain_store_context(&ctx, PERF_CONTEXT_KERNEL);
		perf_callchain_kernel(&ctx, regs);
	}

	if (user) {
		if (!user_mode(regs)) {
			if  (current->mm)
				regs = task_pt_regs(current);
			else
				regs = NULL;
		}

		if (regs) {
			if (crosstask)
				goto exit_put;

			if (add_mark)
				perf_callchain_store_context(&ctx, PERF_CONTEXT_USER);
			perf_callchain_user(&ctx, regs);
		}
	}

exit_put:
	put_callchain_entry(rctx);

	return entry;
}

/*
 * Used for sysctl_perf_event_max_stack and
 * sysctl_perf_event_max_contexts_per_stack.
 */
int perf_event_max_stack_handler(struct ctl_table *table, int write,
				 void __user *buffer, size_t *lenp, loff_t *ppos)
{
	int *value = table->data;
	int new_value = *value, ret;
	struct ctl_table new_table = *table;

	new_table.data = &new_value;
	ret = proc_dointvec_minmax(&new_table, write, buffer, lenp, ppos);
	if (ret || !write)
		return ret;

	mutex_lock(&callchain_mutex);
	if (atomic_read(&nr_callchain_events))
		ret = -EBUSY;
	else
		*value = new_value;

	mutex_unlock(&callchain_mutex);

	return ret;
}