summaryrefslogtreecommitdiff
path: root/tools/perf/util/bpf_skel/augmented_raw_syscalls.bpf.c
blob: 90ce22f9c1a940049dd2fca3c83b6b51b43f136d (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
// SPDX-License-Identifier: GPL-2.0
/*
 * Augment the raw_syscalls tracepoints with the contents of the pointer arguments.
 *
 * This exactly matches what is marshalled into the raw_syscall:sys_enter
 * payload expected by the 'perf trace' beautifiers.
 */

#include <linux/bpf.h>
#include <bpf/bpf_helpers.h>
#include <linux/limits.h>

/**
 * is_power_of_2() - check if a value is a power of two
 * @n: the value to check
 *
 * Determine whether some value is a power of two, where zero is *not*
 * considered a power of two.  Return: true if @n is a power of 2, otherwise
 * false.
 */
#define is_power_of_2(n) (n != 0 && ((n & (n - 1)) == 0))

#define MAX_CPUS  4096

// FIXME: These should come from system headers
typedef char bool;
typedef int pid_t;
typedef long long int __s64;
typedef __s64 time64_t;

struct timespec64 {
	time64_t	tv_sec;
	long int	tv_nsec;
};

/* bpf-output associated map */
struct __augmented_syscalls__ {
	__uint(type, BPF_MAP_TYPE_PERF_EVENT_ARRAY);
	__type(key, int);
	__type(value, __u32);
	__uint(max_entries, MAX_CPUS);
} __augmented_syscalls__ SEC(".maps");

/*
 * What to augment at entry?
 *
 * Pointer arg payloads (filenames, etc) passed from userspace to the kernel
 */
struct syscalls_sys_enter {
	__uint(type, BPF_MAP_TYPE_PROG_ARRAY);
	__type(key, __u32);
	__type(value, __u32);
	__uint(max_entries, 512);
} syscalls_sys_enter SEC(".maps");

/*
 * What to augment at exit?
 *
 * Pointer arg payloads returned from the kernel (struct stat, etc) to userspace.
 */
struct syscalls_sys_exit {
	__uint(type, BPF_MAP_TYPE_PROG_ARRAY);
	__type(key, __u32);
	__type(value, __u32);
	__uint(max_entries, 512);
} syscalls_sys_exit SEC(".maps");

struct syscall_enter_args {
	unsigned long long common_tp_fields;
	long		   syscall_nr;
	unsigned long	   args[6];
};

struct syscall_exit_args {
	unsigned long long common_tp_fields;
	long		   syscall_nr;
	long		   ret;
};

struct augmented_arg {
	unsigned int	size;
	int		err;
	char		value[PATH_MAX];
};

struct pids_filtered {
	__uint(type, BPF_MAP_TYPE_HASH);
	__type(key, pid_t);
	__type(value, bool);
	__uint(max_entries, 64);
} pids_filtered SEC(".maps");

/*
 * Desired design of maximum size and alignment (see RFC2553)
 */
#define SS_MAXSIZE   128     /* Implementation specific max size */

typedef unsigned short sa_family_t;

/*
 * FIXME: Should come from system headers
 *
 * The definition uses anonymous union and struct in order to control the
 * default alignment.
 */
struct sockaddr_storage {
	union {
		struct {
			sa_family_t    ss_family; /* address family */
			/* Following field(s) are implementation specific */
			char __data[SS_MAXSIZE - sizeof(unsigned short)];
				/* space to achieve desired size, */
				/* _SS_MAXSIZE value minus size of ss_family */
		};
		void *__align; /* implementation specific desired alignment */
	};
};

struct augmented_args_payload {
       struct syscall_enter_args args;
       union {
		struct {
			struct augmented_arg arg, arg2;
		};
		struct sockaddr_storage saddr;
		char   __data[sizeof(struct augmented_arg)];
	};
};

// We need more tmp space than the BPF stack can give us
struct augmented_args_tmp {
	__uint(type, BPF_MAP_TYPE_PERCPU_ARRAY);
	__type(key, int);
	__type(value, struct augmented_args_payload);
	__uint(max_entries, 1);
} augmented_args_tmp SEC(".maps");

static inline struct augmented_args_payload *augmented_args_payload(void)
{
	int key = 0;
	return bpf_map_lookup_elem(&augmented_args_tmp, &key);
}

static inline int augmented__output(void *ctx, struct augmented_args_payload *args, int len)
{
	/* If perf_event_output fails, return non-zero so that it gets recorded unaugmented */
	return bpf_perf_event_output(ctx, &__augmented_syscalls__, BPF_F_CURRENT_CPU, args, len);
}

static inline
unsigned int augmented_arg__read_str(struct augmented_arg *augmented_arg, const void *arg, unsigned int arg_len)
{
	unsigned int augmented_len = sizeof(*augmented_arg);
	int string_len = bpf_probe_read_str(&augmented_arg->value, arg_len, arg);

	augmented_arg->size = augmented_arg->err = 0;
	/*
	 * probe_read_str may return < 0, e.g. -EFAULT
	 * So we leave that in the augmented_arg->size that userspace will
	 */
	if (string_len > 0) {
		augmented_len -= sizeof(augmented_arg->value) - string_len;
		_Static_assert(is_power_of_2(sizeof(augmented_arg->value)), "sizeof(augmented_arg->value) needs to be a power of two");
		augmented_len &= sizeof(augmented_arg->value) - 1;
		augmented_arg->size = string_len;
	} else {
		/*
		 * So that username notice the error while still being able
		 * to skip this augmented arg record
		 */
		augmented_arg->err = string_len;
		augmented_len = offsetof(struct augmented_arg, value);
	}

	return augmented_len;
}

SEC("tp/raw_syscalls/sys_enter")
int syscall_unaugmented(struct syscall_enter_args *args)
{
	return 1;
}

/*
 * These will be tail_called from SEC("raw_syscalls:sys_enter"), so will find in
 * augmented_args_tmp what was read by that raw_syscalls:sys_enter and go
 * on from there, reading the first syscall arg as a string, i.e. open's
 * filename.
 */
SEC("tp/syscalls/sys_enter_connect")
int sys_enter_connect(struct syscall_enter_args *args)
{
	struct augmented_args_payload *augmented_args = augmented_args_payload();
	const void *sockaddr_arg = (const void *)args->args[1];
	unsigned int socklen = args->args[2];
	unsigned int len = sizeof(augmented_args->args);

        if (augmented_args == NULL)
                return 1; /* Failure: don't filter */

	_Static_assert(is_power_of_2(sizeof(augmented_args->saddr)), "sizeof(augmented_args->saddr) needs to be a power of two");
	socklen &= sizeof(augmented_args->saddr) - 1;

	bpf_probe_read(&augmented_args->saddr, socklen, sockaddr_arg);

	return augmented__output(args, augmented_args, len + socklen);
}

SEC("tp/syscalls/sys_enter_sendto")
int sys_enter_sendto(struct syscall_enter_args *args)
{
	struct augmented_args_payload *augmented_args = augmented_args_payload();
	const void *sockaddr_arg = (const void *)args->args[4];
	unsigned int socklen = args->args[5];
	unsigned int len = sizeof(augmented_args->args);

        if (augmented_args == NULL)
                return 1; /* Failure: don't filter */

	socklen &= sizeof(augmented_args->saddr) - 1;

	bpf_probe_read(&augmented_args->saddr, socklen, sockaddr_arg);

	return augmented__output(args, augmented_args, len + socklen);
}

SEC("tp/syscalls/sys_enter_open")
int sys_enter_open(struct syscall_enter_args *args)
{
	struct augmented_args_payload *augmented_args = augmented_args_payload();
	const void *filename_arg = (const void *)args->args[0];
	unsigned int len = sizeof(augmented_args->args);

        if (augmented_args == NULL)
                return 1; /* Failure: don't filter */

	len += augmented_arg__read_str(&augmented_args->arg, filename_arg, sizeof(augmented_args->arg.value));

	return augmented__output(args, augmented_args, len);
}

SEC("tp/syscalls/sys_enter_openat")
int sys_enter_openat(struct syscall_enter_args *args)
{
	struct augmented_args_payload *augmented_args = augmented_args_payload();
	const void *filename_arg = (const void *)args->args[1];
	unsigned int len = sizeof(augmented_args->args);

        if (augmented_args == NULL)
                return 1; /* Failure: don't filter */

	len += augmented_arg__read_str(&augmented_args->arg, filename_arg, sizeof(augmented_args->arg.value));

	return augmented__output(args, augmented_args, len);
}

SEC("tp/syscalls/sys_enter_rename")
int sys_enter_rename(struct syscall_enter_args *args)
{
	struct augmented_args_payload *augmented_args = augmented_args_payload();
	const void *oldpath_arg = (const void *)args->args[0],
		   *newpath_arg = (const void *)args->args[1];
	unsigned int len = sizeof(augmented_args->args), oldpath_len;

        if (augmented_args == NULL)
                return 1; /* Failure: don't filter */

	oldpath_len = augmented_arg__read_str(&augmented_args->arg, oldpath_arg, sizeof(augmented_args->arg.value));
	len += oldpath_len + augmented_arg__read_str((void *)(&augmented_args->arg) + oldpath_len, newpath_arg, sizeof(augmented_args->arg.value));

	return augmented__output(args, augmented_args, len);
}

SEC("tp/syscalls/sys_enter_renameat")
int sys_enter_renameat(struct syscall_enter_args *args)
{
	struct augmented_args_payload *augmented_args = augmented_args_payload();
	const void *oldpath_arg = (const void *)args->args[1],
		   *newpath_arg = (const void *)args->args[3];
	unsigned int len = sizeof(augmented_args->args), oldpath_len;

        if (augmented_args == NULL)
                return 1; /* Failure: don't filter */

	oldpath_len = augmented_arg__read_str(&augmented_args->arg, oldpath_arg, sizeof(augmented_args->arg.value));
	len += oldpath_len + augmented_arg__read_str((void *)(&augmented_args->arg) + oldpath_len, newpath_arg, sizeof(augmented_args->arg.value));

	return augmented__output(args, augmented_args, len);
}

#define PERF_ATTR_SIZE_VER0     64      /* sizeof first published struct */

// we need just the start, get the size to then copy it
struct perf_event_attr_size {
        __u32                   type;
        /*
         * Size of the attr structure, for fwd/bwd compat.
         */
        __u32                   size;
};

SEC("tp/syscalls/sys_enter_perf_event_open")
int sys_enter_perf_event_open(struct syscall_enter_args *args)
{
	struct augmented_args_payload *augmented_args = augmented_args_payload();
	const struct perf_event_attr_size *attr = (const struct perf_event_attr_size *)args->args[0], *attr_read;
	unsigned int len = sizeof(augmented_args->args);

        if (augmented_args == NULL)
		goto failure;

	if (bpf_probe_read(&augmented_args->__data, sizeof(*attr), attr) < 0)
		goto failure;

	attr_read = (const struct perf_event_attr_size *)augmented_args->__data;

	__u32 size = attr_read->size;

	if (!size)
		size = PERF_ATTR_SIZE_VER0;

	if (size > sizeof(augmented_args->__data))
                goto failure;

	// Now that we read attr->size and tested it against the size limits, read it completely
	if (bpf_probe_read(&augmented_args->__data, size, attr) < 0)
		goto failure;

	return augmented__output(args, augmented_args, len + size);
failure:
	return 1; /* Failure: don't filter */
}

SEC("tp/syscalls/sys_enter_clock_nanosleep")
int sys_enter_clock_nanosleep(struct syscall_enter_args *args)
{
	struct augmented_args_payload *augmented_args = augmented_args_payload();
	const void *rqtp_arg = (const void *)args->args[2];
	unsigned int len = sizeof(augmented_args->args);
	__u32 size = sizeof(struct timespec64);

        if (augmented_args == NULL)
		goto failure;

	if (size > sizeof(augmented_args->__data))
                goto failure;

	bpf_probe_read(&augmented_args->__data, size, rqtp_arg);

	return augmented__output(args, augmented_args, len + size);
failure:
	return 1; /* Failure: don't filter */
}

static pid_t getpid(void)
{
	return bpf_get_current_pid_tgid();
}

static bool pid_filter__has(struct pids_filtered *pids, pid_t pid)
{
	return bpf_map_lookup_elem(pids, &pid) != NULL;
}

SEC("tp/raw_syscalls/sys_enter")
int sys_enter(struct syscall_enter_args *args)
{
	struct augmented_args_payload *augmented_args;
	/*
	 * We start len, the amount of data that will be in the perf ring
	 * buffer, if this is not filtered out by one of pid_filter__has(),
	 * syscall->enabled, etc, with the non-augmented raw syscall payload,
	 * i.e. sizeof(augmented_args->args).
	 *
	 * We'll add to this as we add augmented syscalls right after that
	 * initial, non-augmented raw_syscalls:sys_enter payload.
	 */

	if (pid_filter__has(&pids_filtered, getpid()))
		return 0;

	augmented_args = augmented_args_payload();
	if (augmented_args == NULL)
		return 1;

	bpf_probe_read(&augmented_args->args, sizeof(augmented_args->args), args);

	/*
	 * Jump to syscall specific augmenter, even if the default one,
	 * "!raw_syscalls:unaugmented" that will just return 1 to return the
	 * unaugmented tracepoint payload.
	 */
	bpf_tail_call(args, &syscalls_sys_enter, augmented_args->args.syscall_nr);

	// If not found on the PROG_ARRAY syscalls map, then we're filtering it:
	return 0;
}

SEC("tp/raw_syscalls/sys_exit")
int sys_exit(struct syscall_exit_args *args)
{
	struct syscall_exit_args exit_args;

	if (pid_filter__has(&pids_filtered, getpid()))
		return 0;

	bpf_probe_read(&exit_args, sizeof(exit_args), args);
	/*
	 * Jump to syscall specific return augmenter, even if the default one,
	 * "!raw_syscalls:unaugmented" that will just return 1 to return the
	 * unaugmented tracepoint payload.
	 */
	bpf_tail_call(args, &syscalls_sys_exit, exit_args.syscall_nr);
	/*
	 * If not found on the PROG_ARRAY syscalls map, then we're filtering it:
	 */
	return 0;
}

char _license[] SEC("license") = "GPL";