1// SPDX-License-Identifier: GPL-2.0
2/*
3 * Augment the raw_syscalls tracepoints with the contents of the pointer arguments.
4 *
5 * Test it with:
6 *
7 * perf trace -e tools/perf/examples/bpf/augmented_raw_syscalls.c cat /etc/passwd > /dev/null
8 *
9 * This exactly matches what is marshalled into the raw_syscall:sys_enter
10 * payload expected by the 'perf trace' beautifiers.
11 *
12 * For now it just uses the existing tracepoint augmentation code in 'perf
13 * trace', in the next csets we'll hook up these with the sys_enter/sys_exit
14 * code that will combine entry/exit in a strace like way.
15 */
16
17#include <unistd.h>
18#include <linux/limits.h>
19#include <linux/socket.h>
20#include <pid_filter.h>
21
22/* bpf-output associated map */
23bpf_map(__augmented_syscalls__, PERF_EVENT_ARRAY, int, u32, __NR_CPUS__);
24
25/*
26 * string_args_len: one per syscall arg, 0 means not a string or don't copy it,
27 * 		    PATH_MAX for copying everything, any other value to limit
28 * 		    it a la 'strace -s strsize'.
29 */
30struct syscall {
31	bool	enabled;
32	u16	string_args_len[6];
33};
34
35bpf_map(syscalls, ARRAY, int, struct syscall, 512);
36
37/*
38 * What to augment at entry?
39 *
40 * Pointer arg payloads (filenames, etc) passed from userspace to the kernel
41 */
42bpf_map(syscalls_sys_enter, PROG_ARRAY, u32, u32, 512);
43
44/*
45 * What to augment at exit?
46 *
47 * Pointer arg payloads returned from the kernel (struct stat, etc) to userspace.
48 */
49bpf_map(syscalls_sys_exit, PROG_ARRAY, u32, u32, 512);
50
51struct syscall_enter_args {
52	unsigned long long common_tp_fields;
53	long		   syscall_nr;
54	unsigned long	   args[6];
55};
56
57struct syscall_exit_args {
58	unsigned long long common_tp_fields;
59	long		   syscall_nr;
60	long		   ret;
61};
62
63struct augmented_arg {
64	unsigned int	size;
65	int		err;
66	char		value[PATH_MAX];
67};
68
69pid_filter(pids_filtered);
70
71struct augmented_args_payload {
72       struct syscall_enter_args args;
73       union {
74		struct {
75			struct augmented_arg arg, arg2;
76		};
77		struct sockaddr_storage saddr;
78	};
79};
80
81// We need more tmp space than the BPF stack can give us
82bpf_map(augmented_args_tmp, PERCPU_ARRAY, int, struct augmented_args_payload, 1);
83
84static inline struct augmented_args_payload *augmented_args_payload(void)
85{
86	int key = 0;
87	return bpf_map_lookup_elem(&augmented_args_tmp, &key);
88}
89
90static inline int augmented__output(void *ctx, struct augmented_args_payload *args, int len)
91{
92	/* If perf_event_output fails, return non-zero so that it gets recorded unaugmented */
93	return perf_event_output(ctx, &__augmented_syscalls__, BPF_F_CURRENT_CPU, args, len);
94}
95
96static inline
97unsigned int augmented_arg__read_str(struct augmented_arg *augmented_arg, const void *arg, unsigned int arg_len)
98{
99	unsigned int augmented_len = sizeof(*augmented_arg);
100	int string_len = probe_read_str(&augmented_arg->value, arg_len, arg);
101
102	augmented_arg->size = augmented_arg->err = 0;
103	/*
104	 * probe_read_str may return < 0, e.g. -EFAULT
105	 * So we leave that in the augmented_arg->size that userspace will
106	 */
107	if (string_len > 0) {
108		augmented_len -= sizeof(augmented_arg->value) - string_len;
109		augmented_len &= sizeof(augmented_arg->value) - 1;
110		augmented_arg->size = string_len;
111	} else {
112		/*
113		 * So that username notice the error while still being able
114		 * to skip this augmented arg record
115		 */
116		augmented_arg->err = string_len;
117		augmented_len = offsetof(struct augmented_arg, value);
118	}
119
120	return augmented_len;
121}
122
123SEC("!raw_syscalls:unaugmented")
124int syscall_unaugmented(struct syscall_enter_args *args)
125{
126	return 1;
127}
128
129/*
130 * These will be tail_called from SEC("raw_syscalls:sys_enter"), so will find in
131 * augmented_args_tmp what was read by that raw_syscalls:sys_enter and go
132 * on from there, reading the first syscall arg as a string, i.e. open's
133 * filename.
134 */
135SEC("!syscalls:sys_enter_connect")
136int sys_enter_connect(struct syscall_enter_args *args)
137{
138	struct augmented_args_payload *augmented_args = augmented_args_payload();
139	const void *sockaddr_arg = (const void *)args->args[1];
140	unsigned int socklen = args->args[2];
141	unsigned int len = sizeof(augmented_args->args);
142
143        if (augmented_args == NULL)
144                return 1; /* Failure: don't filter */
145
146	if (socklen > sizeof(augmented_args->saddr))
147		socklen = sizeof(augmented_args->saddr);
148
149	probe_read(&augmented_args->saddr, socklen, sockaddr_arg);
150
151	return augmented__output(args, augmented_args, len + socklen);
152}
153
154SEC("!syscalls:sys_enter_sendto")
155int sys_enter_sendto(struct syscall_enter_args *args)
156{
157	struct augmented_args_payload *augmented_args = augmented_args_payload();
158	const void *sockaddr_arg = (const void *)args->args[4];
159	unsigned int socklen = args->args[5];
160	unsigned int len = sizeof(augmented_args->args);
161
162        if (augmented_args == NULL)
163                return 1; /* Failure: don't filter */
164
165	if (socklen > sizeof(augmented_args->saddr))
166		socklen = sizeof(augmented_args->saddr);
167
168	probe_read(&augmented_args->saddr, socklen, sockaddr_arg);
169
170	return augmented__output(args, augmented_args, len + socklen);
171}
172
173SEC("!syscalls:sys_enter_open")
174int sys_enter_open(struct syscall_enter_args *args)
175{
176	struct augmented_args_payload *augmented_args = augmented_args_payload();
177	const void *filename_arg = (const void *)args->args[0];
178	unsigned int len = sizeof(augmented_args->args);
179
180        if (augmented_args == NULL)
181                return 1; /* Failure: don't filter */
182
183	len += augmented_arg__read_str(&augmented_args->arg, filename_arg, sizeof(augmented_args->arg.value));
184
185	return augmented__output(args, augmented_args, len);
186}
187
188SEC("!syscalls:sys_enter_openat")
189int sys_enter_openat(struct syscall_enter_args *args)
190{
191	struct augmented_args_payload *augmented_args = augmented_args_payload();
192	const void *filename_arg = (const void *)args->args[1];
193	unsigned int len = sizeof(augmented_args->args);
194
195        if (augmented_args == NULL)
196                return 1; /* Failure: don't filter */
197
198	len += augmented_arg__read_str(&augmented_args->arg, filename_arg, sizeof(augmented_args->arg.value));
199
200	return augmented__output(args, augmented_args, len);
201}
202
203SEC("!syscalls:sys_enter_rename")
204int sys_enter_rename(struct syscall_enter_args *args)
205{
206	struct augmented_args_payload *augmented_args = augmented_args_payload();
207	const void *oldpath_arg = (const void *)args->args[0],
208		   *newpath_arg = (const void *)args->args[1];
209	unsigned int len = sizeof(augmented_args->args), oldpath_len;
210
211        if (augmented_args == NULL)
212                return 1; /* Failure: don't filter */
213
214	oldpath_len = augmented_arg__read_str(&augmented_args->arg, oldpath_arg, sizeof(augmented_args->arg.value));
215	len += oldpath_len + augmented_arg__read_str((void *)(&augmented_args->arg) + oldpath_len, newpath_arg, sizeof(augmented_args->arg.value));
216
217	return augmented__output(args, augmented_args, len);
218}
219
220SEC("!syscalls:sys_enter_renameat")
221int sys_enter_renameat(struct syscall_enter_args *args)
222{
223	struct augmented_args_payload *augmented_args = augmented_args_payload();
224	const void *oldpath_arg = (const void *)args->args[1],
225		   *newpath_arg = (const void *)args->args[3];
226	unsigned int len = sizeof(augmented_args->args), oldpath_len;
227
228        if (augmented_args == NULL)
229                return 1; /* Failure: don't filter */
230
231	oldpath_len = augmented_arg__read_str(&augmented_args->arg, oldpath_arg, sizeof(augmented_args->arg.value));
232	len += oldpath_len + augmented_arg__read_str((void *)(&augmented_args->arg) + oldpath_len, newpath_arg, sizeof(augmented_args->arg.value));
233
234	return augmented__output(args, augmented_args, len);
235}
236
237SEC("raw_syscalls:sys_enter")
238int sys_enter(struct syscall_enter_args *args)
239{
240	struct augmented_args_payload *augmented_args;
241	/*
242	 * We start len, the amount of data that will be in the perf ring
243	 * buffer, if this is not filtered out by one of pid_filter__has(),
244	 * syscall->enabled, etc, with the non-augmented raw syscall payload,
245	 * i.e. sizeof(augmented_args->args).
246	 *
247	 * We'll add to this as we add augmented syscalls right after that
248	 * initial, non-augmented raw_syscalls:sys_enter payload.
249	 */
250	unsigned int len = sizeof(augmented_args->args);
251	struct syscall *syscall;
252
253	if (pid_filter__has(&pids_filtered, getpid()))
254		return 0;
255
256	augmented_args = augmented_args_payload();
257	if (augmented_args == NULL)
258		return 1;
259
260	probe_read(&augmented_args->args, sizeof(augmented_args->args), args);
261
262	/*
263	 * Jump to syscall specific augmenter, even if the default one,
264	 * "!raw_syscalls:unaugmented" that will just return 1 to return the
265	 * unagmented tracepoint payload.
266	 */
267	bpf_tail_call(args, &syscalls_sys_enter, augmented_args->args.syscall_nr);
268
269	// If not found on the PROG_ARRAY syscalls map, then we're filtering it:
270	return 0;
271}
272
273SEC("raw_syscalls:sys_exit")
274int sys_exit(struct syscall_exit_args *args)
275{
276	struct syscall_exit_args exit_args;
277
278	if (pid_filter__has(&pids_filtered, getpid()))
279		return 0;
280
281	probe_read(&exit_args, sizeof(exit_args), args);
282	/*
283	 * Jump to syscall specific return augmenter, even if the default one,
284	 * "!raw_syscalls:unaugmented" that will just return 1 to return the
285	 * unagmented tracepoint payload.
286	 */
287	bpf_tail_call(args, &syscalls_sys_exit, exit_args.syscall_nr);
288	/*
289	 * If not found on the PROG_ARRAY syscalls map, then we're filtering it:
290	 */
291	return 0;
292}
293
294license(GPL);
295