update kernel to 5.10.198

hc

2024-01-03 2f7c68cb55ecb7331f2381deb497c27155f32faf

 kernel/tools/bpf/bpftool/map_perf_ring.c
..
..
@@ -1,4 +1,4 @@
1
-// SPDX-License-Identifier: GPL-2.0-only
1
+// SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
2
2
 /* Copyright (C) 2018 Netronome Systems, Inc. */
3
3
 /* This program is free software; you can redistribute it and/or
4
4
  * modify it under the terms of version 2 of the GNU General Public
..
..
@@ -6,7 +6,7 @@
6
6
  */
7
7
 #include <errno.h>
8
8
 #include <fcntl.h>
9
-#include <libbpf.h>
9
+#include <bpf/libbpf.h>
10
10
 #include <poll.h>
11
11
 #include <signal.h>
12
12
 #include <stdbool.h>
..
..
@@ -21,14 +21,14 @@
21
21
 #include <sys/mman.h>
22
22
 #include <sys/syscall.h>
23
23
 
24
-#include <bpf.h>
24
+#include <bpf/bpf.h>
25
25
 #include <perf-sys.h>
26
26
 
27
27
 #include "main.h"
28
28
 
29
29
 #define MMAP_PAGE_CNT	16
30
30
 
31
-static bool stop;
31
+static volatile bool stop;
32
32
 
33
33
 struct event_ring_info {
34
34
 	int fd;
..
..
@@ -39,9 +39,15 @@
39
39
 
40
40
 struct perf_event_sample {
41
41
 	struct perf_event_header header;
42
-	u64 time;
42
+	__u64 time;
43
43
 	__u32 size;
44
44
 	unsigned char data[];
45
+};
46
+
47
+struct perf_event_lost {
48
+	struct perf_event_header header;
49
+	__u64 id;
50
+	__u64 lost;
45
51
 };
46
52
 
47
53
 static void int_exit(int signo)
..
..
@@ -50,24 +56,32 @@
50
56
 	stop = true;
51
57
 }
52
58
 
53
-static enum bpf_perf_event_ret print_bpf_output(void *event, void *priv)
59
+struct event_pipe_ctx {
60
+	bool all_cpus;
61
+	int cpu;
62
+	int idx;
63
+};
64
+
65
+static enum bpf_perf_event_ret
66
+print_bpf_output(void *private_data, int cpu, struct perf_event_header *event)
54
67
 {
55
-	struct event_ring_info *ring = priv;
56
-	struct perf_event_sample *e = event;
57
-	struct {
58
-		struct perf_event_header header;
59
-		__u64 id;
60
-		__u64 lost;
61
-	} *lost = event;
68
+	struct perf_event_sample *e = container_of(event,
69
+						   struct perf_event_sample,
70
+						   header);
71
+	struct perf_event_lost *lost = container_of(event,
72
+						    struct perf_event_lost,
73
+						    header);
74
+	struct event_pipe_ctx *ctx = private_data;
75
+	int idx = ctx->all_cpus ? cpu : ctx->idx;
62
76
 
63
77
 	if (json_output) {
64
78
 		jsonw_start_object(json_wtr);
65
79
 		jsonw_name(json_wtr, "type");
66
80
 		jsonw_uint(json_wtr, e->header.type);
67
81
 		jsonw_name(json_wtr, "cpu");
68
-		jsonw_uint(json_wtr, ring->cpu);
82
+		jsonw_uint(json_wtr, cpu);
69
83
 		jsonw_name(json_wtr, "index");
70
-		jsonw_uint(json_wtr, ring->key);
84
+		jsonw_uint(json_wtr, idx);
71
85
 		if (e->header.type == PERF_RECORD_SAMPLE) {
72
86
 			jsonw_name(json_wtr, "timestamp");
73
87
 			jsonw_uint(json_wtr, e->time);
..
..
@@ -87,7 +101,7 @@
87
101
 		if (e->header.type == PERF_RECORD_SAMPLE) {
88
102
 			printf("== @%lld.%09lld CPU: %d index: %d =====\n",
89
103
 			       e->time / 1000000000ULL, e->time % 1000000000ULL,
90
-			       ring->cpu, ring->key);
104
+			       cpu, idx);
91
105
 			fprint_hex(stdout, e->data, e->size, " ");
92
106
 			printf("\n");
93
107
 		} else if (e->header.type == PERF_RECORD_LOST) {
..
..
@@ -101,87 +115,25 @@
101
115
 	return LIBBPF_PERF_EVENT_CONT;
102
116
 }
103
117
 
104
-static void
105
-perf_event_read(struct event_ring_info *ring, void **buf, size_t *buf_len)
118
+int do_event_pipe(int argc, char **argv)
106
119
 {
107
-	enum bpf_perf_event_ret ret;
108
-
109
-	ret = bpf_perf_event_read_simple(ring->mem,
110
-					 MMAP_PAGE_CNT * get_page_size(),
111
-					 get_page_size(), buf, buf_len,
112
-					 print_bpf_output, ring);
113
-	if (ret != LIBBPF_PERF_EVENT_CONT) {
114
-		fprintf(stderr, "perf read loop failed with %d\n", ret);
115
-		stop = true;
116
-	}
117
-}
118
-
119
-static int perf_mmap_size(void)
120
-{
121
-	return get_page_size() * (MMAP_PAGE_CNT + 1);
122
-}
123
-
124
-static void *perf_event_mmap(int fd)
125
-{
126
-	int mmap_size = perf_mmap_size();
127
-	void *base;
128
-
129
-	base = mmap(NULL, mmap_size, PROT_READ | PROT_WRITE, MAP_SHARED, fd, 0);
130
-	if (base == MAP_FAILED) {
131
-		p_err("event mmap failed: %s\n", strerror(errno));
132
-		return NULL;
133
-	}
134
-
135
-	return base;
136
-}
137
-
138
-static void perf_event_unmap(void *mem)
139
-{
140
-	if (munmap(mem, perf_mmap_size()))
141
-		fprintf(stderr, "Can't unmap ring memory!\n");
142
-}
143
-
144
-static int bpf_perf_event_open(int map_fd, int key, int cpu)
145
-{
146
-	struct perf_event_attr attr = {
120
+	struct perf_event_attr perf_attr = {
147
121
 		.sample_type = PERF_SAMPLE_RAW | PERF_SAMPLE_TIME,
148
122
 		.type = PERF_TYPE_SOFTWARE,
149
123
 		.config = PERF_COUNT_SW_BPF_OUTPUT,
124
+		.sample_period = 1,
125
+		.wakeup_events = 1,
150
126
 	};
151
-	int pmu_fd;
152
-
153
-	pmu_fd = sys_perf_event_open(&attr, -1, cpu, -1, 0);
154
-	if (pmu_fd < 0) {
155
-		p_err("failed to open perf event %d for CPU %d", key, cpu);
156
-		return -1;
157
-	}
158
-
159
-	if (bpf_map_update_elem(map_fd, &key, &pmu_fd, BPF_ANY)) {
160
-		p_err("failed to update map for event %d for CPU %d", key, cpu);
161
-		goto err_close;
162
-	}
163
-	if (ioctl(pmu_fd, PERF_EVENT_IOC_ENABLE, 0)) {
164
-		p_err("failed to enable event %d for CPU %d", key, cpu);
165
-		goto err_close;
166
-	}
167
-
168
-	return pmu_fd;
169
-
170
-err_close:
171
-	close(pmu_fd);
172
-	return -1;
173
-}
174
-
175
-int do_event_pipe(int argc, char **argv)
176
-{
177
-	int i, nfds, map_fd, index = -1, cpu = -1;
178
127
 	struct bpf_map_info map_info = {};
179
-	struct event_ring_info *rings;
180
-	size_t tmp_buf_sz = 0;
181
-	void *tmp_buf = NULL;
182
-	struct pollfd *pfds;
128
+	struct perf_buffer_raw_opts opts = {};
129
+	struct event_pipe_ctx ctx = {
130
+		.all_cpus = true,
131
+		.cpu = -1,
132
+		.idx = -1,
133
+	};
134
+	struct perf_buffer *pb;
183
135
 	__u32 map_info_len;
184
-	bool do_all = true;
136
+	int err, map_fd;
185
137
 
186
138
 	map_info_len = sizeof(map_info);
187
139
 	map_fd = map_parse_fd_and_info(&argc, &argv, &map_info, &map_info_len);
..
..
@@ -203,7 +155,7 @@
203
155
 			char *endptr;
204
156
 
205
157
 			NEXT_ARG();
206
-			cpu = strtoul(*argv, &endptr, 0);
158
+			ctx.cpu = strtoul(*argv, &endptr, 0);
207
159
 			if (*endptr) {
208
160
 				p_err("can't parse %s as CPU ID", *argv);
209
161
 				goto err_close_map;
..
..
@@ -214,7 +166,7 @@
214
166
 			char *endptr;
215
167
 
216
168
 			NEXT_ARG();
217
-			index = strtoul(*argv, &endptr, 0);
169
+			ctx.idx = strtoul(*argv, &endptr, 0);
218
170
 			if (*endptr) {
219
171
 				p_err("can't parse %s as index", *argv);
220
172
 				goto err_close_map;
..
..
@@ -226,45 +178,32 @@
226
178
 			goto err_close_map;
227
179
 		}
228
180
 
229
-		do_all = false;
181
+		ctx.all_cpus = false;
230
182
 	}
231
183
 
232
-	if (!do_all) {
233
-		if (index == -1 || cpu == -1) {
184
+	if (!ctx.all_cpus) {
185
+		if (ctx.idx == -1 || ctx.cpu == -1) {
234
186
 			p_err("cpu and index must be specified together");
235
187
 			goto err_close_map;
236
188
 		}
237
-
238
-		nfds = 1;
239
189
 	} else {
240
-		nfds = min(get_possible_cpus(), map_info.max_entries);
241
-		cpu = 0;
242
-		index = 0;
190
+		ctx.cpu = 0;
191
+		ctx.idx = 0;
243
192
 	}
244
193
 
245
-	rings = calloc(nfds, sizeof(rings[0]));
246
-	if (!rings)
194
+	opts.attr = &perf_attr;
195
+	opts.event_cb = print_bpf_output;
196
+	opts.ctx = &ctx;
197
+	opts.cpu_cnt = ctx.all_cpus ? 0 : 1;
198
+	opts.cpus = &ctx.cpu;
199
+	opts.map_keys = &ctx.idx;
200
+
201
+	pb = perf_buffer__new_raw(map_fd, MMAP_PAGE_CNT, &opts);
202
+	err = libbpf_get_error(pb);
203
+	if (err) {
204
+		p_err("failed to create perf buffer: %s (%d)",
205
+		      strerror(err), err);
247
206
 		goto err_close_map;
248
-
249
-	pfds = calloc(nfds, sizeof(pfds[0]));
250
-	if (!pfds)
251
-		goto err_free_rings;
252
-
253
-	for (i = 0; i < nfds; i++) {
254
-		rings[i].cpu = cpu + i;
255
-		rings[i].key = index + i;
256
-
257
-		rings[i].fd = bpf_perf_event_open(map_fd, rings[i].key,
258
-						  rings[i].cpu);
259
-		if (rings[i].fd < 0)
260
-			goto err_close_fds_prev;
261
-
262
-		rings[i].mem = perf_event_mmap(rings[i].fd);
263
-		if (!rings[i].mem)
264
-			goto err_close_fds_current;
265
-
266
-		pfds[i].fd = rings[i].fd;
267
-		pfds[i].events = POLLIN;
268
207
 	}
269
208
 
270
209
 	signal(SIGINT, int_exit);
..
..
@@ -275,34 +214,24 @@
275
214
 		jsonw_start_array(json_wtr);
276
215
 
277
216
 	while (!stop) {
278
-		poll(pfds, nfds, 200);
279
-		for (i = 0; i < nfds; i++)
280
-			perf_event_read(&rings[i], &tmp_buf, &tmp_buf_sz);
217
+		err = perf_buffer__poll(pb, 200);
218
+		if (err < 0 && err != -EINTR) {
219
+			p_err("perf buffer polling failed: %s (%d)",
220
+			      strerror(err), err);
221
+			goto err_close_pb;
222
+		}
281
223
 	}
282
-	free(tmp_buf);
283
224
 
284
225
 	if (json_output)
285
226
 		jsonw_end_array(json_wtr);
286
227
 
287
-	for (i = 0; i < nfds; i++) {
288
-		perf_event_unmap(rings[i].mem);
289
-		close(rings[i].fd);
290
-	}
291
-	free(pfds);
292
-	free(rings);
228
+	perf_buffer__free(pb);
293
229
 	close(map_fd);
294
230
 
295
231
 	return 0;
296
232
 
297
-err_close_fds_prev:
298
-	while (i--) {
299
-		perf_event_unmap(rings[i].mem);
300
-err_close_fds_current:
301
-		close(rings[i].fd);
302
-	}
303
-	free(pfds);
304
-err_free_rings:
305
-	free(rings);
233
+err_close_pb:
234
+	perf_buffer__free(pb);
306
235
 err_close_map:
307
236
 	close(map_fd);
308
237
 	return -1;